diff options
Diffstat (limited to 'arch/x86')
61 files changed, 4593 insertions, 3871 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 8d078642b4be..1d6104ea8af0 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -1661,6 +1661,7 @@ config X86_PMEM_LEGACY depends on PHYS_ADDR_T_64BIT depends on BLK_DEV select X86_PMEM_LEGACY_DEVICE + select NUMA_KEEP_MEMINFO if NUMA select LIBNVDIMM help Treat memory marked using the non-standard e820 type of 12 as used @@ -2931,3 +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/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c index b0da5320bcff..624f5d9b0f79 100644 --- a/arch/x86/hyperv/hv_init.c +++ b/arch/x86/hyperv/hv_init.c @@ -20,6 +20,7 @@ #include <linux/mm.h> #include <linux/hyperv.h> #include <linux/slab.h> +#include <linux/kernel.h> #include <linux/cpuhotplug.h> #include <linux/syscore_ops.h> #include <clocksource/hyperv_timer.h> @@ -419,11 +420,14 @@ void hyperv_cleanup(void) } EXPORT_SYMBOL_GPL(hyperv_cleanup); -void hyperv_report_panic(struct pt_regs *regs, long err) +void hyperv_report_panic(struct pt_regs *regs, long err, bool in_die) { static bool panic_reported; u64 guest_id; + if (in_die && !panic_on_oops) + return; + /* * We prefer to report panic on 'die' chain as we have proper * registers to report, but if we miss it (e.g. on BUG()) we need diff --git a/arch/x86/include/asm/cpu.h b/arch/x86/include/asm/cpu.h index ff6f3ca649b3..dd17c2da1af5 100644 --- a/arch/x86/include/asm/cpu.h +++ b/arch/x86/include/asm/cpu.h @@ -44,6 +44,7 @@ unsigned int x86_stepping(unsigned int sig); extern void __init cpu_set_core_cap_bits(struct cpuinfo_x86 *c); extern void switch_to_sld(unsigned long tifn); extern bool handle_user_split_lock(struct pt_regs *regs, long error_code); +extern bool handle_guest_split_lock(unsigned long ip); #else static inline void __init cpu_set_core_cap_bits(struct cpuinfo_x86 *c) {} static inline void switch_to_sld(unsigned long tifn) {} @@ -51,5 +52,10 @@ static inline bool handle_user_split_lock(struct pt_regs *regs, long error_code) { return false; } + +static inline bool handle_guest_split_lock(unsigned long ip) +{ + return false; +} #endif #endif /* _ASM_X86_CPU_H */ 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/efi.h b/arch/x86/include/asm/efi.h index cdcf48d52a12..8391c115c0ec 100644 --- a/arch/x86/include/asm/efi.h +++ b/arch/x86/include/asm/efi.h @@ -178,8 +178,10 @@ extern void efi_free_boot_services(void); extern pgd_t * __init efi_uv1_memmap_phys_prolog(void); extern void __init efi_uv1_memmap_phys_epilog(pgd_t *save_pgd); +/* kexec external ABI */ struct efi_setup_data { u64 fw_vendor; + u64 __unused; u64 tables; u64 smbios; u64 reserved[8]; diff --git a/arch/x86/include/asm/page_types.h b/arch/x86/include/asm/page_types.h index c85e15010f48..a506a411474d 100644 --- a/arch/x86/include/asm/page_types.h +++ b/arch/x86/include/asm/page_types.h @@ -35,9 +35,7 @@ #define PAGE_OFFSET ((unsigned long)__PAGE_OFFSET) -#define VM_DATA_DEFAULT_FLAGS \ - (((current->personality & READ_IMPLIES_EXEC) ? VM_EXEC : 0 ) | \ - VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC) +#define VM_DATA_DEFAULT_FLAGS VM_DATA_FLAGS_TSK_EXEC #define __PHYSICAL_START ALIGN(CONFIG_PHYSICAL_START, \ CONFIG_PHYSICAL_ALIGN) @@ -73,9 +71,6 @@ static inline phys_addr_t get_max_mapped(void) bool pfn_range_is_mapped(unsigned long start_pfn, unsigned long end_pfn); -extern unsigned long init_memory_mapping(unsigned long start, - unsigned long end); - extern void initmem_init(void); #endif /* !__ASSEMBLY__ */ diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index 28838d790191..4d02e64af1b3 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -860,7 +860,10 @@ static inline unsigned long pmd_index(unsigned long address) * * this function returns the index of the entry in the pte page which would * control the given virtual address + * + * Also define macro so we can test if pte_index is defined for arch. */ +#define pte_index pte_index static inline unsigned long pte_index(unsigned long address) { return (address >> PAGE_SHIFT) & (PTRS_PER_PTE - 1); @@ -1078,6 +1081,9 @@ static inline void __meminit init_trampoline_default(void) void __init poking_init(void); +unsigned long init_memory_mapping(unsigned long start, + unsigned long end, pgprot_t prot); + # ifdef CONFIG_RANDOMIZE_MEMORY void __meminit init_trampoline(void); # else diff --git a/arch/x86/include/asm/set_memory.h b/arch/x86/include/asm/set_memory.h index 950532ccbc4a..ec2c0a094b5d 100644 --- a/arch/x86/include/asm/set_memory.h +++ b/arch/x86/include/asm/set_memory.h @@ -34,6 +34,7 @@ * The caller is required to take care of these. */ +int __set_memory_prot(unsigned long addr, int numpages, pgprot_t prot); int _set_memory_uc(unsigned long addr, int numpages); int _set_memory_wc(unsigned long addr, int numpages); int _set_memory_wt(unsigned long addr, int numpages); 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 diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 1ae5439a9a85..683ed9e12e6b 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -45,7 +45,7 @@ EXPORT_SYMBOL(acpi_disabled); #define PREFIX "ACPI: " int acpi_noirq; /* skip ACPI IRQ initialization */ -int acpi_nobgrt; /* skip ACPI BGRT */ +static int acpi_nobgrt; /* skip ACPI BGRT */ int acpi_pci_disabled; /* skip ACPI PCI scan and IRQ initialization */ EXPORT_SYMBOL(acpi_pci_disabled); diff --git a/arch/x86/kernel/amd_gart_64.c b/arch/x86/kernel/amd_gart_64.c index 4e5f50236048..16133819415c 100644 --- a/arch/x86/kernel/amd_gart_64.c +++ b/arch/x86/kernel/amd_gart_64.c @@ -744,7 +744,8 @@ int __init gart_iommu_init(void) start_pfn = PFN_DOWN(aper_base); if (!pfn_range_is_mapped(start_pfn, end_pfn)) - init_memory_mapping(start_pfn<<PAGE_SHIFT, end_pfn<<PAGE_SHIFT); + init_memory_mapping(start_pfn<<PAGE_SHIFT, end_pfn<<PAGE_SHIFT, + PAGE_KERNEL); pr_info("PCI-DMA: using GART IOMMU.\n"); iommu_size = check_iommu_size(info.aper_base, aper_size); diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index 9a26e972cdea..bf08d4508ecb 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -21,6 +21,7 @@ #include <asm/elf.h> #include <asm/cpu_device_id.h> #include <asm/cmdline.h> +#include <asm/traps.h> #ifdef CONFIG_X86_64 #include <linux/topology.h> @@ -1066,13 +1067,10 @@ static void split_lock_init(void) split_lock_verify_msr(sld_state != sld_off); } -bool handle_user_split_lock(struct pt_regs *regs, long error_code) +static void split_lock_warn(unsigned long ip) { - if ((regs->flags & X86_EFLAGS_AC) || sld_state == sld_fatal) - return false; - pr_warn_ratelimited("#AC: %s/%d took a split_lock trap at address: 0x%lx\n", - current->comm, current->pid, regs->ip); + current->comm, current->pid, ip); /* * Disable the split lock detection for this task so it can make @@ -1081,6 +1079,31 @@ bool handle_user_split_lock(struct pt_regs *regs, long error_code) */ sld_update_msr(false); set_tsk_thread_flag(current, TIF_SLD); +} + +bool handle_guest_split_lock(unsigned long ip) +{ + if (sld_state == sld_warn) { + split_lock_warn(ip); + return true; + } + + pr_warn_once("#AC: %s/%d %s split_lock trap at address: 0x%lx\n", + current->comm, current->pid, + sld_state == sld_fatal ? "fatal" : "bogus", ip); + + current->thread.error_code = 0; + current->thread.trap_nr = X86_TRAP_AC; + force_sig_fault(SIGBUS, BUS_ADRALN, NULL); + return false; +} +EXPORT_SYMBOL_GPL(handle_guest_split_lock); + +bool handle_user_split_lock(struct pt_regs *regs, long error_code) +{ + if ((regs->flags & X86_EFLAGS_AC) || sld_state == sld_fatal) + return false; + split_lock_warn(regs->ip); return true; } diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index caa032ce3fe3..ebf34c7bc8bc 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -227,8 +227,8 @@ static void __init ms_hyperv_init_platform(void) ms_hyperv.misc_features = cpuid_edx(HYPERV_CPUID_FEATURES); ms_hyperv.hints = cpuid_eax(HYPERV_CPUID_ENLIGHTMENT_INFO); - pr_info("Hyper-V: features 0x%x, hints 0x%x\n", - ms_hyperv.features, ms_hyperv.hints); + pr_info("Hyper-V: features 0x%x, hints 0x%x, misc 0x%x\n", + ms_hyperv.features, ms_hyperv.hints, ms_hyperv.misc_features); ms_hyperv.max_vp_index = cpuid_eax(HYPERV_CPUID_IMPLEMENT_LIMITS); ms_hyperv.max_lp_index = cpuid_ebx(HYPERV_CPUID_IMPLEMENT_LIMITS); @@ -263,6 +263,16 @@ static void __init ms_hyperv_init_platform(void) cpuid_eax(HYPERV_CPUID_NESTED_FEATURES); } + /* + * Hyper-V expects to get crash register data or kmsg when + * crash enlightment is available and system crashes. Set + * crash_kexec_post_notifiers to be true to make sure that + * calling crash enlightment interface before running kdump + * kernel. + */ + if (ms_hyperv.misc_features & HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE) + crash_kexec_post_notifiers = true; + #ifdef CONFIG_X86_LOCAL_APIC if (ms_hyperv.features & HV_X64_ACCESS_FREQUENCY_MSRS && ms_hyperv.misc_features & HV_FEATURE_FREQUENCY_MSRS_AVAILABLE) { diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index e6b545047f38..4b3fa6cd3106 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -16,6 +16,7 @@ #include <linux/pci.h> #include <linux/root_dev.h> #include <linux/sfi.h> +#include <linux/hugetlb.h> #include <linux/tboot.h> #include <linux/usb/xhci-dbgp.h> @@ -1157,6 +1158,9 @@ void __init setup_arch(char **cmdline_p) initmem_init(); dma_contiguous_reserve(max_pfn_mapped << PAGE_SHIFT); + if (boot_cpu_has(X86_FEATURE_GBPAGES)) + hugetlb_cma_reserve(PUD_SHIFT - PAGE_SHIFT); + /* * Reserve memory for crash kernel after SRAT is parsed so that it * won't consume hotpluggable memory. diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig index 9fea0757db92..d8154e0684b6 100644 --- a/arch/x86/kvm/Kconfig +++ b/arch/x86/kvm/Kconfig @@ -107,8 +107,4 @@ config KVM_MMU_AUDIT This option adds a R/W kVM module parameter 'mmu_audit', which allows auditing of KVM MMU events at runtime. -# OK, it's a little counter-intuitive to do this, but it puts it neatly under -# the virtualization menu. -source "drivers/vhost/Kconfig" - endif # VIRTUALIZATION diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile index e553f0fdd87d..a789759b7261 100644 --- a/arch/x86/kvm/Makefile +++ b/arch/x86/kvm/Makefile @@ -14,7 +14,7 @@ kvm-y += x86.o emulate.o i8259.o irq.o lapic.o \ hyperv.o debugfs.o mmu/mmu.o mmu/page_track.o kvm-intel-y += vmx/vmx.o vmx/vmenter.o vmx/pmu_intel.o vmx/vmcs12.o vmx/evmcs.o vmx/nested.o -kvm-amd-y += svm.o pmu_amd.o +kvm-amd-y += svm/svm.o svm/vmenter.o svm/pmu.o svm/nested.o svm/avic.o svm/sev.o obj-$(CONFIG_KVM) += kvm.o obj-$(CONFIG_KVM_INTEL) += kvm-intel.o diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index ca80daf8f878..9af25c97612a 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -59,9 +59,6 @@ #define MAX_APIC_VECTOR 256 #define APIC_VECTORS_PER_REG 32 -#define APIC_BROADCAST 0xFF -#define X2APIC_BROADCAST 0xFFFFFFFFul - static bool lapic_timer_advance_dynamic __read_mostly; #define LAPIC_TIMER_ADVANCE_ADJUST_MIN 100 /* clock cycles */ #define LAPIC_TIMER_ADVANCE_ADJUST_MAX 10000 /* clock cycles */ diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h index 40ed6ed22751..a0ffb4331418 100644 --- a/arch/x86/kvm/lapic.h +++ b/arch/x86/kvm/lapic.h @@ -17,6 +17,9 @@ #define APIC_BUS_CYCLE_NS 1 #define APIC_BUS_FREQUENCY (1000000000ULL / APIC_BUS_CYCLE_NS) +#define APIC_BROADCAST 0xFF +#define X2APIC_BROADCAST 0xFFFFFFFFul + enum lapic_mode { LAPIC_MODE_DISABLED = 0, LAPIC_MODE_INVALID = X2APIC_ENABLE, diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c new file mode 100644 index 000000000000..e80daa98682f --- /dev/null +++ b/arch/x86/kvm/svm/avic.c @@ -0,0 +1,1027 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Kernel-based Virtual Machine driver for Linux + * + * AMD SVM support + * + * Copyright (C) 2006 Qumranet, Inc. + * Copyright 2010 Red Hat, Inc. and/or its affiliates. + * + * Authors: + * Yaniv Kamay <yaniv@qumranet.com> + * Avi Kivity <avi@qumranet.com> + */ + +#define pr_fmt(fmt) "SVM: " fmt + +#include <linux/kvm_types.h> +#include <linux/hashtable.h> +#include <linux/amd-iommu.h> +#include <linux/kvm_host.h> + +#include <asm/irq_remapping.h> + +#include "trace.h" +#include "lapic.h" +#include "x86.h" +#include "irq.h" +#include "svm.h" + +/* enable / disable AVIC */ +int avic; +#ifdef CONFIG_X86_LOCAL_APIC +module_param(avic, int, S_IRUGO); +#endif + +#define SVM_AVIC_DOORBELL 0xc001011b + +#define AVIC_HPA_MASK ~((0xFFFULL << 52) | 0xFFF) + +/* + * 0xff is broadcast, so the max index allowed for physical APIC ID + * table is 0xfe. APIC IDs above 0xff are reserved. + */ +#define AVIC_MAX_PHYSICAL_ID_COUNT 255 + +#define AVIC_UNACCEL_ACCESS_WRITE_MASK 1 +#define AVIC_UNACCEL_ACCESS_OFFSET_MASK 0xFF0 +#define AVIC_UNACCEL_ACCESS_VECTOR_MASK 0xFFFFFFFF + +/* AVIC GATAG is encoded using VM and VCPU IDs */ +#define AVIC_VCPU_ID_BITS 8 +#define AVIC_VCPU_ID_MASK ((1 << AVIC_VCPU_ID_BITS) - 1) + +#define AVIC_VM_ID_BITS 24 +#define AVIC_VM_ID_NR (1 << AVIC_VM_ID_BITS) +#define AVIC_VM_ID_MASK ((1 << AVIC_VM_ID_BITS) - 1) + +#define AVIC_GATAG(x, y) (((x & AVIC_VM_ID_MASK) << AVIC_VCPU_ID_BITS) | \ + (y & AVIC_VCPU_ID_MASK)) +#define AVIC_GATAG_TO_VMID(x) ((x >> AVIC_VCPU_ID_BITS) & AVIC_VM_ID_MASK) +#define AVIC_GATAG_TO_VCPUID(x) (x & AVIC_VCPU_ID_MASK) + +/* Note: + * This hash table is used to map VM_ID to a struct kvm_svm, + * when handling AMD IOMMU GALOG notification to schedule in + * a particular vCPU. + */ +#define SVM_VM_DATA_HASH_BITS 8 +static DEFINE_HASHTABLE(svm_vm_data_hash, SVM_VM_DATA_HASH_BITS); +static u32 next_vm_id = 0; +static bool next_vm_id_wrapped = 0; +static DEFINE_SPINLOCK(svm_vm_data_hash_lock); + +/* + * This is a wrapper of struct amd_iommu_ir_data. + */ +struct amd_svm_iommu_ir { + struct list_head node; /* Used by SVM for per-vcpu ir_list */ + void *data; /* Storing pointer to struct amd_ir_data */ +}; + +enum avic_ipi_failure_cause { + AVIC_IPI_FAILURE_INVALID_INT_TYPE, + AVIC_IPI_FAILURE_TARGET_NOT_RUNNING, + AVIC_IPI_FAILURE_INVALID_TARGET, + AVIC_IPI_FAILURE_INVALID_BACKING_PAGE, +}; + +/* Note: + * This function is called from IOMMU driver to notify + * SVM to schedule in a particular vCPU of a particular VM. + */ +int avic_ga_log_notifier(u32 ga_tag) +{ + unsigned long flags; + struct kvm_svm *kvm_svm; + struct kvm_vcpu *vcpu = NULL; + u32 vm_id = AVIC_GATAG_TO_VMID(ga_tag); + u32 vcpu_id = AVIC_GATAG_TO_VCPUID(ga_tag); + + pr_debug("SVM: %s: vm_id=%#x, vcpu_id=%#x\n", __func__, vm_id, vcpu_id); + trace_kvm_avic_ga_log(vm_id, vcpu_id); + + spin_lock_irqsave(&svm_vm_data_hash_lock, flags); + hash_for_each_possible(svm_vm_data_hash, kvm_svm, hnode, vm_id) { + if (kvm_svm->avic_vm_id != vm_id) + continue; + vcpu = kvm_get_vcpu_by_id(&kvm_svm->kvm, vcpu_id); + break; + } + spin_unlock_irqrestore(&svm_vm_data_hash_lock, flags); + + /* Note: + * At this point, the IOMMU should have already set the pending + * bit in the vAPIC backing page. So, we just need to schedule + * in the vcpu. + */ + if (vcpu) + kvm_vcpu_wake_up(vcpu); + + return 0; +} + +void avic_vm_destroy(struct kvm *kvm) +{ + unsigned long flags; + struct kvm_svm *kvm_svm = to_kvm_svm(kvm); + + if (!avic) + return; + + if (kvm_svm->avic_logical_id_table_page) + __free_page(kvm_svm->avic_logical_id_table_page); + if (kvm_svm->avic_physical_id_table_page) + __free_page(kvm_svm->avic_physical_id_table_page); + + spin_lock_irqsave(&svm_vm_data_hash_lock, flags); + hash_del(&kvm_svm->hnode); + spin_unlock_irqrestore(&svm_vm_data_hash_lock, flags); +} + +int avic_vm_init(struct kvm *kvm) +{ + unsigned long flags; + int err = -ENOMEM; + struct kvm_svm *kvm_svm = to_kvm_svm(kvm); + struct kvm_svm *k2; + struct page *p_page; + struct page *l_page; + u32 vm_id; + + if (!avic) + return 0; + + /* Allocating physical APIC ID table (4KB) */ + p_page = alloc_page(GFP_KERNEL_ACCOUNT); + if (!p_page) + goto free_avic; + + kvm_svm->avic_physical_id_table_page = p_page; + clear_page(page_address(p_page)); + + /* Allocating logical APIC ID table (4KB) */ + l_page = alloc_page(GFP_KERNEL_ACCOUNT); + if (!l_page) + goto free_avic; + + kvm_svm->avic_logical_id_table_page = l_page; + clear_page(page_address(l_page)); + + spin_lock_irqsave(&svm_vm_data_hash_lock, flags); + again: + vm_id = next_vm_id = (next_vm_id + 1) & AVIC_VM_ID_MASK; + if (vm_id == 0) { /* id is 1-based, zero is not okay */ + next_vm_id_wrapped = 1; + goto again; + } + /* Is it still in use? Only possible if wrapped at least once */ + if (next_vm_id_wrapped) { + hash_for_each_possible(svm_vm_data_hash, k2, hnode, vm_id) { + if (k2->avic_vm_id == vm_id) + goto again; + } + } + kvm_svm->avic_vm_id = vm_id; + hash_add(svm_vm_data_hash, &kvm_svm->hnode, kvm_svm->avic_vm_id); + spin_unlock_irqrestore(&svm_vm_data_hash_lock, flags); + + return 0; + +free_avic: + avic_vm_destroy(kvm); + return err; +} + +void avic_init_vmcb(struct vcpu_svm *svm) +{ + struct vmcb *vmcb = svm->vmcb; + struct kvm_svm *kvm_svm = to_kvm_svm(svm->vcpu.kvm); + phys_addr_t bpa = __sme_set(page_to_phys(svm->avic_backing_page)); + phys_addr_t lpa = __sme_set(page_to_phys(kvm_svm->avic_logical_id_table_page)); + phys_addr_t ppa = __sme_set(page_to_phys(kvm_svm->avic_physical_id_table_page)); + + vmcb->control.avic_backing_page = bpa & AVIC_HPA_MASK; + vmcb->control.avic_logical_id = lpa & AVIC_HPA_MASK; + vmcb->control.avic_physical_id = ppa & AVIC_HPA_MASK; + vmcb->control.avic_physical_id |= AVIC_MAX_PHYSICAL_ID_COUNT; + if (kvm_apicv_activated(svm->vcpu.kvm)) + vmcb->control.int_ctl |= AVIC_ENABLE_MASK; + else + vmcb->control.int_ctl &= ~AVIC_ENABLE_MASK; +} + +static u64 *avic_get_physical_id_entry(struct kvm_vcpu *vcpu, + unsigned int index) +{ + u64 *avic_physical_id_table; + struct kvm_svm *kvm_svm = to_kvm_svm(vcpu->kvm); + + if (index >= AVIC_MAX_PHYSICAL_ID_COUNT) + return NULL; + + avic_physical_id_table = page_address(kvm_svm->avic_physical_id_table_page); + + return &avic_physical_id_table[index]; +} + +/** + * Note: + * AVIC hardware walks the nested page table to check permissions, + * but does not use the SPA address specified in the leaf page + * table entry since it uses address in the AVIC_BACKING_PAGE pointer + * field of the VMCB. Therefore, we set up the + * APIC_ACCESS_PAGE_PRIVATE_MEMSLOT (4KB) here. + */ +static int avic_update_access_page(struct kvm *kvm, bool activate) +{ + int ret = 0; + + mutex_lock(&kvm->slots_lock); + /* + * During kvm_destroy_vm(), kvm_pit_set_reinject() could trigger + * APICv mode change, which update APIC_ACCESS_PAGE_PRIVATE_MEMSLOT + * memory region. So, we need to ensure that kvm->mm == current->mm. + */ + if ((kvm->arch.apic_access_page_done == activate) || + (kvm->mm != current->mm)) + goto out; + + ret = __x86_set_memory_region(kvm, + APIC_ACCESS_PAGE_PRIVATE_MEMSLOT, + APIC_DEFAULT_PHYS_BASE, + activate ? PAGE_SIZE : 0); + if (ret) + goto out; + + kvm->arch.apic_access_page_done = activate; +out: + mutex_unlock(&kvm->slots_lock); + return ret; +} + +static int avic_init_backing_page(struct kvm_vcpu *vcpu) +{ + u64 *entry, new_entry; + int id = vcpu->vcpu_id; + struct vcpu_svm *svm = to_svm(vcpu); + + if (id >= AVIC_MAX_PHYSICAL_ID_COUNT) + return -EINVAL; + + if (!svm->vcpu.arch.apic->regs) + return -EINVAL; + + if (kvm_apicv_activated(vcpu->kvm)) { + int ret; + + ret = avic_update_access_page(vcpu->kvm, true); + if (ret) + return ret; + } + + svm->avic_backing_page = virt_to_page(svm->vcpu.arch.apic->regs); + + /* Setting AVIC backing page address in the phy APIC ID table */ + entry = avic_get_physical_id_entry(vcpu, id); + if (!entry) + return -EINVAL; + + new_entry = __sme_set((page_to_phys(svm->avic_backing_page) & + AVIC_PHYSICAL_ID_ENTRY_BACKING_PAGE_MASK) | + AVIC_PHYSICAL_ID_ENTRY_VALID_MASK); + WRITE_ONCE(*entry, new_entry); + + svm->avic_physical_id_cache = entry; + + return 0; +} + +int avic_incomplete_ipi_interception(struct vcpu_svm *svm) +{ + u32 icrh = svm->vmcb->control.exit_info_1 >> 32; + u32 icrl = svm->vmcb->control.exit_info_1; + u32 id = svm->vmcb->control.exit_info_2 >> 32; + u32 index = svm->vmcb->control.exit_info_2 & 0xFF; + struct kvm_lapic *apic = svm->vcpu.arch.apic; + + trace_kvm_avic_incomplete_ipi(svm->vcpu.vcpu_id, icrh, icrl, id, index); + + switch (id) { + case AVIC_IPI_FAILURE_INVALID_INT_TYPE: + /* + * AVIC hardware handles the generation of + * IPIs when the specified Message Type is Fixed + * (also known as fixed delivery mode) and + * the Trigger Mode is edge-triggered. The hardware + * also supports self and broadcast delivery modes + * specified via the Destination Shorthand(DSH) + * field of the ICRL. Logical and physical APIC ID + * formats are supported. All other IPI types cause + * a #VMEXIT, which needs to emulated. + */ + kvm_lapic_reg_write(apic, APIC_ICR2, icrh); + kvm_lapic_reg_write(apic, APIC_ICR, icrl); + break; + case AVIC_IPI_FAILURE_TARGET_NOT_RUNNING: { + int i; + struct kvm_vcpu *vcpu; + struct kvm *kvm = svm->vcpu.kvm; + struct kvm_lapic *apic = svm->vcpu.arch.apic; + + /* + * At this point, we expect that the AVIC HW has already + * set the appropriate IRR bits on the valid target + * vcpus. So, we just need to kick the appropriate vcpu. + */ + kvm_for_each_vcpu(i, vcpu, kvm) { + bool m = kvm_apic_match_dest(vcpu, apic, + icrl & APIC_SHORT_MASK, + GET_APIC_DEST_FIELD(icrh), + icrl & APIC_DEST_MASK); + + if (m && !avic_vcpu_is_running(vcpu)) + kvm_vcpu_wake_up(vcpu); + } + break; + } + case AVIC_IPI_FAILURE_INVALID_TARGET: + WARN_ONCE(1, "Invalid IPI target: index=%u, vcpu=%d, icr=%#0x:%#0x\n", + index, svm->vcpu.vcpu_id, icrh, icrl); + break; + case AVIC_IPI_FAILURE_INVALID_BACKING_PAGE: + WARN_ONCE(1, "Invalid backing page\n"); + break; + default: + pr_err("Unknown IPI interception\n"); + } + + return 1; +} + +static u32 *avic_get_logical_id_entry(struct kvm_vcpu *vcpu, u32 ldr, bool flat) +{ + struct kvm_svm *kvm_svm = to_kvm_svm(vcpu->kvm); + int index; + u32 *logical_apic_id_table; + int dlid = GET_APIC_LOGICAL_ID(ldr); + + if (!dlid) + return NULL; + + if (flat) { /* flat */ + index = ffs(dlid) - 1; + if (index > 7) + return NULL; + } else { /* cluster */ + int cluster = (dlid & 0xf0) >> 4; + int apic = ffs(dlid & 0x0f) - 1; + + if ((apic < 0) || (apic > 7) || + (cluster >= 0xf)) + return NULL; + index = (cluster << 2) + apic; + } + + logical_apic_id_table = (u32 *) page_address(kvm_svm->avic_logical_id_table_page); + + return &logical_apic_id_table[index]; +} + +static int avic_ldr_write(struct kvm_vcpu *vcpu, u8 g_physical_id, u32 ldr) +{ + bool flat; + u32 *entry, new_entry; + + flat = kvm_lapic_get_reg(vcpu->arch.apic, APIC_DFR) == APIC_DFR_FLAT; + entry = avic_get_logical_id_entry(vcpu, ldr, flat); + if (!entry) + return -EINVAL; + + new_entry = READ_ONCE(*entry); + new_entry &= ~AVIC_LOGICAL_ID_ENTRY_GUEST_PHYSICAL_ID_MASK; + new_entry |= (g_physical_id & AVIC_LOGICAL_ID_ENTRY_GUEST_PHYSICAL_ID_MASK); + new_entry |= AVIC_LOGICAL_ID_ENTRY_VALID_MASK; + WRITE_ONCE(*entry, new_entry); + + return 0; +} + +static void avic_invalidate_logical_id_entry(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + bool flat = svm->dfr_reg == APIC_DFR_FLAT; + u32 *entry = avic_get_logical_id_entry(vcpu, svm->ldr_reg, flat); + + if (entry) + clear_bit(AVIC_LOGICAL_ID_ENTRY_VALID_BIT, (unsigned long *)entry); +} + +static int avic_handle_ldr_update(struct kvm_vcpu *vcpu) +{ + int ret = 0; + struct vcpu_svm *svm = to_svm(vcpu); + u32 ldr = kvm_lapic_get_reg(vcpu->arch.apic, APIC_LDR); + u32 id = kvm_xapic_id(vcpu->arch.apic); + + if (ldr == svm->ldr_reg) + return 0; + + avic_invalidate_logical_id_entry(vcpu); + + if (ldr) + ret = avic_ldr_write(vcpu, id, ldr); + + if (!ret) + svm->ldr_reg = ldr; + + return ret; +} + +static int avic_handle_apic_id_update(struct kvm_vcpu *vcpu) +{ + u64 *old, *new; + struct vcpu_svm *svm = to_svm(vcpu); + u32 id = kvm_xapic_id(vcpu->arch.apic); + + if (vcpu->vcpu_id == id) + return 0; + + old = avic_get_physical_id_entry(vcpu, vcpu->vcpu_id); + new = avic_get_physical_id_entry(vcpu, id); + if (!new || !old) + return 1; + + /* We need to move physical_id_entry to new offset */ + *new = *old; + *old = 0ULL; + to_svm(vcpu)->avic_physical_id_cache = new; + + /* + * Also update the guest physical APIC ID in the logical + * APIC ID table entry if already setup the LDR. + */ + if (svm->ldr_reg) + avic_handle_ldr_update(vcpu); + + return 0; +} + +static void avic_handle_dfr_update(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + u32 dfr = kvm_lapic_get_reg(vcpu->arch.apic, APIC_DFR); + + if (svm->dfr_reg == dfr) + return; + + avic_invalidate_logical_id_entry(vcpu); + svm->dfr_reg = dfr; +} + +static int avic_unaccel_trap_write(struct vcpu_svm *svm) +{ + struct kvm_lapic *apic = svm->vcpu.arch.apic; + u32 offset = svm->vmcb->control.exit_info_1 & + AVIC_UNACCEL_ACCESS_OFFSET_MASK; + + switch (offset) { + case APIC_ID: + if (avic_handle_apic_id_update(&svm->vcpu)) + return 0; + break; + case APIC_LDR: + if (avic_handle_ldr_update(&svm->vcpu)) + return 0; + break; + case APIC_DFR: + avic_handle_dfr_update(&svm->vcpu); + break; + default: + break; + } + + kvm_lapic_reg_write(apic, offset, kvm_lapic_get_reg(apic, offset)); + + return 1; +} + +static bool is_avic_unaccelerated_access_trap(u32 offset) +{ + bool ret = false; + + switch (offset) { + case APIC_ID: + case APIC_EOI: + case APIC_RRR: + case APIC_LDR: + case APIC_DFR: + case APIC_SPIV: + case APIC_ESR: + case APIC_ICR: + case APIC_LVTT: + case APIC_LVTTHMR: + case APIC_LVTPC: + case APIC_LVT0: + case APIC_LVT1: + case APIC_LVTERR: + case APIC_TMICT: + case APIC_TDCR: + ret = true; + break; + default: + break; + } + return ret; +} + +int avic_unaccelerated_access_interception(struct vcpu_svm *svm) +{ + int ret = 0; + u32 offset = svm->vmcb->control.exit_info_1 & + AVIC_UNACCEL_ACCESS_OFFSET_MASK; + u32 vector = svm->vmcb->control.exit_info_2 & + AVIC_UNACCEL_ACCESS_VECTOR_MASK; + bool write = (svm->vmcb->control.exit_info_1 >> 32) & + AVIC_UNACCEL_ACCESS_WRITE_MASK; + bool trap = is_avic_unaccelerated_access_trap(offset); + + trace_kvm_avic_unaccelerated_access(svm->vcpu.vcpu_id, offset, + trap, write, vector); + if (trap) { + /* Handling Trap */ + WARN_ONCE(!write, "svm: Handling trap read.