diff options
678 files changed, 26412 insertions, 9259 deletions
diff --git a/Documentation/devicetree/bindings/net/ieee802154/mcr20a.txt b/Documentation/devicetree/bindings/net/ieee802154/mcr20a.txt new file mode 100644 index 000000000000..2aaef567c5be --- /dev/null +++ b/Documentation/devicetree/bindings/net/ieee802154/mcr20a.txt @@ -0,0 +1,23 @@ +* MCR20A IEEE 802.15.4 * + +Required properties: + - compatible: should be "nxp,mcr20a" + - spi-max-frequency: maximal bus speed, should be set to a frequency + lower than 9000000 depends sync or async operation mode + - reg: the chipselect index + - interrupts: the interrupt generated by the device. Non high-level + can occur deadlocks while handling isr. + +Optional properties: + - rst_b-gpio: GPIO spec for the RST_B pin + +Example: + + mcr20a@0 { + compatible = "nxp,mcr20a"; + spi-max-frequency = <9000000>; + reg = <0>; + interrupts = <17 2>; + interrupt-parent = <&gpio>; + rst_b-gpio = <&gpio 27 1> + }; diff --git a/Documentation/devicetree/bindings/net/sff,sfp.txt b/Documentation/devicetree/bindings/net/sff,sfp.txt index f1c441bedf68..929591d52ed6 100644 --- a/Documentation/devicetree/bindings/net/sff,sfp.txt +++ b/Documentation/devicetree/bindings/net/sff,sfp.txt @@ -33,6 +33,10 @@ Optional Properties: Select (AKA RS1) output gpio signal (SFP+ only), low: low Tx rate, high: high Tx rate. Must not be present for SFF modules +- maximum-power-milliwatt : Maximum module power consumption + Specifies the maximum power consumption allowable by a module in the + slot, in milli-Watts. Presently, modules can be up to 1W, 1.5W or 2W. + Example #1: Direct serdes to SFP connection sfp_eth3: sfp-eth3 { @@ -40,6 +44,7 @@ sfp_eth3: sfp-eth3 { i2c-bus = <&sfp_1g_i2c>; los-gpios = <&cpm_gpio2 22 GPIO_ACTIVE_HIGH>; mod-def0-gpios = <&cpm_gpio2 21 GPIO_ACTIVE_LOW>; + maximum-power-milliwatt = <1000>; pinctrl-names = "default"; pinctrl-0 = <&cpm_sfp_1g_pins &cps_sfp_1g_pins>; tx-disable-gpios = <&cps_gpio1 24 GPIO_ACTIVE_HIGH>; diff --git a/Documentation/devicetree/bindings/net/ti,dp83867.txt b/Documentation/devicetree/bindings/net/ti,dp83867.txt index 02c4353b5cf2..9ef9338aaee1 100644 --- a/Documentation/devicetree/bindings/net/ti,dp83867.txt +++ b/Documentation/devicetree/bindings/net/ti,dp83867.txt @@ -25,6 +25,8 @@ Optional property: software needs to take when this pin is strapped in these modes. See data manual for details. + - ti,clk-output-sel - Muxing option for CLK_OUT pin - see dt-bindings/net/ti-dp83867.h + for applicable values. Note: ti,min-output-impedance and ti,max-output-impedance are mutually exclusive. When both properties are present ti,max-output-impedance diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt index a553d4e4a0fb..783675a730e5 100644 --- a/Documentation/networking/ip-sysctl.txt +++ b/Documentation/networking/ip-sysctl.txt @@ -1363,6 +1363,13 @@ flowlabel_reflect - BOOLEAN FALSE: disabled Default: FALSE +fib_multipath_hash_policy - INTEGER + Controls which hash policy to use for multipath routes. + Default: 0 (Layer 3) + Possible values: + 0 - Layer 3 (source and destination addresses plus flow label) + 1 - Layer 4 (standard 5-tuple) + anycast_src_echo_reply - BOOLEAN Controls the use of anycast addresses as source addresses for ICMPv6 echo reply diff --git a/MAINTAINERS b/MAINTAINERS index 4623caf8d72d..9d632b83c4ce 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -8596,6 +8596,15 @@ S: Maintained F: Documentation/ABI/testing/sysfs-bus-iio-potentiometer-mcp4531 F: drivers/iio/potentiometer/mcp4531.c +MCR20A IEEE-802.15.4 RADIO DRIVER +M: Xue Liu <liuxuenetmail@gmail.com> +L: linux-wpan@vger.kernel.org +W: https://github.com/xueliu/mcr20a-linux +S: Maintained +F: drivers/net/ieee802154/mcr20a.c +F: drivers/net/ieee802154/mcr20a.h +F: Documentation/devicetree/bindings/net/ieee802154/mcr20a.txt + MEASUREMENT COMPUTING CIO-DAC IIO DRIVER M: William Breathitt Gray <vilhelm.gray@gmail.com> L: linux-iio@vger.kernel.org diff --git a/arch/arm/boot/dts/armada-370-rd.dts b/arch/arm/boot/dts/armada-370-rd.dts index 8b2fa9a49967..c28afb242393 100644 --- a/arch/arm/boot/dts/armada-370-rd.dts +++ b/arch/arm/boot/dts/armada-370-rd.dts @@ -56,6 +56,7 @@ /dts-v1/; #include <dt-bindings/input/input.h> +#include <dt-bindings/interrupt-controller/irq.h> #include <dt-bindings/gpio/gpio.h> #include "armada-370.dtsi" @@ -243,6 +244,8 @@ #address-cells = <1>; #size-cells = <0>; reg = <0x10>; + interrupt-controller; + #interrupt-cells = <2>; ports { #address-cells = <1>; @@ -278,6 +281,35 @@ }; }; }; + + mdio { + #address-cells = <1>; + #size-cells = <0>; + + switchphy0: switchphy@0 { + reg = <0>; + interrupt-parent = <&switch>; + interrupts = <0 IRQ_TYPE_LEVEL_HIGH>; + }; + + switchphy1: switchphy@1 { + reg = <1>; + interrupt-parent = <&switch>; + interrupts = <1 IRQ_TYPE_LEVEL_HIGH>; + }; + + switchphy2: switchphy@2 { + reg = <2>; + interrupt-parent = <&switch>; + interrupts = <2 IRQ_TYPE_LEVEL_HIGH>; + }; + + switchphy3: switchphy@3 { + reg = <3>; + interrupt-parent = <&switch>; + interrupts = <3 IRQ_TYPE_LEVEL_HIGH>; + }; + }; }; }; diff --git a/arch/m68k/mac/config.c b/arch/m68k/mac/config.c index d3d435248a24..c73eb8209555 100644 --- a/arch/m68k/mac/config.c +++ b/arch/m68k/mac/config.c @@ -1088,6 +1088,10 @@ int __init mac_platform_init(void) macintosh_config->expansion_type == MAC_EXP_PDS_COMM) platform_device_register_simple("macsonic", -1, NULL, 0); + if (macintosh_config->expansion_type == MAC_EXP_PDS || + macintosh_config->expansion_type == MAC_EXP_PDS_COMM) + platform_device_register_simple("mac89x0", -1, NULL, 0); + if (macintosh_config->ether_type == MAC_ETHER_MACE) platform_device_register_simple("macmace", -1, NULL, 0); diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 45e4eb5bcbb2..eb661fff94d7 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -11,10 +11,10 @@ #include <linux/netdevice.h> #include <linux/filter.h> #include <linux/if_vlan.h> -#include <asm/cacheflush.h> +#include <linux/bpf.h> + #include <asm/set_memory.h> #include <asm/nospec-branch.h> -#include <linux/bpf.h> /* * assembly code in arch/x86/net/bpf_jit.S @@ -61,7 +61,12 @@ static bool is_imm8(int value) static bool is_simm32(s64 value) { - return value == (s64) (s32) value; + return value == (s64)(s32)value; +} + +static bool is_uimm32(u64 value) +{ + return value == (u64)(u32)value; } /* mov dst, src */ @@ -98,16 +103,6 @@ static int bpf_size_to_x86_bytes(int bpf_size) #define X86_JLE 0x7E #define X86_JG 0x7F -static void bpf_flush_icache(void *start, void *end) -{ - mm_segment_t old_fs = get_fs(); - - set_fs(KERNEL_DS); - smp_wmb(); - flush_icache_range((unsigned long)start, (unsigned long)end); - set_fs(old_fs); -} - #define CHOOSE_LOAD_FUNC(K, func) \ ((int)K < 0 ? ((int)K >= SKF_LL_OFF ? func##_negative_offset : func) : func##_positive_offset) @@ -212,7 +207,7 @@ struct jit_context { /* emit x64 prologue code for BPF program and check it's size. * bpf_tail_call helper will skip it while jumping into another program */ -static void emit_prologue(u8 **pprog, u32 stack_depth) +static void emit_prologue(u8 **pprog, u32 stack_depth, bool ebpf_from_cbpf) { u8 *prog = *pprog; int cnt = 0; @@ -247,18 +242,21 @@ static void emit_prologue(u8 **pprog, u32 stack_depth) /* mov qword ptr [rbp+24],r15 */ EMIT4(0x4C, 0x89, 0x7D, 24); - /* Clear the tail call counter (tail_call_cnt): for eBPF tail calls - * we need to reset the counter to 0. It's done in two instructions, - * resetting rax register to 0 (xor on eax gets 0 extended), and - * moving it to the counter location. - */ + if (!ebpf_from_cbpf) { + /* Clear the tail call counter (tail_call_cnt): for eBPF tail + * calls we need to reset the counter to 0. It's done in two + * instructions, resetting rax register to 0, and moving it + * to the counter location. + */ - /* xor eax, eax */ - EMIT2(0x31, 0xc0); - /* mov qword ptr [rbp+32], rax */ - EMIT4(0x48, 0x89, 0x45, 32); + /* xor eax, eax */ + EMIT2(0x31, 0xc0); + /* mov qword ptr [rbp+32], rax */ + EMIT4(0x48, 0x89, 0x45, 32); + + BUILD_BUG_ON(cnt != PROLOGUE_SIZE); + } - BUILD_BUG_ON(cnt != PROLOGUE_SIZE); *pprog = prog; } @@ -356,6 +354,86 @@ static void emit_load_skb_data_hlen(u8 **pprog) *pprog = prog; } +static void emit_mov_imm32(u8 **pprog, bool sign_propagate, + u32 dst_reg, const u32 imm32) +{ + u8 *prog = *pprog; + u8 b1, b2, b3; + int cnt = 0; + + /* optimization: if imm32 is positive, use 'mov %eax, imm32' + * (which zero-extends imm32) to save 2 bytes. + */ + if (sign_propagate && (s32)imm32 < 0) { + /* 'mov %rax, imm32' sign extends imm32 */ + b1 = add_1mod(0x48, dst_reg); + b2 = 0xC7; + b3 = 0xC0; + EMIT3_off32(b1, b2, add_1reg(b3, dst_reg), imm32); + goto done; + } + + /* optimization: if imm32 is zero, use 'xor %eax, %eax' + * to save 3 bytes. + */ + if (imm32 == 0) { + if (is_ereg(dst_reg)) + EMIT1(add_2mod(0x40, dst_reg, dst_reg)); + b2 = 0x31; /* xor */ + b3 = 0xC0; + EMIT2(b2, add_2reg(b3, dst_reg, dst_reg)); + goto done; + } + + /* mov %eax, imm32 */ + if (is_ereg(dst_reg)) + EMIT1(add_1mod(0x40, dst_reg)); + EMIT1_off32(add_1reg(0xB8, dst_reg), imm32); +done: + *pprog = prog; +} + +static void emit_mov_imm64(u8 **pprog, u32 dst_reg, + const u32 imm32_hi, const u32 imm32_lo) +{ + u8 *prog = *pprog; + int cnt = 0; + + if (is_uimm32(((u64)imm32_hi << 32) | (u32)imm32_lo)) { + /* For emitting plain u32, where sign bit must not be + * propagated LLVM tends to load imm64 over mov32 + * directly, so save couple of bytes by just doing + * 'mov %eax, imm32' instead. + */ + emit_mov_imm32(&prog, false, dst_reg, imm32_lo); + } else { + /* movabsq %rax, imm64 */ + EMIT2(add_1mod(0x48, dst_reg), add_1reg(0xB8, dst_reg)); + EMIT(imm32_lo, 4); + EMIT(imm32_hi, 4); + } + + *pprog = prog; +} + +static void emit_mov_reg(u8 **pprog, bool is64, u32 dst_reg, u32 src_reg) +{ + u8 *prog = *pprog; + int cnt = 0; + + if (is64) { + /* mov dst, src */ + EMIT_mov(dst_reg, src_reg); + } else { + /* mov32 dst, src */ + if (is_ereg(dst_reg) || is_ereg(src_reg)) + EMIT1(add_2mod(0x40, dst_reg, src_reg)); + EMIT2(0x89, add_2reg(0xC0, dst_reg, src_reg)); + } + + *pprog = prog; +} + static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, int oldproglen, struct jit_context *ctx) { @@ -369,7 +447,8 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, int proglen = 0; u8 *prog = temp; - emit_prologue(&prog, bpf_prog->aux->stack_depth); + emit_prologue(&prog, bpf_prog->aux->stack_depth, + bpf_prog_was_classic(bpf_prog)); if (seen_ld_abs) emit_load_skb_data_hlen(&prog); @@ -378,7 +457,7 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, const s32 imm32 = insn->imm; u32 dst_reg = insn->dst_reg; u32 src_reg = insn->src_reg; - u8 b1 = 0, b2 = 0, b3 = 0; + u8 b2 = 0, b3 = 0; s64 jmp_offset; u8 jmp_cond; bool reload_skb_data; @@ -414,16 +493,11 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, EMIT2(b2, add_2reg(0xC0, dst_reg, src_reg)); break; - /* mov dst, src */ case BPF_ALU64 | BPF_MOV | BPF_X: - EMIT_mov(dst_reg, src_reg); - break; - - /* mov32 dst, src */ case BPF_ALU | BPF_MOV | BPF_X: - if (is_ereg(dst_reg) || is_ereg(src_reg)) - EMIT1(add_2mod(0x40, dst_reg, src_reg)); - EMIT2(0x89, add_2reg(0xC0, dst_reg, src_reg)); + emit_mov_reg(&prog, + BPF_CLASS(insn->code) == BPF_ALU64, + dst_reg, src_reg); break; /* neg dst */ @@ -486,58 +560,13 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, break; case BPF_ALU64 | BPF_MOV | BPF_K: - /* optimization: if imm32 is positive, - * use 'mov eax, imm32' (which zero-extends imm32) - * to save 2 bytes - */ - if (imm32 < 0) { - /* 'mov rax, imm32' sign extends imm32 */ - b1 = add_1mod(0x48, dst_reg); - b2 = 0xC7; - b3 = 0xC0; - EMIT3_off32(b1, b2, add_1reg(b3, dst_reg), imm32); - break; - } - case BPF_ALU | BPF_MOV | BPF_K: - /* optimization: if imm32 is zero, use 'xor <dst>,<dst>' - * to save 3 bytes. - */ - if (imm32 == 0) { - if (is_ereg(dst_reg)) - EMIT1(add_2mod(0x40, dst_reg, dst_reg)); - b2 = 0x31; /* xor */ - b3 = 0xC0; - EMIT2(b2, add_2reg(b3, dst_reg, dst_reg)); - break; - } - - /* mov %eax, imm32 */ - if (is_ereg(dst_reg)) - EMIT1(add_1mod(0x40, dst_reg)); - EMIT1_off32(add_1reg(0xB8, dst_reg), imm32); + emit_mov_imm32(&prog, BPF_CLASS(insn->code) == BPF_ALU64, + dst_reg, imm32); break; case BPF_LD | BPF_IMM | BPF_DW: - /* optimization: if imm64 is zero, use 'xor <dst>,<dst>' - * to save 7 bytes. - */ - if (insn[0].imm == 0 && insn[1].imm == 0) { - b1 = add_2mod(0x48, dst_reg, dst_reg); - b2 = 0x31; /* xor */ - b3 = 0xC0; - EMIT3(b1, b2, add_2reg(b3, dst_reg, dst_reg)); - - insn++; - i++; - break; - } - - /* movabsq %rax, imm64 */ - EMIT2(add_1mod(0x48, dst_reg), add_1reg(0xB8, dst_reg)); - EMIT(insn[0].imm, 4); - EMIT(insn[1].imm, 4); - + emit_mov_imm64(&prog, dst_reg, insn[1].imm, insn[0].imm); insn++; i++; break; @@ -594,36 +623,38 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, case BPF_ALU | BPF_MUL | BPF_X: case BPF_ALU64 | BPF_MUL | BPF_K: case BPF_ALU64 | BPF_MUL | BPF_X: - EMIT1(0x50); /* push rax */ - EMIT1(0x52); /* push rdx */ + { + bool is64 = BPF_CLASS(insn->code) == BPF_ALU64; + + if (dst_reg != BPF_REG_0) + EMIT1(0x50); /* push rax */ + if (dst_reg != BPF_REG_3) + EMIT1(0x52); /* push rdx */ /* mov r11, dst_reg */ EMIT_mov(AUX_REG, dst_reg); if (BPF_SRC(insn->code) == BPF_X) - /* mov rax, src_reg */ - EMIT_mov(BPF_REG_0, src_reg); + emit_mov_reg(&prog, is64, BPF_REG_0, src_reg); else - /* mov rax, imm32 */ - EMIT3_off32(0x48, 0xC7, 0xC0, imm32); + emit_mov_imm32(&prog, is64, BPF_REG_0, imm32); - if (BPF_CLASS(insn->code) == BPF_ALU64) + if (is64) EMIT1(add_1mod(0x48, AUX_REG)); else if (is_ereg(AUX_REG)) EMIT1(add_1mod(0x40, AUX_REG)); /* mul(q) r11 */ EMIT2(0xF7, add_1reg(0xE0, AUX_REG)); - /* mov r11, rax */ - EMIT_mov(AUX_REG, BPF_REG_0); - - EMIT1(0x5A); /* pop rdx */ - EMIT1(0x58); /* pop rax */ - - /* mov dst_reg, r11 */ - EMIT_mov(dst_reg, AUX_REG); + if (dst_reg != BPF_REG_3) + EMIT1(0x5A); /* pop rdx */ + if (dst_reg != BPF_REG_0) { + /* mov dst_reg, rax */ + EMIT_mov(dst_reg, BPF_REG_0); + EMIT1(0x58); /* pop rax */ + } break; - + } /* shifts */ case BPF_ALU | BPF_LSH | BPF_K: case BPF_ALU | BPF_RSH | BPF_K: @@ -641,7 +672,11 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, case BPF_RSH: b3 = 0xE8; break; case BPF_ARSH: b3 = 0xF8; break; } - EMIT3(0xC1, add_1reg(b3, dst_reg), imm32); + + if (imm32 == 1) + EMIT2(0xD1, add_1reg(b3, dst_reg)); + else + EMIT3(0xC1, add_1reg(b3, dst_reg), imm32); break; case BPF_ALU | BPF_LSH | BPF_X: @@ -1221,7 +1256,6 @@ skip_init_addrs: bpf_jit_dump(prog->len, proglen, pass + 1, image); if (image) { - bpf_flush_icache(header, image + proglen); if (!prog->is_func || extra_pass) { bpf_jit_binary_lock_ro(header); } else { diff --git a/drivers/atm/idt77252.c b/drivers/atm/idt77252.c index 0277f36be85b..6e737142ceaa 100644 --- a/drivers/atm/idt77252.c +++ b/drivers/atm/idt77252.c @@ -3173,14 +3173,10 @@ static void init_sram(struct idt77252_dev *card) (u32) 0xffffffff); } - writel((SAR_FBQ0_LOW << 28) | 0x00000000 | 0x00000000 | - (SAR_FB_SIZE_0 / 48), SAR_REG_FBQS0); - writel((SAR_FBQ1_LOW << 28) | 0x00000000 | 0x00000000 | - (SAR_FB_SIZE_1 / 48), SAR_REG_FBQS1); - writel((SAR_FBQ2_LOW << 28) | 0x00000000 | 0x00000000 | - (SAR_FB_SIZE_2 / 48), SAR_REG_FBQS2); - writel((SAR_FBQ3_LOW << 28) | 0x00000000 | 0x00000000 | - (SAR_FB_SIZE_3 / 48), SAR_REG_FBQS3); + writel((SAR_FBQ0_LOW << 28) | (SAR_FB_SIZE_0 / 48), SAR_REG_FBQS0); + writel((SAR_FBQ1_LOW << 28) | (SAR_FB_SIZE_1 / 48), SAR_REG_FBQS1); + writel((SAR_FBQ2_LOW << 28) | (SAR_FB_SIZE_2 / 48), SAR_REG_FBQS2); + writel((SAR_FBQ3_LOW << 28) | (SAR_FB_SIZE_3 / 48), SAR_REG_FBQS3); /* Initialize rate table */ for (i = 0; i < 256; i++) { diff --git a/drivers/bluetooth/ath3k.c b/drivers/bluetooth/ath3k.c index 204afe66de92..3d7a5c149af3 100644 --- a/drivers/bluetooth/ath3k.c +++ b/drivers/bluetooth/ath3k.c @@ -203,6 +203,12 @@ static const struct usb_device_id ath3k_blist_tbl[] = { { } /* Terminating entry */ }; +static inline void ath3k_log_failed_loading(int err, int len, int size) +{ + BT_ERR("Error in firmware loading err = %d, len = %d, size = %d", + err, len, size); +} + #define USB_REQ_DFU_DNLOAD 1 #define BULK_SIZE 4096 #define FW_HDR_SIZE 20 @@ -227,15 +233,16 @@ static int ath3k_load_firmware(struct usb_device *udev, return -ENOMEM; } - memcpy(send_buf, firmware->data, 20); + memcpy(send_buf, firmware->data, FW_HDR_SIZE); err = usb_control_msg(udev, pipe, USB_REQ_DFU_DNLOAD, USB_TYPE_VENDOR, - 0, 0, send_buf, 20, USB_CTRL_SET_TIMEOUT); + 0, 0, send_buf, FW_HDR_SIZE, + USB_CTRL_SET_TIMEOUT); if (err < 0) { BT_ERR("Can't change to loading configuration err"); goto error; } - sent += 20; - count -= 20; + sent += FW_HDR_SIZE; + count -= FW_HDR_SIZE; pipe = usb_sndbulkpipe(udev, 0x02); @@ -250,8 +257,7 @@ static int ath3k_load_firmware(struct usb_device *udev, &len, 3000); if (err || (len != size)) { - BT_ERR("Error in firmware loading err = %d," - "len = %d, size = %d", err, len, size); + ath3k_log_failed_loading(err, len, size); goto error; } @@ -350,8 +356,7 @@ static int ath3k_load_fwfile(struct usb_device *udev, err = usb_bulk_msg(udev, pipe, send_buf, size, &len, 3000); if (err || (len != size)) { - BT_ERR("Error in firmware loading err = %d," - "len = %d, size = %d", err, len, size); + ath3k_log_failed_loading(err, len, size); kfree(send_buf); return err; } @@ -398,7 +403,7 @@ static int ath3k_set_normal_mode(struct usb_device *udev) static int ath3k_load_patch(struct usb_device *udev) { unsigned char fw_state; - char filename[ATH3K_NAME_LEN] = {0}; + char filename[ATH3K_NAME_LEN]; const struct firmware *firmware; struct ath3k_version fw_version; __u32 pt_rom_version, pt_build_version; @@ -451,7 +456,7 @@ static int ath3k_load_patch(struct usb_device *udev) static int ath3k_load_syscfg(struct usb_device *udev) { unsigned char fw_state; - char filename[ATH3K_NAME_LEN] = {0}; + char filename[ATH3K_NAME_LEN]; const struct firmware *firmware; struct ath3k_version fw_version; int clk_value, ret; @@ -522,7 +527,6 @@ static int ath3k_probe(struct usb_interface *intf, /* load patch and sysconfig files for AR3012 */ if (id->driver_info & BTUSB_ATH3012) { - /* New firmware with patch and sysconfig files already loaded */ if (le16_to_cpu(udev->descriptor.bcdDevice) > 0x0001) return -ENODEV; @@ -565,7 +569,7 @@ static int ath3k_probe(struct usb_interface *intf, static void ath3k_disconnect(struct usb_interface *intf) { - BT_DBG("ath3k_disconnect intf %p", intf); + BT_DBG("%s intf %p", __func__, intf); } static struct usb_driver ath3k_driver = { diff --git a/drivers/bluetooth/btmrvl_main.c b/drivers/bluetooth/btmrvl_main.c index b280d466f05b..f6c694a1b9b0 100644 --- a/drivers/bluetooth/btmrvl_main.c +++ b/drivers/bluetooth/btmrvl_main.c @@ -183,7 +183,7 @@ static int btmrvl_send_sync_cmd(struct btmrvl_private *priv, u16 opcode, return -EFAULT; } - skb = bt_skb_alloc(HCI_COMMAND_HDR_SIZE + len, GFP_ATOMIC); + skb = bt_skb_alloc(HCI_COMMAND_HDR_SIZE + len, GFP_KERNEL); if (!skb) { BT_ERR("No free skb"); return -ENOMEM; diff --git a/drivers/bluetooth/btrtl.c b/drivers/bluetooth/btrtl.c index 6e2ad748abba..437f080deaab 100644 --- a/drivers/bluetooth/btrtl.c +++ b/drivers/bluetooth/btrtl.c @@ -35,6 +35,60 @@ #define RTL_ROM_LMP_8761A 0x8761 #define RTL_ROM_LMP_8822B 0x8822 +#define IC_MATCH_FL_LMPSUBV (1 << 0) +#define IC_MATCH_FL_HCIREV (1 << 1) +#define IC_INFO(lmps, hcir) \ + .match_flags = IC_MATCH_FL_LMPSUBV | IC_MATCH_FL_HCIREV, \ + .lmp_subver = (lmps), \ + .hci_rev = (hcir) + +struct id_table { + __u16 match_flags; + __u16 lmp_subver; + __u16 hci_rev; + bool config_needed; + char *fw_name; + char *cfg_name; +}; + +static const struct id_table ic_id_table[] = { + /* 8723B */ + { IC_INFO(RTL_ROM_LMP_8723B, 0xb), + .config_needed = false, + .fw_name = "rtl_bt/rtl8723b_fw.bin", + .cfg_name = "rtl_bt/rtl8723b_config.bin" }, + + /* 8723D */ + { IC_INFO(RTL_ROM_LMP_8723B, 0xd), + .config_needed = true, + .fw_name = "rtl_bt/rtl8723d_fw.bin", + .cfg_name = "rtl_bt/rtl8723d_config.bin" }, + + /* 8821A */ + { IC_INFO(RTL_ROM_LMP_8821A, 0xa), + .config_needed = false, + .fw_name = "rtl_bt/rtl8821a_fw.bin", + .cfg_name = "rtl_bt/rtl8821a_config.bin" }, + + /* 8821C */ + { IC_INFO(RTL_ROM_LMP_8821A, 0xc), + .config_needed = false, + .fw_name = "rtl_bt/rtl8821c_fw.bin", + .cfg_name = "rtl_bt/rtl8821c_config.bin" }, + + /* 8761A */ + { IC_MATCH_FL_LMPSUBV, RTL_ROM_LMP_8761A, 0x0, + .config_needed = false, + .fw_name = "rtl_bt/rtl8761a_fw.bin", + .cfg_name = "rtl_bt/rtl8761a_config.bin" }, + + /* 8822B */ + { IC_INFO(RTL_ROM_LMP_8822B, 0xb), + .config_needed = true, + .fw_name = "rtl_bt/rtl8822b_fw.bin", + .cfg_name = "rtl_bt/rtl8822b_config.bin" }, + }; + static int rtl_read_rom_version(struct hci_dev *hdev, u8 *version) { struct rtl_rom_version_evt *rom_version; @@ -64,9 +118,9 @@ static int rtl_read_rom_version(struct hci_dev *hdev, u8 *version) return 0; } -static int rtl8723b_parse_firmware(struct hci_dev *hdev, u16 lmp_subver, - const struct firmware *fw, - unsigned char **_buf) +static int rtlbt_parse_firmware(struct hci_dev *hdev, u16 lmp_subver, + const struct firmware *fw, + unsigned char **_buf) { const u8 extension_sig[] = { 0x51, 0x04, 0xfd, 0x77 }; struct rtl_epatch_header *epatch_info; @@ -88,6 +142,8 @@ static int rtl8723b_parse_firmware(struct hci_dev *hdev, u16 lmp_subver, { RTL_ROM_LMP_8821A, 2 }, { RTL_ROM_LMP_8761A, 3 }, { RTL_ROM_LMP_8822B, 8 }, + { RTL_ROM_LMP_8723B, 9 }, /* 8723D */ + { RTL_ROM_LMP_8821A, 10 }, /* 8821C */ }; ret = rtl_read_rom_version(hdev, &rom_version); @@ -320,8 +376,8 @@ out: return ret; } -static int btrtl_setup_rtl8723b(struct hci_dev *hdev, u16 lmp_subver, - const char *fw_name) +static int btrtl_setup_rtl8723b(struct hci_dev *hdev, u16 hci_rev, + u16 lmp_subver) { unsigned char *fw_data = NULL; const struct firmware *fw; @@ -330,39 +386,40 @@ static int btrtl_setup_rtl8723b(struct hci_dev *hdev, u16 lmp_subver, u8 *cfg_buff = NULL; u8 *tbuff; char *cfg_name = NULL; - bool config_needed = false; + char *fw_name = NULL; + int i; + + for (i = 0; i < ARRAY_SIZE(ic_id_table); i++) { + if ((ic_id_table[i].match_flags & IC_MATCH_FL_LMPSUBV) && + (ic_id_table[i].lmp_subver != lmp_subver)) + continue; + if ((ic_id_table[i].match_flags & IC_MATCH_FL_HCIREV) && + (ic_id_table[i].hci_rev != hci_rev)) + continue; - switch (lmp_subver) { - case RTL_ROM_LMP_8723B: - cfg_name = "rtl_bt/rtl8723b_config.bin"; - break; - case RTL_ROM_LMP_8821A: - cfg_name = "rtl_bt/rtl8821a_config.bin"; - break; - case RTL_ROM_LMP_8761A: - cfg_name = "rtl_bt/rtl8761a_config.bin"; - break; - case RTL_ROM_LMP_8822B: - cfg_name = "rtl_bt/rtl8822b_config.bin"; - config_needed = true; - break; - default: - BT_ERR("%s: rtl: no config according to lmp_subver %04x", - hdev->name, lmp_subver); break; } + if (i >= ARRAY_SIZE(ic_id_table)) { + BT_ERR("%s: unknown IC info, lmp subver %04x, hci rev %04x", + hdev->name, lmp_subver, hci_rev); + return -EINVAL; + } + + cfg_name = ic_id_table[i].cfg_name; + if (cfg_name) { cfg_sz = rtl_load_config(hdev, cfg_name, &cfg_buff); if (cfg_sz < 0) { cfg_sz = 0; - if (config_needed) + if (ic_id_table[i].config_needed) BT_ERR("Necessary config file %s not found\n", cfg_name); } } else cfg_sz = 0; + fw_name = ic_id_table[i].fw_name; bt_dev_info(hdev, "rtl: loading %s", fw_name); ret = request_firmware(&fw, fw_name, &hdev->dev); if (ret < 0) { @@ -370,7 +427,7 @@ static int btrtl_setup_rtl8723b(struct hci_dev *hdev, u16 lmp_subver, goto err_req_fw; } - ret = rtl8723b_parse_firmware(hdev, lmp_subver, fw, &fw_data); + ret = rtlbt_parse_firmware(hdev, lmp_subver, fw, &fw_data); if (ret < 0) goto out; @@ -429,7 +486,7 @@ int btrtl_setup_realtek(struct hci_dev *hdev) { struct sk_buff *skb; struct hci_rp_read_local_version *resp; - u16 lmp_subver; + u16 hci_rev, lmp_subver; skb = btrtl_read_local_version(hdev); if (IS_ERR(skb)) @@ -441,6 +498,7 @@ int btrtl_setup_realtek(struct hci_dev *hdev) resp->hci_ver, resp->hci_rev, resp->lmp_ver, resp->lmp_subver); + hci_rev = le16_to_cpu(resp->hci_rev); lmp_subver = le16_to_cpu(resp->lmp_subver); kfree_skb(skb); @@ -455,17 +513,10 @@ int btrtl_setup_realtek(struct hci_dev *hdev) case RTL_ROM_LMP_3499: return btrtl_setup_rtl8723a(hdev); case RTL_ROM_LMP_8723B: - return btrtl_setup_rtl8723b(hdev, lmp_subver, - "rtl_bt/rtl8723b_fw.bin"); case RTL_ROM_LMP_8821A: - return btrtl_setup_rtl8723b(hdev, lmp_subver, - "rtl_bt/rtl8821a_fw.bin"); case RTL_ROM_LMP_8761A: - return btrtl_setup_rtl8723b(hdev, lmp_subver, - "rtl_bt/rtl8761a_fw.bin"); case RTL_ROM_LMP_8822B: - return btrtl_setup_rtl8723b(hdev, lmp_subver, - "rtl_bt/rtl8822b_fw.bin"); + return btrtl_setup_rtl8723b(hdev, hci_rev, lmp_subver); default: bt_dev_info(hdev, "rtl: assuming no firmware upload needed"); return 0; diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c index 60bf04b8f103..fa4ce83893bb 100644 --- a/drivers/bluetooth/btusb.c +++ b/drivers/bluetooth/btusb.c @@ -340,6 +340,7 @@ static const struct usb_device_id blacklist_table[] = { /* Intel Bluetooth devices */ { USB_DEVICE(0x8087, 0x0025), .driver_info = BTUSB_INTEL_NEW }, + { USB_DEVICE(0x8087, 0x0026), .driver_info = BTUSB_INTEL_NEW }, { USB_DEVICE(0x8087, 0x07da), .driver_info = BTUSB_CSR }, { USB_DEVICE(0x8087, 0x07dc), .driver_info = BTUSB_INTEL }, { USB_DEVICE(0x8087, 0x0a2a), .driver_info = BTUSB_INTEL }, @@ -374,6 +375,9 @@ static const struct usb_device_id blacklist_table[] = { { USB_DEVICE(0x13d3, 0x3461), .driver_info = BTUSB_REALTEK }, { USB_DEVICE(0x13d3, 0x3462), .driver_info = BTUSB_REALTEK }, + /* Additional Realtek 8822BE Bluetooth devices */ + { USB_DEVICE(0x0b05, 0x185c), .driver_info = BTUSB_REALTEK }, + /* Silicon Wave based devices */ { USB_DEVICE(0x0c10, 0x0000), .driver_info = BTUSB_SWAVE }, @@ -2073,6 +2077,8 @@ static int btusb_setup_intel_new(struct hci_dev *hdev) case 0x0c: /* WsP */ case 0x11: /* JfP */ case 0x12: /* ThP */ + case 0x13: /* HrP */ + case 0x14: /* QnJ, IcP */ break; default: BT_ERR("%s: Unsupported Intel hardware variant (%u)", @@ -2165,6 +2171,8 @@ static int btusb_setup_intel_new(struct hci_dev *hdev) break; case 0x11: /* JfP */ case 0x12: /* ThP */ + case 0x13: /* HrP */ + case 0x14: /* QnJ, IcP */ snprintf(fwname, sizeof(fwname), "intel/ibt-%u-%u-%u.sfi", le16_to_cpu(ver.hw_variant), le16_to_cpu(ver.hw_revision), @@ -2196,6 +2204,8 @@ static int btusb_setup_intel_new(struct hci_dev *hdev) break; case 0x11: /* JfP */ case 0x12: /* ThP */ + case 0x13: /* HrP */ + case 0x14: /* QnJ, IcP */ snprintf(fwname, sizeof(fwname), "intel/ibt-%u-%u-%u.ddc", le16_to_cpu(ver.hw_variant), le16_to_cpu(ver.hw_revision), diff --git a/drivers/bluetooth/hci_ath.c b/drivers/bluetooth/hci_ath.c index 14ae7ee88acb..d568fbd94d6c 100644 --- a/drivers/bluetooth/hci_ath.c +++ b/drivers/bluetooth/hci_ath.c @@ -71,12 +71,12 @@ static int ath_wakeup_ar3k(struct tty_struct *tty) /* Clear RTS first */ tty->driver->ops->tiocmget(tty); tty->driver->ops->tiocmset(tty, 0x00, TIOCM_RTS); - mdelay(20); + msleep(20); /* Set RTS, wake up board */ tty->driver->ops->tiocmget(tty); tty->driver->ops->tiocmset(tty, TIOCM_RTS, 0x00); - mdelay(20); + msleep(20); status = tty->driver->ops->tiocmget(tty); return status; diff --git a/drivers/bluetooth/hci_ll.c b/drivers/bluetooth/hci_ll.c index 1b4417a623a4..2f30dcad96bd 100644 --- a/drivers/bluetooth/hci_ll.c +++ b/drivers/bluetooth/hci_ll.c @@ -650,7 +650,7 @@ static int download_firmware(struct ll_device *lldev) break; case ACTION_DELAY: /* sleep */ bt_dev_info(lldev->hu.hdev, "sleep command in scr"); - mdelay(((struct bts_action_delay *)action_ptr)->msec); + msleep(((struct bts_action_delay *)action_ptr)->msec); break; } len -= (sizeof(struct bts_action) + diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c index e66963ca58bd..915bbd867b61 100644 --- a/drivers/infiniband/core/cma.c +++ b/drivers/infiniband/core/cma.c @@ -1334,7 +1334,7 @@ static bool validate_ipv6_net_dev(struct net_device *net_dev, IPV6_ADDR_LINKLOCAL; struct rt6_info *rt = rt6_lookup(dev_net(net_dev), &dst_addr->sin6_addr, &src_addr->sin6_addr, net_dev->ifindex, - strict); + NULL, strict); bool ret; if (!rt) @@ -4549,6 +4549,7 @@ static struct pernet_operations cma_pernet_operations = { .exit = cma_exit_net, .id = &cma_pernet_id, .size = sizeof(struct cma_pernet), + .async = true, }; static int __init cma_init(void) diff --git a/drivers/infiniband/hw/mlx5/Makefile b/drivers/infiniband/hw/mlx5/Makefile index bc6299697dda..d42b922bede8 100644 --- a/drivers/infiniband/hw/mlx5/Makefile +++ b/drivers/infiniband/hw/mlx5/Makefile @@ -2,3 +2,4 @@ obj-$(CONFIG_MLX5_INFINIBAND) += mlx5_ib.o mlx5_ib-y := main.o cq.o doorbell.o qp.o mem.o srq.o mr.o ah.o mad.o gsi.o ib_virt.o cmd.o cong.o mlx5_ib-$(CONFIG_INFINIBAND_ON_DEMAND_PAGING) += odp.o +mlx5_ib-$(CONFIG_MLX5_ESWITCH) += ib_rep.o diff --git a/drivers/infiniband/hw/mlx5/cq.c b/drivers/infiniband/hw/mlx5/cq.c index 5b974fb97611..c4c7b82f4ac1 100644 --- a/drivers/infiniband/hw/mlx5/cq.c +++ b/drivers/infiniband/hw/mlx5/cq.c @@ -64,14 +64,9 @@ static void mlx5_ib_cq_event(struct mlx5_core_cq *mcq, enum mlx5_event type) } } -static void *get_cqe_from_buf(struct mlx5_ib_cq_buf *buf, int n, int size) -{ - return mlx5_buf_offset(&buf->buf, n * size); -} - static void *get_cqe(struct mlx5_ib_cq *cq, int n) { - return get_cqe_from_buf(&cq->buf, n, cq->mcq.cqe_sz); + return mlx5_frag_buf_get_wqe(&cq->buf.fbc, n); } static u8 sw_ownership_bit(int n, int nent) @@ -403,7 +398,7 @@ static void handle_atomics(struct mlx5_ib_qp *qp, struct mlx5_cqe64 *cqe64, static void free_cq_buf(struct mlx5_ib_dev *dev, struct mlx5_ib_cq_buf *buf) { - mlx5_buf_free(dev->mdev, &buf->buf); + mlx5_frag_buf_free(dev->mdev, &buf->fbc.frag_buf); } static void get_sig_err_item(struct mlx5_sig_err_cqe *cqe, @@ -724,12 +719,25 @@ int mlx5_ib_arm_cq(struct ib_cq *ibcq, enum ib_cq_notify_flags flags) return ret; } -static int alloc_cq_buf(struct mlx5_ib_dev *dev, struct mlx5_ib_cq_buf *buf, - int nent, int cqe_size) +static int alloc_cq_frag_buf(struct mlx5_ib_dev *dev, + struct mlx5_ib_cq_buf *buf, + int nent, + int cqe_size) { + struct mlx5_frag_buf_ctrl *c = &buf->fbc; + struct mlx5_frag_buf *frag_buf = &c->frag_buf; + u32 cqc_buff[MLX5_ST_SZ_DW(cqc)] = {0}; int err; - err = mlx5_buf_alloc(dev->mdev, nent * cqe_size, &buf->buf); + MLX5_SET(cqc, cqc_buff, log_cq_size, ilog2(cqe_size)); + MLX5_SET(cqc, cqc_buff, cqe_sz, (cqe_size == 128) ? 1 : 0); + + mlx5_core_init_cq_frag_buf(&buf->fbc, cqc_buff); + + err = mlx5_frag_buf_alloc_node(dev->mdev, + nent * cqe_size, + frag_buf, + dev->mdev->priv.numa_node); if (err) return err; @@ -862,14 +870,15 @@ static void destroy_cq_user(struct mlx5_ib_cq *cq, struct ib_ucontext *context) ib_umem_release(cq->buf.umem); } -static void init_cq_buf(struct mlx5_ib_cq *cq, struct mlx5_ib_cq_buf *buf) +static void init_cq_frag_buf(struct mlx5_ib_cq *cq, + struct mlx5_ib_cq_buf *buf) { int i; void *cqe; struct mlx5_cqe64 *cqe64; for (i = 0; i < buf->nent; i++) { - cqe = get_cqe_from_buf(buf, i, buf->cqe_size); + cqe = get_cqe(cq, i); cqe64 = buf->cqe_size == 64 ? cqe : cqe + 64; cqe64->op_own = MLX5_CQE_INVALID << 4; } @@ -891,14 +900,15 @@ static int create_cq_kernel(struct mlx5_ib_dev *dev, struct mlx5_ib_cq *cq, cq->mcq.arm_db = cq->db.db + 1; cq->mcq.cqe_sz = cqe_size; - err = alloc_cq_buf(dev, &cq->buf, entries, cqe_size); + err = alloc_cq_frag_buf(dev, &cq->buf, entries, cqe_size); if (err) goto err_db; - init_cq_buf(cq, &cq->buf); + init_cq_frag_buf(cq, &cq->buf); *inlen = MLX5_ST_SZ_BYTES(create_cq_in) + - MLX5_FLD_SZ_BYTES(create_cq_in, pas[0]) * cq->buf.buf.npages; + MLX5_FLD_SZ_BYTES(create_cq_in, pas[0]) * + cq->buf.fbc.frag_buf.npages; *cqb = kvzalloc(*inlen, GFP_KERNEL); if (!*cqb) { err = -ENOMEM; @@ -906,11 +916,12 @@ static int create_cq_kernel(struct mlx5_ib_dev *dev, struct mlx5_ib_cq *cq, } pas = (__be64 *)MLX5_ADDR_OF(create_cq_in, *cqb, pas); - mlx5_fill_page_array(&cq->buf.buf, pas); + mlx5_fill_page_frag_array(&cq->buf.fbc.frag_buf, pas); cqc = MLX5_ADDR_OF(create_cq_in, *cqb, cq_context); MLX5_SET(cqc, cqc, log_page_size, - cq->buf.buf.page_shift - MLX5_ADAPTER_PAGE_SHIFT); + cq->buf.fbc.frag_buf.page_shift - + MLX5_ADAPTER_PAGE_SHIFT); *index = dev->mdev->priv.uar->index; @@ -1207,11 +1218,11 @@ static int resize_kernel(struct mlx5_ib_dev *dev, struct mlx5_ib_cq *cq, if (!cq->resize_buf) return -ENOMEM; - err = alloc_cq_buf(dev, cq->resize_buf, entries, cqe_size); + err = alloc_cq_frag_buf(dev, cq->resize_buf, entries, cqe_size); if (err) goto ex; - init_cq_buf(cq, cq->resize_buf); + init_cq_frag_buf(cq, cq->resize_buf); return 0; @@ -1256,9 +1267,8 @@ static int copy_resize_cqes(struct mlx5_ib_cq *cq) } while ((scqe64->op_own >> 4) != MLX5_CQE_RESIZE_CQ) { - dcqe = get_cqe_from_buf(cq->resize_buf, - (i + 1) & (cq->resize_buf->nent), - dsize); + dcqe = mlx5_frag_buf_get_wqe(&cq->resize_buf->fbc, + (i + 1) & cq->resize_buf->nent); dcqe64 = dsize == 64 ? dcqe : dcqe + 64; sw_own = sw_ownership_bit(i + 1, cq->resize_buf->nent); memcpy(dcqe, scqe, dsize); @@ -1324,8 +1334,11 @@ int mlx5_ib_resize_cq(struct ib_cq *ibcq, int entries, struct ib_udata *udata) cqe_size = 64; err = resize_kernel(dev, cq, entries, cqe_size); if (!err) { - npas = cq->resize_buf->buf.npages; - page_shift = cq->resize_buf->buf.page_shift; + struct mlx5_frag_buf_ctrl *c; + + c = &cq->resize_buf->fbc; + npas = c->frag_buf.npages; + page_shift = c->frag_buf.page_shift; } } @@ -1346,7 +1359,8 @@ int mlx5_ib_resize_cq(struct ib_cq *ibcq, int entries, struct ib_udata *udata) mlx5_ib_populate_pas(dev, cq->resize_umem, page_shift, pas, 0); else - mlx5_fill_page_array(&cq->resize_buf->buf, pas); + mlx5_fill_page_frag_array(&cq->resize_buf->fbc.frag_buf, + pas); MLX5_SET(modify_cq_in, in, modify_field_select_resize_field_select.resize_field_select.resize_field_select, diff --git a/drivers/infiniband/hw/mlx5/ib_rep.c b/drivers/infiniband/hw/mlx5/ib_rep.c new file mode 100644 index 000000000000..61cc3d7db257 --- /dev/null +++ b/drivers/infiniband/hw/mlx5/ib_rep.c @@ -0,0 +1,189 @@ +/* SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause) */ +/* + * Copyright (c) 2018 Mellanox Technologies. All rights reserved. + */ + +#include "ib_rep.h" + +static const struct mlx5_ib_profile rep_profile = { + STAGE_CREATE(MLX5_IB_STAGE_INIT, + mlx5_ib_stage_init_init, + mlx5_ib_stage_init_cleanup), + STAGE_CREATE(MLX5_IB_STAGE_FLOW_DB, + mlx5_ib_stage_rep_flow_db_init, + NULL), + STAGE_CREATE(MLX5_IB_STAGE_CAPS, + mlx5_ib_stage_caps_init, + NULL), + STAGE_CREATE(MLX5_IB_STAGE_NON_DEFAULT_CB, + mlx5_ib_stage_rep_non_default_cb, + NULL), + STAGE_CREATE(MLX5_IB_STAGE_ROCE, + mlx5_ib_stage_rep_roce_init, + mlx5_ib_stage_rep_roce_cleanup), + STAGE_CREATE(MLX5_IB_STAGE_DEVICE_RESOURCES, + mlx5_ib_stage_dev_res_init, + mlx5_ib_stage_dev_res_cleanup), + STAGE_CREATE(MLX5_IB_STAGE_COUNTERS, + mlx5_ib_stage_counters_init, + mlx5_ib_stage_counters_cleanup), + STAGE_CREATE(MLX5_IB_STAGE_BFREG, + mlx5_ib_stage_bfrag_init, + mlx5_ib_stage_bfrag_cleanup), + STAGE_CREATE(MLX5_IB_STAGE_IB_REG, + mlx5_ib_stage_ib_reg_init, + mlx5_ib_stage_ib_reg_cleanup), + STAGE_CREATE(MLX5_IB_STAGE_UMR_RESOURCES, + mlx5_ib_stage_umr_res_init, + mlx5_ib_stage_umr_res_cleanup), + STAGE_CREATE(MLX5_IB_STAGE_CLASS_ATTR, + mlx5_ib_stage_class_attr_init, + NULL), +}; + +static int +mlx5_ib_nic_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep) +{ + return 0; +} + +static void +mlx5_ib_nic_rep_unload(struct mlx5_eswitch_rep *rep) +{ + rep->rep_if[REP_IB].priv = NULL; +} + +static int +mlx5_ib_vport_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep) +{ + struct mlx5_ib_dev *ibdev; + + ibdev = (struct mlx5_ib_dev *)ib_alloc_device(sizeof(*ibdev)); + if (!ibdev) + return -ENOMEM; + + ibdev->rep = rep; + ibdev->mdev = dev; + ibdev->num_ports = max(MLX5_CAP_GEN(dev, num_ports), + MLX5_CAP_GEN(dev, num_vhca_ports)); + if (!__mlx5_ib_add(ibdev, &rep_profile)) + return -EINVAL; + + rep->rep_if[REP_IB].priv = ibdev; + + return 0; +} + +static void +mlx5_ib_vport_rep_unload(struct mlx5_eswitch_rep *rep) +{ + struct mlx5_ib_dev *dev; + + if (!rep->rep_if[REP_IB].priv) + return; + + dev = mlx5_ib_rep_to_dev(rep); + __mlx5_ib_remove(dev, dev->profile, MLX5_IB_STAGE_MAX); + rep->rep_if[REP_IB].priv = NULL; +} + +static void *mlx5_ib_vport_get_proto_dev(struct mlx5_eswitch_rep *rep) +{ + return mlx5_ib_rep_to_dev(rep); +} + +static void mlx5_ib_rep_register_vf_vports(struct mlx5_ib_dev *dev) +{ + struct mlx5_eswitch *esw = dev->mdev->priv.eswitch; + int total_vfs = MLX5_TOTAL_VPORTS(dev->mdev); + int vport; + + for (vport = 1; vport < total_vfs; vport++) { + struct mlx5_eswitch_rep_if rep_if = {}; + + rep_if.load = mlx5_ib_vport_rep_load; + rep_if.unload = mlx5_ib_vport_rep_unload; + rep_if.get_proto_dev = mlx5_ib_vport_get_proto_dev; + mlx5_eswitch_register_vport_rep(esw, vport, &rep_if, REP_IB); + } +} + +static void mlx5_ib_rep_unregister_vf_vports(struct mlx5_ib_dev *dev) +{ + struct mlx5_eswitch *esw = dev->mdev->priv.eswitch; + int total_vfs = MLX5_TOTAL_VPORTS(dev->mdev); + int vport; + + for (vport = 1; vport < total_vfs; vport++) + mlx5_eswitch_unregister_vport_rep(esw, vport, REP_IB); +} + +void mlx5_ib_register_vport_reps(struct mlx5_ib_dev *dev) +{ + struct mlx5_eswitch *esw = dev->mdev->priv.eswitch; + struct mlx5_eswitch_rep_if rep_if = {}; + + rep_if.load = mlx5_ib_nic_rep_load; + rep_if.unload = mlx5_ib_nic_rep_unload; + rep_if.get_proto_dev = mlx5_ib_vport_get_proto_dev; + rep_if.priv = dev; + + mlx5_eswitch_register_vport_rep(esw, 0, &rep_if, REP_IB); + + mlx5_ib_rep_register_vf_vports(dev); +} + +void mlx5_ib_unregister_vport_reps(struct mlx5_ib_dev *dev) +{ + struct mlx5_eswitch *esw = dev->mdev->priv.eswitch; + + mlx5_ib_rep_unregister_vf_vports(dev); /* VFs vports */ + mlx5_eswitch_unregister_vport_rep(esw, 0, REP_IB); /* UPLINK PF*/ +} + +u8 mlx5_ib_eswitch_mode(struct mlx5_eswitch *esw) +{ + return mlx5_eswitch_mode(esw); +} + +struct mlx5_ib_dev *mlx5_ib_get_rep_ibdev(struct mlx5_eswitch *esw, + int vport_index) +{ + return mlx5_eswitch_get_proto_dev(esw, vport_index, REP_IB); +} + +struct net_device *mlx5_ib_get_rep_netdev(struct mlx5_eswitch *esw, + int vport_index) +{ + return mlx5_eswitch_get_proto_dev(esw, vport_index, REP_ETH); +} + +struct mlx5_ib_dev *mlx5_ib_get_uplink_ibdev(struct mlx5_eswitch *esw) +{ + return mlx5_eswitch_uplink_get_proto_dev(esw, REP_IB); +} + +struct mlx5_eswitch_rep *mlx5_ib_vport_rep(struct mlx5_eswitch *esw, int vport) +{ + return mlx5_eswitch_vport_rep(esw, vport); +} + +int create_flow_rule_vport_sq(struct mlx5_ib_dev *dev, + struct mlx5_ib_sq *sq) +{ + struct mlx5_flow_handle *flow_rule; + struct mlx5_eswitch *esw = dev->mdev->priv.eswitch; + + if (!dev->rep) + return 0; + + flow_rule = + mlx5_eswitch_add_send_to_vport_rule(esw, + dev->rep->vport, + sq->base.mqp.qpn); + if (IS_ERR(flow_rule)) + return PTR_ERR(flow_rule); + sq->flow_rule = flow_rule; + + return 0; +} diff --git a/drivers/infiniband/hw/mlx5/ib_rep.h b/drivers/infiniband/hw/mlx5/ib_rep.h new file mode 100644 index 000000000000..046fd942fd46 --- /dev/null +++ b/drivers/infiniband/hw/mlx5/ib_rep.h @@ -0,0 +1,72 @@ +/* SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause) */ +/* + * Copyright (c) 2018 Mellanox Technologies. All rights reserved. + */ + +#ifndef __MLX5_IB_REP_H__ +#define __MLX5_IB_REP_H__ + +#include <linux/mlx5/eswitch.h> +#include "mlx5_ib.h" + +#ifdef CONFIG_MLX5_ESWITCH +u8 mlx5_ib_eswitch_mode(struct mlx5_eswitch *esw); +struct mlx5_ib_dev *mlx5_ib_get_rep_ibdev(struct mlx5_eswitch *esw, + int vport_index); +struct mlx5_ib_dev *mlx5_ib_get_uplink_ibdev(struct mlx5_eswitch *esw); +struct mlx5_eswitch_rep *mlx5_ib_vport_rep(struct mlx5_eswitch *esw, + int vport_index); +void mlx5_ib_register_vport_reps(struct mlx5_ib_dev *dev); +void mlx5_ib_unregister_vport_reps(struct mlx5_ib_dev *dev); +int create_flow_rule_vport_sq(struct mlx5_ib_dev *dev, + struct mlx5_ib_sq *sq); +struct net_device *mlx5_ib_get_rep_netdev(struct mlx5_eswitch *esw, + int vport_index); +#else /* CONFIG_MLX5_ESWITCH */ +static inline u8 mlx5_ib_eswitch_mode(struct mlx5_eswitch *esw) +{ + return SRIOV_NONE; +} + +static inline +struct mlx5_ib_dev *mlx5_ib_get_rep_ibdev(struct mlx5_eswitch *esw, + int vport_index) +{ + return NULL; +} + +static inline +struct mlx5_ib_dev *mlx5_ib_get_uplink_ibdev(struct mlx5_eswitch *esw) +{ + return NULL; +} + +static inline +struct mlx5_eswitch_rep *mlx5_ib_vport_rep(struct mlx5_eswitch *esw, + int vport_index) +{ + return NULL; +} + +static inline void mlx5_ib_register_vport_reps(struct mlx5_ib_dev *dev) {} +static inline void mlx5_ib_unregister_vport_reps(struct mlx5_ib_dev *dev) {} +static inline int create_flow_rule_vport_sq(struct mlx5_ib_dev *dev, + struct mlx5_ib_sq *sq) +{ + return 0; +} + +static inline +struct net_device *mlx5_ib_get_rep_netdev(struct mlx5_eswitch *esw, + int vport_index) +{ + return NULL; +} +#endif + +static inline +struct mlx5_ib_dev *mlx5_ib_rep_to_dev(struct mlx5_eswitch_rep *rep) +{ + return (struct mlx5_ib_dev *)rep->rep_if[REP_IB].priv; +} +#endif /* __MLX5_IB_REP_H__ */ diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index 4236c8086820..ee55d7d64554 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -57,6 +57,7 @@ #include <linux/in.h> #include <linux/etherdevice.h> #include "mlx5_ib.h" +#include "ib_rep.h" #include "cmd.h" #define DRIVER_NAME "mlx5_ib" @@ -130,7 +131,7 @@ static int get_port_state(struct ib_device *ibdev, int ret; memset(&attr, 0, sizeof(attr)); - ret = mlx5_ib_query_port(ibdev, port_num, &attr); + ret = ibdev->query_port(ibdev, port_num, &attr); if (!ret) *state = attr.state; return ret; @@ -154,10 +155,19 @@ static int mlx5_netdev_event(struct notifier_block *this, case NETDEV_REGISTER: case NETDEV_UNREGISTER: write_lock(&roce->netdev_lock); - - if (ndev->dev.parent == &mdev->pdev->dev) - roce->netdev = (event == NETDEV_UNREGISTER) ? + if (ibdev->rep) { + struct mlx5_eswitch *esw = ibdev->mdev->priv.eswitch; + struct net_device *rep_ndev; + + rep_ndev = mlx5_ib_get_rep_netdev(esw, + ibdev->rep->vport); + if (rep_ndev == ndev) + roce->netdev = (event == NETDEV_UNREGISTER) ? NULL : ndev; + } else if (ndev->dev.parent == &ibdev->mdev->pdev->dev) { + roce->netdev = (event == NETDEV_UNREGISTER) ? + NULL : ndev; + } write_unlock(&roce->netdev_lock); break; @@ -1268,6 +1278,22 @@ int mlx5_ib_query_port(struct ib_device *ibdev, u8 port, return ret; } +static int mlx5_ib_rep_query_port(struct ib_device *ibdev, u8 port, + struct ib_port_attr *props) +{ + int ret; + + /* Only link layer == ethernet is valid for representors */ + ret = mlx5_query_port_roce(ibdev, port, props); + if (ret || !props) + return ret; + + /* We don't support GIDS */ + props->gid_tbl_len = 0; + + return ret; +} + static int mlx5_ib_query_gid(struct ib_device *ibdev, u8 port, int index, union ib_gid *gid) { @@ -2631,7 +2657,7 @@ static int mlx5_ib_destroy_flow(struct ib_flow *flow_id) ibflow); struct mlx5_ib_flow_handler *iter, *tmp; - mutex_lock(&dev->flow_db.lock); + mutex_lock(&dev->flow_db->lock); list_for_each_entry_safe(iter, tmp, &handler->list, list) { mlx5_del_flow_rules(iter->rule); @@ -2642,7 +2668,7 @@ static int mlx5_ib_destroy_flow(struct ib_flow *flow_id) mlx5_del_flow_rules(handler->rule); put_flow_table(dev, handler->prio, true); - mutex_unlock(&dev->flow_db.lock); + mutex_unlock(&dev->flow_db->lock); kfree(handler); @@ -2691,7 +2717,7 @@ static struct mlx5_ib_flow_prio *get_flow_table(struct mlx5_ib_dev *dev, MLX5_FLOW_NAMESPACE_BYPASS); num_entries = MLX5_FS_MAX_ENTRIES; num_groups = MLX5_FS_MAX_TYPES; - prio = &dev->flow_db.prios[priority]; + prio = &dev->flow_db->prios[priority]; } else if (flow_attr->type == IB_FLOW_ATTR_ALL_DEFAULT || flow_attr->type == IB_FLOW_ATTR_MC_DEFAULT) { ns = mlx5_get_flow_namespace(dev->mdev, @@ -2699,7 +2725,7 @@ static struct mlx5_ib_flow_prio *get_flow_table(struct mlx5_ib_dev *dev, build_leftovers_ft_param(&priority, &num_entries, &num_groups); - prio = &dev->flow_db.prios[MLX5_IB_FLOW_LEFTOVERS_PRIO]; + prio = &dev->flow_db->prios[MLX5_IB_FLOW_LEFTOVERS_PRIO]; } else if (flow_attr->type == IB_FLOW_ATTR_SNIFFER) { if (!MLX5_CAP_FLOWTABLE(dev->mdev, allow_sniffer_and_nic_rx_shared_tir)) @@ -2709,7 +2735,7 @@ static struct mlx5_ib_flow_prio *get_flow_table(struct mlx5_ib_dev *dev, MLX5_FLOW_NAMESPACE_SNIFFER_RX : MLX5_FLOW_NAMESPACE_SNIFFER_TX); - prio = &dev->flow_db.sniffer[ft_type]; + prio = &dev->flow_db->sniffer[ft_type]; priority = 0; num_entries = 1; num_groups = 1; @@ -2802,6 +2828,18 @@ static struct mlx5_ib_flow_handler *_create_flow_rule(struct mlx5_ib_dev *dev, if (!flow_is_multicast_only(flow_attr)) set_underlay_qp(dev, spec, underlay_qpn); + if (dev->rep) { + void *misc; + + misc = MLX5_ADDR_OF(fte_match_param, spec->match_value, + misc_parameters); + MLX5_SET(fte_match_set_misc, misc, source_port, + dev->rep->vport); + misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, + misc_parameters); + MLX5_SET_TO_ONES(fte_match_set_misc, misc, source_port); + } + spec->match_criteria_enable = get_match_criteria_enable(spec->match_criteria); if (is_drop) { flow_act.action = MLX5_FLOW_CONTEXT_ACTION_DROP; @@ -2999,7 +3037,7 @@ static struct ib_flow *mlx5_ib_create_flow(struct ib_qp *qp, if (!dst) return ERR_PTR(-ENOMEM); - mutex_lock(&dev->flow_db.lock); + mutex_lock(&dev->flow_db->lock); ft_prio = get_flow_table(dev, flow_attr, MLX5_IB_FT_RX); if (IS_ERR(ft_prio)) { @@ -3048,7 +3086,7 @@ static struct ib_flow *mlx5_ib_create_flow(struct ib_qp *qp, goto destroy_ft; } - mutex_unlock(&dev->flow_db.lock); + mutex_unlock(&dev->flow_db->lock); kfree(dst); return &handler->ibflow; @@ -3058,7 +3096,7 @@ destroy_ft: if (ft_prio_tx) put_flow_table(dev, ft_prio_tx, false); unlock: - mutex_unlock(&dev->flow_db.lock); + mutex_unlock(&dev->flow_db->lock); kfree(dst); kfree(handler); return ERR_PTR(err); @@ -3772,6 +3810,25 @@ static int mlx5_port_immutable(struct ib_device *ibdev, u8 port_num, return 0; } +static int mlx5_port_rep_immutable(struct ib_device *ibdev, u8 port_num, + struct ib_port_immutable *immutable) +{ + struct ib_port_attr attr; + int err; + + immutable->core_cap_flags = RDMA_CORE_PORT_RAW_PACKET; + + err = ib_query_port(ibdev, port_num, &attr); + if (err) + return err; + + immutable->pkey_tbl_len = attr.pkey_tbl_len; + immutable->gid_tbl_len = attr.gid_tbl_len; + immutable->core_cap_flags = RDMA_CORE_PORT_RAW_PACKET; + + return 0; +} + static void get_dev_fw_str(struct ib_device *ibdev, char *str) { struct mlx5_ib_dev *dev = @@ -3802,7 +3859,7 @@ static int mlx5_eth_lag_init(struct mlx5_ib_dev *dev) goto err_destroy_vport_lag; } - dev->flow_db.lag_demux_ft = ft; + dev->flow_db->lag_demux_ft = ft; return 0; err_destroy_vport_lag: @@ -3814,9 +3871,9 @@ static void mlx5_eth_lag_cleanup(struct mlx5_ib_dev *dev) { struct mlx5_core_dev *mdev = dev->mdev; - if (dev->flow_db.lag_demux_ft) { - mlx5_destroy_flow_table(dev->flow_db.lag_demux_ft); - dev->flow_db.lag_demux_ft = NULL; + if (dev->flow_db->lag_demux_ft) { + mlx5_destroy_flow_table(dev->flow_db->lag_demux_ft); + dev->flow_db->lag_demux_ft = NULL; mlx5_cmd_destroy_vport_lag(mdev); } @@ -3848,14 +3905,10 @@ static int mlx5_enable_eth(struct mlx5_ib_dev *dev, u8 port_num) { int err; - err = mlx5_add_netdev_notifier(dev, port_num); - if (err) - return err; - if (MLX5_CAP_GEN(dev->mdev, roce)) { err = mlx5_nic_vport_enable_roce(dev->mdev); if (err) - goto err_unregister_netdevice_notifier; + return err; } err = mlx5_eth_lag_init(dev); @@ -3868,8 +3921,6 @@ err_disable_roce: if (MLX5_CAP_GEN(dev->mdev, roce)) mlx5_nic_vport_disable_roce(dev->mdev); -err_unregister_netdevice_notifier: - mlx5_remove_netdev_notifier(dev, port_num); return err; } @@ -4503,7 +4554,7 @@ static void mlx5_ib_cleanup_multiport_master(struct mlx5_ib_dev *dev) mlx5_nic_vport_disable_roce(dev->mdev); } -static void mlx5_ib_stage_init_cleanup(struct mlx5_ib_dev *dev) +void mlx5_ib_stage_init_cleanup(struct mlx5_ib_dev *dev) { mlx5_ib_cleanup_multiport_master(dev); #ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING @@ -4512,7 +4563,7 @@ static void mlx5_ib_stage_init_cleanup(struct mlx5_ib_dev *dev) kfree(dev->port); } -static int mlx5_ib_stage_init_init(struct mlx5_ib_dev *dev) +int mlx5_ib_stage_init_init(struct mlx5_ib_dev *dev) { struct mlx5_core_dev *mdev = dev->mdev; const char *name; @@ -4564,7 +4615,6 @@ static int mlx5_ib_stage_init_init(struct mlx5_ib_dev *dev) dev->mdev->priv.eq_table.num_comp_vectors; dev->ib_dev.dev.parent = &mdev->pdev->dev; - mutex_init(&dev->flow_db.lock); mutex_init(&dev->cap_mask_mutex); INIT_LIST_HEAD(&dev->qp_list); spin_lock_init(&dev->reset_flow_resource_lock); @@ -4585,7 +4635,38 @@ err_free_port: return -ENOMEM; } -static int mlx5_ib_stage_caps_init(struct mlx5_ib_dev *dev) +static int mlx5_ib_stage_flow_db_init(struct mlx5_ib_dev *dev) +{ + dev->flow_db = kzalloc(sizeof(*dev->flow_db), GFP_KERNEL); + + if (!dev->flow_db) + return -ENOMEM; + + mutex_init(&dev->flow_db->lock); + + return 0; +} + +int mlx5_ib_stage_rep_flow_db_init(struct mlx5_ib_dev *dev) +{ + struct mlx5_ib_dev *nic_dev; + + nic_dev = mlx5_ib_get_uplink_ibdev(dev->mdev->priv.eswitch); + + if (!nic_dev) + return -EINVAL; + + dev->flow_db = nic_dev->flow_db; + + return 0; +} + +static void mlx5_ib_stage_flow_db_cleanup(struct mlx5_ib_dev *dev) +{ + kfree(dev->flow_db); +} + +int mlx5_ib_stage_caps_init(struct mlx5_ib_dev *dev) { struct mlx5_core_dev *mdev = dev->mdev; int err; @@ -4626,7 +4707,6 @@ static int mlx5_ib_stage_caps_init(struct mlx5_ib_dev *dev) (1ull << IB_USER_VERBS_EX_CMD_MODIFY_CQ); dev->ib_dev.query_device = mlx5_ib_query_device; - dev->ib_dev.query_port = mlx5_ib_query_port; dev->ib_dev.get_link_layer = mlx5_ib_port_link_layer; dev->ib_dev.query_gid = mlx5_ib_query_gid; dev->ib_dev.add_gid = mlx5_ib_add_gid; @@ -4669,7 +4749,6 @@ static int mlx5_ib_stage_caps_init(struct mlx5_ib_dev *dev) dev->ib_dev.alloc_mr = mlx5_ib_alloc_mr; dev->ib_dev.map_mr_sg = mlx5_ib_map_mr_sg; dev->ib_dev.check_mr_status = mlx5_ib_check_mr_status; - dev->ib_dev.get_port_immutable = mlx5_port_immutable; dev->ib_dev.get_dev_fw_str = get_dev_fw_str; dev->ib_dev.get_vector_affinity = mlx5_ib_get_vector_affinity; if (MLX5_CAP_GEN(mdev, ipoib_enhanced_offloads)) @@ -4720,6 +4799,80 @@ static int mlx5_ib_stage_caps_init(struct mlx5_ib_dev *dev) return 0; } +static int mlx5_ib_stage_non_default_cb(struct mlx5_ib_dev *dev) +{ + dev->ib_dev.get_port_immutable = mlx5_port_immutable; + dev->ib_dev.query_port = mlx5_ib_query_port; + + return 0; +} + +int mlx5_ib_stage_rep_non_default_cb(struct mlx5_ib_dev *dev) +{ + dev->ib_dev.get_port_immutable = mlx5_port_rep_immutable; + dev->ib_dev.query_port = mlx5_ib_rep_query_port; + + return 0; +} + +static int mlx5_ib_stage_common_roce_init(struct mlx5_ib_dev *dev, + u8 port_num) +{ + int i; + + for (i = 0; i < dev->num_ports; i++) { + dev->roce[i].dev = dev; + dev->roce[i].native_port_num = i + 1; + dev->roce[i].last_port_state = IB_PORT_DOWN; + } + + dev->ib_dev.get_netdev = mlx5_ib_get_netdev; + dev->ib_dev.create_wq = mlx5_ib_create_wq; + dev->ib_dev.modify_wq = mlx5_ib_modify_wq; + dev->ib_dev.destroy_wq = mlx5_ib_destroy_wq; + dev->ib_dev.create_rwq_ind_table = mlx5_ib_create_rwq_ind_table; + dev->ib_dev.destroy_rwq_ind_table = mlx5_ib_destroy_rwq_ind_table; + + dev->ib_dev.uverbs_ex_cmd_mask |= + (1ull << IB_USER_VERBS_EX_CMD_CREATE_WQ) | + (1ull << IB_USER_VERBS_EX_CMD_MODIFY_WQ) | + (1ull << IB_USER_VERBS_EX_CMD_DESTROY_WQ) | + (1ull << IB_USER_VERBS_EX_CMD_CREATE_RWQ_IND_TBL) | + (1ull << IB_USER_VERBS_EX_CMD_DESTROY_RWQ_IND_TBL); + + return mlx5_add_netdev_notifier(dev, port_num); +} + +static void mlx5_ib_stage_common_roce_cleanup(struct mlx5_ib_dev *dev) +{ + u8 port_num = mlx5_core_native_port_num(dev->mdev) - 1; + + mlx5_remove_netdev_notifier(dev, port_num); +} + +int mlx5_ib_stage_rep_roce_init(struct mlx5_ib_dev *dev) +{ + struct mlx5_core_dev *mdev = dev->mdev; + enum rdma_link_layer ll; + int port_type_cap; + int err = 0; + u8 port_num; + + port_num = mlx5_core_native_port_num(dev->mdev) - 1; + port_type_cap = MLX5_CAP_GEN(mdev, port_type); + ll = mlx5_port_type_cap_to_rdma_ll(port_type_cap); + + if (ll == IB_LINK_LAYER_ETHERNET) + err = mlx5_ib_stage_common_roce_init(dev, port_num); + + return err; +} + +void mlx5_ib_stage_rep_roce_cleanup(struct mlx5_ib_dev *dev) +{ + mlx5_ib_stage_common_roce_cleanup(dev); +} + static int mlx5_ib_stage_roce_init(struct mlx5_ib_dev *dev) { struct mlx5_core_dev *mdev = dev->mdev; @@ -4727,37 +4880,26 @@ static int mlx5_ib_stage_roce_init(struct mlx5_ib_dev *dev) int port_type_cap; u8 port_num; int err; - int i; port_num = mlx5_core_native_port_num(dev->mdev) - 1; port_type_cap = MLX5_CAP_GEN(mdev, port_type); ll = mlx5_port_type_cap_to_rdma_ll(port_type_cap); if (ll == IB_LINK_LAYER_ETHERNET) { - for (i = 0; i < dev->num_ports; i++) { - dev->roce[i].dev = dev; - dev->roce[i].native_port_num = i + 1; - dev->roce[i].last_port_state = IB_PORT_DOWN; - } + err = mlx5_ib_stage_common_roce_init(dev, port_num); + if (err) + return err; - dev->ib_dev.get_netdev = mlx5_ib_get_netdev; - dev->ib_dev.create_wq = mlx5_ib_create_wq; - dev->ib_dev.modify_wq = mlx5_ib_modify_wq; - dev->ib_dev.destroy_wq = mlx5_ib_destroy_wq; - dev->ib_dev.create_rwq_ind_table = mlx5_ib_create_rwq_ind_table; - dev->ib_dev.destroy_rwq_ind_table = mlx5_ib_destroy_rwq_ind_table; - dev->ib_dev.uverbs_ex_cmd_mask |= - (1ull << IB_USER_VERBS_EX_CMD_CREATE_WQ) | - (1ull << IB_USER_VERBS_EX_CMD_MODIFY_WQ) | - (1ull << IB_USER_VERBS_EX_CMD_DESTROY_WQ) | - (1ull << IB_USER_VERBS_EX_CMD_CREATE_RWQ_IND_TBL) | - (1ull << IB_USER_VERBS_EX_CMD_DESTROY_RWQ_IND_TBL); err = mlx5_enable_eth(dev, port_num); if (err) - return err; + goto cleanup; } return 0; +cleanup: + mlx5_ib_stage_common_roce_cleanup(dev); + + return err; } static void mlx5_ib_stage_roce_cleanup(struct mlx5_ib_dev *dev) @@ -4773,16 +4915,16 @@ static void mlx5_ib_stage_roce_cleanup(struct mlx5_ib_dev *dev) if (ll == IB_LINK_LAYER_ETHERNET) { mlx5_disable_eth(dev); - mlx5_remove_netdev_notifier(dev, port_num); + mlx5_ib_stage_common_roce_cleanup(dev); } } -static int mlx5_ib_stage_dev_res_init(struct mlx5_ib_dev *dev) +int mlx5_ib_stage_dev_res_init(struct mlx5_ib_dev *dev) { return create_dev_resources(&dev->devr); } -static void mlx5_ib_stage_dev_res_cleanup(struct mlx5_ib_dev *dev) +void mlx5_ib_stage_dev_res_cleanup(struct mlx5_ib_dev *dev) { destroy_dev_resources(&dev->devr); } @@ -4794,7 +4936,7 @@ static int mlx5_ib_stage_odp_init(struct mlx5_ib_dev *dev) return mlx5_ib_odp_init_one(dev); } -static int mlx5_ib_stage_counters_init(struct mlx5_ib_dev *dev) +int mlx5_ib_stage_counters_init(struct mlx5_ib_dev *dev) { if (MLX5_CAP_GEN(dev->mdev, max_qp_cnt)) { dev->ib_dev.get_hw_stats = mlx5_ib_get_hw_stats; @@ -4806,7 +4948,7 @@ static int mlx5_ib_stage_counters_init(struct mlx5_ib_dev *dev) return 0; } -static void mlx5_ib_stage_counters_cleanup(struct mlx5_ib_dev *dev) +void mlx5_ib_stage_counters_cleanup(struct mlx5_ib_dev *dev) { if (MLX5_CAP_GEN(dev->mdev, max_qp_cnt)) mlx5_ib_dealloc_counters(dev); @@ -4837,7 +4979,7 @@ static void mlx5_ib_stage_uar_cleanup(struct mlx5_ib_dev *dev) mlx5_put_uars_page(dev->mdev, dev->mdev->priv.uar); } -static int mlx5_ib_stage_bfrag_init(struct mlx5_ib_dev *dev) +int mlx5_ib_stage_bfrag_init(struct mlx5_ib_dev *dev) { int err; @@ -4852,28 +4994,28 @@ static int mlx5_ib_stage_bfrag_init(struct mlx5_ib_dev *dev) return err; } -static void mlx5_ib_stage_bfrag_cleanup(struct mlx5_ib_dev *dev) +void mlx5_ib_stage_bfrag_cleanup(struct mlx5_ib_dev *dev) { mlx5_free_bfreg(dev->mdev, &dev->fp_bfreg); mlx5_free_bfreg(dev->mdev, &dev->bfreg); } -static int mlx5_ib_stage_ib_reg_init(struct mlx5_ib_dev *dev) +int mlx5_ib_stage_ib_reg_init(struct mlx5_ib_dev *dev) { return ib_register_device(&dev->ib_dev, NULL); } -static void mlx5_ib_stage_ib_reg_cleanup(struct mlx5_ib_dev *dev) +void mlx5_ib_stage_ib_reg_cleanup(struct mlx5_ib_dev *dev) { ib_unregister_device(&dev->ib_dev); } -static int mlx5_ib_stage_umr_res_init(struct mlx5_ib_dev *dev) +int mlx5_ib_stage_umr_res_init(struct mlx5_ib_dev *dev) { return create_umr_res(dev); } -static void mlx5_ib_stage_umr_res_cleanup(struct mlx5_ib_dev *dev) +void mlx5_ib_stage_umr_res_cleanup(struct mlx5_ib_dev *dev) { destroy_umrc_res(dev); } @@ -4890,7 +5032,7 @@ static void mlx5_ib_stage_delay_drop_cleanup(struct mlx5_ib_dev *dev) cancel_delay_drop(dev); } -static int mlx5_ib_stage_class_attr_init(struct mlx5_ib_dev *dev) +int mlx5_ib_stage_class_attr_init(struct mlx5_ib_dev *dev) { int err; int i; @@ -4905,9 +5047,21 @@ static int mlx5_ib_stage_class_attr_init(struct mlx5_ib_dev *dev) return 0; } -static void __mlx5_ib_remove(struct mlx5_ib_dev *dev, - const struct mlx5_ib_profile *profile, - int stage) +static int mlx5_ib_stage_rep_reg_init(struct mlx5_ib_dev *dev) +{ + mlx5_ib_register_vport_reps(dev); + + return 0; +} + +static void mlx5_ib_stage_rep_reg_cleanup(struct mlx5_ib_dev *dev) +{ + mlx5_ib_unregister_vport_reps(dev); +} + +void __mlx5_ib_remove(struct mlx5_ib_dev *dev, + const struct mlx5_ib_profile *profile, + int stage) { /* Number of stages to cleanup */ while (stage) { @@ -4921,23 +5075,14 @@ static void __mlx5_ib_remove(struct mlx5_ib_dev *dev, static void *mlx5_ib_add_slave_port(struct mlx5_core_dev *mdev, u8 port_num); -static void *__mlx5_ib_add(struct mlx5_core_dev *mdev, - const struct mlx5_ib_profile *profile) +void *__mlx5_ib_add(struct mlx5_ib_dev *dev, + const struct mlx5_ib_profile *profile) { - struct mlx5_ib_dev *dev; int err; int i; printk_once(KERN_INFO "%s", mlx5_version); - dev = (struct mlx5_ib_dev *)ib_alloc_device(sizeof(*dev)); - if (!dev) - return NULL; - - dev->mdev = mdev; - dev->num_ports = max(MLX5_CAP_GEN(mdev, num_ports), - MLX5_CAP_GEN(mdev, num_vhca_ports)); - for (i = 0; i < MLX5_IB_STAGE_MAX; i++) { if (profile->stage[i].init) { err = profile->stage[i].init(dev); @@ -4961,9 +5106,15 @@ static const struct mlx5_ib_profile pf_profile = { STAGE_CREATE(MLX5_IB_STAGE_INIT, mlx5_ib_stage_init_init, mlx5_ib_stage_init_cleanup), + STAGE_CREATE(MLX5_IB_STAGE_FLOW_DB, + mlx5_ib_stage_flow_db_init, + mlx5_ib_stage_flow_db_cleanup), STAGE_CREATE(MLX5_IB_STAGE_CAPS, mlx5_ib_stage_caps_init, NULL), + STAGE_CREATE(MLX5_IB_STAGE_NON_DEFAULT_CB, + mlx5_ib_stage_non_default_cb, + NULL), STAGE_CREATE(MLX5_IB_STAGE_ROCE, mlx5_ib_stage_roce_init, mlx5_ib_stage_roce_cleanup), @@ -4999,6 +5150,48 @@ static const struct mlx5_ib_profile pf_profile = { NULL), }; +static const struct mlx5_ib_profile nic_rep_profile = { + STAGE_CREATE(MLX5_IB_STAGE_INIT, + mlx5_ib_stage_init_init, + mlx5_ib_stage_init_cleanup), + STAGE_CREATE(MLX5_IB_STAGE_FLOW_DB, + mlx5_ib_stage_flow_db_init, + mlx5_ib_stage_flow_db_cleanup), + STAGE_CREATE(MLX5_IB_STAGE_CAPS, + mlx5_ib_stage_caps_init, + NULL), + STAGE_CREATE(MLX5_IB_STAGE_NON_DEFAULT_CB, + mlx5_ib_stage_rep_non_default_cb, + NULL), + STAGE_CREATE(MLX5_IB_STAGE_ROCE, + mlx5_ib_stage_rep_roce_init, + mlx5_ib_stage_rep_roce_cleanup), + STAGE_CREATE(MLX5_IB_STAGE_DEVICE_RESOURCES, + mlx5_ib_stage_dev_res_init, + mlx5_ib_stage_dev_res_cleanup), + STAGE_CREATE(MLX5_IB_STAGE_COUNTERS, + mlx5_ib_stage_counters_init, + mlx5_ib_stage_counters_cleanup), + STAGE_CREATE(MLX5_IB_STAGE_UAR, + mlx5_ib_stage_uar_init, + mlx5_ib_stage_uar_cleanup), + STAGE_CREATE(MLX5_IB_STAGE_BFREG, + mlx5_ib_stage_bfrag_init, + mlx5_ib_stage_bfrag_cleanup), + STAGE_CREATE(MLX5_IB_STAGE_IB_REG, + mlx5_ib_stage_ib_reg_init, + mlx5_ib_stage_ib_reg_cleanup), + STAGE_CREATE(MLX5_IB_STAGE_UMR_RESOURCES, + mlx5_ib_stage_umr_res_init, + mlx5_ib_stage_umr_res_cleanup), + STAGE_CREATE(MLX5_IB_STAGE_CLASS_ATTR, + mlx5_ib_stage_class_attr_init, + NULL), + STAGE_CREATE(MLX5_IB_STAGE_REP_REG, + mlx5_ib_stage_rep_reg_init, + mlx5_ib_stage_rep_reg_cleanup), +}; + static void *mlx5_ib_add_slave_port(struct mlx5_core_dev *mdev, u8 port_num) { struct mlx5_ib_multiport_info *mpi; @@ -5044,8 +5237,11 @@ static void *mlx5_ib_add_slave_port(struct mlx5_core_dev *mdev, u8 port_num) static void *mlx5_ib_add(struct mlx5_core_dev *mdev) { enum rdma_link_layer ll; + struct mlx5_ib_dev *dev; int port_type_cap; + printk_once(KERN_INFO "%s", mlx5_version); + port_type_cap = MLX5_CAP_GEN(mdev, port_type); ll = mlx5_port_type_cap_to_rdma_ll(port_type_cap); @@ -5055,7 +5251,22 @@ static void *mlx5_ib_add(struct mlx5_core_dev *mdev) return mlx5_ib_add_slave_port(mdev, port_num); } - return __mlx5_ib_add(mdev, &pf_profile); + dev = (struct mlx5_ib_dev *)ib_alloc_device(sizeof(*dev)); + if (!dev) + return NULL; + + dev->mdev = mdev; + dev->num_ports = max(MLX5_CAP_GEN(mdev, num_ports), + MLX5_CAP_GEN(mdev, num_vhca_ports)); + + if (MLX5_VPORT_MANAGER(mdev) && + mlx5_ib_eswitch_mode(mdev->priv.eswitch) == SRIOV_OFFLOADS) { + dev->rep = mlx5_ib_vport_rep(mdev->priv.eswitch, 0); + + return __mlx5_ib_add(dev, &nic_rep_profile); + } + + return __mlx5_ib_add(dev, &pf_profile); } static void mlx5_ib_remove(struct mlx5_core_dev *mdev, void *context) diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h index 139385129973..e0bad28e0f09 100644 --- a/drivers/infiniband/hw/mlx5/mlx5_ib.h +++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h @@ -343,6 +343,7 @@ struct mlx5_ib_sq { struct mlx5_ib_wq *sq; struct mlx5_ib_ubuffer ubuffer; struct mlx5_db *doorbell; + struct mlx5_flow_handle *flow_rule; u32 tisn; u8 state; }; @@ -371,7 +372,7 @@ struct mlx5_ib_qp { struct mlx5_ib_rss_qp rss_qp; struct mlx5_ib_dct dct; }; - struct mlx5_buf buf; + struct mlx5_frag_buf buf; struct mlx5_db db; struct mlx5_ib_wq rq; @@ -413,7 +414,7 @@ struct mlx5_ib_qp { }; struct mlx5_ib_cq_buf { - struct mlx5_buf buf; + struct mlx5_frag_buf_ctrl fbc; struct ib_umem *umem; int cqe_size; int nent; @@ -495,7 +496,7 @@ struct mlx5_ib_wc { struct mlx5_ib_srq { struct ib_srq ibsrq; struct mlx5_core_srq msrq; - struct mlx5_buf buf; + struct mlx5_frag_buf buf; struct mlx5_db db; u64 *wrid; /* protect SRQ hanlding @@ -731,7 +732,9 @@ struct mlx5_ib_delay_drop { enum mlx5_ib_stages { MLX5_IB_STAGE_INIT, + MLX5_IB_STAGE_FLOW_DB, MLX5_IB_STAGE_CAPS, + MLX5_IB_STAGE_NON_DEFAULT_CB, MLX5_IB_STAGE_ROCE, MLX5_IB_STAGE_DEVICE_RESOURCES, MLX5_IB_STAGE_ODP, @@ -743,6 +746,7 @@ enum mlx5_ib_stages { MLX5_IB_STAGE_UMR_RESOURCES, MLX5_IB_STAGE_DELAY_DROP, MLX5_IB_STAGE_CLASS_ATTR, + MLX5_IB_STAGE_REP_REG, MLX5_IB_STAGE_MAX, }; @@ -797,7 +801,7 @@ struct mlx5_ib_dev { struct srcu_struct mr_srcu; u32 null_mkey; #endif - struct mlx5_ib_flow_db flow_db; + struct mlx5_ib_flow_db *flow_db; /* protect resources needed as part of reset flow */ spinlock_t reset_flow_resource_lock; struct list_head qp_list; @@ -807,6 +811,7 @@ struct mlx5_ib_dev { struct mlx5_sq_bfreg fp_bfreg; struct mlx5_ib_delay_drop delay_drop; const struct mlx5_ib_profile *profile; + struct mlx5_eswitch_rep *rep; /* protect the user_td */ struct mutex lb_mutex; @@ -1049,6 +1054,31 @@ static inline void mlx5_odp_populate_klm(struct mlx5_klm *pklm, size_t offset, #endif /* CONFIG_INFINIBAND_ON_DEMAND_PAGING */ +/* Needed for rep profile */ +int mlx5_ib_stage_init_init(struct mlx5_ib_dev *dev); +void mlx5_ib_stage_init_cleanup(struct mlx5_ib_dev *dev); +int mlx5_ib_stage_rep_flow_db_init(struct mlx5_ib_dev *dev); +int mlx5_ib_stage_caps_init(struct mlx5_ib_dev *dev); +int mlx5_ib_stage_rep_non_default_cb(struct mlx5_ib_dev *dev); +int mlx5_ib_stage_rep_roce_init(struct mlx5_ib_dev *dev); +void mlx5_ib_stage_rep_roce_cleanup(struct mlx5_ib_dev *dev); +int mlx5_ib_stage_dev_res_init(struct mlx5_ib_dev *dev); +void mlx5_ib_stage_dev_res_cleanup(struct mlx5_ib_dev *dev); +int mlx5_ib_stage_counters_init(struct mlx5_ib_dev *dev); +void mlx5_ib_stage_counters_cleanup(struct mlx5_ib_dev *dev); +int mlx5_ib_stage_bfrag_init(struct mlx5_ib_dev *dev); +void mlx5_ib_stage_bfrag_cleanup(struct mlx5_ib_dev *dev); +int mlx5_ib_stage_ib_reg_init(struct mlx5_ib_dev *dev); +void mlx5_ib_stage_ib_reg_cleanup(struct mlx5_ib_dev *dev); +int mlx5_ib_stage_umr_res_init(struct mlx5_ib_dev *dev); +void mlx5_ib_stage_umr_res_cleanup(struct mlx5_ib_dev *dev); +int mlx5_ib_stage_class_attr_init(struct mlx5_ib_dev *dev); +void __mlx5_ib_remove(struct mlx5_ib_dev *dev, + const struct mlx5_ib_profile *profile, + int stage); +void *__mlx5_ib_add(struct mlx5_ib_dev *dev, + const struct mlx5_ib_profile *profile); + int mlx5_ib_get_vf_config(struct ib_device *device, int vf, u8 port, struct ifla_vf_info *info); int mlx5_ib_set_vf_link_state(struct ib_device *device, int vf, diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c index 556e015678de..a5fad3e87ff7 100644 --- a/drivers/infiniband/hw/mlx5/mr.c +++ b/drivers/infiniband/hw/mlx5/mr.c @@ -587,7 +587,7 @@ static void clean_keys(struct mlx5_ib_dev *dev, int c) static void mlx5_mr_cache_debugfs_cleanup(struct mlx5_ib_dev *dev) { - if (!mlx5_debugfs_root) + if (!mlx5_debugfs_root || dev->rep) return; debugfs_remove_recursive(dev->cache.root); @@ -600,7 +600,7 @@ static int mlx5_mr_cache_debugfs_init(struct mlx5_ib_dev *dev) struct mlx5_cache_ent *ent; int i; - if (!mlx5_debugfs_root) + if (!mlx5_debugfs_root || dev->rep) return 0; cache->root = debugfs_create_dir("mr_cache", dev->mdev->priv.dbg_root); @@ -690,6 +690,7 @@ int mlx5_mr_cache_init(struct mlx5_ib_dev *dev) MLX5_IB_UMR_OCTOWORD; ent->access_mode = MLX5_MKC_ACCESS_MODE_MTT; if ((dev->mdev->profile->mask & MLX5_PROF_MASK_MR_CACHE) && + !dev->rep && mlx5_core_is_pf(dev->mdev)) ent->limit = dev->mdev->profile->mr_cache[i].limit; else diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c index 39d24bf694a8..5663530ea5fd 100644 --- a/drivers/infiniband/hw/mlx5/qp.c +++ b/drivers/infiniband/hw/mlx5/qp.c @@ -36,6 +36,7 @@ #include <rdma/ib_user_verbs.h> #include <linux/mlx5/fs.h> #include "mlx5_ib.h" +#include "ib_rep.h" /* not supported currently */ static int wq_signature; @@ -1082,6 +1083,13 @@ static void destroy_raw_packet_qp_tis(struct mlx5_ib_dev *dev, mlx5_core_destroy_tis(dev->mdev, sq->tisn); } +static void destroy_flow_rule_vport_sq(struct mlx5_ib_dev *dev, + struct mlx5_ib_sq *sq) +{ + if (sq->flow_rule) + mlx5_del_flow_rules(sq->flow_rule); +} + static int create_raw_packet_qp_sq(struct mlx5_ib_dev *dev, struct mlx5_ib_sq *sq, void *qpin, struct ib_pd *pd) @@ -1145,8 +1153,15 @@ static int create_raw_packet_qp_sq(struct mlx5_ib_dev *dev, if (err) goto err_umem; + err = create_flow_rule_vport_sq(dev, sq); + if (err) + goto err_flow; + return 0; +err_flow: + mlx5_core_destroy_sq_tracked(dev->mdev, &sq->base.mqp); + err_umem: ib_umem_release(sq->ubuffer.umem); sq->ubuffer.umem = NULL; @@ -1157,6 +1172,7 @@ err_umem: static void destroy_raw_packet_qp_sq(struct mlx5_ib_dev *dev, struct mlx5_ib_sq *sq) { + destroy_flow_rule_vport_sq(dev, sq); mlx5_core_destroy_sq_tracked(dev->mdev, &sq->base.mqp); ib_umem_release(sq->ubuffer.umem); } @@ -1263,6 +1279,10 @@ static int create_raw_packet_qp_tir(struct mlx5_ib_dev *dev, if (tunnel_offload_en) MLX5_SET(tirc, tirc, tunneled_offload_en, 1); + if (dev->rep) + MLX5_SET(tirc, tirc, self_lb_block, + MLX5_TIRC_SELF_LB_BLOCK_BLOCK_UNICAST_); + err = mlx5_core_create_tir(dev->mdev, in, inlen, &rq->tirn); kvfree(in); @@ -1554,6 +1574,10 @@ static int create_rss_raw_qp_tir(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp, MLX5_SET(rx_hash_field_select, hfso, selected_fields, selected_fields); create_tir: + if (dev->rep) + MLX5_SET(tirc, tirc, self_lb_block, + MLX5_TIRC_SELF_LB_BLOCK_BLOCK_UNICAST_); + err = mlx5_core_create_tir(dev->mdev, in, inlen, &qp->rss_qp.tirn); if (err) diff --git a/drivers/infiniband/hw/usnic/usnic_transport.c b/drivers/infiniband/hw/usnic/usnic_transport.c index de318389a301..67de94343cb4 100644 --- a/drivers/infiniband/hw/usnic/usnic_transport.c +++ b/drivers/infiniband/hw/usnic/usnic_transport.c @@ -174,14 +174,13 @@ void usnic_transport_put_socket(struct socket *sock) int usnic_transport_sock_get_addr(struct socket *sock, int *proto, uint32_t *addr, uint16_t *port) { - int len; int err; struct sockaddr_in sock_addr; err = sock->ops->getname(sock, (struct sockaddr *)&sock_addr, - &len, 0); - if (err) + 0); + if (err < 0) return err; if (sock_addr.sin_family != AF_INET) diff --git a/drivers/isdn/mISDN/socket.c b/drivers/isdn/mISDN/socket.c index c5603d1a07d6..1f8f489b4167 100644 --- a/drivers/isdn/mISDN/socket.c +++ b/drivers/isdn/mISDN/socket.c @@ -560,7 +560,7 @@ done: static int data_sock_getname(struct socket *sock, struct sockaddr *addr, - int *addr_len, int peer) + int peer) { struct sockaddr_mISDN *maddr = (struct sockaddr_mISDN *) addr; struct sock *sk = sock->sk; @@ -570,14 +570,13 @@ data_sock_getname(struct socket *sock, struct sockaddr *addr, lock_sock(sk); - *addr_len = sizeof(*maddr); maddr->family = AF_ISDN; maddr->dev = _pms(sk)->dev->id; maddr->channel = _pms(sk)->ch.nr; maddr->sapi = _pms(sk)->ch.addr & 0xff; maddr->tei = (_pms(sk)->ch.addr >> 8) & 0xff; release_sock(sk); - return 0; + return sizeof(*maddr); } static const struct proto_ops data_sock_ops = { diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig index 944ec3c9282c..08b85215c2be 100644 --- a/drivers/net/Kconfig +++ b/drivers/net/Kconfig @@ -149,9 +149,9 @@ config MACVTAP config IPVLAN tristate "IP-VLAN support" depends on INET - depends on IPV6 + depends on IPV6 || !IPV6 depends on NETFILTER - depends on NET_L3_MASTER_DEV + select NET_L3_MASTER_DEV ---help--- This allows one to create virtual devices off of a main interface and packets will be delivered based on the dest L3 (IPv6/IPv4 addr) diff --git a/drivers/net/Space.c b/drivers/net/Space.c index 11fe71278f40..3afda6561434 100644 --- a/drivers/net/Space.c +++ b/drivers/net/Space.c @@ -114,12 +114,6 @@ static struct devprobe2 m68k_probes[] __initdata = { #ifdef CONFIG_MVME147_NET /* MVME147 internal Ethernet */ {mvme147lance_probe, 0}, #endif -#ifdef CONFIG_MAC8390 /* NuBus NS8390-based cards */ - {mac8390_probe, 0}, -#endif -#ifdef CONFIG_MAC89x0 - {mac89x0_probe, 0}, -#endif {NULL, 0}, }; diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index c669554d70bb..4c19d23dd282 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -4791,6 +4791,7 @@ static struct pernet_operations bond_net_ops = { .exit = bond_net_exit, .id = &bond_net_id, .size = sizeof(struct bond_net), + .async = true, }; static int __init bonding_init(void) diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c index db830a1141d9..cd16067265dd 100644 --- a/drivers/net/dsa/b53/b53_common.c +++ b/drivers/net/dsa/b53/b53_common.c @@ -852,7 +852,7 @@ void b53_get_ethtool_stats(struct dsa_switch *ds, int port, uint64_t *data) } EXPORT_SYMBOL(b53_get_ethtool_stats); -int b53_get_sset_count(struct dsa_switch *ds) +int b53_get_sset_count(struct dsa_switch *ds, int port) { struct b53_device *dev = ds->priv; diff --git a/drivers/net/dsa/b53/b53_priv.h b/drivers/net/dsa/b53/b53_priv.h index d954cf36ecd8..1187ebd79287 100644 --- a/drivers/net/dsa/b53/b53_priv.h +++ b/drivers/net/dsa/b53/b53_priv.h @@ -288,7 +288,7 @@ void b53_imp_vlan_setup(struct dsa_switch *ds, int cpu_port); int b53_configure_vlan(struct dsa_switch *ds); void b53_get_strings(struct dsa_switch *ds, int port, uint8_t *data); void b53_get_ethtool_stats(struct dsa_switch *ds, int port, uint64_t *data); -int b53_get_sset_count(struct dsa_switch *ds); +int b53_get_sset_count(struct dsa_switch *ds, int port); int b53_br_join(struct dsa_switch *ds, int port, struct net_device *bridge); void b53_br_leave(struct dsa_switch *ds, int port, struct net_device *bridge); void b53_br_set_stp_state(struct dsa_switch *ds, int port, u8 state); diff --git a/drivers/net/dsa/dsa_loop.c b/drivers/net/dsa/dsa_loop.c index 7aa84ee4e771..f77be9f85cb3 100644 --- a/drivers/net/dsa/dsa_loop.c +++ b/drivers/net/dsa/dsa_loop.c @@ -86,7 +86,7 @@ static int dsa_loop_setup(struct dsa_switch *ds) return 0; } -static int dsa_loop_get_sset_count(struct dsa_switch *ds) +static int dsa_loop_get_sset_count(struct dsa_switch *ds, int port) { return __DSA_LOOP_CNT_MAX; } diff --git a/drivers/net/dsa/lan9303-core.c b/drivers/net/dsa/lan9303-core.c index 6171c0853ff1..fefa454f3e56 100644 --- a/drivers/net/dsa/lan9303-core.c +++ b/drivers/net/dsa/lan9303-core.c @@ -1007,7 +1007,7 @@ static void lan9303_get_ethtool_stats(struct dsa_switch *ds, int port, } } -static int lan9303_get_sset_count(struct dsa_switch *ds) +static int lan9303_get_sset_count(struct dsa_switch *ds, int port) { return ARRAY_SIZE(lan9303_mib); } diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c index 663b0d5b982b..bcb3e6c734f2 100644 --- a/drivers/net/dsa/microchip/ksz_common.c +++ b/drivers/net/dsa/microchip/ksz_common.c @@ -439,7 +439,7 @@ static void ksz_disable_port(struct dsa_switch *ds, int port, ksz_port_cfg(dev, port, REG_PORT_CTRL_0, PORT_MAC_LOOPBACK, true); } -static int ksz_sset_count(struct dsa_switch *ds) +static int ksz_sset_count(struct dsa_switch *ds, int port) { return TOTAL_SWITCH_COUNTER_NUM; } diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c index 8a0bb000d056..511ca134f13f 100644 --- a/drivers/net/dsa/mt7530.c +++ b/drivers/net/dsa/mt7530.c @@ -604,7 +604,7 @@ mt7530_get_ethtool_stats(struct dsa_switch *ds, int port, } static int -mt7530_get_sset_count(struct dsa_switch *ds) +mt7530_get_sset_count(struct dsa_switch *ds, int port) { return ARRAY_SIZE(mt7530_mib); } diff --git a/drivers/net/dsa/mv88e6xxx/Kconfig b/drivers/net/dsa/mv88e6xxx/Kconfig index 1aaa7a95ebc4..ae9e7f7cb31c 100644 --- a/drivers/net/dsa/mv88e6xxx/Kconfig +++ b/drivers/net/dsa/mv88e6xxx/Kconfig @@ -18,3 +18,13 @@ config NET_DSA_MV88E6XXX_GLOBAL2 It is required on most chips. If the chip you compile the support for doesn't have such registers set, say N here. In doubt, say Y. + +config NET_DSA_MV88E6XXX_PTP + bool "PTP support for Marvell 88E6xxx" + default n + depends on NET_DSA_MV88E6XXX_GLOBAL2 + imply NETWORK_PHY_TIMESTAMPING + imply PTP_1588_CLOCK + help + Say Y to enable PTP hardware timestamping on Marvell 88E6xxx switch + chips that support it. diff --git a/drivers/net/dsa/mv88e6xxx/Makefile b/drivers/net/dsa/mv88e6xxx/Makefile index 58a4a0014e59..50de304abe2f 100644 --- a/drivers/net/dsa/mv88e6xxx/Makefile +++ b/drivers/net/dsa/mv88e6xxx/Makefile @@ -5,6 +5,10 @@ mv88e6xxx-objs += global1.o mv88e6xxx-objs += global1_atu.o mv88e6xxx-objs += global1_vtu.o mv88e6xxx-$(CONFIG_NET_DSA_MV88E6XXX_GLOBAL2) += global2.o +mv88e6xxx-$(CONFIG_NET_DSA_MV88E6XXX_GLOBAL2) += global2_avb.o +mv88e6xxx-$(CONFIG_NET_DSA_MV88E6XXX_GLOBAL2) += global2_scratch.o +mv88e6xxx-$(CONFIG_NET_DSA_MV88E6XXX_PTP) += hwtstamp.o mv88e6xxx-objs += phy.o mv88e6xxx-objs += port.o +mv88e6xxx-$(CONFIG_NET_DSA_MV88E6XXX_PTP) += ptp.o mv88e6xxx-objs += serdes.o diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index eb328bade225..cfd53632a655 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -36,8 +36,10 @@ #include "chip.h" #include "global1.h" #include "global2.h" +#include "hwtstamp.h" #include "phy.h" #include "port.h" +#include "ptp.h" #include "serdes.h" static void assert_reg_lock(struct mv88e6xxx_chip *chip) @@ -251,9 +253,8 @@ static void mv88e6xxx_g1_irq_unmask(struct irq_data *d) chip->g1_irq.masked &= ~(1 << n); } -static irqreturn_t mv88e6xxx_g1_irq_thread_fn(int irq, void *dev_id) +static irqreturn_t mv88e6xxx_g1_irq_thread_work(struct mv88e6xxx_chip *chip) { - struct mv88e6xxx_chip *chip = dev_id; unsigned int nhandled = 0; unsigned int sub_irq; unsigned int n; @@ -278,6 +279,13 @@ out: return (nhandled > 0 ? IRQ_HANDLED : IRQ_NONE); } +static irqreturn_t mv88e6xxx_g1_irq_thread_fn(int irq, void *dev_id) +{ + struct mv88e6xxx_chip *chip = dev_id; + + return mv88e6xxx_g1_irq_thread_work(chip); +} + static void mv88e6xxx_g1_irq_bus_lock(struct irq_data *d) { struct mv88e6xxx_chip *chip = irq_data_get_irq_chip_data(d); @@ -333,7 +341,7 @@ static const struct irq_domain_ops mv88e6xxx_g1_irq_domain_ops = { .xlate = irq_domain_xlate_twocell, }; -static void mv88e6xxx_g1_irq_free(struct mv88e6xxx_chip *chip) +static void mv88e6xxx_g1_irq_free_common(struct mv88e6xxx_chip *chip) { int irq, virq; u16 mask; @@ -342,8 +350,6 @@ static void mv88e6xxx_g1_irq_free(struct mv88e6xxx_chip *chip) mask &= ~GENMASK(chip->g1_irq.nirqs, 0); mv88e6xxx_g1_write(chip, MV88E6XXX_G1_CTL1, mask); - free_irq(chip->irq, chip); - for (irq = 0; irq < chip->g1_irq.nirqs; irq++) { virq = irq_find_mapping(chip->g1_irq.domain, irq); irq_dispose_mapping(virq); @@ -352,7 +358,14 @@ static void mv88e6xxx_g1_irq_free(struct mv88e6xxx_chip *chip) irq_domain_remove(chip->g1_irq.domain); } -static int mv88e6xxx_g1_irq_setup(struct mv88e6xxx_chip *chip) +static void mv88e6xxx_g1_irq_free(struct mv88e6xxx_chip *chip) +{ + mv88e6xxx_g1_irq_free(chip); + + free_irq(chip->irq, chip); +} + +static int mv88e6xxx_g1_irq_setup_common(struct mv88e6xxx_chip *chip) { int err, irq, virq; u16 reg, mask; @@ -385,13 +398,6 @@ static int mv88e6xxx_g1_irq_setup(struct mv88e6xxx_chip *chip) if (err) goto out_disable; - err = request_threaded_irq(chip->irq, NULL, - mv88e6xxx_g1_irq_thread_fn, - IRQF_ONESHOT | IRQF_TRIGGER_FALLING, - dev_name(chip->dev), chip); - if (err) - goto out_disable; - return 0; out_disable: @@ -409,6 +415,62 @@ out_mapping: return err; } +static int mv88e6xxx_g1_irq_setup(struct mv88e6xxx_chip *chip) +{ + int err; + + err = mv88e6xxx_g1_irq_setup_common(chip); + if (err) + return err; + + err = request_threaded_irq(chip->irq, NULL, + mv88e6xxx_g1_irq_thread_fn, + IRQF_ONESHOT | IRQF_TRIGGER_FALLING, + dev_name(chip->dev), chip); + if (err) + mv88e6xxx_g1_irq_free_common(chip); + + return err; +} + +static void mv88e6xxx_irq_poll(struct kthread_work *work) +{ + struct mv88e6xxx_chip *chip = container_of(work, + struct mv88e6xxx_chip, + irq_poll_work.work); + mv88e6xxx_g1_irq_thread_work(chip); + + kthread_queue_delayed_work(chip->kworker, &chip->irq_poll_work, + msecs_to_jiffies(100)); +} + +static int mv88e6xxx_irq_poll_setup(struct mv88e6xxx_chip *chip) +{ + int err; + + err = mv88e6xxx_g1_irq_setup_common(chip); + if (err) + return err; + + kthread_init_delayed_work(&chip->irq_poll_work, + mv88e6xxx_irq_poll); + + chip->kworker = kthread_create_worker(0, dev_name(chip->dev)); + if (IS_ERR(chip->kworker)) + return PTR_ERR(chip->kworker); + + kthread_queue_delayed_work(chip->kworker, &chip->irq_poll_work, + msecs_to_jiffies(100)); + + return 0; +} + +static void mv88e6xxx_irq_poll_free(struct mv88e6xxx_chip *chip) +{ + kthread_cancel_delayed_work_sync(&chip->irq_poll_work); + kthread_destroy_worker(chip->kworker); +} + int mv88e6xxx_wait(struct mv88e6xxx_chip *chip, int addr, int reg, u16 mask) { int i; @@ -604,7 +666,7 @@ static uint64_t _mv88e6xxx_get_ethtool_stat(struct mv88e6xxx_chip *chip, return UINT64_MAX; low = reg; - if (s->sizeof_stat == 4) { + if (s->size == 4) { err = mv88e6xxx_port_read(chip, port, s->reg + 1, ®); if (err) return UINT64_MAX; @@ -617,7 +679,7 @@ static uint64_t _mv88e6xxx_get_ethtool_stat(struct mv88e6xxx_chip *chip, case STATS_TYPE_BANK0: reg |= s->reg | histogram; mv88e6xxx_g1_stats_read(chip, reg, &low); - if (s->sizeof_stat == 8) + if (s->size == 8) mv88e6xxx_g1_stats_read(chip, reg + 1, &high); break; default: @@ -627,8 +689,8 @@ static uint64_t _mv88e6xxx_get_ethtool_stat(struct mv88e6xxx_chip *chip, return value; } -static void mv88e6xxx_stats_get_strings(struct mv88e6xxx_chip *chip, - uint8_t *data, int types) +static int mv88e6xxx_stats_get_strings(struct mv88e6xxx_chip *chip, + uint8_t *data, int types) { struct mv88e6xxx_hw_stat *stat; int i, j; @@ -641,29 +703,41 @@ static void mv88e6xxx_stats_get_strings(struct mv88e6xxx_chip *chip, j++; } } + + return j; } -static void mv88e6095_stats_get_strings(struct mv88e6xxx_chip *chip, - uint8_t *data) +static int mv88e6095_stats_get_strings(struct mv88e6xxx_chip *chip, + uint8_t *data) { - mv88e6xxx_stats_get_strings(chip, data, - STATS_TYPE_BANK0 | STATS_TYPE_PORT); + return mv88e6xxx_stats_get_strings(chip, data, + STATS_TYPE_BANK0 | STATS_TYPE_PORT); } -static void mv88e6320_stats_get_strings(struct mv88e6xxx_chip *chip, - uint8_t *data) +static int mv88e6320_stats_get_strings(struct mv88e6xxx_chip *chip, + uint8_t *data) { - mv88e6xxx_stats_get_strings(chip, data, - STATS_TYPE_BANK0 | STATS_TYPE_BANK1); + return mv88e6xxx_stats_get_strings(chip, data, + STATS_TYPE_BANK0 | STATS_TYPE_BANK1); } static void mv88e6xxx_get_strings(struct dsa_switch *ds, int port, uint8_t *data) { struct mv88e6xxx_chip *chip = ds->priv; + int count = 0; + + mutex_lock(&chip->reg_lock); if (chip->info->ops->stats_get_strings) - chip->info->ops->stats_get_strings(chip, data); + count = chip->info->ops->stats_get_strings(chip, data); + + if (chip->info->ops->serdes_get_strings) { + data += count * ETH_GSTRING_LEN; + chip->info->ops->serdes_get_strings(chip, port, data); + } + + mutex_unlock(&chip->reg_lock); } static int mv88e6xxx_stats_get_sset_count(struct mv88e6xxx_chip *chip, @@ -692,19 +766,34 @@ static int mv88e6320_stats_get_sset_count(struct mv88e6xxx_chip *chip) STATS_TYPE_BANK1); } -static int mv88e6xxx_get_sset_count(struct dsa_switch *ds) +static int mv88e6xxx_get_sset_count(struct dsa_switch *ds, int port) { struct mv88e6xxx_chip *chip = ds->priv; + int serdes_count = 0; + int count = 0; + mutex_lock(&chip->reg_lock); if (chip->info->ops->stats_get_sset_count) - return chip->info->ops->stats_get_sset_count(chip); + count = chip->info->ops->stats_get_sset_count(chip); + if (count < 0) + goto out; - return 0; + if (chip->info->ops->serdes_get_sset_count) + serdes_count = chip->info->ops->serdes_get_sset_count(chip, + port); + if (serdes_count < 0) + count = serdes_count; + else + count += serdes_count; +out: + mutex_unlock(&chip->reg_lock); + + return count; } -static void mv88e6xxx_stats_get_stats(struct mv88e6xxx_chip *chip, int port, - uint64_t *data, int types, - u16 bank1_select, u16 histogram) +static int mv88e6xxx_stats_get_stats(struct mv88e6xxx_chip *chip, int port, + uint64_t *data, int types, + u16 bank1_select, u16 histogram) { struct mv88e6xxx_hw_stat *stat; int i, j; @@ -712,24 +801,28 @@ static void mv88e6xxx_stats_get_stats(struct mv88e6xxx_chip *chip, int port, for (i = 0, j = 0; i < ARRAY_SIZE(mv88e6xxx_hw_stats); i++) { stat = &mv88e6xxx_hw_stats[i]; if (stat->type & types) { + mutex_lock(&chip->reg_lock); data[j] = _mv88e6xxx_get_ethtool_stat(chip, stat, port, bank1_select, histogram); + mutex_unlock(&chip->reg_lock); + j++; } } + return j; } -static void mv88e6095_stats_get_stats(struct mv88e6xxx_chip *chip, int port, - uint64_t *data) +static int mv88e6095_stats_get_stats(struct mv88e6xxx_chip *chip, int port, + uint64_t *data) { return mv88e6xxx_stats_get_stats(chip, port, data, STATS_TYPE_BANK0 | STATS_TYPE_PORT, 0, MV88E6XXX_G1_STATS_OP_HIST_RX_TX); } -static void mv88e6320_stats_get_stats(struct mv88e6xxx_chip *chip, int port, - uint64_t *data) +static int mv88e6320_stats_get_stats(struct mv88e6xxx_chip *chip, int port, + uint64_t *data) { return mv88e6xxx_stats_get_stats(chip, port, data, STATS_TYPE_BANK0 | STATS_TYPE_BANK1, @@ -737,8 +830,8 @@ static void mv88e6320_stats_get_stats(struct mv88e6xxx_chip *chip, int port, MV88E6XXX_G1_STATS_OP_HIST_RX_TX); } -static void mv88e6390_stats_get_stats(struct mv88e6xxx_chip *chip, int port, - uint64_t *data) +static int mv88e6390_stats_get_stats(struct mv88e6xxx_chip *chip, int port, + uint64_t *data) { return mv88e6xxx_stats_get_stats(chip, port, data, STATS_TYPE_BANK0 | STATS_TYPE_BANK1, @@ -749,8 +842,15 @@ static void mv88e6390_stats_get_stats(struct mv88e6xxx_chip *chip, int port, static void mv88e6xxx_get_stats(struct mv88e6xxx_chip *chip, int port, uint64_t *data) { + int count = 0; + if (chip->info->ops->stats_get_stats) - chip->info->ops->stats_get_stats(chip, port, data); + count = chip->info->ops->stats_get_stats(chip, port, data); + + if (chip->info->ops->serdes_get_stats) { + data += count; + chip->info->ops->serdes_get_stats(chip, port, data); + } } static void mv88e6xxx_get_ethtool_stats(struct dsa_switch *ds, int port, @@ -762,14 +862,13 @@ static void mv88e6xxx_get_ethtool_stats(struct dsa_switch *ds, int port, mutex_lock(&chip->reg_lock); ret = mv88e6xxx_stats_snapshot(chip, port); - if (ret < 0) { - mutex_unlock(&chip->reg_lock); + mutex_unlock(&chip->reg_lock); + + if (ret < 0) return; - } mv88e6xxx_get_stats(chip, port, data); - mutex_unlock(&chip->reg_lock); } static int mv88e6xxx_stats_set_histogram(struct mv88e6xxx_chip *chip) @@ -1433,7 +1532,9 @@ static int mv88e6xxx_port_db_dump_fid(struct mv88e6xxx_chip *chip, eth_broadcast_addr(addr.mac); do { + mutex_lock(&chip->reg_lock); err = mv88e6xxx_g1_atu_getnext(chip, fid, &addr); + mutex_unlock(&chip->reg_lock); if (err) return err; @@ -1466,7 +1567,10 @@ static int mv88e6xxx_port_db_dump(struct mv88e6xxx_chip *chip, int port, int err; /* Dump port's default Filtering Information Database (VLAN ID 0) */ + mutex_lock(&chip->reg_lock); err = mv88e6xxx_port_get_fid(chip, port, &fid); + mutex_unlock(&chip->reg_lock); + if (err) return err; @@ -1476,7 +1580,9 @@ static int mv88e6xxx_port_db_dump(struct mv88e6xxx_chip *chip, int port, /* Dump VLANs' Filtering Information Databases */ do { + mutex_lock(&chip->reg_lock); err = mv88e6xxx_vtu_getnext(chip, &vlan); + mutex_unlock(&chip->reg_lock); if (err) return err; @@ -1496,13 +1602,8 @@ static int mv88e6xxx_port_fdb_dump(struct dsa_switch *ds, int port, dsa_fdb_dump_cb_t *cb, void *data) { struct mv88e6xxx_chip *chip = ds->priv; - int err; - mutex_lock(&chip->reg_lock); - err = mv88e6xxx_port_db_dump(chip, port, cb, data); - mutex_unlock(&chip->reg_lock); - - return err; + return mv88e6xxx_port_db_dump(chip, port, cb, data); } static int mv88e6xxx_bridge_map(struct mv88e6xxx_chip *chip, @@ -2092,6 +2193,17 @@ static int mv88e6xxx_setup(struct dsa_switch *ds) if (err) goto unlock; + /* Setup PTP Hardware Clock and timestamping */ + if (chip->info->ptp_support) { + err = mv88e6xxx_ptp_setup(chip); + if (err) + goto unlock; + + err = mv88e6xxx_hwtstamp_setup(chip); + if (err) + goto unlock; + } + unlock: mutex_unlock(&chip->reg_lock); @@ -2148,6 +2260,15 @@ static int mv88e6xxx_mdio_register(struct mv88e6xxx_chip *chip, struct mii_bus *bus; int err; + if (external) { + mutex_lock(&chip->reg_lock); + err = mv88e6xxx_g2_scratch_gpio_set_smi(chip, true); + mutex_unlock(&chip->reg_lock); + + if (err) + return err; + } + bus = devm_mdiobus_alloc_size(chip->dev, sizeof(*mdio_bus)); if (!bus) return -ENOMEM; @@ -2472,6 +2593,7 @@ static const struct mv88e6xxx_ops mv88e6141_ops = { .reset = mv88e6352_g1_reset, .vtu_getnext = mv88e6352_g1_vtu_getnext, .vtu_loadpurge = mv88e6352_g1_vtu_loadpurge, + .gpio_ops = &mv88e6352_gpio_ops, }; static const struct mv88e6xxx_ops mv88e6161_ops = { @@ -2602,6 +2724,7 @@ static const struct mv88e6xxx_ops mv88e6172_ops = { .vtu_getnext = mv88e6352_g1_vtu_getnext, .vtu_loadpurge = mv88e6352_g1_vtu_loadpurge, .serdes_power = mv88e6352_serdes_power, + .gpio_ops = &mv88e6352_gpio_ops, }; static const struct mv88e6xxx_ops mv88e6175_ops = { @@ -2673,6 +2796,7 @@ static const struct mv88e6xxx_ops mv88e6176_ops = { .vtu_getnext = mv88e6352_g1_vtu_getnext, .vtu_loadpurge = mv88e6352_g1_vtu_loadpurge, .serdes_power = mv88e6352_serdes_power, + .gpio_ops = &mv88e6352_gpio_ops, }; static const struct mv88e6xxx_ops mv88e6185_ops = { @@ -2736,6 +2860,7 @@ static const struct mv88e6xxx_ops mv88e6190_ops = { .vtu_getnext = mv88e6390_g1_vtu_getnext, .vtu_loadpurge = mv88e6390_g1_vtu_loadpurge, .serdes_power = mv88e6390_serdes_power, + .gpio_ops = &mv88e6352_gpio_ops, }; static const struct mv88e6xxx_ops mv88e6190x_ops = { @@ -2771,6 +2896,7 @@ static const struct mv88e6xxx_ops mv88e6190x_ops = { .vtu_getnext = mv88e6390_g1_vtu_getnext, .vtu_loadpurge = mv88e6390_g1_vtu_loadpurge, .serdes_power = mv88e6390_serdes_power, + .gpio_ops = &mv88e6352_gpio_ops, }; static const struct mv88e6xxx_ops mv88e6191_ops = { @@ -2843,6 +2969,8 @@ static const struct mv88e6xxx_ops mv88e6240_ops = { .vtu_getnext = mv88e6352_g1_vtu_getnext, .vtu_loadpurge = mv88e6352_g1_vtu_loadpurge, .serdes_power = mv88e6352_serdes_power, + .gpio_ops = &mv88e6352_gpio_ops, + .avb_ops = &mv88e6352_avb_ops, }; static const struct mv88e6xxx_ops mv88e6290_ops = { @@ -2879,6 +3007,8 @@ static const struct mv88e6xxx_ops mv88e6290_ops = { .vtu_getnext = mv88e6390_g1_vtu_getnext, .vtu_loadpurge = mv88e6390_g1_vtu_loadpurge, .serdes_power = mv88e6390_serdes_power, + .gpio_ops = &mv88e6352_gpio_ops, + .avb_ops = &mv88e6390_avb_ops, }; static const struct mv88e6xxx_ops mv88e6320_ops = { @@ -2913,6 +3043,8 @@ static const struct mv88e6xxx_ops mv88e6320_ops = { .reset = mv88e6352_g1_reset, .vtu_getnext = mv88e6185_g1_vtu_getnext, .vtu_loadpurge = mv88e6185_g1_vtu_loadpurge, + .gpio_ops = &mv88e6352_gpio_ops, + .avb_ops = &mv88e6352_avb_ops, }; static const struct mv88e6xxx_ops mv88e6321_ops = { @@ -2945,6 +3077,8 @@ static const struct mv88e6xxx_ops mv88e6321_ops = { .reset = mv88e6352_g1_reset, .vtu_getnext = mv88e6185_g1_vtu_getnext, .vtu_loadpurge = mv88e6185_g1_vtu_loadpurge, + .gpio_ops = &mv88e6352_gpio_ops, + .avb_ops = &mv88e6352_avb_ops, }; static const struct mv88e6xxx_ops mv88e6341_ops = { @@ -2981,6 +3115,8 @@ static const struct mv88e6xxx_ops mv88e6341_ops = { .reset = mv88e6352_g1_reset, .vtu_getnext = mv88e6352_g1_vtu_getnext, .vtu_loadpurge = mv88e6352_g1_vtu_loadpurge, + .gpio_ops = &mv88e6352_gpio_ops, + .avb_ops = &mv88e6390_avb_ops, }; static const struct mv88e6xxx_ops mv88e6350_ops = { @@ -3049,6 +3185,7 @@ static const struct mv88e6xxx_ops mv88e6351_ops = { .reset = mv88e6352_g1_reset, .vtu_getnext = mv88e6352_g1_vtu_getnext, .vtu_loadpurge = mv88e6352_g1_vtu_loadpurge, + .avb_ops = &mv88e6352_avb_ops, }; static const struct mv88e6xxx_ops mv88e6352_ops = { @@ -3086,6 +3223,11 @@ static const struct mv88e6xxx_ops mv88e6352_ops = { .vtu_getnext = mv88e6352_g1_vtu_getnext, .vtu_loadpurge = mv88e6352_g1_vtu_loadpurge, .serdes_power = mv88e6352_serdes_power, + .gpio_ops = &mv88e6352_gpio_ops, + .avb_ops = &mv88e6352_avb_ops, + .serdes_get_sset_count = mv88e6352_serdes_get_sset_count, + .serdes_get_strings = mv88e6352_serdes_get_strings, + .serdes_get_stats = mv88e6352_serdes_get_stats, }; static const struct mv88e6xxx_ops mv88e6390_ops = { @@ -3124,6 +3266,8 @@ static const struct mv88e6xxx_ops mv88e6390_ops = { .vtu_getnext = mv88e6390_g1_vtu_getnext, .vtu_loadpurge = mv88e6390_g1_vtu_loadpurge, .serdes_power = mv88e6390_serdes_power, + .gpio_ops = &mv88e6352_gpio_ops, + .avb_ops = &mv88e6390_avb_ops, }; static const struct mv88e6xxx_ops mv88e6390x_ops = { @@ -3162,6 +3306,8 @@ static const struct mv88e6xxx_ops mv88e6390x_ops = { .vtu_getnext = mv88e6390_g1_vtu_getnext, .vtu_loadpurge = mv88e6390_g1_vtu_loadpurge, .serdes_power = mv88e6390_serdes_power, + .gpio_ops = &mv88e6352_gpio_ops, + .avb_ops = &mv88e6390_avb_ops, }; static const struct mv88e6xxx_info mv88e6xxx_table[] = { @@ -3267,6 +3413,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .name = "Marvell 88E6341", .num_databases = 4096, .num_ports = 6, + .num_gpio = 11, .max_vid = 4095, .port_base_addr = 0x10, .global1_addr = 0x1b, @@ -3346,6 +3493,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .name = "Marvell 88E6172", .num_databases = 4096, .num_ports = 7, + .num_gpio = 15, .max_vid = 4095, .port_base_addr = 0x10, .global1_addr = 0x1b, @@ -3386,6 +3534,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .name = "Marvell 88E6176", .num_databases = 4096, .num_ports = 7, + .num_gpio = 15, .max_vid = 4095, .port_base_addr = 0x10, .global1_addr = 0x1b, @@ -3424,6 +3573,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .name = "Marvell 88E6190", .num_databases = 4096, .num_ports = 11, /* 10 + Z80 */ + .num_gpio = 16, .max_vid = 8191, .port_base_addr = 0x0, .global1_addr = 0x1b, @@ -3444,6 +3594,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .name = "Marvell 88E6190X", .num_databases = 4096, .num_ports = 11, /* 10 + Z80 */ + .num_gpio = 16, .max_vid = 8191, .port_base_addr = 0x0, .global1_addr = 0x1b, @@ -3475,6 +3626,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .pvt = true, .multi_chip = true, .tag_protocol = DSA_TAG_PROTO_DSA, + .ptp_support = true, .ops = &mv88e6191_ops, }, @@ -3484,6 +3636,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .name = "Marvell 88E6240", .num_databases = 4096, .num_ports = 7, + .num_gpio = 15, .max_vid = 4095, .port_base_addr = 0x10, .global1_addr = 0x1b, @@ -3495,6 +3648,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .pvt = true, .multi_chip = true, .tag_protocol = DSA_TAG_PROTO_EDSA, + .ptp_support = true, .ops = &mv88e6240_ops, }, @@ -3504,6 +3658,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .name = "Marvell 88E6290", .num_databases = 4096, .num_ports = 11, /* 10 + Z80 */ + .num_gpio = 16, .max_vid = 8191, .port_base_addr = 0x0, .global1_addr = 0x1b, @@ -3515,6 +3670,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .pvt = true, .multi_chip = true, .tag_protocol = DSA_TAG_PROTO_DSA, + .ptp_support = true, .ops = &mv88e6290_ops, }, @@ -3524,6 +3680,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .name = "Marvell 88E6320", .num_databases = 4096, .num_ports = 7, + .num_gpio = 15, .max_vid = 4095, .port_base_addr = 0x10, .global1_addr = 0x1b, @@ -3534,6 +3691,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .pvt = true, .multi_chip = true, .tag_protocol = DSA_TAG_PROTO_EDSA, + .ptp_support = true, .ops = &mv88e6320_ops, }, @@ -3543,6 +3701,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .name = "Marvell 88E6321", .num_databases = 4096, .num_ports = 7, + .num_gpio = 15, .max_vid = 4095, .port_base_addr = 0x10, .global1_addr = 0x1b, @@ -3552,6 +3711,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .atu_move_port_mask = 0xf, .multi_chip = true, .tag_protocol = DSA_TAG_PROTO_EDSA, + .ptp_support = true, .ops = &mv88e6321_ops, }, @@ -3561,6 +3721,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .name = "Marvell 88E6341", .num_databases = 4096, .num_ports = 6, + .num_gpio = 11, .max_vid = 4095, .port_base_addr = 0x10, .global1_addr = 0x1b, @@ -3571,6 +3732,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .pvt = true, .multi_chip = true, .tag_protocol = DSA_TAG_PROTO_EDSA, + .ptp_support = true, .ops = &mv88e6341_ops, }, @@ -3620,6 +3782,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .name = "Marvell 88E6352", .num_databases = 4096, .num_ports = 7, + .num_gpio = 15, .max_vid = 4095, .port_base_addr = 0x10, .global1_addr = 0x1b, @@ -3631,6 +3794,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .pvt = true, .multi_chip = true, .tag_protocol = DSA_TAG_PROTO_EDSA, + .ptp_support = true, .ops = &mv88e6352_ops, }, [MV88E6390] = { @@ -3639,6 +3803,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .name = "Marvell 88E6390", .num_databases = 4096, .num_ports = 11, /* 10 + Z80 */ + .num_gpio = 16, .max_vid = 8191, .port_base_addr = 0x0, .global1_addr = 0x1b, @@ -3650,6 +3815,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .pvt = true, .multi_chip = true, .tag_protocol = DSA_TAG_PROTO_DSA, + .ptp_support = true, .ops = &mv88e6390_ops, }, [MV88E6390X] = { @@ -3658,6 +3824,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .name = "Marvell 88E6390X", .num_databases = 4096, .num_ports = 11, /* 10 + Z80 */ + .num_gpio = 16, .max_vid = 8191, .port_base_addr = 0x0, .global1_addr = 0x1b, @@ -3669,6 +3836,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .pvt = true, .multi_chip = true, .tag_protocol = DSA_TAG_PROTO_DSA, + .ptp_support = true, .ops = &mv88e6390x_ops, }, }; @@ -3880,6 +4048,11 @@ static const struct dsa_switch_ops mv88e6xxx_switch_ops = { .port_mdb_del = mv88e6xxx_port_mdb_del, .crosschip_bridge_join = mv88e6xxx_crosschip_bridge_join, .crosschip_bridge_leave = mv88e6xxx_crosschip_bridge_leave, + .port_hwtstamp_set = mv88e6xxx_port_hwtstamp_set, + .port_hwtstamp_get = mv88e6xxx_port_hwtstamp_get, + .port_txtstamp = mv88e6xxx_port_txtstamp, + .port_rxtstamp = mv88e6xxx_port_rxtstamp, + .get_ts_info = mv88e6xxx_get_ts_info, }; static struct dsa_switch_driver mv88e6xxx_switch_drv = { @@ -3959,33 +4132,34 @@ static int mv88e6xxx_probe(struct mdio_device *mdiodev) goto out; } - if (chip->irq > 0) { - /* Has to be performed before the MDIO bus is created, - * because the PHYs will link there interrupts to these - * interrupt controllers - */ - mutex_lock(&chip->reg_lock); + /* Has to be performed before the MDIO bus is created, because + * the PHYs will link there interrupts to these interrupt + * controllers + */ + mutex_lock(&chip->reg_lock); + if (chip->irq > 0) err = mv88e6xxx_g1_irq_setup(chip); - mutex_unlock(&chip->reg_lock); - - if (err) - goto out; - - if (chip->info->g2_irqs > 0) { - err = mv88e6xxx_g2_irq_setup(chip); - if (err) - goto out_g1_irq; - } + else + err = mv88e6xxx_irq_poll_setup(chip); + mutex_unlock(&chip->reg_lock); - err = mv88e6xxx_g1_atu_prob_irq_setup(chip); - if (err) - goto out_g2_irq; + if (err) + goto out; - err = mv88e6xxx_g1_vtu_prob_irq_setup(chip); + if (chip->info->g2_irqs > 0) { + err = mv88e6xxx_g2_irq_setup(chip); if (err) - goto out_g1_atu_prob_irq; + goto out_g1_irq; } + err = mv88e6xxx_g1_atu_prob_irq_setup(chip); + if (err) + goto out_g2_irq; + + err = mv88e6xxx_g1_vtu_prob_irq_setup(chip); + if (err) + goto out_g1_atu_prob_irq; + err = mv88e6xxx_mdios_register(chip, np); if (err) goto out_g1_vtu_prob_irq; @@ -3999,20 +4173,19 @@ static int mv88e6xxx_probe(struct mdio_device *mdiodev) out_mdio: mv88e6xxx_mdios_unregister(chip); out_g1_vtu_prob_irq: - if (chip->irq > 0) - mv88e6xxx_g1_vtu_prob_irq_free(chip); + mv88e6xxx_g1_vtu_prob_irq_free(chip); out_g1_atu_prob_irq: - if (chip->irq > 0) - mv88e6xxx_g1_atu_prob_irq_free(chip); + mv88e6xxx_g1_atu_prob_irq_free(chip); out_g2_irq: - if (chip->info->g2_irqs > 0 && chip->irq > 0) + if (chip->info->g2_irqs > 0) mv88e6xxx_g2_irq_free(chip); out_g1_irq: - if (chip->irq > 0) { - mutex_lock(&chip->reg_lock); + mutex_lock(&chip->reg_lock); + if (chip->irq > 0) mv88e6xxx_g1_irq_free(chip); - mutex_unlock(&chip->reg_lock); - } + else + mv88e6xxx_irq_poll_free(chip); + mutex_unlock(&chip->reg_lock); out: return err; } @@ -4022,6 +4195,11 @@ static void mv88e6xxx_remove(struct mdio_device *mdiodev) struct dsa_switch *ds = dev_get_drvdata(&mdiodev->dev); struct mv88e6xxx_chip *chip = ds->priv; + if (chip->info->ptp_support) { + mv88e6xxx_hwtstamp_free(chip); + mv88e6xxx_ptp_free(chip); + } + mv88e6xxx_phy_destroy(chip); mv88e6xxx_unregister_switch(chip); mv88e6xxx_mdios_unregister(chip); diff --git a/drivers/net/dsa/mv88e6xxx/chip.h b/drivers/net/dsa/mv88e6xxx/chip.h index 3dba6e90adcf..26b9a618cdee 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.h +++ b/drivers/net/dsa/mv88e6xxx/chip.h @@ -15,7 +15,10 @@ #include <linux/if_vlan.h> #include <linux/irq.h> #include <linux/gpio/consumer.h> +#include <linux/kthread.h> #include <linux/phy.h> +#include <linux/ptp_clock_kernel.h> +#include <linux/timecounter.h> #include <net/dsa.h> #ifndef UINT64_MAX @@ -39,6 +42,8 @@ #define MV88E6XXX_MAX_PVT_SWITCHES 32 #define MV88E6XXX_MAX_PVT_PORTS 16 +#define MV88E6XXX_MAX_GPIO 16 + enum mv88e6xxx_egress_mode { MV88E6XXX_EGRESS_MODE_UNMODIFIED, MV88E6XXX_EGRESS_MODE_UNTAGGED, @@ -105,6 +110,7 @@ struct mv88e6xxx_info { const char *name; unsigned int num_databases; unsigned int num_ports; + unsigned int num_gpio; unsigned int max_vid; unsigned int port_base_addr; unsigned int global1_addr; @@ -126,6 +132,9 @@ struct mv88e6xxx_info { */ u8 atu_move_port_mask; const struct mv88e6xxx_ops *ops; + + /* Supports PTP */ + bool ptp_support; }; struct mv88e6xxx_atu_entry { @@ -146,6 +155,8 @@ struct mv88e6xxx_vtu_entry { struct mv88e6xxx_bus_ops; struct mv88e6xxx_irq_ops; +struct mv88e6xxx_gpio_ops; +struct mv88e6xxx_avb_ops; struct mv88e6xxx_irq { u16 masked; @@ -154,6 +165,36 @@ struct mv88e6xxx_irq { unsigned int nirqs; }; +/* state flags for mv88e6xxx_port_hwtstamp::state */ +enum { + MV88E6XXX_HWTSTAMP_ENABLED, + MV88E6XXX_HWTSTAMP_TX_IN_PROGRESS, +}; + +struct mv88e6xxx_port_hwtstamp { + /* Port index */ + int port_id; + + /* Timestamping state */ + unsigned long state; + + /* Resources for receive timestamping */ + struct sk_buff_head rx_queue; + struct sk_buff_head rx_queue2; + + /* Resources for transmit timestamping */ + unsigned long tx_tstamp_start; + struct sk_buff *tx_skb; + u16 tx_seq_id; + + /* Current timestamp configuration */ + struct hwtstamp_config tstamp_config; +}; + +struct mv88e6xxx_port { + u64 serdes_stats[2]; +}; + struct mv88e6xxx_chip { const struct mv88e6xxx_info *info; @@ -207,8 +248,34 @@ struct mv88e6xxx_chip { int irq; int device_irq; int watchdog_irq; + int atu_prob_irq; int vtu_prob_irq; + struct kthread_worker *kworker; + struct kthread_delayed_work irq_poll_work; + + /* GPIO resources */ + u8 gpio_data[2]; + + /* This cyclecounter abstracts the switch PTP time. + * reg_lock must be held for any operation that read()s. + */ + struct cyclecounter tstamp_cc; + struct timecounter tstamp_tc; + struct delayed_work overflow_work; + + struct ptp_clock *ptp_clock; + struct ptp_clock_info ptp_clock_info; + struct delayed_work tai_event_work; + struct ptp_pin_desc pin_config[MV88E6XXX_MAX_GPIO]; + u16 trig_config; + u16 evcap_config; + + /* Per-port timestamping resources. */ + struct mv88e6xxx_port_hwtstamp port_hwtstamp[DSA_MAX_PORTS]; + + /* Array of port structures. */ + struct mv88e6xxx_port ports[DSA_MAX_PORTS]; }; struct mv88e6xxx_bus_ops { @@ -327,9 +394,9 @@ struct mv88e6xxx_ops { /* Return the number of strings describing statistics */ int (*stats_get_sset_count)(struct mv88e6xxx_chip *chip); - void (*stats_get_strings)(struct mv88e6xxx_chip *chip, uint8_t *data); - void (*stats_get_stats)(struct mv88e6xxx_chip *chip, int port, - uint64_t *data); + int (*stats_get_strings)(struct mv88e6xxx_chip *chip, uint8_t *data); + int (*stats_get_stats)(struct mv88e6xxx_chip *chip, int port, + uint64_t *data); int (*set_cpu_port)(struct mv88e6xxx_chip *chip, int port); int (*set_egress_port)(struct mv88e6xxx_chip *chip, int port); const struct mv88e6xxx_irq_ops *watchdog_ops; @@ -339,11 +406,24 @@ struct mv88e6xxx_ops { /* Power on/off a SERDES interface */ int (*serdes_power)(struct mv88e6xxx_chip *chip, int port, bool on); + /* Statistics from the SERDES interface */ + int (*serdes_get_sset_count)(struct mv88e6xxx_chip *chip, int port); + void (*serdes_get_strings)(struct mv88e6xxx_chip *chip, int port, + uint8_t *data); + void (*serdes_get_stats)(struct mv88e6xxx_chip *chip, int port, + uint64_t *data); + /* VLAN Translation Unit operations */ int (*vtu_getnext)(struct mv88e6xxx_chip *chip, struct mv88e6xxx_vtu_entry *entry); int (*vtu_loadpurge)(struct mv88e6xxx_chip *chip, struct mv88e6xxx_vtu_entry *entry); + + /* GPIO operations */ + const struct mv88e6xxx_gpio_ops *gpio_ops; + + /* Interface to the AVB/PTP registers */ + const struct mv88e6xxx_avb_ops *avb_ops; }; struct mv88e6xxx_irq_ops { @@ -355,13 +435,49 @@ struct mv88e6xxx_irq_ops { void (*irq_free)(struct mv88e6xxx_chip *chip); }; +struct mv88e6xxx_gpio_ops { + /* Get/set data on GPIO pin */ + int (*get_data)(struct mv88e6xxx_chip *chip, unsigned int pin); + int (*set_data)(struct mv88e6xxx_chip *chip, unsigned int pin, + int value); + + /* get/set GPIO direction */ + int (*get_dir)(struct mv88e6xxx_chip *chip, unsigned int pin); + int (*set_dir)(struct mv88e6xxx_chip *chip, unsigned int pin, + bool input); + + /* get/set GPIO pin control */ + int (*get_pctl)(struct mv88e6xxx_chip *chip, unsigned int pin, + int *func); + int (*set_pctl)(struct mv88e6xxx_chip *chip, unsigned int pin, + int func); +}; + +struct mv88e6xxx_avb_ops { + /* Access port-scoped Precision Time Protocol registers */ + int (*port_ptp_read)(struct mv88e6xxx_chip *chip, int port, int addr, + u16 *data, int len); + int (*port_ptp_write)(struct mv88e6xxx_chip *chip, int port, int addr, + u16 data); + + /* Access global Precision Time Protocol registers */ + int (*ptp_read)(struct mv88e6xxx_chip *chip, int addr, u16 *data, + int len); + int (*ptp_write)(struct mv88e6xxx_chip *chip, int addr, u16 data); + + /* Access global Time Application Interface registers */ + int (*tai_read)(struct mv88e6xxx_chip *chip, int addr, u16 *data, + int len); + int (*tai_write)(struct mv88e6xxx_chip *chip, int addr, u16 data); +}; + #define STATS_TYPE_PORT BIT(0) #define STATS_TYPE_BANK0 BIT(1) #define STATS_TYPE_BANK1 BIT(2) struct mv88e6xxx_hw_stat { char string[ETH_GSTRING_LEN]; - int sizeof_stat; + size_t size; int reg; int type; }; @@ -386,6 +502,11 @@ static inline u16 mv88e6xxx_port_mask(struct mv88e6xxx_chip *chip) return GENMASK(mv88e6xxx_num_ports(chip) - 1, 0); } +static inline unsigned int mv88e6xxx_num_gpio(struct mv88e6xxx_chip *chip) +{ + return chip->info->num_gpio; +} + int mv88e6xxx_read(struct mv88e6xxx_chip *chip, int addr, int reg, u16 *val); int mv88e6xxx_write(struct mv88e6xxx_chip *chip, int addr, int reg, u16 val); int mv88e6xxx_update(struct mv88e6xxx_chip *chip, int addr, int reg, diff --git a/drivers/net/dsa/mv88e6xxx/global2.c b/drivers/net/dsa/mv88e6xxx/global2.c index af0727877825..5f370f1fc7c4 100644 --- a/drivers/net/dsa/mv88e6xxx/global2.c +++ b/drivers/net/dsa/mv88e6xxx/global2.c @@ -20,22 +20,22 @@ #include "global1.h" /* for MV88E6XXX_G1_STS_IRQ_DEVICE */ #include "global2.h" -static int mv88e6xxx_g2_read(struct mv88e6xxx_chip *chip, int reg, u16 *val) +int mv88e6xxx_g2_read(struct mv88e6xxx_chip *chip, int reg, u16 *val) { return mv88e6xxx_read(chip, chip->info->global2_addr, reg, val); } -static int mv88e6xxx_g2_write(struct mv88e6xxx_chip *chip, int reg, u16 val) +int mv88e6xxx_g2_write(struct mv88e6xxx_chip *chip, int reg, u16 val) { return mv88e6xxx_write(chip, chip->info->global2_addr, reg, val); } -static int mv88e6xxx_g2_update(struct mv88e6xxx_chip *chip, int reg, u16 update) +int mv88e6xxx_g2_update(struct mv88e6xxx_chip *chip, int reg, u16 update) { return mv88e6xxx_update(chip, chip->info->global2_addr, reg, update); } -static int mv88e6xxx_g2_wait(struct mv88e6xxx_chip *chip, int reg, u16 mask) +int mv88e6xxx_g2_wait(struct mv88e6xxx_chip *chip, int reg, u16 mask) { return mv88e6xxx_wait(chip, chip->info->global2_addr, reg, mask); } @@ -798,6 +798,7 @@ int mv88e6xxx_g2_smi_phy_write(struct mv88e6xxx_chip *chip, struct mii_bus *bus, val); } +/* Offset 0x1B: Watchdog Control */ static int mv88e6097_watchdog_action(struct mv88e6xxx_chip *chip, int irq) { u16 reg; diff --git a/drivers/net/dsa/mv88e6xxx/global2.h b/drivers/net/dsa/mv88e6xxx/global2.h index 669f59017b12..aa3f0a736966 100644 --- a/drivers/net/dsa/mv88e6xxx/global2.h +++ b/drivers/net/dsa/mv88e6xxx/global2.h @@ -149,7 +149,26 @@ #define MV88E6390_G2_EEPROM_ADDR_MASK 0xffff /* Offset 0x16: AVB Command Register */ -#define MV88E6352_G2_AVB_CMD 0x16 +#define MV88E6352_G2_AVB_CMD 0x16 +#define MV88E6352_G2_AVB_CMD_BUSY 0x8000 +#define MV88E6352_G2_AVB_CMD_OP_READ 0x4000 +#define MV88E6352_G2_AVB_CMD_OP_READ_INCR 0x6000 +#define MV88E6352_G2_AVB_CMD_OP_WRITE 0x3000 +#define MV88E6390_G2_AVB_CMD_OP_READ 0x0000 +#define MV88E6390_G2_AVB_CMD_OP_READ_INCR 0x4000 +#define MV88E6390_G2_AVB_CMD_OP_WRITE 0x6000 +#define MV88E6352_G2_AVB_CMD_PORT_MASK 0x0f00 +#define MV88E6352_G2_AVB_CMD_PORT_TAIGLOBAL 0xe +#define MV88E6352_G2_AVB_CMD_PORT_PTPGLOBAL 0xf +#define MV88E6390_G2_AVB_CMD_PORT_MASK 0x1f00 +#define MV88E6390_G2_AVB_CMD_PORT_TAIGLOBAL 0x1e +#define MV88E6390_G2_AVB_CMD_PORT_PTPGLOBAL 0x1f +#define MV88E6352_G2_AVB_CMD_BLOCK_PTP 0 +#define MV88E6352_G2_AVB_CMD_BLOCK_AVB 1 +#define MV88E6352_G2_AVB_CMD_BLOCK_QAV 2 +#define MV88E6352_G2_AVB_CMD_BLOCK_QVB 3 +#define MV88E6352_G2_AVB_CMD_BLOCK_MASK 0x00e0 +#define MV88E6352_G2_AVB_CMD_ADDR_MASK 0x001f /* Offset 0x17: AVB Data Register */ #define MV88E6352_G2_AVB_DATA 0x17 @@ -223,6 +242,40 @@ #define MV88E6352_G2_NOEGR_POLICY 0x2000 #define MV88E6390_G2_LAG_ID_4 0x2000 +/* Scratch/Misc registers accessed through MV88E6XXX_G2_SCRATCH_MISC */ +/* Offset 0x02: Misc Configuration */ +#define MV88E6352_G2_SCRATCH_MISC_CFG 0x02 +#define MV88E6352_G2_SCRATCH_MISC_CFG_NORMALSMI 0x80 +/* Offset 0x60-0x61: GPIO Configuration */ +#define MV88E6352_G2_SCRATCH_GPIO_CFG0 0x60 +#define MV88E6352_G2_SCRATCH_GPIO_CFG1 0x61 +/* Offset 0x62-0x63: GPIO Direction */ +#define MV88E6352_G2_SCRATCH_GPIO_DIR0 0x62 +#define MV88E6352_G2_SCRATCH_GPIO_DIR1 0x63 +#define MV88E6352_G2_SCRATCH_GPIO_DIR_OUT 0 +#define MV88E6352_G2_SCRATCH_GPIO_DIR_IN 1 +/* Offset 0x64-0x65: GPIO Data */ +#define MV88E6352_G2_SCRATCH_GPIO_DATA0 0x64 +#define MV88E6352_G2_SCRATCH_GPIO_DATA1 0x65 +/* Offset 0x68-0x6F: GPIO Pin Control */ +#define MV88E6352_G2_SCRATCH_GPIO_PCTL0 0x68 +#define MV88E6352_G2_SCRATCH_GPIO_PCTL1 0x69 +#define MV88E6352_G2_SCRATCH_GPIO_PCTL2 0x6A +#define MV88E6352_G2_SCRATCH_GPIO_PCTL3 0x6B +#define MV88E6352_G2_SCRATCH_GPIO_PCTL4 0x6C +#define MV88E6352_G2_SCRATCH_GPIO_PCTL5 0x6D +#define MV88E6352_G2_SCRATCH_GPIO_PCTL6 0x6E +#define MV88E6352_G2_SCRATCH_GPIO_PCTL7 0x6F +#define MV88E6352_G2_SCRATCH_CONFIG_DATA0 0x70 +#define MV88E6352_G2_SCRATCH_CONFIG_DATA1 0x71 +#define MV88E6352_G2_SCRATCH_CONFIG_DATA1_NO_CPU BIT(2) +#define MV88E6352_G2_SCRATCH_CONFIG_DATA2 0x72 +#define MV88E6352_G2_SCRATCH_CONFIG_DATA2_P0_MODE_MASK 0x3 + +#define MV88E6352_G2_SCRATCH_GPIO_PCTL_GPIO 0 +#define MV88E6352_G2_SCRATCH_GPIO_PCTL_TRIG 1 +#define MV88E6352_G2_SCRATCH_GPIO_PCTL_EVREQ 2 + #ifdef CONFIG_NET_DSA_MV88E6XXX_GLOBAL2 static inline int mv88e6xxx_g2_require(struct mv88e6xxx_chip *chip) @@ -230,6 +283,11 @@ static inline int mv88e6xxx_g2_require(struct mv88e6xxx_chip *chip) return 0; } +int mv88e6xxx_g2_read(struct mv88e6xxx_chip *chip, int reg, u16 *val); +int mv88e6xxx_g2_write(struct mv88e6xxx_chip *chip, int reg, u16 val); +int mv88e6xxx_g2_update(struct mv88e6xxx_chip *chip, int reg, u16 update); +int mv88e6xxx_g2_wait(struct mv88e6xxx_chip *chip, int reg, u16 mask); + int mv88e6352_g2_irl_init_all(struct mv88e6xxx_chip *chip, int port); int mv88e6390_g2_irl_init_all(struct mv88e6xxx_chip *chip, int port); @@ -267,6 +325,14 @@ int mv88e6xxx_g2_pot_clear(struct mv88e6xxx_chip *chip); extern const struct mv88e6xxx_irq_ops mv88e6097_watchdog_ops; extern const struct mv88e6xxx_irq_ops mv88e6390_watchdog_ops; +extern const struct mv88e6xxx_avb_ops mv88e6352_avb_ops; +extern const struct mv88e6xxx_avb_ops mv88e6390_avb_ops; + +extern const struct mv88e6xxx_gpio_ops mv88e6352_gpio_ops; + +int mv88e6xxx_g2_scratch_gpio_set_smi(struct mv88e6xxx_chip *chip, + bool external); + #else /* !CONFIG_NET_DSA_MV88E6XXX_GLOBAL2 */ static inline int mv88e6xxx_g2_require(struct mv88e6xxx_chip *chip) @@ -279,6 +345,26 @@ static inline int mv88e6xxx_g2_require(struct mv88e6xxx_chip *chip) return 0; } +static inline int mv88e6xxx_g2_read(struct mv88e6xxx_chip *chip, int reg, u16 *val) +{ + return -EOPNOTSUPP; +} + +static inline int mv88e6xxx_g2_write(struct mv88e6xxx_chip *chip, int reg, u16 val) +{ + return -EOPNOTSUPP; +} + +static inline int mv88e6xxx_g2_update(struct mv88e6xxx_chip *chip, int reg, u16 update) +{ + return -EOPNOTSUPP; +} + +static inline int mv88e6xxx_g2_wait(struct mv88e6xxx_chip *chip, int reg, u16 mask) +{ + return -EOPNOTSUPP; +} + static inline int mv88e6352_g2_irl_init_all(struct mv88e6xxx_chip *chip, int port) { @@ -382,6 +468,17 @@ static inline int mv88e6xxx_g2_pot_clear(struct mv88e6xxx_chip *chip) static const struct mv88e6xxx_irq_ops mv88e6097_watchdog_ops = {}; static const struct mv88e6xxx_irq_ops mv88e6390_watchdog_ops = {}; +static const struct mv88e6xxx_avb_ops mv88e6352_avb_ops = {}; +static const struct mv88e6xxx_avb_ops mv88e6390_avb_ops = {}; + +static const struct mv88e6xxx_gpio_ops mv88e6352_gpio_ops = {}; + +static inline int mv88e6xxx_g2_scratch_gpio_set_smi(struct mv88e6xxx_chip *chip, + bool external) +{ + return -EOPNOTSUPP; +} + #endif /* CONFIG_NET_DSA_MV88E6XXX_GLOBAL2 */ #endif /* _MV88E6XXX_GLOBAL2_H */ diff --git a/drivers/net/dsa/mv88e6xxx/global2_avb.c b/drivers/net/dsa/mv88e6xxx/global2_avb.c new file mode 100644 index 000000000000..2e398ccb88ca --- /dev/null +++ b/drivers/net/dsa/mv88e6xxx/global2_avb.c @@ -0,0 +1,193 @@ +/* + * Marvell 88E6xxx Switch Global 2 Registers support + * + * Copyright (c) 2008 Marvell Semiconductor + * + * Copyright (c) 2016-2017 Savoir-faire Linux Inc. + * Vivien Didelot <vivien.didelot@savoirfairelinux.com> + * + * Copyright (c) 2017 National Instruments + * Brandon Streiff <brandon.streiff@ni.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 "global2.h" + +/* Offset 0x16: AVB Command Register + * Offset 0x17: AVB Data Register + * + * There are two different versions of this register interface: + * "6352": 3-bit "op" field, 4-bit "port" field. + * "6390": 2-bit "op" field, 5-bit "port" field. + * + * The "op" codes are different between the two, as well as the special + * port fields for global PTP and TAI configuration. + */ + +/* mv88e6xxx_g2_avb_read -- Read one or multiple 16-bit words. + * The hardware supports snapshotting up to four contiguous registers. + */ +static int mv88e6xxx_g2_avb_read(struct mv88e6xxx_chip *chip, u16 readop, + u16 *data, int len) +{ + int err; + int i; + + /* Hardware can only snapshot four words. */ + if (len > 4) + return -E2BIG; + + err = mv88e6xxx_g2_update(chip, MV88E6352_G2_AVB_CMD, readop); + if (err) + return err; + + for (i = 0; i < len; ++i) { + err = mv88e6xxx_g2_read(chip, MV88E6352_G2_AVB_DATA, + &data[i]); + if (err) + return err; + } + + return 0; +} + +/* mv88e6xxx_g2_avb_write -- Write one 16-bit word. */ +static int mv88e6xxx_g2_avb_write(struct mv88e6xxx_chip *chip, u16 writeop, + u16 data) +{ + int err; + + err = mv88e6xxx_g2_write(chip, MV88E6352_G2_AVB_DATA, data); + if (err) + return err; + + return mv88e6xxx_g2_update(chip, MV88E6352_G2_AVB_CMD, writeop); +} + +static int mv88e6352_g2_avb_port_ptp_read(struct mv88e6xxx_chip *chip, + int port, int addr, u16 *data, + int len) +{ + u16 readop = (len == 1 ? MV88E6352_G2_AVB_CMD_OP_READ : + MV88E6352_G2_AVB_CMD_OP_READ_INCR) | + (port << 8) | (MV88E6352_G2_AVB_CMD_BLOCK_PTP << 5) | + addr; + + return mv88e6xxx_g2_avb_read(chip, readop, data, len); +} + +static int mv88e6352_g2_avb_port_ptp_write(struct mv88e6xxx_chip *chip, + int port, int addr, u16 data) +{ + u16 writeop = MV88E6352_G2_AVB_CMD_OP_WRITE | (port << 8) | + (MV88E6352_G2_AVB_CMD_BLOCK_PTP << 5) | addr; + + return mv88e6xxx_g2_avb_write(chip, writeop, data); +} + +static int mv88e6352_g2_avb_ptp_read(struct mv88e6xxx_chip *chip, int addr, + u16 *data, int len) +{ + return mv88e6352_g2_avb_port_ptp_read(chip, + MV88E6352_G2_AVB_CMD_PORT_PTPGLOBAL, + addr, data, len); +} + +static int mv88e6352_g2_avb_ptp_write(struct mv88e6xxx_chip *chip, int addr, + u16 data) +{ + return mv88e6352_g2_avb_port_ptp_write(chip, + MV88E6352_G2_AVB_CMD_PORT_PTPGLOBAL, + addr, data); +} + +static int mv88e6352_g2_avb_tai_read(struct mv88e6xxx_chip *chip, int addr, + u16 *data, int len) +{ + return mv88e6352_g2_avb_port_ptp_read(chip, + MV88E6352_G2_AVB_CMD_PORT_TAIGLOBAL, + addr, data, len); +} + +static int mv88e6352_g2_avb_tai_write(struct mv88e6xxx_chip *chip, int addr, + u16 data) +{ + return mv88e6352_g2_avb_port_ptp_write(chip, + MV88E6352_G2_AVB_CMD_PORT_TAIGLOBAL, + addr, data); +} + +const struct mv88e6xxx_avb_ops mv88e6352_avb_ops = { + .port_ptp_read = mv88e6352_g2_avb_port_ptp_read, + .port_ptp_write = mv88e6352_g2_avb_port_ptp_write, + .ptp_read = mv88e6352_g2_avb_ptp_read, + .ptp_write = mv88e6352_g2_avb_ptp_write, + .tai_read = mv88e6352_g2_avb_tai_read, + .tai_write = mv88e6352_g2_avb_tai_write, +}; + +static int mv88e6390_g2_avb_port_ptp_read(struct mv88e6xxx_chip *chip, + int port, int addr, u16 *data, + int len) +{ + u16 readop = (len == 1 ? MV88E6390_G2_AVB_CMD_OP_READ : + MV88E6390_G2_AVB_CMD_OP_READ_INCR) | + (port << 8) | (MV88E6352_G2_AVB_CMD_BLOCK_PTP << 5) | + addr; + + return mv88e6xxx_g2_avb_read(chip, readop, data, len); +} + +static int mv88e6390_g2_avb_port_ptp_write(struct mv88e6xxx_chip *chip, + int port, int addr, u16 data) +{ + u16 writeop = MV88E6390_G2_AVB_CMD_OP_WRITE | (port << 8) | + (MV88E6352_G2_AVB_CMD_BLOCK_PTP << 5) | addr; + + return mv88e6xxx_g2_avb_write(chip, writeop, data); +} + +static int mv88e6390_g2_avb_ptp_read(struct mv88e6xxx_chip *chip, int addr, + u16 *data, int len) +{ + return mv88e6390_g2_avb_port_ptp_read(chip, + MV88E6390_G2_AVB_CMD_PORT_PTPGLOBAL, + addr, data, len); +} + +static int mv88e6390_g2_avb_ptp_write(struct mv88e6xxx_chip *chip, int addr, + u16 data) +{ + return mv88e6390_g2_avb_port_ptp_write(chip, + MV88E6390_G2_AVB_CMD_PORT_PTPGLOBAL, + addr, data); +} + +static int mv88e6390_g2_avb_tai_read(struct mv88e6xxx_chip *chip, int addr, + u16 *data, int len) +{ + return mv88e6390_g2_avb_port_ptp_read(chip, + MV88E6390_G2_AVB_CMD_PORT_TAIGLOBAL, + addr, data, len); +} + +static int mv88e6390_g2_avb_tai_write(struct mv88e6xxx_chip *chip, int addr, + u16 data) +{ + return mv88e6390_g2_avb_port_ptp_write(chip, + MV88E6390_G2_AVB_CMD_PORT_TAIGLOBAL, + addr, data); +} + +const struct mv88e6xxx_avb_ops mv88e6390_avb_ops = { + .port_ptp_read = mv88e6390_g2_avb_port_ptp_read, + .port_ptp_write = mv88e6390_g2_avb_port_ptp_write, + .ptp_read = mv88e6390_g2_avb_ptp_read, + .ptp_write = mv88e6390_g2_avb_ptp_write, + .tai_read = mv88e6390_g2_avb_tai_read, + .tai_write = mv88e6390_g2_avb_tai_write, +}; diff --git a/drivers/net/dsa/mv88e6xxx/global2_scratch.c b/drivers/net/dsa/mv88e6xxx/global2_scratch.c new file mode 100644 index 000000000000..3f92b8892dc7 --- /dev/null +++ b/drivers/net/dsa/mv88e6xxx/global2_scratch.c @@ -0,0 +1,291 @@ +/* + * Marvell 88E6xxx Switch Global 2 Scratch & Misc Registers support + * + * Copyright (c) 2008 Marvell Semiconductor + * + * Copyright (c) 2017 National Instruments + * Brandon Streiff <brandon.streiff@ni.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 "chip.h" +#include "global2.h" + +/* Offset 0x1A: Scratch and Misc. Register */ +static int mv88e6xxx_g2_scratch_read(struct mv88e6xxx_chip *chip, int reg, + u8 *data) +{ + u16 value; + int err; + + err = mv88e6xxx_g2_write(chip, MV88E6XXX_G2_SCRATCH_MISC_MISC, + reg << 8); + if (err) + return err; + + err = mv88e6xxx_g2_read(chip, MV88E6XXX_G2_SCRATCH_MISC_MISC, &value); + if (err) + return err; + + *data = (value & MV88E6XXX_G2_SCRATCH_MISC_DATA_MASK); + + return 0; +} + +static int mv88e6xxx_g2_scratch_write(struct mv88e6xxx_chip *chip, int reg, + u8 data) +{ + u16 value = (reg << 8) | data; + + return mv88e6xxx_g2_update(chip, MV88E6XXX_G2_SCRATCH_MISC_MISC, value); +} + +/** + * mv88e6xxx_g2_scratch_gpio_get_bit - get a bit + * @chip: chip private data + * @nr: bit index + * @set: is bit set? + */ +static int mv88e6xxx_g2_scratch_get_bit(struct mv88e6xxx_chip *chip, + int base_reg, unsigned int offset, + int *set) +{ + int reg = base_reg + (offset / 8); + u8 mask = (1 << (offset & 0x7)); + u8 val; + int err; + + err = mv88e6xxx_g2_scratch_read(chip, reg, &val); + if (err) + return err; + + *set = !!(mask & val); + + return 0; +} + +/** + * mv88e6xxx_g2_scratch_gpio_set_bit - set (or clear) a bit + * @chip: chip private data + * @nr: bit index + * @set: set if true, clear if false + * + * Helper function for dealing with the direction and data registers. + */ +static int mv88e6xxx_g2_scratch_set_bit(struct mv88e6xxx_chip *chip, + int base_reg, unsigned int offset, + int set) +{ + int reg = base_reg + (offset / 8); + u8 mask = (1 << (offset & 0x7)); + u8 val; + int err; + + err = mv88e6xxx_g2_scratch_read(chip, reg, &val); + if (err) + return err; + + if (set) + val |= mask; + else + val &= ~mask; + + return mv88e6xxx_g2_scratch_write(chip, reg, val); +} + +/** + * mv88e6352_g2_scratch_gpio_get_data - get data on gpio pin + * @chip: chip private data + * @pin: gpio index + * + * Return: 0 for low, 1 for high, negative error + */ +static int mv88e6352_g2_scratch_gpio_get_data(struct mv88e6xxx_chip *chip, + unsigned int pin) +{ + int val = 0; + int err; + + err = mv88e6xxx_g2_scratch_get_bit(chip, + MV88E6352_G2_SCRATCH_GPIO_DATA0, + pin, &val); + if (err) + return err; + + return val; +} + +/** + * mv88e6352_g2_scratch_gpio_set_data - set data on gpio pin + * @chip: chip private data + * @pin: gpio index + * @value: value to set + */ +static int mv88e6352_g2_scratch_gpio_set_data(struct mv88e6xxx_chip *chip, + unsigned int pin, int value) +{ + u8 mask = (1 << (pin & 0x7)); + int offset = (pin / 8); + int reg; + + reg = MV88E6352_G2_SCRATCH_GPIO_DATA0 + offset; + + if (value) + chip->gpio_data[offset] |= mask; + else + chip->gpio_data[offset] &= ~mask; + + return mv88e6xxx_g2_scratch_write(chip, reg, chip->gpio_data[offset]); +} + +/** + * mv88e6352_g2_scratch_gpio_get_dir - get direction of gpio pin + * @chip: chip private data + * @pin: gpio index + * + * Return: 0 for output, 1 for input (same as GPIOF_DIR_XXX). + */ +static int mv88e6352_g2_scratch_gpio_get_dir(struct mv88e6xxx_chip *chip, + unsigned int pin) +{ + int val = 0; + int err; + + err = mv88e6xxx_g2_scratch_get_bit(chip, + MV88E6352_G2_SCRATCH_GPIO_DIR0, + pin, &val); + if (err) + return err; + + return val; +} + +/** + * mv88e6352_g2_scratch_gpio_set_dir - set direction of gpio pin + * @chip: chip private data + * @pin: gpio index + */ +static int mv88e6352_g2_scratch_gpio_set_dir(struct mv88e6xxx_chip *chip, + unsigned int pin, bool input) +{ + int value = (input ? MV88E6352_G2_SCRATCH_GPIO_DIR_IN : + MV88E6352_G2_SCRATCH_GPIO_DIR_OUT); + + return mv88e6xxx_g2_scratch_set_bit(chip, + MV88E6352_G2_SCRATCH_GPIO_DIR0, + pin, value); +} + +/** + * mv88e6352_g2_scratch_gpio_get_pctl - get pin control setting + * @chip: chip private data + * @pin: gpio index + * @func: function number + * + * Note that the function numbers themselves may vary by chipset. + */ +static int mv88e6352_g2_scratch_gpio_get_pctl(struct mv88e6xxx_chip *chip, + unsigned int pin, int *func) +{ + int reg = MV88E6352_G2_SCRATCH_GPIO_PCTL0 + (pin / 2); + int offset = (pin & 0x1) ? 4 : 0; + u8 mask = (0x7 << offset); + int err; + u8 val; + + err = mv88e6xxx_g2_scratch_read(chip, reg, &val); + if (err) + return err; + + *func = (val & mask) >> offset; + + return 0; +} + +/** + * mv88e6352_g2_scratch_gpio_set_pctl - set pin control setting + * @chip: chip private data + * @pin: gpio index + * @func: function number + */ +static int mv88e6352_g2_scratch_gpio_set_pctl(struct mv88e6xxx_chip *chip, + unsigned int pin, int func) +{ + int reg = MV88E6352_G2_SCRATCH_GPIO_PCTL0 + (pin / 2); + int offset = (pin & 0x1) ? 4 : 0; + u8 mask = (0x7 << offset); + int err; + u8 val; + + err = mv88e6xxx_g2_scratch_read(chip, reg, &val); + if (err) + return err; + + val = (val & ~mask) | ((func & mask) << offset); + + return mv88e6xxx_g2_scratch_write(chip, reg, val); +} + +const struct mv88e6xxx_gpio_ops mv88e6352_gpio_ops = { + .get_data = mv88e6352_g2_scratch_gpio_get_data, + .set_data = mv88e6352_g2_scratch_gpio_set_data, + .get_dir = mv88e6352_g2_scratch_gpio_get_dir, + .set_dir = mv88e6352_g2_scratch_gpio_set_dir, + .get_pctl = mv88e6352_g2_scratch_gpio_get_pctl, + .set_pctl = mv88e6352_g2_scratch_gpio_set_pctl, +}; + +/** + * mv88e6xxx_g2_gpio_set_smi - set gpio muxing for external smi + * @chip: chip private data + * @external: set mux for external smi, or free for gpio usage + * + * Some mv88e6xxx models have GPIO pins that may be configured as + * an external SMI interface, or they may be made free for other + * GPIO uses. + */ +int mv88e6xxx_g2_scratch_gpio_set_smi(struct mv88e6xxx_chip *chip, + bool external) +{ + int misc_cfg = MV88E6352_G2_SCRATCH_MISC_CFG; + int config_data1 = MV88E6352_G2_SCRATCH_CONFIG_DATA1; + int config_data2 = MV88E6352_G2_SCRATCH_CONFIG_DATA2; + bool no_cpu; + u8 p0_mode; + int err; + u8 val; + + err = mv88e6xxx_g2_scratch_read(chip, config_data2, &val); + if (err) + return err; + + p0_mode = val & MV88E6352_G2_SCRATCH_CONFIG_DATA2_P0_MODE_MASK; + + if (p0_mode == 0x01 || p0_mode == 0x02) + return -EBUSY; + + err = mv88e6xxx_g2_scratch_read(chip, config_data1, &val); + if (err) + return err; + + no_cpu = !!(val & MV88E6352_G2_SCRATCH_CONFIG_DATA1_NO_CPU); + + err = mv88e6xxx_g2_scratch_read(chip, misc_cfg, &val); + if (err) + return err; + + /* NO_CPU being 0 inverts the meaning of the bit */ + if (!no_cpu) + external = !external; + + if (external) + val |= MV88E6352_G2_SCRATCH_MISC_CFG_NORMALSMI; + else + val &= ~MV88E6352_G2_SCRATCH_MISC_CFG_NORMALSMI; + + return mv88e6xxx_g2_scratch_write(chip, misc_cfg, val); +} diff --git a/drivers/net/dsa/mv88e6xxx/hwtstamp.c b/drivers/net/dsa/mv88e6xxx/hwtstamp.c new file mode 100644 index 000000000000..ac7694c71266 --- /dev/null +++ b/drivers/net/dsa/mv88e6xxx/hwtstamp.c @@ -0,0 +1,576 @@ +/* + * Marvell 88E6xxx Switch hardware timestamping support + * + * Copyright (c) 2008 Marvell Semiconductor + * + * Copyright (c) 2017 National Instruments + * Erik Hons <erik.hons@ni.com> + * Brandon Streiff <brandon.streiff@ni.com> + * Dane Wagner <dane.wagner@ni.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 "chip.h" +#include "global2.h" +#include "hwtstamp.h" +#include "ptp.h" +#include <linux/ptp_classify.h> + +#define SKB_PTP_TYPE(__skb) (*(unsigned int *)((__skb)->cb)) + +static int mv88e6xxx_port_ptp_read(struct mv88e6xxx_chip *chip, int port, + int addr, u16 *data, int len) +{ + if (!chip->info->ops->avb_ops->port_ptp_read) + return -EOPNOTSUPP; + + return chip->info->ops->avb_ops->port_ptp_read(chip, port, addr, + data, len); +} + +static int mv88e6xxx_port_ptp_write(struct mv88e6xxx_chip *chip, int port, + int addr, u16 data) +{ + if (!chip->info->ops->avb_ops->port_ptp_write) + return -EOPNOTSUPP; + + return chip->info->ops->avb_ops->port_ptp_write(chip, port, addr, + data); +} + +static int mv88e6xxx_ptp_write(struct mv88e6xxx_chip *chip, int addr, + u16 data) +{ + if (!chip->info->ops->avb_ops->ptp_write) + return -EOPNOTSUPP; + + return chip->info->ops->avb_ops->ptp_write(chip, addr, data); +} + +/* TX_TSTAMP_TIMEOUT: This limits the time spent polling for a TX + * timestamp. When working properly, hardware will produce a timestamp + * within 1ms. Software may enounter delays due to MDIO contention, so + * the timeout is set accordingly. + */ +#define TX_TSTAMP_TIMEOUT msecs_to_jiffies(20) + +int mv88e6xxx_get_ts_info(struct dsa_switch *ds, int port, + struct ethtool_ts_info *info) +{ + struct mv88e6xxx_chip *chip = ds->priv; + + if (!chip->info->ptp_support) + return -EOPNOTSUPP; + + info->so_timestamping = + SOF_TIMESTAMPING_TX_HARDWARE | + SOF_TIMESTAMPING_RX_HARDWARE | + SOF_TIMESTAMPING_RAW_HARDWARE; + info->phc_index = ptp_clock_index(chip->ptp_clock); + info->tx_types = + (1 << HWTSTAMP_TX_OFF) | + (1 << HWTSTAMP_TX_ON); + info->rx_filters = + (1 << HWTSTAMP_FILTER_NONE) | + (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); + + return 0; +} + +static int mv88e6xxx_set_hwtstamp_config(struct mv88e6xxx_chip *chip, int port, + struct hwtstamp_config *config) +{ + struct mv88e6xxx_port_hwtstamp *ps = &chip->port_hwtstamp[port]; + bool tstamp_enable = false; + u16 port_config0; + int err; + + /* Prevent the TX/RX paths from trying to interact with the + * timestamp hardware while we reconfigure it. + */ + clear_bit_unlock(MV88E6XXX_HWTSTAMP_ENABLED, &ps->state); + + /* reserved for future extensions */ + if (config->flags) + return -EINVAL; + + switch (config->tx_type) { + case HWTSTAMP_TX_OFF: + tstamp_enable = false; + break; + case HWTSTAMP_TX_ON: + tstamp_enable = true; + break; + default: + return -ERANGE; + } + + /* The switch supports timestamping both L2 and L4; one cannot be + * disabled independently of the other. + */ + switch (config->rx_filter) { + case HWTSTAMP_FILTER_NONE: + tstamp_enable = false; + break; + case HWTSTAMP_FILTER_PTP_V2_L4_EVENT: + case HWTSTAMP_FILTER_PTP_V2_L4_SYNC: + case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ: + case HWTSTAMP_FILTER_PTP_V2_L2_EVENT: + case HWTSTAMP_FILTER_PTP_V2_L2_SYNC: + case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ: + case HWTSTAMP_FILTER_PTP_V2_EVENT: + case HWTSTAMP_FILTER_PTP_V2_SYNC: + case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ: + config->rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT; + break; + case HWTSTAMP_FILTER_ALL: + default: + config->rx_filter = HWTSTAMP_FILTER_NONE; + return -ERANGE; + } + + if (tstamp_enable) { + /* Disable transportSpecific value matching, so that packets + * with either 1588 (0) and 802.1AS (1) will be timestamped. + */ + port_config0 = MV88E6XXX_PORT_PTP_CFG0_DISABLE_TSPEC_MATCH; + } else { + /* Disable PTP. This disables both RX and TX timestamping. */ + port_config0 = MV88E6XXX_PORT_PTP_CFG0_DISABLE_PTP; + } + + mutex_lock(&chip->reg_lock); + err = mv88e6xxx_port_ptp_write(chip, port, MV88E6XXX_PORT_PTP_CFG0, + port_config0); + mutex_unlock(&chip->reg_lock); + + if (err < 0) + return err; + + /* Once hardware has been configured, enable timestamp checks + * in the RX/TX paths. + */ + if (tstamp_enable) + set_bit(MV88E6XXX_HWTSTAMP_ENABLED, &ps->state); + + return 0; +} + +int mv88e6xxx_port_hwtstamp_set(struct dsa_switch *ds, int port, + struct ifreq *ifr) +{ + struct mv88e6xxx_chip *chip = ds->priv; + struct mv88e6xxx_port_hwtstamp *ps = &chip->port_hwtstamp[port]; + struct hwtstamp_config config; + int err; + + if (!chip->info->ptp_support) + return -EOPNOTSUPP; + + if (copy_from_user(&config, ifr->ifr_data, sizeof(config))) + return -EFAULT; + + err = mv88e6xxx_set_hwtstamp_config(chip, port, &config); + if (err) + return err; + + /* Save the chosen configuration to be returned later. */ + memcpy(&ps->tstamp_config, &config, sizeof(config)); + + return copy_to_user(ifr->ifr_data, &config, sizeof(config)) ? + -EFAULT : 0; +} + +int mv88e6xxx_port_hwtstamp_get(struct dsa_switch *ds, int port, + struct ifreq *ifr) +{ + struct mv88e6xxx_chip *chip = ds->priv; + struct mv88e6xxx_port_hwtstamp *ps = &chip->port_hwtstamp[port]; + struct hwtstamp_config *config = &ps->tstamp_config; + + if (!chip->info->ptp_support) + return -EOPNOTSUPP; + + return copy_to_user(ifr->ifr_data, config, sizeof(*config)) ? + -EFAULT : 0; +} + +/* Get the start of the PTP header in this skb */ +static u8 *parse_ptp_header(struct sk_buff *skb, unsigned int type) +{ + u8 *data = skb_mac_header(skb); + unsigned int offset = 0; + + if (type & PTP_CLASS_VLAN) + offset += VLAN_HLEN; + + switch (type & PTP_CLASS_PMASK) { + case PTP_CLASS_IPV4: + offset += ETH_HLEN + IPV4_HLEN(data + offset) + UDP_HLEN; + break; + case PTP_CLASS_IPV6: + offset += ETH_HLEN + IP6_HLEN + UDP_HLEN; + break; + case PTP_CLASS_L2: + offset += ETH_HLEN; + break; + default: + return NULL; + } + + /* Ensure that the entire header is present in this packet. */ + if (skb->len + ETH_HLEN < offset + 34) + return NULL; + + return data + offset; +} + +/* Returns a pointer to the PTP header if the caller should time stamp, + * or NULL if the caller should not. + */ +static u8 *mv88e6xxx_should_tstamp(struct mv88e6xxx_chip *chip, int port, + struct sk_buff *skb, unsigned int type) +{ + struct mv88e6xxx_port_hwtstamp *ps = &chip->port_hwtstamp[port]; + u8 *hdr; + + if (!chip->info->ptp_support) + return NULL; + + hdr = parse_ptp_header(skb, type); + if (!hdr) + return NULL; + + if (!test_bit(MV88E6XXX_HWTSTAMP_ENABLED, &ps->state)) + return NULL; + + return hdr; +} + +static int mv88e6xxx_ts_valid(u16 status) +{ + if (!(status & MV88E6XXX_PTP_TS_VALID)) + return 0; + if (status & MV88E6XXX_PTP_TS_STATUS_MASK) + return 0; + return 1; +} + +static int seq_match(struct sk_buff *skb, u16 ts_seqid) +{ + unsigned int type = SKB_PTP_TYPE(skb); + u8 *hdr = parse_ptp_header(skb, type); + __be16 *seqid; + + seqid = (__be16 *)(hdr + OFF_PTP_SEQUENCE_ID); + + return ts_seqid == ntohs(*seqid); +} + +static void mv88e6xxx_get_rxts(struct mv88e6xxx_chip *chip, + struct mv88e6xxx_port_hwtstamp *ps, + struct sk_buff *skb, u16 reg, + struct sk_buff_head *rxq) +{ + u16 buf[4] = { 0 }, status, seq_id; + u64 ns, timelo, timehi; + struct skb_shared_hwtstamps *shwt; + int err; + + mutex_lock(&chip->reg_lock); + err = mv88e6xxx_port_ptp_read(chip, ps->port_id, + reg, buf, ARRAY_SIZE(buf)); + mutex_unlock(&chip->reg_lock); + if (err) + pr_err("failed to get the receive time stamp\n"); + + status = buf[0]; + timelo = buf[1]; + timehi = buf[2]; + seq_id = buf[3]; + + if (status & MV88E6XXX_PTP_TS_VALID) { + mutex_lock(&chip->reg_lock); + err = mv88e6xxx_port_ptp_write(chip, ps->port_id, reg, 0); + mutex_unlock(&chip->reg_lock); + if (err) + pr_err("failed to clear the receive status\n"); + } + /* Since the device can only handle one time stamp at a time, + * we purge any extra frames from the queue. + */ + for ( ; skb; skb = skb_dequeue(rxq)) { + if (mv88e6xxx_ts_valid(status) && seq_match(skb, seq_id)) { + ns = timehi << 16 | timelo; + + mutex_lock(&chip->reg_lock); + ns = timecounter_cyc2time(&chip->tstamp_tc, ns); + mutex_unlock(&chip->reg_lock); + shwt = skb_hwtstamps(skb); + memset(shwt, 0, sizeof(*shwt)); + shwt->hwtstamp = ns_to_ktime(ns); + status &= ~MV88E6XXX_PTP_TS_VALID; + } + netif_rx_ni(skb); + } +} + +static void mv88e6xxx_rxtstamp_work(struct mv88e6xxx_chip *chip, + struct mv88e6xxx_port_hwtstamp *ps) +{ + struct sk_buff *skb; + + skb = skb_dequeue(&ps->rx_queue); + + if (skb) + mv88e6xxx_get_rxts(chip, ps, skb, MV88E6XXX_PORT_PTP_ARR0_STS, + &ps->rx_queue); + + skb = skb_dequeue(&ps->rx_queue2); + if (skb) + mv88e6xxx_get_rxts(chip, ps, skb, MV88E6XXX_PORT_PTP_ARR1_STS, + &ps->rx_queue2); +} + +static int is_pdelay_resp(u8 *msgtype) +{ + return (*msgtype & 0xf) == 3; +} + +bool mv88e6xxx_port_rxtstamp(struct dsa_switch *ds, int port, + struct sk_buff *skb, unsigned int type) +{ + struct mv88e6xxx_port_hwtstamp *ps; + struct mv88e6xxx_chip *chip; + u8 *hdr; + + chip = ds->priv; + ps = &chip->port_hwtstamp[port]; + + if (ps->tstamp_config.rx_filter != HWTSTAMP_FILTER_PTP_V2_EVENT) + return false; + + hdr = mv88e6xxx_should_tstamp(chip, port, skb, type); + if (!hdr) + return false; + + SKB_PTP_TYPE(skb) = type; + + if (is_pdelay_resp(hdr)) + skb_queue_tail(&ps->rx_queue2, skb); + else + skb_queue_tail(&ps->rx_queue, skb); + + ptp_schedule_worker(chip->ptp_clock, 0); + + return true; +} + +static int mv88e6xxx_txtstamp_work(struct mv88e6xxx_chip *chip, + struct mv88e6xxx_port_hwtstamp *ps) +{ + struct skb_shared_hwtstamps shhwtstamps; + u16 departure_block[4], status; + struct sk_buff *tmp_skb; + u32 time_raw; + int err; + u64 ns; + + if (!ps->tx_skb) + return 0; + + mutex_lock(&chip->reg_lock); + err = mv88e6xxx_port_ptp_read(chip, ps->port_id, + MV88E6XXX_PORT_PTP_DEP_STS, + departure_block, + ARRAY_SIZE(departure_block)); + mutex_unlock(&chip->reg_lock); + + if (err) + goto free_and_clear_skb; + + if (!(departure_block[0] & MV88E6XXX_PTP_TS_VALID)) { + if (time_is_before_jiffies(ps->tx_tstamp_start + + TX_TSTAMP_TIMEOUT)) { + dev_warn(chip->dev, "p%d: clearing tx timestamp hang\n", + ps->port_id); + goto free_and_clear_skb; + } + /* The timestamp should be available quickly, while getting it + * is high priority and time bounded to only 10ms. A poll is + * warranted so restart the work. + */ + return 1; + } + + /* We have the timestamp; go ahead and clear valid now */ + mutex_lock(&chip->reg_lock); + mv88e6xxx_port_ptp_write(chip, ps->port_id, + MV88E6XXX_PORT_PTP_DEP_STS, 0); + mutex_unlock(&chip->reg_lock); + + status = departure_block[0] & MV88E6XXX_PTP_TS_STATUS_MASK; + if (status != MV88E6XXX_PTP_TS_STATUS_NORMAL) { + dev_warn(chip->dev, "p%d: tx timestamp overrun\n", ps->port_id); + goto free_and_clear_skb; + } + + if (departure_block[3] != ps->tx_seq_id) { + dev_warn(chip->dev, "p%d: unexpected seq. id\n", ps->port_id); + goto free_and_clear_skb; + } + + memset(&shhwtstamps, 0, sizeof(shhwtstamps)); + time_raw = ((u32)departure_block[2] << 16) | departure_block[1]; + mutex_lock(&chip->reg_lock); + ns = timecounter_cyc2time(&chip->tstamp_tc, time_raw); + mutex_unlock(&chip->reg_lock); + shhwtstamps.hwtstamp = ns_to_ktime(ns); + + dev_dbg(chip->dev, + "p%d: txtstamp %llx status 0x%04x skb ID 0x%04x hw ID 0x%04x\n", + ps->port_id, ktime_to_ns(shhwtstamps.hwtstamp), + departure_block[0], ps->tx_seq_id, departure_block[3]); + + /* skb_complete_tx_timestamp() will free up the client to make + * another timestamp-able transmit. We have to be ready for it + * -- by clearing the ps->tx_skb "flag" -- beforehand. + */ + + tmp_skb = ps->tx_skb; + ps->tx_skb = NULL; + clear_bit_unlock(MV88E6XXX_HWTSTAMP_TX_IN_PROGRESS, &ps->state); + skb_complete_tx_timestamp(tmp_skb, &shhwtstamps); + + return 0; + +free_and_clear_skb: + dev_kfree_skb_any(ps->tx_skb); + ps->tx_skb = NULL; + clear_bit_unlock(MV88E6XXX_HWTSTAMP_TX_IN_PROGRESS, &ps->state); + + return 0; +} + +long mv88e6xxx_hwtstamp_work(struct ptp_clock_info *ptp) +{ + struct mv88e6xxx_chip *chip = ptp_to_chip(ptp); + struct dsa_switch *ds = chip->ds; + struct mv88e6xxx_port_hwtstamp *ps; + int i, restart = 0; + + for (i = 0; i < ds->num_ports; i++) { + if (!dsa_is_user_port(ds, i)) + continue; + + ps = &chip->port_hwtstamp[i]; + if (test_bit(MV88E6XXX_HWTSTAMP_TX_IN_PROGRESS, &ps->state)) + restart |= mv88e6xxx_txtstamp_work(chip, ps); + + mv88e6xxx_rxtstamp_work(chip, ps); + } + + return restart ? 1 : -1; +} + +bool mv88e6xxx_port_txtstamp(struct dsa_switch *ds, int port, + struct sk_buff *clone, unsigned int type) +{ + struct mv88e6xxx_chip *chip = ds->priv; + struct mv88e6xxx_port_hwtstamp *ps = &chip->port_hwtstamp[port]; + __be16 *seq_ptr; + u8 *hdr; + + if (!(skb_shinfo(clone)->tx_flags & SKBTX_HW_TSTAMP)) + return false; + + hdr = mv88e6xxx_should_tstamp(chip, port, clone, type); + if (!hdr) + return false; + + seq_ptr = (__be16 *)(hdr + OFF_PTP_SEQUENCE_ID); + + if (test_and_set_bit_lock(MV88E6XXX_HWTSTAMP_TX_IN_PROGRESS, + &ps->state)) + return false; + + ps->tx_skb = clone; + ps->tx_tstamp_start = jiffies; + ps->tx_seq_id = be16_to_cpup(seq_ptr); + + ptp_schedule_worker(chip->ptp_clock, 0); + return true; +} + +static int mv88e6xxx_hwtstamp_port_setup(struct mv88e6xxx_chip *chip, int port) +{ + struct mv88e6xxx_port_hwtstamp *ps = &chip->port_hwtstamp[port]; + + ps->port_id = port; + + skb_queue_head_init(&ps->rx_queue); + skb_queue_head_init(&ps->rx_queue2); + + return mv88e6xxx_port_ptp_write(chip, port, MV88E6XXX_PORT_PTP_CFG0, + MV88E6XXX_PORT_PTP_CFG0_DISABLE_PTP); +} + +int mv88e6xxx_hwtstamp_setup(struct mv88e6xxx_chip *chip) +{ + int err; + int i; + + /* Disable timestamping on all ports. */ + for (i = 0; i < mv88e6xxx_num_ports(chip); ++i) { + err = mv88e6xxx_hwtstamp_port_setup(chip, i); + if (err) + return err; + } + + /* MV88E6XXX_PTP_MSG_TYPE is a mask of PTP message types to + * timestamp. This affects all ports that have timestamping enabled, + * but the timestamp config is per-port; thus we configure all events + * here and only support the HWTSTAMP_FILTER_*_EVENT filter types. + */ + err = mv88e6xxx_ptp_write(chip, MV88E6XXX_PTP_MSGTYPE, + MV88E6XXX_PTP_MSGTYPE_ALL_EVENT); + if (err) + return err; + + /* Use ARRIVAL1 for peer delay response messages. */ + err = mv88e6xxx_ptp_write(chip, MV88E6XXX_PTP_TS_ARRIVAL_PTR, + MV88E6XXX_PTP_MSGTYPE_PDLAY_RES); + if (err) + return err; + + /* 88E6341 devices default to timestamping at the PHY, but this has + * a hardware issue that results in unreliable timestamps. Force + * these devices to timestamp at the MAC. + */ + if (chip->info->family == MV88E6XXX_FAMILY_6341) { + u16 val = MV88E6341_PTP_CFG_UPDATE | + MV88E6341_PTP_CFG_MODE_IDX | + MV88E6341_PTP_CFG_MODE_TS_AT_MAC; + err = mv88e6xxx_ptp_write(chip, MV88E6341_PTP_CFG, val); + if (err) + return err; + } + + return 0; +} + +void mv88e6xxx_hwtstamp_free(struct mv88e6xxx_chip *chip) +{ +} diff --git a/drivers/net/dsa/mv88e6xxx/hwtstamp.h b/drivers/net/dsa/mv88e6xxx/hwtstamp.h new file mode 100644 index 000000000000..bc71c9212a08 --- /dev/null +++ b/drivers/net/dsa/mv88e6xxx/hwtstamp.h @@ -0,0 +1,172 @@ +/* + * Marvell 88E6xxx Switch hardware timestamping support + * + * Copyright (c) 2008 Marvell Semiconductor + * + * Copyright (c) 2017 National Instruments + * Erik Hons <erik.hons@ni.com> + * Brandon Streiff <brandon.streiff@ni.com> + * Dane Wagner <dane.wagner@ni.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 _MV88E6XXX_HWTSTAMP_H +#define _MV88E6XXX_HWTSTAMP_H + +#include "chip.h" + +/* Global PTP registers */ +/* Offset 0x00: PTP EtherType */ +#define MV88E6XXX_PTP_ETHERTYPE 0x00 + +/* Offset 0x01: Message Type Timestamp Enables */ +#define MV88E6XXX_PTP_MSGTYPE 0x01 +#define MV88E6XXX_PTP_MSGTYPE_SYNC 0x0001 +#define MV88E6XXX_PTP_MSGTYPE_DELAY_REQ 0x0002 +#define MV88E6XXX_PTP_MSGTYPE_PDLAY_REQ 0x0004 +#define MV88E6XXX_PTP_MSGTYPE_PDLAY_RES 0x0008 +#define MV88E6XXX_PTP_MSGTYPE_ALL_EVENT 0x000f + +/* Offset 0x02: Timestamp Arrival Capture Pointers */ +#define MV88E6XXX_PTP_TS_ARRIVAL_PTR 0x02 + +/* Offset 0x07: PTP Global Configuration */ +#define MV88E6341_PTP_CFG 0x07 +#define MV88E6341_PTP_CFG_UPDATE 0x8000 +#define MV88E6341_PTP_CFG_IDX_MASK 0x7f00 +#define MV88E6341_PTP_CFG_DATA_MASK 0x00ff +#define MV88E6341_PTP_CFG_MODE_IDX 0x0 +#define MV88E6341_PTP_CFG_MODE_TS_AT_PHY 0x00 +#define MV88E6341_PTP_CFG_MODE_TS_AT_MAC 0x80 + +/* Offset 0x08: PTP Interrupt Status */ +#define MV88E6XXX_PTP_IRQ_STATUS 0x08 + +/* Per-Port PTP Registers */ +/* Offset 0x00: PTP Configuration 0 */ +#define MV88E6XXX_PORT_PTP_CFG0 0x00 +#define MV88E6XXX_PORT_PTP_CFG0_TSPEC_SHIFT 12 +#define MV88E6XXX_PORT_PTP_CFG0_TSPEC_MASK 0xf000 +#define MV88E6XXX_PORT_PTP_CFG0_TSPEC_1588 0x0000 +#define MV88E6XXX_PORT_PTP_CFG0_TSPEC_8021AS 0x1000 +#define MV88E6XXX_PORT_PTP_CFG0_DISABLE_TSPEC_MATCH 0x0800 +#define MV88E6XXX_PORT_PTP_CFG0_DISABLE_OVERWRITE 0x0002 +#define MV88E6XXX_PORT_PTP_CFG0_DISABLE_PTP 0x0001 + +/* Offset 0x01: PTP Configuration 1 */ +#define MV88E6XXX_PORT_PTP_CFG1 0x01 + +/* Offset 0x02: PTP Configuration 2 */ +#define MV88E6XXX_PORT_PTP_CFG2 0x02 +#define MV88E6XXX_PORT_PTP_CFG2_EMBED_ARRIVAL 0x1000 +#define MV88E6XXX_PORT_PTP_CFG2_DEP_IRQ_EN 0x0002 +#define MV88E6XXX_PORT_PTP_CFG2_ARR_IRQ_EN 0x0001 + +/* Offset 0x03: PTP LED Configuration */ +#define MV88E6XXX_PORT_PTP_LED_CFG 0x03 + +/* Offset 0x08: PTP Arrival 0 Status */ +#define MV88E6XXX_PORT_PTP_ARR0_STS 0x08 + +/* Offset 0x09/0x0A: PTP Arrival 0 Time */ +#define MV88E6XXX_PORT_PTP_ARR0_TIME_LO 0x09 +#define MV88E6XXX_PORT_PTP_ARR0_TIME_HI 0x0a + +/* Offset 0x0B: PTP Arrival 0 Sequence ID */ +#define MV88E6XXX_PORT_PTP_ARR0_SEQID 0x0b + +/* Offset 0x0C: PTP Arrival 1 Status */ +#define MV88E6XXX_PORT_PTP_ARR1_STS 0x0c + +/* Offset 0x0D/0x0E: PTP Arrival 1 Time */ +#define MV88E6XXX_PORT_PTP_ARR1_TIME_LO 0x0d +#define MV88E6XXX_PORT_PTP_ARR1_TIME_HI 0x0e + +/* Offset 0x0F: PTP Arrival 1 Sequence ID */ +#define MV88E6XXX_PORT_PTP_ARR1_SEQID 0x0f + +/* Offset 0x10: PTP Departure Status */ +#define MV88E6XXX_PORT_PTP_DEP_STS 0x10 + +/* Offset 0x11/0x12: PTP Deperture Time */ +#define MV88E6XXX_PORT_PTP_DEP_TIME_LO 0x11 +#define MV88E6XXX_PORT_PTP_DEP_TIME_HI 0x12 + +/* Offset 0x13: PTP Departure Sequence ID */ +#define MV88E6XXX_PORT_PTP_DEP_SEQID 0x13 + +/* Status fields for arrival and depature timestamp status registers */ +#define MV88E6XXX_PTP_TS_STATUS_MASK 0x0006 +#define MV88E6XXX_PTP_TS_STATUS_NORMAL 0x0000 +#define MV88E6XXX_PTP_TS_STATUS_OVERWITTEN 0x0002 +#define MV88E6XXX_PTP_TS_STATUS_DISCARDED 0x0004 +#define MV88E6XXX_PTP_TS_VALID 0x0001 + +#ifdef CONFIG_NET_DSA_MV88E6XXX_PTP + +int mv88e6xxx_port_hwtstamp_set(struct dsa_switch *ds, int port, + struct ifreq *ifr); +int mv88e6xxx_port_hwtstamp_get(struct dsa_switch *ds, int port, + struct ifreq *ifr); + +bool mv88e6xxx_port_rxtstamp(struct dsa_switch *ds, int port, + struct sk_buff *clone, unsigned int type); +bool mv88e6xxx_port_txtstamp(struct dsa_switch *ds, int port, + struct sk_buff *clone, unsigned int type); + +int mv88e6xxx_get_ts_info(struct dsa_switch *ds, int port, + struct ethtool_ts_info *info); + +int mv88e6xxx_hwtstamp_setup(struct mv88e6xxx_chip *chip); +void mv88e6xxx_hwtstamp_free(struct mv88e6xxx_chip *chip); + +#else /* !CONFIG_NET_DSA_MV88E6XXX_PTP */ + +static inline int mv88e6xxx_port_hwtstamp_set(struct dsa_switch *ds, + int port, struct ifreq *ifr) +{ + return -EOPNOTSUPP; +} + +static inline int mv88e6xxx_port_hwtstamp_get(struct dsa_switch *ds, + int port, struct ifreq *ifr) +{ + return -EOPNOTSUPP; +} + +static inline bool mv88e6xxx_port_rxtstamp(struct dsa_switch *ds, int port, + struct sk_buff *clone, + unsigned int type) +{ + return false; +} + +static inline bool mv88e6xxx_port_txtstamp(struct dsa_switch *ds, int port, + struct sk_buff *clone, + unsigned int type) +{ + return false; +} + +static inline int mv88e6xxx_get_ts_info(struct dsa_switch *ds, int port, + struct ethtool_ts_info *info) +{ + return -EOPNOTSUPP; +} + +static inline int mv88e6xxx_hwtstamp_setup(struct mv88e6xxx_chip *chip) +{ + return 0; +} + +static inline void mv88e6xxx_hwtstamp_free(struct mv88e6xxx_chip *chip) +{ +} + +#endif /* CONFIG_NET_DSA_MV88E6XXX_PTP */ + +#endif /* _MV88E6XXX_HWTSTAMP_H */ diff --git a/drivers/net/dsa/mv88e6xxx/ptp.c b/drivers/net/dsa/mv88e6xxx/ptp.c new file mode 100644 index 000000000000..bd85e2c390e1 --- /dev/null +++ b/drivers/net/dsa/mv88e6xxx/ptp.c @@ -0,0 +1,381 @@ +/* + * Marvell 88E6xxx Switch PTP support + * + * Copyright (c) 2008 Marvell Semiconductor + * + * Copyright (c) 2017 National Instruments + * Erik Hons <erik.hons@ni.com> + * Brandon Streiff <brandon.streiff@ni.com> + * Dane Wagner <dane.wagner@ni.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 "chip.h" +#include "global2.h" +#include "ptp.h" + +/* Raw timestamps are in units of 8-ns clock periods. */ +#define CC_SHIFT 28 +#define CC_MULT (8 << CC_SHIFT) +#define CC_MULT_NUM (1 << 9) +#define CC_MULT_DEM 15625ULL + +#define TAI_EVENT_WORK_INTERVAL msecs_to_jiffies(100) + +#define cc_to_chip(cc) container_of(cc, struct mv88e6xxx_chip, tstamp_cc) +#define dw_overflow_to_chip(dw) container_of(dw, struct mv88e6xxx_chip, \ + overflow_work) +#define dw_tai_event_to_chip(dw) container_of(dw, struct mv88e6xxx_chip, \ + tai_event_work) + +static int mv88e6xxx_tai_read(struct mv88e6xxx_chip *chip, int addr, + u16 *data, int len) +{ + if (!chip->info->ops->avb_ops->tai_read) + return -EOPNOTSUPP; + + return chip->info->ops->avb_ops->tai_read(chip, addr, data, len); +} + +static int mv88e6xxx_tai_write(struct mv88e6xxx_chip *chip, int addr, u16 data) +{ + if (!chip->info->ops->avb_ops->tai_write) + return -EOPNOTSUPP; + + return chip->info->ops->avb_ops->tai_write(chip, addr, data); +} + +/* TODO: places where this are called should be using pinctrl */ +static int mv88e6xxx_set_gpio_func(struct mv88e6xxx_chip *chip, int pin, + int func, int input) +{ + int err; + + if (!chip->info->ops->gpio_ops) + return -EOPNOTSUPP; + + err = chip->info->ops->gpio_ops->set_dir(chip, pin, input); + if (err) + return err; + + return chip->info->ops->gpio_ops->set_pctl(chip, pin, func); +} + +static u64 mv88e6xxx_ptp_clock_read(const struct cyclecounter *cc) +{ + struct mv88e6xxx_chip *chip = cc_to_chip(cc); + u16 phc_time[2]; + int err; + + err = mv88e6xxx_tai_read(chip, MV88E6XXX_TAI_TIME_LO, phc_time, + ARRAY_SIZE(phc_time)); + if (err) + return 0; + else + return ((u32)phc_time[1] << 16) | phc_time[0]; +} + +/* mv88e6xxx_config_eventcap - configure TAI event capture + * @event: PTP_CLOCK_PPS (internal) or PTP_CLOCK_EXTTS (external) + * @rising: zero for falling-edge trigger, else rising-edge trigger + * + * This will also reset the capture sequence counter. + */ +static int mv88e6xxx_config_eventcap(struct mv88e6xxx_chip *chip, int event, + int rising) +{ + u16 global_config; + u16 cap_config; + int err; + + chip->evcap_config = MV88E6XXX_TAI_CFG_CAP_OVERWRITE | + MV88E6XXX_TAI_CFG_CAP_CTR_START; + if (!rising) + chip->evcap_config |= MV88E6XXX_TAI_CFG_EVREQ_FALLING; + + global_config = (chip->evcap_config | chip->trig_config); + err = mv88e6xxx_tai_write(chip, MV88E6XXX_TAI_CFG, global_config); + if (err) + return err; + + if (event == PTP_CLOCK_PPS) { + cap_config = MV88E6XXX_TAI_EVENT_STATUS_CAP_TRIG; + } else if (event == PTP_CLOCK_EXTTS) { + /* if STATUS_CAP_TRIG is unset we capture PTP_EVREQ events */ + cap_config = 0; + } else { + return -EINVAL; + } + + /* Write the capture config; this also clears the capture counter */ + err = mv88e6xxx_tai_write(chip, MV88E6XXX_TAI_EVENT_STATUS, + cap_config); + + return err; +} + +static void mv88e6xxx_tai_event_work(struct work_struct *ugly) +{ + struct delayed_work *dw = to_delayed_work(ugly); + struct mv88e6xxx_chip *chip = dw_tai_event_to_chip(dw); + struct ptp_clock_event ev; + u16 status[4]; + u32 raw_ts; + int err; + + mutex_lock(&chip->reg_lock); + err = mv88e6xxx_tai_read(chip, MV88E6XXX_TAI_EVENT_STATUS, + status, ARRAY_SIZE(status)); + mutex_unlock(&chip->reg_lock); + + if (err) { + dev_err(chip->dev, "failed to read TAI status register\n"); + return; + } + if (status[0] & MV88E6XXX_TAI_EVENT_STATUS_ERROR) { + dev_warn(chip->dev, "missed event capture\n"); + return; + } + if (!(status[0] & MV88E6XXX_TAI_EVENT_STATUS_VALID)) + goto out; + + raw_ts = ((u32)status[2] << 16) | status[1]; + + /* Clear the valid bit so the next timestamp can come in */ + status[0] &= ~MV88E6XXX_TAI_EVENT_STATUS_VALID; + mutex_lock(&chip->reg_lock); + err = mv88e6xxx_tai_write(chip, MV88E6XXX_TAI_EVENT_STATUS, status[0]); + mutex_unlock(&chip->reg_lock); + + /* This is an external timestamp */ + ev.type = PTP_CLOCK_EXTTS; + + /* We only have one timestamping channel. */ + ev.index = 0; + mutex_lock(&chip->reg_lock); + ev.timestamp = timecounter_cyc2time(&chip->tstamp_tc, raw_ts); + mutex_unlock(&chip->reg_lock); + + ptp_clock_event(chip->ptp_clock, &ev); +out: + schedule_delayed_work(&chip->tai_event_work, TAI_EVENT_WORK_INTERVAL); +} + +static int mv88e6xxx_ptp_adjfine(struct ptp_clock_info *ptp, long scaled_ppm) +{ + struct mv88e6xxx_chip *chip = ptp_to_chip(ptp); + int neg_adj = 0; + u32 diff, mult; + u64 adj; + + if (scaled_ppm < 0) { + neg_adj = 1; + scaled_ppm = -scaled_ppm; + } + mult = CC_MULT; + adj = CC_MULT_NUM; + adj *= scaled_ppm; + diff = div_u64(adj, CC_MULT_DEM); + + mutex_lock(&chip->reg_lock); + + timecounter_read(&chip->tstamp_tc); + chip->tstamp_cc.mult = neg_adj ? mult - diff : mult + diff; + + mutex_unlock(&chip->reg_lock); + + return 0; +} + +static int mv88e6xxx_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta) +{ + struct mv88e6xxx_chip *chip = ptp_to_chip(ptp); + + mutex_lock(&chip->reg_lock); + timecounter_adjtime(&chip->tstamp_tc, delta); + mutex_unlock(&chip->reg_lock); + + return 0; +} + +static int mv88e6xxx_ptp_gettime(struct ptp_clock_info *ptp, + struct timespec64 *ts) +{ + struct mv88e6xxx_chip *chip = ptp_to_chip(ptp); + u64 ns; + + mutex_lock(&chip->reg_lock); + ns = timecounter_read(&chip->tstamp_tc); + mutex_unlock(&chip->reg_lock); + + *ts = ns_to_timespec64(ns); + + return 0; +} + +static int mv88e6xxx_ptp_settime(struct ptp_clock_info *ptp, + const struct timespec64 *ts) +{ + struct mv88e6xxx_chip *chip = ptp_to_chip(ptp); + u64 ns; + + ns = timespec64_to_ns(ts); + + mutex_lock(&chip->reg_lock); + timecounter_init(&chip->tstamp_tc, &chip->tstamp_cc, ns); + mutex_unlock(&chip->reg_lock); + + return 0; +} + +static int mv88e6xxx_ptp_enable_extts(struct mv88e6xxx_chip *chip, + struct ptp_clock_request *rq, int on) +{ + int rising = (rq->extts.flags & PTP_RISING_EDGE); + int func; + int pin; + int err; + + pin = ptp_find_pin(chip->ptp_clock, PTP_PF_EXTTS, rq->extts.index); + + if (pin < 0) + return -EBUSY; + + mutex_lock(&chip->reg_lock); + + if (on) { + func = MV88E6352_G2_SCRATCH_GPIO_PCTL_EVREQ; + + err = mv88e6xxx_set_gpio_func(chip, pin, func, true); + if (err) + goto out; + + schedule_delayed_work(&chip->tai_event_work, + TAI_EVENT_WORK_INTERVAL); + + err = mv88e6xxx_config_eventcap(chip, PTP_CLOCK_EXTTS, rising); + } else { + func = MV88E6352_G2_SCRATCH_GPIO_PCTL_GPIO; + + err = mv88e6xxx_set_gpio_func(chip, pin, func, true); + + cancel_delayed_work_sync(&chip->tai_event_work); + } + +out: + mutex_unlock(&chip->reg_lock); + + return err; +} + +static int mv88e6xxx_ptp_enable(struct ptp_clock_info *ptp, + struct ptp_clock_request *rq, int on) +{ + struct mv88e6xxx_chip *chip = ptp_to_chip(ptp); + + switch (rq->type) { + case PTP_CLK_REQ_EXTTS: + return mv88e6xxx_ptp_enable_extts(chip, rq, on); + default: + return -EOPNOTSUPP; + } +} + +static int mv88e6xxx_ptp_verify(struct ptp_clock_info *ptp, unsigned int pin, + enum ptp_pin_function func, unsigned int chan) +{ + switch (func) { + case PTP_PF_NONE: + case PTP_PF_EXTTS: + break; + case PTP_PF_PEROUT: + case PTP_PF_PHYSYNC: + return -EOPNOTSUPP; + } + return 0; +} + +/* With a 125MHz input clock, the 32-bit timestamp counter overflows in ~34.3 + * seconds; this task forces periodic reads so that we don't miss any. + */ +#define MV88E6XXX_TAI_OVERFLOW_PERIOD (HZ * 16) +static void mv88e6xxx_ptp_overflow_check(struct work_struct *work) +{ + struct delayed_work *dw = to_delayed_work(work); + struct mv88e6xxx_chip *chip = dw_overflow_to_chip(dw); + struct timespec64 ts; + + mv88e6xxx_ptp_gettime(&chip->ptp_clock_info, &ts); + + schedule_delayed_work(&chip->overflow_work, + MV88E6XXX_TAI_OVERFLOW_PERIOD); +} + +int mv88e6xxx_ptp_setup(struct mv88e6xxx_chip *chip) +{ + int i; + + /* Set up the cycle counter */ + memset(&chip->tstamp_cc, 0, sizeof(chip->tstamp_cc)); + chip->tstamp_cc.read = mv88e6xxx_ptp_clock_read; + chip->tstamp_cc.mask = CYCLECOUNTER_MASK(32); + chip->tstamp_cc.mult = CC_MULT; + chip->tstamp_cc.shift = CC_SHIFT; + + timecounter_init(&chip->tstamp_tc, &chip->tstamp_cc, + ktime_to_ns(ktime_get_real())); + + INIT_DELAYED_WORK(&chip->overflow_work, mv88e6xxx_ptp_overflow_check); + INIT_DELAYED_WORK(&chip->tai_event_work, mv88e6xxx_tai_event_work); + + chip->ptp_clock_info.owner = THIS_MODULE; + snprintf(chip->ptp_clock_info.name, sizeof(chip->ptp_clock_info.name), + dev_name(chip->dev)); + chip->ptp_clock_info.max_adj = 1000000; + + chip->ptp_clock_info.n_ext_ts = 1; + chip->ptp_clock_info.n_per_out = 0; + chip->ptp_clock_info.n_pins = mv88e6xxx_num_gpio(chip); + chip->ptp_clock_info.pps = 0; + + for (i = 0; i < chip->ptp_clock_info.n_pins; ++i) { + struct ptp_pin_desc *ppd = &chip->pin_config[i]; + + snprintf(ppd->name, sizeof(ppd->name), "mv88e6xxx_gpio%d", i); + ppd->index = i; + ppd->func = PTP_PF_NONE; + } + chip->ptp_clock_info.pin_config = chip->pin_config; + + chip->ptp_clock_info.adjfine = mv88e6xxx_ptp_adjfine; + chip->ptp_clock_info.adjtime = mv88e6xxx_ptp_adjtime; + chip->ptp_clock_info.gettime64 = mv88e6xxx_ptp_gettime; + chip->ptp_clock_info.settime64 = mv88e6xxx_ptp_settime; + chip->ptp_clock_info.enable = mv88e6xxx_ptp_enable; + chip->ptp_clock_info.verify = mv88e6xxx_ptp_verify; + chip->ptp_clock_info.do_aux_work = mv88e6xxx_hwtstamp_work; + + chip->ptp_clock = ptp_clock_register(&chip->ptp_clock_info, chip->dev); + if (IS_ERR(chip->ptp_clock)) + return PTR_ERR(chip->ptp_clock); + + schedule_delayed_work(&chip->overflow_work, + MV88E6XXX_TAI_OVERFLOW_PERIOD); + + return 0; +} + +void mv88e6xxx_ptp_free(struct mv88e6xxx_chip *chip) +{ + if (chip->ptp_clock) { + cancel_delayed_work_sync(&chip->overflow_work); + cancel_delayed_work_sync(&chip->tai_event_work); + + ptp_clock_unregister(chip->ptp_clock); + chip->ptp_clock = NULL; + } +} diff --git a/drivers/net/dsa/mv88e6xxx/ptp.h b/drivers/net/dsa/mv88e6xxx/ptp.h new file mode 100644 index 000000000000..10f271ab650d --- /dev/null +++ b/drivers/net/dsa/mv88e6xxx/ptp.h @@ -0,0 +1,108 @@ +/* + * Marvell 88E6xxx Switch PTP support + * + * Copyright (c) 2008 Marvell Semiconductor + * + * Copyright (c) 2017 National Instruments + * Erik Hons <erik.hons@ni.com> + * Brandon Streiff <brandon.streiff@ni.com> + * Dane Wagner <dane.wagner@ni.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 _MV88E6XXX_PTP_H +#define _MV88E6XXX_PTP_H + +#include "chip.h" + +/* Offset 0x00: TAI Global Config */ +#define MV88E6XXX_TAI_CFG 0x00 +#define MV88E6XXX_TAI_CFG_CAP_OVERWRITE 0x8000 +#define MV88E6XXX_TAI_CFG_CAP_CTR_START 0x4000 +#define MV88E6XXX_TAI_CFG_EVREQ_FALLING 0x2000 +#define MV88E6XXX_TAI_CFG_TRIG_ACTIVE_LO 0x1000 +#define MV88E6XXX_TAI_CFG_IRL_ENABLE 0x0400 +#define MV88E6XXX_TAI_CFG_TRIG_IRQ_EN 0x0200 +#define MV88E6XXX_TAI_CFG_EVREQ_IRQ_EN 0x0100 +#define MV88E6XXX_TAI_CFG_TRIG_LOCK 0x0080 +#define MV88E6XXX_TAI_CFG_BLOCK_UPDATE 0x0008 +#define MV88E6XXX_TAI_CFG_MULTI_PTP 0x0004 +#define MV88E6XXX_TAI_CFG_TRIG_MODE_ONESHOT 0x0002 +#define MV88E6XXX_TAI_CFG_TRIG_ENABLE 0x0001 + +/* Offset 0x01: Timestamp Clock Period (ps) */ +#define MV88E6XXX_TAI_CLOCK_PERIOD 0x01 + +/* Offset 0x02/0x03: Trigger Generation Amount */ +#define MV88E6XXX_TAI_TRIG_GEN_AMOUNT_LO 0x02 +#define MV88E6XXX_TAI_TRIG_GEN_AMOUNT_HI 0x03 + +/* Offset 0x04: Clock Compensation */ +#define MV88E6XXX_TAI_TRIG_CLOCK_COMP 0x04 + +/* Offset 0x05: Trigger Configuration */ +#define MV88E6XXX_TAI_TRIG_CFG 0x05 + +/* Offset 0x06: Ingress Rate Limiter Clock Generation Amount */ +#define MV88E6XXX_TAI_IRL_AMOUNT 0x06 + +/* Offset 0x07: Ingress Rate Limiter Compensation */ +#define MV88E6XXX_TAI_IRL_COMP 0x07 + +/* Offset 0x08: Ingress Rate Limiter Compensation */ +#define MV88E6XXX_TAI_IRL_COMP_PS 0x08 + +/* Offset 0x09: Event Status */ +#define MV88E6XXX_TAI_EVENT_STATUS 0x09 +#define MV88E6XXX_TAI_EVENT_STATUS_CAP_TRIG 0x4000 +#define MV88E6XXX_TAI_EVENT_STATUS_ERROR 0x0200 +#define MV88E6XXX_TAI_EVENT_STATUS_VALID 0x0100 +#define MV88E6XXX_TAI_EVENT_STATUS_CTR_MASK 0x00ff + +/* Offset 0x0A/0x0B: Event Time */ +#define MV88E6XXX_TAI_EVENT_TIME_LO 0x0a +#define MV88E6XXX_TAI_EVENT_TYPE_HI 0x0b + +/* Offset 0x0E/0x0F: PTP Global Time */ +#define MV88E6XXX_TAI_TIME_LO 0x0e +#define MV88E6XXX_TAI_TIME_HI 0x0f + +/* Offset 0x10/0x11: Trig Generation Time */ +#define MV88E6XXX_TAI_TRIG_TIME_LO 0x10 +#define MV88E6XXX_TAI_TRIG_TIME_HI 0x11 + +/* Offset 0x12: Lock Status */ +#define MV88E6XXX_TAI_LOCK_STATUS 0x12 + +#ifdef CONFIG_NET_DSA_MV88E6XXX_PTP + +long mv88e6xxx_hwtstamp_work(struct ptp_clock_info *ptp); +int mv88e6xxx_ptp_setup(struct mv88e6xxx_chip *chip); +void mv88e6xxx_ptp_free(struct mv88e6xxx_chip *chip); + +#define ptp_to_chip(ptp) container_of(ptp, struct mv88e6xxx_chip, \ + ptp_clock_info) + +#else /* !CONFIG_NET_DSA_MV88E6XXX_PTP */ + +static inline long mv88e6xxx_hwtstamp_work(struct ptp_clock_info *ptp) +{ + return -1; +} + +static inline int mv88e6xxx_ptp_setup(struct mv88e6xxx_chip *chip) +{ + return 0; +} + +static inline void mv88e6xxx_ptp_free(struct mv88e6xxx_chip *chip) +{ +} + +#endif /* CONFIG_NET_DSA_MV88E6XXX_PTP */ + +#endif /* _MV88E6XXX_PTP_H */ diff --git a/drivers/net/dsa/mv88e6xxx/serdes.c b/drivers/net/dsa/mv88e6xxx/serdes.c index f3c01119b3d1..4756969c1546 100644 --- a/drivers/net/dsa/mv88e6xxx/serdes.c +++ b/drivers/net/dsa/mv88e6xxx/serdes.c @@ -55,18 +55,30 @@ static int mv88e6352_serdes_power_set(struct mv88e6xxx_chip *chip, bool on) return err; } -int mv88e6352_serdes_power(struct mv88e6xxx_chip *chip, int port, bool on) +static bool mv88e6352_port_has_serdes(struct mv88e6xxx_chip *chip, int port) { - int err; u8 cmode; + int err; err = mv88e6xxx_port_get_cmode(chip, port, &cmode); - if (err) - return err; + if (err) { + dev_err(chip->dev, "failed to read cmode\n"); + return 0; + } if ((cmode == MV88E6XXX_PORT_STS_CMODE_100BASE_X) || (cmode == MV88E6XXX_PORT_STS_CMODE_1000BASE_X) || - (cmode == MV88E6XXX_PORT_STS_CMODE_SGMII)) { + (cmode == MV88E6XXX_PORT_STS_CMODE_SGMII)) + return 1; + + return 0; +} + +int mv88e6352_serdes_power(struct mv88e6xxx_chip *chip, int port, bool on) +{ + int err; + + if (mv88e6352_port_has_serdes(chip, port)) { err = mv88e6352_serdes_power_set(chip, on); if (err < 0) return err; @@ -75,6 +87,90 @@ int mv88e6352_serdes_power(struct mv88e6xxx_chip *chip, int port, bool on) return 0; } +struct mv88e6352_serdes_hw_stat { + char string[ETH_GSTRING_LEN]; + int sizeof_stat; + int reg; +}; + +static struct mv88e6352_serdes_hw_stat mv88e6352_serdes_hw_stats[] = { + { "serdes_fibre_rx_error", 16, 21 }, + { "serdes_PRBS_error", 32, 24 }, +}; + +int mv88e6352_serdes_get_sset_count(struct mv88e6xxx_chip *chip, int port) +{ + if (mv88e6352_port_has_serdes(chip, port)) + return ARRAY_SIZE(mv88e6352_serdes_hw_stats); + + return 0; +} + +void mv88e6352_serdes_get_strings(struct mv88e6xxx_chip *chip, + int port, uint8_t *data) +{ + struct mv88e6352_serdes_hw_stat *stat; + int i; + + if (!mv88e6352_port_has_serdes(chip, port)) + return; + + for (i = 0; i < ARRAY_SIZE(mv88e6352_serdes_hw_stats); i++) { + stat = &mv88e6352_serdes_hw_stats[i]; + memcpy(data + i * ETH_GSTRING_LEN, stat->string, + ETH_GSTRING_LEN); + } +} + +static uint64_t mv88e6352_serdes_get_stat(struct mv88e6xxx_chip *chip, + struct mv88e6352_serdes_hw_stat *stat) +{ + u64 val = 0; + u16 reg; + int err; + + err = mv88e6352_serdes_read(chip, stat->reg, ®); + if (err) { + dev_err(chip->dev, "failed to read statistic\n"); + return 0; + } + + val = reg; + + if (stat->sizeof_stat == 32) { + err = mv88e6352_serdes_read(chip, stat->reg + 1, ®); + if (err) { + dev_err(chip->dev, "failed to read statistic\n"); + return 0; + } + val = val << 16 | reg; + } + + return val; +} + +void mv88e6352_serdes_get_stats(struct mv88e6xxx_chip *chip, int port, + uint64_t *data) +{ + struct mv88e6xxx_port *mv88e6xxx_port = &chip->ports[port]; + struct mv88e6352_serdes_hw_stat *stat; + u64 value; + int i; + + if (!mv88e6352_port_has_serdes(chip, port)) + return; + + BUILD_BUG_ON(ARRAY_SIZE(mv88e6352_serdes_hw_stats) > + ARRAY_SIZE(mv88e6xxx_port->serdes_stats)); + + for (i = 0; i < ARRAY_SIZE(mv88e6352_serdes_hw_stats); i++) { + stat = &mv88e6352_serdes_hw_stats[i]; + value = mv88e6352_serdes_get_stat(chip, stat); + mv88e6xxx_port->serdes_stats[i] += value; + data[i] = mv88e6xxx_port->serdes_stats[i]; + } +} + /* Set the power on/off for 10GBASE-R and 10GBASE-X4/X2 */ static int mv88e6390_serdes_10g(struct mv88e6xxx_chip *chip, int addr, bool on) { diff --git a/drivers/net/dsa/mv88e6xxx/serdes.h b/drivers/net/dsa/mv88e6xxx/serdes.h index 5c1cd6d8e9a5..641baa75f910 100644 --- a/drivers/net/dsa/mv88e6xxx/serdes.h +++ b/drivers/net/dsa/mv88e6xxx/serdes.h @@ -44,5 +44,9 @@ int mv88e6352_serdes_power(struct mv88e6xxx_chip *chip, int port, bool on); int mv88e6390_serdes_power(struct mv88e6xxx_chip *chip, int port, bool on); - +int mv88e6352_serdes_get_sset_count(struct mv88e6xxx_chip *chip, int port); +void mv88e6352_serdes_get_strings(struct mv88e6xxx_chip *chip, + int port, uint8_t *data); +void mv88e6352_serdes_get_stats(struct mv88e6xxx_chip *chip, int port, + uint64_t *data); #endif diff --git a/drivers/net/dsa/qca8k.c b/drivers/net/dsa/qca8k.c index 9df22ebee822..600d5ad1fbde 100644 --- a/drivers/net/dsa/qca8k.c +++ b/drivers/net/dsa/qca8k.c @@ -631,7 +631,7 @@ qca8k_get_ethtool_stats(struct dsa_switch *ds, int port, } static int -qca8k_get_sset_count(struct dsa_switch *ds) +qca8k_get_sset_count(struct dsa_switch *ds, int port) { return ARRAY_SIZE(ar8327_mib); } diff --git a/drivers/net/ethernet/8390/Makefile b/drivers/net/ethernet/8390/Makefile index f975c2fc88a3..1d650e66cc6e 100644 --- a/drivers/net/ethernet/8390/Makefile +++ b/drivers/net/ethernet/8390/Makefile @@ -7,8 +7,8 @@ obj-$(CONFIG_MAC8390) += mac8390.o obj-$(CONFIG_APNE) += apne.o 8390.o obj-$(CONFIG_ARM_ETHERH) += etherh.o obj-$(CONFIG_AX88796) += ax88796.o -obj-$(CONFIG_HYDRA) += hydra.o 8390.o -obj-$(CONFIG_MCF8390) += mcf8390.o 8390.o +obj-$(CONFIG_HYDRA) += hydra.o +obj-$(CONFIG_MCF8390) += mcf8390.o obj-$(CONFIG_NE2000) += ne.o 8390p.o obj-$(CONFIG_NE2K_PCI) += ne2k-pci.o 8390.o obj-$(CONFIG_PCMCIA_AXNET) += axnet_cs.o 8390.o @@ -16,4 +16,4 @@ obj-$(CONFIG_PCMCIA_PCNET) += pcnet_cs.o 8390.o obj-$(CONFIG_STNIC) += stnic.o 8390.o obj-$(CONFIG_ULTRA) += smc-ultra.o 8390.o obj-$(CONFIG_WD80x3) += wd.o 8390.o -obj-$(CONFIG_ZORRO8390) += zorro8390.o 8390.o +obj-$(CONFIG_ZORRO8390) += zorro8390.o diff --git a/drivers/net/ethernet/8390/ax88796.c b/drivers/net/ethernet/8390/ax88796.c index 245554707163..da61cf3cb3a9 100644 --- a/drivers/net/ethernet/8390/ax88796.c +++ b/drivers/net/ethernet/8390/ax88796.c @@ -77,8 +77,6 @@ static unsigned char version[] = "ax88796.c: Copyright 2005,2007 Simtec Electron #define AX_GPOC_PPDSET BIT(6) -static u32 ax_msg_enable; - /* device private data */ struct ax_device { @@ -747,7 +745,6 @@ static int ax_init_dev(struct net_device *dev) ei_local->block_output = &ax_block_output; ei_local->get_8390_hdr = &ax_get_8390_hdr; ei_local->priv = 0; - ei_local->msg_enable = ax_msg_enable; dev->netdev_ops = &ax_netdev_ops; dev->ethtool_ops = &ax_ethtool_ops; diff --git a/drivers/net/ethernet/8390/axnet_cs.c b/drivers/net/ethernet/8390/axnet_cs.c index 7bddb8efb6d5..d422a124cd7c 100644 --- a/drivers/net/ethernet/8390/axnet_cs.c +++ b/drivers/net/ethernet/8390/axnet_cs.c @@ -104,7 +104,6 @@ static void AX88190_init(struct net_device *dev, int startp); static int ax_open(struct net_device *dev); static int ax_close(struct net_device *dev); static irqreturn_t ax_interrupt(int irq, void *dev_id); -static u32 axnet_msg_enable; /*====================================================================*/ @@ -151,7 +150,6 @@ static int axnet_probe(struct pcmcia_device *link) return -ENOMEM; ei_local = netdev_priv(dev); - ei_local->msg_enable = axnet_msg_enable; spin_lock_init(&ei_local->page_lock); info = PRIV(dev); diff --git a/drivers/net/ethernet/8390/etherh.c b/drivers/net/ethernet/8390/etherh.c index 11cbf22ad201..32e9627e3880 100644 --- a/drivers/net/ethernet/8390/etherh.c +++ b/drivers/net/ethernet/8390/etherh.c @@ -64,8 +64,6 @@ static char version[] = #include "lib8390.c" -static u32 etherh_msg_enable; - struct etherh_priv { void __iomem *ioc_fast; void __iomem *memc; @@ -502,18 +500,6 @@ etherh_close(struct net_device *dev) } /* - * Initialisation - */ - -static void __init etherh_banner(void) -{ - static int version_printed; - - if ((etherh_msg_enable & NETIF_MSG_DRV) && (version_printed++ == 0)) - pr_info("%s", version); -} - -/* * Read the ethernet address string from the on board rom. * This is an ascii string... */ @@ -671,8 +657,6 @@ etherh_probe(struct expansion_card *ec, const struct ecard_id *id) struct etherh_priv *eh; int ret; - etherh_banner(); - ret = ecard_request_resources(ec); if (ret) goto out; @@ -757,7 +741,6 @@ etherh_probe(struct expansion_card *ec, const struct ecard_id *id) ei_local->block_output = etherh_block_output; ei_local->get_8390_hdr = etherh_get_header; ei_local->interface_num = 0; - ei_local->msg_enable = etherh_msg_enable; etherh_reset(dev); __NS8390_init(dev, 0); diff --git a/drivers/net/ethernet/8390/hydra.c b/drivers/net/ethernet/8390/hydra.c index 8ae249195301..941754ea78ec 100644 --- a/drivers/net/ethernet/8390/hydra.c +++ b/drivers/net/ethernet/8390/hydra.c @@ -66,7 +66,6 @@ static void hydra_block_input(struct net_device *dev, int count, static void hydra_block_output(struct net_device *dev, int count, const unsigned char *buf, int start_page); static void hydra_remove_one(struct zorro_dev *z); -static u32 hydra_msg_enable; static struct zorro_device_id hydra_zorro_tbl[] = { { ZORRO_PROD_HYDRA_SYSTEMS_AMIGANET }, @@ -119,7 +118,6 @@ static int hydra_init(struct zorro_dev *z) int start_page, stop_page; int j; int err; - struct ei_device *ei_local; static u32 hydra_offsets[16] = { 0x00, 0x02, 0x04, 0x06, 0x08, 0x0a, 0x0c, 0x0e, @@ -138,8 +136,6 @@ static int hydra_init(struct zorro_dev *z) start_page = NESM_START_PG; stop_page = NESM_STOP_PG; - ei_local = netdev_priv(dev); - ei_local->msg_enable = hydra_msg_enable; dev->base_addr = ioaddr; dev->irq = IRQ_AMIGA_PORTS; diff --git a/drivers/net/ethernet/8390/lib8390.c b/drivers/net/ethernet/8390/lib8390.c index 60f8e2c8e726..5d9bbde9fe68 100644 --- a/drivers/net/ethernet/8390/lib8390.c +++ b/drivers/net/ethernet/8390/lib8390.c @@ -975,6 +975,8 @@ static void ethdev_setup(struct net_device *dev) ether_setup(dev); spin_lock_init(&ei_local->page_lock); + + ei_local->msg_enable = msg_enable; } /** diff --git a/drivers/net/ethernet/8390/mac8390.c b/drivers/net/ethernet/8390/mac8390.c index 2f91ce8dc614..b6d735bf8011 100644 --- a/drivers/net/ethernet/8390/mac8390.c +++ b/drivers/net/ethernet/8390/mac8390.c @@ -123,8 +123,7 @@ enum mac8390_access { }; extern int mac8390_memtest(struct net_device *dev); -static int mac8390_initdev(struct net_device *dev, - struct nubus_rsrc *ndev, +static int mac8390_initdev(struct net_device *dev, struct nubus_board *board, enum mac8390_type type); static int mac8390_open(struct net_device *dev); @@ -168,9 +167,8 @@ static void slow_sane_block_output(struct net_device *dev, int count, const unsigned char *buf, int start_page); static void word_memcpy_tocard(unsigned long tp, const void *fp, int count); static void word_memcpy_fromcard(void *tp, unsigned long fp, int count); -static u32 mac8390_msg_enable; -static enum mac8390_type __init mac8390_ident(struct nubus_rsrc *fres) +static enum mac8390_type mac8390_ident(struct nubus_rsrc *fres) { switch (fres->dr_sw) { case NUBUS_DRSW_3COM: @@ -236,7 +234,7 @@ static enum mac8390_type __init mac8390_ident(struct nubus_rsrc *fres) return MAC8390_NONE; } -static enum mac8390_access __init mac8390_testio(volatile unsigned long membase) +static enum mac8390_access mac8390_testio(unsigned long membase) { unsigned long outdata = 0xA5A0B5B0; unsigned long indata = 0x00000000; @@ -254,7 +252,7 @@ static enum mac8390_access __init mac8390_testio(volatile unsigned long membase) return ACCESS_UNKNOWN; } -static int __init mac8390_memsize(unsigned long membase) +static int mac8390_memsize(unsigned long membase) { unsigned long flags; int i, j; @@ -290,36 +288,34 @@ static int __init mac8390_memsize(unsigned long membase) return i * 0x1000; } -static bool __init mac8390_init(struct net_device *dev, - struct nubus_rsrc *ndev, - enum mac8390_type cardtype) +static bool mac8390_rsrc_init(struct net_device *dev, + struct nubus_rsrc *fres, + enum mac8390_type cardtype) { + struct nubus_board *board = fres->board; struct nubus_dir dir; struct nubus_dirent ent; int offset; volatile unsigned short *i; - printk_once(KERN_INFO pr_fmt("%s"), version); - - dev->irq = SLOT2IRQ(ndev->board->slot); + dev->irq = SLOT2IRQ(board->slot); /* This is getting to be a habit */ - dev->base_addr = (ndev->board->slot_addr | - ((ndev->board->slot & 0xf) << 20)); + dev->base_addr = board->slot_addr | ((board->slot & 0xf) << 20); /* * Get some Nubus info - we will trust the card's idea * of where its memory and registers are. */ - if (nubus_get_func_dir(ndev, &dir) == -1) { - pr_err("%s: Unable to get Nubus functional directory for slot %X!\n", - dev->name, ndev->board->slot); + if (nubus_get_func_dir(fres, &dir) == -1) { + dev_err(&board->dev, + "Unable to get Nubus functional directory\n"); return false; } /* Get the MAC address */ if (nubus_find_rsrc(&dir, NUBUS_RESID_MAC_ADDRESS, &ent) == -1) { - pr_info("%s: Couldn't get MAC address!\n", dev->name); + dev_info(&board->dev, "MAC address resource not found\n"); return false; } @@ -329,8 +325,8 @@ static bool __init mac8390_init(struct net_device *dev, nubus_rewinddir(&dir); if (nubus_find_rsrc(&dir, NUBUS_RESID_MINOR_BASEOS, &ent) == -1) { - pr_err("%s: Memory offset resource for slot %X not found!\n", - dev->name, ndev->board->slot); + dev_err(&board->dev, + "Memory offset resource not found\n"); return false; } nubus_get_rsrc_mem(&offset, &ent, 4); @@ -340,8 +336,8 @@ static bool __init mac8390_init(struct net_device *dev, nubus_rewinddir(&dir); if (nubus_find_rsrc(&dir, NUBUS_RESID_MINOR_LENGTH, &ent) == -1) { - pr_info("%s: Memory length resource for slot %X not found, probing\n", - dev->name, ndev->board->slot); + dev_info(&board->dev, + "Memory length resource not found, probing\n"); offset = mac8390_memsize(dev->mem_start); } else { nubus_get_rsrc_mem(&offset, &ent, 4); @@ -351,25 +347,25 @@ static bool __init mac8390_init(struct net_device *dev, switch (cardtype) { case MAC8390_KINETICS: case MAC8390_DAYNA: /* it's the same */ - dev->base_addr = (int)(ndev->board->slot_addr + + dev->base_addr = (int)(board->slot_addr + DAYNA_8390_BASE); - dev->mem_start = (int)(ndev->board->slot_addr + + dev->mem_start = (int)(board->slot_addr + DAYNA_8390_MEM); dev->mem_end = dev->mem_start + mac8390_memsize(dev->mem_start); break; case MAC8390_INTERLAN: - dev->base_addr = (int)(ndev->board->slot_addr + + dev->base_addr = (int)(board->slot_addr + INTERLAN_8390_BASE); - dev->mem_start = (int)(ndev->board->slot_addr + + dev->mem_start = (int)(board->slot_addr + INTERLAN_8390_MEM); dev->mem_end = dev->mem_start + mac8390_memsize(dev->mem_start); break; case MAC8390_CABLETRON: - dev->base_addr = (int)(ndev->board->slot_addr + + dev->base_addr = (int)(board->slot_addr + CABLETRON_8390_BASE); - dev->mem_start = (int)(ndev->board->slot_addr + + dev->mem_start = (int)(board->slot_addr + CABLETRON_8390_MEM); /* The base address is unreadable if 0x00 * has been written to the command register @@ -384,8 +380,8 @@ static bool __init mac8390_init(struct net_device *dev, break; default: - pr_err("Card type %s is unsupported, sorry\n", - ndev->board->name); + dev_err(&board->dev, + "No known base address for card type\n"); return false; } } @@ -393,91 +389,83 @@ static bool __init mac8390_init(struct net_device *dev, return true; } -struct net_device * __init mac8390_probe(int unit) +static int mac8390_device_probe(struct nubus_board *board) { struct net_device *dev; - struct nubus_rsrc *ndev = NULL; int err = -ENODEV; - struct ei_device *ei_local; - - static unsigned int slots; - - enum mac8390_type cardtype; - - /* probably should check for Nubus instead */ - - if (!MACH_IS_MAC) - return ERR_PTR(-ENODEV); + struct nubus_rsrc *fres; + enum mac8390_type cardtype = MAC8390_NONE; dev = ____alloc_ei_netdev(0); if (!dev) - return ERR_PTR(-ENOMEM); - - if (unit >= 0) - sprintf(dev->name, "eth%d", unit); + return -ENOMEM; - for_each_func_rsrc(ndev) { - if (ndev->category != NUBUS_CAT_NETWORK || - ndev->type != NUBUS_TYPE_ETHERNET) - continue; + SET_NETDEV_DEV(dev, &board->dev); - /* Have we seen it already? */ - if (slots & (1 << ndev->board->slot)) + for_each_board_func_rsrc(board, fres) { + if (fres->category != NUBUS_CAT_NETWORK || + fres->type != NUBUS_TYPE_ETHERNET) continue; - slots |= 1 << ndev->board->slot; - cardtype = mac8390_ident(ndev); + cardtype = mac8390_ident(fres); if (cardtype == MAC8390_NONE) continue; - if (!mac8390_init(dev, ndev, cardtype)) - continue; - - /* Do the nasty 8390 stuff */ - if (!mac8390_initdev(dev, ndev, cardtype)) + if (mac8390_rsrc_init(dev, fres, cardtype)) break; } - - if (!ndev) + if (!fres) goto out; - ei_local = netdev_priv(dev); - ei_local->msg_enable = mac8390_msg_enable; + err = mac8390_initdev(dev, board, cardtype); + if (err) + goto out; err = register_netdev(dev); if (err) goto out; - return dev; + + nubus_set_drvdata(board, dev); + return 0; out: free_netdev(dev); - return ERR_PTR(err); + return err; +} + +static int mac8390_device_remove(struct nubus_board *board) +{ + struct net_device *dev = nubus_get_drvdata(board); + + unregister_netdev(dev); + free_netdev(dev); + return 0; } -#ifdef MODULE +static struct nubus_driver mac8390_driver = { + .probe = mac8390_device_probe, + .remove = mac8390_device_remove, + .driver = { + .name = KBUILD_MODNAME, + .owner = THIS_MODULE, + } +}; + MODULE_AUTHOR("David Huggins-Daines <dhd@debian.org> and others"); MODULE_DESCRIPTION("Macintosh NS8390-based Nubus Ethernet driver"); MODULE_LICENSE("GPL"); -static struct net_device *dev_mac8390; - -int __init init_module(void) +static int __init mac8390_init(void) { - dev_mac8390 = mac8390_probe(-1); - if (IS_ERR(dev_mac8390)) { - pr_warn("mac8390: No card found\n"); - return PTR_ERR(dev_mac8390); - } - return 0; + return nubus_driver_register(&mac8390_driver); } +module_init(mac8390_init); -void __exit cleanup_module(void) +static void __exit mac8390_exit(void) { - unregister_netdev(dev_mac8390); - free_netdev(dev_mac8390); + nubus_driver_unregister(&mac8390_driver); } - -#endif /* MODULE */ +module_exit(mac8390_exit); static const struct net_device_ops mac8390_netdev_ops = { .ndo_open = mac8390_open, @@ -493,9 +481,8 @@ static const struct net_device_ops mac8390_netdev_ops = { #endif }; -static int __init mac8390_initdev(struct net_device *dev, - struct nubus_rsrc *ndev, - enum mac8390_type type) +static int mac8390_initdev(struct net_device *dev, struct nubus_board *board, + enum mac8390_type type) { static u32 fwrd4_offsets[16] = { 0, 4, 8, 12, @@ -546,7 +533,8 @@ static int __init mac8390_initdev(struct net_device *dev, case MAC8390_APPLE: switch (mac8390_testio(dev->mem_start)) { case ACCESS_UNKNOWN: - pr_err("Don't know how to access card memory!\n"); + dev_err(&board->dev, + "Don't know how to access card memory\n"); return -ENODEV; case ACCESS_16: @@ -612,21 +600,18 @@ static int __init mac8390_initdev(struct net_device *dev, break; default: - pr_err("Card type %s is unsupported, sorry\n", - ndev->board->name); + dev_err(&board->dev, "Unsupported card type\n"); return -ENODEV; } __NS8390_init(dev, 0); /* Good, done, now spit out some messages */ - pr_info("%s: %s in slot %X (type %s)\n", - dev->name, ndev->board->name, ndev->board->slot, - cardname[type]); - pr_info("MAC %pM IRQ %d, %d KB shared memory at %#lx, %d-bit access.\n", - dev->dev_addr, dev->irq, - (unsigned int)(dev->mem_end - dev->mem_start) >> 10, - dev->mem_start, access_bitmode ? 32 : 16); + dev_info(&board->dev, "%s (type %s)\n", board->name, cardname[type]); + dev_info(&board->dev, "MAC %pM, IRQ %d, %d KB shared memory at %#lx, %d-bit access.\n", + dev->dev_addr, dev->irq, + (unsigned int)(dev->mem_end - dev->mem_start) >> 10, + dev->mem_start, access_bitmode ? 32 : 16); return 0; } diff --git a/drivers/net/ethernet/8390/mcf8390.c b/drivers/net/ethernet/8390/mcf8390.c index 4bb967bc879e..4ad8031ab669 100644 --- a/drivers/net/ethernet/8390/mcf8390.c +++ b/drivers/net/ethernet/8390/mcf8390.c @@ -38,7 +38,6 @@ static const char version[] = #define NESM_START_PG 0x40 /* First page of TX buffer */ #define NESM_STOP_PG 0x80 /* Last page +1 of RX ring */ -static u32 mcf8390_msg_enable; #ifdef NE2000_ODDOFFSET /* @@ -407,7 +406,6 @@ static int mcf8390_init(struct net_device *dev) static int mcf8390_probe(struct platform_device *pdev) { struct net_device *dev; - struct ei_device *ei_local; struct resource *mem, *irq; resource_size_t msize; int ret; @@ -435,8 +433,6 @@ static int mcf8390_probe(struct platform_device *pdev) SET_NETDEV_DEV(dev, &pdev->dev); platform_set_drvdata(pdev, dev); - ei_local = netdev_priv(dev); - ei_local->msg_enable = mcf8390_msg_enable; dev->irq = irq->start; dev->base_addr = mem->start; diff --git a/drivers/net/ethernet/8390/ne.c b/drivers/net/ethernet/8390/ne.c index 66f47987e2a2..4cdff6e6af89 100644 --- a/drivers/net/ethernet/8390/ne.c +++ b/drivers/net/ethernet/8390/ne.c @@ -485,7 +485,7 @@ static int __init ne_probe1(struct net_device *dev, unsigned long ioaddr) mdelay(10); /* wait 10ms for interrupt to propagate */ outb_p(0x00, ioaddr + EN0_IMR); /* Mask it again. */ dev->irq = probe_irq_off(cookie); - if (netif_msg_probe(ei_local)) + if (ne_msg_enable & NETIF_MSG_PROBE) pr_cont(" autoirq is %d", dev->irq); } else if (dev->irq == 2) /* Fixup for users that don't know that IRQ 2 is really IRQ 9, diff --git a/drivers/net/ethernet/8390/pcnet_cs.c b/drivers/net/ethernet/8390/pcnet_cs.c index bcad4a7fac9f..61e43802b9a5 100644 --- a/drivers/net/ethernet/8390/pcnet_cs.c +++ b/drivers/net/ethernet/8390/pcnet_cs.c @@ -66,7 +66,6 @@ #define PCNET_RDC_TIMEOUT (2*HZ/100) /* Max wait in jiffies for Tx RDC */ static const char *if_names[] = { "auto", "10baseT", "10base2"}; -static u32 pcnet_msg_enable; /*====================================================================*/ @@ -556,7 +555,6 @@ static int pcnet_config(struct pcmcia_device *link) int start_pg, stop_pg, cm_offset; int has_shmem = 0; struct hw_info *local_hw_info; - struct ei_device *ei_local; dev_dbg(&link->dev, "pcnet_config\n"); @@ -606,8 +604,6 @@ static int pcnet_config(struct pcmcia_device *link) mii_phy_probe(dev); SET_NETDEV_DEV(dev, &link->dev); - ei_local = netdev_priv(dev); - ei_local->msg_enable = pcnet_msg_enable; if (register_netdev(dev) != 0) { pr_notice("register_netdev() failed\n"); diff --git a/drivers/net/ethernet/8390/wd.c b/drivers/net/ethernet/8390/wd.c index 6efa2722f850..fb17c2c7e1dd 100644 --- a/drivers/net/ethernet/8390/wd.c +++ b/drivers/net/ethernet/8390/wd.c @@ -299,7 +299,7 @@ static int __init wd_probe1(struct net_device *dev, int ioaddr) outb_p(0x00, nic_addr+EN0_IMR); /* Mask all intrs. again. */ - if (netif_msg_drv(ei_local)) + if (wd_msg_enable & NETIF_MSG_PROBE) pr_cont(" autoirq is %d", dev->irq); if (dev->irq < 2) dev->irq = word16 ? 10 : 5; diff --git a/drivers/net/ethernet/8390/zorro8390.c b/drivers/net/ethernet/8390/zorro8390.c index 6d93956b293b..35a500a21521 100644 --- a/drivers/net/ethernet/8390/zorro8390.c +++ b/drivers/net/ethernet/8390/zorro8390.c @@ -44,8 +44,6 @@ static const char version[] = "8390.c:v1.10cvs 9/23/94 Donald Becker (becker@cesdis.gsfc.nasa.gov)\n"; -static u32 zorro8390_msg_enable; - #include "lib8390.c" #define DRV_NAME "zorro8390" @@ -296,7 +294,6 @@ static int zorro8390_init(struct net_device *dev, unsigned long board, int err; unsigned char SA_prom[32]; int start_page, stop_page; - struct ei_device *ei_local = netdev_priv(dev); static u32 zorro8390_offsets[16] = { 0x00, 0x02, 0x04, 0x06, 0x08, 0x0a, 0x0c, 0x0e, 0x10, 0x12, 0x14, 0x16, 0x18, 0x1a, 0x1c, 0x1e, @@ -388,8 +385,6 @@ static int zorro8390_init(struct net_device *dev, unsigned long board, dev->netdev_ops = &zorro8390_netdev_ops; __NS8390_init(dev, 0); - ei_local->msg_enable = zorro8390_msg_enable; - err = register_netdev(dev); if (err) { free_irq(IRQ_AMIGA_PORTS, dev); diff --git a/drivers/net/ethernet/amd/amd8111e.c b/drivers/net/ethernet/amd/amd8111e.c index 358f7ab77c70..c99e3e845ac0 100644 --- a/drivers/net/ethernet/amd/amd8111e.c +++ b/drivers/net/ethernet/amd/amd8111e.c @@ -649,7 +649,7 @@ static void amd8111e_free_ring(struct amd8111e_priv *lp) static int amd8111e_tx(struct net_device *dev) { struct amd8111e_priv *lp = netdev_priv(dev); - int tx_index = lp->tx_complete_idx & TX_RING_DR_MOD_MASK; + int tx_index; int status; /* Complete all the transmit packet */ while (lp->tx_complete_idx != lp->tx_idx){ diff --git a/drivers/net/ethernet/apple/macmace.c b/drivers/net/ethernet/apple/macmace.c index f17a160dbff2..137cbb470af2 100644 --- a/drivers/net/ethernet/apple/macmace.c +++ b/drivers/net/ethernet/apple/macmace.c @@ -247,8 +247,8 @@ static int mace_probe(struct platform_device *pdev) dev->netdev_ops = &mace_netdev_ops; dev->watchdog_timeo = TX_TIMEOUT; - printk(KERN_INFO "%s: 68K MACE, hardware address %pM\n", - dev->name, dev->dev_addr); + pr_info("Onboard MACE, hardware address %pM, chip revision 0x%04X\n", + dev->dev_addr, mp->chipid); err = register_netdev(dev); if (!err) @@ -589,7 +589,6 @@ static irqreturn_t mace_interrupt(int irq, void *dev_id) else if (fs & (UFLO|LCOL|RTRY)) { ++dev->stats.tx_aborted_errors; if (mb->xmtfs & UFLO) { - printk(KERN_ERR "%s: DMA underrun.\n", dev->name); dev->stats.tx_fifo_errors++; mace_txdma_reset(dev); } @@ -644,10 +643,8 @@ static void mace_dma_rx_frame(struct net_device *dev, struct mace_frame *mf) if (frame_status & (RS_OFLO | RS_CLSN | RS_FRAMERR | RS_FCSERR)) { dev->stats.rx_errors++; - if (frame_status & RS_OFLO) { - printk(KERN_DEBUG "%s: fifo overflow.\n", dev->name); + if (frame_status & RS_OFLO) dev->stats.rx_fifo_errors++; - } if (frame_status & RS_CLSN) dev->stats.collisions++; if (frame_status & RS_FRAMERR) @@ -770,18 +767,4 @@ static struct platform_driver mac_mace_driver = { }, }; -static int __init mac_mace_init_module(void) -{ - if (!MACH_IS_MAC) - return -ENODEV; - - return platform_driver_register(&mac_mace_driver); -} - -static void __exit mac_mace_cleanup_module(void) -{ - platform_driver_unregister(&mac_mace_driver); -} - -module_init(mac_mace_init_module); -module_exit(mac_mace_cleanup_module); +module_platform_driver(mac_mace_driver); diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/Makefile b/drivers/net/ethernet/aquantia/atlantic/hw_atl/Makefile new file mode 100644 index 000000000000..805fa28f391a --- /dev/null +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/Makefile @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0 +# kbuild requires Makefile in a directory to build individual objects diff --git a/drivers/net/ethernet/cavium/liquidio/lio_core.c b/drivers/net/ethernet/cavium/liquidio/lio_core.c index 32ae63b6f20e..8b1ee83134e3 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_core.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_core.c @@ -571,7 +571,8 @@ liquidio_push_packet(u32 octeon_id __attribute__((unused)), napi_gro_receive(napi, skb); - droq->stats.rx_bytes_received += len; + droq->stats.rx_bytes_received += len - + rh->r_dh.len * BYTES_PER_DHLEN_UNIT; droq->stats.rx_pkts_received++; } else { recv_buffer_free(skb); diff --git a/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c b/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c index 00a1d2d13169..9da6f57901a9 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c @@ -878,6 +878,86 @@ static int cudbg_get_payload_range(struct adapter *padap, u8 mem_type, &payload->start, &payload->end); } +static int cudbg_memory_read(struct cudbg_init *pdbg_init, int win, + int mtype, u32 addr, u32 len, void *hbuf) +{ + u32 win_pf, memoffset, mem_aperture, mem_base; + struct adapter *adap = pdbg_init->adap; + u32 pos, offset, resid; + u32 *res_buf; + u64 *buf; + int ret; + + /* Argument sanity checks ... + */ + if (addr & 0x3 || (uintptr_t)hbuf & 0x3) + return -EINVAL; + + buf = (u64 *)hbuf; + + /* Try to do 64-bit reads. Residual will be handled later. */ + resid = len & 0x7; + len -= resid; + + ret = t4_memory_rw_init(adap, win, mtype, &memoffset, &mem_base, + &mem_aperture); + if (ret) + return ret; + + addr = addr + memoffset; + win_pf = is_t4(adap->params.chip) ? 0 : PFNUM_V(adap->pf); + + pos = addr & ~(mem_aperture - 1); + offset = addr - pos; + + /* Set up initial PCI-E Memory Window to cover the start of our + * transfer. + */ + t4_memory_update_win(adap, win, pos | win_pf); + + /* Transfer data from the adapter */ + while (len > 0) { + *buf++ = le64_to_cpu((__force __le64) + t4_read_reg64(adap, mem_base + offset)); + offset += sizeof(u64); + len -= sizeof(u64); + + /* If we've reached the end of our current window aperture, + * move the PCI-E Memory Window on to the next. + */ + if (offset == mem_aperture) { + pos += mem_aperture; + offset = 0; + t4_memory_update_win(adap, win, pos | win_pf); + } + } + + res_buf = (u32 *)buf; + /* Read residual in 32-bit multiples */ + while (resid > sizeof(u32)) { + *res_buf++ = le32_to_cpu((__force __le32) + t4_read_reg(adap, mem_base + offset)); + offset += sizeof(u32); + resid -= sizeof(u32); + + /* If we've reached the end of our current window aperture, + * move the PCI-E Memory Window on to the next. + */ + if (offset == mem_aperture) { + pos += mem_aperture; + offset = 0; + t4_memory_update_win(adap, win, pos | win_pf); + } + } + + /* Transfer residual < 32-bits */ + if (resid) + t4_memory_rw_residual(adap, resid, mem_base + offset, + (u8 *)res_buf, T4_MEMORY_READ); + + return 0; +} + #define CUDBG_YIELD_ITERATION 256 static int cudbg_read_fw_mem(struct cudbg_init *pdbg_init, @@ -937,10 +1017,8 @@ static int cudbg_read_fw_mem(struct cudbg_init *pdbg_init, goto skip_read; spin_lock(&padap->win0_lock); - rc = t4_memory_rw(padap, MEMWIN_NIC, mem_type, - bytes_read, bytes, - (__be32 *)temp_buff.data, - 1); + rc = cudbg_memory_read(pdbg_init, MEMWIN_NIC, mem_type, + bytes_read, bytes, temp_buff.data); spin_unlock(&padap->win0_lock); if (rc) { cudbg_err->sys_err = rc; diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h index 9040e13ce4b7..d3fa53db61ee 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h @@ -1488,6 +1488,11 @@ u32 t4_read_pcie_cfg4(struct adapter *adap, int reg); u32 t4_get_util_window(struct adapter *adap); void t4_setup_memwin(struct adapter *adap, u32 memwin_base, u32 window); +int t4_memory_rw_init(struct adapter *adap, int win, int mtype, u32 *mem_off, + u32 *mem_base, u32 *mem_aperture); +void t4_memory_update_win(struct adapter *adap, int win, u32 addr); +void t4_memory_rw_residual(struct adapter *adap, u32 off, u32 addr, u8 *buf, + int dir); #define T4_MEMORY_WRITE 0 #define T4_MEMORY_READ 1 int t4_memory_rw(struct adapter *adap, int win, int mtype, u32 addr, u32 len, diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c index 3177b0c9bd2d..db92f1858060 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c @@ -1335,12 +1335,6 @@ int __cxgb4_set_filter(struct net_device *dev, int filter_id, return ret; } - /* Clear out any old resources being used by the filter before - * we start constructing the new filter. - */ - if (f->valid) - clear_filter(adapter, f); - if (is_t6(adapter->params.chip) && fs->type && ipv6_addr_type((const struct in6_addr *)fs->val.lip) != IPV6_ADDR_ANY) { diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c index 920bccd6bc40..2c889efc78ea 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c @@ -484,6 +484,117 @@ static int t4_edc_err_read(struct adapter *adap, int idx) } /** + * t4_memory_rw_init - Get memory window relative offset, base, and size. + * @adap: the adapter + * @win: PCI-E Memory Window to use + * @mtype: memory type: MEM_EDC0, MEM_EDC1 or MEM_MC + * @mem_off: memory relative offset with respect to @mtype. + * @mem_base: configured memory base address. + * @mem_aperture: configured memory window aperture. + * + * Get the configured memory window's relative offset, base, and size. + */ +int t4_memory_rw_init(struct adapter *adap, int win, int mtype, u32 *mem_off, + u32 *mem_base, u32 *mem_aperture) +{ + u32 edc_size, mc_size, mem_reg; + + /* Offset into the region of memory which is being accessed + * MEM_EDC0 = 0 + * MEM_EDC1 = 1 + * MEM_MC = 2 -- MEM_MC for chips with only 1 memory controller + * MEM_MC1 = 3 -- for chips with 2 memory controllers (e.g. T5) + * MEM_HMA = 4 + */ + edc_size = EDRAM0_SIZE_G(t4_read_reg(adap, MA_EDRAM0_BAR_A)); + if (mtype == MEM_HMA) { + *mem_off = 2 * (edc_size * 1024 * 1024); + } else if (mtype != MEM_MC1) { + *mem_off = (mtype * (edc_size * 1024 * 1024)); + } else { + mc_size = EXT_MEM0_SIZE_G(t4_read_reg(adap, + MA_EXT_MEMORY0_BAR_A)); + *mem_off = (MEM_MC0 * edc_size + mc_size) * 1024 * 1024; + } + + /* Each PCI-E Memory Window is programmed with a window size -- or + * "aperture" -- which controls the granularity of its mapping onto + * adapter memory. We need to grab that aperture in order to know + * how to use the specified window. The window is also programmed + * with the base address of the Memory Window in BAR0's address + * space. For T4 this is an absolute PCI-E Bus Address. For T5 + * the address is relative to BAR0. + */ + mem_reg = t4_read_reg(adap, + PCIE_MEM_ACCESS_REG(PCIE_MEM_ACCESS_BASE_WIN_A, + win)); + /* a dead adapter will return 0xffffffff for PIO reads */ + if (mem_reg == 0xffffffff) + return -ENXIO; + + *mem_aperture = 1 << (WINDOW_G(mem_reg) + WINDOW_SHIFT_X); + *mem_base = PCIEOFST_G(mem_reg) << PCIEOFST_SHIFT_X; + if (is_t4(adap->params.chip)) + *mem_base -= adap->t4_bar0; + + return 0; +} + +/** + * t4_memory_update_win - Move memory window to specified address. + * @adap: the adapter + * @win: PCI-E Memory Window to use + * @addr: location to move. + * + * Move memory window to specified address. + */ +void t4_memory_update_win(struct adapter *adap, int win, u32 addr) +{ + t4_write_reg(adap, + PCIE_MEM_ACCESS_REG(PCIE_MEM_ACCESS_OFFSET_A, win), + addr); + /* Read it back to ensure that changes propagate before we + * attempt to use the new value. + */ + t4_read_reg(adap, + PCIE_MEM_ACCESS_REG(PCIE_MEM_ACCESS_OFFSET_A, win)); +} + +/** + * t4_memory_rw_residual - Read/Write residual data. + * @adap: the adapter + * @off: relative offset within residual to start read/write. + * @addr: address within indicated memory type. + * @buf: host memory buffer + * @dir: direction of transfer T4_MEMORY_READ (1) or T4_MEMORY_WRITE (0) + * + * Read/Write residual data less than 32-bits. + */ +void t4_memory_rw_residual(struct adapter *adap, u32 off, u32 addr, u8 *buf, + int dir) +{ + union { + u32 word; + char byte[4]; + } last; + unsigned char *bp; + int i; + + if (dir == T4_MEMORY_READ) { + last.word = le32_to_cpu((__force __le32) + t4_read_reg(adap, addr)); + for (bp = (unsigned char *)buf, i = off; i < 4; i++) + bp[i] = last.byte[i]; + } else { + last.word = *buf; + for (i = off; i < 4; i++) + last.byte[i] = 0; + t4_write_reg(adap, addr, + (__force u32)cpu_to_le32(last.word)); + } +} + +/** * t4_memory_rw - read/write EDC 0, EDC 1 or MC via PCIE memory window * @adap: the adapter * @win: PCI-E Memory Window to use @@ -504,8 +615,9 @@ int t4_memory_rw(struct adapter *adap, int win, int mtype, u32 addr, u32 len, void *hbuf, int dir) { u32 pos, offset, resid, memoffset; - u32 edc_size, mc_size, win_pf, mem_reg, mem_aperture, mem_base; + u32 win_pf, mem_aperture, mem_base; u32 *buf; + int ret; /* Argument sanity checks ... */ @@ -521,59 +633,26 @@ int t4_memory_rw(struct adapter *adap, int win, int mtype, u32 addr, resid = len & 0x3; len -= resid; - /* Offset into the region of memory which is being accessed - * MEM_EDC0 = 0 - * MEM_EDC1 = 1 - * MEM_MC = 2 -- MEM_MC for chips with only 1 memory controller - * MEM_MC1 = 3 -- for chips with 2 memory controllers (e.g. T5) - * MEM_HMA = 4 - */ - edc_size = EDRAM0_SIZE_G(t4_read_reg(adap, MA_EDRAM0_BAR_A)); - if (mtype == MEM_HMA) { - memoffset = 2 * (edc_size * 1024 * 1024); - } else if (mtype != MEM_MC1) { - memoffset = (mtype * (edc_size * 1024 * 1024)); - } else { - mc_size = EXT_MEM0_SIZE_G(t4_read_reg(adap, - MA_EXT_MEMORY0_BAR_A)); - memoffset = (MEM_MC0 * edc_size + mc_size) * 1024 * 1024; - } + ret = t4_memory_rw_init(adap, win, mtype, &memoffset, &mem_base, + &mem_aperture); + if (ret) + return ret; /* Determine the PCIE_MEM_ACCESS_OFFSET */ addr = addr + memoffset; - /* Each PCI-E Memory Window is programmed with a window size -- or - * "aperture" -- which controls the granularity of its mapping onto - * adapter memory. We need to grab that aperture in order to know - * how to use the specified window. The window is also programmed - * with the base address of the Memory Window in BAR0's address - * space. For T4 this is an absolute PCI-E Bus Address. For T5 - * the address is relative to BAR0. - */ - mem_reg = t4_read_reg(adap, - PCIE_MEM_ACCESS_REG(PCIE_MEM_ACCESS_BASE_WIN_A, - win)); - mem_aperture = 1 << (WINDOW_G(mem_reg) + WINDOW_SHIFT_X); - mem_base = PCIEOFST_G(mem_reg) << PCIEOFST_SHIFT_X; - if (is_t4(adap->params.chip)) - mem_base -= adap->t4_bar0; win_pf = is_t4(adap->params.chip) ? 0 : PFNUM_V(adap->pf); /* Calculate our initial PCI-E Memory Window Position and Offset into * that Window. */ - pos = addr & ~(mem_aperture-1); + pos = addr & ~(mem_aperture - 1); offset = addr - pos; /* Set up initial PCI-E Memory Window to cover the start of our - * transfer. (Read it back to ensure that changes propagate before we - * attempt to use the new value.) + * transfer. */ - t4_write_reg(adap, - PCIE_MEM_ACCESS_REG(PCIE_MEM_ACCESS_OFFSET_A, win), - pos | win_pf); - t4_read_reg(adap, - PCIE_MEM_ACCESS_REG(PCIE_MEM_ACCESS_OFFSET_A, win)); + t4_memory_update_win(adap, win, pos | win_pf); /* Transfer data to/from the adapter as long as there's an integral * number of 32-bit transfers to complete. @@ -628,12 +707,7 @@ int t4_memory_rw(struct adapter *adap, int win, int mtype, u32 addr, if (offset == mem_aperture) { pos += mem_aperture; offset = 0; - t4_write_reg(adap, - PCIE_MEM_ACCESS_REG(PCIE_MEM_ACCESS_OFFSET_A, - win), pos | win_pf); - t4_read_reg(adap, - PCIE_MEM_ACCESS_REG(PCIE_MEM_ACCESS_OFFSET_A, - win)); + t4_memory_update_win(adap, win, pos | win_pf); } } @@ -642,28 +716,9 @@ int t4_memory_rw(struct adapter *adap, int win, int mtype, u32 addr, * residual amount. The PCI-E Memory Window has already been moved * above (if necessary) to cover this final transfer. */ - if (resid) { - union { - u32 word; - char byte[4]; - } last; - unsigned char *bp; - int i; - - if (dir == T4_MEMORY_READ) { - last.word = le32_to_cpu( - (__force __le32)t4_read_reg(adap, - mem_base + offset)); - for (bp = (unsigned char *)buf, i = resid; i < 4; i++) - bp[i] = last.byte[i]; - } else { - last.word = *buf; - for (i = resid; i < 4; i++) - last.byte[i] = 0; - t4_write_reg(adap, mem_base + offset, - (__force u32)cpu_to_le32(last.word)); - } - } + if (resid) + t4_memory_rw_residual(adap, resid, mem_base + offset, + (u8 *)buf, dir); return 0; } @@ -6036,6 +6091,7 @@ unsigned int t4_get_tp_ch_map(struct adapter *adap, int pidx) case CHELSIO_T6: switch (nports) { + case 1: case 2: return 1 << pidx; } break; diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c index b7e79e64d2ed..361de86b65b9 100644 --- a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c @@ -155,8 +155,6 @@ void t4vf_os_link_changed(struct adapter *adapter, int pidx, int link_ok) const char *fc; const struct port_info *pi = netdev_priv(dev); - netif_carrier_on(dev); - switch (pi->link_cfg.speed) { case 100: s = "100Mbps"; @@ -202,7 +200,6 @@ void t4vf_os_link_changed(struct adapter *adapter, int pidx, int link_ok) netdev_info(dev, "link up, %s, full-duplex, %s PAUSE\n", s, fc); } else { - netif_carrier_off(dev); netdev_info(dev, "link down\n"); } } @@ -278,6 +275,17 @@ static int link_start(struct net_device *dev) */ if (ret == 0) ret = t4vf_enable_vi(pi->adapter, pi->viid, true, true); + + /* The Virtual Interfaces are connected to an internal switch on the + * chip which allows VIs attached to the same port to talk to each + * other even when the port link is down. As a result, we generally + * want to always report a VI's link as being "up", provided there are + * no errors in enabling vi. + */ + + if (ret == 0) + netif_carrier_on(dev); + return ret; } diff --git a/drivers/net/ethernet/cirrus/mac89x0.c b/drivers/net/ethernet/cirrus/mac89x0.c index 977d4c2c759d..3f8fe8fd79cc 100644 --- a/drivers/net/ethernet/cirrus/mac89x0.c +++ b/drivers/net/ethernet/cirrus/mac89x0.c @@ -56,21 +56,11 @@ local_irq_{dis,en}able() */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + static const char version[] = "cs89x0.c:v1.02 11/26/96 Russell Nelson <nelson@crynwr.com>\n"; -/* ======================= configure the driver here ======================= */ - -/* use 0 for production, 1 for verification, >2 for debug */ -#ifndef NET_DEBUG -#define NET_DEBUG 0 -#endif - -/* ======================= end of configuration ======================= */ - - -/* Always include 'config.h' first in case the user wants to turn on - or override something. */ #include <linux/module.h> /* @@ -93,6 +83,7 @@ static const char version[] = #include <linux/errno.h> #include <linux/init.h> #include <linux/netdevice.h> +#include <linux/platform_device.h> #include <linux/etherdevice.h> #include <linux/skbuff.h> #include <linux/delay.h> @@ -105,24 +96,22 @@ static const char version[] = #include "cs89x0.h" -static unsigned int net_debug = NET_DEBUG; +static int debug = -1; +module_param(debug, int, 0); +MODULE_PARM_DESC(debug, "debug message level"); /* Information that need to be kept for each board. */ struct net_local { + int msg_enable; int chip_type; /* one of: CS8900, CS8920, CS8920M */ char chip_revision; /* revision letter of the chip ('A'...) */ int send_cmd; /* the propercommand used to send a packet. */ int rx_mode; int curr_rx_cfg; int send_underrun; /* keep track of how many underruns in a row we get */ - struct sk_buff *skb; }; /* Index to functions, as function prototypes. */ - -#if 0 -extern void reset_chip(struct net_device *dev); -#endif static int net_open(struct net_device *dev); static int net_send_packet(struct sk_buff *skb, struct net_device *dev); static irqreturn_t net_interrupt(int irq, void *dev_id); @@ -132,10 +121,6 @@ static int net_close(struct net_device *dev); static struct net_device_stats *net_get_stats(struct net_device *dev); static int set_mac_address(struct net_device *dev, void *addr); - -/* Example routines you must write ;->. */ -#define tx_done(dev) 1 - /* For reading/writing registers ISA-style */ static inline int readreg_io(struct net_device *dev, int portno) @@ -176,12 +161,10 @@ static const struct net_device_ops mac89x0_netdev_ops = { /* Probe for the CS8900 card in slot E. We won't bother looking anywhere else until we have a really good reason to do so. */ -struct net_device * __init mac89x0_probe(int unit) +static int mac89x0_device_probe(struct platform_device *pdev) { struct net_device *dev; - static int once_is_enough; struct net_local *lp; - static unsigned version_printed; int i, slot; unsigned rev_type = 0; unsigned long ioaddr; @@ -189,21 +172,9 @@ struct net_device * __init mac89x0_probe(int unit) int err = -ENODEV; struct nubus_rsrc *fres; - if (!MACH_IS_MAC) - return ERR_PTR(-ENODEV); - dev = alloc_etherdev(sizeof(struct net_local)); if (!dev) - return ERR_PTR(-ENOMEM); - - if (unit >= 0) { - sprintf(dev->name, "eth%d", unit); - netdev_boot_setup_check(dev); - } - - if (once_is_enough) - goto out; - once_is_enough = 1; + return -ENOMEM; /* We might have to parameterize this later */ slot = 0xE; @@ -230,9 +201,13 @@ struct net_device * __init mac89x0_probe(int unit) if (sig != swab16(CHIP_EISA_ID_SIG)) goto out; + SET_NETDEV_DEV(dev, &pdev->dev); + /* Initialize the net_device structure. */ lp = netdev_priv(dev); + lp->msg_enable = netif_msg_init(debug, 0); + /* Fill in the 'dev' fields. */ dev->base_addr = ioaddr; dev->mem_start = (unsigned long) @@ -255,19 +230,16 @@ struct net_device * __init mac89x0_probe(int unit) if (lp->chip_type != CS8900 && lp->chip_revision >= 'C') lp->send_cmd = TX_NOW; - if (net_debug && version_printed++ == 0) - printk(version); + netif_dbg(lp, drv, dev, "%s", version); - printk(KERN_INFO "%s: cs89%c0%s rev %c found at %#8lx", - dev->name, - lp->chip_type==CS8900?'0':'2', - lp->chip_type==CS8920M?"M":"", - lp->chip_revision, - dev->base_addr); + pr_info("cs89%c0%s rev %c found at %#8lx\n", + lp->chip_type == CS8900 ? '0' : '2', + lp->chip_type == CS8920M ? "M" : "", + lp->chip_revision, dev->base_addr); /* Try to read the MAC address */ if ((readreg(dev, PP_SelfST) & (EEPROM_PRESENT | EEPROM_OK)) == 0) { - printk("\nmac89x0: No EEPROM, giving up now.\n"); + pr_info("No EEPROM, giving up now.\n"); goto out1; } else { for (i = 0; i < ETH_ALEN; i += 2) { @@ -282,39 +254,23 @@ struct net_device * __init mac89x0_probe(int unit) /* print the IRQ and ethernet address. */ - printk(" IRQ %d ADDR %pM\n", dev->irq, dev->dev_addr); + pr_info("MAC %pM, IRQ %d\n", dev->dev_addr, dev->irq); dev->netdev_ops = &mac89x0_netdev_ops; err = register_netdev(dev); if (err) goto out1; - return NULL; + + platform_set_drvdata(pdev, dev); + return 0; out1: nubus_writew(0, dev->base_addr + ADD_PORT); out: free_netdev(dev); - return ERR_PTR(err); + return err; } -#if 0 -/* This is useful for something, but I don't know what yet. */ -void __init reset_chip(struct net_device *dev) -{ - int reset_start_time; - - writereg(dev, PP_SelfCTL, readreg(dev, PP_SelfCTL) | POWER_ON_RESET); - - /* wait 30 ms */ - msleep_interruptible(30); - - /* Wait until the chip is reset */ - reset_start_time = jiffies; - while( (readreg(dev, PP_SelfST) & INIT_DONE) == 0 && jiffies - reset_start_time < 2) - ; -} -#endif - /* Open/initialize the board. This is called (in the current kernel) sometime after booting when the 'ifconfig' program is run. @@ -374,11 +330,9 @@ net_send_packet(struct sk_buff *skb, struct net_device *dev) struct net_local *lp = netdev_priv(dev); unsigned long flags; - if (net_debug > 3) - printk("%s: sent %d byte packet of type %x\n", - dev->name, skb->len, - (skb->data[ETH_ALEN+ETH_ALEN] << 8) - | skb->data[ETH_ALEN+ETH_ALEN+1]); + netif_dbg(lp, tx_queued, dev, "sent %d byte packet of type %x\n", + skb->len, skb->data[ETH_ALEN + ETH_ALEN] << 8 | + skb->data[ETH_ALEN + ETH_ALEN + 1]); /* keep the upload from being interrupted, since we ask the chip to start transmitting before the @@ -416,11 +370,6 @@ static irqreturn_t net_interrupt(int irq, void *dev_id) struct net_local *lp; int ioaddr, status; - if (dev == NULL) { - printk ("net_interrupt(): irq %d for unknown device.\n", irq); - return IRQ_NONE; - } - ioaddr = dev->base_addr; lp = netdev_priv(dev); @@ -432,7 +381,7 @@ static irqreturn_t net_interrupt(int irq, void *dev_id) faster than you can read them off, you're screwed. Hasta la vista, baby! */ while ((status = swab16(nubus_readw(dev->base_addr + ISQ_PORT)))) { - if (net_debug > 4)printk("%s: event=%04x\n", dev->name, status); + netif_dbg(lp, intr, dev, "status=%04x\n", status); switch(status & ISQ_EVENT_MASK) { case ISQ_RECEIVER_EVENT: /* Got a packet(s). */ @@ -462,7 +411,7 @@ static irqreturn_t net_interrupt(int irq, void *dev_id) netif_wake_queue(dev); } if (status & TX_UNDERRUN) { - if (net_debug > 0) printk("%s: transmit underrun\n", dev->name); + netif_dbg(lp, tx_err, dev, "transmit underrun\n"); lp->send_underrun++; if (lp->send_underrun == 3) lp->send_cmd = TX_AFTER_381; else if (lp->send_underrun == 6) lp->send_cmd = TX_AFTER_ALL; @@ -483,6 +432,7 @@ static irqreturn_t net_interrupt(int irq, void *dev_id) static void net_rx(struct net_device *dev) { + struct net_local *lp = netdev_priv(dev); struct sk_buff *skb; int status, length; @@ -506,7 +456,6 @@ net_rx(struct net_device *dev) /* Malloc up new buffer. */ skb = alloc_skb(length, GFP_ATOMIC); if (skb == NULL) { - printk("%s: Memory squeeze, dropping packet.\n", dev->name); dev->stats.rx_dropped++; return; } @@ -515,10 +464,9 @@ net_rx(struct net_device *dev) skb_copy_to_linear_data(skb, (void *)(dev->mem_start + PP_RxFrame), length); - if (net_debug > 3)printk("%s: received %d byte packet of type %x\n", - dev->name, length, - (skb->data[ETH_ALEN+ETH_ALEN] << 8) - | skb->data[ETH_ALEN+ETH_ALEN+1]); + netif_dbg(lp, rx_status, dev, "received %d byte packet of type %x\n", + length, skb->data[ETH_ALEN + ETH_ALEN] << 8 | + skb->data[ETH_ALEN + ETH_ALEN + 1]); skb->protocol=eth_type_trans(skb,dev); netif_rx(skb); @@ -594,7 +542,7 @@ static int set_mac_address(struct net_device *dev, void *addr) return -EADDRNOTAVAIL; memcpy(dev->dev_addr, saddr->sa_data, ETH_ALEN); - printk("%s: Setting MAC address to %pM\n", dev->name, dev->dev_addr); + netdev_info(dev, "Setting MAC address to %pM\n", dev->dev_addr); /* set the Ethernet address */ for (i=0; i < ETH_ALEN/2; i++) @@ -603,32 +551,24 @@ static int set_mac_address(struct net_device *dev, void *addr) return 0; } -#ifdef MODULE - -static struct net_device *dev_cs89x0; -static int debug; - -module_param(debug, int, 0); -MODULE_PARM_DESC(debug, "CS89[02]0 debug level (0-5)"); MODULE_LICENSE("GPL"); -int __init -init_module(void) +static int mac89x0_device_remove(struct platform_device *pdev) { - net_debug = debug; - dev_cs89x0 = mac89x0_probe(-1); - if (IS_ERR(dev_cs89x0)) { - printk(KERN_WARNING "mac89x0.c: No card found\n"); - return PTR_ERR(dev_cs89x0); - } + struct net_device *dev = platform_get_drvdata(pdev); + + unregister_netdev(dev); + nubus_writew(0, dev->base_addr + ADD_PORT); + free_netdev(dev); return 0; } -void -cleanup_module(void) -{ - unregister_netdev(dev_cs89x0); - nubus_writew(0, dev_cs89x0->base_addr + ADD_PORT); - free_netdev(dev_cs89x0); -} -#endif /* MODULE */ +static struct platform_driver mac89x0_platform_driver = { + .probe = mac89x0_device_probe, + .remove = mac89x0_device_remove, + .driver = { + .name = "mac89x0", + }, +}; + +module_platform_driver(mac89x0_platform_driver); diff --git a/drivers/net/ethernet/cisco/enic/enic.h b/drivers/net/ethernet/cisco/enic/enic.h index 9b218f0e5a4c..0dd64acd2a3f 100644 --- a/drivers/net/ethernet/cisco/enic/enic.h +++ b/drivers/net/ethernet/cisco/enic/enic.h @@ -33,7 +33,7 @@ #define DRV_NAME "enic" #define DRV_DESCRIPTION "Cisco VIC Ethernet NIC Driver" -#define DRV_VERSION "2.3.0.45" +#define DRV_VERSION "2.3.0.53" #define DRV_COPYRIGHT "Copyright 2008-2013 Cisco Systems, Inc" #define ENIC_BARS_MAX 6 @@ -140,6 +140,7 @@ struct enic_rfs_flw_tbl { struct vxlan_offload { u16 vxlan_udp_port_number; u8 patch_level; + u8 flags; }; /* Per-instance private data structure */ diff --git a/drivers/net/ethernet/cisco/enic/enic_ethtool.c b/drivers/net/ethernet/cisco/enic/enic_ethtool.c index efb9333c7cf8..869006c2002d 100644 --- a/drivers/net/ethernet/cisco/enic/enic_ethtool.c +++ b/drivers/net/ethernet/cisco/enic/enic_ethtool.c @@ -474,6 +474,39 @@ static int enic_grxclsrule(struct enic *enic, struct ethtool_rxnfc *cmd) return 0; } +static int enic_get_rx_flow_hash(struct enic *enic, struct ethtool_rxnfc *cmd) +{ + cmd->data = 0; + + switch (cmd->flow_type) { + case TCP_V6_FLOW: + case TCP_V4_FLOW: + cmd->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3; + /* Fall through */ + case UDP_V6_FLOW: + case UDP_V4_FLOW: + if (vnic_dev_capable_udp_rss(enic->vdev)) + cmd->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3; + /* Fall through */ + case SCTP_V4_FLOW: + case AH_ESP_V4_FLOW: + case AH_V4_FLOW: + case ESP_V4_FLOW: + case SCTP_V6_FLOW: + case AH_ESP_V6_FLOW: + case AH_V6_FLOW: + case ESP_V6_FLOW: + case IPV4_FLOW: + case IPV6_FLOW: + cmd->data |= RXH_IP_SRC | RXH_IP_DST; + break; + default: + return -EINVAL; + } + + return 0; +} + static int enic_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd, u32 *rule_locs) { @@ -500,6 +533,9 @@ static int enic_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd, ret = enic_grxclsrule(enic, cmd); spin_unlock_bh(&enic->rfs_h.lock); break; + case ETHTOOL_GRXFH: + ret = enic_get_rx_flow_hash(enic, cmd); + break; default: ret = -EOPNOTSUPP; break; diff --git a/drivers/net/ethernet/cisco/enic/enic_main.c b/drivers/net/ethernet/cisco/enic/enic_main.c index f202ba72a811..a25fb95492a0 100644 --- a/drivers/net/ethernet/cisco/enic/enic_main.c +++ b/drivers/net/ethernet/cisco/enic/enic_main.c @@ -191,8 +191,16 @@ static void enic_udp_tunnel_add(struct net_device *netdev, goto error; } - if (ti->sa_family != AF_INET) { - netdev_info(netdev, "vxlan: only IPv4 offload supported"); + switch (ti->sa_family) { + case AF_INET6: + if (!(enic->vxlan.flags & ENIC_VXLAN_OUTER_IPV6)) { + netdev_info(netdev, "vxlan: only IPv4 offload supported"); + goto error; + } + /* Fall through */ + case AF_INET: + break; + default: goto error; } @@ -204,6 +212,11 @@ static void enic_udp_tunnel_add(struct net_device *netdev, goto error; } + if ((vnic_dev_get_res_count(enic->vdev, RES_TYPE_WQ) != 1) && + !(enic->vxlan.flags & ENIC_VXLAN_MULTI_WQ)) { + netdev_info(netdev, "vxlan: vxlan offload with multi wq not supported on this adapter"); + goto error; + } err = vnic_dev_overlay_offload_cfg(enic->vdev, OVERLAY_CFG_VXLAN_PORT_UPDATE, @@ -271,22 +284,37 @@ static netdev_features_t enic_features_check(struct sk_buff *skb, struct enic *enic = netdev_priv(dev); struct udphdr *udph; u16 port = 0; - u16 proto; + u8 proto; if (!skb->encapsulation) return features; features = vxlan_features_check(skb, features); - /* hardware only supports IPv4 vxlan tunnel */ - if (vlan_get_protocol(skb) != htons(ETH_P_IP)) + switch (vlan_get_protocol(skb)) { + case htons(ETH_P_IPV6): + if (!(enic->vxlan.flags & ENIC_VXLAN_OUTER_IPV6)) + goto out; + proto = ipv6_hdr(skb)->nexthdr; + break; + case htons(ETH_P_IP): + proto = ip_hdr(skb)->protocol; + break; + default: goto out; + } - /* hardware does not support offload of ipv6 inner pkt */ - if (eth->h_proto != ntohs(ETH_P_IP)) + switch (eth->h_proto) { + case ntohs(ETH_P_IPV6): + if (!(enic->vxlan.flags & ENIC_VXLAN_INNER_IPV6)) + goto out; + /* Fall through */ + case ntohs(ETH_P_IP): + break; + default: goto out; + } - proto = ip_hdr(skb)->protocol; if (proto == IPPROTO_UDP) { udph = udp_hdr(skb); @@ -635,12 +663,25 @@ static int enic_queue_wq_skb_csum_l4(struct enic *enic, struct vnic_wq *wq, static void enic_preload_tcp_csum_encap(struct sk_buff *skb) { - if (skb->protocol == cpu_to_be16(ETH_P_IP)) { + const struct ethhdr *eth = (struct ethhdr *)skb_inner_mac_header(skb); + + switch (eth->h_proto) { + case ntohs(ETH_P_IP): inner_ip_hdr(skb)->check = 0; inner_tcp_hdr(skb)->check = ~csum_tcpudp_magic(inner_ip_hdr(skb)->saddr, inner_ip_hdr(skb)->daddr, 0, IPPROTO_TCP, 0); + break; + case ntohs(ETH_P_IPV6): + inner_tcp_hdr(skb)->check = + ~csum_ipv6_magic(&inner_ipv6_hdr(skb)->saddr, + &inner_ipv6_hdr(skb)->daddr, 0, + IPPROTO_TCP, 0); + break; + default: + WARN_ONCE(1, "Non ipv4/ipv6 inner pkt for encap offload"); + break; } } @@ -1898,6 +1939,8 @@ static int enic_open(struct net_device *netdev) } for (i = 0; i < enic->rq_count; i++) { + /* enable rq before updating rq desc */ + vnic_rq_enable(&enic->rq[i]); vnic_rq_fill(&enic->rq[i], enic_rq_alloc_buf); /* Need at least one buffer on ring to get going */ if (vnic_rq_desc_used(&enic->rq[i]) == 0) { @@ -1909,8 +1952,6 @@ static int enic_open(struct net_device *netdev) for (i = 0; i < enic->wq_count; i++) vnic_wq_enable(&enic->wq[i]); - for (i = 0; i < enic->rq_count; i++) - vnic_rq_enable(&enic->rq[i]); if (!enic_is_dynamic(enic) && !enic_is_sriov_vf(enic)) enic_dev_add_station_addr(enic); @@ -1936,8 +1977,12 @@ static int enic_open(struct net_device *netdev) return 0; err_out_free_rq: - for (i = 0; i < enic->rq_count; i++) + for (i = 0; i < enic->rq_count; i++) { + err = vnic_rq_disable(&enic->rq[i]); + if (err) + return err; vnic_rq_clean(&enic->rq[i], enic_free_rq_buf); + } enic_dev_notify_unset(enic); err_out_free_intr: enic_unset_affinity_hint(enic); @@ -2151,9 +2196,10 @@ static int enic_dev_wait(struct vnic_dev *vdev, static int enic_dev_open(struct enic *enic) { int err; + u32 flags = CMD_OPENF_IG_DESCCACHE; err = enic_dev_wait(enic->vdev, vnic_dev_open, - vnic_dev_open_done, 0); + vnic_dev_open_done, flags); if (err) dev_err(enic_get_dev(enic), "vNIC device open failed, err %d\n", err); @@ -2275,7 +2321,7 @@ static int enic_set_rss_nic_cfg(struct enic *enic) { struct device *dev = enic_get_dev(enic); const u8 rss_default_cpu = 0; - const u8 rss_hash_type = NIC_CFG_RSS_HASH_TYPE_IPV4 | + u8 rss_hash_type = NIC_CFG_RSS_HASH_TYPE_IPV4 | NIC_CFG_RSS_HASH_TYPE_TCP_IPV4 | NIC_CFG_RSS_HASH_TYPE_IPV6 | NIC_CFG_RSS_HASH_TYPE_TCP_IPV6; @@ -2283,6 +2329,8 @@ static int enic_set_rss_nic_cfg(struct enic *enic) const u8 rss_base_cpu = 0; u8 rss_enable = ENIC_SETTING(enic, RSS) && (enic->rq_count > 1); + if (vnic_dev_capable_udp_rss(enic->vdev)) + rss_hash_type |= NIC_CFG_RSS_HASH_TYPE_UDP; if (rss_enable) { if (!enic_set_rsskey(enic)) { if (enic_set_rsscpu(enic, rss_hash_bits)) { @@ -2901,9 +2949,11 @@ static int enic_probe(struct pci_dev *pdev, const struct pci_device_id *ent) netdev->hw_features |= NETIF_F_RXCSUM; if (ENIC_SETTING(enic, VXLAN)) { u64 patch_level; + u64 a1 = 0; netdev->hw_enc_features |= NETIF_F_RXCSUM | NETIF_F_TSO | + NETIF_F_TSO6 | NETIF_F_TSO_ECN | NETIF_F_GSO_UDP_TUNNEL | NETIF_F_HW_CSUM | @@ -2922,9 +2972,10 @@ static int enic_probe(struct pci_dev *pdev, const struct pci_device_id *ent) */ err = vnic_dev_get_supported_feature_ver(enic->vdev, VIC_FEATURE_VXLAN, - &patch_level); + &patch_level, &a1); if (err) patch_level = 0; + enic->vxlan.flags = (u8)a1; /* mask bits that are supported by driver */ patch_level &= BIT_ULL(0) | BIT_ULL(2); diff --git a/drivers/net/ethernet/cisco/enic/vnic_dev.c b/drivers/net/ethernet/cisco/enic/vnic_dev.c index 39bad67422dd..a2b376055b2d 100644 --- a/drivers/net/ethernet/cisco/enic/vnic_dev.c +++ b/drivers/net/ethernet/cisco/enic/vnic_dev.c @@ -1269,16 +1269,32 @@ int vnic_dev_overlay_offload_cfg(struct vnic_dev *vdev, u8 overlay, } int vnic_dev_get_supported_feature_ver(struct vnic_dev *vdev, u8 feature, - u64 *supported_versions) + u64 *supported_versions, u64 *a1) { u64 a0 = feature; int wait = 1000; - u64 a1 = 0; int ret; - ret = vnic_dev_cmd(vdev, CMD_GET_SUPP_FEATURE_VER, &a0, &a1, wait); + ret = vnic_dev_cmd(vdev, CMD_GET_SUPP_FEATURE_VER, &a0, a1, wait); if (!ret) *supported_versions = a0; return ret; } + +bool vnic_dev_capable_udp_rss(struct vnic_dev *vdev) +{ + u64 a0 = CMD_NIC_CFG, a1 = 0; + u64 rss_hash_type; + int wait = 1000; + int err; + + err = vnic_dev_cmd(vdev, CMD_CAPABILITY, &a0, &a1, wait); + if (err || !a0) + return 0; + + rss_hash_type = (a1 >> NIC_CFG_RSS_HASH_TYPE_SHIFT) & + NIC_CFG_RSS_HASH_TYPE_MASK_FIELD; + + return (rss_hash_type & NIC_CFG_RSS_HASH_TYPE_UDP); +} diff --git a/drivers/net/ethernet/cisco/enic/vnic_dev.h b/drivers/net/ethernet/cisco/enic/vnic_dev.h index 9d43d6bb9907..59d4cc8fbb85 100644 --- a/drivers/net/ethernet/cisco/enic/vnic_dev.h +++ b/drivers/net/ethernet/cisco/enic/vnic_dev.h @@ -183,6 +183,7 @@ int vnic_dev_overlay_offload_ctrl(struct vnic_dev *vdev, u8 overlay, u8 config); int vnic_dev_overlay_offload_cfg(struct vnic_dev *vdev, u8 overlay, u16 vxlan_udp_port_number); int vnic_dev_get_supported_feature_ver(struct vnic_dev *vdev, u8 feature, - u64 *supported_versions); + u64 *supported_versions, u64 *a1); +bool vnic_dev_capable_udp_rss(struct vnic_dev *vdev); #endif /* _VNIC_DEV_H_ */ diff --git a/drivers/net/ethernet/cisco/enic/vnic_devcmd.h b/drivers/net/ethernet/cisco/enic/vnic_devcmd.h index d83880b0d468..41de4ba622a1 100644 --- a/drivers/net/ethernet/cisco/enic/vnic_devcmd.h +++ b/drivers/net/ethernet/cisco/enic/vnic_devcmd.h @@ -439,6 +439,7 @@ enum vnic_devcmd_cmd { /* flags for CMD_OPEN */ #define CMD_OPENF_OPROM 0x1 /* open coming from option rom */ +#define CMD_OPENF_IG_DESCCACHE 0x2 /* Do not flush IG DESC cache */ /* flags for CMD_INIT */ #define CMD_INITF_DEFAULT_MAC 0x1 /* init with default mac addr */ @@ -697,6 +698,10 @@ enum overlay_ofld_cmd { #define OVERLAY_CFG_VXLAN_PORT_UPDATE 0 +#define ENIC_VXLAN_INNER_IPV6 BIT(0) +#define ENIC_VXLAN_OUTER_IPV6 BIT(1) +#define ENIC_VXLAN_MULTI_WQ BIT(2) + /* Use this enum to get the supported versions for each of these features * If you need to use the devcmd_get_supported_feature_version(), add * the new feature into this enum and install function handler in devcmd.c diff --git a/drivers/net/ethernet/cisco/enic/vnic_nic.h b/drivers/net/ethernet/cisco/enic/vnic_nic.h index 995a50dd4c99..5a93db0d7afc 100644 --- a/drivers/net/ethernet/cisco/enic/vnic_nic.h +++ b/drivers/net/ethernet/cisco/enic/vnic_nic.h @@ -47,6 +47,7 @@ #define NIC_CFG_RSS_HASH_TYPE_TCP_IPV6 (1 << 4) #define NIC_CFG_RSS_HASH_TYPE_IPV6_EX (1 << 5) #define NIC_CFG_RSS_HASH_TYPE_TCP_IPV6_EX (1 << 6) +#define NIC_CFG_RSS_HASH_TYPE_UDP (1 << 7) static inline void vnic_set_nic_cfg(u32 *nic_cfg, u8 rss_default_cpu, u8 rss_hash_type, diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.c b/drivers/net/ethernet/emulex/benet/be_cmds.c index 1a49297224ed..ff92ab1daeb8 100644 --- a/drivers/net/ethernet/emulex/benet/be_cmds.c +++ b/drivers/net/ethernet/emulex/benet/be_cmds.c @@ -19,7 +19,7 @@ #include "be.h" #include "be_cmds.h" -char *be_misconfig_evt_port_state[] = { +const char * const be_misconfig_evt_port_state[] = { "Physical Link is functional", "Optics faulted/incorrectly installed/not installed - Reseat optics. If issue not resolved, replace.", "Optics of two types installed – Remove one optic or install matching pair of optics.", diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.h b/drivers/net/ethernet/emulex/benet/be_cmds.h index 09da2d82c2f0..e8b43cf44b6f 100644 --- a/drivers/net/ethernet/emulex/benet/be_cmds.h +++ b/drivers/net/ethernet/emulex/benet/be_cmds.h @@ -201,7 +201,7 @@ enum { phy_state == BE_PHY_UNQUALIFIED || \ phy_state == BE_PHY_UNCERTIFIED) -extern char *be_misconfig_evt_port_state[]; +extern const char * const be_misconfig_evt_port_state[]; /* async event indicating misconfigured port */ struct be_async_event_misconfig_port { diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c index 7caa8da48421..159dc2df878d 100644 --- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c +++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c @@ -454,6 +454,16 @@ static void dpaa_set_rx_mode(struct net_device *net_dev) err); } + if (!!