diff options
Diffstat (limited to 'arch/x86')
216 files changed, 8115 insertions, 2971 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index f9920f1341c8..67745ceab0db 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -85,6 +85,7 @@ config X86 select ARCH_HAS_PMEM_API if X86_64 select ARCH_HAS_PTE_DEVMAP if X86_64 select ARCH_HAS_PTE_SPECIAL + select ARCH_HAS_NONLEAF_PMD_YOUNG if PGTABLE_LEVELS > 2 select ARCH_HAS_UACCESS_FLUSHCACHE if X86_64 select ARCH_HAS_COPY_MC if X86_64 select ARCH_HAS_SET_MEMORY @@ -107,6 +108,8 @@ config X86 select ARCH_SUPPORTS_PAGE_TABLE_CHECK if X86_64 select ARCH_SUPPORTS_NUMA_BALANCING if X86_64 select ARCH_SUPPORTS_KMAP_LOCAL_FORCE_MAP if NR_CPUS <= 4096 + select ARCH_SUPPORTS_CFI_CLANG if X86_64 + select ARCH_USES_CFI_TRAPS if X86_64 && CFI_CLANG select ARCH_SUPPORTS_LTO_CLANG select ARCH_SUPPORTS_LTO_CLANG_THIN select ARCH_USE_BUILTIN_BSWAP @@ -128,7 +131,9 @@ config X86 select CLKEVT_I8253 select CLOCKSOURCE_VALIDATE_LAST_CYCLE select CLOCKSOURCE_WATCHDOG - select DCACHE_WORD_ACCESS + # Word-size accesses may read uninitialized data past the trailing \0 + # in strings and cause false KMSAN reports. + select DCACHE_WORD_ACCESS if !KMSAN select DYNAMIC_SIGFRAME select EDAC_ATOMIC_SCRUB select EDAC_SUPPORT @@ -166,6 +171,7 @@ config X86 select HAVE_ARCH_KASAN if X86_64 select HAVE_ARCH_KASAN_VMALLOC if X86_64 select HAVE_ARCH_KFENCE + select HAVE_ARCH_KMSAN if X86_64 select HAVE_ARCH_KGDB select HAVE_ARCH_MMAP_RND_BITS if MMU select HAVE_ARCH_MMAP_RND_COMPAT_BITS if MMU && COMPAT @@ -257,6 +263,7 @@ config X86 select HAVE_STATIC_CALL_INLINE if HAVE_OBJTOOL select HAVE_PREEMPT_DYNAMIC_CALL select HAVE_RSEQ + select HAVE_RUST if X86_64 select HAVE_SYSCALL_TRACEPOINTS select HAVE_UACCESS_VALIDATION if HAVE_OBJTOOL select HAVE_UNSTABLE_SCHED_CLOCK @@ -284,6 +291,7 @@ config X86 select PROC_PID_ARCH_STATUS if PROC_FS select HAVE_ARCH_NODE_DEV_GROUP if X86_SGX imply IMA_SECURE_AND_OR_TRUSTED_BOOT if EFI + select HAVE_DYNAMIC_FTRACE_NO_PATCHABLE config INSTRUCTION_DECODER def_bool y @@ -324,6 +332,10 @@ config GENERIC_ISA_DMA def_bool y depends on ISA_DMA_API +config GENERIC_CSUM + bool + default y if KMSAN || KASAN + config GENERIC_BUG def_bool y depends on BUG @@ -448,6 +460,11 @@ config X86_X2APIC This allows 32-bit apic IDs (so it can support very large systems), and accesses the local apic via MSRs not via mmio. + Some Intel systems circa 2022 and later are locked into x2APIC mode + and can not fall back to the legacy APIC modes if SGX or TDX are + enabled in the BIOS. They will be unable to boot without enabling + this option. + If you don't know what to do here, say N. config X86_MPPARSE @@ -1919,7 +1936,7 @@ endchoice config X86_SGX bool "Software Guard eXtensions (SGX)" - depends on X86_64 && CPU_SUP_INTEL + depends on X86_64 && CPU_SUP_INTEL && X86_X2APIC depends on CRYPTO=y depends on CRYPTO_SHA256=y select SRCU @@ -1956,7 +1973,6 @@ config EFI config EFI_STUB bool "EFI stub support" depends on EFI - depends on $(cc-option,-mabi=ms) || X86_32 select RELOCATABLE help This kernel feature allows a bzImage to be loaded directly @@ -2569,7 +2585,7 @@ menuconfig APM 1) make sure that you have enough swap space and that it is enabled. - 2) pass the "no-hlt" option to the kernel + 2) pass the "idle=poll" option to the kernel 3) switch on floating point emulation in the kernel and pass the "no387" option to the kernel 4) pass the "floppy=nodma" option to the kernel diff --git a/arch/x86/Makefile b/arch/x86/Makefile index 7854685c5f25..415a5d138de4 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -68,6 +68,7 @@ export BITS # https://gcc.gnu.org/bugzilla/show_bug.cgi?id=53383 # KBUILD_CFLAGS += -mno-sse -mno-mmx -mno-sse2 -mno-3dnow -mno-avx +KBUILD_RUSTFLAGS += -Ctarget-feature=-sse,-sse2,-sse3,-ssse3,-sse4.1,-sse4.2,-avx,-avx2 ifeq ($(CONFIG_X86_KERNEL_IBT),y) # @@ -155,8 +156,17 @@ else cflags-$(CONFIG_GENERIC_CPU) += -mtune=generic KBUILD_CFLAGS += $(cflags-y) + rustflags-$(CONFIG_MK8) += -Ctarget-cpu=k8 + rustflags-$(CONFIG_MPSC) += -Ctarget-cpu=nocona + rustflags-$(CONFIG_MCORE2) += -Ctarget-cpu=core2 + rustflags-$(CONFIG_MATOM) += -Ctarget-cpu=atom + rustflags-$(CONFIG_GENERIC_CPU) += -Ztune-cpu=generic + KBUILD_RUSTFLAGS += $(rustflags-y) + KBUILD_CFLAGS += -mno-red-zone KBUILD_CFLAGS += -mcmodel=kernel + KBUILD_RUSTFLAGS += -Cno-redzone=y + KBUILD_RUSTFLAGS += -Ccode-model=kernel endif # @@ -234,11 +244,6 @@ archheaders: ### # Kernel objects -head-y := arch/x86/kernel/head_$(BITS).o -head-y += arch/x86/kernel/head$(BITS).o -head-y += arch/x86/kernel/ebda.o -head-y += arch/x86/kernel/platform-quirks.o - libs-y += arch/x86/lib/ # drivers-y are linked after core-y @@ -286,10 +291,6 @@ vdso_install: archprepare: checkbin checkbin: -ifndef CONFIG_CC_HAS_ASM_GOTO - @echo Compiler lacks asm-goto support. - @exit 1 -endif ifdef CONFIG_RETPOLINE ifeq ($(RETPOLINE_CFLAGS),) @echo "You are building kernel with non-retpoline compiler." >&2 diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile index ffec8bb01ba8..9e38ffaadb5d 100644 --- a/arch/x86/boot/Makefile +++ b/arch/x86/boot/Makefile @@ -12,6 +12,7 @@ # Sanitizer runtimes are unavailable and cannot be linked for early boot code. KASAN_SANITIZE := n KCSAN_SANITIZE := n +KMSAN_SANITIZE := n OBJECT_FILES_NON_STANDARD := y # Kernel does not boot with kcov instrumentation here. @@ -82,7 +83,7 @@ cmd_image = $(obj)/tools/build $(obj)/setup.bin $(obj)/vmlinux.bin \ $(obj)/bzImage: $(obj)/setup.bin $(obj)/vmlinux.bin $(obj)/tools/build FORCE $(call if_changed,image) - @$(kecho) 'Kernel: $@ is ready' ' (#'`cat .version`')' + @$(kecho) 'Kernel: $@ is ready' ' (#'$(or $(KBUILD_BUILD_VERSION),`cat .version`)')' OBJCOPYFLAGS_vmlinux.bin := -O binary -R .note -R .comment -S $(obj)/vmlinux.bin: $(obj)/compressed/vmlinux FORCE diff --git a/arch/x86/boot/bitops.h b/arch/x86/boot/bitops.h index 02e1dea11d94..8518ae214c9b 100644 --- a/arch/x86/boot/bitops.h +++ b/arch/x86/boot/bitops.h @@ -19,13 +19,13 @@ static inline bool constant_test_bit(int nr, const void *addr) { - const u32 *p = (const u32 *)addr; + const u32 *p = addr; return ((1UL << (nr & 31)) & (p[nr >> 5])) != 0; } static inline bool variable_test_bit(int nr, const void *addr) { bool v; - const u32 *p = (const u32 *)addr; + const u32 *p = addr; asm("btl %2,%1" CC_SET(c) : CC_OUT(c) (v) : "m" (*p), "Ir" (nr)); return v; diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile index 35ce1a64068b..3a261abb6d15 100644 --- a/arch/x86/boot/compressed/Makefile +++ b/arch/x86/boot/compressed/Makefile @@ -20,6 +20,7 @@ # Sanitizer runtimes are unavailable and cannot be linked for early boot code. KASAN_SANITIZE := n KCSAN_SANITIZE := n +KMSAN_SANITIZE := n OBJECT_FILES_NON_STANDARD := y # Prevents link failures: __sanitizer_cov_trace_pc() is not linked in. diff --git a/arch/x86/boot/compressed/kaslr.c b/arch/x86/boot/compressed/kaslr.c index 4a3f223973f4..e476bcbd9b42 100644 --- a/arch/x86/boot/compressed/kaslr.c +++ b/arch/x86/boot/compressed/kaslr.c @@ -29,6 +29,7 @@ #include <linux/uts.h> #include <linux/utsname.h> #include <linux/ctype.h> +#include <generated/utsversion.h> #include <generated/utsrelease.h> #define _SETUP diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h index 4910bf230d7b..62208ec04ca4 100644 --- a/arch/x86/boot/compressed/misc.h +++ b/arch/x86/boot/compressed/misc.h @@ -132,7 +132,17 @@ void snp_set_page_private(unsigned long paddr); void snp_set_page_shared(unsigned long paddr); void sev_prep_identity_maps(unsigned long top_level_pgt); #else -static inline void sev_enable(struct boot_params *bp) { } +static inline void sev_enable(struct boot_params *bp) +{ + /* + * bp->cc_blob_address should only be set by boot/compressed kernel. + * Initialize it to 0 unconditionally (thus here in this stub too) to + * ensure that uninitialized values from buggy bootloaders aren't + * propagated. + */ + if (bp) + bp->cc_blob_address = 0; +} static inline void sev_es_shutdown_ghcb(void) { } static inline bool sev_es_check_ghcb_fault(unsigned long address) { diff --git a/arch/x86/boot/compressed/sev.c b/arch/x86/boot/compressed/sev.c index 52f989f6acc2..c93930d5ccbd 100644 --- a/arch/x86/boot/compressed/sev.c +++ b/arch/x86/boot/compressed/sev.c @@ -277,6 +277,14 @@ void sev_enable(struct boot_params *bp) bool snp; /* + * bp->cc_blob_address should only be set by boot/compressed kernel. + * Initialize it to 0 to ensure that uninitialized values from + * buggy bootloaders aren't propagated. + */ + if (bp) + bp->cc_blob_address = 0; + + /* * Setup/preliminary detection of SNP. This will be sanity-checked * against CPUID/MSR values later. */ diff --git a/arch/x86/boot/version.c b/arch/x86/boot/version.c index a1aaaf6c06a6..945383f0f606 100644 --- a/arch/x86/boot/version.c +++ b/arch/x86/boot/version.c @@ -11,6 +11,7 @@ */ #include "boot.h" +#include <generated/utsversion.h> #include <generated/utsrelease.h> #include <generated/compile.h> diff --git a/arch/x86/coco/tdx/tdx.c b/arch/x86/coco/tdx/tdx.c index 928dcf7a20d9..b8998cf0508a 100644 --- a/arch/x86/coco/tdx/tdx.c +++ b/arch/x86/coco/tdx/tdx.c @@ -34,6 +34,8 @@ #define VE_GET_PORT_NUM(e) ((e) >> 16) #define VE_IS_IO_STRING(e) ((e) & BIT(4)) +#define ATTR_SEPT_VE_DISABLE BIT(28) + /* * Wrapper for standard use of __tdx_hypercall with no output aside from * return code. @@ -98,10 +100,11 @@ static inline void tdx_module_call(u64 fn, u64 rcx, u64 rdx, u64 r8, u64 r9, panic("TDCALL %lld failed (Buggy TDX module!)\n", fn); } -static u64 get_cc_mask(void) +static void tdx_parse_tdinfo(u64 *cc_mask) { struct tdx_module_output out; unsigned int gpa_width; + u64 td_attr; /* * TDINFO TDX module call is used to get the TD execution environment @@ -109,19 +112,27 @@ static u64 get_cc_mask(void) * information, etc. More details about the ABI can be found in TDX * Guest-Host-Communication Interface (GHCI), section 2.4.2 TDCALL * [TDG.VP.INFO]. + */ + tdx_module_call(TDX_GET_INFO, 0, 0, 0, 0, &out); + + /* + * The highest bit of a guest physical address is the "sharing" bit. + * Set it for shared pages and clear it for private pages. * * The GPA width that comes out of this call is critical. TDX guests * can not meaningfully run without it. */ - tdx_module_call(TDX_GET_INFO, 0, 0, 0, 0, &out); - gpa_width = out.rcx & GENMASK(5, 0); + *cc_mask = BIT_ULL(gpa_width - 1); /* - * The highest bit of a guest physical address is the "sharing" bit. - * Set it for shared pages and clear it for private pages. + * The kernel can not handle #VE's when accessing normal kernel + * memory. Ensure that no #VE will be delivered for accesses to + * TD-private memory. Only VMM-shared memory (MMIO) will #VE. */ - return BIT_ULL(gpa_width - 1); + td_attr = out.rdx; + if (!(td_attr & ATTR_SEPT_VE_DISABLE)) + panic("TD misconfiguration: SEPT_VE_DISABLE attibute must be set.\n"); } /* @@ -758,7 +769,7 @@ void __init tdx_early_init(void) setup_force_cpu_cap(X86_FEATURE_TDX_GUEST); cc_set_vendor(CC_VENDOR_INTEL); - cc_mask = get_cc_mask(); + tdx_parse_tdinfo(&cc_mask); cc_set_mask(cc_mask); /* diff --git a/arch/x86/configs/i386_defconfig b/arch/x86/configs/i386_defconfig index 7207219509f6..3cf34912abfe 100644 --- a/arch/x86/configs/i386_defconfig +++ b/arch/x86/configs/i386_defconfig @@ -27,7 +27,6 @@ CONFIG_CGROUP_MISC=y CONFIG_CGROUP_DEBUG=y CONFIG_BLK_DEV_INITRD=y CONFIG_KALLSYMS_ALL=y -# CONFIG_COMPAT_BRK is not set CONFIG_PROFILING=y CONFIG_SMP=y CONFIG_HYPERVISOR_GUEST=y @@ -44,6 +43,7 @@ CONFIG_EFI_STUB=y CONFIG_HZ_1000=y CONFIG_KEXEC=y CONFIG_CRASH_DUMP=y +# CONFIG_RETHUNK is not set CONFIG_HIBERNATION=y CONFIG_PM_DEBUG=y CONFIG_PM_TRACE_RTC=y @@ -62,6 +62,7 @@ CONFIG_BLK_CGROUP_IOLATENCY=y CONFIG_BLK_CGROUP_IOCOST=y CONFIG_BLK_CGROUP_IOPRIO=y CONFIG_BINFMT_MISC=y +# CONFIG_COMPAT_BRK is not set CONFIG_NET=y CONFIG_PACKET=y CONFIG_UNIX=y @@ -269,9 +270,10 @@ CONFIG_SECURITY_SELINUX=y CONFIG_SECURITY_SELINUX_BOOTPARAM=y CONFIG_SECURITY_SELINUX_DISABLE=y CONFIG_PRINTK_TIME=y +CONFIG_DEBUG_KERNEL=y CONFIG_FRAME_WARN=1024 CONFIG_MAGIC_SYSRQ=y -CONFIG_DEBUG_KERNEL=y +CONFIG_DEBUG_WX=y CONFIG_DEBUG_STACK_USAGE=y # CONFIG_SCHED_DEBUG is not set CONFIG_SCHEDSTATS=y diff --git a/arch/x86/configs/x86_64_defconfig b/arch/x86/configs/x86_64_defconfig index 5ce67b73e218..27759236fd60 100644 --- a/arch/x86/configs/x86_64_defconfig +++ b/arch/x86/configs/x86_64_defconfig @@ -26,7 +26,6 @@ CONFIG_CGROUP_MISC=y CONFIG_CGROUP_DEBUG=y CONFIG_BLK_DEV_INITRD=y CONFIG_KALLSYMS_ALL=y -# CONFIG_COMPAT_BRK is not set CONFIG_PROFILING=y CONFIG_SMP=y CONFIG_HYPERVISOR_GUEST=y @@ -62,6 +61,7 @@ CONFIG_BLK_CGROUP_IOLATENCY=y CONFIG_BLK_CGROUP_IOCOST=y CONFIG_BLK_CGROUP_IOPRIO=y CONFIG_BINFMT_MISC=y +# CONFIG_COMPAT_BRK is not set CONFIG_NET=y CONFIG_PACKET=y CONFIG_UNIX=y @@ -267,8 +267,9 @@ CONFIG_SECURITY_SELINUX=y CONFIG_SECURITY_SELINUX_BOOTPARAM=y CONFIG_SECURITY_SELINUX_DISABLE=y CONFIG_PRINTK_TIME=y -CONFIG_MAGIC_SYSRQ=y CONFIG_DEBUG_KERNEL=y +CONFIG_MAGIC_SYSRQ=y +CONFIG_DEBUG_WX=y CONFIG_DEBUG_STACK_USAGE=y # CONFIG_SCHED_DEBUG is not set CONFIG_SCHEDSTATS=y diff --git a/arch/x86/configs/xen.config b/arch/x86/configs/xen.config index d9fc7139fd46..581296255b39 100644 --- a/arch/x86/configs/xen.config +++ b/arch/x86/configs/xen.config @@ -14,7 +14,6 @@ CONFIG_CPU_FREQ=y # x86 xen specific config options CONFIG_XEN_PVH=y -CONFIG_XEN_MAX_DOMAIN_MEMORY=500 CONFIG_XEN_SAVE_RESTORE=y # CONFIG_XEN_DEBUG_FS is not set CONFIG_XEN_MCE_LOG=y diff --git a/arch/x86/crypto/Kconfig b/arch/x86/crypto/Kconfig new file mode 100644 index 000000000000..71c4c473d34b --- /dev/null +++ b/arch/x86/crypto/Kconfig @@ -0,0 +1,484 @@ +# SPDX-License-Identifier: GPL-2.0 + +menu "Accelerated Cryptographic Algorithms for CPU (x86)" + +config CRYPTO_CURVE25519_X86 + tristate "Public key crypto: Curve25519 (ADX)" + depends on X86 && 64BIT + select CRYPTO_LIB_CURVE25519_GENERIC + select CRYPTO_ARCH_HAVE_LIB_CURVE25519 + help + Curve25519 algorithm + + Architecture: x86_64 using: + - ADX (large integer arithmetic) + +config CRYPTO_AES_NI_INTEL + tristate "Ciphers: AES, modes: ECB, CBC, CTS, CTR, XTR, XTS, GCM (AES-NI)" + depends on X86 + select CRYPTO_AEAD + select CRYPTO_LIB_AES + select CRYPTO_ALGAPI + select CRYPTO_SKCIPHER + select CRYPTO_SIMD + help + Block cipher: AES cipher algorithms + AEAD cipher: AES with GCM + Length-preserving ciphers: AES with ECB, CBC, CTS, CTR, XTR, XTS + + Architecture: x86 (32-bit and 64-bit) using: + - AES-NI (AES new instructions) + +config CRYPTO_BLOWFISH_X86_64 + tristate "Ciphers: Blowfish, modes: ECB, CBC" + depends on X86 && 64BIT + select CRYPTO_SKCIPHER + select CRYPTO_BLOWFISH_COMMON + imply CRYPTO_CTR + help + Block cipher: Blowfish cipher algorithm + Length-preserving ciphers: Blowfish with ECB and CBC modes + + Architecture: x86_64 + +config CRYPTO_CAMELLIA_X86_64 + tristate "Ciphers: Camellia with modes: ECB, CBC" + depends on X86 && 64BIT + select CRYPTO_SKCIPHER + imply CRYPTO_CTR + help + Block cipher: Camellia cipher algorithms + Length-preserving ciphers: Camellia with ECB and CBC modes + + Architecture: x86_64 + +config CRYPTO_CAMELLIA_AESNI_AVX_X86_64 + tristate "Ciphers: Camellia with modes: ECB, CBC (AES-NI/AVX)" + depends on X86 && 64BIT + select CRYPTO_SKCIPHER + select CRYPTO_CAMELLIA_X86_64 + select CRYPTO_SIMD + imply CRYPTO_XTS + help + Length-preserving ciphers: Camellia with ECB and CBC modes + + Architecture: x86_64 using: + - AES-NI (AES New Instructions) + - AVX (Advanced Vector Extensions) + +config CRYPTO_CAMELLIA_AESNI_AVX2_X86_64 + tristate "Ciphers: Camellia with modes: ECB, CBC (AES-NI/AVX2)" + depends on X86 && 64BIT + select CRYPTO_CAMELLIA_AESNI_AVX_X86_64 + help + Length-preserving ciphers: Camellia with ECB and CBC modes + + Architecture: x86_64 using: + - AES-NI (AES New Instructions) + - AVX2 (Advanced Vector Extensions 2) + +config CRYPTO_CAST5_AVX_X86_64 + tristate "Ciphers: CAST5 with modes: ECB, CBC (AVX)" + depends on X86 && 64BIT + select CRYPTO_SKCIPHER + select CRYPTO_CAST5 + select CRYPTO_CAST_COMMON + select CRYPTO_SIMD + imply CRYPTO_CTR + help + Length-preserving ciphers: CAST5 (CAST-128) cipher algorithm + (RFC2144) with ECB and CBC modes + + Architecture: x86_64 using: + - AVX (Advanced Vector Extensions) + + Processes 16 blocks in parallel. + +config CRYPTO_CAST6_AVX_X86_64 + tristate "Ciphers: CAST6 with modes: ECB, CBC (AVX)" + depends on X86 && 64BIT + select CRYPTO_SKCIPHER + select CRYPTO_CAST6 + select CRYPTO_CAST_COMMON + select CRYPTO_SIMD + imply CRYPTO_XTS + imply CRYPTO_CTR + help + Length-preserving ciphers: CAST6 (CAST-256) cipher algorithm + (RFC2612) with ECB and CBC modes + + Architecture: x86_64 using: + - AVX (Advanced Vector Extensions) + + Processes eight blocks in parallel. + +config CRYPTO_DES3_EDE_X86_64 + tristate "Ciphers: Triple DES EDE with modes: ECB, CBC" + depends on X86 && 64BIT + select CRYPTO_SKCIPHER + select CRYPTO_LIB_DES + imply CRYPTO_CTR + help + Block cipher: Triple DES EDE (FIPS 46-3) cipher algorithm + Length-preserving ciphers: Triple DES EDE with ECB and CBC modes + + Architecture: x86_64 + + Processes one or three blocks in parallel. + +config CRYPTO_SERPENT_SSE2_X86_64 + tristate "Ciphers: Serpent with modes: ECB, CBC (SSE2)" + depends on X86 && 64BIT + select CRYPTO_SKCIPHER + select CRYPTO_SERPENT + select CRYPTO_SIMD + imply CRYPTO_CTR + help + Length-preserving ciphers: Serpent cipher algorithm + with ECB and CBC modes + + Architecture: x86_64 using: + - SSE2 (Streaming SIMD Extensions 2) + + Processes eight blocks in parallel. + +config CRYPTO_SERPENT_SSE2_586 + tristate "Ciphers: Serpent with modes: ECB, CBC (32-bit with SSE2)" + depends on X86 && !64BIT + select CRYPTO_SKCIPHER + select CRYPTO_SERPENT + select CRYPTO_SIMD + imply CRYPTO_CTR + help + Length-preserving ciphers: Serpent cipher algorithm + with ECB and CBC modes + + Architecture: x86 (32-bit) using: + - SSE2 (Streaming SIMD Extensions 2) + + Processes four blocks in parallel. + +config CRYPTO_SERPENT_AVX_X86_64 + tristate "Ciphers: Serpent with modes: ECB, CBC (AVX)" + depends on X86 && 64BIT + select CRYPTO_SKCIPHER + select CRYPTO_SERPENT + select CRYPTO_SIMD + imply CRYPTO_XTS + imply CRYPTO_CTR + help + Length-preserving ciphers: Serpent cipher algorithm + with ECB and CBC modes + + Architecture: x86_64 using: + - AVX (Advanced Vector Extensions) + + Processes eight blocks in parallel. + +config CRYPTO_SERPENT_AVX2_X86_64 + tristate "Ciphers: Serpent with modes: ECB, CBC (AVX2)" + depends on X86 && 64BIT + select CRYPTO_SERPENT_AVX_X86_64 + help + Length-preserving ciphers: Serpent cipher algorithm + with ECB and CBC modes + + Architecture: x86_64 using: + - AVX2 (Advanced Vector Extensions 2) + + Processes 16 blocks in parallel. + +config CRYPTO_SM4_AESNI_AVX_X86_64 + tristate "Ciphers: SM4 with modes: ECB, CBC, CFB, CTR (AES-NI/AVX)" + depends on X86 && 64BIT + select CRYPTO_SKCIPHER + select CRYPTO_SIMD + select CRYPTO_ALGAPI + select CRYPTO_SM4 + help + Length-preserving ciphers: SM4 cipher algorithms + (OSCCA GB/T 32907-2016) with ECB, CBC, CFB, and CTR modes + + Architecture: x86_64 using: + - AES-NI (AES New Instructions) + - AVX (Advanced Vector Extensions) + + Through two affine transforms, + we can use the AES S-Box to simulate the SM4 S-Box to achieve the + effect of instruction acceleration. + + If unsure, say N. + +config CRYPTO_SM4_AESNI_AVX2_X86_64 + tristate "Ciphers: SM4 with modes: ECB, CBC, CFB, CTR (AES-NI/AVX2)" + depends on X86 && 64BIT + select CRYPTO_SKCIPHER + select CRYPTO_SIMD + select CRYPTO_ALGAPI + select CRYPTO_SM4 + select CRYPTO_SM4_AESNI_AVX_X86_64 + help + Length-preserving ciphers: SM4 cipher algorithms + (OSCCA GB/T 32907-2016) with ECB, CBC, CFB, and CTR modes + + Architecture: x86_64 using: + - AES-NI (AES New Instructions) + - AVX2 (Advanced Vector Extensions 2) + + Through two affine transforms, + we can use the AES S-Box to simulate the SM4 S-Box to achieve the + effect of instruction acceleration. + + If unsure, say N. + +config CRYPTO_TWOFISH_586 + tristate "Ciphers: Twofish (32-bit)" + depends on (X86 || UML_X86) && !64BIT + select CRYPTO_ALGAPI + select CRYPTO_TWOFISH_COMMON + imply CRYPTO_CTR + help + Block cipher: Twofish cipher algorithm + + Architecture: x86 (32-bit) + +config CRYPTO_TWOFISH_X86_64 + tristate "Ciphers: Twofish" + depends on (X86 || UML_X86) && 64BIT + select CRYPTO_ALGAPI + select CRYPTO_TWOFISH_COMMON + imply CRYPTO_CTR + help + Block cipher: Twofish cipher algorithm + + Architecture: x86_64 + +config CRYPTO_TWOFISH_X86_64_3WAY + tristate "Ciphers: Twofish with modes: ECB, CBC (3-way parallel)" + depends on X86 && 64BIT + select CRYPTO_SKCIPHER + select CRYPTO_TWOFISH_COMMON + select CRYPTO_TWOFISH_X86_64 + help + Length-preserving cipher: Twofish cipher algorithm + with ECB and CBC modes + + Architecture: x86_64 + + Processes three blocks in parallel, better utilizing resources of + out-of-order CPUs. + +config CRYPTO_TWOFISH_AVX_X86_64 + tristate "Ciphers: Twofish with modes: ECB, CBC (AVX)" + depends on X86 && 64BIT + select CRYPTO_SKCIPHER + select CRYPTO_SIMD + select CRYPTO_TWOFISH_COMMON + select CRYPTO_TWOFISH_X86_64 + select CRYPTO_TWOFISH_X86_64_3WAY + imply CRYPTO_XTS + help + Length-preserving cipher: Twofish cipher algorithm + with ECB and CBC modes + + Architecture: x86_64 using: + - AVX (Advanced Vector Extensions) + + Processes eight blocks in parallel. + +config CRYPTO_ARIA_AESNI_AVX_X86_64 + tristate "Ciphers: ARIA with modes: ECB, CTR (AES-NI/AVX/GFNI)" + depends on X86 && 64BIT + select CRYPTO_SKCIPHER + select CRYPTO_SIMD + select CRYPTO_ALGAPI + select CRYPTO_ARIA + help + Length-preserving cipher: ARIA cipher algorithms + (RFC 5794) with ECB and CTR modes + + Architecture: x86_64 using: + - AES-NI (AES New Instructions) + - AVX (Advanced Vector Extensions) + - GFNI (Galois Field New Instructions) + + Processes 16 blocks in parallel. + +config CRYPTO_CHACHA20_X86_64 + tristate "Ciphers: ChaCha20, XChaCha20, XChaCha12 (SSSE3/AVX2/AVX-512VL)" + depends on X86 && 64BIT + select CRYPTO_SKCIPHER + select CRYPTO_LIB_CHACHA_GENERIC + select CRYPTO_ARCH_HAVE_LIB_CHACHA + help + Length-preserving ciphers: ChaCha20, XChaCha20, and XChaCha12 + stream cipher algorithms + + Architecture: x86_64 using: + - SSSE3 (Supplemental SSE3) + - AVX2 (Advanced Vector Extensions 2) + - AVX-512VL (Advanced Vector Extensions-512VL) + +config CRYPTO_AEGIS128_AESNI_SSE2 + tristate "AEAD ciphers: AEGIS-128 (AES-NI/SSE2)" + depends on X86 && 64BIT + select CRYPTO_AEAD + select CRYPTO_SIMD + help + AEGIS-128 AEAD algorithm + + Architecture: x86_64 using: + - AES-NI (AES New Instructions) + - SSE2 (Streaming SIMD Extensions 2) + +config CRYPTO_NHPOLY1305_SSE2 + tristate "Hash functions: NHPoly1305 (SSE2)" + depends on X86 && 64BIT + select CRYPTO_NHPOLY1305 + help + NHPoly1305 hash function for Adiantum + + Architecture: x86_64 using: + - SSE2 (Streaming SIMD Extensions 2) + +config CRYPTO_NHPOLY1305_AVX2 + tristate "Hash functions: NHPoly1305 (AVX2)" + depends on X86 && 64BIT + select CRYPTO_NHPOLY1305 + help + NHPoly1305 hash function for Adiantum + + Architecture: x86_64 using: + - AVX2 (Advanced Vector Extensions 2) + +config CRYPTO_BLAKE2S_X86 + bool "Hash functions: BLAKE2s (SSSE3/AVX-512)" + depends on X86 && 64BIT + select CRYPTO_LIB_BLAKE2S_GENERIC + select CRYPTO_ARCH_HAVE_LIB_BLAKE2S + help + BLAKE2s cryptographic hash function (RFC 7693) + + Architecture: x86_64 using: + - SSSE3 (Supplemental SSE3) + - AVX-512 (Advanced Vector Extensions-512) + +config CRYPTO_POLYVAL_CLMUL_NI + tristate "Hash functions: POLYVAL (CLMUL-NI)" + depends on X86 && 64BIT + select CRYPTO_POLYVAL + help + POLYVAL hash function for HCTR2 + + Architecture: x86_64 using: + - CLMUL-NI (carry-less multiplication new instructions) + +config CRYPTO_POLY1305_X86_64 + tristate "Hash functions: Poly1305 (SSE2/AVX2)" + depends on X86 && 64BIT + select CRYPTO_LIB_POLY1305_GENERIC + select CRYPTO_ARCH_HAVE_LIB_POLY1305 + help + Poly1305 authenticator algorithm (RFC7539) + + Architecture: x86_64 using: + - SSE2 (Streaming SIMD Extensions 2) + - AVX2 (Advanced Vector Extensions 2) + +config CRYPTO_SHA1_SSSE3 + tristate "Hash functions: SHA-1 (SSSE3/AVX/AVX2/SHA-NI)" + depends on X86 && 64BIT + select CRYPTO_SHA1 + select CRYPTO_HASH + help + SHA-1 secure hash algorithm (FIPS 180) + + Architecture: x86_64 using: + - SSSE3 (Supplemental SSE3) + - AVX (Advanced Vector Extensions) + - AVX2 (Advanced Vector Extensions 2) + - SHA-NI (SHA Extensions New Instructions) + +config CRYPTO_SHA256_SSSE3 + tristate "Hash functions: SHA-224 and SHA-256 (SSSE3/AVX/AVX2/SHA-NI)" + depends on X86 && 64BIT + select CRYPTO_SHA256 + select CRYPTO_HASH + help + SHA-224 and SHA-256 secure hash algorithms (FIPS 180) + + Architecture: x86_64 using: + - SSSE3 (Supplemental SSE3) + - AVX (Advanced Vector Extensions) + - AVX2 (Advanced Vector Extensions 2) + - SHA-NI (SHA Extensions New Instructions) + +config CRYPTO_SHA512_SSSE3 + tristate "Hash functions: SHA-384 and SHA-512 (SSSE3/AVX/AVX2)" + depends on X86 && 64BIT + select CRYPTO_SHA512 + select CRYPTO_HASH + help + SHA-384 and SHA-512 secure hash algorithms (FIPS 180) + + Architecture: x86_64 using: + - SSSE3 (Supplemental SSE3) + - AVX (Advanced Vector Extensions) + - AVX2 (Advanced Vector Extensions 2) + +config CRYPTO_SM3_AVX_X86_64 + tristate "Hash functions: SM3 (AVX)" + depends on X86 && 64BIT + select CRYPTO_HASH + select CRYPTO_SM3 + help + SM3 secure hash function as defined by OSCCA GM/T 0004-2012 SM3 + + Architecture: x86_64 using: + - AVX (Advanced Vector Extensions) + + If unsure, say N. + +config CRYPTO_GHASH_CLMUL_NI_INTEL + tristate "Hash functions: GHASH (CLMUL-NI)" + depends on X86 && 64BIT + select CRYPTO_CRYPTD + help + GCM GHASH hash function (NIST SP800-38D) + + Architecture: x86_64 using: + - CLMUL-NI (carry-less multiplication new instructions) + +config CRYPTO_CRC32C_INTEL + tristate "CRC32c (SSE4.2/PCLMULQDQ)" + depends on X86 + select CRYPTO_HASH + help + CRC32c CRC algorithm with the iSCSI polynomial (RFC 3385 and RFC 3720) + + Architecture: x86 (32-bit and 64-bit) using: + - SSE4.2 (Streaming SIMD Extensions 4.2) CRC32 instruction + - PCLMULQDQ (carry-less multiplication) + +config CRYPTO_CRC32_PCLMUL + tristate "CRC32 (PCLMULQDQ)" + depends on X86 + select CRYPTO_HASH + select CRC32 + help + CRC32 CRC algorithm (IEEE 802.3) + + Architecture: x86 (32-bit and 64-bit) using: + - PCLMULQDQ (carry-less multiplication) + +config