From: "Jason A. Donenfeld" Jason@zx2c4.com

mainline inclusion from mainline-v5.19-rc1 commit d2825fa9365d0101571ed16534b16b7c8d261ab3 category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I50ABL CVE: NA

Reference: https://patchwork.kernel.org/project/linux-crypto/patch/20220314031101.66388...

--------------------------------

The lib/crypto libraries live in lib because they are used by various drivers of the kernel. In contrast, the various helper functions in crypto are there because they're used exclusively by the crypto API. The SM3 and SM4 helper functions were erroniously moved into lib/crypto/ instead of crypto/, even though there are no in-kernel users outside of the crypto API of those functions. This commit moves them into crypto/.

Cc: Herbert Xu herbert@gondor.apana.org.au Cc: Tianjia Zhang tianjia.zhang@linux.alibaba.com Cc: Eric Biggers ebiggers@kernel.org Signed-off-by: Jason A. Donenfeld Jason@zx2c4.com Signed-off-by: Herbert Xu herbert@gondor.apana.org.au

Conflicts: lib/crypto/Kconfig

Signed-off-by: GUO Zihua guozihua@huawei.com Reviewed-by: Wang Weiyang wangweiyang2@huawei.com Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com --- arch/arm64/crypto/Kconfig | 4 ++-- crypto/Kconfig | 18 ++++++++++++------ crypto/Makefile | 6 ++++-- {lib/crypto => crypto}/sm3.c | 0 {lib/crypto => crypto}/sm4.c | 0 lib/crypto/Kconfig | 6 ------ lib/crypto/Makefile | 6 ------ 7 files changed, 18 insertions(+), 22 deletions(-) rename {lib/crypto => crypto}/sm3.c (100%) rename {lib/crypto => crypto}/sm4.c (100%)

diff --git a/arch/arm64/crypto/Kconfig b/arch/arm64/crypto/Kconfig index 764b64837b34..b8eb0453123d 100644 --- a/arch/arm64/crypto/Kconfig +++ b/arch/arm64/crypto/Kconfig @@ -45,13 +45,13 @@ config CRYPTO_SM3_ARM64_CE tristate "SM3 digest algorithm (ARMv8.2 Crypto Extensions)" depends on KERNEL_MODE_NEON select CRYPTO_HASH - select CRYPTO_LIB_SM3 + select CRYPTO_SM3

config CRYPTO_SM4_ARM64_CE tristate "SM4 symmetric cipher (ARMv8.2 Crypto Extensions)" depends on KERNEL_MODE_NEON select CRYPTO_ALGAPI - select CRYPTO_LIB_SM4 + select CRYPTO_SM4

config CRYPTO_GHASH_ARM64_CE tristate "GHASH/AES-GCM using ARMv8 Crypto Extensions" diff --git a/crypto/Kconfig b/crypto/Kconfig index 2d2473806567..ef9000c5db4d 100644 --- a/crypto/Kconfig +++ b/crypto/Kconfig @@ -272,7 +272,7 @@ config CRYPTO_ECRDSA

config CRYPTO_SM2 tristate "SM2 algorithm" - select CRYPTO_LIB_SM3 + select CRYPTO_SM3 select CRYPTO_AKCIPHER select CRYPTO_MANAGER select MPILIB @@ -1039,9 +1039,12 @@ config CRYPTO_SHA3 http://keccak.noekeon.org/

config CRYPTO_SM3 + tristate + +config CRYPTO_SM3_GENERIC tristate "SM3 digest algorithm" select CRYPTO_HASH - select CRYPTO_LIB_SM3 + select CRYPTO_SM3 help SM3 secure hash function as defined by OSCCA GM/T 0004-2012 SM3). It is part of the Chinese Commercial Cryptography suite. @@ -1054,7 +1057,7 @@ config CRYPTO_SM3_AVX_X86_64 tristate "SM3 digest algorithm (x86_64/AVX)" depends on X86 && 64BIT select CRYPTO_HASH - select CRYPTO_LIB_SM3 + select CRYPTO_SM3 help SM3 secure hash function as defined by OSCCA GM/T 0004-2012 SM3). It is part of the Chinese Commercial Cryptography suite. This is @@ -1631,9 +1634,12 @@ config CRYPTO_SERPENT_AVX2_X86_64 https://www.cl.cam.ac.uk/~rja14/serpent.html

config CRYPTO_SM4 + tristate + +config CRYPTO_SM4_GENERIC tristate "SM4 cipher algorithm" select CRYPTO_ALGAPI - select CRYPTO_LIB_SM4 + select CRYPTO_SM4 help SM4 cipher algorithms (OSCCA GB/T 32907-2016).

@@ -1662,7 +1668,7 @@ config CRYPTO_SM4_AESNI_AVX_X86_64 select CRYPTO_SKCIPHER select CRYPTO_SIMD select CRYPTO_ALGAPI - select CRYPTO_LIB_SM4 + select CRYPTO_SM4 help SM4 cipher algorithms (OSCCA GB/T 32907-2016) (x86_64/AES-NI/AVX).

@@ -1683,7 +1689,7 @@ config CRYPTO_SM4_AESNI_AVX2_X86_64 select CRYPTO_SKCIPHER select CRYPTO_SIMD select CRYPTO_ALGAPI - select CRYPTO_LIB_SM4 + select CRYPTO_SM4 select CRYPTO_SM4_AESNI_AVX_X86_64 help SM4 cipher algorithms (OSCCA GB/T 32907-2016) (x86_64/AES-NI/AVX2). diff --git a/crypto/Makefile b/crypto/Makefile index 982066c6bdfb..58dac31a3367 100644 --- a/crypto/Makefile +++ b/crypto/Makefile @@ -81,7 +81,8 @@ obj-$(CONFIG_CRYPTO_SHA1) += sha1_generic.o obj-$(CONFIG_CRYPTO_SHA256) += sha256_generic.o obj-$(CONFIG_CRYPTO_SHA512) += sha512_generic.o obj-$(CONFIG_CRYPTO_SHA3) += sha3_generic.o -obj-$(CONFIG_CRYPTO_SM3) += sm3_generic.o +obj-$(CONFIG_CRYPTO_SM3) += sm3.o +obj-$(CONFIG_CRYPTO_SM3_GENERIC) += sm3_generic.o obj-$(CONFIG_CRYPTO_STREEBOG) += streebog_generic.o obj-$(CONFIG_CRYPTO_WP512) += wp512.o CFLAGS_wp512.o := $(call cc-option,-fno-schedule-insns) # https://gcc.gnu.org/bugzilla/show_bug.cgi?id=79149 @@ -136,7 +137,8 @@ obj-$(CONFIG_CRYPTO_SERPENT) += serpent_generic.o CFLAGS_serpent_generic.o := $(call cc-option,-fsched-pressure) # https://gcc.gnu.org/bugzilla/show_bug.cgi?id=79149 obj-$(CONFIG_CRYPTO_AES) += aes_generic.o CFLAGS_aes_generic.o := $(call cc-option,-fno-code-hoisting) # https://gcc.gnu.org/bugzilla/show_bug.cgi?id=83356 -obj-$(CONFIG_CRYPTO_SM4) += sm4_generic.o +obj-$(CONFIG_CRYPTO_SM4) += sm4.o +obj-$(CONFIG_CRYPTO_SM4_GENERIC) += sm4_generic.o obj-$(CONFIG_CRYPTO_AES_TI) += aes_ti.o obj-$(CONFIG_CRYPTO_CAMELLIA) += camellia_generic.o obj-$(CONFIG_CRYPTO_CAST_COMMON) += cast_common.o diff --git a/lib/crypto/sm3.c b/crypto/sm3.c similarity index 100% rename from lib/crypto/sm3.c rename to crypto/sm3.c diff --git a/lib/crypto/sm4.c b/crypto/sm4.c similarity index 100% rename from lib/crypto/sm4.c rename to crypto/sm4.c diff --git a/lib/crypto/Kconfig b/lib/crypto/Kconfig index 36963e8f4eaa..14c032de276e 100644 --- a/lib/crypto/Kconfig +++ b/lib/crypto/Kconfig @@ -128,9 +128,3 @@ config CRYPTO_LIB_CHACHA20POLY1305

config CRYPTO_LIB_SHA256 tristate - -config CRYPTO_LIB_SM3 - tristate - -config CRYPTO_LIB_SM4 - tristate diff --git a/lib/crypto/Makefile b/lib/crypto/Makefile index 8149bc00b627..3a435629d9ce 100644 --- a/lib/crypto/Makefile +++ b/lib/crypto/Makefile @@ -38,12 +38,6 @@ libpoly1305-y += poly1305.o obj-$(CONFIG_CRYPTO_LIB_SHA256) += libsha256.o libsha256-y := sha256.o

-obj-$(CONFIG_CRYPTO_LIB_SM3) += libsm3.o -libsm3-y := sm3.o - -obj-$(CONFIG_CRYPTO_LIB_SM4) += libsm4.o -libsm4-y := sm4.o - ifneq ($(CONFIG_CRYPTO_MANAGER_DISABLE_TESTS),y) libblake2s-y += blake2s-selftest.o libchacha20poly1305-y += chacha20poly1305-selftest.o

From: Tianjia Zhang tianjia.zhang@linux.alibaba.com

mainline inclusion from mainline-v5.19-rc1 commit 02436762f5ff4b3f662bc196c70a563bcbc92b7d category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I50ABL CVE: NA

Reference: https://patchwork.kernel.org/project/linux-crypto/patch/20220315094454.45269...

--------------------------------

The subsequent patches of the series will have an implementation of SM4-ECB/CBC/CFB/CTR accelerated by the CE instruction set, which conflicts with the current module name. In order to keep the naming rules of the AES algorithm consistent, the sm4-ce algorithm is renamed to sm4-ce-cipher.

In addition, the speed of sm4-ce-cipher is better than that of SM4 NEON. By the way, the priority of the algorithm is adjusted to 300, which is also to leave room for the priority of SM4 NEON.

Signed-off-by: Tianjia Zhang tianjia.zhang@linux.alibaba.com Signed-off-by: Herbert Xu herbert@gondor.apana.org.au Signed-off-by: GUO Zihua guozihua@huawei.com Reviewed-by: Wang Weiyang wangweiyang2@huawei.com Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com --- arch/arm64/crypto/Makefile | 4 ++-- arch/arm64/crypto/{sm4-ce-core.S => sm4-ce-cipher-core.S} | 0 arch/arm64/crypto/{sm4-ce-glue.c => sm4-ce-cipher-glue.c} | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) rename arch/arm64/crypto/{sm4-ce-core.S => sm4-ce-cipher-core.S} (100%) rename arch/arm64/crypto/{sm4-ce-glue.c => sm4-ce-cipher-glue.c} (98%)

diff --git a/arch/arm64/crypto/Makefile b/arch/arm64/crypto/Makefile index a5d4b672b6e1..8c731449285b 100644 --- a/arch/arm64/crypto/Makefile +++ b/arch/arm64/crypto/Makefile @@ -20,8 +20,8 @@ sha3-ce-y := sha3-ce-glue.o sha3-ce-core.o obj-$(CONFIG_CRYPTO_SM3_ARM64_CE) += sm3-ce.o sm3-ce-y := sm3-ce-glue.o sm3-ce-core.o

-obj-$(CONFIG_CRYPTO_SM4_ARM64_CE) += sm4-ce.o -sm4-ce-y := sm4-ce-glue.o sm4-ce-core.o +obj-$(CONFIG_CRYPTO_SM4_ARM64_CE) += sm4-ce-cipher.o +sm4-ce-cipher-y := sm4-ce-cipher-glue.o sm4-ce-cipher-core.o

obj-$(CONFIG_CRYPTO_GHASH_ARM64_CE) += ghash-ce.o ghash-ce-y := ghash-ce-glue.o ghash-ce-core.o diff --git a/arch/arm64/crypto/sm4-ce-core.S b/arch/arm64/crypto/sm4-ce-cipher-core.S similarity index 100% rename from arch/arm64/crypto/sm4-ce-core.S rename to arch/arm64/crypto/sm4-ce-cipher-core.S diff --git a/arch/arm64/crypto/sm4-ce-glue.c b/arch/arm64/crypto/sm4-ce-cipher-glue.c similarity index 98% rename from arch/arm64/crypto/sm4-ce-glue.c rename to arch/arm64/crypto/sm4-ce-cipher-glue.c index 9c93cfc4841b..76a34ef4abbb 100644 --- a/arch/arm64/crypto/sm4-ce-glue.c +++ b/arch/arm64/crypto/sm4-ce-cipher-glue.c @@ -54,7 +54,7 @@ static void sm4_ce_decrypt(struct crypto_tfm *tfm, u8 *out, const u8 *in) static struct crypto_alg sm4_ce_alg = { .cra_name = "sm4", .cra_driver_name = "sm4-ce", - .cra_priority = 200, + .cra_priority = 300, .cra_flags = CRYPTO_ALG_TYPE_CIPHER, .cra_blocksize = SM4_BLOCK_SIZE, .cra_ctxsize = sizeof(struct sm4_ctx),

From: Tianjia Zhang tianjia.zhang@linux.alibaba.com

mainline inclusion from mainline-v5.19-rc1 commit 5b33e0ec881c609d96c9cce63fe15e0d0af457db category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I50ABL CVE: NA

Reference: https://patchwork.kernel.org/project/linux-crypto/patch/20220315094454.45269...

--------------------------------

This adds ARMv8 implementations of SM4 in ECB, CBC, CFB and CTR modes using Crypto Extensions, also includes key expansion operations because the Crypto Extensions instruction is much faster than software implementations.

The Crypto Extensions for SM4 can only run on ARMv8 implementations that have support for these optional extensions.

Benchmark on T-Head Yitian-710 2.75 GHz, the data comes from the 218 mode of tcrypt. The abscissas are blocks of different lengths. The data is tabulated and the unit is Mb/s:

sm4-generic | 16 64 128 256 1024 1420 4096 ECB enc | 80.05 91.42 93.66 94.77 95.69 95.77 95.86 ECB dec | 79.98 91.41 93.64 94.76 95.66 95.77 95.85 CBC enc | 78.55 86.50 88.02 88.77 89.36 89.42 89.48 CBC dec | 76.82 89.06 91.52 92.77 93.75 93.83 93.96 CFB enc | 77.64 86.13 87.62 88.42 89.08 88.83 89.18 CFB dec | 77.57 88.34 90.36 91.45 92.34 92.00 92.44 CTR enc | 77.80 88.28 90.23 91.22 92.11 91.81 92.25 CTR dec | 77.83 88.22 90.22 91.22 92.04 91.82 92.28 sm4-neon ECB enc | 28.31 112.77 203.03 209.89 215.49 202.11 210.59 ECB dec | 28.36 113.45 203.23 210.00 215.52 202.13 210.65 CBC enc | 79.32 87.02 88.51 89.28 89.85 89.89 89.97 CBC dec | 28.29 112.20 203.30 209.82 214.99 201.51 209.95 CFB enc | 79.59 87.16 88.54 89.30 89.83 89.62 89.92 CFB dec | 28.12 111.05 202.47 209.02 214.21 210.90 209.12 CTR enc | 28.04 108.81 200.62 206.65 211.78 208.78 206.74 CTR dec | 28.02 108.82 200.45 206.62 211.78 208.74 206.70 sm4-ce-cipher ECB enc | 336.79 587.13 682.70 747.37 803.75 811.52 818.06 ECB dec | 339.18 584.52 679.72 743.68 798.82 803.83 811.54 CBC enc | 316.63 521.47 597.00 647.14 690.82 695.21 700.55 CBC dec | 291.80 503.79 585.66 640.82 689.86 695.16 701.72 CFB enc | 294.79 482.31 552.13 594.71 631.60 628.91 638.92 CFB dec | 293.09 466.44 526.56 563.17 594.41 592.26 601.97 CTR enc | 309.61 506.13 576.86 620.47 656.38 654.51 665.10 CTR dec | 306.69 505.57 576.84 620.18 657.09 654.52 665.32 sm4-ce ECB enc | 366.96 1329.81 2024.29 2755.50 3790.07 3861.91 4051.40 ECB dec | 367.30 1323.93 2018.72 2747.43 3787.39 3862.55 4052.62 CBC enc | 358.09 682.68 807.24 885.35 958.29 963.60 973.73 CBC dec | 366.51 1303.63 1978.64 2667.93 3624.53 3683.41 3856.08 CFB enc | 351.51 681.26 807.81 893.10 968.54 969.17 985.83 CFB dec | 354.98 1266.61 1929.63 2634.81 3614.23 3611.59 3841.68 CTR enc | 324.23 1121.25 1689.44 2256.70 2981.90 3007.79 3060.74 CTR dec | 324.18 1120.44 1694.31 2258.32 2982.01 3010.09 3060.99

Signed-off-by: Tianjia Zhang tianjia.zhang@linux.alibaba.com Signed-off-by: Herbert Xu herbert@gondor.apana.org.au Signed-off-by: GUO Zihua guozihua@huawei.com Reviewed-by: Wang Weiyang wangweiyang2@huawei.com Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com --- arch/arm64/crypto/Kconfig | 6 + arch/arm64/crypto/Makefile | 3 + arch/arm64/crypto/sm4-ce-core.S | 660 ++++++++++++++++++++++++++++++++ arch/arm64/crypto/sm4-ce-glue.c | 372 ++++++++++++++++++ 4 files changed, 1041 insertions(+) create mode 100644 arch/arm64/crypto/sm4-ce-core.S create mode 100644 arch/arm64/crypto/sm4-ce-glue.c

diff --git a/arch/arm64/crypto/Kconfig b/arch/arm64/crypto/Kconfig index 84aa0c3ab997..46b3cd31b7bb 100644 --- a/arch/arm64/crypto/Kconfig +++ b/arch/arm64/crypto/Kconfig @@ -53,6 +53,12 @@ config CRYPTO_SM4_ARM64_CE select CRYPTO_ALGAPI select CRYPTO_SM4