(net_dev->flags & IFF_ALLMULTI) != priv->mac_dev->allmulti) { + priv->mac_dev->allmulti = !priv->mac_dev->allmulti; + err = priv->mac_dev->set_allmulti(priv->mac_dev->fman_mac, + priv->mac_dev->allmulti); + if (err < 0) + netif_err(priv, drv, net_dev, + "mac_dev->set_allmulti() = %d\n", + err); + } + err = priv->mac_dev->set_multi(net_dev, priv->mac_dev); if (err < 0) netif_err(priv, drv, net_dev, "mac_dev->set_multi() = %d\n", @@ -1916,8 +1926,10 @@ static int skb_to_sg_fd(struct dpaa_priv *priv, goto csum_failed; } + /* SGT[0] is used by the linear part */ sgt = (struct qm_sg_entry *)(sgt_buf + priv->tx_headroom); - qm_sg_entry_set_len(&sgt[0], skb_headlen(skb)); + frag_len = skb_headlen(skb); + qm_sg_entry_set_len(&sgt[0], frag_len); sgt[0].bpid = FSL_DPAA_BPID_INV; sgt[0].offset = 0; addr = dma_map_single(dev, skb->data, @@ -1930,9 +1942,9 @@ static int skb_to_sg_fd(struct dpaa_priv *priv, qm_sg_entry_set64(&sgt[0], addr); /* populate the rest of SGT entries */ - frag = &skb_shinfo(skb)->frags[0]; - frag_len = frag->size; - for (i = 1; i <= nr_frags; i++, frag++) { + for (i = 0; i < nr_frags; i++) { + frag = &skb_shinfo(skb)->frags[i]; + frag_len = frag->size; WARN_ON(!skb_frag_page(frag)); addr = skb_frag_dma_map(dev, frag, 0, frag_len, dma_dir); @@ -1942,15 +1954,16 @@ static int skb_to_sg_fd(struct dpaa_priv *priv, goto sg_map_failed; } - qm_sg_entry_set_len(&sgt[i], frag_len); - sgt[i].bpid = FSL_DPAA_BPID_INV; - sgt[i].offset = 0; + qm_sg_entry_set_len(&sgt[i + 1], frag_len); + sgt[i + 1].bpid = FSL_DPAA_BPID_INV; + sgt[i + 1].offset = 0; /* keep the offset in the address */ - qm_sg_entry_set64(&sgt[i], addr); - frag_len = frag->size; + qm_sg_entry_set64(&sgt[i + 1], addr); } - qm_sg_entry_set_f(&sgt[i - 1], frag_len); + + /* Set the final bit in the last used entry of the SGT */ + qm_sg_entry_set_f(&sgt[nr_frags], frag_len); qm_fd_set_sg(fd, priv->tx_headroom, skb->len); @@ -2052,19 +2065,23 @@ static int dpaa_start_xmit(struct sk_buff *skb, struct net_device *net_dev) /* MAX_SKB_FRAGS is equal or larger than our dpaa_SGT_MAX_ENTRIES; * make sure we don't feed FMan with more fragments than it supports. */ - if (nonlinear && - likely(skb_shinfo(skb)->nr_frags < DPAA_SGT_MAX_ENTRIES)) { - /* Just create a S/G fd based on the skb */ - err = skb_to_sg_fd(priv, skb, &fd); - percpu_priv->tx_frag_skbuffs++; - } else { + if (unlikely(nonlinear && + (skb_shinfo(skb)->nr_frags >= DPAA_SGT_MAX_ENTRIES))) { /* If the egress skb contains more fragments than we support * we have no choice but to linearize it ourselves. */ - if (unlikely(nonlinear) && __skb_linearize(skb)) + if (__skb_linearize(skb)) goto enomem; - /* Finally, create a contig FD from this skb */ + nonlinear = skb_is_nonlinear(skb); + } + + if (nonlinear) { + /* Just create a S/G fd based on the skb */ + err = skb_to_sg_fd(priv, skb, &fd); + percpu_priv->tx_frag_skbuffs++; + } else { + /* Create a contig FD from this skb */ err = skb_to_contig_fd(priv, skb, &fd, &offset); } if (unlikely(err < 0)) @@ -2201,14 +2218,8 @@ static enum qman_cb_dqrr_result rx_error_dqrr(struct qman_portal *portal, if (dpaa_eth_napi_schedule(percpu_priv, portal)) return qman_cb_dqrr_stop; - if (dpaa_eth_refill_bpools(priv)) - /* Unable to refill the buffer pool due to insufficient - * system memory. Just release the frame back into the pool, - * otherwise we'll soon end up with an empty buffer pool. - */ - dpaa_fd_release(net_dev, &dq->fd); - else - dpaa_rx_error(net_dev, priv, percpu_priv, &dq->fd, fq->fqid); + dpaa_eth_refill_bpools(priv); + dpaa_rx_error(net_dev, priv, percpu_priv, &dq->fd, fq->fqid); return qman_cb_dqrr_consume; } @@ -2766,7 +2777,7 @@ static int dpaa_eth_probe(struct platform_device *pdev) priv->channel = (u16)channel; - /* Start a thread that will walk the CPUs with affine portals + /* Walk the CPUs with affine portals * and add this pool channel to each's dequeue mask. */ dpaa_eth_add_channel(priv->channel); diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c b/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c index faea674094b9..85306d1b2acf 100644 --- a/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c +++ b/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c @@ -211,7 +211,7 @@ static int dpaa_set_pauseparam(struct net_device *net_dev, if (epause->rx_pause) newadv = ADVERTISED_Pause | ADVERTISED_Asym_Pause; if (epause->tx_pause) - newadv |= ADVERTISED_Asym_Pause; + newadv ^= ADVERTISED_Asym_Pause; oldadv = phydev->advertising & (ADVERTISED_Pause | ADVERTISED_Asym_Pause); diff --git a/drivers/net/ethernet/freescale/fman/fman_dtsec.c b/drivers/net/ethernet/freescale/fman/fman_dtsec.c index ea43b4974149..9a581faaa742 100644 --- a/drivers/net/ethernet/freescale/fman/fman_dtsec.c +++ b/drivers/net/ethernet/freescale/fman/fman_dtsec.c @@ -1117,6 +1117,25 @@ int dtsec_add_hash_mac_address(struct fman_mac *dtsec, enet_addr_t *eth_addr) return 0; } +int dtsec_set_allmulti(struct fman_mac *dtsec, bool enable) +{ + u32 tmp; + struct dtsec_regs __iomem *regs = dtsec->regs; + + if (!is_init_done(dtsec->dtsec_drv_param)) + return -EINVAL; + + tmp = ioread32be(®s->rctrl); + if (enable) + tmp |= RCTRL_MPROM; + else + tmp &= ~RCTRL_MPROM; + + iowrite32be(tmp, ®s->rctrl); + + return 0; +} + int dtsec_del_hash_mac_address(struct fman_mac *dtsec, enet_addr_t *eth_addr) { struct dtsec_regs __iomem *regs = dtsec->regs; diff --git a/drivers/net/ethernet/freescale/fman/fman_dtsec.h b/drivers/net/ethernet/freescale/fman/fman_dtsec.h index c4467c072058..1a689adf5a22 100644 --- a/drivers/net/ethernet/freescale/fman/fman_dtsec.h +++ b/drivers/net/ethernet/freescale/fman/fman_dtsec.h @@ -55,5 +55,6 @@ int dtsec_set_exception(struct fman_mac *dtsec, int dtsec_add_hash_mac_address(struct fman_mac *dtsec, enet_addr_t *eth_addr); int dtsec_del_hash_mac_address(struct fman_mac *dtsec, enet_addr_t *eth_addr); int dtsec_get_version(struct fman_mac *dtsec, u32 *mac_version); +int dtsec_set_allmulti(struct fman_mac *dtsec, bool enable); #endif /* __DTSEC_H */ diff --git a/drivers/net/ethernet/freescale/fman/fman_memac.c b/drivers/net/ethernet/freescale/fman/fman_memac.c index c0296880feba..446a97b792e3 100644 --- a/drivers/net/ethernet/freescale/fman/fman_memac.c +++ b/drivers/net/ethernet/freescale/fman/fman_memac.c @@ -350,6 +350,7 @@ struct fman_mac { struct fman_rev_info fm_rev_info; bool basex_if; struct phy_device *pcsphy; + bool allmulti_enabled; }; static void add_addr_in_paddr(struct memac_regs __iomem *regs, u8 *adr, @@ -940,6 +941,29 @@ int memac_add_hash_mac_address(struct fman_mac *memac, enet_addr_t *eth_addr) return 0; } +int memac_set_allmulti(struct fman_mac *memac, bool enable) +{ + u32 entry; + struct memac_regs __iomem *regs = memac->regs; + + if (!is_init_done(memac->memac_drv_param)) + return -EINVAL; + + if (enable) { + for (entry = 0; entry < HASH_TABLE_SIZE; entry++) + iowrite32be(entry | HASH_CTRL_MCAST_EN, + ®s->hashtable_ctrl); + } else { + for (entry = 0; entry < HASH_TABLE_SIZE; entry++) + iowrite32be(entry & ~HASH_CTRL_MCAST_EN, + ®s->hashtable_ctrl); + } + + memac->allmulti_enabled = enable; + + return 0; +} + int memac_del_hash_mac_address(struct fman_mac *memac, enet_addr_t *eth_addr) { struct memac_regs __iomem *regs = memac->regs; @@ -963,8 +987,12 @@ int memac_del_hash_mac_address(struct fman_mac *memac, enet_addr_t *eth_addr) break; } } - if (list_empty(&memac->multicast_addr_hash->lsts[hash])) - iowrite32be(hash & ~HASH_CTRL_MCAST_EN, ®s->hashtable_ctrl); + + if (!memac->allmulti_enabled) { + if (list_empty(&memac->multicast_addr_hash->lsts[hash])) + iowrite32be(hash & ~HASH_CTRL_MCAST_EN, + ®s->hashtable_ctrl); + } return 0; } diff --git a/drivers/net/ethernet/freescale/fman/fman_memac.h b/drivers/net/ethernet/freescale/fman/fman_memac.h index c4a66469a907..b5a50338ed9a 100644 --- a/drivers/net/ethernet/freescale/fman/fman_memac.h +++ b/drivers/net/ethernet/freescale/fman/fman_memac.h @@ -57,5 +57,6 @@ int memac_set_exception(struct fman_mac *memac, enum fman_mac_exceptions exception, bool enable); int memac_add_hash_mac_address(struct fman_mac *memac, enet_addr_t *eth_addr); int memac_del_hash_mac_address(struct fman_mac *memac, enet_addr_t *eth_addr); +int memac_set_allmulti(struct fman_mac *memac, bool enable); #endif /* __MEMAC_H */ diff --git a/drivers/net/ethernet/freescale/fman/fman_tgec.c b/drivers/net/ethernet/freescale/fman/fman_tgec.c index 4b0f3a50b293..284735d4ebe9 100644 --- a/drivers/net/ethernet/freescale/fman/fman_tgec.c +++ b/drivers/net/ethernet/freescale/fman/fman_tgec.c @@ -217,6 +217,7 @@ struct fman_mac { struct tgec_cfg *cfg; void *fm; struct fman_rev_info fm_rev_info; + bool allmulti_enabled; }; static void set_mac_address(struct tgec_regs __iomem *regs, u8 *adr) @@ -564,6 +565,29 @@ int tgec_add_hash_mac_address(struct fman_mac *tgec, enet_addr_t *eth_addr) return 0; } +int tgec_set_allmulti(struct fman_mac *tgec, bool enable) +{ + u32 entry; + struct tgec_regs __iomem *regs = tgec->regs; + + if (!is_init_done(tgec->cfg)) + return -EINVAL; + + if (enable) { + for (entry = 0; entry < TGEC_HASH_TABLE_SIZE; entry++) + iowrite32be(entry | TGEC_HASH_MCAST_EN, + ®s->hashtable_ctrl); + } else { + for (entry = 0; entry < TGEC_HASH_TABLE_SIZE; entry++) + iowrite32be(entry & ~TGEC_HASH_MCAST_EN, + ®s->hashtable_ctrl); + } + + tgec->allmulti_enabled = enable; + + return 0; +} + int tgec_del_hash_mac_address(struct fman_mac *tgec, enet_addr_t *eth_addr) { struct tgec_regs __iomem *regs = tgec->regs; @@ -591,9 +615,12 @@ int tgec_del_hash_mac_address(struct fman_mac *tgec, enet_addr_t *eth_addr) break; } } - if (list_empty(&tgec->multicast_addr_hash->lsts[hash])) - iowrite32be((hash & ~TGEC_HASH_MCAST_EN), - ®s->hashtable_ctrl); + + if (!tgec->allmulti_enabled) { + if (list_empty(&tgec->multicast_addr_hash->lsts[hash])) + iowrite32be((hash & ~TGEC_HASH_MCAST_EN), + ®s->hashtable_ctrl); + } return 0; } diff --git a/drivers/net/ethernet/freescale/fman/fman_tgec.h b/drivers/net/ethernet/freescale/fman/fman_tgec.h index 514bba9f47ce..cbbd3b422a98 100644 --- a/drivers/net/ethernet/freescale/fman/fman_tgec.h +++ b/drivers/net/ethernet/freescale/fman/fman_tgec.h @@ -51,5 +51,6 @@ int tgec_set_exception(struct fman_mac *tgec, int tgec_add_hash_mac_address(struct fman_mac *tgec, enet_addr_t *eth_addr); int tgec_del_hash_mac_address(struct fman_mac *tgec, enet_addr_t *eth_addr); int tgec_get_version(struct fman_mac *tgec, u32 *mac_version); +int tgec_set_allmulti(struct fman_mac *tgec, bool enable); #endif /* __TGEC_H */ diff --git a/drivers/net/ethernet/freescale/fman/mac.c b/drivers/net/ethernet/freescale/fman/mac.c index 88c0a0636b44..4829dcd9e077 100644 --- a/drivers/net/ethernet/freescale/fman/mac.c +++ b/drivers/net/ethernet/freescale/fman/mac.c @@ -470,6 +470,7 @@ static void setup_dtsec(struct mac_device *mac_dev) mac_dev->set_tx_pause = dtsec_set_tx_pause_frames; mac_dev->set_rx_pause = dtsec_accept_rx_pause_frames; mac_dev->set_exception = dtsec_set_exception; + mac_dev->set_allmulti = dtsec_set_allmulti; mac_dev->set_multi = set_multi; mac_dev->start = start; mac_dev->stop = stop; @@ -488,6 +489,7 @@ static void setup_tgec(struct mac_device *mac_dev) mac_dev->set_tx_pause = tgec_set_tx_pause_frames; mac_dev->set_rx_pause = tgec_accept_rx_pause_frames; mac_dev->set_exception = tgec_set_exception; + mac_dev->set_allmulti = tgec_set_allmulti; mac_dev->set_multi = set_multi; mac_dev->start = start; mac_dev->stop = stop; @@ -506,6 +508,7 @@ static void setup_memac(struct mac_device *mac_dev) mac_dev->set_tx_pause = memac_set_tx_pause_frames; mac_dev->set_rx_pause = memac_accept_rx_pause_frames; mac_dev->set_exception = memac_set_exception; + mac_dev->set_allmulti = memac_set_allmulti; mac_dev->set_multi = set_multi; mac_dev->start = start; mac_dev->stop = stop; diff --git a/drivers/net/ethernet/freescale/fman/mac.h b/drivers/net/ethernet/freescale/fman/mac.h index eefb3357e304..b520cec120ee 100644 --- a/drivers/net/ethernet/freescale/fman/mac.h +++ b/drivers/net/ethernet/freescale/fman/mac.h @@ -59,6 +59,7 @@ struct mac_device { bool rx_pause_active; bool tx_pause_active; bool promisc; + bool allmulti; int (*init)(struct mac_device *mac_dev); int (*start)(struct mac_device *mac_dev); @@ -66,6 +67,7 @@ struct mac_device { void (*adjust_link)(struct mac_device *mac_dev); int (*set_promisc)(struct fman_mac *mac_dev, bool enable); int (*change_addr)(struct fman_mac *mac_dev, enet_addr_t *enet_addr); + int (*set_allmulti)(struct fman_mac *mac_dev, bool enable); int (*set_multi)(struct net_device *net_dev, struct mac_device *mac_dev); int (*set_rx_pause)(struct fman_mac *mac_dev, bool en); diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index 1b3cc8bb0705..765407179fdd 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -90,7 +90,7 @@ MODULE_VERSION(IBMVNIC_DRIVER_VERSION); static int ibmvnic_version = IBMVNIC_INITIAL_VERSION; static int ibmvnic_remove(struct vio_dev *); -static void release_sub_crqs(struct ibmvnic_adapter *); +static void release_sub_crqs(struct ibmvnic_adapter *, bool); static int ibmvnic_reset_crq(struct ibmvnic_adapter *); static int ibmvnic_send_crq_init(struct ibmvnic_adapter *); static int ibmvnic_reenable_crq_queue(struct ibmvnic_adapter *); @@ -111,7 +111,7 @@ static int ibmvnic_poll(struct napi_struct *napi, int data); static void send_map_query(struct ibmvnic_adapter *adapter); static void send_request_map(struct ibmvnic_adapter *, dma_addr_t, __be32, u8); static void send_request_unmap(struct ibmvnic_adapter *, u8); -static void send_login(struct ibmvnic_adapter *adapter); +static int send_login(struct ibmvnic_adapter *adapter); static void send_cap_queries(struct ibmvnic_adapter *adapter); static int init_sub_crqs(struct ibmvnic_adapter *); static int init_sub_crq_irqs(struct ibmvnic_adapter *adapter); @@ -361,14 +361,14 @@ static void release_stats_buffers(struct ibmvnic_adapter *adapter) static int init_stats_buffers(struct ibmvnic_adapter *adapter) { adapter->tx_stats_buffers = - kcalloc(adapter->req_tx_queues, + kcalloc(IBMVNIC_MAX_QUEUES, sizeof(struct ibmvnic_tx_queue_stats), GFP_KERNEL); if (!adapter->tx_stats_buffers) return -ENOMEM; adapter->rx_stats_buffers = - kcalloc(adapter->req_rx_queues, + kcalloc(IBMVNIC_MAX_QUEUES, sizeof(struct ibmvnic_rx_queue_stats), GFP_KERNEL); if (!adapter->rx_stats_buffers) @@ -509,7 +509,7 @@ static int init_rx_pools(struct net_device *netdev) return -1; } - adapter->num_active_rx_pools = 0; + adapter->num_active_rx_pools = rxadd_subcrqs; for (i = 0; i < rxadd_subcrqs; i++) { rx_pool = &adapter->rx_pool[i]; @@ -554,8 +554,6 @@ static int init_rx_pools(struct net_device *netdev) rx_pool->next_free = 0; } - adapter->num_active_rx_pools = rxadd_subcrqs; - return 0; } @@ -641,7 +639,7 @@ static int init_tx_pools(struct net_device *netdev) if (!adapter->tx_pool) return -1; - adapter->num_active_tx_pools = 0; + adapter->num_active_tx_pools = tx_subcrqs; for (i = 0; i < tx_subcrqs; i++) { tx_pool = &adapter->tx_pool[i]; @@ -690,8 +688,6 @@ static int init_tx_pools(struct net_device *netdev) tx_pool->producer_index = 0; } - adapter->num_active_tx_pools = tx_subcrqs; - return 0; } @@ -740,6 +736,45 @@ static void ibmvnic_napi_disable(struct ibmvnic_adapter *adapter) adapter->napi_enabled = false; } +static int init_napi(struct ibmvnic_adapter *adapter) +{ + int i; + + adapter->napi = kcalloc(adapter->req_rx_queues, + sizeof(struct napi_struct), GFP_KERNEL); + if (!adapter->napi) + return -ENOMEM; + + for (i = 0; i < adapter->req_rx_queues; i++) { + netdev_dbg(adapter->netdev, "Adding napi[%d]\n", i); + netif_napi_add(adapter->netdev, &adapter->napi[i], + ibmvnic_poll, NAPI_POLL_WEIGHT); + } + + adapter->num_active_rx_napi = adapter->req_rx_queues; + return 0; +} + +static void release_napi(struct ibmvnic_adapter *adapter) +{ + int i; + + if (!adapter->napi) + return; + + for (i = 0; i < adapter->num_active_rx_napi; i++) { + if (&adapter->napi[i]) { + netdev_dbg(adapter->netdev, + "Releasing napi[%d]\n", i); + netif_napi_del(&adapter->napi[i]); + } + } + + kfree(adapter->napi); + adapter->napi = NULL; + adapter->num_active_rx_napi = 0; +} + static int ibmvnic_login(struct net_device *netdev) { struct ibmvnic_adapter *adapter = netdev_priv(netdev); @@ -750,7 +785,7 @@ static int ibmvnic_login(struct net_device *netdev) do { if (adapter->renegotiate) { adapter->renegotiate = false; - release_sub_crqs(adapter); + release_sub_crqs(adapter, 1); reinit_completion(&adapter->init_done); send_cap_queries(adapter); @@ -774,8 +809,11 @@ static int ibmvnic_login(struct net_device *netdev) } reinit_completion(&adapter->init_done); - send_login(adapter); - if (!wait_for_completion_timeout(&adapter->init_done, + rc = send_login(adapter); + if (rc) { + dev_err(dev, "Unable to attempt device login\n"); + return rc; + } else if (!wait_for_completion_timeout(&adapter->init_done, timeout)) { dev_err(dev, "Login timeout\n"); return -1; @@ -805,29 +843,13 @@ static void release_login_rsp_buffer(struct ibmvnic_adapter *adapter) static void release_resources(struct ibmvnic_adapter *adapter) { - int i; - release_vpd_data(adapter); release_tx_pools(adapter); release_rx_pools(adapter); - release_stats_token(adapter); - release_stats_buffers(adapter); release_error_buffers(adapter); - - if (adapter->napi) { - for (i = 0; i < adapter->req_rx_queues; i++) { - if (&adapter->napi[i]) { - netdev_dbg(adapter->netdev, - "Releasing napi[%d]\n", i); - netif_napi_del(&adapter->napi[i]); - } - } - } - kfree(adapter->napi); - adapter->napi = NULL; - + release_napi(adapter); release_login_rsp_buffer(adapter); } @@ -947,20 +969,12 @@ static int ibmvnic_get_vpd(struct ibmvnic_adapter *adapter) static int init_resources(struct ibmvnic_adapter *adapter) { struct net_device *netdev = adapter->netdev; - int i, rc; + int rc; rc = set_real_num_queues(netdev); if (rc) return rc; - rc = init_stats_buffers(adapter); - if (rc) - return rc; - - rc = init_stats_token(adapter); - if (rc) - return rc; - adapter->vpd = kzalloc(sizeof(*adapter->vpd), GFP_KERNEL); if (!adapter->vpd) return -ENOMEM; @@ -973,16 +987,10 @@ static int init_resources(struct ibmvnic_adapter *adapter) } adapter->map_id = 1; - adapter->napi = kcalloc(adapter->req_rx_queues, - sizeof(struct napi_struct), GFP_KERNEL); - if (!adapter->napi) - return -ENOMEM; - for (i = 0; i < adapter->req_rx_queues; i++) { - netdev_dbg(netdev, "Adding napi[%d]\n", i); - netif_napi_add(netdev, &adapter->napi[i], ibmvnic_poll, - NAPI_POLL_WEIGHT); - } + rc = init_napi(adapter); + if (rc) + return rc; send_map_query(adapter); @@ -1076,6 +1084,7 @@ static int ibmvnic_open(struct net_device *netdev) static void clean_rx_pools(struct ibmvnic_adapter *adapter) { struct ibmvnic_rx_pool *rx_pool; + struct ibmvnic_rx_buff *rx_buff; u64 rx_entries; int rx_scrqs; int i, j; @@ -1089,14 +1098,15 @@ static void clean_rx_pools(struct ibmvnic_adapter *adapter) /* Free any remaining skbs in the rx buffer pools */ for (i = 0; i < rx_scrqs; i++) { rx_pool = &adapter->rx_pool[i]; - if (!rx_pool) + if (!rx_pool || !rx_pool->rx_buff) continue; netdev_dbg(adapter->netdev, "Cleaning rx_pool[%d]\n", i); for (j = 0; j < rx_entries; j++) { - if (rx_pool->rx_buff[j].skb) { - dev_kfree_skb_any(rx_pool->rx_buff[j].skb); - rx_pool->rx_buff[j].skb = NULL; + rx_buff = &rx_pool->rx_buff[j]; + if (rx_buff && rx_buff->skb) { + dev_kfree_skb_any(rx_buff->skb); + rx_buff->skb = NULL; } } } @@ -1105,6 +1115,7 @@ static void clean_rx_pools(struct ibmvnic_adapter *adapter) static void clean_tx_pools(struct ibmvnic_adapter *adapter) { struct ibmvnic_tx_pool *tx_pool; + struct ibmvnic_tx_buff *tx_buff; u64 tx_entries; int tx_scrqs; int i, j; @@ -1118,14 +1129,15 @@ static void clean_tx_pools(struct ibmvnic_adapter *adapter) /* Free any remaining skbs in the tx buffer pools */ for (i = 0; i < tx_scrqs; i++) { tx_pool = &adapter->tx_pool[i]; - if (!tx_pool) + if (!tx_pool && !tx_pool->tx_buff) continue; netdev_dbg(adapter->netdev, "Cleaning tx_pool[%d]\n", i); for (j = 0; j < tx_entries; j++) { - if (tx_pool->tx_buff[j].skb) { - dev_kfree_skb_any(tx_pool->tx_buff[j].skb); - tx_pool->tx_buff[j].skb = NULL; + tx_buff = &tx_pool->tx_buff[j]; + if (tx_buff && tx_buff->skb) { + dev_kfree_skb_any(tx_buff->skb); + tx_buff->skb = NULL; } } } @@ -1467,6 +1479,7 @@ static int ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev) if ((*hdrs >> 7) & 1) { build_hdr_descs_arr(tx_buff, &num_entries, *hdrs); tx_crq.v1.n_crq_elem = num_entries; + tx_buff->num_entries = num_entries; tx_buff->indir_arr[0] = tx_crq; tx_buff->indir_dma = dma_map_single(dev, tx_buff->indir_arr, sizeof(tx_buff->indir_arr), @@ -1485,6 +1498,7 @@ static int ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev) (u64)tx_buff->indir_dma, (u64)num_entries); } else { + tx_buff->num_entries = num_entries; lpar_rc = send_subcrq(adapter, handle_array[queue_num], &tx_crq); } @@ -1515,9 +1529,9 @@ static int ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev) goto out; } - if (atomic_inc_return(&tx_scrq->used) + if (atomic_add_return(num_entries, &tx_scrq->used) >= adapter->req_tx_entries_per_subcrq) { - netdev_info(netdev, "Stopping queue %d\n", queue_num); + netdev_dbg(netdev, "Stopping queue %d\n", queue_num); netif_stop_subqueue(netdev, queue_num); } @@ -1653,7 +1667,7 @@ static int do_reset(struct ibmvnic_adapter *adapter, if (adapter->reset_reason == VNIC_RESET_CHANGE_PARAM || adapter->wait_for_reset) { release_resources(adapter); - release_sub_crqs(adapter); + release_sub_crqs(adapter, 1); release_crq_queue(adapter); } @@ -1691,6 +1705,9 @@ static int do_reset(struct ibmvnic_adapter *adapter, release_tx_pools(adapter); init_rx_pools(netdev); init_tx_pools(netdev); + + release_napi(adapter); + init_napi(adapter); } else { rc = reset_tx_pools(adapter); if (rc) @@ -2295,24 +2312,27 @@ static int reset_sub_crq_queues(struct ibmvnic_adapter *adapter) } static void release_sub_crq_queue(struct ibmvnic_adapter *adapter, - struct ibmvnic_sub_crq_queue *scrq) + struct ibmvnic_sub_crq_queue *scrq, + bool do_h_free) { struct device *dev = &adapter->vdev->dev; long rc; netdev_dbg(adapter->netdev, "Releasing sub-CRQ\n"); - /* Close the sub-crqs */ - do { - rc = plpar_hcall_norets(H_FREE_SUB_CRQ, - adapter->vdev->unit_address, - scrq->crq_num); - } while (rc == H_BUSY || H_IS_LONG_BUSY(rc)); + if (do_h_free) { + /* Close the sub-crqs */ + do { + rc = plpar_hcall_norets(H_FREE_SUB_CRQ, + adapter->vdev->unit_address, + scrq->crq_num); + } while (rc == H_BUSY || H_IS_LONG_BUSY(rc)); - if (rc) { - netdev_err(adapter->netdev, - "Failed to release sub-CRQ %16lx, rc = %ld\n", - scrq->crq_num, rc); + if (rc) { + netdev_err(adapter->netdev, + "Failed to release sub-CRQ %16lx, rc = %ld\n", + scrq->crq_num, rc); + } } dma_unmap_single(dev, scrq->msg_token, 4 * PAGE_SIZE, @@ -2380,12 +2400,12 @@ zero_page_failed: return NULL; } -static void release_sub_crqs(struct ibmvnic_adapter *adapter) +static void release_sub_crqs(struct ibmvnic_adapter *adapter, bool do_h_free) { int i; if (adapter->tx_scrq) { - for (i = 0; i < adapter->req_tx_queues; i++) { + for (i = 0; i < adapter->num_active_tx_scrqs; i++) { if (!adapter->tx_scrq[i]) continue; @@ -2398,15 +2418,17 @@ static void release_sub_crqs(struct ibmvnic_adapter *adapter) adapter->tx_scrq[i]->irq = 0; } - release_sub_crq_queue(adapter, adapter->tx_scrq[i]); + release_sub_crq_queue(adapter, adapter->tx_scrq[i], + do_h_free); } kfree(adapter->tx_scrq); adapter->tx_scrq = NULL; + adapter->num_active_tx_scrqs = 0; } if (adapter->rx_scrq) { - for (i = 0; i < adapter->req_rx_queues; i++) { + for (i = 0; i < adapter->num_active_rx_scrqs; i++) { if (!adapter->rx_scrq[i]) continue; @@ -2419,11 +2441,13 @@ static void release_sub_crqs(struct ibmvnic_adapter *adapter) adapter->rx_scrq[i]->irq = 0; } - release_sub_crq_queue(adapter, adapter->rx_scrq[i]); + release_sub_crq_queue(adapter, adapter->rx_scrq[i], + do_h_free); } kfree(adapter->rx_scrq); adapter->rx_scrq = NULL; + adapter->num_active_rx_scrqs = 0; } } @@ -2473,6 +2497,7 @@ static int ibmvnic_complete_tx(struct ibmvnic_adapter *adapter, restart_loop: while (pending_scrq(adapter, scrq)) { unsigned int pool = scrq->pool_index; + int num_entries = 0; next = ibmvnic_next_scrq(adapter, scrq); for (i = 0; i < next->tx_comp.num_comps; i++) { @@ -2503,6 +2528,8 @@ restart_loop: txbuff->skb = NULL; } + num_entries += txbuff->num_entries; + adapter->tx_pool[pool].free_map[adapter->tx_pool[pool]. producer_index] = index; adapter->tx_pool[pool].producer_index = @@ -2512,13 +2539,13 @@ restart_loop: /* remove tx_comp scrq*/ next->tx_comp.first = 0; - if (atomic_sub_return(next->tx_comp.num_comps, &scrq->used) <= + if (atomic_sub_return(num_entries, &scrq->used) <= (adapter->req_tx_entries_per_subcrq / 2) && __netif_subqueue_stopped(adapter->netdev, scrq->pool_index)) { netif_wake_subqueue(adapter->netdev, scrq->pool_index); - netdev_info(adapter->netdev, "Started queue %d\n", - scrq->pool_index); + netdev_dbg(adapter->netdev, "Started queue %d\n", + scrq->pool_index); } } @@ -2590,7 +2617,7 @@ static int init_sub_crq_irqs(struct ibmvnic_adapter *adapter) dev_err(dev, "Couldn't register tx irq 0x%x. rc=%d\n", scrq->irq, rc); irq_dispose_mapping(scrq->irq); - goto req_rx_irq_failed; + goto req_tx_irq_failed; } } @@ -2626,7 +2653,7 @@ req_tx_irq_failed: free_irq(adapter->tx_scrq[j]->irq, adapter->tx_scrq[j]); irq_dispose_mapping(adapter->rx_scrq[j]->irq); } - release_sub_crqs(adapter); + release_sub_crqs(adapter, 1); return rc; } @@ -2688,6 +2715,7 @@ static int init_sub_crqs(struct ibmvnic_adapter *adapter) for (i = 0; i < adapter->req_tx_queues; i++) { adapter->tx_scrq[i] = allqueues[i]; adapter->tx_scrq[i]->pool_index = i; + adapter->num_active_tx_scrqs++; } adapter->rx_scrq = kcalloc(adapter->req_rx_queues, @@ -2698,6 +2726,7 @@ static int init_sub_crqs(struct ibmvnic_adapter *adapter) for (i = 0; i < adapter->req_rx_queues; i++) { adapter->rx_scrq[i] = allqueues[i + adapter->req_tx_queues]; adapter->rx_scrq[i]->scrq_num = i; + adapter->num_active_rx_scrqs++; } kfree(allqueues); @@ -2708,7 +2737,7 @@ rx_failed: adapter->tx_scrq = NULL; tx_failed: for (i = 0; i < registered_queues; i++) - release_sub_crq_queue(adapter, allqueues[i]); + release_sub_crq_queue(adapter, allqueues[i], 1); kfree(allqueues); return -1; } @@ -3048,7 +3077,7 @@ static void vnic_add_client_data(struct ibmvnic_adapter *adapter, strncpy(&vlcd->name, adapter->netdev->name, len); } -static void send_login(struct ibmvnic_adapter *adapter) +static int send_login(struct ibmvnic_adapter *adapter) { struct ibmvnic_login_rsp_buffer *login_rsp_buffer; struct ibmvnic_login_buffer *login_buffer; @@ -3064,6 +3093,12 @@ static void send_login(struct ibmvnic_adapter *adapter) struct vnic_login_client_data *vlcd; int i; + if (!adapter->tx_scrq || !adapter->rx_scrq) { + netdev_err(adapter->netdev, + "RX or TX queues are not allocated, device login failed\n"); + return -1; + } + release_login_rsp_buffer(adapter); client_data_len = vnic_client_data_len(adapter); @@ -3161,7 +3196,7 @@ static void send_login(struct ibmvnic_adapter *adapter) crq.login.len = cpu_to_be32(buffer_size); ibmvnic_send_crq(adapter, &crq); - return; + return 0; buf_rsp_map_failed: kfree(login_rsp_buffer); @@ -3170,7 +3205,7 @@ buf_rsp_alloc_failed: buf_map_failed: kfree(login_buffer); buf_alloc_failed: - return; + return -1; } static void send_request_map(struct ibmvnic_adapter *adapter, dma_addr_t addr, @@ -4335,6 +4370,7 @@ static int ibmvnic_init(struct ibmvnic_adapter *adapter) { struct device *dev = &adapter->vdev->dev; unsigned long timeout = msecs_to_jiffies(30000); + u64 old_num_rx_queues, old_num_tx_queues; int rc; if (adapter->resetting && !adapter->wait_for_reset) { @@ -4352,6 +4388,9 @@ static int ibmvnic_init(struct ibmvnic_adapter *adapter) adapter->from_passive_init = false; + old_num_rx_queues = adapter->req_rx_queues; + old_num_tx_queues = adapter->req_tx_queues; + init_completion(&adapter->init_done); adapter->init_done_rc = 0; ibmvnic_send_crq_init(adapter); @@ -4371,10 +4410,18 @@ static int ibmvnic_init(struct ibmvnic_adapter *adapter) return -1; } - if (adapter->resetting && !adapter->wait_for_reset) - rc = reset_sub_crq_queues(adapter); - else + if (adapter->resetting && !adapter->wait_for_reset) { + if (adapter->req_rx_queues != old_num_rx_queues || + adapter->req_tx_queues != old_num_tx_queues) { + release_sub_crqs(adapter, 0); + rc = init_sub_crqs(adapter); + } else { + rc = reset_sub_crq_queues(adapter); + } + } else { rc = init_sub_crqs(adapter); + } + if (rc) { dev_err(dev, "Initialization of sub crqs failed\n"); release_crq_queue(adapter); @@ -4387,6 +4434,14 @@ static int ibmvnic_init(struct ibmvnic_adapter *adapter) release_crq_queue(adapter); } + rc = init_stats_buffers(adapter); + if (rc) + return rc; + + rc = init_stats_token(adapter); + if (rc) + return rc; + return rc; } @@ -4474,7 +4529,7 @@ ibmvnic_register_fail: device_remove_file(&dev->dev, &dev_attr_failover); ibmvnic_init_fail: - release_sub_crqs(adapter); + release_sub_crqs(adapter, 1); release_crq_queue(adapter); free_netdev(netdev); @@ -4491,9 +4546,12 @@ static int ibmvnic_remove(struct vio_dev *dev) mutex_lock(&adapter->reset_lock); release_resources(adapter); - release_sub_crqs(adapter); + release_sub_crqs(adapter, 1); release_crq_queue(adapter); + release_stats_token(adapter); + release_stats_buffers(adapter); + adapter->state = VNIC_REMOVED; mutex_unlock(&adapter->reset_lock); diff --git a/drivers/net/ethernet/ibm/ibmvnic.h b/drivers/net/ethernet/ibm/ibmvnic.h index fe21a6e2ddae..099c89d49945 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.h +++ b/drivers/net/ethernet/ibm/ibmvnic.h @@ -909,6 +909,7 @@ struct ibmvnic_tx_buff { union sub_crq indir_arr[6]; u8 hdr_data[140]; dma_addr_t indir_dma; + int num_entries; }; struct ibmvnic_tx_pool { @@ -1091,8 +1092,11 @@ struct ibmvnic_adapter { u64 opt_rxba_entries_per_subcrq; __be64 tx_rx_desc_req; u8 map_id; - u64 num_active_rx_pools; - u64 num_active_tx_pools; + u32 num_active_rx_scrqs; + u32 num_active_rx_pools; + u32 num_active_rx_napi; + u32 num_active_tx_scrqs; + u32 num_active_tx_pools; struct tasklet_struct tasklet; enum vnic_state state; diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_common.c b/drivers/net/ethernet/intel/fm10k/fm10k_common.c index 736a9f087bc9..c58a5377a287 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_common.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_common.c @@ -1,5 +1,5 @@ /* Intel(R) Ethernet Switch Host Interface Driver - * Copyright(c) 2013 - 2017 Intel Corporation. + * Copyright(c) 2013 - 2018 Intel Corporation. * * This program is free software; you can redistribute it and/or modify it * under the terms and conditions of the GNU General Public License, @@ -262,6 +262,7 @@ s32 fm10k_stop_hw_generic(struct fm10k_hw *hw) * fm10k_read_hw_stats_32b - Reads value of 32-bit registers * @hw: pointer to the hardware structure * @addr: address of register containing a 32-bit value + * @stat: pointer to structure holding hw stat information * * Function reads the content of the register and returns the delta * between the base and the current value. @@ -281,6 +282,7 @@ u32 fm10k_read_hw_stats_32b(struct fm10k_hw *hw, u32 addr, * fm10k_read_hw_stats_48b - Reads value of 48-bit registers * @hw: pointer to the hardware structure * @addr: address of register containing the lower 32-bit value + * @stat: pointer to structure holding hw stat information * * Function reads the content of 2 registers, combined to represent a 48-bit * statistical value. Extra processing is required to handle overflowing. @@ -461,7 +463,6 @@ void fm10k_update_hw_stats_q(struct fm10k_hw *hw, struct fm10k_hw_stats_q *q, /** * fm10k_unbind_hw_stats_q - Unbind the queue counters from their queues - * @hw: pointer to the hardware structure * @q: pointer to the ring of hardware statistics queue * @idx: index pointing to the start of the ring iteration * @count: number of queues to iterate over diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_main.c b/drivers/net/ethernet/intel/fm10k/fm10k_main.c index 8e12aae065d8..2c93d719438f 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_main.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_main.c @@ -28,13 +28,13 @@ #include "fm10k.h" -#define DRV_VERSION "0.22.1-k" +#define DRV_VERSION "0.23.4-k" #define DRV_SUMMARY "Intel(R) Ethernet Switch Host Interface Driver" const char fm10k_driver_version[] = DRV_VERSION; char fm10k_driver_name[] = "fm10k"; static const char fm10k_driver_string[] = DRV_SUMMARY; static const char fm10k_copyright[] = - "Copyright(c) 2013 - 2017 Intel Corporation."; + "Copyright(c) 2013 - 2018 Intel Corporation."; MODULE_AUTHOR("Intel Corporation, <linux.nics@intel.com>"); MODULE_DESCRIPTION(DRV_SUMMARY); diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c b/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c index a38ae5c54da3..75c99aed3c41 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c @@ -1,5 +1,5 @@ /* Intel(R) Ethernet Switch Host Interface Driver - * Copyright(c) 2013 - 2017 Intel Corporation. + * Copyright(c) 2013 - 2018 Intel Corporation. * * This program is free software; you can redistribute it and/or modify it * under the terms and conditions of the GNU General Public License, @@ -486,7 +486,7 @@ static void fm10k_insert_tunnel_port(struct list_head *ports, /** * fm10k_udp_tunnel_add - * @netdev: network interface device structure + * @dev: network interface device structure * @ti: Tunnel endpoint information * * This function is called when a new UDP tunnel port has been added. @@ -518,8 +518,8 @@ static void fm10k_udp_tunnel_add(struct net_device *dev, /** * fm10k_udp_tunnel_del - * @netdev: network interface device structure - * @ti: Tunnel endpoint information + * @dev: network interface device structure + * @ti: Tunnel end point information * * This function is called when a new UDP tunnel port is deleted. The freed * port will be removed from the list, then we reprogram the offloaded port @@ -803,7 +803,7 @@ int fm10k_queue_vlan_request(struct fm10k_intfc *interface, * @glort: the target glort for this update * @addr: the address to update * @vid: the vid to update - * @sync: whether to add or remove + * @set: whether to add or remove * * This function queues up a MAC request for sending to the switch manager. * A separate thread monitors the queue and sends updates to the switch diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c index a434fecfdfeb..50f53e403ef5 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c @@ -1,5 +1,5 @@ /* Intel(R) Ethernet Switch Host Interface Driver - * Copyright(c) 2013 - 2017 Intel Corporation. + * Copyright(c) 2013 - 2018 Intel Corporation. * * This program is free software; you can redistribute it and/or modify it * under the terms and conditions of the GNU General Public License, @@ -29,7 +29,7 @@ static const struct fm10k_info *fm10k_info_tbl[] = { [fm10k_device_vf] = &fm10k_vf_info, }; -/** +/* * fm10k_pci_tbl - PCI Device ID Table * * Wildcard entries (PCI_ANY_ID) should come last @@ -211,7 +211,7 @@ static void fm10k_start_service_event(struct fm10k_intfc *interface) /** * fm10k_service_timer - Timer Call-back - * @data: pointer to interface cast into an unsigned long + * @t: pointer to timer data **/ static void fm10k_service_timer(struct timer_list *t) { @@ -649,7 +649,7 @@ void fm10k_update_stats(struct fm10k_intfc *interface) /** * fm10k_watchdog_flush_tx - flush queues on host not ready - * @interface - pointer to the device interface structure + * @interface: pointer to the device interface structure **/ static void fm10k_watchdog_flush_tx(struct fm10k_intfc *interface) { @@ -679,7 +679,7 @@ static void fm10k_watchdog_flush_tx(struct fm10k_intfc *interface) /** * fm10k_watchdog_subtask - check and bring link up - * @interface - pointer to the device interface structure + * @interface: pointer to the device interface structure **/ static void fm10k_watchdog_subtask(struct fm10k_intfc *interface) { @@ -703,7 +703,7 @@ static void fm10k_watchdog_subtask(struct fm10k_intfc *interface) /** * fm10k_check_hang_subtask - check for hung queues and dropped interrupts - * @interface - pointer to the device interface structure + * @interface: pointer to the device interface structure * * This function serves two purposes. First it strobes the interrupt lines * in order to make certain interrupts are occurring. Secondly it sets the @@ -1995,6 +1995,7 @@ skip_tx_dma_drain: /** * fm10k_sw_init - Initialize general software structures * @interface: host interface private structure to initialize + * @ent: PCI device ID entry * * fm10k_sw_init initializes the interface private data structure. * Fields are initialized based on PCI device information and diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_pf.c b/drivers/net/ethernet/intel/fm10k/fm10k_pf.c index d6406fc31ffb..bee192fe2ffb 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_pf.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_pf.c @@ -1,5 +1,5 @@ /* Intel(R) Ethernet Switch Host Interface Driver - * Copyright(c) 2013 - 2017 Intel Corporation. + * Copyright(c) 2013 - 2018 Intel Corporation. * * This program is free software; you can redistribute it and/or modify it * under the terms and conditions of the GNU General Public License, @@ -1180,7 +1180,7 @@ s32 fm10k_iov_msg_msix_pf(struct fm10k_hw *hw, u32 **results, /** * fm10k_iov_select_vid - Select correct default VLAN ID - * @hw: Pointer to hardware structure + * @vf_info: pointer to VF information structure * @vid: VLAN ID to correct * * Will report an error if the VLAN ID is out of range. For VID = 0, it will diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_tlv.c b/drivers/net/ethernet/intel/fm10k/fm10k_tlv.c index f8e87bf086b9..9d0d31da426b 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_tlv.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_tlv.c @@ -1,5 +1,5 @@ /* Intel(R) Ethernet Switch Host Interface Driver - * Copyright(c) 2013 - 2016 Intel Corporation. + * Copyright(c) 2013 - 2018 Intel Corporation. * * This program is free software; you can redistribute it and/or modify it * under the terms and conditions of the GNU General Public License, @@ -120,6 +120,7 @@ static s32 fm10k_tlv_attr_get_null_string(u32 *attr, unsigned char *string) * @msg: Pointer to message block * @attr_id: Attribute ID * @mac_addr: MAC address to be stored + * @vlan: VLAN to be stored * * This function will reorder a MAC address to be CPU endian and store it * in the attribute buffer. It will return success if provided with a @@ -155,8 +156,8 @@ s32 fm10k_tlv_attr_put_mac_vlan(u32 *msg, u16 attr_id, /** * fm10k_tlv_attr_get_mac_vlan - Get MAC/VLAN stored in attribute * @attr: Pointer to attribute - * @attr_id: Attribute ID * @mac_addr: location of buffer to store MAC address + * @vlan: location of buffer to store VLAN * * This function pulls the MAC address back out of the attribute and will * place it in the array pointed by by mac_addr. It will return success @@ -549,7 +550,7 @@ static s32 fm10k_tlv_attr_parse(u32 *attr, u32 **results, * @hw: Pointer to hardware structure * @msg: Pointer to message * @mbx: Pointer to mailbox information structure - * @func: Function array containing list of message handling functions + * @data: Pointer to message handler data structure * * This function should be the first function called upon receiving a * message. The handler will identify the message type and call the correct diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h index 46e9f4e0a02c..36d9401a6258 100644 --- a/drivers/net/ethernet/intel/i40e/i40e.h +++ b/drivers/net/ethernet/intel/i40e/i40e.h @@ -507,6 +507,7 @@ struct i40e_pf { #define I40E_HW_STOP_FW_LLDP BIT(16) #define I40E_HW_PORT_ID_VALID BIT(17) #define I40E_HW_RESTART_AUTONEG BIT(18) +#define I40E_HW_STOPPABLE_FW_LLDP BIT(19) u64 flags; #define I40E_FLAG_RX_CSUM_ENABLED BIT_ULL(0) @@ -824,6 +825,7 @@ struct i40e_q_vector { struct i40e_ring_container rx; struct i40e_ring_container tx; + u8 itr_countdown; /* when 0 should adjust adaptive ITR */ u8 num_ringpairs; /* total number of ring pairs in vector */ cpumask_t affinity_mask; @@ -832,8 +834,6 @@ struct i40e_q_vector { struct rcu_head rcu; /* to avoid race with update stats on free */ char name[I40E_INT_NAME_STR_LEN]; bool arm_wb_state; -#define ITR_COUNTDOWN_START 100 - u8 itr_countdown; /* when 0 should adjust ITR */ } ____cacheline_internodealigned_in_smp; /* lan device */ @@ -1109,4 +1109,10 @@ static inline bool i40e_enabled_xdp_vsi(struct i40e_vsi *vsi) int i40e_create_queue_channel(struct i40e_vsi *vsi, struct i40e_channel *ch); int i40e_set_bw_limit(struct i40e_vsi *vsi, u16 seid, u64 max_tx_rate); +int i40e_add_del_cloud_filter(struct i40e_vsi *vsi, + struct i40e_cloud_filter *filter, + bool add); +int i40e_add_del_cloud_filter_big_buf(struct i40e_vsi *vsi, + struct i40e_cloud_filter *filter, + bool add); #endif /* _I40E_H_ */ diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h index a852775d3059..0dfc52772c45 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h +++ b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h @@ -1914,6 +1914,43 @@ enum i40e_aq_phy_type { I40E_PHY_TYPE_DEFAULT = 0xFF, }; +#define I40E_PHY_TYPES_BITMASK (BIT_ULL(I40E_PHY_TYPE_SGMII) | \ + BIT_ULL(I40E_PHY_TYPE_1000BASE_KX) | \ + BIT_ULL(I40E_PHY_TYPE_10GBASE_KX4) | \ + BIT_ULL(I40E_PHY_TYPE_10GBASE_KR) | \ + BIT_ULL(I40E_PHY_TYPE_40GBASE_KR4) | \ + BIT_ULL(I40E_PHY_TYPE_XAUI) | \ + BIT_ULL(I40E_PHY_TYPE_XFI) | \ + BIT_ULL(I40E_PHY_TYPE_SFI) | \ + BIT_ULL(I40E_PHY_TYPE_XLAUI) | \ + BIT_ULL(I40E_PHY_TYPE_XLPPI) | \ + BIT_ULL(I40E_PHY_TYPE_40GBASE_CR4_CU) | \ + BIT_ULL(I40E_PHY_TYPE_10GBASE_CR1_CU) | \ + BIT_ULL(I40E_PHY_TYPE_10GBASE_AOC) | \ + BIT_ULL(I40E_PHY_TYPE_40GBASE_AOC) | \ + BIT_ULL(I40E_PHY_TYPE_UNRECOGNIZED) | \ + BIT_ULL(I40E_PHY_TYPE_UNSUPPORTED) | \ + BIT_ULL(I40E_PHY_TYPE_100BASE_TX) | \ + BIT_ULL(I40E_PHY_TYPE_1000BASE_T) | \ + BIT_ULL(I40E_PHY_TYPE_10GBASE_T) | \ + BIT_ULL(I40E_PHY_TYPE_10GBASE_SR) | \ + BIT_ULL(I40E_PHY_TYPE_10GBASE_LR) | \ + BIT_ULL(I40E_PHY_TYPE_10GBASE_SFPP_CU) | \ + BIT_ULL(I40E_PHY_TYPE_10GBASE_CR1) | \ + BIT_ULL(I40E_PHY_TYPE_40GBASE_CR4) | \ + BIT_ULL(I40E_PHY_TYPE_40GBASE_SR4) | \ + BIT_ULL(I40E_PHY_TYPE_40GBASE_LR4) | \ + BIT_ULL(I40E_PHY_TYPE_1000BASE_SX) | \ + BIT_ULL(I40E_PHY_TYPE_1000BASE_LX) | \ + BIT_ULL(I40E_PHY_TYPE_1000BASE_T_OPTICAL) | \ + BIT_ULL(I40E_PHY_TYPE_20GBASE_KR2) | \ + BIT_ULL(I40E_PHY_TYPE_25GBASE_KR) | \ + BIT_ULL(I40E_PHY_TYPE_25GBASE_CR) | \ + BIT_ULL(I40E_PHY_TYPE_25GBASE_SR) | \ + BIT_ULL(I40E_PHY_TYPE_25GBASE_LR) | \ + BIT_ULL(I40E_PHY_TYPE_25GBASE_AOC) | \ + BIT_ULL(I40E_PHY_TYPE_25GBASE_ACC)) + #define I40E_LINK_SPEED_100MB_SHIFT 0x1 #define I40E_LINK_SPEED_1000MB_SHIFT 0x2 #define I40E_LINK_SPEED_10GB_SHIFT 0x3 diff --git a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c index 4c3b4243cf65..b829fd365693 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c +++ b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c @@ -155,8 +155,8 @@ static void i40e_dbg_dump_vsi_seid(struct i40e_pf *pf, int seid) dev_info(&pf->pdev->dev, " vlan_features = 0x%08lx\n", (unsigned long int)nd->vlan_features); } - dev_info(&pf->pdev->dev, - " vlgrp: & = %p\n", vsi->active_vlans); + dev_info(&pf->pdev->dev, " active_vlans is %s\n", + vsi->active_vlans ? "<valid>" : "<null>"); dev_info(&pf->pdev->dev, " flags = 0x%08lx, netdev_registered = %i, current_netdev_flags = 0x%04x\n", vsi->flags, vsi->netdev_registered, vsi->current_netdev_flags); @@ -270,14 +270,6 @@ static void i40e_dbg_dump_vsi_seid(struct i40e_pf *pf, int seid) continue; dev_info(&pf->pdev->dev, - " rx_rings[%i]: desc = %p\n", - i, rx_ring->desc); - dev_info(&pf->pdev->dev, - " rx_rings[%i]: dev = %p, netdev = %p, rx_bi = %p\n", - i, rx_ring->dev, - rx_ring->netdev, - rx_ring->rx_bi); - dev_info(&pf->pdev->dev, " rx_rings[%i]: state = %lu, queue_index = %d, reg_idx = %d\n", i, *rx_ring->state, rx_ring->queue_index, @@ -307,17 +299,12 @@ static void i40e_dbg_dump_vsi_seid(struct i40e_pf *pf, int seid) rx_ring->rx_stats.realloc_count, rx_ring->rx_stats.page_reuse_count); dev_info(&pf->pdev->dev, - " rx_rings[%i]: size = %i, dma = 0x%08lx\n", - i, rx_ring->size, - (unsigned long int)rx_ring->dma); - dev_info(&pf->pdev->dev, - " rx_rings[%i]: vsi = %p, q_vector = %p\n", - i, rx_ring->vsi, - rx_ring->q_vector); + " rx_rings[%i]: size = %i\n", + i, rx_ring->size); dev_info(&pf->pdev->dev, - " rx_rings[%i]: rx_itr_setting = %d (%s)\n", - i, rx_ring->rx_itr_setting, - ITR_IS_DYNAMIC(rx_ring->rx_itr_setting) ? "dynamic" : "fixed"); + " rx_rings[%i]: itr_setting = %d (%s)\n", + i, rx_ring->itr_setting, + ITR_IS_DYNAMIC(rx_ring->itr_setting) ? "dynamic" : "fixed"); } for (i = 0; i < vsi->num_queue_pairs; i++) { struct i40e_ring *tx_ring = READ_ONCE(vsi->tx_rings[i]); @@ -326,14 +313,6 @@ static void i40e_dbg_dump_vsi_seid(struct i40e_pf *pf, int seid) continue; dev_info(&pf->pdev->dev, - " tx_rings[%i]: desc = %p\n", - i, tx_ring->desc); - dev_info(&pf->pdev->dev, - " tx_rings[%i]: dev = %p, netdev = %p, tx_bi = %p\n", - i, tx_ring->dev, - tx_ring->netdev, - tx_ring->tx_bi); - dev_info(&pf->pdev->dev, " tx_rings[%i]: state = %lu, queue_index = %d, reg_idx = %d\n", i, *tx_ring->state, tx_ring->queue_index, @@ -355,20 +334,15 @@ static void i40e_dbg_dump_vsi_seid(struct i40e_pf *pf, int seid) tx_ring->tx_stats.tx_busy, tx_ring->tx_stats.tx_done_old); dev_info(&pf->pdev->dev, - " tx_rings[%i]: size = %i, dma = 0x%08lx\n", - i, tx_ring->size, - (unsigned long int)tx_ring->dma); - dev_info(&pf->pdev->dev, - " tx_rings[%i]: vsi = %p, q_vector = %p\n", - i, tx_ring->vsi, - tx_ring->q_vector); + " tx_rings[%i]: size = %i\n", + i, tx_ring->size); dev_info(&pf->pdev->dev, " tx_rings[%i]: DCB tc = %d\n", i, tx_ring->dcb_tc); dev_info(&pf->pdev->dev, - " tx_rings[%i]: tx_itr_setting = %d (%s)\n", - i, tx_ring->tx_itr_setting, - ITR_IS_DYNAMIC(tx_ring->tx_itr_setting) ? "dynamic" : "fixed"); + " tx_rings[%i]: itr_setting = %d (%s)\n", + i, tx_ring->itr_setting, + ITR_IS_DYNAMIC(tx_ring->itr_setting) ? "dynamic" : "fixed"); } rcu_read_unlock(); dev_info(&pf->pdev->dev, @@ -466,8 +440,6 @@ static void i40e_dbg_dump_vsi_seid(struct i40e_pf *pf, int seid) vsi->info.resp_reserved[6], vsi->info.resp_reserved[7], vsi->info.resp_reserved[8], vsi->info.resp_reserved[9], vsi->info.resp_reserved[10], vsi->info.resp_reserved[11]); - if (vsi->back) - dev_info(&pf->pdev->dev, " PF = %p\n", vsi->back); dev_info(&pf->pdev->dev, " idx = %d\n", vsi->idx); dev_info(&pf->pdev->dev, " tc_config: numtc = %d, enabled_tc = 0x%x\n", diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c index 2f5bee713fef..89807e32a898 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c @@ -230,6 +230,8 @@ static const struct i40e_priv_flags i40e_gstrings_priv_flags[] = { I40E_PRIV_FLAG("flow-director-atr", I40E_FLAG_FD_ATR_ENABLED, 0), I40E_PRIV_FLAG("veb-stats", I40E_FLAG_VEB_STATS_ENABLED, 0), I40E_PRIV_FLAG("hw-atr-eviction", I40E_FLAG_HW_ATR_EVICT_ENABLED, 0), + I40E_PRIV_FLAG("link-down-on-close", + I40E_FLAG_LINK_DOWN_ON_CLOSE_ENABLED, 0), I40E_PRIV_FLAG("legacy-rx", I40E_FLAG_LEGACY_RX, 0), I40E_PRIV_FLAG("disable-source-pruning", I40E_FLAG_SOURCE_PRUNING_DISABLED, 0), @@ -2244,14 +2246,14 @@ static int __i40e_get_coalesce(struct net_device *netdev, rx_ring = vsi->rx_rings[queue]; tx_ring = vsi->tx_rings[queue]; - if (ITR_IS_DYNAMIC(rx_ring->rx_itr_setting)) + if (ITR_IS_DYNAMIC(rx_ring->itr_setting)) ec->use_adaptive_rx_coalesce = 1; - if (ITR_IS_DYNAMIC(tx_ring->tx_itr_setting)) + if (ITR_IS_DYNAMIC(tx_ring->itr_setting)) ec->use_adaptive_tx_coalesce = 1; - ec->rx_coalesce_usecs = rx_ring->rx_itr_setting & ~I40E_ITR_DYNAMIC; - ec->tx_coalesce_usecs = tx_ring->tx_itr_setting & ~I40E_ITR_DYNAMIC; + ec->rx_coalesce_usecs = rx_ring->itr_setting & ~I40E_ITR_DYNAMIC; + ec->tx_coalesce_usecs = tx_ring->itr_setting & ~I40E_ITR_DYNAMIC; /* we use the _usecs_high to store/set the interrupt rate limit * that the hardware supports, that almost but not quite @@ -2311,34 +2313,35 @@ static void i40e_set_itr_per_queue(struct i40e_vsi *vsi, struct i40e_pf *pf = vsi->back; struct i40e_hw *hw = &pf->hw; struct i40e_q_vector *q_vector; - u16 vector, intrl; + u16 intrl; intrl = i40e_intrl_usec_to_reg(vsi->int_rate_limit); - rx_ring->rx_itr_setting = ec->rx_coalesce_usecs; - tx_ring->tx_itr_setting = ec->tx_coalesce_usecs; + rx_ring->itr_setting = ITR_REG_ALIGN(ec->rx_coalesce_usecs); + tx_ring->itr_setting = ITR_REG_ALIGN(ec->tx_coalesce_usecs); if (ec->use_adaptive_rx_coalesce) - rx_ring->rx_itr_setting |= I40E_ITR_DYNAMIC; + rx_ring->itr_setting |= I40E_ITR_DYNAMIC; else - rx_ring->rx_itr_setting &= ~I40E_ITR_DYNAMIC; + rx_ring->itr_setting &= ~I40E_ITR_DYNAMIC; if (ec->use_adaptive_tx_coalesce) - tx_ring->tx_itr_setting |= I40E_ITR_DYNAMIC; + tx_ring->itr_setting |= I40E_ITR_DYNAMIC; else - tx_ring->tx_itr_setting &= ~I40E_ITR_DYNAMIC; + tx_ring->itr_setting &= ~I40E_ITR_DYNAMIC; q_vector = rx_ring->q_vector; - q_vector->rx.itr = ITR_TO_REG(rx_ring->rx_itr_setting); - vector = vsi->base_vector + q_vector->v_idx; - wr32(hw, I40E_PFINT_ITRN(I40E_RX_ITR, vector - 1), q_vector->rx.itr); + q_vector->rx.target_itr = ITR_TO_REG(rx_ring->itr_setting); q_vector = tx_ring->q_vector; - q_vector->tx.itr = ITR_TO_REG(tx_ring->tx_itr_setting); - vector = vsi->base_vector + q_vector->v_idx; - wr32(hw, I40E_PFINT_ITRN(I40E_TX_ITR, vector - 1), q_vector->tx.itr); + q_vector->tx.target_itr = ITR_TO_REG(tx_ring->itr_setting); - wr32(hw, I40E_PFINT_RATEN(vector - 1), intrl); + /* The interrupt handler itself will take care of programming + * the Tx and Rx ITR values based on the values we have entered + * into the q_vector, no need to write the values now. + */ + + wr32(hw, I40E_PFINT_RATEN(q_vector->reg_idx), intrl); i40e_flush(hw); } @@ -2364,11 +2367,11 @@ static int __i40e_set_coalesce(struct net_device *netdev, vsi->work_limit = ec->tx_max_coalesced_frames_irq; if (queue < 0) { - cur_rx_itr = vsi->rx_rings[0]->rx_itr_setting; - cur_tx_itr = vsi->tx_rings[0]->tx_itr_setting; + cur_rx_itr = vsi->rx_rings[0]->itr_setting; + cur_tx_itr = vsi->tx_rings[0]->itr_setting; } else if (queue < vsi->num_queue_pairs) { - cur_rx_itr = vsi->rx_rings[queue]->rx_itr_setting; - cur_tx_itr = vsi->tx_rings[queue]->tx_itr_setting; + cur_rx_itr = vsi->rx_rings[queue]->itr_setting; + cur_tx_itr = vsi->tx_rings[queue]->itr_setting; } else { netif_info(pf, drv, netdev, "Invalid queue value, queue range is 0 - %d\n", vsi->num_queue_pairs - 1); @@ -2396,7 +2399,7 @@ static int __i40e_set_coalesce(struct net_device *netdev, return -EINVAL; } - if (ec->rx_coalesce_usecs > (I40E_MAX_ITR << 1)) { + if (ec->rx_coalesce_usecs > I40E_MAX_ITR) { netif_info(pf, drv, netdev, "Invalid value, rx-usecs range is 0-8160\n"); return -EINVAL; } @@ -2407,16 +2410,16 @@ static int __i40e_set_coalesce(struct net_device *netdev, return -EINVAL; } - if (ec->tx_coalesce_usecs > (I40E_MAX_ITR << 1)) { + if (ec->tx_coalesce_usecs > I40E_MAX_ITR) { netif_info(pf, drv, netdev, "Invalid value, tx-usecs range is 0-8160\n"); return -EINVAL; } if (ec->use_adaptive_rx_coalesce && !cur_rx_itr) - ec->rx_coalesce_usecs = I40E_MIN_ITR << 1; + ec->rx_coalesce_usecs = I40E_MIN_ITR; if (ec->use_adaptive_tx_coalesce && !cur_tx_itr) - ec->tx_coalesce_usecs = I40E_MIN_ITR << 1; + ec->tx_coalesce_usecs = I40E_MIN_ITR; intrl_reg = i40e_intrl_usec_to_reg(ec->rx_coalesce_usecs_high); vsi->int_rate_limit = INTRL_REG_TO_USEC(intrl_reg); @@ -4406,6 +4409,8 @@ static int i40e_set_priv_flags(struct net_device *dev, u32 flags) } flags_complete: + changed_flags = orig_flags ^ new_flags; + /* Before we finalize any flag changes, we need to perform some * checks to ensure that the changes are supported and safe. */ @@ -4415,21 +4420,17 @@ flags_complete: !(pf->hw_features & I40E_HW_ATR_EVICT_CAPABLE)) return -EOPNOTSUPP; - /* Disable FW LLDP not supported if NPAR active or if FW - * API version < 1.7 + /* If the driver detected FW LLDP was disabled on init, this flag could + * be set, however we do not support _changing_ the flag if NPAR is + * enabled or FW API version < 1.7. There are situations where older + * FW versions/NPAR enabled PFs could disable LLDP, however we _must_ + * not allow the user to enable/disable LLDP with this flag on + * unsupported FW versions. */ - if (new_flags & I40E_FLAG_DISABLE_FW_LLDP) { - if (pf->hw.func_caps.npar_enable) { - dev_warn(&pf->pdev->dev, - "Unable to stop FW LLDP if NPAR active\n"); - return -EOPNOTSUPP; - } - - if (pf->hw.aq.api_maj_ver < 1 || - (pf->hw.aq.api_maj_ver == 1 && - pf->hw.aq.api_min_ver < 7)) { + if (changed_flags & I40E_FLAG_DISABLE_FW_LLDP) { + if (!(pf->hw_features & I40E_HW_STOPPABLE_FW_LLDP)) { dev_warn(&pf->pdev->dev, - "FW ver does not support stopping FW LLDP\n"); + "Device does not support changing FW LLDP\n"); return -EOPNOTSUPP; } } @@ -4439,6 +4440,10 @@ flags_complete: * something else has modified the flags variable since we copied it * originally. We'll just punt with an error and log something in the * message buffer. + * + * This is the point of no return for this function. We need to have + * checked any discrepancies or misconfigurations and returned + * EOPNOTSUPP before updating pf->flags here. */ if (cmpxchg64(&pf->flags, orig_flags, new_flags) != orig_flags) { dev_warn(&pf->pdev->dev, @@ -4446,8 +4451,6 @@ flags_complete: return -EAGAIN; } - changed_flags = orig_flags ^ new_flags; - /* Process any additional changes needed as a result of flag changes. * The changed_flags value reflects the list of bits that were * changed in the code above. @@ -4479,6 +4482,12 @@ flags_complete: } } + if ((changed_flags & pf->flags & + I40E_FLAG_LINK_DOWN_ON_CLOSE_ENABLED) && + (pf->flags & I40E_FLAG_MFP_ENABLED)) + dev_warn(&pf->pdev->dev, + "Turning on link-down-on-close flag may affect other partitions\n"); + if (changed_flags & I40E_FLAG_DISABLE_FW_LLDP) { if (pf->flags & I40E_FLAG_DISABLE_FW_LLDP) { struct i40e_dcbx_config *dcbcfg; diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index e31adbc75f9c..be9a1467a1a1 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -69,12 +69,6 @@ static int i40e_reset(struct i40e_pf *pf); static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired); static void i40e_fdir_sb_setup(struct i40e_pf *pf); static int i40e_veb_get_bw_info(struct i40e_veb *veb); -static int i40e_add_del_cloud_filter(struct i40e_vsi *vsi, - struct i40e_cloud_filter *filter, - bool add); -static int i40e_add_del_cloud_filter_big_buf(struct i40e_vsi *vsi, - struct i40e_cloud_filter *filter, - bool add); static int i40e_get_capabilities(struct i40e_pf *pf, enum i40e_admin_queue_opc list_type); @@ -215,8 +209,8 @@ static int i40e_get_lump(struct i40e_pf *pf, struct i40e_lump_tracking *pile, if (!pile || needed == 0 || id >= I40E_PILE_VALID_BIT) { dev_info(&pf->pdev->dev, - "param err: pile=%p needed=%d id=0x%04x\n", - pile, needed, id); + "param err: pile=%s needed=%d id=0x%04x\n", + pile ? "<valid>" : "<null>", needed, id); return -EINVAL; } @@ -1380,14 +1374,7 @@ struct i40e_mac_filter *i40e_add_filter(struct i40e_vsi *vsi, ether_addr_copy(f->macaddr, macaddr); f->vlan = vlan; - /* If we're in overflow promisc mode, set the state directly - * to failed, so we don't bother to try sending the filter - * to the hardware. - */ - if (test_bit(__I40E_VSI_OVERFLOW_PROMISC, vsi->state)) - f->state = I40E_FILTER_FAILED; - else - f->state = I40E_FILTER_NEW; + f->state = I40E_FILTER_NEW; INIT_HLIST_NODE(&f->hlist); key = i40e_addr_to_hkey(macaddr); @@ -2116,17 +2103,16 @@ void i40e_aqc_del_filters(struct i40e_vsi *vsi, const char *vsi_name, * @list: the list of filters to send to firmware * @add_head: Position in the add hlist * @num_add: the number of filters to add - * @promisc_change: set to true on exit if promiscuous mode was forced on * * Send a request to firmware via AdminQ to add a chunk of filters. Will set - * promisc_changed to true if the firmware has run out of space for more - * filters. + * __I40E_VSI_OVERFLOW_PROMISC bit in vsi->state if the firmware has run out of + * space for more filters. */ static void i40e_aqc_add_filters(struct i40e_vsi *vsi, const char *vsi_name, struct i40e_aqc_add_macvlan_element_data *list, struct i40e_new_mac_filter *add_head, - int num_add, bool *promisc_changed) + int num_add) { struct i40e_hw *hw = &vsi->back->hw; int aq_err, fcnt; @@ -2136,7 +2122,6 @@ void i40e_aqc_add_filters(struct i40e_vsi *vsi, const char *vsi_name, fcnt = i40e_update_filter_state(num_add, list, add_head); if (fcnt != num_add) { - *promisc_changed = true; set_bit(__I40E_VSI_OVERFLOW_PROMISC, vsi->state); dev_warn(&vsi->back->pdev->dev, "Error %s adding RX filters on %s, promiscuous mode forced on\n", @@ -2177,11 +2162,13 @@ i40e_aqc_broadcast_filter(struct i40e_vsi *vsi, const char *vsi_name, NULL); } - if (aq_ret) + if (aq_ret) { + set_bit(__I40E_VSI_OVERFLOW_PROMISC, vsi->state); dev_warn(&vsi->back->pdev->dev, - "Error %s setting broadcast promiscuous mode on %s\n", + "Error %s, forcing overflow promiscuous on %s\n", i40e_aq_str(hw, hw->aq.asq_last_status), vsi_name); + } return aq_ret; } @@ -2267,9 +2254,9 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi) struct i40e_mac_filter *f; struct i40e_new_mac_filter *new, *add_head = NULL; struct i40e_hw *hw = &vsi->back->hw; + bool old_overflow, new_overflow; unsigned int failed_filters = 0; unsigned int vlan_filters = 0; - bool promisc_changed = false; char vsi_name[16] = "PF"; int filter_list_len = 0; i40e_status aq_ret = 0; @@ -2291,6 +2278,8 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi) usleep_range(1000, 2000); pf = vsi->back; + old_overflow = test_bit(__I40E_VSI_OVERFLOW_PROMISC, vsi->state); + if (vsi->netdev) { changed_flags = vsi->current_netdev_flags ^ vsi->netdev->flags; vsi->current_netdev_flags = vsi->netdev->flags; @@ -2423,12 +2412,6 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi) num_add = 0; hlist_for_each_entry_safe(new, h, &tmp_add_list, hlist) { - if (test_bit(__I40E_VSI_OVERFLOW_PROMISC, - vsi->state)) { - new->state = I40E_FILTER_FAILED; - continue; - } - /* handle broadcast filters by updating the broadcast * promiscuous flag instead of adding a MAC filter. */ @@ -2464,15 +2447,14 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi) /* flush a full buffer */ if (num_add == filter_list_len) { i40e_aqc_add_filters(vsi, vsi_name, add_list, - add_head, num_add, - &promisc_changed); + add_head, num_add); memset(add_list, 0, list_size); num_add = 0; } } if (num_add) { i40e_aqc_add_filters(vsi, vsi_name, add_list, add_head, - num_add, &promisc_changed); + num_add); } /* Now move all of the filters from the temp add list back to * the VSI's list. @@ -2501,24 +2483,16 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi) } spin_unlock_bh(&vsi->mac_filter_hash_lock); - /* If promiscuous mode has changed, we need to calculate a new - * threshold for when we are safe to exit - */ - if (promisc_changed) - vsi->promisc_threshold = (vsi->active_filters * 3) / 4; - /* Check if we are able to exit overflow promiscuous mode. We can * safely exit if we didn't just enter, we no longer have any failed * filters, and we have reduced filters below the threshold value. */ - if (test_bit(__I40E_VSI_OVERFLOW_PROMISC, vsi->state) && - !promisc_changed && !failed_filters && - (vsi->active_filters < vsi->promisc_threshold)) { + if (old_overflow && !failed_filters && + vsi->active_filters < vsi->promisc_threshold) { dev_info(&pf->pdev->dev, "filter logjam cleared on %s, leaving overflow promiscuous mode\n", vsi_name); clear_bit(__I40E_VSI_OVERFLOW_PROMISC, vsi->state); - promisc_changed = true; vsi->promisc_threshold = 0; } @@ -2528,6 +2502,14 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi) goto out; } + new_overflow = test_bit(__I40E_VSI_OVERFLOW_PROMISC, vsi->state); + + /* If we are entering overflow promiscuous, we need to calculate a new + * threshold for when we are safe to exit + */ + if (!old_overflow && new_overflow) + vsi->promisc_threshold = (vsi->active_filters * 3) / 4; + /* check for changes in promiscuous modes */ if (changed_flags & IFF_ALLMULTI) { bool cur_multipromisc; @@ -2548,12 +2530,11 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi) } } - if ((changed_flags & IFF_PROMISC) || promisc_changed) { + if ((changed_flags & IFF_PROMISC) || old_overflow != new_overflow) { bool cur_promisc; cur_promisc = (!!(vsi->current_netdev_flags & IFF_PROMISC) || - test_bit(__I40E_VSI_OVERFLOW_PROMISC, - vsi->state)); + new_overflow); aq_ret = i40e_set_promiscuous(pf, cur_promisc); if (aq_ret) { retval = i40e_aq_rc_to_posix(aq_ret, @@ -3449,15 +3430,20 @@ static void i40e_vsi_configure_msix(struct i40e_vsi *vsi) for (i = 0; i < vsi->num_q_vectors; i++, vector++) { struct i40e_q_vector *q_vector = vsi->q_vectors[i]; - q_vector->itr_countdown = ITR_COUNTDOWN_START; - q_vector->rx.itr = ITR_TO_REG(vsi->rx_rings[i]->rx_itr_setting); - q_vector->rx.latency_range = I40E_LOW_LATENCY; + q_vector->rx.next_update = jiffies + 1; + q_vector->rx.target_itr = + ITR_TO_REG(vsi->rx_rings[i]->itr_setting); wr32(hw, I40E_PFINT_ITRN(I40E_RX_ITR, vector - 1), - q_vector->rx.itr); - q_vector->tx.itr = ITR_TO_REG(vsi->tx_rings[i]->tx_itr_setting); - q_vector->tx.latency_range = I40E_LOW_LATENCY; + q_vector->rx.target_itr); + q_vector->rx.current_itr = q_vector->rx.target_itr; + + q_vector->tx.next_update = jiffies + 1; + q_vector->tx.target_itr = + ITR_TO_REG(vsi->tx_rings[i]->itr_setting); wr32(hw, I40E_PFINT_ITRN(I40E_TX_ITR, vector - 1), - q_vector->tx.itr); + q_vector->tx.target_itr); + q_vector->tx.current_itr = q_vector->tx.target_itr; + wr32(hw, I40E_PFINT_RATEN(vector - 1), i40e_intrl_usec_to_reg(vsi->int_rate_limit)); @@ -3558,13 +3544,14 @@ static void i40e_configure_msi_and_legacy(struct i40e_vsi *vsi) u32 val; /* set the ITR configuration */ - q_vector->itr_countdown = ITR_COUNTDOWN_START; - q_vector->rx.itr = ITR_TO_REG(vsi->rx_rings[0]->rx_itr_setting); - q_vector->rx.latency_range = I40E_LOW_LATENCY; - wr32(hw, I40E_PFINT_ITR0(I40E_RX_ITR), q_vector->rx.itr); - q_vector->tx.itr = ITR_TO_REG(vsi->tx_rings[0]->tx_itr_setting); - q_vector->tx.latency_range = I40E_LOW_LATENCY; - wr32(hw, I40E_PFINT_ITR0(I40E_TX_ITR), q_vector->tx.itr); + q_vector->rx.next_update = jiffies + 1; + q_vector->rx.target_itr = ITR_TO_REG(vsi->rx_rings[0]->itr_setting); + wr32(hw, I40E_PFINT_ITR0(I40E_RX_ITR), q_vector->rx.target_itr); + q_vector->rx.current_itr = q_vector->rx.target_itr; + q_vector->tx.next_update = jiffies + 1; + q_vector->tx.target_itr = ITR_TO_REG(vsi->tx_rings[0]->itr_setting); + wr32(hw, I40E_PFINT_ITR0(I40E_TX_ITR), q_vector->tx.target_itr); + q_vector->tx.current_itr = q_vector->tx.target_itr; i40e_enable_misc_int_causes(pf); @@ -5375,7 +5362,7 @@ out: * @vsi: VSI to be configured * **/ -int i40e_get_link_speed(struct i40e_vsi *vsi) +static int i40e_get_link_speed(struct i40e_vsi *vsi) { struct i40e_pf *pf = vsi->back; @@ -6560,6 +6547,75 @@ int i40e_up(struct i40e_vsi *vsi) } /** + * i40e_force_link_state - Force the link status + * @pf: board private structure + * @is_up: whether the link state should be forced up or down + **/ +static i40e_status i40e_force_link_state(struct i40e_pf *pf, bool is_up) +{ + struct i40e_aq_get_phy_abilities_resp abilities; + struct i40e_aq_set_phy_config config = {0}; + struct i40e_hw *hw = &pf->hw; + i40e_status err; + u64 mask; + + /* Get the current phy config */ + err = i40e_aq_get_phy_capabilities(hw, false, false, &abilities, + NULL); + if (err) { + dev_err(&pf->pdev->dev, + "failed to get phy cap., ret = %s last_status = %s\n", + i40e_stat_str(hw, err), + i40e_aq_str(hw, hw->aq.asq_last_status)); + return err; + } + + /* If link needs to go up, but was not forced to go down, + * no need for a flap + */ + if (is_up && abilities.phy_type != 0) + return I40E_SUCCESS; + + /* To force link we need to set bits for all supported PHY types, + * but there are now more than 32, so we need to split the bitmap + * across two fields. + */ + mask = I40E_PHY_TYPES_BITMASK; + config.phy_type = is_up ? cpu_to_le32((u32)(mask & 0xffffffff)) : 0; + config.phy_type_ext = is_up ? (u8)((mask >> 32) & 0xff) : 0; + /* Copy the old settings, except of phy_type */ + config.abilities = abilities.abilities; + config.link_speed = abilities.link_speed; + config.eee_capability = abilities.eee_capability; + config.eeer = abilities.eeer_val; + config.low_power_ctrl = abilities.d3_lpan; + err = i40e_aq_set_phy_config(hw, &config, NULL); + + if (err) { + dev_err(&pf->pdev->dev, + "set phy config ret = %s last_status = %s\n", + i40e_stat_str(&pf->hw, err), + i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status)); + return err; + } + + /* Update the link info */ + err = i40e_update_link_info(hw); + if (err) { + /* Wait a little bit (on 40G cards it sometimes takes a really + * long time for link to come back from the atomic reset) + * and try once more + */ + msleep(1000); + i40e_update_link_info(hw); + } + + i40e_aq_set_link_restart_an(hw, true, NULL); + + return I40E_SUCCESS; +} + +/** * i40e_down - Shutdown the connection processing * @vsi: the VSI being stopped **/ @@ -6576,6 +6632,9 @@ void i40e_down(struct i40e_vsi *vsi) } i40e_vsi_disable_irq(vsi); i40e_vsi_stop_rings(vsi); + if (vsi->type == I40E_VSI_MAIN && + vsi->back->flags & I40E_FLAG_LINK_DOWN_ON_CLOSE_ENABLED) + i40e_force_link_state(vsi->back, false); i40e_napi_disable_all(vsi); for (i = 0; i < vsi->num_queue_pairs; i++) { @@ -6848,8 +6907,8 @@ i40e_set_cld_element(struct i40e_cloud_filter *filter, * Add or delete a cloud filter for a specific flow spec. * Returns 0 if the filter were successfully added. **/ -static int i40e_add_del_cloud_filter(struct i40e_vsi *vsi, - struct i40e_cloud_filter *filter, bool add) +int i40e_add_del_cloud_filter(struct i40e_vsi *vsi, + struct i40e_cloud_filter *filter, bool add) { struct i40e_aqc_cloud_filters_element_data cld_filter; struct i40e_pf *pf = vsi->back; @@ -6915,9 +6974,9 @@ static int i40e_add_del_cloud_filter(struct i40e_vsi *vsi, * Add or delete a cloud filter for a specific flow spec using big buffer. * Returns 0 if the filter were successfully added. **/ -static int i40e_add_del_cloud_filter_big_buf(struct i40e_vsi *vsi, - struct i40e_cloud_filter *filter, - bool add) +int i40e_add_del_cloud_filter_big_buf(struct i40e_vsi *vsi, + struct i40e_cloud_filter *filter, + bool add) { struct i40e_aqc_cloud_filters_element_bb cld_filter; struct i40e_pf *pf = vsi->back; @@ -7537,6 +7596,9 @@ int i40e_open(struct net_device *netdev) netif_carrier_off(netdev); + if (i40e_force_link_state(pf, true)) + return -EAGAIN; + err = i40e_vsi_open(vsi); if (err) return err; @@ -9215,6 +9277,17 @@ static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired) } i40e_get_oem_version(&pf->hw); + if (test_bit(__I40E_EMP_RESET_INTR_RECEIVED, pf->state) && + ((hw->aq.fw_maj_ver == 4 && hw->aq.fw_min_ver <= 33) || + hw->aq.fw_maj_ver < 4) && hw->mac.type == I40E_MAC_XL710) { + /* The following delay is necessary for 4.33 firmware and older + * to recover after EMP reset. 200 ms should suffice but we + * put here 300 ms to be sure that FW is ready to operate + * after reset. + */ + mdelay(300); + } + /* re-verify the eeprom if we just had an EMP reset */ if (test_and_clear_bit(__I40E_EMP_RESET_INTR_RECEIVED, pf->state)) i40e_verify_eeprom(pf); @@ -9937,18 +10010,17 @@ static int i40e_vsi_clear(struct i40e_vsi *vsi) mutex_lock(&pf->switch_mutex); if (!pf->vsi[vsi->idx]) { - dev_err(&pf->pdev->dev, "pf->vsi[%d] is NULL, just free vsi[%d](%p,type %d)\n", - vsi->idx, vsi->idx, vsi, vsi->type); + dev_err(&pf->pdev->dev, "pf->vsi[%d] is NULL, just free vsi[%d](type %d)\n", + vsi->idx, vsi->idx, vsi->type); goto unlock_vsi; } if (pf->vsi[vsi->idx] != vsi) { dev_err(&pf->pdev->dev, - "pf->vsi[%d](%p, type %d) != vsi[%d](%p,type %d): no free!\n", + "pf->vsi[%d](type %d) != vsi[%d](type %d): no free!\n", pf->vsi[vsi->idx]->idx, - pf->vsi[vsi->idx], pf->vsi[vsi->idx]->type, - vsi->idx, vsi, vsi->type); + vsi->idx, vsi->type); goto unlock_vsi; } @@ -10018,7 +10090,7 @@ static int i40e_alloc_rings(struct i40e_vsi *vsi) ring->dcb_tc = 0; if (vsi->back->hw_features & I40E_HW_WB_ON_ITR_CAPABLE) ring->flags = I40E_TXR_FLAGS_WB_ON_ITR; - ring->tx_itr_setting = pf->tx_itr_default; + ring->itr_setting = pf->tx_itr_default; vsi->tx_rings[i] = ring++; if (!i40e_enabled_xdp_vsi(vsi)) @@ -10036,7 +10108,7 @@ static int i40e_alloc_rings(struct i40e_vsi *vsi) if (vsi->back->hw_features & I40E_HW_WB_ON_ITR_CAPABLE) ring->flags = I40E_TXR_FLAGS_WB_ON_ITR; set_ring_xdp(ring); - ring->tx_itr_setting = pf->tx_itr_default; + ring->itr_setting = pf->tx_itr_default; vsi->xdp_rings[i] = ring++; setup_rx: @@ -10049,7 +10121,7 @@ setup_rx: ring->count = vsi->num_desc; ring->size = 0; ring->dcb_tc = 0; - ring->rx_itr_setting = pf->rx_itr_default; + ring->itr_setting = pf->rx_itr_default; vsi->rx_rings[i] = ring; } @@ -10328,9 +10400,6 @@ static int i40e_vsi_alloc_q_vector(struct i40e_vsi *vsi, int v_idx, int cpu) netif_napi_add(vsi->netdev, &q_vector->napi, i40e_napi_poll, NAPI_POLL_WEIGHT); - q_vector->rx.latency_range = I40E_LOW_LATENCY; - q_vector->tx.latency_range = I40E_LOW_LATENCY; - /* tie q_vector and vsi together */ vsi->q_vectors[v_idx] = q_vector; @@ -11089,6 +11158,16 @@ static int i40e_sw_init(struct i40e_pf *pf) /* IWARP needs one extra vector for CQP just like MISC.*/ pf->num_iwarp_msix = (int)num_online_cpus() + 1; } + /* Stopping the FW LLDP engine is only supported on the + * XL710 with a FW ver >= 1.7. Also, stopping FW LLDP + * engine is not supported if NPAR is functioning on this + * part + */ + if (pf->hw.mac.type == I40E_MAC_XL710 && + !pf->hw.func_caps.npar_enable && + (pf->hw.aq.api_maj_ver > 1 || + (pf->hw.aq.api_maj_ver == 1 && pf->hw.aq.api_min_ver > 6))) + pf->hw_features |= I40E_HW_STOPPABLE_FW_LLDP; #ifdef CONFIG_PCI_IOV if (pf->hw.func_caps.num_vfs && pf->hw.partition_id == 1) { diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index e554aa6cf070..97cfe944b568 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -708,16 +708,22 @@ void i40e_free_tx_resources(struct i40e_ring *tx_ring) /** * i40e_get_tx_pending - how many tx descriptors not processed * @tx_ring: the ring of descriptors + * @in_sw: use SW variables * * Since there is no access to the ring head register * in XL710, we need to use our local copies **/ -u32 i40e_get_tx_pending(struct i40e_ring *ring) +u32 i40e_get_tx_pending(struct i40e_ring *ring, bool in_sw) { u32 head, tail; - head = i40e_get_head(ring); - tail = readl(ring->tail); + if (!in_sw) { + head = i40e_get_head(ring); + tail = readl(ring->tail); + } else { + head = ring->next_to_clean; + tail = ring->next_to_use; + } if (head != tail) return (head < tail) ? @@ -774,7 +780,7 @@ void i40e_detect_recover_hung(struct i40e_vsi *vsi) */ smp_rmb(); tx_ring->tx_stats.prev_pkt_ctr = - i40e_get_tx_pending(tx_ring) ? packets : -1; + i40e_get_tx_pending(tx_ring, true) ? packets : -1; } } } @@ -898,7 +904,7 @@ static bool i40e_clean_tx_irq(struct i40e_vsi *vsi, * them to be written back in case we stay in NAPI. * In this mode on X722 we do not enable Interrupt. */ - unsigned int j = i40e_get_tx_pending(tx_ring); + unsigned int j = i40e_get_tx_pending(tx_ring, false); if (budget && ((j / WB_STRIDE) == 0) && (j > 0) && @@ -995,99 +1001,241 @@ void i40e_force_wb(struct i40e_vsi *vsi, struct i40e_q_vector *q_vector) } } +static inline bool i40e_container_is_rx(struct i40e_q_vector *q_vector, + struct i40e_ring_container *rc) +{ + return &q_vector->rx == rc; +} + +static inline unsigned int i40e_itr_divisor(struct i40e_q_vector *q_vector) +{ + unsigned int divisor; + + switch (q_vector->vsi->back->hw.phy.link_info.link_speed) { + case I40E_LINK_SPEED_40GB: + divisor = I40E_ITR_ADAPTIVE_MIN_INC * 1024; + break; + case I40E_LINK_SPEED_25GB: + case I40E_LINK_SPEED_20GB: + divisor = I40E_ITR_ADAPTIVE_MIN_INC * 512; + break; + default: + case I40E_LINK_SPEED_10GB: + divisor = I40E_ITR_ADAPTIVE_MIN_INC * 256; + break; + case I40E_LINK_SPEED_1GB: + case I40E_LINK_SPEED_100MB: + divisor = I40E_ITR_ADAPTIVE_MIN_INC * 32; + break; + } + + return divisor; +} + /** - * i40e_set_new_dynamic_itr - Find new ITR level + * i40e_update_itr - update the dynamic ITR value based on statistics + * @q_vector: structure containing interrupt and ring information * @rc: structure containing ring performance data * - * Returns true if ITR changed, false if not - * - * Stores a new ITR value based on packets and byte counts during - * the last interrupt. The advantage of per interrupt computation - * is faster updates and more accurate ITR for the current traffic - * pattern. Constants in this function were computed based on - * theoretical maximum wire speed and thresholds were set based on - * testing data as well as attempting to minimize response time + * Stores a new ITR value based on packets and byte + * counts during the last interrupt. The advantage of per interrupt + * computation is faster updates and more accurate ITR for the current + * traffic pattern. Constants in this function were computed + * based on theoretical maximum wire speed and thresholds were set based + * on testing data as well as attempting to minimize response time * while increasing bulk throughput. **/ -static bool i40e_set_new_dynamic_itr(struct i40e_ring_container *rc) +static void i40e_update_itr(struct i40e_q_vector *q_vector, + struct i40e_ring_container *rc) { - enum i40e_latency_range new_latency_range = rc->latency_range; - u32 new_itr = rc->itr; - int bytes_per_usec; - unsigned int usecs, estimated_usecs; + unsigned int avg_wire_size, packets, bytes, itr; + unsigned long next_update = jiffies; - if (rc->total_packets == 0 || !rc->itr) - return false; + /* If we don't have any rings just leave ourselves set for maximum + * possible latency so we take ourselves out of the equation. + */ + if (!rc->ring || !ITR_IS_DYNAMIC(rc->ring->itr_setting)) + return; + + /* For Rx we want to push the delay up and default to low latency. + * for Tx we want to pull the delay down and default to high latency. + */ + itr = i40e_container_is_rx(q_vector, rc) ? + I40E_ITR_ADAPTIVE_MIN_USECS | I40E_ITR_ADAPTIVE_LATENCY : + I40E_ITR_ADAPTIVE_MAX_USECS | I40E_ITR_ADAPTIVE_LATENCY; + + /* If we didn't update within up to 1 - 2 jiffies we can assume + * that either packets are coming in so slow there hasn't been + * any work, or that there is so much work that NAPI is dealing + * with interrupt moderation and we don't need to do anything. + */ + if (time_after(next_update, rc->next_update)) + goto clear_counts; + + /* If itr_countdown is set it means we programmed an ITR within + * the last 4 interrupt cycles. This has a side effect of us + * potentially firing an early interrupt. In order to work around + * this we need to throw out any data received for a few + * interrupts following the update. + */ + if (q_vector->itr_countdown) { + itr = rc->target_itr; + goto clear_counts; + } + + packets = rc->total_packets; + bytes = rc->total_bytes; - usecs = (rc->itr << 1) * ITR_COUNTDOWN_START; - bytes_per_usec = rc->total_bytes / usecs; + if (i40e_container_is_rx(q_vector, rc)) { + /* If Rx there are 1 to 4 packets and bytes are less than + * 9000 assume insufficient data to use bulk rate limiting + * approach unless Tx is already in bulk rate limiting. We + * are likely latency driven. + */ + if (packets && packets < 4 && bytes < 9000 && + (q_vector->tx.target_itr & I40E_ITR_ADAPTIVE_LATENCY)) { + itr = I40E_ITR_ADAPTIVE_LATENCY; + goto adjust_by_size; + } + } else if (packets < 4) { + /* If we have Tx and Rx ITR maxed and Tx ITR is running in + * bulk mode and we are receiving 4 or fewer packets just + * reset the ITR_ADAPTIVE_LATENCY bit for latency mode so + * that the Rx can relax. + */ + if (rc->target_itr == I40E_ITR_ADAPTIVE_MAX_USECS && + (q_vector->rx.target_itr & I40E_ITR_MASK) == + I40E_ITR_ADAPTIVE_MAX_USECS) + goto clear_counts; + } else if (packets > 32) { + /* If we have processed over 32 packets in a single interrupt + * for Tx assume we need to switch over to "bulk" mode. + */ + rc->target_itr &= ~I40E_ITR_ADAPTIVE_LATENCY; + } - /* The calculations in this algorithm depend on interrupts actually - * firing at the ITR rate. This may not happen if the packet rate is - * really low, or if we've been napi polling. Check to make sure - * that's not the case before we continue. + /* We have no packets to actually measure against. This means + * either one of the other queues on this vector is active or + * we are a Tx queue doing TSO with too high of an interrupt rate. + * + * Between 4 and 56 we can assume that our current interrupt delay + * is only slightly too low. As such we should increase it by a small + * fixed amount. */ - estimated_usecs = jiffies_to_usecs(jiffies - rc->last_itr_update); - if (estimated_usecs > usecs) { - new_latency_range = I40E_LOW_LATENCY; - goto reset_latency; + if (packets < 56) { + itr = rc->target_itr + I40E_ITR_ADAPTIVE_MIN_INC; + if ((itr & I40E_ITR_MASK) > I40E_ITR_ADAPTIVE_MAX_USECS) { + itr &= I40E_ITR_ADAPTIVE_LATENCY; + itr += I40E_ITR_ADAPTIVE_MAX_USECS; + } + goto clear_counts; + } + + if (packets <= 256) { + itr = min(q_vector->tx.current_itr, q_vector->rx.current_itr); + itr &= I40E_ITR_MASK; + + /* Between 56 and 112 is our "goldilocks" zone where we are + * working out "just right". Just report that our current + * ITR is good for us. + */ + if (packets <= 112) + goto clear_counts; + + /* If packet count is 128 or greater we are likely looking + * at a slight overrun of the delay we want. Try halving + * our delay to see if that will cut the number of packets + * in half per interrupt. + */ + itr /= 2; + itr &= I40E_ITR_MASK; + if (itr < I40E_ITR_ADAPTIVE_MIN_USECS) + itr = I40E_ITR_ADAPTIVE_MIN_USECS; + + goto clear_counts; } - /* simple throttlerate management - * 0-10MB/s lowest (50000 ints/s) - * 10-20MB/s low (20000 ints/s) - * 20-1249MB/s bulk (18000 ints/s) + /* The paths below assume we are dealing with a bulk ITR since + * number of packets is greater than 256. We are just going to have + * to compute a value and try to bring the count under control, + * though for smaller packet sizes there isn't much we can do as + * NAPI polling will likely be kicking in sooner rather than later. + */ + itr = I40E_ITR_ADAPTIVE_BULK; + +adjust_by_size: + /* If packet counts are 256 or greater we can assume we have a gross + * overestimation of what the rate should be. Instead of trying to fine + * tune it just use the formula below to try and dial in an exact value + * give the current packet size of the frame. + */ + avg_wire_size = bytes / packets; + + /* The following is a crude approximation of: + * wmem_default / (size + overhead) = desired_pkts_per_int + * rate / bits_per_byte / (size + ethernet overhead) = pkt_rate + * (desired_pkt_rate / pkt_rate) * usecs_per_sec = ITR value + * + * Assuming wmem_default is 212992 and overhead is 640 bytes per + * packet, (256 skb, 64 headroom, 320 shared info), we can reduce the + * formula down to * - * The math works out because the divisor is in 10^(-6) which - * turns the bytes/us input value into MB/s values, but - * make sure to use usecs, as the register values written - * are in 2 usec increments in the ITR registers, and make sure - * to use the smoothed values that the countdown timer gives us. + * (170 * (size + 24)) / (size + 640) = ITR + * + * We first do some math on the packet size and then finally bitshift + * by 8 after rounding up. We also have to account for PCIe link speed + * difference as ITR scales based on this. */ - switch (new_latency_range) { - case I40E_LOWEST_LATENCY: - if (bytes_per_usec > 10) - new_latency_range = I40E_LOW_LATENCY; - break; - case I40E_LOW_LATENCY: - if (bytes_per_usec > 20) - new_latency_range = I40E_BULK_LATENCY; - else if (bytes_per_usec <= 10) - new_latency_range = I40E_LOWEST_LATENCY; - break; - case I40E_BULK_LATENCY: - default: - if (bytes_per_usec <= 20) - new_latency_range = I40E_LOW_LATENCY; - break; + if (avg_wire_size <= 60) { + /* Start at 250k ints/sec */ + avg_wire_size = 4096; + } else if (avg_wire_size <= 380) { + /* 250K ints/sec to 60K ints/sec */ + avg_wire_size *= 40; + avg_wire_size += 1696; + } else if (avg_wire_size <= 1084) { + /* 60K ints/sec to 36K ints/sec */ + avg_wire_size *= 15; + avg_wire_size += 11452; + } else if (avg_wire_size <= 1980) { + /* 36K ints/sec to 30K ints/sec */ + avg_wire_size *= 5; + avg_wire_size += 22420; + } else { + /* plateau at a limit of 30K ints/sec */ + avg_wire_size = 32256; } -reset_latency: - rc->latency_range = new_latency_range; + /* If we are in low latency mode halve our delay which doubles the + * rate to somewhere between 100K to 16K ints/sec + */ + if (itr & I40E_ITR_ADAPTIVE_LATENCY) + avg_wire_size /= 2; - switch (new_latency_range) { - case I40E_LOWEST_LATENCY: - new_itr = I40E_ITR_50K; - break; - case I40E_LOW_LATENCY: - new_itr = I40E_ITR_20K; - break; - case I40E_BULK_LATENCY: - new_itr = I40E_ITR_18K; - break; - default: - break; + /* Resultant value is 256 times larger than it needs to be. This + * gives us room to adjust the value as needed to either increase + * or decrease the value based on link speeds of 10G, 2.5G, 1G, etc. + * + * Use addition as we have already recorded the new latency flag + * for the ITR value. + */ + itr += DIV_ROUND_UP(avg_wire_size, i40e_itr_divisor(q_vector)) * + I40E_ITR_ADAPTIVE_MIN_INC; + + if ((itr & I40E_ITR_MASK) > I40E_ITR_ADAPTIVE_MAX_USECS) { + itr &= I40E_ITR_ADAPTIVE_LATENCY; + itr += I40E_ITR_ADAPTIVE_MAX_USECS; } +clear_counts: + /* write back value */ + rc->target_itr = itr; + + /* next update should occur within next jiffy */ + rc->next_update = next_update + 1; + rc->total_bytes = 0; rc->total_packets = 0; - rc->last_itr_update = jiffies; - - if (new_itr != rc->itr) { - rc->itr = new_itr; - return true; - } - return false; } /** @@ -1991,7 +2139,7 @@ static struct sk_buff *i40e_build_skb(struct i40e_ring *rx_ring, * @rx_buffer: rx buffer to pull data from * * This function will clean up the contents of the rx_buffer. It will - * either recycle the bufer or unmap it and free the associated resources. + * either recycle the buffer or unmap it and free the associated resources. */ static void i40e_put_rx_buffer(struct i40e_ring *rx_ring, struct i40e_rx_buffer *rx_buffer) @@ -2274,29 +2422,45 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget) return failure ? budget : (int)total_rx_packets; } -static u32 i40e_buildreg_itr(const int type, const u16 itr) +static inline u32 i40e_buildreg_itr(const int type, u16 itr) { u32 val; + /* We don't bother with setting the CLEARPBA bit as the data sheet + * points out doing so is "meaningless since it was already + * auto-cleared". The auto-clearing happens when the interrupt is + * asserted. + * + * Hardware errata 28 for also indicates that writing to a + * xxINT_DYN_CTLx CSR with INTENA_MSK (bit 31) set to 0 will clear + * an event in the PBA anyway so we need to rely on the automask + * to hold pending events for us until the interrupt is re-enabled + * + * The itr value is reported in microseconds, and the register + * value is recorded in 2 microsecond units. For this reason we + * only need to shift by the interval shift - 1 instead of the + * full value. + */ + itr &= I40E_ITR_MASK; + val = I40E_PFINT_DYN_CTLN_INTENA_MASK | - I40E_PFINT_DYN_CTLN_CLEARPBA_MASK | (type << I40E_PFINT_DYN_CTLN_ITR_INDX_SHIFT) | - (itr << I40E_PFINT_DYN_CTLN_INTERVAL_SHIFT); + (itr << (I40E_PFINT_DYN_CTLN_INTERVAL_SHIFT - 1)); return val; } /* a small macro to shorten up some long lines */ #define INTREG I40E_PFINT_DYN_CTLN -static inline int get_rx_itr(struct i40e_vsi *vsi, int idx) -{ - return vsi->rx_rings[idx]->rx_itr_setting; -} -static inline int get_tx_itr(struct i40e_vsi *vsi, int idx) -{ - return vsi->tx_rings[idx]->tx_itr_setting; -} +/* The act of updating the ITR will cause it to immediately trigger. In order + * to prevent this from throwing off adaptive update statistics we defer the + * update so that it can only happen so often. So after either Tx or Rx are + * updated we make the adaptive scheme wait until either the ITR completely + * expires via the next_update expiration or we have been through at least + * 3 interrupts. + */ +#define ITR_COUNTDOWN_START 3 /** * i40e_update_enable_itr - Update itr and re-enable MSIX interrupt @@ -2308,10 +2472,7 @@ static inline void i40e_update_enable_itr(struct i40e_vsi *vsi, struct i40e_q_vector *q_vector) { struct i40e_hw *hw = &vsi->back->hw; - bool rx = false, tx = false; - u32 rxval, txval; - int idx = q_vector->v_idx; - int rx_itr_setting, tx_itr_setting; + u32 intval; /* If we don't have MSIX, then we only need to re-enable icr0 */ if (!(vsi->back->flags & I40E_FLAG_MSIX_ENABLED)) { @@ -2319,65 +2480,49 @@ static inline void i40e_update_enable_itr(struct i40e_vsi *vsi, return; } - /* avoid dynamic calculation if in countdown mode OR if - * all dynamic is disabled - */ - rxval = txval = i40e_buildreg_itr(I40E_ITR_NONE, 0); - - rx_itr_setting = get_rx_itr(vsi, idx); - tx_itr_setting = get_tx_itr(vsi, idx); - - if (q_vector->itr_countdown > 0 || - (!ITR_IS_DYNAMIC(rx_itr_setting) && - !ITR_IS_DYNAMIC(tx_itr_setting))) { - goto enable_int; - } - - if (ITR_IS_DYNAMIC(rx_itr_setting)) { - rx = i40e_set_new_dynamic_itr(&q_vector->rx); - rxval = i40e_buildreg_itr(I40E_RX_ITR, q_vector->rx.itr); - } - - if (ITR_IS_DYNAMIC(tx_itr_setting)) { - tx = i40e_set_new_dynamic_itr(&q_vector->tx); - txval = i40e_buildreg_itr(I40E_TX_ITR, q_vector->tx.itr); - } + /* These will do nothing if dynamic updates are not enabled */ + i40e_update_itr(q_vector, &q_vector->tx); + i40e_update_itr(q_vector, &q_vector->rx); - if (rx || tx) { - /* get the higher of the two ITR adjustments and - * use the same value for both ITR registers - * when in adaptive mode (Rx and/or Tx) - */ - u16 itr = max(q_vector->tx.itr, q_vector->rx.itr); - - q_vector->tx.itr = q_vector->rx.itr = itr; - txval = i40e_buildreg_itr(I40E_TX_ITR, itr); - tx = true; - rxval = i40e_buildreg_itr(I40E_RX_ITR, itr); - rx = true; - } - - /* only need to enable the interrupt once, but need - * to possibly update both ITR values + /* This block of logic allows us to get away with only updating + * one ITR value with each interrupt. The idea is to perform a + * pseudo-lazy update with the following criteria. + * + * 1. Rx is given higher priority than Tx if both are in same state + * 2. If we must reduce an ITR that is given highest priority. + * 3. We then give priority to increasing ITR based on amount. */ - if (rx) { - /* set the INTENA_MSK_MASK so that this first write - * won't actually enable the interrupt, instead just - * updating the ITR (it's bit 31 PF and VF) + if (q_vector->rx.target_itr < q_vector->rx.current_itr) { + /* Rx ITR needs to be reduced, this is highest priority */ + intval = i40e_buildreg_itr(I40E_RX_ITR, + q_vector->rx.target_itr); + q_vector->rx.current_itr = q_vector->rx.target_itr; + q_vector->itr_countdown = ITR_COUNTDOWN_START; + } else if ((q_vector->tx.target_itr < q_vector->tx.current_itr) || + ((q_vector->rx.target_itr - q_vector->rx.current_itr) < + (q_vector->tx.target_itr - q_vector->tx.current_itr))) { + /* Tx ITR needs to be reduced, this is second priority + * Tx ITR needs to be increased more than Rx, fourth priority */ - rxval |= BIT(31); - /* don't check _DOWN because interrupt isn't being enabled */ - wr32(hw, INTREG(q_vector->reg_idx), rxval); + intval = i40e_buildreg_itr(I40E_TX_ITR, + q_vector->tx.target_itr); + q_vector->tx.current_itr = q_vector->tx.target_itr; + q_vector->itr_countdown = ITR_COUNTDOWN_START; + } else if (q_vector->rx.current_itr != q_vector->rx.target_itr) { + /* Rx ITR needs to be increased, third priority */ + intval = i40e_buildreg_itr(I40E_RX_ITR, + q_vector->rx.target_itr); + q_vector->rx.current_itr = q_vector->rx.target_itr; + q_vector->itr_countdown = ITR_COUNTDOWN_START; + } else { + /* No ITR update, lowest priority */ + intval = i40e_buildreg_itr(I40E_ITR_NONE, 0); + if (q_vector->itr_countdown) + q_vector->itr_countdown--; } -enable_int: if (!test_bit(__I40E_VSI_DOWN, vsi->state)) - wr32(hw, INTREG(q_vector->reg_idx), txval); - - if (q_vector->itr_countdown) - q_vector->itr_countdown--; - else - q_vector->itr_countdown = ITR_COUNTDOWN_START; + wr32(hw, INTREG(q_vector->reg_idx), intval); } /** diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.h b/drivers/net/ethernet/intel/i40e/i40e_txrx.h index 701b708628b0..3c80ea784389 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.h +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.h @@ -30,32 +30,37 @@ #include <net/xdp.h> /* Interrupt Throttling and Rate Limiting Goodies */ - -#define I40E_MAX_ITR 0x0FF0 /* reg uses 2 usec resolution */ -#define I40E_MIN_ITR 0x0001 /* reg uses 2 usec resolution */ -#define I40E_ITR_100K 0x0005 -#define I40E_ITR_50K 0x000A -#define I40E_ITR_20K 0x0019 -#define I40E_ITR_18K 0x001B -#define I40E_ITR_8K 0x003E -#define I40E_ITR_4K 0x007A -#define I40E_MAX_INTRL 0x3B /* reg uses 4 usec resolution */ -#define I40E_ITR_RX_DEF (ITR_REG_TO_USEC(I40E_ITR_20K) | \ - I40E_ITR_DYNAMIC) -#define I40E_ITR_TX_DEF (ITR_REG_TO_USEC(I40E_ITR_20K) | \ - I40E_ITR_DYNAMIC) -#define I40E_ITR_DYNAMIC 0x8000 /* use top bit as a flag */ -#define I40E_MIN_INT_RATE 250 /* ~= 1000000 / (I40E_MAX_ITR * 2) */ -#define I40E_MAX_INT_RATE 500000 /* == 1000000 / (I40E_MIN_ITR * 2) */ #define I40E_DEFAULT_IRQ_WORK 256 -#define ITR_TO_REG(setting) ((setting & ~I40E_ITR_DYNAMIC) >> 1) -#define ITR_IS_DYNAMIC(setting) (!!(setting & I40E_ITR_DYNAMIC)) -#define ITR_REG_TO_USEC(itr_reg) (itr_reg << 1) + +/* The datasheet for the X710 and XL710 indicate that the maximum value for + * the ITR is 8160usec which is then called out as 0xFF0 with a 2usec + * resolution. 8160 is 0x1FE0 when written out in hex. So instead of storing + * the register value which is divided by 2 lets use the actual values and + * avoid an excessive amount of translation. + */ +#define I40E_ITR_DYNAMIC 0x8000 /* use top bit as a flag */ +#define I40E_ITR_MASK 0x1FFE /* mask for ITR register value */ +#define I40E_MIN_ITR 2 /* reg uses 2 usec resolution */ +#define I40E_ITR_100K 10 /* all values below must be even */ +#define I40E_ITR_50K 20 +#define I40E_ITR_20K 50 +#define I40E_ITR_18K 60 +#define I40E_ITR_8K 122 +#define I40E_MAX_ITR 8160 /* maximum value as per datasheet */ +#define ITR_TO_REG(setting) ((setting) & ~I40E_ITR_DYNAMIC) +#define ITR_REG_ALIGN(setting) __ALIGN_MASK(setting, ~I40E_ITR_MASK) +#define ITR_IS_DYNAMIC(setting) (!!((setting) & I40E_ITR_DYNAMIC)) + +#define I40E_ITR_RX_DEF (I40E_ITR_20K | I40E_ITR_DYNAMIC) +#define I40E_ITR_TX_DEF (I40E_ITR_20K | I40E_ITR_DYNAMIC) + /* 0x40 is the enable bit for interrupt rate limiting, and must be set if * the value of the rate limit is non-zero */ #define INTRL_ENA BIT(6) +#define I40E_MAX_INTRL 0x3B /* reg uses 4 usec resolution */ #define INTRL_REG_TO_USEC(intrl) ((intrl & ~INTRL_ENA) << 2) + /** * i40e_intrl_usec_to_reg - convert interrupt rate limit to register * @intrl: interrupt rate limit to convert @@ -382,8 +387,7 @@ struct i40e_ring { * these values always store the USER setting, and must be converted * before programming to a register. */ - u16 rx_itr_setting; - u16 tx_itr_setting; + u16 itr_setting; u16 count; /* Number of descriptors */ u16 reg_idx; /* HW register index of the ring */ @@ -459,21 +463,21 @@ static inline void set_ring_xdp(struct i40e_ring *ring) ring->flags |= I40E_TXR_FLAGS_XDP; } -enum i40e_latency_range { - I40E_LOWEST_LATENCY = 0, - I40E_LOW_LATENCY = 1, - I40E_BULK_LATENCY = 2, -}; +#define I40E_ITR_ADAPTIVE_MIN_INC 0x0002 +#define I40E_ITR_ADAPTIVE_MIN_USECS 0x0002 +#define I40E_ITR_ADAPTIVE_MAX_USECS 0x007e +#define I40E_ITR_ADAPTIVE_LATENCY 0x8000 +#define I40E_ITR_ADAPTIVE_BULK 0x0000 +#define ITR_IS_BULK(x) (!((x) & I40E_ITR_ADAPTIVE_LATENCY)) struct i40e_ring_container { - /* array of pointers to rings */ - struct i40e_ring *ring; + struct i40e_ring *ring; /* pointer to linked list of ring(s) */ + unsigned long next_update; /* jiffies value of next update */ unsigned int total_bytes; /* total bytes processed this int */ unsigned int total_packets; /* total packets processed this int */ - unsigned long last_itr_update; /* jiffies of last ITR update */ u16 count; - enum i40e_latency_range latency_range; - u16 itr; + u16 target_itr; /* target ITR setting for ring(s) */ + u16 current_itr; /* current ITR setting for ring(s) */ }; /* iterator for handling rings in ring container */ @@ -501,7 +505,7 @@ void i40e_free_tx_resources(struct i40e_ring *tx_ring); void i40e_free_rx_resources(struct i40e_ring *rx_ring); int i40e_napi_poll(struct napi_struct *napi, int budget); void i40e_force_wb(struct i40e_vsi *vsi, struct i40e_q_vector *q_vector); -u32 i40e_get_tx_pending(struct i40e_ring *ring); +u32 i40e_get_tx_pending(struct i40e_ring *ring, bool in_sw); void i40e_detect_recover_hung(struct i40e_vsi *vsi); int __i40e_maybe_stop_tx(struct i40e_ring *tx_ring, int size); bool __i40e_chk_linearize(struct sk_buff *skb); diff --git a/drivers/net/ethernet/intel/i40e/i40e_type.h b/drivers/net/ethernet/intel/i40e/i40e_type.h index cd294e6a8587..b0eed8c0b2f2 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_type.h +++ b/drivers/net/ethernet/intel/i40e/i40e_type.h @@ -39,7 +39,7 @@ #define I40E_MASK(mask, shift) ((u32)(mask) << (shift)) #define I40E_MAX_VSI_QP 16 -#define I40E_MAX_VF_VSI 3 +#define I40E_MAX_VF_VSI 4 #define I40E_MAX_CHAINED_RX_BUFFERS 5 #define I40E_MAX_PF_UDP_OFFLOAD_PORTS 16 diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index e9309fb9084b..e23975c67417 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -258,6 +258,38 @@ static u16 i40e_vc_get_pf_queue_id(struct i40e_vf *vf, u16 vsi_id, } /** + * i40e_get_real_pf_qid + * @vf: pointer to the VF info + * @vsi_id: vsi id + * @queue_id: queue number + * + * wrapper function to get pf_queue_id handling ADq code as well + **/ +static u16 i40e_get_real_pf_qid(struct i40e_vf *vf, u16 vsi_id, u16 queue_id) +{ + int i; + + if (vf->adq_enabled) { + /* Although VF considers all the queues(can be 1 to 16) as its + * own but they may actually belong to different VSIs(up to 4). + * We need to find which queues belongs to which VSI. + */ + for (i = 0; i < vf->num_tc; i++) { + if (queue_id < vf->ch[i].num_qps) { + vsi_id = vf->ch[i].vsi_id; + break; + } + /* find right queue id which is relative to a + * given VSI. + */ + queue_id -= vf->ch[i].num_qps; + } + } + + return i40e_vc_get_pf_queue_id(vf, vsi_id, queue_id); +} + +/** * i40e_config_irq_link_list * @vf: pointer to the VF info * @vsi_id: id of VSI as given by the FW @@ -310,7 +342,7 @@ static void i40e_config_irq_link_list(struct i40e_vf *vf, u16 vsi_id, vsi_queue_id = next_q / I40E_VIRTCHNL_SUPPORTED_QTYPES; qtype = next_q % I40E_VIRTCHNL_SUPPORTED_QTYPES; - pf_queue_id = i40e_vc_get_pf_queue_id(vf, vsi_id, vsi_queue_id); + pf_queue_id = i40e_get_real_pf_qid(vf, vsi_id, vsi_queue_id); reg = ((qtype << I40E_VPINT_LNKLSTN_FIRSTQ_TYPE_SHIFT) | pf_queue_id); wr32(hw, reg_idx, reg); @@ -333,8 +365,9 @@ static void i40e_config_irq_link_list(struct i40e_vf *vf, u16 vsi_id, if (next_q < size) { vsi_queue_id = next_q / I40E_VIRTCHNL_SUPPORTED_QTYPES; qtype = next_q % I40E_VIRTCHNL_SUPPORTED_QTYPES; - pf_queue_id = i40e_vc_get_pf_queue_id(vf, vsi_id, - vsi_queue_id); + pf_queue_id = i40e_get_real_pf_qid(vf, + vsi_id, + vsi_queue_id); } else { pf_queue_id = I40E_QUEUE_END_OF_LIST; qtype = 0; @@ -669,18 +702,20 @@ error_param: /** * i40e_alloc_vsi_res * @vf: pointer to the VF info - * @type: type of VSI to allocate + * @idx: VSI index, applies only for ADq mode, zero otherwise * * alloc VF vsi context & resources **/ -static int i40e_alloc_vsi_res(struct i40e_vf *vf, enum i40e_vsi_type type) +static int i40e_alloc_vsi_res(struct i40e_vf *vf, u8 idx) { struct i40e_mac_filter *f = NULL; struct i40e_pf *pf = vf->pf; struct i40e_vsi *vsi; + u64 max_tx_rate = 0; int ret = 0; - vsi = i40e_vsi_setup(pf, type, pf->vsi[pf->lan_vsi]->seid, vf->vf_id); + vsi = i40e_vsi_setup(pf, I40E_VSI_SRIOV, pf->vsi[pf->lan_vsi]->seid, + vf->vf_id); if (!vsi) { dev_err(&pf->pdev->dev, @@ -689,7 +724,8 @@ static int i40e_alloc_vsi_res(struct i40e_vf *vf, enum i40e_vsi_type type) ret = -ENOENT; goto error_alloc_vsi_res; } - if (type == I40E_VSI_SRIOV) { + + if (!idx) { u64 hena = i40e_pf_get_default_rss_hena(pf); u8 broadcast[ETH_ALEN]; @@ -721,17 +757,29 @@ static int i40e_alloc_vsi_res(struct i40e_vf *vf, enum i40e_vsi_type type) spin_unlock_bh(&vsi->mac_filter_hash_lock); wr32(&pf->hw, I40E_VFQF_HENA1(0, vf->vf_id), (u32)hena); wr32(&pf->hw, I40E_VFQF_HENA1(1, vf->vf_id), (u32)(hena >> 32)); + /* program mac filter only for VF VSI */ + ret = i40e_sync_vsi_filters(vsi); + if (ret) + dev_err(&pf->pdev->dev, "Unable to program ucast filters\n"); } - /* program mac filter */ - ret = i40e_sync_vsi_filters(vsi); - if (ret) - dev_err(&pf->pdev->dev, "Unable to program ucast filters\n"); + /* storing VSI index and id for ADq and don't apply the mac filter */ + if (vf->adq_enabled) { + vf->ch[idx].vsi_idx = vsi->idx; + vf->ch[idx].vsi_id = vsi->id; + } /* Set VF bandwidth if specified */ if (vf->tx_rate) { + max_tx_rate = vf->tx_rate; + } else if (vf->ch[idx].max_tx_rate) { + max_tx_rate = vf->ch[idx].max_tx_rate; + } + + if (max_tx_rate) { + max_tx_rate = div_u64(max_tx_rate, I40E_BW_CREDIT_DIVISOR); ret = i40e_aq_config_vsi_bw_limit(&pf->hw, vsi->seid, - vf->tx_rate / 50, 0, NULL); + max_tx_rate, 0, NULL); if (ret) dev_err(&pf->pdev->dev, "Unable to set tx rate, VF %d, error code %d.\n", vf->vf_id, ret); @@ -742,6 +790,92 @@ error_alloc_vsi_res: } /** + * i40e_map_pf_queues_to_vsi + * @vf: pointer to the VF info + * + * PF maps LQPs to a VF by programming VSILAN_QTABLE & VPLAN_QTABLE. This + * function takes care of first part VSILAN_QTABLE, mapping pf queues to VSI. + **/ +static void i40e_map_pf_queues_to_vsi(struct i40e_vf *vf) +{ + struct i40e_pf *pf = vf->pf; + struct i40e_hw *hw = &pf->hw; + u32 reg, num_tc = 1; /* VF has at least one traffic class */ + u16 vsi_id, qps; + int i, j; + + if (vf->adq_enabled) + num_tc = vf->num_tc; + + for (i = 0; i < num_tc; i++) { + if (vf->adq_enabled) { + qps = vf->ch[i].num_qps; + vsi_id = vf->ch[i].vsi_id; + } else { + qps = pf->vsi[vf->lan_vsi_idx]->alloc_queue_pairs; + vsi_id = vf->lan_vsi_id; + } + + for (j = 0; j < 7; j++) { + if (j * 2 >= qps) { + /* end of list */ + reg = 0x07FF07FF; + } else { + u16 qid = i40e_vc_get_pf_queue_id(vf, + vsi_id, + j * 2); + reg = qid; + qid = i40e_vc_get_pf_queue_id(vf, vsi_id, + (j * 2) + 1); + reg |= qid << 16; + } + i40e_write_rx_ctl(hw, + I40E_VSILAN_QTABLE(j, vsi_id), + reg); + } + } +} + +/** + * i40e_map_pf_to_vf_queues + * @vf: pointer to the VF info + * + * PF maps LQPs to a VF by programming VSILAN_QTABLE & VPLAN_QTABLE. This + * function takes care of the second part VPLAN_QTABLE & completes VF mappings. + **/ +static void i40e_map_pf_to_vf_queues(struct i40e_vf *vf) +{ + struct i40e_pf *pf = vf->pf; + struct i40e_hw *hw = &pf->hw; + u32 reg, total_qps = 0; + u32 qps, num_tc = 1; /* VF has at least one traffic class */ + u16 vsi_id, qid; + int i, j; + + if (vf->adq_enabled) + num_tc = vf->num_tc; + + for (i = 0; i < num_tc; i++) { + if (vf->adq_enabled) { + qps = vf->ch[i].num_qps; + vsi_id = vf->ch[i].vsi_id; + } else { + qps = pf->vsi[vf->lan_vsi_idx]->alloc_queue_pairs; + vsi_id = vf->lan_vsi_id; + } + + for (j = 0; j < qps; j++) { + qid = i40e_vc_get_pf_queue_id(vf, vsi_id, j); + + reg = (qid & I40E_VPLAN_QTABLE_QINDEX_MASK); + wr32(hw, I40E_VPLAN_QTABLE(total_qps, vf->vf_id), + reg); + total_qps++; + } + } +} + +/** * i40e_enable_vf_mappings * @vf: pointer to the VF info * @@ -751,8 +885,7 @@ static void i40e_enable_vf_mappings(struct i40e_vf *vf) { struct i40e_pf *pf = vf->pf; struct i40e_hw *hw = &pf->hw; - u32 reg, total_queue_pairs = 0; - int j; + u32 reg; /* Tell the hardware we're using noncontiguous mapping. HW requires * that VF queues be mapped using this method, even when they are @@ -765,30 +898,8 @@ static void i40e_enable_vf_mappings(struct i40e_vf *vf) reg = I40E_VPLAN_MAPENA_TXRX_ENA_MASK; wr32(hw, I40E_VPLAN_MAPENA(vf->vf_id), reg); - /* map PF queues to VF queues */ - for (j = 0; j < pf->vsi[vf->lan_vsi_idx]->alloc_queue_pairs; j++) { - u16 qid = i40e_vc_get_pf_queue_id(vf, vf->lan_vsi_id, j); - - reg = (qid & I40E_VPLAN_QTABLE_QINDEX_MASK); - wr32(hw, I40E_VPLAN_QTABLE(total_queue_pairs, vf->vf_id), reg); - total_queue_pairs++; - } - - /* map PF queues to VSI */ - for (j = 0; j < 7; j++) { - if (j * 2 >= pf->vsi[vf->lan_vsi_idx]->alloc_queue_pairs) { - reg = 0x07FF07FF; /* unused */ - } else { - u16 qid = i40e_vc_get_pf_queue_id(vf, vf->lan_vsi_id, - j * 2); - reg = qid; - qid = i40e_vc_get_pf_queue_id(vf, vf->lan_vsi_id, - (j * 2) + 1); - reg |= qid << 16; - } - i40e_write_rx_ctl(hw, I40E_VSILAN_QTABLE(j, vf->lan_vsi_id), - reg); - } + i40e_map_pf_to_vf_queues(vf); + i40e_map_pf_queues_to_vsi(vf); i40e_flush(hw); } @@ -824,7 +935,7 @@ static void i40e_free_vf_res(struct i40e_vf *vf) struct i40e_pf *pf = vf->pf; struct i40e_hw *hw = &pf->hw; u32 reg_idx, reg; - int i, msix_vf; + int i, j, msix_vf; /* Start by disabling VF's configuration API to prevent the OS from * accessing the VF's VSI after it's freed / invalidated. @@ -846,6 +957,20 @@ static void i40e_free_vf_res(struct i40e_vf *vf) vf->lan_vsi_id = 0; vf->num_mac = 0; } + + /* do the accounting and remove additional ADq VSI's */ + if (vf->adq_enabled && vf->ch[0].vsi_idx) { + for (j = 0; j < vf->num_tc; j++) { + /* At this point VSI0 is already released so don't + * release it again and only clear their values in + * structure variables + */ + if (j) + i40e_vsi_release(pf->vsi[vf->ch[j].vsi_idx]); + vf->ch[j].vsi_idx = 0; + vf->ch[j].vsi_id = 0; + } + } msix_vf = pf->hw.func_caps.num_msix_vectors_vf; /* disable interrupts so the VF starts in a known state */ @@ -891,7 +1016,7 @@ static int i40e_alloc_vf_res(struct i40e_vf *vf) { struct i40e_pf *pf = vf->pf; int total_queue_pairs = 0; - int ret; + int ret, idx; if (vf->num_req_queues && vf->num_req_queues <= pf->queues_left + I40E_DEFAULT_QUEUES_PER_VF) @@ -900,11 +1025,30 @@ static int i40e_alloc_vf_res(struct i40e_vf *vf) pf->num_vf_qps = I40E_DEFAULT_QUEUES_PER_VF; /* allocate hw vsi context & associated resources */ - ret = i40e_alloc_vsi_res(vf, I40E_VSI_SRIOV); + ret = i40e_alloc_vsi_res(vf, 0); if (ret) goto error_alloc; total_queue_pairs += pf->vsi[vf->lan_vsi_idx]->alloc_queue_pairs; + /* allocate additional VSIs based on tc information for ADq */ + if (vf->adq_enabled) { + if (pf->queues_left >= + (I40E_MAX_VF_QUEUES - I40E_DEFAULT_QUEUES_PER_VF)) { + /* TC 0 always belongs to VF VSI */ + for (idx = 1; idx < vf->num_tc; idx++) { + ret = i40e_alloc_vsi_res(vf, idx); + if (ret) + goto error_alloc; + } + /* send correct number of queues */ + total_queue_pairs = I40E_MAX_VF_QUEUES; + } else { + dev_info(&pf->pdev->dev, "VF %d: Not enough queues to allocate, disabling ADq\n", + vf->vf_id); + vf->adq_enabled = false; + } + } + /* We account for each VF to get a default number of queue pairs. If * the VF has now requested more, we need to account for that to make * certain we never request more queues than we actually have left in @@ -1537,6 +1681,27 @@ static int i40e_vc_get_version_msg(struct i40e_vf *vf, u8 *msg) } /** + * i40e_del_qch - delete all the additional VSIs created as a part of ADq + * @vf: pointer to VF structure + **/ +static void i40e_del_qch(struct i40e_vf *vf) +{ + struct i40e_pf *pf = vf->pf; + int i; + + /* first element in the array belongs to primary VF VSI and we shouldn't + * delete it. We should however delete the rest of the VSIs created + */ + for (i = 1; i < vf->num_tc; i++) { + if (vf->ch[i].vsi_idx) { + i40e_vsi_release(pf->vsi[vf->ch[i].vsi_idx]); + vf->ch[i].vsi_idx = 0; + vf->ch[i].vsi_id = 0; + } + } +} + +/** * i40e_vc_get_vf_resources_msg * @vf: pointer to the VF info * @msg: pointer to the msg buffer @@ -1631,6 +1796,9 @@ static int i40e_vc_get_vf_resources_msg(struct i40e_vf *vf, u8 *msg) if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_REQ_QUEUES) vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_REQ_QUEUES; + if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_ADQ) + vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_ADQ; + vfres->num_vsis = num_vsis; vfres->num_queue_pairs = vf->num_queue_pairs; vfres->max_vectors = pf->hw.func_caps.num_msix_vectors_vf; @@ -1855,27 +2023,37 @@ static int i40e_vc_config_queues_msg(struct i40e_vf *vf, u8 *msg, u16 msglen) (struct virtchnl_vsi_queue_config_info *)msg; struct virtchnl_queue_pair_info *qpi; struct i40e_pf *pf = vf->pf; - u16 vsi_id, vsi_queue_id; + u16 vsi_id, vsi_queue_id = 0; i40e_status aq_ret = 0; - int i; + int i, j = 0, idx = 0; + + vsi_id = qci->vsi_id; if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) { aq_ret = I40E_ERR_PARAM; goto error_param; } - vsi_id = qci->vsi_id; if (!i40e_vc_isvalid_vsi_id(vf, vsi_id)) { aq_ret = I40E_ERR_PARAM; goto error_param; } + for (i = 0; i < qci->num_queue_pairs; i++) { qpi = &qci->qpair[i]; - vsi_queue_id = qpi->txq.queue_id; - if ((qpi->txq.vsi_id != vsi_id) || - (qpi->rxq.vsi_id != vsi_id) || - (qpi->rxq.queue_id != vsi_queue_id) || - !i40e_vc_isvalid_queue_id(vf, vsi_id, vsi_queue_id)) { + + if (!vf->adq_enabled) { + vsi_queue_id = qpi->txq.queue_id; + + if (qpi->txq.vsi_id != qci->vsi_id || + qpi->rxq.vsi_id != qci->vsi_id || + qpi->rxq.queue_id != vsi_queue_id) { + aq_ret = I40E_ERR_PARAM; + goto error_param; + } + } + + if (!i40e_vc_isvalid_queue_id(vf, vsi_id, vsi_queue_id)) { aq_ret = I40E_ERR_PARAM; goto error_param; } @@ -1887,9 +2065,33 @@ static int i40e_vc_config_queues_msg(struct i40e_vf *vf, u8 *msg, u16 msglen) aq_ret = I40E_ERR_PARAM; goto error_param; } + + /* For ADq there can be up to 4 VSIs with max 4 queues each. + * VF does not know about these additional VSIs and all + * it cares is about its own queues. PF configures these queues + * to its appropriate VSIs based on TC mapping + **/ + if (vf->adq_enabled) { + if (j == (vf->ch[idx].num_qps - 1)) { + idx++; + j = 0; /* resetting the queue count */ + vsi_queue_id = 0; + } else { + j++; + vsi_queue_id++; + } + vsi_id = vf->ch[idx].vsi_id; + } } /* set vsi num_queue_pairs in use to num configured by VF */ - pf->vsi[vf->lan_vsi_idx]->num_queue_pairs = qci->num_queue_pairs; + if (!vf->adq_enabled) { + pf->vsi[vf->lan_vsi_idx]->num_queue_pairs = + qci->num_queue_pairs; + } else { + for (i = 0; i < vf->num_tc; i++) + pf->vsi[vf->ch[i].vsi_idx]->num_queue_pairs = + vf->ch[i].num_qps; + } error_param: /* send the response to the VF */ @@ -1898,6 +2100,33 @@ error_param: } /** + * i40e_validate_queue_map + * @vsi_id: vsi id + * @queuemap: Tx or Rx queue map + * + * check if Tx or Rx queue map is valid + **/ +static int i40e_validate_queue_map(struct i40e_vf *vf, u16 vsi_id, + unsigned long queuemap) +{ + u16 vsi_queue_id, queue_id; + + for_each_set_bit(vsi_queue_id, &queuemap, I40E_MAX_VSI_QP) { + if (vf->adq_enabled) { + vsi_id = vf->ch[vsi_queue_id / I40E_MAX_VF_VSI].vsi_id; + queue_id = (vsi_queue_id % I40E_DEFAULT_QUEUES_PER_VF); + } else { + queue_id = vsi_queue_id; + } + + if (!i40e_vc_isvalid_queue_id(vf, vsi_id, queue_id)) + return -EINVAL; + } + + return 0; +} + +/** * i40e_vc_config_irq_map_msg * @vf: pointer to the VF info * @msg: pointer to the msg buffer @@ -1911,9 +2140,8 @@ static int i40e_vc_config_irq_map_msg(struct i40e_vf *vf, u8 *msg, u16 msglen) struct virtchnl_irq_map_info *irqmap_info = (struct virtchnl_irq_map_info *)msg; struct virtchnl_vector_map *map; - u16 vsi_id, vsi_queue_id, vector_id; + u16 vsi_id, vector_id; i40e_status aq_ret = 0; - unsigned long tempmap; int i; if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) { @@ -1923,7 +2151,6 @@ static int i40e_vc_config_irq_map_msg(struct i40e_vf *vf, u8 *msg, u16 msglen) for (i = 0; i < irqmap_info->num_vectors; i++) { map = &irqmap_info->vecmap[i]; - vector_id = map->vector_id; vsi_id = map->vsi_id; /* validate msg params */ @@ -1933,23 +2160,14 @@ static int i40e_vc_config_irq_map_msg(struct i40e_vf *vf, u8 *msg, u16 msglen) goto error_param; } - /* lookout for the invalid queue index */ - tempmap = map->rxq_map; - for_each_set_bit(vsi_queue_id, &tempmap, I40E_MAX_VSI_QP) { - if (!i40e_vc_isvalid_queue_id(vf, vsi_id, - vsi_queue_id)) { - aq_ret = I40E_ERR_PARAM; - goto error_param; - } + if (i40e_validate_queue_map(vf, vsi_id, map->rxq_map)) { + aq_ret = I40E_ERR_PARAM; + goto error_param; } - tempmap = map->txq_map; - for_each_set_bit(vsi_queue_id, &tempmap, I40E_MAX_VSI_QP) { - if (!i40e_vc_isvalid_queue_id(vf, vsi_id, - vsi_queue_id)) { - aq_ret = I40E_ERR_PARAM; - goto error_param; - } + if (i40e_validate_queue_map(vf, vsi_id, map->txq_map)) { + aq_ret = I40E_ERR_PARAM; + goto error_param; } i40e_config_irq_link_list(vf, vsi_id, map); @@ -1975,6 +2193,7 @@ static int i40e_vc_enable_queues_msg(struct i40e_vf *vf, u8 *msg, u16 msglen) struct i40e_pf *pf = vf->pf; u16 vsi_id = vqs->vsi_id; i40e_status aq_ret = 0; + int i; if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) { aq_ret = I40E_ERR_PARAM; @@ -1993,6 +2212,16 @@ static int i40e_vc_enable_queues_msg(struct i40e_vf *vf, u8 *msg, u16 msglen) if (i40e_vsi_start_rings(pf->vsi[vf->lan_vsi_idx])) aq_ret = I40E_ERR_TIMEOUT; + + /* need to start the rings for additional ADq VSI's as well */ + if (vf->adq_enabled) { + /* zero belongs to LAN VSI */ + for (i = 1; i < vf->num_tc; i++) { + if (i40e_vsi_start_rings(pf->vsi[vf->ch[i].vsi_idx])) + aq_ret = I40E_ERR_TIMEOUT; + } + } + error_param: /* send the response to the VF */ return i40e_vc_send_resp_to_vf(vf, VIRTCHNL_OP_ENABLE_QUEUES, @@ -2688,6 +2917,618 @@ err: } /** + * i40e_validate_cloud_filter + * @mask: mask for TC filter + * @data: data for TC filter + * + * This function validates cloud filter programmed as TC filter for ADq + **/ +static int i40e_validate_cloud_filter(struct i40e_vf *vf, + struct virtchnl_filter *tc_filter) +{ + struct virtchnl_l4_spec mask = tc_filter->mask.tcp_spec; + struct virtchnl_l4_spec data = tc_filter->data.tcp_spec; + struct i40e_pf *pf = vf->pf; + struct i40e_vsi *vsi = NULL; + struct i40e_mac_filter *f; + struct hlist_node *h; + bool found = false; + int bkt; + + if (!tc_filter->action) { + dev_info(&pf->pdev->dev, + "VF %d: Currently ADq doesn't support Drop Action\n", + vf->vf_id); + goto err; + } + + /* action_meta is TC number here to which the filter is applied */ + if (!tc_filter->action_meta || + tc_filter->action_meta > I40E_MAX_VF_VSI) { + dev_info(&pf->pdev->dev, "VF %d: Invalid TC number %u\n", + vf->vf_id, tc_filter->action_meta); + goto err; + } + + /* Check filter if it's programmed for advanced mode or basic mode. + * There are two ADq modes (for VF only), + * 1. Basic mode: intended to allow as many filter options as possible + * to be added to a VF in Non-trusted mode. Main goal is + * to add filters to its own MAC and VLAN id. + * 2. Advanced mode: is for allowing filters to be applied other than + * its own MAC or VLAN. This mode requires the VF to be + * Trusted. + */ + if (mask.dst_mac[0] && !mask.dst_ip[0]) { + vsi = pf->vsi[vf->lan_vsi_idx]; + f = i40e_find_mac(vsi, data.dst_mac); + + if (!f) { + dev_info(&pf->pdev->dev, + "Destination MAC %pM doesn't belong to VF %d\n", + data.dst_mac, vf->vf_id); + goto err; + } + + if (mask.vlan_id) { + hash_for_each_safe(vsi->mac_filter_hash, bkt, h, f, + hlist) { + if (f->vlan == ntohs(data.vlan_id)) { + found = true; + break; + } + } + if (!found) { + dev_info(&pf->pdev->dev, + "VF %d doesn't have any VLAN id %u\n", + vf->vf_id, ntohs(data.vlan_id)); + goto err; + } + } + } else { + /* Check if VF is trusted */ + if (!test_bit(I40E_VIRTCHNL_VF_CAP_PRIVILEGE, &vf->vf_caps)) { + dev_err(&pf->pdev->dev, + "VF %d not trusted, make VF trusted to add advanced mode ADq cloud filters\n", + vf->vf_id); + return I40E_ERR_CONFIG; + } + } + + if (mask.dst_mac[0] & data.dst_mac[0]) { + if (is_broadcast_ether_addr(data.dst_mac) || + is_zero_ether_addr(data.dst_mac)) { + dev_info(&pf->pdev->dev, "VF %d: Invalid Dest MAC addr %pM\n", + vf->vf_id, data.dst_mac); + goto err; + } + } + + if (mask.src_mac[0] & data.src_mac[0]) { + if (is_broadcast_ether_addr(data.src_mac) || + is_zero_ether_addr(data.src_mac)) { + dev_info(&pf->pdev->dev, "VF %d: Invalid Source MAC addr %pM\n", + vf->vf_id, data.src_mac); + goto err; + } + } + + if (mask.dst_port & data.dst_port) { + if (!data.dst_port || be16_to_cpu(data.dst_port) > 0xFFFF) { + dev_info(&pf->pdev->dev, "VF %d: Invalid Dest port\n", + vf->vf_id); + goto err; + } + } + + if (mask.src_port & data.src_port) { + if (!data.src_port || be16_to_cpu(data.src_port) > 0xFFFF) { + dev_info(&pf->pdev->dev, "VF %d: Invalid Source port\n", + vf->vf_id); + goto err; + } + } + + if (tc_filter->flow_type != VIRTCHNL_TCP_V6_FLOW && + tc_filter->flow_type != VIRTCHNL_TCP_V4_FLOW) { + dev_info(&pf->pdev->dev, "VF %d: Invalid Flow type\n", + vf->vf_id); + goto err; + } + + if (mask.vlan_id & data.vlan_id) { + if (ntohs(data.vlan_id) > I40E_MAX_VLANID) { + dev_info(&pf->pdev->dev, "VF %d: invalid VLAN ID\n", + vf->vf_id); + goto err; + } + } + + return I40E_SUCCESS; +err: + return I40E_ERR_CONFIG; +} + +/** + * i40e_find_vsi_from_seid - searches for the vsi with the given seid + * @vf: pointer to the VF info + * @seid - seid of the vsi it is searching for + **/ +static struct i40e_vsi *i40e_find_vsi_from_seid(struct i40e_vf *vf, u16 seid) +{ + struct i40e_pf *pf = vf->pf; + struct i40e_vsi *vsi = NULL; + int i; + + for (i = 0; i < vf->num_tc ; i++) { + vsi = i40e_find_vsi_from_id(pf, vf->ch[i].vsi_id); + if (vsi && vsi->seid == seid) + return vsi; + } + return NULL; +} + +/** + * i40e_del_all_cloud_filters + * @vf: pointer to the VF info + * + * This function deletes all cloud filters + **/ +static void i40e_del_all_cloud_filters(struct i40e_vf *vf) +{ + struct i40e_cloud_filter *cfilter = NULL; + struct i40e_pf *pf = vf->pf; + struct i40e_vsi *vsi = NULL; + struct hlist_node *node; + int ret; + + hlist_for_each_entry_safe(cfilter, node, + &vf->cloud_filter_list, cloud_node) { + vsi = i40e_find_vsi_from_seid(vf, cfilter->seid); + + if (!vsi) { + dev_err(&pf->pdev->dev, "VF %d: no VSI found for matching %u seid, can't delete cloud filter\n", + vf->vf_id, cfilter->seid); + continue; + } + + if (cfilter->dst_port) + ret = i40e_add_del_cloud_filter_big_buf(vsi, cfilter, + false); + else + ret = i40e_add_del_cloud_filter(vsi, cfilter, false); + if (ret) + dev_err(&pf->pdev->dev, + "VF %d: Failed to delete cloud filter, err %s aq_err %s\n", + vf->vf_id, i40e_stat_str(&pf->hw, ret), + i40e_aq_str(&pf->hw, + pf->hw.aq.asq_last_status)); + + hlist_del(&cfilter->cloud_node); + kfree(cfilter); + vf->num_cloud_filters--; + } +} + +/** + * i40e_vc_del_cloud_filter + * @vf: pointer to the VF info + * @msg: pointer to the msg buffer + * + * This function deletes a cloud filter programmed as TC filter for ADq + **/ +static int i40e_vc_del_cloud_filter(struct i40e_vf *vf, u8 *msg) +{ + struct virtchnl_filter *vcf = (struct virtchnl_filter *)msg; + struct virtchnl_l4_spec mask = vcf->mask.tcp_spec; + struct virtchnl_l4_spec tcf = vcf->data.tcp_spec; + struct i40e_cloud_filter cfilter, *cf = NULL; + struct i40e_pf *pf = vf->pf; + struct i40e_vsi *vsi = NULL; + struct hlist_node *node; + i40e_status aq_ret = 0; + int i, ret; + + if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) { + aq_ret = I40E_ERR_PARAM; + goto err; + } + + if (!vf->adq_enabled) { + dev_info(&pf->pdev->dev, + "VF %d: ADq not enabled, can't apply cloud filter\n", + vf->vf_id); + aq_ret = I40E_ERR_PARAM; + goto err; + } + + if (i40e_validate_cloud_filter(vf, vcf)) { + dev_info(&pf->pdev->dev, + "VF %d: Invalid input, can't apply cloud filter\n", + vf->vf_id); + aq_ret = I40E_ERR_PARAM; + goto err; + } + + memset(&cfilter, 0, sizeof(cfilter)); + /* parse destination mac address */ + for (i = 0; i < ETH_ALEN; i++) + cfilter.dst_mac[i] = mask.dst_mac[i] & tcf.dst_mac[i]; + + /* parse source mac address */ + for (i = 0; i < ETH_ALEN; i++) + cfilter.src_mac[i] = mask.src_mac[i] & tcf.src_mac[i]; + + cfilter.vlan_id = mask.vlan_id & tcf.vlan_id; + cfilter.dst_port = mask.dst_port & tcf.dst_port; + cfilter.src_port = mask.src_port & tcf.src_port; + + switch (vcf->flow_type) { + case VIRTCHNL_TCP_V4_FLOW: + cfilter.n_proto = ETH_P_IP; + if (mask.dst_ip[0] & tcf.dst_ip[0]) + memcpy(&cfilter.ip.v4.dst_ip, tcf.dst_ip, + ARRAY_SIZE(tcf.dst_ip)); + else if (mask.src_ip[0] & tcf.dst_ip[0]) + memcpy(&cfilter.ip.v4.src_ip, tcf.src_ip, + ARRAY_SIZE(tcf.dst_ip)); + break; + case VIRTCHNL_TCP_V6_FLOW: + cfilter.n_proto = ETH_P_IPV6; + if (mask.dst_ip[3] & tcf.dst_ip[3]) + memcpy(&cfilter.ip.v6.dst_ip6, tcf.dst_ip, + sizeof(cfilter.ip.v6.dst_ip6)); + if (mask.src_ip[3] & tcf.src_ip[3]) + memcpy(&cfilter.ip.v6.src_ip6, tcf.src_ip, + sizeof(cfilter.ip.v6.src_ip6)); + break; + default: + /* TC filter can be configured based on different combinations + * and in this case IP is not a part of filter config + */ + dev_info(&pf->pdev->dev, "VF %d: Flow type not configured\n", + vf->vf_id); + } + + /* get the vsi to which the tc belongs to */ + vsi = pf->vsi[vf->ch[vcf->action_meta].vsi_idx]; + cfilter.seid = vsi->seid; + cfilter.flags = vcf->field_flags; + + /* Deleting TC filter */ + if (tcf.dst_port) + ret = i40e_add_del_cloud_filter_big_buf(vsi, &cfilter, false); + else + ret = i40e_add_del_cloud_filter(vsi, &cfilter, false); + if (ret) { + dev_err(&pf->pdev->dev, + "VF %d: Failed to delete cloud filter, err %s aq_err %s\n", + vf->vf_id, i40e_stat_str(&pf->hw, ret), + i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status)); + goto err; + } + + hlist_for_each_entry_safe(cf, node, + &vf->cloud_filter_list, cloud_node) { + if (cf->seid != cfilter.seid) + continue; + if (mask.dst_port) + if (cfilter.dst_port != cf->dst_port) + continue; + if (mask.dst_mac[0]) + if (!ether_addr_equal(cf->src_mac, cfilter.src_mac)) + continue; + /* for ipv4 data to be valid, only first byte of mask is set */ + if (cfilter.n_proto == ETH_P_IP && mask.dst_ip[0]) + if (memcmp(&cfilter.ip.v4.dst_ip, &cf->ip.v4.dst_ip, + ARRAY_SIZE(tcf.dst_ip))) + continue; + /* for ipv6, mask is set for all sixteen bytes (4 words) */ + if (cfilter.n_proto == ETH_P_IPV6 && mask.dst_ip[3]) + if (memcmp(&cfilter.ip.v6.dst_ip6, &cf->ip.v6.dst_ip6, + sizeof(cfilter.ip.v6.src_ip6))) + continue; + if (mask.vlan_id) + if (cfilter.vlan_id != cf->vlan_id) + continue; + + hlist_del(&cf->cloud_node); + kfree(cf); + vf->num_cloud_filters--; + } + +err: + return i40e_vc_send_resp_to_vf(vf, VIRTCHNL_OP_DEL_CLOUD_FILTER, + aq_ret); +} + +/** + * i40e_vc_add_cloud_filter + * @vf: pointer to the VF info + * @msg: pointer to the msg buffer + * + * This function adds a cloud filter programmed as TC filter for ADq + **/ +static int i40e_vc_add_cloud_filter(struct i40e_vf *vf, u8 *msg) +{ + struct virtchnl_filter *vcf = (struct virtchnl_filter *)msg; + struct virtchnl_l4_spec mask = vcf->mask.tcp_spec; + struct virtchnl_l4_spec tcf = vcf->data.tcp_spec; + struct i40e_cloud_filter *cfilter = NULL; + struct i40e_pf *pf = vf->pf; + struct i40e_vsi *vsi = NULL; + i40e_status aq_ret = 0; + int i, ret; + + if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) { + aq_ret = I40E_ERR_PARAM; + goto err; + } + + if (!vf->adq_enabled) { + dev_info(&pf->pdev->dev, + "VF %d: ADq is not enabled, can't apply cloud filter\n", + vf->vf_id); + aq_ret = I40E_ERR_PARAM; + goto err; + } + + if (i40e_validate_cloud_filter(vf, vcf)) { + dev_info(&pf->pdev->dev, + "VF %d: Invalid input/s, can't apply cloud filter\n", + vf->vf_id); + aq_ret = I40E_ERR_PARAM; + goto err; + } + + cfilter = kzalloc(sizeof(*cfilter), GFP_KERNEL); + if (!cfilter) + return -ENOMEM; + + /* parse destination mac address */ + for (i = 0; i < ETH_ALEN; i++) + cfilter->dst_mac[i] = mask.dst_mac[i] & tcf.dst_mac[i]; + + /* parse source mac address */ + for (i = 0; i < ETH_ALEN; i++) + cfilter->src_mac[i] = mask.src_mac[i] & tcf.src_mac[i]; + + cfilter->vlan_id = mask.vlan_id & tcf.vlan_id; + cfilter->dst_port = mask.dst_port & tcf.dst_port; + cfilter->src_port = mask.src_port & tcf.src_port; + + switch (vcf->flow_type) { + case VIRTCHNL_TCP_V4_FLOW: + cfilter->n_proto = ETH_P_IP; + if (mask.dst_ip[0] & tcf.dst_ip[0]) + memcpy(&cfilter->ip.v4.dst_ip, tcf.dst_ip, + ARRAY_SIZE(tcf.dst_ip)); + else if (mask.src_ip[0] & tcf.dst_ip[0]) + memcpy(&cfilter->ip.v4.src_ip, tcf.src_ip, + ARRAY_SIZE(tcf.dst_ip)); + break; + case VIRTCHNL_TCP_V6_FLOW: + cfilter->n_proto = ETH_P_IPV6; + if (mask.dst_ip[3] & tcf.dst_ip[3]) + memcpy(&cfilter->ip.v6.dst_ip6, tcf.dst_ip, + sizeof(cfilter->ip.v6.dst_ip6)); + if (mask.src_ip[3] & tcf.src_ip[3]) + memcpy(&cfilter->ip.v6.src_ip6, tcf.src_ip, + sizeof(cfilter->ip.v6.src_ip6)); + break; + default: + /* TC filter can be configured based on different combinations + * and in this case IP is not a part of filter config + */ + dev_info(&pf->pdev->dev, "VF %d: Flow type not configured\n", + vf->vf_id); + } + + /* get the VSI to which the TC belongs to */ + vsi = pf->vsi[vf->ch[vcf->action_meta].vsi_idx]; + cfilter->seid = vsi->seid; + cfilter->flags = vcf->field_flags; + + /* Adding cloud filter programmed as TC filter */ + if (tcf.dst_port) + ret = i40e_add_del_cloud_filter_big_buf(vsi, cfilter, true); + else + ret = i40e_add_del_cloud_filter(vsi, cfilter, true); + if (ret) { + dev_err(&pf->pdev->dev, + "VF %d: Failed to add cloud filter, err %s aq_err %s\n", + vf->vf_id, i40e_stat_str(&pf->hw, ret), + i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status)); + goto err; + } + + INIT_HLIST_NODE(&cfilter->cloud_node); + hlist_add_head(&cfilter->cloud_node, &vf->cloud_filter_list); + vf->num_cloud_filters++; +err: + return i40e_vc_send_resp_to_vf(vf, VIRTCHNL_OP_ADD_CLOUD_FILTER, + aq_ret); +} + +/** + * i40e_vc_add_qch_msg: Add queue channel and enable ADq + * @vf: pointer to the VF info + * @msg: pointer to the msg buffer + **/ +static int i40e_vc_add_qch_msg(struct i40e_vf *vf, u8 *msg) +{ + struct virtchnl_tc_info *tci = + (struct virtchnl_tc_info *)msg; + struct i40e_pf *pf = vf->pf; + struct i40e_link_status *ls = &pf->hw.phy.link_info; + int i, adq_request_qps = 0, speed = 0; + i40e_status aq_ret = 0; + + if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) { + aq_ret = I40E_ERR_PARAM; + goto err; + } + + /* ADq cannot be applied if spoof check is ON */ + if (vf->spoofchk) { + dev_err(&pf->pdev->dev, + "Spoof check is ON, turn it OFF to enable ADq\n"); + aq_ret = I40E_ERR_PARAM; + goto err; + } + + if (!(vf->driver_caps & VIRTCHNL_VF_OFFLOAD_ADQ)) { + dev_err(&pf->pdev->dev, + "VF %d attempting to enable ADq, but hasn't properly negotiated that capability\n", + vf->vf_id); + aq_ret = I40E_ERR_PARAM; + goto err; + } + + /* max number of traffic classes for VF currently capped at 4 */ + if (!tci->num_tc || tci->num_tc > I40E_MAX_VF_VSI) { + dev_err(&pf->pdev->dev, + "VF %d trying to set %u TCs, valid range 1-4 TCs per VF\n", + vf->vf_id, tci->num_tc); + aq_ret = I40E_ERR_PARAM; + goto err; + } + + /* validate queues for each TC */ + for (i = 0; i < tci->num_tc; i++) + if (!tci->list[i].count || + tci->list[i].count > I40E_DEFAULT_QUEUES_PER_VF) { + dev_err(&pf->pdev->dev, + "VF %d: TC %d trying to set %u queues, valid range 1-4 queues per TC\n", + vf->vf_id, i, tci->list[i].count); + aq_ret = I40E_ERR_PARAM; + goto err; + } + + /* need Max VF queues but already have default number of queues */ + adq_request_qps = I40E_MAX_VF_QUEUES - I40E_DEFAULT_QUEUES_PER_VF; + + if (pf->queues_left < adq_request_qps) { + dev_err(&pf->pdev->dev, + "No queues left to allocate to VF %d\n", + vf->vf_id); + aq_ret = I40E_ERR_PARAM; + goto err; + } else { + /* we need to allocate max VF queues to enable ADq so as to + * make sure ADq enabled VF always gets back queues when it + * goes through a reset. + */ + vf->num_queue_pairs = I40E_MAX_VF_QUEUES; + } + + /* get link speed in MB to validate rate limit */ + switch (ls->link_speed) { + case VIRTCHNL_LINK_SPEED_100MB: + speed = SPEED_100; + break; + case VIRTCHNL_LINK_SPEED_1GB: + speed = SPEED_1000; + break; + case VIRTCHNL_LINK_SPEED_10GB: + speed = SPEED_10000; + break; + case VIRTCHNL_LINK_SPEED_20GB: + speed = SPEED_20000; + break; + case VIRTCHNL_LINK_SPEED_25GB: + speed = SPEED_25000; + break; + case VIRTCHNL_LINK_SPEED_40GB: + speed = SPEED_40000; + break; + default: + dev_err(&pf->pdev->dev, + "Cannot detect link speed\n"); + aq_ret = I40E_ERR_PARAM; + goto err; + } + + /* parse data from the queue channel info */ + vf->num_tc = tci->num_tc; + for (i = 0; i < vf->num_tc; i++) { + if (tci->list[i].max_tx_rate) { + if (tci->list[i].max_tx_rate > speed) { + dev_err(&pf->pdev->dev, + "Invalid max tx rate %llu specified for VF %d.", + tci->list[i].max_tx_rate, + vf->vf_id); + aq_ret = I40E_ERR_PARAM; + goto err; + } else { + vf->ch[i].max_tx_rate = + tci->list[i].max_tx_rate; + } + } + vf->ch[i].num_qps = tci->list[i].count; + } + + /* set this flag only after making sure all inputs are sane */ + vf->adq_enabled = true; + /* num_req_queues is set when user changes number of queues via ethtool + * and this causes issue for default VSI(which depends on this variable) + * when ADq is enabled, hence reset it. + */ + vf->num_req_queues = 0; + + /* reset the VF in order to allocate resources */ + i40e_vc_notify_vf_reset(vf); + i40e_reset_vf(vf, false); + + return I40E_SUCCESS; + + /* send the response to the VF */ +err: + return i40e_vc_send_resp_to_vf(vf, VIRTCHNL_OP_ENABLE_CHANNELS, + aq_ret); +} + +/** + * i40e_vc_del_qch_msg + * @vf: pointer to the VF info + * @msg: pointer to the msg buffer + **/ +static int i40e_vc_del_qch_msg(struct i40e_vf *vf, u8 *msg) +{ + struct i40e_pf *pf = vf->pf; + i40e_status aq_ret = 0; + + if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) { + aq_ret = I40E_ERR_PARAM; + goto err; + } + + if (vf->adq_enabled) { + i40e_del_all_cloud_filters(vf); + i40e_del_qch(vf); + vf->adq_enabled = false; + vf->num_tc = 0; + dev_info(&pf->pdev->dev, + "Deleting Queue Channels and cloud filters for ADq on VF %d\n", + vf->vf_id); + } else { + dev_info(&pf->pdev->dev, "VF %d trying to delete queue channels but ADq isn't enabled\n", + vf->vf_id); + aq_ret = I40E_ERR_PARAM; + } + + /* reset the VF in order to allocate resources */ + i40e_vc_notify_vf_reset(vf); + i40e_reset_vf(vf, false); + + return I40E_SUCCESS; + +err: + return i40e_vc_send_resp_to_vf(vf, VIRTCHNL_OP_DISABLE_CHANNELS, + aq_ret); +} + +/** * i40e_vc_process_vf_msg * @pf: pointer to the PF structure * @vf_id: source VF id @@ -2816,7 +3657,18 @@ int i40e_vc_process_vf_msg(struct i40e_pf *pf, s16 vf_id, u32 v_opcode, case VIRTCHNL_OP_REQUEST_QUEUES: ret = i40e_vc_request_queues_msg(vf, msg, msglen); break; - + case VIRTCHNL_OP_ENABLE_CHANNELS: + ret = i40e_vc_add_qch_msg(vf, msg); + break; + case VIRTCHNL_OP_DISABLE_CHANNELS: + ret = i40e_vc_del_qch_msg(vf, msg); + break; + case VIRTCHNL_OP_ADD_CLOUD_FILTER: + ret = i40e_vc_add_cloud_filter(vf, msg); + break; + case VIRTCHNL_OP_DEL_CLOUD_FILTER: + ret = i40e_vc_del_cloud_filter(vf, msg); + break; case VIRTCHNL_OP_UNKNOWN: default: dev_err(&pf->pdev->dev, "Unsupported opcode %d from VF %d\n", @@ -3382,6 +4234,16 @@ int i40e_ndo_set_vf_trust(struct net_device *netdev, int vf_id, bool setting) i40e_vc_disable_vf(vf); dev_info(&pf->pdev->dev, "VF %u is now %strusted\n", vf_id, setting ? "" : "un"); + + if (vf->adq_enabled) { + if (!vf->trusted) { + dev_info(&pf->pdev->dev, + "VF %u no longer Trusted, deleting all cloud filters\n", + vf_id); + i40e_del_all_cloud_filters(vf); + } + } + out: return ret; } diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h index 5efc4f92bb37..6852599b2379 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h @@ -69,6 +69,19 @@ enum i40e_vf_capabilities { I40E_VIRTCHNL_VF_CAP_IWARP, }; +/* In ADq, max 4 VSI's can be allocated per VF including primary VF VSI. + * These variables are used to store indices, id's and number of queues + * for each VSI including that of primary VF VSI. Each Traffic class is + * termed as channel and each channel can in-turn have 4 queues which + * means max 16 queues overall per VF. + */ +struct i40evf_channel { + u16 vsi_idx; /* index in PF struct for all channel VSIs */ + u16 vsi_id; /* VSI ID used by firmware */ + u16 num_qps; /* number of queue pairs requested by user */ + u64 max_tx_rate; /* bandwidth rate allocation for VSIs */ +}; + /* VF information structure */ struct i40e_vf { struct i40e_pf *pf; @@ -111,6 +124,13 @@ struct i40e_vf { u16 num_mac; u16 num_vlan; + /* ADq related variables */ + bool adq_enabled; /* flag to enable adq */ + u8 num_tc; + struct i40evf_channel ch[I40E_MAX_VF_VSI]; + struct hlist_head cloud_filter_list; + u16 num_cloud_filters; + /* RDMA Client */ struct virtchnl_iwarp_qvlist_info *qvlist_info; }; diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c index 357d6051281f..e088d23eb083 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c @@ -196,7 +196,7 @@ void i40evf_detect_recover_hung(struct i40e_vsi *vsi) */ smp_rmb(); tx_ring->tx_stats.prev_pkt_ctr = - i40evf_get_tx_pending(tx_ring, false) ? packets : -1; + i40evf_get_tx_pending(tx_ring, true) ? packets : -1; } } } @@ -392,99 +392,241 @@ void i40evf_force_wb(struct i40e_vsi *vsi, struct i40e_q_vector *q_vector) val); } +static inline bool i40e_container_is_rx(struct i40e_q_vector *q_vector, + struct i40e_ring_container *rc) +{ + return &q_vector->rx == rc; +} + +static inline unsigned int i40e_itr_divisor(struct i40e_q_vector *q_vector) +{ + unsigned int divisor; + + switch (q_vector->adapter->link_speed) { + case I40E_LINK_SPEED_40GB: + divisor = I40E_ITR_ADAPTIVE_MIN_INC * 1024; + break; + case I40E_LINK_SPEED_25GB: + case I40E_LINK_SPEED_20GB: + divisor = I40E_ITR_ADAPTIVE_MIN_INC * 512; + break; + default: + case I40E_LINK_SPEED_10GB: + divisor = I40E_ITR_ADAPTIVE_MIN_INC * 256; + break; + case I40E_LINK_SPEED_1GB: + case I40E_LINK_SPEED_100MB: + divisor = I40E_ITR_ADAPTIVE_MIN_INC * 32; + break; + } + + return divisor; +} + /** - * i40e_set_new_dynamic_itr - Find new ITR level + * i40e_update_itr - update the dynamic ITR value based on statistics + * @q_vector: structure containing interrupt and ring information * @rc: structure containing ring performance data * - * Returns true if ITR changed, false if not - * - * Stores a new ITR value based on packets and byte counts during - * the last interrupt. The advantage of per interrupt computation - * is faster updates and more accurate ITR for the current traffic - * pattern. Constants in this function were computed based on - * theoretical maximum wire speed and thresholds were set based on - * testing data as well as attempting to minimize response time + * Stores a new ITR value based on packets and byte + * counts during the last interrupt. The advantage of per interrupt + * computation is faster updates and more accurate ITR for the current + * traffic pattern. Constants in this function were computed + * based on theoretical maximum wire speed and thresholds were set based + * on testing data as well as attempting to minimize response time * while increasing bulk throughput. **/ -static bool i40e_set_new_dynamic_itr(struct i40e_ring_container *rc) +static void i40e_update_itr(struct i40e_q_vector *q_vector, + struct i40e_ring_container *rc) { - enum i40e_latency_range new_latency_range = rc->latency_range; - u32 new_itr = rc->itr; - int bytes_per_usec; - unsigned int usecs, estimated_usecs; + unsigned int avg_wire_size, packets, bytes, itr; + unsigned long next_update = jiffies; - if (rc->total_packets == 0 || !rc->itr) - return false; + /* If we don't have any rings just leave ourselves set for maximum + * possible latency so we take ourselves out of the equation. + */ + if (!rc->ring || !ITR_IS_DYNAMIC(rc->ring->itr_setting)) + return; + + /* For Rx we want to push the delay up and default to low latency. + * for Tx we want to pull the delay down and default to high latency. + */ + itr = i40e_container_is_rx(q_vector, rc) ? + I40E_ITR_ADAPTIVE_MIN_USECS | I40E_ITR_ADAPTIVE_LATENCY : + I40E_ITR_ADAPTIVE_MAX_USECS | I40E_ITR_ADAPTIVE_LATENCY; + + /* If we didn't update within up to 1 - 2 jiffies we can assume + * that either packets are coming in so slow there hasn't been + * any work, or that there is so much work that NAPI is dealing + * with interrupt moderation and we don't need to do anything. + */ + if (time_after(next_update, rc->next_update)) + goto clear_counts; + + /* If itr_countdown is set it means we programmed an ITR within + * the last 4 interrupt cycles. This has a side effect of us + * potentially firing an early interrupt. In order to work around + * this we need to throw out any data received for a few + * interrupts following the update. + */ + if (q_vector->itr_countdown) { + itr = rc->target_itr; + goto clear_counts; + } + + packets = rc->total_packets; + bytes = rc->total_bytes; - usecs = (rc->itr << 1) * ITR_COUNTDOWN_START; - bytes_per_usec = rc->total_bytes / usecs; + if (i40e_container_is_rx(q_vector, rc)) { + /* If Rx there are 1 to 4 packets and bytes are less than + * 9000 assume insufficient data to use bulk rate limiting + * approach unless Tx is already in bulk rate limiting. We + * are likely latency driven. + */ + if (packets && packets < 4 && bytes < 9000 && + (q_vector->tx.target_itr & I40E_ITR_ADAPTIVE_LATENCY)) { + itr = I40E_ITR_ADAPTIVE_LATENCY; + goto adjust_by_size; + } + } else if (packets < 4) { + /* If we have Tx and Rx ITR maxed and Tx ITR is running in + * bulk mode and we are receiving 4 or fewer packets just + * reset the ITR_ADAPTIVE_LATENCY bit for latency mode so + * that the Rx can relax. + */ + if (rc->target_itr == I40E_ITR_ADAPTIVE_MAX_USECS && + (q_vector->rx.target_itr & I40E_ITR_MASK) == + I40E_ITR_ADAPTIVE_MAX_USECS) + goto clear_counts; + } else if (packets > 32) { + /* If we have processed over 32 packets in a single interrupt + * for Tx assume we need to switch over to "bulk" mode. + */ + rc->target_itr &= ~I40E_ITR_ADAPTIVE_LATENCY; + } - /* The calculations in this algorithm depend on interrupts actually - * firing at the ITR rate. This may not happen if the packet rate is - * really low, or if we've been napi polling. Check to make sure - * that's not the case before we continue. + /* We have no packets to actually measure against. This means + * either one of the other queues on this vector is active or + * we are a Tx queue doing TSO with too high of an interrupt rate. + * + * Between 4 and 56 we can assume that our current interrupt delay + * is only slightly too low. As such we should increase it by a small + * fixed amount. */ - estimated_usecs = jiffies_to_usecs(jiffies - rc->last_itr_update); - if (estimated_usecs > usecs) { - new_latency_range = I40E_LOW_LATENCY; - goto reset_latency; + if (packets < 56) { + itr = rc->target_itr + I40E_ITR_ADAPTIVE_MIN_INC; + if ((itr & I40E_ITR_MASK) > I40E_ITR_ADAPTIVE_MAX_USECS) { + itr &= I40E_ITR_ADAPTIVE_LATENCY; + itr += I40E_ITR_ADAPTIVE_MAX_USECS; + } + goto clear_counts; + } + + if (packets <= 256) { + itr = min(q_vector->tx.current_itr, q_vector->rx.current_itr); + itr &= I40E_ITR_MASK; + + /* Between 56 and 112 is our "goldilocks" zone where we are + * working out "just right". Just report that our current + * ITR is good for us. + */ + if (packets <= 112) + goto clear_counts; + + /* If packet count is 128 or greater we are likely looking + * at a slight overrun of the delay we want. Try halving + * our delay to see if that will cut the number of packets + * in half per interrupt. + */ + itr /= 2; + itr &= I40E_ITR_MASK; + if (itr < I40E_ITR_ADAPTIVE_MIN_USECS) + itr = I40E_ITR_ADAPTIVE_MIN_USECS; + + goto clear_counts; } - /* simple throttlerate management - * 0-10MB/s lowest (50000 ints/s) - * 10-20MB/s low (20000 ints/s) - * 20-1249MB/s bulk (18000 ints/s) + /* The paths below assume we are dealing with a bulk ITR since + * number of packets is greater than 256. We are just going to have + * to compute a value and try to bring the count under control, + * though for smaller packet sizes there isn't much we can do as + * NAPI polling will likely be kicking in sooner rather than later. + */ + itr = I40E_ITR_ADAPTIVE_BULK; + +adjust_by_size: + /* If packet counts are 256 or greater we can assume we have a gross + * overestimation of what the rate should be. Instead of trying to fine + * tune it just use the formula below to try and dial in an exact value + * give the current packet size of the frame. + */ + avg_wire_size = bytes / packets; + + /* The following is a crude approximation of: + * wmem_default / (size + overhead) = desired_pkts_per_int + * rate / bits_per_byte / (size + ethernet overhead) = pkt_rate + * (desired_pkt_rate / pkt_rate) * usecs_per_sec = ITR value * - * The math works out because the divisor is in 10^(-6) which - * turns the bytes/us input value into MB/s values, but - * make sure to use usecs, as the register values written - * are in 2 usec increments in the ITR registers, and make sure - * to use the smoothed values that the countdown timer gives us. + * Assuming wmem_default is 212992 and overhead is 640 bytes per + * packet, (256 skb, 64 headroom, 320 shared info), we can reduce the + * formula down to + * + * (170 * (size + 24)) / (size + 640) = ITR + * + * We first do some math on the packet size and then finally bitshift + * by 8 after rounding up. We also have to account for PCIe link speed + * difference as ITR scales based on this. */ - switch (new_latency_range) { - case I40E_LOWEST_LATENCY: - if (bytes_per_usec > 10) - new_latency_range = I40E_LOW_LATENCY; - break; - case I40E_LOW_LATENCY: - if (bytes_per_usec > 20) - new_latency_range = I40E_BULK_LATENCY; - else if (bytes_per_usec <= 10) - new_latency_range = I40E_LOWEST_LATENCY; - break; - case I40E_BULK_LATENCY: - default: - if (bytes_per_usec <= 20) - new_latency_range = I40E_LOW_LATENCY; - break; + if (avg_wire_size <= 60) { + /* Start at 250k ints/sec */ + avg_wire_size = 4096; + } else if (avg_wire_size <= 380) { + /* 250K ints/sec to 60K ints/sec */ + avg_wire_size *= 40; + avg_wire_size += 1696; + } else if (avg_wire_size <= 1084) { + /* 60K ints/sec to 36K ints/sec */ + avg_wire_size *= 15; + avg_wire_size += 11452; + } else if (avg_wire_size <= 1980) { + /* 36K ints/sec to 30K ints/sec */ + avg_wire_size *= 5; + avg_wire_size += 22420; + } else { + /* plateau at a limit of 30K ints/sec */ + avg_wire_size = 32256; } -reset_latency: - rc->latency_range = new_latency_range; + /* If we are in low latency mode halve our delay which doubles the + * rate to somewhere between 100K to 16K ints/sec + */ + if (itr & I40E_ITR_ADAPTIVE_LATENCY) + avg_wire_size /= 2; - switch (new_latency_range) { - case I40E_LOWEST_LATENCY: - new_itr = I40E_ITR_50K; - break; - case I40E_LOW_LATENCY: - new_itr = I40E_ITR_20K; - break; - case I40E_BULK_LATENCY: - new_itr = I40E_ITR_18K; - break; - default: - break; + /* Resultant value is 256 times larger than it needs to be. This + * gives us room to adjust the value as needed to either increase + * or decrease the value based on link speeds of 10G, 2.5G, 1G, etc. + * + * Use addition as we have already recorded the new latency flag + * for the ITR value. + */ + itr += DIV_ROUND_UP(avg_wire_size, i40e_itr_divisor(q_vector)) * + I40E_ITR_ADAPTIVE_MIN_INC; + + if ((itr & I40E_ITR_MASK) > I40E_ITR_ADAPTIVE_MAX_USECS) { + itr &= I40E_ITR_ADAPTIVE_LATENCY; + itr += I40E_ITR_ADAPTIVE_MAX_USECS; } +clear_counts: + /* write back value */ + rc->target_itr = itr; + + /* next update should occur within next jiffy */ + rc->next_update = next_update + 1; + rc->total_bytes = 0; rc->total_packets = 0; - rc->last_itr_update = jiffies; - - if (new_itr != rc->itr) { - rc->itr = new_itr; - return true; - } - return false; } /** @@ -1273,7 +1415,7 @@ static struct sk_buff *i40e_build_skb(struct i40e_ring *rx_ring, * @rx_buffer: rx buffer to pull data from * * This function will clean up the contents of the rx_buffer. It will - * either recycle the bufer or unmap it and free the associated resources. + * either recycle the buffer or unmap it and free the associated resources. */ static void i40e_put_rx_buffer(struct i40e_ring *rx_ring, struct i40e_rx_buffer *rx_buffer) @@ -1457,33 +1599,45 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget) return failure ? budget : (int)total_rx_packets; } -static u32 i40e_buildreg_itr(const int type, const u16 itr) +static inline u32 i40e_buildreg_itr(const int type, u16 itr) { u32 val; + /* We don't bother with setting the CLEARPBA bit as the data sheet + * points out doing so is "meaningless since it was already + * auto-cleared". The auto-clearing happens when the interrupt is + * asserted. + * + * Hardware errata 28 for also indicates that writing to a + * xxINT_DYN_CTLx CSR with INTENA_MSK (bit 31) set to 0 will clear + * an event in the PBA anyway so we need to rely on the automask + * to hold pending events for us until the interrupt is re-enabled + * + * The itr value is reported in microseconds, and the register + * value is recorded in 2 microsecond units. For this reason we + * only need to shift by the interval shift - 1 instead of the + * full value. + */ + itr &= I40E_ITR_MASK; + val = I40E_VFINT_DYN_CTLN1_INTENA_MASK | - I40E_VFINT_DYN_CTLN1_CLEARPBA_MASK | (type << I40E_VFINT_DYN_CTLN1_ITR_INDX_SHIFT) | - (itr << I40E_VFINT_DYN_CTLN1_INTERVAL_SHIFT); + (itr << (I40E_VFINT_DYN_CTLN1_INTERVAL_SHIFT - 1)); return val; } /* a small macro to shorten up some long lines */ #define INTREG I40E_VFINT_DYN_CTLN1 -static inline int get_rx_itr(struct i40e_vsi *vsi, int idx) -{ - struct i40evf_adapter *adapter = vsi->back; - return adapter->rx_rings[idx].rx_itr_setting; -} - -static inline int get_tx_itr(struct i40e_vsi *vsi, int idx) -{ - struct i40evf_adapter *adapter = vsi->back; - - return adapter->tx_rings[idx].tx_itr_setting; -} +/* The act of updating the ITR will cause it to immediately trigger. In order + * to prevent this from throwing off adaptive update statistics we defer the + * update so that it can only happen so often. So after either Tx or Rx are + * updated we make the adaptive scheme wait until either the ITR completely + * expires via the next_update expiration or we have been through at least + * 3 interrupts. + */ +#define ITR_COUNTDOWN_START 3 /** * i40e_update_enable_itr - Update itr and re-enable MSIX interrupt @@ -1495,70 +1649,51 @@ static inline void i40e_update_enable_itr(struct i40e_vsi *vsi, struct i40e_q_vector *q_vector) { struct i40e_hw *hw = &vsi->back->hw; - bool rx = false, tx = false; - u32 rxval, txval; - int idx = q_vector->v_idx; - int rx_itr_setting, tx_itr_setting; - - /* avoid dynamic calculation if in countdown mode OR if - * all dynamic is disabled - */ - rxval = txval = i40e_buildreg_itr(I40E_ITR_NONE, 0); - - rx_itr_setting = get_rx_itr(vsi, idx); - tx_itr_setting = get_tx_itr(vsi, idx); + u32 intval; - if (q_vector->itr_countdown > 0 || - (!ITR_IS_DYNAMIC(rx_itr_setting) && - !ITR_IS_DYNAMIC(tx_itr_setting))) { - goto enable_int; - } - - if (ITR_IS_DYNAMIC(rx_itr_setting)) { - rx = i40e_set_new_dynamic_itr(&q_vector->rx); - rxval = i40e_buildreg_itr(I40E_RX_ITR, q_vector->rx.itr); - } + /* These will do nothing if dynamic updates are not enabled */ + i40e_update_itr(q_vector, &q_vector->tx); + i40e_update_itr(q_vector, &q_vector->rx); - if (ITR_IS_DYNAMIC(tx_itr_setting)) { - tx = i40e_set_new_dynamic_itr(&q_vector->tx); - txval = i40e_buildreg_itr(I40E_TX_ITR, q_vector->tx.itr); - } - - if (rx || tx) { - /* get the higher of the two ITR adjustments and - * use the same value for both ITR registers - * when in adaptive mode (Rx and/or Tx) - */ - u16 itr = max(q_vector->tx.itr, q_vector->rx.itr); - - q_vector->tx.itr = q_vector->rx.itr = itr; - txval = i40e_buildreg_itr(I40E_TX_ITR, itr); - tx = true; - rxval = i40e_buildreg_itr(I40E_RX_ITR, itr); - rx = true; - } - - /* only need to enable the interrupt once, but need - * to possibly update both ITR values + /* This block of logic allows us to get away with only updating + * one ITR value with each interrupt. The idea is to perform a + * pseudo-lazy update with the following criteria. + * + * 1. Rx is given higher priority than Tx if both are in same state + * 2. If we must reduce an ITR that is given highest priority. + * 3. We then give priority to increasing ITR based on amount. */ - if (rx) { - /* set the INTENA_MSK_MASK so that this first write - * won't actually enable the interrupt, instead just - * updating the ITR (it's bit 31 PF and VF) + if (q_vector->rx.target_itr < q_vector->rx.current_itr) { + /* Rx ITR needs to be reduced, this is highest priority */ + intval = i40e_buildreg_itr(I40E_RX_ITR, + q_vector->rx.target_itr); + q_vector->rx.current_itr = q_vector->rx.target_itr; + q_vector->itr_countdown = ITR_COUNTDOWN_START; + } else if ((q_vector->tx.target_itr < q_vector->tx.current_itr) || + ((q_vector->rx.target_itr - q_vector->rx.current_itr) < + (q_vector->tx.target_itr - q_vector->tx.current_itr))) { + /* Tx ITR needs to be reduced, this is second priority + * Tx ITR needs to be increased more than Rx, fourth priority */ - rxval |= BIT(31); - /* don't check _DOWN because interrupt isn't being enabled */ - wr32(hw, INTREG(q_vector->reg_idx), rxval); + intval = i40e_buildreg_itr(I40E_TX_ITR, + q_vector->tx.target_itr); + q_vector->tx.current_itr = q_vector->tx.target_itr; + q_vector->itr_countdown = ITR_COUNTDOWN_START; + } else if (q_vector->rx.current_itr != q_vector->rx.target_itr) { + /* Rx ITR needs to be increased, third priority */ + intval = i40e_buildreg_itr(I40E_RX_ITR, + q_vector->rx.target_itr); + q_vector->rx.current_itr = q_vector->rx.target_itr; + q_vector->itr_countdown = ITR_COUNTDOWN_START; + } else { + /* No ITR update, lowest priority */ + intval = i40e_buildreg_itr(I40E_ITR_NONE, 0); + if (q_vector->itr_countdown) + q_vector->itr_countdown--; } -enable_int: if (!test_bit(__I40E_VSI_DOWN, vsi->state)) - wr32(hw, INTREG(q_vector->reg_idx), txval); - - if (q_vector->itr_countdown) - q_vector->itr_countdown--; - else - q_vector->itr_countdown = ITR_COUNTDOWN_START; + wr32(hw, INTREG(q_vector->reg_idx), intval); } /** diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.h b/drivers/net/ethernet/intel/i40evf/i40e_txrx.h index 7798a6645c3f..9129447d079b 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.h @@ -28,31 +28,35 @@ #define _I40E_TXRX_H_ /* Interrupt Throttling and Rate Limiting Goodies */ - -#define I40E_MAX_ITR 0x0FF0 /* reg uses 2 usec resolution */ -#define I40E_MIN_ITR 0x0001 /* reg uses 2 usec resolution */ -#define I40E_ITR_100K 0x0005 -#define I40E_ITR_50K 0x000A -#define I40E_ITR_20K 0x0019 -#define I40E_ITR_18K 0x001B -#define I40E_ITR_8K 0x003E -#define I40E_ITR_4K 0x007A -#define I40E_MAX_INTRL 0x3B /* reg uses 4 usec resolution */ -#define I40E_ITR_RX_DEF (ITR_REG_TO_USEC(I40E_ITR_20K) | \ - I40E_ITR_DYNAMIC) -#define I40E_ITR_TX_DEF (ITR_REG_TO_USEC(I40E_ITR_20K) | \ - I40E_ITR_DYNAMIC) -#define I40E_ITR_DYNAMIC 0x8000 /* use top bit as a flag */ -#define I40E_MIN_INT_RATE 250 /* ~= 1000000 / (I40E_MAX_ITR * 2) */ -#define I40E_MAX_INT_RATE 500000 /* == 1000000 / (I40E_MIN_ITR * 2) */ #define I40E_DEFAULT_IRQ_WORK 256 -#define ITR_TO_REG(setting) ((setting & ~I40E_ITR_DYNAMIC) >> 1) -#define ITR_IS_DYNAMIC(setting) (!!(setting & I40E_ITR_DYNAMIC)) -#define ITR_REG_TO_USEC(itr_reg) (itr_reg << 1) + +/* The datasheet for the X710 and XL710 indicate that the maximum value for + * the ITR is 8160usec which is then called out as 0xFF0 with a 2usec + * resolution. 8160 is 0x1FE0 when written out in hex. So instead of storing + * the register value which is divided by 2 lets use the actual values and + * avoid an excessive amount of translation. + */ +#define I40E_ITR_DYNAMIC 0x8000 /* use top bit as a flag */ +#define I40E_ITR_MASK 0x1FFE /* mask for ITR register value */ +#define I40E_MIN_ITR 2 /* reg uses 2 usec resolution */ +#define I40E_ITR_100K 10 /* all values below must be even */ +#define I40E_ITR_50K 20 +#define I40E_ITR_20K 50 +#define I40E_ITR_18K 60 +#define I40E_ITR_8K 122 +#define I40E_MAX_ITR 8160 /* maximum value as per datasheet */ +#define ITR_TO_REG(setting) ((setting) & ~I40E_ITR_DYNAMIC) +#define ITR_REG_ALIGN(setting) __ALIGN_MASK(setting, ~I40E_ITR_MASK) +#define ITR_IS_DYNAMIC(setting) (!!((setting) & I40E_ITR_DYNAMIC)) + +#define I40E_ITR_RX_DEF (I40E_ITR_20K | I40E_ITR_DYNAMIC) +#define I40E_ITR_TX_DEF (I40E_ITR_20K | I40E_ITR_DYNAMIC) + /* 0x40 is the enable bit for interrupt rate limiting, and must be set if * the value of the rate limit is non-zero */ #define INTRL_ENA BIT(6) +#define I40E_MAX_INTRL 0x3B /* reg uses 4 usec resolution */ #define INTRL_REG_TO_USEC(intrl) ((intrl & ~INTRL_ENA) << 2) #define INTRL_USEC_TO_REG(set) ((set) ? ((set) >> 2) | INTRL_ENA : 0) #define I40E_INTRL_8K 125 /* 8000 ints/sec */ @@ -362,8 +366,7 @@ struct i40e_ring { * these values always store the USER setting, and must be converted * before programming to a register. */ - u16 rx_itr_setting; - u16 tx_itr_setting; + u16 itr_setting; u16 count; /* Number of descriptors */ u16 reg_idx; /* HW register index of the ring */ @@ -425,21 +428,21 @@ static inline void clear_ring_build_skb_enabled(struct i40e_ring *ring) ring->flags &= ~I40E_RXR_FLAGS_BUILD_SKB_ENABLED; } -enum i40e_latency_range { - I40E_LOWEST_LATENCY = 0, - I40E_LOW_LATENCY = 1, - I40E_BULK_LATENCY = 2, -}; +#define I40E_ITR_ADAPTIVE_MIN_INC 0x0002 +#define I40E_ITR_ADAPTIVE_MIN_USECS 0x0002 +#define I40E_ITR_ADAPTIVE_MAX_USECS 0x007e +#define I40E_ITR_ADAPTIVE_LATENCY 0x8000 +#define I40E_ITR_ADAPTIVE_BULK 0x0000 +#define ITR_IS_BULK(x) (!((x) & I40E_ITR_ADAPTIVE_LATENCY)) struct i40e_ring_container { - /* array of pointers to rings */ - struct i40e_ring *ring; + struct i40e_ring *ring; /* pointer to linked list of ring(s) */ + unsigned long next_update; /* jiffies value of next update */ unsigned int total_bytes; /* total bytes processed this int */ unsigned int total_packets; /* total packets processed this int */ - unsigned long last_itr_update; /* jiffies of last ITR update */ u16 count; - enum i40e_latency_range latency_range; - u16 itr; + u16 target_itr; /* target ITR setting for ring(s) */ + u16 current_itr; /* current ITR setting for ring(s) */ }; /* iterator for handling rings in ring container */ diff --git a/drivers/net/ethernet/intel/i40evf/i40evf.h b/drivers/net/ethernet/intel/i40evf/i40evf.h index 9690c1ea019e..e46555ad7122 100644 --- a/drivers/net/ethernet/intel/i40evf/i40evf.h +++ b/drivers/net/ethernet/intel/i40evf/i40evf.h @@ -52,7 +52,10 @@ #include <linux/socket.h> #include <linux/jiffies.h> #include <net/ip6_checksum.h> +#include <net/pkt_cls.h> #include <net/udp.h> +#include <net/tc_act/tc_gact.h> +#include <net/tc_act/tc_mirred.h> #include "i40e_type.h" #include <linux/avf/virtchnl.h> @@ -106,6 +109,7 @@ struct i40e_vsi { #define I40EVF_HKEY_ARRAY_SIZE ((I40E_VFQF_HKEY_MAX_INDEX + 1) * 4) #define I40EVF_HLUT_ARRAY_SIZE ((I40E_VFQF_HLUT_MAX_INDEX + 1) * 4) +#define I40EVF_MBPS_DIVISOR 125000 /* divisor to convert to Mbps */ /* MAX_MSIX_Q_VECTORS of these are allocated, * but we only use one per queue-specific vector. @@ -117,9 +121,8 @@ struct i40e_q_vector { struct i40e_ring_container rx; struct i40e_ring_container tx; u32 ring_mask; + u8 itr_countdown; /* when 0 should adjust adaptive ITR */ u8 num_ringpairs; /* total number of ring pairs in vector */ -#define ITR_COUNTDOWN_START 100 - u8 itr_countdown; /* when 0 or 1 update ITR */ u16 v_idx; /* index in the vsi->q_vector array. */ u16 reg_idx; /* register index of the interrupt */ char name[IFNAMSIZ + 15]; @@ -169,6 +172,28 @@ struct i40evf_vlan_filter { bool add; /* filter needs to be added */ }; +#define I40EVF_MAX_TRAFFIC_CLASS 4 +/* State of traffic class creation */ +enum i40evf_tc_state_t { + __I40EVF_TC_INVALID, /* no traffic class, default state */ + __I40EVF_TC_RUNNING, /* traffic classes have been created */ +}; + +/* channel info */ +struct i40evf_channel_config { + struct virtchnl_channel_info ch_info[I40EVF_MAX_TRAFFIC_CLASS]; + enum i40evf_tc_state_t state; + u8 total_qps; +}; + +/* State of cloud filter */ +enum i40evf_cloud_filter_state_t { + __I40EVF_CF_INVALID, /* cloud filter not added */ + __I40EVF_CF_ADD_PENDING, /* cloud filter pending add by the PF */ + __I40EVF_CF_DEL_PENDING, /* cloud filter pending del by the PF */ + __I40EVF_CF_ACTIVE, /* cloud filter is active */ +}; + /* Driver state. The order of these is important! */ enum i40evf_state_t { __I40EVF_STARTUP, /* driver loaded, probe complete */ @@ -190,6 +215,36 @@ enum i40evf_critical_section_t { __I40EVF_IN_REMOVE_TASK, /* device being removed */ }; +#define I40EVF_CLOUD_FIELD_OMAC 0x01 +#define I40EVF_CLOUD_FIELD_IMAC 0x02 +#define I40EVF_CLOUD_FIELD_IVLAN 0x04 +#define I40EVF_CLOUD_FIELD_TEN_ID 0x08 +#define I40EVF_CLOUD_FIELD_IIP 0x10 + +#define I40EVF_CF_FLAGS_OMAC I40EVF_CLOUD_FIELD_OMAC +#define I40EVF_CF_FLAGS_IMAC I40EVF_CLOUD_FIELD_IMAC +#define I40EVF_CF_FLAGS_IMAC_IVLAN (I40EVF_CLOUD_FIELD_IMAC |\ + I40EVF_CLOUD_FIELD_IVLAN) +#define I40EVF_CF_FLAGS_IMAC_TEN_ID (I40EVF_CLOUD_FIELD_IMAC |\ + I40EVF_CLOUD_FIELD_TEN_ID) +#define I40EVF_CF_FLAGS_OMAC_TEN_ID_IMAC (I40EVF_CLOUD_FIELD_OMAC |\ + I40EVF_CLOUD_FIELD_IMAC |\ + I40EVF_CLOUD_FIELD_TEN_ID) +#define I40EVF_CF_FLAGS_IMAC_IVLAN_TEN_ID (I40EVF_CLOUD_FIELD_IMAC |\ + I40EVF_CLOUD_FIELD_IVLAN |\ + I40EVF_CLOUD_FIELD_TEN_ID) +#define I40EVF_CF_FLAGS_IIP I40E_CLOUD_FIELD_IIP + +/* bookkeeping of cloud filters */ +struct i40evf_cloud_filter { + enum i40evf_cloud_filter_state_t state; + struct list_head list; + struct virtchnl_filter f; + unsigned long cookie; + bool del; /* filter needs to be deleted */ + bool add; /* filter needs to be added */ +}; + /* board specific private data structure */ struct i40evf_adapter { struct timer_list watchdog_timer; @@ -241,6 +296,7 @@ struct i40evf_adapter { #define I40EVF_FLAG_ALLMULTI_ON BIT(14) #define I40EVF_FLAG_LEGACY_RX BIT(15) #define I40EVF_FLAG_REINIT_ITR_NEEDED BIT(16) +#define I40EVF_FLAG_QUEUES_DISABLED BIT(17) /* duplicates for common code */ #define I40E_FLAG_DCB_ENABLED 0 #define I40E_FLAG_RX_CSUM_ENABLED I40EVF_FLAG_RX_CSUM_ENABLED @@ -269,6 +325,10 @@ struct i40evf_adapter { #define I40EVF_FLAG_AQ_RELEASE_ALLMULTI BIT(18) #define I40EVF_FLAG_AQ_ENABLE_VLAN_STRIPPING BIT(19) #define I40EVF_FLAG_AQ_DISABLE_VLAN_STRIPPING BIT(20) +#define I40EVF_FLAG_AQ_ENABLE_CHANNELS BIT(21) +#define I40EVF_FLAG_AQ_DISABLE_CHANNELS BIT(22) +#define I40EVF_FLAG_AQ_ADD_CLOUD_FILTER BIT(23) +#define I40EVF_FLAG_AQ_DEL_CLOUD_FILTER BIT(24) /* OS defined structs */ struct net_device *netdev; @@ -314,6 +374,13 @@ struct i40evf_adapter { u16 rss_lut_size; u8 *rss_key; u8 *rss_lut; + /* ADQ related members */ + struct i40evf_channel_config ch_config; + u8 num_tc; + struct list_head cloud_filter_list; + /* lock to protest access to the cloud filter list */ + spinlock_t cloud_filter_list_lock; + u16 num_cloud_filters; }; @@ -380,4 +447,8 @@ void i40evf_notify_client_message(struct i40e_vsi *vsi, u8 *msg, u16 len); void i40evf_notify_client_l2_params(struct i40e_vsi *vsi); void i40evf_notify_client_open(struct i40e_vsi *vsi); void i40evf_notify_client_close(struct i40e_vsi *vsi, bool reset); +void i40evf_enable_channels(struct i40evf_adapter *adapter); +void i40evf_disable_channels(struct i40evf_adapter *adapter); +void i40evf_add_cloud_filter(struct i40evf_adapter *adapter); +void i40evf_del_cloud_filter(struct i40evf_adapter *adapter); #endif /* _I40EVF_H_ */ diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c b/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c index e2d8aa19d205..e6793255de0b 100644 --- a/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c +++ b/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c @@ -457,14 +457,14 @@ static int __i40evf_get_coalesce(struct net_device *netdev, rx_ring = &adapter->rx_rings[queue]; tx_ring = &adapter->tx_rings[queue]; - if (ITR_IS_DYNAMIC(rx_ring->rx_itr_setting)) + if (ITR_IS_DYNAMIC(rx_ring->itr_setting)) ec->use_adaptive_rx_coalesce = 1; - if (ITR_IS_DYNAMIC(tx_ring->tx_itr_setting)) + if (ITR_IS_DYNAMIC(tx_ring->itr_setting)) ec->use_adaptive_tx_coalesce = 1; - ec->rx_coalesce_usecs = rx_ring->rx_itr_setting & ~I40E_ITR_DYNAMIC; - ec->tx_coalesce_usecs = tx_ring->tx_itr_setting & ~I40E_ITR_DYNAMIC; + ec->rx_coalesce_usecs = rx_ring->itr_setting & ~I40E_ITR_DYNAMIC; + ec->tx_coalesce_usecs = tx_ring->itr_setting & ~I40E_ITR_DYNAMIC; return 0; } @@ -502,7 +502,7 @@ static int i40evf_get_per_queue_coalesce(struct net_device *netdev, /** * i40evf_set_itr_per_queue - set ITR values for specific queue - * @vsi: the VSI to set values for + * @adapter: the VF adapter struct to set values for * @ec: coalesce settings from ethtool * @queue: the queue to modify * @@ -514,33 +514,29 @@ static void i40evf_set_itr_per_queue(struct i40evf_adapter *adapter, { struct i40e_ring *rx_ring = &adapter->rx_rings[queue]; struct i40e_ring *tx_ring = &adapter->tx_rings[queue]; - struct i40e_vsi *vsi = &adapter->vsi; - struct i40e_hw *hw = &adapter->hw; struct i40e_q_vector *q_vector; - u16 vector; - rx_ring->rx_itr_setting = ec->rx_coalesce_usecs; - tx_ring->tx_itr_setting = ec->tx_coalesce_usecs; + rx_ring->itr_setting = ITR_REG_ALIGN(ec->rx_coalesce_usecs); + tx_ring->itr_setting = ITR_REG_ALIGN(ec->tx_coalesce_usecs); - rx_ring->rx_itr_setting |= I40E_ITR_DYNAMIC; + rx_ring->itr_setting |= I40E_ITR_DYNAMIC; if (!ec->use_adaptive_rx_coalesce) - rx_ring->rx_itr_setting ^= I40E_ITR_DYNAMIC; + rx_ring->itr_setting ^= I40E_ITR_DYNAMIC; - tx_ring->tx_itr_setting |= I40E_ITR_DYNAMIC; + tx_ring->itr_setting |= I40E_ITR_DYNAMIC; if (!ec->use_adaptive_tx_coalesce) - tx_ring->tx_itr_setting ^= I40E_ITR_DYNAMIC; + tx_ring->itr_setting ^= I40E_ITR_DYNAMIC; q_vector = rx_ring->q_vector; - q_vector->rx.itr = ITR_TO_REG(rx_ring->rx_itr_setting); - vector = vsi->base_vector + q_vector->v_idx; - wr32(hw, I40E_VFINT_ITRN1(I40E_RX_ITR, vector - 1), q_vector->rx.itr); + q_vector->rx.target_itr = ITR_TO_REG(rx_ring->itr_setting); q_vector = tx_ring->q_vector; - q_vector->tx.itr = ITR_TO_REG(tx_ring->tx_itr_setting); - vector = vsi->base_vector + q_vector->v_idx; - wr32(hw, I40E_VFINT_ITRN1(I40E_TX_ITR, vector - 1), q_vector->tx.itr); + q_vector->tx.target_itr = ITR_TO_REG(tx_ring->itr_setting); - i40e_flush(hw); + /* The interrupt handler itself will take care of programming + * the Tx and Rx ITR values based on the values we have entered + * into the q_vector, no need to write the values now. + */ } /** @@ -565,8 +561,8 @@ static int __i40evf_set_coalesce(struct net_device *netdev, if (ec->rx_coalesce_usecs == 0) { if (ec->use_adaptive_rx_coalesce) netif_info(adapter, drv, netdev, "rx-usecs=0, need to disable adaptive-rx for a complete disable\n"); - } else if ((ec->rx_coalesce_usecs < (I40E_MIN_ITR << 1)) || - (ec->rx_coalesce_usecs > (I40E_MAX_ITR << 1))) { + } else if ((ec->rx_coalesce_usecs < I40E_MIN_ITR) || + (ec->rx_coalesce_usecs > I40E_MAX_ITR)) { netif_info(adapter, drv, netdev, "Invalid value, rx-usecs range is 0-8160\n"); return -EINVAL; } @@ -575,8 +571,8 @@ static int __i40evf_set_coalesce(struct net_device *netdev, if (ec->tx_coalesce_usecs == 0) { if (ec->use_adaptive_tx_coalesce) netif_info(adapter, drv, netdev, "tx-usecs=0, need to disable adaptive-tx for a complete disable\n"); - } else if ((ec->tx_coalesce_usecs < (I40E_MIN_ITR << 1)) || - (ec->tx_coalesce_usecs > (I40E_MAX_ITR << 1))) { + } else if ((ec->tx_coalesce_usecs < I40E_MIN_ITR) || + (ec->tx_coalesce_usecs > I40E_MAX_ITR)) { netif_info(adapter, drv, netdev, "Invalid value, tx-usecs range is 0-8160\n"); return -EINVAL; } @@ -699,6 +695,12 @@ static int i40evf_set_channels(struct net_device *netdev, return -EINVAL; } + if ((adapter->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_ADQ) && + adapter->num_tc) { + dev_info(&adapter->pdev->dev, "Cannot set channels since ADq is enabled.\n"); + return -EINVAL; + } + /* All of these should have already been checked by ethtool before this * even gets to us, but just to be sure. */ diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_main.c b/drivers/net/ethernet/intel/i40evf/i40evf_main.c index 16989ad2ca90..dae121877935 100644 --- a/drivers/net/ethernet/intel/i40evf/i40evf_main.c +++ b/drivers/net/ethernet/intel/i40evf/i40evf_main.c @@ -353,11 +353,12 @@ i40evf_map_vector_to_rxq(struct i40evf_adapter *adapter, int v_idx, int r_idx) rx_ring->vsi = &adapter->vsi; q_vector->rx.ring = rx_ring; q_vector->rx.count++; - q_vector->rx.latency_range = I40E_LOW_LATENCY; - q_vector->rx.itr = ITR_TO_REG(rx_ring->rx_itr_setting); + q_vector->rx.next_update = jiffies + 1; + q_vector->rx.target_itr = ITR_TO_REG(rx_ring->itr_setting); q_vector->ring_mask |= BIT(r_idx); - q_vector->itr_countdown = ITR_COUNTDOWN_START; - wr32(hw, I40E_VFINT_ITRN1(I40E_RX_ITR, v_idx - 1), q_vector->rx.itr); + wr32(hw, I40E_VFINT_ITRN1(I40E_RX_ITR, q_vector->reg_idx), + q_vector->rx.current_itr); + q_vector->rx.current_itr = q_vector->rx.target_itr; } /** @@ -378,11 +379,12 @@ i40evf_map_vector_to_txq(struct i40evf_adapter *adapter, int v_idx, int t_idx) tx_ring->vsi = &adapter->vsi; q_vector->tx.ring = tx_ring; q_vector->tx.count++; - q_vector->tx.latency_range = I40E_LOW_LATENCY; - q_vector->tx.itr = ITR_TO_REG(tx_ring->tx_itr_setting); - q_vector->itr_countdown = ITR_COUNTDOWN_START; + q_vector->tx.next_update = jiffies + 1; + q_vector->tx.target_itr = ITR_TO_REG(tx_ring->itr_setting); q_vector->num_ringpairs++; - wr32(hw, I40E_VFINT_ITRN1(I40E_TX_ITR, v_idx - 1), q_vector->tx.itr); + wr32(hw, I40E_VFINT_ITRN1(I40E_TX_ITR, q_vector->reg_idx), + q_vector->tx.target_itr); + q_vector->tx.current_itr = q_vector->tx.target_itr; } /** @@ -783,7 +785,7 @@ static int i40evf_vlan_rx_kill_vid(struct net_device *netdev, **/ static struct i40evf_mac_filter *i40evf_find_filter(struct i40evf_adapter *adapter, - u8 *macaddr) + const u8 *macaddr) { struct i40evf_mac_filter *f; @@ -806,20 +808,18 @@ i40evf_mac_filter *i40evf_find_filter(struct i40evf_adapter *adapter, **/ static struct i40evf_mac_filter *i40evf_add_filter(struct i40evf_adapter *adapter, - u8 *macaddr) + const u8 *macaddr) { struct i40evf_mac_filter *f; if (!macaddr) return NULL; - spin_lock_bh(&adapter->mac_vlan_list_lock); - f = i40evf_find_filter(adapter, macaddr); if (!f) { f = kzalloc(sizeof(*f), GFP_ATOMIC); if (!f) - goto clearout; + return f; ether_addr_copy(f->macaddr, macaddr); @@ -830,8 +830,6 @@ i40evf_mac_filter *i40evf_add_filter(struct i40evf_adapter *adapter, f->remove = false; } -clearout: - spin_unlock_bh(&adapter->mac_vlan_list_lock); return f; } @@ -866,9 +864,10 @@ static int i40evf_set_mac(struct net_device *netdev, void *p) adapter->aq_required |= I40EVF_FLAG_AQ_DEL_MAC_FILTER; } + f = i40evf_add_filter(adapter, addr->sa_data); + spin_unlock_bh(&adapter->mac_vlan_list_lock); - f = i40evf_add_filter(adapter, addr->sa_data); if (f) { ether_addr_copy(hw->mac.addr, addr->sa_data); ether_addr_copy(netdev->dev_addr, adapter->hw.mac.addr); @@ -878,50 +877,64 @@ static int i40evf_set_mac(struct net_device *netdev, void *p) } /** - * i40evf_set_rx_mode - NDO callback to set the netdev filters - * @netdev: network interface device structure - **/ -static void i40evf_set_rx_mode(struct net_device *netdev) + * i40evf_addr_sync - Callback for dev_(mc|uc)_sync to add address + * @netdev: the netdevice + * @addr: address to add + * + * Called by __dev_(mc|uc)_sync when an address needs to be added. We call + * __dev_(uc|mc)_sync from .set_rx_mode and guarantee to hold the hash lock. + */ +static int i40evf_addr_sync(struct net_device *netdev, const u8 *addr) { struct i40evf_adapter *adapter = netdev_priv(netdev); - struct i40evf_mac_filter *f, *ftmp; - struct netdev_hw_addr *uca; - struct netdev_hw_addr *mca; - struct netdev_hw_addr *ha; - - /* add addr if not already in the filter list */ - netdev_for_each_uc_addr(uca, netdev) { - i40evf_add_filter(adapter, uca->addr); - } - netdev_for_each_mc_addr(mca, netdev) { - i40evf_add_filter(adapter, mca->addr); - } - spin_lock_bh(&adapter->mac_vlan_list_lock); - - list_for_each_entry_safe(f, ftmp, &adapter->mac_filter_list, list) { - netdev_for_each_mc_addr(mca, netdev) - if (ether_addr_equal(mca->addr, f->macaddr)) - goto bottom_of_search_loop; - - netdev_for_each_uc_addr(uca, netdev) - if (ether_addr_equal(uca->addr, f->macaddr)) - goto bottom_of_search_loop; + if (i40evf_add_filter(adapter, addr)) + return 0; + else + return -ENOMEM; +} - for_each_dev_addr(netdev, ha) - if (ether_addr_equal(ha->addr, f->macaddr)) - goto bottom_of_search_loop; +/** + * i40evf_addr_unsync - Callback for dev_(mc|uc)_sync to remove address + * @netdev: the netdevice + * @addr: address to add + * + * Called by __dev_(mc|uc)_sync when an address needs to be removed. We call + * __dev_(uc|mc)_sync from .set_rx_mode and guarantee to hold the hash lock. + */ +static int i40evf_addr_unsync(struct net_device *netdev, const u8 *addr) +{ + struct i40evf_adapter *adapter = netdev_priv(netdev); + struct i40evf_mac_filter *f; - if (ether_addr_equal(f->macaddr, adapter->hw.mac.addr)) - goto bottom_of_search_loop; + /* Under some circumstances, we might receive a request to delete + * our own device address from our uc list. Because we store the + * device address in the VSI's MAC/VLAN filter list, we need to ignore + * such requests and not delete our device address from this list. + */ + if (ether_addr_equal(addr, netdev->dev_addr)) + return 0; - /* f->macaddr wasn't found in uc, mc, or ha list so delete it */ + f = i40evf_find_filter(adapter, addr); + if (f) { f->remove = true; adapter->aq_required |= I40EVF_FLAG_AQ_DEL_MAC_FILTER; - -bottom_of_search_loop: - continue; } + return 0; +} + +/** + * i40evf_set_rx_mode - NDO callback to set the netdev filters + * @netdev: network interface device structure + **/ +static void i40evf_set_rx_mode(struct net_device *netdev) +{ + struct i40evf_adapter *adapter = netdev_priv(netdev); + + spin_lock_bh(&adapter->mac_vlan_list_lock); + __dev_uc_sync(netdev, i40evf_addr_sync, i40evf_addr_unsync); + __dev_mc_sync(netdev, i40evf_addr_sync, i40evf_addr_unsync); + spin_unlock_bh(&adapter->mac_vlan_list_lock); if (netdev->flags & IFF_PROMISC && !(adapter->flags & I40EVF_FLAG_PROMISC_ON)) @@ -936,8 +949,6 @@ bottom_of_search_loop: else if (!(netdev->flags & IFF_ALLMULTI) && adapter->flags & I40EVF_FLAG_ALLMULTI_ON) adapter->aq_required |= I40EVF_FLAG_AQ_RELEASE_ALLMULTI; - - spin_unlock_bh(&adapter->mac_vlan_list_lock); } /** @@ -1025,7 +1036,9 @@ static void i40evf_up_complete(struct i40evf_adapter *adapter) void i40evf_down(struct i40evf_adapter *adapter) { struct net_device *netdev = adapter->netdev; + struct i40evf_vlan_filter *vlf; struct i40evf_mac_filter *f; + struct i40evf_cloud_filter *cf; if (adapter->state <= __I40EVF_DOWN_PENDING) return; @@ -1038,17 +1051,29 @@ void i40evf_down(struct i40evf_adapter *adapter) spin_lock_bh(&adapter->mac_vlan_list_lock); + /* clear the sync flag on all filters */ + __dev_uc_unsync(adapter->netdev, NULL); + __dev_mc_unsync(adapter->netdev, NULL); + /* remove all MAC filters */ list_for_each_entry(f, &adapter->mac_filter_list, list) { f->remove = true; } + /* remove all VLAN filters */ - list_for_each_entry(f, &adapter->vlan_filter_list, list) { - f->remove = true; + list_for_each_entry(vlf, &adapter->vlan_filter_list, list) { + vlf->remove = true; } spin_unlock_bh(&adapter->mac_vlan_list_lock); + /* remove all cloud filters */ + spin_lock_bh(&adapter->cloud_filter_list_lock); + list_for_each_entry(cf, &adapter->cloud_filter_list, list) { + cf->del = true; + } + spin_unlock_bh(&adapter->cloud_filter_list_lock); + if (!(adapter->flags & I40EVF_FLAG_PF_COMMS_FAILED) && adapter->state != __I40EVF_RESETTING) { /* cancel any current operation */ @@ -1059,6 +1084,7 @@ void i40evf_down(struct i40evf_adapter *adapter) */ adapter->aq_required = I40EVF_FLAG_AQ_DEL_MAC_FILTER; adapter->aq_required |= I40EVF_FLAG_AQ_DEL_VLAN_FILTER; + adapter->aq_required |= I40EVF_FLAG_AQ_DEL_CLOUD_FILTER; adapter->aq_required |= I40EVF_FLAG_AQ_DISABLE_QUEUES; } @@ -1144,6 +1170,9 @@ static int i40evf_alloc_queues(struct i40evf_adapter *adapter) */ if (adapter->num_req_queues) num_active_queues = adapter->num_req_queues; + else if ((adapter->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_ADQ) && + adapter->num_tc) + num_active_queues = adapter->ch_config.total_qps; else num_active_queues = min_t(int, adapter->vsi_res->num_queue_pairs, @@ -1169,7 +1198,7 @@ static int i40evf_alloc_queues(struct i40evf_adapter *adapter) tx_ring->netdev = adapter->netdev; tx_ring->dev = &adapter->pdev->dev; tx_ring->count = adapter->tx_desc_count; - tx_ring->tx_itr_setting = I40E_ITR_TX_DEF; + tx_ring->itr_setting = I40E_ITR_TX_DEF; if (adapter->flags & I40EVF_FLAG_WB_ON_ITR_CAPABLE) tx_ring->flags |= I40E_TXR_FLAGS_WB_ON_ITR; @@ -1178,7 +1207,7 @@ static int i40evf_alloc_queues(struct i40evf_adapter *adapter) rx_ring->netdev = adapter->netdev; rx_ring->dev = &adapter->pdev->dev; rx_ring->count = adapter->rx_desc_count; - rx_ring->rx_itr_setting = I40E_ITR_RX_DEF; + rx_ring->itr_setting = I40E_ITR_RX_DEF; } adapter->num_active_queues = num_active_queues; @@ -1471,6 +1500,16 @@ int i40evf_init_interrupt_scheme(struct i40evf_adapter *adapter) goto err_alloc_q_vectors; } + /* If we've made it so far while ADq flag being ON, then we haven't + * bailed out anywhere in middle. And ADq isn't just enabled but actual + * resources have been allocated in the reset path. + * Now we can truly claim that ADq is enabled. + */ + if ((adapter->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_ADQ) && + adapter->num_tc) + dev_info(&adapter->pdev->dev, "ADq Enabled, %u TCs created", + adapter->num_tc); + dev_info(&adapter->pdev->dev, "Multiqueue %s: Queue pair count = %u", (adapter->num_active_queues > 1) ? "Enabled" : "Disabled", adapter->num_active_queues); @@ -1712,6 +1751,27 @@ static void i40evf_watchdog_task(struct work_struct *work) i40evf_set_promiscuous(adapter, 0); goto watchdog_done; } + + if (adapter->aq_required & I40EVF_FLAG_AQ_ENABLE_CHANNELS) { + i40evf_enable_channels(adapter); + goto watchdog_done; + } + + if (adapter->aq_required & I40EVF_FLAG_AQ_DISABLE_CHANNELS) { + i40evf_disable_channels(adapter); + goto watchdog_done; + } + + if (adapter->aq_required & I40EVF_FLAG_AQ_ADD_CLOUD_FILTER) { + i40evf_add_cloud_filter(adapter); + goto watchdog_done; + } + + if (adapter->aq_required & I40EVF_FLAG_AQ_DEL_CLOUD_FILTER) { + i40evf_del_cloud_filter(adapter); + goto watchdog_done; + } + schedule_delayed_work(&adapter->client_task, msecs_to_jiffies(5)); if (adapter->state == __I40EVF_RUNNING) @@ -1735,6 +1795,7 @@ static void i40evf_disable_vf(struct i40evf_adapter *adapter) { struct i40evf_mac_filter *f, *ftmp; struct i40evf_vlan_filter *fv, *fvtmp; + struct i40evf_cloud_filter *cf, *cftmp; adapter->flags |= I40EVF_FLAG_PF_COMMS_FAILED; @@ -1756,7 +1817,7 @@ static void i40evf_disable_vf(struct i40evf_adapter *adapter) spin_lock_bh(&adapter->mac_vlan_list_lock); - /* Delete all of the filters, both MAC and VLAN. */ + /* Delete all of the filters */ list_for_each_entry_safe(f, ftmp, &adapter->mac_filter_list, list) { list_del(&f->list); kfree(f); @@ -1769,6 +1830,14 @@ static void i40evf_disable_vf(struct i40evf_adapter *adapter) spin_unlock_bh(&adapter->mac_vlan_list_lock); + spin_lock_bh(&adapter->cloud_filter_list_lock); + list_for_each_entry_safe(cf, cftmp, &adapter->cloud_filter_list, list) { + list_del(&cf->list); + kfree(cf); + adapter->num_cloud_filters--; + } + spin_unlock_bh(&adapter->cloud_filter_list_lock); + i40evf_free_misc_irq(adapter); i40evf_reset_interrupt_capability(adapter); i40evf_free_queues(adapter); @@ -1798,9 +1867,11 @@ static void i40evf_reset_task(struct work_struct *work) struct i40evf_adapter *adapter = container_of(work, struct i40evf_adapter, reset_task); + struct virtchnl_vf_resource *vfres = adapter->vf_res; struct net_device *netdev = adapter->netdev; struct i40e_hw *hw = &adapter->hw; struct i40evf_vlan_filter *vlf; + struct i40evf_cloud_filter *cf; struct i40evf_mac_filter *f; u32 reg_val; int i = 0, err; @@ -1893,6 +1964,7 @@ continue_reset: i40evf_free_all_rx_resources(adapter); i40evf_free_all_tx_resources(adapter); + adapter->flags |= I40EVF_FLAG_QUEUES_DISABLED; /* kill and reinit the admin queue */ i40evf_shutdown_adminq(hw); adapter->current_op = VIRTCHNL_OP_UNKNOWN; @@ -1924,8 +1996,19 @@ continue_reset: spin_unlock_bh(&adapter->mac_vlan_list_lock); + /* check if TCs are running and re-add all cloud filters */ + spin_lock_bh(&adapter->cloud_filter_list_lock); + if ((vfres->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_ADQ) && + adapter->num_tc) { + list_for_each_entry(cf, &adapter->cloud_filter_list, list) { + cf->add = true; + } + } + spin_unlock_bh(&adapter->cloud_filter_list_lock); + adapter->aq_required |= I40EVF_FLAG_AQ_ADD_MAC_FILTER; adapter->aq_required |= I40EVF_FLAG_AQ_ADD_VLAN_FILTER; + adapter->aq_required |= I40EVF_FLAG_AQ_ADD_CLOUD_FILTER; i40evf_misc_irq_enable(adapter); mod_timer(&adapter->watchdog_timer, jiffies + 2); @@ -2191,6 +2274,713 @@ void i40evf_free_all_rx_resources(struct i40evf_adapter *adapter) } /** + * i40evf_validate_tx_bandwidth - validate the max Tx bandwidth + * @adapter: board private structure + * @max_tx_rate: max Tx bw for a tc + **/ +static int i40evf_validate_tx_bandwidth(struct i40evf_adapter *adapter, + u64 max_tx_rate) +{ + int speed = 0, ret = 0; + + switch (adapter->link_speed) { + case I40E_LINK_SPEED_40GB: + speed = 40000; + break; + case I40E_LINK_SPEED_25GB: + speed = 25000; + break; + case I40E_LINK_SPEED_20GB: + speed = 20000; + break; + case I40E_LINK_SPEED_10GB: + speed = 10000; + break; + case I40E_LINK_SPEED_1GB: + speed = 1000; + break; + case I40E_LINK_SPEED_100MB: + speed = 100; + break; + default: + break; + } + + if (max_tx_rate > speed) { + dev_err(&adapter->pdev->dev, + "Invalid tx rate specified\n"); + ret = -EINVAL; + } + + return ret; +} + +/** + * i40evf_validate_channel_config - validate queue mapping info + * @adapter: board private structure + * @mqprio_qopt: queue parameters + * + * This function validates if the config provided by the user to + * configure queue channels is valid or not. Returns 0 on a valid + * config. + **/ +static int i40evf_validate_ch_config(struct i40evf_adapter *adapter, + struct tc_mqprio_qopt_offload *mqprio_qopt) +{ + u64 total_max_rate = 0; + int i, num_qps = 0; + u64 tx_rate = 0; + int ret = 0; + + if (mqprio_qopt->qopt.num_tc > I40EVF_MAX_TRAFFIC_CLASS || + mqprio_qopt->qopt.num_tc < 1) + return -EINVAL; + + for (i = 0; i <= mqprio_qopt->qopt.num_tc - 1; i++) { + if (!mqprio_qopt->qopt.count[i] || + mqprio_qopt->qopt.offset[i] != num_qps) + return -EINVAL; + if (mqprio_qopt->min_rate[i]) { + dev_err(&adapter->pdev->dev, + "Invalid min tx rate (greater than 0) specified\n"); + return -EINVAL; + } + /*convert to Mbps */ + tx_rate = div_u64(mqprio_qopt->max_rate[i], + I40EVF_MBPS_DIVISOR); + total_max_rate += tx_rate; + num_qps += mqprio_qopt->qopt.count[i]; + } + if (num_qps > MAX_QUEUES) + return -EINVAL; + + ret = i40evf_validate_tx_bandwidth(adapter, total_max_rate); + return ret; +} + +/** + * i40evf_del_all_cloud_filters - delete all cloud filters + * on the traffic classes + **/ +static void i40evf_del_all_cloud_filters(struct i40evf_adapter *adapter) +{ + struct i40evf_cloud_filter *cf, *cftmp; + + spin_lock_bh(&adapter->cloud_filter_list_lock); + list_for_each_entry_safe(cf, cftmp, &adapter->cloud_filter_list, + list) { + list_del(&cf->list); + kfree(cf); + adapter->num_cloud_filters--; + } + spin_unlock_bh(&adapter->cloud_filter_list_lock); +} + +/** + * __i40evf_setup_tc - configure multiple traffic classes + * @netdev: network interface device structure + * @type_date: tc offload data + * + * This function processes the config information provided by the + * user to configure traffic classes/queue channels and packages the + * information to request the PF to setup traffic classes. + * + * Returns 0 on success. + **/ +static int __i40evf_setup_tc(struct net_device *netdev, void *type_data) +{ + struct tc_mqprio_qopt_offload *mqprio_qopt = type_data; + struct i40evf_adapter *adapter = netdev_priv(netdev); + struct virtchnl_vf_resource *vfres = adapter->vf_res; + u8 num_tc = 0, total_qps = 0; + int ret = 0, netdev_tc = 0; + u64 max_tx_rate; + u16 mode; + int i; + + num_tc = mqprio_qopt->qopt.num_tc; + mode = mqprio_qopt->mode; + + /* delete queue_channel */ + if (!mqprio_qopt->qopt.hw) { + if (adapter->ch_config.state == __I40EVF_TC_RUNNING) { + /* reset the tc configuration */ + netdev_reset_tc(netdev); + adapter->num_tc = 0; + netif_tx_stop_all_queues(netdev); + netif_tx_disable(netdev); + i40evf_del_all_cloud_filters(adapter); + adapter->aq_required = I40EVF_FLAG_AQ_DISABLE_CHANNELS; + goto exit; + } else { + return -EINVAL; + } + } + + /* add queue channel */ + if (mode == TC_MQPRIO_MODE_CHANNEL) { + if (!(vfres->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_ADQ)) { + dev_err(&adapter->pdev->dev, "ADq not supported\n"); + return -EOPNOTSUPP; + } + if (adapter->ch_config.state != __I40EVF_TC_INVALID) { + dev_err(&adapter->pdev->dev, "TC configuration already exists\n"); + return -EINVAL; + } + + ret = i40evf_validate_ch_config(adapter, mqprio_qopt); + if (ret) + return ret; + /* Return if same TC config is requested */ + if (adapter->num_tc == num_tc) + return 0; + adapter->num_tc = num_tc; + + for (i = 0; i < I40EVF_MAX_TRAFFIC_CLASS; i++) { + if (i < num_tc) { + adapter->ch_config.ch_info[i].count = + mqprio_qopt->qopt.count[i]; + adapter->ch_config.ch_info[i].offset = + mqprio_qopt->qopt.offset[i]; + total_qps += mqprio_qopt->qopt.count[i]; + max_tx_rate = mqprio_qopt->max_rate[i]; + /* convert to Mbps */ + max_tx_rate = div_u64(max_tx_rate, + I40EVF_MBPS_DIVISOR); + adapter->ch_config.ch_info[i].max_tx_rate = + max_tx_rate; + } else { + adapter->ch_config.ch_info[i].count = 1; + adapter->ch_config.ch_info[i].offset = 0; + } + } + adapter->ch_config.total_qps = total_qps; + netif_tx_stop_all_queues(netdev); + netif_tx_disable(netdev); + adapter->aq_required |= I40EVF_FLAG_AQ_ENABLE_CHANNELS; + netdev_reset_tc(netdev); + /* Report the tc mapping up the stack */ + netdev_set_num_tc(adapter->netdev, num_tc); + for (i = 0; i < I40EVF_MAX_TRAFFIC_CLASS; i++) { + u16 qcount = mqprio_qopt->qopt.count[i]; + u16 qoffset = mqprio_qopt->qopt.offset[i]; + + if (i < num_tc) + netdev_set_tc_queue(netdev, netdev_tc++, qcount, + qoffset); + } + } +exit: + return ret; +} + +/** + * i40evf_parse_cls_flower - Parse tc flower filters provided by kernel + * @adapter: board private structure + * @cls_flower: pointer to struct tc_cls_flower_offload + * @filter: pointer to cloud filter structure + */ +static int i40evf_parse_cls_flower(struct i40evf_adapter *adapter, + struct tc_cls_flower_offload *f, + struct i40evf_cloud_filter *filter) +{ + u16 n_proto_mask = 0; + u16 n_proto_key = 0; + u8 field_flags = 0; + u16 addr_type = 0; + u16 n_proto = 0; + int i = 0; + struct virtchnl_filter *vf = &filter->f; + + if (f->dissector->used_keys & + ~(BIT(FLOW_DISSECTOR_KEY_CONTROL) | + BIT(FLOW_DISSECTOR_KEY_BASIC) | + BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS) | + BIT(FLOW_DISSECTOR_KEY_VLAN) | + BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS) | + BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS) | + BIT(FLOW_DISSECTOR_KEY_PORTS) | + BIT(FLOW_DISSECTOR_KEY_ENC_KEYID))) { + dev_err(&adapter->pdev->dev, "Unsupported key used: 0x%x\n", + f->dissector->used_keys); + return -EOPNOTSUPP; + } + + if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ENC_KEYID)) { + struct flow_dissector_key_keyid *mask = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_ENC_KEYID, + f->mask); + + if (mask->keyid != 0) + field_flags |= I40EVF_CLOUD_FIELD_TEN_ID; + } + + if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_BASIC)) { + struct flow_dissector_key_basic *key = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_BASIC, + f->key); + + struct flow_dissector_key_basic *mask = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_BASIC, + f->mask); + n_proto_key = ntohs(key->n_proto); + n_proto_mask = ntohs(mask->n_proto); + + if (n_proto_key == ETH_P_ALL) { + n_proto_key = 0; + n_proto_mask = 0; + } + n_proto = n_proto_key & n_proto_mask; + if (n_proto != ETH_P_IP && n_proto != ETH_P_IPV6) + return -EINVAL; + if (n_proto == ETH_P_IPV6) { + /* specify flow type as TCP IPv6 */ + vf->flow_type = VIRTCHNL_TCP_V6_FLOW; + } + + if (key->ip_proto != IPPROTO_TCP) { + dev_info(&adapter->pdev->dev, "Only TCP transport is supported\n"); + return -EINVAL; + } + } + + if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ETH_ADDRS)) { + struct flow_dissector_key_eth_addrs *key = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_ETH_ADDRS, + f->key); + + struct flow_dissector_key_eth_addrs *mask = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_ETH_ADDRS, + f->mask); + /* use is_broadcast and is_zero to check for all 0xf or 0 */ + if (!is_zero_ether_addr(mask->dst)) { + if (is_broadcast_ether_addr(mask->dst)) { + field_flags |= I40EVF_CLOUD_FIELD_OMAC; + } else { + dev_err(&adapter->pdev->dev, "Bad ether dest mask %pM\n", + mask->dst); + return I40E_ERR_CONFIG; + } + } + + if (!is_zero_ether_addr(mask->src)) { + if (is_broadcast_ether_addr(mask->src)) { + field_flags |= I40EVF_CLOUD_FIELD_IMAC; + } else { + dev_err(&adapter->pdev->dev, "Bad ether src mask %pM\n", + mask->src); + return I40E_ERR_CONFIG; + } + } + + if (!is_zero_ether_addr(key->dst)) + if (is_valid_ether_addr(key->dst) || + is_multicast_ether_addr(key->dst)) { + /* set the mask if a valid dst_mac address */ + for (i = 0; i < ETH_ALEN; i++) + vf->mask.tcp_spec.dst_mac[i] |= 0xff; + ether_addr_copy(vf->data.tcp_spec.dst_mac, + key->dst); + } + + if (!is_zero_ether_addr(key->src)) + if (is_valid_ether_addr(key->src) || + is_multicast_ether_addr(key->src)) { + /* set the mask if a valid dst_mac address */ + for (i = 0; i < ETH_ALEN; i++) + vf->mask.tcp_spec.src_mac[i] |= 0xff; + ether_addr_copy(vf->data.tcp_spec.src_mac, + key->src); + } + } + + if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_VLAN)) { + struct flow_dissector_key_vlan *key = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_VLAN, + f->key); + struct flow_dissector_key_vlan *mask = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_VLAN, + f->mask); + + if (mask->vlan_id) { + if (mask->vlan_id == VLAN_VID_MASK) { + field_flags |= I40EVF_CLOUD_FIELD_IVLAN; + } else { + dev_err(&adapter->pdev->dev, "Bad vlan mask %u\n", + mask->vlan_id); + return I40E_ERR_CONFIG; + } + } + vf->mask.tcp_spec.vlan_id |= cpu_to_be16(0xffff); + vf->data.tcp_spec.vlan_id = cpu_to_be16(key->vlan_id); + } + + if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_CONTROL)) { + struct flow_dissector_key_control *key = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_CONTROL, + f->key); + + addr_type = key->addr_type; + } + + if (addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) { + struct flow_dissector_key_ipv4_addrs *key = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_IPV4_ADDRS, + f->key); + struct flow_dissector_key_ipv4_addrs *mask = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_IPV4_ADDRS, + f->mask); + + if (mask->dst) { + if (mask->dst == cpu_to_be32(0xffffffff)) { + field_flags |= I40EVF_CLOUD_FIELD_IIP; + } else { + dev_err(&adapter->pdev->dev, "Bad ip dst mask 0x%08x\n", + be32_to_cpu(mask->dst)); + return I40E_ERR_CONFIG; + } + } + + if (mask->src) { + if (mask->src == cpu_to_be32(0xffffffff)) { + field_flags |= I40EVF_CLOUD_FIELD_IIP; + } else { + dev_err(&adapter->pdev->dev, "Bad ip src mask 0x%08x\n", + be32_to_cpu(mask->dst)); + return I40E_ERR_CONFIG; + } + } + + if (field_flags & I40EVF_CLOUD_FIELD_TEN_ID) { + dev_info(&adapter->pdev->dev, "Tenant id not allowed for ip filter\n"); + return I40E_ERR_CONFIG; + } + if (key->dst) { + vf->mask.tcp_spec.dst_ip[0] |= cpu_to_be32(0xffffffff); + vf->data.tcp_spec.dst_ip[0] = key->dst; + } + if (key->src) { + vf->mask.tcp_spec.src_ip[0] |= cpu_to_be32(0xffffffff); + vf->data.tcp_spec.src_ip[0] = key->src; + } + } + + if (addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS) { + struct flow_dissector_key_ipv6_addrs *key = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_IPV6_ADDRS, + f->key); + struct flow_dissector_key_ipv6_addrs *mask = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_IPV6_ADDRS, + f->mask); + + /* validate mask, make sure it is not IPV6_ADDR_ANY */ + if (ipv6_addr_any(&mask->dst)) { + dev_err(&adapter->pdev->dev, "Bad ipv6 dst mask 0x%02x\n", + IPV6_ADDR_ANY); + return I40E_ERR_CONFIG; + } + + /* src and dest IPv6 address should not be LOOPBACK + * (0:0:0:0:0:0:0:1) which can be represented as ::1 + */ + if (ipv6_addr_loopback(&key->dst) || + ipv6_addr_loopback(&key->src)) { + dev_err(&adapter->pdev->dev, + "ipv6 addr should not be loopback\n"); + return I40E_ERR_CONFIG; + } + if (!ipv6_addr_any(&mask->dst) || !ipv6_addr_any(&mask->src)) + field_flags |= I40EVF_CLOUD_FIELD_IIP; + + for (i = 0; i < 4; i++) + vf->mask.tcp_spec.dst_ip[i] |= cpu_to_be32(0xffffffff); + memcpy(&vf->data.tcp_spec.dst_ip, &key->dst.s6_addr32, + sizeof(vf->data.tcp_spec.dst_ip)); + for (i = 0; i < 4; i++) + vf->mask.tcp_spec.src_ip[i] |= cpu_to_be32(0xffffffff); + memcpy(&vf->data.tcp_spec.src_ip, &key->src.s6_addr32, + sizeof(vf->data.tcp_spec.src_ip)); + } + if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_PORTS)) { + struct flow_dissector_key_ports *key = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_PORTS, + f->key); + struct flow_dissector_key_ports *mask = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_PORTS, + f->mask); + + if (mask->src) { + if (mask->src == cpu_to_be16(0xffff)) { + field_flags |= I40EVF_CLOUD_FIELD_IIP; + } else { + dev_err(&adapter->pdev->dev, "Bad src port mask %u\n", + be16_to_cpu(mask->src)); + return I40E_ERR_CONFIG; + } + } + + if (mask->dst) { + if (mask->dst == cpu_to_be16(0xffff)) { + field_flags |= I40EVF_CLOUD_FIELD_IIP; + } else { + dev_err(&adapter->pdev->dev, "Bad dst port mask %u\n", + be16_to_cpu(mask->dst)); + return I40E_ERR_CONFIG; + } + } + if (key->dst) { + vf->mask.tcp_spec.dst_port |= cpu_to_be16(0xffff); + vf->data.tcp_spec.dst_port = key->dst; + } + + if (key->src) { + vf->mask.tcp_spec.src_port |= cpu_to_be16(0xffff); + vf->data.tcp_spec.src_port = key->dst; + } + } + vf->field_flags = field_flags; + + return 0; +} + +/** + * i40evf_handle_tclass - Forward to a traffic class on the device + * @adapter: board private structure + * @tc: traffic class index on the device + * @filter: pointer to cloud filter structure + */ +static int i40evf_handle_tclass(struct i40evf_adapter *adapter, u32 tc, + struct i40evf_cloud_filter *filter) +{ + if (tc == 0) + return 0; + if (tc < adapter->num_tc) { + if (!filter->f.data.tcp_spec.dst_port) { + dev_err(&adapter->pdev->dev, + "Specify destination port to redirect to traffic class other than TC0\n"); + return -EINVAL; + } + } + /* redirect to a traffic class on the same device */ + filter->f.action = VIRTCHNL_ACTION_TC_REDIRECT; + filter->f.action_meta = tc; + return 0; +} + +/** + * i40evf_configure_clsflower - Add tc flower filters + * @adapter: board private structure + * @cls_flower: Pointer to struct tc_cls_flower_offload + */ +static int i40evf_configure_clsflower(struct i40evf_adapter *adapter, + struct tc_cls_flower_offload *cls_flower) +{ + int tc = tc_classid_to_hwtc(adapter->netdev, cls_flower->classid); + struct i40evf_cloud_filter *filter = NULL; + int err = 0, count = 50; + + while (test_and_set_bit(__I40EVF_IN_CRITICAL_TASK, + &adapter->crit_section)) { + udelay(1); + if (--count == 0) + return -EINVAL; + } + + if (tc < 0) { + dev_err(&adapter->pdev->dev, "Invalid traffic class\n"); + return -EINVAL; + } + + filter = kzalloc(sizeof(*filter), GFP_KERNEL); + if (!filter) { + err = -ENOMEM; + goto clearout; + } + filter->cookie = cls_flower->cookie; + + /* set the mask to all zeroes to begin with */ + memset(&filter->f.mask.tcp_spec, 0, sizeof(struct virtchnl_l4_spec)); + /* start out with flow type and eth type IPv4 to begin with */ + filter->f.flow_type = VIRTCHNL_TCP_V4_FLOW; + err = i40evf_parse_cls_flower(adapter, cls_flower, filter); + if (err < 0) + goto err; + + err = i40evf_handle_tclass(adapter, tc, filter); + if (err < 0) + goto err; + + /* add filter to the list */ + spin_lock_bh(&adapter->cloud_filter_list_lock); + list_add_tail(&filter->list, &adapter->cloud_filter_list); + adapter->num_cloud_filters++; + filter->add = true; + adapter->aq_required |= I40EVF_FLAG_AQ_ADD_CLOUD_FILTER; + spin_unlock_bh(&adapter->cloud_filter_list_lock); +err: + if (err) + kfree(filter); +clearout: + clear_bit(__I40EVF_IN_CRITICAL_TASK, &adapter->crit_section); + return err; +} + +/* i40evf_find_cf - Find the cloud filter in the list + * @adapter: Board private structure + * @cookie: filter specific cookie + * + * Returns ptr to the filter object or NULL. Must be called while holding the + * cloud_filter_list_lock. + */ +static struct i40evf_cloud_filter *i40evf_find_cf(struct i40evf_adapter *adapter, + unsigned long *cookie) +{ + struct i40evf_cloud_filter *filter = NULL; + + if (!cookie) + return NULL; + + list_for_each_entry(filter, &adapter->cloud_filter_list, list) { + if (!memcmp(cookie, &filter->cookie, sizeof(filter->cookie))) + return filter; + } + return NULL; +} + +/** + * i40evf_delete_clsflower - Remove tc flower filters + * @adapter: board private structure + * @cls_flower: Pointer to struct tc_cls_flower_offload + */ +static int i40evf_delete_clsflower(struct i40evf_adapter *adapter, + struct tc_cls_flower_offload *cls_flower) +{ + struct i40evf_cloud_filter *filter = NULL; + int err = 0; + + spin_lock_bh(&adapter->cloud_filter_list_lock); + filter = i40evf_find_cf(adapter, &cls_flower->cookie); + if (filter) { + filter->del = true; + adapter->aq_required |= I40EVF_FLAG_AQ_DEL_CLOUD_FILTER; + } else { + err = -EINVAL; + } + spin_unlock_bh(&adapter->cloud_filter_list_lock); + + return err; +} + +/** + * i40evf_setup_tc_cls_flower - flower classifier offloads + * @netdev: net device to configure + * @type_data: offload data + */ +static int i40evf_setup_tc_cls_flower(struct i40evf_adapter *adapter, + struct tc_cls_flower_offload *cls_flower) +{ + if (cls_flower->common.chain_index) + return -EOPNOTSUPP; + + switch (cls_flower->command) { + case TC_CLSFLOWER_REPLACE: + return i40evf_configure_clsflower(adapter, cls_flower); + case TC_CLSFLOWER_DESTROY: + return i40evf_delete_clsflower(adapter, cls_flower); + case TC_CLSFLOWER_STATS: + return -EOPNOTSUPP; + default: + return -EINVAL; + } +} + +/** + * i40evf_setup_tc_block_cb - block callback for tc + * @type: type of offload + * @type_data: offload data + * @cb_priv: + * + * This function is the block callback for traffic classes + **/ +static int i40evf_setup_tc_block_cb(enum tc_setup_type type, void *type_data, + void *cb_priv) +{ + switch (type) { + case TC_SETUP_CLSFLOWER: + return i40evf_setup_tc_cls_flower(cb_priv, type_data); + default: + return -EOPNOTSUPP; + } +} + +/** + * i40evf_setup_tc_block - register callbacks for tc + * @netdev: network interface device structure + * @f: tc offload data + * + * This function registers block callbacks for tc + * offloads + **/ +static int i40evf_setup_tc_block(struct net_device *dev, + struct tc_block_offload *f) +{ + struct i40evf_adapter *adapter = netdev_priv(dev); + + if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS) + return -EOPNOTSUPP; + + switch (f->command) { + case TC_BLOCK_BIND: + return tcf_block_cb_register(f->block, i40evf_setup_tc_block_cb, + adapter, adapter); + case TC_BLOCK_UNBIND: + tcf_block_cb_unregister(f->block, i40evf_setup_tc_block_cb, + adapter); + return 0; + default: + return -EOPNOTSUPP; + } +} + +/** + * i40evf_setup_tc - configure multiple traffic classes + * @netdev: network interface device structure + * @type: type of offload + * @type_date: tc offload data + * + * This function is the callback to ndo_setup_tc in the + * netdev_ops. + * + * Returns 0 on success + **/ +static int i40evf_setup_tc(struct net_device *netdev, enum tc_setup_type type, + void *type_data) +{ + switch (type) { + case TC_SETUP_QDISC_MQPRIO: + return __i40evf_setup_tc(netdev, type_data); + case TC_SETUP_BLOCK: + return i40evf_setup_tc_block(netdev, type_data); + default: + return -EOPNOTSUPP; + } +} + +/** * i40evf_open - Called when a network interface is made active * @netdev: network interface device structure * @@ -2236,7 +3026,12 @@ static int i40evf_open(struct net_device *netdev) if (err) goto err_req_irq; + spin_lock_bh(&adapter->mac_vlan_list_lock); + i40evf_add_filter(adapter, adapter->hw.mac.addr); + + spin_unlock_bh(&adapter->mac_vlan_list_lock); + i40evf_configure(adapter); i40evf_up_complete(adapter); @@ -2457,6 +3252,7 @@ static const struct net_device_ops i40evf_netdev_ops = { #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = i40evf_netpoll, #endif + .ndo_setup_tc = i40evf_setup_tc, }; /** @@ -2571,6 +3367,9 @@ int i40evf_process_config(struct i40evf_adapter *adapter) if (vfres->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_VLAN) hw_features |= (NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX); + /* Enable cloud filter if ADQ is supported */ + if (vfres->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_ADQ) + hw_features |= NETIF_F_HW_TC; netdev->hw_features |= hw_features; @@ -2938,9 +3737,11 @@ static int i40evf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) mutex_init(&hw->aq.arq_mutex); spin_lock_init(&adapter->mac_vlan_list_lock); + spin_lock_init(&adapter->cloud_filter_list_lock); INIT_LIST_HEAD(&adapter->mac_filter_list); INIT_LIST_HEAD(&adapter->vlan_filter_list); + INIT_LIST_HEAD(&adapter->cloud_filter_list); INIT_WORK(&adapter->reset_task, i40evf_reset_task); INIT_WORK(&adapter->adminq_task, i40evf_adminq_task); @@ -3065,7 +3866,9 @@ static void i40evf_remove(struct pci_dev *pdev) { struct net_device *netdev = pci_get_drvdata(pdev); struct i40evf_adapter *adapter = netdev_priv(netdev); + struct i40evf_vlan_filter *vlf, *vlftmp; struct i40evf_mac_filter *f, *ftmp; + struct i40evf_cloud_filter *cf, *cftmp; struct i40e_hw *hw = &adapter->hw; int err; /* Indicate we are in remove and not to run reset_task */ @@ -3087,6 +3890,7 @@ static void i40evf_remove(struct pci_dev *pdev) /* Shut down all the garbage mashers on the detention level */ adapter->state = __I40EVF_REMOVE; adapter->aq_required = 0; + adapter->flags &= ~I40EVF_FLAG_REINIT_ITR_NEEDED; i40evf_request_reset(adapter); msleep(50); /* If the FW isn't responding, kick it once, but only once. */ @@ -3127,13 +3931,21 @@ static void i40evf_remove(struct pci_dev *pdev) list_del(&f->list); kfree(f); } - list_for_each_entry_safe(f, ftmp, &adapter->vlan_filter_list, list) { - list_del(&f->list); - kfree(f); + list_for_each_entry_safe(vlf, vlftmp, &adapter->vlan_filter_list, + list) { + list_del(&vlf->list); + kfree(vlf); } spin_unlock_bh(&adapter->mac_vlan_list_lock); + spin_lock_bh(&adapter->cloud_filter_list_lock); + list_for_each_entry_safe(cf, cftmp, &adapter->cloud_filter_list, list) { + list_del(&cf->list); + kfree(cf); + } + spin_unlock_bh(&adapter->cloud_filter_list_lock); + free_netdev(netdev); pci_disable_pcie_error_reporting(pdev); diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c b/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c index 50ce0d6c09ef..3c76c817ca1a 100644 --- a/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c +++ b/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c @@ -161,7 +161,8 @@ int i40evf_send_vf_config_msg(struct i40evf_adapter *adapter) VIRTCHNL_VF_OFFLOAD_RSS_PCTYPE_V2 | VIRTCHNL_VF_OFFLOAD_ENCAP | VIRTCHNL_VF_OFFLOAD_ENCAP_CSUM | - VIRTCHNL_VF_OFFLOAD_REQ_QUEUES; + VIRTCHNL_VF_OFFLOAD_REQ_QUEUES | + VIRTCHNL_VF_OFFLOAD_ADQ; adapter->current_op = VIRTCHNL_OP_GET_VF_RESOURCES; adapter->aq_required &= ~I40EVF_FLAG_AQ_GET_CONFIG; @@ -344,6 +345,7 @@ void i40evf_disable_queues(struct i40evf_adapter *adapter) void i40evf_map_queues(struct i40evf_adapter *adapter) { struct virtchnl_irq_map_info *vimi; + struct virtchnl_vector_map *vecmap; int v_idx, q_vectors, len; struct i40e_q_vector *q_vector; @@ -367,17 +369,22 @@ void i40evf_map_queues(struct i40evf_adapter *adapter) vimi->num_vectors = adapter->num_msix_vectors; /* Queue vectors first */ for (v_idx = 0; v_idx < q_vectors; v_idx++) { - q_vector = adapter->q_vectors + v_idx; - vimi->vecmap[v_idx].vsi_id = adapter->vsi_res->vsi_id; - vimi->vecmap[v_idx].vector_id = v_idx + NONQ_VECS; - vimi->vecmap[v_idx].txq_map = q_vector->ring_mask; - vimi->vecmap[v_idx].rxq_map = q_vector->ring_mask; + q_vector = &adapter->q_vectors[v_idx]; + vecmap = &vimi->vecmap[v_idx]; + + vecmap->vsi_id = adapter->vsi_res->vsi_id; + vecmap->vector_id = v_idx + NONQ_VECS; + vecmap->txq_map = q_vector->ring_mask; + vecmap->rxq_map = q_vector->ring_mask; + vecmap->rxitr_idx = I40E_RX_ITR; + vecmap->txitr_idx = I40E_TX_ITR; } /* Misc vector last - this is only for AdminQ messages */ - vimi->vecmap[v_idx].vsi_id = adapter->vsi_res->vsi_id; - vimi->vecmap[v_idx].vector_id = 0; - vimi->vecmap[v_idx].txq_map = 0; - vimi->vecmap[v_idx].rxq_map = 0; + vecmap = &vimi->vecmap[v_idx]; + vecmap->vsi_id = adapter->vsi_res->vsi_id; + vecmap->vector_id = 0; + vecmap->txq_map = 0; + vecmap->rxq_map = 0; adapter->aq_required &= ~I40EVF_FLAG_AQ_MAP_VECTORS; i40evf_send_pf_msg(adapter, VIRTCHNL_OP_CONFIG_IRQ_MAP, @@ -459,7 +466,7 @@ void i40evf_add_ether_addrs(struct i40evf_adapter *adapter) more = true; } - veal = kzalloc(len, GFP_KERNEL); + veal = kzalloc(len, GFP_ATOMIC); if (!veal) { spin_unlock_bh(&adapter->mac_vlan_list_lock); return; @@ -532,7 +539,7 @@ void i40evf_del_ether_addrs(struct i40evf_adapter *adapter) (count * sizeof(struct virtchnl_ether_addr)); more = true; } - veal = kzalloc(len, GFP_KERNEL); + veal = kzalloc(len, GFP_ATOMIC); if (!veal) { spin_unlock_bh(&adapter->mac_vlan_list_lock); return; @@ -606,7 +613,7 @@ void i40evf_add_vlans(struct i40evf_adapter *adapter) (count * sizeof(u16)); more = true; } - vvfl = kzalloc(len, GFP_KERNEL); + vvfl = kzalloc(len, GFP_ATOMIC); if (!vvfl) { spin_unlock_bh(&adapter->mac_vlan_list_lock); return; @@ -678,7 +685,7 @@ void i40evf_del_vlans(struct i40evf_adapter *adapter) (count * sizeof(u16)); more = true; } - vvfl = kzalloc(len, GFP_KERNEL); + vvfl = kzalloc(len, GFP_ATOMIC); if (!vvfl) { spin_unlock_bh(&adapter->mac_vlan_list_lock); return; @@ -967,6 +974,205 @@ static void i40evf_print_link_message(struct i40evf_adapter *adapter) } /** + * i40evf_enable_channel + * @adapter: adapter structure + * + * Request that the PF enable channels as specified by + * the user via tc tool. + **/ +void i40evf_enable_channels(struct i40evf_adapter *adapter) +{ + struct virtchnl_tc_info *vti = NULL; + u16 len; + int i; + + if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) { + /* bail because we already have a command pending */ + dev_err(&adapter->pdev->dev, "Cannot configure mqprio, command %d pending\n", + adapter->current_op); + return; + } + + len = (adapter->num_tc * sizeof(struct virtchnl_channel_info)) + + sizeof(struct virtchnl_tc_info); + + vti = kzalloc(len, GFP_KERNEL); + if (!vti) + return; + vti->num_tc = adapter->num_tc; + for (i = 0; i < vti->num_tc; i++) { + vti->list[i].count = adapter->ch_config.ch_info[i].count; + vti->list[i].offset = adapter->ch_config.ch_info[i].offset; + vti->list[i].pad = 0; + vti->list[i].max_tx_rate = + adapter->ch_config.ch_info[i].max_tx_rate; + } + + adapter->ch_config.state = __I40EVF_TC_RUNNING; + adapter->flags |= I40EVF_FLAG_REINIT_ITR_NEEDED; + adapter->current_op = VIRTCHNL_OP_ENABLE_CHANNELS; + adapter->aq_required &= ~I40EVF_FLAG_AQ_ENABLE_CHANNELS; + i40evf_send_pf_msg(adapter, VIRTCHNL_OP_ENABLE_CHANNELS, + (u8 *)vti, len); + kfree(vti); +} + +/** + * i40evf_disable_channel + * @adapter: adapter structure + * + * Request that the PF disable channels that are configured + **/ +void i40evf_disable_channels(struct i40evf_adapter *adapter) +{ + if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) { + /* bail because we already have a command pending */ + dev_err(&adapter->pdev->dev, "Cannot configure mqprio, command %d pending\n", + adapter->current_op); + return; + } + + adapter->ch_config.state = __I40EVF_TC_INVALID; + adapter->flags |= I40EVF_FLAG_REINIT_ITR_NEEDED; + adapter->current_op = VIRTCHNL_OP_DISABLE_CHANNELS; + adapter->aq_required &= ~I40EVF_FLAG_AQ_DISABLE_CHANNELS; + i40evf_send_pf_msg(adapter, VIRTCHNL_OP_DISABLE_CHANNELS, + NULL, 0); +} + +/** + * i40evf_print_cloud_filter + * @adapter: adapter structure + * @f: cloud filter to print + * + * Print the cloud filter + **/ +static void i40evf_print_cloud_filter(struct i40evf_adapter *adapter, + struct virtchnl_filter *f) +{ + switch (f->flow_type) { + case VIRTCHNL_TCP_V4_FLOW: + dev_info(&adapter->pdev->dev, "dst_mac: %pM src_mac: %pM vlan_id: %hu dst_ip: %pI4 src_ip %pI4 dst_port %hu src_port %hu\n", + &f->data.tcp_spec.dst_mac, + &f->data.tcp_spec.src_mac, + ntohs(f->data.tcp_spec.vlan_id), + &f->data.tcp_spec.dst_ip[0], + &f->data.tcp_spec.src_ip[0], + ntohs(f->data.tcp_spec.dst_port), + ntohs(f->data.tcp_spec.src_port)); + break; + case VIRTCHNL_TCP_V6_FLOW: + dev_info(&adapter->pdev->dev, "dst_mac: %pM src_mac: %pM vlan_id: %hu dst_ip: %pI6 src_ip %pI6 dst_port %hu src_port %hu\n", + &f->data.tcp_spec.dst_mac, + &f->data.tcp_spec.src_mac, + ntohs(f->data.tcp_spec.vlan_id), + &f->data.tcp_spec.dst_ip, + &f->data.tcp_spec.src_ip, + ntohs(f->data.tcp_spec.dst_port), + ntohs(f->data.tcp_spec.src_port)); + break; + } +} + +/** + * i40evf_add_cloud_filter + * @adapter: adapter structure + * + * Request that the PF add cloud filters as specified + * by the user via tc tool. + **/ +void i40evf_add_cloud_filter(struct i40evf_adapter *adapter) +{ + struct i40evf_cloud_filter *cf; + struct virtchnl_filter *f; + int len = 0, count = 0; + + if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) { + /* bail because we already have a command pending */ + dev_err(&adapter->pdev->dev, "Cannot add cloud filter, command %d pending\n", + adapter->current_op); + return; + } + list_for_each_entry(cf, &adapter->cloud_filter_list, list) { + if (cf->add) { + count++; + break; + } + } + if (!count) { + adapter->aq_required &= ~I40EVF_FLAG_AQ_ADD_CLOUD_FILTER; + return; + } + adapter->current_op = VIRTCHNL_OP_ADD_CLOUD_FILTER; + + len = sizeof(struct virtchnl_filter); + f = kzalloc(len, GFP_KERNEL); + if (!f) + return; + + list_for_each_entry(cf, &adapter->cloud_filter_list, list) { + if (cf->add) { + memcpy(f, &cf->f, sizeof(struct virtchnl_filter)); + cf->add = false; + cf->state = __I40EVF_CF_ADD_PENDING; + i40evf_send_pf_msg(adapter, + VIRTCHNL_OP_ADD_CLOUD_FILTER, + (u8 *)f, len); + } + } + kfree(f); +} + +/** + * i40evf_del_cloud_filter + * @adapter: adapter structure + * + * Request that the PF delete cloud filters as specified + * by the user via tc tool. + **/ +void i40evf_del_cloud_filter(struct i40evf_adapter *adapter) +{ + struct i40evf_cloud_filter *cf, *cftmp; + struct virtchnl_filter *f; + int len = 0, count = 0; + + if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) { + /* bail because we already have a command pending */ + dev_err(&adapter->pdev->dev, "Cannot remove cloud filter, command %d pending\n", + adapter->current_op); + return; + } + list_for_each_entry(cf, &adapter->cloud_filter_list, list) { + if (cf->del) { + count++; + break; + } + } + if (!count) { + adapter->aq_required &= ~I40EVF_FLAG_AQ_DEL_CLOUD_FILTER; + return; + } + adapter->current_op = VIRTCHNL_OP_DEL_CLOUD_FILTER; + + len = sizeof(struct virtchnl_filter); + f = kzalloc(len, GFP_KERNEL); + if (!f) + return; + + list_for_each_entry_safe(cf, cftmp, &adapter->cloud_filter_list, list) { + if (cf->del) { + memcpy(f, &cf->f, sizeof(struct virtchnl_filter)); + cf->del = false; + cf->state = __I40EVF_CF_DEL_PENDING; + i40evf_send_pf_msg(adapter, + VIRTCHNL_OP_DEL_CLOUD_FILTER, + (u8 *)f, len); + } + } + kfree(f); +} + +/** * i40evf_request_reset * @adapter: adapter structure * @@ -1011,14 +1217,25 @@ void i40evf_virtchnl_completion(struct i40evf_adapter *adapter, if (adapter->link_up == link_up) break; - /* If we get link up message and start queues before - * our queues are configured it will trigger a TX hang. - * In that case, just ignore the link status message, - * we'll get another one after we enable queues and - * actually prepared to send traffic. - */ - if (link_up && adapter->state != __I40EVF_RUNNING) - break; + if (link_up) { + /* If we get link up message and start queues + * before our queues are configured it will + * trigger a TX hang. In that case, just ignore + * the link status message,we'll get another one + * after we enable queues and actually prepared + * to send traffic. + */ + if (adapter->state != __I40EVF_RUNNING) + break; + + /* For ADq enabled VF, we reconfigure VSIs and + * re-allocate queues. Hence wait till all + * queues are enabled. + */ + if (adapter->flags & + I40EVF_FLAG_QUEUES_DISABLED) + break; + } adapter->link_up = link_up; if (link_up) { @@ -1031,7 +1248,7 @@ void i40evf_virtchnl_completion(struct i40evf_adapter *adapter, i40evf_print_link_message(adapter); break; case VIRTCHNL_EVENT_RESET_IMPENDING: - dev_info(&adapter->pdev->dev, "PF reset warning received\n"); + dev_info(&adapter->pdev->dev, "Reset warning received from the PF\n"); if (!