\n"); + ret = avic_unaccel_trap_write(svm); + } else { + /* Handling Fault */ + ret = kvm_emulate_instruction(&svm->vcpu, 0); + } + + return ret; +} + +int avic_init_vcpu(struct vcpu_svm *svm) +{ + int ret; + struct kvm_vcpu *vcpu = &svm->vcpu; + + if (!avic || !irqchip_in_kernel(vcpu->kvm)) + return 0; + + ret = avic_init_backing_page(&svm->vcpu); + if (ret) + return ret; + + INIT_LIST_HEAD(&svm->ir_list); + spin_lock_init(&svm->ir_list_lock); + svm->dfr_reg = APIC_DFR_FLAT; + + return ret; +} + +void avic_post_state_restore(struct kvm_vcpu *vcpu) +{ + if (avic_handle_apic_id_update(vcpu) != 0) + return; + avic_handle_dfr_update(vcpu); + avic_handle_ldr_update(vcpu); +} + +void svm_toggle_avic_for_irq_window(struct kvm_vcpu *vcpu, bool activate) +{ + if (!avic || !lapic_in_kernel(vcpu)) + return; + + srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); + kvm_request_apicv_update(vcpu->kvm, activate, + APICV_INHIBIT_REASON_IRQWIN); + vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); +} + +void svm_set_virtual_apic_mode(struct kvm_vcpu *vcpu) +{ + return; +} + +void svm_hwapic_irr_update(struct kvm_vcpu *vcpu, int max_irr) +{ +} + +void svm_hwapic_isr_update(struct kvm_vcpu *vcpu, int max_isr) +{ +} + +static int svm_set_pi_irte_mode(struct kvm_vcpu *vcpu, bool activate) +{ + int ret = 0; + unsigned long flags; + struct amd_svm_iommu_ir *ir; + struct vcpu_svm *svm = to_svm(vcpu); + + if (!kvm_arch_has_assigned_device(vcpu->kvm)) + return 0; + + /* + * Here, we go through the per-vcpu ir_list to update all existing + * interrupt remapping table entry targeting this vcpu. + */ + spin_lock_irqsave(&svm->ir_list_lock, flags); + + if (list_empty(&svm->ir_list)) + goto out; + + list_for_each_entry(ir, &svm->ir_list, node) { + if (activate) + ret = amd_iommu_activate_guest_mode(ir->data); + else + ret = amd_iommu_deactivate_guest_mode(ir->data); + if (ret) + break; + } +out: + spin_unlock_irqrestore(&svm->ir_list_lock, flags); + return ret; +} + +void svm_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + struct vmcb *vmcb = svm->vmcb; + bool activated = kvm_vcpu_apicv_active(vcpu); + + if (!avic) + return; + + if (activated) { + /** + * During AVIC temporary deactivation, guest could update + * APIC ID, DFR and LDR registers, which would not be trapped + * by avic_unaccelerated_access_interception(). In this case, + * we need to check and update the AVIC logical APIC ID table + * accordingly before re-activating. + */ + avic_post_state_restore(vcpu); + vmcb->control.int_ctl |= AVIC_ENABLE_MASK; + } else { + vmcb->control.int_ctl &= ~AVIC_ENABLE_MASK; + } + mark_dirty(vmcb, VMCB_AVIC); + + svm_set_pi_irte_mode(vcpu, activated); +} + +void svm_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap) +{ + return; +} + +int svm_deliver_avic_intr(struct kvm_vcpu *vcpu, int vec) +{ + if (!vcpu->arch.apicv_active) + return -1; + + kvm_lapic_set_irr(vec, vcpu->arch.apic); + smp_mb__after_atomic(); + + if (avic_vcpu_is_running(vcpu)) { + int cpuid = vcpu->cpu; + + if (cpuid != get_cpu()) + wrmsrl(SVM_AVIC_DOORBELL, kvm_cpu_get_apicid(cpuid)); + put_cpu(); + } else + kvm_vcpu_wake_up(vcpu); + + return 0; +} + +bool svm_dy_apicv_has_pending_interrupt(struct kvm_vcpu *vcpu) +{ + return false; +} + +static void svm_ir_list_del(struct vcpu_svm *svm, struct amd_iommu_pi_data *pi) +{ + unsigned long flags; + struct amd_svm_iommu_ir *cur; + + spin_lock_irqsave(&svm->ir_list_lock, flags); + list_for_each_entry(cur, &svm->ir_list, node) { + if (cur->data != pi->ir_data) + continue; + list_del(&cur->node); + kfree(cur); + break; + } + spin_unlock_irqrestore(&svm->ir_list_lock, flags); +} + +static int svm_ir_list_add(struct vcpu_svm *svm, struct amd_iommu_pi_data *pi) +{ + int ret = 0; + unsigned long flags; + struct amd_svm_iommu_ir *ir; + + /** + * In some cases, the existing irte is updaed and re-set, + * so we need to check here if it's already been * added + * to the ir_list. + */ + if (pi->ir_data && (pi->prev_ga_tag != 0)) { + struct kvm *kvm = svm->vcpu.kvm; + u32 vcpu_id = AVIC_GATAG_TO_VCPUID(pi->prev_ga_tag); + struct kvm_vcpu *prev_vcpu = kvm_get_vcpu_by_id(kvm, vcpu_id); + struct vcpu_svm *prev_svm; + + if (!prev_vcpu) { + ret = -EINVAL; + goto out; + } + + prev_svm = to_svm(prev_vcpu); + svm_ir_list_del(prev_svm, pi); + } + + /** + * Allocating new amd_iommu_pi_data, which will get + * add to the per-vcpu ir_list. + */ + ir = kzalloc(sizeof(struct amd_svm_iommu_ir), GFP_KERNEL_ACCOUNT); + if (!ir) { + ret = -ENOMEM; + goto out; + } + ir->data = pi->ir_data; + + spin_lock_irqsave(&svm->ir_list_lock, flags); + list_add(&ir->node, &svm->ir_list); + spin_unlock_irqrestore(&svm->ir_list_lock, flags); +out: + return ret; +} + +/** + * Note: + * The HW cannot support posting multicast/broadcast + * interrupts to a vCPU. So, we still use legacy interrupt + * remapping for these kind of interrupts. + * + * For lowest-priority interrupts, we only support + * those with single CPU as the destination, e.g. user + * configures the interrupts via /proc/irq or uses + * irqbalance to make the interrupts single-CPU. + */ +static int +get_pi_vcpu_info(struct kvm *kvm, struct kvm_kernel_irq_routing_entry *e, + struct vcpu_data *vcpu_info, struct vcpu_svm **svm) +{ + struct kvm_lapic_irq irq; + struct kvm_vcpu *vcpu = NULL; + + kvm_set_msi_irq(kvm, e, &irq); + + if (!kvm_intr_is_single_vcpu(kvm, &irq, &vcpu) || + !kvm_irq_is_postable(&irq)) { + pr_debug("SVM: %s: use legacy intr remap mode for irq %u\n", + __func__, irq.vector); + return -1; + } + + pr_debug("SVM: %s: use GA mode for irq %u\n", __func__, + irq.vector); + *svm = to_svm(vcpu); + vcpu_info->pi_desc_addr = __sme_set(page_to_phys((*svm)->avic_backing_page)); + vcpu_info->vector = irq.vector; + + return 0; +} + +/* + * svm_update_pi_irte - set IRTE for Posted-Interrupts + * + * @kvm: kvm + * @host_irq: host irq of the interrupt + * @guest_irq: gsi of the interrupt + * @set: set or unset PI + * returns 0 on success, < 0 on failure + */ +int svm_update_pi_irte(struct kvm *kvm, unsigned int host_irq, + uint32_t guest_irq, bool set) +{ + struct kvm_kernel_irq_routing_entry *e; + struct kvm_irq_routing_table *irq_rt; + int idx, ret = -EINVAL; + + if (!kvm_arch_has_assigned_device(kvm) || + !irq_remapping_cap(IRQ_POSTING_CAP)) + return 0; + + pr_debug("SVM: %s: host_irq=%#x, guest_irq=%#x, set=%#x\n", + __func__, host_irq, guest_irq, set); + + idx = srcu_read_lock(&kvm->irq_srcu); + irq_rt = srcu_dereference(kvm->irq_routing, &kvm->irq_srcu); + WARN_ON(guest_irq >= irq_rt->nr_rt_entries); + + hlist_for_each_entry(e, &irq_rt->map[guest_irq], link) { + struct vcpu_data vcpu_info; + struct vcpu_svm *svm = NULL; + + if (e->type != KVM_IRQ_ROUTING_MSI) + continue; + + /** + * Here, we setup with legacy mode in the following cases: + * 1. When cannot target interrupt to a specific vcpu. + * 2. Unsetting posted interrupt. + * 3. APIC virtialization is disabled for the vcpu. + * 4. IRQ has incompatible delivery mode (SMI, INIT, etc) + */ + if (!get_pi_vcpu_info(kvm, e, &vcpu_info, &svm) && set && + kvm_vcpu_apicv_active(&svm->vcpu)) { + struct amd_iommu_pi_data pi; + + /* Try to enable guest_mode in IRTE */ + pi.base = __sme_set(page_to_phys(svm->avic_backing_page) & + AVIC_HPA_MASK); + pi.ga_tag = AVIC_GATAG(to_kvm_svm(kvm)->avic_vm_id, + svm->vcpu.vcpu_id); + pi.is_guest_mode = true; + pi.vcpu_data = &vcpu_info; + ret = irq_set_vcpu_affinity(host_irq, &pi); + + /** + * Here, we successfully setting up vcpu affinity in + * IOMMU guest mode. Now, we need to store the posted + * interrupt information in a per-vcpu ir_list so that + * we can reference to them directly when we update vcpu + * scheduling information in IOMMU irte. + */ + if (!ret && pi.is_guest_mode) + svm_ir_list_add(svm, &pi); + } else { + /* Use legacy mode in IRTE */ + struct amd_iommu_pi_data pi; + + /** + * Here, pi is used to: + * - Tell IOMMU to use legacy mode for this interrupt. + * - Retrieve ga_tag of prior interrupt remapping data. + */ + pi.is_guest_mode = false; + ret = irq_set_vcpu_affinity(host_irq, &pi); + + /** + * Check if the posted interrupt was previously + * setup with the guest_mode by checking if the ga_tag + * was cached. If so, we need to clean up the per-vcpu + * ir_list. + */ + if (!ret && pi.prev_ga_tag) { + int id = AVIC_GATAG_TO_VCPUID(pi.prev_ga_tag); + struct kvm_vcpu *vcpu; + + vcpu = kvm_get_vcpu_by_id(kvm, id); + if (vcpu) + svm_ir_list_del(to_svm(vcpu), &pi); + } + } + + if (!ret && svm) { + trace_kvm_pi_irte_update(host_irq, svm->vcpu.vcpu_id, + e->gsi, vcpu_info.vector, + vcpu_info.pi_desc_addr, set); + } + + if (ret < 0) { + pr_err("%s: failed to update PI IRTE\n", __func__); + goto out; + } + } + + ret = 0; +out: + srcu_read_unlock(&kvm->irq_srcu, idx); + return ret; +} + +bool svm_check_apicv_inhibit_reasons(ulong bit) +{ + ulong supported = BIT(APICV_INHIBIT_REASON_DISABLE) | + BIT(APICV_INHIBIT_REASON_HYPERV) | + BIT(APICV_INHIBIT_REASON_NESTED) | + BIT(APICV_INHIBIT_REASON_IRQWIN) | + BIT(APICV_INHIBIT_REASON_PIT_REINJ) | + BIT(APICV_INHIBIT_REASON_X2APIC); + + return supported & BIT(bit); +} + +void svm_pre_update_apicv_exec_ctrl(struct kvm *kvm, bool activate) +{ + avic_update_access_page(kvm, activate); +} + +static inline int +avic_update_iommu_vcpu_affinity(struct kvm_vcpu *vcpu, int cpu, bool r) +{ + int ret = 0; + unsigned long flags; + struct amd_svm_iommu_ir *ir; + struct vcpu_svm *svm = to_svm(vcpu); + + if (!kvm_arch_has_assigned_device(vcpu->kvm)) + return 0; + + /* + * Here, we go through the per-vcpu ir_list to update all existing + * interrupt remapping table entry targeting this vcpu. + */ + spin_lock_irqsave(&svm->ir_list_lock, flags); + + if (list_empty(&svm->ir_list)) + goto out; + + list_for_each_entry(ir, &svm->ir_list, node) { + ret = amd_iommu_update_ga(cpu, r, ir->data); + if (ret) + break; + } +out: + spin_unlock_irqrestore(&svm->ir_list_lock, flags); + return ret; +} + +void avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu) +{ + u64 entry; + /* ID = 0xff (broadcast), ID > 0xff (reserved) */ + int h_physical_id = kvm_cpu_get_apicid(cpu); + struct vcpu_svm *svm = to_svm(vcpu); + + if (!kvm_vcpu_apicv_active(vcpu)) + return; + + /* + * Since the host physical APIC id is 8 bits, + * we can support host APIC ID upto 255. + */ + if (WARN_ON(h_physical_id > AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK)) + return; + + entry = READ_ONCE(*(svm->avic_physical_id_cache)); + WARN_ON(entry & AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK); + + entry &= ~AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK; + entry |= (h_physical_id & AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK); + + entry &= ~AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK; + if (svm->avic_is_running) + entry |= AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK; + + WRITE_ONCE(*(svm->avic_physical_id_cache), entry); + avic_update_iommu_vcpu_affinity(vcpu, h_physical_id, + svm->avic_is_running); +} + +void avic_vcpu_put(struct kvm_vcpu *vcpu) +{ + u64 entry; + struct vcpu_svm *svm = to_svm(vcpu); + + if (!kvm_vcpu_apicv_active(vcpu)) + return; + + entry = READ_ONCE(*(svm->avic_physical_id_cache)); + if (entry & AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK) + avic_update_iommu_vcpu_affinity(vcpu, -1, 0); + + entry &= ~AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK; + WRITE_ONCE(*(svm->avic_physical_id_cache), entry); +} + +/** + * This function is called during VCPU halt/unhalt. + */ +static void avic_set_running(struct kvm_vcpu *vcpu, bool is_run) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + svm->avic_is_running = is_run; + if (is_run) + avic_vcpu_load(vcpu, vcpu->cpu); + else + avic_vcpu_put(vcpu); +} + +void svm_vcpu_blocking(struct kvm_vcpu *vcpu) +{ + avic_set_running(vcpu, false); +} + +void svm_vcpu_unblocking(struct kvm_vcpu *vcpu) +{ + if (kvm_check_request(KVM_REQ_APICV_UPDATE, vcpu)) + kvm_vcpu_update_apicv(vcpu); + avic_set_running(vcpu, true); +} diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c new file mode 100644 index 000000000000..90a1ca939627 --- /dev/null +++ b/arch/x86/kvm/svm/nested.c @@ -0,0 +1,823 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Kernel-based Virtual Machine driver for Linux + * + * AMD SVM support + * + * Copyright (C) 2006 Qumranet, Inc. + * Copyright 2010 Red Hat, Inc. and/or its affiliates. + * + * Authors: + * Yaniv Kamay <yaniv@qumranet.com> + * Avi Kivity <avi@qumranet.com> + */ + +#define pr_fmt(fmt) "SVM: " fmt + +#include <linux/kvm_types.h> +#include <linux/kvm_host.h> +#include <linux/kernel.h> + +#include <asm/msr-index.h> + +#include "kvm_emulate.h" +#include "trace.h" +#include "mmu.h" +#include "x86.h" +#include "svm.h" + +static void nested_svm_inject_npf_exit(struct kvm_vcpu *vcpu, + struct x86_exception *fault) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + if (svm->vmcb->control.exit_code != SVM_EXIT_NPF) { + /* + * TODO: track the cause of the nested page fault, and + * correctly fill in the high bits of exit_info_1. + */ + svm->vmcb->control.exit_code = SVM_EXIT_NPF; + svm->vmcb->control.exit_code_hi = 0; + svm->vmcb->control.exit_info_1 = (1ULL << 32); + svm->vmcb->control.exit_info_2 = fault->address; + } + + svm->vmcb->control.exit_info_1 &= ~0xffffffffULL; + svm->vmcb->control.exit_info_1 |= fault->error_code; + + /* + * The present bit is always zero for page structure faults on real + * hardware. + */ + if (svm->vmcb->control.exit_info_1 & (2ULL << 32)) + svm->vmcb->control.exit_info_1 &= ~1; + + nested_svm_vmexit(svm); +} + +static u64 nested_svm_get_tdp_pdptr(struct kvm_vcpu *vcpu, int index) +{ + struct vcpu_svm *svm = to_svm(vcpu); + u64 cr3 = svm->nested.nested_cr3; + u64 pdpte; + int ret; + + ret = kvm_vcpu_read_guest_page(vcpu, gpa_to_gfn(__sme_clr(cr3)), &pdpte, + offset_in_page(cr3) + index * 8, 8); + if (ret) + return 0; + return pdpte; +} + +static unsigned long nested_svm_get_tdp_cr3(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + return svm->nested.nested_cr3; +} + +static void nested_svm_init_mmu_context(struct kvm_vcpu *vcpu) +{ + WARN_ON(mmu_is_nested(vcpu)); + + vcpu->arch.mmu = &vcpu->arch.guest_mmu; + kvm_init_shadow_mmu(vcpu); + vcpu->arch.mmu->get_guest_pgd = nested_svm_get_tdp_cr3; + vcpu->arch.mmu->get_pdptr = nested_svm_get_tdp_pdptr; + vcpu->arch.mmu->inject_page_fault = nested_svm_inject_npf_exit; + vcpu->arch.mmu->shadow_root_level = kvm_x86_ops.get_tdp_level(vcpu); + reset_shadow_zero_bits_mask(vcpu, vcpu->arch.mmu); + vcpu->arch.walk_mmu = &vcpu->arch.nested_mmu; +} + +static void nested_svm_uninit_mmu_context(struct kvm_vcpu *vcpu) +{ + vcpu->arch.mmu = &vcpu->arch.root_mmu; + vcpu->arch.walk_mmu = &vcpu->arch.root_mmu; +} + +void recalc_intercepts(struct vcpu_svm *svm) +{ + struct vmcb_control_area *c, *h; + struct nested_state *g; + + mark_dirty(svm->vmcb, VMCB_INTERCEPTS); + + if (!is_guest_mode(&svm->vcpu)) + return; + + c = &svm->vmcb->control; + h = &svm->nested.hsave->control; + g = &svm->nested; + + c->intercept_cr = h->intercept_cr; + c->intercept_dr = h->intercept_dr; + c->intercept_exceptions = h->intercept_exceptions; + c->intercept = h->intercept; + + if (svm->vcpu.arch.hflags & HF_VINTR_MASK) { + /* We only want the cr8 intercept bits of L1 */ + c->intercept_cr &= ~(1U << INTERCEPT_CR8_READ); + c->intercept_cr &= ~(1U << INTERCEPT_CR8_WRITE); + + /* + * Once running L2 with HF_VINTR_MASK, EFLAGS.IF does not + * affect any interrupt we may want to inject; therefore, + * interrupt window vmexits are irrelevant to L0. + */ + c->intercept &= ~(1ULL << INTERCEPT_VINTR); + } + + /* We don't want to see VMMCALLs from a nested guest */ + c->intercept &= ~(1ULL << INTERCEPT_VMMCALL); + + c->intercept_cr |= g->intercept_cr; + c->intercept_dr |= g->intercept_dr; + c->intercept_exceptions |= g->intercept_exceptions; + c->intercept |= g->intercept; +} + +static void copy_vmcb_control_area(struct vmcb *dst_vmcb, struct vmcb *from_vmcb) +{ + struct vmcb_control_area *dst = &dst_vmcb->control; + struct vmcb_control_area *from = &from_vmcb->control; + + dst->intercept_cr = from->intercept_cr; + dst->intercept_dr = from->intercept_dr; + dst->intercept_exceptions = from->intercept_exceptions; + dst->intercept = from->intercept; + dst->iopm_base_pa = from->iopm_base_pa; + dst->msrpm_base_pa = from->msrpm_base_pa; + dst->tsc_offset = from->tsc_offset; + dst->asid = from->asid; + dst->tlb_ctl = from->tlb_ctl; + dst->int_ctl = from->int_ctl; + dst->int_vector = from->int_vector; + dst->int_state = from->int_state; + dst->exit_code = from->exit_code; + dst->exit_code_hi = from->exit_code_hi; + dst->exit_info_1 = from->exit_info_1; + dst->exit_info_2 = from->exit_info_2; + dst->exit_int_info = from->exit_int_info; + dst->exit_int_info_err = from->exit_int_info_err; + dst->nested_ctl = from->nested_ctl; + dst->event_inj = from->event_inj; + dst->event_inj_err = from->event_inj_err; + dst->nested_cr3 = from->nested_cr3; + dst->virt_ext = from->virt_ext; + dst->pause_filter_count = from->pause_filter_count; + dst->pause_filter_thresh = from->pause_filter_thresh; +} + +static bool nested_svm_vmrun_msrpm(struct vcpu_svm *svm) +{ + /* + * This function merges the msr permission bitmaps of kvm and the + * nested vmcb. It is optimized in that it only merges the parts where + * the kvm msr permission bitmap may contain zero bits + */ + int i; + + if (!(svm->nested.intercept & (1ULL << INTERCEPT_MSR_PROT))) + return true; + + for (i = 0; i < MSRPM_OFFSETS; i++) { + u32 value, p; + u64 offset; + + if (msrpm_offsets[i] == 0xffffffff) + break; + + p = msrpm_offsets[i]; + offset = svm->nested.vmcb_msrpm + (p * 4); + + if (kvm_vcpu_read_guest(&svm->vcpu, offset, &value, 4)) + return false; + + svm->nested.msrpm[p] = svm->msrpm[p] | value; + } + + svm->vmcb->control.msrpm_base_pa = __sme_set(__pa(svm->nested.msrpm)); + + return true; +} + +static bool nested_vmcb_checks(struct vmcb *vmcb) +{ + if ((vmcb->save.efer & EFER_SVME) == 0) + return false; + + if ((vmcb->control.intercept & (1ULL << INTERCEPT_VMRUN)) == 0) + return false; + + if (vmcb->control.asid == 0) + return false; + + if ((vmcb->control.nested_ctl & SVM_NESTED_CTL_NP_ENABLE) && + !npt_enabled) + return false; + + return true; +} + +void enter_svm_guest_mode(struct vcpu_svm *svm, u64 vmcb_gpa, + struct vmcb *nested_vmcb, struct kvm_host_map *map) +{ + bool evaluate_pending_interrupts = + is_intercept(svm, INTERCEPT_VINTR) || + is_intercept(svm, INTERCEPT_IRET); + + if (kvm_get_rflags(&svm->vcpu) & X86_EFLAGS_IF) + svm->vcpu.arch.hflags |= HF_HIF_MASK; + else + svm->vcpu.arch.hflags &= ~HF_HIF_MASK; + + if (nested_vmcb->control.nested_ctl & SVM_NESTED_CTL_NP_ENABLE) { + svm->nested.nested_cr3 = nested_vmcb->control.nested_cr3; + nested_svm_init_mmu_context(&svm->vcpu); + } + + /* Load the nested guest state */ + svm->vmcb->save.es = nested_vmcb->save.es; + svm->vmcb->save.cs = nested_vmcb->save.cs; + svm->vmcb->save.ss = nested_vmcb->save.ss; + svm->vmcb->save.ds = nested_vmcb->save.ds; + svm->vmcb->save.gdtr = nested_vmcb->save.gdtr; + svm->vmcb->save.idtr = nested_vmcb->save.idtr; + kvm_set_rflags(&svm->vcpu, nested_vmcb->save.rflags); + svm_set_efer(&svm->vcpu, nested_vmcb->save.efer); + svm_set_cr0(&svm->vcpu, nested_vmcb->save.cr0); + svm_set_cr4(&svm->vcpu, nested_vmcb->save.cr4); + if (npt_enabled) { + svm->vmcb->save.cr3 = nested_vmcb->save.cr3; + svm->vcpu.arch.cr3 = nested_vmcb->save.cr3; + } else + (void)kvm_set_cr3(&svm->vcpu, nested_vmcb->save.cr3); + + /* Guest paging mode is active - reset mmu */ + kvm_mmu_reset_context(&svm->vcpu); + + svm->vmcb->save.cr2 = svm->vcpu.arch.cr2 = nested_vmcb->save.cr2; + kvm_rax_write(&svm->vcpu, nested_vmcb->save.rax); + kvm_rsp_write(&svm->vcpu, nested_vmcb->save.rsp); + kvm_rip_write(&svm->vcpu, nested_vmcb->save.rip); + + /* In case we don't even reach vcpu_run, the fields are not updated */ + svm->vmcb->save.rax = nested_vmcb->save.rax; + svm->vmcb->save.rsp = nested_vmcb->save.rsp; + svm->vmcb->save.rip = nested_vmcb->save.rip; + svm->vmcb->save.dr7 = nested_vmcb->save.dr7; + svm->vmcb->save.dr6 = nested_vmcb->save.dr6; + svm->vmcb->save.cpl = nested_vmcb->save.cpl; + + svm->nested.vmcb_msrpm = nested_vmcb->control.msrpm_base_pa & ~0x0fffULL; + svm->nested.vmcb_iopm = nested_vmcb->control.iopm_base_pa & ~0x0fffULL; + + /* cache intercepts */ + svm->nested.intercept_cr = nested_vmcb->control.intercept_cr; + svm->nested.intercept_dr = nested_vmcb->control.intercept_dr; + svm->nested.intercept_exceptions = nested_vmcb->control.intercept_exceptions; + svm->nested.intercept = nested_vmcb->control.intercept; + + svm_flush_tlb(&svm->vcpu, true); + svm->vmcb->control.int_ctl = nested_vmcb->control.int_ctl | V_INTR_MASKING_MASK; + if (nested_vmcb->control.int_ctl & V_INTR_MASKING_MASK) + svm->vcpu.arch.hflags |= HF_VINTR_MASK; + else + svm->vcpu.arch.hflags &= ~HF_VINTR_MASK; + + svm->vcpu.arch.tsc_offset += nested_vmcb->control.tsc_offset; + svm->vmcb->control.tsc_offset = svm->vcpu.arch.tsc_offset; + + svm->vmcb->control.virt_ext = nested_vmcb->control.virt_ext; + svm->vmcb->control.int_vector = nested_vmcb->control.int_vector; + svm->vmcb->control.int_state = nested_vmcb->control.int_state; + svm->vmcb->control.event_inj = nested_vmcb->control.event_inj; + svm->vmcb->control.event_inj_err = nested_vmcb->control.event_inj_err; + + svm->vmcb->control.pause_filter_count = + nested_vmcb->control.pause_filter_count; + svm->vmcb->control.pause_filter_thresh = + nested_vmcb->control.pause_filter_thresh; + + kvm_vcpu_unmap(&svm->vcpu, map, true); + + /* Enter Guest-Mode */ + enter_guest_mode(&svm->vcpu); + + /* + * Merge guest and host intercepts - must be called with vcpu in + * guest-mode to take affect here + */ + recalc_intercepts(svm); + + svm->nested.vmcb = vmcb_gpa; + + /* + * If L1 had a pending IRQ/NMI before executing VMRUN, + * which wasn't delivered because it was disallowed (e.g. + * interrupts disabled), L0 needs to evaluate if this pending + * event should cause an exit from L2 to L1 or be delivered + * directly to L2. + * + * Usually this would be handled by the processor noticing an + * IRQ/NMI window request. However, VMRUN can unblock interrupts + * by implicitly setting GIF, so force L0 to perform pending event + * evaluation by requesting a KVM_REQ_EVENT. + */ + enable_gif(svm); + if (unlikely(evaluate_pending_interrupts)) + kvm_make_request(KVM_REQ_EVENT, &svm->vcpu); + + mark_all_dirty(svm->vmcb); +} + +int nested_svm_vmrun(struct vcpu_svm *svm) +{ + int ret; + struct vmcb *nested_vmcb; + struct vmcb *hsave = svm->nested.hsave; + struct vmcb *vmcb = svm->vmcb; + struct kvm_host_map map; + u64 vmcb_gpa; + + vmcb_gpa = svm->vmcb->save.rax; + + ret = kvm_vcpu_map(&svm->vcpu, gpa_to_gfn(vmcb_gpa), &map); + if (ret == -EINVAL) { + kvm_inject_gp(&svm->vcpu, 0); + return 1; + } else if (ret) { + return kvm_skip_emulated_instruction(&svm->vcpu); + } + + ret = kvm_skip_emulated_instruction(&svm->vcpu); + + nested_vmcb = map.hva; + + if (!nested_vmcb_checks(nested_vmcb)) { + nested_vmcb->control.exit_code = SVM_EXIT_ERR; + nested_vmcb->control.exit_code_hi = 0; + nested_vmcb->control.exit_info_1 = 0; + nested_vmcb->control.exit_info_2 = 0; + + kvm_vcpu_unmap(&svm->vcpu, &map, true); + + return ret; + } + + trace_kvm_nested_vmrun(svm->vmcb->save.rip, vmcb_gpa, + nested_vmcb->save.rip, + nested_vmcb->control.int_ctl, + nested_vmcb->control.event_inj, + nested_vmcb->control.nested_ctl); + + trace_kvm_nested_intercepts(nested_vmcb->control.intercept_cr & 0xffff, + nested_vmcb->control.intercept_cr >> 16, + nested_vmcb->control.intercept_exceptions, + nested_vmcb->control.intercept); + + /* Clear internal status */ + kvm_clear_exception_queue(&svm->vcpu); + kvm_clear_interrupt_queue(&svm->vcpu); + + /* + * Save the old vmcb, so we don't need to pick what we save, but can + * restore everything when a VMEXIT occurs + */ + hsave->save.es = vmcb->save.es; + hsave->save.cs = vmcb->save.cs; + hsave->save.ss = vmcb->save.ss; + hsave->save.ds = vmcb->save.ds; + hsave->save.gdtr = vmcb->save.gdtr; + hsave->save.idtr = vmcb->save.idtr; + hsave->save.efer = svm->vcpu.arch.efer; + hsave->save.cr0 = kvm_read_cr0(&svm->vcpu); + hsave->save.cr4 = svm->vcpu.arch.cr4; + hsave->save.rflags = kvm_get_rflags(&svm->vcpu); + hsave->save.rip = kvm_rip_read(&svm->vcpu); + hsave->save.rsp = vmcb->save.rsp; + hsave->save.rax = vmcb->save.rax; + if (npt_enabled) + hsave->save.cr3 = vmcb->save.cr3; + else + hsave->save.cr3 = kvm_read_cr3(&svm->vcpu); + + copy_vmcb_control_area(hsave, vmcb); + + enter_svm_guest_mode(svm, vmcb_gpa, nested_vmcb, &map); + + if (!nested_svm_vmrun_msrpm(svm)) { + svm->vmcb->control.exit_code = SVM_EXIT_ERR; + svm->vmcb->control.exit_code_hi = 0; + svm->vmcb->control.exit_info_1 = 0; + svm->vmcb->control.exit_info_2 = 0; + + nested_svm_vmexit(svm); + } + + return ret; +} + +void nested_svm_vmloadsave(struct vmcb *from_vmcb, struct vmcb *to_vmcb) +{ + to_vmcb->save.fs = from_vmcb->save.fs; + to_vmcb->save.gs = from_vmcb->save.gs; + to_vmcb->save.tr = from_vmcb->save.tr; + to_vmcb->save.ldtr = from_vmcb->save.ldtr; + to_vmcb->save.kernel_gs_base = from_vmcb->save.kernel_gs_base; + to_vmcb->save.star = from_vmcb->save.star; + to_vmcb->save.lstar = from_vmcb->save.lstar; + to_vmcb->save.cstar = from_vmcb->save.cstar; + to_vmcb->save.sfmask = from_vmcb->save.sfmask; + to_vmcb->save.sysenter_cs = from_vmcb->save.sysenter_cs; + to_vmcb->save.sysenter_esp = from_vmcb->save.sysenter_esp; + to_vmcb->save.sysenter_eip = from_vmcb->save.sysenter_eip; +} + +int nested_svm_vmexit(struct vcpu_svm *svm) +{ + int rc; + struct vmcb *nested_vmcb; + struct vmcb *hsave = svm->nested.hsave; + struct vmcb *vmcb = svm->vmcb; + struct kvm_host_map map; + + trace_kvm_nested_vmexit_inject(vmcb->control.exit_code, + vmcb->control.exit_info_1, + vmcb->control.exit_info_2, + vmcb->control.exit_int_info, + vmcb->control.exit_int_info_err, + KVM_ISA_SVM); + + rc = kvm_vcpu_map(&svm->vcpu, gpa_to_gfn(svm->nested.vmcb), &map); + if (rc) { + if (rc == -EINVAL) + kvm_inject_gp(&svm->vcpu, 0); + return 1; + } + + nested_vmcb = map.hva; + + /* Exit Guest-Mode */ + leave_guest_mode(&svm->vcpu); + svm->nested.vmcb = 0; + + /* Give the current vmcb to the guest */ + disable_gif(svm); + + nested_vmcb->save.es = vmcb->save.es; + nested_vmcb->save.cs = vmcb->save.cs; + nested_vmcb->save.ss = vmcb->save.ss; + nested_vmcb->save.ds = vmcb->save.ds; + nested_vmcb->save.gdtr = vmcb->save.gdtr; + nested_vmcb->save.idtr = vmcb->save.idtr; + nested_vmcb->save.efer = svm->vcpu.arch.efer; + nested_vmcb->save.cr0 = kvm_read_cr0(&svm->vcpu); + nested_vmcb->save.cr3 = kvm_read_cr3(&svm->vcpu); + nested_vmcb->save.cr2 = vmcb->save.cr2; + nested_vmcb->save.cr4 = svm->vcpu.arch.cr4; + nested_vmcb->save.rflags = kvm_get_rflags(&svm->vcpu); + nested_vmcb->save.rip = vmcb->save.rip; + nested_vmcb->save.rsp = vmcb->save.rsp; + nested_vmcb->save.rax = vmcb->save.rax; + nested_vmcb->save.dr7 = vmcb->save.dr7; + nested_vmcb->save.dr6 = vmcb->save.dr6; + nested_vmcb->save.cpl = vmcb->save.cpl; + + nested_vmcb->control.int_ctl = vmcb->control.int_ctl; + nested_vmcb->control.int_vector = vmcb->control.int_vector; + nested_vmcb->control.int_state = vmcb->control.int_state; + nested_vmcb->control.exit_code = vmcb->control.exit_code; + nested_vmcb->control.exit_code_hi = vmcb->control.exit_code_hi; + nested_vmcb->control.exit_info_1 = vmcb->control.exit_info_1; + nested_vmcb->control.exit_info_2 = vmcb->control.exit_info_2; + nested_vmcb->control.exit_int_info = vmcb->control.exit_int_info; + nested_vmcb->control.exit_int_info_err = vmcb->control.exit_int_info_err; + + if (svm->nrips_enabled) + nested_vmcb->control.next_rip = vmcb->control.next_rip; + + /* + * If we emulate a VMRUN/#VMEXIT in the same host #vmexit cycle we have + * to make sure that we do not lose injected events. So check event_inj + * here and copy it to exit_int_info if it is valid. + * Exit_int_info and event_inj can't be both valid because the case + * below only happens on a VMRUN instruction intercept which has + * no valid exit_int_info set. + */ + if (vmcb->control.event_inj & SVM_EVTINJ_VALID) { + struct vmcb_control_area *nc = &nested_vmcb->control; + + nc->exit_int_info = vmcb->control.event_inj; + nc->exit_int_info_err = vmcb->control.event_inj_err; + } + + nested_vmcb->control.tlb_ctl = 0; + nested_vmcb->control.event_inj = 0; + nested_vmcb->control.event_inj_err = 0; + + nested_vmcb->control.pause_filter_count = + svm->vmcb->control.pause_filter_count; + nested_vmcb->control.pause_filter_thresh = + svm->vmcb->control.pause_filter_thresh; + + /* We always set V_INTR_MASKING and remember the old value in hflags */ + if (!(svm->vcpu.arch.hflags & HF_VINTR_MASK)) + nested_vmcb->control.int_ctl &= ~V_INTR_MASKING_MASK; + + /* Restore the original control entries */ + copy_vmcb_control_area(vmcb, hsave); + + svm->vcpu.arch.tsc_offset = svm->vmcb->control.tsc_offset; + kvm_clear_exception_queue(&svm->vcpu); + kvm_clear_interrupt_queue(&svm->vcpu); + + svm->nested.nested_cr3 = 0; + + /* Restore selected save entries */ + svm->vmcb->save.es = hsave->save.es; + svm->vmcb->save.cs = hsave->save.cs; + svm->vmcb->save.ss = hsave->save.ss; + svm->vmcb->save.ds = hsave->save.ds; + svm->vmcb->save.gdtr = hsave->save.gdtr; + svm->vmcb->save.idtr = hsave->save.idtr; + kvm_set_rflags(&svm->vcpu, hsave->save.rflags); + svm_set_efer(&svm->vcpu, hsave->save.efer); + svm_set_cr0(&svm->vcpu, hsave->save.cr0 | X86_CR0_PE); + svm_set_cr4(&svm->vcpu, hsave->save.cr4); + if (npt_enabled) { + svm->vmcb->save.cr3 = hsave->save.cr3; + svm->vcpu.arch.cr3 = hsave->save.cr3; + } else { + (void)kvm_set_cr3(&svm->vcpu, hsave->save.cr3); + } + kvm_rax_write(&svm->vcpu, hsave->save.rax); + kvm_rsp_write(&svm->vcpu, hsave->save.rsp); + kvm_rip_write(&svm->vcpu, hsave->save.rip); + svm->vmcb->save.dr7 = 0; + svm->vmcb->save.cpl = 0; + svm->vmcb->control.exit_int_info = 0; + + mark_all_dirty(svm->vmcb); + + kvm_vcpu_unmap(&svm->vcpu, &map, true); + + nested_svm_uninit_mmu_context(&svm->vcpu); + kvm_mmu_reset_context(&svm->vcpu); + kvm_mmu_load(&svm->vcpu); + + /* + * Drop what we picked up for L2 via svm_complete_interrupts() so it + * doesn't end up in L1. + */ + svm->vcpu.arch.nmi_injected = false; + kvm_clear_exception_queue(&svm->vcpu); + kvm_clear_interrupt_queue(&svm->vcpu); + + return 0; +} + +static int nested_svm_exit_handled_msr(struct vcpu_svm *svm) +{ + u32 offset, msr, value; + int write, mask; + + if (!