diff options
Diffstat (limited to 'arch/x86')
23 files changed, 613 insertions, 277 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 0163d764ade4..1d6104ea8af0 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -2932,3 +2932,5 @@ config HAVE_ATOMIC_IOMAP source "drivers/firmware/Kconfig" source "arch/x86/kvm/Kconfig" + +source "arch/x86/Kconfig.assembler" diff --git a/arch/x86/Kconfig.assembler b/arch/x86/Kconfig.assembler new file mode 100644 index 000000000000..13de0db38d4e --- /dev/null +++ b/arch/x86/Kconfig.assembler @@ -0,0 +1,17 @@ +# SPDX-License-Identifier: GPL-2.0 +# Copyright (C) 2020 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved. + +config AS_AVX512 + def_bool $(as-instr,vpmovm2b %k1$(comma)%zmm5) + help + Supported by binutils >= 2.25 and LLVM integrated assembler + +config AS_SHA1_NI + def_bool $(as-instr,sha1msg1 %xmm0$(comma)%xmm1) + help + Supported by binutils >= 2.24 and LLVM integrated assembler + +config AS_SHA256_NI + def_bool $(as-instr,sha256msg1 %xmm0$(comma)%xmm1) + help + Supported by binutils >= 2.24 and LLVM integrated assembler diff --git a/arch/x86/Makefile b/arch/x86/Makefile index 513a55562d75..b65ec63c7db7 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -177,28 +177,6 @@ ifeq ($(ACCUMULATE_OUTGOING_ARGS), 1) KBUILD_CFLAGS += $(call cc-option,-maccumulate-outgoing-args,) endif -# Stackpointer is addressed different for 32 bit and 64 bit x86 -sp-$(CONFIG_X86_32) := esp -sp-$(CONFIG_X86_64) := rsp - -# do binutils support CFI? -cfi := $(call as-instr,.cfi_startproc\n.cfi_rel_offset $(sp-y)$(comma)0\n.cfi_endproc,-DCONFIG_AS_CFI=1) -# is .cfi_signal_frame supported too? -cfi-sigframe := $(call as-instr,.cfi_startproc\n.cfi_signal_frame\n.cfi_endproc,-DCONFIG_AS_CFI_SIGNAL_FRAME=1) -cfi-sections := $(call as-instr,.cfi_sections .debug_frame,-DCONFIG_AS_CFI_SECTIONS=1) - -# does binutils support specific instructions? -asinstr += $(call as-instr,pshufb %xmm0$(comma)%xmm0,-DCONFIG_AS_SSSE3=1) -avx_instr := $(call as-instr,vxorps %ymm0$(comma)%ymm1$(comma)%ymm2,-DCONFIG_AS_AVX=1) -avx2_instr :=$(call as-instr,vpbroadcastb %xmm0$(comma)%ymm1,-DCONFIG_AS_AVX2=1) -avx512_instr :=$(call as-instr,vpmovm2b %k1$(comma)%zmm5,-DCONFIG_AS_AVX512=1) -sha1_ni_instr :=$(call as-instr,sha1msg1 %xmm0$(comma)%xmm1,-DCONFIG_AS_SHA1_NI=1) -sha256_ni_instr :=$(call as-instr,sha256msg1 %xmm0$(comma)%xmm1,-DCONFIG_AS_SHA256_NI=1) -adx_instr := $(call as-instr,adox %r10$(comma)%r10,-DCONFIG_AS_ADX=1) - -KBUILD_AFLAGS += $(cfi) $(cfi-sigframe) $(cfi-sections) $(asinstr) $(avx_instr) $(avx2_instr) $(avx512_instr) $(sha1_ni_instr) $(sha256_ni_instr) $(adx_instr) -KBUILD_CFLAGS += $(cfi) $(cfi-sigframe) $(cfi-sections) $(asinstr) $(avx_instr) $(avx2_instr) $(avx512_instr) $(sha1_ni_instr) $(sha256_ni_instr) $(adx_instr) - KBUILD_LDFLAGS := -m elf_$(UTS_MACHINE) # diff --git a/arch/x86/crypto/Makefile b/arch/x86/crypto/Makefile index 8c2e9eadee8a..a31de0c6ccde 100644 --- a/arch/x86/crypto/Makefile +++ b/arch/x86/crypto/Makefile @@ -1,131 +1,97 @@ # SPDX-License-Identifier: GPL-2.0 # -# Arch-specific CryptoAPI modules. -# +# x86 crypto algorithms OBJECT_FILES_NON_STANDARD := y -avx_supported := $(call as-instr,vpxor %xmm0$(comma)%xmm0$(comma)%xmm0,yes,no) -avx2_supported := $(call as-instr,vpgatherdd %ymm0$(comma)(%eax$(comma)%ymm1\ - $(comma)4)$(comma)%ymm2,yes,no) -avx512_supported :=$(call as-instr,vpmovm2b %k1$(comma)%zmm5,yes,no) -sha1_ni_supported :=$(call as-instr,sha1msg1 %xmm0$(comma)%xmm1,yes,no) -sha256_ni_supported :=$(call as-instr,sha256msg1 %xmm0$(comma)%xmm1,yes,no) -adx_supported := $(call as-instr,adox %r10$(comma)%r10,yes,no) - obj-$(CONFIG_CRYPTO_GLUE_HELPER_X86) += glue_helper.o obj-$(CONFIG_CRYPTO_TWOFISH_586) += twofish-i586.o +twofish-i586-y := twofish-i586-asm_32.o twofish_glue.o +obj-$(CONFIG_CRYPTO_TWOFISH_X86_64) += twofish-x86_64.o +twofish-x86_64-y := twofish-x86_64-asm_64.o twofish_glue.o +obj-$(CONFIG_CRYPTO_TWOFISH_X86_64_3WAY) += twofish-x86_64-3way.o +twofish-x86_64-3way-y := twofish-x86_64-asm_64-3way.o twofish_glue_3way.o +obj-$(CONFIG_CRYPTO_TWOFISH_AVX_X86_64) += twofish-avx-x86_64.o +twofish-avx-x86_64-y := twofish-avx-x86_64-asm_64.o twofish_avx_glue.o + obj-$(CONFIG_CRYPTO_SERPENT_SSE2_586) += serpent-sse2-i586.o +serpent-sse2-i586-y := serpent-sse2-i586-asm_32.o serpent_sse2_glue.o +obj-$(CONFIG_CRYPTO_SERPENT_SSE2_X86_64) += serpent-sse2-x86_64.o +serpent-sse2-x86_64-y := serpent-sse2-x86_64-asm_64.o serpent_sse2_glue.o +obj-$(CONFIG_CRYPTO_SERPENT_AVX_X86_64) += serpent-avx-x86_64.o +serpent-avx-x86_64-y := serpent-avx-x86_64-asm_64.o serpent_avx_glue.o +obj-$(CONFIG_CRYPTO_SERPENT_AVX2_X86_64) += serpent-avx2.o +serpent-avx2-y := serpent-avx2-asm_64.o serpent_avx2_glue.o obj-$(CONFIG_CRYPTO_DES3_EDE_X86_64) += des3_ede-x86_64.o +des3_ede-x86_64-y := des3_ede-asm_64.o des3_ede_glue.o + obj-$(CONFIG_CRYPTO_CAMELLIA_X86_64) += camellia-x86_64.o +camellia-x86_64-y := camellia-x86_64-asm_64.o camellia_glue.o +obj-$(CONFIG_CRYPTO_CAMELLIA_AESNI_AVX_X86_64) += camellia-aesni-avx-x86_64.o +camellia-aesni-avx-x86_64-y := camellia-aesni-avx-asm_64.o camellia_aesni_avx_glue.o +obj-$(CONFIG_CRYPTO_CAMELLIA_AESNI_AVX2_X86_64) += camellia-aesni-avx2.o +camellia-aesni-avx2-y := camellia-aesni-avx2-asm_64.o camellia_aesni_avx2_glue.o + obj-$(CONFIG_CRYPTO_BLOWFISH_X86_64) += blowfish-x86_64.o -obj-$(CONFIG_CRYPTO_TWOFISH_X86_64) += twofish-x86_64.o -obj-$(CONFIG_CRYPTO_TWOFISH_X86_64_3WAY) += twofish-x86_64-3way.o -obj-$(CONFIG_CRYPTO_CHACHA20_X86_64) += chacha-x86_64.o -obj-$(CONFIG_CRYPTO_SERPENT_SSE2_X86_64) += serpent-sse2-x86_64.o -obj-$(CONFIG_CRYPTO_AES_NI_INTEL) += aesni-intel.o -obj-$(CONFIG_CRYPTO_GHASH_CLMUL_NI_INTEL) += ghash-clmulni-intel.o +blowfish-x86_64-y := blowfish-x86_64-asm_64.o blowfish_glue.o -obj-$(CONFIG_CRYPTO_CRC32C_INTEL) += crc32c-intel.o -obj-$(CONFIG_CRYPTO_SHA1_SSSE3) += sha1-ssse3.o -obj-$(CONFIG_CRYPTO_CRC32_PCLMUL) += crc32-pclmul.o -obj-$(CONFIG_CRYPTO_SHA256_SSSE3) += sha256-ssse3.o -obj-$(CONFIG_CRYPTO_SHA512_SSSE3) += sha512-ssse3.o -obj-$(CONFIG_CRYPTO_CRCT10DIF_PCLMUL) += crct10dif-pclmul.o -obj-$(CONFIG_CRYPTO_POLY1305_X86_64) += poly1305-x86_64.o +obj-$(CONFIG_CRYPTO_CAST5_AVX_X86_64) += cast5-avx-x86_64.o +cast5-avx-x86_64-y := cast5-avx-x86_64-asm_64.o cast5_avx_glue.o + +obj-$(CONFIG_CRYPTO_CAST6_AVX_X86_64) += cast6-avx-x86_64.o +cast6-avx-x86_64-y := cast6-avx-x86_64-asm_64.o cast6_avx_glue.o obj-$(CONFIG_CRYPTO_AEGIS128_AESNI_SSE2) += aegis128-aesni.o +aegis128-aesni-y := aegis128-aesni-asm.o aegis128-aesni-glue.o -obj-$(CONFIG_CRYPTO_NHPOLY1305_SSE2) += nhpoly1305-sse2.o -obj-$(CONFIG_CRYPTO_NHPOLY1305_AVX2) += nhpoly1305-avx2.o +obj-$(CONFIG_CRYPTO_CHACHA20_X86_64) += chacha-x86_64.o +chacha-x86_64-y := chacha-avx2-x86_64.o chacha-ssse3-x86_64.o chacha_glue.o +chacha-x86_64-$(CONFIG_AS_AVX512) += chacha-avx512vl-x86_64.o -# These modules require the assembler to support ADX. -ifeq ($(adx_supported),yes) - obj-$(CONFIG_CRYPTO_CURVE25519_X86) += curve25519-x86_64.o -endif - -# These modules require assembler to support AVX. -ifeq ($(avx_supported),yes) - obj-$(CONFIG_CRYPTO_CAMELLIA_AESNI_AVX_X86_64) += \ - camellia-aesni-avx-x86_64.o - obj-$(CONFIG_CRYPTO_CAST5_AVX_X86_64) += cast5-avx-x86_64.o - obj-$(CONFIG_CRYPTO_CAST6_AVX_X86_64) += cast6-avx-x86_64.o - obj-$(CONFIG_CRYPTO_TWOFISH_AVX_X86_64) += twofish-avx-x86_64.o - obj-$(CONFIG_CRYPTO_SERPENT_AVX_X86_64) += serpent-avx-x86_64.o - obj-$(CONFIG_CRYPTO_BLAKE2S_X86) += blake2s-x86_64.o -endif - -# These modules require assembler to support AVX2. -ifeq ($(avx2_supported),yes) - obj-$(CONFIG_CRYPTO_CAMELLIA_AESNI_AVX2_X86_64) += camellia-aesni-avx2.o - obj-$(CONFIG_CRYPTO_SERPENT_AVX2_X86_64) += serpent-avx2.o -endif +obj-$(CONFIG_CRYPTO_AES_NI_INTEL) += aesni-intel.o +aesni-intel-y := aesni-intel_asm.o aesni-intel_glue.o +aesni-intel-$(CONFIG_64BIT) += aesni-intel_avx-x86_64.o aes_ctrby8_avx-x86_64.o -twofish-i586-y := twofish-i586-asm_32.o twofish_glue.o -serpent-sse2-i586-y := serpent-sse2-i586-asm_32.o serpent_sse2_glue.o +obj-$(CONFIG_CRYPTO_SHA1_SSSE3) += sha1-ssse3.o +sha1-ssse3-y := sha1_avx2_x86_64_asm.o sha1_ssse3_asm.o sha1_ssse3_glue.o +sha1-ssse3-$(CONFIG_AS_SHA1_NI) += sha1_ni_asm.o -des3_ede-x86_64-y := des3_ede-asm_64.o des3_ede_glue.o -camellia-x86_64-y := camellia-x86_64-asm_64.o camellia_glue.o -blowfish-x86_64-y := blowfish-x86_64-asm_64.o blowfish_glue.o -twofish-x86_64-y := twofish-x86_64-asm_64.o twofish_glue.o -twofish-x86_64-3way-y := twofish-x86_64-asm_64-3way.o twofish_glue_3way.o -chacha-x86_64-y := chacha-ssse3-x86_64.o chacha_glue.o -serpent-sse2-x86_64-y := serpent-sse2-x86_64-asm_64.o serpent_sse2_glue.o +obj-$(CONFIG_CRYPTO_SHA256_SSSE3) += sha256-ssse3.o +sha256-ssse3-y := sha256-ssse3-asm.o sha256-avx-asm.o sha256-avx2-asm.o sha256_ssse3_glue.o +sha256-ssse3-$(CONFIG_AS_SHA256_NI) += sha256_ni_asm.o -aegis128-aesni-y := aegis128-aesni-asm.o aegis128-aesni-glue.o +obj-$(CONFIG_CRYPTO_SHA512_SSSE3) += sha512-ssse3.o +sha512-ssse3-y := sha512-ssse3-asm.o sha512-avx-asm.o sha512-avx2-asm.o sha512_ssse3_glue.o -nhpoly1305-sse2-y := nh-sse2-x86_64.o nhpoly1305-sse2-glue.o +obj-$(CONFIG_CRYPTO_BLAKE2S_X86) += blake2s-x86_64.o blake2s-x86_64-y := blake2s-core.o blake2s-glue.o -poly1305-x86_64-y := poly1305-x86_64-cryptogams.o poly1305_glue.o -ifneq ($(CONFIG_CRYPTO_POLY1305_X86_64),) -targets += poly1305-x86_64-cryptogams.S -endif - -ifeq ($(avx_supported),yes) - camellia-aesni-avx-x86_64-y := camellia-aesni-avx-asm_64.o \ - camellia_aesni_avx_glue.o - cast5-avx-x86_64-y := cast5-avx-x86_64-asm_64.o cast5_avx_glue.o - cast6-avx-x86_64-y := cast6-avx-x86_64-asm_64.o cast6_avx_glue.o - twofish-avx-x86_64-y := twofish-avx-x86_64-asm_64.o \ - twofish_avx_glue.o - serpent-avx-x86_64-y := serpent-avx-x86_64-asm_64.o \ - serpent_avx_glue.o -endif - -ifeq ($(avx2_supported),yes) - camellia-aesni-avx2-y := camellia-aesni-avx2-asm_64.o camellia_aesni_avx2_glue.o - chacha-x86_64-y += chacha-avx2-x86_64.o - serpent-avx2-y := serpent-avx2-asm_64.o serpent_avx2_glue.o - - nhpoly1305-avx2-y := nh-avx2-x86_64.o nhpoly1305-avx2-glue.o -endif - -ifeq ($(avx512_supported),yes) - chacha-x86_64-y += chacha-avx512vl-x86_64.o -endif -aesni-intel-y := aesni-intel_asm.o aesni-intel_glue.o -aesni-intel-$(CONFIG_64BIT) += aesni-intel_avx-x86_64.o aes_ctrby8_avx-x86_64.o +obj-$(CONFIG_CRYPTO_GHASH_CLMUL_NI_INTEL) += ghash-clmulni-intel.o ghash-clmulni-intel-y := ghash-clmulni-intel_asm.o ghash-clmulni-intel_glue.o -sha1-ssse3-y := sha1_ssse3_asm.o sha1_ssse3_glue.o -ifeq ($(avx2_supported),yes) -sha1-ssse3-y += sha1_avx2_x86_64_asm.o -endif -ifeq ($(sha1_ni_supported),yes) -sha1-ssse3-y += sha1_ni_asm.o -endif + +obj-$(CONFIG_CRYPTO_CRC32C_INTEL) += crc32c-intel.o crc32c-intel-y := crc32c-intel_glue.o crc32c-intel-$(CONFIG_64BIT) += crc32c-pcl-intel-asm_64.o + +obj-$(CONFIG_CRYPTO_CRC32_PCLMUL) += crc32-pclmul.o crc32-pclmul-y := crc32-pclmul_asm.o crc32-pclmul_glue.o -sha256-ssse3-y := sha256-ssse3-asm.o sha256-avx-asm.o sha256-avx2-asm.o sha256_ssse3_glue.o -ifeq ($(sha256_ni_supported),yes) -sha256-ssse3-y += sha256_ni_asm.o -endif -sha512-ssse3-y := sha512-ssse3-asm.o sha512-avx-asm.o sha512-avx2-asm.o sha512_ssse3_glue.o + +obj-$(CONFIG_CRYPTO_CRCT10DIF_PCLMUL) += crct10dif-pclmul.o crct10dif-pclmul-y := crct10dif-pcl-asm_64.o crct10dif-pclmul_glue.o +obj-$(CONFIG_CRYPTO_POLY1305_X86_64) += poly1305-x86_64.o +poly1305-x86_64-y := poly1305-x86_64-cryptogams.o poly1305_glue.o +targets += poly1305-x86_64-cryptogams.S + +obj-$(CONFIG_CRYPTO_NHPOLY1305_SSE2) += nhpoly1305-sse2.o +nhpoly1305-sse2-y := nh-sse2-x86_64.o nhpoly1305-sse2-glue.o +obj-$(CONFIG_CRYPTO_NHPOLY1305_AVX2) += nhpoly1305-avx2.o +nhpoly1305-avx2-y := nh-avx2-x86_64.o nhpoly1305-avx2-glue.o + +obj-$(CONFIG_CRYPTO_CURVE25519_X86) += curve25519-x86_64.o + quiet_cmd_perlasm = PERLASM $@ cmd_perlasm = $(PERL) $< > $@ $(obj)/%.S: $(src)/%.pl FORCE diff --git a/arch/x86/crypto/aesni-intel_avx-x86_64.S b/arch/x86/crypto/aesni-intel_avx-x86_64.S index bfa1c0b3e5b4..0cea33295287 