+config CRYPTO_SM4_ARM64_CE_BLK + tristate "SM4 in ECB/CBC/CFB/CTR modes using ARMv8 Crypto Extensions" + depends on KERNEL_MODE_NEON + select CRYPTO_SKCIPHER + select CRYPTO_LIB_SM4 + config CRYPTO_SM4_ARM64_NEON_BLK tristate "SM4 in ECB/CBC/CFB/CTR modes using NEON instructions" depends on KERNEL_MODE_NEON diff --git a/arch/arm64/crypto/Makefile b/arch/arm64/crypto/Makefile index fe3701123455..5b2bb7e92bad 100644 --- a/arch/arm64/crypto/Makefile +++ b/arch/arm64/crypto/Makefile @@ -23,6 +23,9 @@ sm3-ce-y := sm3-ce-glue.o sm3-ce-core.o obj-$(CONFIG_CRYPTO_SM4_ARM64_CE) += sm4-ce-cipher.o sm4-ce-cipher-y := sm4-ce-cipher-glue.o sm4-ce-cipher-core.o

+obj-$(CONFIG_CRYPTO_SM4_ARM64_CE_BLK) += sm4-ce.o +sm4-ce-y := sm4-ce-glue.o sm4-ce-core.o + obj-$(CONFIG_CRYPTO_SM4_ARM64_NEON_BLK) += sm4-neon.o sm4-neon-y := sm4-neon-glue.o sm4-neon-core.o