CRYPTO_CRCT10DIF_PCLMUL + tristate "CRCT10DIF (PCLMULQDQ)" + depends on X86 && 64BIT && CRC_T10DIF + select CRYPTO_HASH + help + CRC16 CRC algorithm used for the T10 (SCSI) Data Integrity Field (DIF) + + Architecture: x86_64 using: + - PCLMULQDQ (carry-less multiplication) + +endmenu diff --git a/arch/x86/crypto/Makefile b/arch/x86/crypto/Makefile index 04d07ab744b2..3b1d701a4f6c 100644 --- a/arch/x86/crypto/Makefile +++ b/arch/x86/crypto/Makefile @@ -100,6 +100,9 @@ sm4-aesni-avx-x86_64-y := sm4-aesni-avx-asm_64.o sm4_aesni_avx_glue.o obj-$(CONFIG_CRYPTO_SM4_AESNI_AVX2_X86_64) += sm4-aesni-avx2-x86_64.o sm4-aesni-avx2-x86_64-y := sm4-aesni-avx2-asm_64.o sm4_aesni_avx2_glue.o +obj-$(CONFIG_CRYPTO_ARIA_AESNI_AVX_X86_64) += aria-aesni-avx-x86_64.o +aria-aesni-avx-x86_64-y := aria-aesni-avx-asm_64.o aria_aesni_avx_glue.o + quiet_cmd_perlasm = PERLASM $@ cmd_perlasm = $(PERL) $< > $@ $(obj)/%.S: $(src)/%.pl FORCE diff --git a/arch/x86/crypto/aria-aesni-avx-asm_64.S b/arch/x86/crypto/aria-aesni-avx-asm_64.S new file mode 100644 index 000000000000..c75fd7d015ed --- /dev/null +++ b/arch/x86/crypto/aria-aesni-avx-asm_64.S @@ -0,0 +1,1303 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * ARIA Cipher 16-way parallel algorithm (AVX) + * + * Copyright (c) 2022 Taehee Yoo <[email protected]> + * + */ + +#include <linux/linkage.h> +#include <asm/frame.h> + +/* struct aria_ctx: */ +#define enc_key 0 +#define dec_key 272 +#define rounds 544 + +/* register macros */ +#define CTX %rdi + + +#define BV8(a0, a1, a2, a3, a4, a5, a6, a7) \ + ( (((a0) & 1) << 0) | \ + (((a1) & 1) << 1) | \ + (((a2) & 1) << 2) | \ + (((a3) & 1) << 3) | \ + (((a4) & 1) << 4) | \ + (((a5) & 1) << 5) | \ + (((a6) & 1) << 6) | \ + (((a7) & 1) << 7) ) + +#define BM8X8(l0, l1, l2, l3, l4, l5, l6, l7) \ + ( ((l7) << (0 * 8)) | \ + ((l6) << (1 * 8)) | \ + ((l5) << (2 * 8)) | \ + ((l4) << (3 * 8)) | \ + ((l3) << (4 * 8)) | \ + ((l2) << (5 * 8)) | \ + ((l1) << (6 * 8)) | \ + ((l0) << (7 * 8)) ) + +#define inc_le128(x, minus_one, tmp) \ + vpcmpeqq minus_one, x, tmp; \ + vpsubq minus_one, x, x; \ + vpslldq $8, tmp, tmp; \ + vpsubq tmp, x, x; + +#define filter_8bit(x, lo_t, hi_t, mask4bit, tmp0) \ + vpand x, mask4bit, tmp0; \ + vpandn x, mask4bit, x; \ + vpsrld $4, x, x; \ + \ + vpshufb tmp0, lo_t, tmp0; \ + vpshufb x, hi_t, x; \ + vpxor tmp0, x, x; + +#define transpose_4x4(x0, x1, x2, x3, t1, t2) \ + vpunpckhdq x1, x0, t2; \ + vpunpckldq x1, x0, x0; \ + \ + vpunpckldq x3, x2, t1; \ + vpunpckhdq x3, x2, x2; \ + \ + vpunpckhqdq t1, x0, x1; \ + vpunpcklqdq t1, x0, x0; \ + \ + vpunpckhqdq x2, t2, x3; \ + vpunpcklqdq x2, t2, x2; + +#define byteslice_16x16b(a0, b0, c0, d0, \ + a1, b1, c1, d1, \ + a2, b2, c2, d2, \ + a3, b3, c3, d3, \ + st0, st1) \ + vmovdqu d2, st0; \ + vmovdqu d3, st1; \ + transpose_4x4(a0, a1, a2, a3, d2, d3); \ + transpose_4x4(b0, b1, b2, b3, d2, d3); \ + vmovdqu st0, d2; \ + vmovdqu st1, d3; \ + \ + vmovdqu a0, st0; \ + vmovdqu a1, st1; \ + transpose_4x4(c0, c1, c2, c3, a0, a1); \ + transpose_4x4(d0, d1, d2, d3, a0, a1); \ + \ + vmovdqu .Lshufb_16x16b, a0; \ + vmovdqu st1, a1; \ + vpshufb a0, a2, a2; \ + vpshufb a0, a3, a3; \ + vpshufb a0, b0, b0; \ + vpshufb a0, b1, b1; \ + vpshufb a0, b2, b2; \ + vpshufb a0, b3, b3; \ + vpshufb a0, a1, a1; \ + vpshufb a0, c0, c0; \ + vpshufb a0, c1, c1; \ + vpshufb a0, c2, c2; \ + vpshufb a0, c3, c3; \ + vpshufb a0, d0, d0; \ + vpshufb a0, d1, d1; \ + vpshufb a0, d2, d2; \ + vpshufb a0, d3, d3; \ + vmovdqu d3, st1; \ + vmovdqu st0, d3; \ + vpshufb a0, d3, a0; \ + vmovdqu d2, st0; \ + \ + transpose_4x4(a0, b0, c0, d0, d2, d3); \ + transpose_4x4(a1, b1, c1, d1, d2, d3); \ + vmovdqu st0, d2; \ + vmovdqu st1, d3; \ + \ + vmovdqu b0, st0; \ + vmovdqu b1, st1; \ + transpose_4x4(a2, b2, c2, d2, b0, b1); \ + transpose_4x4(a3, b3, c3, d3, b0, b1); \ + vmovdqu st0, b0; \ + vmovdqu st1, b1; \ + /* does not adjust output bytes inside vectors */ + +#define debyteslice_16x16b(a0, b0, c0, d0, \ + a1, b1, c1, d1, \ + a2, b2, c2, d2, \ + a3, b3, c3, d3, \ + st0, st1) \ + vmovdqu d2, st0; \ + vmovdqu d3, st1; \ + transpose_4x4(a0, a1, a2, a3, d2, d3); \ + transpose_4x4(b0, b1, b2, b3, d2, d3); \ + vmovdqu st0, d2; \ + vmovdqu st1, d3; \ + \ + vmovdqu a0, st0; \ + vmovdqu a1, st1; \ + transpose_4x4(c0, c1, c2, c3, a0, a1); \ + transpose_4x4(d0, d1, d2, d3, a0, a1); \ + \ + vmovdqu .Lshufb_16x16b, a0; \ + vmovdqu st1, a1; \ + vpshufb a0, a2, a2; \ + vpshufb a0, a3, a3; \ + vpshufb a0, b0, b0; \ + vpshufb a0, b1, b1; \ + vpshufb a0, b2, b2; \ + vpshufb a0, b3, b3; \ + vpshufb a0, a1, a1; \ + vpshufb a0, c0, c0; \ + vpshufb a0, c1, c1; \ + vpshufb a0, c2, c2; \ + vpshufb a0, c3, c3; \ + vpshufb a0, d0, d0; \ + vpshufb a0, d1, d1; \ + vpshufb a0, d2, d2; \ + vpshufb a0, d3, d3; \ + vmovdqu d3, st1; \ + vmovdqu st0, d3; \ + vpshufb a0, d3, a0; \ + vmovdqu d2, st0; \ + \ + transpose_4x4(c0, d0, a0, b0, d2, d3); \ + transpose_4x4(c1, d1, a1, b1, d2, d3); \ + vmovdqu st0, d2; \ + vmovdqu st1, d3; \ + \ + vmovdqu b0, st0; \ + vmovdqu b1, st1; \ + transpose_4x4(c2, d2, a2, b2, b0, b1); \ + transpose_4x4(c3, d3, a3, b3, b0, b1); \ + vmovdqu st0, b0; \ + vmovdqu st1, b1; \ + /* does not adjust output bytes inside vectors */ + +/* load blocks to registers and apply pre-whitening */ +#define inpack16_pre(x0, x1, x2, x3, \ + x4, x5, x6, x7, \ + y0, y1, y2, y3, \ + y4, y5, y6, y7, \ + rio) \ + vmovdqu (0 * 16)(rio), x0; \ + vmovdqu (1 * 16)(rio), x1; \ + vmovdqu (2 * 16)(rio), x2; \ + vmovdqu (3 * 16)(rio), x3; \ + vmovdqu (4 * 16)(rio), x4; \ + vmovdqu (5 * 16)(rio), x5; \ + vmovdqu (6 * 16)(rio), x6; \ + vmovdqu (7 * 16)(rio), x7; \ + vmovdqu (8 * 16)(rio), y0; \ + vmovdqu (9 * 16)(rio), y1; \ + vmovdqu (10 * 16)(rio), y2; \ + vmovdqu (11 * 16)(rio), y3; \ + vmovdqu (12 * 16)(rio), y4; \ + vmovdqu (13 * 16)(rio), y5; \ + vmovdqu (14 * 16)(rio), y6; \ + vmovdqu (15 * 16)(rio), y7; + +/* byteslice pre-whitened blocks and store to temporary memory */ +#define inpack16_post(x0, x1, x2, x3, \ + x4, x5, x6, x7, \ + y0, y1, y2, y3, \ + y4, y5, y6, y7, \ + mem_ab, mem_cd) \ + byteslice_16x16b(x0, x1, x2, x3, \ + x4, x5, x6, x7, \ + y0, y1, y2, y3, \ + y4, y5, y6, y7, \ + (mem_ab), (mem_cd)); \ + \ + vmovdqu x0, 0 * 16(mem_ab); \ + vmovdqu x1, 1 * 16(mem_ab); \ + vmovdqu x2, 2 * 16(mem_ab); \ + vmovdqu x3, 3 * 16(mem_ab); \ + vmovdqu x4, 4 * 16(mem_ab); \ + vmovdqu x5, 5 * 16(mem_ab); \ + vmovdqu x6, 6 * 16(mem_ab); \ + vmovdqu x7, 7 * 16(mem_ab); \ + vmovdqu y0, 0 * 16(mem_cd); \ + vmovdqu y1, 1 * 16(mem_cd); \ + vmovdqu y2, 2 * 16(mem_cd); \ + vmovdqu y3, 3 * 16(mem_cd); \ + vmovdqu y4, 4 * 16(mem_cd); \ + vmovdqu y5, 5 * 16(mem_cd); \ + vmovdqu y6, 6 * 16(mem_cd); \ + vmovdqu y7, 7 * 16(mem_cd); + +#define write_output(x0, x1, x2, x3, \ + x4, x5, x6, x7, \ + y0, y1, y2, y3, \ + y4, y5, y6, y7, \ + mem) \ + vmovdqu x0, 0 * 16(mem); \ + vmovdqu x1, 1 * 16(mem); \ + vmovdqu x2, 2 * 16(mem); \ + vmovdqu x3, 3 * 16(mem); \ + vmovdqu x4, 4 * 16(mem); \ + vmovdqu x5, 5 * 16(mem); \ + vmovdqu x6, 6 * 16(mem); \ + vmovdqu x7, 7 * 16(mem); \ + vmovdqu y0, 8 * 16(mem); \ + vmovdqu y1, 9 * 16(mem); \ + vmovdqu y2, 10 * 16(mem); \ + vmovdqu y3, 11 * 16(mem); \ + vmovdqu y4, 12 * 16(mem); \ + vmovdqu y5, 13 * 16(mem); \ + vmovdqu y6, 14 * 16(mem); \ + vmovdqu y7, 15 * 16(mem); \ + +#define aria_store_state_8way(x0, x1, x2, x3, \ + x4, x5, x6, x7, \ + mem_tmp, idx) \ + vmovdqu x0, ((idx + 0) * 16)(mem_tmp); \ + vmovdqu x1, ((idx + 1) * 16)(mem_tmp); \ + vmovdqu x2, ((idx + 2) * 16)(mem_tmp); \ + vmovdqu x3, ((idx + 3) * 16)(mem_tmp); \ + vmovdqu x4, ((idx + 4) * 16)(mem_tmp); \ + vmovdqu x5, ((idx + 5) * 16)(mem_tmp); \ + vmovdqu x6, ((idx + 6) * 16)(mem_tmp); \ + vmovdqu x7, ((idx + 7) * 16)(mem_tmp); + +#define aria_load_state_8way(x0, x1, x2, x3, \ + x4, x5, x6, x7, \ + mem_tmp, idx) \ + vmovdqu ((idx + 0) * 16)(mem_tmp), x0; \ + vmovdqu ((idx + 1) * 16)(mem_tmp), x1; \ + vmovdqu ((idx + 2) * 16)(mem_tmp), x2; \ + vmovdqu ((idx + 3) * 16)(mem_tmp), x3; \ + vmovdqu ((idx + 4) * 16)(mem_tmp), x4; \ + vmovdqu ((idx + 5) * 16)(mem_tmp), x5; \ + vmovdqu ((idx + 6) * 16)(mem_tmp), x6; \ + vmovdqu ((idx + 7) * 16)(mem_tmp), x7; + +#define aria_ark_8way(x0, x1, x2, x3, \ + x4, x5, x6, x7, \ + t0, rk, idx, round) \ + /* AddRoundKey */ \ + vpbroadcastb ((round * 16) + idx + 3)(rk), t0; \ + vpxor t0, x0, x0; \ + vpbroadcastb ((round * 16) + idx + 2)(rk), t0; \ + vpxor t0, x1, x1; \ + vpbroadcastb ((round * 16) + idx + 1)(rk), t0; \ + vpxor t0, x2, x2; \ + vpbroadcastb ((round * 16) + idx + 0)(rk), t0; \ + vpxor t0, x3, x3; \ + vpbroadcastb ((round * 16) + idx + 7)(rk), t0; \ + vpxor t0, x4, x4; \ + vpbroadcastb ((round * 16) + idx + 6)(rk), t0; \ + vpxor t0, x5, x5; \ + vpbroadcastb ((round * 16) + idx + 5)(rk), t0; \ + vpxor t0, x6, x6; \ + vpbroadcastb ((round * 16) + idx + 4)(rk), t0; \ + vpxor t0, x7, x7; + +#define aria_sbox_8way_gfni(x0, x1, x2, x3, \ + x4, x5, x6, x7, \ + t0, t1, t2, t3, \ + t4, t5, t6, t7) \ + vpbroadcastq .Ltf_s2_bitmatrix, t0; \ + vpbroadcastq .Ltf_inv_bitmatrix, t1; \ + vpbroadcastq .Ltf_id_bitmatrix, t2; \ + vpbroadcastq .Ltf_aff_bitmatrix, t3; \ + vpbroadcastq .Ltf_x2_bitmatrix, t4; \ + vgf2p8affineinvqb $(tf_s2_const), t0, x1, x1; \ + vgf2p8affineinvqb $(tf_s2_const), t0, x5, x5; \ + vgf2p8affineqb $(tf_inv_const), t1, x2, x2; \ + vgf2p8affineqb $(tf_inv_const), t1, x6, x6; \ + vgf2p8affineinvqb $0, t2, x2, x2; \ + vgf2p8affineinvqb $0, t2, x6, x6; \ + vgf2p8affineinvqb $(tf_aff_const), t3, x0, x0; \ + vgf2p8affineinvqb $(tf_aff_const), t3, x4, x4; \ + vgf2p8affineqb $(tf_x2_const), t4, x3, x3; \ + vgf2p8affineqb $(tf_x2_const), t4, x7, x7; \ + vgf2p8affineinvqb $0, t2, x3, x3; \ + vgf2p8affineinvqb $0, t2, x7, x7 + +#define aria_sbox_8way(x0, x1, x2, x3, \ + x4, x5, x6, x7, \ + t0, t1, t2, t3, \ + t4, t5, t6, t7) \ + vpxor t7, t7, t7; \ + vmovdqa .Linv_shift_row, t0; \ + vmovdqa .Lshift_row, t1; \ + vpbroadcastd .L0f0f0f0f, t6; \ + vmovdqa .Ltf_lo__inv_aff__and__s2, t2; \ + vmovdqa .Ltf_hi__inv_aff__and__s2, t3; \ + vmovdqa .Ltf_lo__x2__and__fwd_aff, t4; \ + vmovdqa .Ltf_hi__x2__and__fwd_aff, t5; \ + \ + vaesenclast t7, x0, x0; \ + vaesenclast t7, x4, x4; \ + vaesenclast t7, x1, x1; \ + vaesenclast t7, x5, x5; \ + vaesdeclast t7, x2, x2; \ + vaesdeclast t7, x6, x6; \ + \ + /* AES inverse shift rows */ \ + vpshufb t0, x0, x0; \ + vpshufb t0, x4, x4; \ + vpshufb t0, x1, x1; \ + vpshufb t0, x5, x5; \ + vpshufb t1, x3, x3; \ + vpshufb t1, x7, x7; \ + vpshufb t1, x2, x2; \ + vpshufb t1, x6, x6; \ + \ + /* affine transformation for S2 */ \ + filter_8bit(x1, t2, t3, t6, t0); \ + /* affine transformation for S2 */ \ + filter_8bit(x5, t2, t3, t6, t0); \ + \ + /* affine transformation for X2 */ \ + filter_8bit(x3, t4, t5, t6, t0); \ + /* affine transformation for X2 */ \ + filter_8bit(x7, t4, t5, t6, t0); \ + vaesdeclast t7, x3, x3; \ + vaesdeclast t7, x7, x7; + +#define aria_diff_m(x0, x1, x2, x3, \ + t0, t1, t2, t3) \ + /* T = rotr32(X, 8); */ \ + /* X ^= T */ \ + vpxor x0, x3, t0; \ + vpxor x1, x0, t1; \ + vpxor x2, x1, t2; \ + vpxor x3, x2, t3; \ + /* X = T ^ rotr(X, 16); */ \ + vpxor t2, x0, x0; \ + vpxor x1, t3, t3; \ + vpxor t0, x2, x2; \ + vpxor t1, x3, x1; \ + vmovdqu t3, x3; + +#define aria_diff_word(x0, x1, x2, x3, \ + x4, x5, x6, x7, \ + y0, y1, y2, y3, \ + y4, y5, y6, y7) \ + /* t1 ^= t2; */ \ + vpxor y0, x4, x4; \ + vpxor y1, x5, x5; \ + vpxor y2, x6, x6; \ + vpxor y3, x7, x7; \ + \ + /* t2 ^= t3; */ \ + vpxor y4, y0, y0; \ + vpxor y5, y1, y1; \ + vpxor y6, y2, y2; \ + vpxor y7, y3, y3; \ + \ + /* t0 ^= t1; */ \ + vpxor x4, x0, x0; \ + vpxor x5, x1, x1; \ + vpxor x6, x2, x2; \ + vpxor x7, x3, x3; \ + \ + /* t3 ^= t1; */ \ + vpxor x4, y4, y4; \ + vpxor x5, y5, y5; \ + vpxor x6, y6, y6; \ + vpxor x7, y7, y7; \ + \ + /* t2 ^= t0; */ \ + vpxor x0, y0, y0; \ + vpxor x1, y1, y1; \ + vpxor x2, y2, y2; \ + vpxor x3, y3, y3; \ + \ + /* t1 ^= t2; */ \ + vpxor y0, x4, x4; \ + vpxor y1, x5, x5; \ + vpxor y2, x6, x6; \ + vpxor y3, x7, x7; + +#define aria_fe(x0, x1, x2, x3, \ + x4, x5, x6, x7, \ + y0, y1, y2, y3, \ + y4, y5, y6, y7, \ + mem_tmp, rk, round) \ + aria_ark_8way(x0, x1, x2, x3, x4, x5, x6, x7, \ + y0, rk, 8, round); \ + \ + aria_sbox_8way(x2, x3, x0, x1, x6, x7, x4, x5, \ + y0, y1, y2, y3, y4, y5, y6, y7); \ + \ + aria_diff_m(x0, x1, x2, x3, y0, y1, y2, y3); \ + aria_diff_m(x4, x5, x6, x7, y0, y1, y2, y3); \ + aria_store_state_8way(x0, x1, x2, x3, \ + x4, x5, x6, x7, \ + mem_tmp, 8); \ + \ + aria_load_state_8way(x0, x1, x2, x3, \ + x4, x5, x6, x7, \ + mem_tmp, 0); \ + aria_ark_8way(x0, x1, x2, x3, x4, x5, x6, x7, \ + y0, rk, 0, round); \ + \ + aria_sbox_8way(x2, x3, x0, x1, x6, x7, x4, x5, \ + y0, y1, y2, y3, y4, y5, y6, y7); \ + \ + aria_diff_m(x0, x1, x2, x3, y0, y1, y2, y3); \ + aria_diff_m(x4, x5, x6, x7, y0, y1, y2, y3); \ + aria_store_state_8way(x0, x1, x2, x3, \ + x4, x5, x6, x7, \ + mem_tmp, 0); \ + aria_load_state_8way(y0, y1, y2, y3, \ + y4, y5, y6, y7, \ + mem_tmp, 8); \ + aria_diff_word(x0, x1, x2, x3, \ + x4, x5, x6, x7, \ + y0, y1, y2, y3, \ + y4, y5, y6, y7); \ + /* aria_diff_byte() \ + * T3 = ABCD -> BADC \ + * T3 = y4, y5, y6, y7 -> y5, y4, y7, y6 \ + * T0 = ABCD -> CDAB \ + * T0 = x0, x1, x2, x3 -> x2, x3, x0, x1 \ + * T1 = ABCD -> DCBA \ + * T1 = x4, x5, x6, x7 -> x7, x6, x5, x4 \ + */ \ + aria_diff_word(x2, x3, x0, x1, \ + x7, x6, x5, x4, \ + y0, y1, y2, y3, \ + y5, y4, y7, y6); \ + aria_store_state_8way(x3, x2, x1, x0, \ + x6, x7, x4, x5, \ + mem_tmp, 0); + +#define aria_fo(x0, x1, x2, x3, \ + x4, x5, x6, x7, \ + y0, y1, y2, y3, \ + y4, y5, y6, y7, \ + mem_tmp, rk, round) \ + aria_ark_8way(x0, x1, x2, x3, x4, x5, x6, x7, \ + y0, rk, 8, round); \ + \ + aria_sbox_8way(x0, x1, x2, x3, x4, x5, x6, x7, \ + y0, y1, y2, y3, y4, y5, y6, y7); \ + \ + aria_diff_m(x0, x1, x2, x3, y0, y1, y2, y3); \ + aria_diff_m(x4, x5, x6, x7, y0, y1, y2, y3); \ + aria_store_state_8way(x0, x1, x2, x3, \ + x4, x5, x6, x7, \ + mem_tmp, 8); \ + \ + aria_load_state_8way(x0, x1, x2, x3, \ + x4, x5, x6, x7, \ + mem_tmp, 0); \ + aria_ark_8way(x0, x1, x2, x3, x4, x5, x6, x7, \ + y0, rk, 0, round); \ + \ + aria_sbox_8way(x0, x1, x2, x3, x4, x5, x6, x7, \ + y0, y1, y2, y3, y4, y5, y6, y7); \ + \ + aria_diff_m(x0, x1, x2, x3, y0, y1, y2, y3); \ + aria_diff_m(x4, x5, x6, x7, y0, y1, y2, y3); \ + aria_store_state_8way(x0, x1, x2, x3, \ + x4, x5, x6, x7, \ + mem_tmp, 0); \ + aria_load_state_8way(y0, y1, y2, y3, \ + y4, y5, y6, y7, \ + mem_tmp, 8); \ + aria_diff_word(x0, x1, x2, x3, \ + x4, x5, x6, x7, \ + y0, y1, y2, y3, \ + y4, y5, y6, y7); \ + /* aria_diff_byte() \ + * T1 = ABCD -> BADC \ + * T1 = x4, x5, x6, x7 -> x5, x4, x7, x6 \ + * T2 = ABCD -> CDAB \ + * T2 = y0, y1, y2, y3, -> y2, y3, y0, y1 \ + * T3 = ABCD -> DCBA \ + * T3 = y4, y5, y6, y7 -> y7, y6, y5, y4 \ + */ \ + aria_diff_word(x0, x1, x2, x3, \ + x5, x4, x7, x6, \ + y2, y3, y0, y1, \ + y7, y6, y5, y4); \ + aria_store_state_8way(x3, x2, x1, x0, \ + x6, x7, x4, x5, \ + mem_tmp, 0); + +#define aria_ff(x0, x1, x2, x3, \ + x4, x5, x6, x7, \ + y0, y1, y2, y3, \ + y4, y5, y6, y7, \ + mem_tmp, rk, round, last_round) \ + aria_ark_8way(x0, x1, x2, x3, x4, x5, x6, x7, \ + y0, rk, 8, round); \ + \ + aria_sbox_8way(x2, x3, x0, x1, x6, x7, x4, x5, \ + y0, y1, y2, y3, y4, y5, y6, y7); \ + \ + aria_ark_8way(x0, x1, x2, x3, x4, x5, x6, x7, \ + y0, rk, 8, last_round); \ + \ + aria_store_state_8way(x0, x1, x2, x3, \ + x4, x5, x6, x7, \ + mem_tmp, 8); \ + \ + aria_load_state_8way(x0, x1, x2, x3, \ + x4, x5, x6, x7, \ + mem_tmp, 0); \ + aria_ark_8way(x0, x1, x2, x3, x4, x5, x6, x7, \ + y0, rk, 0, round); \ + \ + aria_sbox_8way(x2, x3, x0, x1, x6, x7, x4, x5, \ + y0, y1, y2, y3, y4, y5, y6, y7); \ + \ + aria_ark_8way(x0, x1, x2, x3, x4, x5, x6, x7, \ + y0, rk, 0, last_round); \ + \ + aria_load_state_8way(y0, y1, y2, y3, \ + y4, y5, y6, y7, \ + mem_tmp, 8); + +#define aria_fe_gfni(x0, x1, x2, x3, \ + x4, x5, x6, x7, \ + y0, y1, y2, y3, \ + y4, y5, y6, y7, \ + mem_tmp, rk, round) \ + aria_ark_8way(x0, x1, x2, x3, x4, x5, x6, x7, \ + y0, rk, 8, round); \ + \ + aria_sbox_8way_gfni(x2, x3, x0, x1, \ + x6, x7, x4, x5, \ + y0, y1, y2, y3, \ + y4, y5, y6, y7); \ + \ + aria_diff_m(x0, x1, x2, x3, y0, y1, y2, y3); \ + aria_diff_m(x4, x5, x6, x7, y0, y1, y2, y3); \ + aria_store_state_8way(x0, x1, x2, x3, \ + x4, x5, x6, x7, \ + mem_tmp, 8); \ + \ + aria_load_state_8way(x0, x1, x2, x3, \ + x4, x5, x6, x7, \ + mem_tmp, 0); \ + aria_ark_8way(x0, x1, x2, x3, x4, x5, x6, x7, \ + y0, rk, 0, round); \ + \ + aria_sbox_8way_gfni(x2, x3, x0, x1, \ + x6, x7, x4, x5, \ + y0, y1, y2, y3, \ + y4, y5, y6, y7); \ + \ + aria_diff_m(x0, x1, x2, x3, y0, y1, y2, y3); \ + aria_diff_m(x4, x5, x6, x7, y0, y1, y2, y3); \ + aria_store_state_8way(x0, x1, x2, x3, \ + x4, x5, x6, x7, \ + mem_tmp, 0); \ + aria_load_state_8way(y0, y1, y2, y3, \ + y4, y5, y6, y7, \ + mem_tmp, 8); \ + aria_diff_word(x0, x1, x2, x3, \ + x4, x5, x6, x7, \ + y0, y1, y2, y3, \ + y4, y5, y6, y7); \ + /* aria_diff_byte() \ + * T3 = ABCD -> BADC \ + * T3 = y4, y5, y6, y7 -> y5, y4, y7, y6 \ + * T0 = ABCD -> CDAB \ + * T0 = x0, x1, x2, x3 -> x2, x3, x0, x1 \ + * T1 = ABCD -> DCBA \ + * T1 = x4, x5, x6, x7 -> x7, x6, x5, x4 \ + */ \ + aria_diff_word(x2, x3, x0, x1, \ + x7, x6, x5, x4, \ + y0, y1, y2, y3, \ + y5, y4, y7, y6); \ + aria_store_state_8way(x3, x2, x1, x0, \ + x6, x7, x4, x5, \ + mem_tmp, 0); + +#define aria_fo_gfni(x0, x1, x2, x3, \ + x4, x5, x6, x7, \ + y0, y1, y2, y3, \ + y4, y5, y6, y7, \ + mem_tmp, rk, round) \ + aria_ark_8way(x0, x1, x2, x3, x4, x5, x6, x7, \ + y0, rk, 8, round); \ + \ + aria_sbox_8way_gfni(x0, x1, x2, x3, \ + x4, x5, x6, x7, \ + y0, y1, y2, y3, \ + y4, y5, y6, y7); \ + \ + aria_diff_m(x0, x1, x2, x3, y0, y1, y2, y3); \ + aria_diff_m(x4, x5, x6, x7, y0, y1, y2, y3); \ + aria_store_state_8way(x0, x1, x2, x3, \ + x4, x5, x6, x7, \ + mem_tmp, 8); \ + \ + aria_load_state_8way(x0, x1, x2, x3, \ + x4, x5, x6, x7, \ + mem_tmp, 0); \ + aria_ark_8way(x0, x1, x2, x3, x4, x5, x6, x7, \ + y0, rk, 0, round); \ + \ + aria_sbox_8way_gfni(x0, x1, x2, x3, \ + x4, x5, x6, x7, \ + y0, y1, y2, y3, \ + y4, y5, y6, y7); \ + \ + aria_diff_m(x0, x1, x2, x3, y0, y1, y2, y3); \ + aria_diff_m(x4, x5, x6, x7, y0, y1, y2, y3); \ + aria_store_state_8way(x0, x1, x2, x3, \ + x4, x5, x6, x7, \ + mem_tmp, 0); \ + aria_load_state_8way(y0, y1, y2, y3, \ + y4, y5, y6, y7, \ + mem_tmp, 8); \ + aria_diff_word(x0, x1, x2, x3, \ + x4, x5, x6, x7, \ + y0, y1, y2, y3, \ + y4, y5, y6, y7); \ + /* aria_diff_byte() \ + * T1 = ABCD -> BADC \ + * T1 = x4, x5, x6, x7 -> x5, x4, x7, x6 \ + * T2 = ABCD -> CDAB \ + * T2 = y0, y1, y2, y3, -> y2, y3, y0, y1 \ + * T3 = ABCD -> DCBA \ + * T3 = y4, y5, y6, y7 -> y7, y6, y5, y4 \ + */ \ + aria_diff_word(x0, x1, x2, x3, \ + x5, x4, x7, x6, \ + y2, y3, y0, y1, \ + y7, y6, y5, y4); \ + aria_store_state_8way(x3, x2, x1, x0, \ + x6, x7, x4, x5, \ + mem_tmp, 0); + +#define aria_ff_gfni(x0, x1, x2, x3, \ + x4, x5, x6, x7, \ + y0, y1, y2, y3, \ + y4, y5, y6, y7, \ + mem_tmp, rk, round, last_round) \ + aria_ark_8way(x0, x1, x2, x3, x4, x5, x6, x7, \ + y0, rk, 8, round); \ + \ + aria_sbox_8way_gfni(x2, x3, x0, x1, \ + x6, x7, x4, x5, \ + y0, y1, y2, y3, \ + y4, y5, y6, y7); \ + \ + aria_ark_8way(x0, x1, x2, x3, x4, x5, x6, x7, \ + y0, rk, 8, last_round); \ + \ + aria_store_state_8way(x0, x1, x2, x3, \ + x4, x5, x6, x7, \ + mem_tmp, 8); \ + \ + aria_load_state_8way(x0, x1, x2, x3, \ + x4, x5, x6, x7, \ + mem_tmp, 0); \ + aria_ark_8way(x0, x1, x2, x3, x4, x5, x6, x7, \ + y0, rk, 0, round); \ + \ + aria_sbox_8way_gfni(x2, x3, x0, x1, \ + x6, x7, x4, x5, \ + y0, y1, y2, y3, \ + y4, y5, y6, y7); \ + \ + aria_ark_8way(x0, x1, x2, x3, x4, x5, x6, x7, \ + y0, rk, 0, last_round); \ + \ + aria_load_state_8way(y0, y1, y2, y3, \ + y4, y5, y6, y7, \ + mem_tmp, 8); + +/* NB: section is mergeable, all elements must be aligned 16-byte blocks */ +.section .rodata.cst16, "aM", @progbits, 16 +.align 16 + +#define SHUFB_BYTES(idx) \ + 0 + (idx), 4 + (idx), 8 + (idx), 12 + (idx) + +.Lshufb_16x16b: + .byte SHUFB_BYTES(0), SHUFB_BYTES(1), SHUFB_BYTES(2), SHUFB_BYTES(3); +/* For isolating SubBytes from AESENCLAST, inverse shift row */ +.Linv_shift_row: + .byte 0x00, 0x0d, 0x0a, 0x07, 0x04, 0x01, 0x0e, 0x0b + .byte 0x08, 0x05, 0x02, 0x0f, 0x0c, 0x09, 0x06, 0x03 +.Lshift_row: + .byte 0x00, 0x05, 0x0a, 0x0f, 0x04, 0x09, 0x0e, 0x03 + .byte 0x08, 0x0d, 0x02, 0x07, 0x0c, 0x01, 0x06, 0x0b +/* For CTR-mode IV byteswap */ +.Lbswap128_mask: + .byte 0x0f, 0x0e, 0x0d, 0x0c, 0x0b, 0x0a, 0x09, 0x08 + .byte 0x07, 0x06, 0x05, 0x04, 0x03, 0x02, 0x01, 0x00 + +/* AES inverse affine and S2 combined: + * 1 1 0 0 0 0 0 1 x0 0 + * 0 1 0 0 1 0 0 0 x1 0 + * 1 1 0 0 1 1 1 1 x2 0 + * 0 1 1 0 1 0 0 1 x3 1 + * 0 1 0 0 1 1 0 0 * x4 + 0 + * 0 1 0 1 1 0 0 0 x5 0 + * 0 0 0 0 0 1 0 1 x6 0 + * 1 1 1 0 0 1 1 1 x7 1 + */ +.Ltf_lo__inv_aff__and__s2: + .octa 0x92172DA81A9FA520B2370D883ABF8500 +.Ltf_hi__inv_aff__and__s2: + .octa 0x2B15FFC1AF917B45E6D8320C625CB688 + +/* X2 and AES forward affine combined: + * 1 0 1 1 0 0 0 1 x0 0 + * 0 1 1 1 1 0 1 1 x1 0 + * 0 0 0 1 1 0 1 0 x2 1 + * 0 1 0 0 0 1 0 0 x3 0 + * 0 0 1 1 1 0 1 1 * x4 + 0 + * 0 1 0 0 1 0 0 0 x5 0 + * 1 1 0 1 0 0 1 1 x6 0 + * 0 1 0 0 1 0 1 0 x7 0 + */ +.Ltf_lo__x2__and__fwd_aff: + .octa 0xEFAE0544FCBD1657B8F95213ABEA4100 +.Ltf_hi__x2__and__fwd_aff: + .octa 0x3F893781E95FE1576CDA64D2BA0CB204 + +.section .rodata.cst8, "aM", @progbits, 8 +.align 8 +/* AES affine: */ +#define tf_aff_const BV8(1, 1, 0, 0, 0, 1, 1, 0) +.Ltf_aff_bitmatrix: + .quad BM8X8(BV8(1, 0, 0, 0, 1, 1, 1, 1), + BV8(1, 1, 0, 0, 0, 1, 1, 1), + BV8(1, 1, 1, 0, 0, 0, 1, 1), + BV8(1, 1, 1, 1, 0, 0, 0, 1), + BV8(1, 1, 1, 1, 1, 0, 0, 0), + BV8(0, 1, 1, 1, 1, 1, 0, 0), + BV8(0, 0, 1, 1, 1, 1, 1, 0), + BV8(0, 0, 0, 1, 1, 1, 1, 1)) + +/* AES inverse affine: */ +#define tf_inv_const BV8(1, 0, 1, 0, 0, 0, 0, 0) +.Ltf_inv_bitmatrix: + .quad BM8X8(BV8(0, 0, 1, 0, 0, 1, 0, 1), + BV8(1, 0, 0, 1, 0, 0, 1, 0), + BV8(0, 1, 0, 0, 1, 0, 0, 1), + BV8(1, 0, 1, 0, 0, 1, 0, 0), + BV8(0, 1, 0, 1, 0, 0, 1, 0), + BV8(0, 0, 1, 0, 1, 0, 0, 1), + BV8(1, 0, 0, 1, 0, 1, 0, 0), + BV8(0, 1, 0, 0, 1, 0, 1, 0)) + +/* S2: */ +#define tf_s2_const BV8(0, 1, 0, 0, 0, 1, 1, 1) +.Ltf_s2_bitmatrix: + .quad BM8X8(BV8(0, 1, 0, 1, 0, 1, 1, 1), + BV8(0, 0, 1, 1, 1, 1, 1, 1), + BV8(1, 1, 1, 0, 1, 1, 0, 1), + BV8(1, 1, 0, 0, 0, 0, 1, 1), + BV8(0, 1, 0, 0, 0, 0, 1, 1), + BV8(1, 1, 0, 0, 1, 1, 1, 0), + BV8(0, 1, 1, 0, 0, 0, 1, 1), + BV8(1, 1, 1, 1, 0, 1, 1, 0)) + +/* X2: */ +#define tf_x2_const BV8(0, 0, 1, 1, 0, 1, 0, 0) +.Ltf_x2_bitmatrix: + .quad BM8X8(BV8(0, 0, 0, 1, 1, 0, 0, 0), + BV8(0, 0, 1, 0, 0, 1, 1, 0), + BV8(0, 0, 0, 0, 1, 0, 1, 0), + BV8(1, 1, 1, 0, 0, 0, 1, 1), + BV8(1, 1, 1, 0, 1, 1, 0, 0), + BV8(0, 1, 1, 0, 1, 0, 1, 1), + BV8(1, 0, 1, 1, 1, 1, 0, 1), + BV8(1, 0, 0, 1, 0, 0, 1, 1)) + +/* Identity matrix: */ +.Ltf_id_bitmatrix: + .quad BM8X8(BV8(1, 0, 0, 0, 0, 0, 0, 0), + BV8(0, 1, 0, 0, 0, 0, 0, 0), + BV8(0, 0, 1, 0, 0, 0, 0, 0), + BV8(0, 0, 0, 1, 0, 0, 0, 0), + BV8(0, 0, 0, 0, 1, 0, 0, 0), + BV8(0, 0, 0, 0, 0, 1, 0, 0), + BV8(0, 0, 0, 0, 0, 0, 1, 0), + BV8(0, 0, 0, 0, 0, 0, 0, 1)) + +/* 4-bit mask */ +.section .rodata.cst4.L0f0f0f0f, "aM", @progbits, 4 +.align 4 +.L0f0f0f0f: + .long 0x0f0f0f0f + +.text + +SYM_FUNC_START_LOCAL(__aria_aesni_avx_crypt_16way) + /* input: + * %r9: rk + * %rsi: dst + * %rdx: src + * %xmm0..