100644 --- a/arch/x86/crypto/aesni-intel_avx-x86_64.S +++ b/arch/x86/crypto/aesni-intel_avx-x86_64.S @@ -886,7 +886,6 @@ _less_than_8_bytes_left_\@: _partial_block_done_\@: .endm # PARTIAL_BLOCK -#ifdef CONFIG_AS_AVX ############################################################################### # GHASH_MUL MACRO to implement: Data*HashKey mod (128,127,126,121,0) # Input: A and B (128-bits each, bit-reflected) @@ -1869,9 +1868,6 @@ key_256_finalize: ret SYM_FUNC_END(aesni_gcm_finalize_avx_gen2) -#endif /* CONFIG_AS_AVX */ - -#ifdef CONFIG_AS_AVX2 ############################################################################### # GHASH_MUL MACRO to implement: Data*HashKey mod (128,127,126,121,0) # Input: A and B (128-bits each, bit-reflected) @@ -2839,5 +2835,3 @@ key_256_finalize4: FUNC_RESTORE ret SYM_FUNC_END(aesni_gcm_finalize_avx_gen4) - -#endif /* CONFIG_AS_AVX2 */ diff --git a/arch/x86/crypto/aesni-intel_glue.c b/arch/x86/crypto/aesni-intel_glue.c index 75b6ea20491e..ad8a7188a2bf 100644 --- a/arch/x86/crypto/aesni-intel_glue.c +++ b/arch/x86/crypto/aesni-intel_glue.c @@ -185,7 +185,6 @@ static const struct aesni_gcm_tfm_s aesni_gcm_tfm_sse = { .finalize = &aesni_gcm_finalize, }; -#ifdef CONFIG_AS_AVX asmlinkage void aes_ctr_enc_128_avx_by8(const u8 *in, u8 *iv, void *keys, u8 *out, unsigned int num_bytes); asmlinkage void aes_ctr_enc_192_avx_by8(const u8 *in, u8 *iv, @@ -234,9 +233,6 @@ static const struct aesni_gcm_tfm_s aesni_gcm_tfm_avx_gen2 = { .finalize = &aesni_gcm_finalize_avx_gen2, }; -#endif - -#ifdef CONFIG_AS_AVX2 /* * asmlinkage void aesni_gcm_init_avx_gen4() * gcm_data *my_ctx_data, context data @@ -279,8 +275,6 @@ static const struct aesni_gcm_tfm_s aesni_gcm_tfm_avx_gen4 = { .finalize = &aesni_gcm_finalize_avx_gen4, }; -#endif - static inline struct aesni_rfc4106_gcm_ctx *aesni_rfc4106_gcm_ctx_get(struct crypto_aead *tfm) { @@ -476,7 +470,6 @@ static void ctr_crypt_final(struct crypto_aes_ctx *ctx, crypto_inc(ctrblk, AES_BLOCK_SIZE); } -#ifdef CONFIG_AS_AVX static void aesni_ctr_enc_avx_tfm(struct crypto_aes_ctx *ctx, u8 *out, const u8 *in, unsigned int len, u8 *iv) { @@ -493,7 +486,6 @@ static void aesni_ctr_enc_avx_tfm(struct crypto_aes_ctx *ctx, u8 *out, else aes_ctr_enc_256_avx_by8(in, iv, (void *)ctx, out, len); } -#endif static int ctr_crypt(struct skcipher_request *req) { @@ -711,14 +703,10 @@ static int gcmaes_crypt_by_sg(bool enc, struct aead_request *req, if (!enc) left -= auth_tag_len; -#ifdef CONFIG_AS_AVX2 if (left < AVX_GEN4_OPTSIZE && gcm_tfm == &aesni_gcm_tfm_avx_gen4) gcm_tfm = &aesni_gcm_tfm_avx_gen2; -#endif -#ifdef CONFIG_AS_AVX if (left < AVX_GEN2_OPTSIZE && gcm_tfm == &aesni_gcm_tfm_avx_gen2) gcm_tfm = &aesni_gcm_tfm_sse; -#endif /* Linearize assoc, if not already linear */ if (req->src->length >= assoclen && req->src->length && @@ -1076,31 +1064,24 @@ static int __init aesni_init(void) if (!x86_match_cpu(aesni_cpu_id)) return -ENODEV; #ifdef CONFIG_X86_64 -#ifdef CONFIG_AS_AVX2 if (boot_cpu_has(X86_FEATURE_AVX2)) { pr_info("AVX2 version of gcm_enc/dec engaged.\n"); aesni_gcm_tfm = &aesni_gcm_tfm_avx_gen4; } else -#endif -#ifdef CONFIG_AS_AVX if (boot_cpu_has(X86_FEATURE_AVX)) { pr_info("AVX version of gcm_enc/dec engaged.\n"); aesni_gcm_tfm = &aesni_gcm_tfm_avx_gen2; - } else -#endif - { + } else { pr_info("SSE version of gcm_enc/dec engaged.\n"); aesni_gcm_tfm = &aesni_gcm_tfm_sse; } aesni_ctr_enc_tfm = aesni_ctr_enc; -#ifdef CONFIG_AS_AVX if (boot_cpu_has(X86_FEATURE_AVX)) { /* optimize performance of ctr mode encryption transform */ aesni_ctr_enc_tfm = aesni_ctr_enc_avx_tfm; pr_info("AES CTR mode by8 optimization enabled\n"); } #endif -#endif err = crypto_register_alg(&aesni_cipher_alg); if (err) diff --git a/arch/x86/crypto/blake2s-core.S b/arch/x86/crypto/blake2s-core.S index 24910b766bdd..2ca79974f819 100644 --- a/arch/x86/crypto/blake2s-core.S +++ b/arch/x86/crypto/blake2s-core.S @@ -46,7 +46,6 @@ SIGMA2: #endif /* CONFIG_AS_AVX512 */ .text -#ifdef CONFIG_AS_SSSE3 SYM_FUNC_START(blake2s_compress_ssse3) testq %rdx,%rdx je .Lendofloop @@ -174,7 +173,6 @@ SYM_FUNC_START(blake2s_compress_ssse3) .Lendofloop: ret SYM_FUNC_END(blake2s_compress_ssse3) -#endif /* CONFIG_AS_SSSE3 */ #ifdef CONFIG_AS_AVX512 SYM_FUNC_START(blake2s_compress_avx512) diff --git a/arch/x86/crypto/chacha_glue.c b/arch/x86/crypto/chacha_glue.c index 68a74953efaf..b412c21ee06e 100644 --- a/arch/x86/crypto/chacha_glue.c +++ b/arch/x86/crypto/chacha_glue.c @@ -79,8 +79,7 @@ static void chacha_dosimd(u32 *state, u8 *dst, const u8 *src, } } - if (IS_ENABLED(CONFIG_AS_AVX2) && - static_branch_likely(&chacha_use_avx2)) { + if (static_branch_likely(&chacha_use_avx2)) { while (bytes >= CHACHA_BLOCK_SIZE * 8) { chacha_8block_xor_avx2(state, dst, src, bytes, nrounds); bytes -= CHACHA_BLOCK_SIZE * 8; @@ -288,8 +287,7 @@ static int __init chacha_simd_mod_init(void) static_branch_enable(&chacha_use_simd); - if (IS_ENABLED(CONFIG_AS_AVX2) && - boot_cpu_has(X86_FEATURE_AVX) && + if (boot_cpu_has(X86_FEATURE_AVX) && boot_cpu_has(X86_FEATURE_AVX2) && cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, NULL)) { static_branch_enable(&chacha_use_avx2); diff --git a/arch/x86/crypto/poly1305-x86_64-cryptogams.pl b/arch/x86/crypto/poly1305-x86_64-cryptogams.pl index 7a6b5380a46f..137edcf038cb 100644 --- a/arch/x86/crypto/poly1305-x86_64-cryptogams.pl +++ b/arch/x86/crypto/poly1305-x86_64-cryptogams.pl @@ -404,10 +404,6 @@ ___ &end_function("poly1305_emit_x86_64"); if ($avx) { -if($kernel) { - $code .= "#ifdef CONFIG_AS_AVX\n"; -} - ######################################################################## # Layout of opaque area is following. # @@ -1516,16 +1512,8 @@ $code.=<<___; ___ &end_function("poly1305_emit_avx"); -if ($kernel) { - $code .= "#endif\n"; -} - if ($avx>1) { -if ($kernel) { - $code .= "#ifdef CONFIG_AS_AVX2\n"; -} - my ($H0,$H1,$H2,$H3,$H4, $MASK, $T4,$T0,$T1,$T2,$T3, $D0,$D1,$D2,$D3,$D4) = map("%ymm$_",(0..15)); my $S4=$MASK; @@ -2816,10 +2804,6 @@ ___ poly1305_blocks_avxN(0); &end_function("poly1305_blocks_avx2"); -if($kernel) { - $code .