(svm->nested.intercept & (1ULL << INTERCEPT_MSR_PROT))) + return NESTED_EXIT_HOST; + + msr = svm->vcpu.arch.regs[VCPU_REGS_RCX]; + offset = svm_msrpm_offset(msr); + write = svm->vmcb->control.exit_info_1 & 1; + mask = 1 << ((2 * (msr & 0xf)) + write); + + if (offset == MSR_INVALID) + return NESTED_EXIT_DONE; + + /* Offset is in 32 bit units but need in 8 bit units */ + offset *= 4; + + if (kvm_vcpu_read_guest(&svm->vcpu, svm->nested.vmcb_msrpm + offset, &value, 4)) + return NESTED_EXIT_DONE; + + return (value & mask) ? NESTED_EXIT_DONE : NESTED_EXIT_HOST; +} + +/* DB exceptions for our internal use must not cause vmexit */ +static int nested_svm_intercept_db(struct vcpu_svm *svm) +{ + unsigned long dr6; + + /* if we're not singlestepping, it's not ours */ + if (!svm->nmi_singlestep) + return NESTED_EXIT_DONE; + + /* if it's not a singlestep exception, it's not ours */ + if (kvm_get_dr(&svm->vcpu, 6, &dr6)) + return NESTED_EXIT_DONE; + if (!(dr6 & DR6_BS)) + return NESTED_EXIT_DONE; + + /* if the guest is singlestepping, it should get the vmexit */ + if (svm->nmi_singlestep_guest_rflags & X86_EFLAGS_TF) { + disable_nmi_singlestep(svm); + return NESTED_EXIT_DONE; + } + + /* it's ours, the nested hypervisor must not see this one */ + return NESTED_EXIT_HOST; +} + +static int nested_svm_intercept_ioio(struct vcpu_svm *svm) +{ + unsigned port, size, iopm_len; + u16 val, mask; + u8 start_bit; + u64 gpa; + + if (!(svm->nested.intercept & (1ULL << INTERCEPT_IOIO_PROT))) + return NESTED_EXIT_HOST; + + port = svm->vmcb->control.exit_info_1 >> 16; + size = (svm->vmcb->control.exit_info_1 & SVM_IOIO_SIZE_MASK) >> + SVM_IOIO_SIZE_SHIFT; + gpa = svm->nested.vmcb_iopm + (port / 8); + start_bit = port % 8; + iopm_len = (start_bit + size > 8) ? 2 : 1; + mask = (0xf >> (4 - size)) << start_bit; + val = 0; + + if (kvm_vcpu_read_guest(&svm->vcpu, gpa, &val, iopm_len)) + return NESTED_EXIT_DONE; + + return (val & mask) ? NESTED_EXIT_DONE : NESTED_EXIT_HOST; +} + +static int nested_svm_intercept(struct vcpu_svm *svm) +{ + u32 exit_code = svm->vmcb->control.exit_code; + int vmexit = NESTED_EXIT_HOST; + + switch (exit_code) { + case SVM_EXIT_MSR: + vmexit = nested_svm_exit_handled_msr(svm); + break; + case SVM_EXIT_IOIO: + vmexit = nested_svm_intercept_ioio(svm); + break; + case SVM_EXIT_READ_CR0 ... SVM_EXIT_WRITE_CR8: { + u32 bit = 1U << (exit_code - SVM_EXIT_READ_CR0); + if (svm->nested.intercept_cr & bit) + vmexit = NESTED_EXIT_DONE; + break; + } + case SVM_EXIT_READ_DR0 ... SVM_EXIT_WRITE_DR7: { + u32 bit = 1U << (exit_code - SVM_EXIT_READ_DR0); + if (svm->nested.intercept_dr & bit) + vmexit = NESTED_EXIT_DONE; + break; + } + case SVM_EXIT_EXCP_BASE ... SVM_EXIT_EXCP_BASE + 0x1f: { + u32 excp_bits = 1 << (exit_code - SVM_EXIT_EXCP_BASE); + if (svm->nested.intercept_exceptions & excp_bits) { + if (exit_code == SVM_EXIT_EXCP_BASE + DB_VECTOR) + vmexit = nested_svm_intercept_db(svm); + else + vmexit = NESTED_EXIT_DONE; + } + /* async page fault always cause vmexit */ + else if ((exit_code == SVM_EXIT_EXCP_BASE + PF_VECTOR) && + svm->vcpu.arch.exception.nested_apf != 0) + vmexit = NESTED_EXIT_DONE; + break; + } + case SVM_EXIT_ERR: { + vmexit = NESTED_EXIT_DONE; + break; + } + default: { + u64 exit_bits = 1ULL << (exit_code - SVM_EXIT_INTR); + if (svm->nested.intercept & exit_bits) + vmexit = NESTED_EXIT_DONE; + } + } + + return vmexit; +} + +int nested_svm_exit_handled(struct vcpu_svm *svm) +{ + int vmexit; + + vmexit = nested_svm_intercept(svm); + + if (vmexit == NESTED_EXIT_DONE) + nested_svm_vmexit(svm); + + return vmexit; +} + +int nested_svm_check_permissions(struct vcpu_svm *svm) +{ + if (!(svm->vcpu.arch.efer & EFER_SVME) || + !is_paging(&svm->vcpu)) { + kvm_queue_exception(&svm->vcpu, UD_VECTOR); + return 1; + } + + if (svm->vmcb->save.cpl) { + kvm_inject_gp(&svm->vcpu, 0); + return 1; + } + + return 0; +} + +int nested_svm_check_exception(struct vcpu_svm *svm, unsigned nr, + bool has_error_code, u32 error_code) +{ + int vmexit; + + if (!is_guest_mode(&svm->vcpu)) + return 0; + + vmexit = nested_svm_intercept(svm); + if (vmexit != NESTED_EXIT_DONE) + return 0; + + svm->vmcb->control.exit_code = SVM_EXIT_EXCP_BASE + nr; + svm->vmcb->control.exit_code_hi = 0; + svm->vmcb->control.exit_info_1 = error_code; + + /* + * EXITINFO2 is undefined for all exception intercepts other + * than #PF. + */ + if (svm->vcpu.arch.exception.nested_apf) + svm->vmcb->control.exit_info_2 = svm->vcpu.arch.apf.nested_apf_token; + else if (svm->vcpu.arch.exception.has_payload) + svm->vmcb->control.exit_info_2 = svm->vcpu.arch.exception.payload; + else + svm->vmcb->control.exit_info_2 = svm->vcpu.arch.cr2; + + svm->nested.exit_required = true; + return vmexit; +} + +static void nested_svm_intr(struct vcpu_svm *svm) +{ + svm->vmcb->control.exit_code = SVM_EXIT_INTR; + svm->vmcb->control.exit_info_1 = 0; + svm->vmcb->control.exit_info_2 = 0; + + /* nested_svm_vmexit this gets called afterwards from handle_exit */ + svm->nested.exit_required = true; + trace_kvm_nested_intr_vmexit(svm->vmcb->save.rip); +} + +static bool nested_exit_on_intr(struct vcpu_svm *svm) +{ + return (svm->nested.intercept & 1ULL); +} + +int svm_check_nested_events(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + bool block_nested_events = + kvm_event_needs_reinjection(vcpu) || svm->nested.exit_required; + + if (kvm_cpu_has_interrupt(vcpu) && nested_exit_on_intr(svm)) { + if (block_nested_events) + return -EBUSY; + nested_svm_intr(svm); + return 0; + } + + return 0; +} + +int nested_svm_exit_special(struct vcpu_svm *svm) +{ + u32 exit_code = svm->vmcb->control.exit_code; + + switch (exit_code) { + case SVM_EXIT_INTR: + case SVM_EXIT_NMI: + case SVM_EXIT_EXCP_BASE + MC_VECTOR: + return NESTED_EXIT_HOST; + case SVM_EXIT_NPF: + /* For now we are always handling NPFs when using them */ + if (npt_enabled) + return NESTED_EXIT_HOST; + break; + case SVM_EXIT_EXCP_BASE + PF_VECTOR: + /* When we're shadowing, trap PFs, but not async PF */ + if (!npt_enabled && svm->vcpu.arch.apf.host_apf_reason == 0) + return NESTED_EXIT_HOST; + break; + default: + break; + } + + return NESTED_EXIT_CONTINUE; +} diff --git a/arch/x86/kvm/pmu_amd.c b/arch/x86/kvm/svm/pmu.c index ce0b10fe5e2b..ce0b10fe5e2b 100644 --- a/arch/x86/kvm/pmu_amd.c +++ b/arch/x86/kvm/svm/pmu.c diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c new file mode 100644 index 000000000000..0e3fc311d7da --- /dev/null +++ b/arch/x86/kvm/svm/sev.c @@ -0,0 +1,1187 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Kernel-based Virtual Machine driver for Linux + * + * AMD SVM-SEV support + * + * Copyright 2010 Red Hat, Inc. and/or its affiliates. + */ + +#include <linux/kvm_types.h> +#include <linux/kvm_host.h> +#include <linux/kernel.h> +#include <linux/highmem.h> +#include <linux/psp-sev.h> +#include <linux/swap.h> + +#include "x86.h" +#include "svm.h" + +static int sev_flush_asids(void); +static DECLARE_RWSEM(sev_deactivate_lock); +static DEFINE_MUTEX(sev_bitmap_lock); +unsigned int max_sev_asid; +static unsigned int min_sev_asid; +static unsigned long *sev_asid_bitmap; +static unsigned long *sev_reclaim_asid_bitmap; +#define __sme_page_pa(x) __sme_set(page_to_pfn(x) << PAGE_SHIFT) + +struct enc_region { + struct list_head list; + unsigned long npages; + struct page **pages; + unsigned long uaddr; + unsigned long size; +}; + +static int sev_flush_asids(void) +{ + int ret, error = 0; + + /* + * DEACTIVATE will clear the WBINVD indicator causing DF_FLUSH to fail, + * so it must be guarded. + */ + down_write(&sev_deactivate_lock); + + wbinvd_on_all_cpus(); + ret = sev_guest_df_flush(&error); + + up_write(&sev_deactivate_lock); + + if (ret) + pr_err("SEV: DF_FLUSH failed, ret=%d, error=%#x\n", ret, error); + + return ret; +} + +/* Must be called with the sev_bitmap_lock held */ +static bool __sev_recycle_asids(void) +{ + int pos; + + /* Check if there are any ASIDs to reclaim before performing a flush */ + pos = find_next_bit(sev_reclaim_asid_bitmap, + max_sev_asid, min_sev_asid - 1); + if (pos >= max_sev_asid) + return false; + + if (sev_flush_asids()) + return false; + + bitmap_xor(sev_asid_bitmap, sev_asid_bitmap, sev_reclaim_asid_bitmap, + max_sev_asid); + bitmap_zero(sev_reclaim_asid_bitmap, max_sev_asid); + + return true; +} + +static int sev_asid_new(void) +{ + bool retry = true; + int pos; + + mutex_lock(&sev_bitmap_lock); + + /* + * SEV-enabled guest must use asid from min_sev_asid to max_sev_asid. + */ +again: + pos = find_next_zero_bit(sev_asid_bitmap, max_sev_asid, min_sev_asid - 1); + if (pos >= max_sev_asid) { + if (retry && __sev_recycle_asids()) { + retry = false; + goto again; + } + mutex_unlock(&sev_bitmap_lock); + return -EBUSY; + } + + __set_bit(pos, sev_asid_bitmap); + + mutex_unlock(&sev_bitmap_lock); + + return pos + 1; +} + +static int sev_get_asid(struct kvm *kvm) +{ + struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; + + return sev->asid; +} + +static void sev_asid_free(int asid) +{ + struct svm_cpu_data *sd; + int cpu, pos; + + mutex_lock(&sev_bitmap_lock); + + pos = asid - 1; + __set_bit(pos, sev_reclaim_asid_bitmap); + + for_each_possible_cpu(cpu) { + sd = per_cpu(svm_data, cpu); + sd->sev_vmcbs[pos] = NULL; + } + + mutex_unlock(&sev_bitmap_lock); +} + +static void sev_unbind_asid(struct kvm *kvm, unsigned int handle) +{ + struct sev_data_decommission *decommission; + struct sev_data_deactivate *data; + + if (!handle) + return; + + data = kzalloc(sizeof(*data), GFP_KERNEL); + if (!data) + return; + + /* deactivate handle */ + data->handle = handle; + + /* Guard DEACTIVATE against WBINVD/DF_FLUSH used in ASID recycling */ + down_read(&sev_deactivate_lock); + sev_guest_deactivate(data, NULL); + up_read(&sev_deactivate_lock); + + kfree(data); + + decommission = kzalloc(sizeof(*decommission), GFP_KERNEL); + if (!decommission) + return; + + /* decommission handle */ + decommission->handle = handle; + sev_guest_decommission(decommission, NULL); + + kfree(decommission); +} + +static int sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp) +{ + struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; + int asid, ret; + + ret = -EBUSY; + if (unlikely(sev->active)) + return ret; + + asid = sev_asid_new(); + if (asid < 0) + return ret; + + ret = sev_platform_init(&argp->error); + if (ret) + goto e_free; + + sev->active = true; + sev->asid = asid; + INIT_LIST_HEAD(&sev->regions_list); + + return 0; + +e_free: + sev_asid_free(asid); + return ret; +} + +static int sev_bind_asid(struct kvm *kvm, unsigned int handle, int *error) +{ + struct sev_data_activate *data; + int asid = sev_get_asid(kvm); + int ret; + + data = kzalloc(sizeof(*data), GFP_KERNEL_ACCOUNT); + if (!data) + return -ENOMEM; + + /* activate ASID on the given handle */ + data->handle = handle; + data->asid = asid; + ret = sev_guest_activate(data, error); + kfree(data); + + return ret; +} + +static int __sev_issue_cmd(int fd, int id, void *data, int *error) +{ + struct fd f; + int ret; + + f = fdget(fd); + if (!f.file) + return -EBADF; + + ret = sev_issue_cmd_external_user(f.file, id, data, error); + + fdput(f); + return ret; +} + +static int sev_issue_cmd(struct kvm *kvm, int id, void *data, int *error) +{ + struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; + + return __sev_issue_cmd(sev->fd, id, data, error); +} + +static int sev_launch_start(struct kvm *kvm, struct kvm_sev_cmd *argp) +{ + struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; + struct sev_data_launch_start *start; + struct kvm_sev_launch_start params; + void *dh_blob, *session_blob; + int *error = &argp->error; + int ret; + + if (!sev_guest(kvm)) + return -ENOTTY; + + if (copy_from_user(¶ms, (void __user *)(uintptr_t)argp->data, sizeof(params))) + return -EFAULT; + + start = kzalloc(sizeof(*start), GFP_KERNEL_ACCOUNT); + if (!start) + return -ENOMEM; + + dh_blob = NULL; + if (params.dh_uaddr) { + dh_blob = psp_copy_user_blob(params.dh_uaddr, params.dh_len); + if (IS_ERR(dh_blob)) { + ret = PTR_ERR(dh_blob); + goto e_free; + } + + start->dh_cert_address = __sme_set(__pa(dh_blob)); + start->dh_cert_len = params.dh_len; + } + + session_blob = NULL; + if (params.session_uaddr) { + session_blob = psp_copy_user_blob(params.session_uaddr, params.session_len); + if (IS_ERR(session_blob)) { + ret = PTR_ERR(session_blob); + goto e_free_dh; + } + + start->session_address = __sme_set(__pa(session_blob)); + start->session_len = params.session_len; + } + + start->handle = params.handle; + start->policy = params.policy; + + /* create memory encryption context */ + ret = __sev_issue_cmd(argp->sev_fd, SEV_CMD_LAUNCH_START, start, error); + if (ret) + goto e_free_session; + + /* Bind ASID to this guest */ + ret = sev_bind_asid(kvm, start->handle, error); + if (ret) + goto e_free_session; + + /* return handle to userspace */ + params.handle = start->handle; + if (copy_to_user((void __user *)(uintptr_t)argp->data, ¶ms, sizeof(params))) { + sev_unbind_asid(kvm, start->handle); + ret = -EFAULT; + goto e_free_session; + } + + sev->handle = start->handle; + sev->fd = argp->sev_fd; + +e_free_session: + kfree(session_blob); +e_free_dh: + kfree(dh_blob); +e_free: + kfree(start); + return ret; +} + +static struct page **sev_pin_memory(struct kvm *kvm, unsigned long uaddr, + unsigned long ulen, unsigned long *n, + int write) +{ + struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; + unsigned long npages, npinned, size; + unsigned long locked, lock_limit; + struct page **pages; + unsigned long first, last; + + if (ulen == 0 || uaddr + ulen < uaddr) + return NULL; + + /* Calculate number of pages. */ + first = (uaddr & PAGE_MASK) >> PAGE_SHIFT; + last = ((uaddr + ulen - 1) & PAGE_MASK) >> PAGE_SHIFT; + npages = (last - first + 1); + + locked = sev->pages_locked + npages; + lock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT; + if (locked > lock_limit && !capable(CAP_IPC_LOCK)) { + pr_err("SEV: %lu locked pages exceed the lock limit of %lu.\n", locked, lock_limit); + return NULL; + } + + /* Avoid using vmalloc for smaller buffers. */ + size = npages * sizeof(struct page *); + if (size > PAGE_SIZE) + pages = __vmalloc(size, GFP_KERNEL_ACCOUNT | __GFP_ZERO, + PAGE_KERNEL); + else + pages = kmalloc(size, GFP_KERNEL_ACCOUNT); + + if (!pages) + return NULL; + + /* Pin the user virtual address. */ + npinned = get_user_pages_fast(uaddr, npages, FOLL_WRITE, pages); + if (npinned != npages) { + pr_err("SEV: Failure locking %lu pages.\n", npages); + goto err; + } + + *n = npages; + sev->pages_locked = locked; + + return pages; + +err: + if (npinned > 0) + release_pages(pages, npinned); + + kvfree(pages); + return NULL; +} + +static void sev_unpin_memory(struct kvm *kvm, struct page **pages, + unsigned long npages) +{ + struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; + + release_pages(pages, npages); + kvfree(pages); + sev->pages_locked -= npages; +} + +static void sev_clflush_pages(struct page *pages[], unsigned long npages) +{ + uint8_t *page_virtual; + unsigned long i; + + if (npages == 0 || pages == NULL) + return; + + for (i = 0; i < npages; i++) { + page_virtual = kmap_atomic(pages[i]); + clflush_cache_range(page_virtual, PAGE_SIZE); + kunmap_atomic(page_virtual); + } +} + +static unsigned long get_num_contig_pages(unsigned long idx, + struct page **inpages, unsigned long npages) +{ + unsigned long paddr, next_paddr; + unsigned long i = idx + 1, pages = 1; + + /* find the number of contiguous pages starting from idx */ + paddr = __sme_page_pa(inpages[idx]); + while (i < npages) { + next_paddr = __sme_page_pa(inpages[i++]); + if ((paddr + PAGE_SIZE) == next_paddr) { + pages++; + paddr = next_paddr; + continue; + } + break; + } + + return pages; +} + +static int sev_launch_update_data(struct kvm *kvm, struct kvm_sev_cmd *argp) +{ + unsigned long vaddr, vaddr_end, next_vaddr, npages, pages, size, i; + struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; + struct kvm_sev_launch_update_data params; + struct sev_data_launch_update_data *data; + struct page **inpages; + int ret; + + if (!sev_guest(kvm)) + return -ENOTTY; + + if (copy_from_user(¶ms, (void __user *)(uintptr_t)argp->data, sizeof(params))) + return -EFAULT; + + data = kzalloc(sizeof(*data), GFP_KERNEL_ACCOUNT); + if (!data) + return -ENOMEM; + + vaddr = params.uaddr; + size = params.len; + vaddr_end = vaddr + size; + + /* Lock the user memory. */ + inpages = sev_pin_memory(kvm, vaddr, size, &npages, 1); + if (!inpages) { + ret = -ENOMEM; + goto e_free; + } + + /* + * The LAUNCH_UPDATE command will perform in-place encryption of the + * memory content (i.e it will write the same memory region with C=1). + * It's possible that the cache may contain the data with C=0, i.e., + * unencrypted so invalidate it first. + */ + sev_clflush_pages(inpages, npages); + + for (i = 0; vaddr < vaddr_end; vaddr = next_vaddr, i += pages) { + int offset, len; + + /* + * If the user buffer is not page-aligned, calculate the offset + * within the page. + */ + offset = vaddr & (PAGE_SIZE - 1); + + /* Calculate the number of pages that can be encrypted in one go. */ + pages = get_num_contig_pages(i, inpages, npages); + + len = min_t(size_t, ((pages * PAGE_SIZE) - offset), size); + + data->handle = sev->handle; + data->len = len; + data->address = __sme_page_pa(inpages[i]) + offset; + ret = sev_issue_cmd(kvm, SEV_CMD_LAUNCH_UPDATE_DATA, data, &argp->error); + if (ret) + goto e_unpin; + + size -= len; + next_vaddr = vaddr + len; + } + +e_unpin: + /* content of memory is updated, mark pages dirty */ + for (i = 0; i < npages; i++) { + set_page_dirty_lock(inpages[i]); + mark_page_accessed(inpages[i]); + } + /* unlock the user pages */ + sev_unpin_memory(kvm, inpages, npages); +e_free: + kfree(data); + return ret; +} + +static int sev_launch_measure(struct kvm *kvm, struct kvm_sev_cmd *argp) +{ + void __user *measure = (void __user *)(uintptr_t)argp->data; + struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; + struct sev_data_launch_measure *data; + struct kvm_sev_launch_measure params; + void __user *p = NULL; + void *blob = NULL; + int ret; + + if (!sev_guest(kvm)) + return -ENOTTY; + + if (copy_from_user(¶ms, measure, sizeof(params))) + return -EFAULT; + + data = kzalloc(sizeof(*data), GFP_KERNEL_ACCOUNT); + if (!data) + return -ENOMEM; + + /* User wants to query the blob length */ + if (!params.len) + goto cmd; + + p = (void __user *)(uintptr_t)params.uaddr; + if (p) { + if (params.len > SEV_FW_BLOB_MAX_SIZE) { + ret = -EINVAL; + goto e_free; + } + + ret = -ENOMEM; + blob = kmalloc(params.len, GFP_KERNEL); + if (!blob) + goto e_free; + + data->address = __psp_pa(blob); + data->len = params.len; + } + +cmd: + data->handle = sev->handle; + ret = sev_issue_cmd(kvm, SEV_CMD_LAUNCH_MEASURE, data, &argp->error); + + /* + * If we query the session length, FW responded with expected data. + */ + if (!params.len) + goto done; + + if (ret) + goto e_free_blob; + + if (blob) { + if (copy_to_user(p, blob, params.len)) + ret = -EFAULT; + } + +done: + params.len = data->len; + if (copy_to_user(measure, ¶ms, sizeof(params))) + ret = -EFAULT; +e_free_blob: + kfree(blob); +e_free: + kfree(data); + return ret; +} + +static int sev_launch_finish(struct kvm *kvm, struct kvm_sev_cmd *argp) +{ + struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; + struct sev_data_launch_finish *data; + int ret; + + if (!sev_guest(kvm)) + return -ENOTTY; + + data = kzalloc(sizeof(*data), GFP_KERNEL_ACCOUNT); + if (!data) + return -ENOMEM; + + data->handle = sev->handle; + ret = sev_issue_cmd(kvm, SEV_CMD_LAUNCH_FINISH, data, &argp->error); + + kfree(data); + return ret; +} + +static int sev_guest_status(struct kvm *kvm, struct kvm_sev_cmd *argp) +{ + struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; + struct kvm_sev_guest_status params; + struct sev_data_guest_status *data; + int ret; + + if (!sev_guest(kvm)) + return -ENOTTY; + + data = kzalloc(sizeof(*data), GFP_KERNEL_ACCOUNT); + if (!data) + return -ENOMEM; + + data->handle = sev->handle; + ret = sev_issue_cmd(kvm, SEV_CMD_GUEST_STATUS, data, &argp->error); + if (ret) + goto e_free; + + params.policy = data->policy; + params.state = data->state; + params.handle = data->handle; + + if (copy_to_user((void __user *)(uintptr_t)argp->data, ¶ms, sizeof(params))) + ret = -EFAULT; +e_free: + kfree(data); + return ret; +} + +static int __sev_issue_dbg_cmd(struct kvm *kvm, unsigned long src, + unsigned long dst, int size, + int *error, bool enc) +{ + struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; + struct sev_data_dbg *data; + int ret; + + data = kzalloc(sizeof(*data), GFP_KERNEL_ACCOUNT); + if (!data) + return -ENOMEM; + + data->handle = sev->handle; + data->dst_addr = dst; + data->src_addr = src; + data->len = size; + + ret = sev_issue_cmd(kvm, + enc ? SEV_CMD_DBG_ENCRYPT : SEV_CMD_DBG_DECRYPT, + data, error); + kfree(data); + return ret; +} + +static int __sev_dbg_decrypt(struct kvm *kvm, unsigned long src_paddr, + unsigned long dst_paddr, int sz, int *err) +{ + int offset; + + /* + * Its safe to read more than we are asked, caller should ensure that + * destination has enough space. + */ + src_paddr = round_down(src_paddr, 16); + offset = src_paddr & 15; + sz = round_up(sz + offset, 16); + + return __sev_issue_dbg_cmd(kvm, src_paddr, dst_paddr, sz, err, false); +} + +static int __sev_dbg_decrypt_user(struct kvm *kvm, unsigned long paddr, + unsigned long __user dst_uaddr, + unsigned long dst_paddr, + int size, int *err) +{ + struct page *tpage = NULL; + int ret, offset; + + /* if inputs are not 16-byte then use intermediate buffer */ + if (!IS_ALIGNED(dst_paddr, 16) || + !IS_ALIGNED(paddr, 16) || + !IS_ALIGNED(size, 16)) { + tpage = (void *)alloc_page(GFP_KERNEL); + if (!tpage) + return -ENOMEM; + + dst_paddr = __sme_page_pa(tpage); + } + + ret = __sev_dbg_decrypt(kvm, paddr, dst_paddr, size, err); + if (ret) + goto e_free; + + if (tpage) { + offset = paddr & 15; + if (copy_to_user((void __user *)(uintptr_t)dst_uaddr, + page_address(tpage) + offset, size)) + ret = -EFAULT; + } + +e_free: + if (tpage) + __free_page(tpage); + + return ret; +} + +static int __sev_dbg_encrypt_user(struct kvm *kvm, unsigned long paddr, + unsigned long __user vaddr, + unsigned long dst_paddr, + unsigned long __user dst_vaddr, + int size, int *error) +{ + struct page *src_tpage = NULL; + struct page *dst_tpage = NULL; + int ret, len = size; + + /* If source buffer is not aligned then use an intermediate buffer */ + if (!IS_ALIGNED(vaddr, 16)) { + src_tpage = alloc_page(GFP_KERNEL); + if (!src_tpage) + return -ENOMEM; + + if (copy_from_user(page_address(src_tpage), + (void __user *)(uintptr_t)vaddr, size)) { + __free_page(src_tpage); + return -EFAULT; + } + + paddr = __sme_page_pa(src_tpage); + } + + /* + * If destination buffer or length is not aligned then do read-modify-write: + * - decrypt destination in an intermediate buffer + * - copy the source buffer in an intermediate buffer + * - use the intermediate buffer as source buffer + */ + if (!IS_ALIGNED(dst_vaddr, 16) || !IS_ALIGNED(size, 16)) { + int dst_offset; + + dst_tpage = alloc_page(GFP_KERNEL); + if (!dst_tpage) { + ret = -ENOMEM; + goto e_free; + } + + ret = __sev_dbg_decrypt(kvm, dst_paddr, + __sme_page_pa(dst_tpage), size, error); + if (ret) + goto e_free; + + /* + * If source is kernel buffer then use memcpy() otherwise + * copy_from_user(). + */ + dst_offset = dst_paddr & 15; + + if (src_tpage) + memcpy(page_address(dst_tpage) + dst_offset, + page_address(src_tpage), size); + else { + if (copy_from_user(page_address(dst_tpage) + dst_offset, + (void __user *)(uintptr_t)vaddr, size)) { + ret = -EFAULT; + goto e_free; + } + } + + paddr = __sme_page_pa(dst_tpage); + dst_paddr = round_down(dst_paddr, 16); + len = round_up(size, 16); + } + + ret = __sev_issue_dbg_cmd(kvm, paddr, dst_paddr, len, error, true); + +e_free: + if (src_tpage) + __free_page(src_tpage); + if (dst_tpage) + __free_page(dst_tpage); + return ret; +} + +static int sev_dbg_crypt(struct kvm *kvm, struct kvm_sev_cmd *argp, bool dec) +{ + unsigned long vaddr, vaddr_end, next_vaddr; + unsigned long dst_vaddr; + struct page **src_p, **dst_p; + struct kvm_sev_dbg debug; + unsigned long n; + unsigned int size; + int ret; + + if (!sev_guest(kvm)) + return -ENOTTY; + + if (copy_from_user(&debug, (void __user *)(uintptr_t)argp->data, sizeof(debug))) + return -EFAULT; + + if (!debug.len || debug.src_uaddr + debug.len < debug.src_uaddr) + return -EINVAL; + if (!debug.dst_uaddr) + return -EINVAL; + + vaddr = debug.src_uaddr; + size = debug.len; + vaddr_end = vaddr + size; + dst_vaddr = debug.dst_uaddr; + + for (; vaddr < vaddr_end; vaddr = next_vaddr) { + int len, s_off, d_off; + + /* lock userspace source and destination page */ + src_p = sev_pin_memory(kvm, vaddr & PAGE_MASK, PAGE_SIZE, &n, 0); + if (!src_p) + return -EFAULT; + + dst_p = sev_pin_memory(kvm, dst_vaddr & PAGE_MASK, PAGE_SIZE, &n, 1); + if (!dst_p) { + sev_unpin_memory(kvm, src_p, n); + return -EFAULT; + } + + /* + * The DBG_{DE,EN}CRYPT commands will perform {dec,en}cryption of the + * memory content (i.e it will write the same memory region with C=1). + * It's possible that the cache may contain the data with C=0, i.e., + * unencrypted so invalidate it first. + */ + sev_clflush_pages(src_p, 1); + sev_clflush_pages(dst_p, 1); + + /* + * Since user buffer may not be page aligned, calculate the + * offset within the page. + */ + s_off = vaddr & ~PAGE_MASK; + d_off = dst_vaddr & ~PAGE_MASK; + len = min_t(size_t, (PAGE_SIZE - s_off), size); + + if (dec) + ret = __sev_dbg_decrypt_user(kvm, + __sme_page_pa(src_p[0]) + s_off, + dst_vaddr, + __sme_page_pa(dst_p[0]) + d_off, + len, &argp->error); + else + ret = __sev_dbg_encrypt_user(kvm, + __sme_page_pa(src_p[0]) + s_off, + vaddr, + __sme_page_pa(dst_p[0]) + d_off, + dst_vaddr, + len, &argp->error); + + sev_unpin_memory(kvm, src_p, n); + sev_unpin_memory(kvm, dst_p, n); + + if (ret) + goto err; + + next_vaddr = vaddr + len; + dst_vaddr = dst_vaddr + len; + size -= len; + } +err: + return ret; +} + +static int sev_launch_secret(struct kvm *kvm, struct kvm_sev_cmd *argp) +{ + struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; + struct sev_data_launch_secret *data; + struct kvm_sev_launch_secret params; + struct page **pages; + void *blob, *hdr; + unsigned long n; + int ret, offset; + + if (!sev_guest(kvm)) + return -ENOTTY; + + if (copy_from_user(¶ms, (void __user *)(uintptr_t)argp->data, sizeof(params))) + return -EFAULT; + + pages = sev_pin_memory(kvm, params.guest_uaddr, params.guest_len, &n, 1); + if (!pages) + return -ENOMEM; + + /* + * The secret must be copied into contiguous memory region, lets verify + * that userspace memory pages are contiguous before we issue command. + */ + if (get_num_contig_pages(0, pages, n) != n) { + ret = -EINVAL; + goto e_unpin_memory; + } + + ret = -ENOMEM; + data = kzalloc(sizeof(*data), GFP_KERNEL_ACCOUNT); + if (!data) + goto e_unpin_memory; + + offset = params.guest_uaddr & (PAGE_SIZE - 1); + data->guest_address = __sme_page_pa(pages[0]) + offset; + data->guest_len = params.guest_len; + + blob = psp_copy_user_blob(params.trans_uaddr, params.trans_len); + if (IS_ERR(blob)) { + ret = PTR_ERR(blob); + goto e_free; + } + + data->trans_address = __psp_pa(blob); + data->trans_len = params.trans_len; + + hdr = psp_copy_user_blob(params.hdr_uaddr, params.hdr_len); + if (IS_ERR(hdr)) { + ret = PTR_ERR(hdr); + goto e_free_blob; + } + data->hdr_address = __psp_pa(hdr); + data->hdr_len = params.hdr_len; + + data->handle = sev->handle; + ret = sev_issue_cmd(kvm, SEV_CMD_LAUNCH_UPDATE_SECRET, data, &argp->error); + + kfree(hdr); + +e_free_blob: + kfree(blob); +e_free: + kfree(data); +e_unpin_memory: + sev_unpin_memory(kvm, pages, n); + return ret; +} + +int svm_mem_enc_op(struct kvm *kvm, void __user *argp) +{ + struct kvm_sev_cmd sev_cmd; + int r; + + if (!svm_sev_enabled()) + return -ENOTTY; + + if (!argp) + return 0; + + if (copy_from_user(&sev_cmd, argp, sizeof(struct kvm_sev_cmd))) + return -EFAULT; + + mutex_lock(&kvm->lock); + + switch (sev_cmd.id) { + case KVM_SEV_INIT: + r = sev_guest_init(kvm, &sev_cmd); + break; + case KVM_SEV_LAUNCH_START: + r = sev_launch_start(kvm, &sev_cmd); + break; + case KVM_SEV_LAUNCH_UPDATE_DATA: + r = sev_launch_update_data(kvm, &sev_cmd); + break; + case KVM_SEV_LAUNCH_MEASURE: + r = sev_launch_measure(kvm, &sev_cmd); + break; + case KVM_SEV_LAUNCH_FINISH: + r = sev_launch_finish(kvm, &sev_cmd); + break; + case KVM_SEV_GUEST_STATUS: + r = sev_guest_status(kvm, &sev_cmd); + break; + case KVM_SEV_DBG_DECRYPT: + r = sev_dbg_crypt(kvm, &sev_cmd, true); + break; + case KVM_SEV_DBG_ENCRYPT: + r = sev_dbg_crypt(kvm, &sev_cmd, false); + break; + case KVM_SEV_LAUNCH_SECRET: + r = sev_launch_secret(kvm, &sev_cmd); + break; + default: + r = -EINVAL; + goto out; + } + + if (copy_to_user(argp, &sev_cmd, sizeof(struct kvm_sev_cmd))) + r = -EFAULT; + +out: + mutex_unlock(&kvm->lock); + return r; +} + +int svm_register_enc_region(struct kvm *kvm, + struct kvm_enc_region *range) +{ + struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; + struct enc_region *region; + int ret = 0; + + if (!sev_guest(kvm)) + return -ENOTTY; + + if (range->addr > ULONG_MAX || range->size > ULONG_MAX) + return -EINVAL; + + region = kzalloc(sizeof(*region), GFP_KERNEL_ACCOUNT); + if (!region) + return -ENOMEM; + + region->pages = sev_pin_memory(kvm, range->addr, range->size, ®ion->npages, 1); + if (!region->pages) { + ret = -ENOMEM; + goto e_free; + } + + /* + * The guest may change the memory encryption attribute from C=0 -> C=1 + * or vice versa for this memory range. Lets make sure caches are + * flushed to ensure that guest data gets written into memory with + * correct C-bit. + */ + sev_clflush_pages(region->pages, region->npages); + + region->uaddr = range->addr; + region->size = range->size; + + mutex_lock(&kvm->lock); + list_add_tail(®ion->list, &sev->regions_list); + mutex_unlock(&kvm->lock); + + return ret; + +e_free: + kfree(region); + return ret; +} + +static struct enc_region * +find_enc_region(struct kvm *kvm, struct kvm_enc_region *range) +{ + struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; + struct list_head *head = &sev->regions_list; + struct enc_region *i; + + list_for_each_entry(i, head, list) { + if (i->uaddr == range->addr && + i->size == range->size) + return i; + } + + return NULL; +} + +static void __unregister_enc_region_locked(struct kvm *kvm, + struct enc_region *region) +{ + sev_unpin_memory(kvm, region->pages, region->npages); + list_del(®ion->list); + kfree(region); +} + +int svm_unregister_enc_region(struct kvm *kvm, + struct kvm_enc_region *range) +{ + struct enc_region *region; + int ret; + + mutex_lock(&kvm->lock); + + if (!sev_guest(kvm)) { + ret = -ENOTTY; + goto failed; + } + + region = find_enc_region(kvm, range); + if (!region) { + ret = -EINVAL; + goto failed; + } + + /* + * Ensure that all guest tagged cache entries are flushed before + * releasing the pages back to the system for use. CLFLUSH will + * not do this, so issue a WBINVD. + */ + wbinvd_on_all_cpus(); + + __unregister_enc_region_locked(kvm, region); + + mutex_unlock(&kvm->lock); + return 0; + +failed: + mutex_unlock(&kvm->lock); + return ret; +} + +void sev_vm_destroy(struct kvm *kvm) +{ + struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; + struct list_head *head = &sev->regions_list; + struct list_head *pos, *q; + + if (!sev_guest(kvm)) + return; + + mutex_lock(&kvm->lock); + + /* + * Ensure that all guest tagged cache entries are flushed before + * releasing the pages back to the system for use. CLFLUSH will + * not do this, so issue a WBINVD. + */ + wbinvd_on_all_cpus(); + + /* + * if userspace was terminated before unregistering the memory regions + * then lets unpin all the registered memory. + */ + if (!list_empty(head)) { + list_for_each_safe(pos, q, head) { + __unregister_enc_region_locked(kvm, + list_entry(pos, struct enc_region, list)); + } + } + + mutex_unlock(&kvm->lock); + + sev_unbind_asid(kvm, sev->handle); + sev_asid_free(sev->asid); +} + +int __init sev_hardware_setup(void) +{ + struct sev_user_data_status *status; + int rc; + + /* Maximum number of encrypted guests supported simultaneously */ + max_sev_asid = cpuid_ecx(0x8000001F); + + if (!max_sev_asid) + return 1; + + /* Minimum ASID value that should be used for SEV guest */ + min_sev_asid = cpuid_edx(0x8000001F); + + /* Initialize SEV ASID bitmaps */ + sev_asid_bitmap = bitmap_zalloc(max_sev_asid, GFP_KERNEL); + if (!sev_asid_bitmap) + return 1; + + sev_reclaim_asid_bitmap = bitmap_zalloc(max_sev_asid, GFP_KERNEL); + if (!sev_reclaim_asid_bitmap) + return 1; + + status = kmalloc(sizeof(*status), GFP_KERNEL); + if (!status) + return 1; + + /* + * Check SEV platform status. + * + * PLATFORM_STATUS can be called in any state, if we failed to query + * the PLATFORM status then either PSP firmware does not support SEV + * feature or SEV firmware is dead. + */ + rc = sev_platform_status(status, NULL); + if (rc) + goto err; + + pr_info("SEV supported\n"); + +err: + kfree(status); + return rc; +} + +void sev_hardware_teardown(void) +{ + bitmap_free(sev_asid_bitmap); + bitmap_free(sev_reclaim_asid_bitmap); + + sev_flush_asids(); +} + +void pre_sev_run(struct vcpu_svm *svm, int cpu) +{ + struct svm_cpu_data *sd = per_cpu(svm_data, cpu); + int asid = sev_get_asid(svm->vcpu.kvm); + + /* Assign the asid allocated with this SEV guest */ + svm->vmcb->control.asid = asid; + + /* + * Flush guest TLB: + * + * 1) when different VMCB for the same ASID is to be run on the same host CPU. + * 2) or this VMCB was executed on different host CPU in previous VMRUNs. + */ + if (sd->sev_vmcbs[asid] == svm->vmcb && + svm->last_cpu == cpu) + return; + + svm->last_cpu = cpu; + sd->sev_vmcbs[asid] = svm->vmcb; + svm->vmcb->control.tlb_ctl = TLB_CONTROL_FLUSH_ASID; + mark_dirty(svm->vmcb, VMCB_ASID); +} diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm/svm.c index 851e9cc79930..2be5bbae3a40 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -1,17 +1,3 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Kernel-based Virtual Machine driver for Linux - * - * AMD SVM support - * - * Copyright (C) 2006 Qumranet, Inc. - * Copyright 2010 Red Hat, Inc. and/or its affiliates. - * - * Authors: - * Yaniv Kamay <yaniv@qumranet.com> - * Avi Kivity <avi@qumranet.com> - */ - #define pr_fmt(fmt) "SVM: " fmt #include <linux/kvm_host.h> @@ -28,10 +14,10 @@ #include <linux/kernel.h> #include <linux/vmalloc.h> #include <linux/highmem.h> +#include <linux/amd-iommu.h> #include <linux/sched.h> #include <linux/trace_events.h> #include <linux/slab.h> -#include <linux/amd-iommu.h> #include <linux/hashtable.h> #include <linux/frame.h> #include <linux/psp-sev.h> @@ -53,6 +39,8 @@ #include <asm/virtext.h> #include "trace.h" +#include "svm.h" + #define __ex(x) __kvm_handle_fault_on_reboot(x) MODULE_AUTHOR("Qumranet"); @@ -80,107 +68,15 @@ MODULE_DEVICE_TABLE(x86cpu, svm_cpu_id); #define SVM_FEATURE_DECODE_ASSIST (1 << 7) #define SVM_FEATURE_PAUSE_FILTER (1 << 10) -#define SVM_AVIC_DOORBELL 0xc001011b - -#define NESTED_EXIT_HOST 0 /* Exit handled on host level */ -#define NESTED_EXIT_DONE 1 /* Exit caused nested vmexit */ -#define NESTED_EXIT_CONTINUE 2 /* Further checks needed */ - #define DEBUGCTL_RESERVED_BITS (~(0x3fULL)) #define TSC_RATIO_RSVD 0xffffff0000000000ULL #define TSC_RATIO_MIN 0x0000000000000001ULL #define TSC_RATIO_MAX 0x000000ffffffffffULL -#define AVIC_HPA_MASK ~((0xFFFULL << 52) | 0xFFF) - -/* - * 0xff is broadcast, so the max index allowed for physical APIC ID - * table is 0xfe. APIC IDs above 0xff are reserved. - */ -#define AVIC_MAX_PHYSICAL_ID_COUNT 255 - -#define AVIC_UNACCEL_ACCESS_WRITE_MASK 1 -#define AVIC_UNACCEL_ACCESS_OFFSET_MASK 0xFF0 -#define AVIC_UNACCEL_ACCESS_VECTOR_MASK 0xFFFFFFFF - -/* AVIC GATAG is encoded using VM and VCPU IDs */ -#define AVIC_VCPU_ID_BITS 8 -#define AVIC_VCPU_ID_MASK ((1 << AVIC_VCPU_ID_BITS) - 1) - -#define AVIC_VM_ID_BITS 24 -#define AVIC_VM_ID_NR (1 << AVIC_VM_ID_BITS) -#define AVIC_VM_ID_MASK ((1 << AVIC_VM_ID_BITS) - 1) - -#define AVIC_GATAG(x, y) (((x & AVIC_VM_ID_MASK) << AVIC_VCPU_ID_BITS) | \ - (y & AVIC_VCPU_ID_MASK)) -#define AVIC_GATAG_TO_VMID(x) ((x >> AVIC_VCPU_ID_BITS) & AVIC_VM_ID_MASK) -#define AVIC_GATAG_TO_VCPUID(x) (x & AVIC_VCPU_ID_MASK) - static bool erratum_383_found __read_mostly; -static const u32 host_save_user_msrs[] = { -#ifdef CONFIG_X86_64 - MSR_STAR, MSR_LSTAR, MSR_CSTAR, MSR_SYSCALL_MASK, MSR_KERNEL_GS_BASE, - MSR_FS_BASE, -#endif - MSR_IA32_SYSENTER_CS, MSR_IA32_SYSENTER_ESP, MSR_IA32_SYSENTER_EIP, - MSR_TSC_AUX, -}; - -#define NR_HOST_SAVE_USER_MSRS ARRAY_SIZE(host_save_user_msrs) - -struct kvm_sev_info { - bool active; /* SEV enabled guest */ - unsigned int asid; /* ASID used for this guest */ - unsigned int handle; /* SEV firmware handle */ - int fd; /* SEV device fd */ - unsigned long pages_locked; /* Number of pages locked */ - struct list_head regions_list; /* List of registered regions */ -}; - -struct kvm_svm { - struct kvm kvm; - - /* Struct members for AVIC */ - u32 avic_vm_id; - struct page *avic_logical_id_table_page; - struct page *avic_physical_id_table_page; - struct hlist_node hnode; - - struct kvm_sev_info sev_info; -}; - -struct kvm_vcpu; - -struct nested_state { - struct vmcb *hsave; - u64 hsave_msr; - u64 vm_cr_msr; - u64 vmcb; - - /* These are the merged vectors */ - u32 *msrpm; - - /* gpa pointers to the real vectors */ - u64 vmcb_msrpm; - u64 vmcb_iopm; - - /* A VMEXIT is required but not yet emulated */ - bool exit_required; - - /* cache for intercepts of the guest */ - u32 intercept_cr; - u32 intercept_dr; - u32 intercept_exceptions; - u64 intercept; - - /* Nested Paging related state */ - u64 nested_cr3; -}; - -#define MSRPM_OFFSETS 16 -static u32 msrpm_offsets[MSRPM_OFFSETS] __read_mostly; +u32 msrpm_offsets[MSRPM_OFFSETS] __read_mostly; /* * Set osvw_len to higher value when updated Revision Guides @@ -188,92 +84,9 @@ static u32 msrpm_offsets[MSRPM_OFFSETS] __read_mostly; */ static uint64_t osvw_len = 4, osvw_status; -struct vcpu_svm { - struct kvm_vcpu vcpu; - struct vmcb *vmcb; - unsigned long vmcb_pa; - struct svm_cpu_data *svm_data; - uint64_t asid_generation; - uint64_t sysenter_esp; - uint64_t sysenter_eip; - uint64_t tsc_aux; - - u64 msr_decfg; - - u64 next_rip; - - u64 host_user_msrs[NR_HOST_SAVE_USER_MSRS]; - struct { - u16 fs; - u16 gs; - u16 ldt; - u64 gs_base; - } host; - - u64 spec_ctrl; - /* - * Contains guest-controlled bits of VIRT_SPEC_CTRL, which will be - * translated into the appropriate L2_CFG bits on the host to - * perform speculative control. - */ - u64 virt_spec_ctrl; - - u32 *msrpm; - - ulong nmi_iret_rip; - - struct nested_state nested; - - bool nmi_singlestep; - u64 nmi_singlestep_guest_rflags; - - unsigned int3_injected; - unsigned long int3_rip; - - /* cached guest cpuid flags for faster access */ - bool nrips_enabled : 1; - - u32 ldr_reg; - u32 dfr_reg; - struct page *avic_backing_page; - u64 *avic_physical_id_cache; - bool avic_is_running; - - /* - * Per-vcpu list of struct amd_svm_iommu_ir: - * This is used mainly to store interrupt remapping information used - * when update the vcpu affinity. This avoids the need to scan for - * IRTE and try to match ga_tag in the IOMMU driver. - */ - struct list_head ir_list; - spinlock_t ir_list_lock; - - /* which host CPU was used for running this vcpu */ - unsigned int last_cpu; -}; - -/* - * This is a wrapper of struct amd_iommu_ir_data. - */ -struct amd_svm_iommu_ir { - struct list_head node; /* Used by SVM for per-vcpu ir_list */ - void *data; /* Storing pointer to struct amd_ir_data */ -}; - -#define AVIC_LOGICAL_ID_ENTRY_GUEST_PHYSICAL_ID_MASK (0xFF) -#define AVIC_LOGICAL_ID_ENTRY_VALID_BIT 31 -#define AVIC_LOGICAL_ID_ENTRY_VALID_MASK (1 << 31) - -#define AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK (0xFFULL) -#define AVIC_PHYSICAL_ID_ENTRY_BACKING_PAGE_MASK (0xFFFFFFFFFFULL << 12) -#define AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK (1ULL << 62) -#define AVIC_PHYSICAL_ID_ENTRY_VALID_MASK (1ULL << 63) - static DEFINE_PER_CPU(u64, current_tsc_ratio); #define TSC_RATIO_DEFAULT 0x0100000000ULL -#define MSR_INVALID 0xffffffffU - static const struct svm_direct_access_msrs { u32 index; /* Index of the MSR */ bool always; /* True if intercept is always on */ @@ -299,9 +112,9 @@ static const struct svm_direct_access_msrs { /* enable NPT for AMD64 and X86 with PAE */ #if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE) -static bool npt_enabled = true; +bool npt_enabled = true; #else -static bool npt_enabled; +bool npt_enabled; #endif /* @@ -360,12 +173,6 @@ module_param(npt, int, S_IRUGO); static int nested = true; module_param(nested, int, S_IRUGO); -/* enable / disable AVIC */ -static int avic; -#ifdef CONFIG_X86_LOCAL_APIC -module_param(avic, int, S_IRUGO); -#endif - /* enable/disable Next RIP Save */ static int nrips = true; module_param(nrips, int, 0444); @@ -387,303 +194,7 @@ module_param(dump_invalid_vmcb, bool, 0644); static u8 rsm_ins_bytes[] = "\x0f\xaa"; -static void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0); -static void svm_flush_tlb(struct kvm_vcpu *vcpu, bool invalidate_gpa); static void svm_complete_interrupts(struct vcpu_svm *svm); -static void svm_toggle_avic_for_irq_window(struct kvm_vcpu *vcpu, bool activate); -static inline void avic_post_state_restore(struct kvm_vcpu *vcpu); - -static int nested_svm_exit_handled(struct vcpu_svm *svm); -static int nested_svm_intercept(struct vcpu_svm *svm); -static int nested_svm_vmexit(struct vcpu_svm *svm); -static int nested_svm_check_exception(struct vcpu_svm *svm, unsigned nr, - bool has_error_code, u32 error_code); - -enum { - VMCB_INTERCEPTS, /* Intercept vectors, TSC offset, - pause filter count */ - VMCB_PERM_MAP, /* IOPM Base and MSRPM Base */ - VMCB_ASID, /* ASID */ - VMCB_INTR, /* int_ctl, int_vector */ - VMCB_NPT, /* npt_en, nCR3, gPAT */ - VMCB_CR, /* CR0, CR3, CR4, EFER */ - VMCB_DR, /* DR6, DR7 */ - VMCB_DT, /* GDT, IDT */ - VMCB_SEG, /* CS, DS, SS, ES, CPL */ - VMCB_CR2, /* CR2 only */ - VMCB_LBR, /* DBGCTL, BR_FROM, BR_TO, LAST_EX_FROM, LAST_EX_TO */ - VMCB_AVIC, /* AVIC APIC_BAR, AVIC APIC_BACKING_PAGE, - * AVIC PHYSICAL_TABLE pointer, - * AVIC LOGICAL_TABLE pointer - */ - VMCB_DIRTY_MAX, -}; - -/* TPR and CR2 are always written before VMRUN */ -#define VMCB_ALWAYS_DIRTY_MASK ((1U << VMCB_INTR) | (1U << VMCB_CR2)) - -#define VMCB_AVIC_APIC_BAR_MASK 0xFFFFFFFFFF000ULL - -static int sev_flush_asids(void); -static DECLARE_RWSEM(sev_deactivate_lock); -static DEFINE_MUTEX(sev_bitmap_lock); -static unsigned int max_sev_asid; -static unsigned int min_sev_asid; -static unsigned long *sev_asid_bitmap; -static unsigned long *sev_reclaim_asid_bitmap; -#define __sme_page_pa(x) __sme_set(page_to_pfn(x) << PAGE_SHIFT) - -struct enc_region { - struct list_head list; - unsigned long npages; - struct page **pages; - unsigned long uaddr; - unsigned long size; -}; - - -static inline struct kvm_svm *to_kvm_svm(struct kvm *kvm) -{ - return container_of(kvm, struct kvm_svm, kvm); -} - -static inline bool svm_sev_enabled(void) -{ - return IS_ENABLED(CONFIG_KVM_AMD_SEV) ? max_sev_asid : 0; -} - -static inline bool sev_guest(struct kvm *kvm) -{ -#ifdef CONFIG_KVM_AMD_SEV - struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; - - return sev->active; -#else - return false; -#endif -} - -static inline int sev_get_asid(struct kvm *kvm) -{ - struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; - - return sev->asid; -} - -static inline void mark_all_dirty(struct vmcb *vmcb) -{ - vmcb->control.clean = 0; -} - -static inline void mark_all_clean(struct vmcb *vmcb) -{ - vmcb->control.clean = ((1 << VMCB_DIRTY_MAX) - 1) - & ~VMCB_ALWAYS_DIRTY_MASK; -} - -static inline void mark_dirty(struct vmcb *vmcb, int bit) -{ - vmcb->control.clean &= ~(1 << bit); -} - -static inline struct vcpu_svm *to_svm(struct kvm_vcpu *vcpu) -{ - return container_of(vcpu, struct vcpu_svm, vcpu); -} - -static inline void avic_update_vapic_bar(struct vcpu_svm *svm, u64 data) -{ - svm->vmcb->control.avic_vapic_bar = data & VMCB_AVIC_APIC_BAR_MASK; - mark_dirty(svm->vmcb, VMCB_AVIC); -} - -static inline bool avic_vcpu_is_running(struct kvm_vcpu *vcpu) -{ - struct vcpu_svm *svm = to_svm(vcpu); - u64 *entry = svm->avic_physical_id_cache; - - if (!entry) - return false; - - return (READ_ONCE(*entry) & AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK); -} - -static void recalc_intercepts(struct vcpu_svm *svm) -{ - struct vmcb_control_area *c, *h; - struct nested_state *g; - - mark_dirty(svm->vmcb, VMCB_INTERCEPTS); - - if (!is_guest_mode(&svm->vcpu)) - return; - - c = &svm->vmcb->control; - h = &svm->nested.hsave->control; - g = &svm->nested; - - c->intercept_cr = h->intercept_cr; - c->intercept_dr = h->intercept_dr; - c->intercept_exceptions = h->intercept_exceptions; - c->intercept = h->intercept; - - if (svm->vcpu.arch.hflags & HF_VINTR_MASK) { - /* We only want the cr8 intercept bits of L1 */ - c->intercept_cr &= ~(1U << INTERCEPT_CR8_READ); - c->intercept_cr &= ~(1U << INTERCEPT_CR8_WRITE); - - /* - * Once running L2 with HF_VINTR_MASK, EFLAGS.IF does not - * affect any interrupt we may want to inject; therefore, - * interrupt window vmexits are irrelevant to L0. - */ - c->intercept &= ~(1ULL << INTERCEPT_VINTR); - } - - /* We don't want to see VMMCALLs from a nested guest */ - c->intercept &= ~(1ULL << INTERCEPT_VMMCALL); - - c->intercept_cr |= g->intercept_cr; - c->intercept_dr |= g->intercept_dr; - c->intercept_exceptions |= g->intercept_exceptions; - c->intercept |= g->intercept; -} - -static inline struct vmcb *get_host_vmcb(struct vcpu_svm *svm) -{ - if (is_guest_mode(&svm->vcpu)) - return svm->nested.hsave; - else - return svm->vmcb; -} - -static inline void set_cr_intercept(struct vcpu_svm *svm, int bit) -{ - struct vmcb *vmcb = get_host_vmcb(svm); - - vmcb->control.intercept_cr |= (1U << bit); - - recalc_intercepts(svm); -} - -static inline void clr_cr_intercept(struct vcpu_svm *svm, int bit) -{ - struct vmcb *vmcb = get_host_vmcb(svm); - - vmcb->control.intercept_cr &= ~(1U << bit); - - recalc_intercepts(svm); -} - -static inline bool is_cr_intercept(struct vcpu_svm *svm, int bit) -{ - struct vmcb *vmcb = get_host_vmcb(svm); - - return vmcb->control.intercept_cr & (1U << bit); -} - -static inline void set_dr_intercepts(struct vcpu_svm *svm) -{ - struct vmcb *vmcb = get_host_vmcb(svm); - - vmcb->control.intercept_dr = (1 << INTERCEPT_DR0_READ) - | (1 << INTERCEPT_DR1_READ) - | (1 << INTERCEPT_DR2_READ) - | (1 << INTERCEPT_DR3_READ) - | (1 << INTERCEPT_DR4_READ) - | (1 << INTERCEPT_DR5_READ) - | (1 << INTERCEPT_DR6_READ) - | (1 << INTERCEPT_DR7_READ) - | (1 << INTERCEPT_DR0_WRITE) - | (1 << INTERCEPT_DR1_WRITE) - | (1 << INTERCEPT_DR2_WRITE) - | (1 << INTERCEPT_DR3_WRITE) - | (1 << INTERCEPT_DR4_WRITE) - | (1 << INTERCEPT_DR5_WRITE) - | (1 << INTERCEPT_DR6_WRITE) - | (1 << INTERCEPT_DR7_WRITE); - - recalc_intercepts(svm); -} - -static inline void clr_dr_intercepts(struct vcpu_svm *svm) -{ - struct vmcb *vmcb = get_host_vmcb(svm); - - vmcb->control.intercept_dr = 0; - - recalc_intercepts(svm); -} - -static inline void set_exception_intercept(struct vcpu_svm *svm, int bit) -{ - struct vmcb *vmcb = get_host_vmcb(svm); - - vmcb->control.intercept_exceptions |= (1U << bit); - - recalc_intercepts(svm); -} - -static inline void clr_exception_intercept(struct vcpu_svm *svm, int bit) -{ - struct vmcb *vmcb = get_host_vmcb(svm); - - vmcb->control.intercept_exceptions &= ~(1U << bit); - - recalc_intercepts(svm); -} - -static inline void set_intercept(struct vcpu_svm *svm, int bit) -{ - struct vmcb *vmcb = get_host_vmcb(svm); - - vmcb->control.intercept |= (1ULL << bit); - - recalc_intercepts(svm); -} - -static inline void clr_intercept(struct vcpu_svm *svm, int bit) -{ - struct vmcb *vmcb = get_host_vmcb(svm); - - vmcb->control.intercept &= ~(1ULL << bit); - - recalc_intercepts(svm); -} - -static inline bool is_intercept(struct vcpu_svm *svm, int bit) -{ - return (svm->vmcb->control.intercept & (1ULL << bit)) != 0; -} - -static inline bool vgif_enabled(struct vcpu_svm *svm) -{ - return !!(svm->vmcb->control.int_ctl & V_GIF_ENABLE_MASK); -} - -static inline void enable_gif(struct vcpu_svm *svm) -{ - if (vgif_enabled(svm)) - svm->vmcb->control.int_ctl |= V_GIF_MASK; - else - svm->vcpu.arch.hflags |= HF_GIF_MASK; -} - -static inline void disable_gif(struct vcpu_svm *svm) -{ - if (vgif_enabled(svm)) - svm->vmcb->control.int_ctl &= ~V_GIF_MASK; - else - svm->vcpu.arch.hflags &= ~HF_GIF_MASK; -} - -static inline bool gif_set(struct vcpu_svm *svm) -{ - if (vgif_enabled(svm)) - return !!(svm->vmcb->control.int_ctl & V_GIF_MASK); - else - return !!(svm->vcpu.arch.hflags & HF_GIF_MASK); -} static unsigned long iopm_base; @@ -696,23 +207,7 @@ struct kvm_ldttss_desc { u32 zero1; } __attribute__((packed)); -struct svm_cpu_data { - int cpu; - - u64 asid_generation; - u32 max_asid; - u32 next_asid; - u32 min_asid; - struct kvm_ldttss_desc *tss_desc; - - struct page *save_area; - struct vmcb *current_vmcb; - - /* index = sev_asid, value = vmcb pointer */ - struct vmcb **sev_vmcbs; -}; - -static DEFINE_PER_CPU(struct svm_cpu_data *, svm_data); +DEFINE_PER_CPU(struct svm_cpu_data *, svm_data); static const u32 msrpm_ranges[] = {0, 0xc0000000, 0xc0010000}; @@ -720,7 +215,7 @@ static const u32 msrpm_ranges[] = {0, 0xc0000000, 0xc0010000}; #define MSRS_RANGE_SIZE 2048 #define MSRS_IN_RANGE (MSRS_RANGE_SIZE * 8 / 2) -static u32 svm_msrpm_offset(u32 msr) +u32 svm_msrpm_offset(u32 msr) { u32 offset; int i; @@ -767,7 +262,7 @@ static int get_npt_level(struct kvm_vcpu *vcpu) #endif } -static void svm_set_efer(struct kvm_vcpu *vcpu, u64 efer) +void svm_set_efer(struct kvm_vcpu *vcpu, u64 efer) { vcpu->arch.efer = efer; @@ -1198,7 +693,7 @@ static void svm_disable_lbrv(struct vcpu_svm *svm) set_msr_interception(msrpm, MSR_IA32_LASTINTTOIP, 0, 0); } -static void disable_nmi_singlestep(struct vcpu_svm *svm) +void disable_nmi_singlestep(struct vcpu_svm *svm) { svm->nmi_singlestep = false; @@ -1211,97 +706,6 @@ static void disable_nmi_singlestep(struct vcpu_svm *svm) } } -/* Note: - * This hash table is used to map VM_ID to a struct kvm_svm, - * when handling AMD IOMMU GALOG notification to schedule in - * a particular vCPU. - */ -#define SVM_VM_DATA_HASH_BITS 8 -static DEFINE_HASHTABLE(svm_vm_data_hash, SVM_VM_DATA_HASH_BITS); -static u32 next_vm_id = 0; -static bool next_vm_id_wrapped = 0; -static DEFINE_SPINLOCK(svm_vm_data_hash_lock); - -/* Note: - * This function is called from IOMMU driver to notify - * SVM to schedule in a particular vCPU of a particular VM. - */ -static int avic_ga_log_notifier(u32 ga_tag) -{ - unsigned long flags; - struct kvm_svm *kvm_svm; - struct kvm_vcpu *vcpu = NULL; - u32 vm_id = AVIC_GATAG_TO_VMID(ga_tag); - u32 vcpu_id = AVIC_GATAG_TO_VCPUID(ga_tag); - - pr_debug("SVM: %s: vm_id=%#x, vcpu_id=%#x\n", __func__, vm_id, vcpu_id); - trace_kvm_avic_ga_log(vm_id, vcpu_id); - - spin_lock_irqsave(&svm_vm_data_hash_lock, flags); - hash_for_each_possible(svm_vm_data_hash, kvm_svm, hnode, vm_id) { - if (kvm_svm->avic_vm_id != vm_id) - continue; - vcpu = kvm_get_vcpu_by_id(&kvm_svm->kvm, vcpu_id); - break; - } - spin_unlock_irqrestore(&svm_vm_data_hash_lock, flags); - - /* Note: - * At this point, the IOMMU should have already set the pending - * bit in the vAPIC backing page. So, we just need to schedule - * in the vcpu. - */ - if (vcpu) - kvm_vcpu_wake_up(vcpu); - - return 0; -} - -static __init int sev_hardware_setup(void) -{ - struct sev_user_data_status *status; - int rc; - - /* Maximum number of encrypted guests supported simultaneously */ - max_sev_asid = cpuid_ecx(0x8000001F); - - if (!max_sev_asid) - return 1; - - /* Minimum ASID value that should be used for SEV guest */ - min_sev_asid = cpuid_edx(0x8000001F); - - /* Initialize SEV ASID bitmaps */ - sev_asid_bitmap = bitmap_zalloc(max_sev_asid, GFP_KERNEL); - if (!sev_asid_bitmap) - return 1; - - sev_reclaim_asid_bitmap = bitmap_zalloc(max_sev_asid, GFP_KERNEL); - if (!sev_reclaim_asid_bitmap) - return 1; - - status = kmalloc(sizeof(*status), GFP_KERNEL); - if (!status) - return 1; - - /* - * Check SEV platform status. - * - * PLATFORM_STATUS can be called in any state, if we failed to query - * the PLATFORM status then either PSP firmware does not support SEV - * feature or SEV firmware is dead. - */ - rc = sev_platform_status(status, NULL); - if (rc) - goto err; - - pr_info("SEV supported\n"); - -err: - kfree(status); - return rc; -} - static void grow_ple_window(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); @@ -1383,12 +787,8 @@ static void svm_hardware_teardown(void) { int cpu; - if (svm_sev_enabled()) { - bitmap_free(sev_asid_bitmap); - bitmap_free(sev_reclaim_asid_bitmap); - - sev_flush_asids(); - } + if (svm_sev_enabled()) + sev_hardware_teardown(); for_each_possible_cpu(cpu) svm_cpu_uninit(cpu); @@ -1585,24 +985,6 @@ static u64 svm_write_l1_tsc_offset(struct kvm_vcpu *vcpu, u64 offset) return svm->vmcb->control.tsc_offset; } -static void avic_init_vmcb(struct vcpu_svm *svm) -{ - struct vmcb *vmcb = svm->vmcb; - struct kvm_svm *kvm_svm = to_kvm_svm(svm->vcpu.kvm); - phys_addr_t bpa = __sme_set(page_to_phys(svm->avic_backing_page)); - phys_addr_t lpa = __sme_set(page_to_phys(kvm_svm->avic_logical_id_table_page)); - phys_addr_t ppa = __sme_set(page_to_phys(kvm_svm->avic_physical_id_table_page)); - - vmcb->control.avic_backing_page = bpa & AVIC_HPA_MASK; - vmcb->control.avic_logical_id = lpa & AVIC_HPA_MASK; - vmcb->control.avic_physical_id = ppa & AVIC_HPA_MASK; - vmcb->control.avic_physical_id |= AVIC_MAX_PHYSICAL_ID_COUNT; - if (kvm_apicv_activated(svm->vcpu.kvm)) - vmcb->control.int_ctl |= AVIC_ENABLE_MASK; - else - vmcb->control.int_ctl &= ~AVIC_ENABLE_MASK; -} - static void init_vmcb(struct vcpu_svm *svm) { struct vmcb_control_area *control = &svm->vmcb->control; @@ -1762,449 +1144,6 @@ static void init_vmcb(struct vcpu_svm *svm) } -static u64 *avic_get_physical_id_entry(struct kvm_vcpu *vcpu, - unsigned int index) -{ - u64 *avic_physical_id_table; - struct kvm_svm *kvm_svm = to_kvm_svm(vcpu->kvm); - - if (index >= AVIC_MAX_PHYSICAL_ID_COUNT) - return NULL; - - avic_physical_id_table = page_address(kvm_svm->avic_physical_id_table_page); - - return &avic_physical_id_table[index]; -} - -/** - * Note: - * AVIC hardware walks the nested page table to check permissions, - * but does not use the SPA address specified in the leaf page - * table entry since it uses address in the AVIC_BACKING_PAGE pointer - * field of the VMCB. Therefore, we set up the - * APIC_ACCESS_PAGE_PRIVATE_MEMSLOT (4KB) here. - */ -static int avic_update_access_page(struct kvm *kvm, bool activate) -{ - int ret = 0; - - mutex_lock(&kvm->slots_lock); - /* - * During kvm_destroy_vm(), kvm_pit_set_reinject() could trigger - * APICv mode change, which update APIC_ACCESS_PAGE_PRIVATE_MEMSLOT - * memory region. So, we need to ensure that kvm->mm == current->mm. - */ - if ((kvm->arch.apic_access_page_done == activate) || - (kvm->mm != current->mm)) - goto out; - - ret = __x86_set_memory_region(kvm, - APIC_ACCESS_PAGE_PRIVATE_MEMSLOT, - APIC_DEFAULT_PHYS_BASE, - activate ? PAGE_SIZE : 0); - if (ret) - goto out; - - kvm->arch.apic_access_page_done = activate; -out: - mutex_unlock(&kvm->slots_lock); - return ret; -} - -static int avic_init_backing_page(struct kvm_vcpu *vcpu) -{ - u64 *entry, new_entry; - int id = vcpu->vcpu_id; - struct vcpu_svm *svm = to_svm(vcpu); - - if (id >= AVIC_MAX_PHYSICAL_ID_COUNT) - return -EINVAL; - - if (!svm->vcpu.arch.apic->regs) - return -EINVAL; - - if (kvm_apicv_activated(vcpu->kvm)) { - int ret; - - ret = avic_update_access_page(vcpu->kvm, true); - if (ret) - return ret; - } - - svm->avic_backing_page = virt_to_page(svm->vcpu.arch.apic->regs); - - /* Setting AVIC backing page address in the phy APIC ID table */ - entry = avic_get_physical_id_entry(vcpu, id); - if (!entry) - return -EINVAL; - - new_entry = __sme_set((page_to_phys(svm->avic_backing_page) & - AVIC_PHYSICAL_ID_ENTRY_BACKING_PAGE_MASK) | - AVIC_PHYSICAL_ID_ENTRY_VALID_MASK); - WRITE_ONCE(*entry, new_entry); - - svm->avic_physical_id_cache = entry; - - return 0; -} - -static void sev_asid_free(int asid) -{ - struct svm_cpu_data *sd; - int cpu, pos; - - mutex_lock(&sev_bitmap_lock); - - pos = asid - 1; - __set_bit(pos, sev_reclaim_asid_bitmap); - - for_each_possible_cpu(cpu) { - sd = per_cpu(svm_data, cpu); - sd->sev_vmcbs[pos] = NULL; - } - - mutex_unlock(&sev_bitmap_lock); -} - -static void sev_unbind_asid(struct kvm *kvm, unsigned int handle) -{ - struct sev_data_decommission *decommission; - struct sev_data_deactivate *data; - - if (!handle) - return; - - data = kzalloc(sizeof(*data), GFP_KERNEL); - if (!data) - return; - - /* deactivate handle */ - data->handle = handle; - - /* Guard DEACTIVATE against WBINVD/DF_FLUSH used in ASID recycling */ - down_read(&sev_deactivate_lock); - sev_guest_deactivate(data, NULL); - up_read(&sev_deactivate_lock); - - kfree(data); - - decommission = kzalloc(sizeof(*decommission), GFP_KERNEL); - if (!decommission) - return; - - /* decommission handle */ - decommission->handle = handle; - sev_guest_decommission(decommission, NULL); - - kfree(decommission); -} - -static struct page **sev_pin_memory(struct kvm *kvm, unsigned long uaddr, - unsigned long ulen, unsigned long *n, - int write) -{ - struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; - unsigned long npages, npinned, size; - unsigned long locked, lock_limit; - struct page **pages; - unsigned long first, last; - - if (ulen == 0 || uaddr + ulen < uaddr) - return NULL; - - /* Calculate number of pages. */ - first = (uaddr & PAGE_MASK) >> PAGE_SHIFT; - last = ((uaddr + ulen - 1) & PAGE_MASK) >> PAGE_SHIFT; - npages = (last - first + 1); - - locked = sev->pages_locked + npages; - lock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT; - if (locked > lock_limit && !capable(CAP_IPC_LOCK)) { - pr_err("SEV: %lu locked pages exceed the lock limit of %lu.