The following commit has been merged in the master branch: commit 03fe2debbb2771fb90881e4ce8109b09cf772a5c Merge: 6686c459e1449a3ee5f3fd313b0a559ace7a700e f36b7534b83357cf52e747905de6d65b4f7c2512 Author: David S. Miller &lt;davem(a)davemloft.net&gt; Date: Fri Mar 23 11:24:57 2018 -0400 Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net Fun set of conflict resolutions here... For the mac80211 stuff, these were fortunately just parallel adds. Trivially resolved. In drivers/net/phy/phy.c we had a bug fix in 'net' that moved the function phy_disable_interrupts() earlier in the file, whilst in 'net-next' the phy_error() call from this function was removed. In net/ipv4/xfrm4_policy.c, David Ahern's changes to remove the 'rt_table_id' member of rtable collided with a bug fix in 'net' that added a new struct member "rt_mtu_locked" which needs to be copied over here. The mlxsw driver conflict consisted of net-next separating the span code and definitions into separate files, whilst a 'net' bug fix made some changes to that moved code. The mlx5 infiniband conflict resolution was quite non-trivial, the RDMA tree's merge commit was used as a guide here, and here are their notes: ==================== Due to bug fixes found by the syzkaller bot and taken into the for-rc branch after development for the 4.17 merge window had already started being taken into the for-next branch, there were fairly non-trivial merge issues that would need to be resolved between the for-rc branch and the for-next branch. This merge resolves those conflicts and provides a unified base upon which ongoing development for 4.17 can be based. Conflicts: drivers/infiniband/hw/mlx5/main.c - Commit 42cea83f9524 (IB/mlx5: Fix cleanup order on unload) added to for-rc and commit b5ca15ad7e61 (IB/mlx5: Add proper representors support) add as part of the devel cycle both needed to modify the init/de-init functions used by mlx5. To support the new representors, the new functions added by the cleanup patch needed to be made non-static, and the init/de-init list added by the representors patch needed to be modified to match the init/de-init list changes made by the cleanup patch. Updates: drivers/infiniband/hw/mlx5/mlx5_ib.h - Update function prototypes added by representors patch to reflect new function names as changed by cleanup patch drivers/infiniband/hw/mlx5/ib_rep.c - Update init/de-init stage list to match new order from cleanup patch ==================== Signed-off-by: David S. Miller &lt;davem(a)davemloft.net&gt; diff --combined Documentation/devicetree/bindings/net/dsa/marvell.txt index caf71e2fe24a,8c033d48e2ba..60d50a2b0323 --- a/Documentation/devicetree/bindings/net/dsa/marvell.txt +++ b/Documentation/devicetree/bindings/net/dsa/marvell.txt @@@ -13,18 -13,9 +13,18 @@@ placed as a child node of an mdio devic The properties described here are those specific to Marvell devices. Additional required and optional properties can be found in dsa.txt. +The compatibility string is used only to find an identification register, +which is at a different MDIO base address in different switch families. +- "marvell,mv88e6085" : Switch has base address 0x10. Use with models: + 6085, 6095, 6097, 6123, 6131, 6141, 6161, 6165, + 6171, 6172, 6175, 6176, 6185, 6240, 6320, 6321, + 6341, 6350, 6351, 6352 +- "marvell,mv88e6190" : Switch has base address 0x00. Use with models: + 6190, 6190X, 6191, 6290, 6390, 6390X + Required properties: - compatible : Should be one of "marvell,mv88e6085" or - "marvell,mv88e6190" + "marvell,mv88e6190" as indicated above - reg : Address on the MII bus for the switch. Optional properties: @@@ -59,14 -50,15 +59,15 @@@ Example compatible = "marvell,mv88e6085"; reg = <0>; reset-gpios = <&gpio5 1 GPIO_ACTIVE_LOW>; - }; - mdio { - #address-cells = <1>; - #size-cells = <0>; - switch1phy0: switch1phy0@0 { - reg = <0>; - interrupt-parent = <&switch0>; - interrupts = <0 IRQ_TYPE_LEVEL_HIGH>; + + mdio { + #address-cells = <1>; + #size-cells = <0>; + switch1phy0: switch1phy0@0 { + reg = <0>; + interrupt-parent = <&switch0>; + interrupts = <0 IRQ_TYPE_LEVEL_HIGH>; + }; }; }; }; @@@ -83,23 -75,24 +84,24 @@@ compatible = "marvell,mv88e6390"; reg = <0>; reset-gpios = <&gpio5 1 GPIO_ACTIVE_LOW>; - }; - mdio { - #address-cells = <1>; - #size-cells = <0>; - switch1phy0: switch1phy0@0 { - reg = <0>; - interrupt-parent = <&switch0>; - interrupts = <0 IRQ_TYPE_LEVEL_HIGH>; + + mdio { + #address-cells = <1>; + #size-cells = <0>; + switch1phy0: switch1phy0@0 { + reg = <0>; + interrupt-parent = <&switch0>; + interrupts = <0 IRQ_TYPE_LEVEL_HIGH>; + }; }; - }; - mdio1 { - compatible = "marvell,mv88e6xxx-mdio-external"; - #address-cells = <1>; - #size-cells = <0>; - switch1phy9: switch1phy0@9 { - reg = <9>; + mdio1 { + compatible = "marvell,mv88e6xxx-mdio-external"; + #address-cells = <1>; + #size-cells = <0>; + switch1phy9: switch1phy0@9 { + reg = <9>; + }; }; }; }; diff --combined MAINTAINERS index 214c9bca232a,73c0cdabf755..b3ea844cf228 --- a/MAINTAINERS +++ b/MAINTAINERS @@@ -8596,15 -8596,6 +8596,15 @@@ S: Maintaine 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 &lt;liuxuenetmail(a)gmail.com&gt; +L: linux-wpan(a)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 &lt;vilhelm.gray(a)gmail.com&gt; L: linux-iio(a)vger.kernel.org @@@ -9161,13 -9152,6 +9161,13 @@@ F: drivers/net/dsa/microchip/ F: include/linux/platform_data/microchip-ksz.h F: Documentation/devicetree/bindings/net/dsa/ksz.txt +MICROCHIP LAN743X ETHERNET DRIVER +M: Bryan Whitehead &lt;bryan.whitehead(a)microchip.com&gt; +M: Microchip Linux Driver Support &lt;UNGLinuxDriver(a)microchip.com&gt; +L: netdev(a)vger.kernel.org +S: Maintained +F: drivers/net/ethernet/microchip/lan743x_* + MICROCHIP USB251XB DRIVER M: Richard Leitner &lt;richard.leitner(a)skidata.com&gt; L: linux-usb(a)vger.kernel.org @@@ -9941,6 -9925,13 +9941,13 @@@ F: Documentation/ABI/stable/sysfs-bus-n F: include/linux/nvmem-consumer.h F: include/linux/nvmem-provider.h + NXP SGTL5000 DRIVER + M: Fabio Estevam &lt;fabio.estevam(a)nxp.com&gt; + L: alsa-devel(a)alsa-project.org (moderated for non-subscribers) + S: Maintained + F: Documentation/devicetree/bindings/sound/sgtl5000.txt + F: sound/soc/codecs/sgtl5000* + NXP TDA998X DRM DRIVER M: Russell King &lt;linux(a)armlinux.org.uk&gt; S: Supported @@@ -10343,7 -10334,7 +10350,7 @@@ F: drivers/oprofile F: include/linux/oprofile.h ORACLE CLUSTER FILESYSTEM 2 (OCFS2) - M: Mark Fasheh &lt;mfasheh(a)versity.com&gt; + M: Mark Fasheh &lt;mark(a)fasheh.com&gt; M: Joel Becker &lt;jlbec(a)evilplan.org&gt; L: ocfs2-devel(a)oss.oracle.com (moderated for non-subscribers) W: http://ocfs2.wiki.kernel.org @@@ -10853,6 -10844,7 +10860,7 @@@ F: drivers/platform/x86/peaq-wmi. PER-CPU MEMORY ALLOCATOR M: Tejun Heo &lt;tj(a)kernel.org&gt; M: Christoph Lameter &lt;cl(a)linux.com&gt; + M: Dennis Zhou &lt;dennisszhou(a)gmail.com&gt; T: git git://git.kernel.org/pub/scm/linux/kernel/git/tj/percpu.git S: Maintained F: include/linux/percpu*.h @@@ -12123,6 -12115,7 +12131,7 @@@ M: Sylwester Nawrocki <s.nawrocki@samsu L: alsa-devel(a)alsa-project.org (moderated for non-subscribers) S: Supported F: sound/soc/samsung/ + F: Documentation/devicetree/bindings/sound/samsung* SAMSUNG EXYNOS PSEUDO RANDOM NUMBER GENERATOR (RNG) DRIVER M: Krzysztof Kozlowski &lt;krzk(a)kernel.org&gt; diff --combined arch/x86/net/bpf_jit_comp.c index eb661fff94d7,ce5b2ebd5701..b725154182cc --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@@ -11,10 -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 @@@ -61,12 -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 */ @@@ -103,6 -98,16 +103,6 @@@ static int bpf_size_to_x86_bytes(int bp #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) @@@ -207,7 -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; @@@ -242,21 -247,18 +242,21 @@@ /* 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; } @@@ -354,86 -356,6 +354,86 @@@ static void emit_load_skb_data_hlen(u8 *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) { @@@ -447,8 -369,7 +447,8 @@@ 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); @@@ -457,7 -378,7 +457,7 @@@ 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; @@@ -493,11 -414,16 +493,11 @@@ 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 */ @@@ -560,13 -486,58 +560,13 @@@ 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; @@@ -623,38 -594,36 +623,38 @@@ 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: @@@ -672,11 -641,7 +672,11 @@@ 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: @@@ -1223,7 -1188,7 +1223,7 @@@ skip_init_addrs * may converge on the last pass. In such case do one more * pass to emit the final image */ - for (pass = 0; pass < 10 || image; pass++) { + for (pass = 0; pass < 20 || image; pass++) { proglen = do_jit(prog, addrs, image, oldproglen, &ctx); if (proglen <= 0) { image = NULL; @@@ -1250,12 -1215,14 +1250,13 @@@ } } oldproglen = proglen; + cond_resched(); } if (bpf_jit_enable > 1) 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 --combined drivers/bluetooth/btusb.c index fa4ce83893bb,366a49c7c08f..5cd868ea28ed --- a/drivers/bluetooth/btusb.c +++ b/drivers/bluetooth/btusb.c @@@ -231,7 -231,6 +231,6 @@@ static const struct usb_device_id black { USB_DEVICE(0x0930, 0x0227), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x0b05, 0x17d0), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x0cf3, 0x0036), .driver_info = BTUSB_ATH3012 }, - { USB_DEVICE(0x0cf3, 0x3004), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x0cf3, 0x3008), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x0cf3, 0x311d), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x0cf3, 0x311e), .driver_info = BTUSB_ATH3012 }, @@@ -264,6 -263,7 +263,7 @@@ { USB_DEVICE(0x0489, 0xe03c), .driver_info = BTUSB_ATH3012 }, /* QCA ROME chipset */ + { USB_DEVICE(0x0cf3, 0x3004), .driver_info = BTUSB_QCA_ROME }, { USB_DEVICE(0x0cf3, 0xe007), .driver_info = BTUSB_QCA_ROME }, { USB_DEVICE(0x0cf3, 0xe009), .driver_info = BTUSB_QCA_ROME }, { USB_DEVICE(0x0cf3, 0xe010), .driver_info = BTUSB_QCA_ROME }, @@@ -340,7 -340,6 +340,7 @@@ /* 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 }, @@@ -375,9 -374,6 +375,9 @@@ { 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 }, @@@ -390,10 -386,10 +390,10 @@@ */ static const struct dmi_system_id btusb_needs_reset_resume_table[] = { { - /* Lenovo Yoga 920 (QCA Rome device 0cf3:e300) */ + /* Dell OptiPlex 3060 (QCA ROME device 0cf3:e007) */ .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), - DMI_MATCH(DMI_PRODUCT_VERSION, "Lenovo YOGA 920"), + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex 3060"), }, }, {} @@@ -2077,8 -2073,6 +2077,8 @@@ static int btusb_setup_intel_new(struc 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)", @@@ -2171,8 -2165,6 +2171,8 @@@ 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), @@@ -2204,8 -2196,6 +2204,8 @@@ 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 --combined drivers/infiniband/core/cma.c index 915bbd867b61,a5367c5efbe7..66f203730e80 --- a/drivers/infiniband/core/cma.c +++ b/drivers/infiniband/core/cma.c @@@ -1334,7 -1334,7 +1334,7 @@@ static bool validate_ipv6_net_dev(struc 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) @@@ -3069,7 -3069,8 +3069,8 @@@ static int cma_port_is_unique(struct rd continue; /* different dest port -> unique */ - if (!cma_any_port(cur_daddr) && + if (!cma_any_port(daddr) && + !cma_any_port(cur_daddr) && (dport != cur_dport)) continue; @@@ -3080,7 -3081,8 +3081,8 @@@ continue; /* different dst address -> unique */ - if (!cma_any_addr(cur_daddr) && + if (!cma_any_addr(daddr) && + !cma_any_addr(cur_daddr) && cma_addr_cmp(daddr, cur_daddr)) continue; @@@ -3378,13 -3380,13 +3380,13 @@@ int rdma_bind_addr(struct rdma_cm_id *i } #endif } + daddr = cma_dst_addr(id_priv); + daddr->sa_family = addr->sa_family; + ret = cma_get_port(id_priv); if (ret) goto err2; - daddr = cma_dst_addr(id_priv); - daddr->sa_family = addr->sa_family; - return 0; err2: if (id_priv->cma_dev) @@@ -4173,6 -4175,9 +4175,9 @@@ int rdma_join_multicast(struct rdma_cm_ struct cma_multicast *mc; int ret; + if (!id->device) + return -EINVAL; + id_priv = container_of(id, struct rdma_id_private, id); if (!cma_comp(id_priv, RDMA_CM_ADDR_BOUND) && !cma_comp(id_priv, RDMA_CM_ADDR_RESOLVED)) @@@ -4549,7 -4554,6 +4554,7 @@@ static struct pernet_operations cma_per .exit = cma_exit_net, .id = &cma_pernet_id, .size = sizeof(struct cma_pernet), + .async = true, }; static int __init cma_init(void) diff --combined drivers/infiniband/hw/mlx5/cq.c index c4c7b82f4ac1,15457c9569a7..94a27d89a303 --- a/drivers/infiniband/hw/mlx5/cq.c +++ b/drivers/infiniband/hw/mlx5/cq.c @@@ -64,9 -64,14 +64,9 @@@ static void mlx5_ib_cq_event(struct mlx } } -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) @@@ -221,7 -226,6 +221,6 @@@ static void handle_responder(struct ib_ wc->ex.invalidate_rkey = be32_to_cpu(cqe->imm_inval_pkey); break; } - wc->slid = be16_to_cpu(cqe->slid); wc->src_qp = be32_to_cpu(cqe->flags_rqpn) & 0xffffff; wc->dlid_path_bits = cqe->ml_path; g = (be32_to_cpu(cqe->flags_rqpn) >> 28) & 3; @@@ -236,10 -240,12 +235,12 @@@ } if (ll != IB_LINK_LAYER_ETHERNET) { + wc->slid = be16_to_cpu(cqe->slid); wc->sl = (be32_to_cpu(cqe->flags_rqpn) >> 24) & 0xf; return; } + wc->slid = 0; vlan_present = cqe->l4_l3_hdr_type & 0x1; roce_packet_type = (be32_to_cpu(cqe->flags_rqpn) >> 24) & 0x3; if (vlan_present) { @@@ -398,7 -404,7 +399,7 @@@ static void handle_atomics(struct mlx5_ 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, @@@ -719,25 -725,12 +720,25 @@@ int mlx5_ib_arm_cq(struct ib_cq *ibcq, 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; @@@ -870,15 -863,14 +871,15 @@@ static void destroy_cq_user(struct mlx5 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; } @@@ -900,15 -892,14 +901,15 @@@ static int create_cq_kernel(struct mlx5 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; @@@ -916,12 -907,11 +917,12 @@@ } 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; @@@ -1188,7 -1178,12 +1189,12 @@@ static int resize_user(struct mlx5_ib_d if (ucmd.reserved0 || ucmd.reserved1) return -EINVAL; - umem = ib_umem_get(context, ucmd.buf_addr, entries * ucmd.cqe_size, + /* check multiplication overflow */ + if (ucmd.cqe_size && SIZE_MAX / ucmd.cqe_size <= entries - 1) + return -EINVAL; + + umem = ib_umem_get(context, ucmd.buf_addr, + (size_t)ucmd.cqe_size * entries, IB_ACCESS_LOCAL_WRITE, 1); if (IS_ERR(umem)) { err = PTR_ERR(umem); @@@ -1218,11 -1213,11 +1224,11 @@@ static int resize_kernel(struct mlx5_ib 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; @@@ -1267,8 -1262,9 +1273,8 @@@ static int copy_resize_cqes(struct mlx5 } 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); @@@ -1334,11 -1330,8 +1340,11 @@@ int mlx5_ib_resize_cq(struct ib_cq *ibc 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; } } @@@ -1359,8 -1352,7 +1365,8 @@@ 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 --combined drivers/infiniband/hw/mlx5/ib_rep.c index 61cc3d7db257,000000000000..0e04fdddf670 mode 100644,000000..100644 --- a/drivers/infiniband/hw/mlx5/ib_rep.c +++ b/drivers/infiniband/hw/mlx5/ib_rep.c @@@ -1,189 -1,0 +1,192 @@@ +/* 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_PRE_IB_REG_UMR, ++ NULL, ++ mlx5_ib_stage_pre_ib_reg_umr_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_POST_IB_REG_UMR, ++ mlx5_ib_stage_post_ib_reg_umr_init, ++ NULL), + 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 --combined drivers/infiniband/hw/mlx5/main.c index d9474b95d8e5,da091de4e69d..390e4375647e --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@@ -57,9 -57,7 +57,9 @@@ #include <linux/in.h> #include <linux/etherdevice.h> #include "mlx5_ib.h" +#include "ib_rep.h" #include "cmd.h" +#include <linux/mlx5/fs_helpers.h> #define DRIVER_NAME "mlx5_ib" #define DRIVER_VERSION "5.0-0" @@@ -132,7 -130,7 +132,7 @@@ static int get_port_state(struct ib_dev 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; @@@ -156,19 -154,10 +156,19 @@@ static int mlx5_netdev_event(struct not 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; @@@ -256,12 -245,16 +256,16 @@@ struct mlx5_core_dev *mlx5_ib_get_nativ struct mlx5_ib_multiport_info *mpi; struct mlx5_ib_port *port; + if (!mlx5_core_mp_enabled(ibdev->mdev) || + ll != IB_LINK_LAYER_ETHERNET) { + if (native_port_num) + *native_port_num = ib_port_num; + return ibdev->mdev; + } + if (native_port_num) *native_port_num = 1; - if (!mlx5_core_mp_enabled(ibdev->mdev) || ll != IB_LINK_LAYER_ETHERNET) - return ibdev->mdev; - port = &ibdev->port[ib_port_num - 1]; if (!port) return NULL; @@@ -1279,22 -1272,6 +1283,22 @@@ int mlx5_ib_query_port(struct ib_devic 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) { @@@ -2313,9 -2290,11 +2317,9 @@@ static void set_tos(void *outer_c, voi offsetof(typeof(filter), field) -\ sizeof(filter.field)) -#define IPV4_VERSION 4 -#define IPV6_VERSION 6 static int parse_flow_attr(struct mlx5_core_dev *mdev, u32 *match_c, u32 *match_v, const union ib_flow_spec *ib_spec, - u32 *tag_id, bool *is_drop) + struct mlx5_flow_act *action) { void *misc_params_c = MLX5_ADDR_OF(fte_match_param, match_c, misc_parameters); @@@ -2398,7 -2377,7 +2402,7 @@@ MLX5_SET(fte_match_set_lyr_2_4, headers_c, ip_version, 0xf); MLX5_SET(fte_match_set_lyr_2_4, headers_v, - ip_version, IPV4_VERSION); + ip_version, MLX5_FS_IPV4_VERSION); } else { MLX5_SET(fte_match_set_lyr_2_4, headers_c, ethertype, 0xffff); @@@ -2437,7 -2416,7 +2441,7 @@@ MLX5_SET(fte_match_set_lyr_2_4, headers_c, ip_version, 0xf); MLX5_SET(fte_match_set_lyr_2_4, headers_v, - ip_version, IPV6_VERSION); + ip_version, MLX5_FS_IPV6_VERSION); } else { MLX5_SET(fte_match_set_lyr_2_4, headers_c, ethertype, 0xffff); @@@ -2533,14 -2512,13 +2537,14 @@@ if (ib_spec->flow_tag.tag_id >= BIT(24)) return -EINVAL; - *tag_id = ib_spec->flow_tag.tag_id; + action->flow_tag = ib_spec->flow_tag.tag_id; + action->has_flow_tag = true; break; case IB_FLOW_SPEC_ACTION_DROP: if (FIELDS_NOT_SUPPORTED(ib_spec->drop, LAST_DROP_FIELD)) return -EOPNOTSUPP; - *is_drop = true; + action->action |= MLX5_FLOW_CONTEXT_ACTION_DROP; break; default: return -EINVAL; @@@ -2657,7 -2635,7 +2661,7 @@@ static int mlx5_ib_destroy_flow(struct 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); @@@ -2668,7 -2646,7 +2672,7 @@@ 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); @@@ -2717,7 -2695,7 +2721,7 @@@ static struct mlx5_ib_flow_prio *get_fl 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, @@@ -2725,7 -2703,7 +2729,7 @@@ 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)) @@@ -2735,7 -2713,7 +2739,7 @@@ 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; @@@ -2793,11 -2771,13 +2797,11 @@@ static struct mlx5_ib_flow_handler *_cr { struct mlx5_flow_table *ft = ft_prio->flow_table; struct mlx5_ib_flow_handler *handler; - struct mlx5_flow_act flow_act = {0}; + struct mlx5_flow_act flow_act = {.flow_tag = MLX5_FS_DEFAULT_FLOW_TAG}; struct mlx5_flow_spec *spec; struct mlx5_flow_destination *rule_dst = dst; const void *ib_flow = (const void *)flow_attr + sizeof(*flow_attr); unsigned int spec_index; - u32 flow_tag = MLX5_FS_DEFAULT_FLOW_TAG; - bool is_drop = false; int err = 0; int dest_num = 1; @@@ -2816,7 -2796,7 +2820,7 @@@ for (spec_index = 0; spec_index < flow_attr->num_of_specs; spec_index++) { err = parse_flow_attr(dev->mdev, spec->match_criteria, spec->match_value, - ib_flow, &flow_tag, &is_drop); + ib_flow, &flow_act); if (err < 0) goto free; @@@ -2826,20 -2806,9 +2830,20 @@@ 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; + if (flow_act.action & MLX5_FLOW_CONTEXT_ACTION_DROP) { rule_dst = NULL; dest_num = 0; } else { @@@ -2847,14 -2816,15 +2851,14 @@@ MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_PRIO; } - if (flow_tag != MLX5_FS_DEFAULT_FLOW_TAG && + if (flow_act.has_flow_tag && (flow_attr->type == IB_FLOW_ATTR_ALL_DEFAULT || flow_attr->type == IB_FLOW_ATTR_MC_DEFAULT)) { mlx5_ib_warn(dev, "Flow tag %u and attribute type %x isn't allowed in leftovers\n", - flow_tag, flow_attr->type); + flow_act.flow_tag, flow_attr->type); err = -EINVAL; goto free; } - flow_act.flow_tag = flow_tag; handler->rule = mlx5_add_flow_rules(ft, spec, &flow_act, rule_dst, dest_num); @@@ -3033,7 -3003,7 +3037,7 @@@ static struct ib_flow *mlx5_ib_create_f 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)) { @@@ -3082,7 -3052,7 +3086,7 @@@ goto destroy_ft; } - mutex_unlock(&dev->flow_db.lock); + mutex_unlock(&dev->flow_db->lock); kfree(dst); return &handler->ibflow; @@@ -3092,7 -3062,7 +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); @@@ -3297,7 -3267,7 +3301,7 @@@ static void mlx5_ib_handle_event(struc struct mlx5_ib_dev *ibdev; struct ib_event ibev; bool fatal = false; - u8 port = 0; + u8 port = (u8)work->param; if (mlx5_core_is_mp_slave(work->dev)) { ibdev = mlx5_ib_get_ibdev_from_mpi(work->context); @@@ -3317,8 -3287,6 +3321,6 @@@ case MLX5_DEV_EVENT_PORT_UP: case MLX5_DEV_EVENT_PORT_DOWN: case MLX5_DEV_EVENT_PORT_INITIALIZED: - port = (u8)work->param; - /* In RoCE, port up/down events are handled in * mlx5_netdev_event(). */ @@@ -3332,24 -3300,19 +3334,19 @@@ case MLX5_DEV_EVENT_LID_CHANGE: ibev.event = IB_EVENT_LID_CHANGE; - port = (u8)work->param; break; case MLX5_DEV_EVENT_PKEY_CHANGE: ibev.event = IB_EVENT_PKEY_CHANGE; - port = (u8)work->param; - schedule_work(&ibdev->devr.ports[port - 1].pkey_change_work); break; case MLX5_DEV_EVENT_GUID_CHANGE: ibev.event = IB_EVENT_GID_CHANGE; - port = (u8)work->param; break; case MLX5_DEV_EVENT_CLIENT_REREG: ibev.event = IB_EVENT_CLIENT_REREGISTER; - port = (u8)work->param; break; case MLX5_DEV_EVENT_DELAY_DROP_TIMEOUT: schedule_work(&ibdev->delay_drop.delay_drop_work); @@@ -3361,7 -3324,7 +3358,7 @@@ ibev.device = &ibdev->ib_dev; ibev.element.port_num = port; - if (port < 1 || port > ibdev->num_ports) { + if (!rdma_is_port_valid(&ibdev->ib_dev, port)) { mlx5_ib_warn(ibdev, "warning: event on port %d\n", port); goto out; } @@@ -3806,25 -3769,6 +3803,25 @@@ static int mlx5_port_immutable(struct i 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 = @@@ -3855,7 -3799,7 +3852,7 @@@ static int mlx5_eth_lag_init(struct mlx 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: @@@ -3867,9 -3811,9 +3864,9 @@@ static void mlx5_eth_lag_cleanup(struc { 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); } @@@ -3901,10 -3845,14 +3898,10 @@@ static int mlx5_enable_eth(struct mlx5_ { 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); @@@ -3917,6 -3865,8 +3914,6 @@@ 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; } @@@ -4550,7 -4500,7 +4547,7 @@@ static void mlx5_ib_cleanup_multiport_m 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 @@@ -4559,7 -4509,7 +4556,7 @@@ 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; @@@ -4581,6 -4531,8 +4578,6 @@@ goto err_free_port; if (!mlx5_core_mp_enabled(mdev)) { - int i; - for (i = 1; i <= dev->num_ports; i++) { err = get_port_caps(dev, i); if (err) @@@ -4609,6 -4561,7 +4606,6 @@@ 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); @@@ -4629,38 -4582,7 +4626,38 @@@ 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; @@@ -4701,6 -4623,7 +4698,6 @@@ (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; @@@ -4743,6 -4666,7 +4740,6 @@@ 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)) @@@ -4793,80 -4717,6 +4790,80 @@@ 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; @@@ -4874,26 -4724,37 +4871,26 @@@ 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) @@@ -4909,16 -4770,16 +4906,16 @@@ 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); } @@@ -4930,7 -4791,7 +4927,7 @@@ static int mlx5_ib_stage_odp_init(struc 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; @@@ -4942,7 -4803,7 +4939,7 @@@ 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); @@@ -4973,7 -4834,7 +4970,7 @@@ static void mlx5_ib_stage_uar_cleanup(s 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; @@@ -4988,30 -4849,30 +4985,30 @@@ 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); } - void mlx5_ib_stage_ib_reg_cleanup(struct mlx5_ib_dev *dev) -static void mlx5_ib_stage_pre_ib_reg_umr_cleanup(struct mlx5_ib_dev *dev) ++void mlx5_ib_stage_pre_ib_reg_umr_cleanup(struct mlx5_ib_dev *dev) { - ib_unregister_device(&dev->ib_dev); + destroy_umrc_res(dev); } - int mlx5_ib_stage_umr_res_init(struct mlx5_ib_dev *dev) -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) { - return create_umr_res(dev); + ib_unregister_device(&dev->ib_dev); } - void mlx5_ib_stage_umr_res_cleanup(struct mlx5_ib_dev *dev) -static int mlx5_ib_stage_post_ib_reg_umr_init(struct mlx5_ib_dev *dev) ++int mlx5_ib_stage_post_ib_reg_umr_init(struct mlx5_ib_dev *dev) { - destroy_umrc_res(dev); + return create_umr_res(dev); } static int mlx5_ib_stage_delay_drop_init(struct mlx5_ib_dev *dev) @@@ -5026,7 -4887,7 +5023,7 @@@ static void mlx5_ib_stage_delay_drop_cl 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; @@@ -5041,21 -4902,9 +5038,21 @@@ 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) { @@@ -5069,14 -4918,23 +5066,14 @@@ 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); @@@ -5100,15 -4958,9 +5097,15 @@@ static const struct mlx5_ib_profile pf_ 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), @@@ -5130,12 -4982,15 +5127,15 @@@ STAGE_CREATE(MLX5_IB_STAGE_BFREG, mlx5_ib_stage_bfrag_init, mlx5_ib_stage_bfrag_cleanup), + STAGE_CREATE(MLX5_IB_STAGE_PRE_IB_REG_UMR, + NULL, + mlx5_ib_stage_pre_ib_reg_umr_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_POST_IB_REG_UMR, + mlx5_ib_stage_post_ib_reg_umr_init, + NULL), STAGE_CREATE(MLX5_IB_STAGE_DELAY_DROP, mlx5_ib_stage_delay_drop_init, mlx5_ib_stage_delay_drop_cleanup), @@@ -5144,48 -4999,6 +5144,51 @@@ 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_PRE_IB_REG_UMR, ++ NULL, ++ mlx5_ib_stage_pre_ib_reg_umr_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_POST_IB_REG_UMR, ++ mlx5_ib_stage_post_ib_reg_umr_init, ++ NULL), + 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; @@@ -5231,11 -5044,8 +5234,11 @@@ 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); @@@ -5245,22 -5055,7 +5248,22 @@@ 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 --combined drivers/infiniband/hw/mlx5/mlx5_ib.h index e0bad28e0f09,a5272499b600..c33bf1523d67 --- a/drivers/infiniband/hw/mlx5/mlx5_ib.h +++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h @@@ -343,7 -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; }; @@@ -372,7 -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; @@@ -414,7 -413,7 +414,7 @@@ }; struct mlx5_ib_cq_buf { - struct mlx5_buf buf; + struct mlx5_frag_buf_ctrl fbc; struct ib_umem *umem; int cqe_size; int nent; @@@ -496,7 -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 @@@ -732,9 -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, @@@ -742,11 -739,11 +742,12 @@@ MLX5_IB_STAGE_CONG_DEBUGFS, MLX5_IB_STAGE_UAR, MLX5_IB_STAGE_BFREG, + MLX5_IB_STAGE_PRE_IB_REG_UMR, MLX5_IB_STAGE_IB_REG, - MLX5_IB_STAGE_UMR_RESOURCES, + MLX5_IB_STAGE_POST_IB_REG_UMR, MLX5_IB_STAGE_DELAY_DROP, MLX5_IB_STAGE_CLASS_ATTR, + MLX5_IB_STAGE_REP_REG, MLX5_IB_STAGE_MAX, }; @@@ -801,7 -798,7 +802,7 @@@ 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; @@@ -811,7 -808,6 +812,7 @@@ 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; @@@ -1054,31 -1050,6 +1055,31 @@@ static inline void mlx5_odp_populate_kl #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); ++void mlx5_ib_stage_pre_ib_reg_umr_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_post_ib_reg_umr_init(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 --combined drivers/infiniband/hw/mlx5/mr.c index a5fad3e87ff7,c51c602f06d6..95a36e9ea552 --- a/drivers/infiniband/hw/mlx5/mr.c +++ b/drivers/infiniband/hw/mlx5/mr.c @@@ -587,7 -587,7 +587,7 @@@ static void clean_keys(struct mlx5_ib_d 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 +600,7 @@@ static int mlx5_mr_cache_debugfs_init(s 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); @@@ -690,7 -690,6 +690,7 @@@ int mlx5_mr_cache_init(struct mlx5_ib_d 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 @@@ -839,7 -838,8 +839,8 @@@ static int mr_umem_get(struct ib_pd *pd *umem = ib_umem_get(pd->uobject->context, start, length, access_flags, 0); err = PTR_ERR_OR_ZERO(*umem); - if (err < 0) { + if (err) { + *umem = NULL; mlx5_ib_err(dev, "umem get failed (%d)\n", err); return err; } @@@ -1416,6 -1416,7 +1417,7 @@@ int mlx5_ib_rereg_user_mr(struct ib_mr if (err) { mlx5_ib_warn(dev, "Failed to rereg UMR\n"); ib_umem_release(mr->umem); + mr->umem = NULL; clean_mr(dev, mr); return err; } @@@ -1499,14 -1500,11 +1501,11 @@@ static int clean_mr(struct mlx5_ib_dev u32 key = mr->mmkey.key; err = destroy_mkey(dev, mr); - kfree(mr); if (err) { mlx5_ib_warn(dev, "failed to destroy mkey 0x%x (%d)\n", key, err); return err; } - } else { - mlx5_mr_cache_free(dev, mr); } return 0; @@@ -1549,6 -1547,11 +1548,11 @@@ static int dereg_mr(struct mlx5_ib_dev atomic_sub(npages, &dev->mdev->priv.reg_pages); } + if (!mr->allocated_from_cache) + kfree(mr); + else + mlx5_mr_cache_free(dev, mr); + return 0; } @@@ -1817,7 -1820,6 +1821,6 @@@ mlx5_ib_sg_to_klms(struct mlx5_ib_mr *m mr->ibmr.iova = sg_dma_address(sg) + sg_offset; mr->ibmr.length = 0; - mr->ndescs = sg_nents; for_each_sg(sgl, sg, sg_nents, i) { if (unlikely(i >= mr->max_descs)) @@@ -1829,6 -1831,7 +1832,7 @@@ sg_offset = 0; } + mr->ndescs = i; if (sg_offset_p) *sg_offset_p = sg_offset; diff --combined drivers/infiniband/hw/mlx5/qp.c index 0e67e3682bca,a2e1aa86e133..85c612ac547a --- a/drivers/infiniband/hw/mlx5/qp.c +++ b/drivers/infiniband/hw/mlx5/qp.c @@@ -36,7 -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; @@@ -1083,13 -1082,6 +1083,13 @@@ static void destroy_raw_packet_qp_tis(s 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) @@@ -1153,15 -1145,8 +1153,15 @@@ 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; @@@ -1172,12 -1157,11 +1172,12 @@@ 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); } - static int get_rq_pas_size(void *qpc) + static size_t get_rq_pas_size(void *qpc) { u32 log_page_size = MLX5_GET(qpc, qpc, log_page_size) + 12; u32 log_rq_stride = MLX5_GET(qpc, qpc, log_rq_stride); @@@ -1193,7 -1177,8 +1193,8 @@@ } static int create_raw_packet_qp_rq(struct mlx5_ib_dev *dev, - struct mlx5_ib_rq *rq, void *qpin) + struct mlx5_ib_rq *rq, void *qpin, + size_t qpinlen) { struct mlx5_ib_qp *mqp = rq->base.container_mibqp; __be64 *pas; @@@ -1202,9 -1187,12 +1203,12 @@@ void *rqc; void *wq; void *qpc = MLX5_ADDR_OF(create_qp_in, qpin, qpc); - int inlen; + size_t rq_pas_size = get_rq_pas_size(qpc); + size_t inlen; int err; - u32 rq_pas_size = get_rq_pas_size(qpc); + + if (qpinlen < rq_pas_size + MLX5_BYTE_OFF(create_qp_in, pas)) + return -EINVAL; inlen = MLX5_ST_SZ_BYTES(create_rq_in) + rq_pas_size; in = kvzalloc(inlen, GFP_KERNEL); @@@ -1279,10 -1267,6 +1283,10 @@@ static int create_raw_packet_qp_tir(str 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); @@@ -1297,7 -1281,7 +1301,7 @@@ static void destroy_raw_packet_qp_tir(s } static int create_raw_packet_qp(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp, - u32 *in, + u32 *in, size_t inlen, struct ib_pd *pd) { struct mlx5_ib_raw_packet_qp *raw_packet_qp = &qp->raw_packet_qp; @@@ -1329,7 -1313,7 +1333,7 @@@ rq->flags |= MLX5_IB_RQ_CVLAN_STRIPPING; if (qp->flags & MLX5_IB_QP_PCI_WRITE_END_PADDING) rq->flags |= MLX5_IB_RQ_PCI_WRITE_END_PADDING; - err = create_raw_packet_qp_rq(dev, rq, in); + err = create_raw_packet_qp_rq(dev, rq, in, inlen); if (err) goto err_destroy_sq; @@@ -1574,10 -1558,6 +1578,10 @@@ static int create_rss_raw_qp_tir(struc 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) @@@ -1608,6 -1588,7 +1612,7 @@@ static int create_qp_common(struct mlx5 u32 uidx = MLX5_IB_DEFAULT_UIDX; struct mlx5_ib_create_qp ucmd; struct mlx5_ib_qp_base *base; + int mlx5_st; void *qpc; u32 *in; int err; @@@ -1616,6 -1597,10 +1621,10 @@@ spin_lock_init(&qp->sq.lock); spin_lock_init(&qp->rq.lock); + mlx5_st = to_mlx5_st(init_attr->qp_type); + if (mlx5_st < 0) + return -EINVAL; + if (init_attr->rwq_ind_tbl) { if (!udata) return -ENOSYS; @@@ -1777,7 -1762,7 +1786,7 @@@ qpc = MLX5_ADDR_OF(create_qp_in, in, qpc); - MLX5_SET(qpc, qpc, st, to_mlx5_st(init_attr->qp_type)); + MLX5_SET(qpc, qpc, st, mlx5_st); MLX5_SET(qpc, qpc, pm_state, MLX5_QP_PM_MIGRATED); if (init_attr->qp_type != MLX5_IB_QPT_REG_UMR) @@@ -1891,11 -1876,16 +1900,16 @@@ } } + if (inlen < 0) { + err = -EINVAL; + goto err; + } + if (init_attr->qp_type == IB_QPT_RAW_PACKET || qp->flags & MLX5_IB_QP_UNDERLAY) { qp->raw_packet_qp.sq.ubuffer.buf_addr = ucmd.sq_buf_addr; raw_packet_qp_copy_info(qp, &qp->raw_packet_qp); - err = create_raw_packet_qp(dev, qp, in, pd); + err = create_raw_packet_qp(dev, qp, in, inlen, pd); } else { err = mlx5_core_create_qp(dev->mdev, &base->mqp, in, inlen); } @@@ -2153,6 -2143,7 +2167,6 @@@ static struct ib_qp *mlx5_ib_create_dct struct ib_qp_init_attr *attr, struct mlx5_ib_create_qp *ucmd) { - struct mlx5_ib_dev *dev; struct mlx5_ib_qp *qp; int err = 0; u32 uidx = MLX5_IB_DEFAULT_UIDX; @@@ -2161,6 -2152,8 +2175,6 @@@ if (!attr->srq || !attr->recv_cq) return ERR_PTR(-EINVAL); - dev = to_mdev(pd->device); - err = get_qp_user_index(to_mucontext(pd->uobject->context), ucmd, sizeof(*ucmd), &uidx); if (err) @@@ -3116,8 -3109,10 +3130,10 @@@ static int __mlx5_ib_modify_qp(struct i goto out; if (mlx5_cur >= MLX5_QP_NUM_STATE || mlx5_new >= MLX5_QP_NUM_STATE || - !optab[mlx5_cur][mlx5_new]) + !optab[mlx5_cur][mlx5_new]) { + err = -EINVAL; goto out; + } op = optab[mlx5_cur][mlx5_new]; optpar = ib_mask_to_mlx5_opt(attr_mask); diff --combined drivers/net/dsa/b53/b53_common.c index cd16067265dd,63e02a54d537..78616787f2a3 --- a/drivers/net/dsa/b53/b53_common.c +++ b/drivers/net/dsa/b53/b53_common.c @@@ -814,8 -814,8 +814,8 @@@ void b53_get_strings(struct dsa_switch unsigned int i; for (i = 0; i < mib_size; i++) - memcpy(data + i * ETH_GSTRING_LEN, - mibs[i].name, ETH_GSTRING_LEN); + strlcpy(data + i * ETH_GSTRING_LEN, + mibs[i].name, ETH_GSTRING_LEN); } EXPORT_SYMBOL(b53_get_strings); @@@ -852,7 -852,7 +852,7 @@@ void b53_get_ethtool_stats(struct dsa_s } 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 --combined drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c index 99c9b88d6d34,61022b5f6743..e880be8e3c45 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c @@@ -75,7 -75,6 +75,7 @@@ #include "t4fw_api.h" #include "t4fw_version.h" #include "cxgb4_dcb.h" +#include "srq.h" #include "cxgb4_debugfs.h" #include "clip_tbl.h" #include "l2t.h" @@@ -211,9 -210,6 +211,9 @@@ static void link_report(struct net_devi case 40000: s = "40Gbps"; break; + case 50000: + s = "50Gbps"; + break; case 100000: s = "100Gbps"; break; @@@ -587,10 -583,6 +587,10 @@@ static int fwevtq_handler(struct sge_rs const struct cpl_abort_rpl_rss *p = (void *)rsp; hash_del_filter_rpl(q->adap, p); + } else if (opcode == CPL_SRQ_TABLE_RPL) { + const struct cpl_srq_table_rpl *p = (void *)rsp; + + do_srq_table_rpl(q->adap, p); } else dev_err(q->adap->pdev_dev, "unexpected CPL %#x on FW event queue\n", opcode); @@@ -1741,11 -1733,10 +1741,11 @@@ EXPORT_SYMBOL(cxgb4_sync_txq_pidx) int cxgb4_read_tpte(struct net_device *dev, u32 stag, __be32 *tpte) { - struct adapter *adap; - u32 offset, memtype, memaddr; u32 edc0_size, edc1_size, mc0_size, mc1_size, size; u32 edc0_end, edc1_end, mc0_end, mc1_end; + u32 offset, memtype, memaddr; + struct adapter *adap; + u32 hma_size = 0; int ret; adap = netdev2adap(dev); @@@ -1765,10 -1756,6 +1765,10 @@@ size = t4_read_reg(adap, MA_EXT_MEMORY0_BAR_A); mc0_size = EXT_MEM0_SIZE_G(size) << 20; + if (t4_read_reg(adap, MA_TARGET_MEM_ENABLE_A) & HMA_MUX_F) { + size = t4_read_reg(adap, MA_EXT_MEMORY1_BAR_A); + hma_size = EXT_MEM1_SIZE_G(size) << 20; + } edc0_end = edc0_size; edc1_end = edc0_end + edc1_size; mc0_end = edc1_end + mc0_size; @@@ -1780,10 -1767,7 +1780,10 @@@ memtype = MEM_EDC1; memaddr = offset - edc0_end; } else { - if (offset < mc0_end) { + if (hma_size && (offset < (edc1_end + hma_size))) { + memtype = MEM_HMA; + memaddr = offset - edc1_end; + } else if (offset < mc0_end) { memtype = MEM_MC0; memaddr = offset - edc1_end; } else if (is_t5(adap->params.chip)) { @@@ -2886,11 -2870,11 +2886,11 @@@ static int cxgb_set_tx_maxrate(struct n /* Convert from Mbps to Kbps */ req_rate = rate << 10; - /* Max rate is 10 Gbps */ + /* Max rate is 100 Gbps */ if (req_rate >= SCHED_MAX_RATE_KBPS) { dev_err(adap->pdev_dev, - "Invalid rate %u Mbps, Max rate is %u Gbps\n", - rate, SCHED_MAX_RATE_KBPS); + "Invalid rate %u Mbps, Max rate is %u Mbps\n", + rate, SCHED_MAX_RATE_KBPS >> 10); return -ERANGE; } @@@ -3260,14 -3244,6 +3260,14 @@@ static const struct ethtool_ops cxgb4_m .get_drvinfo = cxgb4_mgmt_get_drvinfo, }; +static void notify_fatal_err(struct work_struct *work) +{ + struct adapter *adap; + + adap = container_of(work, struct adapter, fatal_err_notify_task); + notify_ulds(adap, CXGB4_STATE_FATAL_ERROR); +} + void t4_fatal_err(struct adapter *adap) { int port; @@@ -3292,7 -3268,6 +3292,7 @@@ netif_carrier_off(dev); } dev_alert(adap->pdev_dev, "encountered fatal error, adapter stopped\n"); + queue_work(adap->workq, &adap->fatal_err_notify_task); } static void setup_memwin(struct adapter *adap) @@@ -3323,206 -3298,6 +3323,206 @@@ static void setup_memwin_rdma(struct ad } } +/* HMA Definitions */ + +/* The maximum number of address that can be send in a single FW cmd */ +#define HMA_MAX_ADDR_IN_CMD 5 + +#define HMA_PAGE_SIZE PAGE_SIZE + +#define HMA_MAX_NO_FW_ADDRESS (16 << 10) /* FW supports 16K addresses */ + +#define HMA_PAGE_ORDER \ + ((HMA_PAGE_SIZE < HMA_MAX_NO_FW_ADDRESS) ? \ + ilog2(HMA_MAX_NO_FW_ADDRESS / HMA_PAGE_SIZE) : 0) + +/* The minimum and maximum possible HMA sizes that can be specified in the FW + * configuration(in units of MB). + */ +#define HMA_MIN_TOTAL_SIZE 1 +#define HMA_MAX_TOTAL_SIZE \ + (((HMA_PAGE_SIZE << HMA_PAGE_ORDER) * \ + HMA_MAX_NO_FW_ADDRESS) >> 20) + +static void adap_free_hma_mem(struct adapter *adapter) +{ + struct scatterlist *iter; + struct page *page; + int i; + + if (!adapter->hma.sgt) + return; + + if (adapter->hma.flags & HMA_DMA_MAPPED_FLAG) { + dma_unmap_sg(adapter->pdev_dev, adapter->hma.sgt->sgl, + adapter->hma.sgt->nents, PCI_DMA_BIDIRECTIONAL); + adapter->hma.flags &= ~HMA_DMA_MAPPED_FLAG; + } + + for_each_sg(adapter->hma.sgt->sgl, iter, + adapter->hma.sgt->orig_nents, i) { + page = sg_page(iter); + if (page) + __free_pages(page, HMA_PAGE_ORDER); + } + + kfree(adapter->hma.phy_addr); + sg_free_table(adapter->hma.sgt); + kfree(adapter->hma.sgt); + adapter->hma.sgt = NULL; +} + +static int adap_config_hma(struct adapter *adapter) +{ + struct scatterlist *sgl, *iter; + struct sg_table *sgt; + struct page *newpage; + unsigned int i, j, k; + u32 param, hma_size; + unsigned int ncmds; + size_t page_size; + u32 page_order; + int node, ret; + + /* HMA is supported only for T6+ cards. + * Avoid initializing HMA in kdump kernels. + */ + if (is_kdump_kernel() || + CHELSIO_CHIP_VERSION(adapter->params.chip) < CHELSIO_T6) + return 0; + + /* Get the HMA region size required by fw */ + param = (FW_PARAMS_MNEM_V(FW_PARAMS_MNEM_DEV) | + FW_PARAMS_PARAM_X_V(FW_PARAMS_PARAM_DEV_HMA_SIZE)); + ret = t4_query_params(adapter, adapter->mbox, adapter->pf, 0, + 1, &param, &hma_size); + /* An error means card has its own memory or HMA is not supported by + * the firmware. Return without any errors. + */ + if (ret || !hma_size) + return 0; + + if (hma_size < HMA_MIN_TOTAL_SIZE || + hma_size > HMA_MAX_TOTAL_SIZE) { + dev_err(adapter->pdev_dev, + "HMA size %uMB beyond bounds(%u-%lu)MB\n", + hma_size, HMA_MIN_TOTAL_SIZE, HMA_MAX_TOTAL_SIZE); + return -EINVAL; + } + + page_size = HMA_PAGE_SIZE; + page_order = HMA_PAGE_ORDER; + adapter->hma.sgt = kzalloc(sizeof(*adapter->hma.sgt), GFP_KERNEL); + if (unlikely(!adapter->hma.sgt)) { + dev_err(adapter->pdev_dev, "HMA SG table allocation failed\n"); + return -ENOMEM; + } + sgt = adapter->hma.sgt; + /* FW returned value will be in MB's + */ + sgt->orig_nents = (hma_size << 20) / (page_size << page_order); + if (sg_alloc_table(sgt, sgt->orig_nents, GFP_KERNEL)) { + dev_err(adapter->pdev_dev, "HMA SGL allocation failed\n"); + kfree(adapter->hma.sgt); + adapter->hma.sgt = NULL; + return -ENOMEM; + } + + sgl = adapter->hma.sgt->sgl; + node = dev_to_node(adapter->pdev_dev); + for_each_sg(sgl, iter, sgt->orig_nents, i) { + newpage = alloc_pages_node(node, __GFP_NOWARN | GFP_KERNEL, + page_order); + if (!newpage) { + dev_err(adapter->pdev_dev, + "Not enough memory for HMA page allocation\n"); + ret = -ENOMEM; + goto free_hma; + } + sg_set_page(iter, newpage, page_size << page_order, 0); + } + + sgt->nents = dma_map_sg(adapter->pdev_dev, sgl, sgt->orig_nents, + DMA_BIDIRECTIONAL); + if (!sgt->nents) { + dev_err(adapter->pdev_dev, + "Not enough memory for HMA DMA mapping"); + ret = -ENOMEM; + goto free_hma; + } + adapter->hma.flags |= HMA_DMA_MAPPED_FLAG; + + adapter->hma.phy_addr = kcalloc(sgt->nents, sizeof(dma_addr_t), + GFP_KERNEL); + if (unlikely(!adapter->hma.phy_addr)) + goto free_hma; + + for_each_sg(sgl, iter, sgt->nents, i) { + newpage = sg_page(iter); + adapter->hma.phy_addr[i] = sg_dma_address(iter); + } + + ncmds = DIV_ROUND_UP(sgt->nents, HMA_MAX_ADDR_IN_CMD); + /* Pass on the addresses to firmware */ + for (i = 0, k = 0; i < ncmds; i++, k += HMA_MAX_ADDR_IN_CMD) { + struct fw_hma_cmd hma_cmd; + u8 naddr = HMA_MAX_ADDR_IN_CMD; + u8 soc = 0, eoc = 0; + u8 hma_mode = 1; /* Presently we support only Page table mode */ + + soc = (i == 0) ? 1 : 0; + eoc = (i == ncmds - 1) ? 1 : 0; + + /* For last cmd, set naddr corresponding to remaining + * addresses + */ + if (i == ncmds - 1) { + naddr = sgt->nents % HMA_MAX_ADDR_IN_CMD; + naddr = naddr ? naddr : HMA_MAX_ADDR_IN_CMD; + } + memset(&hma_cmd, 0, sizeof(hma_cmd)); + hma_cmd.op_pkd = htonl(FW_CMD_OP_V(FW_HMA_CMD) | + FW_CMD_REQUEST_F | FW_CMD_WRITE_F); + hma_cmd.retval_len16 = htonl(FW_LEN16(hma_cmd)); + + hma_cmd.mode_to_pcie_params = + htonl(FW_HMA_CMD_MODE_V(hma_mode) | + FW_HMA_CMD_SOC_V(soc) | FW_HMA_CMD_EOC_V(eoc)); + + /* HMA cmd size specified in MB's */ + hma_cmd.naddr_size = + htonl(FW_HMA_CMD_SIZE_V(hma_size) | + FW_HMA_CMD_NADDR_V(naddr)); + + /* Total Page size specified in units of 4K */ + hma_cmd.addr_size_pkd = + htonl(FW_HMA_CMD_ADDR_SIZE_V + ((page_size << page_order) >> 12)); + + /* Fill the 5 addresses */ + for (j = 0; j < naddr; j++) { + hma_cmd.phy_address[j] = + cpu_to_be64(adapter->hma.phy_addr[j + k]); + } + ret = t4_wr_mbox(adapter, adapter->mbox, &hma_cmd, + sizeof(hma_cmd), &hma_cmd); + if (ret) { + dev_err(adapter->pdev_dev, + "HMA FW command failed with err %d\n", ret); + goto free_hma; + } + } + + if (!ret) + dev_info(adapter->pdev_dev, + "Reserved %uMB host memory for HMA\n", hma_size); + return ret; + +free_hma: + adap_free_hma_mem(adapter); + return ret; +} + static int adap_init1(struct adapter *adap, struct fw_caps_config_cmd *c) { u32 v; @@@ -3976,12 -3751,6 +3976,12 @@@ static int adap_init0_config(struct ada if (ret < 0) goto bye; + /* We will proceed even if HMA init fails. */ + ret = adap_config_hma(adapter); + if (ret) + dev_err(adapter->pdev_dev, + "HMA configuration failed with error %d\n", ret); + /* * And finally tell the firmware to initialize itself using the * parameters from the Configuration File. @@@ -4188,11 -3957,6 +4188,11 @@@ static int adap_init0(struct adapter *a * effect. Otherwise, it's time to try initializing the adapter. */ if (state == DEV_STATE_INIT) { + ret = adap_config_hma(adap); + if (ret) + dev_err(adap->pdev_dev, + "HMA configuration failed with error %d\n", + ret); dev_info(adap->pdev_dev, "Coming up as %s: "\ "Adapter already initialized\n", adap->flags & MASTER_PF ? "MASTER" : "SLAVE"); @@@ -4472,20 -4236,6 +4472,20 @@@ adap->vres.pbl.start = val[4]; adap->vres.pbl.size = val[5] - val[4] + 1; + params[0] = FW_PARAM_PFVF(SRQ_START); + params[1] = FW_PARAM_PFVF(SRQ_END); + ret = t4_query_params(adap, adap->mbox, adap->pf, 0, 2, + params, val); + if (!ret) { + adap->vres.srq.start = val[0]; + adap->vres.srq.size = val[1] - val[0] + 1; + } + if (adap->vres.srq.size) { + adap->srq = t4_init_srq(adap->vres.srq.size); + if (!adap->srq) + dev_warn(&adap->pdev->dev, "could not allocate SRQ, continuing\n"); + } + params[0] = FW_PARAM_PFVF(SQRQ_START); params[1] = FW_PARAM_PFVF(SQRQ_END); params[2] = FW_PARAM_PFVF(CQ_START); @@@ -4519,18 -4269,6 +4519,18 @@@ "max_ordird_qp %d max_ird_adapter %d\n", adap->params.max_ordird_qp, adap->params.max_ird_adapter); + + /* Enable write_with_immediate if FW supports it */ + params[0] = FW_PARAM_DEV(RDMA_WRITE_WITH_IMM); + ret = t4_query_params(adap, adap->mbox, adap->pf, 0, 1, params, + val); + adap->params.write_w_imm_support = (ret == 0 && val[0] != 0); + + /* Enable write_cmpl if FW supports it */ + params[0] = FW_PARAM_DEV(RI_WRITE_CMPL_WR); + ret = t4_query_params(adap, adap->mbox, adap->pf, 0, 1, params, + val); + adap->params.write_cmpl_support = (ret == 0 && val[0] != 0); adap->num_ofld_uld += 2; } if (caps_cmd.iscsicaps) { @@@ -4608,7 -4346,6 +4608,7 @@@ * happened to HW/FW, stop issuing commands. */ bye: + adap_free_hma_mem(adap); kfree(adap->sge.egr_map); kfree(adap->sge.ingr_map); kfree(adap->sge.starving_fl); @@@ -5166,7 -4903,6 +5166,7 @@@ static void free_some_resources(struct kvfree(adapter->smt); kvfree(adapter->l2t); + kvfree(adapter->srq); t4_cleanup_sched(adapter); kvfree(adapter->tids.tid_tab); cxgb4_cleanup_tc_flower(adapter); @@@ -5234,7 -4970,6 +5234,6 @@@ static void cxgb4_mgmt_setup(struct net /* Initialize the device structure. */ dev->netdev_ops = &cxgb4_mgmt_netdev_ops; dev->ethtool_ops = &cxgb4_mgmt_ethtool_ops; - dev->needs_free_netdev = true; } static int cxgb4_iov_configure(struct pci_dev *pdev, int num_vfs) @@@ -5445,6 -5180,8 +5444,8 @@@ static int init_one(struct pci_dev *pde adapter->name = pci_name(pdev); adapter->mbox = func; adapter->pf = func; + adapter->params.chip = chip; + adapter->adap_idx = adap_idx; adapter->msg_enable = DFLT_MSG_ENABLE; adapter->mbox_log = kzalloc(sizeof(*adapter->mbox_log) + (sizeof(struct mbox_cmd) * @@@ -5520,7 -5257,6 +5521,7 @@@ INIT_WORK(&adapter->tid_release_task, process_tid_release_list); INIT_WORK(&adapter->db_full_task, process_db_full); INIT_WORK(&adapter->db_drop_task, process_db_drop); + INIT_WORK(&adapter->fatal_err_notify_task, notify_fatal_err); err = t4_prep_adapter(adapter); if (err) @@@ -5838,8 -5574,6 +5839,8 @@@ static void remove_one(struct pci_dev * t4_uld_clean_up(adapter); } + adap_free_hma_mem(adapter); + disable_interrupts(adapter); for_each_port(adapter, i) diff --combined drivers/net/ethernet/freescale/dpaa/dpaa_eth.c index 159dc2df878d,e4ec32a9ca15..fd43f98ddbe7 --- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c +++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c @@@ -454,16 -454,6 +454,16 @@@ static void dpaa_set_rx_mode(struct net 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", @@@ -1926,10 -1916,8 +1926,10 @@@ static int skb_to_sg_fd(struct dpaa_pri 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, @@@ -1942,9 -1930,9 +1942,9 @@@ 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); @@@ -1954,16 -1942,15 +1954,16 @@@ 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); @@@ -2021,7 -2008,6 +2021,6 @@@ static inline int dpaa_xmit(struct dpaa } if (unlikely(err < 0)) { - percpu_stats->tx_errors++; percpu_stats->tx_fifo_errors++; return err; } @@@ -2065,23 -2051,19 +2064,23 @@@ static int dpaa_start_xmit(struct sk_bu /* 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)) @@@ -2218,8 -2200,14 +2217,8 @@@ static enum qman_cb_dqrr_result rx_erro 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; } @@@ -2289,7 -2277,6 +2288,6 @@@ static enum qman_cb_dqrr_result rx_defa vaddr = phys_to_virt(addr); prefetch(vaddr + qm_fd_get_offset(fd)); - fd_format = qm_fd_get_format(fd); /* The only FD types that we may receive are contig and S/G */ WARN_ON((fd_format != qm_fd_contig) && (fd_format != qm_fd_sg)); @@@ -2322,8 -2309,10 +2320,10 @@@ skb_len = skb->len; - if (unlikely(netif_receive_skb(skb) == NET_RX_DROP)) + if (unlikely(netif_receive_skb(skb) == NET_RX_DROP)) { + percpu_stats->rx_dropped++; return qman_cb_dqrr_consume; + } percpu_stats->rx_packets++; percpu_stats->rx_bytes += skb_len; @@@ -2777,7 -2766,7 +2777,7 @@@ static int dpaa_eth_probe(struct platfo 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); @@@ -2871,7 -2860,7 +2871,7 @@@ static int dpaa_remove(struct platform_ struct device *dev; int err; - dev = &pdev->dev; + dev = pdev->dev.parent; net_dev = dev_get_drvdata(dev); priv = netdev_priv(net_dev); diff --combined drivers/net/ethernet/freescale/fman/fman_dtsec.c index 9a581faaa742,7af31ddd093f..57b1e2b47c0a --- a/drivers/net/ethernet/freescale/fman/fman_dtsec.c +++ b/drivers/net/ethernet/freescale/fman/fman_dtsec.c @@@ -1100,7 -1100,7 +1100,7 @@@ int dtsec_add_hash_mac_address(struct f set_bucket(dtsec->regs, bucket, true); /* Create element to be added to the driver hash table */ - hash_entry = kmalloc(sizeof(*hash_entry), GFP_KERNEL); + hash_entry = kmalloc(sizeof(*hash_entry), GFP_ATOMIC); if (!hash_entry) return -ENOMEM; hash_entry->addr = addr; @@@ -1117,25 -1117,6 +1117,25 @@@ 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(&regs->rctrl); + if (enable) + tmp |= RCTRL_MPROM; + else + tmp &= ~RCTRL_MPROM; + + iowrite32be(tmp, &regs->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 --combined drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c index ba338428ffd1,996dc099cd58..3c0d882ba183 --- 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 +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 &lt;jiri(a)mellanox.com&gt; * * Redistribution and use in source and binary forms, with or without @@@ -443,6 -443,17 +443,17 @@@ int mlxsw_afa_block_jump(struct mlxsw_a } EXPORT_SYMBOL(mlxsw_afa_block_jump); + int mlxsw_afa_block_terminate(struct mlxsw_afa_block *block) + { + if (block->finished) + return -EINVAL; + mlxsw_afa_set_goto_set(block->cur_set, + MLXSW_AFA_SET_GOTO_BINDING_CMD_TERM, 0); + block->finished = true; + return 0; + } + EXPORT_SYMBOL(mlxsw_afa_block_terminate); + static struct mlxsw_afa_fwd_entry * mlxsw_afa_fwd_entry_create(struct mlxsw_afa *mlxsw_afa, u8 local_port) { @@@ -838,6 -849,7 +849,6 @@@ struct mlxsw_afa_mirror struct mlxsw_afa_resource resource; int span_id; u8 local_in_port; - u8 local_out_port; bool ingress; }; @@@ -847,7 -859,7 +858,7 @@@ mlxsw_afa_mirror_destroy(struct mlxsw_a { block->afa->ops->mirror_del(block->afa->ops_priv, mirror->local_in_port, - mirror->local_out_port, + mirror->span_id, mirror->ingress); kfree(mirror); } @@@ -863,8 -875,9 +874,8 @@@ mlxsw_afa_mirror_destructor(struct mlxs } 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; @@@ -874,12 -887,13 +885,12 @@@ 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); @@@ -906,13 -920,13 +917,13 @@@ mlxsw_afa_block_append_allocated_mirror } 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 --combined drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h index 6dd601703c99,b91f2b0829b0..3a155d104384 --- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h +++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h @@@ -36,7 -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; @@@ -49,10 -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); }; @@@ -67,13 -65,13 +67,14 @@@ char *mlxsw_afa_block_first_set(struct u32 mlxsw_afa_block_first_set_kvdl_index(struct mlxsw_afa_block *block); int mlxsw_afa_block_continue(struct mlxsw_afa_block *block); int mlxsw_afa_block_jump(struct mlxsw_afa_block *block, u16 group_id); + int mlxsw_afa_block_terminate(struct mlxsw_afa_block *block); int mlxsw_afa_block_append_drop(struct mlxsw_afa_block *block); 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 --combined drivers/net/ethernet/mellanox/mlxsw/spectrum.h index 92194a9b2caf,92064db2ae44..21bee8f19894 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h @@@ -70,23 -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; @@@ -118,13 -111,35 +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; - - /* Whether this is a directly bound mirror (port-to-port) or an ACL. */ - bool bound; -}; - -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; }; @@@ -211,8 -226,6 +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 { @@@ -250,7 -263,6 +250,7 @@@ 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; @@@ -388,6 -400,16 +388,6 @@@ struct mlxsw_sp_port *mlxsw_sp_port_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 @@@ -443,7 -465,6 +443,7 @@@ int mlxsw_sp_kvdl_alloc_size_query(stru 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; @@@ -535,6 -556,7 +535,7 @@@ void mlxsw_sp_acl_rulei_keymask_buf(str int mlxsw_sp_acl_rulei_act_continue(struct mlxsw_sp_acl_rule_info *rulei); int mlxsw_sp_acl_rulei_act_jump(struct mlxsw_sp_acl_rule_info *rulei, u16 group_id); + int mlxsw_sp_acl_rulei_act_terminate(struct mlxsw_sp_acl_rule_info *rulei); int mlxsw_sp_acl_rulei_act_drop(struct mlxsw_sp_acl_rule_info *rulei); int mlxsw_sp_acl_rulei_act_trap(struct mlxsw_sp_acl_rule_info *rulei); int mlxsw_sp_acl_rulei_act_mirror(struct mlxsw_sp *mlxsw_sp, diff --combined drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c index 1c1601a43978,92d90ed7207e..79b1fa27a9a4 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c @@@ -160,13 -160,6 +160,13 @@@ bool mlxsw_sp_acl_block_disabled(struc return block->disable_count; } +static bool +mlxsw_sp_acl_ruleset_is_singular(const struct mlxsw_sp_acl_ruleset *ruleset) +{ + /* We hold a reference on ruleset ourselves */ + return ruleset->ref_count == 2; +} + static int mlxsw_sp_acl_ruleset_bind(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_acl_block *block, @@@ -348,8 -341,21 +348,8 @@@ mlxsw_sp_acl_ruleset_create(struct mlxs if (err) goto err_ht_insert; - if (!chain_index) { - /* We only need ruleset with chain index 0, the implicit one, - * to be directly bound to device. The rest of the rulesets - * are bound by "Goto action set". - */ - err = mlxsw_sp_acl_ruleset_block_bind(mlxsw_sp, ruleset, block); - if (err) - goto err_ruleset_bind; - } - return ruleset; -err_ruleset_bind: - rhashtable_remove_fast(&acl->ruleset_ht, &ruleset->ht_node, - mlxsw_sp_acl_ruleset_ht_params); err_ht_insert: ops->ruleset_del(mlxsw_sp, ruleset->priv); err_ops_ruleset_add: @@@ -363,8 -369,12 +363,8 @@@ static void mlxsw_sp_acl_ruleset_destro struct mlxsw_sp_acl_ruleset *ruleset) { const struct mlxsw_sp_acl_profile_ops *ops = ruleset->ht_key.ops; - struct mlxsw_sp_acl_block *block = ruleset->ht_key.block; - u32 chain_index = ruleset->ht_key.chain_index; struct mlxsw_sp_acl *acl = mlxsw_sp->acl; - if (!chain_index) - mlxsw_sp_acl_ruleset_block_unbind(mlxsw_sp, ruleset, block); rhashtable_remove_fast(&acl->ruleset_ht, &ruleset->ht_node, mlxsw_sp_acl_ruleset_ht_params); ops->ruleset_del(mlxsw_sp, ruleset->priv); @@@ -518,6 -528,11 +518,11 @@@ int mlxsw_sp_acl_rulei_act_jump(struct return mlxsw_afa_block_jump(rulei->act_block, group_id); } + int mlxsw_sp_acl_rulei_act_terminate(struct mlxsw_sp_acl_rule_info *rulei) + { + return mlxsw_afa_block_terminate(rulei->act_block); + } + int mlxsw_sp_acl_rulei_act_drop(struct mlxsw_sp_acl_rule_info *rulei) { return mlxsw_afa_block_append_drop(rulei->act_block); @@@ -562,6 -577,7 +567,6 @@@ int mlxsw_sp_acl_rulei_act_mirror(struc 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)) @@@ -570,10 -586,16 +575,10 @@@ 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); } @@@ -678,25 -700,10 +683,25 @@@ int mlxsw_sp_acl_rule_add(struct mlxsw_ if (err) goto err_rhashtable_insert; + if (!ruleset->ht_key.chain_index && + mlxsw_sp_acl_ruleset_is_singular(ruleset)) { + /* We only need ruleset with chain index 0, the implicit + * one, to be directly bound to device. The rest of the + * rulesets are bound by "Goto action set". + */ + err = mlxsw_sp_acl_ruleset_block_bind(mlxsw_sp, ruleset, + ruleset->ht_key.block); + if (err) + goto err_ruleset_block_bind; + } + list_add_tail(&rule->list, &mlxsw_sp->acl->rules); ruleset->ht_key.block->rule_count++; return 0; +err_ruleset_block_bind: + rhashtable_remove_fast(&ruleset->rule_ht, &rule->ht_node, + mlxsw_sp_acl_rule_ht_params); err_rhashtable_insert: ops->rule_del(mlxsw_sp, rule->priv); return err; @@@ -710,10 -717,6 +715,10 @@@ void mlxsw_sp_acl_rule_del(struct mlxsw ruleset->ht_key.block->rule_count--; list_del(&rule->list); + if (!ruleset->ht_key.chain_index && + mlxsw_sp_acl_ruleset_is_singular(ruleset)) + mlxsw_sp_acl_ruleset_block_unbind(mlxsw_sp, ruleset, + ruleset->ht_key.block); rhashtable_remove_fast(&ruleset->rule_ht, &rule->ht_node, mlxsw_sp_acl_rule_ht_params); ops->rule_del(mlxsw_sp, rule->priv); diff --combined drivers/net/ethernet/mellanox/mlxsw/spectrum_span.h index 948aceb512c5,000000000000..4b87ec20e658 mode 100644,000000..100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.h @@@ -1,104 -1,0 +1,107 @@@ +/* + * 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; ++ ++ /* Whether this is a directly bound mirror (port-to-port) or an ACL. */ ++ bool bound; +}; + +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 --combined drivers/net/ethernet/qlogic/qed/qed_iwarp.c index 03ad4eeac7f8,d5d02be72947..69051e98aff9 --- a/drivers/net/ethernet/qlogic/qed/qed_iwarp.c +++ b/drivers/net/ethernet/qlogic/qed/qed_iwarp.c @@@ -1703,6 -1703,13 +1703,13 @@@ qed_iwarp_parse_rx_pkt(struct qed_hwfn iph = (struct iphdr *)((u8 *)(ethh) + eth_hlen); if (eth_type == ETH_P_IP) { + if (iph->protocol != IPPROTO_TCP) { + DP_NOTICE(p_hwfn, + "Unexpected ip protocol on ll2 %x\n", + iph->protocol); + return -EINVAL; + } + cm_info->local_ip[0] = ntohl(iph->daddr); cm_info->remote_ip[0] = ntohl(iph->saddr); cm_info->ip_version = TCP_IPV4; @@@ -1711,6 -1718,14 +1718,14 @@@ *payload_len = ntohs(iph->tot_len) - ip_hlen; } else if (eth_type == ETH_P_IPV6) { ip6h = (struct ipv6hdr *)iph; + + if (ip6h->nexthdr != IPPROTO_TCP) { + DP_NOTICE(p_hwfn, + "Unexpected ip protocol on ll2 %x\n", + iph->protocol); + return -EINVAL; + } + for (i = 0; i < 4; i++) { cm_info->local_ip[i] = ntohl(ip6h->daddr.in6_u.u6_addr32[i]); @@@ -1784,7 -1799,7 +1799,7 @@@ 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" @@@ -1928,8 -1943,8 +1943,8 @@@ qed_iwarp_update_fpdu_length(struct qed /* Missing lower byte is now available */ mpa_len = fpdu->fpdu_length | *mpa_data; fpdu->fpdu_length = QED_IWARP_FPDU_LEN_WITH_PAD(mpa_len); - fpdu->mpa_frag_len = fpdu->fpdu_length; /* one byte of hdr */ + fpdu->mpa_frag_len = 1; fpdu->incomplete_bytes = fpdu->fpdu_length - 1; DP_VERBOSE(p_hwfn, QED_MSG_RDMA, diff --combined drivers/net/ethernet/ti/cpsw.c index 8af8891078e2,b2b30c9df037..1b4af54a4968 --- a/drivers/net/ethernet/ti/cpsw.c +++ b/drivers/net/ethernet/ti/cpsw.c @@@ -120,18 -120,14 +120,18 @@@ do { #define CPDMA_RXCP 0x60 #define CPSW_POLL_WEIGHT 64 +#define CPSW_RX_VLAN_ENCAP_HDR_SIZE 4 #define CPSW_MIN_PACKET_SIZE (VLAN_ETH_ZLEN) -#define CPSW_MAX_PACKET_SIZE (VLAN_ETH_FRAME_LEN + ETH_FCS_LEN) +#define CPSW_MAX_PACKET_SIZE (VLAN_ETH_FRAME_LEN +\ + ETH_FCS_LEN +\ + CPSW_RX_VLAN_ENCAP_HDR_SIZE) #define RX_PRIORITY_MAPPING 0x76543210 #define TX_PRIORITY_MAPPING 0x33221100 #define CPDMA_TX_PRIORITY_MAP 0x01234567 #define CPSW_VLAN_AWARE BIT(1) +#define CPSW_RX_VLAN_ENCAP BIT(2) #define CPSW_ALE_VLAN_AWARE 1 #define CPSW_FIFO_NORMAL_MODE (0 << 16) @@@ -152,18 -148,6 +152,18 @@@ #define CPSW_MAX_QUEUES 8 #define CPSW_CPDMA_DESCS_POOL_SIZE_DEFAULT 256 +#define CPSW_RX_VLAN_ENCAP_HDR_PRIO_SHIFT 29 +#define CPSW_RX_VLAN_ENCAP_HDR_PRIO_MSK GENMASK(2, 0) +#define CPSW_RX_VLAN_ENCAP_HDR_VID_SHIFT 16 +#define CPSW_RX_VLAN_ENCAP_HDR_PKT_TYPE_SHIFT 8 +#define CPSW_RX_VLAN_ENCAP_HDR_PKT_TYPE_MSK GENMASK(1, 0) +enum { + CPSW_RX_VLAN_ENCAP_HDR_PKT_VLAN_TAG = 0, + CPSW_RX_VLAN_ENCAP_HDR_PKT_RESERV, + CPSW_RX_VLAN_ENCAP_HDR_PKT_PRIO_TAG, + CPSW_RX_VLAN_ENCAP_HDR_PKT_UNTAG, +}; + static int debug_level; module_param(debug_level, int, 0); MODULE_PARM_DESC(debug_level, "cpsw debug level (NETIF_MSG bits)"); @@@ -734,49 -718,6 +734,49 @@@ static void cpsw_tx_handler(void *token dev_kfree_skb_any(skb); } +static void cpsw_rx_vlan_encap(struct sk_buff *skb) +{ + struct cpsw_priv *priv = netdev_priv(skb->dev); + struct cpsw_common *cpsw = priv->cpsw; + u32 rx_vlan_encap_hdr = *((u32 *)skb->data); + u16 vtag, vid, prio, pkt_type; + + /* Remove VLAN header encapsulation word */ + skb_pull(skb, CPSW_RX_VLAN_ENCAP_HDR_SIZE); + + pkt_type = (rx_vlan_encap_hdr >> + CPSW_RX_VLAN_ENCAP_HDR_PKT_TYPE_SHIFT) & + CPSW_RX_VLAN_ENCAP_HDR_PKT_TYPE_MSK; + /* Ignore unknown & Priority-tagged packets*/ + if (pkt_type == CPSW_RX_VLAN_ENCAP_HDR_PKT_RESERV || + pkt_type == CPSW_RX_VLAN_ENCAP_HDR_PKT_PRIO_TAG) + return; + + vid = (rx_vlan_encap_hdr >> + CPSW_RX_VLAN_ENCAP_HDR_VID_SHIFT) & + VLAN_VID_MASK; + /* Ignore vid 0 and pass packet as is */ + if (!vid) + return; + /* Ignore default vlans in dual mac mode */ + if (cpsw->data.dual_emac && + vid == cpsw->slaves[priv->emac_port].port_vlan) + return; + + prio = (rx_vlan_encap_hdr >> + CPSW_RX_VLAN_ENCAP_HDR_PRIO_SHIFT) & + CPSW_RX_VLAN_ENCAP_HDR_PRIO_MSK; + + vtag = (prio << VLAN_PRIO_SHIFT) | vid; + __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), vtag); + + /* strip vlan tag for VLAN-tagged packet */ + if (pkt_type == CPSW_RX_VLAN_ENCAP_HDR_PKT_VLAN_TAG) { + memmove(skb->data + VLAN_HLEN, skb->data, 2 * ETH_ALEN); + skb_pull(skb, VLAN_HLEN); + } +} + static void cpsw_rx_handler(void *token, int len, int status) { struct cpdma_chan *ch; @@@ -811,8 -752,6 +811,8 @@@ if (new_skb) { skb_copy_queue_mapping(new_skb, skb); skb_put(skb, len); + if (status & CPDMA_RX_VLAN_ENCAP) + cpsw_rx_vlan_encap(skb); cpts_rx_timestamp(cpsw->cpts, skb); skb->protocol = eth_type_trans(skb, ndev); netif_receive_skb(skb); @@@ -1075,7 -1014,8 +1075,8 @@@ static void _cpsw_adjust_link(struct cp /* set speed_in input in case RMII mode is used in 100Mbps */ if (phy->speed == 100) mac_control |= BIT(15); - else if (phy->speed == 10) + /* in band mode only works in 10Mbps RGMII mode */ + else if ((phy->speed == 10) && phy_interface_is_rgmii(phy)) mac_control |= BIT(18); /* In Band mode */ if (priv->rx_pause) @@@ -1467,7 -1407,7 +1468,7 @@@ static void cpsw_init_host_port(struct cpsw_ale_control_set(cpsw->ale, HOST_PORT_NUM, ALE_VLAN_AWARE, CPSW_ALE_VLAN_AWARE); control_reg = readl(&cpsw->regs->control); - control_reg |= CPSW_VLAN_AWARE; + control_reg |= CPSW_VLAN_AWARE | CPSW_RX_VLAN_ENCAP; writel(control_reg, &cpsw->regs->control); fifo_mode = (cpsw->data.dual_emac) ? CPSW_FIFO_DUAL_MAC_MODE : CPSW_FIFO_NORMAL_MODE; @@@ -3183,7 -3123,7 +3184,7 @@@ static int cpsw_probe(struct platform_d cpsw->quirk_irq = true; } - ndev->features |= NETIF_F_HW_VLAN_CTAG_FILTER; + ndev->features |= NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_HW_VLAN_CTAG_RX; ndev->netdev_ops = &cpsw_netdev_ops; ndev->ethtool_ops = &cpsw_ethtool_ops; diff --combined drivers/net/hyperv/netvsc.c index aa95e81af6e5,7472172823f3..4123d081b1c7 --- a/drivers/net/hyperv/netvsc.c +++ b/drivers/net/hyperv/netvsc.c @@@ -36,7 -36,6 +36,7 @@@ #include <asm/sync_bitops.h> #include "hyperv_net.h" +#include "netvsc_trace.h" /* * Switch the data path from the synthetic interface to the VF @@@ -58,8 -57,6 +58,8 @@@ void netvsc_switch_datapath(struct net_ init_pkt->msg.v4_msg.active_dp.active_datapath = NVSP_DATAPATH_SYNTHETIC; + trace_nvsp_send(ndev, init_pkt); + vmbus_sendpacket(dev->channel, init_pkt, sizeof(struct nvsp_message), (unsigned long)init_pkt, @@@ -93,6 -90,11 +93,11 @@@ static void free_netvsc_device(struct r = container_of(head, struct netvsc_device, rcu); int i; + kfree(nvdev->extension); + vfree(nvdev->recv_buf); + vfree(nvdev->send_buf); + kfree(nvdev->send_section_map); + for (i = 0; i < VRSS_CHANNEL_MAX; i++) vfree(nvdev->chan_table[i].mrc.slots); @@@ -127,8 -129,6 +132,8 @@@ static void netvsc_revoke_buf(struct hv revoke_packet->msg.v1_msg. revoke_recv_buf.id = NETVSC_RECEIVE_BUFFER_ID; + trace_nvsp_send(ndev, revoke_packet); + ret = vmbus_sendpacket(device->channel, revoke_packet, sizeof(struct nvsp_message), @@@ -169,8 -169,6 +174,8 @@@ revoke_packet->msg.v1_msg.revoke_send_buf.id = NETVSC_SEND_BUFFER_ID; + trace_nvsp_send(ndev, revoke_packet); + ret = vmbus_sendpacket(device->channel, revoke_packet, sizeof(struct nvsp_message), @@@ -218,12 -216,6 +223,6 @@@ static void netvsc_teardown_gpadl(struc net_device->recv_buf_gpadl_handle = 0; } - if (net_device->recv_buf) { - /* Free up the receive buffer */ - vfree(net_device->recv_buf); - net_device->recv_buf = NULL; - } - if (net_device->send_buf_gpadl_handle) { ret = vmbus_teardown_gpadl(device->channel, net_device->send_buf_gpadl_handle); @@@ -238,12 -230,6 +237,6 @@@ } net_device->send_buf_gpadl_handle = 0; } - if (net_device->send_buf) { - /* Free up the send buffer */ - vfree(net_device->send_buf); - net_device->send_buf = NULL; - } - kfree(net_device->send_section_map); } int netvsc_alloc_recv_comp_ring(struct netvsc_device *net_device, u32 q_idx) @@@ -312,8 -298,6 +305,8 @@@ static int netvsc_init_buf(struct hv_de init_packet->msg.v1_msg. send_recv_buf.id = NETVSC_RECEIVE_BUFFER_ID; + trace_nvsp_send(ndev, init_packet); + /* Send the gpadl notification request */ ret = vmbus_sendpacket(device->channel, init_packet, sizeof(struct nvsp_message), @@@ -393,8 -377,6 +386,8 @@@ net_device->send_buf_gpadl_handle; init_packet->msg.v1_msg.send_send_buf.id = NETVSC_SEND_BUFFER_ID; + trace_nvsp_send(ndev, init_packet); + /* Send the gpadl notification request */ ret = vmbus_sendpacket(device->channel, init_packet, sizeof(struct nvsp_message), @@@ -463,8 -445,6 +456,8 @@@ static int negotiate_nvsp_ver(struct hv init_packet->msg.init_msg.init.min_protocol_ver = nvsp_ver; init_packet->msg.init_msg.init.max_protocol_ver = nvsp_ver; + trace_nvsp_send(ndev, init_packet); + /* Send the init request */ ret = vmbus_sendpacket(device->channel, init_packet, sizeof(struct nvsp_message), @@@ -497,8 -477,6 +490,8 @@@ init_packet->msg.v2_msg.send_ndis_config.capability.teaming = 1; } + trace_nvsp_send(ndev, init_packet); + ret = vmbus_sendpacket(device->channel, init_packet, sizeof(struct nvsp_message), (unsigned long)init_packet, @@@ -511,7 -489,6 +504,7 @@@ static int netvsc_connect_vsp(struct hv struct netvsc_device *net_device, const struct netvsc_device_info *device_info) { + struct net_device *ndev = hv_get_drvdata(device); static const u32 ver_list[] = { NVSP_PROTOCOL_VERSION_1, NVSP_PROTOCOL_VERSION_2, NVSP_PROTOCOL_VERSION_4, NVSP_PROTOCOL_VERSION_5 @@@ -552,8 -529,6 +545,8 @@@ send_ndis_ver.ndis_minor_ver = ndis_version & 0xFFFF; + trace_nvsp_send(ndev, init_packet); + /* Send the init request */ ret = vmbus_sendpacket(device->channel, init_packet, sizeof(struct nvsp_message), @@@ -580,26 -555,29 +573,29 @@@ void netvsc_device_remove(struct hv_dev = rtnl_dereference(net_device_ctx->nvdev); int i; - cancel_work_sync(&net_device->subchan_work); - netvsc_revoke_buf(device, net_device); RCU_INIT_POINTER(net_device_ctx->nvdev, NULL); + /* And disassociate NAPI context from device */ + for (i = 0; i < net_device->num_chn; i++) + netif_napi_del(&net_device->chan_table[i].napi); + /* * At this point, no one should be accessing net_device * except in here */ netdev_dbg(ndev, "net device safe to remove\n"); + /* older versions require that buffer be revoked before close */ + if (net_device->nvsp_version < NVSP_PROTOCOL_VERSION_4) + netvsc_teardown_gpadl(device, net_device); + /* Now, we can close the channel safely */ vmbus_close(device->channel); - netvsc_teardown_gpadl(device, net_device); - - /* And dissassociate NAPI context from device */ - for (i = 0; i < net_device->num_chn; i++) - netif_napi_del(&net_device->chan_table[i].napi); + if (net_device->nvsp_version >= NVSP_PROTOCOL_VERSION_4) + netvsc_teardown_gpadl(device, net_device); /* Release all resources */ free_netvsc_device_rcu(net_device); @@@ -663,14 -641,18 +659,18 @@@ static void netvsc_send_tx_complete(str queue_sends = atomic_dec_return(&net_device->chan_table[q_idx].queue_sends); - if (net_device->destroy && queue_sends == 0) - wake_up(&net_device->wait_drain); - - if (netif_tx_queue_stopped(netdev_get_tx_queue(ndev, q_idx)) && - (hv_ringbuf_avail_percent(&channel->outbound) > RING_AVAIL_PERCENT_HIWATER || - queue_sends < 1)) { - netif_tx_wake_queue(netdev_get_tx_queue(ndev, q_idx)); - ndev_ctx->eth_stats.wake_queue++; + if (unlikely(net_device->destroy)) { + if (queue_sends == 0) + wake_up(&net_device->wait_drain); + } else { + struct netdev_queue *txq = netdev_get_tx_queue(ndev, q_idx); + + if (netif_tx_queue_stopped(txq) && + (hv_ringbuf_avail_percent(&channel->outbound) > RING_AVAIL_PERCENT_HIWATER || + queue_sends < 1)) { + netif_tx_wake_queue(txq); + ndev_ctx->eth_stats.wake_queue++; + } } } @@@ -765,7 -747,7 +765,7 @@@ static inline int netvsc_send_pkt struct sk_buff *skb) { struct nvsp_message nvmsg; - struct nvsp_1_message_send_rndis_packet * const rpkt = + struct nvsp_1_message_send_rndis_packet *rpkt = &nvmsg.msg.v1_msg.send_rndis_pkt; struct netvsc_channel * const nvchan = &net_device->chan_table[packet->q_idx]; @@@ -794,8 -776,6 +794,8 @@@ if (out_channel->rescind) return -ENODEV; + trace_nvsp_send_pkt(ndev, out_channel, rpkt); + if (packet->page_buf_cnt) { if (packet->cp_partial) pb += packet->rmsg_pgcnt; @@@ -1099,8 -1079,6 +1099,8 @@@ static int netvsc_receive(struct net_de + vmxferpage_packet->ranges[i].byte_offset; u32 buflen = vmxferpage_packet->ranges[i].byte_count; + trace_rndis_recv(ndev, q_idx, data); + /* Pass it to the upper layer */ status = rndis_filter_receive(ndev, net_device, channel, data, buflen); @@@ -1165,8 -1143,6 +1165,8 @@@ static int netvsc_process_raw_pkt(struc struct net_device_context *net_device_ctx = netdev_priv(ndev); struct nvsp_message *nvmsg = hv_pkt_data(desc); + trace_nvsp_recv(ndev, channel, nvmsg); + switch (desc->type) { case VM_PKT_COMP: netvsc_send_completion(net_device, channel, device, diff --combined drivers/net/hyperv/rndis_filter.c index 2dc00f714482,a6ec41c399d6..020f8bc54386 --- a/drivers/net/hyperv/rndis_filter.c +++ b/drivers/net/hyperv/rndis_filter.c @@@ -31,7 -31,6 +31,7 @@@ #include <linux/rtnetlink.h> #include "hyperv_net.h" +#include "netvsc_trace.h" static void rndis_set_multicast(struct work_struct *w); @@@ -242,8 -241,6 +242,8 @@@ static int rndis_filter_send_request(st pb[0].len; } + trace_rndis_send(dev->ndev, 0, &req->request_msg); + rcu_read_lock_bh(); ret = netvsc_send(dev->ndev, packet, NULL, pb, NULL); rcu_read_unlock_bh(); @@@ -267,13 -264,23 +267,23 @@@ static void rndis_set_link_state(struc } } - static void rndis_filter_receive_response(struct rndis_device *dev, - struct rndis_message *resp) + static void rndis_filter_receive_response(struct net_device *ndev, + struct netvsc_device *nvdev, + const struct rndis_message *resp) { + struct rndis_device *dev = nvdev->extension; struct rndis_request *request = NULL; bool found = false; unsigned long flags; - struct net_device *ndev = dev->ndev; + + /* This should never happen, it means control message + * response received after device removed. + */ + if (dev->state == RNDIS_DEV_UNINITIALIZED) { + netdev_err(ndev, + "got rndis message uninitialized\n"); + return; + } spin_lock_irqsave(&dev->request_lock, flags); list_for_each_entry(request, &dev->req_list, list_ent) { @@@ -355,7 -362,6 +365,6 @@@ static inline void *rndis_get_ppi(struc static int rndis_filter_receive_data(struct net_device *ndev, struct netvsc_device *nvdev, - struct rndis_device *dev, struct rndis_message *msg, struct vmbus_channel *channel, void *data, u32 data_buflen) @@@ -375,7 -381,7 +384,7 @@@ * should be the data packet size plus the trailer padding size */ if (unlikely(data_buflen < rndis_pkt->data_len)) { - netdev_err(dev->ndev, "rndis message buffer " + netdev_err(ndev, "rndis message buffer " "overflow detected (got %u, min %u)" "...dropping this message!\n", data_buflen, rndis_pkt->data_len); @@@ -403,35 -409,20 +412,20 @@@ int rndis_filter_receive(struct net_dev void *data, u32 buflen) { struct net_device_context *net_device_ctx = netdev_priv(ndev); - struct rndis_device *rndis_dev = net_dev->extension; struct rndis_message *rndis_msg = data; - /* Make sure the rndis device state is initialized */ - if (unlikely(!rndis_dev)) { - netif_dbg(net_device_ctx, rx_err, ndev, - "got rndis message but no rndis device!\n"); - return NVSP_STAT_FAIL; - } - - if (unlikely(rndis_dev->state == RNDIS_DEV_UNINITIALIZED)) { - netif_dbg(net_device_ctx, rx_err, ndev, - "got rndis message uninitialized\n"); - return NVSP_STAT_FAIL; - } - if (netif_msg_rx_status(net_device_ctx)) dump_rndis_message(ndev, rndis_msg); switch (rndis_msg->ndis_msg_type) { case RNDIS_MSG_PACKET: - return rndis_filter_receive_data(ndev, net_dev, - rndis_dev, rndis_msg, + return rndis_filter_receive_data(ndev, net_dev, rndis_msg, channel, data, buflen); case RNDIS_MSG_INIT_C: case RNDIS_MSG_QUERY_C: case RNDIS_MSG_SET_C: /* completion msgs */ - rndis_filter_receive_response(rndis_dev, rndis_msg); + rndis_filter_receive_response(ndev, net_dev, rndis_msg); break; case RNDIS_MSG_INDICATE: @@@ -828,13 -819,15 +822,15 @@@ static int rndis_filter_set_packet_filt struct rndis_set_request *set; int ret; + if (dev->filter == new_filter) + return 0; + request = get_rndis_request(dev, RNDIS_MSG_SET, RNDIS_MESSAGE_SIZE(struct rndis_set_request) + sizeof(u32)); if (!request) return -ENOMEM; - /* Setup the rndis set */ set = &request->request_msg.msg.set_req; set->oid = RNDIS_OID_GEN_CURRENT_PACKET_FILTER; @@@ -845,8 -838,10 +841,10 @@@ &new_filter, sizeof(u32)); ret = rndis_filter_send_request(dev, request); - if (ret == 0) + if (ret == 0) { wait_for_completion(&request->wait_event); + dev->filter = new_filter; + } put_rndis_request(dev, request); @@@ -864,9 -859,9 +862,9 @@@ static void rndis_set_multicast(struct filter = NDIS_PACKET_TYPE_PROMISCUOUS; } else { if (flags & IFF_ALLMULTI) - flags |= NDIS_PACKET_TYPE_ALL_MULTICAST; + filter |= NDIS_PACKET_TYPE_ALL_MULTICAST; if (flags & IFF_BROADCAST) - flags |= NDIS_PACKET_TYPE_BROADCAST; + filter |= NDIS_PACKET_TYPE_BROADCAST; } rndis_filter_set_packet_filter(rdev, filter); @@@ -947,11 -942,12 +945,11 @@@ static bool netvsc_device_idle(const st return true; } -static void rndis_filter_halt_device(struct rndis_device *dev) +static void rndis_filter_halt_device(struct netvsc_device *nvdev, + struct rndis_device *dev) { struct rndis_request *request; struct rndis_halt_request *halt; - struct net_device_context *net_device_ctx = netdev_priv(dev->ndev); - struct netvsc_device *nvdev = rtnl_dereference(net_device_ctx->nvdev); /* Attempt to do a rndis device halt */ request = get_rndis_request(dev, RNDIS_MSG_HALT, @@@ -1090,8 -1086,6 +1088,8 @@@ void rndis_set_subchannel(struct work_s init_packet->msg.v5_msg.subchn_req.op = NVSP_SUBCHANNEL_ALLOCATE; init_packet->msg.v5_msg.subchn_req.num_subchannels = nvdev->num_chn - 1; + trace_nvsp_send(ndev, init_packet); + ret = vmbus_sendpacket(hv_dev->channel, init_packet, sizeof(struct nvsp_message), (unsigned long)init_packet, @@@ -1124,6 -1118,7 +1122,7 @@@ for (i = 0; i < VRSS_SEND_TAB_SIZE; i++) ndev_ctx->tx_table[i] = i % nvdev->num_chn; + netif_device_attach(ndev); rtnl_unlock(); return; @@@ -1134,6 -1129,8 +1133,8 @@@ failed nvdev->max_chn = 1; nvdev->num_chn = 1; + + netif_device_attach(ndev); unlock: rtnl_unlock(); } @@@ -1336,6 -1333,10 +1337,10 @@@ out net_device->num_chn = 1; } + /* No sub channels, device is ready */ + if (net_device->num_chn == 1) + netif_device_attach(net); + return net_device; err_dev_remv: @@@ -1348,16 -1349,12 +1353,12 @@@ void rndis_filter_device_remove(struct { struct rndis_device *rndis_dev = net_dev->extension; - /* Don't try and setup sub channels if about to halt */ - cancel_work_sync(&net_dev->subchan_work); - /* Halt and release the rndis device */ - rndis_filter_halt_device(rndis_dev); + rndis_filter_halt_device(net_dev, rndis_dev); net_dev->extension = NULL; netvsc_device_remove(dev); - kfree(rndis_dev); } int rndis_filter_open(struct netvsc_device *nvdev) @@@ -1375,10 -1372,3 +1376,3 @@@ int rndis_filter_close(struct netvsc_de return rndis_filter_close_device(nvdev->extension); } - - bool rndis_filter_opened(const struct netvsc_device *nvdev) - { - const struct rndis_device *dev = nvdev->extension; - - return dev->state == RNDIS_DEV_DATAINITIALIZED; - } diff --combined drivers/net/phy/marvell.c index 98fd6b7ceeec,0e0978d8a0eb..a75c511950c3 --- a/drivers/net/phy/marvell.c +++ b/drivers/net/phy/marvell.c @@@ -860,7 -860,7 +860,7 @@@ static int m88e1510_config_init(struct 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. @@@ -1452,8 -1452,8 +1452,8 @@@ static void marvell_get_strings(struct int i; for (i = 0; i < ARRAY_SIZE(marvell_hw_stats); i++) { - memcpy(data + i * ETH_GSTRING_LEN, - marvell_hw_stats[i].string, ETH_GSTRING_LEN); + strlcpy(data + i * ETH_GSTRING_LEN, + marvell_hw_stats[i].string, ETH_GSTRING_LEN); } } diff --combined drivers/net/phy/phy.c index c2d9027be863,9aabfa1a455a..05c1e8ef15e6 --- a/drivers/net/phy/phy.c +++ b/drivers/net/phy/phy.c @@@ -618,6 -618,77 +618,68 @@@ static void phy_error(struct phy_devic } /** + * phy_disable_interrupts - Disable the PHY interrupts from the PHY side + * @phydev: target phy_device struct + */ + static int phy_disable_interrupts(struct phy_device *phydev) + { + int err; + + /* Disable PHY interrupts */ + err = phy_config_interrupt(phydev, PHY_INTERRUPT_DISABLED); + if (err) - goto phy_err; ++ return err; + + /* Clear the interrupt */ - err = phy_clear_interrupt(phydev); - if (err) - goto phy_err; - - return 0; - -phy_err: - phy_error(phydev); - - return err; ++ return phy_clear_interrupt(phydev); + } + + /** + * phy_change - Called by the phy_interrupt to handle PHY changes + * @phydev: phy_device struct that interrupted + */ + static irqreturn_t phy_change(struct phy_device *phydev) + { + if (phy_interrupt_is_valid(phydev)) { + if (phydev->drv->did_interrupt && + !phydev->drv->did_interrupt(phydev)) + return IRQ_NONE; + + if (phydev->state == PHY_HALTED) + if (phy_disable_interrupts(phydev)) + goto phy_err; + } + + mutex_lock(&phydev->lock); + if ((PHY_RUNNING == phydev->state) || (PHY_NOLINK == phydev->state)) + phydev->state = PHY_CHANGELINK; + mutex_unlock(&phydev->lock); + + /* reschedule state queue work to run as soon as possible */ + phy_trigger_machine(phydev, true); + + if (phy_interrupt_is_valid(phydev) && phy_clear_interrupt(phydev)) + goto phy_err; + return IRQ_HANDLED; + + phy_err: + phy_error(phydev); + return IRQ_NONE; + } + + /** + * phy_change_work - Scheduled by the phy_mac_interrupt to handle PHY changes + * @work: work_struct that describes the work to be done + */ + void phy_change_work(struct work_struct *work) + { + struct phy_device *phydev = + container_of(work, struct phy_device, phy_queue); + + phy_change(phydev); + } + + /** * phy_interrupt - PHY interrupt handler * @irq: interrupt line * @phy_dat: phy_device pointer @@@ -632,9 -703,7 +694,7 @@@ static irqreturn_t phy_interrupt(int ir if (PHY_HALTED == phydev->state) return IRQ_NONE; /* It can't be ours. */ - phy_change(phydev); - - return IRQ_HANDLED; + return phy_change(phydev); } /** @@@ -652,23 -721,6 +712,6 @@@ static int phy_enable_interrupts(struc } /** - * phy_disable_interrupts - Disable the PHY interrupts from the PHY side - * @phydev: target phy_device struct - */ - static int phy_disable_interrupts(struct phy_device *phydev) - { - int err; - - /* Disable PHY interrupts */ - err = phy_config_interrupt(phydev, PHY_INTERRUPT_DISABLED); - if (err) - return err; - - /* Clear the interrupt */ - return phy_clear_interrupt(phydev); - } - - /** * phy_start_interrupts - request and enable interrupts for a PHY device * @phydev: target phy_device struct * @@@ -711,50 -763,6 +754,6 @@@ int phy_stop_interrupts(struct phy_devi EXPORT_SYMBOL(phy_stop_interrupts); /** - * phy_change - Called by the phy_interrupt to handle PHY changes - * @phydev: phy_device struct that interrupted - */ - void phy_change(struct phy_device *phydev) - { - if (phy_interrupt_is_valid(phydev)) { - if (phydev->drv->did_interrupt && - !phydev->drv->did_interrupt(phydev)) - return; - - if (phydev->state == PHY_HALTED) - if (phy_disable_interrupts(phydev)) - goto phy_err; - } - - mutex_lock(&phydev->lock); - if ((PHY_RUNNING == phydev->state) || (PHY_NOLINK == phydev->state)) - phydev->state = PHY_CHANGELINK; - mutex_unlock(&phydev->lock); - - /* reschedule state queue work to run as soon as possible */ - phy_trigger_machine(phydev, true); - - if (phy_interrupt_is_valid(phydev) && phy_clear_interrupt(phydev)) - goto phy_err; - return; - - phy_err: - phy_error(phydev); - } - - /** - * phy_change_work - Scheduled by the phy_mac_interrupt to handle PHY changes - * @work: work_struct that describes the work to be done - */ - void phy_change_work(struct work_struct *work) - { - struct phy_device *phydev = - container_of(work, struct phy_device, phy_queue); - - phy_change(phydev); - } - - /** * phy_stop - Bring down the PHY link, and stop checking the status * @phydev: target phy_device struct */ @@@ -765,8 -773,13 +764,8 @@@ void phy_stop(struct phy_device *phydev if (PHY_HALTED == phydev->state) goto out_unlock; - if (phy_interrupt_is_valid(phydev)) { - /* Disable PHY Interrupts */ - phy_config_interrupt(phydev, PHY_INTERRUPT_DISABLED); - - /* Clear any pending interrupts */ - phy_clear_interrupt(phydev); - } + if (phy_interrupt_is_valid(phydev)) + phy_disable_interrupts(phydev); phydev->state = PHY_HALTED; diff --combined drivers/net/phy/phy_device.c index b285323327c4,74664a6c0cdc..ac23322a32e1 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@@ -374,7 -374,7 +374,7 @@@ struct phy_device *phy_device_create(st dev->duplex = -1; dev->pause = 0; dev->asym_pause = 0; - dev->link = 1; + dev->link = 0; dev->interface = PHY_INTERFACE_MODE_GMII; dev->autoneg = AUTONEG_ENABLE; @@@ -1012,10 -1012,17 +1012,17 @@@ int phy_attach_direct(struct net_devic err = sysfs_create_link(&phydev->mdio.dev.kobj, &dev->dev.kobj, "attached_dev"); if (!err) { - err = sysfs_create_link(&dev->dev.kobj, &phydev->mdio.dev.kobj, - "phydev"); - if (err) - goto error; + err = sysfs_create_link_nowarn(&dev->dev.kobj, + &phydev->mdio.dev.kobj, + "phydev"); + if (err) { + dev_err(&dev->dev, "could not add device link to %s err %d\n", + kobject_name(&phydev->mdio.dev.kobj), + err); + /* non-fatal - some net drivers can use one netdevice + * with more then one phy + */ + } phydev->sysfs_links = true; } @@@ -1666,6 -1673,23 +1673,23 @@@ int genphy_config_init(struct phy_devic } EXPORT_SYMBOL(genphy_config_init); + /* This is used for the phy device which doesn't support the MMD extended + * register access, but it does have side effect when we are trying to access + * the MMD register via indirect method. + */ + int genphy_read_mmd_unsupported(struct phy_device *phdev, int devad, u16 regnum) + { + return -EOPNOTSUPP; + } + EXPORT_SYMBOL(genphy_read_mmd_unsupported); + + int genphy_write_mmd_unsupported(struct phy_device *phdev, int devnum, + u16 regnum, u16 val) + { + return -EOPNOTSUPP; + } + EXPORT_SYMBOL(genphy_write_mmd_unsupported); + int genphy_suspend(struct phy_device *phydev) { return phy_set_bits(phydev, MII_BMCR, BMCR_PDOWN); diff --combined drivers/net/ppp/ppp_generic.c index 7dc2f34e7229,da1937832c99..926c2c322d43 --- a/drivers/net/ppp/ppp_generic.c +++ b/drivers/net/ppp/ppp_generic.c @@@ -257,7 -257,7 +257,7 @@@ struct ppp_net /* Prototypes. */ static int ppp_unattached_ioctl(struct net *net, struct ppp_file *pf, struct file *file, unsigned int cmd, unsigned long arg); - static void ppp_xmit_process(struct ppp *ppp); + static void ppp_xmit_process(struct ppp *ppp, struct sk_buff *skb); static void ppp_send_frame(struct ppp *ppp, struct sk_buff *skb); static void ppp_push(struct ppp *ppp); static void ppp_channel_push(struct channel *pch); @@@ -513,13 -513,12 +513,12 @@@ static ssize_t ppp_write(struct file *f goto out; } - skb_queue_tail(&pf->xq, skb); - switch (pf->kind) { case INTERFACE: - ppp_xmit_process(PF_TO_PPP(pf)); + ppp_xmit_process(PF_TO_PPP(pf), skb); break; case CHANNEL: + skb_queue_tail(&pf->xq, skb); ppp_channel_push(PF_TO_CHANNEL(pf)); break; } @@@ -971,7 -970,6 +970,7 @@@ static struct pernet_operations ppp_net .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) @@@ -1268,8 -1266,8 +1267,8 @@@ ppp_start_xmit(struct sk_buff *skb, str put_unaligned_be16(proto, pp); skb_scrub_packet(skb, !net_eq(ppp->ppp_net, dev_net(dev))); - skb_queue_tail(&ppp->file.xq, skb); - ppp_xmit_process(ppp); + ppp_xmit_process(ppp, skb); + return NETDEV_TX_OK; outf: @@@ -1421,13 -1419,14 +1420,14 @@@ static void ppp_setup(struct net_devic */ /* Called to do any work queued up on the transmit side that can now be done */ - static void __ppp_xmit_process(struct ppp *ppp) + static void __ppp_xmit_process(struct ppp *ppp, struct sk_buff *skb) { - struct sk_buff *skb; - ppp_xmit_lock(ppp); if (!ppp->closing) { ppp_push(ppp); + + if (skb) + skb_queue_tail(&ppp->file.xq, skb); while (!ppp->xmit_pending && (skb = skb_dequeue(&ppp->file.xq))) ppp_send_frame(ppp, skb); @@@ -1441,7 -1440,7 +1441,7 @@@ ppp_xmit_unlock(ppp); } - static void ppp_xmit_process(struct ppp *ppp) + static void ppp_xmit_process(struct ppp *ppp, struct sk_buff *skb) { local_bh_disable(); @@@ -1449,7 -1448,7 +1449,7 @@@ goto err; (*this_cpu_ptr(ppp->xmit_recursion))++; - __ppp_xmit_process(ppp); + __ppp_xmit_process(ppp, skb); (*this_cpu_ptr(ppp->xmit_recursion))--; local_bh_enable(); @@@ -1459,6 -1458,8 +1459,8 @@@ err: local_bh_enable(); + kfree_skb(skb); + if (net_ratelimit()) netdev_err(ppp->dev, "recursion detected\n"); } @@@ -1943,7 -1944,7 +1945,7 @@@ static void __ppp_channel_push(struct c if (skb_queue_empty(&pch->file.xq)) { ppp = pch->ppp; if (ppp) - __ppp_xmit_process(ppp); + __ppp_xmit_process(ppp, NULL); } } diff --combined drivers/net/team/team.c index 5dd781e65958,56c701b73c12..222093e878a8 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@@ -1105,15 -1105,14 +1105,15 @@@ static void team_port_disable_netpoll(s } #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; @@@ -1130,8 -1129,7 +1130,8 @@@ static void __team_port_change_port_add 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; @@@ -1139,14 -1137,12 +1139,14 @@@ 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; @@@ -1154,7 -1150,6 +1154,7 @@@ 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; @@@ -1165,7 -1160,6 +1165,7 @@@ 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; @@@ -1233,7 -1227,7 +1233,7 @@@ 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); @@@ -1927,7 -1921,7 +1927,7 @@@ static int team_add_slave(struct net_de 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) @@@ -2401,7 -2395,7 +2401,7 @@@ send_done if (!nlh) { err = __send_and_alloc_skb(&skb, team, portid, send_func); if (err) - goto errout; + return err; goto send_done; } @@@ -2687,7 -2681,7 +2687,7 @@@ send_done if (!nlh) { err = __send_and_alloc_skb(&skb, team, portid, send_func); if (err) - goto errout; + return err; goto send_done; } diff --combined drivers/net/tun.c index baeafa004463,28cfa642e39a..a1ba262f40ad --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@@ -78,7 -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 */ @@@ -656,7 -655,7 +656,7 @@@ static struct tun_struct *tun_enable_qu return tun; } - static void tun_ptr_free(void *ptr) + void tun_ptr_free(void *ptr) { if (!ptr) return; @@@ -668,6 -667,7 +668,7 @@@ __skb_array_destroy_skb(ptr); } } + EXPORT_SYMBOL_GPL(tun_ptr_free); static void tun_queue_purge(struct tun_file *tfile) { @@@ -1613,6 -1613,7 +1614,6 @@@ static struct sk_buff *tun_build_skb(st unsigned int delta = 0; char *buf; size_t copied; - bool xdp_xmit = false; int err, pad = TUN_RX_PAD; rcu_read_lock(); @@@ -1670,14 -1671,8 +1671,14 @@@ preempt_enable(); return NULL; case XDP_TX: - xdp_xmit = true; - /* fall through */ + get_page(alloc_frag->page); + alloc_frag->offset += buflen; + if (tun_xdp_xmit(tun->dev, &xdp)) + goto err_redirect; + tun_xdp_flush(tun->dev); + rcu_read_unlock(); + preempt_enable(); + return NULL; case XDP_PASS: delta = orig_data - xdp.data; break; @@@ -1704,6 -1699,14 +1705,6 @@@ get_page(alloc_frag->page); alloc_frag->offset += buflen; - if (xdp_xmit) { - skb->dev = tun->dev; - generic_xdp_tx(skb, xdp_prog); - rcu_read_unlock(); - preempt_enable(); - return NULL; - } - rcu_read_unlock(); preempt_enable(); @@@ -2284,67 -2287,11 +2285,67 @@@ static int tun_validate(struct nlattr * 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) @@@ -2836,7 -2783,6 +2837,7 @@@ static long __tun_chr_ioctl(struct fil struct tun_struct *tun; void __user* argp = (void __user*)arg; struct ifreq ifr; + struct net *net; kuid_t owner; kgid_t group; int sndbuf; @@@ -2845,8 -2791,7 +2846,8 @@@ 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 { @@@ -2866,7 -2811,6 +2867,7 @@@ rtnl_lock(); tun = tun_get(tfile); + net = sock_net(&tfile->sk); if (cmd == TUNSETIFF) { ret = -EEXIST; if (tun) @@@ -2874,7 -2818,7 +2875,7 @@@ 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; @@@ -2896,14 -2840,6 +2897,14 @@@ 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 --combined drivers/net/wireless/mac80211_hwsim.c index 7b6c3640a94f,35b21f8152bb..100cf42db65d --- a/drivers/net/wireless/mac80211_hwsim.c +++ b/drivers/net/wireless/mac80211_hwsim.c @@@ -253,7 -253,7 +253,7 @@@ static inline void hwsim_clear_chanctx_ static unsigned int hwsim_net_id; -static int hwsim_netgroup; +static struct ida hwsim_netgroup_ida = IDA_INIT; struct hwsim_net { int netgroup; @@@ -267,13 -267,11 +267,13 @@@ static inline int hwsim_net_get_netgrou 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) @@@ -495,7 -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 = { @@@ -640,7 -637,6 +640,7 @@@ static const struct nla_policy hwsim_ge [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, @@@ -2412,7 -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, @@@ -2577,25 -2572,15 +2577,25 @@@ static int mac80211_hwsim_new_radio(str 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; @@@ -2742,6 -2727,7 +2742,7 @@@ mutex_init(&data->mutex); data->netgroup = hwsim_net_get_netgroup(net); + data->wmediumd = hwsim_net_get_wmediumd(net); /* Enable frame retransmissions for lossy channels */ hw->max_rates = 4; @@@ -2800,17 -2786,13 +2801,17 @@@ 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) @@@ -3229,19 -3211,6 +3230,19 @@@ static int hwsim_new_radio_nl(struct sk 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, &param); kfree(hwname); return ret; @@@ -3281,7 -3250,6 +3282,7 @@@ static int hwsim_del_radio_nl(struct sk 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); @@@ -3338,19 -3306,17 +3339,19 @@@ 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))) @@@ -3363,25 -3329,14 +3364,25 @@@ 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 */ @@@ -3439,7 -3394,6 +3440,7 @@@ static void destroy_radio(struct work_s 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); } @@@ -3509,7 -3463,9 +3510,7 @@@ 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) @@@ -3532,8 -3488,6 +3533,8 @@@ 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 = { @@@ -3541,7 -3495,6 +3542,7 @@@ .exit = hwsim_exit_net, .id = &hwsim_net_id, .size = sizeof(struct hwsim_net), + .async = true, }; static void hwsim_exit_netlink(void) diff --combined drivers/s390/net/qeth_core_main.c index 8c97ce2516bb,3653bea38470..19203340f879 --- a/drivers/s390/net/qeth_core_main.c +++ b/drivers/s390/net/qeth_core_main.c @@@ -527,8 -527,7 +527,7 @@@ static inline int qeth_is_cq(struct qet queue == card->qdio.no_in_queues - 1; } - - static int qeth_issue_next_read(struct qeth_card *card) + static int __qeth_issue_next_read(struct qeth_card *card) { int rc; struct qeth_cmd_buffer *iob; @@@ -559,6 -558,17 +558,17 @@@ return rc; } + static int qeth_issue_next_read(struct qeth_card *card) + { + int ret; + + spin_lock_irq(get_ccwdev_lock(CARD_RDEV(card))); + ret = __qeth_issue_next_read(card); + spin_unlock_irq(get_ccwdev_lock(CARD_RDEV(card))); + + return ret; + } + static struct qeth_reply *qeth_alloc_reply(struct qeth_card *card) { struct qeth_reply *reply; @@@ -708,8 -718,11 +718,8 @@@ static int qeth_check_idx_response(stru QETH_DBF_HEX(CTRL, 2, buffer, QETH_DBF_CTRL_LEN); if ((buffer[2] & 0xc0) == 0xc0) { - QETH_DBF_MESSAGE(2, "received an IDX TERMINATE " - "with cause code 0x%02x%s\n", - buffer[4], - ((buffer[4] == 0x22) ? - " -- try another portname" : "")); + QETH_DBF_MESSAGE(2, "received an