= "#endif\n"; -} - ####################################################################### if ($avx>2) { # On entry we have input length divisible by 64. But since inner loop diff --git a/arch/x86/crypto/poly1305_glue.c b/arch/x86/crypto/poly1305_glue.c index 79bb58737d52..6dfec19f7d57 100644 --- a/arch/x86/crypto/poly1305_glue.c +++ b/arch/x86/crypto/poly1305_glue.c @@ -94,7 +94,7 @@ static void poly1305_simd_blocks(void *ctx, const u8 *inp, size_t len, BUILD_BUG_ON(PAGE_SIZE < POLY1305_BLOCK_SIZE || PAGE_SIZE % POLY1305_BLOCK_SIZE); - if (!IS_ENABLED(CONFIG_AS_AVX) || !static_branch_likely(&poly1305_use_avx) || + if (!static_branch_likely(&poly1305_use_avx) || (len < (POLY1305_BLOCK_SIZE * 18) && !state->is_base2_26) || !crypto_simd_usable()) { convert_to_base2_64(ctx); @@ -108,7 +108,7 @@ static void poly1305_simd_blocks(void *ctx, const u8 *inp, size_t len, kernel_fpu_begin(); if (IS_ENABLED(CONFIG_AS_AVX512) && static_branch_likely(&poly1305_use_avx512)) poly1305_blocks_avx512(ctx, inp, bytes, padbit); - else if (IS_ENABLED(CONFIG_AS_AVX2) && static_branch_likely(&poly1305_use_avx2)) + else if (static_branch_likely(&poly1305_use_avx2)) poly1305_blocks_avx2(ctx, inp, bytes, padbit); else poly1305_blocks_avx(ctx, inp, bytes, padbit); @@ -123,7 +123,7 @@ static void poly1305_simd_blocks(void *ctx, const u8 *inp, size_t len, static void poly1305_simd_emit(void *ctx, u8 mac[POLY1305_DIGEST_SIZE], const u32 nonce[4]) { - if (!IS_ENABLED(CONFIG_AS_AVX) || !static_branch_likely(&poly1305_use_avx)) + if (!static_branch_likely(&poly1305_use_avx)) poly1305_emit_x86_64(ctx, mac, nonce); else poly1305_emit_avx(ctx, mac, nonce); @@ -261,11 +261,10 @@ static struct shash_alg alg = { static int __init poly1305_simd_mod_init(void) { - if (IS_ENABLED(CONFIG_AS_AVX) && boot_cpu_has(X86_FEATURE_AVX) && + if (boot_cpu_has(X86_FEATURE_AVX) && cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, NULL)) static_branch_enable(&poly1305_use_avx); - if (IS_ENABLED(CONFIG_AS_AVX2) && boot_cpu_has(X86_FEATURE_AVX) && - boot_cpu_has(X86_FEATURE_AVX2) && + if (boot_cpu_has(X86_FEATURE_AVX) && boot_cpu_has(X86_FEATURE_AVX2) && cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, NULL)) static_branch_enable(&poly1305_use_avx2); if (IS_ENABLED(CONFIG_AS_AVX512) && boot_cpu_has(X86_FEATURE_AVX) && diff --git a/arch/x86/crypto/sha1_ssse3_asm.S b/arch/x86/crypto/sha1_ssse3_asm.S index 12e2d19d7402..d25668d2a1e9 100644 --- a/arch/x86/crypto/sha1_ssse3_asm.S +++ b/arch/x86/crypto/sha1_ssse3_asm.S @@ -467,8 +467,6 @@ W_PRECALC_SSSE3 */ SHA1_VECTOR_ASM sha1_transform_ssse3 -#ifdef CONFIG_AS_AVX - .macro W_PRECALC_AVX .purgem W_PRECALC_00_15 @@ -553,5 +551,3 @@ W_PRECALC_AVX * const u8 *data, int blocks); */ SHA1_VECTOR_ASM sha1_transform_avx - -#endif diff --git a/arch/x86/crypto/sha1_ssse3_glue.c b/arch/x86/crypto/sha1_ssse3_glue.c index d70b40ad594c..a801ffc10cbb 100644 --- a/arch/x86/crypto/sha1_ssse3_glue.c +++ b/arch/x86/crypto/sha1_ssse3_glue.c @@ -114,7 +114,6 @@ static void unregister_sha1_ssse3(void) crypto_unregister_shash(&sha1_ssse3_alg); } -#ifdef CONFIG_AS_AVX asmlinkage void sha1_transform_avx(struct sha1_state *state, const u8 *data, int blocks); @@ -175,13 +174,6 @@ static void unregister_sha1_avx(void) crypto_unregister_shash(&sha1_avx_alg); } -#else /* CONFIG_AS_AVX */ -static inline int register_sha1_avx(void) { return 0; } -static inline void unregister_sha1_avx(void) { } -#endif /* CONFIG_AS_AVX */ - - -#if defined(CONFIG_AS_AVX2) && (CONFIG_AS_AVX) #define SHA1_AVX2_BLOCK_OPTSIZE 4 /* optimal 4*64 bytes of SHA1 blocks */ asmlinkage void sha1_transform_avx2(struct sha1_state *state, @@ -253,11 +245,6 @@ static void unregister_sha1_avx2(void) crypto_unregister_shash(&sha1_avx2_alg); } -#else -static inline int register_sha1_avx2(void) { return 0; } -static inline void unregister_sha1_avx2(void) { } -#endif - #ifdef CONFIG_AS_SHA1_NI asmlinkage void sha1_ni_transform(struct sha1_state *digest, const u8 *data, int rounds); diff --git a/arch/x86/crypto/sha256-avx-asm.S b/arch/x86/crypto/sha256-avx-asm.S index fcbc30f58c38..4739cd31b9db 100644 --- a/arch/x86/crypto/sha256-avx-asm.S +++ b/arch/x86/crypto/sha256-avx-asm.S @@ -47,7 +47,6 @@ # This code schedules 1 block at a time, with 4 lanes per block ######################################################################## -#ifdef CONFIG_AS_AVX #include <linux/linkage.h> ## assume buffers not aligned @@ -498,5 +497,3 @@ _SHUF_00BA: # shuffle xDxC -> DC00 _SHUF_DC00: .octa 0x0b0a090803020100FFFFFFFFFFFFFFFF - -#endif diff --git a/arch/x86/crypto/sha256-avx2-asm.S b/arch/x86/crypto/sha256-avx2-asm.S index 499d9ec129de..11ff60c29c8b 100644 --- a/arch/x86/crypto/sha256-avx2-asm.S +++ b/arch/x86/crypto/sha256-avx2-asm.S @@ -48,7 +48,6 @@ # This code schedules 2 blocks at a time, with 4 lanes per block ######################################################################## -#ifdef CONFIG_AS_AVX2 #include <linux/linkage.h> ## assume buffers not aligned @@ -767,5 +766,3 @@ _SHUF_00BA: .align 32 _SHUF_DC00: .octa 0x0b0a090803020100FFFFFFFFFFFFFFFF,0x0b0a090803020100FFFFFFFFFFFFFFFF - -#endif diff --git a/arch/x86/crypto/sha256_ssse3_glue.c b/arch/x86/crypto/sha256_ssse3_glue.c index 03ad657c04bd..6394b5fe8db6 100644 --- a/arch/x86/crypto/sha256_ssse3_glue.c +++ b/arch/x86/crypto/sha256_ssse3_glue.c @@ -144,7 +144,6 @@ static void unregister_sha256_ssse3(void) ARRAY_SIZE(sha256_ssse3_algs)); } -#ifdef CONFIG_AS_AVX asmlinkage void sha256_transform_avx(struct sha256_state *state, const u8 *data, int blocks); @@ -221,12 +220,6 @@ static void unregister_sha256_avx(void) ARRAY_SIZE(sha256_avx_algs)); } -#else -static inline int register_sha256_avx(void) { return 0; } -static inline void unregister_sha256_avx(void) { } -#endif - -#if defined(CONFIG_AS_AVX2) && defined(CONFIG_AS_AVX) asmlinkage void sha256_transform_rorx(struct sha256_state *state, const u8 *data, int blocks); @@ -301,11 +294,6 @@ static