(adapter->flags & I40EVF_FLAG_RESET_PENDING)) { adapter->flags |= I40EVF_FLAG_RESET_PENDING; dev_info(&adapter->pdev->dev, "Scheduling reset task\n"); @@ -1063,6 +1280,57 @@ void i40evf_virtchnl_completion(struct i40evf_adapter *adapter, dev_err(&adapter->pdev->dev, "Failed to delete MAC filter, error %s\n", i40evf_stat_str(&adapter->hw, v_retval)); break; + case VIRTCHNL_OP_ENABLE_CHANNELS: + dev_err(&adapter->pdev->dev, "Failed to configure queue channels, error %s\n", + i40evf_stat_str(&adapter->hw, v_retval)); + adapter->flags &= ~I40EVF_FLAG_REINIT_ITR_NEEDED; + adapter->ch_config.state = __I40EVF_TC_INVALID; + netdev_reset_tc(netdev); + netif_tx_start_all_queues(netdev); + break; + case VIRTCHNL_OP_DISABLE_CHANNELS: + dev_err(&adapter->pdev->dev, "Failed to disable queue channels, error %s\n", + i40evf_stat_str(&adapter->hw, v_retval)); + adapter->flags &= ~I40EVF_FLAG_REINIT_ITR_NEEDED; + adapter->ch_config.state = __I40EVF_TC_RUNNING; + netif_tx_start_all_queues(netdev); + break; + case VIRTCHNL_OP_ADD_CLOUD_FILTER: { + struct i40evf_cloud_filter *cf, *cftmp; + + list_for_each_entry_safe(cf, cftmp, + &adapter->cloud_filter_list, + list) { + if (cf->state == __I40EVF_CF_ADD_PENDING) { + cf->state = __I40EVF_CF_INVALID; + dev_info(&adapter->pdev->dev, "Failed to add cloud filter, error %s\n", + i40evf_stat_str(&adapter->hw, + v_retval)); + i40evf_print_cloud_filter(adapter, + &cf->f); + list_del(&cf->list); + kfree(cf); + adapter->num_cloud_filters--; + } + } + } + break; + case VIRTCHNL_OP_DEL_CLOUD_FILTER: { + struct i40evf_cloud_filter *cf; + + list_for_each_entry(cf, &adapter->cloud_filter_list, + list) { + if (cf->state == __I40EVF_CF_DEL_PENDING) { + cf->state = __I40EVF_CF_ACTIVE; + dev_info(&adapter->pdev->dev, "Failed to del cloud filter, error %s\n", + i40evf_stat_str(&adapter->hw, + v_retval)); + i40evf_print_cloud_filter(adapter, + &cf->f); + } + } + } + break; default: dev_err(&adapter->pdev->dev, "PF returned error %d (%s) to our request %d\n", v_retval, @@ -1102,6 +1370,7 @@ void i40evf_virtchnl_completion(struct i40evf_adapter *adapter, case VIRTCHNL_OP_ENABLE_QUEUES: /* enable transmits */ i40evf_irq_enable(adapter, true); + adapter->flags &= ~I40EVF_FLAG_QUEUES_DISABLED; break; case VIRTCHNL_OP_DISABLE_QUEUES: i40evf_free_all_tx_resources(adapter); @@ -1156,6 +1425,29 @@ void i40evf_virtchnl_completion(struct i40evf_adapter *adapter, } } break; + case VIRTCHNL_OP_ADD_CLOUD_FILTER: { + struct i40evf_cloud_filter *cf; + + list_for_each_entry(cf, &adapter->cloud_filter_list, list) { + if (cf->state == __I40EVF_CF_ADD_PENDING) + cf->state = __I40EVF_CF_ACTIVE; + } + } + break; + case VIRTCHNL_OP_DEL_CLOUD_FILTER: { + struct i40evf_cloud_filter *cf, *cftmp; + + list_for_each_entry_safe(cf, cftmp, &adapter->cloud_filter_list, + list) { + if (cf->state == __I40EVF_CF_DEL_PENDING) { + cf->state = __I40EVF_CF_INVALID; + list_del(&cf->list); + kfree(cf); + adapter->num_cloud_filters--; + } + } + } + break; default: if (adapter->current_op && (v_opcode != adapter->current_op)) dev_warn(&adapter->pdev->dev, "Expected response %d from PF, received %d\n", diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c index 221f15803480..89edb9fae6f0 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c @@ -3059,6 +3059,8 @@ static int ixgbe_set_rxfh(struct net_device *netdev, const u32 *indir, for (i = 0; i < reta_entries; i++) adapter->rss_indir_tbl[i] = indir[i]; + + ixgbe_store_reta(adapter); } /* Fill out the rss hash key */ @@ -3067,8 +3069,6 @@ static int ixgbe_set_rxfh(struct net_device *netdev, const u32 *indir, ixgbe_store_key(adapter); } - ixgbe_store_reta(adapter); - return 0; } diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c index 4242f0213e46..ed4cbe94c355 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c @@ -58,7 +58,6 @@ static bool ixgbe_cache_ring_dcb_sriov(struct ixgbe_adapter *adapter) return false; /* start at VMDq register offset for SR-IOV enabled setups */ - pool = 0; reg_idx = vmdq->offset * __ALIGN_MASK(1, ~vmdq->mask); for (i = 0, pool = 0; i < adapter->num_rx_queues; i++, reg_idx++) { /* If we are greater than indices move to next pool */ diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 9fc063af233c..85369423452d 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -7711,7 +7711,8 @@ static void ixgbe_service_task(struct work_struct *work) if (test_bit(__IXGBE_PTP_RUNNING, &adapter->state)) { ixgbe_ptp_overflow_check(adapter); - ixgbe_ptp_rx_hang(adapter); + if (adapter->flags & IXGBE_FLAG_RX_HWTSTAMP_IN_REGISTER) + ixgbe_ptp_rx_hang(adapter); ixgbe_ptp_tx_hang(adapter); } diff --git a/drivers/net/ethernet/intel/ixgbevf/ethtool.c b/drivers/net/ethernet/intel/ixgbevf/ethtool.c index 4400e49090b4..e7623fed42da 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ethtool.c +++ b/drivers/net/ethernet/intel/ixgbevf/ethtool.c @@ -94,6 +94,13 @@ static const char ixgbe_gstrings_test[][ETH_GSTRING_LEN] = { #define IXGBEVF_TEST_LEN (sizeof(ixgbe_gstrings_test) / ETH_GSTRING_LEN) +static const char ixgbevf_priv_flags_strings[][ETH_GSTRING_LEN] = { +#define IXGBEVF_PRIV_FLAGS_LEGACY_RX BIT(0) + "legacy-rx", +}; + +#define IXGBEVF_PRIV_FLAGS_STR_LEN ARRAY_SIZE(ixgbevf_priv_flags_strings) + static int ixgbevf_get_link_ksettings(struct net_device *netdev, struct ethtool_link_ksettings *cmd) { @@ -241,6 +248,8 @@ static void ixgbevf_get_drvinfo(struct net_device *netdev, sizeof(drvinfo->version)); strlcpy(drvinfo->bus_info, pci_name(adapter->pdev), sizeof(drvinfo->bus_info)); + + drvinfo->n_priv_flags = IXGBEVF_PRIV_FLAGS_STR_LEN; } static void ixgbevf_get_ringparam(struct net_device *netdev, @@ -392,6 +401,8 @@ static int ixgbevf_get_sset_count(struct net_device *netdev, int stringset) return IXGBEVF_TEST_LEN; case ETH_SS_STATS: return IXGBEVF_STATS_LEN; + case ETH_SS_PRIV_FLAGS: + return IXGBEVF_PRIV_FLAGS_STR_LEN; default: return -EINVAL; } @@ -496,6 +507,10 @@ static void ixgbevf_get_strings(struct net_device *netdev, u32 stringset, p += ETH_GSTRING_LEN; } break; + case ETH_SS_PRIV_FLAGS: + memcpy(data, ixgbevf_priv_flags_strings, + IXGBEVF_PRIV_FLAGS_STR_LEN * ETH_GSTRING_LEN); + break; } } @@ -888,6 +903,37 @@ static int ixgbevf_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key, return err; } +static u32 ixgbevf_get_priv_flags(struct net_device *netdev) +{ + struct ixgbevf_adapter *adapter = netdev_priv(netdev); + u32 priv_flags = 0; + + if (adapter->flags & IXGBEVF_FLAGS_LEGACY_RX) + priv_flags |= IXGBEVF_PRIV_FLAGS_LEGACY_RX; + + return priv_flags; +} + +static int ixgbevf_set_priv_flags(struct net_device *netdev, u32 priv_flags) +{ + struct ixgbevf_adapter *adapter = netdev_priv(netdev); + unsigned int flags = adapter->flags; + + flags &= ~IXGBEVF_FLAGS_LEGACY_RX; + if (priv_flags & IXGBEVF_PRIV_FLAGS_LEGACY_RX) + flags |= IXGBEVF_FLAGS_LEGACY_RX; + + if (flags != adapter->flags) { + adapter->flags = flags; + + /* reset interface to repopulate queues */ + if (netif_running(netdev)) + ixgbevf_reinit_locked(adapter); + } + + return 0; +} + static const struct ethtool_ops ixgbevf_ethtool_ops = { .get_drvinfo = ixgbevf_get_drvinfo, .get_regs_len = ixgbevf_get_regs_len, @@ -909,6 +955,8 @@ static const struct ethtool_ops ixgbevf_ethtool_ops = { .get_rxfh_key_size = ixgbevf_get_rxfh_key_size, .get_rxfh = ixgbevf_get_rxfh, .get_link_ksettings = ixgbevf_get_link_ksettings, + .get_priv_flags = ixgbevf_get_priv_flags, + .set_priv_flags = ixgbevf_set_priv_flags, }; void ixgbevf_set_ethtool_ops(struct net_device *netdev) diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h b/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h index f6952425c87d..f65ca156af2d 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h +++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h @@ -89,19 +89,15 @@ struct ixgbevf_rx_queue_stats { }; enum ixgbevf_ring_state_t { + __IXGBEVF_RX_3K_BUFFER, + __IXGBEVF_RX_BUILD_SKB_ENABLED, __IXGBEVF_TX_DETECT_HANG, __IXGBEVF_HANG_CHECK_ARMED, }; -#define check_for_tx_hang(ring) \ - test_bit(__IXGBEVF_TX_DETECT_HANG, &(ring)->state) -#define set_check_for_tx_hang(ring) \ - set_bit(__IXGBEVF_TX_DETECT_HANG, &(ring)->state) -#define clear_check_for_tx_hang(ring) \ - clear_bit(__IXGBEVF_TX_DETECT_HANG, &(ring)->state) - struct ixgbevf_ring { struct ixgbevf_ring *next; + struct ixgbevf_q_vector *q_vector; /* backpointer to q_vector */ struct net_device *netdev; struct device *dev; void *desc; /* descriptor ring memory */ @@ -133,7 +129,7 @@ struct ixgbevf_ring { */ u16 reg_idx; int queue_index; /* needed for multiqueue queue management */ -}; +} ____cacheline_internodealigned_in_smp; /* How many Rx Buffers do we bundle into one write to the hardware ? */ #define IXGBEVF_RX_BUFFER_WRITE 16 /* Must be power of 2 */ @@ -156,12 +152,20 @@ struct ixgbevf_ring { /* Supported Rx Buffer Sizes */ #define IXGBEVF_RXBUFFER_256 256 /* Used for packet split */ #define IXGBEVF_RXBUFFER_2048 2048 +#define IXGBEVF_RXBUFFER_3072 3072 #define IXGBEVF_RX_HDR_SIZE IXGBEVF_RXBUFFER_256 -#define IXGBEVF_RX_BUFSZ IXGBEVF_RXBUFFER_2048 #define MAXIMUM_ETHERNET_VLAN_SIZE (VLAN_ETH_FRAME_LEN + ETH_FCS_LEN) +#define IXGBEVF_SKB_PAD (NET_SKB_PAD + NET_IP_ALIGN) +#if (PAGE_SIZE < 8192) +#define IXGBEVF_MAX_FRAME_BUILD_SKB \ + (SKB_WITH_OVERHEAD(IXGBEVF_RXBUFFER_2048) - IXGBEVF_SKB_PAD) +#else +#define IXGBEVF_MAX_FRAME_BUILD_SKB IXGBEVF_RXBUFFER_2048 +#endif + #define IXGBE_TX_FLAGS_CSUM BIT(0) #define IXGBE_TX_FLAGS_VLAN BIT(1) #define IXGBE_TX_FLAGS_TSO BIT(2) @@ -170,6 +174,50 @@ struct ixgbevf_ring { #define IXGBE_TX_FLAGS_VLAN_PRIO_MASK 0x0000e000 #define IXGBE_TX_FLAGS_VLAN_SHIFT 16 +#define ring_uses_large_buffer(ring) \ + test_bit(__IXGBEVF_RX_3K_BUFFER, &(ring)->state) +#define set_ring_uses_large_buffer(ring) \ + set_bit(__IXGBEVF_RX_3K_BUFFER, &(ring)->state) +#define clear_ring_uses_large_buffer(ring) \ + clear_bit(__IXGBEVF_RX_3K_BUFFER, &(ring)->state) + +#define ring_uses_build_skb(ring) \ + test_bit(__IXGBEVF_RX_BUILD_SKB_ENABLED, &(ring)->state) +#define set_ring_build_skb_enabled(ring) \ + set_bit(__IXGBEVF_RX_BUILD_SKB_ENABLED, &(ring)->state) +#define clear_ring_build_skb_enabled(ring) \ + clear_bit(__IXGBEVF_RX_BUILD_SKB_ENABLED, &(ring)->state) + +static inline unsigned int ixgbevf_rx_bufsz(struct ixgbevf_ring *ring) +{ +#if (PAGE_SIZE < 8192) + if (ring_uses_large_buffer(ring)) + return IXGBEVF_RXBUFFER_3072; + + if (ring_uses_build_skb(ring)) + return IXGBEVF_MAX_FRAME_BUILD_SKB; +#endif + return IXGBEVF_RXBUFFER_2048; +} + +static inline unsigned int ixgbevf_rx_pg_order(struct ixgbevf_ring *ring) +{ +#if (PAGE_SIZE < 8192) + if (ring_uses_large_buffer(ring)) + return 1; +#endif + return 0; +} + +#define ixgbevf_rx_pg_size(_ring) (PAGE_SIZE << ixgbevf_rx_pg_order(_ring)) + +#define check_for_tx_hang(ring) \ + test_bit(__IXGBEVF_TX_DETECT_HANG, &(ring)->state) +#define set_check_for_tx_hang(ring) \ + set_bit(__IXGBEVF_TX_DETECT_HANG, &(ring)->state) +#define clear_check_for_tx_hang(ring) \ + clear_bit(__IXGBEVF_TX_DETECT_HANG, &(ring)->state) + struct ixgbevf_ring_container { struct ixgbevf_ring *ring; /* pointer to linked list of rings */ unsigned int total_bytes; /* total bytes processed this int */ @@ -194,7 +242,11 @@ struct ixgbevf_q_vector { u16 itr; /* Interrupt throttle rate written to EITR */ struct napi_struct napi; struct ixgbevf_ring_container rx, tx; + struct rcu_head rcu; /* to avoid race with update stats on free */ char name[IFNAMSIZ + 9]; + + /* for dynamic allocation of rings associated with this q_vector */ + struct ixgbevf_ring ring[0] ____cacheline_internodealigned_in_smp; #ifdef CONFIG_NET_RX_BUSY_POLL unsigned int state; #define IXGBEVF_QV_STATE_IDLE 0 @@ -331,6 +383,8 @@ struct ixgbevf_adapter { u32 *rss_key; u8 rss_indir_tbl[IXGBEVF_X550_VFRETA_SIZE]; + u32 flags; +#define IXGBEVF_FLAGS_LEGACY_RX BIT(1) }; enum ixbgevf_state_t { diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c index 9b3d43d28106..f37307131eb6 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c +++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c @@ -130,6 +130,9 @@ static void ixgbevf_service_event_complete(struct ixgbevf_adapter *adapter) static void ixgbevf_queue_reset_subtask(struct ixgbevf_adapter *adapter); static void ixgbevf_set_itr(struct ixgbevf_q_vector *q_vector); static void ixgbevf_free_all_rx_resources(struct ixgbevf_adapter *adapter); +static bool ixgbevf_can_reuse_rx_page(struct ixgbevf_rx_buffer *rx_buffer); +static void ixgbevf_reuse_rx_page(struct ixgbevf_ring *rx_ring, + struct ixgbevf_rx_buffer *old_buff); static void ixgbevf_remove_adapter(struct ixgbe_hw *hw) { @@ -527,6 +530,49 @@ static void ixgbevf_process_skb_fields(struct ixgbevf_ring *rx_ring, skb->protocol = eth_type_trans(skb, rx_ring->netdev); } +static +struct ixgbevf_rx_buffer *ixgbevf_get_rx_buffer(struct ixgbevf_ring *rx_ring, + const unsigned int size) +{ + struct ixgbevf_rx_buffer *rx_buffer; + + rx_buffer = &rx_ring->rx_buffer_info[rx_ring->next_to_clean]; + prefetchw(rx_buffer->page); + + /* we are reusing so sync this buffer for CPU use */ + dma_sync_single_range_for_cpu(rx_ring->dev, + rx_buffer->dma, + rx_buffer->page_offset, + size, + DMA_FROM_DEVICE); + + rx_buffer->pagecnt_bias--; + + return rx_buffer; +} + +static void ixgbevf_put_rx_buffer(struct ixgbevf_ring *rx_ring, + struct ixgbevf_rx_buffer *rx_buffer) +{ + if (ixgbevf_can_reuse_rx_page(rx_buffer)) { + /* hand second half of page back to the ring */ + ixgbevf_reuse_rx_page(rx_ring, rx_buffer); + } else { + /* We are not reusing the buffer so unmap it and free + * any references we are holding to it + */ + dma_unmap_page_attrs(rx_ring->dev, rx_buffer->dma, + ixgbevf_rx_pg_size(rx_ring), + DMA_FROM_DEVICE, + IXGBEVF_RX_DMA_ATTR); + __page_frag_cache_drain(rx_buffer->page, + rx_buffer->pagecnt_bias); + } + + /* clear contents of rx_buffer */ + rx_buffer->page = NULL; +} + /** * ixgbevf_is_non_eop - process handling of non-EOP buffers * @rx_ring: Rx ring being processed @@ -554,32 +600,38 @@ static bool ixgbevf_is_non_eop(struct ixgbevf_ring *rx_ring, return true; } +static inline unsigned int ixgbevf_rx_offset(struct ixgbevf_ring *rx_ring) +{ + return ring_uses_build_skb(rx_ring) ? IXGBEVF_SKB_PAD : 0; +} + static bool ixgbevf_alloc_mapped_page(struct ixgbevf_ring *rx_ring, struct ixgbevf_rx_buffer *bi) { struct page *page = bi->page; - dma_addr_t dma = bi->dma; + dma_addr_t dma; /* since we are recycling buffers we should seldom need to alloc */ if (likely(page)) return true; /* alloc new page for storage */ - page = dev_alloc_page(); + page = dev_alloc_pages(ixgbevf_rx_pg_order(rx_ring)); if (unlikely(!page)) { rx_ring->rx_stats.alloc_rx_page_failed++; return false; } /* map page for use */ - dma = dma_map_page_attrs(rx_ring->dev, page, 0, PAGE_SIZE, + dma = dma_map_page_attrs(rx_ring->dev, page, 0, + ixgbevf_rx_pg_size(rx_ring), DMA_FROM_DEVICE, IXGBEVF_RX_DMA_ATTR); /* if mapping failed free memory back to system since * there isn't much point in holding memory we can't use */ if (dma_mapping_error(rx_ring->dev, dma)) { - __free_page(page); + __free_pages(page, ixgbevf_rx_pg_order(rx_ring)); rx_ring->rx_stats.alloc_rx_page_failed++; return false; @@ -587,7 +639,7 @@ static bool ixgbevf_alloc_mapped_page(struct ixgbevf_ring *rx_ring, bi->dma = dma; bi->page = page; - bi->page_offset = 0; + bi->page_offset = ixgbevf_rx_offset(rx_ring); bi->pagecnt_bias = 1; rx_ring->rx_stats.alloc_rx_page++; @@ -621,7 +673,7 @@ static void ixgbevf_alloc_rx_buffers(struct ixgbevf_ring *rx_ring, /* sync the buffer for use by the device */ dma_sync_single_range_for_device(rx_ring->dev, bi->dma, bi->page_offset, - IXGBEVF_RX_BUFSZ, + ixgbevf_rx_bufsz(rx_ring), DMA_FROM_DEVICE); /* Refresh the desc even if pkt_addr didn't change @@ -734,11 +786,10 @@ static inline bool ixgbevf_page_is_reserved(struct page *page) return (page_to_nid(page) != numa_mem_id()) || page_is_pfmemalloc(page); } -static bool ixgbevf_can_reuse_rx_page(struct ixgbevf_rx_buffer *rx_buffer, - struct page *page, - const unsigned int truesize) +static bool ixgbevf_can_reuse_rx_page(struct ixgbevf_rx_buffer *rx_buffer) { - unsigned int pagecnt_bias = rx_buffer->pagecnt_bias--; + unsigned int pagecnt_bias = rx_buffer->pagecnt_bias; + struct page *page = rx_buffer->page; /* avoid re-using remote pages */ if (unlikely(ixgbevf_page_is_reserved(page))) @@ -746,17 +797,13 @@ static bool ixgbevf_can_reuse_rx_page(struct ixgbevf_rx_buffer *rx_buffer, #if (PAGE_SIZE < 8192) /* if we are only owner of page we can reuse it */ - if (unlikely(page_ref_count(page) != pagecnt_bias)) + if (unlikely((page_ref_count(page) - pagecnt_bias) > 1)) return false; - - /* flip page offset to other buffer */ - rx_buffer->page_offset ^= IXGBEVF_RX_BUFSZ; - #else - /* move offset up to the next cache line */ - rx_buffer->page_offset += truesize; +#define IXGBEVF_LAST_OFFSET \ + (SKB_WITH_OVERHEAD(PAGE_SIZE) - IXGBEVF_RXBUFFER_2048) - if (rx_buffer->page_offset > (PAGE_SIZE - IXGBEVF_RX_BUFSZ)) + if (rx_buffer->page_offset > IXGBEVF_LAST_OFFSET) return false; #endif @@ -765,7 +812,7 @@ static bool ixgbevf_can_reuse_rx_page(struct ixgbevf_rx_buffer *rx_buffer, * the pagecnt_bias and page count so that we fully restock the * number of references the driver holds. */ - if (unlikely(pagecnt_bias == 1)) { + if (unlikely(!pagecnt_bias)) { page_ref_add(page, USHRT_MAX); rx_buffer->pagecnt_bias = USHRT_MAX; } @@ -777,127 +824,81 @@ static bool ixgbevf_can_reuse_rx_page(struct ixgbevf_rx_buffer *rx_buffer, * ixgbevf_add_rx_frag - Add contents of Rx buffer to sk_buff * @rx_ring: rx descriptor ring to transact packets on * @rx_buffer: buffer containing page to add - * @rx_desc: descriptor containing length of buffer written by hardware * @skb: sk_buff to place the data into + * @size: size of buffer to be added * * This function will add the data contained in rx_buffer->page to the skb. - * This is done either through a direct copy if the data in the buffer is - * less than the skb header size, otherwise it will just attach the page as - * a frag to the skb. - * - * The function will then update the page offset if necessary and return - * true if the buffer can be reused by the adapter. **/ -static bool ixgbevf_add_rx_frag(struct ixgbevf_ring *rx_ring, +static void ixgbevf_add_rx_frag(struct ixgbevf_ring *rx_ring, struct ixgbevf_rx_buffer *rx_buffer, - u16 size, - union ixgbe_adv_rx_desc *rx_desc, - struct sk_buff *skb) + struct sk_buff *skb, + unsigned int size) { - struct page *page = rx_buffer->page; - unsigned char *va = page_address(page) + rx_buffer->page_offset; #if (PAGE_SIZE < 8192) - unsigned int truesize = IXGBEVF_RX_BUFSZ; + unsigned int truesize = ixgbevf_rx_pg_size(rx_ring) / 2; #else - unsigned int truesize = ALIGN(size, L1_CACHE_BYTES); + unsigned int truesize = ring_uses_build_skb(rx_ring) ? + SKB_DATA_ALIGN(IXGBEVF_SKB_PAD + size) : + SKB_DATA_ALIGN(size); +#endif + skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, rx_buffer->page, + rx_buffer->page_offset, size, truesize); +#if (PAGE_SIZE < 8192) + rx_buffer->page_offset ^= truesize; +#else + rx_buffer->page_offset += truesize; #endif - unsigned int pull_len; - - 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 */ - if (likely(!ixgbevf_page_is_reserved(page))) - return true; - - /* this page cannot be reused so discard it */ - 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, - (unsigned long)va & ~PAGE_MASK, size, truesize); - - return ixgbevf_can_reuse_rx_page(rx_buffer, page, truesize); } -static struct sk_buff *ixgbevf_fetch_rx_buffer(struct ixgbevf_ring *rx_ring, - union ixgbe_adv_rx_desc *rx_desc, - struct sk_buff *skb) +static +struct sk_buff *ixgbevf_construct_skb(struct ixgbevf_ring *rx_ring, + struct ixgbevf_rx_buffer *rx_buffer, + union ixgbe_adv_rx_desc *rx_desc, + unsigned int size) { - struct ixgbevf_rx_buffer *rx_buffer; - struct page *page; - u16 size = le16_to_cpu(rx_desc->wb.upper.length); - - rx_buffer = &rx_ring->rx_buffer_info[rx_ring->next_to_clean]; - page = rx_buffer->page; - prefetchw(page); - - /* we are reusing so sync this buffer for CPU use */ - dma_sync_single_range_for_cpu(rx_ring->dev, - rx_buffer->dma, - rx_buffer->page_offset, - size, - DMA_FROM_DEVICE); - - if (likely(!skb)) { - void *page_addr = page_address(page) + - rx_buffer->page_offset; + void *va = page_address(rx_buffer->page) + rx_buffer->page_offset; +#if (PAGE_SIZE < 8192) + unsigned int truesize = ixgbevf_rx_pg_size(rx_ring) / 2; +#else + unsigned int truesize = SKB_DATA_ALIGN(size); +#endif + unsigned int headlen; + struct sk_buff *skb; - /* prefetch first cache line of first page */ - prefetch(page_addr); + /* prefetch first cache line of first page */ + prefetch(va); #if L1_CACHE_BYTES < 128 - prefetch(page_addr + L1_CACHE_BYTES); + prefetch(va + L1_CACHE_BYTES); #endif - /* allocate a skb to store the frags */ - skb = netdev_alloc_skb_ip_align(rx_ring->netdev, - IXGBEVF_RX_HDR_SIZE); - if (unlikely(!skb)) { - rx_ring->rx_stats.alloc_rx_buff_failed++; - return NULL; - } + /* allocate a skb to store the frags */ + skb = napi_alloc_skb(&rx_ring->q_vector->napi, IXGBEVF_RX_HDR_SIZE); + if (unlikely(!skb)) + return NULL; - /* we will be copying header into skb->data in - * pskb_may_pull so it is in our interest to prefetch - * it now to avoid a possible cache miss - */ - prefetchw(skb->data); - } + /* Determine available headroom for copy */ + headlen = size; + if (headlen > IXGBEVF_RX_HDR_SIZE) + headlen = eth_get_headlen(va, IXGBEVF_RX_HDR_SIZE); - /* pull page into skb */ - if (ixgbevf_add_rx_frag(rx_ring, rx_buffer, size, rx_desc, skb)) { - /* hand second half of page back to the ring */ - ixgbevf_reuse_rx_page(rx_ring, rx_buffer); + /* align pull length to size of long to optimize memcpy performance */ + memcpy(__skb_put(skb, headlen), va, ALIGN(headlen, sizeof(long))); + + /* update all of the pointers */ + size -= headlen; + if (size) { + skb_add_rx_frag(skb, 0, rx_buffer->page, + (va + headlen) - page_address(rx_buffer->page), + size, truesize); +#if (PAGE_SIZE < 8192) + rx_buffer->page_offset ^= truesize; +#else + rx_buffer->page_offset += truesize; +#endif } else { - /* We are not reusing the buffer so unmap it and free - * any references we are holding to it - */ - dma_unmap_page_attrs(rx_ring->dev, rx_buffer->dma, - PAGE_SIZE, DMA_FROM_DEVICE, - IXGBEVF_RX_DMA_ATTR); - __page_frag_cache_drain(page, rx_buffer->pagecnt_bias); + rx_buffer->pagecnt_bias++; } - /* clear contents of buffer_info */ - rx_buffer->dma = 0; - rx_buffer->page = NULL; - return skb; } @@ -909,6 +910,44 @@ static inline void ixgbevf_irq_enable_queues(struct ixgbevf_adapter *adapter, IXGBE_WRITE_REG(hw, IXGBE_VTEIMS, qmask); } +static struct sk_buff *ixgbevf_build_skb(struct ixgbevf_ring *rx_ring, + struct ixgbevf_rx_buffer *rx_buffer, + union ixgbe_adv_rx_desc *rx_desc, + unsigned int size) +{ + void *va = page_address(rx_buffer->page) + rx_buffer->page_offset; +#if (PAGE_SIZE < 8192) + unsigned int truesize = ixgbevf_rx_pg_size(rx_ring) / 2; +#else + unsigned int truesize = SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) + + SKB_DATA_ALIGN(IXGBEVF_SKB_PAD + size); +#endif + struct sk_buff *skb; + + /* prefetch first cache line of first page */ + prefetch(va); +#if L1_CACHE_BYTES < 128 + prefetch(va + L1_CACHE_BYTES); +#endif + + /* build an skb to around the page buffer */ + skb = build_skb(va - IXGBEVF_SKB_PAD, truesize); + if (unlikely(!skb)) + return NULL; + + /* update pointers within the skb to store the data */ + skb_reserve(skb, IXGBEVF_SKB_PAD); + __skb_put(skb, size); + + /* update buffer offset */ +#if (PAGE_SIZE < 8192) + rx_buffer->page_offset ^= truesize; +#else + rx_buffer->page_offset += truesize; +#endif + + return skb; +} static int ixgbevf_clean_rx_irq(struct ixgbevf_q_vector *q_vector, struct ixgbevf_ring *rx_ring, int budget) @@ -919,6 +958,8 @@ static int ixgbevf_clean_rx_irq(struct ixgbevf_q_vector *q_vector, while (likely(total_rx_packets < budget)) { union ixgbe_adv_rx_desc *rx_desc; + struct ixgbevf_rx_buffer *rx_buffer; + unsigned int size; /* return some buffers to hardware, one at a time is too slow */ if (cleaned_count >= IXGBEVF_RX_BUFFER_WRITE) { @@ -927,8 +968,8 @@ static int ixgbevf_clean_rx_irq(struct ixgbevf_q_vector *q_vector, } rx_desc = IXGBEVF_RX_DESC(rx_ring, rx_ring->next_to_clean); - - if (!rx_desc->wb.upper.length) + size = le16_to_cpu(rx_desc->wb.upper.length); + if (!size) break; /* This memory barrier is needed to keep us from reading @@ -937,15 +978,26 @@ static int ixgbevf_clean_rx_irq(struct ixgbevf_q_vector *q_vector, */ rmb(); + rx_buffer = ixgbevf_get_rx_buffer(rx_ring, size); + /* retrieve a buffer from the ring */ - skb = ixgbevf_fetch_rx_buffer(rx_ring, rx_desc, skb); + if (skb) + ixgbevf_add_rx_frag(rx_ring, rx_buffer, skb, size); + else if (ring_uses_build_skb(rx_ring)) + skb = ixgbevf_build_skb(rx_ring, rx_buffer, + rx_desc, size); + else + skb = ixgbevf_construct_skb(rx_ring, rx_buffer, + rx_desc, size); /* exit if we failed to retrieve a buffer */ if (!skb) { rx_ring->rx_stats.alloc_rx_buff_failed++; + rx_buffer->pagecnt_bias++; break; } + ixgbevf_put_rx_buffer(rx_ring, rx_buffer); cleaned_count++; /* fetch next buffer in frame if non-eop */ @@ -1260,85 +1312,6 @@ static irqreturn_t ixgbevf_msix_clean_rings(int irq, void *data) return IRQ_HANDLED; } -static inline void map_vector_to_rxq(struct ixgbevf_adapter *a, int v_idx, - int r_idx) -{ - struct ixgbevf_q_vector *q_vector = a->q_vector[v_idx]; - - a->rx_ring[r_idx]->next = q_vector->rx.ring; - q_vector->rx.ring = a->rx_ring[r_idx]; - q_vector->rx.count++; -} - -static inline void map_vector_to_txq(struct ixgbevf_adapter *a, int v_idx, - int t_idx) -{ - struct ixgbevf_q_vector *q_vector = a->q_vector[v_idx]; - - a->tx_ring[t_idx]->next = q_vector->tx.ring; - q_vector->tx.ring = a->tx_ring[t_idx]; - q_vector->tx.count++; -} - -/** - * ixgbevf_map_rings_to_vectors - Maps descriptor rings to vectors - * @adapter: board private structure to initialize - * - * This function maps descriptor rings to the queue-specific vectors - * we were allotted through the MSI-X enabling code. Ideally, we'd have - * one vector per ring/queue, but on a constrained vector budget, we - * group the rings as "efficiently" as possible. You would add new - * mapping configurations in here. - **/ -static int ixgbevf_map_rings_to_vectors(struct ixgbevf_adapter *adapter) -{ - int q_vectors; - int v_start = 0; - int rxr_idx = 0, txr_idx = 0; - int rxr_remaining = adapter->num_rx_queues; - int txr_remaining = adapter->num_tx_queues; - int i, j; - int rqpv, tqpv; - - q_vectors = adapter->num_msix_vectors - NON_Q_VECTORS; - - /* The ideal configuration... - * We have enough vectors to map one per queue. - */ - if (q_vectors == adapter->num_rx_queues + adapter->num_tx_queues) { - for (; rxr_idx < rxr_remaining; v_start++, rxr_idx++) - map_vector_to_rxq(adapter, v_start, rxr_idx); - - for (; txr_idx < txr_remaining; v_start++, txr_idx++) - map_vector_to_txq(adapter, v_start, txr_idx); - return 0; - } - - /* If we don't have enough vectors for a 1-to-1 - * mapping, we'll have to group them so there are - * multiple queues per vector. - */ - /* Re-adjusting *qpv takes care of the remainder. */ - for (i = v_start; i < q_vectors; i++) { - rqpv = DIV_ROUND_UP(rxr_remaining, q_vectors - i); - for (j = 0; j < rqpv; j++) { - map_vector_to_rxq(adapter, i, rxr_idx); - rxr_idx++; - rxr_remaining--; - } - } - for (i = v_start; i < q_vectors; i++) { - tqpv = DIV_ROUND_UP(txr_remaining, q_vectors - i); - for (j = 0; j < tqpv; j++) { - map_vector_to_txq(adapter, i, txr_idx); - txr_idx++; - txr_remaining--; - } - } - - return 0; -} - /** * ixgbevf_request_msix_irqs - Initialize MSI-X interrupts * @adapter: board private structure @@ -1411,20 +1384,6 @@ free_queue_irqs: return err; } -static inline void ixgbevf_reset_q_vectors(struct ixgbevf_adapter *adapter) -{ - int i, q_vectors = adapter->num_msix_vectors - NON_Q_VECTORS; - - for (i = 0; i < q_vectors; i++) { - struct ixgbevf_q_vector *q_vector = adapter->q_vector[i]; - - q_vector->rx.ring = NULL; - q_vector->tx.ring = NULL; - q_vector->rx.count = 0; - q_vector->tx.count = 0; - } -} - /** * ixgbevf_request_irq - initialize interrupts * @adapter: board private structure @@ -1464,8 +1423,6 @@ static void ixgbevf_free_irq(struct ixgbevf_adapter *adapter) free_irq(adapter->msix_entries[i].vector, adapter->q_vector[i]); } - - ixgbevf_reset_q_vectors(adapter); } /** @@ -1587,7 +1544,8 @@ static void ixgbevf_configure_tx(struct ixgbevf_adapter *adapter) #define IXGBE_SRRCTL_BSIZEHDRSIZE_SHIFT 2 -static void ixgbevf_configure_srrctl(struct ixgbevf_adapter *adapter, int index) +static void ixgbevf_configure_srrctl(struct ixgbevf_adapter *adapter, + struct ixgbevf_ring *ring, int index) { struct ixgbe_hw *hw = &adapter->hw; u32 srrctl; @@ -1595,7 +1553,10 @@ static void ixgbevf_configure_srrctl(struct ixgbevf_adapter *adapter, int index) srrctl = IXGBE_SRRCTL_DROP_EN; srrctl |= IXGBEVF_RX_HDR_SIZE << IXGBE_SRRCTL_BSIZEHDRSIZE_SHIFT; - srrctl |= IXGBEVF_RX_BUFSZ >> IXGBE_SRRCTL_BSIZEPKT_SHIFT; + if (ring_uses_large_buffer(ring)) + srrctl |= IXGBEVF_RXBUFFER_3072 >> IXGBE_SRRCTL_BSIZEPKT_SHIFT; + else + srrctl |= IXGBEVF_RXBUFFER_2048 >> IXGBE_SRRCTL_BSIZEPKT_SHIFT; srrctl |= IXGBE_SRRCTL_DESCTYPE_ADV_ONEBUF; IXGBE_WRITE_REG(hw, IXGBE_VFSRRCTL(index), srrctl); @@ -1767,10 +1728,21 @@ static void ixgbevf_configure_rx_ring(struct ixgbevf_adapter *adapter, ring->next_to_use = 0; ring->next_to_alloc = 0; - ixgbevf_configure_srrctl(adapter, reg_idx); + ixgbevf_configure_srrctl(adapter, ring, reg_idx); + + /* RXDCTL.RLPML does not work on 82599 */ + if (adapter->hw.mac.type != ixgbe_mac_82599_vf) { + rxdctl &= ~(IXGBE_RXDCTL_RLPMLMASK | + IXGBE_RXDCTL_RLPML_EN); - /* allow any size packet since we can handle overflow */ - rxdctl &= ~IXGBE_RXDCTL_RLPML_EN; +#if (PAGE_SIZE < 8192) + /* Limit the maximum frame size so we don't overrun the skb */ + if (ring_uses_build_skb(ring) && + !ring_uses_large_buffer(ring)) + rxdctl |= IXGBEVF_MAX_FRAME_BUILD_SKB | + IXGBE_RXDCTL_RLPML_EN; +#endif + } rxdctl |= IXGBE_RXDCTL_ENABLE | IXGBE_RXDCTL_VME; IXGBE_WRITE_REG(hw, IXGBE_VFRXDCTL(reg_idx), rxdctl); @@ -1779,6 +1751,29 @@ static void ixgbevf_configure_rx_ring(struct ixgbevf_adapter *adapter, ixgbevf_alloc_rx_buffers(ring, ixgbevf_desc_unused(ring)); } +static void ixgbevf_set_rx_buffer_len(struct ixgbevf_adapter *adapter, + struct ixgbevf_ring *rx_ring) +{ + struct net_device *netdev = adapter->netdev; + unsigned int max_frame = netdev->mtu + ETH_HLEN + ETH_FCS_LEN; + + /* set build_skb and buffer size flags */ + clear_ring_build_skb_enabled(rx_ring); + clear_ring_uses_large_buffer(rx_ring); + + if (adapter->flags & IXGBEVF_FLAGS_LEGACY_RX) + return; + + set_ring_build_skb_enabled(rx_ring); + +#if (PAGE_SIZE < 8192) + if (max_frame <= IXGBEVF_MAX_FRAME_BUILD_SKB) + return; + + set_ring_uses_large_buffer(rx_ring); +#endif +} + /** * ixgbevf_configure_rx - Configure 82599 VF Receive Unit after Reset * @adapter: board private structure @@ -1806,8 +1801,12 @@ static void ixgbevf_configure_rx(struct ixgbevf_adapter *adapter) /* Setup the HW Rx Head and Tail Descriptor Pointers and * the Base and Length of the Rx Descriptor Ring */ - for (i = 0; i < adapter->num_rx_queues; i++) - ixgbevf_configure_rx_ring(adapter, adapter->rx_ring[i]); + for (i = 0; i < adapter->num_rx_queues; i++) { + struct ixgbevf_ring *rx_ring = adapter->rx_ring[i]; + + ixgbevf_set_rx_buffer_len(adapter, rx_ring); + ixgbevf_configure_rx_ring(adapter, rx_ring); + } } static int ixgbevf_vlan_rx_add_vid(struct net_device *netdev, @@ -2136,13 +2135,13 @@ static void ixgbevf_clean_rx_ring(struct ixgbevf_ring *rx_ring) dma_sync_single_range_for_cpu(rx_ring->dev, rx_buffer->dma, rx_buffer->page_offset, - IXGBEVF_RX_BUFSZ, + ixgbevf_rx_bufsz(rx_ring), DMA_FROM_DEVICE); /* free resources associated with mapping */ dma_unmap_page_attrs(rx_ring->dev, rx_buffer->dma, - PAGE_SIZE, + ixgbevf_rx_pg_size(rx_ring), DMA_FROM_DEVICE, IXGBEVF_RX_DMA_ATTR); @@ -2405,105 +2404,171 @@ static void ixgbevf_set_num_queues(struct ixgbevf_adapter *adapter) } /** - * ixgbevf_alloc_queues - Allocate memory for all rings + * ixgbevf_set_interrupt_capability - set MSI-X or FAIL if not supported + * @adapter: board private structure to initialize + * + * Attempt to configure the interrupts using the best available + * capabilities of the hardware and the kernel. + **/ +static int ixgbevf_set_interrupt_capability(struct ixgbevf_adapter *adapter) +{ + int vector, v_budget; + + /* It's easy to be greedy for MSI-X vectors, but it really + * doesn't do us much good if we have a lot more vectors + * than CPU's. So let's be conservative and only ask for + * (roughly) the same number of vectors as there are CPU's. + * The default is to use pairs of vectors. + */ + v_budget = max(adapter->num_rx_queues, adapter->num_tx_queues); + v_budget = min_t(int, v_budget, num_online_cpus()); + v_budget += NON_Q_VECTORS; + + adapter->msix_entries = kcalloc(v_budget, + sizeof(struct msix_entry), GFP_KERNEL); + if (!adapter->msix_entries) + return -ENOMEM; + + for (vector = 0; vector < v_budget; vector++) + adapter->msix_entries[vector].entry = vector; + + /* A failure in MSI-X entry allocation isn't fatal, but the VF driver + * does not support any other modes, so we will simply fail here. Note + * that we clean up the msix_entries pointer else-where. + */ + return ixgbevf_acquire_msix_vectors(adapter, v_budget); +} + +static void ixgbevf_add_ring(struct ixgbevf_ring *ring, + struct ixgbevf_ring_container *head) +{ + ring->next = head->ring; + head->ring = ring; + head->count++; +} + +/** + * ixgbevf_alloc_q_vector - Allocate memory for a single interrupt vector * @adapter: board private structure to initialize + * @v_idx: index of vector in adapter struct + * @txr_count: number of Tx rings for q vector + * @txr_idx: index of first Tx ring to assign + * @rxr_count: number of Rx rings for q vector + * @rxr_idx: index of first Rx ring to assign * - * We allocate one ring per queue at run-time since we don't know the - * number of queues at compile-time. The polling_netdev array is - * intended for Multiqueue, but should work fine with a single queue. + * We allocate one q_vector. If allocation fails we return -ENOMEM. **/ -static int ixgbevf_alloc_queues(struct ixgbevf_adapter *adapter) +static int ixgbevf_alloc_q_vector(struct ixgbevf_adapter *adapter, int v_idx, + int txr_count, int txr_idx, + int rxr_count, int rxr_idx) { + struct ixgbevf_q_vector *q_vector; struct ixgbevf_ring *ring; - int rx = 0, tx = 0; + int ring_count, size; + + ring_count = txr_count + rxr_count; + size = sizeof(*q_vector) + (sizeof(*ring) * ring_count); + + /* allocate q_vector and rings */ + q_vector = kzalloc(size, GFP_KERNEL); + if (!q_vector) + return -ENOMEM; + + /* initialize NAPI */ + netif_napi_add(adapter->netdev, &q_vector->napi, ixgbevf_poll, 64); + + /* tie q_vector and adapter together */ + adapter->q_vector[v_idx] = q_vector; + q_vector->adapter = adapter; + q_vector->v_idx = v_idx; - for (; tx < adapter->num_tx_queues; tx++) { - ring = kzalloc(sizeof(*ring), GFP_KERNEL); - if (!ring) - goto err_allocation; + /* initialize pointer to rings */ + ring = q_vector->ring; + while (txr_count) { + /* assign generic ring traits */ ring->dev = &adapter->pdev->dev; ring->netdev = adapter->netdev; + + /* configure backlink on ring */ + ring->q_vector = q_vector; + + /* update q_vector Tx values */ + ixgbevf_add_ring(ring, &q_vector->tx); + + /* apply Tx specific ring traits */ ring->count = adapter->tx_ring_count; - ring->queue_index = tx; - ring->reg_idx = tx; + ring->queue_index = txr_idx; + ring->reg_idx = txr_idx; - adapter->tx_ring[tx] = ring; - } + /* assign ring to adapter */ + adapter->tx_ring[txr_idx] = ring; + + /* update count and index */ + txr_count--; + txr_idx++; - for (; rx < adapter->num_rx_queues; rx++) { - ring = kzalloc(sizeof(*ring), GFP_KERNEL); - if (!ring) - goto err_allocation; + /* push pointer to next ring */ + ring++; + } + while (rxr_count) { + /* assign generic ring traits */ ring->dev = &adapter->pdev->dev; ring->netdev = adapter->netdev; + /* configure backlink on ring */ + ring->q_vector = q_vector; + + /* update q_vector Rx values */ + ixgbevf_add_ring(ring, &q_vector->rx); + + /* apply Rx specific ring traits */ ring->count = adapter->rx_ring_count; - ring->queue_index = rx; - ring->reg_idx = rx; + ring->queue_index = rxr_idx; + ring->reg_idx = rxr_idx; - adapter->rx_ring[rx] = ring; - } + /* assign ring to adapter */ + adapter->rx_ring[rxr_idx] = ring; - return 0; + /* update count and index */ + rxr_count--; + rxr_idx++; -err_allocation: - while (tx) { - kfree(adapter->tx_ring[--tx]); - adapter->tx_ring[tx] = NULL; + /* push pointer to next ring */ + ring++; } - while (rx) { - kfree(adapter->rx_ring[--rx]); - adapter->rx_ring[rx] = NULL; - } - return -ENOMEM; + return 0; } /** - * ixgbevf_set_interrupt_capability - set MSI-X or FAIL if not supported + * ixgbevf_free_q_vector - Free memory allocated for specific interrupt vector * @adapter: board private structure to initialize + * @v_idx: index of vector in adapter struct * - * Attempt to configure the interrupts using the best available - * capabilities of the hardware and the kernel. + * This function frees the memory allocated to the q_vector. In addition if + * NAPI is enabled it will delete any references to the NAPI struct prior + * to freeing the q_vector. **/ -static int ixgbevf_set_interrupt_capability(struct ixgbevf_adapter *adapter) +static void ixgbevf_free_q_vector(struct ixgbevf_adapter *adapter, int v_idx) { - struct net_device *netdev = adapter->netdev; - int err; - int vector, v_budget; - - /* It's easy to be greedy for MSI-X vectors, but it really - * doesn't do us much good if we have a lot more vectors - * than CPU's. So let's be conservative and only ask for - * (roughly) the same number of vectors as there are CPU's. - * The default is to use pairs of vectors. - */ - v_budget = max(adapter->num_rx_queues, adapter->num_tx_queues); - v_budget = min_t(int, v_budget, num_online_cpus()); - v_budget += NON_Q_VECTORS; - - /* A failure in MSI-X entry allocation isn't fatal, but it does - * mean we disable MSI-X capabilities of the adapter. - */ - adapter->msix_entries = kcalloc(v_budget, - sizeof(struct msix_entry), GFP_KERNEL); - if (!adapter->msix_entries) - return -ENOMEM; + struct ixgbevf_q_vector *q_vector = adapter->q_vector[v_idx]; + struct ixgbevf_ring *ring; - for (vector = 0; vector < v_budget; vector++) - adapter->msix_entries[vector].entry = vector; + ixgbevf_for_each_ring(ring, q_vector->tx) + adapter->tx_ring[ring->queue_index] = NULL; - err = ixgbevf_acquire_msix_vectors(adapter, v_budget); - if (err) - return err; + ixgbevf_for_each_ring(ring, q_vector->rx) + adapter->rx_ring[ring->queue_index] = NULL; - err = netif_set_real_num_tx_queues(netdev, adapter->num_tx_queues); - if (err) - return err; + adapter->q_vector[v_idx] = NULL; + netif_napi_del(&q_vector->napi); - return netif_set_real_num_rx_queues(netdev, adapter->num_rx_queues); + /* ixgbevf_get_stats() might access the rings on this vector, + * we must wait a grace period before freeing it. + */ + kfree_rcu(q_vector, rcu); } /** @@ -2515,35 +2580,53 @@ static int ixgbevf_set_interrupt_capability(struct ixgbevf_adapter *adapter) **/ static int ixgbevf_alloc_q_vectors(struct ixgbevf_adapter *adapter) { - int q_idx, num_q_vectors; - struct ixgbevf_q_vector *q_vector; + int q_vectors = adapter->num_msix_vectors - NON_Q_VECTORS; + int rxr_remaining = adapter->num_rx_queues; + int txr_remaining = adapter->num_tx_queues; + int rxr_idx = 0, txr_idx = 0, v_idx = 0; + int err; + + if (q_vectors >= (rxr_remaining + txr_remaining)) { + for (; rxr_remaining; v_idx++, q_vectors--) { + int rqpv = DIV_ROUND_UP(rxr_remaining, q_vectors); + + err = ixgbevf_alloc_q_vector(adapter, v_idx, + 0, 0, rqpv, rxr_idx); + if (err) + goto err_out; - num_q_vectors = adapter->num_msix_vectors - NON_Q_VECTORS; + /* update counts and index */ + rxr_remaining -= rqpv; + rxr_idx += rqpv; + } + } + + for (; q_vectors; v_idx++, q_vectors--) { + int rqpv = DIV_ROUND_UP(rxr_remaining, q_vectors); + int tqpv = DIV_ROUND_UP(txr_remaining, q_vectors); - for (q_idx = 0; q_idx < num_q_vectors; q_idx++) { - q_vector = kzalloc(sizeof(struct ixgbevf_q_vector), GFP_KERNEL); - if (!q_vector) + err = ixgbevf_alloc_q_vector(adapter, v_idx, + tqpv, txr_idx, + rqpv, rxr_idx); + + if (err) goto err_out; - q_vector->adapter = adapter; - q_vector->v_idx = q_idx; - netif_napi_add(adapter->netdev, &q_vector->napi, - ixgbevf_poll, 64); - adapter->q_vector[q_idx] = q_vector; + + /* update counts and index */ + rxr_remaining -= rqpv; + rxr_idx += rqpv; + txr_remaining -= tqpv; + txr_idx += tqpv; } return 0; err_out: - while (q_idx) { - q_idx--; - q_vector = adapter->q_vector[q_idx]; -#ifdef CONFIG_NET_RX_BUSY_POLL - napi_hash_del(&q_vector->napi); -#endif - netif_napi_del(&q_vector->napi); - kfree(q_vector); - adapter->q_vector[q_idx] = NULL; + while (v_idx) { + v_idx--; + ixgbevf_free_q_vector(adapter, v_idx); } + return -ENOMEM; } @@ -2557,17 +2640,11 @@ err_out: **/ static void ixgbevf_free_q_vectors(struct ixgbevf_adapter *adapter) { - int q_idx, num_q_vectors = adapter->num_msix_vectors - NON_Q_VECTORS; - - for (q_idx = 0; q_idx < num_q_vectors; q_idx++) { - struct ixgbevf_q_vector *q_vector = adapter->q_vector[q_idx]; + int q_vectors = adapter->num_msix_vectors - NON_Q_VECTORS; - adapter->q_vector[q_idx] = NULL; -#ifdef CONFIG_NET_RX_BUSY_POLL - napi_hash_del(&q_vector->napi); -#endif - netif_napi_del(&q_vector->napi); - kfree(q_vector); + while (q_vectors) { + q_vectors--; + ixgbevf_free_q_vector(adapter, q_vectors); } } @@ -2611,12 +2688,6 @@ static int ixgbevf_init_interrupt_scheme(struct ixgbevf_adapter *adapter) goto err_alloc_q_vectors; } - err = ixgbevf_alloc_queues(adapter); - if (err) { - pr_err("Unable to allocate memory for queues\n"); - goto err_alloc_queues; - } - hw_dbg(&adapter->hw, "Multiqueue %s: Rx Queue count = %u, Tx Queue count = %u\n", (adapter->num_rx_queues > 1) ? "Enabled" : "Disabled", adapter->num_rx_queues, adapter->num_tx_queues); @@ -2624,8 +2695,6 @@ static int ixgbevf_init_interrupt_scheme(struct ixgbevf_adapter *adapter) set_bit(__IXGBEVF_DOWN, &adapter->state); return 0; -err_alloc_queues: - ixgbevf_free_q_vectors(adapter); err_alloc_q_vectors: ixgbevf_reset_interrupt_capability(adapter); err_set_interrupt: @@ -2641,17 +2710,6 @@ err_set_interrupt: **/ static void ixgbevf_clear_interrupt_scheme(struct ixgbevf_adapter *adapter) { - int i; - - for (i = 0; i < adapter->num_tx_queues; i++) { - kfree(adapter->tx_ring[i]); - adapter->tx_ring[i] = NULL; - } - for (i = 0; i < adapter->num_rx_queues; i++) { - kfree(adapter->rx_ring[i]); - adapter->rx_ring[i] = NULL; - } - adapter->num_tx_queues = 0; adapter->num_rx_queues = 0; @@ -3088,9 +3146,14 @@ static int ixgbevf_setup_all_tx_resources(struct ixgbevf_adapter *adapter) if (!err) continue; hw_dbg(&adapter->hw, "Allocation for Tx Queue %u failed\n", i); - break; + goto err_setup_tx; } + return 0; +err_setup_tx: + /* rewind the index freeing the rings as we go */ + while (i--) + ixgbevf_free_tx_resources(adapter->tx_ring[i]); return err; } @@ -3148,8 +3211,14 @@ static int ixgbevf_setup_all_rx_resources(struct ixgbevf_adapter *adapter) if (!err) continue; hw_dbg(&adapter->hw, "Allocation for Rx Queue %u failed\n", i); - break; + goto err_setup_rx; } + + return 0; +err_setup_rx: + /* rewind the index freeing the rings as we go */ + while (i--) + ixgbevf_free_rx_resources(adapter->rx_ring[i]); return err; } @@ -3244,28 +3313,31 @@ int ixgbevf_open(struct net_device *netdev) ixgbevf_configure(adapter); - /* Map the Tx/Rx rings to the vectors we were allotted. - * if request_irq will be called in this function map_rings - * must be called *before* up_complete - */ - ixgbevf_map_rings_to_vectors(adapter); - err = ixgbevf_request_irq(adapter); if (err) goto err_req_irq; + /* Notify the stack of the actual queue counts. */ + err = netif_set_real_num_tx_queues(netdev, adapter->num_tx_queues); + if (err) + goto err_set_queues; + + err = netif_set_real_num_rx_queues(netdev, adapter->num_rx_queues); + if (err) + goto err_set_queues; + ixgbevf_up_complete(adapter); return 0; +err_set_queues: + ixgbevf_free_irq(adapter); err_req_irq: - ixgbevf_down(adapter); -err_setup_rx: ixgbevf_free_all_rx_resources(adapter); -err_setup_tx: +err_setup_rx: ixgbevf_free_all_tx_resources(adapter); +err_setup_tx: ixgbevf_reset(adapter); - err_setup_reset: return err; @@ -3707,11 +3779,10 @@ static int ixgbevf_maybe_stop_tx(struct ixgbevf_ring *tx_ring, int size) return __ixgbevf_maybe_stop_tx(tx_ring, size); } -static int ixgbevf_xmit_frame(struct sk_buff *skb, struct net_device *netdev) +static int ixgbevf_xmit_frame_ring(struct sk_buff *skb, + struct ixgbevf_ring *tx_ring) { - struct ixgbevf_adapter *adapter = netdev_priv(netdev); struct ixgbevf_tx_buffer *first; - struct ixgbevf_ring *tx_ring; int tso; u32 tx_flags = 0; u16 count = TXD_USE_COUNT(skb_headlen(skb)); @@ -3726,8 +3797,6 @@ static int ixgbevf_xmit_frame(struct sk_buff *skb, struct net_device *netdev) return NETDEV_TX_OK; } - tx_ring = adapter->tx_ring[skb->queue_mapping]; - /* need: 1 descriptor per page * PAGE_SIZE/IXGBE_MAX_DATA_PER_TXD, * + 1 desc for skb_headlen/IXGBE_MAX_DATA_PER_TXD, * + 2 desc gap to keep tail from touching head, @@ -3780,6 +3849,29 @@ out_drop: return NETDEV_TX_OK; } +static int ixgbevf_xmit_frame(struct sk_buff *skb, struct net_device *netdev) +{ + struct ixgbevf_adapter *adapter = netdev_priv(netdev); + struct ixgbevf_ring *tx_ring; + + if (skb->len <= 0) { + dev_kfree_skb_any(skb); + return NETDEV_TX_OK; + } + + /* The minimum packet size for olinfo paylen is 17 so pad the skb + * in order to meet this minimum size requirement. + */ + if (skb->len < 17) { + if (skb_padto(skb, 17)) + return NETDEV_TX_OK; + skb->len = 17; + } + + tx_ring = adapter->tx_ring[skb->queue_mapping]; + return ixgbevf_xmit_frame_ring(skb, tx_ring); +} + /** * ixgbevf_set_mac - Change the Ethernet Address of the NIC * @netdev: network interface device structure @@ -3839,6 +3931,9 @@ static int ixgbevf_change_mtu(struct net_device *netdev, int new_mtu) /* must set new MTU before calling down or up */ netdev->mtu = new_mtu; + if (netif_running(netdev)) + ixgbevf_reinit_locked(adapter); + return 0; } @@ -3917,17 +4012,11 @@ static int ixgbevf_resume(struct pci_dev *pdev) rtnl_lock(); err = ixgbevf_init_interrupt_scheme(adapter); + if (!err && netif_running(netdev)) + err = ixgbevf_open(netdev); rtnl_unlock(); - if (err) { - dev_err(&pdev->dev, "Cannot initialize interrupts\n"); + if (err) return err; - } - - if (netif_running(netdev)) { - err = ixgbevf_open(netdev); - if (err) - return err; - } netif_device_attach(netdev); @@ -3953,6 +4042,7 @@ static void ixgbevf_get_stats(struct net_device *netdev, stats->multicast = adapter->stats.vfmprc - adapter->stats.base_vfmprc; + rcu_read_lock(); for (i = 0; i < adapter->num_rx_queues; i++) { ring = adapter->rx_ring[i]; do { @@ -3974,6 +4064,7 @@ static void ixgbevf_get_stats(struct net_device *netdev, stats->tx_bytes += bytes; stats->tx_packets += packets; } + rcu_read_unlock(); } #define IXGBEVF_MAX_MAC_HDR_LEN 127 diff --git a/drivers/net/ethernet/marvell/mvpp2.c b/drivers/net/ethernet/marvell/mvpp2.c index 5a1668cdb461..ac0a0dc8f157 100644 --- a/drivers/net/ethernet/marvell/mvpp2.c +++ b/drivers/net/ethernet/marvell/mvpp2.c @@ -44,6 +44,7 @@ #define MVPP2_RX_ATTR_FIFO_SIZE_REG(port) (0x20 + 4 * (port)) #define MVPP2_RX_MIN_PKT_SIZE_REG 0x60 #define MVPP2_RX_FIFO_INIT_REG 0x64 +#define MVPP22_TX_FIFO_THRESH_REG(port) (0x8840 + 4 * (port)) #define MVPP22_TX_FIFO_SIZE_REG(port) (0x8860 + 4 * (port)) /* RX DMA Top Registers */ @@ -65,6 +66,10 @@ #define MVPP2_RXQ_PACKET_OFFSET_MASK 0x70000000 #define MVPP2_RXQ_DISABLE_MASK BIT(31) +/* Top Registers */ +#define MVPP2_MH_REG(port) (0x5040 + 4 * (port)) +#define MVPP2_DSA_EXTENDED BIT(5) + /* Parser Registers */ #define MVPP2_PRS_INIT_LOOKUP_REG 0x1000 #define MVPP2_PRS_PORT_LU_MAX 0xf @@ -254,6 +259,7 @@ #define MVPP2_BM_BPPI_READ_PTR_REG(pool) (0x6100 + ((pool) * 4)) #define MVPP2_BM_BPPI_PTRS_NUM_REG(pool) (0x6140 + ((pool) * 4)) #define MVPP2_BM_BPPI_PTR_NUM_MASK 0x7ff +#define MVPP22_BM_POOL_PTRS_NUM_MASK 0xfff8 #define MVPP2_BM_BPPI_PREFETCH_FULL_MASK BIT(16) #define MVPP2_BM_POOL_CTRL_REG(pool) (0x6200 + ((pool) * 4)) #define MVPP2_BM_START_MASK BIT(0) @@ -473,6 +479,7 @@ #define MVPP2_ETH_TYPE_LEN 2 #define MVPP2_PPPOE_HDR_SIZE 8 #define MVPP2_VLAN_TAG_LEN 4 +#define MVPP2_VLAN_TAG_EDSA_LEN 8 /* Lbtd 802.3 type */ #define MVPP2_IP_LBDT_TYPE 0xfffa @@ -536,6 +543,11 @@ /* TX FIFO constants */ #define MVPP22_TX_FIFO_DATA_SIZE_10KB 0xa #define MVPP22_TX_FIFO_DATA_SIZE_3KB 0x3 +#define MVPP2_TX_FIFO_THRESHOLD_MIN 256 +#define MVPP2_TX_FIFO_THRESHOLD_10KB \ + (MVPP22_TX_FIFO_DATA_SIZE_10KB * 1024 - MVPP2_TX_FIFO_THRESHOLD_MIN) +#define MVPP2_TX_FIFO_THRESHOLD_3KB \ + (MVPP22_TX_FIFO_DATA_SIZE_3KB * 1024 - MVPP2_TX_FIFO_THRESHOLD_MIN) /* RX buffer constants */ #define MVPP2_SKB_SHINFO_SIZE \ @@ -609,35 +621,64 @@ enum mvpp2_tag_type { #define MVPP2_PRS_TCAM_LU_BYTE 20 #define MVPP2_PRS_TCAM_EN_OFFS(offs) ((offs) + 2) #define MVPP2_PRS_TCAM_INV_WORD 5 + +#define MVPP2_PRS_VID_TCAM_BYTE 2 + +/* There is a TCAM range reserved for VLAN filtering entries, range size is 33 + * 10 VLAN ID filter entries per port + * 1 default VLAN filter entry per port + * It is assumed that there are 3 ports for filter, not including loopback port + */ +#define MVPP2_PRS_VLAN_FILT_MAX 11 +#define MVPP2_PRS_VLAN_FILT_RANGE_SIZE 33 + +#define MVPP2_PRS_VLAN_FILT_MAX_ENTRY (MVPP2_PRS_VLAN_FILT_MAX - 2) +#define MVPP2_PRS_VLAN_FILT_DFLT_ENTRY (MVPP2_PRS_VLAN_FILT_MAX - 1) + /* Tcam entries ID */ #define MVPP2_PE_DROP_ALL 0 #define MVPP2_PE_FIRST_FREE_TID 1 -#define MVPP2_PE_LAST_FREE_TID (MVPP2_PRS_TCAM_SRAM_SIZE - 31) + +/* VLAN filtering range */ +#define MVPP2_PE_VID_FILT_RANGE_END (MVPP2_PRS_TCAM_SRAM_SIZE - 31) +#define MVPP2_PE_VID_FILT_RANGE_START (MVPP2_PE_VID_FILT_RANGE_END - \ + MVPP2_PRS_VLAN_FILT_RANGE_SIZE + 1) +#define MVPP2_PE_LAST_FREE_TID (MVPP2_PE_VID_FILT_RANGE_START - 1) #define MVPP2_PE_IP6_EXT_PROTO_UN (MVPP2_PRS_TCAM_SRAM_SIZE - 30) #define MVPP2_PE_MAC_MC_IP6 (MVPP2_PRS_TCAM_SRAM_SIZE - 29) #define MVPP2_PE_IP6_ADDR_UN (MVPP2_PRS_TCAM_SRAM_SIZE - 28) #define MVPP2_PE_IP4_ADDR_UN (MVPP2_PRS_TCAM_SRAM_SIZE - 27) #define MVPP2_PE_LAST_DEFAULT_FLOW (MVPP2_PRS_TCAM_SRAM_SIZE - 26) -#define MVPP2_PE_FIRST_DEFAULT_FLOW (MVPP2_PRS_TCAM_SRAM_SIZE - 19) -#define MVPP2_PE_EDSA_TAGGED (MVPP2_PRS_TCAM_SRAM_SIZE - 18) -#define MVPP2_PE_EDSA_UNTAGGED (MVPP2_PRS_TCAM_SRAM_SIZE - 17) -#define MVPP2_PE_DSA_TAGGED (MVPP2_PRS_TCAM_SRAM_SIZE - 16) -#define MVPP2_PE_DSA_UNTAGGED (MVPP2_PRS_TCAM_SRAM_SIZE - 15) -#define MVPP2_PE_ETYPE_EDSA_TAGGED (MVPP2_PRS_TCAM_SRAM_SIZE - 14) -#define MVPP2_PE_ETYPE_EDSA_UNTAGGED (MVPP2_PRS_TCAM_SRAM_SIZE - 13) -#define MVPP2_PE_ETYPE_DSA_TAGGED (MVPP2_PRS_TCAM_SRAM_SIZE - 12) -#define MVPP2_PE_ETYPE_DSA_UNTAGGED (MVPP2_PRS_TCAM_SRAM_SIZE - 11) -#define MVPP2_PE_MH_DEFAULT (MVPP2_PRS_TCAM_SRAM_SIZE - 10) -#define MVPP2_PE_DSA_DEFAULT (MVPP2_PRS_TCAM_SRAM_SIZE - 9) -#define MVPP2_PE_IP6_PROTO_UN (MVPP2_PRS_TCAM_SRAM_SIZE - 8) -#define MVPP2_PE_IP4_PROTO_UN (MVPP2_PRS_TCAM_SRAM_SIZE - 7) -#define MVPP2_PE_ETH_TYPE_UN (MVPP2_PRS_TCAM_SRAM_SIZE - 6) +#define MVPP2_PE_FIRST_DEFAULT_FLOW (MVPP2_PRS_TCAM_SRAM_SIZE - 21) +#define MVPP2_PE_EDSA_TAGGED (MVPP2_PRS_TCAM_SRAM_SIZE - 20) +#define MVPP2_PE_EDSA_UNTAGGED (MVPP2_PRS_TCAM_SRAM_SIZE - 19) +#define MVPP2_PE_DSA_TAGGED (MVPP2_PRS_TCAM_SRAM_SIZE - 18) +#define MVPP2_PE_DSA_UNTAGGED (MVPP2_PRS_TCAM_SRAM_SIZE - 17) +#define MVPP2_PE_ETYPE_EDSA_TAGGED (MVPP2_PRS_TCAM_SRAM_SIZE - 16) +#define MVPP2_PE_ETYPE_EDSA_UNTAGGED (MVPP2_PRS_TCAM_SRAM_SIZE - 15) +#define MVPP2_PE_ETYPE_DSA_TAGGED (MVPP2_PRS_TCAM_SRAM_SIZE - 14) +#define MVPP2_PE_ETYPE_DSA_UNTAGGED (MVPP2_PRS_TCAM_SRAM_SIZE - 13) +#define MVPP2_PE_MH_DEFAULT (MVPP2_PRS_TCAM_SRAM_SIZE - 12) +#define MVPP2_PE_DSA_DEFAULT (MVPP2_PRS_TCAM_SRAM_SIZE - 11) +#define MVPP2_PE_IP6_PROTO_UN (MVPP2_PRS_TCAM_SRAM_SIZE - 10) +#define MVPP2_PE_IP4_PROTO_UN (MVPP2_PRS_TCAM_SRAM_SIZE - 9) +#define MVPP2_PE_ETH_TYPE_UN (MVPP2_PRS_TCAM_SRAM_SIZE - 8) +#define MVPP2_PE_VID_FLTR_DEFAULT (MVPP2_PRS_TCAM_SRAM_SIZE - 7) +#define MVPP2_PE_VID_EDSA_FLTR_DEFAULT (MVPP2_PRS_TCAM_SRAM_SIZE - 6) #define MVPP2_PE_VLAN_DBL (MVPP2_PRS_TCAM_SRAM_SIZE - 5) #define MVPP2_PE_VLAN_NONE (MVPP2_PRS_TCAM_SRAM_SIZE - 4) #define MVPP2_PE_MAC_MC_ALL (MVPP2_PRS_TCAM_SRAM_SIZE - 3) #define MVPP2_PE_MAC_PROMISCUOUS (MVPP2_PRS_TCAM_SRAM_SIZE - 2) #define MVPP2_PE_MAC_NON_PROMISCUOUS (MVPP2_PRS_TCAM_SRAM_SIZE - 1) +#define MVPP2_PRS_VID_PORT_FIRST(port) (MVPP2_PE_VID_FILT_RANGE_START + \ + ((port) * MVPP2_PRS_VLAN_FILT_MAX)) +#define MVPP2_PRS_VID_PORT_LAST(port) (MVPP2_PRS_VID_PORT_FIRST(port) \ + + MVPP2_PRS_VLAN_FILT_MAX_ENTRY) +/* Index of default vid filter for given port */ +#define MVPP2_PRS_VID_PORT_DFLT(port) (MVPP2_PRS_VID_PORT_FIRST(port) \ + + MVPP2_PRS_VLAN_FILT_DFLT_ENTRY) + /* Sram structure * The fields are represented by MVPP2_PRS_TCAM_DATA_REG(3)->(0). */ @@ -725,6 +766,7 @@ enum mvpp2_tag_type { #define MVPP2_PRS_IPV6_EXT_AH_L4_AI_BIT BIT(4) #define MVPP2_PRS_SINGLE_VLAN_AI 0 #define MVPP2_PRS_DBL_VLAN_AI_BIT BIT(7) +#define MVPP2_PRS_EDSA_VID_AI_BIT BIT(0) /* DSA/EDSA type */ #define MVPP2_PRS_TAGGED true @@ -747,6 +789,7 @@ enum mvpp2_prs_lookup { MVPP2_PRS_LU_MAC, MVPP2_PRS_LU_DSA, MVPP2_PRS_LU_VLAN, + MVPP2_PRS_LU_VID, MVPP2_PRS_LU_L2, MVPP2_PRS_LU_PPPOE, MVPP2_PRS_LU_IP4, @@ -772,23 +815,26 @@ enum mvpp2_prs_l3_cast { #define MVPP22_RSS_TABLE_ENTRIES 32 /* BM constants */ -#define MVPP2_BM_POOLS_NUM 8 +#define MVPP2_BM_JUMBO_BUF_NUM 512 #define MVPP2_BM_LONG_BUF_NUM 1024 #define MVPP2_BM_SHORT_BUF_NUM 2048 #define MVPP2_BM_POOL_SIZE_MAX (16*1024 - MVPP2_BM_POOL_PTR_ALIGN/4) #define MVPP2_BM_POOL_PTR_ALIGN 128 -#define MVPP2_BM_SWF_LONG_POOL(port) ((port > 2) ? 2 : port) -#define MVPP2_BM_SWF_SHORT_POOL 3 /* BM cookie (32 bits) definition */ #define MVPP2_BM_COOKIE_POOL_OFFS 8 #define MVPP2_BM_COOKIE_CPU_OFFS 24 +#define MVPP2_BM_SHORT_FRAME_SIZE 512 +#define MVPP2_BM_LONG_FRAME_SIZE 2048 +#define MVPP2_BM_JUMBO_FRAME_SIZE 10240 /* BM short pool packet size * These value assure that for SWF the total number * of bytes allocated for each buffer will be 512 */ -#define MVPP2_BM_SHORT_PKT_SIZE MVPP2_RX_MAX_PKT_SIZE(512) +#define MVPP2_BM_SHORT_PKT_SIZE MVPP2_RX_MAX_PKT_SIZE(MVPP2_BM_SHORT_FRAME_SIZE) +#define MVPP2_BM_LONG_PKT_SIZE MVPP2_RX_MAX_PKT_SIZE(MVPP2_BM_LONG_FRAME_SIZE) +#define MVPP2_BM_JUMBO_PKT_SIZE MVPP2_RX_MAX_PKT_SIZE(MVPP2_BM_JUMBO_FRAME_SIZE) #define MVPP21_ADDR_SPACE_SZ 0 #define MVPP22_ADDR_SPACE_SZ SZ_64K @@ -796,12 +842,18 @@ enum mvpp2_prs_l3_cast { #define MVPP2_MAX_THREADS 8 #define MVPP2_MAX_QVECS MVPP2_MAX_THREADS -enum mvpp2_bm_type { - MVPP2_BM_FREE, - MVPP2_BM_SWF_LONG, - MVPP2_BM_SWF_SHORT +enum mvpp2_bm_pool_log_num { + MVPP2_BM_SHORT, + MVPP2_BM_LONG, + MVPP2_BM_JUMBO, + MVPP2_BM_POOLS_NUM }; +static struct { + int pkt_size; + int buf_num; +} mvpp2_pools[MVPP2_BM_POOLS_NUM]; + /* GMAC MIB Counters register definitions */ #define MVPP21_MIB_COUNTERS_OFFSET 0x1000 #define MVPP21_MIB_COUNTERS_PORT_SZ 0x400 @@ -1230,7 +1282,6 @@ struct mvpp2_cls_lookup_entry { struct mvpp2_bm_pool { /* Pool number in the range 0-7 */ int id; - enum mvpp2_bm_type type; /* Buffer Pointers Pool External (BPPE) size */ int size; @@ -1662,6 +1713,14 @@ static void mvpp2_prs_match_etype(struct mvpp2_prs_entry *pe, int offset, mvpp2_prs_tcam_data_byte_set(pe, offset + 1, ethertype & 0xff, 0xff); } +/* Set vid in tcam sw entry */ +static void mvpp2_prs_match_vid(struct mvpp2_prs_entry *pe, int offset, + unsigned short vid) +{ + mvpp2_prs_tcam_data_byte_set(pe, offset + 0, (vid & 0xf00) >> 8, 0xf); + mvpp2_prs_tcam_data_byte_set(pe, offset + 1, vid & 0xff, 0xff); +} + /* Set bits in sram sw entry */ static void mvpp2_prs_sram_bits_set(struct mvpp2_prs_entry *pe, int bit_num, int val) @@ -2029,24 +2088,30 @@ static void mvpp2_prs_dsa_tag_set(struct mvpp2 *priv, int port, bool add, mvpp2_prs_tcam_lu_set(&pe, MVPP2_PRS_LU_DSA); pe.index = tid; - /* Shift 4 bytes if DSA tag or 8 bytes in case of EDSA tag*/ - mvpp2_prs_sram_shift_set(&pe, shift, - MVPP2_PRS_SRAM_OP_SEL_SHIFT_ADD); - /* Update shadow table */ mvpp2_prs_shadow_set(priv, pe.index, MVPP2_PRS_LU_DSA); if (tagged) { /* Set tagged bit in DSA tag */ mvpp2_prs_tcam_data_byte_set(&pe, 0, - MVPP2_PRS_TCAM_DSA_TAGGED_BIT, - MVPP2_PRS_TCAM_DSA_TAGGED_BIT); - /* Clear all ai bits for next iteration */ - mvpp2_prs_sram_ai_update(&pe, 0, - MVPP2_PRS_SRAM_AI_MASK); - /* If packet is tagged continue check vlans */ - mvpp2_prs_sram_next_lu_set(&pe, MVPP2_PRS_LU_VLAN); + MVPP2_PRS_TCAM_DSA_TAGGED_BIT, + MVPP2_PRS_TCAM_DSA_TAGGED_BIT); + + /* Set ai bits for next iteration */ + if (extend) + mvpp2_prs_sram_ai_update(&pe, 1, + MVPP2_PRS_SRAM_AI_MASK); + else + mvpp2_prs_sram_ai_update(&pe, 0, + MVPP2_PRS_SRAM_AI_MASK); + + /* If packet is tagged continue check vid filtering */ + mvpp2_prs_sram_next_lu_set(&pe, MVPP2_PRS_LU_VID); } else { + /* Shift 4 bytes for DSA tag or 8 bytes for EDSA tag*/ + mvpp2_prs_sram_shift_set(&pe, shift, + MVPP2_PRS_SRAM_OP_SEL_SHIFT_ADD); + /* Set result info bits to 'no vlans' */ mvpp2_prs_sram_ri_update(&pe, MVPP2_PRS_RI_VLAN_NONE, MVPP2_PRS_RI_VLAN_MASK); @@ -2231,10 +2296,9 @@ static int mvpp2_prs_vlan_add(struct mvpp2 *priv, unsigned short tpid, int ai, mvpp2_prs_match_etype(pe, 0, tpid); - mvpp2_prs_sram_next_lu_set(pe, MVPP2_PRS_LU_L2); - /* Shift 4 bytes - skip 1 vlan tag */ - mvpp2_prs_sram_shift_set(pe, MVPP2_VLAN_TAG_LEN, - MVPP2_PRS_SRAM_OP_SEL_SHIFT_ADD); + /* VLAN tag detected, proceed with VID filtering */ + mvpp2_prs_sram_next_lu_set(pe, MVPP2_PRS_LU_VID); + /* Clear all ai bits for next iteration */ mvpp2_prs_sram_ai_update(pe, 0, MVPP2_PRS_SRAM_AI_MASK); @@ -2375,8 +2439,8 @@ static int mvpp2_prs_double_vlan_add(struct mvpp2 *priv, unsigned short tpid1, mvpp2_prs_match_etype(pe, 4, tpid2); mvpp2_prs_sram_next_lu_set(pe, MVPP2_PRS_LU_VLAN); - /* Shift 8 bytes - skip 2 vlan tags */ - mvpp2_prs_sram_shift_set(pe, 2 * MVPP2_VLAN_TAG_LEN, + /* Shift 4 bytes - skip outer vlan tag */ + mvpp2_prs_sram_shift_set(pe, MVPP2_VLAN_TAG_LEN, MVPP2_PRS_SRAM_OP_SEL_SHIFT_ADD); mvpp2_prs_sram_ri_update(pe, MVPP2_PRS_RI_VLAN_DOUBLE, MVPP2_PRS_RI_VLAN_MASK); @@ -2755,6 +2819,62 @@ static void mvpp2_prs_dsa_init(struct mvpp2 *priv) mvpp2_prs_hw_write(priv, &pe); } +/* Initialize parser entries for VID filtering */ +static void mvpp2_prs_vid_init(struct mvpp2 *priv) +{ + struct mvpp2_prs_entry pe; + + memset(&pe, 0, sizeof(pe)); + + /* Set default vid entry */ + pe.index = MVPP2_PE_VID_FLTR_DEFAULT; + mvpp2_prs_tcam_lu_set(&pe, MVPP2_PRS_LU_VID); + + mvpp2_prs_tcam_ai_update(&pe, 0, MVPP2_PRS_EDSA_VID_AI_BIT); + + /* Skip VLAN header - Set offset to 4 bytes */ + mvpp2_prs_sram_shift_set(&pe, MVPP2_VLAN_TAG_LEN, + MVPP2_PRS_SRAM_OP_SEL_SHIFT_ADD); + + /* Clear all ai bits for next iteration */ + mvpp2_prs_sram_ai_update(&pe, 0, MVPP2_PRS_SRAM_AI_MASK); + + mvpp2_prs_sram_next_lu_set(&pe, MVPP2_PRS_LU_L2); + + /* Unmask all ports */ + mvpp2_prs_tcam_port_map_set(&pe, MVPP2_PRS_PORT_MASK); + + /* Update shadow table and hw entry */ + mvpp2_prs_shadow_set(priv, pe.index, MVPP2_PRS_LU_VID); + mvpp2_prs_hw_write(priv, &pe); + + /* Set default vid entry for extended DSA*/ + memset(&pe, 0, sizeof(pe)); + + /* Set default vid entry */ + pe.index = MVPP2_PE_VID_EDSA_FLTR_DEFAULT; + mvpp2_prs_tcam_lu_set(&pe, MVPP2_PRS_LU_VID); + + mvpp2_prs_tcam_ai_update(&pe, MVPP2_PRS_EDSA_VID_AI_BIT, + MVPP2_PRS_EDSA_VID_AI_BIT); + + /* Skip VLAN header - Set offset to 8 bytes */ + mvpp2_prs_sram_shift_set(&pe, MVPP2_VLAN_TAG_EDSA_LEN, + MVPP2_PRS_SRAM_OP_SEL_SHIFT_ADD); + + /* Clear all ai bits for next iteration */ + mvpp2_prs_sram_ai_update(&pe, 0, MVPP2_PRS_SRAM_AI_MASK); + + mvpp2_prs_sram_next_lu_set(&pe, MVPP2_PRS_LU_L2); + + /* Unmask all ports */ + mvpp2_prs_tcam_port_map_set(&pe, MVPP2_PRS_PORT_MASK); + + /* Update shadow table and hw entry */ + mvpp2_prs_shadow_set(priv, pe.index, MVPP2_PRS_LU_VID); + mvpp2_prs_hw_write(priv, &pe); +} + /* Match basic ethertypes */ static int mvpp2_prs_etype_init(struct mvpp2 *priv) { @@ -3023,7 +3143,8 @@ static int mvpp2_prs_vlan_init(struct platform_device *pdev, struct mvpp2 *priv) mvpp2_prs_tcam_lu_set(&pe, MVPP2_PRS_LU_VLAN); pe.index = MVPP2_PE_VLAN_DBL; - mvpp2_prs_sram_next_lu_set(&pe, MVPP2_PRS_LU_L2); + mvpp2_prs_sram_next_lu_set(&pe, MVPP2_PRS_LU_VID); + /* Clear ai for next iterations */ mvpp2_prs_sram_ai_update(&pe, 0, MVPP2_PRS_SRAM_AI_MASK); mvpp2_prs_sram_ri_update(&pe, MVPP2_PRS_RI_VLAN_DOUBLE, @@ -3386,6 +3507,192 @@ static int mvpp2_prs_ip6_init(struct mvpp2 *priv) return 0; } +/* Find tcam entry with matched pair <vid,port> */ +static int mvpp2_prs_vid_range_find(struct mvpp2 *priv, int pmap, u16 vid, + u16 mask) +{ + unsigned char byte[2], enable[2]; + struct mvpp2_prs_entry pe; + u16 rvid, rmask; + int tid; + + /* Go through the all entries with MVPP2_PRS_LU_VID */ + for (tid = MVPP2_PE_VID_FILT_RANGE_START; + tid <= MVPP2_PE_VID_FILT_RANGE_END; tid++) { + if (!priv->prs_shadow[tid].valid || + priv->prs_shadow[tid].lu != MVPP2_PRS_LU_VID) + continue; + + pe.index = tid; + + mvpp2_prs_hw_read(priv, &pe); + mvpp2_prs_tcam_data_byte_get(&pe, 2, &byte[0], &enable[0]); + mvpp2_prs_tcam_data_byte_get(&pe, 3, &byte[1], &enable[1]); + + rvid = ((byte[0] & 0xf) << 8) + byte[1]; + rmask = ((enable[0] & 0xf) << 8) + enable[1]; + + if (rvid != vid || rmask != mask) + continue; + + return tid; + } + + return 0; +} + +/* Write parser entry for VID filtering */ +static int mvpp2_prs_vid_entry_add(struct mvpp2_port *port, u16 vid) +{ + unsigned int vid_start = MVPP2_PE_VID_FILT_RANGE_START + + port->id * MVPP2_PRS_VLAN_FILT_MAX; + unsigned int mask = 0xfff, reg_val, shift; + struct mvpp2 *priv = port->priv; + struct mvpp2_prs_entry pe; + int tid; + + /* Scan TCAM and see if entry with this <vid,port> already exist */ + tid = mvpp2_prs_vid_range_find(priv, (1 << port->id), vid, mask); + + reg_val = mvpp2_read(priv, MVPP2_MH_REG(port->id)); + if (reg_val & MVPP2_DSA_EXTENDED) + shift = MVPP2_VLAN_TAG_EDSA_LEN; + else + shift = MVPP2_VLAN_TAG_LEN; + + /* No such entry */ + if (!tid) { + memset(&pe, 0, sizeof(pe)); + + /* Go through all entries from first to last in vlan range */ + tid = mvpp2_prs_tcam_first_free(priv, vid_start, + vid_start + + MVPP2_PRS_VLAN_FILT_MAX_ENTRY); + + /* There isn't room for a new VID filter */ + if (tid < 0) + return tid; + + mvpp2_prs_tcam_lu_set(&pe, MVPP2_PRS_LU_VID); + pe.index = tid; + + /* Mask all ports */ + mvpp2_prs_tcam_port_map_set(&pe, 0); + } else { + mvpp2_prs_hw_read(priv, &pe); + } + + /* Enable the current port */ + mvpp2_prs_tcam_port_set(&pe, port->id, true); + + /* Continue - set next lookup */ + mvpp2_prs_sram_next_lu_set(&pe, MVPP2_PRS_LU_L2); + + /* Skip VLAN header - Set offset to 4 or 8 bytes */ + mvpp2_prs_sram_shift_set(&pe, shift, MVPP2_PRS_SRAM_OP_SEL_SHIFT_ADD); + + /* Set match on VID */ + mvpp2_prs_match_vid(&pe, MVPP2_PRS_VID_TCAM_BYTE, vid); + + /* Clear all ai bits for next iteration */ + mvpp2_prs_sram_ai_update(&pe, 0, MVPP2_PRS_SRAM_AI_MASK); + + /* Update shadow table */ + mvpp2_prs_shadow_set(priv, pe.index, MVPP2_PRS_LU_VID); + mvpp2_prs_hw_write(priv, &pe); + + return 0; +} + +/* Write parser entry for VID filtering */ +static void mvpp2_prs_vid_entry_remove(struct mvpp2_port *port, u16 vid) +{ + struct mvpp2 *priv = port->priv; + int tid; + + /* Scan TCAM and see if entry with this <vid,port> already exist */ + tid = mvpp2_prs_vid_range_find(priv, (1 << port->id), vid, 0xfff); + + /* No such entry */ + if (tid) + return; + + mvpp2_prs_hw_inv(priv, tid); + priv->prs_shadow[tid].valid = false; +} + +/* Remove all existing VID filters on this port */ +static void mvpp2_prs_vid_remove_all(struct mvpp2_port *port) +{ + struct mvpp2 *priv = port->priv; + int tid; + + for (tid = MVPP2_PRS_VID_PORT_FIRST(port->id); + tid <= MVPP2_PRS_VID_PORT_LAST(port->id); tid++) { + if (priv->prs_shadow[tid].valid) + mvpp2_prs_vid_entry_remove(port, tid); + } +} + +/* Remove VID filering entry for this port */ +static void mvpp2_prs_vid_disable_filtering(struct mvpp2_port *port) +{ + unsigned int tid = MVPP2_PRS_VID_PORT_DFLT(port->id); + struct mvpp2 *priv = port->priv; + + /* Invalidate the guard entry */ + mvpp2_prs_hw_inv(priv, tid); + + priv->prs_shadow[tid].valid = false; +} + +/* Add guard entry that drops packets when no VID is matched on this port */ +static void mvpp2_prs_vid_enable_filtering(struct mvpp2_port *port) +{ + unsigned int tid = MVPP2_PRS_VID_PORT_DFLT(port->id); + struct mvpp2 *priv = port->priv; + unsigned int reg_val, shift; + struct mvpp2_prs_entry pe; + + if (priv->prs_shadow[tid].valid) + return; + + memset(&pe, 0, sizeof(pe)); + + pe.index = tid; + + reg_val = mvpp2_read(priv, MVPP2_MH_REG(port->id)); + if (reg_val & MVPP2_DSA_EXTENDED) + shift = MVPP2_VLAN_TAG_EDSA_LEN; + else + shift = MVPP2_VLAN_TAG_LEN; + + mvpp2_prs_tcam_lu_set(&pe, MVPP2_PRS_LU_VID); + + /* Mask all ports */ + mvpp2_prs_tcam_port_map_set(&pe, 0); + + /* Update port mask */ + mvpp2_prs_tcam_port_set(&pe, port->id, true); + + /* Continue - set next lookup */ + mvpp2_prs_sram_next_lu_set(&pe, MVPP2_PRS_LU_L2); + + /* Skip VLAN header - Set offset to 4 or 8 bytes */ + mvpp2_prs_sram_shift_set(&pe, shift, MVPP2_PRS_SRAM_OP_SEL_SHIFT_ADD); + + /* Drop VLAN packets that don't belong to any VIDs on this port */ + mvpp2_prs_sram_ri_update(&pe, MVPP2_PRS_RI_DROP_MASK, + MVPP2_PRS_RI_DROP_MASK); + + /* Clear all ai bits for next iteration */ + mvpp2_prs_sram_ai_update(&pe, 0, MVPP2_PRS_SRAM_AI_MASK); + + /* Update shadow table */ + mvpp2_prs_shadow_set(priv, pe.index, MVPP2_PRS_LU_VID); + mvpp2_prs_hw_write(priv, &pe); +} + /* Parser default initialization */ static int mvpp2_prs_default_init(struct platform_device *pdev, struct mvpp2 *priv) @@ -3429,6 +3736,8 @@ static int mvpp2_prs_default_init(struct platform_device *pdev, mvpp2_prs_dsa_init(priv); + mvpp2_prs_vid_init(priv); + err = mvpp2_prs_etype_init(priv); if (err) return err; @@ -3901,7 +4210,6 @@ static int mvpp2_bm_pool_create(struct platform_device *pdev, val |= MVPP2_BM_START_MASK; mvpp2_write(priv, MVPP2_BM_POOL_CTRL_REG(bm_pool->id), val); - bm_pool->type = MVPP2_BM_FREE; bm_pool->size = size; bm_pool->pkt_size = 0; bm_pool->buf_num = 0; @@ -3954,11 +4262,17 @@ static void mvpp2_bm_bufs_get_addrs(struct device *dev, struct mvpp2 *priv, /* Free all buffers from the pool */ static void mvpp2_bm_bufs_free(struct device *dev, struct mvpp2 *priv, - struct mvpp2_bm_pool *bm_pool) + struct mvpp2_bm_pool *bm_pool, int buf_num) { int i; - for (i = 0; i < bm_pool->buf_num; i++) { + if (buf_num > bm_pool->buf_num) { + WARN(1, "Pool does not have so many bufs pool(%d) bufs(%d)\n", + bm_pool->id, buf_num); + buf_num = bm_pool->buf_num; + } + + for (i = 0; i < buf_num; i++) { dma_addr_t buf_dma_addr; phys_addr_t buf_phys_addr; void *data; @@ -3980,16 +4294,39 @@ static void mvpp2_bm_bufs_free(struct device *dev, struct mvpp2 *priv, bm_pool->buf_num -= i; } +/* Check number of buffers in BM pool */ +int mvpp2_check_hw_buf_num(struct mvpp2 *priv, struct mvpp2_bm_pool *bm_pool) +{ + int buf_num = 0; + + buf_num += mvpp2_read(priv, MVPP2_BM_POOL_PTRS_NUM_REG(bm_pool->id)) & + MVPP22_BM_POOL_PTRS_NUM_MASK; + buf_num += mvpp2_read(priv, MVPP2_BM_BPPI_PTRS_NUM_REG(bm_pool->id)) & + MVPP2_BM_BPPI_PTR_NUM_MASK; + + /* HW has one buffer ready which is not reflected in the counters */ + if (buf_num) + buf_num += 1; + + return buf_num; +} + /* Cleanup pool */ static int mvpp2_bm_pool_destroy(struct platform_device *pdev, struct mvpp2 *priv, struct mvpp2_bm_pool *bm_pool) { + int buf_num; u32 val; - mvpp2_bm_bufs_free(&pdev->dev, priv, bm_pool); - if (bm_pool->buf_num) { - WARN(1, "cannot free all buffers in pool %d\n", bm_pool->id); + buf_num = mvpp2_check_hw_buf_num(priv, bm_pool); + mvpp2_bm_bufs_free(&pdev->dev, priv, bm_pool, buf_num); + + /* Check buffer counters after free */ + buf_num = mvpp2_check_hw_buf_num(priv, bm_pool); + if (buf_num) { + WARN(1, "cannot free all buffers in pool %d, buf_num left %d\n", + bm_pool->id, bm_pool->buf_num); return 0; } @@ -4051,6 +4388,21 @@ static int mvpp2_bm_init(struct platform_device *pdev, struct mvpp2 *priv) return 0; } +static void mvpp2_setup_bm_pool(void) +{ + /* Short pool */ + mvpp2_pools[MVPP2_BM_SHORT].buf_num = MVPP2_BM_SHORT_BUF_NUM; + mvpp2_pools[MVPP2_BM_SHORT].pkt_size = MVPP2_BM_SHORT_PKT_SIZE; + + /* Long pool */ + mvpp2_pools[MVPP2_BM_LONG].buf_num = MVPP2_BM_LONG_BUF_NUM; + mvpp2_pools[MVPP2_BM_LONG].pkt_size = MVPP2_BM_LONG_PKT_SIZE; + + /* Jumbo pool */ + mvpp2_pools[MVPP2_BM_JUMBO].buf_num = MVPP2_BM_JUMBO_BUF_NUM; + mvpp2_pools[MVPP2_BM_JUMBO].pkt_size = MVPP2_BM_JUMBO_PKT_SIZE; +} + /* Attach long pool to rxq */ static void mvpp2_rxq_long_pool_set(struct mvpp2_port *port, int lrxq, int long_pool) @@ -4189,13 +4541,11 @@ static int mvpp2_bm_bufs_add(struct mvpp2_port *port, bm_pool->buf_num += i; netdev_dbg(port->dev, - "%s pool %d: pkt_size=%4d, buf_size=%4d, total_size=%4d\n", - bm_pool->type == MVPP2_BM_SWF_SHORT ? "short" : " long", + "pool %d: pkt_size=%4d, buf_size=%4d, total_size=%4d\n", bm_pool->id, bm_pool->pkt_size, buf_size, total_size); netdev_dbg(port->dev, - "%s pool %d: %d of %d buffers added\n", - bm_pool->type == MVPP2_BM_SWF_SHORT ? "short" : " long", + "pool %d: %d of %d buffers added\n", bm_pool->id, i, buf_num); return i; } @@ -4204,25 +4554,20 @@ static int mvpp2_bm_bufs_add(struct mvpp2_port *port, * pool pointer on success */ static struct mvpp2_bm_pool * -mvpp2_bm_pool_use(struct mvpp2_port *port, int pool, enum mvpp2_bm_type type, - int pkt_size) +mvpp2_bm_pool_use(struct mvpp2_port *port, unsigned pool, int pkt_size) { struct mvpp2_bm_pool *new_pool = &port->priv->bm_pools[pool]; int num; - if (new_pool->type != MVPP2_BM_FREE && new_pool->type != type) { - netdev_err(port->dev, "mixing pool types is forbidden\n"); + if (pool >= MVPP2_BM_POOLS_NUM) { + netdev_err(port->dev, "Invalid pool %d\n", pool); return NULL; } - if (new_pool->type == MVPP2_BM_FREE) - new_pool->type = type; - /* Allocate buffers in case BM pool is used as long pool, but packet * size doesn't match MTU or BM pool hasn't being used yet */ - if (((type == MVPP2_BM_SWF_LONG) && (pkt_size > new_pool->pkt_size)) || - (new_pool->pkt_size == 0)) { + if (new_pool->pkt_size == 0) { int pkts_num; /* Set default buffer number or free all the buffers in case @@ -4230,12 +4575,10 @@ mvpp2_bm_pool_use(struct mvpp2_port *port, int pool, enum mvpp2_bm_type type, */ pkts_num = new_pool->buf_num; if (pkts_num == 0) - pkts_num = type == MVPP2_BM_SWF_LONG ? - MVPP2_BM_LONG_BUF_NUM : - MVPP2_BM_SHORT_BUF_NUM; + pkts_num = mvpp2_pools[pool].buf_num; else mvpp2_bm_bufs_free(port->dev->dev.parent, - port->priv, new_pool); + port->priv, new_pool, pkts_num); new_pool->pkt_size = pkt_size; new_pool->frag_size = @@ -4261,16 +4604,28 @@ mvpp2_bm_pool_use(struct mvpp2_port *port, int pool, enum mvpp2_bm_type type, static int mvpp2_swf_bm_pool_init(struct mvpp2_port *port) { int rxq; + enum mvpp2_bm_pool_log_num long_log_pool, short_log_pool; + + /* If port pkt_size is higher than 1518B: + * HW Long pool - SW Jumbo pool, HW Short pool - SW Long pool + * else: HW Long pool - SW Long pool, HW Short pool - SW Short pool + */ + if (port->pkt_size > MVPP2_BM_LONG_PKT_SIZE) { + long_log_pool = MVPP2_BM_JUMBO; + short_log_pool = MVPP2_BM_LONG; + } else { + long_log_pool = MVPP2_BM_LONG; + short_log_pool = MVPP2_BM_SHORT; + } if (!port->pool_long) { port->pool_long = - mvpp2_bm_pool_use(port, MVPP2_BM_SWF_LONG_POOL(port->id), - MVPP2_BM_SWF_LONG, - port->pkt_size); + mvpp2_bm_pool_use(port, long_log_pool, + mvpp2_pools[long_log_pool].pkt_size); if (!port->pool_long) return -ENOMEM; - port->pool_long->port_map |= (1 << port->id); + port->pool_long->port_map |= BIT(port->id); for (rxq = 0; rxq < port->nrxqs; rxq++) mvpp2_rxq_long_pool_set(port, rxq, port->pool_long->id); @@ -4278,13 +4633,12 @@ static int mvpp2_swf_bm_pool_init(struct mvpp2_port *port) if (!port->pool_short) { port->pool_short = - mvpp2_bm_pool_use(port, MVPP2_BM_SWF_SHORT_POOL, - MVPP2_BM_SWF_SHORT, - MVPP2_BM_SHORT_PKT_SIZE); + mvpp2_bm_pool_use(port, short_log_pool, + mvpp2_pools[long_log_pool].pkt_size); if (!port->pool_short) return -ENOMEM; - port->pool_short->port_map |= (1 << port->id); + port->pool_short->port_map |= BIT(port->id); for (rxq = 0; rxq < port->nrxqs; rxq++) mvpp2_rxq_short_pool_set(port, rxq, @@ -4297,30 +4651,49 @@ static int mvpp2_swf_bm_pool_init(struct mvpp2_port *port) static int mvpp2_bm_update_mtu(struct net_device *dev, int mtu) { struct mvpp2_port *port = netdev_priv(dev); - struct mvpp2_bm_pool *port_pool = port->pool_long; - int num, pkts_num = port_pool->buf_num; + enum mvpp2_bm_pool_log_num new_long_pool; int pkt_size = MVPP2_RX_PKT_SIZE(mtu); - /* Update BM pool with new buffer size */ - mvpp2_bm_bufs_free(dev->dev.parent, port->priv, port_pool); - if (port_pool->buf_num) { - WARN(1, "cannot free all buffers in pool %d\n", port_pool->id); - return -EIO; - } - - port_pool->pkt_size = pkt_size; - port_pool->frag_size = SKB_DATA_ALIGN(MVPP2_RX_BUF_SIZE(pkt_size)) + - MVPP2_SKB_SHINFO_SIZE; - num = mvpp2_bm_bufs_add(port, port_pool, pkts_num); - if (num != pkts_num) { - WARN(1, "pool %d: %d of %d allocated\n", - port_pool->id, num, pkts_num); - return -EIO; + /* If port MTU is higher than 1518B: + * HW Long pool - SW Jumbo pool, HW Short pool - SW Long pool + * else: HW Long pool - SW Long pool, HW Short pool - SW Short pool + */ + if (pkt_size > MVPP2_BM_LONG_PKT_SIZE) + new_long_pool = MVPP2_BM_JUMBO; + else + new_long_pool = MVPP2_BM_LONG; + + if (new_long_pool != port->pool_long->id) { + /* Remove port from old short & long pool */ + port->pool_long = mvpp2_bm_pool_use(port, port->pool_long->id, + port->pool_long->pkt_size); + port->pool_long->port_map &= ~BIT(port->id); + port->pool_long = NULL; + + port->pool_short = mvpp2_bm_pool_use(port, port->pool_short->id, + port->pool_short->pkt_size); + port->pool_short->port_map &= ~BIT(port->id); + port->pool_short = NULL; + + port->pkt_size = pkt_size; + + /* Add port to new short & long pool */ + mvpp2_swf_bm_pool_init(port); + + /* Update L4 checksum when jumbo enable/disable on port */ + if (new_long_pool == MVPP2_BM_JUMBO && port->id != 0) { + dev->features &= ~(NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM); + dev->hw_features &= ~(NETIF_F_IP_CSUM | + NETIF_F_IPV6_CSUM); + } else { + dev->features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM; + dev->hw_features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM; + } } - mvpp2_bm_pool_bufsize_set(port->priv, port_pool, - MVPP2_RX_BUF_SIZE(port_pool->pkt_size)); dev->mtu = mtu; + dev->wanted_features = dev->features; + netdev_update_features(dev); return 0; } @@ -7153,6 +7526,12 @@ retry: } } } + + /* Disable VLAN filtering in promiscuous mode */ + if (dev->flags & IFF_PROMISC) + mvpp2_prs_vid_disable_filtering(port); + else + mvpp2_prs_vid_enable_filtering(port); } static int mvpp2_set_mac_address(struct net_device *dev, void *p) @@ -7292,6 +7671,48 @@ static int mvpp2_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) return ret; } +static int mvpp2_vlan_rx_add_vid(struct net_device *dev, __be16 proto, u16 vid) +{ + struct mvpp2_port *port = netdev_priv(dev); + int ret; + + ret = mvpp2_prs_vid_entry_add(port, vid); + if (ret) + netdev_err(dev, "rx-vlan-filter offloading cannot accept more than %d VIDs per port\n", + MVPP2_PRS_VLAN_FILT_MAX - 1); + return ret; +} + +static int mvpp2_vlan_rx_kill_vid(struct net_device *dev, __be16 proto, u16 vid) +{ + struct mvpp2_port *port = netdev_priv(dev); + + mvpp2_prs_vid_entry_remove(port, vid); + return 0; +} + +static int mvpp2_set_features(struct net_device *dev, + netdev_features_t features) +{ + netdev_features_t changed = dev->features ^ features; + struct mvpp2_port *port = netdev_priv(dev); + + if (changed & NETIF_F_HW_VLAN_CTAG_FILTER) { + if (features & NETIF_F_HW_VLAN_CTAG_FILTER) { + mvpp2_prs_vid_enable_filtering(port); + } else { + /* Invalidate all registered VID filters for this + * port + */ + mvpp2_prs_vid_remove_all(port); + + mvpp2_prs_vid_disable_filtering(port); + } + } + + return 0; +} + /* Ethtool methods */ /* Set interrupt coalescing for ethtools */ @@ -7433,6 +7854,9 @@ static const struct net_device_ops mvpp2_netdev_ops = { .ndo_change_mtu = mvpp2_change_mtu, .ndo_get_stats64 = mvpp2_get_stats64, .ndo_do_ioctl = mvpp2_ioctl, + .ndo_vlan_rx_add_vid = mvpp2_vlan_rx_add_vid, + .ndo_vlan_rx_kill_vid = mvpp2_vlan_rx_kill_vid, + .ndo_set_features = mvpp2_set_features, }; static const struct ethtool_ops mvpp2_eth_tool_ops = { @@ -7943,16 +8367,24 @@ static int mvpp2_port_probe(struct platform_device *pdev, } } - features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_TSO; + features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | + NETIF_F_TSO; dev->features = features | NETIF_F_RXCSUM; - dev->hw_features |= features | NETIF_F_RXCSUM | NETIF_F_GRO; + dev->hw_features |= features | NETIF_F_RXCSUM | NETIF_F_GRO | + NETIF_F_HW_VLAN_CTAG_FILTER; + + if (port->pool_long->id == MVPP2_BM_JUMBO && port->id != 0) { + dev->features &= ~(NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM); + dev->hw_features &= ~(NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM); + } + dev->vlan_features |= features; dev->gso_max_segs = MVPP2_MAX_TSO_SEGS; - /* MTU range: 68 - 9676 */ + /* MTU range: 68 - 9704 */ dev->min_mtu = ETH_MIN_MTU; - /* 9676 == 9700 - 20 and rounding to 8 */ - dev->max_mtu = 9676; + /* 9704 == 9728 - 20 and rounding to 8 */ + dev->max_mtu = MVPP2_BM_JUMBO_PKT_SIZE; err = register_netdev(dev); if (err < 0) { @@ -8083,14 +8515,25 @@ static void mvpp22_rx_fifo_init(struct mvpp2 *priv) mvpp2_write(priv, MVPP2_RX_FIFO_INIT_REG, 0x1); } -/* Initialize Tx FIFO's */ +/* Initialize Tx FIFO's: the total FIFO size is 19kB on PPv2.2 and 10G + * interfaces must have a Tx FIFO size of 10kB. As only port 0 can do 10G, + * configure its Tx FIFO size to 10kB and the others ports Tx FIFO size to 3kB. + */ static void mvpp22_tx_fifo_init(struct mvpp2 *priv) { - int port; + int port, size, thrs; - for (port = 0; port < MVPP2_MAX_PORTS; port++) - mvpp2_write(priv, MVPP22_TX_FIFO_SIZE_REG(port), - MVPP22_TX_FIFO_DATA_SIZE_3KB); + for (port = 0; port < MVPP2_MAX_PORTS; port++) { + if (port == 0) { + size = MVPP22_TX_FIFO_DATA_SIZE_10KB; + thrs = MVPP2_TX_FIFO_THRESHOLD_10KB; + } else { + size = MVPP22_TX_FIFO_DATA_SIZE_3KB; + thrs = MVPP2_TX_FIFO_THRESHOLD_3KB; + } + mvpp2_write(priv, MVPP22_TX_FIFO_SIZE_REG(port), size); + mvpp2_write(priv, MVPP22_TX_FIFO_THRESH_REG(port), thrs); + } } static void mvpp2_axi_init(struct mvpp2 *priv) @@ -8284,6 +8727,8 @@ static int mvpp2_probe(struct platform_device *pdev) priv->sysctrl_base = NULL; } + mvpp2_setup_bm_pool(); + for (i = 0; i < MVPP2_MAX_THREADS; i++) { u32 addr_space_sz; diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c index ebc1f566a4d9..9a7a2f05ab35 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c @@ -199,6 +199,10 @@ static const char main_strings[][ETH_GSTRING_LEN] = { "rx_xdp_drop", "rx_xdp_tx", "rx_xdp_tx_full", + + /* phy statistics */ + "rx_packets_phy", "rx_bytes_phy", + "tx_packets_phy", "tx_bytes_phy", }; static const char mlx4_en_test_names[][ETH_GSTRING_LEN]= { @@ -411,6 +415,10 @@ static void mlx4_en_get_ethtool_stats(struct net_device *dev, if (bitmap_iterator_test(&it)) data[index++] = ((unsigned long *)&priv->xdp_stats)[i]; + for (i = 0; i < NUM_PHY_STATS; i++, bitmap_iterator_inc(&it)) + if (bitmap_iterator_test(&it)) + data[index++] = ((unsigned long *)&priv->phy_stats)[i]; + for (i = 0; i < priv->tx_ring_num[TX]; i++) { data[index++] = priv->tx_ring[TX][i]->packets; data[index++] = priv->tx_ring[TX][i]->bytes; @@ -490,6 +498,12 @@ static void mlx4_en_get_strings(struct net_device *dev, strcpy(data + (index++) * ETH_GSTRING_LEN, main_strings[strings]); + for (i = 0; i < NUM_PHY_STATS; i++, strings++, + bitmap_iterator_inc(&it)) + if (bitmap_iterator_test(&it)) + strcpy(data + (index++) * ETH_GSTRING_LEN, + main_strings[strings]); + for (i = 0; i < priv->tx_ring_num[TX]; i++) { sprintf(data + (index++) * ETH_GSTRING_LEN, "tx%d_packets", i); diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index 8fc51bc29003..e0adac4a9a19 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -3256,6 +3256,10 @@ void mlx4_en_set_stats_bitmap(struct mlx4_dev *dev, bitmap_set(stats_bitmap->bitmap, last_i, NUM_XDP_STATS); last_i += NUM_XDP_STATS; + + if (!mlx4_is_slave(dev)) + bitmap_set(stats_bitmap->bitmap, last_i, NUM_PHY_STATS); + last_i += NUM_PHY_STATS; } int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port, @@ -3630,10 +3634,6 @@ int mlx4_en_reset_config(struct net_device *dev, mlx4_en_stop_port(dev, 1); } - en_warn(priv, "Changing device configuration rx filter(%x) rx vlan(%x)\n", - ts_config.rx_filter, - !!(features & NETIF_F_HW_VLAN_CTAG_RX)); - mlx4_en_safe_replace_resources(priv, tmp); if (DEV_FEATURE_CHANGED(dev, features, NETIF_F_HW_VLAN_CTAG_RX)) { diff --git a/drivers/net/ethernet/mellanox/mlx4/en_port.c b/drivers/net/ethernet/mellanox/mlx4/en_port.c index 1fa4849a6f56..0158b88bea5b 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_port.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_port.c @@ -275,19 +275,31 @@ int mlx4_en_DUMP_ETH_STATS(struct mlx4_en_dev *mdev, u8 port, u8 reset) priv->port_stats.xmit_more += READ_ONCE(ring->xmit_more); } - if (mlx4_is_master(mdev->dev)) { - stats->rx_packets = en_stats_adder(&mlx4_en_stats->RTOT_prio_0, - &mlx4_en_stats->RTOT_prio_1, - NUM_PRIORITIES); - stats->tx_packets = en_stats_adder(&mlx4_en_stats->TTOT_prio_0, - &mlx4_en_stats->TTOT_prio_1, - NUM_PRIORITIES); - stats->rx_bytes = en_stats_adder(&mlx4_en_stats->ROCT_prio_0, - &mlx4_en_stats->ROCT_prio_1, - NUM_PRIORITIES); - stats->tx_bytes = en_stats_adder(&mlx4_en_stats->TOCT_prio_0, - &mlx4_en_stats->TOCT_prio_1, - NUM_PRIORITIES); + if (!mlx4_is_slave(mdev->dev)) { + struct mlx4_en_phy_stats *p_stats = &priv->phy_stats; + + p_stats->rx_packets_phy = + en_stats_adder(&mlx4_en_stats->RTOT_prio_0, + &mlx4_en_stats->RTOT_prio_1, + NUM_PRIORITIES); + p_stats->tx_packets_phy = + en_stats_adder(&mlx4_en_stats->TTOT_prio_0, + &mlx4_en_stats->TTOT_prio_1, + NUM_PRIORITIES); + p_stats->rx_bytes_phy = + en_stats_adder(&mlx4_en_stats->ROCT_prio_0, + &mlx4_en_stats->ROCT_prio_1, + NUM_PRIORITIES); + p_stats->tx_bytes_phy = + en_stats_adder(&mlx4_en_stats->TOCT_prio_0, + &mlx4_en_stats->TOCT_prio_1, + NUM_PRIORITIES); + if (mlx4_is_master(mdev->dev)) { + stats->rx_packets = p_stats->rx_packets_phy; + stats->tx_packets = p_stats->tx_packets_phy; + stats->rx_bytes = p_stats->rx_bytes_phy; + stats->tx_bytes = p_stats->tx_bytes_phy; + } } /* net device stats */ diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c index b4d144e67514..c2c6bd7578fd 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c @@ -649,6 +649,12 @@ static int check_csum(struct mlx4_cqe *cqe, struct sk_buff *skb, void *va, return get_fixed_ipv4_csum(hw_checksum, skb, hdr); } +#if IS_ENABLED(CONFIG_IPV6) +#define MLX4_CQE_STATUS_IP_ANY (MLX4_CQE_STATUS_IPV4 | MLX4_CQE_STATUS_IPV6) +#else +#define MLX4_CQE_STATUS_IP_ANY (MLX4_CQE_STATUS_IPV4) +#endif + int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int budget) { struct mlx4_en_priv *priv = netdev_priv(dev); @@ -662,12 +668,9 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud int polled = 0; int index; - if (unlikely(!priv->port_up)) + if (unlikely(!priv->port_up || budget <= 0)) return 0; - if (unlikely(budget <= 0)) - return polled; - ring = priv->rx_ring[cq_ring]; /* Protect accesses to: ring->xdp_prog, priv->mac_hash list */ @@ -838,12 +841,7 @@ xdp_drop_no_cnt: ring->csum_ok++; } else { if (!(priv->flags & MLX4_EN_FLAG_RX_CSUM_NON_TCP_UDP && - (cqe->status & cpu_to_be16(MLX4_CQE_STATUS_IPV4 | -#if IS_ENABLED(CONFIG_IPV6) - MLX4_CQE_STATUS_IPV6)))) -#else - 0)))) -#endif + (cqe->status & cpu_to_be16(MLX4_CQE_STATUS_IP_ANY)))) goto csum_none; if (check_csum(cqe, skb, va, dev->features)) goto csum_none; diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h index f470ae37d937..f7c81133594f 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h @@ -608,6 +608,7 @@ struct mlx4_en_priv { struct mlx4_en_flow_stats_tx tx_flowstats; struct mlx4_en_port_stats port_stats; struct mlx4_en_xdp_stats xdp_stats; + struct mlx4_en_phy_stats phy_stats; struct mlx4_en_stats_bitmap stats_bitmap; struct list_head mc_list; struct list_head curr_list; diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_stats.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_stats.h index aab28eb27a30..86b6051da8ec 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4_stats.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_stats.h @@ -63,6 +63,14 @@ struct mlx4_en_xdp_stats { #define NUM_XDP_STATS 3 }; +struct mlx4_en_phy_stats { + unsigned long rx_packets_phy; + unsigned long rx_bytes_phy; + unsigned long tx_packets_phy; + unsigned long tx_bytes_phy; +#define NUM_PHY_STATS 4 +}; + #define NUM_MAIN_STATS 21 #define MLX4_NUM_PRIORITIES 8 @@ -116,7 +124,7 @@ enum { #define NUM_ALL_STATS (NUM_MAIN_STATS + NUM_PORT_STATS + NUM_PKT_STATS + \ NUM_FLOW_STATS + NUM_PERF_STATS + NUM_PF_STATS + \ - NUM_XDP_STATS) + NUM_XDP_STATS + NUM_PHY_STATS) #define MLX4_FIND_NETDEV_STAT(n) (offsetof(struct net_device_stats, n) / \ sizeof(((struct net_device_stats *)0)->n)) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/alloc.c b/drivers/net/ethernet/mellanox/mlx5/core/alloc.c index 47239bf7bf43..323ffe8bf7e4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/alloc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/alloc.c @@ -71,19 +71,24 @@ static void *mlx5_dma_zalloc_coherent_node(struct mlx5_core_dev *dev, } int mlx5_buf_alloc_node(struct mlx5_core_dev *dev, int size, - struct mlx5_buf *buf, int node) + struct mlx5_frag_buf *buf, int node) { dma_addr_t t; buf->size = size; buf->npages = 1; buf->page_shift = (u8)get_order(size) + PAGE_SHIFT; - buf->direct.buf = mlx5_dma_zalloc_coherent_node(dev, size, - &t, node); - if (!buf->direct.buf) + + buf->frags = kzalloc(sizeof(*buf->frags), GFP_KERNEL); + if (!buf->frags) return -ENOMEM; - buf->direct.map = t; + buf->frags->buf = mlx5_dma_zalloc_coherent_node(dev, size, + &t, node); + if (!buf->frags->buf) + goto err_out; + + buf->frags->map = t; while (t & ((1 << buf->page_shift) - 1)) { --buf->page_shift; @@ -91,18 +96,24 @@ int mlx5_buf_alloc_node(struct mlx5_core_dev *dev, int size, } return 0; +err_out: + kfree(buf->frags); + return -ENOMEM; } -int mlx5_buf_alloc(struct mlx5_core_dev *dev, int size, struct mlx5_buf *buf) +int mlx5_buf_alloc(struct mlx5_core_dev *dev, + int size, struct mlx5_frag_buf *buf) { return mlx5_buf_alloc_node(dev, size, buf, dev->priv.numa_node); } -EXPORT_SYMBOL_GPL(mlx5_buf_alloc); +EXPORT_SYMBOL(mlx5_buf_alloc); -void mlx5_buf_free(struct mlx5_core_dev *dev, struct mlx5_buf *buf) +void mlx5_buf_free(struct mlx5_core_dev *dev, struct mlx5_frag_buf *buf) { - dma_free_coherent(&dev->pdev->dev, buf->size, buf->direct.buf, - buf->direct.map); + dma_free_coherent(&dev->pdev->dev, buf->size, buf->frags->buf, + buf->frags->map); + + kfree(buf->frags); } EXPORT_SYMBOL_GPL(mlx5_buf_free); @@ -147,6 +158,7 @@ err_free_buf: err_out: return -ENOMEM; } +EXPORT_SYMBOL_GPL(mlx5_frag_buf_alloc_node); void mlx5_frag_buf_free(struct mlx5_core_dev *dev, struct mlx5_frag_buf *buf) { @@ -162,6 +174,7 @@ void mlx5_frag_buf_free(struct mlx5_core_dev *dev, struct mlx5_frag_buf *buf) } kfree(buf->frags); } +EXPORT_SYMBOL_GPL(mlx5_frag_buf_free); static struct mlx5_db_pgdir *mlx5_alloc_db_pgdir(struct mlx5_core_dev *dev, int node) @@ -275,13 +288,13 @@ void mlx5_db_free(struct mlx5_core_dev *dev, struct mlx5_db *db) } EXPORT_SYMBOL_GPL(mlx5_db_free); -void mlx5_fill_page_array(struct mlx5_buf *buf, __be64 *pas) +void mlx5_fill_page_array(struct mlx5_frag_buf *buf, __be64 *pas) { u64 addr; int i; for (i = 0; i < buf->npages; i++) { - addr = buf->direct.map + (i << buf->page_shift); + addr = buf->frags->map + (i << buf->page_shift); pas[i] = cpu_to_be64(addr); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cq.c b/drivers/net/ethernet/mellanox/mlx5/core/cq.c index 1016e05c7ec7..669ed16938b3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cq.c @@ -58,8 +58,7 @@ void mlx5_cq_tasklet_cb(unsigned long data) tasklet_ctx.list) { list_del_init(&mcq->tasklet_ctx.list); mcq->tasklet_ctx.comp(mcq); - if (refcount_dec_and_test(&mcq->refcount)) - complete(&mcq->free); + mlx5_cq_put(mcq); if (time_after(jiffies, end)) break; } @@ -80,69 +79,19 @@ static void mlx5_add_cq_to_tasklet(struct mlx5_core_cq *cq) * still arrive. */ if (list_empty_careful(&cq->tasklet_ctx.list)) { - refcount_inc(&cq->refcount); + mlx5_cq_hold(cq); list_add_tail(&cq->tasklet_ctx.list, &tasklet_ctx->list); } spin_unlock_irqrestore(&tasklet_ctx->lock, flags); } -void mlx5_cq_completion(struct mlx5_core_dev *dev, u32 cqn) -{ - struct mlx5_core_cq *cq; - struct mlx5_cq_table *table = &dev->priv.cq_table; - - spin_lock(&table->lock); - cq = radix_tree_lookup(&table->tree, cqn); - if (likely(cq)) - refcount_inc(&cq->refcount); - spin_unlock(&table->lock); - - if (!cq) { - mlx5_core_warn(dev, "Completion event for bogus CQ 0x%x\n", cqn); - return; - } - - ++cq->arm_sn; - - cq->comp(cq); - - if (refcount_dec_and_test(&cq->refcount)) - complete(&cq->free); -} - -void mlx5_cq_event(struct mlx5_core_dev *dev, u32 cqn, int event_type) -{ - struct mlx5_cq_table *table = &dev->priv.cq_table; - struct mlx5_core_cq *cq; - - spin_lock(&table->lock); - - cq = radix_tree_lookup(&table->tree, cqn); - if (cq) - refcount_inc(&cq->refcount); - - spin_unlock(&table->lock); - - if (!cq) { - mlx5_core_warn(dev, "Async event for bogus CQ 0x%x\n", cqn); - return; - } - - cq->event(cq, event_type); - - if (refcount_dec_and_test(&cq->refcount)) - complete(&cq->free); -} - int mlx5_core_create_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq, u32 *in, int inlen) { - struct mlx5_cq_table *table = &dev->priv.cq_table; + int eqn = MLX5_GET(cqc, MLX5_ADDR_OF(create_cq_in, in, cq_context), c_eqn); + u32 dout[MLX5_ST_SZ_DW(destroy_cq_out)]; u32 out[MLX5_ST_SZ_DW(create_cq_out)]; u32 din[MLX5_ST_SZ_DW(destroy_cq_in)]; - u32 dout[MLX5_ST_SZ_DW(destroy_cq_out)]; - int eqn = MLX5_GET(cqc, MLX5_ADDR_OF(create_cq_in, in, cq_context), - c_eqn); struct mlx5_eq *eq; int err; @@ -159,7 +108,9 @@ int mlx5_core_create_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq, cq->cqn = MLX5_GET(create_cq_out, out, cqn); cq->cons_index = 0; cq->arm_sn = 0; - refcount_set(&cq->refcount, 1); + cq->eq = eq; + refcount_set(&cq->refcount, 0); + mlx5_cq_hold(cq); init_completion(&cq->free); if (!cq->comp) cq->comp = mlx5_add_cq_to_tasklet; @@ -167,12 +118,16 @@ int mlx5_core_create_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq, cq->tasklet_ctx.priv = &eq->tasklet_ctx; INIT_LIST_HEAD(&cq->tasklet_ctx.list); - spin_lock_irq(&table->lock); - err = radix_tree_insert(&table->tree, cq->cqn, cq); - spin_unlock_irq(&table->lock); + /* Add to comp EQ CQ tree to recv comp events */ + err = mlx5_eq_add_cq(eq, cq); if (err) goto err_cmd; + /* Add to async EQ CQ tree to recv async events */ + err = mlx5_eq_add_cq(&dev->priv.eq_table.async_eq, cq); + if (err) + goto err_cq_add; + cq->pid = current->pid; err = mlx5_debug_cq_add(dev, cq); if (err) @@ -183,6 +138,8 @@ int mlx5_core_create_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq, return 0; +err_cq_add: + mlx5_eq_del_cq(eq, cq); err_cmd: memset(din, 0, sizeof(din)); memset(dout, 0, sizeof(dout)); @@ -195,23 +152,17 @@ EXPORT_SYMBOL(mlx5_core_create_cq); int mlx5_core_destroy_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq) { - struct mlx5_cq_table *table = &dev->priv.cq_table; u32 out[MLX5_ST_SZ_DW(destroy_cq_out)] = {0}; u32 in[MLX5_ST_SZ_DW(destroy_cq_in)] = {0}; - struct mlx5_core_cq *tmp; int err; - spin_lock_irq(&table->lock); - tmp = radix_tree_delete(&table->tree, cq->cqn); - spin_unlock_irq(&table->lock); - if (!tmp) { - mlx5_core_warn(dev, "cq 0x%x not found in tree\n", cq->cqn); - return -EINVAL; - } - if (tmp != cq) { - mlx5_core_warn(dev, "corruption on srqn 0x%x\n", cq->cqn); - return -EINVAL; - } + err = mlx5_eq_del_cq(&dev->priv.eq_table.async_eq, cq); + if (err) + return err; + + err = mlx5_eq_del_cq(cq->eq, cq); + if (err) + return err; MLX5_SET(destroy_cq_in, in, opcode, MLX5_CMD_OP_DESTROY_CQ); MLX5_SET(destroy_cq_in, in, cqn, cq->cqn); @@ -222,8 +173,7 @@ int mlx5_core_destroy_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq) synchronize_irq(cq->irqn); mlx5_debug_cq_remove(dev, cq); - if (refcount_dec_and_test(&cq->refcount)) - complete(&cq->free); + mlx5_cq_put(cq); wait_for_completion(&cq->free); return 0; @@ -270,21 +220,3 @@ int mlx5_core_modify_cq_moderation(struct mlx5_core_dev *dev, return mlx5_core_modify_cq(dev, cq, in, sizeof(in)); } EXPORT_SYMBOL(mlx5_core_modify_cq_moderation); - -int mlx5_init_cq_table(struct mlx5_core_dev *dev) -{ - struct mlx5_cq_table *table = &dev->priv.cq_table; - int err; - - memset(table, 0, sizeof(*table)); - spin_lock_init(&table->lock); - INIT_RADIX_TREE(&table->tree, GFP_ATOMIC); - err = mlx5_cq_debugfs_init(dev); - - return err; -} - -void mlx5_cleanup_cq_table(struct mlx5_core_dev *dev) -{ - mlx5_cq_debugfs_cleanup(dev); -} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/dev.c b/drivers/net/ethernet/mellanox/mlx5/core/dev.c index 17b723218b0c..b994b80d5714 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/dev.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/dev.c @@ -337,6 +337,14 @@ void mlx5_unregister_interface(struct mlx5_interface *intf) } EXPORT_SYMBOL(mlx5_unregister_interface); +void mlx5_reload_interface(struct mlx5_core_dev *mdev, int protocol) +{ + mutex_lock(&mlx5_intf_mutex); + mlx5_remove_dev_by_protocol(mdev, protocol); + mlx5_add_dev_by_protocol(mdev, protocol); + mutex_unlock(&mlx5_intf_mutex); +} + void *mlx5_get_protocol_dev(struct mlx5_core_dev *mdev, int protocol) { struct mlx5_priv *priv = &mdev->priv; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index 363d8dcb7f17..ea4b255380a2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -1156,6 +1156,15 @@ mlx5e_vport_rep_unload(struct mlx5_eswitch_rep *rep) kfree(ppriv); /* mlx5e_rep_priv */ } +static void *mlx5e_vport_rep_get_proto_dev(struct mlx5_eswitch_rep *rep) +{ + struct mlx5e_rep_priv *rpriv; + + rpriv = mlx5e_rep_to_rep_priv(rep); + + return rpriv->netdev; +} + static void mlx5e_rep_register_vf_vports(struct mlx5e_priv *priv) { struct mlx5_core_dev *mdev = priv->mdev; @@ -1168,6 +1177,7 @@ static void mlx5e_rep_register_vf_vports(struct mlx5e_priv *priv) rep_if.load = mlx5e_vport_rep_load; rep_if.unload = mlx5e_vport_rep_unload; + rep_if.get_proto_dev = mlx5e_vport_rep_get_proto_dev; mlx5_eswitch_register_vport_rep(esw, vport, &rep_if, REP_ETH); } } @@ -1195,6 +1205,7 @@ void mlx5e_register_vport_reps(struct mlx5e_priv *priv) rep_if.load = mlx5e_nic_rep_load; rep_if.unload = mlx5e_nic_rep_unload; + rep_if.get_proto_dev = mlx5e_vport_rep_get_proto_dev; rep_if.priv = rpriv; INIT_LIST_HEAD(&rpriv->vport_sqs_list); mlx5_eswitch_register_vport_rep(esw, 0, &rep_if, REP_ETH); /* UPLINK PF vport*/ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index e5c3ab46a24a..8cce90dc461d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -53,7 +53,7 @@ static inline bool mlx5e_rx_hw_stamp(struct hwtstamp_config *config) static inline void mlx5e_read_cqe_slot(struct mlx5e_cq *cq, u32 cqcc, void *data) { - u32 ci = cqcc & cq->wq.sz_m1; + u32 ci = cqcc & cq->wq.fbc.sz_m1; memcpy(data, mlx5_cqwq_get_wqe(&cq->wq, ci), sizeof(struct mlx5_cqe64)); } @@ -75,9 +75,10 @@ static inline void mlx5e_read_mini_arr_slot(struct mlx5e_cq *cq, u32 cqcc) static inline void mlx5e_cqes_update_owner(struct mlx5e_cq *cq, u32 cqcc, int n) { - u8 op_own = (cqcc >> cq->wq.log_sz) & 1; - u32 wq_sz = 1 << cq->wq.log_sz; - u32 ci = cqcc & cq->wq.sz_m1; + struct mlx5_frag_buf_ctrl *fbc = &cq->wq.fbc; + u8 op_own = (cqcc >> fbc->log_sz) & 1; + u32 wq_sz = 1 << fbc->log_sz; + u32 ci = cqcc & fbc->sz_m1; u32 ci_top = min_t(u32, wq_sz, ci + n); for (; ci < ci_top; ci++, n--) { @@ -102,7 +103,7 @@ static inline void mlx5e_decompress_cqe(struct mlx5e_rq *rq, cq->title.byte_cnt = cq->mini_arr[cq->mini_arr_idx].byte_cnt; cq->title.check_sum = cq->mini_arr[cq->mini_arr_idx].checksum; cq->title.op_own &= 0xf0; - cq->title.op_own |= 0x01 & (cqcc >> cq->wq.log_sz); + cq->title.op_own |= 0x01 & (cqcc >> cq->wq.fbc.log_sz); cq->title.wqe_counter = cpu_to_be16(cq->decmprs_wqe_counter); if (rq->wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c index 25106e996a96..c1c94974e16b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c @@ -393,6 +393,51 @@ static void general_event_handler(struct mlx5_core_dev *dev, } } +/* caller must eventually call mlx5_cq_put on the returned cq */ +static struct mlx5_core_cq *mlx5_eq_cq_get(struct mlx5_eq *eq, u32 cqn) +{ + struct mlx5_cq_table *table = &eq->cq_table; + struct mlx5_core_cq *cq = NULL; + + spin_lock(&table->lock); + cq = radix_tree_lookup(&table->tree, cqn); + if (likely(cq)) + mlx5_cq_hold(cq); + spin_unlock(&table->lock); + + return cq; +} + +static void mlx5_eq_cq_completion(struct mlx5_eq *eq, u32 cqn) +{ + struct mlx5_core_cq *cq = mlx5_eq_cq_get(eq, cqn); + + if (unlikely(!cq)) { + mlx5_core_warn(eq->dev, "Completion event for bogus CQ 0x%x\n", cqn); + return; + } + + ++cq->arm_sn; + + cq->comp(cq); + + mlx5_cq_put(cq); +} + +static void mlx5_eq_cq_event(struct mlx5_eq *eq, u32 cqn, int event_type) +{ + struct mlx5_core_cq *cq = mlx5_eq_cq_get(eq, cqn); + + if (unlikely(!cq)) { + mlx5_core_warn(eq->dev, "Async event for bogus CQ 0x%x\n", cqn); + return; + } + + cq->event(cq, event_type); + + mlx5_cq_put(cq); +} + static irqreturn_t mlx5_eq_int(int irq, void *eq_ptr) { struct mlx5_eq *eq = eq_ptr; @@ -415,7 +460,7 @@ static irqreturn_t mlx5_eq_int(int irq, void *eq_ptr) switch (eqe->type) { case MLX5_EVENT_TYPE_COMP: cqn = be32_to_cpu(eqe->data.comp.cqn) & 0xffffff; - mlx5_cq_completion(dev, cqn); + mlx5_eq_cq_completion(eq, cqn); break; case MLX5_EVENT_TYPE_DCT_DRAINED: rsn = be32_to_cpu(eqe->data.dct.dctn) & 0xffffff; @@ -472,7 +517,7 @@ static irqreturn_t mlx5_eq_int(int irq, void *eq_ptr) cqn = be32_to_cpu(eqe->data.cq_err.cqn) & 0xffffff; mlx5_core_warn(dev, "CQ error on CQN 0x%x, syndrome 0x%x\n", cqn, eqe->data.cq_err.syndrome); - mlx5_cq_event(dev, cqn, eqe->type); + mlx5_eq_cq_event(eq, cqn, eqe->type); break; case MLX5_EVENT_TYPE_PAGE_REQUEST: @@ -567,6 +612,7 @@ int mlx5_create_map_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq, u8 vecidx, int nent, u64 mask, const char *name, enum mlx5_eq_type type) { + struct mlx5_cq_table *cq_table = &eq->cq_table; u32 out[MLX5_ST_SZ_DW(create_eq_out)] = {0}; struct mlx5_priv *priv = &dev->priv; irq_handler_t handler; @@ -576,6 +622,11 @@ int mlx5_create_map_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq, u8 vecidx, u32 *in; int err; + /* Init CQ table */ + memset(cq_table, 0, sizeof(*cq_table)); + spin_lock_init(&cq_table->lock); + INIT_RADIX_TREE(&cq_table->tree, GFP_ATOMIC); + eq->type = type; eq->nent = roundup_pow_of_two(nent + MLX5_NUM_SPARE_EQE); eq->cons_index = 0; @@ -669,7 +720,6 @@ err_buf: mlx5_buf_free(dev, &eq->buf); return err; } -EXPORT_SYMBOL_GPL(mlx5_create_map_eq); int mlx5_destroy_unmap_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq) { @@ -696,7 +746,40 @@ int mlx5_destroy_unmap_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq) return err; } -EXPORT_SYMBOL_GPL(mlx5_destroy_unmap_eq); + +int mlx5_eq_add_cq(struct mlx5_eq *eq, struct mlx5_core_cq *cq) +{ + struct mlx5_cq_table *table = &eq->cq_table; + int err; + + spin_lock_irq(&table->lock); + err = radix_tree_insert(&table->tree, cq->cqn, cq); + spin_unlock_irq(&table->lock); + + return err; +} + +int mlx5_eq_del_cq(struct mlx5_eq *eq, struct mlx5_core_cq *cq) +{ + struct mlx5_cq_table *table = &eq->cq_table; + struct mlx5_core_cq *tmp; + + spin_lock_irq(&table->lock); + tmp = radix_tree_delete(&table->tree, cq->cqn); + spin_unlock_irq(&table->lock); + + if (!tmp) { + mlx5_core_warn(eq->dev, "cq 0x%x not found in eq 0x%x tree\n", eq->eqn, cq->cqn); + return -ENOENT; + } + + if (tmp != cq) { + mlx5_core_warn(eq->dev, "corruption on cqn 0x%x in eq 0x%x\n", eq->eqn, cq->cqn); + return -EINVAL; + } + + return 0; +} int mlx5_eq_init(struct mlx5_core_dev *dev) { @@ -840,4 +923,3 @@ int mlx5_core_eq_query(struct mlx5_core_dev *dev, struct mlx5_eq *eq, MLX5_SET(query_eq_in, in, eq_number, eq->eqn); return mlx5_cmd_exec(dev, in, sizeof(in), out, outlen); } -EXPORT_SYMBOL_GPL(mlx5_core_eq_query); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index c2b1d7d351fc..77b7272eaaa8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -1619,10 +1619,14 @@ int mlx5_eswitch_enable_sriov(struct mlx5_eswitch *esw, int nvfs, int mode) esw_info(esw->dev, "E-Switch enable SRIOV: nvfs(%d) mode (%d)\n", nvfs, mode); esw->mode = mode; - if (mode == SRIOV_LEGACY) + if (mode == SRIOV_LEGACY) { err = esw_create_legacy_fdb_table(esw, nvfs + 1); - else + } else { + mlx5_reload_interface(esw->dev, MLX5_INTERFACE_PROTOCOL_IB); + err = esw_offloads_init(esw, nvfs + 1); + } + if (err) goto abort; @@ -1644,12 +1648,17 @@ int mlx5_eswitch_enable_sriov(struct mlx5_eswitch *esw, int nvfs, int mode) abort: esw->mode = SRIOV_NONE; + + if (mode == SRIOV_OFFLOADS) + mlx5_reload_interface(esw->dev, MLX5_INTERFACE_PROTOCOL_IB); + return err; } void mlx5_eswitch_disable_sriov(struct mlx5_eswitch *esw) { struct esw_mc_addr *mc_promisc; + int old_mode; int nvports; int i; @@ -1675,7 +1684,11 @@ void mlx5_eswitch_disable_sriov(struct mlx5_eswitch *esw) else if (esw->mode == SRIOV_OFFLOADS) esw_offloads_cleanup(esw, nvports); + old_mode = esw->mode; esw->mode = SRIOV_NONE; + + if (old_mode == SRIOV_OFFLOADS) + mlx5_reload_interface(esw->dev, MLX5_INTERFACE_PROTOCOL_IB); } int mlx5_eswitch_init(struct mlx5_core_dev *dev) @@ -2175,3 +2188,9 @@ free_out: kvfree(out); return err; } + +u8 mlx5_eswitch_mode(struct mlx5_eswitch *esw) +{ + return esw->mode; +} +EXPORT_SYMBOL_GPL(mlx5_eswitch_mode); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h index 2fa037066b2f..98d2177d0806 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h @@ -37,19 +37,9 @@ #include <linux/if_link.h> #include <net/devlink.h> #include <linux/mlx5/device.h> +#include <linux/mlx5/eswitch.h> #include "lib/mpfs.h" -enum { - SRIOV_NONE, - SRIOV_LEGACY, - SRIOV_OFFLOADS -}; - -enum { - REP_ETH, - NUM_REP_TYPES, -}; - #ifdef CONFIG_MLX5_ESWITCH #define MLX5_MAX_UC_PER_VPORT(dev) \ @@ -139,29 +129,13 @@ struct mlx5_eswitch_fdb { struct mlx5_flow_table *fdb; struct mlx5_flow_group *send_to_vport_grp; struct mlx5_flow_group *miss_grp; - struct mlx5_flow_handle *miss_rule; + struct mlx5_flow_handle *miss_rule_uni; + struct mlx5_flow_handle *miss_rule_multi; int vlan_push_pop_refcount; } offloads; }; }; -struct mlx5_eswitch_rep; -struct mlx5_eswitch_rep_if { - int (*load)(struct mlx5_core_dev *dev, - struct mlx5_eswitch_rep *rep); - void (*unload)(struct mlx5_eswitch_rep *rep); - void *priv; - bool valid; -}; - -struct mlx5_eswitch_rep { - struct mlx5_eswitch_rep_if rep_if[NUM_REP_TYPES]; - u16 vport; - u8 hw_id[ETH_ALEN]; - u16 vlan; - u32 vlan_refcount; -}; - struct mlx5_esw_offload { struct mlx5_flow_table *ft_offloads; struct mlx5_flow_group *vport_rx_group; @@ -231,9 +205,6 @@ int mlx5_eswitch_get_vport_config(struct mlx5_eswitch *esw, int mlx5_eswitch_get_vport_stats(struct mlx5_eswitch *esw, int vport, struct ifla_vf_stats *vf_stats); -struct mlx5_flow_handle * -mlx5_eswitch_add_send_to_vport_rule(struct mlx5_eswitch *esw, int vport, - u32 sqn); void mlx5_eswitch_del_send_to_vport_rule(struct mlx5_flow_handle *rule); struct mlx5_flow_spec; @@ -278,13 +249,6 @@ int mlx5_devlink_eswitch_inline_mode_get(struct devlink *devlink, u8 *mode); int mlx5_eswitch_inline_mode_get(struct mlx5_eswitch *esw, int nvfs, u8 *mode); int mlx5_devlink_eswitch_encap_mode_set(struct devlink *devlink, u8 encap); int mlx5_devlink_eswitch_encap_mode_get(struct devlink *devlink, u8 *encap); -void mlx5_eswitch_register_vport_rep(struct mlx5_eswitch *esw, - int vport_index, - struct mlx5_eswitch_rep_if *rep_if, - u8 rep_type); -void mlx5_eswitch_unregister_vport_rep(struct mlx5_eswitch *esw, - int vport_index, - u8 rep_type); void *mlx5_eswitch_get_uplink_priv(struct mlx5_eswitch *esw, u8 rep_type); int mlx5_eswitch_add_vlan_action(struct mlx5_eswitch *esw, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index 99f583a15cc3..0a8303c1b52f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -338,6 +338,7 @@ out: kvfree(spec); return flow_rule; } +EXPORT_SYMBOL(mlx5_eswitch_add_send_to_vport_rule); void mlx5_eswitch_del_send_to_vport_rule(struct mlx5_flow_handle *rule) { @@ -350,7 +351,11 @@ static int esw_add_fdb_miss_rule(struct mlx5_eswitch *esw) struct mlx5_flow_destination dest = {}; struct mlx5_flow_handle *flow_rule = NULL; struct mlx5_flow_spec *spec; + void *headers_c; + void *headers_v; int err = 0; + u8 *dmac_c; + u8 *dmac_v; spec = kvzalloc(sizeof(*spec), GFP_KERNEL); if (!spec) { @@ -358,6 +363,13 @@ static int esw_add_fdb_miss_rule(struct mlx5_eswitch *esw) goto out; } + spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS; + headers_c = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, + outer_headers); + dmac_c = MLX5_ADDR_OF(fte_match_param, headers_c, + outer_headers.dmac_47_16); + dmac_c[0] = 0x01; + dest.type = MLX5_FLOW_DESTINATION_TYPE_VPORT; dest.vport_num = 0; flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; @@ -366,11 +378,28 @@ static int esw_add_fdb_miss_rule(struct mlx5_eswitch *esw) &flow_act, &dest, 1); if (IS_ERR(flow_rule)) { err = PTR_ERR(flow_rule); - esw_warn(esw->dev, "FDB: Failed to add miss flow rule err %d\n", err); + esw_warn(esw->dev, "FDB: Failed to add unicast miss flow rule err %d\n", err); goto out; } - esw->fdb_table.offloads.miss_rule = flow_rule; + esw->fdb_table.offloads.miss_rule_uni = flow_rule; + + headers_v = MLX5_ADDR_OF(fte_match_param, spec->match_value, + outer_headers); + dmac_v = MLX5_ADDR_OF(fte_match_param, headers_v, + outer_headers.dmac_47_16); + dmac_v[0] = 0x01; + flow_rule = mlx5_add_flow_rules(esw->fdb_table.offloads.fdb, spec, + &flow_act, &dest, 1); + if (IS_ERR(flow_rule)) { + err = PTR_ERR(flow_rule); + esw_warn(esw->dev, "FDB: Failed to add multicast miss flow rule err %d\n", err); + mlx5_del_flow_rules(esw->fdb_table.offloads.miss_rule_uni); + goto out; + } + + esw->fdb_table.offloads.miss_rule_multi = flow_rule; + out: kvfree(spec); return err; @@ -426,6 +455,7 @@ static void esw_destroy_offloads_fast_fdb_table(struct mlx5_eswitch *esw) } #define MAX_PF_SQ 256 +#define MAX_SQ_NVPORTS 32 static int esw_create_offloads_fdb_tables(struct mlx5_eswitch *esw, int nvports) { @@ -438,6 +468,7 @@ static int esw_create_offloads_fdb_tables(struct mlx5_eswitch *esw, int nvports) struct mlx5_flow_group *g; void *match_criteria; u32 *flow_group_in; + u8 *dmac; esw_debug(esw->dev, "Create offloads FDB Tables\n"); flow_group_in = kvzalloc(inlen, GFP_KERNEL); @@ -455,7 +486,7 @@ static int esw_create_offloads_fdb_tables(struct mlx5_eswitch *esw, int nvports) if (err) goto fast_fdb_err; - table_size = nvports + MAX_PF_SQ + 1; + table_size = nvports * MAX_SQ_NVPORTS + MAX_PF_SQ + 2; ft_attr.max_fte = table_size; ft_attr.prio = FDB_SLOW_PATH; @@ -478,7 +509,7 @@ static int esw_create_offloads_fdb_tables(struct mlx5_eswitch *esw, int nvports) MLX5_SET_TO_ONES(fte_match_param, match_criteria, misc_parameters.source_sqn); MLX5_SET_TO_ONES(fte_match_param, match_criteria, misc_parameters.source_port); - ix = nvports + MAX_PF_SQ; + ix = nvports * MAX_SQ_NVPORTS + MAX_PF_SQ; MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, 0); MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, ix - 1); @@ -492,10 +523,16 @@ static int esw_create_offloads_fdb_tables(struct mlx5_eswitch *esw, int nvports) /* create miss group */ memset(flow_group_in, 0, inlen); - MLX5_SET(create_flow_group_in, flow_group_in, match_criteria_enable, 0); + MLX5_SET(create_flow_group_in, flow_group_in, match_criteria_enable, + MLX5_MATCH_OUTER_HEADERS); + match_criteria = MLX5_ADDR_OF(create_flow_group_in, flow_group_in, + match_criteria); + dmac = MLX5_ADDR_OF(fte_match_param, match_criteria, + outer_headers.dmac_47_16); + dmac[0] = 0x01; MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, ix); - MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, ix + 1); + MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, ix + 2); g = mlx5_create_flow_group(fdb, flow_group_in); if (IS_ERR(g)) { @@ -531,7 +568,8 @@ static void esw_destroy_offloads_fdb_tables(struct mlx5_eswitch *esw) return; esw_debug(esw->dev, "Destroy offloads FDB Tables\n"); - mlx5_del_flow_rules(esw->fdb_table.offloads.miss_rule); + mlx5_del_flow_rules(esw->fdb_table.offloads.miss_rule_multi); + mlx5_del_flow_rules(esw->fdb_table.offloads.miss_rule_uni); mlx5_destroy_flow_group(esw->fdb_table.offloads.send_to_vport_grp); mlx5_destroy_flow_group(esw->fdb_table.offloads.miss_grp); @@ -789,14 +827,9 @@ int esw_offloads_init(struct mlx5_eswitch *esw, int nvports) { int err; - /* disable PF RoCE so missed packets don't go through RoCE steering */ - mlx5_dev_list_lock(); - mlx5_remove_dev_by_protocol(esw->dev, MLX5_INTERFACE_PROTOCOL_IB); - mlx5_dev_list_unlock(); - err = esw_create_offloads_fdb_tables(esw, nvports); if (err) - goto create_fdb_err; + return err; err = esw_create_offloads_table(esw); if (err) @@ -821,12 +854,6 @@ create_fg_err: create_ft_err: esw_destroy_offloads_fdb_tables(esw); -create_fdb_err: - /* enable back PF RoCE */ - mlx5_dev_list_lock(); - mlx5_add_dev_by_protocol(esw->dev, MLX5_INTERFACE_PROTOCOL_IB); - mlx5_dev_list_unlock(); - return err; } @@ -844,9 +871,7 @@ static int esw_offloads_stop(struct mlx5_eswitch *esw) } /* enable back PF RoCE */ - mlx5_dev_list_lock(); - mlx5_add_dev_by_protocol(esw->dev, MLX5_INTERFACE_PROTOCOL_IB); - mlx5_dev_list_unlock(); + mlx5_reload_interface(esw->dev, MLX5_INTERFACE_PROTOCOL_IB); return err; } @@ -1160,10 +1185,12 @@ void mlx5_eswitch_register_vport_rep(struct mlx5_eswitch *esw, rep_if->load = __rep_if->load; rep_if->unload = __rep_if->unload; + rep_if->get_proto_dev = __rep_if->get_proto_dev; rep_if->priv = __rep_if->priv; rep_if->valid = true; } +EXPORT_SYMBOL(mlx5_eswitch_register_vport_rep); void mlx5_eswitch_unregister_vport_rep(struct mlx5_eswitch *esw, int vport_index, u8 rep_type) @@ -1178,6 +1205,7 @@ void mlx5_eswitch_unregister_vport_rep(struct mlx5_eswitch *esw, rep->rep_if[rep_type].valid = false; } +EXPORT_SYMBOL(mlx5_eswitch_unregister_vport_rep); void *mlx5_eswitch_get_uplink_priv(struct mlx5_eswitch *esw, u8 rep_type) { @@ -1188,3 +1216,35 @@ void *mlx5_eswitch_get_uplink_priv(struct mlx5_eswitch *esw, u8 rep_type) rep = &offloads->vport_reps[UPLINK_REP_INDEX]; return rep->rep_if[rep_type].priv; } + +void *mlx5_eswitch_get_proto_dev(struct mlx5_eswitch *esw, + int vport, + u8 rep_type) +{ + struct mlx5_esw_offload *offloads = &esw->offloads; + struct mlx5_eswitch_rep *rep; + + if (vport == FDB_UPLINK_VPORT) + vport = UPLINK_REP_INDEX; + + rep = &offloads->vport_reps[vport]; + + if (rep->rep_if[rep_type].valid && + rep->rep_if[rep_type].get_proto_dev) + return rep->rep_if[rep_type].get_proto_dev(rep); + return NULL; +} +EXPORT_SYMBOL(mlx5_eswitch_get_proto_dev); + +void *mlx5_eswitch_uplink_get_proto_dev(struct mlx5_eswitch *esw, u8 rep_type) +{ + return mlx5_eswitch_get_proto_dev(esw, UPLINK_REP_INDEX, rep_type); +} +EXPORT_SYMBOL(mlx5_eswitch_uplink_get_proto_dev); + +struct mlx5_eswitch_rep *mlx5_eswitch_vport_rep(struct mlx5_eswitch *esw, + int vport) +{ + return &esw->offloads.vport_reps[vport]; +} +EXPORT_SYMBOL(mlx5_eswitch_vport_rep); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index ae391e4b7070..7142c90d4669 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -942,9 +942,9 @@ static int mlx5_init_once(struct mlx5_core_dev *dev, struct mlx5_priv *priv) goto out; } - err = mlx5_init_cq_table(dev); + err = mlx5_cq_debugfs_init(dev); if (err) { - dev_err(&pdev->dev, "failed to initialize cq table\n"); + dev_err(&pdev->dev, "failed to initialize cq debugfs\n"); goto err_eq_cleanup; } @@ -1002,7 +1002,7 @@ err_tables_cleanup: mlx5_cleanup_mkey_table(dev); mlx5_cleanup_srq_table(dev); mlx5_cleanup_qp_table(dev); - mlx5_cleanup_cq_table(dev); + mlx5_cq_debugfs_cleanup(dev); err_eq_cleanup: mlx5_eq_cleanup(dev); @@ -1023,7 +1023,7 @@ static void mlx5_cleanup_once(struct mlx5_core_dev *dev) mlx5_cleanup_mkey_table(dev); mlx5_cleanup_srq_table(dev); mlx5_cleanup_qp_table(dev); - mlx5_cleanup_cq_table(dev); + mlx5_cq_debugfs_cleanup(dev); mlx5_eq_cleanup(dev); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h index 394552f36fcf..4e25f2b2e0bc 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h @@ -38,16 +38,11 @@ #include <linux/sched.h> #include <linux/if_link.h> #include <linux/firmware.h> +#include <linux/mlx5/cq.h> #define DRIVER_NAME "mlx5_core" #define DRIVER_VERSION "5.0-0" -#define MLX5_TOTAL_VPORTS(mdev) (1 + pci_sriov_get_totalvfs(mdev->pdev)) -#define MLX5_VPORT_MANAGER(mdev) \ - (MLX5_CAP_GEN(mdev, vport_group_manager) && \ - (MLX5_CAP_GEN(mdev, port_type) == MLX5_CAP_PORT_TYPE_ETH) && \ - mlx5_core_is_pf(mdev)) - extern uint mlx5_core_debug_mask; #define mlx5_core_dbg(__dev, format, ...) \ @@ -115,9 +110,29 @@ int mlx5_destroy_scheduling_element_cmd(struct mlx5_core_dev *dev, u8 hierarchy, u32 element_id); int mlx5_wait_for_vf_pages(struct mlx5_core_dev *dev); u64 mlx5_read_internal_timer(struct mlx5_core_dev *dev); + +int mlx5_eq_init(struct mlx5_core_dev *dev); +void mlx5_eq_cleanup(struct mlx5_core_dev *dev); +int mlx5_create_map_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq, u8 vecidx, + int nent, u64 mask, const char *name, + enum mlx5_eq_type type); +int mlx5_destroy_unmap_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq); +int mlx5_eq_add_cq(struct mlx5_eq *eq, struct mlx5_core_cq *cq); +int mlx5_eq_del_cq(struct mlx5_eq *eq, struct mlx5_core_cq *cq); +int mlx5_core_eq_query(struct mlx5_core_dev *dev, struct mlx5_eq *eq, + u32 *out, int outlen); +int mlx5_start_eqs(struct mlx5_core_dev *dev); +void mlx5_stop_eqs(struct mlx5_core_dev *dev); struct mlx5_eq *mlx5_eqn2eq(struct mlx5_core_dev *dev, int eqn); u32 mlx5_eq_poll_irq_disabled(struct mlx5_eq *eq); void mlx5_cq_tasklet_cb(unsigned long data); +void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, u64 vec, bool forced); +int mlx5_debug_eq_add(struct mlx5_core_dev *dev, struct mlx5_eq *eq); +void mlx5_debug_eq_remove(struct mlx5_core_dev *dev, struct mlx5_eq *eq); +int mlx5_eq_debugfs_init(struct mlx5_core_dev *dev); +void mlx5_eq_debugfs_cleanup(struct mlx5_core_dev *dev); +int mlx5_cq_debugfs_init(struct mlx5_core_dev *dev); +void mlx5_cq_debugfs_cleanup(struct mlx5_core_dev *dev); int mlx5_query_pcam_reg(struct mlx5_core_dev *dev, u32 *pcam, u8 feature_group, u8 access_reg_group); @@ -186,4 +201,5 @@ static inline int mlx5_lag_is_lacp_owner(struct mlx5_core_dev *dev) int mlx5_lag_allow(struct mlx5_core_dev *dev); int mlx5_lag_forbid(struct mlx5_core_dev *dev); +void mlx5_reload_interface(struct mlx5_core_dev *mdev, int protocol); #endif /* __MLX5_CORE_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/wq.c b/drivers/net/ethernet/mellanox/mlx5/core/wq.c index 6bcfc25350f5..ea66448ba365 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/wq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/wq.c @@ -41,7 +41,7 @@ u32 mlx5_wq_cyc_get_size(struct mlx5_wq_cyc *wq) u32 mlx5_cqwq_get_size(struct mlx5_cqwq *wq) { - return wq->sz_m1 + 1; + return wq->fbc.sz_m1 + 1; } u32 mlx5_wq_ll_get_size(struct mlx5_wq_ll *wq) @@ -62,7 +62,7 @@ static u32 mlx5_wq_qp_get_byte_size(struct mlx5_wq_qp *wq) static u32 mlx5_cqwq_get_byte_size(struct mlx5_cqwq *wq) { - return mlx5_cqwq_get_size(wq) << wq->log_stride; + return mlx5_cqwq_get_size(wq) << wq->fbc.log_stride; } static u32 mlx5_wq_ll_get_byte_size(struct mlx5_wq_ll *wq) @@ -92,7 +92,7 @@ int mlx5_wq_cyc_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param, goto err_db_free; } - wq->buf = wq_ctrl->buf.direct.buf; + wq->buf = wq_ctrl->buf.frags->buf; wq->db = wq_ctrl->db.db; wq_ctrl->mdev = mdev; @@ -130,7 +130,7 @@ int mlx5_wq_qp_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param, goto err_db_free; } - wq->rq.buf = wq_ctrl->buf.direct.buf; + wq->rq.buf = wq_ctrl->buf.frags->buf; wq->sq.buf = wq->rq.buf + mlx5_wq_cyc_get_byte_size(&wq->rq); wq->rq.db = &wq_ctrl->db.db[MLX5_RCV_DBR]; wq->sq.db = &wq_ctrl->db.db[MLX5_SND_DBR]; @@ -151,11 +151,7 @@ int mlx5_cqwq_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param, { int err; - wq->log_stride = 6 + MLX5_GET(cqc, cqc, cqe_sz); - wq->log_sz = MLX5_GET(cqc, cqc, log_cq_size); - wq->sz_m1 = (1 << wq->log_sz) - 1; - wq->log_frag_strides = PAGE_SHIFT - wq->log_stride; - wq->frag_sz_m1 = (1 << wq->log_frag_strides) - 1; + mlx5_core_init_cq_frag_buf(&wq->fbc, cqc); err = mlx5_db_alloc_node(mdev, &wq_ctrl->db, param->db_numa_node); if (err) { @@ -172,7 +168,7 @@ int mlx5_cqwq_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param, goto err_db_free; } - wq->frag_buf = wq_ctrl->frag_buf; + wq->fbc.frag_buf = wq_ctrl->frag_buf; wq->db = wq_ctrl->db.db; wq_ctrl->mdev = mdev; @@ -209,7 +205,7 @@ int mlx5_wq_ll_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param, goto err_db_free; } - wq->buf = wq_ctrl->buf.direct.buf; + wq->buf = wq_ctrl->buf.frags->buf; wq->db = wq_ctrl->db.db; for (i = 0; i < wq->sz_m1; i++) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/wq.h b/drivers/net/ethernet/mellanox/mlx5/core/wq.h index 718589d0cec2..fca90b94596d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/wq.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/wq.h @@ -45,7 +45,7 @@ struct mlx5_wq_param { struct mlx5_wq_ctrl { struct mlx5_core_dev *mdev; - struct mlx5_buf buf; + struct mlx5_frag_buf buf; struct mlx5_db db; }; @@ -68,14 +68,9 @@ struct mlx5_wq_qp { }; struct mlx5_cqwq { - struct mlx5_frag_buf frag_buf; - __be32 *db; - u32 sz_m1; - u32 frag_sz_m1; - u32 cc; /* consumer counter */ - u8 log_sz; - u8 log_stride; - u8 log_frag_strides; + struct mlx5_frag_buf_ctrl fbc; + __be32 *db; + u32 cc; /* consumer counter */ }; struct mlx5_wq_ll { @@ -131,20 +126,17 @@ static inline int mlx5_wq_cyc_cc_bigger(u16 cc1, u16 cc2) static inline u32 mlx5_cqwq_get_ci(struct mlx5_cqwq *wq) { - return wq->cc & wq->sz_m1; + return wq->cc & wq->fbc.sz_m1; } static inline void *mlx5_cqwq_get_wqe(struct mlx5_cqwq *wq, u32 ix) { - unsigned int frag = (ix >> wq->log_frag_strides); - - return wq->frag_buf.frags[frag].buf + - ((wq->frag_sz_m1 & ix) << wq->log_stride); + return mlx5_frag_buf_get_wqe(&wq->fbc, ix); } static inline u32 mlx5_cqwq_get_wrap_cnt(struct mlx5_cqwq *wq) { - return wq->cc >> wq->log_sz; + return wq->cc >> wq->fbc.log_sz; } static inline void mlx5_cqwq_pop(struct mlx5_cqwq *wq) diff --git a/drivers/net/ethernet/mellanox/mlxsw/Kconfig b/drivers/net/ethernet/mellanox/mlxsw/Kconfig index d56eea310509..93d97b4676eb 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/Kconfig +++ b/drivers/net/ethernet/mellanox/mlxsw/Kconfig @@ -78,6 +78,10 @@ config MLXSW_SPECTRUM depends on IPV6 || IPV6=n select PARMAN select MLXFW + depends on NET_IPGRE + depends on !(MLXSW_CORE=y && NET_IPGRE=m) + depends on IPV6_GRE + depends on !(MLXSW_CORE=y && IPV6_GRE=m) default m ---help--- This driver supports Mellanox Technologies Spectrum Ethernet diff --git a/drivers/net/ethernet/mellanox/mlxsw/Makefile b/drivers/net/ethernet/mellanox/mlxsw/Makefile index 9463c3fa254f..0cadcabfe86f 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/Makefile +++ b/drivers/net/ethernet/mellanox/mlxsw/Makefile @@ -20,7 +20,7 @@ mlxsw_spectrum-objs := spectrum.o spectrum_buffers.o \ spectrum_cnt.o spectrum_fid.o \ spectrum_ipip.o spectrum_acl_flex_actions.o \ spectrum_mr.o spectrum_mr_tcam.o \ - spectrum_qdisc.o + spectrum_qdisc.o spectrum_span.o mlxsw_spectrum-$(CONFIG_MLXSW_SPECTRUM_DCB) += spectrum_dcb.o mlxsw_spectrum-$(CONFIG_NET_DEVLINK) += spectrum_dpipe.o obj-$(CONFIG_MLXSW_MINIMAL) += mlxsw_minimal.o diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c index b698fb481b2e..ba338428ffd1 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c @@ -1,6 +1,6 @@ /* * drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c - * Copyright (c) 2017 Mellanox Technologies. All rights reserved. + * Copyright (c) 2017, 2018 Mellanox Technologies. All rights reserved. * Copyright (c) 2017 Jiri Pirko <jiri@mellanox.com> * * Redistribution and use in source and binary forms, with or without @@ -838,7 +838,6 @@ struct mlxsw_afa_mirror { struct mlxsw_afa_resource resource; int span_id; u8 local_in_port; - u8 local_out_port; bool ingress; }; @@ -848,7 +847,7 @@ mlxsw_afa_mirror_destroy(struct mlxsw_afa_block *block, { block->afa->ops->mirror_del(block->afa->ops_priv, mirror->local_in_port, - mirror->local_out_port, + mirror->span_id, mirror->ingress); kfree(mirror); } @@ -864,9 +863,8 @@ mlxsw_afa_mirror_destructor(struct mlxsw_afa_block *block, } static struct mlxsw_afa_mirror * -mlxsw_afa_mirror_create(struct mlxsw_afa_block *block, - u8 local_in_port, u8 local_out_port, - bool ingress) +mlxsw_afa_mirror_create(struct mlxsw_afa_block *block, u8 local_in_port, + const struct net_device *out_dev, bool ingress) { struct mlxsw_afa_mirror *mirror; int err; @@ -876,13 +874,12 @@ mlxsw_afa_mirror_create(struct mlxsw_afa_block *block, return ERR_PTR(-ENOMEM); err = block->afa->ops->mirror_add(block->afa->ops_priv, - local_in_port, local_out_port, + local_in_port, out_dev, ingress, &mirror->span_id); if (err) goto err_mirror_add; mirror->ingress = ingress; - mirror->local_out_port = local_out_port; mirror->local_in_port = local_in_port; mirror->resource.destructor = mlxsw_afa_mirror_destructor; mlxsw_afa_resource_add(block, &mirror->resource); @@ -909,13 +906,13 @@ mlxsw_afa_block_append_allocated_mirror(struct mlxsw_afa_block *block, } int -mlxsw_afa_block_append_mirror(struct mlxsw_afa_block *block, - u8 local_in_port, u8 local_out_port, bool ingress) +mlxsw_afa_block_append_mirror(struct mlxsw_afa_block *block, u8 local_in_port, + const struct net_device *out_dev, bool ingress) { struct mlxsw_afa_mirror *mirror; int err; - mirror = mlxsw_afa_mirror_create(block, local_in_port, local_out_port, + mirror = mlxsw_afa_mirror_create(block, local_in_port, out_dev, ingress); if (IS_ERR(mirror)) return PTR_ERR(mirror); diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h index 43132293475c..6dd601703c99 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h +++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h @@ -36,6 +36,7 @@ #define _MLXSW_CORE_ACL_FLEX_ACTIONS_H #include <linux/types.h> +#include <linux/netdevice.h> struct mlxsw_afa; struct mlxsw_afa_block; @@ -48,9 +49,10 @@ struct mlxsw_afa_ops { void (*kvdl_fwd_entry_del)(void *priv, u32 kvdl_index); int (*counter_index_get)(void *priv, unsigned int *p_counter_index); void (*counter_index_put)(void *priv, unsigned int counter_index); - int (*mirror_add)(void *priv, u8 locol_in_port, u8 local_out_port, + int (*mirror_add)(void *priv, u8 local_in_port, + const struct net_device *out_dev, bool ingress, int *p_span_id); - void (*mirror_del)(void *priv, u8 locol_in_port, u8 local_out_port, + void (*mirror_del)(void *priv, u8 local_in_port, int span_id, bool ingress); }; @@ -70,7 +72,8 @@ int mlxsw_afa_block_append_trap(struct mlxsw_afa_block *block, u16 trap_id); int mlxsw_afa_block_append_trap_and_forward(struct mlxsw_afa_block *block, u16 trap_id); int mlxsw_afa_block_append_mirror(struct mlxsw_afa_block *block, - u8 local_in_port, u8 local_out_port, + u8 local_in_port, + const struct net_device *out_dev, bool ingress); int mlxsw_afa_block_append_fwd(struct mlxsw_afa_block *block, u8 local_port, bool in_port); diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h index 0e08be41c8e0..cb5f77f09f8e 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/reg.h +++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h @@ -1,11 +1,11 @@ /* * drivers/net/ethernet/mellanox/mlxsw/reg.h - * Copyright (c) 2015-2017 Mellanox Technologies. All rights reserved. + * Copyright (c) 2015-2018 Mellanox Technologies. All rights reserved. * Copyright (c) 2015-2016 Ido Schimmel <idosch@mellanox.com> * Copyright (c) 2015 Elad Raz <eladr@mellanox.com> * Copyright (c) 2015-2017 Jiri Pirko <jiri@mellanox.com> * Copyright (c) 2016 Yotam Gigi <yotamg@mellanox.com> - * Copyright (c) 2017 Petr Machata <petrm@mellanox.com> + * Copyright (c) 2017-2018 Petr Machata <petrm@mellanox.com> * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions are met: @@ -6772,8 +6772,104 @@ MLXSW_ITEM32(reg, mpat, qos, 0x04, 26, 1); */ MLXSW_ITEM32(reg, mpat, be, 0x04, 25, 1); +enum mlxsw_reg_mpat_span_type { + /* Local SPAN Ethernet. + * The original packet is not encapsulated. + */ + MLXSW_REG_MPAT_SPAN_TYPE_LOCAL_ETH = 0x0, + + /* Encapsulated Remote SPAN Ethernet L3 GRE. + * The packet is encapsulated with GRE header. + */ + MLXSW_REG_MPAT_SPAN_TYPE_REMOTE_ETH_L3 = 0x3, +}; + +/* reg_mpat_span_type + * SPAN type. + * Access: RW + */ +MLXSW_ITEM32(reg, mpat, span_type, 0x04, 0, 4); + +/* Remote SPAN - Ethernet VLAN + * - - - - - - - - - - - - - - + */ + +/* reg_mpat_eth_rspan_vid + * Encapsulation header VLAN ID. + * Access: RW + */ +MLXSW_ITEM32(reg, mpat, eth_rspan_vid, 0x18, 0, 12); + +/* Encapsulated Remote SPAN - Ethernet L2 + * - - - - - - - - - - - - - - - - - - - + */ + +enum mlxsw_reg_mpat_eth_rspan_version { + MLXSW_REG_MPAT_ETH_RSPAN_VERSION_NO_HEADER = 15, +}; + +/* reg_mpat_eth_rspan_version + * RSPAN mirror header version. + * Access: RW + */ +MLXSW_ITEM32(reg, mpat, eth_rspan_version, 0x10, 18, 4); + +/* reg_mpat_eth_rspan_mac + * Destination MAC address. + * Access: RW + */ +MLXSW_ITEM_BUF(reg, mpat, eth_rspan_mac, 0x12, 6); + +/* reg_mpat_eth_rspan_tp + * Tag Packet. Indicates whether the mirroring header should be VLAN tagged. + * Access: RW + */ +MLXSW_ITEM32(reg, mpat, eth_rspan_tp, 0x18, 16, 1); + +/* Encapsulated Remote SPAN - Ethernet L3 + * - - - - - - - - - - - - - - - - - - - + */ + +enum mlxsw_reg_mpat_eth_rspan_protocol { + MLXSW_REG_MPAT_ETH_RSPAN_PROTOCOL_IPV4, + MLXSW_REG_MPAT_ETH_RSPAN_PROTOCOL_IPV6, +}; + +/* reg_mpat_eth_rspan_protocol + * SPAN encapsulation protocol. + * Access: RW + */ +MLXSW_ITEM32(reg, mpat, eth_rspan_protocol, 0x18, 24, 4); + +/* reg_mpat_eth_rspan_ttl + * Encapsulation header Time-to-Live/HopLimit. + * Access: RW + */ +MLXSW_ITEM32(reg, mpat, eth_rspan_ttl, 0x1C, 4, 8); + +/* reg_mpat_eth_rspan_smac + * Source MAC address + * Access: RW + */ +MLXSW_ITEM_BUF(reg, mpat, eth_rspan_smac, 0x22, 6); + +/* reg_mpat_eth_rspan_dip* + * Destination IP address. The IP version is configured by protocol. + * Access: RW + */ +MLXSW_ITEM32(reg, mpat, eth_rspan_dip4, 0x4C, 0, 32); +MLXSW_ITEM_BUF(reg, mpat, eth_rspan_dip6, 0x40, 16); + +/* reg_mpat_eth_rspan_sip* + * Source IP address. The IP version is configured by protocol. + * Access: RW + */ +MLXSW_ITEM32(reg, mpat, eth_rspan_sip4, 0x5C, 0, 32); +MLXSW_ITEM_BUF(reg, mpat, eth_rspan_sip6, 0x50, 16); + static inline void mlxsw_reg_mpat_pack(char *payload, u8 pa_id, - u16 system_port, bool e) + u16 system_port, bool e, + enum mlxsw_reg_mpat_span_type span_type) { MLXSW_REG_ZERO(mpat, payload); mlxsw_reg_mpat_pa_id_set(payload, pa_id); @@ -6781,6 +6877,49 @@ static inline void mlxsw_reg_mpat_pack(char *payload, u8 pa_id, mlxsw_reg_mpat_e_set(payload, e); mlxsw_reg_mpat_qos_set(payload, 1); mlxsw_reg_mpat_be_set(payload, 1); + mlxsw_reg_mpat_span_type_set(payload, span_type); +} + +static inline void mlxsw_reg_mpat_eth_rspan_pack(char *payload, u16 vid) +{ + mlxsw_reg_mpat_eth_rspan_vid_set(payload, vid); +} + +static inline void +mlxsw_reg_mpat_eth_rspan_l2_pack(char *payload, + enum mlxsw_reg_mpat_eth_rspan_version version, + const char *mac, + bool tp) +{ + mlxsw_reg_mpat_eth_rspan_version_set(payload, version); + mlxsw_reg_mpat_eth_rspan_mac_memcpy_to(payload, mac); + mlxsw_reg_mpat_eth_rspan_tp_set(payload, tp); +} + +static inline void +mlxsw_reg_mpat_eth_rspan_l3_ipv4_pack(char *payload, u8 ttl, + const char *smac, + u32 sip, u32 dip) +{ + mlxsw_reg_mpat_eth_rspan_ttl_set(payload, ttl); + mlxsw_reg_mpat_eth_rspan_smac_memcpy_to(payload, smac); + mlxsw_reg_mpat_eth_rspan_protocol_set(payload, + MLXSW_REG_MPAT_ETH_RSPAN_PROTOCOL_IPV4); + mlxsw_reg_mpat_eth_rspan_sip4_set(payload, sip); + mlxsw_reg_mpat_eth_rspan_dip4_set(payload, dip); +} + +static inline void +mlxsw_reg_mpat_eth_rspan_l3_ipv6_pack(char *payload, u8 ttl, + const char *smac, + struct in6_addr sip, struct in6_addr dip) +{ + mlxsw_reg_mpat_eth_rspan_ttl_set(payload, ttl); + mlxsw_reg_mpat_eth_rspan_smac_memcpy_to(payload, smac); + mlxsw_reg_mpat_eth_rspan_protocol_set(payload, + MLXSW_REG_MPAT_ETH_RSPAN_PROTOCOL_IPV6); + mlxsw_reg_mpat_eth_rspan_sip6_memcpy_to(payload, (void *)&sip); + mlxsw_reg_mpat_eth_rspan_dip6_memcpy_to(payload, (void *)&dip); } /* MPAR - Monitoring Port Analyzer Register diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index c7e941aecc2a..7884e8a2de35 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -1,6 +1,6 @@ /* * drivers/net/ethernet/mellanox/mlxsw/spectrum.c - * Copyright (c) 2015-2017 Mellanox Technologies. All rights reserved. + * Copyright (c) 2015-2018 Mellanox Technologies. All rights reserved. * Copyright (c) 2015-2017 Jiri Pirko <jiri@mellanox.com> * Copyright (c) 2015 Ido Schimmel <idosch@mellanox.com> * Copyright (c) 2015 Elad Raz <eladr@mellanox.com> @@ -71,6 +71,7 @@ #include "spectrum_cnt.h" #include "spectrum_dpipe.h" #include "spectrum_acl_flex_actions.h" +#include "spectrum_span.h" #include "../mlxfw/mlxfw.h" #define MLXSW_FWREV_MAJOR 13 @@ -487,327 +488,6 @@ static int mlxsw_sp_base_mac_get(struct mlxsw_sp *mlxsw_sp) return 0; } -static int mlxsw_sp_span_init(struct mlxsw_sp *mlxsw_sp) -{ - int i; - - if (!MLXSW_CORE_RES_VALID(mlxsw_sp->core, MAX_SPAN)) - return -EIO; - - mlxsw_sp->span.entries_count = MLXSW_CORE_RES_GET(mlxsw_sp->core, - MAX_SPAN); - mlxsw_sp->span.entries = kcalloc(mlxsw_sp->span.entries_count, - sizeof(struct mlxsw_sp_span_entry), - GFP_KERNEL); - if (!mlxsw_sp->span.entries) - return -ENOMEM; - - for (i = 0; i < mlxsw_sp->span.entries_count; i++) - INIT_LIST_HEAD(&mlxsw_sp->span.entries[i].bound_ports_list); - - return 0; -} - -static void mlxsw_sp_span_fini(struct mlxsw_sp *mlxsw_sp) -{ - int i; - - for (i = 0; i < mlxsw_sp->span.entries_count; i++) { - struct mlxsw_sp_span_entry *curr = &mlxsw_sp->span.entries[i]; - - WARN_ON_ONCE(!list_empty(&curr->bound_ports_list)); - } - kfree(mlxsw_sp->span.entries); -} - -static struct mlxsw_sp_span_entry * -mlxsw_sp_span_entry_create(struct mlxsw_sp_port *port) -{ - struct mlxsw_sp *mlxsw_sp = port->mlxsw_sp; - struct mlxsw_sp_span_entry *span_entry; - char mpat_pl[MLXSW_REG_MPAT_LEN]; - u8 local_port = port->local_port; - int index; - int i; - int err; - - /* find a free entry to use */ - index = -1; - for (i = 0; i < mlxsw_sp->span.entries_count; i++) { - if (!mlxsw_sp->span.entries[i].used) { - index = i; - span_entry = &mlxsw_sp->span.entries[i]; - break; - } - } - if (index < 0) - return NULL; - - /* create a new port analayzer entry for local_port */ - mlxsw_reg_mpat_pack(mpat_pl, index, local_port, true); - err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(mpat), mpat_pl); - if (err) - return NULL; - - span_entry->used = true; - span_entry->id = index; - span_entry->ref_count = 1; - span_entry->local_port = local_port; - return span_entry; -} - -static void mlxsw_sp_span_entry_destroy(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_span_entry *span_entry) -{ - u8 local_port = span_entry->local_port; - char mpat_pl[MLXSW_REG_MPAT_LEN]; - int pa_id = span_entry->id; - - mlxsw_reg_mpat_pack(mpat_pl, pa_id, local_port, false); - mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(mpat), mpat_pl); - span_entry->used = false; -} - -struct mlxsw_sp_span_entry * -mlxsw_sp_span_entry_find(struct mlxsw_sp *mlxsw_sp, u8 local_port) -{ - int i; - - for (i = 0; i < mlxsw_sp->span.entries_count; i++) { - struct mlxsw_sp_span_entry *curr = &mlxsw_sp->span.entries[i]; - - if (curr->used && curr->local_port == local_port) - return curr; - } - return NULL; -} - -static struct mlxsw_sp_span_entry -*mlxsw_sp_span_entry_get(struct mlxsw_sp_port *port) -{ - struct mlxsw_sp_span_entry *span_entry; - - span_entry = mlxsw_sp_span_entry_find(port->mlxsw_sp, - port->local_port); - if (span_entry) { - /* Already exists, just take a reference */ - span_entry->ref_count++; - return span_entry; - } - - return mlxsw_sp_span_entry_create(port); -} - -static int mlxsw_sp_span_entry_put(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_span_entry *span_entry) -{ - WARN_ON(!span_entry->ref_count); - if (--span_entry->ref_count == 0) - mlxsw_sp_span_entry_destroy(mlxsw_sp, span_entry); - return 0; -} - -static bool mlxsw_sp_span_is_egress_mirror(struct mlxsw_sp_port *port) -{ - struct mlxsw_sp *mlxsw_sp = port->mlxsw_sp; - struct mlxsw_sp_span_inspected_port *p; - int i; - - for (i = 0; i < mlxsw_sp->span.entries_count; i++) { - struct mlxsw_sp_span_entry *curr = &mlxsw_sp->span.entries[i]; - - list_for_each_entry(p, &curr->bound_ports_list, list) - if (p->local_port == port->local_port && - p->type == MLXSW_SP_SPAN_EGRESS) - return true; - } - - return false; -} - -static int mlxsw_sp_span_mtu_to_buffsize(const struct mlxsw_sp *mlxsw_sp, - int mtu) -{ - return mlxsw_sp_bytes_cells(mlxsw_sp, mtu * 5 / 2) + 1; -} - -static int mlxsw_sp_span_port_mtu_update(struct mlxsw_sp_port *port, u16 mtu) -{ - struct mlxsw_sp *mlxsw_sp = port->mlxsw_sp; - char sbib_pl[MLXSW_REG_SBIB_LEN]; - int err; - - /* If port is egress mirrored, the shared buffer size should be - * updated according to the mtu value - */ - if (mlxsw_sp_span_is_egress_mirror(port)) { - u32 buffsize = mlxsw_sp_span_mtu_to_buffsize(mlxsw_sp, mtu); - - mlxsw_reg_sbib_pack(sbib_pl, port->local_port, buffsize); - err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sbib), sbib_pl); - if (err) { - netdev_err(port->dev, "Could not update shared buffer for mirroring\n"); - return err; - } - } - - return 0; -} - -static struct mlxsw_sp_span_inspected_port * -mlxsw_sp_span_entry_bound_port_find(struct mlxsw_sp_port *port, - struct mlxsw_sp_span_entry *span_entry) -{ - struct mlxsw_sp_span_inspected_port *p; - - list_for_each_entry(p, &span_entry->bound_ports_list, list) - if (port->local_port == p->local_port) - return p; - return NULL; -} - -static int -mlxsw_sp_span_inspected_port_bind(struct mlxsw_sp_port *port, - struct mlxsw_sp_span_entry *span_entry, - enum mlxsw_sp_span_type type, - bool bind) -{ - struct mlxsw_sp *mlxsw_sp = port->mlxsw_sp; - char mpar_pl[MLXSW_REG_MPAR_LEN]; - int pa_id = span_entry->id; - - /* bind the port to the SPAN entry */ - mlxsw_reg_mpar_pack(mpar_pl, port->local_port, - (enum mlxsw_reg_mpar_i_e) type, bind, pa_id); - return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(mpar), mpar_pl); -} - -static int -mlxsw_sp_span_inspected_port_add(struct mlxsw_sp_port *port, - struct mlxsw_sp_span_entry *span_entry, - enum mlxsw_sp_span_type type, - bool bind) -{ - struct mlxsw_sp_span_inspected_port *inspected_port; - struct mlxsw_sp *mlxsw_sp = port->mlxsw_sp; - char sbib_pl[MLXSW_REG_SBIB_LEN]; - int err; - - /* if it is an egress SPAN, bind a shared buffer to it */ - if (type == MLXSW_SP_SPAN_EGRESS) { - u32 buffsize = mlxsw_sp_span_mtu_to_buffsize(mlxsw_sp, - port->dev->mtu); - - mlxsw_reg_sbib_pack(sbib_pl, port->local_port, buffsize); - err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sbib), sbib_pl); - if (err) { - netdev_err(port->dev, "Could not create shared buffer for mirroring\n"); - return err; - } - } - - if (bind) { - err = mlxsw_sp_span_inspected_port_bind(port, span_entry, type, - true); - if (err) - goto err_port_bind; - } - - inspected_port = kzalloc(sizeof(*inspected_port), GFP_KERNEL); - if (!inspected_port) { - err = -ENOMEM; - goto err_inspected_port_alloc; - } - inspected_port->local_port = port->local_port; - inspected_port->type = type; - list_add_tail(&inspected_port->list, &span_entry->bound_ports_list); - - return 0; - -err_inspected_port_alloc: - if (bind) - mlxsw_sp_span_inspected_port_bind(port, span_entry, type, - false); -err_port_bind: - if (type == MLXSW_SP_SPAN_EGRESS) { - mlxsw_reg_sbib_pack(sbib_pl, port->local_port, 0); - mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sbib), sbib_pl); - } - return err; -} - -static void -mlxsw_sp_span_inspected_port_del(struct mlxsw_sp_port *port, - struct mlxsw_sp_span_entry *span_entry, - enum mlxsw_sp_span_type type, - bool bind) -{ - struct mlxsw_sp_span_inspected_port *inspected_port; - struct mlxsw_sp *mlxsw_sp = port->mlxsw_sp; - char sbib_pl[MLXSW_REG_SBIB_LEN]; - - inspected_port = mlxsw_sp_span_entry_bound_port_find(port, span_entry); - if (!inspected_port) - return; - - if (bind) - mlxsw_sp_span_inspected_port_bind(port, span_entry, type, - false); - /* remove the SBIB buffer if it was egress SPAN */ - if (type == MLXSW_SP_SPAN_EGRESS) { - mlxsw_reg_sbib_pack(sbib_pl, port->local_port, 0); - mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sbib), sbib_pl); - } - - mlxsw_sp_span_entry_put(mlxsw_sp, span_entry); - - list_del(&inspected_port->list); - kfree(inspected_port); -} - -int mlxsw_sp_span_mirror_add(struct mlxsw_sp_port *from, - struct mlxsw_sp_port *to, - enum mlxsw_sp_span_type type, bool bind) -{ - struct mlxsw_sp *mlxsw_sp = from->mlxsw_sp; - struct mlxsw_sp_span_entry *span_entry; - int err; - - span_entry = mlxsw_sp_span_entry_get(to); - if (!span_entry) - return -ENOENT; - - netdev_dbg(from->dev, "Adding inspected port to SPAN entry %d\n", - span_entry->id); - - err = mlxsw_sp_span_inspected_port_add(from, span_entry, type, bind); - if (err) - goto err_port_bind; - - return 0; - -err_port_bind: - mlxsw_sp_span_entry_put(mlxsw_sp, span_entry); - return err; -} - -void mlxsw_sp_span_mirror_del(struct mlxsw_sp_port *from, u8 destination_port, - enum mlxsw_sp_span_type type, bool bind) -{ - struct mlxsw_sp_span_entry *span_entry; - - span_entry = mlxsw_sp_span_entry_find(from->mlxsw_sp, - destination_port); - if (!span_entry) { - netdev_err(from->dev, "no span entry found\n"); - return; - } - - netdev_dbg(from->dev, "removing inspected port from SPAN entry %d\n", - span_entry->id); - mlxsw_sp_span_inspected_port_del(from, span_entry, type, bind); -} - static int mlxsw_sp_port_sample_set(struct mlxsw_sp_port *mlxsw_sp_port, bool enable, u32 rate) { @@ -1360,6 +1040,16 @@ mlxsw_sp_port_get_hw_xstats(struct net_device *dev, xstats->tail_drop[i] = mlxsw_reg_ppcnt_tc_no_buffer_discard_uc_get(ppcnt_pl); } + + for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) { + err = mlxsw_sp_port_get_stats_raw(dev, MLXSW_REG_PPCNT_PRIO_CNT, + i, ppcnt_pl); + if (err) + continue; + + xstats->tx_packets[i] = mlxsw_reg_ppcnt_tx_frames_get(ppcnt_pl); + xstats->tx_bytes[i] = mlxsw_reg_ppcnt_tx_octets_get(ppcnt_pl); + } } static void update_stats_cache(struct work_struct *work) @@ -1584,7 +1274,6 @@ mlxsw_sp_port_add_cls_matchall_mirror(struct mlxsw_sp_port *mlxsw_sp_port, bool ingress) { enum mlxsw_sp_span_type span_type; - struct mlxsw_sp_port *to_port; struct net_device *to_dev; to_dev = tcf_mirred_dev(a); @@ -1593,17 +1282,10 @@ mlxsw_sp_port_add_cls_matchall_mirror(struct mlxsw_sp_port *mlxsw_sp_port, return -EINVAL; } - if (!mlxsw_sp_port_dev_check(to_dev)) { - netdev_err(mlxsw_sp_port->dev, "Cannot mirror to a non-spectrum port"); - return -EOPNOTSUPP; - } - to_port = netdev_priv(to_dev); - - mirror->to_local_port = to_port->local_port; mirror->ingress = ingress; span_type = ingress ? MLXSW_SP_SPAN_INGRESS : MLXSW_SP_SPAN_EGRESS; - return mlxsw_sp_span_mirror_add(mlxsw_sp_port, to_port, span_type, - true); + return mlxsw_sp_span_mirror_add(mlxsw_sp_port, to_dev, span_type, + true, &mirror->span_id); } static void @@ -1614,7 +1296,7 @@ mlxsw_sp_port_del_cls_matchall_mirror(struct mlxsw_sp_port *mlxsw_sp_port, span_type = mirror->ingress ? MLXSW_SP_SPAN_INGRESS : MLXSW_SP_SPAN_EGRESS; - mlxsw_sp_span_mirror_del(mlxsw_sp_port, mirror->to_local_port, + mlxsw_sp_span_mirror_del(mlxsw_sp_port, mirror->span_id, span_type, true); } @@ -4001,14 +3683,24 @@ static int mlxsw_sp_init(struct mlxsw_core *mlxsw_core, goto err_afa_init; } + err = mlxsw_sp_span_init(mlxsw_sp); + if (err) { + dev_err(mlxsw_sp->bus_info->dev, "Failed to init span system\n"); + goto err_span_init; + } + + /* Initialize router after SPAN is initialized, so that the FIB and + * neighbor event handlers can issue SPAN respin. + */ err = mlxsw_sp_router_init(mlxsw_sp); if (err) { dev_err(mlxsw_sp->bus_info->dev, "Failed to initialize router\n"); goto err_router_init; } - /* Initialize netdevice notifier after router is initialized, so that - * the event handler can use router structures. + /* Initialize netdevice notifier after router and SPAN is initialized, + * so that the event handler can use router structures and call SPAN + * respin. */ mlxsw_sp->netdevice_nb.notifier_call = mlxsw_sp_netdevice_event; err = register_netdevice_notifier(&mlxsw_sp->netdevice_nb); @@ -4017,12 +3709,6 @@ static int mlxsw_sp_init(struct mlxsw_core *mlxsw_core, goto err_netdev_notifier; } - err = mlxsw_sp_span_init(mlxsw_sp); - if (err) { - dev_err(mlxsw_sp->bus_info->dev, "Failed to init span system\n"); - goto err_span_init; - } - err = mlxsw_sp_acl_init(mlxsw_sp); if (err) { dev_err(mlxsw_sp->bus_info->dev, "Failed to initialize ACL\n"); @@ -4048,12 +3734,12 @@ err_ports_create: err_dpipe_init: mlxsw_sp_acl_fini(mlxsw_sp); err_acl_init: - mlxsw_sp_span_fini(mlxsw_sp); -err_span_init: unregister_netdevice_notifier(&mlxsw_sp->netdevice_nb); err_netdev_notifier: mlxsw_sp_router_fini(mlxsw_sp); err_router_init: + mlxsw_sp_span_fini(mlxsw_sp); +err_span_init: mlxsw_sp_afa_fini(mlxsw_sp); err_afa_init: mlxsw_sp_counter_pool_fini(mlxsw_sp); @@ -4079,9 +3765,9 @@ static void mlxsw_sp_fini(struct mlxsw_core *mlxsw_core) mlxsw_sp_ports_remove(mlxsw_sp); mlxsw_sp_dpipe_fini(mlxsw_sp); mlxsw_sp_acl_fini(mlxsw_sp); - mlxsw_sp_span_fini(mlxsw_sp); unregister_netdevice_notifier(&mlxsw_sp->netdevice_nb); mlxsw_sp_router_fini(mlxsw_sp); + mlxsw_sp_span_fini(mlxsw_sp); mlxsw_sp_afa_fini(mlxsw_sp); mlxsw_sp_counter_pool_fini(mlxsw_sp); mlxsw_sp_switchdev_fini(mlxsw_sp); @@ -4124,70 +3810,6 @@ static const struct mlxsw_config_profile mlxsw_sp_config_profile = { .resource_query_enable = 1, }; -static bool -mlxsw_sp_resource_kvd_granularity_validate(struct netlink_ext_ack *extack, - u64 size) -{ - const struct mlxsw_config_profile *profile; - - profile = &mlxsw_sp_config_profile; - if (size % profile->kvd_hash_granularity) { - NL_SET_ERR_MSG_MOD(extack, "resource set with wrong granularity"); - return false; - } - return true; -} - -static int -mlxsw_sp_resource_kvd_size_validate(struct devlink *devlink, u64 size, - struct netlink_ext_ack *extack) -{ - NL_SET_ERR_MSG_MOD(extack, "kvd size cannot be changed"); - return -EINVAL; -} - -static int -mlxsw_sp_resource_kvd_linear_size_validate(struct devlink *devlink, u64 size, - struct netlink_ext_ack *extack) -{ - if (!mlxsw_sp_resource_kvd_granularity_validate(extack, size)) - return -EINVAL; - - return 0; -} - -static int -mlxsw_sp_resource_kvd_hash_single_size_validate(struct devlink *devlink, u64 size, - struct netlink_ext_ack *extack) -{ - struct mlxsw_core *mlxsw_core = devlink_priv(devlink); - - if (!mlxsw_sp_resource_kvd_granularity_validate(extack, size)) - return -EINVAL; - - if (size < MLXSW_CORE_RES_GET(mlxsw_core, KVD_SINGLE_MIN_SIZE)) { - NL_SET_ERR_MSG_MOD(extack, "hash single size is smaller than minimum"); - return -EINVAL; - } - return 0; -} - -static int -mlxsw_sp_resource_kvd_hash_double_size_validate(struct devlink *devlink, u64 size, - struct netlink_ext_ack *extack) -{ - struct mlxsw_core *mlxsw_core = devlink_priv(devlink); - - if (!mlxsw_sp_resource_kvd_granularity_validate(extack, size)) - return -EINVAL; - - if (size < MLXSW_CORE_RES_GET(mlxsw_core, KVD_DOUBLE_MIN_SIZE)) { - NL_SET_ERR_MSG_MOD(extack, "hash double size is smaller than minimum"); - return -EINVAL; - } - return 0; -} - static u64 mlxsw_sp_resource_kvd_linear_occ_get(struct devlink *devlink) { struct mlxsw_core *mlxsw_core = devlink_priv(devlink); @@ -4196,23 +3818,10 @@ static u64 mlxsw_sp_resource_kvd_linear_occ_get(struct devlink *devlink) return mlxsw_sp_kvdl_occ_get(mlxsw_sp); } -static struct devlink_resource_ops mlxsw_sp_resource_kvd_ops = { - .size_validate = mlxsw_sp_resource_kvd_size_validate, -}; - static struct devlink_resource_ops mlxsw_sp_resource_kvd_linear_ops = { - .size_validate = mlxsw_sp_resource_kvd_linear_size_validate, .occ_get = mlxsw_sp_resource_kvd_linear_occ_get, }; -static struct devlink_resource_ops mlxsw_sp_resource_kvd_hash_single_ops = { - .size_validate = mlxsw_sp_resource_kvd_hash_single_size_validate, -}; - -static struct devlink_resource_ops mlxsw_sp_resource_kvd_hash_double_ops = { - .size_validate = mlxsw_sp_resource_kvd_hash_double_size_validate, -}; - static void mlxsw_sp_resource_size_params_prepare(struct mlxsw_core *mlxsw_core, struct devlink_resource_size_params *kvd_size_params, @@ -4275,7 +3884,7 @@ static int mlxsw_sp_resources_register(struct mlxsw_core *mlxsw_core) MLXSW_SP_RESOURCE_KVD, DEVLINK_RESOURCE_ID_PARENT_TOP, &kvd_size_params, - &mlxsw_sp_resource_kvd_ops); + NULL); if (err) return err; @@ -4289,6 +3898,10 @@ static int mlxsw_sp_resources_register(struct mlxsw_core *mlxsw_core) if (err) return err; + err = mlxsw_sp_kvdl_resources_register(devlink); + if (err) + return err; + double_size = kvd_size - linear_size; double_size *= profile->kvd_hash_double_parts; double_size /= profile->kvd_hash_double_parts + @@ -4299,7 +3912,7 @@ static int mlxsw_sp_resources_register(struct mlxsw_core *mlxsw_core) MLXSW_SP_RESOURCE_KVD_HASH_DOUBLE, MLXSW_SP_RESOURCE_KVD, &hash_double_size_params, - &mlxsw_sp_resource_kvd_hash_double_ops); + NULL); if (err) return err; @@ -4309,7 +3922,7 @@ static int mlxsw_sp_resources_register(struct mlxsw_core *mlxsw_core) MLXSW_SP_RESOURCE_KVD_HASH_SINGLE, MLXSW_SP_RESOURCE_KVD, &hash_single_size_params, - &mlxsw_sp_resource_kvd_hash_single_ops); + NULL); if (err) return err; @@ -4563,13 +4176,11 @@ mlxsw_sp_master_lag_check(struct mlxsw_sp *mlxsw_sp, u16 lag_id; if (mlxsw_sp_lag_index_get(mlxsw_sp, lag_dev, &lag_id) != 0) { - NL_SET_ERR_MSG(extack, - "spectrum: Exceeded number of supported LAG devices"); + NL_SET_ERR_MSG_MOD(extack, "Exceeded number of supported LAG devices"); return false; } if (lag_upper_info->tx_type != NETDEV_LAG_TX_TYPE_HASH) { - NL_SET_ERR_MSG(extack, - "spectrum: LAG device using unsupported Tx type"); + NL_SET_ERR_MSG_MOD(extack, "LAG device using unsupported Tx type"); return false; } return true; @@ -4811,8 +4422,7 @@ static int mlxsw_sp_netdevice_port_upper_event(struct net_device *lower_dev, !netif_is_lag_master(upper_dev) && !netif_is_bridge_master(upper_dev) && !netif_is_ovs_master(upper_dev)) { - NL_SET_ERR_MSG(extack, - "spectrum: Unknown upper device type"); + NL_SET_ERR_MSG_MOD(extack, "Unknown upper device type"); return -EINVAL; } if (!info->linking) @@ -4821,8 +4431,7 @@ static int mlxsw_sp_netdevice_port_upper_event(struct net_device *lower_dev, (!netif_is_bridge_master(upper_dev) || !mlxsw_sp_bridge_device_is_offloaded(mlxsw_sp, upper_dev))) { - NL_SET_ERR_MSG(extack, - "spectrum: Enslaving a port to a device that already has an upper device is not supported"); + NL_SET_ERR_MSG_MOD(extack, "Enslaving a port to a device that already has an upper device is not supported"); return -EINVAL; } if (netif_is_lag_master(upper_dev) && @@ -4830,24 +4439,20 @@ static int mlxsw_sp_netdevice_port_upper_event(struct net_device *lower_dev, info->upper_info, extack)) return -EINVAL; if (netif_is_lag_master(upper_dev) && vlan_uses_dev(dev)) { - NL_SET_ERR_MSG(extack, - "spectrum: Master device is a LAG master and this device has a VLAN"); + NL_SET_ERR_MSG_MOD(extack, "Master device is a LAG master and this device has a VLAN"); return -EINVAL; } if (netif_is_lag_port(dev) && is_vlan_dev(upper_dev) && !netif_is_lag_master(vlan_dev_real_dev(upper_dev))) { - NL_SET_ERR_MSG(extack, - "spectrum: Can not put a VLAN on a LAG port"); + NL_SET_ERR_MSG_MOD(extack, "Can not put a VLAN on a LAG port"); return -EINVAL; } if (netif_is_ovs_master(upper_dev) && vlan_uses_dev(dev)) { - NL_SET_ERR_MSG(extack, - "spectrum: Master device is an OVS master and this device has a VLAN"); + NL_SET_ERR_MSG_MOD(extack, "Master device is an OVS master and this device has a VLAN"); return -EINVAL; } if (netif_is_ovs_port(dev) && is_vlan_dev(upper_dev)) { - NL_SET_ERR_MSG(extack, - "spectrum: Can not put a VLAN on an OVS port"); + NL_SET_ERR_MSG_MOD(extack, "Can not put a VLAN on an OVS port"); return -EINVAL; } break; @@ -4960,7 +4565,7 @@ static int mlxsw_sp_netdevice_port_vlan_event(struct net_device *vlan_dev, case NETDEV_PRECHANGEUPPER: upper_dev = info->upper_dev; if (!netif_is_bridge_master(upper_dev)) { - NL_SET_ERR_MSG(extack, "spectrum: VLAN devices only support bridge and VRF uppers"); + NL_SET_ERR_MSG_MOD(extack, "VLAN devices only support bridge and VRF uppers"); return -EINVAL; } if (!info->linking) @@ -4969,7 +4574,7 @@ static int mlxsw_sp_netdevice_port_vlan_event(struct net_device *vlan_dev, (!netif_is_bridge_master(upper_dev) || !mlxsw_sp_bridge_device_is_offloaded(mlxsw_sp, upper_dev))) { - NL_SET_ERR_MSG(extack, "spectrum: Enslaving a port to a device that already has an upper device is not supported"); + NL_SET_ERR_MSG_MOD(extack, "Enslaving a port to a device that already has an upper device is not supported"); return -EINVAL; } break; @@ -5047,10 +4652,18 @@ static int mlxsw_sp_netdevice_event(struct notifier_block *nb, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); + struct mlxsw_sp_span_entry *span_entry; struct mlxsw_sp *mlxsw_sp; int err = 0; mlxsw_sp = container_of(nb, struct mlxsw_sp, netdevice_nb); + if (event == NETDEV_UNREGISTER) { + span_entry = mlxsw_sp_span_entry_find_by_port(mlxsw_sp, dev); + if (span_entry) + mlxsw_sp_span_entry_invalidate(mlxsw_sp, span_entry); + } + mlxsw_sp_span_respin(mlxsw_sp); + if (mlxsw_sp_netdev_is_ipip_ol(mlxsw_sp, dev)) err = mlxsw_sp_netdevice_ipip_ol_event(mlxsw_sp, dev, event, ptr); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h index 4ec1ca3c96c8..92194a9b2caf 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h @@ -70,16 +70,23 @@ #define MLXSW_SP_RESOURCE_NAME_KVD_LINEAR "linear" #define MLXSW_SP_RESOURCE_NAME_KVD_HASH_SINGLE "hash_single" #define MLXSW_SP_RESOURCE_NAME_KVD_HASH_DOUBLE "hash_double" +#define MLXSW_SP_RESOURCE_NAME_KVD_LINEAR_SINGLES "singles" +#define MLXSW_SP_RESOURCE_NAME_KVD_LINEAR_CHUNKS "chunks" +#define MLXSW_SP_RESOURCE_NAME_KVD_LINEAR_LARGE_CHUNKS "large_chunks" enum mlxsw_sp_resource_id { MLXSW_SP_RESOURCE_KVD, MLXSW_SP_RESOURCE_KVD_LINEAR, MLXSW_SP_RESOURCE_KVD_HASH_SINGLE, MLXSW_SP_RESOURCE_KVD_HASH_DOUBLE, + MLXSW_SP_RESOURCE_KVD_LINEAR_SINGLE, + MLXSW_SP_RESOURCE_KVD_LINEAR_CHUNKS, + MLXSW_SP_RESOURCE_KVD_LINEAR_LARGE_CHUNKS, }; struct mlxsw_sp_port; struct mlxsw_sp_rif; +struct mlxsw_sp_span_entry; struct mlxsw_sp_upper { struct net_device *dev; @@ -111,32 +118,13 @@ struct mlxsw_sp_mid { unsigned long *ports_in_mid; /* bits array */ }; -enum mlxsw_sp_span_type { - MLXSW_SP_SPAN_EGRESS, - MLXSW_SP_SPAN_INGRESS -}; - -struct mlxsw_sp_span_inspected_port { - struct list_head list; - enum mlxsw_sp_span_type type; - u8 local_port; -}; - -struct mlxsw_sp_span_entry { - u8 local_port; - bool used; - struct list_head bound_ports_list; - int ref_count; - int id; -}; - enum mlxsw_sp_port_mall_action_type { MLXSW_SP_PORT_MALL_MIRROR, MLXSW_SP_PORT_MALL_SAMPLE, }; struct mlxsw_sp_port_mall_mirror_tc_entry { - u8 to_local_port; + int span_id; bool ingress; }; @@ -223,6 +211,8 @@ struct mlxsw_sp_port_xstats { u64 wred_drop[TC_MAX_QUEUE]; u64 tail_drop[TC_MAX_QUEUE]; u64 backlog[TC_MAX_QUEUE]; + u64 tx_bytes[IEEE_8021QAZ_MAX_TCS]; + u64 tx_packets[IEEE_8021QAZ_MAX_TCS]; }; struct mlxsw_sp_port { @@ -260,6 +250,7 @@ struct mlxsw_sp_port { struct mlxsw_sp_port_sample *sample; struct list_head vlans_list; struct mlxsw_sp_qdisc *root_qdisc; + struct mlxsw_sp_qdisc *tclass_qdiscs; unsigned acl_rule_count; struct mlxsw_sp_acl_block *ing_acl_block; struct mlxsw_sp_acl_block *eg_acl_block; @@ -397,16 +388,6 @@ struct mlxsw_sp_port *mlxsw_sp_port_dev_lower_find(struct net_device *dev); struct mlxsw_sp_port *mlxsw_sp_port_lower_dev_hold(struct net_device *dev); void mlxsw_sp_port_dev_put(struct mlxsw_sp_port *mlxsw_sp_port); struct mlxsw_sp_port *mlxsw_sp_port_dev_lower_find_rcu(struct net_device *dev); -int mlxsw_sp_span_mirror_add(struct mlxsw_sp_port *from, - struct mlxsw_sp_port *to, - enum mlxsw_sp_span_type type, - bool bind); -void mlxsw_sp_span_mirror_del(struct mlxsw_sp_port *from, - u8 destination_port, - enum mlxsw_sp_span_type type, - bool bind); -struct mlxsw_sp_span_entry * -mlxsw_sp_span_entry_find(struct mlxsw_sp *mlxsw_sp, u8 local_port); /* spectrum_dcb.c */ #ifdef CONFIG_MLXSW_SPECTRUM_DCB @@ -462,6 +443,7 @@ int mlxsw_sp_kvdl_alloc_size_query(struct mlxsw_sp *mlxsw_sp, unsigned int entry_count, unsigned int *p_alloc_size); u64 mlxsw_sp_kvdl_occ_get(const struct mlxsw_sp *mlxsw_sp); +int mlxsw_sp_kvdl_resources_register(struct devlink *devlink); struct mlxsw_sp_acl_rule_info { unsigned int priority; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c index 0897a5435cc2..21ed27ae51e3 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c @@ -572,7 +572,6 @@ int mlxsw_sp_acl_rulei_act_mirror(struct mlxsw_sp *mlxsw_sp, struct net_device *out_dev) { struct mlxsw_sp_acl_block_binding *binding; - struct mlxsw_sp_port *out_port; struct mlxsw_sp_port *in_port; if (!list_is_singular(&block->binding_list)) @@ -581,16 +580,10 @@ int mlxsw_sp_acl_rulei_act_mirror(struct mlxsw_sp *mlxsw_sp, binding = list_first_entry(&block->binding_list, struct mlxsw_sp_acl_block_binding, list); in_port = binding->mlxsw_sp_port; - if (!mlxsw_sp_port_dev_check(out_dev)) - return -EINVAL; - - out_port = netdev_priv(out_dev); - if (out_port->mlxsw_sp != mlxsw_sp) - return -EINVAL; return mlxsw_afa_block_append_mirror(rulei->act_block, in_port->local_port, - out_port->local_port, + out_dev, binding->ingress); } diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_actions.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_actions.c index 6ca6894125f0..510ce48d87f7 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_actions.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_actions.c @@ -1,6 +1,6 @@ /* * drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_actions.c - * Copyright (c) 2017 Mellanox Technologies. All rights reserved. + * Copyright (c) 2017, 2018 Mellanox Technologies. All rights reserved. * Copyright (c) 2017 Jiri Pirko <jiri@mellanox.com> * Copyright (c) 2017 Yotam Gigi <yotamg@mellanox.com> * @@ -35,6 +35,7 @@ #include "spectrum_acl_flex_actions.h" #include "core_acl_flex_actions.h" +#include "spectrum_span.h" #define MLXSW_SP_KVDL_ACT_EXT_SIZE 1 @@ -125,40 +126,23 @@ mlxsw_sp_act_counter_index_put(void *priv, unsigned int counter_index) } static int -mlxsw_sp_act_mirror_add(void *priv, u8 local_in_port, u8 local_out_port, +mlxsw_sp_act_mirror_add(void *priv, u8 local_in_port, + const struct net_device *out_dev, bool ingress, int *p_span_id) { - struct mlxsw_sp_port *in_port, *out_port; - struct mlxsw_sp_span_entry *span_entry; + struct mlxsw_sp_port *in_port; struct mlxsw_sp *mlxsw_sp = priv; enum mlxsw_sp_span_type type; - int err; type = ingress ? MLXSW_SP_SPAN_INGRESS : MLXSW_SP_SPAN_EGRESS; - out_port = mlxsw_sp->ports[local_out_port]; in_port = mlxsw_sp->ports[local_in_port]; - err = mlxsw_sp_span_mirror_add(in_port, out_port, type, false); - if (err) - return err; - - span_entry = mlxsw_sp_span_entry_find(mlxsw_sp, local_out_port); - if (!span_entry) { - err = -ENOENT; - goto err_span_entry_find; - } - - *p_span_id = span_entry->id; - return 0; - -err_span_entry_find: - mlxsw_sp_span_mirror_del(in_port, local_out_port, type, false); - return err; + return mlxsw_sp_span_mirror_add(in_port, out_dev, type, + false, p_span_id); } static void -mlxsw_sp_act_mirror_del(void *priv, u8 local_in_port, u8 local_out_port, - bool ingress) +mlxsw_sp_act_mirror_del(void *priv, u8 local_in_port, int span_id, bool ingress) { struct mlxsw_sp *mlxsw_sp = priv; struct mlxsw_sp_port *in_port; @@ -167,7 +151,7 @@ mlxsw_sp_act_mirror_del(void *priv, u8 local_in_port, u8 local_out_port, type = ingress ? MLXSW_SP_SPAN_INGRESS : MLXSW_SP_SPAN_EGRESS; in_port = mlxsw_sp->ports[local_in_port]; - mlxsw_sp_span_mirror_del(in_port, local_out_port, type, false); + mlxsw_sp_span_mirror_del(in_port, span_id, type, false); } static const struct mlxsw_afa_ops mlxsw_sp_act_afa_ops = { diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c index 7502e53447bd..98d896c14b87 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c @@ -1,7 +1,7 @@ /* * drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c - * Copyright (c) 2017 Mellanox Technologies. All rights reserved. - * Copyright (c) 2017 Petr Machata <petrm@mellanox.com> + * Copyright (c) 2017-2018 Mellanox Technologies. All rights reserved. + * Copyright (c) 2017-2018 Petr Machata <petrm@mellanox.com> * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions are met: @@ -33,126 +33,125 @@ */ #include <net/ip_tunnels.h> +#include <net/ip6_tunnel.h> #include "spectrum_ipip.h" struct ip_tunnel_parm -mlxsw_sp_ipip_netdev_parms(const struct net_device *ol_dev) +mlxsw_sp_ipip_netdev_parms4(const struct net_device *ol_dev) { struct ip_tunnel *tun = netdev_priv(ol_dev); return tun->parms; } -static bool mlxsw_sp_ipip_parms_has_ikey(struct ip_tunnel_parm parms) +struct __ip6_tnl_parm +mlxsw_sp_ipip_netdev_parms6(const struct net_device *ol_dev) +{ + struct ip6_tnl *tun = netdev_priv(ol_dev); + + return tun->parms; +} + +static bool mlxsw_sp_ipip_parms4_has_ikey(struct ip_tunnel_parm parms) { return !!(parms.i_flags & TUNNEL_KEY); } -static bool mlxsw_sp_ipip_parms_has_okey(struct ip_tunnel_parm parms) +static bool mlxsw_sp_ipip_parms4_has_okey(struct ip_tunnel_parm parms) { return !!(parms.o_flags & TUNNEL_KEY); } -static u32 mlxsw_sp_ipip_parms_ikey(struct ip_tunnel_parm parms) +static u32 mlxsw_sp_ipip_parms4_ikey(struct ip_tunnel_parm parms) { - return mlxsw_sp_ipip_parms_has_ikey(parms) ? + return mlxsw_sp_ipip_parms4_has_ikey(parms) ? be32_to_cpu(parms.i_key) : 0; } -static u32 mlxsw_sp_ipip_parms_okey(struct ip_tunnel_parm parms) +static u32 mlxsw_sp_ipip_parms4_okey(struct ip_tunnel_parm parms) { - return mlxsw_sp_ipip_parms_has_okey(parms) ? + return mlxsw_sp_ipip_parms4_has_okey(parms) ? be32_to_cpu(parms.o_key) : 0; } -static __be32 mlxsw_sp_ipip_parms_saddr4(struct ip_tunnel_parm parms) +static union mlxsw_sp_l3addr +mlxsw_sp_ipip_parms4_saddr(struct ip_tunnel_parm parms) { - return parms.iph.saddr; + return (union mlxsw_sp_l3addr) { .addr4 = parms.iph.saddr }; } static union mlxsw_sp_l3addr -mlxsw_sp_ipip_parms_saddr(enum mlxsw_sp_l3proto proto, - struct ip_tunnel_parm parms) +mlxsw_sp_ipip_parms6_saddr(struct __ip6_tnl_parm parms) { - switch (proto) { - case MLXSW_SP_L3_PROTO_IPV4: - return (union mlxsw_sp_l3addr) { - .addr4 = mlxsw_sp_ipip_parms_saddr4(parms), - }; - case MLXSW_SP_L3_PROTO_IPV6: - break; - } - - WARN_ON(1); - return (union mlxsw_sp_l3addr) { - .addr4 = 0, - }; + return (union mlxsw_sp_l3addr) { .addr6 = parms.laddr }; } -static __be32 mlxsw_sp_ipip_parms_daddr4(struct ip_tunnel_parm parms) +static union mlxsw_sp_l3addr +mlxsw_sp_ipip_parms4_daddr(struct ip_tunnel_parm parms) { - return parms.iph.daddr; + return (union mlxsw_sp_l3addr) { .addr4 = parms.iph.daddr }; } static union mlxsw_sp_l3addr -mlxsw_sp_ipip_parms_daddr(enum mlxsw_sp_l3proto proto, - struct ip_tunnel_parm parms) +mlxsw_sp_ipip_parms6_daddr(struct __ip6_tnl_parm parms) +{ + return (union mlxsw_sp_l3addr) { .addr6 = parms.raddr }; +} + +union mlxsw_sp_l3addr +mlxsw_sp_ipip_netdev_saddr(enum mlxsw_sp_l3proto proto, + const struct net_device *ol_dev) { + struct ip_tunnel_parm parms4; + struct __ip6_tnl_parm parms6; + switch (proto) { case MLXSW_SP_L3_PROTO_IPV4: - return (union mlxsw_sp_l3addr) { - .addr4 = mlxsw_sp_ipip_parms_daddr4(parms), - }; + parms4 = mlxsw_sp_ipip_netdev_parms4(ol_dev); + return mlxsw_sp_ipip_parms4_saddr(parms4); case MLXSW_SP_L3_PROTO_IPV6: - break; + parms6 = mlxsw_sp_ipip_netdev_parms6(ol_dev); + return mlxsw_sp_ipip_parms6_saddr(parms6); } WARN_ON(1); - return (union mlxsw_sp_l3addr) { - .addr4 = 0, - }; -} - -static bool mlxsw_sp_ipip_netdev_has_ikey(const struct net_device *ol_dev) -{ - return mlxsw_sp_ipip_parms_has_ikey(mlxsw_sp_ipip_netdev_parms(ol_dev)); + return (union mlxsw_sp_l3addr) {0}; } -static bool mlxsw_sp_ipip_netdev_has_okey(const struct net_device *ol_dev) +static __be32 mlxsw_sp_ipip_netdev_daddr4(const struct net_device *ol_dev) { - return mlxsw_sp_ipip_parms_has_okey(mlxsw_sp_ipip_netdev_parms(ol_dev)); -} -static u32 mlxsw_sp_ipip_netdev_ikey(const struct net_device *ol_dev) -{ - return mlxsw_sp_ipip_parms_ikey(mlxsw_sp_ipip_netdev_parms(ol_dev)); -} + struct ip_tunnel_parm parms4 = mlxsw_sp_ipip_netdev_parms4(ol_dev); -static u32 mlxsw_sp_ipip_netdev_okey(const struct net_device *ol_dev) -{ - return mlxsw_sp_ipip_parms_okey(mlxsw_sp_ipip_netdev_parms(ol_dev)); + return mlxsw_sp_ipip_parms4_daddr(parms4).addr4; } -union mlxsw_sp_l3addr -mlxsw_sp_ipip_netdev_saddr(enum mlxsw_sp_l3proto proto, +static union mlxsw_sp_l3addr +mlxsw_sp_ipip_netdev_daddr(enum mlxsw_sp_l3proto proto, const struct net_device *ol_dev) { - return mlxsw_sp_ipip_parms_saddr(proto, - mlxsw_sp_ipip_netdev_parms(ol_dev)); -} + struct ip_tunnel_parm parms4; + struct __ip6_tnl_parm parms6; -static __be32 mlxsw_sp_ipip_netdev_daddr4(const struct net_device *ol_dev) -{ - return mlxsw_sp_ipip_parms_daddr4(mlxsw_sp_ipip_netdev_parms(ol_dev)); + switch (proto) { + case MLXSW_SP_L3_PROTO_IPV4: + parms4 = mlxsw_sp_ipip_netdev_parms4(ol_dev); + return mlxsw_sp_ipip_parms4_daddr(parms4); + case MLXSW_SP_L3_PROTO_IPV6: + parms6 = mlxsw_sp_ipip_netdev_parms6(ol_dev); + return mlxsw_sp_ipip_parms6_daddr(parms6); + } + + WARN_ON(1); + return (union mlxsw_sp_l3addr) {0}; } -static union mlxsw_sp_l3addr -mlxsw_sp_ipip_netdev_daddr(enum mlxsw_sp_l3proto proto, - const struct net_device *ol_dev) +bool mlxsw_sp_l3addr_is_zero(union mlxsw_sp_l3addr addr) { - return mlxsw_sp_ipip_parms_daddr(proto, - mlxsw_sp_ipip_netdev_parms(ol_dev)); + union mlxsw_sp_l3addr naddr = {0}; + + return !memcmp(&addr, &naddr, sizeof(naddr)); } static int @@ -176,12 +175,17 @@ mlxsw_sp_ipip_fib_entry_op_gre4_rtdp(struct mlxsw_sp *mlxsw_sp, u32 tunnel_index, struct mlxsw_sp_ipip_entry *ipip_entry) { - bool has_ikey = mlxsw_sp_ipip_netdev_has_ikey(ipip_entry->ol_dev); u16 rif_index = mlxsw_sp_ipip_lb_rif_index(ipip_entry->ol_lb); - u32 ikey = mlxsw_sp_ipip_netdev_ikey(ipip_entry->ol_dev); char rtdp_pl[MLXSW_REG_RTDP_LEN]; + struct ip_tunnel_parm parms; unsigned int type_check; + bool has_ikey; u32 daddr4; + u32 ikey; + + parms = mlxsw_sp_ipip_netdev_parms4(ipip_entry->ol_dev); + has_ikey = mlxsw_sp_ipip_parms4_has_ikey(parms); + ikey = mlxsw_sp_ipip_parms4_ikey(parms); mlxsw_reg_rtdp_pack(rtdp_pl, MLXSW_REG_RTDP_TYPE_IPIP, tunnel_index); @@ -243,15 +247,14 @@ static bool mlxsw_sp_ipip_tunnel_complete(enum mlxsw_sp_l3proto proto, { union mlxsw_sp_l3addr saddr = mlxsw_sp_ipip_netdev_saddr(proto, ol_dev); union mlxsw_sp_l3addr daddr = mlxsw_sp_ipip_netdev_daddr(proto, ol_dev); - union mlxsw_sp_l3addr naddr = {0}; /* Tunnels with unset local or remote address are valid in Linux and * used for lightweight tunnels (LWT) and Non-Broadcast Multi-Access * (NBMA) tunnels. In principle these can be offloaded, but the driver * currently doesn't support this. So punt. */ - return memcmp(&saddr, &naddr, sizeof(naddr)) && - memcmp(&daddr, &naddr, sizeof(naddr)); + return !mlxsw_sp_l3addr_is_zero(saddr) && + !mlxsw_sp_l3addr_is_zero(daddr); } static bool mlxsw_sp_ipip_can_offload_gre4(const struct mlxsw_sp *mlxsw_sp, @@ -273,14 +276,15 @@ static struct mlxsw_sp_rif_ipip_lb_config mlxsw_sp_ipip_ol_loopback_config_gre4(struct mlxsw_sp *mlxsw_sp, const struct net_device *ol_dev) { + struct ip_tunnel_parm parms = mlxsw_sp_ipip_netdev_parms4(ol_dev); enum mlxsw_reg_ritr_loopback_ipip_type lb_ipipt; - lb_ipipt = mlxsw_sp_ipip_netdev_has_okey(ol_dev) ? + lb_ipipt = mlxsw_sp_ipip_parms4_has_okey(parms) ? MLXSW_REG_RITR_LOOPBACK_IPIP_TYPE_IP_IN_GRE_KEY_IN_IP : MLXSW_REG_RITR_LOOPBACK_IPIP_TYPE_IP_IN_GRE_IN_IP; return (struct mlxsw_sp_rif_ipip_lb_config){ .lb_ipipt = lb_ipipt, - .okey = mlxsw_sp_ipip_netdev_okey(ol_dev), + .okey = mlxsw_sp_ipip_parms4_okey(parms), .ul_protocol = MLXSW_SP_L3_PROTO_IPV4, .saddr = mlxsw_sp_ipip_netdev_saddr(MLXSW_SP_L3_PROTO_IPV4, ol_dev), @@ -300,16 +304,12 @@ mlxsw_sp_ipip_ol_netdev_change_gre4(struct mlxsw_sp *mlxsw_sp, bool update_nhs = false; int err = 0; - new_parms = mlxsw_sp_ipip_netdev_parms(ipip_entry->ol_dev); + new_parms = mlxsw_sp_ipip_netdev_parms4(ipip_entry->ol_dev); - new_saddr = mlxsw_sp_ipip_parms_saddr(MLXSW_SP_L3_PROTO_IPV4, - new_parms); - old_saddr = mlxsw_sp_ipip_parms_saddr(MLXSW_SP_L3_PROTO_IPV4, - ipip_entry->parms); - new_daddr = mlxsw_sp_ipip_parms_daddr(MLXSW_SP_L3_PROTO_IPV4, - new_parms); - old_daddr = mlxsw_sp_ipip_parms_daddr(MLXSW_SP_L3_PROTO_IPV4, - ipip_entry->parms); + new_saddr = mlxsw_sp_ipip_parms4_saddr(new_parms); + old_saddr = mlxsw_sp_ipip_parms4_saddr(ipip_entry->parms4); + new_daddr = mlxsw_sp_ipip_parms4_daddr(new_parms); + old_daddr = mlxsw_sp_ipip_parms4_daddr(ipip_entry->parms4); if (!mlxsw_sp_l3addr_eq(&new_saddr, &old_saddr)) { u16 ul_tb_id = mlxsw_sp_ipip_dev_ul_tb_id(ipip_entry->ol_dev); @@ -326,14 +326,14 @@ mlxsw_sp_ipip_ol_netdev_change_gre4(struct mlxsw_sp *mlxsw_sp, } update_tunnel = true; - } else if ((mlxsw_sp_ipip_parms_okey(ipip_entry->parms) != - mlxsw_sp_ipip_parms_okey(new_parms)) || - ipip_entry->parms.link != new_parms.link) { + } else if ((mlxsw_sp_ipip_parms4_okey(ipip_entry->parms4) != + mlxsw_sp_ipip_parms4_okey(new_parms)) || + ipip_entry->parms4.link != new_parms.link) { update_tunnel = true; } else if (!mlxsw_sp_l3addr_eq(&new_daddr, &old_daddr)) { update_nhs = true; - } else if (mlxsw_sp_ipip_parms_ikey(ipip_entry->parms) != - mlxsw_sp_ipip_parms_ikey(new_parms)) { + } else if (mlxsw_sp_ipip_parms4_ikey(ipip_entry->parms4) != + mlxsw_sp_ipip_parms4_ikey(new_parms)) { update_decap = true; } @@ -350,7 +350,7 @@ mlxsw_sp_ipip_ol_netdev_change_gre4(struct mlxsw_sp *mlxsw_sp, false, false, false, extack); - ipip_entry->parms = new_parms; + ipip_entry->parms4 = new_parms; return err; } diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.h index 04b08d9d76e9..6909d867bb59 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.h @@ -1,7 +1,7 @@ /* * drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.h - * Copyright (c) 2017 Mellanox Technologies. All rights reserved. - * Copyright (c) 2017 Petr Machata <petrm@mellanox.com> + * Copyright (c) 2017-2018 Mellanox Technologies. All rights reserved. + * Copyright (c) 2017-2018 Petr Machata <petrm@mellanox.com> * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions are met: @@ -37,14 +37,19 @@ #include "spectrum_router.h" #include <net/ip_fib.h> +#include <linux/if_tunnel.h> struct ip_tunnel_parm -mlxsw_sp_ipip_netdev_parms(const struct net_device *ol_dev); +mlxsw_sp_ipip_netdev_parms4(const struct net_device *ol_dev); +struct __ip6_tnl_parm +mlxsw_sp_ipip_netdev_parms6(const struct net_device *ol_dev); union mlxsw_sp_l3addr mlxsw_sp_ipip_netdev_saddr(enum mlxsw_sp_l3proto proto, const struct net_device *ol_dev); +bool mlxsw_sp_l3addr_is_zero(union mlxsw_sp_l3addr addr); + enum mlxsw_sp_ipip_type { MLXSW_SP_IPIP_TYPE_GRE4, MLXSW_SP_IPIP_TYPE_MAX, @@ -56,7 +61,9 @@ struct mlxsw_sp_ipip_entry { struct mlxsw_sp_rif_ipip_lb *ol_lb; struct mlxsw_sp_fib_entry *decap_fib_entry; struct list_head ipip_list_node; - struct ip_tunnel_parm parms; + union { + struct ip_tunnel_parm parms4; + }; }; struct mlxsw_sp_ipip_ops { diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_kvdl.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_kvdl.c index 55f9d2d70f9e..059eb3214328 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_kvdl.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_kvdl.c @@ -67,7 +67,7 @@ struct mlxsw_sp_kvdl_part_info { struct mlxsw_sp_kvdl_part { struct list_head list; - const struct mlxsw_sp_kvdl_part_info *info; + struct mlxsw_sp_kvdl_part_info *info; unsigned long usage[0]; /* Entries */ }; @@ -188,21 +188,27 @@ int mlxsw_sp_kvdl_alloc_size_query(struct mlxsw_sp *mlxsw_sp, return 0; } +enum mlxsw_sp_kvdl_part_id { + MLXSW_SP_KVDL_PART_SINGLE, + MLXSW_SP_KVDL_PART_CHUNKS, + MLXSW_SP_KVDL_PART_LARGE_CHUNKS, +}; + static const struct mlxsw_sp_kvdl_part_info kvdl_parts_info[] = { { - .part_index = 0, + .part_index = MLXSW_SP_KVDL_PART_SINGLE, .start_index = MLXSW_SP_KVDL_SINGLE_BASE, .end_index = MLXSW_SP_KVDL_SINGLE_END, .alloc_size = 1, }, { - .part_index = 1, + .part_index = MLXSW_SP_KVDL_PART_CHUNKS, .start_index = MLXSW_SP_KVDL_CHUNKS_BASE, .end_index = MLXSW_SP_KVDL_CHUNKS_END, .alloc_size = MLXSW_SP_CHUNK_MAX, }, { - .part_index = 2, + .part_index = MLXSW_SP_KVDL_PART_LARGE_CHUNKS, .start_index = MLXSW_SP_KVDL_LARGE_CHUNKS_BASE, .end_index = MLXSW_SP_KVDL_LARGE_CHUNKS_END, .alloc_size = MLXSW_SP_LARGE_CHUNK_MAX, @@ -222,27 +228,76 @@ mlxsw_sp_kvdl_part_find(struct mlxsw_sp *mlxsw_sp, unsigned int part_index) return NULL; } +static void +mlxsw_sp_kvdl_part_update(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_kvdl_part *part, unsigned int size) +{ + struct mlxsw_sp_kvdl_part_info *info = part->info; + + if (list_is_last(&part->list, &mlxsw_sp->kvdl->parts_list)) { + info->end_index = size - 1; + } else { + struct mlxsw_sp_kvdl_part *last_part; + + last_part = list_next_entry(part, list); + info->start_index = last_part->info->end_index + 1; + info->end_index = info->start_index + size - 1; + } +} + static int mlxsw_sp_kvdl_part_init(struct mlxsw_sp *mlxsw_sp, unsigned int part_index) { + struct devlink *devlink = priv_to_devlink(mlxsw_sp->core); const struct mlxsw_sp_kvdl_part_info *info; + enum mlxsw_sp_resource_id resource_id; struct mlxsw_sp_kvdl_part *part; + bool need_update = true; unsigned int nr_entries; size_t usage_size; + u64 resource_size; + int err; info = &kvdl_parts_info[part_index]; - nr_entries = (info->end_index - info->start_index + 1) / - info->alloc_size; + switch (part_index) { + case MLXSW_SP_KVDL_PART_SINGLE: + resource_id = MLXSW_SP_RESOURCE_KVD_LINEAR_SINGLE; + break; + case MLXSW_SP_KVDL_PART_CHUNKS: + resource_id = MLXSW_SP_RESOURCE_KVD_LINEAR_CHUNKS; + break; + case MLXSW_SP_KVDL_PART_LARGE_CHUNKS: + resource_id = MLXSW_SP_RESOURCE_KVD_LINEAR_LARGE_CHUNKS; + break; + default: + return -EINVAL; + } + + err = devlink_resource_size_get(devlink, resource_id, &resource_size); + if (err) { + need_update = false; + resource_size = info->end_index - info->start_index + 1; + } + + nr_entries = div_u64(resource_size, info->alloc_size); usage_size = BITS_TO_LONGS(nr_entries) * sizeof(unsigned long); part = kzalloc(sizeof(*part) + usage_size, GFP_KERNEL); if (!part) return -ENOMEM; - part->info = info; - list_add(&part->list, &mlxsw_sp->kvdl->parts_list); + part->info = kmemdup(info, sizeof(*part->info), GFP_KERNEL); + if (!part->info) + goto err_part_info_alloc; + list_add(&part->list, &mlxsw_sp->kvdl->parts_list); + if (need_update) + mlxsw_sp_kvdl_part_update(mlxsw_sp, part, resource_size); return 0; + +err_part_info_alloc: + kfree(part); + return -ENOMEM; } static void mlxsw_sp_kvdl_part_fini(struct mlxsw_sp *mlxsw_sp, @@ -255,6 +310,7 @@ static void mlxsw_sp_kvdl_part_fini(struct mlxsw_sp *mlxsw_sp, return; list_del(&part->list); + kfree(part->info); kfree(part); } @@ -312,6 +368,123 @@ u64 mlxsw_sp_kvdl_occ_get(const struct mlxsw_sp *mlxsw_sp) return occ; } +u64 mlxsw_sp_kvdl_single_occ_get(struct devlink *devlink) +{ + struct mlxsw_core *mlxsw_core = devlink_priv(devlink); + struct mlxsw_sp *mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core); + struct mlxsw_sp_kvdl_part *part; + + part = mlxsw_sp_kvdl_part_find(mlxsw_sp, MLXSW_SP_KVDL_PART_SINGLE); + if (!part) + return -EINVAL; + + return mlxsw_sp_kvdl_part_occ(part); +} + +u64 mlxsw_sp_kvdl_chunks_occ_get(struct devlink *devlink) +{ + struct mlxsw_core *mlxsw_core = devlink_priv(devlink); + struct mlxsw_sp *mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core); + struct mlxsw_sp_kvdl_part *part; + + part = mlxsw_sp_kvdl_part_find(mlxsw_sp, MLXSW_SP_KVDL_PART_CHUNKS); + if (!part) + return -EINVAL; + + return mlxsw_sp_kvdl_part_occ(part); +} + +u64 mlxsw_sp_kvdl_large_chunks_occ_get(struct devlink *devlink) +{ + struct mlxsw_core *mlxsw_core = devlink_priv(devlink); + struct mlxsw_sp *mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core); + struct mlxsw_sp_kvdl_part *part; + + part = mlxsw_sp_kvdl_part_find(mlxsw_sp, + MLXSW_SP_KVDL_PART_LARGE_CHUNKS); + if (!part) + return -EINVAL; + + return mlxsw_sp_kvdl_part_occ(part); +} + +static struct devlink_resource_ops mlxsw_sp_kvdl_single_ops = { + .occ_get = mlxsw_sp_kvdl_single_occ_get, +}; + +static struct devlink_resource_ops mlxsw_sp_kvdl_chunks_ops = { + .occ_get = mlxsw_sp_kvdl_chunks_occ_get, +}; + +static struct devlink_resource_ops mlxsw_sp_kvdl_chunks_large_ops = { + .occ_get = mlxsw_sp_kvdl_large_chunks_occ_get, +}; + +static struct devlink_resource_size_params mlxsw_sp_kvdl_single_size_params = { + .size_min = 0, + .size_granularity = 1, + .unit = DEVLINK_RESOURCE_UNIT_ENTRY, +}; + +static struct devlink_resource_size_params mlxsw_sp_kvdl_chunks_size_params = { + .size_min = 0, + .size_granularity = MLXSW_SP_CHUNK_MAX, + .unit = DEVLINK_RESOURCE_UNIT_ENTRY, +}; + +static struct devlink_resource_size_params mlxsw_sp_kvdl_large_chunks_size_params = { + .size_min = 0, + .size_granularity = MLXSW_SP_LARGE_CHUNK_MAX, + .unit = DEVLINK_RESOURCE_UNIT_ENTRY, +}; + +static void +mlxsw_sp_kvdl_resource_size_params_prepare(struct devlink *devlink) +{ + struct mlxsw_core *mlxsw_core = devlink_priv(devlink); + u32 kvdl_max_size; + + kvdl_max_size = MLXSW_CORE_RES_GET(mlxsw_core, KVD_SIZE) - + MLXSW_CORE_RES_GET(mlxsw_core, KVD_SINGLE_MIN_SIZE) - + MLXSW_CORE_RES_GET(mlxsw_core, KVD_DOUBLE_MIN_SIZE); + + mlxsw_sp_kvdl_single_size_params.size_max = kvdl_max_size; + mlxsw_sp_kvdl_chunks_size_params.size_max = kvdl_max_size; + mlxsw_sp_kvdl_large_chunks_size_params.size_max = kvdl_max_size; +} + +int mlxsw_sp_kvdl_resources_register(struct devlink *devlink) +{ + int err; + + mlxsw_sp_kvdl_resource_size_params_prepare(devlink); + err = devlink_resource_register(devlink, MLXSW_SP_RESOURCE_NAME_KVD_LINEAR_SINGLES, + false, MLXSW_SP_KVDL_SINGLE_SIZE, + MLXSW_SP_RESOURCE_KVD_LINEAR_SINGLE, + MLXSW_SP_RESOURCE_KVD_LINEAR, + &mlxsw_sp_kvdl_single_size_params, + &mlxsw_sp_kvdl_single_ops); + if (err) + return err; + + err = devlink_resource_register(devlink, MLXSW_SP_RESOURCE_NAME_KVD_LINEAR_CHUNKS, + false, MLXSW_SP_KVDL_CHUNKS_SIZE, + MLXSW_SP_RESOURCE_KVD_LINEAR_CHUNKS, + MLXSW_SP_RESOURCE_KVD_LINEAR, + &mlxsw_sp_kvdl_chunks_size_params, + &mlxsw_sp_kvdl_chunks_ops); + if (err) + return err; + + err = devlink_resource_register(devlink, MLXSW_SP_RESOURCE_NAME_KVD_LINEAR_LARGE_CHUNKS, + false, MLXSW_SP_KVDL_LARGE_CHUNKS_SIZE, + MLXSW_SP_RESOURCE_KVD_LINEAR_LARGE_CHUNKS, + MLXSW_SP_RESOURCE_KVD_LINEAR, + &mlxsw_sp_kvdl_large_chunks_size_params, + &mlxsw_sp_kvdl_chunks_large_ops); + return err; +} + int mlxsw_sp_kvdl_init(struct mlxsw_sp *mlxsw_sp) { struct mlxsw_sp_kvdl *kvdl; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c index d20b143de3b4..978a3c70653a 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c @@ -126,8 +126,8 @@ mlxsw_sp_mr_route_ivif_in_evifs(const struct mlxsw_sp_mr_route *mr_route) switch (mr_route->mr_table->proto) { case MLXSW_SP_L3_PROTO_IPV4: - ivif = mr_route->mfc4->mfc_parent; - return mr_route->mfc4->mfc_un.res.ttls[ivif] != 255; + ivif = mr_route->mfc4->_c.mfc_parent; + return mr_route->mfc4->_c.mfc_un.res.ttls[ivif] != 255; case MLXSW_SP_L3_PROTO_IPV6: /* fall through */ default: @@ -364,7 +364,7 @@ mlxsw_sp_mr_route4_create(struct mlxsw_sp_mr_table *mr_table, mr_route->mfc4 = mfc; mr_route->mr_table = mr_table; for (i = 0; i < MAXVIFS; i++) { - if (mfc->mfc_un.res.ttls[i] != 255) { + if (mfc->_c.mfc_un.res.ttls[i] != 255) { err = mlxsw_sp_mr_route_evif_link(mr_route, &mr_table->vifs[i]); if (err) @@ -374,7 +374,8 @@ mlxsw_sp_mr_route4_create(struct mlxsw_sp_mr_table *mr_table, mr_route->min_mtu = mr_table->vifs[i].dev->mtu; } } - mlxsw_sp_mr_route_ivif_link(mr_route, &mr_table->vifs[mfc->mfc_parent]); + mlxsw_sp_mr_route_ivif_link(mr_route, + &mr_table->vifs[mfc->_c.mfc_parent]); mr_route->route_action = mlxsw_sp_mr_route_action(mr_route); return mr_route; @@ -418,9 +419,9 @@ static void mlxsw_sp_mr_mfc_offload_set(struct mlxsw_sp_mr_route *mr_route, switch (mr_route->mr_table->proto) { case MLXSW_SP_L3_PROTO_IPV4: if (offload) - mr_route->mfc4->mfc_flags |= MFC_OFFLOAD; + mr_route->mfc4->_c.mfc_flags |= MFC_OFFLOAD; else - mr_route->mfc4->mfc_flags &= ~MFC_OFFLOAD; + mr_route->mfc4->_c.mfc_flags &= ~MFC_OFFLOAD; break; case MLXSW_SP_L3_PROTO_IPV6: /* fall through */ @@ -943,10 +944,10 @@ static void mlxsw_sp_mr_route_stats_update(struct mlxsw_sp *mlxsw_sp, switch (mr_route->mr_table->proto) { case MLXSW_SP_L3_PROTO_IPV4: - if (mr_route->mfc4->mfc_un.res.pkt != packets) - mr_route->mfc4->mfc_un.res.lastuse = jiffies; - mr_route->mfc4->mfc_un.res.pkt = packets; - mr_route->mfc4->mfc_un.res.bytes = bytes; + if (mr_route->mfc4->_c.mfc_un.res.pkt != packets) + mr_route->mfc4->_c.mfc_un.res.lastuse = jiffies; + mr_route->mfc4->_c.mfc_un.res.pkt = packets; + mr_route->mfc4->_c.mfc_un.res.bytes = bytes; break; case MLXSW_SP_L3_PROTO_IPV6: /* fall through */ diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_qdisc.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_qdisc.c index 0b7670459051..91262b0573e3 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_qdisc.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_qdisc.c @@ -42,6 +42,8 @@ #include "reg.h" #define MLXSW_SP_PRIO_BAND_TO_TCLASS(band) (IEEE_8021QAZ_MAX_TCS - band - 1) +#define MLXSW_SP_PRIO_CHILD_TO_TCLASS(child) \ + MLXSW_SP_PRIO_BAND_TO_TCLASS((child - 1)) enum mlxsw_sp_qdisc_type { MLXSW_SP_QDISC_NO_QDISC, @@ -76,6 +78,7 @@ struct mlxsw_sp_qdisc_ops { struct mlxsw_sp_qdisc { u32 handle; u8 tclass_num; + u8 prio_bitmap; union { struct red_stats red; } xstats_base; @@ -99,6 +102,44 @@ mlxsw_sp_qdisc_compare(struct mlxsw_sp_qdisc *mlxsw_sp_qdisc, u32 handle, mlxsw_sp_qdisc->handle == handle; } +static struct mlxsw_sp_qdisc * +mlxsw_sp_qdisc_find(struct mlxsw_sp_port *mlxsw_sp_port, u32 parent, + bool root_only) +{ + int tclass, child_index; + + if (parent == TC_H_ROOT) + return mlxsw_sp_port->root_qdisc; + + if (root_only || !mlxsw_sp_port->root_qdisc || + !mlxsw_sp_port->root_qdisc->ops || + TC_H_MAJ(parent) != mlxsw_sp_port->root_qdisc->handle || + TC_H_MIN(parent) > IEEE_8021QAZ_MAX_TCS) + return NULL; + + child_index = TC_H_MIN(parent); + tclass = MLXSW_SP_PRIO_CHILD_TO_TCLASS(child_index); + return &mlxsw_sp_port->tclass_qdiscs[tclass]; +} + +static struct mlxsw_sp_qdisc * +mlxsw_sp_qdisc_find_by_handle(struct mlxsw_sp_port *mlxsw_sp_port, u32 handle) +{ + int i; + + if (mlxsw_sp_port->root_qdisc->handle == handle) + return mlxsw_sp_port->root_qdisc; + + if (mlxsw_sp_port->root_qdisc->handle == TC_H_UNSPEC) + return NULL; + + for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) + if (mlxsw_sp_port->tclass_qdiscs[i].handle == handle) + return &mlxsw_sp_port->tclass_qdiscs[i]; + + return NULL; +} + static int mlxsw_sp_qdisc_destroy(struct mlxsw_sp_port *mlxsw_sp_port, struct mlxsw_sp_qdisc *mlxsw_sp_qdisc) @@ -185,6 +226,23 @@ mlxsw_sp_qdisc_get_xstats(struct mlxsw_sp_port *mlxsw_sp_port, return -EOPNOTSUPP; } +static void +mlxsw_sp_qdisc_bstats_per_priority_get(struct mlxsw_sp_port_xstats *xstats, + u8 prio_bitmap, u64 *tx_packets, + u64 *tx_bytes) +{ + int i; + + *tx_packets = 0; + *tx_bytes = 0; + for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) { + if (prio_bitmap & BIT(i)) { + *tx_packets += xstats->tx_packets[i]; + *tx_bytes += xstats->tx_bytes[i]; + } + } +} + static int mlxsw_sp_tclass_congestion_enable(struct mlxsw_sp_port *mlxsw_sp_port, int tclass_num, u32 min, u32 max, @@ -230,17 +288,16 @@ mlxsw_sp_setup_tc_qdisc_red_clean_stats(struct mlxsw_sp_port *mlxsw_sp_port, u8 tclass_num = mlxsw_sp_qdisc->tclass_num; struct mlxsw_sp_qdisc_stats *stats_base; struct mlxsw_sp_port_xstats *xstats; - struct rtnl_link_stats64 *stats; struct red_stats *red_base; xstats = &mlxsw_sp_port->periodic_hw_stats.xstats; - stats = &mlxsw_sp_port->periodic_hw_stats.stats; stats_base = &mlxsw_sp_qdisc->stats_base; red_base = &mlxsw_sp_qdisc->xstats_base.red; - stats_base->tx_packets = stats->tx_packets; - stats_base->tx_bytes = stats->tx_bytes; - + mlxsw_sp_qdisc_bstats_per_priority_get(xstats, + mlxsw_sp_qdisc->prio_bitmap, + &stats_base->tx_packets, + &stats_base->tx_bytes); red_base->prob_mark = xstats->ecn; red_base->prob_drop = xstats->wred_drop[tclass_num]; red_base->pdrop = xstats->tail_drop[tclass_num]; @@ -255,6 +312,12 @@ static int mlxsw_sp_qdisc_red_destroy(struct mlxsw_sp_port *mlxsw_sp_port, struct mlxsw_sp_qdisc *mlxsw_sp_qdisc) { + struct mlxsw_sp_qdisc *root_qdisc = mlxsw_sp_port->root_qdisc; + + if (root_qdisc != mlxsw_sp_qdisc) + root_qdisc->stats_base.backlog -= + mlxsw_sp_qdisc->stats_base.backlog; + return mlxsw_sp_tclass_congestion_disable(mlxsw_sp_port, mlxsw_sp_qdisc->tclass_num); } @@ -319,6 +382,7 @@ mlxsw_sp_qdisc_red_unoffload(struct mlxsw_sp_port *mlxsw_sp_port, backlog = mlxsw_sp_cells_bytes(mlxsw_sp_port->mlxsw_sp, mlxsw_sp_qdisc->stats_base.backlog); p->qstats->backlog -= backlog; + mlxsw_sp_qdisc->stats_base.backlog = 0; } static int @@ -357,14 +421,16 @@ mlxsw_sp_qdisc_get_red_stats(struct mlxsw_sp_port *mlxsw_sp_port, u8 tclass_num = mlxsw_sp_qdisc->tclass_num; struct mlxsw_sp_qdisc_stats *stats_base; struct mlxsw_sp_port_xstats *xstats; - struct rtnl_link_stats64 *stats; xstats = &mlxsw_sp_port->periodic_hw_stats.xstats; - stats = &mlxsw_sp_port->periodic_hw_stats.stats; stats_base = &mlxsw_sp_qdisc->stats_base; - tx_bytes = stats->tx_bytes - stats_base->tx_bytes; - tx_packets = stats->tx_packets - stats_base->tx_packets; + mlxsw_sp_qdisc_bstats_per_priority_get(xstats, + mlxsw_sp_qdisc->prio_bitmap, + &tx_packets, &tx_bytes); + tx_bytes = tx_bytes - stats_base->tx_bytes; + tx_packets = tx_packets - stats_base->tx_packets; + overlimits = xstats->wred_drop[tclass_num] + xstats->ecn - stats_base->overlimits; drops = xstats->wred_drop[tclass_num] + xstats->tail_drop[tclass_num] - @@ -406,11 +472,10 @@ int mlxsw_sp_setup_tc_red(struct mlxsw_sp_port *mlxsw_sp_port, { struct mlxsw_sp_qdisc *mlxsw_sp_qdisc; - if (p->parent != TC_H_ROOT) + mlxsw_sp_qdisc = mlxsw_sp_qdisc_find(mlxsw_sp_port, p->parent, false); + if (!mlxsw_sp_qdisc) return -EOPNOTSUPP; - mlxsw_sp_qdisc = mlxsw_sp_port->root_qdisc; - if (p->command == TC_RED_REPLACE) return mlxsw_sp_qdisc_replace(mlxsw_sp_port, p->handle, mlxsw_sp_qdisc, @@ -441,9 +506,13 @@ mlxsw_sp_qdisc_prio_destroy(struct mlxsw_sp_port *mlxsw_sp_port, { int i; - for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) + for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) { mlxsw_sp_port_prio_tc_set(mlxsw_sp_port, i, MLXSW_SP_PORT_DEFAULT_TCLASS); + mlxsw_sp_qdisc_destroy(mlxsw_sp_port, + &mlxsw_sp_port->tclass_qdiscs[i]); + mlxsw_sp_port->tclass_qdiscs[i].prio_bitmap = 0; + } return 0; } @@ -467,16 +536,41 @@ mlxsw_sp_qdisc_prio_replace(struct mlxsw_sp_port *mlxsw_sp_port, void *params) { struct tc_prio_qopt_offload_params *p = params; - int tclass, i; + struct mlxsw_sp_qdisc *child_qdisc; + int tclass, i, band, backlog; + u8 old_priomap; int err; - for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) { - tclass = MLXSW_SP_PRIO_BAND_TO_TCLASS(p->priomap[i]); - err = mlxsw_sp_port_prio_tc_set(mlxsw_sp_port, i, tclass); - if (err) - return err; + for (band = 0; band < p->bands; band++) { + tclass = MLXSW_SP_PRIO_BAND_TO_TCLASS(band); + child_qdisc = &mlxsw_sp_port->tclass_qdiscs[tclass]; + old_priomap = child_qdisc->prio_bitmap; + child_qdisc->prio_bitmap = 0; + for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) { + if (p->priomap[i] == band) { + child_qdisc->prio_bitmap |= BIT(i); + if (BIT(i) & old_priomap) + continue; + err = mlxsw_sp_port_prio_tc_set(mlxsw_sp_port, + i, tclass); + if (err) + return err; + } + } + if (old_priomap != child_qdisc->prio_bitmap && + child_qdisc->ops && child_qdisc->ops->clean_stats) { + backlog = child_qdisc->stats_base.backlog; + child_qdisc->ops->clean_stats(mlxsw_sp_port, + child_qdisc); + child_qdisc->stats_base.backlog = backlog; + } + } + for (; band < IEEE_8021QAZ_MAX_TCS; band++) { + tclass = MLXSW_SP_PRIO_BAND_TO_TCLASS(band); + child_qdisc = &mlxsw_sp_port->tclass_qdiscs[tclass]; + child_qdisc->prio_bitmap = 0; + mlxsw_sp_qdisc_destroy(mlxsw_sp_port, child_qdisc); } - return 0; } @@ -513,6 +607,7 @@ mlxsw_sp_qdisc_get_prio_stats(struct mlxsw_sp_port *mlxsw_sp_port, for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) { drops += xstats->tail_drop[i]; + drops += xstats->wred_drop[i]; backlog += xstats->backlog[i]; } drops = drops - stats_base->drops; @@ -548,8 +643,10 @@ mlxsw_sp_setup_tc_qdisc_prio_clean_stats(struct mlxsw_sp_port *mlxsw_sp_port, stats_base->tx_bytes = stats->tx_bytes; stats_base->drops = 0; - for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) + for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) { stats_base->drops += xstats->tail_drop[i]; + stats_base->drops += xstats->wred_drop[i]; + } mlxsw_sp_qdisc->stats_base.backlog = 0; } @@ -564,15 +661,48 @@ static struct mlxsw_sp_qdisc_ops mlxsw_sp_qdisc_ops_prio = { .clean_stats = mlxsw_sp_setup_tc_qdisc_prio_clean_stats, }; +/* Grafting is not supported in mlxsw. It will result in un-offloading of the + * grafted qdisc as well as the qdisc in the qdisc new location. + * (However, if the graft is to the location where the qdisc is already at, it + * will be ignored completely and won't cause un-offloading). + */ +static int +mlxsw_sp_qdisc_prio_graft(struct mlxsw_sp_port *mlxsw_sp_port, + struct mlxsw_sp_qdisc *mlxsw_sp_qdisc, + struct tc_prio_qopt_offload_graft_params *p) +{ + int tclass_num = MLXSW_SP_PRIO_BAND_TO_TCLASS(p->band); + struct mlxsw_sp_qdisc *old_qdisc; + + /* Check if the grafted qdisc is already in its "new" location. If so - + * nothing needs to be done. + */ + if (p->band < IEEE_8021QAZ_MAX_TCS && + mlxsw_sp_port->tclass_qdiscs[tclass_num].handle == p->child_handle) + return 0; + + /* See if the grafted qdisc is already offloaded on any tclass. If so, + * unoffload it. + */ + old_qdisc = mlxsw_sp_qdisc_find_by_handle(mlxsw_sp_port, + p->child_handle); + if (old_qdisc) + mlxsw_sp_qdisc_destroy(mlxsw_sp_port, old_qdisc); + + mlxsw_sp_qdisc_destroy(mlxsw_sp_port, + &mlxsw_sp_port->tclass_qdiscs[tclass_num]); + return -EOPNOTSUPP; +} + int mlxsw_sp_setup_tc_prio(struct mlxsw_sp_port *mlxsw_sp_port, struct tc_prio_qopt_offload *p) { struct mlxsw_sp_qdisc *mlxsw_sp_qdisc; - if (p->parent != TC_H_ROOT) + mlxsw_sp_qdisc = mlxsw_sp_qdisc_find(mlxsw_sp_port, p->parent, true); + if (!mlxsw_sp_qdisc) return -EOPNOTSUPP; - mlxsw_sp_qdisc = mlxsw_sp_port->root_qdisc; if (p->command == TC_PRIO_REPLACE) return mlxsw_sp_qdisc_replace(mlxsw_sp_port, p->handle, mlxsw_sp_qdisc, @@ -589,6 +719,9 @@ int mlxsw_sp_setup_tc_prio(struct mlxsw_sp_port *mlxsw_sp_port, case TC_PRIO_STATS: return mlxsw_sp_qdisc_get_stats(mlxsw_sp_port, mlxsw_sp_qdisc, &p->stats); + case TC_PRIO_GRAFT: + return mlxsw_sp_qdisc_prio_graft(mlxsw_sp_port, mlxsw_sp_qdisc, + &p->graft_params); default: return -EOPNOTSUPP; } @@ -596,17 +729,36 @@ int mlxsw_sp_setup_tc_prio(struct mlxsw_sp_port *mlxsw_sp_port, int mlxsw_sp_tc_qdisc_init(struct mlxsw_sp_port *mlxsw_sp_port) { - mlxsw_sp_port->root_qdisc = kzalloc(sizeof(*mlxsw_sp_port->root_qdisc), - GFP_KERNEL); - if (!mlxsw_sp_port->root_qdisc) - return -ENOMEM; + struct mlxsw_sp_qdisc *mlxsw_sp_qdisc; + int i; + mlxsw_sp_qdisc = kzalloc(sizeof(*mlxsw_sp_qdisc), GFP_KERNEL); + if (!mlxsw_sp_qdisc) + goto err_root_qdisc_init; + + mlxsw_sp_port->root_qdisc = mlxsw_sp_qdisc; + mlxsw_sp_port->root_qdisc->prio_bitmap = 0xff; mlxsw_sp_port->root_qdisc->tclass_num = MLXSW_SP_PORT_DEFAULT_TCLASS; + mlxsw_sp_qdisc = kzalloc(sizeof(*mlxsw_sp_qdisc) * IEEE_8021QAZ_MAX_TCS, + GFP_KERNEL); + if (!mlxsw_sp_qdisc) + goto err_tclass_qdiscs_init; + + mlxsw_sp_port->tclass_qdiscs = mlxsw_sp_qdisc; + for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) + mlxsw_sp_port->tclass_qdiscs[i].tclass_num = i; + return 0; + +err_tclass_qdiscs_init: + kfree(mlxsw_sp_port->root_qdisc); +err_root_qdisc_init: + return -ENOMEM; } void mlxsw_sp_tc_qdisc_fini(struct mlxsw_sp_port *mlxsw_sp_port) { + kfree(mlxsw_sp_port->tclass_qdiscs); kfree(mlxsw_sp_port->root_qdisc); } diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index f7948e983637..a8a578610a7b 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -1,10 +1,10 @@ /* * drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c - * Copyright (c) 2016-2017 Mellanox Technologies. All rights reserved. + * Copyright (c) 2016-2018 Mellanox Technologies. All rights reserved. * Copyright (c) 2016 Jiri Pirko <jiri@mellanox.com> * Copyright (c) 2016 Ido Schimmel <idosch@mellanox.com> * Copyright (c) 2016 Yotam Gigi <yotamg@mellanox.com> - * Copyright (c) 2017 Petr Machata <petrm@mellanox.com> + * Copyright (c) 2017-2018 Petr Machata <petrm@mellanox.com> * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions are met: @@ -70,6 +70,7 @@ #include "spectrum_mr.h" #include "spectrum_mr_tcam.h" #include "spectrum_router.h" +#include "spectrum_span.h" struct mlxsw_sp_fib; struct mlxsw_sp_vr; @@ -796,7 +797,7 @@ static struct mlxsw_sp_vr *mlxsw_sp_vr_create(struct mlxsw_sp *mlxsw_sp, vr = mlxsw_sp_vr_find_unused(mlxsw_sp); if (!vr) { - NL_SET_ERR_MSG(extack, "spectrum: Exceeded number of supported virtual routers"); + NL_SET_ERR_MSG_MOD(extack, "Exceeded number of supported virtual routers"); return ERR_PTR(-EBUSY); } fib4 = mlxsw_sp_fib_create(mlxsw_sp, vr, MLXSW_SP_L3_PROTO_IPV4); @@ -1024,9 +1025,11 @@ mlxsw_sp_ipip_entry_alloc(struct mlxsw_sp *mlxsw_sp, enum mlxsw_sp_ipip_type ipipt, struct net_device *ol_dev) { + const struct mlxsw_sp_ipip_ops *ipip_ops; struct mlxsw_sp_ipip_entry *ipip_entry; struct mlxsw_sp_ipip_entry *ret = NULL; + ipip_ops = mlxsw_sp->router->ipip_ops_arr[ipipt]; ipip_entry = kzalloc(sizeof(*ipip_entry), GFP_KERNEL); if (!ipip_entry) return ERR_PTR(-ENOMEM); @@ -1040,7 +1043,15 @@ mlxsw_sp_ipip_entry_alloc(struct mlxsw_sp *mlxsw_sp, ipip_entry->ipipt = ipipt; ipip_entry->ol_dev = ol_dev; - ipip_entry->parms = mlxsw_sp_ipip_netdev_parms(ol_dev); + + switch (ipip_ops->ul_proto) { + case MLXSW_SP_L3_PROTO_IPV4: + ipip_entry->parms4 = mlxsw_sp_ipip_netdev_parms4(ol_dev); + break; + case MLXSW_SP_L3_PROTO_IPV6: + WARN_ON(1); + break; + } return ipip_entry; @@ -2320,6 +2331,8 @@ static void mlxsw_sp_router_neigh_event_work(struct work_struct *work) read_unlock_bh(&n->lock); rtnl_lock(); + mlxsw_sp_span_respin(mlxsw_sp); + entry_connected = nud_state & NUD_VALID && !dead; neigh_entry = mlxsw_sp_neigh_entry_lookup(mlxsw_sp, n); if (!entry_connected && !neigh_entry) @@ -2417,7 +2430,8 @@ static int mlxsw_sp_router_netevent_event(struct notifier_block *nb, mlxsw_core_schedule_work(&net_work->work); mlxsw_sp_port_dev_put(mlxsw_sp_port); break; - case NETEVENT_MULTIPATH_HASH_UPDATE: + case NETEVENT_IPV4_MPATH_HASH_UPDATE: + case NETEVENT_IPV6_MPATH_HASH_UPDATE: net = ptr; if (!net_eq(net, &init_net)) @@ -5579,6 +5593,8 @@ static void mlxsw_sp_router_fib4_event_work(struct work_struct *work) /* Protect internal structures from changes */ rtnl_lock(); + mlxsw_sp_span_respin(mlxsw_sp); + switch (fib_work->event) { case FIB_EVENT_ENTRY_REPLACE: /* fall through */ case FIB_EVENT_ENTRY_APPEND: /* fall through */ @@ -5621,6 +5637,8 @@ static void mlxsw_sp_router_fib6_event_work(struct work_struct *work) int err; rtnl_lock(); + mlxsw_sp_span_respin(mlxsw_sp); + switch (fib_work->event) { case FIB_EVENT_ENTRY_REPLACE: /* fall through */ case FIB_EVENT_ENTRY_ADD: @@ -5793,7 +5811,7 @@ static int mlxsw_sp_router_fib_rule_event(unsigned long event, } if (err < 0) - NL_SET_ERR_MSG(extack, "spectrum: FIB rules not supported. Aborting offload"); + NL_SET_ERR_MSG_MOD(extack, "FIB rules not supported. Aborting offload"); return err; } @@ -6032,7 +6050,7 @@ mlxsw_sp_rif_create(struct mlxsw_sp *mlxsw_sp, err = mlxsw_sp_rif_index_alloc(mlxsw_sp, &rif_index); if (err) { - NL_SET_ERR_MSG(extack, "spectrum: Exceeded number of supported router interfaces"); + NL_SET_ERR_MSG_MOD(extack, "Exceeded number of supported router interfaces"); goto err_rif_index_alloc; } @@ -7013,13 +7031,25 @@ static void mlxsw_sp_mp4_hash_init(char *recr2_pl) static void mlxsw_sp_mp6_hash_init(char *recr2_pl) { + bool only_l3 = !init_net.ipv6.sysctl.multipath_hash_policy; + mlxsw_sp_mp_hash_header_set(recr2_pl, MLXSW_REG_RECR2_IPV6_EN_NOT_TCP_NOT_UDP); mlxsw_sp_mp_hash_header_set(recr2_pl, MLXSW_REG_RECR2_IPV6_EN_TCP_UDP); mlxsw_reg_recr2_ipv6_sip_enable(recr2_pl); mlxsw_reg_recr2_ipv6_dip_enable(recr2_pl); - mlxsw_sp_mp_hash_field_set(recr2_pl, MLXSW_REG_RECR2_IPV6_FLOW_LABEL); mlxsw_sp_mp_hash_field_set(recr2_pl, MLXSW_REG_RECR2_IPV6_NEXT_HEADER); + if (only_l3) { + mlxsw_sp_mp_hash_field_set(recr2_pl, + MLXSW_REG_RECR2_IPV6_FLOW_LABEL); + } else { + mlxsw_sp_mp_hash_header_set(recr2_pl, + MLXSW_REG_RECR2_TCP_UDP_EN_IPV6); + mlxsw_sp_mp_hash_field_set(recr2_pl, + MLXSW_REG_RECR2_TCP_UDP_SPORT); + mlxsw_sp_mp_hash_field_set(recr2_pl, + MLXSW_REG_RECR2_TCP_UDP_DPORT); + } } static int mlxsw_sp_mp_hash_init(struct mlxsw_sp *mlxsw_sp) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c new file mode 100644 index 000000000000..f537e1de11d9 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c @@ -0,0 +1,796 @@ +/* + * drivers/net/ethernet/mellanox/mlxsw/mlxsw_span.c + * Copyright (c) 2018 Mellanox Technologies. All rights reserved. + * Copyright (c) 2018 Petr Machata <petrm@mellanox.com> + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the names of the copyright holders nor the names of its + * contributors may be used to endorse or promote products derived from + * this software without specific prior written permission. + * + * Alternatively, this software may be distributed under the terms of the + * GNU General Public License ("GPL") version 2 as published by the Free + * Software Foundation. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN + * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE + * POSSIBILITY OF SUCH DAMAGE. + */ + +#include <linux/list.h> +#include <net/arp.h> +#include <net/gre.h> +#include <net/ndisc.h> +#include <net/ip6_tunnel.h> + +#include "spectrum.h" +#include "spectrum_span.h" +#include "spectrum_ipip.h" + +int mlxsw_sp_span_init(struct mlxsw_sp *mlxsw_sp) +{ + int i; + + if (!MLXSW_CORE_RES_VALID(mlxsw_sp->core, MAX_SPAN)) + return -EIO; + + mlxsw_sp->span.entries_count = MLXSW_CORE_RES_GET(mlxsw_sp->core, + MAX_SPAN); + mlxsw_sp->span.entries = kcalloc(mlxsw_sp->span.entries_count, + sizeof(struct mlxsw_sp_span_entry), + GFP_KERNEL); + if (!mlxsw_sp->span.entries) + return -ENOMEM; + + for (i = 0; i < mlxsw_sp->span.entries_count; i++) { + struct mlxsw_sp_span_entry *curr = &mlxsw_sp->span.entries[i]; + + INIT_LIST_HEAD(&curr->bound_ports_list); + curr->id = i; + } + + return 0; +} + +void mlxsw_sp_span_fini(struct mlxsw_sp *mlxsw_sp) +{ + int i; + + for (i = 0; i < mlxsw_sp->span.entries_count; i++) { + struct mlxsw_sp_span_entry *curr = &mlxsw_sp->span.entries[i]; + + WARN_ON_ONCE(!list_empty(&curr->bound_ports_list)); + } + kfree(mlxsw_sp->span.entries); +} + +static int +mlxsw_sp_span_entry_phys_parms(const struct net_device *to_dev, + struct mlxsw_sp_span_parms *sparmsp) +{ + sparmsp->dest_port = netdev_priv(to_dev); + return 0; +} + +static int +mlxsw_sp_span_entry_phys_configure(struct mlxsw_sp_span_entry *span_entry, + struct mlxsw_sp_span_parms sparms) +{ + struct mlxsw_sp_port *dest_port = sparms.dest_port; + struct mlxsw_sp *mlxsw_sp = dest_port->mlxsw_sp; + u8 local_port = dest_port->local_port; + char mpat_pl[MLXSW_REG_MPAT_LEN]; + int pa_id = span_entry->id; + + /* Create a new port analayzer entry for local_port. */ + mlxsw_reg_mpat_pack(mpat_pl, pa_id, local_port, true, + MLXSW_REG_MPAT_SPAN_TYPE_LOCAL_ETH); + + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(mpat), mpat_pl); +} + +static void +mlxsw_sp_span_entry_deconfigure_common(struct mlxsw_sp_span_entry *span_entry, + enum mlxsw_reg_mpat_span_type span_type) +{ + struct mlxsw_sp_port *dest_port = span_entry->parms.dest_port; + struct mlxsw_sp *mlxsw_sp = dest_port->mlxsw_sp; + u8 local_port = dest_port->local_port; + char mpat_pl[MLXSW_REG_MPAT_LEN]; + int pa_id = span_entry->id; + + mlxsw_reg_mpat_pack(mpat_pl, pa_id, local_port, false, span_type); + mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(mpat), mpat_pl); +} + +static void +mlxsw_sp_span_entry_phys_deconfigure(struct mlxsw_sp_span_entry *span_entry) +{ + mlxsw_sp_span_entry_deconfigure_common(span_entry, + MLXSW_REG_MPAT_SPAN_TYPE_LOCAL_ETH); +} + +static const +struct mlxsw_sp_span_entry_ops mlxsw_sp_span_entry_ops_phys = { + .can_handle = mlxsw_sp_port_dev_check, + .parms = mlxsw_sp_span_entry_phys_parms, + .configure = mlxsw_sp_span_entry_phys_configure, + .deconfigure = mlxsw_sp_span_entry_phys_deconfigure, +}; + +static struct net_device * +mlxsw_sp_span_gretap4_route(const struct net_device *to_dev, + __be32 *saddrp, __be32 *daddrp) +{ + struct ip_tunnel *tun = netdev_priv(to_dev); + struct net_device *dev = NULL; + struct ip_tunnel_parm parms; + struct rtable *rt = NULL; + struct flowi4 fl4; + + /* We assume "dev" stays valid after rt is put. */ + ASSERT_RTNL(); + + parms = mlxsw_sp_ipip_netdev_parms4(to_dev); + ip_tunnel_init_flow(&fl4, parms.iph.protocol, *daddrp, *saddrp, + 0, 0, parms.link, tun->fwmark); + + rt = ip_route_output_key(tun->net, &fl4); + if (IS_ERR(rt)) + return NULL; + + if (rt->rt_type != RTN_UNICAST) + goto out; + + dev = rt->dst.dev; + *saddrp = fl4.saddr; + *daddrp = rt->rt_gateway; + +out: + ip_rt_put(rt); + return dev; +} + +static int mlxsw_sp_span_dmac(struct neigh_table *tbl, + const void *pkey, + struct net_device *l3edev, + unsigned char dmac[ETH_ALEN]) +{ + struct neighbour *neigh = neigh_lookup(tbl, pkey, l3edev); + int err = 0; + + if (!neigh) { + neigh = neigh_create(tbl, pkey, l3edev); + if (IS_ERR(neigh)) + return PTR_ERR(neigh); + } + + neigh_event_send(neigh, NULL); + + read_lock_bh(&neigh->lock); + if ((neigh->nud_state & NUD_VALID) && !neigh->dead) + memcpy(dmac, neigh->ha, ETH_ALEN); + else + err = -ENOENT; + read_unlock_bh(&neigh->lock); + + neigh_release(neigh); + return err; +} + +static int +mlxsw_sp_span_entry_unoffloadable(struct mlxsw_sp_span_parms *sparmsp) +{ + sparmsp->dest_port = NULL; + return 0; +} + +static int +mlxsw_sp_span_entry_tunnel_parms_common(struct net_device *l3edev, + union mlxsw_sp_l3addr saddr, + union mlxsw_sp_l3addr daddr, + union mlxsw_sp_l3addr gw, + __u8 ttl, + struct neigh_table *tbl, + struct mlxsw_sp_span_parms *sparmsp) +{ + unsigned char dmac[ETH_ALEN]; + + if (mlxsw_sp_l3addr_is_zero(gw)) + gw = daddr; + + if (!l3edev || !mlxsw_sp_port_dev_check(l3edev) || + mlxsw_sp_span_dmac(tbl, &gw, l3edev, dmac)) + return mlxsw_sp_span_entry_unoffloadable(sparmsp); + + sparmsp->dest_port = netdev_priv(l3edev); + sparmsp->ttl = ttl; + memcpy(sparmsp->dmac, dmac, ETH_ALEN); + memcpy(sparmsp->smac, l3edev->dev_addr, ETH_ALEN); + sparmsp->saddr = saddr; + sparmsp->daddr = daddr; + return 0; +} + +static int +mlxsw_sp_span_entry_gretap4_parms(const struct net_device *to_dev, + struct mlxsw_sp_span_parms *sparmsp) +{ + struct ip_tunnel_parm tparm = mlxsw_sp_ipip_netdev_parms4(to_dev); + union mlxsw_sp_l3addr saddr = { .addr4 = tparm.iph.saddr }; + union mlxsw_sp_l3addr daddr = { .addr4 = tparm.iph.daddr }; + bool inherit_tos = tparm.iph.tos & 0x1; + bool inherit_ttl = !tparm.iph.ttl; + union mlxsw_sp_l3addr gw = daddr; + struct net_device *l3edev; + + if (!(to_dev->flags & IFF_UP) || + /* Reject tunnels with GRE keys, checksums, etc. */ + tparm.i_flags || tparm.o_flags || + /* Require a fixed TTL and a TOS copied from the mirrored packet. */ + inherit_ttl || !inherit_tos || + /* A destination address may not be "any". */ + mlxsw_sp_l3addr_is_zero(daddr)) + return mlxsw_sp_span_entry_unoffloadable(sparmsp); + + l3edev = mlxsw_sp_span_gretap4_route(to_dev, &saddr.addr4, &gw.addr4); + return mlxsw_sp_span_entry_tunnel_parms_common(l3edev, saddr, daddr, gw, + tparm.iph.ttl, + &arp_tbl, sparmsp); +} + +static int +mlxsw_sp_span_entry_gretap4_configure(struct mlxsw_sp_span_entry *span_entry, + struct mlxsw_sp_span_parms sparms) +{ + struct mlxsw_sp_port *dest_port = sparms.dest_port; + struct mlxsw_sp *mlxsw_sp = dest_port->mlxsw_sp; + u8 local_port = dest_port->local_port; + char mpat_pl[MLXSW_REG_MPAT_LEN]; + int pa_id = span_entry->id; + + /* Create a new port analayzer entry for local_port. */ + mlxsw_reg_mpat_pack(mpat_pl, pa_id, local_port, true, + MLXSW_REG_MPAT_SPAN_TYPE_REMOTE_ETH_L3); + mlxsw_reg_mpat_eth_rspan_l2_pack(mpat_pl, + MLXSW_REG_MPAT_ETH_RSPAN_VERSION_NO_HEADER, + sparms.dmac, false); + mlxsw_reg_mpat_eth_rspan_l3_ipv4_pack(mpat_pl, + sparms.ttl, sparms.smac, + be32_to_cpu(sparms.saddr.addr4), + be32_to_cpu(sparms.daddr.addr4)); + + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(mpat), mpat_pl); +} + +static void +mlxsw_sp_span_entry_gretap4_deconfigure(struct mlxsw_sp_span_entry *span_entry) +{ + mlxsw_sp_span_entry_deconfigure_common(span_entry, + MLXSW_REG_MPAT_SPAN_TYPE_REMOTE_ETH_L3); +} + +static const struct mlxsw_sp_span_entry_ops mlxsw_sp_span_entry_ops_gretap4 = { + .can_handle = is_gretap_dev, + .parms = mlxsw_sp_span_entry_gretap4_parms, + .configure = mlxsw_sp_span_entry_gretap4_configure, + .deconfigure = mlxsw_sp_span_entry_gretap4_deconfigure, +}; + +static struct net_device * +mlxsw_sp_span_gretap6_route(const struct net_device *to_dev, + struct in6_addr *saddrp, + struct in6_addr *daddrp) +{ + struct ip6_tnl *t = netdev_priv(to_dev); + struct flowi6 fl6 = t->fl.u.ip6; + struct net_device *dev = NULL; + struct dst_entry *dst; + struct rt6_info *rt6; + + /* We assume "dev" stays valid after dst is released. */ + ASSERT_RTNL(); + + fl6.flowi6_mark = t->parms.fwmark; + if (!ip6_tnl_xmit_ctl(t, &fl6.saddr, &fl6.daddr)) + return NULL; + + dst = ip6_route_output(t->net, NULL, &fl6); + if (!dst || dst->error) + goto out; + + rt6 = container_of(dst, struct rt6_info, dst); + + dev = dst->dev; + *saddrp = fl6.saddr; + *daddrp = rt6->rt6i_gateway; + +out: + dst_release(dst); + return dev; +} + +static int +mlxsw_sp_span_entry_gretap6_parms(const struct net_device *to_dev, + struct mlxsw_sp_span_parms *sparmsp) +{ + struct __ip6_tnl_parm tparm = mlxsw_sp_ipip_netdev_parms6(to_dev); + bool inherit_tos = tparm.flags & IP6_TNL_F_USE_ORIG_TCLASS; + union mlxsw_sp_l3addr saddr = { .addr6 = tparm.laddr }; + union mlxsw_sp_l3addr daddr = { .addr6 = tparm.raddr }; + bool inherit_ttl = !tparm.hop_limit; + union mlxsw_sp_l3addr gw = daddr; + struct net_device *l3edev; + + if (!(to_dev->flags & IFF_UP) || + /* Reject tunnels with GRE keys, checksums, etc. */ + tparm.i_flags || tparm.o_flags || + /* Require a fixed TTL and a TOS copied from the mirrored packet. */ + inherit_ttl || !inherit_tos || + /* A destination address may not be "any". */ + mlxsw_sp_l3addr_is_zero(daddr)) + return mlxsw_sp_span_entry_unoffloadable(sparmsp); + + l3edev = mlxsw_sp_span_gretap6_route(to_dev, &saddr.addr6, &gw.addr6); + return mlxsw_sp_span_entry_tunnel_parms_common(l3edev, saddr, daddr, gw, + tparm.hop_limit, + &nd_tbl, sparmsp); +} + +static int +mlxsw_sp_span_entry_gretap6_configure(struct mlxsw_sp_span_entry *span_entry, + struct mlxsw_sp_span_parms sparms) +{ + struct mlxsw_sp_port *dest_port = sparms.dest_port; + struct mlxsw_sp *mlxsw_sp = dest_port->mlxsw_sp; + u8 local_port = dest_port->local_port; + char mpat_pl[MLXSW_REG_MPAT_LEN]; + int pa_id = span_entry->id; + + /* Create a new port analayzer entry for local_port. */ + mlxsw_reg_mpat_pack(mpat_pl, pa_id, local_port, true, + MLXSW_REG_MPAT_SPAN_TYPE_REMOTE_ETH_L3); + mlxsw_reg_mpat_eth_rspan_l2_pack(mpat_pl, + MLXSW_REG_MPAT_ETH_RSPAN_VERSION_NO_HEADER, + sparms.dmac, false); + mlxsw_reg_mpat_eth_rspan_l3_ipv6_pack(mpat_pl, sparms.ttl, sparms.smac, + sparms.saddr.addr6, + sparms.daddr.addr6); + + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(mpat), mpat_pl); +} + +static void +mlxsw_sp_span_entry_gretap6_deconfigure(struct mlxsw_sp_span_entry *span_entry) +{ + mlxsw_sp_span_entry_deconfigure_common(span_entry, + MLXSW_REG_MPAT_SPAN_TYPE_REMOTE_ETH_L3); +} + +static const +struct mlxsw_sp_span_entry_ops mlxsw_sp_span_entry_ops_gretap6 = { + .can_handle = is_ip6gretap_dev, + .parms = mlxsw_sp_span_entry_gretap6_parms, + .configure = mlxsw_sp_span_entry_gretap6_configure, + .deconfigure = mlxsw_sp_span_entry_gretap6_deconfigure, +}; + +static const +struct mlxsw_sp_span_entry_ops *const mlxsw_sp_span_entry_types[] = { + &mlxsw_sp_span_entry_ops_phys, + &mlxsw_sp_span_entry_ops_gretap4, + &mlxsw_sp_span_entry_ops_gretap6, +}; + +static int +mlxsw_sp_span_entry_nop_parms(const struct net_device *to_dev, + struct mlxsw_sp_span_parms *sparmsp) +{ + return mlxsw_sp_span_entry_unoffloadable(sparmsp); +} + +static int +mlxsw_sp_span_entry_nop_configure(struct mlxsw_sp_span_entry *span_entry, + struct mlxsw_sp_span_parms sparms) +{ + return 0; +} + +static void +mlxsw_sp_span_entry_nop_deconfigure(struct mlxsw_sp_span_entry *span_entry) +{ +} + +static const struct mlxsw_sp_span_entry_ops mlxsw_sp_span_entry_ops_nop = { + .parms = mlxsw_sp_span_entry_nop_parms, + .configure = mlxsw_sp_span_entry_nop_configure, + .deconfigure = mlxsw_sp_span_entry_nop_deconfigure, +}; + +static void +mlxsw_sp_span_entry_configure(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_span_entry *span_entry, + struct mlxsw_sp_span_parms sparms) +{ + if (sparms.dest_port) { + if (sparms.dest_port->mlxsw_sp != mlxsw_sp) { + netdev_err(span_entry->to_dev, "Cannot mirror to %s, which belongs to a different mlxsw instance", + sparms.dest_port->dev->name); + sparms.dest_port = NULL; + } else if (span_entry->ops->configure(span_entry, sparms)) { + netdev_err(span_entry->to_dev, "Failed to offload mirror to %s", + sparms.dest_port->dev->name); + sparms.dest_port = NULL; + } + } + + span_entry->parms = sparms; +} + +static void +mlxsw_sp_span_entry_deconfigure(struct mlxsw_sp_span_entry *span_entry) +{ + if (span_entry->parms.dest_port) + span_entry->ops->deconfigure(span_entry); +} + +static struct mlxsw_sp_span_entry * +mlxsw_sp_span_entry_create(struct mlxsw_sp *mlxsw_sp, + const struct net_device *to_dev, + const struct mlxsw_sp_span_entry_ops *ops, + struct mlxsw_sp_span_parms sparms) +{ + struct mlxsw_sp_span_entry *span_entry = NULL; + int i; + + /* find a free entry to use */ + for (i = 0; i < mlxsw_sp->span.entries_count; i++) { + if (!mlxsw_sp->span.entries[i].ref_count) { + span_entry = &mlxsw_sp->span.entries[i]; + break; + } + } + if (!span_entry) + return NULL; + + span_entry->ops = ops; + span_entry->ref_count = 1; + span_entry->to_dev = to_dev; + mlxsw_sp_span_entry_configure(mlxsw_sp, span_entry, sparms); + + return span_entry; +} + +static void mlxsw_sp_span_entry_destroy(struct mlxsw_sp_span_entry *span_entry) +{ + mlxsw_sp_span_entry_deconfigure(span_entry); +} + +struct mlxsw_sp_span_entry * +mlxsw_sp_span_entry_find_by_port(struct mlxsw_sp *mlxsw_sp, + const struct net_device *to_dev) +{ + int i; + + for (i = 0; i < mlxsw_sp->span.entries_count; i++) { + struct mlxsw_sp_span_entry *curr = &mlxsw_sp->span.entries[i]; + + if (curr->ref_count && curr->to_dev == to_dev) + return curr; + } + return NULL; +} + +void mlxsw_sp_span_entry_invalidate(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_span_entry *span_entry) +{ + mlxsw_sp_span_entry_deconfigure(span_entry); + span_entry->ops = &mlxsw_sp_span_entry_ops_nop; +} + +static struct mlxsw_sp_span_entry * +mlxsw_sp_span_entry_find_by_id(struct mlxsw_sp *mlxsw_sp, int span_id) +{ + int i; + + for (i = 0; i < mlxsw_sp->span.entries_count; i++) { + struct mlxsw_sp_span_entry *curr = &mlxsw_sp->span.entries[i]; + + if (curr->ref_count && curr->id == span_id) + return curr; + } + return NULL; +} + +static struct mlxsw_sp_span_entry * +mlxsw_sp_span_entry_get(struct mlxsw_sp *mlxsw_sp, + const struct net_device *to_dev, + const struct mlxsw_sp_span_entry_ops *ops, + struct mlxsw_sp_span_parms sparms) +{ + struct mlxsw_sp_span_entry *span_entry; + + span_entry = mlxsw_sp_span_entry_find_by_port(mlxsw_sp, to_dev); + if (span_entry) { + /* Already exists, just take a reference */ + span_entry->ref_count++; + return span_entry; + } + + return mlxsw_sp_span_entry_create(mlxsw_sp, to_dev, ops, sparms); +} + +static int mlxsw_sp_span_entry_put(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_span_entry *span_entry) +{ + WARN_ON(!span_entry->ref_count); + if (--span_entry->ref_count == 0) + mlxsw_sp_span_entry_destroy(span_entry); + return 0; +} + +static bool mlxsw_sp_span_is_egress_mirror(struct mlxsw_sp_port *port) +{ + struct mlxsw_sp *mlxsw_sp = port->mlxsw_sp; + struct mlxsw_sp_span_inspected_port *p; + int i; + + for (i = 0; i < mlxsw_sp->span.entries_count; i++) { + struct mlxsw_sp_span_entry *curr = &mlxsw_sp->span.entries[i]; + + list_for_each_entry(p, &curr->bound_ports_list, list) + if (p->local_port == port->local_port && + p->type == MLXSW_SP_SPAN_EGRESS) + return true; + } + + return false; +} + +static int mlxsw_sp_span_mtu_to_buffsize(const struct mlxsw_sp *mlxsw_sp, + int mtu) +{ + return mlxsw_sp_bytes_cells(mlxsw_sp, mtu * 5 / 2) + 1; +} + +int mlxsw_sp_span_port_mtu_update(struct mlxsw_sp_port *port, u16 mtu) +{ + struct mlxsw_sp *mlxsw_sp = port->mlxsw_sp; + char sbib_pl[MLXSW_REG_SBIB_LEN]; + int err; + + /* If port is egress mirrored, the shared buffer size should be + * updated according to the mtu value + */ + if (mlxsw_sp_span_is_egress_mirror(port)) { + u32 buffsize = mlxsw_sp_span_mtu_to_buffsize(mlxsw_sp, mtu); + + mlxsw_reg_sbib_pack(sbib_pl, port->local_port, buffsize); + err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sbib), sbib_pl); + if (err) { + netdev_err(port->dev, "Could not update shared buffer for mirroring\n"); + return err; + } + } + + return 0; +} + +static struct mlxsw_sp_span_inspected_port * +mlxsw_sp_span_entry_bound_port_find(struct mlxsw_sp_port *port, + struct mlxsw_sp_span_entry *span_entry) +{ + struct mlxsw_sp_span_inspected_port *p; + + list_for_each_entry(p, &span_entry->bound_ports_list, list) + if (port->local_port == p->local_port) + return p; + return NULL; +} + +static int +mlxsw_sp_span_inspected_port_bind(struct mlxsw_sp_port *port, + struct mlxsw_sp_span_entry *span_entry, + enum mlxsw_sp_span_type type, + bool bind) +{ + struct mlxsw_sp *mlxsw_sp = port->mlxsw_sp; + char mpar_pl[MLXSW_REG_MPAR_LEN]; + int pa_id = span_entry->id; + + /* bind the port to the SPAN entry */ + mlxsw_reg_mpar_pack(mpar_pl, port->local_port, + (enum mlxsw_reg_mpar_i_e)type, bind, pa_id); + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(mpar), mpar_pl); +} + +static int +mlxsw_sp_span_inspected_port_add(struct mlxsw_sp_port *port, + struct mlxsw_sp_span_entry *span_entry, + enum mlxsw_sp_span_type type, + bool bind) +{ + struct mlxsw_sp_span_inspected_port *inspected_port; + struct mlxsw_sp *mlxsw_sp = port->mlxsw_sp; + char sbib_pl[MLXSW_REG_SBIB_LEN]; + int err; + + /* if it is an egress SPAN, bind a shared buffer to it */ + if (type == MLXSW_SP_SPAN_EGRESS) { + u32 buffsize = mlxsw_sp_span_mtu_to_buffsize(mlxsw_sp, + port->dev->mtu); + + mlxsw_reg_sbib_pack(sbib_pl, port->local_port, buffsize); + err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sbib), sbib_pl); + if (err) { + netdev_err(port->dev, "Could not create shared buffer for mirroring\n"); + return err; + } + } + + if (bind) { + err = mlxsw_sp_span_inspected_port_bind(port, span_entry, type, + true); + if (err) + goto err_port_bind; + } + + inspected_port = kzalloc(sizeof(*inspected_port), GFP_KERNEL); + if (!inspected_port) { + err = -ENOMEM; + goto err_inspected_port_alloc; + } + inspected_port->local_port = port->local_port; + inspected_port->type = type; + list_add_tail(&inspected_port->list, &span_entry->bound_ports_list); + + return 0; + +err_inspected_port_alloc: + if (bind) + mlxsw_sp_span_inspected_port_bind(port, span_entry, type, + false); +err_port_bind: + if (type == MLXSW_SP_SPAN_EGRESS) { + mlxsw_reg_sbib_pack(sbib_pl, port->local_port, 0); + mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sbib), sbib_pl); + } + return err; +} + +static void +mlxsw_sp_span_inspected_port_del(struct mlxsw_sp_port *port, + struct mlxsw_sp_span_entry *span_entry, + enum mlxsw_sp_span_type type, + bool bind) +{ + struct mlxsw_sp_span_inspected_port *inspected_port; + struct mlxsw_sp *mlxsw_sp = port->mlxsw_sp; + char sbib_pl[MLXSW_REG_SBIB_LEN]; + + inspected_port = mlxsw_sp_span_entry_bound_port_find(port, span_entry); + if (!inspected_port) + return; + + if (bind) + mlxsw_sp_span_inspected_port_bind(port, span_entry, type, + false); + /* remove the SBIB buffer if it was egress SPAN */ + if (type == MLXSW_SP_SPAN_EGRESS) { + mlxsw_reg_sbib_pack(sbib_pl, port->local_port, 0); + mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sbib), sbib_pl); + } + + mlxsw_sp_span_entry_put(mlxsw_sp, span_entry); + + list_del(&inspected_port->list); + kfree(inspected_port); +} + +static const struct mlxsw_sp_span_entry_ops * +mlxsw_sp_span_entry_ops(struct mlxsw_sp *mlxsw_sp, + const struct net_device *to_dev) +{ + size_t i; + + for (i = 0; i < ARRAY_SIZE(mlxsw_sp_span_entry_types); ++i) + if (mlxsw_sp_span_entry_types[i]->can_handle(to_dev)) + return mlxsw_sp_span_entry_types[i]; + + return NULL; +} + +int mlxsw_sp_span_mirror_add(struct mlxsw_sp_port *from, + const struct net_device *to_dev, + enum mlxsw_sp_span_type type, bool bind, + int *p_span_id) +{ + struct mlxsw_sp *mlxsw_sp = from->mlxsw_sp; + const struct mlxsw_sp_span_entry_ops *ops; + struct mlxsw_sp_span_parms sparms = {0}; + struct mlxsw_sp_span_entry *span_entry; + int err; + + ops = mlxsw_sp_span_entry_ops(mlxsw_sp, to_dev); + if (!ops) { + netdev_err(to_dev, "Cannot mirror to %s", to_dev->name); + return -EOPNOTSUPP; + } + + err = ops->parms(to_dev, &sparms); + if (err) + return err; + + span_entry = mlxsw_sp_span_entry_get(mlxsw_sp, to_dev, ops, sparms); + if (!span_entry) + return -ENOENT; + + netdev_dbg(from->dev, "Adding inspected port to SPAN entry %d\n", + span_entry->id); + + err = mlxsw_sp_span_inspected_port_add(from, span_entry, type, bind); + if (err) + goto err_port_bind; + + *p_span_id = span_entry->id; + return 0; + +err_port_bind: + mlxsw_sp_span_entry_put(mlxsw_sp, span_entry); + return err; +} + +void mlxsw_sp_span_mirror_del(struct mlxsw_sp_port *from, int span_id, + enum mlxsw_sp_span_type type, bool bind) +{ + struct mlxsw_sp_span_entry *span_entry; + + span_entry = mlxsw_sp_span_entry_find_by_id(from->mlxsw_sp, span_id); + if (!span_entry) { + netdev_err(from->dev, "no span entry found\n"); + return; + } + + netdev_dbg(from->dev, "removing inspected port from SPAN entry %d\n", + span_entry->id); + mlxsw_sp_span_inspected_port_del(from, span_entry, type, bind); +} + +void mlxsw_sp_span_respin(struct mlxsw_sp *mlxsw_sp) +{ + int i; + int err; + + ASSERT_RTNL(); + for (i = 0; i < mlxsw_sp->span.entries_count; i++) { + struct mlxsw_sp_span_entry *curr = &mlxsw_sp->span.entries[i]; + struct mlxsw_sp_span_parms sparms = {0}; + + if (!curr->ref_count) + continue; + + err = curr->ops->parms(curr->to_dev, &sparms); + if (err) + continue; + + if (memcmp(&sparms, &curr->parms, sizeof(sparms))) { + mlxsw_sp_span_entry_deconfigure(curr); + mlxsw_sp_span_entry_configure(mlxsw_sp, curr, sparms); + } + } +} diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.h new file mode 100644 index 000000000000..948aceb512c5 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.h @@ -0,0 +1,104 @@ +/* + * drivers/net/ethernet/mellanox/mlxsw/mlxsw_span.h + * Copyright (c) 2018 Mellanox Technologies. All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the names of the copyright holders nor the names of its + * contributors may be used to endorse or promote products derived from + * this software without specific prior written permission. + * + * Alternatively, this software may be distributed under the terms of the + * GNU General Public License ("GPL") version 2 as published by the Free + * Software Foundation. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN + * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE + * POSSIBILITY OF SUCH DAMAGE. + */ + +#ifndef _MLXSW_SPECTRUM_SPAN_H +#define _MLXSW_SPECTRUM_SPAN_H + +#include <linux/types.h> +#include <linux/if_ether.h> + +#include "spectrum_router.h" + +struct mlxsw_sp; +struct mlxsw_sp_port; + +enum mlxsw_sp_span_type { + MLXSW_SP_SPAN_EGRESS, + MLXSW_SP_SPAN_INGRESS +}; + +struct mlxsw_sp_span_inspected_port { + struct list_head list; + enum mlxsw_sp_span_type type; + u8 local_port; +}; + +struct mlxsw_sp_span_parms { + struct mlxsw_sp_port *dest_port; /* NULL for unoffloaded SPAN. */ + unsigned int ttl; + unsigned char dmac[ETH_ALEN]; + unsigned char smac[ETH_ALEN]; + union mlxsw_sp_l3addr daddr; + union mlxsw_sp_l3addr saddr; +}; + +struct mlxsw_sp_span_entry_ops; + +struct mlxsw_sp_span_entry { + const struct net_device *to_dev; + const struct mlxsw_sp_span_entry_ops *ops; + struct mlxsw_sp_span_parms parms; + struct list_head bound_ports_list; + int ref_count; + int id; +}; + +struct mlxsw_sp_span_entry_ops { + bool (*can_handle)(const struct net_device *to_dev); + int (*parms)(const struct net_device *to_dev, + struct mlxsw_sp_span_parms *sparmsp); + int (*configure)(struct mlxsw_sp_span_entry *span_entry, + struct mlxsw_sp_span_parms sparms); + void (*deconfigure)(struct mlxsw_sp_span_entry *span_entry); +}; + +int mlxsw_sp_span_init(struct mlxsw_sp *mlxsw_sp); +void mlxsw_sp_span_fini(struct mlxsw_sp *mlxsw_sp); +void mlxsw_sp_span_respin(struct mlxsw_sp *mlxsw_sp); + +int mlxsw_sp_span_mirror_add(struct mlxsw_sp_port *from, + const struct net_device *to_dev, + enum mlxsw_sp_span_type type, + bool bind, int *p_span_id); +void mlxsw_sp_span_mirror_del(struct mlxsw_sp_port *from, int span_id, + enum mlxsw_sp_span_type type, bool bind); +struct mlxsw_sp_span_entry * +mlxsw_sp_span_entry_find_by_port(struct mlxsw_sp *mlxsw_sp, + const struct net_device *to_dev); + +void mlxsw_sp_span_entry_invalidate(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_span_entry *span_entry); + +int mlxsw_sp_span_port_mtu_update(struct mlxsw_sp_port *port, u16 mtu); + +#endif diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c index 161bcdc012f0..c11c9a635866 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c @@ -1844,7 +1844,7 @@ mlxsw_sp_bridge_8021q_port_join(struct mlxsw_sp_bridge_device *bridge_device, struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan; if (is_vlan_dev(bridge_port->dev)) { - NL_SET_ERR_MSG(extack, "spectrum: Can not enslave a VLAN device to a VLAN-aware bridge"); + NL_SET_ERR_MSG_MOD(extack, "Can not enslave a VLAN device to a VLAN-aware bridge"); return -EINVAL; } @@ -1907,20 +1907,16 @@ mlxsw_sp_bridge_8021d_port_join(struct mlxsw_sp_bridge_device *bridge_device, struct netlink_ext_ack *extack) { struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan; + struct net_device *dev = bridge_port->dev; u16 vid; - if (!is_vlan_dev(bridge_port->dev)) { - NL_SET_ERR_MSG(extack, "spectrum: Only VLAN devices can be enslaved to a VLAN-unaware bridge"); - return -EINVAL; - } - vid = vlan_dev_vlan_id(bridge_port->dev); - + vid = is_vlan_dev(dev) ? vlan_dev_vlan_id(dev) : 1; mlxsw_sp_port_vlan = mlxsw_sp_port_vlan_find_by_vid(mlxsw_sp_port, vid); if (WARN_ON(!mlxsw_sp_port_vlan)) return -EINVAL; if (mlxsw_sp_port_is_br_member(mlxsw_sp_port, bridge_device->dev)) { - NL_SET_ERR_MSG(extack, "spectrum: Can not bridge VLAN uppers of the same port"); + NL_SET_ERR_MSG_MOD(extack, "Can not bridge VLAN uppers of the same port"); return -EINVAL; } @@ -1937,8 +1933,10 @@ mlxsw_sp_bridge_8021d_port_leave(struct mlxsw_sp_bridge_device *bridge_device, struct mlxsw_sp_port *mlxsw_sp_port) { struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan; - u16 vid = vlan_dev_vlan_id(bridge_port->dev); + struct net_device *dev = bridge_port->dev; + u16 vid; + vid = is_vlan_dev(dev) ? vlan_dev_vlan_id(dev) : 1; mlxsw_sp_port_vlan = mlxsw_sp_port_vlan_find_by_vid(mlxsw_sp_port, vid); if (WARN_ON(!mlxsw_sp_port_vlan)) return; diff --git a/drivers/net/ethernet/natsemi/jazzsonic.c b/drivers/net/ethernet/natsemi/jazzsonic.c index d5b28884e21e..51fa82b429a3 100644 --- a/drivers/net/ethernet/natsemi/jazzsonic.c +++ b/drivers/net/ethernet/natsemi/jazzsonic.c @@ -60,14 +60,6 @@ do { \ *((volatile unsigned int *)dev->base_addr+(reg)) = (val); \ } while (0) - -/* use 0 for production, 1 for verification, >1 for debug */ -#ifdef SONIC_DEBUG -static unsigned int sonic_debug = SONIC_DEBUG; -#else -static unsigned int sonic_debug = 1; -#endif - /* * We cannot use station (ethernet) address prefixes to detect the * sonic controller since these are board manufacturer depended. @@ -117,7 +109,6 @@ static const struct net_device_ops sonic_netdev_ops = { static int sonic_probe1(struct net_device *dev) { - static unsigned version_printed; unsigned int silicon_revision; unsigned int val; struct sonic_local *lp = netdev_priv(dev); @@ -133,26 +124,17 @@ static int sonic_probe1(struct net_device *dev) * the expected location. */ silicon_revision = SONIC_READ(SONIC_SR); - if (sonic_debug > 1) - printk("SONIC Silicon Revision = 0x%04x\n",silicon_revision); - i = 0; while (known_revisions[i] != 0xffff && known_revisions[i] != silicon_revision) i++; if (known_revisions[i] == 0xffff) { - printk("SONIC ethernet controller not found (0x%4x)\n", - silicon_revision); + pr_info("SONIC ethernet controller not found (0x%4x)\n", + silicon_revision); goto out; } - if (sonic_debug && version_printed++ == 0) - printk(version); - - printk(KERN_INFO "%s: Sonic ethernet found at 0x%08lx, ", - dev_name(lp->device), dev->base_addr); - /* * Put the sonic into software reset, then * retrieve and print the ethernet address. @@ -245,12 +227,16 @@ static int jazz_sonic_probe(struct platform_device *pdev) err = sonic_probe1(dev); if (err) goto out; + + pr_info("SONIC ethernet @%08lx, MAC %pM, IRQ %d\n", + dev->base_addr, dev->dev_addr, dev->irq); + + sonic_msg_init(dev); + err = register_netdev(dev); if (err) goto out1; - printk("%s: MAC %pM IRQ %d\n", dev->name, dev->dev_addr, dev->irq); - return 0; out1: @@ -262,8 +248,6 @@ out: } MODULE_DESCRIPTION("Jazz SONIC ethernet driver"); -module_param(sonic_debug, int, 0); -MODULE_PARM_DESC(sonic_debug, "jazzsonic debug level (1-4)"); MODULE_ALIAS("platform:jazzsonic"); #include "sonic.c" diff --git a/drivers/net/ethernet/natsemi/macsonic.c b/drivers/net/ethernet/natsemi/macsonic.c index b922ab5cedea..0937fc2a928e 100644 --- a/drivers/net/ethernet/natsemi/macsonic.c +++ b/drivers/net/ethernet/natsemi/macsonic.c @@ -60,8 +60,6 @@ #include <asm/macints.h> #include <asm/mac_via.h> -static char mac_sonic_string[] = "macsonic"; - #include "sonic.h" /* These should basically be bus-size and endian independent (since @@ -72,15 +70,6 @@ static char mac_sonic_string[] = "macsonic"; #define SONIC_WRITE(reg,val) (nubus_writew(val, dev->base_addr + (reg * 4) \ + lp->reg_offset)) -/* use 0 for production, 1 for verification, >1 for debug */ -#ifdef SONIC_DEBUG -static unsigned int sonic_debug = SONIC_DEBUG; -#else -static unsigned int sonic_debug = 1; -#endif - -static int sonic_version_printed; - /* For onboard SONIC */ #define ONBOARD_SONIC_REGISTERS 0x50F0A000 #define ONBOARD_SONIC_PROM_BASE 0x50f08000 @@ -313,11 +302,6 @@ static int mac_onboard_sonic_probe(struct net_device *dev) int sr; bool commslot = macintosh_config->expansion_type == MAC_EXP_PDS_COMM; - if (!MACH_IS_MAC) - return -ENODEV; - - printk(KERN_INFO "Checking for internal Macintosh ethernet (SONIC).. "); - /* Bogus probing, on the models which may or may not have Ethernet (BTW, the Ethernet *is* always at the same address, and nothing else lives there, at least if Apple's @@ -327,13 +311,11 @@ static int mac_onboard_sonic_probe(struct net_device *dev) card_present = hwreg_present((void*)ONBOARD_SONIC_REGISTERS); if (!card_present) { - printk("none.\n"); + pr_info("Onboard/comm-slot SONIC not found\n"); return -ENODEV; } } - printk("yes\n"); - /* Danger! My arms are flailing wildly! You *must* set lp->reg_offset * and dev->base_addr before using SONIC_READ() or SONIC_WRITE() */ dev->base_addr = ONBOARD_SONIC_REGISTERS; @@ -342,18 +324,10 @@ static int mac_onboard_sonic_probe(struct net_device *dev) else dev->irq = IRQ_NUBUS_9; - if (!sonic_version_printed) { - printk(KERN_INFO "%s", version); - sonic_version_printed = 1; - } - printk(KERN_INFO "%s: onboard / comm-slot SONIC at 0x%08lx\n", - dev_name(lp->device), dev->base_addr); - /* The PowerBook's SONIC is 16 bit always. */ if (macintosh_config->ident == MAC_MODEL_PB520) { lp->reg_offset = 0; lp->dma_bitmode = SONIC_BITMODE16; - sr = SONIC_READ(SONIC_SR); } else if (commslot) { /* Some of the comm-slot cards are 16 bit. But some of them are not. The 32-bit cards use offset 2 and @@ -370,22 +344,21 @@ static int mac_onboard_sonic_probe(struct net_device *dev) else { lp->dma_bitmode = SONIC_BITMODE16; lp->reg_offset = 0; - sr = SONIC_READ(SONIC_SR); } } else { /* All onboard cards are at offset 2 with 32 bit DMA. */ lp->reg_offset = 2; lp->dma_bitmode = SONIC_BITMODE32; - sr = SONIC_READ(SONIC_SR); } - printk(KERN_INFO - "%s: revision 0x%04x, using %d bit DMA and register offset %d\n", - dev_name(lp->device), sr, lp->dma_bitmode?32:16, lp->reg_offset); -#if 0 /* This is sometimes useful to find out how MacOS configured the card. */ - printk(KERN_INFO "%s: DCR: 0x%04x, DCR2: 0x%04x\n", dev_name(lp->device), - SONIC_READ(SONIC_DCR) & 0xffff, SONIC_READ(SONIC_DCR2) & 0xffff); -#endif + pr_info("Onboard/comm-slot SONIC, revision 0x%04x, %d bit DMA, register offset %d\n", + SONIC_READ(SONIC_SR), lp->dma_bitmode ? 32 : 16, + lp->reg_offset); + + /* This is sometimes useful to find out how MacOS configured the card */ + pr_debug("%s: DCR=0x%04x, DCR2=0x%04x\n", __func__, + SONIC_READ(SONIC_DCR) & 0xffff, + SONIC_READ(SONIC_DCR2) & 0xffff); /* Software reset, then initialize control registers. */ SONIC_WRITE(SONIC_CMD, SONIC_CR_RST); @@ -406,11 +379,14 @@ static int mac_onboard_sonic_probe(struct net_device *dev) /* Now look for the MAC address. */ mac_onboard_sonic_ethernet_addr(dev); + pr_info("SONIC ethernet @%08lx, MAC %pM, IRQ %d\n", + dev->base_addr, dev->dev_addr, dev->irq); + /* Shared init code */ return macsonic_init(dev); } -static int mac_nubus_sonic_ethernet_addr(struct net_device *dev, +static int mac_sonic_nubus_ethernet_addr(struct net_device *dev, unsigned long prom_addr, int id) { int i; @@ -449,70 +425,49 @@ static int macsonic_ident(struct nubus_rsrc *fres) return -1; } -static int mac_nubus_sonic_probe(struct net_device *dev) +static int mac_sonic_nubus_probe_board(struct nubus_board *board, int id, + struct net_device *dev) { - static int slots; - struct nubus_rsrc *ndev = NULL; struct sonic_local* lp = netdev_priv(dev); unsigned long base_addr, prom_addr; u16 sonic_dcr; - int id = -1; int reg_offset, dma_bitmode; - /* Find the first SONIC that hasn't been initialized already */ - for_each_func_rsrc(ndev) { - if (ndev->category != NUBUS_CAT_NETWORK || - ndev->type != NUBUS_TYPE_ETHERNET) - continue; - - /* Have we seen it already? */ - if (slots & (1<<ndev->board->slot)) - continue; - slots |= 1<<ndev->board->slot; - - /* Is it one of ours? */ - if ((id = macsonic_ident(ndev)) != -1) - break; - } - - if (ndev == NULL) - return -ENODEV; - switch (id) { case MACSONIC_DUODOCK: - base_addr = ndev->board->slot_addr + DUODOCK_SONIC_REGISTERS; - prom_addr = ndev->board->slot_addr + DUODOCK_SONIC_PROM_BASE; + base_addr = board->slot_addr + DUODOCK_SONIC_REGISTERS; + prom_addr = board->slot_addr + DUODOCK_SONIC_PROM_BASE; sonic_dcr = SONIC_DCR_EXBUS | SONIC_DCR_RFT0 | SONIC_DCR_RFT1 | SONIC_DCR_TFT0; reg_offset = 2; dma_bitmode = SONIC_BITMODE32; break; case MACSONIC_APPLE: - base_addr = ndev->board->slot_addr + APPLE_SONIC_REGISTERS; - prom_addr = ndev->board->slot_addr + APPLE_SONIC_PROM_BASE; + base_addr = board->slot_addr + APPLE_SONIC_REGISTERS; + prom_addr = board->slot_addr + APPLE_SONIC_PROM_BASE; sonic_dcr = SONIC_DCR_BMS | SONIC_DCR_RFT1 | SONIC_DCR_TFT0; reg_offset = 0; dma_bitmode = SONIC_BITMODE32; break; case MACSONIC_APPLE16: - base_addr = ndev->board->slot_addr + APPLE_SONIC_REGISTERS; - prom_addr = ndev->board->slot_addr + APPLE_SONIC_PROM_BASE; + base_addr = board->slot_addr + APPLE_SONIC_REGISTERS; + prom_addr = board->slot_addr + APPLE_SONIC_PROM_BASE; sonic_dcr = SONIC_DCR_EXBUS | SONIC_DCR_RFT1 | SONIC_DCR_TFT0 | SONIC_DCR_PO1 | SONIC_DCR_BMS; reg_offset = 0; dma_bitmode = SONIC_BITMODE16; break; case MACSONIC_DAYNALINK: - base_addr = ndev->board->slot_addr + APPLE_SONIC_REGISTERS; - prom_addr = ndev->board->slot_addr + DAYNALINK_PROM_BASE; + base_addr = board->slot_addr + APPLE_SONIC_REGISTERS; + prom_addr = board->slot_addr + DAYNALINK_PROM_BASE; sonic_dcr = SONIC_DCR_RFT1 | SONIC_DCR_TFT0 | SONIC_DCR_PO1 | SONIC_DCR_BMS; reg_offset = 0; dma_bitmode = SONIC_BITMODE16; break; case MACSONIC_DAYNA: - base_addr = ndev->board->slot_addr + DAYNA_SONIC_REGISTERS; - prom_addr = ndev->board->slot_addr + DAYNA_SONIC_MAC_ADDR; + base_addr = board->slot_addr + DAYNA_SONIC_REGISTERS; + prom_addr = board->slot_addr + DAYNA_SONIC_MAC_ADDR; sonic_dcr = SONIC_DCR_BMS | SONIC_DCR_RFT1 | SONIC_DCR_TFT0 | SONIC_DCR_PO1; reg_offset = 0; @@ -528,21 +483,16 @@ static int mac_nubus_sonic_probe(struct net_device *dev) dev->base_addr = base_addr; lp->reg_offset = reg_offset; lp->dma_bitmode = dma_bitmode; - dev->irq = SLOT2IRQ(ndev->board->slot); + dev->irq = SLOT2IRQ(board->slot); - if (!sonic_version_printed) { - printk(KERN_INFO "%s", version); - sonic_version_printed = 1; - } - printk(KERN_INFO "%s: %s in slot %X\n", - dev_name(lp->device), ndev->board->name, ndev->board->slot); - printk(KERN_INFO "%s: revision 0x%04x, using %d bit DMA and register offset %d\n", - dev_name(lp->device), SONIC_READ(SONIC_SR), dma_bitmode?32:16, reg_offset); + dev_info(&board->dev, "%s, revision 0x%04x, %d bit DMA, register offset %d\n", + board->name, SONIC_READ(SONIC_SR), + lp->dma_bitmode ? 32 : 16, lp->reg_offset); -#if 0 /* This is sometimes useful to find out how MacOS configured the card. */ - printk(KERN_INFO "%s: DCR: 0x%04x, DCR2: 0x%04x\n", dev_name(lp->device), - SONIC_READ(SONIC_DCR) & 0xffff, SONIC_READ(SONIC_DCR2) & 0xffff); -#endif + /* This is sometimes useful to find out how MacOS configured the card */ + dev_dbg(&board->dev, "%s: DCR=0x%04x, DCR2=0x%04x\n", __func__, + SONIC_READ(SONIC_DCR) & 0xffff, + SONIC_READ(SONIC_DCR2) & 0xffff); /* Software reset, then initialize control registers. */ SONIC_WRITE(SONIC_CMD, SONIC_CR_RST); @@ -557,14 +507,17 @@ static int mac_nubus_sonic_probe(struct net_device *dev) SONIC_WRITE(SONIC_ISR, 0x7fff); /* Now look for the MAC address. */ - if (mac_nubus_sonic_ethernet_addr(dev, prom_addr, id) != 0) + if (mac_sonic_nubus_ethernet_addr(dev, prom_addr, id) != 0) return -ENODEV; + dev_info(&board->dev, "SONIC ethernet @%08lx, MAC %pM, IRQ %d\n", + dev->base_addr, dev->dev_addr, dev->irq); + /* Shared init code */ return macsonic_init(dev); } -static int mac_sonic_probe(struct platform_device *pdev) +static int mac_sonic_platform_probe(struct platform_device *pdev) { struct net_device *dev; struct sonic_local *lp; @@ -579,22 +532,16 @@ static int mac_sonic_probe(struct platform_device *pdev) SET_NETDEV_DEV(dev, &pdev->dev); platform_set_drvdata(pdev, dev); - /* This will catch fatal stuff like -ENOMEM as well as success */ err = mac_onboard_sonic_probe(dev); - if (err == 0) - goto found; - if (err != -ENODEV) - goto out; - err = mac_nubus_sonic_probe(dev); if (err) goto out; -found: + + sonic_msg_init(dev); + err = register_netdev(dev); if (err) goto out; - printk("%s: MAC %pM IRQ %d\n", dev->name, dev->dev_addr, dev->irq); - return 0; out: @@ -604,13 +551,11 @@ out: } MODULE_DESCRIPTION("Macintosh SONIC ethernet driver"); -module_param(sonic_debug, int, 0); -MODULE_PARM_DESC(sonic_debug, "macsonic debug level (1-4)"); MODULE_ALIAS("platform:macsonic"); #include "sonic.c" -static int mac_sonic_device_remove(struct platform_device *pdev) +static int mac_sonic_platform_remove(struct platform_device *pdev) { struct net_device *dev = platform_get_drvdata(pdev); struct sonic_local* lp = netdev_priv(dev); @@ -623,12 +568,105 @@ static int mac_sonic_device_remove(struct platform_device *pdev) return 0; } -static struct platform_driver mac_sonic_driver = { - .probe = mac_sonic_probe, - .remove = mac_sonic_device_remove, - .driver = { - .name = mac_sonic_string, +static struct platform_driver mac_sonic_platform_driver = { + .probe = mac_sonic_platform_probe, + .remove = mac_sonic_platform_remove, + .driver = { + .name = "macsonic", + }, +}; + +static int mac_sonic_nubus_probe(struct nubus_board *board) +{ + struct net_device *ndev; + struct sonic_local *lp; + struct nubus_rsrc *fres; + int id = -1; + int err; + + /* The platform driver will handle a PDS or Comm Slot card (even if + * it has a pseudoslot declaration ROM). + */ + if (macintosh_config->expansion_type == MAC_EXP_PDS_COMM) + return -ENODEV; + + for_each_board_func_rsrc(board, fres) { + if (fres->category != NUBUS_CAT_NETWORK || + fres->type != NUBUS_TYPE_ETHERNET) + continue; + + id = macsonic_ident(fres); + if (id != -1) + break; + } + if (!fres) + return -ENODEV; + + ndev = alloc_etherdev(sizeof(struct sonic_local)); + if (!ndev) + return -ENOMEM; + + lp = netdev_priv(ndev); + lp->device = &board->dev; + SET_NETDEV_DEV(ndev, &board->dev); + + err = mac_sonic_nubus_probe_board(board, id, ndev); + if (err) + goto out; + + sonic_msg_init(ndev); + + err = register_netdev(ndev); + if (err) + goto out; + + nubus_set_drvdata(board, ndev); + + return 0; + +out: + free_netdev(ndev); + return err; +} + +static int mac_sonic_nubus_remove(struct nubus_board *board) +{ + struct net_device *ndev = nubus_get_drvdata(board); + struct sonic_local *lp = netdev_priv(ndev); + + unregister_netdev(ndev); + dma_free_coherent(lp->device, + SIZEOF_SONIC_DESC * SONIC_BUS_SCALE(lp->dma_bitmode), + lp->descriptors, lp->descriptors_laddr); + free_netdev(ndev); + + return 0; +} + +static struct nubus_driver mac_sonic_nubus_driver = { + .probe = mac_sonic_nubus_probe, + .remove = mac_sonic_nubus_remove, + .driver = { + .name = "macsonic-nubus", + .owner = THIS_MODULE, }, }; -module_platform_driver(mac_sonic_driver); +static int perr, nerr; + +static int __init mac_sonic_init(void) +{ + perr = platform_driver_register(&mac_sonic_platform_driver); + nerr = nubus_driver_register(&mac_sonic_nubus_driver); + return 0; +} +module_init(mac_sonic_init); + +static void __exit mac_sonic_exit(void) +{ + if (!perr) + platform_driver_unregister(&mac_sonic_platform_driver); + if (!nerr) + nubus_driver_unregister(&mac_sonic_nubus_driver); +} +module_exit(mac_sonic_exit); diff --git a/drivers/net/ethernet/natsemi/sonic.c b/drivers/net/ethernet/natsemi/sonic.c index 612c7a44b26c..7ed08486ae23 100644 --- a/drivers/net/ethernet/natsemi/sonic.c +++ b/drivers/net/ethernet/natsemi/sonic.c @@ -33,7 +33,21 @@ * the NetBSD file "sys/arch/mac68k/dev/if_sn.c". */ +static unsigned int version_printed; +static int sonic_debug = -1; +module_param(sonic_debug, int, 0); +MODULE_PARM_DESC(sonic_debug, "debug message level"); + +static void sonic_msg_init(struct net_device *dev) +{ + struct sonic_local *lp = netdev_priv(dev); + + lp->msg_enable = netif_msg_init(sonic_debug, 0); + + if (version_printed++ == 0) + netif_dbg(lp, drv, dev, "%s", version); +} /* * Open/initialize the SONIC controller. @@ -47,8 +61,7 @@ static int sonic_open(struct net_device *dev) struct sonic_local *lp = netdev_priv(dev); int i; - if (sonic_debug > 2) - printk("sonic_open: initializing sonic driver.\n"); + netif_dbg(lp, ifup, dev, "%s: initializing sonic driver\n", __func__); for (i = 0; i < SONIC_NUM_RRS; i++) { struct sk_buff *skb = netdev_alloc_skb(dev, SONIC_RBSIZE + 2); @@ -95,8 +108,7 @@ static int sonic_open(struct net_device *dev) netif_start_queue(dev); - if (sonic_debug > 2) - printk("sonic_open: Initialization done.