diff --git a/arch/arm64/crypto/sm4-ce-core.S b/arch/arm64/crypto/sm4-ce-core.S new file mode 100644 index 000000000000..934e0f093279 --- /dev/null +++ b/arch/arm64/crypto/sm4-ce-core.S @@ -0,0 +1,660 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * SM4 Cipher Algorithm for ARMv8 with Crypto Extensions + * as specified in + * https://tools.ietf.org/id/draft-ribose-cfrg-sm4-10.html + * + * Copyright (C) 2022, Alibaba Group. + * Copyright (C) 2022 Tianjia Zhang tianjia.zhang@linux.alibaba.com + */ + +#include <linux/linkage.h> +#include <asm/assembler.h> + +.arch armv8-a+crypto + +.irp b, 0, 1, 2, 3, 4, 5, 6, 7, 16, 20, 24, 25, 26, 27, 28, 29, 30, 31 + .set .Lv\b().4s, \b +.endr + +.macro sm4e, vd, vn + .inst 0xcec08400 | (.L\vn << 5) | .L\vd +.endm + +.macro sm4ekey, vd, vn, vm + .inst 0xce60c800 | (.L\vm << 16) | (.L\vn << 5) | .L\vd +.endm + +/* Register macros */ + +#define RTMP0 v16 +#define RTMP1 v17 +#define RTMP2 v18 +#define RTMP3 v19 + +#define RIV v20 + +/* Helper macros. */ + +#define PREPARE \ + ld1 {v24.16b-v27.16b}, [x0], #64; \ + ld1 {v28.16b-v31.16b}, [x0]; + +#define SM4_CRYPT_BLK(b0) \ + rev32 b0.16b, b0.16b; \ + sm4e b0.4s, v24.4s; \ + sm4e b0.4s, v25.4s; \ + sm4e b0.4s, v26.4s; \ + sm4e b0.4s, v27.4s; \ + sm4e b0.4s, v28.4s; \ + sm4e b0.4s, v29.4s; \ + sm4e b0.4s, v30.4s; \ + sm4e b0.4s, v31.4s; \ + rev64 b0.4s, b0.4s; \ + ext b0.16b, b0.16b, b0.16b, #8; \ + rev32 b0.16b, b0.16b; + +#define SM4_CRYPT_BLK4(b0, b1, b2, b3) \ + rev32 b0.16b, b0.16b; \ + rev32 b1.16b, b1.16b; \ + rev32 b2.16b, b2.16b; \ + rev32 b3.16b, b3.16b; \ + sm4e b0.4s, v24.4s; \ + sm4e b1.4s, v24.4s; \ + sm4e b2.4s, v24.4s; \ + sm4e b3.4s, v24.4s; \ + sm4e b0.4s, v25.4s; \ + sm4e b1.4s, v25.4s; \ + sm4e b2.4s, v25.4s; \ + sm4e b3.4s, v25.4s; \ + sm4e b0.4s, v26.4s; \ + sm4e b1.4s, v26.4s; \ + sm4e b2.4s, v26.4s; \ + sm4e b3.4s, v26.4s; \ + sm4e b0.4s, v27.4s; \ + sm4e b1.4s, v27.4s; \ + sm4e b2.4s, v27.4s; \ + sm4e b3.4s, v27.4s; \ + sm4e b0.4s, v28.4s; \ + sm4e b1.4s, v28.4s; \ + sm4e b2.4s, v28.4s; \ + sm4e b3.4s, v28.4s; \ + sm4e b0.4s, v29.4s; \ + sm4e b1.4s, v29.4s; \ + sm4e b2.4s, v29.4s; \ + sm4e b3.4s, v29.4s; \ + sm4e b0.4s, v30.4s; \ + sm4e b1.4s, v30.4s; \ + sm4e b2.4s, v30.4s; \ + sm4e b3.4s, v30.4s; \ + sm4e b0.4s, v31.4s; \ + sm4e b1.4s, v31.4s; \ + sm4e b2.4s, v31.4s; \ + sm4e b3.4s, v31.4s; \ + rev64 b0.4s, b0.4s; \ + rev64 b1.4s, b1.4s; \ + rev64 b2.4s, b2.4s; \ + rev64 b3.4s, b3.4s; \ + ext b0.16b, b0.16b, b0.16b, #8; \ + ext b1.16b, b1.16b, b1.16b, #8; \ + ext b2.16b, b2.16b, b2.16b, #8; \ + ext b3.16b, b3.16b, b3.16b, #8; \ + rev32 b0.16b, b0.16b; \ + rev32 b1.16b, b1.16b; \ + rev32 b2.16b, b2.16b; \ + rev32 b3.16b, b3.16b; + +#define SM4_CRYPT_BLK8(b0, b1, b2, b3, b4, b5, b6, b7) \ + rev32 b0.16b, b0.16b; \ + rev32 b1.16b, b1.16b; \ + rev32 b2.16b, b2.16b; \ + rev32 b3.16b, b3.16b; \ + rev32 b4.16b, b4.16b; \ + rev32 b5.16b, b5.16b; \ + rev32 b6.16b, b6.16b; \ + rev32 b7.16b, b7.16b; \ + sm4e b0.4s, v24.4s; \ + sm4e b1.4s, v24.4s; \ + sm4e b2.4s, v24.4s; \ + sm4e b3.4s, v24.4s; \ + sm4e b4.4s, v24.4s; \ + sm4e b5.4s, v24.4s; \ + sm4e b6.4s, v24.4s; \ + sm4e b7.4s, v24.4s; \ + sm4e b0.4s, v25.4s; \ + sm4e b1.4s, v25.4s; \ + sm4e b2.4s, v25.4s; \ + sm4e b3.4s, v25.4s; \ + sm4e b4.4s, v25.4s; \ + sm4e b5.4s, v25.4s; \ + sm4e b6.4s, v25.4s; \ + sm4e b7.4s, v25.4s; \ + sm4e b0.4s, v26.4s; \ + sm4e b1.4s, v26.4s; \ + sm4e b2.4s, v26.4s; \ + sm4e b3.4s, v26.4s; \ + sm4e b4.4s, v26.4s; \ + sm4e b5.4s, v26.4s; \ + sm4e b6.4s, v26.4s; \ + sm4e b7.4s, v26.4s; \ + sm4e b0.4s, v27.4s; \ + sm4e b1.4s, v27.4s; \ + sm4e b2.4s, v27.4s; \ + sm4e b3.4s, v27.4s; \ + sm4e b4.4s, v27.4s; \ + sm4e b5.4s, v27.4s; \ + sm4e b6.4s, v27.4s; \ + sm4e b7.4s, v27.4s; \ + sm4e b0.4s, v28.4s; \ + sm4e b1.4s, v28.4s; \ + sm4e b2.4s, v28.4s; \ + sm4e b3.4s, v28.4s; \ + sm4e b4.4s, v28.4s; \ + sm4e b5.4s, v28.4s; \ + sm4e b6.4s, v28.4s; \ + sm4e b7.4s, v28.4s; \ + sm4e b0.4s, v29.4s; \ + sm4e b1.4s, v29.4s; \ + sm4e b2.4s, v29.4s; \ + sm4e b3.4s, v29.4s; \ + sm4e b4.4s, v29.4s; \ + sm4e b5.4s, v29.4s; \ + sm4e b6.4s, v29.4s; \ + sm4e b7.4s, v29.4s; \ + sm4e b0.4s, v30.4s; \ + sm4e b1.4s, v30.4s; \ + sm4e b2.4s, v30.4s; \ + sm4e b3.4s, v30.4s; \ + sm4e b4.4s, v30.4s; \ + sm4e b5.4s, v30.4s; \ + sm4e b6.4s, v30.4s; \ + sm4e b7.4s, v30.4s; \ + sm4e b0.4s, v31.4s; \ + sm4e b1.4s, v31.4s; \ + sm4e b2.4s, v31.4s; \ + sm4e b3.4s, v31.4s; \ + sm4e b4.4s, v31.4s; \ + sm4e b5.4s, v31.4s; \ + sm4e b6.4s, v31.4s; \ + sm4e b7.4s, v31.4s; \ + rev64 b0.4s, b0.4s; \ + rev64 b1.4s, b1.4s; \ + rev64 b2.4s, b2.4s; \ + rev64 b3.4s, b3.4s; \ + rev64 b4.4s, b4.4s; \ + rev64 b5.4s, b5.4s; \ + rev64 b6.4s, b6.4s; \ + rev64 b7.4s, b7.4s; \ + ext b0.16b, b0.16b, b0.16b, #8; \ + ext b1.16b, b1.16b, b1.16b, #8; \ + ext b2.16b, b2.16b, b2.16b, #8; \ + ext b3.16b, b3.16b, b3.16b, #8; \ + ext b4.16b, b4.16b, b4.16b, #8; \ + ext b5.16b, b5.16b, b5.16b, #8; \ + ext b6.16b, b6.16b, b6.16b, #8; \ + ext b7.16b, b7.16b, b7.16b, #8; \ + rev32 b0.16b, b0.16b; \ + rev32 b1.16b, b1.16b; \ + rev32 b2.16b, b2.16b; \ + rev32 b3.16b, b3.16b; \ + rev32 b4.16b, b4.16b; \ + rev32 b5.16b, b5.16b; \ + rev32 b6.16b, b6.16b; \ + rev32 b7.16b, b7.16b; + + +.align 3 +SYM_FUNC_START(sm4_ce_expand_key) + /* input: + * x0: 128-bit key + * x1: rkey_enc + * x2: rkey_dec + * x3: fk array + * x4: ck array + */ + ld1 {v0.16b}, [x0]; + rev32 v0.16b, v0.16b; + ld1 {v1.16b}, [x3]; + /* load ck */ + ld1 {v24.16b-v27.16b}, [x4], #64; + ld1 {v28.16b-v31.16b}, [x4]; + + /* input ^ fk */ + eor v0.16b, v0.16b, v1.16b; + + sm4ekey v0.4s, v0.4s, v24.4s; + sm4ekey v1.4s, v0.4s, v25.4s; + sm4ekey v2.4s, v1.4s, v26.4s; + sm4ekey v3.4s, v2.4s, v27.4s; + sm4ekey v4.4s, v3.4s, v28.4s; + sm4ekey v5.4s, v4.4s, v29.4s; + sm4ekey v6.4s, v5.4s, v30.4s; + sm4ekey v7.4s, v6.4s, v31.4s; + + st1 {v0.16b-v3.16b}, [x1], #64; + st1 {v4.16b-v7.16b}, [x1]; + rev64 v7.4s, v7.4s; + rev64 v6.4s, v6.4s; + rev64 v5.4s, v5.4s; + rev64 v4.4s, v4.4s; + rev64 v3.4s, v3.4s; + rev64 v2.4s, v2.4s; + rev64 v1.4s, v1.4s; + rev64 v0.4s, v0.4s; + ext v7.16b, v7.16b, v7.16b, #8; + ext v6.16b, v6.16b, v6.16b, #8; + ext v5.16b, v5.16b, v5.16b, #8; + ext v4.16b, v4.16b, v4.16b, #8; + ext v3.16b, v3.16b, v3.16b, #8; + ext v2.16b, v2.16b, v2.16b, #8; + ext v1.16b, v1.16b, v1.16b, #8; + ext v0.16b, v0.16b, v0.16b, #8; + st1 {v7.16b}, [x2], #16; + st1 {v6.16b}, [x2], #16; + st1 {v5.16b}, [x2], #16; + st1 {v4.16b}, [x2], #16; + st1 {v3.16b}, [x2], #16; + st1 {v2.16b}, [x2], #16; + st1 {v1.16b}, [x2], #16; + st1 {v0.16b}, [x2]; + + ret; +SYM_FUNC_END(sm4_ce_expand_key) + +.align 3 +SYM_FUNC_START(sm4_ce_crypt_block) + /* input: + * x0: round key array, CTX + * x1: dst + * x2: src + */ + PREPARE; + + ld1 {v0.16b}, [x2]; + SM4_CRYPT_BLK(v0); + st1 {v0.16b}, [x1]; + + ret; +SYM_FUNC_END(sm4_ce_crypt_block) + +.align 3 +SYM_FUNC_START(sm4_ce_crypt) + /* input: + * x0: round key array, CTX + * x1: dst + * x2: src + * w3: nblocks + */ + PREPARE; + +.Lcrypt_loop_blk: + sub w3, w3, #8; + tbnz w3, #31, .Lcrypt_tail8; + + ld1 {v0.16b-v3.16b}, [x2], #64; + ld1 {v4.16b-v7.16b}, [x2], #64; + + SM4_CRYPT_BLK8(v0, v1, v2, v3, v4, v5, v6, v7); + + st1 {v0.16b-v3.16b}, [x1], #64; + st1 {v4.16b-v7.16b}, [x1], #64; + + cbz w3, .Lcrypt_end; + b .Lcrypt_loop_blk; + +.Lcrypt_tail8: + add w3, w3, #8; + cmp w3, #4; + blt .Lcrypt_tail4; + + sub w3, w3, #4; + + ld1 {v0.16b-v3.16b}, [x2], #64; + SM4_CRYPT_BLK4(v0, v1, v2, v3); + st1 {v0.16b-v3.16b}, [x1], #64; + + cbz w3, .Lcrypt_end; + +.Lcrypt_tail4: + sub w3, w3, #1; + + ld1 {v0.16b}, [x2], #16; + SM4_CRYPT_BLK(v0); + st1 {v0.16b}, [x1], #16; + + cbnz w3, .Lcrypt_tail4; + +.Lcrypt_end: + ret; +SYM_FUNC_END(sm4_ce_crypt) + +.align 3 +SYM_FUNC_START(sm4_ce_cbc_enc) + /* input: + * x0: round key array, CTX + * x1: dst + * x2: src + * x3: iv (big endian, 128 bit) + * w4: nblocks + */ + PREPARE; + + ld1 {RIV.16b}, [x3]; + +.Lcbc_enc_loop: + sub w4, w4, #1; + + ld1 {RTMP0.16b}, [x2], #16; + eor RIV.16b, RIV.16b, RTMP0.16b; + + SM4_CRYPT_BLK(RIV); + + st1 {RIV.16b}, [x1], #16; + + cbnz w4, .Lcbc_enc_loop; + + /* store new IV */ + st1 {RIV.16b}, [x3]; + + ret; +SYM_FUNC_END(sm4_ce_cbc_enc) + +.align 3 +SYM_FUNC_START(sm4_ce_cbc_dec) + /* input: + * x0: round key array, CTX + * x1: dst + * x2: src + * x3: iv (big endian, 128 bit) + * w4: nblocks + */ + PREPARE; + + ld1 {RIV.16b}, [x3]; + +.Lcbc_loop_blk: + sub w4, w4, #8; + tbnz w4, #31, .Lcbc_tail8; + + ld1 {v0.16b-v3.16b}, [x2], #64; + ld1 {v4.16b-v7.16b}, [x2]; + + SM4_CRYPT_BLK8(v0, v1, v2, v3, v4, v5, v6, v7); + + sub x2, x2, #64; + eor v0.16b, v0.16b, RIV.16b; + ld1 {RTMP0.16b-RTMP3.16b}, [x2], #64; + eor v1.16b, v1.16b, RTMP0.16b; + eor v2.16b, v2.16b, RTMP1.16b; + eor v3.16b, v3.16b, RTMP2.16b; + st1 {v0.16b-v3.16b}, [x1], #64; + + eor v4.16b, v4.16b, RTMP3.16b; + ld1 {RTMP0.16b-RTMP3.16b}, [x2], #64; + eor v5.16b, v5.16b, RTMP0.16b; + eor v6.16b, v6.16b, RTMP1.16b; + eor v7.16b, v7.16b, RTMP2.16b; + + mov RIV.16b, RTMP3.16b; + st1 {v4.16b-v7.16b}, [x1], #64; + + cbz w4, .Lcbc_end; + b .Lcbc_loop_blk; + +.Lcbc_tail8: + add w4, w4, #8; + cmp w4, #4; + blt .Lcbc_tail4; + + sub w4, w4, #4; + + ld1 {v0.16b-v3.16b}, [x2]; + + SM4_CRYPT_BLK4(v0, v1, v2, v3); + + eor v0.16b, v0.16b, RIV.16b; + ld1 {RTMP0.16b-RTMP3.16b}, [x2], #64; + eor v1.16b, v1.16b, RTMP0.16b; + eor v2.16b, v2.16b, RTMP1.16b; + eor v3.16b, v3.16b, RTMP2.16b; + + mov RIV.16b, RTMP3.16b; + st1 {v0.16b-v3.16b}, [x1], #64; + + cbz w4, .Lcbc_end; + +.Lcbc_tail4: + sub w4, w4, #1; + + ld1 {v0.16b}, [x2]; + + SM4_CRYPT_BLK(v0); + + eor v0.16b, v0.16b, RIV.16b; + ld1 {RIV.16b}, [x2], #16; + st1 {v0.16b}, [x1], #16; + + cbnz w4, .Lcbc_tail4; + +.Lcbc_end: + /* store new IV */ + st1 {RIV.16b}, [x3]; + + ret; +SYM_FUNC_END(sm4_ce_cbc_dec) + +.align 3 +SYM_FUNC_START(sm4_ce_cfb_enc) + /* input: + * x0: round key array, CTX + * x1: dst + * x2: src + * x3: iv (big endian, 128 bit) + * w4: nblocks + */ + PREPARE; + + ld1 {RIV.16b}, [x3]; + +.Lcfb_enc_loop: + sub w4, w4, #1; + + SM4_CRYPT_BLK(RIV); + + ld1 {RTMP0.16b}, [x2], #16; + eor RIV.16b, RIV.16b, RTMP0.16b; + st1 {RIV.16b}, [x1], #16; + + cbnz w4, .Lcfb_enc_loop; + + /* store new IV */ + st1 {RIV.16b}, [x3]; + + ret; +SYM_FUNC_END(sm4_ce_cfb_enc) + +.align 3 +SYM_FUNC_START(sm4_ce_cfb_dec) + /* input: + * x0: round key array, CTX + * x1: dst + * x2: src + * x3: iv (big endian, 128 bit) + * w4: nblocks + */ + PREPARE; + + ld1 {v0.16b}, [x3]; + +.Lcfb_loop_blk: + sub w4, w4, #8; + tbnz w4, #31, .Lcfb_tail8; + + ld1 {v1.16b, v2.16b, v3.16b}, [x2], #48; + ld1 {v4.16b-v7.16b}, [x2]; + + SM4_CRYPT_BLK8(v0, v1, v2, v3, v4, v5, v6, v7); + + sub x2, x2, #48; + ld1 {RTMP0.16b-RTMP3.16b}, [x2], #64; + eor v0.16b, v0.16b, RTMP0.16b; + eor v1.16b, v1.16b, RTMP1.16b; + eor v2.16b, v2.16b, RTMP2.16b; + eor v3.16b, v3.16b, RTMP3.16b; + st1 {v0.16b-v3.16b}, [x1], #64; + + ld1 {RTMP0.16b-RTMP3.16b}, [x2], #64; + eor v4.16b, v4.16b, RTMP0.16b; + eor v5.16b, v5.16b, RTMP1.16b; + eor v6.16b, v6.16b, RTMP2.16b; + eor v7.16b, v7.16b, RTMP3.16b; + st1 {v4.16b-v7.16b}, [x1], #64; + + mov v0.16b, RTMP3.16b; + + cbz w4, .Lcfb_end; + b .Lcfb_loop_blk; + +.Lcfb_tail8: + add w4, w4, #8; + cmp w4, #4; + blt .Lcfb_tail4; + + sub w4, w4, #4; + + ld1 {v1.16b, v2.16b, v3.16b}, [x2]; + + SM4_CRYPT_BLK4(v0, v1, v2, v3); + + ld1 {RTMP0.16b-RTMP3.16b}, [x2], #64; + eor v0.16b, v0.16b, RTMP0.16b; + eor v1.16b, v1.16b, RTMP1.16b; + eor v2.16b, v2.16b, RTMP2.16b; + eor v3.16b, v3.16b, RTMP3.16b; + st1 {v0.16b-v3.16b}, [x1], #64; + + mov v0.16b, RTMP3.16b; + + cbz w4, .Lcfb_end; + +.Lcfb_tail4: + sub w4, w4, #1; + + SM4_CRYPT_BLK(v0); + + ld1 {RTMP0.16b}, [x2], #16; + eor v0.16b, v0.16b, RTMP0.16b; + st1 {v0.16b}, [x1], #16; + + mov v0.16b, RTMP0.16b; + + cbnz w4, .Lcfb_tail4; + +.Lcfb_end: + /* store new IV */ + st1 {v0.16b}, [x3]; + + ret; +SYM_FUNC_END(sm4_ce_cfb_dec) + +.align 3 +SYM_FUNC_START(sm4_ce_ctr_enc) + /* input: + * x0: round key array, CTX + * x1: dst + * x2: src + * x3: ctr (big endian, 128 bit) + * w4: nblocks + */ + PREPARE; + + ldp x7, x8, [x3]; + rev x7, x7; + rev x8, x8; + +.Lctr_loop_blk: + sub w4, w4, #8; + tbnz w4, #31, .Lctr_tail8; + +#define inc_le128(vctr) \ + mov vctr.d[1], x8; \ + mov vctr.d[0], x7; \ + adds x8, x8, #1; \ + adc x7, x7, xzr; \ + rev64 vctr.16b, vctr.16b; + + /* construct CTRs */ + inc_le128(v0); /* +0 */ + inc_le128(v1); /* +1 */ + inc_le128(v2); /* +2 */ + inc_le128(v3); /* +3 */ + inc_le128(v4); /* +4 */ + inc_le128(v5); /* +5 */ + inc_le128(v6); /* +6 */ + inc_le128(v7); /* +7 */ + + SM4_CRYPT_BLK8(v0, v1, v2, v3, v4, v5, v6, v7); + + ld1 {RTMP0.16b-RTMP3.16b}, [x2], #64; + eor v0.16b, v0.16b, RTMP0.16b; + eor v1.16b, v1.16b, RTMP1.16b; + eor v2.16b, v2.16b, RTMP2.16b; + eor v3.16b, v3.16b, RTMP3.16b; + st1 {v0.16b-v3.16b}, [x1], #64; + + ld1 {RTMP0.16b-RTMP3.16b}, [x2], #64; + eor v4.16b, v4.16b, RTMP0.16b; + eor v5.16b, v5.16b, RTMP1.16b; + eor v6.16b, v6.16b, RTMP2.16b; + eor v7.16b, v7.16b, RTMP3.16b; + st1 {v4.16b-v7.16b}, [x1], #64; + + cbz w4, .Lctr_end; + b .Lctr_loop_blk; + +.Lctr_tail8: + add w4, w4, #8; + cmp w4, #4; + blt .Lctr_tail4; + + sub w4, w4, #4; + + /* construct CTRs */ + inc_le128(v0); /* +0 */ + inc_le128(v1); /* +1 */ + inc_le128(v2); /* +2 */ + inc_le128(v3); /* +3 */ + + SM4_CRYPT_BLK4(v0, v1, v2, v3); + + ld1 {RTMP0.16b-RTMP3.16b}, [x2], #64; + eor v0.16b, v0.16b, RTMP0.16b; + eor v1.16b, v1.16b, RTMP1.16b; + eor v2.16b, v2.16b, RTMP2.16b; + eor v3.16b, v3.16b, RTMP3.16b; + st1 {v0.16b-v3.16b}, [x1], #64; + + cbz w4, .Lctr_end; + +.Lctr_tail4: + sub w4, w4, #1; + + /* construct CTRs */ + inc_le128(v0); + + SM4_CRYPT_BLK(v0); + + ld1 {RTMP0.16b}, [x2], #16; + eor v0.16b, v0.16b, RTMP0.16b; + st1 {v0.16b}, [x1], #16; + + cbnz w4, .Lctr_tail4; + +.Lctr_end: + /* store new CTR */ + rev x7, x7; + rev x8, x8; + stp x7, x8, [x3]; + + ret; +SYM_FUNC_END(sm4_ce_ctr_enc) diff --git a/arch/arm64/crypto/sm4-ce-glue.c b/arch/arm64/crypto/sm4-ce-glue.c new file mode 100644 index 000000000000..496d55c0d01a --- /dev/null +++ b/arch/arm64/crypto/sm4-ce-glue.c @@ -0,0 +1,372 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * SM4 Cipher Algorithm, using ARMv8 Crypto Extensions + * as specified in + * https://tools.ietf.org/id/draft-ribose-cfrg-sm4-10.html + * + * Copyright (C) 2022, Alibaba Group. + * Copyright (C) 2022 Tianjia Zhang tianjia.zhang@linux.alibaba.com + */ + +#include <linux/module.h> +#include <linux/crypto.h> +#include <linux/kernel.h> +#include <linux/cpufeature.h> +#include <asm/neon.h> +#include <asm/simd.h> +#include <crypto/internal/simd.h> +#include <crypto/internal/skcipher.h> +#include <crypto/sm4.h> + +#define BYTES2BLKS(nbytes) ((nbytes) >> 4) + +asmlinkage void sm4_ce_expand_key(const u8 *key, u32 *rkey_enc, u32 *rkey_dec, + const u32 *fk, const u32 *ck); +asmlinkage void sm4_ce_crypt_block(const u32 *rkey, u8 *dst, const u8 *src); +asmlinkage void sm4_ce_crypt(const u32 *rkey, u8 *dst, const u8 *src, + unsigned int nblks); +asmlinkage void sm4_ce_cbc_enc(const u32 *rkey, u8 *dst, const u8 *src, + u8 *iv, unsigned int nblks); +asmlinkage void sm4_ce_cbc_dec(const u32 *rkey, u8 *dst, const u8 *src, + u8 *iv, unsigned int nblks); +asmlinkage void sm4_ce_cfb_enc(const u32 *rkey, u8 *dst, const u8 *src, + u8 *iv, unsigned int nblks); +asmlinkage void sm4_ce_cfb_dec(const u32 *rkey, u8 *dst, const u8 *src, + u8 *iv, unsigned int nblks); +asmlinkage void sm4_ce_ctr_enc(const u32 *rkey, u8 *dst, const u8 *src, + u8 *iv, unsigned int nblks); + +static int sm4_setkey(struct crypto_skcipher *tfm, const u8 *key, + unsigned int key_len) +{ + struct sm4_ctx *ctx = crypto_skcipher_ctx(tfm); + + if (key_len != SM4_KEY_SIZE) + return -EINVAL; + + sm4_ce_expand_key(key, ctx->rkey_enc, ctx->rkey_dec, + crypto_sm4_fk, crypto_sm4_ck); + return 0; +} + +static int sm4_ecb_do_crypt(struct skcipher_request *req, const u32 *rkey) +{ + struct skcipher_walk walk; + unsigned int nbytes; + int err; + + err = skcipher_walk_virt(&walk, req, false); + + while ((nbytes = walk.nbytes) > 0) { + const u8 *src = walk.src.virt.addr; + u8 *dst = walk.dst.virt.addr; + unsigned int nblks; + + kernel_neon_begin(); + + nblks = BYTES2BLKS(nbytes); + if (nblks) { + sm4_ce_crypt(rkey, dst, src, nblks); + nbytes -= nblks * SM4_BLOCK_SIZE; + } + + kernel_neon_end(); + + err = skcipher_walk_done(&walk, nbytes); + } + + return err; +} + +static int sm4_ecb_encrypt(struct skcipher_request *req) +{ + struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); + struct sm4_ctx *ctx = crypto_skcipher_ctx(tfm); + + return sm4_ecb_do_crypt(req, ctx->rkey_enc); +} + +static int sm4_ecb_decrypt(struct skcipher_request *req) +{ + struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); + struct sm4_ctx *ctx = crypto_skcipher_ctx(tfm); + + return sm4_ecb_do_crypt(req, ctx->rkey_dec); +} + +static int sm4_cbc_encrypt(struct skcipher_request *req) +{ + struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); + struct sm4_ctx *ctx = crypto_skcipher_ctx(tfm); + struct skcipher_walk walk; + unsigned int nbytes; + int err; + + err = skcipher_walk_virt(&walk, req, false); + + while ((nbytes = walk.nbytes) > 0) { + const u8 *src = walk.src.virt.addr; + u8 *dst = walk.dst.virt.addr; + unsigned int nblks; + + kernel_neon_begin(); + + nblks = BYTES2BLKS(nbytes); + if (nblks) { + sm4_ce_cbc_enc(ctx->rkey_enc, dst, src, walk.iv, nblks); + nbytes -= nblks * SM4_BLOCK_SIZE; + } + + kernel_neon_end(); + + err = skcipher_walk_done(&walk, nbytes); + } + + return err; +} + +static int sm4_cbc_decrypt(struct skcipher_request *req) +{ + struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); + struct sm4_ctx *ctx = crypto_skcipher_ctx(tfm); + struct skcipher_walk walk; + unsigned int nbytes; + int err; + + err = skcipher_walk_virt(&walk, req, false); + + while ((nbytes = walk.nbytes) > 0) { + const u8 *src = walk.src.virt.addr; + u8 *dst = walk.dst.virt.addr; + unsigned int nblks; + + kernel_neon_begin(); + + nblks = BYTES2BLKS(nbytes); + if (nblks) { + sm4_ce_cbc_dec(ctx->rkey_dec, dst, src, walk.iv, nblks); + nbytes -= nblks * SM4_BLOCK_SIZE; + } + + kernel_neon_end(); + + err = skcipher_walk_done(&walk, nbytes); + } + + return err; +} + +static int sm4_cfb_encrypt(struct skcipher_request *req) +{ + struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); + struct sm4_ctx *ctx = crypto_skcipher_ctx(tfm); + struct skcipher_walk walk; + unsigned int nbytes; + int err; + + err = skcipher_walk_virt(&walk, req, false); + + while ((nbytes = walk.nbytes) > 0) { + const u8 *src = walk.src.virt.addr; + u8 *dst = walk.dst.virt.addr; + unsigned int nblks; + + kernel_neon_begin(); + + nblks = BYTES2BLKS(nbytes); + if (nblks) { + sm4_ce_cfb_enc(ctx->rkey_enc, dst, src, walk.iv, nblks); + dst += nblks * SM4_BLOCK_SIZE; + src += nblks * SM4_BLOCK_SIZE; + nbytes -= nblks * SM4_BLOCK_SIZE; + } + + /* tail */ + if (walk.nbytes == walk.total && nbytes > 0) { + u8 keystream[SM4_BLOCK_SIZE]; + + sm4_ce_crypt_block(ctx->rkey_enc, keystream, walk.iv); + crypto_xor_cpy(dst, src, keystream, nbytes); + nbytes = 0; + } + + kernel_neon_end(); + + err = skcipher_walk_done(&walk, nbytes); + } + + return err; +} + +static int sm4_cfb_decrypt(struct skcipher_request *req) +{ + struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); + struct sm4_ctx *ctx = crypto_skcipher_ctx(tfm); + struct skcipher_walk walk; + unsigned int nbytes; + int err; + + err = skcipher_walk_virt(&walk, req, false); + + while ((nbytes = walk.nbytes) > 0) { + const u8 *src = walk.src.virt.addr; + u8 *dst = walk.dst.virt.addr; + unsigned int nblks; + + kernel_neon_begin(); + + nblks = BYTES2BLKS(nbytes); + if (nblks) { + sm4_ce_cfb_dec(ctx->rkey_enc, dst, src, walk.iv, nblks); + dst += nblks * SM4_BLOCK_SIZE; + src += nblks * SM4_BLOCK_SIZE; + nbytes -= nblks * SM4_BLOCK_SIZE; + } + + /* tail */ + if (walk.nbytes == walk.total && nbytes > 0) { + u8 keystream[SM4_BLOCK_SIZE]; + + sm4_ce_crypt_block(ctx->rkey_enc, keystream, walk.iv); + crypto_xor_cpy(dst, src, keystream, nbytes); + nbytes = 0; + } + + kernel_neon_end(); + + err = skcipher_walk_done(&walk, nbytes); + } + + return err; +} + +static int sm4_ctr_crypt(struct skcipher_request *req) +{ + struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); + struct sm4_ctx *ctx = crypto_skcipher_ctx(tfm); + struct skcipher_walk walk; + unsigned int nbytes; + int err; + + err = skcipher_walk_virt(&walk, req, false); + + while ((nbytes = walk.nbytes) > 0) { + const u8 *src = walk.src.virt.addr; + u8 *dst = walk.dst.virt.addr; + unsigned int nblks; + + kernel_neon_begin(); + + nblks = BYTES2BLKS(nbytes); + if (nblks) { + sm4_ce_ctr_enc(ctx->rkey_enc, dst, src, walk.iv, nblks); + dst += nblks * SM4_BLOCK_SIZE; + src += nblks * SM4_BLOCK_SIZE; + nbytes -= nblks * SM4_BLOCK_SIZE; + } + + /* tail */ + if (walk.nbytes == walk.total && nbytes > 0) { + u8 keystream[SM4_BLOCK_SIZE]; + + sm4_ce_crypt_block(ctx->rkey_enc, keystream, walk.iv); + crypto_inc(walk.iv, SM4_BLOCK_SIZE); + crypto_xor_cpy(dst, src, keystream, nbytes); + nbytes = 0; + } + + kernel_neon_end(); + + err = skcipher_walk_done(&walk, nbytes); + } + + return err; +} + +static struct skcipher_alg sm4_algs[] = { + { + .base = { + .cra_name = "ecb(sm4)", + .cra_driver_name = "ecb-sm4-ce", + .cra_priority = 400, + .cra_blocksize = SM4_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct sm4_ctx), + .cra_module = THIS_MODULE, + }, + .min_keysize = SM4_KEY_SIZE, + .max_keysize = SM4_KEY_SIZE, + .setkey = sm4_setkey, + .encrypt = sm4_ecb_encrypt, + .decrypt = sm4_ecb_decrypt, + }, { + .base = { + .cra_name = "cbc(sm4)", + .cra_driver_name = "cbc-sm4-ce", + .cra_priority = 400, + .cra_blocksize = SM4_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct sm4_ctx), + .cra_module = THIS_MODULE, + }, + .min_keysize = SM4_KEY_SIZE, + .max_keysize = SM4_KEY_SIZE, + .ivsize = SM4_BLOCK_SIZE, + .setkey = sm4_setkey, + .encrypt = sm4_cbc_encrypt, + .decrypt = sm4_cbc_decrypt, + }, { + .base = { + .cra_name = "cfb(sm4)", + .cra_driver_name = "cfb-sm4-ce", + .cra_priority = 400, + .cra_blocksize = 1, + .cra_ctxsize = sizeof(struct sm4_ctx), + .cra_module = THIS_MODULE, + }, + .min_keysize = SM4_KEY_SIZE, + .max_keysize = SM4_KEY_SIZE, + .ivsize = SM4_BLOCK_SIZE, + .chunksize = SM4_BLOCK_SIZE, + .setkey = sm4_setkey, + .encrypt = sm4_cfb_encrypt, + .decrypt = sm4_cfb_decrypt, + }, { + .base = { + .cra_name = "ctr(sm4)", + .cra_driver_name = "ctr-sm4-ce", + .cra_priority = 400, + .cra_blocksize = 1, + .cra_ctxsize = sizeof(struct sm4_ctx), + .cra_module = THIS_MODULE, + }, + .min_keysize = SM4_KEY_SIZE, + .max_keysize = SM4_KEY_SIZE, + .ivsize = SM4_BLOCK_SIZE, + .chunksize = SM4_BLOCK_SIZE, + .setkey = sm4_setkey, + .encrypt = sm4_ctr_crypt, + .decrypt = sm4_ctr_crypt, + } +}; + +static int __init sm4_init(void) +{ + return crypto_register_skciphers(sm4_algs, ARRAY_SIZE(sm4_algs)); +} + +static void __exit sm4_exit(void) +{ + crypto_unregister_skciphers(sm4_algs, ARRAY_SIZE(sm4_algs)); +} + +module_cpu_feature_match(SM4, sm4_init); +module_exit(sm4_exit); + +MODULE_DESCRIPTION("SM4 ECB/CBC/CFB/CTR using ARMv8 Crypto Extensions"); +MODULE_ALIAS_CRYPTO("sm4-ce"); +MODULE_ALIAS_CRYPTO("sm4"); +MODULE_ALIAS_CRYPTO("ecb(sm4)"); +MODULE_ALIAS_CRYPTO("cbc(sm4)"); +MODULE_ALIAS_CRYPTO("cfb(sm4)"); +MODULE_ALIAS_CRYPTO("ctr(sm4)"); +MODULE_AUTHOR("Tianjia Zhang tianjia.zhang@linux.alibaba.com"); +MODULE_LICENSE("GPL v2");

From: Pablo Neira Ayuso pablo@netfilter.org

stable inclusion from stable-v5.10.120 commit c0aff1faf66b6b7a19103f83e6a5d0fdc64b9048 category: bugfix bugzilla: 186913 https://gitee.com/src-openeuler/kernel/issues/I5B69E CVE: CVE-2022-1972

--------------------------------

commit fecf31ee395b0295f2d7260aa29946b7605f7c85 upstream.