IDX TERMINATE with cause code %#02x\n", + buffer[4]); QETH_CARD_TEXT(card, 2, "ckidxres"); QETH_CARD_TEXT(card, 2, " idxterm"); QETH_CARD_TEXT_(card, 2, " rc%d", -EIO); @@@ -957,7 -970,7 +967,7 @@@ void qeth_clear_thread_running_bit(stru spin_lock_irqsave(&card->thread_mask_lock, flags); card->thread_running_mask &= ~thread; spin_unlock_irqrestore(&card->thread_mask_lock, flags); - wake_up(&card->wait_q); + wake_up_all(&card->wait_q); } EXPORT_SYMBOL_GPL(qeth_clear_thread_running_bit); @@@ -1161,6 -1174,7 +1171,7 @@@ static void qeth_irq(struct ccw_device } rc = qeth_get_problem(cdev, irb); if (rc) { + card->read_or_write_problem = 1; qeth_clear_ipacmd_list(card); qeth_schedule_recovery(card); goto out; @@@ -1179,7 -1193,7 +1190,7 @@@ return; if (channel == &card->read && channel->state == CH_STATE_UP) - qeth_issue_next_read(card); + __qeth_issue_next_read(card); iob = channel->iob; index = channel->buf_no; @@@ -2835,8 -2849,7 +2846,8 @@@ static int qeth_init_input_buffer(struc int i; if ((card->options.cq == QETH_CQ_ENABLED) && (!buf->rx_skb)) { - buf->rx_skb = dev_alloc_skb(QETH_RX_PULL_LEN + ETH_HLEN); + buf->rx_skb = netdev_alloc_skb(card->dev, + QETH_RX_PULL_LEN + ETH_HLEN); if (!buf->rx_skb) return 1; } @@@ -2873,8 -2886,8 +2884,8 @@@ int qeth_init_qdio_queues(struct qeth_c QETH_DBF_TEXT(SETUP, 2, "initqdqs"); /* inbound queue */ - qdio_reset_buffers(card->qdio.in_q->qdio_bufs, - QDIO_MAX_BUFFERS_PER_Q); + qdio_reset_buffers(card->qdio.in_q->qdio_bufs, QDIO_MAX_BUFFERS_PER_Q); + memset(&card->rx, 0, sizeof(struct qeth_rx)); qeth_initialize_working_pool_list(card); /*give only as many buffers to hardware as we have buffer pool entries*/ for (i = 0; i < card->qdio.in_buf_pool.buf_count - 1; ++i) @@@ -2949,10 -2962,12 +2960,10 @@@ struct qeth_cmd_buffer *qeth_get_ipacmd enum qeth_ipa_cmds ipacmd, enum qeth_prot_versions prot) { struct qeth_cmd_buffer *iob; - struct qeth_ipa_cmd *cmd; iob = qeth_get_buffer(&card->write); if (iob) { - cmd = (struct qeth_ipa_cmd *)(iob->data+IPA_PDU_HEADER_SIZE); - qeth_fill_ipacmd_header(card, cmd, ipacmd, prot); + qeth_fill_ipacmd_header(card, __ipa_cmd(iob), ipacmd, prot); } else { dev_warn(&card->gdev->dev, "The qeth driver ran out of channel command buffers\n"); @@@ -3063,7 -3078,7 +3074,7 @@@ static struct qeth_cmd_buffer *qeth_get iob = qeth_get_ipacmd_buffer(card, IPA_CMD_SETADAPTERPARMS, QETH_PROT_IPV4); if (iob) { - cmd = (struct qeth_ipa_cmd *)(iob->data+IPA_PDU_HEADER_SIZE); + cmd = __ipa_cmd(iob); cmd->data.setadapterparms.hdr.cmdlength = cmdlen; cmd->data.setadapterparms.hdr.command_code = command; cmd->data.setadapterparms.hdr.used_total = 1; @@@ -3205,7 -3220,7 +3216,7 @@@ static int qeth_query_setdiagass(struc iob = qeth_get_ipacmd_buffer(card, IPA_CMD_SET_DIAG_ASS, 0); if (!iob) return -ENOMEM; - cmd = (struct qeth_ipa_cmd *)(iob->data+IPA_PDU_HEADER_SIZE); + cmd = __ipa_cmd(iob); cmd->data.diagass.subcmd_len = 16; cmd->data.diagass.subcmd = QETH_DIAGS_CMD_QUERY; return qeth_send_ipa_cmd(card, iob, qeth_query_setdiagass_cb, NULL); @@@ -3258,7 -3273,7 +3269,7 @@@ int qeth_hw_trap(struct qeth_card *card iob = qeth_get_ipacmd_buffer(card, IPA_CMD_SET_DIAG_ASS, 0); if (!iob) return -ENOMEM; - cmd = (struct qeth_ipa_cmd *)(iob->data+IPA_PDU_HEADER_SIZE); + cmd = __ipa_cmd(iob); cmd->data.diagass.subcmd_len = 80; cmd->data.diagass.subcmd = QETH_DIAGS_CMD_TRAP; cmd->data.diagass.type = 1; @@@ -4236,7 -4251,7 +4247,7 @@@ void qeth_setadp_promisc_mode(struct qe sizeof(struct qeth_ipacmd_setadpparms_hdr) + 8); if (!iob) return; - cmd = (struct qeth_ipa_cmd *)(iob->data + IPA_PDU_HEADER_SIZE); + cmd = __ipa_cmd(iob); cmd->data.setadapterparms.data.mode = mode; qeth_send_ipa_cmd(card, iob, qeth_setadp_promisc_mode_cb, NULL); } @@@ -4303,7 -4318,7 +4314,7 @@@ int qeth_setadpparms_change_macaddr(str sizeof(struct qeth_change_addr)); if (!iob) return -ENOMEM; - cmd = (struct qeth_ipa_cmd *)(iob->data+IPA_PDU_HEADER_SIZE); + cmd = __ipa_cmd(iob); cmd->data.setadapterparms.data.change_addr.cmd = CHANGE_ADDR_READ_MAC; cmd->data.setadapterparms.data.change_addr.addr_size = ETH_ALEN; ether_addr_copy(cmd->data.setadapterparms.data.change_addr.addr, @@@ -4418,7 -4433,7 +4429,7 @@@ static int qeth_setadpparms_set_access_ sizeof(struct qeth_set_access_ctrl)); if (!iob) return -ENOMEM; - cmd = (struct qeth_ipa_cmd *)(iob->data+IPA_PDU_HEADER_SIZE); + cmd = __ipa_cmd(iob); access_ctrl_req = &cmd->data.setadapterparms.data.set_access_ctrl; access_ctrl_req->subcmd_code = isolation; @@@ -4664,7 -4679,7 +4675,7 @@@ static int qeth_snmp_command(struct qet rc = -ENOMEM; goto out; } - cmd = (struct qeth_ipa_cmd *)(iob->data+IPA_PDU_HEADER_SIZE); + cmd = __ipa_cmd(iob); memcpy(&cmd->data.setadapterparms.data.snmp, &ureq->cmd, req_len); rc = qeth_send_ipa_snmp_cmd(card, iob, QETH_SETADP_BASE_LEN + req_len, qeth_snmp_command_cb, (void *)&qinfo); @@@ -4749,7 -4764,7 +4760,7 @@@ static int qeth_query_oat_command(struc rc = -ENOMEM; goto out_free; } - cmd = (struct qeth_ipa_cmd *)(iob->data+IPA_PDU_HEADER_SIZE); + cmd = __ipa_cmd(iob); oat_req = &cmd->data.setadapterparms.data.query_oat; oat_req->subcmd_code = oat_data.command; @@@ -5083,8 -5098,6 +5094,6 @@@ static void qeth_core_free_card(struct QETH_DBF_HEX(SETUP, 2, &card, sizeof(void *)); qeth_clean_channel(&card->read); qeth_clean_channel(&card->write); - if (card->dev) - free_netdev(card->dev); qeth_free_qdio_buffers(card); unregister_service_level(&card->qeth_service_level); kfree(card); @@@ -5326,7 -5339,7 +5335,7 @@@ struct sk_buff *qeth_core_get_next_skb( } else { unsigned int linear = (use_rx_sg) ? QETH_RX_PULL_LEN : skb_len; - skb = dev_alloc_skb(linear + headroom); + skb = napi_alloc_skb(&card->napi, linear + headroom); } if (!skb) goto no_mem; @@@ -5490,7 -5503,7 +5499,7 @@@ struct qeth_cmd_buffer *qeth_get_setass iob = qeth_get_ipacmd_buffer(card, IPA_CMD_SETASSPARMS, prot); if (iob) { - cmd = (struct qeth_ipa_cmd *)(iob->data+IPA_PDU_HEADER_SIZE); + cmd = __ipa_cmd(iob); cmd->data.setassparms.hdr.assist_no = ipa_func; cmd->data.setassparms.hdr.length = 8 + len; cmd->data.setassparms.hdr.command_code = cmd_code; @@@ -5513,7 -5526,7 +5522,7 @@@ int qeth_send_setassparms(struct qeth_c QETH_CARD_TEXT(card, 4, "sendassp"); - cmd = (struct qeth_ipa_cmd *)(iob->data+IPA_PDU_HEADER_SIZE); + cmd = __ipa_cmd(iob); if (len <= sizeof(__u32)) cmd->data.setassparms.data.flags_32bit = (__u32) data; else /* (len > sizeof(__u32)) */ diff --combined drivers/s390/net/qeth_l2_main.c index 8f5babdccb42,5ef4c978ad19..50a313806dde --- a/drivers/s390/net/qeth_l2_main.c +++ b/drivers/s390/net/qeth_l2_main.c @@@ -108,7 -108,7 +108,7 @@@ static int qeth_l2_send_setdelmac(struc iob = qeth_get_ipacmd_buffer(card, ipacmd, QETH_PROT_IPV4); if (!iob) return -ENOMEM; - cmd = (struct qeth_ipa_cmd *)(iob->data+IPA_PDU_HEADER_SIZE); + cmd = __ipa_cmd(iob); cmd->data.setdelmac.mac_length = ETH_ALEN; ether_addr_copy(cmd->data.setdelmac.mac, mac); return qeth_setdelmac_makerc(card, qeth_send_ipa_cmd(card, iob, @@@ -305,7 -305,7 +305,7 @@@ static int qeth_l2_send_setdelvlan(stru iob = qeth_get_ipacmd_buffer(card, ipacmd, QETH_PROT_IPV4); if (!iob) return -ENOMEM; - cmd = (struct qeth_ipa_cmd *)(iob->data+IPA_PDU_HEADER_SIZE); + cmd = __ipa_cmd(iob); cmd->data.setdelvlan.vlan_id = i; return qeth_setdelvlan_makerc(card, qeth_send_ipa_cmd(card, iob, qeth_l2_send_setdelvlan_cb, NULL)); @@@ -437,8 -437,10 +437,8 @@@ static int qeth_l2_process_inbound_buff *done = 1; break; } - skb->dev = card->dev; switch (hdr->hdr.l2.id) { case QETH_HEADER_TYPE_LAYER2: - skb->pkt_type = PACKET_HOST; skb->protocol = eth_type_trans(skb, skb->dev); if ((card->dev->features & NETIF_F_RXCSUM) && ((hdr->hdr.l2.flags[1] & @@@ -913,8 -915,8 +913,8 @@@ static void qeth_l2_remove_device(struc qeth_l2_set_offline(cgdev); if (card->dev) { - netif_napi_del(&card->napi); unregister_netdev(card->dev); + free_netdev(card->dev); card->dev = NULL; } return; @@@ -973,7 -975,6 +973,7 @@@ static int qeth_l2_setup_netdev(struct return -ENODEV; card->dev->ml_priv = card; + card->dev->priv_flags |= IFF_UNICAST_FLT; card->dev->watchdog_timeo = QETH_TX_TIMEOUT; card->dev->mtu = card->info.initial_mtu; card->dev->min_mtu = 64; @@@ -990,16 -991,9 +990,16 @@@ card->dev->features |= NETIF_F_VLAN_CHALLENGED; else card->dev->features |= NETIF_F_HW_VLAN_CTAG_FILTER; + + if (card->info.type != QETH_CARD_TYPE_OSN && + card->info.type != QETH_CARD_TYPE_IQD) { + card->dev->priv_flags &= ~IFF_TX_SKB_SHARING; + card->dev->needed_headroom = sizeof(struct qeth_hdr); + card->dev->hw_features |= NETIF_F_SG; + card->dev->vlan_features |= NETIF_F_SG; + } + if (card->info.type == QETH_CARD_TYPE_OSD && !card->info.guestlan) { - card->dev->hw_features = NETIF_F_SG; - card->dev->vlan_features = NETIF_F_SG; card->dev->features |= NETIF_F_SG; /* OSA 3S and earlier has no RX/TX support */ if (qeth_is_supported(card, IPA_OUTBOUND_CHECKSUM)) { @@@ -1011,6 -1005,11 +1011,6 @@@ card->dev->vlan_features |= NETIF_F_RXCSUM; } } - if (card->info.type != QETH_CARD_TYPE_OSN && - card->info.type != QETH_CARD_TYPE_IQD) { - card->dev->priv_flags &= ~IFF_TX_SKB_SHARING; - card->dev->needed_headroom = sizeof(struct qeth_hdr); - } card->info.broadcast_capable = 1; qeth_l2_request_initial_mac(card); @@@ -1087,6 -1086,7 +1087,6 @@@ static int __qeth_l2_set_online(struct qeth_l2_setup_bridgeport_attrs(card); card->state = CARD_STATE_HARDSETUP; - memset(&card->rx, 0, sizeof(struct qeth_rx)); qeth_print_status_message(card); /* softsetup */ @@@ -1374,6 -1374,7 +1374,6 @@@ int qeth_osn_assist(struct net_device * { struct qeth_cmd_buffer *iob; struct qeth_card *card; - int rc; if (!dev) return -ENODEV; @@@ -1384,8 -1385,9 +1384,8 @@@ if (!qeth_card_hw_is_reachable(card)) return -ENODEV; iob = qeth_wait_for_buffer(&card->write); - memcpy(iob->data+IPA_PDU_HEADER_SIZE, data, data_len); - rc = qeth_osn_send_ipa_cmd(card, iob, data_len); - return rc; + memcpy(__ipa_cmd(iob), data, data_len); + return qeth_osn_send_ipa_cmd(card, iob, data_len); } EXPORT_SYMBOL(qeth_osn_assist); @@@ -1762,7 -1764,7 +1762,7 @@@ static struct qeth_cmd_buffer *qeth_sbp iob = qeth_get_ipacmd_buffer(card, ipa_cmd, 0); if (!iob) return iob; - cmd = (struct qeth_ipa_cmd *)(iob->data+IPA_PDU_HEADER_SIZE); + cmd = __ipa_cmd(iob); cmd->data.sbp.hdr.cmdlength = sizeof(struct qeth_ipacmd_sbp_hdr) + cmd_length; cmd->data.sbp.hdr.command_code = sbp_cmd; @@@ -2127,7 -2129,7 +2127,7 @@@ static int qeth_l2_vnicc_request(struc return -ENOMEM; /* create header for request */ - cmd = (struct qeth_ipa_cmd *)(iob->data + IPA_PDU_HEADER_SIZE); + cmd = __ipa_cmd(iob); req = &cmd->data.vnicc; /* create sub command header for request */ diff --combined drivers/s390/net/qeth_l3_main.c index ef3f548b7d35,b6b12220da71..c1a16a74aa83 --- a/drivers/s390/net/qeth_l3_main.c +++ b/drivers/s390/net/qeth_l3_main.c @@@ -67,15 -67,6 +67,15 @@@ void qeth_l3_ipaddr_to_string(enum qeth qeth_l3_ipaddr6_to_string(addr, buf); } +static struct qeth_ipaddr *qeth_l3_get_addr_buffer(enum qeth_prot_versions prot) +{ + struct qeth_ipaddr *addr = kmalloc(sizeof(*addr), GFP_ATOMIC); + + if (addr) + qeth_l3_init_ipaddr(addr, QETH_IP_TYPE_NORMAL, prot); + return addr; +} + static struct qeth_ipaddr *qeth_l3_find_addr_by_ip(struct qeth_card *card, struct qeth_ipaddr *query) { @@@ -147,18 -138,12 +147,18 @@@ static bool qeth_l3_is_addr_covered_by_ return rc; } -int qeth_l3_delete_ip(struct qeth_card *card, struct qeth_ipaddr *tmp_addr) +static int qeth_l3_delete_ip(struct qeth_card *card, + struct qeth_ipaddr *tmp_addr) { int rc = 0; struct qeth_ipaddr *addr; - QETH_CARD_TEXT(card, 4, "delip"); + if (tmp_addr->type == QETH_IP_TYPE_RXIP) + QETH_CARD_TEXT(card, 2, "delrxip"); + else if (tmp_addr->type == QETH_IP_TYPE_VIPA) + QETH_CARD_TEXT(card, 2, "delvipa"); + else + QETH_CARD_TEXT(card, 2, "delip"); if (tmp_addr->proto == QETH_PROT_IPV4) QETH_CARD_HEX(card, 4, &tmp_addr->u.a4.addr, 4); @@@ -186,18 -171,13 +186,18 @@@ return rc; } -int qeth_l3_add_ip(struct qeth_card *card, struct qeth_ipaddr *tmp_addr) +static int qeth_l3_add_ip(struct qeth_card *card, struct qeth_ipaddr *tmp_addr) { int rc = 0; struct qeth_ipaddr *addr; char buf[40]; - QETH_CARD_TEXT(card, 4, "addip"); + if (tmp_addr->type == QETH_IP_TYPE_RXIP) + QETH_CARD_TEXT(card, 2, "addrxip"); + else if (tmp_addr->type == QETH_IP_TYPE_VIPA) + QETH_CARD_TEXT(card, 2, "addvipa"); + else + QETH_CARD_TEXT(card, 2, "addip"); if (tmp_addr->proto == QETH_PROT_IPV4) QETH_CARD_HEX(card, 4, &tmp_addr->u.a4.addr, 4); @@@ -229,7 -209,7 +229,7 @@@ if (qeth_l3_is_addr_covered_by_ipato(card, addr)) { QETH_CARD_TEXT(card, 2, "tkovaddr"); - addr->set_flags |= QETH_IPA_SETIP_TAKEOVER_FLAG; + addr->ipato = 1; } hash_add(card->ip_htable, &addr->hnode, qeth_l3_ipaddr_hash(addr)); @@@ -271,6 -251,23 +271,6 @@@ return rc; } - -struct qeth_ipaddr *qeth_l3_get_addr_buffer( - enum qeth_prot_versions prot) -{ - struct qeth_ipaddr *addr; - - addr = kzalloc(sizeof(struct qeth_ipaddr), GFP_ATOMIC); - if (!addr) - return NULL; - - addr->type = QETH_IP_TYPE_NORMAL; - addr->disp_flag = QETH_DISP_ADDR_DO_NOTHING; - addr->proto = prot; - - return addr; -} - static void qeth_l3_clear_ip_htable(struct qeth_card *card, int recover) { struct qeth_ipaddr *addr; @@@ -355,7 -352,7 +355,7 @@@ static int qeth_l3_send_setdelmc(struc iob = qeth_get_ipacmd_buffer(card, ipacmd, addr->proto); if (!iob) return -ENOMEM; - cmd = (struct qeth_ipa_cmd *)(iob->data+IPA_PDU_HEADER_SIZE); + cmd = __ipa_cmd(iob); ether_addr_copy(cmd->data.setdelipm.mac, addr->mac); if (addr->proto == QETH_PROT_IPV6) memcpy(cmd->data.setdelipm.ip6, &addr->u.a6.addr, @@@ -382,38 -379,21 +382,38 @@@ static void qeth_l3_fill_netmask(u8 *ne } } +static u32 qeth_l3_get_setdelip_flags(struct qeth_ipaddr *addr, bool set) +{ + switch (addr->type) { + case QETH_IP_TYPE_RXIP: + return (set) ? QETH_IPA_SETIP_TAKEOVER_FLAG : 0; + case QETH_IP_TYPE_VIPA: + return (set) ? QETH_IPA_SETIP_VIPA_FLAG : + QETH_IPA_DELIP_VIPA_FLAG; + default: + return (set && addr->ipato) ? QETH_IPA_SETIP_TAKEOVER_FLAG : 0; + } +} + static int qeth_l3_send_setdelip(struct qeth_card *card, - struct qeth_ipaddr *addr, int ipacmd, unsigned int flags) + struct qeth_ipaddr *addr, + enum qeth_ipa_cmds ipacmd) { - int rc; struct qeth_cmd_buffer *iob; struct qeth_ipa_cmd *cmd; __u8 netmask[16]; + u32 flags; QETH_CARD_TEXT(card, 4, "setdelip"); - QETH_CARD_TEXT_(card, 4, "flags%02X", flags); iob = qeth_get_ipacmd_buffer(card, ipacmd, addr->proto); if (!iob) return -ENOMEM; - cmd = (struct qeth_ipa_cmd *)(iob->data+IPA_PDU_HEADER_SIZE); + cmd = __ipa_cmd(iob); + + flags = qeth_l3_get_setdelip_flags(addr, ipacmd == IPA_CMD_SETIP); + QETH_CARD_TEXT_(card, 4, "flags%02X", flags); + if (addr->proto == QETH_PROT_IPV6) { memcpy(cmd->data.setdelip6.ip_addr, &addr->u.a6.addr, sizeof(struct in6_addr)); @@@ -427,7 -407,9 +427,7 @@@ cmd->data.setdelip4.flags = flags; } - rc = qeth_send_ipa_cmd(card, iob, NULL, NULL); - - return rc; + return qeth_send_ipa_cmd(card, iob, NULL, NULL); } static int qeth_l3_send_setrouting(struct qeth_card *card, @@@ -441,7 -423,7 +441,7 @@@ iob = qeth_get_ipacmd_buffer(card, IPA_CMD_SETRTG, prot); if (!iob) return -ENOMEM; - cmd = (struct qeth_ipa_cmd *)(iob->data+IPA_PDU_HEADER_SIZE); + cmd = __ipa_cmd(iob); cmd->data.setrtg.type = (type); rc = qeth_send_ipa_cmd(card, iob, NULL, NULL); @@@ -543,7 -525,10 +543,7 @@@ void qeth_l3_update_ipato(struct qeth_c hash_for_each(card->ip_htable, i, addr, hnode) { if (addr->type != QETH_IP_TYPE_NORMAL) continue; - if (qeth_l3_is_addr_covered_by_ipato(card, addr)) - addr->set_flags |= QETH_IPA_SETIP_TAKEOVER_FLAG; - else - addr->set_flags &= ~QETH_IPA_SETIP_TAKEOVER_FLAG; + addr->ipato = qeth_l3_is_addr_covered_by_ipato(card, addr); } } @@@ -621,39 -606,132 +621,39 @@@ int qeth_l3_del_ipato_entry(struct qeth return rc; } -/* - * VIPA related functions - */ -int qeth_l3_add_vipa(struct qeth_card *card, enum qeth_prot_versions proto, - const u8 *addr) -{ - struct qeth_ipaddr *ipaddr; - int rc; - - ipaddr = qeth_l3_get_addr_buffer(proto); - if (ipaddr) { - if (proto == QETH_PROT_IPV4) { - QETH_CARD_TEXT(card, 2, "addvipa4"); - memcpy(&ipaddr->u.a4.addr, addr, 4); - ipaddr->u.a4.mask = 0; - } else if (proto == QETH_PROT_IPV6) { - QETH_CARD_TEXT(card, 2, "addvipa6"); - memcpy(&ipaddr->u.a6.addr, addr, 16); - ipaddr->u.a6.pfxlen = 0; - } - ipaddr->type = QETH_IP_TYPE_VIPA; - ipaddr->set_flags = QETH_IPA_SETIP_VIPA_FLAG; - ipaddr->del_flags = QETH_IPA_DELIP_VIPA_FLAG; - } else - return -ENOMEM; - - spin_lock_bh(&card->ip_lock); - rc = qeth_l3_add_ip(card, ipaddr); - spin_unlock_bh(&card->ip_lock); - - kfree(ipaddr); - - return rc; -} - -int qeth_l3_del_vipa(struct qeth_card *card, enum qeth_prot_versions proto, - const u8 *addr) -{ - struct qeth_ipaddr *ipaddr; - int rc; - - ipaddr = qeth_l3_get_addr_buffer(proto); - if (ipaddr) { - if (proto == QETH_PROT_IPV4) { - QETH_CARD_TEXT(card, 2, "delvipa4"); - memcpy(&ipaddr->u.a4.addr, addr, 4); - ipaddr->u.a4.mask = 0; - } else if (proto == QETH_PROT_IPV6) { - QETH_CARD_TEXT(card, 2, "delvipa6"); - memcpy(&ipaddr->u.a6.addr, addr, 16); - ipaddr->u.a6.pfxlen = 0; - } - ipaddr->type = QETH_IP_TYPE_VIPA; - } else - return -ENOMEM; - - spin_lock_bh(&card->ip_lock); - rc = qeth_l3_delete_ip(card, ipaddr); - spin_unlock_bh(&card->ip_lock); - - kfree(ipaddr); - return rc; -} - -/* - * proxy ARP related functions - */ -int qeth_l3_add_rxip(struct qeth_card *card, enum qeth_prot_versions proto, - const u8 *addr) +int qeth_l3_modify_rxip_vipa(struct qeth_card *card, bool add, const u8 *ip, + enum qeth_ip_types type, + enum qeth_prot_versions proto) { - struct qeth_ipaddr *ipaddr; + struct qeth_ipaddr addr; int rc; - ipaddr = qeth_l3_get_addr_buffer(proto); - if (ipaddr) { - if (proto == QETH_PROT_IPV4) { - QETH_CARD_TEXT(card, 2, "addrxip4"); - memcpy(&ipaddr->u.a4.addr, addr, 4); - ipaddr->u.a4.mask = 0; - } else if (proto == QETH_PROT_IPV6) { - QETH_CARD_TEXT(card, 2, "addrxip6"); - memcpy(&ipaddr->u.a6.addr, addr, 16); - ipaddr->u.a6.pfxlen = 0; - } - - ipaddr->type = QETH_IP_TYPE_RXIP; - ipaddr->set_flags = QETH_IPA_SETIP_TAKEOVER_FLAG; - ipaddr->del_flags = 0; - } else - return -ENOMEM; + qeth_l3_init_ipaddr(&addr, type, proto); + if (proto == QETH_PROT_IPV4) + memcpy(&addr.u.a4.addr, ip, 4); + else + memcpy(&addr.u.a6.addr, ip, 16); spin_lock_bh(&card->ip_lock); - rc = qeth_l3_add_ip(card, ipaddr); + rc = add ? qeth_l3_add_ip(card, &addr) : qeth_l3_delete_ip(card, &addr); spin_unlock_bh(&card->ip_lock); - - kfree(ipaddr); - return rc; } -int qeth_l3_del_rxip(struct qeth_card *card, enum qeth_prot_versions proto, - const u8 *addr) +int qeth_l3_modify_hsuid(struct qeth_card *card, bool add) { - struct qeth_ipaddr *ipaddr; - int rc; + struct qeth_ipaddr addr; + int rc, i; - ipaddr = qeth_l3_get_addr_buffer(proto); - if (ipaddr) { - if (proto == QETH_PROT_IPV4) { - QETH_CARD_TEXT(card, 2, "delrxip4"); - memcpy(&ipaddr->u.a4.addr, addr, 4); - ipaddr->u.a4.mask = 0; - } else if (proto == QETH_PROT_IPV6) { - QETH_CARD_TEXT(card, 2, "delrxip6"); - memcpy(&ipaddr->u.a6.addr, addr, 16); - ipaddr->u.a6.pfxlen = 0; - } - ipaddr->type = QETH_IP_TYPE_RXIP; - } else - return -ENOMEM; + qeth_l3_init_ipaddr(&addr, QETH_IP_TYPE_NORMAL, QETH_PROT_IPV6); + addr.u.a6.addr.s6_addr[0] = 0xfe; + addr.u.a6.addr.s6_addr[1] = 0x80; + for (i = 0; i < 8; i++) + addr.u.a6.addr.s6_addr[8+i] = card->options.hsuid[i]; spin_lock_bh(&card->ip_lock); - rc = qeth_l3_delete_ip(card, ipaddr); + rc = add ? qeth_l3_add_ip(card, &addr) : qeth_l3_delete_ip(card, &addr); spin_unlock_bh(&card->ip_lock); - - kfree(ipaddr); return rc; } @@@ -680,7 -758,8 +680,7 @@@ static int qeth_l3_register_addr_entry( if (addr->is_multicast) rc = qeth_l3_send_setdelmc(card, addr, IPA_CMD_SETIPM); else - rc = qeth_l3_send_setdelip(card, addr, IPA_CMD_SETIP, - addr->set_flags); + rc = qeth_l3_send_setdelip(card, addr, IPA_CMD_SETIP); if (rc) QETH_CARD_TEXT(card, 2, "failed"); } while ((--cnt > 0) && rc); @@@ -712,7 -791,8 +712,7 @@@ static int qeth_l3_deregister_addr_entr if (addr->is_multicast) rc = qeth_l3_send_setdelmc(card, addr, IPA_CMD_DELIPM); else - rc = qeth_l3_send_setdelip(card, addr, IPA_CMD_DELIP, - addr->del_flags); + rc = qeth_l3_send_setdelip(card, addr, IPA_CMD_DELIP); if (rc) QETH_CARD_TEXT(card, 2, "failed"); @@@ -992,7 -1072,7 +992,7 @@@ static int qeth_l3_iqd_read_initial_mac QETH_PROT_IPV6); if (!iob) return -ENOMEM; - cmd = (struct qeth_ipa_cmd *)(iob->data+IPA_PDU_HEADER_SIZE); + cmd = __ipa_cmd(iob); *((__u16 *) &cmd->data.create_destroy_addr.unique_id[6]) = card->info.unique_id; @@@ -1037,7 -1117,7 +1037,7 @@@ static int qeth_l3_get_unique_id(struc QETH_PROT_IPV6); if (!iob) return -ENOMEM; - cmd = (struct qeth_ipa_cmd *)(iob->data+IPA_PDU_HEADER_SIZE); + cmd = __ipa_cmd(iob); *((__u16 *) &cmd->data.create_destroy_addr.unique_id[6]) = card->info.unique_id; @@@ -1113,7 -1193,7 +1113,7 @@@ qeth_diags_trace(struct qeth_card *card iob = qeth_get_ipacmd_buffer(card, IPA_CMD_SET_DIAG_ASS, 0); if (!iob) return -ENOMEM; - cmd = (struct qeth_ipa_cmd *)(iob->data+IPA_PDU_HEADER_SIZE); + cmd = __ipa_cmd(iob); cmd->data.diagass.subcmd_len = 16; cmd->data.diagass.subcmd = QETH_DIAGS_CMD_TRACE; cmd->data.diagass.type = QETH_DIAGS_TYPE_HIPERSOCKET; @@@ -1422,24 -1502,30 +1422,24 @@@ static void qeth_l3_rebuild_skb(struct ipv6_eth_mc_map(&ipv6_hdr(skb)->daddr, tg_addr); card->stats.multicast++; - skb->pkt_type = PACKET_MULTICAST; break; case QETH_CAST_BROADCAST: ether_addr_copy(tg_addr, card->dev->broadcast); card->stats.multicast++; - skb->pkt_type = PACKET_BROADCAST; break; - case QETH_CAST_UNICAST: - case QETH_CAST_ANYCAST: - case QETH_CAST_NOCAST: default: if (card->options.sniffer) skb->pkt_type = PACKET_OTHERHOST; - else - skb->pkt_type = PACKET_HOST; ether_addr_copy(tg_addr, card->dev->dev_addr); } + if (hdr->hdr.l3.ext_flags & QETH_HDR_EXT_SRC_MAC_ADDR) card->dev->header_ops->create(skb, card->dev, prot, tg_addr, &hdr->hdr.l3.next_hop.rx.src_mac, - card->dev->addr_len); + skb->len); else card->dev->header_ops->create(skb, card->dev, prot, - tg_addr, "FAKELL", card->dev->addr_len); + tg_addr, "FAKELL", skb->len); } skb->protocol = eth_type_trans(skb, card->dev); @@@ -1486,16 -1572,20 +1486,16 @@@ static int qeth_l3_process_inbound_buff *done = 1; break; } - skb->dev = card->dev; switch (hdr->hdr.l3.id) { case QETH_HEADER_TYPE_LAYER3: magic = *(__u16 *)skb->data; if ((card->info.type == QETH_CARD_TYPE_IQD) && (magic == ETH_P_AF_IUCV)) { skb->protocol = cpu_to_be16(ETH_P_AF_IUCV); - skb->pkt_type = PACKET_HOST; - skb->mac_header = NET_SKB_PAD; - skb->dev = card->dev; len = skb->len; card->dev->header_ops->create(skb, card->dev, 0, - card->dev->dev_addr, "FAKELL", - card->dev->addr_len); + card->dev->dev_addr, "FAKELL", len); + skb_reset_mac_header(skb); netif_receive_skb(skb); } else { qeth_l3_rebuild_skb(card, skb, hdr); @@@ -1504,6 -1594,7 +1504,6 @@@ } break; case QETH_HEADER_TYPE_LAYER2: /* for HiperSockets sniffer */ - skb->pkt_type = PACKET_HOST; skb->protocol = eth_type_trans(skb, skb->dev); len = skb->len; netif_receive_skb(skb); @@@ -1522,6 -1613,69 +1522,6 @@@ return work_done; } -static int qeth_l3_verify_vlan_dev(struct net_device *dev, - struct qeth_card *card) -{ - int rc = 0; - u16 vid; - - for_each_set_bit(vid, card->active_vlans, VLAN_N_VID) { - struct net_device *netdev; - - rcu_read_lock(); - netdev = __vlan_find_dev_deep_rcu(card->dev, htons(ETH_P_8021Q), - vid); - rcu_read_unlock(); - if (netdev == dev) { - rc = QETH_VLAN_CARD; - break; - } - } - - if (rc && !(vlan_dev_real_dev(dev)->ml_priv == (void *)card)) - return 0; - - return rc; -} - -static int qeth_l3_verify_dev(struct net_device *dev) -{ - struct qeth_card *card; - int rc = 0; - unsigned long flags; - - read_lock_irqsave(&qeth_core_card_list.rwlock, flags); - list_for_each_entry(card, &qeth_core_card_list.list, list) { - if (card->dev == dev) { - rc = QETH_REAL_CARD; - break; - } - rc = qeth_l3_verify_vlan_dev(dev, card); - if (rc) - break; - } - read_unlock_irqrestore(&qeth_core_card_list.rwlock, flags); - - return rc; -} - -static struct qeth_card *qeth_l3_get_card_from_dev(struct net_device *dev) -{ - struct qeth_card *card = NULL; - int rc; - - rc = qeth_l3_verify_dev(dev); - if (rc == QETH_REAL_CARD) - card = dev->ml_priv; - else if (rc == QETH_VLAN_CARD) - card = vlan_dev_real_dev(dev)->ml_priv; - if (card && card->options.layer2) - card = NULL; - if (card) - QETH_CARD_TEXT_(card, 4, "%d", rc); - return card ; -} - static void qeth_l3_stop_card(struct qeth_card *card, int recovery_mode) { QETH_DBF_TEXT(SETUP, 2, "stopcard"); @@@ -1850,7 -2004,7 +1850,7 @@@ static int qeth_l3_query_arp_cache_info prot); if (!iob) return -ENOMEM; - cmd = (struct qeth_ipa_cmd *)(iob->data+IPA_PDU_HEADER_SIZE); + cmd = __ipa_cmd(iob); cmd->data.setassparms.data.query_arp.request_bits = 0x000F; cmd->data.setassparms.data.query_arp.reply_bits = 0; cmd->data.setassparms.data.query_arp.no_entries = 0; @@@ -2631,16 -2785,14 +2631,16 @@@ static int qeth_l3_setup_netdev(struct if (!(card->info.unique_id & UNIQUE_ID_NOT_BY_CARD)) card->dev->dev_id = card->info.unique_id & 0xffff; + + card->dev->hw_features |= NETIF_F_SG; + card->dev->vlan_features |= NETIF_F_SG; + if (!card->info.guestlan) { - card->dev->hw_features = NETIF_F_SG | - NETIF_F_RXCSUM | NETIF_F_IP_CSUM | - NETIF_F_TSO; - card->dev->vlan_features = NETIF_F_SG | - NETIF_F_RXCSUM | NETIF_F_IP_CSUM | - NETIF_F_TSO; card->dev->features |= NETIF_F_SG; + card->dev->hw_features |= NETIF_F_TSO | + NETIF_F_RXCSUM | NETIF_F_IP_CSUM; + card->dev->vlan_features |= NETIF_F_TSO | + NETIF_F_RXCSUM | NETIF_F_IP_CSUM; } } } else if (card->info.type == QETH_CARD_TYPE_IQD) { @@@ -2713,8 -2865,8 +2713,8 @@@ static void qeth_l3_remove_device(struc qeth_l3_set_offline(cgdev); if (card->dev) { - netif_napi_del(&card->napi); unregister_netdev(card->dev); + free_netdev(card->dev); card->dev = NULL; } @@@ -2755,6 -2907,7 +2755,6 @@@ static int __qeth_l3_set_online(struct card->info.hwtrap = 0; card->state = CARD_STATE_HARDSETUP; - memset(&card->rx, 0, sizeof(struct qeth_rx)); qeth_print_status_message(card); /* softsetup */ @@@ -2977,43 -3130,13 +2977,43 @@@ struct qeth_discipline qeth_l3_discipli }; EXPORT_SYMBOL_GPL(qeth_l3_discipline); +static int qeth_l3_handle_ip_event(struct qeth_card *card, + struct qeth_ipaddr *addr, + unsigned long event) +{ + switch (event) { + case NETDEV_UP: + spin_lock_bh(&card->ip_lock); + qeth_l3_add_ip(card, addr); + spin_unlock_bh(&card->ip_lock); + return NOTIFY_OK; + case NETDEV_DOWN: + spin_lock_bh(&card->ip_lock); + qeth_l3_delete_ip(card, addr); + spin_unlock_bh(&card->ip_lock); + return NOTIFY_OK; + default: + return NOTIFY_DONE; + } +} + +static struct qeth_card *qeth_l3_get_card_from_dev(struct net_device *dev) +{ + if (is_vlan_dev(dev)) + dev = vlan_dev_real_dev(dev); + if (dev->netdev_ops == &qeth_l3_osa_netdev_ops || + dev->netdev_ops == &qeth_l3_netdev_ops) + return (struct qeth_card *) dev->ml_priv; + return NULL; +} + static int qeth_l3_ip_event(struct notifier_block *this, unsigned long event, void *ptr) { struct in_ifaddr *ifa = (struct in_ifaddr *)ptr; - struct net_device *dev = (struct net_device *)ifa->ifa_dev->dev; - struct qeth_ipaddr *addr; + struct net_device *dev = ifa->ifa_dev->dev; + struct qeth_ipaddr addr; struct qeth_card *card; if (dev_net(dev) != &init_net) @@@ -3024,11 -3147,29 +3024,11 @@@ return NOTIFY_DONE; QETH_CARD_TEXT(card, 3, "ipevent"); - addr = qeth_l3_get_addr_buffer(QETH_PROT_IPV4); - if (addr) { - addr->u.a4.addr = be32_to_cpu(ifa->ifa_address); - addr->u.a4.mask = be32_to_cpu(ifa->ifa_mask); - addr->type = QETH_IP_TYPE_NORMAL; - } else - return NOTIFY_DONE; - - switch (event) { - case NETDEV_UP: - spin_lock_bh(&card->ip_lock); - qeth_l3_add_ip(card, addr); - spin_unlock_bh(&card->ip_lock); - break; - case NETDEV_DOWN: - spin_lock_bh(&card->ip_lock); - qeth_l3_delete_ip(card, addr); - spin_unlock_bh(&card->ip_lock); - break; - } + qeth_l3_init_ipaddr(&addr, QETH_IP_TYPE_NORMAL, QETH_PROT_IPV4); + addr.u.a4.addr = be32_to_cpu(ifa->ifa_address); + addr.u.a4.mask = be32_to_cpu(ifa->ifa_mask); - kfree(addr); - return NOTIFY_DONE; + return qeth_l3_handle_ip_event(card, &addr, event); } static struct notifier_block qeth_l3_ip_notifier = { @@@ -3040,8 -3181,8 +3040,8 @@@ static int qeth_l3_ip6_event(struct not unsigned long event, void *ptr) { struct inet6_ifaddr *ifa = (struct inet6_ifaddr *)ptr; - struct net_device *dev = (struct net_device *)ifa->idev->dev; - struct qeth_ipaddr *addr; + struct net_device *dev = ifa->idev->dev; + struct qeth_ipaddr addr; struct qeth_card *card; card = qeth_l3_get_card_from_dev(dev); @@@ -3051,11 -3192,29 +3051,11 @@@ if (!qeth_is_supported(card, IPA_IPV6)) return NOTIFY_DONE; - addr = qeth_l3_get_addr_buffer(QETH_PROT_IPV6); - if (addr) { - memcpy(&addr->u.a6.addr, &ifa->addr, sizeof(struct in6_addr)); - addr->u.a6.pfxlen = ifa->prefix_len; - addr->type = QETH_IP_TYPE_NORMAL; - } else - return NOTIFY_DONE; - - switch (event) { - case NETDEV_UP: - spin_lock_bh(&card->ip_lock); - qeth_l3_add_ip(card, addr); - spin_unlock_bh(&card->ip_lock); - break; - case NETDEV_DOWN: - spin_lock_bh(&card->ip_lock); - qeth_l3_delete_ip(card, addr); - spin_unlock_bh(&card->ip_lock); - break; - } + qeth_l3_init_ipaddr(&addr, QETH_IP_TYPE_NORMAL, QETH_PROT_IPV6); + addr.u.a6.addr = ifa->addr; + addr.u.a6.pfxlen = ifa->prefix_len; - kfree(addr); - return NOTIFY_DONE; + return qeth_l3_handle_ip_event(card, &addr, event); } static struct notifier_block qeth_l3_ip6_notifier = { diff --combined drivers/vhost/net.c index b5fb56b822fd,8139bc70ad7d..a31d9b240af8 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@@ -170,7 -170,7 +170,7 @@@ static void vhost_net_buf_unproduce(str if (nvq->rx_ring && !vhost_net_buf_is_empty(rxq)) { ptr_ring_unconsume(nvq->rx_ring, rxq->queue + rxq->head, vhost_net_buf_get_size(rxq), - __skb_array_destroy_skb); + tun_ptr_free); rxq->head = rxq->tail = 0; } } @@@ -948,6 -948,7 +948,7 @@@ static int vhost_net_open(struct inode n->vqs[i].done_idx = 0; n->vqs[i].vhost_hlen = 0; n->vqs[i].sock_hlen = 0; + n->vqs[i].rx_ring = NULL; vhost_net_buf_init(&n->vqs[i].rxq); } vhost_dev_init(dev, vqs, VHOST_NET_VQ_MAX); @@@ -972,6 -973,7 +973,7 @@@ static struct socket *vhost_net_stop_vq vhost_net_disable_vq(n, vq); vq->private_data = NULL; vhost_net_buf_unproduce(nvq); + nvq->rx_ring = NULL; mutex_unlock(&vq->mutex); return sock; } @@@ -1038,7 -1040,7 +1040,7 @@@ static struct socket *get_raw_socket(in 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) @@@ -1050,8 -1052,9 +1052,8 @@@ 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) { @@@ -1160,14 -1163,14 +1162,14 @@@ static long vhost_net_set_backend(struc vhost_net_disable_vq(n, vq); vq->private_data = sock; vhost_net_buf_unproduce(nvq); - if (index == VHOST_NET_VQ_RX) - nvq->rx_ring = get_tap_ptr_ring(fd); r = vhost_vq_init_access(vq); if (r) goto err_used; r = vhost_net_enable_vq(n, vq); if (r) goto err_used; + if (index == VHOST_NET_VQ_RX) + nvq->rx_ring = get_tap_ptr_ring(fd); oldubufs = nvq->ubufs; nvq->ubufs = ubufs; diff --combined include/linux/mlx5/driver.h index 4814cad7456e,9d3a03364e6e..cded85ab6fe4 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@@ -345,6 -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; @@@ -352,15 -359,6 +352,15 @@@ 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; @@@ -377,18 -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; @@@ -462,8 -453,8 +462,8 @@@ struct mlx5_core_srq struct mlx5_core_rsc_common common; /* must be first */ u32 srqn; int max; - int max_gs; - int max_avail_gather; + size_t max_gs; + size_t max_avail_gather; int wqe_shift; void (*event) (struct mlx5_core_srq *, enum mlx5_event); @@@ -535,6 -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 */ @@@ -656,6 -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 */ @@@ -934,9 -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) \ @@@ -975,25 -977,6 +975,25 @@@ static inline u32 mlx5_base_mkey(const 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); @@@ -1019,10 -1002,9 +1019,10 @@@ void mlx5_drain_health_wq(struct mlx5_c 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); @@@ -1067,12 -1049,22 +1067,12 @@@ int mlx5_satisfy_startup_pages(struct m 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); @@@ -1084,6 -1076,14 +1084,6 @@@ int mlx5_core_access_reg(struct mlx5_co 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); @@@ -1224,12 -1224,6 +1224,12 @@@ static inline int mlx5_core_is_pf(struc 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 --combined include/linux/net.h index 000d1aada74f,2a0391eea05c..2248a052061d --- a/include/linux/net.h +++ b/include/linux/net.h @@@ -146,7 -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, @@@ -222,6 -222,7 +222,7 @@@ enum int sock_wake_async(struct socket_wq *sk_wq, int how, int band); int sock_register(const struct net_proto_family *fam); void sock_unregister(int family); + bool sock_is_registered(int family); int __sock_create(struct net *net, int family, int type, int proto, struct socket **res, int kern); int sock_create(int family, int type, int proto, struct socket **res); @@@ -294,8 -295,10 +295,8 @@@ int kernel_listen(struct socket *sock, 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 --combined include/linux/phy.h index 5a9b1753fdc5,7c4c2379e010..f0b5870a6d40 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@@ -984,6 -984,10 +984,10 @@@ static inline int genphy_no_soft_reset( { return 0; } + int genphy_read_mmd_unsupported(struct phy_device *phdev, int devad, + u16 regnum); + int genphy_write_mmd_unsupported(struct phy_device *phdev, int devnum, + u16 regnum, u16 val); /* Clause 45 PHY */ int genphy_c45_restart_aneg(struct phy_device *phydev); @@@ -995,14 -999,6 +999,14 @@@ int genphy_c45_pma_setup_forced(struct 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) @@@ -1020,7 -1016,6 +1024,6 @@@ int phy_driver_register(struct phy_driv int phy_drivers_register(struct phy_driver *new_driver, int n, struct module *owner); void phy_state_machine(struct work_struct *work); - void phy_change(struct phy_device *phydev); void phy_change_work(struct work_struct *work); void phy_mac_interrupt(struct phy_device *phydev); void phy_start_machine(struct phy_device *phydev); diff --combined include/linux/skbuff.h index d8340e6e8814,99df17109e1b..47082f54ec1f --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@@ -466,9 -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); @@@ -4040,6 -4037,12 +4040,12 @@@ static inline bool skb_is_gso_v6(const return skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6; } + /* Note: Should be called only if skb_is_gso(skb) is true */ + static inline bool skb_is_gso_sctp(const struct sk_buff *skb) + { + return skb_shinfo(skb)->gso_type & SKB_GSO_SCTP; + } + static inline void skb_gso_reset(struct sk_buff *skb) { skb_shinfo(skb)->gso_size = 0; @@@ -4047,6 -4050,22 +4053,22 @@@ skb_shinfo(skb)->gso_type = 0; } + static inline void skb_increase_gso_size(struct skb_shared_info *shinfo, + u16 increment) + { + if (WARN_ON_ONCE(shinfo->gso_size == GSO_BY_FRAGS)) + return; + shinfo->gso_size += increment; + } + + static inline void skb_decrease_gso_size(struct skb_shared_info *shinfo, + u16 decrement) + { + if (WARN_ON_ONCE(shinfo->gso_size == GSO_BY_FRAGS)) + return; + shinfo->gso_size -= decrement; + } + void __skb_warn_lro_forwarding(const struct sk_buff *skb); static inline bool skb_warn_if_lro(const struct sk_buff *skb) diff --combined include/net/ip.h index d53b5a9eae34,f49b3a576bec..36f8f7811093 --- a/include/net/ip.h +++ b/include/net/ip.h @@@ -91,17 -91,6 +91,17 @@@ static inline int inet_sdif(struct sk_b return 0; } +/* Special input handler for packets caught by router alert option. + They are selected only by protocol field, and then processed likely + local ones; but only if someone wants them! Otherwise, router + not running rsvpd will kill RSVP. + + It is user level problem, what it will make with them. + I have no idea, how it will masquearde or NAT them (it is joke, joke :-)), + but receiver should be enough clever f.e. to forward mtrace requests, + sent to multicast group to reach destination designated router. + */ + struct ip_ra_chain { struct ip_ra_chain __rcu *next; struct sock *sk; @@@ -112,6 -101,8 +112,6 @@@ struct rcu_head rcu; }; -extern struct ip_ra_chain __rcu *ip_ra_chain; - /* IP flags. */ #define IP_CE 0x8000 /* Flag: "Congestion" */ #define IP_DF 0x4000 /* Flag: "Don't Fragment" */ @@@ -195,15 -186,15 +195,15 @@@ int ip4_datagram_connect(struct sock *s 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 @@@ -337,6 -328,13 +337,13 @@@ int ip_decrease_ttl(struct iphdr *iph return --iph->ttl; } + static inline int ip_mtu_locked(const struct dst_entry *dst) + { + const struct rtable *rt = (const struct rtable *)dst; + + return rt->rt_mtu_locked || dst_metric_locked(dst, RTAX_MTU); + } + static inline int ip_dont_fragment(const struct sock *sk, const struct dst_entry *dst) { @@@ -344,7 -342,7 +351,7 @@@ return pmtudisc == IP_PMTUDISC_DO || (pmtudisc == IP_PMTUDISC_WANT && - !(dst_metric_locked(dst, RTAX_MTU))); + !ip_mtu_locked(dst)); } static inline bool ip_sk_accept_pmtu(const struct sock *sk) @@@ -370,7 -368,7 +377,7 @@@ static inline unsigned int ip_dst_mtu_m struct net *net = dev_net(dst->dev); if (net->ipv4.sysctl_ip_fwd_use_pmtu || - dst_metric_locked(dst, RTAX_MTU) || + ip_mtu_locked(dst) || !forwarding) return dst_mtu(dst); @@@ -586,13 -584,13 +593,13 @@@ 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 --combined include/net/ip6_route.h index ce2abc0ff102,ac0866bb9e93..0084013d6bed --- a/include/net/ip6_route.h +++ b/include/net/ip6_route.h @@@ -75,8 -75,7 +75,8 @@@ static inline bool rt6_qualify_for_ecmp 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); @@@ -89,10 -88,9 +89,10 @@@ static inline struct dst_entry *ip6_rou } 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); @@@ -128,10 -126,8 +128,10 @@@ static inline int ip6_route_get_saddr(s } 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); @@@ -183,6 -179,9 +183,9 @@@ void rt6_disable_ip(struct net_device * void rt6_sync_down_dev(struct net_device *dev, unsigned long event); void rt6_multipath_rebalance(struct rt6_info *rt); + void rt6_uncached_list_add(struct rt6_info *rt); + void rt6_uncached_list_del(struct rt6_info *rt); + static inline const struct rt6_info *skb_rt6_info(const struct sk_buff *skb) { const struct dst_entry *dst = skb_dst(skb); @@@ -270,5 -269,4 +273,5 @@@ static inline bool rt6_duplicate_nextho ipv6_addr_equal(&a->rt6i_gateway, &b->rt6i_gateway) && !lwtunnel_cmp_encap(a->dst.lwtstate, b->dst.lwtstate); } + #endif diff --combined include/net/ip_fib.h index 7c7522e8585b,77d0a78cf7d2..81d0f2107ff1 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@@ -59,6 -59,7 +59,7 @@@ struct fib_nh_exception int fnhe_genid; __be32 fnhe_daddr; u32 fnhe_pmtu; + bool fnhe_mtu_locked; __be32 fnhe_gw; unsigned long fnhe_expires; struct rtable __rcu *fnhe_rth_input; @@@ -157,7 -158,7 +158,7 @@@ struct fib_result_nl unsigned char nh_sel; unsigned char type; unsigned char scope; - int err; + int err; }; #ifdef CONFIG_IP_ROUTE_MULTIPATH @@@ -293,13 -294,6 +294,13 @@@ static inline unsigned int fib4_rules_s 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); @@@ -348,24 -342,6 +349,24 @@@ bool fib4_rule_default(const struct fib 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 */ @@@ -395,8 -371,8 +396,8 @@@ int fib_sync_down_addr(struct net_devic 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 --combined include/net/mac80211.h index 2fd59ed3be00,2b581bd93812..2449982daf75 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@@ -6,7 -6,6 +6,7 @@@ * Copyright 2007-2010 Johannes Berg &lt;johannes(a)sipsolutions.net&gt; * 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 @@@ -935,7 -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 { @@@ -1100,9 -1098,6 +1100,9 @@@ ieee80211_tx_info_clear_status(struct i * 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), @@@ -1129,8 -1124,6 +1129,8 @@@ 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), }; /** @@@ -2070,13 -2063,8 +2070,16 @@@ 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. ++ > + * @IEEE80211_HW_DOESNT_SUPPORT_QOS_NDP: The driver (or firmware) doesn't + * support QoS NDP for AP probing - that's most likely a driver bug. * * @NUM_IEEE80211_HW_FLAGS: number of hardware flags, used for sizing arrays */ @@@ -2121,7 -2109,7 +2124,8 @@@ 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, + IEEE80211_HW_DOESNT_SUPPORT_QOS_NDP, /* keep last, obviously */ NUM_IEEE80211_HW_FLAGS @@@ -3366,9 -3354,6 +3370,9 @@@ 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 --combined include/net/route.h index 158833ea7988,20a92ca9e115..dbb032d5921b --- a/include/net/route.h +++ b/include/net/route.h @@@ -63,8 -63,11 +63,9 @@@ struct rtable __be32 rt_gateway; /* Miscellaneous cached information */ - u32 rt_pmtu; + u32 rt_mtu_locked:1, + rt_pmtu:31; - u32 rt_table_id; - struct list_head rt_uncached; struct uncached_list *rt_uncached_list; }; @@@ -225,6 -228,9 +226,9 @@@ struct in_ifaddr void fib_add_ifaddr(struct in_ifaddr *); void fib_del_ifaddr(struct in_ifaddr *, struct in_ifaddr *); + void rt_add_uncached_list(struct rtable *rt); + void rt_del_uncached_list(struct rtable *rt); + static inline void ip_rt_put(struct rtable *rt) { /* dst_release() accepts a NULL parameter. diff --combined include/net/sch_generic.h index d4907b584b38,2092d33194dd..493e311bbe93 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@@ -540,7 -540,7 +540,7 @@@ static inline bool skb_skip_tc_classify 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; @@@ -824,6 -824,16 +824,16 @@@ static inline void __qdisc_drop(struct *to_free = skb; } + static inline void __qdisc_drop_all(struct sk_buff *skb, + struct sk_buff **to_free) + { + if (skb->prev) + skb->prev->next = *to_free; + else + skb->next = *to_free; + *to_free = skb; + } + static inline unsigned int __qdisc_queue_drop_head(struct Qdisc *sch, struct qdisc_skb_head *qh, struct sk_buff **to_free) @@@ -956,6 -966,15 +966,15 @@@ static inline int qdisc_drop(struct sk_ return NET_XMIT_DROP; } + static inline int qdisc_drop_all(struct sk_buff *skb, struct Qdisc *sch, + struct sk_buff **to_free) + { + __qdisc_drop_all(skb, to_free); + qdisc_qstats_drop(sch); + + return NET_XMIT_DROP; + } + /* Length to Time (L2T) lookup in a qdisc_rate_table, to determine how long it will take to send a packet given its size. */ diff --combined include/net/sock.h index b7c75e024e37,ae23f3b389ca..709311132d4c --- a/include/net/sock.h +++ b/include/net/sock.h @@@ -417,7 -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; @@@ -1138,6 -1137,7 +1138,7 @@@ struct proto int proto_register(struct proto *prot, int alloc_slab); void proto_unregister(struct proto *prot); + int sock_load_diag_module(int family, int protocol); #ifdef SOCK_REFCNT_DEBUG static inline void sk_refcnt_debug_inc(struct sock *sk) @@@ -1585,7 -1585,7 +1586,7 @@@ int sock_no_bind(struct socket *, struc 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); @@@ -1863,6 -1863,15 +1864,6 @@@ static inline void sk_nocaps_add(struc 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) @@@ -2141,10 -2150,6 +2142,10 @@@ static inline struct page_frag *sk_page bool sk_page_frag_refill(struct sock *sk, struct page_frag *pfrag); +int sk_alloc_sg(struct sock *sk, int len, struct scatterlist *sg, + int sg_start, int *sg_curr, unsigned int *sg_size, + int first_coalesce); + /* * Default write policy as shown to user space via poll/select/SIGIO */ diff --combined include/uapi/linux/if_ether.h index 2e4a6c1accaa,820de5d222d2..3a45b4ad71a3 --- a/include/uapi/linux/if_ether.h +++ b/include/uapi/linux/if_ether.h @@@ -30,6 -30,7 +30,7 @@@ */ #define ETH_ALEN 6 /* Octets in one ethernet addr */ + #define ETH_TLEN 2 /* Octets in ethernet type field */ #define ETH_HLEN 14 /* Total octets in header. */ #define ETH_ZLEN 60 /* Min. octets in frame sans FCS */ #define ETH_DATA_LEN 1500 /* Max. octets in payload */ @@@ -88,7 -89,6 +89,7 @@@ #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 --combined kernel/bpf/syscall.c index 3aeb4ea2a93a,43f95d190eea..dd172ee16716 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@@ -1315,8 -1315,7 +1315,8 @@@ static int bpf_obj_get(const union bpf_ #define BPF_PROG_ATTACH_LAST_FIELD attach_flags -static int sockmap_get_from_fd(const union bpf_attr *attr, bool attach) +static int sockmap_get_from_fd(const union bpf_attr *attr, + int type, bool attach) { struct bpf_prog *prog = NULL; int ufd = attr->target_fd; @@@ -1330,7 -1329,8 +1330,7 @@@ return PTR_ERR(map); if (attach) { - prog = bpf_prog_get_type(attr->attach_bpf_fd, - BPF_PROG_TYPE_SK_SKB); + prog = bpf_prog_get_type(attr->attach_bpf_fd, type); if (IS_ERR(prog)) { fdput(f); return PTR_ERR(prog); @@@ -1382,11 -1382,9 +1382,11 @@@ static int bpf_prog_attach(const union case BPF_CGROUP_DEVICE: ptype = BPF_PROG_TYPE_CGROUP_DEVICE; break; + case BPF_SK_MSG_VERDICT: + return sockmap_get_from_fd(attr, BPF_PROG_TYPE_SK_MSG, true); case BPF_SK_SKB_STREAM_PARSER: case BPF_SK_SKB_STREAM_VERDICT: - return sockmap_get_from_fd(attr, true); + return sockmap_get_from_fd(attr, BPF_PROG_TYPE_SK_SKB, true); default: return -EINVAL; } @@@ -1439,11 -1437,9 +1439,11 @@@ static int bpf_prog_detach(const union case BPF_CGROUP_DEVICE: ptype = BPF_PROG_TYPE_CGROUP_DEVICE; break; + case BPF_SK_MSG_VERDICT: + return sockmap_get_from_fd(attr, BPF_PROG_TYPE_SK_MSG, false); case BPF_SK_SKB_STREAM_PARSER: case BPF_SK_SKB_STREAM_VERDICT: - return sockmap_get_from_fd(attr, false); + return sockmap_get_from_fd(attr, BPF_PROG_TYPE_SK_SKB, false); default: return -EINVAL; } @@@ -1849,7 -1845,7 +1849,7 @@@ SYSCALL_DEFINE3(bpf, int, cmd, union bp union bpf_attr attr = {}; int err; - if (!capable(CAP_SYS_ADMIN) && sysctl_unprivileged_bpf_disabled) + if (sysctl_unprivileged_bpf_disabled && !capable(CAP_SYS_ADMIN)) return -EPERM; err = check_uarg_tail_zero(uattr, sizeof(attr), size); diff --combined kernel/trace/bpf_trace.c index c634e093951f,01e6b3a38871..7f9691c86b6e --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@@ -661,7 -661,41 +661,41 @@@ static const struct bpf_func_proto bpf_ .arg3_type = ARG_ANYTHING, }; - BPF_CALL_3(bpf_perf_prog_read_value_tp, struct bpf_perf_event_data_kern *, ctx, + static const struct bpf_func_proto *tp_prog_func_proto(enum bpf_func_id func_id) + { + switch (func_id) { + case BPF_FUNC_perf_event_output: + return &bpf_perf_event_output_proto_tp; + case BPF_FUNC_get_stackid: + return &bpf_get_stackid_proto_tp; + default: + return tracing_func_proto(func_id); + } + } + + static bool tp_prog_is_valid_access(int off, int size, enum bpf_access_type type, + struct bpf_insn_access_aux *info) + { + if (off < sizeof(void *) || off >= PERF_MAX_TRACE_SIZE) + return false; + if (type != BPF_READ) + return false; + if (off % size != 0) + return false; + + BUILD_BUG_ON(PERF_MAX_TRACE_SIZE % sizeof(__u64)); + return true; + } + + const struct bpf_verifier_ops tracepoint_verifier_ops = { + .get_func_proto = tp_prog_func_proto, + .is_valid_access = tp_prog_is_valid_access, + }; + + const struct bpf_prog_ops tracepoint_prog_ops = { + }; + + BPF_CALL_3(bpf_perf_prog_read_value, struct bpf_perf_event_data_kern *, ctx, struct bpf_perf_event_value *, buf, u32, size) { int err = -EINVAL; @@@ -678,8 -712,8 +712,8 @@@ clear return err; } - static const struct bpf_func_proto bpf_perf_prog_read_value_proto_tp = { - .func = bpf_perf_prog_read_value_tp, + static const struct bpf_func_proto bpf_perf_prog_read_value_proto = { + .func = bpf_perf_prog_read_value, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, @@@ -687,7 -721,7 +721,7 @@@ .arg3_type = ARG_CONST_SIZE, }; - static const struct bpf_func_proto *tp_prog_func_proto(enum bpf_func_id func_id) + static const struct bpf_func_proto *pe_prog_func_proto(enum bpf_func_id func_id) { switch (func_id) { case BPF_FUNC_perf_event_output: @@@ -695,38 -729,17 +729,16 @@@ case BPF_FUNC_get_stackid: return &bpf_get_stackid_proto_tp; case BPF_FUNC_perf_prog_read_value: - return &bpf_perf_prog_read_value_proto_tp; + return &bpf_perf_prog_read_value_proto; default: return tracing_func_proto(func_id); } } - static bool tp_prog_is_valid_access(int off, int size, enum bpf_access_type type, - struct bpf_insn_access_aux *info) - { - if (off < sizeof(void *) || off >= PERF_MAX_TRACE_SIZE) - return false; - if (type != BPF_READ) - return false; - if (off % size != 0) - return false; - - BUILD_BUG_ON(PERF_MAX_TRACE_SIZE % sizeof(__u64)); - return true; - } - - const struct bpf_verifier_ops tracepoint_verifier_ops = { - .get_func_proto = tp_prog_func_proto, - .is_valid_access = tp_prog_is_valid_access, - }; - - const struct bpf_prog_ops tracepoint_prog_ops = { - }; - static bool pe_prog_is_valid_access(int off, int size, enum bpf_access_type type, struct bpf_insn_access_aux *info) { - const int size_sp = FIELD_SIZEOF(struct bpf_perf_event_data, - sample_period); + const int size_u64 = sizeof(u64); if (off < 0 || off >= sizeof(struct bpf_perf_event_data)) return false; @@@ -737,13 -750,8 +749,13 @@@ switch (off) { case bpf_ctx_range(struct bpf_perf_event_data, sample_period): - bpf_ctx_record_field_size(info, size_sp); - if (!bpf_ctx_narrow_access_ok(off, size, size_sp)) + bpf_ctx_record_field_size(info, size_u64); + if (!bpf_ctx_narrow_access_ok(off, size, size_u64)) + return false; + break; + case bpf_ctx_range(struct bpf_perf_event_data, addr): + bpf_ctx_record_field_size(info, size_u64); + if (!bpf_ctx_narrow_access_ok(off, size, size_u64)) return false; break; default: @@@ -770,14 -778,6 +782,14 @@@ static u32 pe_prog_convert_ctx_access(e bpf_target_off(struct perf_sample_data, period, 8, target_size)); break; + case offsetof(struct bpf_perf_event_data, addr): + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_perf_event_data_kern, + data), si->dst_reg, si->src_reg, + offsetof(struct bpf_perf_event_data_kern, data)); + *insn++ = BPF_LDX_MEM(BPF_DW, si->dst_reg, si->dst_reg, + bpf_target_off(struct perf_sample_data, addr, 8, + target_size)); + break; default: *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_perf_event_data_kern, regs), si->dst_reg, si->src_reg, @@@ -791,7 -791,7 +803,7 @@@ } const struct bpf_verifier_ops perf_event_verifier_ops = { - .get_func_proto = tp_prog_func_proto, + .get_func_proto = pe_prog_func_proto, .is_valid_access = pe_prog_is_valid_access, .convert_ctx_access = pe_prog_convert_ctx_access, }; diff --combined net/batman-adv/distributed-arp-table.c index 75dda9454ccf,87cd962d28d5..a60bacf7120b --- a/net/batman-adv/distributed-arp-table.c +++ b/net/batman-adv/distributed-arp-table.c @@@ -1,5 -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 * @@@ -33,7 -33,6 +33,7 @@@ #include <linux/kernel.h> #include <linux/kref.h> #include <linux/list.h> +#include <linux/netlink.h> #include <linux/rculist.h> #include <linux/rcupdate.h> #include <linux/seq_file.h> @@@ -44,19 -43,13 +44,19 @@@ #include <linux/string.h> #include <linux/workqueue.h> #include <net/arp.h> +#include <net/genetlink.h> +#include <net/netlink.h> +#include <net/sock.h> +#include <uapi/linux/batman_adv.h> #include "bridge_loop_avoidance.h" #include "hard-interface.h" #include "hash.h" #include "log.h" +#include "netlink.h" #include "originator.h" #include "send.h" +#include "soft-interface.h" #include "translation-table.h" #include "tvlv.h" @@@ -400,7 -393,7 +400,7 @@@ static void batadv_dbg_arp(struct batad batadv_arp_hw_src(skb, hdr_size), &ip_src, batadv_arp_hw_dst(skb, hdr_size), &ip_dst); - if (hdr_size == 0) + if (hdr_size < sizeof(struct batadv_unicast_packet)) return; unicast_4addr_packet = (struct batadv_unicast_4addr_packet *)skb->data; @@@ -502,7 -495,7 +502,7 @@@ static bool batadv_is_orig_node_eligibl * 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; @@@ -859,151 -852,6 +859,151 @@@ out #endif /** + * batadv_dat_cache_dump_entry() - dump one entry of the DAT cache table to a + * netlink socket + * @msg: buffer for the message + * @portid: netlink port + * @seq: Sequence number of netlink message + * @dat_entry: entry to dump + * + * Return: 0 or error code. + */ +static int +batadv_dat_cache_dump_entry(struct sk_buff *msg, u32 portid, u32 seq, + struct batadv_dat_entry *dat_entry) +{ + int msecs; + void *hdr; + + hdr = genlmsg_put(msg, portid, seq, &batadv_netlink_family, + NLM_F_MULTI, BATADV_CMD_GET_DAT_CACHE); + if (!hdr) + return -ENOBUFS; + + msecs = jiffies_to_msecs(jiffies - dat_entry->last_update); + + if (nla_put_in_addr(msg, BATADV_ATTR_DAT_CACHE_IP4ADDRESS, + dat_entry->ip) || + nla_put(msg, BATADV_ATTR_DAT_CACHE_HWADDRESS, ETH_ALEN, + dat_entry->mac_addr) || + nla_put_u16(msg, BATADV_ATTR_DAT_CACHE_VID, dat_entry->vid) || + nla_put_u32(msg, BATADV_ATTR_LAST_SEEN_MSECS, msecs)) { + genlmsg_cancel(msg, hdr); + return -EMSGSIZE; + } + + genlmsg_end(msg, hdr); + return 0; +} + +/** + * batadv_dat_cache_dump_bucket() - dump one bucket of the DAT cache table to + * a netlink socket + * @msg: buffer for the message + * @portid: netlink port + * @seq: Sequence number of netlink message + * @head: bucket to dump + * @idx_skip: How many entries to skip + * + * Return: 0 or error code. + */ +static int +batadv_dat_cache_dump_bucket(struct sk_buff *msg, u32 portid, u32 seq, + struct hlist_head *head, int *idx_skip) +{ + struct batadv_dat_entry *dat_entry; + int idx = 0; + + rcu_read_lock(); + hlist_for_each_entry_rcu(dat_entry, head, hash_entry) { + if (idx < *idx_skip) + goto skip; + + if (batadv_dat_cache_dump_entry(msg, portid, seq, + dat_entry)) { + rcu_read_unlock(); + *idx_skip = idx; + + return -EMSGSIZE; + } + +skip: + idx++; + } + rcu_read_unlock(); + + return 0; +} + +/** + * batadv_dat_cache_dump() - dump DAT cache table to a netlink socket + * @msg: buffer for the message + * @cb: callback structure containing arguments + * + * Return: message length. + */ +int batadv_dat_cache_dump(struct sk_buff *msg, struct netlink_callback *cb) +{ + struct batadv_hard_iface *primary_if = NULL; + int portid = NETLINK_CB(cb->skb).portid; + struct net *net = sock_net(cb->skb->sk); + struct net_device *soft_iface; + struct batadv_hashtable *hash; + struct batadv_priv *bat_priv; + int bucket = cb->args[0]; + struct hlist_head *head; + int idx = cb->args[1]; + int ifindex; + int ret = 0; + + ifindex = batadv_netlink_get_ifindex(cb->nlh, + BATADV_ATTR_MESH_IFINDEX); + if (!ifindex) + return -EINVAL; + + soft_iface = dev_get_by_index(net, ifindex); + if (!soft_iface || !batadv_softif_is_valid(soft_iface)) { + ret = -ENODEV; + goto out; + } + + bat_priv = netdev_priv(soft_iface); + hash = bat_priv->dat.hash; + + primary_if = batadv_primary_if_get_selected(bat_priv); + if (!primary_if || primary_if->if_status != BATADV_IF_ACTIVE) { + ret = -ENOENT; + goto out; + } + + while (bucket < hash->size) { + head = &hash->table[bucket]; + + if (batadv_dat_cache_dump_bucket(msg, portid, + cb->nlh->nlmsg_seq, head, + &idx)) + break; + + bucket++; + idx = 0; + } + + cb->args[0] = bucket; + cb->args[1] = idx; + + ret = msg->len; + +out: + if (primary_if) + batadv_hardif_put(primary_if); + + if (soft_iface) + dev_put(soft_iface); + + return ret; +} + +/** * batadv_arp_get_type() - parse an ARP packet and gets the type * @bat_priv: the bat priv with all the soft interface information * @skb: packet to analyse diff --combined net/batman-adv/icmp_socket.c index 7d5e9abb7a65,5daa3d50da17..55c358ad3331 --- a/net/batman-adv/icmp_socket.c +++ b/net/batman-adv/icmp_socket.c @@@ -1,5 -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 * @@@ -24,6 -24,7 +24,7 @@@ #include <linux/debugfs.h> #include <linux/errno.h> #include <linux/etherdevice.h> + #include <linux/eventpoll.h> #include <linux/export.h> #include <linux/fcntl.h> #include <linux/fs.h> diff --combined net/batman-adv/log.c index 52d8a4b848c0,cdbe0e5e208b..853773e45f79 --- a/net/batman-adv/log.c +++ b/net/batman-adv/log.c @@@ -1,5 -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 * @@@ -22,6 -22,7 +22,7 @@@ #include <linux/compiler.h> #include <linux/debugfs.h> #include <linux/errno.h> + #include <linux/eventpoll.h> #include <linux/export.h> #include <linux/fcntl.h> #include <linux/fs.h> diff --combined net/batman-adv/multicast.c index 5615b6abea6f,d70640135e3a..de3a055f7dd8 --- a/net/batman-adv/multicast.c +++ b/net/batman-adv/multicast.c @@@ -1,5 -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 * @@@ -40,7 -40,6 +40,7 @@@ #include <linux/list.h> #include <linux/lockdep.h> #include <linux/netdevice.h> +#include <linux/netlink.h> #include <linux/printk.h> #include <linux/rculist.h> #include <linux/rcupdate.h> @@@ -53,20 -52,14 +53,20 @@@ #include <linux/types.h> #include <linux/workqueue.h> #include <net/addrconf.h> +#include <net/genetlink.h> #include <net/if_inet6.h> #include <net/ip.h> #include <net/ipv6.h> +#include <net/netlink.h> +#include <net/sock.h> #include <uapi/linux/batadv_packet.h> +#include <uapi/linux/batman_adv.h> #include "hard-interface.h" #include "hash.h" #include "log.h" +#include "netlink.h" +#include "soft-interface.h" #include "translation-table.h" #include "tvlv.h" @@@ -109,36 -102,7 +109,36 @@@ static struct net_device *batadv_mcast_ } /** + * batadv_mcast_addr_is_ipv4() - check if multicast MAC is IPv4 + * @addr: the MAC address to check + * + * Return: True, if MAC address is one reserved for IPv4 multicast, false + * otherwise. + */ +static bool batadv_mcast_addr_is_ipv4(const u8 *addr) +{ + static const u8 prefix[] = {0x01, 0x00, 0x5E}; + + return memcmp(prefix, addr, sizeof(prefix)) == 0; +} + +/** + * batadv_mcast_addr_is_ipv6() - check if multicast MAC is IPv6 + * @addr: the MAC address to check + * + * Return: True, if MAC address is one reserved for IPv6 multicast, false + * otherwise. + */ +static bool batadv_mcast_addr_is_ipv6(const u8 *addr) +{ + static const u8 prefix[] = {0x33, 0x33}; + + return memcmp(prefix, addr, sizeof(prefix)) == 0; +} + +/** * batadv_mcast_mla_softif_get() - get softif multicast listeners + * @bat_priv: the bat priv with all the soft interface information * @dev: the device to collect multicast addresses from * @mcast_list: a list to put found addresses into * @@@ -155,12 -119,9 +155,12 @@@ * Return: -ENOMEM on memory allocation error or the number of * items added to the mcast_list otherwise. */ -static int batadv_mcast_mla_softif_get(struct net_device *dev, +static int batadv_mcast_mla_softif_get(struct batadv_priv *bat_priv, + struct net_device *dev, struct hlist_head *mcast_list) { + bool all_ipv4 = bat_priv->mcast.flags & BATADV_MCAST_WANT_ALL_IPV4; + bool all_ipv6 = bat_priv->mcast.flags & BATADV_MCAST_WANT_ALL_IPV6; struct net_device *bridge = batadv_mcast_get_bridge(dev); struct netdev_hw_addr *mc_list_entry; struct batadv_hw_addr *new; @@@ -168,12 -129,6 +168,12 @@@ netif_addr_lock_bh(bridge ? bridge : dev); netdev_for_each_mc_addr(mc_list_entry, bridge ? bridge : dev) { + if (all_ipv4 && batadv_mcast_addr_is_ipv4(mc_list_entry->addr)) + continue; + + if (all_ipv6 && batadv_mcast_addr_is_ipv6(mc_list_entry->addr)) + continue; + new = kmalloc(sizeof(*new), GFP_ATOMIC); if (!new) { ret = -ENOMEM; @@@ -238,7 -193,6 +238,7 @@@ static void batadv_mcast_mla_br_addr_cp /** * batadv_mcast_mla_bridge_get() - get bridged-in multicast listeners + * @bat_priv: the bat priv with all the soft interface information * @dev: a bridge slave whose bridge to collect multicast addresses from * @mcast_list: a list to put found addresses into * @@@ -250,13 -204,10 +250,13 @@@ * Return: -ENOMEM on memory allocation error or the number of * items added to the mcast_list otherwise. */ -static int batadv_mcast_mla_bridge_get(struct net_device *dev, +static int batadv_mcast_mla_bridge_get(struct batadv_priv *bat_priv, + struct net_device *dev, struct hlist_head *mcast_list) { struct list_head bridge_mcast_list = LIST_HEAD_INIT(bridge_mcast_list); + bool all_ipv4 = bat_priv->mcast.flags & BATADV_MCAST_WANT_ALL_IPV4; + bool all_ipv6 = bat_priv->mcast.flags & BATADV_MCAST_WANT_ALL_IPV6; struct br_ip_list *br_ip_entry, *tmp; struct batadv_hw_addr *new; u8 mcast_addr[ETH_ALEN]; @@@ -270,12 -221,6 +270,12 @@@ goto out; list_for_each_entry(br_ip_entry, &bridge_mcast_list, list) { + if (all_ipv4 && br_ip_entry->addr.proto == htons(ETH_P_IP)) + continue; + + if (all_ipv6 && br_ip_entry->addr.proto == htons(ETH_P_IPV6)) + continue; + batadv_mcast_mla_br_addr_cpy(mcast_addr, &br_ip_entry->addr); if (batadv_mcast_mla_is_duplicate(mcast_addr, mcast_list)) continue; @@@ -598,8 -543,8 +598,8 @@@ update bat_priv->mcast.enabled = true; } - return !(mcast_data.flags & - (BATADV_MCAST_WANT_ALL_IPV4 | BATADV_MCAST_WANT_ALL_IPV6)); + return !