\n"); + netif_dbg(lp, ifup, dev, "%s: Initialization done\n", __func__); return 0; } @@ -110,8 +122,7 @@ static int sonic_close(struct net_device *dev) struct sonic_local *lp = netdev_priv(dev); int i; - if (sonic_debug > 2) - printk("sonic_close\n"); + netif_dbg(lp, ifdown, dev, "%s\n", __func__); netif_stop_queue(dev); @@ -205,8 +216,7 @@ static int sonic_send_packet(struct sk_buff *skb, struct net_device *dev) int length; int entry = lp->next_tx; - if (sonic_debug > 2) - printk("sonic_send_packet: skb=%p, dev=%p\n", skb, dev); + netif_dbg(lp, tx_queued, dev, "%s: skb=%p\n", __func__, skb); length = skb->len; if (length < ETH_ZLEN) { @@ -252,14 +262,12 @@ static int sonic_send_packet(struct sk_buff *skb, struct net_device *dev) lp->next_tx = (entry + 1) & SONIC_TDS_MASK; if (lp->tx_skb[lp->next_tx] != NULL) { /* The ring is full, the ISR has yet to process the next TD. */ - if (sonic_debug > 3) - printk("%s: stopping queue\n", dev->name); + netif_dbg(lp, tx_queued, dev, "%s: stopping queue\n", __func__); netif_stop_queue(dev); /* after this packet, wait for ISR to free up some TDAs */ } else netif_start_queue(dev); - if (sonic_debug > 2) - printk("sonic_send_packet: issuing Tx command\n"); + netif_dbg(lp, tx_queued, dev, "%s: issuing Tx command\n", __func__); SONIC_WRITE(SONIC_CMD, SONIC_CR_TXP); @@ -281,8 +289,7 @@ static irqreturn_t sonic_interrupt(int irq, void *dev_id) do { if (status & SONIC_INT_PKTRX) { - if (sonic_debug > 2) - printk("%s: packet rx\n", dev->name); + netif_dbg(lp, intr, dev, "%s: packet rx\n", __func__); sonic_rx(dev); /* got packet(s) */ SONIC_WRITE(SONIC_ISR, SONIC_INT_PKTRX); /* clear the interrupt */ } @@ -299,8 +306,7 @@ static irqreturn_t sonic_interrupt(int irq, void *dev_id) * still being allocated by sonic_send_packet (status clear & tx_skb[entry] clear) */ - if (sonic_debug > 2) - printk("%s: tx done\n", dev->name); + netif_dbg(lp, intr, dev, "%s: tx done\n", __func__); while (lp->tx_skb[entry] != NULL) { if ((td_status = sonic_tda_get(dev, entry, SONIC_TD_STATUS)) == 0) @@ -346,20 +352,20 @@ static irqreturn_t sonic_interrupt(int irq, void *dev_id) * check error conditions */ if (status & SONIC_INT_RFO) { - if (sonic_debug > 1) - printk("%s: rx fifo overrun\n", dev->name); + netif_dbg(lp, rx_err, dev, "%s: rx fifo overrun\n", + __func__); lp->stats.rx_fifo_errors++; SONIC_WRITE(SONIC_ISR, SONIC_INT_RFO); /* clear the interrupt */ } if (status & SONIC_INT_RDE) { - if (sonic_debug > 1) - printk("%s: rx descriptors exhausted\n", dev->name); + netif_dbg(lp, rx_err, dev, "%s: rx descriptors exhausted\n", + __func__); lp->stats.rx_dropped++; SONIC_WRITE(SONIC_ISR, SONIC_INT_RDE); /* clear the interrupt */ } if (status & SONIC_INT_RBAE) { - if (sonic_debug > 1) - printk("%s: rx buffer area exceeded\n", dev->name); + netif_dbg(lp, rx_err, dev, "%s: rx buffer area exceeded\n", + __func__); lp->stats.rx_dropped++; SONIC_WRITE(SONIC_ISR, SONIC_INT_RBAE); /* clear the interrupt */ } @@ -380,8 +386,9 @@ static irqreturn_t sonic_interrupt(int irq, void *dev_id) /* transmit error */ if (status & SONIC_INT_TXER) { - if ((SONIC_READ(SONIC_TCR) & SONIC_TCR_FU) && (sonic_debug > 2)) - printk(KERN_ERR "%s: tx fifo underrun\n", dev->name); + if (SONIC_READ(SONIC_TCR) & SONIC_TCR_FU) + netif_dbg(lp, tx_err, dev, "%s: tx fifo underrun\n", + __func__); SONIC_WRITE(SONIC_ISR, SONIC_INT_TXER); /* clear the interrupt */ } @@ -475,8 +482,8 @@ static void sonic_rx(struct net_device *dev) if (lp->cur_rwp >= lp->rra_end) lp->cur_rwp = lp->rra_laddr & 0xffff; SONIC_WRITE(SONIC_RWP, lp->cur_rwp); if (SONIC_READ(SONIC_ISR) & SONIC_INT_RBE) { - if (sonic_debug > 2) - printk("%s: rx buffer exhausted\n", dev->name); + netif_dbg(lp, rx_err, dev, "%s: rx buffer exhausted\n", + __func__); SONIC_WRITE(SONIC_ISR, SONIC_INT_RBE); /* clear the flag */ } } else @@ -542,9 +549,8 @@ static void sonic_multicast_list(struct net_device *dev) (netdev_mc_count(dev) > 15)) { rcr |= SONIC_RCR_AMC; } else { - if (sonic_debug > 2) - printk("sonic_multicast_list: mc_count %d\n", - netdev_mc_count(dev)); + netif_dbg(lp, ifup, dev, "%s: mc_count %d\n", __func__, + netdev_mc_count(dev)); sonic_set_cam_enable(dev, 1); /* always enable our own address */ i = 1; netdev_for_each_mc_addr(ha, dev) { @@ -562,8 +568,7 @@ static void sonic_multicast_list(struct net_device *dev) } } - if (sonic_debug > 2) - printk("sonic_multicast_list: setting RCR=%x\n", rcr); + netif_dbg(lp, ifup, dev, "%s: setting RCR=%x\n", __func__, rcr); SONIC_WRITE(SONIC_RCR, rcr); } @@ -596,8 +601,8 @@ static int sonic_init(struct net_device *dev) /* * initialize the receive resource area */ - if (sonic_debug > 2) - printk("sonic_init: initialize receive resource area\n"); + netif_dbg(lp, ifup, dev, "%s: initialize receive resource area\n", + __func__); for (i = 0; i < SONIC_NUM_RRS; i++) { u16 bufadr_l = (unsigned long)lp->rx_laddr[i] & 0xffff; @@ -622,8 +627,7 @@ static int sonic_init(struct net_device *dev) SONIC_WRITE(SONIC_EOBC, (SONIC_RBSIZE >> 1) - (lp->dma_bitmode ? 2 : 1)); /* load the resource pointers */ - if (sonic_debug > 3) - printk("sonic_init: issuing RRRA command\n"); + netif_dbg(lp, ifup, dev, "%s: issuing RRRA command\n", __func__); SONIC_WRITE(SONIC_CMD, SONIC_CR_RRRA); i = 0; @@ -632,16 +636,17 @@ static int sonic_init(struct net_device *dev) break; } - if (sonic_debug > 2) - printk("sonic_init: status=%x i=%d\n", SONIC_READ(SONIC_CMD), i); + netif_dbg(lp, ifup, dev, "%s: status=%x, i=%d\n", __func__, + SONIC_READ(SONIC_CMD), i); /* * Initialize the receive descriptors so that they * become a circular linked list, ie. let the last * descriptor point to the first again. */ - if (sonic_debug > 2) - printk("sonic_init: initialize receive descriptors\n"); + netif_dbg(lp, ifup, dev, "%s: initialize receive descriptors\n", + __func__); + for (i=0; i<SONIC_NUM_RDS; i++) { sonic_rda_put(dev, i, SONIC_RD_STATUS, 0); sonic_rda_put(dev, i, SONIC_RD_PKTLEN, 0); @@ -664,8 +669,9 @@ static int sonic_init(struct net_device *dev) /* * initialize transmit descriptors */ - if (sonic_debug > 2) - printk("sonic_init: initialize transmit descriptors\n"); + netif_dbg(lp, ifup, dev, "%s: initialize transmit descriptors\n", + __func__); + for (i = 0; i < SONIC_NUM_TDS; i++) { sonic_tda_put(dev, i, SONIC_TD_STATUS, 0); sonic_tda_put(dev, i, SONIC_TD_CONFIG, 0); @@ -712,10 +718,8 @@ static int sonic_init(struct net_device *dev) if (SONIC_READ(SONIC_ISR) & SONIC_INT_LCD) break; } - if (sonic_debug > 2) { - printk("sonic_init: CMD=%x, ISR=%x\n, i=%d", - SONIC_READ(SONIC_CMD), SONIC_READ(SONIC_ISR), i); - } + netif_dbg(lp, ifup, dev, "%s: CMD=%x, ISR=%x, i=%d\n", __func__, + SONIC_READ(SONIC_CMD), SONIC_READ(SONIC_ISR), i); /* * enable receiver, disable loopback @@ -731,9 +735,8 @@ static int sonic_init(struct net_device *dev) if ((cmd & SONIC_CR_RXEN) == 0 || (cmd & SONIC_CR_STP) == 0) printk(KERN_ERR "sonic_init: failed, status=%x\n", cmd); - if (sonic_debug > 2) - printk("sonic_init: new status=%x\n", - SONIC_READ(SONIC_CMD)); + netif_dbg(lp, ifup, dev, "%s: new status=%x\n", __func__, + SONIC_READ(SONIC_CMD)); return 0; } diff --git a/drivers/net/ethernet/natsemi/sonic.h b/drivers/net/ethernet/natsemi/sonic.h index 421b1a283fed..2b27f7049acb 100644 --- a/drivers/net/ethernet/natsemi/sonic.h +++ b/drivers/net/ethernet/natsemi/sonic.h @@ -319,6 +319,7 @@ struct sonic_local { unsigned int eol_rx; unsigned int eol_tx; /* last unacked transmit packet */ unsigned int next_tx; /* next free TD */ + int msg_enable; struct device *device; /* generic device */ struct net_device_stats stats; }; @@ -336,6 +337,7 @@ static struct net_device_stats *sonic_get_stats(struct net_device *dev); static void sonic_multicast_list(struct net_device *dev); static int sonic_init(struct net_device *dev); static void sonic_tx_timeout(struct net_device *dev); +static void sonic_msg_init(struct net_device *dev); /* Internal inlines for reading/writing DMA buffers. Note that bus size and endianness matter here, whereas they don't for registers, diff --git a/drivers/net/ethernet/natsemi/xtsonic.c b/drivers/net/ethernet/natsemi/xtsonic.c index 1817deea98a4..e1b886e87a76 100644 --- a/drivers/net/ethernet/natsemi/xtsonic.c +++ b/drivers/net/ethernet/natsemi/xtsonic.c @@ -73,14 +73,6 @@ extern void xtboard_get_ether_addr(unsigned char *buf); #define SONIC_WRITE(reg,val) \ *((volatile unsigned int *)dev->base_addr+reg) = val - -/* Use 0 for production, 1 for verification, and >2 for debug */ -#ifdef SONIC_DEBUG -static unsigned int sonic_debug = SONIC_DEBUG; -#else -static unsigned int sonic_debug = 1; -#endif - /* * We cannot use station (ethernet) address prefixes to detect the * sonic controller since these are board manufacturer depended. @@ -130,7 +122,6 @@ static const struct net_device_ops xtsonic_netdev_ops = { static int __init sonic_probe1(struct net_device *dev) { - static unsigned version_printed = 0; unsigned int silicon_revision; struct sonic_local *lp = netdev_priv(dev); unsigned int base_addr = dev->base_addr; @@ -146,23 +137,17 @@ static int __init sonic_probe1(struct net_device *dev) * the expected location. */ silicon_revision = SONIC_READ(SONIC_SR); - if (sonic_debug > 1) - printk("SONIC Silicon Revision = 0x%04x\n",silicon_revision); - i = 0; while ((known_revisions[i] != 0xffff) && (known_revisions[i] != silicon_revision)) i++; if (known_revisions[i] == 0xffff) { - printk("SONIC ethernet controller not found (0x%4x)\n", - silicon_revision); + pr_info("SONIC ethernet controller not found (0x%4x)\n", + silicon_revision); return -ENODEV; } - if (sonic_debug && version_printed++ == 0) - printk(version); - /* * Put the sonic into software reset, then retrieve ethernet address. * Note: we are assuming that the boot-loader has initialized the cam. @@ -273,12 +258,15 @@ int xtsonic_probe(struct platform_device *pdev) if ((err = sonic_probe1(dev))) goto out; + + pr_info("SONIC ethernet @%08lx, MAC %pM, IRQ %d\n", + dev->base_addr, dev->dev_addr, dev->irq); + + sonic_msg_init(dev); + if ((err = register_netdev(dev))) goto out1; - printk("%s: SONIC ethernet @%08lx, MAC %pM, IRQ %d\n", dev->name, - dev->base_addr, dev->dev_addr, dev->irq); - return 0; out1: @@ -290,8 +278,6 @@ out: } MODULE_DESCRIPTION("Xtensa XT2000 SONIC ethernet driver"); -module_param(sonic_debug, int, 0); -MODULE_PARM_DESC(sonic_debug, "xtsonic debug level (1-4)"); #include "sonic.c" diff --git a/drivers/net/ethernet/netronome/nfp/bpf/Makefile b/drivers/net/ethernet/netronome/nfp/bpf/Makefile new file mode 100644 index 000000000000..805fa28f391a --- /dev/null +++ b/drivers/net/ethernet/netronome/nfp/bpf/Makefile @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0 +# kbuild requires Makefile in a directory to build individual objects diff --git a/drivers/net/ethernet/netronome/nfp/flower/Makefile b/drivers/net/ethernet/netronome/nfp/flower/Makefile new file mode 100644 index 000000000000..805fa28f391a --- /dev/null +++ b/drivers/net/ethernet/netronome/nfp/flower/Makefile @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0 +# kbuild requires Makefile in a directory to build individual objects diff --git a/drivers/net/ethernet/netronome/nfp/flower/cmsg.h b/drivers/net/ethernet/netronome/nfp/flower/cmsg.h index adfe474c2cf0..28c1cd5b823b 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/cmsg.h +++ b/drivers/net/ethernet/netronome/nfp/flower/cmsg.h @@ -61,6 +61,13 @@ #define NFP_FLOWER_MASK_MPLS_BOS BIT(8) #define NFP_FLOWER_MASK_MPLS_Q BIT(0) +/* Compressed HW representation of TCP Flags */ +#define NFP_FL_TCP_FLAG_URG BIT(4) +#define NFP_FL_TCP_FLAG_PSH BIT(3) +#define NFP_FL_TCP_FLAG_RST BIT(2) +#define NFP_FL_TCP_FLAG_SYN BIT(1) +#define NFP_FL_TCP_FLAG_FIN BIT(0) + #define NFP_FL_SC_ACT_DROP 0x80000000 #define NFP_FL_SC_ACT_USER 0x7D000000 #define NFP_FL_SC_ACT_POPV 0x6A000000 @@ -257,7 +264,7 @@ struct nfp_flower_tp_ports { * 3 2 1 * 1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0 * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - * | DSCP |ECN| protocol | reserved | + * | DSCP |ECN| protocol | ttl | flags | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | ipv4_addr_src | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ @@ -268,7 +275,7 @@ struct nfp_flower_ipv4 { u8 tos; u8 proto; u8 ttl; - u8 reserved; + u8 flags; __be32 ipv4_src; __be32 ipv4_dst; }; diff --git a/drivers/net/ethernet/netronome/nfp/flower/main.h b/drivers/net/ethernet/netronome/nfp/flower/main.h index 332ff0fdc038..c5cebf6fb1d3 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/main.h +++ b/drivers/net/ethernet/netronome/nfp/flower/main.h @@ -41,6 +41,7 @@ #include <linux/time64.h> #include <linux/types.h> #include <net/pkt_cls.h> +#include <net/tcp.h> #include <linux/workqueue.h> struct net_device; diff --git a/drivers/net/ethernet/netronome/nfp/flower/match.c b/drivers/net/ethernet/netronome/nfp/flower/match.c index 37c2ecae2a7a..b3bc8279d4fb 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/match.c +++ b/drivers/net/ethernet/netronome/nfp/flower/match.c @@ -181,6 +181,26 @@ nfp_flower_compile_ipv4(struct nfp_flower_ipv4 *frame, frame->tos = flow_ip->tos; frame->ttl = flow_ip->ttl; } + + if (dissector_uses_key(flow->dissector, FLOW_DISSECTOR_KEY_TCP)) { + struct flow_dissector_key_tcp *tcp; + u32 tcp_flags; + + tcp = skb_flow_dissector_target(flow->dissector, + FLOW_DISSECTOR_KEY_TCP, target); + tcp_flags = be16_to_cpu(tcp->flags); + + if (tcp_flags & TCPHDR_FIN) + frame->flags |= NFP_FL_TCP_FLAG_FIN; + if (tcp_flags & TCPHDR_SYN) + frame->flags |= NFP_FL_TCP_FLAG_SYN; + if (tcp_flags & TCPHDR_RST) + frame->flags |= NFP_FL_TCP_FLAG_RST; + if (tcp_flags & TCPHDR_PSH) + frame->flags |= NFP_FL_TCP_FLAG_PSH; + if (tcp_flags & TCPHDR_URG) + frame->flags |= NFP_FL_TCP_FLAG_URG; + } } static void diff --git a/drivers/net/ethernet/netronome/nfp/flower/offload.c b/drivers/net/ethernet/netronome/nfp/flower/offload.c index eb5c13dea8f5..f3586c519805 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/offload.c +++ b/drivers/net/ethernet/netronome/nfp/flower/offload.c @@ -44,11 +44,16 @@ #include "../nfp_net.h" #include "../nfp_port.h" +#define NFP_FLOWER_SUPPORTED_TCPFLAGS \ + (TCPHDR_FIN | TCPHDR_SYN | TCPHDR_RST | \ + TCPHDR_PSH | TCPHDR_URG) + #define NFP_FLOWER_WHITELIST_DISSECTOR \ (BIT(FLOW_DISSECTOR_KEY_CONTROL) | \ BIT(FLOW_DISSECTOR_KEY_BASIC) | \ BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS) | \ BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS) | \ + BIT(FLOW_DISSECTOR_KEY_TCP) | \ BIT(FLOW_DISSECTOR_KEY_PORTS) | \ BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS) | \ BIT(FLOW_DISSECTOR_KEY_VLAN) | \ @@ -288,6 +293,35 @@ nfp_flower_calculate_key_layers(struct nfp_app *app, } } + if (dissector_uses_key(flow->dissector, FLOW_DISSECTOR_KEY_TCP)) { + struct flow_dissector_key_tcp *tcp; + u32 tcp_flags; + + tcp = skb_flow_dissector_target(flow->dissector, + FLOW_DISSECTOR_KEY_TCP, + flow->key); + tcp_flags = be16_to_cpu(tcp->flags); + + if (tcp_flags & ~NFP_FLOWER_SUPPORTED_TCPFLAGS) + return -EOPNOTSUPP; + + /* We only support PSH and URG flags when either + * FIN, SYN or RST is present as well. + */ + if ((tcp_flags & (TCPHDR_PSH | TCPHDR_URG)) && + !(tcp_flags & (TCPHDR_FIN | TCPHDR_SYN | TCPHDR_RST))) + return -EOPNOTSUPP; + + /* We need to store TCP flags in the IPv4 key space, thus + * we need to ensure we include a IPv4 key layer if we have + * not done so already. + */ + if (!(key_layer & NFP_FLOWER_LAYER_IPV4)) { + key_layer |= NFP_FLOWER_LAYER_IPV4; + key_size += sizeof(struct nfp_flower_ipv4); + } + } + ret_key_ls->key_layer = key_layer; ret_key_ls->key_layer_two = key_layer_two; ret_key_ls->key_size = key_size; diff --git a/drivers/net/ethernet/netronome/nfp/nfp_main.c b/drivers/net/ethernet/netronome/nfp/nfp_main.c index ab301d56430b..c4b1f344b4da 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_main.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_main.c @@ -645,6 +645,7 @@ MODULE_FIRMWARE("netronome/nic_AMDA0097-0001_4x10_1x40.nffw"); MODULE_FIRMWARE("netronome/nic_AMDA0097-0001_8x10.nffw"); MODULE_FIRMWARE("netronome/nic_AMDA0099-0001_2x10.nffw"); MODULE_FIRMWARE("netronome/nic_AMDA0099-0001_2x25.nffw"); +MODULE_FIRMWARE("netronome/nic_AMDA0099-0001_1x10_1x25.nffw"); MODULE_AUTHOR("Netronome Systems <oss-drivers@netronome.com>"); MODULE_LICENSE("GPL"); diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h b/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h index 4499a7333078..bb63c115537d 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h @@ -1,5 +1,5 @@ /* - * Copyright (C) 2015-2017 Netronome Systems, Inc. + * Copyright (C) 2015-2018 Netronome Systems, Inc. * * This software is dual licensed under the GNU General License Version 2, * June 1991 as shown in the file COPYING in the top-level directory of this @@ -51,12 +51,12 @@ * The configuration BAR is 8K in size, but due to * THB-350, 32k needs to be reserved. */ -#define NFP_NET_CFG_BAR_SZ (32 * 1024) +#define NFP_NET_CFG_BAR_SZ (32 * 1024) /** * Offset in Freelist buffer where packet starts on RX */ -#define NFP_NET_RX_OFFSET 32 +#define NFP_NET_RX_OFFSET 32 /** * LSO parameters @@ -75,65 +75,65 @@ #define NFP_NET_META_PORTID 5 #define NFP_NET_META_CSUM 6 /* checksum complete type */ -#define NFP_META_PORT_ID_CTRL ~0U +#define NFP_META_PORT_ID_CTRL ~0U /** * Hash type pre-pended when a RSS hash was computed */ -#define NFP_NET_RSS_NONE 0 -#define NFP_NET_RSS_IPV4 1 -#define NFP_NET_RSS_IPV6 2 -#define NFP_NET_RSS_IPV6_EX 3 -#define NFP_NET_RSS_IPV4_TCP 4 -#define NFP_NET_RSS_IPV6_TCP 5 -#define NFP_NET_RSS_IPV6_EX_TCP 6 -#define NFP_NET_RSS_IPV4_UDP 7 -#define NFP_NET_RSS_IPV6_UDP 8 -#define NFP_NET_RSS_IPV6_EX_UDP 9 +#define NFP_NET_RSS_NONE 0 +#define NFP_NET_RSS_IPV4 1 +#define NFP_NET_RSS_IPV6 2 +#define NFP_NET_RSS_IPV6_EX 3 +#define NFP_NET_RSS_IPV4_TCP 4 +#define NFP_NET_RSS_IPV6_TCP 5 +#define NFP_NET_RSS_IPV6_EX_TCP 6 +#define NFP_NET_RSS_IPV4_UDP 7 +#define NFP_NET_RSS_IPV6_UDP 8 +#define NFP_NET_RSS_IPV6_EX_UDP 9 /** * Ring counts - * %NFP_NET_TXR_MAX: Maximum number of TX rings - * %NFP_NET_RXR_MAX: Maximum number of RX rings + * %NFP_NET_TXR_MAX: Maximum number of TX rings + * %NFP_NET_RXR_MAX: Maximum number of RX rings */ -#define NFP_NET_TXR_MAX 64 -#define NFP_NET_RXR_MAX 64 +#define NFP_NET_TXR_MAX 64 +#define NFP_NET_RXR_MAX 64 /** * Read/Write config words (0x0000 - 0x002c) - * %NFP_NET_CFG_CTRL: Global control + * %NFP_NET_CFG_CTRL: Global control * %NFP_NET_CFG_UPDATE: Indicate which fields are updated * %NFP_NET_CFG_TXRS_ENABLE: Bitmask of enabled TX rings * %NFP_NET_CFG_RXRS_ENABLE: Bitmask of enabled RX rings - * %NFP_NET_CFG_MTU: Set MTU size + * %NFP_NET_CFG_MTU: Set MTU size * %NFP_NET_CFG_FLBUFSZ: Set freelist buffer size (must be larger than MTU) - * %NFP_NET_CFG_EXN: MSI-X table entry for exceptions - * %NFP_NET_CFG_LSC: MSI-X table entry for link state changes + * %NFP_NET_CFG_EXN: MSI-X table entry for exceptions + * %NFP_NET_CFG_LSC: MSI-X table entry for link state changes * %NFP_NET_CFG_MACADDR: MAC address * * TODO: * - define Error details in UPDATE */ -#define NFP_NET_CFG_CTRL 0x0000 -#define NFP_NET_CFG_CTRL_ENABLE (0x1 << 0) /* Global enable */ -#define NFP_NET_CFG_CTRL_PROMISC (0x1 << 1) /* Enable Promisc mode */ -#define NFP_NET_CFG_CTRL_L2BC (0x1 << 2) /* Allow L2 Broadcast */ -#define NFP_NET_CFG_CTRL_L2MC (0x1 << 3) /* Allow L2 Multicast */ -#define NFP_NET_CFG_CTRL_RXCSUM (0x1 << 4) /* Enable RX Checksum */ -#define NFP_NET_CFG_CTRL_TXCSUM (0x1 << 5) /* Enable TX Checksum */ -#define NFP_NET_CFG_CTRL_RXVLAN (0x1 << 6) /* Enable VLAN strip */ -#define NFP_NET_CFG_CTRL_TXVLAN (0x1 << 7) /* Enable VLAN insert */ -#define NFP_NET_CFG_CTRL_SCATTER (0x1 << 8) /* Scatter DMA */ -#define NFP_NET_CFG_CTRL_GATHER (0x1 << 9) /* Gather DMA */ -#define NFP_NET_CFG_CTRL_LSO (0x1 << 10) /* LSO/TSO (version 1) */ +#define NFP_NET_CFG_CTRL 0x0000 +#define NFP_NET_CFG_CTRL_ENABLE (0x1 << 0) /* Global enable */ +#define NFP_NET_CFG_CTRL_PROMISC (0x1 << 1) /* Enable Promisc mode */ +#define NFP_NET_CFG_CTRL_L2BC (0x1 << 2) /* Allow L2 Broadcast */ +#define NFP_NET_CFG_CTRL_L2MC (0x1 << 3) /* Allow L2 Multicast */ +#define NFP_NET_CFG_CTRL_RXCSUM (0x1 << 4) /* Enable RX Checksum */ +#define NFP_NET_CFG_CTRL_TXCSUM (0x1 << 5) /* Enable TX Checksum */ +#define NFP_NET_CFG_CTRL_RXVLAN (0x1 << 6) /* Enable VLAN strip */ +#define NFP_NET_CFG_CTRL_TXVLAN (0x1 << 7) /* Enable VLAN insert */ +#define NFP_NET_CFG_CTRL_SCATTER (0x1 << 8) /* Scatter DMA */ +#define NFP_NET_CFG_CTRL_GATHER (0x1 << 9) /* Gather DMA */ +#define NFP_NET_CFG_CTRL_LSO (0x1 << 10) /* LSO/TSO (version 1) */ #define NFP_NET_CFG_CTRL_CTAG_FILTER (0x1 << 11) /* VLAN CTAG filtering */ -#define NFP_NET_CFG_CTRL_RINGCFG (0x1 << 16) /* Ring runtime changes */ +#define NFP_NET_CFG_CTRL_RINGCFG (0x1 << 16) /* Ring runtime changes */ #define NFP_NET_CFG_CTRL_RSS (0x1 << 17) /* RSS (version 1) */ -#define NFP_NET_CFG_CTRL_IRQMOD (0x1 << 18) /* Interrupt moderation */ -#define NFP_NET_CFG_CTRL_RINGPRIO (0x1 << 19) /* Ring priorities */ -#define NFP_NET_CFG_CTRL_MSIXAUTO (0x1 << 20) /* MSI-X auto-masking */ -#define NFP_NET_CFG_CTRL_TXRWB (0x1 << 21) /* Write-back of TX ring*/ -#define NFP_NET_CFG_CTRL_L2SWITCH (0x1 << 22) /* L2 Switch */ +#define NFP_NET_CFG_CTRL_IRQMOD (0x1 << 18) /* Interrupt moderation */ +#define NFP_NET_CFG_CTRL_RINGPRIO (0x1 << 19) /* Ring priorities */ +#define NFP_NET_CFG_CTRL_MSIXAUTO (0x1 << 20) /* MSI-X auto-masking */ +#define NFP_NET_CFG_CTRL_TXRWB (0x1 << 21) /* Write-back of TX ring*/ +#define NFP_NET_CFG_CTRL_L2SWITCH (0x1 << 22) /* L2 Switch */ #define NFP_NET_CFG_CTRL_L2SWITCH_LOCAL (0x1 << 23) /* Switch to local */ #define NFP_NET_CFG_CTRL_VXLAN (0x1 << 24) /* VXLAN tunnel support */ #define NFP_NET_CFG_CTRL_NVGRE (0x1 << 25) /* NVGRE tunnel support */ @@ -152,35 +152,35 @@ #define NFP_NET_CFG_CTRL_CHAIN_META (NFP_NET_CFG_CTRL_RSS2 | \ NFP_NET_CFG_CTRL_CSUM_COMPLETE) -#define NFP_NET_CFG_UPDATE 0x0004 -#define NFP_NET_CFG_UPDATE_GEN (0x1 << 0) /* General update */ -#define NFP_NET_CFG_UPDATE_RING (0x1 << 1) /* Ring config change */ -#define NFP_NET_CFG_UPDATE_RSS (0x1 << 2) /* RSS config change */ -#define NFP_NET_CFG_UPDATE_TXRPRIO (0x1 << 3) /* TX Ring prio change */ -#define NFP_NET_CFG_UPDATE_RXRPRIO (0x1 << 4) /* RX Ring prio change */ -#define NFP_NET_CFG_UPDATE_MSIX (0x1 << 5) /* MSI-X change */ -#define NFP_NET_CFG_UPDATE_L2SWITCH (0x1 << 6) /* Switch changes */ -#define NFP_NET_CFG_UPDATE_RESET (0x1 << 7) /* Update due to FLR */ -#define NFP_NET_CFG_UPDATE_IRQMOD (0x1 << 8) /* IRQ mod change */ +#define NFP_NET_CFG_UPDATE 0x0004 +#define NFP_NET_CFG_UPDATE_GEN (0x1 << 0) /* General update */ +#define NFP_NET_CFG_UPDATE_RING (0x1 << 1) /* Ring config change */ +#define NFP_NET_CFG_UPDATE_RSS (0x1 << 2) /* RSS config change */ +#define NFP_NET_CFG_UPDATE_TXRPRIO (0x1 << 3) /* TX Ring prio change */ +#define NFP_NET_CFG_UPDATE_RXRPRIO (0x1 << 4) /* RX Ring prio change */ +#define NFP_NET_CFG_UPDATE_MSIX (0x1 << 5) /* MSI-X change */ +#define NFP_NET_CFG_UPDATE_L2SWITCH (0x1 << 6) /* Switch changes */ +#define NFP_NET_CFG_UPDATE_RESET (0x1 << 7) /* Update due to FLR */ +#define NFP_NET_CFG_UPDATE_IRQMOD (0x1 << 8) /* IRQ mod change */ #define NFP_NET_CFG_UPDATE_VXLAN (0x1 << 9) /* VXLAN port change */ #define NFP_NET_CFG_UPDATE_BPF (0x1 << 10) /* BPF program load */ #define NFP_NET_CFG_UPDATE_MACADDR (0x1 << 11) /* MAC address change */ #define NFP_NET_CFG_UPDATE_MBOX (0x1 << 12) /* Mailbox update */ #define NFP_NET_CFG_UPDATE_VF (0x1 << 13) /* VF settings change */ -#define NFP_NET_CFG_UPDATE_ERR (0x1 << 31) /* A error occurred */ -#define NFP_NET_CFG_TXRS_ENABLE 0x0008 -#define NFP_NET_CFG_RXRS_ENABLE 0x0010 -#define NFP_NET_CFG_MTU 0x0018 -#define NFP_NET_CFG_FLBUFSZ 0x001c -#define NFP_NET_CFG_EXN 0x001f -#define NFP_NET_CFG_LSC 0x0020 -#define NFP_NET_CFG_MACADDR 0x0024 +#define NFP_NET_CFG_UPDATE_ERR (0x1 << 31) /* A error occurred */ +#define NFP_NET_CFG_TXRS_ENABLE 0x0008 +#define NFP_NET_CFG_RXRS_ENABLE 0x0010 +#define NFP_NET_CFG_MTU 0x0018 +#define NFP_NET_CFG_FLBUFSZ 0x001c +#define NFP_NET_CFG_EXN 0x001f +#define NFP_NET_CFG_LSC 0x0020 +#define NFP_NET_CFG_MACADDR 0x0024 /** * Read-only words (0x0030 - 0x0050): * %NFP_NET_CFG_VERSION: Firmware version number - * %NFP_NET_CFG_STS: Status - * %NFP_NET_CFG_CAP: Capabilities (same bits as %NFP_NET_CFG_CTRL) + * %NFP_NET_CFG_STS: Status + * %NFP_NET_CFG_CAP: Capabilities (same bits as %NFP_NET_CFG_CTRL) * %NFP_NET_CFG_MAX_TXRINGS: Maximum number of TX rings * %NFP_NET_CFG_MAX_RXRINGS: Maximum number of RX rings * %NFP_NET_CFG_MAX_MTU: Maximum support MTU @@ -190,37 +190,37 @@ * TODO: * - define more STS bits */ -#define NFP_NET_CFG_VERSION 0x0030 +#define NFP_NET_CFG_VERSION 0x0030 #define NFP_NET_CFG_VERSION_RESERVED_MASK (0xff << 24) #define NFP_NET_CFG_VERSION_CLASS_MASK (0xff << 16) -#define NFP_NET_CFG_VERSION_CLASS(x) (((x) & 0xff) << 16) +#define NFP_NET_CFG_VERSION_CLASS(x) (((x) & 0xff) << 16) #define NFP_NET_CFG_VERSION_CLASS_GENERIC 0 #define NFP_NET_CFG_VERSION_MAJOR_MASK (0xff << 8) -#define NFP_NET_CFG_VERSION_MAJOR(x) (((x) & 0xff) << 8) +#define NFP_NET_CFG_VERSION_MAJOR(x) (((x) & 0xff) << 8) #define NFP_NET_CFG_VERSION_MINOR_MASK (0xff << 0) -#define NFP_NET_CFG_VERSION_MINOR(x) (((x) & 0xff) << 0) -#define NFP_NET_CFG_STS 0x0034 -#define NFP_NET_CFG_STS_LINK (0x1 << 0) /* Link up or down */ +#define NFP_NET_CFG_VERSION_MINOR(x) (((x) & 0xff) << 0) +#define NFP_NET_CFG_STS 0x0034 +#define NFP_NET_CFG_STS_LINK (0x1 << 0) /* Link up or down */ /* Link rate */ #define NFP_NET_CFG_STS_LINK_RATE_SHIFT 1 #define NFP_NET_CFG_STS_LINK_RATE_MASK 0xF -#define NFP_NET_CFG_STS_LINK_RATE \ +#define NFP_NET_CFG_STS_LINK_RATE \ (NFP_NET_CFG_STS_LINK_RATE_MASK << NFP_NET_CFG_STS_LINK_RATE_SHIFT) #define NFP_NET_CFG_STS_LINK_RATE_UNSUPPORTED 0 -#define NFP_NET_CFG_STS_LINK_RATE_UNKNOWN 1 -#define NFP_NET_CFG_STS_LINK_RATE_1G 2 -#define NFP_NET_CFG_STS_LINK_RATE_10G 3 -#define NFP_NET_CFG_STS_LINK_RATE_25G 4 -#define NFP_NET_CFG_STS_LINK_RATE_40G 5 -#define NFP_NET_CFG_STS_LINK_RATE_50G 6 -#define NFP_NET_CFG_STS_LINK_RATE_100G 7 -#define NFP_NET_CFG_CAP 0x0038 -#define NFP_NET_CFG_MAX_TXRINGS 0x003c -#define NFP_NET_CFG_MAX_RXRINGS 0x0040 -#define NFP_NET_CFG_MAX_MTU 0x0044 +#define NFP_NET_CFG_STS_LINK_RATE_UNKNOWN 1 +#define NFP_NET_CFG_STS_LINK_RATE_1G 2 +#define NFP_NET_CFG_STS_LINK_RATE_10G 3 +#define NFP_NET_CFG_STS_LINK_RATE_25G 4 +#define NFP_NET_CFG_STS_LINK_RATE_40G 5 +#define NFP_NET_CFG_STS_LINK_RATE_50G 6 +#define NFP_NET_CFG_STS_LINK_RATE_100G 7 +#define NFP_NET_CFG_CAP 0x0038 +#define NFP_NET_CFG_MAX_TXRINGS 0x003c +#define NFP_NET_CFG_MAX_RXRINGS 0x0040 +#define NFP_NET_CFG_MAX_MTU 0x0044 /* Next two words are being used by VFs for solving THB350 issue */ -#define NFP_NET_CFG_START_TXQ 0x0048 -#define NFP_NET_CFG_START_RXQ 0x004c +#define NFP_NET_CFG_START_TXQ 0x0048 +#define NFP_NET_CFG_START_RXQ 0x004c /** * Prepend configuration @@ -280,8 +280,8 @@ /** * 40B reserved for future use (0x0098 - 0x00c0) */ -#define NFP_NET_CFG_RESERVED 0x0098 -#define NFP_NET_CFG_RESERVED_SZ 0x0028 +#define NFP_NET_CFG_RESERVED 0x0098 +#define NFP_NET_CFG_RESERVED_SZ 0x0028 /** * RSS configuration (0x0100 - 0x01ac): @@ -290,26 +290,26 @@ * %NFP_NET_CFG_RSS_KEY: RSS "secret" key * %NFP_NET_CFG_RSS_ITBL: RSS indirection table */ -#define NFP_NET_CFG_RSS_BASE 0x0100 -#define NFP_NET_CFG_RSS_CTRL NFP_NET_CFG_RSS_BASE -#define NFP_NET_CFG_RSS_MASK (0x7f) -#define NFP_NET_CFG_RSS_MASK_of(_x) ((_x) & 0x7f) -#define NFP_NET_CFG_RSS_IPV4 (1 << 8) /* RSS for IPv4 */ -#define NFP_NET_CFG_RSS_IPV6 (1 << 9) /* RSS for IPv6 */ -#define NFP_NET_CFG_RSS_IPV4_TCP (1 << 10) /* RSS for IPv4/TCP */ -#define NFP_NET_CFG_RSS_IPV4_UDP (1 << 11) /* RSS for IPv4/UDP */ -#define NFP_NET_CFG_RSS_IPV6_TCP (1 << 12) /* RSS for IPv6/TCP */ -#define NFP_NET_CFG_RSS_IPV6_UDP (1 << 13) /* RSS for IPv6/UDP */ +#define NFP_NET_CFG_RSS_BASE 0x0100 +#define NFP_NET_CFG_RSS_CTRL NFP_NET_CFG_RSS_BASE +#define NFP_NET_CFG_RSS_MASK (0x7f) +#define NFP_NET_CFG_RSS_MASK_of(_x) ((_x) & 0x7f) +#define NFP_NET_CFG_RSS_IPV4 (1 << 8) /* RSS for IPv4 */ +#define NFP_NET_CFG_RSS_IPV6 (1 << 9) /* RSS for IPv6 */ +#define NFP_NET_CFG_RSS_IPV4_TCP (1 << 10) /* RSS for IPv4/TCP */ +#define NFP_NET_CFG_RSS_IPV4_UDP (1 << 11) /* RSS for IPv4/UDP */ +#define NFP_NET_CFG_RSS_IPV6_TCP (1 << 12) /* RSS for IPv6/TCP */ +#define NFP_NET_CFG_RSS_IPV6_UDP (1 << 13) /* RSS for IPv6/UDP */ #define NFP_NET_CFG_RSS_HFUNC 0xff000000 -#define NFP_NET_CFG_RSS_TOEPLITZ (1 << 24) /* Use Toeplitz hash */ +#define NFP_NET_CFG_RSS_TOEPLITZ (1 << 24) /* Use Toeplitz hash */ #define NFP_NET_CFG_RSS_XOR (1 << 25) /* Use XOR as hash */ #define NFP_NET_CFG_RSS_CRC32 (1 << 26) /* Use CRC32 as hash */ #define NFP_NET_CFG_RSS_HFUNCS 3 -#define NFP_NET_CFG_RSS_KEY (NFP_NET_CFG_RSS_BASE + 0x4) -#define NFP_NET_CFG_RSS_KEY_SZ 0x28 -#define NFP_NET_CFG_RSS_ITBL (NFP_NET_CFG_RSS_BASE + 0x4 + \ +#define NFP_NET_CFG_RSS_KEY (NFP_NET_CFG_RSS_BASE + 0x4) +#define NFP_NET_CFG_RSS_KEY_SZ 0x28 +#define NFP_NET_CFG_RSS_ITBL (NFP_NET_CFG_RSS_BASE + 0x4 + \ NFP_NET_CFG_RSS_KEY_SZ) -#define NFP_NET_CFG_RSS_ITBL_SZ 0x80 +#define NFP_NET_CFG_RSS_ITBL_SZ 0x80 /** * TX ring configuration (0x200 - 0x800) @@ -321,13 +321,13 @@ * %NFP_NET_CFG_TXR_PRIO: Per TX ring priority (1B entries) * %NFP_NET_CFG_TXR_IRQ_MOD: Per TX ring interrupt moderation packet */ -#define NFP_NET_CFG_TXR_BASE 0x0200 -#define NFP_NET_CFG_TXR_ADDR(_x) (NFP_NET_CFG_TXR_BASE + ((_x) * 0x8)) -#define NFP_NET_CFG_TXR_WB_ADDR(_x) (NFP_NET_CFG_TXR_BASE + 0x200 + \ +#define NFP_NET_CFG_TXR_BASE 0x0200 +#define NFP_NET_CFG_TXR_ADDR(_x) (NFP_NET_CFG_TXR_BASE + ((_x) * 0x8)) +#define NFP_NET_CFG_TXR_WB_ADDR(_x) (NFP_NET_CFG_TXR_BASE + 0x200 + \ ((_x) * 0x8)) -#define NFP_NET_CFG_TXR_SZ(_x) (NFP_NET_CFG_TXR_BASE + 0x400 + (_x)) -#define NFP_NET_CFG_TXR_VEC(_x) (NFP_NET_CFG_TXR_BASE + 0x440 + (_x)) -#define NFP_NET_CFG_TXR_PRIO(_x) (NFP_NET_CFG_TXR_BASE + 0x480 + (_x)) +#define NFP_NET_CFG_TXR_SZ(_x) (NFP_NET_CFG_TXR_BASE + 0x400 + (_x)) +#define NFP_NET_CFG_TXR_VEC(_x) (NFP_NET_CFG_TXR_BASE + 0x440 + (_x)) +#define NFP_NET_CFG_TXR_PRIO(_x) (NFP_NET_CFG_TXR_BASE + 0x480 + (_x)) #define NFP_NET_CFG_TXR_IRQ_MOD(_x) (NFP_NET_CFG_TXR_BASE + 0x500 + \ ((_x) * 0x4)) @@ -340,11 +340,11 @@ * %NFP_NET_CFG_RXR_PRIO: Per RX ring priority (1B entries) * %NFP_NET_CFG_RXR_IRQ_MOD: Per RX ring interrupt moderation (4B entries) */ -#define NFP_NET_CFG_RXR_BASE 0x0800 -#define NFP_NET_CFG_RXR_ADDR(_x) (NFP_NET_CFG_RXR_BASE + ((_x) * 0x8)) -#define NFP_NET_CFG_RXR_SZ(_x) (NFP_NET_CFG_RXR_BASE + 0x200 + (_x)) -#define NFP_NET_CFG_RXR_VEC(_x) (NFP_NET_CFG_RXR_BASE + 0x240 + (_x)) -#define NFP_NET_CFG_RXR_PRIO(_x) (NFP_NET_CFG_RXR_BASE + 0x280 + (_x)) +#define NFP_NET_CFG_RXR_BASE 0x0800 +#define NFP_NET_CFG_RXR_ADDR(_x) (NFP_NET_CFG_RXR_BASE + ((_x) * 0x8)) +#define NFP_NET_CFG_RXR_SZ(_x) (NFP_NET_CFG_RXR_BASE + 0x200 + (_x)) +#define NFP_NET_CFG_RXR_VEC(_x) (NFP_NET_CFG_RXR_BASE + 0x240 + (_x)) +#define NFP_NET_CFG_RXR_PRIO(_x) (NFP_NET_CFG_RXR_BASE + 0x280 + (_x)) #define NFP_NET_CFG_RXR_IRQ_MOD(_x) (NFP_NET_CFG_RXR_BASE + 0x300 + \ ((_x) * 0x4)) @@ -358,36 +358,36 @@ * the MSI-X entry and the host driver must clear the register to * re-enable the interrupt. */ -#define NFP_NET_CFG_ICR_BASE 0x0c00 -#define NFP_NET_CFG_ICR(_x) (NFP_NET_CFG_ICR_BASE + (_x)) -#define NFP_NET_CFG_ICR_UNMASKED 0x0 -#define NFP_NET_CFG_ICR_RXTX 0x1 -#define NFP_NET_CFG_ICR_LSC 0x2 +#define NFP_NET_CFG_ICR_BASE 0x0c00 +#define NFP_NET_CFG_ICR(_x) (NFP_NET_CFG_ICR_BASE + (_x)) +#define NFP_NET_CFG_ICR_UNMASKED 0x0 +#define NFP_NET_CFG_ICR_RXTX 0x1 +#define NFP_NET_CFG_ICR_LSC 0x2 /** * General device stats (0x0d00 - 0x0d90) * all counters are 64bit. */ -#define NFP_NET_CFG_STATS_BASE 0x0d00 -#define NFP_NET_CFG_STATS_RX_DISCARDS (NFP_NET_CFG_STATS_BASE + 0x00) -#define NFP_NET_CFG_STATS_RX_ERRORS (NFP_NET_CFG_STATS_BASE + 0x08) -#define NFP_NET_CFG_STATS_RX_OCTETS (NFP_NET_CFG_STATS_BASE + 0x10) -#define NFP_NET_CFG_STATS_RX_UC_OCTETS (NFP_NET_CFG_STATS_BASE + 0x18) -#define NFP_NET_CFG_STATS_RX_MC_OCTETS (NFP_NET_CFG_STATS_BASE + 0x20) -#define NFP_NET_CFG_STATS_RX_BC_OCTETS (NFP_NET_CFG_STATS_BASE + 0x28) -#define NFP_NET_CFG_STATS_RX_FRAMES (NFP_NET_CFG_STATS_BASE + 0x30) -#define NFP_NET_CFG_STATS_RX_MC_FRAMES (NFP_NET_CFG_STATS_BASE + 0x38) -#define NFP_NET_CFG_STATS_RX_BC_FRAMES (NFP_NET_CFG_STATS_BASE + 0x40) - -#define NFP_NET_CFG_STATS_TX_DISCARDS (NFP_NET_CFG_STATS_BASE + 0x48) -#define NFP_NET_CFG_STATS_TX_ERRORS (NFP_NET_CFG_STATS_BASE + 0x50) -#define NFP_NET_CFG_STATS_TX_OCTETS (NFP_NET_CFG_STATS_BASE + 0x58) -#define NFP_NET_CFG_STATS_TX_UC_OCTETS (NFP_NET_CFG_STATS_BASE + 0x60) -#define NFP_NET_CFG_STATS_TX_MC_OCTETS (NFP_NET_CFG_STATS_BASE + 0x68) -#define NFP_NET_CFG_STATS_TX_BC_OCTETS (NFP_NET_CFG_STATS_BASE + 0x70) -#define NFP_NET_CFG_STATS_TX_FRAMES (NFP_NET_CFG_STATS_BASE + 0x78) -#define NFP_NET_CFG_STATS_TX_MC_FRAMES (NFP_NET_CFG_STATS_BASE + 0x80) -#define NFP_NET_CFG_STATS_TX_BC_FRAMES (NFP_NET_CFG_STATS_BASE + 0x88) +#define NFP_NET_CFG_STATS_BASE 0x0d00 +#define NFP_NET_CFG_STATS_RX_DISCARDS (NFP_NET_CFG_STATS_BASE + 0x00) +#define NFP_NET_CFG_STATS_RX_ERRORS (NFP_NET_CFG_STATS_BASE + 0x08) +#define NFP_NET_CFG_STATS_RX_OCTETS (NFP_NET_CFG_STATS_BASE + 0x10) +#define NFP_NET_CFG_STATS_RX_UC_OCTETS (NFP_NET_CFG_STATS_BASE + 0x18) +#define NFP_NET_CFG_STATS_RX_MC_OCTETS (NFP_NET_CFG_STATS_BASE + 0x20) +#define NFP_NET_CFG_STATS_RX_BC_OCTETS (NFP_NET_CFG_STATS_BASE + 0x28) +#define NFP_NET_CFG_STATS_RX_FRAMES (NFP_NET_CFG_STATS_BASE + 0x30) +#define NFP_NET_CFG_STATS_RX_MC_FRAMES (NFP_NET_CFG_STATS_BASE + 0x38) +#define NFP_NET_CFG_STATS_RX_BC_FRAMES (NFP_NET_CFG_STATS_BASE + 0x40) + +#define NFP_NET_CFG_STATS_TX_DISCARDS (NFP_NET_CFG_STATS_BASE + 0x48) +#define NFP_NET_CFG_STATS_TX_ERRORS (NFP_NET_CFG_STATS_BASE + 0x50) +#define NFP_NET_CFG_STATS_TX_OCTETS (NFP_NET_CFG_STATS_BASE + 0x58) +#define NFP_NET_CFG_STATS_TX_UC_OCTETS (NFP_NET_CFG_STATS_BASE + 0x60) +#define NFP_NET_CFG_STATS_TX_MC_OCTETS (NFP_NET_CFG_STATS_BASE + 0x68) +#define NFP_NET_CFG_STATS_TX_BC_OCTETS (NFP_NET_CFG_STATS_BASE + 0x70) +#define NFP_NET_CFG_STATS_TX_FRAMES (NFP_NET_CFG_STATS_BASE + 0x78) +#define NFP_NET_CFG_STATS_TX_MC_FRAMES (NFP_NET_CFG_STATS_BASE + 0x80) +#define NFP_NET_CFG_STATS_TX_BC_FRAMES (NFP_NET_CFG_STATS_BASE + 0x88) #define NFP_NET_CFG_STATS_APP0_FRAMES (NFP_NET_CFG_STATS_BASE + 0x90) #define NFP_NET_CFG_STATS_APP0_BYTES (NFP_NET_CFG_STATS_BASE + 0x98) @@ -404,11 +404,11 @@ * %NFP_NET_CFG_TXR_STATS: TX ring statistics (Packet and Byte count) * %NFP_NET_CFG_RXR_STATS: RX ring statistics (Packet and Byte count) */ -#define NFP_NET_CFG_TXR_STATS_BASE 0x1000 -#define NFP_NET_CFG_TXR_STATS(_x) (NFP_NET_CFG_TXR_STATS_BASE + \ +#define NFP_NET_CFG_TXR_STATS_BASE 0x1000 +#define NFP_NET_CFG_TXR_STATS(_x) (NFP_NET_CFG_TXR_STATS_BASE + \ ((_x) * 0x10)) -#define NFP_NET_CFG_RXR_STATS_BASE 0x1400 -#define NFP_NET_CFG_RXR_STATS(_x) (NFP_NET_CFG_RXR_STATS_BASE + \ +#define NFP_NET_CFG_RXR_STATS_BASE 0x1400 +#define NFP_NET_CFG_RXR_STATS(_x) (NFP_NET_CFG_RXR_STATS_BASE + \ ((_x) * 0x10)) /** @@ -444,7 +444,7 @@ * %NFP_NET_CFG_TLV_TYPE: Offset of type within the TLV * %NFP_NET_CFG_TLV_TYPE_REQUIRED: Driver must be able to parse the TLV * %NFP_NET_CFG_TLV_LENGTH: Offset of length within the TLV - * %NFP_NET_CFG_TLV_LENGTH_INC: TLV length increments + * %NFP_NET_CFG_TLV_LENGTH_INC: TLV length increments * %NFP_NET_CFG_TLV_VALUE: Offset of value with the TLV * * List of simple TLV structures, first one starts at %NFP_NET_CFG_TLV_BASE. @@ -457,12 +457,12 @@ * Note that the 4 byte TLV header is not counted in %NFP_NET_CFG_TLV_LENGTH. */ #define NFP_NET_CFG_TLV_TYPE 0x00 -#define NFP_NET_CFG_TLV_TYPE_REQUIRED 0x8000 +#define NFP_NET_CFG_TLV_TYPE_REQUIRED 0x8000 #define NFP_NET_CFG_TLV_LENGTH 0x02 #define NFP_NET_CFG_TLV_LENGTH_INC 4 #define NFP_NET_CFG_TLV_VALUE 0x04 -#define NFP_NET_CFG_TLV_HEADER_REQUIRED 0x80000000 +#define NFP_NET_CFG_TLV_HEADER_REQUIRED 0x80000000 #define NFP_NET_CFG_TLV_HEADER_TYPE 0x7fff0000 #define NFP_NET_CFG_TLV_HEADER_LENGTH 0x0000ffff diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/Makefile b/drivers/net/ethernet/netronome/nfp/nfpcore/Makefile new file mode 100644 index 000000000000..805fa28f391a --- /dev/null +++ b/drivers/net/ethernet/netronome/nfp/nfpcore/Makefile @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0 +# kbuild requires Makefile in a directory to build individual objects diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp6000/Makefile b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp6000/Makefile new file mode 100644 index 000000000000..805fa28f391a --- /dev/null +++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp6000/Makefile @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0 +# kbuild requires Makefile in a directory to build individual objects diff --git a/drivers/net/ethernet/netronome/nfp/nic/Makefile b/drivers/net/ethernet/netronome/nfp/nic/Makefile new file mode 100644 index 000000000000..805fa28f391a --- /dev/null +++ b/drivers/net/ethernet/netronome/nfp/nic/Makefile @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0 +# kbuild requires Makefile in a directory to build individual objects diff --git a/drivers/net/ethernet/qlogic/qed/qed_iwarp.c b/drivers/net/ethernet/qlogic/qed/qed_iwarp.c index ca4a81dc1ace..03ad4eeac7f8 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_iwarp.c +++ b/drivers/net/ethernet/qlogic/qed/qed_iwarp.c @@ -1784,7 +1784,7 @@ enum qed_iwarp_mpa_pkt_type { /* fpdu can be fragmented over maximum 3 bds: header, partial mpa, unaligned */ #define QED_IWARP_MAX_BDS_PER_FPDU 3 -char *pkt_type_str[] = { +static const char * const pkt_type_str[] = { "QED_IWARP_MPA_PKT_PACKED", "QED_IWARP_MPA_PKT_PARTIAL", "QED_IWARP_MPA_PKT_UNALIGNED" diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c index 0bf7d1759250..7055db161b1b 100644 --- a/drivers/net/ethernet/realtek/r8169.c +++ b/drivers/net/ethernet/realtek/r8169.c @@ -99,12 +99,12 @@ static const int multicast_filter_limit = 32; #define RTL8169_PHY_TIMEOUT (10*HZ) /* write/read MMIO register */ -#define RTL_W8(reg, val8) writeb ((val8), ioaddr + (reg)) -#define RTL_W16(reg, val16) writew ((val16), ioaddr + (reg)) -#define RTL_W32(reg, val32) writel ((val32), ioaddr + (reg)) -#define RTL_R8(reg) readb (ioaddr + (reg)) -#define RTL_R16(reg) readw (ioaddr + (reg)) -#define RTL_R32(reg) readl (ioaddr + (reg)) +#define RTL_W8(tp, reg, val8) writeb((val8), tp->mmio_addr + (reg)) +#define RTL_W16(tp, reg, val16) writew((val16), tp->mmio_addr + (reg)) +#define RTL_W32(tp, reg, val32) writel((val32), tp->mmio_addr + (reg)) +#define RTL_R8(tp, reg) readb(tp->mmio_addr + (reg)) +#define RTL_R16(tp, reg) readw(tp->mmio_addr + (reg)) +#define RTL_R32(tp, reg) readl(tp->mmio_addr + (reg)) enum mac_version { RTL_GIGA_MAC_VER_01 = 0, @@ -735,12 +735,6 @@ struct ring_info { u8 __pad[sizeof(void *) - sizeof(u32)]; }; -enum features { - RTL_FEATURE_WOL = (1 << 0), - RTL_FEATURE_MSI = (1 << 1), - RTL_FEATURE_GMII = (1 << 2), -}; - struct rtl8169_counters { __le64 tx_packets; __le64 rx_packets; @@ -829,7 +823,7 @@ struct rtl8169_private { void (*phy_reset_enable)(struct rtl8169_private *tp); void (*hw_start)(struct net_device *); unsigned int (*phy_reset_pending)(struct rtl8169_private *tp); - unsigned int (*link_ok)(void __iomem *); + unsigned int (*link_ok)(struct rtl8169_private *tp); int (*do_ioctl)(struct rtl8169_private *tp, struct mii_ioctl_data *data, int cmd); bool (*tso_csum)(struct rtl8169_private *, struct sk_buff *, u32 *); @@ -984,56 +978,46 @@ static bool rtl_ocp_reg_failure(struct rtl8169_private *tp, u32 reg) DECLARE_RTL_COND(rtl_ocp_gphy_cond) { - void __iomem *ioaddr = tp->mmio_addr; - - return RTL_R32(GPHY_OCP) & OCPAR_FLAG; + return RTL_R32(tp, GPHY_OCP) & OCPAR_FLAG; } static void r8168_phy_ocp_write(struct rtl8169_private *tp, u32 reg, u32 data) { - void __iomem *ioaddr = tp->mmio_addr; - if (rtl_ocp_reg_failure(tp, reg)) return; - RTL_W32(GPHY_OCP, OCPAR_FLAG | (reg << 15) | data); + RTL_W32(tp, GPHY_OCP, OCPAR_FLAG | (reg << 15) | data); rtl_udelay_loop_wait_low(tp, &rtl_ocp_gphy_cond, 25, 10); } static u16 r8168_phy_ocp_read(struct rtl8169_private *tp, u32 reg) { - void __iomem *ioaddr = tp->mmio_addr; - if (rtl_ocp_reg_failure(tp, reg)) return 0; - RTL_W32(GPHY_OCP, reg << 15); + RTL_W32(tp, GPHY_OCP, reg << 15); return rtl_udelay_loop_wait_high(tp, &rtl_ocp_gphy_cond, 25, 10) ? - (RTL_R32(GPHY_OCP) & 0xffff) : ~0; + (RTL_R32(tp, GPHY_OCP) & 0xffff) : ~0; } static void r8168_mac_ocp_write(struct rtl8169_private *tp, u32 reg, u32 data) { - void __iomem *ioaddr = tp->mmio_addr; - if (rtl_ocp_reg_failure(tp, reg)) return; - RTL_W32(OCPDR, OCPAR_FLAG | (reg << 15) | data); + RTL_W32(tp, OCPDR, OCPAR_FLAG | (reg << 15) | data); } static u16 r8168_mac_ocp_read(struct rtl8169_private *tp, u32 reg) { - void __iomem *ioaddr = tp->mmio_addr; - if (rtl_ocp_reg_failure(tp, reg)) return 0; - RTL_W32(OCPDR, reg << 15); + RTL_W32(tp, OCPDR, reg << 15); - return RTL_R32(OCPDR); + return RTL_R32(tp, OCPDR); } #define OCP_STD_PHY_BASE 0xa400 @@ -1076,16 +1060,12 @@ static int mac_mcu_read(struct rtl8169_private *tp, int reg) DECLARE_RTL_COND(rtl_phyar_cond) { - void __iomem *ioaddr = tp->mmio_addr; - - return RTL_R32(PHYAR) & 0x80000000; + return RTL_R32(tp, PHYAR) & 0x80000000; } static void r8169_mdio_write(struct rtl8169_private *tp, int reg, int value) { - void __iomem *ioaddr = tp->mmio_addr; - - RTL_W32(PHYAR, 0x80000000 | (reg & 0x1f) << 16 | (value & 0xffff)); + RTL_W32(tp, PHYAR, 0x80000000 | (reg & 0x1f) << 16 | (value & 0xffff)); rtl_udelay_loop_wait_low(tp, &rtl_phyar_cond, 25, 20); /* @@ -1097,13 +1077,12 @@ static void r8169_mdio_write(struct rtl8169_private *tp, int reg, int value) static int r8169_mdio_read(struct rtl8169_private *tp, int reg) { - void __iomem *ioaddr = tp->mmio_addr; int value; - RTL_W32(PHYAR, 0x0 | (reg & 0x1f) << 16); + RTL_W32(tp, PHYAR, 0x0 | (reg & 0x1f) << 16); value = rtl_udelay_loop_wait_high(tp, &rtl_phyar_cond, 25, 20) ? - RTL_R32(PHYAR) & 0xffff : ~0; + RTL_R32(tp, PHYAR) & 0xffff : ~0; /* * According to hardware specs a 20us delay is required after read @@ -1116,18 +1095,14 @@ static int r8169_mdio_read(struct rtl8169_private *tp, int reg) DECLARE_RTL_COND(rtl_ocpar_cond) { - void __iomem *ioaddr = tp->mmio_addr; - - return RTL_R32(OCPAR) & OCPAR_FLAG; + return RTL_R32(tp, OCPAR) & OCPAR_FLAG; } static void r8168dp_1_mdio_access(struct rtl8169_private *tp, int reg, u32 data) { - void __iomem *ioaddr = tp->mmio_addr; - - RTL_W32(OCPDR, data | ((reg & OCPDR_REG_MASK) << OCPDR_GPHY_REG_SHIFT)); - RTL_W32(OCPAR, OCPAR_GPHY_WRITE_CMD); - RTL_W32(EPHY_RXER_NUM, 0); + RTL_W32(tp, OCPDR, data | ((reg & OCPDR_REG_MASK) << OCPDR_GPHY_REG_SHIFT)); + RTL_W32(tp, OCPAR, OCPAR_GPHY_WRITE_CMD); + RTL_W32(tp, EPHY_RXER_NUM, 0); rtl_udelay_loop_wait_low(tp, &rtl_ocpar_cond, 1000, 100); } @@ -1140,51 +1115,46 @@ static void r8168dp_1_mdio_write(struct rtl8169_private *tp, int reg, int value) static int r8168dp_1_mdio_read(struct rtl8169_private *tp, int reg) { - void __iomem *ioaddr = tp->mmio_addr; - r8168dp_1_mdio_access(tp, reg, OCPDR_READ_CMD); mdelay(1); - RTL_W32(OCPAR, OCPAR_GPHY_READ_CMD); - RTL_W32(EPHY_RXER_NUM, 0); + RTL_W32(tp, OCPAR, OCPAR_GPHY_READ_CMD); + RTL_W32(tp, EPHY_RXER_NUM, 0); return rtl_udelay_loop_wait_high(tp, &rtl_ocpar_cond, 1000, 100) ? - RTL_R32(OCPDR) & OCPDR_DATA_MASK : ~0; + RTL_R32(tp, OCPDR) & OCPDR_DATA_MASK : ~0; } #define R8168DP_1_MDIO_ACCESS_BIT 0x00020000 -static void r8168dp_2_mdio_start(void __iomem *ioaddr) +static void r8168dp_2_mdio_start(struct rtl8169_private *tp) { - RTL_W32(0xd0, RTL_R32(0xd0) & ~R8168DP_1_MDIO_ACCESS_BIT); + RTL_W32(tp, 0xd0, RTL_R32(tp, 0xd0) & ~R8168DP_1_MDIO_ACCESS_BIT); } -static void r8168dp_2_mdio_stop(void __iomem *ioaddr) +static void r8168dp_2_mdio_stop(struct rtl8169_private *tp) { - RTL_W32(0xd0, RTL_R32(0xd0) | R8168DP_1_MDIO_ACCESS_BIT); + RTL_W32(tp, 0xd0, RTL_R32(tp, 0xd0) | R8168DP_1_MDIO_ACCESS_BIT); } static void r8168dp_2_mdio_write(struct rtl8169_private *tp, int reg, int value) { - void __iomem *ioaddr = tp->mmio_addr; - - r8168dp_2_mdio_start(ioaddr); + r8168dp_2_mdio_start(tp); r8169_mdio_write(tp, reg, value); - r8168dp_2_mdio_stop(ioaddr); + r8168dp_2_mdio_stop(tp); } static int r8168dp_2_mdio_read(struct rtl8169_private *tp, int reg) { - void __iomem *ioaddr = tp->mmio_addr; int value; - r8168dp_2_mdio_start(ioaddr); + r8168dp_2_mdio_start(tp); value = r8169_mdio_read(tp, reg); - r8168dp_2_mdio_stop(ioaddr); + r8168dp_2_mdio_stop(tp); return value; } @@ -1229,16 +1199,12 @@ static int rtl_mdio_read(struct net_device *dev, int phy_id, int location) DECLARE_RTL_COND(rtl_ephyar_cond) { - void __iomem *ioaddr = tp->mmio_addr; - - return RTL_R32(EPHYAR) & EPHYAR_FLAG; + return RTL_R32(tp, EPHYAR) & EPHYAR_FLAG; } static void rtl_ephy_write(struct rtl8169_private *tp, int reg_addr, int value) { - void __iomem *ioaddr = tp->mmio_addr; - - RTL_W32(EPHYAR, EPHYAR_WRITE_CMD | (value & EPHYAR_DATA_MASK) | + RTL_W32(tp, EPHYAR, EPHYAR_WRITE_CMD | (value & EPHYAR_DATA_MASK) | (reg_addr & EPHYAR_REG_MASK) << EPHYAR_REG_SHIFT); rtl_udelay_loop_wait_low(tp, &rtl_ephyar_cond, 10, 100); @@ -1248,41 +1214,33 @@ static void rtl_ephy_write(struct rtl8169_private *tp, int reg_addr, int value) static u16 rtl_ephy_read(struct rtl8169_private *tp, int reg_addr) { - void __iomem *ioaddr = tp->mmio_addr; - - RTL_W32(EPHYAR, (reg_addr & EPHYAR_REG_MASK) << EPHYAR_REG_SHIFT); + RTL_W32(tp, EPHYAR, (reg_addr & EPHYAR_REG_MASK) << EPHYAR_REG_SHIFT); return rtl_udelay_loop_wait_high(tp, &rtl_ephyar_cond, 10, 100) ? - RTL_R32(EPHYAR) & EPHYAR_DATA_MASK : ~0; + RTL_R32(tp, EPHYAR) & EPHYAR_DATA_MASK : ~0; } DECLARE_RTL_COND(rtl_eriar_cond) { - void __iomem *ioaddr = tp->mmio_addr; - - return RTL_R32(ERIAR) & ERIAR_FLAG; + return RTL_R32(tp, ERIAR) & ERIAR_FLAG; } static void rtl_eri_write(struct rtl8169_private *tp, int addr, u32 mask, u32 val, int type) { - void __iomem *ioaddr = tp->mmio_addr; - BUG_ON((addr & 3) || (mask == 0)); - RTL_W32(ERIDR, val); - RTL_W32(ERIAR, ERIAR_WRITE_CMD | type | mask | addr); + RTL_W32(tp, ERIDR, val); + RTL_W32(tp, ERIAR, ERIAR_WRITE_CMD | type | mask | addr); rtl_udelay_loop_wait_low(tp, &rtl_eriar_cond, 100, 100); } static u32 rtl_eri_read(struct rtl8169_private *tp, int addr, int type) { - void __iomem *ioaddr = tp->mmio_addr; - - RTL_W32(ERIAR, ERIAR_READ_CMD | type | ERIAR_MASK_1111 | addr); + RTL_W32(tp, ERIAR, ERIAR_READ_CMD | type | ERIAR_MASK_1111 | addr); return rtl_udelay_loop_wait_high(tp, &rtl_eriar_cond, 100, 100) ? - RTL_R32(ERIDR) : ~0; + RTL_R32(tp, ERIDR) : ~0; } static void rtl_w0w1_eri(struct rtl8169_private *tp, int addr, u32 mask, u32 p, @@ -1296,11 +1254,9 @@ static void rtl_w0w1_eri(struct rtl8169_private *tp, int addr, u32 mask, u32 p, static u32 r8168dp_ocp_read(struct rtl8169_private *tp, u8 mask, u16 reg) { - void __iomem *ioaddr = tp->mmio_addr; - - RTL_W32(OCPAR, ((u32)mask & 0x0f) << 12 | (reg & 0x0fff)); + RTL_W32(tp, OCPAR, ((u32)mask & 0x0f) << 12 | (reg & 0x0fff)); return rtl_udelay_loop_wait_high(tp, &rtl_ocpar_cond, 100, 20) ? - RTL_R32(OCPDR) : ~0; + RTL_R32(tp, OCPDR) : ~0; } static u32 r8168ep_ocp_read(struct rtl8169_private *tp, u8 mask, u16 reg) @@ -1328,10 +1284,8 @@ static u32 ocp_read(struct rtl8169_private *tp, u8 mask, u16 reg) static void r8168dp_ocp_write(struct rtl8169_private *tp, u8 mask, u16 reg, u32 data) { - void __iomem *ioaddr = tp->mmio_addr; - - RTL_W32(OCPDR, data); - RTL_W32(OCPAR, OCPAR_FLAG | ((u32)mask & 0x0f) << 12 | (reg & 0x0fff)); + RTL_W32(tp, OCPDR, data); + RTL_W32(tp, OCPAR, OCPAR_FLAG | ((u32)mask & 0x0f) << 12 | (reg & 0x0fff)); rtl_udelay_loop_wait_low(tp, &rtl_ocpar_cond, 100, 20); } @@ -1393,19 +1347,15 @@ DECLARE_RTL_COND(rtl_ep_ocp_read_cond) DECLARE_RTL_COND(rtl_ocp_tx_cond) { - void __iomem *ioaddr = tp->mmio_addr; - - return RTL_R8(IBISR0) & 0x20; + return RTL_R8(tp, IBISR0) & 0x20; } static void rtl8168ep_stop_cmac(struct rtl8169_private *tp) { - void __iomem *ioaddr = tp->mmio_addr; - - RTL_W8(IBCR2, RTL_R8(IBCR2) & ~0x01); + RTL_W8(tp, IBCR2, RTL_R8(tp, IBCR2) & ~0x01); rtl_msleep_loop_wait_high(tp, &rtl_ocp_tx_cond, 50, 2000); - RTL_W8(IBISR0, RTL_R8(IBISR0) | 0x20); - RTL_W8(IBCR0, RTL_R8(IBCR0) & ~0x01); + RTL_W8(tp, IBISR0, RTL_R8(tp, IBISR0) | 0x20); + RTL_W8(tp, IBCR0, RTL_R8(tp, IBCR0) & ~0x01); } static void rtl8168dp_driver_start(struct rtl8169_private *tp) @@ -1473,19 +1423,19 @@ static void rtl8168_driver_stop(struct rtl8169_private *tp) } } -static int r8168dp_check_dash(struct rtl8169_private *tp) +static bool r8168dp_check_dash(struct rtl8169_private *tp) { u16 reg = rtl8168_get_ocp_reg(tp); - return (ocp_read(tp, 0x0f, reg) & 0x00008000) ? 1 : 0; + return !!(ocp_read(tp, 0x0f, reg) & 0x00008000); } -static int r8168ep_check_dash(struct rtl8169_private *tp) +static bool r8168ep_check_dash(struct rtl8169_private *tp) { - return (ocp_read(tp, 0x0f, 0x128) & 0x00000001) ? 1 : 0; + return !!(ocp_read(tp, 0x0f, 0x128) & 0x00000001); } -static int r8168_check_dash(struct rtl8169_private *tp) +static bool r8168_check_dash(struct rtl8169_private *tp) { switch (tp->mac_version) { case RTL_GIGA_MAC_VER_27: @@ -1497,7 +1447,7 @@ static int r8168_check_dash(struct rtl8169_private *tp) case RTL_GIGA_MAC_VER_51: return r8168ep_check_dash(tp); default: - return 0; + return false; } } @@ -1518,49 +1468,37 @@ static void rtl_write_exgmac_batch(struct rtl8169_private *tp, DECLARE_RTL_COND(rtl_efusear_cond) { - void __iomem *ioaddr = tp->mmio_addr; - - return RTL_R32(EFUSEAR) & EFUSEAR_FLAG; + return RTL_R32(tp, EFUSEAR) & EFUSEAR_FLAG; } static u8 rtl8168d_efuse_read(struct rtl8169_private *tp, int reg_addr) { - void __iomem *ioaddr = tp->mmio_addr; - - RTL_W32(EFUSEAR, (reg_addr & EFUSEAR_REG_MASK) << EFUSEAR_REG_SHIFT); + RTL_W32(tp, EFUSEAR, (reg_addr & EFUSEAR_REG_MASK) << EFUSEAR_REG_SHIFT); return rtl_udelay_loop_wait_high(tp, &rtl_efusear_cond, 100, 300) ? - RTL_R32(EFUSEAR) & EFUSEAR_DATA_MASK : ~0; + RTL_R32(tp, EFUSEAR) & EFUSEAR_DATA_MASK : ~0; } static u16 rtl_get_events(struct rtl8169_private *tp) { - void __iomem *ioaddr = tp->mmio_addr; - - return RTL_R16(IntrStatus); + return RTL_R16(tp, IntrStatus); } static void rtl_ack_events(struct rtl8169_private *tp, u16 bits) { - void __iomem *ioaddr = tp->mmio_addr; - - RTL_W16(IntrStatus, bits); + RTL_W16(tp, IntrStatus, bits); mmiowb(); } static void rtl_irq_disable(struct rtl8169_private *tp) { - void __iomem *ioaddr = tp->mmio_addr; - - RTL_W16(IntrMask, 0); + RTL_W16(tp, IntrMask, 0); mmiowb(); } static void rtl_irq_enable(struct rtl8169_private *tp, u16 bits) { - void __iomem *ioaddr = tp->mmio_addr; - - RTL_W16(IntrMask, bits); + RTL_W16(tp, IntrMask, bits); } #define RTL_EVENT_NAPI_RX (RxOK | RxErr) @@ -1574,18 +1512,14 @@ static void rtl_irq_enable_all(struct rtl8169_private *tp) static void rtl8169_irq_mask_and_ack(struct rtl8169_private *tp) { - void __iomem *ioaddr = tp->mmio_addr; - rtl_irq_disable(tp); rtl_ack_events(tp, RTL_EVENT_NAPI | tp->event_slow); - RTL_R8(ChipCmd); + RTL_R8(tp, ChipCmd); } static unsigned int rtl8169_tbi_reset_pending(struct rtl8169_private *tp) { - void __iomem *ioaddr = tp->mmio_addr; - - return RTL_R32(TBICSR) & TBIReset; + return RTL_R32(tp, TBICSR) & TBIReset; } static unsigned int rtl8169_xmii_reset_pending(struct rtl8169_private *tp) @@ -1593,21 +1527,19 @@ static unsigned int rtl8169_xmii_reset_pending(struct rtl8169_private *tp) return rtl_readphy(tp, MII_BMCR) & BMCR_RESET; } -static unsigned int rtl8169_tbi_link_ok(void __iomem *ioaddr) +static unsigned int rtl8169_tbi_link_ok(struct rtl8169_private *tp) { - return RTL_R32(TBICSR) & TBILinkOk; + return RTL_R32(tp, TBICSR) & TBILinkOk; } -static unsigned int rtl8169_xmii_link_ok(void __iomem *ioaddr) +static unsigned int rtl8169_xmii_link_ok(struct rtl8169_private *tp) { - return RTL_R8(PHYstatus) & LinkStatus; + return RTL_R8(tp, PHYstatus) & LinkStatus; } static void rtl8169_tbi_reset_enable(struct rtl8169_private *tp) { - void __iomem *ioaddr = tp->mmio_addr; - - RTL_W32(TBICSR, RTL_R32(TBICSR) | TBIReset); + RTL_W32(tp, TBICSR, RTL_R32(tp, TBICSR) | TBIReset); } static void rtl8169_xmii_reset_enable(struct rtl8169_private *tp) @@ -1620,7 +1552,6 @@ static void rtl8169_xmii_reset_enable(struct rtl8169_private *tp) static void rtl_link_chg_patch(struct rtl8169_private *tp) { - void __iomem *ioaddr = tp->mmio_addr; struct net_device *dev = tp->dev; if (!netif_running(dev)) @@ -1628,12 +1559,12 @@ static void rtl_link_chg_patch(struct rtl8169_private *tp) if (tp->mac_version == RTL_GIGA_MAC_VER_34 || tp->mac_version == RTL_GIGA_MAC_VER_38) { - if (RTL_R8(PHYstatus) & _1000bpsF) { + if (RTL_R8(tp, PHYstatus) & _1000bpsF) { rtl_eri_write(tp, 0x1bc, ERIAR_MASK_1111, 0x00000011, ERIAR_EXGMAC); rtl_eri_write(tp, 0x1dc, ERIAR_MASK_1111, 0x00000005, ERIAR_EXGMAC); - } else if (RTL_R8(PHYstatus) & _100bps) { + } else if (RTL_R8(tp, PHYstatus) & _100bps) { rtl_eri_write(tp, 0x1bc, ERIAR_MASK_1111, 0x0000001f, ERIAR_EXGMAC); rtl_eri_write(tp, 0x1dc, ERIAR_MASK_1111, 0x00000005, @@ -1651,7 +1582,7 @@ static void rtl_link_chg_patch(struct rtl8169_private *tp) ERIAR_EXGMAC); } else if (tp->mac_version == RTL_GIGA_MAC_VER_35 || tp->mac_version == RTL_GIGA_MAC_VER_36) { - if (RTL_R8(PHYstatus) & _1000bpsF) { + if (RTL_R8(tp, PHYstatus) & _1000bpsF) { rtl_eri_write(tp, 0x1bc, ERIAR_MASK_1111, 0x00000011, ERIAR_EXGMAC); rtl_eri_write(tp, 0x1dc, ERIAR_MASK_1111, 0x00000005, @@ -1663,7 +1594,7 @@ static void rtl_link_chg_patch(struct rtl8169_private *tp) ERIAR_EXGMAC); } } else if (tp->mac_version == RTL_GIGA_MAC_VER_37) { - if (RTL_R8(PHYstatus) & _10bps) { + if (RTL_R8(tp, PHYstatus) & _10bps) { rtl_eri_write(tp, 0x1d0, ERIAR_MASK_0011, 0x4d02, ERIAR_EXGMAC); rtl_eri_write(tp, 0x1dc, ERIAR_MASK_0011, 0x0060, @@ -1676,10 +1607,9 @@ static void rtl_link_chg_patch(struct rtl8169_private *tp) } static void rtl8169_check_link_status(struct net_device *dev, - struct rtl8169_private *tp, - void __iomem *ioaddr) + struct rtl8169_private *tp) { - if (tp->link_ok(ioaddr)) { + if (tp->link_ok(tp)) { rtl_link_chg_patch(tp); /* This is to cancel a scheduled suspend if there's one. */ pm_request_resume(&tp->pci_dev->dev); @@ -1697,15 +1627,14 @@ static void rtl8169_check_link_status(struct net_device *dev, static u32 __rtl8169_get_wol(struct rtl8169_private *tp) { - void __iomem *ioaddr = tp->mmio_addr; u8 options; u32 wolopts = 0; - options = RTL_R8(Config1); + options = RTL_R8(tp, Config1); if (!(options & PMEnable)) return 0; - options = RTL_R8(Config3); + options = RTL_R8(tp, Config3); if (options & LinkUp) wolopts |= WAKE_PHY; switch (tp->mac_version) { @@ -1735,7 +1664,7 @@ static u32 __rtl8169_get_wol(struct rtl8169_private *tp) break; } - options = RTL_R8(Config5); + options = RTL_R8(tp, Config5); if (options & UWF) wolopts |= WAKE_UCAST; if (options & BWF) @@ -1768,7 +1697,6 @@ static void rtl8169_get_wol(struct net_device *dev, struct ethtool_wolinfo *wol) static void __rtl8169_set_wol(struct rtl8169_private *tp, u32 wolopts) { - void __iomem *ioaddr = tp->mmio_addr; unsigned int i, tmp; static const struct { u32 opt; @@ -1784,7 +1712,7 @@ static void __rtl8169_set_wol(struct rtl8169_private *tp, u32 wolopts) }; u8 options; - RTL_W8(Cfg9346, Cfg9346_Unlock); + RTL_W8(tp, Cfg9346, Cfg9346_Unlock); switch (tp->mac_version) { case RTL_GIGA_MAC_VER_34: @@ -1826,28 +1754,28 @@ static void __rtl8169_set_wol(struct rtl8169_private *tp, u32 wolopts) } for (i = 0; i < tmp; i++) { - options = RTL_R8(cfg[i].reg) & ~cfg[i].mask; + options = RTL_R8(tp, cfg[i].reg) & ~cfg[i].mask; if (wolopts & cfg[i].opt) options |= cfg[i].mask; - RTL_W8(cfg[i].reg, options); + RTL_W8(tp, cfg[i].reg, options); } switch (tp->mac_version) { case RTL_GIGA_MAC_VER_01 ... RTL_GIGA_MAC_VER_17: - options = RTL_R8(Config1) & ~PMEnable; + options = RTL_R8(tp, Config1) & ~PMEnable; if (wolopts) options |= PMEnable; - RTL_W8(Config1, options); + RTL_W8(tp, Config1, options); break; default: - options = RTL_R8(Config2) & ~PME_SIGNAL; + options = RTL_R8(tp, Config2) & ~PME_SIGNAL; if (wolopts) options |= PME_SIGNAL; - RTL_W8(Config2, options); + RTL_W8(tp, Config2, options); break; } - RTL_W8(Cfg9346, Cfg9346_Lock); + RTL_W8(tp, Cfg9346, Cfg9346_Lock); } static int rtl8169_set_wol(struct net_device *dev, struct ethtool_wolinfo *wol) @@ -1859,10 +1787,6 @@ static int rtl8169_set_wol(struct net_device *dev, struct ethtool_wolinfo *wol) rtl_lock_work(tp); - if (wol->wolopts) - tp->features |= RTL_FEATURE_WOL; - else - tp->features &= ~RTL_FEATURE_WOL; if (pm_runtime_active(d)) __rtl8169_set_wol(tp, wol->wolopts); else @@ -1906,16 +1830,15 @@ static int rtl8169_set_speed_tbi(struct net_device *dev, u8 autoneg, u16 speed, u8 duplex, u32 ignored) { struct rtl8169_private *tp = netdev_priv(dev); - void __iomem *ioaddr = tp->mmio_addr; int ret = 0; u32 reg; - reg = RTL_R32(TBICSR); + reg = RTL_R32(tp, TBICSR); if ((autoneg == AUTONEG_DISABLE) && (speed == SPEED_1000) && (duplex == DUPLEX_FULL)) { - RTL_W32(TBICSR, reg & ~(TBINwEnable | TBINwRestart)); + RTL_W32(tp, TBICSR, reg & ~(TBINwEnable | TBINwRestart)); } else if (autoneg == AUTONEG_ENABLE) - RTL_W32(TBICSR, reg | TBINwEnable | TBINwRestart); + RTL_W32(tp, TBICSR, reg | TBINwEnable | TBINwRestart); else { netif_warn(tp, link, dev, "incorrect speed setting refused in TBI mode\n"); @@ -2040,16 +1963,15 @@ static void __rtl8169_set_features(struct net_device *dev, netdev_features_t features) { struct rtl8169_private *tp = netdev_priv(dev); - void __iomem *ioaddr = tp->mmio_addr; u32 rx_config; - rx_config = RTL_R32(RxConfig); + rx_config = RTL_R32(tp, RxConfig); if (features & NETIF_F_RXALL) rx_config |= (AcceptErr | AcceptRunt); else rx_config &= ~(AcceptErr | AcceptRunt); - RTL_W32(RxConfig, rx_config); + RTL_W32(tp, RxConfig, rx_config); if (features & NETIF_F_RXCSUM) tp->cp_cmd |= RxChkSum; @@ -2061,10 +1983,10 @@ static void __rtl8169_set_features(struct net_device *dev, else tp->cp_cmd &= ~RxVlan; - tp->cp_cmd |= RTL_R16(CPlusCmd) & ~(RxVlan | RxChkSum); + tp->cp_cmd |= RTL_R16(tp, CPlusCmd) & ~(RxVlan | RxChkSum); - RTL_W16(CPlusCmd, tp->cp_cmd); - RTL_R16(CPlusCmd); + RTL_W16(tp, CPlusCmd, tp->cp_cmd); + RTL_R16(tp, CPlusCmd); } static int rtl8169_set_features(struct net_device *dev, @@ -2101,7 +2023,6 @@ static int rtl8169_get_link_ksettings_tbi(struct net_device *dev, struct ethtool_link_ksettings *cmd) { struct rtl8169_private *tp = netdev_priv(dev); - void __iomem *ioaddr = tp->mmio_addr; u32 status; u32 supported, advertising; @@ -2109,7 +2030,7 @@ static int rtl8169_get_link_ksettings_tbi(struct net_device *dev, SUPPORTED_1000baseT_Full | SUPPORTED_Autoneg | SUPPORTED_FIBRE; cmd->base.port = PORT_FIBRE; - status = RTL_R32(TBICSR); + status = RTL_R32(tp, TBICSR); advertising = (status & TBINwEnable) ? ADVERTISED_Autoneg : 0; cmd->base.autoneg = !!(status & TBINwEnable); @@ -2224,23 +2145,20 @@ static int rtl8169_get_sset_count(struct net_device *dev, int sset) DECLARE_RTL_COND(rtl_counters_cond) { - void __iomem *ioaddr = tp->mmio_addr; - - return RTL_R32(CounterAddrLow) & (CounterReset | CounterDump); + return RTL_R32(tp, CounterAddrLow) & (CounterReset | CounterDump); } static bool rtl8169_do_counters(struct net_device *dev, u32 counter_cmd) { struct rtl8169_private *tp = netdev_priv(dev); - void __iomem *ioaddr = tp->mmio_addr; dma_addr_t paddr = tp->counters_phys_addr; u32 cmd; - RTL_W32(CounterAddrHigh, (u64)paddr >> 32); - RTL_R32(CounterAddrHigh); + RTL_W32(tp, CounterAddrHigh, (u64)paddr >> 32); + RTL_R32(tp, CounterAddrHigh); cmd = (u64)paddr & DMA_BIT_MASK(32); - RTL_W32(CounterAddrLow, cmd); - RTL_W32(CounterAddrLow, cmd | counter_cmd); + RTL_W32(tp, CounterAddrLow, cmd); + RTL_W32(tp, CounterAddrLow, cmd | counter_cmd); return rtl_udelay_loop_wait_low(tp, &rtl_counters_cond, 10, 1000); } @@ -2262,13 +2180,12 @@ static bool rtl8169_reset_counters(struct net_device *dev) static bool rtl8169_update_counters(struct net_device *dev) { struct rtl8169_private *tp = netdev_priv(dev); - void __iomem *ioaddr = tp->mmio_addr; /* * Some chips are unable to dump tally counters when the receiver * is disabled. */ - if ((RTL_R8(ChipCmd) & CmdRxEnb) == 0) + if ((RTL_R8(tp, ChipCmd) & CmdRxEnb) == 0) return true; return rtl8169_do_counters(dev, CounterDump); @@ -2448,7 +2365,6 @@ static const struct rtl_coalesce_info *rtl_coalesce_info(struct net_device *dev) static int rtl_get_coalesce(struct net_device *dev, struct ethtool_coalesce *ec) { struct rtl8169_private *tp = netdev_priv(dev); - void __iomem *ioaddr = tp->mmio_addr; const struct rtl_coalesce_info *ci; const struct rtl_coalesce_scale *scale; struct { @@ -2468,10 +2384,10 @@ static int rtl_get_coalesce(struct net_device *dev, struct ethtool_coalesce *ec) if (IS_ERR(ci)) return PTR_ERR(ci); - scale = &ci->scalev[RTL_R16(CPlusCmd) & 3]; + scale = &ci->scalev[RTL_R16(tp, CPlusCmd) & 3]; /* read IntrMitigate and adjust according to scale */ - for (w = RTL_R16(IntrMitigate); w; w >>= RTL_COALESCE_SHIFT, p++) { + for (w = RTL_R16(tp, IntrMitigate); w; w >>= RTL_COALESCE_SHIFT, p++) { *p->max_frames = (w & RTL_COALESCE_MASK) << 2; w >>= RTL_COALESCE_SHIFT; *p->usecs = w & RTL_COALESCE_MASK; @@ -2518,7 +2434,6 @@ static const struct rtl_coalesce_scale *rtl_coalesce_choose_scale( static int rtl_set_coalesce(struct net_device *dev, struct ethtool_coalesce *ec) { struct rtl8169_private *tp = netdev_priv(dev); - void __iomem *ioaddr = tp->mmio_addr; const struct rtl_coalesce_scale *scale; struct { u32 frames; @@ -2566,11 +2481,11 @@ static int rtl_set_coalesce(struct net_device *dev, struct ethtool_coalesce *ec) rtl_lock_work(tp); - RTL_W16(IntrMitigate, swab16(w)); + RTL_W16(tp, IntrMitigate, swab16(w)); tp->cp_cmd = (tp->cp_cmd & ~3) | cp01; - RTL_W16(CPlusCmd, tp->cp_cmd); - RTL_R16(CPlusCmd); + RTL_W16(tp, CPlusCmd, tp->cp_cmd); + RTL_R16(tp, CPlusCmd); rtl_unlock_work(tp); @@ -2600,17 +2515,16 @@ static const struct ethtool_ops rtl8169_ethtool_ops = { static void rtl8169_get_mac_version(struct rtl8169_private *tp, struct net_device *dev, u8 default_version) { - void __iomem *ioaddr = tp->mmio_addr; /* * The driver currently handles the 8168Bf and the 8168Be identically * but they can be identified more specifically through the test below * if needed: * - * (RTL_R32(TxConfig) & 0x700000) == 0x500000 ? 8168Bf : 8168Be + * (RTL_R32(tp, TxConfig) & 0x700000) == 0x500000 ? 8168Bf : 8168Be * * Same thing for the 8101Eb and the 8101Ec: * - * (RTL_R32(TxConfig) & 0x700000) == 0x200000 ? 8101Eb : 8101Ec + * (RTL_R32(tp, TxConfig) & 0x700000) == 0x200000 ? 8101Eb : 8101Ec */ static const struct rtl_mac_info { u32 mask; @@ -2708,7 +2622,7 @@ static void rtl8169_get_mac_version(struct rtl8169_private *tp, const struct rtl_mac_info *p = mac_info; u32 reg; - reg = RTL_R32(TxConfig); + reg = RTL_R32(tp, TxConfig); while ((reg & p->mask) != p->val) p++; tp->mac_version = p->mac_version; @@ -3805,8 +3719,6 @@ static void rtl8168e_2_hw_phy_config(struct rtl8169_private *tp) rtl_writephy(tp, 0x1f, 0x0005); rtl_w0w1_phy(tp, 0x01, 0x0100, 0x0000); rtl_writephy(tp, 0x1f, 0x0000); - /* soft-reset phy */ - rtl_writephy(tp, MII_BMCR, BMCR_RESET | BMCR_ANENABLE | BMCR_ANRESTART); /* Broken BIOS workaround: feed GigaMAC registers with MAC address. */ rtl_rar_exgmac_set(tp, tp->dev->dev_addr); @@ -4591,7 +4503,6 @@ static void rtl_hw_phy_config(struct net_device *dev) static void rtl_phy_work(struct rtl8169_private *tp) { struct timer_list *timer = &tp->timer; - void __iomem *ioaddr = tp->mmio_addr; unsigned long timeout = RTL8169_PHY_TIMEOUT; assert(tp->mac_version > RTL_GIGA_MAC_VER_01); @@ -4605,7 +4516,7 @@ static void rtl_phy_work(struct rtl8169_private *tp) goto out_mod_timer; } - if (tp->link_ok(ioaddr)) + if (tp->link_ok(tp)) return; netif_dbg(tp, link, tp->dev, "PHY reset until link up\n"); @@ -4643,21 +4554,17 @@ static void rtl8169_phy_reset(struct net_device *dev, static bool rtl_tbi_enabled(struct rtl8169_private *tp) { - void __iomem *ioaddr = tp->mmio_addr; - return (tp->mac_version == RTL_GIGA_MAC_VER_01) && - (RTL_R8(PHYstatus) & TBI_Enable); + (RTL_R8(tp, PHYstatus) & TBI_Enable); } static void rtl8169_init_phy(struct net_device *dev, struct rtl8169_private *tp) { - void __iomem *ioaddr = tp->mmio_addr; - rtl_hw_phy_config(dev); if (tp->mac_version <= RTL_GIGA_MAC_VER_06) { dprintk("Set MAC Reg C+CR Offset 0x82h = 0x01h\n"); - RTL_W8(0x82, 0x01); + RTL_W8(tp, 0x82, 0x01); } pci_write_config_byte(tp->pci_dev, PCI_LATENCY_TIMER, 0x40); @@ -4667,7 +4574,7 @@ static void rtl8169_init_phy(struct net_device *dev, struct rtl8169_private *tp) if (tp->mac_version == RTL_GIGA_MAC_VER_02) { dprintk("Set MAC Reg C+CR Offset 0x82h = 0x01h\n"); - RTL_W8(0x82, 0x01); + RTL_W8(tp, 0x82, 0x01); dprintk("Set PHY Reg 0x0bh = 0x00h\n"); rtl_writephy(tp, 0x0b, 0x0000); //w 0x0b 15 0 0 } @@ -4687,22 +4594,20 @@ static void rtl8169_init_phy(struct net_device *dev, struct rtl8169_private *tp) static void rtl_rar_set(struct rtl8169_private *tp, u8 *addr) { - void __iomem *ioaddr = tp->mmio_addr; - rtl_lock_work(tp); - RTL_W8(Cfg9346, Cfg9346_Unlock); + RTL_W8(tp, Cfg9346, Cfg9346_Unlock); - RTL_W32(MAC4, addr[4] | addr[5] << 8); - RTL_R32(MAC4); + RTL_W32(tp, MAC4, addr[4] | addr[5] << 8); + RTL_R32(tp, MAC4); - RTL_W32(MAC0, addr[0] | addr[1] << 8 | addr[2] << 16 | addr[3] << 24); - RTL_R32(MAC0); + RTL_W32(tp, MAC0, addr[0] | addr[1] << 8 | addr[2] << 16 | addr[3] << 24); + RTL_R32(tp, MAC0); if (tp->mac_version == RTL_GIGA_MAC_VER_34) rtl_rar_exgmac_set(tp, addr); - RTL_W8(Cfg9346, Cfg9346_Lock); + RTL_W8(tp, Cfg9346, Cfg9346_Lock); rtl_unlock_work(tp); } @@ -4822,8 +4727,6 @@ static void rtl_speed_down(struct rtl8169_private *tp) static void rtl_wol_suspend_quirk(struct rtl8169_private *tp) { - void __iomem *ioaddr = tp->mmio_addr; - switch (tp->mac_version) { case RTL_GIGA_MAC_VER_25: case RTL_GIGA_MAC_VER_26: @@ -4847,7 +4750,7 @@ static void rtl_wol_suspend_quirk(struct rtl8169_private *tp) case RTL_GIGA_MAC_VER_49: case RTL_GIGA_MAC_VER_50: case RTL_GIGA_MAC_VER_51: - RTL_W32(RxConfig, RTL_R32(RxConfig) | + RTL_W32(tp, RxConfig, RTL_R32(tp, RxConfig) | AcceptBroadcast | AcceptMulticast | AcceptMyPhys); break; default: @@ -4880,8 +4783,6 @@ static void r810x_phy_power_up(struct rtl8169_private *tp) static void r810x_pll_power_down(struct rtl8169_private *tp) { - void __iomem *ioaddr = tp->mmio_addr; - if (rtl_wol_pll_power_down(tp)) return; @@ -4896,15 +4797,13 @@ static void r810x_pll_power_down(struct rtl8169_private *tp) case RTL_GIGA_MAC_VER_16: break; default: - RTL_W8(PMCH, RTL_R8(PMCH) & ~0x80); + RTL_W8(tp, PMCH, RTL_R8(tp, PMCH) & ~0x80); break; } } static void r810x_pll_power_up(struct rtl8169_private *tp) { - void __iomem *ioaddr = tp->mmio_addr; - r810x_phy_power_up(tp); switch (tp->mac_version) { @@ -4917,10 +4816,10 @@ static void r810x_pll_power_up(struct rtl8169_private *tp) break; case RTL_GIGA_MAC_VER_47: case RTL_GIGA_MAC_VER_48: - RTL_W8(PMCH, RTL_R8(PMCH) | 0xc0); + RTL_W8(tp, PMCH, RTL_R8(tp, PMCH) | 0xc0); break; default: - RTL_W8(PMCH, RTL_R8(PMCH) | 0x80); + RTL_W8(tp, PMCH, RTL_R8(tp, PMCH) | 0x80); break; } } @@ -4987,21 +4886,12 @@ static void r8168_phy_power_down(struct rtl8169_private *tp) static void r8168_pll_power_down(struct rtl8169_private *tp) { - void __iomem *ioaddr = tp->mmio_addr; - - if ((tp->mac_version == RTL_GIGA_MAC_VER_27 || - tp->mac_version == RTL_GIGA_MAC_VER_28 || - tp->mac_version == RTL_GIGA_MAC_VER_31 || - tp->mac_version == RTL_GIGA_MAC_VER_49 || - tp->mac_version == RTL_GIGA_MAC_VER_50 || - tp->mac_version == RTL_GIGA_MAC_VER_51) && - r8168_check_dash(tp)) { + if (r8168_check_dash(tp)) return; - } if ((tp->mac_version == RTL_GIGA_MAC_VER_23 || tp->mac_version == RTL_GIGA_MAC_VER_24) && - (RTL_R16(CPlusCmd) & ASF)) { + (RTL_R16(tp, CPlusCmd) & ASF)) { return; } @@ -5027,22 +4917,20 @@ static void r8168_pll_power_down(struct rtl8169_private *tp) case RTL_GIGA_MAC_VER_46: case RTL_GIGA_MAC_VER_50: case RTL_GIGA_MAC_VER_51: - RTL_W8(PMCH, RTL_R8(PMCH) & ~0x80); + RTL_W8(tp, PMCH, RTL_R8(tp, PMCH) & ~0x80); break; case RTL_GIGA_MAC_VER_40: case RTL_GIGA_MAC_VER_41: case RTL_GIGA_MAC_VER_49: rtl_w0w1_eri(tp, 0x1a8, ERIAR_MASK_1111, 0x00000000, 0xfc000000, ERIAR_EXGMAC); - RTL_W8(PMCH, RTL_R8(PMCH) & ~0x80); + RTL_W8(tp, PMCH, RTL_R8(tp, PMCH) & ~0x80); break; } } static void r8168_pll_power_up(struct rtl8169_private *tp) { - void __iomem *ioaddr = tp->mmio_addr; - switch (tp->mac_version) { case RTL_GIGA_MAC_VER_25: case RTL_GIGA_MAC_VER_26: @@ -5051,19 +4939,19 @@ static void r8168_pll_power_up(struct rtl8169_private *tp) case RTL_GIGA_MAC_VER_31: case RTL_GIGA_MAC_VER_32: case RTL_GIGA_MAC_VER_33: - RTL_W8(PMCH, RTL_R8(PMCH) | 0x80); + RTL_W8(tp, PMCH, RTL_R8(tp, PMCH) | 0x80); break; case RTL_GIGA_MAC_VER_44: case RTL_GIGA_MAC_VER_45: case RTL_GIGA_MAC_VER_46: case RTL_GIGA_MAC_VER_50: case RTL_GIGA_MAC_VER_51: - RTL_W8(PMCH, RTL_R8(PMCH) | 0xc0); + RTL_W8(tp, PMCH, RTL_R8(tp, PMCH) | 0xc0); break; case RTL_GIGA_MAC_VER_40: case RTL_GIGA_MAC_VER_41: case RTL_GIGA_MAC_VER_49: - RTL_W8(PMCH, RTL_R8(PMCH) | 0xc0); + RTL_W8(tp, PMCH, RTL_R8(tp, PMCH) | 0xc0); rtl_w0w1_eri(tp, 0x1a8, ERIAR_MASK_1111, 0xfc000000, 0x00000000, ERIAR_EXGMAC); break; @@ -5153,8 +5041,6 @@ static void rtl_init_pll_power_ops(struct rtl8169_private *tp) static void rtl_init_rxcfg(struct rtl8169_private *tp) { - void __iomem *ioaddr = tp->mmio_addr; - switch (tp->mac_version) { case RTL_GIGA_MAC_VER_01: case RTL_GIGA_MAC_VER_02: @@ -5170,7 +5056,7 @@ static void rtl_init_rxcfg(struct rtl8169_private *tp) case RTL_GIGA_MAC_VER_15: case RTL_GIGA_MAC_VER_16: case RTL_GIGA_MAC_VER_17: - RTL_W32(RxConfig, RX_FIFO_THRESH | RX_DMA_BURST); + RTL_W32(tp, RxConfig, RX_FIFO_THRESH | RX_DMA_BURST); break; case RTL_GIGA_MAC_VER_18: case RTL_GIGA_MAC_VER_19: @@ -5181,7 +5067,7 @@ static void rtl_init_rxcfg(struct rtl8169_private *tp) case RTL_GIGA_MAC_VER_24: case RTL_GIGA_MAC_VER_34: case RTL_GIGA_MAC_VER_35: - RTL_W32(RxConfig, RX128_INT_EN | RX_MULTI_EN | RX_DMA_BURST); + RTL_W32(tp, RxConfig, RX128_INT_EN | RX_MULTI_EN | RX_DMA_BURST); break; case RTL_GIGA_MAC_VER_40: case RTL_GIGA_MAC_VER_41: @@ -5195,10 +5081,10 @@ static void rtl_init_rxcfg(struct rtl8169_private *tp) case RTL_GIGA_MAC_VER_49: case RTL_GIGA_MAC_VER_50: case RTL_GIGA_MAC_VER_51: - RTL_W32(RxConfig, RX128_INT_EN | RX_MULTI_EN | RX_DMA_BURST | RX_EARLY_OFF); + RTL_W32(tp, RxConfig, RX128_INT_EN | RX_MULTI_EN | RX_DMA_BURST | RX_EARLY_OFF); break; default: - RTL_W32(RxConfig, RX128_INT_EN | RX_DMA_BURST); + RTL_W32(tp, RxConfig, RX128_INT_EN | RX_DMA_BURST); break; } } @@ -5210,71 +5096,55 @@ static void rtl8169_init_ring_indexes(struct rtl8169_private *tp) static void rtl_hw_jumbo_enable(struct rtl8169_private *tp) { - void __iomem *ioaddr = tp->mmio_addr; - - RTL_W8(Cfg9346, Cfg9346_Unlock); + RTL_W8(tp, Cfg9346, Cfg9346_Unlock); rtl_generic_op(tp, tp->jumbo_ops.enable); - RTL_W8(Cfg9346, Cfg9346_Lock); + RTL_W8(tp, Cfg9346, Cfg9346_Lock); } static void rtl_hw_jumbo_disable(struct rtl8169_private *tp) { - void __iomem *ioaddr = tp->mmio_addr; - - RTL_W8(Cfg9346, Cfg9346_Unlock); + RTL_W8(tp, Cfg9346, Cfg9346_Unlock); rtl_generic_op(tp, tp->jumbo_ops.disable); - RTL_W8(Cfg9346, Cfg9346_Lock); + RTL_W8(tp, Cfg9346, Cfg9346_Lock); } static void r8168c_hw_jumbo_enable(struct rtl8169_private *tp) { - void __iomem *ioaddr = tp->mmio_addr; - - RTL_W8(Config3, RTL_R8(Config3) | Jumbo_En0); - RTL_W8(Config4, RTL_R8(Config4) | Jumbo_En1); + RTL_W8(tp, Config3, RTL_R8(tp, Config3) | Jumbo_En0); + RTL_W8(tp, Config4, RTL_R8(tp, Config4) | Jumbo_En1); rtl_tx_performance_tweak(tp->pci_dev, PCI_EXP_DEVCTL_READRQ_512B); } static void r8168c_hw_jumbo_disable(struct rtl8169_private *tp) { - void __iomem *ioaddr = tp->mmio_addr; - - RTL_W8(Config3, RTL_R8(Config3) & ~Jumbo_En0); - RTL_W8(Config4, RTL_R8(Config4) & ~Jumbo_En1); + RTL_W8(tp, Config3, RTL_R8(tp, Config3) & ~Jumbo_En0); + RTL_W8(tp, Config4, RTL_R8(tp, Config4) & ~Jumbo_En1); rtl_tx_performance_tweak(tp->pci_dev, 0x5 << MAX_READ_REQUEST_SHIFT); } static void r8168dp_hw_jumbo_enable(struct rtl8169_private *tp) { - void __iomem *ioaddr = tp->mmio_addr; - - RTL_W8(Config3, RTL_R8(Config3) | Jumbo_En0); + RTL_W8(tp, Config3, RTL_R8(tp, Config3) | Jumbo_En0); } static void r8168dp_hw_jumbo_disable(struct rtl8169_private *tp) { - void __iomem *ioaddr = tp->mmio_addr; - - RTL_W8(Config3, RTL_R8(Config3) & ~Jumbo_En0); + RTL_W8(tp, Config3, RTL_R8(tp, Config3) & ~Jumbo_En0); } static void r8168e_hw_jumbo_enable(struct rtl8169_private *tp) { - void __iomem *ioaddr = tp->mmio_addr; - - RTL_W8(MaxTxPacketSize, 0x3f); - RTL_W8(Config3, RTL_R8(Config3) | Jumbo_En0); - RTL_W8(Config4, RTL_R8(Config4) | 0x01); + RTL_W8(tp, MaxTxPacketSize, 0x3f); + RTL_W8(tp, Config3, RTL_R8(tp, Config3) | Jumbo_En0); + RTL_W8(tp, Config4, RTL_R8(tp, Config4) | 0x01); rtl_tx_performance_tweak(tp->pci_dev, PCI_EXP_DEVCTL_READRQ_512B); } static void r8168e_hw_jumbo_disable(struct rtl8169_private *tp) { - void __iomem *ioaddr = tp->mmio_addr; - - RTL_W8(MaxTxPacketSize, 0x0c); - RTL_W8(Config3, RTL_R8(Config3) & ~Jumbo_En0); - RTL_W8(Config4, RTL_R8(Config4) & ~0x01); + RTL_W8(tp, MaxTxPacketSize, 0x0c); + RTL_W8(tp, Config3, RTL_R8(tp, Config3) & ~Jumbo_En0); + RTL_W8(tp, Config4, RTL_R8(tp, Config4) & ~0x01); rtl_tx_performance_tweak(tp->pci_dev, 0x5 << MAX_READ_REQUEST_SHIFT); } @@ -5292,20 +5162,16 @@ static void r8168b_0_hw_jumbo_disable(struct rtl8169_private *tp) static void r8168b_1_hw_jumbo_enable(struct rtl8169_private *tp) { - void __iomem *ioaddr = tp->mmio_addr; - r8168b_0_hw_jumbo_enable(tp); - RTL_W8(Config4, RTL_R8(Config4) | (1 << 0)); + RTL_W8(tp, Config4, RTL_R8(tp, Config4) | (1 << 0)); } static void r8168b_1_hw_jumbo_disable(struct rtl8169_private *tp) { - void __iomem *ioaddr = tp->mmio_addr; - r8168b_0_hw_jumbo_disable(tp); - RTL_W8(Config4, RTL_R8(Config4) & ~(1 << 0)); + RTL_W8(tp, Config4, RTL_R8(tp, Config4) & ~(1 << 0)); } static void rtl_init_jumbo_ops(struct rtl8169_private *tp) @@ -5372,16 +5238,12 @@ static void rtl_init_jumbo_ops(struct rtl8169_private *tp) DECLARE_RTL_COND(rtl_chipcmd_cond) { - void __iomem *ioaddr = tp->mmio_addr; - - return RTL_R8(ChipCmd) & CmdReset; + return RTL_R8(tp, ChipCmd) & CmdReset; } static void rtl_hw_reset(struct rtl8169_private *tp) { - void __iomem *ioaddr = tp->mmio_addr; - - RTL_W8(ChipCmd, CmdReset); + RTL_W8(tp, ChipCmd, CmdReset); rtl_udelay_loop_wait_low(tp, &rtl_chipcmd_cond, 100, 100); } @@ -5432,29 +5294,21 @@ static void rtl_request_firmware(struct rtl8169_private *tp) static void rtl_rx_close(struct rtl8169_private *tp) { - void __iomem *ioaddr = tp->mmio_addr; - - RTL_W32(RxConfig, RTL_R32(RxConfig) & ~RX_CONFIG_ACCEPT_MASK); + RTL_W32(tp, RxConfig, RTL_R32(tp, RxConfig) & ~RX_CONFIG_ACCEPT_MASK); } DECLARE_RTL_COND(rtl_npq_cond) { - void __iomem *ioaddr = tp->mmio_addr; - - return RTL_R8(TxPoll) & NPQ; + return RTL_R8(tp, TxPoll) & NPQ; } DECLARE_RTL_COND(rtl_txcfg_empty_cond) { - void __iomem *ioaddr = tp->mmio_addr; - - return RTL_R32(TxConfig) & TXCFG_EMPTY; + return RTL_R32(tp, TxConfig) & TXCFG_EMPTY; } static void rtl8169_hw_reset(struct rtl8169_private *tp) { - void __iomem *ioaddr = tp->mmio_addr; - /* Disable interrupts */ rtl8169_irq_mask_and_ack(tp); @@ -5481,10 +5335,10 @@ static void rtl8169_hw_reset(struct rtl8169_private *tp) tp->mac_version == RTL_GIGA_MAC_VER_49 || tp->mac_version == RTL_GIGA_MAC_VER_50 || tp->mac_version == RTL_GIGA_MAC_VER_51) { - RTL_W8(ChipCmd, RTL_R8(ChipCmd) | StopReq); + RTL_W8(tp, ChipCmd, RTL_R8(tp, ChipCmd) | StopReq); rtl_udelay_loop_wait_high(tp, &rtl_txcfg_empty_cond, 100, 666); } else { - RTL_W8(ChipCmd, RTL_R8(ChipCmd) | StopReq); + RTL_W8(tp, ChipCmd, RTL_R8(tp, ChipCmd) | StopReq); udelay(100); } @@ -5493,10 +5347,8 @@ static void rtl8169_hw_reset(struct rtl8169_private *tp) static void rtl_set_rx_tx_config_registers(struct rtl8169_private *tp) { - void __iomem *ioaddr = tp->mmio_addr; - /* Set DMA burst size and Interframe Gap Time */ - RTL_W32(TxConfig, (TX_DMA_BURST << TxDMAShift) | + RTL_W32(tp, TxConfig, (TX_DMA_BURST << TxDMAShift) | (InterFrameGap << TxInterFrameGapShift)); } @@ -5509,36 +5361,35 @@ static void rtl_hw_start(struct net_device *dev) rtl_irq_enable_all(tp); } -static void rtl_set_rx_tx_desc_registers(struct rtl8169_private *tp, - void __iomem *ioaddr) +static void rtl_set_rx_tx_desc_registers(struct rtl8169_private *tp) { /* * Magic spell: some iop3xx ARM board needs the TxDescAddrHigh * register to be written before TxDescAddrLow to work. * Switching from MMIO to I/O access fixes the issue as well. */ - RTL_W32(TxDescStartAddrHigh, ((u64) tp->TxPhyAddr) >> 32); - RTL_W32(TxDescStartAddrLow, ((u64) tp->TxPhyAddr) & DMA_BIT_MASK(32)); - RTL_W32(RxDescAddrHigh, ((u64) tp->RxPhyAddr) >> 32); - RTL_W32(RxDescAddrLow, ((u64) tp->RxPhyAddr) & DMA_BIT_MASK(32)); + RTL_W32(tp, TxDescStartAddrHigh, ((u64) tp->TxPhyAddr) >> 32); + RTL_W32(tp, TxDescStartAddrLow, ((u64) tp->TxPhyAddr) & DMA_BIT_MASK(32)); + RTL_W32(tp, RxDescAddrHigh, ((u64) tp->RxPhyAddr) >> 32); + RTL_W32(tp, RxDescAddrLow, ((u64) tp->RxPhyAddr) & DMA_BIT_MASK(32)); } -static u16 rtl_rw_cpluscmd(void __iomem *ioaddr) +static u16 rtl_rw_cpluscmd(struct rtl8169_private *tp) { u16 cmd; - cmd = RTL_R16(CPlusCmd); - RTL_W16(CPlusCmd, cmd); + cmd = RTL_R16(tp, CPlusCmd); + RTL_W16(tp, CPlusCmd, cmd); return cmd; } -static void rtl_set_rx_max_size(void __iomem *ioaddr, unsigned int rx_buf_sz) +static void rtl_set_rx_max_size(struct rtl8169_private *tp, unsigned int rx_buf_sz) { /* Low hurts. Let's disable the filtering. */ - RTL_W16(RxMaxSize, rx_buf_sz + 1); + RTL_W16(tp, RxMaxSize, rx_buf_sz + 1); } -static void rtl8169_set_magic_reg(void __iomem *ioaddr, unsigned mac_version) +static void rtl8169_set_magic_reg(struct rtl8169_private *tp, unsigned mac_version) { static const struct rtl_cfg2_info { u32 mac_version; @@ -5554,10 +5405,10 @@ static void rtl8169_set_magic_reg(void __iomem *ioaddr, unsigned mac_version) unsigned int i; u32 clk; - clk = RTL_R8(Config2) & PCI_Clock_66MHz; + clk = RTL_R8(tp, Config2) & PCI_Clock_66MHz; for (i = 0; i < ARRAY_SIZE(cfg2_info); i++, p++) { if ((p->mac_version == mac_version) && (p->clk == clk)) { - RTL_W32(0x7c, p->val); + RTL_W32(tp, 0x7c, p->val); break; } } @@ -5566,7 +5417,6 @@ static void rtl8169_set_magic_reg(void __iomem *ioaddr, unsigned mac_version) static void rtl_set_rx_mode(struct net_device *dev) { struct rtl8169_private *tp = netdev_priv(dev); - void __iomem *ioaddr = tp->mmio_addr; u32 mc_filter[2]; /* Multicast hash filter */ int rx_mode; u32 tmp = 0; @@ -5598,7 +5448,7 @@ static void rtl_set_rx_mode(struct net_device *dev) if (dev->features & NETIF_F_RXALL) rx_mode |= (AcceptErr | AcceptRunt); - tmp = (RTL_R32(RxConfig) & ~RX_CONFIG_ACCEPT_MASK) | rx_mode; + tmp = (RTL_R32(tp, RxConfig) & ~RX_CONFIG_ACCEPT_MASK) | rx_mode; if (tp->mac_version > RTL_GIGA_MAC_VER_06) { u32 data = mc_filter[0]; @@ -5610,35 +5460,34 @@ static void rtl_set_rx_mode(struct net_device *dev) if (tp->mac_version == RTL_GIGA_MAC_VER_35) mc_filter[1] = mc_filter[0] = 0xffffffff; - RTL_W32(MAR0 + 4, mc_filter[1]); - RTL_W32(MAR0 + 0, mc_filter[0]); + RTL_W32(tp, MAR0 + 4, mc_filter[1]); + RTL_W32(tp, MAR0 + 0, mc_filter[0]); - RTL_W32(RxConfig, tmp); + RTL_W32(tp, RxConfig, tmp); } static void rtl_hw_start_8169(struct net_device *dev) { struct rtl8169_private *tp = netdev_priv(dev); - void __iomem *ioaddr = tp->mmio_addr; struct pci_dev *pdev = tp->pci_dev; if (tp->mac_version == RTL_GIGA_MAC_VER_05) { - RTL_W16(CPlusCmd, RTL_R16(CPlusCmd) | PCIMulRW); + RTL_W16(tp, CPlusCmd, RTL_R16(tp, CPlusCmd) | PCIMulRW); pci_write_config_byte(pdev, PCI_CACHE_LINE_SIZE, 0x08); } - RTL_W8(Cfg9346, Cfg9346_Unlock); + RTL_W8(tp, Cfg9346, Cfg9346_Unlock); if (tp->mac_version == RTL_GIGA_MAC_VER_01 || tp->mac_version == RTL_GIGA_MAC_VER_02 || tp->mac_version == RTL_GIGA_MAC_VER_03 || tp->mac_version == RTL_GIGA_MAC_VER_04) - RTL_W8(ChipCmd, CmdTxEnb | CmdRxEnb); + RTL_W8(tp, ChipCmd, CmdTxEnb | CmdRxEnb); rtl_init_rxcfg(tp); - RTL_W8(EarlyTxThres, NoEarlyTx); + RTL_W8(tp, EarlyTxThres, NoEarlyTx); - rtl_set_rx_max_size(ioaddr, rx_buf_sz); + rtl_set_rx_max_size(tp, rx_buf_sz); if (tp->mac_version == RTL_GIGA_MAC_VER_01 || tp->mac_version == RTL_GIGA_MAC_VER_02 || @@ -5646,7 +5495,7 @@ static void rtl_hw_start_8169(struct net_device *dev) tp->mac_version == RTL_GIGA_MAC_VER_04) rtl_set_rx_tx_config_registers(tp); - tp->cp_cmd |= rtl_rw_cpluscmd(ioaddr) | PCIMulRW; + tp->cp_cmd |= rtl_rw_cpluscmd(tp) | PCIMulRW; if (tp->mac_version == RTL_GIGA_MAC_VER_02 || tp->mac_version == RTL_GIGA_MAC_VER_03) { @@ -5655,37 +5504,37 @@ static void rtl_hw_start_8169(struct net_device *dev) tp->cp_cmd |= (1 << 14); } - RTL_W16(CPlusCmd, tp->cp_cmd); + RTL_W16(tp, CPlusCmd, tp->cp_cmd); - rtl8169_set_magic_reg(ioaddr, tp->mac_version); + rtl8169_set_magic_reg(tp, tp->mac_version); /* * Undocumented corner. Supposedly: * (TxTimer << 12) | (TxPackets << 8) | (RxTimer << 4) | RxPackets */ - RTL_W16(IntrMitigate, 0x0000); + RTL_W16(tp, IntrMitigate, 0x0000); - rtl_set_rx_tx_desc_registers(tp, ioaddr); + rtl_set_rx_tx_desc_registers(tp); if (tp->mac_version != RTL_GIGA_MAC_VER_01 && tp->mac_version != RTL_GIGA_MAC_VER_02 && tp->mac_version != RTL_GIGA_MAC_VER_03 && tp->mac_version != RTL_GIGA_MAC_VER_04) { - RTL_W8(ChipCmd, CmdTxEnb | CmdRxEnb); + RTL_W8(tp, ChipCmd, CmdTxEnb | CmdRxEnb); rtl_set_rx_tx_config_registers(tp); } - RTL_W8(Cfg9346, Cfg9346_Lock); + RTL_W8(tp, Cfg9346, Cfg9346_Lock); /* Initially a 10 us delay. Turned it into a PCI commit. - FR */ - RTL_R8(IntrMask); + RTL_R8(tp, IntrMask); - RTL_W32(RxMissed, 0); + RTL_W32(tp, RxMissed, 0); rtl_set_rx_mode(dev); /* no early-rx interrupts */ - RTL_W16(MultiIntr, RTL_R16(MultiIntr) & 0xf000); + RTL_W16(tp, MultiIntr, RTL_R16(tp, MultiIntr) & 0xf000); } static void rtl_csi_write(struct rtl8169_private *tp, int addr, int value) @@ -5719,17 +5568,13 @@ static void rtl_csi_access_enable_2(struct rtl8169_private *tp) DECLARE_RTL_COND(rtl_csiar_cond) { - void __iomem *ioaddr = tp->mmio_addr; - - return RTL_R32(CSIAR) & CSIAR_FLAG; + return RTL_R32(tp, CSIAR) & CSIAR_FLAG; } static void r8169_csi_write(struct rtl8169_private *tp, int addr, int value) { - void __iomem *ioaddr = tp->mmio_addr; - - RTL_W32(CSIDR, value); - RTL_W32(CSIAR, CSIAR_WRITE_CMD | (addr & CSIAR_ADDR_MASK) | + RTL_W32(tp, CSIDR, value); + RTL_W32(tp, CSIAR, CSIAR_WRITE_CMD | (addr & CSIAR_ADDR_MASK) | CSIAR_BYTE_ENABLE << CSIAR_BYTE_ENABLE_SHIFT); rtl_udelay_loop_wait_low(tp, &rtl_csiar_cond, 10, 100); @@ -5737,21 +5582,17 @@ static void r8169_csi_write(struct rtl8169_private *tp, int addr, int value) static u32 r8169_csi_read(struct rtl8169_private *tp, int addr) { - void __iomem *ioaddr = tp->mmio_addr; - - RTL_W32(CSIAR, (addr & CSIAR_ADDR_MASK) | + RTL_W32(tp, CSIAR, (addr & CSIAR_ADDR_MASK) | CSIAR_BYTE_ENABLE << CSIAR_BYTE_ENABLE_SHIFT); return rtl_udelay_loop_wait_high(tp, &rtl_csiar_cond, 10, 100) ? - RTL_R32(CSIDR) : ~0; + RTL_R32(tp, CSIDR) : ~0; } static void r8402_csi_write(struct rtl8169_private *tp, int addr, int value) { - void __iomem *ioaddr = tp->mmio_addr; - - RTL_W32(CSIDR, value); - RTL_W32(CSIAR, CSIAR_WRITE_CMD | (addr & CSIAR_ADDR_MASK) | + RTL_W32(tp, CSIDR, value); + RTL_W32(tp, CSIAR, CSIAR_WRITE_CMD | (addr & CSIAR_ADDR_MASK) | CSIAR_BYTE_ENABLE << CSIAR_BYTE_ENABLE_SHIFT | CSIAR_FUNC_NIC); @@ -5760,21 +5601,17 @@ static void r8402_csi_write(struct rtl8169_private *tp, int addr, int value) static u32 r8402_csi_read(struct rtl8169_private *tp, int addr) { - void __iomem *ioaddr = tp->mmio_addr; - - RTL_W32(CSIAR, (addr & CSIAR_ADDR_MASK) | CSIAR_FUNC_NIC | + RTL_W32(tp, CSIAR, (addr & CSIAR_ADDR_MASK) | CSIAR_FUNC_NIC | CSIAR_BYTE_ENABLE << CSIAR_BYTE_ENABLE_SHIFT); return rtl_udelay_loop_wait_high(tp, &rtl_csiar_cond, 10, 100) ? - RTL_R32(CSIDR) : ~0; + RTL_R32(tp, CSIDR) : ~0; } static void r8411_csi_write(struct rtl8169_private *tp, int addr, int value) { - void __iomem *ioaddr = tp->mmio_addr; - - RTL_W32(CSIDR, value); - RTL_W32(CSIAR, CSIAR_WRITE_CMD | (addr & CSIAR_ADDR_MASK) | + RTL_W32(tp, CSIDR, value); + RTL_W32(tp, CSIAR, CSIAR_WRITE_CMD | (addr & CSIAR_ADDR_MASK) | CSIAR_BYTE_ENABLE << CSIAR_BYTE_ENABLE_SHIFT | CSIAR_FUNC_NIC2); @@ -5783,13 +5620,11 @@ static void r8411_csi_write(struct rtl8169_private *tp, int addr, int value) static u32 r8411_csi_read(struct rtl8169_private *tp, int addr) { - void __iomem *ioaddr = tp->mmio_addr; - - RTL_W32(CSIAR, (addr & CSIAR_ADDR_MASK) | CSIAR_FUNC_NIC2 | + RTL_W32(tp, CSIAR, (addr & CSIAR_ADDR_MASK) | CSIAR_FUNC_NIC2 | CSIAR_BYTE_ENABLE << CSIAR_BYTE_ENABLE_SHIFT); return rtl_udelay_loop_wait_high(tp, &rtl_csiar_cond, 10, 100) ? - RTL_R32(CSIDR) : ~0; + RTL_R32(tp, CSIDR) : ~0; } static void rtl_init_csi_ops(struct rtl8169_private *tp) @@ -5865,17 +5700,16 @@ static void rtl_enable_clock_request(struct pci_dev *pdev) static void rtl_pcie_state_l2l3_enable(struct rtl8169_private *tp, bool enable) { - void __iomem *ioaddr = tp->mmio_addr; u8 data; - data = RTL_R8(Config3); + data = RTL_R8(tp, Config3); if (enable) data |= Rdy_to_L23; else data &= ~Rdy_to_L23; - RTL_W8(Config3, data); + RTL_W8(tp, Config3, data); } #define R8168_CPCMD_QUIRK_MASK (\ @@ -5891,12 +5725,11 @@ static void rtl_pcie_state_l2l3_enable(struct rtl8169_private *tp, bool enable) static void rtl_hw_start_8168bb(struct rtl8169_private *tp) { - void __iomem *ioaddr = tp->mmio_addr; struct pci_dev *pdev = tp->pci_dev; - RTL_W8(Config3, RTL_R8(Config3) & ~Beacon_en); + RTL_W8(tp, Config3, RTL_R8(tp, Config3) & ~Beacon_en); - RTL_W16(CPlusCmd, RTL_R16(CPlusCmd) & ~R8168_CPCMD_QUIRK_MASK); + RTL_W16(tp, CPlusCmd, RTL_R16(tp, CPlusCmd) & ~R8168_CPCMD_QUIRK_MASK); if (tp->dev->mtu <= ETH_DATA_LEN) { rtl_tx_performance_tweak(pdev, (0x5 << MAX_READ_REQUEST_SHIFT) | @@ -5906,30 +5739,27 @@ static void rtl_hw_start_8168bb(struct rtl8169_private *tp) static void rtl_hw_start_8168bef(struct rtl8169_private *tp) { - void __iomem *ioaddr = tp->mmio_addr; - rtl_hw_start_8168bb(tp); - RTL_W8(MaxTxPacketSize, TxPacketMax); + RTL_W8(tp, MaxTxPacketSize, TxPacketMax); - RTL_W8(Config4, RTL_R8(Config4) & ~(1 << 0)); + RTL_W8(tp, Config4, RTL_R8(tp, Config4) & ~(1 << 0)); } static void __rtl_hw_start_8168cp(struct rtl8169_private *tp) { - void __iomem *ioaddr = tp->mmio_addr; struct pci_dev *pdev = tp->pci_dev; - RTL_W8(Config1, RTL_R8(Config1) | Speed_down); + RTL_W8(tp, Config1, RTL_R8(tp, Config1) | Speed_down); - RTL_W8(Config3, RTL_R8(Config3) & ~Beacon_en); + RTL_W8(tp, Config3, RTL_R8(tp, Config3) & ~Beacon_en); if (tp->dev->mtu <= ETH_DATA_LEN) rtl_tx_performance_tweak(pdev, 0x5 << MAX_READ_REQUEST_SHIFT); rtl_disable_clock_request(pdev); - RTL_W16(CPlusCmd, RTL_R16(CPlusCmd) & ~R8168_CPCMD_QUIRK_MASK); + RTL_W16(tp, CPlusCmd, RTL_R16(tp, CPlusCmd) & ~R8168_CPCMD_QUIRK_MASK); } static void rtl_hw_start_8168cp_1(struct rtl8169_private *tp) @@ -5951,42 +5781,39 @@ static void rtl_hw_start_8168cp_1(struct rtl8169_private *tp) static void rtl_hw_start_8168cp_2(struct rtl8169_private *tp) { - void __iomem *ioaddr = tp->mmio_addr; struct pci_dev *pdev = tp->pci_dev; rtl_csi_access_enable_2(tp); - RTL_W8(Config3, RTL_R8(Config3) & ~Beacon_en); + RTL_W8(tp, Config3, RTL_R8(tp, Config3) & ~Beacon_en); if (tp->dev->mtu <= ETH_DATA_LEN) rtl_tx_performance_tweak(pdev, 0x5 << MAX_READ_REQUEST_SHIFT); - RTL_W16(CPlusCmd, RTL_R16(CPlusCmd) & ~R8168_CPCMD_QUIRK_MASK); + RTL_W16(tp, CPlusCmd, RTL_R16(tp, CPlusCmd) & ~R8168_CPCMD_QUIRK_MASK); } static void rtl_hw_start_8168cp_3(struct rtl8169_private *tp) { - void __iomem *ioaddr = tp->mmio_addr; struct pci_dev *pdev = tp->pci_dev; rtl_csi_access_enable_2(tp); - RTL_W8(Config3, RTL_R8(Config3) & ~Beacon_en); + RTL_W8(tp, Config3, RTL_R8(tp, Config3) & ~Beacon_en); /* Magic. */ - RTL_W8(DBG_REG, 0x20); + RTL_W8(tp, DBG_REG, 0x20); - RTL_W8(MaxTxPacketSize, TxPacketMax); + RTL_W8(tp, MaxTxPacketSize, TxPacketMax); if (tp->dev->mtu <= ETH_DATA_LEN) rtl_tx_performance_tweak(pdev, 0x5 << MAX_READ_REQUEST_SHIFT); - RTL_W16(CPlusCmd, RTL_R16(CPlusCmd) & ~R8168_CPCMD_QUIRK_MASK); + RTL_W16(tp, CPlusCmd, RTL_R16(tp, CPlusCmd) & ~R8168_CPCMD_QUIRK_MASK); } static void rtl_hw_start_8168c_1(struct rtl8169_private *tp) { - void __iomem *ioaddr = tp->mmio_addr; static const struct ephy_info e_info_8168c_1[] = { { 0x02, 0x0800, 0x1000 }, { 0x03, 0, 0x0002 }, @@ -5995,7 +5822,7 @@ static void rtl_hw_start_8168c_1(struct rtl8169_private *tp) rtl_csi_access_enable_2(tp); - RTL_W8(DBG_REG, 0x06 | FIX_NAK_1 | FIX_NAK_2); + RTL_W8(tp, DBG_REG, 0x06 | FIX_NAK_1 | FIX_NAK_2); rtl_ephy_init(tp, e_info_8168c_1, ARRAY_SIZE(e_info_8168c_1)); @@ -6030,24 +5857,22 @@ static void rtl_hw_start_8168c_4(struct rtl8169_private *tp) static void rtl_hw_start_8168d(struct rtl8169_private *tp) { - void __iomem *ioaddr = tp->mmio_addr; struct pci_dev *pdev = tp->pci_dev; rtl_csi_access_enable_2(tp); rtl_disable_clock_request(pdev); - RTL_W8(MaxTxPacketSize, TxPacketMax); + RTL_W8(tp, MaxTxPacketSize, TxPacketMax); if (tp->dev->mtu <= ETH_DATA_LEN) rtl_tx_performance_tweak(pdev, 0x5 << MAX_READ_REQUEST_SHIFT); - RTL_W16(CPlusCmd, RTL_R16(CPlusCmd) & ~R8168_CPCMD_QUIRK_MASK); + RTL_W16(tp, CPlusCmd, RTL_R16(tp, CPlusCmd) & ~R8168_CPCMD_QUIRK_MASK); } static void rtl_hw_start_8168dp(struct rtl8169_private *tp) { - void __iomem *ioaddr = tp->mmio_addr; struct pci_dev *pdev = tp->pci_dev; rtl_csi_access_enable_1(tp); @@ -6055,14 +5880,13 @@ static void rtl_hw_start_8168dp(struct rtl8169_private *tp) if (tp->dev->mtu <= ETH_DATA_LEN) rtl_tx_performance_tweak(pdev, 0x5 << MAX_READ_REQUEST_SHIFT); - RTL_W8(MaxTxPacketSize, TxPacketMax); + RTL_W8(tp, MaxTxPacketSize, TxPacketMax); rtl_disable_clock_request(pdev); } static void rtl_hw_start_8168d_4(struct rtl8169_private *tp) { - void __iomem *ioaddr = tp->mmio_addr; struct pci_dev *pdev = tp->pci_dev; static const struct ephy_info e_info_8168d_4[] = { { 0x0b, 0x0000, 0x0048 }, @@ -6074,7 +5898,7 @@ static void rtl_hw_start_8168d_4(struct rtl8169_private *tp) rtl_tx_performance_tweak(pdev, 0x5 << MAX_READ_REQUEST_SHIFT); - RTL_W8(MaxTxPacketSize, TxPacketMax); + RTL_W8(tp, MaxTxPacketSize, TxPacketMax); rtl_ephy_init(tp, e_info_8168d_4, ARRAY_SIZE(e_info_8168d_4)); @@ -6083,7 +5907,6 @@ static void rtl_hw_start_8168d_4(struct rtl8169_private *tp) static void rtl_hw_start_8168e_1(struct rtl8169_private *tp) { - void __iomem *ioaddr = tp->mmio_addr; struct pci_dev *pdev = tp->pci_dev; static const struct ephy_info e_info_8168e_1[] = { { 0x00, 0x0200, 0x0100 }, @@ -6108,20 +5931,19 @@ static void rtl_hw_start_8168e_1(struct rtl8169_private *tp) if (tp->dev->mtu <= ETH_DATA_LEN) rtl_tx_performance_tweak(pdev, 0x5 << MAX_READ_REQUEST_SHIFT); - RTL_W8(MaxTxPacketSize, TxPacketMax); + RTL_W8(tp, MaxTxPacketSize, TxPacketMax); rtl_disable_clock_request(pdev); /* Reset tx FIFO pointer */ - RTL_W32(MISC, RTL_R32(MISC) | TXPLA_RST); - RTL_W32(MISC, RTL_R32(MISC) & ~TXPLA_RST); + RTL_W32(tp, MISC, RTL_R32(tp, MISC) | TXPLA_RST); + RTL_W32(tp, MISC, RTL_R32(tp, MISC) & ~TXPLA_RST); - RTL_W8(Config5, RTL_R8(Config5) & ~Spi_en); + RTL_W8(tp, Config5, RTL_R8(tp, Config5) & ~Spi_en); } static void rtl_hw_start_8168e_2(struct rtl8169_private *tp) { - void __iomem *ioaddr = tp->mmio_addr; struct pci_dev *pdev = tp->pci_dev; static const struct ephy_info e_info_8168e_2[] = { { 0x09, 0x0000, 0x0080 }, @@ -6144,24 +5966,23 @@ static void rtl_hw_start_8168e_2(struct rtl8169_private *tp) rtl_w0w1_eri(tp, 0x1b0, ERIAR_MASK_0001, 0x10, 0x00, ERIAR_EXGMAC); rtl_w0w1_eri(tp, 0x0d4, ERIAR_MASK_0011, 0x0c00, 0xff00, ERIAR_EXGMAC); - RTL_W8(MaxTxPacketSize, EarlySize); + RTL_W8(tp, MaxTxPacketSize, EarlySize); rtl_disable_clock_request(pdev); - RTL_W32(TxConfig, RTL_R32(TxConfig) | TXCFG_AUTO_FIFO); - RTL_W8(MCU, RTL_R8(MCU) & ~NOW_IS_OOB); + RTL_W32(tp, TxConfig, RTL_R32(tp, TxConfig) | TXCFG_AUTO_FIFO); + RTL_W8(tp, MCU, RTL_R8(tp, MCU) & ~NOW_IS_OOB); /* Adjust EEE LED frequency */ - RTL_W8(EEE_LED, RTL_R8(EEE_LED) & ~0x07); + RTL_W8(tp, EEE_LED, RTL_R8(tp, EEE_LED) & ~0x07); - RTL_W8(DLLPR, RTL_R8(DLLPR) | PFM_EN); - RTL_W32(MISC, RTL_R32(MISC) | PWM_EN); - RTL_W8(Config5, RTL_R8(Config5) & ~Spi_en); + RTL_W8(tp, DLLPR, RTL_R8(tp, DLLPR) | PFM_EN); + RTL_W32(tp, MISC, RTL_R32(tp, MISC) | PWM_EN); + RTL_W8(tp, Config5, RTL_R8(tp, Config5) & ~Spi_en); } static void rtl_hw_start_8168f(struct rtl8169_private *tp) { - void __iomem *ioaddr = tp->mmio_addr; struct pci_dev *pdev = tp->pci_dev; rtl_csi_access_enable_2(tp); @@ -6179,20 +6000,19 @@ static void rtl_hw_start_8168f(struct rtl8169_private *tp) rtl_eri_write(tp, 0xcc, ERIAR_MASK_1111, 0x00000050, ERIAR_EXGMAC); rtl_eri_write(tp, 0xd0, ERIAR_MASK_1111, 0x00000060, ERIAR_EXGMAC); - RTL_W8(MaxTxPacketSize, EarlySize); + RTL_W8(tp, MaxTxPacketSize, EarlySize); rtl_disable_clock_request(pdev); - RTL_W32(TxConfig, RTL_R32(TxConfig) | TXCFG_AUTO_FIFO); - RTL_W8(MCU, RTL_R8(MCU) & ~NOW_IS_OOB); - RTL_W8(DLLPR, RTL_R8(DLLPR) | PFM_EN); - RTL_W32(MISC, RTL_R32(MISC) | PWM_EN); - RTL_W8(Config5, RTL_R8(Config5) & ~Spi_en); + RTL_W32(tp, TxConfig, RTL_R32(tp, TxConfig) | TXCFG_AUTO_FIFO); + RTL_W8(tp, MCU, RTL_R8(tp, MCU) & ~NOW_IS_OOB); + RTL_W8(tp, DLLPR, RTL_R8(tp, DLLPR) | PFM_EN); + RTL_W32(tp, MISC, RTL_R32(tp, MISC) | PWM_EN); + RTL_W8(tp, Config5, RTL_R8(tp, Config5) & ~Spi_en); } static void rtl_hw_start_8168f_1(struct rtl8169_private *tp) { - void __iomem *ioaddr = tp->mmio_addr; static const struct ephy_info e_info_8168f_1[] = { { 0x06, 0x00c0, 0x0020 }, { 0x08, 0x0001, 0x0002 }, @@ -6207,7 +6027,7 @@ static void rtl_hw_start_8168f_1(struct rtl8169_private *tp) rtl_w0w1_eri(tp, 0x0d4, ERIAR_MASK_0011, 0x0c00, 0xff00, ERIAR_EXGMAC); /* Adjust EEE LED frequency */ - RTL_W8(EEE_LED, RTL_R8(EEE_LED) & ~0x07); + RTL_W8(tp, EEE_LED, RTL_R8(tp, EEE_LED) & ~0x07); } static void rtl_hw_start_8411(struct rtl8169_private *tp) @@ -6229,10 +6049,9 @@ static void rtl_hw_start_8411(struct rtl8169_private *tp) static void rtl_hw_start_8168g(struct rtl8169_private *tp) { - void __iomem *ioaddr = tp->mmio_addr; struct pci_dev *pdev = tp->pci_dev; - RTL_W32(TxConfig, RTL_R32(TxConfig) | TXCFG_AUTO_FIFO); + RTL_W32(tp, TxConfig, RTL_R32(tp, TxConfig) | TXCFG_AUTO_FIFO); rtl_eri_write(tp, 0xc8, ERIAR_MASK_0101, 0x080002, ERIAR_EXGMAC); rtl_eri_write(tp, 0xcc, ERIAR_MASK_0001, 0x38, ERIAR_EXGMAC); @@ -6247,14 +6066,14 @@ static void rtl_hw_start_8168g(struct rtl8169_private *tp) rtl_w0w1_eri(tp, 0xdc, ERIAR_MASK_0001, 0x01, 0x00, ERIAR_EXGMAC); rtl_eri_write(tp, 0x2f8, ERIAR_MASK_0011, 0x1d8f, ERIAR_EXGMAC); - RTL_W32(MISC, RTL_R32(MISC) & ~RXDV_GATED_EN); - RTL_W8(MaxTxPacketSize, EarlySize); + RTL_W32(tp, MISC, RTL_R32(tp, MISC) & ~RXDV_GATED_EN); + RTL_W8(tp, MaxTxPacketSize, EarlySize); rtl_eri_write(tp, 0xc0, ERIAR_MASK_0011, 0x0000, ERIAR_EXGMAC); rtl_eri_write(tp, 0xb8, ERIAR_MASK_0011, 0x0000, ERIAR_EXGMAC); /* Adjust EEE LED frequency */ - RTL_W8(EEE_LED, RTL_R8(EEE_LED) & ~0x07); + RTL_W8(tp, EEE_LED, RTL_R8(tp, EEE_LED) & ~0x07); rtl_w0w1_eri(tp, 0x2fc, ERIAR_MASK_0001, 0x01, 0x06, ERIAR_EXGMAC); rtl_w0w1_eri(tp, 0x1b0, ERIAR_MASK_0011, 0x0000, 0x1000, ERIAR_EXGMAC); @@ -6264,7 +6083,6 @@ static void rtl_hw_start_8168g(struct rtl8169_private *tp) static void rtl_hw_start_8168g_1(struct rtl8169_private *tp) { - void __iomem *ioaddr = tp->mmio_addr; static const struct ephy_info e_info_8168g_1[] = { { 0x00, 0x0000, 0x0008 }, { 0x0c, 0x37d0, 0x0820 }, @@ -6275,14 +6093,13 @@ static void rtl_hw_start_8168g_1(struct rtl8169_private *tp) rtl_hw_start_8168g(tp); /* disable aspm and clock request before access ephy */ - RTL_W8(Config2, RTL_R8(Config2) & ~ClkReqEn); - RTL_W8(Config5, RTL_R8(Config5) & ~ASPM_en); + RTL_W8(tp, Config2, RTL_R8(tp, Config2) & ~ClkReqEn); + RTL_W8(tp, Config5, RTL_R8(tp, Config5) & ~ASPM_en); rtl_ephy_init(tp, e_info_8168g_1, ARRAY_SIZE(e_info_8168g_1)); } static void rtl_hw_start_8168g_2(struct rtl8169_private *tp) { - void __iomem *ioaddr = tp->mmio_addr; static const struct ephy_info e_info_8168g_2[] = { { 0x00, 0x0000, 0x0008 }, { 0x0c, 0x3df0, 0x0200 }, @@ -6293,14 +6110,13 @@ static void rtl_hw_start_8168g_2(struct rtl8169_private *tp) rtl_hw_start_8168g(tp); /* disable aspm and clock request before access ephy */ - RTL_W8(Config2, RTL_R8(Config2) & ~ClkReqEn); - RTL_W8(Config5, RTL_R8(Config5) & ~ASPM_en); + RTL_W8(tp, Config2, RTL_R8(tp, Config2) & ~ClkReqEn); + RTL_W8(tp, Config5, RTL_R8(tp, Config5) & ~ASPM_en); rtl_ephy_init(tp, e_info_8168g_2, ARRAY_SIZE(e_info_8168g_2)); } static void rtl_hw_start_8411_2(struct rtl8169_private *tp) { - void __iomem *ioaddr = tp->mmio_addr; static const struct ephy_info e_info_8411_2[] = { { 0x00, 0x0000, 0x0008 }, { 0x0c, 0x3df0, 0x0200 }, @@ -6312,14 +6128,13 @@ static void rtl_hw_start_8411_2(struct rtl8169_private *tp) rtl_hw_start_8168g(tp); /* disable aspm and clock request before access ephy */ - RTL_W8(Config2, RTL_R8(Config2) & ~ClkReqEn); - RTL_W8(Config5, RTL_R8(Config5) & ~ASPM_en); + RTL_W8(tp, Config2, RTL_R8(tp, Config2) & ~ClkReqEn); + RTL_W8(tp, Config5, RTL_R8(tp, Config5) & ~ASPM_en); rtl_ephy_init(tp, e_info_8411_2, ARRAY_SIZE(e_info_8411_2)); } static void rtl_hw_start_8168h_1(struct rtl8169_private *tp) { - void __iomem *ioaddr = tp->mmio_addr; struct pci_dev *pdev = tp->pci_dev; int rg_saw_cnt; u32 data; @@ -6333,11 +6148,11 @@ static void rtl_hw_start_8168h_1(struct rtl8169_private *tp) }; /* disable aspm and clock request before access ephy */ - RTL_W8(Config2, RTL_R8(Config2) & ~ClkReqEn); - RTL_W8(Config5, RTL_R8(Config5) & ~ASPM_en); + RTL_W8(tp, Config2, RTL_R8(tp, Config2) & ~ClkReqEn); + RTL_W8(tp, Config5, RTL_R8(tp, Config5) & ~ASPM_en); rtl_ephy_init(tp, e_info_8168h_1, ARRAY_SIZE(e_info_8168h_1)); - RTL_W32(TxConfig, RTL_R32(TxConfig) | TXCFG_AUTO_FIFO); + RTL_W32(tp, TxConfig, RTL_R32(tp, TxConfig) | TXCFG_AUTO_FIFO); rtl_eri_write(tp, 0xc8, ERIAR_MASK_0101, 0x00080002, ERIAR_EXGMAC); rtl_eri_write(tp, 0xcc, ERIAR_MASK_0001, 0x38, ERIAR_EXGMAC); @@ -6357,19 +6172,19 @@ static void rtl_hw_start_8168h_1(struct rtl8169_private *tp) rtl_eri_write(tp, 0x5f0, ERIAR_MASK_0011, 0x4f87, ERIAR_EXGMAC); - RTL_W32(MISC, RTL_R32(MISC) & ~RXDV_GATED_EN); - RTL_W8(MaxTxPacketSize, EarlySize); + RTL_W32(tp, MISC, RTL_R32(tp, MISC) & ~RXDV_GATED_EN); + RTL_W8(tp, MaxTxPacketSize, EarlySize); rtl_eri_write(tp, 0xc0, ERIAR_MASK_0011, 0x0000, ERIAR_EXGMAC); rtl_eri_write(tp, 0xb8, ERIAR_MASK_0011, 0x0000, ERIAR_EXGMAC); /* Adjust EEE LED frequency */ - RTL_W8(EEE_LED, RTL_R8(EEE_LED) & ~0x07); + RTL_W8(tp, EEE_LED, RTL_R8(tp, EEE_LED) & ~0x07); - RTL_W8(DLLPR, RTL_R8(DLLPR) & ~PFM_EN); - RTL_W8(MISC_1, RTL_R8(MISC_1) & ~PFM_D3COLD_EN); + RTL_W8(tp, DLLPR, RTL_R8(tp, DLLPR) & ~PFM_EN); + RTL_W8(tp, MISC_1, RTL_R8(tp, MISC_1) & ~PFM_D3COLD_EN); - RTL_W8(DLLPR, RTL_R8(DLLPR) & ~TX_10M_PS_EN); + RTL_W8(tp, DLLPR, RTL_R8(tp, DLLPR) & ~TX_10M_PS_EN); rtl_w0w1_eri(tp, 0x1b0, ERIAR_MASK_0011, 0x0000, 0x1000, ERIAR_EXGMAC); @@ -6417,12 +6232,11 @@ static void rtl_hw_start_8168h_1(struct rtl8169_private *tp) static void rtl_hw_start_8168ep(struct rtl8169_private *tp) { - void __iomem *ioaddr = tp->mmio_addr; struct pci_dev *pdev = tp->pci_dev; rtl8168ep_stop_cmac(tp); - RTL_W32(TxConfig, RTL_R32(TxConfig) | TXCFG_AUTO_FIFO); + RTL_W32(tp, TxConfig, RTL_R32(tp, TxConfig) | TXCFG_AUTO_FIFO); rtl_eri_write(tp, 0xc8, ERIAR_MASK_0101, 0x00080002, ERIAR_EXGMAC); rtl_eri_write(tp, 0xcc, ERIAR_MASK_0001, 0x2f, ERIAR_EXGMAC); @@ -6440,25 +6254,24 @@ static void rtl_hw_start_8168ep(struct rtl8169_private *tp) rtl_eri_write(tp, 0x5f0, ERIAR_MASK_0011, 0x4f87, ERIAR_EXGMAC); - RTL_W32(MISC, RTL_R32(MISC) & ~RXDV_GATED_EN); - RTL_W8(MaxTxPacketSize, EarlySize); + RTL_W32(tp, MISC, RTL_R32(tp, MISC) & ~RXDV_GATED_EN); + RTL_W8(tp, MaxTxPacketSize, EarlySize); rtl_eri_write(tp, 0xc0, ERIAR_MASK_0011, 0x0000, ERIAR_EXGMAC); rtl_eri_write(tp, 0xb8, ERIAR_MASK_0011, 0x0000, ERIAR_EXGMAC); /* Adjust EEE LED frequency */ - RTL_W8(EEE_LED, RTL_R8(EEE_LED) & ~0x07); + RTL_W8(tp, EEE_LED, RTL_R8(tp, EEE_LED) & ~0x07); rtl_w0w1_eri(tp, 0x2fc, ERIAR_MASK_0001, 0x01, 0x06, ERIAR_EXGMAC); - RTL_W8(DLLPR, RTL_R8(DLLPR) & ~TX_10M_PS_EN); + RTL_W8(tp, DLLPR, RTL_R8(tp, DLLPR) & ~TX_10M_PS_EN); rtl_pcie_state_l2l3_enable(tp, false); } static void rtl_hw_start_8168ep_1(struct rtl8169_private *tp) { - void __iomem *ioaddr = tp->mmio_addr; static const struct ephy_info e_info_8168ep_1[] = { { 0x00, 0xffff, 0x10ab }, { 0x06, 0xffff, 0xf030 }, @@ -6468,8 +6281,8 @@ static void rtl_hw_start_8168ep_1(struct rtl8169_private *tp) }; /* disable aspm and clock request before access ephy */ - RTL_W8(Config2, RTL_R8(Config2) & ~ClkReqEn); - RTL_W8(Config5, RTL_R8(Config5) & ~ASPM_en); + RTL_W8(tp, Config2, RTL_R8(tp, Config2) & ~ClkReqEn); + RTL_W8(tp, Config5, RTL_R8(tp, Config5) & ~ASPM_en); rtl_ephy_init(tp, e_info_8168ep_1, ARRAY_SIZE(e_info_8168ep_1)); rtl_hw_start_8168ep(tp); @@ -6477,7 +6290,6 @@ static void rtl_hw_start_8168ep_1(struct rtl8169_private *tp) static void rtl_hw_start_8168ep_2(struct rtl8169_private *tp) { - void __iomem *ioaddr = tp->mmio_addr; static const struct ephy_info e_info_8168ep_2[] = { { 0x00, 0xffff, 0x10a3 }, { 0x19, 0xffff, 0xfc00 }, @@ -6485,19 +6297,18 @@ static void rtl_hw_start_8168ep_2(struct rtl8169_private *tp) }; /* disable aspm and clock request before access ephy */ - RTL_W8(Config2, RTL_R8(Config2) & ~ClkReqEn); - RTL_W8(Config5, RTL_R8(Config5) & ~ASPM_en); + RTL_W8(tp, Config2, RTL_R8(tp, Config2) & ~ClkReqEn); + RTL_W8(tp, Config5, RTL_R8(tp, Config5) & ~ASPM_en); rtl_ephy_init(tp, e_info_8168ep_2, ARRAY_SIZE(e_info_8168ep_2)); rtl_hw_start_8168ep(tp); - RTL_W8(DLLPR, RTL_R8(DLLPR) & ~PFM_EN); - RTL_W8(MISC_1, RTL_R8(MISC_1) & ~PFM_D3COLD_EN); + RTL_W8(tp, DLLPR, RTL_R8(tp, DLLPR) & ~PFM_EN); + RTL_W8(tp, MISC_1, RTL_R8(tp, MISC_1) & ~PFM_D3COLD_EN); } static void rtl_hw_start_8168ep_3(struct rtl8169_private *tp) { - void __iomem *ioaddr = tp->mmio_addr; u32 data; static const struct ephy_info e_info_8168ep_3[] = { { 0x00, 0xffff, 0x10a3 }, @@ -6507,14 +6318,14 @@ static void rtl_hw_start_8168ep_3(struct rtl8169_private *tp) }; /* disable aspm and clock request before access ephy */ - RTL_W8(Config2, RTL_R8(Config2) & ~ClkReqEn); - RTL_W8(Config5, RTL_R8(Config5) & ~ASPM_en); + RTL_W8(tp, Config2, RTL_R8(tp, Config2) & ~ClkReqEn); + RTL_W8(tp, Config5, RTL_R8(tp, Config5) & ~ASPM_en); rtl_ephy_init(tp, e_info_8168ep_3, ARRAY_SIZE(e_info_8168ep_3)); rtl_hw_start_8168ep(tp); - RTL_W8(DLLPR, RTL_R8(DLLPR) & ~PFM_EN); - RTL_W8(MISC_1, RTL_R8(MISC_1) & ~PFM_D3COLD_EN); + RTL_W8(tp, DLLPR, RTL_R8(tp, DLLPR) & ~PFM_EN); + RTL_W8(tp, MISC_1, RTL_R8(tp, MISC_1) & ~PFM_D3COLD_EN); data = r8168_mac_ocp_read(tp, 0xd3e2); data &= 0xf000; @@ -6533,19 +6344,18 @@ static void rtl_hw_start_8168ep_3(struct rtl8169_private *tp) static void rtl_hw_start_8168(struct net_device *dev) { struct rtl8169_private *tp = netdev_priv(dev); - void __iomem *ioaddr = tp->mmio_addr; - RTL_W8(Cfg9346, Cfg9346_Unlock); + RTL_W8(tp, Cfg9346, Cfg9346_Unlock); - RTL_W8(MaxTxPacketSize, TxPacketMax); + RTL_W8(tp, MaxTxPacketSize, TxPacketMax); - rtl_set_rx_max_size(ioaddr, rx_buf_sz); + rtl_set_rx_max_size(tp, rx_buf_sz); - tp->cp_cmd |= RTL_R16(CPlusCmd) | PktCntrDisable | INTT_1; + tp->cp_cmd |= RTL_R16(tp, CPlusCmd) | PktCntrDisable | INTT_1; - RTL_W16(CPlusCmd, tp->cp_cmd); + RTL_W16(tp, CPlusCmd, tp->cp_cmd); - RTL_W16(IntrMitigate, 0x5151); + RTL_W16(tp, IntrMitigate, 0x5151); /* Work around for RxFIFO overflow. */ if (tp->mac_version == RTL_GIGA_MAC_VER_11) { @@ -6553,11 +6363,11 @@ static void rtl_hw_start_8168(struct net_device *dev) tp->event_slow &= ~RxOverflow; } - rtl_set_rx_tx_desc_registers(tp, ioaddr); + rtl_set_rx_tx_desc_registers(tp); rtl_set_rx_tx_config_registers(tp); - RTL_R8(IntrMask); + RTL_R8(tp, IntrMask); switch (tp->mac_version) { case RTL_GIGA_MAC_VER_11: @@ -6663,13 +6473,13 @@ static void rtl_hw_start_8168(struct net_device *dev) break; } - RTL_W8(Cfg9346, Cfg9346_Lock); + RTL_W8(tp, Cfg9346, Cfg9346_Lock); - RTL_W8(ChipCmd, CmdTxEnb | CmdRxEnb); + RTL_W8(tp, ChipCmd, CmdTxEnb | CmdRxEnb); rtl_set_rx_mode(dev); - RTL_W16(MultiIntr, RTL_R16(MultiIntr) & 0xf000); + RTL_W16(tp, MultiIntr, RTL_R16(tp, MultiIntr) & 0xf000); } #define R810X_CPCMD_QUIRK_MASK (\ @@ -6685,7 +6495,6 @@ static void rtl_hw_start_8168(struct net_device *dev) static void rtl_hw_start_8102e_1(struct rtl8169_private *tp) { - void __iomem *ioaddr = tp->mmio_addr; struct pci_dev *pdev = tp->pci_dev; static const struct ephy_info e_info_8102e_1[] = { { 0x01, 0, 0x6e65 }, @@ -6701,32 +6510,31 @@ static void rtl_hw_start_8102e_1(struct rtl8169_private *tp) rtl_csi_access_enable_2(tp); - RTL_W8(DBG_REG, FIX_NAK_1); + RTL_W8(tp, DBG_REG, FIX_NAK_1); rtl_tx_performance_tweak(pdev, 0x5 << MAX_READ_REQUEST_SHIFT); - RTL_W8(Config1, + RTL_W8(tp, Config1, LEDS1 | LEDS0 | Speed_down | MEMMAP | IOMAP | VPD | PMEnable); - RTL_W8(Config3, RTL_R8(Config3) & ~Beacon_en); + RTL_W8(tp, Config3, RTL_R8(tp, Config3) & ~Beacon_en); - cfg1 = RTL_R8(Config1); + cfg1 = RTL_R8(tp, Config1); if ((cfg1 & LEDS0) && (cfg1 & LEDS1)) - RTL_W8(Config1, cfg1 & ~LEDS0); + RTL_W8(tp, Config1, cfg1 & ~LEDS0); rtl_ephy_init(tp, e_info_8102e_1, ARRAY_SIZE(e_info_8102e_1)); } static void rtl_hw_start_8102e_2(struct rtl8169_private *tp) { - void __iomem *ioaddr = tp->mmio_addr; struct pci_dev *pdev = tp->pci_dev; rtl_csi_access_enable_2(tp); rtl_tx_performance_tweak(pdev, 0x5 << MAX_READ_REQUEST_SHIFT); - RTL_W8(Config1, MEMMAP | IOMAP | VPD | PMEnable); - RTL_W8(Config3, RTL_R8(Config3) & ~Beacon_en); + RTL_W8(tp, Config1, MEMMAP | IOMAP | VPD | PMEnable); + RTL_W8(tp, Config3, RTL_R8(tp, Config3) & ~Beacon_en); } static void rtl_hw_start_8102e_3(struct rtl8169_private *tp) @@ -6738,7 +6546,6 @@ static void rtl_hw_start_8102e_3(struct rtl8169_private *tp) static void rtl_hw_start_8105e_1(struct rtl8169_private *tp) { - void __iomem *ioaddr = tp->mmio_addr; static const struct ephy_info e_info_8105e_1[] = { { 0x07, 0, 0x4000 }, { 0x19, 0, 0x0200 }, @@ -6751,13 +6558,13 @@ static void rtl_hw_start_8105e_1(struct rtl8169_private *tp) }; /* Force LAN exit from ASPM if Rx/Tx are not idle */ - RTL_W32(FuncEvent, RTL_R32(FuncEvent) | 0x002800); + RTL_W32(tp, FuncEvent, RTL_R32(tp, FuncEvent) | 0x002800); /* Disable Early Tally Counter */ - RTL_W32(FuncEvent, RTL_R32(FuncEvent) & ~0x010000); + RTL_W32(tp, FuncEvent, RTL_R32(tp, FuncEvent) & ~0x010000); - RTL_W8(MCU, RTL_R8(MCU) | EN_NDP | EN_OOB_RESET); - RTL_W8(DLLPR, RTL_R8(DLLPR) | PFM_EN); + RTL_W8(tp, MCU, RTL_R8(tp, MCU) | EN_NDP | EN_OOB_RESET); + RTL_W8(tp, DLLPR, RTL_R8(tp, DLLPR) | PFM_EN); rtl_ephy_init(tp, e_info_8105e_1, ARRAY_SIZE(e_info_8105e_1)); @@ -6772,7 +6579,6 @@ static void rtl_hw_start_8105e_2(struct rtl8169_private *tp) static void rtl_hw_start_8402(struct rtl8169_private *tp) { - void __iomem *ioaddr = tp->mmio_addr; static const struct ephy_info e_info_8402[] = { { 0x19, 0xffff, 0xff64 }, { 0x1e, 0, 0x4000 } @@ -6781,10 +6587,10 @@ static void rtl_hw_start_8402(struct rtl8169_private *tp) rtl_csi_access_enable_2(tp); /* Force LAN exit from ASPM if Rx/Tx are not idle */ - RTL_W32(FuncEvent, RTL_R32(FuncEvent) | 0x002800); + RTL_W32(tp, FuncEvent, RTL_R32(tp, FuncEvent) | 0x002800); - RTL_W32(TxConfig, RTL_R32(TxConfig) | TXCFG_AUTO_FIFO); - RTL_W8(MCU, RTL_R8(MCU) & ~NOW_IS_OOB); + RTL_W32(tp, TxConfig, RTL_R32(tp, TxConfig) | TXCFG_AUTO_FIFO); + RTL_W8(tp, MCU, RTL_R8(tp, MCU) & ~NOW_IS_OOB); rtl_ephy_init(tp, e_info_8402, ARRAY_SIZE(e_info_8402)); @@ -6803,14 +6609,12 @@ static void rtl_hw_start_8402(struct rtl8169_private *tp) static void rtl_hw_start_8106(struct rtl8169_private *tp) { - void __iomem *ioaddr = tp->mmio_addr; - /* Force LAN exit from ASPM if Rx/Tx are not idle */ - RTL_W32(FuncEvent, RTL_R32(FuncEvent) | 0x002800); + RTL_W32(tp, FuncEvent, RTL_R32(tp, FuncEvent) | 0x002800); - RTL_W32(MISC, (RTL_R32(MISC) | DISABLE_LAN_EN) & ~EARLY_TALLY_EN); - RTL_W8(MCU, RTL_R8(MCU) | EN_NDP | EN_OOB_RESET); - RTL_W8(DLLPR, RTL_R8(DLLPR) & ~PFM_EN); + RTL_W32(tp, MISC, (RTL_R32(tp, MISC) | DISABLE_LAN_EN) & ~EARLY_TALLY_EN); + RTL_W8(tp, MCU, RTL_R8(tp, MCU) | EN_NDP | EN_OOB_RESET); + RTL_W8(tp, DLLPR, RTL_R8(tp, DLLPR) & ~PFM_EN); rtl_pcie_state_l2l3_enable(tp, false); } @@ -6818,7 +6622,6 @@ static void rtl_hw_start_8106(struct rtl8169_private *tp) static void rtl_hw_start_8101(struct net_device *dev) { struct rtl8169_private *tp = netdev_priv(dev); - void __iomem *ioaddr = tp->mmio_addr; struct pci_dev *pdev = tp->pci_dev; if (tp->mac_version >= RTL_GIGA_MAC_VER_30) @@ -6829,16 +6632,16 @@ static void rtl_hw_start_8101(struct net_device *dev) pcie_capability_set_word(pdev, PCI_EXP_DEVCTL, PCI_EXP_DEVCTL_NOSNOOP_EN); - RTL_W8(Cfg9346, Cfg9346_Unlock); + RTL_W8(tp, Cfg9346, Cfg9346_Unlock); - RTL_W8(MaxTxPacketSize, TxPacketMax); + RTL_W8(tp, MaxTxPacketSize, TxPacketMax); - rtl_set_rx_max_size(ioaddr, rx_buf_sz); + rtl_set_rx_max_size(tp, rx_buf_sz); tp->cp_cmd &= ~R810X_CPCMD_QUIRK_MASK; - RTL_W16(CPlusCmd, tp->cp_cmd); + RTL_W16(tp, CPlusCmd, tp->cp_cmd); - rtl_set_rx_tx_desc_registers(tp, ioaddr); + rtl_set_rx_tx_desc_registers(tp); rtl_set_rx_tx_config_registers(tp); @@ -6878,17 +6681,17 @@ static void rtl_hw_start_8101(struct net_device *dev) break; } - RTL_W8(Cfg9346, Cfg9346_Lock); + RTL_W8(tp, Cfg9346, Cfg9346_Lock); - RTL_W16(IntrMitigate, 0x0000); + RTL_W16(tp, IntrMitigate, 0x0000); - RTL_W8(ChipCmd, CmdTxEnb | CmdRxEnb); + RTL_W8(tp, ChipCmd, CmdTxEnb | CmdRxEnb); rtl_set_rx_mode(dev); - RTL_R8(IntrMask); + RTL_R8(tp, IntrMask); - RTL_W16(MultiIntr, RTL_R16(MultiIntr) & 0xf000); + RTL_W16(tp, MultiIntr, RTL_R16(tp, MultiIntr) & 0xf000); } static int rtl8169_change_mtu(struct net_device *dev, int new_mtu) @@ -7098,7 +6901,7 @@ static void rtl_reset_work(struct rtl8169_private *tp) napi_enable(&tp->napi); rtl_hw_start(dev); netif_wake_queue(dev); - rtl8169_check_link_status(dev, tp, tp->mmio_addr); + rtl8169_check_link_status(dev, tp); } static void rtl8169_tx_timeout(struct net_device *dev) @@ -7346,7 +7149,6 @@ static netdev_tx_t rtl8169_start_xmit(struct sk_buff *skb, struct rtl8169_private *tp = netdev_priv(dev); unsigned int entry = tp->cur_tx % NUM_TX_DESC; struct TxDesc *txd = tp->TxDescArray + entry; - void __iomem *ioaddr = tp->mmio_addr; struct device *d = &tp->pci_dev->dev; dma_addr_t mapping; u32 status, len; @@ -7406,7 +7208,7 @@ static netdev_tx_t rtl8169_start_xmit(struct sk_buff *skb, tp->cur_tx += frags + 1; - RTL_W8(TxPoll, NPQ); + RTL_W8(tp, TxPoll, NPQ); mmiowb(); @@ -7477,11 +7279,9 @@ static void rtl8169_pcierr_interrupt(struct net_device *dev) /* The infamous DAC f*ckup only happens at boot time */ if ((tp->cp_cmd & PCIDAC) && !tp->cur_rx) { - void __iomem *ioaddr = tp->mmio_addr; - netif_info(tp, intr, dev, "disabling PCI DAC\n"); tp->cp_cmd &= ~PCIDAC; - RTL_W16(CPlusCmd, tp->cp_cmd); + RTL_W16(tp, CPlusCmd, tp->cp_cmd); dev->features &= ~NETIF_F_HIGHDMA; } @@ -7547,11 +7347,8 @@ static void rtl_tx(struct net_device *dev, struct rtl8169_private *tp) * of start_xmit activity is detected (if it is not detected, * it is slow enough). -- FR */ - if (tp->cur_tx != dirty_tx) { - void __iomem *ioaddr = tp->mmio_addr; - - RTL_W8(TxPoll, NPQ); - } + if (tp->cur_tx != dirty_tx) + RTL_W8(tp, TxPoll, NPQ); } } @@ -7732,7 +7529,7 @@ static void rtl_slow_event_work(struct rtl8169_private *tp) rtl8169_pcierr_interrupt(dev); if (status & LinkChg) - rtl8169_check_link_status(dev, tp, tp->mmio_addr); + rtl8169_check_link_status(dev, tp); rtl_irq_enable_all(tp); } @@ -7804,21 +7601,20 @@ static int rtl8169_poll(struct napi_struct *napi, int budget) return work_done; } -static void rtl8169_rx_missed(struct net_device *dev, void __iomem *ioaddr) +static void rtl8169_rx_missed(struct net_device *dev) { struct rtl8169_private *tp = netdev_priv(dev); if (tp->mac_version > RTL_GIGA_MAC_VER_06) return; - dev->stats.rx_missed_errors += (RTL_R32(RxMissed) & 0xffffff); - RTL_W32(RxMissed, 0); + dev->stats.rx_missed_errors += RTL_R32(tp, RxMissed) & 0xffffff; + RTL_W32(tp, RxMissed, 0); } static void rtl8169_down(struct net_device *dev) { struct rtl8169_private *tp = netdev_priv(dev); - void __iomem *ioaddr = tp->mmio_addr; del_timer_sync(&tp->timer); @@ -7831,7 +7627,7 @@ static void rtl8169_down(struct net_device *dev) * as netif_running is not true (rtl8169_interrupt, rtl8169_reset_task) * and napi is disabled (rtl8169_poll). */ - rtl8169_rx_missed(dev, ioaddr); + rtl8169_rx_missed(dev); /* Give a racing hard_start_xmit a few cycles to complete. */ synchronize_sched(); @@ -7861,7 +7657,7 @@ static int rtl8169_close(struct net_device *dev) cancel_work_sync(&tp->wk.work); - free_irq(pdev->irq, dev); + pci_free_irq(pdev, 0, dev); dma_free_coherent(&pdev->dev, R8169_RX_RING_BYTES, tp->RxDescArray, tp->RxPhyAddr); @@ -7880,14 +7676,13 @@ static void rtl8169_netpoll(struct net_device *dev) { struct rtl8169_private *tp = netdev_priv(dev); - rtl8169_interrupt(tp->pci_dev->irq, dev); + rtl8169_interrupt(pci_irq_vector(tp->pci_dev, 0), dev); } #endif static int rtl_open(struct net_device *dev) { struct rtl8169_private *tp = netdev_priv(dev); - void __iomem *ioaddr = tp->mmio_addr; struct pci_dev *pdev = tp->pci_dev; int retval = -ENOMEM; @@ -7917,9 +7712,8 @@ static int rtl_open(struct net_device *dev) rtl_request_firmware(tp); - retval = request_irq(pdev->irq, rtl8169_interrupt, - (tp->features & RTL_FEATURE_MSI) ? 0 : IRQF_SHARED, - dev->name, dev); + retval = pci_request_irq(pdev, 0, rtl8169_interrupt, NULL, dev, + dev->name); if (retval < 0) goto err_release_fw_2; @@ -7947,7 +7741,7 @@ static int rtl_open(struct net_device *dev) tp->saved_wolopts = 0; pm_runtime_put_sync(&pdev->dev); - rtl8169_check_link_status(dev, tp, ioaddr); + rtl8169_check_link_status(dev, tp); out: return retval; @@ -7971,7 +7765,6 @@ static void rtl8169_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats) { struct rtl8169_private *tp = netdev_priv(dev); - void __iomem *ioaddr = tp->mmio_addr; struct pci_dev *pdev = tp->pci_dev; struct rtl8169_counters *counters = tp->counters; unsigned int start; @@ -7979,7 +7772,7 @@ rtl8169_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats) pm_runtime_get_noresume(&pdev->dev); if (netif_running(dev) && pm_runtime_active(&pdev->dev)) - rtl8169_rx_missed(dev, ioaddr); + rtl8169_rx_missed(dev); do { start = u64_stats_fetch_begin_irq(&tp->rx_stats.syncp); @@ -8102,7 +7895,7 @@ static int rtl8169_runtime_suspend(struct device *device) rtl8169_net_suspend(dev); /* Update counters before going runtime suspend */ - rtl8169_rx_missed(dev, tp->mmio_addr); + rtl8169_rx_missed(dev); rtl8169_update_counters(dev); return 0; @@ -8163,8 +7956,6 @@ static const struct dev_pm_ops rtl8169_pm_ops = { static void rtl_wol_shutdown_quirk(struct rtl8169_private *tp) { - void __iomem *ioaddr = tp->mmio_addr; - /* WoL fails with 8168b when the receiver is disabled. */ switch (tp->mac_version) { case RTL_GIGA_MAC_VER_11: @@ -8172,9 +7963,9 @@ static void rtl_wol_shutdown_quirk(struct rtl8169_private *tp) case RTL_GIGA_MAC_VER_17: pci_clear_master(tp->pci_dev); - RTL_W8(ChipCmd, CmdRxEnb); + RTL_W8(tp, ChipCmd, CmdRxEnb); /* PCI commit */ - RTL_R8(ChipCmd); + RTL_R8(tp, ChipCmd); break; default: break; @@ -8209,15 +8000,8 @@ static void rtl_remove_one(struct pci_dev *pdev) struct net_device *dev = pci_get_drvdata(pdev); struct rtl8169_private *tp = netdev_priv(dev); - if ((tp->mac_version == RTL_GIGA_MAC_VER_27 || - tp->mac_version == RTL_GIGA_MAC_VER_28 || - tp->mac_version == RTL_GIGA_MAC_VER_31 || - tp->mac_version == RTL_GIGA_MAC_VER_49 || - tp->mac_version == RTL_GIGA_MAC_VER_50 || - tp->mac_version == RTL_GIGA_MAC_VER_51) && - r8168_check_dash(tp)) { + if (r8168_check_dash(tp)) rtl8168_driver_stop(tp); - } netif_napi_del(&tp->napi); @@ -8256,7 +8040,7 @@ static const struct rtl_cfg_info { unsigned int region; unsigned int align; u16 event_slow; - unsigned features; + unsigned int has_gmii:1; const struct rtl_coalesce_info *coalesce_info; u8 default_ver; } rtl_cfg_infos [] = { @@ -8265,7 +8049,7 @@ static const struct rtl_cfg_info { .region = 1, .align = 0, .event_slow = SYSErr | LinkChg | RxOverflow | RxFIFOOver, - .features = RTL_FEATURE_GMII, + .has_gmii = 1, .coalesce_info = rtl_coalesce_info_8169, .default_ver = RTL_GIGA_MAC_VER_01, }, @@ -8274,7 +8058,7 @@ static const struct rtl_cfg_info { .region = 2, .align = 8, .event_slow = SYSErr | LinkChg | RxOverflow, - .features = RTL_FEATURE_GMII | RTL_FEATURE_MSI, + .has_gmii = 1, .coalesce_info = rtl_coalesce_info_8168_8136, .default_ver = RTL_GIGA_MAC_VER_11, }, @@ -8284,56 +8068,44 @@ static const struct rtl_cfg_info { .align = 8, .event_slow = SYSErr | LinkChg | RxOverflow | RxFIFOOver | PCSTimeout, - .features = RTL_FEATURE_MSI, .coalesce_info = rtl_coalesce_info_8168_8136, .default_ver = RTL_GIGA_MAC_VER_13, } }; -/* Cfg9346_Unlock assumed. */ -static unsigned rtl_try_msi(struct rtl8169_private *tp, - const struct rtl_cfg_info *cfg) +static int rtl_alloc_irq(struct rtl8169_private *tp) { - void __iomem *ioaddr = tp->mmio_addr; - unsigned msi = 0; - u8 cfg2; + unsigned int flags; - cfg2 = RTL_R8(Config2) & ~MSIEnable; - if (cfg->features & RTL_FEATURE_MSI) { - if (pci_enable_msi(tp->pci_dev)) { - netif_info(tp, hw, tp->dev, "no MSI. Back to INTx.\n"); - } else { - cfg2 |= MSIEnable; - msi = RTL_FEATURE_MSI; - } + if (tp->mac_version <= RTL_GIGA_MAC_VER_06) { + RTL_W8(tp, Cfg9346, Cfg9346_Unlock); + RTL_W8(tp, Config2, RTL_R8(tp, Config2) & ~MSIEnable); + RTL_W8(tp, Cfg9346, Cfg9346_Lock); + flags = PCI_IRQ_LEGACY; + } else { + flags = PCI_IRQ_ALL_TYPES; } - if (tp->mac_version <= RTL_GIGA_MAC_VER_06) - RTL_W8(Config2, cfg2); - return msi; + + return pci_alloc_irq_vectors(tp->pci_dev, 1, 1, flags); } DECLARE_RTL_COND(rtl_link_list_ready_cond) { - void __iomem *ioaddr = tp->mmio_addr; - - return RTL_R8(MCU) & LINK_LIST_RDY; + return RTL_R8(tp, MCU) & LINK_LIST_RDY; } DECLARE_RTL_COND(rtl_rxtx_empty_cond) { - void __iomem *ioaddr = tp->mmio_addr; - - return (RTL_R8(MCU) & RXTX_EMPTY) == RXTX_EMPTY; + return (RTL_R8(tp, MCU) & RXTX_EMPTY) == RXTX_EMPTY; } static void rtl_hw_init_8168g(struct rtl8169_private *tp) { - void __iomem *ioaddr = tp->mmio_addr; u32 data; tp->ocp_base = OCP_STD_PHY_BASE; - RTL_W32(MISC, RTL_R32(MISC) | RXDV_GATED_EN); + RTL_W32(tp, MISC, RTL_R32(tp, MISC) | RXDV_GATED_EN); if (!rtl_udelay_loop_wait_high(tp, &rtl_txcfg_empty_cond, 100, 42)) return; @@ -8341,9 +8113,9 @@ static void rtl_hw_init_8168g(struct rtl8169_private *tp) if (!rtl_udelay_loop_wait_high(tp, &rtl_rxtx_empty_cond, 100, 42)) return; - RTL_W8(ChipCmd, RTL_R8(ChipCmd) & ~(CmdTxEnb | CmdRxEnb)); + RTL_W8(tp, ChipCmd, RTL_R8(tp, ChipCmd) & ~(CmdTxEnb | CmdRxEnb)); msleep(1); - RTL_W8(MCU, RTL_R8(MCU) & ~NOW_IS_OOB); + RTL_W8(tp, MCU, RTL_R8(tp, MCU) & ~NOW_IS_OOB); data = r8168_mac_ocp_read(tp, 0xe8de); data &= ~(1 << 14); @@ -8397,7 +8169,6 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) struct rtl8169_private *tp; struct mii_if_info *mii; struct net_device *dev; - void __iomem *ioaddr; int chipset, i; int rc; @@ -8423,7 +8194,7 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) mii->mdio_write = rtl_mdio_write; mii->phy_id_mask = 0x1f; mii->reg_num_mask = 0x1f; - mii->supports_gmii = !!(cfg->features & RTL_FEATURE_GMII); + mii->supports_gmii = cfg->has_gmii; /* disable ASPM completely as that cause random device stop working * problems as well as full system hangs for some PCIe devices users */ @@ -8455,20 +8226,13 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) return -ENODEV; } - rc = pci_request_regions(pdev, MODULENAME); + rc = pcim_iomap_regions(pdev, BIT(region), MODULENAME); if (rc < 0) { - netif_err(tp, probe, dev, "could not request regions\n"); + netif_err(tp, probe, dev, "cannot remap MMIO, aborting\n"); return rc; } - /* ioremap MMIO region */ - ioaddr = devm_ioremap(&pdev->dev, pci_resource_start(pdev, region), - R8169_REGS_SIZE); - if (!ioaddr) { - netif_err(tp, probe, dev, "cannot remap MMIO, aborting\n"); - return -EIO; - } - tp->mmio_addr = ioaddr; + tp->mmio_addr = pcim_iomap_table(pdev)[region]; if (!pci_is_pcie(pdev)) netif_info(tp, probe, dev, "not PCI Express\n"); @@ -8518,41 +8282,14 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) chipset = tp->mac_version; tp->txd_version = rtl_chip_infos[chipset].txd_version; - RTL_W8(Cfg9346, Cfg9346_Unlock); - RTL_W8(Config1, RTL_R8(Config1) | PMEnable); - RTL_W8(Config5, RTL_R8(Config5) & (BWF | MWF | UWF | LanWake | PMEStatus)); - switch (tp->mac_version) { - case RTL_GIGA_MAC_VER_34: - case RTL_GIGA_MAC_VER_35: - case RTL_GIGA_MAC_VER_36: - case RTL_GIGA_MAC_VER_37: - case RTL_GIGA_MAC_VER_38: - case RTL_GIGA_MAC_VER_40: - case RTL_GIGA_MAC_VER_41: - case RTL_GIGA_MAC_VER_42: - case RTL_GIGA_MAC_VER_43: - case RTL_GIGA_MAC_VER_44: - case RTL_GIGA_MAC_VER_45: - case RTL_GIGA_MAC_VER_46: - case RTL_GIGA_MAC_VER_47: - case RTL_GIGA_MAC_VER_48: - case RTL_GIGA_MAC_VER_49: - case RTL_GIGA_MAC_VER_50: - case RTL_GIGA_MAC_VER_51: - if (rtl_eri_read(tp, 0xdc, ERIAR_EXGMAC) & MagicPacket_v2) - tp->features |= RTL_FEATURE_WOL; - if ((RTL_R8(Config3) & LinkUp) != 0) - tp->features |= RTL_FEATURE_WOL; - break; - default: - if ((RTL_R8(Config3) & (LinkUp | MagicPacket)) != 0) - tp->features |= RTL_FEATURE_WOL; - break; + rc = rtl_alloc_irq(tp); + if (rc < 0) { + netif_err(tp, probe, dev, "Can't allocate interrupt\n"); + return rc; } - if ((RTL_R8(Config5) & (UWF | BWF | MWF)) != 0) - tp->features |= RTL_FEATURE_WOL; - tp->features |= rtl_try_msi(tp, cfg); - RTL_W8(Cfg9346, Cfg9346_Lock); + + /* override BIOS settings, use userspace tools to enable WOL */ + __rtl8169_set_wol(tp, 0); if (rtl_tbi_enabled(tp)) { tp->set_speed = rtl8169_set_speed_tbi; @@ -8600,7 +8337,7 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) rtl_rar_set(tp, (u8 *)mac_addr); } for (i = 0; i < ETH_ALEN; i++) - dev->dev_addr[i] = RTL_R8(MAC0 + i); + dev->dev_addr[i] = RTL_R8(tp, MAC0 + i); dev->ethtool_ops = &rtl8169_ethtool_ops; dev->watchdog_timeo = RTL8169_TX_TIMEOUT; @@ -8667,8 +8404,9 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) pci_set_drvdata(pdev, dev); netif_info(tp, probe, dev, "%s at 0x%p, %pM, XID %08x IRQ %d\n", - rtl_chip_infos[chipset].name, ioaddr, dev->dev_addr, - (u32)(RTL_R32(TxConfig) & 0x9cf0f8ff), pdev->irq); + rtl_chip_infos[chipset].name, tp->mmio_addr, dev->dev_addr, + (u32)(RTL_R32(tp, TxConfig) & 0x9cf0f8ff), + pci_irq_vector(pdev, 0)); if (rtl_chip_infos[chipset].jumbo_max != JUMBO_1K) { netif_info(tp, probe, dev, "jumbo features [frames: %d bytes, " "tx checksumming: %s]\n", @@ -8676,15 +8414,8 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) rtl_chip_infos[chipset].jumbo_tx_csum ? "ok" : "ko"); } - if ((tp->mac_version == RTL_GIGA_MAC_VER_27 || - tp->mac_version == RTL_GIGA_MAC_VER_28 || - tp->mac_version == RTL_GIGA_MAC_VER_31 || - tp->mac_version == RTL_GIGA_MAC_VER_49 || - tp->mac_version == RTL_GIGA_MAC_VER_50 || - tp->mac_version == RTL_GIGA_MAC_VER_51) && - r8168_check_dash(tp)) { + if (r8168_check_dash(tp)) rtl8168_driver_start(tp); - } netif_carrier_off(dev); diff --git a/drivers/net/ethernet/renesas/ravb.h b/drivers/net/ethernet/renesas/ravb.h index 96a27b00c90e..b81f4faf7b10 100644 --- a/drivers/net/ethernet/renesas/ravb.h +++ b/drivers/net/ethernet/renesas/ravb.h @@ -1018,6 +1018,7 @@ struct ravb_private { u32 dirty_rx[NUM_RX_QUEUE]; /* Producer ring indices */ u32 cur_tx[NUM_TX_QUEUE]; u32 dirty_tx[NUM_TX_QUEUE]; + u32 rx_buf_sz; /* Based on MTU+slack. */ struct napi_struct napi[NUM_RX_QUEUE]; struct work_struct work; /* MII transceiver section. */ diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c index a95fbd5510d9..54a6265da7a0 100644 --- a/drivers/net/ethernet/renesas/ravb_main.c +++ b/drivers/net/ethernet/renesas/ravb_main.c @@ -238,7 +238,7 @@ static void ravb_ring_free(struct net_device *ndev, int q) le32_to_cpu(desc->dptr))) dma_unmap_single(ndev->dev.parent, le32_to_cpu(desc->dptr), - PKT_BUF_SZ, + priv->rx_buf_sz, DMA_FROM_DEVICE); } ring_size = sizeof(struct ravb_ex_rx_desc) * @@ -300,9 +300,9 @@ static void ravb_ring_format(struct net_device *ndev, int q) for (i = 0; i < priv->num_rx_ring[q]; i++) { /* RX descriptor */ rx_desc = &priv->rx_ring[q][i]; - rx_desc->ds_cc = cpu_to_le16(PKT_BUF_SZ); + rx_desc->ds_cc = cpu_to_le16(priv->rx_buf_sz); dma_addr = dma_map_single(ndev->dev.parent, priv->rx_skb[q][i]->data, - PKT_BUF_SZ, + priv->rx_buf_sz, DMA_FROM_DEVICE); /* We just set the data size to 0 for a failed mapping which * should prevent DMA from happening... @@ -346,6 +346,10 @@ static int ravb_ring_init(struct net_device *ndev, int q) int ring_size; int i; + /* +16 gets room from the status from the card. */ + priv->rx_buf_sz = (ndev->mtu <= 1492 ? PKT_BUF_SZ : ndev->mtu) + + ETH_HLEN + VLAN_HLEN; + /* Allocate RX and TX skb rings */ priv->rx_skb[q] = kcalloc(priv->num_rx_ring[q], sizeof(*priv->rx_skb[q]), GFP_KERNEL); @@ -355,7 +359,7 @@ static int ravb_ring_init(struct net_device *ndev, int q) goto error; for (i = 0; i < priv->num_rx_ring[q]; i++) { - skb = netdev_alloc_skb(ndev, PKT_BUF_SZ + RAVB_ALIGN - 1); + skb = netdev_alloc_skb(ndev, priv->rx_buf_sz + RAVB_ALIGN - 1); if (!skb) goto error; ravb_set_buffer_align(skb); @@ -586,7 +590,7 @@ static bool ravb_rx(struct net_device *ndev, int *quota, int q) skb = priv->rx_skb[q][entry]; priv->rx_skb[q][entry] = NULL; dma_unmap_single(ndev->dev.parent, le32_to_cpu(desc->dptr), - PKT_BUF_SZ, + priv->rx_buf_sz, DMA_FROM_DEVICE); get_ts &= (q == RAVB_NC) ? RAVB_RXTSTAMP_TYPE_V2_L2_EVENT : @@ -619,11 +623,12 @@ static bool ravb_rx(struct net_device *ndev, int *quota, int q) for (; priv->cur_rx[q] - priv->dirty_rx[q] > 0; priv->dirty_rx[q]++) { entry = priv->dirty_rx[q] % priv->num_rx_ring[q]; desc = &priv->rx_ring[q][entry]; - desc->ds_cc = cpu_to_le16(PKT_BUF_SZ); + desc->ds_cc = cpu_to_le16(priv->rx_buf_sz); if (!priv->rx_skb[q][entry]) { skb = netdev_alloc_skb(ndev, - PKT_BUF_SZ + RAVB_ALIGN - 1); + priv->rx_buf_sz + + RAVB_ALIGN - 1); if (!skb) break; /* Better luck next round. */ ravb_set_buffer_align(skb); @@ -1854,6 +1859,17 @@ static int ravb_do_ioctl(struct net_device *ndev, struct ifreq *req, int cmd) return phy_mii_ioctl(phydev, req, cmd); } +static int ravb_change_mtu(struct net_device *ndev, int new_mtu) +{ + if (netif_running(ndev)) + return -EBUSY; + + ndev->mtu = new_mtu; + netdev_update_features(ndev); + + return 0; +} + static void ravb_set_rx_csum(struct net_device *ndev, bool enable) { struct ravb_private *priv = netdev_priv(ndev); @@ -1895,6 +1911,7 @@ static const struct net_device_ops ravb_netdev_ops = { .ndo_set_rx_mode = ravb_set_rx_mode, .ndo_tx_timeout = ravb_tx_timeout, .ndo_do_ioctl = ravb_do_ioctl, + .ndo_change_mtu = ravb_change_mtu, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = eth_mac_addr, .ndo_set_features = ravb_set_features, @@ -2117,6 +2134,9 @@ static int ravb_probe(struct platform_device *pdev) goto out_release; } + ndev->max_mtu = 2048 - (ETH_HLEN + VLAN_HLEN + ETH_FCS_LEN); + ndev->min_mtu = ETH_MIN_MTU; + /* Set function */ ndev->netdev_ops = &ravb_netdev_ops; ndev->ethtool_ops = &ravb_ethtool_ops; diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c index 14c839bb09e7..3557fe3f2bb5 100644 --- a/drivers/net/ethernet/renesas/sh_eth.c +++ b/drivers/net/ethernet/renesas/sh_eth.c @@ -123,8 +123,8 @@ static const u16 sh_eth_offset_gigabit[SH_ETH_MAX_REGISTER_OFFSET] = { [TSU_FWSL0] = 0x0030, [TSU_FWSL1] = 0x0034, [TSU_FWSLC] = 0x0038, - [TSU_QTAG0] = 0x0040, - [TSU_QTAG1] = 0x0044, + [TSU_QTAGM0] = 0x0040, + [TSU_QTAGM1] = 0x0044, [TSU_FWSR] = 0x0050, [TSU_FWINMK] = 0x0054, [TSU_ADQT0] = 0x0048, @@ -763,6 +763,7 @@ static struct sh_eth_cpu_data sh7757_data = { .rpadir = 1, .rpadir_value = 2 << 16, .rtrate = 1, + .dual_port = 1, }; #define SH_GIGA_ETH_BASE 0xfee00000UL @@ -841,6 +842,7 @@ static struct sh_eth_cpu_data sh7757_data_giga = { .no_trimd = 1, .no_ade = 1, .tsu = 1, + .dual_port = 1, }; /* SH7734 */ @@ -911,6 +913,7 @@ static struct sh_eth_cpu_data sh7763_data = { .tsu = 1, .irq_flags = IRQF_SHARED, .magic = 1, + .dual_port = 1, }; static struct sh_eth_cpu_data sh7619_data = { @@ -943,6 +946,7 @@ static struct sh_eth_cpu_data sh771x_data = { EESIPR_RRFIP | EESIPR_RTLFIP | EESIPR_RTSFIP | EESIPR_PREIP | EESIPR_CERFIP, .tsu = 1, + .dual_port = 1, }; static void sh_eth_set_default_cpu_data(struct sh_eth_cpu_data *cd) @@ -972,20 +976,16 @@ static void sh_eth_set_default_cpu_data(struct sh_eth_cpu_data *cd) static int sh_eth_check_reset(struct net_device *ndev) { - int ret = 0; - int cnt = 100; + int cnt; - while (cnt > 0) { + for (cnt = 100; cnt > 0; cnt--) { if (!(sh_eth_read(ndev, EDMR) & EDMR_SRST_GETHER)) - break; + return 0; mdelay(1); - cnt--; - } - if (cnt <= 0) { - netdev_err(ndev, "Device reset failed\n"); - ret = -ETIMEDOUT; } - return ret; + + netdev_err(ndev, "Device reset failed\n"); + return -ETIMEDOUT; } static int sh_eth_reset(struct net_device *ndev) @@ -2112,8 +2112,6 @@ static size_t __sh_eth_get_regs(struct net_device *ndev, u32 *buf) add_tsu_reg(TSU_FWSL0); add_tsu_reg(TSU_FWSL1); add_tsu_reg(TSU_FWSLC); - add_tsu_reg(TSU_QTAG0); - add_tsu_reg(TSU_QTAG1); add_tsu_reg(TSU_QTAGM0); add_tsu_reg(TSU_QTAGM1); add_tsu_reg(TSU_FWSR); @@ -2932,7 +2930,7 @@ static int sh_eth_vlan_rx_kill_vid(struct net_device *ndev, /* SuperH's TSU register init function */ static void sh_eth_tsu_init(struct sh_eth_private *mdp) { - if (sh_eth_is_rz_fast_ether(mdp)) { + if (!mdp->cd->dual_port) { sh_eth_tsu_write(mdp, 0, TSU_TEN); /* Disable all CAM entry */ sh_eth_tsu_write(mdp, TSU_FWSLC_POSTENU | TSU_FWSLC_POSTENL, TSU_FWSLC); /* Enable POST registers */ @@ -2949,13 +2947,8 @@ static void sh_eth_tsu_init(struct sh_eth_private *mdp) sh_eth_tsu_write(mdp, 0, TSU_FWSL0); sh_eth_tsu_write(mdp, 0, TSU_FWSL1); sh_eth_tsu_write(mdp, TSU_FWSLC_POSTENU | TSU_FWSLC_POSTENL, TSU_FWSLC); - if (sh_eth_is_gether(mdp)) { - sh_eth_tsu_write(mdp, 0, TSU_QTAG0); /* Disable QTAG(0->1) */ - sh_eth_tsu_write(mdp, 0, TSU_QTAG1); /* Disable QTAG(1->0) */ - } else { - sh_eth_tsu_write(mdp, 0, TSU_QTAGM0); /* Disable QTAG(0->1) */ - sh_eth_tsu_write(mdp, 0, TSU_QTAGM1); /* Disable QTAG(1->0) */ - } + sh_eth_tsu_write(mdp, 0, TSU_QTAGM0); /* Disable QTAG(0->1) */ + sh_eth_tsu_write(mdp, 0, TSU_QTAGM1); /* Disable QTAG(1->0) */ sh_eth_tsu_write(mdp, 0, TSU_FWSR); /* all interrupt status clear */ sh_eth_tsu_write(mdp, 0, TSU_FWINMK); /* Disable all interrupt */ sh_eth_tsu_write(mdp, 0, TSU_TEN); /* Disable all CAM entry */ diff --git a/drivers/net/ethernet/renesas/sh_eth.h b/drivers/net/ethernet/renesas/sh_eth.h index e5fe70134690..21047d58a93f 100644 --- a/drivers/net/ethernet/renesas/sh_eth.h +++ b/drivers/net/ethernet/renesas/sh_eth.h @@ -118,8 +118,8 @@ enum { TSU_FWSL0, TSU_FWSL1, TSU_FWSLC, - TSU_QTAG0, - TSU_QTAG1, + TSU_QTAG0, /* Same as TSU_QTAGM0 */ + TSU_QTAG1, /* Same as TSU_QTAGM1 */ TSU_QTAGM0, TSU_QTAGM1, TSU_FWSR, @@ -509,6 +509,7 @@ struct sh_eth_cpu_data { unsigned rmiimode:1; /* EtherC has RMIIMODE register */ unsigned rtrate:1; /* EtherC has RTRATE register */ unsigned magic:1; /* EtherC has ECMR.MPDE and ECSR.MPD */ + unsigned dual_port:1; /* Dual EtherC/E-DMAC */ }; struct sh_eth_private { diff --git a/drivers/net/ethernet/sfc/falcon/enum.h b/drivers/net/ethernet/sfc/falcon/enum.h index 30a1136fc909..4824fcf5c3d4 100644 --- a/drivers/net/ethernet/sfc/falcon/enum.h +++ b/drivers/net/ethernet/sfc/falcon/enum.h @@ -81,7 +81,6 @@ enum ef4_loopback_mode { (1 << LOOPBACK_XAUI) | \ (1 << LOOPBACK_GMII) | \ (1 << LOOPBACK_SGMII) | \ - (1 << LOOPBACK_SGMII) | \ (1 << LOOPBACK_XGBR) | \ (1 << LOOPBACK_XFI) | \ (1 << LOOPBACK_XAUI_FAR) | \ diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c index 5270d26f0bc6..2d5d4aea3bcb 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c @@ -48,26 +48,18 @@ #define MUX_CLK_NUM_PARENTS 2 struct meson8b_dwmac { - struct platform_device *pdev; - + struct device *dev; void __iomem *regs; - phy_interface_t phy_mode; + struct clk *rgmii_tx_clk; + u32 tx_delay_ns; +}; +struct meson8b_dwmac_clk_configs { struct clk_mux m250_mux; - struct clk *m250_mux_clk; - struct clk *m250_mux_parent[MUX_CLK_NUM_PARENTS]; - struct clk_divider m250_div; - struct clk *m250_div_clk; - struct clk_fixed_factor fixed_div2; - struct clk *fixed_div2_clk; - struct clk_gate rgmii_tx_en; - struct clk *rgmii_tx_en_clk; - - u32 tx_delay_ns; }; static void meson8b_dwmac_mask_bits(struct meson8b_dwmac *dwmac, u32 reg, @@ -82,106 +74,99 @@ static void meson8b_dwmac_mask_bits(struct meson8b_dwmac *dwmac, u32 reg, writel(data, dwmac->regs + reg); } -static int meson8b_init_rgmii_tx_clk(struct meson8b_dwmac *dwmac) +static struct clk *meson8b_dwmac_register_clk(struct meson8b_dwmac *dwmac, + const char *name_suffix, + const char **parent_names, + int num_parents, + const struct clk_ops *ops, + struct clk_hw *hw) { struct clk_init_data init; - int i, ret; - struct device *dev = &dwmac->pdev->dev; char clk_name[32]; - const char *clk_div_parents[1]; - const char *mux_parent_names[MUX_CLK_NUM_PARENTS]; + + snprintf(clk_name, sizeof(clk_name), "%s#%s", dev_name(dwmac->dev), + name_suffix); + + init.name = clk_name; + init.ops = ops; + init.flags = CLK_SET_RATE_PARENT; + init.parent_names = parent_names; + init.num_parents = num_parents; + + hw->init = &init; + + return devm_clk_register(dwmac->dev, hw); +} + +static int meson8b_init_rgmii_tx_clk(struct meson8b_dwmac *dwmac) +{ + int i, ret; + struct clk *clk; + struct device *dev = dwmac->dev; + const char *parent_name, *mux_parent_names[MUX_CLK_NUM_PARENTS]; + struct meson8b_dwmac_clk_configs *clk_configs; + + clk_configs = devm_kzalloc(dev, sizeof(*clk_configs), GFP_KERNEL); + if (!clk_configs) + return -ENOMEM; /* get the mux parents from DT */ for (i = 0; i < MUX_CLK_NUM_PARENTS; i++) { char name[16]; snprintf(name, sizeof(name), "clkin%d", i); - dwmac->m250_mux_parent[i] = devm_clk_get(dev, name); - if (IS_ERR(dwmac->m250_mux_parent[i])) { - ret = PTR_ERR(dwmac->m250_mux_parent[i]); + clk = devm_clk_get(dev, name); + if (IS_ERR(clk)) { + ret = PTR_ERR(clk); if (ret != -EPROBE_DEFER) dev_err(dev, "Missing clock %s\n", name); return ret; } - mux_parent_names[i] = - __clk_get_name(dwmac->m250_mux_parent[i]); + mux_parent_names[i] = __clk_get_name(clk); } - /* create the m250_mux */ - snprintf(clk_name, sizeof(clk_name), "%s#m250_sel", dev_name(dev)); - init.name = clk_name; - init.ops = &clk_mux_ops; - init.flags = CLK_SET_RATE_PARENT; - init.parent_names = mux_parent_names; - init.num_parents = MUX_CLK_NUM_PARENTS; - - dwmac->m250_mux.reg = dwmac->regs + PRG_ETH0; - dwmac->m250_mux.shift = PRG_ETH0_CLK_M250_SEL_SHIFT; - dwmac->m250_mux.mask = PRG_ETH0_CLK_M250_SEL_MASK; - dwmac->m250_mux.flags = 0; - dwmac->m250_mux.table = NULL; - dwmac->m250_mux.hw.init = &init; - - dwmac->m250_mux_clk = devm_clk_register(dev, &dwmac->m250_mux.hw); - if (WARN_ON(IS_ERR(dwmac->m250_mux_clk))) - return PTR_ERR(dwmac->m250_mux_clk); - - /* create the m250_div */ - snprintf(clk_name, sizeof(clk_name), "%s#m250_div", dev_name(dev)); - init.name = devm_kstrdup(dev, clk_name, GFP_KERNEL); - init.ops = &clk_divider_ops; - init.flags = CLK_SET_RATE_PARENT; - clk_div_parents[0] = __clk_get_name(dwmac->m250_mux_clk); - init.parent_names = clk_div_parents; - init.num_parents = ARRAY_SIZE(clk_div_parents); - - dwmac->m250_div.reg = dwmac->regs + PRG_ETH0; - dwmac->m250_div.shift = PRG_ETH0_CLK_M250_DIV_SHIFT; - dwmac->m250_div.width = PRG_ETH0_CLK_M250_DIV_WIDTH; - dwmac->m250_div.hw.init = &init; - dwmac->m250_div.flags = CLK_DIVIDER_ONE_BASED | + clk_configs->m250_mux.reg = dwmac->regs + PRG_ETH0; + clk_configs->m250_mux.shift = PRG_ETH0_CLK_M250_SEL_SHIFT; + clk_configs->m250_mux.mask = PRG_ETH0_CLK_M250_SEL_MASK; + clk = meson8b_dwmac_register_clk(dwmac, "m250_sel", mux_parent_names, + MUX_CLK_NUM_PARENTS, &clk_mux_ops, + &clk_configs->m250_mux.hw); + if (WARN_ON(IS_ERR(clk))) + return PTR_ERR(clk); + + parent_name = __clk_get_name(clk); + clk_configs->m250_div.reg = dwmac->regs + PRG_ETH0; + clk_configs->m250_div.shift = PRG_ETH0_CLK_M250_DIV_SHIFT; + clk_configs->m250_div.width = PRG_ETH0_CLK_M250_DIV_WIDTH; + clk_configs->m250_div.flags = CLK_DIVIDER_ONE_BASED | CLK_DIVIDER_ALLOW_ZERO | CLK_DIVIDER_ROUND_CLOSEST; - - dwmac->m250_div_clk = devm_clk_register(dev, &dwmac->m250_div.hw); - if (WARN_ON(IS_ERR(dwmac->m250_div_clk))) - return PTR_ERR(dwmac->m250_div_clk); - - /* create the fixed_div2 */ - snprintf(clk_name, sizeof(clk_name), "%s#fixed_div2", dev_name(dev)); - init.name = devm_kstrdup(dev, clk_name, GFP_KERNEL); - init.ops = &clk_fixed_factor_ops; - init.flags = CLK_SET_RATE_PARENT; - clk_div_parents[0] = __clk_get_name(dwmac->m250_div_clk); - init.parent_names = clk_div_parents; - init.num_parents = ARRAY_SIZE(clk_div_parents); - - dwmac->fixed_div2.mult = 1; - dwmac->fixed_div2.div = 2; - dwmac->fixed_div2.hw.init = &init; - - dwmac->fixed_div2_clk = devm_clk_register(dev, &dwmac->fixed_div2.hw); - if (WARN_ON(IS_ERR(dwmac->fixed_div2_clk))) - return PTR_ERR(dwmac->fixed_div2_clk); - - /* create the rgmii_tx_en */ - init.name = devm_kasprintf(dev, GFP_KERNEL, "%s#rgmii_tx_en", - dev_name(dev)); - init.ops = &clk_gate_ops; - init.flags = CLK_SET_RATE_PARENT; - clk_div_parents[0] = __clk_get_name(dwmac->fixed_div2_clk); - init.parent_names = clk_div_parents; - init.num_parents = ARRAY_SIZE(clk_div_parents); - - dwmac->rgmii_tx_en.reg = dwmac->regs + PRG_ETH0; - dwmac->rgmii_tx_en.bit_idx = PRG_ETH0_RGMII_TX_CLK_EN; - dwmac->rgmii_tx_en.hw.init = &init; - - dwmac->rgmii_tx_en_clk = devm_clk_register(dev, - &dwmac->rgmii_tx_en.hw); - if (WARN_ON(IS_ERR(dwmac->rgmii_tx_en_clk))) - return PTR_ERR(dwmac->rgmii_tx_en_clk); + clk = meson8b_dwmac_register_clk(dwmac, "m250_div", &parent_name, 1, + &clk_divider_ops, + &clk_configs->m250_div.hw); + if (WARN_ON(IS_ERR(clk))) + return PTR_ERR(clk); + + parent_name = __clk_get_name(clk); + clk_configs->fixed_div2.mult = 1; + clk_configs->fixed_div2.div = 2; + clk = meson8b_dwmac_register_clk(dwmac, "fixed_div2", &parent_name, 1, + &clk_fixed_factor_ops, + &clk_configs->fixed_div2.hw); + if (WARN_ON(IS_ERR(clk))) + return PTR_ERR(clk); + + parent_name = __clk_get_name(clk); + clk_configs->rgmii_tx_en.reg = dwmac->regs + PRG_ETH0; + clk_configs->rgmii_tx_en.bit_idx = PRG_ETH0_RGMII_TX_CLK_EN; + clk = meson8b_dwmac_register_clk(dwmac, "rgmii_tx_en", &parent_name, 1, + &clk_gate_ops, + &clk_configs->rgmii_tx_en.hw); + if (WARN_ON(IS_ERR(clk))) + return PTR_ERR(clk); + + dwmac->rgmii_tx_clk = clk; return 0; } @@ -219,19 +204,23 @@ static int meson8b_init_prg_eth(struct meson8b_dwmac *dwmac) * a register) based on the line-speed (125MHz for Gbit speeds, * 25MHz for 100Mbit/s and 2.5MHz for 10Mbit/s). */ - ret = clk_set_rate(dwmac->rgmii_tx_en_clk, 125 * 1000 * 1000); + ret = clk_set_rate(dwmac->rgmii_tx_clk, 125 * 1000 * 1000); if (ret) { - dev_err(&dwmac->pdev->dev, + dev_err(dwmac->dev, "failed to set RGMII TX clock\n"); return ret; } - ret = clk_prepare_enable(dwmac->rgmii_tx_en_clk); + ret = clk_prepare_enable(dwmac->rgmii_tx_clk); if (ret) { - dev_err(&dwmac->pdev->dev, + dev_err(dwmac->dev, "failed to enable the RGMII TX clock\n"); return ret; } + + devm_add_action_or_reset(dwmac->dev, + (void(*)(void *))clk_disable_unprepare, + dwmac->rgmii_tx_clk); break; case PHY_INTERFACE_MODE_RMII: @@ -251,7 +240,7 @@ static int meson8b_init_prg_eth(struct meson8b_dwmac *dwmac) break; default: - dev_err(&dwmac->pdev->dev, "unsupported phy-mode %s\n", + dev_err(dwmac->dev, "unsupported phy-mode %s\n", phy_modes(dwmac->phy_mode)); return -EINVAL; } @@ -292,7 +281,7 @@ static int meson8b_dwmac_probe(struct platform_device *pdev) goto err_remove_config_dt; } - dwmac->pdev = pdev; + dwmac->dev = &pdev->dev; dwmac->phy_mode = of_get_phy_mode(pdev->dev.of_node); if (dwmac->phy_mode < 0) { dev_err(&pdev->dev, "missing phy-mode property\n"); @@ -317,29 +306,16 @@ static int meson8b_dwmac_probe(struct platform_device *pdev) ret = stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res); if (ret) - goto err_clk_disable; + goto err_remove_config_dt; return 0; -err_clk_disable: - if (phy_interface_mode_is_rgmii(dwmac->phy_mode)) - clk_disable_unprepare(dwmac->rgmii_tx_en_clk); err_remove_config_dt: stmmac_remove_config_dt(pdev, plat_dat); return ret; } -static int meson8b_dwmac_remove(struct platform_device *pdev) -{ - struct meson8b_dwmac *dwmac = get_stmmac_bsp_priv(&pdev->dev); - - if (phy_interface_mode_is_rgmii(dwmac->phy_mode)) - clk_disable_unprepare(dwmac->rgmii_tx_en_clk); - - return stmmac_pltfr_remove(pdev); -} - static const struct of_device_id meson8b_dwmac_match[] = { { .compatible = "amlogic,meson8b-dwmac" }, { .compatible = "amlogic,meson-gxbb-dwmac" }, @@ -349,7 +325,7 @@ MODULE_DEVICE_TABLE(of, meson8b_dwmac_match); static struct platform_driver meson8b_dwmac_driver = { .probe = meson8b_dwmac_probe, - .remove = meson8b_dwmac_remove, + .remove = stmmac_pltfr_remove, .driver = { .name = "meson8b-dwmac", .pm = &stmmac_pltfr_pm_ops, diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c index 63795ecafc8d..46b9ae20ff6c 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c @@ -120,7 +120,7 @@ static void dwmac4_tx_queue_priority(struct mac_device_info *hw, writel(value, ioaddr + base_register); } -static void dwmac4_tx_queue_routing(struct mac_device_info *hw, +static void dwmac4_rx_queue_routing(struct mac_device_info *hw, u8 packet, u32 queue) { void __iomem *ioaddr = hw->pcsr; @@ -713,7 +713,7 @@ static const struct stmmac_ops dwmac4_ops = { .rx_queue_enable = dwmac4_rx_queue_enable, .rx_queue_prio = dwmac4_rx_queue_priority, .tx_queue_prio = dwmac4_tx_queue_priority, - .rx_queue_routing = dwmac4_tx_queue_routing, + .rx_queue_routing = dwmac4_rx_queue_routing, .prog_mtl_rx_algorithms = dwmac4_prog_mtl_rx_algorithms, .prog_mtl_tx_algorithms = dwmac4_prog_mtl_tx_algorithms, .set_mtl_tx_queue_weight = dwmac4_set_mtl_tx_queue_weight, @@ -744,7 +744,7 @@ static const struct stmmac_ops dwmac410_ops = { .rx_queue_enable = dwmac4_rx_queue_enable, .rx_queue_prio = dwmac4_rx_queue_priority, .tx_queue_prio = dwmac4_tx_queue_priority, - .rx_queue_routing = dwmac4_tx_queue_routing, + .rx_queue_routing = dwmac4_rx_queue_routing, .prog_mtl_rx_algorithms = dwmac4_prog_mtl_rx_algorithms, .prog_mtl_tx_algorithms = dwmac4_prog_mtl_tx_algorithms, .set_mtl_tx_queue_weight = dwmac4_set_mtl_tx_queue_weight, diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c index c728ffa095de..2a6521d33e43 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c @@ -389,6 +389,8 @@ static void dwmac4_rd_prepare_tso_tx_desc(struct dma_desc *p, int is_fs, static void dwmac4_release_tx_desc(struct dma_desc *p, int mode) { + p->des0 = 0; + p->des1 = 0; p->des2 = 0; p->des3 = 0; } diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h index a916e13624eb..75161e1b7e55 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h @@ -58,6 +58,7 @@ struct stmmac_tx_queue { unsigned int dirty_tx; dma_addr_t dma_tx_phy; u32 tx_tail_addr; + u32 mss; }; struct stmmac_rx_queue { @@ -138,7 +139,6 @@ struct stmmac_priv { spinlock_t ptp_lock; void __iomem *mmcaddr; void __iomem *ptpaddr; - u32 mss; #ifdef CONFIG_DEBUG_FS struct dentry *dbgfs_dir; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 7ad841434ec8..a9856a8bf8ad 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -1355,6 +1355,7 @@ static int init_dma_tx_desc_rings(struct net_device *dev) tx_q->dirty_tx = 0; tx_q->cur_tx = 0; + tx_q->mss = 0; netdev_tx_reset_queue(netdev_get_tx_queue(priv->dev, queue)); } @@ -1843,6 +1844,11 @@ static void stmmac_tx_clean(struct stmmac_priv *priv, u32 queue) if (unlikely(status & tx_dma_own)) break; + /* Make sure descriptor fields are read after reading + * the own bit. + */ + dma_rmb(); + /* Just consider the last segment and ...*/ if (likely(!(status & tx_not_ls))) { /* ... verify the status error condition */ @@ -1946,6 +1952,7 @@ static void stmmac_tx_err(struct stmmac_priv *priv, u32 chan) (i == DMA_TX_SIZE - 1)); tx_q->dirty_tx = 0; tx_q->cur_tx = 0; + tx_q->mss = 0; netdev_tx_reset_queue(netdev_get_tx_queue(priv->dev, chan)); stmmac_start_tx_dma(priv, chan); @@ -2430,7 +2437,7 @@ static void stmmac_mac_config_rx_queues_routing(struct stmmac_priv *priv) continue; packet = priv->plat->rx_queues_cfg[queue].pkt_route; - priv->hw->mac->rx_queue_prio(priv->hw, packet, queue); + priv->hw->mac->rx_queue_routing(priv->hw, packet, queue); } } @@ -2632,7 +2639,6 @@ static int stmmac_open(struct net_device *dev) priv->dma_buf_sz = STMMAC_ALIGN(buf_sz); priv->rx_copybreak = STMMAC_RX_COPYBREAK; - priv->mss = 0; ret = alloc_dma_desc_resources(priv); if (ret < 0) { @@ -2793,6 +2799,7 @@ static void stmmac_tso_allocator(struct stmmac_priv *priv, unsigned int des, while (tmp_len > 0) { tx_q->cur_tx = STMMAC_GET_ENTRY(tx_q->cur_tx, DMA_TX_SIZE); + WARN_ON(tx_q->tx_skbuff[tx_q->cur_tx]); desc = tx_q->dma_tx + tx_q->cur_tx; desc->des0 = cpu_to_le32(des + (total_len - tmp_len)); @@ -2872,11 +2879,12 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev) mss = skb_shinfo(skb)->gso_size; /* set new MSS value if needed */ - if (mss != priv->mss) { + if (mss != tx_q->mss) { mss_desc = tx_q->dma_tx + tx_q->cur_tx; priv->hw->desc->set_mss(mss_desc, mss); - priv->mss = mss; + tx_q->mss = mss; tx_q->cur_tx = STMMAC_GET_ENTRY(tx_q->cur_tx, DMA_TX_SIZE); + WARN_ON(tx_q->tx_skbuff[tx_q->cur_tx]); } if (netif_msg_tx_queued(priv)) { @@ -2887,6 +2895,7 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev) } first_entry = tx_q->cur_tx; + WARN_ON(tx_q->tx_skbuff[first_entry]); desc = tx_q->dma_tx + first_entry; first = desc; @@ -2926,7 +2935,6 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev) tx_q->tx_skbuff_dma[tx_q->cur_tx].buf = des; tx_q->tx_skbuff_dma[tx_q->cur_tx].len = skb_frag_size(frag); - tx_q->tx_skbuff[tx_q->cur_tx] = NULL; tx_q->tx_skbuff_dma[tx_q->cur_tx].map_as_page = true; } @@ -2980,14 +2988,21 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev) tcp_hdrlen(skb) / 4, (skb->len - proto_hdr_len)); /* If context desc is used to change MSS */ - if (mss_desc) + if (mss_desc) { + /* Make sure that first descriptor has been completely + * written, including its own bit. This is because MSS is + * actually before first descriptor, so we need to make + * sure that MSS's own bit is the last thing written. + */ + dma_wmb(); priv->hw->desc->set_tx_owner(mss_desc); + } /* The own bit must be the latest setting done when prepare the * descriptor and then barrier is needed to make sure that * all is coherent before granting the DMA engine. */ - dma_wmb(); + wmb(); if (netif_msg_pktdata(priv)) { pr_info("%s: curr=%d dirty=%d f=%d, e=%d, f_p=%p, nfrags %d\n", @@ -3062,6 +3077,7 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev) entry = tx_q->cur_tx; first_entry = entry; + WARN_ON(tx_q->tx_skbuff[first_entry]); csum_insertion = (skb->ip_summed == CHECKSUM_PARTIAL); @@ -3090,6 +3106,7 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev) bool last_segment = (i == (nfrags - 1)); entry = STMMAC_GET_ENTRY(entry, DMA_TX_SIZE); + WARN_ON(tx_q->tx_skbuff[entry]); if (likely(priv->extend_desc)) desc = (struct dma_desc *)(tx_q->dma_etx + entry); @@ -3101,8 +3118,6 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev) if (dma_mapping_error(priv->device, des)) goto dma_map_err; /* should reuse desc w/o issues */ - tx_q->tx_skbuff[entry] = NULL; - tx_q->tx_skbuff_dma[entry].buf = des; if (unlikely(priv->synopsys_id >= DWMAC_CORE_4_00)) desc->des0 = cpu_to_le32(des); @@ -3211,7 +3226,7 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev) * descriptor and then barrier is needed to make sure that * all is coherent before granting the DMA engine. */ - dma_wmb(); + wmb(); } netdev_tx_sent_queue(netdev_get_tx_queue(dev, queue), skb->len); @@ -4436,6 +4451,7 @@ static void stmmac_reset_queues_param(struct stmmac_priv *priv) tx_q->cur_tx = 0; tx_q->dirty_tx = 0; + tx_q->mss = 0; } } @@ -4481,11 +4497,6 @@ int stmmac_resume(struct device *dev) stmmac_reset_queues_param(priv); - /* reset private mss value to force mss context settings at - * next tso xmit (only used for gmac4). - */ - priv->mss = 0; - stmmac_clear_descriptors(priv); stmmac_hw_setup(ndev, false); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c index 05f122b8424a..ebd3e5ffa73c 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c @@ -135,13 +135,14 @@ static struct stmmac_axi *stmmac_axi_setup(struct platform_device *pdev) * stmmac_mtl_setup - parse DT parameters for multiple queues configuration * @pdev: platform device */ -static void stmmac_mtl_setup(struct platform_device *pdev, - struct plat_stmmacenet_data *plat) +static int stmmac_mtl_setup(struct platform_device *pdev, + struct plat_stmmacenet_data *plat) { struct device_node *q_node; struct device_node *rx_node; struct device_node *tx_node; u8 queue = 0; + int ret = 0; /* For backwards-compatibility with device trees that don't have any * snps,mtl-rx-config or snps,mtl-tx-config properties, we fall back @@ -159,12 +160,12 @@ static void stmmac_mtl_setup(struct platform_device *pdev, rx_node = of_parse_phandle(pdev->dev.of_node, "snps,mtl-rx-config", 0); if (!rx_node) - return; + return ret; tx_node = of_parse_phandle(pdev->dev.of_node, "snps,mtl-tx-config", 0); if (!tx_node) { of_node_put(rx_node); - return; + return ret; } /* Processing RX queues common config */ @@ -220,6 +221,11 @@ static void stmmac_mtl_setup(struct platform_device *pdev, queue++; } + if (queue != plat->rx_queues_to_use) { + ret = -EINVAL; + dev_err(&pdev->dev, "Not all RX queues were configured\n"); + goto out; + } /* Processing TX queues common config */ if (of_property_read_u32(tx_node, "snps,tx-queues-to-use", @@ -281,10 +287,18 @@ static void stmmac_mtl_setup(struct platform_device *pdev, queue++; } + if (queue != plat->tx_queues_to_use) { + ret = -EINVAL; + dev_err(&pdev->dev, "Not all TX queues were configured\n"); + goto out; + } +out: of_node_put(rx_node); of_node_put(tx_node); of_node_put(q_node); + + return ret; } /** @@ -376,6 +390,7 @@ stmmac_probe_config_dt(struct platform_device *pdev, const char **mac) struct device_node *np = pdev->dev.of_node; struct plat_stmmacenet_data *plat; struct stmmac_dma_cfg *dma_cfg; + int rc; plat = devm_kzalloc(&pdev->dev, sizeof(*plat), GFP_KERNEL); if (!plat) @@ -402,8 +417,9 @@ stmmac_probe_config_dt(struct platform_device *pdev, const char **mac) dev_warn(&pdev->dev, "snps,phy-addr property is deprecated\n"); /* To Configure PHY by using all device-tree supported properties */ - if (stmmac_dt_phy(plat, np, &pdev->dev)) - return ERR_PTR(-ENODEV); + rc = stmmac_dt_phy(plat, np, &pdev->dev); + if (rc) + return ERR_PTR(rc); of_property_read_u32(np, "tx-fifo-depth", &plat->tx_fifo_size); @@ -499,7 +515,11 @@ stmmac_probe_config_dt(struct platform_device *pdev, const char **mac) plat->axi = stmmac_axi_setup(pdev); - stmmac_mtl_setup(pdev, plat); + rc = stmmac_mtl_setup(pdev, plat); + if (rc) { + stmmac_remove_config_dt(pdev, plat); + return ERR_PTR(rc); + } /* clock setup */ plat->stmmac_clk = devm_clk_get(&pdev->dev, diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c index b919e89a9b93..516dd59249d7 100644 --- a/drivers/net/geneve.c +++ b/drivers/net/geneve.c @@ -1694,6 +1694,7 @@ static struct pernet_operations geneve_net_ops = { .exit_batch = geneve_exit_batch_net, .id = &geneve_net_id, .size = sizeof(struct geneve_net), + .async = true, }; static int __init geneve_init_module(void) diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c index f38e32a7ec9c..127edd23018f 100644 --- a/drivers/net/gtp.c +++ b/drivers/net/gtp.c @@ -1325,6 +1325,7 @@ static struct pernet_operations gtp_net_ops = { .exit = gtp_net_exit, .id = >p_net_id, .size = sizeof(struct gtp_net), + .async = true, }; static int __init gtp_init(void) diff --git a/drivers/net/ieee802154/Kconfig b/drivers/net/ieee802154/Kconfig index 303ba4133920..8782f5655e3f 100644 --- a/drivers/net/ieee802154/Kconfig +++ b/drivers/net/ieee802154/Kconfig @@ -104,3 +104,14 @@ config IEEE802154_CA8210_DEBUGFS exposes a debugfs node for each CA8210 instance which allows direct use of the Cascoda API, exposing the 802.15.4 MAC management entities. + +config IEEE802154_MCR20A + tristate "MCR20A transceiver driver" + depends on IEEE802154_DRIVERS && MAC802154 + depends on SPI + ---help--- + Say Y here to enable the MCR20A SPI 802.15.4 wireless + controller. + + This driver can also be built as a module. To do so, say M here. + the module will be called 'mcr20a'. diff --git a/drivers/net/ieee802154/Makefile b/drivers/net/ieee802154/Makefile index bea1de5e726c..104744d5a668 100644 --- a/drivers/net/ieee802154/Makefile +++ b/drivers/net/ieee802154/Makefile @@ -6,3 +6,4 @@ obj-$(CONFIG_IEEE802154_CC2520) += cc2520.o obj-$(CONFIG_IEEE802154_ATUSB) += atusb.o obj-$(CONFIG_IEEE802154_ADF7242) += adf7242.o obj-$(CONFIG_IEEE802154_CA8210) += ca8210.o +obj-$(CONFIG_IEEE802154_MCR20A) += mcr20a.o diff --git a/drivers/net/ieee802154/mcr20a.c b/drivers/net/ieee802154/mcr20a.c new file mode 100644 index 000000000000..d9eb22a52551 --- /dev/null +++ b/drivers/net/ieee802154/mcr20a.c @@ -0,0 +1,1413 @@ +/* + * Driver for NXP MCR20A 802.15.4 Wireless-PAN Networking controller + * + * Copyright (C) 2018 Xue Liu <liuxuenetmail@gmail.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 + * 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. + * + */ +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/gpio.h> +#include <linux/spi/spi.h> +#include <linux/workqueue.h> +#include <linux/interrupt.h> +#include <linux/skbuff.h> +#include <linux/of_gpio.h> +#include <linux/regmap.h> +#include <linux/ieee802154.h> +#include <linux/debugfs.h> + +#include <net/mac802154.h> +#include <net/cfg802154.h> + +#include <linux/device.h> + +#include "mcr20a.h" + +#define SPI_COMMAND_BUFFER 3 + +#define REGISTER_READ BIT(7) +#define REGISTER_WRITE (0 << 7) +#define REGISTER_ACCESS (0 << 6) +#define PACKET_BUFF_BURST_ACCESS BIT(6) +#define PACKET_BUFF_BYTE_ACCESS BIT(5) + +#define MCR20A_WRITE_REG(x) (x) +#define MCR20A_READ_REG(x) (REGISTER_READ | (x)) +#define MCR20A_BURST_READ_PACKET_BUF (0xC0) +#define MCR20A_BURST_WRITE_PACKET_BUF (0x40) + +#define MCR20A_CMD_REG 0x80 +#define MCR20A_CMD_REG_MASK 0x3f +#define MCR20A_CMD_WRITE 0x40 +#define MCR20A_CMD_FB 0x20 + +/* Number of Interrupt Request Status Register */ +#define MCR20A_IRQSTS_NUM 2 /* only IRQ_STS1 and IRQ_STS2 */ + +/* MCR20A CCA Type */ +enum { + MCR20A_CCA_ED, // energy detect - CCA bit not active, + // not to be used for T and CCCA sequences + MCR20A_CCA_MODE1, // energy detect - CCA bit ACTIVE + MCR20A_CCA_MODE2, // 802.15.4 compliant signal detect - CCA bit ACTIVE + MCR20A_CCA_MODE3 +}; + +enum { + MCR20A_XCVSEQ_IDLE = 0x00, + MCR20A_XCVSEQ_RX = 0x01, + MCR20A_XCVSEQ_TX = 0x02, + MCR20A_XCVSEQ_CCA = 0x03, + MCR20A_XCVSEQ_TR = 0x04, + MCR20A_XCVSEQ_CCCA = 0x05, +}; + +/* IEEE-802.15.4 defined constants (2.4 GHz logical channels) */ +#define MCR20A_MIN_CHANNEL (11) +#define MCR20A_MAX_CHANNEL (26) +#define MCR20A_CHANNEL_SPACING (5) + +/* MCR20A CCA Threshold constans */ +#define MCR20A_MIN_CCA_THRESHOLD (0x6EU) +#define MCR20A_MAX_CCA_THRESHOLD (0x00U) + +/* version 0C */ +#define MCR20A_OVERWRITE_VERSION (0x0C) + +/* MCR20A PLL configurations */ +static const u8 PLL_INT[16] = { + /* 2405 */ 0x0B, /* 2410 */ 0x0B, /* 2415 */ 0x0B, + /* 2420 */ 0x0B, /* 2425 */ 0x0B, /* 2430 */ 0x0B, + /* 2435 */ 0x0C, /* 2440 */ 0x0C, /* 2445 */ 0x0C, + /* 2450 */ 0x0C, /* 2455 */ 0x0C, /* 2460 */ 0x0C, + /* 2465 */ 0x0D, /* 2470 */ 0x0D, /* 2475 */ 0x0D, + /* 2480 */ 0x0D +}; + +static const u8 PLL_FRAC[16] = { + /* 2405 */ 0x28, /* 2410 */ 0x50, /* 2415 */ 0x78, + /* 2420 */ 0xA0, /* 2425 */ 0xC8, /* 2430 */ 0xF0, + /* 2435 */ 0x18, /* 2440 */ 0x40, /* 2445 */ 0x68, + /* 2450 */ 0x90, /* 2455 */ 0xB8, /* 2460 */ 0xE0, + /* 2465 */ 0x08, /* 2470 */ 0x30, /* 2475 */ 0x58, + /* 2480 */ 0x80 +}; + +static const struct reg_sequence mar20a_iar_overwrites[] = { + { IAR_MISC_PAD_CTRL, 0x02 }, + { IAR_VCO_CTRL1, 0xB3 }, + { IAR_VCO_CTRL2, 0x07 }, + { IAR_PA_TUNING, 0x71 }, + { IAR_CHF_IBUF, 0x2F }, + { IAR_CHF_QBUF, 0x2F }, + { IAR_CHF_IRIN, 0x24 }, + { IAR_CHF_QRIN, 0x24 }, + { IAR_CHF_IL, 0x24 }, + { IAR_CHF_QL, 0x24 }, + { IAR_CHF_CC1, 0x32 }, + { IAR_CHF_CCL, 0x1D }, + { IAR_CHF_CC2, 0x2D }, + { IAR_CHF_IROUT, 0x24 }, + { IAR_CHF_QROUT, 0x24 }, + { IAR_PA_CAL, 0x28 }, + { IAR_AGC_THR1, 0x55 }, + { IAR_AGC_THR2, 0x2D }, + { IAR_ATT_RSSI1, 0x5F }, + { IAR_ATT_RSSI2, 0x8F }, + { IAR_RSSI_OFFSET, 0x61 }, + { IAR_CHF_PMA_GAIN, 0x03 }, + { IAR_CCA1_THRESH, 0x50 }, + { IAR_CORR_NVAL, 0x13 }, + { IAR_ACKDELAY, 0x3D }, +}; + +#define MCR20A_VALID_CHANNELS (0x07FFF800) + +struct mcr20a_platform_data { + int rst_gpio; +}; + +#define MCR20A_MAX_BUF (127) + +#define printdev(X) (&X->spi->dev) + +/* regmap information for Direct Access Register (DAR) access */ +#define MCR20A_DAR_WRITE 0x01 +#define MCR20A_DAR_READ 0x00 +#define MCR20A_DAR_NUMREGS 0x3F + +/* regmap information for Indirect Access Register (IAR) access */ +#define MCR20A_IAR_ACCESS 0x80 +#define MCR20A_IAR_NUMREGS 0xBEFF + +/* Read/Write SPI Commands for DAR and IAR registers. */ +#define MCR20A_READSHORT(reg) ((reg) << 1) +#define MCR20A_WRITESHORT(reg) ((reg) << 1 | 1) +#define MCR20A_READLONG(reg) (1 << 15 | (reg) << 5) +#define MCR20A_WRITELONG(reg) (1 << 15 | (reg) << 5 | 1 << 4) + +/* Type definitions for link configuration of instantiable layers */ +#define MCR20A_PHY_INDIRECT_QUEUE_SIZE (12) + +static bool +mcr20a_dar_writeable(struct device *dev, unsigned int reg) +{ + switch (reg) { + case DAR_IRQ_STS1: + case DAR_IRQ_STS2: + case DAR_IRQ_STS3: + case DAR_PHY_CTRL1: + case DAR_PHY_CTRL2: + case DAR_PHY_CTRL3: + case DAR_PHY_CTRL4: + case DAR_SRC_CTRL: + case DAR_SRC_ADDRS_SUM_LSB: + case DAR_SRC_ADDRS_SUM_MSB: + case DAR_T3CMP_LSB: + case DAR_T3CMP_MSB: + case DAR_T3CMP_USB: + case DAR_T2PRIMECMP_LSB: + case DAR_T2PRIMECMP_MSB: + case DAR_T1CMP_LSB: + case DAR_T1CMP_MSB: + case DAR_T1CMP_USB: + case DAR_T2CMP_LSB: + case DAR_T2CMP_MSB: + case DAR_T2CMP_USB: + case DAR_T4CMP_LSB: + case DAR_T4CMP_MSB: + case DAR_T4CMP_USB: + case DAR_PLL_INT0: + case DAR_PLL_FRAC0_LSB: + case DAR_PLL_FRAC0_MSB: + case DAR_PA_PWR: + /* no DAR_ACM */ + case DAR_OVERWRITE_VER: + case DAR_CLK_OUT_CTRL: + case DAR_PWR_MODES: + return true; + default: + return false; + } +} + +static bool +mcr20a_dar_readable(struct device *dev, unsigned int reg) +{ + bool rc; + + /* all writeable are also readable */ + rc = mcr20a_dar_writeable(dev, reg); + if (rc) + return rc; + + /* readonly regs */ + switch (reg) { + case DAR_RX_FRM_LEN: + case DAR_CCA1_ED_FNL: + case DAR_EVENT_TMR_LSB: + case DAR_EVENT_TMR_MSB: + case DAR_EVENT_TMR_USB: + case DAR_TIMESTAMP_LSB: + case DAR_TIMESTAMP_MSB: + case DAR_TIMESTAMP_USB: + case DAR_SEQ_STATE: + case DAR_LQI_VALUE: + case DAR_RSSI_CCA_CONT: + return true; + default: + return false; + } +} + +static bool +mcr20a_dar_volatile(struct device *dev, unsigned int reg) +{ + /* can be changed during runtime */ + switch (reg) { + case DAR_IRQ_STS1: + case DAR_IRQ_STS2: + case DAR_IRQ_STS3: + /* use them in spi_async and regmap so it's volatile */ + return true; + default: + return false; + } +} + +static bool +mcr20a_dar_precious(struct device *dev, unsigned int reg) +{ + /* don't clear irq line on read */ + switch (reg) { + case DAR_IRQ_STS1: + case DAR_IRQ_STS2: + case DAR_IRQ_STS3: + return true; + default: + return false; + } +} + +static const struct regmap_config mcr20a_dar_regmap = { + .name = "mcr20a_dar", + .reg_bits = 8, + .val_bits = 8, + .write_flag_mask = REGISTER_ACCESS | REGISTER_WRITE, + .read_flag_mask = REGISTER_ACCESS | REGISTER_READ, + .cache_type = REGCACHE_RBTREE, + .writeable_reg = mcr20a_dar_writeable, + .readable_reg = mcr20a_dar_readable, + .volatile_reg = mcr20a_dar_volatile, + .precious_reg = mcr20a_dar_precious, + .fast_io = true, + .can_multi_write = true, +}; + +static bool +mcr20a_iar_writeable(struct device *dev, unsigned int reg) +{ + switch (reg) { + case IAR_XTAL_TRIM: + case IAR_PMC_LP_TRIM: + case IAR_MACPANID0_LSB: + case IAR_MACPANID0_MSB: + case IAR_MACSHORTADDRS0_LSB: + case IAR_MACSHORTADDRS0_MSB: + case IAR_MACLONGADDRS0_0: + case IAR_MACLONGADDRS0_8: + case IAR_MACLONGADDRS0_16: + case IAR_MACLONGADDRS0_24: + case IAR_MACLONGADDRS0_32: + case IAR_MACLONGADDRS0_40: + case IAR_MACLONGADDRS0_48: + case IAR_MACLONGADDRS0_56: + case IAR_RX_FRAME_FILTER: + case IAR_PLL_INT1: + case IAR_PLL_FRAC1_LSB: + case IAR_PLL_FRAC1_MSB: + case IAR_MACPANID1_LSB: + case IAR_MACPANID1_MSB: + case IAR_MACSHORTADDRS1_LSB: + case IAR_MACSHORTADDRS1_MSB: + case IAR_MACLONGADDRS1_0: + case IAR_MACLONGADDRS1_8: + case IAR_MACLONGADDRS1_16: + case IAR_MACLONGADDRS1_24: + case IAR_MACLONGADDRS1_32: + case IAR_MACLONGADDRS1_40: + case IAR_MACLONGADDRS1_48: + case IAR_MACLONGADDRS1_56: + case IAR_DUAL_PAN_CTRL: + case IAR_DUAL_PAN_DWELL: + case IAR_CCA1_THRESH: + case IAR_CCA1_ED_OFFSET_COMP: + case IAR_LQI_OFFSET_COMP: + case IAR_CCA_CTRL: + case IAR_CCA2_CORR_PEAKS: + case IAR_CCA2_CORR_THRESH: + case IAR_TMR_PRESCALE: + case IAR_ANT_PAD_CTRL: + case IAR_MISC_PAD_CTRL: + case IAR_BSM_CTRL: + case IAR_RNG: + case IAR_RX_WTR_MARK: + case IAR_SOFT_RESET: + case IAR_TXDELAY: + case IAR_ACKDELAY: + case IAR_CORR_NVAL: + case IAR_ANT_AGC_CTRL: + case IAR_AGC_THR1: + case IAR_AGC_THR2: + case IAR_PA_CAL: + case IAR_ATT_RSSI1: + case IAR_ATT_RSSI2: + case IAR_RSSI_OFFSET: + case IAR_XTAL_CTRL: + case IAR_CHF_PMA_GAIN: + case IAR_CHF_IBUF: + case IAR_CHF_QBUF: + case IAR_CHF_IRIN: + case IAR_CHF_QRIN: + case IAR_CHF_IL: + case IAR_CHF_QL: + case IAR_CHF_CC1: + case IAR_CHF_CCL: + case IAR_CHF_CC2: + case IAR_CHF_IROUT: + case IAR_CHF_QROUT: + case IAR_PA_TUNING: + case IAR_VCO_CTRL1: + case IAR_VCO_CTRL2: + return true; + default: + return false; + } +} + +static bool +mcr20a_iar_readable(struct device *dev, unsigned int reg) +{ + bool rc; + + /* all writeable are also readable */ + rc = mcr20a_iar_writeable(dev, reg); + if (rc) + return rc; + + /* readonly regs */ + switch (reg) { + case IAR_PART_ID: + case IAR_DUAL_PAN_STS: + case IAR_RX_BYTE_COUNT: + case IAR_FILTERFAIL_CODE1: + case IAR_FILTERFAIL_CODE2: + case IAR_RSSI: + return true; + default: + return false; + } +} + +static bool +mcr20a_iar_volatile(struct device *dev, unsigned int reg) +{ +/* can be changed during runtime */ + switch (reg) { + case IAR_DUAL_PAN_STS: + case IAR_RX_BYTE_COUNT: + case IAR_FILTERFAIL_CODE1: + case IAR_FILTERFAIL_CODE2: + case IAR_RSSI: + return true; + default: + return false; + } +} + +static const struct regmap_config mcr20a_iar_regmap = { + .name = "mcr20a_iar", + .reg_bits = 16, + .val_bits = 8, + .write_flag_mask = REGISTER_ACCESS | REGISTER_WRITE | IAR_INDEX, + .read_flag_mask = REGISTER_ACCESS | REGISTER_READ | IAR_INDEX, + .cache_type = REGCACHE_RBTREE, + .writeable_reg = mcr20a_iar_writeable, + .readable_reg = mcr20a_iar_readable, + .volatile_reg = mcr20a_iar_volatile, + .fast_io = true, +}; + +struct mcr20a_local { + struct spi_device *spi; + + struct ieee802154_hw *hw; + struct mcr20a_platform_data *pdata; + struct regmap *regmap_dar; + struct regmap *regmap_iar; + + u8 *buf; + + bool is_tx; + + /* for writing tx buffer */ + struct spi_message tx_buf_msg; + u8 tx_header[1]; + /* burst buffer write command */ + struct spi_transfer tx_xfer_header; + u8 tx_len[1]; + /* len of tx packet */ + struct spi_transfer tx_xfer_len; + /* data of tx packet */ + struct spi_transfer tx_xfer_buf; + struct sk_buff *tx_skb; + + /* for read length rxfifo */ + struct spi_message reg_msg; + u8 reg_cmd[1]; + u8 reg_data[MCR20A_IRQSTS_NUM]; + struct spi_transfer reg_xfer_cmd; + struct spi_transfer reg_xfer_data; + + /* receive handling */ + struct spi_message rx_buf_msg; + u8 rx_header[1]; + struct spi_transfer rx_xfer_header; + u8 rx_lqi[1]; + struct spi_transfer rx_xfer_lqi; + u8 rx_buf[MCR20A_MAX_BUF]; + struct spi_transfer rx_xfer_buf; + + /* isr handling for reading intstat */ + struct spi_message irq_msg; + u8 irq_header[1]; + u8 irq_data[MCR20A_IRQSTS_NUM]; + struct spi_transfer irq_xfer_data; + struct spi_transfer irq_xfer_header; +}; + +static void +mcr20a_write_tx_buf_complete(void *context) +{ + struct mcr20a_local *lp = context; + int ret; + + dev_dbg(printdev(lp), "%s\n", __func__); + + lp->reg_msg.complete = NULL; + lp->reg_cmd[0] = MCR20A_WRITE_REG(DAR_PHY_CTRL1); + lp->reg_data[0] = MCR20A_XCVSEQ_TX; + lp->reg_xfer_data.len = 1; + + ret = spi_async(lp->spi, &lp->reg_msg); + if (ret) + dev_err(printdev(lp), "failed to set SEQ TX\n"); +} + +static int +mcr20a_xmit(struct ieee802154_hw *hw, struct sk_buff *skb) +{ + struct mcr20a_local *lp = hw->priv; + + dev_dbg(printdev(lp), "%s\n", __func__); + + lp->tx_skb = skb; + + print_hex_dump_debug("mcr20a tx: ", DUMP_PREFIX_OFFSET, 16, 1, + skb->data, skb->len, 0); + + lp->is_tx = 1; + + lp->reg_msg.complete = NULL; + lp->reg_cmd[0] = MCR20A_WRITE_REG(DAR_PHY_CTRL1); + lp->reg_data[0] = MCR20A_XCVSEQ_IDLE; + lp->reg_xfer_data.len = 1; + + return spi_async(lp->spi, &lp->reg_msg); +} + +static int +mcr20a_ed(struct ieee802154_hw *hw, u8 *level) +{ + WARN_ON(!level); + *level = 0xbe; + return 0; +} + +static int +mcr20a_set_channel(struct ieee802154_hw *hw, u8 page, u8 channel) +{ + struct mcr20a_local *lp = hw->priv; + int ret; + + dev_dbg(printdev(lp), "%s\n", __func__); + + /* freqency = ((PLL_INT+64) + (PLL_FRAC/65536)) * 32 MHz */ + ret = regmap_write(lp->regmap_dar, DAR_PLL_INT0, PLL_INT[channel - 11]); + if (ret) + return ret; + ret = regmap_write(lp->regmap_dar, DAR_PLL_FRAC0_LSB, 0x00); + if (ret) + return ret; + ret = regmap_write(lp->regmap_dar, DAR_PLL_FRAC0_MSB, + PLL_FRAC[channel - 11]); + if (ret) + return ret; + + return 0; +} + +static int +mcr20a_start(struct ieee802154_hw *hw) +{ + struct mcr20a_local *lp = hw->priv; + int ret; + + dev_dbg(printdev(lp), "%s\n", __func__); + + /* No slotted operation */ + dev_dbg(printdev(lp), "no slotted operation\n"); + ret = regmap_update_bits(lp->regmap_dar, DAR_PHY_CTRL1, + DAR_PHY_CTRL1_SLOTTED, 0x0); + + /* enable irq */ + enable_irq(lp->spi->irq); + + /* Unmask SEQ interrupt */ + ret = regmap_update_bits(lp->regmap_dar, DAR_PHY_CTRL2, + DAR_PHY_CTRL2_SEQMSK, 0x0); + + /* Start the RX sequence */ + dev_dbg(printdev(lp), "start the RX sequence\n"); + ret = regmap_update_bits(lp->regmap_dar, DAR_PHY_CTRL1, + DAR_PHY_CTRL1_XCVSEQ_MASK, MCR20A_XCVSEQ_RX); + + return 0; +} + +static void +mcr20a_stop(struct ieee802154_hw *hw) +{ + struct mcr20a_local *lp = hw->priv; + + dev_dbg(printdev(lp), "%s\n", __func__); + + /* stop all running sequence */ + regmap_update_bits(lp->regmap_dar, DAR_PHY_CTRL1, + DAR_PHY_CTRL1_XCVSEQ_MASK, MCR20A_XCVSEQ_IDLE); + + /* disable irq */ + disable_irq(lp->spi->irq); +} + +static int +mcr20a_set_hw_addr_filt(struct ieee802154_hw *hw, + struct ieee802154_hw_addr_filt *filt, + unsigned long changed) +{ + struct mcr20a_local *lp = hw->priv; + + dev_dbg(printdev(lp), "%s\n", __func__); + + if (changed & IEEE802154_AFILT_SADDR_CHANGED) { + u16 addr = le16_to_cpu(filt->short_addr); + + regmap_write(lp->regmap_iar, IAR_MACSHORTADDRS0_LSB, addr); + regmap_write(lp->regmap_iar, IAR_MACSHORTADDRS0_MSB, addr >> 8); + } + + if (changed & IEEE802154_AFILT_PANID_CHANGED) { + u16 pan = le16_to_cpu(filt->pan_id); + + regmap_write(lp->regmap_iar, IAR_MACPANID0_LSB, pan); + regmap_write(lp->regmap_iar, IAR_MACPANID0_MSB, pan >> 8); + } + + if (changed & IEEE802154_AFILT_IEEEADDR_CHANGED) { + u8 addr[8], i; + + memcpy(addr, &filt->ieee_addr, 8); + for (i = 0; i < 8; i++) + regmap_write(lp->regmap_iar, + IAR_MACLONGADDRS0_0 + i, addr[i]); + } + + if (changed & IEEE802154_AFILT_PANC_CHANGED) { + if (filt->pan_coord) { + regmap_update_bits(lp->regmap_dar, DAR_PHY_CTRL4, + DAR_PHY_CTRL4_PANCORDNTR0, 0x10); + } else { + regmap_update_bits(lp->regmap_dar, DAR_PHY_CTRL4, + DAR_PHY_CTRL4_PANCORDNTR0, 0x00); + } + } + + return 0; +} + +/* -30 dBm to 10 dBm */ +#define MCR20A_MAX_TX_POWERS 0x14 +static const s32 mcr20a_powers[MCR20A_MAX_TX_POWERS + 1] = { + -3000, -2800, -2600, -2400, -2200, -2000, -1800, -1600, -1400, + -1200, -1000, -800, -600, -400, -200, 0, 200, 400, 600, 800, 1000 +}; + +static int +mcr20a_set_txpower(struct ieee802154_hw *hw, s32 mbm) +{ + struct mcr20a_local *lp = hw->priv; + u32 i; + + dev_dbg(printdev(lp), "%s(%d)\n", __func__, mbm); + + for (i = 0; i < lp->hw->phy->supported.tx_powers_size; i++) { + if (lp->hw->phy->supported.tx_powers[i] == mbm) + return regmap_write(lp->regmap_dar, DAR_PA_PWR, + ((i + 8) & 0x1F)); + } + + return -EINVAL; +} + +#define MCR20A_MAX_ED_LEVELS MCR20A_MIN_CCA_THRESHOLD +static s32 mcr20a_ed_levels[MCR20A_MAX_ED_LEVELS + 1]; + +static int +mcr20a_set_cca_mode(struct ieee802154_hw *hw, + const struct wpan_phy_cca *cca) +{ + struct mcr20a_local *lp = hw->priv; + unsigned int cca_mode = 0xff; + bool cca_mode_and = false; + int ret; + + dev_dbg(printdev(lp), "%s\n", __func__); + + /* mapping 802.15.4 to driver spec */ + switch (cca->mode) { + case NL802154_CCA_ENERGY: + cca_mode = MCR20A_CCA_MODE1; + break; + case NL802154_CCA_CARRIER: + cca_mode = MCR20A_CCA_MODE2; + break; + case NL802154_CCA_ENERGY_CARRIER: + switch (cca->opt) { + case NL802154_CCA_OPT_ENERGY_CARRIER_AND: + cca_mode = MCR20A_CCA_MODE3; + cca_mode_and = true; + break; + case NL802154_CCA_OPT_ENERGY_CARRIER_OR: + cca_mode = MCR20A_CCA_MODE3; + cca_mode_and = false; + break; + default: + return -EINVAL; + } + break; + default: + return -EINVAL; + } + ret = regmap_update_bits(lp->regmap_dar, DAR_PHY_CTRL4, + DAR_PHY_CTRL4_CCATYPE_MASK, + cca_mode << DAR_PHY_CTRL4_CCATYPE_SHIFT); + if (ret < 0) + return ret; + + if (cca_mode == MCR20A_CCA_MODE3) { + if (cca_mode_and) { + ret = regmap_update_bits(lp->regmap_iar, IAR_CCA_CTRL, + IAR_CCA_CTRL_CCA3_AND_NOT_OR, + 0x08); + } else { + ret = regmap_update_bits(lp->regmap_iar, + IAR_CCA_CTRL, + IAR_CCA_CTRL_CCA3_AND_NOT_OR, + 0x00); + } + if (ret < 0) + return ret; + } + + return ret; +} + +static int +mcr20a_set_cca_ed_level(struct ieee802154_hw *hw, s32 mbm) +{ + struct mcr20a_local *lp = hw->priv; + u32 i; + + dev_dbg(printdev(lp), "%s\n", __func__); + + for (i = 0; i < hw->phy->supported.cca_ed_levels_size; i++) { + if (hw->phy->supported.cca_ed_levels[i] == mbm) + return regmap_write(lp->regmap_iar, IAR_CCA1_THRESH, i); + } + + return 0; +} + +static int +mcr20a_set_promiscuous_mode(struct ieee802154_hw *hw, const bool on) +{ + struct mcr20a_local *lp = hw->priv; + int ret; + u8 rx_frame_filter_reg = 0x0; + u8 val; + + dev_dbg(printdev(lp), "%s(%d)\n", __func__, on); + + if (on) { + /* All frame types accepted*/ + val |= DAR_PHY_CTRL4_PROMISCUOUS; + rx_frame_filter_reg &= ~(IAR_RX_FRAME_FLT_FRM_VER); + rx_frame_filter_reg |= (IAR_RX_FRAME_FLT_ACK_FT | + IAR_RX_FRAME_FLT_NS_FT); + + ret = regmap_update_bits(lp->regmap_dar, DAR_PHY_CTRL4, + DAR_PHY_CTRL4_PROMISCUOUS, + DAR_PHY_CTRL4_PROMISCUOUS); + if (ret < 0) + return ret; + + ret = regmap_write(lp->regmap_iar, IAR_RX_FRAME_FILTER, + rx_frame_filter_reg); + if (ret < 0) + return ret; + } else { + ret = regmap_update_bits(lp->regmap_dar, DAR_PHY_CTRL4, + DAR_PHY_CTRL4_PROMISCUOUS, 0x0); + if (ret < 0) + return ret; + + ret = regmap_write(lp->regmap_iar, IAR_RX_FRAME_FILTER, + IAR_RX_FRAME_FLT_FRM_VER | + IAR_RX_FRAME_FLT_BEACON_FT | + IAR_RX_FRAME_FLT_DATA_FT | + IAR_RX_FRAME_FLT_CMD_FT); + if (ret < 0) + return ret; + } + + return 0; +} + +static const struct ieee802154_ops mcr20a_hw_ops = { + .owner = THIS_MODULE, + .xmit_async = mcr20a_xmit, + .ed = mcr20a_ed, + .set_channel = mcr20a_set_channel, + .start = mcr20a_start, + .stop = mcr20a_stop, + .set_hw_addr_filt = mcr20a_set_hw_addr_filt, + .set_txpower = mcr20a_set_txpower, + .set_cca_mode = mcr20a_set_cca_mode, + .set_cca_ed_level = mcr20a_set_cca_ed_level, + .set_promiscuous_mode = mcr20a_set_promiscuous_mode, +}; + +static int +mcr20a_request_rx(struct mcr20a_local *lp) +{ + dev_dbg(printdev(lp), "%s\n", __func__); + + /* Start the RX sequence */ + regmap_update_bits_async(lp->regmap_dar, DAR_PHY_CTRL1, + DAR_PHY_CTRL1_XCVSEQ_MASK, MCR20A_XCVSEQ_RX); + + return 0; +} + +static void +mcr20a_handle_rx_read_buf_complete(void *context) +{ + struct mcr20a_local *lp = context; + u8 len = lp->reg_data[0] & DAR_RX_FRAME_LENGTH_MASK; + struct sk_buff *skb; + + dev_dbg(printdev(lp), "%s\n", __func__); + + dev_dbg(printdev(lp), "RX is done\n"); + + if (!ieee802154_is_valid_psdu_len(len)) { + dev_vdbg(&lp->spi->dev, "corrupted frame received\n"); + len = IEEE802154_MTU; + } + + len = len - 2; /* get rid of frame check field */ + + skb = dev_alloc_skb(len); + if (!skb) + return; + + memcpy(skb_put(skb, len), lp->rx_buf, len); + ieee802154_rx_irqsafe(lp->hw, skb, lp->rx_lqi[0]); + + print_hex_dump_debug("mcr20a rx: ", DUMP_PREFIX_OFFSET, 16, 1, + lp->rx_buf, len, 0); + pr_debug("mcr20a rx: lqi: %02hhx\n", lp->rx_lqi[0]); + + /* start RX sequence */ + mcr20a_request_rx(lp); +} + +static void +mcr20a_handle_rx_read_len_complete(void *context) +{ + struct mcr20a_local *lp = context; + u8 len; + int ret; + + dev_dbg(printdev(lp), "%s\n", __func__); + + /* get the length of received frame */ + len = lp->reg_data[0] & DAR_RX_FRAME_LENGTH_MASK; + dev_dbg(printdev(lp), "frame len : %d\n", len); + + /* prepare to read the rx buf */ + lp->rx_buf_msg.complete = mcr20a_handle_rx_read_buf_complete; + lp->rx_header[0] = MCR20A_BURST_READ_PACKET_BUF; + lp->rx_xfer_buf.len = len; + + ret = spi_async(lp->spi, &lp->rx_buf_msg); + if (ret) + dev_err(printdev(lp), "failed to read rx buffer length\n"); +} + +static int +mcr20a_handle_rx(struct mcr20a_local *lp) +{ + dev_dbg(printdev(lp), "%s\n", __func__); + lp->reg_msg.complete = mcr20a_handle_rx_read_len_complete; + lp->reg_cmd[0] = MCR20A_READ_REG(DAR_RX_FRM_LEN); + lp->reg_xfer_data.len = 1; + + return spi_async(lp->spi, &lp->reg_msg); +} + +static int +mcr20a_handle_tx_complete(struct mcr20a_local *lp) +{ + dev_dbg(printdev(lp), "%s\n", __func__); + + ieee802154_xmit_complete(lp->hw, lp->tx_skb, false); + + return mcr20a_request_rx(lp); +} + +static int +mcr20a_handle_tx(struct mcr20a_local *lp) +{ + int ret; + + dev_dbg(printdev(lp), "%s\n", __func__); + + /* write tx buffer */ + lp->tx_header[0] = MCR20A_BURST_WRITE_PACKET_BUF; + /* add 2 bytes of FCS */ + lp->tx_len[0] = lp->tx_skb->len + 2; + lp->tx_xfer_buf.tx_buf = lp->tx_skb->data; + /* add 1 byte psduLength */ + lp->tx_xfer_buf.len = lp->tx_skb->len + 1; + + ret = spi_async(lp->spi, &lp->tx_buf_msg); + if (ret) { + dev_err(printdev(lp), "SPI write Failed for TX buf\n"); + return ret; + } + + return 0; +} + +static void +mcr20a_irq_clean_complete(void *context) +{ + struct mcr20a_local *lp = context; + u8 seq_state = lp->irq_data[DAR_IRQ_STS1] & DAR_PHY_CTRL1_XCVSEQ_MASK; + + dev_dbg(printdev(lp), "%s\n", __func__); + + enable_irq(lp->spi->irq); + + dev_dbg(printdev(lp), "IRQ STA1 (%02x) STA2 (%02x)\n", + lp->irq_data[DAR_IRQ_STS1], lp->irq_data[DAR_IRQ_STS2]); + + switch (seq_state) { + /* TX IRQ, RX IRQ and SEQ IRQ */ + case (0x03): + if (lp->is_tx) { + lp->is_tx = 0; + dev_dbg(printdev(lp), "TX is done. No ACK\n"); + mcr20a_handle_tx_complete(lp); + } + break; + case (0x05): + /* rx is starting */ + dev_dbg(printdev(lp), "RX is starting\n"); + mcr20a_handle_rx(lp); + break; + case (0x07): + if (lp->is_tx) { + /* tx is done */ + lp->is_tx = 0; + dev_dbg(printdev(lp), "TX is done. Get ACK\n"); + mcr20a_handle_tx_complete(lp); + } else { + /* rx is starting */ + dev_dbg(printdev(lp), "RX is starting\n"); + mcr20a_handle_rx(lp); + } + break; + case (0x01): + if (lp->is_tx) { + dev_dbg(printdev(lp), "TX is starting\n"); + mcr20a_handle_tx(lp); + } else { + dev_dbg(printdev(lp), "MCR20A is stop\n"); + } + break; + } +} + +static void mcr20a_irq_status_complete(void *context) +{ + int ret; + struct mcr20a_local *lp = context; + + dev_dbg(printdev(lp), "%s\n", __func__); + regmap_update_bits_async(lp->regmap_dar, DAR_PHY_CTRL1, + DAR_PHY_CTRL1_XCVSEQ_MASK, MCR20A_XCVSEQ_IDLE); + + lp->reg_msg.complete = mcr20a_irq_clean_complete; + lp->reg_cmd[0] = MCR20A_WRITE_REG(DAR_IRQ_STS1); + memcpy(lp->reg_data, lp->irq_data, MCR20A_IRQSTS_NUM); + lp->reg_xfer_data.len = MCR20A_IRQSTS_NUM; + + ret = spi_async(lp->spi, &lp->reg_msg); + + if (ret) + dev_err(printdev(lp), "failed to clean irq status\n"); +} + +static irqreturn_t mcr20a_irq_isr(int irq, void *data) +{ + struct mcr20a_local *lp = data; + int ret; + + disable_irq_nosync(irq); + + lp->irq_header[0] = MCR20A_READ_REG(DAR_IRQ_STS1); + /* read IRQSTSx */ + ret = spi_async(lp->spi, &lp->irq_msg); + if (ret) { + enable_irq(irq); + return IRQ_NONE; + } + + return IRQ_HANDLED; +} + +static int mcr20a_get_platform_data(struct spi_device *spi, + struct mcr20a_platform_data *pdata) +{ + int ret = 0; + + if (!spi->dev.of_node) + return -EINVAL; + + pdata->rst_gpio = of_get_named_gpio(spi->dev.of_node, "rst_b-gpio", 0); + dev_dbg(&spi->dev, "rst_b-gpio: %d\n", pdata->rst_gpio); + + return ret; +} + +static void mcr20a_hw_setup(struct mcr20a_local *lp) +{ + u8 i; + struct ieee802154_hw *hw = lp->hw; + struct wpan_phy *phy = lp->hw->phy; + + dev_dbg(printdev(lp), "%s\n", __func__); + + phy->symbol_duration = 16; + phy->lifs_period = 40; + phy->sifs_period = 12; + + hw->flags = IEEE802154_HW_TX_OMIT_CKSUM | + IEEE802154_HW_AFILT | + IEEE802154_HW_PROMISCUOUS; + + phy->flags = WPAN_PHY_FLAG_TXPOWER | WPAN_PHY_FLAG_CCA_ED_LEVEL | + WPAN_PHY_FLAG_CCA_MODE; + + phy->supported.cca_modes = BIT(NL802154_CCA_ENERGY) | + BIT(NL802154_CCA_CARRIER) | BIT(NL802154_CCA_ENERGY_CARRIER); + phy->supported.cca_opts = BIT(NL802154_CCA_OPT_ENERGY_CARRIER_AND) | + BIT(NL802154_CCA_OPT_ENERGY_CARRIER_OR); + + /* initiating cca_ed_levels */ + for (i = MCR20A_MAX_CCA_THRESHOLD; i < MCR20A_MIN_CCA_THRESHOLD + 1; + ++i) { + mcr20a_ed_levels[i] = -i * 100; + } + + phy->supported.cca_ed_levels = mcr20a_ed_levels; + phy->supported.cca_ed_levels_size = ARRAY_SIZE(mcr20a_ed_levels); + + phy->cca.mode = NL802154_CCA_ENERGY; + + phy->supported.channels[0] = MCR20A_VALID_CHANNELS; + phy->current_page = 0; + /* MCR20A default reset value */ + phy->current_channel = 20; + phy->symbol_duration = 16; + phy->supported.tx_powers = mcr20a_powers; + phy->supported.tx_powers_size = ARRAY_SIZE(mcr20a_powers); + phy->cca_ed_level = phy->supported.cca_ed_levels[75]; + phy->transmit_power = phy->supported.tx_powers[0x0F]; +} + +static void +mcr20a_setup_tx_spi_messages(struct mcr20a_local *lp) +{ + spi_message_init(&lp->tx_buf_msg); + lp->tx_buf_msg.context = lp; + lp->tx_buf_msg.complete = mcr20a_write_tx_buf_complete; + + lp->tx_xfer_header.len = 1; + lp->tx_xfer_header.tx_buf = lp->tx_header; + + lp->tx_xfer_len.len = 1; + lp->tx_xfer_len.tx_buf = lp->tx_len; + + spi_message_add_tail(&lp->tx_xfer_header, &lp->tx_buf_msg); + spi_message_add_tail(&lp->tx_xfer_len, &lp->tx_buf_msg); + spi_message_add_tail(&lp->tx_xfer_buf, &lp->tx_buf_msg); +} + +static void +mcr20a_setup_rx_spi_messages(struct mcr20a_local *lp) +{ + spi_message_init(&lp->reg_msg); + lp->reg_msg.context = lp; + + lp->reg_xfer_cmd.len = 1; + lp->reg_xfer_cmd.tx_buf = lp->reg_cmd; + lp->reg_xfer_cmd.rx_buf = lp->reg_cmd; + + lp->reg_xfer_data.rx_buf = lp->reg_data; + lp->reg_xfer_data.tx_buf = lp->reg_data; + + spi_message_add_tail(&lp->reg_xfer_cmd, &lp->reg_msg); + spi_message_add_tail(&lp->reg_xfer_data, &lp->reg_msg); + + spi_message_init(&lp->rx_buf_msg); + lp->rx_buf_msg.context = lp; + lp->rx_buf_msg.complete = mcr20a_handle_rx_read_buf_complete; + lp->rx_xfer_header.len = 1; + lp->rx_xfer_header.tx_buf = lp->rx_header; + lp->rx_xfer_header.rx_buf = lp->rx_header; + + lp->rx_xfer_buf.rx_buf = lp->rx_buf; + + lp->rx_xfer_lqi.len = 1; + lp->rx_xfer_lqi.rx_buf = lp->rx_lqi; + + spi_message_add_tail(&lp->rx_xfer_header, &lp->rx_buf_msg); + spi_message_add_tail(&lp->rx_xfer_buf, &lp->rx_buf_msg); + spi_message_add_tail(&lp->rx_xfer_lqi, &lp->rx_buf_msg); +} + +static void +mcr20a_setup_irq_spi_messages(struct mcr20a_local *lp) +{ + spi_message_init(&lp->irq_msg); + lp->irq_msg.context = lp; + lp->irq_msg.complete = mcr20a_irq_status_complete; + lp->irq_xfer_header.len = 1; + lp->irq_xfer_header.tx_buf = lp->irq_header; + lp->irq_xfer_header.rx_buf = lp->irq_header; + + lp->irq_xfer_data.len = MCR20A_IRQSTS_NUM; + lp->irq_xfer_data.rx_buf = lp->irq_data; + + spi_message_add_tail(&lp->irq_xfer_header, &lp->irq_msg); + spi_message_add_tail(&lp->irq_xfer_data, &lp->irq_msg); +} + +static int +mcr20a_phy_init(struct mcr20a_local *lp) +{ + u8 index; + unsigned int phy_reg = 0; + int ret; + + dev_dbg(printdev(lp), "%s\n", __func__); + + /* Disable Tristate on COCO MISO for SPI reads */ + ret = regmap_write(lp->regmap_iar, IAR_MISC_PAD_CTRL, 0x02); + if (ret) + goto err_ret; + + /* Clear all PP IRQ bits in IRQSTS1 to avoid unexpected interrupts + * immediately after init + */ + ret = regmap_write(lp->regmap_dar, DAR_IRQ_STS1, 0xEF); + if (ret) + goto err_ret; + + /* Clear all PP IRQ bits in IRQSTS2 */ + ret = regmap_write(lp->regmap_dar, DAR_IRQ_STS2, + DAR_IRQSTS2_ASM_IRQ | DAR_IRQSTS2_PB_ERR_IRQ | + DAR_IRQSTS2_WAKE_IRQ); + if (ret) + goto err_ret; + + /* Disable all timer interrupts */ + ret = regmap_write(lp->regmap_dar, DAR_IRQ_STS3, 0xFF); + if (ret) + goto err_ret; + + /* PHY_CTRL1 : default HW settings + AUTOACK enabled */ + ret = regmap_update_bits(lp->regmap_dar, DAR_PHY_CTRL1, + DAR_PHY_CTRL1_AUTOACK, DAR_PHY_CTRL1_AUTOACK); + + /* PHY_CTRL2 : disable all interrupts */ + ret = regmap_write(lp->regmap_dar, DAR_PHY_CTRL2, 0xFF); + if (ret) + goto err_ret; + + /* PHY_CTRL3 : disable all timers and remaining interrupts */ + ret = regmap_write(lp->regmap_dar, DAR_PHY_CTRL3, + DAR_PHY_CTRL3_ASM_MSK | DAR_PHY_CTRL3_PB_ERR_MSK | + DAR_PHY_CTRL3_WAKE_MSK); + if (ret) + goto err_ret; + + /* SRC_CTRL : enable Acknowledge Frame Pending and + * Source Address Matching Enable + */ + ret = regmap_write(lp->regmap_dar, DAR_SRC_CTRL, + DAR_SRC_CTRL_ACK_FRM_PND | + (DAR_SRC_CTRL_INDEX << DAR_SRC_CTRL_INDEX_SHIFT)); + if (ret) + goto err_ret; + + /* RX_FRAME_FILTER */ + /* FRM_VER[1:0] = b11. Accept FrameVersion 0 and 1 packets */ + ret = regmap_write(lp->regmap_iar, IAR_RX_FRAME_FILTER, + IAR_RX_FRAME_FLT_FRM_VER | + IAR_RX_FRAME_FLT_BEACON_FT | + IAR_RX_FRAME_FLT_DATA_FT | + IAR_RX_FRAME_FLT_CMD_FT); + if (ret) + goto err_ret; + + dev_info(printdev(lp), "MCR20A DAR overwrites version: 0x%02x\n", + MCR20A_OVERWRITE_VERSION); + + /* Overwrites direct registers */ + ret = regmap_write(lp->regmap_dar, DAR_OVERWRITE_VER, + MCR20A_OVERWRITE_VERSION); + if (ret) + goto err_ret; + + /* Overwrites indirect registers */ + ret = regmap_multi_reg_write(lp->regmap_iar, mar20a_iar_overwrites, + ARRAY_SIZE(mar20a_iar_overwrites)); + if (ret) + goto err_ret; + + /* Clear HW indirect queue */ + dev_dbg(printdev(lp), "clear HW indirect queue\n"); + for (index = 0; index < MCR20A_PHY_INDIRECT_QUEUE_SIZE; index++) { + phy_reg = (u8)(((index & DAR_SRC_CTRL_INDEX) << + DAR_SRC_CTRL_INDEX_SHIFT) + | (DAR_SRC_CTRL_SRCADDR_EN) + | (DAR_SRC_CTRL_INDEX_DISABLE)); + ret = regmap_write(lp->regmap_dar, DAR_SRC_CTRL, phy_reg); + if (ret) + goto err_ret; + phy_reg = 0; + } + + /* Assign HW Indirect hash table to PAN0 */ + ret = regmap_read(lp->regmap_iar, IAR_DUAL_PAN_CTRL, &phy_reg); + if (ret) + goto err_ret; + + /* Clear current lvl */ + phy_reg &= ~IAR_DUAL_PAN_CTRL_DUAL_PAN_SAM_LVL_MSK; + + /* Set new lvl */ + phy_reg |= MCR20A_PHY_INDIRECT_QUEUE_SIZE << + IAR_DUAL_PAN_CTRL_DUAL_PAN_SAM_LVL_SHIFT; + ret = regmap_write(lp->regmap_iar, IAR_DUAL_PAN_CTRL, phy_reg); + if (ret) + goto err_ret; + + /* Set CCA threshold to -75 dBm */ + ret = regmap_write(lp->regmap_iar, IAR_CCA1_THRESH, 0x4B); + if (ret) + goto err_ret; + + /* Set prescaller to obtain 1 symbol (16us) timebase */ + ret = regmap_write(lp->regmap_iar, IAR_TMR_PRESCALE, 0x05); + if (ret) + goto err_ret; + + /* Enable autodoze mode. */ + ret = regmap_update_bits(lp->regmap_dar, DAR_PWR_MODES, + DAR_PWR_MODES_AUTODOZE, + DAR_PWR_MODES_AUTODOZE); + if (ret) + goto err_ret; + + /* Disable clk_out */ + ret = regmap_update_bits(lp->regmap_dar, DAR_CLK_OUT_CTRL, + DAR_CLK_OUT_CTRL_EN, 0x0); + if (ret) + goto err_ret; + + return 0; + +err_ret: + return ret; +} + +static int +mcr20a_probe(struct spi_device *spi) +{ + struct ieee802154_hw *hw; + struct mcr20a_local *lp; + struct mcr20a_platform_data *pdata; + int irq_type; + int ret = -ENOMEM; + + dev_dbg(&spi->dev, "%s\n", __func__); + + if (!spi->irq) { + dev_err(&spi->dev, "no IRQ specified\n"); + return -EINVAL; + } + + pdata = kmalloc(sizeof(*pdata), GFP_KERNEL); + if (!pdata) + return -ENOMEM; + + /* set mcr20a platform data */ + ret = mcr20a_get_platform_data(spi, pdata); + if (ret < 0) { + dev_crit(&spi->dev, "mcr20a_get_platform_data failed.\n"); + return ret; + } + + /* init reset gpio */ + if (gpio_is_valid(pdata->rst_gpio)) { + ret = devm_gpio_request_one(&spi->dev, pdata->rst_gpio, + GPIOF_OUT_INIT_HIGH, "reset"); + if (ret) + return ret; + } + + /* reset mcr20a */ + if (gpio_is_valid(pdata->rst_gpio)) { + usleep_range(10, 20); + gpio_set_value_cansleep(pdata->rst_gpio, 0); + usleep_range(10, 20); + gpio_set_value_cansleep(pdata->rst_gpio, 1); + usleep_range(120, 240); + } + + /* allocate ieee802154_hw and private data */ + hw = ieee802154_alloc_hw(sizeof(*lp), &mcr20a_hw_ops); + if (!hw) { + dev_crit(&spi->dev, "ieee802154_alloc_hw failed\n"); + return -ENOMEM; + } + + /* init mcr20a local data */ + lp = hw->priv; + lp->hw = hw; + lp->spi = spi; + lp->spi->dev.platform_data = pdata; + lp->pdata = pdata; + + /* init ieee802154_hw */ + hw->parent = &spi->dev; + ieee802154_random_extended_addr(&hw->phy->perm_extended_addr); + + /* init buf */ + lp->buf = devm_kzalloc(&spi->dev, SPI_COMMAND_BUFFER, GFP_KERNEL); + + if (!lp->buf) + return -ENOMEM; + + mcr20a_setup_tx_spi_messages(lp); + mcr20a_setup_rx_spi_messages(lp); + mcr20a_setup_irq_spi_messages(lp); + + /* setup regmap */ + lp->regmap_dar = devm_regmap_init_spi(spi, &mcr20a_dar_regmap); + if (IS_ERR(lp->regmap_dar)) { + ret = PTR_ERR(lp->regmap_dar); + dev_err(&spi->dev, "Failed to allocate dar map: %d\n", + ret); + goto free_dev; + } + + lp->regmap_iar = devm_regmap_init_spi(spi, &mcr20a_iar_regmap); + if (IS_ERR(lp->regmap_iar)) { + ret = PTR_ERR(lp->regmap_iar); + dev_err(&spi->dev, "Failed to allocate iar map: %d\n", ret); + goto free_dev; + } + + mcr20a_hw_setup(lp); + + spi_set_drvdata(spi, lp); + + ret = mcr20a_phy_init(lp); + if (ret < 0) { + dev_crit(&spi->dev, "mcr20a_phy_init failed\n"); + goto free_dev; + } + + irq_type = irq_get_trigger_type(spi->irq); + if (!irq_type) + irq_type = IRQF_TRIGGER_FALLING; + + ret = devm_request_irq(&spi->dev, spi->irq, mcr20a_irq_isr, + irq_type, dev_name(&spi->dev), lp); + if (ret) { + dev_err(&spi->dev, "could not request_irq for mcr20a\n"); + ret = -ENODEV; + goto free_dev; + } + + /* disable_irq by default and wait for starting hardware */ + disable_irq(spi->irq); + + ret = ieee802154_register_hw(hw); + if (ret) { + dev_crit(&spi->dev, "ieee802154_register_hw failed\n"); + goto free_dev; + } + + return ret; + +free_dev: + ieee802154_free_hw(lp->hw); + + return ret; +} + +static int mcr20a_remove(struct spi_device *spi) +{ + struct mcr20a_local *lp = spi_get_drvdata(spi); + + dev_dbg(&spi->dev, "%s\n", __func__); + + ieee802154_unregister_hw(lp->hw); + ieee802154_free_hw(lp->hw); + + return 0; +} + +static const struct of_device_id mcr20a_of_match[] = { + { .compatible = "nxp,mcr20a", }, + { }, +}; +MODULE_DEVICE_TABLE(of, mcr20a_of_match); + +static const struct spi_device_id mcr20a_device_id[] = { + { .name = "mcr20a", }, + { }, +}; +MODULE_DEVICE_TABLE(spi, mcr20a_device_id); + +static struct spi_driver mcr20a_driver = { + .id_table = mcr20a_device_id, + .driver = { + .of_match_table = of_match_ptr(mcr20a_of_match), + .name = "mcr20a", + }, + .probe = mcr20a_probe, + .remove = mcr20a_remove, +}; + +module_spi_driver(mcr20a_driver); + +MODULE_DESCRIPTION("MCR20A Transceiver Driver"); +MODULE_LICENSE("GPL v2"); +MODULE_AUTHOR("Xue Liu <liuxuenetmail@gmail>"); diff --git a/drivers/net/ieee802154/mcr20a.h b/drivers/net/ieee802154/mcr20a.h new file mode 100644 index 000000000000..6da4fd00b3c5 --- /dev/null +++ b/drivers/net/ieee802154/mcr20a.h @@ -0,0 +1,498 @@ +/* + * Driver for NXP MCR20A 802.15.4 Wireless-PAN Networking controller + * + * Copyright (C) 2018 Xue Liu <liuxuenetmail@gmail.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 + * 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 _MCR20A_H +#define _MCR20A_H + +/* Direct Accress Register */ +#define DAR_IRQ_STS1 0x00 +#define DAR_IRQ_STS2 0x01 +#define DAR_IRQ_STS3 0x02 +#define DAR_PHY_CTRL1 0x03 +#define DAR_PHY_CTRL2 0x04 +#define DAR_PHY_CTRL3 0x05 +#define DAR_RX_FRM_LEN 0x06 +#define DAR_PHY_CTRL4 0x07 +#define DAR_SRC_CTRL 0x08 +#define DAR_SRC_ADDRS_SUM_LSB 0x09 +#define DAR_SRC_ADDRS_SUM_MSB 0x0A +#define DAR_CCA1_ED_FNL 0x0B +#define DAR_EVENT_TMR_LSB 0x0C +#define DAR_EVENT_TMR_MSB 0x0D +#define DAR_EVENT_TMR_USB 0x0E +#define DAR_TIMESTAMP_LSB 0x0F +#define DAR_TIMESTAMP_MSB 0x10 +#define DAR_TIMESTAMP_USB 0x11 +#define DAR_T3CMP_LSB 0x12 +#define DAR_T3CMP_MSB 0x13 +#define DAR_T3CMP_USB 0x14 +#define DAR_T2PRIMECMP_LSB 0x15 +#define DAR_T2PRIMECMP_MSB 0x16 +#define DAR_T1CMP_LSB 0x17 +#define DAR_T1CMP_MSB 0x18 +#define DAR_T1CMP_USB 0x19 +#define DAR_T2CMP_LSB 0x1A +#define DAR_T2CMP_MSB 0x1B +#define DAR_T2CMP_USB 0x1C +#define DAR_T4CMP_LSB 0x1D +#define DAR_T4CMP_MSB 0x1E +#define DAR_T4CMP_USB 0x1F +#define DAR_PLL_INT0 0x20 +#define DAR_PLL_FRAC0_LSB 0x21 +#define DAR_PLL_FRAC0_MSB 0x22 +#define DAR_PA_PWR 0x23 +#define DAR_SEQ_STATE 0x24 +#define DAR_LQI_VALUE 0x25 +#define DAR_RSSI_CCA_CONT 0x26 +/*------------------ 0x27 */ +#define DAR_ASM_CTRL1 0x28 +#define DAR_ASM_CTRL2 0x29 +#define DAR_ASM_DATA_0 0x2A +#define DAR_ASM_DATA_1 0x2B +#define DAR_ASM_DATA_2 0x2C +#define DAR_ASM_DATA_3 0x2D +#define DAR_ASM_DATA_4 0x2E +#define DAR_ASM_DATA_5 0x2F +#define DAR_ASM_DATA_6 0x30 +#define DAR_ASM_DATA_7 0x31 +#define DAR_ASM_DATA_8 0x32 +#define DAR_ASM_DATA_9 0x33 +#define DAR_ASM_DATA_A 0x34 +#define DAR_ASM_DATA_B 0x35 +#define DAR_ASM_DATA_C 0x36 +#define DAR_ASM_DATA_D 0x37 +#define DAR_ASM_DATA_E 0x38 +#define DAR_ASM_DATA_F 0x39 +/*----------------------- 0x3A */ +#define DAR_OVERWRITE_VER 0x3B +#define DAR_CLK_OUT_CTRL 0x3C +#define DAR_PWR_MODES 0x3D +#define IAR_INDEX 0x3E +#define IAR_DATA 0x3F + +/* Indirect Resgister Memory */ +#define IAR_PART_ID 0x00 +#define IAR_XTAL_TRIM 0x01 +#define IAR_PMC_LP_TRIM 0x02 +#define IAR_MACPANID0_LSB 0x03 +#define IAR_MACPANID0_MSB 0x04 +#define IAR_MACSHORTADDRS0_LSB 0x05 +#define IAR_MACSHORTADDRS0_MSB 0x06 +#define IAR_MACLONGADDRS0_0 0x07 +#define IAR_MACLONGADDRS0_8 0x08 +#define IAR_MACLONGADDRS0_16 0x09 +#define IAR_MACLONGADDRS0_24 0x0A +#define IAR_MACLONGADDRS0_32 0x0B +#define IAR_MACLONGADDRS0_40 0x0C +#define IAR_MACLONGADDRS0_48 0x0D +#define IAR_MACLONGADDRS0_56 0x0E +#define IAR_RX_FRAME_FILTER 0x0F +#define IAR_PLL_INT1 0x10 +#define IAR_PLL_FRAC1_LSB 0x11 +#define IAR_PLL_FRAC1_MSB 0x12 +#define IAR_MACPANID1_LSB 0x13 +#define IAR_MACPANID1_MSB 0x14 +#define IAR_MACSHORTADDRS1_LSB 0x15 +#define IAR_MACSHORTADDRS1_MSB 0x16 +#define IAR_MACLONGADDRS1_0 0x17 +#define IAR_MACLONGADDRS1_8 0x18 +#define IAR_MACLONGADDRS1_16 0x19 +#define IAR_MACLONGADDRS1_24 0x1A +#define IAR_MACLONGADDRS1_32 0x1B +#define IAR_MACLONGADDRS1_40 0x1C +#define IAR_MACLONGADDRS1_48 0x1D +#define IAR_MACLONGADDRS1_56 0x1E +#define IAR_DUAL_PAN_CTRL 0x1F +#define IAR_DUAL_PAN_DWELL 0x20 +#define IAR_DUAL_PAN_STS 0x21 +#define IAR_CCA1_THRESH 0x22 +#define IAR_CCA1_ED_OFFSET_COMP 0x23 +#define IAR_LQI_OFFSET_COMP 0x24 +#define IAR_CCA_CTRL 0x25 +#define IAR_CCA2_CORR_PEAKS 0x26 +#define IAR_CCA2_CORR_THRESH 0x27 +#define IAR_TMR_PRESCALE 0x28 +/*-------------------- 0x29 */ +#define IAR_GPIO_DATA 0x2A +#define IAR_GPIO_DIR 0x2B +#define IAR_GPIO_PUL_EN 0x2C +#define IAR_GPIO_PUL_SEL 0x2D +#define IAR_GPIO_DS 0x2E +/*------------------ 0x2F */ +#define IAR_ANT_PAD_CTRL 0x30 +#define IAR_MISC_PAD_CTRL 0x31 +#define IAR_BSM_CTRL 0x32 +/*------------------- 0x33 */ +#define IAR_RNG 0x34 +#define IAR_RX_BYTE_COUNT 0x35 +#define IAR_RX_WTR_MARK 0x36 +#define IAR_SOFT_RESET 0x37 +#define IAR_TXDELAY 0x38 +#define IAR_ACKDELAY 0x39 +#define IAR_SEQ_MGR_CTRL 0x3A +#define IAR_SEQ_MGR_STS 0x3B +#define IAR_SEQ_T_STS 0x3C +#define IAR_ABORT_STS 0x3D +#define IAR_CCCA_BUSY_CNT 0x3E +#define IAR_SRC_ADDR_CHECKSUM1 0x3F +#define IAR_SRC_ADDR_CHECKSUM2 0x40 +#define IAR_SRC_TBL_VALID1 0x41 +#define IAR_SRC_TBL_VALID2 0x42 +#define IAR_FILTERFAIL_CODE1 0x43 +#define IAR_FILTERFAIL_CODE2 0x44 +#define IAR_SLOT_PRELOAD 0x45 +/*-------------------- 0x46 */ +#define IAR_CORR_VT 0x47 +#define IAR_SYNC_CTRL 0x48 +#define IAR_PN_LSB_0 0x49 +#define IAR_PN_LSB_1 0x4A +#define IAR_PN_MSB_0 0x4B +#define IAR_PN_MSB_1 0x4C +#define IAR_CORR_NVAL 0x4D +#define IAR_TX_MODE_CTRL 0x4E +#define IAR_SNF_THR 0x4F +#define IAR_FAD_THR 0x50 +#define IAR_ANT_AGC_CTRL 0x51 +#define IAR_AGC_THR1 0x52 +#define IAR_AGC_THR2 0x53 +#define IAR_AGC_HYS 0x54 +#define IAR_AFC 0x55 +/*------------------- 0x56 */ +/*------------------- 0x57 */ +#define IAR_PHY_STS 0x58 +#define IAR_RX_MAX_CORR 0x59 +#define IAR_RX_MAX_PREAMBLE 0x5A +#define IAR_RSSI 0x5B +/*------------------- 0x5C */ +/*------------------- 0x5D */ +#define IAR_PLL_DIG_CTRL 0x5E +#define IAR_VCO_CAL 0x5F +#define IAR_VCO_BEST_DIFF 0x60 +#define IAR_VCO_BIAS 0x61 +#define IAR_KMOD_CTRL 0x62 +#define IAR_KMOD_CAL 0x63 +#define IAR_PA_CAL 0x64 +#define IAR_PA_PWRCAL 0x65 +#define IAR_ATT_RSSI1 0x66 +#define IAR_ATT_RSSI2 0x67 +#define IAR_RSSI_OFFSET 0x68 +#define IAR_RSSI_SLOPE 0x69 +#define IAR_RSSI_CAL1 0x6A +#define IAR_RSSI_CAL2 0x6B +/*------------------- 0x6C */ +/*------------------- 0x6D */ +#define IAR_XTAL_CTRL 0x6E +#define IAR_XTAL_COMP_MIN 0x6F +#define IAR_XTAL_COMP_MAX 0x70 +#define IAR_XTAL_GM 0x71 +/*------------------- 0x72 */ +/*------------------- 0x73 */ +#define IAR_LNA_TUNE 0x74 +#define IAR_LNA_AGCGAIN 0x75 +/*------------------- 0x76 */ +/*------------------- 0x77 */ +#define IAR_CHF_PMA_GAIN 0x78 +#define IAR_CHF_IBUF 0x79 +#define IAR_CHF_QBUF 0x7A +#define IAR_CHF_IRIN 0x7B +#define IAR_CHF_QRIN 0x7C +#define IAR_CHF_IL 0x7D +#define IAR_CHF_QL 0x7E +#define IAR_CHF_CC1 0x7F +#define IAR_CHF_CCL 0x80 +#define IAR_CHF_CC2 0x81 +#define IAR_CHF_IROUT 0x82 +#define IAR_CHF_QROUT 0x83 +/*------------------- 0x84 */ +/*------------------- 0x85 */ +#define IAR_RSSI_CTRL 0x86 +/*------------------- 0x87 */ +/*------------------- 0x88 */ +#define IAR_PA_BIAS 0x89 +#define IAR_PA_TUNING 0x8A +/*------------------- 0x8B */ +/*------------------- 0x8C */ +#define IAR_PMC_HP_TRIM 0x8D +#define IAR_VREGA_TRIM 0x8E +/*------------------- 0x8F */ +/*------------------- 0x90 */ +#define IAR_VCO_CTRL1 0x91 +#define IAR_VCO_CTRL2 0x92 +/*------------------- 0x93 */ +/*------------------- 0x94 */ +#define IAR_ANA_SPARE_OUT1 0x95 +#define IAR_ANA_SPARE_OUT2 0x96 +#define IAR_ANA_SPARE_IN 0x97 +#define IAR_MISCELLANEOUS 0x98 +/*------------------- 0x99 */ +#define IAR_SEQ_MGR_OVRD0 0x9A +#define IAR_SEQ_MGR_OVRD1 0x9B +#define IAR_SEQ_MGR_OVRD2 0x9C +#define IAR_SEQ_MGR_OVRD3 0x9D +#define IAR_SEQ_MGR_OVRD4 0x9E +#define IAR_SEQ_MGR_OVRD5 0x9F +#define IAR_SEQ_MGR_OVRD6 0xA0 +#define IAR_SEQ_MGR_OVRD7 0xA1 +/*------------------- 0xA2 */ +#define IAR_TESTMODE_CTRL 0xA3 +#define IAR_DTM_CTRL1 0xA4 +#define IAR_DTM_CTRL2 0xA5 +#define IAR_ATM_CTRL1 0xA6 +#define IAR_ATM_CTRL2 0xA7 +#define IAR_ATM_CTRL3 0xA8 +/*------------------- 0xA9 */ +#define IAR_LIM_FE_TEST_CTRL 0xAA +#define IAR_CHF_TEST_CTRL 0xAB +#define IAR_VCO_TEST_CTRL 0xAC +#define IAR_PLL_TEST_CTRL 0xAD +#define IAR_PA_TEST_CTRL 0xAE +#define IAR_PMC_TEST_CTRL 0xAF +#define IAR_SCAN_DTM_PROTECT_1 0xFE +#define IAR_SCAN_DTM_PROTECT_0 0xFF + +/* IRQSTS1 bits */ +#define DAR_IRQSTS1_RX_FRM_PEND BIT(7) +#define DAR_IRQSTS1_PLL_UNLOCK_IRQ BIT(6) +#define DAR_IRQSTS1_FILTERFAIL_IRQ BIT(5) +#define DAR_IRQSTS1_RXWTRMRKIRQ BIT(4) +#define DAR_IRQSTS1_CCAIRQ BIT(3) +#define DAR_IRQSTS1_RXIRQ BIT(2) +#define DAR_IRQSTS1_TXIRQ BIT(1) +#define DAR_IRQSTS1_SEQIRQ BIT(0) + +/* IRQSTS2 bits */ +#define DAR_IRQSTS2_CRCVALID BIT(7) +#define DAR_IRQSTS2_CCA BIT(6) +#define DAR_IRQSTS2_SRCADDR BIT(5) +#define DAR_IRQSTS2_PI BIT(4) +#define DAR_IRQSTS2_TMRSTATUS BIT(3) +#define DAR_IRQSTS2_ASM_IRQ BIT(2) +#define DAR_IRQSTS2_PB_ERR_IRQ BIT(1) +#define DAR_IRQSTS2_WAKE_IRQ BIT(0) + +/* IRQSTS3 bits */ +#define DAR_IRQSTS3_TMR4MSK BIT(7) +#define DAR_IRQSTS3_TMR3MSK BIT(6) +#define DAR_IRQSTS3_TMR2MSK BIT(5) +#define DAR_IRQSTS3_TMR1MSK BIT(4) +#define DAR_IRQSTS3_TMR4IRQ BIT(3) +#define DAR_IRQSTS3_TMR3IRQ BIT(2) +#define DAR_IRQSTS3_TMR2IRQ BIT(1) +#define DAR_IRQSTS3_TMR1IRQ BIT(0) + +/* PHY_CTRL1 bits */ +#define DAR_PHY_CTRL1_TMRTRIGEN BIT(7) +#define DAR_PHY_CTRL1_SLOTTED BIT(6) +#define DAR_PHY_CTRL1_CCABFRTX BIT(5) +#define DAR_PHY_CTRL1_CCABFRTX_SHIFT 5 +#define DAR_PHY_CTRL1_RXACKRQD BIT(4) +#define DAR_PHY_CTRL1_AUTOACK BIT(3) +#define DAR_PHY_CTRL1_XCVSEQ_MASK 0x07 + +/* PHY_CTRL2 bits */ +#define DAR_PHY_CTRL2_CRC_MSK BIT(7) +#define DAR_PHY_CTRL2_PLL_UNLOCK_MSK BIT(6) +#define DAR_PHY_CTRL2_FILTERFAIL_MSK BIT(5) +#define DAR_PHY_CTRL2_RX_WMRK_MSK BIT(4) +#define DAR_PHY_CTRL2_CCAMSK BIT(3) +#define DAR_PHY_CTRL2_RXMSK BIT(2) +#define DAR_PHY_CTRL2_TXMSK BIT(1) +#define DAR_PHY_CTRL2_SEQMSK BIT(0) + +/* PHY_CTRL3 bits */ +#define DAR_PHY_CTRL3_TMR4CMP_EN BIT(7) +#define DAR_PHY_CTRL3_TMR3CMP_EN BIT(6) +#define DAR_PHY_CTRL3_TMR2CMP_EN BIT(5) +#define DAR_PHY_CTRL3_TMR1CMP_EN BIT(4) +#define DAR_PHY_CTRL3_ASM_MSK BIT(2) +#define DAR_PHY_CTRL3_PB_ERR_MSK BIT(1) +#define DAR_PHY_CTRL3_WAKE_MSK BIT(0) + +/* RX_FRM_LEN bits */ +#define DAR_RX_FRAME_LENGTH_MASK (0x7F) + +/* PHY_CTRL4 bits */ +#define DAR_PHY_CTRL4_TRCV_MSK BIT(7) +#define DAR_PHY_CTRL4_TC3TMOUT BIT(6) +#define DAR_PHY_CTRL4_PANCORDNTR0 BIT(5) +#define DAR_PHY_CTRL4_CCATYPE (3) +#define DAR_PHY_CTRL4_CCATYPE_SHIFT (3) +#define DAR_PHY_CTRL4_CCATYPE_MASK (0x18) +#define DAR_PHY_CTRL4_TMRLOAD BIT(2) +#define DAR_PHY_CTRL4_PROMISCUOUS BIT(1) +#define DAR_PHY_CTRL4_TC2PRIME_EN BIT(0) + +/* SRC_CTRL bits */ +#define DAR_SRC_CTRL_INDEX (0x0F) +#define DAR_SRC_CTRL_INDEX_SHIFT (4) +#define DAR_SRC_CTRL_ACK_FRM_PND BIT(3) +#define DAR_SRC_CTRL_SRCADDR_EN BIT(2) +#define DAR_SRC_CTRL_INDEX_EN BIT(1) +#define DAR_SRC_CTRL_INDEX_DISABLE BIT(0) + +/* DAR_ASM_CTRL1 bits */ +#define DAR_ASM_CTRL1_CLEAR BIT(7) +#define DAR_ASM_CTRL1_START BIT(6) +#define DAR_ASM_CTRL1_SELFTST BIT(5) +#define DAR_ASM_CTRL1_CTR BIT(4) +#define DAR_ASM_CTRL1_CBC BIT(3) +#define DAR_ASM_CTRL1_AES BIT(2) +#define DAR_ASM_CTRL1_LOAD_MAC BIT(1) + +/* DAR_ASM_CTRL2 bits */ +#define DAR_ASM_CTRL2_DATA_REG_TYPE_SEL (7) +#define DAR_ASM_CTRL2_DATA_REG_TYPE_SEL_SHIFT (5) +#define DAR_ASM_CTRL2_TSTPAS BIT(1) + +/* DAR_CLK_OUT_CTRL bits */ +#define DAR_CLK_OUT_CTRL_EXTEND BIT(7) +#define DAR_CLK_OUT_CTRL_HIZ BIT(6) +#define DAR_CLK_OUT_CTRL_SR BIT(5) +#define DAR_CLK_OUT_CTRL_DS BIT(4) +#define DAR_CLK_OUT_CTRL_EN BIT(3) +#define DAR_CLK_OUT_CTRL_DIV (7) + +/* DAR_PWR_MODES bits */ +#define DAR_PWR_MODES_XTAL_READY BIT(5) +#define DAR_PWR_MODES_XTALEN BIT(4) +#define DAR_PWR_MODES_ASM_CLK_EN BIT(3) +#define DAR_PWR_MODES_AUTODOZE BIT(1) +#define DAR_PWR_MODES_PMC_MODE BIT(0) + +/* RX_FRAME_FILTER bits */ +#define IAR_RX_FRAME_FLT_FRM_VER (0xC0) +#define IAR_RX_FRAME_FLT_FRM_VER_SHIFT (6) +#define IAR_RX_FRAME_FLT_ACTIVE_PROMISCUOUS BIT(5) +#define IAR_RX_FRAME_FLT_NS_FT BIT(4) +#define IAR_RX_FRAME_FLT_CMD_FT BIT(3) +#define IAR_RX_FRAME_FLT_ACK_FT BIT(2) +#define IAR_RX_FRAME_FLT_DATA_FT BIT(1) +#define IAR_RX_FRAME_FLT_BEACON_FT BIT(0) + +/* DUAL_PAN_CTRL bits */ +#define IAR_DUAL_PAN_CTRL_DUAL_PAN_SAM_LVL_MSK (0xF0) +#define IAR_DUAL_PAN_CTRL_DUAL_PAN_SAM_LVL_SHIFT (4) +#define IAR_DUAL_PAN_CTRL_CURRENT_NETWORK BIT(3) +#define IAR_DUAL_PAN_CTRL_PANCORDNTR1 BIT(2) +#define IAR_DUAL_PAN_CTRL_DUAL_PAN_AUTO BIT(1) +#define IAR_DUAL_PAN_CTRL_ACTIVE_NETWORK BIT(0) + +/* DUAL_PAN_STS bits */ +#define IAR_DUAL_PAN_STS_RECD_ON_PAN1 BIT(7) +#define IAR_DUAL_PAN_STS_RECD_ON_PAN0 BIT(6) +#define IAR_DUAL_PAN_STS_DUAL_PAN_REMAIN (0x3F) + +/* CCA_CTRL bits */ +#define IAR_CCA_CTRL_AGC_FRZ_EN BIT(6) +#define IAR_CCA_CTRL_CONT_RSSI_EN BIT(5) +#define IAR_CCA_CTRL_LQI_RSSI_NOT_CORR BIT(4) +#define IAR_CCA_CTRL_CCA3_AND_NOT_OR BIT(3) +#define IAR_CCA_CTRL_POWER_COMP_EN_LQI BIT(2) +#define IAR_CCA_CTRL_POWER_COMP_EN_ED BIT(1) +#define IAR_CCA_CTRL_POWER_COMP_EN_CCA1 BIT(0) + +/* ANT_PAD_CTRL bits */ +#define IAR_ANT_PAD_CTRL_ANTX_POL (0x0F) +#define IAR_ANT_PAD_CTRL_ANTX_POL_SHIFT (4) +#define IAR_ANT_PAD_CTRL_ANTX_CTRLMODE BIT(3) +#define IAR_ANT_PAD_CTRL_ANTX_HZ BIT(2) +#define IAR_ANT_PAD_CTRL_ANTX_EN (3) + +/* MISC_PAD_CTRL bits */ +#define IAR_MISC_PAD_CTRL_MISO_HIZ_EN BIT(3) +#define IAR_MISC_PAD_CTRL_IRQ_B_OD BIT(2) +#define IAR_MISC_PAD_CTRL_NON_GPIO_DS BIT(1) +#define IAR_MISC_PAD_CTRL_ANTX_CURR (1) + +/* ANT_AGC_CTRL bits */ +#define IAR_ANT_AGC_CTRL_FAD_EN_SHIFT (0) +#define IAR_ANT_AGC_CTRL_FAD_EN_MASK (1) +#define IAR_ANT_AGC_CTRL_ANTX_SHIFT (1) +#define IAR_ANT_AGC_CTRL_ANTX_MASK BIT(AR_ANT_AGC_CTRL_ANTX_SHIFT) + +/* BSM_CTRL bits */ +#define BSM_CTRL_BSM_EN (1) + +/* SOFT_RESET bits */ +#define IAR_SOFT_RESET_SOG_RST BIT(7) +#define IAR_SOFT_RESET_REGS_RST BIT(4) +#define IAR_SOFT_RESET_PLL_RST BIT(3) +#define IAR_SOFT_RESET_TX_RST BIT(2) +#define IAR_SOFT_RESET_RX_RST BIT(1) +#define IAR_SOFT_RESET_SEQ_MGR_RST BIT(0) + +/* SEQ_MGR_CTRL bits */ +#define IAR_SEQ_MGR_CTRL_SEQ_STATE_CTRL (3) +#define IAR_SEQ_MGR_CTRL_SEQ_STATE_CTRL_SHIFT (6) +#define IAR_SEQ_MGR_CTRL_NO_RX_RECYCLE BIT(5) +#define IAR_SEQ_MGR_CTRL_LATCH_PREAMBLE BIT(4) +#define IAR_SEQ_MGR_CTRL_EVENT_TMR_DO_NOT_LATCH BIT(3) +#define IAR_SEQ_MGR_CTRL_CLR_NEW_SEQ_INHIBIT BIT(2) +#define IAR_SEQ_MGR_CTRL_PSM_LOCK_DIS BIT(1) +#define IAR_SEQ_MGR_CTRL_PLL_ABORT_OVRD BIT(0) + +/* SEQ_MGR_STS bits */ +#define IAR_SEQ_MGR_STS_TMR2_SEQ_TRIG_ARMED BIT(7) +#define IAR_SEQ_MGR_STS_RX_MODE BIT(6) +#define IAR_SEQ_MGR_STS_RX_TIMEOUT_PENDING BIT(5) +#define IAR_SEQ_MGR_STS_NEW_SEQ_INHIBIT BIT(4) +#define IAR_SEQ_MGR_STS_SEQ_IDLE BIT(3) +#define IAR_SEQ_MGR_STS_XCVSEQ_ACTUAL (7) + +/* ABORT_STS bits */ +#define IAR_ABORT_STS_PLL_ABORTED BIT(2) +#define IAR_ABORT_STS_TC3_ABORTED BIT(1) +#define IAR_ABORT_STS_SW_ABORTED BIT(0) + +/* IAR_FILTERFAIL_CODE2 bits */ +#define IAR_FILTERFAIL_CODE2_PAN_SEL BIT(7) +#define IAR_FILTERFAIL_CODE2_9_8 (3) + +/* PHY_STS bits */ +#define IAR_PHY_STS_PLL_UNLOCK BIT(7) +#define IAR_PHY_STS_PLL_LOCK_ERR BIT(6) +#define IAR_PHY_STS_PLL_LOCK BIT(5) +#define IAR_PHY_STS_CRCVALID BIT(3) +#define IAR_PHY_STS_FILTERFAIL_FLAG_SEL BIT(2) +#define IAR_PHY_STS_SFD_DET BIT(1) +#define IAR_PHY_STS_PREAMBLE_DET BIT(0) + +/* TESTMODE_CTRL bits */ +#define IAR_TEST_MODE_CTRL_HOT_ANT BIT(4) +#define IAR_TEST_MODE_CTRL_IDEAL_RSSI_EN BIT(3) +#define IAR_TEST_MODE_CTRL_IDEAL_PFC_EN BIT(2) +#define IAR_TEST_MODE_CTRL_CONTINUOUS_EN BIT(1) +#define IAR_TEST_MODE_CTRL_FPGA_EN BIT(0) + +/* DTM_CTRL1 bits */ +#define IAR_DTM_CTRL1_ATM_LOCKED BIT(7) +#define IAR_DTM_CTRL1_DTM_EN BIT(6) +#define IAR_DTM_CTRL1_PAGE5 BIT(5) +#define IAR_DTM_CTRL1_PAGE4 BIT(4) +#define IAR_DTM_CTRL1_PAGE3 BIT(3) +#define IAR_DTM_CTRL1_PAGE2 BIT(2) +#define IAR_DTM_CTRL1_PAGE1 BIT(1) +#define IAR_DTM_CTRL1_PAGE0 BIT(0) + +/* TX_MODE_CTRL */ +#define IAR_TX_MODE_CTRL_TX_INV BIT(4) +#define IAR_TX_MODE_CTRL_BT_EN BIT(3) +#define IAR_TX_MODE_CTRL_DTS2 BIT(2) +#define IAR_TX_MODE_CTRL_DTS1 BIT(1) +#define IAR_TX_MODE_CTRL_DTS0 BIT(0) + +#define TX_MODE_CTRL_DTS_MASK (7) + +#endif /* _MCR20A_H */ diff --git a/drivers/net/ipvlan/ipvlan.h b/drivers/net/ipvlan/ipvlan.h index 5166575a164d..a115f12bf130 100644 --- a/drivers/net/ipvlan/ipvlan.h +++ b/drivers/net/ipvlan/ipvlan.h @@ -74,6 +74,7 @@ struct ipvl_dev { DECLARE_BITMAP(mac_filters, IPVLAN_MAC_FILTER_SIZE); netdev_features_t sfeatures; u32 msg_enable; + spinlock_t addrs_lock; }; struct ipvl_addr { diff --git a/drivers/net/ipvlan/ipvlan_core.c b/drivers/net/ipvlan/ipvlan_core.c index c1f008fe4e1d..1a8132eb2a3e 100644 --- a/drivers/net/ipvlan/ipvlan_core.c +++ b/drivers/net/ipvlan/ipvlan_core.c @@ -35,6 +35,7 @@ void ipvlan_count_rx(const struct ipvl_dev *ipvlan, } EXPORT_SYMBOL_GPL(ipvlan_count_rx); +#if IS_ENABLED(CONFIG_IPV6) static u8 ipvlan_get_v6_hash(const void *iaddr) { const struct in6_addr *ip6_addr = iaddr; @@ -42,6 +43,12 @@ static u8 ipvlan_get_v6_hash(const void *iaddr) return __ipv6_addr_jhash(ip6_addr, ipvlan_jhash_secret) & IPVLAN_HASH_MASK; } +#else +static u8 ipvlan_get_v6_hash(const void *iaddr) +{ + return 0; +} +#endif static u8 ipvlan_get_v4_hash(const void *iaddr) { @@ -51,6 +58,23 @@ static u8 ipvlan_get_v4_hash(const void *iaddr) IPVLAN_HASH_MASK; } +static bool addr_equal(bool is_v6, struct ipvl_addr *addr, const void *iaddr) +{ + if (!is_v6 && addr->atype == IPVL_IPV4) { + struct in_addr *i4addr = (struct in_addr *)iaddr; + + return addr->ip4addr.s_addr == i4addr->s_addr; +#if IS_ENABLED(CONFIG_IPV6) + } else if (is_v6 && addr->atype == IPVL_IPV6) { + struct in6_addr *i6addr = (struct in6_addr *)iaddr; + + return ipv6_addr_equal(&addr->ip6addr, i6addr); +#endif + } + + return false; +} + static struct ipvl_addr *ipvlan_ht_addr_lookup(const struct ipvl_port *port, const void *iaddr, bool is_v6) { @@ -59,15 +83,9 @@ static struct ipvl_addr *ipvlan_ht_addr_lookup(const struct ipvl_port *port, hash = is_v6 ? ipvlan_get_v6_hash(iaddr) : ipvlan_get_v4_hash(iaddr); - hlist_for_each_entry_rcu(addr, &port->hlhead[hash], hlnode) { - if (is_v6 && addr->atype == IPVL_IPV6 && - ipv6_addr_equal(&addr->ip6addr, iaddr)) - return addr; - else if (!is_v6 && addr->atype == IPVL_IPV4 && - addr->ip4addr.s_addr == - ((struct in_addr *)iaddr)->s_addr) + hlist_for_each_entry_rcu(addr, &port->hlhead[hash], hlnode) + if (addr_equal(is_v6, addr, iaddr)) return addr; - } return NULL; } @@ -91,29 +109,33 @@ void ipvlan_ht_addr_del(struct ipvl_addr *addr) struct ipvl_addr *ipvlan_find_addr(const struct ipvl_dev *ipvlan, const void *iaddr, bool is_v6) { - struct ipvl_addr *addr; + struct ipvl_addr *addr, *ret = NULL; - list_for_each_entry(addr, &ipvlan->addrs, anode) { - if ((is_v6 && addr->atype == IPVL_IPV6 && - ipv6_addr_equal(&addr->ip6addr, iaddr)) || - (!is_v6 && addr->atype == IPVL_IPV4 && - addr->ip4addr.s_addr == ((struct in_addr *)iaddr)->s_addr)) - return addr; + rcu_read_lock(); + list_for_each_entry_rcu(addr, &ipvlan->addrs, anode) { + if (addr_equal(is_v6, addr, iaddr)) { + ret = addr; + break; + } } - return NULL; + rcu_read_unlock(); + return ret; } bool ipvlan_addr_busy(struct ipvl_port *port, void *iaddr, bool is_v6) { struct ipvl_dev *ipvlan; + bool ret = false; - ASSERT_RTNL(); - - list_for_each_entry(ipvlan, &port->ipvlans, pnode) { - if (ipvlan_find_addr(ipvlan, iaddr, is_v6)) - return true; + rcu_read_lock(); + list_for_each_entry_rcu(ipvlan, &port->ipvlans, pnode) { + if (ipvlan_find_addr(ipvlan, iaddr, is_v6)) { + ret = true; + break; + } } - return false; + rcu_read_unlock(); + return ret; } static void *ipvlan_get_L3_hdr(struct ipvl_port *port, struct sk_buff *skb, int *type) @@ -150,6 +172,7 @@ static void *ipvlan_get_L3_hdr(struct ipvl_port *port, struct sk_buff *skb, int lyr3h = ip4h; break; } +#if IS_ENABLED(CONFIG_IPV6) case htons(ETH_P_IPV6): { struct ipv6hdr *ip6h; @@ -188,6 +211,7 @@ static void *ipvlan_get_L3_hdr(struct ipvl_port *port, struct sk_buff *skb, int } break; } +#endif default: return NULL; } @@ -337,14 +361,18 @@ static struct ipvl_addr *ipvlan_addr_lookup(struct ipvl_port *port, { struct ipvl_addr *addr = NULL; - if (addr_type == IPVL_IPV6) { + switch (addr_type) { +#if IS_ENABLED(CONFIG_IPV6) + case IPVL_IPV6: { struct ipv6hdr *ip6h; struct in6_addr *i6addr; ip6h = (struct ipv6hdr *)lyr3h; i6addr = use_dest ? &ip6h->daddr : &ip6h->saddr; addr = ipvlan_ht_addr_lookup(port, i6addr, true); - } else if (addr_type == IPVL_ICMPV6) { + break; + } + case IPVL_ICMPV6: { struct nd_msg *ndmh; struct in6_addr *i6addr; @@ -356,14 +384,19 @@ static struct ipvl_addr *ipvlan_addr_lookup(struct ipvl_port *port, i6addr = &ndmh->target; addr = ipvlan_ht_addr_lookup(port, i6addr, true); } - } else if (addr_type == IPVL_IPV4) { + break; + } +#endif + case IPVL_IPV4: { struct iphdr *ip4h; __be32 *i4addr; ip4h = (struct iphdr *)lyr3h; i4addr = use_dest ? &ip4h->daddr : &ip4h->saddr; addr = ipvlan_ht_addr_lookup(port, i4addr, false); - } else if (addr_type == IPVL_ARP) { + break; + } + case IPVL_ARP: { struct arphdr *arph; unsigned char *arp_ptr; __be32 dip; @@ -377,6 +410,8 @@ static struct ipvl_addr *ipvlan_addr_lookup(struct ipvl_port *port, memcpy(&dip, arp_ptr, 4); addr = ipvlan_ht_addr_lookup(port, &dip, false); + break; + } } return addr; @@ -420,6 +455,7 @@ out: return ret; } +#if IS_ENABLED(CONFIG_IPV6) static int ipvlan_process_v6_outbound(struct sk_buff *skb) { const struct ipv6hdr *ip6h = ipv6_hdr(skb); @@ -456,6 +492,12 @@ err: out: return ret; } +#else +static int ipvlan_process_v6_outbound(struct sk_buff *skb) +{ + return NET_XMIT_DROP; +} +#endif static int ipvlan_process_outbound(struct sk_buff *skb) { @@ -464,8 +506,8 @@ static int ipvlan_process_outbound(struct sk_buff *skb) /* In this mode we dont care about multicast and broadcast traffic */ if (is_multicast_ether_addr(ethh->h_dest)) { - pr_warn_ratelimited("Dropped {multi|broad}cast of type= [%x]\n", - ntohs(skb->protocol)); + pr_debug_ratelimited("Dropped {multi|broad}cast of type=[%x]\n", + ntohs(skb->protocol)); kfree_skb(skb); goto out; } @@ -759,6 +801,7 @@ struct sk_buff *ipvlan_l3_rcv(struct net_device *dev, struct sk_buff *skb, goto out; break; } +#if IS_ENABLED(CONFIG_IPV6) case AF_INET6: { struct dst_entry *dst; @@ -774,10 +817,12 @@ struct sk_buff *ipvlan_l3_rcv(struct net_device *dev, struct sk_buff *skb, }; skb_dst_drop(skb); - dst = ip6_route_input_lookup(dev_net(sdev), sdev, &fl6, flags); + dst = ip6_route_input_lookup(dev_net(sdev), sdev, &fl6, + skb, flags); skb_dst_set(skb, dst); break; } +#endif default: break; } diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c index 2469df118fbf..4cbe9e27287d 100644 --- a/drivers/net/ipvlan/ipvlan_main.c +++ b/drivers/net/ipvlan/ipvlan_main.c @@ -22,12 +22,14 @@ static const struct nf_hook_ops ipvl_nfops[] = { .hooknum = NF_INET_LOCAL_IN, .priority = INT_MAX, }, +#if IS_ENABLED(CONFIG_IPV6) { .hook = ipvlan_nf_input, .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_IN, .priority = INT_MAX, }, +#endif }; static const struct l3mdev_ops ipvl_l3mdev_ops = { @@ -176,7 +178,7 @@ static int ipvlan_init(struct net_device *dev) dev->state = (dev->state & ~IPVLAN_STATE_MASK) | (phy_dev->state & IPVLAN_STATE_MASK); dev->features = phy_dev->features & IPVLAN_FEATURES; - dev->features |= NETIF_F_LLTX; + dev->features |= NETIF_F_LLTX | NETIF_F_VLAN_CHALLENGED; dev->gso_max_size = phy_dev->gso_max_size; dev->gso_max_segs = phy_dev->gso_max_segs; dev->hard_header_len = phy_dev->hard_header_len; @@ -225,8 +227,10 @@ static int ipvlan_open(struct net_device *dev) else dev->flags &= ~IFF_NOARP; - list_for_each_entry(addr, &ipvlan->addrs, anode) + rcu_read_lock(); + list_for_each_entry_rcu(addr, &ipvlan->addrs, anode) ipvlan_ht_addr_add(ipvlan, addr); + rcu_read_unlock(); return dev_uc_add(phy_dev, phy_dev->dev_addr); } @@ -242,8 +246,10 @@ static int ipvlan_stop(struct net_device *dev) dev_uc_del(phy_dev, phy_dev->dev_addr); - list_for_each_entry(addr, &ipvlan->addrs, anode) + rcu_read_lock(); + list_for_each_entry_rcu(addr, &ipvlan->addrs, anode) ipvlan_ht_addr_del(addr); + rcu_read_unlock(); return 0; } @@ -586,6 +592,7 @@ int ipvlan_link_new(struct net *src_net, struct net_device *dev, ipvlan->sfeatures = IPVLAN_FEATURES; ipvlan_adjust_mtu(ipvlan, phy_dev); INIT_LIST_HEAD(&ipvlan->addrs); + spin_lock_init(&ipvlan->addrs_lock); /* TODO Probably put random address here to be presented to the * world but keep using the physical-dev address for the outgoing @@ -663,11 +670,13 @@ void ipvlan_link_delete(struct net_device *dev, struct list_head *head) struct ipvl_dev *ipvlan = netdev_priv(dev); struct ipvl_addr *addr, *next; + spin_lock_bh(&ipvlan->addrs_lock); list_for_each_entry_safe(addr, next, &ipvlan->addrs, anode) { ipvlan_ht_addr_del(addr); - list_del(&addr->anode); + list_del_rcu(&addr->anode); kfree_rcu(addr, rcu); } + spin_unlock_bh(&ipvlan->addrs_lock); ida_simple_remove(&ipvlan->port->ida, dev->dev_id); list_del_rcu(&ipvlan->pnode); @@ -758,8 +767,7 @@ static int ipvlan_device_event(struct notifier_block *unused, if (dev->reg_state != NETREG_UNREGISTERING) break; - list_for_each_entry_safe(ipvlan, next, &port->ipvlans, - pnode) + list_for_each_entry_safe(ipvlan, next, &port->ipvlans, pnode) ipvlan->dev->rtnl_link_ops->dellink(ipvlan->dev, &lst_kill); unregister_netdevice_many(&lst_kill); @@ -791,6 +799,7 @@ static int ipvlan_device_event(struct notifier_block *unused, return NOTIFY_DONE; } +/* the caller must held the addrs lock */ static int ipvlan_add_addr(struct ipvl_dev *ipvlan, void *iaddr, bool is_v6) { struct ipvl_addr *addr; @@ -800,14 +809,17 @@ static int ipvlan_add_addr(struct ipvl_dev *ipvlan, void *iaddr, bool is_v6) return -ENOMEM; addr->master = ipvlan; - if (is_v6) { - memcpy(&addr->ip6addr, iaddr, sizeof(struct in6_addr)); - addr->atype = IPVL_IPV6; - } else { + if (!is_v6) { memcpy(&addr->ip4addr, iaddr, sizeof(struct in_addr)); addr->atype = IPVL_IPV4; +#if IS_ENABLED(CONFIG_IPV6) + } else { + memcpy(&addr->ip6addr, iaddr, sizeof(struct in6_addr)); + addr->atype = IPVL_IPV6; +#endif } - list_add_tail(&addr->anode, &ipvlan->addrs); + + list_add_tail_rcu(&addr->anode, &ipvlan->addrs); /* If the interface is not up, the address will be added to the hash * list by ipvlan_open. @@ -822,32 +834,17 @@ static void ipvlan_del_addr(struct ipvl_dev *ipvlan, void *iaddr, bool is_v6) { struct ipvl_addr *addr; + spin_lock_bh(&ipvlan->addrs_lock); addr = ipvlan_find_addr(ipvlan, iaddr, is_v6); - if (!addr) + if (!addr) { + spin_unlock_bh(&ipvlan->addrs_lock); return; + } ipvlan_ht_addr_del(addr); - list_del(&addr->anode); + list_del_rcu(&addr->anode); + spin_unlock_bh(&ipvlan->addrs_lock); kfree_rcu(addr, rcu); - - return; -} - -static int ipvlan_add_addr6(struct ipvl_dev *ipvlan, struct in6_addr *ip6_addr) -{ - if (ipvlan_addr_busy(ipvlan->port, ip6_addr, true)) { - netif_err(ipvlan, ifup, ipvlan->dev, - "Failed to add IPv6=%pI6c addr for %s intf\n", - ip6_addr, ipvlan->dev->name); - return -EINVAL; - } - - return ipvlan_add_addr(ipvlan, ip6_addr, true); -} - -static void ipvlan_del_addr6(struct ipvl_dev *ipvlan, struct in6_addr *ip6_addr) -{ - return ipvlan_del_addr(ipvlan, ip6_addr, true); } static bool ipvlan_is_valid_dev(const struct net_device *dev) @@ -863,6 +860,27 @@ static bool ipvlan_is_valid_dev(const struct net_device *dev) return true; } +#if IS_ENABLED(CONFIG_IPV6) +static int ipvlan_add_addr6(struct ipvl_dev *ipvlan, struct in6_addr *ip6_addr) +{ + int ret = -EINVAL; + + spin_lock_bh(&ipvlan->addrs_lock); + if (ipvlan_addr_busy(ipvlan->port, ip6_addr, true)) + netif_err(ipvlan, ifup, ipvlan->dev, + "Failed to add IPv6=%pI6c addr for %s intf\n", + ip6_addr, ipvlan->dev->name); + else + ret = ipvlan_add_addr(ipvlan, ip6_addr, true); + spin_unlock_bh(&ipvlan->addrs_lock); + return ret; +} + +static void ipvlan_del_addr6(struct ipvl_dev *ipvlan, struct in6_addr *ip6_addr) +{ + return ipvlan_del_addr(ipvlan, ip6_addr, true); +} + static int ipvlan_addr6_event(struct notifier_block *unused, unsigned long event, void *ptr) { @@ -894,10 +912,6 @@ static int ipvlan_addr6_validator_event(struct notifier_block *unused, struct net_device *dev = (struct net_device *)i6vi->i6vi_dev->dev; struct ipvl_dev *ipvlan = netdev_priv(dev); - /* FIXME IPv6 autoconf calls us from bh without RTNL */ - if (in_softirq()) - return NOTIFY_DONE; - if (!ipvlan_is_valid_dev(dev)) return NOTIFY_DONE; @@ -913,17 +927,21 @@ static int ipvlan_addr6_validator_event(struct notifier_block *unused, return NOTIFY_OK; } +#endif static int ipvlan_add_addr4(struct ipvl_dev *ipvlan, struct in_addr *ip4_addr) { - if (ipvlan_addr_busy(ipvlan->port, ip4_addr, false)) { + int ret = -EINVAL; + + spin_lock_bh(&ipvlan->addrs_lock); + if (ipvlan_addr_busy(ipvlan->port, ip4_addr, false)) netif_err(ipvlan, ifup, ipvlan->dev, "Failed to add IPv4=%pI4 on %s intf.\n", ip4_addr, ipvlan->dev->name); - return -EINVAL; - } - - return ipvlan_add_addr(ipvlan, ip4_addr, false); + else + ret = ipvlan_add_addr(ipvlan, ip4_addr, false); + spin_unlock_bh(&ipvlan->addrs_lock); + return ret; } static void ipvlan_del_addr4(struct ipvl_dev *ipvlan, struct in_addr *ip4_addr) @@ -993,6 +1011,7 @@ static struct notifier_block ipvlan_notifier_block __read_mostly = { .notifier_call = ipvlan_device_event, }; +#if IS_ENABLED(CONFIG_IPV6) static struct notifier_block ipvlan_addr6_notifier_block __read_mostly = { .notifier_call = ipvlan_addr6_event, }; @@ -1000,6 +1019,7 @@ static struct notifier_block ipvlan_addr6_notifier_block __read_mostly = { static struct notifier_block ipvlan_addr6_vtor_notifier_block __read_mostly = { .notifier_call = ipvlan_addr6_validator_event, }; +#endif static void ipvlan_ns_exit(struct net *net) { @@ -1016,6 +1036,7 @@ static struct pernet_operations ipvlan_net_ops = { .id = &ipvlan_netid, .size = sizeof(struct ipvlan_netns), .exit = ipvlan_ns_exit, + .async = true, }; static int __init ipvlan_init_module(void) @@ -1024,9 +1045,11 @@ static int __init ipvlan_init_module(void) ipvlan_init_secret(); register_netdevice_notifier(&ipvlan_notifier_block); +#if IS_ENABLED(CONFIG_IPV6) register_inet6addr_notifier(&ipvlan_addr6_notifier_block); register_inet6addr_validator_notifier( &ipvlan_addr6_vtor_notifier_block); +#endif register_inetaddr_notifier(&ipvlan_addr4_notifier_block); register_inetaddr_validator_notifier(&ipvlan_addr4_vtor_notifier_block); @@ -1045,9 +1068,11 @@ error: unregister_inetaddr_notifier(&ipvlan_addr4_notifier_block); unregister_inetaddr_validator_notifier( &ipvlan_addr4_vtor_notifier_block); +#if IS_ENABLED(CONFIG_IPV6) unregister_inet6addr_notifier(&ipvlan_addr6_notifier_block); unregister_inet6addr_validator_notifier( &ipvlan_addr6_vtor_notifier_block); +#endif unregister_netdevice_notifier(&ipvlan_notifier_block); return err; } @@ -1060,9 +1085,11 @@ static void __exit ipvlan_cleanup_module(void) unregister_inetaddr_notifier(&ipvlan_addr4_notifier_block); unregister_inetaddr_validator_notifier( &ipvlan_addr4_vtor_notifier_block); +#if IS_ENABLED(CONFIG_IPV6) unregister_inet6addr_notifier(&ipvlan_addr6_notifier_block); unregister_inet6addr_validator_notifier( &ipvlan_addr6_vtor_notifier_block); +#endif } module_init(ipvlan_init_module); diff --git a/drivers/net/loopback.c b/drivers/net/loopback.c index 30612497643c..b97a907ea5aa 100644 --- a/drivers/net/loopback.c +++ b/drivers/net/loopback.c @@ -230,4 +230,5 @@ out: /* Registered in net/core/dev.c */ struct pernet_operations __net_initdata loopback_net_ops = { .init = loopback_net_init, + .async = true, }; diff --git a/drivers/net/phy/aquantia.c b/drivers/net/phy/aquantia.c index e8ae50e1255e..319edc9c8ec7 100644 --- a/drivers/net/phy/aquantia.c +++ b/drivers/net/phy/aquantia.c @@ -38,14 +38,6 @@ static int aquantia_config_aneg(struct phy_device *phydev) return 0; } -static int aquantia_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 aquantia_config_intr(struct phy_device *phydev) { int err; @@ -125,7 +117,7 @@ static struct phy_driver aquantia_driver[] = { .name = "Aquantia AQ1202", .features = PHY_AQUANTIA_FEATURES, .flags = PHY_HAS_INTERRUPT, - .aneg_done = aquantia_aneg_done, + .aneg_done = genphy_c45_aneg_done, .config_aneg = aquantia_config_aneg, .config_intr = aquantia_config_intr, .ack_interrupt = aquantia_ack_interrupt, @@ -137,7 +129,7 @@ static struct phy_driver aquantia_driver[] = { .name = "Aquantia AQ2104", .features = PHY_AQUANTIA_FEATURES, .flags = PHY_HAS_INTERRUPT, - .aneg_done = aquantia_aneg_done, + .aneg_done = genphy_c45_aneg_done, .config_aneg = aquantia_config_aneg, .config_intr = aquantia_config_intr, .ack_interrupt = aquantia_ack_interrupt, @@ -149,7 +141,7 @@ static struct phy_driver aquantia_driver[] = { .name = "Aquantia AQR105", .features = PHY_AQUANTIA_FEATURES, .flags = PHY_HAS_INTERRUPT, - .aneg_done = aquantia_aneg_done, + .aneg_done = genphy_c45_aneg_done, .config_aneg = aquantia_config_aneg, .config_intr = aquantia_config_intr, .ack_interrupt = aquantia_ack_interrupt, @@ -161,7 +153,7 @@ static struct phy_driver aquantia_driver[] = { .name = "Aquantia AQR106", .features = PHY_AQUANTIA_FEATURES, .flags = PHY_HAS_INTERRUPT, - .aneg_done = aquantia_aneg_done, + .aneg_done = genphy_c45_aneg_done, .config_aneg = aquantia_config_aneg, .config_intr = aquantia_config_intr, .ack_interrupt = aquantia_ack_interrupt, @@ -173,7 +165,7 @@ static struct phy_driver aquantia_driver[] = { .name = "Aquantia AQR107", .features = PHY_AQUANTIA_FEATURES, .flags = PHY_HAS_INTERRUPT, - .aneg_done = aquantia_aneg_done, + .aneg_done = genphy_c45_aneg_done, .config_aneg = aquantia_config_aneg, .config_intr = aquantia_config_intr, .ack_interrupt = aquantia_ack_interrupt, @@ -185,7 +177,7 @@ static struct phy_driver aquantia_driver[] = { .name = "Aquantia AQR405", .features = PHY_AQUANTIA_FEATURES, .flags = PHY_HAS_INTERRUPT, - .aneg_done = aquantia_aneg_done, + .aneg_done = genphy_c45_aneg_done, .config_aneg = aquantia_config_aneg, .config_intr = aquantia_config_intr, .ack_interrupt = aquantia_ack_interrupt, diff --git a/drivers/net/phy/bcm7xxx.c b/drivers/net/phy/bcm7xxx.c index 421feb8f92fe..29b1c88b55cc 100644 --- a/drivers/net/phy/bcm7xxx.c +++ b/drivers/net/phy/bcm7xxx.c @@ -565,7 +565,7 @@ static int bcm7xxx_28nm_set_tunable(struct phy_device *phydev, if (ret) return ret; - /* Disable EEE advertisment since this prevents the PHY + /* Disable EEE advertisement since this prevents the PHY * from successfully linking up, trigger auto-negotiation restart * to let the MAC decide what to do. */ diff --git a/drivers/net/phy/cortina.c b/drivers/net/phy/cortina.c index 9442db221834..8022cd317f62 100644 --- a/drivers/net/phy/cortina.c +++ b/drivers/net/phy/cortina.c @@ -30,14 +30,6 @@ static int cortina_read_reg(struct phy_device *phydev, u16 regnum) MII_ADDR_C45 | regnum); } -static int cortina_config_aneg(struct phy_device *phydev) -{ - phydev->supported = SUPPORTED_10000baseT_Full; - phydev->advertising = SUPPORTED_10000baseT_Full; - - return 0; -} - static int cortina_read_status(struct phy_device *phydev) { int gpio_int_status, ret = 0; @@ -61,11 +53,6 @@ err: return ret; } -static int cortina_soft_reset(struct phy_device *phydev) -{ - return 0; -} - static int cortina_probe(struct phy_device *phydev) { u32 phy_id = 0; @@ -101,9 +88,10 @@ static struct phy_driver cortina_driver[] = { .phy_id = PHY_ID_CS4340, .phy_id_mask = 0xffffffff, .name = "Cortina CS4340", - .config_aneg = cortina_config_aneg, + .config_init = gen10g_config_init, + .config_aneg = gen10g_config_aneg, .read_status = cortina_read_status, - .soft_reset = cortina_soft_reset, + .soft_reset = gen10g_no_soft_reset, .probe = cortina_probe, }, }; diff --git a/drivers/net/phy/dp83867.c b/drivers/net/phy/dp83867.c index ab58224f897f..b3935778b19f 100644 --- a/drivers/net/phy/dp83867.c +++ b/drivers/net/phy/dp83867.c @@ -75,6 +75,8 @@ #define DP83867_IO_MUX_CFG_IO_IMPEDANCE_MAX 0x0 #define DP83867_IO_MUX_CFG_IO_IMPEDANCE_MIN 0x1f +#define DP83867_IO_MUX_CFG_CLK_O_SEL_MASK (0x1f << 8) +#define DP83867_IO_MUX_CFG_CLK_O_SEL_SHIFT 8 /* CFG4 bits */ #define DP83867_CFG4_PORT_MIRROR_EN BIT(0) @@ -92,6 +94,7 @@ struct dp83867_private { int io_impedance; int port_mirroring; bool rxctrl_strap_quirk; + int clk_output_sel; }; static int dp83867_ack_interrupt(struct phy_device *phydev) @@ -160,6 +163,14 @@ static int dp83867_of_init(struct phy_device *phydev) dp83867->io_impedance = -EINVAL; /* Optional configuration */ + ret = of_property_read_u32(of_node, "ti,clk-output-sel", + &dp83867->clk_output_sel); + if (ret || dp83867->clk_output_sel > DP83867_CLK_O_SEL_REF_CLK) + /* Keep the default value if ti,clk-output-sel is not set + * or too high + */ + dp83867->clk_output_sel = DP83867_CLK_O_SEL_REF_CLK; + if (of_property_read_bool(of_node, "ti,max-output-impedance")) dp83867->io_impedance = DP83867_IO_MUX_CFG_IO_IMPEDANCE_MAX; else if (of_property_read_bool(of_node, "ti,min-output-impedance")) @@ -295,6 +306,14 @@ static int dp83867_config_init(struct phy_device *phydev) if (dp83867->port_mirroring != DP83867_PORT_MIRROING_KEEP) dp83867_config_port_mirroring(phydev); + /* Clock output selection if muxing property is set */ + if (dp83867->clk_output_sel != DP83867_CLK_O_SEL_REF_CLK) { + val = phy_read_mmd(phydev, DP83867_DEVADDR, DP83867_IO_MUX_CFG); + val &= ~DP83867_IO_MUX_CFG_CLK_O_SEL_MASK; + val |= (dp83867->clk_output_sel << DP83867_IO_MUX_CFG_CLK_O_SEL_SHIFT); + phy_write_mmd(phydev, DP83867_DEVADDR, DP83867_IO_MUX_CFG, val); + } + return 0; } diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c index 22d9bc9c33a4..98fd6b7ceeec 100644 --- a/drivers/net/phy/marvell.c +++ b/drivers/net/phy/marvell.c @@ -860,7 +860,7 @@ static int m88e1510_config_init(struct phy_device *phydev) return err; /* There appears to be a bug in the 88e1512 when used in - * SGMII to copper mode, where the AN advertisment register + * SGMII to copper mode, where the AN advertisement register * clears the pause bits each time a negotiation occurs. * This means we can never be truely sure what was advertised, * so disable Pause support. diff --git a/drivers/net/phy/marvell10g.c b/drivers/net/phy/marvell10g.c index 8a0bd98fdec7..9564916d2d7b 100644 --- a/drivers/net/phy/marvell10g.c +++ b/drivers/net/phy/marvell10g.c @@ -71,15 +71,6 @@ static int mv3310_probe(struct phy_device *phydev) return 0; } -/* - * Resetting the MV88X3310 causes it to become non-responsive. Avoid - * setting the reset bit(s). - */ -static int mv3310_soft_reset(struct phy_device *phydev) -{ - return 0; -} - static int mv3310_config_init(struct phy_device *phydev) { __ETHTOOL_DECLARE_LINK_MODE_MASK(supported) = { 0, }; @@ -317,7 +308,7 @@ static int mv3310_read_status(struct phy_device *phydev) if (val < 0) return val; - /* Read the link partner's 1G advertisment */ + /* Read the link partner's 1G advertisement */ val = phy_read_mmd(phydev, MDIO_MMD_AN, MV_AN_STAT1000); if (val < 0) return val; @@ -377,7 +368,7 @@ static struct phy_driver mv3310_drivers[] = { SUPPORTED_10000baseT_Full | SUPPORTED_Backplane, .probe = mv3310_probe, - .soft_reset = mv3310_soft_reset, + .soft_reset = gen10g_no_soft_reset, .config_init = mv3310_config_init, .config_aneg = mv3310_config_aneg, .aneg_done = mv3310_aneg_done, diff --git a/drivers/net/phy/phy-c45.c b/drivers/net/phy/phy-c45.c index a4576859afae..e1225545362d 100644 --- a/drivers/net/phy/phy-c45.c +++ b/drivers/net/phy/phy-c45.c @@ -163,11 +163,11 @@ int genphy_c45_read_link(struct phy_device *phydev, u32 mmd_mask) EXPORT_SYMBOL_GPL(genphy_c45_read_link); /** - * genphy_c45_read_lpa - read the link partner advertisment and pause + * genphy_c45_read_lpa - read the link partner advertisement and pause * @phydev: target phy_device struct * * Read the Clause 45 defined base (7.19) and 10G (7.33) status registers, - * filling in the link partner advertisment, pause and asym_pause members + * filling in the link partner advertisement, pause and asym_pause members * in @phydev. This assumes that the auto-negotiation MMD is present, and * the backplane bit (7.48.0) is clear. Clause 45 PHY drivers are expected * to fill in the remainder of the link partner advert from vendor registers. @@ -176,7 +176,7 @@ int genphy_c45_read_lpa(struct phy_device *phydev) { int val; - /* Read the link partner's base page advertisment */ + /* Read the link partner's base page advertisement */ val = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_AN_LPA); if (val < 0) return val; @@ -185,7 +185,7 @@ int genphy_c45_read_lpa(struct phy_device *phydev) phydev->pause = val & LPA_PAUSE_CAP ? 