Add several sanity checks for nft_set_desc_concat_parse():

- validate desc->field_count not larger than desc->field_len array. - field length cannot be larger than desc->field_len (ie. U8_MAX) - total length of the concatenation cannot be larger than register array.

Joint work with Florian Westphal.

Fixes: f3a2181e16f1 ("netfilter: nf_tables: Support for sets with multiple ranged fields") Reported-by: zhangziming.zzm@antgroup.com Reviewed-by: Stefano Brivio sbrivio@redhat.com Signed-off-by: Florian Westphal fw@strlen.de Signed-off-by: Pablo Neira Ayuso pablo@netfilter.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Zhengchao Shao shaozhengchao@huawei.com Reviewed-by: Wei Yongjun weiyongjun1@huawei.com Reviewed-by: Yue Haibing yuehaibing@huawei.com Reviewed-by: Xiu Jianfeng xiujianfeng@huawei.com Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com --- net/netfilter/nf_tables_api.c | 17 +++++++++++++---- 1 file changed, 13 insertions(+), 4 deletions(-)

diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index fdd1da9ecea9..164b686bb4c9 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -4047,6 +4047,9 @@ static int nft_set_desc_concat_parse(const struct nlattr *attr, u32 len; int err;

+ if (desc->field_count >= ARRAY_SIZE(desc->field_len)) + return -E2BIG; + err = nla_parse_nested_deprecated(tb, NFTA_SET_FIELD_MAX, attr, nft_concat_policy, NULL); if (err < 0) @@ -4056,9 +4059,8 @@ static int nft_set_desc_concat_parse(const struct nlattr *attr, return -EINVAL;

len = ntohl(nla_get_be32(tb[NFTA_SET_FIELD_LEN])); - - if (len * BITS_PER_BYTE / 32 > NFT_REG32_COUNT) - return -E2BIG; + if (!len || len > U8_MAX) + return -EINVAL;

desc->field_len[desc->field_count++] = len;

@@ -4069,7 +4071,8 @@ static int nft_set_desc_concat(struct nft_set_desc *desc, const struct nlattr *nla) { struct nlattr *attr; - int rem, err; + u32 num_regs = 0; + int rem, err, i;

nla_for_each_nested(attr, nla, rem) { if (nla_type(attr) != NFTA_LIST_ELEM) @@ -4080,6 +4083,12 @@ static int nft_set_desc_concat(struct nft_set_desc *desc, return err; }

+ for (i = 0; i < desc->field_count; i++) + num_regs += DIV_ROUND_UP(desc->field_len[i], sizeof(u32)); + + if (num_regs > NFT_REG32_COUNT) + return -E2BIG; + return 0; }

From: Yufeng Mo moyufeng@huawei.com

mainline inclusion from mainline-v5.18-rc1 commit 9c9a04212fa3 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I56XHY CVE: NA

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i...

----------------------------------------------------------------------

Currently, the debugfs mechanism is that all functions share a global variable to save the pointer for obtaining data. When different functions concurrently access the same file node, repeated release exceptions occur. Therefore, the granularity of the pointer for storing the obtained data is adjusted to be private for each function.

Fixes: 5e69ea7ee2a6 ("net: hns3: refactor the debugfs process") Signed-off-by: Yufeng Mo moyufeng@huawei.com Signed-off-by: Guangbin Huang huangguangbin2@huawei.com Signed-off-by: Paolo Abeni pabeni@redhat.com Signed-off-by: Jiantao Xiao xiaojiantao1@h-partners.com Reviewed-by: Yue Haibing yuehaibing@huawei.com Reviewed-by: Jian Shen shenjian15@huawei.com Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com --- drivers/net/ethernet/hisilicon/hns3/hnae3.h | 1 + .../net/ethernet/hisilicon/hns3/hns3_debugfs.c | 15 +++++++++++---- .../net/ethernet/hisilicon/hns3/hns3_debugfs.h | 1 - 3 files changed, 12 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h index 6618ab32ab25..be4d2adebfc9 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h +++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h @@ -845,6 +845,7 @@ struct hnae3_handle { struct dentry *hnae3_dbgfs; /* protects concurrent contention between debugfs commands */ struct mutex dbgfs_lock; + char **dbgfs_buf;

/* Network interface message level enabled bits */ u32 msg_enable; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c index f726a5b70f9e..44d9b560b337 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c @@ -1227,7 +1227,7 @@ static ssize_t hns3_dbg_read(struct file *filp, char __user *buffer, return ret;

mutex_lock(&handle->dbgfs_lock); - save_buf = &hns3_dbg_cmd[index].buf; + save_buf = &handle->dbgfs_buf[index];

if (!test_bit(HNS3_NIC_STATE_INITED, &priv->state) || test_bit(HNS3_NIC_STATE_RESETTING, &priv->state)) { @@ -1332,6 +1332,13 @@ int hns3_dbg_init(struct hnae3_handle *handle) int ret; u32 i;

+ handle->dbgfs_buf = devm_kcalloc(&handle->pdev->dev, + ARRAY_SIZE(hns3_dbg_cmd), + sizeof(*handle->dbgfs_buf), + GFP_KERNEL); + if (!handle->dbgfs_buf) + return -ENOMEM; + hns3_dbg_dentry[HNS3_DBG_DENTRY_COMMON].dentry = debugfs_create_dir(name, hns3_dbgfs_root); handle->hnae3_dbgfs = hns3_dbg_dentry[HNS3_DBG_DENTRY_COMMON].dentry; @@ -1380,9 +1387,9 @@ void hns3_dbg_uninit(struct hnae3_handle *handle) u32 i;

for (i = 0; i < ARRAY_SIZE(hns3_dbg_cmd); i++) - if (hns3_dbg_cmd[i].buf) { - kvfree(hns3_dbg_cmd[i].buf); - hns3_dbg_cmd[i].buf = NULL; + if (handle->dbgfs_buf[i]) { + kvfree(handle->dbgfs_buf[i]); + handle->dbgfs_buf[i] = NULL; }

mutex_destroy(&handle->dbgfs_lock); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.h b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.h index 83aa1450ab9f..97578eabb7d8 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.h @@ -49,7 +49,6 @@ struct hns3_dbg_cmd_info { enum hnae3_dbg_cmd cmd; enum hns3_dbg_dentry_type dentry; u32 buf_len; - char *buf; int (*init)(struct hnae3_handle *handle, unsigned int cmd); };

From: Yufeng Mo moyufeng@huawei.com

mainline inclusion from mainline-origin commit 286c61e72797 category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I56XHY CVE: NA

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i...

----------------------------------------------------------------------

For DEVICE_VERSION_V2, the hardware does not support the CQE mode. So add capability bit for coalesce CQE mode and add parameter check for it in ethtool.

Signed-off-by: Yufeng Mo moyufeng@huawei.com Signed-off-by: Guangbin Huang huangguangbin2@huawei.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Jiantao Xiao xiaojiantao1@h-partners.com Reviewed-by: Yue Haibing yuehaibing@huawei.com Reviewed-by: Jian Shen shenjian15@huawei.com Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com --- drivers/net/ethernet/hisilicon/hns3/hnae3.h | 4 +++ .../hns3/hns3_common/hclge_comm_cmd.c | 2 ++ .../hns3/hns3_common/hclge_comm_cmd.h | 1 + .../net/ethernet/hisilicon/hns3/hns3_enet.c | 5 +--- .../ethernet/hisilicon/hns3/hns3_ethtool.c | 28 +++++++++++++++++-- 5 files changed, 33 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h index be4d2adebfc9..f8d31372ba9a 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h +++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h @@ -95,6 +95,7 @@ enum HNAE3_DEV_CAP_BITS { HNAE3_DEV_SUPPORT_PORT_VLAN_BYPASS_B, HNAE3_DEV_SUPPORT_VLAN_FLTR_MDF_B, HNAE3_DEV_SUPPORT_MC_MAC_MNG_B, + HNAE3_DEV_SUPPORT_CQ_B, };

#define hnae3_dev_fd_supported(hdev) \ @@ -154,6 +155,9 @@ enum HNAE3_DEV_CAP_BITS { #define hnae3_ae_dev_mc_mac_mng_supported(ae_dev) \ test_bit(HNAE3_DEV_SUPPORT_MC_MAC_MNG_B, (ae_dev)->caps)

+#define hnae3_ae_dev_cq_supported(ae_dev) \ + test_bit(HNAE3_DEV_SUPPORT_CQ_B, (ae_dev)->caps) + enum HNAE3_PF_CAP_BITS { HNAE3_PF_SUPPORT_VLAN_FLTR_MDF_B = 0, }; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_cmd.c b/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_cmd.c index c15ca710dabb..c8b151d29f53 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_cmd.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_cmd.c @@ -149,6 +149,7 @@ static const struct hclge_comm_caps_bit_map hclge_pf_cmd_caps[] = { {HCLGE_COMM_CAP_PORT_VLAN_BYPASS_B, HNAE3_DEV_SUPPORT_PORT_VLAN_BYPASS_B}, {HCLGE_COMM_CAP_PORT_VLAN_BYPASS_B, HNAE3_DEV_SUPPORT_VLAN_FLTR_MDF_B}, + {HCLGE_COMM_CAP_CQ_B, HNAE3_DEV_SUPPORT_CQ_B}, };

static const struct hclge_comm_caps_bit_map hclge_vf_cmd_caps[] = { @@ -160,6 +161,7 @@ static const struct hclge_comm_caps_bit_map hclge_vf_cmd_caps[] = { {HCLGE_COMM_CAP_QB_B, HNAE3_DEV_SUPPORT_QB_B}, {HCLGE_COMM_CAP_TX_PUSH_B, HNAE3_DEV_SUPPORT_TX_PUSH_B}, {HCLGE_COMM_CAP_RXD_ADV_LAYOUT_B, HNAE3_DEV_SUPPORT_RXD_ADV_LAYOUT_B}, + {HCLGE_COMM_CAP_CQ_B, HNAE3_DEV_SUPPORT_CQ_B}, };

static void diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_cmd.h index 876650eddac4..7a7d4cf9bf35 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_cmd.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_cmd.h @@ -338,6 +338,7 @@ enum HCLGE_COMM_CAP_BITS { HCLGE_COMM_CAP_PAUSE_B = 14, HCLGE_COMM_CAP_RXD_ADV_LAYOUT_B = 15, HCLGE_COMM_CAP_PORT_VLAN_BYPASS_B = 17, + HCLGE_COMM_CAP_CQ_B = 18, };

enum HCLGE_COMM_API_CAP_BITS { diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c index e3911116a88f..b35f100e273a 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c @@ -5158,10 +5158,7 @@ static void hns3_set_cq_period_mode(struct hns3_nic_priv *priv, priv->tqp_vector[i].rx_group.dim.mode = mode; }

- /* only device version above V3(include V3), GL can switch CQ/EQ - * period mode. - */ - if (ae_dev->dev_version >= HNAE3_DEVICE_VERSION_V3) { + if (hnae3_ae_dev_cq_supported(ae_dev)) { u32 new_mode; u64 reg;

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c index 69cee085ddee..e347e6bf8cca 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c @@ -1402,11 +1402,33 @@ static int hns3_check_ql_coalesce_param(struct net_device *netdev, return 0; }

-static int hns3_check_coalesce_para(struct net_device *netdev, - struct ethtool_coalesce *cmd) +static int +hns3_check_cqe_coalesce_param(struct net_device *netdev, + struct kernel_ethtool_coalesce *kernel_coal) +{ + struct hnae3_handle *handle = hns3_get_handle(netdev); + struct hnae3_ae_dev *ae_dev = pci_get_drvdata(handle->pdev); + + if ((kernel_coal->use_cqe_mode_tx || kernel_coal->use_cqe_mode_rx) && + !hnae3_ae_dev_cq_supported(ae_dev)) { + netdev_err(netdev, "coalesced cqe mode is not supported\n"); + return -EOPNOTSUPP; + } + + return 0; +} + +static int +hns3_check_coalesce_para(struct net_device *netdev, + struct ethtool_coalesce *cmd, + struct kernel_ethtool_coalesce *kernel_coal) { int ret;

+ ret = hns3_check_cqe_coalesce_param(netdev, kernel_coal); + if (ret) + return ret; + ret = hns3_check_gl_coalesce_para(netdev, cmd); if (ret) { netdev_err(netdev, @@ -1481,7 +1503,7 @@ static int hns3_set_coalesce(struct net_device *netdev, if (hns3_nic_resetting(netdev)) return -EBUSY;

- ret = hns3_check_coalesce_para(netdev, cmd); + ret = hns3_check_coalesce_para(netdev, cmd, kernel_coal); if (ret) return ret;

From: Jian Shen shenjian15@huawei.com

mainline inclusion from mainline-origin commit 6fde96df0447 category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I56XHY CVE: NA

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i...

----------------------------------------------------------------------

The struct hclge_pf_to_vf_msg is used for mailbox message from PF to VF, including both response and request. But its definition can only indicate respone, which makes the message data copy in function hclge_send_mbx_msg() unreadable. So refine it by edding a general message definition into it.

Signed-off-by: Jian Shen shenjian15@huawei.com Signed-off-by: Guangbin Huang huangguangbin2@huawei.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Jiantao Xiao xiaojiantao1@h-partners.com Reviewed-by: Yue Haibing yuehaibing@huawei.com Reviewed-by: Jian Shen shenjian15@huawei.com Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com --- drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h | 17 +++++++++++++---- .../ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c | 2 +- 2 files changed, 14 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h b/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h index b668df6193be..8c7fadf2b734 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h +++ b/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h @@ -135,10 +135,19 @@ struct hclge_vf_to_pf_msg {

struct hclge_pf_to_vf_msg { u16 code; - u16 vf_mbx_msg_code; - u16 vf_mbx_msg_subcode; - u16 resp_status; - u8 resp_data[HCLGE_MBX_MAX_RESP_DATA_SIZE]; + union { + /* used for mbx response */ + struct { + u16 vf_mbx_msg_code; + u16 vf_mbx_msg_subcode; + u16 resp_status; + u8 resp_data[HCLGE_MBX_MAX_RESP_DATA_SIZE]; + }; + /* used for general mbx */ + struct { + u8 msg_data[HCLGE_MBX_MAX_MSG_SIZE]; + }; + }; };

struct hclge_mbx_vf_to_pf_cmd { diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c index 6799d16de34b..76d0f17d6be3 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c @@ -102,7 +102,7 @@ static int hclge_send_mbx_msg(struct hclge_vport *vport, u8 *msg, u16 msg_len, resp_pf_to_vf->msg_len = msg_len; resp_pf_to_vf->msg.code = mbx_opcode;

- memcpy(&resp_pf_to_vf->msg.vf_mbx_msg_code, msg, msg_len); + memcpy(resp_pf_to_vf->msg.msg_data, msg, msg_len);

trace_hclge_pf_mbx_send(hdev, resp_pf_to_vf);

From: Hao Chen chenhao288@hisilicon.com

mainline inclusion from mainline-origin commit 2373b35c24ff category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I56XHY CVE: NA

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i...

----------------------------------------------------------------------

For the active tx spare buffer size maybe changed according to the page size, so add log to notice it.