(mcast_data.flags & BATADV_MCAST_WANT_ALL_IPV4 && + mcast_data.flags & BATADV_MCAST_WANT_ALL_IPV6); } /** @@@ -623,11 -568,11 +623,11 @@@ static void __batadv_mcast_mla_update(s if (!batadv_mcast_mla_tvlv_update(bat_priv)) goto update; - ret = batadv_mcast_mla_softif_get(soft_iface, &mcast_list); + ret = batadv_mcast_mla_softif_get(bat_priv, soft_iface, &mcast_list); if (ret < 0) goto out; - ret = batadv_mcast_mla_bridge_get(soft_iface, &mcast_list); + ret = batadv_mcast_mla_bridge_get(bat_priv, soft_iface, &mcast_list); if (ret < 0) goto out; @@@ -1341,236 -1286,6 +1341,236 @@@ int batadv_mcast_flags_seq_print_text(s #endif /** + * batadv_mcast_mesh_info_put() - put multicast info into a netlink message + * @msg: buffer for the message + * @bat_priv: the bat priv with all the soft interface information + * + * Return: 0 or error code. + */ +int batadv_mcast_mesh_info_put(struct sk_buff *msg, + struct batadv_priv *bat_priv) +{ + u32 flags = bat_priv->mcast.flags; + u32 flags_priv = BATADV_NO_FLAGS; + + if (bat_priv->mcast.bridged) { + flags_priv |= BATADV_MCAST_FLAGS_BRIDGED; + + if (bat_priv->mcast.querier_ipv4.exists) + flags_priv |= BATADV_MCAST_FLAGS_QUERIER_IPV4_EXISTS; + if (bat_priv->mcast.querier_ipv6.exists) + flags_priv |= BATADV_MCAST_FLAGS_QUERIER_IPV6_EXISTS; + if (bat_priv->mcast.querier_ipv4.shadowing) + flags_priv |= BATADV_MCAST_FLAGS_QUERIER_IPV4_SHADOWING; + if (bat_priv->mcast.querier_ipv6.shadowing) + flags_priv |= BATADV_MCAST_FLAGS_QUERIER_IPV6_SHADOWING; + } + + if (nla_put_u32(msg, BATADV_ATTR_MCAST_FLAGS, flags) || + nla_put_u32(msg, BATADV_ATTR_MCAST_FLAGS_PRIV, flags_priv)) + return -EMSGSIZE; + + return 0; +} + +/** + * batadv_mcast_flags_dump_entry() - dump one entry of the multicast flags table + * to a netlink socket + * @msg: buffer for the message + * @portid: netlink port + * @seq: Sequence number of netlink message + * @orig_node: originator to dump the multicast flags of + * + * Return: 0 or error code. + */ +static int +batadv_mcast_flags_dump_entry(struct sk_buff *msg, u32 portid, u32 seq, + struct batadv_orig_node *orig_node) +{ + void *hdr; + + hdr = genlmsg_put(msg, portid, seq, &batadv_netlink_family, + NLM_F_MULTI, BATADV_CMD_GET_MCAST_FLAGS); + if (!hdr) + return -ENOBUFS; + + if (nla_put(msg, BATADV_ATTR_ORIG_ADDRESS, ETH_ALEN, + orig_node->orig)) { + genlmsg_cancel(msg, hdr); + return -EMSGSIZE; + } + + if (test_bit(BATADV_ORIG_CAPA_HAS_MCAST, + &orig_node->capabilities)) { + if (nla_put_u32(msg, BATADV_ATTR_MCAST_FLAGS, + orig_node->mcast_flags)) { + genlmsg_cancel(msg, hdr); + return -EMSGSIZE; + } + } + + genlmsg_end(msg, hdr); + return 0; +} + +/** + * batadv_mcast_flags_dump_bucket() - dump one bucket of the multicast flags + * table to a netlink socket + * @msg: buffer for the message + * @portid: netlink port + * @seq: Sequence number of netlink message + * @head: bucket to dump + * @idx_skip: How many entries to skip + * + * Return: 0 or error code. + */ +static int +batadv_mcast_flags_dump_bucket(struct sk_buff *msg, u32 portid, u32 seq, + struct hlist_head *head, long *idx_skip) +{ + struct batadv_orig_node *orig_node; + long idx = 0; + + rcu_read_lock(); + hlist_for_each_entry_rcu(orig_node, head, hash_entry) { + if (!test_bit(BATADV_ORIG_CAPA_HAS_MCAST, + &orig_node->capa_initialized)) + continue; + + if (idx < *idx_skip) + goto skip; + + if (batadv_mcast_flags_dump_entry(msg, portid, seq, + orig_node)) { + rcu_read_unlock(); + *idx_skip = idx; + + return -EMSGSIZE; + } + +skip: + idx++; + } + rcu_read_unlock(); + + return 0; +} + +/** + * __batadv_mcast_flags_dump() - dump multicast flags table to a netlink socket + * @msg: buffer for the message + * @portid: netlink port + * @seq: Sequence number of netlink message + * @bat_priv: the bat priv with all the soft interface information + * @bucket: current bucket to dump + * @idx: index in current bucket to the next entry to dump + * + * Return: 0 or error code. + */ +static int +__batadv_mcast_flags_dump(struct sk_buff *msg, u32 portid, u32 seq, + struct batadv_priv *bat_priv, long *bucket, long *idx) +{ + struct batadv_hashtable *hash = bat_priv->orig_hash; + long bucket_tmp = *bucket; + struct hlist_head *head; + long idx_tmp = *idx; + + while (bucket_tmp < hash->size) { + head = &hash->table[bucket_tmp]; + + if (batadv_mcast_flags_dump_bucket(msg, portid, seq, head, + &idx_tmp)) + break; + + bucket_tmp++; + idx_tmp = 0; + } + + *bucket = bucket_tmp; + *idx = idx_tmp; + + return msg->len; +} + +/** + * batadv_mcast_netlink_get_primary() - get primary interface from netlink + * callback + * @cb: netlink callback structure + * @primary_if: the primary interface pointer to return the result in + * + * Return: 0 or error code. + */ +static int +batadv_mcast_netlink_get_primary(struct netlink_callback *cb, + struct batadv_hard_iface **primary_if) +{ + struct batadv_hard_iface *hard_iface = NULL; + struct net *net = sock_net(cb->skb->sk); + struct net_device *soft_iface; + struct batadv_priv *bat_priv; + int ifindex; + int ret = 0; + + ifindex = batadv_netlink_get_ifindex(cb->nlh, BATADV_ATTR_MESH_IFINDEX); + if (!ifindex) + return -EINVAL; + + soft_iface = dev_get_by_index(net, ifindex); + if (!soft_iface || !batadv_softif_is_valid(soft_iface)) { + ret = -ENODEV; + goto out; + } + + bat_priv = netdev_priv(soft_iface); + + hard_iface = batadv_primary_if_get_selected(bat_priv); + if (!hard_iface || hard_iface->if_status != BATADV_IF_ACTIVE) { + ret = -ENOENT; + goto out; + } + +out: + if (soft_iface) + dev_put(soft_iface); + + if (!ret && primary_if) + *primary_if = hard_iface; + else + batadv_hardif_put(hard_iface); + + return ret; +} + +/** + * batadv_mcast_flags_dump() - dump multicast flags table to a netlink socket + * @msg: buffer for the message + * @cb: callback structure containing arguments + * + * Return: message length. + */ +int batadv_mcast_flags_dump(struct sk_buff *msg, struct netlink_callback *cb) +{ + struct batadv_hard_iface *primary_if = NULL; + int portid = NETLINK_CB(cb->skb).portid; + struct batadv_priv *bat_priv; + long *bucket = &cb->args[0]; + long *idx = &cb->args[1]; + int ret; + + ret = batadv_mcast_netlink_get_primary(cb, &primary_if); + if (ret) + return ret; + + bat_priv = netdev_priv(primary_if->soft_iface); + ret = __batadv_mcast_flags_dump(msg, portid, cb->nlh->nlmsg_seq, + bat_priv, bucket, idx); + + batadv_hardif_put(primary_if); + return ret; +} + +/** * batadv_mcast_free() - free the multicast optimizations structures * @bat_priv: the bat priv with all the soft interface information */ diff --combined net/batman-adv/routing.c index 289df027ecdd,e61dc1293bb5..cc3ed93a6d51 --- a/net/batman-adv/routing.c +++ b/net/batman-adv/routing.c @@@ -1,5 -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 * @@@ -759,6 -759,7 +759,7 @@@ free_skb /** * batadv_reroute_unicast_packet() - update the unicast header for re-routing * @bat_priv: the bat priv with all the soft interface information + * @skb: unicast packet to process * @unicast_packet: the unicast header to be updated * @dst_addr: the payload destination * @vid: VLAN identifier @@@ -770,7 -771,7 +771,7 @@@ * Return: true if the packet header has been updated, false otherwise */ static bool - batadv_reroute_unicast_packet(struct batadv_priv *bat_priv, + batadv_reroute_unicast_packet(struct batadv_priv *bat_priv, struct sk_buff *skb, struct batadv_unicast_packet *unicast_packet, u8 *dst_addr, unsigned short vid) { @@@ -799,8 -800,10 +800,10 @@@ } /* update the packet header */ + skb_postpull_rcsum(skb, unicast_packet, sizeof(*unicast_packet)); ether_addr_copy(unicast_packet->dest, orig_addr); unicast_packet->ttvn = orig_ttvn; + skb_postpush_rcsum(skb, unicast_packet, sizeof(*unicast_packet)); ret = true; out: @@@ -841,7 -844,7 +844,7 @@@ static bool batadv_check_unicast_ttvn(s * the packet to */ if (batadv_tt_local_client_is_roaming(bat_priv, ethhdr->h_dest, vid)) { - if (batadv_reroute_unicast_packet(bat_priv, unicast_packet, + if (batadv_reroute_unicast_packet(bat_priv, skb, unicast_packet, ethhdr->h_dest, vid)) batadv_dbg_ratelimited(BATADV_DBG_TT, bat_priv, @@@ -887,7 -890,7 +890,7 @@@ * destination can possibly be updated and forwarded towards the new * target host */ - if (batadv_reroute_unicast_packet(bat_priv, unicast_packet, + if (batadv_reroute_unicast_packet(bat_priv, skb, unicast_packet, ethhdr->h_dest, vid)) { batadv_dbg_ratelimited(BATADV_DBG_TT, bat_priv, "Rerouting unicast packet to %pM (dst=%pM): TTVN mismatch old_ttvn=%u new_ttvn=%u\n", @@@ -910,12 -913,14 +913,14 @@@ if (!primary_if) return false; + /* update the packet header */ + skb_postpull_rcsum(skb, unicast_packet, sizeof(*unicast_packet)); ether_addr_copy(unicast_packet->dest, primary_if->net_dev->dev_addr); + unicast_packet->ttvn = curr_ttvn; + skb_postpush_rcsum(skb, unicast_packet, sizeof(*unicast_packet)); batadv_hardif_put(primary_if); - unicast_packet->ttvn = curr_ttvn; - return true; } @@@ -968,14 -973,10 +973,10 @@@ int batadv_recv_unicast_packet(struct s struct batadv_orig_node *orig_node = NULL, *orig_node_gw = NULL; int check, hdr_size = sizeof(*unicast_packet); enum batadv_subtype subtype; - struct ethhdr *ethhdr; int ret = NET_RX_DROP; bool is4addr, is_gw; unicast_packet = (struct batadv_unicast_packet *)skb->data; - unicast_4addr_packet = (struct batadv_unicast_4addr_packet *)skb->data; - ethhdr = eth_hdr(skb); - is4addr = unicast_packet->packet_type == BATADV_UNICAST_4ADDR; /* the caller function should have already pulled 2 bytes */ if (is4addr) @@@ -995,12 -996,14 +996,14 @@@ if (!batadv_check_unicast_ttvn(bat_priv, skb, hdr_size)) goto free_skb; + unicast_packet = (struct batadv_unicast_packet *)skb->data; + /* packet for me */ if (batadv_is_my_mac(bat_priv, unicast_packet->dest)) { /* If this is a unicast packet from another backgone gw, * drop it. */ - orig_addr_gw = ethhdr->h_source; + orig_addr_gw = eth_hdr(skb)->h_source; orig_node_gw = batadv_orig_hash_find(bat_priv, orig_addr_gw); if (orig_node_gw) { is_gw = batadv_bla_is_backbone_gw(skb, orig_node_gw, @@@ -1015,6 -1018,8 +1018,8 @@@ } if (is4addr) { + unicast_4addr_packet = + (struct batadv_unicast_4addr_packet *)skb->data; subtype = unicast_4addr_packet->subtype; batadv_dat_inc_counter(bat_priv, subtype); diff --combined net/core/dev.c index d8887cc38e7b,12be20535714..f9c28f44286c --- a/net/core/dev.c +++ b/net/core/dev.c @@@ -2378,7 -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) { @@@ -3278,15 -3278,23 +3278,23 @@@ static inline int __dev_xmit_skb(struc #if IS_ENABLED(CONFIG_CGROUP_NET_PRIO) static void skb_update_prio(struct sk_buff *skb) { - struct netprio_map *map = rcu_dereference_bh(skb->dev->priomap); + const struct netprio_map *map; + const struct sock *sk; + unsigned int prioidx; - if (!skb->priority && skb->sk && map) { - unsigned int prioidx = - sock_cgroup_prioidx(&skb->sk->sk_cgrp_data); + if (skb->priority) + return; + map = rcu_dereference_bh(skb->dev->priomap); + if (!map) + return; + sk = skb_to_full_sk(skb); + if (!sk) + return; - if (prioidx < map->priomap_len) - skb->priority = map->priomap[prioidx]; - } + prioidx = sock_cgroup_prioidx(&sk->sk_cgrp_data); + + if (prioidx < map->priomap_len) + skb->priority = map->priomap[prioidx]; } #else #define skb_update_prio(skb) @@@ -4351,9 -4359,6 +4359,9 @@@ int netdev_rx_handler_register(struct n if (netdev_is_rx_handler_busy(dev)) return -EBUSY; + if (dev->priv_flags & IFF_NO_RX_HANDLER) + return -EINVAL; + /* Note: rx_handler_data must be set before rx_handler */ rcu_assign_pointer(dev->rx_handler_data, rx_handler_data); rcu_assign_pointer(dev->rx_handler, rx_handler); @@@ -7549,19 -7554,6 +7557,19 @@@ static netdev_features_t netdev_fix_fea } } + /* LRO/HW-GRO features cannot be combined with RX-FCS */ + if (features & NETIF_F_RXFCS) { + if (features & NETIF_F_LRO) { + netdev_dbg(dev, "Dropping LRO feature since RX-FCS is requested.\n"); + features &= ~NETIF_F_LRO; + } + + if (features & NETIF_F_GRO_HW) { + netdev_dbg(dev, "Dropping HW-GRO feature since RX-FCS is requested.\n"); + features &= ~NETIF_F_GRO_HW; + } + } + return features; } @@@ -8018,8 -8010,7 +8026,8 @@@ int register_netdev(struct net_device * { int err; - rtnl_lock(); + if (rtnl_lock_killable()) + return -EINTR; err = register_netdevice(dev); rtnl_unlock(); return err; @@@ -8162,9 -8153,8 +8170,9 @@@ 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) @@@ -8862,7 -8852,6 +8870,7 @@@ static void __net_exit netdev_exit(stru 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) @@@ -8963,7 -8952,6 +8971,7 @@@ static void __net_exit default_device_e static struct pernet_operations __net_initdata default_device_ops = { .exit = default_device_exit, .exit_batch = default_device_exit_batch, + .async = true, }; /* diff --combined net/core/devlink.c index d03b96f87c25,effd4848c2b4..9236e421bd62 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@@ -1798,7 -1798,7 +1798,7 @@@ send_done if (!nlh) { err = devlink_dpipe_send_and_alloc_skb(&skb, info); if (err) - goto err_skb_send_alloc; + return err; goto send_done; } @@@ -1807,7 -1807,6 +1807,6 @@@ nla_put_failure: err = -EMSGSIZE; err_table_put: - err_skb_send_alloc: genlmsg_cancel(skb, hdr); nlmsg_free(skb); return err; @@@ -2073,7 -2072,7 +2072,7 @@@ static int devlink_dpipe_entries_fill(s table->counters_enabled, &dump_ctx); if (err) - goto err_entries_dump; + return err; send_done: nlh = nlmsg_put(dump_ctx.skb, info->snd_portid, info->snd_seq, @@@ -2081,16 -2080,10 +2080,10 @@@ if (!nlh) { err = devlink_dpipe_send_and_alloc_skb(&dump_ctx.skb, info); if (err) - goto err_skb_send_alloc; + return err; goto send_done; } return genlmsg_reply(dump_ctx.skb, info); - - err_entries_dump: - err_skb_send_alloc: - genlmsg_cancel(dump_ctx.skb, dump_ctx.hdr); - nlmsg_free(dump_ctx.skb); - return err; } static int devlink_nl_cmd_dpipe_entries_get(struct sk_buff *skb, @@@ -2229,7 -2222,7 +2222,7 @@@ send_done if (!nlh) { err = devlink_dpipe_send_and_alloc_skb(&skb, info); if (err) - goto err_skb_send_alloc; + return err; goto send_done; } return genlmsg_reply(skb, info); @@@ -2237,7 -2230,6 +2230,6 @@@ nla_put_failure: err = -EMSGSIZE; err_table_put: - err_skb_send_alloc: genlmsg_cancel(skb, hdr); nlmsg_free(skb); return err; @@@ -2339,32 -2331,6 +2331,32 @@@ 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) { @@@ -2383,8 -2349,12 +2375,8 @@@ 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; @@@ -2744,22 -2714,22 +2736,22 @@@ static const struct genl_ops devlink_nl .cmd = DEVLINK_CMD_DPIPE_TABLE_GET, .doit = devlink_nl_cmd_dpipe_table_get, .policy = devlink_nl_policy, - .flags = GENL_ADMIN_PERM, .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK, + /* can be retrieved by unprivileged users */ }, { .cmd = DEVLINK_CMD_DPIPE_ENTRIES_GET, .doit = devlink_nl_cmd_dpipe_entries_get, .policy = devlink_nl_policy, - .flags = GENL_ADMIN_PERM, .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK, + /* can be retrieved by unprivileged users */ }, { .cmd = DEVLINK_CMD_DPIPE_HEADERS_GET, .doit = devlink_nl_cmd_dpipe_headers_get, .policy = devlink_nl_policy, - .flags = GENL_ADMIN_PERM, .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK, + /* can be retrieved by unprivileged users */ }, { .cmd = DEVLINK_CMD_DPIPE_TABLE_COUNTERS_SET, @@@ -2779,8 -2749,8 +2771,8 @@@ .cmd = DEVLINK_CMD_RESOURCE_DUMP, .doit = devlink_nl_cmd_resource_dump, .policy = devlink_nl_policy, - .flags = GENL_ADMIN_PERM, .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK, + /* can be retrieved by unprivileged users */ }, { .cmd = DEVLINK_CMD_RELOAD, @@@ -3174,6 -3144,7 +3166,6 @@@ EXPORT_SYMBOL_GPL(devlink_dpipe_table_u */ int devlink_resource_register(struct devlink *devlink, const char *resource_name, - bool top_hierarchy, u64 resource_size, u64 resource_id, u64 parent_resource_id, @@@ -3182,11 -3153,8 +3174,11 @@@ { struct devlink_resource *resource; struct list_head *resource_list; + bool top_hierarchy; int err = 0; + top_hierarchy = parent_resource_id == DEVLINK_RESOURCE_ID_PARENT_TOP; + mutex_lock(&devlink->lock); resource = devlink_resource_find(devlink, NULL, resource_id); if (resource) { diff --combined net/core/filter.c index c86f03fd9ea5,48aa7c7320db..00c711c5f1a2 --- a/net/core/filter.c +++ b/net/core/filter.c @@@ -1890,202 -1890,6 +1890,202 @@@ static const struct bpf_func_proto bpf_ .arg4_type = ARG_ANYTHING, }; +BPF_CALL_4(bpf_msg_redirect_map, struct sk_msg_buff *, msg, + struct bpf_map *, map, u32, key, u64, flags) +{ + /* If user passes invalid input drop the packet. */ + if (unlikely(flags)) + return SK_DROP; + + msg->key = key; + msg->flags = flags; + msg->map = map; + + return SK_PASS; +} + +struct sock *do_msg_redirect_map(struct sk_msg_buff *msg) +{ + struct sock *sk = NULL; + + if (msg->map) { + sk = __sock_map_lookup_elem(msg->map, msg->key); + + msg->key = 0; + msg->map = NULL; + } + + return sk; +} + +static const struct bpf_func_proto bpf_msg_redirect_map_proto = { + .func = bpf_msg_redirect_map, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_CONST_MAP_PTR, + .arg3_type = ARG_ANYTHING, + .arg4_type = ARG_ANYTHING, +}; + +BPF_CALL_2(bpf_msg_apply_bytes, struct sk_msg_buff *, msg, u32, bytes) +{ + msg->apply_bytes = bytes; + return 0; +} + +static const struct bpf_func_proto bpf_msg_apply_bytes_proto = { + .func = bpf_msg_apply_bytes, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_ANYTHING, +}; + +BPF_CALL_2(bpf_msg_cork_bytes, struct sk_msg_buff *, msg, u32, bytes) +{ + msg->cork_bytes = bytes; + return 0; +} + +static const struct bpf_func_proto bpf_msg_cork_bytes_proto = { + .func = bpf_msg_cork_bytes, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_ANYTHING, +}; + +BPF_CALL_4(bpf_msg_pull_data, + struct sk_msg_buff *, msg, u32, start, u32, end, u64, flags) +{ + unsigned int len = 0, offset = 0, copy = 0; + struct scatterlist *sg = msg->sg_data; + int first_sg, last_sg, i, shift; + unsigned char *p, *to, *from; + int bytes = end - start; + struct page *page; + + if (unlikely(flags || end <= start)) + return -EINVAL; + + /* First find the starting scatterlist element */ + i = msg->sg_start; + do { + len = sg[i].length; + offset += len; + if (start < offset + len) + break; + i++; + if (i == MAX_SKB_FRAGS) + i = 0; + } while (i != msg->sg_end); + + if (unlikely(start >= offset + len)) + return -EINVAL; + + if (!msg->sg_copy[i] && bytes <= len) + goto out; + + first_sg = i; + + /* At this point we need to linearize multiple scatterlist + * elements or a single shared page. Either way we need to + * copy into a linear buffer exclusively owned by BPF. Then + * place the buffer in the scatterlist and fixup the original + * entries by removing the entries now in the linear buffer + * and shifting the remaining entries. For now we do not try + * to copy partial entries to avoid complexity of running out + * of sg_entry slots. The downside is reading a single byte + * will copy the entire sg entry. + */ + do { + copy += sg[i].length; + i++; + if (i == MAX_SKB_FRAGS) + i = 0; + if (bytes < copy) + break; + } while (i != msg->sg_end); + last_sg = i; + + if (unlikely(copy < end - start)) + return -EINVAL; + + page = alloc_pages(__GFP_NOWARN | GFP_ATOMIC, get_order(copy)); + if (unlikely(!page)) + return -ENOMEM; + p = page_address(page); + offset = 0; + + i = first_sg; + do { + from = sg_virt(&sg[i]); + len = sg[i].length; + to = p + offset; + + memcpy(to, from, len); + offset += len; + sg[i].length = 0; + put_page(sg_page(&sg[i])); + + i++; + if (i == MAX_SKB_FRAGS) + i = 0; + } while (i != last_sg); + + sg[first_sg].length = copy; + sg_set_page(&sg[first_sg], page, copy, 0); + + /* To repair sg ring we need to shift entries. If we only + * had a single entry though we can just replace it and + * be done. Otherwise walk the ring and shift the entries. + */ + shift = last_sg - first_sg - 1; + if (!shift) + goto out; + + i = first_sg + 1; + do { + int move_from; + + if (i + shift >= MAX_SKB_FRAGS) + move_from = i + shift - MAX_SKB_FRAGS; + else + move_from = i + shift; + + if (move_from == msg->sg_end) + break; + + sg[i] = sg[move_from]; + sg[move_from].length = 0; + sg[move_from].page_link = 0; + sg[move_from].offset = 0; + + i++; + if (i == MAX_SKB_FRAGS) + i = 0; + } while (1); + msg->sg_end -= shift; + if (msg->sg_end < 0) + msg->sg_end += MAX_SKB_FRAGS; +out: + msg->data = sg_virt(&sg[i]) + start - offset; + msg->data_end = msg->data + bytes; + + return 0; +} + +static const struct bpf_func_proto bpf_msg_pull_data_proto = { + .func = bpf_msg_pull_data, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_ANYTHING, + .arg3_type = ARG_ANYTHING, + .arg4_type = ARG_ANYTHING, +}; + BPF_CALL_1(bpf_get_cgroup_classid, const struct sk_buff *, skb) { return task_get_classid(skb); @@@ -2283,6 -2087,10 +2283,10 @@@ static int bpf_skb_proto_4_to_6(struct u32 off = skb_mac_header_len(skb); int ret; + /* SCTP uses GSO_BY_FRAGS, thus cannot adjust it. */ + if (skb_is_gso(skb) && unlikely(skb_is_gso_sctp(skb))) + return -ENOTSUPP; + ret = skb_cow(skb, len_diff); if (unlikely(ret < 0)) return ret; @@@ -2292,19 -2100,21 +2296,21 @@@ return ret; if (skb_is_gso(skb)) { + struct skb_shared_info *shinfo = skb_shinfo(skb); + /* SKB_GSO_TCPV4 needs to be changed into * SKB_GSO_TCPV6. */ - if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4) { - skb_shinfo(skb)->gso_type &= ~SKB_GSO_TCPV4; - skb_shinfo(skb)->gso_type |= SKB_GSO_TCPV6; + if (shinfo->gso_type & SKB_GSO_TCPV4) { + shinfo->gso_type &= ~SKB_GSO_TCPV4; + shinfo->gso_type |= SKB_GSO_TCPV6; } /* Due to IPv6 header, MSS needs to be downgraded. */ - skb_shinfo(skb)->gso_size -= len_diff; + skb_decrease_gso_size(shinfo, len_diff); /* Header must be checked, and gso_segs recomputed. */ - skb_shinfo(skb)->gso_type |= SKB_GSO_DODGY; - skb_shinfo(skb)->gso_segs = 0; + shinfo->gso_type |= SKB_GSO_DODGY; + shinfo->gso_segs = 0; } skb->protocol = htons(ETH_P_IPV6); @@@ -2319,6 -2129,10 +2325,10 @@@ static int bpf_skb_proto_6_to_4(struct u32 off = skb_mac_header_len(skb); int ret; + /* SCTP uses GSO_BY_FRAGS, thus cannot adjust it. */ + if (skb_is_gso(skb) && unlikely(skb_is_gso_sctp(skb))) + return -ENOTSUPP; + ret = skb_unclone(skb, GFP_ATOMIC); if (unlikely(ret < 0)) return ret; @@@ -2328,19 -2142,21 +2338,21 @@@ return ret; if (skb_is_gso(skb)) { + struct skb_shared_info *shinfo = skb_shinfo(skb); + /* SKB_GSO_TCPV6 needs to be changed into * SKB_GSO_TCPV4. */ - if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6) { - skb_shinfo(skb)->gso_type &= ~SKB_GSO_TCPV6; - skb_shinfo(skb)->gso_type |= SKB_GSO_TCPV4; + if (shinfo->gso_type & SKB_GSO_TCPV6) { + shinfo->gso_type &= ~SKB_GSO_TCPV6; + shinfo->gso_type |= SKB_GSO_TCPV4; } /* Due to IPv4 header, MSS can be upgraded. */ - skb_shinfo(skb)->gso_size += len_diff; + skb_increase_gso_size(shinfo, len_diff); /* Header must be checked, and gso_segs recomputed. */ - skb_shinfo(skb)->gso_type |= SKB_GSO_DODGY; - skb_shinfo(skb)->gso_segs = 0; + shinfo->gso_type |= SKB_GSO_DODGY; + shinfo->gso_segs = 0; } skb->protocol = htons(ETH_P_IP); @@@ -2439,6 -2255,10 +2451,10 @@@ static int bpf_skb_net_grow(struct sk_b u32 off = skb_mac_header_len(skb) + bpf_skb_net_base_len(skb); int ret; + /* SCTP uses GSO_BY_FRAGS, thus cannot adjust it. */ + if (skb_is_gso(skb) && unlikely(skb_is_gso_sctp(skb))) + return -ENOTSUPP; + ret = skb_cow(skb, len_diff); if (unlikely(ret < 0)) return ret; @@@ -2448,11 -2268,13 +2464,13 @@@ return ret; if (skb_is_gso(skb)) { + struct skb_shared_info *shinfo = skb_shinfo(skb); + /* Due to header grow, MSS needs to be downgraded. */ - skb_shinfo(skb)->gso_size -= len_diff; + skb_decrease_gso_size(shinfo, len_diff); /* Header must be checked, and gso_segs recomputed. */ - skb_shinfo(skb)->gso_type |= SKB_GSO_DODGY; - skb_shinfo(skb)->gso_segs = 0; + shinfo->gso_type |= SKB_GSO_DODGY; + shinfo->gso_segs = 0; } return 0; @@@ -2463,6 -2285,10 +2481,10 @@@ static int bpf_skb_net_shrink(struct sk u32 off = skb_mac_header_len(skb) + bpf_skb_net_base_len(skb); int ret; + /* SCTP uses GSO_BY_FRAGS, thus cannot adjust it. */ + if (skb_is_gso(skb) && unlikely(skb_is_gso_sctp(skb))) + return -ENOTSUPP; + ret = skb_unclone(skb, GFP_ATOMIC); if (unlikely(ret < 0)) return ret; @@@ -2472,11 -2298,13 +2494,13 @@@ return ret; if (skb_is_gso(skb)) { + struct skb_shared_info *shinfo = skb_shinfo(skb); + /* Due to header shrink, MSS can be upgraded. */ - skb_shinfo(skb)->gso_size += len_diff; + skb_increase_gso_size(shinfo, len_diff); /* Header must be checked, and gso_segs recomputed. */ - skb_shinfo(skb)->gso_type |= SKB_GSO_DODGY; - skb_shinfo(skb)->gso_segs = 0; + shinfo->gso_type |= SKB_GSO_DODGY; + shinfo->gso_segs = 0; } return 0; @@@ -3027,8 -2855,7 +3051,8 @@@ bool bpf_helper_changes_pkt_data(void * func == bpf_l3_csum_replace || func == bpf_l4_csum_replace || func == bpf_xdp_adjust_head || - func == bpf_xdp_adjust_meta) + func == bpf_xdp_adjust_meta || + func == bpf_msg_pull_data) return true; return false; @@@ -3188,7 -3015,7 +3212,7 @@@ BPF_CALL_4(bpf_skb_set_tunnel_key, stru 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) { @@@ -3222,8 -3049,6 +3246,8 @@@ 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; @@@ -3788,22 -3613,6 +3812,22 @@@ static const struct bpf_func_proto } } +static const struct bpf_func_proto *sk_msg_func_proto(enum bpf_func_id func_id) +{ + switch (func_id) { + case BPF_FUNC_msg_redirect_map: + return &bpf_msg_redirect_map_proto; + case BPF_FUNC_msg_apply_bytes: + return &bpf_msg_apply_bytes_proto; + case BPF_FUNC_msg_cork_bytes: + return &bpf_msg_cork_bytes_proto; + case BPF_FUNC_msg_pull_data: + return &bpf_msg_pull_data_proto; + default: + return bpf_base_func_proto(func_id); + } +} + static const struct bpf_func_proto *sk_skb_func_proto(enum bpf_func_id func_id) { switch (func_id) { @@@ -4193,32 -4002,6 +4217,32 @@@ static bool sk_skb_is_valid_access(int return bpf_skb_is_valid_access(off, size, type, info); } +static bool sk_msg_is_valid_access(int off, int size, + enum bpf_access_type type, + struct bpf_insn_access_aux *info) +{ + if (type == BPF_WRITE) + return false; + + switch (off) { + case offsetof(struct sk_msg_md, data): + info->reg_type = PTR_TO_PACKET; + break; + case offsetof(struct sk_msg_md, data_end): + info->reg_type = PTR_TO_PACKET_END; + break; + } + + if (off < 0 || off >= sizeof(struct sk_msg_md)) + return false; + if (off % size != 0) + return false; + if (size != sizeof(__u64)) + return false; + + return true; +} + static u32 bpf_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, @@@ -5017,29 -4800,6 +5041,29 @@@ static u32 sk_skb_convert_ctx_access(en return insn - insn_buf; } +static u32 sk_msg_convert_ctx_access(enum bpf_access_type type, + const struct bpf_insn *si, + struct bpf_insn *insn_buf, + struct bpf_prog *prog, u32 *target_size) +{ + struct bpf_insn *insn = insn_buf; + + switch (si->off) { + case offsetof(struct sk_msg_md, data): + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_msg_buff, data), + si->dst_reg, si->src_reg, + offsetof(struct sk_msg_buff, data)); + break; + case offsetof(struct sk_msg_md, data_end): + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_msg_buff, data_end), + si->dst_reg, si->src_reg, + offsetof(struct sk_msg_buff, data_end)); + break; + } + + return insn - insn_buf; +} + const struct bpf_verifier_ops sk_filter_verifier_ops = { .get_func_proto = sk_filter_func_proto, .is_valid_access = sk_filter_is_valid_access, @@@ -5130,15 -4890,6 +5154,15 @@@ const struct bpf_verifier_ops sk_skb_ve const struct bpf_prog_ops sk_skb_prog_ops = { }; +const struct bpf_verifier_ops sk_msg_verifier_ops = { + .get_func_proto = sk_msg_func_proto, + .is_valid_access = sk_msg_is_valid_access, + .convert_ctx_access = sk_msg_convert_ctx_access, +}; + +const struct bpf_prog_ops sk_msg_prog_ops = { +}; + int sk_detach_filter(struct sock *sk) { int ret = -ENOENT; diff --combined net/core/skbuff.c index 715c13495ba6,1e7acdc30732..46cb22215ff4 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@@ -77,8 -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 +890,7 @@@ struct sk_buff *skb_morph(struct sk_buf } 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; @@@ -919,16 -919,14 +919,16 @@@ 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) { @@@ -4181,7 -4179,7 +4181,7 @@@ int sock_queue_err_skb(struct sock *sk skb_queue_tail(&sk->sk_error_queue, skb); if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_data_ready(sk); + sk->sk_error_report(sk); return 0; } EXPORT_SYMBOL(sock_queue_err_skb); @@@ -4906,7 -4904,7 +4906,7 @@@ static unsigned int skb_gso_transport_s thlen += inner_tcp_hdrlen(skb); } else if (likely(shinfo->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6))) { thlen = tcp_hdrlen(skb); - } else if (unlikely(shinfo->gso_type & SKB_GSO_SCTP)) { + } else if (unlikely(skb_is_gso_sctp(skb))) { thlen = sizeof(struct sctphdr); } /* UFO sets gso_size to the size of the fragmentation @@@ -5022,13 -5020,16 +5022,16 @@@ EXPORT_SYMBOL_GPL(skb_gso_validate_mac_ static struct sk_buff *skb_reorder_vlan_header(struct sk_buff *skb) { + int mac_len; + if (skb_cow(skb, skb_headroom(skb)) < 0) { kfree_skb(skb); return NULL; } - memmove(skb->data - ETH_HLEN, skb->data - skb->mac_len - VLAN_HLEN, - 2 * ETH_ALEN); + mac_len = skb->data - skb_mac_header(skb); + memmove(skb_mac_header(skb) + VLAN_HLEN, skb_mac_header(skb), + mac_len - VLAN_HLEN - ETH_TLEN); skb->mac_header += VLAN_HLEN; return skb; } diff --combined net/core/sock.c index f704324d1219,85b0b64e7f9d..e689496dfd8a --- a/net/core/sock.c +++ b/net/core/sock.c @@@ -1049,18 -1049,16 +1049,18 @@@ 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_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); + } + if (!ret) { + if (val < 0 || val > 1) + ret = -EINVAL; + else + sock_valbool_flag(sk, SOCK_ZEROCOPY, valbool); + } break; default: @@@ -1276,8 -1274,7 +1276,8 @@@ int sock_getsockopt(struct socket *sock { 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; @@@ -1776,7 -1773,7 +1776,7 @@@ void sk_setup_caps(struct sock *sk, str 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; @@@ -2237,67 -2234,6 +2237,67 @@@ bool sk_page_frag_refill(struct sock *s } EXPORT_SYMBOL(sk_page_frag_refill); +int sk_alloc_sg(struct sock *sk, int len, struct scatterlist *sg, + int sg_start, int *sg_curr_index, unsigned int *sg_curr_size, + int first_coalesce) +{ + int sg_curr = *sg_curr_index, use = 0, rc = 0; + unsigned int size = *sg_curr_size; + struct page_frag *pfrag; + struct scatterlist *sge; + + len -= size; + pfrag = sk_page_frag(sk); + + while (len > 0) { + unsigned int orig_offset; + + if (!sk_page_frag_refill(sk, pfrag)) { + rc = -ENOMEM; + goto out; + } + + use = min_t(int, len, pfrag->size - pfrag->offset); + + if (!sk_wmem_schedule(sk, use)) { + rc = -ENOMEM; + goto out; + } + + sk_mem_charge(sk, use); + size += use; + orig_offset = pfrag->offset; + pfrag->offset += use; + + sge = sg + sg_curr - 1; + if (sg_curr > first_coalesce && sg_page(sg) == pfrag->page && + sg->offset + sg->length == orig_offset) { + sg->length += use; + } else { + sge = sg + sg_curr; + sg_unmark_end(sge); + sg_set_page(sge, pfrag->page, use, orig_offset); + get_page(pfrag->page); + sg_curr++; + + if (sg_curr == MAX_SKB_FRAGS) + sg_curr = 0; + + if (sg_curr == sg_start) { + rc = -ENOSPC; + break; + } + } + + len -= use; + } +out: + *sg_curr_size = size; + *sg_curr_index = sg_curr; + return rc; +} +EXPORT_SYMBOL(sk_alloc_sg); + static void __lock_sock(struct sock *sk) __releases(&sk->sk_lock.slock) __acquires(&sk->sk_lock.slock) @@@ -2561,7 -2497,7 +2561,7 @@@ int sock_no_accept(struct socket *sock EXPORT_SYMBOL(sock_no_accept); int sock_no_getname(struct socket *sock, struct sockaddr *saddr, - int *len, int peer) + int peer) { return -EOPNOTSUPP; } @@@ -3175,7 -3111,6 +3175,7 @@@ static void __net_exit sock_inuse_exit_ 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) @@@ -3326,6 -3261,27 +3326,27 @@@ void proto_unregister(struct proto *pro } EXPORT_SYMBOL(proto_unregister); + int sock_load_diag_module(int family, int protocol) + { + if (!protocol) { + if (!sock_is_registered(family)) + return -ENOENT; + + return request_module("net-pf-%d-proto-%d-type-%d", PF_NETLINK, + NETLINK_SOCK_DIAG, family); + } + + #ifdef CONFIG_INET + if (family == AF_INET && + !rcu_access_pointer(inet_protos[protocol])) + return -ENOENT; + #endif + + return request_module("net-pf-%d-proto-%d-type-%d-%d", PF_NETLINK, + NETLINK_SOCK_DIAG, family, protocol); + } + EXPORT_SYMBOL(sock_load_diag_module); + #ifdef CONFIG_PROC_FS static void *proto_seq_start(struct seq_file *seq, loff_t *pos) __acquires(proto_list_mutex) @@@ -3449,7 -3405,6 +3470,7 @@@ static __net_exit void proto_exit_net(s 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 --combined net/core/sock_diag.c index aee5642affd9,c37b5be7c5e4..a3392a8f9276 --- a/net/core/sock_diag.c +++ b/net/core/sock_diag.c @@@ -220,8 -220,7 +220,7 @@@ static int __sock_diag_cmd(struct sk_bu return -EINVAL; if (sock_diag_handlers[req->sdiag_family] == NULL) - request_module("net-pf-%d-proto-%d-type-%d", PF_NETLINK, - NETLINK_SOCK_DIAG, req->sdiag_family); + sock_load_diag_module(req->sdiag_family, 0); mutex_lock(&sock_diag_table_mutex); hndl = sock_diag_handlers[req->sdiag_family]; @@@ -247,8 -246,7 +246,7 @@@ static int sock_diag_rcv_msg(struct sk_ case TCPDIAG_GETSOCK: case DCCPDIAG_GETSOCK: if (inet_rcv_compat == NULL) - request_module("net-pf-%d-proto-%d-type-%d", PF_NETLINK, - NETLINK_SOCK_DIAG, AF_INET); + sock_load_diag_module(AF_INET, 0); mutex_lock(&sock_diag_table_mutex); if (inet_rcv_compat != NULL) @@@ -281,14 -279,12 +279,12 @@@ static int sock_diag_bind(struct net *n case SKNLGRP_INET_TCP_DESTROY: case SKNLGRP_INET_UDP_DESTROY: if (!sock_diag_handlers[AF_INET]) - request_module("net-pf-%d-proto-%d-type-%d", PF_NETLINK, - NETLINK_SOCK_DIAG, AF_INET); + sock_load_diag_module(AF_INET, 0); break; case SKNLGRP_INET6_TCP_DESTROY: case SKNLGRP_INET6_UDP_DESTROY: if (!sock_diag_handlers[AF_INET6]) - request_module("net-pf-%d-proto-%d-type-%d", PF_NETLINK, - NETLINK_SOCK_DIAG, AF_INET6); + sock_load_diag_module(AF_INET6, 0); break; } return 0; @@@ -328,7 -324,6 +324,7 @@@ static void __net_exit diag_net_exit(st 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 --combined net/ieee802154/6lowpan/core.c index e4f305320519,e9f0489e4229..275449b0d633 --- a/net/ieee802154/6lowpan/core.c +++ b/net/ieee802154/6lowpan/core.c @@@ -104,7 -104,6 +104,7 @@@ static void lowpan_setup(struct net_dev /* 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; @@@ -207,9 -206,13 +207,13 @@@ static inline void lowpan_netlink_fini( static int lowpan_device_event(struct notifier_block *unused, unsigned long event, void *ptr) { - struct net_device *wdev = netdev_notifier_info_to_dev(ptr); + struct net_device *ndev = netdev_notifier_info_to_dev(ptr); + struct wpan_dev *wpan_dev; - if (wdev->type != ARPHRD_IEEE802154) + if (ndev->type != ARPHRD_IEEE802154) + return NOTIFY_DONE; + wpan_dev = ndev->ieee802154_ptr; + if (!wpan_dev) return NOTIFY_DONE; switch (event) { @@@ -218,8 -221,8 +222,8 @@@ * also delete possible lowpan interfaces which belongs * to the wpan interface. */ - if (wdev->ieee802154_ptr->lowpan_dev) - lowpan_dellink(wdev->ieee802154_ptr->lowpan_dev, NULL); + if (wpan_dev->lowpan_dev) + lowpan_dellink(wpan_dev->lowpan_dev, NULL); break; default: return NOTIFY_DONE; diff --combined net/ipv4/route.c index e74ee837b300,299e247b2032..4ac5728689f5 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@@ -418,7 -418,6 +418,7 @@@ static void __net_exit ip_rt_do_proc_ex 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) @@@ -635,6 -634,7 +635,7 @@@ static inline u32 fnhe_hashfun(__be32 d static void fill_route_from_fnhe(struct rtable *rt, struct fib_nh_exception *fnhe) { rt->rt_pmtu = fnhe->fnhe_pmtu; + rt->rt_mtu_locked = fnhe->fnhe_mtu_locked; rt->dst.expires = fnhe->fnhe_expires; if (fnhe->fnhe_gw) { @@@ -645,7 -645,7 +646,7 @@@ } static void update_or_create_fnhe(struct fib_nh *nh, __be32 daddr, __be32 gw, - u32 pmtu, unsigned long expires) + u32 pmtu, bool lock, unsigned long expires) { struct fnhe_hash_bucket *hash; struct fib_nh_exception *fnhe; @@@ -682,8 -682,10 +683,10 @@@ fnhe->fnhe_genid = genid; if (gw) fnhe->fnhe_gw = gw; - if (pmtu) + if (pmtu) { fnhe->fnhe_pmtu = pmtu; + fnhe->fnhe_mtu_locked = lock; + } fnhe->fnhe_expires = max(1UL, expires); /* Update all cached dsts too */ rt = rcu_dereference(fnhe->fnhe_rth_input); @@@ -707,6 -709,7 +710,7 @@@ fnhe->fnhe_daddr = daddr; fnhe->fnhe_gw = gw; fnhe->fnhe_pmtu = pmtu; + fnhe->fnhe_mtu_locked = lock; fnhe->fnhe_expires = expires; /* Exception created; mark the cached routes for the nexthop @@@ -788,7 -791,8 +792,8 @@@ static void __ip_do_redirect(struct rta struct fib_nh *nh = &FIB_RES_NH(res); update_or_create_fnhe(nh, fl4->daddr, new_gw, - 0, jiffies + ip_rt_gc_timeout); + 0, false, + jiffies + ip_rt_gc_timeout); } if (kill_route) rt->dst.obsolete = DST_OBSOLETE_KILL; @@@ -1010,15 -1014,18 +1015,18 @@@ static void __ip_rt_update_pmtu(struct { struct dst_entry *dst = &rt->dst; struct fib_result res; + bool lock = false; - if (dst_metric_locked(dst, RTAX_MTU)) + if (ip_mtu_locked(dst)) return; if (ipv4_mtu(dst) < mtu) return; - if (mtu < ip_rt_min_pmtu) + if (mtu < ip_rt_min_pmtu) { + lock = true; mtu = ip_rt_min_pmtu; + } if (rt->rt_pmtu == mtu && time_before(jiffies, dst->expires - ip_rt_mtu_expires / 2)) @@@ -1028,7 -1035,7 +1036,7 @@@ if (fib_lookup(dev_net(dst->dev), fl4, &res, 0) == 0) { struct fib_nh *nh = &FIB_RES_NH(res); - update_or_create_fnhe(nh, fl4->daddr, 0, mtu, + update_or_create_fnhe(nh, fl4->daddr, 0, mtu, lock, jiffies + ip_rt_mtu_expires); } rcu_read_unlock(); @@@ -1281,7 -1288,7 +1289,7 @@@ static unsigned int ipv4_mtu(const stru mtu = READ_ONCE(dst->dev->mtu); - if (unlikely(dst_metric_locked(dst, RTAX_MTU))) { + if (unlikely(ip_mtu_locked(dst))) { if (rt->rt_uses_gateway && mtu > 576) mtu = 576; } @@@ -1394,7 -1401,7 +1402,7 @@@ struct uncached_list static DEFINE_PER_CPU_ALIGNED(struct uncached_list, rt_uncached_list); - static void rt_add_uncached_list(struct rtable *rt) + void rt_add_uncached_list(struct rtable *rt) { struct uncached_list *ul = raw_cpu_ptr(&rt_uncached_list); @@@ -1405,14 -1412,8 +1413,8 @@@ spin_unlock_bh(&ul->lock); } - static void ipv4_dst_destroy(struct dst_entry *dst) + void rt_del_uncached_list(struct rtable *rt) { - struct dst_metrics *p = (struct dst_metrics *)DST_METRICS_PTR(dst); - struct rtable *rt = (struct rtable *) dst; - - if (p != &dst_default_metrics && refcount_dec_and_test(&p->refcnt)) - kfree(p); - if (!list_empty(&rt->rt_uncached)) { struct uncached_list *ul = rt->rt_uncached_list; @@@ -1422,6 -1423,17 +1424,17 @@@ } } + static void ipv4_dst_destroy(struct dst_entry *dst) + { + struct dst_metrics *p = (struct dst_metrics *)DST_METRICS_PTR(dst); + struct rtable *rt = (struct rtable *)dst; + + if (p != &dst_default_metrics && refcount_dec_and_test(&p->refcnt)) + kfree(p); + + rt_del_uncached_list(rt); + } + void rt_flush_dev(struct net_device *dev) { struct net *net = dev_net(dev); @@@ -1517,8 -1529,10 +1530,9 @@@ struct rtable *rt_dst_alloc(struct net_ rt->rt_is_input = 0; rt->rt_iif = 0; rt->rt_pmtu = 0; + rt->rt_mtu_locked = 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; @@@ -1654,6 -1668,19 +1668,6 @@@ static void ip_del_fnhe(struct fib_nh * 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, @@@ -1736,13 -1763,15 +1750,13 @@@ 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; @@@ -1758,45 -1787,44 +1772,45 @@@ static void ip_multipath_l3_keys(const 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; @@@ -1820,20 -1848,15 +1834,20 @@@ /* 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; @@@ -1849,17 -1872,17 +1863,17 @@@ 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); } @@@ -1885,14 -1908,13 +1899,14 @@@ static int ip_route_input_slow(struct s 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. */ @@@ -1951,10 -1973,6 +1965,10 @@@ 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)) @@@ -1980,7 -1998,7 +1994,7 @@@ 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: @@@ -2022,6 -2040,8 +2036,6 @@@ 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) { @@@ -2250,6 -2270,8 +2264,6 @@@ 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); @@@ -2271,7 -2293,7 +2285,7 @@@ } rt_set_nexthop(rth, fl4->daddr, res, fnhe, fi, type, 0, do_cache); - set_lwt_redirect(rth); + lwtunnel_set_redirect(&rth->dst); return rth; } @@@ -2533,6 -2555,7 +2547,7 @@@ struct dst_entry *ipv4_blackhole_route( rt->rt_is_input = ort->rt_is_input; rt->rt_iif = ort->rt_iif; rt->rt_pmtu = ort->rt_pmtu; + rt->rt_mtu_locked = ort->rt_mtu_locked; rt->rt_genid = rt_genid_ipv4(net); rt->rt_flags = ort->rt_flags; @@@ -2635,6 -2658,8 +2650,8 @@@ static int rt_fill_info(struct net *net memcpy(metrics, dst_metrics_ptr(&rt->dst), sizeof(metrics)); if (rt->rt_pmtu && expires) metrics[RTAX_MTU - 1] = rt->rt_pmtu; + if (rt->rt_mtu_locked && expires) + metrics[RTAX_LOCK - 1] |= BIT(RTAX_MTU); if (rtnetlink_put_metrics(skb, metrics) < 0) goto nla_put_failure; @@@ -2779,7 -2804,7 +2796,7 @@@ static int inet_rtm_getroute(struct sk_ 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) { @@@ -3000,7 -3025,6 +3017,7 @@@ static __net_exit void sysctl_route_net static __net_initdata struct pernet_operations sysctl_route_ops = { .init = sysctl_route_net_init, .exit = sysctl_route_net_exit, + .async = true, }; #endif @@@ -3014,7 -3038,6 +3031,7 @@@ static __net_init int rt_genid_init(str 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) @@@ -3040,7 -3063,6 +3057,7 @@@ static void __net_exit ipv4_inetpeer_ex 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 --combined net/ipv4/tcp.c index d763fae1b574,8b8059b7af4d..0c31be306572 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@@ -453,7 -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); @@@ -898,7 -897,7 +898,7 @@@ static unsigned int tcp_xmit_size_goal( 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 */ @@@ -994,9 -993,7 +994,9 @@@ new_segment get_page(page); skb_fill_page_desc(skb, i, page, offset, copy); } - skb_shinfo(skb)->tx_flags |= SKBTX_SHARED_FRAG; + + if (!(flags & MSG_NO_SHARED_FRAGS)) + skb_shinfo(skb)->tx_flags |= SKBTX_SHARED_FRAG; skb->len += copy; skb->data_len += copy; @@@ -1065,7 -1062,8 +1065,7 @@@ 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? */ @@@ -1104,11 -1102,27 +1104,11 @@@ static int linear_payload_sz(bool first 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) @@@ -1173,7 -1187,7 +1173,7 @@@ int tcp_sendmsg_locked(struct sock *sk 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; @@@ -1191,7 -1205,7 +1191,7 @@@ 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; } @@@ -1254,12 -1268,18 +1254,12 @@@ 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; @@@ -1277,17 -1297,22 +1277,17 @@@ 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 @@@ -1318,7 -1343,7 +1318,7 @@@ 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; } @@@ -1371,7 -1396,7 +1371,7 @@@ 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)) { @@@ -3033,8 -3058,8 +3033,8 @@@ struct sk_buff *tcp_get_timestamping_op 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); + 5 * nla_total_size(sizeof(u32)) + + 3 * nla_total_size(sizeof(u8)), GFP_ATOMIC); if (!stats) return NULL; @@@ -3063,10 -3088,6 +3063,10 @@@ 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_SND_SSTHRESH, tp->snd_ssthresh); + + 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; } @@@ -3545,6 -3566,7 +3545,7 @@@ int tcp_abort(struct sock *sk, int err bh_unlock_sock(sk); local_bh_enable(); + tcp_write_queue_purge(sk); release_sock(sk); return 0; } diff --combined net/ipv4/xfrm4_policy.c index 0c752dc3f93b,fbebda67ac1b..6c76a757fa4a --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@@ -100,7 -100,10 +100,9 @@@ static int xfrm4_fill_dst(struct xfrm_d 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_mtu_locked = rt->rt_mtu_locked; - xdst->u.rt.rt_table_id = rt->rt_table_id; INIT_LIST_HEAD(&xdst->u.rt.rt_uncached); + rt_add_uncached_list(&xdst->u.rt); return 0; } @@@ -240,7 -243,8 +242,8 @@@ static void xfrm4_dst_destroy(struct ds struct xfrm_dst *xdst = (struct xfrm_dst *)dst; dst_destroy_metrics_generic(dst); - + if (xdst->u.rt.rt_uncached_list) + rt_del_uncached_list(&xdst->u.rt); xfrm_dst_destroy(xdst); } @@@ -364,7 -368,6 +367,7 @@@ static void __net_exit xfrm4_net_exit(s 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) @@@ -379,3 -382,4 +382,3 @@@ void __init xfrm4_init(void xfrm4_protocol_init(); register_pernet_subsys(&xfrm4_net_ops); } - diff --combined net/ipv6/datagram.c index b27333d7b099,a9f7eca0b6a3..88bc2ef7c7a8 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@@ -146,10 -146,12 +146,12 @@@ int __ip6_datagram_connect(struct sock struct sockaddr_in6 *usin = (struct sockaddr_in6 *) uaddr; struct inet_sock *inet = inet_sk(sk); struct ipv6_pinfo *np = inet6_sk(sk); - struct in6_addr *daddr; + struct in6_addr *daddr, old_daddr; + __be32 fl6_flowlabel = 0; + __be32 old_fl6_flowlabel; + __be16 old_dport; int addr_type; int err; - __be32 fl6_flowlabel = 0; if (usin->sin6_family == AF_INET) { if (__ipv6_only_sock(sk)) @@@ -238,9 -240,13 +240,13 @@@ ipv4_connected } } + /* save the current peer information before updating it */ + old_daddr = sk->sk_v6_daddr; + old_fl6_flowlabel = np->flow_label; + old_dport = inet->inet_dport; + sk->sk_v6_daddr = *daddr; np->flow_label = fl6_flowlabel; - inet->inet_dport = usin->sin6_port; /* @@@ -250,11 -256,12 +256,12 @@@ err = ip6_datagram_dst_update(sk, true); if (err) { - /* Reset daddr and dport so that udp_v6_early_demux() - * fails to find this socket + /* Restore the socket peer info, to keep it consistent with + * the old socket state */ - memset(&sk->sk_v6_daddr, 0, sizeof(sk->sk_v6_daddr)); - inet->inet_dport = 0; + sk->sk_v6_daddr = old_daddr; + np->flow_label = old_fl6_flowlabel; + inet->inet_dport = old_dport; goto out; } @@@ -801,9 -808,8 +808,9 @@@ int ip6_datagram_send_ctl(struct net *n if (addr_type != IPV6_ADDR_ANY) { int strict = __ipv6_addr_src_scope(addr_type) <= IPV6_ADDR_SCOPE_LINKLOCAL; if (!(inet_sk(sk)->freebind || inet_sk(sk)->transparent) && - !ipv6_chk_addr(net, &src_info->ipi6_addr, - strict ? dev : NULL, 0) && + !ipv6_chk_addr_and_flags(net, &src_info->ipi6_addr, + dev, !strict, 0, + IFA_F_TENTATIVE) && !ipv6_chk_acast_addr_src(net, dev, &src_info->ipi6_addr)) err = -EINVAL; diff --combined net/ipv6/ip6_gre.c index 6adbcf40cf8c,1bbd0930063e..3a98c694da5f --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@@ -126,7 -126,8 +126,8 @@@ static struct ip6_tnl *ip6gre_tunnel_lo struct ip6_tnl *t, *cand = NULL; struct ip6gre_net *ign = net_generic(net, ip6gre_net_id); int dev_type = (gre_proto == htons(ETH_P_TEB) || - gre_proto == htons(ETH_P_ERSPAN)) ? + gre_proto == htons(ETH_P_ERSPAN) || + gre_proto == htons(ETH_P_ERSPAN2)) ? ARPHRD_ETHER : ARPHRD_IP6GRE; int score, cand_score = 4; @@@ -236,7 -237,7 +237,7 @@@ return t; dev = ign->fb_tunnel_dev; - if (dev->flags & IFF_UP) + if (dev && dev->flags & IFF_UP) return netdev_priv(dev); return NULL; @@@ -695,6 -696,9 +696,6 @@@ static netdev_tx_t __gre6_xmit(struct s 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; @@@ -717,20 -721,14 +718,20 @@@ 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)); @@@ -905,6 -903,9 +906,9 @@@ static netdev_tx_t ip6erspan_tunnel_xmi truncate = true; } + if (skb_cow_head(skb, dev->needed_headroom)) + goto tx_err; + t->parms.o_flags &= ~TUNNEL_KEY; IPCB(skb)->flags = 0; @@@ -947,6 -948,8 +951,8 @@@ md->u.md2.dir, get_hwid(&md->u.md2), truncate, false); + } else { + goto tx_err; } } else { switch (skb->protocol) { @@@ -1056,7 -1059,7 +1062,7 @@@ static void ip6gre_tnl_link_config(stru struct rt6_info *rt = rt6_lookup(t->net, &p->raddr, &p->laddr, - p->link, strict); + p->link, NULL, strict); if (!rt) return; @@@ -1472,8 -1475,6 +1478,8 @@@ static int __net_init ip6gre_init_net(s struct ip6gre_net *ign = net_generic(net, ip6gre_net_id); int err; + if (!net_has_fallback_tunnels(net)) + return 0; ign->fb_tunnel_dev = alloc_netdev(sizeof(struct ip6_tnl), "ip6gre0", NET_NAME_UNKNOWN, ip6gre_tunnel_setup); @@@ -1522,7 -1523,6 +1528,7 @@@ static struct pernet_operations ip6gre_ .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[], @@@ -1790,12 -1790,6 +1796,12 @@@ static void ip6gre_tap_setup(struct net 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 --combined net/ipv6/ndisc.c index 10024eb0c521,ba5e04c6ae17..d1d0b2fa7a07 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@@ -527,7 -527,7 +527,7 @@@ void ndisc_send_na(struct net_device *d } if (!dev->addr_len) - inc_opt = 0; + inc_opt = false; if (inc_opt) optlen += ndisc_opt_addr_space(dev, NDISC_NEIGHBOUR_ADVERTISEMENT); @@@ -707,7 -707,7 +707,7 @@@ static void ndisc_solicit(struct neighb int probes = atomic_read(&neigh->probes); if (skb && ipv6_chk_addr_and_flags(dev_net(dev), &ipv6_hdr(skb)->saddr, - dev, 1, + dev, false, 1, IFA_F_TENTATIVE|IFA_F_OPTIMISTIC)) saddr = &ipv6_hdr(skb)->saddr; probes -= NEIGH_VAR(neigh->parms, UCAST_PROBES); @@@ -1554,7 -1554,8 +1554,8 @@@ static void ndisc_fill_redirect_hdr_opt *(opt++) = (rd_len >> 3); opt += 6; - memcpy(opt, ipv6_hdr(orig_skb), rd_len - 8); + skb_copy_bits(orig_skb, skb_network_offset(orig_skb), opt, + rd_len - 8); } void ndisc_send_redirect(struct sk_buff *skb, const struct in6_addr *target) @@@ -1882,7 -1883,6 +1883,7 @@@ static void __net_exit ndisc_net_exit(s static struct pernet_operations ndisc_net_ops = { .init = ndisc_net_init, .exit = ndisc_net_exit, + .async = true, }; int __init ndisc_init(void) diff --combined net/ipv6/route.c index 939d122e71b4,b0d5c64e1978..a2ed9fdd58d4 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@@ -128,7 -128,7 +128,7 @@@ struct uncached_list static DEFINE_PER_CPU_ALIGNED(struct uncached_list, rt6_uncached_list); - static void rt6_uncached_list_add(struct rt6_info *rt) + void rt6_uncached_list_add(struct rt6_info *rt) { struct uncached_list *ul = raw_cpu_ptr(&rt6_uncached_list); @@@ -139,7 -139,7 +139,7 @@@ spin_unlock_bh(&ul->lock); } - static void rt6_uncached_list_del(struct rt6_info *rt) + void rt6_uncached_list_del(struct rt6_info *rt) { if (!list_empty(&rt->rt6i_uncached)) { struct uncached_list *ul = rt->rt6i_uncached_list; @@@ -450,10 -450,8 +450,10 @@@ static bool rt6_check_expired(const str 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; @@@ -462,7 -460,7 +462,7 @@@ * 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; @@@ -916,9 -914,7 +916,9 @@@ static bool ip6_hold_safe(struct net *n 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; @@@ -933,8 -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); @@@ -958,15 -954,14 +958,15 @@@ } 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, @@@ -980,7 -975,7 +980,7 @@@ 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; @@@ -1514,7 -1509,30 +1514,30 @@@ static void rt6_exceptions_remove_prefs } } - static void rt6_exceptions_update_pmtu(struct rt6_info *rt, int mtu) + static bool rt6_mtu_change_route_allowed(struct inet6_dev *idev, + struct rt6_info *rt, int mtu) + { + /* If the new MTU is lower than the route PMTU, this new MTU will be the + * lowest MTU in the path: always allow updating the route PMTU to + * reflect PMTU decreases. + * + * If the new MTU is higher, and the route PMTU is equal to the local + * MTU, this means the old MTU is the lowest in the path, so allow + * updating it: if other nodes now have lower MTUs, PMTU discovery will + * handle this. + */ + + if (dst_mtu(&rt->dst) >= mtu) + return true; + + if (dst_mtu(&rt->dst) == idev->cnf.mtu6) + return true; + + return false; + } + + static void rt6_exceptions_update_pmtu(struct inet6_dev *idev, + struct rt6_info *rt, int mtu) { struct rt6_exception_bucket *bucket; struct rt6_exception *rt6_ex; @@@ -1523,20 -1541,22 +1546,22 @@@ bucket = rcu_dereference_protected(rt->rt6i_exception_bucket, lockdep_is_held(&rt6_exception_lock)); - if (bucket) { - for (i = 0; i < FIB6_EXCEPTION_BUCKET_SIZE; i++) { - hlist_for_each_entry(rt6_ex, &bucket->chain, hlist) { - struct rt6_info *entry = rt6_ex->rt6i; - /* For RTF_CACHE with rt6i_pmtu == 0 - * (i.e. a redirected route), - * the metrics of its rt->dst.from has already - * been updated. - */ - if (entry->rt6i_pmtu && entry->rt6i_pmtu > mtu) - entry->rt6i_pmtu = mtu; - } - bucket++; + if (!bucket) + return; + + for (i = 0; i < FIB6_EXCEPTION_BUCKET_SIZE; i++) { + hlist_for_each_entry(rt6_ex, &bucket->chain, hlist) { + struct rt6_info *entry = rt6_ex->rt6i; + + /* For RTF_CACHE with rt6i_pmtu == 0 (i.e. a redirected + * route), the metrics of its rt->dst.from have already + * been updated. + */ + if (entry->rt6i_pmtu && + rt6_mtu_change_route_allowed(idev, entry, mtu)) + entry->rt6i_pmtu = mtu; } + bucket++; } } @@@ -1652,8 -1672,7 +1677,8 @@@ void rt6_age_exceptions(struct rt6_inf } 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; @@@ -1675,7 -1694,7 +1700,7 @@@ 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) @@@ -1774,35 -1793,28 +1799,35 @@@ 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; @@@ -1824,76 -1836,26 +1849,76 @@@ 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 (ip6_multipath_hash_policy(net)) { + 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) @@@ -1910,29 -1872,20 +1935,29 @@@ .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, @@@ -1960,7 -1913,7 +1985,7 @@@ 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); @@@ -2209,7 -2162,6 +2234,7 @@@ 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; @@@ -2283,9 -2235,8 +2308,9 @@@ 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; @@@ -2293,7 -2244,7 +2318,7 @@@ 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); } @@@ -2313,7 -2264,7 +2338,7 @@@ void ip6_redirect(struct sk_buff *skb, 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); } @@@ -2335,7 -2286,7 +2360,7 @@@ void ip6_redirect_no_header(struct sk_b 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); } @@@ -2537,7 -2488,7 +2562,7 @@@ static struct rt6_info *ip6_nh_lookup_t 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) { @@@ -2550,7 -2501,7 +2575,7 @@@ static int ip6_route_check_nh_onlink(struct net *net, struct fib6_config *cfg, - struct net_device *dev, + const struct net_device *dev, struct netlink_ext_ack *extack) { u32 tbid = l3mdev_fib_table(dev) ? : RT_TABLE_MAIN; @@@ -2600,7 -2551,7 +2625,7 @@@ static int ip6_route_check_nh(struct ne } 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; @@@ -2626,79 -2577,6 +2651,79 @@@ out return err; } +static int ip6_validate_gw(struct net *net, struct fib6_config *cfg, + struct net_device **_dev, struct inet6_dev **idev, + struct netlink_ext_ack *extack) +{ + const struct in6_addr *gw_addr = &cfg->fc_gateway; + int gwa_type = ipv6_addr_type(gw_addr); + bool skip_dev = gwa_type & IPV6_ADDR_LINKLOCAL ? false : true; + const struct net_device *dev = *_dev; + bool need_addr_check = !dev; + int err = -EINVAL; + + /* if gw_addr is local we will fail to detect this in case + * address is still TENTATIVE (DAD in progress). rt6_lookup() + * will return already-added prefix route via interface that + * prefix route was assigned to, which might be non-loopback. + */ + if (dev && + ipv6_chk_addr_and_flags(net, gw_addr, dev, skip_dev, 0, 0)) { + NL_SET_ERR_MSG(extack, "Gateway can not be a local address"); + goto out; + } + + if (gwa_type != (IPV6_ADDR_LINKLOCAL | IPV6_ADDR_UNICAST)) { + /* IPv6 strictly inhibits using not link-local + * addresses as nexthop address. + * Otherwise, router will not able to send redirects. + * It is very good, but in some (rare!) circumstances + * (SIT, PtP, NBMA NOARP links) it is handy to allow + * some exceptions. --ANK + * We allow IPv4-mapped nexthops to support RFC4798-type + * addressing + */ + if (!(gwa_type & (IPV6_ADDR_UNICAST | IPV6_ADDR_MAPPED))) { + NL_SET_ERR_MSG(extack, "Invalid gateway address"); + goto out; + } + + if (cfg->fc_flags & RTNH_F_ONLINK) + err = ip6_route_check_nh_onlink(net, cfg, dev, extack); + else + err = ip6_route_check_nh(net, cfg, _dev, idev); + + if (err) + goto out; + } + + /* reload in case device was changed */ + dev = *_dev; + + err = -EINVAL; + if (!dev) { + NL_SET_ERR_MSG(extack, "Egress device not specified"); + goto out; + } else if (dev->flags & IFF_LOOPBACK) { + NL_SET_ERR_MSG(extack, + "Egress device can not be loopback device for this route"); + goto out; + } + + /* if we did not check gw_addr above, do so now that the + * egress device has been resolved. + */ + if (need_addr_check && + ipv6_chk_addr_and_flags(net, gw_addr, dev, skip_dev, 0, 0)) { + NL_SET_ERR_MSG(extack, "Gateway can not be a local address"); + goto out; + } + + err = 0; +out: + return err; +} + static struct rt6_info *ip6_route_info_create(struct fib6_config *cfg, struct netlink_ext_ack *extack) { @@@ -2818,7 -2696,14 +2843,7 @@@ 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); @@@ -2881,11 -2766,61 +2906,11 @@@ } if (cfg->fc_flags & RTF_GATEWAY) { - const struct in6_addr *gw_addr; - int gwa_type; - - gw_addr = &cfg->fc_gateway; - gwa_type = ipv6_addr_type(gw_addr); - - /* if gw_addr is local we will fail to detect this in case - * address is still TENTATIVE (DAD in progress). rt6_lookup() - * will return already-added prefix route via interface that - * prefix route was assigned to, which might be non-loopback. - */ - err = -EINVAL; - if (ipv6_chk_addr_and_flags(net, gw_addr, - gwa_type & IPV6_ADDR_LINKLOCAL ? - dev : NULL, 0, 0)) { - NL_SET_ERR_MSG(extack, "Invalid gateway address"); + err = ip6_validate_gw(net, cfg, &dev, &idev, extack); + if (err) goto out; - } - rt->rt6i_gateway = *gw_addr; - - if (gwa_type != (IPV6_ADDR_LINKLOCAL|IPV6_ADDR_UNICAST)) { - /* IPv6 strictly inhibits using not link-local - addresses as nexthop address. - Otherwise, router will not able to send redirects. - It is very good, but in some (rare!) circumstances - (SIT, PtP, NBMA NOARP links) it is handy to allow - some exceptions. --ANK - We allow IPv4-mapped nexthops to support RFC4798-type - addressing - */ - if (!(gwa_type & (IPV6_ADDR_UNICAST | - IPV6_ADDR_MAPPED))) { - NL_SET_ERR_MSG(extack, - "Invalid gateway address"); - goto out; - } - if (cfg->fc_flags & RTNH_F_ONLINK) { - err = ip6_route_check_nh_onlink(net, cfg, dev, - extack); - } else { - err = ip6_route_check_nh(net, cfg, &dev, &idev); - } - if (err) - goto out; - } - err = -EINVAL; - if (!dev) { - NL_SET_ERR_MSG(extack, "Egress device not specified"); - goto out; - } else if (dev->flags & IFF_LOOPBACK) { - NL_SET_ERR_MSG(extack, - "Egress device can not be loopback device for this route"); - goto out; - } + rt->rt6i_gateway = cfg->fc_gateway; } err = -ENODEV; @@@ -3899,25 -3834,13 +3924,13 @@@ static int rt6_mtu_change_route(struct Since RFC 1981 doesn't include administrative MTU increase update PMTU increase is a MUST. (i.e. jumbo frame) */ - /* - If new MTU is less than route PMTU, this new MTU will be the - lowest MTU in the path, update the route PMTU to reflect PMTU - decreases; if new MTU is greater than route PMTU, and the - old MTU is the lowest MTU in the path, update the route PMTU - to reflect the increase. In this case if the other nodes' MTU - also have the lowest MTU, TOO BIG MESSAGE will be lead to - PMTU discovery. - */ if (rt->dst.dev == arg->dev && - dst_metric_raw(&rt->dst, RTAX_MTU) && !dst_metric_locked(&rt->dst, RTAX_MTU)) { spin_lock_bh(&rt6_exception_lock); - if (dst_mtu(&rt->dst) >= arg->mtu || - (dst_mtu(&rt->dst) < arg->mtu && - dst_mtu(&rt->dst) == idev->cnf.mtu6)) { + if (dst_metric_raw(&rt->dst, RTAX_MTU) && + rt6_mtu_change_route_allowed(idev, rt, arg->mtu)) dst_metric_set(&rt->dst, RTAX_MTU, arg->mtu); - } - rt6_exceptions_update_pmtu(rt, arg->mtu); + rt6_exceptions_update_pmtu(idev, rt, arg->mtu); spin_unlock_bh(&rt6_exception_lock); } return 0; @@@ -4189,6 -4112,7 +4202,7 @@@ static int ip6_route_multipath_add(stru r_cfg.fc_encap_type = nla_get_u16(nla); } + r_cfg.fc_flags |= (rtnh->rtnh_flags & RTNH_F_ONLINK); rt = ip6_route_info_create(&r_cfg, extack); if (IS_ERR(rt)) { err = PTR_ERR(rt); @@@ -4688,7 -4612,7 +4702,7 @@@ static int inet6_rtm_getroute(struct sk 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 { @@@ -5069,7 -4993,6 +5083,7 @@@ static void __net_exit ip6_route_net_ex 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) @@@ -5095,13 -5018,11 +5109,13 @@@ static void __net_exit ipv6_inetpeer_ex 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 --combined net/ipv6/xfrm6_policy.c index 88cd0c90fa81,416fe67271a9..cbb270bd81b0 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@@ -113,6 -113,9 +113,9 @@@ static int xfrm6_fill_dst(struct xfrm_d xdst->u.rt6.rt6i_gateway = rt->rt6i_gateway; xdst->u.rt6.rt6i_dst = rt->rt6i_dst; xdst->u.rt6.rt6i_src = rt->rt6i_src; + INIT_LIST_HEAD(&xdst->u.rt6.rt6i_uncached); + rt6_uncached_list_add(&xdst->u.rt6); + atomic_inc(&dev_net(dev)->ipv6.rt6_stats->fib_rt_uncache); return 0; } @@@ -244,6 -247,8 +247,8 @@@ static void xfrm6_dst_destroy(struct ds if (likely(xdst->u.rt6.rt6i_idev)) in6_dev_put(xdst->u.rt6.rt6i_idev); dst_destroy_metrics_generic(dst); + if (xdst->u.rt6.rt6i_uncached_list) + rt6_uncached_list_del(&xdst->u.rt6); xfrm_dst_destroy(xdst); } @@@ -395,7 -400,6 +400,7 @@@ static void __net_exit xfrm6_net_exit(s static struct pernet_operations xfrm6_net_ops = { .init = xfrm6_net_init, .exit = xfrm6_net_exit, + .async = true, }; int __init xfrm6_init(void) diff --combined net/iucv/af_iucv.c index 81ce15ffb878,9e2643ab4ccb..893a022f9620 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@@ -989,13 -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); @@@ -1008,7 -1009,7 +1008,7 @@@ 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); } /** @@@ -2432,9 -2433,11 +2432,11 @@@ static int afiucv_iucv_init(void af_iucv_dev->driver = &af_iucv_driver; err = device_register(af_iucv_dev); if (err) - goto out_driver; + goto out_iucv_dev; return 0; + out_iucv_dev: + put_device(af_iucv_dev); out_driver: driver_unregister(&af_iucv_driver); out_iucv: diff --combined net/kcm/kcmsock.c index a6cd0712e063,34355fd19f27..516cfad71b85 --- a/net/kcm/kcmsock.c +++ b/net/kcm/kcmsock.c @@@ -1381,24 -1381,32 +1381,32 @@@ static int kcm_attach(struct socket *so .parse_msg = kcm_parse_func_strparser, .read_sock_done = kcm_read_sock_done, }; - int err; + int err = 0; csk = csock->sk; if (!csk) return -EINVAL; + lock_sock(csk); + /* Only allow TCP sockets to be attached for now */ if ((csk->sk_family != AF_INET && csk->sk_family != AF_INET6) || - csk->sk_protocol != IPPROTO_TCP) - return -EOPNOTSUPP; + csk->sk_protocol != IPPROTO_TCP) { + err = -EOPNOTSUPP; + goto out; + } /* Don't allow listeners or closed sockets */ - if (csk->sk_state == TCP_LISTEN || csk->sk_state == TCP_CLOSE) - return -EOPNOTSUPP; + if (csk->sk_state == TCP_LISTEN || csk->sk_state == TCP_CLOSE) { + err = -EOPNOTSUPP; + goto out; + } psock = kmem_cache_zalloc(kcm_psockp, GFP_KERNEL); - if (!psock) - return -ENOMEM; + if (!psock) { + err = -ENOMEM; + goto out; + } psock->mux = mux; psock->sk = csk; @@@ -1407,7 -1415,7 +1415,7 @@@ err = strp_init(&psock->strp, csk, &cb); if (err) { kmem_cache_free(kcm_psockp, psock); - return err; + goto out; } write_lock_bh(&csk->sk_callback_lock); @@@ -1417,10 -1425,10 +1425,11 @@@ */ 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; + err = -EALREADY; + goto out; } psock->save_data_ready = csk->sk_data_ready; @@@ -1456,7 -1464,10 +1465,10 @@@ /* Schedule RX work in case there are already bytes queued */ strp_check_rcv(&psock->strp); - return 0; + out: + release_sock(csk); + + return err; } static int kcm_attach_ioctl(struct socket *sock, struct kcm_attach *info) @@@ -1508,6 -1519,7 +1520,7 @@@ static void kcm_unattach(struct kcm_pso if (WARN_ON(psock->rx_kcm)) { write_unlock_bh(&csk->sk_callback_lock); + release_sock(csk); return; } @@@ -2015,7 -2027,6 +2028,7 @@@ static struct pernet_operations kcm_net .exit = kcm_exit_net, .id = &kcm_net_id, .size = sizeof(struct kcm_net), + .async = true, }; static int __init kcm_init(void) diff --combined net/l2tp/l2tp_core.c index 189a12a5e4ac,14b67dfacc4b..b86868da50d4 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@@ -111,6 -111,13 +111,13 @@@ struct l2tp_net spinlock_t l2tp_session_hlist_lock; }; + #if IS_ENABLED(CONFIG_IPV6) + static bool l2tp_sk_is_v6(struct sock *sk) + { + return sk->sk_family == PF_INET6 && + !ipv6_addr_v4mapped(&sk->sk_v6_daddr); + } + #endif static inline struct l2tp_tunnel *l2tp_tunnel(struct sock *sk) { @@@ -1049,7 -1056,7 +1056,7 @@@ static int l2tp_xmit_core(struct l2tp_s /* Queue the packet to IP for output */ skb->ignore_df = 1; #if IS_ENABLED(CONFIG_IPV6) - if (tunnel->sock->sk_family == PF_INET6 && !tunnel->v4mapped) + if (l2tp_sk_is_v6(tunnel->sock)) error = inet6_csk_xmit(tunnel->sock, skb, NULL); else #endif @@@ -1112,6 -1119,15 +1119,15 @@@ int l2tp_xmit_skb(struct l2tp_session * goto out_unlock; } + /* The user-space may change the connection status for the user-space + * provided socket at run time: we must check it under the socket lock + */ + if (tunnel->fd >= 0 && sk->sk_state != TCP_ESTABLISHED) { + kfree_skb(skb); + ret = NET_XMIT_DROP; + goto out_unlock; + } + /* Get routing info from the tunnel socket */ skb_dst_drop(skb); skb_dst_set(skb, dst_clone(__sk_dst_check(sk, 0))); @@@ -1131,7 -1147,7 +1147,7 @@@ /* Calculate UDP checksum if configured to do so */ #if IS_ENABLED(CONFIG_IPV6) - if (sk->sk_family == PF_INET6 && !tunnel->v4mapped) + if (l2tp_sk_is_v6(sk)) udp6_set_csum(udp_get_no_check6_tx(sk), skb, &inet6_sk(sk)->saddr, &sk->sk_v6_daddr, udp_len); @@@ -1457,9 -1473,14 +1473,14 @@@ int l2tp_tunnel_create(struct net *net encap = cfg->encap; /* Quick sanity checks */ + err = -EPROTONOSUPPORT; + if (sk->sk_type != SOCK_DGRAM) { + pr_debug("tunl %hu: fd %d wrong socket type\n", + tunnel_id, fd); + goto err; + } switch (encap) { case L2TP_ENCAPTYPE_UDP: - err = -EPROTONOSUPPORT; if (sk->sk_protocol != IPPROTO_UDP) { pr_err("tunl %hu: fd %d wrong protocol, got %d, expected %d\n", tunnel_id, fd, sk->sk_protocol, IPPROTO_UDP); @@@ -1467,7 -1488,6 +1488,6 @@@ } break; case L2TP_ENCAPTYPE_IP: - err = -EPROTONOSUPPORT; if (sk->sk_protocol != IPPROTO_L2TP) { pr_err("tunl %hu: fd %d wrong protocol, got %d, expected %d\n", tunnel_id, fd, sk->sk_protocol, IPPROTO_L2TP); @@@ -1507,24 -1527,6 +1527,6 @@@ if (cfg != NULL) tunnel->debug = cfg->debug; - #if IS_ENABLED(CONFIG_IPV6) - if (sk->sk_family == PF_INET6) { - struct ipv6_pinfo *np = inet6_sk(sk); - - if (ipv6_addr_v4mapped(&np->saddr) && - ipv6_addr_v4mapped(&sk->sk_v6_daddr)) { - struct inet_sock *inet = inet_sk(sk); - - tunnel->v4mapped = true; - inet->inet_saddr = np->saddr.s6_addr32[3]; - inet->inet_rcv_saddr = sk->sk_v6_rcv_saddr.s6_addr32[3]; - inet->inet_daddr = sk->sk_v6_daddr.s6_addr32[3]; - } else { - tunnel->v4mapped = false; - } - } - #endif - /* Mark socket as an encapsulation socket. See net/ipv4/udp.c */ tunnel->encap = encap; if (encap == L2TP_ENCAPTYPE_UDP) { @@@ -1787,7 -1789,6 +1789,7 @@@ static struct pernet_operations l2tp_ne .exit = l2tp_exit_net, .id = &l2tp_net_id, .size = sizeof(struct l2tp_net), + .async = true, }; static int __init l2tp_init(void) diff --combined net/mac80211/debugfs.c index a75653affbf7,94c7ee9df33b..b5adf3625d16 --- a/net/mac80211/debugfs.c +++ b/net/mac80211/debugfs.c @@@ -212,7 -212,7 +212,8 @@@ 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), + FLAG(DOESNT_SUPPORT_QOS_NDP), #undef FLAG }; diff --combined net/mac80211/mlme.c index 0024eff9bb84,5f303abac5ad..fe4aefb06d9f --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@@ -7,7 -7,6 +7,7 @@@ * Copyright 2007, Michael Wu &lt;flamingice(a)sourmilk.net&gt; * 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 @@@ -897,7 -896,8 +897,8 @@@ void ieee80211_send_nullfunc(struct iee struct ieee80211_hdr_3addr *nullfunc; struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; - skb = ieee80211_nullfunc_get(&local->hw, &sdata->vif, true); + skb = ieee80211_nullfunc_get(&local->hw, &sdata->vif, + !ieee80211_hw_check(&local->hw, DOESNT_SUPPORT_QOS_NDP)); if (!skb) return; @@@ -2009,22 -2009,9 +2010,22 @@@ static void ieee80211_set_disassoc(stru 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) @@@ -2165,7 -2152,7 +2166,7 @@@ static void ieee80211_sta_tx_wmm_ac_not 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 --combined net/netfilter/nf_tables_api.c index 8e19c86d1aa6,c4acc7340eb1..fd13d28e4ca7 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@@ -5423,6 -5423,7 +5423,7 @@@ err static void nf_tables_flowtable_destroy(struct nft_flowtable *flowtable) { cancel_delayed_work_sync(&flowtable->data.gc_work); + kfree(flowtable->ops); kfree(flowtable->name); flowtable->data.type->free(&flowtable->data); rhashtable_destroy(&flowtable->data.rhashtable); @@@ -6596,7 -6597,6 +6597,7 @@@ static void __net_exit nf_tables_exit_n static struct pernet_operations nf_tables_net_ops = { .init = nf_tables_init_net, .exit = nf_tables_exit_net, + .async = true, }; static int __init nf_tables_module_init(void) diff --combined net/netfilter/x_tables.c index d9deebe599ec,4aa01c90e9d1..6de1f6a4cb80 --- a/net/netfilter/x_tables.c +++ b/net/netfilter/x_tables.c @@@ -423,6 -423,36 +423,36 @@@ textify_hooks(char *buf, size_t size, u return buf; } + /** + * xt_check_proc_name - check that name is suitable for /proc file creation + * + * @name: file name candidate + * @size: length of buffer + * + * some x_tables modules wish to create a file in /proc. + * This function makes sure that the name is suitable for this + * purpose, it checks that name is NUL terminated and isn't a 'special' + * name, like "..". + * + * returns negative number on error or 0 if name is useable. + */ + int xt_check_proc_name(const char *name, unsigned int size) + { + if (name[0] == '\0') + return -EINVAL; + + if (strnlen(name, size) == size) + return -ENAMETOOLONG; + + if (strcmp(name, ".") == 0 || + strcmp(name, "..") == 0 || + strchr(name, '/')) + return -EINVAL; + + return 0; + } + EXPORT_SYMBOL(xt_check_proc_name); + int xt_check_match(struct xt_mtchk_param *par, unsigned int size, u_int8_t proto, bool inv_proto) { @@@ -1759,7 -1789,6 +1789,7 @@@ static void __net_exit xt_net_exit(stru static struct pernet_operations xt_net_ops = { .init = xt_net_init, .exit = xt_net_exit, + .async = true, }; static int __init xt_init(void) diff --combined net/netfilter/xt_hashlimit.c index db2fe0911740,3360f13dc208..ef65b7a9173e --- a/net/netfilter/xt_hashlimit.c +++ b/net/netfilter/xt_hashlimit.c @@@ -917,8 -917,9 +917,9 @@@ static int hashlimit_mt_check_v1(const struct hashlimit_cfg3 cfg = {}; int ret; - if (info->name[sizeof(info->name) - 1] != '\0') - return -EINVAL; + ret = xt_check_proc_name(info->name, sizeof(info->name)); + if (ret) + return ret; ret = cfg_copy(&cfg, (void *)&info->cfg, 1); @@@ -935,8 -936,9 +936,9 @@@ static int hashlimit_mt_check_v2(const struct hashlimit_cfg3 cfg = {}; int ret; - if (info->name[sizeof(info->name) - 1] != '\0') - return -EINVAL; + ret = xt_check_proc_name(info->name, sizeof(info->name)); + if (ret) + return ret; ret = cfg_copy(&cfg, (void *)&info->cfg, 2); @@@ -950,9 -952,11 +952,11 @@@ static int hashlimit_mt_check(const struct xt_mtchk_param *par) { struct xt_hashlimit_mtinfo3 *info = par->matchinfo; + int ret; - if (info->name[sizeof(info->name) - 1] != '\0') - return -EINVAL; + ret = xt_check_proc_name(info->name, sizeof(info->name)); + if (ret) + return ret; return hashlimit_mt_check_common(par, &info->hinfo, &info->cfg, info->name, 3); @@@ -1345,7 -1349,6 +1349,7 @@@ static struct pernet_operations hashlim .exit = hashlimit_net_exit, .id = &hashlimit_net_id, .size = sizeof(struct hashlimit_net), + .async = true, }; static int __init hashlimit_mt_init(void) diff --combined net/netfilter/xt_recent.c index 19efdb757944,81ee1d6543b2..486dd24da78b --- a/net/netfilter/xt_recent.c +++ b/net/netfilter/xt_recent.c @@@ -361,9 -361,9 +361,9 @@@ static int recent_mt_check(const struc info->hit_count, XT_RECENT_MAX_NSTAMPS - 1); return -EINVAL; } - if (info->name[0] == '\0' || - strnlen(info->name, XT_RECENT_NAME_LEN) == XT_RECENT_NAME_LEN) - return -EINVAL; + ret = xt_check_proc_name(info->name, sizeof(info->name)); + if (ret) + return ret; if (ip_pkt_list_tot && info->hit_count < ip_pkt_list_tot) nstamp_mask = roundup_pow_of_two(ip_pkt_list_tot) - 1; @@@ -687,7 -687,6 +687,7 @@@ static struct pernet_operations recent_ .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 --combined net/netlink/genetlink.c index a6f63a5faee7,b9ce82c9440f..af51b8c0a2cb --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@@ -1035,7 -1035,6 +1035,7 @@@ static void __net_exit genl_pernet_exit static struct pernet_operations genl_pernet_ops = { .init = genl_pernet_init, .exit = genl_pernet_exit, + .async = true, }; static int __init genl_init(void) @@@ -1107,7 -1106,7 +1107,7 @@@ static int genlmsg_mcast(struct sk_buf if (!err) delivered = true; else if (err != -ESRCH) - goto error; + return err; return delivered ? 0 : -ESRCH; error: kfree_skb(skb); diff --combined net/sched/act_bpf.c index da72e0cf2b1f,9d2cabf1dc7e..5cb9b268e8ff --- a/net/sched/act_bpf.c +++ b/net/sched/act_bpf.c @@@ -272,7 -272,7 +272,7 @@@ static void tcf_bpf_prog_fill_cfg(cons 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]; @@@ -352,7 -352,7 +352,7 @@@ return res; out: if (res == ACT_P_CREATED) - tcf_idr_cleanup(*act, est); + tcf_idr_release(*act, bind); return ret; } @@@ -367,16 -367,14 +367,16 @@@ static void tcf_bpf_cleanup(struct tc_a 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); @@@ -413,7 -411,6 +413,7 @@@ static struct pernet_operations bpf_net .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 --combined net/sched/act_csum.c index 1fb1f1f6a555,2a5c8fd860cf..a527e287c086 --- a/net/sched/act_csum.c +++ b/net/sched/act_csum.c @@@ -46,7 -46,7 +46,7 @@@ static struct tc_action_ops act_csum_op 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; @@@ -350,7 -350,7 +350,7 @@@ static int tcf_csum_sctp(struct sk_buf { struct sctphdr *sctph; - if (skb_is_gso(skb) && skb_shinfo(skb)->gso_type & SKB_GSO_SCTP) + if (skb_is_gso(skb) && skb_is_gso_sctp(skb)) return 1; sctph = tcf_csum_skb_nextlayer(skb, ihl, ipl, sizeof(*sctph)); @@@ -626,21 -626,20 +626,22 @@@ static void tcf_csum_cleanup(struct tc_ struct tcf_csum_params *params; params = rcu_dereference_protected(p->params, 1); - kfree_rcu(params, rcu); + if (params) + kfree_rcu(params, rcu); } 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); @@@ -677,7 -676,6 +678,7 @@@ static struct pernet_operations csum_ne .exit_batch = csum_exit_net, .id = &csum_net_id, .size = sizeof(struct tc_action_net), + .async = true, }; MODULE_DESCRIPTION("Checksum updating actions"); diff --combined net/sched/act_ipt.c index 10866717f88e,7e06b9b62613..b5e8565b89c7 --- a/net/sched/act_ipt.c +++ b/net/sched/act_ipt.c @@@ -80,9 -80,12 +80,12 @@@ static void ipt_destroy_target(struct x static void tcf_ipt_release(struct tc_action *a) { struct tcf_ipt *ipt = to_ipt(a); - ipt_destroy_target(ipt->tcfi_t); + + if (ipt->tcfi_t) { + ipt_destroy_target(ipt->tcfi_t); + kfree(ipt->tcfi_t); + } kfree(ipt->tcfi_tname); - kfree(ipt->tcfi_t); } static const struct nla_policy ipt_policy[TCA_IPT_MAX + 1] = { @@@ -187,13 -190,13 +190,13 @@@ err2 kfree(tname); err1: if (ret == ACT_P_CREATED) - tcf_idr_cleanup(*a, est); + tcf_idr_release(*a, bind); return err; } 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 -204,7 +204,7 @@@ 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); @@@ -303,16 -306,14 +306,16 @@@ 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); @@@ -349,21 -350,18 +352,21 @@@ static struct pernet_operations ipt_net .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); @@@ -400,7 -398,6 +403,7 @@@ static struct pernet_operations xt_net_ .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 --combined net/sched/act_pedit.c index 5e8cc8f63acd,fef08835f26d..f392ccaaa0d8 --- a/net/sched/act_pedit.c +++ b/net/sched/act_pedit.c @@@ -132,7 -132,7 +132,7 @@@ static int tcf_pedit_key_ex_dump(struc 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]; @@@ -176,7 -176,7 +176,7 @@@ p = to_pedit(*a); keys = kmalloc(ksize, GFP_KERNEL); if (keys == NULL) { - tcf_idr_cleanup(*a, est); + tcf_idr_release(*a, bind); kfree(keys_ex); return -ENOMEM; } @@@ -419,16 -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); @@@ -465,7 -463,6 +465,7 @@@ static struct pernet_operations pedit_n .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 --combined net/sched/act_police.c index 51fe4fe343f7,faebf82b99f1..7081ec75e696 --- a/net/sched/act_police.c +++ b/net/sched/act_police.c @@@ -58,12 -58,11 +58,12 @@@ static struct tc_action_ops act_police_ 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] = { @@@ -75,8 -74,7 +75,8 @@@ 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]; @@@ -196,7 -194,7 +196,7 @@@ failure qdisc_put_rtab(P_tab); qdisc_put_rtab(R_tab); if (ret == ACT_P_CREATED) - tcf_idr_cleanup(*a, est); + tcf_idr_release(*a, bind); return err; } @@@ -306,8 -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); @@@ -347,7 -344,6 +347,7 @@@ static struct pernet_operations police_ .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 --combined net/sched/act_sample.c index 238dfd27e995,74c5d7e6a0fa..3a89f98f17e6 --- a/net/sched/act_sample.c +++ b/net/sched/act_sample.c @@@ -37,7 -37,7 +37,7 @@@ static const struct nla_policy sample_p 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]; @@@ -103,7 -103,8 +103,8 @@@ static void tcf_sample_cleanup(struct t psample_group = rtnl_dereference(s->psample_group); RCU_INIT_POINTER(s->psample_group, NULL); - psample_group_put(psample_group); + if (psample_group) + psample_group_put(psample_group); } static bool tcf_sample_dev_ok_push(struct net_device *dev) @@@ -202,16 -203,14 +203,16 @@@ 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); @@@ -248,7 -247,6 +249,7 @@@ static struct pernet_operations sample_ .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 --combined net/sched/act_simple.c index 91816d73f3f3,b1f38063ada0..e84768ae610a --- a/net/sched/act_simple.c +++ b/net/sched/act_simple.c @@@ -79,7 -79,7 +79,7 @@@ static const struct nla_policy simple_p 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]; @@@ -121,7 -121,7 +121,7 @@@ d = to_defact(*a); ret = alloc_defdata(d, defdata); if (ret < 0) { - tcf_idr_cleanup(*a, est); + tcf_idr_release(*a, bind); return ret; } d->tcf_action = parm->action; @@@ -170,16 -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); @@@ -216,7 -214,6 +216,7 @@@ static struct pernet_operations simp_ne .exit_batch = simp_exit_net, .id = &simp_net_id, .size = sizeof(struct tc_action_net), + .async = true, }; MODULE_AUTHOR("Jamal Hadi Salim(2005)"); diff --combined net/sched/act_skbmod.c index febec75f4f7a,7b0700f52b50..142a996ac776 --- a/net/sched/act_skbmod.c +++ b/net/sched/act_skbmod.c @@@ -84,7 -84,7 +84,7 @@@ static const struct nla_policy skbmod_p 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]; @@@ -152,7 -152,7 +152,7 @@@ ASSERT_RTNL(); p = kzalloc(sizeof(struct tcf_skbmod_params), GFP_KERNEL); if (unlikely(!p)) { - if (ovr) + if (ret == ACT_P_CREATED) tcf_idr_release(*a, bind); return -ENOMEM; } @@@ -190,7 -190,8 +190,8 @@@ static void tcf_skbmod_cleanup(struct t struct tcf_skbmod_params *p; p = rcu_dereference_protected(d->skbmod_p, 1); - kfree_rcu(p, rcu); + if (p) + kfree_rcu(p, rcu); } static int tcf_skbmod_dump(struct sk_buff *skb, struct tc_action *a, @@@ -232,16 -233,14 +233,16 @@@ 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); @@@ -278,7 -277,6 +279,7 @@@ static struct pernet_operations skbmod_ .exit_batch = skbmod_exit_net, .id = &skbmod_net_id, .size = sizeof(struct tc_action_net), + .async = true, }; MODULE_AUTHOR("Jamal Hadi Salim, &lt;jhs(a)mojatatu.com&gt;&quot;)>"); diff --combined net/sched/act_tunnel_key.c index 9169b7e78ada,1281ca463727..a1c8dd406a04 --- a/net/sched/act_tunnel_key.c +++ b/net/sched/act_tunnel_key.c @@@ -70,7 -70,7 +70,7 @@@ static const struct nla_policy tunnel_k 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]; @@@ -153,6 -153,7 +153,7 @@@ metadata->u.tun_info.mode |= IP_TUNNEL_INFO_TX; break; default: + ret = -EINVAL; goto err_out; } @@@ -207,11 -208,12 +208,12 @@@ static void tunnel_key_release(struct t struct tcf_tunnel_key_params *params; params = rcu_dereference_protected(t->params, 1); + if (params) { + if (params->tcft_action == TCA_TUNNEL_KEY_ACT_SET) + dst_release(&params->tcft_enc_metadata->dst); - if (params->tcft_action == TCA_TUNNEL_KEY_ACT_SET) - dst_release(&params->tcft_enc_metadata->dst); - - kfree_rcu(params, rcu); + kfree_rcu(params, rcu); + } } static int tunnel_key_dump_addresses(struct sk_buff *skb, @@@ -291,16 -293,14 +293,16 @@@ 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); @@@ -337,7 -337,6 +339,7 @@@ static struct pernet_operations tunnel_ .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 --combined net/sched/act_vlan.c index c2ee7fd51cc9,c49cb61adedf..4595391c2129 --- a/net/sched/act_vlan.c +++ b/net/sched/act_vlan.c @@@ -109,7 -109,7 +109,7 @@@ static const struct nla_policy vlan_pol 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]; @@@ -195,7 -195,7 +195,7 @@@ ASSERT_RTNL(); p = kzalloc(sizeof(*p), GFP_KERNEL); if (!p) { - if (ovr) + if (ret == ACT_P_CREATED) tcf_idr_release(*a, bind); return -ENOMEM; } @@@ -225,7 -225,8 +225,8 @@@ static void tcf_vlan_cleanup(struct tc_ struct tcf_vlan_params *p; p = rcu_dereference_protected(v->vlan_p, 1); - kfree_rcu(p, rcu); + if (p) + kfree_rcu(p, rcu); } static int tcf_vlan_dump(struct sk_buff *skb, struct tc_action *a, @@@ -267,16 -268,14 +268,16 @@@ 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); @@@ -313,7 -312,6 +314,7 @@@ static struct pernet_operations vlan_ne .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 --combined net/smc/af_smc.c index 86913eb5cfa0,1e0d780855c3..5f8046c62d90 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@@ -7,11 -7,13 +7,11 @@@ * 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 * - support for urgent data postponed * - * Copyright IBM Corp. 2016 + * Copyright IBM Corp. 2016, 2018 * * Author(s): Ursula Braun &lt;ubraun(a)linux.vnet.ibm.com&gt; * based on prototype from Frank Blaschka @@@ -22,6 -24,7 +22,6 @@@ #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> @@@ -63,10 -66,6 +63,10 @@@ static struct smc_hashinfo smc_v4_hashi .lock = __RW_LOCK_UNLOCKED(smc_v4_hashinfo.lock), }; +static struct smc_hashinfo smc_v6_hashinfo = { + .lock = __RW_LOCK_UNLOCKED(smc_v6_hashinfo.lock), +}; + int smc_hash_sk(struct sock *sk) { struct smc_hashinfo *h = sk->sk_prot->h.smc_hash; @@@ -106,18 -105,6 +106,18 @@@ struct proto smc_proto = }; EXPORT_SYMBOL_GPL(smc_proto); +struct proto smc_proto6 = { + .name = "SMC6", + .owner = THIS_MODULE, + .keepalive = smc_set_keepalive, + .hash = smc_hash_sk, + .unhash = smc_unhash_sk, + .obj_size = sizeof(struct smc_sock), + .h.smc_hash = &smc_v6_hashinfo, + .slab_flags = SLAB_TYPESAFE_BY_RCU, +}; +EXPORT_SYMBOL_GPL(smc_proto6); + static int smc_release(struct socket *sock) { struct sock *sk = sock->sk; @@@ -174,22 -161,19 +174,22 @@@ static void smc_destruct(struct sock *s sk_refcnt_debug_dec(sk); } -static struct sock *smc_sock_alloc(struct net *net, struct socket *sock) +static struct sock *smc_sock_alloc(struct net *net, struct socket *sock, + int protocol) { struct smc_sock *smc; + struct proto *prot; struct sock *sk; - sk = sk_alloc(net, PF_SMC, GFP_KERNEL, &smc_proto, 0); + prot = (protocol == SMCPROTO_SMC6) ? &smc_proto6 : &smc_proto; + sk = sk_alloc(net, PF_SMC, GFP_KERNEL, prot, 0); if (!sk) return NULL; sock_init_data(sock, sk); /* sets sk_refcnt to 1 */ sk->sk_state = SMC_INIT; sk->sk_destruct = smc_destruct; - sk->sk_protocol = SMCPROTO_SMC; + sk->sk_protocol = protocol; smc = smc_sk(sk); INIT_WORK(&smc->tcp_listen_work, smc_tcp_listen_work); INIT_LIST_HEAD(&smc->accept_q); @@@ -216,13 -200,10 +216,13 @@@ static int smc_bind(struct socket *sock goto out; rc = -EAFNOSUPPORT; + if (addr->sin_family != AF_INET && + addr->sin_family != AF_INET6 && + addr->sin_family != AF_UNSPEC) + goto out; /* accept AF_UNSPEC (mapped to AF_INET) only if s_addr is INADDR_ANY */ - if ((addr->sin_family != AF_INET) && - ((addr->sin_family != AF_UNSPEC) || - (addr->sin_addr.s_addr != htonl(INADDR_ANY)))) + if (addr->sin_family == AF_UNSPEC && + addr->sin_addr.s_addr != htonl(INADDR_ANY)) goto out; lock_sock(sk); @@@ -292,7 -273,47 +292,7 @@@ static void smc_copy_sock_settings_to_s 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; @@@ -312,9 -333,6 +312,9 @@@ 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; @@@ -329,33 -347,11 +329,33 @@@ /* 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, @@@ -377,9 -373,19 +377,9 @@@ static void smc_link_save_peer_info(str 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; @@@ -433,8 -439,8 +433,8 @@@ 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) @@@ -493,7 -499,8 +493,7 @@@ 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; @@@ -550,8 -557,9 +550,8 @@@ static int smc_connect(struct socket *s /* separate smc parameter checking to be safe */ if (alen < sizeof(addr->sa_family)) goto out_err; - if (addr->sa_family != AF_INET) + if (addr->sa_family != AF_INET && addr->sa_family != AF_INET6) goto out_err; - smc->addr = addr; /* needed for nonblocking connect */ lock_sock(sk); switch (sk->sk_state) { @@@ -592,7 -600,7 +592,7 @@@ static int smc_clcsock_accept(struct sm int rc; release_sock(lsk); - new_sk = smc_sock_alloc(sock_net(lsk), NULL); + new_sk = smc_sock_alloc(sock_net(lsk), NULL, lsk->sk_protocol); if (!new_sk) { rc = -ENOMEM; lsk->sk_err = ENOMEM; @@@ -741,34 -749,9 +741,34 @@@ static int smc_serv_conf_first_link(str 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 */ @@@ -784,10 -767,13 +784,10 @@@ static void smc_listen_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; - __be32 subnet; - u8 prefix_len; + int rc = 0; u8 ibport; /* check if peer is smc capable */ @@@ -822,19 -808,28 +822,19 @@@ goto decline_rdma; } - /* determine subnet and mask from internal TCP socket */ - rc = smc_netinfo_by_tcpsk(newclcsock, &subnet, &prefix_len); - if (rc) { - reason_code = SMC_CLC_DECL_CNFERR; /* configuration error */ - goto decline_rdma; - } - pclc = (struct smc_clc_msg_proposal *)&buf; pclc_prfx = smc_clc_proposal_get_prefix(pclc); - if (pclc_prfx->outgoing_subnet != subnet || - pclc_prfx->prefix_len != prefix_len) { + + rc = smc_clc_prfx_match(newclcsock, pclc_prfx); + if (rc) { reason_code = SMC_CLC_DECL_CNFERR; /* configuration error */ 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) @@@ -983,10 -978,6 +983,6 @@@ out lsmc->clcsock = NULL; } release_sock(lsk); - /* no more listening, wake up smc_close_wait_listen_clcsock and - * accept - */ - lsk->sk_state_change(lsk); sock_put(&lsmc->sk); /* sock_hold in smc_listen */ } @@@ -1080,7 -1071,7 +1076,7 @@@ out } static int smc_getname(struct socket *sock, struct sockaddr *addr, - int *len, int peer) + int peer) { struct smc_sock *smc; @@@ -1090,7 -1081,7 +1086,7 @@@ 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) @@@ -1388,7 -1379,6 +1384,7 @@@ static const struct proto_ops smc_sock_ static int smc_create(struct net *net, struct socket *sock, int protocol, int kern) { + int family = (protocol == SMCPROTO_SMC6) ? PF_INET6 : PF_INET; struct smc_sock *smc; struct sock *sk; int rc; @@@ -1398,20 -1388,20 +1394,20 @@@ goto out; rc = -EPROTONOSUPPORT; - if ((protocol != IPPROTO_IP) && (protocol != IPPROTO_TCP)) + if (protocol != SMCPROTO_SMC && protocol != SMCPROTO_SMC6) goto out; rc = -ENOBUFS; sock->ops = &smc_sock_ops; - sk = smc_sock_alloc(net, sock); + sk = smc_sock_alloc(net, sock, protocol); if (!sk) goto out; /* create internal TCP socket for CLC handshake and fallback */ smc = smc_sk(sk); smc->use_fallback = false; /* assume rdma capability first */ - rc = sock_create_kern(net, PF_INET, SOCK_STREAM, - IPPROTO_TCP, &smc->clcsock); + rc = sock_create_kern(net, family, SOCK_STREAM, IPPROTO_TCP, + &smc->clcsock); if (rc) { sk_common_release(sk); goto out; @@@ -1451,23 -1441,16 +1447,23 @@@ static int __init smc_init(void rc = proto_register(&smc_proto, 1); if (rc) { - pr_err("%s: proto_register fails with %d\n", __func__, rc); + pr_err("%s: proto_register(v4) fails with %d\n", __func__, rc); goto out_pnet; } + rc = proto_register(&smc_proto6, 1); + if (rc) { + pr_err("%s: proto_register(v6) fails with %d\n", __func__, rc); + goto out_proto; + } + rc = sock_register(&smc_sock_family_ops); if (rc) { pr_err("%s: sock_register fails with %d\n", __func__, rc); - goto out_proto; + goto out_proto6; } INIT_HLIST_HEAD(&smc_v4_hashinfo.ht); + INIT_HLIST_HEAD(&smc_v6_hashinfo.ht); rc = smc_ib_register_client(); if (rc) { @@@ -1480,8 -1463,6 +1476,8 @@@ out_sock: sock_unregister(PF_SMC); +out_proto6: + proto_unregister(&smc_proto6); out_proto: proto_unregister(&smc_proto); out_pnet: @@@ -1500,13 -1481,11 +1496,13 @@@ static void __exit smc_exit(void spin_unlock_bh(&smc_lgr_list.lock); list_for_each_entry_safe(lgr, lg, &lgr_freeing_list, list) { list_del_init(&lgr->list); + cancel_delayed_work_sync(&lgr->free_work); smc_lgr_free(lgr); /* free link group */ } static_branch_disable(&tcp_have_smc); smc_ib_unregister_client(); sock_unregister(PF_SMC); + proto_unregister(&smc_proto6); proto_unregister(&smc_proto); smc_pnet_exit(); } diff --combined net/socket.c index d9a1ac233b35,08847c3b8c39..3d1948d27a25 --- a/net/socket.c +++ b/net/socket.c @@@ -104,6 -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> @@@ -233,7 -234,7 +233,7 @@@ static int move_addr_to_user(struct soc 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) { @@@ -990,11 -991,10 +990,11 @@@ static long sock_do_ioctl(struct net *n * 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) { @@@ -1573,9 -1573,8 +1573,9 @@@ SYSCALL_DEFINE4(accept4, int, fd, struc 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; } @@@ -1655,7 -1654,7 +1655,7 @@@ SYSCALL_DEFINE3(getsockname, int, fd, s { 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) @@@ -1665,11 -1664,10 +1665,11 @@@ 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); @@@ -1687,7 -1685,7 +1687,7 @@@ SYSCALL_DEFINE3(getpeername, int, fd, s { 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) { @@@ -1697,10 -1695,11 +1697,10 @@@ 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); } @@@ -2289,12 -2288,10 +2289,12 @@@ int __sys_recvmmsg(int fd, struct mmsgh 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; @@@ -2590,6 -2587,11 +2590,11 @@@ void sock_unregister(int family } EXPORT_SYMBOL(sock_unregister); + bool sock_is_registered(int family) + { + return family < NPROTO && rcu_access_pointer(net_families[family]); + } + static int __init sock_init(void) { int err; @@@ -3169,15 -3171,17 +3174,15 @@@ int kernel_connect(struct socket *sock } 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 --combined net/xfrm/xfrm_policy.c index 77d9d1ab05ce,625b3fca5704..cb3bb9ae4407 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@@ -1458,10 -1458,13 +1458,13 @@@ xfrm_tmpl_resolve(struct xfrm_policy ** static int xfrm_get_tos(const struct flowi *fl, int family) { const struct xfrm_policy_afinfo *afinfo; - int tos = 0; + int tos; afinfo = xfrm_policy_get_afinfo(family); - tos = afinfo ? afinfo->get_tos(fl) : 0; + if (!afinfo) + return 0; + + tos = afinfo->get_tos(fl); rcu_read_unlock(); @@@ -1891,7 -1894,7 +1894,7 @@@ static void xfrm_policy_queue_process(s spin_unlock(&pq->hold_queue.lock); dst_hold(xfrm_dst_path(dst)); - dst = xfrm_lookup(net, xfrm_dst_path(dst), &fl, sk, 0); + dst = xfrm_lookup(net, xfrm_dst_path(dst), &fl, sk, XFRM_LOOKUP_QUEUE); if (IS_ERR(dst)) goto purge_queue; @@@ -2729,14 -2732,14 +2732,14 @@@ static const void *xfrm_get_dst_nexthop while (dst->xfrm) { const struct xfrm_state *xfrm = dst->xfrm; + dst = xfrm_dst_child(dst); + if (xfrm->props.mode == XFRM_MODE_TRANSPORT) continue; if (xfrm->type->flags & XFRM_TYPE_REMOTE_COADDR) daddr = xfrm->coaddr; else if (!(xfrm->type->flags & XFRM_TYPE_LOCAL_COADDR)) daddr = &xfrm->id.daddr; - - dst = xfrm_dst_child(dst); } return daddr; } @@@ -2982,7 -2985,6 +2985,7 @@@ static void __net_exit xfrm_net_exit(st 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 --combined net/xfrm/xfrm_user.c index aff2e84ec761,080035f056d9..e92b8c019c88 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@@ -121,22 -121,17 +121,17 @@@ static inline int verify_replay(struct struct nlattr *rt = attrs[XFRMA_REPLAY_ESN_VAL]; struct xfrm_replay_state_esn *rs; - if (p->flags & XFRM_STATE_ESN) { - if (!rt) - return -EINVAL; - - rs = nla_data(rt); + if (!rt) + return (p->flags & XFRM_STATE_ESN) ? -EINVAL : 0; - if (rs->bmp_len > XFRMA_REPLAY_ESN_MAX / sizeof(rs->bmp[0]) / 8) - return -EINVAL; + rs = nla_data(rt); - if (nla_len(rt) < (int)xfrm_replay_state_esn_len(rs) && - nla_len(rt) != sizeof(*rs)) - return -EINVAL; - } + if (rs->bmp_len > XFRMA_REPLAY_ESN_MAX / sizeof(rs->bmp[0]) / 8) + return -EINVAL; - if (!rt) - return 0; + if (nla_len(rt) < (int)xfrm_replay_state_esn_len(rs) && + nla_len(rt) != sizeof(*rs)) + return -EINVAL; /* As only ESP and AH support ESN feature. */ if ((p->id.proto != IPPROTO_ESP) && (p->id.proto != IPPROTO_AH)) @@@ -3258,7 -3253,6 +3253,7 @@@ static void __net_exit xfrm_user_net_ex static struct pernet_operations xfrm_user_net_ops = { .init = xfrm_user_net_init, .exit_batch = xfrm_user_net_exit, + .async = true, }; static int __init xfrm_user_init(void) -- LinuxNextTracking