1 : 0; phydev->asym_pause = val & LPA_PAUSE_ASYM ? 1 : 0; - /* Read the link partner's 10G advertisment */ + /* Read the link partner's 10G advertisement */ val = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_AN_10GBT_STAT); if (val < 0) return val; @@ -268,12 +268,13 @@ EXPORT_SYMBOL_GPL(genphy_c45_read_mdix); /* The gen10g_* functions are the old Clause 45 stub */ -static int gen10g_config_aneg(struct phy_device *phydev) +int gen10g_config_aneg(struct phy_device *phydev) { return 0; } +EXPORT_SYMBOL_GPL(gen10g_config_aneg); -static int gen10g_read_status(struct phy_device *phydev) +int gen10g_read_status(struct phy_device *phydev) { u32 mmd_mask = phydev->c45_ids.devices_in_package; int ret; @@ -291,14 +292,16 @@ static int gen10g_read_status(struct phy_device *phydev) return 0; } +EXPORT_SYMBOL_GPL(gen10g_read_status); -static int gen10g_soft_reset(struct phy_device *phydev) +int gen10g_no_soft_reset(struct phy_device *phydev) { /* Do nothing for now */ return 0; } +EXPORT_SYMBOL_GPL(gen10g_no_soft_reset); -static int gen10g_config_init(struct phy_device *phydev) +int gen10g_config_init(struct phy_device *phydev) { /* Temporarily just say we support everything */ phydev->supported = SUPPORTED_10000baseT_Full; @@ -306,22 +309,25 @@ static int gen10g_config_init(struct phy_device *phydev) return 0; } +EXPORT_SYMBOL_GPL(gen10g_config_init); -static int gen10g_suspend(struct phy_device *phydev) +int gen10g_suspend(struct phy_device *phydev) { return 0; } +EXPORT_SYMBOL_GPL(gen10g_suspend); -static int gen10g_resume(struct phy_device *phydev) +int gen10g_resume(struct phy_device *phydev) { return 0; } +EXPORT_SYMBOL_GPL(gen10g_resume); struct phy_driver genphy_10g_driver = { .phy_id = 0xffffffff, .phy_id_mask = 0xffffffff, .name = "Generic 10G PHY", - .soft_reset = gen10g_soft_reset, + .soft_reset = gen10g_no_soft_reset, .config_init = gen10g_config_init, .features = 0, .config_aneg = gen10g_config_aneg, diff --git a/drivers/net/phy/phy-core.c b/drivers/net/phy/phy-core.c index 4083f00c97a5..c7da4cbb1103 100644 --- a/drivers/net/phy/phy-core.c +++ b/drivers/net/phy/phy-core.c @@ -190,10 +190,10 @@ size_t phy_speeds(unsigned int *speeds, size_t size, } /** - * phy_resolve_aneg_linkmode - resolve the advertisments into phy settings + * phy_resolve_aneg_linkmode - resolve the advertisements into phy settings * @phydev: The phy_device struct * - * Resolve our and the link partner advertisments into their corresponding + * Resolve our and the link partner advertisements into their corresponding * speed and duplex. If full duplex was negotiated, extract the pause mode * from the link partner mask. */ diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index 6ac8b29b2dc3..51a011a349fe 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -364,7 +364,7 @@ static void phylink_get_fixed_state(struct phylink *pl, struct phylink_link_stat } /* Flow control is resolved according to our and the link partners - * advertisments using the following drawn from the 802.3 specs: + * advertisements using the following drawn from the 802.3 specs: * Local device Link partner * Pause AsymDir Pause AsymDir Result * 1 X 1 X TX+RX @@ -679,12 +679,11 @@ static int phylink_bringup_phy(struct phylink *pl, struct phy_device *phy) mutex_lock(&phy->lock); mutex_lock(&pl->state_mutex); - pl->netdev->phydev = phy; pl->phydev = phy; linkmode_copy(pl->supported, supported); linkmode_copy(pl->link_config.advertising, config.advertising); - /* Restrict the phy advertisment according to the MAC support. */ + /* Restrict the phy advertisement according to the MAC support. */ ethtool_convert_link_mode_to_legacy_u32(&advertising, config.advertising); phy->advertising = advertising; mutex_unlock(&pl->state_mutex); @@ -817,7 +816,6 @@ void phylink_disconnect_phy(struct phylink *pl) if (phy) { mutex_lock(&phy->lock); mutex_lock(&pl->state_mutex); - pl->netdev->phydev = NULL; pl->phydev = NULL; mutex_unlock(&pl->state_mutex); mutex_unlock(&phy->lock); @@ -889,7 +887,7 @@ void phylink_start(struct phylink *pl) /* Apply the link configuration to the MAC when starting. This allows * a fixed-link to start with the correct parameters, and also - * ensures that we set the appropriate advertisment for Serdes links. + * ensures that we set the appropriate advertisement for Serdes links. */ phylink_resolve_flow(pl, &pl->link_config); phylink_mac_config(pl, &pl->link_config); @@ -1076,7 +1074,7 @@ int phylink_ethtool_ksettings_set(struct phylink *pl, config = pl->link_config; - /* Mask out unsupported advertisments */ + /* Mask out unsupported advertisements */ linkmode_and(config.advertising, kset->link_modes.advertising, pl->supported); @@ -1121,7 +1119,7 @@ int phylink_ethtool_ksettings_set(struct phylink *pl, if (phylink_validate(pl, pl->supported, &config)) return -EINVAL; - /* If autonegotiation is enabled, we must have an advertisment */ + /* If autonegotiation is enabled, we must have an advertisement */ if (config.an_enabled && phylink_is_empty_linkmode(config.advertising)) return -EINVAL; @@ -1584,25 +1582,14 @@ static int phylink_sfp_module_insert(void *upstream, bool changed; u8 port; - sfp_parse_support(pl->sfp_bus, id, support); - port = sfp_parse_port(pl->sfp_bus, id, support); - iface = sfp_parse_interface(pl->sfp_bus, id); - ASSERT_RTNL(); - switch (iface) { - case PHY_INTERFACE_MODE_SGMII: - case PHY_INTERFACE_MODE_1000BASEX: - case PHY_INTERFACE_MODE_2500BASEX: - case PHY_INTERFACE_MODE_10GKR: - break; - default: - return -EINVAL; - } + sfp_parse_support(pl->sfp_bus, id, support); + port = sfp_parse_port(pl->sfp_bus, id, support); memset(&config, 0, sizeof(config)); linkmode_copy(config.advertising, support); - config.interface = iface; + config.interface = PHY_INTERFACE_MODE_NA; config.speed = SPEED_UNKNOWN; config.duplex = DUPLEX_UNKNOWN; config.pause = MLO_PAUSE_AN; @@ -1611,6 +1598,22 @@ static int phylink_sfp_module_insert(void *upstream, /* Ignore errors if we're expecting a PHY to attach later */ ret = phylink_validate(pl, support, &config); if (ret) { + netdev_err(pl->netdev, "validation with support %*pb failed: %d\n", + __ETHTOOL_LINK_MODE_MASK_NBITS, support, ret); + return ret; + } + + iface = sfp_select_interface(pl->sfp_bus, id, config.advertising); + if (iface == PHY_INTERFACE_MODE_NA) { + netdev_err(pl->netdev, + "selection of interface failed, advertisement %*pb\n", + __ETHTOOL_LINK_MODE_MASK_NBITS, config.advertising); + return -EINVAL; + } + + config.interface = iface; + ret = phylink_validate(pl, support, &config); + if (ret) { netdev_err(pl->netdev, "validation of %s/%s with support %*pb failed: %d\n", phylink_an_mode_str(MLO_AN_INBAND), phy_modes(config.interface), diff --git a/drivers/net/phy/sfp-bus.c b/drivers/net/phy/sfp-bus.c index 8961209ee949..3d4ff5d0d2a6 100644 --- a/drivers/net/phy/sfp-bus.c +++ b/drivers/net/phy/sfp-bus.c @@ -106,68 +106,6 @@ int sfp_parse_port(struct sfp_bus *bus, const struct sfp_eeprom_id *id, EXPORT_SYMBOL_GPL(sfp_parse_port); /** - * sfp_parse_interface() - Parse the phy_interface_t - * @bus: a pointer to the &struct sfp_bus structure for the sfp module - * @id: a pointer to the module's &struct sfp_eeprom_id - * - * Derive the phy_interface_t mode for the information found in the - * module's identifying EEPROM. There is no standard or defined way - * to derive this information, so we use some heuristics. - * - * If the encoding is 64b66b, then the module must be >= 10G, so - * return %PHY_INTERFACE_MODE_10GKR. - * - * If it's 8b10b, then it's 1G or slower. If it's definitely a fibre - * module, return %PHY_INTERFACE_MODE_1000BASEX mode, otherwise return - * %PHY_INTERFACE_MODE_SGMII mode. - * - * If the encoding is not known, return %PHY_INTERFACE_MODE_NA. - */ -phy_interface_t sfp_parse_interface(struct sfp_bus *bus, - const struct sfp_eeprom_id *id) -{ - phy_interface_t iface; - - /* Setting the serdes link mode is guesswork: there's no field in - * the EEPROM which indicates what mode should be used. - * - * If the module wants 64b66b, then it must be >= 10G. - * - * If it's a gigabit-only fiber module, it probably does not have - * a PHY, so switch to 802.3z negotiation mode. Otherwise, switch - * to SGMII mode (which is required to support non-gigabit speeds). - */ - switch (id->base.encoding) { - case SFP_ENCODING_8472_64B66B: - iface = PHY_INTERFACE_MODE_10GKR; - break; - - case SFP_ENCODING_8B10B: - if (!id->base.e1000_base_t && - !id->base.e100_base_lx && - !id->base.e100_base_fx) - iface = PHY_INTERFACE_MODE_1000BASEX; - else - iface = PHY_INTERFACE_MODE_SGMII; - break; - - default: - if (id->base.e1000_base_cx) { - iface = PHY_INTERFACE_MODE_1000BASEX; - break; - } - - iface = PHY_INTERFACE_MODE_NA; - dev_err(bus->sfp_dev, - "SFP module encoding does not support 8b10b nor 64b66b\n"); - break; - } - - return iface; -} -EXPORT_SYMBOL_GPL(sfp_parse_interface); - -/** * sfp_parse_support() - Parse the eeprom id for supported link modes * @bus: a pointer to the &struct sfp_bus structure for the sfp module * @id: a pointer to the module's &struct sfp_eeprom_id @@ -180,10 +118,7 @@ void sfp_parse_support(struct sfp_bus *bus, const struct sfp_eeprom_id *id, unsigned long *support) { unsigned int br_min, br_nom, br_max; - - phylink_set(support, Autoneg); - phylink_set(support, Pause); - phylink_set(support, Asym_Pause); + __ETHTOOL_DECLARE_LINK_MODE_MASK(modes) = { 0, }; /* Decode the bitrate information to MBd */ br_min = br_nom = br_max = 0; @@ -201,20 +136,20 @@ void sfp_parse_support(struct sfp_bus *bus, const struct sfp_eeprom_id *id, /* Set ethtool support from the compliance fields. */ if (id->base.e10g_base_sr) - phylink_set(support, 10000baseSR_Full); + phylink_set(modes, 10000baseSR_Full); if (id->base.e10g_base_lr) - phylink_set(support, 10000baseLR_Full); + phylink_set(modes, 10000baseLR_Full); if (id->base.e10g_base_lrm) - phylink_set(support, 10000baseLRM_Full); + phylink_set(modes, 10000baseLRM_Full); if (id->base.e10g_base_er) - phylink_set(support, 10000baseER_Full); + phylink_set(modes, 10000baseER_Full); if (id->base.e1000_base_sx || id->base.e1000_base_lx || id->base.e1000_base_cx) - phylink_set(support, 1000baseX_Full); + phylink_set(modes, 1000baseX_Full); if (id->base.e1000_base_t) { - phylink_set(support, 1000baseT_Half); - phylink_set(support, 1000baseT_Full); + phylink_set(modes, 1000baseT_Half); + phylink_set(modes, 1000baseT_Full); } /* 1000Base-PX or 1000Base-BX10 */ @@ -228,20 +163,20 @@ void sfp_parse_support(struct sfp_bus *bus, const struct sfp_eeprom_id *id, if ((id->base.sfp_ct_passive || id->base.sfp_ct_active) && br_nom) { /* This may look odd, but some manufacturers use 12000MBd */ if (br_min <= 12000 && br_max >= 10300) - phylink_set(support, 10000baseCR_Full); + phylink_set(modes, 10000baseCR_Full); if (br_min <= 3200 && br_max >= 3100) - phylink_set(support, 2500baseX_Full); + phylink_set(modes, 2500baseX_Full); if (br_min <= 1300 && br_max >= 1200) - phylink_set(support, 1000baseX_Full); + phylink_set(modes, 1000baseX_Full); } if (id->base.sfp_ct_passive) { if (id->base.passive.sff8431_app_e) - phylink_set(support, 10000baseCR_Full); + phylink_set(modes, 10000baseCR_Full); } if (id->base.sfp_ct_active) { if (id->base.active.sff8431_app_e || id->base.active.sff8431_lim) { - phylink_set(support, 10000baseCR_Full); + phylink_set(modes, 10000baseCR_Full); } } @@ -249,18 +184,18 @@ void sfp_parse_support(struct sfp_bus *bus, const struct sfp_eeprom_id *id, case 0x00: /* Unspecified */ break; case 0x02: /* 100Gbase-SR4 or 25Gbase-SR */ - phylink_set(support, 100000baseSR4_Full); - phylink_set(support, 25000baseSR_Full); + phylink_set(modes, 100000baseSR4_Full); + phylink_set(modes, 25000baseSR_Full); break; case 0x03: /* 100Gbase-LR4 or 25Gbase-LR */ case 0x04: /* 100Gbase-ER4 or 25Gbase-ER */ - phylink_set(support, 100000baseLR4_ER4_Full); + phylink_set(modes, 100000baseLR4_ER4_Full); break; case 0x0b: /* 100Gbase-CR4 or 25Gbase-CR CA-L */ case 0x0c: /* 25Gbase-CR CA-S */ case 0x0d: /* 25Gbase-CR CA-N */ - phylink_set(support, 100000baseCR4_Full); - phylink_set(support, 25000baseCR_Full); + phylink_set(modes, 100000baseCR4_Full); + phylink_set(modes, 25000baseCR_Full); break; default: dev_warn(bus->sfp_dev, @@ -274,13 +209,70 @@ void sfp_parse_support(struct sfp_bus *bus, const struct sfp_eeprom_id *id, id->base.fc_speed_200 || id->base.fc_speed_400) { if (id->base.br_nominal >= 31) - phylink_set(support, 2500baseX_Full); + phylink_set(modes, 2500baseX_Full); if (id->base.br_nominal >= 12) - phylink_set(support, 1000baseX_Full); + phylink_set(modes, 1000baseX_Full); } + + /* If we haven't discovered any modes that this module supports, try + * the encoding and bitrate to determine supported modes. Some BiDi + * modules (eg, 1310nm/1550nm) are not 1000BASE-BX compliant due to + * the differing wavelengths, so do not set any transceiver bits. + */ + if (bitmap_empty(modes, __ETHTOOL_LINK_MODE_MASK_NBITS)) { + /* If the encoding and bit rate allows 1000baseX */ + if (id->base.encoding == SFP_ENCODING_8B10B && br_nom && + br_min <= 1300 && br_max >= 1200) + phylink_set(modes, 1000baseX_Full); + } + + bitmap_or(support, support, modes, __ETHTOOL_LINK_MODE_MASK_NBITS); + + phylink_set(support, Autoneg); + phylink_set(support, Pause); + phylink_set(support, Asym_Pause); } EXPORT_SYMBOL_GPL(sfp_parse_support); +/** + * sfp_select_interface() - Select appropriate phy_interface_t mode + * @bus: a pointer to the &struct sfp_bus structure for the sfp module + * @id: a pointer to the module's &struct sfp_eeprom_id + * @link_modes: ethtool link modes mask + * + * Derive the phy_interface_t mode for the information found in the + * module's identifying EEPROM and the link modes mask. There is no + * standard or defined way to derive this information, so we decide + * based upon the link mode mask. + */ +phy_interface_t sfp_select_interface(struct sfp_bus *bus, + const struct sfp_eeprom_id *id, + unsigned long *link_modes) +{ + if (phylink_test(link_modes, 10000baseCR_Full) || + phylink_test(link_modes, 10000baseSR_Full) || + phylink_test(link_modes, 10000baseLR_Full) || + phylink_test(link_modes, 10000baseLRM_Full) || + phylink_test(link_modes, 10000baseER_Full)) + return PHY_INTERFACE_MODE_10GKR; + + if (phylink_test(link_modes, 2500baseX_Full)) + return PHY_INTERFACE_MODE_2500BASEX; + + if (id->base.e1000_base_t || + id->base.e100_base_lx || + id->base.e100_base_fx) + return PHY_INTERFACE_MODE_SGMII; + + if (phylink_test(link_modes, 1000baseX_Full)) + return PHY_INTERFACE_MODE_1000BASEX; + + dev_warn(bus->sfp_dev, "Unable to ascertain link mode\n"); + + return PHY_INTERFACE_MODE_NA; +} +EXPORT_SYMBOL_GPL(sfp_select_interface); + static LIST_HEAD(sfp_buses); static DEFINE_MUTEX(sfp_mutex); diff --git a/drivers/net/phy/sfp.c b/drivers/net/phy/sfp.c index 6c7d9289078d..83bf4959b043 100644 --- a/drivers/net/phy/sfp.c +++ b/drivers/net/phy/sfp.c @@ -42,6 +42,7 @@ enum { SFP_MOD_EMPTY = 0, SFP_MOD_PROBE, + SFP_MOD_HPOWER, SFP_MOD_PRESENT, SFP_MOD_ERROR, @@ -86,6 +87,7 @@ static const enum gpiod_flags gpio_flags[] = { * access the I2C EEPROM. However, Avago modules require 300ms. */ #define T_PROBE_INIT msecs_to_jiffies(300) +#define T_HPOWER_LEVEL msecs_to_jiffies(300) #define T_PROBE_RETRY msecs_to_jiffies(100) /* SFP modules appear to always have their PHY configured for bus address @@ -110,10 +112,12 @@ struct sfp { struct sfp_bus *sfp_bus; struct phy_device *mod_phy; const struct sff_data *type; + u32 max_power_mW; unsigned int (*get_state)(struct sfp *); void (*set_state)(struct sfp *, unsigned int); int (*read)(struct sfp *, bool, u8, void *, size_t); + int (*write)(struct sfp *, bool, u8, void *, size_t); struct gpio_desc *gpio[GPIO_MAX]; @@ -201,10 +205,11 @@ static void sfp_gpio_set_state(struct sfp *sfp, unsigned int state) } } -static int sfp__i2c_read(struct i2c_adapter *i2c, u8 bus_addr, u8 dev_addr, - void *buf, size_t len) +static int sfp_i2c_read(struct sfp *sfp, bool a2, u8 dev_addr, void *buf, + size_t len) { struct i2c_msg msgs[2]; + u8 bus_addr = a2 ? 0x51 : 0x50; int ret; msgs[0].addr = bus_addr; @@ -216,17 +221,38 @@ static int sfp__i2c_read(struct i2c_adapter *i2c, u8 bus_addr, u8 dev_addr, msgs[1].len = len; msgs[1].buf = buf; - ret = i2c_transfer(i2c, msgs, ARRAY_SIZE(msgs)); + ret = i2c_transfer(sfp->i2c, msgs, ARRAY_SIZE(msgs)); if (ret < 0) return ret; return ret == ARRAY_SIZE(msgs) ? len : 0; } -static int sfp_i2c_read(struct sfp *sfp, bool a2, u8 addr, void *buf, - size_t len) +static int sfp_i2c_write(struct sfp *sfp, bool a2, u8 dev_addr, void *buf, + size_t len) { - return sfp__i2c_read(sfp->i2c, a2 ? 0x51 : 0x50, addr, buf, len); + struct i2c_msg msgs[1]; + u8 bus_addr = a2 ? 0x51 : 0x50; + int ret; + + msgs[0].addr = bus_addr; + msgs[0].flags = 0; + msgs[0].len = 1 + len; + msgs[0].buf = kmalloc(1 + len, GFP_KERNEL); + if (!msgs[0].buf) + return -ENOMEM; + + msgs[0].buf[0] = dev_addr; + memcpy(&msgs[0].buf[1], buf, len); + + ret = i2c_transfer(sfp->i2c, msgs, ARRAY_SIZE(msgs)); + + kfree(msgs[0].buf); + + if (ret < 0) + return ret; + + return ret == ARRAY_SIZE(msgs) ? len : 0; } static int sfp_i2c_configure(struct sfp *sfp, struct i2c_adapter *i2c) @@ -239,6 +265,7 @@ static int sfp_i2c_configure(struct sfp *sfp, struct i2c_adapter *i2c) sfp->i2c = i2c; sfp->read = sfp_i2c_read; + sfp->write = sfp_i2c_write; i2c_mii = mdio_i2c_alloc(sfp->dev, i2c); if (IS_ERR(i2c_mii)) @@ -274,6 +301,11 @@ static int sfp_read(struct sfp *sfp, bool a2, u8 addr, void *buf, size_t len) return sfp->read(sfp, a2, addr, buf, len); } +static int sfp_write(struct sfp *sfp, bool a2, u8 addr, void *buf, size_t len) +{ + return sfp->write(sfp, a2, addr, buf, len); +} + static unsigned int sfp_check(void *buf, size_t len) { u8 *p, check; @@ -462,21 +494,83 @@ static void sfp_sm_mod_init(struct sfp *sfp) sfp_sm_probe_phy(sfp); } +static int sfp_sm_mod_hpower(struct sfp *sfp) +{ + u32 power; + u8 val; + int err; + + power = 1000; + if (sfp->id.ext.options & cpu_to_be16(SFP_OPTIONS_POWER_DECL)) + power = 1500; + if (sfp->id.ext.options & cpu_to_be16(SFP_OPTIONS_HIGH_POWER_LEVEL)) + power = 2000; + + if (sfp->id.ext.sff8472_compliance == SFP_SFF8472_COMPLIANCE_NONE && + (sfp->id.ext.diagmon & (SFP_DIAGMON_DDM | SFP_DIAGMON_ADDRMODE)) != + SFP_DIAGMON_DDM) { + /* The module appears not to implement bus address 0xa2, + * or requires an address change sequence, so assume that + * the module powers up in the indicated power mode. + */ + if (power > sfp->max_power_mW) { + dev_err(sfp->dev, + "Host does not support %u.%uW modules\n", + power / 1000, (power / 100) % 10); + return -EINVAL; + } + return 0; + } + + if (power > sfp->max_power_mW) { + dev_warn(sfp->dev, + "Host does not support %u.%uW modules, module left in power mode 1\n", + power / 1000, (power / 100) % 10); + return 0; + } + + if (power <= 1000) + return 0; + + err = sfp_read(sfp, true, SFP_EXT_STATUS, &val, sizeof(val)); + if (err != sizeof(val)) { + dev_err(sfp->dev, "Failed to read EEPROM: %d\n", err); + err = -EAGAIN; + goto err; + } + + val |= BIT(0); + + err = sfp_write(sfp, true, SFP_EXT_STATUS, &val, sizeof(val)); + if (err != sizeof(val)) { + dev_err(sfp->dev, "Failed to write EEPROM: %d\n", err); + err = -EAGAIN; + goto err; + } + + dev_info(sfp->dev, "Module switched to %u.%uW power level\n", + power / 1000, (power / 100) % 10); + return T_HPOWER_LEVEL; + +err: + return err; +} + static int sfp_sm_mod_probe(struct sfp *sfp) { /* SFP module inserted - read I2C data */ struct sfp_eeprom_id id; u8 check; - int err; + int ret; - err = sfp_read(sfp, false, 0, &id, sizeof(id)); - if (err < 0) { - dev_err(sfp->dev, "failed to read EEPROM: %d\n", err); + ret = sfp_read(sfp, false, 0, &id, sizeof(id)); + if (ret < 0) { + dev_err(sfp->dev, "failed to read EEPROM: %d\n", ret); return -EAGAIN; } - if (err != sizeof(id)) { - dev_err(sfp->dev, "EEPROM short read: %d\n", err); + if (ret != sizeof(id)) { + dev_err(sfp->dev, "EEPROM short read: %d\n", ret); return -EAGAIN; } @@ -521,7 +615,11 @@ static int sfp_sm_mod_probe(struct sfp *sfp) dev_warn(sfp->dev, "module address swap to access page 0xA2 is not supported.\n"); - return sfp_module_insert(sfp->sfp_bus, &sfp->id); + ret = sfp_module_insert(sfp->sfp_bus, &sfp->id); + if (ret < 0) + return ret; + + return sfp_sm_mod_hpower(sfp); } static void sfp_sm_mod_remove(struct sfp *sfp) @@ -560,17 +658,25 @@ static void sfp_sm_event(struct sfp *sfp, unsigned int event) if (event == SFP_E_REMOVE) { sfp_sm_ins_next(sfp, SFP_MOD_EMPTY, 0); } else if (event == SFP_E_TIMEOUT) { - int err = sfp_sm_mod_probe(sfp); + int val = sfp_sm_mod_probe(sfp); - if (err == 0) + if (val == 0) sfp_sm_ins_next(sfp, SFP_MOD_PRESENT, 0); - else if (err == -EAGAIN) - sfp_sm_set_timer(sfp, T_PROBE_RETRY); - else + else if (val > 0) + sfp_sm_ins_next(sfp, SFP_MOD_HPOWER, val); + else if (val != -EAGAIN) sfp_sm_ins_next(sfp, SFP_MOD_ERROR, 0); + else + sfp_sm_set_timer(sfp, T_PROBE_RETRY); } break; + case SFP_MOD_HPOWER: + if (event == SFP_E_TIMEOUT) { + sfp_sm_ins_next(sfp, SFP_MOD_PRESENT, 0); + break; + } + /* fallthrough */ case SFP_MOD_PRESENT: case SFP_MOD_ERROR: if (event == SFP_E_REMOVE) { @@ -889,6 +995,14 @@ static int sfp_probe(struct platform_device *pdev) if (!(sfp->gpio[GPIO_MODDEF0])) sfp->get_state = sff_gpio_get_state; + device_property_read_u32(&pdev->dev, "maximum-power-milliwatt", + &sfp->max_power_mW); + if (!sfp->max_power_mW) + sfp->max_power_mW = 1000; + + dev_info(sfp->dev, "Host maximum power %u.%uW\n", + sfp->max_power_mW / 1000, (sfp->max_power_mW / 100) % 10); + sfp->sfp_bus = sfp_register_socket(sfp->dev, sfp, &sfp_module_ops); if (!sfp->sfp_bus) return -ENOMEM; diff --git a/drivers/net/phy/teranetics.c b/drivers/net/phy/teranetics.c index fb2cef764e9a..22f3bdd8206c 100644 --- a/drivers/net/phy/teranetics.c +++ b/drivers/net/phy/teranetics.c @@ -34,39 +34,17 @@ MODULE_LICENSE("GPL v2"); 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; - /* auto negotiation state can only be checked when using copper * port, if using fiber port, just lie it's done. */ - if (!phy_read_mmd(phydev, MDIO_MMD_VEND1, 93)) { - reg = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_STAT1); - return (reg < 0) ? reg : (reg & BMSR_ANEGCOMPLETE); - } + if (!phy_read_mmd(phydev, MDIO_MMD_VEND1, 93)) + return genphy_c45_aneg_done(phydev); return 1; } -static int teranetics_config_aneg(struct phy_device *phydev) -{ - return 0; -} - static int teranetics_read_status(struct phy_device *phydev) { int reg; @@ -102,10 +80,10 @@ static struct phy_driver teranetics_driver[] = { .phy_id = PHY_ID_TN2020, .phy_id_mask = 0xffffffff, .name = "Teranetics TN2020", - .soft_reset = teranetics_soft_reset, + .soft_reset = gen10g_no_soft_reset, .aneg_done = teranetics_aneg_done, - .config_init = teranetics_config_init, - .config_aneg = teranetics_config_aneg, + .config_init = gen10g_config_init, + .config_aneg = gen10g_config_aneg, .read_status = teranetics_read_status, .match_phy_device = teranetics_match_phy_device, }, diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c index fa2a9bdd1866..7dc2f34e7229 100644 --- a/drivers/net/ppp/ppp_generic.c +++ b/drivers/net/ppp/ppp_generic.c @@ -971,6 +971,7 @@ static struct pernet_operations ppp_net_ops = { .exit = ppp_exit_net, .id = &ppp_net_id, .size = sizeof(struct ppp_net), + .async = true, }; static int ppp_unit_register(struct ppp *ppp, int unit, bool ifname_is_set) diff --git a/drivers/net/ppp/pppoe.c b/drivers/net/ppp/pppoe.c index 5aa59f41bf8c..c10e6181a2f0 100644 --- a/drivers/net/ppp/pppoe.c +++ b/drivers/net/ppp/pppoe.c @@ -714,7 +714,7 @@ err_put: } static int pppoe_getname(struct socket *sock, struct sockaddr *uaddr, - int *usockaddr_len, int peer) + int peer) { int len = sizeof(struct sockaddr_pppox); struct sockaddr_pppox sp; @@ -726,9 +726,7 @@ static int pppoe_getname(struct socket *sock, struct sockaddr *uaddr, memcpy(uaddr, &sp, len); - *usockaddr_len = len; - - return 0; + return len; } static int pppoe_ioctl(struct socket *sock, unsigned int cmd, @@ -1163,6 +1161,7 @@ static struct pernet_operations pppoe_net_ops = { .exit = pppoe_exit_net, .id = &pppoe_net_id, .size = sizeof(struct pppoe_net), + .async = true, }; static int __init pppoe_init(void) diff --git a/drivers/net/ppp/pptp.c b/drivers/net/ppp/pptp.c index 6dde9a0cfe76..8249d46a7844 100644 --- a/drivers/net/ppp/pptp.c +++ b/drivers/net/ppp/pptp.c @@ -483,7 +483,7 @@ static int pptp_connect(struct socket *sock, struct sockaddr *uservaddr, } static int pptp_getname(struct socket *sock, struct sockaddr *uaddr, - int *usockaddr_len, int peer) + int peer) { int len = sizeof(struct sockaddr_pppox); struct sockaddr_pppox sp; @@ -496,9 +496,7 @@ static int pptp_getname(struct socket *sock, struct sockaddr *uaddr, memcpy(uaddr, &sp, len); - *usockaddr_len = len; - - return 0; + return len; } static int pptp_release(struct socket *sock) diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index a468439969df..5dd781e65958 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -1105,14 +1105,15 @@ static void team_port_disable_netpoll(struct team_port *port) } #endif -static int team_upper_dev_link(struct team *team, struct team_port *port) +static int team_upper_dev_link(struct team *team, struct team_port *port, + struct netlink_ext_ack *extack) { struct netdev_lag_upper_info lag_upper_info; int err; lag_upper_info.tx_type = team->mode->lag_tx_type; err = netdev_master_upper_dev_link(port->dev, team->dev, NULL, - &lag_upper_info, NULL); + &lag_upper_info, extack); if (err) return err; port->dev->priv_flags |= IFF_TEAM_PORT; @@ -1129,7 +1130,8 @@ static void __team_port_change_port_added(struct team_port *port, bool linkup); static int team_dev_type_check_change(struct net_device *dev, struct net_device *port_dev); -static int team_port_add(struct team *team, struct net_device *port_dev) +static int team_port_add(struct team *team, struct net_device *port_dev, + struct netlink_ext_ack *extack) { struct net_device *dev = team->dev; struct team_port *port; @@ -1137,12 +1139,14 @@ static int team_port_add(struct team *team, struct net_device *port_dev) int err; if (port_dev->flags & IFF_LOOPBACK) { + NL_SET_ERR_MSG(extack, "Loopback device can't be added as a team port"); netdev_err(dev, "Device %s is loopback device. Loopback devices can't be added as a team port\n", portname); return -EINVAL; } if (team_port_exists(port_dev)) { + NL_SET_ERR_MSG(extack, "Device is already a port of a team device"); netdev_err(dev, "Device %s is already a port " "of a team device\n", portname); return -EBUSY; @@ -1150,6 +1154,7 @@ static int team_port_add(struct team *team, struct net_device *port_dev) if (port_dev->features & NETIF_F_VLAN_CHALLENGED && vlan_uses_dev(dev)) { + NL_SET_ERR_MSG(extack, "Device is VLAN challenged and team device has VLAN set up"); netdev_err(dev, "Device %s is VLAN challenged and team device has VLAN set up\n", portname); return -EPERM; @@ -1160,6 +1165,7 @@ static int team_port_add(struct team *team, struct net_device *port_dev) return err; if (port_dev->flags & IFF_UP) { + NL_SET_ERR_MSG(extack, "Device is up. Set it down before adding it as a team port"); netdev_err(dev, "Device %s is up. Set it down before adding it as a team port\n", portname); return -EBUSY; @@ -1227,7 +1233,7 @@ static int team_port_add(struct team *team, struct net_device *port_dev) goto err_handler_register; } - err = team_upper_dev_link(team, port); + err = team_upper_dev_link(team, port, extack); if (err) { netdev_err(dev, "Device %s failed to set upper link\n", portname); @@ -1921,7 +1927,7 @@ static int team_add_slave(struct net_device *dev, struct net_device *port_dev, int err; mutex_lock(&team->lock); - err = team_port_add(team, port_dev); + err = team_port_add(team, port_dev, extack); mutex_unlock(&team->lock); if (!err) diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 7433bb2e4451..475088f947bb 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -78,6 +78,7 @@ #include <linux/mutex.h> #include <linux/uaccess.h> +#include <linux/proc_fs.h> /* Uncomment to enable debugging */ /* #define TUN_DEBUG 1 */ @@ -2286,11 +2287,67 @@ static int tun_validate(struct nlattr *tb[], struct nlattr *data[], return -EINVAL; } +static size_t tun_get_size(const struct net_device *dev) +{ + BUILD_BUG_ON(sizeof(u32) != sizeof(uid_t)); + BUILD_BUG_ON(sizeof(u32) != sizeof(gid_t)); + + return nla_total_size(sizeof(uid_t)) + /* OWNER */ + nla_total_size(sizeof(gid_t)) + /* GROUP */ + nla_total_size(sizeof(u8)) + /* TYPE */ + nla_total_size(sizeof(u8)) + /* PI */ + nla_total_size(sizeof(u8)) + /* VNET_HDR */ + nla_total_size(sizeof(u8)) + /* PERSIST */ + nla_total_size(sizeof(u8)) + /* MULTI_QUEUE */ + nla_total_size(sizeof(u32)) + /* NUM_QUEUES */ + nla_total_size(sizeof(u32)) + /* NUM_DISABLED_QUEUES */ + 0; +} + +static int tun_fill_info(struct sk_buff *skb, const struct net_device *dev) +{ + struct tun_struct *tun = netdev_priv(dev); + + if (nla_put_u8(skb, IFLA_TUN_TYPE, tun->flags & TUN_TYPE_MASK)) + goto nla_put_failure; + if (uid_valid(tun->owner) && + nla_put_u32(skb, IFLA_TUN_OWNER, + from_kuid_munged(current_user_ns(), tun->owner))) + goto nla_put_failure; + if (gid_valid(tun->group) && + nla_put_u32(skb, IFLA_TUN_GROUP, + from_kgid_munged(current_user_ns(), tun->group))) + goto nla_put_failure; + if (nla_put_u8(skb, IFLA_TUN_PI, !(tun->flags & IFF_NO_PI))) + goto nla_put_failure; + if (nla_put_u8(skb, IFLA_TUN_VNET_HDR, !!(tun->flags & IFF_VNET_HDR))) + goto nla_put_failure; + if (nla_put_u8(skb, IFLA_TUN_PERSIST, !!(tun->flags & IFF_PERSIST))) + goto nla_put_failure; + if (nla_put_u8(skb, IFLA_TUN_MULTI_QUEUE, + !!(tun->flags & IFF_MULTI_QUEUE))) + goto nla_put_failure; + if (tun->flags & IFF_MULTI_QUEUE) { + if (nla_put_u32(skb, IFLA_TUN_NUM_QUEUES, tun->numqueues)) + goto nla_put_failure; + if (nla_put_u32(skb, IFLA_TUN_NUM_DISABLED_QUEUES, + tun->numdisabled)) + goto nla_put_failure; + } + + return 0; + +nla_put_failure: + return -EMSGSIZE; +} + static struct rtnl_link_ops tun_link_ops __read_mostly = { .kind = DRV_NAME, .priv_size = sizeof(struct tun_struct), .setup = tun_setup, .validate = tun_validate, + .get_size = tun_get_size, + .fill_info = tun_fill_info, }; static void tun_sock_write_space(struct sock *sk) @@ -2782,6 +2839,7 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd, struct tun_struct *tun; void __user* argp = (void __user*)arg; struct ifreq ifr; + struct net *net; kuid_t owner; kgid_t group; int sndbuf; @@ -2790,7 +2848,8 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd, int le; int ret; - if (cmd == TUNSETIFF || cmd == TUNSETQUEUE || _IOC_TYPE(cmd) == SOCK_IOC_TYPE) { + if (cmd == TUNSETIFF || cmd == TUNSETQUEUE || + (_IOC_TYPE(cmd) == SOCK_IOC_TYPE && cmd != SIOCGSKNS)) { if (copy_from_user(&ifr, argp, ifreq_len)) return -EFAULT; } else { @@ -2810,6 +2869,7 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd, rtnl_lock(); tun = tun_get(tfile); + net = sock_net(&tfile->sk); if (cmd == TUNSETIFF) { ret = -EEXIST; if (tun) @@ -2817,7 +2877,7 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd, ifr.ifr_name[IFNAMSIZ-1] = '\0'; - ret = tun_set_iff(sock_net(&tfile->sk), file, &ifr); + ret = tun_set_iff(net, file, &ifr); if (ret) goto unlock; @@ -2839,6 +2899,14 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd, tfile->ifindex = ifindex; goto unlock; } + if (cmd == SIOCGSKNS) { + ret = -EPERM; + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) + goto unlock; + + ret = open_related_ns(&net->ns, get_net_ns); + goto unlock; + } ret = -EBADFD; if (!tun) diff --git a/drivers/net/usb/kalmia.c b/drivers/net/usb/kalmia.c index ce0b0b4e3a57..1ec523b0e932 100644 --- a/drivers/net/usb/kalmia.c +++ b/drivers/net/usb/kalmia.c @@ -114,14 +114,14 @@ kalmia_init_and_get_ethernet_addr(struct usbnet *dev, u8 *ethernet_addr) return -ENOMEM; memcpy(usb_buf, init_msg_1, 12); - status = kalmia_send_init_packet(dev, usb_buf, sizeof(init_msg_1) - / sizeof(init_msg_1[0]), usb_buf, 24); + status = kalmia_send_init_packet(dev, usb_buf, ARRAY_SIZE(init_msg_1), + usb_buf, 24); if (status != 0) return status; memcpy(usb_buf, init_msg_2, 12); - status = kalmia_send_init_packet(dev, usb_buf, sizeof(init_msg_2) - / sizeof(init_msg_2[0]), usb_buf, 28); + status = kalmia_send_init_packet(dev, usb_buf, ARRAY_SIZE(init_msg_2), + usb_buf, 28); if (status != 0) return status; diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c index 139c61c8244a..c6be49d3a9eb 100644 --- a/drivers/net/vrf.c +++ b/drivers/net/vrf.c @@ -736,7 +736,6 @@ static int vrf_rtable_create(struct net_device *dev) return -ENOMEM; rth->dst.output = vrf_output; - rth->rt_table_id = vrf->tb_id; rcu_assign_pointer(vrf->rth, rth); @@ -942,6 +941,7 @@ static struct rt6_info *vrf_ip6_route_lookup(struct net *net, const struct net_device *dev, struct flowi6 *fl6, int ifindex, + const struct sk_buff *skb, int flags) { struct net_vrf *vrf = netdev_priv(dev); @@ -960,7 +960,7 @@ static struct rt6_info *vrf_ip6_route_lookup(struct net *net, if (!table) return NULL; - return ip6_pol_route(net, table, ifindex, fl6, flags); + return ip6_pol_route(net, table, ifindex, fl6, skb, flags); } static void vrf_ip6_input_dst(struct sk_buff *skb, struct net_device *vrf_dev, @@ -978,7 +978,7 @@ static void vrf_ip6_input_dst(struct sk_buff *skb, struct net_device *vrf_dev, struct net *net = dev_net(vrf_dev); struct rt6_info *rt6; - rt6 = vrf_ip6_route_lookup(net, vrf_dev, &fl6, ifindex, + rt6 = vrf_ip6_route_lookup(net, vrf_dev, &fl6, ifindex, skb, RT6_LOOKUP_F_HAS_SADDR | RT6_LOOKUP_F_IFACE); if (unlikely(!rt6)) return; @@ -1111,7 +1111,7 @@ static struct dst_entry *vrf_link_scope_lookup(const struct net_device *dev, if (!ipv6_addr_any(&fl6->saddr)) flags |= RT6_LOOKUP_F_HAS_SADDR; - rt = vrf_ip6_route_lookup(net, dev, fl6, fl6->flowi6_oif, flags); + rt = vrf_ip6_route_lookup(net, dev, fl6, fl6->flowi6_oif, NULL, flags); if (rt) dst = &rt->dst; @@ -1146,6 +1146,7 @@ static inline size_t vrf_fib_rule_nl_size(void) sz = NLMSG_ALIGN(sizeof(struct fib_rule_hdr)); sz += nla_total_size(sizeof(u8)); /* FRA_L3MDEV */ sz += nla_total_size(sizeof(u32)); /* FRA_PRIORITY */ + sz += nla_total_size(sizeof(u8)); /* FRA_PROTOCOL */ return sz; } @@ -1176,6 +1177,9 @@ static int vrf_fib_rule(const struct net_device *dev, __u8 family, bool add_it) frh->family = family; frh->action = FR_ACT_TO_TBL; + if (nla_put_u8(skb, FRA_PROTOCOL, RTPROT_KERNEL)) + goto nla_put_failure; + if (nla_put_u8(skb, FRA_L3MDEV, 1)) goto nla_put_failure; @@ -1431,6 +1435,7 @@ static struct pernet_operations vrf_net_ops __net_initdata = { .init = vrf_netns_init, .id = &vrf_net_id, .size = sizeof(bool), + .async = true, }; static int __init vrf_init_module(void) diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index fab7a4db249e..aa5f034d6ad1 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -3752,6 +3752,7 @@ static struct pernet_operations vxlan_net_ops = { .exit_batch = vxlan_exit_batch_net, .id = &vxlan_net_id, .size = sizeof(struct vxlan_net), + .async = true, }; static int __init vxlan_init_module(void) diff --git a/drivers/net/wireless/ath/wil6210/cfg80211.c b/drivers/net/wireless/ath/wil6210/cfg80211.c index 768f63f38341..b799a5384abb 100644 --- a/drivers/net/wireless/ath/wil6210/cfg80211.c +++ b/drivers/net/wireless/ath/wil6210/cfg80211.c @@ -1599,7 +1599,8 @@ static void wil_probe_client_handle(struct wil6210_priv *wil, */ bool alive = (sta->status == wil_sta_connected); - cfg80211_probe_status(ndev, sta->addr, req->cookie, alive, GFP_KERNEL); + cfg80211_probe_status(ndev, sta->addr, req->cookie, alive, + 0, false, GFP_KERNEL); } static struct list_head *next_probe_client(struct wil6210_priv *wil) diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c index 6e0af815f25e..7b6c3640a94f 100644 --- a/drivers/net/wireless/mac80211_hwsim.c +++ b/drivers/net/wireless/mac80211_hwsim.c @@ -253,7 +253,7 @@ static inline void hwsim_clear_chanctx_magic(struct ieee80211_chanctx_conf *c) static unsigned int hwsim_net_id; -static int hwsim_netgroup; +static struct ida hwsim_netgroup_ida = IDA_INIT; struct hwsim_net { int netgroup; @@ -267,11 +267,13 @@ static inline int hwsim_net_get_netgroup(struct net *net) return hwsim_net->netgroup; } -static inline void hwsim_net_set_netgroup(struct net *net) +static inline int hwsim_net_set_netgroup(struct net *net) { struct hwsim_net *hwsim_net = net_generic(net, hwsim_net_id); - hwsim_net->netgroup = hwsim_netgroup++; + hwsim_net->netgroup = ida_simple_get(&hwsim_netgroup_ida, + 0, 0, GFP_KERNEL); + return hwsim_net->netgroup >= 0 ? 0 : -ENOMEM; } static inline u32 hwsim_net_get_wmediumd(struct net *net) @@ -493,6 +495,7 @@ static LIST_HEAD(hwsim_radios); static struct workqueue_struct *hwsim_wq; static struct rhashtable hwsim_radios_rht; static int hwsim_radio_idx; +static int hwsim_radios_generation = 1; static struct platform_driver mac80211_hwsim_driver = { .driver = { @@ -637,6 +640,7 @@ static const struct nla_policy hwsim_genl_policy[HWSIM_ATTR_MAX + 1] = { [HWSIM_ATTR_RADIO_NAME] = { .type = NLA_STRING }, [HWSIM_ATTR_NO_VIF] = { .type = NLA_FLAG }, [HWSIM_ATTR_FREQ] = { .type = NLA_U32 }, + [HWSIM_ATTR_PERM_ADDR] = { .type = NLA_UNSPEC, .len = ETH_ALEN }, }; static void mac80211_hwsim_tx_frame(struct ieee80211_hw *hw, @@ -2408,6 +2412,7 @@ struct hwsim_new_radio_params { bool destroy_on_close; const char *hwname; bool no_vif; + const u8 *perm_addr; }; static void hwsim_mcast_config_msg(struct sk_buff *mcast_skb, @@ -2572,15 +2577,25 @@ static int mac80211_hwsim_new_radio(struct genl_info *info, skb_queue_head_init(&data->pending); SET_IEEE80211_DEV(hw, data->dev); - eth_zero_addr(addr); - addr[0] = 0x02; - addr[3] = idx >> 8; - addr[4] = idx; - memcpy(data->addresses[0].addr, addr, ETH_ALEN); - memcpy(data->addresses[1].addr, addr, ETH_ALEN); - data->addresses[1].addr[0] |= 0x40; - hw->wiphy->n_addresses = 2; - hw->wiphy->addresses = data->addresses; + if (!param->perm_addr) { + eth_zero_addr(addr); + addr[0] = 0x02; + addr[3] = idx >> 8; + addr[4] = idx; + memcpy(data->addresses[0].addr, addr, ETH_ALEN); + /* Why need here second address ? */ + data->addresses[1].addr[0] |= 0x40; + memcpy(data->addresses[1].addr, addr, ETH_ALEN); + hw->wiphy->n_addresses = 2; + hw->wiphy->addresses = data->addresses; + /* possible address clash is checked at hash table insertion */ + } else { + memcpy(data->addresses[0].addr, param->perm_addr, ETH_ALEN); + /* compatibility with automatically generated mac addr */ + memcpy(data->addresses[1].addr, param->perm_addr, ETH_ALEN); + hw->wiphy->n_addresses = 2; + hw->wiphy->addresses = data->addresses; + } data->channels = param->channels; data->use_chanctx = param->use_chanctx; @@ -2785,13 +2800,17 @@ static int mac80211_hwsim_new_radio(struct genl_info *info, err = rhashtable_insert_fast(&hwsim_radios_rht, &data->rht, hwsim_rht_params); if (err < 0) { - pr_debug("mac80211_hwsim: radio index %d already present\n", - idx); + if (info) { + GENL_SET_ERR_MSG(info, "perm addr already present"); + NL_SET_BAD_ATTR(info->extack, + info->attrs[HWSIM_ATTR_PERM_ADDR]); + } spin_unlock_bh(&hwsim_radio_lock); goto failed_final_insert; } list_add_tail(&data->list, &hwsim_radios); + hwsim_radios_generation++; spin_unlock_bh(&hwsim_radio_lock); if (idx > 0) @@ -3210,6 +3229,19 @@ static int hwsim_new_radio_nl(struct sk_buff *msg, struct genl_info *info) param.regd = hwsim_world_regdom_custom[idx]; } + if (info->attrs[HWSIM_ATTR_PERM_ADDR]) { + if (!is_valid_ether_addr( + nla_data(info->attrs[HWSIM_ATTR_PERM_ADDR]))) { + GENL_SET_ERR_MSG(info,"MAC is no valid source addr"); + NL_SET_BAD_ATTR(info->extack, + info->attrs[HWSIM_ATTR_PERM_ADDR]); + return -EINVAL; + } + + + param.perm_addr = nla_data(info->attrs[HWSIM_ATTR_PERM_ADDR]); + } + ret = mac80211_hwsim_new_radio(info, ¶m); kfree(hwname); return ret; @@ -3249,6 +3281,7 @@ static int hwsim_del_radio_nl(struct sk_buff *msg, struct genl_info *info) list_del(&data->list); rhashtable_remove_fast(&hwsim_radios_rht, &data->rht, hwsim_rht_params); + hwsim_radios_generation++; spin_unlock_bh(&hwsim_radio_lock); mac80211_hwsim_del_radio(data, wiphy_name(data->hw->wiphy), info); @@ -3305,17 +3338,19 @@ out_err: static int hwsim_dump_radio_nl(struct sk_buff *skb, struct netlink_callback *cb) { - int idx = cb->args[0]; + int last_idx = cb->args[0]; struct mac80211_hwsim_data *data = NULL; - int res; + int res = 0; + void *hdr; spin_lock_bh(&hwsim_radio_lock); + cb->seq = hwsim_radios_generation; - if (idx == hwsim_radio_idx) + if (last_idx >= hwsim_radio_idx-1) goto done; list_for_each_entry(data, &hwsim_radios, list) { - if (data->idx < idx) + if (data->idx <= last_idx) continue; if (!net_eq(wiphy_net(data->hw->wiphy), sock_net(skb->sk))) @@ -3328,14 +3363,25 @@ static int hwsim_dump_radio_nl(struct sk_buff *skb, if (res < 0) break; - idx = data->idx + 1; + last_idx = data->idx; } - cb->args[0] = idx; + cb->args[0] = last_idx; + + /* list changed, but no new element sent, set interrupted flag */ + if (skb->len == 0 && cb->prev_seq && cb->seq != cb->prev_seq) { + hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, &hwsim_genl_family, + NLM_F_MULTI, HWSIM_CMD_GET_RADIO); + if (!hdr) + res = -EMSGSIZE; + genl_dump_check_consistent(cb, hdr); + genlmsg_end(skb, hdr); + } done: spin_unlock_bh(&hwsim_radio_lock); - return skb->len; + return res ?: skb->len; } /* Generic Netlink operations array */ @@ -3393,6 +3439,7 @@ static void destroy_radio(struct work_struct *work) struct mac80211_hwsim_data *data = container_of(work, struct mac80211_hwsim_data, destroy_work); + hwsim_radios_generation++; mac80211_hwsim_del_radio(data, wiphy_name(data->hw->wiphy), NULL); } @@ -3462,9 +3509,7 @@ failure: static __net_init int hwsim_init_net(struct net *net) { - hwsim_net_set_netgroup(net); - - return 0; + return hwsim_net_set_netgroup(net); } static void __net_exit hwsim_exit_net(struct net *net) @@ -3487,6 +3532,8 @@ static void __net_exit hwsim_exit_net(struct net *net) queue_work(hwsim_wq, &data->destroy_work); } spin_unlock_bh(&hwsim_radio_lock); + + ida_simple_remove(&hwsim_netgroup_ida, hwsim_net_get_netgroup(net)); } static struct pernet_operations hwsim_net_ops = { @@ -3494,6 +3541,7 @@ static struct pernet_operations hwsim_net_ops = { .exit = hwsim_exit_net, .id = &hwsim_net_id, .size = sizeof(struct hwsim_net), + .async = true, }; static void hwsim_exit_netlink(void) diff --git a/drivers/net/wireless/mac80211_hwsim.h b/drivers/net/wireless/mac80211_hwsim.h index a96a79c1eff5..0fe3199f8c72 100644 --- a/drivers/net/wireless/mac80211_hwsim.h +++ b/drivers/net/wireless/mac80211_hwsim.h @@ -68,7 +68,12 @@ enum hwsim_tx_control_flags { * %HWSIM_ATTR_SIGNAL, %HWSIM_ATTR_COOKIE * @HWSIM_CMD_NEW_RADIO: create a new radio with the given parameters, * returns the radio ID (>= 0) or negative on errors, if successful - * then multicast the result + * then multicast the result, uses optional parameter: + * %HWSIM_ATTR_REG_STRICT_REG, %HWSIM_ATTR_SUPPORT_P2P_DEVICE, + * %HWSIM_ATTR_DESTROY_RADIO_ON_CLOSE, %HWSIM_ATTR_CHANNELS, + * %HWSIM_ATTR_NO_VIF, %HWSIM_ATTR_RADIO_NAME, %HWSIM_ATTR_USE_CHANCTX, + * %HWSIM_ATTR_REG_HINT_ALPHA2, %HWSIM_ATTR_REG_CUSTOM_REG, + * %HWSIM_ATTR_PERM_ADDR * @HWSIM_CMD_DEL_RADIO: destroy a radio, reply is multicasted * @HWSIM_CMD_GET_RADIO: fetch information about existing radios, uses: * %HWSIM_ATTR_RADIO_ID @@ -126,6 +131,7 @@ enum { * @HWSIM_ATTR_FREQ: Frequency at which packet is transmitted or received. * @HWSIM_ATTR_TX_INFO_FLAGS: additional flags for corresponding * rates of %HWSIM_ATTR_TX_INFO + * @HWSIM_ATTR_PERM_ADDR: permanent mac address of new radio * @__HWSIM_ATTR_MAX: enum limit */ @@ -153,6 +159,7 @@ enum { HWSIM_ATTR_FREQ, HWSIM_ATTR_PAD, HWSIM_ATTR_TX_INFO_FLAGS, + HWSIM_ATTR_PERM_ADDR, __HWSIM_ATTR_MAX, }; #define HWSIM_ATTR_MAX (__HWSIM_ATTR_MAX - 1) diff --git a/drivers/net/xen-netback/rx.c b/drivers/net/xen-netback/rx.c index b1cf7c6f407a..ef5887037b22 100644 --- a/drivers/net/xen-netback/rx.c +++ b/drivers/net/xen-netback/rx.c @@ -419,7 +419,7 @@ static void xenvif_rx_extra_slot(struct xenvif_queue *queue, BUG(); } -void xenvif_rx_skb(struct xenvif_queue *queue) +static void xenvif_rx_skb(struct xenvif_queue *queue) { struct xenvif_pkt_state pkt; diff --git a/drivers/scsi/iscsi_tcp.c b/drivers/scsi/iscsi_tcp.c index 6198559abbd8..0ad00dbf912d 100644 --- a/drivers/scsi/iscsi_tcp.c +++ b/drivers/scsi/iscsi_tcp.c @@ -732,7 +732,7 @@ static int iscsi_sw_tcp_conn_get_param(struct iscsi_cls_conn *cls_conn, struct iscsi_tcp_conn *tcp_conn = conn->dd_data; struct iscsi_sw_tcp_conn *tcp_sw_conn = tcp_conn->dd_data; struct sockaddr_in6 addr; - int rc, len; + int rc; switch(param) { case ISCSI_PARAM_CONN_PORT: @@ -745,12 +745,12 @@ static int iscsi_sw_tcp_conn_get_param(struct iscsi_cls_conn *cls_conn, } if (param == ISCSI_PARAM_LOCAL_PORT) rc = kernel_getsockname(tcp_sw_conn->sock, - (struct sockaddr *)&addr, &len); + (struct sockaddr *)&addr); else rc = kernel_getpeername(tcp_sw_conn->sock, - (struct sockaddr *)&addr, &len); + (struct sockaddr *)&addr); spin_unlock_bh(&conn->session->frwd_lock); - if (rc) + if (rc < 0) return rc; return iscsi_conn_get_addr_param((struct sockaddr_storage *) @@ -771,7 +771,7 @@ static int iscsi_sw_tcp_host_get_param(struct Scsi_Host *shost, struct iscsi_tcp_conn *tcp_conn; struct iscsi_sw_tcp_conn *tcp_sw_conn; struct sockaddr_in6 addr; - int rc, len; + int rc; switch (param) { case ISCSI_HOST_PARAM_IPADDRESS: @@ -793,9 +793,9 @@ static int iscsi_sw_tcp_host_get_param(struct Scsi_Host *shost, } rc = kernel_getsockname(tcp_sw_conn->sock, - (struct sockaddr *)&addr, &len); + (struct sockaddr *)&addr); spin_unlock_bh(&session->frwd_lock); - if (rc) + if (rc < 0) return rc; return iscsi_conn_get_addr_param((struct sockaddr_storage *) diff --git a/drivers/soc/qcom/qmi_interface.c b/drivers/soc/qcom/qmi_interface.c index 877611d5c42b..321982277697 100644 --- a/drivers/soc/qcom/qmi_interface.c +++ b/drivers/soc/qcom/qmi_interface.c @@ -586,7 +586,6 @@ static struct socket *qmi_sock_create(struct qmi_handle *qmi, struct sockaddr_qrtr *sq) { struct socket *sock; - int sl = sizeof(*sq); int ret; ret = sock_create_kern(&init_net, AF_QIPCRTR, SOCK_DGRAM, @@ -594,7 +593,7 @@ static struct socket *qmi_sock_create(struct qmi_handle *qmi, if (ret < 0) return ERR_PTR(ret); - ret = kernel_getsockname(sock, (struct sockaddr *)sq, &sl); + ret = kernel_getsockname(sock, (struct sockaddr *)sq); if (ret < 0) { sock_release(sock); return ERR_PTR(ret); diff --git a/drivers/staging/ipx/af_ipx.c b/drivers/staging/ipx/af_ipx.c index d21a9d128d3e..5703dd176787 100644 --- a/drivers/staging/ipx/af_ipx.c +++ b/drivers/staging/ipx/af_ipx.c @@ -1577,7 +1577,7 @@ out: static int ipx_getname(struct socket *sock, struct sockaddr *uaddr, - int *uaddr_len, int peer) + int peer) { struct ipx_address *addr; struct sockaddr_ipx sipx; @@ -1585,8 +1585,6 @@ static int ipx_getname(struct socket *sock, struct sockaddr *uaddr, struct ipx_sock *ipxs = ipx_sk(sk); int rc; - *uaddr_len = sizeof(struct sockaddr_ipx); - lock_sock(sk); if (peer) { rc = -ENOTCONN; @@ -1620,7 +1618,7 @@ static int ipx_getname(struct socket *sock, struct sockaddr *uaddr, sipx.sipx_zero = 0; memcpy(uaddr, &sipx, sizeof(sipx)); - rc = 0; + rc = sizeof(struct sockaddr_ipx); out: release_sock(sk); return rc; diff --git a/drivers/staging/irda/net/af_irda.c b/drivers/staging/irda/net/af_irda.c index 2f1e9ab3d6d0..c13553a9ee11 100644 --- a/drivers/staging/irda/net/af_irda.c +++ b/drivers/staging/irda/net/af_irda.c @@ -697,7 +697,7 @@ static int irda_discover_daddr_and_lsap_sel(struct irda_sock *self, char *name) * */ static int irda_getname(struct socket *sock, struct sockaddr *uaddr, - int *uaddr_len, int peer) + int peer) { struct sockaddr_irda saddr; struct sock *sk = sock->sk; @@ -720,11 +720,9 @@ static int irda_getname(struct socket *sock, struct sockaddr *uaddr, pr_debug("%s(), tsap_sel = %#x\n", __func__, saddr.sir_lsap_sel); pr_debug("%s(), addr = %08x\n", __func__, saddr.sir_addr); - /* uaddr_len come to us uninitialised */ - *uaddr_len = sizeof (struct sockaddr_irda); - memcpy(uaddr, &saddr, *uaddr_len); + memcpy(uaddr, &saddr, sizeof (struct sockaddr_irda)); - return 0; + return sizeof (struct sockaddr_irda); } /* diff --git a/drivers/staging/lustre/lnet/lnet/lib-socket.c b/drivers/staging/lustre/lnet/lnet/lib-socket.c index ce93806eefca..1bee667802b0 100644 --- a/drivers/staging/lustre/lnet/lnet/lib-socket.c +++ b/drivers/staging/lustre/lnet/lnet/lib-socket.c @@ -448,14 +448,13 @@ int lnet_sock_getaddr(struct socket *sock, bool remote, __u32 *ip, int *port) { struct sockaddr_in sin; - int len = sizeof(sin); int rc; if (remote) - rc = kernel_getpeername(sock, (struct sockaddr *)&sin, &len); + rc = kernel_getpeername(sock, (struct sockaddr *)&sin); else - rc = kernel_getsockname(sock, (struct sockaddr *)&sin, &len); - if (rc) { + rc = kernel_getsockname(sock, (struct sockaddr *)&sin); + if (rc < 0) { CERROR("Error %d getting sock %s IP/port\n", rc, remote ? "peer" : "local"); return rc; diff --git a/drivers/target/iscsi/iscsi_target_login.c b/drivers/target/iscsi/iscsi_target_login.c index 64c5a57b92e4..99501785cdc1 100644 --- a/drivers/target/iscsi/iscsi_target_login.c +++ b/drivers/target/iscsi/iscsi_target_login.c @@ -1020,7 +1020,7 @@ int iscsit_accept_np(struct iscsi_np *np, struct iscsi_conn *conn) struct socket *new_sock, *sock = np->np_socket; struct sockaddr_in sock_in; struct sockaddr_in6 sock_in6; - int rc, err; + int rc; rc = kernel_accept(sock, &new_sock, 0); if (rc < 0) @@ -1033,8 +1033,8 @@ int iscsit_accept_np(struct iscsi_np *np, struct iscsi_conn *conn) memset(&sock_in6, 0, sizeof(struct sockaddr_in6)); rc = conn->sock->ops->getname(conn->sock, - (struct sockaddr *)&sock_in6, &err, 1); - if (!rc) { + (struct sockaddr *)&sock_in6, 1); + if (rc >= 0) { if (!ipv6_addr_v4mapped(&sock_in6.sin6_addr)) { memcpy(&conn->login_sockaddr, &sock_in6, sizeof(sock_in6)); } else { @@ -1047,8 +1047,8 @@ int iscsit_accept_np(struct iscsi_np *np, struct iscsi_conn *conn) } rc = conn->sock->ops->getname(conn->sock, - (struct sockaddr *)&sock_in6, &err, 0); - if (!rc) { + (struct sockaddr *)&sock_in6, 0); + if (rc >= 0) { if (!ipv6_addr_v4mapped(&sock_in6.sin6_addr)) { memcpy(&conn->local_sockaddr, &sock_in6, sizeof(sock_in6)); } else { @@ -1063,13 +1063,13 @@ int iscsit_accept_np(struct iscsi_np *np, struct iscsi_conn *conn) memset(&sock_in, 0, sizeof(struct sockaddr_in)); rc = conn->sock->ops->getname(conn->sock, - (struct sockaddr *)&sock_in, &err, 1); - if (!rc) + (struct sockaddr *)&sock_in, 1); + if (rc >= 0) memcpy(&conn->login_sockaddr, &sock_in, sizeof(sock_in)); rc = conn->sock->ops->getname(conn->sock, - (struct sockaddr *)&sock_in, &err, 0); - if (!rc) + (struct sockaddr *)&sock_in, 0); + if (rc >= 0) memcpy(&conn->local_sockaddr, &sock_in, sizeof(sock_in)); } diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index 610cba276d47..b5fb56b822fd 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -1038,7 +1038,7 @@ static struct socket *get_raw_socket(int fd) struct sockaddr_ll sa; char buf[MAX_ADDR_LEN]; } uaddr; - int uaddr_len = sizeof uaddr, r; + int r; struct socket *sock = sockfd_lookup(fd, &r); if (!sock) @@ -1050,9 +1050,8 @@ static struct socket *get_raw_socket(int fd) goto err; } - r = sock->ops->getname(sock, (struct sockaddr *)&uaddr.sa, - &uaddr_len, 0); - if (r) + r = sock->ops->getname(sock, (struct sockaddr *)&uaddr.sa, 0); + if (r < 0) goto err; if (uaddr.sa.sll_family != AF_PACKET) { diff --git a/fs/dlm/lowcomms.c b/fs/dlm/lowcomms.c index cff79ea0c01d..5243989a60cc 100644 --- a/fs/dlm/lowcomms.c +++ b/fs/dlm/lowcomms.c @@ -482,7 +482,6 @@ static void lowcomms_error_report(struct sock *sk) { struct connection *con; struct sockaddr_storage saddr; - int buflen; void (*orig_report)(struct sock *) = NULL; read_lock_bh(&sk->sk_callback_lock); @@ -492,7 +491,7 @@ static void lowcomms_error_report(struct sock *sk) orig_report = listen_sock.sk_error_report; if (con->sock == NULL || - kernel_getpeername(con->sock, (struct sockaddr *)&saddr, &buflen)) { + kernel_getpeername(con->sock, (struct sockaddr *)&saddr) < 0) { printk_ratelimited(KERN_ERR "dlm: node %d: socket error " "sending to node %d, port %d, " "sk_err=%d/%d\n", dlm_our_nodeid(), @@ -757,8 +756,8 @@ static int tcp_accept_from_sock(struct connection *con) /* Get the connected socket's peer */ memset(&peeraddr, 0, sizeof(peeraddr)); - if (newsock->ops->getname(newsock, (struct sockaddr *)&peeraddr, - &len, 2)) { + len = newsock->ops->getname(newsock, (struct sockaddr *)&peeraddr, 2); + if (len < 0) { result = -ECONNABORTED; goto accept_err; } diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c index 9c36d614bf89..2dee4e03ff1c 100644 --- a/fs/lockd/svc.c +++ b/fs/lockd/svc.c @@ -709,6 +709,7 @@ static struct pernet_operations lockd_net_ops = { .exit = lockd_exit_net, .id = &lockd_net_id, .size = sizeof(struct lockd_net), + .async = true, }; diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 7d893543cf3b..6c3083c992e5 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -2122,6 +2122,7 @@ static struct pernet_operations nfs_net_ops = { .exit = nfs_net_exit, .id = &nfs_net_id, .size = sizeof(struct nfs_net), + .async = true, }; /* diff --git a/fs/nfs_common/grace.c b/fs/nfs_common/grace.c index 5be08f02a76b..8c743a405df6 100644 --- a/fs/nfs_common/grace.c +++ b/fs/nfs_common/grace.c @@ -118,6 +118,7 @@ static struct pernet_operations grace_net_ops = { .exit = grace_exit_net, .id = &grace_net_id, .size = sizeof(struct list_head), + .async = true, }; static int __init diff --git a/fs/nsfs.c b/fs/nsfs.c index 36b0772701a0..60702d677bd4 100644 --- a/fs/nsfs.c +++ b/fs/nsfs.c @@ -184,6 +184,7 @@ int open_related_ns(struct ns_common *ns, return fd; } +EXPORT_SYMBOL_GPL(open_related_ns); static long ns_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) diff --git a/fs/ocfs2/cluster/tcp.c b/fs/ocfs2/cluster/tcp.c index eac5140aac47..e5076185cc1e 100644 --- a/fs/ocfs2/cluster/tcp.c +++ b/fs/ocfs2/cluster/tcp.c @@ -1819,7 +1819,7 @@ int o2net_register_hb_callbacks(void) static int o2net_accept_one(struct socket *sock, int *more) { - int ret, slen; + int ret; struct sockaddr_in sin; struct socket *new_sock = NULL; struct o2nm_node *node = NULL; @@ -1864,9 +1864,7 @@ static int o2net_accept_one(struct socket *sock, int *more) goto out; } - slen = sizeof(sin); - ret = new_sock->ops->getname(new_sock, (struct sockaddr *) &sin, - &slen, 1); + ret = new_sock->ops->getname(new_sock, (struct sockaddr *) &sin, 1); if (ret < 0) goto out; diff --git a/fs/proc/proc_net.c b/fs/proc/proc_net.c index 68c06ae7888c..da6f8733c9c5 100644 --- a/fs/proc/proc_net.c +++ b/fs/proc/proc_net.c @@ -237,6 +237,7 @@ static __net_exit void proc_net_ns_exit(struct net *net) static struct pernet_operations __net_initdata proc_net_ns_ops = { .init = proc_net_ns_init, .exit = proc_net_ns_exit, + .async = true, }; int __init proc_net_init(void) diff --git a/include/dt-bindings/net/ti-dp83867.h b/include/dt-bindings/net/ti-dp83867.h index 172744a72eb7..7b1656427cbe 100644 --- a/include/dt-bindings/net/ti-dp83867.h +++ b/include/dt-bindings/net/ti-dp83867.h @@ -42,4 +42,18 @@ #define DP83867_RGMIIDCTL_3_75_NS 0xe #define DP83867_RGMIIDCTL_4_00_NS 0xf +/* IO_MUX_CFG - Clock output selection */ +#define DP83867_CLK_O_SEL_CHN_A_RCLK 0x0 +#define DP83867_CLK_O_SEL_CHN_B_RCLK 0x1 +#define DP83867_CLK_O_SEL_CHN_C_RCLK 0x2 +#define DP83867_CLK_O_SEL_CHN_D_RCLK 0x3 +#define DP83867_CLK_O_SEL_CHN_A_RCLK_DIV5 0x4 +#define DP83867_CLK_O_SEL_CHN_B_RCLK_DIV5 0x5 +#define DP83867_CLK_O_SEL_CHN_C_RCLK_DIV5 0x6 +#define DP83867_CLK_O_SEL_CHN_D_RCLK_DIV5 0x7 +#define DP83867_CLK_O_SEL_CHN_A_TCLK 0x8 +#define DP83867_CLK_O_SEL_CHN_B_TCLK 0x9 +#define DP83867_CLK_O_SEL_CHN_C_TCLK 0xA +#define DP83867_CLK_O_SEL_CHN_D_TCLK 0xB +#define DP83867_CLK_O_SEL_REF_CLK 0xC #endif diff --git a/include/linux/atalk.h b/include/linux/atalk.h index 4d356e168692..40373920ea58 100644 --- a/include/linux/atalk.h +++ b/include/linux/atalk.h @@ -113,10 +113,12 @@ extern void aarp_proto_init(void); /* Inter module exports */ /* Give a device find its atif control structure */ +#if IS_ENABLED(CONFIG_IRDA) || IS_ENABLED(CONFIG_ATALK) static inline struct atalk_iface *atalk_find_dev(struct net_device *dev) { return dev->atalk_ptr; } +#endif extern struct atalk_addr *atalk_find_dev_addr(struct net_device *dev); extern struct net_device *atrtr_get_dev(struct atalk_addr *sa); diff --git a/include/linux/avf/virtchnl.h b/include/linux/avf/virtchnl.h index 3ce61342fa31..b0a7f315bfbe 100644 --- a/include/linux/avf/virtchnl.h +++ b/include/linux/avf/virtchnl.h @@ -136,15 +136,21 @@ enum virtchnl_ops { VIRTCHNL_OP_ENABLE_VLAN_STRIPPING = 27, VIRTCHNL_OP_DISABLE_VLAN_STRIPPING = 28, VIRTCHNL_OP_REQUEST_QUEUES = 29, + VIRTCHNL_OP_ENABLE_CHANNELS = 30, + VIRTCHNL_OP_DISABLE_CHANNELS = 31, + VIRTCHNL_OP_ADD_CLOUD_FILTER = 32, + VIRTCHNL_OP_DEL_CLOUD_FILTER = 33, }; -/* This macro is used to generate a compilation error if a structure +/* These macros are used to generate compilation errors if a structure/union * is not exactly the correct length. It gives a divide by zero error if the - * structure is not of the correct size, otherwise it creates an enum that is - * never used. + * structure/union is not of the correct size, otherwise it creates an enum + * that is never used. */ #define VIRTCHNL_CHECK_STRUCT_LEN(n, X) enum virtchnl_static_assert_enum_##X \ { virtchnl_static_assert_##X = (n)/((sizeof(struct X) == (n)) ? 1 : 0) } +#define VIRTCHNL_CHECK_UNION_LEN(n, X) enum virtchnl_static_asset_enum_##X \ + { virtchnl_static_assert_##X = (n)/((sizeof(union X) == (n)) ? 1 : 0) } /* Virtual channel message descriptor. This overlays the admin queue * descriptor. All other data is passed in external buffers. @@ -244,6 +250,7 @@ VIRTCHNL_CHECK_STRUCT_LEN(16, virtchnl_vsi_resource); #define VIRTCHNL_VF_OFFLOAD_ENCAP 0X00100000 #define VIRTCHNL_VF_OFFLOAD_ENCAP_CSUM 0X00200000 #define VIRTCHNL_VF_OFFLOAD_RX_ENCAP_CSUM 0X00400000 +#define VIRTCHNL_VF_OFFLOAD_ADQ 0X00800000 #define VF_BASE_MODE_OFFLOADS (VIRTCHNL_VF_OFFLOAD_L2 | \ VIRTCHNL_VF_OFFLOAD_VLAN | \ @@ -496,6 +503,81 @@ struct virtchnl_rss_hena { VIRTCHNL_CHECK_STRUCT_LEN(8, virtchnl_rss_hena); +/* VIRTCHNL_OP_ENABLE_CHANNELS + * VIRTCHNL_OP_DISABLE_CHANNELS + * VF sends these messages to enable or disable channels based on + * the user specified queue count and queue offset for each traffic class. + * This struct encompasses all the information that the PF needs from + * VF to create a channel. + */ +struct virtchnl_channel_info { + u16 count; /* number of queues in a channel */ + u16 offset; /* queues in a channel start from 'offset' */ + u32 pad; + u64 max_tx_rate; +}; + +VIRTCHNL_CHECK_STRUCT_LEN(16, virtchnl_channel_info); + +struct virtchnl_tc_info { + u32 num_tc; + u32 pad; + struct virtchnl_channel_info list[1]; +}; + +VIRTCHNL_CHECK_STRUCT_LEN(24, virtchnl_tc_info); + +/* VIRTCHNL_ADD_CLOUD_FILTER + * VIRTCHNL_DEL_CLOUD_FILTER + * VF sends these messages to add or delete a cloud filter based on the + * user specified match and action filters. These structures encompass + * all the information that the PF needs from the VF to add/delete a + * cloud filter. + */ + +struct virtchnl_l4_spec { + u8 src_mac[ETH_ALEN]; + u8 dst_mac[ETH_ALEN]; + __be16 vlan_id; + __be16 pad; /* reserved for future use */ + __be32 src_ip[4]; + __be32 dst_ip[4]; + __be16 src_port; + __be16 dst_port; +}; + +VIRTCHNL_CHECK_STRUCT_LEN(52, virtchnl_l4_spec); + +union virtchnl_flow_spec { + struct virtchnl_l4_spec tcp_spec; + u8 buffer[128]; /* reserved for future use */ +}; + +VIRTCHNL_CHECK_UNION_LEN(128, virtchnl_flow_spec); + +enum virtchnl_action { + /* action types */ + VIRTCHNL_ACTION_DROP = 0, + VIRTCHNL_ACTION_TC_REDIRECT, +}; + +enum virtchnl_flow_type { + /* flow types */ + VIRTCHNL_TCP_V4_FLOW = 0, + VIRTCHNL_TCP_V6_FLOW, +}; + +struct virtchnl_filter { + union virtchnl_flow_spec data; + union virtchnl_flow_spec mask; + enum virtchnl_flow_type flow_type; + enum virtchnl_action action; + u32 action_meta; + __u8 field_flags; +}; + +VIRTCHNL_CHECK_STRUCT_LEN(272, virtchnl_filter); + /* VIRTCHNL_OP_EVENT * PF sends this message to inform the VF driver of events that may affect it. * No direct response is expected from the VF, though it may generate other @@ -711,6 +793,25 @@ virtchnl_vc_validate_vf_msg(struct virtchnl_version_info *ver, u32 v_opcode, case VIRTCHNL_OP_REQUEST_QUEUES: valid_len = sizeof(struct virtchnl_vf_res_request); break; + case VIRTCHNL_OP_ENABLE_CHANNELS: + valid_len = sizeof(struct virtchnl_tc_info); + if (msglen >= valid_len) { + struct virtchnl_tc_info *vti = + (struct virtchnl_tc_info *)msg; + valid_len += vti->num_tc * + sizeof(struct virtchnl_channel_info); + if (vti->num_tc == 0) + err_msg_format = true; + } + break; + case VIRTCHNL_OP_DISABLE_CHANNELS: + break; + case VIRTCHNL_OP_ADD_CLOUD_FILTER: + valid_len = sizeof(struct virtchnl_filter); + break; + case VIRTCHNL_OP_DEL_CLOUD_FILTER: + valid_len = sizeof(struct virtchnl_filter); + break; /* These are always errors coming from the VF. */ case VIRTCHNL_OP_EVENT: case VIRTCHNL_OP_UNKNOWN: diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index a7f16e0f8d68..8a4566691c8f 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -96,7 +96,7 @@ int __cgroup_bpf_check_dev_permission(short dev_type, u32 major, u32 minor, #define BPF_CGROUP_RUN_PROG_INET_SOCK(sk) \ ({ \ int __ret = 0; \ - if (cgroup_bpf_enabled && sk) { \ + if (cgroup_bpf_enabled) { \ __ret = __cgroup_bpf_run_filter_sk(sk, \ BPF_CGROUP_INET_SOCK_CREATE); \ } \ diff --git a/include/linux/filter.h b/include/linux/filter.h index 276932d75975..fdb691b520c0 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -20,7 +20,6 @@ #include <linux/set_memory.h> #include <linux/kallsyms.h> -#include <net/xdp.h> #include <net/sch_generic.h> #include <uapi/linux/filter.h> @@ -30,6 +29,7 @@ struct sk_buff; struct sock; struct seccomp_data; struct bpf_prog_aux; +struct xdp_rxq_info; /* ArgX, context and stack frame pointer register positions. Note, * Arg1, Arg2, Arg3, etc are used as argument mappings of function diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index ee6657a0ed69..8fe7e4306816 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -8,6 +8,7 @@ * Copyright (c) 2006, Michael Wu <flamingice@sourmilk.net> * Copyright (c) 2013 - 2014 Intel Mobile Communications GmbH * Copyright (c) 2016 - 2017 Intel Deutschland GmbH + * Copyright (c) 2018 Intel Corporation * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -2111,7 +2112,7 @@ enum ieee80211_key_len { #define FILS_ERP_MAX_REALM_LEN 253 #define FILS_ERP_MAX_RRK_LEN 64 -#define PMK_MAX_LEN 48 +#define PMK_MAX_LEN 64 /* Public action codes (IEEE Std 802.11-2016, 9.6.8.1, Table 9-307) */ enum ieee80211_pub_actioncode { @@ -2502,6 +2503,17 @@ static inline u8 *ieee80211_get_qos_ctl(struct ieee80211_hdr *hdr) } /** + * ieee80211_get_tid - get qos TID + * @hdr: the frame + */ +static inline u8 ieee80211_get_tid(struct ieee80211_hdr *hdr) +{ + u8 *qc = ieee80211_get_qos_ctl(hdr); + + return qc[0] & IEEE80211_QOS_CTL_TID_MASK; +} + +/** * ieee80211_get_SA - get pointer to SA * @hdr: the frame * diff --git a/include/linux/mlx5/cq.h b/include/linux/mlx5/cq.h index 48c181a2acc9..445ad194e0fe 100644 --- a/include/linux/mlx5/cq.h +++ b/include/linux/mlx5/cq.h @@ -60,6 +60,7 @@ struct mlx5_core_cq { } tasklet_ctx; int reset_notify_added; struct list_head reset_notify; + struct mlx5_eq *eq; }; @@ -171,8 +172,17 @@ static inline void mlx5_cq_arm(struct mlx5_core_cq *cq, u32 cmd, mlx5_write64(doorbell, uar_page + MLX5_CQ_DOORBELL, NULL); } -int mlx5_init_cq_table(struct mlx5_core_dev *dev); -void mlx5_cleanup_cq_table(struct mlx5_core_dev *dev); +static inline void mlx5_cq_hold(struct mlx5_core_cq *cq) +{ + refcount_inc(&cq->refcount); +} + +static inline void mlx5_cq_put(struct mlx5_core_cq *cq) +{ + if (refcount_dec_and_test(&cq->refcount)) + complete(&cq->free); +} + int mlx5_core_create_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq, u32 *in, int inlen); int mlx5_core_destroy_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq); diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 6ed79a8a8318..4814cad7456e 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -345,13 +345,6 @@ struct mlx5_buf_list { dma_addr_t map; }; -struct mlx5_buf { - struct mlx5_buf_list direct; - int npages; - int size; - u8 page_shift; -}; - struct mlx5_frag_buf { struct mlx5_buf_list *frags; int npages; @@ -359,6 +352,15 @@ struct mlx5_frag_buf { u8 page_shift; }; +struct mlx5_frag_buf_ctrl { + struct mlx5_frag_buf frag_buf; + u32 sz_m1; + u32 frag_sz_m1; + u8 log_sz; + u8 log_stride; + u8 log_frag_strides; +}; + struct mlx5_eq_tasklet { struct list_head list; struct list_head process_list; @@ -375,11 +377,18 @@ struct mlx5_eq_pagefault { mempool_t *pool; }; +struct mlx5_cq_table { + /* protect radix tree */ + spinlock_t lock; + struct radix_tree_root tree; +}; + struct mlx5_eq { struct mlx5_core_dev *dev; + struct mlx5_cq_table cq_table; __be32 __iomem *doorbell; u32 cons_index; - struct mlx5_buf buf; + struct mlx5_frag_buf buf; int size; unsigned int irqn; u8 eqn; @@ -526,13 +535,6 @@ struct mlx5_core_health { struct delayed_work recover_work; }; -struct mlx5_cq_table { - /* protect radix tree - */ - spinlock_t lock; - struct radix_tree_root tree; -}; - struct mlx5_qp_table { /* protect radix tree */ @@ -654,10 +656,6 @@ struct mlx5_priv { struct dentry *cmdif_debugfs; /* end: qp staff */ - /* start: cq staff */ - struct mlx5_cq_table cq_table; - /* end: cq staff */ - /* start: mkey staff */ struct mlx5_mkey_table mkey_table; /* end: mkey staff */ @@ -936,9 +934,9 @@ struct mlx5_hca_vport_context { bool grh_required; }; -static inline void *mlx5_buf_offset(struct mlx5_buf *buf, int offset) +static inline void *mlx5_buf_offset(struct mlx5_frag_buf *buf, int offset) { - return buf->direct.buf + offset; + return buf->frags->buf + offset; } #define STRUCT_FIELD(header, field) \ @@ -977,6 +975,25 @@ static inline u32 mlx5_base_mkey(const u32 key) return key & 0xffffff00u; } +static inline void mlx5_core_init_cq_frag_buf(struct mlx5_frag_buf_ctrl *fbc, + void *cqc) +{ + fbc->log_stride = 6 + MLX5_GET(cqc, cqc, cqe_sz); + fbc->log_sz = MLX5_GET(cqc, cqc, log_cq_size); + fbc->sz_m1 = (1 << fbc->log_sz) - 1; + fbc->log_frag_strides = PAGE_SHIFT - fbc->log_stride; + fbc->frag_sz_m1 = (1 << fbc->log_frag_strides) - 1; +} + +static inline void *mlx5_frag_buf_get_wqe(struct mlx5_frag_buf_ctrl *fbc, + u32 ix) +{ + unsigned int frag = (ix >> fbc->log_frag_strides); + + return fbc->frag_buf.frags[frag].buf + + ((fbc->frag_sz_m1 & ix) << fbc->log_stride); +} + int mlx5_cmd_init(struct mlx5_core_dev *dev); void mlx5_cmd_cleanup(struct mlx5_core_dev *dev); void mlx5_cmd_use_events(struct mlx5_core_dev *dev); @@ -1002,9 +1019,10 @@ void mlx5_drain_health_wq(struct mlx5_core_dev *dev); void mlx5_trigger_health_work(struct mlx5_core_dev *dev); void mlx5_drain_health_recovery(struct mlx5_core_dev *dev); int mlx5_buf_alloc_node(struct mlx5_core_dev *dev, int size, - struct mlx5_buf *buf, int node); -int mlx5_buf_alloc(struct mlx5_core_dev *dev, int size, struct mlx5_buf *buf); -void mlx5_buf_free(struct mlx5_core_dev *dev, struct mlx5_buf *buf); + struct mlx5_frag_buf *buf, int node); +int mlx5_buf_alloc(struct mlx5_core_dev *dev, + int size, struct mlx5_frag_buf *buf); +void mlx5_buf_free(struct mlx5_core_dev *dev, struct mlx5_frag_buf *buf); int mlx5_frag_buf_alloc_node(struct mlx5_core_dev *dev, int size, struct mlx5_frag_buf *buf, int node); void mlx5_frag_buf_free(struct mlx5_core_dev *dev, struct mlx5_frag_buf *buf); @@ -1049,22 +1067,12 @@ int mlx5_satisfy_startup_pages(struct mlx5_core_dev *dev, int boot); int mlx5_reclaim_startup_pages(struct mlx5_core_dev *dev); void mlx5_register_debugfs(void); void mlx5_unregister_debugfs(void); -int mlx5_eq_init(struct mlx5_core_dev *dev); -void mlx5_eq_cleanup(struct mlx5_core_dev *dev); -void mlx5_fill_page_array(struct mlx5_buf *buf, __be64 *pas); + +void mlx5_fill_page_array(struct mlx5_frag_buf *buf, __be64 *pas); void mlx5_fill_page_frag_array(struct mlx5_frag_buf *frag_buf, __be64 *pas); -void mlx5_cq_completion(struct mlx5_core_dev *dev, u32 cqn); void mlx5_rsc_event(struct mlx5_core_dev *dev, u32 rsn, int event_type); void mlx5_srq_event(struct mlx5_core_dev *dev, u32 srqn, int event_type); struct mlx5_core_srq *mlx5_core_get_srq(struct mlx5_core_dev *dev, u32 srqn); -void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, u64 vec, bool forced); -void mlx5_cq_event(struct mlx5_core_dev *dev, u32 cqn, int event_type); -int mlx5_create_map_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq, u8 vecidx, - int nent, u64 mask, const char *name, - enum mlx5_eq_type type); -int mlx5_destroy_unmap_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq); -int mlx5_start_eqs(struct mlx5_core_dev *dev); -void mlx5_stop_eqs(struct mlx5_core_dev *dev); int mlx5_vector2eqn(struct mlx5_core_dev *dev, int vector, int *eqn, unsigned int *irqn); int mlx5_core_attach_mcg(struct mlx5_core_dev *dev, union ib_gid *mgid, u32 qpn); @@ -1076,14 +1084,6 @@ int mlx5_core_access_reg(struct mlx5_core_dev *dev, void *data_in, int size_in, void *data_out, int size_out, u16 reg_num, int arg, int write); -int mlx5_debug_eq_add(struct mlx5_core_dev *dev, struct mlx5_eq *eq); -void mlx5_debug_eq_remove(struct mlx5_core_dev *dev, struct mlx5_eq *eq); -int mlx5_core_eq_query(struct mlx5_core_dev *dev, struct mlx5_eq *eq, - u32 *out, int outlen); -int mlx5_eq_debugfs_init(struct mlx5_core_dev *dev); -void mlx5_eq_debugfs_cleanup(struct mlx5_core_dev *dev); -int mlx5_cq_debugfs_init(struct mlx5_core_dev *dev); -void mlx5_cq_debugfs_cleanup(struct mlx5_core_dev *dev); int mlx5_db_alloc(struct mlx5_core_dev *dev, struct mlx5_db *db); int mlx5_db_alloc_node(struct mlx5_core_dev *dev, struct mlx5_db *db, int node); @@ -1224,6 +1224,12 @@ static inline int mlx5_core_is_pf(struct mlx5_core_dev *dev) return !(dev->priv.pci_dev_data & MLX5_PCI_DEV_IS_VF); } +#define MLX5_TOTAL_VPORTS(mdev) (1 + pci_sriov_get_totalvfs((mdev)->pdev)) +#define MLX5_VPORT_MANAGER(mdev) \ + (MLX5_CAP_GEN(mdev, vport_group_manager) && \ + (MLX5_CAP_GEN(mdev, port_type) == MLX5_CAP_PORT_TYPE_ETH) && \ + mlx5_core_is_pf(mdev)) + static inline int mlx5_get_gid_table_len(u16 param) { if (param > 4) { diff --git a/include/linux/mlx5/eswitch.h b/include/linux/mlx5/eswitch.h new file mode 100644 index 000000000000..d3c9db492b30 --- /dev/null +++ b/include/linux/mlx5/eswitch.h @@ -0,0 +1,58 @@ +/* SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause) */ +/* + * Copyright (c) 2018 Mellanox Technologies. All rights reserved. + */ + +#ifndef _MLX5_ESWITCH_ +#define _MLX5_ESWITCH_ + +#include <linux/mlx5/driver.h> + +enum { + SRIOV_NONE, + SRIOV_LEGACY, + SRIOV_OFFLOADS +}; + +enum { + REP_ETH, + REP_IB, + NUM_REP_TYPES, +}; + +struct mlx5_eswitch_rep; +struct mlx5_eswitch_rep_if { + int (*load)(struct mlx5_core_dev *dev, + struct mlx5_eswitch_rep *rep); + void (*unload)(struct mlx5_eswitch_rep *rep); + void *(*get_proto_dev)(struct mlx5_eswitch_rep *rep); + void *priv; + bool valid; +}; + +struct mlx5_eswitch_rep { + struct mlx5_eswitch_rep_if rep_if[NUM_REP_TYPES]; + u16 vport; + u8 hw_id[ETH_ALEN]; + u16 vlan; + u32 vlan_refcount; +}; + +void mlx5_eswitch_register_vport_rep(struct mlx5_eswitch *esw, + int vport_index, + struct mlx5_eswitch_rep_if *rep_if, + u8 rep_type); +void mlx5_eswitch_unregister_vport_rep(struct mlx5_eswitch *esw, + int vport_index, + u8 rep_type); +void *mlx5_eswitch_get_proto_dev(struct mlx5_eswitch *esw, + int vport, + u8 rep_type); +struct mlx5_eswitch_rep *mlx5_eswitch_vport_rep(struct mlx5_eswitch *esw, + int vport); +void *mlx5_eswitch_uplink_get_proto_dev(struct mlx5_eswitch *esw, u8 rep_type); +u8 mlx5_eswitch_mode(struct mlx5_eswitch *esw); +struct mlx5_flow_handle * +mlx5_eswitch_add_send_to_vport_rule(struct mlx5_eswitch *esw, + int vport, u32 sqn); +#endif diff --git a/include/linux/mroute.h b/include/linux/mroute.h index 5396521a776a..7ed82e4f11b3 100644 --- a/include/linux/mroute.h +++ b/include/linux/mroute.h @@ -4,11 +4,10 @@ #include <linux/in.h> #include <linux/pim.h> -#include <linux/rhashtable.h> -#include <net/sock.h> #include <net/fib_rules.h> #include <net/fib_notifier.h> #include <uapi/linux/mroute.h> +#include <linux/mroute_base.h> #ifdef CONFIG_IP_MROUTE static inline int ip_mroute_opt(int opt) @@ -56,18 +55,6 @@ static inline bool ipmr_rule_default(const struct fib_rule *rule) } #endif -struct vif_device { - struct net_device *dev; /* Device we are using */ - struct netdev_phys_item_id dev_parent_id; /* Device parent ID */ - unsigned long bytes_in,bytes_out; - unsigned long pkt_in,pkt_out; /* Statistics */ - unsigned long rate_limit; /* Traffic shaping (NI) */ - unsigned char threshold; /* TTL threshold */ - unsigned short flags; /* Control flags */ - __be32 local,remote; /* Addresses(remote for tunnels)*/ - int link; /* Physical interface index */ -}; - struct vif_entry_notifier_info { struct fib_notifier_info info; struct net_device *dev; @@ -78,34 +65,6 @@ struct vif_entry_notifier_info { #define VIFF_STATIC 0x8000 -#define VIF_EXISTS(_mrt, _idx) ((_mrt)->vif_table[_idx].dev != NULL) - -struct mr_table { - struct list_head list; - possible_net_t net; - u32 id; - struct sock __rcu *mroute_sk; - struct timer_list ipmr_expire_timer; - struct list_head mfc_unres_queue; - struct vif_device vif_table[MAXVIFS]; - struct rhltable mfc_hash; - struct list_head mfc_cache_list; - int maxvif; - atomic_t cache_resolve_queue_len; - bool mroute_do_assert; - bool mroute_do_pim; - int mroute_reg_vif_num; -}; - -/* mfc_flags: - * MFC_STATIC - the entry was added statically (not by a routing daemon) - * MFC_OFFLOAD - the entry was offloaded to the hardware - */ -enum { - MFC_STATIC = BIT(0), - MFC_OFFLOAD = BIT(1), -}; - struct mfc_cache_cmp_arg { __be32 mfc_mcastgrp; __be32 mfc_origin; @@ -113,28 +72,13 @@ struct mfc_cache_cmp_arg { /** * struct mfc_cache - multicast routing entries - * @mnode: rhashtable list + * @_c: Common multicast routing information; has to be first [for casting] * @mfc_mcastgrp: destination multicast group address * @mfc_origin: source address * @cmparg: used for rhashtable comparisons - * @mfc_parent: source interface (iif) - * @mfc_flags: entry flags - * @expires: unresolved entry expire time - * @unresolved: unresolved cached skbs - * @last_assert: time of last assert - * @minvif: minimum VIF id - * @maxvif: maximum VIF id - * @bytes: bytes that have passed for this entry - * @pkt: packets that have passed for this entry - * @wrong_if: number of wrong source interface hits - * @lastuse: time of last use of the group (traffic or update) - * @ttls: OIF TTL threshold array - * @refcount: reference count for this entry - * @list: global entry list - * @rcu: used for entry destruction */ struct mfc_cache { - struct rhlist_head mnode; + struct mr_mfc _c; union { struct { __be32 mfc_mcastgrp; @@ -142,28 +86,6 @@ struct mfc_cache { }; struct mfc_cache_cmp_arg cmparg; }; - vifi_t mfc_parent; - int mfc_flags; - - union { - struct { - unsigned long expires; - struct sk_buff_head unresolved; - } unres; - struct { - unsigned long last_assert; - int minvif; - int maxvif; - unsigned long bytes; - unsigned long pkt; - unsigned long wrong_if; - unsigned long lastuse; - unsigned char ttls[MAXVIFS]; - refcount_t refcount; - } res; - } mfc_un; - struct list_head list; - struct rcu_head rcu; }; struct mfc_entry_notifier_info { @@ -187,12 +109,12 @@ static inline void ipmr_cache_free(struct mfc_cache *mfc_cache) static inline void ipmr_cache_put(struct mfc_cache *c) { - if (refcount_dec_and_test(&c->mfc_un.res.refcount)) + if (refcount_dec_and_test(&c->_c.mfc_un.res.refcount)) ipmr_cache_free(c); } static inline void ipmr_cache_hold(struct mfc_cache *c) { - refcount_inc(&c->mfc_un.res.refcount); + refcount_inc(&c->_c.mfc_un.res.refcount); } #endif diff --git a/include/linux/mroute6.h b/include/linux/mroute6.h index 3014c52bfd86..1ac38e6819f5 100644 --- a/include/linux/mroute6.h +++ b/include/linux/mroute6.h @@ -7,6 +7,7 @@ #include <linux/skbuff.h> /* for struct sk_buff_head */ #include <net/net_namespace.h> #include <uapi/linux/mroute6.h> +#include <linux/mroute_base.h> #ifdef CONFIG_IPV6_MROUTE static inline int ip6_mroute_opt(int opt) @@ -62,57 +63,24 @@ static inline void ip6_mr_cleanup(void) } #endif -struct mif_device { - struct net_device *dev; /* Device we are using */ - unsigned long bytes_in,bytes_out; - unsigned long pkt_in,pkt_out; /* Statistics */ - unsigned long rate_limit; /* Traffic shaping (NI) */ - unsigned char threshold; /* TTL threshold */ - unsigned short flags; /* Control flags */ - int link; /* Physical interface index */ -}; - #define VIFF_STATIC 0x8000 -struct mfc6_cache { - struct list_head list; - struct in6_addr mf6c_mcastgrp; /* Group the entry belongs to */ - struct in6_addr mf6c_origin; /* Source of packet */ - mifi_t mf6c_parent; /* Source interface */ - int mfc_flags; /* Flags on line */ +struct mfc6_cache_cmp_arg { + struct in6_addr mf6c_mcastgrp; + struct in6_addr mf6c_origin; +}; +struct mfc6_cache { + struct mr_mfc _c; union { struct { - unsigned long expires; - struct sk_buff_head unresolved; /* Unresolved buffers */ - } unres; - struct { - unsigned long last_assert; - int minvif; - int maxvif; - unsigned long bytes; - unsigned long pkt; - unsigned long wrong_if; - unsigned long lastuse; - unsigned char ttls[MAXMIFS]; /* TTL thresholds */ - } res; - } mfc_un; + struct in6_addr mf6c_mcastgrp; + struct in6_addr mf6c_origin; + }; + struct mfc6_cache_cmp_arg cmparg; + }; }; -#define MFC_STATIC 1 -#define MFC_NOTIFY 2 - -#define MFC6_LINES 64 - -#define MFC6_HASH(a, g) (((__force u32)(a)->s6_addr32[0] ^ \ - (__force u32)(a)->s6_addr32[1] ^ \ - (__force u32)(a)->s6_addr32[2] ^ \ - (__force u32)(a)->s6_addr32[3] ^ \ - (__force u32)(g)->s6_addr32[0] ^ \ - (__force u32)(g)->s6_addr32[1] ^ \ - (__force u32)(g)->s6_addr32[2] ^ \ - (__force u32)(g)->s6_addr32[3]) % MFC6_LINES) - #define MFC_ASSERT_THRESH (3*HZ) /* Maximal freq. of asserts */ struct rtmsg; @@ -120,12 +88,12 @@ extern int ip6mr_get_route(struct net *net, struct sk_buff *skb, struct rtmsg *rtm, u32 portid); #ifdef CONFIG_IPV6_MROUTE -extern struct sock *mroute6_socket(struct net *net, struct sk_buff *skb); +bool mroute6_is_socket(struct net *net, struct sk_buff *skb); extern int ip6mr_sk_done(struct sock *sk); #else -static inline struct sock *mroute6_socket(struct net *net, struct sk_buff *skb) +static inline bool mroute6_is_socket(struct net *net, struct sk_buff *skb) { - return NULL; + return false; } static inline int ip6mr_sk_done(struct sock *sk) { diff --git a/include/linux/mroute_base.h b/include/linux/mroute_base.h new file mode 100644 index 000000000000..c2560cb50f1d --- /dev/null +++ b/include/linux/mroute_base.h @@ -0,0 +1,346 @@ +#ifndef __LINUX_MROUTE_BASE_H +#define __LINUX_MROUTE_BASE_H + +#include <linux/netdevice.h> +#include <linux/rhashtable.h> +#include <linux/spinlock.h> +#include <net/net_namespace.h> +#include <net/sock.h> + +/** + * struct vif_device - interface representor for multicast routing + * @dev: network device being used + * @bytes_in: statistic; bytes ingressing + * @bytes_out: statistic; bytes egresing + * @pkt_in: statistic; packets ingressing + * @pkt_out: statistic; packets egressing + * @rate_limit: Traffic shaping (NI) + * @threshold: TTL threshold + * @flags: Control flags + * @link: Physical interface index + * @dev_parent_id: device parent id + * @local: Local address + * @remote: Remote address for tunnels + */ +struct vif_device { + struct net_device *dev; + unsigned long bytes_in, bytes_out; + unsigned long pkt_in, pkt_out; + unsigned long rate_limit; + unsigned char threshold; + unsigned short flags; + int link; + + /* Currently only used by ipmr */ + struct netdev_phys_item_id dev_parent_id; + __be32 local, remote; +}; + +#ifndef MAXVIFS +/* This one is nasty; value is defined in uapi using different symbols for + * mroute and morute6 but both map into same 32. + */ +#define MAXVIFS 32 +#endif + +#define VIF_EXISTS(_mrt, _idx) (!!((_mrt)->vif_table[_idx].dev)) + +/* mfc_flags: + * MFC_STATIC - the entry was added statically (not by a routing daemon) + * MFC_OFFLOAD - the entry was offloaded to the hardware + */ +enum { + MFC_STATIC = BIT(0), + MFC_OFFLOAD = BIT(1), +}; + +/** + * struct mr_mfc - common multicast routing entries + * @mnode: rhashtable list + * @mfc_parent: source interface (iif) + * @mfc_flags: entry flags + * @expires: unresolved entry expire time + * @unresolved: unresolved cached skbs + * @last_assert: time of last assert + * @minvif: minimum VIF id + * @maxvif: maximum VIF id + * @bytes: bytes that have passed for this entry + * @pkt: packets that have passed for this entry + * @wrong_if: number of wrong source interface hits + * @lastuse: time of last use of the group (traffic or update) + * @ttls: OIF TTL threshold array + * @refcount: reference count for this entry + * @list: global entry list + * @rcu: used for entry destruction + */ +struct mr_mfc { + struct rhlist_head mnode; + unsigned short mfc_parent; + int mfc_flags; + + union { + struct { + unsigned long expires; + struct sk_buff_head unresolved; + } unres; + struct { + unsigned long last_assert; + int minvif; + int maxvif; + unsigned long bytes; + unsigned long pkt; + unsigned long wrong_if; + unsigned long lastuse; + unsigned char ttls[MAXVIFS]; + refcount_t refcount; + } res; + } mfc_un; + struct list_head list; + struct rcu_head rcu; +}; + +struct mr_table; + +/** + * struct mr_table_ops - callbacks and info for protocol-specific ops + * @rht_params: parameters for accessing the MFC hash + * @cmparg_any: a hash key to be used for matching on (*,*) routes + */ +struct mr_table_ops { + const struct rhashtable_params *rht_params; + void *cmparg_any; +}; + +/** + * struct mr_table - a multicast routing table + * @list: entry within a list of multicast routing tables + * @net: net where this table belongs + * @ops: protocol specific operations + * @id: identifier of the table + * @mroute_sk: socket associated with the table + * @ipmr_expire_timer: timer for handling unresolved routes + * @mfc_unres_queue: list of unresolved MFC entries + * @vif_table: array containing all possible vifs + * @mfc_hash: Hash table of all resolved routes for easy lookup + * @mfc_cache_list: list of resovled routes for possible traversal + * @maxvif: Identifier of highest value vif currently in use + * @cache_resolve_queue_len: current size of unresolved queue + * @mroute_do_assert: Whether to inform userspace on wrong ingress + * @mroute_do_pim: Whether to receive IGMP PIMv1 + * @mroute_reg_vif_num: PIM-device vif index + */ +struct mr_table { + struct list_head list; + possible_net_t net; + struct mr_table_ops ops; + u32 id; + struct sock __rcu *mroute_sk; + struct timer_list ipmr_expire_timer; + struct list_head mfc_unres_queue; + struct vif_device vif_table[MAXVIFS]; + struct rhltable mfc_hash; + struct list_head mfc_cache_list; + int maxvif; + atomic_t cache_resolve_queue_len; + bool mroute_do_assert; + bool mroute_do_pim; + int mroute_reg_vif_num; +}; + +#ifdef CONFIG_IP_MROUTE_COMMON +void vif_device_init(struct vif_device *v, + struct net_device *dev, + unsigned long rate_limit, + unsigned char threshold, + unsigned short flags, + unsigned short get_iflink_mask); + +struct mr_table * +mr_table_alloc(struct net *net, u32 id, + struct mr_table_ops *ops, + void (*expire_func)(struct timer_list *t), + void (*table_set)(struct mr_table *mrt, + struct net *net)); + +/* These actually return 'struct mr_mfc *', but to avoid need for explicit + * castings they simply return void. + */ +void *mr_mfc_find_parent(struct mr_table *mrt, + void *hasharg, int parent); +void *mr_mfc_find_any_parent(struct mr_table *mrt, int vifi); +void *mr_mfc_find_any(struct mr_table *mrt, int vifi, void *hasharg); + +int mr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb, + struct mr_mfc *c, struct rtmsg *rtm); +int mr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb, + struct mr_table *(*iter)(struct net *net, + struct mr_table *mrt), + int (*fill)(struct mr_table *mrt, + struct sk_buff *skb, + u32 portid, u32 seq, struct mr_mfc *c, + int cmd, int flags), + spinlock_t *lock); +#else +static inline void vif_device_init(struct vif_device *v, + struct net_device *dev, + unsigned long rate_limit, + unsigned char threshold, + unsigned short flags, + unsigned short get_iflink_mask) +{ +} + +static inline void * +mr_table_alloc(struct net *net, u32 id, + struct mr_table_ops *ops, + void (*expire_func)(struct timer_list *t), + void (*table_set)(struct mr_table *mrt, + struct net *net)) +{ + return NULL; +} + +static inline void *mr_mfc_find_parent(struct mr_table *mrt, + void *hasharg, int parent) +{ + return NULL; +} + +static inline void *mr_mfc_find_any_parent(struct mr_table *mrt, + int vifi) +{ + return NULL; +} + +static inline struct mr_mfc *mr_mfc_find_any(struct mr_table *mrt, + int vifi, void *hasharg) +{ + return NULL; +} + +static inline int mr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb, + struct mr_mfc *c, struct rtmsg *rtm) +{ + return -EINVAL; +} + +static inline int +mr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb, + struct mr_table *(*iter)(struct net *net, + struct mr_table *mrt), + int (*fill)(struct mr_table *mrt, + struct sk_buff *skb, + u32 portid, u32 seq, struct mr_mfc *c, + int cmd, int flags), + spinlock_t *lock) +{ + return -EINVAL; +} +#endif + +static inline void *mr_mfc_find(struct mr_table *mrt, void *hasharg) +{ + return mr_mfc_find_parent(mrt, hasharg, -1); +} + +#ifdef CONFIG_PROC_FS +struct mr_vif_iter { + struct seq_net_private p; + struct mr_table *mrt; + int ct; +}; + +struct mr_mfc_iter { + struct seq_net_private p; + struct mr_table *mrt; + struct list_head *cache; + + /* Lock protecting the mr_table's unresolved queue */ + spinlock_t *lock; +}; + +#ifdef CONFIG_IP_MROUTE_COMMON +void *mr_vif_seq_idx(struct net *net, struct mr_vif_iter *iter, loff_t pos); +void *mr_vif_seq_next(struct seq_file *seq, void *v, loff_t *pos); + +static inline void *mr_vif_seq_start(struct seq_file *seq, loff_t *pos) +{ + return *pos ? mr_vif_seq_idx(seq_file_net(seq), + seq->private, *pos - 1) + : SEQ_START_TOKEN; +} + +/* These actually return 'struct mr_mfc *', but to avoid need for explicit + * castings they simply return void. + */ +void *mr_mfc_seq_idx(struct net *net, + struct mr_mfc_iter *it, loff_t pos); +void *mr_mfc_seq_next(struct seq_file *seq, void *v, + loff_t *pos); + +static inline void *mr_mfc_seq_start(struct seq_file *seq, loff_t *pos, + struct mr_table *mrt, spinlock_t *lock) +{ + struct mr_mfc_iter *it = seq->private; + + it->mrt = mrt; + it->cache = NULL; + it->lock = lock; + + return *pos ? mr_mfc_seq_idx(seq_file_net(seq), + seq->private, *pos - 1) + : SEQ_START_TOKEN; +} + +static inline void mr_mfc_seq_stop(struct seq_file *seq, void *v) +{ + struct mr_mfc_iter *it = seq->private; + struct mr_table *mrt = it->mrt; + + if (it->cache == &mrt->mfc_unres_queue) + spin_unlock_bh(it->lock); + else if (it->cache == &mrt->mfc_cache_list) + rcu_read_unlock(); +} +#else +static inline void *mr_vif_seq_idx(struct net *net, struct mr_vif_iter *iter, + loff_t pos) +{ + return NULL; +} + +static inline void *mr_vif_seq_next(struct seq_file *seq, + void *v, loff_t *pos) +{ + return NULL; +} + +static inline void *mr_vif_seq_start(struct seq_file *seq, loff_t *pos) +{ + return NULL; +} + +static inline void *mr_mfc_seq_idx(struct net *net, + struct mr_mfc_iter *it, loff_t pos) +{ + return NULL; +} + +static inline void *mr_mfc_seq_next(struct seq_file *seq, void *v, + loff_t *pos) +{ + return NULL; +} + +static inline void *mr_mfc_seq_start(struct seq_file *seq, loff_t *pos, + struct mr_table *mrt, spinlock_t *lock) +{ + return NULL; +} + +static inline void mr_mfc_seq_stop(struct seq_file *seq, void *v) +{ +} +#endif +#endif +#endif diff --git a/include/linux/net.h b/include/linux/net.h index 91216b16feb7..000d1aada74f 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -146,7 +146,7 @@ struct proto_ops { struct socket *newsock, int flags, bool kern); int (*getname) (struct socket *sock, struct sockaddr *addr, - int *sockaddr_len, int peer); + int peer); __poll_t (*poll) (struct file *file, struct socket *sock, struct poll_table_struct *wait); int (*ioctl) (struct socket *sock, unsigned int cmd, @@ -294,10 +294,8 @@ int kernel_listen(struct socket *sock, int backlog); int kernel_accept(struct socket *sock, struct socket **newsock, int flags); int kernel_connect(struct socket *sock, struct sockaddr *addr, int addrlen, int flags); -int kernel_getsockname(struct socket *sock, struct sockaddr *addr, - int *addrlen); -int kernel_getpeername(struct socket *sock, struct sockaddr *addr, - int *addrlen); +int kernel_getsockname(struct socket *sock, struct sockaddr *addr); +int kernel_getpeername(struct socket *sock, struct sockaddr *addr); int kernel_getsockopt(struct socket *sock, int level, int optname, char *optval, int *optlen); int kernel_setsockopt(struct socket *sock, int level, int optname, char *optval, diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 5eef6c8e2741..dbe6344b727a 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1798,11 +1798,17 @@ struct net_device { #if IS_ENABLED(CONFIG_TIPC) struct tipc_bearer __rcu *tipc_ptr; #endif +#if IS_ENABLED(CONFIG_IRDA) || IS_ENABLED(CONFIG_ATALK) void *atalk_ptr; +#endif struct in_device __rcu *ip_ptr; +#if IS_ENABLED(CONFIG_DECNET) struct dn_dev __rcu *dn_ptr; +#endif struct inet6_dev __rcu *ip6_ptr; +#if IS_ENABLED(CONFIG_AX25) void *ax25_ptr; +#endif struct wireless_dev *ieee80211_ptr; struct wpan_dev *ieee802154_ptr; #if IS_ENABLED(CONFIG_MPLS_ROUTING) diff --git a/include/linux/phy.h b/include/linux/phy.h index d7069539f351..5a9b1753fdc5 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -995,6 +995,14 @@ int genphy_c45_pma_setup_forced(struct phy_device *phydev); int genphy_c45_an_disable_aneg(struct phy_device *phydev); int genphy_c45_read_mdix(struct phy_device *phydev); +/* The gen10g_* functions are the old Clause 45 stub */ +int gen10g_config_aneg(struct phy_device *phydev); +int gen10g_read_status(struct phy_device *phydev); +int gen10g_no_soft_reset(struct phy_device *phydev); +int gen10g_config_init(struct phy_device *phydev); +int gen10g_suspend(struct phy_device *phydev); +int gen10g_resume(struct phy_device *phydev); + static inline int phy_read_status(struct phy_device *phydev) { if (!phydev->drv) diff --git a/include/linux/ptp_classify.h b/include/linux/ptp_classify.h index a079656b614c..059242030631 100644 --- a/include/linux/ptp_classify.h +++ b/include/linux/ptp_classify.h @@ -75,5 +75,9 @@ void __init ptp_classifier_init(void); static inline void ptp_classifier_init(void) { } +static inline unsigned int ptp_classify_raw(struct sk_buff *skb) +{ + return PTP_CLASS_NONE; +} #endif #endif /* _PTP_CLASSIFY_H_ */ diff --git a/include/linux/ptr_ring.h b/include/linux/ptr_ring.h index e6335227b844..6894976b54e3 100644 --- a/include/linux/ptr_ring.h +++ b/include/linux/ptr_ring.h @@ -296,13 +296,14 @@ static inline void *__ptr_ring_consume(struct ptr_ring *r) { void *ptr; + /* The READ_ONCE in __ptr_ring_peek guarantees that anyone + * accessing data through the pointer is up to date. Pairs + * with smp_wmb in __ptr_ring_produce. + */ ptr = __ptr_ring_peek(r); if (ptr) __ptr_ring_discard_one(r); - /* Make sure anyone accessing data through the pointer is up to date. */ - /* Pairs with smp_wmb in __ptr_ring_produce. */ - smp_read_barrier_depends(); return ptr; } diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index 1fdcde96eb65..3573b4bf2fdf 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -35,7 +35,7 @@ extern int rtnl_trylock(void); extern int rtnl_is_locked(void); extern wait_queue_head_t netdev_unregistering_wq; -extern struct mutex net_mutex; +extern struct rw_semaphore net_sem; #ifdef CONFIG_PROVE_LOCKING extern bool lockdep_rtnl_is_held(void); diff --git a/include/linux/sfp.h b/include/linux/sfp.h index e724d5a3dd80..ebce9e24906a 100644 --- a/include/linux/sfp.h +++ b/include/linux/sfp.h @@ -422,10 +422,11 @@ struct sfp_upstream_ops { #if IS_ENABLED(CONFIG_SFP) int sfp_parse_port(struct sfp_bus *bus, const struct sfp_eeprom_id *id, unsigned long *support); -phy_interface_t sfp_parse_interface(struct sfp_bus *bus, - const struct sfp_eeprom_id *id); void sfp_parse_support(struct sfp_bus *bus, const struct sfp_eeprom_id *id, unsigned long *support); +phy_interface_t sfp_select_interface(struct sfp_bus *bus, + const struct sfp_eeprom_id *id, + unsigned long *link_modes); int sfp_get_module_info(struct sfp_bus *bus, struct ethtool_modinfo *modinfo); int sfp_get_module_eeprom(struct sfp_bus *bus, struct ethtool_eeprom *ee, @@ -444,18 +445,19 @@ static inline int sfp_parse_port(struct sfp_bus *bus, return PORT_OTHER; } -static inline phy_interface_t sfp_parse_interface(struct sfp_bus *bus, - const struct sfp_eeprom_id *id) -{ - return PHY_INTERFACE_MODE_NA; -} - static inline void sfp_parse_support(struct sfp_bus *bus, const struct sfp_eeprom_id *id, unsigned long *support) { } +static inline phy_interface_t sfp_select_interface(struct sfp_bus *bus, + const struct sfp_eeprom_id *id, + unsigned long *link_modes) +{ + return PHY_INTERFACE_MODE_NA; +} + static inline int sfp_get_module_info(struct sfp_bus *bus, struct ethtool_modinfo *modinfo) { diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index ddf77cf4ff2d..d8340e6e8814 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -466,6 +466,9 @@ struct ubuf_info { #define skb_uarg(SKB) ((struct ubuf_info *)(skb_shinfo(SKB)->destructor_arg)) +int mm_account_pinned_pages(struct mmpin *mmp, size_t size); +void mm_unaccount_pinned_pages(struct mmpin *mmp); + struct ubuf_info *sock_zerocopy_alloc(struct sock *sk, size_t size); struct ubuf_info *sock_zerocopy_realloc(struct sock *sk, size_t size, struct ubuf_info *uarg); diff --git a/include/linux/socket.h b/include/linux/socket.h index 9286a5a8c60c..1ce1f768a58c 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -353,4 +353,6 @@ extern int __sys_recvmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen unsigned int flags, struct timespec *timeout); extern int __sys_sendmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen, unsigned int flags); + +extern struct ns_common *get_net_ns(struct ns_common *ns); #endif /* _LINUX_SOCKET_H */ diff --git a/include/net/Space.h b/include/net/Space.h index 27fb5c937c4f..9cce0d80d37a 100644 --- a/include/net/Space.h +++ b/include/net/Space.h @@ -20,8 +20,6 @@ struct net_device *cs89x0_probe(int unit); struct net_device *mvme147lance_probe(int unit); struct net_device *tc515_probe(int unit); struct net_device *lance_probe(int unit); -struct net_device *mac8390_probe(int unit); -struct net_device *mac89x0_probe(int unit); struct net_device *cops_probe(int unit); struct net_device *ltpc_probe(void); diff --git a/include/net/act_api.h b/include/net/act_api.h index 6ed9692f20bd..9c2f22695025 100644 --- a/include/net/act_api.h +++ b/include/net/act_api.h @@ -87,12 +87,15 @@ struct tc_action_ops { struct tcf_result *); int (*dump)(struct sk_buff *, struct tc_action *, int, int); void (*cleanup)(struct tc_action *); - int (*lookup)(struct net *, struct tc_action **, u32); + int (*lookup)(struct net *net, struct tc_action **a, u32 index, + struct netlink_ext_ack *extack); int (*init)(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **act, int ovr, - int bind); + int bind, struct netlink_ext_ack *extack); int (*walk)(struct net *, struct sk_buff *, - struct netlink_callback *, int, const struct tc_action_ops *); + struct netlink_callback *, int, + const struct tc_action_ops *, + struct netlink_ext_ack *); void (*stats_update)(struct tc_action *, u64, u32, u64); struct net_device *(*get_dev)(const struct tc_action *a); }; @@ -137,7 +140,8 @@ static inline void tc_action_net_exit(struct list_head *net_list, int tcf_generic_walker(struct tc_action_net *tn, struct sk_buff *skb, struct netlink_callback *cb, int type, - const struct tc_action_ops *ops); + const struct tc_action_ops *ops, + struct netlink_ext_ack *extack); int tcf_idr_search(struct tc_action_net *tn, struct tc_action **a, u32 index); bool tcf_idr_check(struct tc_action_net *tn, u32 index, struct tc_action **a, int bind); @@ -162,10 +166,11 @@ int tcf_action_exec(struct sk_buff *skb, struct tc_action **actions, int nr_actions, struct tcf_result *res); int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla, struct nlattr *est, char *name, int ovr, int bind, - struct list_head *actions); + struct list_head *actions, struct netlink_ext_ack *extack); struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp, struct nlattr *nla, struct nlattr *est, - char *name, int ovr, int bind); + char *name, int ovr, int bind, + struct netlink_ext_ack *extack); int tcf_action_dump(struct sk_buff *skb, struct list_head *, int, int); int tcf_action_dump_old(struct sk_buff *skb, struct tc_action *a, int, int); int tcf_action_dump_1(struct sk_buff *skb, struct tc_action *a, int, int); diff --git a/include/net/ax25.h b/include/net/ax25.h index 76fb39c272a7..c91bc87931c7 100644 --- a/include/net/ax25.h +++ b/include/net/ax25.h @@ -318,10 +318,12 @@ void ax25_digi_invert(const ax25_digi *, ax25_digi *); extern ax25_dev *ax25_dev_list; extern spinlock_t ax25_dev_lock; +#if IS_ENABLED(CONFIG_AX25) static inline ax25_dev *ax25_dev_ax25dev(struct net_device *dev) { return dev->ax25_ptr; } +#endif ax25_dev *ax25_addr_ax25dev(ax25_address *); void ax25_dev_device_up(struct net_device *); diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 81174f9b8d14..fc40843baed3 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -1147,6 +1147,7 @@ struct cfg80211_tid_stats { * @rx_duration: aggregate PPDU duration(usecs) for all the frames from a peer * @pertid: per-TID statistics, see &struct cfg80211_tid_stats, using the last * (IEEE80211_NUM_TIDS) index for MSDUs not encapsulated in QoS-MPDUs. + * @ack_signal: signal strength (in dBm) of the last ACK frame. */ struct station_info { u64 filled; @@ -1191,6 +1192,7 @@ struct station_info { u64 rx_duration; u8 rx_beacon_signal_avg; struct cfg80211_tid_stats pertid[IEEE80211_NUM_TIDS + 1]; + s8 ack_signal; }; #if IS_ENABLED(CONFIG_CFG80211) @@ -1905,11 +1907,16 @@ struct cfg80211_auth_request { * @ASSOC_REQ_DISABLE_HT: Disable HT (802.11n) * @ASSOC_REQ_DISABLE_VHT: Disable VHT * @ASSOC_REQ_USE_RRM: Declare RRM capability in this association + * @CONNECT_REQ_EXTERNAL_AUTH_SUPPORT: User space indicates external + * authentication capability. Drivers can offload authentication to + * userspace if this flag is set. Only applicable for cfg80211_connect() + * request (connect callback). */ enum cfg80211_assoc_req_flags { - ASSOC_REQ_DISABLE_HT = BIT(0), - ASSOC_REQ_DISABLE_VHT = BIT(1), - ASSOC_REQ_USE_RRM = BIT(2), + ASSOC_REQ_DISABLE_HT = BIT(0), + ASSOC_REQ_DISABLE_VHT = BIT(1), + ASSOC_REQ_USE_RRM = BIT(2), + CONNECT_REQ_EXTERNAL_AUTH_SUPPORT = BIT(3), }; /** @@ -2601,6 +2608,33 @@ struct cfg80211_pmk_conf { }; /** + * struct cfg80211_external_auth_params - Trigger External authentication. + * + * Commonly used across the external auth request and event interfaces. + * + * @action: action type / trigger for external authentication. Only significant + * for the authentication request event interface (driver to user space). + * @bssid: BSSID of the peer with which the authentication has + * to happen. Used by both the authentication request event and + * authentication response command interface. + * @ssid: SSID of the AP. Used by both the authentication request event and + * authentication response command interface. + * @key_mgmt_suite: AKM suite of the respective authentication. Used by the + * authentication request event interface. + * @status: status code, %WLAN_STATUS_SUCCESS for successful authentication, + * use %WLAN_STATUS_UNSPECIFIED_FAILURE if user space cannot give you + * the real status code for failures. Used only for the authentication + * response command interface (user space to driver). + */ +struct cfg80211_external_auth_params { + enum nl80211_external_auth_action action; + u8 bssid[ETH_ALEN] __aligned(2); + struct cfg80211_ssid ssid; + unsigned int key_mgmt_suite; + u16 status; +}; + +/** * struct cfg80211_ops - backend description for wireless configuration * * This struct is registered by fullmac card drivers and/or wireless stacks @@ -2923,6 +2957,9 @@ struct cfg80211_pmk_conf { * (invoked with the wireless_dev mutex held) * @del_pmk: delete the previously configured PMK for the given authenticator. * (invoked with the wireless_dev mutex held) + * + * @external_auth: indicates result of offloaded authentication processing from + * user space */ struct cfg80211_ops { int (*suspend)(struct wiphy *wiphy, struct cfg80211_wowlan *wow); @@ -3216,6 +3253,8 @@ struct cfg80211_ops { const struct cfg80211_pmk_conf *conf); int (*del_pmk)(struct wiphy *wiphy, struct net_device *dev, const u8 *aa); + int (*external_auth)(struct wiphy *wiphy, struct net_device *dev, + struct cfg80211_external_auth_params *params); }; /* @@ -3517,6 +3556,35 @@ enum wiphy_vendor_command_flags { }; /** + * enum wiphy_opmode_flag - Station's ht/vht operation mode information flags + * + * @STA_OPMODE_MAX_BW_CHANGED: Max Bandwidth changed + * @STA_OPMODE_SMPS_MODE_CHANGED: SMPS mode changed + * @STA_OPMODE_N_SS_CHANGED: max N_SS (number of spatial streams) changed + * + */ +enum wiphy_opmode_flag { + STA_OPMODE_MAX_BW_CHANGED = BIT(0), + STA_OPMODE_SMPS_MODE_CHANGED = BIT(1), + STA_OPMODE_N_SS_CHANGED = BIT(2), +}; + +/** + * struct sta_opmode_info - Station's ht/vht operation mode information + * @changed: contains value from &enum wiphy_opmode_flag + * @smps_mode: New SMPS mode of a station + * @bw: new max bandwidth value of a station + * @rx_nss: new rx_nss value of a station + */ + +struct sta_opmode_info { + u32 changed; + u8 smps_mode; + u8 bw; + u8 rx_nss; +}; + +/** * struct wiphy_vendor_command - vendor command definition * @info: vendor command identifying information, as used in nl80211 * @flags: flags, see &enum wiphy_vendor_command_flags @@ -4342,10 +4410,12 @@ unsigned int ieee80211_get_mesh_hdrlen(struct ieee80211s_hdr *meshhdr); * of it being pushed into the SKB * @addr: the device MAC address * @iftype: the virtual interface type + * @data_offset: offset of payload after the 802.11 header * Return: 0 on success. Non-zero on error. */ int ieee80211_data_to_8023_exthdr(struct sk_buff *skb, struct ethhdr *ehdr, - const u8 *addr, enum nl80211_iftype iftype); + const u8 *addr, enum nl80211_iftype iftype, + u8 data_offset); /** * ieee80211_data_to_8023 - convert an 802.11 data frame to 802.3 @@ -4357,7 +4427,7 @@ int ieee80211_data_to_8023_exthdr(struct sk_buff *skb, struct ethhdr *ehdr, static inline int ieee80211_data_to_8023(struct sk_buff *skb, const u8 *addr, enum nl80211_iftype iftype) { - return ieee80211_data_to_8023_exthdr(skb, NULL, addr, iftype); + return ieee80211_data_to_8023_exthdr(skb, NULL, addr, iftype, 0); } /** @@ -5685,6 +5755,20 @@ void cfg80211_radar_event(struct wiphy *wiphy, struct cfg80211_chan_def *chandef, gfp_t gfp); /** + * cfg80211_sta_opmode_change_notify - STA's ht/vht operation mode change event + * @dev: network device + * @mac: MAC address of a station which opmode got modified + * @sta_opmode: station's current opmode value + * @gfp: context flags + * + * Driver should call this function when station's opmode modified via action + * frame. + */ +void cfg80211_sta_opmode_change_notify(struct net_device *dev, const u8 *mac, + struct sta_opmode_info *sta_opmode, + gfp_t gfp); + +/** * cfg80211_cac_event - Channel availability check (CAC) event * @netdev: network device * @chandef: chandef for the current channel @@ -5758,10 +5842,13 @@ bool cfg80211_rx_unexpected_4addr_frame(struct net_device *dev, * @addr: the address of the peer * @cookie: the cookie filled in @probe_client previously * @acked: indicates whether probe was acked or not + * @ack_signal: signal strength (in dBm) of the ACK frame. + * @is_valid_ack_signal: indicates the ack_signal is valid or not. * @gfp: allocation flags */ void cfg80211_probe_status(struct net_device *dev, const u8 *addr, - u64 cookie, bool acked, gfp_t gfp); + u64 cookie, bool acked, s32 ack_signal, + bool is_valid_ack_signal, gfp_t gfp); /** * cfg80211_report_obss_beacon - report beacon from other APs @@ -6202,6 +6289,17 @@ void cfg80211_nan_func_terminated(struct wireless_dev *wdev, /* ethtool helper */ void cfg80211_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info); +/** + * cfg80211_external_auth_request - userspace request for authentication + * @netdev: network device + * @params: External authentication parameters + * @gfp: allocation flags + * Returns: 0 on success, < 0 on error + */ +int cfg80211_external_auth_request(struct net_device *netdev, + struct cfg80211_external_auth_params *params, + gfp_t gfp); + /* Logging, debugging and troubleshooting/diagnostic helpers. */ /* wiphy_printk helpers, similar to dev_printk */ diff --git a/include/net/devlink.h b/include/net/devlink.h index 4de35ed12bcc..c83125ad20ff 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -234,13 +234,9 @@ struct devlink_dpipe_headers { /** * struct devlink_resource_ops - resource ops * @occ_get: get the occupied size - * @size_validate: validate the size of the resource before update, reload - * is needed for changes to take place */ struct devlink_resource_ops { u64 (*occ_get)(struct devlink *devlink); - int (*size_validate)(struct devlink *devlink, u64 size, - struct netlink_ext_ack *extack); }; /** diff --git a/include/net/dsa.h b/include/net/dsa.h index 6cb602dd970c..60fb4ec8ba61 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -19,6 +19,7 @@ #include <linux/workqueue.h> #include <linux/of.h> #include <linux/ethtool.h> +#include <linux/net_tstamp.h> #include <net/devlink.h> #include <net/switchdev.h> @@ -101,6 +102,7 @@ struct dsa_platform_data { }; struct packet_type; +struct dsa_switch; struct dsa_device_ops { struct sk_buff *(*xmit)(struct sk_buff *skb, struct net_device *dev); @@ -357,7 +359,7 @@ struct dsa_switch_ops { void (*get_strings)(struct dsa_switch *ds, int port, uint8_t *data); void (*get_ethtool_stats)(struct dsa_switch *ds, int port, uint64_t *data); - int (*get_sset_count)(struct dsa_switch *ds); + int (*get_sset_count)(struct dsa_switch *ds, int port); /* * ethtool Wake-on-LAN @@ -368,6 +370,12 @@ struct dsa_switch_ops { struct ethtool_wolinfo *w); /* + * ethtool timestamp info + */ + int (*get_ts_info)(struct dsa_switch *ds, int port, + struct ethtool_ts_info *ts); + + /* * Suspend and resume */ int (*suspend)(struct dsa_switch *ds); @@ -469,6 +477,18 @@ struct dsa_switch_ops { int port, struct net_device *br); void (*crosschip_bridge_leave)(struct dsa_switch *ds, int sw_index, int port, struct net_device *br); + + /* + * PTP functionality + */ + int (*port_hwtstamp_get)(struct dsa_switch *ds, int port, + struct ifreq *ifr); + int (*port_hwtstamp_set)(struct dsa_switch *ds, int port, + struct ifreq *ifr); + bool (*port_txtstamp)(struct dsa_switch *ds, int port, + struct sk_buff *clone, unsigned int type); + bool (*port_rxtstamp)(struct dsa_switch *ds, int port, + struct sk_buff *skb, unsigned int type); }; struct dsa_switch_driver { diff --git a/include/net/dst.h b/include/net/dst.h index c63d2c37f6e9..b3219cd8a5a1 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -356,6 +356,7 @@ static inline void __skb_tunnel_rx(struct sk_buff *skb, struct net_device *dev, * skb_tunnel_rx - prepare skb for rx reinsert * @skb: buffer * @dev: tunnel device + * @net: netns for packet i/o * * After decapsulation, packet is going to re-enter (netif_rx()) our stack, * so make some cleanups, and perform accounting. diff --git a/include/net/dst_cache.h b/include/net/dst_cache.h index 72fd5067c353..67634675e919 100644 --- a/include/net/dst_cache.h +++ b/include/net/dst_cache.h @@ -54,7 +54,7 @@ void dst_cache_set_ip4(struct dst_cache *dst_cache, struct dst_entry *dst, * local BH must be disabled. */ void dst_cache_set_ip6(struct dst_cache *dst_cache, struct dst_entry *dst, - const struct in6_addr *addr); + const struct in6_addr *saddr); /** * dst_cache_get_ip6 - perform cache lookup and fetch ipv6 source address @@ -71,7 +71,7 @@ struct dst_entry *dst_cache_get_ip6(struct dst_cache *dst_cache, * dst_cache_reset - invalidate the cache contents * @dst_cache: the cache * - * This do not free the cached dst to avoid races and contentions. + * This does not free the cached dst to avoid races and contentions. * the dst will be freed on later cache lookup. */ static inline void dst_cache_reset(struct dst_cache *dst_cache) diff --git a/include/net/ethoc.h b/include/net/ethoc.h index bb7f467da7fc..29ba069a1d93 100644 --- a/include/net/ethoc.h +++ b/include/net/ethoc.h @@ -21,4 +21,3 @@ struct ethoc_platform_data { }; #endif /* !LINUX_NET_ETHOC_H */ - diff --git a/include/net/fib_rules.h b/include/net/fib_rules.h index 648caf90ec07..e5cfcfc7dd93 100644 --- a/include/net/fib_rules.h +++ b/include/net/fib_rules.h @@ -26,7 +26,8 @@ struct fib_rule { u32 table; u8 action; u8 l3mdev; - /* 2 bytes hole, try to use */ + u8 proto; + u8 ip_proto; u32 target; __be64 tun_id; struct fib_rule __rcu *ctarget; @@ -39,11 +40,14 @@ struct fib_rule { char iifname[IFNAMSIZ]; char oifname[IFNAMSIZ]; struct fib_kuid_range uid_range; + struct fib_rule_port_range sport_range; + struct fib_rule_port_range dport_range; struct rcu_head rcu; }; struct fib_lookup_arg { void *lookup_ptr; + const void *lookup_data; void *result; struct fib_rule *rule; u32 table; @@ -108,7 +112,12 @@ struct fib_rule_notifier_info { [FRA_SUPPRESS_IFGROUP] = { .type = NLA_U32 }, \ [FRA_GOTO] = { .type = NLA_U32 }, \ [FRA_L3MDEV] = { .type = NLA_U8 }, \ - [FRA_UID_RANGE] = { .len = sizeof(struct fib_rule_uid_range) } + [FRA_UID_RANGE] = { .len = sizeof(struct fib_rule_uid_range) }, \ + [FRA_PROTOCOL] = { .type = NLA_U8 }, \ + [FRA_IP_PROTO] = { .type = NLA_U8 }, \ + [FRA_SPORT_RANGE] = { .len = sizeof(struct fib_rule_port_range) }, \ + [FRA_DPORT_RANGE] = { .len = sizeof(struct fib_rule_port_range) } + static inline void fib_rule_get(struct fib_rule *rule) { @@ -142,6 +151,38 @@ static inline u32 frh_get_table(struct fib_rule_hdr *frh, struct nlattr **nla) return frh->table; } +static inline bool fib_rule_port_range_set(const struct fib_rule_port_range *range) +{ + return range->start != 0 && range->end != 0; +} + +static inline bool fib_rule_port_inrange(const struct fib_rule_port_range *a, + __be16 port) +{ + return ntohs(port) >= a->start && + ntohs(port) <= a->end; +} + +static inline bool fib_rule_port_range_valid(const struct fib_rule_port_range *a) +{ + return a->start != 0 && a->end != 0 && a->end < 0xffff && + a->start <= a->end; +} + +static inline bool fib_rule_port_range_compare(struct fib_rule_port_range *a, + struct fib_rule_port_range *b) +{ + return a->start == b->start && + a->end == b->end; +} + +static inline bool fib_rule_requires_fldissect(struct fib_rule *rule) +{ + return rule->ip_proto || + fib_rule_port_range_set(&rule->sport_range) || + fib_rule_port_range_set(&rule->dport_range); +} + struct fib_rules_ops *fib_rules_register(const struct fib_rules_ops *, struct net *); void fib_rules_unregister(struct fib_rules_ops *); diff --git a/include/net/flow.h b/include/net/flow.h index f1624fd5b1d0..8ce21793094e 100644 --- a/include/net/flow.h +++ b/include/net/flow.h @@ -125,7 +125,7 @@ static inline void flowi4_update_output(struct flowi4 *fl4, int oif, __u8 tos, fl4->daddr = daddr; fl4->saddr = saddr; } - + struct flowi6 { struct flowi_common __fl_common; @@ -222,20 +222,4 @@ static inline unsigned int flow_key_size(u16 family) __u32 __get_hash_from_flowi6(const struct flowi6 *fl6, struct flow_keys *keys); -static inline __u32 get_hash_from_flowi6(const struct flowi6 *fl6) -{ - struct flow_keys keys; - - return __get_hash_from_flowi6(fl6, &keys); -} - -__u32 __get_hash_from_flowi4(const struct flowi4 *fl4, struct flow_keys *keys); - -static inline __u32 get_hash_from_flowi4(const struct flowi4 *fl4) -{ - struct flow_keys keys; - - return __get_hash_from_flowi4(fl4, &keys); -} - #endif diff --git a/include/net/gre.h b/include/net/gre.h index f90585decbce..797142eee9cd 100644 --- a/include/net/gre.h +++ b/include/net/gre.h @@ -37,6 +37,9 @@ struct net_device *gretap_fb_dev_create(struct net *net, const char *name, int gre_parse_header(struct sk_buff *skb, struct tnl_ptk_info *tpi, bool *csum_err, __be16 proto, int nhs); +bool is_gretap_dev(const struct net_device *dev); +bool is_ip6gretap_dev(const struct net_device *dev); + static inline int gre_calc_hlen(__be16 o_flags) { int addend = 4; diff --git a/include/net/ieee80211_radiotap.h b/include/net/ieee80211_radiotap.h index d91f9e7f4d71..960236fb1681 100644 --- a/include/net/ieee80211_radiotap.h +++ b/include/net/ieee80211_radiotap.h @@ -149,6 +149,8 @@ enum ieee80211_radiotap_ampdu_flags { IEEE80211_RADIOTAP_AMPDU_IS_LAST = 0x0008, IEEE80211_RADIOTAP_AMPDU_DELIM_CRC_ERR = 0x0010, IEEE80211_RADIOTAP_AMPDU_DELIM_CRC_KNOWN = 0x0020, + IEEE80211_RADIOTAP_AMPDU_EOF = 0x0040, + IEEE80211_RADIOTAP_AMPDU_EOF_KNOWN = 0x0080, }; /* for IEEE80211_RADIOTAP_VHT */ diff --git a/include/net/inet_common.h b/include/net/inet_common.h index 5a54c9570977..500f81375200 100644 --- a/include/net/inet_common.h +++ b/include/net/inet_common.h @@ -32,7 +32,7 @@ int inet_shutdown(struct socket *sock, int how); int inet_listen(struct socket *sock, int backlog); void inet_sock_destruct(struct sock *sk); int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len); -int inet_getname(struct socket *sock, struct sockaddr *uaddr, int *uaddr_len, +int inet_getname(struct socket *sock, struct sockaddr *uaddr, int peer); int inet_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg); int inet_ctl_sock_create(struct sock **sk, unsigned short family, diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index c1a93ce35e62..b68fea022a82 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -49,9 +49,9 @@ struct inet_connection_sock_af_ops { u16 net_header_len; u16 net_frag_header_len; u16 sockaddr_len; - int (*setsockopt)(struct sock *sk, int level, int optname, + int (*setsockopt)(struct sock *sk, int level, int optname, char __user *optval, unsigned int optlen); - int (*getsockopt)(struct sock *sk, int level, int optname, + int (*getsockopt)(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen); #ifdef CONFIG_COMPAT int (*compat_setsockopt)(struct sock *sk, @@ -67,7 +67,7 @@ struct inet_connection_sock_af_ops { /** inet_connection_sock - INET connection oriented sock * - * @icsk_accept_queue: FIFO of established children + * @icsk_accept_queue: FIFO of established children * @icsk_bind_hash: Bind node * @icsk_timeout: Timeout * @icsk_retransmit_timer: Resend (no ack) @@ -122,7 +122,7 @@ struct inet_connection_sock { unsigned long timeout; /* Currently scheduled timeout */ __u32 lrcvtime; /* timestamp of last received data packet */ __u16 last_seg_size; /* Size of last incoming segment */ - __u16 rcv_mss; /* MSS used for delayed ACK decisions */ + __u16 rcv_mss; /* MSS used for delayed ACK decisions */ } icsk_ack; struct { int enabled; @@ -201,7 +201,7 @@ extern const char inet_csk_timer_bug_msg[]; static inline void inet_csk_clear_xmit_timer(struct sock *sk, const int what) { struct inet_connection_sock *icsk = inet_csk(sk); - + if (what == ICSK_TIME_RETRANS || what == ICSK_TIME_PROBE0) { icsk->icsk_pending = 0; #ifdef INET_CSK_CLEAR_TIMERS diff --git a/include/net/ip.h b/include/net/ip.h index 746abff9ce51..fe63ba95d12b 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -186,15 +186,15 @@ int ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len); void ip4_datagram_release_cb(struct sock *sk); struct ip_reply_arg { - struct kvec iov[1]; + struct kvec iov[1]; int flags; __wsum csum; int csumoffset; /* u16 offset of csum in iov[0].iov_base */ - /* -1 if not needed */ + /* -1 if not needed */ int bound_dev_if; u8 tos; kuid_t uid; -}; +}; #define IP_REPLY_ARG_NOSRCCHECK 1 @@ -577,13 +577,13 @@ int ip_frag_mem(struct net *net); /* * Functions provided by ip_forward.c */ - + int ip_forward(struct sk_buff *skb); - + /* * Functions provided by ip_options.c */ - + void ip_options_build(struct sk_buff *skb, struct ip_options *opt, __be32 daddr, struct rtable *rt, int is_frag); diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index 34ec321d6a03..5e86fd9dc857 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -350,7 +350,8 @@ struct fib6_table { typedef struct rt6_info *(*pol_lookup_t)(struct net *, struct fib6_table *, - struct flowi6 *, int); + struct flowi6 *, + const struct sk_buff *, int); struct fib6_entry_notifier_info { struct fib_notifier_info info; /* must be first */ @@ -364,6 +365,7 @@ struct fib6_entry_notifier_info { struct fib6_table *fib6_get_table(struct net *net, u32 id); struct fib6_table *fib6_new_table(struct net *net, u32 id); struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi6 *fl6, + const struct sk_buff *skb, int flags, pol_lookup_t lookup); struct fib6_node *fib6_lookup(struct fib6_node *root, @@ -415,6 +417,24 @@ void fib6_rules_cleanup(void); bool fib6_rule_default(const struct fib_rule *rule); int fib6_rules_dump(struct net *net, struct notifier_block *nb); unsigned int fib6_rules_seq_read(struct net *net); + +static inline bool fib6_rules_early_flow_dissect(struct net *net, + struct sk_buff *skb, + struct flowi6 *fl6, + struct flow_keys *flkeys) +{ + unsigned int flag = FLOW_DISSECTOR_F_STOP_AT_ENCAP; + + if (!net->ipv6.fib6_rules_require_fldissect) + return false; + + skb_flow_dissect_flow_keys(skb, flkeys, flag); + fl6->fl6_sport = flkeys->ports.src; + fl6->fl6_dport = flkeys->ports.dst; + fl6->flowi6_proto = flkeys->basic.ip_proto; + + return true; +} #else static inline int fib6_rules_init(void) { @@ -436,5 +456,12 @@ static inline unsigned int fib6_rules_seq_read(struct net *net) { return 0; } +static inline bool fib6_rules_early_flow_dissect(struct net *net, + struct sk_buff *skb, + struct flowi6 *fl6, + struct flow_keys *flkeys) +{ + return false; +} #endif #endif diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h index 27d23a65f3cd..ce2abc0ff102 100644 --- a/include/net/ip6_route.h +++ b/include/net/ip6_route.h @@ -75,7 +75,8 @@ static inline bool rt6_qualify_for_ecmp(const struct rt6_info *rt) void ip6_route_input(struct sk_buff *skb); struct dst_entry *ip6_route_input_lookup(struct net *net, struct net_device *dev, - struct flowi6 *fl6, int flags); + struct flowi6 *fl6, + const struct sk_buff *skb, int flags); struct dst_entry *ip6_route_output_flags(struct net *net, const struct sock *sk, struct flowi6 *fl6, int flags); @@ -88,9 +89,10 @@ static inline struct dst_entry *ip6_route_output(struct net *net, } struct dst_entry *ip6_route_lookup(struct net *net, struct flowi6 *fl6, - int flags); + const struct sk_buff *skb, int flags); struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table, - int ifindex, struct flowi6 *fl6, int flags); + int ifindex, struct flowi6 *fl6, + const struct sk_buff *skb, int flags); void ip6_route_init_special_entries(void); int ip6_route_init(void); @@ -126,8 +128,10 @@ static inline int ip6_route_get_saddr(struct net *net, struct rt6_info *rt, } struct rt6_info *rt6_lookup(struct net *net, const struct in6_addr *daddr, - const struct in6_addr *saddr, int oif, int flags); -u32 rt6_multipath_hash(const struct flowi6 *fl6, const struct sk_buff *skb); + const struct in6_addr *saddr, int oif, + const struct sk_buff *skb, int flags); +u32 rt6_multipath_hash(const struct net *net, const struct flowi6 *fl6, + const struct sk_buff *skb, struct flow_keys *hkeys); struct dst_entry *icmp6_dst_alloc(struct net_device *dev, struct flowi6 *fl6); @@ -266,4 +270,5 @@ static inline bool rt6_duplicate_nexthop(struct rt6_info *a, struct rt6_info *b) ipv6_addr_equal(&a->rt6i_gateway, &b->rt6i_gateway) && !lwtunnel_cmp_encap(a->dst.lwtstate, b->dst.lwtstate); } + #endif diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index f80524396c06..7c7522e8585b 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -157,7 +157,7 @@ struct fib_result_nl { unsigned char nh_sel; unsigned char type; unsigned char scope; - int err; + int err; }; #ifdef CONFIG_IP_ROUTE_MULTIPATH @@ -293,6 +293,13 @@ static inline unsigned int fib4_rules_seq_read(struct net *net) return 0; } +static inline bool fib4_rules_early_flow_dissect(struct net *net, + struct sk_buff *skb, + struct flowi4 *fl4, + struct flow_keys *flkeys) +{ + return false; +} #else /* CONFIG_IP_MULTIPLE_TABLES */ int __net_init fib4_rules_init(struct net *net); void __net_exit fib4_rules_exit(struct net *net); @@ -341,6 +348,24 @@ bool fib4_rule_default(const struct fib_rule *rule); int fib4_rules_dump(struct net *net, struct notifier_block *nb); unsigned int fib4_rules_seq_read(struct net *net); +static inline bool fib4_rules_early_flow_dissect(struct net *net, + struct sk_buff *skb, + struct flowi4 *fl4, + struct flow_keys *flkeys) +{ + unsigned int flag = FLOW_DISSECTOR_F_STOP_AT_ENCAP; + + if (!net->ipv4.fib_rules_require_fldissect) + return false; + + skb_flow_dissect_flow_keys(skb, flkeys, flag); + fl4->fl4_sport = flkeys->ports.src; + fl4->fl4_dport = flkeys->ports.dst; + fl4->flowi4_proto = flkeys->basic.ip_proto; + + return true; +} + #endif /* CONFIG_IP_MULTIPLE_TABLES */ /* Exported by fib_frontend.c */ @@ -370,8 +395,8 @@ int fib_sync_down_addr(struct net_device *dev, __be32 local); int fib_sync_up(struct net_device *dev, unsigned int nh_flags); #ifdef CONFIG_IP_ROUTE_MULTIPATH -int fib_multipath_hash(const struct fib_info *fi, const struct flowi4 *fl4, - const struct sk_buff *skb); +int fib_multipath_hash(const struct net *net, const struct flowi4 *fl4, + const struct sk_buff *skb, struct flow_keys *flkeys); #endif void fib_select_multipath(struct fib_result *res, int hash); void fib_select_path(struct net *net, struct fib_result *res, diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index 1f16773cfd76..cbe5addb9293 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -254,6 +254,22 @@ static inline __be32 tunnel_id_to_key32(__be64 tun_id) #ifdef CONFIG_INET +static inline void ip_tunnel_init_flow(struct flowi4 *fl4, + int proto, + __be32 daddr, __be32 saddr, + __be32 key, __u8 tos, int oif, + __u32 mark) +{ + memset(fl4, 0, sizeof(*fl4)); + fl4->flowi4_oif = oif; + fl4->daddr = daddr; + fl4->saddr = saddr; + fl4->flowi4_tos = tos; + fl4->flowi4_proto = proto; + fl4->fl4_gre_key = key; + fl4->flowi4_mark = mark; +} + int ip_tunnel_init(struct net_device *dev); void ip_tunnel_uninit(struct net_device *dev); void ip_tunnel_dellink(struct net_device *dev, struct list_head *head); diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 8606c9113d3f..cabd3cdd4015 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -105,8 +105,8 @@ #define IPV6_ADDR_ANY 0x0000U -#define IPV6_ADDR_UNICAST 0x0001U -#define IPV6_ADDR_MULTICAST 0x0002U +#define IPV6_ADDR_UNICAST 0x0001U +#define IPV6_ADDR_MULTICAST 0x0002U #define IPV6_ADDR_LOOPBACK 0x0010U #define IPV6_ADDR_LINKLOCAL 0x0020U @@ -447,7 +447,7 @@ ipv6_masked_addr_cmp(const struct in6_addr *a1, const struct in6_addr *m, #endif } -static inline void ipv6_addr_prefix(struct in6_addr *pfx, +static inline void ipv6_addr_prefix(struct in6_addr *pfx, const struct in6_addr *addr, int plen) { @@ -496,7 +496,7 @@ static inline void __ipv6_addr_set_half(__be32 *addr, addr[1] = wl; } -static inline void ipv6_addr_set(struct in6_addr *addr, +static inline void ipv6_addr_set(struct in6_addr *addr, __be32 w1, __be32 w2, __be32 w3, __be32 w4) { @@ -732,7 +732,7 @@ static inline int __ipv6_addr_diff32(const void *token1, const void *token2, int } /* - * we should *never* get to this point since that + * we should *never* get to this point since that * would mean the addrs are equal * * However, we do get to it 8) And exacly, when @@ -1056,7 +1056,7 @@ void ipv6_local_rxpmtu(struct sock *sk, struct flowi6 *fl6, u32 mtu); int inet6_release(struct socket *sock); int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len); -int inet6_getname(struct socket *sock, struct sockaddr *uaddr, int *uaddr_len, +int inet6_getname(struct socket *sock, struct sockaddr *uaddr, int peer); int inet6_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg); diff --git a/include/net/lwtunnel.h b/include/net/lwtunnel.h index d747ef975cd8..33fd9ba7e0e5 100644 --- a/include/net/lwtunnel.h +++ b/include/net/lwtunnel.h @@ -127,6 +127,17 @@ int lwtunnel_output(struct net *net, struct sock *sk, struct sk_buff *skb); int lwtunnel_input(struct sk_buff *skb); int lwtunnel_xmit(struct sk_buff *skb); +static inline void lwtunnel_set_redirect(struct dst_entry *dst) +{ + if (lwtunnel_output_redirect(dst->lwtstate)) { + dst->lwtstate->orig_output = dst->output; + dst->output = lwtunnel_output; + } + if (lwtunnel_input_redirect(dst->lwtstate)) { + dst->lwtstate->orig_input = dst->input; + dst->input = lwtunnel_input; + } +} #else static inline void lwtstate_free(struct lwtunnel_state *lws) @@ -158,6 +169,10 @@ static inline bool lwtunnel_xmit_redirect(struct lwtunnel_state *lwtstate) return false; } +static inline void lwtunnel_set_redirect(struct dst_entry *dst) +{ +} + static inline unsigned int lwtunnel_headroom(struct lwtunnel_state *lwtstate, unsigned int mtu) { diff --git a/include/net/mac80211.h b/include/net/mac80211.h index c96511fa9198..2fd59ed3be00 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -6,6 +6,7 @@ * Copyright 2007-2010 Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright (C) 2015 - 2017 Intel Deutschland GmbH + * Copyright (C) 2018 Intel Corporation * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -934,6 +935,7 @@ struct ieee80211_tx_info { u8 ampdu_len; u8 antenna; u16 tx_time; + bool is_valid_ack_signal; void *status_driver_data[19 / sizeof(void *)]; } status; struct { @@ -1098,6 +1100,9 @@ ieee80211_tx_info_clear_status(struct ieee80211_tx_info *info) * the first subframe. * @RX_FLAG_ICV_STRIPPED: The ICV is stripped from this frame. CRC checking must * be done in the hardware. + * @RX_FLAG_AMPDU_EOF_BIT: Value of the EOF bit in the A-MPDU delimiter for this + * frame + * @RX_FLAG_AMPDU_EOF_BIT_KNOWN: The EOF value is known */ enum mac80211_rx_flags { RX_FLAG_MMIC_ERROR = BIT(0), @@ -1124,6 +1129,8 @@ enum mac80211_rx_flags { RX_FLAG_MIC_STRIPPED = BIT(21), RX_FLAG_ALLOW_SAME_PN = BIT(22), RX_FLAG_ICV_STRIPPED = BIT(23), + RX_FLAG_AMPDU_EOF_BIT = BIT(24), + RX_FLAG_AMPDU_EOF_BIT_KNOWN = BIT(25), }; /** @@ -2063,6 +2070,14 @@ struct ieee80211_txq { * @IEEE80211_HW_SUPPORTS_TDLS_BUFFER_STA: Hardware supports buffer STA on * TDLS links. * + * @IEEE80211_HW_DEAUTH_NEED_MGD_TX_PREP: The driver requires the + * mgd_prepare_tx() callback to be called before transmission of a + * deauthentication frame in case the association was completed but no + * beacon was heard. This is required in multi-channel scenarios, where the + * virtual interface might not be given air time for the transmission of + * the frame, as it is not synced with the AP/P2P GO yet, and thus the + * deauthentication frame might not be transmitted. + * * @NUM_IEEE80211_HW_FLAGS: number of hardware flags, used for sizing arrays */ enum ieee80211_hw_flags { @@ -2106,6 +2121,7 @@ enum ieee80211_hw_flags { IEEE80211_HW_REPORTS_LOW_ACK, IEEE80211_HW_SUPPORTS_TX_FRAG, IEEE80211_HW_SUPPORTS_TDLS_BUFFER_STA, + IEEE80211_HW_DEAUTH_NEED_MGD_TX_PREP, /* keep last, obviously */ NUM_IEEE80211_HW_FLAGS @@ -3350,6 +3366,9 @@ enum ieee80211_reconfig_type { * management frame prior to having successfully associated to allow the * driver to give it channel time for the transmission, to get a response * and to be able to synchronize with the GO. + * For drivers that set %IEEE80211_HW_DEAUTH_NEED_MGD_TX_PREP, mac80211 + * would also call this function before transmitting a deauthentication + * frame in case that no beacon was heard from the AP/P2P GO. * The callback will be called before each transmission and upon return * mac80211 will transmit the frame right away. * The callback is optional and can (should!) sleep. diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index f306b2aa15a4..d4417495773a 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -59,8 +59,12 @@ struct net { atomic64_t cookie_gen; struct list_head list; /* list of network namespaces */ - struct list_head cleanup_list; /* namespaces on death row */ - struct list_head exit_list; /* Use only net_mutex */ + struct list_head exit_list; /* To linked to call pernet exit + * methods on dead net (net_sem + * read locked), or to unregister + * pernet ops (net_sem wr locked). + */ + struct llist_node cleanup_list; /* namespaces on death row */ struct user_namespace *user_ns; /* Owning user namespace */ struct ucounts *ucounts; @@ -89,7 +93,7 @@ struct net { /* core fib_rules */ struct list_head rules_ops; - struct list_head fib_notifier_ops; /* protected by net_mutex */ + struct list_head fib_notifier_ops; /* protected by net_sem */ struct net_device *loopback_dev; /* The loopback */ struct netns_core core; @@ -313,6 +317,12 @@ struct pernet_operations { void (*exit_batch)(struct list_head *net_exit_list); unsigned int *id; size_t size; + /* + * Indicates above methods are allowed to be executed in parallel + * with methods of any other pernet_operations, i.e. they are not + * need write locked net_sem. + */ + bool async; }; /* diff --git a/include/net/netevent.h b/include/net/netevent.h index 40e7bab68490..d9918261701c 100644 --- a/include/net/netevent.h +++ b/include/net/netevent.h @@ -26,7 +26,8 @@ enum netevent_notif_type { NETEVENT_NEIGH_UPDATE = 1, /* arg is struct neighbour ptr */ NETEVENT_REDIRECT, /* arg is struct netevent_redirect ptr */ NETEVENT_DELAY_PROBE_TIME_UPDATE, /* arg is struct neigh_parms ptr */ - NETEVENT_MULTIPATH_HASH_UPDATE, /* arg is struct net ptr */ + NETEVENT_IPV4_MPATH_HASH_UPDATE, /* arg is struct net ptr */ + NETEVENT_IPV6_MPATH_HASH_UPDATE, /* arg is struct net ptr */ }; int register_netevent_notifier(struct notifier_block *nb); diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index 44668c29701a..3a970e429ab6 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -52,6 +52,7 @@ struct netns_ipv4 { #ifdef CONFIG_IP_MULTIPLE_TABLES struct fib_rules_ops *rules_ops; bool fib_has_custom_rules; + unsigned int fib_rules_require_fldissect; struct fib_table __rcu *fib_main; struct fib_table __rcu *fib_default; #endif diff --git a/include/net/netns/ipv6.h b/include/net/netns/ipv6.h index 987cc4569cb8..5b51110435fc 100644 --- a/include/net/netns/ipv6.h +++ b/include/net/netns/ipv6.h @@ -28,6 +28,7 @@ struct netns_sysctl_ipv6 { int ip6_rt_gc_elasticity; int ip6_rt_mtu_expires; int ip6_rt_min_advmss; + int multipath_hash_policy; int flowlabel_consistency; int auto_flowlabels; int icmpv6_time; @@ -71,7 +72,8 @@ struct netns_ipv6 { unsigned int ip6_rt_gc_expire; unsigned long ip6_rt_last_gc; #ifdef CONFIG_IPV6_MULTIPLE_TABLES - bool fib6_has_custom_rules; + unsigned int fib6_rules_require_fldissect; + bool fib6_has_custom_rules; struct rt6_info *ip6_prohibit_entry; struct rt6_info *ip6_blk_hole_entry; struct fib6_table *fib6_local_tbl; @@ -84,7 +86,7 @@ struct netns_ipv6 { struct sock *mc_autojoin_sk; #ifdef CONFIG_IPV6_MROUTE #ifndef CONFIG_IPV6_MROUTE_MULTIPLE_TABLES - struct mr6_table *mrt6; + struct mr_table *mrt6; #else struct list_head mr6_tables; struct fib_rules_ops *mr6_rules_ops; diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index 87406252f0a3..e828d31be5da 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -806,6 +806,7 @@ enum tc_prio_command { TC_PRIO_REPLACE, TC_PRIO_DESTROY, TC_PRIO_STATS, + TC_PRIO_GRAFT, }; struct tc_prio_qopt_offload_params { @@ -818,6 +819,11 @@ struct tc_prio_qopt_offload_params { struct gnet_stats_queue *qstats; }; +struct tc_prio_qopt_offload_graft_params { + u8 band; + u32 child_handle; +}; + struct tc_prio_qopt_offload { enum tc_prio_command command; u32 handle; @@ -825,6 +831,8 @@ struct tc_prio_qopt_offload { union { struct tc_prio_qopt_offload_params replace_params; struct tc_qopt_offload_stats stats; + struct tc_prio_qopt_offload_graft_params graft_params; }; }; + #endif diff --git a/include/net/route.h b/include/net/route.h index 1eb9ce470e25..158833ea7988 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -65,8 +65,6 @@ struct rtable { /* Miscellaneous cached information */ u32 rt_pmtu; - u32 rt_table_id; - struct list_head rt_uncached; struct uncached_list *rt_uncached_list; }; diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index e2ab13687fb9..d4907b584b38 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -540,7 +540,7 @@ static inline bool skb_skip_tc_classify(struct sk_buff *skb) return false; } -/* Reset all TX qdiscs greater then index of a device. */ +/* Reset all TX qdiscs greater than index of a device. */ static inline void qdisc_reset_all_tx_gt(struct net_device *dev, unsigned int i) { struct Qdisc *qdisc; diff --git a/include/net/sock.h b/include/net/sock.h index 169c92afcafa..b9624581d639 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -417,6 +417,7 @@ struct sock { struct page_frag sk_frag; netdev_features_t sk_route_caps; netdev_features_t sk_route_nocaps; + netdev_features_t sk_route_forced_caps; int sk_gso_type; unsigned int sk_gso_max_size; gfp_t sk_allocation; @@ -1584,7 +1585,7 @@ int sock_no_bind(struct socket *, struct sockaddr *, int); int sock_no_connect(struct socket *, struct sockaddr *, int, int); int sock_no_socketpair(struct socket *, struct socket *); int sock_no_accept(struct socket *, struct socket *, int, bool); -int sock_no_getname(struct socket *, struct sockaddr *, int *, int); +int sock_no_getname(struct socket *, struct sockaddr *, int); __poll_t sock_no_poll(struct file *, struct socket *, struct poll_table_struct *); int sock_no_ioctl(struct socket *, unsigned int, unsigned long); @@ -1862,15 +1863,6 @@ static inline void sk_nocaps_add(struct sock *sk, netdev_features_t flags) sk->sk_route_caps &= ~flags; } -static inline bool sk_check_csum_caps(struct sock *sk) -{ - return (sk->sk_route_caps & NETIF_F_HW_CSUM) || - (sk->sk_family == PF_INET && - (sk->sk_route_caps & NETIF_F_IP_CSUM)) || - (sk->sk_family == PF_INET6 && - (sk->sk_route_caps & NETIF_F_IPV6_CSUM)); -} - static inline int skb_do_copy_data_nocache(struct sock *sk, struct sk_buff *skb, struct iov_iter *from, char *to, int copy, int offset) diff --git a/include/net/tcp.h b/include/net/tcp.h index e3fc667f9ac2..9c9b3768b350 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -374,7 +374,8 @@ enum tcp_tw_status tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb, const struct tcphdr *th); struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, - struct request_sock *req, bool fastopen); + struct request_sock *req, bool fastopen, + bool *lost_race); int tcp_child_process(struct sock *parent, struct sock *child, struct sk_buff *skb); void tcp_enter_loss(struct sock *sk); @@ -510,8 +511,6 @@ __u32 cookie_v6_init_sequence(const struct sk_buff *skb, __u16 *mss); #endif /* tcp_output.c */ -u32 tcp_tso_autosize(const struct sock *sk, unsigned int mss_now, - int min_tso_segs); void __tcp_push_pending_frames(struct sock *sk, unsigned int cur_mss, int nonagle); int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs); @@ -980,8 +979,8 @@ struct tcp_congestion_ops { u32 (*undo_cwnd)(struct sock *sk); /* hook for packet ack accounting (optional) */ void (*pkts_acked)(struct sock *sk, const struct ack_sample *sample); - /* suggest number of segments for each skb to transmit (optional) */ - u32 (*tso_segs_goal)(struct sock *sk); + /* override sysctl_tcp_min_tso_segs */ + u32 (*min_tso_segs)(struct sock *sk); /* returns the multiplier used in tcp_sndbuf_expand (optional) */ u32 (*sndbuf_expand)(struct sock *sk); /* call when packets are delivered to update cwnd and pacing rate, diff --git a/include/net/tcp_states.h b/include/net/tcp_states.h index 50e78a74d0df..2875e169d744 100644 --- a/include/net/tcp_states.h +++ b/include/net/tcp_states.h @@ -32,21 +32,21 @@ enum { #define TCP_STATE_MASK 0xF -#define TCP_ACTION_FIN (1 << 7) +#define TCP_ACTION_FIN (1 << TCP_CLOSE) enum { - TCPF_ESTABLISHED = (1 << 1), - TCPF_SYN_SENT = (1 << 2), - TCPF_SYN_RECV = (1 << 3), - TCPF_FIN_WAIT1 = (1 << 4), - TCPF_FIN_WAIT2 = (1 << 5), - TCPF_TIME_WAIT = (1 << 6), - TCPF_CLOSE = (1 << 7), - TCPF_CLOSE_WAIT = (1 << 8), - TCPF_LAST_ACK = (1 << 9), - TCPF_LISTEN = (1 << 10), - TCPF_CLOSING = (1 << 11), - TCPF_NEW_SYN_RECV = (1 << 12), + TCPF_ESTABLISHED = (1 << TCP_ESTABLISHED), + TCPF_SYN_SENT = (1 << TCP_SYN_SENT), + TCPF_SYN_RECV = (1 << TCP_SYN_RECV), + TCPF_FIN_WAIT1 = (1 << TCP_FIN_WAIT1), + TCPF_FIN_WAIT2 = (1 << TCP_FIN_WAIT2), + TCPF_TIME_WAIT = (1 << TCP_TIME_WAIT), + TCPF_CLOSE = (1 << TCP_CLOSE), + TCPF_CLOSE_WAIT = (1 << TCP_CLOSE_WAIT), + TCPF_LAST_ACK = (1 << TCP_LAST_ACK), + TCPF_LISTEN = (1 << TCP_LISTEN), + TCPF_CLOSING = (1 << TCP_CLOSING), + TCPF_NEW_SYN_RECV = (1 << TCP_NEW_SYN_RECV), }; #endif /* _LINUX_TCP_STATES_H */ diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 7d2077665c0b..aa027ba1d032 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -1267,12 +1267,12 @@ static inline void xfrm_sk_free_policy(struct sock *sk) static inline void xfrm_sk_free_policy(struct sock *sk) {} static inline int xfrm_sk_clone_policy(struct sock *sk, const struct sock *osk) { return 0; } -static inline int xfrm6_route_forward(struct sk_buff *skb) { return 1; } -static inline int xfrm4_route_forward(struct sk_buff *skb) { return 1; } +static inline int xfrm6_route_forward(struct sk_buff *skb) { return 1; } +static inline int xfrm4_route_forward(struct sk_buff *skb) { return 1; } static inline int xfrm6_policy_check(struct sock *sk, int dir, struct sk_buff *skb) -{ - return 1; -} +{ + return 1; +} static inline int xfrm4_policy_check(struct sock *sk, int dir, struct sk_buff *skb) { return 1; @@ -1356,7 +1356,7 @@ __xfrm6_state_addr_check(const struct xfrm_state *x, { if (ipv6_addr_equal((struct in6_addr *)daddr, (struct in6_addr *)&x->id.daddr) && (ipv6_addr_equal((struct in6_addr *)saddr, (struct in6_addr *)&x->props.saddr) || - ipv6_addr_any((struct in6_addr *)saddr) || + ipv6_addr_any((struct in6_addr *)saddr) || ipv6_addr_any((struct in6_addr *)&x->props.saddr))) return 1; return 0; @@ -1666,7 +1666,7 @@ int xfrm_user_policy(struct sock *sk, int optname, static inline int xfrm_user_policy(struct sock *sk, int optname, u8 __user *optval, int optlen) { return -ENOPROTOOPT; -} +} static inline int xfrm4_udp_encap_rcv(struct sock *sk, struct sk_buff *skb) { diff --git a/include/uapi/linux/batadv_packet.h b/include/uapi/linux/batadv_packet.h index 5cb360be2a11..894d8d2f713d 100644 --- a/include/uapi/linux/batadv_packet.h +++ b/include/uapi/linux/batadv_packet.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: (GPL-2.0 WITH Linux-syscall-note) */ -/* Copyright (C) 2007-2017 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2018 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * @@ -196,8 +196,6 @@ struct batadv_bla_claim_dst { __be16 group; /* group id */ }; -#pragma pack() - /** * struct batadv_ogm_packet - ogm (routing protocol) packet * @packet_type: batman-adv packet type, part of the general header @@ -222,9 +220,6 @@ struct batadv_ogm_packet { __u8 reserved; __u8 tq; __be16 tvlv_len; - /* __packed is not needed as the struct size is divisible by 4, - * and the largest data type in this struct has a size of 4. - */ }; #define BATADV_OGM_HLEN sizeof(struct batadv_ogm_packet) @@ -249,9 +244,6 @@ struct batadv_ogm2_packet { __u8 orig[ETH_ALEN]; __be16 tvlv_len; __be32 throughput; - /* __packed is not needed as the struct size is divisible by 4, - * and the largest data type in this struct has a size of 4. - */ }; #define BATADV_OGM2_HLEN sizeof(struct batadv_ogm2_packet) @@ -405,7 +397,6 @@ struct batadv_icmp_packet_rr { * misalignment of the payload after the ethernet header. It may also lead to * leakage of information when the padding it not initialized before sending. */ -#pragma pack(2) /** * struct batadv_unicast_packet - unicast packet for network payload @@ -533,8 +524,6 @@ struct batadv_coded_packet { __be16 coded_len; }; -#pragma pack() - /** * struct batadv_unicast_tvlv_packet - generic unicast packet with tvlv payload * @packet_type: batman-adv packet type, part of the general header @@ -641,4 +630,6 @@ struct batadv_tvlv_mcast_data { __u8 reserved[3]; }; +#pragma pack() + #endif /* _UAPI_LINUX_BATADV_PACKET_H_ */ diff --git a/include/uapi/linux/batman_adv.h b/include/uapi/linux/batman_adv.h index ae00c99cbed0..56ae28934070 100644 --- a/include/uapi/linux/batman_adv.h +++ b/include/uapi/linux/batman_adv.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: MIT */ -/* Copyright (C) 2016-2017 B.A.T.M.A.N. contributors: +/* Copyright (C) 2016-2018 B.A.T.M.A.N. contributors: * * Matthias Schiffer * diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index db6bdc375126..2a66769e5875 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -800,6 +800,7 @@ enum bpf_func_id { /* BPF_FUNC_skb_set_tunnel_key flags. */ #define BPF_F_ZERO_CSUM_TX (1ULL << 1) #define BPF_F_DONT_FRAGMENT (1ULL << 2) +#define BPF_F_SEQ_NUMBER (1ULL << 3) /* BPF_FUNC_perf_event_output, BPF_FUNC_perf_event_read and * BPF_FUNC_perf_event_read_value flags. diff --git a/include/uapi/linux/fib_rules.h b/include/uapi/linux/fib_rules.h index 2b642bf9b5a0..232df14e1287 100644 --- a/include/uapi/linux/fib_rules.h +++ b/include/uapi/linux/fib_rules.h @@ -23,7 +23,7 @@ struct fib_rule_hdr { __u8 tos; __u8 table; - __u8 res1; /* reserved */ + __u8 res1; /* reserved */ __u8 res2; /* reserved */ __u8 action; @@ -35,6 +35,11 @@ struct fib_rule_uid_range { __u32 end; }; +struct fib_rule_port_range { + __u16 start; + __u16 end; +}; + enum { FRA_UNSPEC, FRA_DST, /* destination address */ @@ -58,6 +63,10 @@ enum { FRA_PAD, FRA_L3MDEV, /* iif or oif is l3mdev goto its table */ FRA_UID_RANGE, /* UID range */ + FRA_PROTOCOL, /* Originator of the rule */ + FRA_IP_PROTO, /* ip proto */ + FRA_SPORT_RANGE, /* sport */ + FRA_DPORT_RANGE, /* dport */ __FRA_MAX }; diff --git a/include/uapi/linux/if_ether.h b/include/uapi/linux/if_ether.h index 8bbbcb5cd94b..2e4a6c1accaa 100644 --- a/include/uapi/linux/if_ether.h +++ b/include/uapi/linux/if_ether.h @@ -88,6 +88,7 @@ #define ETH_P_AOE 0x88A2 /* ATA over Ethernet */ #define ETH_P_8021AD 0x88A8 /* 802.1ad Service VLAN */ #define ETH_P_802_EX1 0x88B5 /* 802.1 Local Experimental 1. */ +#define ETH_P_PREAUTH 0x88C7 /* 802.11 Preauthentication */ #define ETH_P_TIPC 0x88CA /* TIPC */ #define ETH_P_MACSEC 0x88E5 /* 802.1ae MACsec */ #define ETH_P_8021AH 0x88E7 /* 802.1ah Backbone Service Tag */ diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 6d9447700e18..11d0c0ea2bfa 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -941,4 +941,22 @@ enum { IFLA_EVENT_BONDING_OPTIONS, /* change in bonding options */ }; +/* tun section */ + +enum { + IFLA_TUN_UNSPEC, + IFLA_TUN_OWNER, + IFLA_TUN_GROUP, + IFLA_TUN_TYPE, + IFLA_TUN_PI, + IFLA_TUN_VNET_HDR, + IFLA_TUN_PERSIST, + IFLA_TUN_MULTI_QUEUE, + IFLA_TUN_NUM_QUEUES, + IFLA_TUN_NUM_DISABLED_QUEUES, + __IFLA_TUN_MAX, +}; + +#define IFLA_TUN_MAX (__IFLA_TUN_MAX - 1) + #endif /* _UAPI_LINUX_IF_LINK_H */ diff --git a/include/uapi/linux/ncsi.h b/include/uapi/linux/ncsi.h new file mode 100644 index 000000000000..4c292ecbb748 --- /dev/null +++ b/include/uapi/linux/ncsi.h @@ -0,0 +1,115 @@ +/* + * Copyright Samuel Mendoza-Jonas, IBM Corporation 2018. + * + * 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_NCSI_NETLINK_H__ +#define __UAPI_NCSI_NETLINK_H__ + +/** + * enum ncsi_nl_commands - supported NCSI commands + * + * @NCSI_CMD_UNSPEC: unspecified command to catch errors + * @NCSI_CMD_PKG_INFO: list package and channel attributes. Requires + * NCSI_ATTR_IFINDEX. If NCSI_ATTR_PACKAGE_ID is specified returns the + * specific package and its channels - otherwise a dump request returns + * all packages and their associated channels. + * @NCSI_CMD_SET_INTERFACE: set preferred package and channel combination. + * Requires NCSI_ATTR_IFINDEX and the preferred NCSI_ATTR_PACKAGE_ID and + * optionally the preferred NCSI_ATTR_CHANNEL_ID. + * @NCSI_CMD_CLEAR_INTERFACE: clear any preferred package/channel combination. + * Requires NCSI_ATTR_IFINDEX. + * @NCSI_CMD_MAX: highest command number + */ +enum ncsi_nl_commands { + NCSI_CMD_UNSPEC, + NCSI_CMD_PKG_INFO, + NCSI_CMD_SET_INTERFACE, + NCSI_CMD_CLEAR_INTERFACE, + + __NCSI_CMD_AFTER_LAST, + NCSI_CMD_MAX = __NCSI_CMD_AFTER_LAST - 1 +}; + +/** + * enum ncsi_nl_attrs - General NCSI netlink attributes + * + * @NCSI_ATTR_UNSPEC: unspecified attributes to catch errors + * @NCSI_ATTR_IFINDEX: ifindex of network device using NCSI + * @NCSI_ATTR_PACKAGE_LIST: nested array of NCSI_PKG_ATTR attributes + * @NCSI_ATTR_PACKAGE_ID: package ID + * @NCSI_ATTR_CHANNEL_ID: channel ID + * @NCSI_ATTR_MAX: highest attribute number + */ +enum ncsi_nl_attrs { + NCSI_ATTR_UNSPEC, + NCSI_ATTR_IFINDEX, + NCSI_ATTR_PACKAGE_LIST, + NCSI_ATTR_PACKAGE_ID, + NCSI_ATTR_CHANNEL_ID, + + __NCSI_ATTR_AFTER_LAST, + NCSI_ATTR_MAX = __NCSI_ATTR_AFTER_LAST - 1 +}; + +/** + * enum ncsi_nl_pkg_attrs - NCSI netlink package-specific attributes + * + * @NCSI_PKG_ATTR_UNSPEC: unspecified attributes to catch errors + * @NCSI_PKG_ATTR: nested array of package attributes + * @NCSI_PKG_ATTR_ID: package ID + * @NCSI_PKG_ATTR_FORCED: flag signifying a package has been set as preferred + * @NCSI_PKG_ATTR_CHANNEL_LIST: nested array of NCSI_CHANNEL_ATTR attributes + * @NCSI_PKG_ATTR_MAX: highest attribute number + */ +enum ncsi_nl_pkg_attrs { + NCSI_PKG_ATTR_UNSPEC, + NCSI_PKG_ATTR, + NCSI_PKG_ATTR_ID, + NCSI_PKG_ATTR_FORCED, + NCSI_PKG_ATTR_CHANNEL_LIST, + + __NCSI_PKG_ATTR_AFTER_LAST, + NCSI_PKG_ATTR_MAX = __NCSI_PKG_ATTR_AFTER_LAST - 1 +}; + +/** + * enum ncsi_nl_channel_attrs - NCSI netlink channel-specific attributes + * + * @NCSI_CHANNEL_ATTR_UNSPEC: unspecified attributes to catch errors + * @NCSI_CHANNEL_ATTR: nested array of channel attributes + * @NCSI_CHANNEL_ATTR_ID: channel ID + * @NCSI_CHANNEL_ATTR_VERSION_MAJOR: channel major version number + * @NCSI_CHANNEL_ATTR_VERSION_MINOR: channel minor version number + * @NCSI_CHANNEL_ATTR_VERSION_STR: channel version string + * @NCSI_CHANNEL_ATTR_LINK_STATE: channel link state flags + * @NCSI_CHANNEL_ATTR_ACTIVE: channels with this flag are in + * NCSI_CHANNEL_ACTIVE state + * @NCSI_CHANNEL_ATTR_FORCED: flag signifying a channel has been set as + * preferred + * @NCSI_CHANNEL_ATTR_VLAN_LIST: nested array of NCSI_CHANNEL_ATTR_VLAN_IDs + * @NCSI_CHANNEL_ATTR_VLAN_ID: VLAN ID being filtered on this channel + * @NCSI_CHANNEL_ATTR_MAX: highest attribute number + */ +enum ncsi_nl_channel_attrs { + NCSI_CHANNEL_ATTR_UNSPEC, + NCSI_CHANNEL_ATTR, + NCSI_CHANNEL_ATTR_ID, + NCSI_CHANNEL_ATTR_VERSION_MAJOR, + NCSI_CHANNEL_ATTR_VERSION_MINOR, + NCSI_CHANNEL_ATTR_VERSION_STR, + NCSI_CHANNEL_ATTR_LINK_STATE, + NCSI_CHANNEL_ATTR_ACTIVE, + NCSI_CHANNEL_ATTR_FORCED, + NCSI_CHANNEL_ATTR_VLAN_LIST, + NCSI_CHANNEL_ATTR_VLAN_ID, + + __NCSI_CHANNEL_ATTR_AFTER_LAST, + NCSI_CHANNEL_ATTR_MAX = __NCSI_CHANNEL_ATTR_AFTER_LAST - 1 +}; + +#endif /* __UAPI_NCSI_NETLINK_H__ */ diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index c587a61c32bf..c13c84304be3 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -992,6 +992,32 @@ * * @NL80211_CMD_RELOAD_REGDB: Request that the regdb firmware file is reloaded. * + * @NL80211_CMD_EXTERNAL_AUTH: This interface is exclusively defined for host + * drivers that do not define separate commands for authentication and + * association, but rely on user space for the authentication to happen. + * This interface acts both as the event request (driver to user space) + * to trigger the authentication and command response (userspace to + * driver) to indicate the authentication status. + * + * User space uses the %NL80211_CMD_CONNECT command to the host driver to + * trigger a connection. The host driver selects a BSS and further uses + * this interface to offload only the authentication part to the user + * space. Authentication frames are passed between the driver and user + * space through the %NL80211_CMD_FRAME interface. Host driver proceeds + * further with the association after getting successful authentication + * status. User space indicates the authentication status through + * %NL80211_ATTR_STATUS_CODE attribute in %NL80211_CMD_EXTERNAL_AUTH + * command interface. + * + * Host driver reports this status on an authentication failure to the + * user space through the connect result as the user space would have + * initiated the connection through the connect request. + * + * @NL80211_CMD_STA_OPMODE_CHANGED: An event that notify station's + * ht opmode or vht opmode changes using any of &NL80211_ATTR_SMPS_MODE, + * &NL80211_ATTR_CHANNEL_WIDTH,&NL80211_ATTR_NSS attributes with its + * address(specified in &NL80211_ATTR_MAC). + * * @NL80211_CMD_MAX: highest used command number * @__NL80211_CMD_AFTER_LAST: internal use */ @@ -1198,6 +1224,10 @@ enum nl80211_commands { NL80211_CMD_RELOAD_REGDB, + NL80211_CMD_EXTERNAL_AUTH, + + NL80211_CMD_STA_OPMODE_CHANGED, + /* add new commands above here */ /* used to define NL80211_CMD_MAX below */ @@ -2153,6 +2183,19 @@ enum nl80211_commands { * @NL80211_ATTR_PMKR0_NAME: PMK-R0 Name for offloaded FT. * @NL80211_ATTR_PORT_AUTHORIZED: (reserved) * + * @NL80211_ATTR_EXTERNAL_AUTH_ACTION: Identify the requested external + * authentication operation (u32 attribute with an + * &enum nl80211_external_auth_action value). This is used with the + * &NL80211_CMD_EXTERNAL_AUTH request event. + * @NL80211_ATTR_EXTERNAL_AUTH_SUPPORT: Flag attribute indicating that the user + * space supports external authentication. This attribute shall be used + * only with %NL80211_CMD_CONNECT request. The driver may offload + * authentication processing to user space if this capability is indicated + * in NL80211_CMD_CONNECT requests from the user space. + * + * @NL80211_ATTR_NSS: Station's New/updated RX_NSS value notified using this + * u8 attribute. This is used with %NL80211_CMD_STA_OPMODE_CHANGED. + * * @NUM_NL80211_ATTR: total number of nl80211_attrs available * @NL80211_ATTR_MAX: highest attribute number currently defined * @__NL80211_ATTR_AFTER_LAST: internal use @@ -2579,6 +2622,12 @@ enum nl80211_attrs { NL80211_ATTR_PMKR0_NAME, NL80211_ATTR_PORT_AUTHORIZED, + NL80211_ATTR_EXTERNAL_AUTH_ACTION, + NL80211_ATTR_EXTERNAL_AUTH_SUPPORT, + + NL80211_ATTR_NSS, + NL80211_ATTR_ACK_SIGNAL, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, @@ -2899,6 +2948,7 @@ enum nl80211_sta_bss_param { * @NL80211_STA_INFO_RX_DURATION: aggregate PPDU duration for all frames * received from the station (u64, usec) * @NL80211_STA_INFO_PAD: attribute used for padding for 64-bit alignment + * @NL80211_STA_INFO_ACK_SIGNAL: signal strength of the last ACK frame(u8, dBm) * @__NL80211_STA_INFO_AFTER_LAST: internal * @NL80211_STA_INFO_MAX: highest possible station info attribute */ @@ -2937,6 +2987,7 @@ enum nl80211_sta_info { NL80211_STA_INFO_TID_STATS, NL80211_STA_INFO_RX_DURATION, NL80211_STA_INFO_PAD, + NL80211_STA_INFO_ACK_SIGNAL, /* keep last */ __NL80211_STA_INFO_AFTER_LAST, @@ -4945,6 +4996,9 @@ enum nl80211_feature_flags { * probe request tx deferral and suppression * @NL80211_EXT_FEATURE_MFP_OPTIONAL: Driver supports the %NL80211_MFP_OPTIONAL * value in %NL80211_ATTR_USE_MFP. + * @NL80211_EXT_FEATURE_LOW_SPAN_SCAN: Driver supports low span scan. + * @NL80211_EXT_FEATURE_LOW_POWER_SCAN: Driver supports low power scan. + * @NL80211_EXT_FEATURE_HIGH_ACCURACY_SCAN: Driver supports high accuracy scan. * * @NUM_NL80211_EXT_FEATURES: number of extended features. * @MAX_NL80211_EXT_FEATURES: highest extended feature index. @@ -4972,6 +5026,9 @@ enum nl80211_ext_feature_index { NL80211_EXT_FEATURE_OCE_PROBE_REQ_HIGH_TX_RATE, NL80211_EXT_FEATURE_OCE_PROBE_REQ_DEFERRAL_SUPPRESSION, NL80211_EXT_FEATURE_MFP_OPTIONAL, + NL80211_EXT_FEATURE_LOW_SPAN_SCAN, + NL80211_EXT_FEATURE_LOW_POWER_SCAN, + NL80211_EXT_FEATURE_HIGH_ACCURACY_SCAN, /* add new features before the definition below */ NUM_NL80211_EXT_FEATURES, @@ -5032,6 +5089,10 @@ enum nl80211_timeout_reason { * of NL80211_CMD_TRIGGER_SCAN and NL80211_CMD_START_SCHED_SCAN * requests. * + * NL80211_SCAN_FLAG_LOW_SPAN, NL80211_SCAN_FLAG_LOW_POWER, and + * NL80211_SCAN_FLAG_HIGH_ACCURACY flags are exclusive of each other, i.e., only + * one of them can be used in the request. + * * @NL80211_SCAN_FLAG_LOW_PRIORITY: scan request has low priority * @NL80211_SCAN_FLAG_FLUSH: flush cache before scanning * @NL80211_SCAN_FLAG_AP: force a scan even if the interface is configured @@ -5059,7 +5120,20 @@ enum nl80211_timeout_reason { * and suppression (if it has received a broadcast Probe Response frame, * Beacon frame or FILS Discovery frame from an AP that the STA considers * a suitable candidate for (re-)association - suitable in terms of - * SSID and/or RSSI + * SSID and/or RSSI. + * @NL80211_SCAN_FLAG_LOW_SPAN: Span corresponds to the total time taken to + * accomplish the scan. Thus, this flag intends the driver to perform the + * scan request with lesser span/duration. It is specific to the driver + * implementations on how this is accomplished. Scan accuracy may get + * impacted with this flag. + * @NL80211_SCAN_FLAG_LOW_POWER: This flag intends the scan attempts to consume + * optimal possible power. Drivers can resort to their specific means to + * optimize the power. Scan accuracy may get impacted with this flag. + * @NL80211_SCAN_FLAG_HIGH_ACCURACY: Accuracy here intends to the extent of scan + * results obtained. Thus HIGH_ACCURACY scan flag aims to get maximum + * possible scan results. This flag hints the driver to use the best + * possible scan configuration to improve the accuracy in scanning. + * Latency and power use may get impacted with this flag. */ enum nl80211_scan_flags { NL80211_SCAN_FLAG_LOW_PRIORITY = 1<<0, @@ -5070,6 +5144,9 @@ enum nl80211_scan_flags { NL80211_SCAN_FLAG_ACCEPT_BCAST_PROBE_RESP = 1<<5, NL80211_SCAN_FLAG_OCE_PROBE_REQ_HIGH_TX_RATE = 1<<6, NL80211_SCAN_FLAG_OCE_PROBE_REQ_DEFERRAL_SUPPRESSION = 1<<7, + NL80211_SCAN_FLAG_LOW_SPAN = 1<<8, + NL80211_SCAN_FLAG_LOW_POWER = 1<<9, + NL80211_SCAN_FLAG_HIGH_ACCURACY = 1<<10, }; /** @@ -5469,4 +5546,15 @@ enum nl80211_nan_match_attributes { NL80211_NAN_MATCH_ATTR_MAX = NUM_NL80211_NAN_MATCH_ATTR - 1 }; +/** + * nl80211_external_auth_action - Action to perform with external + * authentication request. Used by NL80211_ATTR_EXTERNAL_AUTH_ACTION. + * @NL80211_EXTERNAL_AUTH_START: Start the authentication. + * @NL80211_EXTERNAL_AUTH_ABORT: Abort the ongoing authentication. + */ +enum nl80211_external_auth_action { + NL80211_EXTERNAL_AUTH_START, + NL80211_EXTERNAL_AUTH_ABORT, +}; + #endif /* __LINUX_NL80211_H */ diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index 46c506615f4a..7cafb26df555 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -555,7 +555,8 @@ enum { #define TCF_EM_VLAN 6 #define TCF_EM_CANID 7 #define TCF_EM_IPSET 8 -#define TCF_EM_MAX 8 +#define TCF_EM_IPT 9 +#define TCF_EM_MAX 9 enum { TCF_EM_PROG_TC diff --git a/include/uapi/linux/rds.h b/include/uapi/linux/rds.h index e71d4491f225..a66b213de3d7 100644 --- a/include/uapi/linux/rds.h +++ b/include/uapi/linux/rds.h @@ -103,6 +103,8 @@ #define RDS_CMSG_MASKED_ATOMIC_FADD 8 #define RDS_CMSG_MASKED_ATOMIC_CSWP 9 #define RDS_CMSG_RXPATH_LATENCY 11 +#define RDS_CMSG_ZCOPY_COOKIE 12 +#define RDS_CMSG_ZCOPY_COMPLETION 13 #define RDS_INFO_FIRST 10000 #define RDS_INFO_COUNTERS 10000 @@ -316,6 +318,12 @@ struct rds_rdma_notify { #define RDS_RDMA_DROPPED 3 #define RDS_RDMA_OTHER_ERROR 4 +#define RDS_MAX_ZCOOKIES 8 +struct rds_zcopy_cookies { + __u32 num; + __u32 cookies[RDS_MAX_ZCOOKIES]; +}; + /* * Common set of flags for all RDMA related structs */ diff --git a/include/uapi/linux/tc_ematch/tc_em_ipt.h b/include/uapi/linux/tc_ematch/tc_em_ipt.h new file mode 100644 index 000000000000..49a65530992c --- /dev/null +++ b/include/uapi/linux/tc_ematch/tc_em_ipt.h @@ -0,0 +1,20 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef __LINUX_TC_EM_IPT_H +#define __LINUX_TC_EM_IPT_H + +#include <linux/types.h> +#include <linux/pkt_cls.h> + +enum { + TCA_EM_IPT_UNSPEC, + TCA_EM_IPT_HOOK, + TCA_EM_IPT_MATCH_NAME, + TCA_EM_IPT_MATCH_REVISION, + TCA_EM_IPT_NFPROTO, + TCA_EM_IPT_MATCH_DATA, + __TCA_EM_IPT_MAX +}; + +#define TCA_EM_IPT_MAX (__TCA_EM_IPT_MAX - 1) + +#endif diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h index b4a4f64635fa..4c0ae0faf7ca 100644 --- a/include/uapi/linux/tcp.h +++ b/include/uapi/linux/tcp.h @@ -241,6 +241,8 @@ enum { TCP_NLA_MIN_RTT, /* minimum RTT */ TCP_NLA_RECUR_RETRANS, /* Recurring retransmits for the current pkt */ TCP_NLA_DELIVERY_RATE_APP_LMT, /* delivery rate application limited ? */ + TCP_NLA_SNDQ_SIZE, /* Data (bytes) pending in send queue */ + TCP_NLA_CA_STATE, /* ca_state of socket */ }; diff --git a/kernel/audit.c b/kernel/audit.c index 227db99b0f19..5e49b614d0e6 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -1526,6 +1526,7 @@ static struct pernet_operations audit_net_ops __net_initdata = { .exit = audit_net_exit, .id = &audit_net_id, .size = sizeof(struct audit_net), + .async = true, }; /* Initialize audit support at boot time. */ diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index c6eff108aa99..eb79a34359c0 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -508,10 +508,6 @@ err: static const int caller_saved[CALLER_SAVED_REGS] = { BPF_REG_0, BPF_REG_1, BPF_REG_2, BPF_REG_3, BPF_REG_4, BPF_REG_5 }; -#define CALLEE_SAVED_REGS 5 -static const int callee_saved[CALLEE_SAVED_REGS] = { - BPF_REG_6, BPF_REG_7, BPF_REG_8, BPF_REG_9 -}; static void __mark_reg_not_init(struct bpf_reg_state *reg); diff --git a/lib/kobject_uevent.c b/lib/kobject_uevent.c index 9fe6ec8fda28..9539d7ab3ea8 100644 --- a/lib/kobject_uevent.c +++ b/lib/kobject_uevent.c @@ -650,6 +650,7 @@ found: static struct pernet_operations uevent_net_ops = { .init = uevent_net_init, .exit = uevent_net_exit, + .async = true, }; static int __init kobject_uevent_init(void) diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index bad01b14a4ad..bd0ed39f65fb 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -729,6 +729,7 @@ static struct pernet_operations vlan_net_ops = { .exit = vlan_exit_net, .id = &vlan_net_id, .size = sizeof(struct vlan_net), + .async = true, }; static int __init vlan_proto_init(void) diff --git a/net/appletalk/ddp.c b/net/appletalk/ddp.c index 03a9fc0771c0..9b6bc5abe946 100644 --- a/net/appletalk/ddp.c +++ b/net/appletalk/ddp.c @@ -1238,7 +1238,7 @@ out: * fields into the sockaddr. */ static int atalk_getname(struct socket *sock, struct sockaddr *uaddr, - int *uaddr_len, int peer) + int peer) { struct sockaddr_at sat; struct sock *sk = sock->sk; @@ -1251,7 +1251,6 @@ static int atalk_getname(struct socket *sock, struct sockaddr *uaddr, if (atalk_autobind(sk) < 0) goto out; - *uaddr_len = sizeof(struct sockaddr_at); memset(&sat, 0, sizeof(sat)); if (peer) { @@ -1268,9 +1267,9 @@ static int atalk_getname(struct socket *sock, struct sockaddr *uaddr, sat.sat_port = at->src_port; } - err = 0; sat.sat_family = AF_APPLETALK; memcpy(uaddr, &sat, sizeof(sat)); + err = sizeof(struct sockaddr_at); out: release_sock(sk); diff --git a/net/atm/pvc.c b/net/atm/pvc.c index e1140b3bdcaa..2cb10af16afc 100644 --- a/net/atm/pvc.c +++ b/net/atm/pvc.c @@ -87,21 +87,20 @@ static int pvc_getsockopt(struct socket *sock, int level, int optname, } static int pvc_getname(struct socket *sock, struct sockaddr *sockaddr, - int *sockaddr_len, int peer) + int peer) { struct sockaddr_atmpvc *addr; struct atm_vcc *vcc = ATM_SD(sock); if (!vcc->dev || !test_bit(ATM_VF_ADDR, &vcc->flags)) return -ENOTCONN; - *sockaddr_len = sizeof(struct sockaddr_atmpvc); addr = (struct sockaddr_atmpvc *)sockaddr; memset(addr, 0, sizeof(*addr)); addr->sap_family = AF_ATMPVC; addr->sap_addr.itf = vcc->dev->number; addr->sap_addr.vpi = vcc->vpi; addr->sap_addr.vci = vcc->vci; - return 0; + return sizeof(struct sockaddr_atmpvc); } static const struct proto_ops pvc_proto_ops = { diff --git a/net/atm/svc.c b/net/atm/svc.c index c458adcbc177..2f91b766ac42 100644 --- a/net/atm/svc.c +++ b/net/atm/svc.c @@ -419,15 +419,14 @@ out: } static int svc_getname(struct socket *sock, struct sockaddr *sockaddr, - int *sockaddr_len, int peer) + int peer) { struct sockaddr_atmsvc *addr; - *sockaddr_len = sizeof(struct sockaddr_atmsvc); addr = (struct sockaddr_atmsvc *) sockaddr; memcpy(addr, peer ? &ATM_SD(sock)->remote : &ATM_SD(sock)->local, sizeof(struct sockaddr_atmsvc)); - return 0; + return sizeof(struct sockaddr_atmsvc); } int svc_change_qos(struct atm_vcc *vcc, struct atm_qos *qos) diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c index 47fdd399626b..c8319ed48485 100644 --- a/net/ax25/af_ax25.c +++ b/net/ax25/af_ax25.c @@ -1388,7 +1388,7 @@ out: } static int ax25_getname(struct socket *sock, struct sockaddr *uaddr, - int *uaddr_len, int peer) + int peer) { struct full_sockaddr_ax25 *fsa = (struct full_sockaddr_ax25 *)uaddr; struct sock *sk = sock->sk; @@ -1427,7 +1427,7 @@ static int ax25_getname(struct socket *sock, struct sockaddr *uaddr, fsa->fsa_digipeater[0] = null_ax25_address; } } - *uaddr_len = sizeof (struct full_sockaddr_ax25); + err = sizeof (struct full_sockaddr_ax25); out: release_sock(sk); diff --git a/net/batman-adv/Kconfig b/net/batman-adv/Kconfig index c44f6515be5e..e4e2e02b7380 100644 --- a/net/batman-adv/Kconfig +++ b/net/batman-adv/Kconfig @@ -1,5 +1,5 @@ # SPDX-License-Identifier: GPL-2.0 -# Copyright (C) 2007-2017 B.A.T.M.A.N. contributors: +# Copyright (C) 2007-2018 B.A.T.M.A.N. contributors: # # Marek Lindner, Simon Wunderlich # diff --git a/net/batman-adv/Makefile b/net/batman-adv/Makefile index 022f6e77307b..b97ba6fb8353 100644 --- a/net/batman-adv/Makefile +++ b/net/batman-adv/Makefile @@ -1,5 +1,5 @@ # SPDX-License-Identifier: GPL-2.0 -# Copyright (C) 2007-2017 B.A.T.M.A.N. contributors: +# Copyright (C) 2007-2018 B.A.T.M.A.N. contributors: # # Marek Lindner, Simon Wunderlich # diff --git a/net/batman-adv/bat_algo.c b/net/batman-adv/bat_algo.c index 80c72c7d3cad..ea309ad06175 100644 --- a/net/batman-adv/bat_algo.c +++ b/net/batman-adv/bat_algo.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2007-2017 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2018 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * diff --git a/net/batman-adv/bat_algo.h b/net/batman-adv/bat_algo.h index 029221615ba3..534b790c3753 100644 --- a/net/batman-adv/bat_algo.h +++ b/net/batman-adv/bat_algo.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2011-2017 B.A.T.M.A.N. contributors: +/* Copyright (C) 2011-2018 B.A.T.M.A.N. contributors: * * Marek Lindner, Linus Lüssing * diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c index 99abeadf416e..be09a9883825 100644 --- a/net/batman-adv/bat_iv_ogm.c +++ b/net/batman-adv/bat_iv_ogm.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2007-2017 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2018 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * diff --git a/net/batman-adv/bat_iv_ogm.h b/net/batman-adv/bat_iv_ogm.h index 9dc0dd5c83df..317cafd302cf 100644 --- a/net/batman-adv/bat_iv_ogm.h +++ b/net/batman-adv/bat_iv_ogm.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2007-2017 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2018 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * diff --git a/net/batman-adv/bat_v.c b/net/batman-adv/bat_v.c index c74f81341dab..ec93337ee259 100644 --- a/net/batman-adv/bat_v.c +++ b/net/batman-adv/bat_v.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2013-2017 B.A.T.M.A.N. contributors: +/* Copyright (C) 2013-2018 B.A.T.M.A.N. contributors: * * Linus Lüssing, Marek Lindner * diff --git a/net/batman-adv/bat_v.h b/net/batman-adv/bat_v.h index a17ab68bbce8..ec4a2a569750 100644 --- a/net/batman-adv/bat_v.h +++ b/net/batman-adv/bat_v.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2011-2017 B.A.T.M.A.N. contributors: +/* Copyright (C) 2011-2018 B.A.T.M.A.N. contributors: * * Marek Lindner, Linus Lüssing * diff --git a/net/batman-adv/bat_v_elp.c b/net/batman-adv/bat_v_elp.c index a83478c46597..28687493599f 100644 --- a/net/batman-adv/bat_v_elp.c +++ b/net/batman-adv/bat_v_elp.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2011-2017 B.A.T.M.A.N. contributors: +/* Copyright (C) 2011-2018 B.A.T.M.A.N. contributors: * * Linus Lüssing, Marek Lindner * diff --git a/net/batman-adv/bat_v_elp.h b/net/batman-adv/bat_v_elp.h index 5e39d0588a48..e8c7b7fd290d 100644 --- a/net/batman-adv/bat_v_elp.h +++ b/net/batman-adv/bat_v_elp.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2013-2017 B.A.T.M.A.N. contributors: +/* Copyright (C) 2013-2018 B.A.T.M.A.N. contributors: * * Linus Lüssing, Marek Lindner * diff --git a/net/batman-adv/bat_v_ogm.c b/net/batman-adv/bat_v_ogm.c index ba59b77c605d..2948b41b06d4 100644 --- a/net/batman-adv/bat_v_ogm.c +++ b/net/batman-adv/bat_v_ogm.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2013-2017 B.A.T.M.A.N. contributors: +/* Copyright (C) 2013-2018 B.A.T.M.A.N. contributors: * * Antonio Quartulli * diff --git a/net/batman-adv/bat_v_ogm.h b/net/batman-adv/bat_v_ogm.h index 6a4c14ccc3c6..ed36c5e79fde 100644 --- a/net/batman-adv/bat_v_ogm.h +++ b/net/batman-adv/bat_v_ogm.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2013-2017 B.A.T.M.A.N. contributors: +/* Copyright (C) 2013-2018 B.A.T.M.A.N. contributors: * * Antonio Quartulli * diff --git a/net/batman-adv/bitarray.c b/net/batman-adv/bitarray.c index bdc1ef06e05b..a296a4d851f5 100644 --- a/net/batman-adv/bitarray.c +++ b/net/batman-adv/bitarray.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2006-2017 B.A.T.M.A.N. contributors: +/* Copyright (C) 2006-2018 B.A.T.M.A.N. contributors: * * Simon Wunderlich, Marek Lindner * diff --git a/net/batman-adv/bitarray.h b/net/batman-adv/bitarray.h index ca9d0753dd6b..48f683289531 100644 --- a/net/batman-adv/bitarray.h +++ b/net/batman-adv/bitarray.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2006-2017 B.A.T.M.A.N. contributors: +/* Copyright (C) 2006-2018 B.A.T.M.A.N. contributors: * * Simon Wunderlich, Marek Lindner * diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c index b1a08374088b..a2de5a44bd41 100644 --- a/net/batman-adv/bridge_loop_avoidance.c +++ b/net/batman-adv/bridge_loop_avoidance.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2011-2017 B.A.T.M.A.N. contributors: +/* Copyright (C) 2011-2018 B.A.T.M.A.N. contributors: * * Simon Wunderlich * diff --git a/net/batman-adv/bridge_loop_avoidance.h b/net/batman-adv/bridge_loop_avoidance.h index b27571abcd2f..71f95a3e4d3f 100644 --- a/net/batman-adv/bridge_loop_avoidance.h +++ b/net/batman-adv/bridge_loop_avoidance.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2011-2017 B.A.T.M.A.N. contributors: +/* Copyright (C) 2011-2018 B.A.T.M.A.N. contributors: * * Simon Wunderlich * diff --git a/net/batman-adv/debugfs.c b/net/batman-adv/debugfs.c index 21d1189957a7..4229b01ac7b5 100644 --- a/net/batman-adv/debugfs.c +++ b/net/batman-adv/debugfs.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2010-2017 B.A.T.M.A.N. contributors: +/* Copyright (C) 2010-2018 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/debugfs.h b/net/batman-adv/debugfs.h index 90a08d35c501..37b069698b04 100644 --- a/net/batman-adv/debugfs.h +++ b/net/batman-adv/debugfs.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2010-2017 B.A.T.M.A.N. contributors: +/* Copyright (C) 2010-2018 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/distributed-arp-table.c b/net/batman-adv/distributed-arp-table.c index 9703c791ffc5..4469dcc1558f 100644 --- a/net/batman-adv/distributed-arp-table.c +++ b/net/batman-adv/distributed-arp-table.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2011-2017 B.A.T.M.A.N. contributors: +/* Copyright (C) 2011-2018 B.A.T.M.A.N. contributors: * * Antonio Quartulli * @@ -495,7 +495,7 @@ static bool batadv_is_orig_node_eligible(struct batadv_dat_candidate *res, * the one with the lowest address */ if (tmp_max == max && max_orig_node && - batadv_compare_eth(candidate->orig, max_orig_node->orig) > 0) + batadv_compare_eth(candidate->orig, max_orig_node->orig)) goto out; ret = true; diff --git a/net/batman-adv/distributed-arp-table.h b/net/batman-adv/distributed-arp-table.h index 12897eb46268..e24aa9601c52 100644 --- a/net/batman-adv/distributed-arp-table.h +++ b/net/batman-adv/distributed-arp-table.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2011-2017 B.A.T.M.A.N. contributors: +/* Copyright (C) 2011-2018 B.A.T.M.A.N. contributors: * * Antonio Quartulli * diff --git a/net/batman-adv/fragmentation.c b/net/batman-adv/fragmentation.c index 5afe641ee4b0..0fddc17106bd 100644 --- a/net/batman-adv/fragmentation.c +++ b/net/batman-adv/fragmentation.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2013-2017 B.A.T.M.A.N. contributors: +/* Copyright (C) 2013-2018 B.A.T.M.A.N. contributors: * * Martin Hundebøll <martin@hundeboll.net> * diff --git a/net/batman-adv/fragmentation.h b/net/batman-adv/fragmentation.h index 138b22a1836a..944512e07782 100644 --- a/net/batman-adv/fragmentation.h +++ b/net/batman-adv/fragmentation.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2013-2017 B.A.T.M.A.N. contributors: +/* Copyright (C) 2013-2018 B.A.T.M.A.N. contributors: * * Martin Hundebøll <martin@hundeboll.net> * diff --git a/net/batman-adv/gateway_client.c b/net/batman-adv/gateway_client.c index 37fe9a644f22..c294f6fd43e0 100644 --- a/net/batman-adv/gateway_client.c +++ b/net/batman-adv/gateway_client.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2009-2017 B.A.T.M.A.N. contributors: +/* Copyright (C) 2009-2018 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/gateway_client.h b/net/batman-adv/gateway_client.h index 981f58421a32..f0b86fcb2493 100644 --- a/net/batman-adv/gateway_client.h +++ b/net/batman-adv/gateway_client.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2009-2017 B.A.T.M.A.N. contributors: +/* Copyright (C) 2009-2018 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/gateway_common.c b/net/batman-adv/gateway_common.c index b3e156af2256..936c107f3199 100644 --- a/net/batman-adv/gateway_common.c +++ b/net/batman-adv/gateway_common.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2009-2017 B.A.T.M.A.N. contributors: +/* Copyright (C) 2009-2018 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/gateway_common.h b/net/batman-adv/gateway_common.h index afebd9c7edf4..80afb2793687 100644 --- a/net/batman-adv/gateway_common.h +++ b/net/batman-adv/gateway_common.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2009-2017 B.A.T.M.A.N. contributors: +/* Copyright (C) 2009-2018 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c index 68b54a39c51d..c405d15befd6 100644 --- a/net/batman-adv/hard-interface.c +++ b/net/batman-adv/hard-interface.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2007-2017 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2018 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * diff --git a/net/batman-adv/hard-interface.h b/net/batman-adv/hard-interface.h index de5e9a374ece..d1c0f6189301 100644 --- a/net/batman-adv/hard-interface.h +++ b/net/batman-adv/hard-interface.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2007-2017 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2018 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * diff --git a/net/batman-adv/hash.c b/net/batman-adv/hash.c index 04d964358c98..7b49e4001778 100644 --- a/net/batman-adv/hash.c +++ b/net/batman-adv/hash.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2006-2017 B.A.T.M.A.N. contributors: +/* Copyright (C) 2006-2018 B.A.T.M.A.N. contributors: * * Simon Wunderlich, Marek Lindner * diff --git a/net/batman-adv/hash.h b/net/batman-adv/hash.h index 4ce1b6d3ad5c..9490a7ca2ba6 100644 --- a/net/batman-adv/hash.h +++ b/net/batman-adv/hash.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2006-2017 B.A.T.M.A.N. contributors: +/* Copyright (C) 2006-2018 B.A.T.M.A.N. contributors: * * Simon Wunderlich, Marek Lindner * diff --git a/net/batman-adv/icmp_socket.c b/net/batman-adv/icmp_socket.c index e91f29c7c638..7d5e9abb7a65 100644 --- a/net/batman-adv/icmp_socket.c +++ b/net/batman-adv/icmp_socket.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2007-2017 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2018 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/icmp_socket.h b/net/batman-adv/icmp_socket.h index 84cddd01eeab..958be22beda9 100644 --- a/net/batman-adv/icmp_socket.h +++ b/net/batman-adv/icmp_socket.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2007-2017 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2018 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/log.c b/net/batman-adv/log.c index dc9fa37ddd14..52d8a4b848c0 100644 --- a/net/batman-adv/log.c +++ b/net/batman-adv/log.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2010-2017 B.A.T.M.A.N. contributors: +/* Copyright (C) 2010-2018 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/log.h b/net/batman-adv/log.h index 35e02b2b9e72..35f4f397ed57 100644 --- a/net/batman-adv/log.h +++ b/net/batman-adv/log.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2007-2017 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2018 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * diff --git a/net/batman-adv/main.c b/net/batman-adv/main.c index d31c8266e244..69c0d85bceb3 100644 --- a/net/batman-adv/main.c +++ b/net/batman-adv/main.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2007-2017 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2018 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * diff --git a/net/batman-adv/main.h b/net/batman-adv/main.h index f7ba3f96d8f3..057a28a9fe88 100644 --- a/net/batman-adv/main.h +++ b/net/batman-adv/main.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2007-2017 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2018 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * @@ -25,7 +25,7 @@ #define BATADV_DRIVER_DEVICE "batman-adv" #ifndef BATADV_SOURCE_VERSION -#define BATADV_SOURCE_VERSION "2018.0" +#define BATADV_SOURCE_VERSION "2018.1" #endif /* B.A.T.M.A.N. parameters */ @@ -331,11 +331,13 @@ static inline bool batadv_has_timed_out(unsigned long timestamp, * * Return: true when x is a predecessor of y, false otherwise */ -#define batadv_seq_before(x, y) ({typeof(x)_d1 = (x); \ - typeof(y)_d2 = (y); \ - typeof(x)_dummy = (_d1 - _d2); \ - (void)(&_d1 == &_d2); \ - _dummy > batadv_smallest_signed_int(_dummy); }) +#define batadv_seq_before(x, y) ({ \ + typeof(x)_d1 = (x); \ + typeof(y)_d2 = (y); \ + typeof(x)_dummy = (_d1 - _d2); \ + (void)(&_d1 == &_d2); \ + _dummy > batadv_smallest_signed_int(_dummy); \ +}) /** * batadv_seq_after() - Checks if a sequence number x is a successor of y diff --git a/net/batman-adv/multicast.c b/net/batman-adv/multicast.c index cbdeb47ec3f6..6eaffe50335a 100644 --- a/net/batman-adv/multicast.c +++ b/net/batman-adv/multicast.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2014-2017 B.A.T.M.A.N. contributors: +/* Copyright (C) 2014-2018 B.A.T.M.A.N. contributors: * * Linus Lüssing * diff --git a/net/batman-adv/multicast.h b/net/batman-adv/multicast.h index 3ac06337ab71..6b8594e23da3 100644 --- a/net/batman-adv/multicast.h +++ b/net/batman-adv/multicast.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2014-2017 B.A.T.M.A.N. contributors: +/* Copyright (C) 2014-2018 B.A.T.M.A.N. contributors: * * Linus Lüssing * diff --git a/net/batman-adv/netlink.c b/net/batman-adv/netlink.c index a823d3899bad..129af56b944d 100644 --- a/net/batman-adv/netlink.c +++ b/net/batman-adv/netlink.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2016-2017 B.A.T.M.A.N. contributors: +/* Copyright (C) 2016-2018 B.A.T.M.A.N. contributors: * * Matthias Schiffer * diff --git a/net/batman-adv/netlink.h b/net/batman-adv/netlink.h index 0e7e57b69b54..571d9a5ae7aa 100644 --- a/net/batman-adv/netlink.h +++ b/net/batman-adv/netlink.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2016-2017 B.A.T.M.A.N. contributors: +/* Copyright (C) 2016-2018 B.A.T.M.A.N. contributors: * * Matthias Schiffer * diff --git a/net/batman-adv/network-coding.c b/net/batman-adv/network-coding.c index b48116bb24ef..c3578444f3cb 100644 --- a/net/batman-adv/network-coding.c +++ b/net/batman-adv/network-coding.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2012-2017 B.A.T.M.A.N. contributors: +/* Copyright (C) 2012-2018 B.A.T.M.A.N. contributors: * * Martin Hundebøll, Jeppe Ledet-Pedersen * diff --git a/net/batman-adv/network-coding.h b/net/batman-adv/network-coding.h index adaeafa4f71e..65c346812bc1 100644 --- a/net/batman-adv/network-coding.h +++ b/net/batman-adv/network-coding.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2012-2017 B.A.T.M.A.N. contributors: +/* Copyright (C) 2012-2018 B.A.T.M.A.N. contributors: * * Martin Hundebøll, Jeppe Ledet-Pedersen * diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c index 74782426bb77..716e5b43acfa 100644 --- a/net/batman-adv/originator.c +++ b/net/batman-adv/originator.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2009-2017 B.A.T.M.A.N. contributors: +/* Copyright (C) 2009-2018 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * diff --git a/net/batman-adv/originator.h b/net/batman-adv/originator.h index 15d896b2de6f..3b3f59b881e1 100644 --- a/net/batman-adv/originator.h +++ b/net/batman-adv/originator.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2007-2017 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2018 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * diff --git a/net/batman-adv/routing.c b/net/batman-adv/routing.c index b6891e8b741c..289df027ecdd 100644 --- a/net/batman-adv/routing.c +++ b/net/batman-adv/routing.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2007-2017 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2018 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * diff --git a/net/batman-adv/routing.h b/net/batman-adv/routing.h index a1289bc5f115..db54c2d9b8bf 100644 --- a/net/batman-adv/routing.h +++ b/net/batman-adv/routing.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2007-2017 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2018 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * diff --git a/net/batman-adv/send.c b/net/batman-adv/send.c index 2a5ab6f1076d..4a35f5c2f52b 100644 --- a/net/batman-adv/send.c +++ b/net/batman-adv/send.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2007-2017 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2018 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * diff --git a/net/batman-adv/send.h b/net/batman-adv/send.h index 1e8c79093623..64cce07b8fe6 100644 --- a/net/batman-adv/send.h +++ b/net/batman-adv/send.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2007-2017 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2018 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c index 367a81fb785f..edeffcb9f3a2 100644 --- a/net/batman-adv/soft-interface.c +++ b/net/batman-adv/soft-interface.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2007-2017 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2018 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * diff --git a/net/batman-adv/soft-interface.h b/net/batman-adv/soft-interface.h index 075c5b5b2ce1..daf87f07fadd 100644 --- a/net/batman-adv/soft-interface.h +++ b/net/batman-adv/soft-interface.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2007-2017 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2018 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/sysfs.c b/net/batman-adv/sysfs.c index c1578fa0b952..f2eef43bd2ec 100644 --- a/net/batman-adv/sysfs.c +++ b/net/batman-adv/sysfs.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2010-2017 B.A.T.M.A.N. contributors: +/* Copyright (C) 2010-2018 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/sysfs.h b/net/batman-adv/sysfs.h index bbeee61221fa..c1e3fb69952d 100644 --- a/net/batman-adv/sysfs.h +++ b/net/batman-adv/sysfs.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2010-2017 B.A.T.M.A.N. contributors: +/* Copyright (C) 2010-2018 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/tp_meter.c b/net/batman-adv/tp_meter.c index 8b576712d0c1..11520de96ccb 100644 --- a/net/batman-adv/tp_meter.c +++ b/net/batman-adv/tp_meter.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2012-2017 B.A.T.M.A.N. contributors: +/* Copyright (C) 2012-2018 B.A.T.M.A.N. contributors: * * Edo Monticelli, Antonio Quartulli * diff --git a/net/batman-adv/tp_meter.h b/net/batman-adv/tp_meter.h index c8b8f2cb2c2b..68e600974759 100644 --- a/net/batman-adv/tp_meter.h +++ b/net/batman-adv/tp_meter.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2012-2017 B.A.T.M.A.N. contributors: +/* Copyright (C) 2012-2018 B.A.T.M.A.N. contributors: * * Edo Monticelli, Antonio Quartulli * diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c index 7550a9ccd695..0225616d5771 100644 --- a/net/batman-adv/translation-table.c +++ b/net/batman-adv/translation-table.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2007-2017 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2018 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich, Antonio Quartulli * diff --git a/net/batman-adv/translation-table.h b/net/batman-adv/translation-table.h index 8d9e3abec2c8..01b6c8eafaf9 100644 --- a/net/batman-adv/translation-table.h +++ b/net/batman-adv/translation-table.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2007-2017 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2018 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich, Antonio Quartulli * diff --git a/net/batman-adv/tvlv.c b/net/batman-adv/tvlv.c index 5ffcb45ac6ff..a637458205d1 100644 --- a/net/batman-adv/tvlv.c +++ b/net/batman-adv/tvlv.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2007-2017 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2018 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * diff --git a/net/batman-adv/tvlv.h b/net/batman-adv/tvlv.h index a74df33f446d..ef5867f49824 100644 --- a/net/batman-adv/tvlv.h +++ b/net/batman-adv/tvlv.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2007-2017 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2018 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h index a5aa6d61f4e2..476b052ad982 100644 --- a/net/batman-adv/types.h +++ b/net/batman-adv/types.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2007-2017 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2018 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * diff --git a/net/bluetooth/hci_request.c b/net/bluetooth/hci_request.c index 3394e6791673..66c0781773df 100644 --- a/net/bluetooth/hci_request.c +++ b/net/bluetooth/hci_request.c @@ -934,8 +934,8 @@ static bool is_advertising_allowed(struct hci_dev *hdev, bool connectable) /* Slave connection state and connectable mode bit 38 * and scannable bit 21. */ - if (connectable && (!(hdev->le_states[4] & 0x01) || - !(hdev->le_states[2] & 0x40))) + if (connectable && (!(hdev->le_states[4] & 0x40) || + !(hdev->le_states[2] & 0x20))) return false; } @@ -948,7 +948,7 @@ static bool is_advertising_allowed(struct hci_dev *hdev, bool connectable) /* Master connection state and connectable mode bit 35 and * scannable 19. */ - if (connectable && (!(hdev->le_states[4] & 0x10) || + if (connectable && (!(hdev->le_states[4] & 0x08) || !(hdev->le_states[2] & 0x08))) return false; } diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c index 923e9a271872..1506e1632394 100644 --- a/net/bluetooth/hci_sock.c +++ b/net/bluetooth/hci_sock.c @@ -1340,7 +1340,7 @@ done: } static int hci_sock_getname(struct socket *sock, struct sockaddr *addr, - int *addr_len, int peer) + int peer) { struct sockaddr_hci *haddr = (struct sockaddr_hci *)addr; struct sock *sk = sock->sk; @@ -1360,10 +1360,10 @@ static int hci_sock_getname(struct socket *sock, struct sockaddr *addr, goto done; } - *addr_len = sizeof(*haddr); haddr->hci_family = AF_BLUETOOTH; haddr->hci_dev = hdev->id; haddr->hci_channel= hci_pi(sk)->channel; + err = sizeof(*haddr); done: release_sock(sk); diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c index 67a8642f57ea..686bdc6b35b0 100644 --- a/net/bluetooth/l2cap_sock.c +++ b/net/bluetooth/l2cap_sock.c @@ -358,7 +358,7 @@ done: } static int l2cap_sock_getname(struct socket *sock, struct sockaddr *addr, - int *len, int peer) + int peer) { struct sockaddr_l2 *la = (struct sockaddr_l2 *) addr; struct sock *sk = sock->sk; @@ -373,7 +373,6 @@ static int l2cap_sock_getname(struct socket *sock, struct sockaddr *addr, memset(la, 0, sizeof(struct sockaddr_l2)); addr->sa_family = AF_BLUETOOTH; - *len = sizeof(struct sockaddr_l2); la->l2_psm = chan->psm; @@ -387,7 +386,7 @@ static int l2cap_sock_getname(struct socket *sock, struct sockaddr *addr, la->l2_bdaddr_type = chan->src_type; } - return 0; + return sizeof(struct sockaddr_l2); } static int l2cap_sock_getsockopt_old(struct socket *sock, int optname, diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c index 1aaccf637479..93a3b219db09 100644 --- a/net/bluetooth/rfcomm/sock.c +++ b/net/bluetooth/rfcomm/sock.c @@ -533,7 +533,7 @@ done: return err; } -static int rfcomm_sock_getname(struct socket *sock, struct sockaddr *addr, int *len, int peer) +static int rfcomm_sock_getname(struct socket *sock, struct sockaddr *addr, int peer) { struct sockaddr_rc *sa = (struct sockaddr_rc *) addr; struct sock *sk = sock->sk; @@ -552,8 +552,7 @@ static int rfcomm_sock_getname(struct socket *sock, struct sockaddr *addr, int * else bacpy(&sa->rc_bdaddr, &rfcomm_pi(sk)->src); - *len = sizeof(struct sockaddr_rc); - return 0; + return sizeof(struct sockaddr_rc); } static int rfcomm_sock_sendmsg(struct socket *sock, struct msghdr *msg, diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c index 08df57665e1f..413b8ee49fec 100644 --- a/net/bluetooth/sco.c +++ b/net/bluetooth/sco.c @@ -680,7 +680,7 @@ done: } static int sco_sock_getname(struct socket *sock, struct sockaddr *addr, - int *len, int peer) + int peer) { struct sockaddr_sco *sa = (struct sockaddr_sco *) addr; struct sock *sk = sock->sk; @@ -688,14 +688,13 @@ static int sco_sock_getname(struct socket *sock, struct sockaddr *addr, BT_DBG("sock %p, sk %p", sock, sk); addr->sa_family = AF_BLUETOOTH; - *len = sizeof(struct sockaddr_sco); if (peer) bacpy(&sa->sco_bdaddr, &sco_pi(sk)->dst); else bacpy(&sa->sco_bdaddr, &sco_pi(sk)->src); - return 0; + return sizeof(struct sockaddr_sco); } static int sco_sock_sendmsg(struct socket *sock, struct msghdr *msg, diff --git a/net/bridge/br.c b/net/bridge/br.c index 6bf06e756df2..7770481a6506 100644 --- a/net/bridge/br.c +++ b/net/bridge/br.c @@ -188,6 +188,7 @@ static void __net_exit br_net_exit(struct net *net) static struct pernet_operations br_net_ops = { .exit = br_net_exit, + .async = true, }; static const struct stp_proto br_stp_proto = { diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c index 9b16eaf33819..c2120eb889a9 100644 --- a/net/bridge/br_netfilter_hooks.c +++ b/net/bridge/br_netfilter_hooks.c @@ -969,6 +969,7 @@ static struct pernet_operations brnf_net_ops __read_mostly = { .exit = brnf_exit_net, .id = &brnf_net_id, .size = sizeof(struct brnf_net), + .async = true, }; static struct notifier_block brnf_notifier __read_mostly = { diff --git a/net/bridge/netfilter/ebtable_broute.c b/net/bridge/netfilter/ebtable_broute.c index 276b60262981..f070b5e5b9dd 100644 --- a/net/bridge/netfilter/ebtable_broute.c +++ b/net/bridge/netfilter/ebtable_broute.c @@ -77,6 +77,7 @@ static void __net_exit broute_net_exit(struct net *net) static struct pernet_operations broute_net_ops = { .init = broute_net_init, .exit = broute_net_exit, + .async = true, }; static int __init ebtable_broute_init(void) diff --git a/net/bridge/netfilter/ebtable_filter.c b/net/bridge/netfilter/ebtable_filter.c index c41da5fac84f..4151afc8efcc 100644 --- a/net/bridge/netfilter/ebtable_filter.c +++ b/net/bridge/netfilter/ebtable_filter.c @@ -105,6 +105,7 @@ static void __net_exit frame_filter_net_exit(struct net *net) static struct pernet_operations frame_filter_net_ops = { .init = frame_filter_net_init, .exit = frame_filter_net_exit, + .async = true, }; static int __init ebtable_filter_init(void) diff --git a/net/bridge/netfilter/ebtable_nat.c b/net/bridge/netfilter/ebtable_nat.c index 08df7406ecb3..b8da2dfe2ec5 100644 --- a/net/bridge/netfilter/ebtable_nat.c +++ b/net/bridge/netfilter/ebtable_nat.c @@ -105,6 +105,7 @@ static void __net_exit frame_nat_net_exit(struct net *net) static struct pernet_operations frame_nat_net_ops = { .init = frame_nat_net_init, .exit = frame_nat_net_exit, + .async = true, }; static int __init ebtable_nat_init(void) diff --git a/net/bridge/netfilter/nf_log_bridge.c b/net/bridge/netfilter/nf_log_bridge.c index bd2b3c78f59b..91bfc2ac055a 100644 --- a/net/bridge/netfilter/nf_log_bridge.c +++ b/net/bridge/netfilter/nf_log_bridge.c @@ -48,6 +48,7 @@ static void __net_exit nf_log_bridge_net_exit(struct net *net) static struct pernet_operations nf_log_bridge_net_ops = { .init = nf_log_bridge_net_init, .exit = nf_log_bridge_net_exit, + .async = true, }; static int __init nf_log_bridge_init(void) diff --git a/net/caif/caif_dev.c b/net/caif/caif_dev.c index e0adcd123f48..7a78268cc572 100644 --- a/net/caif/caif_dev.c +++ b/net/caif/caif_dev.c @@ -544,6 +544,7 @@ static struct pernet_operations caif_net_ops = { .exit = caif_exit_net, .id = &caif_net_id, .size = sizeof(struct caif_net), + .async = true, }; /* Initialize Caif devices list */ diff --git a/net/can/bcm.c b/net/can/bcm.c index ac5e5e34fee3..26730d39e048 100644 --- a/net/can/bcm.c +++ b/net/can/bcm.c @@ -1717,6 +1717,7 @@ static void canbcm_pernet_exit(struct net *net) static struct pernet_operations canbcm_pernet_ops __read_mostly = { .init = canbcm_pernet_init, .exit = canbcm_pernet_exit, + .async = true, }; static int __init bcm_module_init(void) diff --git a/net/can/gw.c b/net/can/gw.c index 398dd0395ad9..08e97668d5cf 100644 --- a/net/can/gw.c +++ b/net/can/gw.c @@ -1010,6 +1010,7 @@ static void __net_exit cangw_pernet_exit(struct net *net) static struct pernet_operations cangw_pernet_ops = { .init = cangw_pernet_init, .exit = cangw_pernet_exit, + .async = true, }; static __init int cgw_module_init(void) diff --git a/net/can/raw.c b/net/can/raw.c index f2ecc43376a1..1051eee82581 100644 --- a/net/can/raw.c +++ b/net/can/raw.c @@ -470,7 +470,7 @@ static int raw_bind(struct socket *sock, struct sockaddr *uaddr, int len) } static int raw_getname(struct socket *sock, struct sockaddr *uaddr, - int *len, int peer) + int peer) { struct sockaddr_can *addr = (struct sockaddr_can *)uaddr; struct sock *sk = sock->sk; @@ -483,9 +483,7 @@ static int raw_getname(struct socket *sock, struct sockaddr *uaddr, addr->can_family = AF_CAN; addr->can_ifindex = ro->ifindex; - *len = sizeof(*addr); - - return 0; + return sizeof(*addr); } static int raw_setsockopt(struct socket *sock, int level, int optname, diff --git a/net/core/dev.c b/net/core/dev.c index 2cedf520cb28..e5b8d42b6410 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2378,7 +2378,7 @@ EXPORT_SYMBOL(netdev_set_num_tc); /* * Routine to help set real_num_tx_queues. To avoid skbs mapped to queues - * greater then real_num_tx_queues stale skbs on the qdisc must be flushed. + * greater than real_num_tx_queues stale skbs on the qdisc must be flushed. */ int netif_set_real_num_tx_queues(struct net_device *dev, unsigned int txq) { @@ -7546,6 +7546,12 @@ static netdev_features_t netdev_fix_features(struct net_device *dev, } } + /* LRO feature cannot be combined with RX-FCS */ + if ((features & NETIF_F_LRO) && (features & NETIF_F_RXFCS)) { + netdev_dbg(dev, "Dropping LRO feature since RX-FCS is requested.\n"); + features &= ~NETIF_F_LRO; + } + return features; } @@ -8145,8 +8151,9 @@ void netdev_run_todo(void) BUG_ON(!list_empty(&dev->ptype_specific)); WARN_ON(rcu_access_pointer(dev->ip_ptr)); WARN_ON(rcu_access_pointer(dev->ip6_ptr)); +#if IS_ENABLED(CONFIG_DECNET) WARN_ON(dev->dn_ptr); - +#endif if (dev->priv_destructor) dev->priv_destructor(dev); if (dev->needs_free_netdev) @@ -8844,6 +8851,7 @@ static void __net_exit netdev_exit(struct net *net) static struct pernet_operations __net_initdata netdev_net_ops = { .init = netdev_init, .exit = netdev_exit, + .async = true, }; static void __net_exit default_device_exit(struct net *net) @@ -8944,6 +8952,7 @@ static void __net_exit default_device_exit_batch(struct list_head *net_list) static struct pernet_operations __net_initdata default_device_ops = { .exit = default_device_exit, .exit_batch = default_device_exit_batch, + .async = true, }; /* diff --git a/net/core/devlink.c b/net/core/devlink.c index 2f2307d94787..1b5bf0d1cee9 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -2339,6 +2339,32 @@ out: resource->size_valid = size_valid; } +static int +devlink_resource_validate_size(struct devlink_resource *resource, u64 size, + struct netlink_ext_ack *extack) +{ + u64 reminder; + int err = 0; + + if (size > resource->size_params.size_max) { + NL_SET_ERR_MSG_MOD(extack, "Size larger than maximum"); + err = -EINVAL; + } + + if (size < resource->size_params.size_min) { + NL_SET_ERR_MSG_MOD(extack, "Size smaller than minimum"); + err = -EINVAL; + } + + div64_u64_rem(size, resource->size_params.size_granularity, &reminder); + if (reminder) { + NL_SET_ERR_MSG_MOD(extack, "Wrong granularity"); + err = -EINVAL; + } + + return err; +} + static int devlink_nl_cmd_resource_set(struct sk_buff *skb, struct genl_info *info) { @@ -2357,12 +2383,8 @@ static int devlink_nl_cmd_resource_set(struct sk_buff *skb, if (!resource) return -EINVAL; - if (!resource->resource_ops->size_validate) - return -EINVAL; - size = nla_get_u64(info->attrs[DEVLINK_ATTR_RESOURCE_SIZE]); - err = resource->resource_ops->size_validate(devlink, size, - info->extack); + err = devlink_resource_validate_size(resource, size, info->extack); if (err) return err; diff --git a/net/core/dst_cache.c b/net/core/dst_cache.c index 554d36449231..64cef977484a 100644 --- a/net/core/dst_cache.c +++ b/net/core/dst_cache.c @@ -107,7 +107,7 @@ EXPORT_SYMBOL_GPL(dst_cache_set_ip4); #if IS_ENABLED(CONFIG_IPV6) void dst_cache_set_ip6(struct dst_cache *dst_cache, struct dst_entry *dst, - const struct in6_addr *addr) + const struct in6_addr *saddr) { struct dst_cache_pcpu *idst; @@ -117,7 +117,7 @@ void dst_cache_set_ip6(struct dst_cache *dst_cache, struct dst_entry *dst, idst = this_cpu_ptr(dst_cache->cache); dst_cache_per_cpu_dst_set(this_cpu_ptr(dst_cache->cache), dst, rt6_get_cookie((struct rt6_info *)dst)); - idst->in6_saddr = *addr; + idst->in6_saddr = *saddr; } EXPORT_SYMBOL_GPL(dst_cache_set_ip6); diff --git a/net/core/fib_notifier.c b/net/core/fib_notifier.c index 0c048bdeb016..5ace0705a3f9 100644 --- a/net/core/fib_notifier.c +++ b/net/core/fib_notifier.c @@ -171,6 +171,7 @@ static void __net_exit fib_notifier_net_exit(struct net *net) static struct pernet_operations fib_notifier_net_ops = { .init = fib_notifier_net_init, .exit = fib_notifier_net_exit, + .async = true, }; static int __init fib_notifier_init(void) diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index 98e1066c3d55..f6f04fc0f629 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -33,6 +33,10 @@ bool fib_rule_matchall(const struct fib_rule *rule) if (!uid_eq(rule->uid_range.start, fib_kuid_range_unset.start) || !uid_eq(rule->uid_range.end, fib_kuid_range_unset.end)) return false; + if (fib_rule_port_range_set(&rule->sport_range)) + return false; + if (fib_rule_port_range_set(&rule->dport_range)) + return false; return true; } EXPORT_SYMBOL_GPL(fib_rule_matchall); @@ -51,6 +55,7 @@ int fib_default_rule_add(struct fib_rules_ops *ops, r->pref = pref; r->table = table; r->flags = flags; + r->proto = RTPROT_KERNEL; r->fr_net = ops->fro_net; r->uid_range = fib_kuid_range_unset; @@ -220,6 +225,26 @@ static int nla_put_uid_range(struct sk_buff *skb, struct fib_kuid_range *range) return nla_put(skb, FRA_UID_RANGE, sizeof(out), &out); } +static int nla_get_port_range(struct nlattr *pattr, + struct fib_rule_port_range *port_range) +{ + const struct fib_rule_port_range *pr = nla_data(pattr); + + if (!fib_rule_port_range_valid(pr)) + return -EINVAL; + + port_range->start = pr->start; + port_range->end = pr->end; + + return 0; +} + +static int nla_put_port_range(struct sk_buff *skb, int attrtype, + struct fib_rule_port_range *range) +{ + return nla_put(skb, attrtype, sizeof(*range), range); +} + static int fib_rule_match(struct fib_rule *rule, struct fib_rules_ops *ops, struct flowi *fl, int flags, struct fib_lookup_arg *arg) @@ -424,6 +449,17 @@ static int rule_exists(struct fib_rules_ops *ops, struct fib_rule_hdr *frh, !uid_eq(r->uid_range.end, rule->uid_range.end)) continue; + if (r->ip_proto != rule->ip_proto) + continue; + + if (!fib_rule_port_range_compare(&r->sport_range, + &rule->sport_range)) + continue; + + if (!fib_rule_port_range_compare(&r->dport_range, + &rule->dport_range)) + continue; + if (!ops->compare(r, frh, tb)) continue; return 1; @@ -469,6 +505,9 @@ int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh, rule->pref = tb[FRA_PRIORITY] ? nla_get_u32(tb[FRA_PRIORITY]) : fib_default_rule_pref(ops); + rule->proto = tb[FRA_PROTOCOL] ? + nla_get_u8(tb[FRA_PROTOCOL]) : RTPROT_UNSPEC; + if (tb[FRA_IIFNAME]) { struct net_device *dev; @@ -565,6 +604,23 @@ int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh, rule->uid_range = fib_kuid_range_unset; } + if (tb[FRA_IP_PROTO]) + rule->ip_proto = nla_get_u8(tb[FRA_IP_PROTO]); + + if (tb[FRA_SPORT_RANGE]) { + err = nla_get_port_range(tb[FRA_SPORT_RANGE], + &rule->sport_range); + if (err) + goto errout_free; + } + + if (tb[FRA_DPORT_RANGE]) { + err = nla_get_port_range(tb[FRA_DPORT_RANGE], + &rule->dport_range); + if (err) + goto errout_free; + } + if ((nlh->nlmsg_flags & NLM_F_EXCL) && rule_exists(ops, frh, tb, rule)) { err = -EEXIST; @@ -630,6 +686,8 @@ int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr *nlh, { struct net *net = sock_net(skb->sk); struct fib_rule_hdr *frh = nlmsg_data(nlh); + struct fib_rule_port_range sprange = {0, 0}; + struct fib_rule_port_range dprange = {0, 0}; struct fib_rules_ops *ops = NULL; struct fib_rule *rule, *r; struct nlattr *tb[FRA_MAX+1]; @@ -663,7 +721,25 @@ int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr *nlh, range = fib_kuid_range_unset; } + if (tb[FRA_SPORT_RANGE]) { + err = nla_get_port_range(tb[FRA_SPORT_RANGE], + &sprange); + if (err) + goto errout; + } + + if (tb[FRA_DPORT_RANGE]) { + err = nla_get_port_range(tb[FRA_DPORT_RANGE], + &dprange); + if (err) + goto errout; + } + list_for_each_entry(rule, &ops->rules_list, list) { + if (tb[FRA_PROTOCOL] && + (rule->proto != nla_get_u8(tb[FRA_PROTOCOL]))) + continue; + if (frh->action && (frh->action != rule->action)) continue; @@ -704,6 +780,18 @@ int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr *nlh, !uid_eq(rule->uid_range.end, range.end))) continue; + if (tb[FRA_IP_PROTO] && + (rule->ip_proto != nla_get_u8(tb[FRA_IP_PROTO]))) + continue; + + if (fib_rule_port_range_set(&sprange) && + !fib_rule_port_range_compare(&rule->sport_range, &sprange)) + continue; + + if (fib_rule_port_range_set(&dprange) && + !fib_rule_port_range_compare(&rule->dport_range, &dprange)) + continue; + if (!ops->compare(rule, frh, tb)) continue; @@ -781,7 +869,11 @@ static inline size_t fib_rule_nlmsg_size(struct fib_rules_ops *ops, + nla_total_size(4) /* FRA_FWMARK */ + nla_total_size(4) /* FRA_FWMASK */ + nla_total_size_64bit(8) /* FRA_TUN_ID */ - + nla_total_size(sizeof(struct fib_kuid_range)); + + nla_total_size(sizeof(struct fib_kuid_range)) + + nla_total_size(1) /* FRA_PROTOCOL */ + + nla_total_size(1) /* FRA_IP_PROTO */ + + nla_total_size(sizeof(struct fib_rule_port_range)) /* FRA_SPORT_RANGE */ + + nla_total_size(sizeof(struct fib_rule_port_range)); /* FRA_DPORT_RANGE */ if (ops->nlmsg_payload) payload += ops->nlmsg_payload(rule); @@ -812,6 +904,9 @@ static int fib_nl_fill_rule(struct sk_buff *skb, struct fib_rule *rule, frh->action = rule->action; frh->flags = rule->flags; + if (nla_put_u8(skb, FRA_PROTOCOL, rule->proto)) + goto nla_put_failure; + if (rule->action == FR_ACT_GOTO && rcu_access_pointer(rule->ctarget) == NULL) frh->flags |= FIB_RULE_UNRESOLVED; @@ -843,7 +938,12 @@ static int fib_nl_fill_rule(struct sk_buff *skb, struct fib_rule *rule, (rule->l3mdev && nla_put_u8(skb, FRA_L3MDEV, rule->l3mdev)) || (uid_range_set(&rule->uid_range) && - nla_put_uid_range(skb, &rule->uid_range))) + nla_put_uid_range(skb, &rule->uid_range)) || + (fib_rule_port_range_set(&rule->sport_range) && + nla_put_port_range(skb, FRA_SPORT_RANGE, &rule->sport_range)) || + (fib_rule_port_range_set(&rule->dport_range) && + nla_put_port_range(skb, FRA_DPORT_RANGE, &rule->dport_range)) || + (rule->ip_proto && nla_put_u8(skb, FRA_IP_PROTO, rule->ip_proto))) goto nla_put_failure; if (rule->suppress_ifgroup != -1) { @@ -1030,6 +1130,7 @@ static void __net_exit fib_rules_net_exit(struct net *net) static struct pernet_operations fib_rules_net_ops = { .init = fib_rules_net_init, .exit = fib_rules_net_exit, + .async = true, }; static int __init fib_rules_init(void) diff --git a/net/core/filter.c b/net/core/filter.c index 0c121adbdbaa..33edfa8372fd 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -2991,7 +2991,7 @@ BPF_CALL_4(bpf_skb_set_tunnel_key, struct sk_buff *, skb, struct ip_tunnel_info *info; if (unlikely(flags & ~(BPF_F_TUNINFO_IPV6 | BPF_F_ZERO_CSUM_TX | - BPF_F_DONT_FRAGMENT))) + BPF_F_DONT_FRAGMENT | BPF_F_SEQ_NUMBER))) return -EINVAL; if (unlikely(size != sizeof(struct bpf_tunnel_key))) { switch (size) { @@ -3025,6 +3025,8 @@ BPF_CALL_4(bpf_skb_set_tunnel_key, struct sk_buff *, skb, info->key.tun_flags |= TUNNEL_DONT_FRAGMENT; if (flags & BPF_F_ZERO_CSUM_TX) info->key.tun_flags &= ~TUNNEL_CSUM; + if (flags & BPF_F_SEQ_NUMBER) + info->key.tun_flags |= TUNNEL_SEQ; info->key.tun_id = cpu_to_be64(from->tunnel_id); info->key.tos = from->tunnel_tos; diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 559db9ea8d86..d29f09bc5ff9 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -1341,22 +1341,6 @@ __u32 __get_hash_from_flowi6(const struct flowi6 *fl6, struct flow_keys *keys) } EXPORT_SYMBOL(__get_hash_from_flowi6); -__u32 __get_hash_from_flowi4(const struct flowi4 *fl4, struct flow_keys *keys) -{ - memset(keys, 0, sizeof(*keys)); - - keys->addrs.v4addrs.src = fl4->saddr; - keys->addrs.v4addrs.dst = fl4->daddr; - keys->control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; - keys->ports.src = fl4->fl4_sport; - keys->ports.dst = fl4->fl4_dport; - keys->keyid.keyid = fl4->fl4_gre_key; - keys->basic.ip_proto = fl4->flowi4_proto; - - return flow_hash_from_keys(keys); -} -EXPORT_SYMBOL(__get_hash_from_flowi4); - static const struct flow_dissector_key flow_keys_dissector_keys[] = { { .key_id = FLOW_DISSECTOR_KEY_CONTROL, diff --git a/net/core/net-procfs.c b/net/core/net-procfs.c index e010bb800d7b..65b51e778782 100644 --- a/net/core/net-procfs.c +++ b/net/core/net-procfs.c @@ -349,6 +349,7 @@ static void __net_exit dev_proc_net_exit(struct net *net) static struct pernet_operations __net_initdata dev_proc_ops = { .init = dev_proc_net_init, .exit = dev_proc_net_exit, + .async = true, }; static int dev_mc_seq_show(struct seq_file *seq, void *v) @@ -405,6 +406,7 @@ static void __net_exit dev_mc_net_exit(struct net *net) static struct pernet_operations __net_initdata dev_mc_net_ops = { .init = dev_mc_net_init, .exit = dev_mc_net_exit, + .async = true, }; int __init dev_proc_init(void) diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index 3cad5f51afd3..690e78c6af45 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -29,7 +29,6 @@ static LIST_HEAD(pernet_list); static struct list_head *first_device = &pernet_list; -DEFINE_MUTEX(net_mutex); LIST_HEAD(net_namespace_list); EXPORT_SYMBOL_GPL(net_namespace_list); @@ -41,6 +40,12 @@ struct net init_net = { EXPORT_SYMBOL(init_net); static bool init_net_initialized; +static unsigned nr_sync_pernet_ops; +/* + * net_sem: protects: pernet_list, net_generic_ids, nr_sync_pernet_ops, + * init_net_initialized and first_device pointer. + */ +DECLARE_RWSEM(net_sem); #define MIN_PERNET_OPS_ID \ ((sizeof(struct net_generic) + sizeof(void *) - 1) / sizeof(void *)) @@ -65,11 +70,10 @@ static int net_assign_generic(struct net *net, unsigned int id, void *data) { struct net_generic *ng, *old_ng; - BUG_ON(!mutex_is_locked(&net_mutex)); BUG_ON(id < MIN_PERNET_OPS_ID); old_ng = rcu_dereference_protected(net->gen, - lockdep_is_held(&net_mutex)); + lockdep_is_held(&net_sem)); if (old_ng->s.len > id) { old_ng->ptr[id] = data; return 0; @@ -286,7 +290,7 @@ struct net *get_net_ns_by_id(struct net *net, int id) */ static __net_init int setup_net(struct net *net, struct user_namespace *user_ns) { - /* Must be called with net_mutex held */ + /* Must be called with net_sem held */ const struct pernet_operations *ops, *saved_ops; int error = 0; LIST_HEAD(net_exit_list); @@ -303,6 +307,9 @@ static __net_init int setup_net(struct net *net, struct user_namespace *user_ns) if (error < 0) goto out_undo; } + rtnl_lock(); + list_add_tail_rcu(&net->list, &net_namespace_list); + rtnl_unlock(); out: return error; @@ -331,6 +338,7 @@ static int __net_init net_defaults_init_net(struct net *net) static struct pernet_operations net_defaults_ops = { .init = net_defaults_init_net, + .async = true, }; static __init int net_defaults_init(void) @@ -354,7 +362,7 @@ static void dec_net_namespaces(struct ucounts *ucounts) dec_ucount(ucounts, UCOUNT_NET_NAMESPACES); } -static struct kmem_cache *net_cachep; +static struct kmem_cache *net_cachep __ro_after_init; static struct workqueue_struct *netns_wq; static struct net *net_alloc(void) @@ -397,6 +405,7 @@ struct net *copy_net_ns(unsigned long flags, { struct ucounts *ucounts; struct net *net; + unsigned write; int rv; if (!(flags & CLONE_NEWNET)) @@ -408,32 +417,38 @@ struct net *copy_net_ns(unsigned long flags, net = net_alloc(); if (!net) { - dec_net_namespaces(ucounts); - return ERR_PTR(-ENOMEM); + rv = -ENOMEM; + goto dec_ucounts; } - + refcount_set(&net->passive, 1); + net->ucounts = ucounts; get_user_ns(user_ns); +again: + write = READ_ONCE(nr_sync_pernet_ops); + if (write) + rv = down_write_killable(&net_sem); + else + rv = down_read_killable(&net_sem); + if (rv < 0) + goto put_userns; - rv = mutex_lock_killable(&net_mutex); - if (rv < 0) { - net_free(net); - dec_net_namespaces(ucounts); - put_user_ns(user_ns); - return ERR_PTR(rv); + if (!write && unlikely(READ_ONCE(nr_sync_pernet_ops))) { + up_read(&net_sem); + goto again; } - - net->ucounts = ucounts; rv = setup_net(net, user_ns); - if (rv == 0) { - rtnl_lock(); - list_add_tail_rcu(&net->list, &net_namespace_list); - rtnl_unlock(); - } - mutex_unlock(&net_mutex); + + if (write) + up_write(&net_sem); + else + up_read(&net_sem); + if (rv < 0) { - dec_net_namespaces(ucounts); +put_userns: put_user_ns(user_ns); net_drop_ns(net); +dec_ucounts: + dec_net_namespaces(ucounts); return ERR_PTR(rv); } return net; @@ -466,26 +481,33 @@ static void unhash_nsid(struct net *net, struct net *last) spin_unlock_bh(&net->nsid_lock); } -static DEFINE_SPINLOCK(cleanup_list_lock); -static LIST_HEAD(cleanup_list); /* Must hold cleanup_list_lock to touch */ +static LLIST_HEAD(cleanup_list); static void cleanup_net(struct work_struct *work) { const struct pernet_operations *ops; struct net *net, *tmp, *last; - struct list_head net_kill_list; + struct llist_node *net_kill_list; LIST_HEAD(net_exit_list); + unsigned write; /* Atomically snapshot the list of namespaces to cleanup */ - spin_lock_irq(&cleanup_list_lock); - list_replace_init(&cleanup_list, &net_kill_list); - spin_unlock_irq(&cleanup_list_lock); + net_kill_list = llist_del_all(&cleanup_list); +again: + write = READ_ONCE(nr_sync_pernet_ops); + if (write) + down_write(&net_sem); + else + down_read(&net_sem); - mutex_lock(&net_mutex); + if (!write && unlikely(READ_ONCE(nr_sync_pernet_ops))) { + up_read(&net_sem); + goto again; + } /* Don't let anyone else find us. */ rtnl_lock(); - list_for_each_entry(net, &net_kill_list, cleanup_list) + llist_for_each_entry(net, net_kill_list, cleanup_list) list_del_rcu(&net->list); /* Cache last net. After we unlock rtnl, no one new net * added to net_namespace_list can assign nsid pointer @@ -500,7 +522,7 @@ static void cleanup_net(struct work_struct *work) last = list_last_entry(&net_namespace_list, struct net, list); rtnl_unlock(); - list_for_each_entry(net, &net_kill_list, cleanup_list) { + llist_for_each_entry(net, net_kill_list, cleanup_list) { unhash_nsid(net, last); list_add_tail(&net->exit_list, &net_exit_list); } @@ -520,7 +542,10 @@ static void cleanup_net(struct work_struct *work) list_for_each_entry_reverse(ops, &pernet_list, list) ops_free_list(ops, &net_exit_list); - mutex_unlock(&net_mutex); + if (write) + up_write(&net_sem); + else + up_read(&net_sem); /* Ensure there are no outstanding rcu callbacks using this * network namespace. @@ -547,8 +572,8 @@ static void cleanup_net(struct work_struct *work) */ void net_ns_barrier(void) { - mutex_lock(&net_mutex); - mutex_unlock(&net_mutex); + down_write(&net_sem); + up_write(&net_sem); } EXPORT_SYMBOL(net_ns_barrier); @@ -557,13 +582,8 @@ static DECLARE_WORK(net_cleanup_work, cleanup_net); void __put_net(struct net *net) { /* Cleanup the network namespace in process context */ - unsigned long flags; - - spin_lock_irqsave(&cleanup_list_lock, flags); - list_add(&net->cleanup_list, &cleanup_list); - spin_unlock_irqrestore(&cleanup_list_lock, flags); - - queue_work(netns_wq, &net_cleanup_work); + if (llist_add(&net->cleanup_list, &cleanup_list)) + queue_work(netns_wq, &net_cleanup_work); } EXPORT_SYMBOL_GPL(__put_net); @@ -633,6 +653,7 @@ static __net_exit void net_ns_net_exit(struct net *net) static struct pernet_operations __net_initdata net_ns_ops = { .init = net_ns_net_init, .exit = net_ns_net_exit, + .async = true, }; static const struct nla_policy rtnl_net_policy[NETNSA_MAX + 1] = { @@ -875,17 +896,12 @@ static int __init net_ns_init(void) rcu_assign_pointer(init_net.gen, ng); - mutex_lock(&net_mutex); + down_write(&net_sem); if (setup_net(&init_net, &init_user_ns)) panic("Could not setup the initial network namespace"); init_net_initialized = true; - - rtnl_lock(); - list_add_tail_rcu(&init_net.list, &net_namespace_list); - rtnl_unlock(); - - mutex_unlock(&net_mutex); + up_write(&net_sem); register_pernet_subsys(&net_ns_ops); @@ -989,6 +1005,9 @@ again: rcu_barrier(); if (ops->id) ida_remove(&net_generic_ids, *ops->id); + } else if (!ops->async) { + pr_info_once("Pernet operations %ps are sync.