Signed-off-by: Hao Chen chenhao288@hisilicon.com Signed-off-by: Guangbin Huang huangguangbin2@huawei.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Jiantao Xiao xiaojiantao1@h-partners.com Reviewed-by: Yue Haibing yuehaibing@huawei.com Reviewed-by: Jian Shen shenjian15@huawei.com Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com --- drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c | 6 ++++++ 1 file changed, 6 insertions(+)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c index 4899b89fe69b..fb86da4296a2 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c @@ -1885,6 +1885,8 @@ static int hns3_set_tunable(struct net_device *netdev, case ETHTOOL_TX_COPYBREAK_BUF_SIZE: old_tx_spare_buf_size = h->kinfo.tx_spare_buf_size; new_tx_spare_buf_size = *(u32 *)data; + netdev_info(netdev, "request to set tx spare buf size from %u to %u\n", + old_tx_spare_buf_size, new_tx_spare_buf_size); ret = hns3_set_tx_spare_buf_size(netdev, new_tx_spare_buf_size); if (ret || (!priv->ring->tx_spare && new_tx_spare_buf_size != 0)) { @@ -1902,6 +1904,10 @@ static int hns3_set_tunable(struct net_device *netdev,

return ret; } + + netdev_info(netdev, "the actvie tx spare buf size is %u, due to page order\n", + priv->ring->tx_spare->len); + break; default: ret = -EOPNOTSUPP;

From: Peng Li lipeng321@huawei.com

mainline inclusion from mainline-origin commit 9c657cbc2c15 category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I56XHY CVE: NA

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i...

----------------------------------------------------------------------

This patch fixes wrong words in comments.

Signed-off-by: Peng Lilipeng321@huawei.com Signed-off-by: Guangbin Huang huangguangbin2@huawei.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Jiantao Xiao xiaojiantao1@h-partners.com Reviewed-by: Yue Haibing yuehaibing@huawei.com Reviewed-by: Jian Shen shenjian15@huawei.com Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com --- drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c | 2 +- drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c | 2 +- drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c index 42a9e73d8588..6efd768cc07c 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c @@ -1977,7 +1977,7 @@ static int hclge_handle_mpf_ras_error(struct hclge_dev *hdev, * @num: number of extended command structures * * This function handles all the PF RAS errors in the - * hw register/s using command. + * hw registers using command. */ static int hclge_handle_pf_ras_error(struct hclge_dev *hdev, struct hclge_desc *desc, diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c index c956da60d90a..be4171e0bab0 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c @@ -2963,7 +2963,7 @@ static int hclgevf_init_hdev(struct hclgevf_dev *hdev) goto err_config; }

- /* ensure vf tbl list as empty before init*/ + /* ensure vf tbl list as empty before init */ ret = hclgevf_clear_vport_list(hdev); if (ret) { dev_err(&pdev->dev, diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c index 4761dceccea5..c8055d69255c 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c @@ -17,7 +17,7 @@ static int hclgevf_resp_to_errno(u16 resp_code) static void hclgevf_reset_mbx_resp_status(struct hclgevf_dev *hdev) { /* this function should be called with mbx_resp.mbx_mutex held - * to prtect the received_response from race condition + * to protect the received_response from race condition */ hdev->mbx_resp.received_resp = false; hdev->mbx_resp.origin_mbx_msg = 0;

From: Hao Chen chenhao288@hisilicon.com

mainline inclusion from mainline-origin commit 29c17cb67271 category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I56XHY CVE: NA

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i...

----------------------------------------------------------------------

Remove unnecessary line wrap for hns3_set_tunable to improve function readability.

Signed-off-by: Hao Chen chenhao288@hisilicon.com Signed-off-by: Guangbin Huang huangguangbin2@huawei.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Jiantao Xiao xiaojiantao1@h-partners.com Reviewed-by: Yue Haibing yuehaibing@huawei.com Reviewed-by: Jian Shen shenjian15@huawei.com Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com --- drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c index fb86da4296a2..ff0342988b11 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c @@ -1189,8 +1189,7 @@ static int hns3_set_ringparam(struct net_device *ndev,

tmp_rings = hns3_backup_ringparam(priv); if (!tmp_rings) { - netdev_err(ndev, - "backup ring param failed by allocating memory fail\n"); + netdev_err(ndev, "backup ring param failed by allocating memory fail\n"); return -ENOMEM; }

@@ -1892,13 +1891,11 @@ static int hns3_set_tunable(struct net_device *netdev, (!priv->ring->tx_spare && new_tx_spare_buf_size != 0)) { int ret1;

- netdev_warn(netdev, - "change tx spare buf size fail, revert to old value\n"); + netdev_warn(netdev, "change tx spare buf size fail, revert to old value\n"); ret1 = hns3_set_tx_spare_buf_size(netdev, old_tx_spare_buf_size); if (ret1) { - netdev_err(netdev, - "revert to old tx spare buf size fail\n"); + netdev_err(netdev, "revert to old tx spare buf size fail\n"); return ret1; }

From: Jian Shen shenjian15@huawei.com

mainline inclusion from mainline-v5.18-rc5 commit e98365afc1e9 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I56XHY CVE: NA

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i...

----------------------------------------------------------------------

If failed to register netdev, it needs to clear INITED state and stop client in case of cause problem when concurrency with uninitialized process of driver.

Fixes: a289a7e5c1d4 ("net: hns3: put off calling register_netdev() until client initialize complete") Signed-off-by: Jian Shen shenjian15@huawei.com Signed-off-by: Guangbin Huang huangguangbin2@huawei.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Jiantao Xiao xiaojiantao1@h-partners.com Reviewed-by: Yue Haibing yuehaibing@huawei.com Reviewed-by: Jian Shen shenjian15@huawei.com Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com --- drivers/net/ethernet/hisilicon/hns3/hns3_enet.c | 9 +++++++++ 1 file changed, 9 insertions(+)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c index b35f100e273a..2174b5756b07 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c @@ -5202,6 +5202,13 @@ static void hns3_state_init(struct hnae3_handle *handle) set_bit(HNS3_NIC_STATE_RXD_ADV_LAYOUT_ENABLE, &priv->state); }

+static void hns3_state_uninit(struct hnae3_handle *handle) +{ + struct hns3_nic_priv *priv = handle->priv; + + clear_bit(HNS3_NIC_STATE_INITED, &priv->state); +} + static int hns3_client_init(struct hnae3_handle *handle) { struct pci_dev *pdev = handle->pdev; @@ -5319,7 +5326,9 @@ static int hns3_client_init(struct hnae3_handle *handle) return ret;

out_reg_netdev_fail: + hns3_state_uninit(handle); hns3_dbg_uninit(handle); + hns3_client_stop(handle); out_client_start: hns3_free_rx_cpu_rmap(netdev); hns3_nic_uninit_irq(priv);

From: Peng Li lipeng321@huawei.com

mainline inclusion from mainline-v5.18-rc5 commit 123521b6b260 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I56XHY CVE: NA

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i...

----------------------------------------------------------------------

The comments in function hclge_comm_tqps_update_stats is not right, so fix it.

Fixes: 287db5c40d15 ("net: hns3: create new set of common tqp stats APIs for PF and VF reuse") Signed-off-by: Peng Li lipeng321@huawei.com Signed-off-by: Guangbin Huang huangguangbin2@huawei.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Jiantao Xiao xiaojiantao1@h-partners.com Reviewed-by: Yue Haibing yuehaibing@huawei.com Reviewed-by: Jian Shen shenjian15@huawei.com Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com --- .../hisilicon/hns3/hns3_common/hclge_comm_tqp_stats.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_tqp_stats.c b/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_tqp_stats.c index 0c60f41fca8a..f3c9395d8351 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_tqp_stats.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_tqp_stats.c @@ -75,7 +75,7 @@ int hclge_comm_tqps_update_stats(struct hnae3_handle *handle, ret = hclge_comm_cmd_send(hw, &desc, 1); if (ret) { dev_err(&hw->cmq.csq.pdev->dev, - "failed to get tqp stat, ret = %d, tx = %u.\n", + "failed to get tqp stat, ret = %d, rx = %u.\n", ret, i); return ret; } @@ -89,7 +89,7 @@ int hclge_comm_tqps_update_stats(struct hnae3_handle *handle, ret = hclge_comm_cmd_send(hw, &desc, 1); if (ret) { dev_err(&hw->cmq.csq.pdev->dev, - "failed to get tqp stat, ret = %d, rx = %u.\n", + "failed to get tqp stat, ret = %d, tx = %u.\n", ret, i); return ret; }

From: Jian Shen shenjian15@huawei.com

mainline inclusion from mainline-v5.18-rc5 commit 7d413735cb18 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I56XHY CVE: NA

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i...

----------------------------------------------------------------------

Add validity check for message data length in function hclge_send_mbx_msg(), avoid unexpected overflow.

Fixes: dde1a86e93ca ("net: hns3: Add mailbox support to PF driver") Signed-off-by: Jian Shen shenjian15@huawei.com Signed-off-by: Guangbin Huang huangguangbin2@huawei.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Jiantao Xiao xiaojiantao1@h-partners.com Reviewed-by: Yue Haibing yuehaibing@huawei.com Reviewed-by: Jian Shen shenjian15@huawei.com Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com --- drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c | 7 +++++++ 1 file changed, 7 insertions(+)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c index d53946bca5d1..1221a250eb61 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c @@ -94,6 +94,13 @@ static int hclge_send_mbx_msg(struct hclge_vport *vport, u8 *msg, u16 msg_len, enum hclge_comm_cmd_status status; struct hclge_desc desc;

+ if (msg_len > HCLGE_MBX_MAX_MSG_SIZE) { + dev_err(&hdev->pdev->dev, + "msg data length(=%u) exceeds maximum(=%u)\n", + msg_len, HCLGE_MBX_MAX_MSG_SIZE); + return -EMSGSIZE; + } + resp_pf_to_vf = (struct hclge_mbx_pf_to_vf_cmd *)desc.data;

hclge_cmd_setup_basic_desc(&desc, HCLGEVF_OPC_MBX_PF_TO_VF, false);

From: Hao Chen chenhao288@hisilicon.com

mainline inclusion from mainline-origin commit a4fe9b6db6f9 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I56XHY CVE: NA

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i...

----------------------------------------------------------------------

When set tx-buf-size as 0 by ethtool, hns3_init_tx_spare_buffer() will return directly and priv->ring->tx_spare->len is uninitialized, then print function access priv->ring->tx_spare->len will cause this issue.

When set tx-buf-size as 0 by ethtool, the print function will print 0 directly and not access priv->ring->tx_spare->len.

Fixes: 2373b35c24ff ("net: hns3: add log for setting tx spare buf size") Signed-off-by: Hao Chen chenhao288@hisilicon.com Signed-off-by: Guangbin Huang huangguangbin2@huawei.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Jiantao Xiao xiaojiantao1@h-partners.com Reviewed-by: Yue Haibing yuehaibing@huawei.com Reviewed-by: Jian Shen shenjian15@huawei.com Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com --- drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c index 578cc30a0444..76ae71b4ddd5 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c @@ -1902,8 +1902,11 @@ static int hns3_set_tunable(struct net_device *netdev, return ret; }

- netdev_info(netdev, "the active tx spare buf size is %u, due to page order\n", - priv->ring->tx_spare->len); + if (!priv->ring->tx_spare) + netdev_info(netdev, "the active tx spare buf size is 0, disable tx spare buffer\n"); + else + netdev_info(netdev, "the active tx spare buf size is %u, due to page order\n", + priv->ring->tx_spare->len);

break; default:

From: Jie Wang wangjie125@huawei.com

mainline inclusion from mainline-origin commit 767975e582c5 category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I56XHY CVE: NA

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i...

----------------------------------------------------------------------

Currently, hns3 mailbox processing between PF and VF missed to convert message byte order and use data type u16 instead of __le16 for mailbox data process. These processes may cause problems between different architectures.

So this patch uses __le16/__le32 data type to define mailbox data structures. To be compatible with old hns3 driver, these structures use one-byte alignment. Then byte order conversions are added to mailbox messages from PF to VF.

Signed-off-by: Jie Wang wangjie125@huawei.com Signed-off-by: Guangbin Huang huangguangbin2@huawei.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Jiantao Xiao xiaojiantao1@h-partners.com Reviewed-by: Yue Haibing yuehaibing@huawei.com Reviewed-by: Jian Shen shenjian15@huawei.com Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com --- .../net/ethernet/hisilicon/hns3/hclge_mbx.h | 36 +++++++-- .../hisilicon/hns3/hns3pf/hclge_mbx.c | 60 +++++++------- .../hisilicon/hns3/hns3pf/hclge_trace.h | 2 +- .../hisilicon/hns3/hns3vf/hclgevf_main.c | 4 +- .../hisilicon/hns3/hns3vf/hclgevf_main.h | 2 +- .../hisilicon/hns3/hns3vf/hclgevf_mbx.c | 80 +++++++++++-------- .../hisilicon/hns3/hns3vf/hclgevf_trace.h | 2 +- 7 files changed, 109 insertions(+), 77 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h b/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h index 8c7fadf2b734..e1ba0ae055b0 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h +++ b/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h @@ -134,13 +134,13 @@ struct hclge_vf_to_pf_msg { };

struct hclge_pf_to_vf_msg { - u16 code; + __le16 code; union { /* used for mbx response */ struct { - u16 vf_mbx_msg_code; - u16 vf_mbx_msg_subcode; - u16 resp_status; + __le16 vf_mbx_msg_code; + __le16 vf_mbx_msg_subcode; + __le16 resp_status; u8 resp_data[HCLGE_MBX_MAX_RESP_DATA_SIZE]; }; /* used for general mbx */ @@ -157,7 +157,7 @@ struct hclge_mbx_vf_to_pf_cmd { u8 rsv1[1]; u8 msg_len; u8 rsv2; - u16 match_id; + __le16 match_id; struct hclge_vf_to_pf_msg msg; };

@@ -168,7 +168,7 @@ struct hclge_mbx_pf_to_vf_cmd { u8 rsv[3]; u8 msg_len; u8 rsv1; - u16 match_id; + __le16 match_id; struct hclge_pf_to_vf_msg msg; };

@@ -178,6 +178,28 @@ struct hclge_vf_rst_cmd { u8 rsv[22]; };

+#pragma pack(1) +struct hclge_mbx_link_status { + __le16 link_status; + __le32 speed; + __le16 duplex; + u8 flag; +}; + +struct hclge_mbx_link_mode { + __le16 idx; + __le64 link_mode; +}; + +struct hclge_mbx_port_base_vlan { + __le16 state; + __le16 vlan_proto; + __le16 qos; + __le16 vlan_tag; +}; + +#pragma pack() + /* used by VF to store the received Async responses from PF */ struct hclgevf_mbx_arq_ring { #define HCLGE_MBX_MAX_ARQ_MSG_SIZE 8 @@ -186,7 +208,7 @@ struct hclgevf_mbx_arq_ring { u32 head; u32 tail; atomic_t count; - u16 msg_q[HCLGE_MBX_MAX_ARQ_MSG_NUM][HCLGE_MBX_MAX_ARQ_MSG_SIZE]; + __le16 msg_q[HCLGE_MBX_MAX_ARQ_MSG_NUM][HCLGE_MBX_MAX_ARQ_MSG_SIZE]; };

#define hclge_mbx_ring_ptr_move_crq(crq) \ diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c index 49c40744cda5..d3c4d2c4a5ba 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c @@ -57,17 +57,19 @@ static int hclge_gen_resp_to_vf(struct hclge_vport *vport, resp_pf_to_vf->msg_len = vf_to_pf_req->msg_len; resp_pf_to_vf->match_id = vf_to_pf_req->match_id;

- resp_pf_to_vf->msg.code = HCLGE_MBX_PF_VF_RESP; - resp_pf_to_vf->msg.vf_mbx_msg_code = vf_to_pf_req->msg.code; - resp_pf_to_vf->msg.vf_mbx_msg_subcode = vf_to_pf_req->msg.subcode; + resp_pf_to_vf->msg.code = cpu_to_le16(HCLGE_MBX_PF_VF_RESP); + resp_pf_to_vf->msg.vf_mbx_msg_code = + cpu_to_le16(vf_to_pf_req->msg.code); + resp_pf_to_vf->msg.vf_mbx_msg_subcode = + cpu_to_le16(vf_to_pf_req->msg.subcode); resp = hclge_errno_to_resp(resp_msg->status); if (resp < SHRT_MAX) { - resp_pf_to_vf->msg.resp_status = resp; + resp_pf_to_vf->msg.resp_status = cpu_to_le16(resp); } else { dev_warn(&hdev->pdev->dev, "failed to send response to VF, response status %u is out-of-bound\n", resp); - resp_pf_to_vf->msg.resp_status = EIO; + resp_pf_to_vf->msg.resp_status = cpu_to_le16(EIO); }

if (resp_msg->len > 0) @@ -107,7 +109,7 @@ static int hclge_send_mbx_msg(struct hclge_vport *vport, u8 *msg, u16 msg_len,

resp_pf_to_vf->dest_vfid = dest_vfid; resp_pf_to_vf->msg_len = msg_len; - resp_pf_to_vf->msg.code = mbx_opcode; + resp_pf_to_vf->msg.code = cpu_to_le16(mbx_opcode);

memcpy(resp_pf_to_vf->msg.msg_data, msg, msg_len);

@@ -125,8 +127,8 @@ static int hclge_send_mbx_msg(struct hclge_vport *vport, u8 *msg, u16 msg_len, int hclge_inform_reset_assert_to_vf(struct hclge_vport *vport) { struct hclge_dev *hdev = vport->back; + __le16 msg_data; u16 reset_type; - u8 msg_data[2]; u8 dest_vfid;

BUILD_BUG_ON(HNAE3_MAX_RESET > U16_MAX); @@ -140,10 +142,10 @@ int hclge_inform_reset_assert_to_vf(struct hclge_vport *vport) else reset_type = HNAE3_VF_FUNC_RESET;

- memcpy(&msg_data[0], &reset_type, sizeof(u16)); + msg_data = cpu_to_le16(reset_type);

/* send this requested info to VF */ - return hclge_send_mbx_msg(vport, msg_data, sizeof(msg_data), + return hclge_send_mbx_msg(vport, (u8 *)&msg_data, sizeof(msg_data), HCLGE_MBX_ASSERTING_RESET, dest_vfid); }

@@ -339,16 +341,14 @@ int hclge_push_vf_port_base_vlan_info(struct hclge_vport *vport, u8 vfid, u16 state, struct hclge_vlan_info *vlan_info) { -#define MSG_DATA_SIZE 8 + struct hclge_mbx_port_base_vlan base_vlan;

- u8 msg_data[MSG_DATA_SIZE]; + base_vlan.state = cpu_to_le16(state); + base_vlan.vlan_proto = cpu_to_le16(vlan_info->vlan_proto); + base_vlan.qos = cpu_to_le16(vlan_info->qos); + base_vlan.vlan_tag = cpu_to_le16(vlan_info->vlan_tag);