%xmm15: 16 byte-sliced blocks + */ + + FRAME_BEGIN + + movq %rsi, %rax; + leaq 8 * 16(%rax), %r8; + + inpack16_post(%xmm0, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, + %xmm8, %xmm9, %xmm10, %xmm11, %xmm12, %xmm13, %xmm14, + %xmm15, %rax, %r8); + aria_fo(%xmm8, %xmm9, %xmm10, %xmm11, %xmm12, %xmm13, %xmm14, %xmm15, + %xmm0, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, + %rax, %r9, 0); + aria_fe(%xmm1, %xmm0, %xmm3, %xmm2, %xmm4, %xmm5, %xmm6, %xmm7, + %xmm8, %xmm9, %xmm10, %xmm11, %xmm12, %xmm13, %xmm14, + %xmm15, %rax, %r9, 1); + aria_fo(%xmm9, %xmm8, %xmm11, %xmm10, %xmm12, %xmm13, %xmm14, %xmm15, + %xmm0, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, + %rax, %r9, 2); + aria_fe(%xmm1, %xmm0, %xmm3, %xmm2, %xmm4, %xmm5, %xmm6, %xmm7, + %xmm8, %xmm9, %xmm10, %xmm11, %xmm12, %xmm13, %xmm14, + %xmm15, %rax, %r9, 3); + aria_fo(%xmm9, %xmm8, %xmm11, %xmm10, %xmm12, %xmm13, %xmm14, %xmm15, + %xmm0, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, + %rax, %r9, 4); + aria_fe(%xmm1, %xmm0, %xmm3, %xmm2, %xmm4, %xmm5, %xmm6, %xmm7, + %xmm8, %xmm9, %xmm10, %xmm11, %xmm12, %xmm13, %xmm14, + %xmm15, %rax, %r9, 5); + aria_fo(%xmm9, %xmm8, %xmm11, %xmm10, %xmm12, %xmm13, %xmm14, %xmm15, + %xmm0, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, + %rax, %r9, 6); + aria_fe(%xmm1, %xmm0, %xmm3, %xmm2, %xmm4, %xmm5, %xmm6, %xmm7, + %xmm8, %xmm9, %xmm10, %xmm11, %xmm12, %xmm13, %xmm14, + %xmm15, %rax, %r9, 7); + aria_fo(%xmm9, %xmm8, %xmm11, %xmm10, %xmm12, %xmm13, %xmm14, %xmm15, + %xmm0, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, + %rax, %r9, 8); + aria_fe(%xmm1, %xmm0, %xmm3, %xmm2, %xmm4, %xmm5, %xmm6, %xmm7, + %xmm8, %xmm9, %xmm10, %xmm11, %xmm12, %xmm13, %xmm14, + %xmm15, %rax, %r9, 9); + aria_fo(%xmm9, %xmm8, %xmm11, %xmm10, %xmm12, %xmm13, %xmm14, %xmm15, + %xmm0, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, + %rax, %r9, 10); + cmpl $12, rounds(CTX); + jne .Laria_192; + aria_ff(%xmm1, %xmm0, %xmm3, %xmm2, %xmm4, %xmm5, %xmm6, %xmm7, + %xmm8, %xmm9, %xmm10, %xmm11, %xmm12, %xmm13, %xmm14, + %xmm15, %rax, %r9, 11, 12); + jmp .Laria_end; +.Laria_192: + aria_fe(%xmm1, %xmm0, %xmm3, %xmm2, %xmm4, %xmm5, %xmm6, %xmm7, + %xmm8, %xmm9, %xmm10, %xmm11, %xmm12, %xmm13, %xmm14, + %xmm15, %rax, %r9, 11); + aria_fo(%xmm9, %xmm8, %xmm11, %xmm10, %xmm12, %xmm13, %xmm14, %xmm15, + %xmm0, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, + %rax, %r9, 12); + cmpl $14, rounds(CTX); + jne .Laria_256; + aria_ff(%xmm1, %xmm0, %xmm3, %xmm2, %xmm4, %xmm5, %xmm6, %xmm7, + %xmm8, %xmm9, %xmm10, %xmm11, %xmm12, %xmm13, %xmm14, + %xmm15, %rax, %r9, 13, 14); + jmp .Laria_end; +.Laria_256: + aria_fe(%xmm1, %xmm0, %xmm3, %xmm2, %xmm4, %xmm5, %xmm6, %xmm7, + %xmm8, %xmm9, %xmm10, %xmm11, %xmm12, %xmm13, %xmm14, + %xmm15, %rax, %r9, 13); + aria_fo(%xmm9, %xmm8, %xmm11, %xmm10, %xmm12, %xmm13, %xmm14, %xmm15, + %xmm0, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, + %rax, %r9, 14); + aria_ff(%xmm1, %xmm0, %xmm3, %xmm2, %xmm4, %xmm5, %xmm6, %xmm7, + %xmm8, %xmm9, %xmm10, %xmm11, %xmm12, %xmm13, %xmm14, + %xmm15, %rax, %r9, 15, 16); +.Laria_end: + debyteslice_16x16b(%xmm8, %xmm12, %xmm1, %xmm4, + %xmm9, %xmm13, %xmm0, %xmm5, + %xmm10, %xmm14, %xmm3, %xmm6, + %xmm11, %xmm15, %xmm2, %xmm7, + (%rax), (%r8)); + + FRAME_END + RET; +SYM_FUNC_END(__aria_aesni_avx_crypt_16way) + +SYM_FUNC_START(aria_aesni_avx_encrypt_16way) + /* input: + * %rdi: ctx, CTX + * %rsi: dst + * %rdx: src + */ + + FRAME_BEGIN + + leaq enc_key(CTX), %r9; + + inpack16_pre(%xmm0, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, + %xmm8, %xmm9, %xmm10, %xmm11, %xmm12, %xmm13, %xmm14, + %xmm15, %rdx); + + call __aria_aesni_avx_crypt_16way; + + write_output(%xmm1, %xmm0, %xmm3, %xmm2, %xmm4, %xmm5, %xmm6, %xmm7, + %xmm8, %xmm9, %xmm10, %xmm11, %xmm12, %xmm13, %xmm14, + %xmm15, %rax); + + FRAME_END + RET; +SYM_FUNC_END(aria_aesni_avx_encrypt_16way) + +SYM_FUNC_START(aria_aesni_avx_decrypt_16way) + /* input: + * %rdi: ctx, CTX + * %rsi: dst + * %rdx: src + */ + + FRAME_BEGIN + + leaq dec_key(CTX), %r9; + + inpack16_pre(%xmm0, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, + %xmm8, %xmm9, %xmm10, %xmm11, %xmm12, %xmm13, %xmm14, + %xmm15, %rdx); + + call __aria_aesni_avx_crypt_16way; + + write_output(%xmm1, %xmm0, %xmm3, %xmm2, %xmm4, %xmm5, %xmm6, %xmm7, + %xmm8, %xmm9, %xmm10, %xmm11, %xmm12, %xmm13, %xmm14, + %xmm15, %rax); + + FRAME_END + RET; +SYM_FUNC_END(aria_aesni_avx_decrypt_16way) + +SYM_FUNC_START_LOCAL(__aria_aesni_avx_ctr_gen_keystream_16way) + /* input: + * %rdi: ctx + * %rsi: dst + * %rdx: src + * %rcx: keystream + * %r8: iv (big endian, 128bit) + */ + + FRAME_BEGIN + /* load IV and byteswap */ + vmovdqu (%r8), %xmm8; + + vmovdqa .Lbswap128_mask (%rip), %xmm1; + vpshufb %xmm1, %xmm8, %xmm3; /* be => le */ + + vpcmpeqd %xmm0, %xmm0, %xmm0; + vpsrldq $8, %xmm0, %xmm0; /* low: -1, high: 0 */ + + /* construct IVs */ + inc_le128(%xmm3, %xmm0, %xmm5); /* +1 */ + vpshufb %xmm1, %xmm3, %xmm9; + inc_le128(%xmm3, %xmm0, %xmm5); /* +1 */ + vpshufb %xmm1, %xmm3, %xmm10; + inc_le128(%xmm3, %xmm0, %xmm5); /* +1 */ + vpshufb %xmm1, %xmm3, %xmm11; + inc_le128(%xmm3, %xmm0, %xmm5); /* +1 */ + vpshufb %xmm1, %xmm3, %xmm12; + inc_le128(%xmm3, %xmm0, %xmm5); /* +1 */ + vpshufb %xmm1, %xmm3, %xmm13; + inc_le128(%xmm3, %xmm0, %xmm5); /* +1 */ + vpshufb %xmm1, %xmm3, %xmm14; + inc_le128(%xmm3, %xmm0, %xmm5); /* +1 */ + vpshufb %xmm1, %xmm3, %xmm15; + vmovdqu %xmm8, (0 * 16)(%rcx); + vmovdqu %xmm9, (1 * 16)(%rcx); + vmovdqu %xmm10, (2 * 16)(%rcx); + vmovdqu %xmm11, (3 * 16)(%rcx); + vmovdqu %xmm12, (4 * 16)(%rcx); + vmovdqu %xmm13, (5 * 16)(%rcx); + vmovdqu %xmm14, (6 * 16)(%rcx); + vmovdqu %xmm15, (7 * 16)(%rcx); + + inc_le128(%xmm3, %xmm0, %xmm5); /* +1 */ + vpshufb %xmm1, %xmm3, %xmm8; + inc_le128(%xmm3, %xmm0, %xmm5); /* +1 */ + vpshufb %xmm1, %xmm3, %xmm9; + inc_le128(%xmm3, %xmm0, %xmm5); /* +1 */ + vpshufb %xmm1, %xmm3, %xmm10; + inc_le128(%xmm3, %xmm0, %xmm5); /* +1 */ + vpshufb %xmm1, %xmm3, %xmm11; + inc_le128(%xmm3, %xmm0, %xmm5); /* +1 */ + vpshufb %xmm1, %xmm3, %xmm12; + inc_le128(%xmm3, %xmm0, %xmm5); /* +1 */ + vpshufb %xmm1, %xmm3, %xmm13; + inc_le128(%xmm3, %xmm0, %xmm5); /* +1 */ + vpshufb %xmm1, %xmm3, %xmm14; + inc_le128(%xmm3, %xmm0, %xmm5); /* +1 */ + vpshufb %xmm1, %xmm3, %xmm15; + inc_le128(%xmm3, %xmm0, %xmm5); /* +1 */ + vpshufb %xmm1, %xmm3, %xmm4; + vmovdqu %xmm4, (%r8); + + vmovdqu (0 * 16)(%rcx), %xmm0; + vmovdqu (1 * 16)(%rcx), %xmm1; + vmovdqu (2 * 16)(%rcx), %xmm2; + vmovdqu (3 * 16)(%rcx), %xmm3; + vmovdqu (4 * 16)(%rcx), %xmm4; + vmovdqu (5 * 16)(%rcx), %xmm5; + vmovdqu (6 * 16)(%rcx), %xmm6; + vmovdqu (7 * 16)(%rcx), %xmm7; + + FRAME_END + RET; +SYM_FUNC_END(__aria_aesni_avx_ctr_gen_keystream_16way) + +SYM_FUNC_START(aria_aesni_avx_ctr_crypt_16way) + /* input: + * %rdi: ctx + * %rsi: dst + * %rdx: src + * %rcx: keystream + * %r8: iv (big endian, 128bit) + */ + FRAME_BEGIN + + call __aria_aesni_avx_ctr_gen_keystream_16way; + + leaq (%rsi), %r10; + leaq (%rdx), %r11; + leaq (%rcx), %rsi; + leaq (%rcx), %rdx; + leaq enc_key(CTX), %r9; + + call __aria_aesni_avx_crypt_16way; + + vpxor (0 * 16)(%r11), %xmm1, %xmm1; + vpxor (1 * 16)(%r11), %xmm0, %xmm0; + vpxor (2 * 16)(%r11), %xmm3, %xmm3; + vpxor (3 * 16)(%r11), %xmm2, %xmm2; + vpxor (4 * 16)(%r11), %xmm4, %xmm4; + vpxor (5 * 16)(%r11), %xmm5, %xmm5; + vpxor (6 * 16)(%r11), %xmm6, %xmm6; + vpxor (7 * 16)(%r11), %xmm7, %xmm7; + vpxor (8 * 16)(%r11), %xmm8, %xmm8; + vpxor (9 * 16)(%r11), %xmm9, %xmm9; + vpxor (10 * 16)(%r11), %xmm10, %xmm10; + vpxor (11 * 16)(%r11), %xmm11, %xmm11; + vpxor (12 * 16)(%r11), %xmm12, %xmm12; + vpxor (13 * 16)(%r11), %xmm13, %xmm13; + vpxor (14 * 16)(%r11), %xmm14, %xmm14; + vpxor (15 * 16)(%r11), %xmm15, %xmm15; + write_output(%xmm1, %xmm0, %xmm3, %xmm2, %xmm4, %xmm5, %xmm6, %xmm7, + %xmm8, %xmm9, %xmm10, %xmm11, %xmm12, %xmm13, %xmm14, + %xmm15, %r10); + + FRAME_END + RET; +SYM_FUNC_END(aria_aesni_avx_ctr_crypt_16way) + +SYM_FUNC_START_LOCAL(__aria_aesni_avx_gfni_crypt_16way) + /* input: + * %r9: rk + * %rsi: dst + * %rdx: src + * %xmm0..%xmm15: 16 byte-sliced blocks + */ + + FRAME_BEGIN + + movq %rsi, %rax; + leaq 8 * 16(%rax), %r8; + + inpack16_post(%xmm0, %xmm1, %xmm2, %xmm3, + %xmm4, %xmm5, %xmm6, %xmm7, + %xmm8, %xmm9, %xmm10, %xmm11, + %xmm12, %xmm13, %xmm14, + %xmm15, %rax, %r8); + aria_fo_gfni(%xmm8, %xmm9, %xmm10, %xmm11, + %xmm12, %xmm13, %xmm14, %xmm15, + %xmm0, %xmm1, %xmm2, %xmm3, + %xmm4, %xmm5, %xmm6, %xmm7, + %rax, %r9, 0); + aria_fe_gfni(%xmm1, %xmm0, %xmm3, %xmm2, + %xmm4, %xmm5, %xmm6, %xmm7, + %xmm8, %xmm9, %xmm10, %xmm11, + %xmm12, %xmm13, %xmm14, + %xmm15, %rax, %r9, 1); + aria_fo_gfni(%xmm9, %xmm8, %xmm11, %xmm10, + %xmm12, %xmm13, %xmm14, %xmm15, + %xmm0, %xmm1, %xmm2, %xmm3, + %xmm4, %xmm5, %xmm6, %xmm7, + %rax, %r9, 2); + aria_fe_gfni(%xmm1, %xmm0, %xmm3, %xmm2, + %xmm4, %xmm5, %xmm6, %xmm7, + %xmm8, %xmm9, %xmm10, %xmm11, + %xmm12, %xmm13, %xmm14, + %xmm15, %rax, %r9, 3); + aria_fo_gfni(%xmm9, %xmm8, %xmm11, %xmm10, + %xmm12, %xmm13, %xmm14, %xmm15, + %xmm0, %xmm1, %xmm2, %xmm3, + %xmm4, %xmm5, %xmm6, %xmm7, + %rax, %r9, 4); + aria_fe_gfni(%xmm1, %xmm0, %xmm3, %xmm2, + %xmm4, %xmm5, %xmm6, %xmm7, + %xmm8, %xmm9, %xmm10, %xmm11, + %xmm12, %xmm13, %xmm14, + %xmm15, %rax, %r9, 5); + aria_fo_gfni(%xmm9, %xmm8, %xmm11, %xmm10, + %xmm12, %xmm13, %xmm14, %xmm15, + %xmm0, %xmm1, %xmm2, %xmm3, + %xmm4, %xmm5, %xmm6, %xmm7, + %rax, %r9, 6); + aria_fe_gfni(%xmm1, %xmm0, %xmm3, %xmm2, + %xmm4, %xmm5, %xmm6, %xmm7, + %xmm8, %xmm9, %xmm10, %xmm11, + %xmm12, %xmm13, %xmm14, + %xmm15, %rax, %r9, 7); + aria_fo_gfni(%xmm9, %xmm8, %xmm11, %xmm10, + %xmm12, %xmm13, %xmm14, %xmm15, + %xmm0, %xmm1, %xmm2, %xmm3, + %xmm4, %xmm5, %xmm6, %xmm7, + %rax, %r9, 8); + aria_fe_gfni(%xmm1, %xmm0, %xmm3, %xmm2, + %xmm4, %xmm5, %xmm6, %xmm7, + %xmm8, %xmm9, %xmm10, %xmm11, + %xmm12, %xmm13, %xmm14, + %xmm15, %rax, %r9, 9); + aria_fo_gfni(%xmm9, %xmm8, %xmm11, %xmm10, + %xmm12, %xmm13, %xmm14, %xmm15, + %xmm0, %xmm1, %xmm2, %xmm3, + %xmm4, %xmm5, %xmm6, %xmm7, + %rax, %r9, 10); + cmpl $12, rounds(CTX); + jne .Laria_gfni_192; + aria_ff_gfni(%xmm1, %xmm0, %xmm3, %xmm2, %xmm4, %xmm5, %xmm6, %xmm7, + %xmm8, %xmm9, %xmm10, %xmm11, %xmm12, %xmm13, %xmm14, + %xmm15, %rax, %r9, 11, 12); + jmp .Laria_gfni_end; +.Laria_gfni_192: + aria_fe_gfni(%xmm1, %xmm0, %xmm3, %xmm2, + %xmm4, %xmm5, %xmm6, %xmm7, + %xmm8, %xmm9, %xmm10, %xmm11, + %xmm12, %xmm13, %xmm14, + %xmm15, %rax, %r9, 11); + aria_fo_gfni(%xmm9, %xmm8, %xmm11, %xmm10, + %xmm12, %xmm13, %xmm14, %xmm15, + %xmm0, %xmm1, %xmm2, %xmm3, + %xmm4, %xmm5, %xmm6, %xmm7, + %rax, %r9, 12); + cmpl $14, rounds(CTX); + jne .Laria_gfni_256; + aria_ff_gfni(%xmm1, %xmm0, %xmm3, %xmm2, + %xmm4, %xmm5, %xmm6, %xmm7, + %xmm8, %xmm9, %xmm10, %xmm11, + %xmm12, %xmm13, %xmm14, + %xmm15, %rax, %r9, 13, 14); + jmp .Laria_gfni_end; +.Laria_gfni_256: + aria_fe_gfni(%xmm1, %xmm0, %xmm3, %xmm2, + %xmm4, %xmm5, %xmm6, %xmm7, + %xmm8, %xmm9, %xmm10, %xmm11, + %xmm12, %xmm13, %xmm14, + %xmm15, %rax, %r9, 13); + aria_fo_gfni(%xmm9, %xmm8, %xmm11, %xmm10, + %xmm12, %xmm13, %xmm14, %xmm15, + %xmm0, %xmm1, %xmm2, %xmm3, + %xmm4, %xmm5, %xmm6, %xmm7, + %rax, %r9, 14); + aria_ff_gfni(%xmm1, %xmm0, %xmm3, %xmm2, + %xmm4, %xmm5, %xmm6, %xmm7, + %xmm8, %xmm9, %xmm10, %xmm11, + %xmm12, %xmm13, %xmm14, + %xmm15, %rax, %r9, 15, 16); +.Laria_gfni_end: + debyteslice_16x16b(%xmm8, %xmm12, %xmm1, %xmm4, + %xmm9, %xmm13, %xmm0, %xmm5, + %xmm10, %xmm14, %xmm3, %xmm6, + %xmm11, %xmm15, %xmm2, %xmm7, + (%rax), (%r8)); + + FRAME_END + RET; +SYM_FUNC_END(__aria_aesni_avx_gfni_crypt_16way) + +SYM_FUNC_START(aria_aesni_avx_gfni_encrypt_16way) + /* input: + * %rdi: ctx, CTX + * %rsi: dst + * %rdx: src + */ + + FRAME_BEGIN + + leaq enc_key(CTX), %r9; + + inpack16_pre(%xmm0, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, + %xmm8, %xmm9, %xmm10, %xmm11, %xmm12, %xmm13, %xmm14, + %xmm15, %rdx); + + call __aria_aesni_avx_gfni_crypt_16way; + + write_output(%xmm1, %xmm0, %xmm3, %xmm2, %xmm4, %xmm5, %xmm6, %xmm7, + %xmm8, %xmm9, %xmm10, %xmm11, %xmm12, %xmm13, %xmm14, + %xmm15, %rax); + + FRAME_END + RET; +SYM_FUNC_END(aria_aesni_avx_gfni_encrypt_16way) + +SYM_FUNC_START(aria_aesni_avx_gfni_decrypt_16way) + /* input: + * %rdi: ctx, CTX + * %rsi: dst + * %rdx: src + */ + + FRAME_BEGIN + + leaq dec_key(CTX), %r9; + + inpack16_pre(%xmm0, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, + %xmm8, %xmm9, %xmm10, %xmm11, %xmm12, %xmm13, %xmm14, + %xmm15, %rdx); + + call __aria_aesni_avx_gfni_crypt_16way; + + write_output(%xmm1, %xmm0, %xmm3, %xmm2, %xmm4, %xmm5, %xmm6, %xmm7, + %xmm8, %xmm9, %xmm10, %xmm11, %xmm12, %xmm13, %xmm14, + %xmm15, %rax); + + FRAME_END + RET; +SYM_FUNC_END(aria_aesni_avx_gfni_decrypt_16way) + +SYM_FUNC_START(aria_aesni_avx_gfni_ctr_crypt_16way) + /* input: + * %rdi: ctx + * %rsi: dst + * %rdx: src + * %rcx: keystream + * %r8: iv (big endian, 128bit) + */ + FRAME_BEGIN + + call __aria_aesni_avx_ctr_gen_keystream_16way + + leaq (%rsi), %r10; + leaq (%rdx), %r11; + leaq (%rcx), %rsi; + leaq (%rcx), %rdx; + leaq enc_key(CTX), %r9; + + call __aria_aesni_avx_gfni_crypt_16way; + + vpxor (0 * 16)(%r11), %xmm1, %xmm1; + vpxor (1 * 16)(%r11), %xmm0, %xmm0; + vpxor (2 * 16)(%r11), %xmm3, %xmm3; + vpxor (3 * 16)(%r11), %xmm2, %xmm2; + vpxor (4 * 16)(%r11), %xmm4, %xmm4; + vpxor (5 * 16)(%r11), %xmm5, %xmm5; + vpxor (6 * 16)(%r11), %xmm6, %xmm6; + vpxor (7 * 16)(%r11), %xmm7, %xmm7; + vpxor (8 * 16)(%r11), %xmm8, %xmm8; + vpxor (9 * 16)(%r11), %xmm9, %xmm9; + vpxor (10 * 16)(%r11), %xmm10, %xmm10; + vpxor (11 * 16)(%r11), %xmm11, %xmm11; + vpxor (12 * 16)(%r11), %xmm12, %xmm12; + vpxor (13 * 16)(%r11), %xmm13, %xmm13; + vpxor (14 * 16)(%r11), %xmm14, %xmm14; + vpxor (15 * 16)(%r11), %xmm15, %xmm15; + write_output(%xmm1, %xmm0, %xmm3, %xmm2, %xmm4, %xmm5, %xmm6, %xmm7, + %xmm8, %xmm9, %xmm10, %xmm11, %xmm12, %xmm13, %xmm14, + %xmm15, %r10); + + FRAME_END + RET; +SYM_FUNC_END(aria_aesni_avx_gfni_ctr_crypt_16way) diff --git a/arch/x86/crypto/aria-avx.h b/arch/x86/crypto/aria-avx.h new file mode 100644 index 000000000000..01e9a01dc157 --- /dev/null +++ b/arch/x86/crypto/aria-avx.h @@ -0,0 +1,16 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +#ifndef ASM_X86_ARIA_AVX_H +#define ASM_X86_ARIA_AVX_H + +#include <linux/types.h> + +#define ARIA_AESNI_PARALLEL_BLOCKS 16 +#define ARIA_AESNI_PARALLEL_BLOCK_SIZE (ARIA_BLOCK_SIZE * 16) + +struct aria_avx_ops { + void (*aria_encrypt_16way)(const void *ctx, u8 *dst, const u8 *src); + void (*aria_decrypt_16way)(const void *ctx, u8 *dst, const u8 *src); + void (*aria_ctr_crypt_16way)(const void *ctx, u8 *dst, const u8 *src, + u8 *keystream, u8 *iv); +}; +#endif diff --git a/arch/x86/crypto/aria_aesni_avx_glue.c b/arch/x86/crypto/aria_aesni_avx_glue.c new file mode 100644 index 000000000000..c561ea4fefa5 --- /dev/null +++ b/arch/x86/crypto/aria_aesni_avx_glue.c @@ -0,0 +1,213 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Glue Code for the AVX/AES-NI/GFNI assembler implementation of the ARIA Cipher + * + * Copyright (c) 2022 Taehee Yoo <[email protected]> + */ + +#include <crypto/algapi.h> +#include <crypto/internal/simd.h> +#include <crypto/aria.h> +#include <linux/crypto.h> +#include <linux/err.h> +#include <linux/module.h> +#include <linux/types.h> + +#include "ecb_cbc_helpers.h" +#include "aria-avx.h" + +asmlinkage void aria_aesni_avx_encrypt_16way(const void *ctx, u8 *dst, + const u8 *src); +asmlinkage void aria_aesni_avx_decrypt_16way(const void *ctx, u8 *dst, + const u8 *src); +asmlinkage void aria_aesni_avx_ctr_crypt_16way(const void *ctx, u8 *dst, + const u8 *src, + u8 *keystream, u8 *iv); +asmlinkage void aria_aesni_avx_gfni_encrypt_16way(const void *ctx, u8 *dst, + const u8 *src); +asmlinkage void aria_aesni_avx_gfni_decrypt_16way(const void *ctx, u8 *dst, + const u8 *src); +asmlinkage void aria_aesni_avx_gfni_ctr_crypt_16way(const void *ctx, u8 *dst, + const u8 *src, + u8 *keystream, u8 *iv); + +static struct aria_avx_ops aria_ops; + +static int ecb_do_encrypt(struct skcipher_request *req, const u32 *rkey) +{ + ECB_WALK_START(req, ARIA_BLOCK_SIZE, ARIA_AESNI_PARALLEL_BLOCKS); + ECB_BLOCK(ARIA_AESNI_PARALLEL_BLOCKS, aria_ops.aria_encrypt_16way); + ECB_BLOCK(1, aria_encrypt); + ECB_WALK_END(); +} + +static int ecb_do_decrypt(struct skcipher_request *req, const u32 *rkey) +{ + ECB_WALK_START(req, ARIA_BLOCK_SIZE, ARIA_AESNI_PARALLEL_BLOCKS); + ECB_BLOCK(ARIA_AESNI_PARALLEL_BLOCKS, aria_ops.aria_decrypt_16way); + ECB_BLOCK(1, aria_decrypt); + ECB_WALK_END(); +} + +static int aria_avx_ecb_encrypt(struct skcipher_request *req) +{ + struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); + struct aria_ctx *ctx = crypto_skcipher_ctx(tfm); + + return ecb_do_encrypt(req, ctx->enc_key[0]); +} + +static int aria_avx_ecb_decrypt(struct skcipher_request *req) +{ + struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); + struct aria_ctx *ctx = crypto_skcipher_ctx(tfm); + + return ecb_do_decrypt(req, ctx->dec_key[0]); +} + +static int aria_avx_set_key(struct crypto_skcipher *tfm, const u8 *key, + unsigned int keylen) +{ + return aria_set_key(&tfm->base, key, keylen); +} + +static int aria_avx_ctr_encrypt(struct skcipher_request *req) +{ + struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); + struct aria_ctx *ctx = crypto_skcipher_ctx(tfm); + struct skcipher_walk walk; + unsigned int nbytes; + int err; + + err = skcipher_walk_virt(&walk, req, false); + + while ((nbytes = walk.nbytes) > 0) { + const u8 *src = walk.src.virt.addr; + u8 *dst = walk.dst.virt.addr; + + while (nbytes >= ARIA_AESNI_PARALLEL_BLOCK_SIZE) { + u8 keystream[ARIA_AESNI_PARALLEL_BLOCK_SIZE]; + + kernel_fpu_begin(); + aria_ops.aria_ctr_crypt_16way(ctx, dst, src, keystream, + walk.iv); + kernel_fpu_end(); + dst += ARIA_AESNI_PARALLEL_BLOCK_SIZE; + src += ARIA_AESNI_PARALLEL_BLOCK_SIZE; + nbytes -= ARIA_AESNI_PARALLEL_BLOCK_SIZE; + } + + while (nbytes >= ARIA_BLOCK_SIZE) { + u8 keystream[ARIA_BLOCK_SIZE]; + + memcpy(keystream, walk.iv, ARIA_BLOCK_SIZE); + crypto_inc(walk.iv, ARIA_BLOCK_SIZE); + + aria_encrypt(ctx, keystream, keystream); + + crypto_xor_cpy(dst, src, keystream, ARIA_BLOCK_SIZE); + dst += ARIA_BLOCK_SIZE; + src += ARIA_BLOCK_SIZE; + nbytes -= ARIA_BLOCK_SIZE; + } + + if (walk.nbytes == walk.total && nbytes > 0) { + u8 keystream[ARIA_BLOCK_SIZE]; + + memcpy(keystream, walk.iv, ARIA_BLOCK_SIZE); + crypto_inc(walk.iv, ARIA_BLOCK_SIZE); + + aria_encrypt(ctx, keystream, keystream); + + crypto_xor_cpy(dst, src, keystream, nbytes); + dst += nbytes; + src += nbytes; + nbytes = 0; + } + err = skcipher_walk_done(&walk, nbytes); + } + + return err; +} + +static struct skcipher_alg aria_algs[] = { + { + .base.cra_name = "__ecb(aria)", + .base.cra_driver_name = "__ecb-aria-avx", + .base.cra_priority = 400, + .base.cra_flags = CRYPTO_ALG_INTERNAL, + .base.cra_blocksize = ARIA_BLOCK_SIZE, + .base.cra_ctxsize = sizeof(struct aria_ctx), + .base.cra_module = THIS_MODULE, + .min_keysize = ARIA_MIN_KEY_SIZE, + .max_keysize = ARIA_MAX_KEY_SIZE, + .setkey = aria_avx_set_key, + .encrypt = aria_avx_ecb_encrypt, + .decrypt = aria_avx_ecb_decrypt, + }, { + .base.cra_name = "__ctr(aria)", + .base.cra_driver_name = "__ctr-aria-avx", + .base.cra_priority = 400, + .base.cra_flags = CRYPTO_ALG_INTERNAL, + .base.cra_blocksize = 1, + .base.cra_ctxsize = sizeof(struct aria_ctx), + .base.cra_module = THIS_MODULE, + .min_keysize = ARIA_MIN_KEY_SIZE, + .max_keysize = ARIA_MAX_KEY_SIZE, + .ivsize = ARIA_BLOCK_SIZE, + .chunksize = ARIA_BLOCK_SIZE, + .walksize = 16 * ARIA_BLOCK_SIZE, + .setkey = aria_avx_set_key, + .encrypt = aria_avx_ctr_encrypt, + .decrypt = aria_avx_ctr_encrypt, + } +}; + +static struct simd_skcipher_alg *aria_simd_algs[ARRAY_SIZE(aria_algs)]; + +static int __init aria_avx_init(void) +{ + const char *feature_name; + + if (!boot_cpu_has(X86_FEATURE_AVX) || + !boot_cpu_has(X86_FEATURE_AES) || + !boot_cpu_has(X86_FEATURE_OSXSAVE)) { + pr_info("AVX or AES-NI instructions are not detected.\n"); + return -ENODEV; + } + + if (!cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, + &feature_name)) { + pr_info("CPU feature '%s' is not supported.\n", feature_name); + return -ENODEV; + } + + if (boot_cpu_has(X86_FEATURE_GFNI)) { + aria_ops.aria_encrypt_16way = aria_aesni_avx_gfni_encrypt_16way; + aria_ops.aria_decrypt_16way = aria_aesni_avx_gfni_decrypt_16way; + aria_ops.aria_ctr_crypt_16way = aria_aesni_avx_gfni_ctr_crypt_16way; + } else { + aria_ops.aria_encrypt_16way = aria_aesni_avx_encrypt_16way; + aria_ops.aria_decrypt_16way = aria_aesni_avx_decrypt_16way; + aria_ops.aria_ctr_crypt_16way = aria_aesni_avx_ctr_crypt_16way; + } + + return simd_register_skciphers_compat(aria_algs, + ARRAY_SIZE(aria_algs), + aria_simd_algs); +} + +static void __exit aria_avx_exit(void) +{ + simd_unregister_skciphers(aria_algs, ARRAY_SIZE(aria_algs), + aria_simd_algs); +} + +module_init(aria_avx_init); +module_exit(aria_avx_exit); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Taehee Yoo <[email protected]>"); +MODULE_DESCRIPTION("ARIA Cipher Algorithm, AVX/AES-NI/GFNI optimized"); +MODULE_ALIAS_CRYPTO("aria"); +MODULE_ALIAS_CRYPTO("aria-aesni-avx"); diff --git a/arch/x86/crypto/blowfish-x86_64-asm_64.S b/arch/x86/crypto/blowfish-x86_64-asm_64.S index 802d71582689..4a43e072d2d1 100644 --- a/arch/x86/crypto/blowfish-x86_64-asm_64.S +++ b/arch/x86/crypto/blowfish-x86_64-asm_64.S @@ -6,6 +6,7 @@ */ #include <linux/linkage.h> +#include <linux/cfi_types.h> .file "blowfish-x86_64-asm.S" .text @@ -141,7 +142,7 @@ SYM_FUNC_START(__blowfish_enc_blk) RET; SYM_FUNC_END(__blowfish_enc_blk) -SYM_FUNC_START(blowfish_dec_blk) +SYM_TYPED_FUNC_START(blowfish_dec_blk) /* input: * %rdi: ctx * %rsi: dst @@ -332,7 +333,7 @@ SYM_FUNC_START(__blowfish_enc_blk_4way) RET; SYM_FUNC_END(__blowfish_enc_blk_4way) -SYM_FUNC_START(blowfish_dec_blk_4way) +SYM_TYPED_FUNC_START(blowfish_dec_blk_4way) /* input: * %rdi: ctx * %rsi: dst diff --git a/arch/x86/crypto/polyval-clmulni_glue.c b/arch/x86/crypto/polyval-clmulni_glue.c index b7664d018851..8fa58b0f3cb3 100644 --- a/arch/x86/crypto/polyval-clmulni_glue.c +++ b/arch/x86/crypto/polyval-clmulni_glue.c @@ -27,13 +27,17 @@ #include <asm/cpu_device_id.h> #include <asm/simd.h> +#define POLYVAL_ALIGN 16 +#define POLYVAL_ALIGN_ATTR __aligned(POLYVAL_ALIGN) +#define POLYVAL_ALIGN_EXTRA ((POLYVAL_ALIGN - 1) & ~(CRYPTO_MINALIGN - 1)) +#define POLYVAL_CTX_SIZE (sizeof(struct polyval_tfm_ctx) + POLYVAL_ALIGN_EXTRA) #define NUM_KEY_POWERS 8 struct polyval_tfm_ctx { /* * These powers must be in the order h^8, ..., h^1. */ - u8 key_powers[NUM_KEY_POWERS][POLYVAL_BLOCK_SIZE]; + u8 key_powers[NUM_KEY_POWERS][POLYVAL_BLOCK_SIZE] POLYVAL_ALIGN_ATTR; }; struct polyval_desc_ctx { @@ -45,6 +49,11 @@ asmlinkage void clmul_polyval_update(const struct polyval_tfm_ctx *keys, const u8 *in, size_t nblocks, u8 *accumulator); asmlinkage void clmul_polyval_mul(u8 *op1, const u8 *op2); +static inline struct polyval_tfm_ctx *polyval_tfm_ctx(struct crypto_shash *tfm) +{ + return PTR_ALIGN(crypto_shash_ctx(tfm), POLYVAL_ALIGN); +} + static void internal_polyval_update(const struct polyval_tfm_ctx *keys, const u8 *in, size_t nblocks, u8 *accumulator) { @@ -72,7 +81,7 @@ static void internal_polyval_mul(u8 *op1, const u8 *op2) static int polyval_x86_setkey(struct crypto_shash *tfm, const u8 *key, unsigned int keylen) { - struct polyval_tfm_ctx *tctx = crypto_shash_ctx(tfm); + struct polyval_tfm_ctx *tctx = polyval_tfm_ctx(tfm); int i; if (keylen != POLYVAL_BLOCK_SIZE) @@ -102,7 +111,7 @@ static int polyval_x86_update(struct shash_desc *desc, const u8 *src, unsigned int srclen) { struct polyval_desc_ctx *dctx = shash_desc_ctx(desc); - const struct polyval_tfm_ctx *tctx = crypto_shash_ctx(desc->tfm); + const struct polyval_tfm_ctx *tctx = polyval_tfm_ctx(desc->tfm); u8 *pos; unsigned int nblocks; unsigned int n; @@ -143,7 +152,7 @@ static int polyval_x86_update(struct shash_desc *desc, static int polyval_x86_final(struct shash_desc *desc, u8 *dst) { struct polyval_desc_ctx *dctx = shash_desc_ctx(desc); - const struct polyval_tfm_ctx *tctx = crypto_shash_ctx(desc->tfm); + const struct polyval_tfm_ctx *tctx = polyval_tfm_ctx(desc->tfm); if (dctx->bytes) { internal_polyval_mul(dctx->buffer, @@ -167,7 +176,7 @@ static struct shash_alg polyval_alg = { .cra_driver_name = "polyval-clmulni", .cra_priority = 200, .cra_blocksize = POLYVAL_BLOCK_SIZE, - .cra_ctxsize = sizeof(struct polyval_tfm_ctx), + .cra_ctxsize = POLYVAL_CTX_SIZE, .cra_module = THIS_MODULE, }, }; diff --git a/arch/x86/crypto/sha512_ssse3_glue.c b/arch/x86/crypto/sha512_ssse3_glue.c index 30e70f4fe2f7..6d3b85e53d0e 100644 --- a/arch/x86/crypto/sha512_ssse3_glue.c +++ b/arch/x86/crypto/sha512_ssse3_glue.c @@ -36,6 +36,7 @@ #include <linux/types.h> #include <crypto/sha2.h> #include <crypto/sha512_base.h> +#include <asm/cpu_device_id.h> #include <asm/simd.h> asmlinkage void sha512_transform_ssse3(struct sha512_state *state, @@ -284,6 +285,13 @@ static int register_sha512_avx2(void) ARRAY_SIZE(sha512_avx2_algs)); return 0; } +static const struct x86_cpu_id module_cpu_ids[] = { + X86_MATCH_FEATURE(X86_FEATURE_AVX2, NULL), + X86_MATCH_FEATURE(X86_FEATURE_AVX, NULL), + X86_MATCH_FEATURE(X86_FEATURE_SSSE3, NULL), + {} +}; +MODULE_DEVICE_TABLE(x86cpu, module_cpu_ids); static void unregister_sha512_avx2(void) { @@ -294,6 +302,8 @@ static void unregister_sha512_avx2(void) static int __init sha512_ssse3_mod_init(void) { + if (!x86_match_cpu(module_cpu_ids)) + return -ENODEV; if (register_sha512_ssse3()) goto fail; diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S index 682338e7e2a3..4dd19819053a 100644 --- a/arch/x86/entry/entry_64_compat.S +++ b/arch/x86/entry/entry_64_compat.S @@ -311,7 +311,7 @@ SYM_CODE_START(entry_INT80_compat) * Interrupts are off on entry. */ ASM_CLAC /* Do this early to minimize exposure */ - SWAPGS + ALTERNATIVE "swapgs", "", X86_FEATURE_XENPV /* * User tracing code (ptrace or signal handlers) might assume that diff --git a/arch/x86/entry/vdso/Makefile b/arch/x86/entry/vdso/Makefile index 12f6c4d714cd..3e88b9df8c8f 100644 --- a/arch/x86/entry/vdso/Makefile +++ b/arch/x86/entry/vdso/Makefile @@ -11,6 +11,9 @@ include $(srctree)/lib/vdso/Makefile # Sanitizer runtimes are unavailable and cannot be linked here. KASAN_SANITIZE := n +KMSAN_SANITIZE_vclock_gettime.o := n +KMSAN_SANITIZE_vgetcpu.o := n + UBSAN_SANITIZE := n KCSAN_SANITIZE := n OBJECT_FILES_NON_STANDARD := y @@ -91,7 +94,7 @@ ifneq ($(RETPOLINE_VDSO_CFLAGS),) endif endif -$(vobjs): KBUILD_CFLAGS := $(filter-out $(CC_FLAGS_LTO) $(RANDSTRUCT_CFLAGS) $(GCC_PLUGINS_CFLAGS) $(RETPOLINE_CFLAGS),$(KBUILD_CFLAGS)) $(CFL) +$(vobjs): KBUILD_CFLAGS := $(filter-out $(CC_FLAGS_LTO) $(CC_FLAGS_CFI) $(RANDSTRUCT_CFLAGS) $(GCC_PLUGINS_CFLAGS) $(RETPOLINE_CFLAGS),$(KBUILD_CFLAGS)) $(CFL) $(vobjs): KBUILD_AFLAGS += -DBUILD_VDSO # @@ -153,6 +156,7 @@ KBUILD_CFLAGS_32 := $(filter-out $(RANDSTRUCT_CFLAGS),$(KBUILD_CFLAGS_32)) KBUILD_CFLAGS_32 := $(filter-out $(GCC_PLUGINS_CFLAGS),$(KBUILD_CFLAGS_32)) KBUILD_CFLAGS_32 := $(filter-out $(RETPOLINE_CFLAGS),$(KBUILD_CFLAGS_32)) KBUILD_CFLAGS_32 := $(filter-out $(CC_FLAGS_LTO),$(KBUILD_CFLAGS_32)) +KBUILD_CFLAGS_32 := $(filter-out $(CC_FLAGS_CFI),$(KBUILD_CFLAGS_32)) KBUILD_CFLAGS_32 += -m32 -msoft-float -mregparm=0 -fpic KBUILD_CFLAGS_32 += -fno-stack-protector KBUILD_CFLAGS_32 += $(call cc-option, -foptimize-sibling-calls) diff --git a/arch/x86/entry/vdso/vma.c b/arch/x86/entry/vdso/vma.c index 1000d457c332..311eae30e089 100644 --- a/arch/x86/entry/vdso/vma.c +++ b/arch/x86/entry/vdso/vma.c @@ -127,17 +127,17 @@ int vdso_join_timens(struct task_struct *task, struct time_namespace *ns) { struct mm_struct *mm = task->mm; struct vm_area_struct *vma; + VMA_ITERATOR(vmi, mm, 0); mmap_read_lock(mm); - - for (vma = mm->mmap; vma; vma = vma->vm_next) { + for_each_vma(vmi, vma) { unsigned long size = vma->vm_end - vma->vm_start; if (vma_is_special_mapping(vma, &vvar_mapping)) zap_page_range(vma, vma->vm_start, size); } - mmap_read_unlock(mm); + return 0; } #else @@ -327,7 +327,7 @@ static unsigned long vdso_addr(unsigned long start, unsigned len) end -= len; if (end > start) { - offset = get_random_int() % (((end - start) >> PAGE_SHIFT) + 1); + offset = prandom_u32_max(((end - start) >> PAGE_SHIFT) + 1); addr = start + (offset << PAGE_SHIFT); } else { addr = start; @@ -354,6 +354,7 @@ int map_vdso_once(const struct vdso_image *image, unsigned long addr) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma; + VMA_ITERATOR(vmi, mm, 0); mmap_write_lock(mm); /* @@ -363,7 +364,7 @@ int map_vdso_once(const struct vdso_image *image, unsigned long addr) * We could search vma near context.vdso, but it's a slowpath, * so let's explicitly check all VMAs to be completely sure. */ - for (vma = mm->mmap; vma; vma = vma->vm_next) { + for_each_vma(vmi, vma) { if (vma_is_special_mapping(vma, &vdso_mapping) || vma_is_special_mapping(vma, &vvar_mapping)) { mmap_write_unlock(mm); diff --git a/arch/x86/events/Makefile b/arch/x86/events/Makefile index 9933c0e8e97a..86a76efa8bb6 100644 --- a/arch/x86/events/Makefile +++ b/arch/x86/events/Makefile @@ -1,5 +1,5 @@ # SPDX-License-Identifier: GPL-2.0-only -obj-y += core.o probe.o +obj-y += core.o probe.o utils.o obj-$(CONFIG_PERF_EVENTS_INTEL_RAPL) += rapl.o obj-y += amd/ obj-$(CONFIG_X86_LOCAL_APIC) += msr.o diff --git a/arch/x86/events/amd/Makefile b/arch/x86/events/amd/Makefile index b9f5d4610256..527d947eb76b 100644 --- a/arch/x86/events/amd/Makefile +++ b/arch/x86/events/amd/Makefile @@ -1,5 +1,5 @@ # SPDX-License-Identifier: GPL-2.0 -obj-$(CONFIG_CPU_SUP_AMD) += core.o +obj-$(CONFIG_CPU_SUP_AMD) += core.o