\n", ops); + nr_sync_pernet_ops++; } return error; @@ -996,7 +1015,8 @@ again: static void unregister_pernet_operations(struct pernet_operations *ops) { - + if (!ops->async) + BUG_ON(nr_sync_pernet_ops-- == 0); __unregister_pernet_operations(ops); rcu_barrier(); if (ops->id) @@ -1025,9 +1045,9 @@ static void unregister_pernet_operations(struct pernet_operations *ops) int register_pernet_subsys(struct pernet_operations *ops) { int error; - mutex_lock(&net_mutex); + down_write(&net_sem); error = register_pernet_operations(first_device, ops); - mutex_unlock(&net_mutex); + up_write(&net_sem); return error; } EXPORT_SYMBOL_GPL(register_pernet_subsys); @@ -1043,9 +1063,9 @@ EXPORT_SYMBOL_GPL(register_pernet_subsys); */ void unregister_pernet_subsys(struct pernet_operations *ops) { - mutex_lock(&net_mutex); + down_write(&net_sem); unregister_pernet_operations(ops); - mutex_unlock(&net_mutex); + up_write(&net_sem); } EXPORT_SYMBOL_GPL(unregister_pernet_subsys); @@ -1071,11 +1091,11 @@ EXPORT_SYMBOL_GPL(unregister_pernet_subsys); int register_pernet_device(struct pernet_operations *ops) { int error; - mutex_lock(&net_mutex); + down_write(&net_sem); error = register_pernet_operations(&pernet_list, ops); if (!error && (first_device == &pernet_list)) first_device = &ops->list; - mutex_unlock(&net_mutex); + up_write(&net_sem); return error; } EXPORT_SYMBOL_GPL(register_pernet_device); @@ -1091,11 +1111,11 @@ EXPORT_SYMBOL_GPL(register_pernet_device); */ void unregister_pernet_device(struct pernet_operations *ops) { - mutex_lock(&net_mutex); + down_write(&net_sem); if (&ops->list == first_device) first_device = first_device->next; unregister_pernet_operations(ops); - mutex_unlock(&net_mutex); + up_write(&net_sem); } EXPORT_SYMBOL_GPL(unregister_pernet_device); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index bc290413a49d..67f375cfb982 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -454,11 +454,11 @@ static void rtnl_lock_unregistering_all(void) void rtnl_link_unregister(struct rtnl_link_ops *ops) { /* Close the race with cleanup_net() */ - mutex_lock(&net_mutex); + down_write(&net_sem); rtnl_lock_unregistering_all(); __rtnl_link_unregister(ops); rtnl_unlock(); - mutex_unlock(&net_mutex); + up_write(&net_sem); } EXPORT_SYMBOL_GPL(rtnl_link_unregister); @@ -4724,6 +4724,7 @@ static void __net_exit rtnetlink_net_exit(struct net *net) static struct pernet_operations rtnetlink_net_ops = { .init = rtnetlink_net_init, .exit = rtnetlink_net_exit, + .async = true, }; void __init rtnetlink_init(void) diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 0bb0d8877954..715c13495ba6 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -77,8 +77,8 @@ #include <linux/capability.h> #include <linux/user_namespace.h> -struct kmem_cache *skbuff_head_cache __read_mostly; -static struct kmem_cache *skbuff_fclone_cache __read_mostly; +struct kmem_cache *skbuff_head_cache __ro_after_init; +static struct kmem_cache *skbuff_fclone_cache __ro_after_init; int sysctl_max_skb_frags __read_mostly = MAX_SKB_FRAGS; EXPORT_SYMBOL(sysctl_max_skb_frags); @@ -890,7 +890,7 @@ struct sk_buff *skb_morph(struct sk_buff *dst, struct sk_buff *src) } EXPORT_SYMBOL_GPL(skb_morph); -static int mm_account_pinned_pages(struct mmpin *mmp, size_t size) +int mm_account_pinned_pages(struct mmpin *mmp, size_t size) { unsigned long max_pg, num_pg, new_pg, old_pg; struct user_struct *user; @@ -919,14 +919,16 @@ static int mm_account_pinned_pages(struct mmpin *mmp, size_t size) return 0; } +EXPORT_SYMBOL_GPL(mm_account_pinned_pages); -static void mm_unaccount_pinned_pages(struct mmpin *mmp) +void mm_unaccount_pinned_pages(struct mmpin *mmp) { if (mmp->user) { atomic_long_sub(mmp->num_pg, &mmp->user->locked_vm); free_uid(mmp->user); } } +EXPORT_SYMBOL_GPL(mm_unaccount_pinned_pages); struct ubuf_info *sock_zerocopy_alloc(struct sock *sk, size_t size) { diff --git a/net/core/sock.c b/net/core/sock.c index c501499a04fe..507d8c6c4319 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1049,18 +1049,21 @@ set_rcvbuf: break; case SO_ZEROCOPY: - if (sk->sk_family != PF_INET && sk->sk_family != PF_INET6) + if (sk->sk_family == PF_INET || sk->sk_family == PF_INET6) { + if (sk->sk_protocol != IPPROTO_TCP) + ret = -ENOTSUPP; + else if (sk->sk_state != TCP_CLOSE) + ret = -EBUSY; + } else if (sk->sk_family != PF_RDS) { ret = -ENOTSUPP; - else if (sk->sk_protocol != IPPROTO_TCP) - ret = -ENOTSUPP; - else if (sk->sk_state != TCP_CLOSE) - ret = -EBUSY; - else if (val < 0 || val > 1) - ret = -EINVAL; - else - sock_valbool_flag(sk, SOCK_ZEROCOPY, valbool); - break; - + } + if (!ret) { + if (val < 0 || val > 1) + ret = -EINVAL; + else + sock_valbool_flag(sk, SOCK_ZEROCOPY, valbool); + break; + } default: ret = -ENOPROTOOPT; break; @@ -1274,7 +1277,8 @@ int sock_getsockopt(struct socket *sock, int level, int optname, { char address[128]; - if (sock->ops->getname(sock, (struct sockaddr *)address, &lv, 2)) + lv = sock->ops->getname(sock, (struct sockaddr *)address, 2); + if (lv < 0) return -ENOTCONN; if (lv < len) return -EINVAL; @@ -1773,7 +1777,7 @@ void sk_setup_caps(struct sock *sk, struct dst_entry *dst) u32 max_segs = 1; sk_dst_set(sk, dst); - sk->sk_route_caps = dst->dev->features; + sk->sk_route_caps = dst->dev->features | sk->sk_route_forced_caps; if (sk->sk_route_caps & NETIF_F_GSO) sk->sk_route_caps |= NETIF_F_GSO_SOFTWARE; sk->sk_route_caps &= ~sk->sk_route_nocaps; @@ -2497,7 +2501,7 @@ int sock_no_accept(struct socket *sock, struct socket *newsock, int flags, EXPORT_SYMBOL(sock_no_accept); int sock_no_getname(struct socket *sock, struct sockaddr *saddr, - int *len, int peer) + int peer) { return -EOPNOTSUPP; } @@ -3111,6 +3115,7 @@ static void __net_exit sock_inuse_exit_net(struct net *net) static struct pernet_operations net_inuse_ops = { .init = sock_inuse_init_net, .exit = sock_inuse_exit_net, + .async = true, }; static __init int net_inuse_init(void) @@ -3384,6 +3389,7 @@ static __net_exit void proto_exit_net(struct net *net) static __net_initdata struct pernet_operations proto_net_ops = { .init = proto_init_net, .exit = proto_exit_net, + .async = true, }; static int __init proto_init(void) diff --git a/net/core/sock_diag.c b/net/core/sock_diag.c index 146b50e30659..aee5642affd9 100644 --- a/net/core/sock_diag.c +++ b/net/core/sock_diag.c @@ -328,6 +328,7 @@ static void __net_exit diag_net_exit(struct net *net) static struct pernet_operations diag_net_ops = { .init = diag_net_init, .exit = diag_net_exit, + .async = true, }; static int __init sock_diag_init(void) diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index f2d0462611c3..d714f65782b7 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -572,6 +572,7 @@ static __net_exit void sysctl_core_net_exit(struct net *net) static __net_initdata struct pernet_operations sysctl_core_ops = { .init = sysctl_core_net_init, .exit = sysctl_core_net_exit, + .async = true, }; static __init int sysctl_core_init(void) diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index e65fcb45c3f6..13ad28ab1e79 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -1031,6 +1031,7 @@ static struct pernet_operations dccp_v4_ops = { .init = dccp_v4_init_net, .exit = dccp_v4_exit_net, .exit_batch = dccp_v4_exit_batch, + .async = true, }; static int __init dccp_v4_init(void) diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index 5df7857fc0f3..2f48c020f8c3 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -1116,6 +1116,7 @@ static struct pernet_operations dccp_v6_ops = { .init = dccp_v6_init_net, .exit = dccp_v6_exit_net, .exit_batch = dccp_v6_exit_batch, + .async = true, }; static int __init dccp_v6_init(void) diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c index 791aff68af88..2ee8306c23e3 100644 --- a/net/decnet/af_decnet.c +++ b/net/decnet/af_decnet.c @@ -1180,14 +1180,12 @@ static int dn_accept(struct socket *sock, struct socket *newsock, int flags, } -static int dn_getname(struct socket *sock, struct sockaddr *uaddr,int *uaddr_len,int peer) +static int dn_getname(struct socket *sock, struct sockaddr *uaddr,int peer) { struct sockaddr_dn *sa = (struct sockaddr_dn *)uaddr; struct sock *sk = sock->sk; struct dn_scp *scp = DN_SK(sk); - *uaddr_len = sizeof(struct sockaddr_dn); - lock_sock(sk); if (peer) { @@ -1205,7 +1203,7 @@ static int dn_getname(struct socket *sock, struct sockaddr *uaddr,int *uaddr_len release_sock(sk); - return 0; + return sizeof(struct sockaddr_dn); } diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c index 6a9d0f50fbee..e63c554e0623 100644 --- a/net/dsa/dsa.c +++ b/net/dsa/dsa.c @@ -23,6 +23,7 @@ #include <linux/netdevice.h> #include <linux/sysfs.h> #include <linux/phy_fixed.h> +#include <linux/ptp_classify.h> #include <linux/gpio/consumer.h> #include <linux/etherdevice.h> @@ -122,6 +123,38 @@ struct net_device *dsa_dev_to_net_device(struct device *dev) } EXPORT_SYMBOL_GPL(dsa_dev_to_net_device); +/* Determine if we should defer delivery of skb until we have a rx timestamp. + * + * Called from dsa_switch_rcv. For now, this will only work if tagging is + * enabled on the switch. Normally the MAC driver would retrieve the hardware + * timestamp when it reads the packet out of the hardware. However in a DSA + * switch, the DSA driver owning the interface to which the packet is + * delivered is never notified unless we do so here. + */ +static bool dsa_skb_defer_rx_timestamp(struct dsa_slave_priv *p, + struct sk_buff *skb) +{ + struct dsa_switch *ds = p->dp->ds; + unsigned int type; + + if (skb_headroom(skb) < ETH_HLEN) + return false; + + __skb_push(skb, ETH_HLEN); + + type = ptp_classify_raw(skb); + + __skb_pull(skb, ETH_HLEN); + + if (type == PTP_CLASS_NONE) + return false; + + if (likely(ds->ops->port_rxtstamp)) + return ds->ops->port_rxtstamp(ds, p->dp->index, skb, type); + + return false; +} + static int dsa_switch_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *unused) { @@ -157,6 +190,9 @@ static int dsa_switch_rcv(struct sk_buff *skb, struct net_device *dev, s->rx_bytes += skb->len; u64_stats_update_end(&s->syncp); + if (dsa_skb_defer_rx_timestamp(p, skb)) + return 0; + netif_receive_skb(skb); return 0; diff --git a/net/dsa/master.c b/net/dsa/master.c index 00589147f042..90e6df0351eb 100644 --- a/net/dsa/master.c +++ b/net/dsa/master.c @@ -42,7 +42,7 @@ static int dsa_master_get_sset_count(struct net_device *dev, int sset) count += ops->get_sset_count(dev, sset); if (sset == ETH_SS_STATS && ds->ops->get_sset_count) - count += ds->ops->get_sset_count(ds); + count += ds->ops->get_sset_count(ds, cpu_dp->index); return count; } @@ -76,7 +76,7 @@ static void dsa_master_get_strings(struct net_device *dev, uint32_t stringset, * constructed earlier */ ds->ops->get_strings(ds, port, ndata); - count = ds->ops->get_sset_count(ds); + count = ds->ops->get_sset_count(ds, port); for (i = 0; i < count; i++) { memmove(ndata + (i * len + sizeof(pfx)), ndata + i * len, len - sizeof(pfx)); diff --git a/net/dsa/slave.c b/net/dsa/slave.c index f52307296de4..18561af7a8f1 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -21,6 +21,7 @@ #include <net/tc_act/tc_mirred.h> #include <linux/if_bridge.h> #include <linux/netpoll.h> +#include <linux/ptp_classify.h> #include "dsa_priv.h" @@ -255,6 +256,22 @@ dsa_slave_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb, static int dsa_slave_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) { + struct dsa_slave_priv *p = netdev_priv(dev); + struct dsa_switch *ds = p->dp->ds; + int port = p->dp->index; + + /* Pass through to switch driver if it supports timestamping */ + switch (cmd) { + case SIOCGHWTSTAMP: + if (ds->ops->port_hwtstamp_get) + return ds->ops->port_hwtstamp_get(ds, port, ifr); + break; + case SIOCSHWTSTAMP: + if (ds->ops->port_hwtstamp_set) + return ds->ops->port_hwtstamp_set(ds, port, ifr); + break; + } + if (!dev->phydev) return -ENODEV; @@ -385,6 +402,30 @@ static inline netdev_tx_t dsa_slave_netpoll_send_skb(struct net_device *dev, return NETDEV_TX_OK; } +static void dsa_skb_tx_timestamp(struct dsa_slave_priv *p, + struct sk_buff *skb) +{ + struct dsa_switch *ds = p->dp->ds; + struct sk_buff *clone; + unsigned int type; + + type = ptp_classify_raw(skb); + if (type == PTP_CLASS_NONE) + return; + + if (!ds->ops->port_txtstamp) + return; + + clone = skb_clone_sk(skb); + if (!clone) + return; + + if (ds->ops->port_txtstamp(ds, p->dp->index, clone, type)) + return; + + kfree_skb(clone); +} + static netdev_tx_t dsa_slave_xmit(struct sk_buff *skb, struct net_device *dev) { struct dsa_slave_priv *p = netdev_priv(dev); @@ -397,6 +438,11 @@ static netdev_tx_t dsa_slave_xmit(struct sk_buff *skb, struct net_device *dev) s->tx_bytes += skb->len; u64_stats_update_end(&s->syncp); + /* Identify PTP protocol packets, clone them, and pass them to the + * switch driver + */ + dsa_skb_tx_timestamp(p, skb); + /* Transmit function may have to reallocate the original SKB, * in which case it must have freed it. Only free it here on error. */ @@ -559,7 +605,7 @@ static int dsa_slave_get_sset_count(struct net_device *dev, int sset) count = 4; if (ds->ops->get_sset_count) - count += ds->ops->get_sset_count(ds); + count += ds->ops->get_sset_count(ds, dp->index); return count; } @@ -918,6 +964,18 @@ static int dsa_slave_set_rxnfc(struct net_device *dev, return ds->ops->set_rxnfc(ds, dp->index, nfc); } +static int dsa_slave_get_ts_info(struct net_device *dev, + struct ethtool_ts_info *ts) +{ + struct dsa_slave_priv *p = netdev_priv(dev); + struct dsa_switch *ds = p->dp->ds; + + if (!ds->ops->get_ts_info) + return -EOPNOTSUPP; + + return ds->ops->get_ts_info(ds, p->dp->index, ts); +} + static const struct ethtool_ops dsa_slave_ethtool_ops = { .get_drvinfo = dsa_slave_get_drvinfo, .get_regs_len = dsa_slave_get_regs_len, @@ -938,6 +996,7 @@ static const struct ethtool_ops dsa_slave_ethtool_ops = { .set_link_ksettings = phy_ethtool_set_link_ksettings, .get_rxnfc = dsa_slave_get_rxnfc, .set_rxnfc = dsa_slave_set_rxnfc, + .get_ts_info = dsa_slave_get_ts_info, }; /* legacy way, bypassing the bridge *****************************************/ diff --git a/net/ieee802154/6lowpan/core.c b/net/ieee802154/6lowpan/core.c index 974765b7d92a..e4f305320519 100644 --- a/net/ieee802154/6lowpan/core.c +++ b/net/ieee802154/6lowpan/core.c @@ -104,6 +104,7 @@ static void lowpan_setup(struct net_device *ldev) /* We need an ipv6hdr as minimum len when calling xmit */ ldev->hard_header_len = sizeof(struct ipv6hdr); ldev->flags = IFF_BROADCAST | IFF_MULTICAST; + ldev->priv_flags |= IFF_NO_QUEUE; ldev->netdev_ops = &lowpan_netdev_ops; ldev->header_ops = &lowpan_header_ops; diff --git a/net/ieee802154/core.c b/net/ieee802154/core.c index cb7176cd4cd6..9104943c15ba 100644 --- a/net/ieee802154/core.c +++ b/net/ieee802154/core.c @@ -345,6 +345,7 @@ static void __net_exit cfg802154_pernet_exit(struct net *net) static struct pernet_operations cfg802154_pernet_ops = { .exit = cfg802154_pernet_exit, + .async = true, }; static int __init wpan_phy_class_init(void) diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig index f48fe6fc7e8c..80dad301361d 100644 --- a/net/ipv4/Kconfig +++ b/net/ipv4/Kconfig @@ -212,9 +212,14 @@ config NET_IPGRE_BROADCAST Network), but can be distributed all over the Internet. If you want to do that, say Y here and to "IP multicast routing" below. +config IP_MROUTE_COMMON + bool + depends on IP_MROUTE || IPV6_MROUTE + config IP_MROUTE bool "IP: multicast routing" depends on IP_MULTICAST + select IP_MROUTE_COMMON help This is used if you want your machine to act as a router for IP packets that have several destination addresses. It is needed on the diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile index 47a0a6649a9d..a07b7dd06def 100644 --- a/net/ipv4/Makefile +++ b/net/ipv4/Makefile @@ -20,6 +20,7 @@ obj-$(CONFIG_SYSCTL) += sysctl_net_ipv4.o obj-$(CONFIG_PROC_FS) += proc.o obj-$(CONFIG_IP_MULTIPLE_TABLES) += fib_rules.o obj-$(CONFIG_IP_MROUTE) += ipmr.o +obj-$(CONFIG_IP_MROUTE_COMMON) += ipmr_base.o obj-$(CONFIG_NET_IPIP) += ipip.o gre-y := gre_demux.o obj-$(CONFIG_NET_FOU) += fou.o diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index e4329e161943..e8c7fad8c329 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -723,7 +723,7 @@ EXPORT_SYMBOL(inet_accept); * This does both peername and sockname. */ int inet_getname(struct socket *sock, struct sockaddr *uaddr, - int *uaddr_len, int peer) + int peer) { struct sock *sk = sock->sk; struct inet_sock *inet = inet_sk(sk); @@ -745,8 +745,7 @@ int inet_getname(struct socket *sock, struct sockaddr *uaddr, sin->sin_addr.s_addr = addr; } memset(sin->sin_zero, 0, sizeof(sin->sin_zero)); - *uaddr_len = sizeof(*sin); - return 0; + return sizeof(*sin); } EXPORT_SYMBOL(inet_getname); @@ -1736,6 +1735,7 @@ static __net_exit void ipv4_mib_exit_net(struct net *net) static __net_initdata struct pernet_operations ipv4_mib_ops = { .init = ipv4_mib_init_net, .exit = ipv4_mib_exit_net, + .async = true, }; static int __init init_ipv4_mibs(void) @@ -1789,6 +1789,7 @@ static __net_exit void inet_exit_net(struct net *net) static __net_initdata struct pernet_operations af_inet_ops = { .init = inet_init_net, .exit = inet_exit_net, + .async = true, }; static int __init init_inet_pernet_ops(void) diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index f28f06c91ead..7dc9de8444a9 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -1447,6 +1447,7 @@ static void __net_exit arp_net_exit(struct net *net) static struct pernet_operations arp_net_ops = { .init = arp_net_init, .exit = arp_net_exit, + .async = true, }; static int __init arp_proc_init(void) diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 40f001782c1b..5ae0d1f097ca 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -2469,6 +2469,7 @@ static __net_exit void devinet_exit_net(struct net *net) static __net_initdata struct pernet_operations devinet_ops = { .init = devinet_init_net, .exit = devinet_exit_net, + .async = true, }; static struct rtnl_af_ops inet_af_ops __read_mostly = { diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index f05afaf3235c..ac71c3d496c0 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -1362,6 +1362,7 @@ static void __net_exit fib_net_exit(struct net *net) static struct pernet_operations fib_net_ops = { .init = fib_net_init, .exit = fib_net_exit, + .async = true, }; void __init ip_fib_init(void) diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c index 35d646a62ad4..737d11bc8838 100644 --- a/net/ipv4/fib_rules.c +++ b/net/ipv4/fib_rules.c @@ -182,6 +182,17 @@ static int fib4_rule_match(struct fib_rule *rule, struct flowi *fl, int flags) if (r->tos && (r->tos != fl4->flowi4_tos)) return 0; + if (rule->ip_proto && (rule->ip_proto != fl4->flowi4_proto)) + return 0; + + if (fib_rule_port_range_set(&rule->sport_range) && + !fib_rule_port_inrange(&rule->sport_range, fl4->fl4_sport)) + return 0; + + if (fib_rule_port_range_set(&rule->dport_range) && + !fib_rule_port_inrange(&rule->dport_range, fl4->fl4_dport)) + return 0; + return 1; } @@ -244,6 +255,9 @@ static int fib4_rule_configure(struct fib_rule *rule, struct sk_buff *skb, } #endif + if (fib_rule_requires_fldissect(rule)) + net->ipv4.fib_rules_require_fldissect++; + rule4->src_len = frh->src_len; rule4->srcmask = inet_make_mask(rule4->src_len); rule4->dst_len = frh->dst_len; @@ -272,6 +286,10 @@ static int fib4_rule_delete(struct fib_rule *rule) net->ipv4.fib_num_tclassid_users--; #endif net->ipv4.fib_has_custom_rules = true; + + if (net->ipv4.fib_rules_require_fldissect && + fib_rule_requires_fldissect(rule)) + net->ipv4.fib_rules_require_fldissect--; errout: return err; } @@ -389,6 +407,7 @@ int __net_init fib4_rules_init(struct net *net) goto fail; net->ipv4.rules_ops = ops; net->ipv4.fib_has_custom_rules = false; + net->ipv4.fib_rules_require_fldissect = 0; return 0; fail: diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index 7d36a950d961..e7c602c600ac 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -171,7 +171,7 @@ static void free_nh_exceptions(struct fib_nh *nh) fnhe = rcu_dereference_protected(hash[i].chain, 1); while (fnhe) { struct fib_nh_exception *next; - + next = rcu_dereference_protected(fnhe->fnhe_next, 1); rt_fibinfo_free(&fnhe->fnhe_rth_input); @@ -1765,14 +1765,12 @@ void fib_select_multipath(struct fib_result *res, int hash) void fib_select_path(struct net *net, struct fib_result *res, struct flowi4 *fl4, const struct sk_buff *skb) { - bool oif_check; - - oif_check = (fl4->flowi4_oif == 0 || - fl4->flowi4_flags & FLOWI_FLAG_SKIP_NH_OIF); + if (fl4->flowi4_oif && !(fl4->flowi4_flags & FLOWI_FLAG_SKIP_NH_OIF)) + goto check_saddr; #ifdef CONFIG_IP_ROUTE_MULTIPATH - if (res->fi->fib_nhs > 1 && oif_check) { - int h = fib_multipath_hash(res->fi, fl4, skb); + if (res->fi->fib_nhs > 1) { + int h = fib_multipath_hash(net, fl4, skb, NULL); fib_select_multipath(res, h); } @@ -1780,10 +1778,10 @@ void fib_select_path(struct net *net, struct fib_result *res, #endif if (!res->prefixlen && res->table->tb_num_default > 1 && - res->type == RTN_UNICAST && oif_check) + res->type == RTN_UNICAST) fib_select_default(fl4, res); +check_saddr: if (!fl4->saddr) fl4->saddr = FIB_RES_PREFSRC(net, *res); } -EXPORT_SYMBOL_GPL(fib_select_path); diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 5530cd6fdbc7..62243a8abf92 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -50,6 +50,7 @@ #define VERSION "0.409" +#include <linux/cache.h> #include <linux/uaccess.h> #include <linux/bitops.h> #include <linux/types.h> @@ -191,8 +192,8 @@ static size_t tnode_free_size; */ static const int sync_pages = 128; -static struct kmem_cache *fn_alias_kmem __read_mostly; -static struct kmem_cache *trie_leaf_kmem __read_mostly; +static struct kmem_cache *fn_alias_kmem __ro_after_init; +static struct kmem_cache *trie_leaf_kmem __ro_after_init; static inline struct tnode *tn_info(struct key_vector *kv) { diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c index 1540db65241a..d3e1a9af478b 100644 --- a/net/ipv4/fou.c +++ b/net/ipv4/fou.c @@ -1081,6 +1081,7 @@ static struct pernet_operations fou_net_ops = { .exit = fou_exit_net, .id = &fou_net_id, .size = sizeof(struct fou_net), + .async = true, }; static int __init fou_init(void) diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 1617604c9284..cc56efa64d5c 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -1257,6 +1257,7 @@ fail: static struct pernet_operations __net_initdata icmp_sk_ops = { .init = icmp_sk_init, .exit = icmp_sk_exit, + .async = true, }; int __init icmp_init(void) diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index f2402581fef1..c2743763777e 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -3028,6 +3028,7 @@ static void __net_exit igmp_net_exit(struct net *net) static struct pernet_operations igmp_net_ops = { .init = igmp_net_init, .exit = igmp_net_exit, + .async = true, }; #endif diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c index 914d56928578..1f04bd91fc2e 100644 --- a/net/ipv4/inetpeer.c +++ b/net/ipv4/inetpeer.c @@ -6,6 +6,7 @@ * Authors: Andrey V. Savochkin <saw@msu.ru> */ +#include <linux/cache.h> #include <linux/module.h> #include <linux/types.h> #include <linux/slab.h> @@ -51,7 +52,7 @@ * daddr: unchangeable */ -static struct kmem_cache *peer_cachep __read_mostly; +static struct kmem_cache *peer_cachep __ro_after_init; void inet_peer_base_init(struct inet_peer_base *bp) { diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index bbf1b94942c0..5e843ae5e468 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -885,6 +885,7 @@ static void __net_exit ipv4_frags_exit_net(struct net *net) static struct pernet_operations ip4_frags_ops = { .init = ipv4_frags_init_net, .exit = ipv4_frags_exit_net, + .async = true, }; void __init ipfrag_init(void) diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 0901de42ed85..2fa2ef2e2af9 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -522,6 +522,7 @@ err_free_skb: static void gre_fb_xmit(struct sk_buff *skb, struct net_device *dev, __be16 proto) { + struct ip_tunnel *tunnel = netdev_priv(dev); struct ip_tunnel_info *tun_info; const struct ip_tunnel_key *key; struct rtable *rt = NULL; @@ -545,9 +546,11 @@ static void gre_fb_xmit(struct sk_buff *skb, struct net_device *dev, if (gre_handle_offloads(skb, !!(tun_info->key.tun_flags & TUNNEL_CSUM))) goto err_free_rt; - flags = tun_info->key.tun_flags & (TUNNEL_CSUM | TUNNEL_KEY); + flags = tun_info->key.tun_flags & + (TUNNEL_CSUM | TUNNEL_KEY | TUNNEL_SEQ); gre_build_header(skb, tunnel_hlen, flags, proto, - tunnel_id_to_key32(tun_info->key.tun_id), 0); + tunnel_id_to_key32(tun_info->key.tun_id), + (flags | TUNNEL_SEQ) ? htonl(tunnel->o_seqno++) : 0); df = key->tun_flags & TUNNEL_DONT_FRAGMENT ? htons(IP_DF) : 0; @@ -1041,6 +1044,7 @@ static struct pernet_operations ipgre_net_ops = { .exit_batch = ipgre_exit_batch_net, .id = &ipgre_net_id, .size = sizeof(struct ip_tunnel_net), + .async = true, }; static int ipgre_tunnel_validate(struct nlattr *tb[], struct nlattr *data[], @@ -1317,6 +1321,12 @@ static void ipgre_tap_setup(struct net_device *dev) ip_tunnel_setup(dev, gre_tap_net_id); } +bool is_gretap_dev(const struct net_device *dev) +{ + return dev->netdev_ops == &gre_tap_netdev_ops; +} +EXPORT_SYMBOL_GPL(is_gretap_dev); + static int ipgre_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) @@ -1618,6 +1628,7 @@ static struct pernet_operations ipgre_tap_net_ops = { .exit_batch = ipgre_tap_exit_batch_net, .id = &gre_tap_net_id, .size = sizeof(struct ip_tunnel_net), + .async = true, }; static int __net_init erspan_init_net(struct net *net) @@ -1636,6 +1647,7 @@ static struct pernet_operations erspan_net_ops = { .exit_batch = erspan_exit_batch_net, .id = &erspan_net_id, .size = sizeof(struct ip_tunnel_net), + .async = true, }; static int __init ipgre_init(void) diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 9c41a0cef1a5..74c962b9b09c 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -258,7 +258,8 @@ int ip_cmsg_send(struct sock *sk, struct msghdr *msg, struct ipcm_cookie *ipc, src_info = (struct in6_pktinfo *)CMSG_DATA(cmsg); if (!ipv6_addr_v4mapped(&src_info->ipi6_addr)) return -EINVAL; - ipc->oif = src_info->ipi6_ifindex; + if (src_info->ipi6_ifindex) + ipc->oif = src_info->ipi6_ifindex; ipc->addr = src_info->ipi6_addr.s6_addr32[3]; continue; } @@ -288,7 +289,8 @@ int ip_cmsg_send(struct sock *sk, struct msghdr *msg, struct ipcm_cookie *ipc, if (cmsg->cmsg_len != CMSG_LEN(sizeof(struct in_pktinfo))) return -EINVAL; info = (struct in_pktinfo *)CMSG_DATA(cmsg); - ipc->oif = info->ipi_ifindex; + if (info->ipi_ifindex) + ipc->oif = info->ipi_ifindex; ipc->addr = info->ipi_spec_dst.s_addr; break; } diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index 6d21068f9b55..602597dfc395 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -290,22 +290,6 @@ failed: return ERR_PTR(err); } -static inline void init_tunnel_flow(struct flowi4 *fl4, - int proto, - __be32 daddr, __be32 saddr, - __be32 key, __u8 tos, int oif, - __u32 mark) -{ - memset(fl4, 0, sizeof(*fl4)); - fl4->flowi4_oif = oif; - fl4->daddr = daddr; - fl4->saddr = saddr; - fl4->flowi4_tos = tos; - fl4->flowi4_proto = proto; - fl4->fl4_gre_key = key; - fl4->flowi4_mark = mark; -} - static int ip_tunnel_bind_dev(struct net_device *dev) { struct net_device *tdev = NULL; @@ -322,10 +306,10 @@ static int ip_tunnel_bind_dev(struct net_device *dev) struct flowi4 fl4; struct rtable *rt; - init_tunnel_flow(&fl4, iph->protocol, iph->daddr, - iph->saddr, tunnel->parms.o_key, - RT_TOS(iph->tos), tunnel->parms.link, - tunnel->fwmark); + ip_tunnel_init_flow(&fl4, iph->protocol, iph->daddr, + iph->saddr, tunnel->parms.o_key, + RT_TOS(iph->tos), tunnel->parms.link, + tunnel->fwmark); rt = ip_route_output_key(tunnel->net, &fl4); if (!IS_ERR(rt)) { @@ -581,8 +565,8 @@ void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, u8 proto) else if (skb->protocol == htons(ETH_P_IPV6)) tos = ipv6_get_dsfield((const struct ipv6hdr *)inner_iph); } - init_tunnel_flow(&fl4, proto, key->u.ipv4.dst, key->u.ipv4.src, 0, - RT_TOS(tos), tunnel->parms.link, tunnel->fwmark); + ip_tunnel_init_flow(&fl4, proto, key->u.ipv4.dst, key->u.ipv4.src, 0, + RT_TOS(tos), tunnel->parms.link, tunnel->fwmark); if (tunnel->encap.type != TUNNEL_ENCAP_NONE) goto tx_error; rt = ip_route_output_key(tunnel->net, &fl4); @@ -710,9 +694,9 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, } } - init_tunnel_flow(&fl4, protocol, dst, tnl_params->saddr, - tunnel->parms.o_key, RT_TOS(tos), tunnel->parms.link, - tunnel->fwmark); + ip_tunnel_init_flow(&fl4, protocol, dst, tnl_params->saddr, + tunnel->parms.o_key, RT_TOS(tos), tunnel->parms.link, + tunnel->fwmark); if (ip_tunnel_encap(skb, tunnel, &protocol, &fl4) < 0) goto tx_error; diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index 51b1669334fe..b10bf563afd9 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -454,6 +454,7 @@ static struct pernet_operations vti_net_ops = { .exit_batch = vti_exit_batch_net, .id = &vti_net_id, .size = sizeof(struct ip_tunnel_net), + .async = true, }; static int vti_tunnel_validate(struct nlattr *tb[], struct nlattr *data[], diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index c891235b4966..9c5a4d164f09 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -669,6 +669,7 @@ static struct pernet_operations ipip_net_ops = { .exit_batch = ipip_exit_batch_net, .id = &ipip_net_id, .size = sizeof(struct ip_tunnel_net), + .async = true, }; static int __init ipip_init(void) diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index b05689bbba31..d752a70855d8 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -28,9 +28,9 @@ #include <linux/uaccess.h> #include <linux/types.h> +#include <linux/cache.h> #include <linux/capability.h> #include <linux/errno.h> -#include <linux/timer.h> #include <linux/mm.h> #include <linux/kernel.h> #include <linux/fcntl.h> @@ -52,7 +52,6 @@ #include <net/protocol.h> #include <linux/skbuff.h> #include <net/route.h> -#include <net/sock.h> #include <net/icmp.h> #include <net/udp.h> #include <net/raw.h> @@ -96,7 +95,7 @@ static DEFINE_SPINLOCK(mfc_unres_lock); * In this case data path is free of exclusive locks at all. */ -static struct kmem_cache *mrt_cachep __read_mostly; +static struct kmem_cache *mrt_cachep __ro_after_init; static struct mr_table *ipmr_new_table(struct net *net, u32 id); static void ipmr_free_table(struct mr_table *mrt); @@ -106,8 +105,6 @@ static void ip_mr_forward(struct net *net, struct mr_table *mrt, struct mfc_cache *cache, int local); static int ipmr_cache_report(struct mr_table *mrt, struct sk_buff *pkt, vifi_t vifi, int assert); -static int __ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb, - struct mfc_cache *c, struct rtmsg *rtm); static void mroute_netlink_event(struct mr_table *mrt, struct mfc_cache *mfc, int cmd); static void igmpmsg_netlink_event(struct mr_table *mrt, struct sk_buff *pkt); @@ -118,6 +115,23 @@ static void ipmr_expire_process(struct timer_list *t); #define ipmr_for_each_table(mrt, net) \ list_for_each_entry_rcu(mrt, &net->ipv4.mr_tables, list) +static struct mr_table *ipmr_mr_table_iter(struct net *net, + struct mr_table *mrt) +{ + struct mr_table *ret; + + if (!mrt) + ret = list_entry_rcu(net->ipv4.mr_tables.next, + struct mr_table, list); + else + ret = list_entry_rcu(mrt->list.next, + struct mr_table, list); + + if (&ret->list == &net->ipv4.mr_tables) + return NULL; + return ret; +} + static struct mr_table *ipmr_get_table(struct net *net, u32 id) { struct mr_table *mrt; @@ -285,6 +299,14 @@ EXPORT_SYMBOL(ipmr_rule_default); #define ipmr_for_each_table(mrt, net) \ for (mrt = net->ipv4.mrt; mrt; mrt = NULL) +static struct mr_table *ipmr_mr_table_iter(struct net *net, + struct mr_table *mrt) +{ + if (!mrt) + return net->ipv4.mrt; + return NULL; +} + static struct mr_table *ipmr_get_table(struct net *net, u32 id) { return net->ipv4.mrt; @@ -344,7 +366,7 @@ static inline int ipmr_hash_cmp(struct rhashtable_compare_arg *arg, } static const struct rhashtable_params ipmr_rht_params = { - .head_offset = offsetof(struct mfc_cache, mnode), + .head_offset = offsetof(struct mr_mfc, mnode), .key_offset = offsetof(struct mfc_cache, cmparg), .key_len = sizeof(struct mfc_cache_cmp_arg), .nelem_hint = 3, @@ -353,6 +375,24 @@ static const struct rhashtable_params ipmr_rht_params = { .automatic_shrinking = true, }; +static void ipmr_new_table_set(struct mr_table *mrt, + struct net *net) +{ +#ifdef CONFIG_IP_MROUTE_MULTIPLE_TABLES + list_add_tail_rcu(&mrt->list, &net->ipv4.mr_tables); +#endif +} + +static struct mfc_cache_cmp_arg ipmr_mr_table_ops_cmparg_any = { + .mfc_mcastgrp = htonl(INADDR_ANY), + .mfc_origin = htonl(INADDR_ANY), +}; + +static struct mr_table_ops ipmr_mr_table_ops = { + .rht_params = &ipmr_rht_params, + .cmparg_any = &ipmr_mr_table_ops_cmparg_any, +}; + static struct mr_table *ipmr_new_table(struct net *net, u32 id) { struct mr_table *mrt; @@ -365,23 +405,8 @@ static struct mr_table *ipmr_new_table(struct net *net, u32 id) if (mrt) return mrt; - mrt = kzalloc(sizeof(*mrt), GFP_KERNEL); - if (!mrt) - return ERR_PTR(-ENOMEM); - write_pnet(&mrt->net, net); - mrt->id = id; - - rhltable_init(&mrt->mfc_hash, &ipmr_rht_params); - INIT_LIST_HEAD(&mrt->mfc_cache_list); - INIT_LIST_HEAD(&mrt->mfc_unres_queue); - - timer_setup(&mrt->ipmr_expire_timer, ipmr_expire_process, 0); - - mrt->mroute_reg_vif_num = -1; -#ifdef CONFIG_IP_MROUTE_MULTIPLE_TABLES - list_add_tail_rcu(&mrt->list, &net->ipv4.mr_tables); -#endif - return mrt; + return mr_table_alloc(net, id, &ipmr_mr_table_ops, + ipmr_expire_process, ipmr_new_table_set); } static void ipmr_free_table(struct mr_table *mrt) @@ -760,14 +785,14 @@ static int vif_delete(struct mr_table *mrt, int vifi, int notify, static void ipmr_cache_free_rcu(struct rcu_head *head) { - struct mfc_cache *c = container_of(head, struct mfc_cache, rcu); + struct mr_mfc *c = container_of(head, struct mr_mfc, rcu); - kmem_cache_free(mrt_cachep, c); + kmem_cache_free(mrt_cachep, (struct mfc_cache *)c); } void ipmr_cache_free(struct mfc_cache *c) { - call_rcu(&c->rcu, ipmr_cache_free_rcu); + call_rcu(&c->_c.rcu, ipmr_cache_free_rcu); } EXPORT_SYMBOL(ipmr_cache_free); @@ -782,7 +807,7 @@ static void ipmr_destroy_unres(struct mr_table *mrt, struct mfc_cache *c) atomic_dec(&mrt->cache_resolve_queue_len); - while ((skb = skb_dequeue(&c->mfc_un.unres.unresolved))) { + while ((skb = skb_dequeue(&c->_c.mfc_un.unres.unresolved))) { if (ip_hdr(skb)->version == 0) { struct nlmsghdr *nlh = skb_pull(skb, sizeof(struct iphdr)); @@ -806,9 +831,9 @@ static void ipmr_destroy_unres(struct mr_table *mrt, struct mfc_cache *c) static void ipmr_expire_process(struct timer_list *t) { struct mr_table *mrt = from_timer(mrt, t, ipmr_expire_timer); - unsigned long now; + struct mr_mfc *c, *next; unsigned long expires; - struct mfc_cache *c, *next; + unsigned long now; if (!spin_trylock(&mfc_unres_lock)) { mod_timer(&mrt->ipmr_expire_timer, jiffies+HZ/10); @@ -830,8 +855,8 @@ static void ipmr_expire_process(struct timer_list *t) } list_del(&c->list); - mroute_netlink_event(mrt, c, RTM_DELROUTE); - ipmr_destroy_unres(mrt, c); + mroute_netlink_event(mrt, (struct mfc_cache *)c, RTM_DELROUTE); + ipmr_destroy_unres(mrt, (struct mfc_cache *)c); } if (!list_empty(&mrt->mfc_unres_queue)) @@ -842,7 +867,7 @@ out: } /* Fill oifs list. It is called under write locked mrt_lock. */ -static void ipmr_update_thresholds(struct mr_table *mrt, struct mfc_cache *cache, +static void ipmr_update_thresholds(struct mr_table *mrt, struct mr_mfc *cache, unsigned char *ttls) { int vifi; @@ -944,6 +969,10 @@ static int vif_add(struct net *net, struct mr_table *mrt, ip_rt_multicast_event(in_dev); /* Fill in the VIF structures */ + vif_device_init(v, dev, vifc->vifc_rate_limit, + vifc->vifc_threshold, + vifc->vifc_flags | (!mrtsock ? VIFF_STATIC : 0), + (VIFF_TUNNEL | VIFF_REGISTER)); attr.orig_dev = dev; if (!switchdev_port_attr_get(dev, &attr)) { @@ -952,20 +981,9 @@ static int vif_add(struct net *net, struct mr_table *mrt, } else { v->dev_parent_id.id_len = 0; } - v->rate_limit = vifc->vifc_rate_limit; + v->local = vifc->vifc_lcl_addr.s_addr; v->remote = vifc->vifc_rmt_addr.s_addr; - v->flags = vifc->vifc_flags; - if (!mrtsock) - v->flags |= VIFF_STATIC; - v->threshold = vifc->vifc_threshold; - v->bytes_in = 0; - v->bytes_out = 0; - v->pkt_in = 0; - v->pkt_out = 0; - v->link = dev->ifindex; - if (v->flags & (VIFF_TUNNEL | VIFF_REGISTER)) - v->link = dev_get_iflink(dev); /* And finish update writing critical data */ write_lock_bh(&mrt_lock); @@ -988,33 +1006,8 @@ static struct mfc_cache *ipmr_cache_find(struct mr_table *mrt, .mfc_mcastgrp = mcastgrp, .mfc_origin = origin }; - struct rhlist_head *tmp, *list; - struct mfc_cache *c; - - list = rhltable_lookup(&mrt->mfc_hash, &arg, ipmr_rht_params); - rhl_for_each_entry_rcu(c, tmp, list, mnode) - return c; - - return NULL; -} - -/* Look for a (*,*,oif) entry */ -static struct mfc_cache *ipmr_cache_find_any_parent(struct mr_table *mrt, - int vifi) -{ - struct mfc_cache_cmp_arg arg = { - .mfc_mcastgrp = htonl(INADDR_ANY), - .mfc_origin = htonl(INADDR_ANY) - }; - struct rhlist_head *tmp, *list; - struct mfc_cache *c; - list = rhltable_lookup(&mrt->mfc_hash, &arg, ipmr_rht_params); - rhl_for_each_entry_rcu(c, tmp, list, mnode) - if (c->mfc_un.res.ttls[vifi] < 255) - return c; - - return NULL; + return mr_mfc_find(mrt, &arg); } /* Look for a (*,G) entry */ @@ -1025,25 +1018,10 @@ static struct mfc_cache *ipmr_cache_find_any(struct mr_table *mrt, .mfc_mcastgrp = mcastgrp, .mfc_origin = htonl(INADDR_ANY) }; - struct rhlist_head *tmp, *list; - struct mfc_cache *c, *proxy; if (mcastgrp == htonl(INADDR_ANY)) - goto skip; - - list = rhltable_lookup(&mrt->mfc_hash, &arg, ipmr_rht_params); - rhl_for_each_entry_rcu(c, tmp, list, mnode) { - if (c->mfc_un.res.ttls[vifi] < 255) - return c; - - /* It's ok if the vifi is part of the static tree */ - proxy = ipmr_cache_find_any_parent(mrt, c->mfc_parent); - if (proxy && proxy->mfc_un.res.ttls[vifi] < 255) - return c; - } - -skip: - return ipmr_cache_find_any_parent(mrt, vifi); + return mr_mfc_find_any_parent(mrt, vifi); + return mr_mfc_find_any(mrt, vifi, &arg); } /* Look for a (S,G,iif) entry if parent != -1 */ @@ -1055,15 +1033,8 @@ static struct mfc_cache *ipmr_cache_find_parent(struct mr_table *mrt, .mfc_mcastgrp = mcastgrp, .mfc_origin = origin, }; - struct rhlist_head *tmp, *list; - struct mfc_cache *c; - - list = rhltable_lookup(&mrt->mfc_hash, &arg, ipmr_rht_params); - rhl_for_each_entry_rcu(c, tmp, list, mnode) - if (parent == -1 || parent == c->mfc_parent) - return c; - return NULL; + return mr_mfc_find_parent(mrt, &arg, parent); } /* Allocate a multicast cache entry */ @@ -1072,9 +1043,9 @@ static struct mfc_cache *ipmr_cache_alloc(void) struct mfc_cache *c = kmem_cache_zalloc(mrt_cachep, GFP_KERNEL); if (c) { - c->mfc_un.res.last_assert = jiffies - MFC_ASSERT_THRESH - 1; - c->mfc_un.res.minvif = MAXVIFS; - refcount_set(&c->mfc_un.res.refcount, 1); + c->_c.mfc_un.res.last_assert = jiffies - MFC_ASSERT_THRESH - 1; + c->_c.mfc_un.res.minvif = MAXVIFS; + refcount_set(&c->_c.mfc_un.res.refcount, 1); } return c; } @@ -1084,8 +1055,8 @@ static struct mfc_cache *ipmr_cache_alloc_unres(void) struct mfc_cache *c = kmem_cache_zalloc(mrt_cachep, GFP_ATOMIC); if (c) { - skb_queue_head_init(&c->mfc_un.unres.unresolved); - c->mfc_un.unres.expires = jiffies + 10*HZ; + skb_queue_head_init(&c->_c.mfc_un.unres.unresolved); + c->_c.mfc_un.unres.expires = jiffies + 10 * HZ; } return c; } @@ -1098,12 +1069,13 @@ static void ipmr_cache_resolve(struct net *net, struct mr_table *mrt, struct nlmsgerr *e; /* Play the pending entries through our router */ - while ((skb = __skb_dequeue(&uc->mfc_un.unres.unresolved))) { + while ((skb = __skb_dequeue(&uc->_c.mfc_un.unres.unresolved))) { if (ip_hdr(skb)->version == 0) { struct nlmsghdr *nlh = skb_pull(skb, sizeof(struct iphdr)); - if (__ipmr_fill_mroute(mrt, skb, c, nlmsg_data(nlh)) > 0) { + if (mr_fill_mroute(mrt, skb, &c->_c, + nlmsg_data(nlh)) > 0) { nlh->nlmsg_len = skb_tail_pointer(skb) - (u8 *)nlh; } else { @@ -1211,7 +1183,7 @@ static int ipmr_cache_unresolved(struct mr_table *mrt, vifi_t vifi, int err; spin_lock_bh(&mfc_unres_lock); - list_for_each_entry(c, &mrt->mfc_unres_queue, list) { + list_for_each_entry(c, &mrt->mfc_unres_queue, _c.list) { if (c->mfc_mcastgrp == iph->daddr && c->mfc_origin == iph->saddr) { found = true; @@ -1230,12 +1202,13 @@ static int ipmr_cache_unresolved(struct mr_table *mrt, vifi_t vifi, } /* Fill in the new cache entry */ - c->mfc_parent = -1; + c->_c.mfc_parent = -1; c->mfc_origin = iph->saddr; c->mfc_mcastgrp = iph->daddr; /* Reflect first query at mrouted. */ err = ipmr_cache_report(mrt, skb, vifi, IGMPMSG_NOCACHE); + if (err < 0) { /* If the report failed throw the cache entry out - Brad Parker @@ -1248,15 +1221,16 @@ static int ipmr_cache_unresolved(struct mr_table *mrt, vifi_t vifi, } atomic_inc(&mrt->cache_resolve_queue_len); - list_add(&c->list, &mrt->mfc_unres_queue); + list_add(&c->_c.list, &mrt->mfc_unres_queue); mroute_netlink_event(mrt, c, RTM_NEWROUTE); if (atomic_read(&mrt->cache_resolve_queue_len) == 1) - mod_timer(&mrt->ipmr_expire_timer, c->mfc_un.unres.expires); + mod_timer(&mrt->ipmr_expire_timer, + c->_c.mfc_un.unres.expires); } /* See if we can append the packet */ - if (c->mfc_un.unres.unresolved.qlen > 3) { + if (c->_c.mfc_un.unres.unresolved.qlen > 3) { kfree_skb(skb); err = -ENOBUFS; } else { @@ -1264,7 +1238,7 @@ static int ipmr_cache_unresolved(struct mr_table *mrt, vifi_t vifi, skb->dev = dev; skb->skb_iif = dev->ifindex; } - skb_queue_tail(&c->mfc_un.unres.unresolved, skb); + skb_queue_tail(&c->_c.mfc_un.unres.unresolved, skb); err = 0; } @@ -1286,8 +1260,8 @@ static int ipmr_mfc_delete(struct mr_table *mrt, struct mfcctl *mfc, int parent) rcu_read_unlock(); if (!c) return -ENOENT; - rhltable_remove(&mrt->mfc_hash, &c->mnode, ipmr_rht_params); - list_del_rcu(&c->list); + rhltable_remove(&mrt->mfc_hash, &c->_c.mnode, ipmr_rht_params); + list_del_rcu(&c->_c.list); call_ipmr_mfc_entry_notifiers(net, FIB_EVENT_ENTRY_DEL, c, mrt->id); mroute_netlink_event(mrt, c, RTM_DELROUTE); ipmr_cache_put(c); @@ -1299,6 +1273,7 @@ static int ipmr_mfc_add(struct net *net, struct mr_table *mrt, struct mfcctl *mfc, int mrtsock, int parent) { struct mfc_cache *uc, *c; + struct mr_mfc *_uc; bool found; int ret; @@ -1312,10 +1287,10 @@ static int ipmr_mfc_add(struct net *net, struct mr_table *mrt, rcu_read_unlock(); if (c) { write_lock_bh(&mrt_lock); - c->mfc_parent = mfc->mfcc_parent; - ipmr_update_thresholds(mrt, c, mfc->mfcc_ttls); + c->_c.mfc_parent = mfc->mfcc_parent; + ipmr_update_thresholds(mrt, &c->_c, mfc->mfcc_ttls); if (!mrtsock) - c->mfc_flags |= MFC_STATIC; + c->_c.mfc_flags |= MFC_STATIC; write_unlock_bh(&mrt_lock); call_ipmr_mfc_entry_notifiers(net, FIB_EVENT_ENTRY_REPLACE, c, mrt->id); @@ -1333,28 +1308,29 @@ static int ipmr_mfc_add(struct net *net, struct mr_table *mrt, c->mfc_origin = mfc->mfcc_origin.s_addr; c->mfc_mcastgrp = mfc->mfcc_mcastgrp.s_addr; - c->mfc_parent = mfc->mfcc_parent; - ipmr_update_thresholds(mrt, c, mfc->mfcc_ttls); + c->_c.mfc_parent = mfc->mfcc_parent; + ipmr_update_thresholds(mrt, &c->_c, mfc->mfcc_ttls); if (!mrtsock) - c->mfc_flags |= MFC_STATIC; + c->_c.mfc_flags |= MFC_STATIC; - ret = rhltable_insert_key(&mrt->mfc_hash, &c->cmparg, &c->mnode, + ret = rhltable_insert_key(&mrt->mfc_hash, &c->cmparg, &c->_c.mnode, ipmr_rht_params); if (ret) { pr_err("ipmr: rhtable insert error %d\n", ret); ipmr_cache_free(c); return ret; } - list_add_tail_rcu(&c->list, &mrt->mfc_cache_list); + list_add_tail_rcu(&c->_c.list, &mrt->mfc_cache_list); /* Check to see if we resolved a queued list. If so we * need to send on the frames and tidy up. */ found = false; spin_lock_bh(&mfc_unres_lock); - list_for_each_entry(uc, &mrt->mfc_unres_queue, list) { + list_for_each_entry(_uc, &mrt->mfc_unres_queue, list) { + uc = (struct mfc_cache *)_uc; if (uc->mfc_origin == c->mfc_origin && uc->mfc_mcastgrp == c->mfc_mcastgrp) { - list_del(&uc->list); + list_del(&_uc->list); atomic_dec(&mrt->cache_resolve_queue_len); found = true; break; @@ -1377,7 +1353,8 @@ static int ipmr_mfc_add(struct net *net, struct mr_table *mrt, static void mroute_clean_tables(struct mr_table *mrt, bool all) { struct net *net = read_pnet(&mrt->net); - struct mfc_cache *c, *tmp; + struct mr_mfc *c, *tmp; + struct mfc_cache *cache; LIST_HEAD(list); int i; @@ -1395,18 +1372,20 @@ static void mroute_clean_tables(struct mr_table *mrt, bool all) continue; rhltable_remove(&mrt->mfc_hash, &c->mnode, ipmr_rht_params); list_del_rcu(&c->list); - call_ipmr_mfc_entry_notifiers(net, FIB_EVENT_ENTRY_DEL, c, + cache = (struct mfc_cache *)c; + call_ipmr_mfc_entry_notifiers(net, FIB_EVENT_ENTRY_DEL, cache, mrt->id); - mroute_netlink_event(mrt, c, RTM_DELROUTE); - ipmr_cache_put(c); + mroute_netlink_event(mrt, cache, RTM_DELROUTE); + ipmr_cache_put(cache); } if (atomic_read(&mrt->cache_resolve_queue_len) != 0) { spin_lock_bh(&mfc_unres_lock); list_for_each_entry_safe(c, tmp, &mrt->mfc_unres_queue, list) { list_del(&c->list); - mroute_netlink_event(mrt, c, RTM_DELROUTE); - ipmr_destroy_unres(mrt, c); + cache = (struct mfc_cache *)c; + mroute_netlink_event(mrt, cache, RTM_DELROUTE); + ipmr_destroy_unres(mrt, cache); } spin_unlock_bh(&mfc_unres_lock); } @@ -1698,9 +1677,9 @@ int ipmr_ioctl(struct sock *sk, int cmd, void __user *arg) rcu_read_lock(); c = ipmr_cache_find(mrt, sr.src.s_addr, sr.grp.s_addr); if (c) { - sr.pktcnt = c->mfc_un.res.pkt; - sr.bytecnt = c->mfc_un.res.bytes; - sr.wrong_if = c->mfc_un.res.wrong_if; + sr.pktcnt = c->_c.mfc_un.res.pkt; + sr.bytecnt = c->_c.mfc_un.res.bytes; + sr.wrong_if = c->_c.mfc_un.res.wrong_if; rcu_read_unlock(); if (copy_to_user(arg, &sr, sizeof(sr))) @@ -1772,9 +1751,9 @@ int ipmr_compat_ioctl(struct sock *sk, unsigned int cmd, void __user *arg) rcu_read_lock(); c = ipmr_cache_find(mrt, sr.src.s_addr, sr.grp.s_addr); if (c) { - sr.pktcnt = c->mfc_un.res.pkt; - sr.bytecnt = c->mfc_un.res.bytes; - sr.wrong_if = c->mfc_un.res.wrong_if; + sr.pktcnt = c->_c.mfc_un.res.pkt; + sr.bytecnt = c->_c.mfc_un.res.bytes; + sr.wrong_if = c->_c.mfc_un.res.wrong_if; rcu_read_unlock(); if (copy_to_user(arg, &sr, sizeof(sr))) @@ -1998,26 +1977,26 @@ static int ipmr_find_vif(struct mr_table *mrt, struct net_device *dev) /* "local" means that we should preserve one skb (for local delivery) */ static void ip_mr_forward(struct net *net, struct mr_table *mrt, struct net_device *dev, struct sk_buff *skb, - struct mfc_cache *cache, int local) + struct mfc_cache *c, int local) { int true_vifi = ipmr_find_vif(mrt, dev); int psend = -1; int vif, ct; - vif = cache->mfc_parent; - cache->mfc_un.res.pkt++; - cache->mfc_un.res.bytes += skb->len; - cache->mfc_un.res.lastuse = jiffies; + vif = c->_c.mfc_parent; + c->_c.mfc_un.res.pkt++; + c->_c.mfc_un.res.bytes += skb->len; + c->_c.mfc_un.res.lastuse = jiffies; - if (cache->mfc_origin == htonl(INADDR_ANY) && true_vifi >= 0) { + if (c->mfc_origin == htonl(INADDR_ANY) && true_vifi >= 0) { struct mfc_cache *cache_proxy; /* For an (*,G) entry, we only check that the incomming * interface is part of the static tree. */ - cache_proxy = ipmr_cache_find_any_parent(mrt, vif); + cache_proxy = mr_mfc_find_any_parent(mrt, vif); if (cache_proxy && - cache_proxy->mfc_un.res.ttls[true_vifi] < 255) + cache_proxy->_c.mfc_un.res.ttls[true_vifi] < 255) goto forward; } @@ -2038,7 +2017,7 @@ static void ip_mr_forward(struct net *net, struct mr_table *mrt, goto dont_forward; } - cache->mfc_un.res.wrong_if++; + c->_c.mfc_un.res.wrong_if++; if (true_vifi >= 0 && mrt->mroute_do_assert && /* pimsm uses asserts, when switching from RPT to SPT, @@ -2047,10 +2026,11 @@ static void ip_mr_forward(struct net *net, struct mr_table *mrt, * large chunk of pimd to kernel. Ough... --ANK */ (mrt->mroute_do_pim || - cache->mfc_un.res.ttls[true_vifi] < 255) && + c->_c.mfc_un.res.ttls[true_vifi] < 255) && time_after(jiffies, - cache->mfc_un.res.last_assert + MFC_ASSERT_THRESH)) { - cache->mfc_un.res.last_assert = jiffies; + c->_c.mfc_un.res.last_assert + + MFC_ASSERT_THRESH)) { + c->_c.mfc_un.res.last_assert = jiffies; ipmr_cache_report(mrt, skb, true_vifi, IGMPMSG_WRONGVIF); } goto dont_forward; @@ -2061,33 +2041,33 @@ forward: mrt->vif_table[vif].bytes_in += skb->len; /* Forward the frame */ - if (cache->mfc_origin == htonl(INADDR_ANY) && - cache->mfc_mcastgrp == htonl(INADDR_ANY)) { + if (c->mfc_origin == htonl(INADDR_ANY) && + c->mfc_mcastgrp == htonl(INADDR_ANY)) { if (true_vifi >= 0 && - true_vifi != cache->mfc_parent && + true_vifi != c->_c.mfc_parent && ip_hdr(skb)->ttl > - cache->mfc_un.res.ttls[cache->mfc_parent]) { + c->_c.mfc_un.res.ttls[c->_c.mfc_parent]) { /* It's an (*,*) entry and the packet is not coming from * the upstream: forward the packet to the upstream * only. */ - psend = cache->mfc_parent; + psend = c->_c.mfc_parent; goto last_forward; } goto dont_forward; } - for (ct = cache->mfc_un.res.maxvif - 1; - ct >= cache->mfc_un.res.minvif; ct--) { + for (ct = c->_c.mfc_un.res.maxvif - 1; + ct >= c->_c.mfc_un.res.minvif; ct--) { /* For (*,G) entry, don't forward to the incoming interface */ - if ((cache->mfc_origin != htonl(INADDR_ANY) || + if ((c->mfc_origin != htonl(INADDR_ANY) || ct != true_vifi) && - ip_hdr(skb)->ttl > cache->mfc_un.res.ttls[ct]) { + ip_hdr(skb)->ttl > c->_c.mfc_un.res.ttls[ct]) { if (psend != -1) { struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC); if (skb2) ipmr_queue_xmit(net, mrt, true_vifi, - skb2, cache, psend); + skb2, c, psend); } psend = ct; } @@ -2099,9 +2079,9 @@ last_forward: if (skb2) ipmr_queue_xmit(net, mrt, true_vifi, skb2, - cache, psend); + c, psend); } else { - ipmr_queue_xmit(net, mrt, true_vifi, skb, cache, psend); + ipmr_queue_xmit(net, mrt, true_vifi, skb, c, psend); return; } } @@ -2299,62 +2279,6 @@ drop: } #endif -static int __ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb, - struct mfc_cache *c, struct rtmsg *rtm) -{ - struct rta_mfc_stats mfcs; - struct nlattr *mp_attr; - struct rtnexthop *nhp; - unsigned long lastuse; - int ct; - - /* If cache is unresolved, don't try to parse IIF and OIF */ - if (c->mfc_parent >= MAXVIFS) { - rtm->rtm_flags |= RTNH_F_UNRESOLVED; - return -ENOENT; - } - - if (VIF_EXISTS(mrt, c->mfc_parent) && - nla_put_u32(skb, RTA_IIF, mrt->vif_table[c->mfc_parent].dev->ifindex) < 0) - return -EMSGSIZE; - - if (c->mfc_flags & MFC_OFFLOAD) - rtm->rtm_flags |= RTNH_F_OFFLOAD; - - if (!(mp_attr = nla_nest_start(skb, RTA_MULTIPATH))) - return -EMSGSIZE; - - for (ct = c->mfc_un.res.minvif; ct < c->mfc_un.res.maxvif; ct++) { - if (VIF_EXISTS(mrt, ct) && c->mfc_un.res.ttls[ct] < 255) { - if (!(nhp = nla_reserve_nohdr(skb, sizeof(*nhp)))) { - nla_nest_cancel(skb, mp_attr); - return -EMSGSIZE; - } - - nhp->rtnh_flags = 0; - nhp->rtnh_hops = c->mfc_un.res.ttls[ct]; - nhp->rtnh_ifindex = mrt->vif_table[ct].dev->ifindex; - nhp->rtnh_len = sizeof(*nhp); - } - } - - nla_nest_end(skb, mp_attr); - - lastuse = READ_ONCE(c->mfc_un.res.lastuse); - lastuse = time_after_eq(jiffies, lastuse) ? jiffies - lastuse : 0; - - mfcs.mfcs_packets = c->mfc_un.res.pkt; - mfcs.mfcs_bytes = c->mfc_un.res.bytes; - mfcs.mfcs_wrong_if = c->mfc_un.res.wrong_if; - if (nla_put_64bit(skb, RTA_MFC_STATS, sizeof(mfcs), &mfcs, RTA_PAD) || - nla_put_u64_64bit(skb, RTA_EXPIRES, jiffies_to_clock_t(lastuse), - RTA_PAD)) - return -EMSGSIZE; - - rtm->rtm_type = RTN_MULTICAST; - return 1; -} - int ipmr_get_route(struct net *net, struct sk_buff *skb, __be32 saddr, __be32 daddr, struct rtmsg *rtm, u32 portid) @@ -2412,7 +2336,7 @@ int ipmr_get_route(struct net *net, struct sk_buff *skb, } read_lock(&mrt_lock); - err = __ipmr_fill_mroute(mrt, skb, cache, rtm); + err = mr_fill_mroute(mrt, skb, &cache->_c, rtm); read_unlock(&mrt_lock); rcu_read_unlock(); return err; @@ -2440,7 +2364,7 @@ static int ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb, goto nla_put_failure; rtm->rtm_type = RTN_MULTICAST; rtm->rtm_scope = RT_SCOPE_UNIVERSE; - if (c->mfc_flags & MFC_STATIC) + if (c->_c.mfc_flags & MFC_STATIC) rtm->rtm_protocol = RTPROT_STATIC; else rtm->rtm_protocol = RTPROT_MROUTED; @@ -2449,7 +2373,7 @@ static int ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb, if (nla_put_in_addr(skb, RTA_SRC, c->mfc_origin) || nla_put_in_addr(skb, RTA_DST, c->mfc_mcastgrp)) goto nla_put_failure; - err = __ipmr_fill_mroute(mrt, skb, c, rtm); + err = mr_fill_mroute(mrt, skb, &c->_c, rtm); /* do not break the dump if cache is unresolved */ if (err < 0 && err != -ENOENT) goto nla_put_failure; @@ -2462,6 +2386,14 @@ nla_put_failure: return -EMSGSIZE; } +static int _ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb, + u32 portid, u32 seq, struct mr_mfc *c, int cmd, + int flags) +{ + return ipmr_fill_mroute(mrt, skb, portid, seq, (struct mfc_cache *)c, + cmd, flags); +} + static size_t mroute_msgsize(bool unresolved, int maxvif) { size_t len = @@ -2490,7 +2422,8 @@ static void mroute_netlink_event(struct mr_table *mrt, struct mfc_cache *mfc, struct sk_buff *skb; int err = -ENOBUFS; - skb = nlmsg_new(mroute_msgsize(mfc->mfc_parent >= MAXVIFS, mrt->maxvif), + skb = nlmsg_new(mroute_msgsize(mfc->_c.mfc_parent >= MAXVIFS, + mrt->maxvif), GFP_ATOMIC); if (!skb) goto errout; @@ -2634,62 +2567,8 @@ errout_free: static int ipmr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb) { - struct net *net = sock_net(skb->sk); - struct mr_table *mrt; - struct mfc_cache *mfc; - unsigned int t = 0, s_t; - unsigned int e = 0, s_e; - - s_t = cb->args[0]; - s_e = cb->args[1]; - - rcu_read_lock(); - ipmr_for_each_table(mrt, net) { - if (t < s_t) - goto next_table; - list_for_each_entry_rcu(mfc, &mrt->mfc_cache_list, list) { - if (e < s_e) - goto next_entry; - if (ipmr_fill_mroute(mrt, skb, - NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, - mfc, RTM_NEWROUTE, - NLM_F_MULTI) < 0) - goto done; -next_entry: - e++; - } - e = 0; - s_e = 0; - - spin_lock_bh(&mfc_unres_lock); - list_for_each_entry(mfc, &mrt->mfc_unres_queue, list) { - if (e < s_e) - goto next_entry2; - if (ipmr_fill_mroute(mrt, skb, - NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, - mfc, RTM_NEWROUTE, - NLM_F_MULTI) < 0) { - spin_unlock_bh(&mfc_unres_lock); - goto done; - } -next_entry2: - e++; - } - spin_unlock_bh(&mfc_unres_lock); - e = 0; - s_e = 0; -next_table: - t++; - } -done: - rcu_read_unlock(); - - cb->args[1] = e; - cb->args[0] = t; - - return skb->len; + return mr_rtm_dumproute(skb, cb, ipmr_mr_table_iter, + _ipmr_fill_mroute, &mfc_unres_lock); } static const struct nla_policy rtm_ipmr_policy[RTA_MAX + 1] = { @@ -2946,31 +2825,11 @@ out: /* The /proc interfaces to multicast routing : * /proc/net/ip_mr_cache & /proc/net/ip_mr_vif */ -struct ipmr_vif_iter { - struct seq_net_private p; - struct mr_table *mrt; - int ct; -}; - -static struct vif_device *ipmr_vif_seq_idx(struct net *net, - struct ipmr_vif_iter *iter, - loff_t pos) -{ - struct mr_table *mrt = iter->mrt; - - for (iter->ct = 0; iter->ct < mrt->maxvif; ++iter->ct) { - if (!VIF_EXISTS(mrt, iter->ct)) - continue; - if (pos-- == 0) - return &mrt->vif_table[iter->ct]; - } - return NULL; -} static void *ipmr_vif_seq_start(struct seq_file *seq, loff_t *pos) __acquires(mrt_lock) { - struct ipmr_vif_iter *iter = seq->private; + struct mr_vif_iter *iter = seq->private; struct net *net = seq_file_net(seq); struct mr_table *mrt; @@ -2981,26 +2840,7 @@ static void *ipmr_vif_seq_start(struct seq_file *seq, loff_t *pos) iter->mrt = mrt; read_lock(&mrt_lock); - return *pos ? ipmr_vif_seq_idx(net, seq->private, *pos - 1) - : SEQ_START_TOKEN; -} - -static void *ipmr_vif_seq_next(struct seq_file *seq, void *v, loff_t *pos) -{ - struct ipmr_vif_iter *iter = seq->private; - struct net *net = seq_file_net(seq); - struct mr_table *mrt = iter->mrt; - - ++*pos; - if (v == SEQ_START_TOKEN) - return ipmr_vif_seq_idx(net, iter, 0); - - while (++iter->ct < mrt->maxvif) { - if (!VIF_EXISTS(mrt, iter->ct)) - continue; - return &mrt->vif_table[iter->ct]; - } - return NULL; + return mr_vif_seq_start(seq, pos); } static void ipmr_vif_seq_stop(struct seq_file *seq, void *v) @@ -3011,7 +2851,7 @@ static void ipmr_vif_seq_stop(struct seq_file *seq, void *v) static int ipmr_vif_seq_show(struct seq_file *seq, void *v) { - struct ipmr_vif_iter *iter = seq->private; + struct mr_vif_iter *iter = seq->private; struct mr_table *mrt = iter->mrt; if (v == SEQ_START_TOKEN) { @@ -3019,7 +2859,8 @@ static int ipmr_vif_seq_show(struct seq_file *seq, void *v) "Interface BytesIn PktsIn BytesOut PktsOut Flags Local Remote\n"); } else { const struct vif_device *vif = v; - const char *name = vif->dev ? vif->dev->name : "none"; + const char *name = vif->dev ? + vif->dev->name : "none"; seq_printf(seq, "%2td %-10s %8ld %7ld %8ld %7ld %05X %08X %08X\n", @@ -3033,7 +2874,7 @@ static int ipmr_vif_seq_show(struct seq_file *seq, void *v) static const struct seq_operations ipmr_vif_seq_ops = { .start = ipmr_vif_seq_start, - .next = ipmr_vif_seq_next, + .next = mr_vif_seq_next, .stop = ipmr_vif_seq_stop, .show = ipmr_vif_seq_show, }; @@ -3041,7 +2882,7 @@ static const struct seq_operations ipmr_vif_seq_ops = { static int ipmr_vif_open(struct inode *inode, struct file *file) { return seq_open_net(inode, file, &ipmr_vif_seq_ops, - sizeof(struct ipmr_vif_iter)); + sizeof(struct mr_vif_iter)); } static const struct file_operations ipmr_vif_fops = { @@ -3051,40 +2892,8 @@ static const struct file_operations ipmr_vif_fops = { .release = seq_release_net, }; -struct ipmr_mfc_iter { - struct seq_net_private p; - struct mr_table *mrt; - struct list_head *cache; -}; - -static struct mfc_cache *ipmr_mfc_seq_idx(struct net *net, - struct ipmr_mfc_iter *it, loff_t pos) -{ - struct mr_table *mrt = it->mrt; - struct mfc_cache *mfc; - - rcu_read_lock(); - it->cache = &mrt->mfc_cache_list; - list_for_each_entry_rcu(mfc, &mrt->mfc_cache_list, list) - if (pos-- == 0) - return mfc; - rcu_read_unlock(); - - spin_lock_bh(&mfc_unres_lock); - it->cache = &mrt->mfc_unres_queue; - list_for_each_entry(mfc, it->cache, list) - if (pos-- == 0) - return mfc; - spin_unlock_bh(&mfc_unres_lock); - - it->cache = NULL; - return NULL; -} - - static void *ipmr_mfc_seq_start(struct seq_file *seq, loff_t *pos) { - struct ipmr_mfc_iter *it = seq->private; struct net *net = seq_file_net(seq); struct mr_table *mrt; @@ -3092,54 +2901,7 @@ static void *ipmr_mfc_seq_start(struct seq_file *seq, loff_t *pos) if (!mrt) return ERR_PTR(-ENOENT); - it->mrt = mrt; - it->cache = NULL; - return *pos ? ipmr_mfc_seq_idx(net, seq->private, *pos - 1) - : SEQ_START_TOKEN; -} - -static void *ipmr_mfc_seq_next(struct seq_file *seq, void *v, loff_t *pos) -{ - struct ipmr_mfc_iter *it = seq->private; - struct net *net = seq_file_net(seq); - struct mr_table *mrt = it->mrt; - struct mfc_cache *mfc = v; - - ++*pos; - - if (v == SEQ_START_TOKEN) - return ipmr_mfc_seq_idx(net, seq->private, 0); - - if (mfc->list.next != it->cache) - return list_entry(mfc->list.next, struct mfc_cache, list); - - if (it->cache == &mrt->mfc_unres_queue) - goto end_of_list; - - /* exhausted cache_array, show unresolved */ - rcu_read_unlock(); - it->cache = &mrt->mfc_unres_queue; - - spin_lock_bh(&mfc_unres_lock); - if (!list_empty(it->cache)) - return list_first_entry(it->cache, struct mfc_cache, list); - -end_of_list: - spin_unlock_bh(&mfc_unres_lock); - it->cache = NULL; - - return NULL; -} - -static void ipmr_mfc_seq_stop(struct seq_file *seq, void *v) -{ - struct ipmr_mfc_iter *it = seq->private; - struct mr_table *mrt = it->mrt; - - if (it->cache == &mrt->mfc_unres_queue) - spin_unlock_bh(&mfc_unres_lock); - else if (it->cache == &mrt->mfc_cache_list) - rcu_read_unlock(); + return mr_mfc_seq_start(seq, pos, mrt, &mfc_unres_lock); } static int ipmr_mfc_seq_show(struct seq_file *seq, void *v) @@ -3151,26 +2913,26 @@ static int ipmr_mfc_seq_show(struct seq_file *seq, void *v) "Group Origin Iif Pkts Bytes Wrong Oifs\n"); } else { const struct mfc_cache *mfc = v; - const struct ipmr_mfc_iter *it = seq->private; + const struct mr_mfc_iter *it = seq->private; const struct mr_table *mrt = it->mrt; seq_printf(seq, "%08X %08X %-3hd", (__force u32) mfc->mfc_mcastgrp, (__force u32) mfc->mfc_origin, - mfc->mfc_parent); + mfc->_c.mfc_parent); if (it->cache != &mrt->mfc_unres_queue) { seq_printf(seq, " %8lu %8lu %8lu", - mfc->mfc_un.res.pkt, - mfc->mfc_un.res.bytes, - mfc->mfc_un.res.wrong_if); - for (n = mfc->mfc_un.res.minvif; - n < mfc->mfc_un.res.maxvif; n++) { + mfc->_c.mfc_un.res.pkt, + mfc->_c.mfc_un.res.bytes, + mfc->_c.mfc_un.res.wrong_if); + for (n = mfc->_c.mfc_un.res.minvif; + n < mfc->_c.mfc_un.res.maxvif; n++) { if (VIF_EXISTS(mrt, n) && - mfc->mfc_un.res.ttls[n] < 255) + mfc->_c.mfc_un.res.ttls[n] < 255) seq_printf(seq, " %2d:%-3d", - n, mfc->mfc_un.res.ttls[n]); + n, mfc->_c.mfc_un.res.ttls[n]); } } else { /* unresolved mfc_caches don't contain @@ -3185,15 +2947,15 @@ static int ipmr_mfc_seq_show(struct seq_file *seq, void *v) static const struct seq_operations ipmr_mfc_seq_ops = { .start = ipmr_mfc_seq_start, - .next = ipmr_mfc_seq_next, - .stop = ipmr_mfc_seq_stop, + .next = mr_mfc_seq_next, + .stop = mr_mfc_seq_stop, .show = ipmr_mfc_seq_show, }; static int ipmr_mfc_open(struct inode *inode, struct file *file) { return seq_open_net(inode, file, &ipmr_mfc_seq_ops, - sizeof(struct ipmr_mfc_iter)); + sizeof(struct mr_mfc_iter)); } static const struct file_operations ipmr_mfc_fops = { @@ -3229,7 +2991,7 @@ static int ipmr_dump(struct net *net, struct notifier_block *nb) ipmr_for_each_table(mrt, net) { struct vif_device *v = &mrt->vif_table[0]; - struct mfc_cache *mfc; + struct mr_mfc *mfc; int vifi; /* Notifiy on table VIF entries */ @@ -3246,7 +3008,8 @@ static int ipmr_dump(struct net *net, struct notifier_block *nb) /* Notify on table MFC entries */ list_for_each_entry_rcu(mfc, &mrt->mfc_cache_list, list) call_ipmr_mfc_entry_notifier(nb, net, - FIB_EVENT_ENTRY_ADD, mfc, + FIB_EVENT_ENTRY_ADD, + (struct mfc_cache *)mfc, mrt->id); } @@ -3327,6 +3090,7 @@ static void __net_exit ipmr_net_exit(struct net *net) static struct pernet_operations ipmr_net_ops = { .init = ipmr_net_init, .exit = ipmr_net_exit, + .async = true, }; int __init ip_mr_init(void) diff --git a/net/ipv4/ipmr_base.c b/net/ipv4/ipmr_base.c new file mode 100644 index 000000000000..8ba55bfda817 --- /dev/null +++ b/net/ipv4/ipmr_base.c @@ -0,0 +1,323 @@ +/* Linux multicast routing support + * Common logic shared by IPv4 [ipmr] and IPv6 [ip6mr] implementation + */ + +#include <linux/mroute_base.h> + +/* Sets everything common except 'dev', since that is done under locking */ +void vif_device_init(struct vif_device *v, + struct net_device *dev, + unsigned long rate_limit, + unsigned char threshold, + unsigned short flags, + unsigned short get_iflink_mask) +{ + v->dev = NULL; + v->bytes_in = 0; + v->bytes_out = 0; + v->pkt_in = 0; + v->pkt_out = 0; + v->rate_limit = rate_limit; + v->flags = flags; + v->threshold = threshold; + if (v->flags & get_iflink_mask) + v->link = dev_get_iflink(dev); + else + v->link = dev->ifindex; +} +EXPORT_SYMBOL(vif_device_init); + +struct mr_table * +mr_table_alloc(struct net *net, u32 id, + struct mr_table_ops *ops, + void (*expire_func)(struct timer_list *t), + void (*table_set)(struct mr_table *mrt, + struct net *net)) +{ + struct mr_table *mrt; + + mrt = kzalloc(sizeof(*mrt), GFP_KERNEL); + if (!mrt) + return NULL; + mrt->id = id; + write_pnet(&mrt->net, net); + + mrt->ops = *ops; + rhltable_init(&mrt->mfc_hash, mrt->ops.rht_params); + INIT_LIST_HEAD(&mrt->mfc_cache_list); + INIT_LIST_HEAD(&mrt->mfc_unres_queue); + + timer_setup(&mrt->ipmr_expire_timer, expire_func, 0); + + mrt->mroute_reg_vif_num = -1; + table_set(mrt, net); + return mrt; +} +EXPORT_SYMBOL(mr_table_alloc); + +void *mr_mfc_find_parent(struct mr_table *mrt, void *hasharg, int parent) +{ + struct rhlist_head *tmp, *list; + struct mr_mfc *c; + + list = rhltable_lookup(&mrt->mfc_hash, hasharg, *mrt->ops.rht_params); + rhl_for_each_entry_rcu(c, tmp, list, mnode) + if (parent == -1 || parent == c->mfc_parent) + return c; + + return NULL; +} +EXPORT_SYMBOL(mr_mfc_find_parent); + +void *mr_mfc_find_any_parent(struct mr_table *mrt, int vifi) +{ + struct rhlist_head *tmp, *list; + struct mr_mfc *c; + + list = rhltable_lookup(&mrt->mfc_hash, mrt->ops.cmparg_any, + *mrt->ops.rht_params); + rhl_for_each_entry_rcu(c, tmp, list, mnode) + if (c->mfc_un.res.ttls[vifi] < 255) + return c; + + return NULL; +} +EXPORT_SYMBOL(mr_mfc_find_any_parent); + +void *mr_mfc_find_any(struct mr_table *mrt, int vifi, void *hasharg) +{ + struct rhlist_head *tmp, *list; + struct mr_mfc *c, *proxy; + + list = rhltable_lookup(&mrt->mfc_hash, hasharg, *mrt->ops.rht_params); + rhl_for_each_entry_rcu(c, tmp, list, mnode) { + if (c->mfc_un.res.ttls[vifi] < 255) + return c; + + /* It's ok if the vifi is part of the static tree */ + proxy = mr_mfc_find_any_parent(mrt, c->mfc_parent); + if (proxy && proxy->mfc_un.res.ttls[vifi] < 255) + return c; + } + + return mr_mfc_find_any_parent(mrt, vifi); +} +EXPORT_SYMBOL(mr_mfc_find_any); + +#ifdef CONFIG_PROC_FS +void *mr_vif_seq_idx(struct net *net, struct mr_vif_iter *iter, loff_t pos) +{ + struct mr_table *mrt = iter->mrt; + + for (iter->ct = 0; iter->ct < mrt->maxvif; ++iter->ct) { + if (!VIF_EXISTS(mrt, iter->ct)) + continue; + if (pos-- == 0) + return &mrt->vif_table[iter->ct]; + } + return NULL; +} +EXPORT_SYMBOL(mr_vif_seq_idx); + +void *mr_vif_seq_next(struct seq_file *seq, void *v, loff_t *pos) +{ + struct mr_vif_iter *iter = seq->private; + struct net *net = seq_file_net(seq); + struct mr_table *mrt = iter->mrt; + + ++*pos; + if (v == SEQ_START_TOKEN) + return mr_vif_seq_idx(net, iter, 0); + + while (++iter->ct < mrt->maxvif) { + if (!VIF_EXISTS(mrt, iter->ct)) + continue; + return &mrt->vif_table[iter->ct]; + } + return NULL; +} +EXPORT_SYMBOL(mr_vif_seq_next); + +void *mr_mfc_seq_idx(struct net *net, + struct mr_mfc_iter *it, loff_t pos) +{ + struct mr_table *mrt = it->mrt; + struct mr_mfc *mfc; + + rcu_read_lock(); + it->cache = &mrt->mfc_cache_list; + list_for_each_entry_rcu(mfc, &mrt->mfc_cache_list, list) + if (pos-- == 0) + return mfc; + rcu_read_unlock(); + + spin_lock_bh(it->lock); + it->cache = &mrt->mfc_unres_queue; + list_for_each_entry(mfc, it->cache, list) + if (pos-- == 0) + return mfc; + spin_unlock_bh(it->lock); + + it->cache = NULL; + return NULL; +} +EXPORT_SYMBOL(mr_mfc_seq_idx); + +void *mr_mfc_seq_next(struct seq_file *seq, void *v, + loff_t *pos) +{ + struct mr_mfc_iter *it = seq->private; + struct net *net = seq_file_net(seq); + struct mr_table *mrt = it->mrt; + struct mr_mfc *c = v; + + ++*pos; + + if (v == SEQ_START_TOKEN) + return mr_mfc_seq_idx(net, seq->private, 0); + + if (c->list.next != it->cache) + return list_entry(c->list.next, struct mr_mfc, list); + + if (it->cache == &mrt->mfc_unres_queue) + goto end_of_list; + + /* exhausted cache_array, show unresolved */ + rcu_read_unlock(); + it->cache = &mrt->mfc_unres_queue; + + spin_lock_bh(it->lock); + if (!list_empty(it->cache)) + return list_first_entry(it->cache, struct mr_mfc, list); + +end_of_list: + spin_unlock_bh(it->lock); + it->cache = NULL; + + return NULL; +} +EXPORT_SYMBOL(mr_mfc_seq_next); +#endif + +int mr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb, + struct mr_mfc *c, struct rtmsg *rtm) +{ + struct rta_mfc_stats mfcs; + struct nlattr *mp_attr; + struct rtnexthop *nhp; + unsigned long lastuse; + int ct; + + /* If cache is unresolved, don't try to parse IIF and OIF */ + if (c->mfc_parent >= MAXVIFS) { + rtm->rtm_flags |= RTNH_F_UNRESOLVED; + return -ENOENT; + } + + if (VIF_EXISTS(mrt, c->mfc_parent) && + nla_put_u32(skb, RTA_IIF, + mrt->vif_table[c->mfc_parent].dev->ifindex) < 0) + return -EMSGSIZE; + + if (c->mfc_flags & MFC_OFFLOAD) + rtm->rtm_flags |= RTNH_F_OFFLOAD; + + mp_attr = nla_nest_start(skb, RTA_MULTIPATH); + if (!mp_attr) + return -EMSGSIZE; + + for (ct = c->mfc_un.res.minvif; ct < c->mfc_un.res.maxvif; ct++) { + if (VIF_EXISTS(mrt, ct) && c->mfc_un.res.ttls[ct] < 255) { + struct vif_device *vif; + + nhp = nla_reserve_nohdr(skb, sizeof(*nhp)); + if (!nhp) { + nla_nest_cancel(skb, mp_attr); + return -EMSGSIZE; + } + + nhp->rtnh_flags = 0; + nhp->rtnh_hops = c->mfc_un.res.ttls[ct]; + vif = &mrt->vif_table[ct]; + nhp->rtnh_ifindex = vif->dev->ifindex; + nhp->rtnh_len = sizeof(*nhp); + } + } + + nla_nest_end(skb, mp_attr); + + lastuse = READ_ONCE(c->mfc_un.res.lastuse); + lastuse = time_after_eq(jiffies, lastuse) ? jiffies - lastuse : 0; + + mfcs.mfcs_packets = c->mfc_un.res.pkt; + mfcs.mfcs_bytes = c->mfc_un.res.bytes; + mfcs.mfcs_wrong_if = c->mfc_un.res.wrong_if; + if (nla_put_64bit(skb, RTA_MFC_STATS, sizeof(mfcs), &mfcs, RTA_PAD) || + nla_put_u64_64bit(skb, RTA_EXPIRES, jiffies_to_clock_t(lastuse), + RTA_PAD)) + return -EMSGSIZE; + + rtm->rtm_type = RTN_MULTICAST; + return 1; +} +EXPORT_SYMBOL(mr_fill_mroute); + +int mr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb, + struct mr_table *(*iter)(struct net *net, + struct mr_table *mrt), + int (*fill)(struct mr_table *mrt, + struct sk_buff *skb, + u32 portid, u32 seq, struct mr_mfc *c, + int cmd, int flags), + spinlock_t *lock) +{ + unsigned int t = 0, e = 0, s_t = cb->args[0], s_e = cb->args[1]; + struct net *net = sock_net(skb->sk); + struct mr_table *mrt; + struct mr_mfc *mfc; + + rcu_read_lock(); + for (mrt = iter(net, NULL); mrt; mrt = iter(net, mrt)) { + if (t < s_t) + goto next_table; + list_for_each_entry_rcu(mfc, &mrt->mfc_cache_list, list) { + if (e < s_e) + goto next_entry; + if (fill(mrt, skb, NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, mfc, + RTM_NEWROUTE, NLM_F_MULTI) < 0) + goto done; +next_entry: + e++; + } + e = 0; + s_e = 0; + + spin_lock_bh(lock); + list_for_each_entry(mfc, &mrt->mfc_unres_queue, list) { + if (e < s_e) + goto next_entry2; + if (fill(mrt, skb, NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, mfc, + RTM_NEWROUTE, NLM_F_MULTI) < 0) { + spin_unlock_bh(lock); + goto done; + } +next_entry2: + e++; + } + spin_unlock_bh(lock); + e = 0; + s_e = 0; +next_table: + t++; + } +done: + rcu_read_unlock(); + + cb->args[1] = e; + cb->args[0] = t; + + return skb->len; +} +EXPORT_SYMBOL(mr_rtm_dumproute); diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index e3e420f3ba7b..c36ffce3c812 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -1635,6 +1635,7 @@ static void __net_exit arp_tables_net_exit(struct net *net) static struct pernet_operations arp_tables_net_ops = { .init = arp_tables_net_init, .exit = arp_tables_net_exit, + .async = true, }; static int __init arp_tables_init(void) diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index e38395a8dcf2..d4f7584d2dbe 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -1916,6 +1916,7 @@ static void __net_exit ip_tables_net_exit(struct net *net) static struct pernet_operations ip_tables_net_ops = { .init = ip_tables_net_init, .exit = ip_tables_net_exit, + .async = true, }; static int __init ip_tables_init(void) diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c index 8a8ae61cea71..0fc88fa7a4dc 100644 --- a/net/ipv4/netfilter/ipt_CLUSTERIP.c +++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c @@ -845,6 +845,7 @@ static struct pernet_operations clusterip_net_ops = { .exit = clusterip_net_exit, .id = &clusterip_net_id, .size = sizeof(struct clusterip_net), + .async = true, }; static int __init clusterip_tg_init(void) diff --git a/net/ipv4/netfilter/iptable_filter.c b/net/ipv4/netfilter/iptable_filter.c index 9ac92ea7b93c..c1c136a93911 100644 --- a/net/ipv4/netfilter/iptable_filter.c +++ b/net/ipv4/netfilter/iptable_filter.c @@ -87,6 +87,7 @@ static void __net_exit iptable_filter_net_exit(struct net *net) static struct pernet_operations iptable_filter_net_ops = { .init = iptable_filter_net_init, .exit = iptable_filter_net_exit, + .async = true, }; static int __init iptable_filter_init(void) diff --git a/net/ipv4/netfilter/nf_defrag_ipv4.c b/net/ipv4/netfilter/nf_defrag_ipv4.c index a0d3ad60a411..57244b62a4fc 100644 --- a/net/ipv4/netfilter/nf_defrag_ipv4.c +++ b/net/ipv4/netfilter/nf_defrag_ipv4.c @@ -118,6 +118,7 @@ static void __net_exit defrag4_net_exit(struct net *net) static struct pernet_operations defrag4_net_ops = { .exit = defrag4_net_exit, + .async = true, }; static int __init nf_defrag_init(void) diff --git a/net/ipv4/netfilter/nf_log_arp.c b/net/ipv4/netfilter/nf_log_arp.c index df5c2a2061a4..162293469ac2 100644 --- a/net/ipv4/netfilter/nf_log_arp.c +++ b/net/ipv4/netfilter/nf_log_arp.c @@ -122,6 +122,7 @@ static void __net_exit nf_log_arp_net_exit(struct net *net) static struct pernet_operations nf_log_arp_net_ops = { .init = nf_log_arp_net_init, .exit = nf_log_arp_net_exit, + .async = true, }; static int __init nf_log_arp_init(void) diff --git a/net/ipv4/netfilter/nf_log_ipv4.c b/net/ipv4/netfilter/nf_log_ipv4.c index 4388de0e5380..7a06de140f3c 100644 --- a/net/ipv4/netfilter/nf_log_ipv4.c +++ b/net/ipv4/netfilter/nf_log_ipv4.c @@ -358,6 +358,7 @@ static void __net_exit nf_log_ipv4_net_exit(struct net *net) static struct pernet_operations nf_log_ipv4_net_ops = { .init = nf_log_ipv4_net_init, .exit = nf_log_ipv4_net_exit, + .async = true, }; static int __init nf_log_ipv4_init(void) diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index b8f0db54b197..0164def9c808 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -1204,6 +1204,7 @@ static void __net_exit ping_v4_proc_exit_net(struct net *net) static struct pernet_operations ping_v4_net_ops = { .init = ping_v4_proc_init_net, .exit = ping_v4_proc_exit_net, + .async = true, }; int __init ping_proc_init(void) diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index dc5edc8f7564..d97e83b2dd33 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -549,10 +549,10 @@ static __net_exit void ip_proc_exit_net(struct net *net) static __net_initdata struct pernet_operations ip_proc_ops = { .init = ip_proc_init_net, .exit = ip_proc_exit_net, + .async = true, }; int __init ip_misc_proc_init(void) { return register_pernet_subsys(&ip_proc_ops); } - diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 9b367fc48d7d..54648d20bf0f 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -1156,6 +1156,7 @@ static __net_exit void raw_exit_net(struct net *net) static __net_initdata struct pernet_operations raw_net_ops = { .init = raw_init_net, .exit = raw_exit_net, + .async = true, }; int __init raw_proc_init(void) diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 860b3fd2f54b..e74ee837b300 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -418,6 +418,7 @@ static void __net_exit ip_rt_do_proc_exit(struct net *net) static struct pernet_operations ip_rt_proc_ops __net_initdata = { .init = ip_rt_do_proc_init, .exit = ip_rt_do_proc_exit, + .async = true, }; static int __init ip_rt_proc_init(void) @@ -1518,7 +1519,6 @@ struct rtable *rt_dst_alloc(struct net_device *dev, rt->rt_pmtu = 0; rt->rt_gateway = 0; rt->rt_uses_gateway = 0; - rt->rt_table_id = 0; INIT_LIST_HEAD(&rt->rt_uncached); rt->dst.output = ip_output; @@ -1654,19 +1654,6 @@ static void ip_del_fnhe(struct fib_nh *nh, __be32 daddr) spin_unlock_bh(&fnhe_lock); } -static void set_lwt_redirect(struct rtable *rth) -{ - if (lwtunnel_output_redirect(rth->dst.lwtstate)) { - rth->dst.lwtstate->orig_output = rth->dst.output; - rth->dst.output = lwtunnel_output; - } - - if (lwtunnel_input_redirect(rth->dst.lwtstate)) { - rth->dst.lwtstate->orig_input = rth->dst.input; - rth->dst.input = lwtunnel_input; - } -} - /* called in rcu_read_lock() section */ static int __mkroute_input(struct sk_buff *skb, const struct fib_result *res, @@ -1749,15 +1736,13 @@ rt_cache: } rth->rt_is_input = 1; - if (res->table) - rth->rt_table_id = res->table->tb_id; RT_CACHE_STAT_INC(in_slow_tot); rth->dst.input = ip_forward; rt_set_nexthop(rth, daddr, res, fnhe, res->fi, res->type, itag, do_cache); - set_lwt_redirect(rth); + lwtunnel_set_redirect(&rth->dst); skb_dst_set(skb, &rth->dst); out: err = 0; @@ -1773,44 +1758,45 @@ static void ip_multipath_l3_keys(const struct sk_buff *skb, struct flow_keys *hash_keys) { const struct iphdr *outer_iph = ip_hdr(skb); + const struct iphdr *key_iph = outer_iph; const struct iphdr *inner_iph; const struct icmphdr *icmph; struct iphdr _inner_iph; struct icmphdr _icmph; - hash_keys->addrs.v4addrs.src = outer_iph->saddr; - hash_keys->addrs.v4addrs.dst = outer_iph->daddr; if (likely(outer_iph->protocol != IPPROTO_ICMP)) - return; + goto out; if (unlikely((outer_iph->frag_off & htons(IP_OFFSET)) != 0)) - return; + goto out; icmph = skb_header_pointer(skb, outer_iph->ihl * 4, sizeof(_icmph), &_icmph); if (!icmph) - return; + goto out; if (icmph->type != ICMP_DEST_UNREACH && icmph->type != ICMP_REDIRECT && icmph->type != ICMP_TIME_EXCEEDED && icmph->type != ICMP_PARAMETERPROB) - return; + goto out; inner_iph = skb_header_pointer(skb, outer_iph->ihl * 4 + sizeof(_icmph), sizeof(_inner_iph), &_inner_iph); if (!inner_iph) - return; - hash_keys->addrs.v4addrs.src = inner_iph->saddr; - hash_keys->addrs.v4addrs.dst = inner_iph->daddr; + goto out; + + key_iph = inner_iph; +out: + hash_keys->addrs.v4addrs.src = key_iph->saddr; + hash_keys->addrs.v4addrs.dst = key_iph->daddr; } /* if skb is set it will be used and fl4 can be NULL */ -int fib_multipath_hash(const struct fib_info *fi, const struct flowi4 *fl4, - const struct sk_buff *skb) +int fib_multipath_hash(const struct net *net, const struct flowi4 *fl4, + const struct sk_buff *skb, struct flow_keys *flkeys) { - struct net *net = fi->fib_net; struct flow_keys hash_keys; u32 mhash; @@ -1834,15 +1820,20 @@ int fib_multipath_hash(const struct fib_info *fi, const struct flowi4 *fl4, /* short-circuit if we already have L4 hash present */ if (skb->l4_hash) return skb_get_hash_raw(skb) >> 1; + memset(&hash_keys, 0, sizeof(hash_keys)); - skb_flow_dissect_flow_keys(skb, &keys, flag); + + if (!flkeys) { + skb_flow_dissect_flow_keys(skb, &keys, flag); + flkeys = &keys; + } hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; - hash_keys.addrs.v4addrs.src = keys.addrs.v4addrs.src; - hash_keys.addrs.v4addrs.dst = keys.addrs.v4addrs.dst; - hash_keys.ports.src = keys.ports.src; - hash_keys.ports.dst = keys.ports.dst; - hash_keys.basic.ip_proto = keys.basic.ip_proto; + hash_keys.addrs.v4addrs.src = flkeys->addrs.v4addrs.src; + hash_keys.addrs.v4addrs.dst = flkeys->addrs.v4addrs.dst; + hash_keys.ports.src = flkeys->ports.src; + hash_keys.ports.dst = flkeys->ports.dst; + hash_keys.basic.ip_proto = flkeys->basic.ip_proto; } else { memset(&hash_keys, 0, sizeof(hash_keys)); hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; @@ -1858,17 +1849,17 @@ int fib_multipath_hash(const struct fib_info *fi, const struct flowi4 *fl4, return mhash >> 1; } -EXPORT_SYMBOL_GPL(fib_multipath_hash); #endif /* CONFIG_IP_ROUTE_MULTIPATH */ static int ip_mkroute_input(struct sk_buff *skb, struct fib_result *res, struct in_device *in_dev, - __be32 daddr, __be32 saddr, u32 tos) + __be32 daddr, __be32 saddr, u32 tos, + struct flow_keys *hkeys) { #ifdef CONFIG_IP_ROUTE_MULTIPATH if (res->fi && res->fi->fib_nhs > 1) { - int h = fib_multipath_hash(res->fi, NULL, skb); + int h = fib_multipath_hash(res->fi->fib_net, NULL, skb, hkeys); fib_select_multipath(res, h); } @@ -1894,13 +1885,14 @@ 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 flow_keys *flkeys = NULL, _flkeys; + struct net *net = dev_net(dev); struct ip_tunnel_info *tun_info; - struct flowi4 fl4; + int err = -EINVAL; unsigned int flags = 0; u32 itag = 0; struct rtable *rth; - int err = -EINVAL; - struct net *net = dev_net(dev); + struct flowi4 fl4; bool do_cache; /* IP on this device is disabled. */ @@ -1959,6 +1951,10 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, fl4.daddr = daddr; fl4.saddr = saddr; fl4.flowi4_uid = sock_net_uid(net, NULL); + + if (fib4_rules_early_flow_dissect(net, skb, &fl4, &_flkeys)) + flkeys = &_flkeys; + err = fib_lookup(net, &fl4, res, 0); if (err != 0) { if (!IN_DEV_FORWARD(in_dev)) @@ -1984,7 +1980,7 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, if (res->type != RTN_UNICAST) goto martian_destination; - err = ip_mkroute_input(skb, res, in_dev, daddr, saddr, tos); + err = ip_mkroute_input(skb, res, in_dev, daddr, saddr, tos, flkeys); out: return err; brd_input: @@ -2026,8 +2022,6 @@ local_input: rth->dst.tclassid = itag; #endif rth->rt_is_input = 1; - if (res->table) - rth->rt_table_id = res->table->tb_id; RT_CACHE_STAT_INC(in_slow_tot); if (res->type == RTN_UNREACHABLE) { @@ -2256,8 +2250,6 @@ add: return ERR_PTR(-ENOBUFS); rth->rt_iif = orig_oif; - if (res->table) - rth->rt_table_id = res->table->tb_id; RT_CACHE_STAT_INC(out_slow_tot); @@ -2279,7 +2271,7 @@ add: } rt_set_nexthop(rth, fl4->daddr, res, fnhe, fi, type, 0, do_cache); - set_lwt_redirect(rth); + lwtunnel_set_redirect(&rth->dst); return rth; } @@ -2787,7 +2779,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, rt->rt_flags |= RTCF_NOTIFY; if (rtm->rtm_flags & RTM_F_LOOKUP_TABLE) - table_id = rt->rt_table_id; + table_id = res.table ? res.table->tb_id : 0; if (rtm->rtm_flags & RTM_F_FIB_MATCH) { if (!res.fi) { @@ -3008,6 +3000,7 @@ static __net_exit void sysctl_route_net_exit(struct net *net) static __net_initdata struct pernet_operations sysctl_route_ops = { .init = sysctl_route_net_init, .exit = sysctl_route_net_exit, + .async = true, }; #endif @@ -3021,6 +3014,7 @@ static __net_init int rt_genid_init(struct net *net) static __net_initdata struct pernet_operations rt_genid_ops = { .init = rt_genid_init, + .async = true, }; static int __net_init ipv4_inetpeer_init(struct net *net) @@ -3046,6 +3040,7 @@ static void __net_exit ipv4_inetpeer_exit(struct net *net) static __net_initdata struct pernet_operations ipv4_inetpeer_ops = { .init = ipv4_inetpeer_init, .exit = ipv4_inetpeer_exit, + .async = true, }; #ifdef CONFIG_IP_ROUTE_CLASSID diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 93e172118a94..011de9a20ec6 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -400,7 +400,7 @@ static int proc_fib_multipath_hash_policy(struct ctl_table *table, int write, ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); if (write && ret == 0) - call_netevent_notifiers(NETEVENT_MULTIPATH_HASH_UPDATE, net); + call_netevent_notifiers(NETEVENT_IPV4_MPATH_HASH_UPDATE, net); return ret; } @@ -1219,6 +1219,7 @@ static __net_exit void ipv4_sysctl_exit_net(struct net *net) static __net_initdata struct pernet_operations ipv4_sysctl_ops = { .init = ipv4_sysctl_init_net, .exit = ipv4_sysctl_exit_net, + .async = true, }; static __init int sysctl_ipv4_init(void) diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 48636aee23c3..fb350f740f69 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -453,6 +453,7 @@ void tcp_init_sock(struct sock *sk) sk->sk_rcvbuf = sock_net(sk)->ipv4.sysctl_tcp_rmem[1]; sk_sockets_allocated_inc(sk); + sk->sk_route_forced_caps = NETIF_F_GSO; } EXPORT_SYMBOL(tcp_init_sock); @@ -897,7 +898,7 @@ static unsigned int tcp_xmit_size_goal(struct sock *sk, u32 mss_now, struct tcp_sock *tp = tcp_sk(sk); u32 new_size_goal, size_goal; - if (!large_allowed || !sk_can_gso(sk)) + if (!large_allowed) return mss_now; /* Note : tcp_tso_autosize() will eventually split this later */ @@ -1062,8 +1063,7 @@ EXPORT_SYMBOL_GPL(do_tcp_sendpages); int tcp_sendpage_locked(struct sock *sk, struct page *page, int offset, size_t size, int flags) { - if (!(sk->sk_route_caps & NETIF_F_SG) || - !sk_check_csum_caps(sk)) + if (!(sk->sk_route_caps & NETIF_F_SG)) return sock_no_sendpage_locked(sk, page, offset, size, flags); tcp_rate_check_app_limited(sk); /* is sending application-limited? */ @@ -1102,27 +1102,11 @@ static int linear_payload_sz(bool first_skb) return 0; } -static int select_size(const struct sock *sk, bool sg, bool first_skb, bool zc) +static int select_size(bool first_skb, bool zc) { - const struct tcp_sock *tp = tcp_sk(sk); - int tmp = tp->mss_cache; - - if (sg) { - if (zc) - return 0; - - if (sk_can_gso(sk)) { - tmp = linear_payload_sz(first_skb); - } else { - int pgbreak = SKB_MAX_HEAD(MAX_TCP_HEADER); - - if (tmp >= pgbreak && - tmp <= pgbreak + (MAX_SKB_FRAGS - 1) * PAGE_SIZE) - tmp = pgbreak; - } - } - - return tmp; + if (zc) + return 0; + return linear_payload_sz(first_skb); } void tcp_free_fastopen_req(struct tcp_sock *tp) @@ -1187,7 +1171,7 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size) int flags, err, copied = 0; int mss_now = 0, size_goal, copied_syn = 0; bool process_backlog = false; - bool sg, zc = false; + bool zc = false; long timeo; flags = msg->msg_flags; @@ -1205,7 +1189,7 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size) goto out_err; } - zc = sk_check_csum_caps(sk) && sk->sk_route_caps & NETIF_F_SG; + zc = sk->sk_route_caps & NETIF_F_SG; if (!zc) uarg->zerocopy = 0; } @@ -1268,18 +1252,12 @@ restart: if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN)) goto do_error; - sg = !!(sk->sk_route_caps & NETIF_F_SG); - while (msg_data_left(msg)) { int copy = 0; - int max = size_goal; skb = tcp_write_queue_tail(sk); - if (skb) { - if (skb->ip_summed == CHECKSUM_NONE) - max = mss_now; - copy = max - skb->len; - } + if (skb) + copy = size_goal - skb->len; if (copy <= 0 || !tcp_skb_can_collapse_to(skb)) { bool first_skb; @@ -1297,22 +1275,17 @@ new_segment: goto restart; } first_skb = tcp_rtx_and_write_queues_empty(sk); - linear = select_size(sk, sg, first_skb, zc); + linear = select_size(first_skb, zc); skb = sk_stream_alloc_skb(sk, linear, sk->sk_allocation, first_skb); if (!skb) goto wait_for_memory; process_backlog = true; - /* - * Check whether we can use HW checksum. - */ - if (sk_check_csum_caps(sk)) - skb->ip_summed = CHECKSUM_PARTIAL; + skb->ip_summed = CHECKSUM_PARTIAL; skb_entail(sk, skb); copy = size_goal; - max = size_goal; /* All packets are restored as if they have * already been sent. skb_mstamp isn't set to @@ -1343,7 +1316,7 @@ new_segment: if (!skb_can_coalesce(skb, i, pfrag->page, pfrag->offset)) { - if (i >= sysctl_max_skb_frags || !sg) { + if (i >= sysctl_max_skb_frags) { tcp_mark_push(tp, skb); goto new_segment; } @@ -1396,7 +1369,7 @@ new_segment: goto out; } - if (skb->len < max || (flags & MSG_OOB) || unlikely(tp->repair)) + if (skb->len < size_goal || (flags & MSG_OOB) || unlikely(tp->repair)) continue; if (forced_push(tp)) { @@ -3058,8 +3031,8 @@ struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk) u32 rate; stats = alloc_skb(7 * nla_total_size_64bit(sizeof(u64)) + - 3 * nla_total_size(sizeof(u32)) + - 2 * nla_total_size(sizeof(u8)), GFP_ATOMIC); + 4 * nla_total_size(sizeof(u32)) + + 3 * nla_total_size(sizeof(u8)), GFP_ATOMIC); if (!stats) return NULL; @@ -3088,6 +3061,9 @@ struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk) nla_put_u8(stats, TCP_NLA_RECUR_RETRANS, inet_csk(sk)->icsk_retransmits); nla_put_u8(stats, TCP_NLA_DELIVERY_RATE_APP_LMT, !!tp->rate_app_limited); + + nla_put_u32(stats, TCP_NLA_SNDQ_SIZE, tp->write_seq - tp->snd_una); + nla_put_u8(stats, TCP_NLA_CA_STATE, inet_csk(sk)->icsk_ca_state); return stats; } diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c index a471f696e13c..c92014cb1e16 100644 --- a/net/ipv4/tcp_bbr.c +++ b/net/ipv4/tcp_bbr.c @@ -97,10 +97,9 @@ struct bbr { packet_conservation:1, /* use packet conservation? */ restore_cwnd:1, /* decided to revert cwnd to old value */ round_start:1, /* start of packet-timed tx->ack round? */ - tso_segs_goal:7, /* segments we want in each skb we send */ idle_restart:1, /* restarting after idle? */ probe_rtt_round_done:1, /* a BBR_PROBE_RTT round at 4 pkts? */ - unused:5, + unused:12, lt_is_sampling:1, /* taking long-term ("LT") samples now? */ lt_rtt_cnt:7, /* round trips in long-term interval */ lt_use_bw:1; /* use lt_bw as our bw estimate? */ @@ -261,23 +260,25 @@ static void bbr_set_pacing_rate(struct sock *sk, u32 bw, int gain) sk->sk_pacing_rate = rate; } -/* Return count of segments we want in the skbs we send, or 0 for default. */ -static u32 bbr_tso_segs_goal(struct sock *sk) +/* override sysctl_tcp_min_tso_segs */ +static u32 bbr_min_tso_segs(struct sock *sk) { - struct bbr *bbr = inet_csk_ca(sk); - - return bbr->tso_segs_goal; + return sk->sk_pacing_rate < (bbr_min_tso_rate >> 3) ? 1 : 2; } -static void bbr_set_tso_segs_goal(struct sock *sk) +static u32 bbr_tso_segs_goal(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); - struct bbr *bbr = inet_csk_ca(sk); - u32 min_segs; + u32 segs, bytes; + + /* Sort of tcp_tso_autosize() but ignoring + * driver provided sk_gso_max_size. + */ + bytes = min_t(u32, sk->sk_pacing_rate >> sk->sk_pacing_shift, + GSO_MAX_SIZE - 1 - MAX_TCP_HEADER); + segs = max_t(u32, bytes / tp->mss_cache, bbr_min_tso_segs(sk)); - min_segs = sk->sk_pacing_rate < (bbr_min_tso_rate >> 3) ? 1 : 2; - bbr->tso_segs_goal = min(tcp_tso_autosize(sk, tp->mss_cache, min_segs), - 0x7FU); + return min(segs, 0x7FU); } /* Save "last known good" cwnd so we can restore it after losses or PROBE_RTT */ @@ -348,7 +349,7 @@ static u32 bbr_target_cwnd(struct sock *sk, u32 bw, int gain) cwnd = (((w * gain) >> BBR_SCALE) + BW_UNIT - 1) / BW_UNIT; /* Allow enough full-sized skbs in flight to utilize end systems. */ - cwnd += 3 * bbr->tso_segs_goal; + cwnd += 3 * bbr_tso_segs_goal(sk); /* Reduce delayed ACKs by rounding up cwnd to the next even number. */ cwnd = (cwnd + 1) & ~1U; @@ -824,7 +825,6 @@ static void bbr_main(struct sock *sk, const struct rate_sample *rs) bw = bbr_bw(sk); bbr_set_pacing_rate(sk, bw, bbr->pacing_gain); - bbr_set_tso_segs_goal(sk); bbr_set_cwnd(sk, rs, rs->acked_sacked, bw, bbr->cwnd_gain); } @@ -834,7 +834,6 @@ static void bbr_init(struct sock *sk) struct bbr *bbr = inet_csk_ca(sk); bbr->prior_cwnd = 0; - bbr->tso_segs_goal = 0; /* default segs per skb until first ACK */ bbr->rtt_cnt = 0; bbr->next_rtt_delivered = 0; bbr->prev_ca_state = TCP_CA_Open; @@ -936,7 +935,7 @@ static struct tcp_congestion_ops tcp_bbr_cong_ops __read_mostly = { .undo_cwnd = bbr_undo_cwnd, .cwnd_event = bbr_cwnd_event, .ssthresh = bbr_ssthresh, - .tso_segs_goal = bbr_tso_segs_goal, + .min_tso_segs = bbr_min_tso_segs, .get_info = bbr_get_info, .set_state = bbr_set_state, }; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 9a1b3c1c1c14..451ef3012636 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -1358,9 +1358,6 @@ static struct sk_buff *tcp_shift_skb_data(struct sock *sk, struct sk_buff *skb, int len; int in_sack; - if (!sk_can_gso(sk)) - goto fallback; - /* Normally R but no L won't result in plain S */ if (!dup_sack && (TCP_SKB_CB(skb)->sacked & (TCPCB_LOST|TCPCB_SACKED_RETRANS)) == TCPCB_SACKED_RETRANS) @@ -5862,10 +5859,12 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) tp->rx_opt.saw_tstamp = 0; req = tp->fastopen_rsk; if (req) { + bool req_stolen; + WARN_ON_ONCE(sk->sk_state != TCP_SYN_RECV && sk->sk_state != TCP_FIN_WAIT1); - if (!tcp_check_req(sk, skb, req, true)) + if (!tcp_check_req(sk, skb, req, true, &req_stolen)) goto discard; } diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index f8ad397e285e..2c6aec2643e8 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -561,16 +561,9 @@ void __tcp_v4_send_check(struct sk_buff *skb, __be32 saddr, __be32 daddr) { struct tcphdr *th = tcp_hdr(skb); - if (skb->ip_summed == CHECKSUM_PARTIAL) { - th->check = ~tcp_v4_check(skb->len, saddr, daddr, 0); - skb->csum_start = skb_transport_header(skb) - skb->head; - skb->csum_offset = offsetof(struct tcphdr, check); - } else { - th->check = tcp_v4_check(skb->len, saddr, daddr, - csum_partial(th, - th->doff << 2, - skb->csum)); - } + th->check = ~tcp_v4_check(skb->len, saddr, daddr, 0); + skb->csum_start = skb_transport_header(skb) - skb->head; + skb->csum_offset = offsetof(struct tcphdr, check); } /* This routine computes an IPv4 TCP checksum. */ @@ -1672,6 +1665,7 @@ process: if (sk->sk_state == TCP_NEW_SYN_RECV) { struct request_sock *req = inet_reqsk(sk); + bool req_stolen = false; struct sock *nsk; sk = req->rsk_listener; @@ -1694,10 +1688,20 @@ process: th = (const struct tcphdr *)skb->data; iph = ip_hdr(skb); tcp_v4_fill_cb(skb, iph, th); - nsk = tcp_check_req(sk, skb, req, false); + nsk = tcp_check_req(sk, skb, req, false, &req_stolen); } if (!nsk) { reqsk_put(req); + if (req_stolen) { + /* Another cpu got exclusive access to req + * and created a full blown socket. + * Try to feed this packet to this socket + * instead of discarding it. + */ + tcp_v4_restore_cb(skb); + sock_put(sk); + goto lookup; + } goto discard_and_relse; } if (nsk == sk) { @@ -2387,6 +2391,7 @@ static void __net_exit tcp4_proc_exit_net(struct net *net) static struct pernet_operations tcp4_net_ops = { .init = tcp4_proc_init_net, .exit = tcp4_proc_exit_net, + .async = true, }; int __init tcp4_proc_init(void) @@ -2573,6 +2578,7 @@ static struct pernet_operations __net_initdata tcp_sk_ops = { .init = tcp_sk_init, .exit = tcp_sk_exit, .exit_batch = tcp_sk_exit_batch, + .async = true, }; void __init tcp_v4_init(void) diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c index 03b51cdcc731..aa6fea9f3328 100644 --- a/net/ipv4/tcp_metrics.c +++ b/net/ipv4/tcp_metrics.c @@ -1024,6 +1024,7 @@ static void __net_exit tcp_net_metrics_exit_batch(struct list_head *net_exit_lis static __net_initdata struct pernet_operations tcp_net_metrics_ops = { .init = tcp_net_metrics_init, .exit_batch = tcp_net_metrics_exit_batch, + .async = true, }; void __init tcp_metrics_init(void) diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index a8384b0c11f8..e7e36433cdb5 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -578,7 +578,7 @@ EXPORT_SYMBOL(tcp_create_openreq_child); struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, struct request_sock *req, - bool fastopen) + bool fastopen, bool *req_stolen) { struct tcp_options_received tmp_opt; struct sock *child; @@ -785,6 +785,7 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, sock_rps_save_rxhash(child, skb); tcp_synack_rtt_meas(child, req); + *req_stolen = !own_req; return inet_csk_complete_hashdance(sk, child, req, own_req); listen_overflow: diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 6818042cd8a9..383cac0ff0ec 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -1206,7 +1206,7 @@ static void tcp_queue_skb(struct sock *sk, struct sk_buff *skb) /* Initialize TSO segments for a packet. */ static void tcp_set_skb_tso_segs(struct sk_buff *skb, unsigned int mss_now) { - if (skb->len <= mss_now || skb->ip_summed == CHECKSUM_NONE) { + if (skb->len <= mss_now) { /* Avoid the costly divide in the normal * non-TSO case. */ @@ -1335,21 +1335,9 @@ int tcp_fragment(struct sock *sk, enum tcp_queue tcp_queue, TCP_SKB_CB(buff)->sacked = TCP_SKB_CB(skb)->sacked; tcp_skb_fragment_eor(skb, buff); - if (!skb_shinfo(skb)->nr_frags && skb->ip_summed != CHECKSUM_PARTIAL) { - /* Copy and checksum data tail into the new buffer. */ - buff->csum = csum_partial_copy_nocheck(skb->data + len, - skb_put(buff, nsize), - nsize, 0); - - skb_trim(skb, len); - - skb->csum = csum_block_sub(skb->csum, buff->csum, len); - } else { - skb->ip_summed = CHECKSUM_PARTIAL; - skb_split(skb, buff, len); - } + skb_split(skb, buff, len); - buff->ip_summed = skb->ip_summed; + buff->ip_summed = CHECKSUM_PARTIAL; buff->tstamp = skb->tstamp; tcp_fragment_tstamp(skb, buff); @@ -1715,8 +1703,8 @@ static bool tcp_nagle_check(bool partial, const struct tcp_sock *tp, /* Return how many segs we'd like on a TSO packet, * to send one TSO packet per ms */ -u32 tcp_tso_autosize(const struct sock *sk, unsigned int mss_now, - int min_tso_segs) +static u32 tcp_tso_autosize(const struct sock *sk, unsigned int mss_now, + int min_tso_segs) { u32 bytes, segs; @@ -1732,7 +1720,6 @@ u32 tcp_tso_autosize(const struct sock *sk, unsigned int mss_now, return segs; } -EXPORT_SYMBOL(tcp_tso_autosize); /* Return the number of segments we want in the skb we are transmitting. * See if congestion control module wants to decide; otherwise, autosize. @@ -1740,11 +1727,13 @@ EXPORT_SYMBOL(tcp_tso_autosize); static u32 tcp_tso_segs(struct sock *sk, unsigned int mss_now) { const struct tcp_congestion_ops *ca_ops = inet_csk(sk)->icsk_ca_ops; - u32 tso_segs = ca_ops->tso_segs_goal ? ca_ops->tso_segs_goal(sk) : 0; + u32 min_tso, tso_segs; - if (!tso_segs) - tso_segs = tcp_tso_autosize(sk, mss_now, - sock_net(sk)->ipv4.sysctl_tcp_min_tso_segs); + min_tso = ca_ops->min_tso_segs ? + ca_ops->min_tso_segs(sk) : + sock_net(sk)->ipv4.sysctl_tcp_min_tso_segs; + + tso_segs = tcp_tso_autosize(sk, mss_now, min_tso); return min_t(u32, tso_segs, sk->sk_gso_max_segs); } @@ -1902,7 +1891,7 @@ static int tso_fragment(struct sock *sk, enum tcp_queue tcp_queue, tcp_skb_fragment_eor(skb, buff); - buff->ip_summed = skb->ip_summed = CHECKSUM_PARTIAL; + buff->ip_summed = CHECKSUM_PARTIAL; skb_split(skb, buff, len); tcp_fragment_tstamp(skb, buff); @@ -2135,7 +2124,7 @@ static int tcp_mtu_probe(struct sock *sk) TCP_SKB_CB(nskb)->tcp_flags = TCPHDR_ACK; TCP_SKB_CB(nskb)->sacked = 0; nskb->csum = 0; - nskb->ip_summed = skb->ip_summed; + nskb->ip_summed = CHECKSUM_PARTIAL; tcp_insert_write_queue_before(nskb, skb, sk); tcp_highest_sack_replace(sk, skb, nskb); @@ -2143,14 +2132,7 @@ static int tcp_mtu_probe(struct sock *sk) len = 0; tcp_for_write_queue_from_safe(skb, next, sk) { copy = min_t(int, skb->len, probe_size - len); - if (nskb->ip_summed) { - skb_copy_bits(skb, 0, skb_put(nskb, copy), copy); - } else { - __wsum csum = skb_copy_and_csum_bits(skb, 0, - skb_put(nskb, copy), - copy, 0); - nskb->csum = csum_block_add(nskb->csum, csum, len); - } + skb_copy_bits(skb, 0, skb_put(nskb, copy), copy); if (skb->len <= copy) { /* We've eaten all the data from this skb. @@ -2167,9 +2149,6 @@ static int tcp_mtu_probe(struct sock *sk) ~(TCPHDR_FIN|TCPHDR_PSH); if (!skb_shinfo(skb)->nr_frags) { skb_pull(skb, copy); - if (skb->ip_summed != CHECKSUM_PARTIAL) - skb->csum = csum_partial(skb->data, - skb->len, 0); } else { __pskb_trim_head(skb, copy); tcp_set_skb_tso_segs(skb, mss_now); @@ -2747,12 +2726,6 @@ static bool tcp_collapse_retrans(struct sock *sk, struct sk_buff *skb) } tcp_highest_sack_replace(sk, next_skb, skb); - if (next_skb->ip_summed == CHECKSUM_PARTIAL) - skb->ip_summed = CHECKSUM_PARTIAL; - - if (skb->ip_summed != CHECKSUM_PARTIAL) - skb->csum = csum_block_add(skb->csum, next_skb->csum, skb_size); - /* Update sequence range on original skb. */ TCP_SKB_CB(skb)->end_seq = TCP_SKB_CB(next_skb)->end_seq; diff --git a/net/ipv4/tunnel4.c b/net/ipv4/tunnel4.c index ec35eaa5c029..c0630013c1ae 100644 --- a/net/ipv4/tunnel4.c +++ b/net/ipv4/tunnel4.c @@ -90,7 +90,7 @@ EXPORT_SYMBOL(xfrm4_tunnel_deregister); for (handler = rcu_dereference(head); \ handler != NULL; \ handler = rcu_dereference(handler->next)) \ - + static int tunnel4_rcv(struct sk_buff *skb) { struct xfrm_tunnel *handler; diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index e5ef7c38c934..3013404d0935 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -2762,6 +2762,7 @@ static void __net_exit udp4_proc_exit_net(struct net *net) static struct pernet_operations udp4_net_ops = { .init = udp4_proc_init_net, .exit = udp4_proc_exit_net, + .async = true, }; int __init udp4_proc_init(void) diff --git a/net/ipv4/udplite.c b/net/ipv4/udplite.c index f96614e9b9a5..72f2c3806408 100644 --- a/net/ipv4/udplite.c +++ b/net/ipv4/udplite.c @@ -104,6 +104,7 @@ static void __net_exit udplite4_proc_exit_net(struct net *net) static struct pernet_operations udplite4_net_ops = { .init = udplite4_proc_init_net, .exit = udplite4_proc_exit_net, + .async = true, }; static __init int udplite4_proc_init(void) diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index 05017e2c849c..0c752dc3f93b 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -100,7 +100,6 @@ static int xfrm4_fill_dst(struct xfrm_dst *xdst, struct net_device *dev, xdst->u.rt.rt_gateway = rt->rt_gateway; xdst->u.rt.rt_uses_gateway = rt->rt_uses_gateway; xdst->u.rt.rt_pmtu = rt->rt_pmtu; - xdst->u.rt.rt_table_id = rt->rt_table_id; INIT_LIST_HEAD(&xdst->u.rt.rt_uncached); return 0; @@ -365,6 +364,7 @@ static void __net_exit xfrm4_net_exit(struct net *net) static struct pernet_operations __net_initdata xfrm4_net_ops = { .init = xfrm4_net_init, .exit = xfrm4_net_exit, + .async = true, }; static void __init xfrm4_policy_init(void) @@ -379,4 +379,3 @@ void __init xfrm4_init(void) xfrm4_protocol_init(); register_pernet_subsys(&xfrm4_net_ops); } - diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig index ea71e4b0ab7a..6794ddf0547c 100644 --- a/net/ipv6/Kconfig +++ b/net/ipv6/Kconfig @@ -278,6 +278,7 @@ config IPV6_SUBTREES config IPV6_MROUTE bool "IPv6: multicast routing" depends on IPV6 + select IP_MROUTE_COMMON ---help--- Experimental support for IPv6 multicast forwarding. If unsure, say N. diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index e1846b97ee69..b5fd116c046a 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -1459,6 +1459,21 @@ static bool ipv6_use_optimistic_addr(struct net *net, #endif } +static bool ipv6_allow_optimistic_dad(struct net *net, + struct inet6_dev *idev) +{ +#ifdef CONFIG_IPV6_OPTIMISTIC_DAD + if (!idev) + return false; + if (!net->ipv6.devconf_all->optimistic_dad && !idev->cnf.optimistic_dad) + return false; + + return true; +#else + return false; +#endif +} + static int ipv6_get_saddr_eval(struct net *net, struct ipv6_saddr_score *score, struct ipv6_saddr_dst *dst, @@ -1968,6 +1983,8 @@ static void addrconf_dad_stop(struct inet6_ifaddr *ifp, int dad_failed) spin_lock_bh(&ifp->lock); addrconf_del_dad_work(ifp); ifp->flags |= IFA_F_TENTATIVE; + if (dad_failed) + ifp->flags &= ~IFA_F_OPTIMISTIC; spin_unlock_bh(&ifp->lock); if (dad_failed) ipv6_ifa_notify(0, ifp); @@ -4257,6 +4274,7 @@ static void __net_exit if6_proc_net_exit(struct net *net) static struct pernet_operations if6_proc_net_ops = { .init = if6_proc_net_init, .exit = if6_proc_net_exit, + .async = true, }; int __init if6_proc_init(void) @@ -4500,6 +4518,9 @@ static int inet6_addr_modify(struct inet6_ifaddr *ifp, u32 ifa_flags, (ifp->flags & IFA_F_TEMPORARY || ifp->prefix_len != 64)) return -EINVAL; + if (!(ifp->flags & IFA_F_TENTATIVE) || ifp->flags & IFA_F_DADFAILED) + ifa_flags &= ~IFA_F_OPTIMISTIC; + timeout = addrconf_timeout_fixup(valid_lft, HZ); if (addrconf_finite_timeout(timeout)) { expires = jiffies_to_clock_t(timeout * HZ); @@ -4573,6 +4594,7 @@ inet6_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh, struct in6_addr *pfx, *peer_pfx; struct inet6_ifaddr *ifa; struct net_device *dev; + struct inet6_dev *idev; u32 valid_lft = INFINITY_LIFE_TIME, preferred_lft = INFINITY_LIFE_TIME; u32 ifa_flags; int err; @@ -4606,7 +4628,19 @@ inet6_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh, /* We ignore other flags so far. */ ifa_flags &= IFA_F_NODAD | IFA_F_HOMEADDRESS | IFA_F_MANAGETEMPADDR | - IFA_F_NOPREFIXROUTE | IFA_F_MCAUTOJOIN; + IFA_F_NOPREFIXROUTE | IFA_F_MCAUTOJOIN | IFA_F_OPTIMISTIC; + + idev = ipv6_find_idev(dev); + if (IS_ERR(idev)) + return PTR_ERR(idev); + + if (!ipv6_allow_optimistic_dad(net, idev)) + ifa_flags &= ~IFA_F_OPTIMISTIC; + + if (ifa_flags & IFA_F_NODAD && ifa_flags & IFA_F_OPTIMISTIC) { + NL_SET_ERR_MSG(extack, "IFA_F_NODAD and IFA_F_OPTIMISTIC are mutually exclusive"); + return -EINVAL; + } ifa = ipv6_get_ifaddr(net, pfx, dev, 1); if (!ifa) { @@ -6550,6 +6584,7 @@ static void __net_exit addrconf_exit_net(struct net *net) static struct pernet_operations addrconf_ops = { .init = addrconf_init_net, .exit = addrconf_exit_net, + .async = true, }; static struct rtnl_af_ops inet6_ops __read_mostly = { diff --git a/net/ipv6/addrlabel.c b/net/ipv6/addrlabel.c index 1d6ced37ad71..ba2e63633370 100644 --- a/net/ipv6/addrlabel.c +++ b/net/ipv6/addrlabel.c @@ -344,6 +344,7 @@ static void __net_exit ip6addrlbl_net_exit(struct net *net) static struct pernet_operations ipv6_addr_label_ops = { .init = ip6addrlbl_net_init, .exit = ip6addrlbl_net_exit, + .async = true, }; int __init ipv6_addr_label_init(void) diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 416917719a6f..dbbe04018813 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -470,7 +470,7 @@ EXPORT_SYMBOL_GPL(inet6_destroy_sock); */ int inet6_getname(struct socket *sock, struct sockaddr *uaddr, - int *uaddr_len, int peer) + int peer) { struct sockaddr_in6 *sin = (struct sockaddr_in6 *)uaddr; struct sock *sk = sock->sk; @@ -500,8 +500,7 @@ int inet6_getname(struct socket *sock, struct sockaddr *uaddr, } sin->sin6_scope_id = ipv6_iface_scope_id(&sin->sin6_addr, sk->sk_bound_dev_if); - *uaddr_len = sizeof(*sin); - return 0; + return sizeof(*sin); } EXPORT_SYMBOL(inet6_getname); @@ -858,6 +857,7 @@ static void __net_exit inet6_net_exit(struct net *net) static struct pernet_operations inet6_net_ops = { .init = inet6_net_init, .exit = inet6_net_exit, + .async = true, }; static const struct ipv6_stub ipv6_stub_impl = { diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c index 8e085cc05aeb..c61718dba2e6 100644 --- a/net/ipv6/anycast.c +++ b/net/ipv6/anycast.c @@ -78,7 +78,7 @@ int ipv6_sock_ac_join(struct sock *sk, int ifindex, const struct in6_addr *addr) if (ifindex == 0) { struct rt6_info *rt; - rt = rt6_lookup(net, addr, NULL, 0, 0); + rt = rt6_lookup(net, addr, NULL, 0, NULL, 0); if (rt) { dev = rt->dst.dev; ip6_rt_put(rt); @@ -552,4 +552,3 @@ void ac6_proc_exit(struct net *net) remove_proc_entry("anycast6", net->proc_net); } #endif - diff --git a/net/ipv6/exthdrs_core.c b/net/ipv6/exthdrs_core.c index 11025f8d124b..b643f5ce6c80 100644 --- a/net/ipv6/exthdrs_core.c +++ b/net/ipv6/exthdrs_core.c @@ -279,4 +279,3 @@ int ipv6_find_hdr(const struct sk_buff *skb, unsigned int *offset, return nexthdr; } EXPORT_SYMBOL(ipv6_find_hdr); - diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c index b240f24a6e52..00ef9467f3c0 100644 --- a/net/ipv6/fib6_rules.c +++ b/net/ipv6/fib6_rules.c @@ -61,11 +61,13 @@ unsigned int fib6_rules_seq_read(struct net *net) } struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi6 *fl6, + const struct sk_buff *skb, int flags, pol_lookup_t lookup) { if (net->ipv6.fib6_has_custom_rules) { struct fib_lookup_arg arg = { .lookup_ptr = lookup, + .lookup_data = skb, .flags = FIB_LOOKUP_NOREF, }; @@ -80,11 +82,11 @@ struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi6 *fl6, } else { struct rt6_info *rt; - rt = lookup(net, net->ipv6.fib6_local_tbl, fl6, flags); + rt = lookup(net, net->ipv6.fib6_local_tbl, fl6, skb, flags); if (rt != net->ipv6.ip6_null_entry && rt->dst.error != -EAGAIN) return &rt->dst; ip6_rt_put(rt); - rt = lookup(net, net->ipv6.fib6_main_tbl, fl6, flags); + rt = lookup(net, net->ipv6.fib6_main_tbl, fl6, skb, flags); if (rt->dst.error != -EAGAIN) return &rt->dst; ip6_rt_put(rt); @@ -130,7 +132,7 @@ static int fib6_rule_action(struct fib_rule *rule, struct flowi *flp, goto out; } - rt = lookup(net, table, flp6, flags); + rt = lookup(net, table, flp6, arg->lookup_data, flags); if (rt != net->ipv6.ip6_null_entry) { struct fib6_rule *r = (struct fib6_rule *)rule; @@ -223,6 +225,17 @@ static int fib6_rule_match(struct fib_rule *rule, struct flowi *fl, int flags) if (r->tclass && r->tclass != ip6_tclass(fl6->flowlabel)) return 0; + if (rule->ip_proto && (rule->ip_proto != fl6->flowi6_proto)) + return 0; + + if (fib_rule_port_range_set(&rule->sport_range) && + !fib_rule_port_inrange(&rule->sport_range, fl6->fl6_sport)) + return 0; + + if (fib_rule_port_range_set(&rule->dport_range) && + !fib_rule_port_inrange(&rule->dport_range, fl6->fl6_dport)) + return 0; + return 1; } @@ -258,12 +271,26 @@ static int fib6_rule_configure(struct fib_rule *rule, struct sk_buff *skb, rule6->dst.plen = frh->dst_len; rule6->tclass = frh->tos; + if (fib_rule_requires_fldissect(rule)) + net->ipv6.fib6_rules_require_fldissect++; + net->ipv6.fib6_has_custom_rules = true; err = 0; errout: return err; } +static int fib6_rule_delete(struct fib_rule *rule) +{ + struct net *net = rule->fr_net; + + if (net->ipv6.fib6_rules_require_fldissect && + fib_rule_requires_fldissect(rule)) + net->ipv6.fib6_rules_require_fldissect--; + + return 0; +} + static int fib6_rule_compare(struct fib_rule *rule, struct fib_rule_hdr *frh, struct nlattr **tb) { @@ -323,6 +350,7 @@ static const struct fib_rules_ops __net_initconst fib6_rules_ops_template = { .match = fib6_rule_match, .suppress = fib6_rule_suppress, .configure = fib6_rule_configure, + .delete = fib6_rule_delete, .compare = fib6_rule_compare, .fill = fib6_rule_fill, .nlmsg_payload = fib6_rule_nlmsg_payload, @@ -350,6 +378,7 @@ static int __net_init fib6_rules_net_init(struct net *net) goto out_fib6_rules_ops; net->ipv6.fib6_rules_ops = ops; + net->ipv6.fib6_rules_require_fldissect = 0; out: return err; @@ -368,6 +397,7 @@ static void __net_exit fib6_rules_net_exit(struct net *net) static struct pernet_operations fib6_rules_net_ops = { .init = fib6_rules_net_init, .exit = fib6_rules_net_exit, + .async = true, }; int __init fib6_rules_init(void) diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index 6ae5dd3f4d0d..6f84668be6ea 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -522,7 +522,7 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, fl6.fl6_icmp_type = type; fl6.fl6_icmp_code = code; fl6.flowi6_uid = sock_net_uid(net, NULL); - fl6.mp_hash = rt6_multipath_hash(&fl6, skb); + fl6.mp_hash = rt6_multipath_hash(net, &fl6, skb, NULL); security_skb_classify_flow(skb, flowi6_to_flowi(&fl6)); sk = icmpv6_xmit_lock(net); @@ -629,7 +629,8 @@ int ip6_err_gen_icmpv6_unreach(struct sk_buff *skb, int nhs, int type, skb_pull(skb2, nhs); skb_reset_network_header(skb2); - rt = rt6_lookup(dev_net(skb->dev), &ipv6_hdr(skb2)->saddr, NULL, 0, 0); + rt = rt6_lookup(dev_net(skb->dev), &ipv6_hdr(skb2)->saddr, NULL, 0, + skb, 0); if (rt && rt->dst.dev) skb2->dev = rt->dst.dev; @@ -997,6 +998,7 @@ static void __net_exit icmpv6_sk_exit(struct net *net) static struct pernet_operations icmpv6_sk_ops = { .init = icmpv6_sk_init, .exit = icmpv6_sk_exit, + .async = true, }; int __init icmpv6_init(void) diff --git a/net/ipv6/ila/ila_xlat.c b/net/ipv6/ila/ila_xlat.c index 44c39c5f0638..e438699f000f 100644 --- a/net/ipv6/ila/ila_xlat.c +++ b/net/ipv6/ila/ila_xlat.c @@ -613,6 +613,7 @@ static struct pernet_operations ila_net_ops = { .exit = ila_exit_net, .id = &ila_net_id, .size = sizeof(struct ila_net), + .async = true, }; static int ila_xlat_addr(struct sk_buff *skb, bool sir2ila) diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 92b8d8c75eed..2f995e9e3050 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -299,11 +299,12 @@ struct fib6_table *fib6_get_table(struct net *net, u32 id) } struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi6 *fl6, + const struct sk_buff *skb, int flags, pol_lookup_t lookup) { struct rt6_info *rt; - rt = lookup(net, net->ipv6.fib6_main_tbl, fl6, flags); + rt = lookup(net, net->ipv6.fib6_main_tbl, fl6, skb, flags); if (rt->dst.error == -EAGAIN) { ip6_rt_put(rt); rt = net->ipv6.ip6_null_entry; @@ -2160,6 +2161,7 @@ static void fib6_net_exit(struct net *net) static struct pernet_operations fib6_net_ops = { .init = fib6_net_init, .exit = fib6_net_exit, + .async = true, }; int __init fib6_init(void) diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c index 3dab664ff503..6ddf52282894 100644 --- a/net/ipv6/ip6_flowlabel.c +++ b/net/ipv6/ip6_flowlabel.c @@ -873,6 +873,7 @@ static void __net_exit ip6_flowlabel_net_exit(struct net *net) static struct pernet_operations ip6_flowlabel_net_ops = { .init = ip6_flowlabel_proc_init, .exit = ip6_flowlabel_net_exit, + .async = true, }; int ip6_flowlabel_init(void) diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 3c353125546d..18a3dfbd0300 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -695,9 +695,6 @@ static netdev_tx_t __gre6_xmit(struct sk_buff *skb, else fl6->daddr = tunnel->parms.raddr; - if (tunnel->parms.o_flags & TUNNEL_SEQ) - tunnel->o_seqno++; - /* Push GRE header. */ protocol = (dev->type == ARPHRD_ETHER) ? htons(ETH_P_TEB) : proto; @@ -720,14 +717,20 @@ static netdev_tx_t __gre6_xmit(struct sk_buff *skb, fl6->flowi6_uid = sock_net_uid(dev_net(dev), NULL); dsfield = key->tos; - flags = key->tun_flags & (TUNNEL_CSUM | TUNNEL_KEY); + flags = key->tun_flags & + (TUNNEL_CSUM | TUNNEL_KEY | TUNNEL_SEQ); tunnel->tun_hlen = gre_calc_hlen(flags); gre_build_header(skb, tunnel->tun_hlen, flags, protocol, - tunnel_id_to_key32(tun_info->key.tun_id), 0); + tunnel_id_to_key32(tun_info->key.tun_id), + (flags | TUNNEL_SEQ) ? htonl(tunnel->o_seqno++) + : 0); } else { + if (tunnel->parms.o_flags & TUNNEL_SEQ) + tunnel->o_seqno++; + gre_build_header(skb, tunnel->tun_hlen, tunnel->parms.o_flags, protocol, tunnel->parms.o_key, htonl(tunnel->o_seqno)); @@ -1053,7 +1056,7 @@ static void ip6gre_tnl_link_config(struct ip6_tnl *t, int set_mtu) struct rt6_info *rt = rt6_lookup(t->net, &p->raddr, &p->laddr, - p->link, strict); + p->link, NULL, strict); if (!rt) return; @@ -1517,6 +1520,7 @@ static struct pernet_operations ip6gre_net_ops = { .exit_batch = ip6gre_exit_batch_net, .id = &ip6gre_net_id, .size = sizeof(struct ip6gre_net), + .async = true, }; static int ip6gre_tunnel_validate(struct nlattr *tb[], struct nlattr *data[], @@ -1784,6 +1788,12 @@ static void ip6gre_tap_setup(struct net_device *dev) netif_keep_dst(dev); } +bool is_ip6gretap_dev(const struct net_device *dev) +{ + return dev->netdev_ops == &ip6gre_tap_netdev_ops; +} +EXPORT_SYMBOL_GPL(is_ip6gretap_dev); + static bool ip6gre_netlink_encap_parms(struct nlattr *data[], struct ip_tunnel_encap *ipencap) { diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index a8a919520090..2c7f09c3c39e 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -71,7 +71,7 @@ static int ip6_finish_output2(struct net *net, struct sock *sk, struct sk_buff * struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb)); if (!(dev->flags & IFF_LOOPBACK) && sk_mc_loop(sk) && - ((mroute6_socket(net, skb) && + ((mroute6_is_socket(net, skb) && !(IP6CB(skb)->flags & IP6SKB_FORWARDED)) || ipv6_chk_mcast_addr(dev, &ipv6_hdr(skb)->daddr, &ipv6_hdr(skb)->saddr))) { diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 6e0f21eed88a..56c4967f1868 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -679,7 +679,7 @@ ip6ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, /* Try to guess incoming interface */ rt = rt6_lookup(dev_net(skb->dev), &ipv6_hdr(skb2)->saddr, - NULL, 0, 0); + NULL, 0, skb2, 0); if (rt && rt->dst.dev) skb2->dev = rt->dst.dev; @@ -1444,7 +1444,7 @@ static void ip6_tnl_link_config(struct ip6_tnl *t) struct rt6_info *rt = rt6_lookup(t->net, &p->raddr, &p->laddr, - p->link, strict); + p->link, NULL, strict); if (!rt) return; @@ -2254,6 +2254,7 @@ static struct pernet_operations ip6_tnl_net_ops = { .exit_batch = ip6_tnl_exit_batch_net, .id = &ip6_tnl_net_id, .size = sizeof(struct ip6_tnl_net), + .async = true, }; /** diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c index fa3ae1cb50d3..a482b854eeea 100644 --- a/net/ipv6/ip6_vti.c +++ b/net/ipv6/ip6_vti.c @@ -645,7 +645,7 @@ static void vti6_link_config(struct ip6_tnl *t) (IPV6_ADDR_MULTICAST | IPV6_ADDR_LINKLOCAL)); struct rt6_info *rt = rt6_lookup(t->net, &p->raddr, &p->laddr, - p->link, strict); + p->link, NULL, strict); if (rt) tdev = rt->dst.dev; @@ -1148,6 +1148,7 @@ static struct pernet_operations vti6_net_ops = { .exit_batch = vti6_exit_batch_net, .id = &vti6_net_id, .size = sizeof(struct vti6_net), + .async = true, }; static struct xfrm6_protocol vti_esp6_protocol __read_mostly = { diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 9f6cace9c817..2a38f9de45d3 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -20,7 +20,6 @@ #include <linux/types.h> #include <linux/sched.h> #include <linux/errno.h> -#include <linux/timer.h> #include <linux/mm.h> #include <linux/kernel.h> #include <linux/fcntl.h> @@ -32,11 +31,9 @@ #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/init.h> -#include <linux/slab.h> #include <linux/compat.h> #include <net/protocol.h> #include <linux/skbuff.h> -#include <net/sock.h> #include <net/raw.h> #include <linux/notifier.h> #include <linux/if_arp.h> @@ -54,30 +51,12 @@ #include <net/ip6_checksum.h> #include <linux/netconf.h> -struct mr6_table { - struct list_head list; - possible_net_t net; - u32 id; - struct sock *mroute6_sk; - struct timer_list ipmr_expire_timer; - struct list_head mfc6_unres_queue; - struct list_head mfc6_cache_array[MFC6_LINES]; - struct mif_device vif6_table[MAXMIFS]; - int maxvif; - atomic_t cache_resolve_queue_len; - bool mroute_do_assert; - bool mroute_do_pim; -#ifdef CONFIG_IPV6_PIMSM_V2 - int mroute_reg_vif_num; -#endif -}; - struct ip6mr_rule { struct fib_rule common; }; struct ip6mr_result { - struct mr6_table *mrt; + struct mr_table *mrt; }; /* Big lock, protecting vif table, mrt cache and mroute socket state. @@ -86,11 +65,7 @@ struct ip6mr_result { static DEFINE_RWLOCK(mrt_lock); -/* - * Multicast router control variables - */ - -#define MIF_EXISTS(_mrt, _idx) ((_mrt)->vif6_table[_idx].dev != NULL) +/* Multicast router control variables */ /* Special spinlock for queue of unresolved entries */ static DEFINE_SPINLOCK(mfc_unres_lock); @@ -105,30 +80,45 @@ static DEFINE_SPINLOCK(mfc_unres_lock); static struct kmem_cache *mrt_cachep __read_mostly; -static struct mr6_table *ip6mr_new_table(struct net *net, u32 id); -static void ip6mr_free_table(struct mr6_table *mrt); +static struct mr_table *ip6mr_new_table(struct net *net, u32 id); +static void ip6mr_free_table(struct mr_table *mrt); -static void ip6_mr_forward(struct net *net, struct mr6_table *mrt, +static void ip6_mr_forward(struct net *net, struct mr_table *mrt, struct sk_buff *skb, struct mfc6_cache *cache); -static int ip6mr_cache_report(struct mr6_table *mrt, struct sk_buff *pkt, +static int ip6mr_cache_report(struct mr_table *mrt, struct sk_buff *pkt, mifi_t mifi, int assert); -static int __ip6mr_fill_mroute(struct mr6_table *mrt, struct sk_buff *skb, - struct mfc6_cache *c, struct rtmsg *rtm); -static void mr6_netlink_event(struct mr6_table *mrt, struct mfc6_cache *mfc, +static void mr6_netlink_event(struct mr_table *mrt, struct mfc6_cache *mfc, int cmd); -static void mrt6msg_netlink_event(struct mr6_table *mrt, struct sk_buff *pkt); +static void mrt6msg_netlink_event(struct mr_table *mrt, struct sk_buff *pkt); static int ip6mr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb); -static void mroute_clean_tables(struct mr6_table *mrt, bool all); +static void mroute_clean_tables(struct mr_table *mrt, bool all); static void ipmr_expire_process(struct timer_list *t); #ifdef CONFIG_IPV6_MROUTE_MULTIPLE_TABLES #define ip6mr_for_each_table(mrt, net) \ list_for_each_entry_rcu(mrt, &net->ipv6.mr6_tables, list) -static struct mr6_table *ip6mr_get_table(struct net *net, u32 id) +static struct mr_table *ip6mr_mr_table_iter(struct net *net, + struct mr_table *mrt) +{ + struct mr_table *ret; + + if (!mrt) + ret = list_entry_rcu(net->ipv6.mr6_tables.next, + struct mr_table, list); + else + ret = list_entry_rcu(mrt->list.next, + struct mr_table, list); + + if (&ret->list == &net->ipv6.mr6_tables) + return NULL; + return ret; +} + +static struct mr_table *ip6mr_get_table(struct net *net, u32 id) { - struct mr6_table *mrt; + struct mr_table *mrt; ip6mr_for_each_table(mrt, net) { if (mrt->id == id) @@ -138,7 +128,7 @@ static struct mr6_table *ip6mr_get_table(struct net *net, u32 id) } static int ip6mr_fib_lookup(struct net *net, struct flowi6 *flp6, - struct mr6_table **mrt) + struct mr_table **mrt) { int err; struct ip6mr_result res; @@ -159,7 +149,7 @@ static int ip6mr_rule_action(struct fib_rule *rule, struct flowi *flp, int flags, struct fib_lookup_arg *arg) { struct ip6mr_result *res = arg->result; - struct mr6_table *mrt; + struct mr_table *mrt; switch (rule->action) { case FR_ACT_TO_TBL: @@ -227,7 +217,7 @@ static const struct fib_rules_ops __net_initconst ip6mr_rules_ops_template = { static int __net_init ip6mr_rules_init(struct net *net) { struct fib_rules_ops *ops; - struct mr6_table *mrt; + struct mr_table *mrt; int err; ops = fib_rules_register(&ip6mr_rules_ops_template, net); @@ -258,7 +248,7 @@ err1: static void __net_exit ip6mr_rules_exit(struct net *net) { - struct mr6_table *mrt, *next; + struct mr_table *mrt, *next; rtnl_lock(); list_for_each_entry_safe(mrt, next, &net->ipv6.mr6_tables, list) { @@ -272,13 +262,21 @@ static void __net_exit ip6mr_rules_exit(struct net *net) #define ip6mr_for_each_table(mrt, net) \ for (mrt = net->ipv6.mrt6; mrt; mrt = NULL) -static struct mr6_table *ip6mr_get_table(struct net *net, u32 id) +static struct mr_table *ip6mr_mr_table_iter(struct net *net, + struct mr_table *mrt) +{ + if (!mrt) + return net->ipv6.mrt6; + return NULL; +} + +static struct mr_table *ip6mr_get_table(struct net *net, u32 id) { return net->ipv6.mrt6; } static int ip6mr_fib_lookup(struct net *net, struct flowi6 *flp6, - struct mr6_table **mrt) + struct mr_table **mrt) { *mrt = net->ipv6.mrt6; return 0; @@ -299,112 +297,75 @@ static void __net_exit ip6mr_rules_exit(struct net *net) } #endif -static struct mr6_table *ip6mr_new_table(struct net *net, u32 id) +static int ip6mr_hash_cmp(struct rhashtable_compare_arg *arg, + const void *ptr) { - struct mr6_table *mrt; - unsigned int i; + const struct mfc6_cache_cmp_arg *cmparg = arg->key; + struct mfc6_cache *c = (struct mfc6_cache *)ptr; - mrt = ip6mr_get_table(net, id); - if (mrt) - return mrt; - - mrt = kzalloc(sizeof(*mrt), GFP_KERNEL); - if (!mrt) - return NULL; - mrt->id = id; - write_pnet(&mrt->net, net); - - /* Forwarding cache */ - for (i = 0; i < MFC6_LINES; i++) - INIT_LIST_HEAD(&mrt->mfc6_cache_array[i]); - - INIT_LIST_HEAD(&mrt->mfc6_unres_queue); + return !ipv6_addr_equal(&c->mf6c_mcastgrp, &cmparg->mf6c_mcastgrp) || + !ipv6_addr_equal(&c->mf6c_origin, &cmparg->mf6c_origin); +} - timer_setup(&mrt->ipmr_expire_timer, ipmr_expire_process, 0); +static const struct rhashtable_params ip6mr_rht_params = { + .head_offset = offsetof(struct mr_mfc, mnode), + .key_offset = offsetof(struct mfc6_cache, cmparg), + .key_len = sizeof(struct mfc6_cache_cmp_arg), + .nelem_hint = 3, + .locks_mul = 1, + .obj_cmpfn = ip6mr_hash_cmp, + .automatic_shrinking = true, +}; -#ifdef CONFIG_IPV6_PIMSM_V2 - mrt->mroute_reg_vif_num = -1; -#endif +static void ip6mr_new_table_set(struct mr_table *mrt, + struct net *net) +{ #ifdef CONFIG_IPV6_MROUTE_MULTIPLE_TABLES list_add_tail_rcu(&mrt->list, &net->ipv6.mr6_tables); #endif - return mrt; } -static void ip6mr_free_table(struct mr6_table *mrt) -{ - del_timer_sync(&mrt->ipmr_expire_timer); - mroute_clean_tables(mrt, true); - kfree(mrt); -} - -#ifdef CONFIG_PROC_FS - -struct ipmr_mfc_iter { - struct seq_net_private p; - struct mr6_table *mrt; - struct list_head *cache; - int ct; +static struct mfc6_cache_cmp_arg ip6mr_mr_table_ops_cmparg_any = { + .mf6c_origin = IN6ADDR_ANY_INIT, + .mf6c_mcastgrp = IN6ADDR_ANY_INIT, }; +static struct mr_table_ops ip6mr_mr_table_ops = { + .rht_params = &ip6mr_rht_params, + .cmparg_any = &ip6mr_mr_table_ops_cmparg_any, +}; -static struct mfc6_cache *ipmr_mfc_seq_idx(struct net *net, - struct ipmr_mfc_iter *it, loff_t pos) +static struct mr_table *ip6mr_new_table(struct net *net, u32 id) { - struct mr6_table *mrt = it->mrt; - struct mfc6_cache *mfc; - - read_lock(&mrt_lock); - for (it->ct = 0; it->ct < MFC6_LINES; it->ct++) { - it->cache = &mrt->mfc6_cache_array[it->ct]; - list_for_each_entry(mfc, it->cache, list) - if (pos-- == 0) - return mfc; - } - read_unlock(&mrt_lock); + struct mr_table *mrt; - spin_lock_bh(&mfc_unres_lock); - it->cache = &mrt->mfc6_unres_queue; - list_for_each_entry(mfc, it->cache, list) - if (pos-- == 0) - return mfc; - spin_unlock_bh(&mfc_unres_lock); + mrt = ip6mr_get_table(net, id); + if (mrt) + return mrt; - it->cache = NULL; - return NULL; + return mr_table_alloc(net, id, &ip6mr_mr_table_ops, + ipmr_expire_process, ip6mr_new_table_set); } -/* - * The /proc interfaces to multicast routing /proc/ip6_mr_cache /proc/ip6_mr_vif - */ - -struct ipmr_vif_iter { - struct seq_net_private p; - struct mr6_table *mrt; - int ct; -}; - -static struct mif_device *ip6mr_vif_seq_idx(struct net *net, - struct ipmr_vif_iter *iter, - loff_t pos) +static void ip6mr_free_table(struct mr_table *mrt) { - struct mr6_table *mrt = iter->mrt; - - for (iter->ct = 0; iter->ct < mrt->maxvif; ++iter->ct) { - if (!MIF_EXISTS(mrt, iter->ct)) - continue; - if (pos-- == 0) - return &mrt->vif6_table[iter->ct]; - } - return NULL; + del_timer_sync(&mrt->ipmr_expire_timer); + mroute_clean_tables(mrt, true); + rhltable_destroy(&mrt->mfc_hash); + kfree(mrt); } +#ifdef CONFIG_PROC_FS +/* The /proc interfaces to multicast routing + * /proc/ip6_mr_cache /proc/ip6_mr_vif + */ + static void *ip6mr_vif_seq_start(struct seq_file *seq, loff_t *pos) __acquires(mrt_lock) { - struct ipmr_vif_iter *iter = seq->private; + struct mr_vif_iter *iter = seq->private; struct net *net = seq_file_net(seq); - struct mr6_table *mrt; + struct mr_table *mrt; mrt = ip6mr_get_table(net, RT6_TABLE_DFLT); if (!mrt) @@ -413,26 +374,7 @@ static void *ip6mr_vif_seq_start(struct seq_file *seq, loff_t *pos) iter->mrt = mrt; read_lock(&mrt_lock); - return *pos ? ip6mr_vif_seq_idx(net, seq->private, *pos - 1) - : SEQ_START_TOKEN; -} - -static void *ip6mr_vif_seq_next(struct seq_file *seq, void *v, loff_t *pos) -{ - struct ipmr_vif_iter *iter = seq->private; - struct net *net = seq_file_net(seq); - struct mr6_table *mrt = iter->mrt; - - ++*pos; - if (v == SEQ_START_TOKEN) - return ip6mr_vif_seq_idx(net, iter, 0); - - while (++iter->ct < mrt->maxvif) { - if (!MIF_EXISTS(mrt, iter->ct)) - continue; - return &mrt->vif6_table[iter->ct]; - } - return NULL; + return mr_vif_seq_start(seq, pos); } static void ip6mr_vif_seq_stop(struct seq_file *seq, void *v) @@ -443,19 +385,19 @@ static void ip6mr_vif_seq_stop(struct seq_file *seq, void *v) static int ip6mr_vif_seq_show(struct seq_file *seq, void *v) { - struct ipmr_vif_iter *iter = seq->private; - struct mr6_table *mrt = iter->mrt; + struct mr_vif_iter *iter = seq->private; + struct mr_table *mrt = iter->mrt; if (v == SEQ_START_TOKEN) { seq_puts(seq, "Interface BytesIn PktsIn BytesOut PktsOut Flags\n"); } else { - const struct mif_device *vif = v; + const struct vif_device *vif = v; const char *name = vif->dev ? vif->dev->name : "none"; seq_printf(seq, "%2td %-10s %8ld %7ld %8ld %7ld %05X\n", - vif - mrt->vif6_table, + vif - mrt->vif_table, name, vif->bytes_in, vif->pkt_in, vif->bytes_out, vif->pkt_out, vif->flags); @@ -465,7 +407,7 @@ static int ip6mr_vif_seq_show(struct seq_file *seq, void *v) static const struct seq_operations ip6mr_vif_seq_ops = { .start = ip6mr_vif_seq_start, - .next = ip6mr_vif_seq_next, + .next = mr_vif_seq_next, .stop = ip6mr_vif_seq_stop, .show = ip6mr_vif_seq_show, }; @@ -473,7 +415,7 @@ static const struct seq_operations ip6mr_vif_seq_ops = { static int ip6mr_vif_open(struct inode *inode, struct file *file) { return seq_open_net(inode, file, &ip6mr_vif_seq_ops, - sizeof(struct ipmr_vif_iter)); + sizeof(struct mr_vif_iter)); } static const struct file_operations ip6mr_vif_fops = { @@ -485,72 +427,14 @@ static const struct file_operations ip6mr_vif_fops = { static void *ipmr_mfc_seq_start(struct seq_file *seq, loff_t *pos) { - struct ipmr_mfc_iter *it = seq->private; struct net *net = seq_file_net(seq); - struct mr6_table *mrt; + struct mr_table *mrt; mrt = ip6mr_get_table(net, RT6_TABLE_DFLT); if (!mrt) return ERR_PTR(-ENOENT); - it->mrt = mrt; - it->cache = NULL; - return *pos ? ipmr_mfc_seq_idx(net, seq->private, *pos - 1) - : SEQ_START_TOKEN; -} - -static void *ipmr_mfc_seq_next(struct seq_file *seq, void *v, loff_t *pos) -{ - struct mfc6_cache *mfc = v; - struct ipmr_mfc_iter *it = seq->private; - struct net *net = seq_file_net(seq); - struct mr6_table *mrt = it->mrt; - - ++*pos; - - if (v == SEQ_START_TOKEN) - return ipmr_mfc_seq_idx(net, seq->private, 0); - - if (mfc->list.next != it->cache) - return list_entry(mfc->list.next, struct mfc6_cache, list); - - if (it->cache == &mrt->mfc6_unres_queue) - goto end_of_list; - - BUG_ON(it->cache != &mrt->mfc6_cache_array[it->ct]); - - while (++it->ct < MFC6_LINES) { - it->cache = &mrt->mfc6_cache_array[it->ct]; - if (list_empty(it->cache)) - continue; - return list_first_entry(it->cache, struct mfc6_cache, list); - } - - /* exhausted cache_array, show unresolved */ - read_unlock(&mrt_lock); - it->cache = &mrt->mfc6_unres_queue; - it->ct = 0; - - spin_lock_bh(&mfc_unres_lock); - if (!list_empty(it->cache)) - return list_first_entry(it->cache, struct mfc6_cache, list); - - end_of_list: - spin_unlock_bh(&mfc_unres_lock); - it->cache = NULL; - - return NULL; -} - -static void ipmr_mfc_seq_stop(struct seq_file *seq, void *v) -{ - struct ipmr_mfc_iter *it = seq->private; - struct mr6_table *mrt = it->mrt; - - if (it->cache == &mrt->mfc6_unres_queue) - spin_unlock_bh(&mfc_unres_lock); - else if (it->cache == &mrt->mfc6_cache_array[it->ct]) - read_unlock(&mrt_lock); + return mr_mfc_seq_start(seq, pos, mrt, &mfc_unres_lock); } static int ipmr_mfc_seq_show(struct seq_file *seq, void *v) @@ -564,25 +448,25 @@ static int ipmr_mfc_seq_show(struct seq_file *seq, void *v) "Iif Pkts Bytes Wrong Oifs\n"); } else { const struct mfc6_cache *mfc = v; - const struct ipmr_mfc_iter *it = seq->private; - struct mr6_table *mrt = it->mrt; + const struct mr_mfc_iter *it = seq->private; + struct mr_table *mrt = it->mrt; seq_printf(seq, "%pI6 %pI6 %-3hd", &mfc->mf6c_mcastgrp, &mfc->mf6c_origin, - mfc->mf6c_parent); + mfc->_c.mfc_parent); - if (it->cache != &mrt->mfc6_unres_queue) { + if (it->cache != &mrt->mfc_unres_queue) { seq_printf(seq, " %8lu %8lu %8lu", - mfc->mfc_un.res.pkt, - mfc->mfc_un.res.bytes, - mfc->mfc_un.res.wrong_if); - for (n = mfc->mfc_un.res.minvif; - n < mfc->mfc_un.res.maxvif; n++) { - if (MIF_EXISTS(mrt, n) && - mfc->mfc_un.res.ttls[n] < 255) + mfc->_c.mfc_un.res.pkt, + mfc->_c.mfc_un.res.bytes, + mfc->_c.mfc_un.res.wrong_if); + for (n = mfc->_c.mfc_un.res.minvif; + n < mfc->_c.mfc_un.res.maxvif; n++) { + if (VIF_EXISTS(mrt, n) && + mfc->_c.mfc_un.res.ttls[n] < 255) seq_printf(seq, - " %2d:%-3d", - n, mfc->mfc_un.res.ttls[n]); + " %2d:%-3d", n, + mfc->_c.mfc_un.res.ttls[n]); } } else { /* unresolved mfc_caches don't contain @@ -597,15 +481,15 @@ static int ipmr_mfc_seq_show(struct seq_file *seq, void *v) static const struct seq_operations ipmr_mfc_seq_ops = { .start = ipmr_mfc_seq_start, - .next = ipmr_mfc_seq_next, - .stop = ipmr_mfc_seq_stop, + .next = mr_mfc_seq_next, + .stop = mr_mfc_seq_stop, .show = ipmr_mfc_seq_show, }; static int ipmr_mfc_open(struct inode *inode, struct file *file) { return seq_open_net(inode, file, &ipmr_mfc_seq_ops, - sizeof(struct ipmr_mfc_iter)); + sizeof(struct mr_mfc_iter)); } static const struct file_operations ip6mr_mfc_fops = { @@ -624,7 +508,7 @@ static int pim6_rcv(struct sk_buff *skb) struct ipv6hdr *encap; struct net_device *reg_dev = NULL; struct net *net = dev_net(skb->dev); - struct mr6_table *mrt; + struct mr_table *mrt; struct flowi6 fl6 = { .flowi6_iif = skb->dev->ifindex, .flowi6_mark = skb->mark, @@ -658,7 +542,7 @@ static int pim6_rcv(struct sk_buff *skb) read_lock(&mrt_lock); if (reg_vif_num >= 0) - reg_dev = mrt->vif6_table[reg_vif_num].dev; + reg_dev = mrt->vif_table[reg_vif_num].dev; if (reg_dev) dev_hold(reg_dev); read_unlock(&mrt_lock); @@ -693,7 +577,7 @@ static netdev_tx_t reg_vif_xmit(struct sk_buff *skb, struct net_device *dev) { struct net *net = dev_net(dev); - struct mr6_table *mrt; + struct mr_table *mrt; struct flowi6 fl6 = { .flowi6_oif = dev->ifindex, .flowi6_iif = skb->skb_iif ? : LOOPBACK_IFINDEX, @@ -736,7 +620,7 @@ static void reg_vif_setup(struct net_device *dev) dev->features |= NETIF_F_NETNS_LOCAL; } -static struct net_device *ip6mr_reg_vif(struct net *net, struct mr6_table *mrt) +static struct net_device *ip6mr_reg_vif(struct net *net, struct mr_table *mrt) { struct net_device *dev; char name[IFNAMSIZ]; @@ -773,17 +657,17 @@ failure: * Delete a VIF entry */ -static int mif6_delete(struct mr6_table *mrt, int vifi, int notify, +static int mif6_delete(struct mr_table *mrt, int vifi, int notify, struct list_head *head) { - struct mif_device *v; + struct vif_device *v; struct net_device *dev; struct inet6_dev *in6_dev; if (vifi < 0 || vifi >= mrt->maxvif) return -EADDRNOTAVAIL; - v = &mrt->vif6_table[vifi]; + v = &mrt->vif_table[vifi]; write_lock_bh(&mrt_lock); dev = v->dev; @@ -802,7 +686,7 @@ static int mif6_delete(struct mr6_table *mrt, int vifi, int notify, if (vifi + 1 == mrt->maxvif) { int tmp; for (tmp = vifi - 1; tmp >= 0; tmp--) { - if (MIF_EXISTS(mrt, tmp)) + if (VIF_EXISTS(mrt, tmp)) break; } mrt->maxvif = tmp + 1; @@ -827,23 +711,30 @@ static int mif6_delete(struct mr6_table *mrt, int vifi, int notify, return 0; } +static inline void ip6mr_cache_free_rcu(struct rcu_head *head) +{ + struct mr_mfc *c = container_of(head, struct mr_mfc, rcu); + + kmem_cache_free(mrt_cachep, (struct mfc6_cache *)c); +} + static inline void ip6mr_cache_free(struct mfc6_cache *c) { - kmem_cache_free(mrt_cachep, c); + call_rcu(&c->_c.rcu, ip6mr_cache_free_rcu); } /* Destroy an unresolved cache entry, killing queued skbs and reporting error to netlink readers. */ -static void ip6mr_destroy_unres(struct mr6_table *mrt, struct mfc6_cache *c) +static void ip6mr_destroy_unres(struct mr_table *mrt, struct mfc6_cache *c) { struct net *net = read_pnet(&mrt->net); struct sk_buff *skb; atomic_dec(&mrt->cache_resolve_queue_len); - while ((skb = skb_dequeue(&c->mfc_un.unres.unresolved)) != NULL) { + while ((skb = skb_dequeue(&c->_c.mfc_un.unres.unresolved)) != NULL) { if (ipv6_hdr(skb)->version == 0) { struct nlmsghdr *nlh = skb_pull(skb, sizeof(struct ipv6hdr)); @@ -862,13 +753,13 @@ static void ip6mr_destroy_unres(struct mr6_table *mrt, struct mfc6_cache *c) /* Timer process for all the unresolved queue. */ -static void ipmr_do_expire_process(struct mr6_table *mrt) +static void ipmr_do_expire_process(struct mr_table *mrt) { unsigned long now = jiffies; unsigned long expires = 10 * HZ; - struct mfc6_cache *c, *next; + struct mr_mfc *c, *next; - list_for_each_entry_safe(c, next, &mrt->mfc6_unres_queue, list) { + list_for_each_entry_safe(c, next, &mrt->mfc_unres_queue, list) { if (time_after(c->mfc_un.unres.expires, now)) { /* not yet... */ unsigned long interval = c->mfc_un.unres.expires - now; @@ -878,24 +769,24 @@ static void ipmr_do_expire_process(struct mr6_table *mrt) } list_del(&c->list); - mr6_netlink_event(mrt, c, RTM_DELROUTE); - ip6mr_destroy_unres(mrt, c); + mr6_netlink_event(mrt, (struct mfc6_cache *)c, RTM_DELROUTE); + ip6mr_destroy_unres(mrt, (struct mfc6_cache *)c); } - if (!list_empty(&mrt->mfc6_unres_queue)) + if (!list_empty(&mrt->mfc_unres_queue)) mod_timer(&mrt->ipmr_expire_timer, jiffies + expires); } static void ipmr_expire_process(struct timer_list *t) { - struct mr6_table *mrt = from_timer(mrt, t, ipmr_expire_timer); + struct mr_table *mrt = from_timer(mrt, t, ipmr_expire_timer); if (!spin_trylock(&mfc_unres_lock)) { mod_timer(&mrt->ipmr_expire_timer, jiffies + 1); return; } - if (!list_empty(&mrt->mfc6_unres_queue)) + if (!list_empty(&mrt->mfc_unres_queue)) ipmr_do_expire_process(mrt); spin_unlock(&mfc_unres_lock); @@ -903,7 +794,8 @@ static void ipmr_expire_process(struct timer_list *t) /* Fill oifs list. It is called under write locked mrt_lock. */ -static void ip6mr_update_thresholds(struct mr6_table *mrt, struct mfc6_cache *cache, +static void ip6mr_update_thresholds(struct mr_table *mrt, + struct mr_mfc *cache, unsigned char *ttls) { int vifi; @@ -913,7 +805,7 @@ static void ip6mr_update_thresholds(struct mr6_table *mrt, struct mfc6_cache *ca memset(cache->mfc_un.res.ttls, 255, MAXMIFS); for (vifi = 0; vifi < mrt->maxvif; vifi++) { - if (MIF_EXISTS(mrt, vifi) && + if (VIF_EXISTS(mrt, vifi) && ttls[vifi] && ttls[vifi] < 255) { cache->mfc_un.res.ttls[vifi] = ttls[vifi]; if (cache->mfc_un.res.minvif > vifi) @@ -925,17 +817,17 @@ static void ip6mr_update_thresholds(struct mr6_table *mrt, struct mfc6_cache *ca cache->mfc_un.res.lastuse = jiffies; } -static int mif6_add(struct net *net, struct mr6_table *mrt, +static int mif6_add(struct net *net, struct mr_table *mrt, struct mif6ctl *vifc, int mrtsock) { int vifi = vifc->mif6c_mifi; - struct mif_device *v = &mrt->vif6_table[vifi]; + struct vif_device *v = &mrt->vif_table[vifi]; struct net_device *dev; struct inet6_dev *in6_dev; int err; /* Is vif busy ? */ - if (MIF_EXISTS(mrt, vifi)) + if (VIF_EXISTS(mrt, vifi)) return -EADDRINUSE; switch (vifc->mif6c_flags) { @@ -980,21 +872,10 @@ static int mif6_add(struct net *net, struct mr6_table *mrt, dev->ifindex, &in6_dev->cnf); } - /* - * Fill in the VIF structures - */ - v->rate_limit = vifc->vifc_rate_limit; - v->flags = vifc->mif6c_flags; - if (!mrtsock) - v->flags |= VIFF_STATIC; - v->threshold = vifc->vifc_threshold; - v->bytes_in = 0; - v->bytes_out = 0; - v->pkt_in = 0; - v->pkt_out = 0; - v->link = dev->ifindex; - if (v->flags & MIFF_REGISTER) - v->link = dev_get_iflink(dev); + /* Fill in the VIF structures */ + vif_device_init(v, dev, vifc->vifc_rate_limit, vifc->vifc_threshold, + vifc->mif6c_flags | (!mrtsock ? VIFF_STATIC : 0), + MIFF_REGISTER); /* And finish update writing critical data */ write_lock_bh(&mrt_lock); @@ -1009,75 +890,56 @@ static int mif6_add(struct net *net, struct mr6_table *mrt, return 0; } -static struct mfc6_cache *ip6mr_cache_find(struct mr6_table *mrt, +static struct mfc6_cache *ip6mr_cache_find(struct mr_table *mrt, const struct in6_addr *origin, const struct in6_addr *mcastgrp) { - int line = MFC6_HASH(mcastgrp, origin); - struct mfc6_cache *c; - - list_for_each_entry(c, &mrt->mfc6_cache_array[line], list) { - if (ipv6_addr_equal(&c->mf6c_origin, origin) && - ipv6_addr_equal(&c->mf6c_mcastgrp, mcastgrp)) - return c; - } - return NULL; -} - -/* Look for a (*,*,oif) entry */ -static struct mfc6_cache *ip6mr_cache_find_any_parent(struct mr6_table *mrt, - mifi_t mifi) -{ - int line = MFC6_HASH(&in6addr_any, &in6addr_any); - struct mfc6_cache *c; - - list_for_each_entry(c, &mrt->mfc6_cache_array[line], list) - if (ipv6_addr_any(&c->mf6c_origin) && - ipv6_addr_any(&c->mf6c_mcastgrp) && - (c->mfc_un.res.ttls[mifi] < 255)) - return c; + struct mfc6_cache_cmp_arg arg = { + .mf6c_origin = *origin, + .mf6c_mcastgrp = *mcastgrp, + }; - return NULL; + return mr_mfc_find(mrt, &arg); } /* Look for a (*,G) entry */ -static struct mfc6_cache *ip6mr_cache_find_any(struct mr6_table *mrt, +static struct mfc6_cache *ip6mr_cache_find_any(struct mr_table *mrt, struct in6_addr *mcastgrp, mifi_t mifi) { - int line = MFC6_HASH(mcastgrp, &in6addr_any); - struct mfc6_cache *c, *proxy; + struct mfc6_cache_cmp_arg arg = { + .mf6c_origin = in6addr_any, + .mf6c_mcastgrp = *mcastgrp, + }; if (ipv6_addr_any(mcastgrp)) - goto skip; - - list_for_each_entry(c, &mrt->mfc6_cache_array[line], list) - if (ipv6_addr_any(&c->mf6c_origin) && - ipv6_addr_equal(&c->mf6c_mcastgrp, mcastgrp)) { - if (c->mfc_un.res.ttls[mifi] < 255) - return c; - - /* It's ok if the mifi is part of the static tree */ - proxy = ip6mr_cache_find_any_parent(mrt, - c->mf6c_parent); - if (proxy && proxy->mfc_un.res.ttls[mifi] < 255) - return c; - } + return mr_mfc_find_any_parent(mrt, mifi); + return mr_mfc_find_any(mrt, mifi, &arg); +} -skip: - return ip6mr_cache_find_any_parent(mrt, mifi); +/* Look for a (S,G,iif) entry if parent != -1 */ +static struct mfc6_cache * +ip6mr_cache_find_parent(struct mr_table *mrt, + const struct in6_addr *origin, + const struct in6_addr *mcastgrp, + int parent) +{ + struct mfc6_cache_cmp_arg arg = { + .mf6c_origin = *origin, + .mf6c_mcastgrp = *mcastgrp, + }; + + return mr_mfc_find_parent(mrt, &arg, parent); } -/* - * Allocate a multicast cache entry - */ +/* Allocate a multicast cache entry */ static struct mfc6_cache *ip6mr_cache_alloc(void) { struct mfc6_cache *c = kmem_cache_zalloc(mrt_cachep, GFP_KERNEL); if (!c) return NULL; - c->mfc_un.res.last_assert = jiffies - MFC_ASSERT_THRESH - 1; - c->mfc_un.res.minvif = MAXMIFS; + c->_c.mfc_un.res.last_assert = jiffies - MFC_ASSERT_THRESH - 1; + c->_c.mfc_un.res.minvif = MAXMIFS; return c; } @@ -1086,8 +948,8 @@ static struct mfc6_cache *ip6mr_cache_alloc_unres(void) struct mfc6_cache *c = kmem_cache_zalloc(mrt_cachep, GFP_ATOMIC); if (!c) return NULL; - skb_queue_head_init(&c->mfc_un.unres.unresolved); - c->mfc_un.unres.expires = jiffies + 10 * HZ; + skb_queue_head_init(&c->_c.mfc_un.unres.unresolved); + c->_c.mfc_un.unres.expires = jiffies + 10 * HZ; return c; } @@ -1095,7 +957,7 @@ static struct mfc6_cache *ip6mr_cache_alloc_unres(void) * A cache entry has gone into a resolved state from queued */ -static void ip6mr_cache_resolve(struct net *net, struct mr6_table *mrt, +static void ip6mr_cache_resolve(struct net *net, struct mr_table *mrt, struct mfc6_cache *uc, struct mfc6_cache *c) { struct sk_buff *skb; @@ -1104,12 +966,13 @@ static void ip6mr_cache_resolve(struct net *net, struct mr6_table *mrt, * Play the pending entries through our router */ - while ((skb = __skb_dequeue(&uc->mfc_un.unres.unresolved))) { + while ((skb = __skb_dequeue(&uc->_c.mfc_un.unres.unresolved))) { if (ipv6_hdr(skb)->version == 0) { struct nlmsghdr *nlh = skb_pull(skb, sizeof(struct ipv6hdr)); - if (__ip6mr_fill_mroute(mrt, skb, c, nlmsg_data(nlh)) > 0) { + if (mr_fill_mroute(mrt, skb, &c->_c, + nlmsg_data(nlh)) > 0) { nlh->nlmsg_len = skb_tail_pointer(skb) - (u8 *)nlh; } else { nlh->nlmsg_type = NLMSG_ERROR; @@ -1129,9 +992,10 @@ static void ip6mr_cache_resolve(struct net *net, struct mr6_table *mrt, * Called under mrt_lock. */ -static int ip6mr_cache_report(struct mr6_table *mrt, struct sk_buff *pkt, +static int ip6mr_cache_report(struct mr_table *mrt, struct sk_buff *pkt, mifi_t mifi, int assert) { + struct sock *mroute6_sk; struct sk_buff *skb; struct mrt6msg *msg; int ret; @@ -1201,17 +1065,19 @@ static int ip6mr_cache_report(struct mr6_table *mrt, struct sk_buff *pkt, skb->ip_summed = CHECKSUM_UNNECESSARY; } - if (!mrt->mroute6_sk) { + rcu_read_lock(); + mroute6_sk = rcu_dereference(mrt->mroute_sk); + if (!mroute6_sk) { + rcu_read_unlock(); kfree_skb(skb); return -EINVAL; } mrt6msg_netlink_event(mrt, skb); - /* - * Deliver to user space multicast routing algorithms - */ - ret = sock_queue_rcv_skb(mrt->mroute6_sk, skb); + /* Deliver to user space multicast routing algorithms */ + ret = sock_queue_rcv_skb(mroute6_sk, skb); + rcu_read_unlock(); if (ret < 0) { net_warn_ratelimited("mroute6: pending queue full, dropping entries\n"); kfree_skb(skb); @@ -1220,19 +1086,16 @@ static int ip6mr_cache_report(struct mr6_table *mrt, struct sk_buff *pkt, return ret; } -/* - * Queue a packet for resolution. It gets locked cache entry! - */ - -static int -ip6mr_cache_unresolved(struct mr6_table *mrt, mifi_t mifi, struct sk_buff *skb) +/* Queue a packet for resolution. It gets locked cache entry! */ +static int ip6mr_cache_unresolved(struct mr_table *mrt, mifi_t mifi, + struct sk_buff *skb) { + struct mfc6_cache *c; bool found = false; int err; - struct mfc6_cache *c; spin_lock_bh(&mfc_unres_lock); - list_for_each_entry(c, &mrt->mfc6_unres_queue, list) { + list_for_each_entry(c, &mrt->mfc_unres_queue, _c.list) { if (ipv6_addr_equal(&c->mf6c_mcastgrp, &ipv6_hdr(skb)->daddr) && ipv6_addr_equal(&c->mf6c_origin, &ipv6_hdr(skb)->saddr)) { found = true; @@ -1253,10 +1116,8 @@ ip6mr_cache_unresolved(struct mr6_table *mrt, mifi_t mifi, struct sk_buff *skb) return -ENOBUFS; } - /* - * Fill in the new cache entry - */ - c->mf6c_parent = -1; + /* Fill in the new cache entry */ + c->_c.mfc_parent = -1; c->mf6c_origin = ipv6_hdr(skb)->saddr; c->mf6c_mcastgrp = ipv6_hdr(skb)->daddr; @@ -1276,20 +1137,18 @@ ip6mr_cache_unresolved(struct mr6_table *mrt, mifi_t mifi, struct sk_buff *skb) } atomic_inc(&mrt->cache_resolve_queue_len); - list_add(&c->list, &mrt->mfc6_unres_queue); + list_add(&c->_c.list, &mrt->mfc_unres_queue); mr6_netlink_event(mrt, c, RTM_NEWROUTE); ipmr_do_expire_process(mrt); } - /* - * See if we can append the packet - */ - if (c->mfc_un.unres.unresolved.qlen > 3) { + /* See if we can append the packet */ + if (c->_c.mfc_un.unres.unresolved.qlen > 3) { kfree_skb(skb); err = -ENOBUFS; } else { - skb_queue_tail(&c->mfc_un.unres.unresolved, skb); + skb_queue_tail(&c->_c.mfc_un.unres.unresolved, skb); err = 0; } @@ -1301,29 +1160,24 @@ ip6mr_cache_unresolved(struct mr6_table *mrt, mifi_t mifi, struct sk_buff *skb) * MFC6 cache manipulation by user space */ -static int ip6mr_mfc_delete(struct mr6_table *mrt, struct mf6cctl *mfc, +static int ip6mr_mfc_delete(struct mr_table *mrt, struct mf6cctl *mfc, int parent) { - int line; - struct mfc6_cache *c, *next; - - line = MFC6_HASH(&mfc->mf6cc_mcastgrp.sin6_addr, &mfc->mf6cc_origin.sin6_addr); + struct mfc6_cache *c; - list_for_each_entry_safe(c, next, &mrt->mfc6_cache_array[line], list) { - if (ipv6_addr_equal(&c->mf6c_origin, &mfc->mf6cc_origin.sin6_addr) && - ipv6_addr_equal(&c->mf6c_mcastgrp, - &mfc->mf6cc_mcastgrp.sin6_addr) && - (parent == -1 || parent == c->mf6c_parent)) { - write_lock_bh(&mrt_lock); - list_del(&c->list); - write_unlock_bh(&mrt_lock); + /* The entries are added/deleted only under RTNL */ + rcu_read_lock(); + c = ip6mr_cache_find_parent(mrt, &mfc->mf6cc_origin.sin6_addr, + &mfc->mf6cc_mcastgrp.sin6_addr, parent); + rcu_read_unlock(); + if (!c) + return -ENOENT; + rhltable_remove(&mrt->mfc_hash, &c->_c.mnode, ip6mr_rht_params); + list_del_rcu(&c->_c.list); - mr6_netlink_event(mrt, c, RTM_DELROUTE); - ip6mr_cache_free(c); - return 0; - } - } - return -ENOENT; + mr6_netlink_event(mrt, c, RTM_DELROUTE); + ip6mr_cache_free(c); + return 0; } static int ip6mr_device_event(struct notifier_block *this, @@ -1331,15 +1185,15 @@ static int ip6mr_device_event(struct notifier_block *this, { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct net *net = dev_net(dev); - struct mr6_table *mrt; - struct mif_device *v; + struct mr_table *mrt; + struct vif_device *v; int ct; if (event != NETDEV_UNREGISTER) return NOTIFY_DONE; ip6mr_for_each_table(mrt, net) { - v = &mrt->vif6_table[0]; + v = &mrt->vif_table[0]; for (ct = 0; ct < mrt->maxvif; ct++, v++) { if (v->dev == dev) mif6_delete(mrt, ct, 1, NULL); @@ -1397,6 +1251,7 @@ static void __net_exit ip6mr_net_exit(struct net *net) static struct pernet_operations ip6mr_net_ops = { .init = ip6mr_net_init, .exit = ip6mr_net_exit, + .async = true, }; int __init ip6_mr_init(void) @@ -1452,14 +1307,14 @@ void ip6_mr_cleanup(void) kmem_cache_destroy(mrt_cachep); } -static int ip6mr_mfc_add(struct net *net, struct mr6_table *mrt, +static int ip6mr_mfc_add(struct net *net, struct mr_table *mrt, struct mf6cctl *mfc, int mrtsock, int parent) { - bool found = false; - int line; - struct mfc6_cache *uc, *c; unsigned char ttls[MAXMIFS]; - int i; + struct mfc6_cache *uc, *c; + struct mr_mfc *_uc; + bool found; + int i, err; if (mfc->mf6cc_parent >= MAXMIFS) return -ENFILE; @@ -1468,27 +1323,19 @@ static int ip6mr_mfc_add(struct net *net, struct mr6_table *mrt, for (i = 0; i < MAXMIFS; i++) { if (IF_ISSET(i, &mfc->mf6cc_ifset)) ttls[i] = 1; - - } - - line = MFC6_HASH(&mfc->mf6cc_mcastgrp.sin6_addr, &mfc->mf6cc_origin.sin6_addr); - - list_for_each_entry(c, &mrt->mfc6_cache_array[line], list) { - if (ipv6_addr_equal(&c->mf6c_origin, &mfc->mf6cc_origin.sin6_addr) && - ipv6_addr_equal(&c->mf6c_mcastgrp, - &mfc->mf6cc_mcastgrp.sin6_addr) && - (parent == -1 || parent == mfc->mf6cc_parent)) { - found = true; - break; - } } - if (found) { + /* The entries are added/deleted only under RTNL */ + rcu_read_lock(); + c = ip6mr_cache_find_parent(mrt, &mfc->mf6cc_origin.sin6_addr, + &mfc->mf6cc_mcastgrp.sin6_addr, parent); + rcu_read_unlock(); + if (c) { write_lock_bh(&mrt_lock); - c->mf6c_parent = mfc->mf6cc_parent; - ip6mr_update_thresholds(mrt, c, ttls); + c->_c.mfc_parent = mfc->mf6cc_parent; + ip6mr_update_thresholds(mrt, &c->_c, ttls); if (!mrtsock) - c->mfc_flags |= MFC_STATIC; + c->_c.mfc_flags |= MFC_STATIC; write_unlock_bh(&mrt_lock); mr6_netlink_event(mrt, c, RTM_NEWROUTE); return 0; @@ -1504,31 +1351,36 @@ static int ip6mr_mfc_add(struct net *net, struct mr6_table *mrt, c->mf6c_origin = mfc->mf6cc_origin.sin6_addr; c->mf6c_mcastgrp = mfc->mf6cc_mcastgrp.sin6_addr; - c->mf6c_parent = mfc->mf6cc_parent; - ip6mr_update_thresholds(mrt, c, ttls); + c->_c.mfc_parent = mfc->mf6cc_parent; + ip6mr_update_thresholds(mrt, &c->_c, ttls); if (!mrtsock) - c->mfc_flags |= MFC_STATIC; + c->_c.mfc_flags |= MFC_STATIC; - write_lock_bh(&mrt_lock); - list_add(&c->list, &mrt->mfc6_cache_array[line]); - write_unlock_bh(&mrt_lock); + err = rhltable_insert_key(&mrt->mfc_hash, &c->cmparg, &c->_c.mnode, + ip6mr_rht_params); + if (err) { + pr_err("ip6mr: rhtable insert error %d\n", err); + ip6mr_cache_free(c); + return err; + } + list_add_tail_rcu(&c->_c.list, &mrt->mfc_cache_list); - /* - * Check to see if we resolved a queued list. If so we - * need to send on the frames and tidy up. + /* Check to see if we resolved a queued list. If so we + * need to send on the frames and tidy up. */ found = false; spin_lock_bh(&mfc_unres_lock); - list_for_each_entry(uc, &mrt->mfc6_unres_queue, list) { + list_for_each_entry(_uc, &mrt->mfc_unres_queue, list) { + uc = (struct mfc6_cache *)_uc; if (ipv6_addr_equal(&uc->mf6c_origin, &c->mf6c_origin) && ipv6_addr_equal(&uc->mf6c_mcastgrp, &c->mf6c_mcastgrp)) { - list_del(&uc->list); + list_del(&_uc->list); atomic_dec(&mrt->cache_resolve_queue_len); found = true; break; } } - if (list_empty(&mrt->mfc6_unres_queue)) + if (list_empty(&mrt->mfc_unres_queue)) del_timer(&mrt->ipmr_expire_timer); spin_unlock_bh(&mfc_unres_lock); @@ -1544,61 +1396,54 @@ static int ip6mr_mfc_add(struct net *net, struct mr6_table *mrt, * Close the multicast socket, and clear the vif tables etc */ -static void mroute_clean_tables(struct mr6_table *mrt, bool all) +static void mroute_clean_tables(struct mr_table *mrt, bool all) { - int i; + struct mr_mfc *c, *tmp; LIST_HEAD(list); - struct mfc6_cache *c, *next; + int i; - /* - * Shut down all active vif entries - */ + /* Shut down all active vif entries */ for (i = 0; i < mrt->maxvif; i++) { - if (!all && (mrt->vif6_table[i].flags & VIFF_STATIC)) + if (!all && (mrt->vif_table[i].flags & VIFF_STATIC)) continue; mif6_delete(mrt, i, 0, &list); } unregister_netdevice_many(&list); - /* - * Wipe the cache - */ - for (i = 0; i < MFC6_LINES; i++) { - list_for_each_entry_safe(c, next, &mrt->mfc6_cache_array[i], list) { - if (!all && (c->mfc_flags & MFC_STATIC)) - continue; - write_lock_bh(&mrt_lock); - list_del(&c->list); - write_unlock_bh(&mrt_lock); - - mr6_netlink_event(mrt, c, RTM_DELROUTE); - ip6mr_cache_free(c); - } + /* Wipe the cache */ + list_for_each_entry_safe(c, tmp, &mrt->mfc_cache_list, list) { + if (!all && (c->mfc_flags & MFC_STATIC)) + continue; + rhltable_remove(&mrt->mfc_hash, &c->mnode, ip6mr_rht_params); + list_del_rcu(&c->list); + mr6_netlink_event(mrt, (struct mfc6_cache *)c, RTM_DELROUTE); + ip6mr_cache_free((struct mfc6_cache *)c); } if (atomic_read(&mrt->cache_resolve_queue_len) != 0) { spin_lock_bh(&mfc_unres_lock); - list_for_each_entry_safe(c, next, &mrt->mfc6_unres_queue, list) { + list_for_each_entry_safe(c, tmp, &mrt->mfc_unres_queue, list) { list_del(&c->list); - mr6_netlink_event(mrt, c, RTM_DELROUTE); - ip6mr_destroy_unres(mrt, c); + mr6_netlink_event(mrt, (struct mfc6_cache *)c, + RTM_DELROUTE); + ip6mr_destroy_unres(mrt, (struct mfc6_cache *)c); } spin_unlock_bh(&mfc_unres_lock); } } -static int ip6mr_sk_init(struct mr6_table *mrt, struct sock *sk) +static int ip6mr_sk_init(struct mr_table *mrt, struct sock *sk) { int err = 0; struct net *net = sock_net(sk); rtnl_lock(); write_lock_bh(&mrt_lock); - if (likely(mrt->mroute6_sk == NULL)) { - mrt->mroute6_sk = sk; - net->ipv6.devconf_all->mc_forwarding++; - } else { + if (rtnl_dereference(mrt->mroute_sk)) { err = -EADDRINUSE; + } else { + rcu_assign_pointer(mrt->mroute_sk, sk); + net->ipv6.devconf_all->mc_forwarding++; } write_unlock_bh(&mrt_lock); @@ -1616,7 +1461,7 @@ int ip6mr_sk_done(struct sock *sk) { int err = -EACCES; struct net *net = sock_net(sk); - struct mr6_table *mrt; + struct mr_table *mrt; if (sk->sk_type != SOCK_RAW || inet_sk(sk)->inet_num != IPPROTO_ICMPV6) @@ -1624,9 +1469,9 @@ int ip6mr_sk_done(struct sock *sk) rtnl_lock(); ip6mr_for_each_table(mrt, net) { - if (sk == mrt->mroute6_sk) { + if (sk == rtnl_dereference(mrt->mroute_sk)) { write_lock_bh(&mrt_lock); - mrt->mroute6_sk = NULL; + RCU_INIT_POINTER(mrt->mroute_sk, NULL); net->ipv6.devconf_all->mc_forwarding--; write_unlock_bh(&mrt_lock); inet6_netconf_notify_devconf(net, RTM_NEWNETCONF, @@ -1640,13 +1485,14 @@ int ip6mr_sk_done(struct sock *sk) } } rtnl_unlock(); + synchronize_rcu(); return err; } -struct sock *mroute6_socket(struct net *net, struct sk_buff *skb) +bool mroute6_is_socket(struct net *net, struct sk_buff *skb) { - struct mr6_table *mrt; + struct mr_table *mrt; struct flowi6 fl6 = { .flowi6_iif = skb->skb_iif ? : LOOPBACK_IFINDEX, .flowi6_oif = skb->dev->ifindex, @@ -1656,8 +1502,9 @@ struct sock *mroute6_socket(struct net *net, struct sk_buff *skb) if (ip6mr_fib_lookup(net, &fl6, &mrt) < 0) return NULL; - return mrt->mroute6_sk; + return rcu_access_pointer(mrt->mroute_sk); } +EXPORT_SYMBOL(mroute6_is_socket); /* * Socket options and virtual interface manipulation. The whole @@ -1673,7 +1520,7 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns struct mf6cctl mfc; mifi_t mifi; struct net *net = sock_net(sk); - struct mr6_table *mrt; + struct mr_table *mrt; if (sk->sk_type != SOCK_RAW || inet_sk(sk)->inet_num != IPPROTO_ICMPV6) @@ -1684,7 +1531,8 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns return -ENOENT; if (optname != MRT6_INIT) { - if (sk != mrt->mroute6_sk && !ns_capable(net->user_ns, CAP_NET_ADMIN)) + if (sk != rcu_access_pointer(mrt->mroute_sk) && + !ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EACCES; } @@ -1706,7 +1554,8 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns if (vif.mif6c_mifi >= MAXMIFS) return -ENFILE; rtnl_lock(); - ret = mif6_add(net, mrt, &vif, sk == mrt->mroute6_sk); + ret = mif6_add(net, mrt, &vif, + sk == rtnl_dereference(mrt->mroute_sk)); rtnl_unlock(); return ret; @@ -1741,7 +1590,9 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns ret = ip6mr_mfc_delete(mrt, &mfc, parent); else ret = ip6mr_mfc_add(net, mrt, &mfc, - sk == mrt->mroute6_sk, parent); + sk == + rtnl_dereference(mrt->mroute_sk), + parent); rtnl_unlock(); return ret; @@ -1793,7 +1644,7 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns /* "pim6reg%u" should not exceed 16 bytes (IFNAMSIZ) */ if (v != RT_TABLE_DEFAULT && v >= 100000000) return -EINVAL; - if (sk == mrt->mroute6_sk) + if (sk == rcu_access_pointer(mrt->mroute_sk)) return -EBUSY; rtnl_lock(); @@ -1824,7 +1675,7 @@ int ip6_mroute_getsockopt(struct sock *sk, int optname, char __user *optval, int olr; int val; struct net *net = sock_net(sk); - struct mr6_table *mrt; + struct mr_table *mrt; if (sk->sk_type != SOCK_RAW || inet_sk(sk)->inet_num != IPPROTO_ICMPV6) @@ -1872,10 +1723,10 @@ int ip6mr_ioctl(struct sock *sk, int cmd, void __user *arg) { struct sioc_sg_req6 sr; struct sioc_mif_req6 vr; - struct mif_device *vif; + struct vif_device *vif; struct mfc6_cache *c; struct net *net = sock_net(sk); - struct mr6_table *mrt; + struct mr_table *mrt; mrt = ip6mr_get_table(net, raw6_sk(sk)->ip6mr_table ? : RT6_TABLE_DFLT); if (!mrt) @@ -1888,8 +1739,8 @@ int ip6mr_ioctl(struct sock *sk, int cmd, void __user *arg) if (vr.mifi >= mrt->maxvif) return -EINVAL; read_lock(&mrt_lock); - vif = &mrt->vif6_table[vr.mifi]; - if (MIF_EXISTS(mrt, vr.mifi)) { + vif = &mrt->vif_table[vr.mifi]; + if (VIF_EXISTS(mrt, vr.mifi)) { vr.icount = vif->pkt_in; vr.ocount = vif->pkt_out; vr.ibytes = vif->bytes_in; @@ -1906,19 +1757,19 @@ int ip6mr_ioctl(struct sock *sk, int cmd, void __user *arg) if (copy_from_user(&sr, arg, sizeof(sr))) return -EFAULT; - read_lock(&mrt_lock); + rcu_read_lock(); c = ip6mr_cache_find(mrt, &sr.src.sin6_addr, &sr.grp.sin6_addr); if (c) { - sr.pktcnt = c->mfc_un.res.pkt; - sr.bytecnt = c->mfc_un.res.bytes; - sr.wrong_if = c->mfc_un.res.wrong_if; - read_unlock(&mrt_lock); + sr.pktcnt = c->_c.mfc_un.res.pkt; + sr.bytecnt = c->_c.mfc_un.res.bytes; + sr.wrong_if = c->_c.mfc_un.res.wrong_if; + rcu_read_unlock(); if (copy_to_user(arg, &sr, sizeof(sr))) return -EFAULT; return 0; } - read_unlock(&mrt_lock); + rcu_read_unlock(); return -EADDRNOTAVAIL; default: return -ENOIOCTLCMD; @@ -1946,10 +1797,10 @@ int ip6mr_compat_ioctl(struct sock *sk, unsigned int cmd, void __user *arg) { struct compat_sioc_sg_req6 sr; struct compat_sioc_mif_req6 vr; - struct mif_device *vif; + struct vif_device *vif; struct mfc6_cache *c; struct net *net = sock_net(sk); - struct mr6_table *mrt; + struct mr_table *mrt; mrt = ip6mr_get_table(net, raw6_sk(sk)->ip6mr_table ? : RT6_TABLE_DFLT); if (!mrt) @@ -1962,8 +1813,8 @@ int ip6mr_compat_ioctl(struct sock *sk, unsigned int cmd, void __user *arg) if (vr.mifi >= mrt->maxvif) return -EINVAL; read_lock(&mrt_lock); - vif = &mrt->vif6_table[vr.mifi]; - if (MIF_EXISTS(mrt, vr.mifi)) { + vif = &mrt->vif_table[vr.mifi]; + if (VIF_EXISTS(mrt, vr.mifi)) { vr.icount = vif->pkt_in; vr.ocount = vif->pkt_out; vr.ibytes = vif->bytes_in; @@ -1980,19 +1831,19 @@ int ip6mr_compat_ioctl(struct sock *sk, unsigned int cmd, void __user *arg) if (copy_from_user(&sr, arg, sizeof(sr))) return -EFAULT; - read_lock(&mrt_lock); + rcu_read_lock(); c = ip6mr_cache_find(mrt, &sr.src.sin6_addr, &sr.grp.sin6_addr); if (c) { - sr.pktcnt = c->mfc_un.res.pkt; - sr.bytecnt = c->mfc_un.res.bytes; - sr.wrong_if = c->mfc_un.res.wrong_if; - read_unlock(&mrt_lock); + sr.pktcnt = c->_c.mfc_un.res.pkt; + sr.bytecnt = c->_c.mfc_un.res.bytes; + sr.wrong_if = c->_c.mfc_un.res.wrong_if; + rcu_read_unlock(); if (copy_to_user(arg, &sr, sizeof(sr))) return -EFAULT; return 0; } - read_unlock(&mrt_lock); + rcu_read_unlock(); return -EADDRNOTAVAIL; default: return -ENOIOCTLCMD; @@ -2013,11 +1864,11 @@ static inline int ip6mr_forward2_finish(struct net *net, struct sock *sk, struct * Processing handlers for ip6mr_forward */ -static int ip6mr_forward2(struct net *net, struct mr6_table *mrt, +static int ip6mr_forward2(struct net *net, struct mr_table *mrt, struct sk_buff *skb, struct mfc6_cache *c, int vifi) { struct ipv6hdr *ipv6h; - struct mif_device *vif = &mrt->vif6_table[vifi]; + struct vif_device *vif = &mrt->vif_table[vifi]; struct net_device *dev; struct dst_entry *dst; struct flowi6 fl6; @@ -2087,46 +1938,50 @@ out_free: return 0; } -static int ip6mr_find_vif(struct mr6_table *mrt, struct net_device *dev) +static int ip6mr_find_vif(struct mr_table *mrt, struct net_device *dev) { int ct; for (ct = mrt->maxvif - 1; ct >= 0; ct--) { - if (mrt->vif6_table[ct].dev == dev) + if (mrt->vif_table[ct].dev == dev) break; } return ct; } -static void ip6_mr_forward(struct net *net, struct mr6_table *mrt, - struct sk_buff *skb, struct mfc6_cache *cache) +static void ip6_mr_forward(struct net *net, struct mr_table *mrt, + struct sk_buff *skb, struct mfc6_cache *c) { int psend = -1; int vif, ct; int true_vifi = ip6mr_find_vif(mrt, skb->dev); - vif = cache->mf6c_parent; - cache->mfc_un.res.pkt++; - cache->mfc_un.res.bytes += skb->len; - cache->mfc_un.res.lastuse = jiffies; + vif = c->_c.mfc_parent; + c->_c.mfc_un.res.pkt++; + c->_c.mfc_un.res.bytes += skb->len; + c->_c.mfc_un.res.lastuse = jiffies; - if (ipv6_addr_any(&cache->mf6c_origin) && true_vifi >= 0) { + if (ipv6_addr_any(&c->mf6c_origin) && true_vifi >= 0) { struct mfc6_cache *cache_proxy; /* For an (*,G) entry, we only check that the incoming * interface is part of the static tree. */ - cache_proxy = ip6mr_cache_find_any_parent(mrt, vif); + rcu_read_lock(); + cache_proxy = mr_mfc_find_any_parent(mrt, vif); if (cache_proxy && - cache_proxy->mfc_un.res.ttls[true_vifi] < 255) + cache_proxy->_c.mfc_un.res.ttls[true_vifi] < 255) { + rcu_read_unlock(); goto forward; + } + rcu_read_unlock(); } /* * Wrong interface: drop packet and (maybe) send PIM assert. */ - if (mrt->vif6_table[vif].dev != skb->dev) { - cache->mfc_un.res.wrong_if++; + if (mrt->vif_table[vif].dev != skb->dev) { + c->_c.mfc_un.res.wrong_if++; if (true_vifi >= 0 && mrt->mroute_do_assert && /* pimsm uses asserts, when switching from RPT to SPT, @@ -2135,52 +1990,55 @@ static void ip6_mr_forward(struct net *net, struct mr6_table *mrt, large chunk of pimd to kernel. Ough... --ANK */ (mrt->mroute_do_pim || - cache->mfc_un.res.ttls[true_vifi] < 255) && + c->_c.mfc_un.res.ttls[true_vifi] < 255) && time_after(jiffies, - cache->mfc_un.res.last_assert + MFC_ASSERT_THRESH)) { - cache->mfc_un.res.last_assert = jiffies; + c->_c.mfc_un.res.last_assert + + MFC_ASSERT_THRESH)) { + c->_c.mfc_un.res.last_assert = jiffies; ip6mr_cache_report(mrt, skb, true_vifi, MRT6MSG_WRONGMIF); } goto dont_forward; } forward: - mrt->vif6_table[vif].pkt_in++; - mrt->vif6_table[vif].bytes_in += skb->len; + mrt->vif_table[vif].pkt_in++; + mrt->vif_table[vif].bytes_in += skb->len; /* * Forward the frame */ - if (ipv6_addr_any(&cache->mf6c_origin) && - ipv6_addr_any(&cache->mf6c_mcastgrp)) { + if (ipv6_addr_any(&c->mf6c_origin) && + ipv6_addr_any(&c->mf6c_mcastgrp)) { if (true_vifi >= 0 && - true_vifi != cache->mf6c_parent && + true_vifi != c->_c.mfc_parent && ipv6_hdr(skb)->hop_limit > - cache->mfc_un.res.ttls[cache->mf6c_parent]) { + c->_c.mfc_un.res.ttls[c->_c.mfc_parent]) { /* It's an (*,*) entry and the packet is not coming from * the upstream: forward the packet to the upstream * only. */ - psend = cache->mf6c_parent; + psend = c->_c.mfc_parent; goto last_forward; } goto dont_forward; } - for (ct = cache->mfc_un.res.maxvif - 1; ct >= cache->mfc_un.res.minvif; ct--) { + for (ct = c->_c.mfc_un.res.maxvif - 1; + ct >= c->_c.mfc_un.res.minvif; ct--) { /* For (*,G) entry, don't forward to the incoming interface */ - if ((!ipv6_addr_any(&cache->mf6c_origin) || ct != true_vifi) && - ipv6_hdr(skb)->hop_limit > cache->mfc_un.res.ttls[ct]) { + if ((!ipv6_addr_any(&c->mf6c_origin) || ct != true_vifi) && + ipv6_hdr(skb)->hop_limit > c->_c.mfc_un.res.ttls[ct]) { if (psend != -1) { struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC); if (skb2) - ip6mr_forward2(net, mrt, skb2, cache, psend); + ip6mr_forward2(net, mrt, skb2, + c, psend); } psend = ct; } } last_forward: if (psend != -1) { - ip6mr_forward2(net, mrt, skb, cache, psend); + ip6mr_forward2(net, mrt, skb, c, psend); return; } @@ -2197,7 +2055,7 @@ int ip6_mr_input(struct sk_buff *skb) { struct mfc6_cache *cache; struct net *net = dev_net(skb->dev); - struct mr6_table *mrt; + struct mr_table *mrt; struct flowi6 fl6 = { .flowi6_iif = skb->dev->ifindex, .flowi6_mark = skb->mark, @@ -2247,66 +2105,11 @@ int ip6_mr_input(struct sk_buff *skb) return 0; } - -static int __ip6mr_fill_mroute(struct mr6_table *mrt, struct sk_buff *skb, - struct mfc6_cache *c, struct rtmsg *rtm) -{ - struct rta_mfc_stats mfcs; - struct nlattr *mp_attr; - struct rtnexthop *nhp; - unsigned long lastuse; - int ct; - - /* If cache is unresolved, don't try to parse IIF and OIF */ - if (c->mf6c_parent >= MAXMIFS) { - rtm->rtm_flags |= RTNH_F_UNRESOLVED; - return -ENOENT; - } - - if (MIF_EXISTS(mrt, c->mf6c_parent) && - nla_put_u32(skb, RTA_IIF, mrt->vif6_table[c->mf6c_parent].dev->ifindex) < 0) - return -EMSGSIZE; - mp_attr = nla_nest_start(skb, RTA_MULTIPATH); - if (!mp_attr) - return -EMSGSIZE; - - for (ct = c->mfc_un.res.minvif; ct < c->mfc_un.res.maxvif; ct++) { - if (MIF_EXISTS(mrt, ct) && c->mfc_un.res.ttls[ct] < 255) { - nhp = nla_reserve_nohdr(skb, sizeof(*nhp)); - if (!nhp) { - nla_nest_cancel(skb, mp_attr); - return -EMSGSIZE; - } - - nhp->rtnh_flags = 0; - nhp->rtnh_hops = c->mfc_un.res.ttls[ct]; - nhp->rtnh_ifindex = mrt->vif6_table[ct].dev->ifindex; - nhp->rtnh_len = sizeof(*nhp); - } - } - - nla_nest_end(skb, mp_attr); - - lastuse = READ_ONCE(c->mfc_un.res.lastuse); - lastuse = time_after_eq(jiffies, lastuse) ? jiffies - lastuse : 0; - - mfcs.mfcs_packets = c->mfc_un.res.pkt; - mfcs.mfcs_bytes = c->mfc_un.res.bytes; - mfcs.mfcs_wrong_if = c->mfc_un.res.wrong_if; - if (nla_put_64bit(skb, RTA_MFC_STATS, sizeof(mfcs), &mfcs, RTA_PAD) || - nla_put_u64_64bit(skb, RTA_EXPIRES, jiffies_to_clock_t(lastuse), - RTA_PAD)) - return -EMSGSIZE; - - rtm->rtm_type = RTN_MULTICAST; - return 1; -} - int ip6mr_get_route(struct net *net, struct sk_buff *skb, struct rtmsg *rtm, u32 portid) { int err; - struct mr6_table *mrt; + struct mr_table *mrt; struct mfc6_cache *cache; struct rt6_info *rt = (struct rt6_info *)skb_dst(skb); @@ -2367,15 +2170,12 @@ int ip6mr_get_route(struct net *net, struct sk_buff *skb, struct rtmsg *rtm, return err; } - if (rtm->rtm_flags & RTM_F_NOTIFY) - cache->mfc_flags |= MFC_NOTIFY; - - err = __ip6mr_fill_mroute(mrt, skb, cache, rtm); + err = mr_fill_mroute(mrt, skb, &cache->_c, rtm); read_unlock(&mrt_lock); return err; } -static int ip6mr_fill_mroute(struct mr6_table *mrt, struct sk_buff *skb, +static int ip6mr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb, u32 portid, u32 seq, struct mfc6_cache *c, int cmd, int flags) { @@ -2397,7 +2197,7 @@ static int ip6mr_fill_mroute(struct mr6_table *mrt, struct sk_buff *skb, goto nla_put_failure; rtm->rtm_type = RTN_MULTICAST; rtm->rtm_scope = RT_SCOPE_UNIVERSE; - if (c->mfc_flags & MFC_STATIC) + if (c->_c.mfc_flags & MFC_STATIC) rtm->rtm_protocol = RTPROT_STATIC; else rtm->rtm_protocol = RTPROT_MROUTED; @@ -2406,7 +2206,7 @@ static int ip6mr_fill_mroute(struct mr6_table *mrt, struct sk_buff *skb, if (nla_put_in6_addr(skb, RTA_SRC, &c->mf6c_origin) || nla_put_in6_addr(skb, RTA_DST, &c->mf6c_mcastgrp)) goto nla_put_failure; - err = __ip6mr_fill_mroute(mrt, skb, c, rtm); + err = mr_fill_mroute(mrt, skb, &c->_c, rtm); /* do not break the dump if cache is unresolved */ if (err < 0 && err != -ENOENT) goto nla_put_failure; @@ -2419,6 +2219,14 @@ nla_put_failure: return -EMSGSIZE; } +static int _ip6mr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb, + u32 portid, u32 seq, struct mr_mfc *c, + int cmd, int flags) +{ + return ip6mr_fill_mroute(mrt, skb, portid, seq, (struct mfc6_cache *)c, + cmd, flags); +} + static int mr6_msgsize(bool unresolved, int maxvif) { size_t len = @@ -2440,14 +2248,14 @@ static int mr6_msgsize(bool unresolved, int maxvif) return len; } -static void mr6_netlink_event(struct mr6_table *mrt, struct mfc6_cache *mfc, +static void mr6_netlink_event(struct mr_table *mrt, struct mfc6_cache *mfc, int cmd) { struct net *net = read_pnet(&mrt->net); struct sk_buff *skb; int err = -ENOBUFS; - skb = nlmsg_new(mr6_msgsize(mfc->mf6c_parent >= MAXMIFS, mrt->maxvif), + skb = nlmsg_new(mr6_msgsize(mfc->_c.mfc_parent >= MAXMIFS, mrt->maxvif), GFP_ATOMIC); if (!skb) goto errout; @@ -2482,7 +2290,7 @@ static size_t mrt6msg_netlink_msgsize(size_t payloadlen) return len; } -static void mrt6msg_netlink_event(struct mr6_table *mrt, struct sk_buff *pkt) +static void mrt6msg_netlink_event(struct mr_table *mrt, struct sk_buff *pkt) { struct net *net = read_pnet(&mrt->net); struct nlmsghdr *nlh; @@ -2532,65 +2340,6 @@ errout: static int ip6mr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb) { - struct net *net = sock_net(skb->sk); - struct mr6_table *mrt; - struct mfc6_cache *mfc; - unsigned int t = 0, s_t; - unsigned int h = 0, s_h; - unsigned int e = 0, s_e; - - s_t = cb->args[0]; - s_h = cb->args[1]; - s_e = cb->args[2]; - - read_lock(&mrt_lock); - ip6mr_for_each_table(mrt, net) { - if (t < s_t) - goto next_table; - if (t > s_t) - s_h = 0; - for (h = s_h; h < MFC6_LINES; h++) { - list_for_each_entry(mfc, &mrt->mfc6_cache_array[h], list) { - if (e < s_e) - goto next_entry; - if (ip6mr_fill_mroute(mrt, skb, - NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, - mfc, RTM_NEWROUTE, - NLM_F_MULTI) < 0) - goto done; -next_entry: - e++; - } - e = s_e = 0; - } - spin_lock_bh(&mfc_unres_lock); - list_for_each_entry(mfc, &mrt->mfc6_unres_queue, list) { - if (e < s_e) - goto next_entry2; - if (ip6mr_fill_mroute(mrt, skb, - NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, - mfc, RTM_NEWROUTE, - NLM_F_MULTI) < 0) { - spin_unlock_bh(&mfc_unres_lock); - goto done; - } -next_entry2: - e++; - } - spin_unlock_bh(&mfc_unres_lock); - e = s_e = 0; - s_h = 0; -next_table: - t++; - } -done: - read_unlock(&mrt_lock); - - cb->args[2] = e; - cb->args[1] = h; - cb->args[0] = t; - - return skb->len; + return mr_rtm_dumproute(skb, cb, ip6mr_mr_table_iter, + _ip6mr_fill_mroute, &mfc_unres_lock); } diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index 24535169663d..4d780c7f0130 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -1415,4 +1415,3 @@ int compat_ipv6_getsockopt(struct sock *sk, int level, int optname, } EXPORT_SYMBOL(compat_ipv6_getsockopt); #endif - diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index 9b9d2ff01b35..d1a0cefac273 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -165,7 +165,7 @@ int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr) if (ifindex == 0) { struct rt6_info *rt; - rt = rt6_lookup(net, addr, NULL, 0, 0); + rt = rt6_lookup(net, addr, NULL, 0, NULL, 0); if (rt) { dev = rt->dst.dev; ip6_rt_put(rt); @@ -254,7 +254,7 @@ static struct inet6_dev *ip6_mc_find_dev_rcu(struct net *net, struct inet6_dev *idev = NULL; if (ifindex == 0) { - struct rt6_info *rt = rt6_lookup(net, group, NULL, 0, 0); + struct rt6_info *rt = rt6_lookup(net, group, NULL, 0, NULL, 0); if (rt) { dev = rt->dst.dev; @@ -2997,6 +2997,7 @@ static void __net_exit igmp6_net_exit(struct net *net) static struct pernet_operations igmp6_net_ops = { .init = igmp6_net_init, .exit = igmp6_net_exit, + .async = true, }; int __init igmp6_init(void) diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index f61a5b613b52..0a19ce3a6f7f 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -1882,6 +1882,7 @@ static void __net_exit ndisc_net_exit(struct net *net) static struct pernet_operations ndisc_net_ops = { .init = ndisc_net_init, .exit = ndisc_net_exit, + .async = true, }; int __init ndisc_init(void) diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index 62358b93bbac..4de8ac1e5af4 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -1928,6 +1928,7 @@ static void __net_exit ip6_tables_net_exit(struct net *net) static struct pernet_operations ip6_tables_net_ops = { .init = ip6_tables_net_init, .exit = ip6_tables_net_exit, + .async = true, }; static int __init ip6_tables_init(void) diff --git a/net/ipv6/netfilter/ip6t_rpfilter.c b/net/ipv6/netfilter/ip6t_rpfilter.c index 91ed25a24b79..d12f511929f5 100644 --- a/net/ipv6/netfilter/ip6t_rpfilter.c +++ b/net/ipv6/netfilter/ip6t_rpfilter.c @@ -49,7 +49,7 @@ static bool rpfilter_lookup_reverse6(struct net *net, const struct sk_buff *skb, fl6.flowi6_mark = flags & XT_RPFILTER_VALID_MARK ? skb->mark : 0; - rt = (void *) ip6_route_lookup(net, &fl6, lookup_flags); + rt = (void *)ip6_route_lookup(net, &fl6, skb, lookup_flags); if (rt->dst.error) goto out; diff --git a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c index c87b48359e8f..32f98bc06900 100644 --- a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c +++ b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c @@ -103,6 +103,7 @@ static void __net_exit defrag6_net_exit(struct net *net) static struct pernet_operations defrag6_net_ops = { .exit = defrag6_net_exit, + .async = true, }; static int __init nf_defrag_init(void) diff --git a/net/ipv6/netfilter/nf_log_ipv6.c b/net/ipv6/netfilter/nf_log_ipv6.c index b397a8fe88b9..0220e584589c 100644 --- a/net/ipv6/netfilter/nf_log_ipv6.c +++ b/net/ipv6/netfilter/nf_log_ipv6.c @@ -390,6 +390,7 @@ static void __net_exit nf_log_ipv6_net_exit(struct net *net) static struct pernet_operations nf_log_ipv6_net_ops = { .init = nf_log_ipv6_net_init, .exit = nf_log_ipv6_net_exit, + .async = true, }; static int __init nf_log_ipv6_init(void) diff --git a/net/ipv6/netfilter/nft_fib_ipv6.c b/net/ipv6/netfilter/nft_fib_ipv6.c index 62fc84d7bdff..36be3cf0adef 100644 --- a/net/ipv6/netfilter/nft_fib_ipv6.c +++ b/net/ipv6/netfilter/nft_fib_ipv6.c @@ -180,7 +180,8 @@ void nft_fib6_eval(const struct nft_expr *expr, struct nft_regs *regs, } *dest = 0; - rt = (void *)ip6_route_lookup(nft_net(pkt), &fl6, lookup_flags); + rt = (void *)ip6_route_lookup(nft_net(pkt), &fl6, pkt->skb, + lookup_flags); if (rt->dst.error) goto put_rt_err; diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c index d12c55dad7d1..318c6e914234 100644 --- a/net/ipv6/ping.c +++ b/net/ipv6/ping.c @@ -240,6 +240,7 @@ static void __net_init ping_v6_proc_exit_net(struct net *net) static struct pernet_operations ping_v6_net_ops = { .init = ping_v6_proc_init_net, .exit = ping_v6_proc_exit_net, + .async = true, }; #endif diff --git a/net/ipv6/proc.c b/net/ipv6/proc.c index b67814242f78..1678cf037688 100644 --- a/net/ipv6/proc.c +++ b/net/ipv6/proc.c @@ -343,6 +343,7 @@ static void __net_exit ipv6_proc_exit_net(struct net *net) static struct pernet_operations ipv6_proc_ops = { .init = ipv6_proc_init_net, .exit = ipv6_proc_exit_net, + .async = true, }; int __init ipv6_misc_proc_init(void) @@ -354,4 +355,3 @@ void ipv6_misc_proc_exit(void) { unregister_pernet_subsys(&ipv6_proc_ops); } - diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 4c25339b1984..10a4ac4933b7 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -1332,6 +1332,7 @@ static void __net_exit raw6_exit_net(struct net *net) static struct pernet_operations raw6_net_ops = { .init = raw6_init_net, .exit = raw6_exit_net, + .async = true, }; int __init raw6_proc_init(void) diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index afbc000ad4f2..b5da69c83123 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -733,6 +733,7 @@ static void __net_exit ipv6_frags_exit_net(struct net *net) static struct pernet_operations ip6_frags_ops = { .init = ipv6_frags_init_net, .exit = ipv6_frags_exit_net, + .async = true, }; int __init ipv6_frag_init(void) diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 9dcfadddd800..f0ae58424c45 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -450,8 +450,10 @@ static bool rt6_check_expired(const struct rt6_info *rt) return false; } -static struct rt6_info *rt6_multipath_select(struct rt6_info *match, +static struct rt6_info *rt6_multipath_select(const struct net *net, + struct rt6_info *match, struct flowi6 *fl6, int oif, + const struct sk_buff *skb, int strict) { struct rt6_info *sibling, *next_sibling; @@ -460,7 +462,7 @@ static struct rt6_info *rt6_multipath_select(struct rt6_info *match, * case it will always be non-zero. Otherwise now is the time to do it. */ if (!fl6->mp_hash) - fl6->mp_hash = rt6_multipath_hash(fl6, NULL); + fl6->mp_hash = rt6_multipath_hash(net, fl6, skb, NULL); if (fl6->mp_hash <= atomic_read(&match->rt6i_nh_upper_bound)) return match; @@ -914,7 +916,9 @@ static bool ip6_hold_safe(struct net *net, struct rt6_info **prt, static struct rt6_info *ip6_pol_route_lookup(struct net *net, struct fib6_table *table, - struct flowi6 *fl6, int flags) + struct flowi6 *fl6, + const struct sk_buff *skb, + int flags) { struct rt6_info *rt, *rt_cache; struct fib6_node *fn; @@ -929,8 +933,8 @@ restart: rt = rt6_device_match(net, rt, &fl6->saddr, fl6->flowi6_oif, flags); if (rt->rt6i_nsiblings && fl6->flowi6_oif == 0) - rt = rt6_multipath_select(rt, fl6, - fl6->flowi6_oif, flags); + rt = rt6_multipath_select(net, rt, fl6, fl6->flowi6_oif, + skb, flags); } if (rt == net->ipv6.ip6_null_entry) { fn = fib6_backtrack(fn, &fl6->saddr); @@ -954,14 +958,15 @@ restart: } struct dst_entry *ip6_route_lookup(struct net *net, struct flowi6 *fl6, - int flags) + const struct sk_buff *skb, int flags) { - return fib6_rule_lookup(net, fl6, flags, ip6_pol_route_lookup); + return fib6_rule_lookup(net, fl6, skb, flags, ip6_pol_route_lookup); } EXPORT_SYMBOL_GPL(ip6_route_lookup); struct rt6_info *rt6_lookup(struct net *net, const struct in6_addr *daddr, - const struct in6_addr *saddr, int oif, int strict) + const struct in6_addr *saddr, int oif, + const struct sk_buff *skb, int strict) { struct flowi6 fl6 = { .flowi6_oif = oif, @@ -975,7 +980,7 @@ struct rt6_info *rt6_lookup(struct net *net, const struct in6_addr *daddr, flags |= RT6_LOOKUP_F_HAS_SADDR; } - dst = fib6_rule_lookup(net, &fl6, flags, ip6_pol_route_lookup); + dst = fib6_rule_lookup(net, &fl6, skb, flags, ip6_pol_route_lookup); if (dst->error == 0) return (struct rt6_info *) dst; @@ -1647,7 +1652,8 @@ void rt6_age_exceptions(struct rt6_info *rt, } struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table, - int oif, struct flowi6 *fl6, int flags) + int oif, struct flowi6 *fl6, + const struct sk_buff *skb, int flags) { struct fib6_node *fn, *saved_fn; struct rt6_info *rt, *rt_cache; @@ -1669,7 +1675,7 @@ struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table, redo_rt6_select: rt = rt6_select(net, fn, oif, strict); if (rt->rt6i_nsiblings) - rt = rt6_multipath_select(rt, fl6, oif, strict); + rt = rt6_multipath_select(net, rt, fl6, oif, skb, strict); if (rt == net->ipv6.ip6_null_entry) { fn = fib6_backtrack(fn, &fl6->saddr); if (fn) @@ -1768,28 +1774,35 @@ uncached_rt_out: } EXPORT_SYMBOL_GPL(ip6_pol_route); -static struct rt6_info *ip6_pol_route_input(struct net *net, struct fib6_table *table, - struct flowi6 *fl6, int flags) +static struct rt6_info *ip6_pol_route_input(struct net *net, + struct fib6_table *table, + struct flowi6 *fl6, + const struct sk_buff *skb, + int flags) { - return ip6_pol_route(net, table, fl6->flowi6_iif, fl6, flags); + return ip6_pol_route(net, table, fl6->flowi6_iif, fl6, skb, flags); } struct dst_entry *ip6_route_input_lookup(struct net *net, struct net_device *dev, - struct flowi6 *fl6, int flags) + struct flowi6 *fl6, + const struct sk_buff *skb, + int flags) { if (rt6_need_strict(&fl6->daddr) && dev->type != ARPHRD_PIMREG) flags |= RT6_LOOKUP_F_IFACE; - return fib6_rule_lookup(net, fl6, flags, ip6_pol_route_input); + return fib6_rule_lookup(net, fl6, skb, flags, ip6_pol_route_input); } EXPORT_SYMBOL_GPL(ip6_route_input_lookup); static void ip6_multipath_l3_keys(const struct sk_buff *skb, - struct flow_keys *keys) + struct flow_keys *keys, + struct flow_keys *flkeys) { const struct ipv6hdr *outer_iph = ipv6_hdr(skb); const struct ipv6hdr *key_iph = outer_iph; + struct flow_keys *_flkeys = flkeys; const struct ipv6hdr *inner_iph; const struct icmp6hdr *icmph; struct ipv6hdr _inner_iph; @@ -1811,26 +1824,76 @@ static void ip6_multipath_l3_keys(const struct sk_buff *skb, goto out; key_iph = inner_iph; + _flkeys = NULL; out: - memset(keys, 0, sizeof(*keys)); - keys->control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; - keys->addrs.v6addrs.src = key_iph->saddr; - keys->addrs.v6addrs.dst = key_iph->daddr; - keys->tags.flow_label = ip6_flowinfo(key_iph); - keys->basic.ip_proto = key_iph->nexthdr; + if (_flkeys) { + keys->addrs.v6addrs.src = _flkeys->addrs.v6addrs.src; + keys->addrs.v6addrs.dst = _flkeys->addrs.v6addrs.dst; + keys->tags.flow_label = _flkeys->tags.flow_label; + keys->basic.ip_proto = _flkeys->basic.ip_proto; + } else { + keys->addrs.v6addrs.src = key_iph->saddr; + keys->addrs.v6addrs.dst = key_iph->daddr; + keys->tags.flow_label = ip6_flowinfo(key_iph); + keys->basic.ip_proto = key_iph->nexthdr; + } } /* if skb is set it will be used and fl6 can be NULL */ -u32 rt6_multipath_hash(const struct flowi6 *fl6, const struct sk_buff *skb) +u32 rt6_multipath_hash(const struct net *net, const struct flowi6 *fl6, + const struct sk_buff *skb, struct flow_keys *flkeys) { struct flow_keys hash_keys; + u32 mhash; - if (skb) { - ip6_multipath_l3_keys(skb, &hash_keys); - return flow_hash_from_keys(&hash_keys) >> 1; + switch (net->ipv6.sysctl.multipath_hash_policy) { + case 0: + memset(&hash_keys, 0, sizeof(hash_keys)); + hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; + if (skb) { + ip6_multipath_l3_keys(skb, &hash_keys, flkeys); + } else { + hash_keys.addrs.v6addrs.src = fl6->saddr; + hash_keys.addrs.v6addrs.dst = fl6->daddr; + hash_keys.tags.flow_label = (__force u32)fl6->flowlabel; + hash_keys.basic.ip_proto = fl6->flowi6_proto; + } + break; + case 1: + if (skb) { + unsigned int flag = FLOW_DISSECTOR_F_STOP_AT_ENCAP; + struct flow_keys keys; + + /* short-circuit if we already have L4 hash present */ + if (skb->l4_hash) + return skb_get_hash_raw(skb) >> 1; + + memset(&hash_keys, 0, sizeof(hash_keys)); + + if (!flkeys) { + skb_flow_dissect_flow_keys(skb, &keys, flag); + flkeys = &keys; + } + hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; + hash_keys.addrs.v6addrs.src = flkeys->addrs.v6addrs.src; + hash_keys.addrs.v6addrs.dst = flkeys->addrs.v6addrs.dst; + hash_keys.ports.src = flkeys->ports.src; + hash_keys.ports.dst = flkeys->ports.dst; + hash_keys.basic.ip_proto = flkeys->basic.ip_proto; + } else { + memset(&hash_keys, 0, sizeof(hash_keys)); + hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; + hash_keys.addrs.v6addrs.src = fl6->saddr; + hash_keys.addrs.v6addrs.dst = fl6->daddr; + hash_keys.ports.src = fl6->fl6_sport; + hash_keys.ports.dst = fl6->fl6_dport; + hash_keys.basic.ip_proto = fl6->flowi6_proto; + } + break; } + mhash = flow_hash_from_keys(&hash_keys); - return get_hash_from_flowi6(fl6) >> 1; + return mhash >> 1; } void ip6_route_input(struct sk_buff *skb) @@ -1847,20 +1910,29 @@ void ip6_route_input(struct sk_buff *skb) .flowi6_mark = skb->mark, .flowi6_proto = iph->nexthdr, }; + struct flow_keys *flkeys = NULL, _flkeys; tun_info = skb_tunnel_info(skb); if (tun_info && !(tun_info->mode & IP_TUNNEL_INFO_TX)) fl6.flowi6_tun_key.tun_id = tun_info->key.tun_id; + + if (fib6_rules_early_flow_dissect(net, skb, &fl6, &_flkeys)) + flkeys = &_flkeys; + if (unlikely(fl6.flowi6_proto == IPPROTO_ICMPV6)) - fl6.mp_hash = rt6_multipath_hash(&fl6, skb); + fl6.mp_hash = rt6_multipath_hash(net, &fl6, skb, flkeys); skb_dst_drop(skb); - skb_dst_set(skb, ip6_route_input_lookup(net, skb->dev, &fl6, flags)); + skb_dst_set(skb, + ip6_route_input_lookup(net, skb->dev, &fl6, skb, flags)); } -static struct rt6_info *ip6_pol_route_output(struct net *net, struct fib6_table *table, - struct flowi6 *fl6, int flags) +static struct rt6_info *ip6_pol_route_output(struct net *net, + struct fib6_table *table, + struct flowi6 *fl6, + const struct sk_buff *skb, + int flags) { - return ip6_pol_route(net, table, fl6->flowi6_oif, fl6, flags); + return ip6_pol_route(net, table, fl6->flowi6_oif, fl6, skb, flags); } struct dst_entry *ip6_route_output_flags(struct net *net, const struct sock *sk, @@ -1888,7 +1960,7 @@ struct dst_entry *ip6_route_output_flags(struct net *net, const struct sock *sk, else if (sk) flags |= rt6_srcprefs2flags(inet6_sk(sk)->srcprefs); - return fib6_rule_lookup(net, fl6, flags, ip6_pol_route_output); + return fib6_rule_lookup(net, fl6, NULL, flags, ip6_pol_route_output); } EXPORT_SYMBOL_GPL(ip6_route_output_flags); @@ -2137,6 +2209,7 @@ struct ip6rd_flowi { static struct rt6_info *__ip6_route_redirect(struct net *net, struct fib6_table *table, struct flowi6 *fl6, + const struct sk_buff *skb, int flags) { struct ip6rd_flowi *rdfl = (struct ip6rd_flowi *)fl6; @@ -2210,8 +2283,9 @@ out: }; static struct dst_entry *ip6_route_redirect(struct net *net, - const struct flowi6 *fl6, - const struct in6_addr *gateway) + const struct flowi6 *fl6, + const struct sk_buff *skb, + const struct in6_addr *gateway) { int flags = RT6_LOOKUP_F_HAS_SADDR; struct ip6rd_flowi rdfl; @@ -2219,7 +2293,7 @@ static struct dst_entry *ip6_route_redirect(struct net *net, rdfl.fl6 = *fl6; rdfl.gateway = *gateway; - return fib6_rule_lookup(net, &rdfl.fl6, + return fib6_rule_lookup(net, &rdfl.fl6, skb, flags, __ip6_route_redirect); } @@ -2239,7 +2313,7 @@ void ip6_redirect(struct sk_buff *skb, struct net *net, int oif, u32 mark, fl6.flowlabel = ip6_flowinfo(iph); fl6.flowi6_uid = uid; - dst = ip6_route_redirect(net, &fl6, &ipv6_hdr(skb)->saddr); + dst = ip6_route_redirect(net, &fl6, skb, &ipv6_hdr(skb)->saddr); rt6_do_redirect(dst, NULL, skb); dst_release(dst); } @@ -2261,7 +2335,7 @@ void ip6_redirect_no_header(struct sk_buff *skb, struct net *net, int oif, fl6.saddr = iph->daddr; fl6.flowi6_uid = sock_net_uid(net, NULL); - dst = ip6_route_redirect(net, &fl6, &iph->saddr); + dst = ip6_route_redirect(net, &fl6, skb, &iph->saddr); rt6_do_redirect(dst, NULL, skb); dst_release(dst); } @@ -2463,7 +2537,7 @@ static struct rt6_info *ip6_nh_lookup_table(struct net *net, flags |= RT6_LOOKUP_F_HAS_SADDR; flags |= RT6_LOOKUP_F_IGNORE_LINKSTATE; - rt = ip6_pol_route(net, table, cfg->fc_ifindex, &fl6, flags); + rt = ip6_pol_route(net, table, cfg->fc_ifindex, &fl6, NULL, flags); /* if table lookup failed, fall back to full lookup */ if (rt == net->ipv6.ip6_null_entry) { @@ -2526,7 +2600,7 @@ static int ip6_route_check_nh(struct net *net, } if (!grt) - grt = rt6_lookup(net, gw_addr, NULL, cfg->fc_ifindex, 1); + grt = rt6_lookup(net, gw_addr, NULL, cfg->fc_ifindex, NULL, 1); if (!grt) goto out; @@ -2671,14 +2745,7 @@ static struct rt6_info *ip6_route_info_create(struct fib6_config *cfg, if (err) goto out; rt->dst.lwtstate = lwtstate_get(lwtstate); - if (lwtunnel_output_redirect(rt->dst.lwtstate)) { - rt->dst.lwtstate->orig_output = rt->dst.output; - rt->dst.output = lwtunnel_output; - } - if (lwtunnel_input_redirect(rt->dst.lwtstate)) { - rt->dst.lwtstate->orig_input = rt->dst.input; - rt->dst.input = lwtunnel_input; - } + lwtunnel_set_redirect(&rt->dst); } ipv6_addr_prefix(&rt->rt6i_dst.addr, &cfg->fc_dst, cfg->fc_dst_len); @@ -4598,7 +4665,7 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, if (!ipv6_addr_any(&fl6.saddr)) flags |= RT6_LOOKUP_F_HAS_SADDR; - dst = ip6_route_input_lookup(net, dev, &fl6, flags); + dst = ip6_route_input_lookup(net, dev, &fl6, NULL, flags); rcu_read_unlock(); } else { @@ -4979,6 +5046,7 @@ static void __net_exit ip6_route_net_exit_late(struct net *net) static struct pernet_operations ip6_route_net_ops = { .init = ip6_route_net_init, .exit = ip6_route_net_exit, + .async = true, }; static int __net_init ipv6_inetpeer_init(struct net *net) @@ -5004,11 +5072,13 @@ static void __net_exit ipv6_inetpeer_exit(struct net *net) static struct pernet_operations ipv6_inetpeer_ops = { .init = ipv6_inetpeer_init, .exit = ipv6_inetpeer_exit, + .async = true, }; static struct pernet_operations ip6_route_net_late_ops = { .init = ip6_route_net_init_late, .exit = ip6_route_net_exit_late, + .async = true, }; static struct notifier_block ip6_route_dev_notifier = { diff --git a/net/ipv6/seg6.c b/net/ipv6/seg6.c index 7f5621d09571..c3f13c3bd8a9 100644 --- a/net/ipv6/seg6.c +++ b/net/ipv6/seg6.c @@ -395,6 +395,7 @@ static void __net_exit seg6_net_exit(struct net *net) static struct pernet_operations ip6_segments_ops = { .init = seg6_net_init, .exit = seg6_net_exit, + .async = true, }; static const struct genl_ops seg6_genl_ops[] = { diff --git a/net/ipv6/seg6_local.c b/net/ipv6/seg6_local.c index ba3767ef5e93..45722327375a 100644 --- a/net/ipv6/seg6_local.c +++ b/net/ipv6/seg6_local.c @@ -161,7 +161,7 @@ static void lookup_nexthop(struct sk_buff *skb, struct in6_addr *nhaddr, fl6.flowi6_flags = FLOWI_FLAG_KNOWN_NH; if (!tbl_id) { - dst = ip6_route_input_lookup(net, skb->dev, &fl6, flags); + dst = ip6_route_input_lookup(net, skb->dev, &fl6, skb, flags); } else { struct fib6_table *table; @@ -169,7 +169,7 @@ static void lookup_nexthop(struct sk_buff *skb, struct in6_addr *nhaddr, if (!table) goto out; - rt = ip6_pol_route(net, table, 0, &fl6, flags); + rt = ip6_pol_route(net, table, 0, &fl6, skb, flags); dst = &rt->dst; } diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 0195598f7bb5..a9c4ac6efe22 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -1885,6 +1885,7 @@ static struct pernet_operations sit_net_ops = { .exit_batch = sit_exit_batch_net, .id = &sit_net_id, .size = sizeof(struct sit_net), + .async = true, }; static void __exit sit_cleanup(void) diff --git a/net/ipv6/sysctl_net_ipv6.c b/net/ipv6/sysctl_net_ipv6.c index a789a8ac6a64..966c42af92f4 100644 --- a/net/ipv6/sysctl_net_ipv6.c +++ b/net/ipv6/sysctl_net_ipv6.c @@ -16,14 +16,31 @@ #include <net/ipv6.h> #include <net/addrconf.h> #include <net/inet_frag.h> +#include <net/netevent.h> #ifdef CONFIG_NETLABEL #include <net/calipso.h> #endif +static int zero; static int one = 1; static int auto_flowlabels_min; static int auto_flowlabels_max = IP6_AUTO_FLOW_LABEL_MAX; +static int proc_rt6_multipath_hash_policy(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, + loff_t *ppos) +{ + struct net *net; + int ret; + + net = container_of(table->data, struct net, + ipv6.sysctl.multipath_hash_policy); + ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); + if (write && ret == 0) + call_netevent_notifiers(NETEVENT_IPV6_MPATH_HASH_UPDATE, net); + + return ret; +} static struct ctl_table ipv6_table_template[] = { { @@ -126,6 +143,15 @@ static struct ctl_table ipv6_table_template[] = { .mode = 0644, .proc_handler = proc_dointvec }, + { + .procname = "fib_multipath_hash_policy", + .data = &init_net.ipv6.sysctl.multipath_hash_policy, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_rt6_multipath_hash_policy, + .extra1 = &zero, + .extra2 = &one, + }, { } }; @@ -190,6 +216,7 @@ static int __net_init ipv6_sysctl_net_init(struct net *net) ipv6_table[11].data = &net->ipv6.sysctl.max_hbh_opts_cnt; ipv6_table[12].data = &net->ipv6.sysctl.max_dst_opts_len; ipv6_table[13].data = &net->ipv6.sysctl.max_hbh_opts_len; + ipv6_table[14].data = &net->ipv6.sysctl.multipath_hash_policy, ipv6_route_table = ipv6_route_sysctl_init(net); if (!ipv6_route_table) @@ -251,6 +278,7 @@ static void __net_exit ipv6_sysctl_net_exit(struct net *net) static struct pernet_operations ipv6_sysctl_net_ops = { .init = ipv6_sysctl_net_init, .exit = ipv6_sysctl_net_exit, + .async = true, }; static struct ctl_table_header *ip6_header; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 412139f4eccd..5425d7b100ee 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1451,6 +1451,7 @@ process: if (sk->sk_state == TCP_NEW_SYN_RECV) { struct request_sock *req = inet_reqsk(sk); + bool req_stolen = false; struct sock *nsk; sk = req->rsk_listener; @@ -1470,10 +1471,20 @@ process: th = (const struct tcphdr *)skb->data; hdr = ipv6_hdr(skb); tcp_v6_fill_cb(skb, hdr, th); - nsk = tcp_check_req(sk, skb, req, false); + nsk = tcp_check_req(sk, skb, req, false, &req_stolen); } if (!nsk) { reqsk_put(req); + if (req_stolen) { + /* Another cpu got exclusive access to req + * and created a full blown socket. + * Try to feed this packet to this socket + * instead of discarding it. + */ + tcp_v6_restore_cb(skb); + sock_put(sk); + goto lookup; + } goto discard_and_relse; } if (nsk == sk) { @@ -1996,6 +2007,7 @@ static struct pernet_operations tcpv6_net_ops = { .init = tcpv6_net_init, .exit = tcpv6_net_exit, .exit_batch = tcpv6_net_exit_batch, + .async = true, }; int __init tcpv6_init(void) diff --git a/net/ipv6/udplite.c b/net/ipv6/udplite.c index 14ae32bb1f3d..f3839780dc31 100644 --- a/net/ipv6/udplite.c +++ b/net/ipv6/udplite.c @@ -123,6 +123,7 @@ static void __net_exit udplite6_proc_exit_net(struct net *net) static struct pernet_operations udplite6_net_ops = { .init = udplite6_proc_init_net, .exit = udplite6_proc_exit_net, + .async = true, }; int __init udplite6_proc_init(void) diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index 09fb44ee3b45..88cd0c90fa81 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -395,6 +395,7 @@ static void __net_exit xfrm6_net_exit(struct net *net) static struct pernet_operations xfrm6_net_ops = { .init = xfrm6_net_init, .exit = xfrm6_net_exit, + .async = true, }; int __init xfrm6_init(void) diff --git a/net/ipv6/xfrm6_state.c b/net/ipv6/xfrm6_state.c index b15075a5c227..16f434791763 100644 --- a/net/ipv6/xfrm6_state.c +++ b/net/ipv6/xfrm6_state.c @@ -196,4 +196,3 @@ void xfrm6_state_fini(void) { xfrm_state_unregister_afinfo(&xfrm6_state_afinfo); } - diff --git a/net/ipv6/xfrm6_tunnel.c b/net/ipv6/xfrm6_tunnel.c index f85f0d7480ac..a9673619e0e9 100644 --- a/net/ipv6/xfrm6_tunnel.c +++ b/net/ipv6/xfrm6_tunnel.c @@ -353,6 +353,7 @@ static struct pernet_operations xfrm6_tunnel_net_ops = { .exit = xfrm6_tunnel_net_exit, .id = &xfrm6_tunnel_net_id, .size = sizeof(struct xfrm6_tunnel_net), + .async = true, }; static int __init xfrm6_tunnel_init(void) diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index 1e8cc7bcbca3..81ce15ffb878 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -989,14 +989,13 @@ done: } static int iucv_sock_getname(struct socket *sock, struct sockaddr *addr, - int *len, int peer) + int peer) { struct sockaddr_iucv *siucv = (struct sockaddr_iucv *) addr; struct sock *sk = sock->sk; struct iucv_sock *iucv = iucv_sk(sk); addr->sa_family = AF_IUCV; - *len = sizeof(struct sockaddr_iucv); if (peer) { memcpy(siucv->siucv_user_id, iucv->dst_user_id, 8); @@ -1009,7 +1008,7 @@ static int iucv_sock_getname(struct socket *sock, struct sockaddr *addr, memset(&siucv->siucv_addr, 0, sizeof(siucv->siucv_addr)); memset(&siucv->siucv_nodeid, 0, sizeof(siucv->siucv_nodeid)); - return 0; + return sizeof(struct sockaddr_iucv); } /** diff --git a/net/kcm/kcmproc.c b/net/kcm/kcmproc.c index 9d5649e4e8b7..2c1c8b3e4452 100644 --- a/net/kcm/kcmproc.c +++ b/net/kcm/kcmproc.c @@ -433,6 +433,7 @@ static void kcm_proc_exit_net(struct net *net) static struct pernet_operations kcm_net_ops = { .init = kcm_proc_init_net, .exit = kcm_proc_exit_net, + .async = true, }; int __init kcm_proc_init(void) diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c index f297d53a11aa..a6cd0712e063 100644 --- a/net/kcm/kcmsock.c +++ b/net/kcm/kcmsock.c @@ -1417,6 +1417,7 @@ static int kcm_attach(struct socket *sock, struct socket *csock, */ if (csk->sk_user_data) { write_unlock_bh(&csk->sk_callback_lock); + strp_stop(&psock->strp); strp_done(&psock->strp); kmem_cache_free(kcm_psockp, psock); return -EALREADY; @@ -2014,6 +2015,7 @@ static struct pernet_operations kcm_net_ops = { .exit = kcm_exit_net, .id = &kcm_net_id, .size = sizeof(struct kcm_net), + .async = true, }; static int __init kcm_init(void) diff --git a/net/key/af_key.c b/net/key/af_key.c index 7e2e7188e7f4..3ac08ab26207 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -3863,6 +3863,7 @@ static struct pernet_operations pfkey_net_ops = { .exit = pfkey_net_exit, .id = &pfkey_net_id, .size = sizeof(struct netns_pfkey), + .async = true, }; static void __exit ipsec_pfkey_exit(void) diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c index 3428fba6f2b7..a9c05b2bc1b0 100644 --- a/net/l2tp/l2tp_ip.c +++ b/net/l2tp/l2tp_ip.c @@ -345,7 +345,7 @@ static int l2tp_ip_disconnect(struct sock *sk, int flags) } static int l2tp_ip_getname(struct socket *sock, struct sockaddr *uaddr, - int *uaddr_len, int peer) + int peer) { struct sock *sk = sock->sk; struct inet_sock *inet = inet_sk(sk); @@ -366,8 +366,7 @@ static int l2tp_ip_getname(struct socket *sock, struct sockaddr *uaddr, lsa->l2tp_conn_id = lsk->conn_id; lsa->l2tp_addr.s_addr = addr; } - *uaddr_len = sizeof(*lsa); - return 0; + return sizeof(*lsa); } static int l2tp_ip_backlog_recv(struct sock *sk, struct sk_buff *skb) diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c index 6f009eaa5fbe..957369192ca1 100644 --- a/net/l2tp/l2tp_ip6.c +++ b/net/l2tp/l2tp_ip6.c @@ -419,7 +419,7 @@ static int l2tp_ip6_disconnect(struct sock *sk, int flags) } static int l2tp_ip6_getname(struct socket *sock, struct sockaddr *uaddr, - int *uaddr_len, int peer) + int peer) { struct sockaddr_l2tpip6 *lsa = (struct sockaddr_l2tpip6 *)uaddr; struct sock *sk = sock->sk; @@ -447,8 +447,7 @@ static int l2tp_ip6_getname(struct socket *sock, struct sockaddr *uaddr, } if (ipv6_addr_type(&lsa->l2tp_addr) & IPV6_ADDR_LINKLOCAL) lsa->l2tp_scope_id = sk->sk_bound_dev_if; - *uaddr_len = sizeof(*lsa); - return 0; + return sizeof(*lsa); } static int l2tp_ip6_backlog_recv(struct sock *sk, struct sk_buff *skb) diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c index 3b02f24ea9ec..977bca659787 100644 --- a/net/l2tp/l2tp_ppp.c +++ b/net/l2tp/l2tp_ppp.c @@ -862,7 +862,7 @@ err: /* getname() support. */ static int pppol2tp_getname(struct socket *sock, struct sockaddr *uaddr, - int *usockaddr_len, int peer) + int peer) { int len = 0; int error = 0; @@ -961,8 +961,7 @@ static int pppol2tp_getname(struct socket *sock, struct sockaddr *uaddr, memcpy(uaddr, &sp, len); } - *usockaddr_len = len; - error = 0; + error = len; sock_put(sk); end: @@ -1763,6 +1762,7 @@ static struct pernet_operations pppol2tp_net_ops = { .init = pppol2tp_init_net, .exit = pppol2tp_exit_net, .id = &pppol2tp_net_id, + .async = true, }; /***************************************************************************** diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c index c38d16f22d2a..01dcc0823d1f 100644 --- a/net/llc/af_llc.c +++ b/net/llc/af_llc.c @@ -971,7 +971,7 @@ release: * Return the address information of a socket. */ static int llc_ui_getname(struct socket *sock, struct sockaddr *uaddr, - int *uaddrlen, int peer) + int peer) { struct sockaddr_llc sllc; struct sock *sk = sock->sk; @@ -982,7 +982,6 @@ static int llc_ui_getname(struct socket *sock, struct sockaddr *uaddr, lock_sock(sk); if (sock_flag(sk, SOCK_ZAPPED)) goto out; - *uaddrlen = sizeof(sllc); if (peer) { rc = -ENOTCONN; if (sk->sk_state != TCP_ESTABLISHED) @@ -1003,9 +1002,9 @@ static int llc_ui_getname(struct socket *sock, struct sockaddr *uaddr, IFHWADDRLEN); } } - rc = 0; sllc.sllc_family = AF_LLC; memcpy(uaddr, &sllc, sizeof(sllc)); + rc = sizeof(sllc); out: release_sock(sk); return rc; diff --git a/net/mac80211/agg-rx.c b/net/mac80211/agg-rx.c index 1f3188d03840..e83c19d4c292 100644 --- a/net/mac80211/agg-rx.c +++ b/net/mac80211/agg-rx.c @@ -298,13 +298,23 @@ void ___ieee80211_start_rx_ba_session(struct sta_info *sta, if (test_bit(tid, sta->ampdu_mlme.agg_session_valid)) { if (sta->ampdu_mlme.tid_rx_token[tid] == dialog_token) { + struct tid_ampdu_rx *tid_rx; + ht_dbg_ratelimited(sta->sdata, "updated AddBA Req from %pM on tid %u\n", sta->sta.addr, tid); /* We have no API to update the timeout value in the - * driver so reject the timeout update. + * driver so reject the timeout update if the timeout + * changed. If if did not change, i.e., no real update, + * just reply with success. */ - status = WLAN_STATUS_REQUEST_DECLINED; + rcu_read_lock(); + tid_rx = rcu_dereference(sta->ampdu_mlme.tid_rx[tid]); + if (tid_rx && tid_rx->timeout == timeout) + status = WLAN_STATUS_SUCCESS; + else + status = WLAN_STATUS_REQUEST_DECLINED; + rcu_read_unlock(); goto end; } diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index f4195a0f0279..fd68f6fb02d7 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -2685,6 +2685,7 @@ static int ieee80211_set_power_mgmt(struct wiphy *wiphy, struct net_device *dev, ieee80211_recalc_ps(local); ieee80211_recalc_ps_vif(sdata); + ieee80211_check_fast_rx_iface(sdata); return 0; } diff --git a/net/mac80211/debugfs.c b/net/mac80211/debugfs.c index 1f466d12a6bc..a75653affbf7 100644 --- a/net/mac80211/debugfs.c +++ b/net/mac80211/debugfs.c @@ -212,6 +212,7 @@ static const char *hw_flag_names[] = { FLAG(REPORTS_LOW_ACK), FLAG(SUPPORTS_TX_FRAG), FLAG(SUPPORTS_TDLS_BUFFER_STA), + FLAG(DEAUTH_NEED_MGD_TX_PREP), #undef FLAG }; diff --git a/net/mac80211/debugfs_sta.c b/net/mac80211/debugfs_sta.c index 444ea8d127fe..4105081dc1df 100644 --- a/net/mac80211/debugfs_sta.c +++ b/net/mac80211/debugfs_sta.c @@ -160,12 +160,12 @@ static ssize_t sta_aqm_read(struct file *file, char __user *userbuf, sta->cparams.ecn ? "yes" : "no"); p += scnprintf(p, bufsz+buf-p, - "tid ac backlog-bytes backlog-packets new-flows drops marks overlimit collisions tx-bytes tx-packets\n"); + "tid ac backlog-bytes backlog-packets new-flows drops marks overlimit collisions tx-bytes tx-packets flags\n"); for (i = 0; i < IEEE80211_NUM_TIDS; i++) { txqi = to_txq_info(sta->sta.txq[i]); p += scnprintf(p, bufsz+buf-p, - "%d %d %u %u %u %u %u %u %u %u %u\n", + "%d %d %u %u %u %u %u %u %u %u %u 0x%lx(%s%s%s)\n", txqi->txq.tid, txqi->txq.ac, txqi->tin.backlog_bytes, @@ -176,7 +176,11 @@ static ssize_t sta_aqm_read(struct file *file, char __user *userbuf, txqi->tin.overlimit, txqi->tin.collisions, txqi->tin.tx_bytes, - txqi->tin.tx_packets); + txqi->tin.tx_packets, + txqi->flags, + txqi->flags & (1<<IEEE80211_TXQ_STOP) ? "STOP" : "RUN", + txqi->flags & (1<<IEEE80211_TXQ_AMPDU) ? " AMPDU" : "", + txqi->flags & (1<<IEEE80211_TXQ_NO_AMSDU) ? " NO-AMSDU" : ""); } rcu_read_unlock(); diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index 5fe01f82df12..d13ba064951f 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -1324,8 +1324,7 @@ static void ieee80211_iface_work(struct work_struct *work) mutex_lock(&local->sta_mtx); sta = sta_info_get_bss(sdata, mgmt->sa); if (sta) { - u16 tid = *ieee80211_get_qos_ctl(hdr) & - IEEE80211_QOS_CTL_TID_MASK; + u16 tid = ieee80211_get_tid(hdr); __ieee80211_stop_rx_ba_session( sta, tid, WLAN_BACK_RECIPIENT, diff --git a/net/mac80211/michael.c b/net/mac80211/michael.c index 408649bd4702..37e172701a63 100644 --- a/net/mac80211/michael.c +++ b/net/mac80211/michael.c @@ -35,7 +35,7 @@ static void michael_mic_hdr(struct michael_mic_ctx *mctx, const u8 *key, da = ieee80211_get_DA(hdr); sa = ieee80211_get_SA(hdr); if (ieee80211_is_data_qos(hdr->frame_control)) - tid = *ieee80211_get_qos_ctl(hdr) & IEEE80211_QOS_CTL_TID_MASK; + tid = ieee80211_get_tid(hdr); else tid = 0; diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 39b660b9a908..0024eff9bb84 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -7,6 +7,7 @@ * Copyright 2007, Michael Wu <flamingice@sourmilk.net> * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright (C) 2015 - 2017 Intel Deutschland GmbH + * Copyright (C) 2018 Intel Corporation * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -2008,9 +2009,22 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata, ieee80211_flush_queues(local, sdata, true); /* deauthenticate/disassociate now */ - if (tx || frame_buf) + if (tx || frame_buf) { + struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; + + /* + * In multi channel scenarios guarantee that the virtual + * interface is granted immediate airtime to transmit the + * deauthentication frame by calling mgd_prepare_tx, if the + * driver requested so. + */ + if (ieee80211_hw_check(&local->hw, DEAUTH_NEED_MGD_TX_PREP) && + !ifmgd->have_beacon) + drv_mgd_prepare_tx(sdata->local, sdata); + ieee80211_send_deauth_disassoc(sdata, ifmgd->bssid, stype, reason, tx, frame_buf); + } /* flush out frame - make sure the deauth was actually sent */ if (tx) @@ -2151,7 +2165,7 @@ static void ieee80211_sta_tx_wmm_ac_notify(struct ieee80211_sub_if_data *sdata, u16 tx_time) { struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; - u16 tid = *ieee80211_get_qos_ctl(hdr) & IEEE80211_QOS_CTL_TID_MASK; + u16 tid = ieee80211_get_tid(hdr); int ac = ieee80211_ac_from_tid(tid); struct ieee80211_sta_tx_tspec *tx_tspec = &ifmgd->tx_tspec[ac]; unsigned long now = jiffies; diff --git a/net/mac80211/rc80211_minstrel_ht.c b/net/mac80211/rc80211_minstrel_ht.c index 4a5bdad9f303..fb586b6e5d49 100644 --- a/net/mac80211/rc80211_minstrel_ht.c +++ b/net/mac80211/rc80211_minstrel_ht.c @@ -669,7 +669,7 @@ minstrel_aggr_check(struct ieee80211_sta *pubsta, struct sk_buff *skb) if (unlikely(skb->protocol == cpu_to_be16(ETH_P_PAE))) return; - tid = *ieee80211_get_qos_ctl(hdr) & IEEE80211_QOS_CTL_TID_MASK; + tid = ieee80211_get_tid(hdr); if (likely(sta->ampdu_mlme.tid_tx[tid])) return; diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 56fe16b07538..d01743234cf6 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -439,6 +439,10 @@ ieee80211_add_rx_radiotap_header(struct ieee80211_local *local, flags |= IEEE80211_RADIOTAP_AMPDU_DELIM_CRC_ERR; if (status->flag & RX_FLAG_AMPDU_DELIM_CRC_KNOWN) flags |= IEEE80211_RADIOTAP_AMPDU_DELIM_CRC_KNOWN; + if (status->flag & RX_FLAG_AMPDU_EOF_BIT_KNOWN) + flags |= IEEE80211_RADIOTAP_AMPDU_EOF_KNOWN; + if (status->flag & RX_FLAG_AMPDU_EOF_BIT) + flags |= IEEE80211_RADIOTAP_AMPDU_EOF; put_unaligned_le16(flags, pos); pos += 2; if (status->flag & RX_FLAG_AMPDU_DELIM_CRC_KNOWN) @@ -1185,7 +1189,7 @@ static void ieee80211_rx_reorder_ampdu(struct ieee80211_rx_data *rx, ack_policy = *ieee80211_get_qos_ctl(hdr) & IEEE80211_QOS_CTL_ACK_POLICY_MASK; - tid = *ieee80211_get_qos_ctl(hdr) & IEEE80211_QOS_CTL_TID_MASK; + tid = ieee80211_get_tid(hdr); tid_agg_rx = rcu_dereference(sta->ampdu_mlme.tid_rx[tid]); if (!tid_agg_rx) { @@ -1524,9 +1528,7 @@ ieee80211_rx_h_uapsd_and_pspoll(struct ieee80211_rx_data *rx) ieee80211_has_pm(hdr->frame_control) && (ieee80211_is_data_qos(hdr->frame_control) || ieee80211_is_qos_nullfunc(hdr->frame_control))) { - u8 tid; - - tid = *ieee80211_get_qos_ctl(hdr) & IEEE80211_QOS_CTL_TID_MASK; + u8 tid = ieee80211_get_tid(hdr); ieee80211_sta_uapsd_trigger(&rx->sta->sta, tid); } @@ -2351,39 +2353,17 @@ ieee80211_deliver_skb(struct ieee80211_rx_data *rx) } static ieee80211_rx_result debug_noinline -ieee80211_rx_h_amsdu(struct ieee80211_rx_data *rx) +__ieee80211_rx_h_amsdu(struct ieee80211_rx_data *rx, u8 data_offset) { struct net_device *dev = rx->sdata->dev; struct sk_buff *skb = rx->skb; struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data; __le16 fc = hdr->frame_control; struct sk_buff_head frame_list; - struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(rx->skb); struct ethhdr ethhdr; const u8 *check_da = ethhdr.h_dest, *check_sa = ethhdr.h_source; - if (unlikely(!ieee80211_is_data(fc))) - return RX_CONTINUE; - - if (unlikely(!ieee80211_is_data_present(fc))) - return RX_DROP_MONITOR; - - if (!(status->rx_flags & IEEE80211_RX_AMSDU)) - return RX_CONTINUE; - if (unlikely(ieee80211_has_a4(hdr->frame_control))) { - switch (rx->sdata->vif.type) { - case NL80211_IFTYPE_AP_VLAN: - if (!rx->sdata->u.vlan.sta) - return RX_DROP_UNUSABLE; - break; - case NL80211_IFTYPE_STATION: - if (!rx->sdata->u.mgd.use_4addr) - return RX_DROP_UNUSABLE; - break; - default: - return RX_DROP_UNUSABLE; - } check_da = NULL; check_sa = NULL; } else switch (rx->sdata->vif.type) { @@ -2403,15 +2383,13 @@ ieee80211_rx_h_amsdu(struct ieee80211_rx_data *rx) break; } - if (is_multicast_ether_addr(hdr->addr1)) - return RX_DROP_UNUSABLE; - skb->dev = dev; __skb_queue_head_init(&frame_list); if (ieee80211_data_to_8023_exthdr(skb, ðhdr, rx->sdata->vif.addr, - rx->sdata->vif.type)) + rx->sdata->vif.type, + data_offset)) return RX_DROP_UNUSABLE; ieee80211_amsdu_to_8023s(skb, &frame_list, dev->dev_addr, @@ -2433,6 +2411,44 @@ ieee80211_rx_h_amsdu(struct ieee80211_rx_data *rx) return RX_QUEUED; } +static ieee80211_rx_result debug_noinline +ieee80211_rx_h_amsdu(struct ieee80211_rx_data *rx) +{ + struct sk_buff *skb = rx->skb; + struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb); + struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data; + __le16 fc = hdr->frame_control; + + if (!(status->rx_flags & IEEE80211_RX_AMSDU)) + return RX_CONTINUE; + + if (unlikely(!ieee80211_is_data(fc))) + return RX_CONTINUE; + + if (unlikely(!ieee80211_is_data_present(fc))) + return RX_DROP_MONITOR; + + if (unlikely(ieee80211_has_a4(hdr->frame_control))) { + switch (rx->sdata->vif.type) { + case NL80211_IFTYPE_AP_VLAN: + if (!rx->sdata->u.vlan.sta) + return RX_DROP_UNUSABLE; + break; + case NL80211_IFTYPE_STATION: + if (!rx->sdata->u.mgd.use_4addr) + return RX_DROP_UNUSABLE; + break; + default: + return RX_DROP_UNUSABLE; + } + } + + if (is_multicast_ether_addr(hdr->addr1)) + return RX_DROP_UNUSABLE; + + return __ieee80211_rx_h_amsdu(rx, 0); +} + #ifdef CONFIG_MAC80211_MESH static ieee80211_rx_result ieee80211_rx_h_mesh_fwding(struct ieee80211_rx_data *rx) @@ -2848,6 +2864,7 @@ ieee80211_rx_h_action(struct ieee80211_rx_data *rx) case WLAN_HT_ACTION_SMPS: { struct ieee80211_supported_band *sband; enum ieee80211_smps_mode smps_mode; + struct sta_opmode_info sta_opmode = {}; /* convert to HT capability */ switch (mgmt->u.action.u.ht_smps.smps_control) { @@ -2868,17 +2885,24 @@ ieee80211_rx_h_action(struct ieee80211_rx_data *rx) if (rx->sta->sta.smps_mode == smps_mode) goto handled; rx->sta->sta.smps_mode = smps_mode; + sta_opmode.smps_mode = smps_mode; + sta_opmode.changed = STA_OPMODE_SMPS_MODE_CHANGED; sband = rx->local->hw.wiphy->bands[status->band]; rate_control_rate_update(local, sband, rx->sta, IEEE80211_RC_SMPS_CHANGED); + cfg80211_sta_opmode_change_notify(sdata->dev, + rx->sta->addr, + &sta_opmode, + GFP_KERNEL); goto handled; } case WLAN_HT_ACTION_NOTIFY_CHANWIDTH: { struct ieee80211_supported_band *sband; u8 chanwidth = mgmt->u.action.u.ht_notify_cw.chanwidth; enum ieee80211_sta_rx_bandwidth max_bw, new_bw; + struct sta_opmode_info sta_opmode = {}; /* If it doesn't support 40 MHz it can't change ... */ if (!(rx->sta->sta.ht_cap.cap & @@ -2899,9 +2923,15 @@ ieee80211_rx_h_action(struct ieee80211_rx_data *rx) rx->sta->sta.bandwidth = new_bw; sband = rx->local->hw.wiphy->bands[status->band]; + sta_opmode.bw = new_bw; + sta_opmode.changed = STA_OPMODE_MAX_BW_CHANGED; rate_control_rate_update(local, sband, rx->sta, IEEE80211_RC_BW_CHANGED); + cfg80211_sta_opmode_change_notify(sdata->dev, + rx->sta->addr, + &sta_opmode, + GFP_KERNEL); goto handled; } default: @@ -3731,15 +3761,6 @@ void ieee80211_check_fast_rx(struct sta_info *sta) switch (sdata->vif.type) { case NL80211_IFTYPE_STATION: - /* 4-addr is harder to deal with, later maybe */ - if (sdata->u.mgd.use_4addr) - goto clear; - /* software powersave is a huge mess, avoid all of it */ - if (ieee80211_hw_check(&local->hw, PS_NULLFUNC_STACK)) - goto clear; - if (ieee80211_hw_check(&local->hw, SUPPORTS_PS) && - !ieee80211_hw_check(&local->hw, SUPPORTS_DYNAMIC_PS)) - goto clear; if (sta->sta.tdls) { fastrx.da_offs = offsetof(struct ieee80211_hdr, addr1); fastrx.sa_offs = offsetof(struct ieee80211_hdr, addr2); @@ -3751,6 +3772,23 @@ void ieee80211_check_fast_rx(struct sta_info *sta) fastrx.expected_ds_bits = cpu_to_le16(IEEE80211_FCTL_FROMDS); } + + if (sdata->u.mgd.use_4addr && !sta->sta.tdls) { + fastrx.expected_ds_bits |= + cpu_to_le16(IEEE80211_FCTL_TODS); + fastrx.da_offs = offsetof(struct ieee80211_hdr, addr3); + fastrx.sa_offs = offsetof(struct ieee80211_hdr, addr4); + } + + if (!sdata->u.mgd.powersave) + break; + + /* software powersave is a huge mess, avoid all of it */ + if (ieee80211_hw_check(&local->hw, PS_NULLFUNC_STACK)) + goto clear; + if (ieee80211_hw_check(&local->hw, SUPPORTS_PS) && + !ieee80211_hw_check(&local->hw, SUPPORTS_DYNAMIC_PS)) + goto clear; break; case NL80211_IFTYPE_AP_VLAN: case NL80211_IFTYPE_AP: @@ -3767,6 +3805,15 @@ void ieee80211_check_fast_rx(struct sta_info *sta) !(sdata->flags & IEEE80211_SDATA_DONT_BRIDGE_PACKETS) && (sdata->vif.type != NL80211_IFTYPE_AP_VLAN || !sdata->u.vlan.sta); + + if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN && + sdata->u.vlan.sta) { + fastrx.expected_ds_bits |= + cpu_to_le16(IEEE80211_FCTL_FROMDS); + fastrx.sa_offs = offsetof(struct ieee80211_hdr, addr4); + fastrx.internal_forward = 0; + } + break; default: goto clear; @@ -3865,7 +3912,8 @@ static bool ieee80211_invoke_fast_rx(struct ieee80211_rx_data *rx, struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb); struct sta_info *sta = rx->sta; int orig_len = skb->len; - int snap_offs = ieee80211_hdrlen(hdr->frame_control); + int hdrlen = ieee80211_hdrlen(hdr->frame_control); + int snap_offs = hdrlen; struct { u8 snap[sizeof(rfc1042_header)]; __be16 proto; @@ -3896,10 +3944,6 @@ static bool ieee80211_invoke_fast_rx(struct ieee80211_rx_data *rx, (status->flag & FAST_RX_CRYPT_FLAGS) != FAST_RX_CRYPT_FLAGS) return false; - /* we don't deal with A-MSDU deaggregation here */ - if (status->rx_flags & IEEE80211_RX_AMSDU) - return false; - if (unlikely(!ieee80211_is_data_present(hdr->frame_control))) return false; @@ -3931,21 +3975,24 @@ static bool ieee80211_invoke_fast_rx(struct ieee80211_rx_data *rx, snap_offs += IEEE80211_CCMP_HDR_LEN; } - if (!pskb_may_pull(skb, snap_offs + sizeof(*payload))) - goto drop; - payload = (void *)(skb->data + snap_offs); + if (!(status->rx_flags & IEEE80211_RX_AMSDU)) { + if (!pskb_may_pull(skb, snap_offs + sizeof(*payload))) + goto drop; - if (!ether_addr_equal(payload->snap, fast_rx->rfc1042_hdr)) - return false; + payload = (void *)(skb->data + snap_offs); - /* Don't handle these here since they require special code. - * Accept AARP and IPX even though they should come with a - * bridge-tunnel header - but if we get them this way then - * there's little point in discarding them. - */ - if (unlikely(payload->proto == cpu_to_be16(ETH_P_TDLS) || - payload->proto == fast_rx->control_port_protocol)) - return false; + if (!ether_addr_equal(payload->snap, fast_rx->rfc1042_hdr)) + return false; + + /* Don't handle these here since they require special code. + * Accept AARP and IPX even though they should come with a + * bridge-tunnel header - but if we get them this way then + * there's little point in discarding them. + */ + if (unlikely(payload->proto == cpu_to_be16(ETH_P_TDLS) || + payload->proto == fast_rx->control_port_protocol)) + return false; + } /* after this point, don't punt to the slowpath! */ @@ -3959,12 +4006,6 @@ static bool ieee80211_invoke_fast_rx(struct ieee80211_rx_data *rx, } /* statistics part of ieee80211_rx_h_sta_process() */ - stats->last_rx = jiffies; - stats->last_rate = sta_stats_encode_rate(status); - - stats->fragments++; - stats->packets++; - if (!(status->flag & RX_FLAG_NO_SIGNAL_VAL)) { stats->last_signal = status->signal; if (!fast_rx->uses_rss) @@ -3993,6 +4034,20 @@ static bool ieee80211_invoke_fast_rx(struct ieee80211_rx_data *rx, if (rx->key && !ieee80211_has_protected(hdr->frame_control)) goto drop; + if (status->rx_flags & IEEE80211_RX_AMSDU) { + if (__ieee80211_rx_h_amsdu(rx, snap_offs - hdrlen) != + RX_QUEUED) + goto drop; + + return true; + } + + stats->last_rx = jiffies; + stats->last_rate = sta_stats_encode_rate(status); + + stats->fragments++; + stats->packets++; + /* do the header conversion - first grab the addresses */ ether_addr_copy(addrs.da, skb->data + fast_rx->da_offs); ether_addr_copy(addrs.sa, skb->data + fast_rx->sa_offs); diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index af0b608ee8ed..655c3d8b0d80 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -2288,6 +2288,12 @@ void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo) sinfo->filled |= BIT(NL80211_STA_INFO_EXPECTED_THROUGHPUT); sinfo->expected_throughput = thr; } + + if (!(sinfo->filled & BIT_ULL(NL80211_STA_INFO_ACK_SIGNAL)) && + sta->status_stats.ack_signal_filled) { + sinfo->ack_signal = sta->status_stats.last_ack_signal; + sinfo->filled |= BIT_ULL(NL80211_STA_INFO_ACK_SIGNAL); + } } u32 sta_get_expected_throughput(struct sta_info *sta) diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h index cd53619435b6..f64eb86ca64b 100644 --- a/net/mac80211/sta_info.h +++ b/net/mac80211/sta_info.h @@ -548,6 +548,8 @@ struct sta_info { u64 msdu_retries[IEEE80211_NUM_TIDS + 1]; u64 msdu_failed[IEEE80211_NUM_TIDS + 1]; unsigned long last_ack; + s8 last_ack_signal; + bool ack_signal_filled; } status_stats; /* Updated from TX path only, no locking requirements */ diff --git a/net/mac80211/status.c b/net/mac80211/status.c index da7427a41529..743e89c5926c 100644 --- a/net/mac80211/status.c +++ b/net/mac80211/status.c @@ -187,9 +187,16 @@ static void ieee80211_frame_acked(struct sta_info *sta, struct sk_buff *skb) struct ieee80211_mgmt *mgmt = (void *) skb->data; struct ieee80211_local *local = sta->local; struct ieee80211_sub_if_data *sdata = sta->sdata; + struct ieee80211_tx_info *txinfo = IEEE80211_SKB_CB(skb); - if (ieee80211_hw_check(&local->hw, REPORTS_TX_ACK_STATUS)) + if (ieee80211_hw_check(&local->hw, REPORTS_TX_ACK_STATUS)) { sta->status_stats.last_ack = jiffies; + if (txinfo->status.is_valid_ack_signal) { + sta->status_stats.last_ack_signal = + (s8)txinfo->status.ack_signal; + sta->status_stats.ack_signal_filled = true; + } + } if (ieee80211_is_data_qos(mgmt->frame_control)) { struct ieee80211_hdr *hdr = (void *) skb->data; @@ -487,6 +494,8 @@ static void ieee80211_report_ack_skb(struct ieee80211_local *local, ieee80211_is_qos_nullfunc(hdr->frame_control)) cfg80211_probe_status(sdata->dev, hdr->addr1, cookie, acked, + info->status.ack_signal, + info->status.is_valid_ack_signal, GFP_ATOMIC); else cfg80211_mgmt_tx_status(&sdata->wdev, cookie, diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 69722504e3e1..933c67b5f845 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -797,7 +797,6 @@ ieee80211_tx_h_sequence(struct ieee80211_tx_data *tx) { struct ieee80211_tx_info *info = IEEE80211_SKB_CB(tx->skb); struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)tx->skb->data; - u8 *qc; int tid; /* @@ -844,9 +843,7 @@ ieee80211_tx_h_sequence(struct ieee80211_tx_data *tx) return TX_CONTINUE; /* include per-STA, per-TID sequence counter */ - - qc = ieee80211_get_qos_ctl(hdr); - tid = *qc & IEEE80211_QOS_CTL_TID_MASK; + tid = ieee80211_get_tid(hdr); tx->sta->tx_stats.msdu[tid]++; hdr->seq_ctrl = ieee80211_tx_next_seq(tx->sta, tid); @@ -1158,7 +1155,6 @@ ieee80211_tx_prepare(struct ieee80211_sub_if_data *sdata, struct ieee80211_hdr *hdr; struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); int tid; - u8 *qc; memset(tx, 0, sizeof(*tx)); tx->skb = skb; @@ -1198,8 +1194,7 @@ ieee80211_tx_prepare(struct ieee80211_sub_if_data *sdata, !ieee80211_hw_check(&local->hw, TX_AMPDU_SETUP_IN_HW)) { struct tid_ampdu_tx *tid_tx; - qc = ieee80211_get_qos_ctl(hdr); - tid = *qc & IEEE80211_QOS_CTL_TID_MASK; + tid = ieee80211_get_tid(hdr); tid_tx = rcu_dereference(tx->sta->ampdu_mlme.tid_tx[tid]); if (tid_tx) { @@ -1921,7 +1916,7 @@ void ieee80211_xmit(struct ieee80211_sub_if_data *sdata, { struct ieee80211_local *local = sdata->local; struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); - struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data; + struct ieee80211_hdr *hdr; int headroom; bool may_encrypt; diff --git a/net/mac80211/vht.c b/net/mac80211/vht.c index b9276ac849fa..5714dee76b12 100644 --- a/net/mac80211/vht.c +++ b/net/mac80211/vht.c @@ -447,6 +447,7 @@ u32 __ieee80211_vht_handle_opmode(struct ieee80211_sub_if_data *sdata, enum nl80211_band band) { enum ieee80211_sta_rx_bandwidth new_bw; + struct sta_opmode_info sta_opmode = {}; u32 changed = 0; u8 nss; @@ -460,7 +461,9 @@ u32 __ieee80211_vht_handle_opmode(struct ieee80211_sub_if_data *sdata, if (sta->sta.rx_nss != nss) { sta->sta.rx_nss = nss; + sta_opmode.rx_nss = nss; changed |= IEEE80211_RC_NSS_CHANGED; + sta_opmode.changed |= STA_OPMODE_N_SS_CHANGED; } switch (opmode & IEEE80211_OPMODE_NOTIF_CHANWIDTH_MASK) { @@ -481,9 +484,15 @@ u32 __ieee80211_vht_handle_opmode(struct ieee80211_sub_if_data *sdata, new_bw = ieee80211_sta_cur_vht_bw(sta); if (new_bw != sta->sta.bandwidth) { sta->sta.bandwidth = new_bw; + sta_opmode.bw = new_bw; changed |= IEEE80211_RC_BW_CHANGED; + sta_opmode.changed |= STA_OPMODE_MAX_BW_CHANGED; } + if (sta_opmode.changed) + cfg80211_sta_opmode_change_notify(sdata->dev, sta->addr, + &sta_opmode, GFP_KERNEL); + return changed; } diff --git a/net/mac80211/wpa.c b/net/mac80211/wpa.c index 785056cb76f6..58d0b258b684 100644 --- a/net/mac80211/wpa.c +++ b/net/mac80211/wpa.c @@ -340,7 +340,7 @@ static void ccmp_special_blocks(struct sk_buff *skb, u8 *pn, u8 *b_0, u8 *aad) a4_included = ieee80211_has_a4(hdr->frame_control); if (ieee80211_is_data_qos(hdr->frame_control)) - qos_tid = *ieee80211_get_qos_ctl(hdr) & IEEE80211_QOS_CTL_TID_MASK; + qos_tid = ieee80211_get_tid(hdr); else qos_tid = 0; @@ -601,8 +601,7 @@ static void gcmp_special_blocks(struct sk_buff *skb, u8 *pn, u8 *j_0, u8 *aad) aad[23] = 0; if (ieee80211_is_data_qos(hdr->frame_control)) - qos_tid = *ieee80211_get_qos_ctl(hdr) & - IEEE80211_QOS_CTL_TID_MASK; + qos_tid = ieee80211_get_tid(hdr); else qos_tid = 0; @@ -867,8 +866,7 @@ ieee80211_crypto_cs_decrypt(struct ieee80211_rx_data *rx) return RX_DROP_UNUSABLE; if (ieee80211_is_data_qos(hdr->frame_control)) - qos_tid = *ieee80211_get_qos_ctl(hdr) & - IEEE80211_QOS_CTL_TID_MASK; + qos_tid = ieee80211_get_tid(hdr); else qos_tid = 0; diff --git a/net/ncsi/Makefile b/net/ncsi/Makefile index dd12b564f2e7..436ef68331f2 100644 --- a/net/ncsi/Makefile +++ b/net/ncsi/Makefile @@ -1,4 +1,4 @@ # # Makefile for NCSI API # -obj-$(CONFIG_NET_NCSI) += ncsi-cmd.o ncsi-rsp.o ncsi-aen.o ncsi-manage.o +obj-$(CONFIG_NET_NCSI) += ncsi-cmd.o ncsi-rsp.o ncsi-aen.o ncsi-manage.o ncsi-netlink.o diff --git a/net/ncsi/internal.h b/net/ncsi/internal.h index d30f7bd741d0..8da84312cd3b 100644 --- a/net/ncsi/internal.h +++ b/net/ncsi/internal.h @@ -276,6 +276,8 @@ struct ncsi_dev_priv { unsigned int package_num; /* Number of packages */ struct list_head packages; /* List of packages */ struct ncsi_channel *hot_channel; /* Channel was ever active */ + struct ncsi_package *force_package; /* Force a specific package */ + struct ncsi_channel *force_channel; /* Force a specific channel */ struct ncsi_request requests[256]; /* Request table */ unsigned int request_id; /* Last used request ID */ #define NCSI_REQ_START_IDX 1 @@ -318,6 +320,7 @@ extern spinlock_t ncsi_dev_lock; list_for_each_entry_rcu(nc, &np->channels, node) /* Resources */ +u32 *ncsi_get_filter(struct ncsi_channel *nc, int table, int index); int ncsi_find_filter(struct ncsi_channel *nc, int table, void *data); int ncsi_add_filter(struct ncsi_channel *nc, int table, void *data); int ncsi_remove_filter(struct ncsi_channel *nc, int table, int index); diff --git a/net/ncsi/ncsi-manage.c b/net/ncsi/ncsi-manage.c index c989211bbabc..c3695ba0cf94 100644 --- a/net/ncsi/ncsi-manage.c +++ b/net/ncsi/ncsi-manage.c @@ -12,7 +12,6 @@ #include <linux/init.h> #include <linux/netdevice.h> #include <linux/skbuff.h> -#include <linux/netlink.h> #include <net/ncsi.h> #include <net/net_namespace.h> @@ -23,6 +22,7 @@ #include "internal.h" #include "ncsi-pkt.h" +#include "ncsi-netlink.h" LIST_HEAD(ncsi_dev_list); DEFINE_SPINLOCK(ncsi_dev_lock); @@ -38,7 +38,7 @@ static inline int ncsi_filter_size(int table) return sizes[table]; } -static u32 *ncsi_get_filter(struct ncsi_channel *nc, int table, int index) +u32 *ncsi_get_filter(struct ncsi_channel *nc, int table, int index) { struct ncsi_channel_filter *ncf; int size; @@ -965,20 +965,37 @@ error: static int ncsi_choose_active_channel(struct ncsi_dev_priv *ndp) { - struct ncsi_package *np; - struct ncsi_channel *nc, *found, *hot_nc; + struct ncsi_package *np, *force_package; + struct ncsi_channel *nc, *found, *hot_nc, *force_channel; struct ncsi_channel_mode *ncm; unsigned long flags; spin_lock_irqsave(&ndp->lock, flags); hot_nc = ndp->hot_channel; + force_channel = ndp->force_channel; + force_package = ndp->force_package; spin_unlock_irqrestore(&ndp->lock, flags); + /* Force a specific channel whether or not it has link if we have been + * configured to do so + */ + if (force_package && force_channel) { + found = force_channel; + ncm = &found->modes[NCSI_MODE_LINK]; + if (!(ncm->data[2] & 0x1)) + netdev_info(ndp->ndev.dev, + "NCSI: Channel %u forced, but it is link down\n", + found->id); + goto out; + } + /* The search is done once an inactive channel with up * link is found. */ found = NULL; NCSI_FOR_EACH_PACKAGE(ndp, np) { + if (ndp->force_package && np != ndp->force_package) + continue; NCSI_FOR_EACH_CHANNEL(np, nc) { spin_lock_irqsave(&nc->lock, flags); @@ -1594,6 +1611,9 @@ struct ncsi_dev *ncsi_register_dev(struct net_device *dev, ndp->ptype.dev = dev; dev_add_pack(&ndp->ptype); + /* Set up generic netlink interface */ + ncsi_init_netlink(dev); + return nd; } EXPORT_SYMBOL_GPL(ncsi_register_dev); @@ -1673,6 +1693,8 @@ void ncsi_unregister_dev(struct ncsi_dev *nd) #endif spin_unlock_irqrestore(&ncsi_dev_lock, flags); + ncsi_unregister_netlink(nd->dev); + kfree(ndp); } EXPORT_SYMBOL_GPL(ncsi_unregister_dev); diff --git a/net/ncsi/ncsi-netlink.c b/net/ncsi/ncsi-netlink.c new file mode 100644 index 000000000000..d4201665a580 --- /dev/null +++ b/net/ncsi/ncsi-netlink.c @@ -0,0 +1,421 @@ +/* + * Copyright Samuel Mendoza-Jonas, IBM Corporation 2018. + * + * 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/module.h> +#include <linux/kernel.h> +#include <linux/if_arp.h> +#include <linux/rtnetlink.h> +#include <linux/etherdevice.h> +#include <linux/module.h> +#include <net/genetlink.h> +#include <net/ncsi.h> +#include <linux/skbuff.h> +#include <net/sock.h> +#include <uapi/linux/ncsi.h> + +#include "internal.h" +#include "ncsi-netlink.h" + +static struct genl_family ncsi_genl_family; + +static const struct nla_policy ncsi_genl_policy[NCSI_ATTR_MAX + 1] = { + [NCSI_ATTR_IFINDEX] = { .type = NLA_U32 }, + [NCSI_ATTR_PACKAGE_LIST] = { .type = NLA_NESTED }, + [NCSI_ATTR_PACKAGE_ID] = { .type = NLA_U32 }, + [NCSI_ATTR_CHANNEL_ID] = { .type = NLA_U32 }, +}; + +static struct ncsi_dev_priv *ndp_from_ifindex(struct net *net, u32 ifindex) +{ + struct ncsi_dev_priv *ndp; + struct net_device *dev; + struct ncsi_dev *nd; + struct ncsi_dev; + + if (!net) + return NULL; + + dev = dev_get_by_index(net, ifindex); + if (!dev) { + pr_err("NCSI netlink: No device for ifindex %u\n", ifindex); + return NULL; + } + + nd = ncsi_find_dev(dev); + ndp = nd ? TO_NCSI_DEV_PRIV(nd) : NULL; + + dev_put(dev); + return ndp; +} + +static int ncsi_write_channel_info(struct sk_buff *skb, + struct ncsi_dev_priv *ndp, + struct ncsi_channel *nc) +{ + struct nlattr *vid_nest; + struct ncsi_channel_filter *ncf; + struct ncsi_channel_mode *m; + u32 *data; + int i; + + nla_put_u32(skb, NCSI_CHANNEL_ATTR_ID, nc->id); + m = &nc->modes[NCSI_MODE_LINK]; + nla_put_u32(skb, NCSI_CHANNEL_ATTR_LINK_STATE, m->data[2]); + if (nc->state == NCSI_CHANNEL_ACTIVE) + nla_put_flag(skb, NCSI_CHANNEL_ATTR_ACTIVE); + if (ndp->force_channel == nc) + nla_put_flag(skb, NCSI_CHANNEL_ATTR_FORCED); + + nla_put_u32(skb, NCSI_CHANNEL_ATTR_VERSION_MAJOR, nc->version.version); + nla_put_u32(skb, NCSI_CHANNEL_ATTR_VERSION_MINOR, nc->version.alpha2); + nla_put_string(skb, NCSI_CHANNEL_ATTR_VERSION_STR, nc->version.fw_name); + + vid_nest = nla_nest_start(skb, NCSI_CHANNEL_ATTR_VLAN_LIST); + if (!vid_nest) + return -ENOMEM; + ncf = nc->filters[NCSI_FILTER_VLAN]; + i = -1; + if (ncf) { + while ((i = find_next_bit((void *)&ncf->bitmap, ncf->total, + i + 1)) < ncf->total) { + data = ncsi_get_filter(nc, NCSI_FILTER_VLAN, i); + /* Uninitialised channels will have 'zero' vlan ids */ + if (!data || !*data) + continue; + nla_put_u16(skb, NCSI_CHANNEL_ATTR_VLAN_ID, + *(u16 *)data); + } + } + nla_nest_end(skb, vid_nest); + + return 0; +} + +static int ncsi_write_package_info(struct sk_buff *skb, + struct ncsi_dev_priv *ndp, unsigned int id) +{ + struct nlattr *pnest, *cnest, *nest; + struct ncsi_package *np; + struct ncsi_channel *nc; + bool found; + int rc; + + if (id > ndp->package_num) { + netdev_info(ndp->ndev.dev, "NCSI: No package with id %u\n", id); + return -ENODEV; + } + + found = false; + NCSI_FOR_EACH_PACKAGE(ndp, np) { + if (np->id != id) + continue; + pnest = nla_nest_start(skb, NCSI_PKG_ATTR); + if (!pnest) + return -ENOMEM; + nla_put_u32(skb, NCSI_PKG_ATTR_ID, np->id); + if (ndp->force_package == np) + nla_put_flag(skb, NCSI_PKG_ATTR_FORCED); + cnest = nla_nest_start(skb, NCSI_PKG_ATTR_CHANNEL_LIST); + if (!cnest) { + nla_nest_cancel(skb, pnest); + return -ENOMEM; + } + NCSI_FOR_EACH_CHANNEL(np, nc) { + nest = nla_nest_start(skb, NCSI_CHANNEL_ATTR); + if (!nest) { + nla_nest_cancel(skb, cnest); + nla_nest_cancel(skb, pnest); + return -ENOMEM; + } + rc = ncsi_write_channel_info(skb, ndp, nc); + if (rc) { + nla_nest_cancel(skb, nest); + nla_nest_cancel(skb, cnest); + nla_nest_cancel(skb, pnest); + return rc; + } + nla_nest_end(skb, nest); + } + nla_nest_end(skb, cnest); + nla_nest_end(skb, pnest); + found = true; + } + + if (!found) + return -ENODEV; + + return 0; +} + +static int ncsi_pkg_info_nl(struct sk_buff *msg, struct genl_info *info) +{ + struct ncsi_dev_priv *ndp; + unsigned int package_id; + struct sk_buff *skb; + struct nlattr *attr; + void *hdr; + int rc; + + if (!info || !info->attrs) + return -EINVAL; + + if (!info->attrs[NCSI_ATTR_IFINDEX]) + return -EINVAL; + + if (!info->attrs[NCSI_ATTR_PACKAGE_ID]) + return -EINVAL; + + ndp = ndp_from_ifindex(genl_info_net(info), + nla_get_u32(info->attrs[NCSI_ATTR_IFINDEX])); + if (!ndp) + return -ENODEV; + + skb = genlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!skb) + return -ENOMEM; + + hdr = genlmsg_put(skb, info->snd_portid, info->snd_seq, + &ncsi_genl_family, 0, NCSI_CMD_PKG_INFO); + if (!hdr) { + kfree(skb); + return -EMSGSIZE; + } + + package_id = nla_get_u32(info->attrs[NCSI_ATTR_PACKAGE_ID]); + + attr = nla_nest_start(skb, NCSI_ATTR_PACKAGE_LIST); + rc = ncsi_write_package_info(skb, ndp, package_id); + + if (rc) { + nla_nest_cancel(skb, attr); + goto err; + } + + nla_nest_end(skb, attr); + + genlmsg_end(skb, hdr); + return genlmsg_reply(skb, info); + +err: + genlmsg_cancel(skb, hdr); + kfree(skb); + return rc; +} + +static int ncsi_pkg_info_all_nl(struct sk_buff *skb, + struct netlink_callback *cb) +{ + struct nlattr *attrs[NCSI_ATTR_MAX]; + struct ncsi_package *np, *package; + struct ncsi_dev_priv *ndp; + unsigned int package_id; + struct nlattr *attr; + void *hdr; + int rc; + + rc = genlmsg_parse(cb->nlh, &ncsi_genl_family, attrs, NCSI_ATTR_MAX, + ncsi_genl_policy, NULL); + if (rc) + return rc; + + if (!attrs[NCSI_ATTR_IFINDEX]) + return -EINVAL; + + ndp = ndp_from_ifindex(get_net(sock_net(skb->sk)), + nla_get_u32(attrs[NCSI_ATTR_IFINDEX])); + + if (!ndp) + return -ENODEV; + + package_id = cb->args[0]; + package = NULL; + NCSI_FOR_EACH_PACKAGE(ndp, np) + if (np->id == package_id) + package = np; + + if (!package) + return 0; /* done */ + + hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, + &ncsi_genl_family, 0, NCSI_CMD_PKG_INFO); + if (!hdr) { + rc = -EMSGSIZE; + goto err; + } + + attr = nla_nest_start(skb, NCSI_ATTR_PACKAGE_LIST); + rc = ncsi_write_package_info(skb, ndp, package->id); + if (rc) { + nla_nest_cancel(skb, attr); + goto err; + } + + nla_nest_end(skb, attr); + genlmsg_end(skb, hdr); + + cb->args[0] = package_id + 1; + + return skb->len; +err: + genlmsg_cancel(skb, hdr); + return rc; +} + +static int ncsi_set_interface_nl(struct sk_buff *msg, struct genl_info *info) +{ + struct ncsi_package *np, *package; + struct ncsi_channel *nc, *channel; + u32 package_id, channel_id; + struct ncsi_dev_priv *ndp; + unsigned long flags; + + if (!info || !info->attrs) + return -EINVAL; + + if (!info->attrs[NCSI_ATTR_IFINDEX]) + return -EINVAL; + + if (!info->attrs[NCSI_ATTR_PACKAGE_ID]) + return -EINVAL; + + ndp = ndp_from_ifindex(get_net(sock_net(msg->sk)), + nla_get_u32(info->attrs[NCSI_ATTR_IFINDEX])); + if (!ndp) + return -ENODEV; + + package_id = nla_get_u32(info->attrs[NCSI_ATTR_PACKAGE_ID]); + package = NULL; + + spin_lock_irqsave(&ndp->lock, flags); + + NCSI_FOR_EACH_PACKAGE(ndp, np) + if (np->id == package_id) + package = np; + if (!package) { + /* The user has set a package that does not exist */ + return -ERANGE; + } + + channel = NULL; + if (!info->attrs[NCSI_ATTR_CHANNEL_ID]) { + /* Allow any channel */ + channel_id = NCSI_RESERVED_CHANNEL; + } else { + channel_id = nla_get_u32(info->attrs[NCSI_ATTR_CHANNEL_ID]); + NCSI_FOR_EACH_CHANNEL(package, nc) + if (nc->id == channel_id) + channel = nc; + } + + if (channel_id != NCSI_RESERVED_CHANNEL && !channel) { + /* The user has set a channel that does not exist on this + * package + */ + netdev_info(ndp->ndev.dev, "NCSI: Channel %u does not exist!