\n", locked, lock_limit); - return NULL; - } - - /* Avoid using vmalloc for smaller buffers. */ - size = npages * sizeof(struct page *); - if (size > PAGE_SIZE) - pages = __vmalloc(size, GFP_KERNEL_ACCOUNT | __GFP_ZERO, - PAGE_KERNEL); - else - pages = kmalloc(size, GFP_KERNEL_ACCOUNT); - - if (!pages) - return NULL; - - /* Pin the user virtual address. */ - npinned = get_user_pages_fast(uaddr, npages, FOLL_WRITE, pages); - if (npinned != npages) { - pr_err("SEV: Failure locking %lu pages.\n", npages); - goto err; - } - - *n = npages; - sev->pages_locked = locked; - - return pages; - -err: - if (npinned > 0) - release_pages(pages, npinned); - - kvfree(pages); - return NULL; -} - -static void sev_unpin_memory(struct kvm *kvm, struct page **pages, - unsigned long npages) -{ - struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; - - release_pages(pages, npages); - kvfree(pages); - sev->pages_locked -= npages; -} - -static void sev_clflush_pages(struct page *pages[], unsigned long npages) -{ - uint8_t *page_virtual; - unsigned long i; - - if (npages == 0 || pages == NULL) - return; - - for (i = 0; i < npages; i++) { - page_virtual = kmap_atomic(pages[i]); - clflush_cache_range(page_virtual, PAGE_SIZE); - kunmap_atomic(page_virtual); - } -} - -static void __unregister_enc_region_locked(struct kvm *kvm, - struct enc_region *region) -{ - sev_unpin_memory(kvm, region->pages, region->npages); - list_del(®ion->list); - kfree(region); -} - -static void sev_vm_destroy(struct kvm *kvm) -{ - struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; - struct list_head *head = &sev->regions_list; - struct list_head *pos, *q; - - if (!sev_guest(kvm)) - return; - - mutex_lock(&kvm->lock); - - /* - * Ensure that all guest tagged cache entries are flushed before - * releasing the pages back to the system for use. CLFLUSH will - * not do this, so issue a WBINVD. - */ - wbinvd_on_all_cpus(); - - /* - * if userspace was terminated before unregistering the memory regions - * then lets unpin all the registered memory. - */ - if (!list_empty(head)) { - list_for_each_safe(pos, q, head) { - __unregister_enc_region_locked(kvm, - list_entry(pos, struct enc_region, list)); - } - } - - mutex_unlock(&kvm->lock); - - sev_unbind_asid(kvm, sev->handle); - sev_asid_free(sev->asid); -} - -static void avic_vm_destroy(struct kvm *kvm) -{ - unsigned long flags; - struct kvm_svm *kvm_svm = to_kvm_svm(kvm); - - if (!avic) - return; - - if (kvm_svm->avic_logical_id_table_page) - __free_page(kvm_svm->avic_logical_id_table_page); - if (kvm_svm->avic_physical_id_table_page) - __free_page(kvm_svm->avic_physical_id_table_page); - - spin_lock_irqsave(&svm_vm_data_hash_lock, flags); - hash_del(&kvm_svm->hnode); - spin_unlock_irqrestore(&svm_vm_data_hash_lock, flags); -} - -static void svm_vm_destroy(struct kvm *kvm) -{ - avic_vm_destroy(kvm); - sev_vm_destroy(kvm); -} - -static int avic_vm_init(struct kvm *kvm) -{ - unsigned long flags; - int err = -ENOMEM; - struct kvm_svm *kvm_svm = to_kvm_svm(kvm); - struct kvm_svm *k2; - struct page *p_page; - struct page *l_page; - u32 vm_id; - - if (!avic) - return 0; - - /* Allocating physical APIC ID table (4KB) */ - p_page = alloc_page(GFP_KERNEL_ACCOUNT); - if (!p_page) - goto free_avic; - - kvm_svm->avic_physical_id_table_page = p_page; - clear_page(page_address(p_page)); - - /* Allocating logical APIC ID table (4KB) */ - l_page = alloc_page(GFP_KERNEL_ACCOUNT); - if (!l_page) - goto free_avic; - - kvm_svm->avic_logical_id_table_page = l_page; - clear_page(page_address(l_page)); - - spin_lock_irqsave(&svm_vm_data_hash_lock, flags); - again: - vm_id = next_vm_id = (next_vm_id + 1) & AVIC_VM_ID_MASK; - if (vm_id == 0) { /* id is 1-based, zero is not okay */ - next_vm_id_wrapped = 1; - goto again; - } - /* Is it still in use? Only possible if wrapped at least once */ - if (next_vm_id_wrapped) { - hash_for_each_possible(svm_vm_data_hash, k2, hnode, vm_id) { - if (k2->avic_vm_id == vm_id) - goto again; - } - } - kvm_svm->avic_vm_id = vm_id; - hash_add(svm_vm_data_hash, &kvm_svm->hnode, kvm_svm->avic_vm_id); - spin_unlock_irqrestore(&svm_vm_data_hash_lock, flags); - - return 0; - -free_avic: - avic_vm_destroy(kvm); - return err; -} - -static int svm_vm_init(struct kvm *kvm) -{ - if (avic) { - int ret = avic_vm_init(kvm); - if (ret) - return ret; - } - - kvm_apicv_init(kvm, avic); - return 0; -} - -static inline int -avic_update_iommu_vcpu_affinity(struct kvm_vcpu *vcpu, int cpu, bool r) -{ - int ret = 0; - unsigned long flags; - struct amd_svm_iommu_ir *ir; - struct vcpu_svm *svm = to_svm(vcpu); - - if (!kvm_arch_has_assigned_device(vcpu->kvm)) - return 0; - - /* - * Here, we go through the per-vcpu ir_list to update all existing - * interrupt remapping table entry targeting this vcpu. - */ - spin_lock_irqsave(&svm->ir_list_lock, flags); - - if (list_empty(&svm->ir_list)) - goto out; - - list_for_each_entry(ir, &svm->ir_list, node) { - ret = amd_iommu_update_ga(cpu, r, ir->data); - if (ret) - break; - } -out: - spin_unlock_irqrestore(&svm->ir_list_lock, flags); - return ret; -} - -static void avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu) -{ - u64 entry; - /* ID = 0xff (broadcast), ID > 0xff (reserved) */ - int h_physical_id = kvm_cpu_get_apicid(cpu); - struct vcpu_svm *svm = to_svm(vcpu); - - if (!kvm_vcpu_apicv_active(vcpu)) - return; - - /* - * Since the host physical APIC id is 8 bits, - * we can support host APIC ID upto 255. - */ - if (WARN_ON(h_physical_id > AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK)) - return; - - entry = READ_ONCE(*(svm->avic_physical_id_cache)); - WARN_ON(entry & AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK); - - entry &= ~AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK; - entry |= (h_physical_id & AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK); - - entry &= ~AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK; - if (svm->avic_is_running) - entry |= AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK; - - WRITE_ONCE(*(svm->avic_physical_id_cache), entry); - avic_update_iommu_vcpu_affinity(vcpu, h_physical_id, - svm->avic_is_running); -} - -static void avic_vcpu_put(struct kvm_vcpu *vcpu) -{ - u64 entry; - struct vcpu_svm *svm = to_svm(vcpu); - - if (!kvm_vcpu_apicv_active(vcpu)) - return; - - entry = READ_ONCE(*(svm->avic_physical_id_cache)); - if (entry & AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK) - avic_update_iommu_vcpu_affinity(vcpu, -1, 0); - - entry &= ~AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK; - WRITE_ONCE(*(svm->avic_physical_id_cache), entry); -} - -/** - * This function is called during VCPU halt/unhalt. - */ -static void avic_set_running(struct kvm_vcpu *vcpu, bool is_run) -{ - struct vcpu_svm *svm = to_svm(vcpu); - - svm->avic_is_running = is_run; - if (is_run) - avic_vcpu_load(vcpu, vcpu->cpu); - else - avic_vcpu_put(vcpu); -} - static void svm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) { struct vcpu_svm *svm = to_svm(vcpu); @@ -2229,25 +1168,6 @@ static void svm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) avic_update_vapic_bar(svm, APIC_DEFAULT_PHYS_BASE); } -static int avic_init_vcpu(struct vcpu_svm *svm) -{ - int ret; - struct kvm_vcpu *vcpu = &svm->vcpu; - - if (!avic || !irqchip_in_kernel(vcpu->kvm)) - return 0; - - ret = avic_init_backing_page(&svm->vcpu); - if (ret) - return ret; - - INIT_LIST_HEAD(&svm->ir_list); - spin_lock_init(&svm->ir_list_lock); - svm->dfr_reg = APIC_DFR_FLAT; - - return ret; -} - static int svm_create_vcpu(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm; @@ -2404,18 +1324,6 @@ static void svm_vcpu_put(struct kvm_vcpu *vcpu) wrmsrl(host_save_user_msrs[i], svm->host_user_msrs[i]); } -static void svm_vcpu_blocking(struct kvm_vcpu *vcpu) -{ - avic_set_running(vcpu, false); -} - -static void svm_vcpu_unblocking(struct kvm_vcpu *vcpu) -{ - if (kvm_check_request(KVM_REQ_APICV_UPDATE, vcpu)) - kvm_vcpu_update_apicv(vcpu); - avic_set_running(vcpu, true); -} - static unsigned long svm_get_rflags(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); @@ -2652,7 +1560,7 @@ static void update_cr0_intercept(struct vcpu_svm *svm) } } -static void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) +void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) { struct vcpu_svm *svm = to_svm(vcpu); @@ -2686,7 +1594,7 @@ static void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) update_cr0_intercept(svm); } -static int svm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) +int svm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) { unsigned long host_cr4_mce = cr4_read_shadow() & X86_CR4_MCE; unsigned long old_cr4 = to_svm(vcpu)->vmcb->save.cr4; @@ -3022,776 +1930,6 @@ static int vmmcall_interception(struct vcpu_svm *svm) return kvm_emulate_hypercall(&svm->vcpu); } -static unsigned long nested_svm_get_tdp_cr3(struct kvm_vcpu *vcpu) -{ - struct vcpu_svm *svm = to_svm(vcpu); - - return svm->nested.nested_cr3; -} - -static u64 nested_svm_get_tdp_pdptr(struct kvm_vcpu *vcpu, int index) -{ - struct vcpu_svm *svm = to_svm(vcpu); - u64 cr3 = svm->nested.nested_cr3; - u64 pdpte; - int ret; - - ret = kvm_vcpu_read_guest_page(vcpu, gpa_to_gfn(__sme_clr(cr3)), &pdpte, - offset_in_page(cr3) + index * 8, 8); - if (ret) - return 0; - return pdpte; -} - -static void nested_svm_inject_npf_exit(struct kvm_vcpu *vcpu, - struct x86_exception *fault) -{ - struct vcpu_svm *svm = to_svm(vcpu); - - if (svm->vmcb->control.exit_code != SVM_EXIT_NPF) { - /* - * TODO: track the cause of the nested page fault, and - * correctly fill in the high bits of exit_info_1. - */ - svm->vmcb->control.exit_code = SVM_EXIT_NPF; - svm->vmcb->control.exit_code_hi = 0; - svm->vmcb->control.exit_info_1 = (1ULL << 32); - svm->vmcb->control.exit_info_2 = fault->address; - } - - svm->vmcb->control.exit_info_1 &= ~0xffffffffULL; - svm->vmcb->control.exit_info_1 |= fault->error_code; - - /* - * The present bit is always zero for page structure faults on real - * hardware. - */ - if (svm->vmcb->control.exit_info_1 & (2ULL << 32)) - svm->vmcb->control.exit_info_1 &= ~1; - - nested_svm_vmexit(svm); -} - -static void nested_svm_init_mmu_context(struct kvm_vcpu *vcpu) -{ - WARN_ON(mmu_is_nested(vcpu)); - - vcpu->arch.mmu = &vcpu->arch.guest_mmu; - kvm_init_shadow_mmu(vcpu); - vcpu->arch.mmu->get_guest_pgd = nested_svm_get_tdp_cr3; - vcpu->arch.mmu->get_pdptr = nested_svm_get_tdp_pdptr; - vcpu->arch.mmu->inject_page_fault = nested_svm_inject_npf_exit; - vcpu->arch.mmu->shadow_root_level = get_npt_level(vcpu); - reset_shadow_zero_bits_mask(vcpu, vcpu->arch.mmu); - vcpu->arch.walk_mmu = &vcpu->arch.nested_mmu; -} - -static void nested_svm_uninit_mmu_context(struct kvm_vcpu *vcpu) -{ - vcpu->arch.mmu = &vcpu->arch.root_mmu; - vcpu->arch.walk_mmu = &vcpu->arch.root_mmu; -} - -static int nested_svm_check_permissions(struct vcpu_svm *svm) -{ - if (!(svm->vcpu.arch.efer & EFER_SVME) || - !is_paging(&svm->vcpu)) { - kvm_queue_exception(&svm->vcpu, UD_VECTOR); - return 1; - } - - if (svm->vmcb->save.cpl) { - kvm_inject_gp(&svm->vcpu, 0); - return 1; - } - - return 0; -} - -static int nested_svm_check_exception(struct vcpu_svm *svm, unsigned nr, - bool has_error_code, u32 error_code) -{ - int vmexit; - - if (!is_guest_mode(&svm->vcpu)) - return 0; - - vmexit = nested_svm_intercept(svm); - if (vmexit != NESTED_EXIT_DONE) - return 0; - - svm->vmcb->control.exit_code = SVM_EXIT_EXCP_BASE + nr; - svm->vmcb->control.exit_code_hi = 0; - svm->vmcb->control.exit_info_1 = error_code; - - /* - * EXITINFO2 is undefined for all exception intercepts other - * than #PF. - */ - if (svm->vcpu.arch.exception.nested_apf) - svm->vmcb->control.exit_info_2 = svm->vcpu.arch.apf.nested_apf_token; - else if (svm->vcpu.arch.exception.has_payload) - svm->vmcb->control.exit_info_2 = svm->vcpu.arch.exception.payload; - else - svm->vmcb->control.exit_info_2 = svm->vcpu.arch.cr2; - - svm->nested.exit_required = true; - return vmexit; -} - -static void nested_svm_intr(struct vcpu_svm *svm) -{ - svm->vmcb->control.exit_code = SVM_EXIT_INTR; - svm->vmcb->control.exit_info_1 = 0; - svm->vmcb->control.exit_info_2 = 0; - - /* nested_svm_vmexit this gets called afterwards from handle_exit */ - svm->nested.exit_required = true; - trace_kvm_nested_intr_vmexit(svm->vmcb->save.rip); -} - -static bool nested_exit_on_intr(struct vcpu_svm *svm) -{ - return (svm->nested.intercept & 1ULL); -} - -static int svm_check_nested_events(struct kvm_vcpu *vcpu) -{ - struct vcpu_svm *svm = to_svm(vcpu); - bool block_nested_events = - kvm_event_needs_reinjection(vcpu) || svm->nested.exit_required; - - if (kvm_cpu_has_interrupt(vcpu) && nested_exit_on_intr(svm)) { - if (block_nested_events) - return -EBUSY; - nested_svm_intr(svm); - return 0; - } - - return 0; -} - -/* This function returns true if it is save to enable the nmi window */ -static inline bool nested_svm_nmi(struct vcpu_svm *svm) -{ - if (!is_guest_mode(&svm->vcpu)) - return true; - - if (!(svm->nested.intercept & (1ULL << INTERCEPT_NMI))) - return true; - - svm->vmcb->control.exit_code = SVM_EXIT_NMI; - svm->nested.exit_required = true; - - return false; -} - -static int nested_svm_intercept_ioio(struct vcpu_svm *svm) -{ - unsigned port, size, iopm_len; - u16 val, mask; - u8 start_bit; - u64 gpa; - - if (!(svm->nested.intercept & (1ULL << INTERCEPT_IOIO_PROT))) - return NESTED_EXIT_HOST; - - port = svm->vmcb->control.exit_info_1 >> 16; - size = (svm->vmcb->control.exit_info_1 & SVM_IOIO_SIZE_MASK) >> - SVM_IOIO_SIZE_SHIFT; - gpa = svm->nested.vmcb_iopm + (port / 8); - start_bit = port % 8; - iopm_len = (start_bit + size > 8) ? 2 : 1; - mask = (0xf >> (4 - size)) << start_bit; - val = 0; - - if (kvm_vcpu_read_guest(&svm->vcpu, gpa, &val, iopm_len)) - return NESTED_EXIT_DONE; - - return (val & mask) ? NESTED_EXIT_DONE : NESTED_EXIT_HOST; -} - -static int nested_svm_exit_handled_msr(struct vcpu_svm *svm) -{ - u32 offset, msr, value; - int write, mask; - - if (!(svm->nested.intercept & (1ULL << INTERCEPT_MSR_PROT))) - return NESTED_EXIT_HOST; - - msr = svm->vcpu.arch.regs[VCPU_REGS_RCX]; - offset = svm_msrpm_offset(msr); - write = svm->vmcb->control.exit_info_1 & 1; - mask = 1 << ((2 * (msr & 0xf)) + write); - - if (offset == MSR_INVALID) - return NESTED_EXIT_DONE; - - /* Offset is in 32 bit units but need in 8 bit units */ - offset *= 4; - - if (kvm_vcpu_read_guest(&svm->vcpu, svm->nested.vmcb_msrpm + offset, &value, 4)) - return NESTED_EXIT_DONE; - - return (value & mask) ? NESTED_EXIT_DONE : NESTED_EXIT_HOST; -} - -/* DB exceptions for our internal use must not cause vmexit */ -static int nested_svm_intercept_db(struct vcpu_svm *svm) -{ - unsigned long dr6; - - /* if we're not singlestepping, it's not ours */ - if (!svm->nmi_singlestep) - return NESTED_EXIT_DONE; - - /* if it's not a singlestep exception, it's not ours */ - if (kvm_get_dr(&svm->vcpu, 6, &dr6)) - return NESTED_EXIT_DONE; - if (!(dr6 & DR6_BS)) - return NESTED_EXIT_DONE; - - /* if the guest is singlestepping, it should get the vmexit */ - if (svm->nmi_singlestep_guest_rflags & X86_EFLAGS_TF) { - disable_nmi_singlestep(svm); - return NESTED_EXIT_DONE; - } - - /* it's ours, the nested hypervisor must not see this one */ - return NESTED_EXIT_HOST; -} - -static int nested_svm_exit_special(struct vcpu_svm *svm) -{ - u32 exit_code = svm->vmcb->control.exit_code; - - switch (exit_code) { - case SVM_EXIT_INTR: - case SVM_EXIT_NMI: - case SVM_EXIT_EXCP_BASE + MC_VECTOR: - return NESTED_EXIT_HOST; - case SVM_EXIT_NPF: - /* For now we are always handling NPFs when using them */ - if (npt_enabled) - return NESTED_EXIT_HOST; - break; - case SVM_EXIT_EXCP_BASE + PF_VECTOR: - /* When we're shadowing, trap PFs, but not async PF */ - if (!npt_enabled && svm->vcpu.arch.apf.host_apf_reason == 0) - return NESTED_EXIT_HOST; - break; - default: - break; - } - - return NESTED_EXIT_CONTINUE; -} - -static int nested_svm_intercept(struct vcpu_svm *svm) -{ - u32 exit_code = svm->vmcb->control.exit_code; - int vmexit = NESTED_EXIT_HOST; - - switch (exit_code) { - case SVM_EXIT_MSR: - vmexit = nested_svm_exit_handled_msr(svm); - break; - case SVM_EXIT_IOIO: - vmexit = nested_svm_intercept_ioio(svm); - break; - case SVM_EXIT_READ_CR0 ... SVM_EXIT_WRITE_CR8: { - u32 bit = 1U << (exit_code - SVM_EXIT_READ_CR0); - if (svm->nested.intercept_cr & bit) - vmexit = NESTED_EXIT_DONE; - break; - } - case SVM_EXIT_READ_DR0 ... SVM_EXIT_WRITE_DR7: { - u32 bit = 1U << (exit_code - SVM_EXIT_READ_DR0); - if (svm->nested.intercept_dr & bit) - vmexit = NESTED_EXIT_DONE; - break; - } - case SVM_EXIT_EXCP_BASE ... SVM_EXIT_EXCP_BASE + 0x1f: { - u32 excp_bits = 1 << (exit_code - SVM_EXIT_EXCP_BASE); - if (svm->nested.intercept_exceptions & excp_bits) { - if (exit_code == SVM_EXIT_EXCP_BASE + DB_VECTOR) - vmexit = nested_svm_intercept_db(svm); - else - vmexit = NESTED_EXIT_DONE; - } - /* async page fault always cause vmexit */ - else if ((exit_code == SVM_EXIT_EXCP_BASE + PF_VECTOR) && - svm->vcpu.arch.exception.nested_apf != 0) - vmexit = NESTED_EXIT_DONE; - break; - } - case SVM_EXIT_ERR: { - vmexit = NESTED_EXIT_DONE; - break; - } - default: { - u64 exit_bits = 1ULL << (exit_code - SVM_EXIT_INTR); - if (svm->nested.intercept & exit_bits) - vmexit = NESTED_EXIT_DONE; - } - } - - return vmexit; -} - -static int nested_svm_exit_handled(struct vcpu_svm *svm) -{ - int vmexit; - - vmexit = nested_svm_intercept(svm); - - if (vmexit == NESTED_EXIT_DONE) - nested_svm_vmexit(svm); - - return vmexit; -} - -static inline void copy_vmcb_control_area(struct vmcb *dst_vmcb, struct vmcb *from_vmcb) -{ - struct vmcb_control_area *dst = &dst_vmcb->control; - struct vmcb_control_area *from = &from_vmcb->control; - - dst->intercept_cr = from->intercept_cr; - dst->intercept_dr = from->intercept_dr; - dst->intercept_exceptions = from->intercept_exceptions; - dst->intercept = from->intercept; - dst->iopm_base_pa = from->iopm_base_pa; - dst->msrpm_base_pa = from->msrpm_base_pa; - dst->tsc_offset = from->tsc_offset; - dst->asid = from->asid; - dst->tlb_ctl = from->tlb_ctl; - dst->int_ctl = from->int_ctl; - dst->int_vector = from->int_vector; - dst->int_state = from->int_state; - dst->exit_code = from->exit_code; - dst->exit_code_hi = from->exit_code_hi; - dst->exit_info_1 = from->exit_info_1; - dst->exit_info_2 = from->exit_info_2; - dst->exit_int_info = from->exit_int_info; - dst->exit_int_info_err = from->exit_int_info_err; - dst->nested_ctl = from->nested_ctl; - dst->event_inj = from->event_inj; - dst->event_inj_err = from->event_inj_err; - dst->nested_cr3 = from->nested_cr3; - dst->virt_ext = from->virt_ext; - dst->pause_filter_count = from->pause_filter_count; - dst->pause_filter_thresh = from->pause_filter_thresh; -} - -static int nested_svm_vmexit(struct vcpu_svm *svm) -{ - int rc; - struct vmcb *nested_vmcb; - struct vmcb *hsave = svm->nested.hsave; - struct vmcb *vmcb = svm->vmcb; - struct kvm_host_map map; - - trace_kvm_nested_vmexit_inject(vmcb->control.exit_code, - vmcb->control.exit_info_1, - vmcb->control.exit_info_2, - vmcb->control.exit_int_info, - vmcb->control.exit_int_info_err, - KVM_ISA_SVM); - - rc = kvm_vcpu_map(&svm->vcpu, gpa_to_gfn(svm->nested.vmcb), &map); - if (rc) { - if (rc == -EINVAL) - kvm_inject_gp(&svm->vcpu, 0); - return 1; - } - - nested_vmcb = map.hva; - - /* Exit Guest-Mode */ - leave_guest_mode(&svm->vcpu); - svm->nested.vmcb = 0; - - /* Give the current vmcb to the guest */ - disable_gif(svm); - - nested_vmcb->save.es = vmcb->save.es; - nested_vmcb->save.cs = vmcb->save.cs; - nested_vmcb->save.ss = vmcb->save.ss; - nested_vmcb->save.ds = vmcb->save.ds; - nested_vmcb->save.gdtr = vmcb->save.gdtr; - nested_vmcb->save.idtr = vmcb->save.idtr; - nested_vmcb->save.efer = svm->vcpu.arch.efer; - nested_vmcb->save.cr0 = kvm_read_cr0(&svm->vcpu); - nested_vmcb->save.cr3 = kvm_read_cr3(&svm->vcpu); - nested_vmcb->save.cr2 = vmcb->save.cr2; - nested_vmcb->save.cr4 = svm->vcpu.arch.cr4; - nested_vmcb->save.rflags = kvm_get_rflags(&svm->vcpu); - nested_vmcb->save.rip = vmcb->save.rip; - nested_vmcb->save.rsp = vmcb->save.rsp; - nested_vmcb->save.rax = vmcb->save.rax; - nested_vmcb->save.dr7 = vmcb->save.dr7; - nested_vmcb->save.dr6 = vmcb->save.dr6; - nested_vmcb->save.cpl = vmcb->save.cpl; - - nested_vmcb->control.int_ctl = vmcb->control.int_ctl; - nested_vmcb->control.int_vector = vmcb->control.int_vector; - nested_vmcb->control.int_state = vmcb->control.int_state; - nested_vmcb->control.exit_code = vmcb->control.exit_code; - nested_vmcb->control.exit_code_hi = vmcb->control.exit_code_hi; - nested_vmcb->control.exit_info_1 = vmcb->control.exit_info_1; - nested_vmcb->control.exit_info_2 = vmcb->control.exit_info_2; - nested_vmcb->control.exit_int_info = vmcb->control.exit_int_info; - nested_vmcb->control.exit_int_info_err = vmcb->control.exit_int_info_err; - - if (svm->nrips_enabled) - nested_vmcb->control.next_rip = vmcb->control.next_rip; - - /* - * If we emulate a VMRUN/#VMEXIT in the same host #vmexit cycle we have - * to make sure that we do not lose injected events. So check event_inj - * here and copy it to exit_int_info if it is valid. - * Exit_int_info and event_inj can't be both valid because the case - * below only happens on a VMRUN instruction intercept which has - * no valid exit_int_info set. - */ - if (vmcb->control.event_inj & SVM_EVTINJ_VALID) { - struct vmcb_control_area *nc = &nested_vmcb->control; - - nc->exit_int_info = vmcb->control.event_inj; - nc->exit_int_info_err = vmcb->control.event_inj_err; - } - - nested_vmcb->control.tlb_ctl = 0; - nested_vmcb->control.event_inj = 0; - nested_vmcb->control.event_inj_err = 0; - - nested_vmcb->control.pause_filter_count = - svm->vmcb->control.pause_filter_count; - nested_vmcb->control.pause_filter_thresh = - svm->vmcb->control.pause_filter_thresh; - - /* We always set V_INTR_MASKING and remember the old value in hflags */ - if (!(svm->vcpu.arch.hflags & HF_VINTR_MASK)) - nested_vmcb->control.int_ctl &= ~V_INTR_MASKING_MASK; - - /* Restore the original control entries */ - copy_vmcb_control_area(vmcb, hsave); - - svm->vcpu.arch.tsc_offset = svm->vmcb->control.tsc_offset; - kvm_clear_exception_queue(&svm->vcpu); - kvm_clear_interrupt_queue(&svm->vcpu); - - svm->nested.nested_cr3 = 0; - - /* Restore selected save entries */ - svm->vmcb->save.es = hsave->save.es; - svm->vmcb->save.cs = hsave->save.cs; - svm->vmcb->save.ss = hsave->save.ss; - svm->vmcb->save.ds = hsave->save.ds; - svm->vmcb->save.gdtr = hsave->save.gdtr; - svm->vmcb->save.idtr = hsave->save.idtr; - kvm_set_rflags(&svm->vcpu, hsave->save.rflags); - svm_set_efer(&svm->vcpu, hsave->save.efer); - svm_set_cr0(&svm->vcpu, hsave->save.cr0 | X86_CR0_PE); - svm_set_cr4(&svm->vcpu, hsave->save.cr4); - if (npt_enabled) { - svm->vmcb->save.cr3 = hsave->save.cr3; - svm->vcpu.arch.cr3 = hsave->save.cr3; - } else { - (void)kvm_set_cr3(&svm->vcpu, hsave->save.cr3); - } - kvm_rax_write(&svm->vcpu, hsave->save.rax); - kvm_rsp_write(&svm->vcpu, hsave->save.rsp); - kvm_rip_write(&svm->vcpu, hsave->save.rip); - svm->vmcb->save.dr7 = 0; - svm->vmcb->save.cpl = 0; - svm->vmcb->control.exit_int_info = 0; - - mark_all_dirty(svm->vmcb); - - kvm_vcpu_unmap(&svm->vcpu, &map, true); - - nested_svm_uninit_mmu_context(&svm->vcpu); - kvm_mmu_reset_context(&svm->vcpu); - kvm_mmu_load(&svm->vcpu); - - /* - * Drop what we picked up for L2 via svm_complete_interrupts() so it - * doesn't end up in L1. - */ - svm->vcpu.arch.nmi_injected = false; - kvm_clear_exception_queue(&svm->vcpu); - kvm_clear_interrupt_queue(&svm->vcpu); - - return 0; -} - -static bool nested_svm_vmrun_msrpm(struct vcpu_svm *svm) -{ - /* - * This function merges the msr permission bitmaps of kvm and the - * nested vmcb. It is optimized in that it only merges the parts where - * the kvm msr permission bitmap may contain zero bits - */ - int i; - - if (!