void unregister_sha256_avx2(void) ARRAY_SIZE(sha256_avx2_algs)); } -#else -static inline int register_sha256_avx2(void) { return 0; } -static inline void unregister_sha256_avx2(void) { } -#endif - #ifdef CONFIG_AS_SHA256_NI asmlinkage void sha256_ni_transform(struct sha256_state *digest, const u8 *data, int rounds); diff --git a/arch/x86/crypto/sha512-avx-asm.S b/arch/x86/crypto/sha512-avx-asm.S index 90ea945ba5e6..63470fd6ae32 100644 --- a/arch/x86/crypto/sha512-avx-asm.S +++ b/arch/x86/crypto/sha512-avx-asm.S @@ -47,7 +47,6 @@ # ######################################################################## -#ifdef CONFIG_AS_AVX #include <linux/linkage.h> .text @@ -424,4 +423,3 @@ K512: .quad 0x3c9ebe0a15c9bebc,0x431d67c49c100d4c .quad 0x4cc5d4becb3e42b6,0x597f299cfc657e2a .quad 0x5fcb6fab3ad6faec,0x6c44198c4a475817 -#endif diff --git a/arch/x86/crypto/sha512-avx2-asm.S b/arch/x86/crypto/sha512-avx2-asm.S index 3dd886b14e7d..3a44bdcfd583 100644 --- a/arch/x86/crypto/sha512-avx2-asm.S +++ b/arch/x86/crypto/sha512-avx2-asm.S @@ -49,7 +49,6 @@ # This code schedules 1 blocks at a time, with 4 lanes per block ######################################################################## -#ifdef CONFIG_AS_AVX2 #include <linux/linkage.h> .text @@ -749,5 +748,3 @@ PSHUFFLE_BYTE_FLIP_MASK: MASK_YMM_LO: .octa 0x00000000000000000000000000000000 .octa 0xFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFF - -#endif diff --git a/arch/x86/crypto/sha512_ssse3_glue.c b/arch/x86/crypto/sha512_ssse3_glue.c index 1c444f41037c..82cc1b3ced1d 100644 --- a/arch/x86/crypto/sha512_ssse3_glue.c +++ b/arch/x86/crypto/sha512_ssse3_glue.c @@ -142,7 +142,6 @@ static void unregister_sha512_ssse3(void) ARRAY_SIZE(sha512_ssse3_algs)); } -#ifdef CONFIG_AS_AVX asmlinkage void sha512_transform_avx(struct sha512_state *state, const u8 *data, int blocks); static bool avx_usable(void) @@ -218,12 +217,7 @@ static void unregister_sha512_avx(void) crypto_unregister_shashes(sha512_avx_algs, ARRAY_SIZE(sha512_avx_algs)); } -#else -static inline int register_sha512_avx(void) { return 0; } -static inline void unregister_sha512_avx(void) { } -#endif -#if defined(CONFIG_AS_AVX2) && defined(CONFIG_AS_AVX) asmlinkage void sha512_transform_rorx(struct sha512_state *state, const u8 *data, int blocks); @@ -298,10 +292,6 @@ static void unregister_sha512_avx2(void) crypto_unregister_shashes(sha512_avx2_algs, ARRAY_SIZE(sha512_avx2_algs)); } -#else -static inline int register_sha512_avx2(void) { return 0; } -static inline void unregister_sha512_avx2(void) { } -#endif static int __init sha512_ssse3_mod_init(void) { diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c index 1ba72c563313..cf76d6631afa 100644 --- a/arch/x86/events/intel/uncore.c +++ b/arch/x86/events/intel/uncore.c @@ -1476,6 +1476,12 @@ static const struct intel_uncore_init_fun tgl_l_uncore_init __initconst = { .mmio_init = tgl_l_uncore_mmio_init, }; +static const struct intel_uncore_init_fun icx_uncore_init __initconst = { + .cpu_init = icx_uncore_cpu_init, + .pci_init = icx_uncore_pci_init, + .mmio_init = icx_uncore_mmio_init, +}; + static const struct intel_uncore_init_fun snr_uncore_init __initconst = { .cpu_init = snr_uncore_cpu_init, .pci_init = snr_uncore_pci_init, @@ -1511,6 +1517,8 @@ static const struct x86_cpu_id intel_uncore_match[] __initconst = { X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_L, &icl_uncore_init), X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_NNPI, &icl_uncore_init), X86_MATCH_INTEL_FAM6_MODEL(ICELAKE, &icl_uncore_init), + X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_D, &icx_uncore_init), + X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_X, &icx_uncore_init), X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE_L, &tgl_l_uncore_init), X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE, &tgl_uncore_init), X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT_D, &snr_uncore_init), diff --git a/arch/x86/events/intel/uncore.h b/arch/x86/events/intel/uncore.h index b30429f8a53a..0da4a4605536 100644 --- a/arch/x86/events/intel/uncore.h +++ b/arch/x86/events/intel/uncore.h @@ -550,6 +550,9 @@ void skx_uncore_cpu_init(void); int snr_uncore_pci_init(void); void snr_uncore_cpu_init(void); void snr_uncore_mmio_init(void); +int icx_uncore_pci_init(void); +void icx_uncore_cpu_init(void); +void icx_uncore_mmio_init(void); /* uncore_nhmex.c */ void nhmex_uncore_cpu_init(void); diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c index 01023f0d935b..07652fa20ebb 100644 --- a/arch/x86/events/intel/uncore_snbep.c +++ b/arch/x86/events/intel/uncore_snbep.c @@ -382,6 +382,42 @@ #define SNR_IMC_MMIO_MEM0_OFFSET 0xd8 #define SNR_IMC_MMIO_MEM0_MASK 0x7FF +/* ICX CHA */ +#define ICX_C34_MSR_PMON_CTR0 0xb68 +#define ICX_C34_MSR_PMON_CTL0 0xb61 +#define ICX_C34_MSR_PMON_BOX_CTL 0xb60 +#define ICX_C34_MSR_PMON_BOX_FILTER0 0xb65 + +/* ICX IIO */ +#define ICX_IIO_MSR_PMON_CTL0 0xa58 +#define ICX_IIO_MSR_PMON_CTR0 0xa51 +#define ICX_IIO_MSR_PMON_BOX_CTL 0xa50 + +/* ICX IRP */ +#define ICX_IRP0_MSR_PMON_CTL0 0xa4d +#define ICX_IRP0_MSR_PMON_CTR0 0xa4b +#define ICX_IRP0_MSR_PMON_BOX_CTL 0xa4a + +/* ICX M2PCIE */ +#define ICX_M2PCIE_MSR_PMON_CTL0 0xa46 +#define ICX_M2PCIE_MSR_PMON_CTR0 0xa41 +#define ICX_M2PCIE_MSR_PMON_BOX_CTL 0xa40 + +/* ICX UPI */ +#define ICX_UPI_PCI_PMON_CTL0 0x350 +#define ICX_UPI_PCI_PMON_CTR0 0x320 +#define ICX_UPI_PCI_PMON_BOX_CTL 0x318 +#define ICX_UPI_CTL_UMASK_EXT 0xffffff + +/* ICX M3UPI*/ +#define ICX_M3UPI_PCI_PMON_CTL0 0xd8 +#define ICX_M3UPI_PCI_PMON_CTR0 0xa8 +#define ICX_M3UPI_PCI_PMON_BOX_CTL 0xa0 + +/* ICX IMC */ +#define ICX_NUMBER_IMC_CHN 2 +#define ICX_IMC_MEM_STRIDE 0x4 + DEFINE_UNCORE_FORMAT_ATTR(event, event, "config:0-7"); DEFINE_UNCORE_FORMAT_ATTR(event2, event, "config:0-6"); DEFINE_UNCORE_FORMAT_ATTR(event_ext, event, "config:0-7,21"); @@ -390,6 +426,7 @@ DEFINE_UNCORE_FORMAT_ATTR(umask, umask, "config:8-15"); DEFINE_UNCORE_FORMAT_ATTR(umask_ext, umask, "config:8-15,32-43,45-55"); DEFINE_UNCORE_FORMAT_ATTR(umask_ext2, umask, "config:8-15,32-57"); DEFINE_UNCORE_FORMAT_ATTR(umask_ext3, umask, "config:8-15,32-39"); +DEFINE_UNCORE_FORMAT_ATTR(umask_ext4, umask, "config:8-15,32-55"); DEFINE_UNCORE_FORMAT_ATTR(qor, qor, "config:16"); DEFINE_UNCORE_FORMAT_ATTR(edge, edge, "config:18"); DEFINE_UNCORE_FORMAT_ATTR(tid_en, tid_en, "config:19"); @@ -4551,3 +4588,477 @@ void snr_uncore_mmio_init(void) } /* end of SNR uncore support */ + +/* ICX uncore support */ + +static unsigned icx_cha_msr_offsets[] = { + 0x2a0, 0x2ae, 0x2bc, 0x2ca, 0x2d8, 0x2e6, 0x2f4, 0x302, 0x310, + 0x31e, 0x32c, 0x33a, 0x348, 0x356, 0x364, 0x372, 0x380, 0x38e, + 0x3aa, 0x3b8, 0x3c6, 0x3d4, 0x3e2, 0x3f0, 0x3fe, 0x40c, 0x41a, + 0x428, 0x436, 0x444, 0x452, 0x460, 0x46e, 0x47c, 0x0, 0xe, + 0x1c, 0x2a, 0x38, 0x46, +}; + +static int icx_cha_hw_config(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; + bool tie_en = !!(event->hw.config & SNBEP_CBO_PMON_CTL_TID_EN); + + if (tie_en) { + reg1->reg = ICX_C34_MSR_PMON_BOX_FILTER0 + + icx_cha_msr_offsets[box->pmu->pmu_idx]; + reg1->config = event->attr.config1 & SKX_CHA_MSR_PMON_BOX_FILTER_TID; + reg1->idx = 0; + } + + return 0; +} + +static struct intel_uncore_ops icx_uncore_chabox_ops = { + .init_box = ivbep_uncore_msr_init_box, + .disable_box = snbep_uncore_msr_disable_box, + .enable_box = snbep_uncore_msr_enable_box, + .disable_event = snbep_uncore_msr_disable_event, + .enable_event = snr_cha_enable_event, + .read_counter = uncore_msr_read_counter, + .hw_config = icx_cha_hw_config, +}; + +static struct intel_uncore_type icx_uncore_chabox = { + .name = "cha", + .num_counters = 4, + .perf_ctr_bits = 48, + .event_ctl = ICX_C34_MSR_PMON_CTL0, + .perf_ctr = ICX_C34_MSR_PMON_CTR0, + .box_ctl = ICX_C34_MSR_PMON_BOX_CTL, + .msr_offsets = icx_cha_msr_offsets, + .event_mask = HSWEP_S_MSR_PMON_RAW_EVENT_MASK, + .event_mask_ext = SNR_CHA_RAW_EVENT_MASK_EXT, + .constraints = skx_uncore_chabox_constraints, + .ops = &icx_uncore_chabox_ops, + .format_group = &snr_uncore_chabox_format_group, +}; + +static unsigned icx_msr_offsets[] = { + 0x0, 0x20, 0x40, 0x90, 0xb0, 0xd0, +}; + +static struct event_constraint icx_uncore_iio_constraints[] = { + UNCORE_EVENT_CONSTRAINT(0x02, 0x3), + UNCORE_EVENT_CONSTRAINT(0x03, 0x3), + UNCORE_EVENT_CONSTRAINT(0x83, 0x3), + UNCORE_EVENT_CONSTRAINT(0xc0, 0xc), + UNCORE_EVENT_CONSTRAINT(0xc5, 0xc), + EVENT_CONSTRAINT_END +}; + +static struct intel_uncore_type icx_uncore_iio = { + .name = "iio", + .num_counters = 4, + .num_boxes = 6, + .perf_ctr_bits = 48, + .event_ctl = ICX_IIO_MSR_PMON_CTL0, + .perf_ctr = ICX_IIO_MSR_PMON_CTR0, + .event_mask = SNBEP_PMON_RAW_EVENT_MASK, + .event_mask_ext = SNR_IIO_PMON_RAW_EVENT_MASK_EXT, + .box_ctl = ICX_IIO_MSR_PMON_BOX_CTL, + .msr_offsets = icx_msr_offsets, + .constraints = icx_uncore_iio_constraints, + .ops = &skx_uncore_iio_ops, + .format_group = &snr_uncore_iio_format_group, +}; + +static struct intel_uncore_type icx_uncore_irp = { + .name = "irp", + .num_counters = 2, + .num_boxes = 6, + .perf_ctr_bits = 48, + .event_ctl = ICX_IRP0_MSR_PMON_CTL0, + .perf_ctr = ICX_IRP0_MSR_PMON_CTR0, + .event_mask = SNBEP_PMON_RAW_EVENT_MASK, + .box_ctl = ICX_IRP0_MSR_PMON_BOX_CTL, + .msr_offsets = icx_msr_offsets, + .ops = &ivbep_uncore_msr_ops, + .format_group = &ivbep_uncore_format_group, +}; + +static struct event_constraint icx_uncore_m2pcie_constraints[] = { + UNCORE_EVENT_CONSTRAINT(0x14, 0x3), + UNCORE_EVENT_CONSTRAINT(0x23, 0x3), + UNCORE_EVENT_CONSTRAINT(0x2d, 0x3), + EVENT_CONSTRAINT_END +}; + +static struct intel_uncore_type icx_uncore_m2pcie = { + .name = "m2pcie", + .num_counters = 4, + .num_boxes = 6, + .perf_ctr_bits = 48, + .event_ctl = ICX_M2PCIE_MSR_PMON_CTL0, + .perf_ctr = ICX_M2PCIE_MSR_PMON_CTR0, + .box_ctl = ICX_M2PCIE_MSR_PMON_BOX_CTL, + .msr_offsets = icx_msr_offsets, + .constraints = icx_uncore_m2pcie_constraints, + .event_mask = SNBEP_PMON_RAW_EVENT_MASK, + .ops = &ivbep_uncore_msr_ops, + .format_group = &ivbep_uncore_format_group, +}; + +enum perf_uncore_icx_iio_freerunning_type_id { + ICX_IIO_MSR_IOCLK, + ICX_IIO_MSR_BW_IN, + + ICX_IIO_FREERUNNING_TYPE_MAX, +}; + +static unsigned icx_iio_clk_freerunning_box_offsets[] = { + 0x0, 0x20, 0x40, 0x90, 0xb0, 0xd0, +}; + +static unsigned icx_iio_bw_freerunning_box_offsets[] = { + 0x0, 0x10, 0x20, 0x90, 0xa0, 0xb0, +}; + +static struct freerunning_counters icx_iio_freerunning[] = { + [ICX_IIO_MSR_IOCLK] = { 0xa55, 0x1, 0x20, 1, 48, icx_iio_clk_freerunning_box_offsets }, + [ICX_IIO_MSR_BW_IN] = { 0xaa0, 0x1, 0x10, 8, 48, icx_iio_bw_freerunning_box_offsets }, +}; + +static struct uncore_event_desc icx_uncore_iio_freerunning_events[] = { + /* Free-Running IIO CLOCKS Counter */ + INTEL_UNCORE_EVENT_DESC(ioclk, "event=0xff,umask=0x10"), + /* Free-Running IIO BANDWIDTH IN Counters */ + INTEL_UNCORE_EVENT_DESC(bw_in_port0, "event=0xff,umask=0x20"), + INTEL_UNCORE_EVENT_DESC(bw_in_port0.scale, "3.814697266e-6"), + INTEL_UNCORE_EVENT_DESC(bw_in_port0.unit, "MiB"), + INTEL_UNCORE_EVENT_DESC(bw_in_port1, "event=0xff,umask=0x21"), + INTEL_UNCORE_EVENT_DESC(bw_in_port1.scale, "3.814697266e-6"), + INTEL_UNCORE_EVENT_DESC(bw_in_port1.unit, "MiB"), + INTEL_UNCORE_EVENT_DESC(bw_in_port2, "event=0xff,umask=0x22"), + INTEL_UNCORE_EVENT_DESC(bw_in_port2.scale, "3.814697266e-6"), + INTEL_UNCORE_EVENT_DESC(bw_in_port2.unit, "MiB"), + INTEL_UNCORE_EVENT_DESC(bw_in_port3, "event=0xff,umask=0x23"), + INTEL_UNCORE_EVENT_DESC(bw_in_port3.scale, "3.814697266e-6"), + INTEL_UNCORE_EVENT_DESC(bw_in_port3.unit, "MiB"), + INTEL_UNCORE_EVENT_DESC(bw_in_port4, "event=0xff,umask=0x24"), + INTEL_UNCORE_EVENT_DESC(bw_in_port4.scale, "3.814697266e-6"), + INTEL_UNCORE_EVENT_DESC(bw_in_port4.unit, "MiB"), + INTEL_UNCORE_EVENT_DESC(bw_in_port5, "event=0xff,umask=0x25"), + INTEL_UNCORE_EVENT_DESC(bw_in_port5.scale, "3.814697266e-6"), + INTEL_UNCORE_EVENT_DESC(bw_in_port5.unit, "MiB"), + INTEL_UNCORE_EVENT_DESC(bw_in_port6, "event=0xff,umask=0x26"), + INTEL_UNCORE_EVENT_DESC(bw_in_port6.scale, "3.814697266e-6"), + INTEL_UNCORE_EVENT_DESC(bw_in_port6.unit, "MiB"), + INTEL_UNCORE_EVENT_DESC(bw_in_port7, "event=0xff,umask=0x27"), + INTEL_UNCORE_EVENT_DESC(bw_in_port7.scale, "3.814697266e-6"), + INTEL_UNCORE_EVENT_DESC(bw_in_port7.unit, "MiB"), + { /* end: all zeroes */ }, +}; + +static struct intel_uncore_type icx_uncore_iio_free_running = { + .name = "iio_free_running", + .num_counters = 9, + .num_boxes = 6, + .num_freerunning_types = ICX_IIO_FREERUNNING_TYPE_MAX, + .freerunning = icx_iio_freerunning, + .ops = &skx_uncore_iio_freerunning_ops, + .event_descs = icx_uncore_iio_freerunning_events, + .format_group = &skx_uncore_iio_freerunning_format_group, +}; + +static struct intel_uncore_type *icx_msr_uncores[] = { + &skx_uncore_ubox, + &icx_uncore_chabox, + &icx_uncore_iio, + &icx_uncore_irp, + &icx_uncore_m2pcie, + &skx_uncore_pcu, + &icx_uncore_iio_free_running, + NULL, +}; + +/* + * To determine the number of CHAs, it should read CAPID6(Low) and CAPID7 (High) + * registers which located at Device 30, Function 3 + */ +#define ICX_CAPID6 0x9c +#define ICX_CAPID7 0xa0 + +static u64 icx_count_chabox(void) +{ + struct pci_dev *dev = NULL; + u64 caps = 0; + + dev = pci_get_device(PCI_VENDOR_ID_INTEL, 0x345b, dev); + if (!dev) + goto out; + + pci_read_config_dword(dev, ICX_CAPID6, (u32 *)&caps); + pci_read_config_dword(dev, ICX_CAPID7, (u32 *)&caps + 1); +out: + pci_dev_put(dev); + return hweight64(caps); +} + +void icx_uncore_cpu_init(void) +{ + u64 num_boxes = icx_count_chabox(); + + if (WARN_ON(num_boxes > ARRAY_SIZE(icx_cha_msr_offsets))) + return; + icx_uncore_chabox.num_boxes = num_boxes; + uncore_msr_uncores = icx_msr_uncores; +} + +static struct intel_uncore_type icx_uncore_m2m = { + .name = "m2m", + .num_counters = 4, + .num_boxes = 4, + .perf_ctr_bits = 48, + .perf_ctr = SNR_M2M_PCI_PMON_CTR0, + .event_ctl = SNR_M2M_PCI_PMON_CTL0, + .event_mask = SNBEP_PMON_RAW_EVENT_MASK, + .box_ctl = SNR_M2M_PCI_PMON_BOX_CTL, + .ops = &snr_m2m_uncore_pci_ops, + .format_group = &skx_uncore_format_group, +}; + +static struct attribute *icx_upi_uncore_formats_attr[] = { + &format_attr_event.attr, + &format_attr_umask_ext4.attr, + &format_attr_edge.attr, + &format_attr_inv.attr, + &format_attr_thresh8.attr, + NULL, +}; + +static const struct attribute_group icx_upi_uncore_format_group = { + .name = "format", + .attrs = icx_upi_uncore_formats_attr, +}; + +static struct intel_uncore_type icx_uncore_upi = { + .name = "upi", + .num_counters = 4, + .num_boxes = 3, + .perf_ctr_bits = 48, + .perf_ctr = ICX_UPI_PCI_PMON_CTR0, + .event_ctl = ICX_UPI_PCI_PMON_CTL0, + .event_mask = SNBEP_PMON_RAW_EVENT_MASK, + .event_mask_ext = ICX_UPI_CTL_UMASK_EXT, + .box_ctl = ICX_UPI_PCI_PMON_BOX_CTL, + .ops = &skx_upi_uncore_pci_ops, + .format_group = &icx_upi_uncore_format_group, +}; + +static struct event_constraint icx_uncore_m3upi_constraints[] = { + UNCORE_EVENT_CONSTRAINT(0x1c, 0x1), + UNCORE_EVENT_CONSTRAINT(0x1d, 0x1), + UNCORE_EVENT_CONSTRAINT(0x1e, 0x1), + UNCORE_EVENT_CONSTRAINT(0x1f, 0x1), + UNCORE_EVENT_CONSTRAINT(0x40, 0x7), + UNCORE_EVENT_CONSTRAINT(0x4e, 0x7), + UNCORE_EVENT_CONSTRAINT(0x4f, 0x7), + UNCORE_EVENT_CONSTRAINT(0x50, 0x7), + EVENT_CONSTRAINT_END +}; + +static struct intel_uncore_type icx_uncore_m3upi = { + .name = "m3upi", + .num_counters = 4, + .num_boxes = 3, + .perf_ctr_bits = 48, + .perf_ctr = ICX_M3UPI_PCI_PMON_CTR0, + .event_ctl = ICX_M3UPI_PCI_PMON_CTL0, + .event_mask = SNBEP_PMON_RAW_EVENT_MASK, + .box_ctl = ICX_M3UPI_PCI_PMON_BOX_CTL, + .constraints = icx_uncore_m3upi_constraints, + .ops = &ivbep_uncore_pci_ops, + .format_group = &skx_uncore_format_group, +}; + +enum { + ICX_PCI_UNCORE_M2M, + ICX_PCI_UNCORE_UPI, + ICX_PCI_UNCORE_M3UPI, +}; + +static struct intel_uncore_type *icx_pci_uncores[] = { + [ICX_PCI_UNCORE_M2M] = &icx_uncore_m2m, + [ICX_PCI_UNCORE_UPI] = &icx_uncore_upi, + [ICX_PCI_UNCORE_M3UPI] = &icx_uncore_m3upi, + NULL, +}; + +static const struct pci_device_id icx_uncore_pci_ids[] = { + { /* M2M 0 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x344a), + .driver_data = UNCORE_PCI_DEV_FULL_DATA(12, 0, ICX_PCI_UNCORE_M2M, 0), + }, + { /* M2M 1 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x344a), + .driver_data = UNCORE_PCI_DEV_FULL_DATA(13, 0, ICX_PCI_UNCORE_M2M, 1), + }, + { /* M2M 2 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x344a), + .driver_data = UNCORE_PCI_DEV_FULL_DATA(14, 0, ICX_PCI_UNCORE_M2M, 2), + }, + { /* M2M 3 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x344a), + .driver_data = UNCORE_PCI_DEV_FULL_DATA(15, 0, ICX_PCI_UNCORE_M2M, 3), + }, + { /* UPI Link 0 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x3441), + .driver_data = UNCORE_PCI_DEV_FULL_DATA(2, 1, ICX_PCI_UNCORE_UPI, 0), + }, + { /* UPI Link 1 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x3441), + .driver_data = UNCORE_PCI_DEV_FULL_DATA(3, 1, ICX_PCI_UNCORE_UPI, 1), + }, + { /* UPI Link 2 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x3441), + .driver_data = UNCORE_PCI_DEV_FULL_DATA(4, 1, ICX_PCI_UNCORE_UPI, 2), + }, + { /* M3UPI Link 0 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x3446), + .driver_data = UNCORE_PCI_DEV_FULL_DATA(5, 1, ICX_PCI_UNCORE_M3UPI, 0), + }, + { /* M3UPI Link 1 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x3446), + .driver_data = UNCORE_PCI_DEV_FULL_DATA(6, 1, ICX_PCI_UNCORE_M3UPI, 1), + }, + { /* M3UPI Link 2 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x3446), + .driver_data = UNCORE_PCI_DEV_FULL_DATA(7, 1, ICX_PCI_UNCORE_M3UPI, 2), + }, + { /* end: all zeroes */ } +}; + +static struct pci_driver icx_uncore_pci_driver = { + .name = "icx_uncore", + .id_table = icx_uncore_pci_ids, +}; + +int icx_uncore_pci_init(void) +{ + /* ICX UBOX DID */ + int ret = snbep_pci2phy_map_init(0x3450, SKX_CPUNODEID, + SKX_GIDNIDMAP, true); + + if (ret) + return ret; + + uncore_pci_uncores = icx_pci_uncores; + uncore_pci_driver = &icx_uncore_pci_driver; + return 0; +} + +static void icx_uncore_imc_init_box(struct intel_uncore_box *box) +{ + unsigned int box_ctl = box->pmu->type->box_ctl + + box->pmu->type->mmio_offset * (box->pmu->pmu_idx % ICX_NUMBER_IMC_CHN); + int mem_offset = (box->pmu->pmu_idx / ICX_NUMBER_IMC_CHN) * ICX_IMC_MEM_STRIDE + + SNR_IMC_MMIO_MEM0_OFFSET; + + __snr_uncore_mmio_init_box(box, box_ctl, mem_offset); +} + +static struct intel_uncore_ops icx_uncore_mmio_ops = { + .init_box = icx_uncore_imc_init_box, + .exit_box = uncore_mmio_exit_box, + .disable_box = snr_uncore_mmio_disable_box, + .enable_box = snr_uncore_mmio_enable_box, + .disable_event = snr_uncore_mmio_disable_event, + .enable_event = snr_uncore_mmio_enable_event, + .read_counter = uncore_mmio_read_counter, +}; + +static struct intel_uncore_type icx_uncore_imc = { + .name = "imc", + .num_counters = 4, + .num_boxes = 8, + .perf_ctr_bits = 48, + .fixed_ctr_bits = 48, + .fixed_ctr = SNR_IMC_MMIO_PMON_FIXED_CTR, + .fixed_ctl = SNR_IMC_MMIO_PMON_FIXED_CTL, + .event_descs = hswep_uncore_imc_events, + .perf_ctr = SNR_IMC_MMIO_PMON_CTR0, + .event_ctl = SNR_IMC_MMIO_PMON_CTL0, + .event_mask = SNBEP_PMON_RAW_EVENT_MASK, + .box_ctl = SNR_IMC_MMIO_PMON_BOX_CTL, + .mmio_offset = SNR_IMC_MMIO_OFFSET, + .ops = &icx_uncore_mmio_ops, + .format_group = &skx_uncore_format_group, +}; + +enum perf_uncore_icx_imc_freerunning_type_id { + ICX_IMC_DCLK, + ICX_IMC_DDR, + ICX_IMC_DDRT, + + ICX_IMC_FREERUNNING_TYPE_MAX, +}; + +static struct freerunning_counters icx_imc_freerunning[] = { + [ICX_IMC_DCLK] = { 0x22b0, 0x0, 0, 1, 48 }, + [ICX_IMC_DDR] = { 0x2290, 0x8, 0, 2, 48 }, + [ICX_IMC_DDRT] = { 0x22a0, 0x8, 0, 2, 48 }, +}; + +static struct uncore_event_desc icx_uncore_imc_freerunning_events[] = { + INTEL_UNCORE_EVENT_DESC(dclk, "event=0xff,umask=0x10"), + + INTEL_UNCORE_EVENT_DESC(read, "event=0xff,umask=0x20"), + INTEL_UNCORE_EVENT_DESC(read.scale, "3.814697266e-6"), + INTEL_UNCORE_EVENT_DESC(read.unit, "MiB"), + INTEL_UNCORE_EVENT_DESC(write, "event=0xff,umask=0x21"), + INTEL_UNCORE_EVENT_DESC(write.scale, "3.814697266e-6"), + INTEL_UNCORE_EVENT_DESC(write.unit, "MiB"), + + INTEL_UNCORE_EVENT_DESC(ddrt_read, "event=0xff,umask=0x30"), + INTEL_UNCORE_EVENT_DESC(ddrt_read.scale, "3.814697266e-6"), + INTEL_UNCORE_EVENT_DESC(ddrt_read.unit, "MiB"), + INTEL_UNCORE_EVENT_DESC(ddrt_write, "event=0xff,umask=0x31"), + INTEL_UNCORE_EVENT_DESC(ddrt_write.scale, "3.814697266e-6"), + INTEL_UNCORE_EVENT_DESC(ddrt_write.unit, "MiB"), + { /* end: all zeroes */ }, +}; + +static void icx_uncore_imc_freerunning_init_box(struct intel_uncore_box *box) +{ + int mem_offset = box->pmu->pmu_idx * ICX_IMC_MEM_STRIDE + + SNR_IMC_MMIO_MEM0_OFFSET; + + __snr_uncore_mmio_init_box(box, uncore_mmio_box_ctl(box), mem_offset); +} + +static struct intel_uncore_ops icx_uncore_imc_freerunning_ops = { + .init_box = icx_uncore_imc_freerunning_init_box, + .exit_box = uncore_mmio_exit_box, + .read_counter = uncore_mmio_read_counter, + .hw_config = uncore_freerunning_hw_config, +}; + +static struct intel_uncore_type icx_uncore_imc_free_running = { + .name = "imc_free_running", + .num_counters = 5, + .num_boxes = 4, + .num_freerunning_types = ICX_IMC_FREERUNNING_TYPE_MAX, + .freerunning = icx_imc_freerunning, + .ops = &icx_uncore_imc_freerunning_ops, + .event_descs = icx_uncore_imc_freerunning_events, + .format_group = &skx_uncore_iio_freerunning_format_group, +}; + +static struct intel_uncore_type *icx_mmio_uncores[] = { + &icx_uncore_imc, + &icx_uncore_imc_free_running, + NULL, +}; + +void icx_uncore_mmio_init(void) +{ + uncore_mmio_uncores = icx_mmio_uncores; +} + +/* end of ICX uncore support */ diff --git a/arch/x86/include/asm/dwarf2.h b/arch/x86/include/asm/dwarf2.h index f71a0cce9373..430fca13bb56 100644 --- a/arch/x86/include/asm/dwarf2.h +++ b/arch/x86/include/asm/dwarf2.h @@ -6,15 +6,6 @@ #warning "asm/dwarf2.h should be only included in pure assembly files" #endif -/* - * Macros for dwarf2 CFI unwind table entries. - * See "as.info" for details on these pseudo ops. Unfortunately - * they are only supported in very new binutils, so define them - * away for older version. - */ - -#ifdef CONFIG_AS_CFI - #define CFI_STARTPROC .cfi_startproc #define CFI_ENDPROC .cfi_endproc #define CFI_DEF_CFA .cfi_def_cfa @@ -30,13 +21,6 @@ #define CFI_UNDEFINED .cfi_undefined #define CFI_ESCAPE .cfi_escape -#ifdef CONFIG_AS_CFI_SIGNAL_FRAME -#define CFI_SIGNAL_FRAME .cfi_signal_frame -#else -#define CFI_SIGNAL_FRAME -#endif - -#if defined(CONFIG_AS_CFI_SECTIONS) && defined(__ASSEMBLY__) #ifndef BUILD_VDSO /* * Emit CFI data in .debug_frame sections, not .eh_frame sections. @@ -53,33 +37,5 @@ */ .cfi_sections .eh_frame, .debug_frame #endif -#endif - -#else - -/* - * Due to the structure of pre-exisiting code, don't use assembler line - * comment character # to ignore the arguments. Instead, use a dummy macro. - */ -.macro cfi_ignore a=0, b=0, c=0, d=0 -.endm - -#define CFI_STARTPROC cfi_ignore -#define CFI_ENDPROC cfi_ignore -#define CFI_DEF_CFA cfi_ignore -#define CFI_DEF_CFA_REGISTER cfi_ignore -#define CFI_DEF_CFA_OFFSET cfi_ignore -#define CFI_ADJUST_CFA_OFFSET cfi_ignore -#define CFI_OFFSET cfi_ignore -#define CFI_REL_OFFSET cfi_ignore -#define CFI_REGISTER cfi_ignore -#define CFI_RESTORE cfi_ignore -#define CFI_REMEMBER_STATE cfi_ignore -#define CFI_RESTORE_STATE cfi_ignore -#define CFI_UNDEFINED cfi_ignore -#define CFI_ESCAPE cfi_ignore -#define CFI_SIGNAL_FRAME cfi_ignore - -#endif #endif /* _ASM_X86_DWARF2_H */ diff --git a/arch/x86/include/asm/xor_avx.h b/arch/x86/include/asm/xor_avx.h index d61ddf3d052b..0c4e5b5e3852 100644 --- a/arch/x86/include/asm/xor_avx.h +++ b/arch/x86/include/asm/xor_avx.h @@ -11,8 +11,6 @@ * Based on Ingo Molnar and Zach Brown's respective MMX and SSE routines */ -#ifdef CONFIG_AS_AVX - #include <linux/compiler.h> #include <asm/fpu/api.h> @@ -170,11 +168,4 @@ do { \ #define AVX_SELECT(FASTEST) \ (boot_cpu_has(X86_FEATURE_AVX) && boot_cpu_has(X86_FEATURE_OSXSAVE) ? &xor_block_avx : FASTEST) -#else - -#define AVX_XOR_SPEED {} - -#define AVX_SELECT(FASTEST) (FASTEST) - -#endif #endif |