lbr.o obj-$(CONFIG_PERF_EVENTS_AMD_BRS) += brs.o obj-$(CONFIG_PERF_EVENTS_AMD_POWER) += power.o obj-$(CONFIG_X86_LOCAL_APIC) += ibs.o diff --git a/arch/x86/events/amd/brs.c b/arch/x86/events/amd/brs.c index bee8765a1e9b..f1bff153d945 100644 --- a/arch/x86/events/amd/brs.c +++ b/arch/x86/events/amd/brs.c @@ -81,7 +81,7 @@ static bool __init amd_brs_detect(void) * a br_sel_map. Software filtering is not supported because it would not correlate well * with a sampling period. */ -int amd_brs_setup_filter(struct perf_event *event) +static int amd_brs_setup_filter(struct perf_event *event) { u64 type = event->attr.branch_sample_type; @@ -96,6 +96,73 @@ int amd_brs_setup_filter(struct perf_event *event) return 0; } +static inline int amd_is_brs_event(struct perf_event *e) +{ + return (e->hw.config & AMD64_RAW_EVENT_MASK) == AMD_FAM19H_BRS_EVENT; +} + +int amd_brs_hw_config(struct perf_event *event) +{ + int ret = 0; + + /* + * Due to interrupt holding, BRS is not recommended in + * counting mode. + */ + if (!is_sampling_event(event)) + return -EINVAL; + + /* + * Due to the way BRS operates by holding the interrupt until + * lbr_nr entries have been captured, it does not make sense + * to allow sampling on BRS with an event that does not match + * what BRS is capturing, i.e., retired taken branches. + * Otherwise the correlation with the event's period is even + * more loose: + * + * With retired taken branch: + * Effective P = P + 16 + X + * With any other event: + * Effective P = P + Y + X + * + * Where X is the number of taken branches due to interrupt + * skid. Skid is large. + * + * Where Y is the occurences of the event while BRS is + * capturing the lbr_nr entries. + * + * By using retired taken branches, we limit the impact on the + * Y variable. We know it cannot be more than the depth of + * BRS. + */ + if (!amd_is_brs_event(event)) + return -EINVAL; + + /* + * BRS implementation does not work with frequency mode + * reprogramming of the period. + */ + if (event->attr.freq) + return -EINVAL; + /* + * The kernel subtracts BRS depth from period, so it must + * be big enough. + */ + if (event->attr.sample_period <= x86_pmu.lbr_nr) + return -EINVAL; + + /* + * Check if we can allow PERF_SAMPLE_BRANCH_STACK + */ + ret = amd_brs_setup_filter(event); + + /* only set in case of success */ + if (!ret) + event->hw.flags |= PERF_X86_EVENT_AMD_BRS; + + return ret; +} + /* tos = top of stack, i.e., last valid entry written */ static inline int amd_brs_get_tos(union amd_debug_extn_cfg *cfg) { diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c index 9ac3718410ce..d6f3703e4119 100644 --- a/arch/x86/events/amd/core.c +++ b/arch/x86/events/amd/core.c @@ -330,16 +330,10 @@ static inline bool amd_is_pair_event_code(struct hw_perf_event *hwc) } } -#define AMD_FAM19H_BRS_EVENT 0xc4 /* RETIRED_TAKEN_BRANCH_INSTRUCTIONS */ -static inline int amd_is_brs_event(struct perf_event *e) -{ - return (e->hw.config & AMD64_RAW_EVENT_MASK) == AMD_FAM19H_BRS_EVENT; -} +DEFINE_STATIC_CALL_RET0(amd_pmu_branch_hw_config, *x86_pmu.hw_config); static int amd_core_hw_config(struct perf_event *event) { - int ret = 0; - if (event->attr.exclude_host && event->attr.exclude_guest) /* * When HO == GO == 1 the hardware treats that as GO == HO == 0 @@ -356,66 +350,10 @@ static int amd_core_hw_config(struct perf_event *event) if ((x86_pmu.flags & PMU_FL_PAIR) && amd_is_pair_event_code(&event->hw)) event->hw.flags |= PERF_X86_EVENT_PAIR; - /* - * if branch stack is requested - */ - if (has_branch_stack(event)) { - /* - * Due to interrupt holding, BRS is not recommended in - * counting mode. - */ - if (!is_sampling_event(event)) - return -EINVAL; - - /* - * Due to the way BRS operates by holding the interrupt until - * lbr_nr entries have been captured, it does not make sense - * to allow sampling on BRS with an event that does not match - * what BRS is capturing, i.e., retired taken branches. - * Otherwise the correlation with the event's period is even - * more loose: - * - * With retired taken branch: - * Effective P = P + 16 + X - * With any other event: - * Effective P = P + Y + X - * - * Where X is the number of taken branches due to interrupt - * skid. Skid is large. - * - * Where Y is the occurences of the event while BRS is - * capturing the lbr_nr entries. - * - * By using retired taken branches, we limit the impact on the - * Y variable. We know it cannot be more than the depth of - * BRS. - */ - if (!amd_is_brs_event(event)) - return -EINVAL; - - /* - * BRS implementation does not work with frequency mode - * reprogramming of the period. - */ - if (event->attr.freq) - return -EINVAL; - /* - * The kernel subtracts BRS depth from period, so it must - * be big enough. - */ - if (event->attr.sample_period <= x86_pmu.lbr_nr) - return -EINVAL; - - /* - * Check if we can allow PERF_SAMPLE_BRANCH_STACK - */ - ret = amd_brs_setup_filter(event); + if (has_branch_stack(event)) + return static_call(amd_pmu_branch_hw_config)(event); - /* only set in case of success */ - if (!ret) - event->hw.flags |= PERF_X86_EVENT_AMD_BRS; - } - return ret; + return 0; } static inline int amd_is_nb_event(struct hw_perf_event *hwc) @@ -582,8 +520,14 @@ static struct amd_nb *amd_alloc_nb(int cpu) return nb; } +typedef void (amd_pmu_branch_reset_t)(void); +DEFINE_STATIC_CALL_NULL(amd_pmu_branch_reset, amd_pmu_branch_reset_t); + static void amd_pmu_cpu_reset(int cpu) { + if (x86_pmu.lbr_nr) + static_call(amd_pmu_branch_reset)(); + if (x86_pmu.version < 2) return; @@ -598,16 +542,24 @@ static int amd_pmu_cpu_prepare(int cpu) { struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu); + cpuc->lbr_sel = kzalloc_node(sizeof(struct er_account), GFP_KERNEL, + cpu_to_node(cpu)); + if (!cpuc->lbr_sel) + return -ENOMEM; + WARN_ON_ONCE(cpuc->amd_nb); if (!x86_pmu.amd_nb_constraints) return 0; cpuc->amd_nb = amd_alloc_nb(cpu); - if (!cpuc->amd_nb) - return -ENOMEM; + if (cpuc->amd_nb) + return 0; - return 0; + kfree(cpuc->lbr_sel); + cpuc->lbr_sel = NULL; + + return -ENOMEM; } static void amd_pmu_cpu_starting(int cpu) @@ -640,19 +592,19 @@ static void amd_pmu_cpu_starting(int cpu) cpuc->amd_nb->nb_id = nb_id; cpuc->amd_nb->refcnt++; - amd_brs_reset(); amd_pmu_cpu_reset(cpu); } static void amd_pmu_cpu_dead(int cpu) { - struct cpu_hw_events *cpuhw; + struct cpu_hw_events *cpuhw = &per_cpu(cpu_hw_events, cpu); + + kfree(cpuhw->lbr_sel); + cpuhw->lbr_sel = NULL; if (!x86_pmu.amd_nb_constraints) return; - cpuhw = &per_cpu(cpu_hw_events, cpu); - if (cpuhw->amd_nb) { struct amd_nb *nb = cpuhw->amd_nb; @@ -677,7 +629,7 @@ static inline u64 amd_pmu_get_global_status(void) /* PerfCntrGlobalStatus is read-only */ rdmsrl(MSR_AMD64_PERF_CNTR_GLOBAL_STATUS, status); - return status & amd_pmu_global_cntr_mask; + return status; } static inline void amd_pmu_ack_global_status(u64 status) @@ -688,8 +640,6 @@ static inline void amd_pmu_ack_global_status(u64 status) * clears the same bit in PerfCntrGlobalStatus */ - /* Only allow modifications to PerfCntrGlobalStatus.PerfCntrOvfl */ - status &= amd_pmu_global_cntr_mask; wrmsrl(MSR_AMD64_PERF_CNTR_GLOBAL_STATUS_CLR, status); } @@ -799,11 +749,17 @@ static void amd_pmu_v2_enable_event(struct perf_event *event) __x86_pmu_enable_event(hwc, ARCH_PERFMON_EVENTSEL_ENABLE); } -static void amd_pmu_v2_enable_all(int added) +static __always_inline void amd_pmu_core_enable_all(void) { amd_pmu_set_global_ctl(amd_pmu_global_cntr_mask); } +static void amd_pmu_v2_enable_all(int added) +{ + amd_pmu_lbr_enable_all(); + amd_pmu_core_enable_all(); +} + static void amd_pmu_disable_event(struct perf_event *event) { x86_pmu_disable_event(event); @@ -828,23 +784,32 @@ static void amd_pmu_disable_all(void) amd_pmu_check_overflow(); } -static void amd_pmu_v2_disable_all(void) +static __always_inline void amd_pmu_core_disable_all(void) { - /* Disable all PMCs */ amd_pmu_set_global_ctl(0); +} + +static void amd_pmu_v2_disable_all(void) +{ + amd_pmu_core_disable_all(); + amd_pmu_lbr_disable_all(); amd_pmu_check_overflow(); } +DEFINE_STATIC_CALL_NULL(amd_pmu_branch_add, *x86_pmu.add); + static void amd_pmu_add_event(struct perf_event *event) { if (needs_branch_stack(event)) - amd_pmu_brs_add(event); + static_call(amd_pmu_branch_add)(event); } +DEFINE_STATIC_CALL_NULL(amd_pmu_branch_del, *x86_pmu.del); + static void amd_pmu_del_event(struct perf_event *event) { if (needs_branch_stack(event)) - amd_pmu_brs_del(event); + static_call(amd_pmu_branch_del)(event); } /* @@ -896,8 +861,7 @@ static int amd_pmu_handle_irq(struct pt_regs *regs) pmu_enabled = cpuc->enabled; cpuc->enabled = 0; - /* stop everything (includes BRS) */ - amd_pmu_disable_all(); + amd_brs_disable_all(); /* Drain BRS is in use (could be inactive) */ if (cpuc->lbr_users) @@ -908,7 +872,7 @@ static int amd_pmu_handle_irq(struct pt_regs *regs) cpuc->enabled = pmu_enabled; if (pmu_enabled) - amd_pmu_enable_all(0); + amd_brs_enable_all(); return amd_pmu_adjust_nmi_window(handled); } @@ -930,8 +894,8 @@ static int amd_pmu_v2_handle_irq(struct pt_regs *regs) pmu_enabled = cpuc->enabled; cpuc->enabled = 0; - /* Stop counting */ - amd_pmu_v2_disable_all(); + /* Stop counting but do not disable LBR */ + amd_pmu_core_disable_all(); status = amd_pmu_get_global_status(); @@ -939,6 +903,12 @@ static int amd_pmu_v2_handle_irq(struct pt_regs *regs) if (!status) goto done; + /* Read branch records before unfreezing */ + if (status & GLOBAL_STATUS_LBRS_FROZEN) { + amd_pmu_lbr_read(); + status &= ~GLOBAL_STATUS_LBRS_FROZEN; + } + for (idx = 0; idx < x86_pmu.num_counters; idx++) { if (!test_bit(idx, cpuc->active_mask)) continue; @@ -958,6 +928,11 @@ static int amd_pmu_v2_handle_irq(struct pt_regs *regs) if (!x86_perf_event_set_period(event)) continue; + if (has_branch_stack(event)) { + data.br_stack = &cpuc->lbr_stack; + data.sample_flags |= PERF_SAMPLE_BRANCH_STACK; + } + if (perf_event_overflow(event, &data, regs)) x86_pmu_stop(event, 0); @@ -971,7 +946,7 @@ static int amd_pmu_v2_handle_irq(struct pt_regs *regs) */ WARN_ON(status > 0); - /* Clear overflow bits */ + /* Clear overflow and freeze bits */ amd_pmu_ack_global_status(~status); /* @@ -985,7 +960,7 @@ done: /* Resume counting only if PMU is active */ if (pmu_enabled) - amd_pmu_v2_enable_all(0); + amd_pmu_core_enable_all(); return amd_pmu_adjust_nmi_window(handled); } @@ -1248,23 +1223,14 @@ static ssize_t amd_event_sysfs_show(char *page, u64 config) return x86_event_sysfs_show(page, config, event); } -static void amd_pmu_sched_task(struct perf_event_context *ctx, - bool sched_in) -{ - if (sched_in && x86_pmu.lbr_nr) - amd_pmu_brs_sched_task(ctx, sched_in); -} - -static u64 amd_pmu_limit_period(struct perf_event *event, u64 left) +static void amd_pmu_limit_period(struct perf_event *event, s64 *left) { /* * Decrease period by the depth of the BRS feature to get the last N * taken branches and approximate the desired period */ - if (has_branch_stack(event) && left > x86_pmu.lbr_nr) - left -= x86_pmu.lbr_nr; - - return left; + if (has_branch_stack(event) && *left > x86_pmu.lbr_nr) + *left -= x86_pmu.lbr_nr; } static __initconst const struct x86_pmu amd_pmu = { @@ -1311,23 +1277,25 @@ static ssize_t branches_show(struct device *cdev, static DEVICE_ATTR_RO(branches); -static struct attribute *amd_pmu_brs_attrs[] = { +static struct attribute *amd_pmu_branches_attrs[] = { &dev_attr_branches.attr, NULL, }; static umode_t -amd_brs_is_visible(struct kobject *kobj, struct attribute *attr, int i) +amd_branches_is_visible(struct kobject *kobj, struct attribute *attr, int i) { return x86_pmu.lbr_nr ? attr->mode : 0; } -static struct attribute_group group_caps_amd_brs = { +static struct attribute_group group_caps_amd_branches = { .name = "caps", - .attrs = amd_pmu_brs_attrs, - .is_visible = amd_brs_is_visible, + .attrs = amd_pmu_branches_attrs, + .is_visible = amd_branches_is_visible, }; +#ifdef CONFIG_PERF_EVENTS_AMD_BRS + EVENT_ATTR_STR(branch-brs, amd_branch_brs, "event=" __stringify(AMD_FAM19H_BRS_EVENT)"\n"); @@ -1336,15 +1304,26 @@ static struct attribute *amd_brs_events_attrs[] = { NULL, }; +static umode_t +amd_brs_is_visible(struct kobject *kobj, struct attribute *attr, int i) +{ + return static_cpu_has(X86_FEATURE_BRS) && x86_pmu.lbr_nr ? + attr->mode : 0; +} + static struct attribute_group group_events_amd_brs = { .name = "events", .attrs = amd_brs_events_attrs, .is_visible = amd_brs_is_visible, }; +#endif /* CONFIG_PERF_EVENTS_AMD_BRS */ + static const struct attribute_group *amd_attr_update[] = { - &group_caps_amd_brs, + &group_caps_amd_branches, +#ifdef CONFIG_PERF_EVENTS_AMD_BRS &group_events_amd_brs, +#endif NULL, }; @@ -1421,13 +1400,27 @@ static int __init amd_core_pmu_init(void) x86_pmu.flags |= PMU_FL_PAIR; } - /* - * BRS requires special event constraints and flushing on ctxsw. - */ - if (boot_cpu_data.x86 >= 0x19 && !amd_brs_init()) { + /* LBR and BRS are mutually exclusive features */ + if (!amd_pmu_lbr_init()) { + /* LBR requires flushing on context switch */ + x86_pmu.sched_task = amd_pmu_lbr_sched_task; + static_call_update(amd_pmu_branch_hw_config, amd_pmu_lbr_hw_config); + static_call_update(amd_pmu_branch_reset, amd_pmu_lbr_reset); + static_call_update(amd_pmu_branch_add, amd_pmu_lbr_add); + static_call_update(amd_pmu_branch_del, amd_pmu_lbr_del); + } else if (!amd_brs_init()) { + /* + * BRS requires special event constraints and flushing on ctxsw. + */ x86_pmu.get_event_constraints = amd_get_event_constraints_f19h; - x86_pmu.sched_task = amd_pmu_sched_task; + x86_pmu.sched_task = amd_pmu_brs_sched_task; x86_pmu.limit_period = amd_pmu_limit_period; + + static_call_update(amd_pmu_branch_hw_config, amd_brs_hw_config); + static_call_update(amd_pmu_branch_reset, amd_brs_reset); + static_call_update(amd_pmu_branch_add, amd_pmu_brs_add); + static_call_update(amd_pmu_branch_del, amd_pmu_brs_del); + /* * put_event_constraints callback same as Fam17h, set above */ diff --git a/arch/x86/events/amd/ibs.c b/arch/x86/events/amd/ibs.c index c251bc44c088..4cb710efbdd9 100644 --- a/arch/x86/events/amd/ibs.c +++ b/arch/x86/events/amd/ibs.c @@ -300,16 +300,6 @@ static int perf_ibs_init(struct perf_event *event) hwc->config_base = perf_ibs->msr; hwc->config = config; - /* - * rip recorded by IbsOpRip will not be consistent with rsp and rbp - * recorded as part of interrupt regs. Thus we need to use rip from - * interrupt regs while unwinding call stack. Setting _EARLY flag - * makes sure we unwind call-stack before perf sample rip is set to - * IbsOpRip. - */ - if (event->attr.sample_type & PERF_SAMPLE_CALLCHAIN) - event->attr.sample_type |= __PERF_SAMPLE_CALLCHAIN_EARLY; - return 0; } @@ -688,6 +678,339 @@ static struct perf_ibs perf_ibs_op = { .get_count = get_ibs_op_count, }; +static void perf_ibs_get_mem_op(union ibs_op_data3 *op_data3, + struct perf_sample_data *data) +{ + union perf_mem_data_src *data_src = &data->data_src; + + data_src->mem_op = PERF_MEM_OP_NA; + + if (op_data3->ld_op) + data_src->mem_op = PERF_MEM_OP_LOAD; + else if (op_data3->st_op) + data_src->mem_op = PERF_MEM_OP_STORE; +} + +/* + * Processors having CPUID_Fn8000001B_EAX[11] aka IBS_CAPS_ZEN4 has + * more fine granular DataSrc encodings. Others have coarse. + */ +static u8 perf_ibs_data_src(union ibs_op_data2 *op_data2) +{ + if (ibs_caps & IBS_CAPS_ZEN4) + return (op_data2->data_src_hi << 3) | op_data2->data_src_lo; + + return op_data2->data_src_lo; +} + +static void perf_ibs_get_mem_lvl(union ibs_op_data2 *op_data2, + union ibs_op_data3 *op_data3, + struct perf_sample_data *data) +{ + union perf_mem_data_src *data_src = &data->data_src; + u8 ibs_data_src = perf_ibs_data_src(op_data2); + + data_src->mem_lvl = 0; + + /* + * DcMiss, L2Miss, DataSrc, DcMissLat etc. are all invalid for Uncached + * memory accesses. So, check DcUcMemAcc bit early. + */ + if (op_data3->dc_uc_mem_acc && ibs_data_src != IBS_DATA_SRC_EXT_IO) { + data_src->mem_lvl = PERF_MEM_LVL_UNC | PERF_MEM_LVL_HIT; + return; + } + + /* L1 Hit */ + if (op_data3->dc_miss == 0) { + data_src->mem_lvl = PERF_MEM_LVL_L1 | PERF_MEM_LVL_HIT; + return; + } + + /* L2 Hit */ + if (op_data3->l2_miss == 0) { + /* Erratum #1293 */ + if (boot_cpu_data.x86 != 0x19 || boot_cpu_data.x86_model > 0xF || + !(op_data3->sw_pf || op_data3->dc_miss_no_mab_alloc)) { + data_src->mem_lvl = PERF_MEM_LVL_L2 | PERF_MEM_LVL_HIT; + return; + } + } + + /* + * OP_DATA2 is valid only for load ops. Skip all checks which + * uses OP_DATA2[DataSrc]. + */ + if (data_src->mem_op != PERF_MEM_OP_LOAD) + goto check_mab; + + /* L3 Hit */ + if (ibs_caps & IBS_CAPS_ZEN4) { + if (ibs_data_src == IBS_DATA_SRC_EXT_LOC_CACHE) { + data_src->mem_lvl = PERF_MEM_LVL_L3 | PERF_MEM_LVL_HIT; + return; + } + } else { + if (ibs_data_src == IBS_DATA_SRC_LOC_CACHE) { + data_src->mem_lvl = PERF_MEM_LVL_L3 | PERF_MEM_LVL_REM_CCE1 | + PERF_MEM_LVL_HIT; + return; + } + } + + /* A peer cache in a near CCX */ + if (ibs_caps & IBS_CAPS_ZEN4 && + ibs_data_src == IBS_DATA_SRC_EXT_NEAR_CCX_CACHE) { + data_src->mem_lvl = PERF_MEM_LVL_REM_CCE1 | PERF_MEM_LVL_HIT; + return; + } + + /* A peer cache in a far CCX */ + if (ibs_caps & IBS_CAPS_ZEN4) { + if (ibs_data_src == IBS_DATA_SRC_EXT_FAR_CCX_CACHE) { + data_src->mem_lvl = PERF_MEM_LVL_REM_CCE2 | PERF_MEM_LVL_HIT; + return; + } + } else { + if (ibs_data_src == IBS_DATA_SRC_REM_CACHE) { + data_src->mem_lvl = PERF_MEM_LVL_REM_CCE2 | PERF_MEM_LVL_HIT; + return; + } + } + + /* DRAM */ + if (ibs_data_src == IBS_DATA_SRC_EXT_DRAM) { + if (op_data2->rmt_node == 0) + data_src->mem_lvl = PERF_MEM_LVL_LOC_RAM | PERF_MEM_LVL_HIT; + else + data_src->mem_lvl = PERF_MEM_LVL_REM_RAM1 | PERF_MEM_LVL_HIT; + return; + } + + /* PMEM */ + if (ibs_caps & IBS_CAPS_ZEN4 && ibs_data_src == IBS_DATA_SRC_EXT_PMEM) { + data_src->mem_lvl_num = PERF_MEM_LVLNUM_PMEM; + if (op_data2->rmt_node) { + data_src->mem_remote = PERF_MEM_REMOTE_REMOTE; + /* IBS doesn't provide Remote socket detail */ + data_src->mem_hops = PERF_MEM_HOPS_1; + } + return; + } + + /* Extension Memory */ + if (ibs_caps & IBS_CAPS_ZEN4 && + ibs_data_src == IBS_DATA_SRC_EXT_EXT_MEM) { + data_src->mem_lvl_num = PERF_MEM_LVLNUM_CXL; + if (op_data2->rmt_node) { + data_src->mem_remote = PERF_MEM_REMOTE_REMOTE; + /* IBS doesn't provide Remote socket detail */ + data_src->mem_hops = PERF_MEM_HOPS_1; + } + return; + } + + /* IO */ + if (ibs_data_src == IBS_DATA_SRC_EXT_IO) { + data_src->mem_lvl = PERF_MEM_LVL_IO; + data_src->mem_lvl_num = PERF_MEM_LVLNUM_IO; + if (op_data2->rmt_node) { + data_src->mem_remote = PERF_MEM_REMOTE_REMOTE; + /* IBS doesn't provide Remote socket detail */ + data_src->mem_hops = PERF_MEM_HOPS_1; + } + return; + } + +check_mab: + /* + * MAB (Miss Address Buffer) Hit. MAB keeps track of outstanding + * DC misses. However, such data may come from any level in mem + * hierarchy. IBS provides detail about both MAB as well as actual + * DataSrc simultaneously. Prioritize DataSrc over MAB, i.e. set + * MAB only when IBS fails to provide DataSrc. + */ + if (op_data3->dc_miss_no_mab_alloc) { + data_src->mem_lvl = PERF_MEM_LVL_LFB | PERF_MEM_LVL_HIT; + return; + } + + data_src->mem_lvl = PERF_MEM_LVL_NA; +} + +static bool perf_ibs_cache_hit_st_valid(void) +{ + /* 0: Uninitialized, 1: Valid, -1: Invalid */ + static int cache_hit_st_valid; + + if (unlikely(!cache_hit_st_valid)) { + if (boot_cpu_data.x86 == 0x19 && + (boot_cpu_data.x86_model <= 0xF || + (boot_cpu_data.x86_model >= 0x20 && + boot_cpu_data.x86_model <= 0x5F))) { + cache_hit_st_valid = -1; + } else { + cache_hit_st_valid = 1; + } + } + + return cache_hit_st_valid == 1; +} + +static void perf_ibs_get_mem_snoop(union ibs_op_data2 *op_data2, + struct perf_sample_data *data) +{ + union perf_mem_data_src *data_src = &data->data_src; + u8 ibs_data_src; + + data_src->mem_snoop = PERF_MEM_SNOOP_NA; + + if (!perf_ibs_cache_hit_st_valid() || + data_src->mem_op != PERF_MEM_OP_LOAD || + data_src->mem_lvl & PERF_MEM_LVL_L1 || + data_src->mem_lvl & PERF_MEM_LVL_L2 || + op_data2->cache_hit_st) + return; + + ibs_data_src = perf_ibs_data_src(op_data2); + + if (ibs_caps & IBS_CAPS_ZEN4) { + if (ibs_data_src == IBS_DATA_SRC_EXT_LOC_CACHE || + ibs_data_src == IBS_DATA_SRC_EXT_NEAR_CCX_CACHE || + ibs_data_src == IBS_DATA_SRC_EXT_FAR_CCX_CACHE) + data_src->mem_snoop = PERF_MEM_SNOOP_HITM; + } else if (ibs_data_src == IBS_DATA_SRC_LOC_CACHE) { + data_src->mem_snoop = PERF_MEM_SNOOP_HITM; + } +} + +static void perf_ibs_get_tlb_lvl(union ibs_op_data3 *op_data3, + struct perf_sample_data *data) +{ + union perf_mem_data_src *data_src = &data->data_src; + + data_src->mem_dtlb = PERF_MEM_TLB_NA; + + if (!op_data3->dc_lin_addr_valid) + return; + + if (!op_data3->dc_l1tlb_miss) { + data_src->mem_dtlb = PERF_MEM_TLB_L1 | PERF_MEM_TLB_HIT; + return; + } + + if (!op_data3->dc_l2tlb_miss) { + data_src->mem_dtlb = PERF_MEM_TLB_L2 | PERF_MEM_TLB_HIT; + return; + } + + data_src->mem_dtlb = PERF_MEM_TLB_L2 | PERF_MEM_TLB_MISS; +} + +static void perf_ibs_get_mem_lock(union ibs_op_data3 *op_data3, + struct perf_sample_data *data) +{ + union perf_mem_data_src *data_src = &data->data_src; + + data_src->mem_lock = PERF_MEM_LOCK_NA; + + if (op_data3->dc_locked_op) + data_src->mem_lock = PERF_MEM_LOCK_LOCKED; +} + +#define ibs_op_msr_idx(msr) (msr - MSR_AMD64_IBSOPCTL) + +static void perf_ibs_get_data_src(struct perf_ibs_data *ibs_data, + struct perf_sample_data *data, + union ibs_op_data2 *op_data2, + union ibs_op_data3 *op_data3) +{ + perf_ibs_get_mem_lvl(op_data2, op_data3, data); + perf_ibs_get_mem_snoop(op_data2, data); + perf_ibs_get_tlb_lvl(op_data3, data); + perf_ibs_get_mem_lock(op_data3, data); +} + +static __u64 perf_ibs_get_op_data2(struct perf_ibs_data *ibs_data, + union ibs_op_data3 *op_data3) +{ + __u64 val = ibs_data->regs[ibs_op_msr_idx(MSR_AMD64_IBSOPDATA2)]; + + /* Erratum #1293 */ + if (boot_cpu_data.x86 == 0x19 && boot_cpu_data.x86_model <= 0xF && + (op_data3->sw_pf || op_data3->dc_miss_no_mab_alloc)) { + /* + * OP_DATA2 has only two fields on Zen3: DataSrc and RmtNode. + * DataSrc=0 is 'No valid status' and RmtNode is invalid when + * DataSrc=0. + */ + val = 0; + } + return val; +} + +static void perf_ibs_parse_ld_st_data(__u64 sample_type, + struct perf_ibs_data *ibs_data, + struct perf_sample_data *data) +{ + union ibs_op_data3 op_data3; + union ibs_op_data2 op_data2; + union ibs_op_data op_data; + + data->data_src.val = PERF_MEM_NA; + op_data3.val = ibs_data->regs[ibs_op_msr_idx(MSR_AMD64_IBSOPDATA3)]; + + perf_ibs_get_mem_op(&op_data3, data); + if (data->data_src.mem_op != PERF_MEM_OP_LOAD && + data->data_src.mem_op != PERF_MEM_OP_STORE) + return; + + op_data2.val = perf_ibs_get_op_data2(ibs_data, &op_data3); + + if (sample_type & PERF_SAMPLE_DATA_SRC) { + perf_ibs_get_data_src(ibs_data, data, &op_data2, &op_data3); + data->sample_flags |= PERF_SAMPLE_DATA_SRC; + } + + if (sample_type & PERF_SAMPLE_WEIGHT_TYPE && op_data3.dc_miss && + data->data_src.mem_op == PERF_MEM_OP_LOAD) { + op_data.val = ibs_data->regs[ibs_op_msr_idx(MSR_AMD64_IBSOPDATA)]; + + if (sample_type & PERF_SAMPLE_WEIGHT_STRUCT) { + data->weight.var1_dw = op_data3.dc_miss_lat; + data->weight.var2_w = op_data.tag_to_ret_ctr; + } else if (sample_type & PERF_SAMPLE_WEIGHT) { + data->weight.full = op_data3.dc_miss_lat; + } + data->sample_flags |= PERF_SAMPLE_WEIGHT_TYPE; + } + + if (sample_type & PERF_SAMPLE_ADDR && op_data3.dc_lin_addr_valid) { + data->addr = ibs_data->regs[ibs_op_msr_idx(MSR_AMD64_IBSDCLINAD)]; + data->sample_flags |= PERF_SAMPLE_ADDR; + } + + if (sample_type & PERF_SAMPLE_PHYS_ADDR && op_data3.dc_phy_addr_valid) { + data->phys_addr = ibs_data->regs[ibs_op_msr_idx(MSR_AMD64_IBSDCPHYSAD)]; + data->sample_flags |= PERF_SAMPLE_PHYS_ADDR; + } +} + +static int perf_ibs_get_offset_max(struct perf_ibs *perf_ibs, u64 sample_type, + int check_rip) +{ + if (sample_type & PERF_SAMPLE_RAW || + (perf_ibs == &perf_ibs_op && + (sample_type & PERF_SAMPLE_DATA_SRC || + sample_type & PERF_SAMPLE_WEIGHT_TYPE || + sample_type & PERF_SAMPLE_ADDR || + sample_type & PERF_SAMPLE_PHYS_ADDR))) + return perf_ibs->offset_max; + else if (check_rip) + return 3; + return 1; +} + static int perf_ibs_handle_irq(struct perf_ibs *perf_ibs, struct pt_regs *iregs) { struct cpu_perf_ibs *pcpu = this_cpu_ptr(perf_ibs->pcpu); @@ -735,12 +1058,9 @@ fail: size = 1; offset = 1; check_rip = (perf_ibs == &perf_ibs_op && (ibs_caps & IBS_CAPS_RIPINVALIDCHK)); - if (event->attr.sample_type & PERF_SAMPLE_RAW) - offset_max = perf_ibs->offset_max; - else if (check_rip) - offset_max = 3; - else - offset_max = 1; + + offset_max = perf_ibs_get_offset_max(perf_ibs, event->attr.sample_type, check_rip); + do { rdmsrl(msr + offset, *buf++); size++; @@ -791,15 +1111,21 @@ fail: }, }; data.raw = &raw; + data.sample_flags |= PERF_SAMPLE_RAW; } + if (perf_ibs == &perf_ibs_op) + perf_ibs_parse_ld_st_data(event->attr.sample_type, &ibs_data, &data); + /* * rip recorded by IbsOpRip will not be consistent with rsp and rbp * recorded as part of interrupt regs. Thus we need to use rip from * interrupt regs while unwinding call stack. */ - if (event->attr.sample_type & PERF_SAMPLE_CALLCHAIN) + if (event->attr.sample_type & PERF_SAMPLE_CALLCHAIN) { data.callchain = perf_callchain(event, iregs); + data.sample_flags |= PERF_SAMPLE_CALLCHAIN; + } throttle = perf_event_overflow(event, &data, ®s); out: diff --git a/arch/x86/events/amd/lbr.c b/arch/x86/events/amd/lbr.c new file mode 100644 index 000000000000..38a75216c12c --- /dev/null +++ b/arch/x86/events/amd/lbr.c @@ -0,0 +1,439 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/perf_event.h> +#include <asm/perf_event.h> + +#include "../perf_event.h" + +/* LBR Branch Select valid bits */ +#define LBR_SELECT_MASK 0x1ff + +/* + * LBR Branch Select filter bits which when set, ensures that the + * corresponding type of branches are not recorded + */ +#define LBR_SELECT_KERNEL 0 /* Branches ending in CPL = 0 */ +#define LBR_SELECT_USER 1 /* Branches ending in CPL > 0 */ +#define LBR_SELECT_JCC 2 /* Conditional branches */ +#define LBR_SELECT_CALL_NEAR_REL 3 /* Near relative calls */ +#define LBR_SELECT_CALL_NEAR_IND 4 /* Indirect relative calls */ +#define LBR_SELECT_RET_NEAR 5 /* Near returns */ +#define LBR_SELECT_JMP_NEAR_IND 6 /* Near indirect jumps (excl. calls and returns) */ +#define LBR_SELECT_JMP_NEAR_REL 7 /* Near relative jumps (excl. calls) */ +#define LBR_SELECT_FAR_BRANCH 8 /* Far branches */ + +#define LBR_KERNEL BIT(LBR_SELECT_KERNEL) +#define LBR_USER BIT(LBR_SELECT_USER) +#define LBR_JCC BIT(LBR_SELECT_JCC) +#define