\n", + channel_id); + return -ERANGE; + } + + ndp->force_package = package; + ndp->force_channel = channel; + spin_unlock_irqrestore(&ndp->lock, flags); + + netdev_info(ndp->ndev.dev, "Set package 0x%x, channel 0x%x%s as preferred\n", + package_id, channel_id, + channel_id == NCSI_RESERVED_CHANNEL ? " (any)" : ""); + + /* Bounce the NCSI channel to set changes */ + ncsi_stop_dev(&ndp->ndev); + ncsi_start_dev(&ndp->ndev); + + return 0; +} + +static int ncsi_clear_interface_nl(struct sk_buff *msg, struct genl_info *info) +{ + struct ncsi_dev_priv *ndp; + unsigned long flags; + + if (!info || !info->attrs) + return -EINVAL; + + if (!info->attrs[NCSI_ATTR_IFINDEX]) + return -EINVAL; + + ndp = ndp_from_ifindex(get_net(sock_net(msg->sk)), + nla_get_u32(info->attrs[NCSI_ATTR_IFINDEX])); + if (!ndp) + return -ENODEV; + + /* Clear any override */ + spin_lock_irqsave(&ndp->lock, flags); + ndp->force_package = NULL; + ndp->force_channel = NULL; + spin_unlock_irqrestore(&ndp->lock, flags); + netdev_info(ndp->ndev.dev, "NCSI: Cleared preferred package/channel\n"); + + /* Bounce the NCSI channel to set changes */ + ncsi_stop_dev(&ndp->ndev); + ncsi_start_dev(&ndp->ndev); + + return 0; +} + +static const struct genl_ops ncsi_ops[] = { + { + .cmd = NCSI_CMD_PKG_INFO, + .policy = ncsi_genl_policy, + .doit = ncsi_pkg_info_nl, + .dumpit = ncsi_pkg_info_all_nl, + .flags = 0, + }, + { + .cmd = NCSI_CMD_SET_INTERFACE, + .policy = ncsi_genl_policy, + .doit = ncsi_set_interface_nl, + .flags = GENL_ADMIN_PERM, + }, + { + .cmd = NCSI_CMD_CLEAR_INTERFACE, + .policy = ncsi_genl_policy, + .doit = ncsi_clear_interface_nl, + .flags = GENL_ADMIN_PERM, + }, +}; + +static struct genl_family ncsi_genl_family __ro_after_init = { + .name = "NCSI", + .version = 0, + .maxattr = NCSI_ATTR_MAX, + .module = THIS_MODULE, + .ops = ncsi_ops, + .n_ops = ARRAY_SIZE(ncsi_ops), +}; + +int ncsi_init_netlink(struct net_device *dev) +{ + int rc; + + rc = genl_register_family(&ncsi_genl_family); + if (rc) + netdev_err(dev, "ncsi: failed to register netlink family\n"); + + return rc; +} + +int ncsi_unregister_netlink(struct net_device *dev) +{ + int rc; + + rc = genl_unregister_family(&ncsi_genl_family); + if (rc) + netdev_err(dev, "ncsi: failed to unregister netlink family\n"); + + return rc; +} diff --git a/net/ncsi/ncsi-netlink.h b/net/ncsi/ncsi-netlink.h new file mode 100644 index 000000000000..91a5c256f8c4 --- /dev/null +++ b/net/ncsi/ncsi-netlink.h @@ -0,0 +1,20 @@ +/* + * Copyright Samuel Mendoza-Jonas, IBM Corporation 2018. + * + * 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 __NCSI_NETLINK_H__ +#define __NCSI_NETLINK_H__ + +#include <linux/netdevice.h> + +#include "internal.h" + +int ncsi_init_netlink(struct net_device *dev); +int ncsi_unregister_netlink(struct net_device *dev); + +#endif /* __NCSI_NETLINK_H__ */ diff --git a/net/netfilter/core.c b/net/netfilter/core.c index 0f6b8172fb9a..d72cc786c7b7 100644 --- a/net/netfilter/core.c +++ b/net/netfilter/core.c @@ -629,6 +629,7 @@ static void __net_exit netfilter_net_exit(struct net *net) static struct pernet_operations netfilter_net_ops = { .init = netfilter_net_init, .exit = netfilter_net_exit, + .async = true, }; int __init netfilter_init(void) diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index 975a85a48d39..2523ebe2b3cc 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -2094,7 +2094,8 @@ static struct pernet_operations ip_set_net_ops = { .init = ip_set_net_init, .exit = ip_set_net_exit, .id = &ip_set_net_id, - .size = sizeof(struct ip_set_net) + .size = sizeof(struct ip_set_net), + .async = true, }; static int __init diff --git a/net/netfilter/ipvs/ip_vs_lblc.c b/net/netfilter/ipvs/ip_vs_lblc.c index d625179de485..6a340c94c4b8 100644 --- a/net/netfilter/ipvs/ip_vs_lblc.c +++ b/net/netfilter/ipvs/ip_vs_lblc.c @@ -604,6 +604,7 @@ static void __net_exit __ip_vs_lblc_exit(struct net *net) { } static struct pernet_operations ip_vs_lblc_ops = { .init = __ip_vs_lblc_init, .exit = __ip_vs_lblc_exit, + .async = true, }; static int __init ip_vs_lblc_init(void) diff --git a/net/netfilter/ipvs/ip_vs_lblcr.c b/net/netfilter/ipvs/ip_vs_lblcr.c index 84c57b62a588..0627881128da 100644 --- a/net/netfilter/ipvs/ip_vs_lblcr.c +++ b/net/netfilter/ipvs/ip_vs_lblcr.c @@ -789,6 +789,7 @@ static void __net_exit __ip_vs_lblcr_exit(struct net *net) { } static struct pernet_operations ip_vs_lblcr_ops = { .init = __ip_vs_lblcr_init, .exit = __ip_vs_lblcr_exit, + .async = true, }; static int __init ip_vs_lblcr_init(void) diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index dd177ebee9aa..8884d302d33a 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -3417,6 +3417,7 @@ static void __net_exit ctnetlink_net_exit_batch(struct list_head *net_exit_list) static struct pernet_operations ctnetlink_net_ops = { .init = ctnetlink_net_init, .exit_batch = ctnetlink_net_exit_batch, + .async = true, }; static int __init ctnetlink_init(void) diff --git a/net/netfilter/nf_conntrack_proto_gre.c b/net/netfilter/nf_conntrack_proto_gre.c index d049ea5a3770..9bcd72fe91f9 100644 --- a/net/netfilter/nf_conntrack_proto_gre.c +++ b/net/netfilter/nf_conntrack_proto_gre.c @@ -406,6 +406,7 @@ static struct pernet_operations proto_gre_net_ops = { .exit = proto_gre_net_exit, .id = &proto_gre_net_id, .size = sizeof(struct netns_proto_gre), + .async = true, }; static int __init nf_ct_proto_gre_init(void) diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index 9123fdec5e14..3cdce391362e 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -705,6 +705,7 @@ static void nf_conntrack_pernet_exit(struct list_head *net_exit_list) static struct pernet_operations nf_conntrack_net_ops = { .init = nf_conntrack_pernet_init, .exit_batch = nf_conntrack_pernet_exit, + .async = true, }; static int __init nf_conntrack_standalone_init(void) diff --git a/net/netfilter/nf_log.c b/net/netfilter/nf_log.c index c2c1b16b7538..1ba3da51050d 100644 --- a/net/netfilter/nf_log.c +++ b/net/netfilter/nf_log.c @@ -577,6 +577,7 @@ static void __net_exit nf_log_net_exit(struct net *net) static struct pernet_operations nf_log_net_ops = { .init = nf_log_net_init, .exit = nf_log_net_exit, + .async = true, }; int __init netfilter_log_init(void) diff --git a/net/netfilter/nf_log_netdev.c b/net/netfilter/nf_log_netdev.c index 350eb147754d..254c2c6bde48 100644 --- a/net/netfilter/nf_log_netdev.c +++ b/net/netfilter/nf_log_netdev.c @@ -47,6 +47,7 @@ static void __net_exit nf_log_netdev_net_exit(struct net *net) static struct pernet_operations nf_log_netdev_net_ops = { .init = nf_log_netdev_net_init, .exit = nf_log_netdev_net_exit, + .async = true, }; static int __init nf_log_netdev_init(void) diff --git a/net/netfilter/nf_synproxy_core.c b/net/netfilter/nf_synproxy_core.c index 92139a087260..64b875e452ca 100644 --- a/net/netfilter/nf_synproxy_core.c +++ b/net/netfilter/nf_synproxy_core.c @@ -398,6 +398,7 @@ static struct pernet_operations synproxy_net_ops = { .exit = synproxy_net_exit, .id = &synproxy_net_id, .size = sizeof(struct synproxy_net), + .async = true, }; static int __init synproxy_core_init(void) diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c index fa1655aff8d3..d9deebe599ec 100644 --- a/net/netfilter/x_tables.c +++ b/net/netfilter/x_tables.c @@ -1759,6 +1759,7 @@ static void __net_exit xt_net_exit(struct net *net) static struct pernet_operations xt_net_ops = { .init = xt_net_init, .exit = xt_net_exit, + .async = true, }; static int __init xt_init(void) diff --git a/net/netfilter/xt_hashlimit.c b/net/netfilter/xt_hashlimit.c index 66f5aca62a08..db2fe0911740 100644 --- a/net/netfilter/xt_hashlimit.c +++ b/net/netfilter/xt_hashlimit.c @@ -1345,6 +1345,7 @@ static struct pernet_operations hashlimit_net_ops = { .exit = hashlimit_net_exit, .id = &hashlimit_net_id, .size = sizeof(struct hashlimit_net), + .async = true, }; static int __init hashlimit_mt_init(void) diff --git a/net/netfilter/xt_recent.c b/net/netfilter/xt_recent.c index 6d232d18faff..19efdb757944 100644 --- a/net/netfilter/xt_recent.c +++ b/net/netfilter/xt_recent.c @@ -687,6 +687,7 @@ static struct pernet_operations recent_net_ops = { .exit = recent_net_exit, .id = &recent_net_id, .size = sizeof(struct recent_net), + .async = true, }; static struct xt_match recent_mt_reg[] __read_mostly = { diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 07e8478068f0..5d10dcfe6411 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -253,6 +253,7 @@ static struct pernet_operations netlink_tap_net_ops = { .exit = netlink_tap_exit_net, .id = &netlink_tap_net_id, .size = sizeof(struct netlink_tap_net), + .async = true, }; static bool netlink_filter_tap(const struct sk_buff *skb) @@ -1105,7 +1106,7 @@ static int netlink_connect(struct socket *sock, struct sockaddr *addr, } static int netlink_getname(struct socket *sock, struct sockaddr *addr, - int *addr_len, int peer) + int peer) { struct sock *sk = sock->sk; struct netlink_sock *nlk = nlk_sk(sk); @@ -1113,7 +1114,6 @@ static int netlink_getname(struct socket *sock, struct sockaddr *addr, nladdr->nl_family = AF_NETLINK; nladdr->nl_pad = 0; - *addr_len = sizeof(*nladdr); if (peer) { nladdr->nl_pid = nlk->dst_portid; @@ -1124,7 +1124,7 @@ static int netlink_getname(struct socket *sock, struct sockaddr *addr, nladdr->nl_groups = nlk->groups ? nlk->groups[0] : 0; netlink_unlock_table(); } - return 0; + return sizeof(*nladdr); } static int netlink_ioctl(struct socket *sock, unsigned int cmd, @@ -2726,6 +2726,7 @@ static void __init netlink_add_usersock_entry(void) static struct pernet_operations __net_initdata netlink_net_ops = { .init = netlink_net_init, .exit = netlink_net_exit, + .async = true, }; static inline u32 netlink_hash(const void *data, u32 len, u32 seed) diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index 6f02499ef007..a6f63a5faee7 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -1035,6 +1035,7 @@ static void __net_exit genl_pernet_exit(struct net *net) static struct pernet_operations genl_pernet_ops = { .init = genl_pernet_init, .exit = genl_pernet_exit, + .async = true, }; static int __init genl_init(void) diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c index 9ba30c63be3d..35bb6807927f 100644 --- a/net/netrom/af_netrom.c +++ b/net/netrom/af_netrom.c @@ -829,11 +829,12 @@ out_release: } static int nr_getname(struct socket *sock, struct sockaddr *uaddr, - int *uaddr_len, int peer) + int peer) { struct full_sockaddr_ax25 *sax = (struct full_sockaddr_ax25 *)uaddr; struct sock *sk = sock->sk; struct nr_sock *nr = nr_sk(sk); + int uaddr_len; memset(&sax->fsa_ax25, 0, sizeof(struct sockaddr_ax25)); @@ -848,16 +849,16 @@ static int nr_getname(struct socket *sock, struct sockaddr *uaddr, sax->fsa_ax25.sax25_call = nr->user_addr; memset(sax->fsa_digipeater, 0, sizeof(sax->fsa_digipeater)); sax->fsa_digipeater[0] = nr->dest_addr; - *uaddr_len = sizeof(struct full_sockaddr_ax25); + uaddr_len = sizeof(struct full_sockaddr_ax25); } else { sax->fsa_ax25.sax25_family = AF_NETROM; sax->fsa_ax25.sax25_ndigis = 0; sax->fsa_ax25.sax25_call = nr->source_addr; - *uaddr_len = sizeof(struct sockaddr_ax25); + uaddr_len = sizeof(struct sockaddr_ax25); } release_sock(sk); - return 0; + return uaddr_len; } int nr_rx_frame(struct sk_buff *skb, struct net_device *dev) diff --git a/net/nfc/llcp_sock.c b/net/nfc/llcp_sock.c index 376040092142..ea0c0c6f1874 100644 --- a/net/nfc/llcp_sock.c +++ b/net/nfc/llcp_sock.c @@ -497,7 +497,7 @@ error: } static int llcp_sock_getname(struct socket *sock, struct sockaddr *uaddr, - int *len, int peer) + int peer) { struct sock *sk = sock->sk; struct nfc_llcp_sock *llcp_sock = nfc_llcp_sock(sk); @@ -510,7 +510,6 @@ static int llcp_sock_getname(struct socket *sock, struct sockaddr *uaddr, llcp_sock->dsap, llcp_sock->ssap); memset(llcp_addr, 0, sizeof(*llcp_addr)); - *len = sizeof(struct sockaddr_nfc_llcp); lock_sock(sk); if (!llcp_sock->dev) { @@ -528,7 +527,7 @@ static int llcp_sock_getname(struct socket *sock, struct sockaddr *uaddr, llcp_addr->service_name_len); release_sock(sk); - return 0; + return sizeof(struct sockaddr_nfc_llcp); } static inline __poll_t llcp_accept_poll(struct sock *parent) diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index e0f3f4aeeb4f..2c5a6fe5d749 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -3409,7 +3409,7 @@ out: } static int packet_getname_spkt(struct socket *sock, struct sockaddr *uaddr, - int *uaddr_len, int peer) + int peer) { struct net_device *dev; struct sock *sk = sock->sk; @@ -3424,13 +3424,12 @@ static int packet_getname_spkt(struct socket *sock, struct sockaddr *uaddr, if (dev) strlcpy(uaddr->sa_data, dev->name, sizeof(uaddr->sa_data)); rcu_read_unlock(); - *uaddr_len = sizeof(*uaddr); - return 0; + return sizeof(*uaddr); } static int packet_getname(struct socket *sock, struct sockaddr *uaddr, - int *uaddr_len, int peer) + int peer) { struct net_device *dev; struct sock *sk = sock->sk; @@ -3455,9 +3454,8 @@ static int packet_getname(struct socket *sock, struct sockaddr *uaddr, sll->sll_halen = 0; } rcu_read_unlock(); - *uaddr_len = offsetof(struct sockaddr_ll, sll_addr) + sll->sll_halen; - return 0; + return offsetof(struct sockaddr_ll, sll_addr) + sll->sll_halen; } static int packet_dev_mc(struct net_device *dev, struct packet_mclist *i, @@ -4559,6 +4557,7 @@ static void __net_exit packet_net_exit(struct net *net) static struct pernet_operations packet_net_ops = { .init = packet_net_init, .exit = packet_net_exit, + .async = true, }; diff --git a/net/phonet/pn_dev.c b/net/phonet/pn_dev.c index 77787512fc32..9454e8393793 100644 --- a/net/phonet/pn_dev.c +++ b/net/phonet/pn_dev.c @@ -342,6 +342,7 @@ static struct pernet_operations phonet_net_ops = { .exit = phonet_exit_net, .id = &phonet_net_id, .size = sizeof(struct phonet_net), + .async = true, }; /* Initialize Phonet devices list */ diff --git a/net/phonet/socket.c b/net/phonet/socket.c index fffcd69f63ff..f9b40e6a18a5 100644 --- a/net/phonet/socket.c +++ b/net/phonet/socket.c @@ -326,7 +326,7 @@ static int pn_socket_accept(struct socket *sock, struct socket *newsock, } static int pn_socket_getname(struct socket *sock, struct sockaddr *addr, - int *sockaddr_len, int peer) + int peer) { struct sock *sk = sock->sk; struct pn_sock *pn = pn_sk(sk); @@ -337,8 +337,7 @@ static int pn_socket_getname(struct socket *sock, struct sockaddr *addr, pn_sockaddr_set_object((struct sockaddr_pn *)addr, pn->sobject); - *sockaddr_len = sizeof(struct sockaddr_pn); - return 0; + return sizeof(struct sockaddr_pn); } static __poll_t pn_socket_poll(struct file *file, struct socket *sock, diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c index 5fb3929e3d7d..b33e5aeb4c06 100644 --- a/net/qrtr/qrtr.c +++ b/net/qrtr/qrtr.c @@ -893,7 +893,7 @@ static int qrtr_connect(struct socket *sock, struct sockaddr *saddr, } static int qrtr_getname(struct socket *sock, struct sockaddr *saddr, - int *len, int peer) + int peer) { struct qrtr_sock *ipc = qrtr_sk(sock->sk); struct sockaddr_qrtr qaddr; @@ -912,12 +912,11 @@ static int qrtr_getname(struct socket *sock, struct sockaddr *saddr, } release_sock(sk); - *len = sizeof(qaddr); qaddr.sq_family = AF_QIPCRTR; memcpy(saddr, &qaddr, sizeof(qaddr)); - return 0; + return sizeof(qaddr); } static int qrtr_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) diff --git a/net/rds/af_rds.c b/net/rds/af_rds.c index 744c637c86b0..f7126108a811 100644 --- a/net/rds/af_rds.c +++ b/net/rds/af_rds.c @@ -77,6 +77,7 @@ static int rds_release(struct socket *sock) rds_send_drop_to(rs, NULL); rds_rdma_drop_keys(rs); rds_notify_queue_get(rs, NULL); + __skb_queue_purge(&rs->rs_zcookie_queue); spin_lock_bh(&rds_sock_lock); list_del_init(&rs->rs_item); @@ -110,7 +111,7 @@ void rds_wake_sk_sleep(struct rds_sock *rs) } static int rds_getname(struct socket *sock, struct sockaddr *uaddr, - int *uaddr_len, int peer) + int peer) { struct sockaddr_in *sin = (struct sockaddr_in *)uaddr; struct rds_sock *rs = rds_sk_to_rs(sock->sk); @@ -131,8 +132,7 @@ static int rds_getname(struct socket *sock, struct sockaddr *uaddr, sin->sin_family = AF_INET; - *uaddr_len = sizeof(*sin); - return 0; + return sizeof(*sin); } /* @@ -145,7 +145,7 @@ static int rds_getname(struct socket *sock, struct sockaddr *uaddr, * - to signal that a previously congested destination may have become * uncongested * - A notification has been queued to the socket (this can be a congestion - * update, or a RDMA completion). + * update, or a RDMA completion, or a MSG_ZEROCOPY completion). * * EPOLLOUT is asserted if there is room on the send queue. This does not mean * however, that the next sendmsg() call will succeed. If the application tries @@ -179,10 +179,13 @@ static __poll_t rds_poll(struct file *file, struct socket *sock, spin_unlock(&rs->rs_lock); } if (!list_empty(&rs->rs_recv_queue) || - !list_empty(&rs->rs_notify_queue)) + !list_empty(&rs->rs_notify_queue) || + !skb_queue_empty(&rs->rs_zcookie_queue)) mask |= (EPOLLIN | EPOLLRDNORM); if (rs->rs_snd_bytes < rds_sk_sndbuf(rs)) mask |= (EPOLLOUT | EPOLLWRNORM); + if (sk->sk_err || !skb_queue_empty(&sk->sk_error_queue)) + mask |= POLLERR; read_unlock_irqrestore(&rs->rs_recv_lock, flags); /* clear state any time we wake a seen-congested socket */ @@ -512,6 +515,7 @@ static int __rds_create(struct socket *sock, struct sock *sk, int protocol) INIT_LIST_HEAD(&rs->rs_recv_queue); INIT_LIST_HEAD(&rs->rs_notify_queue); INIT_LIST_HEAD(&rs->rs_cong_list); + skb_queue_head_init(&rs->rs_zcookie_queue); spin_lock_init(&rs->rs_rdma_lock); rs->rs_rdma_keys = RB_ROOT; rs->rs_rx_traces = 0; diff --git a/net/rds/message.c b/net/rds/message.c index 4318cc9b78f7..116cf87ccb89 100644 --- a/net/rds/message.c +++ b/net/rds/message.c @@ -33,6 +33,9 @@ #include <linux/kernel.h> #include <linux/slab.h> #include <linux/export.h> +#include <linux/skbuff.h> +#include <linux/list.h> +#include <linux/errqueue.h> #include "rds.h" @@ -53,20 +56,84 @@ void rds_message_addref(struct rds_message *rm) } EXPORT_SYMBOL_GPL(rds_message_addref); +static inline bool skb_zcookie_add(struct sk_buff *skb, u32 cookie) +{ + struct rds_zcopy_cookies *ck = (struct rds_zcopy_cookies *)skb->cb; + int ncookies = ck->num; + + if (ncookies == RDS_MAX_ZCOOKIES) + return false; + ck->cookies[ncookies] = cookie; + ck->num = ++ncookies; + return true; +} + +static void rds_rm_zerocopy_callback(struct rds_sock *rs, + struct rds_znotifier *znotif) +{ + struct sk_buff *skb, *tail; + unsigned long flags; + struct sk_buff_head *q; + u32 cookie = znotif->z_cookie; + struct rds_zcopy_cookies *ck; + + q = &rs->rs_zcookie_queue; + spin_lock_irqsave(&q->lock, flags); + tail = skb_peek_tail(q); + + if (tail && skb_zcookie_add(tail, cookie)) { + spin_unlock_irqrestore(&q->lock, flags); + mm_unaccount_pinned_pages(&znotif->z_mmp); + consume_skb(rds_skb_from_znotifier(znotif)); + /* caller invokes rds_wake_sk_sleep() */ + return; + } + + skb = rds_skb_from_znotifier(znotif); + ck = (struct rds_zcopy_cookies *)skb->cb; + memset(ck, 0, sizeof(*ck)); + WARN_ON(!skb_zcookie_add(skb, cookie)); + + __skb_queue_tail(q, skb); + + spin_unlock_irqrestore(&q->lock, flags); + /* caller invokes rds_wake_sk_sleep() */ + + mm_unaccount_pinned_pages(&znotif->z_mmp); +} + /* * This relies on dma_map_sg() not touching sg[].page during merging. */ static void rds_message_purge(struct rds_message *rm) { - unsigned long i; + unsigned long i, flags; + bool zcopy = false; if (unlikely(test_bit(RDS_MSG_PAGEVEC, &rm->m_flags))) return; + spin_lock_irqsave(&rm->m_rs_lock, flags); + if (rm->m_rs) { + struct rds_sock *rs = rm->m_rs; + + if (rm->data.op_mmp_znotifier) { + zcopy = true; + rds_rm_zerocopy_callback(rs, rm->data.op_mmp_znotifier); + rds_wake_sk_sleep(rs); + rm->data.op_mmp_znotifier = NULL; + } + sock_put(rds_rs_to_sk(rs)); + rm->m_rs = NULL; + } + spin_unlock_irqrestore(&rm->m_rs_lock, flags); + for (i = 0; i < rm->data.op_nents; i++) { - rdsdebug("putting data page %p\n", (void *)sg_page(&rm->data.op_sg[i])); /* XXX will have to put_page for page refs */ - __free_page(sg_page(&rm->data.op_sg[i])); + if (!zcopy) + __free_page(sg_page(&rm->data.op_sg[i])); + else + put_page(sg_page(&rm->data.op_sg[i])); } rm->data.op_nents = 0; @@ -266,12 +333,14 @@ struct rds_message *rds_message_map_pages(unsigned long *page_addrs, unsigned in return rm; } -int rds_message_copy_from_user(struct rds_message *rm, struct iov_iter *from) +int rds_message_copy_from_user(struct rds_message *rm, struct iov_iter *from, + bool zcopy) { unsigned long to_copy, nbytes; unsigned long sg_off; struct scatterlist *sg; int ret = 0; + int length = iov_iter_count(from); rm->m_inc.i_hdr.h_len = cpu_to_be32(iov_iter_count(from)); @@ -281,6 +350,55 @@ int rds_message_copy_from_user(struct rds_message *rm, struct iov_iter *from) sg = rm->data.op_sg; sg_off = 0; /* Dear gcc, sg->page will be null from kzalloc. */ + if (zcopy) { + int total_copied = 0; + struct sk_buff *skb; + + skb = alloc_skb(0, GFP_KERNEL); + if (!skb) + return -ENOMEM; + BUILD_BUG_ON(sizeof(skb->cb) < + max_t(int, sizeof(struct rds_znotifier), + sizeof(struct rds_zcopy_cookies))); + rm->data.op_mmp_znotifier = RDS_ZCOPY_SKB(skb); + if (mm_account_pinned_pages(&rm->data.op_mmp_znotifier->z_mmp, + length)) { + ret = -ENOMEM; + goto err; + } + while (iov_iter_count(from)) { + struct page *pages; + size_t start; + ssize_t copied; + + copied = iov_iter_get_pages(from, &pages, PAGE_SIZE, + 1, &start); + if (copied < 0) { + struct mmpin *mmp; + int i; + + for (i = 0; i < rm->data.op_nents; i++) + put_page(sg_page(&rm->data.op_sg[i])); + mmp = &rm->data.op_mmp_znotifier->z_mmp; + mm_unaccount_pinned_pages(mmp); + ret = -EFAULT; + goto err; + } + total_copied += copied; + iov_iter_advance(from, copied); + length -= copied; + sg_set_page(sg, pages, copied, start); + rm->data.op_nents++; + sg++; + } + WARN_ON_ONCE(length != 0); + return ret; +err: + consume_skb(skb); + rm->data.op_mmp_znotifier = NULL; + return ret; + } /* zcopy */ + while (iov_iter_count(from)) { if (!sg_page(sg)) { ret = rds_page_remainder_alloc(sg, iov_iter_count(from), diff --git a/net/rds/rds.h b/net/rds/rds.h index 7301b9b01890..33b16353d8f3 100644 --- a/net/rds/rds.h +++ b/net/rds/rds.h @@ -356,6 +356,19 @@ static inline u32 rds_rdma_cookie_offset(rds_rdma_cookie_t cookie) #define RDS_MSG_PAGEVEC 7 #define RDS_MSG_FLUSH 8 +struct rds_znotifier { + struct list_head z_list; + struct mmpin z_mmp; + u32 z_cookie; +}; + +#define RDS_ZCOPY_SKB(__skb) ((struct rds_znotifier *)&((__skb)->cb[0])) + +static inline struct sk_buff *rds_skb_from_znotifier(struct rds_znotifier *z) +{ + return container_of((void *)z, struct sk_buff, cb); +} + struct rds_message { refcount_t m_refcount; struct list_head m_sock_item; @@ -436,6 +449,7 @@ struct rds_message { unsigned int op_count; unsigned int op_dmasg; unsigned int op_dmaoff; + struct rds_znotifier *op_mmp_znotifier; struct scatterlist *op_sg; } data; }; @@ -589,6 +603,8 @@ struct rds_sock { /* Socket receive path trace points*/ u8 rs_rx_traces; u8 rs_rx_trace[RDS_MSG_RX_DGRAM_TRACE_MAX]; + + struct sk_buff_head rs_zcookie_queue; }; static inline struct rds_sock *rds_sk_to_rs(const struct sock *sk) @@ -771,7 +787,8 @@ rds_conn_connecting(struct rds_connection *conn) /* message.c */ struct rds_message *rds_message_alloc(unsigned int nents, gfp_t gfp); struct scatterlist *rds_message_alloc_sgs(struct rds_message *rm, int nents); -int rds_message_copy_from_user(struct rds_message *rm, struct iov_iter *from); +int rds_message_copy_from_user(struct rds_message *rm, struct iov_iter *from, + bool zcopy); struct rds_message *rds_message_map_pages(unsigned long *page_addrs, unsigned int total_len); void rds_message_populate_header(struct rds_header *hdr, __be16 sport, __be16 dport, u64 seq); diff --git a/net/rds/recv.c b/net/rds/recv.c index b25bcfe411ca..d50747725221 100644 --- a/net/rds/recv.c +++ b/net/rds/recv.c @@ -577,6 +577,32 @@ out: return ret; } +static bool rds_recvmsg_zcookie(struct rds_sock *rs, struct msghdr *msg) +{ + struct sk_buff *skb; + struct sk_buff_head *q = &rs->rs_zcookie_queue; + struct rds_zcopy_cookies *done; + + if (!msg->msg_control) + return false; + + if (!sock_flag(rds_rs_to_sk(rs), SOCK_ZEROCOPY) || + msg->msg_controllen < CMSG_SPACE(sizeof(*done))) + return false; + + skb = skb_dequeue(q); + if (!skb) + return false; + done = (struct rds_zcopy_cookies *)skb->cb; + if (put_cmsg(msg, SOL_RDS, RDS_CMSG_ZCOPY_COMPLETION, sizeof(*done), + done)) { + skb_queue_head(q, skb); + return false; + } + consume_skb(skb); + return true; +} + int rds_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, int msg_flags) { @@ -594,6 +620,8 @@ int rds_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, if (msg_flags & MSG_OOB) goto out; + if (msg_flags & MSG_ERRQUEUE) + return sock_recv_errqueue(sk, msg, size, SOL_IP, IP_RECVERR); while (1) { /* If there are pending notifications, do those - and nothing else */ @@ -609,7 +637,9 @@ int rds_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, if (!rds_next_incoming(rs, &inc)) { if (nonblock) { - ret = -EAGAIN; + bool reaped = rds_recvmsg_zcookie(rs, msg); + + ret = reaped ? 0 : -EAGAIN; break; } @@ -658,6 +688,7 @@ int rds_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, ret = -EFAULT; goto out; } + rds_recvmsg_zcookie(rs, msg); rds_stats_inc(s_recv_delivered); diff --git a/net/rds/send.c b/net/rds/send.c index b1b0022b8370..acad04243b41 100644 --- a/net/rds/send.c +++ b/net/rds/send.c @@ -649,7 +649,6 @@ static void rds_send_remove_from_sock(struct list_head *messages, int status) rm->rdma.op_notifier = NULL; } was_on_sock = 1; - rm->m_rs = NULL; } spin_unlock(&rs->rs_lock); @@ -756,9 +755,6 @@ void rds_send_drop_to(struct rds_sock *rs, struct sockaddr_in *dest) */ if (!test_and_clear_bit(RDS_MSG_ON_CONN, &rm->m_flags)) { spin_unlock_irqrestore(&cp->cp_lock, flags); - spin_lock_irqsave(&rm->m_rs_lock, flags); - rm->m_rs = NULL; - spin_unlock_irqrestore(&rm->m_rs_lock, flags); continue; } list_del_init(&rm->m_conn_item); @@ -774,7 +770,6 @@ void rds_send_drop_to(struct rds_sock *rs, struct sockaddr_in *dest) __rds_send_complete(rs, rm, RDS_RDMA_CANCELED); spin_unlock(&rs->rs_lock); - rm->m_rs = NULL; spin_unlock_irqrestore(&rm->m_rs_lock, flags); rds_message_put(rm); @@ -798,7 +793,6 @@ void rds_send_drop_to(struct rds_sock *rs, struct sockaddr_in *dest) __rds_send_complete(rs, rm, RDS_RDMA_CANCELED); spin_unlock(&rs->rs_lock); - rm->m_rs = NULL; spin_unlock_irqrestore(&rm->m_rs_lock, flags); rds_message_put(rm); @@ -849,6 +843,7 @@ static int rds_send_queue_rm(struct rds_sock *rs, struct rds_connection *conn, list_add_tail(&rm->m_sock_item, &rs->rs_send_queue); set_bit(RDS_MSG_ON_SOCK, &rm->m_flags); rds_message_addref(rm); + sock_hold(rds_rs_to_sk(rs)); rm->m_rs = rs; /* The code ordering is a little weird, but we're @@ -880,12 +875,13 @@ out: * rds_message is getting to be quite complicated, and we'd like to allocate * it all in one go. This figures out how big it needs to be up front. */ -static int rds_rm_size(struct msghdr *msg, int data_len) +static int rds_rm_size(struct msghdr *msg, int num_sgs) { struct cmsghdr *cmsg; int size = 0; int cmsg_groups = 0; int retval; + bool zcopy_cookie = false; for_each_cmsghdr(cmsg, msg) { if (!CMSG_OK(msg, cmsg)) @@ -904,6 +900,10 @@ static int rds_rm_size(struct msghdr *msg, int data_len) break; + case RDS_CMSG_ZCOPY_COOKIE: + zcopy_cookie = true; + /* fall through */ + case RDS_CMSG_RDMA_DEST: case RDS_CMSG_RDMA_MAP: cmsg_groups |= 2; @@ -924,7 +924,10 @@ static int rds_rm_size(struct msghdr *msg, int data_len) } - size += ceil(data_len, PAGE_SIZE) * sizeof(struct scatterlist); + if ((msg->msg_flags & MSG_ZEROCOPY) && !zcopy_cookie) + return -EINVAL; + + size += num_sgs * sizeof(struct scatterlist); /* Ensure (DEST, MAP) are never used with (ARGS, ATOMIC) */ if (cmsg_groups == 3) @@ -933,6 +936,19 @@ static int rds_rm_size(struct msghdr *msg, int data_len) return size; } +static int rds_cmsg_zcopy(struct rds_sock *rs, struct rds_message *rm, + struct cmsghdr *cmsg) +{ + u32 *cookie; + + if (cmsg->cmsg_len < CMSG_LEN(sizeof(*cookie)) || + !rm->data.op_mmp_znotifier) + return -EINVAL; + cookie = CMSG_DATA(cmsg); + rm->data.op_mmp_znotifier->z_cookie = *cookie; + return 0; +} + static int rds_cmsg_send(struct rds_sock *rs, struct rds_message *rm, struct msghdr *msg, int *allocated_mr) { @@ -975,6 +991,10 @@ static int rds_cmsg_send(struct rds_sock *rs, struct rds_message *rm, ret = rds_cmsg_atomic(rs, rm, cmsg); break; + case RDS_CMSG_ZCOPY_COOKIE: + ret = rds_cmsg_zcopy(rs, rm, cmsg); + break; + default: return -EINVAL; } @@ -1045,10 +1065,13 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len) long timeo = sock_sndtimeo(sk, nonblock); struct rds_conn_path *cpath; size_t total_payload_len = payload_len, rdma_payload_len = 0; + bool zcopy = ((msg->msg_flags & MSG_ZEROCOPY) && + sock_flag(rds_rs_to_sk(rs), SOCK_ZEROCOPY)); + int num_sgs = ceil(payload_len, PAGE_SIZE); /* Mirror Linux UDP mirror of BSD error message compatibility */ /* XXX: Perhaps MSG_MORE someday */ - if (msg->msg_flags & ~(MSG_DONTWAIT | MSG_CMSG_COMPAT)) { + if (msg->msg_flags & ~(MSG_DONTWAIT | MSG_CMSG_COMPAT | MSG_ZEROCOPY)) { ret = -EOPNOTSUPP; goto out; } @@ -1092,8 +1115,15 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len) goto out; } + if (zcopy) { + if (rs->rs_transport->t_type != RDS_TRANS_TCP) { + ret = -EOPNOTSUPP; + goto out; + } + num_sgs = iov_iter_npages(&msg->msg_iter, INT_MAX); + } /* size of rm including all sgs */ - ret = rds_rm_size(msg, payload_len); + ret = rds_rm_size(msg, num_sgs); if (ret < 0) goto out; @@ -1105,12 +1135,12 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len) /* Attach data to the rm */ if (payload_len) { - rm->data.op_sg = rds_message_alloc_sgs(rm, ceil(payload_len, PAGE_SIZE)); + rm->data.op_sg = rds_message_alloc_sgs(rm, num_sgs); if (!rm->data.op_sg) { ret = -ENOMEM; goto out; } - ret = rds_message_copy_from_user(rm, &msg->msg_iter); + ret = rds_message_copy_from_user(rm, &msg->msg_iter, zcopy); if (ret) goto out; } diff --git a/net/rds/tcp.c b/net/rds/tcp.c index 44c4652721af..08230a145042 100644 --- a/net/rds/tcp.c +++ b/net/rds/tcp.c @@ -227,7 +227,6 @@ static void rds_tcp_tc_info(struct socket *rds_sock, unsigned int len, struct rds_tcp_connection *tc; unsigned long flags; struct sockaddr_in sin; - int sinlen; struct socket *sock; spin_lock_irqsave(&rds_tcp_tc_list_lock, flags); @@ -239,12 +238,10 @@ static void rds_tcp_tc_info(struct socket *rds_sock, unsigned int len, sock = tc->t_sock; if (sock) { - sock->ops->getname(sock, (struct sockaddr *)&sin, - &sinlen, 0); + sock->ops->getname(sock, (struct sockaddr *)&sin, 0); tsinfo.local_addr = sin.sin_addr.s_addr; tsinfo.local_port = sin.sin_port; - sock->ops->getname(sock, (struct sockaddr *)&sin, - &sinlen, 1); + sock->ops->getname(sock, (struct sockaddr *)&sin, 1); tsinfo.peer_addr = sin.sin_addr.s_addr; tsinfo.peer_port = sin.sin_port; } diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c index 083bd251406f..5170373b797c 100644 --- a/net/rose/af_rose.c +++ b/net/rose/af_rose.c @@ -938,7 +938,7 @@ out_release: } static int rose_getname(struct socket *sock, struct sockaddr *uaddr, - int *uaddr_len, int peer) + int peer) { struct full_sockaddr_rose *srose = (struct full_sockaddr_rose *)uaddr; struct sock *sk = sock->sk; @@ -964,8 +964,7 @@ static int rose_getname(struct socket *sock, struct sockaddr *uaddr, srose->srose_digis[n] = rose->source_digis[n]; } - *uaddr_len = sizeof(struct full_sockaddr_rose); - return 0; + return sizeof(struct full_sockaddr_rose); } int rose_rx_call_request(struct sk_buff *skb, struct net_device *dev, struct rose_neigh *neigh, unsigned int lci) diff --git a/net/sched/Kconfig b/net/sched/Kconfig index f24a6ae6819a..a01169fb5325 100644 --- a/net/sched/Kconfig +++ b/net/sched/Kconfig @@ -658,6 +658,18 @@ config NET_EMATCH_IPSET To compile this code as a module, choose M here: the module will be called em_ipset. +config NET_EMATCH_IPT + tristate "IPtables Matches" + depends on NET_EMATCH && NETFILTER && NETFILTER_XTABLES + ---help--- + Say Y here to be able to classify packets based on iptables + matches. + Current supported match is "policy" which allows packet classification + based on IPsec policy that was used during decapsulation + + To compile this code as a module, choose M here: the + module will be called em_ipt. + config NET_CLS_ACT bool "Actions" select NET_CLS diff --git a/net/sched/Makefile b/net/sched/Makefile index 5b635447e3f8..8811d3804878 100644 --- a/net/sched/Makefile +++ b/net/sched/Makefile @@ -75,3 +75,4 @@ obj-$(CONFIG_NET_EMATCH_META) += em_meta.o obj-$(CONFIG_NET_EMATCH_TEXT) += em_text.o obj-$(CONFIG_NET_EMATCH_CANID) += em_canid.o obj-$(CONFIG_NET_EMATCH_IPSET) += em_ipset.o +obj-$(CONFIG_NET_EMATCH_IPT) += em_ipt.o diff --git a/net/sched/act_api.c b/net/sched/act_api.c index eba6682727dd..a54fa7b8c217 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -202,7 +202,8 @@ nla_put_failure: int tcf_generic_walker(struct tc_action_net *tn, struct sk_buff *skb, struct netlink_callback *cb, int type, - const struct tc_action_ops *ops) + const struct tc_action_ops *ops, + struct netlink_ext_ack *extack) { struct tcf_idrinfo *idrinfo = tn->idrinfo; @@ -211,7 +212,8 @@ int tcf_generic_walker(struct tc_action_net *tn, struct sk_buff *skb, } else if (type == RTM_GETACTION) { return tcf_dump_walker(idrinfo, skb, cb); } else { - WARN(1, "tcf_generic_walker: unknown action %d\n", type); + WARN(1, "tcf_generic_walker: unknown command %d\n", type); + NL_SET_ERR_MSG(extack, "tcf_generic_walker: unknown command"); return -EINVAL; } } @@ -605,7 +607,8 @@ static struct tc_cookie *nla_memdup_cookie(struct nlattr **tb) struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp, struct nlattr *nla, struct nlattr *est, - char *name, int ovr, int bind) + char *name, int ovr, int bind, + struct netlink_ext_ack *extack) { struct tc_action *a; struct tc_action_ops *a_o; @@ -616,31 +619,40 @@ struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp, int err; if (name == NULL) { - err = nla_parse_nested(tb, TCA_ACT_MAX, nla, NULL, NULL); + err = nla_parse_nested(tb, TCA_ACT_MAX, nla, NULL, extack); if (err < 0) goto err_out; err = -EINVAL; kind = tb[TCA_ACT_KIND]; - if (kind == NULL) + if (!kind) { + NL_SET_ERR_MSG(extack, "TC action kind must be specified"); goto err_out; - if (nla_strlcpy(act_name, kind, IFNAMSIZ) >= IFNAMSIZ) + } + if (nla_strlcpy(act_name, kind, IFNAMSIZ) >= IFNAMSIZ) { + NL_SET_ERR_MSG(extack, "TC action name too long"); goto err_out; + } if (tb[TCA_ACT_COOKIE]) { int cklen = nla_len(tb[TCA_ACT_COOKIE]); - if (cklen > TC_COOKIE_MAX_SIZE) + if (cklen > TC_COOKIE_MAX_SIZE) { + NL_SET_ERR_MSG(extack, "TC cookie size above the maximum"); goto err_out; + } cookie = nla_memdup_cookie(tb); if (!cookie) { + NL_SET_ERR_MSG(extack, "No memory to generate TC cookie"); err = -ENOMEM; goto err_out; } } } else { - err = -EINVAL; - if (strlcpy(act_name, name, IFNAMSIZ) >= IFNAMSIZ) + if (strlcpy(act_name, name, IFNAMSIZ) >= IFNAMSIZ) { + NL_SET_ERR_MSG(extack, "TC action name too long"); + err = -EINVAL; goto err_out; + } } a_o = tc_lookup_action_n(act_name); @@ -663,15 +675,17 @@ struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp, goto err_mod; } #endif + NL_SET_ERR_MSG(extack, "Failed to load TC action module"); err = -ENOENT; goto err_out; } /* backward compatibility for policer */ if (name == NULL) - err = a_o->init(net, tb[TCA_ACT_OPTIONS], est, &a, ovr, bind); + err = a_o->init(net, tb[TCA_ACT_OPTIONS], est, &a, ovr, bind, + extack); else - err = a_o->init(net, nla, est, &a, ovr, bind); + err = a_o->init(net, nla, est, &a, ovr, bind, extack); if (err < 0) goto err_mod; @@ -697,6 +711,7 @@ struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp, list_add_tail(&a->list, &actions); tcf_action_destroy(&actions, bind); + NL_SET_ERR_MSG(extack, "Failed to init TC action chain"); return ERR_PTR(err); } } @@ -726,19 +741,20 @@ static void cleanup_a(struct list_head *actions, int ovr) int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla, struct nlattr *est, char *name, int ovr, int bind, - struct list_head *actions) + struct list_head *actions, struct netlink_ext_ack *extack) { struct nlattr *tb[TCA_ACT_MAX_PRIO + 1]; struct tc_action *act; int err; int i; - err = nla_parse_nested(tb, TCA_ACT_MAX_PRIO, nla, NULL, NULL); + err = nla_parse_nested(tb, TCA_ACT_MAX_PRIO, nla, NULL, extack); if (err < 0) return err; for (i = 1; i <= TCA_ACT_MAX_PRIO && tb[i]; i++) { - act = tcf_action_init_1(net, tp, tb[i], est, name, ovr, bind); + act = tcf_action_init_1(net, tp, tb[i], est, name, ovr, bind, + extack); if (IS_ERR(act)) { err = PTR_ERR(act); goto err; @@ -822,7 +838,7 @@ static int tca_get_fill(struct sk_buff *skb, struct list_head *actions, t->tca__pad2 = 0; nest = nla_nest_start(skb, TCA_ACT_TAB); - if (nest == NULL) + if (!nest) goto out_nlmsg_trim; if (tcf_action_dump(skb, actions, bind, ref) < 0) @@ -840,7 +856,8 @@ out_nlmsg_trim: static int tcf_get_notify(struct net *net, u32 portid, struct nlmsghdr *n, - struct list_head *actions, int event) + struct list_head *actions, int event, + struct netlink_ext_ack *extack) { struct sk_buff *skb; @@ -849,6 +866,7 @@ tcf_get_notify(struct net *net, u32 portid, struct nlmsghdr *n, return -ENOBUFS; if (tca_get_fill(skb, actions, portid, n->nlmsg_seq, 0, event, 0, 0) <= 0) { + NL_SET_ERR_MSG(extack, "Failed to fill netlink attributes while adding TC action"); kfree_skb(skb); return -EINVAL; } @@ -857,7 +875,8 @@ tcf_get_notify(struct net *net, u32 portid, struct nlmsghdr *n, } static struct tc_action *tcf_action_get_1(struct net *net, struct nlattr *nla, - struct nlmsghdr *n, u32 portid) + struct nlmsghdr *n, u32 portid, + struct netlink_ext_ack *extack) { struct nlattr *tb[TCA_ACT_MAX + 1]; const struct tc_action_ops *ops; @@ -865,22 +884,26 @@ static struct tc_action *tcf_action_get_1(struct net *net, struct nlattr *nla, int index; int err; - err = nla_parse_nested(tb, TCA_ACT_MAX, nla, NULL, NULL); + err = nla_parse_nested(tb, TCA_ACT_MAX, nla, NULL, extack); if (err < 0) goto err_out; err = -EINVAL; if (tb[TCA_ACT_INDEX] == NULL || - nla_len(tb[TCA_ACT_INDEX]) < sizeof(index)) + nla_len(tb[TCA_ACT_INDEX]) < sizeof(index)) { + NL_SET_ERR_MSG(extack, "Invalid TC action index value"); goto err_out; + } index = nla_get_u32(tb[TCA_ACT_INDEX]); err = -EINVAL; ops = tc_lookup_action(tb[TCA_ACT_KIND]); - if (!ops) /* could happen in batch of actions */ + if (!ops) { /* could happen in batch of actions */ + NL_SET_ERR_MSG(extack, "Specified TC action not found"); goto err_out; + } err = -ENOENT; - if (ops->lookup(net, &a, index) == 0) + if (ops->lookup(net, &a, index, extack) == 0) goto err_mod; module_put(ops->owner); @@ -893,7 +916,8 @@ err_out: } static int tca_action_flush(struct net *net, struct nlattr *nla, - struct nlmsghdr *n, u32 portid) + struct nlmsghdr *n, u32 portid, + struct netlink_ext_ack *extack) { struct sk_buff *skb; unsigned char *b; @@ -907,39 +931,45 @@ static int tca_action_flush(struct net *net, struct nlattr *nla, int err = -ENOMEM; skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); - if (!skb) { - pr_debug("tca_action_flush: failed skb alloc\n"); + if (!skb) return err; - } b = skb_tail_pointer(skb); - err = nla_parse_nested(tb, TCA_ACT_MAX, nla, NULL, NULL); + err = nla_parse_nested(tb, TCA_ACT_MAX, nla, NULL, extack); if (err < 0) goto err_out; err = -EINVAL; kind = tb[TCA_ACT_KIND]; ops = tc_lookup_action(kind); - if (!ops) /*some idjot trying to flush unknown action */ + if (!ops) { /*some idjot trying to flush unknown action */ + NL_SET_ERR_MSG(extack, "Cannot flush unknown TC action"); goto err_out; + } nlh = nlmsg_put(skb, portid, n->nlmsg_seq, RTM_DELACTION, sizeof(*t), 0); - if (!nlh) + if (!nlh) { + NL_SET_ERR_MSG(extack, "Failed to create TC action flush notification"); goto out_module_put; + } t = nlmsg_data(nlh); t->tca_family = AF_UNSPEC; t->tca__pad1 = 0; t->tca__pad2 = 0; nest = nla_nest_start(skb, TCA_ACT_TAB); - if (nest == NULL) + if (!nest) { + NL_SET_ERR_MSG(extack, "Failed to add new netlink message"); goto out_module_put; + } - err = ops->walk(net, skb, &dcb, RTM_DELACTION, ops); - if (err <= 0) + err = ops->walk(net, skb, &dcb, RTM_DELACTION, ops, extack); + if (err <= 0) { + nla_nest_cancel(skb, nest); goto out_module_put; + } nla_nest_end(skb, nest); @@ -950,6 +980,8 @@ static int tca_action_flush(struct net *net, struct nlattr *nla, n->nlmsg_flags & NLM_F_ECHO); if (err > 0) return 0; + if (err < 0) + NL_SET_ERR_MSG(extack, "Failed to send TC action flush notification"); return err; @@ -962,7 +994,7 @@ err_out: static int tcf_del_notify(struct net *net, struct nlmsghdr *n, struct list_head *actions, - u32 portid) + u32 portid, struct netlink_ext_ack *extack) { int ret; struct sk_buff *skb; @@ -973,6 +1005,7 @@ tcf_del_notify(struct net *net, struct nlmsghdr *n, struct list_head *actions, if (tca_get_fill(skb, actions, portid, n->nlmsg_seq, 0, RTM_DELACTION, 0, 1) <= 0) { + NL_SET_ERR_MSG(extack, "Failed to fill netlink TC action attributes"); kfree_skb(skb); return -EINVAL; } @@ -980,6 +1013,7 @@ tcf_del_notify(struct net *net, struct nlmsghdr *n, struct list_head *actions, /* now do the delete */ ret = tcf_action_destroy(actions, 0); if (ret < 0) { + NL_SET_ERR_MSG(extack, "Failed to delete TC action"); kfree_skb(skb); return ret; } @@ -993,26 +1027,27 @@ tcf_del_notify(struct net *net, struct nlmsghdr *n, struct list_head *actions, static int tca_action_gd(struct net *net, struct nlattr *nla, struct nlmsghdr *n, - u32 portid, int event) + u32 portid, int event, struct netlink_ext_ack *extack) { int i, ret; struct nlattr *tb[TCA_ACT_MAX_PRIO + 1]; struct tc_action *act; LIST_HEAD(actions); - ret = nla_parse_nested(tb, TCA_ACT_MAX_PRIO, nla, NULL, NULL); + ret = nla_parse_nested(tb, TCA_ACT_MAX_PRIO, nla, NULL, extack); if (ret < 0) return ret; if (event == RTM_DELACTION && n->nlmsg_flags & NLM_F_ROOT) { - if (tb[1] != NULL) - return tca_action_flush(net, tb[1], n, portid); - else - return -EINVAL; + if (tb[1]) + return tca_action_flush(net, tb[1], n, portid, extack); + + NL_SET_ERR_MSG(extack, "Invalid netlink attributes while flushing TC action"); + return -EINVAL; } for (i = 1; i <= TCA_ACT_MAX_PRIO && tb[i]; i++) { - act = tcf_action_get_1(net, tb[i], n, portid); + act = tcf_action_get_1(net, tb[i], n, portid, extack); if (IS_ERR(act)) { ret = PTR_ERR(act); goto err; @@ -1022,9 +1057,9 @@ tca_action_gd(struct net *net, struct nlattr *nla, struct nlmsghdr *n, } if (event == RTM_GETACTION) - ret = tcf_get_notify(net, portid, n, &actions, event); + ret = tcf_get_notify(net, portid, n, &actions, event, extack); else { /* delete */ - ret = tcf_del_notify(net, n, &actions, portid); + ret = tcf_del_notify(net, n, &actions, portid, extack); if (ret) goto err; return ret; @@ -1037,7 +1072,7 @@ err: static int tcf_add_notify(struct net *net, struct nlmsghdr *n, struct list_head *actions, - u32 portid) + u32 portid, struct netlink_ext_ack *extack) { struct sk_buff *skb; int err = 0; @@ -1048,6 +1083,7 @@ tcf_add_notify(struct net *net, struct nlmsghdr *n, struct list_head *actions, if (tca_get_fill(skb, actions, portid, n->nlmsg_seq, n->nlmsg_flags, RTM_NEWACTION, 0, 0) <= 0) { + NL_SET_ERR_MSG(extack, "Failed to fill netlink attributes while adding TC action"); kfree_skb(skb); return -EINVAL; } @@ -1060,16 +1096,18 @@ tcf_add_notify(struct net *net, struct nlmsghdr *n, struct list_head *actions, } static int tcf_action_add(struct net *net, struct nlattr *nla, - struct nlmsghdr *n, u32 portid, int ovr) + struct nlmsghdr *n, u32 portid, int ovr, + struct netlink_ext_ack *extack) { int ret = 0; LIST_HEAD(actions); - ret = tcf_action_init(net, NULL, nla, NULL, NULL, ovr, 0, &actions); + ret = tcf_action_init(net, NULL, nla, NULL, NULL, ovr, 0, &actions, + extack); if (ret) return ret; - return tcf_add_notify(net, n, &actions, portid); + return tcf_add_notify(net, n, &actions, portid, extack); } static u32 tcaa_root_flags_allowed = TCA_FLAG_LARGE_DUMP_ON; @@ -1097,7 +1135,7 @@ static int tc_ctl_action(struct sk_buff *skb, struct nlmsghdr *n, return ret; if (tca[TCA_ACT_TAB] == NULL) { - pr_notice("tc_ctl_action: received NO action attribs\n"); + NL_SET_ERR_MSG(extack, "Netlink action attributes missing"); return -EINVAL; } @@ -1113,17 +1151,18 @@ static int tc_ctl_action(struct sk_buff *skb, struct nlmsghdr *n, if (n->nlmsg_flags & NLM_F_REPLACE) ovr = 1; replay: - ret = tcf_action_add(net, tca[TCA_ACT_TAB], n, portid, ovr); + ret = tcf_action_add(net, tca[TCA_ACT_TAB], n, portid, ovr, + extack); if (ret == -EAGAIN) goto replay; break; case RTM_DELACTION: ret = tca_action_gd(net, tca[TCA_ACT_TAB], n, - portid, RTM_DELACTION); + portid, RTM_DELACTION, extack); break; case RTM_GETACTION: ret = tca_action_gd(net, tca[TCA_ACT_TAB], n, - portid, RTM_GETACTION); + portid, RTM_GETACTION, extack); break; default: BUG(); @@ -1218,7 +1257,7 @@ static int tc_dump_action(struct sk_buff *skb, struct netlink_callback *cb) if (nest == NULL) goto out_module_put; - ret = a_o->walk(net, skb, cb, RTM_GETACTION, a_o); + ret = a_o->walk(net, skb, cb, RTM_GETACTION, a_o, NULL); if (ret < 0) goto out_module_put; @@ -1454,6 +1493,7 @@ static struct pernet_operations tcf_action_net_ops = { .exit = tcf_action_net_exit, .id = &tcf_action_net_id, .size = sizeof(struct tcf_action_net), + .async = true, }; static int __init tc_action_init(void) diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c index b3f2c15affa7..da72e0cf2b1f 100644 --- a/net/sched/act_bpf.c +++ b/net/sched/act_bpf.c @@ -272,7 +272,7 @@ static void tcf_bpf_prog_fill_cfg(const struct tcf_bpf *prog, static int tcf_bpf_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **act, - int replace, int bind) + int replace, int bind, struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, bpf_net_id); struct nlattr *tb[TCA_ACT_BPF_MAX + 1]; @@ -367,14 +367,16 @@ static void tcf_bpf_cleanup(struct tc_action *act) static int tcf_bpf_walker(struct net *net, struct sk_buff *skb, struct netlink_callback *cb, int type, - const struct tc_action_ops *ops) + const struct tc_action_ops *ops, + struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, bpf_net_id); - return tcf_generic_walker(tn, skb, cb, type, ops); + return tcf_generic_walker(tn, skb, cb, type, ops, extack); } -static int tcf_bpf_search(struct net *net, struct tc_action **a, u32 index) +static int tcf_bpf_search(struct net *net, struct tc_action **a, u32 index, + struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, bpf_net_id); @@ -411,6 +413,7 @@ static struct pernet_operations bpf_net_ops = { .exit_batch = bpf_exit_net, .id = &bpf_net_id, .size = sizeof(struct tc_action_net), + .async = true, }; static int __init bpf_init_module(void) diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c index 2b15ba84e0c8..371e5e4ab3e2 100644 --- a/net/sched/act_connmark.c +++ b/net/sched/act_connmark.c @@ -96,7 +96,8 @@ static const struct nla_policy connmark_policy[TCA_CONNMARK_MAX + 1] = { static int tcf_connmark_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, - int ovr, int bind) + int ovr, int bind, + struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, connmark_net_id); struct nlattr *tb[TCA_CONNMARK_MAX + 1]; @@ -176,14 +177,16 @@ nla_put_failure: static int tcf_connmark_walker(struct net *net, struct sk_buff *skb, struct netlink_callback *cb, int type, - const struct tc_action_ops *ops) + const struct tc_action_ops *ops, + struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, connmark_net_id); - return tcf_generic_walker(tn, skb, cb, type, ops); + return tcf_generic_walker(tn, skb, cb, type, ops, extack); } -static int tcf_connmark_search(struct net *net, struct tc_action **a, u32 index) +static int tcf_connmark_search(struct net *net, struct tc_action **a, u32 index, + struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, connmark_net_id); @@ -219,6 +222,7 @@ static struct pernet_operations connmark_net_ops = { .exit_batch = connmark_exit_net, .id = &connmark_net_id, .size = sizeof(struct tc_action_net), + .async = true, }; static int __init connmark_init_module(void) diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c index b7ba9b06b147..1fb1f1f6a555 100644 --- a/net/sched/act_csum.c +++ b/net/sched/act_csum.c @@ -46,7 +46,7 @@ static struct tc_action_ops act_csum_ops; static int tcf_csum_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, int ovr, - int bind) + int bind, struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, csum_net_id); struct tcf_csum_params *params_old, *params_new; @@ -631,14 +631,16 @@ static void tcf_csum_cleanup(struct tc_action *a) static int tcf_csum_walker(struct net *net, struct sk_buff *skb, struct netlink_callback *cb, int type, - const struct tc_action_ops *ops) + const struct tc_action_ops *ops, + struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, csum_net_id); - return tcf_generic_walker(tn, skb, cb, type, ops); + return tcf_generic_walker(tn, skb, cb, type, ops, extack); } -static int tcf_csum_search(struct net *net, struct tc_action **a, u32 index) +static int tcf_csum_search(struct net *net, struct tc_action **a, u32 index, + struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, csum_net_id); @@ -675,6 +677,7 @@ static struct pernet_operations csum_net_ops = { .exit_batch = csum_exit_net, .id = &csum_net_id, .size = sizeof(struct tc_action_net), + .async = true, }; MODULE_DESCRIPTION("Checksum updating actions"); diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c index b56986d41c87..74563254e676 100644 --- a/net/sched/act_gact.c +++ b/net/sched/act_gact.c @@ -56,7 +56,7 @@ static const struct nla_policy gact_policy[TCA_GACT_MAX + 1] = { static int tcf_gact_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, - int ovr, int bind) + int ovr, int bind, struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, gact_net_id); struct nlattr *tb[TCA_GACT_MAX + 1]; @@ -201,14 +201,16 @@ nla_put_failure: static int tcf_gact_walker(struct net *net, struct sk_buff *skb, struct netlink_callback *cb, int type, - const struct tc_action_ops *ops) + const struct tc_action_ops *ops, + struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, gact_net_id); - return tcf_generic_walker(tn, skb, cb, type, ops); + return tcf_generic_walker(tn, skb, cb, type, ops, extack); } -static int tcf_gact_search(struct net *net, struct tc_action **a, u32 index) +static int tcf_gact_search(struct net *net, struct tc_action **a, u32 index, + struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, gact_net_id); @@ -245,6 +247,7 @@ static struct pernet_operations gact_net_ops = { .exit_batch = gact_exit_net, .id = &gact_net_id, .size = sizeof(struct tc_action_net), + .async = true, }; MODULE_AUTHOR("Jamal Hadi Salim(2002-4)"); diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c index 5954e992685a..555b1caeff72 100644 --- a/net/sched/act_ife.c +++ b/net/sched/act_ife.c @@ -447,7 +447,7 @@ static int populate_metalist(struct tcf_ife_info *ife, struct nlattr **tb, static int tcf_ife_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, - int ovr, int bind) + int ovr, int bind, struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, ife_net_id); struct nlattr *tb[TCA_IFE_MAX + 1]; @@ -824,14 +824,16 @@ static int tcf_ife_act(struct sk_buff *skb, const struct tc_action *a, static int tcf_ife_walker(struct net *net, struct sk_buff *skb, struct netlink_callback *cb, int type, - const struct tc_action_ops *ops) + const struct tc_action_ops *ops, + struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, ife_net_id); - return tcf_generic_walker(tn, skb, cb, type, ops); + return tcf_generic_walker(tn, skb, cb, type, ops, extack); } -static int tcf_ife_search(struct net *net, struct tc_action **a, u32 index) +static int tcf_ife_search(struct net *net, struct tc_action **a, u32 index, + struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, ife_net_id); @@ -868,6 +870,7 @@ static struct pernet_operations ife_net_ops = { .exit_batch = ife_exit_net, .id = &ife_net_id, .size = sizeof(struct tc_action_net), + .async = true, }; static int __init ife_init_module(void) diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c index 06e380ae0928..10866717f88e 100644 --- a/net/sched/act_ipt.c +++ b/net/sched/act_ipt.c @@ -193,7 +193,7 @@ err1: static int tcf_ipt_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, int ovr, - int bind) + int bind, struct netlink_ext_ack *extack) { return __tcf_ipt_init(net, ipt_net_id, nla, est, a, &act_ipt_ops, ovr, bind); @@ -201,7 +201,7 @@ static int tcf_ipt_init(struct net *net, struct nlattr *nla, static int tcf_xt_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, int ovr, - int bind) + int bind, struct netlink_ext_ack *extack) { return __tcf_ipt_init(net, xt_net_id, nla, est, a, &act_xt_ops, ovr, bind); @@ -303,14 +303,16 @@ nla_put_failure: static int tcf_ipt_walker(struct net *net, struct sk_buff *skb, struct netlink_callback *cb, int type, - const struct tc_action_ops *ops) + const struct tc_action_ops *ops, + struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, ipt_net_id); - return tcf_generic_walker(tn, skb, cb, type, ops); + return tcf_generic_walker(tn, skb, cb, type, ops, extack); } -static int tcf_ipt_search(struct net *net, struct tc_action **a, u32 index) +static int tcf_ipt_search(struct net *net, struct tc_action **a, u32 index, + struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, ipt_net_id); @@ -347,18 +349,21 @@ static struct pernet_operations ipt_net_ops = { .exit_batch = ipt_exit_net, .id = &ipt_net_id, .size = sizeof(struct tc_action_net), + .async = true, }; static int tcf_xt_walker(struct net *net, struct sk_buff *skb, struct netlink_callback *cb, int type, - const struct tc_action_ops *ops) + const struct tc_action_ops *ops, + struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, xt_net_id); - return tcf_generic_walker(tn, skb, cb, type, ops); + return tcf_generic_walker(tn, skb, cb, type, ops, extack); } -static int tcf_xt_search(struct net *net, struct tc_action **a, u32 index) +static int tcf_xt_search(struct net *net, struct tc_action **a, u32 index, + struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, xt_net_id); @@ -395,6 +400,7 @@ static struct pernet_operations xt_net_ops = { .exit_batch = xt_exit_net, .id = &xt_net_id, .size = sizeof(struct tc_action_net), + .async = true, }; MODULE_AUTHOR("Jamal Hadi Salim(2002-13)"); diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index e6ff88f72900..64c86579c3d9 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -69,7 +69,7 @@ static struct tc_action_ops act_mirred_ops; static int tcf_mirred_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, int ovr, - int bind) + int bind, struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, mirred_net_id); struct nlattr *tb[TCA_MIRRED_MAX + 1]; @@ -80,13 +80,17 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla, bool exists = false; int ret; - if (nla == NULL) + if (!nla) { + NL_SET_ERR_MSG_MOD(extack, "Mirred requires attributes to be passed"); return -EINVAL; - ret = nla_parse_nested(tb, TCA_MIRRED_MAX, nla, mirred_policy, NULL); + } + ret = nla_parse_nested(tb, TCA_MIRRED_MAX, nla, mirred_policy, extack); if (ret < 0) return ret; - if (tb[TCA_MIRRED_PARMS] == NULL) + if (!tb[TCA_MIRRED_PARMS]) { + NL_SET_ERR_MSG_MOD(extack, "Missing required mirred parameters"); return -EINVAL; + } parm = nla_data(tb[TCA_MIRRED_PARMS]); exists = tcf_idr_check(tn, parm->index, a, bind); @@ -102,6 +106,7 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla, default: if (exists) tcf_idr_release(*a, bind); + NL_SET_ERR_MSG_MOD(extack, "Unknown mirred option"); return -EINVAL; } if (parm->ifindex) { @@ -117,8 +122,10 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla, } if (!exists) { - if (dev == NULL) + if (!dev) { + NL_SET_ERR_MSG_MOD(extack, "Specified device does not exist"); return -EINVAL; + } ret = tcf_idr_create(tn, parm->index, est, a, &act_mirred_ops, bind, true); if (ret) @@ -265,14 +272,16 @@ nla_put_failure: static int tcf_mirred_walker(struct net *net, struct sk_buff *skb, struct netlink_callback *cb, int type, - const struct tc_action_ops *ops) + const struct tc_action_ops *ops, + struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, mirred_net_id); - return tcf_generic_walker(tn, skb, cb, type, ops); + return tcf_generic_walker(tn, skb, cb, type, ops, extack); } -static int tcf_mirred_search(struct net *net, struct tc_action **a, u32 index) +static int tcf_mirred_search(struct net *net, struct tc_action **a, u32 index, + struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, mirred_net_id); @@ -344,6 +353,7 @@ static struct pernet_operations mirred_net_ops = { .exit_batch = mirred_exit_net, .id = &mirred_net_id, .size = sizeof(struct tc_action_net), + .async = true, }; MODULE_AUTHOR("Jamal Hadi Salim(2002)"); diff --git a/net/sched/act_nat.c b/net/sched/act_nat.c index 98c6a4b2f523..b1bc757f6491 100644 --- a/net/sched/act_nat.c +++ b/net/sched/act_nat.c @@ -37,7 +37,8 @@ static const struct nla_policy nat_policy[TCA_NAT_MAX + 1] = { }; static int tcf_nat_init(struct net *net, struct nlattr *nla, struct nlattr *est, - struct tc_action **a, int ovr, int bind) + struct tc_action **a, int ovr, int bind, + struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, nat_net_id); struct nlattr *tb[TCA_NAT_MAX + 1]; @@ -277,14 +278,16 @@ nla_put_failure: static int tcf_nat_walker(struct net *net, struct sk_buff *skb, struct netlink_callback *cb, int type, - const struct tc_action_ops *ops) + const struct tc_action_ops *ops, + struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, nat_net_id); - return tcf_generic_walker(tn, skb, cb, type, ops); + return tcf_generic_walker(tn, skb, cb, type, ops, extack); } -static int tcf_nat_search(struct net *net, struct tc_action **a, u32 index) +static int tcf_nat_search(struct net *net, struct tc_action **a, u32 index, + struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, nat_net_id); @@ -320,6 +323,7 @@ static struct pernet_operations nat_net_ops = { .exit_batch = nat_exit_net, .id = &nat_net_id, .size = sizeof(struct tc_action_net), + .async = true, }; MODULE_DESCRIPTION("Stateless NAT actions"); diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c index 349beaffb29e..5e8cc8f63acd 100644 --- a/net/sched/act_pedit.c +++ b/net/sched/act_pedit.c @@ -132,7 +132,7 @@ static int tcf_pedit_key_ex_dump(struct sk_buff *skb, static int tcf_pedit_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, - int ovr, int bind) + int ovr, int bind, struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, pedit_net_id); struct nlattr *tb[TCA_PEDIT_MAX + 1]; @@ -419,14 +419,16 @@ nla_put_failure: static int tcf_pedit_walker(struct net *net, struct sk_buff *skb, struct netlink_callback *cb, int type, - const struct tc_action_ops *ops) + const struct tc_action_ops *ops, + struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, pedit_net_id); - return tcf_generic_walker(tn, skb, cb, type, ops); + return tcf_generic_walker(tn, skb, cb, type, ops, extack); } -static int tcf_pedit_search(struct net *net, struct tc_action **a, u32 index) +static int tcf_pedit_search(struct net *net, struct tc_action **a, u32 index, + struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, pedit_net_id); @@ -463,6 +465,7 @@ static struct pernet_operations pedit_net_ops = { .exit_batch = pedit_exit_net, .id = &pedit_net_id, .size = sizeof(struct tc_action_net), + .async = true, }; MODULE_AUTHOR("Jamal Hadi Salim(2002-4)"); diff --git a/net/sched/act_police.c b/net/sched/act_police.c index 95d3c9097b25..51fe4fe343f7 100644 --- a/net/sched/act_police.c +++ b/net/sched/act_police.c @@ -58,11 +58,12 @@ static struct tc_action_ops act_police_ops; static int tcf_act_police_walker(struct net *net, struct sk_buff *skb, struct netlink_callback *cb, int type, - const struct tc_action_ops *ops) + const struct tc_action_ops *ops, + struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, police_net_id); - return tcf_generic_walker(tn, skb, cb, type, ops); + return tcf_generic_walker(tn, skb, cb, type, ops, extack); } static const struct nla_policy police_policy[TCA_POLICE_MAX + 1] = { @@ -74,7 +75,8 @@ static const struct nla_policy police_policy[TCA_POLICE_MAX + 1] = { static int tcf_act_police_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, - int ovr, int bind) + int ovr, int bind, + struct netlink_ext_ack *extack) { int ret = 0, err; struct nlattr *tb[TCA_POLICE_MAX + 1]; @@ -304,7 +306,8 @@ nla_put_failure: return -1; } -static int tcf_police_search(struct net *net, struct tc_action **a, u32 index) +static int tcf_police_search(struct net *net, struct tc_action **a, u32 index, + struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, police_net_id); @@ -344,6 +347,7 @@ static struct pernet_operations police_net_ops = { .exit_batch = police_exit_net, .id = &police_net_id, .size = sizeof(struct tc_action_net), + .async = true, }; static int __init police_init_module(void) diff --git a/net/sched/act_sample.c b/net/sched/act_sample.c index 1ba0df238756..238dfd27e995 100644 --- a/net/sched/act_sample.c +++ b/net/sched/act_sample.c @@ -37,7 +37,7 @@ static const struct nla_policy sample_policy[TCA_SAMPLE_MAX + 1] = { static int tcf_sample_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, int ovr, - int bind) + int bind, struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, sample_net_id); struct nlattr *tb[TCA_SAMPLE_MAX + 1]; @@ -202,14 +202,16 @@ nla_put_failure: static int tcf_sample_walker(struct net *net, struct sk_buff *skb, struct netlink_callback *cb, int type, - const struct tc_action_ops *ops) + const struct tc_action_ops *ops, + struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, sample_net_id); - return tcf_generic_walker(tn, skb, cb, type, ops); + return tcf_generic_walker(tn, skb, cb, type, ops, extack); } -static int tcf_sample_search(struct net *net, struct tc_action **a, u32 index) +static int tcf_sample_search(struct net *net, struct tc_action **a, u32 index, + struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, sample_net_id); @@ -246,6 +248,7 @@ static struct pernet_operations sample_net_ops = { .exit_batch = sample_exit_net, .id = &sample_net_id, .size = sizeof(struct tc_action_net), + .async = true, }; static int __init sample_init_module(void) diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c index 425eac11f6da..91816d73f3f3 100644 --- a/net/sched/act_simple.c +++ b/net/sched/act_simple.c @@ -79,7 +79,7 @@ static const struct nla_policy simple_policy[TCA_DEF_MAX + 1] = { static int tcf_simp_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, - int ovr, int bind) + int ovr, int bind, struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, simp_net_id); struct nlattr *tb[TCA_DEF_MAX + 1]; @@ -170,14 +170,16 @@ nla_put_failure: static int tcf_simp_walker(struct net *net, struct sk_buff *skb, struct netlink_callback *cb, int type, - const struct tc_action_ops *ops) + const struct tc_action_ops *ops, + struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, simp_net_id); - return tcf_generic_walker(tn, skb, cb, type, ops); + return tcf_generic_walker(tn, skb, cb, type, ops, extack); } -static int tcf_simp_search(struct net *net, struct tc_action **a, u32 index) +static int tcf_simp_search(struct net *net, struct tc_action **a, u32 index, + struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, simp_net_id); @@ -214,6 +216,7 @@ static struct pernet_operations simp_net_ops = { .exit_batch = simp_exit_net, .id = &simp_net_id, .size = sizeof(struct tc_action_net), + .async = true, }; MODULE_AUTHOR("Jamal Hadi Salim(2005)"); diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c index 5a3f691bb545..7971510fe61b 100644 --- a/net/sched/act_skbedit.c +++ b/net/sched/act_skbedit.c @@ -66,7 +66,7 @@ static const struct nla_policy skbedit_policy[TCA_SKBEDIT_MAX + 1] = { static int tcf_skbedit_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, - int ovr, int bind) + int ovr, int bind, struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, skbedit_net_id); struct nlattr *tb[TCA_SKBEDIT_MAX + 1]; @@ -208,14 +208,16 @@ nla_put_failure: static int tcf_skbedit_walker(struct net *net, struct sk_buff *skb, struct netlink_callback *cb, int type, - const struct tc_action_ops *ops) + const struct tc_action_ops *ops, + struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, skbedit_net_id); - return tcf_generic_walker(tn, skb, cb, type, ops); + return tcf_generic_walker(tn, skb, cb, type, ops, extack); } -static int tcf_skbedit_search(struct net *net, struct tc_action **a, u32 index) +static int tcf_skbedit_search(struct net *net, struct tc_action **a, u32 index, + struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, skbedit_net_id); @@ -251,6 +253,7 @@ static struct pernet_operations skbedit_net_ops = { .exit_batch = skbedit_exit_net, .id = &skbedit_net_id, .size = sizeof(struct tc_action_net), + .async = true, }; MODULE_AUTHOR("Alexander Duyck, <alexander.h.duyck@intel.com>"); diff --git a/net/sched/act_skbmod.c b/net/sched/act_skbmod.c index fa975262dbac..febec75f4f7a 100644 --- a/net/sched/act_skbmod.c +++ b/net/sched/act_skbmod.c @@ -84,7 +84,7 @@ static const struct nla_policy skbmod_policy[TCA_SKBMOD_MAX + 1] = { static int tcf_skbmod_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, - int ovr, int bind) + int ovr, int bind, struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, skbmod_net_id); struct nlattr *tb[TCA_SKBMOD_MAX + 1]; @@ -232,14 +232,16 @@ nla_put_failure: static int tcf_skbmod_walker(struct net *net, struct sk_buff *skb, struct netlink_callback *cb, int type, - const struct tc_action_ops *ops) + const struct tc_action_ops *ops, + struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, skbmod_net_id); - return tcf_generic_walker(tn, skb, cb, type, ops); + return tcf_generic_walker(tn, skb, cb, type, ops, extack); } -static int tcf_skbmod_search(struct net *net, struct tc_action **a, u32 index) +static int tcf_skbmod_search(struct net *net, struct tc_action **a, u32 index, + struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, skbmod_net_id); @@ -276,6 +278,7 @@ static struct pernet_operations skbmod_net_ops = { .exit_batch = skbmod_exit_net, .id = &skbmod_net_id, .size = sizeof(struct tc_action_net), + .async = true, }; MODULE_AUTHOR("Jamal Hadi Salim, <jhs@mojatatu.com>"); diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c index 0e23aac09ad6..9169b7e78ada 100644 --- a/net/sched/act_tunnel_key.c +++ b/net/sched/act_tunnel_key.c @@ -70,7 +70,7 @@ static const struct nla_policy tunnel_key_policy[TCA_TUNNEL_KEY_MAX + 1] = { static int tunnel_key_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, - int ovr, int bind) + int ovr, int bind, struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, tunnel_key_net_id); struct nlattr *tb[TCA_TUNNEL_KEY_MAX + 1]; @@ -291,14 +291,16 @@ nla_put_failure: static int tunnel_key_walker(struct net *net, struct sk_buff *skb, struct netlink_callback *cb, int type, - const struct tc_action_ops *ops) + const struct tc_action_ops *ops, + struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, tunnel_key_net_id); - return tcf_generic_walker(tn, skb, cb, type, ops); + return tcf_generic_walker(tn, skb, cb, type, ops, extack); } -static int tunnel_key_search(struct net *net, struct tc_action **a, u32 index) +static int tunnel_key_search(struct net *net, struct tc_action **a, u32 index, + struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, tunnel_key_net_id); @@ -335,6 +337,7 @@ static struct pernet_operations tunnel_key_net_ops = { .exit_batch = tunnel_key_exit_net, .id = &tunnel_key_net_id, .size = sizeof(struct tc_action_net), + .async = true, }; static int __init tunnel_key_init_module(void) diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c index e1a1b3f3983a..c2ee7fd51cc9 100644 --- a/net/sched/act_vlan.c +++ b/net/sched/act_vlan.c @@ -109,7 +109,7 @@ static const struct nla_policy vlan_policy[TCA_VLAN_MAX + 1] = { static int tcf_vlan_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, - int ovr, int bind) + int ovr, int bind, struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, vlan_net_id); struct nlattr *tb[TCA_VLAN_MAX + 1]; @@ -267,14 +267,16 @@ nla_put_failure: static int tcf_vlan_walker(struct net *net, struct sk_buff *skb, struct netlink_callback *cb, int type, - const struct tc_action_ops *ops) + const struct tc_action_ops *ops, + struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, vlan_net_id); - return tcf_generic_walker(tn, skb, cb, type, ops); + return tcf_generic_walker(tn, skb, cb, type, ops, extack); } -static int tcf_vlan_search(struct net *net, struct tc_action **a, u32 index) +static int tcf_vlan_search(struct net *net, struct tc_action **a, u32 index, + struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, vlan_net_id); @@ -311,6 +313,7 @@ static struct pernet_operations vlan_net_ops = { .exit_batch = vlan_exit_net, .id = &vlan_net_id, .size = sizeof(struct tc_action_net), + .async = true, }; static int __init vlan_init_module(void) diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 247b7cc20c13..19f9f421d5b7 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -1437,7 +1437,7 @@ int tcf_exts_validate(struct net *net, struct tcf_proto *tp, struct nlattr **tb, if (exts->police && tb[exts->police]) { act = tcf_action_init_1(net, tp, tb[exts->police], rate_tlv, "police", ovr, - TCA_ACT_BIND); + TCA_ACT_BIND, extack); if (IS_ERR(act)) return PTR_ERR(act); @@ -1450,7 +1450,7 @@ int tcf_exts_validate(struct net *net, struct tcf_proto *tp, struct nlattr **tb, err = tcf_action_init(net, tp, tb[exts->action], rate_tlv, NULL, ovr, TCA_ACT_BIND, - &actions); + &actions, extack); if (err) return err; list_for_each_entry(act, &actions, list) @@ -1618,6 +1618,7 @@ static struct pernet_operations tcf_net_ops = { .exit = tcf_net_exit, .id = &tcf_net_id, .size = sizeof(struct tcf_net), + .async = true, }; static int __init tc_filter_init(void) diff --git a/net/sched/em_ipt.c b/net/sched/em_ipt.c new file mode 100644 index 000000000000..a5f34e930eff --- /dev/null +++ b/net/sched/em_ipt.c @@ -0,0 +1,257 @@ +/* + * net/sched/em_ipt.c IPtables matches Ematch + * + * (c) 2018 Eyal Birger <eyal.birger@gmail.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/gfp.h> +#include <linux/module.h> +#include <linux/types.h> +#include <linux/kernel.h> +#include <linux/string.h> +#include <linux/skbuff.h> +#include <linux/tc_ematch/tc_em_ipt.h> +#include <linux/netfilter.h> +#include <linux/netfilter/x_tables.h> +#include <linux/netfilter_ipv4/ip_tables.h> +#include <linux/netfilter_ipv6/ip6_tables.h> +#include <net/pkt_cls.h> + +struct em_ipt_match { + const struct xt_match *match; + u32 hook; + u8 match_data[0] __aligned(8); +}; + +struct em_ipt_xt_match { + char *match_name; + int (*validate_match_data)(struct nlattr **tb, u8 mrev); +}; + +static const struct nla_policy em_ipt_policy[TCA_EM_IPT_MAX + 1] = { + [TCA_EM_IPT_MATCH_NAME] = { .type = NLA_STRING, + .len = XT_EXTENSION_MAXNAMELEN }, + [TCA_EM_IPT_MATCH_REVISION] = { .type = NLA_U8 }, + [TCA_EM_IPT_HOOK] = { .type = NLA_U32 }, + [TCA_EM_IPT_NFPROTO] = { .type = NLA_U8 }, + [TCA_EM_IPT_MATCH_DATA] = { .type = NLA_UNSPEC }, +}; + +static int check_match(struct net *net, struct em_ipt_match *im, int mdata_len) +{ + struct xt_mtchk_param mtpar = {}; + union { + struct ipt_entry e4; + struct ip6t_entry e6; + } e = {}; + + mtpar.net = net; + mtpar.table = "filter"; + mtpar.hook_mask = 1 << im->hook; + mtpar.family = im->match->family; + mtpar.match = im->match; + mtpar.entryinfo = &e; + mtpar.matchinfo = (void *)im->match_data; + return xt_check_match(&mtpar, mdata_len, 0, 0); +} + +static int policy_validate_match_data(struct nlattr **tb, u8 mrev) +{ + if (mrev != 0) { + pr_err("only policy match revision 0 supported"); + return -EINVAL; + } + + if (nla_get_u32(tb[TCA_EM_IPT_HOOK]) != NF_INET_PRE_ROUTING) { + pr_err("policy can only be matched on NF_INET_PRE_ROUTING"); + return -EINVAL; + } + + return 0; +} + +static const struct em_ipt_xt_match em_ipt_xt_matches[] = { + { + .match_name = "policy", + .validate_match_data = policy_validate_match_data + }, + {} +}; + +static struct xt_match *get_xt_match(struct nlattr **tb) +{ + const struct em_ipt_xt_match *m; + struct nlattr *mname_attr; + u8 nfproto, mrev = 0; + int ret; + + mname_attr = tb[TCA_EM_IPT_MATCH_NAME]; + for (m = em_ipt_xt_matches; m->match_name; m++) { + if (!nla_strcmp(mname_attr, m->match_name)) + break; + } + + if (!m->match_name) { + pr_err("Unsupported xt match"); + return ERR_PTR(-EINVAL); + } + + if (tb[TCA_EM_IPT_MATCH_REVISION]) + mrev = nla_get_u8(tb[TCA_EM_IPT_MATCH_REVISION]); + + ret = m->validate_match_data(tb, mrev); + if (ret < 0) + return ERR_PTR(ret); + + nfproto = nla_get_u8(tb[TCA_EM_IPT_NFPROTO]); + return xt_request_find_match(nfproto, m->match_name, mrev); +} + +static int em_ipt_change(struct net *net, void *data, int data_len, + struct tcf_ematch *em) +{ + struct nlattr *tb[TCA_EM_IPT_MAX + 1]; + struct em_ipt_match *im = NULL; + struct xt_match *match; + int mdata_len, ret; + + ret = nla_parse(tb, TCA_EM_IPT_MAX, data, data_len, em_ipt_policy, + NULL); + if (ret < 0) + return ret; + + if (!tb[TCA_EM_IPT_HOOK] || !tb[TCA_EM_IPT_MATCH_NAME] || + !tb[TCA_EM_IPT_MATCH_DATA] || !tb[TCA_EM_IPT_NFPROTO]) + return -EINVAL; + + match = get_xt_match(tb); + if (IS_ERR(match)) { + pr_err("unable to load match\n"); + return PTR_ERR(match); + } + + mdata_len = XT_ALIGN(nla_len(tb[TCA_EM_IPT_MATCH_DATA])); + im = kzalloc(sizeof(*im) + mdata_len, GFP_KERNEL); + if (!im) { + ret = -ENOMEM; + goto err; + } + + im->match = match; + im->hook = nla_get_u32(tb[TCA_EM_IPT_HOOK]); + nla_memcpy(im->match_data, tb[TCA_EM_IPT_MATCH_DATA], mdata_len); + + ret = check_match(net, im, mdata_len); + if (ret) + goto err; + + em->datalen = sizeof(*im) + mdata_len; + em->data = (unsigned long)im; + return 0; + +err: + kfree(im); + module_put(match->me); + return ret; +} + +static void em_ipt_destroy(struct tcf_ematch *em) +{ + struct em_ipt_match *im = (void *)em->data; + + if (!im) + return; + + if (im->match->destroy) { + struct xt_mtdtor_param par = { + .net = em->net, + .match = im->match, + .matchinfo = im->match_data, + .family = im->match->family + }; + im->match->destroy(&par); + } + module_put(im->match->me); + kfree((void *)im); +} + +static int em_ipt_match(struct sk_buff *skb, struct tcf_ematch *em, + struct tcf_pkt_info *info) +{ + const struct em_ipt_match *im = (const void *)em->data; + struct xt_action_param acpar = {}; + struct net_device *indev = NULL; + struct nf_hook_state state; + int ret; + + rcu_read_lock(); + + if (skb->skb_iif) + indev = dev_get_by_index_rcu(em->net, skb->skb_iif); + + nf_hook_state_init(&state, im->hook, im->match->family, + indev ?: skb->dev, skb->dev, NULL, em->net, NULL); + + acpar.match = im->match; + acpar.matchinfo = im->match_data; + acpar.state = &state; + + ret = im->match->match(skb, &acpar); + + rcu_read_unlock(); + return ret; +} + +static int em_ipt_dump(struct sk_buff *skb, struct tcf_ematch *em) +{ + struct em_ipt_match *im = (void *)em->data; + + if (nla_put_string(skb, TCA_EM_IPT_MATCH_NAME, im->match->name) < 0) + return -EMSGSIZE; + if (nla_put_u32(skb, TCA_EM_IPT_HOOK, im->hook) < 0) + return -EMSGSIZE; + if (nla_put_u8(skb, TCA_EM_IPT_MATCH_REVISION, im->match->revision) < 0) + return -EMSGSIZE; + if (nla_put_u8(skb, TCA_EM_IPT_NFPROTO, im->match->family) < 0) + return -EMSGSIZE; + if (nla_put(skb, TCA_EM_IPT_MATCH_DATA, + im->match->usersize ?: im->match->matchsize, + im->match_data) < 0) + return -EMSGSIZE; + + return 0; +} + +static struct tcf_ematch_ops em_ipt_ops = { + .kind = TCF_EM_IPT, + .change = em_ipt_change, + .destroy = em_ipt_destroy, + .match = em_ipt_match, + .dump = em_ipt_dump, + .owner = THIS_MODULE, + .link = LIST_HEAD_INIT(em_ipt_ops.link) +}; + +static int __init init_em_ipt(void) +{ + return tcf_em_register(&em_ipt_ops); +} + +static void __exit exit_em_ipt(void) +{ + tcf_em_unregister(&em_ipt_ops); +} + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Eyal Birger <eyal.birger@gmail.com>"); +MODULE_DESCRIPTION("TC extended match for IPtables matches"); + +module_init(init_em_ipt); +module_exit(exit_em_ipt); + +MODULE_ALIAS_TCF_EMATCH(TCF_EM_IPT); diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index d512f49ee83c..68f9d942bed4 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -739,6 +739,7 @@ static u32 qdisc_alloc_handle(struct net_device *dev) void qdisc_tree_reduce_backlog(struct Qdisc *sch, unsigned int n, unsigned int len) { + bool qdisc_is_offloaded = sch->flags & TCQ_F_OFFLOADED; const struct Qdisc_class_ops *cops; unsigned long cl; u32 parentid; @@ -760,8 +761,12 @@ void qdisc_tree_reduce_backlog(struct Qdisc *sch, unsigned int n, * If child was empty even before update then backlog * counter is screwed and we skip notification because * parent class is already passive. + * + * If the original child was offloaded then it is allowed + * to be seem as empty, so the parent is notified anyway. */ - notify = !sch->q.qlen && !WARN_ON_ONCE(!n); + notify = !sch->q.qlen && !WARN_ON_ONCE(!n && + !qdisc_is_offloaded); /* TODO: perform the search on a per txq basis */ sch = qdisc_lookup(qdisc_dev(sch), TC_H_MAJ(parentid)); if (sch == NULL) { @@ -2128,6 +2133,7 @@ static void __net_exit psched_net_exit(struct net *net) static struct pernet_operations psched_net_ops = { .init = psched_net_init, .exit = psched_net_exit, + .async = true, }; static int __init pktsched_init(void) diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c index efbf51f35778..222e53d3d27a 100644 --- a/net/sched/sch_prio.c +++ b/net/sched/sch_prio.c @@ -142,9 +142,8 @@ prio_reset(struct Qdisc *sch) sch->q.qlen = 0; } -static int prio_offload(struct Qdisc *sch, bool enable) +static int prio_offload(struct Qdisc *sch, struct tc_prio_qopt *qopt) { - struct prio_sched_data *q = qdisc_priv(sch); struct net_device *dev = qdisc_dev(sch); struct tc_prio_qopt_offload opt = { .handle = sch->handle, @@ -154,10 +153,10 @@ static int prio_offload(struct Qdisc *sch, bool enable) if (!tc_can_offload(dev) || !dev->netdev_ops->ndo_setup_tc) return -EOPNOTSUPP; - if (enable) { + if (qopt) { opt.command = TC_PRIO_REPLACE; - opt.replace_params.bands = q->bands; - memcpy(&opt.replace_params.priomap, q->prio2band, + opt.replace_params.bands = qopt->bands; + memcpy(&opt.replace_params.priomap, qopt->priomap, TC_PRIO_MAX + 1); opt.replace_params.qstats = &sch->qstats; } else { @@ -174,7 +173,7 @@ prio_destroy(struct Qdisc *sch) struct prio_sched_data *q = qdisc_priv(sch); tcf_block_put(q->block); - prio_offload(sch, false); + prio_offload(sch, NULL); for (prio = 0; prio < q->bands; prio++) qdisc_destroy(q->queues[prio]); } @@ -211,6 +210,7 @@ static int prio_tune(struct Qdisc *sch, struct nlattr *opt, } } + prio_offload(sch, qopt); sch_tree_lock(sch); q->bands = qopt->bands; memcpy(q->prio2band, qopt->priomap, TC_PRIO_MAX+1); @@ -230,7 +230,6 @@ static int prio_tune(struct Qdisc *sch, struct nlattr *opt, } sch_tree_unlock(sch); - prio_offload(sch, true); return 0; } @@ -309,12 +308,44 @@ static int prio_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new, struct Qdisc **old, struct netlink_ext_ack *extack) { struct prio_sched_data *q = qdisc_priv(sch); + struct tc_prio_qopt_offload graft_offload; + struct net_device *dev = qdisc_dev(sch); unsigned long band = arg - 1; + bool any_qdisc_is_offloaded; + int err; if (new == NULL) new = &noop_qdisc; *old = qdisc_replace(sch, new, &q->queues[band]); + + if (!tc_can_offload(dev)) + return 0; + + graft_offload.handle = sch->handle; + graft_offload.parent = sch->parent; + graft_offload.graft_params.band = band; + graft_offload.graft_params.child_handle = new->handle; + graft_offload.command = TC_PRIO_GRAFT; + + err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_QDISC_PRIO, + &graft_offload); + + /* Don't report error if the graft is part of destroy operation. */ + if (err && new != &noop_qdisc) { + /* Don't report error if the parent, the old child and the new + * one are not offloaded. + */ + any_qdisc_is_offloaded = sch->flags & TCQ_F_OFFLOADED; + any_qdisc_is_offloaded |= new->flags & TCQ_F_OFFLOADED; + if (*old) + any_qdisc_is_offloaded |= (*old)->flags & + TCQ_F_OFFLOADED; + + if (any_qdisc_is_offloaded) + NL_SET_ERR_MSG(extack, "Offloading graft operation failed."); + } + return 0; } diff --git a/net/sctp/Makefile b/net/sctp/Makefile index 6776582ec449..e845e4588535 100644 --- a/net/sctp/Makefile +++ b/net/sctp/Makefile @@ -15,6 +15,8 @@ sctp-y := sm_statetable.o sm_statefuns.o sm_sideeffect.o \ offload.o stream_sched.o stream_sched_prio.o \ stream_sched_rr.o stream_interleave.o +sctp_diag-y := diag.o + sctp-$(CONFIG_SCTP_DBG_OBJCNT) += objcnt.o sctp-$(CONFIG_PROC_FS) += proc.o sctp-$(CONFIG_SYSCTL) += sysctl.o diff --git a/net/sctp/sctp_diag.c b/net/sctp/diag.c index a72a7d925d46..078f01a8d582 100644 --- a/net/sctp/sctp_diag.c +++ b/net/sctp/diag.c @@ -1,3 +1,34 @@ +/* SCTP kernel implementation + * (C) Copyright Red Hat Inc. 2017 + * + * This file is part of the SCTP kernel implementation + * + * These functions implement sctp diag support. + * + * This SCTP implementation 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, or (at your option) + * any later version. + * + * This SCTP implementation 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 GNU CC; see the file COPYING. If not, see + * <http://www.gnu.org/licenses/>. + * + * Please send any bug reports or fixes you make to the + * email addresched(es): + * lksctp developers <linux-sctp@vger.kernel.org> + * + * Written or modified by: + * Xin Long <lucien.xin@gmail.com> + */ + #include <linux/module.h> #include <linux/inet_diag.h> #include <linux/sock_diag.h> diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index e35d4f73d2df..0d873c58e516 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -952,16 +952,16 @@ static int sctp_inet6_supported_addrs(const struct sctp_sock *opt, /* Handle SCTP_I_WANT_MAPPED_V4_ADDR for getpeername() and getsockname() */ static int sctp_getname(struct socket *sock, struct sockaddr *uaddr, - int *uaddr_len, int peer) + int peer) { int rc; - rc = inet6_getname(sock, uaddr, uaddr_len, peer); + rc = inet6_getname(sock, uaddr, peer); - if (rc != 0) + if (rc < 0) return rc; - *uaddr_len = sctp_v6_addr_to_user(sctp_sk(sock->sk), + rc = sctp_v6_addr_to_user(sctp_sk(sock->sk), (union sctp_addr *)uaddr); return rc; diff --git a/net/sctp/socket.c b/net/sctp/socket.c index bf271f8c2dc9..7fa76031bb08 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -1606,396 +1606,214 @@ static int sctp_error(struct sock *sk, int flags, int err) static int sctp_msghdr_parse(const struct msghdr *msg, struct sctp_cmsgs *cmsgs); -static int sctp_sendmsg(struct sock *sk, struct msghdr *msg, size_t msg_len) +static int sctp_sendmsg_parse(struct sock *sk, struct sctp_cmsgs *cmsgs, + struct sctp_sndrcvinfo *srinfo, + const struct msghdr *msg, size_t msg_len) { - struct net *net = sock_net(sk); - struct sctp_sock *sp; - struct sctp_endpoint *ep; - struct sctp_association *new_asoc = NULL, *asoc = NULL; - struct sctp_transport *transport, *chunk_tp; - struct sctp_chunk *chunk; - union sctp_addr to; - struct sockaddr *msg_name = NULL; - struct sctp_sndrcvinfo default_sinfo; - struct sctp_sndrcvinfo *sinfo; - struct sctp_initmsg *sinit; - sctp_assoc_t associd = 0; - struct sctp_cmsgs cmsgs = { NULL }; - enum sctp_scope scope; - bool fill_sinfo_ttl = false, wait_connect = false; - struct sctp_datamsg *datamsg; - int msg_flags = msg->msg_flags; - __u16 sinfo_flags = 0; - long timeo; + __u16 sflags; int err; - err = 0; - sp = sctp_sk(sk); - ep = sp->ep; - - pr_debug("%s: sk:%p, msg:%p, msg_len:%zu ep:%p\n", __func__, sk, - msg, msg_len, ep); + if (sctp_sstate(sk, LISTENING) && sctp_style(sk, TCP)) + return -EPIPE; - /* We cannot send a message over a TCP-style listening socket. */ - if (sctp_style(sk, TCP) && sctp_sstate(sk, LISTENING)) { - err = -EPIPE; - goto out_nounlock; - } + if (msg_len > sk->sk_sndbuf) + return -EMSGSIZE; - /* Parse out the SCTP CMSGs. */ - err = sctp_msghdr_parse(msg, &cmsgs); + memset(cmsgs, 0, sizeof(*cmsgs)); + err = sctp_msghdr_parse(msg, cmsgs); if (err) { pr_debug("%s: msghdr parse err:%x\n", __func__, err); - goto out_nounlock; + return err; } - /* Fetch the destination address for this packet. This - * address only selects the association--it is not necessarily - * the address we will send to. - * For a peeled-off socket, msg_name is ignored. - */ - if (!sctp_style(sk, UDP_HIGH_BANDWIDTH) && msg->msg_name) { - int msg_namelen = msg->msg_namelen; - - err = sctp_verify_addr(sk, (union sctp_addr *)msg->msg_name, - msg_namelen); - if (err) - return err; + memset(srinfo, 0, sizeof(*srinfo)); + if (cmsgs->srinfo) { + srinfo->sinfo_stream = cmsgs->srinfo->sinfo_stream; + srinfo->sinfo_flags = cmsgs->srinfo->sinfo_flags; + srinfo->sinfo_ppid = cmsgs->srinfo->sinfo_ppid; + srinfo->sinfo_context = cmsgs->srinfo->sinfo_context; + srinfo->sinfo_assoc_id = cmsgs->srinfo->sinfo_assoc_id; + srinfo->sinfo_timetolive = cmsgs->srinfo->sinfo_timetolive; + } - if (msg_namelen > sizeof(to)) - msg_namelen = sizeof(to); - memcpy(&to, msg->msg_name, msg_namelen); - msg_name = msg->msg_name; + if (cmsgs->sinfo) { + srinfo->sinfo_stream = cmsgs->sinfo->snd_sid; + srinfo->sinfo_flags = cmsgs->sinfo->snd_flags; + srinfo->sinfo_ppid = cmsgs->sinfo->snd_ppid; + srinfo->sinfo_context = cmsgs->sinfo->snd_context; + srinfo->sinfo_assoc_id = cmsgs->sinfo->snd_assoc_id; } - sinit = cmsgs.init; - if (cmsgs.sinfo != NULL) { - memset(&default_sinfo, 0, sizeof(default_sinfo)); - default_sinfo.sinfo_stream = cmsgs.sinfo->snd_sid; - default_sinfo.sinfo_flags = cmsgs.sinfo->snd_flags; - default_sinfo.sinfo_ppid = cmsgs.sinfo->snd_ppid; - default_sinfo.sinfo_context = cmsgs.sinfo->snd_context; - default_sinfo.sinfo_assoc_id = cmsgs.sinfo->snd_assoc_id; + sflags = srinfo->sinfo_flags; + if (!sflags && msg_len) + return 0; - sinfo = &default_sinfo; - fill_sinfo_ttl = true; - } else { - sinfo = cmsgs.srinfo; - } - /* Did the user specify SNDINFO/SNDRCVINFO? */ - if (sinfo) { - sinfo_flags = sinfo->sinfo_flags; - associd = sinfo->sinfo_assoc_id; - } + if (sctp_style(sk, TCP) && (sflags & (SCTP_EOF | SCTP_ABORT))) + return -EINVAL; - pr_debug("%s: msg_len:%zu, sinfo_flags:0x%x\n", __func__, - msg_len, sinfo_flags); + if (((sflags & SCTP_EOF) && msg_len > 0) || + (!(sflags & (SCTP_EOF | SCTP_ABORT)) && msg_len == 0)) + return -EINVAL; - /* SCTP_EOF or SCTP_ABORT cannot be set on a TCP-style socket. */ - if (sctp_style(sk, TCP) && (sinfo_flags & (SCTP_EOF | SCTP_ABORT))) { - err = -EINVAL; - goto out_nounlock; - } + if ((sflags & SCTP_ADDR_OVER) && !msg->msg_name) + return -EINVAL; - /* If SCTP_EOF is set, no data can be sent. Disallow sending zero - * length messages when SCTP_EOF|SCTP_ABORT is not set. - * If SCTP_ABORT is set, the message length could be non zero with - * the msg_iov set to the user abort reason. - */ - if (((sinfo_flags & SCTP_EOF) && (msg_len > 0)) || - (!(sinfo_flags & (SCTP_EOF|SCTP_ABORT)) && (msg_len == 0))) { - err = -EINVAL; - goto out_nounlock; - } + return 0; +} - /* If SCTP_ADDR_OVER is set, there must be an address - * specified in msg_name. - */ - if ((sinfo_flags & SCTP_ADDR_OVER) && (!msg->msg_name)) { - err = -EINVAL; - goto out_nounlock; - } +static int sctp_sendmsg_new_asoc(struct sock *sk, __u16 sflags, + struct sctp_cmsgs *cmsgs, + union sctp_addr *daddr, + struct sctp_transport **tp) +{ + struct sctp_endpoint *ep = sctp_sk(sk)->ep; + struct net *net = sock_net(sk); + struct sctp_association *asoc; + enum sctp_scope scope; + int err = -EINVAL; - transport = NULL; + *tp = NULL; - pr_debug("%s: about to look up association\n", __func__); + if (sflags & (SCTP_EOF | SCTP_ABORT)) + return -EINVAL; - lock_sock(sk); + if (sctp_style(sk, TCP) && (sctp_sstate(sk, ESTABLISHED) || + sctp_sstate(sk, CLOSING))) + return -EADDRNOTAVAIL; - /* If a msg_name has been specified, assume this is to be used. */ - if (msg_name) { - /* Look for a matching association on the endpoint. */ - asoc = sctp_endpoint_lookup_assoc(ep, &to, &transport); + if (sctp_endpoint_is_peeled_off(ep, daddr)) + return -EADDRNOTAVAIL; - /* If we could not find a matching association on the - * endpoint, make sure that it is not a TCP-style - * socket that already has an association or there is - * no peeled-off association on another socket. - */ - if (!asoc && - ((sctp_style(sk, TCP) && - (sctp_sstate(sk, ESTABLISHED) || - sctp_sstate(sk, CLOSING))) || - sctp_endpoint_is_peeled_off(ep, &to))) { - err = -EADDRNOTAVAIL; - goto out_unlock; - } + if (!ep->base.bind_addr.port) { + if (sctp_autobind(sk)) + return -EAGAIN; } else { - asoc = sctp_id2assoc(sk, associd); - if (!asoc) { - err = -EPIPE; - goto out_unlock; - } + if (ep->base.bind_addr.port < inet_prot_sock(net) && + !ns_capable(net->user_ns, CAP_NET_BIND_SERVICE)) + return -EACCES; } - if (asoc) { - pr_debug("%s: just looked up association:%p\n", __func__, asoc); + scope = sctp_scope(daddr); - /* We cannot send a message on a TCP-style SCTP_SS_ESTABLISHED - * socket that has an association in CLOSED state. This can - * happen when an accepted socket has an association that is - * already CLOSED. - */ - if (sctp_state(asoc, CLOSED) && sctp_style(sk, TCP)) { - err = -EPIPE; - goto out_unlock; - } + asoc = sctp_association_new(ep, sk, scope, GFP_KERNEL); + if (!asoc) + return -ENOMEM; - if (sinfo_flags & SCTP_EOF) { - pr_debug("%s: shutting down association:%p\n", - __func__, asoc); + if (sctp_assoc_set_bind_addr_from_ep(asoc, scope, GFP_KERNEL) < 0) { + err = -ENOMEM; + goto free; + } - sctp_primitive_SHUTDOWN(net, asoc, NULL); - err = 0; - goto out_unlock; + if (cmsgs->init) { + struct sctp_initmsg *init = cmsgs->init; + + if (init->sinit_num_ostreams) { + __u16 outcnt = init->sinit_num_ostreams; + + asoc->c.sinit_num_ostreams = outcnt; + /* outcnt has been changed, need to re-init stream */ + err = sctp_stream_init(&asoc->stream, outcnt, 0, + GFP_KERNEL); + if (err) + goto free; } - if (sinfo_flags & SCTP_ABORT) { - chunk = sctp_make_abort_user(asoc, msg, msg_len); - if (!chunk) { - err = -ENOMEM; - goto out_unlock; - } + if (init->sinit_max_instreams) + asoc->c.sinit_max_instreams = init->sinit_max_instreams; - pr_debug("%s: aborting association:%p\n", - __func__, asoc); + if (init->sinit_max_attempts) + asoc->max_init_attempts = init->sinit_max_attempts; - sctp_primitive_ABORT(net, asoc, chunk); - err = 0; - goto out_unlock; - } + if (init->sinit_max_init_timeo) + asoc->max_init_timeo = + msecs_to_jiffies(init->sinit_max_init_timeo); } - /* Do we need to create the association? */ - if (!asoc) { - pr_debug("%s: there is no association yet\n", __func__); + *tp = sctp_assoc_add_peer(asoc, daddr, GFP_KERNEL, SCTP_UNKNOWN); + if (!*tp) { + err = -ENOMEM; + goto free; + } - if (sinfo_flags & (SCTP_EOF | SCTP_ABORT)) { - err = -EINVAL; - goto out_unlock; - } + return 0; - /* Check for invalid stream against the stream counts, - * either the default or the user specified stream counts. - */ - if (sinfo) { - if (!sinit || !sinit->sinit_num_ostreams) { - /* Check against the defaults. */ - if (sinfo->sinfo_stream >= - sp->initmsg.sinit_num_ostreams) { - err = -EINVAL; - goto out_unlock; - } - } else { - /* Check against the requested. */ - if (sinfo->sinfo_stream >= - sinit->sinit_num_ostreams) { - err = -EINVAL; - goto out_unlock; - } - } - } +free: + sctp_association_free(asoc); + return err; +} - /* - * API 3.1.2 bind() - UDP Style Syntax - * If a bind() or sctp_bindx() is not called prior to a - * sendmsg() call that initiates a new association, the - * system picks an ephemeral port and will choose an address - * set equivalent to binding with a wildcard address. - */ - if (!ep->base.bind_addr.port) { - if (sctp_autobind(sk)) { - err = -EAGAIN; - goto out_unlock; - } - } else { - /* - * If an unprivileged user inherits a one-to-many - * style socket with open associations on a privileged - * port, it MAY be permitted to accept new associations, - * but it SHOULD NOT be permitted to open new - * associations. - */ - if (ep->base.bind_addr.port < inet_prot_sock(net) && - !ns_capable(net->user_ns, CAP_NET_BIND_SERVICE)) { - err = -EACCES; - goto out_unlock; - } - } +static int sctp_sendmsg_check_sflags(struct sctp_association *asoc, + __u16 sflags, struct msghdr *msg, + size_t msg_len) +{ + struct sock *sk = asoc->base.sk; + struct net *net = sock_net(sk); - scope = sctp_scope(&to); - new_asoc = sctp_association_new(ep, sk, scope, GFP_KERNEL); - if (!new_asoc) { - err = -ENOMEM; - goto out_unlock; - } - asoc = new_asoc; - err = sctp_assoc_set_bind_addr_from_ep(asoc, scope, GFP_KERNEL); - if (err < 0) { - err = -ENOMEM; - goto out_free; - } + if (sctp_state(asoc, CLOSED) && sctp_style(sk, TCP)) + return -EPIPE; - /* If the SCTP_INIT ancillary data is specified, set all - * the association init values accordingly. - */ - if (sinit) { - if (sinit->sinit_num_ostreams) { - __u16 outcnt = sinit->sinit_num_ostreams; - - asoc->c.sinit_num_ostreams = outcnt; - /* outcnt has been changed, so re-init stream */ - err = sctp_stream_init(&asoc->stream, outcnt, 0, - GFP_KERNEL); - if (err) - goto out_free; - } - if (sinit->sinit_max_instreams) { - asoc->c.sinit_max_instreams = - sinit->sinit_max_instreams; - } - if (sinit->sinit_max_attempts) { - asoc->max_init_attempts - = sinit->sinit_max_attempts; - } - if (sinit->sinit_max_init_timeo) { - asoc->max_init_timeo = - msecs_to_jiffies(sinit->sinit_max_init_timeo); - } - } + if (sflags & SCTP_EOF) { + pr_debug("%s: shutting down association:%p\n", __func__, asoc); + sctp_primitive_SHUTDOWN(net, asoc, NULL); - /* Prime the peer's transport structures. */ - transport = sctp_assoc_add_peer(asoc, &to, GFP_KERNEL, SCTP_UNKNOWN); - if (!transport) { - err = -ENOMEM; - goto out_free; - } + return 0; } - /* ASSERT: we have a valid association at this point. */ - pr_debug("%s: we have a valid association\n", __func__); + if (sflags & SCTP_ABORT) { + struct sctp_chunk *chunk; - if (!sinfo) { - /* If the user didn't specify SNDINFO/SNDRCVINFO, make up - * one with some defaults. - */ - memset(&default_sinfo, 0, sizeof(default_sinfo)); - default_sinfo.sinfo_stream = asoc->default_stream; - default_sinfo.sinfo_flags = asoc->default_flags; - default_sinfo.sinfo_ppid = asoc->default_ppid; - default_sinfo.sinfo_context = asoc->default_context; - default_sinfo.sinfo_timetolive = asoc->default_timetolive; - default_sinfo.sinfo_assoc_id = sctp_assoc2id(asoc); - - sinfo = &default_sinfo; - } else if (fill_sinfo_ttl) { - /* In case SNDINFO was specified, we still need to fill - * it with a default ttl from the assoc here. - */ - sinfo->sinfo_timetolive = asoc->default_timetolive; - } + chunk = sctp_make_abort_user(asoc, msg, msg_len); + if (!chunk) + return -ENOMEM; - /* API 7.1.7, the sndbuf size per association bounds the - * maximum size of data that can be sent in a single send call. - */ - if (msg_len > sk->sk_sndbuf) { - err = -EMSGSIZE; - goto out_free; + pr_debug("%s: aborting association:%p\n", __func__, asoc); + sctp_primitive_ABORT(net, asoc, chunk); + + return 0; } - if (asoc->pmtu_pending) - sctp_assoc_pending_pmtu(asoc); + return 1; +} - /* If fragmentation is disabled and the message length exceeds the - * association fragmentation point, return EMSGSIZE. The I-D - * does not specify what this error is, but this looks like - * a great fit. - */ - if (sctp_sk(sk)->disable_fragments && (msg_len > asoc->frag_point)) { - err = -EMSGSIZE; - goto out_free; - } +static int sctp_sendmsg_to_asoc(struct sctp_association *asoc, + struct msghdr *msg, size_t msg_len, + struct sctp_transport *transport, + struct sctp_sndrcvinfo *sinfo) +{ + struct sock *sk = asoc->base.sk; + struct net *net = sock_net(sk); + struct sctp_datamsg *datamsg; + bool wait_connect = false; + struct sctp_chunk *chunk; + long timeo; + int err; - /* Check for invalid stream. */ if (sinfo->sinfo_stream >= asoc->stream.outcnt) { err = -EINVAL; - goto out_free; + goto err; } - /* Allocate sctp_stream_out_ext if not already done */ if (unlikely(!asoc->stream.out[sinfo->sinfo_stream].ext)) { err = sctp_stream_init_ext(&asoc->stream, sinfo->sinfo_stream); if (err) - goto out_free; + goto err; } - if (sctp_wspace(asoc) < msg_len) - sctp_prsctp_prune(asoc, sinfo, msg_len - sctp_wspace(asoc)); - - timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT); - if (!sctp_wspace(asoc)) { - /* sk can be changed by peel off when waiting for buf. */ - err = sctp_wait_for_sndbuf(asoc, &timeo, msg_len); - if (err) { - if (err == -ESRCH) { - /* asoc is already dead. */ - new_asoc = NULL; - err = -EPIPE; - } - goto out_free; - } + if (sctp_sk(sk)->disable_fragments && msg_len > asoc->frag_point) { + err = -EMSGSIZE; + goto err; } - /* If an address is passed with the sendto/sendmsg call, it is used - * to override the primary destination address in the TCP model, or - * when SCTP_ADDR_OVER flag is set in the UDP model. - */ - if ((sctp_style(sk, TCP) && msg_name) || - (sinfo_flags & SCTP_ADDR_OVER)) { - chunk_tp = sctp_assoc_lookup_paddr(asoc, &to); - if (!chunk_tp) { - err = -EINVAL; - goto out_free; - } - } else - chunk_tp = NULL; - - /* Auto-connect, if we aren't connected already. */ if (sctp_state(asoc, CLOSED)) { err = sctp_primitive_ASSOCIATE(net, asoc, NULL); - if (err < 0) - goto out_free; + if (err) + goto err; - /* If stream interleave is enabled, wait_connect has to be - * done earlier than data enqueue, as it needs to make data - * or idata according to asoc->intl_enable which is set - * after connection is done. - */ - if (sctp_sk(asoc->base.sk)->strm_interleave) { + if (sctp_sk(sk)->strm_interleave) { timeo = sock_sndtimeo(sk, 0); err = sctp_wait_for_connect(asoc, &timeo); if (err) - goto out_unlock; + goto err; } else { wait_connect = true; } @@ -2003,73 +1821,165 @@ static int sctp_sendmsg(struct sock *sk, struct msghdr *msg, size_t msg_len) pr_debug("%s: we associated primitively\n", __func__); } - /* Break the message into multiple chunks of maximum size. */ + if (asoc->pmtu_pending) + sctp_assoc_pending_pmtu(asoc); + + if (sctp_wspace(asoc) < msg_len) + sctp_prsctp_prune(asoc, sinfo, msg_len - sctp_wspace(asoc)); + + if (!sctp_wspace(asoc)) { + timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT); + err = sctp_wait_for_sndbuf(asoc, &timeo, msg_len); + if (err) + goto err; + } + datamsg = sctp_datamsg_from_user(asoc, sinfo, &msg->msg_iter); if (IS_ERR(datamsg)) { err = PTR_ERR(datamsg); - goto out_free; + goto err; } + asoc->force_delay = !!(msg->msg_flags & MSG_MORE); - /* Now send the (possibly) fragmented message. */ list_for_each_entry(chunk, &datamsg->chunks, frag_list) { sctp_chunk_hold(chunk); - - /* Do accounting for the write space. */ sctp_set_owner_w(chunk); - - chunk->transport = chunk_tp; + chunk->transport = transport; } - /* Send it to the lower layers. Note: all chunks - * must either fail or succeed. The lower layer - * works that way today. Keep it that way or this - * breaks. - */ err = sctp_primitive_SEND(net, asoc, datamsg); - /* Did the lower layer accept the chunk? */ if (err) { sctp_datamsg_free(datamsg); - goto out_free; + goto err; } pr_debug("%s: we sent primitively\n", __func__); sctp_datamsg_put(datamsg); - err = msg_len; if (unlikely(wait_connect)) { - timeo = sock_sndtimeo(sk, msg_flags & MSG_DONTWAIT); + timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT); sctp_wait_for_connect(asoc, &timeo); } - /* If we are already past ASSOCIATE, the lower - * layers are responsible for association cleanup. - */ - goto out_unlock; + err = msg_len; -out_free: - if (new_asoc) - sctp_association_free(asoc); -out_unlock: - release_sock(sk); +err: + return err; +} -out_nounlock: - return sctp_error(sk, msg_flags, err); +static union sctp_addr *sctp_sendmsg_get_daddr(struct sock *sk, + const struct msghdr *msg, + struct sctp_cmsgs *cmsgs) +{ + union sctp_addr *daddr = NULL; + int err; -#if 0 -do_sock_err: - if (msg_len) - err = msg_len; - else - err = sock_error(sk); - goto out; + if (!sctp_style(sk, UDP_HIGH_BANDWIDTH) && msg->msg_name) { + int len = msg->msg_namelen; -do_interrupted: - if (msg_len) - err = msg_len; - goto out; -#endif /* 0 */ + if (len > sizeof(*daddr)) + len = sizeof(*daddr); + + daddr = (union sctp_addr *)msg->msg_name; + + err = sctp_verify_addr(sk, daddr, len); + if (err) + return ERR_PTR(err); + } + + return daddr; +} + +static void sctp_sendmsg_update_sinfo(struct sctp_association *asoc, + struct sctp_sndrcvinfo *sinfo, + struct sctp_cmsgs *cmsgs) +{ + if (!cmsgs->srinfo && !cmsgs->sinfo) { + sinfo->sinfo_stream = asoc->default_stream; + sinfo->sinfo_ppid = asoc->default_ppid; + sinfo->sinfo_context = asoc->default_context; + sinfo->sinfo_assoc_id = sctp_assoc2id(asoc); + } + + if (!cmsgs->srinfo) + sinfo->sinfo_timetolive = asoc->default_timetolive; +} + +static int sctp_sendmsg(struct sock *sk, struct msghdr *msg, size_t msg_len) +{ + struct sctp_endpoint *ep = sctp_sk(sk)->ep; + struct sctp_transport *transport = NULL; + struct sctp_sndrcvinfo _sinfo, *sinfo; + struct sctp_association *asoc; + struct sctp_cmsgs cmsgs; + union sctp_addr *daddr; + bool new = false; + __u16 sflags; + int err; + + /* Parse and get snd_info */ + err = sctp_sendmsg_parse(sk, &cmsgs, &_sinfo, msg, msg_len); + if (err) + goto out; + + sinfo = &_sinfo; + sflags = sinfo->sinfo_flags; + + /* Get daddr from msg */ + daddr = sctp_sendmsg_get_daddr(sk, msg, &cmsgs); + if (IS_ERR(daddr)) { + err = PTR_ERR(daddr); + goto out; + } + + lock_sock(sk); + + /* Get and check or create asoc */ + if (daddr) { + asoc = sctp_endpoint_lookup_assoc(ep, daddr, &transport); + if (asoc) { + err = sctp_sendmsg_check_sflags(asoc, sflags, msg, + msg_len); + if (err <= 0) + goto out_unlock; + } else { + err = sctp_sendmsg_new_asoc(sk, sflags, &cmsgs, daddr, + &transport); + if (err) + goto out_unlock; + + asoc = transport->asoc; + new = true; + } + + if (!sctp_style(sk, TCP) && !(sflags & SCTP_ADDR_OVER)) + transport = NULL; + } else { + asoc = sctp_id2assoc(sk, sinfo->sinfo_assoc_id); + if (!asoc) { + err = -EPIPE; + goto out_unlock; + } + + err = sctp_sendmsg_check_sflags(asoc, sflags, msg, msg_len); + if (err <= 0) + goto out_unlock; + } + + /* Update snd_info with the asoc */ + sctp_sendmsg_update_sinfo(asoc, sinfo, &cmsgs); + + /* Send msg to the asoc */ + err = sctp_sendmsg_to_asoc(asoc, msg, msg_len, transport, sinfo); + if (err < 0 && err != -ESRCH && new) + sctp_association_free(asoc); + +out_unlock: + release_sock(sk); +out: + return sctp_error(sk, msg->msg_flags, err); } /* This is an extended version of skb_pull() that removes the data from the diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 8cc97834d4f6..2c6f4e0a9f3d 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -7,7 +7,6 @@ * applicable with RoCE-cards only * * Initial restrictions: - * - non-blocking connect postponed * - IPv6 support postponed * - support for alternate links postponed * - partial support for non-blocking sockets only @@ -24,7 +23,6 @@ #include <linux/module.h> #include <linux/socket.h> -#include <linux/inetdevice.h> #include <linux/workqueue.h> #include <linux/in.h> #include <linux/sched/signal.h> @@ -273,47 +271,7 @@ static void smc_copy_sock_settings_to_smc(struct smc_sock *smc) smc_copy_sock_settings(&smc->sk, smc->clcsock->sk, SK_FLAGS_CLC_TO_SMC); } -/* determine subnet and mask of internal TCP socket */ -int smc_netinfo_by_tcpsk(struct socket *clcsock, - __be32 *subnet, u8 *prefix_len) -{ - struct dst_entry *dst = sk_dst_get(clcsock->sk); - struct in_device *in_dev; - struct sockaddr_in addr; - int rc = -ENOENT; - int len; - - if (!dst) { - rc = -ENOTCONN; - goto out; - } - if (!dst->dev) { - rc = -ENODEV; - goto out_rel; - } - - /* get address to which the internal TCP socket is bound */ - kernel_getsockname(clcsock, (struct sockaddr *)&addr, &len); - /* analyze IPv4 specific data of net_device belonging to TCP socket */ - rcu_read_lock(); - in_dev = __in_dev_get_rcu(dst->dev); - for_ifa(in_dev) { - if (!inet_ifa_match(addr.sin_addr.s_addr, ifa)) - continue; - *prefix_len = inet_mask_len(ifa->ifa_mask); - *subnet = ifa->ifa_address & ifa->ifa_mask; - rc = 0; - break; - } endfor_ifa(in_dev); - rcu_read_unlock(); - -out_rel: - dst_release(dst); -out: - return rc; -} - -static int smc_clnt_conf_first_link(struct smc_sock *smc, union ib_gid *gid) +static int smc_clnt_conf_first_link(struct smc_sock *smc) { struct smc_link_group *lgr = smc->conn.lgr; struct smc_link *link; @@ -333,6 +291,9 @@ static int smc_clnt_conf_first_link(struct smc_sock *smc, union ib_gid *gid) return rc; } + if (link->llc_confirm_rc) + return SMC_CLC_DECL_RMBE_EC; + rc = smc_ib_modify_qp_rts(link); if (rc) return SMC_CLC_DECL_INTERR; @@ -347,11 +308,33 @@ static int smc_clnt_conf_first_link(struct smc_sock *smc, union ib_gid *gid) /* send CONFIRM LINK response over RoCE fabric */ rc = smc_llc_send_confirm_link(link, link->smcibdev->mac[link->ibport - 1], - gid, SMC_LLC_RESP); + &link->smcibdev->gid[link->ibport - 1], + SMC_LLC_RESP); if (rc < 0) return SMC_CLC_DECL_TCL; - return rc; + /* receive ADD LINK request from server over RoCE fabric */ + rest = wait_for_completion_interruptible_timeout(&link->llc_add, + SMC_LLC_WAIT_TIME); + if (rest <= 0) { + struct smc_clc_msg_decline dclc; + + rc = smc_clc_wait_msg(smc, &dclc, sizeof(dclc), + SMC_CLC_DECLINE); + return rc; + } + + /* send add link reject message, only one link supported for now */ + rc = smc_llc_send_add_link(link, + link->smcibdev->mac[link->ibport - 1], + &link->smcibdev->gid[link->ibport - 1], + SMC_LLC_RESP); + if (rc < 0) + return SMC_CLC_DECL_TCL; + + link->state = SMC_LNK_ACTIVE; + + return 0; } static void smc_conn_save_peer_info(struct smc_sock *smc, @@ -373,19 +356,9 @@ static void smc_link_save_peer_info(struct smc_link *link, link->peer_mtu = clc->qp_mtu; } -static void smc_lgr_forget(struct smc_link_group *lgr) -{ - spin_lock_bh(&smc_lgr_list.lock); - /* do not use this link group for new connections */ - if (!list_empty(&lgr->list)) - list_del_init(&lgr->list); - spin_unlock_bh(&smc_lgr_list.lock); -} - /* setup for RDMA connection of client */ static int smc_connect_rdma(struct smc_sock *smc) { - struct sockaddr_in *inaddr = (struct sockaddr_in *)smc->addr; struct smc_clc_msg_accept_confirm aclc; int local_contact = SMC_FIRST_CONTACT; struct smc_ib_device *smcibdev; @@ -439,8 +412,8 @@ static int smc_connect_rdma(struct smc_sock *smc) srv_first_contact = aclc.hdr.flag; mutex_lock(&smc_create_lgr_pending); - local_contact = smc_conn_create(smc, inaddr->sin_addr.s_addr, smcibdev, - ibport, &aclc.lcl, srv_first_contact); + local_contact = smc_conn_create(smc, smcibdev, ibport, &aclc.lcl, + srv_first_contact); if (local_contact < 0) { rc = local_contact; if (rc == -ENOMEM) @@ -499,8 +472,7 @@ static int smc_connect_rdma(struct smc_sock *smc) if (local_contact == SMC_FIRST_CONTACT) { /* QP confirmation over RoCE fabric */ - reason_code = smc_clnt_conf_first_link( - smc, &smcibdev->gid[ibport - 1]); + reason_code = smc_clnt_conf_first_link(smc); if (reason_code < 0) { rc = reason_code; goto out_err_unlock; @@ -559,7 +531,6 @@ static int smc_connect(struct socket *sock, struct sockaddr *addr, goto out_err; if (addr->sa_family != AF_INET) goto out_err; - smc->addr = addr; /* needed for nonblocking connect */ lock_sock(sk); switch (sk->sk_state) { @@ -749,9 +720,34 @@ static int smc_serv_conf_first_link(struct smc_sock *smc) rc = smc_clc_wait_msg(smc, &dclc, sizeof(dclc), SMC_CLC_DECLINE); + return rc; } - return rc; + if (link->llc_confirm_resp_rc) + return SMC_CLC_DECL_RMBE_EC; + + /* send ADD LINK request to client over the RoCE fabric */ + rc = smc_llc_send_add_link(link, + link->smcibdev->mac[link->ibport - 1], + &link->smcibdev->gid[link->ibport - 1], + SMC_LLC_REQ); + if (rc < 0) + return SMC_CLC_DECL_TCL; + + /* receive ADD LINK response from client over the RoCE fabric */ + rest = wait_for_completion_interruptible_timeout(&link->llc_add_resp, + SMC_LLC_WAIT_TIME); + if (rest <= 0) { + struct smc_clc_msg_decline dclc; + + rc = smc_clc_wait_msg(smc, &dclc, sizeof(dclc), + SMC_CLC_DECLINE); + return rc; + } + + link->state = SMC_LNK_ACTIVE; + + return 0; } /* setup for RDMA connection of server */ @@ -767,11 +763,10 @@ static void smc_listen_work(struct work_struct *work) struct sock *newsmcsk = &new_smc->sk; struct smc_clc_msg_proposal *pclc; struct smc_ib_device *smcibdev; - struct sockaddr_in peeraddr; u8 buf[SMC_CLC_MAX_LEN]; struct smc_link *link; int reason_code = 0; - int rc = 0, len; + int rc = 0; __be32 subnet; u8 prefix_len; u8 ibport; @@ -809,7 +804,7 @@ static void smc_listen_work(struct work_struct *work) } /* determine subnet and mask from internal TCP socket */ - rc = smc_netinfo_by_tcpsk(newclcsock, &subnet, &prefix_len); + rc = smc_clc_netinfo_by_tcpsk(newclcsock, &subnet, &prefix_len); if (rc) { reason_code = SMC_CLC_DECL_CNFERR; /* configuration error */ goto decline_rdma; @@ -823,13 +818,10 @@ static void smc_listen_work(struct work_struct *work) goto decline_rdma; } - /* get address of the peer connected to the internal TCP socket */ - kernel_getpeername(newclcsock, (struct sockaddr *)&peeraddr, &len); - /* allocate connection / link group */ mutex_lock(&smc_create_lgr_pending); - local_contact = smc_conn_create(new_smc, peeraddr.sin_addr.s_addr, - smcibdev, ibport, &pclc->lcl, 0); + local_contact = smc_conn_create(new_smc, smcibdev, ibport, &pclc->lcl, + 0); if (local_contact < 0) { rc = local_contact; if (rc == -ENOMEM) @@ -1075,7 +1067,7 @@ out: } static int smc_getname(struct socket *sock, struct sockaddr *addr, - int *len, int peer) + int peer) { struct smc_sock *smc; @@ -1085,7 +1077,7 @@ static int smc_getname(struct socket *sock, struct sockaddr *addr, smc = smc_sk(sock->sk); - return smc->clcsock->ops->getname(smc->clcsock, addr, len, peer); + return smc->clcsock->ops->getname(smc->clcsock, addr, peer); } static int smc_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) diff --git a/net/smc/smc.h b/net/smc/smc.h index 9518986c97b1..268cdf11533c 100644 --- a/net/smc/smc.h +++ b/net/smc/smc.h @@ -172,7 +172,6 @@ struct smc_sock { /* smc sock container */ struct sock sk; struct socket *clcsock; /* internal tcp socket */ struct smc_connection conn; /* smc connection */ - struct sockaddr *addr; /* inet connect address */ struct smc_sock *listen_smc; /* listen parent */ struct work_struct tcp_listen_work;/* handle tcp socket accepts */ struct work_struct smc_listen_work;/* prepare new accept socket */ @@ -263,10 +262,8 @@ static inline bool using_ipsec(struct smc_sock *smc) struct smc_clc_msg_local; -int smc_netinfo_by_tcpsk(struct socket *clcsock, __be32 *subnet, - u8 *prefix_len); void smc_conn_free(struct smc_connection *conn); -int smc_conn_create(struct smc_sock *smc, __be32 peer_in_addr, +int smc_conn_create(struct smc_sock *smc, struct smc_ib_device *smcibdev, u8 ibport, struct smc_clc_msg_local *lcl, int srv_first_contact); struct sock *smc_accept_dequeue(struct sock *parent, struct socket *new_sock); diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c index 8ac51583a063..874c5a75d6dd 100644 --- a/net/smc/smc_clc.c +++ b/net/smc/smc_clc.c @@ -11,6 +11,7 @@ */ #include <linux/in.h> +#include <linux/inetdevice.h> #include <linux/if_ether.h> #include <linux/sched/signal.h> @@ -22,6 +23,9 @@ #include "smc_clc.h" #include "smc_ib.h" +/* eye catcher "SMCR" EBCDIC for CLC messages */ +static const char SMC_EYECATCHER[4] = {'\xe2', '\xd4', '\xc3', '\xd9'}; + /* check if received message has a correct header length and contains valid * heading and trailing eyecatchers */ @@ -70,6 +74,45 @@ static bool smc_clc_msg_hdr_valid(struct smc_clc_msg_hdr *clcm) return true; } +/* determine subnet and mask of internal TCP socket */ +int smc_clc_netinfo_by_tcpsk(struct socket *clcsock, + __be32 *subnet, u8 *prefix_len) +{ + struct dst_entry *dst = sk_dst_get(clcsock->sk); + struct in_device *in_dev; + struct sockaddr_in addr; + int rc = -ENOENT; + + if (!dst) { + rc = -ENOTCONN; + goto out; + } + if (!dst->dev) { + rc = -ENODEV; + goto out_rel; + } + + /* get address to which the internal TCP socket is bound */ + kernel_getsockname(clcsock, (struct sockaddr *)&addr); + /* analyze IPv4 specific data of net_device belonging to TCP socket */ + rcu_read_lock(); + in_dev = __in_dev_get_rcu(dst->dev); + for_ifa(in_dev) { + if (!inet_ifa_match(addr.sin_addr.s_addr, ifa)) + continue; + *prefix_len = inet_mask_len(ifa->ifa_mask); + *subnet = ifa->ifa_address & ifa->ifa_mask; + rc = 0; + break; + } endfor_ifa(in_dev); + rcu_read_unlock(); + +out_rel: + dst_release(dst); +out: + return rc; +} + /* Wait for data on the tcp-socket, analyze received data * Returns: * 0 if success and it was not a decline that we received. @@ -211,8 +254,8 @@ int smc_clc_send_proposal(struct smc_sock *smc, memset(&pclc_prfx, 0, sizeof(pclc_prfx)); /* determine subnet and mask from internal TCP socket */ - rc = smc_netinfo_by_tcpsk(smc->clcsock, &pclc_prfx.outgoing_subnet, - &pclc_prfx.prefix_len); + rc = smc_clc_netinfo_by_tcpsk(smc->clcsock, &pclc_prfx.outgoing_subnet, + &pclc_prfx.prefix_len); if (rc) return SMC_CLC_DECL_CNFERR; /* configuration error */ pclc_prfx.ipv6_prefixes_cnt = 0; diff --git a/net/smc/smc_clc.h b/net/smc/smc_clc.h index c145a0f36a68..20e048beac30 100644 --- a/net/smc/smc_clc.h +++ b/net/smc/smc_clc.h @@ -22,9 +22,6 @@ #define SMC_CLC_CONFIRM 0x03 #define SMC_CLC_DECLINE 0x04 -/* eye catcher "SMCR" EBCDIC for CLC messages */ -static const char SMC_EYECATCHER[4] = {'\xe2', '\xd4', '\xc3', '\xd9'}; - #define SMC_CLC_V1 0x1 /* SMC version */ #define CLC_WAIT_TIME (6 * HZ) /* max. wait time on clcsock */ #define SMC_CLC_DECL_MEM 0x01010000 /* insufficient memory resources */ @@ -36,6 +33,7 @@ static const char SMC_EYECATCHER[4] = {'\xe2', '\xd4', '\xc3', '\xd9'}; #define SMC_CLC_DECL_INTERR 0x99990000 /* internal error */ #define SMC_CLC_DECL_TCL 0x02040000 /* timeout w4 QP confirm */ #define SMC_CLC_DECL_SEND 0x07000000 /* sending problem */ +#define SMC_CLC_DECL_RMBE_EC 0x08000000 /* peer has eyecatcher in RMBE */ struct smc_clc_msg_hdr { /* header1 of clc messages */ u8 eyecatcher[4]; /* eye catcher */ @@ -124,9 +122,8 @@ smc_clc_proposal_get_prefix(struct smc_clc_msg_proposal *pclc) ((u8 *)pclc + sizeof(*pclc) + ntohs(pclc->iparea_offset)); } -struct smc_sock; -struct smc_ib_device; - +int smc_clc_netinfo_by_tcpsk(struct socket *clcsock, __be32 *subnet, + u8 *prefix_len); int smc_clc_wait_msg(struct smc_sock *smc, void *buf, int buflen, u8 expected_type); int smc_clc_send_decline(struct smc_sock *smc, u32 peer_diag_info); diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index 645dd226177b..f76f60e463cb 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -144,7 +144,7 @@ free: } /* create a new SMC link group */ -static int smc_lgr_create(struct smc_sock *smc, __be32 peer_in_addr, +static int smc_lgr_create(struct smc_sock *smc, struct smc_ib_device *smcibdev, u8 ibport, char *peer_systemid, unsigned short vlan_id) { @@ -161,7 +161,6 @@ static int smc_lgr_create(struct smc_sock *smc, __be32 peer_in_addr, } lgr->role = smc->listen_smc ? SMC_SERV : SMC_CLNT; lgr->sync_err = false; - lgr->daddr = peer_in_addr; memcpy(lgr->peer_systemid, peer_systemid, SMC_SYSTEMID_LEN); lgr->vlan_id = vlan_id; rwlock_init(&lgr->sndbufs_lock); @@ -177,6 +176,7 @@ static int smc_lgr_create(struct smc_sock *smc, __be32 peer_in_addr, lnk = &lgr->lnk[SMC_SINGLE_LINK]; /* initialize link */ + lnk->state = SMC_LNK_ACTIVATING; lnk->link_id = SMC_SINGLE_LINK; lnk->smcibdev = smcibdev; lnk->ibport = ibport; @@ -199,6 +199,8 @@ static int smc_lgr_create(struct smc_sock *smc, __be32 peer_in_addr, goto destroy_qp; init_completion(&lnk->llc_confirm); init_completion(&lnk->llc_confirm_resp); + init_completion(&lnk->llc_add); + init_completion(&lnk->llc_add_resp); smc->conn.lgr = lgr; rwlock_init(&lgr->conns_lock); @@ -307,6 +309,15 @@ void smc_lgr_free(struct smc_link_group *lgr) kfree(lgr); } +void smc_lgr_forget(struct smc_link_group *lgr) +{ + spin_lock_bh(&smc_lgr_list.lock); + /* do not use this link group for new connections */ + if (!list_empty(&lgr->list)) + list_del_init(&lgr->list); + spin_unlock_bh(&smc_lgr_list.lock); +} + /* terminate linkgroup abnormally */ void smc_lgr_terminate(struct smc_link_group *lgr) { @@ -314,15 +325,7 @@ void smc_lgr_terminate(struct smc_link_group *lgr) struct smc_sock *smc; struct rb_node *node; - spin_lock_bh(&smc_lgr_list.lock); - if (list_empty(&lgr->list)) { - /* termination already triggered */ - spin_unlock_bh(&smc_lgr_list.lock); - return; - } - /* do not use this link group for new connections */ - list_del_init(&lgr->list); - spin_unlock_bh(&smc_lgr_list.lock); + smc_lgr_forget(lgr); write_lock_bh(&lgr->conns_lock); node = rb_first(&lgr->conns_all); @@ -401,7 +404,7 @@ static int smc_link_determine_gid(struct smc_link_group *lgr) } /* create a new SMC connection (and a new link group if necessary) */ -int smc_conn_create(struct smc_sock *smc, __be32 peer_in_addr, +int smc_conn_create(struct smc_sock *smc, struct smc_ib_device *smcibdev, u8 ibport, struct smc_clc_msg_local *lcl, int srv_first_contact) { @@ -458,7 +461,7 @@ int smc_conn_create(struct smc_sock *smc, __be32 peer_in_addr, create: if (local_contact == SMC_FIRST_CONTACT) { - rc = smc_lgr_create(smc, peer_in_addr, smcibdev, ibport, + rc = smc_lgr_create(smc, smcibdev, ibport, lcl->id_for_peer, vlan_id); if (rc) goto out; @@ -699,27 +702,55 @@ static inline int smc_rmb_reserve_rtoken_idx(struct smc_link_group *lgr) return -ENOSPC; } -/* save rkey and dma_addr received from peer during clc handshake */ -int smc_rmb_rtoken_handling(struct smc_connection *conn, - struct smc_clc_msg_accept_confirm *clc) +/* add a new rtoken from peer */ +int smc_rtoken_add(struct smc_link_group *lgr, __be64 nw_vaddr, __be32 nw_rkey) { - u64 dma_addr = be64_to_cpu(clc->rmb_dma_addr); - struct smc_link_group *lgr = conn->lgr; - u32 rkey = ntohl(clc->rmb_rkey); + u64 dma_addr = be64_to_cpu(nw_vaddr); + u32 rkey = ntohl(nw_rkey); int i; for (i = 0; i < SMC_RMBS_PER_LGR_MAX; i++) { if ((lgr->rtokens[i][SMC_SINGLE_LINK].rkey == rkey) && (lgr->rtokens[i][SMC_SINGLE_LINK].dma_addr == dma_addr) && test_bit(i, lgr->rtokens_used_mask)) { - conn->rtoken_idx = i; + /* already in list */ + return i; + } + } + i = smc_rmb_reserve_rtoken_idx(lgr); + if (i < 0) + return i; + lgr->rtokens[i][SMC_SINGLE_LINK].rkey = rkey; + lgr->rtokens[i][SMC_SINGLE_LINK].dma_addr = dma_addr; + return i; +} + +/* delete an rtoken */ +int smc_rtoken_delete(struct smc_link_group *lgr, __be32 nw_rkey) +{ + u32 rkey = ntohl(nw_rkey); + int i; + + for (i = 0; i < SMC_RMBS_PER_LGR_MAX; i++) { + if (lgr->rtokens[i][SMC_SINGLE_LINK].rkey == rkey && + test_bit(i, lgr->rtokens_used_mask)) { + lgr->rtokens[i][SMC_SINGLE_LINK].rkey = 0; + lgr->rtokens[i][SMC_SINGLE_LINK].dma_addr = 0; + + clear_bit(i, lgr->rtokens_used_mask); return 0; } } - conn->rtoken_idx = smc_rmb_reserve_rtoken_idx(lgr); + return -ENOENT; +} + +/* save rkey and dma_addr received from peer during clc handshake */ +int smc_rmb_rtoken_handling(struct smc_connection *conn, + struct smc_clc_msg_accept_confirm *clc) +{ + conn->rtoken_idx = smc_rtoken_add(conn->lgr, clc->rmb_dma_addr, + clc->rmb_rkey); if (conn->rtoken_idx < 0) return conn->rtoken_idx; - lgr->rtokens[conn->rtoken_idx][SMC_SINGLE_LINK].rkey = rkey; - lgr->rtokens[conn->rtoken_idx][SMC_SINGLE_LINK].dma_addr = dma_addr; return 0; } diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h index fe691bf9af91..07e2a393e6d9 100644 --- a/net/smc/smc_core.h +++ b/net/smc/smc_core.h @@ -32,6 +32,12 @@ enum smc_lgr_role { /* possible roles of a link group */ SMC_SERV /* server */ }; +enum smc_link_state { /* possible states of a link */ + SMC_LNK_INACTIVE, /* link is inactive */ + SMC_LNK_ACTIVATING, /* link is being activated */ + SMC_LNK_ACTIVE /* link is active */ +}; + #define SMC_WR_BUF_SIZE 48 /* size of work request buffer */ struct smc_wr_buf { @@ -87,8 +93,14 @@ struct smc_link { u8 peer_mac[ETH_ALEN]; /* = gid[8:10||13:15] */ u8 peer_gid[sizeof(union ib_gid)]; /* gid of peer*/ u8 link_id; /* unique # within link group */ + + enum smc_link_state state; /* state of link */ struct completion llc_confirm; /* wait for rx of conf link */ struct completion llc_confirm_resp; /* wait 4 rx of cnf lnk rsp */ + int llc_confirm_rc; /* rc from confirm link msg */ + int llc_confirm_resp_rc; /* rc from conf_resp msg */ + struct completion llc_add; /* wait for rx of add link */ + struct completion llc_add_resp; /* wait for rx of add link rsp*/ }; /* For now we just allow one parallel link per link group. The SMC protocol @@ -124,7 +136,6 @@ struct smc_rtoken { /* address/key of remote RMB */ struct smc_link_group { struct list_head list; enum smc_lgr_role role; /* client or server */ - __be32 daddr; /* destination ip address */ struct smc_link lnk[SMC_LINKS_PER_LGR_MAX]; /* smc link */ char peer_systemid[SMC_SYSTEMID_LEN]; /* unique system_id of peer */ @@ -186,10 +197,13 @@ struct smc_sock; struct smc_clc_msg_accept_confirm; void smc_lgr_free(struct smc_link_group *lgr); +void smc_lgr_forget(struct smc_link_group *lgr); void smc_lgr_terminate(struct smc_link_group *lgr); int smc_buf_create(struct smc_sock *smc); int smc_rmb_rtoken_handling(struct smc_connection *conn, struct smc_clc_msg_accept_confirm *clc); +int smc_rtoken_add(struct smc_link_group *lgr, __be64 nw_vaddr, __be32 nw_rkey); +int smc_rtoken_delete(struct smc_link_group *lgr, __be32 nw_rkey); void smc_sndbuf_sync_sg_for_cpu(struct smc_connection *conn); void smc_sndbuf_sync_sg_for_device(struct smc_connection *conn); void smc_rmb_sync_sg_for_cpu(struct smc_connection *conn); diff --git a/net/smc/smc_llc.c b/net/smc/smc_llc.c index b4aa4fcedb96..ea4b21981b4b 100644 --- a/net/smc/smc_llc.c +++ b/net/smc/smc_llc.c @@ -4,9 +4,6 @@ * * Link Layer Control (LLC) * - * For now, we only support the necessary "confirm link" functionality - * which happens for the first RoCE link after successful CLC handshake. - * * Copyright IBM Corp. 2016 * * Author(s): Klaus Wacker <Klaus.Wacker@de.ibm.com> @@ -21,6 +18,122 @@ #include "smc_clc.h" #include "smc_llc.h" +#define SMC_LLC_DATA_LEN 40 + +struct smc_llc_hdr { + struct smc_wr_rx_hdr common; + u8 length; /* 44 */ +#if defined(__BIG_ENDIAN_BITFIELD) + u8 reserved:4, + add_link_rej_rsn:4; +#elif defined(__LITTLE_ENDIAN_BITFIELD) + u8 add_link_rej_rsn:4, + reserved:4; +#endif + u8 flags; +}; + +#define SMC_LLC_FLAG_NO_RMBE_EYEC 0x03 + +struct smc_llc_msg_confirm_link { /* type 0x01 */ + struct smc_llc_hdr hd; + u8 sender_mac[ETH_ALEN]; + u8 sender_gid[SMC_GID_SIZE]; + u8 sender_qp_num[3]; + u8 link_num; + u8 link_uid[SMC_LGR_ID_SIZE]; + u8 max_links; + u8 reserved[9]; +}; + +#define SMC_LLC_FLAG_ADD_LNK_REJ 0x40 +#define SMC_LLC_REJ_RSN_NO_ALT_PATH 1 + +#define SMC_LLC_ADD_LNK_MAX_LINKS 2 + +struct smc_llc_msg_add_link { /* type 0x02 */ + struct smc_llc_hdr hd; + u8 sender_mac[ETH_ALEN]; + u8 reserved2[2]; + u8 sender_gid[SMC_GID_SIZE]; + u8 sender_qp_num[3]; + u8 link_num; + u8 flags2; /* QP mtu */ + u8 initial_psn[3]; + u8 reserved[8]; +}; + +#define SMC_LLC_FLAG_DEL_LINK_ALL 0x40 +#define SMC_LLC_FLAG_DEL_LINK_ORDERLY 0x20 + +struct smc_llc_msg_del_link { /* type 0x04 */ + struct smc_llc_hdr hd; + u8 link_num; + __be32 reason; + u8 reserved[35]; +} __packed; /* format defined in RFC7609 */ + +struct smc_llc_msg_test_link { /* type 0x07 */ + struct smc_llc_hdr hd; + u8 user_data[16]; + u8 reserved[24]; +}; + +struct smc_rmb_rtoken { + union { + u8 num_rkeys; /* first rtoken byte of CONFIRM LINK msg */ + /* is actually the num of rtokens, first */ + /* rtoken is always for the current link */ + u8 link_id; /* link id of the rtoken */ + }; + __be32 rmb_key; + __be64 rmb_vaddr; +} __packed; /* format defined in RFC7609 */ + +#define SMC_LLC_RKEYS_PER_MSG 3 + +struct smc_llc_msg_confirm_rkey { /* type 0x06 */ + struct smc_llc_hdr hd; + struct smc_rmb_rtoken rtoken[SMC_LLC_RKEYS_PER_MSG]; + u8 reserved; +}; + +struct smc_llc_msg_confirm_rkey_cont { /* type 0x08 */ + struct smc_llc_hdr hd; + u8 num_rkeys; + struct smc_rmb_rtoken rtoken[SMC_LLC_RKEYS_PER_MSG]; +}; + +#define SMC_LLC_DEL_RKEY_MAX 8 +#define SMC_LLC_FLAG_RKEY_NEG 0x20 + +struct smc_llc_msg_delete_rkey { /* type 0x09 */ + struct smc_llc_hdr hd; + u8 num_rkeys; + u8 err_mask; + u8 reserved[2]; + __be32 rkey[8]; + u8 reserved2[4]; +}; + +union smc_llc_msg { + struct smc_llc_msg_confirm_link confirm_link; + struct smc_llc_msg_add_link add_link; + struct smc_llc_msg_del_link delete_link; + + struct smc_llc_msg_confirm_rkey confirm_rkey; + struct smc_llc_msg_confirm_rkey_cont confirm_rkey_cont; + struct smc_llc_msg_delete_rkey delete_rkey; + + struct smc_llc_msg_test_link test_link; + struct { + struct smc_llc_hdr hdr; + u8 data[SMC_LLC_DATA_LEN]; + } raw; +}; + +#define SMC_LLC_FLAG_RESP 0x80 + /********************************** send *************************************/ struct smc_llc_tx_pend { @@ -87,6 +200,7 @@ int smc_llc_send_confirm_link(struct smc_link *link, u8 mac[], memset(confllc, 0, sizeof(*confllc)); confllc->hd.common.type = SMC_LLC_CONFIRM_LINK; confllc->hd.length = sizeof(struct smc_llc_msg_confirm_link); + confllc->hd.flags |= SMC_LLC_FLAG_NO_RMBE_EYEC; if (reqresp == SMC_LLC_RESP) confllc->hd.flags |= SMC_LLC_FLAG_RESP; memcpy(confllc->sender_mac, mac, ETH_ALEN); @@ -94,7 +208,104 @@ int smc_llc_send_confirm_link(struct smc_link *link, u8 mac[], hton24(confllc->sender_qp_num, link->roce_qp->qp_num); confllc->link_num = link->link_id; memcpy(confllc->link_uid, lgr->id, SMC_LGR_ID_SIZE); - confllc->max_links = SMC_LINKS_PER_LGR_MAX; + confllc->max_links = SMC_LLC_ADD_LNK_MAX_LINKS; /* enforce peer resp. */ + /* send llc message */ + rc = smc_wr_tx_send(link, pend); + return rc; +} + +/* send ADD LINK request or response */ +int smc_llc_send_add_link(struct smc_link *link, u8 mac[], + union ib_gid *gid, + enum smc_llc_reqresp reqresp) +{ + struct smc_llc_msg_add_link *addllc; + struct smc_wr_tx_pend_priv *pend; + struct smc_wr_buf *wr_buf; + int rc; + + rc = smc_llc_add_pending_send(link, &wr_buf, &pend); + if (rc) + return rc; + addllc = (struct smc_llc_msg_add_link *)wr_buf; + memset(addllc, 0, sizeof(*addllc)); + addllc->hd.common.type = SMC_LLC_ADD_LINK; + addllc->hd.length = sizeof(struct smc_llc_msg_add_link); + if (reqresp == SMC_LLC_RESP) { + addllc->hd.flags |= SMC_LLC_FLAG_RESP; + /* always reject more links for now */ + addllc->hd.flags |= SMC_LLC_FLAG_ADD_LNK_REJ; + addllc->hd.add_link_rej_rsn = SMC_LLC_REJ_RSN_NO_ALT_PATH; + } + memcpy(addllc->sender_mac, mac, ETH_ALEN); + memcpy(addllc->sender_gid, gid, SMC_GID_SIZE); + /* send llc message */ + rc = smc_wr_tx_send(link, pend); + return rc; +} + +/* send DELETE LINK request or response */ +int smc_llc_send_delete_link(struct smc_link *link, + enum smc_llc_reqresp reqresp) +{ + struct smc_llc_msg_del_link *delllc; + struct smc_wr_tx_pend_priv *pend; + struct smc_wr_buf *wr_buf; + int rc; + + rc = smc_llc_add_pending_send(link, &wr_buf, &pend); + if (rc) + return rc; + delllc = (struct smc_llc_msg_del_link *)wr_buf; + memset(delllc, 0, sizeof(*delllc)); + delllc->hd.common.type = SMC_LLC_DELETE_LINK; + delllc->hd.length = sizeof(struct smc_llc_msg_add_link); + if (reqresp == SMC_LLC_RESP) + delllc->hd.flags |= SMC_LLC_FLAG_RESP; + /* DEL_LINK_ALL because only 1 link supported */ + delllc->hd.flags |= SMC_LLC_FLAG_DEL_LINK_ALL; + delllc->hd.flags |= SMC_LLC_FLAG_DEL_LINK_ORDERLY; + delllc->link_num = link->link_id; + /* send llc message */ + rc = smc_wr_tx_send(link, pend); + return rc; +} + +/* send LLC test link request or response */ +int smc_llc_send_test_link(struct smc_link *link, u8 user_data[16], + enum smc_llc_reqresp reqresp) +{ + struct smc_llc_msg_test_link *testllc; + struct smc_wr_tx_pend_priv *pend; + struct smc_wr_buf *wr_buf; + int rc; + + rc = smc_llc_add_pending_send(link, &wr_buf, &pend); + if (rc) + return rc; + testllc = (struct smc_llc_msg_test_link *)wr_buf; + memset(testllc, 0, sizeof(*testllc)); + testllc->hd.common.type = SMC_LLC_TEST_LINK; + testllc->hd.length = sizeof(struct smc_llc_msg_test_link); + if (reqresp == SMC_LLC_RESP) + testllc->hd.flags |= SMC_LLC_FLAG_RESP; + memcpy(testllc->user_data, user_data, sizeof(testllc->user_data)); + /* send llc message */ + rc = smc_wr_tx_send(link, pend); + return rc; +} + +/* send a prepared message */ +static int smc_llc_send_message(struct smc_link *link, void *llcbuf, int llclen) +{ + struct smc_wr_tx_pend_priv *pend; + struct smc_wr_buf *wr_buf; + int rc; + + rc = smc_llc_add_pending_send(link, &wr_buf, &pend); + if (rc) + return rc; + memcpy(wr_buf, llcbuf, llclen); /* send llc message */ rc = smc_wr_tx_send(link, pend); return rc; @@ -106,19 +317,156 @@ static void smc_llc_rx_confirm_link(struct smc_link *link, struct smc_llc_msg_confirm_link *llc) { struct smc_link_group *lgr; + int conf_rc; lgr = container_of(link, struct smc_link_group, lnk[SMC_SINGLE_LINK]); + + /* RMBE eyecatchers are not supported */ + if (llc->hd.flags & SMC_LLC_FLAG_NO_RMBE_EYEC) + conf_rc = 0; + else + conf_rc = ENOTSUPP; + if (llc->hd.flags & SMC_LLC_FLAG_RESP) { - if (lgr->role == SMC_SERV) + if (lgr->role == SMC_SERV && + link->state == SMC_LNK_ACTIVATING) { + link->llc_confirm_resp_rc = conf_rc; complete(&link->llc_confirm_resp); + } } else { - if (lgr->role == SMC_CLNT) { + if (lgr->role == SMC_CLNT && + link->state == SMC_LNK_ACTIVATING) { + link->llc_confirm_rc = conf_rc; link->link_id = llc->link_num; complete(&link->llc_confirm); } } } +static void smc_llc_rx_add_link(struct smc_link *link, + struct smc_llc_msg_add_link *llc) +{ + struct smc_link_group *lgr = container_of(link, struct smc_link_group, + lnk[SMC_SINGLE_LINK]); + + if (llc->hd.flags & SMC_LLC_FLAG_RESP) { + if (link->state == SMC_LNK_ACTIVATING) + complete(&link->llc_add_resp); + } else { + if (link->state == SMC_LNK_ACTIVATING) { + complete(&link->llc_add); + return; + } + + if (lgr->role == SMC_SERV) { + smc_llc_send_add_link(link, + link->smcibdev->mac[link->ibport - 1], + &link->smcibdev->gid[link->ibport - 1], + SMC_LLC_REQ); + + } else { + smc_llc_send_add_link(link, + link->smcibdev->mac[link->ibport - 1], + &link->smcibdev->gid[link->ibport - 1], + SMC_LLC_RESP); + } + } +} + +static void smc_llc_rx_delete_link(struct smc_link *link, + struct smc_llc_msg_del_link *llc) +{ + struct smc_link_group *lgr = container_of(link, struct smc_link_group, + lnk[SMC_SINGLE_LINK]); + + if (llc->hd.flags & SMC_LLC_FLAG_RESP) { + if (lgr->role == SMC_SERV) + smc_lgr_terminate(lgr); + } else { + if (lgr->role == SMC_SERV) { + smc_lgr_forget(lgr); + smc_llc_send_delete_link(link, SMC_LLC_REQ); + } else { + smc_llc_send_delete_link(link, SMC_LLC_RESP); + smc_lgr_terminate(lgr); + } + } +} + +static void smc_llc_rx_test_link(struct smc_link *link, + struct smc_llc_msg_test_link *llc) +{ + if (llc->hd.flags & SMC_LLC_FLAG_RESP) { + /* unused as long as we don't send this type of msg */ + } else { + smc_llc_send_test_link(link, llc->user_data, SMC_LLC_RESP); + } +} + +static void smc_llc_rx_confirm_rkey(struct smc_link *link, + struct smc_llc_msg_confirm_rkey *llc) +{ + struct smc_link_group *lgr; + int rc; + + lgr = container_of(link, struct smc_link_group, lnk[SMC_SINGLE_LINK]); + + if (llc->hd.flags & SMC_LLC_FLAG_RESP) { + /* unused as long as we don't send this type of msg */ + } else { + rc = smc_rtoken_add(lgr, + llc->rtoken[0].rmb_vaddr, + llc->rtoken[0].rmb_key); + + /* ignore rtokens for other links, we have only one link */ + + llc->hd.flags |= SMC_LLC_FLAG_RESP; + if (rc < 0) + llc->hd.flags |= SMC_LLC_FLAG_RKEY_NEG; + smc_llc_send_message(link, (void *)llc, sizeof(*llc)); + } +} + +static void smc_llc_rx_confirm_rkey_cont(struct smc_link *link, + struct smc_llc_msg_confirm_rkey_cont *llc) +{ + if (llc->hd.flags & SMC_LLC_FLAG_RESP) { + /* unused as long as we don't send this type of msg */ + } else { + /* ignore rtokens for other links, we have only one link */ + llc->hd.flags |= SMC_LLC_FLAG_RESP; + smc_llc_send_message(link, (void *)llc, sizeof(*llc)); + } +} + +static void smc_llc_rx_delete_rkey(struct smc_link *link, + struct smc_llc_msg_delete_rkey *llc) +{ + struct smc_link_group *lgr; + u8 err_mask = 0; + int i, max; + + lgr = container_of(link, struct smc_link_group, lnk[SMC_SINGLE_LINK]); + + if (llc->hd.flags & SMC_LLC_FLAG_RESP) { + /* unused as long as we don't send this type of msg */ + } else { + max = min_t(u8, llc->num_rkeys, SMC_LLC_DEL_RKEY_MAX); + for (i = 0; i < max; i++) { + if (smc_rtoken_delete(lgr, llc->rkey[i])) + err_mask |= 1 << (SMC_LLC_DEL_RKEY_MAX - 1 - i); + } + + if (err_mask) { + llc->hd.flags |= SMC_LLC_FLAG_RKEY_NEG; + llc->err_mask = err_mask; + } + + llc->hd.flags |= SMC_LLC_FLAG_RESP; + smc_llc_send_message(link, (void *)llc, sizeof(*llc)); + } +} + static void smc_llc_rx_handler(struct ib_wc *wc, void *buf) { struct smc_link *link = (struct smc_link *)wc->qp->qp_context; @@ -128,8 +476,30 @@ static void smc_llc_rx_handler(struct ib_wc *wc, void *buf) return; /* short message */ if (llc->raw.hdr.length != sizeof(*llc)) return; /* invalid message */ - if (llc->raw.hdr.common.type == SMC_LLC_CONFIRM_LINK) + + switch (llc->raw.hdr.common.type) { + case SMC_LLC_TEST_LINK: + smc_llc_rx_test_link(link, &llc->test_link); + break; + case SMC_LLC_CONFIRM_LINK: smc_llc_rx_confirm_link(link, &llc->confirm_link); + break; + case SMC_LLC_ADD_LINK: + smc_llc_rx_add_link(link, &llc->add_link); + break; + case SMC_LLC_DELETE_LINK: + smc_llc_rx_delete_link(link, &llc->delete_link); + break; + case SMC_LLC_CONFIRM_RKEY: + smc_llc_rx_confirm_rkey(link, &llc->confirm_rkey); + break; + case SMC_LLC_CONFIRM_RKEY_CONT: + smc_llc_rx_confirm_rkey_cont(link, &llc->confirm_rkey_cont); + break; + case SMC_LLC_DELETE_RKEY: + smc_llc_rx_delete_rkey(link, &llc->delete_rkey); + break; + } } /***************************** init, exit, misc ******************************/ @@ -140,6 +510,30 @@ static struct smc_wr_rx_handler smc_llc_rx_handlers[] = { .type = SMC_LLC_CONFIRM_LINK }, { + .handler = smc_llc_rx_handler, + .type = SMC_LLC_TEST_LINK + }, + { + .handler = smc_llc_rx_handler, + .type = SMC_LLC_ADD_LINK + }, + { + .handler = smc_llc_rx_handler, + .type = SMC_LLC_DELETE_LINK + }, + { + .handler = smc_llc_rx_handler, + .type = SMC_LLC_CONFIRM_RKEY + }, + { + .handler = smc_llc_rx_handler, + .type = SMC_LLC_CONFIRM_RKEY_CONT + }, + { + .handler = smc_llc_rx_handler, + .type = SMC_LLC_DELETE_RKEY + }, + { .handler = NULL, } }; diff --git a/net/smc/smc_llc.h b/net/smc/smc_llc.h index 51b27ce90dbd..e4a7d5e234d5 100644 --- a/net/smc/smc_llc.h +++ b/net/smc/smc_llc.h @@ -18,6 +18,7 @@ #define SMC_LLC_FLAG_RESP 0x80 #define SMC_LLC_WAIT_FIRST_TIME (5 * HZ) +#define SMC_LLC_WAIT_TIME (2 * HZ) enum smc_llc_reqresp { SMC_LLC_REQ, @@ -26,39 +27,23 @@ enum smc_llc_reqresp { enum smc_llc_msg_type { SMC_LLC_CONFIRM_LINK = 0x01, -}; - -#define SMC_LLC_DATA_LEN 40 - -struct smc_llc_hdr { - struct smc_wr_rx_hdr common; - u8 length; /* 44 */ - u8 reserved; - u8 flags; -}; - -struct smc_llc_msg_confirm_link { /* type 0x01 */ - struct smc_llc_hdr hd; - u8 sender_mac[ETH_ALEN]; - u8 sender_gid[SMC_GID_SIZE]; - u8 sender_qp_num[3]; - u8 link_num; - u8 link_uid[SMC_LGR_ID_SIZE]; - u8 max_links; - u8 reserved[9]; -}; - -union smc_llc_msg { - struct smc_llc_msg_confirm_link confirm_link; - struct { - struct smc_llc_hdr hdr; - u8 data[SMC_LLC_DATA_LEN]; - } raw; + SMC_LLC_ADD_LINK = 0x02, + SMC_LLC_DELETE_LINK = 0x04, + SMC_LLC_CONFIRM_RKEY = 0x06, + SMC_LLC_TEST_LINK = 0x07, + SMC_LLC_CONFIRM_RKEY_CONT = 0x08, + SMC_LLC_DELETE_RKEY = 0x09, }; /* transmit */ int smc_llc_send_confirm_link(struct smc_link *lnk, u8 mac[], union ib_gid *gid, enum smc_llc_reqresp reqresp); +int smc_llc_send_add_link(struct smc_link *link, u8 mac[], union ib_gid *gid, + enum smc_llc_reqresp reqresp); +int smc_llc_send_delete_link(struct smc_link *link, + enum smc_llc_reqresp reqresp); +int smc_llc_send_test_link(struct smc_link *lnk, u8 user_data[16], + enum smc_llc_reqresp reqresp); int smc_llc_init(void) __init; #endif /* SMC_LLC_H */ diff --git a/net/socket.c b/net/socket.c index a93c99b518ca..d9a1ac233b35 100644 --- a/net/socket.c +++ b/net/socket.c @@ -104,7 +104,6 @@ #include <linux/ipv6_route.h> #include <linux/route.h> #include <linux/sockios.h> -#include <linux/atalk.h> #include <net/busy_poll.h> #include <linux/errqueue.h> @@ -234,7 +233,7 @@ static int move_addr_to_user(struct sockaddr_storage *kaddr, int klen, return __put_user(klen, ulen); } -static struct kmem_cache *sock_inode_cachep __read_mostly; +static struct kmem_cache *sock_inode_cachep __ro_after_init; static struct inode *sock_alloc_inode(struct super_block *sb) { @@ -991,10 +990,11 @@ static long sock_do_ioctl(struct net *net, struct socket *sock, * what to do with it - that's up to the protocol still. */ -static struct ns_common *get_net_ns(struct ns_common *ns) +struct ns_common *get_net_ns(struct ns_common *ns) { return &get_net(container_of(ns, struct net, ns))->ns; } +EXPORT_SYMBOL_GPL(get_net_ns); static long sock_ioctl(struct file *file, unsigned cmd, unsigned long arg) { @@ -1573,8 +1573,9 @@ SYSCALL_DEFINE4(accept4, int, fd, struct sockaddr __user *, upeer_sockaddr, goto out_fd; if (upeer_sockaddr) { - if (newsock->ops->getname(newsock, (struct sockaddr *)&address, - &len, 2) < 0) { + len = newsock->ops->getname(newsock, + (struct sockaddr *)&address, 2); + if (len < 0) { err = -ECONNABORTED; goto out_fd; } @@ -1654,7 +1655,7 @@ SYSCALL_DEFINE3(getsockname, int, fd, struct sockaddr __user *, usockaddr, { struct socket *sock; struct sockaddr_storage address; - int len, err, fput_needed; + int err, fput_needed; sock = sockfd_lookup_light(fd, &err, &fput_needed); if (!sock) @@ -1664,10 +1665,11 @@ SYSCALL_DEFINE3(getsockname, int, fd, struct sockaddr __user *, usockaddr, if (err) goto out_put; - err = sock->ops->getname(sock, (struct sockaddr *)&address, &len, 0); - if (err) + err = sock->ops->getname(sock, (struct sockaddr *)&address, 0); + if (err < 0) goto out_put; - err = move_addr_to_user(&address, len, usockaddr, usockaddr_len); + /* "err" is actually length in this case */ + err = move_addr_to_user(&address, err, usockaddr, usockaddr_len); out_put: fput_light(sock->file, fput_needed); @@ -1685,7 +1687,7 @@ SYSCALL_DEFINE3(getpeername, int, fd, struct sockaddr __user *, usockaddr, { struct socket *sock; struct sockaddr_storage address; - int len, err, fput_needed; + int err, fput_needed; sock = sockfd_lookup_light(fd, &err, &fput_needed); if (sock != NULL) { @@ -1695,11 +1697,10 @@ SYSCALL_DEFINE3(getpeername, int, fd, struct sockaddr __user *, usockaddr, return err; } - err = - sock->ops->getname(sock, (struct sockaddr *)&address, &len, - 1); - if (!err) - err = move_addr_to_user(&address, len, usockaddr, + err = sock->ops->getname(sock, (struct sockaddr *)&address, 1); + if (err >= 0) + /* "err" is actually length in this case */ + err = move_addr_to_user(&address, err, usockaddr, usockaddr_len); fput_light(sock->file, fput_needed); } @@ -2288,10 +2289,12 @@ int __sys_recvmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen, if (!sock) return err; - err = sock_error(sock->sk); - if (err) { - datagrams = err; - goto out_put; + if (likely(!(flags & MSG_ERRQUEUE))) { + err = sock_error(sock->sk); + if (err) { + datagrams = err; + goto out_put; + } } entry = mmsg; @@ -3166,17 +3169,15 @@ int kernel_connect(struct socket *sock, struct sockaddr *addr, int addrlen, } EXPORT_SYMBOL(kernel_connect); -int kernel_getsockname(struct socket *sock, struct sockaddr *addr, - int *addrlen) +int kernel_getsockname(struct socket *sock, struct sockaddr *addr) { - return sock->ops->getname(sock, addr, addrlen, 0); + return sock->ops->getname(sock, addr, 0); } EXPORT_SYMBOL(kernel_getsockname); -int kernel_getpeername(struct socket *sock, struct sockaddr *addr, - int *addrlen) +int kernel_getpeername(struct socket *sock, struct sockaddr *addr) { - return sock->ops->getname(sock, addr, addrlen, 1); + return sock->ops->getname(sock, addr, 1); } EXPORT_SYMBOL(kernel_getpeername); diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index 6e432ecd7f99..806395687bb6 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -1231,7 +1231,7 @@ static const struct sockaddr_in6 rpc_in6addr_loopback = { * negative errno is returned. */ static int rpc_sockname(struct net *net, struct sockaddr *sap, size_t salen, - struct sockaddr *buf, int buflen) + struct sockaddr *buf) { struct socket *sock; int err; @@ -1269,7 +1269,7 @@ static int rpc_sockname(struct net *net, struct sockaddr *sap, size_t salen, goto out_release; } - err = kernel_getsockname(sock, buf, &buflen); + err = kernel_getsockname(sock, buf); if (err < 0) { dprintk("RPC: getsockname failed (%d)\n", err); goto out_release; @@ -1353,7 +1353,7 @@ int rpc_localaddr(struct rpc_clnt *clnt, struct sockaddr *buf, size_t buflen) rcu_read_unlock(); rpc_set_port(sap, 0); - err = rpc_sockname(net, sap, salen, buf, buflen); + err = rpc_sockname(net, sap, salen, buf); put_net(net); if (err != 0) /* Couldn't discover local address, return ANYADDR */ diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index 943f2a745cd5..08cd951aaeea 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -832,12 +832,13 @@ static struct svc_xprt *svc_tcp_accept(struct svc_xprt *xprt) } set_bit(XPT_CONN, &svsk->sk_xprt.xpt_flags); - err = kernel_getpeername(newsock, sin, &slen); + err = kernel_getpeername(newsock, sin); if (err < 0) { net_warn_ratelimited("%s: peername failed (err %d)!\n", serv->sv_name, -err); goto failed; /* aborted connection or whatever */ } + slen = err; /* Ideally, we would want to reject connections from unauthorized * hosts here, but when we get encryption, the IP of the host won't @@ -866,7 +867,8 @@ static struct svc_xprt *svc_tcp_accept(struct svc_xprt *xprt) if (IS_ERR(newsvsk)) goto failed; svc_xprt_set_remote(&newsvsk->sk_xprt, sin, slen); - err = kernel_getsockname(newsock, sin, &slen); + err = kernel_getsockname(newsock, sin); + slen = err; if (unlikely(err < 0)) { dprintk("svc_tcp_accept: kernel_getsockname error %d\n", -err); slen = offsetof(struct sockaddr, sa_data); @@ -1465,7 +1467,8 @@ int svc_addsock(struct svc_serv *serv, const int fd, char *name_return, err = PTR_ERR(svsk); goto out; } - if (kernel_getsockname(svsk->sk_sock, sin, &salen) == 0) + salen = kernel_getsockname(svsk->sk_sock, sin); + if (salen >= 0) svc_xprt_set_local(&svsk->sk_xprt, sin, salen); svc_add_new_perm_xprt(serv, &svsk->sk_xprt); return svc_one_sock_name(svsk, name_return, len); @@ -1539,10 +1542,10 @@ static struct svc_xprt *svc_create_socket(struct svc_serv *serv, if (error < 0) goto bummer; - newlen = len; - error = kernel_getsockname(sock, newsin, &newlen); + error = kernel_getsockname(sock, newsin); if (error < 0) goto bummer; + newlen = error; if (protocol == IPPROTO_TCP) { if ((error = kernel_listen(sock, 64)) < 0) diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index a6b8c1f8f92a..956e29c1438d 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -1794,10 +1794,9 @@ static void xs_sock_set_reuseport(struct socket *sock) static unsigned short xs_sock_getport(struct socket *sock) { struct sockaddr_storage buf; - int buflen; unsigned short port = 0; - if (kernel_getsockname(sock, (struct sockaddr *)&buf, &buflen) < 0) + if (kernel_getsockname(sock, (struct sockaddr *)&buf) < 0) goto out; switch (buf.ss_family) { case AF_INET6: diff --git a/net/sysctl_net.c b/net/sysctl_net.c index 9aed6fe1bf1a..f424539829b7 100644 --- a/net/sysctl_net.c +++ b/net/sysctl_net.c @@ -89,6 +89,7 @@ static void __net_exit sysctl_net_exit(struct net *net) static struct pernet_operations sysctl_pernet_ops = { .init = sysctl_net_init, .exit = sysctl_net_exit, + .async = true, }; static struct ctl_table_header *net_header; diff --git a/net/tipc/Makefile b/net/tipc/Makefile index 37bb0bfbd936..1edb7192aa2f 100644 --- a/net/tipc/Makefile +++ b/net/tipc/Makefile @@ -9,7 +9,7 @@ tipc-y += addr.o bcast.o bearer.o \ core.o link.o discover.o msg.o \ name_distr.o subscr.o monitor.o name_table.o net.o \ netlink.o netlink_compat.o node.o socket.o eth_media.o \ - server.o socket.o group.o + topsrv.o socket.o group.o tipc-$(CONFIG_TIPC_MEDIA_UDP) += udp_media.o tipc-$(CONFIG_TIPC_MEDIA_IB) += ib_media.o diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c index 3e3dce3d4c63..f3d2e83313e1 100644 --- a/net/tipc/bearer.c +++ b/net/tipc/bearer.c @@ -956,11 +956,11 @@ int tipc_nl_bearer_add(struct sk_buff *skb, struct genl_info *info) int __tipc_nl_bearer_set(struct sk_buff *skb, struct genl_info *info) { - int err; - char *name; struct tipc_bearer *b; struct nlattr *attrs[TIPC_NLA_BEARER_MAX + 1]; struct net *net = sock_net(skb->sk); + char *name; + int err; if (!info->attrs[TIPC_NLA_BEARER]) return -EINVAL; @@ -987,8 +987,10 @@ int __tipc_nl_bearer_set(struct sk_buff *skb, struct genl_info *info) if (err) return err; - if (props[TIPC_NLA_PROP_TOL]) + if (props[TIPC_NLA_PROP_TOL]) { b->tolerance = nla_get_u32(props[TIPC_NLA_PROP_TOL]); + tipc_node_apply_tolerance(net, b); + } if (props[TIPC_NLA_PROP_PRIO]) b->priority = nla_get_u32(props[TIPC_NLA_PROP_PRIO]); if (props[TIPC_NLA_PROP_WIN]) diff --git a/net/tipc/core.h b/net/tipc/core.h index 20b21af2ff14..ff8b071654f5 100644 --- a/net/tipc/core.h +++ b/net/tipc/core.h @@ -64,7 +64,7 @@ struct tipc_bearer; struct tipc_bc_base; struct tipc_link; struct tipc_name_table; -struct tipc_server; +struct tipc_topsrv; struct tipc_monitor; #define TIPC_MOD_VER "2.0.0" @@ -112,7 +112,7 @@ struct tipc_net { struct list_head dist_queue; /* Topology subscription server */ - struct tipc_server *topsrv; + struct tipc_topsrv *topsrv; atomic_t subscription_count; }; @@ -131,7 +131,7 @@ static inline struct list_head *tipc_nodes(struct net *net) return &tipc_net(net)->node_list; } -static inline struct tipc_server *tipc_topsrv(struct net *net) +static inline struct tipc_topsrv *tipc_topsrv(struct net *net) { return tipc_net(net)->topsrv; } diff --git a/net/tipc/group.c b/net/tipc/group.c index 04e516d18054..d7a7befeddd4 100644 --- a/net/tipc/group.c +++ b/net/tipc/group.c @@ -37,7 +37,7 @@ #include "addr.h" #include "group.h" #include "bcast.h" -#include "server.h" +#include "topsrv.h" #include "msg.h" #include "socket.h" #include "node.h" diff --git a/net/tipc/link.c b/net/tipc/link.c index 2d6b2aed30e0..3c230466804d 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -2126,7 +2126,8 @@ void tipc_link_set_tolerance(struct tipc_link *l, u32 tol, struct sk_buff_head *xmitq) { l->tolerance = tol; - tipc_link_build_proto_msg(l, STATE_MSG, 0, 0, 0, tol, 0, xmitq); + if (link_is_up(l)) + tipc_link_build_proto_msg(l, STATE_MSG, 0, 0, 0, tol, 0, xmitq); } void tipc_link_set_prio(struct tipc_link *l, u32 prio, diff --git a/net/tipc/name_table.c b/net/tipc/name_table.c index ed0457cc99d6..e01c9c691ba2 100644 --- a/net/tipc/name_table.c +++ b/net/tipc/name_table.c @@ -326,10 +326,10 @@ static struct publication *tipc_nameseq_insert_publ(struct net *net, /* Any subscriptions waiting for notification? */ list_for_each_entry_safe(s, st, &nseq->subscriptions, nameseq_list) { - tipc_subscrp_report_overlap(s, publ->lower, publ->upper, - TIPC_PUBLISHED, publ->ref, - publ->node, publ->scope, - created_subseq); + tipc_sub_report_overlap(s, publ->lower, publ->upper, + TIPC_PUBLISHED, publ->ref, + publ->node, publ->scope, + created_subseq); } return publ; } @@ -397,10 +397,9 @@ found: /* Notify any waiting subscriptions */ list_for_each_entry_safe(s, st, &nseq->subscriptions, nameseq_list) { - tipc_subscrp_report_overlap(s, publ->lower, publ->upper, - TIPC_WITHDRAWN, publ->ref, - publ->node, publ->scope, - removed_subseq); + tipc_sub_report_overlap(s, publ->lower, publ->upper, + TIPC_WITHDRAWN, publ->ref, publ->node, + publ->scope, removed_subseq); } return publ; @@ -412,33 +411,37 @@ found: * sequence overlapping with the requested sequence */ static void tipc_nameseq_subscribe(struct name_seq *nseq, - struct tipc_subscription *s, - bool status) + struct tipc_subscription *sub) { struct sub_seq *sseq = nseq->sseqs; struct tipc_name_seq ns; + struct tipc_subscr *s = &sub->evt.s; + bool no_status; - tipc_subscrp_convert_seq(&s->evt.s.seq, s->swap, &ns); + ns.type = tipc_sub_read(s, seq.type); + ns.lower = tipc_sub_read(s, seq.lower); + ns.upper = tipc_sub_read(s, seq.upper); + no_status = tipc_sub_read(s, filter) & TIPC_SUB_NO_STATUS; - tipc_subscrp_get(s); - list_add(&s->nameseq_list, &nseq->subscriptions); + tipc_sub_get(sub); + list_add(&sub->nameseq_list, &nseq->subscriptions); - if (!status || !sseq) + if (no_status || !sseq) return; while (sseq != &nseq->sseqs[nseq->first_free]) { - if (tipc_subscrp_check_overlap(&ns, sseq->lower, sseq->upper)) { + if (tipc_sub_check_overlap(&ns, sseq->lower, sseq->upper)) { struct publication *crs; struct name_info *info = sseq->info; int must_report = 1; list_for_each_entry(crs, &info->zone_list, zone_list) { - tipc_subscrp_report_overlap(s, sseq->lower, - sseq->upper, - TIPC_PUBLISHED, - crs->ref, crs->node, - crs->scope, - must_report); + tipc_sub_report_overlap(sub, sseq->lower, + sseq->upper, + TIPC_PUBLISHED, + crs->ref, crs->node, + crs->scope, + must_report); must_report = 0; } } @@ -808,24 +811,27 @@ int tipc_nametbl_withdraw(struct net *net, u32 type, u32 lower, u32 ref, /** * tipc_nametbl_subscribe - add a subscription object to the name table */ -void tipc_nametbl_subscribe(struct tipc_subscription *s, bool status) +void tipc_nametbl_subscribe(struct tipc_subscription *sub) { - struct tipc_net *tn = net_generic(s->net, tipc_net_id); - u32 type = tipc_subscrp_convert_seq_type(s->evt.s.seq.type, s->swap); + struct tipc_net *tn = tipc_net(sub->net); + struct tipc_subscr *s = &sub->evt.s; + u32 type = tipc_sub_read(s, seq.type); int index = hash(type); struct name_seq *seq; struct tipc_name_seq ns; spin_lock_bh(&tn->nametbl_lock); - seq = nametbl_find_seq(s->net, type); + seq = nametbl_find_seq(sub->net, type); if (!seq) seq = tipc_nameseq_create(type, &tn->nametbl->seq_hlist[index]); if (seq) { spin_lock_bh(&seq->lock); - tipc_nameseq_subscribe(seq, s, status); + tipc_nameseq_subscribe(seq, sub); spin_unlock_bh(&seq->lock); } else { - tipc_subscrp_convert_seq(&s->evt.s.seq, s->swap, &ns); + ns.type = tipc_sub_read(s, seq.type); + ns.lower = tipc_sub_read(s, seq.lower); + ns.upper = tipc_sub_read(s, seq.upper); pr_warn("Failed to create subscription for {%u,%u,%u}\n", ns.type, ns.lower, ns.upper); } @@ -835,18 +841,19 @@ void tipc_nametbl_subscribe(struct tipc_subscription *s, bool status) /** * tipc_nametbl_unsubscribe - remove a subscription object from name table */ -void tipc_nametbl_unsubscribe(struct tipc_subscription *s) +void tipc_nametbl_unsubscribe(struct tipc_subscription *sub) { - struct tipc_net *tn = net_generic(s->net, tipc_net_id); + struct tipc_subscr *s = &sub->evt.s; + struct tipc_net *tn = tipc_net(sub->net); struct name_seq *seq; - u32 type = tipc_subscrp_convert_seq_type(s->evt.s.seq.type, s->swap); + u32 type = tipc_sub_read(s, seq.type); spin_lock_bh(&tn->nametbl_lock); - seq = nametbl_find_seq(s->net, type); + seq = nametbl_find_seq(sub->net, type); if (seq != NULL) { spin_lock_bh(&seq->lock); - list_del_init(&s->nameseq_list); - tipc_subscrp_put(s); + list_del_init(&sub->nameseq_list); + tipc_sub_put(sub); if (!seq->first_free && list_empty(&seq->subscriptions)) { hlist_del_init_rcu(&seq->ns_list); kfree(seq->sseqs); diff --git a/net/tipc/name_table.h b/net/tipc/name_table.h index f56e7cb3d436..17652602d5e2 100644 --- a/net/tipc/name_table.h +++ b/net/tipc/name_table.h @@ -120,7 +120,7 @@ struct publication *tipc_nametbl_insert_publ(struct net *net, u32 type, struct publication *tipc_nametbl_remove_publ(struct net *net, u32 type, u32 lower, u32 node, u32 ref, u32 key); -void tipc_nametbl_subscribe(struct tipc_subscription *s, bool status); +void tipc_nametbl_subscribe(struct tipc_subscription *s); void tipc_nametbl_unsubscribe(struct tipc_subscription *s); int tipc_nametbl_init(struct net *net); void tipc_nametbl_stop(struct net *net); diff --git a/net/tipc/node.c b/net/tipc/node.c index 9036d8756e73..389193d7cf67 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -1618,6 +1618,30 @@ discard: kfree_skb(skb); } +void tipc_node_apply_tolerance(struct net *net, struct tipc_bearer *b) +{ + struct tipc_net *tn = tipc_net(net); + int bearer_id = b->identity; + struct sk_buff_head xmitq; + struct tipc_link_entry *e; + struct tipc_node *n; + + __skb_queue_head_init(&xmitq); + + rcu_read_lock(); + + list_for_each_entry_rcu(n, &tn->node_list, list) { + tipc_node_write_lock(n); + e = &n->links[bearer_id]; + if (e->link) + tipc_link_set_tolerance(e->link, b->tolerance, &xmitq); + tipc_node_write_unlock(n); + tipc_bearer_xmit(net, bearer_id, &xmitq, &e->maddr); + } + + rcu_read_unlock(); +} + int tipc_nl_peer_rm(struct sk_buff *skb, struct genl_info *info) { struct net *net = sock_net(skb->sk); diff --git a/net/tipc/node.h b/net/tipc/node.h index acd58d23a70e..4ce5e3a185c0 100644 --- a/net/tipc/node.h +++ b/net/tipc/node.h @@ -65,6 +65,7 @@ void tipc_node_check_dest(struct net *net, u32 onode, struct tipc_media_addr *maddr, bool *respond, bool *dupl_addr); void tipc_node_delete_links(struct net *net, int bearer_id); +void tipc_node_apply_tolerance(struct net *net, struct tipc_bearer *b); int tipc_node_get_linkname(struct net *net, u32 bearer_id, u32 node, char *linkname, size_t len); int tipc_node_xmit(struct net *net, struct sk_buff_head *list, u32 dnode, diff --git a/net/tipc/server.c b/net/tipc/server.c deleted file mode 100644 index df0c563c90cd..000000000000 --- a/net/tipc/server.c +++ /dev/null @@ -1,710 +0,0 @@ -/* - * net/tipc/server.c: TIPC server infrastructure - * - * Copyright (c) 2012-2013, Wind River Systems - * All rights reserved. - * - * Redistribution and use in source and binary forms, with or without - * modification, are permitted provided that the following conditions are met: - * - * 1. Redistributions of source code must retain the above copyright - * notice, this list of conditions and the following disclaimer. - * 2. Redistributions in binary form must reproduce the above copyright - * notice, this list of conditions and the following disclaimer in the - * documentation and/or other materials provided with the distribution. - * 3. Neither the names of the copyright holders nor the names of its - * contributors may be used to endorse or promote products derived from - * this software without specific prior written permission. - * - * Alternatively, this software may be distributed under the terms of the - * GNU General Public License ("GPL") version 2 as published by the Free - * Software Foundation. - * - * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" - * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE - * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE - * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE - * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR - * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF - * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS - * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN - * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) - * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE - * POSSIBILITY OF SUCH DAMAGE. - */ - -#include "server.h" -#include "core.h" -#include "socket.h" -#include "addr.h" -#include "msg.h" -#include <net/sock.h> -#include <linux/module.h> - -/* Number of messages to send before rescheduling */ -#define MAX_SEND_MSG_COUNT 25 -#define MAX_RECV_MSG_COUNT 25 -#define CF_CONNECTED 1 -#define CF_SERVER 2 - -#define sock2con(x) ((struct tipc_conn *)(x)->sk_user_data) - -/** - * struct tipc_conn - TIPC connection structure - * @kref: reference counter to connection object - * @conid: connection identifier - * @sock: socket handler associated with connection - * @flags: indicates connection state - * @server: pointer to connected server - * @rwork: receive work item - * @usr_data: user-specified field - * @rx_action: what to do when connection socket is active - * @outqueue: pointer to first outbound message in queue - * @outqueue_lock: control access to the outqueue - * @outqueue: list of connection objects for its server - * @swork: send work item - */ -struct tipc_conn { - struct kref kref; - int conid; - struct socket *sock; - unsigned long flags; - struct tipc_server *server; - struct work_struct rwork; - int (*rx_action) (struct tipc_conn *con); - void *usr_data; - struct list_head outqueue; - spinlock_t outqueue_lock; - struct work_struct swork; -}; - -/* An entry waiting to be sent */ -struct outqueue_entry { - struct list_head list; - struct kvec iov; - struct sockaddr_tipc dest; -}; - -static void tipc_recv_work(struct work_struct *work); -static void tipc_send_work(struct work_struct *work); -static void tipc_clean_outqueues(struct tipc_conn *con); - -static void tipc_conn_kref_release(struct kref *kref) -{ - struct tipc_conn *con = container_of(kref, struct tipc_conn, kref); - struct tipc_server *s = con->server; - struct sockaddr_tipc *saddr = s->saddr; - struct socket *sock = con->sock; - struct sock *sk; - - if (sock) { - sk = sock->sk; - if (test_bit(CF_SERVER, &con->flags)) { - __module_get(sock->ops->owner); - __module_get(sk->sk_prot_creator->owner); - } - saddr->scope = -TIPC_NODE_SCOPE; - kernel_bind(sock, (struct sockaddr *)saddr, sizeof(*saddr)); - sock_release(sock); - con->sock = NULL; - } - spin_lock_bh(&s->idr_lock); - idr_remove(&s->conn_idr, con->conid); - s->idr_in_use--; - spin_unlock_bh(&s->idr_lock); - tipc_clean_outqueues(con); - kfree(con); -} - -static void conn_put(struct tipc_conn *con) -{ - kref_put(&con->kref, tipc_conn_kref_release); -} - -static void conn_get(struct tipc_conn *con) -{ - kref_get(&con->kref); -} - -static struct tipc_conn *tipc_conn_lookup(struct tipc_server *s, int conid) -{ - struct tipc_conn *con; - - spin_lock_bh(&s->idr_lock); - con = idr_find(&s->conn_idr, conid); - if (con) { - if (!test_bit(CF_CONNECTED, &con->flags) || - !kref_get_unless_zero(&con->kref)) - con = NULL; - } - spin_unlock_bh(&s->idr_lock); - return con; -} - -static void sock_data_ready(struct sock *sk) -{ - struct tipc_conn *con; - - read_lock_bh(&sk->sk_callback_lock); - con = sock2con(sk); - if (con && test_bit(CF_CONNECTED, &con->flags)) { - conn_get(con); - if (!queue_work(con->server->rcv_wq, &con->rwork)) - conn_put(con); - } - read_unlock_bh(&sk->sk_callback_lock); -} - -static void sock_write_space(struct sock *sk) -{ - struct tipc_conn *con; - - read_lock_bh(&sk->sk_callback_lock); - con = sock2con(sk); - if (con && test_bit(CF_CONNECTED, &con->flags)) { - conn_get(con); - if (!queue_work(con->server->send_wq, &con->swork)) - conn_put(con); - } - read_unlock_bh(&sk->sk_callback_lock); -} - -static void tipc_register_callbacks(struct socket *sock, struct tipc_conn *con) -{ - struct sock *sk = sock->sk; - - write_lock_bh(&sk->sk_callback_lock); - - sk->sk_data_ready = sock_data_ready; - sk->sk_write_space = sock_write_space; - sk->sk_user_data = con; - - con->sock = sock; - - write_unlock_bh(&sk->sk_callback_lock); -} - -static void tipc_close_conn(struct tipc_conn *con) -{ - struct tipc_server *s = con->server; - struct sock *sk = con->sock->sk; - bool disconnect = false; - - write_lock_bh(&sk->sk_callback_lock); - disconnect = test_and_clear_bit(CF_CONNECTED, &con->flags); - if (disconnect) { - sk->sk_user_data = NULL; - if (con->conid) - s->tipc_conn_release(con->conid, con->usr_data); - } - write_unlock_bh(&sk->sk_callback_lock); - - /* Handle concurrent calls from sending and receiving threads */ - if (!disconnect) - return; - - /* Don't flush pending works, -just let them expire */ - kernel_sock_shutdown(con->sock, SHUT_RDWR); - conn_put(con); -} - -static struct tipc_conn *tipc_alloc_conn(struct tipc_server *s) -{ - struct tipc_conn *con; - int ret; - - con = kzalloc(sizeof(struct tipc_conn), GFP_ATOMIC); - if (!con) - return ERR_PTR(-ENOMEM); - - kref_init(&con->kref); - INIT_LIST_HEAD(&con->outqueue); - spin_lock_init(&con->outqueue_lock); - INIT_WORK(&con->swork, tipc_send_work); - INIT_WORK(&con->rwork, tipc_recv_work); - - spin_lock_bh(&s->idr_lock); - ret = idr_alloc(&s->conn_idr, con, 0, 0, GFP_ATOMIC); - if (ret < 0) { - kfree(con); - spin_unlock_bh(&s->idr_lock); - return ERR_PTR(-ENOMEM); - } - con->conid = ret; - s->idr_in_use++; - spin_unlock_bh(&s->idr_lock); - - set_bit(CF_CONNECTED, &con->flags); - con->server = s; - - return con; -} - -static int tipc_receive_from_sock(struct tipc_conn *con) -{ - struct tipc_server *s = con->server; - struct sock *sk = con->sock->sk; - struct sockaddr_tipc addr; - struct msghdr msg = {}; - struct kvec iov; - void *buf; - int ret; - - buf = kmem_cache_alloc(s->rcvbuf_cache, GFP_ATOMIC); - if (!buf) { - ret = -ENOMEM; - goto out_close; - } - - iov.iov_base = buf; - iov.iov_len = s->max_rcvbuf_size; - msg.msg_name = &addr; - iov_iter_kvec(&msg.msg_iter, READ | ITER_KVEC, &iov, 1, iov.iov_len); - ret = sock_recvmsg(con->sock, &msg, MSG_DONTWAIT); - if (ret <= 0) { - kmem_cache_free(s->rcvbuf_cache, buf); - goto out_close; - } - - read_lock_bh(&sk->sk_callback_lock); - if (test_bit(CF_CONNECTED, &con->flags)) - ret = s->tipc_conn_recvmsg(sock_net(con->sock->sk), con->conid, - &addr, con->usr_data, buf, ret); - read_unlock_bh(&sk->sk_callback_lock); - kmem_cache_free(s->rcvbuf_cache, buf); - if (ret < 0) - tipc_conn_terminate(s, con->conid); - return ret; - -out_close: - if (ret != -EWOULDBLOCK) - tipc_close_conn(con); - else if (ret == 0) - /* Don't return success if we really got EOF */ - ret = -EAGAIN; - - return ret; -} - -static int tipc_accept_from_sock(struct tipc_conn *con) -{ - struct tipc_server *s = con->server; - struct socket *sock = con->sock; - struct socket *newsock; - struct tipc_conn *newcon; - int ret; - - ret = kernel_accept(sock, &newsock, O_NONBLOCK); - if (ret < 0) - return ret; - - newcon = tipc_alloc_conn(con->server); - if (IS_ERR(newcon)) { - ret = PTR_ERR(newcon); - sock_release(newsock); - return ret; - } - - newcon->rx_action = tipc_receive_from_sock; - tipc_register_callbacks(newsock, newcon); - - /* Notify that new connection is incoming */ - newcon->usr_data = s->tipc_conn_new(newcon->conid); - if (!newcon->usr_data) { - sock_release(newsock); - conn_put(newcon); - return -ENOMEM; - } - - /* Wake up receive process in case of 'SYN+' message */ - newsock->sk->sk_data_ready(newsock->sk); - return ret; -} - -static struct socket *tipc_create_listen_sock(struct tipc_conn *con) -{ - struct tipc_server *s = con->server; - struct socket *sock = NULL; - int ret; - - ret = sock_create_kern(s->net, AF_TIPC, SOCK_SEQPACKET, 0, &sock); - if (ret < 0) - return NULL; - ret = kernel_setsockopt(sock, SOL_TIPC, TIPC_IMPORTANCE, - (char *)&s->imp, sizeof(s->imp)); - if (ret < 0) - goto create_err; - ret = kernel_bind(sock, (struct sockaddr *)s->saddr, sizeof(*s->saddr)); - if (ret < 0) - goto create_err; - - switch (s->type) { - case SOCK_STREAM: - case SOCK_SEQPACKET: - con->rx_action = tipc_accept_from_sock; - - ret = kernel_listen(sock, 0); - if (ret < 0) - goto create_err; - break; - case SOCK_DGRAM: - case SOCK_RDM: - con->rx_action = tipc_receive_from_sock; - break; - default: - pr_err("Unknown socket type %d\n", s->type); - goto create_err; - } - - /* As server's listening socket owner and creator is the same module, - * we have to decrease TIPC module reference count to guarantee that - * it remains zero after the server socket is created, otherwise, - * executing "rmmod" command is unable to make TIPC module deleted - * after TIPC module is inserted successfully. - * - * However, the reference count is ever increased twice in - * sock_create_kern(): one is to increase the reference count of owner - * of TIPC socket's proto_ops struct; another is to increment the - * reference count of owner of TIPC proto struct. Therefore, we must - * decrement the module reference count twice to ensure that it keeps - * zero after server's listening socket is created. Of course, we - * must bump the module reference count twice as well before the socket - * is closed. - */ - module_put(sock->ops->owner); - module_put(sock->sk->sk_prot_creator->owner); - set_bit(CF_SERVER, &con->flags); - - return sock; - -create_err: - kernel_sock_shutdown(sock, SHUT_RDWR); - sock_release(sock); - return NULL; -} - -static int tipc_open_listening_sock(struct tipc_server *s) -{ - struct socket *sock; - struct tipc_conn *con; - - con = tipc_alloc_conn(s); - if (IS_ERR(con)) - return PTR_ERR(con); - - sock = tipc_create_listen_sock(con); - if (!sock) { - idr_remove(&s->conn_idr, con->conid); - s->idr_in_use--; - kfree(con); - return -EINVAL; - } - - tipc_register_callbacks(sock, con); - return 0; -} - -static struct outqueue_entry *tipc_alloc_entry(void *data, int len) -{ - struct outqueue_entry *entry; - void *buf; - - entry = kmalloc(sizeof(struct outqueue_entry), GFP_ATOMIC); - if (!entry) - return NULL; - - buf = kmemdup(data, len, GFP_ATOMIC); - if (!buf) { - kfree(entry); - return NULL; - } - - entry->iov.iov_base = buf; - entry->iov.iov_len = len; - - return entry; -} - -static void tipc_free_entry(struct outqueue_entry *e) -{ - kfree(e->iov.iov_base); - kfree(e); -} - -static void tipc_clean_outqueues(struct tipc_conn *con) -{ - struct outqueue_entry *e, *safe; - - spin_lock_bh(&con->outqueue_lock); - list_for_each_entry_safe(e, safe, &con->outqueue, list) { - list_del(&e->list); - tipc_free_entry(e); - } - spin_unlock_bh(&con->outqueue_lock); -} - -int tipc_conn_sendmsg(struct tipc_server *s, int conid, - struct sockaddr_tipc *addr, void *data, size_t len) -{ - struct outqueue_entry *e; - struct tipc_conn *con; - - con = tipc_conn_lookup(s, conid); - if (!con) - return -EINVAL; - - if (!test_bit(CF_CONNECTED, &con->flags)) { - conn_put(con); - return 0; - } - - e = tipc_alloc_entry(data, len); - if (!e) { - conn_put(con); - return -ENOMEM; - } - - if (addr) - memcpy(&e->dest, addr, sizeof(struct sockaddr_tipc)); - - spin_lock_bh(&con->outqueue_lock); - list_add_tail(&e->list, &con->outqueue); - spin_unlock_bh(&con->outqueue_lock); - - if (!queue_work(s->send_wq, &con->swork)) - conn_put(con); - return 0; -} - -void tipc_conn_terminate(struct tipc_server *s, int conid) -{ - struct tipc_conn *con; - - con = tipc_conn_lookup(s, conid); - if (con) { - tipc_close_conn(con); - conn_put(con); - } -} - -bool tipc_topsrv_kern_subscr(struct net *net, u32 port, u32 type, u32 lower, - u32 upper, u32 filter, int *conid) -{ - struct tipc_subscriber *scbr; - struct tipc_subscr sub; - struct tipc_server *s; - struct tipc_conn *con; - - sub.seq.type = type; - sub.seq.lower = lower; - sub.seq.upper = upper; - sub.timeout = TIPC_WAIT_FOREVER; - sub.filter = filter; - *(u32 *)&sub.usr_handle = port; - - con = tipc_alloc_conn(tipc_topsrv(net)); - if (IS_ERR(con)) - return false; - - *conid = con->conid; - s = con->server; - scbr = s->tipc_conn_new(*conid); - if (!scbr) { - conn_put(con); - return false; - } - - con->usr_data = scbr; - con->sock = NULL; - s->tipc_conn_recvmsg(net, *conid, NULL, scbr, &sub, sizeof(sub)); - return true; -} - -void tipc_topsrv_kern_unsubscr(struct net *net, int conid) -{ - struct tipc_conn *con; - struct tipc_server *srv; - - con = tipc_conn_lookup(tipc_topsrv(net), conid); - if (!con) - return; - - test_and_clear_bit(CF_CONNECTED, &con->flags); - srv = con->server; - if (con->conid) - srv->tipc_conn_release(con->conid, con->usr_data); - conn_put(con); - conn_put(con); -} - -static void tipc_send_kern_top_evt(struct net *net, struct tipc_event *evt) -{ - u32 port = *(u32 *)&evt->s.usr_handle; - u32 self = tipc_own_addr(net); - struct sk_buff_head evtq; - struct sk_buff *skb; - - skb = tipc_msg_create(TOP_SRV, 0, INT_H_SIZE, sizeof(*evt), - self, self, port, port, 0); - if (!skb) - return; - msg_set_dest_droppable(buf_msg(skb), true); - memcpy(msg_data(buf_msg(skb)), evt, sizeof(*evt)); - skb_queue_head_init(&evtq); - __skb_queue_tail(&evtq, skb); - tipc_sk_rcv(net, &evtq); -} - -static void tipc_send_to_sock(struct tipc_conn *con) -{ - struct tipc_server *s = con->server; - struct outqueue_entry *e; - struct tipc_event *evt; - struct msghdr msg; - int count = 0; - int ret; - - spin_lock_bh(&con->outqueue_lock); - while (test_bit(CF_CONNECTED, &con->flags)) { - e = list_entry(con->outqueue.next, struct outqueue_entry, list); - if ((struct list_head *) e == &con->outqueue) - break; - - spin_unlock_bh(&con->outqueue_lock); - - if (con->sock) { - memset(&msg, 0, sizeof(msg)); - msg.msg_flags = MSG_DONTWAIT; - if (s->type == SOCK_DGRAM || s->type == SOCK_RDM) { - msg.msg_name = &e->dest; - msg.msg_namelen = sizeof(struct sockaddr_tipc); - } - ret = kernel_sendmsg(con->sock, &msg, &e->iov, 1, - e->iov.iov_len); - if (ret == -EWOULDBLOCK || ret == 0) { - cond_resched(); - goto out; - } else if (ret < 0) { - goto send_err; - } - } else { - evt = e->iov.iov_base; - tipc_send_kern_top_evt(s->net, evt); - } - /* Don't starve users filling buffers */ - if (++count >= MAX_SEND_MSG_COUNT) { - cond_resched(); - count = 0; - } - - spin_lock_bh(&con->outqueue_lock); - list_del(&e->list); - tipc_free_entry(e); - } - spin_unlock_bh(&con->outqueue_lock); -out: - return; - -send_err: - tipc_close_conn(con); -} - -static void tipc_recv_work(struct work_struct *work) -{ - struct tipc_conn *con = container_of(work, struct tipc_conn, rwork); - int count = 0; - - while (test_bit(CF_CONNECTED, &con->flags)) { - if (con->rx_action(con)) - break; - - /* Don't flood Rx machine */ - if (++count >= MAX_RECV_MSG_COUNT) { - cond_resched(); - count = 0; - } - } - conn_put(con); -} - -static void tipc_send_work(struct work_struct *work) -{ - struct tipc_conn *con = container_of(work, struct tipc_conn, swork); - - if (test_bit(CF_CONNECTED, &con->flags)) - tipc_send_to_sock(con); - - conn_put(con); -} - -static void tipc_work_stop(struct tipc_server *s) -{ - destroy_workqueue(s->rcv_wq); - destroy_workqueue(s->send_wq); -} - -static int tipc_work_start(struct tipc_server *s) -{ - s->rcv_wq = alloc_ordered_workqueue("tipc_rcv", 0); - if (!s->rcv_wq) { - pr_err("can't start tipc receive workqueue\n"); - return -ENOMEM; - } - - s->send_wq = alloc_ordered_workqueue("tipc_send", 0); - if (!s->send_wq) { - pr_err("can't start tipc send workqueue\n"); - destroy_workqueue(s->rcv_wq); - return -ENOMEM; - } - - return 0; -} - -int tipc_server_start(struct tipc_server *s) -{ - int ret; - - spin_lock_init(&s->idr_lock); - idr_init(&s->conn_idr); - s->idr_in_use = 0; - - s->rcvbuf_cache = kmem_cache_create(s->name, s->max_rcvbuf_size, - 0, SLAB_HWCACHE_ALIGN, NULL); - if (!s->rcvbuf_cache) - return -ENOMEM; - - ret = tipc_work_start(s); - if (ret < 0) { - kmem_cache_destroy(s->rcvbuf_cache); - return ret; - } - ret = tipc_open_listening_sock(s); - if (ret < 0) { - tipc_work_stop(s); - kmem_cache_destroy(s->rcvbuf_cache); - return ret; - } - return ret; -} - -void tipc_server_stop(struct tipc_server *s) -{ - struct tipc_conn *con; - int id; - - spin_lock_bh(&s->idr_lock); - for (id = 0; s->idr_in_use; id++) { - con = idr_find(&s->conn_idr, id); - if (con) { - spin_unlock_bh(&s->idr_lock); - tipc_close_conn(con); - spin_lock_bh(&s->idr_lock); - } - } - spin_unlock_bh(&s->idr_lock); - - tipc_work_stop(s); - kmem_cache_destroy(s->rcvbuf_cache); - idr_destroy(&s->conn_idr); -} diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 7dfa9fc99ec3..8b04e601311c 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -666,7 +666,7 @@ exit: * a completely predictable manner). */ static int tipc_getname(struct socket *sock, struct sockaddr *uaddr, - int *uaddr_len, int peer) + int peer) { struct sockaddr_tipc *addr = (struct sockaddr_tipc *)uaddr; struct sock *sk = sock->sk; @@ -685,13 +685,12 @@ static int tipc_getname(struct socket *sock, struct sockaddr *uaddr, addr->addr.id.node = tn->own_addr; } - *uaddr_len = sizeof(*addr); addr->addrtype = TIPC_ADDR_ID; addr->family = AF_TIPC; addr->scope = 0; addr->addr.name.domain = 0; - return 0; + return sizeof(*addr); } /** diff --git a/net/tipc/subscr.c b/net/tipc/subscr.c index 68e26470c516..6925a989569b 100644 --- a/net/tipc/subscr.c +++ b/net/tipc/subscr.c @@ -1,7 +1,7 @@ /* * net/tipc/subscr.c: TIPC network topology service * - * Copyright (c) 2000-2006, Ericsson AB + * Copyright (c) 2000-2017, Ericsson AB * Copyright (c) 2005-2007, 2010-2013, Wind River Systems * All rights reserved. * @@ -38,61 +38,30 @@ #include "name_table.h" #include "subscr.h" -/** - * struct tipc_subscriber - TIPC network topology subscriber - * @kref: reference counter to tipc_subscription object - * @conid: connection identifier to server connecting to subscriber - * @lock: control access to subscriber - * @subscrp_list: list of subscription objects for this subscriber - */ -struct tipc_subscriber { - struct kref kref; - int conid; - spinlock_t lock; - struct list_head subscrp_list; -}; - -static void tipc_subscrb_put(struct tipc_subscriber *subscriber); - -/** - * htohl - convert value to endianness used by destination - * @in: value to convert - * @swap: non-zero if endianness must be reversed - * - * Returns converted value - */ -static u32 htohl(u32 in, int swap) -{ - return swap ? swab32(in) : in; -} - -static void tipc_subscrp_send_event(struct tipc_subscription *sub, - u32 found_lower, u32 found_upper, - u32 event, u32 port_ref, u32 node) +static void tipc_sub_send_event(struct tipc_subscription *sub, + u32 found_lower, u32 found_upper, + u32 event, u32 port, u32 node) { - struct tipc_net *tn = net_generic(sub->net, tipc_net_id); - struct tipc_subscriber *subscriber = sub->subscriber; - struct kvec msg_sect; + struct tipc_event *evt = &sub->evt; - msg_sect.iov_base = (void *)&sub->evt; - msg_sect.iov_len = sizeof(struct tipc_event); - sub->evt.event = htohl(event, sub->swap); - sub->evt.found_lower = htohl(found_lower, sub->swap); - sub->evt.found_upper = htohl(found_upper, sub->swap); - sub->evt.port.ref = htohl(port_ref, sub->swap); - sub->evt.port.node = htohl(node, sub->swap); - tipc_conn_sendmsg(tn->topsrv, subscriber->conid, NULL, - msg_sect.iov_base, msg_sect.iov_len); + if (sub->inactive) + return; + tipc_evt_write(evt, event, event); + tipc_evt_write(evt, found_lower, found_lower); + tipc_evt_write(evt, found_upper, found_upper); + tipc_evt_write(evt, port.ref, port); + tipc_evt_write(evt, port.node, node); + tipc_topsrv_queue_evt(sub->net, sub->conid, event, evt); } /** - * tipc_subscrp_check_overlap - test for subscription overlap with the + * tipc_sub_check_overlap - test for subscription overlap with the * given values * * Returns 1 if there is overlap, otherwise 0. */ -int tipc_subscrp_check_overlap(struct tipc_name_seq *seq, u32 found_lower, - u32 found_upper) +int tipc_sub_check_overlap(struct tipc_name_seq *seq, u32 found_lower, + u32 found_upper) { if (found_lower < seq->lower) found_lower = seq->lower; @@ -103,298 +72,98 @@ int tipc_subscrp_check_overlap(struct tipc_name_seq *seq, u32 found_lower, return 1; } -u32 tipc_subscrp_convert_seq_type(u32 type, int swap) -{ - return htohl(type, swap); -} - -void tipc_subscrp_convert_seq(struct tipc_name_seq *in, int swap, - struct tipc_name_seq *out) -{ - out->type = htohl(in->type, swap); - out->lower = htohl(in->lower, swap); - out->upper = htohl(in->upper, swap); -} - -void tipc_subscrp_report_overlap(struct tipc_subscription *sub, u32 found_lower, - u32 found_upper, u32 event, u32 port_ref, - u32 node, u32 scope, int must) +void tipc_sub_report_overlap(struct tipc_subscription *sub, + u32 found_lower, u32 found_upper, + u32 event, u32 port, u32 node, + u32 scope, int must) { - u32 filter = htohl(sub->evt.s.filter, sub->swap); + struct tipc_subscr *s = &sub->evt.s; + u32 filter = tipc_sub_read(s, filter); struct tipc_name_seq seq; - tipc_subscrp_convert_seq(&sub->evt.s.seq, sub->swap, &seq); - if (!tipc_subscrp_check_overlap(&seq, found_lower, found_upper)) + seq.type = tipc_sub_read(s, seq.type); + seq.lower = tipc_sub_read(s, seq.lower); + seq.upper = tipc_sub_read(s, seq.upper); + + if (!tipc_sub_check_overlap(&seq, found_lower, found_upper)) return; + if (!must && !(filter & TIPC_SUB_PORTS)) return; if (filter & TIPC_SUB_CLUSTER_SCOPE && scope == TIPC_NODE_SCOPE) return; if (filter & TIPC_SUB_NODE_SCOPE && scope != TIPC_NODE_SCOPE) return; - - tipc_subscrp_send_event(sub, found_lower, found_upper, event, port_ref, - node); + spin_lock(&sub->lock); + tipc_sub_send_event(sub, found_lower, found_upper, + event, port, node); + spin_unlock(&sub->lock); } -static void tipc_subscrp_timeout(struct timer_list *t) +static void tipc_sub_timeout(struct timer_list *t) { struct tipc_subscription *sub = from_timer(sub, t, timer); - struct tipc_subscriber *subscriber = sub->subscriber; - - spin_lock_bh(&subscriber->lock); - tipc_nametbl_unsubscribe(sub); - list_del(&sub->subscrp_list); - spin_unlock_bh(&subscriber->lock); - - /* Notify subscriber of timeout */ - tipc_subscrp_send_event(sub, sub->evt.s.seq.lower, sub->evt.s.seq.upper, - TIPC_SUBSCR_TIMEOUT, 0, 0); - - tipc_subscrp_put(sub); -} - -static void tipc_subscrb_kref_release(struct kref *kref) -{ - kfree(container_of(kref,struct tipc_subscriber, kref)); -} - -static void tipc_subscrb_put(struct tipc_subscriber *subscriber) -{ - kref_put(&subscriber->kref, tipc_subscrb_kref_release); -} + struct tipc_subscr *s = &sub->evt.s; -static void tipc_subscrb_get(struct tipc_subscriber *subscriber) -{ - kref_get(&subscriber->kref); + spin_lock(&sub->lock); + tipc_sub_send_event(sub, s->seq.lower, s->seq.upper, + TIPC_SUBSCR_TIMEOUT, 0, 0); + sub->inactive = true; + spin_unlock(&sub->lock); } -static void tipc_subscrp_kref_release(struct kref *kref) +static void tipc_sub_kref_release(struct kref *kref) { - struct tipc_subscription *sub = container_of(kref, - struct tipc_subscription, - kref); - struct tipc_net *tn = net_generic(sub->net, tipc_net_id); - struct tipc_subscriber *subscriber = sub->subscriber; - - atomic_dec(&tn->subscription_count); - kfree(sub); - tipc_subscrb_put(subscriber); + kfree(container_of(kref, struct tipc_subscription, kref)); } -void tipc_subscrp_put(struct tipc_subscription *subscription) +void tipc_sub_put(struct tipc_subscription *subscription) { - kref_put(&subscription->kref, tipc_subscrp_kref_release); + kref_put(&subscription->kref, tipc_sub_kref_release); } -void tipc_subscrp_get(struct tipc_subscription *subscription) +void tipc_sub_get(struct tipc_subscription *subscription) { kref_get(&subscription->kref); } -/* tipc_subscrb_subscrp_delete - delete a specific subscription or all - * subscriptions for a given subscriber. - */ -static void tipc_subscrb_subscrp_delete(struct tipc_subscriber *subscriber, - struct tipc_subscr *s) -{ - struct list_head *subscription_list = &subscriber->subscrp_list; - struct tipc_subscription *sub, *temp; - u32 timeout; - - spin_lock_bh(&subscriber->lock); - list_for_each_entry_safe(sub, temp, subscription_list, subscrp_list) { - if (s && memcmp(s, &sub->evt.s, sizeof(struct tipc_subscr))) - continue; - - timeout = htohl(sub->evt.s.timeout, sub->swap); - if (timeout == TIPC_WAIT_FOREVER || del_timer(&sub->timer)) { - tipc_nametbl_unsubscribe(sub); - list_del(&sub->subscrp_list); - tipc_subscrp_put(sub); - } - - if (s) - break; - } - spin_unlock_bh(&subscriber->lock); -} - -static struct tipc_subscriber *tipc_subscrb_create(int conid) -{ - struct tipc_subscriber *subscriber; - - subscriber = kzalloc(sizeof(*subscriber), GFP_ATOMIC); - if (!subscriber) { - pr_warn("Subscriber rejected, no memory\n"); - return NULL; - } - INIT_LIST_HEAD(&subscriber->subscrp_list); - kref_init(&subscriber->kref); - subscriber->conid = conid; - spin_lock_init(&subscriber->lock); - - return subscriber; -} - -static void tipc_subscrb_delete(struct tipc_subscriber *subscriber) -{ - tipc_subscrb_subscrp_delete(subscriber, NULL); - tipc_subscrb_put(subscriber); -} - -static void tipc_subscrp_cancel(struct tipc_subscr *s, - struct tipc_subscriber *subscriber) -{ - tipc_subscrb_get(subscriber); - tipc_subscrb_subscrp_delete(subscriber, s); - tipc_subscrb_put(subscriber); -} - -static struct tipc_subscription *tipc_subscrp_create(struct net *net, - struct tipc_subscr *s, - int swap) +struct tipc_subscription *tipc_sub_subscribe(struct net *net, + struct tipc_subscr *s, + int conid) { - struct tipc_net *tn = net_generic(net, tipc_net_id); + u32 filter = tipc_sub_read(s, filter); struct tipc_subscription *sub; - u32 filter = htohl(s->filter, swap); + u32 timeout; - /* Refuse subscription if global limit exceeded */ - if (atomic_read(&tn->subscription_count) >= TIPC_MAX_SUBSCRIPTIONS) { - pr_warn("Subscription rejected, limit reached (%u)\n", - TIPC_MAX_SUBSCRIPTIONS); + if ((filter & TIPC_SUB_PORTS && filter & TIPC_SUB_SERVICE) || + (tipc_sub_read(s, seq.lower) > tipc_sub_read(s, seq.upper))) { + pr_warn("Subscription rejected, illegal request\n"); return NULL; } - - /* Allocate subscription object */ sub = kmalloc(sizeof(*sub), GFP_ATOMIC); if (!sub) { pr_warn("Subscription rejected, no memory\n"); return NULL; } - - /* Initialize subscription object */ sub->net = net; - if (((filter & TIPC_SUB_PORTS) && (filter & TIPC_SUB_SERVICE)) || - (htohl(s->seq.lower, swap) > htohl(s->seq.upper, swap))) { - pr_warn("Subscription rejected, illegal request\n"); - kfree(sub); - return NULL; - } - - sub->swap = swap; + sub->conid = conid; + sub->inactive = false; memcpy(&sub->evt.s, s, sizeof(*s)); - atomic_inc(&tn->subscription_count); + spin_lock_init(&sub->lock); kref_init(&sub->kref); - return sub; -} - -static int tipc_subscrp_subscribe(struct net *net, struct tipc_subscr *s, - struct tipc_subscriber *subscriber, int swap, - bool status) -{ - struct tipc_subscription *sub = NULL; - u32 timeout; - - sub = tipc_subscrp_create(net, s, swap); - if (!sub) - return -1; - - spin_lock_bh(&subscriber->lock); - list_add(&sub->subscrp_list, &subscriber->subscrp_list); - sub->subscriber = subscriber; - tipc_nametbl_subscribe(sub, status); - tipc_subscrb_get(subscriber); - spin_unlock_bh(&subscriber->lock); - - timer_setup(&sub->timer, tipc_subscrp_timeout, 0); - timeout = htohl(sub->evt.s.timeout, swap); - + tipc_nametbl_subscribe(sub); + timer_setup(&sub->timer, tipc_sub_timeout, 0); + timeout = tipc_sub_read(&sub->evt.s, timeout); if (timeout != TIPC_WAIT_FOREVER) mod_timer(&sub->timer, jiffies + msecs_to_jiffies(timeout)); - return 0; -} - -/* Handle one termination request for the subscriber */ -static void tipc_subscrb_release_cb(int conid, void *usr_data) -{ - tipc_subscrb_delete((struct tipc_subscriber *)usr_data); -} - -/* Handle one request to create a new subscription for the subscriber */ -static int tipc_subscrb_rcv_cb(struct net *net, int conid, - struct sockaddr_tipc *addr, void *usr_data, - void *buf, size_t len) -{ - struct tipc_subscriber *subscriber = usr_data; - struct tipc_subscr *s = (struct tipc_subscr *)buf; - bool status; - int swap; - - /* Determine subscriber's endianness */ - swap = !(s->filter & (TIPC_SUB_PORTS | TIPC_SUB_SERVICE | - TIPC_SUB_CANCEL)); - - /* Detect & process a subscription cancellation request */ - if (s->filter & htohl(TIPC_SUB_CANCEL, swap)) { - s->filter &= ~htohl(TIPC_SUB_CANCEL, swap); - tipc_subscrp_cancel(s, subscriber); - return 0; - } - status = !(s->filter & htohl(TIPC_SUB_NO_STATUS, swap)); - return tipc_subscrp_subscribe(net, s, subscriber, swap, status); -} - -/* Handle one request to establish a new subscriber */ -static void *tipc_subscrb_connect_cb(int conid) -{ - return (void *)tipc_subscrb_create(conid); -} - -int tipc_topsrv_start(struct net *net) -{ - struct tipc_net *tn = net_generic(net, tipc_net_id); - const char name[] = "topology_server"; - struct tipc_server *topsrv; - struct sockaddr_tipc *saddr; - - saddr = kzalloc(sizeof(*saddr), GFP_ATOMIC); - if (!saddr) - return -ENOMEM; - saddr->family = AF_TIPC; - saddr->addrtype = TIPC_ADDR_NAMESEQ; - saddr->addr.nameseq.type = TIPC_TOP_SRV; - saddr->addr.nameseq.lower = TIPC_TOP_SRV; - saddr->addr.nameseq.upper = TIPC_TOP_SRV; - saddr->scope = TIPC_NODE_SCOPE; - - topsrv = kzalloc(sizeof(*topsrv), GFP_ATOMIC); - if (!topsrv) { - kfree(saddr); - return -ENOMEM; - } - topsrv->net = net; - topsrv->saddr = saddr; - topsrv->imp = TIPC_CRITICAL_IMPORTANCE; - topsrv->type = SOCK_SEQPACKET; - topsrv->max_rcvbuf_size = sizeof(struct tipc_subscr); - topsrv->tipc_conn_recvmsg = tipc_subscrb_rcv_cb; - topsrv->tipc_conn_new = tipc_subscrb_connect_cb; - topsrv->tipc_conn_release = tipc_subscrb_release_cb; - - strncpy(topsrv->name, name, strlen(name) + 1); - tn->topsrv = topsrv; - atomic_set(&tn->subscription_count, 0); - - return tipc_server_start(topsrv); + return sub; } -void tipc_topsrv_stop(struct net *net) +void tipc_sub_unsubscribe(struct tipc_subscription *sub) { - struct tipc_net *tn = net_generic(net, tipc_net_id); - struct tipc_server *topsrv = tn->topsrv; - - tipc_server_stop(topsrv); - kfree(topsrv->saddr); - kfree(topsrv); + tipc_nametbl_unsubscribe(sub); + if (sub->evt.s.timeout != TIPC_WAIT_FOREVER) + del_timer_sync(&sub->timer); + list_del(&sub->sub_list); + tipc_sub_put(sub); } diff --git a/net/tipc/subscr.h b/net/tipc/subscr.h index f3edca775d9f..8b2d22b18f22 100644 --- a/net/tipc/subscr.h +++ b/net/tipc/subscr.h @@ -1,7 +1,7 @@ /* * net/tipc/subscr.h: Include file for TIPC network topology service * - * Copyright (c) 2003-2006, Ericsson AB + * Copyright (c) 2003-2017, Ericsson AB * Copyright (c) 2005-2007, 2012-2013, Wind River Systems * All rights reserved. * @@ -37,48 +37,72 @@ #ifndef _TIPC_SUBSCR_H #define _TIPC_SUBSCR_H -#include "server.h" +#include "topsrv.h" -#define TIPC_MAX_SUBSCRIPTIONS 65535 -#define TIPC_MAX_PUBLICATIONS 65535 +#define TIPC_MAX_SUBSCR 65535 +#define TIPC_MAX_PUBLICATIONS 65535 struct tipc_subscription; -struct tipc_subscriber; +struct tipc_conn; /** * struct tipc_subscription - TIPC network topology subscription object * @subscriber: pointer to its subscriber * @seq: name sequence associated with subscription - * @net: point to network namespace * @timer: timer governing subscription duration (optional) * @nameseq_list: adjacent subscriptions in name sequence's subscription list - * @subscrp_list: adjacent subscriptions in subscriber's subscription list - * @swap: indicates if subscriber uses opposite endianness in its messages + * @sub_list: adjacent subscriptions in subscriber's subscription list * @evt: template for events generated by subscription */ struct tipc_subscription { struct kref kref; - struct tipc_subscriber *subscriber; struct net *net; struct timer_list timer; struct list_head nameseq_list; - struct list_head subscrp_list; - int swap; + struct list_head sub_list; struct tipc_event evt; + int conid; + bool inactive; + spinlock_t lock; /* serialize up/down and timer events */ }; -int tipc_subscrp_check_overlap(struct tipc_name_seq *seq, u32 found_lower, - u32 found_upper); -void tipc_subscrp_report_overlap(struct tipc_subscription *sub, - u32 found_lower, u32 found_upper, u32 event, - u32 port_ref, u32 node, u32 scope, int must); -void tipc_subscrp_convert_seq(struct tipc_name_seq *in, int swap, - struct tipc_name_seq *out); -u32 tipc_subscrp_convert_seq_type(u32 type, int swap); +struct tipc_subscription *tipc_sub_subscribe(struct net *net, + struct tipc_subscr *s, + int conid); +void tipc_sub_unsubscribe(struct tipc_subscription *sub); + +int tipc_sub_check_overlap(struct tipc_name_seq *seq, u32 found_lower, + u32 found_upper); +void tipc_sub_report_overlap(struct tipc_subscription *sub, + u32 found_lower, u32 found_upper, + u32 event, u32 port, u32 node, + u32 scope, int must); int tipc_topsrv_start(struct net *net); void tipc_topsrv_stop(struct net *net); -void tipc_subscrp_put(struct tipc_subscription *subscription); -void tipc_subscrp_get(struct tipc_subscription *subscription); +void tipc_sub_put(struct tipc_subscription *subscription); +void tipc_sub_get(struct tipc_subscription *subscription); + +#define TIPC_FILTER_MASK (TIPC_SUB_PORTS | TIPC_SUB_SERVICE | TIPC_SUB_CANCEL) + +/* tipc_sub_read - return field_ of struct sub_ in host endian format + */ +#define tipc_sub_read(sub_, field_) \ + ({ \ + struct tipc_subscr *sub__ = sub_; \ + u32 val__ = (sub__)->field_; \ + int swap_ = !((sub__)->filter & TIPC_FILTER_MASK); \ + (swap_ ? swab32(val__) : val__); \ + }) + +/* tipc_evt_write - write val_ to field_ of struct evt_ in user endian format + */ +#define tipc_evt_write(evt_, field_, val_) \ + ({ \ + struct tipc_event *evt__ = evt_; \ + u32 val__ = val_; \ + int swap_ = !((evt__)->s.filter & (TIPC_FILTER_MASK)); \ + (evt__)->field_ = swap_ ? swab32(val__) : val__; \ + }) #endif diff --git a/net/tipc/topsrv.c b/net/tipc/topsrv.c new file mode 100644 index 000000000000..c8e34ef22c30 --- /dev/null +++ b/net/tipc/topsrv.c @@ -0,0 +1,703 @@ +/* + * net/tipc/server.c: TIPC server infrastructure + * + * Copyright (c) 2012-2013, Wind River Systems + * Copyright (c) 2017-2018, Ericsson AB + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the names of the copyright holders nor the names of its + * contributors may be used to endorse or promote products derived from + * this software without specific prior written permission. + * + * Alternatively, this software may be distributed under the terms of the + * GNU General Public License ("GPL") version 2 as published by the Free + * Software Foundation. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN + * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE + * POSSIBILITY OF SUCH DAMAGE. + */ + +#include "subscr.h" +#include "topsrv.h" +#include "core.h" +#include "socket.h" +#include "addr.h" +#include "msg.h" +#include <net/sock.h> +#include <linux/module.h> + +/* Number of messages to send before rescheduling */ +#define MAX_SEND_MSG_COUNT 25 +#define MAX_RECV_MSG_COUNT 25 +#define CF_CONNECTED 1 +#define CF_SERVER 2 + +#define TIPC_SERVER_NAME_LEN 32 + +/** + * struct tipc_topsrv - TIPC server structure + * @conn_idr: identifier set of connection + * @idr_lock: protect the connection identifier set + * @idr_in_use: amount of allocated identifier entry + * @net: network namspace instance + * @rcvbuf_cache: memory cache of server receive buffer + * @rcv_wq: receive workqueue + * @send_wq: send workqueue + * @max_rcvbuf_size: maximum permitted receive message length + * @tipc_conn_new: callback will be called when new connection is incoming + * @tipc_conn_release: callback will be called before releasing the connection + * @tipc_conn_recvmsg: callback will be called when message arrives + * @name: server name + * @imp: message importance + * @type: socket type + */ +struct tipc_topsrv { + struct idr conn_idr; + spinlock_t idr_lock; /* for idr list */ + int idr_in_use; + struct net *net; + struct work_struct awork; + struct workqueue_struct *rcv_wq; + struct workqueue_struct *send_wq; + int max_rcvbuf_size; + struct socket *listener; + char name[TIPC_SERVER_NAME_LEN]; +}; + +/** + * struct tipc_conn - TIPC connection structure + * @kref: reference counter to connection object + * @conid: connection identifier + * @sock: socket handler associated with connection + * @flags: indicates connection state + * @server: pointer to connected server + * @sub_list: lsit to all pertaing subscriptions + * @sub_lock: lock protecting the subscription list + * @outqueue_lock: control access to the outqueue + * @rwork: receive work item + * @rx_action: what to do when connection socket is active + * @outqueue: pointer to first outbound message in queue + * @outqueue_lock: control access to the outqueue + * @swork: send work item + */ +struct tipc_conn { + struct kref kref; + int conid; + struct socket *sock; + unsigned long flags; + struct tipc_topsrv *server; + struct list_head sub_list; + spinlock_t sub_lock; /* for subscription list */ + struct work_struct rwork; + struct list_head outqueue; + spinlock_t outqueue_lock; /* for outqueue */ + struct work_struct swork; +}; + +/* An entry waiting to be sent */ +struct outqueue_entry { + bool inactive; + struct tipc_event evt; + struct list_head list; +}; + +static void tipc_conn_recv_work(struct work_struct *work); +static void tipc_conn_send_work(struct work_struct *work); +static void tipc_topsrv_kern_evt(struct net *net, struct tipc_event *evt); +static void tipc_conn_delete_sub(struct tipc_conn *con, struct tipc_subscr *s); + +static bool connected(struct tipc_conn *con) +{ + return con && test_bit(CF_CONNECTED, &con->flags); +} + +static void tipc_conn_kref_release(struct kref *kref) +{ + struct tipc_conn *con = container_of(kref, struct tipc_conn, kref); + struct tipc_topsrv *s = con->server; + struct outqueue_entry *e, *safe; + + spin_lock_bh(&s->idr_lock); + idr_remove(&s->conn_idr, con->conid); + s->idr_in_use--; + spin_unlock_bh(&s->idr_lock); + if (con->sock) + sock_release(con->sock); + + spin_lock_bh(&con->outqueue_lock); + list_for_each_entry_safe(e, safe, &con->outqueue, list) { + list_del(&e->list); + kfree(e); + } + spin_unlock_bh(&con->outqueue_lock); + kfree(con); +} + +static void conn_put(struct tipc_conn *con) +{ + kref_put(&con->kref, tipc_conn_kref_release); +} + +static void conn_get(struct tipc_conn *con) +{ + kref_get(&con->kref); +} + +static void tipc_conn_close(struct tipc_conn *con) +{ + struct sock *sk = con->sock->sk; + bool disconnect = false; + + write_lock_bh(&sk->sk_callback_lock); + disconnect = test_and_clear_bit(CF_CONNECTED, &con->flags); + + if (disconnect) { + sk->sk_user_data = NULL; + tipc_conn_delete_sub(con, NULL); + } + write_unlock_bh(&sk->sk_callback_lock); + + /* Handle concurrent calls from sending and receiving threads */ + if (!disconnect) + return; + + /* Don't flush pending works, -just let them expire */ + kernel_sock_shutdown(con->sock, SHUT_RDWR); + + conn_put(con); +} + +static struct tipc_conn *tipc_conn_alloc(struct tipc_topsrv *s) +{ + struct tipc_conn *con; + int ret; + + con = kzalloc(sizeof(*con), GFP_ATOMIC); + if (!con) + return ERR_PTR(-ENOMEM); + + kref_init(&con->kref); + INIT_LIST_HEAD(&con->outqueue); + INIT_LIST_HEAD(&con->sub_list); + spin_lock_init(&con->outqueue_lock); + spin_lock_init(&con->sub_lock); + INIT_WORK(&con->swork, tipc_conn_send_work); + INIT_WORK(&con->rwork, tipc_conn_recv_work); + + spin_lock_bh(&s->idr_lock); + ret = idr_alloc(&s->conn_idr, con, 0, 0, GFP_ATOMIC); + if (ret < 0) { + kfree(con); + spin_unlock_bh(&s->idr_lock); + return ERR_PTR(-ENOMEM); + } + con->conid = ret; + s->idr_in_use++; + spin_unlock_bh(&s->idr_lock); + + set_bit(CF_CONNECTED, &con->flags); + con->server = s; + + return con; +} + +static struct tipc_conn *tipc_conn_lookup(struct tipc_topsrv *s, int conid) +{ + struct tipc_conn *con; + + spin_lock_bh(&s->idr_lock); + con = idr_find(&s->conn_idr, conid); + if (!connected(con) || !kref_get_unless_zero(&con->kref)) + con = NULL; + spin_unlock_bh(&s->idr_lock); + return con; +} + +/* tipc_conn_delete_sub - delete a specific or all subscriptions + * for a given subscriber + */ +static void tipc_conn_delete_sub(struct tipc_conn *con, struct tipc_subscr *s) +{ + struct tipc_net *tn = tipc_net(con->server->net); + struct list_head *sub_list = &con->sub_list; + struct tipc_subscription *sub, *tmp; + + spin_lock_bh(&con->sub_lock); + list_for_each_entry_safe(sub, tmp, sub_list, sub_list) { + if (!s || !memcmp(s, &sub->evt.s, sizeof(*s))) { + tipc_sub_unsubscribe(sub); + atomic_dec(&tn->subscription_count); + } else if (s) { + break; + } + } + spin_unlock_bh(&con->sub_lock); +} + +static void tipc_conn_send_to_sock(struct tipc_conn *con) +{ + struct list_head *queue = &con->outqueue; + struct tipc_topsrv *srv = con->server; + struct outqueue_entry *e; + struct tipc_event *evt; + struct msghdr msg; + struct kvec iov; + int count = 0; + int ret; + + spin_lock_bh(&con->outqueue_lock); + + while (!list_empty(queue)) { + e = list_first_entry(queue, struct outqueue_entry, list); + evt = &e->evt; + spin_unlock_bh(&con->outqueue_lock); + + if (e->inactive) + tipc_conn_delete_sub(con, &evt->s); + + memset(&msg, 0, sizeof(msg)); + msg.msg_flags = MSG_DONTWAIT; + iov.iov_base = evt; + iov.iov_len = sizeof(*evt); + msg.msg_name = NULL; + + if (con->sock) { + ret = kernel_sendmsg(con->sock, &msg, &iov, + 1, sizeof(*evt)); + if (ret == -EWOULDBLOCK || ret == 0) { + cond_resched(); + return; + } else if (ret < 0) { + return tipc_conn_close(con); + } + } else { + tipc_topsrv_kern_evt(srv->net, evt); + } + + /* Don't starve users filling buffers */ + if (++count >= MAX_SEND_MSG_COUNT) { + cond_resched(); + count = 0; + } + spin_lock_bh(&con->outqueue_lock); + list_del(&e->list); + kfree(e); + } + spin_unlock_bh(&con->outqueue_lock); +} + +static void tipc_conn_send_work(struct work_struct *work) +{ + struct tipc_conn *con = container_of(work, struct tipc_conn, swork); + + if (connected(con)) + tipc_conn_send_to_sock(con); + + conn_put(con); +} + +/* tipc_conn_queue_evt() - interrupt level call from a subscription instance + * The queued work is launched into tipc_send_work()->tipc_send_to_sock() + */ +void tipc_topsrv_queue_evt(struct net *net, int conid, + u32 event, struct tipc_event *evt) +{ + struct tipc_topsrv *srv = tipc_topsrv(net); + struct outqueue_entry *e; + struct tipc_conn *con; + + con = tipc_conn_lookup(srv, conid); + if (!con) + return; + + if (!connected(con)) + goto err; + + e = kmalloc(sizeof(*e), GFP_ATOMIC); + if (!e) + goto err; + e->inactive = (event == TIPC_SUBSCR_TIMEOUT); + memcpy(&e->evt, evt, sizeof(*evt)); + spin_lock_bh(&con->outqueue_lock); + list_add_tail(&e->list, &con->outqueue); + spin_unlock_bh(&con->outqueue_lock); + + if (queue_work(srv->send_wq, &con->swork)) + return; +err: + conn_put(con); +} + +/* tipc_conn_write_space - interrupt callback after a sendmsg EAGAIN + * Indicates that there now is more space in the send buffer + * The queued work is launched into tipc_send_work()->tipc_conn_send_to_sock() + */ +static void tipc_conn_write_space(struct sock *sk) +{ + struct tipc_conn *con; + + read_lock_bh(&sk->sk_callback_lock); + con = sk->sk_user_data; + if (connected(con)) { + conn_get(con); + if (!queue_work(con->server->send_wq, &con->swork)) + conn_put(con); + } + read_unlock_bh(&sk->sk_callback_lock); +} + +static int tipc_conn_rcv_sub(struct tipc_topsrv *srv, + struct tipc_conn *con, + struct tipc_subscr *s) +{ + struct tipc_net *tn = tipc_net(srv->net); + struct tipc_subscription *sub; + + if (tipc_sub_read(s, filter) & TIPC_SUB_CANCEL) { + tipc_conn_delete_sub(con, s); + return 0; + } + if (atomic_read(&tn->subscription_count) >= TIPC_MAX_SUBSCR) { + pr_warn("Subscription rejected, max (%u)\n", TIPC_MAX_SUBSCR); + return -1; + } + sub = tipc_sub_subscribe(srv->net, s, con->conid); + if (!sub) + return -1; + atomic_inc(&tn->subscription_count); + spin_lock_bh(&con->sub_lock); + list_add(&sub->sub_list, &con->sub_list); + spin_unlock_bh(&con->sub_lock); + return 0; +} + +static int tipc_conn_rcv_from_sock(struct tipc_conn *con) +{ + struct tipc_topsrv *srv = con->server; + struct sock *sk = con->sock->sk; + struct msghdr msg = {}; + struct tipc_subscr s; + struct kvec iov; + int ret; + + iov.iov_base = &s; + iov.iov_len = sizeof(s); + msg.msg_name = NULL; + iov_iter_kvec(&msg.msg_iter, READ | ITER_KVEC, &iov, 1, iov.iov_len); + ret = sock_recvmsg(con->sock, &msg, MSG_DONTWAIT); + if (ret == -EWOULDBLOCK) + return -EWOULDBLOCK; + if (ret > 0) { + read_lock_bh(&sk->sk_callback_lock); + ret = tipc_conn_rcv_sub(srv, con, &s); + read_unlock_bh(&sk->sk_callback_lock); + } + if (ret < 0) + tipc_conn_close(con); + + return ret; +} + +static void tipc_conn_recv_work(struct work_struct *work) +{ + struct tipc_conn *con = container_of(work, struct tipc_conn, rwork); + int count = 0; + + while (connected(con)) { + if (tipc_conn_rcv_from_sock(con)) + break; + + /* Don't flood Rx machine */ + if (++count >= MAX_RECV_MSG_COUNT) { + cond_resched(); + count = 0; + } + } + conn_put(con); +} + +/* tipc_conn_data_ready - interrupt callback indicating the socket has data + * The queued work is launched into tipc_recv_work()->tipc_conn_rcv_from_sock() + */ +static void tipc_conn_data_ready(struct sock *sk) +{ + struct tipc_conn *con; + + read_lock_bh(&sk->sk_callback_lock); + con = sk->sk_user_data; + if (connected(con)) { + conn_get(con); + if (!queue_work(con->server->rcv_wq, &con->rwork)) + conn_put(con); + } + read_unlock_bh(&sk->sk_callback_lock); +} + +static void tipc_topsrv_accept(struct work_struct *work) +{ + struct tipc_topsrv *srv = container_of(work, struct tipc_topsrv, awork); + struct socket *lsock = srv->listener; + struct socket *newsock; + struct tipc_conn *con; + struct sock *newsk; + int ret; + + while (1) { + ret = kernel_accept(lsock, &newsock, O_NONBLOCK); + if (ret < 0) + return; + con = tipc_conn_alloc(srv); + if (IS_ERR(con)) { + ret = PTR_ERR(con); + sock_release(newsock); + return; + } + /* Register callbacks */ + newsk = newsock->sk; + write_lock_bh(&newsk->sk_callback_lock); + newsk->sk_data_ready = tipc_conn_data_ready; + newsk->sk_write_space = tipc_conn_write_space; + newsk->sk_user_data = con; + con->sock = newsock; + write_unlock_bh(&newsk->sk_callback_lock); + + /* Wake up receive process in case of 'SYN+' message */ + newsk->sk_data_ready(newsk); + } +} + +/* tipc_toprsv_listener_data_ready - interrupt callback with connection request + * The queued job is launched into tipc_topsrv_accept() + */ +static void tipc_topsrv_listener_data_ready(struct sock *sk) +{ + struct tipc_topsrv *srv; + + read_lock_bh(&sk->sk_callback_lock); + srv = sk->sk_user_data; + if (srv->listener) + queue_work(srv->rcv_wq, &srv->awork); + read_unlock_bh(&sk->sk_callback_lock); +} + +static int tipc_topsrv_create_listener(struct tipc_topsrv *srv) +{ + int imp = TIPC_CRITICAL_IMPORTANCE; + struct socket *lsock = NULL; + struct sockaddr_tipc saddr; + struct sock *sk; + int rc; + + rc = sock_create_kern(srv->net, AF_TIPC, SOCK_SEQPACKET, 0, &lsock); + if (rc < 0) + return rc; + + srv->listener = lsock; + sk = lsock->sk; + write_lock_bh(&sk->sk_callback_lock); + sk->sk_data_ready = tipc_topsrv_listener_data_ready; + sk->sk_user_data = srv; + write_unlock_bh(&sk->sk_callback_lock); + + rc = kernel_setsockopt(lsock, SOL_TIPC, TIPC_IMPORTANCE, + (char *)&imp, sizeof(imp)); + if (rc < 0) + goto err; + + saddr.family = AF_TIPC; + saddr.addrtype = TIPC_ADDR_NAMESEQ; + saddr.addr.nameseq.type = TIPC_TOP_SRV; + saddr.addr.nameseq.lower = TIPC_TOP_SRV; + saddr.addr.nameseq.upper = TIPC_TOP_SRV; + saddr.scope = TIPC_NODE_SCOPE; + + rc = kernel_bind(lsock, (struct sockaddr *)&saddr, sizeof(saddr)); + if (rc < 0) + goto err; + rc = kernel_listen(lsock, 0); + if (rc < 0) + goto err; + + /* As server's listening socket owner and creator is the same module, + * we have to decrease TIPC module reference count to guarantee that + * it remains zero after the server socket is created, otherwise, + * executing "rmmod" command is unable to make TIPC module deleted + * after TIPC module is inserted successfully. + * + * However, the reference count is ever increased twice in + * sock_create_kern(): one is to increase the reference count of owner + * of TIPC socket's proto_ops struct; another is to increment the + * reference count of owner of TIPC proto struct. Therefore, we must + * decrement the module reference count twice to ensure that it keeps + * zero after server's listening socket is created. Of course, we + * must bump the module reference count twice as well before the socket + * is closed. + */ + module_put(lsock->ops->owner); + module_put(sk->sk_prot_creator->owner); + + return 0; +err: + sock_release(lsock); + return -EINVAL; +} + +bool tipc_topsrv_kern_subscr(struct net *net, u32 port, u32 type, u32 lower, + u32 upper, u32 filter, int *conid) +{ + struct tipc_subscr sub; + struct tipc_conn *con; + int rc; + + sub.seq.type = type; + sub.seq.lower = lower; + sub.seq.upper = upper; + sub.timeout = TIPC_WAIT_FOREVER; + sub.filter = filter; + *(u32 *)&sub.usr_handle = port; + + con = tipc_conn_alloc(tipc_topsrv(net)); + if (IS_ERR(con)) + return false; + + *conid = con->conid; + con->sock = NULL; + rc = tipc_conn_rcv_sub(tipc_topsrv(net), con, &sub); + if (rc >= 0) + return true; + conn_put(con); + return false; +} + +void tipc_topsrv_kern_unsubscr(struct net *net, int conid) +{ + struct tipc_conn *con; + + con = tipc_conn_lookup(tipc_topsrv(net), conid); + if (!con) + return; + + test_and_clear_bit(CF_CONNECTED, &con->flags); + tipc_conn_delete_sub(con, NULL); + conn_put(con); + conn_put(con); +} + +static void tipc_topsrv_kern_evt(struct net *net, struct tipc_event *evt) +{ + u32 port = *(u32 *)&evt->s.usr_handle; + u32 self = tipc_own_addr(net); + struct sk_buff_head evtq; + struct sk_buff *skb; + + skb = tipc_msg_create(TOP_SRV, 0, INT_H_SIZE, sizeof(*evt), + self, self, port, port, 0); + if (!skb) + return; + msg_set_dest_droppable(buf_msg(skb), true); + memcpy(msg_data(buf_msg(skb)), evt, sizeof(*evt)); + skb_queue_head_init(&evtq); + __skb_queue_tail(&evtq, skb); + tipc_sk_rcv(net, &evtq); +} + +static int tipc_topsrv_work_start(struct tipc_topsrv *s) +{ + s->rcv_wq = alloc_ordered_workqueue("tipc_rcv", 0); + if (!s->rcv_wq) { + pr_err("can't start tipc receive workqueue\n"); + return -ENOMEM; + } + + s->send_wq = alloc_ordered_workqueue("tipc_send", 0); + if (!s->send_wq) { + pr_err("can't start tipc send workqueue\n"); + destroy_workqueue(s->rcv_wq); + return -ENOMEM; + } + + return 0; +} + +static void tipc_topsrv_work_stop(struct tipc_topsrv *s) +{ + destroy_workqueue(s->rcv_wq); + destroy_workqueue(s->send_wq); +} + +int tipc_topsrv_start(struct net *net) +{ + struct tipc_net *tn = tipc_net(net); + const char name[] = "topology_server"; + struct tipc_topsrv *srv; + int ret; + + srv = kzalloc(sizeof(*srv), GFP_ATOMIC); + if (!srv) + return -ENOMEM; + + srv->net = net; + srv->max_rcvbuf_size = sizeof(struct tipc_subscr); + INIT_WORK(&srv->awork, tipc_topsrv_accept); + + strncpy(srv->name, name, strlen(name) + 1); + tn->topsrv = srv; + atomic_set(&tn->subscription_count, 0); + + spin_lock_init(&srv->idr_lock); + idr_init(&srv->conn_idr); + srv->idr_in_use = 0; + + ret = tipc_topsrv_work_start(srv); + if (ret < 0) + return ret; + + ret = tipc_topsrv_create_listener(srv); + if (ret < 0) + tipc_topsrv_work_stop(srv); + + return ret; +} + +void tipc_topsrv_stop(struct net *net) +{ + struct tipc_topsrv *srv = tipc_topsrv(net); + struct socket *lsock = srv->listener; + struct tipc_conn *con; + int id; + + spin_lock_bh(&srv->idr_lock); + for (id = 0; srv->idr_in_use; id++) { + con = idr_find(&srv->conn_idr, id); + if (con) { + spin_unlock_bh(&srv->idr_lock); + tipc_conn_close(con); + spin_lock_bh(&srv->idr_lock); + } + } + __module_get(lsock->ops->owner); + __module_get(lsock->sk->sk_prot_creator->owner); + srv->listener = NULL; + spin_unlock_bh(&srv->idr_lock); + sock_release(lsock); + tipc_topsrv_work_stop(srv); + idr_destroy(&srv->conn_idr); + kfree(srv); +} diff --git a/net/tipc/server.h b/net/tipc/topsrv.h index 64df7513cd70..c7ea71293748 100644 --- a/net/tipc/server.h +++ b/net/tipc/topsrv.h @@ -2,6 +2,7 @@ * net/tipc/server.h: Include file for TIPC server code * * Copyright (c) 2012-2013, Wind River Systems + * Copyright (c) 2017, Ericsson AB * All rights reserved. * * Redistribution and use in source and binary forms, with or without @@ -36,68 +37,18 @@ #ifndef _TIPC_SERVER_H #define _TIPC_SERVER_H -#include <linux/idr.h> -#include <linux/tipc.h> -#include <net/net_namespace.h> +#include "core.h" #define TIPC_SERVER_NAME_LEN 32 #define TIPC_SUB_CLUSTER_SCOPE 0x20 #define TIPC_SUB_NODE_SCOPE 0x40 #define TIPC_SUB_NO_STATUS 0x80 -/** - * struct tipc_server - TIPC server structure - * @conn_idr: identifier set of connection - * @idr_lock: protect the connection identifier set - * @idr_in_use: amount of allocated identifier entry - * @net: network namspace instance - * @rcvbuf_cache: memory cache of server receive buffer - * @rcv_wq: receive workqueue - * @send_wq: send workqueue - * @max_rcvbuf_size: maximum permitted receive message length - * @tipc_conn_new: callback will be called when new connection is incoming - * @tipc_conn_release: callback will be called before releasing the connection - * @tipc_conn_recvmsg: callback will be called when message arrives - * @saddr: TIPC server address - * @name: server name - * @imp: message importance - * @type: socket type - */ -struct tipc_server { - struct idr conn_idr; - spinlock_t idr_lock; - int idr_in_use; - struct net *net; - struct kmem_cache *rcvbuf_cache; - struct workqueue_struct *rcv_wq; - struct workqueue_struct *send_wq; - int max_rcvbuf_size; - void *(*tipc_conn_new)(int conid); - void (*tipc_conn_release)(int conid, void *usr_data); - int (*tipc_conn_recvmsg)(struct net *net, int conid, - struct sockaddr_tipc *addr, void *usr_data, - void *buf, size_t len); - struct sockaddr_tipc *saddr; - char name[TIPC_SERVER_NAME_LEN]; - int imp; - int type; -}; - -int tipc_conn_sendmsg(struct tipc_server *s, int conid, - struct sockaddr_tipc *addr, void *data, size_t len); +void tipc_topsrv_queue_evt(struct net *net, int conid, + u32 event, struct tipc_event *evt); bool tipc_topsrv_kern_subscr(struct net *net, u32 port, u32 type, u32 lower, u32 upper, u32 filter, int *conid); void tipc_topsrv_kern_unsubscr(struct net *net, int conid); -/** - * tipc_conn_terminate - terminate connection with server - * - * Note: Must call it in process context since it might sleep - */ -void tipc_conn_terminate(struct tipc_server *s, int conid); -int tipc_server_start(struct tipc_server *s); - -void tipc_server_stop(struct tipc_server *s); - #endif diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 2d465bdeccbc..bc2970a8e7f3 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -637,7 +637,7 @@ static int unix_stream_connect(struct socket *, struct sockaddr *, int addr_len, int flags); static int unix_socketpair(struct socket *, struct socket *); static int unix_accept(struct socket *, struct socket *, int, bool); -static int unix_getname(struct socket *, struct sockaddr *, int *, int); +static int unix_getname(struct socket *, struct sockaddr *, int); static __poll_t unix_poll(struct file *, struct socket *, poll_table *); static __poll_t unix_dgram_poll(struct file *, struct socket *, poll_table *); @@ -1453,7 +1453,7 @@ out: } -static int unix_getname(struct socket *sock, struct sockaddr *uaddr, int *uaddr_len, int peer) +static int unix_getname(struct socket *sock, struct sockaddr *uaddr, int peer) { struct sock *sk = sock->sk; struct unix_sock *u; @@ -1476,12 +1476,12 @@ static int unix_getname(struct socket *sock, struct sockaddr *uaddr, int *uaddr_ if (!u->addr) { sunaddr->sun_family = AF_UNIX; sunaddr->sun_path[0] = 0; - *uaddr_len = sizeof(short); + err = sizeof(short); } else { struct unix_address *addr = u->addr; - *uaddr_len = addr->len; - memcpy(sunaddr, addr->name, *uaddr_len); + err = addr->len; + memcpy(sunaddr, addr->name, addr->len); } unix_state_unlock(sk); sock_put(sk); @@ -2913,6 +2913,7 @@ static void __net_exit unix_net_exit(struct net *net) static struct pernet_operations unix_net_ops = { .init = unix_net_init, .exit = unix_net_exit, + .async = true, }; static int __init af_unix_init(void) diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index e0fc84daed94..aac9b8f6552e 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -759,7 +759,7 @@ vsock_bind(struct socket *sock, struct sockaddr *addr, int addr_len) } static int vsock_getname(struct socket *sock, - struct sockaddr *addr, int *addr_len, int peer) + struct sockaddr *addr, int peer) { int err; struct sock *sk; @@ -794,7 +794,7 @@ static int vsock_getname(struct socket *sock, */ BUILD_BUG_ON(sizeof(*vm_addr) > 128); memcpy(addr, vm_addr, sizeof(*vm_addr)); - *addr_len = sizeof(*vm_addr); + err = sizeof(*vm_addr); out: release_sock(sk); diff --git a/net/wireless/core.c b/net/wireless/core.c index a6f3cac8c640..670aa229168a 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -1340,6 +1340,7 @@ static void __net_exit cfg80211_pernet_exit(struct net *net) static struct pernet_operations cfg80211_pernet_ops = { .exit = cfg80211_pernet_exit, + .async = true, }; static int __init cfg80211_init(void) diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 9c0dcc8324b0..a910150f8169 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -421,6 +421,7 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { [NL80211_ATTR_FILS_CACHE_ID] = { .len = 2 }, [NL80211_ATTR_PMK] = { .type = NLA_BINARY, .len = PMK_MAX_LEN }, [NL80211_ATTR_SCHED_SCAN_MULTI] = { .type = NLA_FLAG }, + [NL80211_ATTR_EXTERNAL_AUTH_SUPPORT] = { .type = NLA_FLAG }, }; /* policy for the key attributes */ @@ -3923,9 +3924,10 @@ static bool nl80211_valid_auth_type(struct cfg80211_registered_device *rdev, return false; return true; case NL80211_CMD_CONNECT: - /* SAE not supported yet */ - if (auth_type == NL80211_AUTHTYPE_SAE) + if (!(rdev->wiphy.features & NL80211_FEATURE_SAE) && + auth_type == NL80211_AUTHTYPE_SAE) return false; + /* FILS with SK PFS or PK not supported yet */ if (auth_type == NL80211_AUTHTYPE_FILS_SK_PFS || auth_type == NL80211_AUTHTYPE_FILS_PK) @@ -4487,6 +4489,7 @@ static int nl80211_send_station(struct sk_buff *msg, u32 cmd, u32 portid, PUT_SINFO_U64(RX_DROP_MISC, rx_dropped_misc); PUT_SINFO_U64(BEACON_RX, rx_beacon); PUT_SINFO(BEACON_SIGNAL_AVG, rx_beacon_signal_avg, u8); + PUT_SINFO(ACK_SIGNAL, ack_signal, u8); #undef PUT_SINFO #undef PUT_SINFO_U64 @@ -5848,7 +5851,6 @@ static int nl80211_get_mesh_config(struct sk_buff *skb, return genlmsg_reply(msg, info); nla_put_failure: - genlmsg_cancel(msg, hdr); out: nlmsg_free(msg); return -ENOBUFS; @@ -6329,7 +6331,6 @@ static int nl80211_get_reg_do(struct sk_buff *skb, struct genl_info *info) nla_put_failure_rcu: rcu_read_unlock(); nla_put_failure: - genlmsg_cancel(msg, hdr); put_failure: nlmsg_free(msg); return -EMSGSIZE; @@ -6718,8 +6719,17 @@ nl80211_check_scan_flags(struct wiphy *wiphy, struct wireless_dev *wdev, *flags = nla_get_u32(attrs[NL80211_ATTR_SCAN_FLAGS]); - if ((*flags & NL80211_SCAN_FLAG_LOW_PRIORITY) && - !(wiphy->features & NL80211_FEATURE_LOW_PRIORITY_SCAN)) + if (((*flags & NL80211_SCAN_FLAG_LOW_PRIORITY) && + !(wiphy->features & NL80211_FEATURE_LOW_PRIORITY_SCAN)) || + ((*flags & NL80211_SCAN_FLAG_LOW_SPAN) && + !wiphy_ext_feature_isset(wiphy, + NL80211_EXT_FEATURE_LOW_SPAN_SCAN)) || + ((*flags & NL80211_SCAN_FLAG_LOW_POWER) && + !wiphy_ext_feature_isset(wiphy, + NL80211_EXT_FEATURE_LOW_POWER_SCAN)) || + ((*flags & NL80211_SCAN_FLAG_HIGH_ACCURACY) && + !wiphy_ext_feature_isset(wiphy, + NL80211_EXT_FEATURE_HIGH_ACCURACY_SCAN))) return -EOPNOTSUPP; if (*flags & NL80211_SCAN_FLAG_RANDOM_ADDR) { @@ -9155,6 +9165,15 @@ static int nl80211_connect(struct sk_buff *skb, struct genl_info *info) return -EINVAL; } + if (nla_get_flag(info->attrs[NL80211_ATTR_EXTERNAL_AUTH_SUPPORT])) { + if (!info->attrs[NL80211_ATTR_SOCKET_OWNER]) { + GENL_SET_ERR_MSG(info, + "external auth requires connection ownership"); + return -EINVAL; + } + connect.flags |= CONNECT_REQ_EXTERNAL_AUTH_SUPPORT; + } + wdev_lock(dev->ieee80211_ptr); err = cfg80211_connect(rdev, dev, &connect, connkeys, @@ -12463,6 +12482,41 @@ static int nl80211_del_pmk(struct sk_buff *skb, struct genl_info *info) return ret; } +static int nl80211_external_auth(struct sk_buff *skb, struct genl_info *info) +{ + struct cfg80211_registered_device *rdev = info->user_ptr[0]; + struct net_device *dev = info->user_ptr[1]; + struct cfg80211_external_auth_params params; + + if (!rdev->ops->external_auth) + return -EOPNOTSUPP; + + if (!info->attrs[NL80211_ATTR_SSID]) + return -EINVAL; + + if (!info->attrs[NL80211_ATTR_BSSID]) + return -EINVAL; + + if (!info->attrs[NL80211_ATTR_STATUS_CODE]) + return -EINVAL; + + memset(¶ms, 0, sizeof(params)); + + params.ssid.ssid_len = nla_len(info->attrs[NL80211_ATTR_SSID]); + if (params.ssid.ssid_len == 0 || + params.ssid.ssid_len > IEEE80211_MAX_SSID_LEN) + return -EINVAL; + memcpy(params.ssid.ssid, nla_data(info->attrs[NL80211_ATTR_SSID]), + params.ssid.ssid_len); + + memcpy(params.bssid, nla_data(info->attrs[NL80211_ATTR_BSSID]), + ETH_ALEN); + + params.status = nla_get_u16(info->attrs[NL80211_ATTR_STATUS_CODE]); + + return rdev_external_auth(rdev, dev, ¶ms); +} + #define NL80211_FLAG_NEED_WIPHY 0x01 #define NL80211_FLAG_NEED_NETDEV 0x02 #define NL80211_FLAG_NEED_RTNL 0x04 @@ -13358,6 +13412,14 @@ static const struct genl_ops nl80211_ops[] = { .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | NL80211_FLAG_NEED_RTNL, }, + { + .cmd = NL80211_CMD_EXTERNAL_AUTH, + .doit = nl80211_external_auth, + .policy = nl80211_policy, + .flags = GENL_ADMIN_PERM, + .