- memcpy(&msg_data[0], &state, sizeof(u16)); - memcpy(&msg_data[2], &vlan_info->vlan_proto, sizeof(u16)); - memcpy(&msg_data[4], &vlan_info->qos, sizeof(u16)); - memcpy(&msg_data[6], &vlan_info->vlan_tag, sizeof(u16)); - - return hclge_send_mbx_msg(vport, msg_data, sizeof(msg_data), + return hclge_send_mbx_msg(vport, (u8 *)&base_vlan, sizeof(base_vlan), HCLGE_MBX_PUSH_VLAN_INFO, vfid); }

@@ -488,10 +488,9 @@ int hclge_push_vf_link_status(struct hclge_vport *vport) #define HCLGE_VF_LINK_STATE_UP 1U #define HCLGE_VF_LINK_STATE_DOWN 0U

+ struct hclge_mbx_link_status link_info; struct hclge_dev *hdev = vport->back; u16 link_status; - u8 msg_data[9]; - u16 duplex;

/* mac.link can only be 0 or 1 */ switch (vport->vf_info.link_state) { @@ -507,14 +506,13 @@ int hclge_push_vf_link_status(struct hclge_vport *vport) break; }

- duplex = hdev->hw.mac.duplex; - memcpy(&msg_data[0], &link_status, sizeof(u16)); - memcpy(&msg_data[2], &hdev->hw.mac.speed, sizeof(u32)); - memcpy(&msg_data[6], &duplex, sizeof(u16)); - msg_data[8] = HCLGE_MBX_PUSH_LINK_STATUS_EN; + link_info.link_status = cpu_to_le16(link_status); + link_info.speed = cpu_to_le32(hdev->hw.mac.speed); + link_info.duplex = cpu_to_le16(hdev->hw.mac.duplex); + link_info.flag = HCLGE_MBX_PUSH_LINK_STATUS_EN;

/* send this requested info to VF */ - return hclge_send_mbx_msg(vport, msg_data, sizeof(msg_data), + return hclge_send_mbx_msg(vport, (u8 *)&link_info, sizeof(link_info), HCLGE_MBX_LINK_STAT_CHANGE, vport->vport_id); }

@@ -522,22 +520,22 @@ static void hclge_get_link_mode(struct hclge_vport *vport, struct hclge_mbx_vf_to_pf_cmd *mbx_req) { #define HCLGE_SUPPORTED 1 + struct hclge_mbx_link_mode link_mode; struct hclge_dev *hdev = vport->back; unsigned long advertising; unsigned long supported; unsigned long send_data; - u8 msg_data[10] = {}; u8 dest_vfid;

advertising = hdev->hw.mac.advertising[0]; supported = hdev->hw.mac.supported[0]; dest_vfid = mbx_req->mbx_src_vfid; - msg_data[0] = mbx_req->msg.data[0]; - - send_data = msg_data[0] == HCLGE_SUPPORTED ? supported : advertising; + send_data = mbx_req->msg.data[0] == HCLGE_SUPPORTED ? supported : + advertising; + link_mode.idx = cpu_to_le16((u16)mbx_req->msg.data[0]); + link_mode.link_mode = cpu_to_le64(send_data);

- memcpy(&msg_data[2], &send_data, sizeof(unsigned long)); - hclge_send_mbx_msg(vport, msg_data, sizeof(msg_data), + hclge_send_mbx_msg(vport, (u8 *)&link_mode, sizeof(link_mode), HCLGE_MBX_LINK_STAT_MODE, dest_vfid); }

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_trace.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_trace.h index 5b0b71bd6120..8510b88d4982 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_trace.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_trace.h @@ -62,7 +62,7 @@ TRACE_EVENT(hclge_pf_mbx_send,

TP_fast_assign( __entry->vfid = req->dest_vfid; - __entry->code = req->msg.code; + __entry->code = le16_to_cpu(req->msg.code); __assign_str(pciname, pci_name(hdev->pdev)); __assign_str(devname, &hdev->vport[0].nic.kinfo.netdev->name); memcpy(__entry->mbx_data, req, diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c index cbb2a8891c52..052b7781f1b4 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c @@ -3333,7 +3333,7 @@ static void hclgevf_get_regs(struct hnae3_handle *handle, u32 *version, }

void hclgevf_update_port_base_vlan_info(struct hclgevf_dev *hdev, u16 state, - u8 *port_base_vlan_info, u8 data_size) + struct hclge_mbx_port_base_vlan *port_base_vlan) { struct hnae3_handle *nic = &hdev->nic; struct hclge_vf_to_pf_msg send_msg; @@ -3358,7 +3358,7 @@ void hclgevf_update_port_base_vlan_info(struct hclgevf_dev *hdev, u16 state, /* send msg to PF and wait update port based vlan info */ hclgevf_build_send_msg(&send_msg, HCLGE_MBX_SET_VLAN, HCLGE_MBX_PORT_BASE_VLAN_CFG); - memcpy(send_msg.data, port_base_vlan_info, data_size); + memcpy(send_msg.data, port_base_vlan, sizeof(*port_base_vlan)); ret = hclgevf_send_mbx_msg(hdev, &send_msg, false, NULL, 0); if (!ret) { if (state == HNAE3_PORT_BASE_VLAN_DISABLE) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h index 4b00fd44f118..59ca6c794d6d 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h @@ -293,5 +293,5 @@ void hclgevf_update_speed_duplex(struct hclgevf_dev *hdev, u32 speed, void hclgevf_reset_task_schedule(struct hclgevf_dev *hdev); void hclgevf_mbx_task_schedule(struct hclgevf_dev *hdev); void hclgevf_update_port_base_vlan_info(struct hclgevf_dev *hdev, u16 state, - u8 *port_base_vlan_info, u8 data_size); + struct hclge_mbx_port_base_vlan *port_base_vlan); #endif diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c index c8055d69255c..bbf7b14079de 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c @@ -124,7 +124,7 @@ int hclgevf_send_mbx_msg(struct hclgevf_dev *hdev, if (need_resp) { mutex_lock(&hdev->mbx_resp.mbx_mutex); hclgevf_reset_mbx_resp_status(hdev); - req->match_id = hdev->mbx_resp.match_id; + req->match_id = cpu_to_le16(hdev->mbx_resp.match_id); status = hclgevf_cmd_send(&hdev->hw, &desc, 1); if (status) { dev_err(&hdev->pdev->dev, @@ -162,27 +162,29 @@ static bool hclgevf_cmd_crq_empty(struct hclgevf_hw *hw) static void hclgevf_handle_mbx_response(struct hclgevf_dev *hdev, struct hclge_mbx_pf_to_vf_cmd *req) { + u16 vf_mbx_msg_subcode = le16_to_cpu(req->msg.vf_mbx_msg_subcode); + u16 vf_mbx_msg_code = le16_to_cpu(req->msg.vf_mbx_msg_code); struct hclgevf_mbx_resp_status *resp = &hdev->mbx_resp; + u16 resp_status = le16_to_cpu(req->msg.resp_status); + u16 match_id = le16_to_cpu(req->match_id);

if (resp->received_resp) dev_warn(&hdev->pdev->dev, - "VF mbx resp flag not clear(%u)\n", - req->msg.vf_mbx_msg_code); - - resp->origin_mbx_msg = - (req->msg.vf_mbx_msg_code << 16); - resp->origin_mbx_msg |= req->msg.vf_mbx_msg_subcode; - resp->resp_status = - hclgevf_resp_to_errno(req->msg.resp_status); + "VF mbx resp flag not clear(%u)\n", + vf_mbx_msg_code); + + resp->origin_mbx_msg = (vf_mbx_msg_code << 16); + resp->origin_mbx_msg |= vf_mbx_msg_subcode; + resp->resp_status = hclgevf_resp_to_errno(resp_status); memcpy(resp->additional_info, req->msg.resp_data, HCLGE_MBX_MAX_RESP_DATA_SIZE * sizeof(u8)); - if (req->match_id) { + if (match_id) { /* If match_id is not zero, it means PF support match_id. * if the match_id is right, VF get the right response, or * ignore the response. and driver will clear hdev->mbx_resp * when send next message which need response. */ - if (req->match_id == resp->match_id) + if (match_id == resp->match_id) resp->received_resp = true; } else { resp->received_resp = true; @@ -199,7 +201,7 @@ static void hclgevf_handle_mbx_msg(struct hclgevf_dev *hdev, HCLGE_MBX_MAX_ARQ_MSG_NUM) { dev_warn(&hdev->pdev->dev, "Async Q full, dropping msg(%u)\n", - req->msg.code); + le16_to_cpu(req->msg.code)); return; }

@@ -218,6 +220,7 @@ void hclgevf_mbx_handler(struct hclgevf_dev *hdev) struct hclge_comm_cmq_ring *crq; struct hclge_desc *desc; u16 flag; + u16 code;

crq = &hdev->hw.hw.cmq.crq;

@@ -232,10 +235,11 @@ void hclgevf_mbx_handler(struct hclgevf_dev *hdev) req = (struct hclge_mbx_pf_to_vf_cmd *)desc->data;

flag = le16_to_cpu(crq->desc[crq->next_to_use].flag); + code = le16_to_cpu(req->msg.code); if (unlikely(!hnae3_get_bit(flag, HCLGEVF_CMDQ_RX_OUTVLD_B))) { dev_warn(&hdev->pdev->dev, "dropped invalid mailbox message, code = %u\n", - req->msg.code); + code);

/* dropping/not processing this invalid message */ crq->desc[crq->next_to_use].flag = 0; @@ -251,7 +255,7 @@ void hclgevf_mbx_handler(struct hclgevf_dev *hdev) * timeout and simultaneously queue the async messages for later * prcessing in context of mailbox task i.e. the slow path. */ - switch (req->msg.code) { + switch (code) { case HCLGE_MBX_PF_VF_RESP: hclgevf_handle_mbx_response(hdev, req); break; @@ -265,7 +269,7 @@ void hclgevf_mbx_handler(struct hclgevf_dev *hdev) default: dev_err(&hdev->pdev->dev, "VF received unsupported(%u) mbx msg from PF\n", - req->msg.code); + code); break; } crq->desc[crq->next_to_use].flag = 0; @@ -287,14 +291,18 @@ static void hclgevf_parse_promisc_info(struct hclgevf_dev *hdev,

void hclgevf_mbx_async_handler(struct hclgevf_dev *hdev) { + struct hclge_mbx_port_base_vlan *vlan_info; + struct hclge_mbx_link_status *link_info; + struct hclge_mbx_link_mode *link_mode; enum hnae3_reset_type reset_type; u16 link_status, state; - u16 *msg_q, *vlan_info; + __le16 *msg_q; + u16 opcode; u8 duplex; u32 speed; u32 tail; u8 flag; - u8 idx; + u16 idx;

tail = hdev->arq.tail;

@@ -308,13 +316,14 @@ void hclgevf_mbx_async_handler(struct hclgevf_dev *hdev) }

msg_q = hdev->arq.msg_q[hdev->arq.head]; - - switch (msg_q[0]) { + opcode = le16_to_cpu(msg_q[0]); + switch (opcode) { case HCLGE_MBX_LINK_STAT_CHANGE: - link_status = msg_q[1]; - memcpy(&speed, &msg_q[2], sizeof(speed)); - duplex = (u8)msg_q[4]; - flag = (u8)msg_q[5]; + link_info = (struct hclge_mbx_link_status *)(msg_q + 1); + link_status = le16_to_cpu(link_info->link_status); + speed = le32_to_cpu(link_info->speed); + duplex = (u8)le16_to_cpu(link_info->duplex); + flag = link_info->flag;

/* update upper layer with new link link status */ hclgevf_update_speed_duplex(hdev, speed, duplex); @@ -326,13 +335,14 @@ void hclgevf_mbx_async_handler(struct hclgevf_dev *hdev)

break; case HCLGE_MBX_LINK_STAT_MODE: - idx = (u8)msg_q[1]; + link_mode = (struct hclge_mbx_link_mode *)(msg_q + 1); + idx = le16_to_cpu(link_mode->idx); if (idx) - memcpy(&hdev->hw.mac.supported, &msg_q[2], - sizeof(unsigned long)); + hdev->hw.mac.supported = + le64_to_cpu(link_mode->link_mode); else - memcpy(&hdev->hw.mac.advertising, &msg_q[2], - sizeof(unsigned long)); + hdev->hw.mac.advertising = + le64_to_cpu(link_mode->link_mode); break; case HCLGE_MBX_ASSERTING_RESET: /* PF has asserted reset hence VF should go in pending @@ -340,25 +350,27 @@ void hclgevf_mbx_async_handler(struct hclgevf_dev *hdev) * has been completely reset. After this stack should * eventually be re-initialized. */ - reset_type = (enum hnae3_reset_type)msg_q[1]; + reset_type = + (enum hnae3_reset_type)le16_to_cpu(msg_q[1]); set_bit(reset_type, &hdev->reset_pending); set_bit(HCLGEVF_RESET_PENDING, &hdev->reset_state); hclgevf_reset_task_schedule(hdev);

break; case HCLGE_MBX_PUSH_VLAN_INFO: - state = msg_q[1]; - vlan_info = &msg_q[1]; + vlan_info = + (struct hclge_mbx_port_base_vlan *)(msg_q + 1); + state = le16_to_cpu(vlan_info->state); hclgevf_update_port_base_vlan_info(hdev, state, - (u8 *)vlan_info, 8); + vlan_info); break; case HCLGE_MBX_PUSH_PROMISC_INFO: - hclgevf_parse_promisc_info(hdev, msg_q[1]); + hclgevf_parse_promisc_info(hdev, le16_to_cpu(msg_q[1])); break; default: dev_err(&hdev->pdev->dev, "fetched unsupported(%u) message from arq\n", - msg_q[0]); + opcode); break; }

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_trace.h b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_trace.h index e4bfb6191fef..5d4895bb57a1 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_trace.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_trace.h @@ -29,7 +29,7 @@ TRACE_EVENT(hclge_vf_mbx_get,

TP_fast_assign( __entry->vfid = req->dest_vfid; - __entry->code = req->msg.code; + __entry->code = le16_to_cpu(req->msg.code); __assign_str(pciname, pci_name(hdev->pdev)); __assign_str(devname, &hdev->nic.kinfo.netdev->name); memcpy(__entry->mbx_data, req,

From: Guangbin Huang huangguangbin2@huawei.com

mainline inclusion from mainline-origin commit a1aed456e326 category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I56XHY CVE: NA

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i...

----------------------------------------------------------------------

This patch adds a new mailbox opcode to query map relation between vf ring and vector.

Signed-off-by: Guangbin Huang huangguangbin2@huawei.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Jiantao Xiao xiaojiantao1@h-partners.com Reviewed-by: Yue Haibing yuehaibing@huawei.com Reviewed-by: Jian Shen shenjian15@huawei.com Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com --- .../net/ethernet/hisilicon/hns3/hclge_mbx.h | 1 + .../hisilicon/hns3/hns3pf/hclge_mbx.c | 83 +++++++++++++++++++ 2 files changed, 84 insertions(+)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h b/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h index c52876555d4b..7d4ae467f3ad 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h +++ b/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h @@ -46,6 +46,7 @@ enum HCLGE_MBX_OPCODE { HCLGE_MBX_PUSH_PROMISC_INFO, /* (PF -> VF) push vf promisc info */ HCLGE_MBX_VF_UNINIT, /* (VF -> PF) vf is unintializing */ HCLGE_MBX_HANDLE_VF_TBL, /* (VF -> PF) store/clear hw table */ + HCLGE_MBX_GET_RING_VECTOR_MAP, /* (VF -> PF) get ring-to-vector map */

HCLGE_MBX_GET_VF_FLR_STATUS = 200, /* (M7 -> PF) get vf flr status */ HCLGE_MBX_PUSH_LINK_STATUS, /* (M7 -> PF) get port link status */ diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c index 6957b5e158c9..e1012f7f9b73 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c @@ -251,6 +251,81 @@ static int hclge_map_unmap_ring_to_vf_vector(struct hclge_vport *vport, bool en, return ret; }

+static int hclge_query_ring_vector_map(struct hclge_vport *vport, + struct hnae3_ring_chain_node *ring_chain, + struct hclge_desc *desc) +{ + struct hclge_ctrl_vector_chain_cmd *req = + (struct hclge_ctrl_vector_chain_cmd *)desc->data; + struct hclge_dev *hdev = vport->back; + u16 tqp_type_and_id; + int status; + + hclge_cmd_setup_basic_desc(desc, HCLGE_OPC_ADD_RING_TO_VECTOR, true); + + tqp_type_and_id = le16_to_cpu(req->tqp_type_and_id[0]); + hnae3_set_field(tqp_type_and_id, HCLGE_INT_TYPE_M, HCLGE_INT_TYPE_S, + hnae3_get_bit(ring_chain->flag, HNAE3_RING_TYPE_B)); + hnae3_set_field(tqp_type_and_id, HCLGE_TQP_ID_M, HCLGE_TQP_ID_S, + ring_chain->tqp_index); + req->tqp_type_and_id[0] = cpu_to_le16(tqp_type_and_id); + req->vfid = vport->vport_id; + + status = hclge_cmd_send(&hdev->hw, desc, 1); + if (status) + dev_err(&hdev->pdev->dev, + "Get VF ring vector map info fail, status is %d.\n", + status); + + return status; +} + +static int hclge_get_vf_ring_vector_map(struct hclge_vport *vport, + struct hclge_mbx_vf_to_pf_cmd *req, + struct hclge_respond_to_vf_msg *resp) +{ +#define HCLGE_LIMIT_RING_NUM 1 +#define HCLGE_RING_TYPE_OFFSET 0 +#define HCLGE_TQP_INDEX_OFFSET 1 +#define HCLGE_INT_GL_INDEX_OFFSET 2 +#define HCLGE_VECTOR_ID_OFFSET 3 +#define HCLGE_RING_VECTOR_MAP_INFO_LEN 4 + struct hnae3_ring_chain_node ring_chain; + struct hclge_desc desc; + struct hclge_ctrl_vector_chain_cmd *data = + (struct hclge_ctrl_vector_chain_cmd *)desc.data; + u16 tqp_type_and_id; + u8 int_gl_index; + int ret; + + req->msg.ring_num = HCLGE_LIMIT_RING_NUM; + + memset(&ring_chain, 0, sizeof(ring_chain)); + ret = hclge_get_ring_chain_from_mbx(req, &ring_chain, vport); + if (ret) + return ret; + + ret = hclge_query_ring_vector_map(vport, &ring_chain, &desc); + if (ret) { + hclge_free_vector_ring_chain(&ring_chain); + return ret; + } + + tqp_type_and_id = le16_to_cpu(data->tqp_type_and_id[0]); + int_gl_index = hnae3_get_field(tqp_type_and_id, + HCLGE_INT_GL_IDX_M, HCLGE_INT_GL_IDX_S); + + resp->data[HCLGE_RING_TYPE_OFFSET] = req->msg.param[0].ring_type; + resp->data[HCLGE_TQP_INDEX_OFFSET] = req->msg.param[0].tqp_index; + resp->data[HCLGE_INT_GL_INDEX_OFFSET] = int_gl_index; + resp->data[HCLGE_VECTOR_ID_OFFSET] = data->int_vector_id_l; + resp->len = HCLGE_RING_VECTOR_MAP_INFO_LEN; + + hclge_free_vector_ring_chain(&ring_chain); + + return ret; +} + static void hclge_set_vf_promisc_mode(struct hclge_vport *vport, struct hclge_mbx_vf_to_pf_cmd *req) { @@ -755,6 +830,14 @@ void hclge_mbx_handler(struct hclge_dev *hdev) ret = hclge_map_unmap_ring_to_vf_vector(vport, false, req); break; + case HCLGE_MBX_GET_RING_VECTOR_MAP: + ret = hclge_get_vf_ring_vector_map(vport, req, + &resp_msg); + if (ret) + dev_err(&hdev->pdev->dev, + "PF fail(%d) to get VF ring vector map\n", + ret); + break; case HCLGE_MBX_SET_PROMISC_MODE: hclge_set_vf_promisc_mode(vport, req); break;

From: Ming Lei ming.lei@redhat.com

mainline inclusion from mainline-v5.16-rc2 commit 2a19b28f7929866e1cec92a3619f4de9f2d20005 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I58VDJ CVE: NA

Reference: https://lore.kernel.org/all/20211116014343.610501-1-ming.lei

--------------------------------

For avoiding to slow down queue destroy, we don't call blk_mq_quiesce_queue() in blk_cleanup_queue(), instead of delaying to cancel dispatch work in blk_release_queue().