LBR_REL_CALL BIT(LBR_SELECT_CALL_NEAR_REL) +#define LBR_IND_CALL BIT(LBR_SELECT_CALL_NEAR_IND) +#define LBR_RETURN BIT(LBR_SELECT_RET_NEAR) +#define LBR_REL_JMP BIT(LBR_SELECT_JMP_NEAR_REL) +#define LBR_IND_JMP BIT(LBR_SELECT_JMP_NEAR_IND) +#define LBR_FAR BIT(LBR_SELECT_FAR_BRANCH) +#define LBR_NOT_SUPP -1 /* unsupported filter */ +#define LBR_IGNORE 0 + +#define LBR_ANY \ + (LBR_JCC | LBR_REL_CALL | LBR_IND_CALL | LBR_RETURN | \ + LBR_REL_JMP | LBR_IND_JMP | LBR_FAR) + +struct branch_entry { + union { + struct { + u64 ip:58; + u64 ip_sign_ext:5; + u64 mispredict:1; + } split; + u64 full; + } from; + + union { + struct { + u64 ip:58; + u64 ip_sign_ext:3; + u64 reserved:1; + u64 spec:1; + u64 valid:1; + } split; + u64 full; + } to; +}; + +static __always_inline void amd_pmu_lbr_set_from(unsigned int idx, u64 val) +{ + wrmsrl(MSR_AMD_SAMP_BR_FROM + idx * 2, val); +} + +static __always_inline void amd_pmu_lbr_set_to(unsigned int idx, u64 val) +{ + wrmsrl(MSR_AMD_SAMP_BR_FROM + idx * 2 + 1, val); +} + +static __always_inline u64 amd_pmu_lbr_get_from(unsigned int idx) +{ + u64 val; + + rdmsrl(MSR_AMD_SAMP_BR_FROM + idx * 2, val); + + return val; +} + +static __always_inline u64 amd_pmu_lbr_get_to(unsigned int idx) +{ + u64 val; + + rdmsrl(MSR_AMD_SAMP_BR_FROM + idx * 2 + 1, val); + + return val; +} + +static __always_inline u64 sign_ext_branch_ip(u64 ip) +{ + u32 shift = 64 - boot_cpu_data.x86_virt_bits; + + return (u64)(((s64)ip << shift) >> shift); +} + +static void amd_pmu_lbr_filter(void) +{ + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + int br_sel = cpuc->br_sel, offset, type, i, j; + bool compress = false; + bool fused_only = false; + u64 from, to; + + /* If sampling all branches, there is nothing to filter */ + if (((br_sel & X86_BR_ALL) == X86_BR_ALL) && + ((br_sel & X86_BR_TYPE_SAVE) != X86_BR_TYPE_SAVE)) + fused_only = true; + + for (i = 0; i < cpuc->lbr_stack.nr; i++) { + from = cpuc->lbr_entries[i].from; + to = cpuc->lbr_entries[i].to; + type = branch_type_fused(from, to, 0, &offset); + + /* + * Adjust the branch from address in case of instruction + * fusion where it points to an instruction preceding the + * actual branch + */ + if (offset) { + cpuc->lbr_entries[i].from += offset; + if (fused_only) + continue; + } + + /* If type does not correspond, then discard */ + if (type == X86_BR_NONE || (br_sel & type) != type) { + cpuc->lbr_entries[i].from = 0; /* mark invalid */ + compress = true; + } + + if ((br_sel & X86_BR_TYPE_SAVE) == X86_BR_TYPE_SAVE) + cpuc->lbr_entries[i].type = common_branch_type(type); + } + + if (!compress) + return; + + /* Remove all invalid entries */ + for (i = 0; i < cpuc->lbr_stack.nr; ) { + if (!cpuc->lbr_entries[i].from) { + j = i; + while (++j < cpuc->lbr_stack.nr) + cpuc->lbr_entries[j - 1] = cpuc->lbr_entries[j]; + cpuc->lbr_stack.nr--; + if (!cpuc->lbr_entries[i].from) + continue; + } + i++; + } +} + +static const int lbr_spec_map[PERF_BR_SPEC_MAX] = { + PERF_BR_SPEC_NA, + PERF_BR_SPEC_WRONG_PATH, + PERF_BR_NON_SPEC_CORRECT_PATH, + PERF_BR_SPEC_CORRECT_PATH, +}; + +void amd_pmu_lbr_read(void) +{ + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + struct perf_branch_entry *br = cpuc->lbr_entries; + struct branch_entry entry; + int out = 0, idx, i; + + if (!cpuc->lbr_users) + return; + + for (i = 0; i < x86_pmu.lbr_nr; i++) { + entry.from.full = amd_pmu_lbr_get_from(i); + entry.to.full = amd_pmu_lbr_get_to(i); + + /* + * Check if a branch has been logged; if valid = 0, spec = 0 + * then no branch was recorded + */ + if (!entry.to.split.valid && !entry.to.split.spec) + continue; + + perf_clear_branch_entry_bitfields(br + out); + + br[out].from = sign_ext_branch_ip(entry.from.split.ip); + br[out].to = sign_ext_branch_ip(entry.to.split.ip); + br[out].mispred = entry.from.split.mispredict; + br[out].predicted = !br[out].mispred; + + /* + * Set branch speculation information using the status of + * the valid and spec bits. + * + * When valid = 0, spec = 0, no branch was recorded and the + * entry is discarded as seen above. + * + * When valid = 0, spec = 1, the recorded branch was + * speculative but took the wrong path. + * + * When valid = 1, spec = 0, the recorded branch was + * non-speculative but took the correct path. + * + * When valid = 1, spec = 1, the recorded branch was + * speculative and took the correct path + */ + idx = (entry.to.split.valid << 1) | entry.to.split.spec; + br[out].spec = lbr_spec_map[idx]; + out++; + } + + cpuc->lbr_stack.nr = out; + + /* + * Internal register renaming always ensures that LBR From[0] and + * LBR To[0] always represent the TOS + */ + cpuc->lbr_stack.hw_idx = 0; + + /* Perform further software filtering */ + amd_pmu_lbr_filter(); +} + +static const int lbr_select_map[PERF_SAMPLE_BRANCH_MAX_SHIFT] = { + [PERF_SAMPLE_BRANCH_USER_SHIFT] = LBR_USER, + [PERF_SAMPLE_BRANCH_KERNEL_SHIFT] = LBR_KERNEL, + [PERF_SAMPLE_BRANCH_HV_SHIFT] = LBR_IGNORE, + + [PERF_SAMPLE_BRANCH_ANY_SHIFT] = LBR_ANY, + [PERF_SAMPLE_BRANCH_ANY_CALL_SHIFT] = LBR_REL_CALL | LBR_IND_CALL | LBR_FAR, + [PERF_SAMPLE_BRANCH_ANY_RETURN_SHIFT] = LBR_RETURN | LBR_FAR, + [PERF_SAMPLE_BRANCH_IND_CALL_SHIFT] = LBR_IND_CALL, + [PERF_SAMPLE_BRANCH_ABORT_TX_SHIFT] = LBR_NOT_SUPP, + [PERF_SAMPLE_BRANCH_IN_TX_SHIFT] = LBR_NOT_SUPP, + [PERF_SAMPLE_BRANCH_NO_TX_SHIFT] = LBR_NOT_SUPP, + [PERF_SAMPLE_BRANCH_COND_SHIFT] = LBR_JCC, + + [PERF_SAMPLE_BRANCH_CALL_STACK_SHIFT] = LBR_NOT_SUPP, + [PERF_SAMPLE_BRANCH_IND_JUMP_SHIFT] = LBR_IND_JMP, + [PERF_SAMPLE_BRANCH_CALL_SHIFT] = LBR_REL_CALL, + + [PERF_SAMPLE_BRANCH_NO_FLAGS_SHIFT] = LBR_NOT_SUPP, + [PERF_SAMPLE_BRANCH_NO_CYCLES_SHIFT] = LBR_NOT_SUPP, +}; + +static int amd_pmu_lbr_setup_filter(struct perf_event *event) +{ + struct hw_perf_event_extra *reg = &event->hw.branch_reg; + u64 br_type = event->attr.branch_sample_type; + u64 mask = 0, v; + int i; + + /* No LBR support */ + if (!x86_pmu.lbr_nr) + return -EOPNOTSUPP; + + if (br_type & PERF_SAMPLE_BRANCH_USER) + mask |= X86_BR_USER; + + if (br_type & PERF_SAMPLE_BRANCH_KERNEL) + mask |= X86_BR_KERNEL; + + /* Ignore BRANCH_HV here */ + + if (br_type & PERF_SAMPLE_BRANCH_ANY) + mask |= X86_BR_ANY; + + if (br_type & PERF_SAMPLE_BRANCH_ANY_CALL) + mask |= X86_BR_ANY_CALL; + + if (br_type & PERF_SAMPLE_BRANCH_ANY_RETURN) + mask |= X86_BR_RET | X86_BR_IRET | X86_BR_SYSRET; + + if (br_type & PERF_SAMPLE_BRANCH_IND_CALL) + mask |= X86_BR_IND_CALL; + + if (br_type & PERF_SAMPLE_BRANCH_COND) + mask |= X86_BR_JCC; + + if (br_type & PERF_SAMPLE_BRANCH_IND_JUMP) + mask |= X86_BR_IND_JMP; + + if (br_type & PERF_SAMPLE_BRANCH_CALL) + mask |= X86_BR_CALL | X86_BR_ZERO_CALL; + + if (br_type & PERF_SAMPLE_BRANCH_TYPE_SAVE) + mask |= X86_BR_TYPE_SAVE; + + reg->reg = mask; + mask = 0; + + for (i = 0; i < PERF_SAMPLE_BRANCH_MAX_SHIFT; i++) { + if (!(br_type & BIT_ULL(i))) + continue; + + v = lbr_select_map[i]; + if (v == LBR_NOT_SUPP) + return -EOPNOTSUPP; + + if (v != LBR_IGNORE) + mask |= v; + } + + /* Filter bits operate in suppress mode */ + reg->config = mask ^ LBR_SELECT_MASK; + + return 0; +} + +int amd_pmu_lbr_hw_config(struct perf_event *event) +{ + int ret = 0; + + /* LBR is not recommended in counting mode */ + if (!is_sampling_event(event)) + return -EINVAL; + + ret = amd_pmu_lbr_setup_filter(event); + if (!ret) + event->attach_state |= PERF_ATTACH_SCHED_CB; + + return ret; +} + +void amd_pmu_lbr_reset(void) +{ + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + int i; + + if (!x86_pmu.lbr_nr) + return; + + /* Reset all branch records individually */ + for (i = 0; i < x86_pmu.lbr_nr; i++) { + amd_pmu_lbr_set_from(i, 0); + amd_pmu_lbr_set_to(i, 0); + } + + cpuc->last_task_ctx = NULL; + cpuc->last_log_id = 0; + wrmsrl(MSR_AMD64_LBR_SELECT, 0); +} + +void amd_pmu_lbr_add(struct perf_event *event) +{ + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + struct hw_perf_event_extra *reg = &event->hw.branch_reg; + + if (!x86_pmu.lbr_nr) + return; + + if (has_branch_stack(event)) { + cpuc->lbr_select = 1; + cpuc->lbr_sel->config = reg->config; + cpuc->br_sel = reg->reg; + } + + perf_sched_cb_inc(event->ctx->pmu); + + if (!cpuc->lbr_users++ && !event->total_time_running) + amd_pmu_lbr_reset(); +} + +void amd_pmu_lbr_del(struct perf_event *event) +{ + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + + if (!x86_pmu.lbr_nr) + return; + + if (has_branch_stack(event)) + cpuc->lbr_select = 0; + + cpuc->lbr_users--; + WARN_ON_ONCE(cpuc->lbr_users < 0); + perf_sched_cb_dec(event->ctx->pmu); +} + +void amd_pmu_lbr_sched_task(struct perf_event_context *ctx, bool sched_in) +{ + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + + /* + * A context switch can flip the address space and LBR entries are + * not tagged with an identifier. Hence, branches cannot be resolved + * from the old address space and the LBR records should be wiped. + */ + if (cpuc->lbr_users && sched_in) + amd_pmu_lbr_reset(); +} + +void amd_pmu_lbr_enable_all(void) +{ + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + u64 lbr_select, dbg_ctl, dbg_extn_cfg; + + if (!cpuc->lbr_users || !x86_pmu.lbr_nr) + return; + + /* Set hardware branch filter */ + if (cpuc->lbr_select) { + lbr_select = cpuc->lbr_sel->config & LBR_SELECT_MASK; + wrmsrl(MSR_AMD64_LBR_SELECT, lbr_select); + } + + rdmsrl(MSR_IA32_DEBUGCTLMSR, dbg_ctl); + rdmsrl(MSR_AMD_DBG_EXTN_CFG, dbg_extn_cfg); + + wrmsrl(MSR_IA32_DEBUGCTLMSR, dbg_ctl | DEBUGCTLMSR_FREEZE_LBRS_ON_PMI); + wrmsrl(MSR_AMD_DBG_EXTN_CFG, dbg_extn_cfg | DBG_EXTN_CFG_LBRV2EN); +} + +void amd_pmu_lbr_disable_all(void) +{ + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + u64 dbg_ctl, dbg_extn_cfg; + + if (!cpuc->lbr_users || !x86_pmu.lbr_nr) + return; + + rdmsrl(MSR_AMD_DBG_EXTN_CFG, dbg_extn_cfg); + rdmsrl(MSR_IA32_DEBUGCTLMSR, dbg_ctl); + + wrmsrl(MSR_AMD_DBG_EXTN_CFG, dbg_extn_cfg & ~DBG_EXTN_CFG_LBRV2EN); + wrmsrl(MSR_IA32_DEBUGCTLMSR, dbg_ctl & ~DEBUGCTLMSR_FREEZE_LBRS_ON_PMI); +} + +__init int amd_pmu_lbr_init(void) +{ + union cpuid_0x80000022_ebx ebx; + + if (x86_pmu.version < 2 || !boot_cpu_has(X86_FEATURE_AMD_LBR_V2)) + return -EOPNOTSUPP; + + /* Set number of entries */ + ebx.full = cpuid_ebx(EXT_PERFMON_DEBUG_FEATURES); + x86_pmu.lbr_nr = ebx.split.lbr_v2_stack_sz; + + pr_cont("%d-deep LBR, ", x86_pmu.lbr_nr); + + return 0; +} diff --git a/arch/x86/events/amd/uncore.c b/arch/x86/events/amd/uncore.c index d568afc705d2..83f15fe411b3 100644 --- a/arch/x86/events/amd/uncore.c +++ b/arch/x86/events/amd/uncore.c @@ -553,6 +553,7 @@ static void uncore_clean_online(void) hlist_for_each_entry_safe(uncore, n, &uncore_unused_list, node) { hlist_del(&uncore->node); + kfree(uncore->events); kfree(uncore); } } diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index f969410d0c90..b30b8bbcd1e2 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -72,6 +72,10 @@ DEFINE_STATIC_CALL_NULL(x86_pmu_add, *x86_pmu.add); DEFINE_STATIC_CALL_NULL(x86_pmu_del, *x86_pmu.del); DEFINE_STATIC_CALL_NULL(x86_pmu_read, *x86_pmu.read); +DEFINE_STATIC_CALL_NULL(x86_pmu_set_period, *x86_pmu.set_period); +DEFINE_STATIC_CALL_NULL(x86_pmu_update, *x86_pmu.update); +DEFINE_STATIC_CALL_NULL(x86_pmu_limit_period, *x86_pmu.limit_period); + DEFINE_STATIC_CALL_NULL(x86_pmu_schedule_events, *x86_pmu.schedule_events); DEFINE_STATIC_CALL_NULL(x86_pmu_get_event_constraints, *x86_pmu.get_event_constraints); DEFINE_STATIC_CALL_NULL(x86_pmu_put_event_constraints, *x86_pmu.put_event_constraints); @@ -116,9 +120,6 @@ u64 x86_perf_event_update(struct perf_event *event) if (unlikely(!hwc->event_base)) return 0; - if (unlikely(is_topdown_count(event)) && x86_pmu.update_topdown_event) - return x86_pmu.update_topdown_event(event); - /* * Careful: an NMI might modify the previous event value. * @@ -621,8 +622,9 @@ int x86_pmu_hw_config(struct perf_event *event) event->hw.config |= event->attr.config & X86_RAW_EVENT_MASK; if (event->attr.sample_period && x86_pmu.limit_period) { - if (x86_pmu.limit_period(event, event->attr.sample_period) > - event->attr.sample_period) + s64 left = event->attr.sample_period; + x86_pmu.limit_period(event, &left); + if (left > event->attr.sample_period) return -EINVAL; } @@ -1354,7 +1356,7 @@ static void x86_pmu_enable(struct pmu *pmu) static_call(x86_pmu_enable_all)(added); } -static DEFINE_PER_CPU(u64 [X86_PMC_IDX_MAX], pmc_prev_left); +DEFINE_PER_CPU(u64 [X86_PMC_IDX_MAX], pmc_prev_left); /* * Set the next IRQ period, based on the hwc->period_left value. @@ -1370,10 +1372,6 @@ int x86_perf_event_set_period(struct perf_event *event) if (unlikely(!hwc->event_base)) return 0; - if (unlikely(is_topdown_count(event)) && - x86_pmu.set_topdown_event_period) - return x86_pmu.set_topdown_event_period(event); - /* * If we are way outside a reasonable range then just skip forward: */ @@ -1399,10 +1397,9 @@ int x86_perf_event_set_period(struct perf_event *event) if (left > x86_pmu.max_period) left = x86_pmu.max_period; - if (x86_pmu.limit_period) - left = x86_pmu.limit_period(event, left); + static_call_cond(x86_pmu_limit_period)(event, &left); - per_cpu(pmc_prev_left[idx], smp_processor_id()) = left; + this_cpu_write(pmc_prev_left[idx], left); /* * The hw event starts counting from this event offset, @@ -1419,16 +1416,6 @@ int x86_perf_event_set_period(struct perf_event *event) if (is_counter_pair(hwc)) wrmsrl(x86_pmu_event_addr(idx + 1), 0xffff); - /* - * Due to erratum on certan cpu we need - * a second write to be sure the register - * is updated properly - */ - if (x86_pmu.perfctr_second_write) { - wrmsrl(hwc->event_base, - (u64)(-left) & x86_pmu.cntval_mask); - } - perf_event_update_userpage(event); return ret; @@ -1518,7 +1505,7 @@ static void x86_pmu_start(struct perf_event *event, int flags) if (flags & PERF_EF_RELOAD) { WARN_ON_ONCE(!(event->hw.state & PERF_HES_UPTODATE)); - x86_perf_event_set_period(event); + static_call(x86_pmu_set_period)(event); } event->hw.state = 0; @@ -1610,7 +1597,7 @@ void x86_pmu_stop(struct perf_event *event, int flags) * Drain the remaining delta count out of a event * that we are disabling: */ - x86_perf_event_update(event); + static_call(x86_pmu_update)(event); hwc->state |= PERF_HES_UPTODATE; } } @@ -1700,7 +1687,7 @@ int x86_pmu_handle_irq(struct pt_regs *regs) event = cpuc->events[idx]; - val = x86_perf_event_update(event); + val = static_call(x86_pmu_update)(event); if (val & (1ULL << (x86_pmu.cntval_bits - 1))) continue; @@ -1709,13 +1696,15 @@ int x86_pmu_handle_irq(struct pt_regs *regs) */ handled++; - if (!x86_perf_event_set_period(event)) + if (!static_call(x86_pmu_set_period)(event)) continue; perf_sample_data_init(&data, 0, event->hw.last_period); - if (has_branch_stack(event)) + if (has_branch_stack(event)) { data.br_stack = &cpuc->lbr_stack; + data.sample_flags |= PERF_SAMPLE_BRANCH_STACK; + } if (perf_event_overflow(event, &data, regs)) x86_pmu_stop(event, 0); @@ -2023,6 +2012,10 @@ static void x86_pmu_static_call_update(void) static_call_update(x86_pmu_del, x86_pmu.del); static_call_update(x86_pmu_read, x86_pmu.read); + static_call_update(x86_pmu_set_period, x86_pmu.set_period); + static_call_update(x86_pmu_update, x86_pmu.update); + static_call_update(x86_pmu_limit_period, x86_pmu.limit_period); + static_call_update(x86_pmu_schedule_events, x86_pmu.schedule_events); static_call_update(x86_pmu_get_event_constraints, x86_pmu.get_event_constraints); static_call_update(x86_pmu_put_event_constraints, x86_pmu.put_event_constraints); @@ -2042,7 +2035,7 @@ static void x86_pmu_static_call_update(void) static void _x86_pmu_read(struct perf_event *event) { - x86_perf_event_update(event); + static_call(x86_pmu_update)(event); } void x86_pmu_show_pmu_cap(int num_counters, int num_counters_fixed, @@ -2149,6 +2142,12 @@ static int __init init_hw_perf_events(void) if (!x86_pmu.guest_get_msrs) x86_pmu.guest_get_msrs = (void *)&__static_call_return0; + if (!x86_pmu.set_period) + x86_pmu.set_period = x86_perf_event_set_period; + + if (!x86_pmu.update) + x86_pmu.update = x86_perf_event_update; + x86_pmu_static_call_update(); /* @@ -2670,7 +2669,9 @@ static int x86_pmu_check_period(struct perf_event *event, u64 value) return -EINVAL; if (value && x86_pmu.limit_period) { - if (x86_pmu.limit_period(event, value) > value) + s64 left = value; + x86_pmu.limit_period(event, &left); + if (left > value) return -EINVAL; } diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 2db93498ff71..1b92bf05fd65 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -2102,6 +2102,15 @@ static struct extra_reg intel_tnt_extra_regs[] __read_mostly = { EVENT_EXTRA_END }; +EVENT_ATTR_STR(mem-loads, mem_ld_grt, "event=0xd0,umask=0x5,ldlat=3"); +EVENT_ATTR_STR(mem-stores, mem_st_grt, "event=0xd0,umask=0x6"); + +static struct attribute *grt_mem_attrs[] = { + EVENT_PTR(mem_ld_grt), + EVENT_PTR(mem_st_grt), + NULL +}; + static struct extra_reg intel_grt_extra_regs[] __read_mostly = { /* must define OFFCORE_RSP_X first, see intel_fixup_er() */ INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0x3fffffffffull, RSP_0), @@ -2190,6 +2199,12 @@ static void __intel_pmu_enable_all(int added, bool pmi) u64 intel_ctrl = hybrid(cpuc->pmu, intel_ctrl); intel_pmu_lbr_enable_all(pmi); + + if (cpuc->fixed_ctrl_val != cpuc->active_fixed_ctrl_val) { + wrmsrl(MSR_ARCH_PERFMON_FIXED_CTR_CTRL, cpuc->fixed_ctrl_val); + cpuc->active_fixed_ctrl_val = cpuc->fixed_ctrl_val; + } + wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL, intel_ctrl & ~cpuc->intel_ctrl_guest_mask); @@ -2302,7 +2317,7 @@ static void intel_pmu_nhm_workaround(void) for (i = 0; i < 4; i++) { event = cpuc->events[i]; if (event) - x86_perf_event_update(event); + static_call(x86_pmu_update)(event); } for (i = 0; i < 4; i++) { @@ -2317,7 +2332,7 @@ static void intel_pmu_nhm_workaround(void) event = cpuc->events[i]; if (event) { - x86_perf_event_set_period(event); + static_call(x86_pmu_set_period)(event); __x86_pmu_enable_event(&event->hw, ARCH_PERFMON_EVENTSEL_ENABLE); } else @@ -2407,9 +2422,10 @@ static inline void intel_clear_masks(struct perf_event *event, int idx) static void intel_pmu_disable_fixed(struct perf_event *event) { + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct hw_perf_event *hwc = &event->hw; - u64 ctrl_val, mask; int idx = hwc->idx; + u64 mask; if (is_topdown_idx(idx)) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); @@ -2426,9 +2442,7 @@ static void intel_pmu_disable_fixed(struct perf_event *event) intel_clear_masks(event, idx); mask = 0xfULL << ((idx - INTEL_PMC_IDX_FIXED) * 4); - rdmsrl(hwc->config_base, ctrl_val); - ctrl_val &= ~mask; - wrmsrl(hwc->config_base, ctrl_val); + cpuc->fixed_ctrl_val &= ~mask; } static void intel_pmu_disable_event(struct perf_event *event) @@ -2521,6 +2535,8 @@ static int adl_set_topdown_event_period(struct perf_event *event) return icl_set_topdown_event_period(event); } +DEFINE_STATIC_CALL(intel_pmu_set_topdown_event_period, x86_perf_event_set_period); + static inline u64 icl_get_metrics_event_value(u64 metric, u64 slots, int idx) { u32 val; @@ -2671,6 +2687,7 @@ static u64 adl_update_topdown_event(struct perf_event *event) return icl_update_topdown_event(event); } +DEFINE_STATIC_CALL(intel_pmu_update_topdown_event, x86_perf_event_update); static void intel_pmu_read_topdown_event(struct perf_event *event) { @@ -2682,7 +2699,7 @@ static void intel_pmu_read_topdown_event(struct perf_event *event) return; perf_pmu_disable(event->pmu); - x86_pmu.update_topdown_event(event); + static_call(intel_pmu_update_topdown_event)(event); perf_pmu_enable(event->pmu); } @@ -2690,7 +2707,7 @@ static void intel_pmu_read_event(struct perf_event *event) { if (event->hw.flags & PERF_X86_EVENT_AUTO_RELOAD) intel_pmu_auto_reload_read(event); - else if (is_topdown_count(event) && x86_pmu.update_topdown_event) + else if (is_topdown_count(event)) intel_pmu_read_topdown_event(event); else x86_perf_event_update(event); @@ -2698,8 +2715,9 @@ static void intel_pmu_read_event(struct perf_event *event) static void intel_pmu_enable_fixed(struct perf_event *event) { + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct hw_perf_event *hwc = &event->hw; - u64 ctrl_val, mask, bits = 0; + u64 mask, bits = 0; int idx = hwc->idx; if (is_topdown_idx(idx)) { @@ -2743,10 +2761,8 @@ static void intel_pmu_enable_fixed(struct perf_event *event) mask |= ICL_FIXED_0_ADAPTIVE << (idx * 4); } - rdmsrl(hwc->config_base, ctrl_val); - ctrl_val &= ~mask; - ctrl_val |= bits; - wrmsrl(hwc->config_base, ctrl_val); + cpuc->fixed_ctrl_val &= ~mask; + cpuc->fixed_ctrl_val |= bits; } static void intel_pmu_enable_event(struct perf_event *event) @@ -2794,7 +2810,7 @@ static void intel_pmu_add_event(struct perf_event *event) */ int intel_pmu_save_and_restart(struct perf_event *event) { - x86_perf_event_update(event); + static_call(x86_pmu_update)(event); /* * For a checkpointed counter always reset back to 0. This * avoids a situation where the counter overflows, aborts the @@ -2806,9 +2822,25 @@ int intel_pmu_save_and_restart(struct perf_event *event) wrmsrl(event->hw.event_base, 0); local64_set(&event->hw.prev_count, 0); } + return static_call(x86_pmu_set_period)(event); +} + +static int intel_pmu_set_period(struct perf_event *event) +{ + if (unlikely(is_topdown_count(event))) + return static_call(intel_pmu_set_topdown_event_period)(event); + return x86_perf_event_set_period(event); } +static u64 intel_pmu_update(struct perf_event *event) +{ + if (unlikely(is_topdown_count(event))) + return static_call(intel_pmu_update_topdown_event)(event); + + return x86_perf_event_update(event); +} + static void intel_pmu_reset(void) { struct debug_store *ds = __this_cpu_read(cpu_hw_events.ds); @@ -2971,8 +3003,7 @@ static int handle_pmi_common(struct pt_regs *regs, u64 status) */ if (__test_and_clear_bit(GLOBAL_STATUS_PERF_METRICS_OVF_BIT, (unsigned long *)&status)) { handled++; - if (x86_pmu.update_topdown_event) - x86_pmu.update_topdown_event(NULL); + static_call(intel_pmu_update_topdown_event)(NULL); } /* @@ -2995,8 +3026,10 @@ static int handle_pmi_common(struct pt_regs *regs, u64 status) perf_sample_data_init(&data, 0, event->hw.last_period); - if (has_branch_stack(event)) + if (has_branch_stack(event)) { data.br_stack = &cpuc->lbr_stack; + data.sample_flags |= PERF_SAMPLE_BRANCH_STACK; + } if (perf_event_overflow(event, &data, regs)) x86_pmu_stop(event, 0); @@ -3844,9 +3877,6 @@ static int intel_pmu_hw_config(struct perf_event *event) } if (x86_pmu.pebs_aliases) x86_pmu.pebs_aliases(event); - - if (event->attr.sample_type & PERF_SAMPLE_CALLCHAIN) - event->attr.sample_type |= __PERF_SAMPLE_CALLCHAIN_EARLY; } if (needs_branch_stack(event)) { @@ -4052,8 +4082,9 @@ static struct perf_guest_switch_msr *intel_guest_get_msrs(int *nr, void *data) /* Disable guest PEBS if host PEBS is enabled. */ arr[pebs_enable].guest = 0; } else { - /* Disable guest PEBS for cross-mapped PEBS counters. */ + /* Disable guest PEBS thoroughly for cross-mapped PEBS counters. */ arr[pebs_enable].guest &= ~kvm_pmu->host_cross_mapped_mask; + arr[global_ctrl].guest &= ~kvm_pmu->host_cross_mapped_mask; /* Set hw GLOBAL_CTRL bits for PEBS counter when it runs for guest */ arr[global_ctrl].guest |= arr[pebs_enable].guest; } @@ -4324,28 +4355,25 @@ static u8 adl_get_hybrid_cpu_type(void) * Therefore the effective (average) period matches the requested period, * despite coarser hardware granularity. */ -static u64 bdw_limit_period(struct perf_event *event, u64 left) +static void bdw_limit_period(struct perf_event *event, s64 *left) { if ((event->hw.config & INTEL_ARCH_EVENT_MASK) == X86_CONFIG(.event=0xc0, .umask=0x01)) { - if (left < 128) - left = 128; - left &= ~0x3fULL; + if (*left < 128) + *left = 128; + *left &= ~0x3fULL; } - return left; } -static u64 nhm_limit_period(struct perf_event *event, u64 left) +static void nhm_limit_period(struct perf_event *event, s64 *left) { - return max(left, 32ULL); + *left = max(*left, 32LL); } -static u64 spr_limit_period(struct perf_event *event, u64 left) +static void spr_limit_period(struct perf_event *event, s64 *left) { if (event->attr.precise_ip == 3) - return max(left, 128ULL); - - return left; + *left = max(*left, 128LL); } PMU_FORMAT_ATTR(event, "config:0-7" ); @@ -4784,6 +4812,8 @@ static __initconst const struct x86_pmu intel_pmu = { .add = intel_pmu_add_event, .del = intel_pmu_del_event, .read = intel_pmu_read_event, + .set_period = intel_pmu_set_period, + .update = intel_pmu_update, .hw_config = intel_pmu_hw_config, .schedule_events = x86_schedule_events, .eventsel = MSR_ARCH_PERFMON_EVENTSEL0, @@ -4881,6 +4911,7 @@ static const struct x86_cpu_desc isolation_ucodes[] = { INTEL_CPU_DESC(INTEL_FAM6_SKYLAKE_X, 5, 0x00000000), INTEL_CPU_DESC(INTEL_FAM6_SKYLAKE_X, 6, 0x00000000), INTEL_CPU_DESC(INTEL_FAM6_SKYLAKE_X, 7, 0x00000000), + INTEL_CPU_DESC(INTEL_FAM6_SKYLAKE_X, 11, 0x00000000), INTEL_CPU_DESC(INTEL_FAM6_SKYLAKE_L, 3, 0x0000007c), INTEL_CPU_DESC(INTEL_FAM6_SKYLAKE, 3, 0x0000007c), INTEL_CPU_DESC(INTEL_FAM6_KABYLAKE, 9, 0x0000004e), @@ -5974,6 +6005,36 @@ __init int intel_pmu_init(void) name = "Tremont"; break; + case INTEL_FAM6_ALDERLAKE_N: + x86_pmu.mid_ack = true; + memcpy(hw_cache_event_ids, glp_hw_cache_event_ids, + sizeof(hw_cache_event_ids)); + memcpy(hw_cache_extra_regs, tnt_hw_cache_extra_regs, + sizeof(hw_cache_extra_regs)); + hw_cache_event_ids[C(ITLB)][C(OP_READ)][C(RESULT_ACCESS)] = -1; + + x86_pmu.event_constraints = intel_slm_event_constraints; + x86_pmu.pebs_constraints = intel_grt_pebs_event_constraints; + x86_pmu.extra_regs = intel_grt_extra_regs; + + x86_pmu.pebs_aliases = NULL; + x86_pmu.pebs_prec_dist = true; + x86_pmu.pebs_block = true; + x86_pmu.lbr_pt_coexist = true; + x86_pmu.flags |= PMU_FL_HAS_RSP_1; + x86_pmu.flags |= PMU_FL_INSTR_LATENCY; + + intel_pmu_pebs_data_source_grt(); + x86_pmu.pebs_latency_data = adl_latency_data_small; + x86_pmu.get_event_constraints = tnt_get_event_constraints; + x86_pmu.limit_period = spr_limit_period; + td_attr = tnt_events_attrs; + mem_attr = grt_mem_attrs; + extra_attr = nhm_format_attr; + pr_cont("Gracemont events, "); + name = "gracemont"; + break; + case INTEL_FAM6_WESTMERE: case INTEL_FAM6_WESTMERE_EP: case INTEL_FAM6_WESTMERE_EX: @@ -6272,8 +6333,10 @@ __init int intel_pmu_init(void) x86_pmu.lbr_pt_coexist = true; intel_pmu_pebs_data_source_skl(pmem); x86_pmu.num_topdown_events = 4; - x86_pmu.update_topdown_event = icl_update_topdown_event; - x86_pmu.set_topdown_event_period = icl_set_topdown_event_period; + static_call_update(intel_pmu_update_topdown_event, + &icl_update_topdown_event); + static_call_update(intel_pmu_set_topdown_event_period, + &icl_set_topdown_event_period); pr_cont("Icelake events, "); name = "icelake"; break; @@ -6291,10 +6354,8 @@ __init int intel_pmu_init(void) x86_pmu.pebs_aliases = NULL; x86_pmu.pebs_prec_dist = true; x86_pmu.pebs_block = true; - x86_pmu.pebs_capable = ~0ULL; x86_pmu.flags |= PMU_FL_HAS_RSP_1; x86_pmu.flags |= PMU_FL_NO_HT_SHARING; - x86_pmu.flags |= PMU_FL_PEBS_ALL; x86_pmu.flags |= PMU_FL_INSTR_LATENCY; x86_pmu.flags |= PMU_FL_MEM_LOADS_AUX; @@ -6310,17 +6371,19 @@ __init int intel_pmu_init(void) x86_pmu.lbr_pt_coexist = true; intel_pmu_pebs_data_source_skl(pmem); x86_pmu.num_topdown_events = 8; - x86_pmu.update_topdown_event = icl_update_topdown_event; - x86_pmu.set_topdown_event_period = icl_set_topdown_event_period; + static_call_update(intel_pmu_update_topdown_event, + &icl_update_topdown_event); + static_call_update(intel_pmu_set_topdown_event_period, + &icl_set_topdown_event_period); pr_cont("Sapphire Rapids events, "); name = "sapphire_rapids"; break; case INTEL_FAM6_ALDERLAKE: case INTEL_FAM6_ALDERLAKE_L: - case INTEL_FAM6_ALDERLAKE_N: case INTEL_FAM6_RAPTORLAKE: case INTEL_FAM6_RAPTORLAKE_P: + case INTEL_FAM6_RAPTORLAKE_S: /* * Alder Lake has 2 types of CPU, core and atom. * @@ -6337,18 +6400,18 @@ __init int intel_pmu_init(void) x86_pmu.pebs_aliases = NULL; x86_pmu.pebs_prec_dist = true; x86_pmu.pebs_block = true; - x86_pmu.pebs_capable = ~0ULL; x86_pmu.flags |= PMU_FL_HAS_RSP_1; x86_pmu.flags |= PMU_FL_NO_HT_SHARING; - x86_pmu.flags |= PMU_FL_PEBS_ALL; x86_pmu.flags |= PMU_FL_INSTR_LATENCY; x86_pmu.flags |= PMU_FL_MEM_LOADS_AUX; x86_pmu.lbr_pt_coexist = true; intel_pmu_pebs_data_source_adl(); x86_pmu.pebs_latency_data = adl_latency_data_small; x86_pmu.num_topdown_events = 8; - x86_pmu.update_topdown_event = adl_update_topdown_event; - x86_pmu.set_topdown_event_period = adl_set_topdown_event_period; + static_call_update(intel_pmu_update_topdown_event, + &adl_update_topdown_event); + static_call_update(intel_pmu_set_topdown_event_period, + &adl_set_topdown_event_period); x86_pmu.filter_match = intel_pmu_filter_match; x86_pmu.get_event_constraints = adl_get_event_constraints; diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c index 8ec23f47fee9..a2834bc93149 100644 --- a/arch/x86/events/intel/cstate.c +++ b/arch/x86/events/intel/cstate.c @@ -685,6 +685,7 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = { X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_N, &adl_cstates), X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE, &adl_cstates), X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_P, &adl_cstates), + X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_S, &adl_cstates), { }, }; MODULE_DEVICE_TABLE(x86cpu, intel_cstates_match); diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index ba60427caa6d..446d2833efa7 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -110,13 +110,18 @@ void __init intel_pmu_pebs_data_source_skl(bool pmem) __intel_pmu_pebs_data_source_skl(pmem, pebs_data_source); } -static void __init intel_pmu_pebs_data_source_grt(u64 *data_source) +static void __init __intel_pmu_pebs_data_source_grt(u64 *data_source) { data_source[0x05] = OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOP, HIT); data_source[0x06] = OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOP, HITM); data_source[0x08] = OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOPX, FWD); } +void __init intel_pmu_pebs_data_source_grt(void) +{ + __intel_pmu_pebs_data_source_grt(pebs_data_source); +} + void __init intel_pmu_pebs_data_source_adl(void) { u64 *data_source; @@ -127,7 +132,7 @@ void __init intel_pmu_pebs_data_source_adl(void) data_source = x86_pmu.hybrid_pmu[X86_HYBRID_PMU_ATOM_IDX].pebs_data_source; memcpy(data_source, pebs_data_source, sizeof(pebs_data_source)); - intel_pmu_pebs_data_source_grt(data_source); + __intel_pmu_pebs_data_source_grt(data_source); } static u64 precise_store_data(u64 status) @@ -291,6 +296,7 @@ static u64 load_latency_data(struct perf_event *event, u64 status) static u64 store_latency_data(struct perf_event *event, u64 status) { union intel_x86_pebs_dse dse; + union perf_mem_data_src src; u64 val; dse.val = status; @@ -304,7 +310,14 @@ static u64 store_latency_data(struct perf_event *event, u64 status) val |= P(BLK, NA); - return val; + /* + * the pebs_data_source table is only for loads + * so override the mem_op to say STORE instead + */ + src.val = val; + src.mem_op = P(OP,STORE); + + return src.val; } struct pebs_record_core { @@ -822,7 +835,7 @@ struct event_constraint intel_glm_pebs_event_constraints[] = { struct event_constraint intel_grt_pebs_event_constraints[] = { /* Allow all events as PEBS with no flags */ - INTEL_HYBRID_LAT_CONSTRAINT(0x5d0, 0xf), + INTEL_HYBRID_LAT_CONSTRAINT(0x5d0, 0x3), INTEL_HYBRID_LAT_CONSTRAINT(0x6d0, 0xf), EVENT_CONSTRAINT_END }; @@ -969,8 +982,13 @@ struct event_constraint intel_icl_pebs_event_constraints[] = { INTEL_FLAGS_UEVENT_CONSTRAINT(0x0400, 0x800000000ULL), /* SLOTS */ INTEL_PLD_CONSTRAINT(0x1cd, 0xff), /* MEM_TRANS_RETIRED.LOAD_LATENCY */ - INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x1d0, 0xf), /* MEM_INST_RETIRED.LOAD */ - INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x2d0, 0xf), /* MEM_INST_RETIRED.STORE */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x11d0, 0xf), /* MEM_INST_RETIRED.STLB_MISS_LOADS */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x12d0, 0xf), /* MEM_INST_RETIRED.STLB_MISS_STORES */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x21d0, 0xf), /* MEM_INST_RETIRED.LOCK_LOADS */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x41d0, 0xf), /* MEM_INST_RETIRED.SPLIT_LOADS */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x42d0, 0xf), /* MEM_INST_RETIRED.SPLIT_STORES */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x81d0, 0xf), /* MEM_INST_RETIRED.ALL_LOADS */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x82d0, 0xf), /* MEM_INST_RETIRED.ALL_STORES */ INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD_RANGE(0xd1, 0xd4, 0xf), /* MEM_LOAD_*_RETIRED.* */ @@ -991,8 +1009,13 @@ struct event_constraint intel_spr_pebs_event_constraints[] = { INTEL_FLAGS_EVENT_CONSTRAINT(0xc0, 0xfe), INTEL_PLD_CONSTRAINT(0x1cd, 0xfe), INTEL_PSD_CONSTRAINT(0x2cd, 0x1), - INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x1d0, 0xf), - INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x2d0, 0xf), + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x11d0, 0xf), /* MEM_INST_RETIRED.STLB_MISS_LOADS */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x12d0, 0xf), /* MEM_INST_RETIRED.STLB_MISS_STORES */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x21d0, 0xf), /* MEM_INST_RETIRED.LOCK_LOADS */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x41d0, 0xf), /* MEM_INST_RETIRED.SPLIT_LOADS */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x42d0, 0xf), /* MEM_INST_RETIRED.SPLIT_STORES */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x81d0, 0xf), /* MEM_INST_RETIRED.ALL_LOADS */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x82d0, 0xf), /* MEM_INST_RETIRED.ALL_STORES */ INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD_RANGE(0xd1, 0xd4, 0xf), @@ -1527,14 +1550,18 @@ static void setup_pebs_fixed_sample_data(struct perf_event *event, /* * Use latency for weight (only avail with PEBS-LL) */ - if (fll && (sample_type & PERF_SAMPLE_WEIGHT_TYPE)) + if (fll && (sample_type & PERF_SAMPLE_WEIGHT_TYPE)) { data->weight.full = pebs->lat; + data->sample_flags |= PERF_SAMPLE_WEIGHT_TYPE; + } /* * data.data_src encodes the data source */ - if (sample_type & PERF_SAMPLE_DATA_SRC) + if (sample_type & PERF_SAMPLE_DATA_SRC) { data->data_src.val = get_data_src(event, pebs->dse); + data->sample_flags |= PERF_SAMPLE_DATA_SRC; + } /* * We must however always use iregs for the unwinder to stay sane; the @@ -1542,8 +1569,10 @@ static void setup_pebs_fixed_sample_data(struct perf_event *event, * previous PMI context or an (I)RET happened between the record and * PMI. */ - if (sample_type & PERF_SAMPLE_CALLCHAIN) + if (sample_type & PERF_SAMPLE_CALLCHAIN) { data->callchain = perf_callchain(event, iregs); + data->sample_flags |= PERF_SAMPLE_CALLCHAIN; + } /* * We use the interrupt regs as a base because the PEBS record does not @@ -1615,17 +1644,22 @@ static void setup_pebs_fixed_sample_data(struct perf_event *event, if ((sample_type & PERF_SAMPLE_ADDR_TYPE) && - x86_pmu.intel_cap.pebs_format >= 1) + x86_pmu.intel_cap.pebs_format >= 1) { data->addr = pebs->dla; + data->sample_flags |= PERF_SAMPLE_ADDR; + } if (x86_pmu.intel_cap.pebs_format >= 2) { /* Only set the TSX weight when no memory weight. */ - if ((sample_type & PERF_SAMPLE_WEIGHT_TYPE) && !fll) + if ((sample_type & PERF_SAMPLE_WEIGHT_TYPE) && !fll) { data->weight.full = intel_get_tsx_weight(pebs->tsx_tuning); - - if (sample_type & PERF_SAMPLE_TRANSACTION) + data->sample_flags |= PERF_SAMPLE_WEIGHT_TYPE; + } + if (sample_type & PERF_SAMPLE_TRANSACTION) { data->txn = intel_get_tsx_transaction(pebs->tsx_tuning, pebs->ax); + data->sample_flags |= PERF_SAMPLE_TRANSACTION; + } } /* @@ -1635,11 +1669,15 @@ static void setup_pebs_fixed_sample_data(struct perf_event *event, * We can only do this for the default trace clock. */ if (x86_pmu.intel_cap.pebs_format >= 3 && - event->attr.use_clockid == 0) + event->attr.use_clockid == 0) { data->time = native_sched_clock_from_tsc(pebs->tsc); + data->sample_flags |= PERF_SAMPLE_TIME; + } - if (has_branch_stack(event)) + if (has_branch_stack(event)) { data->br_stack = &cpuc->lbr_stack; + data->sample_flags |= PERF_SAMPLE_BRANCH_STACK; + } } static void adaptive_pebs_save_regs(struct pt_regs *regs, @@ -1697,8 +1735,10 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event, perf_sample_data_init(data, 0, event->hw.last_period); data->period = event->hw.last_period; - if (event->attr.use_clockid == 0) + if (event->attr.use_clockid == 0) { data->time = native_sched_clock_from_tsc(basic->tsc); + data->sample_flags |= PERF_SAMPLE_TIME; + } /* * We must however always use iregs for the unwinder to stay sane; the @@ -1706,8 +1746,10 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event, * previous PMI context or an (I)RET happened between the record and * PMI. */ - if (sample_type & PERF_SAMPLE_CALLCHAIN) + if (sample_type & PERF_SAMPLE_CALLCHAIN) { data->callchain = perf_callchain(event, iregs); + data->sample_flags |= PERF_SAMPLE_CALLCHAIN; + } *regs = *iregs; /* The ip in basic is EventingIP */ @@ -1758,17 +1800,24 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event, data->weight.var1_dw = (u32)(weight & PEBS_LATENCY_MASK) ?: intel_get_tsx_weight(meminfo->tsx_tuning); } + data->sample_flags |= PERF_SAMPLE_WEIGHT_TYPE; } - if (sample_type & PERF_SAMPLE_DATA_SRC) + if (sample_type & PERF_SAMPLE_DATA_SRC) { data->data_src.val = get_data_src(event, meminfo->aux); + data->sample_flags |= PERF_SAMPLE_DATA_SRC; + } - if (sample_type & PERF_SAMPLE_ADDR_TYPE) + if (sample_type & PERF_SAMPLE_ADDR_TYPE) { data->addr = meminfo->address; + data->sample_flags |= PERF_SAMPLE_ADDR; + } - if (sample_type & PERF_SAMPLE_TRANSACTION) + if (sample_type & PERF_SAMPLE_TRANSACTION) { data->txn = intel_get_tsx_transaction(meminfo->tsx_tuning, gprs ? gprs->ax : 0); + data->sample_flags |= PERF_SAMPLE_TRANSACTION; + } } if (format_size & PEBS_DATACFG_XMMS) { @@ -1787,6 +1836,7 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event, if (has_branch_stack(event)) { intel_pmu_store_pebs_lbrs(lbr); data->br_stack = &cpuc->lbr_stack; + data->sample_flags |= PERF_SAMPLE_BRANCH_STACK; } } @@ -2262,6 +2312,7 @@ void __init intel_ds_init(void) PERF_SAMPLE_BRANCH_STACK | PERF_SAMPLE_TIME; x86_pmu.flags |= PMU_FL_PEBS_ALL; + x86_pmu.pebs_capable = ~0ULL; pebs_qual = "-baseline"; x86_get_pmu(smp_processor_id())->capabilities |= PERF_PMU_CAP_EXTENDED_REGS; } else { diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c index 4f70fb6c2c1e..8259d725054d 100644 --- a/arch/x86/events/intel/lbr.c +++ b/arch/x86/events/intel/lbr.c @@ -4,7 +4,6 @@ #include <asm/perf_event.h> #include <asm/msr.h> -#include <asm/insn.h> #include "../perf_event.h" @@ -66,65 +65,6 @@ #define LBR_FROM_SIGNEXT_2MSB (BIT_ULL(60) | BIT_ULL(59)) /* - * x86control flow change classification - * x86control flow changes include branches, interrupts, traps, faults - */ -enum { - X86_BR_NONE = 0, /* unknown */ - - X86_BR_USER = 1 << 0, /* branch target is user */ - X86_BR_KERNEL = 1 << 1, /* branch target is kernel */ - - X86_BR_CALL = 1 << 2, /* call */ - X86_BR_RET = 1 << 3, /* return */ - X86_BR_SYSCALL = 1 << 4, /* syscall */ - X86_BR_SYSRET = 1 << 5, /* syscall return */ - X86_BR_INT = 1 << 6, /* sw interrupt */ - X86_BR_IRET = 1 << 7, /* return from interrupt */ - X86_BR_JCC = 1 << 8, /* conditional */ - X86_BR_JMP = 1 << 9, /* jump */ - X86_BR_IRQ = 1 << 10,/* hw interrupt or trap or fault */ - X86_BR_IND_CALL = 1 << 11,/* indirect calls */ - X86_BR_ABORT = 1 << 12,/* transaction abort */ - X86_BR_IN_TX = 1 << 13,/* in transaction */ - X86_BR_NO_TX = 1 << 14,/* not in transaction */ - X86_BR_ZERO_CALL = 1 << 15,/* zero length call */ - X86_BR_CALL_STACK = 1 << 16,/* call stack */ - X86_BR_IND_JMP = 1 << 17,/* indirect jump */ - - X86_BR_TYPE_SAVE = 1 << 18,/* indicate to save branch type */ - -}; - -#define X86_BR_PLM (X86_BR_USER | X86_BR_KERNEL) -#define X86_BR_ANYTX (X86_BR_NO_TX | X86_BR_IN_TX) - -#define X86_BR_ANY \ - (X86_BR_CALL |\ - X86_BR_RET |\ - X86_BR_SYSCALL |\ - X86_BR_SYSRET |\ - X86_BR_INT |\ - X86_BR_IRET |\ - X86_BR_JCC |\ - X86_BR_JMP |\ - X86_BR_IRQ |\ - X86_BR_ABORT |\ - X86_BR_IND_CALL |\ - X86_BR_IND_JMP |\ - X86_BR_ZERO_CALL) - -#define X86_BR_ALL (X86_BR_PLM | X86_BR_ANY) - -#define X86_BR_ANY_CALL \ - (X86_BR_CALL |\ - X86_BR_IND_CALL |\ - X86_BR_ZERO_CALL |\ - X86_BR_SYSCALL |\ - X86_BR_IRQ |\ - X86_BR_INT) - -/* * Intel LBR_CTL bits * * Hardware branch filter for Arch LBR @@ -1097,6 +1037,14 @@ static int intel_pmu_setup_hw_lbr_filter(struct perf_event *event) if (static_cpu_has(X86_FEATURE_ARCH_LBR)) { reg->config = mask; + + /* + * The Arch LBR HW can retrieve the common branch types + * from the LBR_INFO. It doesn't require the high overhead + * SW disassemble. + * Enable the branch type by default for the Arch LBR. + */ + reg->reg |= X86_BR_TYPE_SAVE; return 0; } @@ -1143,219 +1091,6 @@ int intel_pmu_setup_lbr_filter(struct perf_event *event) return ret; } -/* - * return the type of control flow change at address "from" - * instruction is not necessarily a branch (in case of interrupt). - * - * The branch type returned also includes the priv level of the - * target of the control flow change (X86_BR_USER, X86_BR_KERNEL). - * - * If a branch type is unknown OR the instruction cannot be - * decoded (e.g., text page not present), then X86_BR_NONE is - * returned. - */ -static int branch_type(unsigned long from, unsigned long to, int abort) -{ - struct insn insn; - void *addr; - int bytes_read, bytes_left; - int ret = X86_BR_NONE; - int ext, to_plm, from_plm; - u8 buf[MAX_INSN_SIZE]; - int is64 = 0; - - to_plm = kernel_ip(to) ? X86_BR_KERNEL : X86_BR_USER; - from_plm = kernel_ip(from) ? X86_BR_KERNEL : X86_BR_USER; - - /* - * maybe zero if lbr did not fill up after a reset by the time - * we get a PMU interrupt - */ - if (from == 0 || to == 0) - return X86_BR_NONE; - - if (abort) - return X86_BR_ABORT | to_plm; - - if (from_plm == X86_BR_USER) { - /* - * can happen if measuring at the user level only - * and we interrupt in a kernel thread, e.g., idle. - */ - if (!current->mm) - return X86_BR_NONE; - - /* may fail if text not present */ - bytes_left = copy_from_user_nmi(buf, (void __user *)from, - MAX_INSN_SIZE); - bytes_read = MAX_INSN_SIZE - bytes_left; - if (!bytes_read) - return X86_BR_NONE; - - addr = buf; - } else { - /* - * The LBR logs any address in the IP, even if the IP just - * faulted. This means userspace can control the from address. - * Ensure we don't blindly read any address by validating it is - * a known text address. - */ - if (kernel_text_address(from)) { - addr = (void *)from; - /* - * Assume we can get the maximum possible size - * when grabbing kernel data. This is not - * _strictly_ true since we could possibly be - * executing up next to a memory hole, but - * it is very unlikely to be a problem. - */ - bytes_read = MAX_INSN_SIZE; - } else { - return X86_BR_NONE; - } - } - - /* - * decoder needs to know the ABI especially - * on 64-bit systems running 32-bit apps - */ -#ifdef CONFIG_X86_64 - is64 = kernel_ip((unsigned long)addr) || any_64bit_mode(current_pt_regs()); -#endif - insn_init(&insn, addr, bytes_read, is64); - if (insn_get_opcode(&insn)) - return X86_BR_ABORT; - - switch (insn.opcode.bytes[0]) { - case 0xf: - switch (insn.opcode.bytes[1]) { - case 0x05: /* syscall */ - case 0x34: /* sysenter */ - ret = X86_BR_SYSCALL; - break; - case 0x07: /* sysret */ - case 0x35: /* sysexit */ - ret = X86_BR_SYSRET; - break; - case 0x80 ... 0x8f: /* conditional */ - ret = X86_BR_JCC; - break; - default: - ret = X86_BR_NONE; - } - break; - case 0x70 ... 0x7f: /* conditional */ - ret = X86_BR_JCC; - break; - case 0xc2: /* near ret */ - case 0xc3: /* near ret */ - case 0xca: /* far ret */ - case 0xcb: /* far ret */ - ret = X86_BR_RET; - break; - case 0xcf: /* iret */ - ret = X86_BR_IRET; - break; - case 0xcc ... 0xce: /* int */ - ret = X86_BR_INT; - break; - case 0xe8: /* call near rel */ - if (insn_get_immediate(&insn) || insn.immediate1.value == 0) { - /* zero length call */ - ret = X86_BR_ZERO_CALL; - break; - } - fallthrough; - case 0x9a: /* call far absolute */ - ret = X86_BR_CALL; - break; - case 0xe0 ... 0xe3: /* loop jmp */ - ret = X86_BR_JCC; - break; - case 0xe9 ... 0xeb: /* jmp */ - ret = X86_BR_JMP; - break; - case 0xff: /* call near absolute, call far absolute ind */ - if (insn_get_modrm(&insn)) - return X86_BR_ABORT; - - ext = (insn.modrm.bytes[0] >> 3) & 0x7; - switch (ext) { - case 2: /* near ind call */ - case 3: /* far ind call */ - ret = X86_BR_IND_CALL; - break; - case 4: - case 5: - ret = X86_BR_IND_JMP; - break; - } - break; - default: - ret = X86_BR_NONE; - } - /* - * interrupts, traps, faults (and thus ring transition) may - * occur on any instructions. Thus, to classify them correctly, - * we need to first look at the from and to priv levels. If they - * are different and to is in the kernel, then it indicates - * a ring transition. If the from instruction is not a ring - * transition instr (syscall, systenter, int), then it means - * it was a irq, trap or fault. - * - * we have no way of detecting kernel to kernel faults. - */ - if (from_plm == X86_BR_USER && to_plm == X86_BR_KERNEL - && ret != X86_BR_SYSCALL && ret != X86_BR_INT) - ret = X86_BR_IRQ; - - /* - * branch priv level determined by target as - * is done by HW when LBR_SELECT is implemented - */ - if (ret != X86_BR_NONE) - ret |= to_plm; - - return ret; -} - -#define X86_BR_TYPE_MAP_MAX 16 - -static int branch_map[X86_BR_TYPE_MAP_MAX] = { - PERF_BR_CALL, /* X86_BR_CALL */ - PERF_BR_RET, /* X86_BR_RET */ - PERF_BR_SYSCALL, /* X86_BR_SYSCALL */ - PERF_BR_SYSRET, /* X86_BR_SYSRET */ - PERF_BR_UNKNOWN, /* X86_BR_INT */ - PERF_BR_ERET, /* X86_BR_IRET */ - PERF_BR_COND, /* X86_BR_JCC */ - PERF_BR_UNCOND, /* X86_BR_JMP */ - PERF_BR_IRQ, /* X86_BR_IRQ */ - PERF_BR_IND_CALL, /* X86_BR_IND_CALL */ - PERF_BR_UNKNOWN, /* X86_BR_ABORT */ - PERF_BR_UNKNOWN, /* X86_BR_IN_TX */ - PERF_BR_UNKNOWN, /* X86_BR_NO_TX */ - PERF_BR_CALL, /* X86_BR_ZERO_CALL */ - PERF_BR_UNKNOWN, /* X86_BR_CALL_STACK */ - PERF_BR_IND, /* X86_BR_IND_JMP */ -}; - -static int -common_branch_type(int type) -{ - int i; - - type >>= 2; /* skip X86_BR_USER and X86_BR_KERNEL */ - - if (type) { - i = __ffs(type); - if (i < X86_BR_TYPE_MAP_MAX) - return branch_map[i]; - } - - return PERF_BR_UNKNOWN; -} - enum { ARCH_LBR_BR_TYPE_JCC = 0, ARCH_LBR_BR_TYPE_NEAR_IND_JMP = 1, @@ -1861,7 +1596,7 @@ void __init intel_pmu_arch_lbr_init(void) return; clear_arch_lbr: - clear_cpu_cap(&boot_cpu_data, X86_FEATURE_ARCH_LBR); + setup_clear_cpu_cap(X86_FEATURE_ARCH_LBR); } /** diff --git a/arch/x86/events/intel/p4.c b/arch/x86/events/intel/p4.c index 7951a5dc73b6..03bbcc2fa2ff 100644 --- a/arch/x86/events/intel/p4.c +++ b/arch/x86/events/intel/p4.c @@ -1006,6 +1006,29 @@ static void p4_pmu_enable_all(int added) } } +static int p4_pmu_set_period(struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + s64 left = this_cpu_read(pmc_prev_left[hwc->idx]); + int ret; + + ret = x86_perf_event_set_period(event); + + if (hwc->event_base) { + /* + * This handles erratum N15 in intel doc 249199-029, + * the counter may not be updated correctly on write + * so we need a second write operation to do the trick + * (the official workaround didn't work) + * + * the former idea is taken from OProfile code + */ + wrmsrl(hwc->event_base, (u64)(-left) & x86_pmu.cntval_mask); + } + + return ret; +} + static int p4_pmu_handle_irq(struct pt_regs *regs) { struct perf_sample_data data; @@ -1044,7 +1067,7 @@ static int p4_pmu_handle_irq(struct pt_regs *regs) /* event overflow for sure */ perf_sample_data_init(&data, 0, hwc->last_period); - if (!x86_perf_event_set_period(event)) + if (!static_call(x86_pmu_set_period)(event)) continue; @@ -1316,6 +1339,9 @@ static __initconst const struct x86_pmu p4_pmu = { .enable_all = p4_pmu_enable_all, .enable = p4_pmu_enable_event, .disable = p4_pmu_disable_event, + + .set_period = p4_pmu_set_period, + .eventsel = MSR_P4_BPU_CCCR0, .perfctr = MSR_P4_BPU_PERFCTR0, .event_map = p4_pmu_event_map, @@ -1334,15 +1360,6 @@ static __initconst const struct x86_pmu p4_pmu = { .max_period = (1ULL << (ARCH_P4_CNTRVAL_BITS - 1)) - 1, .hw_config = p4_hw_config, .schedule_events = p4_pmu_schedule_events, - /* - * This handles erratum N15 in intel doc 249199-029, - * the counter may not be updated correctly on write - * so we need a second write operation to do the trick - * (the official workaround didn't work) - * - * the former idea is taken from OProfile code - */ - .perfctr_second_write = 1, .format_attrs = intel_p4_formats_attr, }; diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c index 82ef87e9a897..42a55794004a 100644 --- a/arch/x86/events/intel/pt.c +++ b/arch/x86/events/intel/pt.c @@ -1263,6 +1263,15 @@ static int pt_buffer_try_single(struct pt_buffer *buf, int nr_pages) if (1 << order != nr_pages) goto out; + /* + * Some processors cannot always support single range for more than + * 4KB - refer errata TGL052, ADL037 and RPL017. Future processors might + * also be affected, so for now rather than trying to keep track of + * which ones, just disable it for all. + */ + if (nr_pages > 1) + goto out; + buf->single = true; buf->nr_pages = nr_pages; ret = 0; diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c index db6c31bca809..6f1ccc57a692 100644 --- a/arch/x86/events/intel/uncore.c +++ b/arch/x86/events/intel/uncore.c @@ -1831,6 +1831,7 @@ static const struct x86_cpu_id intel_uncore_match[] __initconst = { X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_N, &adl_uncore_init), X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE, &adl_uncore_init), X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_P, &adl_uncore_init), + X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_S, &adl_uncore_init), X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X, &spr_uncore_init), X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT_D, &snr_uncore_init), {}, diff --git a/arch/x86/events/intel/uncore_snb.c b/arch/x86/events/intel/uncore_snb.c index ce440011cc4e..1ef4f7861e2e 100644 --- a/arch/x86/events/intel/uncore_snb.c +++ b/arch/x86/events/intel/uncore_snb.c @@ -841,6 +841,22 @@ int snb_pci2phy_map_init(int devid) return 0; } +static u64 snb_uncore_imc_read_counter(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + + /* + * SNB IMC counters are 32-bit and are laid out back to back + * in MMIO space. Therefore we must use a 32-bit accessor function + * using readq() from uncore_mmio_read_counter() causes problems + * because it is reading 64-bit at a time. This is okay for the + * uncore_perf_event_update() function because it drops the upper + * 32-bits but not okay for plain uncore_read_counter() as invoked + * in uncore_pmu_event_start(). + */ + return (u64)readl(box->io_addr + hwc->event_base); +} + static struct pmu snb_uncore_imc_pmu = { .task_ctx_nr = perf_invalid_context, .event_init = snb_uncore_imc_event_init, @@ -860,7 +876,7 @@ static struct intel_uncore_ops snb_uncore_imc_ops = { .disable_event = snb_uncore_imc_disable_event, .enable_event = snb_uncore_imc_enable_event, .hw_config = snb_uncore_imc_hw_config, - .read_counter = uncore_mmio_read_counter, + .read_counter = snb_uncore_imc_read_counter, }; static struct intel_uncore_type snb_uncore_imc = { diff --git a/arch/x86/events/msr.c b/arch/x86/events/msr.c index ac542f98c070..ecced3a52668 100644 --- a/arch/x86/events/msr.c +++ b/arch/x86/events/msr.c @@ -106,6 +106,7 @@ static bool test_intel(int idx, void *data) case INTEL_FAM6_ALDERLAKE_N: case INTEL_FAM6_RAPTORLAKE: case INTEL_FAM6_RAPTORLAKE_P: + case INTEL_FAM6_RAPTORLAKE_S: if (idx == PERF_MSR_SMI || idx == PERF_MSR_PPERF) return true; break; diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index ba3d24a6a4ec..332d2e6d8ae4 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -64,27 +64,25 @@ static inline bool constraint_match(struct event_constraint *c, u64 ecode) return ((ecode & c->cmask) - c->code) <= (u64)c->size; } +#define PERF_ARCH(name, val) \ + PERF_X86_EVENT_##name = val, + /* * struct hw_perf_event.flags flags */ -#define PERF_X86_EVENT_PEBS_LDLAT 0x00001 /* ld+ldlat data address sampling */ -#define PERF_X86_EVENT_PEBS_ST 0x00002 /* st data address sampling */ -#define PERF_X86_EVENT_PEBS_ST_HSW 0x00004 /* haswell style datala, store */ -#define PERF_X86_EVENT_PEBS_LD_HSW 0x00008 /* haswell style datala, load */ -#define PERF_X86_EVENT_PEBS_NA_HSW 0x00010 /* haswell style datala, unknown */ -#define PERF_X86_EVENT_EXCL 0x00020 /* HT exclusivity on counter */ -#define PERF_X86_EVENT_DYNAMIC 0x00040 /* dynamic alloc'd constraint */ - -#define PERF_X86_EVENT_EXCL_ACCT 0x00100 /* accounted EXCL event */ -#define PERF_X86_EVENT_AUTO_RELOAD 0x00200 /* use PEBS auto-reload */ -#define PERF_X86_EVENT_LARGE_PEBS 0x00400 /* use large PEBS */ -#define PERF_X86_EVENT_PEBS_VIA_PT 0x00800 /* use PT buffer for