(svm->nested.intercept & (1ULL << INTERCEPT_MSR_PROT))) - return true; - - for (i = 0; i < MSRPM_OFFSETS; i++) { - u32 value, p; - u64 offset; - - if (msrpm_offsets[i] == 0xffffffff) - break; - - p = msrpm_offsets[i]; - offset = svm->nested.vmcb_msrpm + (p * 4); - - if (kvm_vcpu_read_guest(&svm->vcpu, offset, &value, 4)) - return false; - - svm->nested.msrpm[p] = svm->msrpm[p] | value; - } - - svm->vmcb->control.msrpm_base_pa = __sme_set(__pa(svm->nested.msrpm)); - - return true; -} - -static bool nested_vmcb_checks(struct vmcb *vmcb) -{ - if ((vmcb->save.efer & EFER_SVME) == 0) - return false; - - if ((vmcb->control.intercept & (1ULL << INTERCEPT_VMRUN)) == 0) - return false; - - if (vmcb->control.asid == 0) - return false; - - if ((vmcb->control.nested_ctl & SVM_NESTED_CTL_NP_ENABLE) && - !npt_enabled) - return false; - - return true; -} - -static void enter_svm_guest_mode(struct vcpu_svm *svm, u64 vmcb_gpa, - struct vmcb *nested_vmcb, struct kvm_host_map *map) -{ - bool evaluate_pending_interrupts = - is_intercept(svm, INTERCEPT_VINTR) || - is_intercept(svm, INTERCEPT_IRET); - - if (kvm_get_rflags(&svm->vcpu) & X86_EFLAGS_IF) - svm->vcpu.arch.hflags |= HF_HIF_MASK; - else - svm->vcpu.arch.hflags &= ~HF_HIF_MASK; - - if (nested_vmcb->control.nested_ctl & SVM_NESTED_CTL_NP_ENABLE) { - svm->nested.nested_cr3 = nested_vmcb->control.nested_cr3; - nested_svm_init_mmu_context(&svm->vcpu); - } - - /* Load the nested guest state */ - svm->vmcb->save.es = nested_vmcb->save.es; - svm->vmcb->save.cs = nested_vmcb->save.cs; - svm->vmcb->save.ss = nested_vmcb->save.ss; - svm->vmcb->save.ds = nested_vmcb->save.ds; - svm->vmcb->save.gdtr = nested_vmcb->save.gdtr; - svm->vmcb->save.idtr = nested_vmcb->save.idtr; - kvm_set_rflags(&svm->vcpu, nested_vmcb->save.rflags); - svm_set_efer(&svm->vcpu, nested_vmcb->save.efer); - svm_set_cr0(&svm->vcpu, nested_vmcb->save.cr0); - svm_set_cr4(&svm->vcpu, nested_vmcb->save.cr4); - if (npt_enabled) { - svm->vmcb->save.cr3 = nested_vmcb->save.cr3; - svm->vcpu.arch.cr3 = nested_vmcb->save.cr3; - } else - (void)kvm_set_cr3(&svm->vcpu, nested_vmcb->save.cr3); - - /* Guest paging mode is active - reset mmu */ - kvm_mmu_reset_context(&svm->vcpu); - - svm->vmcb->save.cr2 = svm->vcpu.arch.cr2 = nested_vmcb->save.cr2; - kvm_rax_write(&svm->vcpu, nested_vmcb->save.rax); - kvm_rsp_write(&svm->vcpu, nested_vmcb->save.rsp); - kvm_rip_write(&svm->vcpu, nested_vmcb->save.rip); - - /* In case we don't even reach vcpu_run, the fields are not updated */ - svm->vmcb->save.rax = nested_vmcb->save.rax; - svm->vmcb->save.rsp = nested_vmcb->save.rsp; - svm->vmcb->save.rip = nested_vmcb->save.rip; - svm->vmcb->save.dr7 = nested_vmcb->save.dr7; - svm->vmcb->save.dr6 = nested_vmcb->save.dr6; - svm->vmcb->save.cpl = nested_vmcb->save.cpl; - - svm->nested.vmcb_msrpm = nested_vmcb->control.msrpm_base_pa & ~0x0fffULL; - svm->nested.vmcb_iopm = nested_vmcb->control.iopm_base_pa & ~0x0fffULL; - - /* cache intercepts */ - svm->nested.intercept_cr = nested_vmcb->control.intercept_cr; - svm->nested.intercept_dr = nested_vmcb->control.intercept_dr; - svm->nested.intercept_exceptions = nested_vmcb->control.intercept_exceptions; - svm->nested.intercept = nested_vmcb->control.intercept; - - svm_flush_tlb(&svm->vcpu, true); - svm->vmcb->control.int_ctl = nested_vmcb->control.int_ctl | V_INTR_MASKING_MASK; - if (nested_vmcb->control.int_ctl & V_INTR_MASKING_MASK) - svm->vcpu.arch.hflags |= HF_VINTR_MASK; - else - svm->vcpu.arch.hflags &= ~HF_VINTR_MASK; - - svm->vcpu.arch.tsc_offset += nested_vmcb->control.tsc_offset; - svm->vmcb->control.tsc_offset = svm->vcpu.arch.tsc_offset; - - svm->vmcb->control.virt_ext = nested_vmcb->control.virt_ext; - svm->vmcb->control.int_vector = nested_vmcb->control.int_vector; - svm->vmcb->control.int_state = nested_vmcb->control.int_state; - svm->vmcb->control.event_inj = nested_vmcb->control.event_inj; - svm->vmcb->control.event_inj_err = nested_vmcb->control.event_inj_err; - - svm->vmcb->control.pause_filter_count = - nested_vmcb->control.pause_filter_count; - svm->vmcb->control.pause_filter_thresh = - nested_vmcb->control.pause_filter_thresh; - - kvm_vcpu_unmap(&svm->vcpu, map, true); - - /* Enter Guest-Mode */ - enter_guest_mode(&svm->vcpu); - - /* - * Merge guest and host intercepts - must be called with vcpu in - * guest-mode to take affect here - */ - recalc_intercepts(svm); - - svm->nested.vmcb = vmcb_gpa; - - /* - * If L1 had a pending IRQ/NMI before executing VMRUN, - * which wasn't delivered because it was disallowed (e.g. - * interrupts disabled), L0 needs to evaluate if this pending - * event should cause an exit from L2 to L1 or be delivered - * directly to L2. - * - * Usually this would be handled by the processor noticing an - * IRQ/NMI window request. However, VMRUN can unblock interrupts - * by implicitly setting GIF, so force L0 to perform pending event - * evaluation by requesting a KVM_REQ_EVENT. - */ - enable_gif(svm); - if (unlikely(evaluate_pending_interrupts)) - kvm_make_request(KVM_REQ_EVENT, &svm->vcpu); - - mark_all_dirty(svm->vmcb); -} - -static int nested_svm_vmrun(struct vcpu_svm *svm) -{ - int ret; - struct vmcb *nested_vmcb; - struct vmcb *hsave = svm->nested.hsave; - struct vmcb *vmcb = svm->vmcb; - struct kvm_host_map map; - u64 vmcb_gpa; - - vmcb_gpa = svm->vmcb->save.rax; - - ret = kvm_vcpu_map(&svm->vcpu, gpa_to_gfn(vmcb_gpa), &map); - if (ret == -EINVAL) { - kvm_inject_gp(&svm->vcpu, 0); - return 1; - } else if (ret) { - return kvm_skip_emulated_instruction(&svm->vcpu); - } - - ret = kvm_skip_emulated_instruction(&svm->vcpu); - - nested_vmcb = map.hva; - - if (!nested_vmcb_checks(nested_vmcb)) { - nested_vmcb->control.exit_code = SVM_EXIT_ERR; - nested_vmcb->control.exit_code_hi = 0; - nested_vmcb->control.exit_info_1 = 0; - nested_vmcb->control.exit_info_2 = 0; - - kvm_vcpu_unmap(&svm->vcpu, &map, true); - - return ret; - } - - trace_kvm_nested_vmrun(svm->vmcb->save.rip, vmcb_gpa, - nested_vmcb->save.rip, - nested_vmcb->control.int_ctl, - nested_vmcb->control.event_inj, - nested_vmcb->control.nested_ctl); - - trace_kvm_nested_intercepts(nested_vmcb->control.intercept_cr & 0xffff, - nested_vmcb->control.intercept_cr >> 16, - nested_vmcb->control.intercept_exceptions, - nested_vmcb->control.intercept); - - /* Clear internal status */ - kvm_clear_exception_queue(&svm->vcpu); - kvm_clear_interrupt_queue(&svm->vcpu); - - /* - * Save the old vmcb, so we don't need to pick what we save, but can - * restore everything when a VMEXIT occurs - */ - hsave->save.es = vmcb->save.es; - hsave->save.cs = vmcb->save.cs; - hsave->save.ss = vmcb->save.ss; - hsave->save.ds = vmcb->save.ds; - hsave->save.gdtr = vmcb->save.gdtr; - hsave->save.idtr = vmcb->save.idtr; - hsave->save.efer = svm->vcpu.arch.efer; - hsave->save.cr0 = kvm_read_cr0(&svm->vcpu); - hsave->save.cr4 = svm->vcpu.arch.cr4; - hsave->save.rflags = kvm_get_rflags(&svm->vcpu); - hsave->save.rip = kvm_rip_read(&svm->vcpu); - hsave->save.rsp = vmcb->save.rsp; - hsave->save.rax = vmcb->save.rax; - if (npt_enabled) - hsave->save.cr3 = vmcb->save.cr3; - else - hsave->save.cr3 = kvm_read_cr3(&svm->vcpu); - - copy_vmcb_control_area(hsave, vmcb); - - enter_svm_guest_mode(svm, vmcb_gpa, nested_vmcb, &map); - - if (!nested_svm_vmrun_msrpm(svm)) { - svm->vmcb->control.exit_code = SVM_EXIT_ERR; - svm->vmcb->control.exit_code_hi = 0; - svm->vmcb->control.exit_info_1 = 0; - svm->vmcb->control.exit_info_2 = 0; - - nested_svm_vmexit(svm); - } - - return ret; -} - -static void nested_svm_vmloadsave(struct vmcb *from_vmcb, struct vmcb *to_vmcb) -{ - to_vmcb->save.fs = from_vmcb->save.fs; - to_vmcb->save.gs = from_vmcb->save.gs; - to_vmcb->save.tr = from_vmcb->save.tr; - to_vmcb->save.ldtr = from_vmcb->save.ldtr; - to_vmcb->save.kernel_gs_base = from_vmcb->save.kernel_gs_base; - to_vmcb->save.star = from_vmcb->save.star; - to_vmcb->save.lstar = from_vmcb->save.lstar; - to_vmcb->save.cstar = from_vmcb->save.cstar; - to_vmcb->save.sfmask = from_vmcb->save.sfmask; - to_vmcb->save.sysenter_cs = from_vmcb->save.sysenter_cs; - to_vmcb->save.sysenter_esp = from_vmcb->save.sysenter_esp; - to_vmcb->save.sysenter_eip = from_vmcb->save.sysenter_eip; -} - static int vmload_interception(struct vcpu_svm *svm) { struct vmcb *nested_vmcb; @@ -4565,276 +2703,6 @@ static int mwait_interception(struct vcpu_svm *svm) return nop_interception(svm); } -enum avic_ipi_failure_cause { - AVIC_IPI_FAILURE_INVALID_INT_TYPE, - AVIC_IPI_FAILURE_TARGET_NOT_RUNNING, - AVIC_IPI_FAILURE_INVALID_TARGET, - AVIC_IPI_FAILURE_INVALID_BACKING_PAGE, -}; - -static int avic_incomplete_ipi_interception(struct vcpu_svm *svm) -{ - u32 icrh = svm->vmcb->control.exit_info_1 >> 32; - u32 icrl = svm->vmcb->control.exit_info_1; - u32 id = svm->vmcb->control.exit_info_2 >> 32; - u32 index = svm->vmcb->control.exit_info_2 & 0xFF; - struct kvm_lapic *apic = svm->vcpu.arch.apic; - - trace_kvm_avic_incomplete_ipi(svm->vcpu.vcpu_id, icrh, icrl, id, index); - - switch (id) { - case AVIC_IPI_FAILURE_INVALID_INT_TYPE: - /* - * AVIC hardware handles the generation of - * IPIs when the specified Message Type is Fixed - * (also known as fixed delivery mode) and - * the Trigger Mode is edge-triggered. The hardware - * also supports self and broadcast delivery modes - * specified via the Destination Shorthand(DSH) - * field of the ICRL. Logical and physical APIC ID - * formats are supported. All other IPI types cause - * a #VMEXIT, which needs to emulated. - */ - kvm_lapic_reg_write(apic, APIC_ICR2, icrh); - kvm_lapic_reg_write(apic, APIC_ICR, icrl); - break; - case AVIC_IPI_FAILURE_TARGET_NOT_RUNNING: { - int i; - struct kvm_vcpu *vcpu; - struct kvm *kvm = svm->vcpu.kvm; - struct kvm_lapic *apic = svm->vcpu.arch.apic; - - /* - * At this point, we expect that the AVIC HW has already - * set the appropriate IRR bits on the valid target - * vcpus. So, we just need to kick the appropriate vcpu. - */ - kvm_for_each_vcpu(i, vcpu, kvm) { - bool m = kvm_apic_match_dest(vcpu, apic, - icrl & APIC_SHORT_MASK, - GET_APIC_DEST_FIELD(icrh), - icrl & APIC_DEST_MASK); - - if (m && !avic_vcpu_is_running(vcpu)) - kvm_vcpu_wake_up(vcpu); - } - break; - } - case AVIC_IPI_FAILURE_INVALID_TARGET: - WARN_ONCE(1, "Invalid IPI target: index=%u, vcpu=%d, icr=%#0x:%#0x\n", - index, svm->vcpu.vcpu_id, icrh, icrl); - break; - case AVIC_IPI_FAILURE_INVALID_BACKING_PAGE: - WARN_ONCE(1, "Invalid backing page\n"); - break; - default: - pr_err("Unknown IPI interception\n"); - } - - return 1; -} - -static u32 *avic_get_logical_id_entry(struct kvm_vcpu *vcpu, u32 ldr, bool flat) -{ - struct kvm_svm *kvm_svm = to_kvm_svm(vcpu->kvm); - int index; - u32 *logical_apic_id_table; - int dlid = GET_APIC_LOGICAL_ID(ldr); - - if (!dlid) - return NULL; - - if (flat) { /* flat */ - index = ffs(dlid) - 1; - if (index > 7) - return NULL; - } else { /* cluster */ - int cluster = (dlid & 0xf0) >> 4; - int apic = ffs(dlid & 0x0f) - 1; - - if ((apic < 0) || (apic > 7) || - (cluster >= 0xf)) - return NULL; - index = (cluster << 2) + apic; - } - - logical_apic_id_table = (u32 *) page_address(kvm_svm->avic_logical_id_table_page); - - return &logical_apic_id_table[index]; -} - -static int avic_ldr_write(struct kvm_vcpu *vcpu, u8 g_physical_id, u32 ldr) -{ - bool flat; - u32 *entry, new_entry; - - flat = kvm_lapic_get_reg(vcpu->arch.apic, APIC_DFR) == APIC_DFR_FLAT; - entry = avic_get_logical_id_entry(vcpu, ldr, flat); - if (!entry) - return -EINVAL; - - new_entry = READ_ONCE(*entry); - new_entry &= ~AVIC_LOGICAL_ID_ENTRY_GUEST_PHYSICAL_ID_MASK; - new_entry |= (g_physical_id & AVIC_LOGICAL_ID_ENTRY_GUEST_PHYSICAL_ID_MASK); - new_entry |= AVIC_LOGICAL_ID_ENTRY_VALID_MASK; - WRITE_ONCE(*entry, new_entry); - - return 0; -} - -static void avic_invalidate_logical_id_entry(struct kvm_vcpu *vcpu) -{ - struct vcpu_svm *svm = to_svm(vcpu); - bool flat = svm->dfr_reg == APIC_DFR_FLAT; - u32 *entry = avic_get_logical_id_entry(vcpu, svm->ldr_reg, flat); - - if (entry) - clear_bit(AVIC_LOGICAL_ID_ENTRY_VALID_BIT, (unsigned long *)entry); -} - -static int avic_handle_ldr_update(struct kvm_vcpu *vcpu) -{ - int ret = 0; - struct vcpu_svm *svm = to_svm(vcpu); - u32 ldr = kvm_lapic_get_reg(vcpu->arch.apic, APIC_LDR); - u32 id = kvm_xapic_id(vcpu->arch.apic); - - if (ldr == svm->ldr_reg) - return 0; - - avic_invalidate_logical_id_entry(vcpu); - - if (ldr) - ret = avic_ldr_write(vcpu, id, ldr); - - if (!ret) - svm->ldr_reg = ldr; - - return ret; -} - -static int avic_handle_apic_id_update(struct kvm_vcpu *vcpu) -{ - u64 *old, *new; - struct vcpu_svm *svm = to_svm(vcpu); - u32 id = kvm_xapic_id(vcpu->arch.apic); - - if (vcpu->vcpu_id == id) - return 0; - - old = avic_get_physical_id_entry(vcpu, vcpu->vcpu_id); - new = avic_get_physical_id_entry(vcpu, id); - if (!new || !old) - return 1; - - /* We need to move physical_id_entry to new offset */ - *new = *old; - *old = 0ULL; - to_svm(vcpu)->avic_physical_id_cache = new; - - /* - * Also update the guest physical APIC ID in the logical - * APIC ID table entry if already setup the LDR. - */ - if (svm->ldr_reg) - avic_handle_ldr_update(vcpu); - - return 0; -} - -static void avic_handle_dfr_update(struct kvm_vcpu *vcpu) -{ - struct vcpu_svm *svm = to_svm(vcpu); - u32 dfr = kvm_lapic_get_reg(vcpu->arch.apic, APIC_DFR); - - if (svm->dfr_reg == dfr) - return; - - avic_invalidate_logical_id_entry(vcpu); - svm->dfr_reg = dfr; -} - -static int avic_unaccel_trap_write(struct vcpu_svm *svm) -{ - struct kvm_lapic *apic = svm->vcpu.arch.apic; - u32 offset = svm->vmcb->control.exit_info_1 & - AVIC_UNACCEL_ACCESS_OFFSET_MASK; - - switch (offset) { - case APIC_ID: - if (avic_handle_apic_id_update(&svm->vcpu)) - return 0; - break; - case APIC_LDR: - if (avic_handle_ldr_update(&svm->vcpu)) - return 0; - break; - case APIC_DFR: - avic_handle_dfr_update(&svm->vcpu); - break; - default: - break; - } - - kvm_lapic_reg_write(apic, offset, kvm_lapic_get_reg(apic, offset)); - - return 1; -} - -static bool is_avic_unaccelerated_access_trap(u32 offset) -{ - bool ret = false; - - switch (offset) { - case APIC_ID: - case APIC_EOI: - case APIC_RRR: - case APIC_LDR: - case APIC_DFR: - case APIC_SPIV: - case APIC_ESR: - case APIC_ICR: - case APIC_LVTT: - case APIC_LVTTHMR: - case APIC_LVTPC: - case APIC_LVT0: - case APIC_LVT1: - case APIC_LVTERR: - case APIC_TMICT: - case APIC_TDCR: - ret = true; - break; - default: - break; - } - return ret; -} - -static int avic_unaccelerated_access_interception(struct vcpu_svm *svm) -{ - int ret = 0; - u32 offset = svm->vmcb->control.exit_info_1 & - AVIC_UNACCEL_ACCESS_OFFSET_MASK; - u32 vector = svm->vmcb->control.exit_info_2 & - AVIC_UNACCEL_ACCESS_VECTOR_MASK; - bool write = (svm->vmcb->control.exit_info_1 >> 32) & - AVIC_UNACCEL_ACCESS_WRITE_MASK; - bool trap = is_avic_unaccelerated_access_trap(offset); - - trace_kvm_avic_unaccelerated_access(svm->vcpu.vcpu_id, offset, - trap, write, vector); - if (trap) { - /* Handling Trap */ - WARN_ONCE(!write, "svm: Handling trap read.\n"); - ret = avic_unaccel_trap_write(svm); - } else { - /* Handling Fault */ - ret = kvm_emulate_instruction(&svm->vcpu, 0); - } - - return ret; -} - static int (*const svm_exit_handlers[])(struct vcpu_svm *svm) = { [SVM_EXIT_READ_CR0] = cr_interception, [SVM_EXIT_READ_CR3] = cr_interception, @@ -5125,30 +2993,6 @@ static void reload_tss(struct kvm_vcpu *vcpu) load_TR_desc(); } -static void pre_sev_run(struct vcpu_svm *svm, int cpu) -{ - struct svm_cpu_data *sd = per_cpu(svm_data, cpu); - int asid = sev_get_asid(svm->vcpu.kvm); - - /* Assign the asid allocated with this SEV guest */ - svm->vmcb->control.asid = asid; - - /* - * Flush guest TLB: - * - * 1) when different VMCB for the same ASID is to be run on the same host CPU. - * 2) or this VMCB was executed on different host CPU in previous VMRUNs. - */ - if (sd->sev_vmcbs[asid] == svm->vmcb && - svm->last_cpu == cpu) - return; - - svm->last_cpu = cpu; - sd->sev_vmcbs[asid] = svm->vmcb; - svm->vmcb->control.tlb_ctl = TLB_CONTROL_FLUSH_ASID; - mark_dirty(svm->vmcb, VMCB_ASID); -} - static void pre_svm_run(struct vcpu_svm *svm) { int cpu = raw_smp_processor_id(); @@ -5186,11 +3030,6 @@ static void svm_set_irq(struct kvm_vcpu *vcpu) SVM_EVTINJ_VALID | SVM_EVTINJ_TYPE_INTR; } -static inline bool svm_nested_virtualize_tpr(struct kvm_vcpu *vcpu) -{ - return is_guest_mode(vcpu) && (vcpu->arch.hflags & HF_VINTR_MASK); -} - static void update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr) { struct vcpu_svm *svm = to_svm(vcpu); @@ -5207,324 +3046,6 @@ static void update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr) set_cr_intercept(svm, INTERCEPT_CR8_WRITE); } -static void svm_set_virtual_apic_mode(struct kvm_vcpu *vcpu) -{ - return; -} - -static void svm_hwapic_irr_update(struct kvm_vcpu *vcpu, int max_irr) -{ -} - -static void svm_hwapic_isr_update(struct kvm_vcpu *vcpu, int max_isr) -{ -} - -static void svm_toggle_avic_for_irq_window(struct kvm_vcpu *vcpu, bool activate) -{ - if (!avic || !lapic_in_kernel(vcpu)) - return; - - srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); - kvm_request_apicv_update(vcpu->kvm, activate, - APICV_INHIBIT_REASON_IRQWIN); - vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); -} - -static int svm_set_pi_irte_mode(struct kvm_vcpu *vcpu, bool activate) -{ - int ret = 0; - unsigned long flags; - struct amd_svm_iommu_ir *ir; - struct vcpu_svm *svm = to_svm(vcpu); - - if (!kvm_arch_has_assigned_device(vcpu->kvm)) - return 0; - - /* - * Here, we go through the per-vcpu ir_list to update all existing - * interrupt remapping table entry targeting this vcpu. - */ - spin_lock_irqsave(&svm->ir_list_lock, flags); - - if (list_empty(&svm->ir_list)) - goto out; - - list_for_each_entry(ir, &svm->ir_list, node) { - if (activate) - ret = amd_iommu_activate_guest_mode(ir->data); - else - ret = amd_iommu_deactivate_guest_mode(ir->data); - if (ret) - break; - } -out: - spin_unlock_irqrestore(&svm->ir_list_lock, flags); - return ret; -} - -static void svm_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu) -{ - struct vcpu_svm *svm = to_svm(vcpu); - struct vmcb *vmcb = svm->vmcb; - bool activated = kvm_vcpu_apicv_active(vcpu); - - if (!avic) - return; - - if (activated) { - /** - * During AVIC temporary deactivation, guest could update - * APIC ID, DFR and LDR registers, which would not be trapped - * by avic_unaccelerated_access_interception(). In this case, - * we need to check and update the AVIC logical APIC ID table - * accordingly before re-activating. - */ - avic_post_state_restore(vcpu); - vmcb->control.int_ctl |= AVIC_ENABLE_MASK; - } else { - vmcb->control.int_ctl &= ~AVIC_ENABLE_MASK; - } - mark_dirty(vmcb, VMCB_AVIC); - - svm_set_pi_irte_mode(vcpu, activated); -} - -static void svm_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap) -{ - return; -} - -static int svm_deliver_avic_intr(struct kvm_vcpu *vcpu, int vec) -{ - if (!vcpu->arch.apicv_active) - return -1; - - kvm_lapic_set_irr(vec, vcpu->arch.apic); - smp_mb__after_atomic(); - - if (avic_vcpu_is_running(vcpu)) { - int cpuid = vcpu->cpu; - - if (cpuid != get_cpu()) - wrmsrl(SVM_AVIC_DOORBELL, kvm_cpu_get_apicid(cpuid)); - put_cpu(); - } else - kvm_vcpu_wake_up(vcpu); - - return 0; -} - -static bool svm_dy_apicv_has_pending_interrupt(struct kvm_vcpu *vcpu) -{ - return false; -} - -static void svm_ir_list_del(struct vcpu_svm *svm, struct amd_iommu_pi_data *pi) -{ - unsigned long flags; - struct amd_svm_iommu_ir *cur; - - spin_lock_irqsave(&svm->ir_list_lock, flags); - list_for_each_entry(cur, &svm->ir_list, node) { - if (cur->data != pi->ir_data) - continue; - list_del(&cur->node); - kfree(cur); - break; - } - spin_unlock_irqrestore(&svm->ir_list_lock, flags); -} - -static int svm_ir_list_add(struct vcpu_svm *svm, struct amd_iommu_pi_data *pi) -{ - int ret = 0; - unsigned long flags; - struct amd_svm_iommu_ir *ir; - - /** - * In some cases, the existing irte is updaed and re-set, - * so we need to check here if it's already been * added - * to the ir_list. - */ - if (pi->ir_data && (pi->prev_ga_tag != 0)) { - struct kvm *kvm = svm->vcpu.kvm; - u32 vcpu_id = AVIC_GATAG_TO_VCPUID(pi->prev_ga_tag); - struct kvm_vcpu *prev_vcpu = kvm_get_vcpu_by_id(kvm, vcpu_id); - struct vcpu_svm *prev_svm; - - if (!prev_vcpu) { - ret = -EINVAL; - goto out; - } - - prev_svm = to_svm(prev_vcpu); - svm_ir_list_del(prev_svm, pi); - } - - /** - * Allocating new amd_iommu_pi_data, which will get - * add to the per-vcpu ir_list. - */ - ir = kzalloc(sizeof(struct amd_svm_iommu_ir), GFP_KERNEL_ACCOUNT); - if (!ir) { - ret = -ENOMEM; - goto out; - } - ir->data = pi->ir_data; - - spin_lock_irqsave(&svm->ir_list_lock, flags); - list_add(&ir->node, &svm->ir_list); - spin_unlock_irqrestore(&svm->ir_list_lock, flags); -out: - return ret; -} - -/** - * Note: - * The HW cannot support posting multicast/broadcast - * interrupts to a vCPU. So, we still use legacy interrupt - * remapping for these kind of interrupts. - * - * For lowest-priority interrupts, we only support - * those with single CPU as the destination, e.g. user - * configures the interrupts via /proc/irq or uses - * irqbalance to make the interrupts single-CPU. - */ -static int -get_pi_vcpu_info(struct kvm *kvm, struct kvm_kernel_irq_routing_entry *e, - struct vcpu_data *vcpu_info, struct vcpu_svm **svm) -{ - struct kvm_lapic_irq irq; - struct kvm_vcpu *vcpu = NULL; - - kvm_set_msi_irq(kvm, e, &irq); - - if (!kvm_intr_is_single_vcpu(kvm, &irq, &vcpu) || - !kvm_irq_is_postable(&irq)) { - pr_debug("SVM: %s: use legacy intr remap mode for irq %u\n", - __func__, irq.vector); - return -1; - } - - pr_debug("SVM: %s: use GA mode for irq %u\n", __func__, - irq.vector); - *svm = to_svm(vcpu); - vcpu_info->pi_desc_addr = __sme_set(page_to_phys((*svm)->avic_backing_page)); - vcpu_info->vector = irq.vector; - - return 0; -} - -/* - * svm_update_pi_irte - set IRTE for Posted-Interrupts - * - * @kvm: kvm - * @host_irq: host irq of the interrupt - * @guest_irq: gsi of the interrupt - * @set: set or unset PI - * returns 0 on success, < 0 on failure - */ -static int svm_update_pi_irte(struct kvm *kvm, unsigned int host_irq, - uint32_t guest_irq, bool set) -{ - struct kvm_kernel_irq_routing_entry *e; - struct kvm_irq_routing_table *irq_rt; - int idx, ret = -EINVAL; - - if (!kvm_arch_has_assigned_device(kvm) || - !irq_remapping_cap(IRQ_POSTING_CAP)) - return 0; - - pr_debug("SVM: %s: host_irq=%#x, guest_irq=%#x, set=%#x\n", - __func__, host_irq, guest_irq, set); - - idx = srcu_read_lock(&kvm->irq_srcu); - irq_rt = srcu_dereference(kvm->irq_routing, &kvm->irq_srcu); - WARN_ON(guest_irq >= irq_rt->nr_rt_entries); - - hlist_for_each_entry(e, &irq_rt->map[guest_irq], link) { - struct vcpu_data vcpu_info; - struct vcpu_svm *svm = NULL; - - if (e->type != KVM_IRQ_ROUTING_MSI) - continue; - - /** - * Here, we setup with legacy mode in the following cases: - * 1. When cannot target interrupt to a specific vcpu. - * 2. Unsetting posted interrupt. - * 3. APIC virtialization is disabled for the vcpu. - * 4. IRQ has incompatible delivery mode (SMI, INIT, etc) - */ - if (!get_pi_vcpu_info(kvm, e, &vcpu_info, &svm) && set && - kvm_vcpu_apicv_active(&svm->vcpu)) { - struct amd_iommu_pi_data pi; - - /* Try to enable guest_mode in IRTE */ - pi.base = __sme_set(page_to_phys(svm->avic_backing_page) & - AVIC_HPA_MASK); - pi.ga_tag = AVIC_GATAG(to_kvm_svm(kvm)->avic_vm_id, - svm->vcpu.vcpu_id); - pi.is_guest_mode = true; - pi.vcpu_data = &vcpu_info; - ret = irq_set_vcpu_affinity(host_irq, &pi); - - /** - * Here, we successfully setting up vcpu affinity in - * IOMMU guest mode. Now, we need to store the posted - * interrupt information in a per-vcpu ir_list so that - * we can reference to them directly when we update vcpu - * scheduling information in IOMMU irte. - */ - if (!ret && pi.is_guest_mode) - svm_ir_list_add(svm, &pi); - } else { - /* Use legacy mode in IRTE */ - struct amd_iommu_pi_data pi; - - /** - * Here, pi is used to: - * - Tell IOMMU to use legacy mode for this interrupt. - * - Retrieve ga_tag of prior interrupt remapping data. - */ - pi.is_guest_mode = false; - ret = irq_set_vcpu_affinity(host_irq, &pi); - - /** - * Check if the posted interrupt was previously - * setup with the guest_mode by checking if the ga_tag - * was cached. If so, we need to clean up the per-vcpu - * ir_list. - */ - if (!ret && pi.prev_ga_tag) { - int id = AVIC_GATAG_TO_VCPUID(pi.prev_ga_tag); - struct kvm_vcpu *vcpu; - - vcpu = kvm_get_vcpu_by_id(kvm, id); - if (vcpu) - svm_ir_list_del(to_svm(vcpu), &pi); - } - } - - if (!ret && svm) { - trace_kvm_pi_irte_update(host_irq, svm->vcpu.vcpu_id, - e->gsi, vcpu_info.vector, - vcpu_info.pi_desc_addr, set); - } - - if (ret < 0) { - pr_err("%s: failed to update PI IRTE\n", __func__); - goto out; - } - } - - ret = 0; -out: - srcu_read_unlock(&kvm->irq_srcu, idx); - return ret; -} - static int svm_nmi_allowed(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); @@ -5632,7 +3153,7 @@ static int svm_set_identity_map_addr(struct kvm *kvm, u64 ident_addr) return 0; } -static void svm_flush_tlb(struct kvm_vcpu *vcpu, bool invalidate_gpa) +void svm_flush_tlb(struct kvm_vcpu *vcpu, bool invalidate_gpa) { struct vcpu_svm *svm = to_svm(vcpu); @@ -5755,6 +3276,8 @@ static void svm_cancel_injection(struct kvm_vcpu *vcpu) svm_complete_interrupts(svm); } +bool __svm_vcpu_run(unsigned long vmcb_pa, unsigned long *regs); + static void svm_vcpu_run(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); @@ -5809,95 +3332,7 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu) local_irq_enable(); - asm volatile ( - "push %%" _ASM_BP "; \n\t" - "mov %c[rbx](%[svm]), %%" _ASM_BX " \n\t" - "mov %c[rcx](%[svm]), %%" _ASM_CX " \n\t" - "mov %c[rdx](%[svm]), %%" _ASM_DX " \n\t" - "mov %c[rsi](%[svm]), %%" _ASM_SI " \n\t" - "mov %c[rdi](%[svm]), %%" _ASM_DI " \n\t" - "mov %c[rbp](%[svm]), %%" _ASM_BP " \n\t" -#ifdef CONFIG_X86_64 - "mov %c[r8](%[svm]), %%r8 \n\t" - "mov %c[r9](%[svm]), %%r9 \n\t" - "mov %c[r10](%[svm]), %%r10 \n\t" - "mov %c[r11](%[svm]), %%r11 \n\t" - "mov %c[r12](%[svm]), %%r12 \n\t" - "mov %c[r13](%[svm]), %%r13 \n\t" - "mov %c[r14](%[svm]), %%r14 \n\t" - "mov %c[r15](%[svm]), %%r15 \n\t" -#endif - - /* Enter guest mode */ - "push %%" _ASM_AX " \n\t" - "mov %c[vmcb](%[svm]), %%" _ASM_AX " \n\t" - __ex("vmload %%" _ASM_AX) "\n\t" - __ex("vmrun %%" _ASM_AX) "\n\t" - __ex("vmsave %%" _ASM_AX) "\n\t" - "pop %%" _ASM_AX " \n\t" - - /* Save guest registers, load host registers */ - "mov %%" _ASM_BX ", %c[rbx](%[svm]) \n\t" - "mov %%" _ASM_CX ", %c[rcx](%[svm]) \n\t" - "mov %%" _ASM_DX ", %c[rdx](%[svm]) \n\t" - "mov %%" _ASM_SI ", %c[rsi](%[svm]) \n\t" - "mov %%" _ASM_DI ", %c[rdi](%[svm]) \n\t" - "mov %%" _ASM_BP ", %c[rbp](%[svm]) \n\t" -#ifdef CONFIG_X86_64 - "mov %%r8, %c[r8](%[svm]) \n\t" - "mov %%r9, %c[r9](%[svm]) \n\t" - "mov %%r10, %c[r10](%[svm]) \n\t" - "mov %%r11, %c[r11](%[svm]) \n\t" - "mov %%r12, %c[r12](%[svm]) \n\t" - "mov %%r13, %c[r13](%[svm]) \n\t" - "mov %%r14, %c[r14](%[svm]) \n\t" - "mov %%r15, %c[r15](%[svm]) \n\t" - /* - * Clear host registers marked as clobbered to prevent - * speculative use. - */ - "xor %%r8d, %%r8d \n\t" - "xor %%r9d, %%r9d \n\t" - "xor %%r10d, %%r10d \n\t" - "xor %%r11d, %%r11d \n\t" - "xor %%r12d, %%r12d \n\t" - "xor %%r13d, %%r13d \n\t" - "xor %%r14d, %%r14d \n\t" - "xor %%r15d, %%r15d \n\t" -#endif - "xor %%ebx, %%ebx \n\t" - "xor %%ecx, %%ecx \n\t" - "xor %%edx, %%edx \n\t" - "xor %%esi, %%esi \n\t" - "xor %%edi, %%edi \n\t" - "pop %%" _ASM_BP - : - : [svm]"a"(svm), - [vmcb]"i"(offsetof(struct vcpu_svm, vmcb_pa)), - [rbx]"i"(offsetof(struct vcpu_svm, vcpu.arch.regs[VCPU_REGS_RBX])), - [rcx]"i"(offsetof(struct vcpu_svm, vcpu.arch.regs[VCPU_REGS_RCX])), - [rdx]"i"(offsetof(struct vcpu_svm, vcpu.arch.regs[VCPU_REGS_RDX])), - [rsi]"i"(offsetof(struct vcpu_svm, vcpu.arch.regs[VCPU_REGS_RSI])), - [rdi]"i"(offsetof(struct vcpu_svm, vcpu.arch.regs[VCPU_REGS_RDI])), - [rbp]"i"(offsetof(struct vcpu_svm, vcpu.arch.regs[VCPU_REGS_RBP])) -#ifdef CONFIG_X86_64 - , [r8]"i"(offsetof(struct vcpu_svm, vcpu.arch.regs[VCPU_REGS_R8])), - [r9]"i"(offsetof(struct vcpu_svm, vcpu.arch.regs[VCPU_REGS_R9])), - [r10]"i"(offsetof(struct vcpu_svm, vcpu.arch.regs[VCPU_REGS_R10])), - [r11]"i"(offsetof(struct vcpu_svm, vcpu.arch.regs[VCPU_REGS_R11])), - [r12]"i"(offsetof(struct vcpu_svm, vcpu.arch.regs[VCPU_REGS_R12])), - [r13]"i"(offsetof(struct vcpu_svm, vcpu.arch.regs[VCPU_REGS_R13])), - [r14]"i"(offsetof(struct vcpu_svm, vcpu.arch.regs[VCPU_REGS_R14])), - [r15]"i"(offsetof(struct vcpu_svm, vcpu.arch.regs[VCPU_REGS_R15])) -#endif - : "cc", "memory" -#ifdef CONFIG_X86_64 - , "rbx", "rcx", "rdx", "rsi", "rdi" - , "r8", "r9", "r10", "r11" , "r12", "r13", "r14", "r15" -#else - , "ebx", "ecx", "edx", "esi", "edi" -#endif - ); + __svm_vcpu_run(svm->vmcb_pa, (unsigned long *)&svm->vcpu.arch.regs); /* Eliminate branch target predictions from guest mode */ vmexit_fill_RSB(); @@ -6292,14 +3727,6 @@ static void svm_sched_in(struct kvm_vcpu *vcpu, int cpu) shrink_ple_window(vcpu); } -static inline void avic_post_state_restore(struct kvm_vcpu *vcpu) -{ - if (avic_handle_apic_id_update(vcpu) != 0) - return; - avic_handle_dfr_update(vcpu); - avic_handle_ldr_update(vcpu); -} - static void svm_setup_mce(struct kvm_vcpu *vcpu) { /* [63:9] are reserved. */ @@ -6380,900 +3807,6 @@ static int enable_smi_window(struct kvm_vcpu *vcpu) return 0; } -static int sev_flush_asids(void) -{ - int ret, error; - - /* - * DEACTIVATE will clear the WBINVD indicator causing DF_FLUSH to fail, - * so it must be guarded. - */ - down_write(&sev_deactivate_lock); - - wbinvd_on_all_cpus(); - ret = sev_guest_df_flush(&error); - - up_write(&sev_deactivate_lock); - - if (ret) - pr_err("SEV: DF_FLUSH failed, ret=%d, error=%#x\n", ret, error); - - return ret; -} - -/* Must be called with the sev_bitmap_lock held */ -static bool __sev_recycle_asids(void) -{ - int pos; - - /* Check if there are any ASIDs to reclaim before performing a flush */ - pos = find_next_bit(sev_reclaim_asid_bitmap, - max_sev_asid, min_sev_asid - 1); - if (pos >= max_sev_asid) - return false; - - if (sev_flush_asids()) - return false; - - bitmap_xor(sev_asid_bitmap, sev_asid_bitmap, sev_reclaim_asid_bitmap, - max_sev_asid); - bitmap_zero(sev_reclaim_asid_bitmap, max_sev_asid); - - return true; -} - -static int sev_asid_new(void) -{ - bool retry = true; - int pos; - - mutex_lock(&sev_bitmap_lock); - - /* - * SEV-enabled guest must use asid from min_sev_asid to max_sev_asid. - */ -again: - pos = find_next_zero_bit(sev_asid_bitmap, max_sev_asid, min_sev_asid - 1); - if (pos >= max_sev_asid) { - if (retry && __sev_recycle_asids()) { - retry = false; - goto again; - } - mutex_unlock(&sev_bitmap_lock); - return -EBUSY; - } - - __set_bit(pos, sev_asid_bitmap); - - mutex_unlock(&sev_bitmap_lock); - - return pos + 1; -} - -static int sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp) -{ - struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; - int asid, ret; - - ret = -EBUSY; - if (unlikely(sev->active)) - return ret; - - asid = sev_asid_new(); - if (asid < 0) - return ret; - - ret = sev_platform_init(&argp->error); - if (ret) - goto e_free; - - sev->active = true; - sev->asid = asid; - INIT_LIST_HEAD(&sev->regions_list); - - return 0; - -e_free: - sev_asid_free(asid); - return ret; -} - -static int sev_bind_asid(struct kvm *kvm, unsigned int handle, int *error) -{ - struct sev_data_activate *data; - int asid = sev_get_asid(kvm); - int ret; - - data = kzalloc(sizeof(*data), GFP_KERNEL_ACCOUNT); - if (!data) - return -ENOMEM; - - /* activate ASID on the given handle */ - data->handle = handle; - data->asid = asid; - ret = sev_guest_activate(data, error); - kfree(data); - - return ret; -} - -static int __sev_issue_cmd(int fd, int id, void *data, int *error) -{ - struct fd f; - int ret; - - f = fdget(fd); - if (!f.file) - return -EBADF; - - ret = sev_issue_cmd_external_user(f.file, id, data, error); - - fdput(f); - return ret; -} - -static int sev_issue_cmd(struct kvm *kvm, int id, void *data, int *error) -{ - struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; - - return __sev_issue_cmd(sev->fd, id, data, error); -} - -static int sev_launch_start(struct kvm *kvm, struct kvm_sev_cmd *argp) -{ - struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; - struct sev_data_launch_start *start; - struct kvm_sev_launch_start params; - void *dh_blob, *session_blob; - int *error = &argp->error; - int ret; - - if (!sev_guest(kvm)) - return -ENOTTY; - - if (copy_from_user(¶ms, (void __user *)(uintptr_t)argp->data, sizeof(params))) - return -EFAULT; - - start = kzalloc(sizeof(*start), GFP_KERNEL_ACCOUNT); - if (!start) - return -ENOMEM; - - dh_blob = NULL; - if (params.dh_uaddr) { - dh_blob = psp_copy_user_blob(params.dh_uaddr, params.dh_len); - if (IS_ERR(dh_blob)) { - ret = PTR_ERR(dh_blob); - goto e_free; - } - - start->dh_cert_address = __sme_set(__pa(dh_blob)); - start->dh_cert_len = params.dh_len; - } - - session_blob = NULL; - if (params.session_uaddr) { - session_blob = psp_copy_user_blob(params.session_uaddr, params.session_len); - if (IS_ERR(session_blob)) { - ret = PTR_ERR(session_blob); - goto e_free_dh; - } - - start->session_address = __sme_set(__pa(session_blob)); - start->session_len = params.session_len; - } - - start->handle = params.handle; - start->policy = params.policy; - - /* create memory encryption context */ - ret = __sev_issue_cmd(argp->sev_fd, SEV_CMD_LAUNCH_START, start, error); - if (ret) - goto e_free_session; - - /* Bind ASID to this guest */ - ret = sev_bind_asid(kvm, start->handle, error); - if (ret) - goto e_free_session; - - /* return handle to userspace */ - params.handle = start->handle; - if (copy_to_user((void __user *)(uintptr_t)argp->data, ¶ms, sizeof(params))) { - sev_unbind_asid(kvm, start->handle); - ret = -EFAULT; - goto e_free_session; - } - - sev->handle = start->handle; - sev->fd = argp->sev_fd; - -e_free_session: - kfree(session_blob); -e_free_dh: - kfree(dh_blob); -e_free: - kfree(start); - return ret; -} - -static unsigned long get_num_contig_pages(unsigned long idx, - struct page **inpages, unsigned long npages) -{ - unsigned long paddr, next_paddr; - unsigned long i = idx + 1, pages = 1; - - /* find the number of contiguous pages starting from idx */ - paddr = __sme_page_pa(inpages[idx]); - while (i < npages) { - next_paddr = __sme_page_pa(inpages[i++]); - if ((paddr + PAGE_SIZE) == next_paddr) { - pages++; - paddr = next_paddr; - continue; - } - break; - } - - return pages; -} - -static int sev_launch_update_data(struct kvm *kvm, struct kvm_sev_cmd *argp) -{ - unsigned long vaddr, vaddr_end, next_vaddr, npages, pages, size, i; - struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; - struct kvm_sev_launch_update_data params; - struct sev_data_launch_update_data *data; - struct page **inpages; - int ret; - - if (!sev_guest(kvm)) - return -ENOTTY; - - if (copy_from_user(¶ms, (void __user *)(uintptr_t)argp->data, sizeof(params))) - return -EFAULT; - - data = kzalloc(sizeof(*data), GFP_KERNEL_ACCOUNT); - if (!data) - return -ENOMEM; - - vaddr = params.uaddr; - size = params.len; - vaddr_end = vaddr + size; - - /* Lock the user memory. */ - inpages = sev_pin_memory(kvm, vaddr, size, &npages, 1); - if (!inpages) { - ret = -ENOMEM; - goto e_free; - } - - /* - * The LAUNCH_UPDATE command will perform in-place encryption of the - * memory content (i.e it will write the same memory region with C=1). - * It's possible that the cache may contain the data with C=0, i.e., - * unencrypted so invalidate it first. - */ - sev_clflush_pages(inpages, npages); - - for (i = 0; vaddr < vaddr_end; vaddr = next_vaddr, i += pages) { - int offset, len; - - /* - * If the user buffer is not page-aligned, calculate the offset - * within the page. - */ - offset = vaddr & (PAGE_SIZE - 1); - - /* Calculate the number of pages that can be encrypted in one go. */ - pages = get_num_contig_pages(i, inpages, npages); - - len = min_t(size_t, ((pages * PAGE_SIZE) - offset), size); - - data->handle = sev->handle; - data->len = len; - data->address = __sme_page_pa(inpages[i]) + offset; - ret = sev_issue_cmd(kvm, SEV_CMD_LAUNCH_UPDATE_DATA, data, &argp->error); - if (ret) - goto e_unpin; - - size -= len; - next_vaddr = vaddr + len; - } - -e_unpin: - /* content of memory is updated, mark pages dirty */ - for (i = 0; i < npages; i++) { - set_page_dirty_lock(inpages[i]); - mark_page_accessed(inpages[i]); - } - /* unlock the user pages */ - sev_unpin_memory(kvm, inpages, npages); -e_free: - kfree(data); - return ret; -} - -static int sev_launch_measure(struct kvm *kvm, struct kvm_sev_cmd *argp) -{ - void __user *measure = (void __user *)(uintptr_t)argp->data; - struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; - struct sev_data_launch_measure *data; - struct kvm_sev_launch_measure params; - void __user *p = NULL; - void *blob = NULL; - int ret; - - if (!sev_guest(kvm)) - return -ENOTTY; - - if (copy_from_user(¶ms, measure, sizeof(params))) - return -EFAULT; - - data = kzalloc(sizeof(*data), GFP_KERNEL_ACCOUNT); - if (!data) - return -ENOMEM; - - /* User wants to query the blob length */ - if (!params.len) - goto cmd; - - p = (void __user *)(uintptr_t)params.uaddr; - if (p) { - if (params.len > SEV_FW_BLOB_MAX_SIZE) { - ret = -EINVAL; - goto e_free; - } - - ret = -ENOMEM; - blob = kmalloc(params.len, GFP_KERNEL); - if (!blob) - goto e_free; - - data->address = __psp_pa(blob); - data->len = params.len; - } - -cmd: - data->handle = sev->handle; - ret = sev_issue_cmd(kvm, SEV_CMD_LAUNCH_MEASURE, data, &argp->error); - - /* - * If we query the session length, FW responded with expected data. - */ - if (!params.len) - goto done; - - if (ret) - goto e_free_blob; - - if (blob) { - if (copy_to_user(p, blob, params.len)) - ret = -EFAULT; - } - -done: - params.len = data->len; - if (copy_to_user(measure, ¶ms, sizeof(params))) - ret = -EFAULT; -e_free_blob: - kfree(blob); -e_free: - kfree(data); - return ret; -} - -static int sev_launch_finish(struct kvm *kvm, struct kvm_sev_cmd *argp) -{ - struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; - struct sev_data_launch_finish *data; - int ret; - - if (!sev_guest(kvm)) - return -ENOTTY; - - data = kzalloc(sizeof(*data), GFP_KERNEL_ACCOUNT); - if (!data) - return -ENOMEM; - - data->handle = sev->handle; - ret = sev_issue_cmd(kvm, SEV_CMD_LAUNCH_FINISH, data, &argp->error); - - kfree(data); - return ret; -} - -static int sev_guest_status(struct kvm *kvm, struct kvm_sev_cmd *argp) -{ - struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; - struct kvm_sev_guest_status params; - struct sev_data_guest_status *data; - int ret; - - if (!sev_guest(kvm)) - return -ENOTTY; - - data = kzalloc(sizeof(*data), GFP_KERNEL_ACCOUNT); - if (!data) - return -ENOMEM; - - data->handle = sev->handle; - ret = sev_issue_cmd(kvm, SEV_CMD_GUEST_STATUS, data, &argp->error); - if (ret) - goto e_free; - - params.policy = data->policy; - params.state = data->state; - params.handle = data->handle; - - if (copy_to_user((void __user *)(uintptr_t)argp->data, ¶ms, sizeof(params))) - ret = -EFAULT; -e_free: - kfree(data); - return ret; -} - -static int __sev_issue_dbg_cmd(struct kvm *kvm, unsigned long src, - unsigned long dst, int size, - int *error, bool enc) -{ - struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; - struct sev_data_dbg *data; - int ret; - - data = kzalloc(sizeof(*data), GFP_KERNEL_ACCOUNT); - if (!data) - return -ENOMEM; - - data->handle = sev->handle; - data->dst_addr = dst; - data->src_addr = src; - data->len = size; - - ret = sev_issue_cmd(kvm, - enc ? SEV_CMD_DBG_ENCRYPT : SEV_CMD_DBG_DECRYPT, - data, error); - kfree(data); - return ret; -} - -static int __sev_dbg_decrypt(struct kvm *kvm, unsigned long src_paddr, - unsigned long dst_paddr, int sz, int *err) -{ - int offset; - - /* - * Its safe to read more than we are asked, caller should ensure that - * destination has enough space. - */ - src_paddr = round_down(src_paddr, 16); - offset = src_paddr & 15; - sz = round_up(sz + offset, 16); - - return __sev_issue_dbg_cmd(kvm, src_paddr, dst_paddr, sz, err, false); -} - -static int __sev_dbg_decrypt_user(struct kvm *kvm, unsigned long paddr, - unsigned long __user dst_uaddr, - unsigned long dst_paddr, - int size, int *err) -{ - struct page *tpage = NULL; - int ret, offset; - - /* if inputs are not 16-byte then use intermediate buffer */ - if (!IS_ALIGNED(dst_paddr, 16) || - !IS_ALIGNED(paddr, 16) || - !IS_ALIGNED(size, 16)) { - tpage = (void *)alloc_page(GFP_KERNEL); - if (!tpage) - return -ENOMEM; - - dst_paddr = __sme_page_pa(tpage); - } - - ret = __sev_dbg_decrypt(kvm, paddr, dst_paddr, size, err); - if (ret) - goto e_free; - - if (tpage) { - offset = paddr & 15; - if (copy_to_user((void __user *)(uintptr_t)dst_uaddr, - page_address(tpage) + offset, size)) - ret = -EFAULT; - } - -e_free: - if (tpage) - __free_page(tpage); - - return ret; -} - -static int __sev_dbg_encrypt_user(struct kvm *kvm, unsigned long paddr, - unsigned long __user vaddr, - unsigned long dst_paddr, - unsigned long __user dst_vaddr, - int size, int *error) -{ - struct page *src_tpage = NULL; - struct page *dst_tpage = NULL; - int ret, len = size; - - /* If source buffer is not aligned then use an intermediate buffer */ - if (!IS_ALIGNED(vaddr, 16)) { - src_tpage = alloc_page(GFP_KERNEL); - if (!src_tpage) - return -ENOMEM; - - if (copy_from_user(page_address(src_tpage), - (void __user *)(uintptr_t)vaddr, size)) { - __free_page(src_tpage); - return -EFAULT; - } - - paddr = __sme_page_pa(src_tpage); - } - - /* - * If destination buffer or length is not aligned then do read-modify-write: - * - decrypt destination in an intermediate buffer - * - copy the source buffer in an intermediate buffer - * - use the intermediate buffer as source buffer - */ - if (!IS_ALIGNED(dst_vaddr, 16) || !IS_ALIGNED(size, 16)) { - int dst_offset; - - dst_tpage = alloc_page(GFP_KERNEL); - if (!dst_tpage) { - ret = -ENOMEM; - goto e_free; - } - - ret = __sev_dbg_decrypt(kvm, dst_paddr, - __sme_page_pa(dst_tpage), size, error); - if (ret) - goto e_free; - - /* - * If source is kernel buffer then use memcpy() otherwise - * copy_from_user(). - */ - dst_offset = dst_paddr & 15; - - if (src_tpage) - memcpy(page_address(dst_tpage) + dst_offset, - page_address(src_tpage), size); - else { - if (copy_from_user(page_address(dst_tpage) + dst_offset, - (void __user *)(uintptr_t)vaddr, size)) { - ret = -EFAULT; - goto e_free; - } - } - - paddr = __sme_page_pa(dst_tpage); - dst_paddr = round_down(dst_paddr, 16); - len = round_up(size, 16); - } - - ret = __sev_issue_dbg_cmd(kvm, paddr, dst_paddr, len, error, true); - -e_free: - if (src_tpage) - __free_page(src_tpage); - if (dst_tpage) - __free_page(dst_tpage); - return ret; -} - -static int sev_dbg_crypt(struct kvm *kvm, struct kvm_sev_cmd *argp, bool dec) -{ - unsigned long vaddr, vaddr_end, next_vaddr; - unsigned long dst_vaddr; - struct page **src_p, **dst_p; - struct kvm_sev_dbg debug; - unsigned long n; - unsigned int size; - int ret; - - if (!sev_guest(kvm)) - return -ENOTTY; - - if (copy_from_user(&debug, (void __user *)(uintptr_t)argp->data, sizeof(debug))) - return -EFAULT; - - if (!debug.len || debug.src_uaddr + debug.len < debug.src_uaddr) - return -EINVAL; - if (!debug.dst_uaddr) - return -EINVAL; - - vaddr = debug.src_uaddr; - size = debug.len; - vaddr_end = vaddr + size; - dst_vaddr = debug.dst_uaddr; - - for (; vaddr < vaddr_end; vaddr = next_vaddr) { - int len, s_off, d_off; - - /* lock userspace source and destination page */ - src_p = sev_pin_memory(kvm, vaddr & PAGE_MASK, PAGE_SIZE, &n, 0); - if (!src_p) - return -EFAULT; - - dst_p = sev_pin_memory(kvm, dst_vaddr & PAGE_MASK, PAGE_SIZE, &n, 1); - if (!dst_p) { - sev_unpin_memory(kvm, src_p, n); - return -EFAULT; - } - - /* - * The DBG_{DE,EN}CRYPT commands will perform {dec,en}cryption of the - * memory content (i.e it will write the same memory region with C=1). - * It's possible that the cache may contain the data with C=0, i.e., - * unencrypted so invalidate it first. - */ - sev_clflush_pages(src_p, 1); - sev_clflush_pages(dst_p, 1); - - /* - * Since user buffer may not be page aligned, calculate the - * offset within the page. - */ - s_off = vaddr & ~PAGE_MASK; - d_off = dst_vaddr & ~PAGE_MASK; - len = min_t(size_t, (PAGE_SIZE - s_off), size); - - if (dec) - ret = __sev_dbg_decrypt_user(kvm, - __sme_page_pa(src_p[0]) + s_off, - dst_vaddr, - __sme_page_pa(dst_p[0]) + d_off, - len, &argp->error); - else - ret = __sev_dbg_encrypt_user(kvm, - __sme_page_pa(src_p[0]) + s_off, - vaddr, - __sme_page_pa(dst_p[0]) + d_off, - dst_vaddr, - len, &argp->error); - - sev_unpin_memory(kvm, src_p, n); - sev_unpin_memory(kvm, dst_p, n); - - if (ret) - goto err; - - next_vaddr = vaddr + len; - dst_vaddr = dst_vaddr + len; - size -= len; - } -err: - return ret; -} - -static int sev_launch_secret(struct kvm *kvm, struct kvm_sev_cmd *argp) -{ - struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; - struct sev_data_launch_secret *data; - struct kvm_sev_launch_secret params; - struct page **pages; - void *blob, *hdr; - unsigned long n; - int ret, offset; - - if (!sev_guest(kvm)) - return -ENOTTY; - - if (copy_from_user(¶ms, (void __user *)(uintptr_t)argp->data, sizeof(params))) - return -EFAULT; - - pages = sev_pin_memory(kvm, params.guest_uaddr, params.guest_len, &n, 1); - if (!pages) - return -ENOMEM; - - /* - * The secret must be copied into contiguous memory region, lets verify - * that userspace memory pages are contiguous before we issue command. - */ - if (get_num_contig_pages(0, pages, n) != n) { - ret = -EINVAL; - goto e_unpin_memory; - } - - ret = -ENOMEM; - data = kzalloc(sizeof(*data), GFP_KERNEL_ACCOUNT); - if (!data) - goto e_unpin_memory; - - offset = params.guest_uaddr & (PAGE_SIZE - 1); - data->guest_address = __sme_page_pa(pages[0]) + offset; - data->guest_len = params.guest_len; - - blob = psp_copy_user_blob(params.trans_uaddr, params.trans_len); - if (IS_ERR(blob)) { - ret = PTR_ERR(blob); - goto e_free; - } - - data->trans_address = __psp_pa(blob); - data->trans_len = params.trans_len; - - hdr = psp_copy_user_blob(params.hdr_uaddr, params.hdr_len); - if (IS_ERR(hdr)) { - ret = PTR_ERR(hdr); - goto e_free_blob; - } - data->hdr_address = __psp_pa(hdr); - data->hdr_len = params.hdr_len; - - data->handle = sev->handle; - ret = sev_issue_cmd(kvm, SEV_CMD_LAUNCH_UPDATE_SECRET, data, &argp->error); - - kfree(hdr); - -e_free_blob: - kfree(blob); -e_free: - kfree(data); -e_unpin_memory: - sev_unpin_memory(kvm, pages, n); - return ret; -} - -static int svm_mem_enc_op(struct kvm *kvm, void __user *argp) -{ - struct kvm_sev_cmd sev_cmd; - int r; - - if (!svm_sev_enabled()) - return -ENOTTY; - - if (!argp) - return 0; - - if (copy_from_user(&sev_cmd, argp, sizeof(struct kvm_sev_cmd))) - return -EFAULT; - - mutex_lock(&kvm->lock); - - switch (sev_cmd.id) { - case KVM_SEV_INIT: - r = sev_guest_init(kvm, &sev_cmd); - break; - case KVM_SEV_LAUNCH_START: - r = sev_launch_start(kvm, &sev_cmd); - break; - case KVM_SEV_LAUNCH_UPDATE_DATA: - r = sev_launch_update_data(kvm, &sev_cmd); - break; - case KVM_SEV_LAUNCH_MEASURE: - r = sev_launch_measure(kvm, &sev_cmd); - break; - case KVM_SEV_LAUNCH_FINISH: - r = sev_launch_finish(kvm, &sev_cmd); - break; - case KVM_SEV_GUEST_STATUS: - r = sev_guest_status(kvm, &sev_cmd); - break; - case KVM_SEV_DBG_DECRYPT: - r = sev_dbg_crypt(kvm, &sev_cmd, true); - break; - case KVM_SEV_DBG_ENCRYPT: - r = sev_dbg_crypt(kvm, &sev_cmd, false); - break; - case KVM_SEV_LAUNCH_SECRET: - r = sev_launch_secret(kvm, &sev_cmd); - break; - default: - r = -EINVAL; - goto out; - } - - if (copy_to_user(argp, &sev_cmd, sizeof(struct kvm_sev_cmd))) - r = -EFAULT; - -out: - mutex_unlock(&kvm->lock); - return r; -} - -static int svm_register_enc_region(struct kvm *kvm, - struct kvm_enc_region *range) -{ - struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; - struct enc_region *region; - int ret = 0; - - if (!sev_guest(kvm)) - return -ENOTTY; - - if (range->addr > ULONG_MAX || range->size > ULONG_MAX) - return -EINVAL; - - region = kzalloc(sizeof(*region), GFP_KERNEL_ACCOUNT); - if (!region) - return -ENOMEM; - - region->pages = sev_pin_memory(kvm, range->addr, range->size, ®ion->npages, 1); - if (!region->pages) { - ret = -ENOMEM; - goto e_free; - } - - /* - * The guest may change the memory encryption attribute from C=0 -> C=1 - * or vice versa for this memory range. Lets make sure caches are - * flushed to ensure that guest data gets written into memory with - * correct C-bit. - */ - sev_clflush_pages(region->pages, region->npages); - - region->uaddr = range->addr; - region->size = range->size; - - mutex_lock(&kvm->lock); - list_add_tail(®ion->list, &sev->regions_list); - mutex_unlock(&kvm->lock); - - return ret; - -e_free: - kfree(region); - return ret; -} - -static struct enc_region * -find_enc_region(struct kvm *kvm, struct kvm_enc_region *range) -{ - struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; - struct list_head *head = &sev->regions_list; - struct enc_region *i; - - list_for_each_entry(i, head, list) { - if (i->uaddr == range->addr && - i->size == range->size) - return i; - } - - return NULL; -} - - -static int svm_unregister_enc_region(struct kvm *kvm, - struct kvm_enc_region *range) -{ - struct enc_region *region; - int ret; - - mutex_lock(&kvm->lock); - - if (!sev_guest(kvm)) { - ret = -ENOTTY; - goto failed; - } - - region = find_enc_region(kvm, range); - if (!region) { - ret = -EINVAL; - goto failed; - } - - /* - * Ensure that all guest tagged cache entries are flushed before - * releasing the pages back to the system for use. CLFLUSH will - * not do this, so issue a WBINVD. - */ - wbinvd_on_all_cpus(); - - __unregister_enc_region_locked(kvm, region); - - mutex_unlock(&kvm->lock); - return 0; - -failed: - mutex_unlock(&kvm->lock); - return ret; -} - static bool svm_need_emulation_on_page_fault(struct kvm_vcpu *vcpu) { unsigned long cr4 = kvm_read_cr4(vcpu); @@ -7347,21 +3880,22 @@ static bool svm_apic_init_signal_blocked(struct kvm_vcpu *vcpu) (svm->vmcb->control.intercept & (1ULL << INTERCEPT_INIT)); } -static bool svm_check_apicv_inhibit_reasons(ulong bit) +static void svm_vm_destroy(struct kvm *kvm) { - ulong supported = BIT(APICV_INHIBIT_REASON_DISABLE) | - BIT(APICV_INHIBIT_REASON_HYPERV) | - BIT(APICV_INHIBIT_REASON_NESTED) | - BIT(APICV_INHIBIT_REASON_IRQWIN) | - BIT(APICV_INHIBIT_REASON_PIT_REINJ) | - BIT(APICV_INHIBIT_REASON_X2APIC); - - return supported & BIT(bit); + avic_vm_destroy(kvm); + sev_vm_destroy(kvm); } -static void svm_pre_update_apicv_exec_ctrl(struct kvm *kvm, bool activate) +static int svm_vm_init(struct kvm *kvm) { - avic_update_access_page(kvm, activate); + if (avic) { + int ret = avic_vm_init(kvm); + if (ret) + return ret; + } + + kvm_apicv_init(kvm, avic); + return 0; } static struct kvm_x86_ops svm_x86_ops __initdata = { diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h new file mode 100644 index 000000000000..df3474f4fb02 --- /dev/null +++ b/arch/x86/kvm/svm/svm.h @@ -0,0 +1,491 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Kernel-based Virtual Machine driver for Linux + * + * AMD SVM support + * + * Copyright (C) 2006 Qumranet, Inc. + * Copyright 2010 Red Hat, Inc. and/or its affiliates. + * + * Authors: + * Yaniv Kamay <yaniv@qumranet.com> + * Avi Kivity <avi@qumranet.com> + */ + +#ifndef __SVM_SVM_H +#define __SVM_SVM_H + +#include <linux/kvm_types.h> +#include <linux/kvm_host.h> + +#include <asm/svm.h> + +static const u32 host_save_user_msrs[] = { +#ifdef CONFIG_X86_64 + MSR_STAR, MSR_LSTAR, MSR_CSTAR, MSR_SYSCALL_MASK, MSR_KERNEL_GS_BASE, + MSR_FS_BASE, +#endif + MSR_IA32_SYSENTER_CS, MSR_IA32_SYSENTER_ESP, MSR_IA32_SYSENTER_EIP, + MSR_TSC_AUX, +}; + +#define NR_HOST_SAVE_USER_MSRS ARRAY_SIZE(host_save_user_msrs) + +#define MSRPM_OFFSETS 16 +extern u32 msrpm_offsets[MSRPM_OFFSETS] __read_mostly; +extern bool npt_enabled; + +enum { + VMCB_INTERCEPTS, /* Intercept vectors, TSC offset, + pause filter count */ + VMCB_PERM_MAP, /* IOPM Base and MSRPM Base */ + VMCB_ASID, /* ASID */ + VMCB_INTR, /* int_ctl, int_vector */ + VMCB_NPT, /* npt_en, nCR3, gPAT */ + VMCB_CR, /* CR0, CR3, CR4, EFER */ + VMCB_DR, /* DR6, DR7 */ + VMCB_DT, /* GDT, IDT */ + VMCB_SEG, /* CS, DS, SS, ES, CPL */ + VMCB_CR2, /* CR2 only */ + VMCB_LBR, /* DBGCTL, BR_FROM, BR_TO, LAST_EX_FROM, LAST_EX_TO */ + VMCB_AVIC, /* AVIC APIC_BAR, AVIC APIC_BACKING_PAGE, + * AVIC PHYSICAL_TABLE pointer, + * AVIC LOGICAL_TABLE pointer + */ + VMCB_DIRTY_MAX, +}; + +/* TPR and CR2 are always written before VMRUN */ +#define VMCB_ALWAYS_DIRTY_MASK ((1U << VMCB_INTR) | (1U << VMCB_CR2)) + +struct kvm_sev_info { + bool active; /* SEV enabled guest */ + unsigned int asid; /* ASID used for this guest */ + unsigned int handle; /* SEV firmware handle */ + int fd; /* SEV device fd */ + unsigned long pages_locked; /* Number of pages locked */ + struct list_head regions_list; /* List of registered regions */ +}; + +struct kvm_svm { + struct kvm kvm; + + /* Struct members for AVIC */ + u32 avic_vm_id; + struct page *avic_logical_id_table_page; + struct page *avic_physical_id_table_page; + struct hlist_node hnode; + + struct kvm_sev_info sev_info; +}; + +struct kvm_vcpu; + +struct nested_state { + struct vmcb *hsave; + u64 hsave_msr; + u64 vm_cr_msr; + u64 vmcb; + + /* These are the merged vectors */ + u32 *msrpm; + + /* gpa pointers to the real vectors */ + u64 vmcb_msrpm; + u64 vmcb_iopm; + + /* A VMEXIT is required but not yet emulated */ + bool exit_required; + + /* cache for intercepts of the guest */ + u32 intercept_cr; + u32 intercept_dr; + u32 intercept_exceptions; + u64 intercept; + + /* Nested Paging related state */ + u64 nested_cr3; +}; + +struct vcpu_svm { + struct kvm_vcpu vcpu; + struct vmcb *vmcb; + unsigned long vmcb_pa; + struct svm_cpu_data *svm_data; + uint64_t asid_generation; + uint64_t sysenter_esp; + uint64_t sysenter_eip; + uint64_t tsc_aux; + + u64 msr_decfg; + + u64 next_rip; + + u64 host_user_msrs[NR_HOST_SAVE_USER_MSRS]; + struct { + u16 fs; + u16 gs; + u16 ldt; + u64 gs_base; + } host; + + u64 spec_ctrl; + /* + * Contains guest-controlled bits of VIRT_SPEC_CTRL, which will be + * translated into the appropriate L2_CFG bits on the host to + * perform speculative control. + */ + u64 virt_spec_ctrl; + + u32 *msrpm; + + ulong nmi_iret_rip; + + struct nested_state nested; + + bool nmi_singlestep; + u64 nmi_singlestep_guest_rflags; + + unsigned int3_injected; + unsigned long int3_rip; + + /* cached guest cpuid flags for faster access */ + bool nrips_enabled : 1; + + u32 ldr_reg; + u32 dfr_reg; + struct page *avic_backing_page; + u64 *avic_physical_id_cache; + bool avic_is_running; + + /* + * Per-vcpu list of struct amd_svm_iommu_ir: + * This is used mainly to store interrupt remapping information used + * when update the vcpu affinity. This avoids the need to scan for + * IRTE and try to match ga_tag in the IOMMU driver. + */ + struct list_head ir_list; + spinlock_t ir_list_lock; + + /* which host CPU was used for running this vcpu */ + unsigned int last_cpu; +}; + +struct svm_cpu_data { + int cpu; + + u64 asid_generation; + u32 max_asid; + u32 next_asid; + u32 min_asid; + struct kvm_ldttss_desc *tss_desc; + + struct page *save_area; + struct vmcb *current_vmcb; + + /* index = sev_asid, value = vmcb pointer */ + struct vmcb **sev_vmcbs; +}; + +DECLARE_PER_CPU(struct svm_cpu_data *, svm_data); + +void recalc_intercepts(struct vcpu_svm *svm); + +static inline struct kvm_svm *to_kvm_svm(struct kvm *kvm) +{ + return container_of(kvm, struct kvm_svm, kvm); +} + +static inline void mark_all_dirty(struct vmcb *vmcb) +{ + vmcb->control.clean = 0; +} + +static inline void mark_all_clean(struct vmcb *vmcb) +{ + vmcb->control.clean = ((1 << VMCB_DIRTY_MAX) - 1) + & ~VMCB_ALWAYS_DIRTY_MASK; +} + +static inline void mark_dirty(struct vmcb *vmcb, int bit) +{ + vmcb->control.clean &= ~(1 << bit); +} + +static inline struct vcpu_svm *to_svm(struct kvm_vcpu *vcpu) +{ + return container_of(vcpu, struct vcpu_svm, vcpu); +} + +static inline struct vmcb *get_host_vmcb(struct vcpu_svm *svm) +{ + if (is_guest_mode(&svm->vcpu)) + return svm->nested.hsave; + else + return svm->vmcb; +} + +static inline void set_cr_intercept(struct vcpu_svm *svm, int bit) +{ + struct vmcb *vmcb = get_host_vmcb(svm); + + vmcb->control.intercept_cr |= (1U << bit); + + recalc_intercepts(svm); +} + +static inline void clr_cr_intercept(struct vcpu_svm *svm, int bit) +{ + struct vmcb *vmcb = get_host_vmcb(svm); + + vmcb->control.intercept_cr &= ~(1U << bit); + + recalc_intercepts(svm); +} + +static inline bool is_cr_intercept(struct vcpu_svm *svm, int bit) +{ + struct vmcb *vmcb = get_host_vmcb(svm); + + return vmcb->control.intercept_cr & (1U << bit); +} + +static inline void set_dr_intercepts(struct vcpu_svm *svm) +{ + struct vmcb *vmcb = get_host_vmcb(svm); + + vmcb->control.intercept_dr = (1 << INTERCEPT_DR0_READ) + | (1 << INTERCEPT_DR1_READ) + | (1 << INTERCEPT_DR2_READ) + | (1 << INTERCEPT_DR3_READ) + | (1 << INTERCEPT_DR4_READ) + | (1 << INTERCEPT_DR5_READ) + | (1 << INTERCEPT_DR6_READ) + | (1 << INTERCEPT_DR7_READ) + | (1 << INTERCEPT_DR0_WRITE) + | (1 << INTERCEPT_DR1_WRITE) + | (1 << INTERCEPT_DR2_WRITE) + | (1 << INTERCEPT_DR3_WRITE) + | (1 << INTERCEPT_DR4_WRITE) + | (1 << INTERCEPT_DR5_WRITE) + | (1 << INTERCEPT_DR6_WRITE) + | (1 << INTERCEPT_DR7_WRITE); + + recalc_intercepts(svm); +} + +static inline void clr_dr_intercepts(struct vcpu_svm *svm) +{ + struct vmcb *vmcb = get_host_vmcb(svm); + + vmcb->control.intercept_dr = 0; + + recalc_intercepts(svm); +} + +static inline void set_exception_intercept(struct vcpu_svm *svm, int bit) +{ + struct vmcb *vmcb = get_host_vmcb(svm); + + vmcb->control.intercept_exceptions |= (1U << bit); + + recalc_intercepts(svm); +} + +static inline void clr_exception_intercept(struct vcpu_svm *svm, int bit) +{ + struct vmcb *vmcb = get_host_vmcb(svm); + + vmcb->control.intercept_exceptions &= ~(1U << bit); + + recalc_intercepts(svm); +} + +static inline void set_intercept(struct vcpu_svm *svm, int bit) +{ + struct vmcb *vmcb = get_host_vmcb(svm); + + vmcb->control.intercept |= (1ULL << bit); + + recalc_intercepts(svm); +} + +static inline void clr_intercept(struct vcpu_svm *svm, int bit) +{ + struct vmcb *vmcb = get_host_vmcb(svm); + + vmcb->control.intercept &= ~(1ULL << bit); + + recalc_intercepts(svm); +} + +static inline bool is_intercept(struct vcpu_svm *svm, int bit) +{ + return (svm->vmcb->control.intercept & (1ULL << bit)) != 0; +} + +static inline bool vgif_enabled(struct vcpu_svm *svm) +{ + return !!(svm->vmcb->control.int_ctl & V_GIF_ENABLE_MASK); +} + +static inline void enable_gif(struct vcpu_svm *svm) +{ + if (vgif_enabled(svm)) + svm->vmcb->control.int_ctl |= V_GIF_MASK; + else + svm->vcpu.arch.hflags |= HF_GIF_MASK; +} + +static inline void disable_gif(struct vcpu_svm *svm) +{ + if (vgif_enabled(svm)) + svm->vmcb->control.int_ctl &= ~V_GIF_MASK; + else + svm->vcpu.arch.hflags &= ~HF_GIF_MASK; +} + +static inline bool gif_set(struct vcpu_svm *svm) +{ + if (vgif_enabled(svm)) + return !!(svm->vmcb->control.int_ctl & V_GIF_MASK); + else + return !!(svm->vcpu.arch.hflags & HF_GIF_MASK); +} + +/* svm.c */ +#define MSR_INVALID 0xffffffffU + +u32 svm_msrpm_offset(u32 msr); +void svm_set_efer(struct kvm_vcpu *vcpu, u64 efer); +void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0); +int svm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4); +void svm_flush_tlb(struct kvm_vcpu *vcpu, bool invalidate_gpa); +void disable_nmi_singlestep(struct vcpu_svm *svm); + +/* nested.c */ + +#define NESTED_EXIT_HOST 0 /* Exit handled on host level */ +#define NESTED_EXIT_DONE 1 /* Exit caused nested vmexit */ +#define NESTED_EXIT_CONTINUE 2 /* Further checks needed */ + +/* This function returns true if it is save to enable the nmi window */ +static inline bool nested_svm_nmi(struct vcpu_svm *svm) +{ + if (!is_guest_mode(&svm->vcpu)) + return true; + + if (!