However, this way has caused kernel oops[1], reported by Changhui. The log shows that scsi_device can be freed before running blk_release_queue(), which is expected too since scsi_device is released after the scsi disk is closed and the scsi_device is removed.

Fixes the issue by canceling blk-mq dispatch work in both blk_cleanup_queue() and disk_release():

1) when disk_release() is run, the disk has been closed, and any sync dispatch activities have been done, so canceling dispatch work is enough to quiesce filesystem I/O dispatch activity.

2) in blk_cleanup_queue(), we only focus on passthrough request, and passthrough request is always explicitly allocated & freed by its caller, so once queue is frozen, all sync dispatch activity for passthrough request has been done, then it is enough to just cancel dispatch work for avoiding any dispatch activity.

[1] kernel panic log [12622.769416] BUG: kernel NULL pointer dereference, address: 0000000000000300 [12622.777186] #PF: supervisor read access in kernel mode [12622.782918] #PF: error_code(0x0000) - not-present page [12622.788649] PGD 0 P4D 0 [12622.791474] Oops: 0000 [#1] PREEMPT SMP PTI [12622.796138] CPU: 10 PID: 744 Comm: kworker/10:1H Kdump: loaded Not tainted 5.15.0+ #1 [12622.804877] Hardware name: Dell Inc. PowerEdge R730/0H21J3, BIOS 1.5.4 10/002/2015 [12622.813321] Workqueue: kblockd blk_mq_run_work_fn [12622.818572] RIP: 0010:sbitmap_get+0x75/0x190 [12622.823336] Code: 85 80 00 00 00 41 8b 57 08 85 d2 0f 84 b1 00 00 00 45 31 e4 48 63 cd 48 8d 1c 49 48 c1 e3 06 49 03 5f 10 4c 8d 6b 40 83 f0 01 <48> 8b 33 44 89 f2 4c 89 ef 0f b6 c8 e8 fa f3 ff ff 83 f8 ff 75 58 [12622.844290] RSP: 0018:ffffb00a446dbd40 EFLAGS: 00010202 [12622.850120] RAX: 0000000000000001 RBX: 0000000000000300 RCX: 0000000000000004 [12622.858082] RDX: 0000000000000006 RSI: 0000000000000082 RDI: ffffa0b7a2dfe030 [12622.866042] RBP: 0000000000000004 R08: 0000000000000001 R09: ffffa0b742721334 [12622.874003] R10: 0000000000000008 R11: 0000000000000008 R12: 0000000000000000 [12622.881964] R13: 0000000000000340 R14: 0000000000000000 R15: ffffa0b7a2dfe030 [12622.889926] FS: 0000000000000000(0000) GS:ffffa0baafb40000(0000) knlGS:0000000000000000 [12622.898956] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [12622.905367] CR2: 0000000000000300 CR3: 0000000641210001 CR4: 00000000001706e0 [12622.913328] Call Trace: [12622.916055] <TASK> [12622.918394] scsi_mq_get_budget+0x1a/0x110 [12622.922969] __blk_mq_do_dispatch_sched+0x1d4/0x320 [12622.928404] ? pick_next_task_fair+0x39/0x390 [12622.933268] __blk_mq_sched_dispatch_requests+0xf4/0x140 [12622.939194] blk_mq_sched_dispatch_requests+0x30/0x60 [12622.944829] __blk_mq_run_hw_queue+0x30/0xa0 [12622.949593] process_one_work+0x1e8/0x3c0 [12622.954059] worker_thread+0x50/0x3b0 [12622.958144] ? rescuer_thread+0x370/0x370 [12622.962616] kthread+0x158/0x180 [12622.966218] ? set_kthread_struct+0x40/0x40 [12622.970884] ret_from_fork+0x22/0x30 [12622.974875] </TASK> [12622.977309] Modules linked in: scsi_debug rpcsec_gss_krb5 auth_rpcgss nfsv4 dns_resolver nfs lockd grace fscache netfs sunrpc dm_multipath intel_rapl_msr intel_rapl_common dell_wmi_descriptor sb_edac rfkill video x86_pkg_temp_thermal intel_powerclamp dcdbas coretemp kvm_intel kvm mgag200 irqbypass i2c_algo_bit rapl drm_kms_helper ipmi_ssif intel_cstate intel_uncore syscopyarea sysfillrect sysimgblt fb_sys_fops pcspkr cec mei_me lpc_ich mei ipmi_si ipmi_devintf ipmi_msghandler acpi_power_meter drm fuse xfs libcrc32c sr_mod cdrom sd_mod t10_pi sg ixgbe ahci libahci crct10dif_pclmul crc32_pclmul crc32c_intel libata megaraid_sas ghash_clmulni_intel tg3 wdat_wdt mdio dca wmi dm_mirror dm_region_hash dm_log dm_mod [last unloaded: scsi_debug]

Reported-by: ChanghuiZhong czhong@redhat.com Cc: Christoph Hellwig hch@lst.de Cc: "Martin K. Petersen" martin.petersen@oracle.com Cc: Bart Van Assche bvanassche@acm.org Cc: linux-scsi@vger.kernel.org Signed-off-by: Ming Lei ming.lei@redhat.com Link: https://lore.kernel.org/r/20211116014343.610501-1-ming.lei@redhat.com Signed-off-by: Jens Axboe axboe@kernel.dk

Conflict: commit 1509607853c0 ("block: avoid quiesce while elevator init") introduced blk_mq_cancel_work_sync() already. Signed-off-by: Yu Kuai yukuai3@huawei.com Reviewed-by: Jason Yan yanaijie@huawei.com Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com --- block/blk-core.c | 4 +++- block/blk-sysfs.c | 10 ---------- block/genhd.c | 1 + 3 files changed, 4 insertions(+), 11 deletions(-)

diff --git a/block/blk-core.c b/block/blk-core.c index 9e43501d7759..bbd3d4560458 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -398,8 +398,10 @@ void blk_cleanup_queue(struct request_queue *q) del_timer_sync(&q->backing_dev_info->laptop_mode_wb_timer); blk_sync_queue(q);

- if (queue_is_mq(q)) + if (queue_is_mq(q)) { + blk_mq_cancel_work_sync(q); blk_mq_exit_queue(q); + }

/* * In theory, request pool of sched_tags belongs to request queue. diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index 751b7b0bec88..65f4f2d3f30f 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -790,16 +790,6 @@ static void blk_release_queue(struct kobject *kobj)

blk_free_queue_stats(q->stats);

- if (queue_is_mq(q)) { - struct blk_mq_hw_ctx *hctx; - int i; - - cancel_delayed_work_sync(&q->requeue_work); - - queue_for_each_hw_ctx(q, hctx, i) - cancel_delayed_work_sync(&hctx->run_work); - } - blk_exit_queue(q);

blk_queue_free_zone_bitmaps(q); diff --git a/block/genhd.c b/block/genhd.c index f94152e99876..5b6cd992c6a6 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -1572,6 +1572,7 @@ static void disk_release(struct device *dev) might_sleep();

blk_free_devt(dev->devt); + blk_mq_cancel_work_sync(disk->queue); disk_release_events(disk); kfree(disk->random); disk_replace_part_tbl(disk, NULL);

From: Yu Kuai yukuai3@huawei.com

hulk inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I58VDJ CVE: NA

--------------------------------

bfq_has_work() is using busy_queues currently, which is not accurate because bfq_queue is busy doesn't represent that it has requests. Since bfqd aready has a counter 'queued' to record how many requests are in bfq, use it instead of busy_queues.

Noted that bfq_has_work() can be called with 'bfqd->lock' held, thus the lock can't be held in bfq_has_work() to protect 'bfqd->queued'.

Signed-off-by: Yu Kuai yukuai3@huawei.com Reviewed-by: Jan Kara jack@suse.cz Reviewed-by: Jason Yan yanaijie@huawei.com Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com --- block/bfq-iosched.c | 16 ++++++++++++---- 1 file changed, 12 insertions(+), 4 deletions(-)

diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c index b5da3ad76d77..940184335104 100644 --- a/block/bfq-iosched.c +++ b/block/bfq-iosched.c @@ -1871,7 +1871,11 @@ static void bfq_add_request(struct request *rq)

bfq_log_bfqq(bfqd, bfqq, "add_request %d", rq_is_sync(rq)); bfqq->queued[rq_is_sync(rq)]++; - bfqd->queued++; + /* + * Updating of 'bfqd->queued' is protected by 'bfqd->lock', however, it + * may be read without holding the lock in bfq_has_work(). + */ + WRITE_ONCE(bfqd->queued, bfqd->queued + 1);

if (RB_EMPTY_ROOT(&bfqq->sort_list) && bfq_bfqq_sync(bfqq)) { /* @@ -2164,7 +2168,11 @@ static void bfq_remove_request(struct request_queue *q, if (rq->queuelist.prev != &rq->queuelist) list_del_init(&rq->queuelist); bfqq->queued[sync]--; - bfqd->queued--; + /* + * Updating of 'bfqd->queued' is protected by 'bfqd->lock', however, it + * may be read without holding the lock in bfq_has_work(). + */ + WRITE_ONCE(bfqd->queued, bfqd->queued - 1); elv_rb_del(&bfqq->sort_list, rq);

elv_rqhash_del(q, rq); @@ -4652,11 +4660,11 @@ static bool bfq_has_work(struct blk_mq_hw_ctx *hctx) struct bfq_data *bfqd = hctx->queue->elevator->elevator_data;

/* - * Avoiding lock: a race on bfqd->busy_queues should cause at + * Avoiding lock: a race on bfqd->queued should cause at * most a call to dispatch for nothing */ return !list_empty_careful(&bfqd->dispatch) || - bfq_tot_busy_queues(bfqd) > 0; + READ_ONCE(bfqd->queued); }

static struct request *__bfq_dispatch_request(struct blk_mq_hw_ctx *hctx)

From: Duoming Zhou duoming@zju.edu.cn

stable inclusion from stable-v5.10.115 commit 8a9e7c64f4a02c4c397e55ba379609168ec7df4a category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I5B79D CVE: CVE-2022-1974

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

commit da5c0f119203ad9728920456a0f52a6d850c01cd upstream.

The device_is_registered() in nfc core is used to check whether nfc device is registered in netlink related functions such as nfc_fw_download(), nfc_dev_up() and so on. Although device_is_registered() is protected by device_lock, there is still a race condition between device_del() and device_is_registered(). The root cause is that kobject_del() in device_del() is not protected by device_lock.

(cleanup task) | (netlink task) | nfc_unregister_device | nfc_fw_download device_del | device_lock ... | if (!device_is_registered)//(1) kobject_del//(2) | ... ... | device_unlock

The device_is_registered() returns the value of state_in_sysfs and the state_in_sysfs is set to zero in kobject_del(). If we pass check in position (1), then set zero in position (2). As a result, the check in position (1) is useless.

This patch uses bool variable instead of device_is_registered() to judge whether the nfc device is registered, which is well synchronized.

Fixes: 3e256b8f8dfa ("NFC: add nfc subsystem core") Signed-off-by: Duoming Zhou duoming@zju.edu.cn Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Baisong Zhong zhongbaisong@huawei.com Reviewed-by: Xiu Jianfeng xiujianfeng@huawei.com Reviewed-by: Wei Yongjun weiyongjun1@huawei.com Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com --- net/nfc/core.c | 29 ++++++++++++++--------------- 1 file changed, 14 insertions(+), 15 deletions(-)

diff --git a/net/nfc/core.c b/net/nfc/core.c index 6800470dd6df..3b2983813ff1 100644 --- a/net/nfc/core.c +++ b/net/nfc/core.c @@ -38,7 +38,7 @@ int nfc_fw_download(struct nfc_dev *dev, const char *firmware_name)

device_lock(&dev->dev);

- if (!device_is_registered(&dev->dev)) { + if (dev->shutting_down) { rc = -ENODEV; goto error; } @@ -94,7 +94,7 @@ int nfc_dev_up(struct nfc_dev *dev)

device_lock(&dev->dev);

- if (!device_is_registered(&dev->dev)) { + if (dev->shutting_down) { rc = -ENODEV; goto error; } @@ -142,7 +142,7 @@ int nfc_dev_down(struct nfc_dev *dev)

device_lock(&dev->dev);

- if (!device_is_registered(&dev->dev)) { + if (dev->shutting_down) { rc = -ENODEV; goto error; } @@ -206,7 +206,7 @@ int nfc_start_poll(struct nfc_dev *dev, u32 im_protocols, u32 tm_protocols)

device_lock(&dev->dev);

- if (!device_is_registered(&dev->dev)) { + if (dev->shutting_down) { rc = -ENODEV; goto error; } @@ -245,7 +245,7 @@ int nfc_stop_poll(struct nfc_dev *dev)

device_lock(&dev->dev);

- if (!device_is_registered(&dev->dev)) { + if (dev->shutting_down) { rc = -ENODEV; goto error; } @@ -290,7 +290,7 @@ int nfc_dep_link_up(struct nfc_dev *dev, int target_index, u8 comm_mode)

device_lock(&dev->dev);

- if (!device_is_registered(&dev->dev)) { + if (dev->shutting_down) { rc = -ENODEV; goto error; } @@ -334,7 +334,7 @@ int nfc_dep_link_down(struct nfc_dev *dev)

device_lock(&dev->dev);

- if (!device_is_registered(&dev->dev)) { + if (dev->shutting_down) { rc = -ENODEV; goto error; } @@ -400,7 +400,7 @@ int nfc_activate_target(struct nfc_dev *dev, u32 target_idx, u32 protocol)

device_lock(&dev->dev);

- if (!device_is_registered(&dev->dev)) { + if (dev->shutting_down) { rc = -ENODEV; goto error; } @@ -446,7 +446,7 @@ int nfc_deactivate_target(struct nfc_dev *dev, u32 target_idx, u8 mode)

device_lock(&dev->dev);

- if (!device_is_registered(&dev->dev)) { + if (dev->shutting_down) { rc = -ENODEV; goto error; } @@ -493,7 +493,7 @@ int nfc_data_exchange(struct nfc_dev *dev, u32 target_idx, struct sk_buff *skb,

device_lock(&dev->dev);

- if (!device_is_registered(&dev->dev)) { + if (dev->shutting_down) { rc = -ENODEV; kfree_skb(skb); goto error; @@ -550,7 +550,7 @@ int nfc_enable_se(struct nfc_dev *dev, u32 se_idx)

device_lock(&dev->dev);

- if (!device_is_registered(&dev->dev)) { + if (dev->shutting_down) { rc = -ENODEV; goto error; } @@ -599,7 +599,7 @@ int nfc_disable_se(struct nfc_dev *dev, u32 se_idx)

device_lock(&dev->dev);

- if (!device_is_registered(&dev->dev)) { + if (dev->shutting_down) { rc = -ENODEV; goto error; } @@ -1126,6 +1126,7 @@ int nfc_register_device(struct nfc_dev *dev) dev->rfkill = NULL; } } + dev->shutting_down = false; device_unlock(&dev->dev);

rc = nfc_genl_device_added(dev); @@ -1158,12 +1159,10 @@ void nfc_unregister_device(struct nfc_dev *dev) rfkill_unregister(dev->rfkill); rfkill_destroy(dev->rfkill); } + dev->shutting_down = true; device_unlock(&dev->dev);

if (dev->ops->check_presence) { - device_lock(&dev->dev); - dev->shutting_down = true; - device_unlock(&dev->dev); del_timer_sync(&dev->check_pres_timer); cancel_work_sync(&dev->check_pres_work); }

From: Pavel Begunkov asml.silence@gmail.com

stable inclusion from stable-v5.10.119 commit 8adb751d294ed3b668f1c7e41bd7ebe49002a744 category: bugfix bugzilla: 186671,https://gitee.com/src-openeuler/kernel/issues/I56MH6 CVE: CVE-2022-1508

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

[ upstream commit cd65869512ab5668a5d16f789bc4da1319c435c4 ]

The issue was first described and addressed in 89c2b3b7491820 ("io_uring: reexpand under-reexpanded iters"), but shortly after reimplemented as. cd65869512ab56 ("io_uring: use iov_iter state save/restore helpers").