PEBS */ -#define PERF_X86_EVENT_PAIR 0x01000 /* Large Increment per Cycle */ -#define PERF_X86_EVENT_LBR_SELECT 0x02000 /* Save/Restore MSR_LBR_SELECT */ -#define PERF_X86_EVENT_TOPDOWN 0x04000 /* Count Topdown slots/metrics events */ -#define PERF_X86_EVENT_PEBS_STLAT 0x08000 /* st+stlat data address sampling */ -#define PERF_X86_EVENT_AMD_BRS 0x10000 /* AMD Branch Sampling */ -#define PERF_X86_EVENT_PEBS_LAT_HYBRID 0x20000 /* ld and st lat for hybrid */ +enum { +#include "perf_event_flags.h" +}; + +#undef PERF_ARCH + +#define PERF_ARCH(name, val) \ + static_assert((PERF_X86_EVENT_##name & PERF_EVENT_FLAG_ARCH) == \ + PERF_X86_EVENT_##name); + +#include "perf_event_flags.h" + +#undef PERF_ARCH static inline bool is_topdown_count(struct perf_event *event) { @@ -272,6 +270,10 @@ struct cpu_hw_events { u64 active_pebs_data_cfg; int pebs_record_size; + /* Intel Fixed counter configuration */ + u64 fixed_ctrl_val; + u64 active_fixed_ctrl_val; + /* * Intel LBR bits */ @@ -745,6 +747,8 @@ struct x86_pmu { void (*add)(struct perf_event *); void (*del)(struct perf_event *); void (*read)(struct perf_event *event); + int (*set_period)(struct perf_event *event); + u64 (*update)(struct perf_event *event); int (*hw_config)(struct perf_event *event); int (*schedule_events)(struct cpu_hw_events *cpuc, int n, int *assign); unsigned eventsel; @@ -780,8 +784,7 @@ struct x86_pmu { struct event_constraint *event_constraints; struct x86_pmu_quirk *quirks; - int perfctr_second_write; - u64 (*limit_period)(struct perf_event *event, u64 l); + void (*limit_period)(struct perf_event *event, s64 *l); /* PMI handler bits */ unsigned int late_ack :1, @@ -889,8 +892,6 @@ struct x86_pmu { * Intel perf metrics */ int num_topdown_events; - u64 (*update_topdown_event)(struct perf_event *event); - int (*set_topdown_event_period)(struct perf_event *event); /* * perf task context (i.e. struct perf_event_context::task_ctx_data) @@ -1044,6 +1045,9 @@ static struct perf_pmu_format_hybrid_attr format_attr_hybrid_##_name = {\ struct pmu *x86_get_pmu(unsigned int cpu); extern struct x86_pmu x86_pmu __read_mostly; +DECLARE_STATIC_CALL(x86_pmu_set_period, *x86_pmu.set_period); +DECLARE_STATIC_CALL(x86_pmu_update, *x86_pmu.update); + static __always_inline struct x86_perf_task_context_opt *task_context_opt(void *ctx) { if (static_cpu_has(X86_FEATURE_ARCH_LBR)) @@ -1059,6 +1063,7 @@ static inline bool x86_pmu_has_lbr_callstack(void) } DECLARE_PER_CPU(struct cpu_hw_events, cpu_hw_events); +DECLARE_PER_CPU(u64 [X86_PMC_IDX_MAX], pmc_prev_left); int x86_perf_event_set_period(struct perf_event *event); @@ -1210,6 +1215,70 @@ static inline void set_linear_ip(struct pt_regs *regs, unsigned long ip) regs->ip = ip; } +/* + * x86control flow change classification + * x86control flow changes include branches, interrupts, traps, faults + */ +enum { + X86_BR_NONE = 0, /* unknown */ + + X86_BR_USER = 1 << 0, /* branch target is user */ + X86_BR_KERNEL = 1 << 1, /* branch target is kernel */ + + X86_BR_CALL = 1 << 2, /* call */ + X86_BR_RET = 1 << 3, /* return */ + X86_BR_SYSCALL = 1 << 4, /* syscall */ + X86_BR_SYSRET = 1 << 5, /* syscall return */ + X86_BR_INT = 1 << 6, /* sw interrupt */ + X86_BR_IRET = 1 << 7, /* return from interrupt */ + X86_BR_JCC = 1 << 8, /* conditional */ + X86_BR_JMP = 1 << 9, /* jump */ + X86_BR_IRQ = 1 << 10,/* hw interrupt or trap or fault */ + X86_BR_IND_CALL = 1 << 11,/* indirect calls */ + X86_BR_ABORT = 1 << 12,/* transaction abort */ + X86_BR_IN_TX = 1 << 13,/* in transaction */ + X86_BR_NO_TX = 1 << 14,/* not in transaction */ + X86_BR_ZERO_CALL = 1 << 15,/* zero length call */ + X86_BR_CALL_STACK = 1 << 16,/* call stack */ + X86_BR_IND_JMP = 1 << 17,/* indirect jump */ + + X86_BR_TYPE_SAVE = 1 << 18,/* indicate to save branch type */ + +}; + +#define X86_BR_PLM (X86_BR_USER | X86_BR_KERNEL) +#define X86_BR_ANYTX (X86_BR_NO_TX | X86_BR_IN_TX) + +#define X86_BR_ANY \ + (X86_BR_CALL |\ + X86_BR_RET |\ + X86_BR_SYSCALL |\ + X86_BR_SYSRET |\ + X86_BR_INT |\ + X86_BR_IRET |\ + X86_BR_JCC |\ + X86_BR_JMP |\ + X86_BR_IRQ |\ + X86_BR_ABORT |\ + X86_BR_IND_CALL |\ + X86_BR_IND_JMP |\ + X86_BR_ZERO_CALL) + +#define X86_BR_ALL (X86_BR_PLM | X86_BR_ANY) + +#define X86_BR_ANY_CALL \ + (X86_BR_CALL |\ + X86_BR_IND_CALL |\ + X86_BR_ZERO_CALL |\ + X86_BR_SYSCALL |\ + X86_BR_IRQ |\ + X86_BR_INT) + +int common_branch_type(int type); +int branch_type(unsigned long from, unsigned long to, int abort); +int branch_type_fused(unsigned long from, unsigned long to, int abort, + int *offset); + ssize_t x86_event_sysfs_show(char *page, u64 config, u64 event); ssize_t intel_event_sysfs_show(char *page, u64 config); @@ -1232,7 +1301,20 @@ static inline bool fixed_counter_disabled(int i, struct pmu *pmu) int amd_pmu_init(void); +int amd_pmu_lbr_init(void); +void amd_pmu_lbr_reset(void); +void amd_pmu_lbr_read(void); +void amd_pmu_lbr_add(struct perf_event *event); +void amd_pmu_lbr_del(struct perf_event *event); +void amd_pmu_lbr_sched_task(struct perf_event_context *ctx, bool sched_in); +void amd_pmu_lbr_enable_all(void); +void amd_pmu_lbr_disable_all(void); +int amd_pmu_lbr_hw_config(struct perf_event *event); + #ifdef CONFIG_PERF_EVENTS_AMD_BRS + +#define AMD_FAM19H_BRS_EVENT 0xc4 /* RETIRED_TAKEN_BRANCH_INSTRUCTIONS */ + int amd_brs_init(void); void amd_brs_disable(void); void amd_brs_enable(void); @@ -1241,7 +1323,7 @@ void amd_brs_disable_all(void); void amd_brs_drain(void); void amd_brs_lopwr_init(void); void amd_brs_disable_all(void); -int amd_brs_setup_filter(struct perf_event *event); +int amd_brs_hw_config(struct perf_event *event); void amd_brs_reset(void); static inline void amd_pmu_brs_add(struct perf_event *event) @@ -1277,7 +1359,7 @@ static inline void amd_brs_enable(void) {} static inline void amd_brs_drain(void) {} static inline void amd_brs_lopwr_init(void) {} static inline void amd_brs_disable_all(void) {} -static inline int amd_brs_setup_filter(struct perf_event *event) +static inline int amd_brs_hw_config(struct perf_event *event) { return 0; } @@ -1516,6 +1598,8 @@ void intel_pmu_pebs_data_source_skl(bool pmem); void intel_pmu_pebs_data_source_adl(void); +void intel_pmu_pebs_data_source_grt(void); + int intel_pmu_setup_lbr_filter(struct perf_event *event); void intel_pt_interrupt(void); diff --git a/arch/x86/events/perf_event_flags.h b/arch/x86/events/perf_event_flags.h new file mode 100644 index 000000000000..1dc19b9b4426 --- /dev/null +++ b/arch/x86/events/perf_event_flags.h @@ -0,0 +1,22 @@ + +/* + * struct hw_perf_event.flags flags + */ +PERF_ARCH(PEBS_LDLAT, 0x00001) /* ld+ldlat data address sampling */ +PERF_ARCH(PEBS_ST, 0x00002) /* st data address sampling */ +PERF_ARCH(PEBS_ST_HSW, 0x00004) /* haswell style datala, store */ +PERF_ARCH(PEBS_LD_HSW, 0x00008) /* haswell style datala, load */ +PERF_ARCH(PEBS_NA_HSW, 0x00010) /* haswell style datala, unknown */ +PERF_ARCH(EXCL, 0x00020) /* HT exclusivity on counter */ +PERF_ARCH(DYNAMIC, 0x00040) /* dynamic alloc'd constraint */ + /* 0x00080 */ +PERF_ARCH(EXCL_ACCT, 0x00100) /* accounted EXCL event */ +PERF_ARCH(AUTO_RELOAD, 0x00200) /* use PEBS auto-reload */ +PERF_ARCH(LARGE_PEBS, 0x00400) /* use large PEBS */ +PERF_ARCH(PEBS_VIA_PT, 0x00800) /* use PT buffer for PEBS */ +PERF_ARCH(PAIR, 0x01000) /* Large Increment per Cycle */ +PERF_ARCH(LBR_SELECT, 0x02000) /* Save/Restore MSR_LBR_SELECT */ +PERF_ARCH(TOPDOWN, 0x04000) /* Count Topdown slots/metrics events */ +PERF_ARCH(PEBS_STLAT, 0x08000) /* st+stlat data address sampling */ +PERF_ARCH(AMD_BRS, 0x10000) /* AMD Branch Sampling */ +PERF_ARCH(PEBS_LAT_HYBRID, 0x20000) /* ld and st lat for hybrid */ diff --git a/arch/x86/events/rapl.c b/arch/x86/events/rapl.c index 77e3a47af5ad..a829492bca4c 100644 --- a/arch/x86/events/rapl.c +++ b/arch/x86/events/rapl.c @@ -619,12 +619,8 @@ static int rapl_check_hw_unit(struct rapl_model *rm) case RAPL_UNIT_QUIRK_INTEL_HSW: rapl_hw_unit[PERF_RAPL_RAM] = 16; break; - /* - * SPR shares the same DRAM domain energy unit as HSW, plus it - * also has a fixed energy unit for Psys domain. - */ + /* SPR uses a fixed energy unit for Psys domain. */ case RAPL_UNIT_QUIRK_INTEL_SPR: - rapl_hw_unit[PERF_RAPL_RAM] = 16; rapl_hw_unit[PERF_RAPL_PSYS] = 0; break; default: @@ -806,7 +802,11 @@ static const struct x86_cpu_id rapl_model_match[] __initconst = { X86_MATCH_INTEL_FAM6_MODEL(COMETLAKE, &model_skl), X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE, &model_skl), X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_L, &model_skl), + X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_N, &model_skl), X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X, &model_spr), + X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE, &model_skl), + X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_P, &model_skl), + X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_S, &model_skl), {}, }; MODULE_DEVICE_TABLE(x86cpu, rapl_model_match); diff --git a/arch/x86/events/utils.c b/arch/x86/events/utils.c new file mode 100644 index 000000000000..76b1f8bb0fd5 --- /dev/null +++ b/arch/x86/events/utils.c @@ -0,0 +1,251 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <asm/insn.h> + +#include "perf_event.h" + +static int decode_branch_type(struct insn *insn) +{ + int ext; + + if (insn_get_opcode(insn)) + return X86_BR_ABORT; + + switch (insn->opcode.bytes[0]) { + case 0xf: + switch (insn->opcode.bytes[1]) { + case 0x05: /* syscall */ + case 0x34: /* sysenter */ + return X86_BR_SYSCALL; + case 0x07: /* sysret */ + case 0x35: /* sysexit */ + return X86_BR_SYSRET; + case 0x80 ... 0x8f: /* conditional */ + return X86_BR_JCC; + } + return X86_BR_NONE; + case 0x70 ... 0x7f: /* conditional */ + return X86_BR_JCC; + case 0xc2: /* near ret */ + case 0xc3: /* near ret */ + case 0xca: /* far ret */ + case 0xcb: /* far ret */ + return X86_BR_RET; + case 0xcf: /* iret */ + return X86_BR_IRET; + case 0xcc ... 0xce: /* int */ + return X86_BR_INT; + case 0xe8: /* call near rel */ + if (insn_get_immediate(insn) || insn->immediate1.value == 0) { + /* zero length call */ + return X86_BR_ZERO_CALL; + } + fallthrough; + case 0x9a: /* call far absolute */ + return X86_BR_CALL; + case 0xe0 ... 0xe3: /* loop jmp */ + return X86_BR_JCC; + case 0xe9 ... 0xeb: /* jmp */ + return X86_BR_JMP; + case 0xff: /* call near absolute, call far absolute ind */ + if (insn_get_modrm(insn)) + return X86_BR_ABORT; + + ext = (insn->modrm.bytes[0] >> 3) & 0x7; + switch (ext) { + case 2: /* near ind call */ + case 3: /* far ind call */ + return X86_BR_IND_CALL; + case 4: + case 5: + return X86_BR_IND_JMP; + } + return X86_BR_NONE; + } + + return X86_BR_NONE; +} + +/* + * return the type of control flow change at address "from" + * instruction is not necessarily a branch (in case of interrupt). + * + * The branch type returned also includes the priv level of the + * target of the control flow change (X86_BR_USER, X86_BR_KERNEL). + * + * If a branch type is unknown OR the instruction cannot be + * decoded (e.g., text page not present), then X86_BR_NONE is + * returned. + * + * While recording branches, some processors can report the "from" + * address to be that of an instruction preceding the actual branch + * when instruction fusion occurs. If fusion is expected, attempt to + * find the type of the first branch instruction within the next + * MAX_INSN_SIZE bytes and if found, provide the offset between the + * reported "from" address and the actual branch instruction address. + */ +static int get_branch_type(unsigned long from, unsigned long to, int abort, + bool fused, int *offset) +{ + struct insn insn; + void *addr; + int bytes_read, bytes_left, insn_offset; + int ret = X86_BR_NONE; + int to_plm, from_plm; + u8 buf[MAX_INSN_SIZE]; + int is64 = 0; + + /* make sure we initialize offset */ + if (offset) + *offset = 0; + + to_plm = kernel_ip(to) ? X86_BR_KERNEL : X86_BR_USER; + from_plm = kernel_ip(from) ? X86_BR_KERNEL : X86_BR_USER; + + /* + * maybe zero if lbr did not fill up after a reset by the time + * we get a PMU interrupt + */ + if (from == 0 || to == 0) + return X86_BR_NONE; + + if (abort) + return X86_BR_ABORT | to_plm; + + if (from_plm == X86_BR_USER) { + /* + * can happen if measuring at the user level only + * and we interrupt in a kernel thread, e.g., idle. + */ + if (!current->mm) + return X86_BR_NONE; + + /* may fail if text not present */ + bytes_left = copy_from_user_nmi(buf, (void __user *)from, + MAX_INSN_SIZE); + bytes_read = MAX_INSN_SIZE - bytes_left; + if (!bytes_read) + return X86_BR_NONE; + + addr = buf; + } else { + /* + * The LBR logs any address in the IP, even if the IP just + * faulted. This means userspace can control the from address. + * Ensure we don't blindly read any address by validating it is + * a known text address. + */ + if (kernel_text_address(from)) { + addr = (void *)from; + /* + * Assume we can get the maximum possible size + * when grabbing kernel data. This is not + * _strictly_ true since we could possibly be + * executing up next to a memory hole, but + * it is very unlikely to be a problem. + */ + bytes_read = MAX_INSN_SIZE; + } else { + return X86_BR_NONE; + } + } + + /* + * decoder needs to know the ABI especially + * on 64-bit systems running 32-bit apps + */ +#ifdef CONFIG_X86_64 + is64 = kernel_ip((unsigned long)addr) || any_64bit_mode(current_pt_regs()); +#endif + insn_init(&insn, addr, bytes_read, is64); + ret = decode_branch_type(&insn); + insn_offset = 0; + + /* Check for the possibility of branch fusion */ + while (fused && ret == X86_BR_NONE) { + /* Check for decoding errors */ + if (insn_get_length(&insn) || !insn.length) + break; + + insn_offset += insn.length; + bytes_read -= insn.length; + if (bytes_read < 0) + break; + + insn_init(&insn, addr + insn_offset, bytes_read, is64); + ret = decode_branch_type(&insn); + } + + if (offset) + *offset = insn_offset; + + /* + * interrupts, traps, faults (and thus ring transition) may + * occur on any instructions. Thus, to classify them correctly, + * we need to first look at the from and to priv levels. If they + * are different and to is in the kernel, then it indicates + * a ring transition. If the from instruction is not a ring + * transition instr (syscall, systenter, int), then it means + * it was a irq, trap or fault. + * + * we have no way of detecting kernel to kernel faults. + */ + if (from_plm == X86_BR_USER && to_plm == X86_BR_KERNEL + && ret != X86_BR_SYSCALL && ret != X86_BR_INT) + ret = X86_BR_IRQ; + + /* + * branch priv level determined by target as + * is done by HW when LBR_SELECT is implemented + */ + if (ret != X86_BR_NONE) + ret |= to_plm; + + return ret; +} + +int branch_type(unsigned long from, unsigned long to, int abort) +{ + return get_branch_type(from, to, abort, false, NULL); +} + +int branch_type_fused(unsigned long from, unsigned long to, int abort, + int *offset) +{ + return get_branch_type(from, to, abort, true, offset); +} + +#define X86_BR_TYPE_MAP_MAX 16 + +static int branch_map[X86_BR_TYPE_MAP_MAX] = { + PERF_BR_CALL, /* X86_BR_CALL */ + PERF_BR_RET, /* X86_BR_RET */ + PERF_BR_SYSCALL, /* X86_BR_SYSCALL */ + PERF_BR_SYSRET, /* X86_BR_SYSRET */ + PERF_BR_UNKNOWN, /* X86_BR_INT */ + PERF_BR_ERET, /* X86_BR_IRET */ + PERF_BR_COND, /* X86_BR_JCC */ + PERF_BR_UNCOND, /* X86_BR_JMP */ + PERF_BR_IRQ, /* X86_BR_IRQ */ + PERF_BR_IND_CALL, /* X86_BR_IND_CALL */ + PERF_BR_UNKNOWN, /* X86_BR_ABORT */ + PERF_BR_UNKNOWN, /* X86_BR_IN_TX */ + PERF_BR_NO_TX, /* X86_BR_NO_TX */ + PERF_BR_CALL, /* X86_BR_ZERO_CALL */ + PERF_BR_UNKNOWN, /* X86_BR_CALL_STACK */ + PERF_BR_IND, /* X86_BR_IND_JMP */ +}; + +int common_branch_type(int type) +{ + int i; + + type >>= 2; /* skip X86_BR_USER and X86_BR_KERNEL */ + + if (type) { + i = __ffs(type); + if (i < X86_BR_TYPE_MAP_MAX) + return branch_map[i]; + } + + return PERF_BR_UNKNOWN; +} diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c index 3de6d8b53367..a269049a43ce 100644 --- a/arch/x86/hyperv/hv_init.c +++ b/arch/x86/hyperv/hv_init.c @@ -77,7 +77,7 @@ static int hyperv_init_ghcb(void) static int hv_cpu_init(unsigned int cpu) { union hv_vp_assist_msr_contents msr = { 0 }; - struct hv_vp_assist_page **hvp = &hv_vp_assist_page[smp_processor_id()]; + struct hv_vp_assist_page **hvp = &hv_vp_assist_page[cpu]; int ret; ret = hv_common_cpu_init(cpu); @@ -87,34 +87,32 @@ static int hv_cpu_init(unsigned int cpu) if (!hv_vp_assist_page) return 0; - if (!*hvp) { - if (hv_root_partition) { - /* - * For root partition we get the hypervisor provided VP assist - * page, instead of allocating a new page. - */ - rdmsrl(HV_X64_MSR_VP_ASSIST_PAGE, msr.as_uint64); - *hvp = memremap(msr.pfn << - HV_X64_MSR_VP_ASSIST_PAGE_ADDRESS_SHIFT, - PAGE_SIZE, MEMREMAP_WB); - } else { - /* - * The VP assist page is an "overlay" page (see Hyper-V TLFS's - * Section 5.2.1 "GPA Overlay Pages"). Here it must be zeroed - * out to make sure we always write the EOI MSR in - * hv_apic_eoi_write() *after* the EOI optimization is disabled - * in hv_cpu_die(), otherwise a CPU may not be stopped in the - * case of CPU offlining and the VM will hang. - */ + if (hv_root_partition) { + /* + * For root partition we get the hypervisor provided VP assist + * page, instead of allocating a new page. + */ + rdmsrl(HV_X64_MSR_VP_ASSIST_PAGE, msr.as_uint64); + *hvp = memremap(msr.pfn << HV_X64_MSR_VP_ASSIST_PAGE_ADDRESS_SHIFT, + PAGE_SIZE, MEMREMAP_WB); + } else { + /* + * The VP assist page is an "overlay" page (see Hyper-V TLFS's + * Section 5.2.1 "GPA Overlay Pages"). Here it must be zeroed + * out to make sure we always write the EOI MSR in + * hv_apic_eoi_write() *after* the EOI optimization is disabled + * in hv_cpu_die(), otherwise a CPU may not be stopped in the + * case of CPU offlining and the VM will hang. + */ + if (!*hvp) *hvp = __vmalloc(PAGE_SIZE, GFP_KERNEL | __GFP_ZERO); - if (*hvp) - msr.pfn = vmalloc_to_pfn(*hvp); - } - WARN_ON(!(*hvp)); - if (*hvp) { - msr.enable = 1; - wrmsrl(HV_X64_MSR_VP_ASSIST_PAGE, msr.as_uint64); - } + if (*hvp) + msr.pfn = vmalloc_to_pfn(*hvp); + + } + if (!WARN_ON(!(*hvp))) { + msr.enable = 1; + wrmsrl(HV_X64_MSR_VP_ASSIST_PAGE, msr.as_uint64); } return hyperv_init_ghcb(); @@ -426,7 +424,7 @@ void __init hyperv_init(void) * 1. Register the guest ID * 2. Enable the hypercall and register the hypercall page */ - guest_id = generate_guest_id(0, LINUX_VERSION_CODE, 0); + guest_id = hv_generate_guest_id(LINUX_VERSION_CODE); wrmsrl(HV_X64_MSR_GUEST_OS_ID, guest_id); /* Hyper-V requires to write guest os id via ghcb in SNP IVM. */ @@ -444,7 +442,7 @@ void __init hyperv_init(void) if (hv_root_partition) { struct page *pg; - void *src, *dst; + void *src; /* * For the root partition, the hypervisor will set up its @@ -459,13 +457,11 @@ void __init hyperv_init(void) wrmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64); pg = vmalloc_to_page(hv_hypercall_pg); - dst = kmap(pg); src = memremap(hypercall_msr.guest_physical_address << PAGE_SHIFT, PAGE_SIZE, MEMREMAP_WB); - BUG_ON(!(src && dst)); - memcpy(dst, src, HV_HYP_PAGE_SIZE); + BUG_ON(!src); + memcpy_to_page(pg, 0, src, HV_HYP_PAGE_SIZE); memunmap(src); - kunmap(pg); } else { hypercall_msr.guest_physical_address = vmalloc_to_pfn(hv_hypercall_pg); wrmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64); @@ -537,6 +533,7 @@ common_free: void hyperv_cleanup(void) { union hv_x64_msr_hypercall_contents hypercall_msr; + union hv_reference_tsc_msr tsc_msr; unregister_syscore_ops(&hv_syscore_ops); @@ -552,12 +549,14 @@ void hyperv_cleanup(void) hv_hypercall_pg = NULL; /* Reset the hypercall page */ - hypercall_msr.as_uint64 = 0; - wrmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64); + hypercall_msr.as_uint64 = hv_get_register(HV_X64_MSR_HYPERCALL); + hypercall_msr.enable = 0; + hv_set_register(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64); /* Reset the TSC page */ - hypercall_msr.as_uint64 = 0; - wrmsrl(HV_X64_MSR_REFERENCE_TSC, hypercall_msr.as_uint64); + tsc_msr.as_uint64 = hv_get_register(HV_X64_MSR_REFERENCE_TSC); + tsc_msr.enable = 0; + hv_set_register(HV_X64_MSR_REFERENCE_TSC, tsc_msr.as_uint64); } void hyperv_report_panic(struct pt_regs *regs, long err, bool in_die) diff --git a/arch/x86/include/asm/acrn.h b/arch/x86/include/asm/acrn.h index e003a01b7c67..1dd14381bcb6 100644 --- a/arch/x86/include/asm/acrn.h +++ b/arch/x86/include/asm/acrn.h @@ -10,6 +10,15 @@ /* Bit 0 indicates whether guest VM is privileged */ #define ACRN_FEATURE_PRIVILEGED_VM BIT(0) +/* + * Timing Information. + * This leaf returns the current TSC frequency in kHz. + * + * EAX: (Virtual) TSC frequency in kHz. + * EBX, ECX, EDX: RESERVED (reserved fields are set to zero). + */ +#define ACRN_CPUID_TIMING_INFO 0x40000010 + void acrn_setup_intr_handler(void (*handler)(void)); void acrn_remove_intr_handler(void); @@ -21,6 +30,11 @@ static inline u32 acrn_cpuid_base(void) return 0; } +static inline unsigned long acrn_get_tsc_khz(void) +{ + return cpuid_eax(ACRN_CPUID_TIMING_INFO); +} + /* * Hypercalls for ACRN * diff --git a/arch/x86/include/asm/amd-ibs.h b/arch/x86/include/asm/amd-ibs.h index f3eb098d63d4..cb2a5e113daa 100644 --- a/arch/x86/include/asm/amd-ibs.h +++ b/arch/x86/include/asm/amd-ibs.h @@ -6,6 +6,22 @@ #include <asm/msr-index.h> +/* IBS_OP_DATA2 DataSrc */ +#define IBS_DATA_SRC_LOC_CACHE 2 +#define IBS_DATA_SRC_DRAM 3 +#define IBS_DATA_SRC_REM_CACHE 4 +#define IBS_DATA_SRC_IO 7 + +/* IBS_OP_DATA2 DataSrc Extension */ +#define IBS_DATA_SRC_EXT_LOC_CACHE 1 +#define IBS_DATA_SRC_EXT_NEAR_CCX_CACHE 2 +#define IBS_DATA_SRC_EXT_DRAM 3 +#define IBS_DATA_SRC_EXT_FAR_CCX_CACHE 5 +#define IBS_DATA_SRC_EXT_PMEM 6 +#define IBS_DATA_SRC_EXT_IO 7 +#define IBS_DATA_SRC_EXT_EXT_MEM 8 +#define IBS_DATA_SRC_EXT_PEER_AGENT_MEM 12 + /* * IBS Hardware MSRs */ diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h index 973c6bd17f98..2edf68475fec 100644 --- a/arch/x86/include/asm/bitops.h +++ b/arch/x86/include/asm/bitops.h @@ -207,6 +207,20 @@ static __always_inline bool constant_test_bit(long nr, const volatile unsigned l (addr[nr >> _BITOPS_LONG_SHIFT])) != 0; } +static __always_inline bool constant_test_bit_acquire(long nr, const volatile unsigned long *addr) +{ + bool oldbit; + + asm volatile("testb %2,%1" + CC_SET(nz) + : CC_OUT(nz) (oldbit) + : "m" (((unsigned char *)addr)[nr >> 3]), + "i" (1 << (nr & 7)) + :"memory"); + + return oldbit; +} + static __always_inline bool variable_test_bit(long nr, volatile const unsigned long *addr) { bool oldbit; @@ -226,17 +240,37 @@ arch_test_bit(unsigned long nr, const volatile unsigned long *addr) variable_test_bit(nr, addr); } +static __always_inline bool +arch_test_bit_acquire(unsigned long nr, const volatile unsigned long *addr) +{ + return __builtin_constant_p(nr) ? constant_test_bit_acquire(nr, addr) : + variable_test_bit(nr, addr); +} + +static __always_inline unsigned long variable__ffs(unsigned long word) +{ + asm("rep; bsf %1,%0" + : "=r" (word) + : "rm" (word)); + return word; +} + /** * __ffs - find first set bit in word * @word: The word to search * * Undefined if no bit exists, so code should check against 0 first. */ -static __always_inline unsigned long __ffs(unsigned long word) +#define __ffs(word) \ + (__builtin_constant_p(word) ? \ + (unsigned long)__builtin_ctzl(word) : \ + variable__ffs(word)) + +static __always_inline unsigned long variable_ffz(unsigned long word) { asm("rep; bsf %1,%0" : "=r" (word) - : "rm" (word)); + : "r" (~word)); return word; } @@ -246,13 +280,10 @@ static __always_inline unsigned long __ffs(unsigned long word) * * Undefined if no zero exists, so code should check against ~0UL first. */ -static __always_inline unsigned long ffz(unsigned long word) -{ - asm("rep; bsf %1,%0" - : "=r" (word) - : "r" (~word)); - return word; -} +#define ffz(word) \ + (__builtin_constant_p(word) ? \ + (unsigned long)__builtin_ctzl(~word) : \ + variable_ffz(word)) /* * __fls: find last set bit in word @@ -271,18 +302,7 @@ static __always_inline unsigned long __fls(unsigned long word) #undef ADDR #ifdef __KERNEL__ -/** - * ffs - find first set bit in word - * @x: the word to search - * - * This is defined the same way as the libc and compiler builtin ffs - * routines, therefore differs in spirit from the other bitops. - * - * ffs(value) returns 0 if value is 0 or the position of the first - * set bit if value is nonzero. The first (least significant) bit - * is at position 1. - */ -static __always_inline int ffs(int x) +static __always_inline int variable_ffs(int x) { int r; @@ -313,6 +333,19 @@ static __always_inline int ffs(int x) } /** + * ffs - find first set bit in word + * @x: the word to search + * + * This is defined the same way as the libc and compiler builtin ffs + * routines, therefore differs in spirit from the other bitops. + * + * ffs(value) returns 0 if value is 0 or the position of the first + * set bit if value is nonzero. The first (least significant) bit + * is at position 1. + */ +#define ffs(x) (__builtin_constant_p(x) ? __builtin_ffs(x) : variable_ffs(x)) + +/** * fls - find last set bit in word * @x: the word to search * diff --git a/arch/x86/include/asm/cfi.h b/arch/x86/include/asm/cfi.h new file mode 100644 index 000000000000..58dacd90daef --- /dev/null +++ b/arch/x86/include/asm/cfi.h @@ -0,0 +1,22 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_CFI_H +#define _ASM_X86_CFI_H + +/* + * Clang Control Flow Integrity (CFI) support. + * + * Copyright (C) 2022 Google LLC + */ + +#include <linux/cfi.h> + +#ifdef CONFIG_CFI_CLANG +enum bug_trap_type handle_cfi_failure(struct pt_regs *regs); +#else +static inline enum bug_trap_type handle_cfi_failure(struct pt_regs *regs) +{ + return BUG_TRAP_TYPE_NONE; +} +#endif /* CONFIG_CFI_CLANG */ + +#endif /* _ASM_X86_CFI_H */ diff --git a/arch/x86/include/asm/checksum.h b/arch/x86/include/asm/checksum.h index bca625a60186..6df6ece8a28e 100644 --- a/arch/x86/include/asm/checksum.h +++ b/arch/x86/include/asm/checksum.h @@ -1,9 +1,13 @@ /* SPDX-License-Identifier: GPL-2.0 */ -#define _HAVE_ARCH_COPY_AND_CSUM_FROM_USER 1 -#define HAVE_CSUM_COPY_USER -#define _HAVE_ARCH_CSUM_AND_COPY -#ifdef CONFIG_X86_32 -# include <asm/checksum_32.h> +#ifdef CONFIG_GENERIC_CSUM +# include <asm-generic/checksum.h> #else -# include <asm/checksum_64.h> +# define _HAVE_ARCH_COPY_AND_CSUM_FROM_USER 1 +# define HAVE_CSUM_COPY_USER +# define _HAVE_ARCH_CSUM_AND_COPY +# ifdef CONFIG_X86_32 +# include <asm/checksum_32.h> +# else +# include <asm/checksum_64.h> +# endif #endif