(svm->nested.intercept & (1ULL << INTERCEPT_NMI))) + return true; + + svm->vmcb->control.exit_code = SVM_EXIT_NMI; + svm->nested.exit_required = true; + + return false; +} + +static inline bool svm_nested_virtualize_tpr(struct kvm_vcpu *vcpu) +{ + return is_guest_mode(vcpu) && (vcpu->arch.hflags & HF_VINTR_MASK); +} + +void enter_svm_guest_mode(struct vcpu_svm *svm, u64 vmcb_gpa, + struct vmcb *nested_vmcb, struct kvm_host_map *map); +int nested_svm_vmrun(struct vcpu_svm *svm); +void nested_svm_vmloadsave(struct vmcb *from_vmcb, struct vmcb *to_vmcb); +int nested_svm_vmexit(struct vcpu_svm *svm); +int nested_svm_exit_handled(struct vcpu_svm *svm); +int nested_svm_check_permissions(struct vcpu_svm *svm); +int nested_svm_check_exception(struct vcpu_svm *svm, unsigned nr, + bool has_error_code, u32 error_code); +int svm_check_nested_events(struct kvm_vcpu *vcpu); +int nested_svm_exit_special(struct vcpu_svm *svm); + +/* avic.c */ + +#define AVIC_LOGICAL_ID_ENTRY_GUEST_PHYSICAL_ID_MASK (0xFF) +#define AVIC_LOGICAL_ID_ENTRY_VALID_BIT 31 +#define AVIC_LOGICAL_ID_ENTRY_VALID_MASK (1 << 31) + +#define AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK (0xFFULL) +#define AVIC_PHYSICAL_ID_ENTRY_BACKING_PAGE_MASK (0xFFFFFFFFFFULL << 12) +#define AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK (1ULL << 62) +#define AVIC_PHYSICAL_ID_ENTRY_VALID_MASK (1ULL << 63) + +#define VMCB_AVIC_APIC_BAR_MASK 0xFFFFFFFFFF000ULL + +extern int avic; + +static inline void avic_update_vapic_bar(struct vcpu_svm *svm, u64 data) +{ + svm->vmcb->control.avic_vapic_bar = data & VMCB_AVIC_APIC_BAR_MASK; + mark_dirty(svm->vmcb, VMCB_AVIC); +} + +static inline bool avic_vcpu_is_running(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + u64 *entry = svm->avic_physical_id_cache; + + if (!entry) + return false; + + return (READ_ONCE(*entry) & AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK); +} + +int avic_ga_log_notifier(u32 ga_tag); +void avic_vm_destroy(struct kvm *kvm); +int avic_vm_init(struct kvm *kvm); +void avic_init_vmcb(struct vcpu_svm *svm); +void svm_toggle_avic_for_irq_window(struct kvm_vcpu *vcpu, bool activate); +int avic_incomplete_ipi_interception(struct vcpu_svm *svm); +int avic_unaccelerated_access_interception(struct vcpu_svm *svm); +int avic_init_vcpu(struct vcpu_svm *svm); +void avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu); +void avic_vcpu_put(struct kvm_vcpu *vcpu); +void avic_post_state_restore(struct kvm_vcpu *vcpu); +void svm_set_virtual_apic_mode(struct kvm_vcpu *vcpu); +void svm_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu); +bool svm_check_apicv_inhibit_reasons(ulong bit); +void svm_pre_update_apicv_exec_ctrl(struct kvm *kvm, bool activate); +void svm_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap); +void svm_hwapic_irr_update(struct kvm_vcpu *vcpu, int max_irr); +void svm_hwapic_isr_update(struct kvm_vcpu *vcpu, int max_isr); +int svm_deliver_avic_intr(struct kvm_vcpu *vcpu, int vec); +bool svm_dy_apicv_has_pending_interrupt(struct kvm_vcpu *vcpu); +int svm_update_pi_irte(struct kvm *kvm, unsigned int host_irq, + uint32_t guest_irq, bool set); +void svm_vcpu_blocking(struct kvm_vcpu *vcpu); +void svm_vcpu_unblocking(struct kvm_vcpu *vcpu); + +/* sev.c */ + +extern unsigned int max_sev_asid; + +static inline bool sev_guest(struct kvm *kvm) +{ +#ifdef CONFIG_KVM_AMD_SEV + struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; + + return sev->active; +#else + return false; +#endif +} + +static inline bool svm_sev_enabled(void) +{ + return IS_ENABLED(CONFIG_KVM_AMD_SEV) ? max_sev_asid : 0; +} + +void sev_vm_destroy(struct kvm *kvm); +int svm_mem_enc_op(struct kvm *kvm, void __user *argp); +int svm_register_enc_region(struct kvm *kvm, + struct kvm_enc_region *range); +int svm_unregister_enc_region(struct kvm *kvm, + struct kvm_enc_region *range); +void pre_sev_run(struct vcpu_svm *svm, int cpu); +int __init sev_hardware_setup(void); +void sev_hardware_teardown(void); + +#endif diff --git a/arch/x86/kvm/svm/vmenter.S b/arch/x86/kvm/svm/vmenter.S new file mode 100644 index 000000000000..fa1af90067e9 --- /dev/null +++ b/arch/x86/kvm/svm/vmenter.S @@ -0,0 +1,162 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#include <linux/linkage.h> +#include <asm/asm.h> +#include <asm/bitsperlong.h> +#include <asm/kvm_vcpu_regs.h> + +#define WORD_SIZE (BITS_PER_LONG / 8) + +/* Intentionally omit RAX as it's context switched by hardware */ +#define VCPU_RCX __VCPU_REGS_RCX * WORD_SIZE +#define VCPU_RDX __VCPU_REGS_RDX * WORD_SIZE +#define VCPU_RBX __VCPU_REGS_RBX * WORD_SIZE +/* Intentionally omit RSP as it's context switched by hardware */ +#define VCPU_RBP __VCPU_REGS_RBP * WORD_SIZE +#define VCPU_RSI __VCPU_REGS_RSI * WORD_SIZE +#define VCPU_RDI __VCPU_REGS_RDI * WORD_SIZE + +#ifdef CONFIG_X86_64 +#define VCPU_R8 __VCPU_REGS_R8 * WORD_SIZE +#define VCPU_R9 __VCPU_REGS_R9 * WORD_SIZE +#define VCPU_R10 __VCPU_REGS_R10 * WORD_SIZE +#define VCPU_R11 __VCPU_REGS_R11 * WORD_SIZE +#define VCPU_R12 __VCPU_REGS_R12 * WORD_SIZE +#define VCPU_R13 __VCPU_REGS_R13 * WORD_SIZE +#define VCPU_R14 __VCPU_REGS_R14 * WORD_SIZE +#define VCPU_R15 __VCPU_REGS_R15 * WORD_SIZE +#endif + + .text + +/** + * __svm_vcpu_run - Run a vCPU via a transition to SVM guest mode + * @vmcb_pa: unsigned long + * @regs: unsigned long * (to guest registers) + */ +SYM_FUNC_START(__svm_vcpu_run) + push %_ASM_BP + mov %_ASM_SP, %_ASM_BP +#ifdef CONFIG_X86_64 + push %r15 + push %r14 + push %r13 + push %r12 +#else + push %edi + push %esi +#endif + push %_ASM_BX + + /* Save @regs. */ + push %_ASM_ARG2 + + /* Save @vmcb. */ + push %_ASM_ARG1 + + /* Move @regs to RAX. */ + mov %_ASM_ARG2, %_ASM_AX + + /* Load guest registers. */ + mov VCPU_RCX(%_ASM_AX), %_ASM_CX + mov VCPU_RDX(%_ASM_AX), %_ASM_DX + mov VCPU_RBX(%_ASM_AX), %_ASM_BX + mov VCPU_RBP(%_ASM_AX), %_ASM_BP + mov VCPU_RSI(%_ASM_AX), %_ASM_SI + mov VCPU_RDI(%_ASM_AX), %_ASM_DI +#ifdef CONFIG_X86_64 + mov VCPU_R8 (%_ASM_AX), %r8 + mov VCPU_R9 (%_ASM_AX), %r9 + mov VCPU_R10(%_ASM_AX), %r10 + mov VCPU_R11(%_ASM_AX), %r11 + mov VCPU_R12(%_ASM_AX), %r12 + mov VCPU_R13(%_ASM_AX), %r13 + mov VCPU_R14(%_ASM_AX), %r14 + mov VCPU_R15(%_ASM_AX), %r15 +#endif + + /* "POP" @vmcb to RAX. */ + pop %_ASM_AX + + /* Enter guest mode */ +1: vmload %_ASM_AX + jmp 3f +2: cmpb $0, kvm_rebooting + jne 3f + ud2 + _ASM_EXTABLE(1b, 2b) + +3: vmrun %_ASM_AX + jmp 5f +4: cmpb $0, kvm_rebooting + jne 5f + ud2 + _ASM_EXTABLE(3b, 4b) + +5: vmsave %_ASM_AX + jmp 7f +6: cmpb $0, kvm_rebooting + jne 7f + ud2 + _ASM_EXTABLE(5b, 6b) +7: + /* "POP" @regs to RAX. */ + pop %_ASM_AX + + /* Save all guest registers. */ + mov %_ASM_CX, VCPU_RCX(%_ASM_AX) + mov %_ASM_DX, VCPU_RDX(%_ASM_AX) + mov %_ASM_BX, VCPU_RBX(%_ASM_AX) + mov %_ASM_BP, VCPU_RBP(%_ASM_AX) + mov %_ASM_SI, VCPU_RSI(%_ASM_AX) + mov %_ASM_DI, VCPU_RDI(%_ASM_AX) +#ifdef CONFIG_X86_64 + mov %r8, VCPU_R8 (%_ASM_AX) + mov %r9, VCPU_R9 (%_ASM_AX) + mov %r10, VCPU_R10(%_ASM_AX) + mov %r11, VCPU_R11(%_ASM_AX) + mov %r12, VCPU_R12(%_ASM_AX) + mov %r13, VCPU_R13(%_ASM_AX) + mov %r14, VCPU_R14(%_ASM_AX) + mov %r15, VCPU_R15(%_ASM_AX) +#endif + + /* + * Clear all general purpose registers except RSP and RAX to prevent + * speculative use of the guest's values, even those that are reloaded + * via the stack. In theory, an L1 cache miss when restoring registers + * could lead to speculative execution with the guest's values. + * Zeroing XORs are dirt cheap, i.e. the extra paranoia is essentially + * free. RSP and RAX are exempt as they are restored by hardware + * during VM-Exit. + */ + xor %ecx, %ecx + xor %edx, %edx + xor %ebx, %ebx + xor %ebp, %ebp + xor %esi, %esi + xor %edi, %edi +#ifdef CONFIG_X86_64 + xor %r8d, %r8d + xor %r9d, %r9d + xor %r10d, %r10d + xor %r11d, %r11d + xor %r12d, %r12d + xor %r13d, %r13d + xor %r14d, %r14d + xor %r15d, %r15d +#endif + + pop %_ASM_BX + +#ifdef CONFIG_X86_64 + pop %r12 + pop %r13 + pop %r14 + pop %r15 +#else + pop %esi + pop %edi +#endif + pop %_ASM_BP + ret +SYM_FUNC_END(__svm_vcpu_run) diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index de232306561a..cbc9ea2de28f 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -3645,7 +3645,8 @@ static int vmx_check_nested_events(struct kvm_vcpu *vcpu) * Clear the MTF state. If a higher priority VM-exit is delivered first, * this state is discarded. */ - vmx->nested.mtf_pending = false; + if (!block_nested_events) + vmx->nested.mtf_pending = false; if (lapic_in_kernel(vcpu) && test_bit(KVM_APIC_INIT, &apic->pending_events)) { diff --git a/arch/x86/kvm/vmx/vmenter.S b/arch/x86/kvm/vmx/vmenter.S index 9651ba388ba9..87f3f24fef37 100644 --- a/arch/x86/kvm/vmx/vmenter.S +++ b/arch/x86/kvm/vmx/vmenter.S @@ -58,12 +58,8 @@ SYM_FUNC_START(vmx_vmenter) ret 4: ud2 - .pushsection .fixup, "ax" -5: jmp 3b - .popsection - - _ASM_EXTABLE(1b, 5b) - _ASM_EXTABLE(2b, 5b) + _ASM_EXTABLE(1b, 3b) + _ASM_EXTABLE(2b, 3b) SYM_FUNC_END(vmx_vmenter) diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 91749f1254e8..83050977490c 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -2261,10 +2261,6 @@ static int hardware_enable(void) !hv_get_vp_assist_page(cpu)) return -EFAULT; - INIT_LIST_HEAD(&per_cpu(loaded_vmcss_on_cpu, cpu)); - INIT_LIST_HEAD(&per_cpu(blocked_vcpu_on_cpu, cpu)); - spin_lock_init(&per_cpu(blocked_vcpu_on_cpu_lock, cpu)); - r = kvm_cpu_vmxon(phys_addr); if (r) return r; @@ -4592,6 +4588,26 @@ static int handle_machine_check(struct kvm_vcpu *vcpu) return 1; } +/* + * If the host has split lock detection disabled, then #AC is + * unconditionally injected into the guest, which is the pre split lock + * detection behaviour. + * + * If the host has split lock detection enabled then #AC is + * only injected into the guest when: + * - Guest CPL == 3 (user mode) + * - Guest has #AC detection enabled in CR0 + * - Guest EFLAGS has AC bit set + */ +static inline bool guest_inject_ac(struct kvm_vcpu *vcpu) +{ + if (!boot_cpu_has(X86_FEATURE_SPLIT_LOCK_DETECT)) + return true; + + return vmx_get_cpl(vcpu) == 3 && kvm_read_cr0_bits(vcpu, X86_CR0_AM) && + (kvm_get_rflags(vcpu) & X86_EFLAGS_AC); +} + static int handle_exception_nmi(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -4657,9 +4673,6 @@ static int handle_exception_nmi(struct kvm_vcpu *vcpu) return handle_rmode_exception(vcpu, ex_no, error_code); switch (ex_no) { - case AC_VECTOR: - kvm_queue_exception_e(vcpu, AC_VECTOR, error_code); - return 1; case DB_VECTOR: dr6 = vmcs_readl(EXIT_QUALIFICATION); if (!(vcpu->guest_debug & @@ -4688,6 +4701,20 @@ static int handle_exception_nmi(struct kvm_vcpu *vcpu) kvm_run->debug.arch.pc = vmcs_readl(GUEST_CS_BASE) + rip; kvm_run->debug.arch.exception = ex_no; break; + case AC_VECTOR: + if (guest_inject_ac(vcpu)) { + kvm_queue_exception_e(vcpu, AC_VECTOR, error_code); + return 1; + } + + /* + * Handle split lock. Depending on detection mode this will + * either warn and disable split lock detection for this + * task or force SIGBUS on it. + */ + if (handle_guest_split_lock(kvm_rip_read(vcpu))) + return 1; + fallthrough; default: kvm_run->exit_reason = KVM_EXIT_EXCEPTION; kvm_run->ex.exception = ex_no; @@ -8044,7 +8071,7 @@ module_exit(vmx_exit); static int __init vmx_init(void) { - int r; + int r, cpu; #if IS_ENABLED(CONFIG_HYPERV) /* @@ -8098,6 +8125,12 @@ static int __init vmx_init(void) return r; } + for_each_possible_cpu(cpu) { + INIT_LIST_HEAD(&per_cpu(loaded_vmcss_on_cpu, cpu)); + INIT_LIST_HEAD(&per_cpu(blocked_vcpu_on_cpu, cpu)); + spin_lock_init(&per_cpu(blocked_vcpu_on_cpu_lock, cpu)); + } + #ifdef CONFIG_KEXEC_CORE rcu_assign_pointer(crash_vmclear_loaded_vmcss, crash_vmclear_local_loaded_vmcss); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index b8124b562dea..3bf2ecafd027 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1586,7 +1586,8 @@ static int handle_fastpath_set_x2apic_icr_irqoff(struct kvm_vcpu *vcpu, u64 data if (((data & APIC_SHORT_MASK) == APIC_DEST_NOSHORT) && ((data & APIC_DEST_MASK) == APIC_DEST_PHYSICAL) && - ((data & APIC_MODE_MASK) == APIC_DM_FIXED)) { + ((data & APIC_MODE_MASK) == APIC_DM_FIXED) && + ((u32)(data >> 32) != X2APIC_BROADCAST)) { data &= ~(1 << 12); kvm_apic_send_ipi(vcpu->arch.apic, (u32)data, (u32)(data >> 32)); @@ -5838,6 +5839,7 @@ static int emulator_cmpxchg_emulated(struct x86_emulate_ctxt *ctxt, { struct kvm_host_map map; struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); + u64 page_line_mask; gpa_t gpa; char *kaddr; bool exchanged; @@ -5852,7 +5854,16 @@ static int emulator_cmpxchg_emulated(struct x86_emulate_ctxt *ctxt, (gpa & PAGE_MASK) == APIC_DEFAULT_PHYS_BASE) goto emul_write; - if (((gpa + bytes - 1) & PAGE_MASK) != (gpa & PAGE_MASK)) + /* + * Emulate the atomic as a straight write to avoid #AC if SLD is + * enabled in the host and the access splits a cache line. + */ + if (boot_cpu_has(X86_FEATURE_SPLIT_LOCK_DETECT)) + page_line_mask = ~(cache_line_size() - 1); + else + page_line_mask = PAGE_MASK; + + if (((gpa + bytes - 1) & page_line_mask) != (gpa & page_line_mask)) goto emul_write; if (kvm_vcpu_map(vcpu, gpa_to_gfn(gpa), &map)) diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index e7bb483557c9..1bba16c5742b 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -467,7 +467,7 @@ bool pfn_range_is_mapped(unsigned long start_pfn, unsigned long end_pfn) * the physical memory. To access them they are temporarily mapped. */ unsigned long __ref init_memory_mapping(unsigned long start, - unsigned long end) + unsigned long end, pgprot_t prot) { struct map_range mr[NR_RANGE_MR]; unsigned long ret = 0; @@ -481,7 +481,8 @@ unsigned long __ref init_memory_mapping(unsigned long start, for (i = 0; i < nr_range; i++) ret = kernel_physical_mapping_init(mr[i].start, mr[i].end, - mr[i].page_size_mask); + mr[i].page_size_mask, + prot); add_pfn_range_mapped(start >> PAGE_SHIFT, ret >> PAGE_SHIFT); @@ -521,7 +522,7 @@ static unsigned long __init init_range_memory_mapping( */ can_use_brk_pgt = max(start, (u64)pgt_buf_end<<PAGE_SHIFT) >= min(end, (u64)pgt_buf_top<<PAGE_SHIFT); - init_memory_mapping(start, end); + init_memory_mapping(start, end, PAGE_KERNEL); mapped_ram_size += end - start; can_use_brk_pgt = true; } @@ -661,7 +662,7 @@ void __init init_mem_mapping(void) #endif /* the ISA range is always mapped regardless of memory holes */ - init_memory_mapping(0, ISA_END_ADDRESS); + init_memory_mapping(0, ISA_END_ADDRESS, PAGE_KERNEL); /* Init the trampoline, possibly with KASLR memory offset */ init_trampoline(); diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index de73992b8432..4222a010057a 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -257,7 +257,8 @@ static inline int __is_kernel_text(unsigned long addr) unsigned long __init kernel_physical_mapping_init(unsigned long start, unsigned long end, - unsigned long page_size_mask) + unsigned long page_size_mask, + pgprot_t prot) { int use_pse = page_size_mask == (1<<PG_LEVEL_2M); unsigned long last_map_addr = end; @@ -819,12 +820,24 @@ void __init mem_init(void) #ifdef CONFIG_MEMORY_HOTPLUG int arch_add_memory(int nid, u64 start, u64 size, - struct mhp_restrictions *restrictions) + struct mhp_params *params) { unsigned long start_pfn = start >> PAGE_SHIFT; unsigned long nr_pages = size >> PAGE_SHIFT; + int ret; - return __add_pages(nid, start_pfn, nr_pages, restrictions); + /* + * The page tables were already mapped at boot so if the caller + * requests a different mapping type then we must change all the + * pages with __set_memory_prot(). + */ + if (params->pgprot.pgprot != PAGE_KERNEL.pgprot) { + ret = __set_memory_prot(start, nr_pages, params->pgprot); + if (ret) + return ret; + } + + return __add_pages(nid, start_pfn, nr_pages, params); } void arch_remove_memory(int nid, u64 start, u64 size, diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 0a14711d3a93..3b289c2f75cd 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -585,7 +585,7 @@ phys_pmd_init(pmd_t *pmd_page, unsigned long paddr, unsigned long paddr_end, */ static unsigned long __meminit phys_pud_init(pud_t *pud_page, unsigned long paddr, unsigned long paddr_end, - unsigned long page_size_mask, bool init) + unsigned long page_size_mask, pgprot_t _prot, bool init) { unsigned long pages = 0, paddr_next; unsigned long paddr_last = paddr_end; @@ -595,7 +595,7 @@ phys_pud_init(pud_t *pud_page, unsigned long paddr, unsigned long paddr_end, for (; i < PTRS_PER_PUD; i++, paddr = paddr_next) { pud_t *pud; pmd_t *pmd; - pgprot_t prot = PAGE_KERNEL; + pgprot_t prot = _prot; vaddr = (unsigned long)__va(paddr); pud = pud_page + pud_index(vaddr); @@ -644,9 +644,12 @@ phys_pud_init(pud_t *pud_page, unsigned long paddr, unsigned long paddr_end, if (page_size_mask & (1<<PG_LEVEL_1G)) { pages++; spin_lock(&init_mm.page_table_lock); + + prot = __pgprot(pgprot_val(prot) | __PAGE_KERNEL_LARGE); + set_pte_init((pte_t *)pud, pfn_pte((paddr & PUD_MASK) >> PAGE_SHIFT, - PAGE_KERNEL_LARGE), + prot), init); spin_unlock(&init_mm.page_table_lock); paddr_last = paddr_next; @@ -669,7 +672,7 @@ phys_pud_init(pud_t *pud_page, unsigned long paddr, unsigned long paddr_end, static unsigned long __meminit phys_p4d_init(p4d_t *p4d_page, unsigned long paddr, unsigned long paddr_end, - unsigned long page_size_mask, bool init) + unsigned long page_size_mask, pgprot_t prot, bool init) { unsigned long vaddr, vaddr_end, vaddr_next, paddr_next, paddr_last; @@ -679,7 +682,7 @@ phys_p4d_init(p4d_t *p4d_page, unsigned long paddr, unsigned long paddr_end, if (!pgtable_l5_enabled()) return phys_pud_init((pud_t *) p4d_page, paddr, paddr_end, - page_size_mask, init); + page_size_mask, prot, init); for (; vaddr < vaddr_end; vaddr = vaddr_next) { p4d_t *p4d = p4d_page + p4d_index(vaddr); @@ -702,13 +705,13 @@ phys_p4d_init(p4d_t *p4d_page, unsigned long paddr, unsigned long paddr_end, if (!p4d_none(*p4d)) { pud = pud_offset(p4d, 0); paddr_last = phys_pud_init(pud, paddr, __pa(vaddr_end), - page_size_mask, init); + page_size_mask, prot, init); continue; } pud = alloc_low_page(); paddr_last = phys_pud_init(pud, paddr, __pa(vaddr_end), - page_size_mask, init); + page_size_mask, prot, init); spin_lock(&init_mm.page_table_lock); p4d_populate_init(&init_mm, p4d, pud, init); @@ -722,7 +725,7 @@ static unsigned long __meminit __kernel_physical_mapping_init(unsigned long paddr_start, unsigned long paddr_end, unsigned long page_size_mask, - bool init) + pgprot_t prot, bool init) { bool pgd_changed = false; unsigned long vaddr, vaddr_start, vaddr_end, vaddr_next, paddr_last; @@ -743,13 +746,13 @@ __kernel_physical_mapping_init(unsigned long paddr_start, paddr_last = phys_p4d_init(p4d, __pa(vaddr), __pa(vaddr_end), page_size_mask, - init); + prot, init); continue; } p4d = alloc_low_page(); paddr_last = phys_p4d_init(p4d, __pa(vaddr), __pa(vaddr_end), - page_size_mask, init); + page_size_mask, prot, init); spin_lock(&init_mm.page_table_lock); if (pgtable_l5_enabled()) @@ -778,10 +781,10 @@ __kernel_physical_mapping_init(unsigned long paddr_start, unsigned long __meminit kernel_physical_mapping_init(unsigned long paddr_start, unsigned long paddr_end, - unsigned long page_size_mask) + unsigned long page_size_mask, pgprot_t prot) { return __kernel_physical_mapping_init(paddr_start, paddr_end, - page_size_mask, true); + page_size_mask, prot, true); } /* @@ -796,7 +799,8 @@ kernel_physical_mapping_change(unsigned long paddr_start, unsigned long page_size_mask) { return __kernel_physical_mapping_init(paddr_start, paddr_end, - page_size_mask, false); + page_size_mask, PAGE_KERNEL, + false); } #ifndef CONFIG_NUMA @@ -843,11 +847,11 @@ static void update_end_of_memory_vars(u64 start, u64 size) } int add_pages(int nid, unsigned long start_pfn, unsigned long nr_pages, - struct mhp_restrictions *restrictions) + struct mhp_params *params) { int ret; - ret = __add_pages(nid, start_pfn, nr_pages, restrictions); + ret = __add_pages(nid, start_pfn, nr_pages, params); WARN_ON_ONCE(ret); /* update max_pfn, max_low_pfn and high_memory */ @@ -858,14 +862,14 @@ int add_pages(int nid, unsigned long start_pfn, unsigned long nr_pages, } int arch_add_memory(int nid, u64 start, u64 size, - struct mhp_restrictions *restrictions) + struct mhp_params *params) { unsigned long start_pfn = start >> PAGE_SHIFT; unsigned long nr_pages = size >> PAGE_SHIFT; - init_memory_mapping(start, start + size); + init_memory_mapping(start, start + size, params->pgprot); - return add_pages(nid, start_pfn, nr_pages, restrictions); + return add_pages(nid, start_pfn, nr_pages, params); } #define PAGE_INUSE 0xFD diff --git a/arch/x86/mm/mm_internal.h b/arch/x86/mm/mm_internal.h index eeae142062ed..3f37b5c80bb3 100644 --- a/arch/x86/mm/mm_internal.h +++ b/arch/x86/mm/mm_internal.h @@ -12,7 +12,8 @@ void early_ioremap_page_table_range_init(void); unsigned long kernel_physical_mapping_init(unsigned long start, unsigned long end, - unsigned long page_size_mask); + unsigned long page_size_mask, + pgprot_t prot); unsigned long kernel_physical_mapping_change(unsigned long start, unsigned long end, unsigned long page_size_mask); diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c index 99f7a68738f0..59ba008504dc 100644 --- a/arch/x86/mm/numa.c +++ b/arch/x86/mm/numa.c @@ -25,11 +25,8 @@ nodemask_t numa_nodes_parsed __initdata; struct pglist_data *node_data[MAX_NUMNODES] __read_mostly; EXPORT_SYMBOL(node_data); -static struct numa_meminfo numa_meminfo -#ifndef CONFIG_MEMORY_HOTPLUG -__initdata -#endif -; +static struct numa_meminfo numa_meminfo __initdata_or_meminfo; +static struct numa_meminfo numa_reserved_meminfo __initdata_or_meminfo; static int numa_distance_cnt; static u8 *numa_distance; @@ -169,6 +166,19 @@ void __init numa_remove_memblk_from(int idx, struct numa_meminfo *mi) } /** + * numa_move_tail_memblk - Move a numa_memblk from one numa_meminfo to another + * @dst: numa_meminfo to append block to + * @idx: Index of memblk to remove + * @src: numa_meminfo to remove memblk from + */ +static void __init numa_move_tail_memblk(struct numa_meminfo *dst, int idx, + struct numa_meminfo *src) +{ + dst->blk[dst->nr_blks++] = src->blk[idx]; + numa_remove_memblk_from(idx, src); +} + +/** * numa_add_memblk - Add one numa_memblk to numa_meminfo * @nid: NUMA node ID of the new memblk * @start: Start address of the new memblk @@ -237,14 +247,19 @@ int __init numa_cleanup_meminfo(struct numa_meminfo *mi) for (i = 0; i < mi->nr_blks; i++) { struct numa_memblk *bi = &mi->blk[i]; - /* make sure all blocks are inside the limits */ + /* move / save reserved memory ranges */ + if (!memblock_overlaps_region(&memblock.memory, + bi->start, bi->end - bi->start)) { + numa_move_tail_memblk(&numa_reserved_meminfo, i--, mi); + continue; + } + + /* make sure all non-reserved blocks are inside the limits */ bi->start = max(bi->start, low); bi->end = min(bi->end, high); - /* and there's no empty or non-exist block */ - if (bi->start >= bi->end || - !memblock_overlaps_region(&memblock.memory, - bi->start, bi->end - bi->start)) + /* and there's no empty block */ + if (bi->start >= bi->end) numa_remove_memblk_from(i--, mi); } @@ -881,16 +896,38 @@ EXPORT_SYMBOL(cpumask_of_node); #endif /* !CONFIG_DEBUG_PER_CPU_MAPS */ -#ifdef CONFIG_MEMORY_HOTPLUG -int memory_add_physaddr_to_nid(u64 start) +#ifdef CONFIG_NUMA_KEEP_MEMINFO +static int meminfo_to_nid(struct numa_meminfo *mi, u64 start) { - struct numa_meminfo *mi = &numa_meminfo; - int nid = mi->blk[0].nid; int i; for (i = 0; i < mi->nr_blks; i++) if (mi->blk[i].start <= start && mi->blk[i].end > start) - nid = mi->blk[i].nid; + return mi->blk[i].nid; + return NUMA_NO_NODE; +} + +int phys_to_target_node(phys_addr_t start) +{ + int nid = meminfo_to_nid(&numa_meminfo, start); + + /* + * Prefer online nodes, but if reserved memory might be + * hot-added continue the search with reserved ranges. + */ + if (nid != NUMA_NO_NODE) + return nid; + + return meminfo_to_nid(&numa_reserved_meminfo, start); +} +EXPORT_SYMBOL_GPL(phys_to_target_node); + +int memory_add_physaddr_to_nid(u64 start) +{ + int nid = meminfo_to_nid(&numa_meminfo, start); + + if (nid == NUMA_NO_NODE) + nid = numa_meminfo.blk[0].nid; return nid; } EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid); diff --git a/arch/x86/mm/pat/set_memory.c b/arch/x86/mm/pat/set_memory.c index 6d5424069e2b..59eca6a94ce7 100644 --- a/arch/x86/mm/pat/set_memory.c +++ b/arch/x86/mm/pat/set_memory.c @@ -1795,6 +1795,19 @@ static inline int cpa_clear_pages_array(struct page **pages, int numpages, CPA_PAGES_ARRAY, pages); } +/* + * _set_memory_prot is an internal helper for callers that have been passed + * a pgprot_t value from upper layers and a reservation has already been taken. + * If you want to set the pgprot to a specific page protocol, use the + * set_memory_xx() functions. + */ +int __set_memory_prot(unsigned long addr, int numpages, pgprot_t prot) +{ + return change_page_attr_set_clr(&addr, numpages, prot, + __pgprot(~pgprot_val(prot)), 0, 0, + NULL); +} + int _set_memory_uc(unsigned long addr, int numpages) { /* diff --git a/arch/x86/mm/pkeys.c b/arch/x86/mm/pkeys.c index c6f84c0b5d7a..8873ed1438a9 100644 --- a/arch/x86/mm/pkeys.c +++ b/arch/x86/mm/pkeys.c @@ -63,7 +63,7 @@ int __execute_only_pkey(struct mm_struct *mm) static inline bool vma_is_pkey_exec_only(struct vm_area_struct *vma) { /* Do this check first since the vm_flags should be hot */ - if ((vma->vm_flags & (VM_READ | VM_WRITE | VM_EXEC)) != VM_EXEC) + if ((vma->vm_flags & VM_ACCESS_FLAGS) != VM_EXEC) return false; if (vma_pkey(vma) != vma->vm_mm->context.execute_only_pkey) return false; diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c index 211bb9358b73..c5e393f8bb3f 100644 --- a/arch/x86/platform/efi/efi_64.c +++ b/arch/x86/platform/efi/efi_64.c @@ -202,7 +202,7 @@ virt_to_phys_or_null_size(void *va, unsigned long size) int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages) { - unsigned long pfn, text, pf; + unsigned long pfn, text, pf, rodata; struct page *page; unsigned npages; pgd_t *pgd = efi_mm.pgd; @@ -256,7 +256,7 @@ int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages) efi_scratch.phys_stack = page_to_phys(page + 1); /* stack grows down */ - npages = (__end_rodata_aligned - _text) >> PAGE_SHIFT; + npages = (_etext - _text) >> PAGE_SHIFT; text = __pa(_text); pfn = text >> PAGE_SHIFT; @@ -266,6 +266,14 @@ int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages) return 1; } + npages = (__end_rodata - __start_rodata) >> PAGE_SHIFT; + rodata = __pa(__start_rodata); + pfn = rodata >> PAGE_SHIFT; + if (kernel_map_pages_in_pgd(pgd, pfn, rodata, npages, pf)) { + pr_err("Failed to map kernel rodata 1:1\n"); + return 1; + } + return 0; } @@ -638,7 +646,7 @@ efi_thunk_set_variable(efi_char16_t *name, efi_guid_t *vendor, phys_vendor = virt_to_phys_or_null(vnd); phys_data = virt_to_phys_or_null_size(data, data_size); - if (!phys_name || !phys_data) + if (!phys_name || (data && !phys_data)) status = EFI_INVALID_PARAMETER; else status = efi_thunk(set_variable, phys_name, phys_vendor, @@ -669,7 +677,7 @@ efi_thunk_set_variable_nonblocking(efi_char16_t *name, efi_guid_t *vendor, phys_vendor = virt_to_phys_or_null(vnd); phys_data = virt_to_phys_or_null_size(data, data_size); - if (!phys_name || !phys_data) + if (!phys_name || (data && !phys_data)) status = EFI_INVALID_PARAMETER; else status = efi_thunk(set_variable, phys_name, phys_vendor, diff --git a/arch/x86/platform/uv/bios_uv.c b/arch/x86/platform/uv/bios_uv.c index 607f58147311..c60255da5a6c 100644 --- a/arch/x86/platform/uv/bios_uv.c +++ b/arch/x86/platform/uv/bios_uv.c @@ -352,7 +352,8 @@ void __iomem *__init efi_ioremap(unsigned long phys_addr, unsigned long size, if (type == EFI_MEMORY_MAPPED_IO) return ioremap(phys_addr, size); - last_map_pfn = init_memory_mapping(phys_addr, phys_addr + size); + last_map_pfn = init_memory_mapping(phys_addr, phys_addr + size, + PAGE_KERNEL); if ((last_map_pfn << PAGE_SHIFT) < phys_addr + size) { unsigned long top = last_map_pfn << PAGE_SHIFT; efi_ioremap(top, size - (top - phys_addr), type, attribute); diff --git a/arch/x86/um/asm/vm-flags.h b/arch/x86/um/asm/vm-flags.h index 7c297e9e2413..df7a3896f5dd 100644 --- a/arch/x86/um/asm/vm-flags.h +++ b/arch/x86/um/asm/vm-flags.h @@ -9,17 +9,11 @@ #ifdef CONFIG_X86_32 -#define VM_DATA_DEFAULT_FLAGS \ - (VM_READ | VM_WRITE | \ - ((current->personality & READ_IMPLIES_EXEC) ? VM_EXEC : 0 ) | \ - VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC) +#define VM_DATA_DEFAULT_FLAGS VM_DATA_FLAGS_TSK_EXEC #else -#define VM_DATA_DEFAULT_FLAGS (VM_READ | VM_WRITE | VM_EXEC | \ - VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC) -#define VM_STACK_DEFAULT_FLAGS (VM_GROWSDOWN | VM_READ | VM_WRITE | \ - VM_EXEC | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC) +#define VM_STACK_DEFAULT_FLAGS (VM_GROWSDOWN | VM_DATA_FLAGS_EXEC) #endif #endif diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c index 33b0e20df7fc..1a2d8a50dac4 100644 --- a/arch/x86/xen/setup.c +++ b/arch/x86/xen/setup.c @@ -985,7 +985,7 @@ void xen_enable_syscall(void) #endif /* CONFIG_X86_64 */ } -void __init xen_pvmmu_arch_setup(void) +static void __init xen_pvmmu_arch_setup(void) { HYPERVISOR_vm_assist(VMASST_CMD_enable, VMASST_TYPE_4gb_segments); HYPERVISOR_vm_assist(VMASST_CMD_enable, VMASST_TYPE_writable_pagetables); diff --git a/arch/x86/xen/xen-head.S b/arch/x86/xen/xen-head.S index 7d1c4fcbe8f7..1ba601df3a37 100644 --- a/arch/x86/xen/xen-head.S +++ b/arch/x86/xen/xen-head.S @@ -38,7 +38,7 @@ SYM_CODE_START(startup_xen) #ifdef CONFIG_X86_64 mov initial_stack(%rip), %rsp #else - mov pa(initial_stack), %esp + mov initial_stack, %esp #endif #ifdef CONFIG_X86_64 |