Here we follow the approach from the second patch but without in-callback resubmissions, fixups for not yet supported in 5.10 short read retries and replacing iov_iter_state with iter copies to not pull even more dependencies, and because it's just much simpler.

Signed-off-by: Pavel Begunkov asml.silence@gmail.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Guo Xuenan guoxuenan@huawei.com Reviewed-by: Xiu Jianfeng xiujianfeng@huawei.com Reviewed-by: Zhang Yi yi.zhang@huawei.com Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com --- fs/io_uring.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/fs/io_uring.c b/fs/io_uring.c index 8a565b77dbeb..438b5782e412 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -3383,6 +3383,7 @@ static int io_read(struct io_kiocb *req, bool force_nonblock, struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs; struct kiocb *kiocb = &req->rw.kiocb; struct iov_iter __iter, *iter = &__iter; + struct iov_iter iter_cp; struct io_async_rw *rw = req->async_data; ssize_t io_size, ret, ret2; bool no_async; @@ -3393,6 +3394,7 @@ static int io_read(struct io_kiocb *req, bool force_nonblock, ret = io_import_iovec(READ, req, &iovec, iter, !force_nonblock); if (ret < 0) return ret; + iter_cp = *iter; io_size = iov_iter_count(iter); req->result = io_size; ret = 0; @@ -3428,7 +3430,7 @@ static int io_read(struct io_kiocb *req, bool force_nonblock, if (req->file->f_flags & O_NONBLOCK) goto done; /* some cases will consume bytes even on error returns */ - iov_iter_revert(iter, io_size - iov_iter_count(iter)); + *iter = iter_cp; ret = 0; goto copy_iov; } else if (ret < 0) { @@ -3511,6 +3513,7 @@ static int io_write(struct io_kiocb *req, bool force_nonblock, struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs; struct kiocb *kiocb = &req->rw.kiocb; struct iov_iter __iter, *iter = &__iter; + struct iov_iter iter_cp; struct io_async_rw *rw = req->async_data; ssize_t ret, ret2, io_size;

@@ -3520,6 +3523,7 @@ static int io_write(struct io_kiocb *req, bool force_nonblock, ret = io_import_iovec(WRITE, req, &iovec, iter, !force_nonblock); if (ret < 0) return ret; + iter_cp = *iter; io_size = iov_iter_count(iter); req->result = io_size;

@@ -3581,7 +3585,7 @@ static int io_write(struct io_kiocb *req, bool force_nonblock, } else { copy_iov: /* some cases will consume bytes even on error returns */ - iov_iter_revert(iter, io_size - iov_iter_count(iter)); + *iter = iter_cp; ret = io_setup_async_rw(req, iovec, inline_vecs, iter, false); if (!ret) return -EAGAIN;

From: Qi Zheng zhengqi.arch@bytedance.com

mainline inclusion from mainline-v5.16-rc1 commit bc9bbb81730ea667c31c5b284f95ee312bab466f category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5BLBZ CVE: NA

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i...

--------------------------------

Currently, the kernel CONFIG_UNWINDER_ORC option is enabled by default on x86, but the implementation of get_wchan() is still based on the frame pointer unwinder, so the /proc/<pid>/wchan usually returned 0 regardless of whether the task <pid> is running.

Reimplement get_wchan() by calling stack_trace_save_tsk(), which is adapted to the ORC and frame pointer unwinders.

Fixes: ee9f8fce9964 ("x86/unwind: Add the ORC unwinder") Signed-off-by: Qi Zheng zhengqi.arch@bytedance.com Signed-off-by: Kees Cook keescook@chromium.org Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Link: https://lkml.kernel.org/r/20211008111626.271115116@infradead.org Signed-off-by: Lin Yujun linyujun809@huawei.com Reviewed-by: Zhang Jianhua chris.zjh@huawei.com Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com --- arch/x86/kernel/process.c | 51 +++------------------------------------ 1 file changed, 3 insertions(+), 48 deletions(-) mode change 100644 => 100755 arch/x86/kernel/process.c

diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c old mode 100644 new mode 100755 index 035cd1e1ede5..65562d0b14a6 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -918,58 +918,13 @@ unsigned long arch_randomize_brk(struct mm_struct *mm) */ unsigned long get_wchan(struct task_struct *p) { - unsigned long start, bottom, top, sp, fp, ip, ret = 0; - int count = 0; + unsigned long entry = 0;

if (p == current || p->state == TASK_RUNNING) return 0;

- if (!try_get_task_stack(p)) - return 0; - - start = (unsigned long)task_stack_page(p); - if (!start) - goto out; - - /* - * Layout of the stack page: - * - * ----------- topmax = start + THREAD_SIZE - sizeof(unsigned long) - * PADDING - * ----------- top = topmax - TOP_OF_KERNEL_STACK_PADDING - * stack - * ----------- bottom = start - * - * The tasks stack pointer points at the location where the - * framepointer is stored. The data on the stack is: - * ... IP FP ... IP FP - * - * We need to read FP and IP, so we need to adjust the upper - * bound by another unsigned long. - */ - top = start + THREAD_SIZE - TOP_OF_KERNEL_STACK_PADDING; - top -= 2 * sizeof(unsigned long); - bottom = start; - - sp = READ_ONCE(p->thread.sp); - if (sp < bottom || sp > top) - goto out; - - fp = READ_ONCE_NOCHECK(((struct inactive_task_frame *)sp)->bp); - do { - if (fp < bottom || fp > top) - goto out; - ip = READ_ONCE_NOCHECK(*(unsigned long *)(fp + sizeof(unsigned long))); - if (!in_sched_functions(ip)) { - ret = ip; - goto out; - } - fp = READ_ONCE_NOCHECK(*(unsigned long *)fp); - } while (count++ < 16 && p->state != TASK_RUNNING); - -out: - put_task_stack(p); - return ret; + stack_trace_save_tsk(p, &entry, 1, 0); + return entry; }

long do_arch_prctl_common(struct task_struct *task, int option,

From: Peter Zijlstra peterz@infradead.org

mainline inclusion from mainline-v5.16-rc2 commit 0dc636b3b757a6b747a156de613275f9d74a4a66 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5BLBZ CVE: NA

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i...

--------------------------------

When commit 5d1ceb3969b6 ("x86: Fix __get_wchan() for !STACKTRACE") moved from stacktrace to native unwind_*() usage, the try_get_task_stack() got lost, leading to use-after-free issues for dying tasks.

Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Fixes: 5d1ceb3969b6 ("x86: Fix __get_wchan() for !STACKTRACE") Link: https://bugzilla.kernel.org/show_bug.cgi?id=215031 Link: https://lore.kernel.org/stable/YZV02RCRVHIa144u@fedora64.linuxtx.org/ Reported-by: Justin Forbes jmforbes@linuxtx.org Reported-by: Holger Hoffstätte holger@applied-asynchrony.com Cc: Qi Zheng zhengqi.arch@bytedance.com Cc: Kees Cook keescook@chromium.org Cc: Thomas Gleixner tglx@linutronix.de Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Lin Yujun linyujun809@huawei.com Reviewed-by: Zhang Jianhua chris.zjh@huawei.com Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com --- arch/x86/kernel/process.c | 5 +++++ 1 file changed, 5 insertions(+)

diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 5bdb9a329f59..ca588a3ac01b 100755 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -925,6 +925,9 @@ unsigned long get_wchan(struct task_struct *p) if (p == current || p->state == TASK_RUNNING) return 0;

+ if (!try_get_task_stack(p)) + return 0; + for (unwind_start(&state, p, NULL, NULL); !unwind_done(&state); unwind_next_frame(&state)) { addr = unwind_get_return_address(&state); @@ -935,6 +938,8 @@ unsigned long get_wchan(struct task_struct *p) break; }

+ put_task_stack(p); + return addr; }

From: Ye Bin yebin10@huawei.com

mainline inclusion from mainline-v5.18-rc4 commit 23e3d7f7061f8682c751c46512718f47580ad8f0 category: bugfix bugzilla: 186431, https://gitee.com/openeuler/kernel/issues/I5C04J CVE: NA

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

we got issue as follows: [ 72.796117] EXT4-fs error (device sda): ext4_journal_check_start:83: comm fallocate: Detected aborted journal [ 72.826847] EXT4-fs (sda): Remounting filesystem read-only fallocate: fallocate failed: Read-only file system [ 74.791830] jbd2_journal_commit_transaction: jh=0xffff9cfefe725d90 bh=0x0000000000000000 end delay [ 74.793597] ------------[ cut here ]------------ [ 74.794203] kernel BUG at fs/jbd2/transaction.c:2063! [ 74.794886] invalid opcode: 0000 [#1] PREEMPT SMP PTI [ 74.795533] CPU: 4 PID: 2260 Comm: jbd2/sda-8 Not tainted 5.17.0-rc8-next-20220315-dirty #150 [ 74.798327] RIP: 0010:__jbd2_journal_unfile_buffer+0x3e/0x60 [ 74.801971] RSP: 0018:ffffa828c24a3cb8 EFLAGS: 00010202 [ 74.802694] RAX: 0000000000000000 RBX: 0000000000000000 RCX: 0000000000000000 [ 74.803601] RDX: 0000000000000001 RSI: ffff9cfefe725d90 RDI: ffff9cfefe725d90 [ 74.804554] RBP: ffff9cfefe725d90 R08: 0000000000000000 R09: ffffa828c24a3b20 [ 74.805471] R10: 0000000000000001 R11: 0000000000000001 R12: ffff9cfefe725d90 [ 74.806385] R13: ffff9cfefe725d98 R14: 0000000000000000 R15: ffff9cfe833a4d00 [ 74.807301] FS: 0000000000000000(0000) GS:ffff9d01afb00000(0000) knlGS:0000000000000000 [ 74.808338] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 74.809084] CR2: 00007f2b81bf4000 CR3: 0000000100056000 CR4: 00000000000006e0 [ 74.810047] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 74.810981] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 74.811897] Call Trace: [ 74.812241] <TASK> [ 74.812566] __jbd2_journal_refile_buffer+0x12f/0x180 [ 74.813246] jbd2_journal_refile_buffer+0x4c/0xa0 [ 74.813869] jbd2_journal_commit_transaction.cold+0xa1/0x148 [ 74.817550] kjournald2+0xf8/0x3e0 [ 74.819056] kthread+0x153/0x1c0 [ 74.819963] ret_from_fork+0x22/0x30

Above issue may happen as follows: write truncate kjournald2 generic_perform_write ext4_write_begin ext4_walk_page_buffers do_journal_get_write_access ->add BJ_Reserved list ext4_journalled_write_end ext4_walk_page_buffers write_end_fn ext4_handle_dirty_metadata ***************JBD2 ABORT************** jbd2_journal_dirty_metadata -> return -EROFS, jh in reserved_list jbd2_journal_commit_transaction while (commit_transaction->t_reserved_list) jh = commit_transaction->t_reserved_list; truncate_pagecache_range do_invalidatepage ext4_journalled_invalidatepage jbd2_journal_invalidatepage journal_unmap_buffer __dispose_buffer __jbd2_journal_unfile_buffer jbd2_journal_put_journal_head ->put last ref_count __journal_remove_journal_head bh->b_private = NULL; jh->b_bh = NULL; jbd2_journal_refile_buffer(journal, jh); bh = jh2bh(jh); ->bh is NULL, later will trigger null-ptr-deref journal_free_journal_head(jh);

After commit 96f1e0974575, we no longer hold the j_state_lock while iterating over the list of reserved handles in jbd2_journal_commit_transaction(). This potentially allows the journal_head to be freed by journal_unmap_buffer while the commit codepath is also trying to free the BJ_Reserved buffers. Keeping j_state_lock held while trying extends hold time of the lock minimally, and solves this issue.

Fixes: 96f1e0974575("jbd2: avoid long hold times of j_state_lock while committing a transaction") Signed-off-by: Ye Bin yebin10@huawei.com Reviewed-by: Jan Kara jack@suse.cz Link: https://lore.kernel.org/r/20220317142137.1821590-1-yebin10@huawei.com Signed-off-by: Theodore Ts'o tytso@mit.edu

conflict: fs/jbd2/commit.c

Signed-off-by: ChenXiaoSong chenxiaosong2@huawei.com Reviewed-by: Zhang Yi yi.zhang@huawei.com Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com --- fs/jbd2/commit.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c index b121d7d434c6..867362f45cf6 100644 --- a/fs/jbd2/commit.c +++ b/fs/jbd2/commit.c @@ -501,7 +501,6 @@ void jbd2_journal_commit_transaction(journal_t *journal) } spin_unlock(&commit_transaction->t_handle_lock); commit_transaction->t_state = T_SWITCH; - write_unlock(&journal->j_state_lock);

J_ASSERT (atomic_read(&commit_transaction->t_outstanding_credits) <= journal->j_max_transaction_buffers); @@ -521,6 +520,8 @@ void jbd2_journal_commit_transaction(journal_t *journal) * has reserved. This is consistent with the existing behaviour * that multiple jbd2_journal_get_write_access() calls to the same * buffer are perfectly permissible. + * We use journal->j_state_lock here to serialize processing of + * t_reserved_list with eviction of buffers from journal_unmap_buffer(). */ while (commit_transaction->t_reserved_list) { jh = commit_transaction->t_reserved_list; @@ -540,6 +541,7 @@ void jbd2_journal_commit_transaction(journal_t *journal) jbd2_journal_refile_buffer(journal, jh); }

+ write_unlock(&journal->j_state_lock); /* * Now try to drop any written-back buffers from the journal's * checkpoint lists. We do this *before* commit because it potentially

From: ChenXiaoSong chenxiaosong2@huawei.com

stable inclusion from stable-v5.10.111 commit 45b9932b4daa928a65c9e7ad070df46132fe579a category: bugfix bugzilla: 186205, https://gitee.com/openeuler/kernel/issues/I5BZTX CVE: NA

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

[ Upstream commit b243874f6f9568b2daf1a00e9222cacdc15e159c ]

open() with O_ACCMODE|O_DIRECT flags secondly will fail.

Reproducer: 1. mount -t nfs -o vers=4.2 $server_ip:/ /mnt/ 2. fd = open("/mnt/file", O_ACCMODE|O_DIRECT|O_CREAT) 3. close(fd) 4. fd = open("/mnt/file", O_ACCMODE|O_DIRECT)

Server nfsd4_decode_share_access() will fail with error nfserr_bad_xdr when client use incorrect share access mode of 0.

Fix this by using NFS4_SHARE_ACCESS_BOTH share access mode in client, just like firstly opening.

Fixes: ce4ef7c0a8a05 ("NFS: Split out NFS v4 file operations") Signed-off-by: ChenXiaoSong chenxiaosong2@huawei.com Signed-off-by: Trond Myklebust trond.myklebust@hammerspace.com Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: ChenXiaoSong chenxiaosong2@huawei.com Reviewed-by: Zhang Xiaoxu zhangxiaoxu5@huawei.com Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com --- fs/nfs/dir.c | 10 ---------- fs/nfs/internal.h | 10 ++++++++++ fs/nfs/nfs4file.c | 6 ++++-- 3 files changed, 14 insertions(+), 12 deletions(-)

diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index 2ad56ff4752c..9f88ca7b2001 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -1628,16 +1628,6 @@ const struct dentry_operations nfs4_dentry_operations = { }; EXPORT_SYMBOL_GPL(nfs4_dentry_operations);

-static fmode_t flags_to_mode(int flags) -{ - fmode_t res = (__force fmode_t)flags & FMODE_EXEC; - if ((flags & O_ACCMODE) != O_WRONLY) - res |= FMODE_READ; - if ((flags & O_ACCMODE) != O_RDONLY) - res |= FMODE_WRITE; - return res; -} - static struct nfs_open_context *create_nfs_open_context(struct dentry *dentry, int open_flags, struct file *filp) { return alloc_nfs_open_context(dentry, flags_to_mode(open_flags), filp); diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 98554dd18a71..4c7666cd20e1 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -42,6 +42,16 @@ static inline bool nfs_lookup_is_soft_revalidate(const struct dentry *dentry) return true; }

+static inline fmode_t flags_to_mode(int flags) +{ + fmode_t res = (__force fmode_t)flags & FMODE_EXEC; + if ((flags & O_ACCMODE) != O_WRONLY) + res |= FMODE_READ; + if ((flags & O_ACCMODE) != O_RDONLY) + res |= FMODE_WRITE; + return res; +} + /* * Note: RFC 1813 doesn't limit the number of auth flavors that * a server can return, so make something up. diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c index 1fe2f612c5c9..f12494e08267 100644 --- a/fs/nfs/nfs4file.c +++ b/fs/nfs/nfs4file.c @@ -32,6 +32,7 @@ nfs4_file_open(struct inode *inode, struct file *filp) struct dentry *parent = NULL; struct inode *dir; unsigned openflags = filp->f_flags; + fmode_t f_mode; struct iattr attr; int err;

@@ -50,8 +51,9 @@ nfs4_file_open(struct inode *inode, struct file *filp) if (err) return err;

+ f_mode = filp->f_mode; if ((openflags & O_ACCMODE) == 3) - openflags--; + f_mode |= flags_to_mode(openflags);

/* We can't create new files here */ openflags &= ~(O_CREAT|O_EXCL); @@ -59,7 +61,7 @@ nfs4_file_open(struct inode *inode, struct file *filp) parent = dget_parent(dentry); dir = d_inode(parent);

- ctx = alloc_nfs_open_context(file_dentry(filp), filp->f_mode, filp); + ctx = alloc_nfs_open_context(file_dentry(filp), f_mode, filp); err = PTR_ERR(ctx); if (IS_ERR(ctx)) goto out;