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | + NL80211_FLAG_NEED_RTNL, + }, }; @@ -13672,7 +13734,6 @@ void nl80211_common_reg_change_event(enum nl80211_commands cmd_id, return; nla_put_failure: - genlmsg_cancel(msg, hdr); nlmsg_free(msg); } @@ -13720,7 +13781,6 @@ static void nl80211_send_mlme_event(struct cfg80211_registered_device *rdev, return; nla_put_failure: - genlmsg_cancel(msg, hdr); nlmsg_free(msg); } @@ -13808,7 +13868,6 @@ static void nl80211_send_mlme_timeout(struct cfg80211_registered_device *rdev, return; nla_put_failure: - genlmsg_cancel(msg, hdr); nlmsg_free(msg); } @@ -13884,7 +13943,6 @@ void nl80211_send_connect_result(struct cfg80211_registered_device *rdev, return; nla_put_failure: - genlmsg_cancel(msg, hdr); nlmsg_free(msg); } @@ -13924,7 +13982,6 @@ void nl80211_send_roamed(struct cfg80211_registered_device *rdev, return; nla_put_failure: - genlmsg_cancel(msg, hdr); nlmsg_free(msg); } @@ -13954,7 +14011,6 @@ void nl80211_send_port_authorized(struct cfg80211_registered_device *rdev, return; nla_put_failure: - genlmsg_cancel(msg, hdr); nlmsg_free(msg); } @@ -13991,7 +14047,6 @@ void nl80211_send_disconnected(struct cfg80211_registered_device *rdev, return; nla_put_failure: - genlmsg_cancel(msg, hdr); nlmsg_free(msg); } @@ -14024,7 +14079,6 @@ void nl80211_send_ibss_bssid(struct cfg80211_registered_device *rdev, return; nla_put_failure: - genlmsg_cancel(msg, hdr); nlmsg_free(msg); } @@ -14065,7 +14119,6 @@ void cfg80211_notify_new_peer_candidate(struct net_device *dev, const u8 *addr, return; nla_put_failure: - genlmsg_cancel(msg, hdr); nlmsg_free(msg); } EXPORT_SYMBOL(cfg80211_notify_new_peer_candidate); @@ -14104,7 +14157,6 @@ void nl80211_michael_mic_failure(struct cfg80211_registered_device *rdev, return; nla_put_failure: - genlmsg_cancel(msg, hdr); nlmsg_free(msg); } @@ -14159,7 +14211,6 @@ void nl80211_send_beacon_hint_event(struct wiphy *wiphy, return; nla_put_failure: - genlmsg_cancel(msg, hdr); nlmsg_free(msg); } @@ -14205,7 +14256,6 @@ static void nl80211_send_remain_on_chan_event( return; nla_put_failure: - genlmsg_cancel(msg, hdr); nlmsg_free(msg); } @@ -14319,7 +14369,6 @@ void cfg80211_conn_failed(struct net_device *dev, const u8 *mac_addr, return; nla_put_failure: - genlmsg_cancel(msg, hdr); nlmsg_free(msg); } EXPORT_SYMBOL(cfg80211_conn_failed); @@ -14356,7 +14405,6 @@ static bool __nl80211_unexpected_frame(struct net_device *dev, u8 cmd, return true; nla_put_failure: - genlmsg_cancel(msg, hdr); nlmsg_free(msg); return true; } @@ -14440,7 +14488,6 @@ int nl80211_send_mgmt(struct cfg80211_registered_device *rdev, return genlmsg_unicast(wiphy_net(&rdev->wiphy), msg, nlportid); nla_put_failure: - genlmsg_cancel(msg, hdr); nlmsg_free(msg); return -ENOBUFS; } @@ -14484,7 +14531,6 @@ void cfg80211_mgmt_tx_status(struct wireless_dev *wdev, u64 cookie, return; nla_put_failure: - genlmsg_cancel(msg, hdr); nlmsg_free(msg); } EXPORT_SYMBOL(cfg80211_mgmt_tx_status); @@ -14693,7 +14739,6 @@ static void nl80211_gtk_rekey_notify(struct cfg80211_registered_device *rdev, return; nla_put_failure: - genlmsg_cancel(msg, hdr); nlmsg_free(msg); } @@ -14751,7 +14796,6 @@ nl80211_pmksa_candidate_notify(struct cfg80211_registered_device *rdev, return; nla_put_failure: - genlmsg_cancel(msg, hdr); nlmsg_free(msg); } @@ -14804,7 +14848,6 @@ static void nl80211_ch_switch_notify(struct cfg80211_registered_device *rdev, return; nla_put_failure: - genlmsg_cancel(msg, hdr); nlmsg_free(msg); } @@ -14886,12 +14929,67 @@ nl80211_radar_notify(struct cfg80211_registered_device *rdev, return; nla_put_failure: - genlmsg_cancel(msg, hdr); nlmsg_free(msg); } +void cfg80211_sta_opmode_change_notify(struct net_device *dev, const u8 *mac, + struct sta_opmode_info *sta_opmode, + gfp_t gfp) +{ + struct sk_buff *msg; + struct wireless_dev *wdev = dev->ieee80211_ptr; + struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); + void *hdr; + + if (WARN_ON(!mac)) + return; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, gfp); + if (!msg) + return; + + hdr = nl80211hdr_put(msg, 0, 0, 0, NL80211_CMD_STA_OPMODE_CHANGED); + if (!hdr) { + nlmsg_free(msg); + return; + } + + if (nla_put_u32(msg, NL80211_ATTR_WIPHY, rdev->wiphy_idx)) + goto nla_put_failure; + + if (nla_put_u32(msg, NL80211_ATTR_IFINDEX, dev->ifindex)) + goto nla_put_failure; + + if (nla_put(msg, NL80211_ATTR_MAC, ETH_ALEN, mac)) + goto nla_put_failure; + + if ((sta_opmode->changed & STA_OPMODE_SMPS_MODE_CHANGED) && + nla_put_u8(msg, NL80211_ATTR_SMPS_MODE, sta_opmode->smps_mode)) + goto nla_put_failure; + + if ((sta_opmode->changed & STA_OPMODE_MAX_BW_CHANGED) && + nla_put_u8(msg, NL80211_ATTR_CHANNEL_WIDTH, sta_opmode->bw)) + goto nla_put_failure; + + if ((sta_opmode->changed & STA_OPMODE_N_SS_CHANGED) && + nla_put_u8(msg, NL80211_ATTR_NSS, sta_opmode->rx_nss)) + goto nla_put_failure; + + genlmsg_end(msg, hdr); + + genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), msg, 0, + NL80211_MCGRP_MLME, gfp); + + return; + +nla_put_failure: + nlmsg_free(msg); +} +EXPORT_SYMBOL(cfg80211_sta_opmode_change_notify); + void cfg80211_probe_status(struct net_device *dev, const u8 *addr, - u64 cookie, bool acked, gfp_t gfp) + u64 cookie, bool acked, s32 ack_signal, + bool is_valid_ack_signal, gfp_t gfp) { struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); @@ -14916,7 +15014,9 @@ void cfg80211_probe_status(struct net_device *dev, const u8 *addr, nla_put(msg, NL80211_ATTR_MAC, ETH_ALEN, addr) || nla_put_u64_64bit(msg, NL80211_ATTR_COOKIE, cookie, NL80211_ATTR_PAD) || - (acked && nla_put_flag(msg, NL80211_ATTR_ACK))) + (acked && nla_put_flag(msg, NL80211_ATTR_ACK)) || + (is_valid_ack_signal && nla_put_s32(msg, NL80211_ATTR_ACK_SIGNAL, + ack_signal))) goto nla_put_failure; genlmsg_end(msg, hdr); @@ -14926,7 +15026,6 @@ void cfg80211_probe_status(struct net_device *dev, const u8 *addr, return; nla_put_failure: - genlmsg_cancel(msg, hdr); nlmsg_free(msg); } EXPORT_SYMBOL(cfg80211_probe_status); @@ -14971,8 +15070,6 @@ void cfg80211_report_obss_beacon(struct wiphy *wiphy, nla_put_failure: spin_unlock_bh(&rdev->beacon_registrations_lock); - if (hdr) - genlmsg_cancel(msg, hdr); nlmsg_free(msg); } EXPORT_SYMBOL(cfg80211_report_obss_beacon); @@ -15188,7 +15285,6 @@ void cfg80211_tdls_oper_request(struct net_device *dev, const u8 *peer, return; nla_put_failure: - genlmsg_cancel(msg, hdr); nlmsg_free(msg); } EXPORT_SYMBOL(cfg80211_tdls_oper_request); @@ -15333,8 +15429,6 @@ void cfg80211_crit_proto_stopped(struct wireless_dev *wdev, gfp_t gfp) return; nla_put_failure: - if (hdr) - genlmsg_cancel(msg, hdr); nlmsg_free(msg); } EXPORT_SYMBOL(cfg80211_crit_proto_stopped); @@ -15369,6 +15463,47 @@ void nl80211_send_ap_stopped(struct wireless_dev *wdev) nlmsg_free(msg); } +int cfg80211_external_auth_request(struct net_device *dev, + struct cfg80211_external_auth_params *params, + gfp_t gfp) +{ + struct wireless_dev *wdev = dev->ieee80211_ptr; + struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); + struct sk_buff *msg; + void *hdr; + + if (!wdev->conn_owner_nlportid) + return -EINVAL; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, gfp); + if (!msg) + return -ENOMEM; + + hdr = nl80211hdr_put(msg, 0, 0, 0, NL80211_CMD_EXTERNAL_AUTH); + if (!hdr) + goto nla_put_failure; + + if (nla_put_u32(msg, NL80211_ATTR_WIPHY, rdev->wiphy_idx) || + nla_put_u32(msg, NL80211_ATTR_IFINDEX, dev->ifindex) || + nla_put_u32(msg, NL80211_ATTR_AKM_SUITES, params->key_mgmt_suite) || + nla_put_u32(msg, NL80211_ATTR_EXTERNAL_AUTH_ACTION, + params->action) || + nla_put(msg, NL80211_ATTR_BSSID, ETH_ALEN, params->bssid) || + nla_put(msg, NL80211_ATTR_SSID, params->ssid.ssid_len, + params->ssid.ssid)) + goto nla_put_failure; + + genlmsg_end(msg, hdr); + genlmsg_unicast(wiphy_net(&rdev->wiphy), msg, + wdev->conn_owner_nlportid); + return 0; + + nla_put_failure: + nlmsg_free(msg); + return -ENOBUFS; +} +EXPORT_SYMBOL(cfg80211_external_auth_request); + /* initialisation/exit functions */ int __init nl80211_init(void) diff --git a/net/wireless/rdev-ops.h b/net/wireless/rdev-ops.h index 0c06240d25af..84f23ae015fc 100644 --- a/net/wireless/rdev-ops.h +++ b/net/wireless/rdev-ops.h @@ -1190,4 +1190,19 @@ static inline int rdev_del_pmk(struct cfg80211_registered_device *rdev, trace_rdev_return_int(&rdev->wiphy, ret); return ret; } + +static inline int +rdev_external_auth(struct cfg80211_registered_device *rdev, + struct net_device *dev, + struct cfg80211_external_auth_params *params) +{ + int ret = -EOPNOTSUPP; + + trace_rdev_external_auth(&rdev->wiphy, dev, params); + if (rdev->ops->external_auth) + ret = rdev->ops->external_auth(&rdev->wiphy, dev, params); + trace_rdev_return_int(&rdev->wiphy, ret); + return ret; +} + #endif /* __CFG80211_RDEV_OPS */ diff --git a/net/wireless/trace.h b/net/wireless/trace.h index bcfedd39e7a3..5152938b358d 100644 --- a/net/wireless/trace.h +++ b/net/wireless/trace.h @@ -2319,6 +2319,29 @@ TRACE_EVENT(rdev_del_pmk, WIPHY_PR_ARG, NETDEV_PR_ARG, MAC_PR_ARG(aa)) ); +TRACE_EVENT(rdev_external_auth, + TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, + struct cfg80211_external_auth_params *params), + TP_ARGS(wiphy, netdev, params), + TP_STRUCT__entry(WIPHY_ENTRY + NETDEV_ENTRY + MAC_ENTRY(bssid) + __array(u8, ssid, IEEE80211_MAX_SSID_LEN + 1) + __field(u16, status) + ), + TP_fast_assign(WIPHY_ASSIGN; + NETDEV_ASSIGN; + MAC_ASSIGN(bssid, params->bssid); + memset(__entry->ssid, 0, IEEE80211_MAX_SSID_LEN + 1); + memcpy(__entry->ssid, params->ssid.ssid, + params->ssid.ssid_len); + __entry->status = params->status; + ), + TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", bssid: " MAC_PR_FMT + ", ssid: %s, status: %u", WIPHY_PR_ARG, NETDEV_PR_ARG, + __entry->bssid, __entry->ssid, __entry->status) +); + /************************************************************* * cfg80211 exported functions traces * *************************************************************/ diff --git a/net/wireless/util.c b/net/wireless/util.c index c69160694b6c..d112e9a89364 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -420,7 +420,8 @@ unsigned int ieee80211_get_mesh_hdrlen(struct ieee80211s_hdr *meshhdr) EXPORT_SYMBOL(ieee80211_get_mesh_hdrlen); int ieee80211_data_to_8023_exthdr(struct sk_buff *skb, struct ethhdr *ehdr, - const u8 *addr, enum nl80211_iftype iftype) + const u8 *addr, enum nl80211_iftype iftype, + u8 data_offset) { struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data; struct { @@ -434,7 +435,7 @@ int ieee80211_data_to_8023_exthdr(struct sk_buff *skb, struct ethhdr *ehdr, if (unlikely(!ieee80211_is_data_present(hdr->frame_control))) return -1; - hdrlen = ieee80211_hdrlen(hdr->frame_control); + hdrlen = ieee80211_hdrlen(hdr->frame_control) + data_offset; if (skb->len < hdrlen + 8) return -1; diff --git a/net/wireless/wext-core.c b/net/wireless/wext-core.c index 9efbfc753347..bc7064486b15 100644 --- a/net/wireless/wext-core.c +++ b/net/wireless/wext-core.c @@ -390,6 +390,7 @@ static void __net_exit wext_pernet_exit(struct net *net) static struct pernet_operations wext_pernet_ops = { .init = wext_pernet_init, .exit = wext_pernet_exit, + .async = true, }; static int __init wireless_nlevent_init(void) diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c index 562cc11131f6..d49aa79b7997 100644 --- a/net/x25/af_x25.c +++ b/net/x25/af_x25.c @@ -896,7 +896,7 @@ out: } static int x25_getname(struct socket *sock, struct sockaddr *uaddr, - int *uaddr_len, int peer) + int peer) { struct sockaddr_x25 *sx25 = (struct sockaddr_x25 *)uaddr; struct sock *sk = sock->sk; @@ -913,7 +913,7 @@ static int x25_getname(struct socket *sock, struct sockaddr *uaddr, sx25->sx25_addr = x25->source_addr; sx25->sx25_family = AF_X25; - *uaddr_len = sizeof(*sx25); + rc = sizeof(*sx25); out: return rc; diff --git a/net/x25/x25_subr.c b/net/x25/x25_subr.c index db0b1315d577..9c214ec681ac 100644 --- a/net/x25/x25_subr.c +++ b/net/x25/x25_subr.c @@ -335,8 +335,7 @@ int x25_decode(struct sock *sk, struct sk_buff *skb, int *ns, int *nr, int *q, } } - pr_debug("invalid PLP frame %02X %02X %02X\n", - frame[0], frame[1], frame[2]); + pr_debug("invalid PLP frame %3ph\n", frame); return X25_ILLEGAL; } diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 7a23078132cf..77d9d1ab05ce 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -2982,6 +2982,7 @@ static void __net_exit xfrm_net_exit(struct net *net) static struct pernet_operations __net_initdata xfrm_net_ops = { .init = xfrm_net_init, .exit = xfrm_net_exit, + .async = true, }; void __init xfrm_init(void) diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile index ec3fc8d88e87..2c2a587e0942 100644 --- a/samples/bpf/Makefile +++ b/samples/bpf/Makefile @@ -43,6 +43,7 @@ hostprogs-y += xdp_redirect_cpu hostprogs-y += xdp_monitor hostprogs-y += xdp_rxq_info hostprogs-y += syscall_tp +hostprogs-y += cpustat # Libbpf dependencies LIBBPF := ../../tools/lib/bpf/bpf.o ../../tools/lib/bpf/nlattr.o @@ -93,6 +94,7 @@ xdp_redirect_cpu-objs := bpf_load.o $(LIBBPF) xdp_redirect_cpu_user.o xdp_monitor-objs := bpf_load.o $(LIBBPF) xdp_monitor_user.o xdp_rxq_info-objs := bpf_load.o $(LIBBPF) xdp_rxq_info_user.o syscall_tp-objs := bpf_load.o $(LIBBPF) syscall_tp_user.o +cpustat-objs := bpf_load.o $(LIBBPF) cpustat_user.o # Tell kbuild to always build the programs always := $(hostprogs-y) @@ -144,6 +146,7 @@ always += xdp_monitor_kern.o always += xdp_rxq_info_kern.o always += xdp2skb_meta_kern.o always += syscall_tp_kern.o +always += cpustat_kern.o HOSTCFLAGS += -I$(objtree)/usr/include HOSTCFLAGS += -I$(srctree)/tools/lib/ @@ -188,6 +191,7 @@ HOSTLOADLIBES_xdp_redirect_cpu += -lelf HOSTLOADLIBES_xdp_monitor += -lelf HOSTLOADLIBES_xdp_rxq_info += -lelf HOSTLOADLIBES_syscall_tp += -lelf +HOSTLOADLIBES_cpustat += -lelf # Allows pointing LLC/CLANG to a LLVM backend with bpf support, redefine on cmdline: # make samples/bpf/ LLC=~/git/llvm/build/bin/llc CLANG=~/git/llvm/build/bin/clang diff --git a/samples/bpf/cpustat_kern.c b/samples/bpf/cpustat_kern.c new file mode 100644 index 000000000000..68c84da065b1 --- /dev/null +++ b/samples/bpf/cpustat_kern.c @@ -0,0 +1,281 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/version.h> +#include <linux/ptrace.h> +#include <uapi/linux/bpf.h> +#include "bpf_helpers.h" + +/* + * The CPU number, cstate number and pstate number are based + * on 96boards Hikey with octa CA53 CPUs. + * + * Every CPU have three idle states for cstate: + * WFI, CPU_OFF, CLUSTER_OFF + * + * Every CPU have 5 operating points: + * 208MHz, 432MHz, 729MHz, 960MHz, 1200MHz + * + * This code is based on these assumption and other platforms + * need to adjust these definitions. + */ +#define MAX_CPU 8 +#define MAX_PSTATE_ENTRIES 5 +#define MAX_CSTATE_ENTRIES 3 + +static int cpu_opps[] = { 208000, 432000, 729000, 960000, 1200000 }; + +/* + * my_map structure is used to record cstate and pstate index and + * timestamp (Idx, Ts), when new event incoming we need to update + * combination for new state index and timestamp (Idx`, Ts`). + * + * Based on (Idx, Ts) and (Idx`, Ts`) we can calculate the time + * interval for the previous state: Duration(Idx) = Ts` - Ts. + * + * Every CPU has one below array for recording state index and + * timestamp, and record for cstate and pstate saperately: + * + * +--------------------------+ + * | cstate timestamp | + * +--------------------------+ + * | cstate index | + * +--------------------------+ + * | pstate timestamp | + * +--------------------------+ + * | pstate index | + * +--------------------------+ + */ +#define MAP_OFF_CSTATE_TIME 0 +#define MAP_OFF_CSTATE_IDX 1 +#define MAP_OFF_PSTATE_TIME 2 +#define MAP_OFF_PSTATE_IDX 3 +#define MAP_OFF_NUM 4 + +struct bpf_map_def SEC("maps") my_map = { + .type = BPF_MAP_TYPE_ARRAY, + .key_size = sizeof(u32), + .value_size = sizeof(u64), + .max_entries = MAX_CPU * MAP_OFF_NUM, +}; + +/* cstate_duration records duration time for every idle state per CPU */ +struct bpf_map_def SEC("maps") cstate_duration = { + .type = BPF_MAP_TYPE_ARRAY, + .key_size = sizeof(u32), + .value_size = sizeof(u64), + .max_entries = MAX_CPU * MAX_CSTATE_ENTRIES, +}; + +/* pstate_duration records duration time for every operating point per CPU */ +struct bpf_map_def SEC("maps") pstate_duration = { + .type = BPF_MAP_TYPE_ARRAY, + .key_size = sizeof(u32), + .value_size = sizeof(u64), + .max_entries = MAX_CPU * MAX_PSTATE_ENTRIES, +}; + +/* + * The trace events for cpu_idle and cpu_frequency are taken from: + * /sys/kernel/debug/tracing/events/power/cpu_idle/format + * /sys/kernel/debug/tracing/events/power/cpu_frequency/format + * + * These two events have same format, so define one common structure. + */ +struct cpu_args { + u64 pad; + u32 state; + u32 cpu_id; +}; + +/* calculate pstate index, returns MAX_PSTATE_ENTRIES for failure */ +static u32 find_cpu_pstate_idx(u32 frequency) +{ + u32 i; + + for (i = 0; i < sizeof(cpu_opps) / sizeof(u32); i++) { + if (frequency == cpu_opps[i]) + return i; + } + + return i; +} + +SEC("tracepoint/power/cpu_idle") +int bpf_prog1(struct cpu_args *ctx) +{ + u64 *cts, *pts, *cstate, *pstate, prev_state, cur_ts, delta; + u32 key, cpu, pstate_idx; + u64 *val; + + if (ctx->cpu_id > MAX_CPU) + return 0; + + cpu = ctx->cpu_id; + + key = cpu * MAP_OFF_NUM + MAP_OFF_CSTATE_TIME; + cts = bpf_map_lookup_elem(&my_map, &key); + if (!cts) + return 0; + + key = cpu * MAP_OFF_NUM + MAP_OFF_CSTATE_IDX; + cstate = bpf_map_lookup_elem(&my_map, &key); + if (!cstate) + return 0; + + key = cpu * MAP_OFF_NUM + MAP_OFF_PSTATE_TIME; + pts = bpf_map_lookup_elem(&my_map, &key); + if (!pts) + return 0; + + key = cpu * MAP_OFF_NUM + MAP_OFF_PSTATE_IDX; + pstate = bpf_map_lookup_elem(&my_map, &key); + if (!pstate) + return 0; + + prev_state = *cstate; + *cstate = ctx->state; + + if (!*cts) { + *cts = bpf_ktime_get_ns(); + return 0; + } + + cur_ts = bpf_ktime_get_ns(); + delta = cur_ts - *cts; + *cts = cur_ts; + + /* + * When state doesn't equal to (u32)-1, the cpu will enter + * one idle state; for this case we need to record interval + * for the pstate. + * + * OPP2 + * +---------------------+ + * OPP1 | | + * ---------+ | + * | Idle state + * +--------------- + * + * |<- pstate duration ->| + * ^ ^ + * pts cur_ts + */ + if (ctx->state != (u32)-1) { + + /* record pstate after have first cpu_frequency event */ + if (!*pts) + return 0; + + delta = cur_ts - *pts; + + pstate_idx = find_cpu_pstate_idx(*pstate); + if (pstate_idx >= MAX_PSTATE_ENTRIES) + return 0; + + key = cpu * MAX_PSTATE_ENTRIES + pstate_idx; + val = bpf_map_lookup_elem(&pstate_duration, &key); + if (val) + __sync_fetch_and_add((long *)val, delta); + + /* + * When state equal to (u32)-1, the cpu just exits from one + * specific idle state; for this case we need to record + * interval for the pstate. + * + * OPP2 + * -----------+ + * | OPP1 + * | +----------- + * | Idle state | + * +---------------------+ + * + * |<- cstate duration ->| + * ^ ^ + * cts cur_ts + */ + } else { + + key = cpu * MAX_CSTATE_ENTRIES + prev_state; + val = bpf_map_lookup_elem(&cstate_duration, &key); + if (val) + __sync_fetch_and_add((long *)val, delta); + } + + /* Update timestamp for pstate as new start time */ + if (*pts) + *pts = cur_ts; + + return 0; +} + +SEC("tracepoint/power/cpu_frequency") +int bpf_prog2(struct cpu_args *ctx) +{ + u64 *pts, *cstate, *pstate, prev_state, cur_ts, delta; + u32 key, cpu, pstate_idx; + u64 *val; + + cpu = ctx->cpu_id; + + key = cpu * MAP_OFF_NUM + MAP_OFF_PSTATE_TIME; + pts = bpf_map_lookup_elem(&my_map, &key); + if (!pts) + return 0; + + key = cpu * MAP_OFF_NUM + MAP_OFF_PSTATE_IDX; + pstate = bpf_map_lookup_elem(&my_map, &key); + if (!pstate) + return 0; + + key = cpu * MAP_OFF_NUM + MAP_OFF_CSTATE_IDX; + cstate = bpf_map_lookup_elem(&my_map, &key); + if (!cstate) + return 0; + + prev_state = *pstate; + *pstate = ctx->state; + + if (!*pts) { + *pts = bpf_ktime_get_ns(); + return 0; + } + + cur_ts = bpf_ktime_get_ns(); + delta = cur_ts - *pts; + *pts = cur_ts; + + /* When CPU is in idle, bail out to skip pstate statistics */ + if (*cstate != (u32)(-1)) + return 0; + + /* + * The cpu changes to another different OPP (in below diagram + * change frequency from OPP3 to OPP1), need recording interval + * for previous frequency OPP3 and update timestamp as start + * time for new frequency OPP1. + * + * OPP3 + * +---------------------+ + * OPP2 | | + * ---------+ | + * | OPP1 + * +--------------- + * + * |<- pstate duration ->| + * ^ ^ + * pts cur_ts + */ + pstate_idx = find_cpu_pstate_idx(*pstate); + if (pstate_idx >= MAX_PSTATE_ENTRIES) + return 0; + + key = cpu * MAX_PSTATE_ENTRIES + pstate_idx; + val = bpf_map_lookup_elem(&pstate_duration, &key); + if (val) + __sync_fetch_and_add((long *)val, delta); + + return 0; +} + +char _license[] SEC("license") = "GPL"; +u32 _version SEC("version") = LINUX_VERSION_CODE; diff --git a/samples/bpf/cpustat_user.c b/samples/bpf/cpustat_user.c new file mode 100644 index 000000000000..2b4cd1ae57c5 --- /dev/null +++ b/samples/bpf/cpustat_user.c @@ -0,0 +1,219 @@ +// SPDX-License-Identifier: GPL-2.0 + +#define _GNU_SOURCE +#include <errno.h> +#include <stdio.h> +#include <stdlib.h> +#include <signal.h> +#include <sched.h> +#include <string.h> +#include <unistd.h> +#include <fcntl.h> +#include <linux/bpf.h> +#include <locale.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <sys/time.h> +#include <sys/resource.h> +#include <sys/wait.h> + +#include "libbpf.h" +#include "bpf_load.h" + +#define MAX_CPU 8 +#define MAX_PSTATE_ENTRIES 5 +#define MAX_CSTATE_ENTRIES 3 +#define MAX_STARS 40 + +#define CPUFREQ_MAX_SYSFS_PATH "/sys/devices/system/cpu/cpu0/cpufreq/scaling_max_freq" +#define CPUFREQ_LOWEST_FREQ "208000" +#define CPUFREQ_HIGHEST_FREQ "12000000" + +struct cpu_stat_data { + unsigned long cstate[MAX_CSTATE_ENTRIES]; + unsigned long pstate[MAX_PSTATE_ENTRIES]; +}; + +static struct cpu_stat_data stat_data[MAX_CPU]; + +static void cpu_stat_print(void) +{ + int i, j; + char state_str[sizeof("cstate-9")]; + struct cpu_stat_data *data; + + /* Clear screen */ + printf("\033[2J"); + + /* Header */ + printf("\nCPU states statistics:\n"); + printf("%-10s ", "state(ms)"); + + for (i = 0; i < MAX_CSTATE_ENTRIES; i++) { + sprintf(state_str, "cstate-%d", i); + printf("%-11s ", state_str); + } + + for (i = 0; i < MAX_PSTATE_ENTRIES; i++) { + sprintf(state_str, "pstate-%d", i); + printf("%-11s ", state_str); + } + + printf("\n"); + + for (j = 0; j < MAX_CPU; j++) { + data = &stat_data[j]; + + printf("CPU-%-6d ", j); + for (i = 0; i < MAX_CSTATE_ENTRIES; i++) + printf("%-11ld ", data->cstate[i] / 1000000); + + for (i = 0; i < MAX_PSTATE_ENTRIES; i++) + printf("%-11ld ", data->pstate[i] / 1000000); + + printf("\n"); + } +} + +static void cpu_stat_update(int cstate_fd, int pstate_fd) +{ + unsigned long key, value; + int c, i; + + for (c = 0; c < MAX_CPU; c++) { + for (i = 0; i < MAX_CSTATE_ENTRIES; i++) { + key = c * MAX_CSTATE_ENTRIES + i; + bpf_map_lookup_elem(cstate_fd, &key, &value); + stat_data[c].cstate[i] = value; + } + + for (i = 0; i < MAX_PSTATE_ENTRIES; i++) { + key = c * MAX_PSTATE_ENTRIES + i; + bpf_map_lookup_elem(pstate_fd, &key, &value); + stat_data[c].pstate[i] = value; + } + } +} + +/* + * This function is copied from 'idlestat' tool function + * idlestat_wake_all() in idlestate.c. + * + * It sets the self running task affinity to cpus one by one so can wake up + * the specific CPU to handle scheduling; this results in all cpus can be + * waken up once and produce ftrace event 'trace_cpu_idle'. + */ +static int cpu_stat_inject_cpu_idle_event(void) +{ + int rcpu, i, ret; + cpu_set_t cpumask; + cpu_set_t original_cpumask; + + ret = sysconf(_SC_NPROCESSORS_CONF); + if (ret < 0) + return -1; + + rcpu = sched_getcpu(); + if (rcpu < 0) + return -1; + + /* Keep track of the CPUs we will run on */ + sched_getaffinity(0, sizeof(original_cpumask), &original_cpumask); + + for (i = 0; i < ret; i++) { + + /* Pointless to wake up ourself */ + if (i == rcpu) + continue; + + /* Pointless to wake CPUs we will not run on */ + if (!CPU_ISSET(i, &original_cpumask)) + continue; + + CPU_ZERO(&cpumask); + CPU_SET(i, &cpumask); + + sched_setaffinity(0, sizeof(cpumask), &cpumask); + } + + /* Enable all the CPUs of the original mask */ + sched_setaffinity(0, sizeof(original_cpumask), &original_cpumask); + return 0; +} + +/* + * It's possible to have no any frequency change for long time and cannot + * get ftrace event 'trace_cpu_frequency' for long period, this introduces + * big deviation for pstate statistics. + * + * To solve this issue, below code forces to set 'scaling_max_freq' to 208MHz + * for triggering ftrace event 'trace_cpu_frequency' and then recovery back to + * the maximum frequency value 1.2GHz. + */ +static int cpu_stat_inject_cpu_frequency_event(void) +{ + int len, fd; + + fd = open(CPUFREQ_MAX_SYSFS_PATH, O_WRONLY); + if (fd < 0) { + printf("failed to open scaling_max_freq, errno=%d\n", errno); + return fd; + } + + len = write(fd, CPUFREQ_LOWEST_FREQ, strlen(CPUFREQ_LOWEST_FREQ)); + if (len < 0) { + printf("failed to open scaling_max_freq, errno=%d\n", errno); + goto err; + } + + len = write(fd, CPUFREQ_HIGHEST_FREQ, strlen(CPUFREQ_HIGHEST_FREQ)); + if (len < 0) { + printf("failed to open scaling_max_freq, errno=%d\n", errno); + goto err; + } + +err: + close(fd); + return len; +} + +static void int_exit(int sig) +{ + cpu_stat_inject_cpu_idle_event(); + cpu_stat_inject_cpu_frequency_event(); + cpu_stat_update(map_fd[1], map_fd[2]); + cpu_stat_print(); + exit(0); +} + +int main(int argc, char **argv) +{ + char filename[256]; + int ret; + + snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); + + if (load_bpf_file(filename)) { + printf("%s", bpf_log_buf); + return 1; + } + + ret = cpu_stat_inject_cpu_idle_event(); + if (ret < 0) + return 1; + + ret = cpu_stat_inject_cpu_frequency_event(); + if (ret < 0) + return 1; + + signal(SIGINT, int_exit); + signal(SIGTERM, int_exit); + + while (1) { + cpu_stat_update(map_fd[1], map_fd[2]); + cpu_stat_print(); + sleep(5); + } + + return 0; +} diff --git a/samples/bpf/tcbpf2_kern.c b/samples/bpf/tcbpf2_kern.c index efdc16d195ff..9a8db7bd6db4 100644 --- a/samples/bpf/tcbpf2_kern.c +++ b/samples/bpf/tcbpf2_kern.c @@ -52,7 +52,8 @@ int _gre_set_tunnel(struct __sk_buff *skb) key.tunnel_tos = 0; key.tunnel_ttl = 64; - ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key), BPF_F_ZERO_CSUM_TX); + ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key), + BPF_F_ZERO_CSUM_TX | BPF_F_SEQ_NUMBER); if (ret < 0) { ERROR(ret); return TC_ACT_SHOT; @@ -92,7 +93,8 @@ int _ip6gretap_set_tunnel(struct __sk_buff *skb) key.tunnel_label = 0xabcde; ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key), - BPF_F_TUNINFO_IPV6 | BPF_F_ZERO_CSUM_TX); + BPF_F_TUNINFO_IPV6 | BPF_F_ZERO_CSUM_TX | + BPF_F_SEQ_NUMBER); if (ret < 0) { ERROR(ret); return TC_ACT_SHOT; diff --git a/samples/bpf/test_cgrp2_sock.sh b/samples/bpf/test_cgrp2_sock.sh index 8ee0371a100a..9f6174236856 100755 --- a/samples/bpf/test_cgrp2_sock.sh +++ b/samples/bpf/test_cgrp2_sock.sh @@ -61,6 +61,7 @@ cleanup_and_exit() [ -n "$msg" ] && echo "ERROR: $msg" + test_cgrp2_sock -d ${CGRP_MNT}/sockopts ip li del cgrp2_sock umount ${CGRP_MNT} diff --git a/samples/bpf/test_cgrp2_sock2.sh b/samples/bpf/test_cgrp2_sock2.sh index fc4e64d00cb3..0f396a86e0cb 100755 --- a/samples/bpf/test_cgrp2_sock2.sh +++ b/samples/bpf/test_cgrp2_sock2.sh @@ -28,6 +28,9 @@ function attach_bpf { } function cleanup { + if [ -d /tmp/cgroupv2/foo ]; then + test_cgrp2_sock -d /tmp/cgroupv2/foo + fi ip link del veth0b ip netns delete at_ns0 umount /tmp/cgroupv2 diff --git a/samples/bpf/test_tunnel_bpf.sh b/samples/bpf/test_tunnel_bpf.sh index 43ce049996ee..c265863ccdf9 100755 --- a/samples/bpf/test_tunnel_bpf.sh +++ b/samples/bpf/test_tunnel_bpf.sh @@ -23,7 +23,8 @@ function config_device { function add_gre_tunnel { # in namespace ip netns exec at_ns0 \ - ip link add dev $DEV_NS type $TYPE key 2 local 172.16.1.100 remote 172.16.1.200 + ip link add dev $DEV_NS type $TYPE seq key 2 \ + local 172.16.1.100 remote 172.16.1.200 ip netns exec at_ns0 ip link set dev $DEV_NS up ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24 @@ -43,7 +44,7 @@ function add_ip6gretap_tunnel { # in namespace ip netns exec at_ns0 \ - ip link add dev $DEV_NS type $TYPE flowlabel 0xbcdef key 2 \ + ip link add dev $DEV_NS type $TYPE seq flowlabel 0xbcdef key 2 \ local ::11 remote ::22 ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24 diff --git a/samples/bpf/xdp_redirect_user.c b/samples/bpf/xdp_redirect_user.c index d54e91eb6cbf..b701b5c21342 100644 --- a/samples/bpf/xdp_redirect_user.c +++ b/samples/bpf/xdp_redirect_user.c @@ -20,6 +20,7 @@ #include <string.h> #include <unistd.h> #include <libgen.h> +#include <sys/resource.h> #include "bpf_load.h" #include "bpf_util.h" @@ -75,6 +76,7 @@ static void usage(const char *prog) int main(int argc, char **argv) { + struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; const char *optstr = "SN"; char filename[256]; int ret, opt, key = 0; @@ -98,6 +100,11 @@ int main(int argc, char **argv) return 1; } + if (setrlimit(RLIMIT_MEMLOCK, &r)) { + perror("setrlimit(RLIMIT_MEMLOCK)"); + return 1; + } + ifindex_in = strtoul(argv[optind], NULL, 0); ifindex_out = strtoul(argv[optind + 1], NULL, 0); printf("input: %d output: %d\n", ifindex_in, ifindex_out); diff --git a/samples/sockmap/Makefile b/samples/sockmap/Makefile index 73f1da4d116c..9bf2881bd11b 100644 --- a/samples/sockmap/Makefile +++ b/samples/sockmap/Makefile @@ -2,7 +2,7 @@ hostprogs-y := sockmap # Libbpf dependencies -LIBBPF := ../../tools/lib/bpf/bpf.o +LIBBPF := ../../tools/lib/bpf/bpf.o ../../tools/lib/bpf/nlattr.o HOSTCFLAGS += -I$(objtree)/usr/include HOSTCFLAGS += -I$(srctree)/tools/lib/ diff --git a/samples/sockmap/sockmap_user.c b/samples/sockmap/sockmap_user.c index 7c25c0c112bc..95a54a89a532 100644 --- a/samples/sockmap/sockmap_user.c +++ b/samples/sockmap/sockmap_user.c @@ -566,6 +566,7 @@ run: else fprintf(stderr, "unknown test\n"); out: + bpf_prog_detach2(prog_fd[2], cg_fd, BPF_CGROUP_SOCK_OPS); close(s1); close(s2); close(p1); diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index 8644d864e3c1..b4d7b6242a40 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -6743,6 +6743,7 @@ static void __net_exit selinux_nf_unregister(struct net *net) static struct pernet_operations selinux_net_ops = { .init = selinux_nf_register, .exit = selinux_nf_unregister, + .async = true, }; static int __init selinux_nf_ip_init(void) diff --git a/security/smack/smack_netfilter.c b/security/smack/smack_netfilter.c index e36d17835d4f..3f29c03162ca 100644 --- a/security/smack/smack_netfilter.c +++ b/security/smack/smack_netfilter.c @@ -89,6 +89,7 @@ static void __net_exit smack_nf_unregister(struct net *net) static struct pernet_operations smack_net_ops = { .init = smack_nf_register, .exit = smack_nf_unregister, + .async = true, }; static int __init smack_nf_ip_init(void) diff --git a/security/tomoyo/network.c b/security/tomoyo/network.c index cd6932e5225c..9094f4b3b367 100644 --- a/security/tomoyo/network.c +++ b/security/tomoyo/network.c @@ -655,10 +655,11 @@ int tomoyo_socket_listen_permission(struct socket *sock) return 0; { const int error = sock->ops->getname(sock, (struct sockaddr *) - &addr, &addr_len, 0); + &addr, 0); - if (error) + if (error < 0) return error; + addr_len = error; } address.protocol = type; address.operation = TOMOYO_NETWORK_LISTEN; diff --git a/tools/bpf/bpftool/Documentation/bpftool-prog.rst b/tools/bpf/bpftool/Documentation/bpftool-prog.rst index e4ceee7f2dff..67ca6c69376c 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-prog.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-prog.rst @@ -21,7 +21,7 @@ MAP COMMANDS ============= | **bpftool** **prog { show | list }** [*PROG*] -| **bpftool** **prog dump xlated** *PROG* [{**file** *FILE* | **opcodes**}] +| **bpftool** **prog dump xlated** *PROG* [{**file** *FILE* | **opcodes** | **visual**}] | **bpftool** **prog dump jited** *PROG* [{**file** *FILE* | **opcodes**}] | **bpftool** **prog pin** *PROG* *FILE* | **bpftool** **prog load** *OBJ* *FILE* @@ -39,12 +39,18 @@ DESCRIPTION Output will start with program ID followed by program type and zero or more named attributes (depending on kernel version). - **bpftool prog dump xlated** *PROG* [{ **file** *FILE* | **opcodes** }] - Dump eBPF instructions of the program from the kernel. - If *FILE* is specified image will be written to a file, - otherwise it will be disassembled and printed to stdout. + **bpftool prog dump xlated** *PROG* [{ **file** *FILE* | **opcodes** | **visual** }] + Dump eBPF instructions of the program from the kernel. By + default, eBPF will be disassembled and printed to standard + output in human-readable format. In this case, **opcodes** + controls if raw opcodes should be printed as well. - **opcodes** controls if raw opcodes will be printed. + If **file** is specified, the binary image will instead be + written to *FILE*. + + If **visual** is specified, control flow graph (CFG) will be + built instead, and eBPF instructions will be presented with + CFG in DOT format, on standard output. **bpftool prog dump jited** *PROG* [{ **file** *FILE* | **opcodes** }] Dump jited image (host machine code) of the program. diff --git a/tools/bpf/bpftool/bash-completion/bpftool b/tools/bpf/bpftool/bash-completion/bpftool index 08719c54a614..490811b45fa7 100644 --- a/tools/bpf/bpftool/bash-completion/bpftool +++ b/tools/bpf/bpftool/bash-completion/bpftool @@ -147,7 +147,7 @@ _bpftool() # Deal with simplest keywords case $prev in - help|key|opcodes) + help|key|opcodes|visual) return 0 ;; tag) @@ -223,11 +223,16 @@ _bpftool() return 0 ;; *) - _bpftool_once_attr 'file' + _bpftool_once_attr 'file' + if _bpftool_search_list 'xlated'; then + COMPREPLY+=( $( compgen -W 'opcodes visual' -- \ + "$cur" ) ) + else COMPREPLY+=( $( compgen -W 'opcodes' -- \ "$cur" ) ) - return 0 - ;; + fi + return 0 + ;; esac ;; pin) diff --git a/tools/bpf/bpftool/cfg.c b/tools/bpf/bpftool/cfg.c new file mode 100644 index 000000000000..f30b3a4a840b --- /dev/null +++ b/tools/bpf/bpftool/cfg.c @@ -0,0 +1,514 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +/* + * Copyright (C) 2018 Netronome Systems, Inc. + * + * This software is dual licensed under the GNU General License Version 2, + * June 1991 as shown in the file COPYING in the top-level directory of this + * source tree or the BSD 2-Clause License provided below. You have the + * option to license this software under the complete terms of either license. + * + * The BSD 2-Clause License: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * 1. Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * 2. Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN + * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE + * POSSIBILITY OF SUCH DAMAGE. + */ + +#include <linux/list.h> +#include <stdlib.h> +#include <string.h> + +#include "cfg.h" +#include "main.h" +#include "xlated_dumper.h" + +struct cfg { + struct list_head funcs; + int func_num; +}; + +struct func_node { + struct list_head l; + struct list_head bbs; + struct bpf_insn *start; + struct bpf_insn *end; + int idx; + int bb_num; +}; + +struct bb_node { + struct list_head l; + struct list_head e_prevs; + struct list_head e_succs; + struct bpf_insn *head; + struct bpf_insn *tail; + int idx; +}; + +#define EDGE_FLAG_EMPTY 0x0 +#define EDGE_FLAG_FALLTHROUGH 0x1 +#define EDGE_FLAG_JUMP 0x2 +struct edge_node { + struct list_head l; + struct bb_node *src; + struct bb_node *dst; + int flags; +}; + +#define ENTRY_BLOCK_INDEX 0 +#define EXIT_BLOCK_INDEX 1 +#define NUM_FIXED_BLOCKS 2 +#define func_prev(func) list_prev_entry(func, l) +#define func_next(func) list_next_entry(func, l) +#define bb_prev(bb) list_prev_entry(bb, l) +#define bb_next(bb) list_next_entry(bb, l) +#define entry_bb(func) func_first_bb(func) +#define exit_bb(func) func_last_bb(func) +#define cfg_first_func(cfg) \ + list_first_entry(&cfg->funcs, struct func_node, l) +#define cfg_last_func(cfg) \ + list_last_entry(&cfg->funcs, struct func_node, l) +#define func_first_bb(func) \ + list_first_entry(&func->bbs, struct bb_node, l) +#define func_last_bb(func) \ + list_last_entry(&func->bbs, struct bb_node, l) + +static struct func_node *cfg_append_func(struct cfg *cfg, struct bpf_insn *insn) +{ + struct func_node *new_func, *func; + + list_for_each_entry(func, &cfg->funcs, l) { + if (func->start == insn) + return func; + else if (func->start > insn) + break; + } + + func = func_prev(func); + new_func = calloc(1, sizeof(*new_func)); + if (!new_func) { + p_err("OOM when allocating FUNC node"); + return NULL; + } + new_func->start = insn; + new_func->idx = cfg->func_num; + list_add(&new_func->l, &func->l); + cfg->func_num++; + + return new_func; +} + +static struct bb_node *func_append_bb(struct func_node *func, + struct bpf_insn *insn) +{ + struct bb_node *new_bb, *bb; + + list_for_each_entry(bb, &func->bbs, l) { + if (bb->head == insn) + return bb; + else if (bb->head > insn) + break; + } + + bb = bb_prev(bb); + new_bb = calloc(1, sizeof(*new_bb)); + if (!new_bb) { + p_err("OOM when allocating BB node"); + return NULL; + } + new_bb->head = insn; + INIT_LIST_HEAD(&new_bb->e_prevs); + INIT_LIST_HEAD(&new_bb->e_succs); + list_add(&new_bb->l, &bb->l); + + return new_bb; +} + +static struct bb_node *func_insert_dummy_bb(struct list_head *after) +{ + struct bb_node *bb; + + bb = calloc(1, sizeof(*bb)); + if (!bb) { + p_err("OOM when allocating BB node"); + return NULL; + } + + INIT_LIST_HEAD(&bb->e_prevs); + INIT_LIST_HEAD(&bb->e_succs); + list_add(&bb->l, after); + + return bb; +} + +static bool cfg_partition_funcs(struct cfg *cfg, struct bpf_insn *cur, + struct bpf_insn *end) +{ + struct func_node *func, *last_func; + + func = cfg_append_func(cfg, cur); + if (!func) + return true; + + for (; cur < end; cur++) { + if (cur->code != (BPF_JMP | BPF_CALL)) + continue; + if (cur->src_reg != BPF_PSEUDO_CALL) + continue; + func = cfg_append_func(cfg, cur + cur->off + 1); + if (!func) + return true; + } + + last_func = cfg_last_func(cfg); + last_func->end = end - 1; + func = cfg_first_func(cfg); + list_for_each_entry_from(func, &last_func->l, l) { + func->end = func_next(func)->start - 1; + } + + return false; +} + +static bool func_partition_bb_head(struct func_node *func) +{ + struct bpf_insn *cur, *end; + struct bb_node *bb; + + cur = func->start; + end = func->end; + INIT_LIST_HEAD(&func->bbs); + bb = func_append_bb(func, cur); + if (!bb) + return true; + + for (; cur <= end; cur++) { + if (BPF_CLASS(cur->code) == BPF_JMP) { + u8 opcode = BPF_OP(cur->code); + + if (opcode == BPF_EXIT || opcode == BPF_CALL) + continue; + + bb = func_append_bb(func, cur + cur->off + 1); + if (!bb) + return true; + + if (opcode != BPF_JA) { + bb = func_append_bb(func, cur + 1); + if (!bb) + return true; + } + } + } + + return false; +} + +static void func_partition_bb_tail(struct func_node *func) +{ + unsigned int bb_idx = NUM_FIXED_BLOCKS; + struct bb_node *bb, *last; + + last = func_last_bb(func); + last->tail = func->end; + bb = func_first_bb(func); + list_for_each_entry_from(bb, &last->l, l) { + bb->tail = bb_next(bb)->head - 1; + bb->idx = bb_idx++; + } + + last->idx = bb_idx++; + func->bb_num = bb_idx; +} + +static bool func_add_special_bb(struct func_node *func) +{ + struct bb_node *bb; + + bb = func_insert_dummy_bb(&func->bbs); + if (!bb) + return true; + bb->idx = ENTRY_BLOCK_INDEX; + + bb = func_insert_dummy_bb(&func_last_bb(func)->l); + if (!bb) + return true; + bb->idx = EXIT_BLOCK_INDEX; + + return false; +} + +static bool func_partition_bb(struct func_node *func) +{ + if (func_partition_bb_head(func)) + return true; + + func_partition_bb_tail(func); + + return false; +} + +static struct bb_node *func_search_bb_with_head(struct func_node *func, + struct bpf_insn *insn) +{ + struct bb_node *bb; + + list_for_each_entry(bb, &func->bbs, l) { + if (bb->head == insn) + return bb; + } + + return NULL; +} + +static struct edge_node *new_edge(struct bb_node *src, struct bb_node *dst, + int flags) +{ + struct edge_node *e; + + e = calloc(1, sizeof(*e)); + if (!e) { + p_err("OOM when allocating edge node"); + return NULL; + } + + if (src) + e->src = src; + if (dst) + e->dst = dst; + + e->flags |= flags; + + return e; +} + +static bool func_add_bb_edges(struct func_node *func) +{ + struct bpf_insn *insn; + struct edge_node *e; + struct bb_node *bb; + + bb = entry_bb(func); + e = new_edge(bb, bb_next(bb), EDGE_FLAG_FALLTHROUGH); + if (!e) + return true; + list_add_tail(&e->l, &bb->e_succs); + + bb = exit_bb(func); + e = new_edge(bb_prev(bb), bb, EDGE_FLAG_FALLTHROUGH); + if (!e) + return true; + list_add_tail(&e->l, &bb->e_prevs); + + bb = entry_bb(func); + bb = bb_next(bb); + list_for_each_entry_from(bb, &exit_bb(func)->l, l) { + e = new_edge(bb, NULL, EDGE_FLAG_EMPTY); + if (!e) + return true; + e->src = bb; + + insn = bb->tail; + if (BPF_CLASS(insn->code) != BPF_JMP || + BPF_OP(insn->code) == BPF_EXIT) { + e->dst = bb_next(bb); + e->flags |= EDGE_FLAG_FALLTHROUGH; + list_add_tail(&e->l, &bb->e_succs); + continue; + } else if (BPF_OP(insn->code) == BPF_JA) { + e->dst = func_search_bb_with_head(func, + insn + insn->off + 1); + e->flags |= EDGE_FLAG_JUMP; + list_add_tail(&e->l, &bb->e_succs); + continue; + } + + e->dst = bb_next(bb); + e->flags |= EDGE_FLAG_FALLTHROUGH; + list_add_tail(&e->l, &bb->e_succs); + + e = new_edge(bb, NULL, EDGE_FLAG_JUMP); + if (!e) + return true; + e->src = bb; + e->dst = func_search_bb_with_head(func, insn + insn->off + 1); + list_add_tail(&e->l, &bb->e_succs); + } + + return false; +} + +static bool cfg_build(struct cfg *cfg, struct bpf_insn *insn, unsigned int len) +{ + int cnt = len / sizeof(*insn); + struct func_node *func; + + INIT_LIST_HEAD(&cfg->funcs); + + if (cfg_partition_funcs(cfg, insn, insn + cnt)) + return true; + + list_for_each_entry(func, &cfg->funcs, l) { + if (func_partition_bb(func) || func_add_special_bb(func)) + return true; + + if (func_add_bb_edges(func)) + return true; + } + + return false; +} + +static void cfg_destroy(struct cfg *cfg) +{ + struct func_node *func, *func2; + + list_for_each_entry_safe(func, func2, &cfg->funcs, l) { + struct bb_node *bb, *bb2; + + list_for_each_entry_safe(bb, bb2, &func->bbs, l) { + struct edge_node *e, *e2; + + list_for_each_entry_safe(e, e2, &bb->e_prevs, l) { + list_del(&e->l); + free(e); + } + + list_for_each_entry_safe(e, e2, &bb->e_succs, l) { + list_del(&e->l); + free(e); + } + + list_del(&bb->l); + free(bb); + } + + list_del(&func->l); + free(func); + } +} + +static void draw_bb_node(struct func_node *func, struct bb_node *bb) +{ + const char *shape; + + if (bb->idx == ENTRY_BLOCK_INDEX || bb->idx == EXIT_BLOCK_INDEX) + shape = "Mdiamond"; + else + shape = "record"; + + printf("\tfn_%d_bb_%d [shape=%s,style=filled,label=\"", + func->idx, bb->idx, shape); + + if (bb->idx == ENTRY_BLOCK_INDEX) { + printf("ENTRY"); + } else if (bb->idx == EXIT_BLOCK_INDEX) { + printf("EXIT"); + } else { + unsigned int start_idx; + struct dump_data dd = {}; + + printf("{"); + kernel_syms_load(&dd); + start_idx = bb->head - func->start; + dump_xlated_for_graph(&dd, bb->head, bb->tail, start_idx); + kernel_syms_destroy(&dd); + printf("}"); + } + + printf("\"];\n\n"); +} + +static void draw_bb_succ_edges(struct func_node *func, struct bb_node *bb) +{ + const char *style = "\"solid,bold\""; + const char *color = "black"; + int func_idx = func->idx; + struct edge_node *e; + int weight = 10; + + if (list_empty(&bb->e_succs)) + return; + + list_for_each_entry(e, &bb->e_succs, l) { + printf("\tfn_%d_bb_%d:s -> fn_%d_bb_%d:n [style=%s, color=%s, weight=%d, constraint=true", + func_idx, e->src->idx, func_idx, e->dst->idx, + style, color, weight); + printf("];\n"); + } +} + +static void func_output_bb_def(struct func_node *func) +{ + struct bb_node *bb; + + list_for_each_entry(bb, &func->bbs, l) { + draw_bb_node(func, bb); + } +} + +static void func_output_edges(struct func_node *func) +{ + int func_idx = func->idx; + struct bb_node *bb; + + list_for_each_entry(bb, &func->bbs, l) { + draw_bb_succ_edges(func, bb); + } + + /* Add an invisible edge from ENTRY to EXIT, this is to + * improve the graph layout. + */ + printf("\tfn_%d_bb_%d:s -> fn_%d_bb_%d:n [style=\"invis\", constraint=true];\n", + func_idx, ENTRY_BLOCK_INDEX, func_idx, EXIT_BLOCK_INDEX); +} + +static void cfg_dump(struct cfg *cfg) +{ + struct func_node *func; + + printf("digraph \"DOT graph for eBPF program\" {\n"); + list_for_each_entry(func, &cfg->funcs, l) { + printf("subgraph \"cluster_%d\" {\n\tstyle=\"dashed\";\n\tcolor=\"black\";\n\tlabel=\"func_%d ()\";\n", + func->idx, func->idx); + func_output_bb_def(func); + func_output_edges(func); + printf("}\n"); + } + printf("}\n"); +} + +void dump_xlated_cfg(void *buf, unsigned int len) +{ + struct bpf_insn *insn = buf; + struct cfg cfg; + + memset(&cfg, 0, sizeof(cfg)); + if (cfg_build(&cfg, insn, len)) + return; + + cfg_dump(&cfg); + + cfg_destroy(&cfg); +} diff --git a/tools/bpf/bpftool/cfg.h b/tools/bpf/bpftool/cfg.h new file mode 100644 index 000000000000..2cc9bd990b13 --- /dev/null +++ b/tools/bpf/bpftool/cfg.h @@ -0,0 +1,43 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +/* + * Copyright (C) 2018 Netronome Systems, Inc. + * + * This software is dual licensed under the GNU General License Version 2, + * June 1991 as shown in the file COPYING in the top-level directory of this + * source tree or the BSD 2-Clause License provided below. You have the + * option to license this software under the complete terms of either license. + * + * The BSD 2-Clause License: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * 1. Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * 2. Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN + * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE + * POSSIBILITY OF SUCH DAMAGE. + */ + +#ifndef __BPF_TOOL_CFG_H +#define __BPF_TOOL_CFG_H + +void dump_xlated_cfg(void *buf, unsigned int len); + +#endif /* __BPF_TOOL_CFG_H */ diff --git a/tools/bpf/bpftool/main.c b/tools/bpf/bpftool/main.c index 185acfa229b5..1ec852d21d44 100644 --- a/tools/bpf/bpftool/main.c +++ b/tools/bpf/bpftool/main.c @@ -46,6 +46,9 @@ #include "main.h" +#define BATCH_LINE_LEN_MAX 65536 +#define BATCH_ARG_NB_MAX 4096 + const char *bin_name; static int last_argc; static char **last_argv; @@ -157,6 +160,54 @@ void fprint_hex(FILE *f, void *arg, unsigned int n, const char *sep) } } +/* Split command line into argument vector. */ +static int make_args(char *line, char *n_argv[], int maxargs, int cmd_nb) +{ + static const char ws[] = " \t\r\n"; + char *cp = line; + int n_argc = 0; + + while (*cp) { + /* Skip leading whitespace. */ + cp += strspn(cp, ws); + + if (*cp == '\0') + break; + + if (n_argc >= (maxargs - 1)) { + p_err("too many arguments to command %d", cmd_nb); + return -1; + } + + /* Word begins with quote. */ + if (*cp == '\'' || *cp == '"') { + char quote = *cp++; + + n_argv[n_argc++] = cp; + /* Find ending quote. */ + cp = strchr(cp, quote); + if (!cp) { + p_err("unterminated quoted string in command %d", + cmd_nb); + return -1; + } + } else { + n_argv[n_argc++] = cp; + + /* Find end of word. */ + cp += strcspn(cp, ws); + if (*cp == '\0') + break; + } + + /* Separate words. */ + *cp++ = 0; + } + n_argv[n_argc] = NULL; + + return n_argc; +} + static int do_batch(int argc, char **argv); static const struct cmd cmds[] = { @@ -171,11 +222,12 @@ static const struct cmd cmds[] = { static int do_batch(int argc, char **argv) { + char buf[BATCH_LINE_LEN_MAX], contline[BATCH_LINE_LEN_MAX]; + char *n_argv[BATCH_ARG_NB_MAX]; unsigned int lines = 0; - char *n_argv[4096]; - char buf[65536]; int n_argc; FILE *fp; + char *cp; int err; int i; @@ -191,7 +243,10 @@ static int do_batch(int argc, char **argv) } NEXT_ARG(); - fp = fopen(*argv, "r"); + if (!strcmp(*argv, "-")) + fp = stdin; + else + fp = fopen(*argv, "r"); if (!fp) { p_err("Can't open file (%s): %s", *argv, strerror(errno)); return -1; @@ -200,27 +255,45 @@ static int do_batch(int argc, char **argv) if (json_output) jsonw_start_array(json_wtr); while (fgets(buf, sizeof(buf), fp)) { + cp = strchr(buf, '#'); + if (cp) + *cp = '\0'; + if (strlen(buf) == sizeof(buf) - 1) { errno = E2BIG; break; } - n_argc = 0; - n_argv[n_argc] = strtok(buf, " \t\n"); - - while (n_argv[n_argc]) { - n_argc++; - if (n_argc == ARRAY_SIZE(n_argv)) { - p_err("line %d has too many arguments, skip", + /* Append continuation lines if any (coming after a line ending + * with '\' in the batch file). + */ + while ((cp = strstr(buf, "\\\n")) != NULL) { + if (!fgets(contline, sizeof(contline), fp) || + strlen(contline) == 0) { + p_err("missing continuation line on command %d", lines); - n_argc = 0; - break; + err = -1; + goto err_close; + } + + cp = strchr(contline, '#'); + if (cp) + *cp = '\0'; + + if (strlen(buf) + strlen(contline) + 1 > sizeof(buf)) { + p_err("command %d is too long", lines); + err = -1; + goto err_close; } - n_argv[n_argc] = strtok(NULL, " \t\n"); + buf[strlen(buf) - 2] = '\0'; + strcat(buf, contline); } + n_argc = make_args(buf, n_argv, BATCH_ARG_NB_MAX, lines); if (!n_argc) continue; + if (n_argc < 0) + goto err_close; if (json_output) { jsonw_start_object(json_wtr); @@ -247,11 +320,12 @@ static int do_batch(int argc, char **argv) p_err("reading batch file failed: %s", strerror(errno)); err = -1; } else { - p_info("processed %d lines", lines); + p_info("processed %d commands", lines); err = 0; } err_close: - fclose(fp); + if (fp != stdin) + fclose(fp); if (json_output) jsonw_end_array(json_wtr); diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c index e549e329be82..f7a810897eac 100644 --- a/tools/bpf/bpftool/prog.c +++ b/tools/bpf/bpftool/prog.c @@ -47,8 +47,9 @@ #include <bpf.h> #include <libbpf.h> +#include "cfg.h" #include "main.h" -#include "disasm.h" +#include "xlated_dumper.h" static const char * const prog_type_name[] = { [BPF_PROG_TYPE_UNSPEC] = "unspec", @@ -407,259 +408,6 @@ static int do_show(int argc, char **argv) return err; } -#define SYM_MAX_NAME 256 - -struct kernel_sym { - unsigned long address; - char name[SYM_MAX_NAME]; -}; - -struct dump_data { - unsigned long address_call_base; - struct kernel_sym *sym_mapping; - __u32 sym_count; - char scratch_buff[SYM_MAX_NAME]; -}; - -static int kernel_syms_cmp(const void *sym_a, const void *sym_b) -{ - return ((struct kernel_sym *)sym_a)->address - - ((struct kernel_sym *)sym_b)->address; -} - -static void kernel_syms_load(struct dump_data *dd) -{ - struct kernel_sym *sym; - char buff[256]; - void *tmp, *address; - FILE *fp; - - fp = fopen("/proc/kallsyms", "r"); - if (!fp) - return; - - while (!feof(fp)) { - if (!fgets(buff, sizeof(buff), fp)) - break; - tmp = realloc(dd->sym_mapping, - (dd->sym_count + 1) * - sizeof(*dd->sym_mapping)); - if (!tmp) { -out: - free(dd->sym_mapping); - dd->sym_mapping = NULL; - fclose(fp); - return; - } - dd->sym_mapping = tmp; - sym = &dd->sym_mapping[dd->sym_count]; - if (sscanf(buff, "%p %*c %s", &address, sym->name) != 2) - continue; - sym->address = (unsigned long)address; - if (!strcmp(sym->name, "__bpf_call_base")) { - dd->address_call_base = sym->address; - /* sysctl kernel.kptr_restrict was set */ - if (!sym->address) - goto out; - } - if (sym->address) - dd->sym_count++; - } - - fclose(fp); - - qsort(dd->sym_mapping, dd->sym_count, - sizeof(*dd->sym_mapping), kernel_syms_cmp); -} - -static void kernel_syms_destroy(struct dump_data *dd) -{ - free(dd->sym_mapping); -} - -static struct kernel_sym *kernel_syms_search(struct dump_data *dd, - unsigned long key) -{ - struct kernel_sym sym = { - .address = key, - }; - - return dd->sym_mapping ? - bsearch(&sym, dd->sym_mapping, dd->sym_count, - sizeof(*dd->sym_mapping), kernel_syms_cmp) : NULL; -} - -static void print_insn(struct bpf_verifier_env *env, const char *fmt, ...) -{ - va_list args; - - va_start(args, fmt); - vprintf(fmt, args); - va_end(args); -} - -static const char *print_call_pcrel(struct dump_data *dd, - struct kernel_sym *sym, - unsigned long address, - const struct bpf_insn *insn) -{ - if (sym) - snprintf(dd->scratch_buff, sizeof(dd->scratch_buff), - "%+d#%s", insn->off, sym->name); - else - snprintf(dd->scratch_buff, sizeof(dd->scratch_buff), - "%+d#0x%lx", insn->off, address); - return dd->scratch_buff; -} - -static const char *print_call_helper(struct dump_data *dd, - struct kernel_sym *sym, - unsigned long address) -{ - if (sym) - snprintf(dd->scratch_buff, sizeof(dd->scratch_buff), - "%s", sym->name); - else - snprintf(dd->scratch_buff, sizeof(dd->scratch_buff), - "0x%lx", address); - return dd->scratch_buff; -} - -static const char *print_call(void *private_data, - const struct bpf_insn *insn) -{ - struct dump_data *dd = private_data; - unsigned long address = dd->address_call_base + insn->imm; - struct kernel_sym *sym; - - sym = kernel_syms_search(dd, address); - if (insn->src_reg == BPF_PSEUDO_CALL) - return print_call_pcrel(dd, sym, address, insn); - else - return print_call_helper(dd, sym, address); -} - -static const char *print_imm(void *private_data, - const struct bpf_insn *insn, - __u64 full_imm) -{ - struct dump_data *dd = private_data; - - if (insn->src_reg == BPF_PSEUDO_MAP_FD) - snprintf(dd->scratch_buff, sizeof(dd->scratch_buff), - "map[id:%u]", insn->imm); - else - snprintf(dd->scratch_buff, sizeof(dd->scratch_buff), - "0x%llx", (unsigned long long)full_imm); - return dd->scratch_buff; -} - -static void dump_xlated_plain(struct dump_data *dd, void *buf, - unsigned int len, bool opcodes) -{ - const struct bpf_insn_cbs cbs = { - .cb_print = print_insn, - .cb_call = print_call, - .cb_imm = print_imm, - .private_data = dd, - }; - struct bpf_insn *insn = buf; - bool double_insn = false; - unsigned int i; - - for (i = 0; i < len / sizeof(*insn); i++) { - if (double_insn) { - double_insn = false; - continue; - } - - double_insn = insn[i].code == (BPF_LD | BPF_IMM | BPF_DW); - - printf("% 4d: ", i); - print_bpf_insn(&cbs, NULL, insn + i, true); - - if (opcodes) { - printf(" "); - fprint_hex(stdout, insn + i, 8, " "); - if (double_insn && i < len - 1) { - printf(" "); - fprint_hex(stdout, insn + i + 1, 8, " "); - } - printf("\n"); - } - } -} - -static void print_insn_json(struct bpf_verifier_env *env, const char *fmt, ...) -{ - unsigned int l = strlen(fmt); - char chomped_fmt[l]; - va_list args; - - va_start(args, fmt); - if (l > 0) { - strncpy(chomped_fmt, fmt, l - 1); - chomped_fmt[l - 1] = '\0'; - } - jsonw_vprintf_enquote(json_wtr, chomped_fmt, args); - va_end(args); -} - -static void dump_xlated_json(struct dump_data *dd, void *buf, - unsigned int len, bool opcodes) -{ - const struct bpf_insn_cbs cbs = { - .cb_print = print_insn_json, - .cb_call = print_call, - .cb_imm = print_imm, - .private_data = dd, - }; - struct bpf_insn *insn = buf; - bool double_insn = false; - unsigned int i; - - jsonw_start_array(json_wtr); - for (i = 0; i < len / sizeof(*insn); i++) { - if (double_insn) { - double_insn = false; - continue; - } - double_insn = insn[i].code == (BPF_LD | BPF_IMM | BPF_DW); - - jsonw_start_object(json_wtr); - jsonw_name(json_wtr, "disasm"); - print_bpf_insn(&cbs, NULL, insn + i, true); - - if (opcodes) { - jsonw_name(json_wtr, "opcodes"); - jsonw_start_object(json_wtr); - - jsonw_name(json_wtr, "code"); - jsonw_printf(json_wtr, "\"0x%02hhx\"", insn[i].code); - - jsonw_name(json_wtr, "src_reg"); - jsonw_printf(json_wtr, "\"0x%hhx\"", insn[i].src_reg); - - jsonw_name(json_wtr, "dst_reg"); - jsonw_printf(json_wtr, "\"0x%hhx\"", insn[i].dst_reg); - - jsonw_name(json_wtr, "off"); - print_hex_data_json((uint8_t *)(&insn[i].off), 2); - - jsonw_name(json_wtr, "imm"); - if (double_insn && i < len - 1) - print_hex_data_json((uint8_t *)(&insn[i].imm), - 12); - else - print_hex_data_json((uint8_t *)(&insn[i].imm), - 4); - jsonw_end_object(json_wtr); - } - jsonw_end_object(json_wtr); - } - jsonw_end_array(json_wtr); -} - static int do_dump(int argc, char **argv) { struct bpf_prog_info info = {}; @@ -668,6 +416,7 @@ static int do_dump(int argc, char **argv) unsigned int buf_size; char *filepath = NULL; bool opcodes = false; + bool visual = false; unsigned char *buf; __u32 *member_len; __u64 *member_ptr; @@ -706,6 +455,9 @@ static int do_dump(int argc, char **argv) } else if (is_prefix(*argv, "opcodes")) { opcodes = true; NEXT_ARG(); + } else if (is_prefix(*argv, "visual")) { + visual = true; + NEXT_ARG(); } if (argc) { @@ -777,27 +529,30 @@ static int do_dump(int argc, char **argv) if (json_output) jsonw_null(json_wtr); - } else { - if (member_len == &info.jited_prog_len) { - const char *name = NULL; - - if (info.ifindex) { - name = ifindex_to_bfd_name_ns(info.ifindex, - info.netns_dev, - info.netns_ino); - if (!name) - goto err_free; - } - - disasm_print_insn(buf, *member_len, opcodes, name); - } else { - kernel_syms_load(&dd); - if (json_output) - dump_xlated_json(&dd, buf, *member_len, opcodes); - else - dump_xlated_plain(&dd, buf, *member_len, opcodes); - kernel_syms_destroy(&dd); + } else if (member_len == &info.jited_prog_len) { + const char *name = NULL; + + if (info.ifindex) { + name = ifindex_to_bfd_name_ns(info.ifindex, + info.netns_dev, + info.netns_ino); + if (!name) + goto err_free; } + + disasm_print_insn(buf, *member_len, opcodes, name); + } else if (visual) { + if (json_output) + jsonw_null(json_wtr); + else + dump_xlated_cfg(buf, *member_len); + } else { + kernel_syms_load(&dd); + if (json_output) + dump_xlated_json(&dd, buf, *member_len, opcodes); + else + dump_xlated_plain(&dd, buf, *member_len, opcodes); + kernel_syms_destroy(&dd); } free(buf); @@ -851,7 +606,7 @@ static int do_help(int argc, char **argv) fprintf(stderr, "Usage: %s %s { show | list } [PROG]\n" - " %s %s dump xlated PROG [{ file FILE | opcodes }]\n" + " %s %s dump xlated PROG [{ file FILE | opcodes | visual }]\n" " %s %s dump jited PROG [{ file FILE | opcodes }]\n" " %s %s pin PROG FILE\n" " %s %s load OBJ FILE\n" diff --git a/tools/bpf/bpftool/xlated_dumper.c b/tools/bpf/bpftool/xlated_dumper.c new file mode 100644 index 000000000000..20da835e9e38 --- /dev/null +++ b/tools/bpf/bpftool/xlated_dumper.c @@ -0,0 +1,338 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +/* + * Copyright (C) 2018 Netronome Systems, Inc. + * + * This software is dual licensed under the GNU General License Version 2, + * June 1991 as shown in the file COPYING in the top-level directory of this + * source tree or the BSD 2-Clause License provided below. You have the + * option to license this software under the complete terms of either license. + * + * The BSD 2-Clause License: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * 1. Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * 2. Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN + * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE + * POSSIBILITY OF SUCH DAMAGE. + */ + +#include <stdarg.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/types.h> + +#include "disasm.h" +#include "json_writer.h" +#include "main.h" +#include "xlated_dumper.h" + +static int kernel_syms_cmp(const void *sym_a, const void *sym_b) +{ + return ((struct kernel_sym *)sym_a)->address - + ((struct kernel_sym *)sym_b)->address; +} + +void kernel_syms_load(struct dump_data *dd) +{ + struct kernel_sym *sym; + char buff[256]; + void *tmp, *address; + FILE *fp; + + fp = fopen("/proc/kallsyms", "r"); + if (!fp) + return; + + while (!feof(fp)) { + if (!fgets(buff, sizeof(buff), fp)) + break; + tmp = realloc(dd->sym_mapping, + (dd->sym_count + 1) * + sizeof(*dd->sym_mapping)); + if (!tmp) { +out: + free(dd->sym_mapping); + dd->sym_mapping = NULL; + fclose(fp); + return; + } + dd->sym_mapping = tmp; + sym = &dd->sym_mapping[dd->sym_count]; + if (sscanf(buff, "%p %*c %s", &address, sym->name) != 2) + continue; + sym->address = (unsigned long)address; + if (!strcmp(sym->name, "__bpf_call_base")) { + dd->address_call_base = sym->address; + /* sysctl kernel.kptr_restrict was set */ + if (!sym->address) + goto out; + } + if (sym->address) + dd->sym_count++; + } + + fclose(fp); + + qsort(dd->sym_mapping, dd->sym_count, + sizeof(*dd->sym_mapping), kernel_syms_cmp); +} + +void kernel_syms_destroy(struct dump_data *dd) +{ + free(dd->sym_mapping); +} + +static struct kernel_sym *kernel_syms_search(struct dump_data *dd, + unsigned long key) +{ + struct kernel_sym sym = { + .address = key, + }; + + return dd->sym_mapping ? + bsearch(&sym, dd->sym_mapping, dd->sym_count, + sizeof(*dd->sym_mapping), kernel_syms_cmp) : NULL; +} + +static void print_insn(struct bpf_verifier_env *env, const char *fmt, ...) +{ + va_list args; + + va_start(args, fmt); + vprintf(fmt, args); + va_end(args); +} + +static void +print_insn_for_graph(struct bpf_verifier_env *env, const char *fmt, ...) +{ + char buf[64], *p; + va_list args; + + va_start(args, fmt); + vsnprintf(buf, sizeof(buf), fmt, args); + va_end(args); + + p = buf; + while (*p != '\0') { + if (*p == '\n') { + memmove(p + 3, p, strlen(buf) + 1 - (p - buf)); + /* Align each instruction dump row left. */ + *p++ = '\\'; + *p++ = 'l'; + /* Output multiline concatenation. */ + *p++ = '\\'; + } else if (*p == '<' || *p == '>' || *p == '|' || *p == '&') { + memmove(p + 1, p, strlen(buf) + 1 - (p - buf)); + /* Escape special character. */ + *p++ = '\\'; + } + + p++; + } + + printf("%s", buf); +} + +static void print_insn_json(struct bpf_verifier_env *env, const char *fmt, ...) +{ + unsigned int l = strlen(fmt); + char chomped_fmt[l]; + va_list args; + + va_start(args, fmt); + if (l > 0) { + strncpy(chomped_fmt, fmt, l - 1); + chomped_fmt[l - 1] = '\0'; + } + jsonw_vprintf_enquote(json_wtr, chomped_fmt, args); + va_end(args); +} + +static const char *print_call_pcrel(struct dump_data *dd, + struct kernel_sym *sym, + unsigned long address, + const struct bpf_insn *insn) +{ + if (sym) + snprintf(dd->scratch_buff, sizeof(dd->scratch_buff), + "%+d#%s", insn->off, sym->name); + else + snprintf(dd->scratch_buff, sizeof(dd->scratch_buff), + "%+d#0x%lx", insn->off, address); + return dd->scratch_buff; +} + +static const char *print_call_helper(struct dump_data *dd, + struct kernel_sym *sym, + unsigned long address) +{ + if (sym) + snprintf(dd->scratch_buff, sizeof(dd->scratch_buff), + "%s", sym->name); + else + snprintf(dd->scratch_buff, sizeof(dd->scratch_buff), + "0x%lx", address); + return dd->scratch_buff; +} + +static const char *print_call(void *private_data, + const struct bpf_insn *insn) +{ + struct dump_data *dd = private_data; + unsigned long address = dd->address_call_base + insn->imm; + struct kernel_sym *sym; + + sym = kernel_syms_search(dd, address); + if (insn->src_reg == BPF_PSEUDO_CALL) + return print_call_pcrel(dd, sym, address, insn); + else + return print_call_helper(dd, sym, address); +} + +static const char *print_imm(void *private_data, + const struct bpf_insn *insn, + __u64 full_imm) +{ + struct dump_data *dd = private_data; + + if (insn->src_reg == BPF_PSEUDO_MAP_FD) + snprintf(dd->scratch_buff, sizeof(dd->scratch_buff), + "map[id:%u]", insn->imm); + else + snprintf(dd->scratch_buff, sizeof(dd->scratch_buff), + "0x%llx", (unsigned long long)full_imm); + return dd->scratch_buff; +} + +void dump_xlated_json(struct dump_data *dd, void *buf, unsigned int len, + bool opcodes) +{ + const struct bpf_insn_cbs cbs = { + .cb_print = print_insn_json, + .cb_call = print_call, + .cb_imm = print_imm, + .private_data = dd, + }; + struct bpf_insn *insn = buf; + bool double_insn = false; + unsigned int i; + + jsonw_start_array(json_wtr); + for (i = 0; i < len / sizeof(*insn); i++) { + if (double_insn) { + double_insn = false; + continue; + } + double_insn = insn[i].code == (BPF_LD | BPF_IMM | BPF_DW); + + jsonw_start_object(json_wtr); + jsonw_name(json_wtr, "disasm"); + print_bpf_insn(&cbs, NULL, insn + i, true); + + if (opcodes) { + jsonw_name(json_wtr, "opcodes"); + jsonw_start_object(json_wtr); + + jsonw_name(json_wtr, "code"); + jsonw_printf(json_wtr, "\"0x%02hhx\"", insn[i].code); + + jsonw_name(json_wtr, "src_reg"); + jsonw_printf(json_wtr, "\"0x%hhx\"", insn[i].src_reg); + + jsonw_name(json_wtr, "dst_reg"); + jsonw_printf(json_wtr, "\"0x%hhx\"", insn[i].dst_reg); + + jsonw_name(json_wtr, "off"); + print_hex_data_json((uint8_t *)(&insn[i].off), 2); + + jsonw_name(json_wtr, "imm"); + if (double_insn && i < len - 1) + print_hex_data_json((uint8_t *)(&insn[i].imm), + 12); + else + print_hex_data_json((uint8_t *)(&insn[i].imm), + 4); + jsonw_end_object(json_wtr); + } + jsonw_end_object(json_wtr); + } + jsonw_end_array(json_wtr); +} + +void dump_xlated_plain(struct dump_data *dd, void *buf, unsigned int len, + bool opcodes) +{ + const struct bpf_insn_cbs cbs = { + .cb_print = print_insn, + .cb_call = print_call, + .cb_imm = print_imm, + .private_data = dd, + }; + struct bpf_insn *insn = buf; + bool double_insn = false; + unsigned int i; + + for (i = 0; i < len / sizeof(*insn); i++) { + if (double_insn) { + double_insn = false; + continue; + } + + double_insn = insn[i].code == (BPF_LD | BPF_IMM | BPF_DW); + + printf("% 4d: ", i); + print_bpf_insn(&cbs, NULL, insn + i, true); + + if (opcodes) { + printf(" "); + fprint_hex(stdout, insn + i, 8, " "); + if (double_insn && i < len - 1) { + printf(" "); + fprint_hex(stdout, insn + i + 1, 8, " "); + } + printf("\n"); + } + } +} + +void dump_xlated_for_graph(struct dump_data *dd, void *buf_start, void *buf_end, + unsigned int start_idx) +{ + const struct bpf_insn_cbs cbs = { + .cb_print = print_insn_for_graph, + .cb_call = print_call, + .cb_imm = print_imm, + .private_data = dd, + }; + struct bpf_insn *insn_start = buf_start; + struct bpf_insn *insn_end = buf_end; + struct bpf_insn *cur = insn_start; + + for (; cur <= insn_end; cur++) { + printf("% 4d: ", (int)(cur - insn_start + start_idx)); + print_bpf_insn(&cbs, NULL, cur, true); + if (cur != insn_end) + printf(" | "); + } +} diff --git a/tools/bpf/bpftool/xlated_dumper.h b/tools/bpf/bpftool/xlated_dumper.h new file mode 100644 index 000000000000..51c935d38ae2 --- /dev/null +++ b/tools/bpf/bpftool/xlated_dumper.h @@ -0,0 +1,64 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +/* + * Copyright (C) 2018 Netronome Systems, Inc. + * + * This software is dual licensed under the GNU General License Version 2, + * June 1991 as shown in the file COPYING in the top-level directory of this + * source tree or the BSD 2-Clause License provided below. You have the + * option to license this software under the complete terms of either license. + * + * The BSD 2-Clause License: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * 1. Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * 2. Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN + * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE + * POSSIBILITY OF SUCH DAMAGE. + */ + +#ifndef __BPF_TOOL_XLATED_DUMPER_H +#define __BPF_TOOL_XLATED_DUMPER_H + +#define SYM_MAX_NAME 256 + +struct kernel_sym { + unsigned long address; + char name[SYM_MAX_NAME]; +}; + +struct dump_data { + unsigned long address_call_base; + struct kernel_sym *sym_mapping; + __u32 sym_count; + char scratch_buff[SYM_MAX_NAME]; +}; + +void kernel_syms_load(struct dump_data *dd); +void kernel_syms_destroy(struct dump_data *dd); +void dump_xlated_json(struct dump_data *dd, void *buf, unsigned int len, + bool opcodes); +void dump_xlated_plain(struct dump_data *dd, void *buf, unsigned int len, + bool opcodes); +void dump_xlated_for_graph(struct dump_data *dd, void *buf, void *buf_end, + unsigned int start_index); + +#endif diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 5c43c187f27c..8567a858b789 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -35,12 +35,14 @@ TEST_GEN_PROGS_EXTENDED = test_libbpf_open include ../lib.mk -BPFOBJ := $(OUTPUT)/libbpf.a cgroup_helpers.c +BPFOBJ := $(OUTPUT)/libbpf.a $(TEST_GEN_PROGS): $(BPFOBJ) $(TEST_GEN_PROGS_EXTENDED): $(OUTPUT)/libbpf.a +$(OUTPUT)/test_dev_cgroup: cgroup_helpers.c + .PHONY: force # force a rebuild of BPFOBJ when its dependencies are updated diff --git a/tools/testing/selftests/bpf/bpf_rlimit.h b/tools/testing/selftests/bpf/bpf_rlimit.h new file mode 100644 index 000000000000..9dac9b30f8ef --- /dev/null +++ b/tools/testing/selftests/bpf/bpf_rlimit.h @@ -0,0 +1,28 @@ +#include <sys/resource.h> +#include <stdio.h> + +static __attribute__((constructor)) void bpf_rlimit_ctor(void) +{ + struct rlimit rlim_old, rlim_new = { + .rlim_cur = RLIM_INFINITY, + .rlim_max = RLIM_INFINITY, + }; + + getrlimit(RLIMIT_MEMLOCK, &rlim_old); + /* For the sake of running the test cases, we temporarily + * set rlimit to infinity in order for kernel to focus on + * errors from actual test cases and not getting noise + * from hitting memlock limits. The limit is on per-process + * basis and not a global one, hence destructor not really + * needed here. + */ + if (setrlimit(RLIMIT_MEMLOCK, &rlim_new) < 0) { + perror("Unable to lift memlock rlimit"); + /* Trying out lower limit, but expect potential test + * case failures from this! + */ + rlim_new.rlim_cur = rlim_old.rlim_cur + (1UL << 20); + rlim_new.rlim_max = rlim_old.rlim_max + (1UL << 20); + setrlimit(RLIMIT_MEMLOCK, &rlim_new); + } +} diff --git a/tools/testing/selftests/bpf/test_align.c b/tools/testing/selftests/bpf/test_align.c index ff8bd7e3e50c..6b1b302310fe 100644 --- a/tools/testing/selftests/bpf/test_align.c +++ b/tools/testing/selftests/bpf/test_align.c @@ -9,8 +9,6 @@ #include <stddef.h> #include <stdbool.h> -#include <sys/resource.h> - #include <linux/unistd.h> #include <linux/filter.h> #include <linux/bpf_perf_event.h> @@ -19,6 +17,7 @@ #include <bpf/bpf.h> #include "../../../include/linux/filter.h" +#include "bpf_rlimit.h" #ifndef ARRAY_SIZE # define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0])) @@ -702,9 +701,6 @@ static int do_test(unsigned int from, unsigned int to) int main(int argc, char **argv) { unsigned int from = 0, to = ARRAY_SIZE(tests); - struct rlimit rinf = { RLIM_INFINITY, RLIM_INFINITY }; - - setrlimit(RLIMIT_MEMLOCK, &rinf); if (argc == 3) { unsigned int l = atoi(argv[argc - 2]); diff --git a/tools/testing/selftests/bpf/test_dev_cgroup.c b/tools/testing/selftests/bpf/test_dev_cgroup.c index 3489cc283433..9c8b50bac7e0 100644 --- a/tools/testing/selftests/bpf/test_dev_cgroup.c +++ b/tools/testing/selftests/bpf/test_dev_cgroup.c @@ -11,13 +11,13 @@ #include <errno.h> #include <assert.h> #include <sys/time.h> -#include <sys/resource.h> #include <linux/bpf.h> #include <bpf/bpf.h> #include <bpf/libbpf.h> #include "cgroup_helpers.h" +#include "bpf_rlimit.h" #define DEV_CGROUP_PROG "./dev_cgroup.o" @@ -25,15 +25,11 @@ int main(int argc, char **argv) { - struct rlimit limit = { RLIM_INFINITY, RLIM_INFINITY }; struct bpf_object *obj; int error = EXIT_FAILURE; int prog_fd, cgroup_fd; __u32 prog_cnt; - if (setrlimit(RLIMIT_MEMLOCK, &limit) < 0) - perror("Unable to lift memlock rlimit"); - if (bpf_prog_load(DEV_CGROUP_PROG, BPF_PROG_TYPE_CGROUP_DEVICE, &obj, &prog_fd)) { printf("Failed to load DEV_CGROUP program\n"); diff --git a/tools/testing/selftests/bpf/test_lpm_map.c b/tools/testing/selftests/bpf/test_lpm_map.c index 2be87e9ee28d..147e34cfceb7 100644 --- a/tools/testing/selftests/bpf/test_lpm_map.c +++ b/tools/testing/selftests/bpf/test_lpm_map.c @@ -22,10 +22,11 @@ #include <unistd.h> #include <arpa/inet.h> #include <sys/time.h> -#include <sys/resource.h> #include <bpf/bpf.h> + #include "bpf_util.h" +#include "bpf_rlimit.h" struct tlpm_node { struct tlpm_node *next; @@ -736,17 +737,11 @@ static void test_lpm_multi_thread(void) int main(void) { - struct rlimit limit = { RLIM_INFINITY, RLIM_INFINITY }; - int i, ret; + int i; /* we want predictable, pseudo random tests */ srand(0xf00ba1); - /* allow unlimited locked memory */ - ret = setrlimit(RLIMIT_MEMLOCK, &limit); - if (ret < 0) - perror("Unable to lift memlock rlimit"); - test_lpm_basic(); test_lpm_order(); @@ -755,11 +750,8 @@ int main(void) test_lpm_map(i); test_lpm_ipaddr(); - test_lpm_delete(); - test_lpm_get_next_key(); - test_lpm_multi_thread(); printf("test_lpm: OK\n"); diff --git a/tools/testing/selftests/bpf/test_lru_map.c b/tools/testing/selftests/bpf/test_lru_map.c index 8c10c9180c1a..781c7de343be 100644 --- a/tools/testing/selftests/bpf/test_lru_map.c +++ b/tools/testing/selftests/bpf/test_lru_map.c @@ -16,10 +16,11 @@ #include <time.h> #include <sys/wait.h> -#include <sys/resource.h> #include <bpf/bpf.h> + #include "bpf_util.h" +#include "bpf_rlimit.h" #define LOCAL_FREE_TARGET (128) #define PERCPU_FREE_TARGET (4) @@ -613,7 +614,6 @@ static void test_lru_sanity6(int map_type, int map_flags, int tgt_free) int main(int argc, char **argv) { - struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; int map_types[] = {BPF_MAP_TYPE_LRU_HASH, BPF_MAP_TYPE_LRU_PERCPU_HASH}; int map_flags[] = {0, BPF_F_NO_COMMON_LRU}; @@ -621,8 +621,6 @@ int main(int argc, char **argv) setbuf(stdout, NULL); - assert(!setrlimit(RLIMIT_MEMLOCK, &r)); - nr_cpus = bpf_num_possible_cpus(); assert(nr_cpus != -1); printf("nr_cpus:%d\n\n", nr_cpus); diff --git a/tools/testing/selftests/bpf/test_maps.c b/tools/testing/selftests/bpf/test_maps.c index 9e03a4c356a4..1238733c5b33 100644 --- a/tools/testing/selftests/bpf/test_maps.c +++ b/tools/testing/selftests/bpf/test_maps.c @@ -17,13 +17,14 @@ #include <stdlib.h> #include <sys/wait.h> -#include <sys/resource.h> #include <linux/bpf.h> #include <bpf/bpf.h> #include <bpf/libbpf.h> + #include "bpf_util.h" +#include "bpf_rlimit.h" static int map_flags; @@ -1126,10 +1127,6 @@ static void run_all_tests(void) int main(void) { - struct rlimit rinf = { RLIM_INFINITY, RLIM_INFINITY }; - - setrlimit(RLIMIT_MEMLOCK, &rinf); - map_flags = 0; run_all_tests(); diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c index b549308abd19..27ad5404389e 100644 --- a/tools/testing/selftests/bpf/test_progs.c +++ b/tools/testing/selftests/bpf/test_progs.c @@ -26,7 +26,6 @@ typedef __u16 __sum16; #include <sys/ioctl.h> #include <sys/wait.h> -#include <sys/resource.h> #include <sys/types.h> #include <fcntl.h> @@ -34,9 +33,11 @@ typedef __u16 __sum16; #include <linux/err.h> #include <bpf/bpf.h> #include <bpf/libbpf.h> + #include "test_iptunnel_common.h" #include "bpf_util.h" #include "bpf_endian.h" +#include "bpf_rlimit.h" static int error_cnt, pass_cnt; @@ -965,10 +966,6 @@ out: int main(void) { - struct rlimit rinf = { RLIM_INFINITY, RLIM_INFINITY }; - - setrlimit(RLIMIT_MEMLOCK, &rinf); - test_pkt_access(); test_xdp(); test_l4lb_all(); diff --git a/tools/testing/selftests/bpf/test_tag.c b/tools/testing/selftests/bpf/test_tag.c index 8b201895c569..6272c784ca2a 100644 --- a/tools/testing/selftests/bpf/test_tag.c +++ b/tools/testing/selftests/bpf/test_tag.c @@ -12,7 +12,6 @@ #include <assert.h> #include <sys/socket.h> -#include <sys/resource.h> #include <linux/filter.h> #include <linux/bpf.h> @@ -21,6 +20,7 @@ #include <bpf/bpf.h> #include "../../../include/linux/filter.h" +#include "bpf_rlimit.h" static struct bpf_insn prog[BPF_MAXINSNS]; @@ -184,11 +184,9 @@ static void do_test(uint32_t *tests, int start_insns, int fd_map, int main(void) { - struct rlimit rinf = { RLIM_INFINITY, RLIM_INFINITY }; uint32_t tests = 0; int i, fd_map; - setrlimit(RLIMIT_MEMLOCK, &rinf); fd_map = bpf_create_map(BPF_MAP_TYPE_HASH, sizeof(int), sizeof(int), 1, BPF_F_NO_PREALLOC); assert(fd_map > 0); diff --git a/tools/testing/selftests/bpf/test_tcpbpf_user.c b/tools/testing/selftests/bpf/test_tcpbpf_user.c index 95a370f3d378..84ab5163c828 100644 --- a/tools/testing/selftests/bpf/test_tcpbpf_user.c +++ b/tools/testing/selftests/bpf/test_tcpbpf_user.c @@ -11,12 +11,14 @@ #include <linux/ptrace.h> #include <linux/bpf.h> #include <sys/ioctl.h> +#include <sys/time.h> #include <sys/types.h> #include <sys/stat.h> #include <fcntl.h> #include <bpf/bpf.h> #include <bpf/libbpf.h> #include "bpf_util.h" +#include "bpf_rlimit.h" #include <linux/perf_event.h> #include "test_tcpbpf.h" diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c index 437c0b1c9d21..86d7ff491b6f 100644 --- a/tools/testing/selftests/bpf/test_verifier.c +++ b/tools/testing/selftests/bpf/test_verifier.c @@ -24,7 +24,6 @@ #include <limits.h> #include <sys/capability.h> -#include <sys/resource.h> #include <linux/unistd.h> #include <linux/filter.h> @@ -41,7 +40,7 @@ # define CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS 1 # endif #endif - +#include "bpf_rlimit.h" #include "../../../include/linux/filter.h" #ifndef ARRAY_SIZE @@ -57,6 +56,9 @@ #define F_NEEDS_EFFICIENT_UNALIGNED_ACCESS (1 << 0) #define F_LOAD_WITH_STRICT_ALIGNMENT (1 << 1) +#define UNPRIV_SYSCTL "kernel/unprivileged_bpf_disabled" +static bool unpriv_disabled = false; + struct bpf_test { const char *descr; struct bpf_insn insns[MAX_INSNS]; @@ -2587,17 +2589,74 @@ static struct bpf_test tests[] = { .result = ACCEPT, }, { + "runtime/jit: tail_call within bounds, prog once", + .insns = { + BPF_MOV64_IMM(BPF_REG_3, 0), + BPF_LD_MAP_FD(BPF_REG_2, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_tail_call), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .fixup_prog = { 1 }, + .result = ACCEPT, + .retval = 42, + }, + { + "runtime/jit: tail_call within bounds, prog loop", + .insns = { + BPF_MOV64_IMM(BPF_REG_3, 1), + BPF_LD_MAP_FD(BPF_REG_2, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_tail_call), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .fixup_prog = { 1 }, + .result = ACCEPT, + .retval = 41, + }, + { + "runtime/jit: tail_call within bounds, no prog", + .insns = { + BPF_MOV64_IMM(BPF_REG_3, 2), + BPF_LD_MAP_FD(BPF_REG_2, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_tail_call), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .fixup_prog = { 1 }, + .result = ACCEPT, + .retval = 1, + }, + { + "runtime/jit: tail_call out of bounds", + .insns = { + BPF_MOV64_IMM(BPF_REG_3, 256), + BPF_LD_MAP_FD(BPF_REG_2, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_tail_call), + BPF_MOV64_IMM(BPF_REG_0, 2), + BPF_EXIT_INSN(), + }, + .fixup_prog = { 1 }, + .result = ACCEPT, + .retval = 2, + }, + { "runtime/jit: pass negative index to tail_call", .insns = { BPF_MOV64_IMM(BPF_REG_3, -1), BPF_LD_MAP_FD(BPF_REG_2, 0), BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_tail_call), - BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_MOV64_IMM(BPF_REG_0, 2), BPF_EXIT_INSN(), }, .fixup_prog = { 1 }, .result = ACCEPT, + .retval = 2, }, { "runtime/jit: pass > 32bit index to tail_call", @@ -2606,11 +2665,12 @@ static struct bpf_test tests[] = { BPF_LD_MAP_FD(BPF_REG_2, 0), BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_tail_call), - BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_MOV64_IMM(BPF_REG_0, 2), BPF_EXIT_INSN(), }, .fixup_prog = { 2 }, .result = ACCEPT, + .retval = 42, }, { "stack pointer arithmetic", @@ -11164,6 +11224,94 @@ static struct bpf_test tests[] = { .prog_type = BPF_PROG_TYPE_TRACEPOINT, }, { + "jit: lsh, rsh, arsh by 1", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_MOV64_IMM(BPF_REG_1, 0xff), + BPF_ALU64_IMM(BPF_LSH, BPF_REG_1, 1), + BPF_ALU32_IMM(BPF_LSH, BPF_REG_1, 1), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0x3fc, 1), + BPF_EXIT_INSN(), + BPF_ALU64_IMM(BPF_RSH, BPF_REG_1, 1), + BPF_ALU32_IMM(BPF_RSH, BPF_REG_1, 1), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0xff, 1), + BPF_EXIT_INSN(), + BPF_ALU64_IMM(BPF_ARSH, BPF_REG_1, 1), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0x7f, 1), + BPF_EXIT_INSN(), + BPF_MOV64_IMM(BPF_REG_0, 2), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .retval = 2, + }, + { + "jit: mov32 for ldimm64, 1", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 2), + BPF_LD_IMM64(BPF_REG_1, 0xfeffffffffffffffULL), + BPF_ALU64_IMM(BPF_RSH, BPF_REG_1, 32), + BPF_LD_IMM64(BPF_REG_2, 0xfeffffffULL), + BPF_JMP_REG(BPF_JEQ, BPF_REG_1, BPF_REG_2, 1), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .retval = 2, + }, + { + "jit: mov32 for ldimm64, 2", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_LD_IMM64(BPF_REG_1, 0x1ffffffffULL), + BPF_LD_IMM64(BPF_REG_2, 0xffffffffULL), + BPF_JMP_REG(BPF_JEQ, BPF_REG_1, BPF_REG_2, 1), + BPF_MOV64_IMM(BPF_REG_0, 2), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .retval = 2, + }, + { + "jit: various mul tests", + .insns = { + BPF_LD_IMM64(BPF_REG_2, 0xeeff0d413122ULL), + BPF_LD_IMM64(BPF_REG_0, 0xfefefeULL), + BPF_LD_IMM64(BPF_REG_1, 0xefefefULL), + BPF_ALU64_REG(BPF_MUL, BPF_REG_0, BPF_REG_1), + BPF_JMP_REG(BPF_JEQ, BPF_REG_0, BPF_REG_2, 2), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + BPF_LD_IMM64(BPF_REG_3, 0xfefefeULL), + BPF_ALU64_REG(BPF_MUL, BPF_REG_3, BPF_REG_1), + BPF_JMP_REG(BPF_JEQ, BPF_REG_3, BPF_REG_2, 2), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + BPF_MOV32_REG(BPF_REG_2, BPF_REG_2), + BPF_LD_IMM64(BPF_REG_0, 0xfefefeULL), + BPF_ALU32_REG(BPF_MUL, BPF_REG_0, BPF_REG_1), + BPF_JMP_REG(BPF_JEQ, BPF_REG_0, BPF_REG_2, 2), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + BPF_LD_IMM64(BPF_REG_3, 0xfefefeULL), + BPF_ALU32_REG(BPF_MUL, BPF_REG_3, BPF_REG_1), + BPF_JMP_REG(BPF_JEQ, BPF_REG_3, BPF_REG_2, 2), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + BPF_LD_IMM64(BPF_REG_0, 0x952a7bbcULL), + BPF_LD_IMM64(BPF_REG_1, 0xfefefeULL), + BPF_LD_IMM64(BPF_REG_2, 0xeeff0d413122ULL), + BPF_ALU32_REG(BPF_MUL, BPF_REG_2, BPF_REG_1), + BPF_JMP_REG(BPF_JEQ, BPF_REG_2, BPF_REG_0, 2), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + BPF_MOV64_IMM(BPF_REG_0, 2), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .retval = 2, + }, + { "xadd/w check unaligned stack", .insns = { BPF_MOV64_IMM(BPF_REG_0, 1), @@ -11245,16 +11393,61 @@ static int create_map(uint32_t size_value, uint32_t max_elem) return fd; } +static int create_prog_dummy1(void) +{ + struct bpf_insn prog[] = { + BPF_MOV64_IMM(BPF_REG_0, 42), + BPF_EXIT_INSN(), + }; + + return bpf_load_program(BPF_PROG_TYPE_SOCKET_FILTER, prog, + ARRAY_SIZE(prog), "GPL", 0, NULL, 0); +} + +static int create_prog_dummy2(int mfd, int idx) +{ + struct bpf_insn prog[] = { + BPF_MOV64_IMM(BPF_REG_3, idx), + BPF_LD_MAP_FD(BPF_REG_2, mfd), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_tail_call), + BPF_MOV64_IMM(BPF_REG_0, 41), + BPF_EXIT_INSN(), + }; + + return bpf_load_program(BPF_PROG_TYPE_SOCKET_FILTER, prog, + ARRAY_SIZE(prog), "GPL", 0, NULL, 0); +} + static int create_prog_array(void) { - int fd; + int p1key = 0, p2key = 1; + int mfd, p1fd, p2fd; - fd = bpf_create_map(BPF_MAP_TYPE_PROG_ARRAY, sizeof(int), - sizeof(int), 4, 0); - if (fd < 0) + mfd = bpf_create_map(BPF_MAP_TYPE_PROG_ARRAY, sizeof(int), + sizeof(int), 4, 0); + if (mfd < 0) { printf("Failed to create prog array '%s'!\n", strerror(errno)); + return -1; + } - return fd; + p1fd = create_prog_dummy1(); + p2fd = create_prog_dummy2(mfd, p2key); + if (p1fd < 0 || p2fd < 0) + goto out; + if (bpf_map_update_elem(mfd, &p1key, &p1fd, BPF_ANY) < 0) + goto out; + if (bpf_map_update_elem(mfd, &p2key, &p2fd, BPF_ANY) < 0) + goto out; + close(p2fd); + close(p1fd); + + return mfd; +out: + close(p2fd); + close(p1fd); + close(mfd); + return -1; } static int create_map_in_map(void) @@ -11375,7 +11568,8 @@ static void do_test_single(struct bpf_test *test, bool unpriv, goto fail_log; } if (!strstr(bpf_vlog, expected_err) && !reject_from_alignment) { - printf("FAIL\nUnexpected error message!\n"); + printf("FAIL\nUnexpected error message!\n\tEXP: %s\n\tRES: %s\n", + expected_err, bpf_vlog); goto fail_log; } } @@ -11459,9 +11653,20 @@ out: return ret; } +static void get_unpriv_disabled() +{ + char buf[2]; + FILE *fd; + + fd = fopen("/proc/sys/"UNPRIV_SYSCTL, "r"); + if (fgets(buf, 2, fd) == buf && atoi(buf)) + unpriv_disabled = true; + fclose(fd); +} + static int do_test(bool unpriv, unsigned int from, unsigned int to) { - int i, passes = 0, errors = 0; + int i, passes = 0, errors = 0, skips = 0; for (i = from; i < to; i++) { struct bpf_test *test = &tests[i]; @@ -11469,7 +11674,10 @@ static int do_test(bool unpriv, unsigned int from, unsigned int to) /* Program types that are not supported by non-root we * skip right away. */ - if (!test->prog_type) { + if (!test->prog_type && unpriv_disabled) { + printf("#%d/u %s SKIP\n", i, test->descr); + skips++; + } else if (!test->prog_type) { if (!unpriv) set_admin(false); printf("#%d/u %s ", i, test->descr); @@ -11478,20 +11686,22 @@ static int do_test(bool unpriv, unsigned int from, unsigned int to) set_admin(true); } - if (!unpriv) { + if (unpriv) { + printf("#%d/p %s SKIP\n", i, test->descr); + skips++; + } else { printf("#%d/p %s ", i, test->descr); do_test_single(test, false, &passes, &errors); } } - printf("Summary: %d PASSED, %d FAILED\n", passes, errors); + printf("Summary: %d PASSED, %d SKIPPED, %d FAILED\n", passes, + skips, errors); return errors ? EXIT_FAILURE : EXIT_SUCCESS; } int main(int argc, char **argv) { - struct rlimit rinf = { RLIM_INFINITY, RLIM_INFINITY }; - struct rlimit rlim = { 1 << 20, 1 << 20 }; unsigned int from = 0, to = ARRAY_SIZE(tests); bool unpriv = !is_admin(); @@ -11512,6 +11722,12 @@ int main(int argc, char **argv) } } - setrlimit(RLIMIT_MEMLOCK, unpriv ? &rlim : &rinf); + get_unpriv_disabled(); + if (unpriv && unpriv_disabled) { + printf("Cannot run as unprivileged user with sysctl %s.\n", + UNPRIV_SYSCTL); + return EXIT_FAILURE; + } + return do_test(unpriv, from, to); } diff --git a/tools/testing/selftests/bpf/test_verifier_log.c b/tools/testing/selftests/bpf/test_verifier_log.c index e9626cf5607a..8d6918c3b4a2 100644 --- a/tools/testing/selftests/bpf/test_verifier_log.c +++ b/tools/testing/selftests/bpf/test_verifier_log.c @@ -4,7 +4,6 @@ #include <string.h> #include <unistd.h> #include <sys/time.h> -#include <sys/resource.h> #include <linux/bpf.h> #include <linux/filter.h> @@ -12,6 +11,8 @@ #include <bpf/bpf.h> +#include "bpf_rlimit.h" + #define LOG_SIZE (1 << 20) #define err(str...) printf("ERROR: " str) @@ -133,16 +134,11 @@ static void test_log_bad(char *log, size_t log_len, int log_level) int main(int argc, char **argv) { - struct rlimit limit = { RLIM_INFINITY, RLIM_INFINITY }; char full_log[LOG_SIZE]; char log[LOG_SIZE]; size_t want_len; int i; - /* allow unlimited locked memory to have more consistent error code */ - if (setrlimit(RLIMIT_MEMLOCK, &limit) < 0) - perror("Unable to lift memlock rlimit"); - memset(log, 1, LOG_SIZE); /* Test incorrect attr */ diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index d7c30d366935..229a038966e3 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -5,7 +5,7 @@ CFLAGS = -Wall -Wl,--no-as-needed -O2 -g CFLAGS += -I../../../../usr/include/ TEST_PROGS := run_netsocktests run_afpackettests test_bpf.sh netdevice.sh rtnetlink.sh -TEST_PROGS += fib_tests.sh +TEST_PROGS += fib_tests.sh fib-onlink-tests.sh TEST_GEN_FILES = socket TEST_GEN_FILES += psock_fanout psock_tpacket msg_zerocopy TEST_GEN_PROGS = reuseport_bpf reuseport_bpf_cpu reuseport_bpf_numa diff --git a/tools/testing/selftests/net/fib-onlink-tests.sh b/tools/testing/selftests/net/fib-onlink-tests.sh new file mode 100755 index 000000000000..06b1d7cc12cc --- /dev/null +++ b/tools/testing/selftests/net/fib-onlink-tests.sh @@ -0,0 +1,375 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# IPv4 and IPv6 onlink tests + +PAUSE_ON_FAIL=${PAUSE_ON_FAIL:=no} + +# Network interfaces +# - odd in current namespace; even in peer ns +declare -A NETIFS +# default VRF +NETIFS[p1]=veth1 +NETIFS[p2]=veth2 +NETIFS[p3]=veth3 +NETIFS[p4]=veth4 +# VRF +NETIFS[p5]=veth5 +NETIFS[p6]=veth6 +NETIFS[p7]=veth7 +NETIFS[p8]=veth8 + +# /24 network +declare -A V4ADDRS +V4ADDRS[p1]=169.254.1.1 +V4ADDRS[p2]=169.254.1.2 +V4ADDRS[p3]=169.254.3.1 +V4ADDRS[p4]=169.254.3.2 +V4ADDRS[p5]=169.254.5.1 +V4ADDRS[p6]=169.254.5.2 +V4ADDRS[p7]=169.254.7.1 +V4ADDRS[p8]=169.254.7.2 + +# /64 network +declare -A V6ADDRS +V6ADDRS[p1]=2001:db8:101::1 +V6ADDRS[p2]=2001:db8:101::2 +V6ADDRS[p3]=2001:db8:301::1 +V6ADDRS[p4]=2001:db8:301::2 +V6ADDRS[p5]=2001:db8:501::1 +V6ADDRS[p6]=2001:db8:501::2 +V6ADDRS[p7]=2001:db8:701::1 +V6ADDRS[p8]=2001:db8:701::2 + +# Test networks: +# [1] = default table +# [2] = VRF +# +# /32 host routes +declare -A TEST_NET4 +TEST_NET4[1]=169.254.101 +TEST_NET4[2]=169.254.102 +# /128 host routes +declare -A TEST_NET6 +TEST_NET6[1]=2001:db8:101 +TEST_NET6[2]=2001:db8:102 + +# connected gateway +CONGW[1]=169.254.1.254 +CONGW[2]=169.254.5.254 + +# recursive gateway +RECGW4[1]=169.254.11.254 +RECGW4[2]=169.254.12.254 +RECGW6[1]=2001:db8:11::64 +RECGW6[2]=2001:db8:12::64 + +# for v4 mapped to v6 +declare -A TEST_NET4IN6IN6 +TEST_NET4IN6[1]=10.1.1.254 +TEST_NET4IN6[2]=10.2.1.254 + +# mcast address +MCAST6=ff02::1 + + +PEER_NS=bart +PEER_CMD="ip netns exec ${PEER_NS}" +VRF=lisa +VRF_TABLE=1101 +PBR_TABLE=101 + +################################################################################ +# utilities + +log_test() +{ + local rc=$1 + local expected=$2 + local msg="$3" + + if [ ${rc} -eq ${expected} ]; then + nsuccess=$((nsuccess+1)) + printf "\n TEST: %-50s [ OK ]\n" "${msg}" + else + nfail=$((nfail+1)) + printf "\n TEST: %-50s [FAIL]\n" "${msg}" + if [ "${PAUSE_ON_FAIL}" = "yes" ]; then + echo + echo "hit enter to continue, 'q' to quit" + read a + [ "$a" = "q" ] && exit 1 + fi + fi +} + +log_section() +{ + echo + echo "######################################################################" + echo "TEST SECTION: $*" + echo "######################################################################" +} + +log_subsection() +{ + echo + echo "#########################################" + echo "TEST SUBSECTION: $*" +} + +run_cmd() +{ + echo + echo "COMMAND: $*" + eval $* +} + +get_linklocal() +{ + local dev=$1 + local pfx + local addr + + addr=$(${pfx} ip -6 -br addr show dev ${dev} | \ + awk '{ + for (i = 3; i <= NF; ++i) { + if ($i ~ /^fe80/) + print $i + } + }' + ) + addr=${addr/\/*} + + [ -z "$addr" ] && return 1 + + echo $addr + + return 0 +} + +################################################################################ +# + +setup() +{ + echo + echo "########################################" + echo "Configuring interfaces" + + set -e + + # create namespace + ip netns add ${PEER_NS} + ip -netns ${PEER_NS} li set lo up + + # add vrf table + ip li add ${VRF} type vrf table ${VRF_TABLE} + ip li set ${VRF} up + ip ro add table ${VRF_TABLE} unreachable default + ip -6 ro add table ${VRF_TABLE} unreachable default + + # create test interfaces + ip li add ${NETIFS[p1]} type veth peer name ${NETIFS[p2]} + ip li add ${NETIFS[p3]} type veth peer name ${NETIFS[p4]} + ip li add ${NETIFS[p5]} type veth peer name ${NETIFS[p6]} + ip li add ${NETIFS[p7]} type veth peer name ${NETIFS[p8]} + + # enslave vrf interfaces + for n in 5 7; do + ip li set ${NETIFS[p${n}]} vrf ${VRF} + done + + # add addresses + for n in 1 3 5 7; do + ip li set ${NETIFS[p${n}]} up + ip addr add ${V4ADDRS[p${n}]}/24 dev ${NETIFS[p${n}]} + ip addr add ${V6ADDRS[p${n}]}/64 dev ${NETIFS[p${n}]} + done + + # move peer interfaces to namespace and add addresses + for n in 2 4 6 8; do + ip li set ${NETIFS[p${n}]} netns ${PEER_NS} up + ip -netns ${PEER_NS} addr add ${V4ADDRS[p${n}]}/24 dev ${NETIFS[p${n}]} + ip -netns ${PEER_NS} addr add ${V6ADDRS[p${n}]}/64 dev ${NETIFS[p${n}]} + done + + set +e + + # let DAD complete - assume default of 1 probe + sleep 1 +} + +cleanup() +{ + # make sure we start from a clean slate + ip netns del ${PEER_NS} 2>/dev/null + for n in 1 3 5 7; do + ip link del ${NETIFS[p${n}]} 2>/dev/null + done + ip link del ${VRF} 2>/dev/null + ip ro flush table ${VRF_TABLE} + ip -6 ro flush table ${VRF_TABLE} +} + +################################################################################ +# IPv4 tests +# + +run_ip() +{ + local table="$1" + local prefix="$2" + local gw="$3" + local dev="$4" + local exp_rc="$5" + local desc="$6" + + # dev arg may be empty + [ -n "${dev}" ] && dev="dev ${dev}" + + run_cmd ip ro add table "${table}" "${prefix}"/32 via "${gw}" "${dev}" onlink + log_test $? ${exp_rc} "${desc}" +} + +valid_onlink_ipv4() +{ + # - unicast connected, unicast recursive + # + log_subsection "default VRF - main table" + + run_ip 254 ${TEST_NET4[1]}.1 ${CONGW[1]} ${NETIFS[p1]} 0 "unicast connected" + run_ip 254 ${TEST_NET4[1]}.2 ${RECGW4[1]} ${NETIFS[p1]} 0 "unicast recursive" + + log_subsection "VRF ${VRF}" + + run_ip ${VRF_TABLE} ${TEST_NET4[2]}.1 ${CONGW[2]} ${NETIFS[p5]} 0 "unicast connected" + run_ip ${VRF_TABLE} ${TEST_NET4[2]}.2 ${RECGW4[2]} ${NETIFS[p5]} 0 "unicast recursive" + + log_subsection "VRF device, PBR table" + + run_ip ${PBR_TABLE} ${TEST_NET4[2]}.3 ${CONGW[2]} ${NETIFS[p5]} 0 "unicast connected" + run_ip ${PBR_TABLE} ${TEST_NET4[2]}.4 ${RECGW4[2]} ${NETIFS[p5]} 0 "unicast recursive" +} + +invalid_onlink_ipv4() +{ + run_ip 254 ${TEST_NET4[1]}.11 ${V4ADDRS[p1]} ${NETIFS[p1]} 2 \ + "Invalid gw - local unicast address" + + run_ip ${VRF_TABLE} ${TEST_NET4[2]}.11 ${V4ADDRS[p5]} ${NETIFS[p5]} 2 \ + "Invalid gw - local unicast address, VRF" + + run_ip 254 ${TEST_NET4[1]}.101 ${V4ADDRS[p1]} "" 2 "No nexthop device given" + + run_ip 254 ${TEST_NET4[1]}.102 ${V4ADDRS[p3]} ${NETIFS[p1]} 2 \ + "Gateway resolves to wrong nexthop device" + + run_ip ${VRF_TABLE} ${TEST_NET4[2]}.103 ${V4ADDRS[p7]} ${NETIFS[p5]} 2 \ + "Gateway resolves to wrong nexthop device - VRF" +} + +################################################################################ +# IPv6 tests +# + +run_ip6() +{ + local table="$1" + local prefix="$2" + local gw="$3" + local dev="$4" + local exp_rc="$5" + local desc="$6" + + # dev arg may be empty + [ -n "${dev}" ] && dev="dev ${dev}" + + run_cmd ip -6 ro add table "${table}" "${prefix}"/128 via "${gw}" "${dev}" onlink + log_test $? ${exp_rc} "${desc}" +} + +valid_onlink_ipv6() +{ + # - unicast connected, unicast recursive, v4-mapped + # + log_subsection "default VRF - main table" + + run_ip6 254 ${TEST_NET6[1]}::1 ${V6ADDRS[p1]/::*}::64 ${NETIFS[p1]} 0 "unicast connected" + run_ip6 254 ${TEST_NET6[1]}::2 ${RECGW6[1]} ${NETIFS[p1]} 0 "unicast recursive" + run_ip6 254 ${TEST_NET6[1]}::3 ::ffff:${TEST_NET4IN6[1]} ${NETIFS[p1]} 0 "v4-mapped" + + log_subsection "VRF ${VRF}" + + run_ip6 ${VRF_TABLE} ${TEST_NET6[2]}::1 ${V6ADDRS[p5]/::*}::64 ${NETIFS[p5]} 0 "unicast connected" + run_ip6 ${VRF_TABLE} ${TEST_NET6[2]}::2 ${RECGW6[2]} ${NETIFS[p5]} 0 "unicast recursive" + run_ip6 ${VRF_TABLE} ${TEST_NET6[2]}::3 ::ffff:${TEST_NET4IN6[2]} ${NETIFS[p5]} 0 "v4-mapped" + + log_subsection "VRF device, PBR table" + + run_ip6 ${PBR_TABLE} ${TEST_NET6[2]}::4 ${V6ADDRS[p5]/::*}::64 ${NETIFS[p5]} 0 "unicast connected" + run_ip6 ${PBR_TABLE} ${TEST_NET6[2]}::5 ${RECGW6[2]} ${NETIFS[p5]} 0 "unicast recursive" + run_ip6 ${PBR_TABLE} ${TEST_NET6[2]}::6 ::ffff:${TEST_NET4IN6[2]} ${NETIFS[p5]} 0 "v4-mapped" +} + +invalid_onlink_ipv6() +{ + local lladdr + + lladdr=$(get_linklocal ${NETIFS[p1]}) || return 1 + + run_ip6 254 ${TEST_NET6[1]}::11 ${V6ADDRS[p1]} ${NETIFS[p1]} 2 \ + "Invalid gw - local unicast address" + run_ip6 254 ${TEST_NET6[1]}::12 ${lladdr} ${NETIFS[p1]} 2 \ + "Invalid gw - local linklocal address" + run_ip6 254 ${TEST_NET6[1]}::12 ${MCAST6} ${NETIFS[p1]} 2 \ + "Invalid gw - multicast address" + + lladdr=$(get_linklocal ${NETIFS[p5]}) || return 1 + run_ip6 ${VRF_TABLE} ${TEST_NET6[2]}::11 ${V6ADDRS[p5]} ${NETIFS[p5]} 2 \ + "Invalid gw - local unicast address, VRF" + run_ip6 ${VRF_TABLE} ${TEST_NET6[2]}::12 ${lladdr} ${NETIFS[p5]} 2 \ + "Invalid gw - local linklocal address, VRF" + run_ip6 ${VRF_TABLE} ${TEST_NET6[2]}::12 ${MCAST6} ${NETIFS[p5]} 2 \ + "Invalid gw - multicast address, VRF" + + run_ip6 254 ${TEST_NET6[1]}::101 ${V6ADDRS[p1]} "" 2 \ + "No nexthop device given" + + # default VRF validation is done against LOCAL table + # run_ip6 254 ${TEST_NET6[1]}::102 ${V6ADDRS[p3]/::[0-9]/::64} ${NETIFS[p1]} 2 \ + # "Gateway resolves to wrong nexthop device" + + run_ip6 ${VRF_TABLE} ${TEST_NET6[2]}::103 ${V6ADDRS[p7]/::[0-9]/::64} ${NETIFS[p5]} 2 \ + "Gateway resolves to wrong nexthop device - VRF" +} + +run_onlink_tests() +{ + log_section "IPv4 onlink" + log_subsection "Valid onlink commands" + valid_onlink_ipv4 + log_subsection "Invalid onlink commands" + invalid_onlink_ipv4 + + log_section "IPv6 onlink" + log_subsection "Valid onlink commands" + valid_onlink_ipv6 + invalid_onlink_ipv6 +} + +################################################################################ +# main + +nsuccess=0 +nfail=0 + +cleanup +setup +run_onlink_tests +cleanup + +if [ "$TESTS" != "none" ]; then + printf "\nTests passed: %3d\n" ${nsuccess} + printf "Tests failed: %3d\n" ${nfail} +fi diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh index a9154eefb2e2..b617985ecdc1 100755 --- a/tools/testing/selftests/net/fib_tests.sh +++ b/tools/testing/selftests/net/fib_tests.sh @@ -6,154 +6,155 @@ ret=0 -check_err() -{ - if [ $ret -eq 0 ]; then - ret=$1 - fi -} +PAUSE_ON_FAIL=${PAUSE_ON_FAIL:=no} -check_fail() +log_test() { - if [ $1 -eq 0 ]; then + local rc=$1 + local expected=$2 + local msg="$3" + + if [ ${rc} -eq ${expected} ]; then + printf " %-60s [ OK ]\n" "${msg}" + else ret=1 + printf " %-60s [FAIL]\n" "${msg}" + if [ "${PAUSE_ON_FAIL}" = "yes" ]; then + echo + echo "hit enter to continue, 'q' to quit" + read a + [ "$a" = "q" ] && exit 1 + fi fi } -netns_create() +setup() { - local testns=$1 + set -e + ip netns add testns + ip -netns testns link set dev lo up + + ip -netns testns link add dummy0 type dummy + ip -netns testns link set dev dummy0 up + ip -netns testns address add 198.51.100.1/24 dev dummy0 + ip -netns testns -6 address add 2001:db8:1::1/64 dev dummy0 + set +e - ip netns add $testns - ip netns exec $testns ip link set dev lo up } -fib_unreg_unicast_test() +cleanup() { - ret=0 - - netns_create "testns" - - ip netns exec testns ip link add dummy0 type dummy - ip netns exec testns ip link set dev dummy0 up + ip -netns testns link del dev dummy0 &> /dev/null + ip netns del testns +} - ip netns exec testns ip address add 198.51.100.1/24 dev dummy0 - ip netns exec testns ip -6 address add 2001:db8:1::1/64 dev dummy0 +fib_unreg_unicast_test() +{ + echo + echo "Single path route test" - ip netns exec testns ip route get fibmatch 198.51.100.2 &> /dev/null - check_err $? - ip netns exec testns ip -6 route get fibmatch 2001:db8:1::2 &> /dev/null - check_err $? + setup - ip netns exec testns ip link del dev dummy0 - check_err $? + echo " Start point" + ip -netns testns route get fibmatch 198.51.100.2 &> /dev/null + log_test $? 0 "IPv4 fibmatch" + ip -netns testns -6 route get fibmatch 2001:db8:1::2 &> /dev/null + log_test $? 0 "IPv6 fibmatch" - ip netns exec testns ip route get fibmatch 198.51.100.2 &> /dev/null - check_fail $? - ip netns exec testns ip -6 route get fibmatch 2001:db8:1::2 &> /dev/null - check_fail $? + set -e + ip -netns testns link del dev dummy0 + set +e - ip netns del testns + echo " Nexthop device deleted" + ip -netns testns route get fibmatch 198.51.100.2 &> /dev/null + log_test $? 2 "IPv4 fibmatch - no route" + ip -netns testns -6 route get fibmatch 2001:db8:1::2 &> /dev/null + log_test $? 2 "IPv6 fibmatch - no route" - if [ $ret -ne 0 ]; then - echo "FAIL: unicast route test" - return 1 - fi - echo "PASS: unicast route test" + cleanup } fib_unreg_multipath_test() { - ret=0 - - netns_create "testns" - ip netns exec testns ip link add dummy0 type dummy - ip netns exec testns ip link set dev dummy0 up + echo + echo "Multipath route test" - ip netns exec testns ip link add dummy1 type dummy - ip netns exec testns ip link set dev dummy1 up + setup - ip netns exec testns ip address add 198.51.100.1/24 dev dummy0 - ip netns exec testns ip -6 address add 2001:db8:1::1/64 dev dummy0 + set -e + ip -netns testns link add dummy1 type dummy + ip -netns testns link set dev dummy1 up + ip -netns testns address add 192.0.2.1/24 dev dummy1 + ip -netns testns -6 address add 2001:db8:2::1/64 dev dummy1 - ip netns exec testns ip address add 192.0.2.1/24 dev dummy1 - ip netns exec testns ip -6 address add 2001:db8:2::1/64 dev dummy1 - - ip netns exec testns ip route add 203.0.113.0/24 \ + ip -netns testns route add 203.0.113.0/24 \ nexthop via 198.51.100.2 dev dummy0 \ nexthop via 192.0.2.2 dev dummy1 - ip netns exec testns ip -6 route add 2001:db8:3::/64 \ + ip -netns testns -6 route add 2001:db8:3::/64 \ nexthop via 2001:db8:1::2 dev dummy0 \ nexthop via 2001:db8:2::2 dev dummy1 + set +e + + echo " Start point" + ip -netns testns route get fibmatch 203.0.113.1 &> /dev/null + log_test $? 0 "IPv4 fibmatch" + ip -netns testns -6 route get fibmatch 2001:db8:3::1 &> /dev/null + log_test $? 0 "IPv6 fibmatch" - ip netns exec testns ip route get fibmatch 203.0.113.1 &> /dev/null - check_err $? - ip netns exec testns ip -6 route get fibmatch 2001:db8:3::1 &> /dev/null - check_err $? + set -e + ip -netns testns link del dev dummy0 + set +e - ip netns exec testns ip link del dev dummy0 - check_err $? + echo " One nexthop device deleted" + ip -netns testns route get fibmatch 203.0.113.1 &> /dev/null + log_test $? 2 "IPv4 - multipath route removed on delete" - ip netns exec testns ip route get fibmatch 203.0.113.1 &> /dev/null - check_fail $? - ip netns exec testns ip -6 route get fibmatch 2001:db8:3::1 &> /dev/null + ip -netns testns -6 route get fibmatch 2001:db8:3::1 &> /dev/null # In IPv6 we do not flush the entire multipath route. - check_err $? + log_test $? 0 "IPv6 - multipath down to single path" - ip netns exec testns ip link del dev dummy1 + set -e + ip -netns testns link del dev dummy1 + set +e - ip netns del testns + echo " Second nexthop device deleted" + ip -netns testns -6 route get fibmatch 2001:db8:3::1 &> /dev/null + log_test $? 2 "IPv6 - no route" - if [ $ret -ne 0 ]; then - echo "FAIL: multipath route test" - return 1 - fi - echo "PASS: multipath route test" + cleanup } fib_unreg_test() { - echo "Running netdev unregister tests" - fib_unreg_unicast_test fib_unreg_multipath_test } fib_down_unicast_test() { - ret=0 - - netns_create "testns" - - ip netns exec testns ip link add dummy0 type dummy - ip netns exec testns ip link set dev dummy0 up - - ip netns exec testns ip address add 198.51.100.1/24 dev dummy0 - ip netns exec testns ip -6 address add 2001:db8:1::1/64 dev dummy0 + echo + echo "Single path, admin down" - ip netns exec testns ip route get fibmatch 198.51.100.2 &> /dev/null - check_err $? - ip netns exec testns ip -6 route get fibmatch 2001:db8:1::2 &> /dev/null - check_err $? + setup - ip netns exec testns ip link set dev dummy0 down - check_err $? + echo " Start point" + ip -netns testns route get fibmatch 198.51.100.2 &> /dev/null + log_test $? 0 "IPv4 fibmatch" + ip -netns testns -6 route get fibmatch 2001:db8:1::2 &> /dev/null + log_test $? 0 "IPv6 fibmatch" - ip netns exec testns ip route get fibmatch 198.51.100.2 &> /dev/null - check_fail $? - ip netns exec testns ip -6 route get fibmatch 2001:db8:1::2 &> /dev/null - check_fail $? + set -e + ip -netns testns link set dev dummy0 down + set +e - ip netns exec testns ip link del dev dummy0 + echo " Route deleted on down" + ip -netns testns route get fibmatch 198.51.100.2 &> /dev/null + log_test $? 2 "IPv4 fibmatch" + ip -netns testns -6 route get fibmatch 2001:db8:1::2 &> /dev/null + log_test $? 2 "IPv6 fibmatch" - ip netns del testns - - if [ $ret -ne 0 ]; then - echo "FAIL: unicast route test" - return 1 - fi - echo "PASS: unicast route test" + cleanup } fib_down_multipath_test_do() @@ -161,242 +162,229 @@ fib_down_multipath_test_do() local down_dev=$1 local up_dev=$2 - ip netns exec testns ip route get fibmatch 203.0.113.1 \ + ip -netns testns route get fibmatch 203.0.113.1 \ oif $down_dev &> /dev/null - check_fail $? - ip netns exec testns ip -6 route get fibmatch 2001:db8:3::1 \ + log_test $? 2 "IPv4 fibmatch on down device" + ip -netns testns -6 route get fibmatch 2001:db8:3::1 \ oif $down_dev &> /dev/null - check_fail $? + log_test $? 2 "IPv6 fibmatch on down device" - ip netns exec testns ip route get fibmatch 203.0.113.1 \ + ip -netns testns route get fibmatch 203.0.113.1 \ oif $up_dev &> /dev/null - check_err $? - ip netns exec testns ip -6 route get fibmatch 2001:db8:3::1 \ + log_test $? 0 "IPv4 fibmatch on up device" + ip -netns testns -6 route get fibmatch 2001:db8:3::1 \ oif $up_dev &> /dev/null - check_err $? + log_test $? 0 "IPv6 fibmatch on up device" - ip netns exec testns ip route get fibmatch 203.0.113.1 | \ + ip -netns testns route get fibmatch 203.0.113.1 | \ grep $down_dev | grep -q "dead linkdown" - check_err $? - ip netns exec testns ip -6 route get fibmatch 2001:db8:3::1 | \ + log_test $? 0 "IPv4 flags on down device" + ip -netns testns -6 route get fibmatch 2001:db8:3::1 | \ grep $down_dev | grep -q "dead linkdown" - check_err $? + log_test $? 0 "IPv6 flags on down device" - ip netns exec testns ip route get fibmatch 203.0.113.1 | \ + ip -netns testns route get fibmatch 203.0.113.1 | \ grep $up_dev | grep -q "dead linkdown" - check_fail $? - ip netns exec testns ip -6 route get fibmatch 2001:db8:3::1 | \ + log_test $? 1 "IPv4 flags on up device" + ip -netns testns -6 route get fibmatch 2001:db8:3::1 | \ grep $up_dev | grep -q "dead linkdown" - check_fail $? + log_test $? 1 "IPv6 flags on up device" } fib_down_multipath_test() { - ret=0 + echo + echo "Admin down multipath" - netns_create "testns" + setup - ip netns exec testns ip link add dummy0 type dummy - ip netns exec testns ip link set dev dummy0 up + set -e + ip -netns testns link add dummy1 type dummy + ip -netns testns link set dev dummy1 up - ip netns exec testns ip link add dummy1 type dummy - ip netns exec testns ip link set dev dummy1 up + ip -netns testns address add 192.0.2.1/24 dev dummy1 + ip -netns testns -6 address add 2001:db8:2::1/64 dev dummy1 - ip netns exec testns ip address add 198.51.100.1/24 dev dummy0 - ip netns exec testns ip -6 address add 2001:db8:1::1/64 dev dummy0 - - ip netns exec testns ip address add 192.0.2.1/24 dev dummy1 - ip netns exec testns ip -6 address add 2001:db8:2::1/64 dev dummy1 - - ip netns exec testns ip route add 203.0.113.0/24 \ + ip -netns testns route add 203.0.113.0/24 \ nexthop via 198.51.100.2 dev dummy0 \ nexthop via 192.0.2.2 dev dummy1 - ip netns exec testns ip -6 route add 2001:db8:3::/64 \ + ip -netns testns -6 route add 2001:db8:3::/64 \ nexthop via 2001:db8:1::2 dev dummy0 \ nexthop via 2001:db8:2::2 dev dummy1 + set +e + + echo " Verify start point" + ip -netns testns route get fibmatch 203.0.113.1 &> /dev/null + log_test $? 0 "IPv4 fibmatch" - ip netns exec testns ip route get fibmatch 203.0.113.1 &> /dev/null - check_err $? - ip netns exec testns ip -6 route get fibmatch 2001:db8:3::1 &> /dev/null - check_err $? + ip -netns testns -6 route get fibmatch 2001:db8:3::1 &> /dev/null + log_test $? 0 "IPv6 fibmatch" - ip netns exec testns ip link set dev dummy0 down - check_err $? + set -e + ip -netns testns link set dev dummy0 down + set +e + echo " One device down, one up" fib_down_multipath_test_do "dummy0" "dummy1" - ip netns exec testns ip link set dev dummy0 up - check_err $? - ip netns exec testns ip link set dev dummy1 down - check_err $? + set -e + ip -netns testns link set dev dummy0 up + ip -netns testns link set dev dummy1 down + set +e + echo " Other device down and up" fib_down_multipath_test_do "dummy1" "dummy0" - ip netns exec testns ip link set dev dummy0 down - check_err $? + set -e + ip -netns testns link set dev dummy0 down + set +e - ip netns exec testns ip route get fibmatch 203.0.113.1 &> /dev/null - check_fail $? - ip netns exec testns ip -6 route get fibmatch 2001:db8:3::1 &> /dev/null - check_fail $? + echo " Both devices down" + ip -netns testns route get fibmatch 203.0.113.1 &> /dev/null + log_test $? 2 "IPv4 fibmatch" + ip -netns testns -6 route get fibmatch 2001:db8:3::1 &> /dev/null + log_test $? 2 "IPv6 fibmatch" - ip netns exec testns ip link del dev dummy1 - ip netns exec testns ip link del dev dummy0 - - ip netns del testns - - if [ $ret -ne 0 ]; then - echo "FAIL: multipath route test" - return 1 - fi - echo "PASS: multipath route test" + ip -netns testns link del dev dummy1 + cleanup } fib_down_test() { - echo "Running netdev down tests" - fib_down_unicast_test fib_down_multipath_test } +# Local routes should not be affected when carrier changes. fib_carrier_local_test() { - ret=0 + echo + echo "Local carrier tests - single path" - # Local routes should not be affected when carrier changes. - netns_create "testns" + setup - ip netns exec testns ip link add dummy0 type dummy - ip netns exec testns ip link set dev dummy0 up + set -e + ip -netns testns link set dev dummy0 carrier on + set +e - ip netns exec testns ip link set dev dummy0 carrier on + echo " Start point" + ip -netns testns route get fibmatch 198.51.100.1 &> /dev/null + log_test $? 0 "IPv4 fibmatch" + ip -netns testns -6 route get fibmatch 2001:db8:1::1 &> /dev/null + log_test $? 0 "IPv6 fibmatch" - ip netns exec testns ip address add 198.51.100.1/24 dev dummy0 - ip netns exec testns ip -6 address add 2001:db8:1::1/64 dev dummy0 - - ip netns exec testns ip route get fibmatch 198.51.100.1 &> /dev/null - check_err $? - ip netns exec testns ip -6 route get fibmatch 2001:db8:1::1 &> /dev/null - check_err $? - - ip netns exec testns ip route get fibmatch 198.51.100.1 | \ + ip -netns testns route get fibmatch 198.51.100.1 | \ grep -q "linkdown" - check_fail $? - ip netns exec testns ip -6 route get fibmatch 2001:db8:1::1 | \ + log_test $? 1 "IPv4 - no linkdown flag" + ip -netns testns -6 route get fibmatch 2001:db8:1::1 | \ grep -q "linkdown" - check_fail $? + log_test $? 1 "IPv6 - no linkdown flag" - ip netns exec testns ip link set dev dummy0 carrier off + set -e + ip -netns testns link set dev dummy0 carrier off + sleep 1 + set +e - ip netns exec testns ip route get fibmatch 198.51.100.1 &> /dev/null - check_err $? - ip netns exec testns ip -6 route get fibmatch 2001:db8:1::1 &> /dev/null - check_err $? + echo " Carrier off on nexthop" + ip -netns testns route get fibmatch 198.51.100.1 &> /dev/null + log_test $? 0 "IPv4 fibmatch" + ip -netns testns -6 route get fibmatch 2001:db8:1::1 &> /dev/null + log_test $? 0 "IPv6 fibmatch" - ip netns exec testns ip route get fibmatch 198.51.100.1 | \ + ip -netns testns route get fibmatch 198.51.100.1 | \ grep -q "linkdown" - check_fail $? - ip netns exec testns ip -6 route get fibmatch 2001:db8:1::1 | \ + log_test $? 1 "IPv4 - linkdown flag set" + ip -netns testns -6 route get fibmatch 2001:db8:1::1 | \ grep -q "linkdown" - check_fail $? + log_test $? 1 "IPv6 - linkdown flag set" - ip netns exec testns ip address add 192.0.2.1/24 dev dummy0 - ip netns exec testns ip -6 address add 2001:db8:2::1/64 dev dummy0 + set -e + ip -netns testns address add 192.0.2.1/24 dev dummy0 + ip -netns testns -6 address add 2001:db8:2::1/64 dev dummy0 + set +e - ip netns exec testns ip route get fibmatch 192.0.2.1 &> /dev/null - check_err $? - ip netns exec testns ip -6 route get fibmatch 2001:db8:2::1 &> /dev/null - check_err $? + echo " Route to local address with carrier down" + ip -netns testns route get fibmatch 192.0.2.1 &> /dev/null + log_test $? 0 "IPv4 fibmatch" + ip -netns testns -6 route get fibmatch 2001:db8:2::1 &> /dev/null + log_test $? 0 "IPv6 fibmatch" - ip netns exec testns ip route get fibmatch 192.0.2.1 | \ + ip -netns testns route get fibmatch 192.0.2.1 | \ grep -q "linkdown" - check_fail $? - ip netns exec testns ip -6 route get fibmatch 2001:db8:2::1 | \ + log_test $? 1 "IPv4 linkdown flag set" + ip -netns testns -6 route get fibmatch 2001:db8:2::1 | \ grep -q "linkdown" - check_fail $? + log_test $? 1 "IPv6 linkdown flag set" - ip netns exec testns ip link del dev dummy0 - - ip netns del testns - - if [ $ret -ne 0 ]; then - echo "FAIL: local route carrier test" - return 1 - fi - echo "PASS: local route carrier test" + cleanup } fib_carrier_unicast_test() { ret=0 - netns_create "testns" - - ip netns exec testns ip link add dummy0 type dummy - ip netns exec testns ip link set dev dummy0 up + echo + echo "Single path route carrier test" - ip netns exec testns ip link set dev dummy0 carrier on + setup - ip netns exec testns ip address add 198.51.100.1/24 dev dummy0 - ip netns exec testns ip -6 address add 2001:db8:1::1/64 dev dummy0 + set -e + ip -netns testns link set dev dummy0 carrier on + set +e - ip netns exec testns ip route get fibmatch 198.51.100.2 &> /dev/null - check_err $? - ip netns exec testns ip -6 route get fibmatch 2001:db8:1::2 &> /dev/null - check_err $? + echo " Start point" + ip -netns testns route get fibmatch 198.51.100.2 &> /dev/null + log_test $? 0 "IPv4 fibmatch" + ip -netns testns -6 route get fibmatch 2001:db8:1::2 &> /dev/null + log_test $? 0 "IPv6 fibmatch" - ip netns exec testns ip route get fibmatch 198.51.100.2 | \ + ip -netns testns route get fibmatch 198.51.100.2 | \ grep -q "linkdown" - check_fail $? - ip netns exec testns ip -6 route get fibmatch 2001:db8:1::2 | \ + log_test $? 1 "IPv4 no linkdown flag" + ip -netns testns -6 route get fibmatch 2001:db8:1::2 | \ grep -q "linkdown" - check_fail $? + log_test $? 1 "IPv6 no linkdown flag" - ip netns exec testns ip link set dev dummy0 carrier off + set -e + ip -netns testns link set dev dummy0 carrier off + set +e - ip netns exec testns ip route get fibmatch 198.51.100.2 &> /dev/null - check_err $? - ip netns exec testns ip -6 route get fibmatch 2001:db8:1::2 &> /dev/null - check_err $? + echo " Carrier down" + ip -netns testns route get fibmatch 198.51.100.2 &> /dev/null + log_test $? 0 "IPv4 fibmatch" + ip -netns testns -6 route get fibmatch 2001:db8:1::2 &> /dev/null + log_test $? 0 "IPv6 fibmatch" - ip netns exec testns ip route get fibmatch 198.51.100.2 | \ + ip -netns testns route get fibmatch 198.51.100.2 | \ grep -q "linkdown" - check_err $? - ip netns exec testns ip -6 route get fibmatch 2001:db8:1::2 | \ + log_test $? 0 "IPv4 linkdown flag set" + ip -netns testns -6 route get fibmatch 2001:db8:1::2 | \ grep -q "linkdown" - check_err $? + log_test $? 0 "IPv6 linkdown flag set" - ip netns exec testns ip address add 192.0.2.1/24 dev dummy0 - ip netns exec testns ip -6 address add 2001:db8:2::1/64 dev dummy0 + set -e + ip -netns testns address add 192.0.2.1/24 dev dummy0 + ip -netns testns -6 address add 2001:db8:2::1/64 dev dummy0 + set +e - ip netns exec testns ip route get fibmatch 192.0.2.2 &> /dev/null - check_err $? - ip netns exec testns ip -6 route get fibmatch 2001:db8:2::2 &> /dev/null - check_err $? + echo " Second address added with carrier down" + ip -netns testns route get fibmatch 192.0.2.2 &> /dev/null + log_test $? 0 "IPv4 fibmatch" + ip -netns testns -6 route get fibmatch 2001:db8:2::2 &> /dev/null + log_test $? 0 "IPv6 fibmatch" - ip netns exec testns ip route get fibmatch 192.0.2.2 | \ + ip -netns testns route get fibmatch 192.0.2.2 | \ grep -q "linkdown" - check_err $? - ip netns exec testns ip -6 route get fibmatch 2001:db8:2::2 | \ + log_test $? 0 "IPv4 linkdown flag set" + ip -netns testns -6 route get fibmatch 2001:db8:2::2 | \ grep -q "linkdown" - check_err $? + log_test $? 0 "IPv6 linkdown flag set" - ip netns exec testns ip link del dev dummy0 - - ip netns del testns - - if [ $ret -ne 0 ]; then - echo "FAIL: unicast route carrier test" - return 1 - fi - echo "PASS: unicast route carrier test" + cleanup } fib_carrier_test() { - echo "Running netdev carrier change tests" - fib_carrier_local_test fib_carrier_unicast_test } @@ -424,6 +412,9 @@ if [ $? -ne 0 ]; then exit 0 fi +# start clean +cleanup &> /dev/null + fib_test exit $ret diff --git a/tools/testing/selftests/net/forwarding/.gitignore b/tools/testing/selftests/net/forwarding/.gitignore new file mode 100644 index 000000000000..a793eef5b876 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/.gitignore @@ -0,0 +1 @@ +forwarding.config diff --git a/tools/testing/selftests/net/forwarding/README b/tools/testing/selftests/net/forwarding/README new file mode 100644 index 000000000000..4a0964c42860 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/README @@ -0,0 +1,56 @@ +Motivation +========== + +One of the nice things about network namespaces is that they allow one +to easily create and test complex environments. + +Unfortunately, these namespaces can not be used with actual switching +ASICs, as their ports can not be migrated to other network namespaces +(NETIF_F_NETNS_LOCAL) and most of them probably do not support the +L1-separation provided by namespaces. + +However, a similar kind of flexibility can be achieved by using VRFs and +by looping the switch ports together. For example: + + br0 + + + vrf-h1 | vrf-h2 + + +---+----+ + + | | | | + 192.0.2.1/24 + + + + 192.0.2.2/24 + swp1 swp2 swp3 swp4 + + + + + + | | | | + +--------+ +--------+ + +The VRFs act as lightweight namespaces representing hosts connected to +the switch. + +This approach for testing switch ASICs has several advantages over the +traditional method that requires multiple physical machines, to name a +few: + +1. Only the device under test (DUT) is being tested without noise from +other system. + +2. Ability to easily provision complex topologies. Testing bridging +between 4-ports LAGs or 8-way ECMP requires many physical links that are +not always available. With the VRF-based approach one merely needs to +loopback more ports. + +These tests are written with switch ASICs in mind, but they can be run +on any Linux box using veth pairs to emulate physical loopbacks. + +Guidelines for Writing Tests +============================ + +o Where possible, reuse an existing topology for different tests instead + of recreating the same topology. +o Where possible, IPv6 and IPv4 addresses shall conform to RFC 3849 and + RFC 5737, respectively. +o Where possible, tests shall be written so that they can be reused by + multiple topologies and added to lib.sh. +o Checks shall be added to lib.sh for any external dependencies. +o Code shall be checked using ShellCheck [1] prior to submission. + +1. https://www.shellcheck.net/ diff --git a/tools/testing/selftests/net/forwarding/bridge_vlan_aware.sh b/tools/testing/selftests/net/forwarding/bridge_vlan_aware.sh new file mode 100755 index 000000000000..75d922438bc9 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/bridge_vlan_aware.sh @@ -0,0 +1,88 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +NUM_NETIFS=4 +CHECK_TC="yes" +source lib.sh + +h1_create() +{ + simple_if_init $h1 192.0.2.1/24 2001:db8:1::1/64 +} + +h1_destroy() +{ + simple_if_fini $h1 192.0.2.1/24 2001:db8:1::1/64 +} + +h2_create() +{ + simple_if_init $h2 192.0.2.2/24 2001:db8:1::2/64 +} + +h2_destroy() +{ + simple_if_fini $h2 192.0.2.2/24 2001:db8:1::2/64 +} + +switch_create() +{ + # 10 Seconds ageing time. + ip link add dev br0 type bridge vlan_filtering 1 ageing_time 1000 \ + mcast_snooping 0 + + ip link set dev $swp1 master br0 + ip link set dev $swp2 master br0 + + ip link set dev br0 up + ip link set dev $swp1 up + ip link set dev $swp2 up +} + +switch_destroy() +{ + ip link set dev $swp2 down + ip link set dev $swp1 down + + ip link del dev br0 +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + swp2=${NETIFS[p3]} + h2=${NETIFS[p4]} + + vrf_prepare + + h1_create + h2_create + + switch_create +} + +cleanup() +{ + pre_cleanup + + switch_destroy + + h2_destroy + h1_destroy + + vrf_cleanup +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +ping_test $h1 192.0.2.2 +ping6_test $h1 2001:db8:1::2 +learning_test "br0" $swp1 $h1 $h2 +flood_test $swp2 $h1 $h2 + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/config b/tools/testing/selftests/net/forwarding/config new file mode 100644 index 000000000000..5cd2aed97958 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/config @@ -0,0 +1,12 @@ +CONFIG_BRIDGE=m +CONFIG_VLAN_8021Q=m +CONFIG_BRIDGE_VLAN_FILTERING=y +CONFIG_NET_L3_MASTER_DEV=y +CONFIG_IPV6_MULTIPLE_TABLES=y +CONFIG_NET_VRF=m +CONFIG_BPF_SYSCALL=y +CONFIG_CGROUP_BPF=y +CONFIG_NET_CLS_FLOWER=m +CONFIG_NET_SCH_INGRESS=m +CONFIG_NET_ACT_GACT=m +CONFIG_VETH=m diff --git a/tools/testing/selftests/net/forwarding/forwarding.config.sample b/tools/testing/selftests/net/forwarding/forwarding.config.sample new file mode 100644 index 000000000000..df54c9eb5100 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/forwarding.config.sample @@ -0,0 +1,36 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +############################################################################## +# Topology description. p1 looped back to p2, p3 to p4 and so on. +declare -A NETIFS + +NETIFS[p1]=veth0 +NETIFS[p2]=veth1 +NETIFS[p3]=veth2 +NETIFS[p4]=veth3 +NETIFS[p5]=veth4 +NETIFS[p6]=veth5 +NETIFS[p7]=veth6 +NETIFS[p8]=veth7 + +NETIF_TYPE=veth + +# only virtual interfaces (veth) can be created by test infra +#NETIF_CREATE=yes + +############################################################################## +# Defines + +# IPv4 ping utility name +PING=ping +# IPv6 ping utility name. Some distributions use 'ping' for IPv6. +PING6=ping6 +# Packet generator. Some distributions use 'mz'. +MZ=mausezahn +# Time to wait after interfaces participating in the test are all UP +WAIT_TIME=5 +# Whether to pause on failure or not. +PAUSE_ON_FAIL=no +# Whether to pause on cleanup or not. +PAUSE_ON_CLEANUP=no diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh new file mode 100644 index 000000000000..273511ef2b43 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/lib.sh @@ -0,0 +1,575 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +############################################################################## +# Defines + +# Can be overridden by the configuration file. +PING=${PING:=ping} +PING6=${PING6:=ping6} +MZ=${MZ:=mausezahn} +WAIT_TIME=${WAIT_TIME:=5} +PAUSE_ON_FAIL=${PAUSE_ON_FAIL:=no} +PAUSE_ON_CLEANUP=${PAUSE_ON_CLEANUP:=no} + +if [[ -f forwarding.config ]]; then + source forwarding.config +fi + +############################################################################## +# Sanity checks + +check_tc_version() +{ + tc -j &> /dev/null + if [[ $? -ne 0 ]]; then + echo "SKIP: iproute2 too old; tc is missing JSON support" + exit 1 + fi + + tc filter help 2>&1 | grep block &> /dev/null + if [[ $? -ne 0 ]]; then + echo "SKIP: iproute2 too old; tc is missing shared block support" + exit 1 + fi +} + +if [[ "$(id -u)" -ne 0 ]]; then + echo "SKIP: need root privileges" + exit 0 +fi + +if [[ "$CHECK_TC" = "yes" ]]; then + check_tc_version +fi + +if [[ ! -x "$(command -v jq)" ]]; then + echo "SKIP: jq not installed" + exit 1 +fi + +if [[ ! -x "$(command -v $MZ)" ]]; then + echo "SKIP: $MZ not installed" + exit 0 +fi + +if [[ ! -v NUM_NETIFS ]]; then + echo "SKIP: importer does not define \"NUM_NETIFS\"" + exit 0 +fi + +############################################################################## +# Command line options handling + +count=0 + +while [[ $# -gt 0 ]]; do + if [[ "$count" -eq "0" ]]; then + unset NETIFS + declare -A NETIFS + fi + count=$((count + 1)) + NETIFS[p$count]="$1" + shift +done + +############################################################################## +# Network interfaces configuration + +create_netif_veth() +{ + local i + + for i in $(eval echo {1..$NUM_NETIFS}); do + local j=$((i+1)) + + ip link show dev ${NETIFS[p$i]} &> /dev/null + if [[ $? -ne 0 ]]; then + ip link add ${NETIFS[p$i]} type veth \ + peer name ${NETIFS[p$j]} + if [[ $? -ne 0 ]]; then + echo "Failed to create netif" + exit 1 + fi + fi + i=$j + done +} + +create_netif() +{ + case "$NETIF_TYPE" in + veth) create_netif_veth + ;; + *) echo "Can not create interfaces of type \'$NETIF_TYPE\'" + exit 1 + ;; + esac +} + +if [[ "$NETIF_CREATE" = "yes" ]]; then + create_netif +fi + +for i in $(eval echo {1..$NUM_NETIFS}); do + ip link show dev ${NETIFS[p$i]} &> /dev/null + if [[ $? -ne 0 ]]; then + echo "SKIP: could not find all required interfaces" + exit 0 + fi +done + +############################################################################## +# Helpers + +# Exit status to return at the end. Set in case one of the tests fails. +EXIT_STATUS=0 +# Per-test return value. Clear at the beginning of each test. +RET=0 + +check_err() +{ + local err=$1 + local msg=$2 + + if [[ $RET -eq 0 && $err -ne 0 ]]; then + RET=$err + retmsg=$msg + fi +} + +check_fail() +{ + local err=$1 + local msg=$2 + + if [[ $RET -eq 0 && $err -eq 0 ]]; then + RET=1 + retmsg=$msg + fi +} + +log_test() +{ + local test_name=$1 + local opt_str=$2 + + if [[ $# -eq 2 ]]; then + opt_str="($opt_str)" + fi + + if [[ $RET -ne 0 ]]; then + EXIT_STATUS=1 + printf "TEST: %-60s [FAIL]\n" "$test_name $opt_str" + if [[ ! -z "$retmsg" ]]; then + printf "\t%s\n" "$retmsg" + fi + if [ "${PAUSE_ON_FAIL}" = "yes" ]; then + echo "Hit enter to continue, 'q' to quit" + read a + [ "$a" = "q" ] && exit 1 + fi + return 1 + fi + + printf "TEST: %-60s [PASS]\n" "$test_name $opt_str" + return 0 +} + +log_info() +{ + local msg=$1 + + echo "INFO: $msg" +} + +setup_wait() +{ + for i in $(eval echo {1..$NUM_NETIFS}); do + while true; do + ip link show dev ${NETIFS[p$i]} up \ + | grep 'state UP' &> /dev/null + if [[ $? -ne 0 ]]; then + sleep 1 + else + break + fi + done + done + + # Make sure links are ready. + sleep $WAIT_TIME +} + +pre_cleanup() +{ + if [ "${PAUSE_ON_CLEANUP}" = "yes" ]; then + echo "Pausing before cleanup, hit any key to continue" + read + fi +} + +vrf_prepare() +{ + ip -4 rule add pref 32765 table local + ip -4 rule del pref 0 + ip -6 rule add pref 32765 table local + ip -6 rule del pref 0 +} + +vrf_cleanup() +{ + ip -6 rule add pref 0 table local + ip -6 rule del pref 32765 + ip -4 rule add pref 0 table local + ip -4 rule del pref 32765 +} + +__last_tb_id=0 +declare -A __TB_IDS + +__vrf_td_id_assign() +{ + local vrf_name=$1 + + __last_tb_id=$((__last_tb_id + 1)) + __TB_IDS[$vrf_name]=$__last_tb_id + return $__last_tb_id +} + +__vrf_td_id_lookup() +{ + local vrf_name=$1 + + return ${__TB_IDS[$vrf_name]} +} + +vrf_create() +{ + local vrf_name=$1 + local tb_id + + __vrf_td_id_assign $vrf_name + tb_id=$? + + ip link add dev $vrf_name type vrf table $tb_id + ip -4 route add table $tb_id unreachable default metric 4278198272 + ip -6 route add table $tb_id unreachable default metric 4278198272 +} + +vrf_destroy() +{ + local vrf_name=$1 + local tb_id + + __vrf_td_id_lookup $vrf_name + tb_id=$? + + ip -6 route del table $tb_id unreachable default metric 4278198272 + ip -4 route del table $tb_id unreachable default metric 4278198272 + ip link del dev $vrf_name +} + +__addr_add_del() +{ + local if_name=$1 + local add_del=$2 + local array + + shift + shift + array=("${@}") + + for addrstr in "${array[@]}"; do + ip address $add_del $addrstr dev $if_name + done +} + +simple_if_init() +{ + local if_name=$1 + local vrf_name + local array + + shift + vrf_name=v$if_name + array=("${@}") + + vrf_create $vrf_name + ip link set dev $if_name master $vrf_name + ip link set dev $vrf_name up + ip link set dev $if_name up + + __addr_add_del $if_name add "${array[@]}" +} + +simple_if_fini() +{ + local if_name=$1 + local vrf_name + local array + + shift + vrf_name=v$if_name + array=("${@}") + + __addr_add_del $if_name del "${array[@]}" + + ip link set dev $if_name down + vrf_destroy $vrf_name +} + +master_name_get() +{ + local if_name=$1 + + ip -j link show dev $if_name | jq -r '.[]["master"]' +} + +link_stats_tx_packets_get() +{ + local if_name=$1 + + ip -j -s link show dev $if_name | jq '.[]["stats64"]["tx"]["packets"]' +} + +mac_get() +{ + local if_name=$1 + + ip -j link show dev $if_name | jq -r '.[]["address"]' +} + +bridge_ageing_time_get() +{ + local bridge=$1 + local ageing_time + + # Need to divide by 100 to convert to seconds. + ageing_time=$(ip -j -d link show dev $bridge \ + | jq '.[]["linkinfo"]["info_data"]["ageing_time"]') + echo $((ageing_time / 100)) +} + +forwarding_enable() +{ + ipv4_fwd=$(sysctl -n net.ipv4.conf.all.forwarding) + ipv6_fwd=$(sysctl -n net.ipv6.conf.all.forwarding) + + sysctl -q -w net.ipv4.conf.all.forwarding=1 + sysctl -q -w net.ipv6.conf.all.forwarding=1 +} + +forwarding_restore() +{ + sysctl -q -w net.ipv6.conf.all.forwarding=$ipv6_fwd + sysctl -q -w net.ipv4.conf.all.forwarding=$ipv4_fwd +} + +tc_offload_check() +{ + for i in $(eval echo {1..$NUM_NETIFS}); do + ethtool -k ${NETIFS[p$i]} \ + | grep "hw-tc-offload: on" &> /dev/null + if [[ $? -ne 0 ]]; then + return 1 + fi + done + + return 0 +} + +############################################################################## +# Tests + +ping_test() +{ + local if_name=$1 + local dip=$2 + local vrf_name + + RET=0 + + vrf_name=$(master_name_get $if_name) + ip vrf exec $vrf_name $PING $dip -c 10 -i 0.1 -w 2 &> /dev/null + check_err $? + log_test "ping" +} + +ping6_test() +{ + local if_name=$1 + local dip=$2 + local vrf_name + + RET=0 + + vrf_name=$(master_name_get $if_name) + ip vrf exec $vrf_name $PING6 $dip -c 10 -i 0.1 -w 2 &> /dev/null + check_err $? + log_test "ping6" +} + +learning_test() +{ + local bridge=$1 + local br_port1=$2 # Connected to `host1_if`. + local host1_if=$3 + local host2_if=$4 + local mac=de:ad:be:ef:13:37 + local ageing_time + + RET=0 + + bridge -j fdb show br $bridge brport $br_port1 \ + | jq -e ".[] | select(.mac == \"$mac\")" &> /dev/null + check_fail $? "Found FDB record when should not" + + # Disable unknown unicast flooding on `br_port1` to make sure + # packets are only forwarded through the port after a matching + # FDB entry was installed. + bridge link set dev $br_port1 flood off + + tc qdisc add dev $host1_if ingress + tc filter add dev $host1_if ingress protocol ip pref 1 handle 101 \ + flower dst_mac $mac action drop + + $MZ $host2_if -c 1 -p 64 -b $mac -t ip -q + sleep 1 + + tc -j -s filter show dev $host1_if ingress \ + | jq -e ".[] | select(.options.handle == 101) \ + | select(.options.actions[0].stats.packets == 1)" &> /dev/null + check_fail $? "Packet reached second host when should not" + + $MZ $host1_if -c 1 -p 64 -a $mac -t ip -q + sleep 1 + + bridge -j fdb show br $bridge brport $br_port1 \ + | jq -e ".[] | select(.mac == \"$mac\")" &> /dev/null + check_err $? "Did not find FDB record when should" + + $MZ $host2_if -c 1 -p 64 -b $mac -t ip -q + sleep 1 + + tc -j -s filter show dev $host1_if ingress \ + | jq -e ".[] | select(.options.handle == 101) \ + | select(.options.actions[0].stats.packets == 1)" &> /dev/null + check_err $? "Packet did not reach second host when should" + + # Wait for 10 seconds after the ageing time to make sure FDB + # record was aged-out. + ageing_time=$(bridge_ageing_time_get $bridge) + sleep $((ageing_time + 10)) + + bridge -j fdb show br $bridge brport $br_port1 \ + | jq -e ".[] | select(.mac == \"$mac\")" &> /dev/null + check_fail $? "Found FDB record when should not" + + bridge link set dev $br_port1 learning off + + $MZ $host1_if -c 1 -p 64 -a $mac -t ip -q + sleep 1 + + bridge -j fdb show br $bridge brport $br_port1 \ + | jq -e ".[] | select(.mac == \"$mac\")" &> /dev/null + check_fail $? "Found FDB record when should not" + + bridge link set dev $br_port1 learning on + + tc filter del dev $host1_if ingress protocol ip pref 1 handle 101 flower + tc qdisc del dev $host1_if ingress + + bridge link set dev $br_port1 flood on + + log_test "FDB learning" +} + +flood_test_do() +{ + local should_flood=$1 + local mac=$2 + local ip=$3 + local host1_if=$4 + local host2_if=$5 + local err=0 + + # Add an ACL on `host2_if` which will tell us whether the packet + # was flooded to it or not. + tc qdisc add dev $host2_if ingress + tc filter add dev $host2_if ingress protocol ip pref 1 handle 101 \ + flower dst_mac $mac action drop + + $MZ $host1_if -c 1 -p 64 -b $mac -B $ip -t ip -q + sleep 1 + + tc -j -s filter show dev $host2_if ingress \ + | jq -e ".[] | select(.options.handle == 101) \ + | select(.options.actions[0].stats.packets == 1)" &> /dev/null + if [[ $? -ne 0 && $should_flood == "true" || \ + $? -eq 0 && $should_flood == "false" ]]; then + err=1 + fi + + tc filter del dev $host2_if ingress protocol ip pref 1 handle 101 flower + tc qdisc del dev $host2_if ingress + + return $err +} + +flood_unicast_test() +{ + local br_port=$1 + local host1_if=$2 + local host2_if=$3 + local mac=de:ad:be:ef:13:37 + local ip=192.0.2.100 + + RET=0 + + bridge link set dev $br_port flood off + + flood_test_do false $mac $ip $host1_if $host2_if + check_err $? "Packet flooded when should not" + + bridge link set dev $br_port flood on + + flood_test_do true $mac $ip $host1_if $host2_if + check_err $? "Packet was not flooded when should" + + log_test "Unknown unicast flood" +} + +flood_multicast_test() +{ + local br_port=$1 + local host1_if=$2 + local host2_if=$3 + local mac=01:00:5e:00:00:01 + local ip=239.0.0.1 + + RET=0 + + bridge link set dev $br_port mcast_flood off + + flood_test_do false $mac $ip $host1_if $host2_if + check_err $? "Packet flooded when should not" + + bridge link set dev $br_port mcast_flood on + + flood_test_do true $mac $ip $host1_if $host2_if + check_err $? "Packet was not flooded when should" + + log_test "Unregistered multicast flood" +} + +flood_test() +{ + # `br_port` is connected to `host2_if` + local br_port=$1 + local host1_if=$2 + local host2_if=$3 + + flood_unicast_test $br_port $host1_if $host2_if + flood_multicast_test $br_port $host1_if $host2_if +} diff --git a/tools/testing/selftests/net/forwarding/router.sh b/tools/testing/selftests/net/forwarding/router.sh new file mode 100755 index 000000000000..cc6a14abfa87 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/router.sh @@ -0,0 +1,125 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +NUM_NETIFS=4 +source lib.sh + +h1_create() +{ + vrf_create "vrf-h1" + ip link set dev $h1 master vrf-h1 + + ip link set dev vrf-h1 up + ip link set dev $h1 up + + ip address add 192.0.2.2/24 dev $h1 + ip address add 2001:db8:1::2/64 dev $h1 + + ip route add 198.51.100.0/24 vrf vrf-h1 nexthop via 192.0.2.1 + ip route add 2001:db8:2::/64 vrf vrf-h1 nexthop via 2001:db8:1::1 +} + +h1_destroy() +{ + ip route del 2001:db8:2::/64 vrf vrf-h1 + ip route del 198.51.100.0/24 vrf vrf-h1 + + ip address del 2001:db8:1::2/64 dev $h1 + ip address del 192.0.2.2/24 dev $h1 + + ip link set dev $h1 down + vrf_destroy "vrf-h1" +} + +h2_create() +{ + vrf_create "vrf-h2" + ip link set dev $h2 master vrf-h2 + + ip link set dev vrf-h2 up + ip link set dev $h2 up + + ip address add 198.51.100.2/24 dev $h2 + ip address add 2001:db8:2::2/64 dev $h2 + + ip route add 192.0.2.0/24 vrf vrf-h2 nexthop via 198.51.100.1 + ip route add 2001:db8:1::/64 vrf vrf-h2 nexthop via 2001:db8:2::1 +} + +h2_destroy() +{ + ip route del 2001:db8:1::/64 vrf vrf-h2 + ip route del 192.0.2.0/24 vrf vrf-h2 + + ip address del 2001:db8:2::2/64 dev $h2 + ip address del 198.51.100.2/24 dev $h2 + + ip link set dev $h2 down + vrf_destroy "vrf-h2" +} + +router_create() +{ + ip link set dev $rp1 up + ip link set dev $rp2 up + + ip address add 192.0.2.1/24 dev $rp1 + ip address add 2001:db8:1::1/64 dev $rp1 + + ip address add 198.51.100.1/24 dev $rp2 + ip address add 2001:db8:2::1/64 dev $rp2 +} + +router_destroy() +{ + ip address del 2001:db8:2::1/64 dev $rp2 + ip address del 198.51.100.1/24 dev $rp2 + + ip address del 2001:db8:1::1/64 dev $rp1 + ip address del 192.0.2.1/24 dev $rp1 + + ip link set dev $rp2 down + ip link set dev $rp1 down +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + rp1=${NETIFS[p2]} + + rp2=${NETIFS[p3]} + h2=${NETIFS[p4]} + + vrf_prepare + + h1_create + h2_create + + router_create + + forwarding_enable +} + +cleanup() +{ + pre_cleanup + + forwarding_restore + + router_destroy + + h2_destroy + h1_destroy + + vrf_cleanup +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +ping_test $h1 198.51.100.2 +ping6_test $h1 2001:db8:2::2 + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/router_multipath.sh b/tools/testing/selftests/net/forwarding/router_multipath.sh new file mode 100755 index 000000000000..3bc351008db6 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/router_multipath.sh @@ -0,0 +1,376 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +NUM_NETIFS=8 +source lib.sh + +h1_create() +{ + vrf_create "vrf-h1" + ip link set dev $h1 master vrf-h1 + + ip link set dev vrf-h1 up + ip link set dev $h1 up + + ip address add 192.0.2.2/24 dev $h1 + ip address add 2001:db8:1::2/64 dev $h1 + + ip route add 198.51.100.0/24 vrf vrf-h1 nexthop via 192.0.2.1 + ip route add 2001:db8:2::/64 vrf vrf-h1 nexthop via 2001:db8:1::1 +} + +h1_destroy() +{ + ip route del 2001:db8:2::/64 vrf vrf-h1 + ip route del 198.51.100.0/24 vrf vrf-h1 + + ip address del 2001:db8:1::2/64 dev $h1 + ip address del 192.0.2.2/24 dev $h1 + + ip link set dev $h1 down + vrf_destroy "vrf-h1" +} + +h2_create() +{ + vrf_create "vrf-h2" + ip link set dev $h2 master vrf-h2 + + ip link set dev vrf-h2 up + ip link set dev $h2 up + + ip address add 198.51.100.2/24 dev $h2 + ip address add 2001:db8:2::2/64 dev $h2 + + ip route add 192.0.2.0/24 vrf vrf-h2 nexthop via 198.51.100.1 + ip route add 2001:db8:1::/64 vrf vrf-h2 nexthop via 2001:db8:2::1 +} + +h2_destroy() +{ + ip route del 2001:db8:1::/64 vrf vrf-h2 + ip route del 192.0.2.0/24 vrf vrf-h2 + + ip address del 2001:db8:2::2/64 dev $h2 + ip address del 198.51.100.2/24 dev $h2 + + ip link set dev $h2 down + vrf_destroy "vrf-h2" +} + +router1_create() +{ + vrf_create "vrf-r1" + ip link set dev $rp11 master vrf-r1 + ip link set dev $rp12 master vrf-r1 + ip link set dev $rp13 master vrf-r1 + + ip link set dev vrf-r1 up + ip link set dev $rp11 up + ip link set dev $rp12 up + ip link set dev $rp13 up + + ip address add 192.0.2.1/24 dev $rp11 + ip address add 2001:db8:1::1/64 dev $rp11 + + ip address add 169.254.2.12/24 dev $rp12 + ip address add fe80:2::12/64 dev $rp12 + + ip address add 169.254.3.13/24 dev $rp13 + ip address add fe80:3::13/64 dev $rp13 + + ip route add 198.51.100.0/24 vrf vrf-r1 \ + nexthop via 169.254.2.22 dev $rp12 \ + nexthop via 169.254.3.23 dev $rp13 + ip route add 2001:db8:2::/64 vrf vrf-r1 \ + nexthop via fe80:2::22 dev $rp12 \ + nexthop via fe80:3::23 dev $rp13 +} + +router1_destroy() +{ + ip route del 2001:db8:2::/64 vrf vrf-r1 + ip route del 198.51.100.0/24 vrf vrf-r1 + + ip address del fe80:3::13/64 dev $rp13 + ip address del 169.254.3.13/24 dev $rp13 + + ip address del fe80:2::12/64 dev $rp12 + ip address del 169.254.2.12/24 dev $rp12 + + ip address del 2001:db8:1::1/64 dev $rp11 + ip address del 192.0.2.1/24 dev $rp11 + + ip link set dev $rp13 down + ip link set dev $rp12 down + ip link set dev $rp11 down + + vrf_destroy "vrf-r1" +} + +router2_create() +{ + vrf_create "vrf-r2" + ip link set dev $rp21 master vrf-r2 + ip link set dev $rp22 master vrf-r2 + ip link set dev $rp23 master vrf-r2 + + ip link set dev vrf-r2 up + ip link set dev $rp21 up + ip link set dev $rp22 up + ip link set dev $rp23 up + + ip address add 198.51.100.1/24 dev $rp21 + ip address add 2001:db8:2::1/64 dev $rp21 + + ip address add 169.254.2.22/24 dev $rp22 + ip address add fe80:2::22/64 dev $rp22 + + ip address add 169.254.3.23/24 dev $rp23 + ip address add fe80:3::23/64 dev $rp23 + + ip route add 192.0.2.0/24 vrf vrf-r2 \ + nexthop via 169.254.2.12 dev $rp22 \ + nexthop via 169.254.3.13 dev $rp23 + ip route add 2001:db8:1::/64 vrf vrf-r2 \ + nexthop via fe80:2::12 dev $rp22 \ + nexthop via fe80:3::13 dev $rp23 +} + +router2_destroy() +{ + ip route del 2001:db8:1::/64 vrf vrf-r2 + ip route del 192.0.2.0/24 vrf vrf-r2 + + ip address del fe80:3::23/64 dev $rp23 + ip address del 169.254.3.23/24 dev $rp23 + + ip address del fe80:2::22/64 dev $rp22 + ip address del 169.254.2.22/24 dev $rp22 + + ip address del 2001:db8:2::1/64 dev $rp21 + ip address del 198.51.100.1/24 dev $rp21 + + ip link set dev $rp23 down + ip link set dev $rp22 down + ip link set dev $rp21 down + + vrf_destroy "vrf-r2" +} + +multipath_eval() +{ + local desc="$1" + local weight_rp12=$2 + local weight_rp13=$3 + local packets_rp12=$4 + local packets_rp13=$5 + local weights_ratio packets_ratio diff + + RET=0 + + if [[ "$packets_rp12" -eq "0" || "$packets_rp13" -eq "0" ]]; then + check_err 1 "Packet difference is 0" + log_test "Multipath" + log_info "Expected ratio $weights_ratio" + return + fi + + if [[ "$weight_rp12" -gt "$weight_rp13" ]]; then + weights_ratio=$(echo "scale=2; $weight_rp12 / $weight_rp13" \ + | bc -l) + packets_ratio=$(echo "scale=2; $packets_rp12 / $packets_rp13" \ + | bc -l) + else + weights_ratio=$(echo "scale=2; $weight_rp13 / $weight_rp12" | \ + bc -l) + packets_ratio=$(echo "scale=2; $packets_rp13 / $packets_rp12" | \ + bc -l) + fi + + diff=$(echo $weights_ratio - $packets_ratio | bc -l) + diff=${diff#-} + + test "$(echo "$diff / $weights_ratio > 0.1" | bc -l)" -eq 0 + check_err $? "Too large discrepancy between expected and measured ratios" + log_test "$desc" + log_info "Expected ratio $weights_ratio Measured ratio $packets_ratio" +} + +multipath4_test() +{ + local desc="$1" + local weight_rp12=$2 + local weight_rp13=$3 + local t0_rp12 t0_rp13 t1_rp12 t1_rp13 + local packets_rp12 packets_rp13 + local hash_policy + + # Transmit multiple flows from h1 to h2 and make sure they are + # distributed between both multipath links (rp12 and rp13) + # according to the configured weights. + hash_policy=$(sysctl -n net.ipv4.fib_multipath_hash_policy) + sysctl -q -w net.ipv4.fib_multipath_hash_policy=1 + ip route replace 198.51.100.0/24 vrf vrf-r1 \ + nexthop via 169.254.2.22 dev $rp12 weight $weight_rp12 \ + nexthop via 169.254.3.23 dev $rp13 weight $weight_rp13 + + t0_rp12=$(link_stats_tx_packets_get $rp12) + t0_rp13=$(link_stats_tx_packets_get $rp13) + + ip vrf exec vrf-h1 $MZ -q -p 64 -A 192.0.2.2 -B 198.51.100.2 \ + -d 1msec -t udp "sp=1024,dp=0-32768" + + t1_rp12=$(link_stats_tx_packets_get $rp12) + t1_rp13=$(link_stats_tx_packets_get $rp13) + + let "packets_rp12 = $t1_rp12 - $t0_rp12" + let "packets_rp13 = $t1_rp13 - $t0_rp13" + multipath_eval "$desc" $weight_rp12 $weight_rp13 $packets_rp12 $packets_rp13 + + # Restore settings. + ip route replace 198.51.100.0/24 vrf vrf-r1 \ + nexthop via 169.254.2.22 dev $rp12 \ + nexthop via 169.254.3.23 dev $rp13 + sysctl -q -w net.ipv4.fib_multipath_hash_policy=$hash_policy +} + +multipath6_l4_test() +{ + local desc="$1" + local weight_rp12=$2 + local weight_rp13=$3 + local t0_rp12 t0_rp13 t1_rp12 t1_rp13 + local packets_rp12 packets_rp13 + local hash_policy + + # Transmit multiple flows from h1 to h2 and make sure they are + # distributed between both multipath links (rp12 and rp13) + # according to the configured weights. + hash_policy=$(sysctl -n net.ipv6.fib_multipath_hash_policy) + sysctl -q -w net.ipv6.fib_multipath_hash_policy=1 + + ip route replace 2001:db8:2::/64 vrf vrf-r1 \ + nexthop via fe80:2::22 dev $rp12 weight $weight_rp12 \ + nexthop via fe80:3::23 dev $rp13 weight $weight_rp13 + + t0_rp12=$(link_stats_tx_packets_get $rp12) + t0_rp13=$(link_stats_tx_packets_get $rp13) + + $MZ $h1 -6 -q -p 64 -A 2001:db8:1::2 -B 2001:db8:2::2 \ + -d 1msec -t udp "sp=1024,dp=0-32768" + + t1_rp12=$(link_stats_tx_packets_get $rp12) + t1_rp13=$(link_stats_tx_packets_get $rp13) + + let "packets_rp12 = $t1_rp12 - $t0_rp12" + let "packets_rp13 = $t1_rp13 - $t0_rp13" + multipath_eval "$desc" $weight_rp12 $weight_rp13 $packets_rp12 $packets_rp13 + + ip route replace 2001:db8:2::/64 vrf vrf-r1 \ + nexthop via fe80:2::22 dev $rp12 \ + nexthop via fe80:3::23 dev $rp13 + + sysctl -q -w net.ipv6.fib_multipath_hash_policy=$hash_policy +} + +multipath6_test() +{ + local desc="$1" + local weight_rp12=$2 + local weight_rp13=$3 + local t0_rp12 t0_rp13 t1_rp12 t1_rp13 + local packets_rp12 packets_rp13 + + ip route replace 2001:db8:2::/64 vrf vrf-r1 \ + nexthop via fe80:2::22 dev $rp12 weight $weight_rp12 \ + nexthop via fe80:3::23 dev $rp13 weight $weight_rp13 + + t0_rp12=$(link_stats_tx_packets_get $rp12) + t0_rp13=$(link_stats_tx_packets_get $rp13) + + # Generate 16384 echo requests, each with a random flow label. + for _ in $(seq 1 16384); do + ip vrf exec vrf-h1 $PING6 2001:db8:2::2 -F 0 -c 1 -q &> /dev/null + done + + t1_rp12=$(link_stats_tx_packets_get $rp12) + t1_rp13=$(link_stats_tx_packets_get $rp13) + + let "packets_rp12 = $t1_rp12 - $t0_rp12" + let "packets_rp13 = $t1_rp13 - $t0_rp13" + multipath_eval "$desc" $weight_rp12 $weight_rp13 $packets_rp12 $packets_rp13 + + ip route replace 2001:db8:2::/64 vrf vrf-r1 \ + nexthop via fe80:2::22 dev $rp12 \ + nexthop via fe80:3::23 dev $rp13 +} + +multipath_test() +{ + log_info "Running IPv4 multipath tests" + multipath4_test "ECMP" 1 1 + multipath4_test "Weighted MP 2:1" 2 1 + multipath4_test "Weighted MP 11:45" 11 45 + + log_info "Running IPv6 multipath tests" + multipath6_test "ECMP" 1 1 + multipath6_test "Weighted MP 2:1" 2 1 + multipath6_test "Weighted MP 11:45" 11 45 + + log_info "Running IPv6 L4 hash multipath tests" + multipath6_l4_test "ECMP" 1 1 + multipath6_l4_test "Weighted MP 2:1" 2 1 + multipath6_l4_test "Weighted MP 11:45" 11 45 +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + rp11=${NETIFS[p2]} + + rp12=${NETIFS[p3]} + rp22=${NETIFS[p4]} + + rp13=${NETIFS[p5]} + rp23=${NETIFS[p6]} + + rp21=${NETIFS[p7]} + h2=${NETIFS[p8]} + + vrf_prepare + + h1_create + h2_create + + router1_create + router2_create + + forwarding_enable +} + +cleanup() +{ + pre_cleanup + + forwarding_restore + + router2_destroy + router1_destroy + + h2_destroy + h1_destroy + + vrf_cleanup +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +ping_test $h1 198.51.100.2 +ping6_test $h1 2001:db8:2::2 +multipath_test + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/tc_actions.sh b/tools/testing/selftests/net/forwarding/tc_actions.sh new file mode 100755 index 000000000000..6b18ba2d3982 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/tc_actions.sh @@ -0,0 +1,199 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +NUM_NETIFS=4 +source tc_common.sh +source lib.sh + +tcflags="skip_hw" + +h1_create() +{ + simple_if_init $h1 192.0.2.1/24 +} + +h1_destroy() +{ + simple_if_fini $h1 192.0.2.1/24 +} + +h2_create() +{ + simple_if_init $h2 192.0.2.2/24 + tc qdisc add dev $h2 clsact +} + +h2_destroy() +{ + tc qdisc del dev $h2 clsact + simple_if_fini $h2 192.0.2.2/24 +} + +switch_create() +{ + simple_if_init $swp1 192.0.2.2/24 + tc qdisc add dev $swp1 clsact + + simple_if_init $swp2 192.0.2.1/24 +} + +switch_destroy() +{ + simple_if_fini $swp2 192.0.2.1/24 + + tc qdisc del dev $swp1 clsact + simple_if_fini $swp1 192.0.2.2/24 +} + +mirred_egress_test() +{ + local action=$1 + + RET=0 + + tc filter add dev $h2 ingress protocol ip pref 1 handle 101 flower \ + $tcflags dst_ip 192.0.2.2 action drop + + $MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac -A 192.0.2.1 -B 192.0.2.2 \ + -t ip -q + + tc_check_packets "dev $h2 ingress" 101 1 + check_fail $? "Matched without redirect rule inserted" + + tc filter add dev $swp1 ingress protocol ip pref 1 handle 101 flower \ + $tcflags dst_ip 192.0.2.2 action mirred egress $action \ + dev $swp2 + + $MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac -A 192.0.2.1 -B 192.0.2.2 \ + -t ip -q + + tc_check_packets "dev $h2 ingress" 101 1 + check_err $? "Did not match incoming $action packet" + + tc filter del dev $swp1 ingress protocol ip pref 1 handle 101 flower + tc filter del dev $h2 ingress protocol ip pref 1 handle 101 flower + + log_test "mirred egress $action ($tcflags)" +} + +gact_drop_and_ok_test() +{ + RET=0 + + tc filter add dev $swp1 ingress protocol ip pref 2 handle 102 flower \ + skip_hw dst_ip 192.0.2.2 action drop + + $MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac -A 192.0.2.1 -B 192.0.2.2 \ + -t ip -q + + tc_check_packets "dev $swp1 ingress" 102 1 + check_err $? "Packet was not dropped" + + tc filter add dev $swp1 ingress protocol ip pref 1 handle 101 flower \ + $tcflags dst_ip 192.0.2.2 action ok + + $MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac -A 192.0.2.1 -B 192.0.2.2 \ + -t ip -q + + tc_check_packets "dev $swp1 ingress" 101 1 + check_err $? "Did not see trapped packet" + + tc filter del dev $swp1 ingress protocol ip pref 2 handle 102 flower + tc filter del dev $swp1 ingress protocol ip pref 1 handle 101 flower + + log_test "gact drop and ok ($tcflags)" +} + +gact_trap_test() +{ + RET=0 + + tc filter add dev $swp1 ingress protocol ip pref 1 handle 101 flower \ + skip_hw dst_ip 192.0.2.2 action drop + tc filter add dev $swp1 ingress protocol ip pref 3 handle 103 flower \ + $tcflags dst_ip 192.0.2.2 action mirred egress redirect \ + dev $swp2 + + $MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac -A 192.0.2.1 -B 192.0.2.2 \ + -t ip -q + + tc_check_packets "dev $swp1 ingress" 101 1 + check_fail $? "Saw packet without trap rule inserted" + + tc filter add dev $swp1 ingress protocol ip pref 2 handle 102 flower \ + $tcflags dst_ip 192.0.2.2 action trap + + $MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac -A 192.0.2.1 -B 192.0.2.2 \ + -t ip -q + + tc_check_packets "dev $swp1 ingress" 102 1 + check_err $? "Packet was not trapped" + + tc_check_packets "dev $swp1 ingress" 101 1 + check_err $? "Did not see trapped packet" + + tc filter del dev $swp1 ingress protocol ip pref 3 handle 103 flower + tc filter del dev $swp1 ingress protocol ip pref 2 handle 102 flower + tc filter del dev $swp1 ingress protocol ip pref 1 handle 101 flower + + log_test "trap ($tcflags)" +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + swp2=${NETIFS[p3]} + h2=${NETIFS[p4]} + + h1mac=$(mac_get $h1) + h2mac=$(mac_get $h2) + + swp1origmac=$(mac_get $swp1) + swp2origmac=$(mac_get $swp2) + ip link set $swp1 address $h2mac + ip link set $swp2 address $h1mac + + vrf_prepare + + h1_create + h2_create + switch_create +} + +cleanup() +{ + pre_cleanup + + switch_destroy + h2_destroy + h1_destroy + + vrf_cleanup + + ip link set $swp2 address $swp2origmac + ip link set $swp1 address $swp1origmac +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +gact_drop_and_ok_test +mirred_egress_test "redirect" +mirred_egress_test "mirror" + +tc_offload_check +if [[ $? -ne 0 ]]; then + log_info "Could not test offloaded functionality" +else + tcflags="skip_sw" + gact_drop_and_ok_test + mirred_egress_test "redirect" + mirred_egress_test "mirror" + gact_trap_test +fi + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/tc_chains.sh b/tools/testing/selftests/net/forwarding/tc_chains.sh new file mode 100755 index 000000000000..2fd15226974b --- /dev/null +++ b/tools/testing/selftests/net/forwarding/tc_chains.sh @@ -0,0 +1,122 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +NUM_NETIFS=2 +source tc_common.sh +source lib.sh + +tcflags="skip_hw" + +h1_create() +{ + simple_if_init $h1 192.0.2.1/24 +} + +h1_destroy() +{ + simple_if_fini $h1 192.0.2.1/24 +} + +h2_create() +{ + simple_if_init $h2 192.0.2.2/24 + tc qdisc add dev $h2 clsact +} + +h2_destroy() +{ + tc qdisc del dev $h2 clsact + simple_if_fini $h2 192.0.2.2/24 +} + +unreachable_chain_test() +{ + RET=0 + + tc filter add dev $h2 ingress chain 1 protocol ip pref 1 handle 1101 \ + flower $tcflags dst_mac $h2mac action drop + + $MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac -A 192.0.2.1 -B 192.0.2.2 \ + -t ip -q + + tc_check_packets "dev $h2 ingress" 1101 1 + check_fail $? "matched on filter in unreachable chain" + + tc filter del dev $h2 ingress chain 1 protocol ip pref 1 handle 1101 \ + flower + + log_test "unreachable chain ($tcflags)" +} + +gact_goto_chain_test() +{ + RET=0 + + tc filter add dev $h2 ingress chain 1 protocol ip pref 1 handle 1101 \ + flower $tcflags dst_mac $h2mac action drop + tc filter add dev $h2 ingress protocol ip pref 2 handle 102 flower \ + $tcflags dst_mac $h2mac action drop + tc filter add dev $h2 ingress protocol ip pref 1 handle 101 flower \ + $tcflags dst_mac $h2mac action goto chain 1 + + $MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac -A 192.0.2.1 -B 192.0.2.2 \ + -t ip -q + + tc_check_packets "dev $h2 ingress" 102 1 + check_fail $? "Matched on a wrong filter" + + tc_check_packets "dev $h2 ingress" 101 1 + check_err $? "Did not match on correct filter with goto chain action" + + tc_check_packets "dev $h2 ingress" 1101 1 + check_err $? "Did not match on correct filter in chain 1" + + tc filter del dev $h2 ingress protocol ip pref 1 handle 101 flower + tc filter del dev $h2 ingress protocol ip pref 2 handle 102 flower + tc filter del dev $h2 ingress chain 1 protocol ip pref 1 handle 1101 \ + flower + + log_test "gact goto chain ($tcflags)" +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + h2=${NETIFS[p2]} + h1mac=$(mac_get $h1) + h2mac=$(mac_get $h2) + + vrf_prepare + + h1_create + h2_create +} + +cleanup() +{ + pre_cleanup + + h2_destroy + h1_destroy + + vrf_cleanup +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +unreachable_chain_test +gact_goto_chain_test + +tc_offload_check +if [[ $? -ne 0 ]]; then + log_info "Could not test offloaded functionality" +else + tcflags="skip_sw" + unreachable_chain_test + gact_goto_chain_test +fi + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/tc_common.sh b/tools/testing/selftests/net/forwarding/tc_common.sh new file mode 100644 index 000000000000..9d3b64a2a264 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/tc_common.sh @@ -0,0 +1,25 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +CHECK_TC="yes" + +tc_check_packets() +{ + local id=$1 + local handle=$2 + local count=$3 + local ret + + output="$(tc -j -s filter show $id)" + # workaround the jq bug which causes jq to return 0 in case input is "" + ret=$? + if [[ $ret -ne 0 ]]; then + return $ret + fi + echo $output | \ + jq -e ".[] \ + | select(.options.handle == $handle) \ + | select(.options.actions[0].stats.packets == $count)" \ + &> /dev/null + return $? +} diff --git a/tools/testing/selftests/net/forwarding/tc_flower.sh b/tools/testing/selftests/net/forwarding/tc_flower.sh new file mode 100755 index 000000000000..032b882adfc0 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/tc_flower.sh @@ -0,0 +1,196 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +NUM_NETIFS=2 +source tc_common.sh +source lib.sh + +tcflags="skip_hw" + +h1_create() +{ + simple_if_init $h1 192.0.2.1/24 198.51.100.1/24 +} + +h1_destroy() +{ + simple_if_fini $h1 192.0.2.1/24 198.51.100.1/24 +} + +h2_create() +{ + simple_if_init $h2 192.0.2.2/24 198.51.100.2/24 + tc qdisc add dev $h2 clsact +} + +h2_destroy() +{ + tc qdisc del dev $h2 clsact + simple_if_fini $h2 192.0.2.2/24 198.51.100.2/24 +} + +match_dst_mac_test() +{ + local dummy_mac=de:ad:be:ef:aa:aa + + RET=0 + + tc filter add dev $h2 ingress protocol ip pref 1 handle 101 flower \ + $tcflags dst_mac $dummy_mac action drop + tc filter add dev $h2 ingress protocol ip pref 2 handle 102 flower \ + $tcflags dst_mac $h2mac action drop + + $MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac -A 192.0.2.1 -B 192.0.2.2 \ + -t ip -q + + tc_check_packets "dev $h2 ingress" 101 1 + check_fail $? "Matched on a wrong filter" + + tc_check_packets "dev $h2 ingress" 102 1 + check_err $? "Did not match on correct filter" + + tc filter del dev $h2 ingress protocol ip pref 1 handle 101 flower + tc filter del dev $h2 ingress protocol ip pref 2 handle 102 flower + + log_test "dst_mac match ($tcflags)" +} + +match_src_mac_test() +{ + local dummy_mac=de:ad:be:ef:aa:aa + + RET=0 + + tc filter add dev $h2 ingress protocol ip pref 1 handle 101 flower \ + $tcflags src_mac $dummy_mac action drop + tc filter add dev $h2 ingress protocol ip pref 2 handle 102 flower \ + $tcflags src_mac $h1mac action drop + + $MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac -A 192.0.2.1 -B 192.0.2.2 \ + -t ip -q + + tc_check_packets "dev $h2 ingress" 101 1 + check_fail $? "Matched on a wrong filter" + + tc_check_packets "dev $h2 ingress" 102 1 + check_err $? "Did not match on correct filter" + + tc filter del dev $h2 ingress protocol ip pref 1 handle 101 flower + tc filter del dev $h2 ingress protocol ip pref 2 handle 102 flower + + log_test "src_mac match ($tcflags)" +} + +match_dst_ip_test() +{ + RET=0 + + tc filter add dev $h2 ingress protocol ip pref 1 handle 101 flower \ + $tcflags dst_ip 198.51.100.2 action drop + tc filter add dev $h2 ingress protocol ip pref 2 handle 102 flower \ + $tcflags dst_ip 192.0.2.2 action drop + tc filter add dev $h2 ingress protocol ip pref 3 handle 103 flower \ + $tcflags dst_ip 192.0.2.0/24 action drop + + $MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac -A 192.0.2.1 -B 192.0.2.2 \ + -t ip -q + + tc_check_packets "dev $h2 ingress" 101 1 + check_fail $? "Matched on a wrong filter" + + tc_check_packets "dev $h2 ingress" 102 1 + check_err $? "Did not match on correct filter" + + tc filter del dev $h2 ingress protocol ip pref 2 handle 102 flower + + $MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac -A 192.0.2.1 -B 192.0.2.2 \ + -t ip -q + + tc_check_packets "dev $h2 ingress" 103 1 + check_err $? "Did not match on correct filter with mask" + + tc filter del dev $h2 ingress protocol ip pref 1 handle 101 flower + tc filter del dev $h2 ingress protocol ip pref 3 handle 103 flower + + log_test "dst_ip match ($tcflags)" +} + +match_src_ip_test() +{ + RET=0 + + tc filter add dev $h2 ingress protocol ip pref 1 handle 101 flower \ + $tcflags src_ip 198.51.100.1 action drop + tc filter add dev $h2 ingress protocol ip pref 2 handle 102 flower \ + $tcflags src_ip 192.0.2.1 action drop + tc filter add dev $h2 ingress protocol ip pref 3 handle 103 flower \ + $tcflags src_ip 192.0.2.0/24 action drop + + $MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac -A 192.0.2.1 -B 192.0.2.2 \ + -t ip -q + + tc_check_packets "dev $h2 ingress" 101 1 + check_fail $? "Matched on a wrong filter" + + tc_check_packets "dev $h2 ingress" 102 1 + check_err $? "Did not match on correct filter" + + tc filter del dev $h2 ingress protocol ip pref 2 handle 102 flower + + $MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac -A 192.0.2.1 -B 192.0.2.2 \ + -t ip -q + + tc_check_packets "dev $h2 ingress" 103 1 + check_err $? "Did not match on correct filter with mask" + + tc filter del dev $h2 ingress protocol ip pref 1 handle 101 flower + tc filter del dev $h2 ingress protocol ip pref 3 handle 103 flower + + log_test "src_ip match ($tcflags)" +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + h2=${NETIFS[p2]} + h1mac=$(mac_get $h1) + h2mac=$(mac_get $h2) + + vrf_prepare + + h1_create + h2_create +} + +cleanup() +{ + pre_cleanup + + h2_destroy + h1_destroy + + vrf_cleanup +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +match_dst_mac_test +match_src_mac_test +match_dst_ip_test +match_src_ip_test + +tc_offload_check +if [[ $? -ne 0 ]]; then + log_info "Could not test offloaded functionality" +else + tcflags="skip_sw" + match_dst_mac_test + match_src_mac_test + match_dst_ip_test + match_src_ip_test +fi + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/tc_shblocks.sh b/tools/testing/selftests/net/forwarding/tc_shblocks.sh new file mode 100755 index 000000000000..077b98048ef4 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/tc_shblocks.sh @@ -0,0 +1,122 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +NUM_NETIFS=4 +source tc_common.sh +source lib.sh + +tcflags="skip_hw" + +h1_create() +{ + simple_if_init $h1 192.0.2.1/24 +} + +h1_destroy() +{ + simple_if_fini $h1 192.0.2.1/24 +} + +h2_create() +{ + simple_if_init $h2 192.0.2.1/24 +} + +h2_destroy() +{ + simple_if_fini $h2 192.0.2.1/24 +} + +switch_create() +{ + simple_if_init $swp1 192.0.2.2/24 + tc qdisc add dev $swp1 ingress_block 22 egress_block 23 clsact + + simple_if_init $swp2 192.0.2.2/24 + tc qdisc add dev $swp2 ingress_block 22 egress_block 23 clsact +} + +switch_destroy() +{ + tc qdisc del dev $swp2 clsact + simple_if_fini $swp2 192.0.2.2/24 + + tc qdisc del dev $swp1 clsact + simple_if_fini $swp1 192.0.2.2/24 +} + +shared_block_test() +{ + RET=0 + + tc filter add block 22 protocol ip pref 1 handle 101 flower \ + $tcflags dst_ip 192.0.2.2 action drop + + $MZ $h1 -c 1 -p 64 -a $h1mac -b $swmac -A 192.0.2.1 -B 192.0.2.2 \ + -t ip -q + + tc_check_packets "block 22" 101 1 + check_err $? "Did not match first incoming packet on a block" + + $MZ $h2 -c 1 -p 64 -a $h2mac -b $swmac -A 192.0.2.1 -B 192.0.2.2 \ + -t ip -q + + tc_check_packets "block 22" 101 2 + check_err $? "Did not match second incoming packet on a block" + + tc filter del block 22 protocol ip pref 1 handle 101 flower + + log_test "shared block ($tcflags)" +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + swp2=${NETIFS[p3]} + h2=${NETIFS[p4]} + + h1mac=$(mac_get $h1) + h2mac=$(mac_get $h2) + + swmac=$(mac_get $swp1) + swp2origmac=$(mac_get $swp2) + ip link set $swp2 address $swmac + + vrf_prepare + + h1_create + h2_create + switch_create +} + +cleanup() +{ + pre_cleanup + + switch_destroy + h2_destroy + h1_destroy + + vrf_cleanup + + ip link set $swp2 address $swp2origmac +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +shared_block_test + +tc_offload_check +if [[ $? -ne 0 ]]; then + log_info "Could not test offloaded functionality" +else + tcflags="skip_sw" + shared_block_test +fi + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/in_netns.sh b/tools/testing/selftests/net/in_netns.sh new file mode 100755 index 000000000000..f57a2eaad069 --- /dev/null +++ b/tools/testing/selftests/net/in_netns.sh @@ -0,0 +1,23 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 +# +# Execute a subprocess in a network namespace + +set -e + +readonly NETNS="ns-$(mktemp -u XXXXXX)" + +setup() { + ip netns add "${NETNS}" + ip -netns "${NETNS}" link set lo up +} + +cleanup() { + ip netns del "${NETNS}" +} + +trap cleanup EXIT +setup + +"$@" +exit "$?" diff --git a/tools/testing/selftests/net/msg_zerocopy.c b/tools/testing/selftests/net/msg_zerocopy.c index e11fe84de0fd..406cc70c571d 100644 --- a/tools/testing/selftests/net/msg_zerocopy.c +++ b/tools/testing/selftests/net/msg_zerocopy.c @@ -14,6 +14,9 @@ * - SOCK_DGRAM * - SOCK_RAW * + * PF_RDS + * - SOCK_SEQPACKET + * * Start this program on two connected hosts, one in send mode and * the other with option '-r' to put it in receiver mode. * @@ -53,6 +56,7 @@ #include <sys/types.h> #include <sys/wait.h> #include <unistd.h> +#include <linux/rds.h> #ifndef SO_EE_ORIGIN_ZEROCOPY #define SO_EE_ORIGIN_ZEROCOPY 5 @@ -164,17 +168,39 @@ static int do_accept(int fd) return fd; } -static bool do_sendmsg(int fd, struct msghdr *msg, bool do_zerocopy) +static void add_zcopy_cookie(struct msghdr *msg, uint32_t cookie) +{ + struct cmsghdr *cm; + + if (!msg->msg_control) + error(1, errno, "NULL cookie"); + cm = (void *)msg->msg_control; + cm->cmsg_len = CMSG_LEN(sizeof(cookie)); + cm->cmsg_level = SOL_RDS; + cm->cmsg_type = RDS_CMSG_ZCOPY_COOKIE; + memcpy(CMSG_DATA(cm), &cookie, sizeof(cookie)); +} + +static bool do_sendmsg(int fd, struct msghdr *msg, bool do_zerocopy, int domain) { int ret, len, i, flags; + static uint32_t cookie; + char ckbuf[CMSG_SPACE(sizeof(cookie))]; len = 0; for (i = 0; i < msg->msg_iovlen; i++) len += msg->msg_iov[i].iov_len; flags = MSG_DONTWAIT; - if (do_zerocopy) + if (do_zerocopy) { flags |= MSG_ZEROCOPY; + if (domain == PF_RDS) { + memset(&msg->msg_control, 0, sizeof(msg->msg_control)); + msg->msg_controllen = CMSG_SPACE(sizeof(cookie)); + msg->msg_control = (struct cmsghdr *)ckbuf; + add_zcopy_cookie(msg, ++cookie); + } + } ret = sendmsg(fd, msg, flags); if (ret == -1 && errno == EAGAIN) @@ -190,6 +216,10 @@ static bool do_sendmsg(int fd, struct msghdr *msg, bool do_zerocopy) if (do_zerocopy && ret) expected_completions++; } + if (do_zerocopy && domain == PF_RDS) { + msg->msg_control = NULL; + msg->msg_controllen = 0; + } return true; } @@ -216,7 +246,9 @@ static void do_sendmsg_corked(int fd, struct msghdr *msg) msg->msg_iov[0].iov_len = payload_len + extra_len; extra_len = 0; - do_sendmsg(fd, msg, do_zerocopy); + do_sendmsg(fd, msg, do_zerocopy, + (cfg_dst_addr.ss_family == AF_INET ? + PF_INET : PF_INET6)); } do_setsockopt(fd, IPPROTO_UDP, UDP_CORK, 0); @@ -300,14 +332,65 @@ static int do_setup_tx(int domain, int type, int protocol) if (cfg_zerocopy) do_setsockopt(fd, SOL_SOCKET, SO_ZEROCOPY, 1); - if (domain != PF_PACKET) + if (domain != PF_PACKET && domain != PF_RDS) if (connect(fd, (void *) &cfg_dst_addr, cfg_alen)) error(1, errno, "connect"); + if (domain == PF_RDS) { + if (bind(fd, (void *) &cfg_src_addr, cfg_alen)) + error(1, errno, "bind"); + } + return fd; } -static bool do_recv_completion(int fd) +static uint32_t do_process_zerocopy_cookies(struct rds_zcopy_cookies *ck) +{ + int i; + + if (ck->num > RDS_MAX_ZCOOKIES) + error(1, 0, "Returned %d cookies, max expected %d\n", + ck->num, RDS_MAX_ZCOOKIES); + for (i = 0; i < ck->num; i++) + if (cfg_verbose >= 2) + fprintf(stderr, "%d\n", ck->cookies[i]); + return ck->num; +} + +static bool do_recvmsg_completion(int fd) +{ + char cmsgbuf[CMSG_SPACE(sizeof(struct rds_zcopy_cookies))]; + struct rds_zcopy_cookies *ck; + struct cmsghdr *cmsg; + struct msghdr msg; + bool ret = false; + + memset(&msg, 0, sizeof(msg)); + msg.msg_control = cmsgbuf; + msg.msg_controllen = sizeof(cmsgbuf); + + if (recvmsg(fd, &msg, MSG_DONTWAIT)) + return ret; + + if (msg.msg_flags & MSG_CTRUNC) + error(1, errno, "recvmsg notification: truncated"); + + for (cmsg = CMSG_FIRSTHDR(&msg); cmsg; cmsg = CMSG_NXTHDR(&msg, cmsg)) { + if (cmsg->cmsg_level == SOL_RDS && + cmsg->cmsg_type == RDS_CMSG_ZCOPY_COMPLETION) { + + ck = (struct rds_zcopy_cookies *)CMSG_DATA(cmsg); + completions += do_process_zerocopy_cookies(ck); + ret = true; + break; + } + error(0, 0, "ignoring cmsg at level %d type %d\n", + cmsg->cmsg_level, cmsg->cmsg_type); + } + return ret; +} + +static bool do_recv_completion(int fd, int domain) { struct sock_extended_err *serr; struct msghdr msg = {}; @@ -316,6 +399,9 @@ static bool do_recv_completion(int fd) int ret, zerocopy; char control[100]; + if (domain == PF_RDS) + return do_recvmsg_completion(fd); + msg.msg_control = control; msg.msg_controllen = sizeof(control); @@ -337,6 +423,7 @@ static bool do_recv_completion(int fd) cm->cmsg_level, cm->cmsg_type); serr = (void *) CMSG_DATA(cm); + if (serr->ee_origin != SO_EE_ORIGIN_ZEROCOPY) error(1, 0, "serr: wrong origin: %u", serr->ee_origin); if (serr->ee_errno != 0) @@ -371,20 +458,20 @@ static bool do_recv_completion(int fd) } /* Read all outstanding messages on the errqueue */ -static void do_recv_completions(int fd) +static void do_recv_completions(int fd, int domain) { - while (do_recv_completion(fd)) {} + while (do_recv_completion(fd, domain)) {} } /* Wait for all remaining completions on the errqueue */ -static void do_recv_remaining_completions(int fd) +static void do_recv_remaining_completions(int fd, int domain) { int64_t tstop = gettimeofday_ms() + cfg_waittime_ms; while (completions < expected_completions && gettimeofday_ms() < tstop) { - if (do_poll(fd, POLLERR)) - do_recv_completions(fd); + if (do_poll(fd, domain == PF_RDS ? POLLIN : POLLERR)) + do_recv_completions(fd, domain); } if (completions < expected_completions) @@ -444,6 +531,13 @@ static void do_tx(int domain, int type, int protocol) msg.msg_iovlen++; } + if (domain == PF_RDS) { + msg.msg_name = &cfg_dst_addr; + msg.msg_namelen = (cfg_dst_addr.ss_family == AF_INET ? + sizeof(struct sockaddr_in) : + sizeof(struct sockaddr_in6)); + } + iov[2].iov_base = payload; iov[2].iov_len = cfg_payload_len; msg.msg_iovlen++; @@ -454,17 +548,17 @@ static void do_tx(int domain, int type, int protocol) if (cfg_cork) do_sendmsg_corked(fd, &msg); else - do_sendmsg(fd, &msg, cfg_zerocopy); + do_sendmsg(fd, &msg, cfg_zerocopy, domain); while (!do_poll(fd, POLLOUT)) { if (cfg_zerocopy) - do_recv_completions(fd); + do_recv_completions(fd, domain); } } while (gettimeofday_ms() < tstop); if (cfg_zerocopy) - do_recv_remaining_completions(fd); + do_recv_remaining_completions(fd, domain); if (close(fd)) error(1, errno, "close"); @@ -610,6 +704,7 @@ static void parse_opts(int argc, char **argv) 40 /* max tcp options */; int c; char *daddr = NULL, *saddr = NULL; + char *cfg_test; cfg_payload_len = max_payload_len; @@ -667,6 +762,14 @@ static void parse_opts(int argc, char **argv) break; } } + + cfg_test = argv[argc - 1]; + if (strcmp(cfg_test, "rds") == 0) { + if (!daddr) + error(1, 0, "-D <server addr> required for PF_RDS\n"); + if (!cfg_rx && !saddr) + error(1, 0, "-S <client addr> required for PF_RDS\n"); + } setup_sockaddr(cfg_family, daddr, &cfg_dst_addr); setup_sockaddr(cfg_family, saddr, &cfg_src_addr); @@ -699,6 +802,8 @@ int main(int argc, char **argv) do_test(cfg_family, SOCK_STREAM, 0); else if (!strcmp(cfg_test, "udp")) do_test(cfg_family, SOCK_DGRAM, 0); + else if (!strcmp(cfg_test, "rds")) + do_test(PF_RDS, SOCK_SEQPACKET, 0); else error(1, 0, "unknown cfg_test %s", cfg_test); diff --git a/tools/testing/selftests/net/psock_fanout.c b/tools/testing/selftests/net/psock_fanout.c index 989f917068d1..bd9b9632c72b 100644 --- a/tools/testing/selftests/net/psock_fanout.c +++ b/tools/testing/selftests/net/psock_fanout.c @@ -50,6 +50,7 @@ #include <linux/filter.h> #include <linux/bpf.h> #include <linux/if_packet.h> +#include <net/if.h> #include <net/ethernet.h> #include <netinet/ip.h> #include <netinet/udp.h> @@ -73,14 +74,29 @@ * @return -1 if mode is bad, a valid socket otherwise */ static int sock_fanout_open(uint16_t typeflags, uint16_t group_id) { + struct sockaddr_ll addr = {0}; int fd, val; - fd = socket(PF_PACKET, SOCK_RAW, htons(ETH_P_IP)); + fd = socket(PF_PACKET, SOCK_RAW, 0); if (fd < 0) { perror("socket packet"); exit(1); } + pair_udp_setfilter(fd); + + addr.sll_family = AF_PACKET; + addr.sll_protocol = htons(ETH_P_IP); + addr.sll_ifindex = if_nametoindex("lo"); + if (addr.sll_ifindex == 0) { + perror("if_nametoindex"); + exit(1); + } + if (bind(fd, (void *) &addr, sizeof(addr))) { + perror("bind packet"); + exit(1); + } + val = (((int) typeflags) << 16) | group_id; if (setsockopt(fd, SOL_PACKET, PACKET_FANOUT, &val, sizeof(val))) { if (close(fd)) { @@ -90,7 +106,6 @@ static int sock_fanout_open(uint16_t typeflags, uint16_t group_id) return -1; } - pair_udp_setfilter(fd); return fd; } @@ -128,6 +143,8 @@ static void sock_fanout_getopts(int fd, uint16_t *typeflags, uint16_t *group_id) static void sock_fanout_set_ebpf(int fd) { + static char log_buf[65536]; + const int len_off = __builtin_offsetof(struct __sk_buff, len); struct bpf_insn prog[] = { { BPF_ALU64 | BPF_MOV | BPF_X, 6, 1, 0, 0 }, @@ -140,7 +157,6 @@ static void sock_fanout_set_ebpf(int fd) { BPF_ALU | BPF_MOV | BPF_K, 0, 0, 0, 0 }, { BPF_JMP | BPF_EXIT, 0, 0, 0, 0 } }; - char log_buf[512]; union bpf_attr attr; int pfd; @@ -228,7 +244,7 @@ static int sock_fanout_read(int fds[], char *rings[], const int expect[]) if ((!(ret[0] == expect[0] && ret[1] == expect[1])) && (!(ret[0] == expect[1] && ret[1] == expect[0]))) { - fprintf(stderr, "ERROR: incorrect queue lengths\n"); + fprintf(stderr, "warning: incorrect queue lengths\n"); return 1; } @@ -347,7 +363,8 @@ static int test_datapath(uint16_t typeflags, int port_off, uint8_t type = typeflags & 0xFF; int fds[2], fds_udp[2][2], ret; - fprintf(stderr, "test: datapath 0x%hx\n", typeflags); + fprintf(stderr, "\ntest: datapath 0x%hx ports %hu,%hu\n", + typeflags, PORT_BASE, PORT_BASE + port_off); fds[0] = sock_fanout_open(typeflags, 0); fds[1] = sock_fanout_open(typeflags, 0); @@ -418,7 +435,7 @@ int main(int argc, char **argv) const int expect_cpu1[2][2] = { { 0, 20 }, { 0, 20 } }; const int expect_bpf[2][2] = { { 15, 5 }, { 15, 20 } }; const int expect_uniqueid[2][2] = { { 20, 20}, { 20, 20 } }; - int port_off = 2, tries = 5, ret; + int port_off = 2, tries = 20, ret; test_control_single(); test_control_group(); @@ -427,10 +444,14 @@ int main(int argc, char **argv) /* find a set of ports that do not collide onto the same socket */ ret = test_datapath(PACKET_FANOUT_HASH, port_off, expect_hash[0], expect_hash[1]); - while (ret && tries--) { + while (ret) { fprintf(stderr, "info: trying alternate ports (%d)\n", tries); ret = test_datapath(PACKET_FANOUT_HASH, ++port_off, expect_hash[0], expect_hash[1]); + if (!--tries) { + fprintf(stderr, "too many collisions\n"); + return 1; + } } ret |= test_datapath(PACKET_FANOUT_HASH | PACKET_FANOUT_FLAG_ROLLOVER, diff --git a/tools/testing/selftests/net/rtnetlink.sh b/tools/testing/selftests/net/rtnetlink.sh index a622eeecc3a6..e6f485235435 100755 --- a/tools/testing/selftests/net/rtnetlink.sh +++ b/tools/testing/selftests/net/rtnetlink.sh @@ -517,6 +517,7 @@ kci_test_gretap() ip link help gretap 2>&1 | grep -q "^Usage:" if [ $? -ne 0 ];then echo "SKIP: gretap: iproute2 too old" + ip netns del "$testns" return 1 fi @@ -543,6 +544,7 @@ kci_test_gretap() if [ $ret -ne 0 ]; then echo "FAIL: gretap" + ip netns del "$testns" return 1 fi echo "PASS: gretap" @@ -565,6 +567,7 @@ kci_test_ip6gretap() ip link help ip6gretap 2>&1 | grep -q "^Usage:" if [ $? -ne 0 ];then echo "SKIP: ip6gretap: iproute2 too old" + ip netns del "$testns" return 1 fi @@ -591,6 +594,7 @@ kci_test_ip6gretap() if [ $ret -ne 0 ]; then echo "FAIL: ip6gretap" + ip netns del "$testns" return 1 fi echo "PASS: ip6gretap" @@ -655,6 +659,7 @@ kci_test_erspan() if [ $ret -ne 0 ]; then echo "FAIL: erspan" + ip netns del "$testns" return 1 fi echo "PASS: erspan" @@ -720,6 +725,7 @@ kci_test_ip6erspan() if [ $ret -ne 0 ]; then echo "FAIL: ip6erspan" + ip netns del "$testns" return 1 fi echo "PASS: ip6erspan" diff --git a/tools/testing/selftests/net/run_afpackettests b/tools/testing/selftests/net/run_afpackettests index 21fe149e3de1..bea079edc278 100755 --- a/tools/testing/selftests/net/run_afpackettests +++ b/tools/testing/selftests/net/run_afpackettests @@ -9,7 +9,7 @@ fi echo "--------------------" echo "running psock_fanout test" echo "--------------------" -./psock_fanout +./in_netns.sh ./psock_fanout if [ $? -ne 0 ]; then echo "[FAIL]" else @@ -19,7 +19,7 @@ fi echo "--------------------" echo "running psock_tpacket test" echo "--------------------" -./psock_tpacket +./in_netns.sh ./psock_tpacket if [ $? -ne 0 ]; then echo "[FAIL]" else diff --git a/tools/testing/selftests/tc-testing/README b/tools/testing/selftests/tc-testing/README index 970ff294fec8..3a0336782d2d 100644 --- a/tools/testing/selftests/tc-testing/README +++ b/tools/testing/selftests/tc-testing/README @@ -14,11 +14,11 @@ REQUIREMENTS * The kernel must have network namespace support -* The kernel must have veth support available, as a veth pair is created +* The kernel must have veth support available, as a veth pair is created prior to running the tests. -* All tc-related features must be built in or available as modules. - To check what is required in current setup run: +* All tc-related features being tested must be built in or available as + modules. To check what is required in current setup run: ./tdc.py -c Note: @@ -44,10 +44,13 @@ using the -p option when running tdc: RUNNING TDC ----------- -To use tdc, root privileges are required. tdc will not run otherwise. +To use tdc, root privileges are required. This is because the +commands being tested must be run as root. The code that enforces +execution by root uid has been moved into a plugin (see PLUGIN +ARCHITECTURE, below). -All tests are executed inside a network namespace to prevent conflicts -within the host. +If nsPlugin is linked, all tests are executed inside a network +namespace to prevent conflicts within the host. Running tdc without any arguments will run all tests. Refer to the section on command line arguments for more information, or run: @@ -59,6 +62,33 @@ output captured from the failing test will be printed immediately following the failed test in the TAP output. +OVERVIEW OF TDC EXECUTION +------------------------- + +One run of tests is considered a "test suite" (this will be refined in the +future). A test suite has one or more test cases in it. + +A test case has four stages: + + - setup + - execute + - verify + - teardown + +The setup and teardown stages can run zero or more commands. The setup +stage does some setup if the test needs it. The teardown stage undoes +the setup and returns the system to a "neutral" state so any other test +can be run next. These two stages require any commands run to return +success, but do not otherwise verify the results. + +The execute and verify stages each run one command. The execute stage +tests the return code against one or more acceptable values. The +verify stage checks the return code for success, and also compares +the stdout with a regular expression. + +Each of the commands in any stage will run in a shell instance. + + USER-DEFINED CONSTANTS ---------------------- @@ -70,23 +100,132 @@ executed as part of the test. More will be added as test cases require. Example: $TC qdisc add dev $DEV1 ingress +The NAMES values are used to substitute into the commands in the test cases. + COMMAND LINE ARGUMENTS ---------------------- Run tdc.py -h to see the full list of available arguments. --p PATH Specify the tc executable located at PATH to be used on this - test run --c Show the available test case categories in this test file --c CATEGORY Run only tests that belong to CATEGORY --f FILE Read test cases from the JSON file named FILE --l [CATEGORY] List all test cases in the JSON file. If CATEGORY is - specified, list test cases matching that category. --s ID Show the test case matching ID --e ID Execute the test case identified by ID --i Generate unique ID numbers for test cases with no existing - ID number +usage: tdc.py [-h] [-p PATH] [-D DIR [DIR ...]] [-f FILE [FILE ...]] + [-c [CATG [CATG ...]]] [-e ID [ID ...]] [-l] [-s] [-i] [-v] + [-d DEVICE] [-n NS] [-V] + +Linux TC unit tests + +optional arguments: + -h, --help show this help message and exit + -p PATH, --path PATH The full path to the tc executable to use + -v, --verbose Show the commands that are being run + -d DEVICE, --device DEVICE + Execute the test case in flower category + +selection: + select which test cases: files plus directories; filtered by categories + plus testids + + -D DIR [DIR ...], --directory DIR [DIR ...] + Collect tests from the specified directory(ies) + (default [tc-tests]) + -f FILE [FILE ...], --file FILE [FILE ...] + Run tests from the specified file(s) + -c [CATG [CATG ...]], --category [CATG [CATG ...]] + Run tests only from the specified category/ies, or if + no category/ies is/are specified, list known + categories. + -e ID [ID ...], --execute ID [ID ...] + Execute the specified test cases with specified IDs + +action: + select action to perform on selected test cases + + -l, --list List all test cases, or those only within the + specified category + -s, --show Display the selected test cases + -i, --id Generate ID numbers for new test cases + +netns: + options for nsPlugin(run commands in net namespace) + + -n NS, --namespace NS + Run commands in namespace NS + +valgrind: + options for valgrindPlugin (run command under test under Valgrind) + + -V, --valgrind Run commands under valgrind + + +PLUGIN ARCHITECTURE +------------------- + +There is now a plugin architecture, and some of the functionality that +was in the tdc.py script has been moved into the plugins. + +The plugins are in the directory plugin-lib. The are executed from +directory plugins. Put symbolic links from plugins to plugin-lib, +and name them according to the order you want them to run. + +Example: + +bjb@bee:~/work/tc-testing$ ls -l plugins +total 4 +lrwxrwxrwx 1 bjb bjb 27 Oct 4 16:12 10-rootPlugin.py -> ../plugin-lib/rootPlugin.py +lrwxrwxrwx 1 bjb bjb 25 Oct 12 17:55 20-nsPlugin.py -> ../plugin-lib/nsPlugin.py +-rwxr-xr-x 1 bjb bjb 0 Sep 29 15:56 __init__.py + +The plugins are a subclass of TdcPlugin, defined in TdcPlugin.py and +must be called "SubPlugin" so tdc can find them. They are +distinguished from each other in the python program by their module +name. + +This base class supplies "hooks" to run extra functions. These hooks are as follows: + +pre- and post-suite +pre- and post-case +pre- and post-execute stage +adjust-command (runs in all stages and receives the stage name) + +The pre-suite hook receives the number of tests and an array of test ids. +This allows you to dump out the list of skipped tests in the event of a +failure during setup or teardown stage. + +The pre-case hook receives the ordinal number and test id of the current test. + +The adjust-command hook receives the stage id (see list below) and the +full command to be executed. This allows for last-minute adjustment +of the command. + +The stages are identified by the following strings: + + - pre (pre-suite) + - setup + - command + - verify + - teardown + - post (post-suite) + + +To write a plugin, you need to inherit from TdcPlugin in +TdcPlugin.py. To use the plugin, you have to put the +implementation file in plugin-lib, and add a symbolic link to it from +plugins. It will be detected at run time and invoked at the +appropriate times. There are a few examples in the plugin-lib +directory: + + - rootPlugin.py: + implements the enforcement of running as root + - nsPlugin.py: + sets up a network namespace and runs all commands in that namespace + - valgrindPlugin.py + runs each command in the execute stage under valgrind, + and checks for leaks. + This plugin will output an extra test for each test in the test file, + one is the existing output as to whether the test passed or failed, + and the other is a test whether the command leaked memory or not. + (This one is a preliminary version, it may not work quite right yet, + but the overall template is there and it should only need tweaks.) ACKNOWLEDGEMENTS diff --git a/tools/testing/selftests/tc-testing/TODO.txt b/tools/testing/selftests/tc-testing/TODO.txt index 6a266d811a78..c40698557e2f 100644 --- a/tools/testing/selftests/tc-testing/TODO.txt +++ b/tools/testing/selftests/tc-testing/TODO.txt @@ -5,6 +5,27 @@ tc Testing Suite To-Do list: - Add support for multiple versions of tc to run successively -- Improve error messages when tdc aborts its run +- Improve error messages when tdc aborts its run. Partially done - still + need to better handle problems in pre- and post-suite. -- Allow tdc to write its results to file +- Use python logger module for debug/verbose output + +- Allow tdc to write its results to file. + Maybe use python logger module for this too. + +- A better implementation of the "hooks". Currently, every plugin + will attempt to run a function at every hook point. Could be + changed so that plugin __init__ methods will register functions to + be run in the various predefined times. Then if a plugin does not + require action at a specific point, no penalty will be paid for + trying to run a function that will do nothing. + +- Proper exception handling - make an exception class and use it + +- a TestCase class, for easier testcase handling, searching, comparison + +- a TestSuite class + and a way to configure a test suite, + to automate running multiple "test suites" with different requirements + +- super simple test case example using ls, touch, etc diff --git a/tools/testing/selftests/tc-testing/TdcPlugin.py b/tools/testing/selftests/tc-testing/TdcPlugin.py new file mode 100644 index 000000000000..3ee9a6dacb52 --- /dev/null +++ b/tools/testing/selftests/tc-testing/TdcPlugin.py @@ -0,0 +1,74 @@ +#!/usr/bin/env python3 + +class TdcPlugin: + def __init__(self): + super().__init__() + print(' -- {}.__init__'.format(self.sub_class)) + + def pre_suite(self, testcount, testidlist): + '''run commands before test_runner goes into a test loop''' + self.testcount = testcount + self.testidlist = testidlist + if self.args.verbose > 1: + print(' -- {}.pre_suite'.format(self.sub_class)) + + def post_suite(self, index): + '''run commands after test_runner completes the test loop + index is the last ordinal number of test that was attempted''' + if self.args.verbose > 1: + print(' -- {}.post_suite'.format(self.sub_class)) + + def pre_case(self, test_ordinal, testid): + '''run commands before test_runner does one test''' + if self.args.verbose > 1: + print(' -- {}.pre_case'.format(self.sub_class)) + self.args.testid = testid + self.args.test_ordinal = test_ordinal + + def post_case(self): + '''run commands after test_runner does one test''' + if self.args.verbose > 1: + print(' -- {}.post_case'.format(self.sub_class)) + + def pre_execute(self): + '''run command before test-runner does the execute step''' + if self.args.verbose > 1: + print(' -- {}.pre_execute'.format(self.sub_class)) + + def post_execute(self): + '''run command after test-runner does the execute step''' + if self.args.verbose > 1: + print(' -- {}.post_execute'.format(self.sub_class)) + + def adjust_command(self, stage, command): + '''adjust the command''' + if self.args.verbose > 1: + print(' -- {}.adjust_command {}'.format(self.sub_class, stage)) + + # if stage == 'pre': + # pass + # elif stage == 'setup': + # pass + # elif stage == 'execute': + # pass + # elif stage == 'verify': + # pass + # elif stage == 'teardown': + # pass + # elif stage == 'post': + # pass + # else: + # pass + + return command + + def add_args(self, parser): + '''Get the plugin args from the command line''' + self.argparser = parser + return self.argparser + + def check_args(self, args, remaining): + '''Check that the args are set correctly''' + self.args = args + if self.args.verbose > 1: + print(' -- {}.check_args'.format(self.sub_class)) diff --git a/tools/testing/selftests/tc-testing/creating-plugins/AddingPlugins.txt b/tools/testing/selftests/tc-testing/creating-plugins/AddingPlugins.txt new file mode 100644 index 000000000000..c18f88d09360 --- /dev/null +++ b/tools/testing/selftests/tc-testing/creating-plugins/AddingPlugins.txt @@ -0,0 +1,104 @@ +tdc - Adding plugins for tdc + +Author: Brenda J. Butler - bjb@mojatatu.com + +ADDING PLUGINS +-------------- + +A new plugin should be written in python as a class that inherits from TdcPlugin. +There are some examples in plugin-lib. + +The plugin can be used to add functionality to the test framework, +such as: + +- adding commands to be run before and/or after the test suite +- adding commands to be run before and/or after the test cases +- adding commands to be run before and/or after the execute phase of the test cases +- ability to alter the command to be run in any phase: + pre (the pre-suite stage) + prepare + execute + verify + teardown + post (the post-suite stage) +- ability to add to the command line args, and use them at run time + + +The functions in the class should follow the following interfaces: + + def __init__(self) + def pre_suite(self, testcount, testidlist) # see "PRE_SUITE" below + def post_suite(self, ordinal) # see "SKIPPING" below + def pre_case(self, test_ordinal, testid) # see "PRE_CASE" below + def post_case(self) + def pre_execute(self) + def post_execute(self) + def adjust_command(self, stage, command) # see "ADJUST" below + def add_args(self, parser) # see "ADD_ARGS" below + def check_args(self, args, remaining) # see "CHECK_ARGS" below + + +PRE_SUITE + +This method takes a testcount (number of tests to be run) and +testidlist (array of test ids for tests that will be run). This is +useful for various things, including when an exception occurs and the +rest of the tests must be skipped. The info is stored in the object, +and the post_suite method can refer to it when dumping the "skipped" +TAP output. The tdc.py script will do that for the test suite as +defined in the test case, but if the plugin is being used to run extra +tests on each test (eg, check for memory leaks on associated +co-processes) then that other tap output can be generated in the +post-suite method using this info passed in to the pre_suite method. + + +SKIPPING + +The post_suite method will receive the ordinal number of the last +test to be attempted. It can use this info when outputting +the TAP output for the extra test cases. + + +PRE_CASE + +The pre_case method will receive the ordinal number of the test +and the test id. Useful for outputing the extra test results. + + +ADJUST + +The adjust_command method receives a string representing +the execution stage and a string which is the actual command to be +executed. The plugin can adjust the command, based on the stage of +execution. + +The stages are represented by the following strings: + + 'pre' + 'setup' + 'command' + 'verify' + 'teardown' + 'post' + +The adjust_command method must return the adjusted command so tdc +can use it. + + +ADD_ARGS + +The add_args method receives the argparser object and can add +arguments to it. Care should be taken that the new arguments do not +conflict with any from tdc.py or from other plugins that will be used +concurrently. + +The add_args method should return the argparser object. + + +CHECK_ARGS + +The check_args method is so that the plugin can do validation on +the args, if needed. If there is a problem, and Exception should +be raised, with a string that explains the problem. + +eg: raise Exception('plugin xxx, arg -y is wrong, fix it') diff --git a/tools/testing/selftests/tc-testing/creating-testcases/AddingTestCases.txt b/tools/testing/selftests/tc-testing/creating-testcases/AddingTestCases.txt index 00438331ba47..17b267dedbd9 100644 --- a/tools/testing/selftests/tc-testing/creating-testcases/AddingTestCases.txt +++ b/tools/testing/selftests/tc-testing/creating-testcases/AddingTestCases.txt @@ -12,14 +12,18 @@ template.json for the required JSON format for test cases. Include the 'id' field, but do not assign a value. Running tdc with the -i option will generate a unique ID for that test case. -tdc will recursively search the 'tc' subdirectory for .json files. Any -test case files you create in these directories will automatically be included. -If you wish to store your custom test cases elsewhere, be sure to run tdc -with the -f argument and the path to your file. +tdc will recursively search the 'tc-tests' subdirectory (or the +directories named with the -D option) for .json files. Any test case +files you create in these directories will automatically be included. +If you wish to store your custom test cases elsewhere, be sure to run +tdc with the -f argument and the path to your file, or the -D argument +and the path to your directory(ies). -Be aware of required escape characters in the JSON data - particularly when -defining the match pattern. Refer to the tctests.json file for examples when -in doubt. +Be aware of required escape characters in the JSON data - particularly +when defining the match pattern. Refer to the supplied json test files +for examples when in doubt. The match pattern is written in json, and +will be used by python. So the match pattern will be a python regular +expression, but should be written using json syntax. TEST CASE STRUCTURE @@ -69,7 +73,8 @@ SETUP/TEARDOWN ERRORS If an error is detected during the setup/teardown process, execution of the tests will immediately stop with an error message and the namespace in which the tests are run will be destroyed. This is to prevent inaccurate results -in the test cases. +in the test cases. tdc will output a series of TAP results for the skipped +tests. Repeated failures of the setup/teardown may indicate a problem with the test case, or possibly even a bug in one of the commands that are not being tested. @@ -79,3 +84,17 @@ so that it doesn't halt the script for an error that doesn't matter. Turn the individual command into a list, with the command being first, followed by all acceptable exit codes for the command. +Example: + +A pair of setup commands. The first can have exit code 0, 1 or 255, the +second must have exit code 0. + + "setup": [ + [ + "$TC actions flush action gact", + 0, + 1, + 255 + ], + "$TC actions add action reclassify index 65536" + ], diff --git a/tools/testing/selftests/tc-testing/plugin-lib/README-PLUGINS b/tools/testing/selftests/tc-testing/plugin-lib/README-PLUGINS new file mode 100644 index 000000000000..aa8a2669702b --- /dev/null +++ b/tools/testing/selftests/tc-testing/plugin-lib/README-PLUGINS @@ -0,0 +1,27 @@ +tdc.py will look for plugins in a directory plugins off the cwd. +Make a set of numbered symbolic links from there to the actual plugins. +Eg: + +tdc.py +plugin-lib/ +plugins/ + __init__.py + 10-rootPlugin.py -> ../plugin-lib/rootPlugin.py + 20-valgrindPlugin.py -> ../plugin-lib/valgrindPlugin.py + 30-nsPlugin.py -> ../plugin-lib/nsPlugin.py + + +tdc.py will find them and use them. + + +rootPlugin + Check if the uid is root. If not, bail out. + +valgrindPlugin + Run the command under test with valgrind, and produce an extra set of TAP results for the memory tests. + This plugin will write files to the cwd, called vgnd-xxx.log. These will contain + the valgrind output for test xxx. Any file matching the glob 'vgnd-*.log' will be + deleted at the end of the run. + +nsPlugin + Run all the commands in a network namespace. diff --git a/tools/testing/selftests/tc-testing/plugin-lib/nsPlugin.py b/tools/testing/selftests/tc-testing/plugin-lib/nsPlugin.py new file mode 100644 index 000000000000..a194b1af2b30 --- /dev/null +++ b/tools/testing/selftests/tc-testing/plugin-lib/nsPlugin.py @@ -0,0 +1,141 @@ +import os +import signal +from string import Template +import subprocess +import time +from TdcPlugin import TdcPlugin + +from tdc_config import * + +class SubPlugin(TdcPlugin): + def __init__(self): + self.sub_class = 'ns/SubPlugin' + super().__init__() + + def pre_suite(self, testcount, testidlist): + '''run commands before test_runner goes into a test loop''' + super().pre_suite(testcount, testidlist) + + if self.args.namespace: + self._ns_create() + + def post_suite(self, index): + '''run commands after test_runner goes into a test loop''' + super().post_suite(index) + if self.args.verbose: + print('{}.post_suite'.format(self.sub_class)) + + if self.args.namespace: + self._ns_destroy() + + def add_args(self, parser): + super().add_args(parser) + self.argparser_group = self.argparser.add_argument_group( + 'netns', + 'options for nsPlugin(run commands in net namespace)') + self.argparser_group.add_argument( + '-n', '--namespace', action='store_true', + help='Run commands in namespace') + return self.argparser + + def adjust_command(self, stage, command): + super().adjust_command(stage, command) + cmdform = 'list' + cmdlist = list() + + if not self.args.namespace: + return command + + if self.args.verbose: + print('{}.adjust_command'.format(self.sub_class)) + + if not isinstance(command, list): + cmdform = 'str' + cmdlist = command.split() + else: + cmdlist = command + if stage == 'setup' or stage == 'execute' or stage == 'verify' or stage == 'teardown': + if self.args.verbose: + print('adjust_command: stage is {}; inserting netns stuff in command [{}] list [{}]'.format(stage, command, cmdlist)) + cmdlist.insert(0, self.args.NAMES['NS']) + cmdlist.insert(0, 'exec') + cmdlist.insert(0, 'netns') + cmdlist.insert(0, 'ip') + else: + pass + + if cmdform == 'str': + command = ' '.join(cmdlist) + else: + command = cmdlist + + if self.args.verbose: + print('adjust_command: return command [{}]'.format(command)) + return command + + def _ns_create(self): + ''' + Create the network namespace in which the tests will be run and set up + the required network devices for it. + ''' + if self.args.namespace: + cmd = 'ip netns add {}'.format(self.args.NAMES['NS']) + self._exec_cmd('pre', cmd) + cmd = 'ip link add $DEV0 type veth peer name $DEV1' + self._exec_cmd('pre', cmd) + cmd = 'ip link set $DEV1 netns {}'.format(self.args.NAMES['NS']) + self._exec_cmd('pre', cmd) + cmd = 'ip link set $DEV0 up' + self._exec_cmd('pre', cmd) + cmd = 'ip -n {} link set $DEV1 up'.format(self.args.NAMES['NS']) + self._exec_cmd('pre', cmd) + if self.args.device: + cmd = 'ip link set $DEV2 netns {}'.format(self.args.NAMES['NS']) + self._exec_cmd('pre', cmd) + cmd = 'ip -n {} link set $DEV2 up'.format(self.args.NAMES['NS']) + self._exec_cmd('pre', cmd) + + def _ns_destroy(self): + ''' + Destroy the network namespace for testing (and any associated network + devices as well) + ''' + if self.args.namespace: + cmd = 'ip netns delete {}'.format(self.args.NAMES['NS']) + self._exec_cmd('post', cmd) + + def _exec_cmd(self, stage, command): + ''' + Perform any required modifications on an executable command, then run + it in a subprocess and return the results. + ''' + if '$' in command: + command = self._replace_keywords(command) + + self.adjust_command(stage, command) + if self.args.verbose: + print('_exec_cmd: command "{}"'.format(command)) + proc = subprocess.Popen(command, + shell=True, + stdout=subprocess.PIPE, + stderr=subprocess.PIPE, + env=ENVIR) + (rawout, serr) = proc.communicate() + + if proc.returncode != 0 and len(serr) > 0: + foutput = serr.decode("utf-8") + else: + foutput = rawout.decode("utf-8") + + proc.stdout.close() + proc.stderr.close() + return proc, foutput + + def _replace_keywords(self, cmd): + """ + For a given executable command, substitute any known + variables contained within NAMES with the correct values + """ + tcmd = Template(cmd) + subcmd = tcmd.safe_substitute(self.args.NAMES) + return subcmd diff --git a/tools/testing/selftests/tc-testing/plugin-lib/rootPlugin.py b/tools/testing/selftests/tc-testing/plugin-lib/rootPlugin.py new file mode 100644 index 000000000000..e36775bd4d12 --- /dev/null +++ b/tools/testing/selftests/tc-testing/plugin-lib/rootPlugin.py @@ -0,0 +1,19 @@ +import os +import sys +from TdcPlugin import TdcPlugin + +from tdc_config import * + + +class SubPlugin(TdcPlugin): + def __init__(self): + self.sub_class = 'root/SubPlugin' + super().__init__() + + def pre_suite(self, testcount, testidlist): + # run commands before test_runner goes into a test loop + super().pre_suite(testcount, testidlist) + + if os.geteuid(): + print('This script must be run with root privileges', file=sys.stderr) + exit(1) diff --git a/tools/testing/selftests/tc-testing/plugin-lib/valgrindPlugin.py b/tools/testing/selftests/tc-testing/plugin-lib/valgrindPlugin.py new file mode 100644 index 000000000000..477a7bd7d7fb --- /dev/null +++ b/tools/testing/selftests/tc-testing/plugin-lib/valgrindPlugin.py @@ -0,0 +1,142 @@ +''' +run the command under test, under valgrind and collect memory leak info +as a separate test. +''' + + +import os +import re +import signal +from string import Template +import subprocess +import time +from TdcPlugin import TdcPlugin + +from tdc_config import * + +def vp_extract_num_from_string(num_as_string_maybe_with_commas): + return int(num_as_string_maybe_with_commas.replace(',','')) + +class SubPlugin(TdcPlugin): + def __init__(self): + self.sub_class = 'valgrind/SubPlugin' + self.tap = '' + super().__init__() + + def pre_suite(self, testcount, testidlist): + '''run commands before test_runner goes into a test loop''' + super().pre_suite(testcount, testidlist) + if self.args.verbose > 1: + print('{}.pre_suite'.format(self.sub_class)) + if self.args.valgrind: + self._add_to_tap('1..{}\n'.format(self.testcount)) + + def post_suite(self, index): + '''run commands after test_runner goes into a test loop''' + super().post_suite(index) + self._add_to_tap('\n|---\n') + if self.args.verbose > 1: + print('{}.post_suite'.format(self.sub_class)) + print('{}'.format(self.tap)) + if self.args.verbose < 4: + subprocess.check_output('rm -f vgnd-*.log', shell=True) + + def add_args(self, parser): + super().add_args(parser) + self.argparser_group = self.argparser.add_argument_group( + 'valgrind', + 'options for valgrindPlugin (run command under test under Valgrind)') + + self.argparser_group.add_argument( + '-V', '--valgrind', action='store_true', + help='Run commands under valgrind') + + return self.argparser + + def adjust_command(self, stage, command): + super().adjust_command(stage, command) + cmdform = 'list' + cmdlist = list() + + if not self.args.valgrind: + return command + + if self.args.verbose > 1: + print('{}.adjust_command'.format(self.sub_class)) + + if not isinstance(command, list): + cmdform = 'str' + cmdlist = command.split() + else: + cmdlist = command + + if stage == 'execute': + if self.args.verbose > 1: + print('adjust_command: stage is {}; inserting valgrind stuff in command [{}] list [{}]'. + format(stage, command, cmdlist)) + cmdlist.insert(0, '--track-origins=yes') + cmdlist.insert(0, '--show-leak-kinds=definite,indirect') + cmdlist.insert(0, '--leak-check=full') + cmdlist.insert(0, '--log-file=vgnd-{}.log'.format(self.args.testid)) + cmdlist.insert(0, '-v') # ask for summary of non-leak errors + cmdlist.insert(0, ENVIR['VALGRIND_BIN']) + else: + pass + + if cmdform == 'str': + command = ' '.join(cmdlist) + else: + command = cmdlist + + if self.args.verbose > 1: + print('adjust_command: return command [{}]'.format(command)) + return command + + def post_execute(self): + if not self.args.valgrind: + return + + self.definitely_lost_re = re.compile( + r'definitely lost:\s+([,0-9]+)\s+bytes in\s+([,0-9]+)\sblocks', re.MULTILINE | re.DOTALL) + self.indirectly_lost_re = re.compile( + r'indirectly lost:\s+([,0-9]+)\s+bytes in\s+([,0-9]+)\s+blocks', re.MULTILINE | re.DOTALL) + self.possibly_lost_re = re.compile( + r'possibly lost:\s+([,0-9]+)bytes in\s+([,0-9]+)\s+blocks', re.MULTILINE | re.DOTALL) + self.non_leak_error_re = re.compile( + r'ERROR SUMMARY:\s+([,0-9]+) errors from\s+([,0-9]+)\s+contexts', re.MULTILINE | re.DOTALL) + + def_num = 0 + ind_num = 0 + pos_num = 0 + nle_num = 0 + + # what about concurrent test runs? Maybe force them to be in different directories? + with open('vgnd-{}.log'.format(self.args.testid)) as vfd: + content = vfd.read() + def_mo = self.definitely_lost_re.search(content) + ind_mo = self.indirectly_lost_re.search(content) + pos_mo = self.possibly_lost_re.search(content) + nle_mo = self.non_leak_error_re.search(content) + + if def_mo: + def_num = int(def_mo.group(2)) + if ind_mo: + ind_num = int(ind_mo.group(2)) + if pos_mo: + pos_num = int(pos_mo.group(2)) + if nle_mo: + nle_num = int(nle_mo.group(1)) + + mem_results = '' + if (def_num > 0) or (ind_num > 0) or (pos_num > 0) or (nle_num > 0): + mem_results += 'not ' + + mem_results += 'ok {} - {}-mem # {}\n'.format( + self.args.test_ordinal, self.args.testid, 'memory leak check') + self._add_to_tap(mem_results) + if mem_results.startswith('not '): + print('{}'.format(content)) + self._add_to_tap(content) + + def _add_to_tap(self, more_tap_output): + self.tap += more_tap_output diff --git a/tools/testing/selftests/tc-testing/plugins/__init__.py b/tools/testing/selftests/tc-testing/plugins/__init__.py new file mode 100644 index 000000000000..e69de29bb2d1 --- /dev/null +++ b/tools/testing/selftests/tc-testing/plugins/__init__.py diff --git a/tools/testing/selftests/tc-testing/tdc.py b/tools/testing/selftests/tc-testing/tdc.py index fc373fdf2bdc..241eea37e4a4 100755 --- a/tools/testing/selftests/tc-testing/tdc.py +++ b/tools/testing/selftests/tc-testing/tdc.py @@ -11,16 +11,96 @@ import re import os import sys import argparse +import importlib import json import subprocess +import time +import traceback from collections import OrderedDict from string import Template from tdc_config import * from tdc_helper import * - -USE_NS = True +import TdcPlugin + + +class PluginMgrTestFail(Exception): + def __init__(self, stage, output, message): + self.stage = stage + self.output = output + self.message = message + +class PluginMgr: + def __init__(self, argparser): + super().__init__() + self.plugins = {} + self.plugin_instances = [] + self.args = [] + self.argparser = argparser + + # TODO, put plugins in order + plugindir = os.getenv('TDC_PLUGIN_DIR', './plugins') + for dirpath, dirnames, filenames in os.walk(plugindir): + for fn in filenames: + if (fn.endswith('.py') and + not fn == '__init__.py' and + not fn.startswith('#') and + not fn.startswith('.#')): + mn = fn[0:-3] + foo = importlib.import_module('plugins.' + mn) + self.plugins[mn] = foo + self.plugin_instances.append(foo.SubPlugin()) + + def call_pre_suite(self, testcount, testidlist): + for pgn_inst in self.plugin_instances: + pgn_inst.pre_suite(testcount, testidlist) + + def call_post_suite(self, index): + for pgn_inst in reversed(self.plugin_instances): + pgn_inst.post_suite(index) + + def call_pre_case(self, test_ordinal, testid): + for pgn_inst in self.plugin_instances: + try: + pgn_inst.pre_case(test_ordinal, testid) + except Exception as ee: + print('exception {} in call to pre_case for {} plugin'. + format(ee, pgn_inst.__class__)) + print('test_ordinal is {}'.format(test_ordinal)) + print('testid is {}'.format(testid)) + raise + + def call_post_case(self): + for pgn_inst in reversed(self.plugin_instances): + pgn_inst.post_case() + + def call_pre_execute(self): + for pgn_inst in self.plugin_instances: + pgn_inst.pre_execute() + + def call_post_execute(self): + for pgn_inst in reversed(self.plugin_instances): + pgn_inst.post_execute() + + def call_add_args(self, parser): + for pgn_inst in self.plugin_instances: + parser = pgn_inst.add_args(parser) + return parser + + def call_check_args(self, args, remaining): + for pgn_inst in self.plugin_instances: + pgn_inst.check_args(args, remaining) + + def call_adjust_command(self, stage, command): + for pgn_inst in self.plugin_instances: + command = pgn_inst.adjust_command(stage, command) + return command + + @staticmethod + def _make_argparser(args): + self.argparser = argparse.ArgumentParser( + description='Linux TC unit tests') def replace_keywords(cmd): @@ -33,21 +113,24 @@ def replace_keywords(cmd): return subcmd -def exec_cmd(command, nsonly=True): +def exec_cmd(args, pm, stage, command): """ Perform any required modifications on an executable command, then run it in a subprocess and return the results. """ - if (USE_NS and nsonly): - command = 'ip netns exec $NS ' + command - + if len(command.strip()) == 0: + return None, None if '$' in command: command = replace_keywords(command) + command = pm.call_adjust_command(stage, command) + if args.verbose > 0: + print('command "{}"'.format(command)) proc = subprocess.Popen(command, shell=True, stdout=subprocess.PIPE, - stderr=subprocess.PIPE) + stderr=subprocess.PIPE, + env=ENVIR) (rawout, serr) = proc.communicate() if proc.returncode != 0 and len(serr) > 0: @@ -60,36 +143,93 @@ def exec_cmd(command, nsonly=True): return proc, foutput -def prepare_env(cmdlist): +def prepare_env(args, pm, stage, prefix, cmdlist, output = None): """ - Execute the setup/teardown commands for a test case. Optionally - terminate test execution if the command fails. + Execute the setup/teardown commands for a test case. + Optionally terminate test execution if the command fails. """ + if args.verbose > 0: + print('{}'.format(prefix)) for cmdinfo in cmdlist: - if (type(cmdinfo) == list): + if isinstance(cmdinfo, list): exit_codes = cmdinfo[1:] cmd = cmdinfo[0] else: exit_codes = [0] cmd = cmdinfo - if (len(cmd) == 0): + if not cmd: continue - (proc, foutput) = exec_cmd(cmd) + (proc, foutput) = exec_cmd(args, pm, stage, cmd) + + if proc and (proc.returncode not in exit_codes): + print('', file=sys.stderr) + print("{} *** Could not execute: \"{}\"".format(prefix, cmd), + file=sys.stderr) + print("\n{} *** Error message: \"{}\"".format(prefix, foutput), + file=sys.stderr) + print("\n{} *** Aborting test run.".format(prefix), file=sys.stderr) + print("\n\n{} *** stdout ***".format(proc.stdout), file=sys.stderr) + print("\n\n{} *** stderr ***".format(proc.stderr), file=sys.stderr) + raise PluginMgrTestFail( + stage, output, + '"{}" did not complete successfully'.format(prefix)) + +def run_one_test(pm, args, index, tidx): + result = True + tresult = "" + tap = "" + if args.verbose > 0: + print("\t====================\n=====> ", end="") + print("Test " + tidx["id"] + ": " + tidx["name"]) + + pm.call_pre_case(index, tidx['id']) + prepare_env(args, pm, 'setup', "-----> prepare stage", tidx["setup"]) + + if (args.verbose > 0): + print('-----> execute stage') + pm.call_pre_execute() + (p, procout) = exec_cmd(args, pm, 'execute', tidx["cmdUnderTest"]) + exit_code = p.returncode + pm.call_post_execute() + + if (exit_code != int(tidx["expExitCode"])): + result = False + print("exit:", exit_code, int(tidx["expExitCode"])) + print(procout) + else: + if args.verbose > 0: + print('-----> verify stage') + match_pattern = re.compile( + str(tidx["matchPattern"]), re.DOTALL | re.MULTILINE) + (p, procout) = exec_cmd(args, pm, 'verify', tidx["verifyCmd"]) + if procout: + match_index = re.findall(match_pattern, procout) + if len(match_index) != int(tidx["matchCount"]): + result = False + elif int(tidx["matchCount"]) != 0: + result = False + + if not result: + tresult += 'not ' + tresult += 'ok {} - {} # {}\n'.format(str(index), tidx['id'], tidx['name']) + tap += tresult + + if result == False: + if procout: + tap += procout + else: + tap += 'No output!\n' - if proc.returncode not in exit_codes: - print - print("Could not execute:") - print(cmd) - print("\nError message:") - print(foutput) - print("\nAborting test run.") - ns_destroy() - exit(1) + prepare_env(args, pm, 'teardown', '-----> teardown stage', tidx['teardown'], procout) + pm.call_post_case() + index += 1 -def test_runner(filtered_tests, args): + return tap + +def test_runner(pm, args, filtered_tests): """ Driver function for the unit tests. @@ -101,75 +241,86 @@ def test_runner(filtered_tests, args): testlist = filtered_tests tcount = len(testlist) index = 1 - tap = str(index) + ".." + str(tcount) + "\n" - + tap = '' + badtest = None + stage = None + emergency_exit = False + emergency_exit_message = '' + + if args.notap: + if args.verbose: + tap = 'notap requested: omitting test plan\n' + else: + tap = str(index) + ".." + str(tcount) + "\n" + try: + pm.call_pre_suite(tcount, [tidx['id'] for tidx in testlist]) + except Exception as ee: + ex_type, ex, ex_tb = sys.exc_info() + print('Exception {} {} (caught in pre_suite).'. + format(ex_type, ex)) + # when the extra print statements are uncommented, + # the traceback does not appear between them + # (it appears way earlier in the tdc.py output) + # so don't bother ... + # print('--------------------(') + # print('traceback') + traceback.print_tb(ex_tb) + # print('--------------------)') + emergency_exit_message = 'EMERGENCY EXIT, call_pre_suite failed with exception {} {}\n'.format(ex_type, ex) + emergency_exit = True + stage = 'pre-SUITE' + + if emergency_exit: + pm.call_post_suite(index) + return emergency_exit_message + if args.verbose > 1: + print('give test rig 2 seconds to stabilize') + time.sleep(2) for tidx in testlist: - result = True - tresult = "" if "flower" in tidx["category"] and args.device == None: + if args.verbose > 1: + print('Not executing test {} {} because DEV2 not defined'. + format(tidx['id'], tidx['name'])) continue - print("Test " + tidx["id"] + ": " + tidx["name"]) - prepare_env(tidx["setup"]) - (p, procout) = exec_cmd(tidx["cmdUnderTest"]) - exit_code = p.returncode - - if (exit_code != int(tidx["expExitCode"])): - result = False - print("exit:", exit_code, int(tidx["expExitCode"])) - print(procout) - else: - match_pattern = re.compile(str(tidx["matchPattern"]), re.DOTALL) - (p, procout) = exec_cmd(tidx["verifyCmd"]) - match_index = re.findall(match_pattern, procout) - if len(match_index) != int(tidx["matchCount"]): - result = False - - if result == True: - tresult += "ok " - else: - tresult += "not ok " - tap += tresult + str(index) + " " + tidx["id"] + " " + tidx["name"] + "\n" - - if result == False: - tap += procout - - prepare_env(tidx["teardown"]) + try: + badtest = tidx # in case it goes bad + tap += run_one_test(pm, args, index, tidx) + except PluginMgrTestFail as pmtf: + ex_type, ex, ex_tb = sys.exc_info() + stage = pmtf.stage + message = pmtf.message + output = pmtf.output + print(message) + print('Exception {} {} (caught in test_runner, running test {} {} {} stage {})'. + format(ex_type, ex, index, tidx['id'], tidx['name'], stage)) + print('---------------') + print('traceback') + traceback.print_tb(ex_tb) + print('---------------') + if stage == 'teardown': + print('accumulated output for this test:') + if pmtf.output: + print(pmtf.output) + print('---------------') + break index += 1 - return tap - - -def ns_create(): - """ - Create the network namespace in which the tests will be run and set up - the required network devices for it. - """ - if (USE_NS): - cmd = 'ip netns add $NS' - exec_cmd(cmd, False) - cmd = 'ip link add $DEV0 type veth peer name $DEV1' - exec_cmd(cmd, False) - cmd = 'ip link set $DEV1 netns $NS' - exec_cmd(cmd, False) - cmd = 'ip link set $DEV0 up' - exec_cmd(cmd, False) - cmd = 'ip -n $NS link set $DEV1 up' - exec_cmd(cmd, False) - cmd = 'ip link set $DEV2 netns $NS' - exec_cmd(cmd, False) - cmd = 'ip -n $NS link set $DEV2 up' - exec_cmd(cmd, False) - - -def ns_destroy(): - """ - Destroy the network namespace for testing (and any associated network - devices as well) - """ - if (USE_NS): - cmd = 'ip netns delete $NS' - exec_cmd(cmd, False) + # if we failed in setup or teardown, + # fill in the remaining tests with ok-skipped + count = index + if not args.notap: + tap += 'about to flush the tap output if tests need to be skipped\n' + if tcount + 1 != index: + for tidx in testlist[index - 1:]: + msg = 'skipped - previous {} failed'.format(stage) + tap += 'ok {} - {} # {} {} {}\n'.format( + count, tidx['id'], msg, index, badtest.get('id', '--Unknown--')) + count += 1 + + tap += 'done flushing skipped test tap output\n' + pm.call_post_suite(index) + return tap def has_blank_ids(idlist): """ @@ -209,41 +360,67 @@ def set_args(parser): """ Set the command line arguments for tdc. """ - parser.add_argument('-p', '--path', type=str, - help='The full path to the tc executable to use') - parser.add_argument('-c', '--category', type=str, nargs='?', const='+c', - help='Run tests only from the specified category, or if no category is specified, list known categories.') - parser.add_argument('-f', '--file', type=str, - help='Run tests from the specified file') - parser.add_argument('-l', '--list', type=str, nargs='?', const="++", metavar='CATEGORY', - help='List all test cases, or those only within the specified category') - parser.add_argument('-s', '--show', type=str, nargs=1, metavar='ID', dest='showID', - help='Display the test case with specified id') - parser.add_argument('-e', '--execute', type=str, nargs=1, metavar='ID', - help='Execute the single test case with specified ID') - parser.add_argument('-i', '--id', action='store_true', dest='gen_id', - help='Generate ID numbers for new test cases') + parser.add_argument( + '-p', '--path', type=str, + help='The full path to the tc executable to use') + sg = parser.add_argument_group( + 'selection', 'select which test cases: ' + + 'files plus directories; filtered by categories plus testids') + ag = parser.add_argument_group( + 'action', 'select action to perform on selected test cases') + + sg.add_argument( + '-D', '--directory', nargs='+', metavar='DIR', + help='Collect tests from the specified directory(ies) ' + + '(default [tc-tests])') + sg.add_argument( + '-f', '--file', nargs='+', metavar='FILE', + help='Run tests from the specified file(s)') + sg.add_argument( + '-c', '--category', nargs='*', metavar='CATG', default=['+c'], + help='Run tests only from the specified category/ies, ' + + 'or if no category/ies is/are specified, list known categories.') + sg.add_argument( + '-e', '--execute', nargs='+', metavar='ID', + help='Execute the specified test cases with specified IDs') + ag.add_argument( + '-l', '--list', action='store_true', + help='List all test cases, or those only within the specified category') + ag.add_argument( + '-s', '--show', action='store_true', dest='showID', + help='Display the selected test cases') + ag.add_argument( + '-i', '--id', action='store_true', dest='gen_id', + help='Generate ID numbers for new test cases') + parser.add_argument( + '-v', '--verbose', action='count', default=0, + help='Show the commands that are being run') + parser.add_argument( + '-N', '--notap', action='store_true', + help='Suppress tap results for command under test') parser.add_argument('-d', '--device', help='Execute the test case in flower category') return parser -def check_default_settings(args): +def check_default_settings(args, remaining, pm): """ - Process any arguments overriding the default settings, and ensure the - settings are correct. + Process any arguments overriding the default settings, + and ensure the settings are correct. """ # Allow for overriding specific settings global NAMES if args.path != None: - NAMES['TC'] = args.path + NAMES['TC'] = args.path if args.device != None: - NAMES['DEV2'] = args.device + NAMES['DEV2'] = args.device if not os.path.isfile(NAMES['TC']): print("The specified tc path " + NAMES['TC'] + " does not exist.") exit(1) + pm.call_check_args(args, remaining) + def get_id_list(alltests): """ @@ -277,7 +454,7 @@ def generate_case_ids(alltests): for c in alltests: if (c["id"] == ""): while True: - newid = str('%04x' % random.randrange(16**4)) + newid = str('{:04x}'.format(random.randrange(16**4))) if (does_id_exist(alltests, newid)): continue else: @@ -300,40 +477,107 @@ def generate_case_ids(alltests): json.dump(testlist, outfile, indent=4) outfile.close() +def filter_tests_by_id(args, testlist): + ''' + Remove tests from testlist that are not in the named id list. + If id list is empty, return empty list. + ''' + newlist = list() + if testlist and args.execute: + target_ids = args.execute + + if isinstance(target_ids, list) and (len(target_ids) > 0): + newlist = list(filter(lambda x: x['id'] in target_ids, testlist)) + return newlist + +def filter_tests_by_category(args, testlist): + ''' + Remove tests from testlist that are not in a named category. + ''' + answer = list() + if args.category and testlist: + test_ids = list() + for catg in set(args.category): + if catg == '+c': + continue + print('considering category {}'.format(catg)) + for tc in testlist: + if catg in tc['category'] and tc['id'] not in test_ids: + answer.append(tc) + test_ids.append(tc['id']) + + return answer def get_test_cases(args): """ If a test case file is specified, retrieve tests from that file. Otherwise, glob for all json files in subdirectories and load from each one. + Also, if requested, filter by category, and add tests matching + certain ids. """ import fnmatch - if args.file != None: - if not os.path.isfile(args.file): - print("The specified test case file " + args.file + " does not exist.") - exit(1) - flist = [args.file] - else: - flist = [] - for root, dirnames, filenames in os.walk('tc-tests'): + + flist = [] + testdirs = ['tc-tests'] + + if args.file: + # at least one file was specified - remove the default directory + testdirs = [] + + for ff in args.file: + if not os.path.isfile(ff): + print("IGNORING file " + ff + "\n\tBECAUSE does not exist.") + else: + flist.append(os.path.abspath(ff)) + + if args.directory: + testdirs = args.directory + + for testdir in testdirs: + for root, dirnames, filenames in os.walk(testdir): for filename in fnmatch.filter(filenames, '*.json'): - flist.append(os.path.join(root, filename)) - alltests = list() + candidate = os.path.abspath(os.path.join(root, filename)) + if candidate not in testdirs: + flist.append(candidate) + + alltestcases = list() for casefile in flist: - alltests = alltests + (load_from_file(casefile)) - return alltests + alltestcases = alltestcases + (load_from_file(casefile)) + allcatlist = get_test_categories(alltestcases) + allidlist = get_id_list(alltestcases) -def set_operation_mode(args): + testcases_by_cats = get_categorized_testlist(alltestcases, allcatlist) + idtestcases = filter_tests_by_id(args, alltestcases) + cattestcases = filter_tests_by_category(args, alltestcases) + + cat_ids = [x['id'] for x in cattestcases] + if args.execute: + if args.category: + alltestcases = cattestcases + [x for x in idtestcases if x['id'] not in cat_ids] + else: + alltestcases = idtestcases + else: + if cat_ids: + alltestcases = cattestcases + else: + # just accept the existing value of alltestcases, + # which has been filtered by file/directory + pass + + return allcatlist, allidlist, testcases_by_cats, alltestcases + + +def set_operation_mode(pm, args): """ Load the test case data and process remaining arguments to determine what the script should do for this run, and call the appropriate function. """ - alltests = get_test_cases(args) + ucat, idlist, testcases, alltests = get_test_cases(args) if args.gen_id: - idlist = get_id_list(alltests) if (has_blank_ids(idlist)): alltests = generate_case_ids(alltests) else: @@ -347,70 +591,29 @@ def set_operation_mode(args): print("Please correct them before continuing.") exit(1) - ucat = get_test_categories(alltests) - if args.showID: - show_test_case_by_id(alltests, args.showID[0]) + for atest in alltests: + print_test_case(atest) exit(0) - if args.execute: - target_id = args.execute[0] - else: - target_id = "" - - if args.category: - if (args.category == '+c'): - print("Available categories:") - print_sll(ucat) - exit(0) - else: - target_category = args.category - else: - target_category = "" - - - testcases = get_categorized_testlist(alltests, ucat) + if isinstance(args.category, list) and (len(args.category) == 0): + print("Available categories:") + print_sll(ucat) + exit(0) if args.list: - if (args.list == "++"): + if args.list: list_test_cases(alltests) exit(0) - elif(len(args.list) > 0): - if (args.list not in ucat): - print("Unknown category " + args.list) - print("Available categories:") - print_sll(ucat) - exit(1) - list_test_cases(testcases[args.list]) - exit(0) - - if (os.geteuid() != 0): - print("This script must be run with root privileges.\n") - exit(1) - - ns_create() - - if (len(target_category) == 0): - if (len(target_id) > 0): - alltests = list(filter(lambda x: target_id in x['id'], alltests)) - if (len(alltests) == 0): - print("Cannot find a test case with ID matching " + target_id) - exit(1) - catresults = test_runner(alltests, args) - print("All test results: " + "\n\n" + catresults) - elif (len(target_category) > 0): - if (target_category == "flower") and args.device == None: - print("Please specify a NIC device (-d) to run category flower") - exit(1) - if (target_category not in ucat): - print("Specified category is not present in this file.") - exit(1) - else: - catresults = test_runner(testcases[target_category], args) - print("Category " + target_category + "\n\n" + catresults) - - ns_destroy() + if len(alltests): + catresults = test_runner(pm, args, alltests) + else: + catresults = 'No tests found\n' + if args.notap: + print('Tap output suppression requested\n') + else: + print('All test results: \n\n{}'.format(catresults)) def main(): """ @@ -419,10 +622,15 @@ def main(): """ parser = args_parse() parser = set_args(parser) + pm = PluginMgr(parser) + parser = pm.call_add_args(parser) (args, remaining) = parser.parse_known_args() - check_default_settings(args) + args.NAMES = NAMES + check_default_settings(args, remaining, pm) + if args.verbose > 2: + print('args is {}'.format(args)) - set_operation_mode(args) + set_operation_mode(pm, args) exit(0) diff --git a/tools/testing/selftests/tc-testing/tdc_batch.py b/tools/testing/selftests/tc-testing/tdc_batch.py index 707c6bfef689..52fa539dc662 100755 --- a/tools/testing/selftests/tc-testing/tdc_batch.py +++ b/tools/testing/selftests/tc-testing/tdc_batch.py @@ -49,13 +49,13 @@ index = 0 for i in range(0x100): for j in range(0x100): for k in range(0x100): - mac = ("%02x:%02x:%02x" % (i, j, k)) + mac = ("{:02x}:{:02x}:{:02x}".format(i, j, k)) src_mac = "e4:11:00:" + mac dst_mac = "e4:12:00:" + mac - cmd = ("filter add dev %s %s protocol ip parent ffff: flower %s " - "src_mac %s dst_mac %s action drop %s" % + cmd = ("filter add dev {} {} protocol ip parent ffff: flower {} " + "src_mac {} dst_mac {} action drop {}".format (device, prio, skip, src_mac, dst_mac, share_action)) - file.write("%s\n" % cmd) + file.write("{}\n".format(cmd)) index += 1 if index >= number: file.close() diff --git a/tools/testing/selftests/tc-testing/tdc_helper.py b/tools/testing/selftests/tc-testing/tdc_helper.py index db381120a566..9f35c96c88a0 100644 --- a/tools/testing/selftests/tc-testing/tdc_helper.py +++ b/tools/testing/selftests/tc-testing/tdc_helper.py @@ -57,20 +57,11 @@ def print_sll(items): def print_test_case(tcase): """ Pretty-printing of a given test case. """ + print('\n==============\nTest {}\t{}\n'.format(tcase['id'], tcase['name'])) for k in tcase.keys(): if (isinstance(tcase[k], list)): print(k + ":") print_list(tcase[k]) else: - print(k + ": " + tcase[k]) - - -def show_test_case_by_id(testlist, caseID): - """ Find the specified test case to pretty-print. """ - if not any(d.get('id', None) == caseID for d in testlist): - print("That ID does not exist.") - exit(1) - else: - print_test_case(next((d for d in testlist if d['id'] == caseID))) - - + if not ((k == 'id') or (k == 'name')): + print(k + ": " + str(tcase[k])) |