diff --git a/arch/x86/include/asm/cpu.h b/arch/x86/include/asm/cpu.h index 8cbf623f0ecf..b472ef76826a 100644 --- a/arch/x86/include/asm/cpu.h +++ b/arch/x86/include/asm/cpu.h @@ -94,4 +94,6 @@ static inline bool intel_cpu_signatures_match(unsigned int s1, unsigned int p1, return p1 & p2; } +extern u64 x86_read_arch_cap_msr(void); + #endif /* _ASM_X86_CPU_H */ diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index ea34cc31b047..1a85e1fb0922 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -155,20 +155,6 @@ extern void clear_cpu_cap(struct cpuinfo_x86 *c, unsigned int bit); #define setup_force_cpu_bug(bit) setup_force_cpu_cap(bit) -#if defined(__clang__) && !defined(CONFIG_CC_HAS_ASM_GOTO) - -/* - * Workaround for the sake of BPF compilation which utilizes kernel - * headers, but clang does not support ASM GOTO and fails the build. - */ -#ifndef __BPF_TRACING__ -#warning "Compiler lacks ASM_GOTO support. Add -D __BPF_TRACING__ to your compiler arguments" -#endif - -#define static_cpu_has(bit) boot_cpu_has(bit) - -#else - /* * Static testing of CPU features. Used the same as boot_cpu_has(). It * statically patches the target code for additional performance. Use @@ -208,7 +194,6 @@ t_no: boot_cpu_has(bit) : \ _static_cpu_has(bit) \ ) -#endif #define cpu_has_bug(c, bit) cpu_has(c, (bit)) #define set_cpu_bug(c, bit) set_cpu_cap(c, (bit)) diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 235dc85c91c3..b2da7cb64b31 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -96,7 +96,7 @@ #define X86_FEATURE_SYSCALL32 ( 3*32+14) /* "" syscall in IA32 userspace */ #define X86_FEATURE_SYSENTER32 ( 3*32+15) /* "" sysenter in IA32 userspace */ #define X86_FEATURE_REP_GOOD ( 3*32+16) /* REP microcode works well */ -/* FREE! ( 3*32+17) */ +#define X86_FEATURE_AMD_LBR_V2 ( 3*32+17) /* AMD Last Branch Record Extension Version 2 */ #define X86_FEATURE_LFENCE_RDTSC ( 3*32+18) /* "" LFENCE synchronizes RDTSC */ #define X86_FEATURE_ACC_POWER ( 3*32+19) /* AMD Accumulated Power Mechanism */ #define X86_FEATURE_NOPL ( 3*32+20) /* The NOPL (0F 1F) instructions */ @@ -305,6 +305,9 @@ #define X86_FEATURE_USE_IBPB_FW (11*32+16) /* "" Use IBPB during runtime firmware calls */ #define X86_FEATURE_RSB_VMEXIT_LITE (11*32+17) /* "" Fill RSB on VM exit when EIBRS is enabled */ + +#define X86_FEATURE_MSR_TSX_CTRL (11*32+20) /* "" MSR IA32_TSX_CTRL (Intel) implemented */ + /* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */ #define X86_FEATURE_AVX_VNNI (12*32+ 4) /* AVX VNNI instructions */ #define X86_FEATURE_AVX512_BF16 (12*32+ 5) /* AVX512 BFLOAT16 instructions */ @@ -457,7 +460,8 @@ #define X86_BUG_ITLB_MULTIHIT X86_BUG(23) /* CPU may incur MCE during certain page attribute changes */ #define X86_BUG_SRBDS X86_BUG(24) /* CPU may leak RNG bits if not mitigated */ #define X86_BUG_MMIO_STALE_DATA X86_BUG(25) /* CPU is affected by Processor MMIO Stale Data vulnerabilities */ -#define X86_BUG_RETBLEED X86_BUG(26) /* CPU is affected by RETBleed */ -#define X86_BUG_EIBRS_PBRSB X86_BUG(27) /* EIBRS is vulnerable to Post Barrier RSB Predictions */ +#define X86_BUG_MMIO_UNKNOWN X86_BUG(26) /* CPU is too old and its MMIO Stale Data status is unknown */ +#define X86_BUG_RETBLEED X86_BUG(27) /* CPU is affected by RETBleed */ +#define X86_BUG_EIBRS_PBRSB X86_BUG(28) /* EIBRS is vulnerable to Post Barrier RSB Predictions */ #endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/arch/x86/include/asm/extable_fixup_types.h b/arch/x86/include/asm/extable_fixup_types.h index 503622627400..991e31cfde94 100644 --- a/arch/x86/include/asm/extable_fixup_types.h +++ b/arch/x86/include/asm/extable_fixup_types.h @@ -64,4 +64,6 @@ #define EX_TYPE_UCOPY_LEN4 (EX_TYPE_UCOPY_LEN | EX_DATA_IMM(4)) #define EX_TYPE_UCOPY_LEN8 (EX_TYPE_UCOPY_LEN | EX_DATA_IMM(8)) +#define EX_TYPE_ZEROPAD 20 /* longword load with zeropad on fault */ + #endif diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h index b5ef474be858..908d99b127d3 100644 --- a/arch/x86/include/asm/ftrace.h +++ b/arch/x86/include/asm/ftrace.h @@ -23,7 +23,6 @@ #define HAVE_FUNCTION_GRAPH_RET_ADDR_PTR #ifndef __ASSEMBLY__ -extern atomic_t modifying_ftrace_code; extern void __fentry__(void); static inline unsigned long ftrace_call_adjust(unsigned long addr) diff --git a/arch/x86/include/asm/hw_breakpoint.h b/arch/x86/include/asm/hw_breakpoint.h index a1f0e90d0818..0bc931cd0698 100644 --- a/arch/x86/include/asm/hw_breakpoint.h +++ b/arch/x86/include/asm/hw_breakpoint.h @@ -44,10 +44,7 @@ struct arch_hw_breakpoint { /* Total number of available HW breakpoint registers */ #define HBP_NUM 4 -static inline int hw_breakpoint_slots(int type) -{ - return HBP_NUM; -} +#define hw_breakpoint_slots(type) (HBP_NUM) struct perf_event_attr; struct perf_event; diff --git a/arch/x86/include/asm/hyperv-tlfs.h b/arch/x86/include/asm/hyperv-tlfs.h index 0a9407dc0859..3089ec352743 100644 --- a/arch/x86/include/asm/hyperv-tlfs.h +++ b/arch/x86/include/asm/hyperv-tlfs.h @@ -138,6 +138,9 @@ #define HV_X64_NESTED_GUEST_MAPPING_FLUSH BIT(18) #define HV_X64_NESTED_MSR_BITMAP BIT(19) +/* Nested features #2. These are HYPERV_CPUID_NESTED_FEATURES.EBX bits. */ +#define HV_X64_NESTED_EVMCS1_PERF_GLOBAL_CTRL BIT(0) + /* * This is specific to AMD and specifies that enlightened TLB flush is * supported. If guest opts in to this feature, ASID invalidations only @@ -546,7 +549,7 @@ struct hv_enlightened_vmcs { u64 guest_rip; u32 hv_clean_fields; - u32 hv_padding_32; + u32 padding32_1; u32 hv_synthetic_controls; struct { u32 nested_flush_hypercall:1; @@ -554,14 +557,25 @@ struct hv_enlightened_vmcs { u32 reserved:30; } __packed hv_enlightenments_control; u32 hv_vp_id; - + u32 padding32_2; u64 hv_vm_id; u64 partition_assist_page; u64 padding64_4[4]; u64 guest_bndcfgs; - u64 padding64_5[7]; + u64 guest_ia32_perf_global_ctrl; + u64 guest_ia32_s_cet; + u64 guest_ssp; + u64 guest_ia32_int_ssp_table_addr; + u64 guest_ia32_lbr_ctl; + u64 padding64_5[2]; u64 xss_exit_bitmap; - u64 padding64_6[7]; + u64 encls_exiting_bitmap; + u64 host_ia32_perf_global_ctrl; + u64 tsc_multiplier; + u64 host_ia32_s_cet; + u64 host_ssp; + u64 host_ia32_int_ssp_table_addr; + u64 padding64_6; } __packed; #define HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE 0 diff --git a/arch/x86/include/asm/ibt.h b/arch/x86/include/asm/ibt.h index 689880eca9ba..9b08082a5d9f 100644 --- a/arch/x86/include/asm/ibt.h +++ b/arch/x86/include/asm/ibt.h @@ -31,6 +31,16 @@ #define __noendbr __attribute__((nocf_check)) +/* + * Create a dummy function pointer reference to prevent objtool from marking + * the function as needing to be "sealed" (i.e. ENDBR converted to NOP by + * apply_ibt_endbr()). + */ +#define IBT_NOSEAL(fname) \ + ".pushsection .discard.ibt_endbr_noseal\n\t" \ + _ASM_PTR fname "\n\t" \ + ".popsection\n\t" + static inline __attribute_const__ u32 gen_endbr(void) { u32 endbr; @@ -84,6 +94,7 @@ extern __noendbr void ibt_restore(u64 save); #ifndef __ASSEMBLY__ #define ASM_ENDBR +#define IBT_NOSEAL(name) #define __noendbr diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h index def6ca121111..347707d459c6 100644 --- a/arch/x86/include/asm/intel-family.h +++ b/arch/x86/include/asm/intel-family.h @@ -27,6 +27,7 @@ * _X - regular server parts * _D - micro server parts * _N,_P - other mobile parts + * _S - other client parts * * Historical OPTDIFFs: * @@ -106,14 +107,23 @@ #define INTEL_FAM6_SAPPHIRERAPIDS_X 0x8F /* Golden Cove */ +#define INTEL_FAM6_EMERALDRAPIDS_X 0xCF + +#define INTEL_FAM6_GRANITERAPIDS_X 0xAD +#define INTEL_FAM6_GRANITERAPIDS_D 0xAE + #define INTEL_FAM6_ALDERLAKE 0x97 /* Golden Cove / Gracemont */ #define INTEL_FAM6_ALDERLAKE_L 0x9A /* Golden Cove / Gracemont */ #define INTEL_FAM6_ALDERLAKE_N 0xBE #define INTEL_FAM6_RAPTORLAKE 0xB7 #define INTEL_FAM6_RAPTORLAKE_P 0xBA +#define INTEL_FAM6_RAPTORLAKE_S 0xBF + +#define INTEL_FAM6_METEORLAKE 0xAC +#define INTEL_FAM6_METEORLAKE_L 0xAA -/* "Small Core" Processors (Atom) */ +/* "Small Core" Processors (Atom/E-Core) */ #define INTEL_FAM6_ATOM_BONNELL 0x1C /* Diamondville, Pineview */ #define INTEL_FAM6_ATOM_BONNELL_MID 0x26 /* Silverthorne, Lincroft */ @@ -140,6 +150,10 @@ #define INTEL_FAM6_ATOM_TREMONT 0x96 /* Elkhart Lake */ #define INTEL_FAM6_ATOM_TREMONT_L 0x9C /* Jasper Lake */ +#define INTEL_FAM6_SIERRAFOREST_X 0xAF + +#define INTEL_FAM6_GRANDRIDGE 0xB6 + /* Xeon Phi */ #define INTEL_FAM6_XEON_PHI_KNL 0x57 /* Knights Landing */ diff --git a/arch/x86/include/asm/iommu.h b/arch/x86/include/asm/iommu.h index 0bef44d30a27..2fd52b65deac 100644 --- a/arch/x86/include/asm/iommu.h +++ b/arch/x86/include/asm/iommu.h @@ -25,8 +25,10 @@ arch_rmrr_sanity_check(struct acpi_dmar_reserved_memory *rmrr) { u64 start = rmrr->base_address; u64 end = rmrr->end_address + 1; + int entry_type; - if (e820__mapped_all(start, end, E820_TYPE_RESERVED)) + entry_type = e820__get_entry_type(start, end); + if (entry_type == E820_TYPE_RESERVED || entry_type == E820_TYPE_NVS) return 0; pr_err(FW_BUG "No firmware reserved region can cover this RMRR [%#018Lx-%#018Lx], contact BIOS vendor for fixes\n", diff --git a/arch/x86/include/asm/irq_stack.h b/arch/x86/include/asm/irq_stack.h index 63f818aedf77..147cb8fdda92 100644 --- a/arch/x86/include/asm/irq_stack.h +++ b/arch/x86/include/asm/irq_stack.h @@ -203,7 +203,7 @@ IRQ_CONSTRAINTS, regs, vector); \ } -#ifndef CONFIG_PREEMPT_RT +#ifdef CONFIG_SOFTIRQ_ON_OWN_STACK /* * Macro to invoke __do_softirq on the irq stack. This is only called from * task context when bottom halves are about to be reenabled and soft diff --git a/arch/x86/include/asm/kmsan.h b/arch/x86/include/asm/kmsan.h new file mode 100644 index 000000000000..8fa6ac0e2d76 --- /dev/null +++ b/arch/x86/include/asm/kmsan.h @@ -0,0 +1,87 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * x86 KMSAN support. + * + * Copyright (C) 2022, Google LLC + * Author: Alexander Potapenko <[email protected]> + */ + +#ifndef _ASM_X86_KMSAN_H +#define _ASM_X86_KMSAN_H + +#ifndef MODULE + +#include <asm/cpu_entry_area.h> +#include <asm/processor.h> +#include <linux/mmzone.h> + +DECLARE_PER_CPU(char[CPU_ENTRY_AREA_SIZE], cpu_entry_area_shadow); +DECLARE_PER_CPU(char[CPU_ENTRY_AREA_SIZE], cpu_entry_area_origin); + +/* + * Functions below are declared in the header to make sure they are inlined. + * They all are called from kmsan_get_metadata() for every memory access in + * the kernel, so speed is important here. + */ + +/* + * Compute metadata addresses for the CPU entry area on x86. + */ +static inline void *arch_kmsan_get_meta_or_null(void *addr, bool is_origin) +{ + unsigned long addr64 = (unsigned long)addr; + char *metadata_array; + unsigned long off; + int cpu; + + if ((addr64 < CPU_ENTRY_AREA_BASE) || + (addr64 >= (CPU_ENTRY_AREA_BASE + CPU_ENTRY_AREA_MAP_SIZE))) + return NULL; + cpu = (addr64 - CPU_ENTRY_AREA_BASE) / CPU_ENTRY_AREA_SIZE; + off = addr64 - (unsigned long)get_cpu_entry_area(cpu); + if ((off < 0) || (off >= CPU_ENTRY_AREA_SIZE)) + return NULL; + metadata_array = is_origin ? cpu_entry_area_origin : + cpu_entry_area_shadow; + return &per_cpu(metadata_array[off], cpu); +} + +/* + * Taken from arch/x86/mm/physaddr.h to avoid using an instrumented version. + */ +static inline bool kmsan_phys_addr_valid(unsigned long addr) +{ + if (IS_ENABLED(CONFIG_PHYS_ADDR_T_64BIT)) + return !(addr >> boot_cpu_data.x86_phys_bits); + else + return true; +} + +/* + * Taken from arch/x86/mm/physaddr.c to avoid using an instrumented version. + */ +static inline bool kmsan_virt_addr_valid(void *addr) +{ + unsigned long x = (unsigned long)addr; + unsigned long y = x - __START_KERNEL_map; + + /* use the carry flag to determine if x was < __START_KERNEL_map */ + if (unlikely(x > y)) { + x = y + phys_base; + + if (y >= KERNEL_IMAGE_SIZE) + return false; + } else { + x = y + (__START_KERNEL_map - PAGE_OFFSET); + + /* carry flag will be set if starting x was >= PAGE_OFFSET */ + if ((x > y) || !kmsan_phys_addr_valid(x)) + return false; + } + + return pfn_valid(x >> PAGE_SHIFT); +} + +#endif /* !MODULE */ + +#endif /* _ASM_X86_KMSAN_H */ diff --git a/arch/x86/include/asm/kprobes.h b/arch/x86/include/asm/kprobes.h index 71ea2eab43d5..a2e9317aad49 100644 --- a/arch/x86/include/asm/kprobes.h +++ b/arch/x86/include/asm/kprobes.h @@ -50,8 +50,6 @@ extern const int kretprobe_blacklist_size; void arch_remove_kprobe(struct kprobe *p); -extern void arch_kprobe_override_function(struct pt_regs *regs); - /* Architecture specific copy of original instruction*/ struct arch_specific_insn { /* copy of the original instruction */ diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h index 51f777071584..82ba4a564e58 100644 --- a/arch/x86/include/asm/kvm-x86-ops.h +++ b/arch/x86/include/asm/kvm-x86-ops.h @@ -67,7 +67,7 @@ KVM_X86_OP(get_interrupt_shadow) KVM_X86_OP(patch_hypercall) KVM_X86_OP(inject_irq) KVM_X86_OP(inject_nmi) -KVM_X86_OP(queue_exception) +KVM_X86_OP(inject_exception) KVM_X86_OP(cancel_injection) KVM_X86_OP(interrupt_allowed) KVM_X86_OP(nmi_allowed) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 5ffa578cafe1..f05ebaa26f0f 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -53,7 +53,7 @@ #define KVM_MAX_VCPU_IDS (KVM_MAX_VCPUS * KVM_VCPU_ID_RATIO) /* memory slots that are not exposed to userspace */ -#define KVM_PRIVATE_MEM_SLOTS 3 +#define KVM_INTERNAL_MEM_SLOTS 3 #define KVM_HALT_POLL_NS_DEFAULT 200000 @@ -501,7 +501,12 @@ struct kvm_pmc { bool intr; }; +/* More counters may conflict with other existing Architectural MSRs */ +#define KVM_INTEL_PMC_MAX_GENERIC 8 +#define MSR_ARCH_PERFMON_PERFCTR_MAX (MSR_ARCH_PERFMON_PERFCTR0 + KVM_INTEL_PMC_MAX_GENERIC - 1) +#define MSR_ARCH_PERFMON_EVENTSEL_MAX (MSR_ARCH_PERFMON_EVENTSEL0 + KVM_INTEL_PMC_MAX_GENERIC - 1) #define KVM_PMC_MAX_FIXED 3 +#define KVM_AMD_PMC_MAX_GENERIC 6 struct kvm_pmu { unsigned nr_arch_gp_counters; unsigned nr_arch_fixed_counters; @@ -516,7 +521,7 @@ struct kvm_pmu { u64 reserved_bits; u64 raw_event_mask; u8 version; - struct kvm_pmc gp_counters[INTEL_PMC_MAX_GENERIC]; + struct kvm_pmc gp_counters[KVM_INTEL_PMC_MAX_GENERIC]; struct kvm_pmc fixed_counters[KVM_PMC_MAX_FIXED]; struct irq_work irq_work; DECLARE_BITMAP(reprogram_pmi, X86_PMC_IDX_MAX); @@ -615,6 +620,8 @@ struct kvm_vcpu_hv { u32 enlightenments_eax; /* HYPERV_CPUID_ENLIGHTMENT_INFO.EAX */ u32 enlightenments_ebx; /* HYPERV_CPUID_ENLIGHTMENT_INFO.EBX */ u32 syndbg_cap_eax; /* HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES.EAX */ + u32 nested_eax; /* HYPERV_CPUID_NESTED_FEATURES.EAX */ + u32 nested_ebx; /* HYPERV_CPUID_NESTED_FEATURES.EBX */ } cpuid_cache; }; @@ -639,6 +646,16 @@ struct kvm_vcpu_xen { struct timer_list poll_timer; }; +struct kvm_queued_exception { + bool pending; + bool injected; + bool has_error_code; + u8 vector; + u32 error_code; + unsigned long payload; + bool has_payload; +}; + struct kvm_vcpu_arch { /* * rip and regs accesses must go through @@ -729,6 +746,7 @@ struct kvm_vcpu_arch { struct fpu_guest guest_fpu; u64 xcr0; + u64 guest_supported_xcr0; struct kvm_pio_request pio; void *pio_data; @@ -737,16 +755,12 @@ struct kvm_vcpu_arch { u8 event_exit_inst_len; - struct kvm_queued_exception { - bool pending; - bool injected; - bool has_error_code; - u8 nr; - u32 error_code; - unsigned long payload; - bool has_payload; - u8 nested_apf; - } exception; + bool exception_from_userspace; + + /* Exceptions to be injected to the guest. */ + struct kvm_queued_exception exception; + /* Exception VM-Exits to be synthesized to L1. */ + struct kvm_queued_exception exception_vmexit; struct kvm_queued_interrupt { bool injected; @@ -857,7 +871,6 @@ struct kvm_vcpu_arch { u32 id; bool send_user_only; u32 host_apf_flags; - unsigned long nested_apf_token; bool delivery_as_pf_vmexit; bool pageready_pending; } apf; @@ -1272,8 +1285,8 @@ struct kvm_arch { bool tdp_mmu_enabled; /* - * List of struct kvm_mmu_pages being used as roots. - * All struct kvm_mmu_pages in the list should have + * List of kvm_mmu_page structs being used as roots. + * All kvm_mmu_page structs in the list should have * tdp_mmu_page set. * * For reads, this list is protected by: @@ -1292,8 +1305,8 @@ struct kvm_arch { struct list_head tdp_mmu_roots; /* - * List of struct kvmp_mmu_pages not being used as roots. - * All struct kvm_mmu_pages in the list should have + * List of kvm_mmu_page structs not being used as roots. + * All kvm_mmu_page structs in the list should have * tdp_mmu_page set and a tdp_mmu_root_count of 0. */ struct list_head tdp_mmu_pages; @@ -1303,9 +1316,9 @@ struct kvm_arch { * is held in read mode: * - tdp_mmu_roots (above) * - tdp_mmu_pages (above) - * - the link field of struct kvm_mmu_pages used by the TDP MMU + * - the link field of kvm_mmu_page structs used by the TDP MMU * - lpage_disallowed_mmu_pages - * - the lpage_disallowed_link field of struct kvm_mmu_pages used + * - the lpage_disallowed_link field of kvm_mmu_page structs used * by the TDP MMU * It is acceptable, but not necessary, to acquire this lock when * the thread holds the MMU lock in write mode. @@ -1523,7 +1536,7 @@ struct kvm_x86_ops { unsigned char *hypercall_addr); void (*inject_irq)(struct kvm_vcpu *vcpu, bool reinjected); void (*inject_nmi)(struct kvm_vcpu *vcpu); - void (*queue_exception)(struct kvm_vcpu *vcpu); + void (*inject_exception)(struct kvm_vcpu *vcpu); void (*cancel_injection)(struct kvm_vcpu *vcpu); int (*interrupt_allowed)(struct kvm_vcpu *vcpu, bool for_injection); int (*nmi_allowed)(struct kvm_vcpu *vcpu, bool for_injection); @@ -1633,10 +1646,10 @@ struct kvm_x86_ops { struct kvm_x86_nested_ops { void (*leave_nested)(struct kvm_vcpu *vcpu); + bool (*is_exception_vmexit)(struct kvm_vcpu *vcpu, u8 vector, + u32 error_code); int (*check_events)(struct kvm_vcpu *vcpu); - bool (*handle_page_fault_workaround)(struct kvm_vcpu *vcpu, - struct x86_exception *fault); - bool (*hv_timer_pending)(struct kvm_vcpu *vcpu); + bool (*has_events)(struct kvm_vcpu *vcpu); void (*triple_fault)(struct kvm_vcpu *vcpu); int (*get_state)(struct kvm_vcpu *vcpu, struct kvm_nested_state __user *user_kvm_nested_state, @@ -1862,7 +1875,7 @@ void kvm_queue_exception_p(struct kvm_vcpu *vcpu, unsigned nr, unsigned long pay void kvm_requeue_exception(struct kvm_vcpu *vcpu, unsigned nr); void kvm_requeue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code); void kvm_inject_page_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault); -bool kvm_inject_emulated_page_fault(struct kvm_vcpu *vcpu, +void kvm_inject_emulated_page_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault); bool kvm_require_cpl(struct kvm_vcpu *vcpu, int required_cpl); bool kvm_require_dr(struct kvm_vcpu *vcpu, int dr); diff --git a/arch/x86/include/asm/linkage.h b/arch/x86/include/asm/linkage.h index 73ca20049835..f484d656d34e 100644 --- a/arch/x86/include/asm/linkage.h +++ b/arch/x86/include/asm/linkage.h @@ -43,6 +43,18 @@ #endif /* __ASSEMBLY__ */ +#define __CFI_TYPE(name) \ + SYM_START(__cfi_##name, SYM_L_LOCAL, SYM_A_NONE) \ + .fill 11, 1, 0x90 ASM_NL \ + .byte 0xb8 ASM_NL \ + .long __kcfi_typeid_##name ASM_NL \ + SYM_FUNC_END(__cfi_##name) + +/* SYM_TYPED_FUNC_START -- use for indirectly called globals, w/ CFI type */ +#define SYM_TYPED_FUNC_START(name) \ + SYM_TYPED_START(name, SYM_L_GLOBAL, SYM_A_ALIGN) \ + ENDBR + /* SYM_FUNC_START -- use for global functions */ #define SYM_FUNC_START(name) \ SYM_START(name, SYM_L_GLOBAL, SYM_A_ALIGN) \ diff --git a/arch/x86/include/asm/mc146818rtc.h b/arch/x86/include/asm/mc146818rtc.h index 97198001e567..6115bb3d5795 100644 --- a/arch/x86/include/asm/mc146818rtc.h +++ b/arch/x86/include/asm/mc146818rtc.h @@ -95,7 +95,7 @@ static inline unsigned char current_lock_cmos_reg(void) unsigned char rtc_cmos_read(unsigned char addr); void rtc_cmos_write(unsigned char val, unsigned char addr); -extern int mach_set_rtc_mmss(const struct timespec64 *now); +extern int mach_set_cmos_time(const struct timespec64 *now); extern void mach_get_cmos_time(struct timespec64 *now); #define RTC_IRQ 8 diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h index cc73061e7255..6e986088817d 100644 --- a/arch/x86/include/asm/mce.h +++ b/arch/x86/include/asm/mce.h @@ -42,6 +42,7 @@ #define MCI_STATUS_CEC_SHIFT 38 /* Corrected Error Count */ #define MCI_STATUS_CEC_MASK GENMASK_ULL(52,38) #define MCI_STATUS_CEC(c) (((c) & MCI_STATUS_CEC_MASK) >> MCI_STATUS_CEC_SHIFT) +#define MCI_STATUS_MSCOD(m) (((m) >> 16) & 0xffff) /* AMD-specific bits */ #define MCI_STATUS_TCC BIT_ULL(55) /* Task context corrupt */ diff --git a/arch/x86/include/asm/microcode.h b/arch/x86/include/asm/microcode.h index 0c3d3440fe27..74ecc2bd6cd0 100644 --- a/arch/x86/include/asm/microcode.h +++ b/arch/x86/include/asm/microcode.h @@ -9,6 +9,7 @@ struct ucode_patch { struct list_head plist; void *data; /* Intel uses only this one */ + unsigned int size; u32 patch_id; u16 equiv_cpu; }; @@ -32,9 +33,6 @@ enum ucode_state { }; struct microcode_ops { - enum ucode_state (*request_microcode_user) (int cpu, - const void __user *buf, size_t size); - enum ucode_state (*request_microcode_fw) (int cpu, struct device *, bool refresh_fw); diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 6674bdb096f3..4a2af82553e4 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -155,6 +155,11 @@ * Return Stack Buffer Predictions. */ +#define ARCH_CAP_XAPIC_DISABLE BIT(21) /* + * IA32_XAPIC_DISABLE_STATUS MSR + * supported + */ + #define MSR_IA32_FLUSH_CMD 0x0000010b #define L1D_FLUSH BIT(0) /* * Writeback and invalidate the @@ -530,6 +535,11 @@ #define MSR_AMD64_CPUID_FN_1 0xc0011004 #define MSR_AMD64_LS_CFG 0xc0011020 #define MSR_AMD64_DC_CFG 0xc0011022 + +#define MSR_AMD64_DE_CFG 0xc0011029 +#define MSR_AMD64_DE_CFG_LFENCE_SERIALIZE_BIT 1 +#define MSR_AMD64_DE_CFG_LFENCE_SERIALIZE BIT_ULL(MSR_AMD64_DE_CFG_LFENCE_SERIALIZE_BIT) + #define MSR_AMD64_BU_CFG2 0xc001102a #define MSR_AMD64_IBSFETCHCTL 0xc0011030 #define MSR_AMD64_IBSFETCHLINAD 0xc0011031 @@ -585,6 +595,9 @@ #define MSR_AMD64_PERF_CNTR_GLOBAL_CTL 0xc0000301 #define MSR_AMD64_PERF_CNTR_GLOBAL_STATUS_CLR 0xc0000302 +/* AMD Last Branch Record MSRs */ +#define MSR_AMD64_LBR_SELECT 0xc000010e + /* Fam 17h MSRs */ #define MSR_F17H_IRPERF 0xc00000e9 @@ -632,9 +645,6 @@ #define FAM10H_MMIO_CONF_BASE_MASK 0xfffffffULL #define FAM10H_MMIO_CONF_BASE_SHIFT 20 #define MSR_FAM10H_NODE_ID 0xc001100c -#define MSR_F10H_DECFG 0xc0011029 -#define MSR_F10H_DECFG_LFENCE_SERIALIZE_BIT 1 -#define MSR_F10H_DECFG_LFENCE_SERIALIZE BIT_ULL(MSR_F10H_DECFG_LFENCE_SERIALIZE_BIT) /* K8 MSRs */ #define MSR_K8_TOP_MEM1 0xc001001a @@ -756,6 +766,8 @@ #define MSR_AMD_DBG_EXTN_CFG 0xc000010f #define MSR_AMD_SAMP_BR_FROM 0xc0010300 +#define DBG_EXTN_CFG_LBRV2EN BIT_ULL(6) + #define MSR_IA32_MPERF 0x000000e7 #define MSR_IA32_APERF 0x000000e8 @@ -1054,4 +1066,12 @@ #define MSR_IA32_HW_FEEDBACK_PTR 0x17d0 #define MSR_IA32_HW_FEEDBACK_CONFIG 0x17d1 +/* x2APIC locked status */ +#define MSR_IA32_XAPIC_DISABLE_STATUS 0xBD +#define LEGACY_XAPIC_DISABLED BIT(0) /* + * x2APIC mode is locked and + * disabling x2APIC will cause + * a #GP + */ + #endif /* _ASM_X86_MSR_INDEX_H */ diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index e64fd20778b6..c936ce9f0c47 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -35,33 +35,56 @@ #define RSB_CLEAR_LOOPS 32 /* To forcibly overwrite all entries */ /* + * Common helper for __FILL_RETURN_BUFFER and __FILL_ONE_RETURN. + */ +#define __FILL_RETURN_SLOT \ + ANNOTATE_INTRA_FUNCTION_CALL; \ + call 772f; \ + int3; \ +772: + +/* + * Stuff the entire RSB. + * * Google experimented with loop-unrolling and this turned out to be * the optimal version - two calls, each with their own speculation * trap should their return address end up getting used, in a loop. */ -#define __FILL_RETURN_BUFFER(reg, nr, sp) \ - mov $(nr/2), reg; \ -771: \ - ANNOTATE_INTRA_FUNCTION_CALL; \ - call 772f; \ -773: /* speculation trap */ \ - UNWIND_HINT_EMPTY; \ - pause; \ - lfence; \ - jmp 773b; \ -772: \ - ANNOTATE_INTRA_FUNCTION_CALL; \ - call 774f; \ -775: /* speculation trap */ \ - UNWIND_HINT_EMPTY; \ - pause; \ - lfence; \ - jmp 775b; \ -774: \ - add $(BITS_PER_LONG/8) * 2, sp; \ - dec reg; \ - jnz 771b; \ - /* barrier for jnz misprediction */ \ +#ifdef CONFIG_X86_64 +#define __FILL_RETURN_BUFFER(reg, nr) \ + mov $(nr/2), reg; \ +771: \ + __FILL_RETURN_SLOT \ + __FILL_RETURN_SLOT \ + add $(BITS_PER_LONG/8) * 2, %_ASM_SP; \ + dec reg; \ + jnz 771b; \ + /* barrier for jnz misprediction */ \ + lfence; +#else +/* + * i386 doesn't unconditionally have LFENCE, as such it can't + * do a loop. + */ +#define __FILL_RETURN_BUFFER(reg, nr) \ + .rept nr; \ + __FILL_RETURN_SLOT; \ + .endr; \ + add $(BITS_PER_LONG/8) * nr, %_ASM_SP; +#endif + +/* + * Stuff a single RSB slot. + * + * To mitigate Post-Barrier RSB speculation, one CALL instruction must be + * forced to retire before letting a RET instruction execute. + * + * On PBRSB-vulnerable CPUs, it is not safe for a RET to be executed + * before this point. + */ +#define __FILL_ONE_RETURN \ + __FILL_RETURN_SLOT \ + add $(BITS_PER_LONG/8), %_ASM_SP; \ lfence; #ifdef __ASSEMBLY__ @@ -132,28 +155,15 @@ #endif .endm -.macro ISSUE_UNBALANCED_RET_GUARD - ANNOTATE_INTRA_FUNCTION_CALL - call .Lunbalanced_ret_guard_\@ - int3 -.Lunbalanced_ret_guard_\@: - add $(BITS_PER_LONG/8), %_ASM_SP - lfence -.endm - /* * A simpler FILL_RETURN_BUFFER macro. Don't make people use the CPP * monstrosity above, manually. */ -.macro FILL_RETURN_BUFFER reg:req nr:req ftr:req ftr2 -.ifb \ftr2 - ALTERNATIVE "jmp .Lskip_rsb_\@", "", \ftr -.else - ALTERNATIVE_2 "jmp .Lskip_rsb_\@", "", \ftr, "jmp .Lunbalanced_\@", \ftr2 -.endif - __FILL_RETURN_BUFFER(\reg,\nr,%_ASM_SP) -.Lunbalanced_\@: - ISSUE_UNBALANCED_RET_GUARD +.macro FILL_RETURN_BUFFER reg:req nr:req ftr:req ftr2=ALT_NOT(X86_FEATURE_ALWAYS) + ALTERNATIVE_2 "jmp .Lskip_rsb_\@", \ + __stringify(__FILL_RETURN_BUFFER(\reg,\nr)), \ftr, \ + __stringify(__FILL_ONE_RETURN), \ftr2 + .Lskip_rsb_\@: .endm diff --git a/arch/x86/include/asm/page_64.h b/arch/x86/include/asm/page_64.h index baa70451b8df..198e03e59ca1 100644 --- a/arch/x86/include/asm/page_64.h +++ b/arch/x86/include/asm/page_64.h @@ -8,6 +8,8 @@ #include <asm/cpufeatures.h> #include <asm/alternative.h> +#include <linux/kmsan-checks.h> + /* duplicated to the one in bootmem.h */ extern unsigned long max_pfn; extern unsigned long phys_base; @@ -47,6 +49,11 @@ void clear_page_erms(void *page); static inline void clear_page(void *page) { + /* + * Clean up KMSAN metadata for the page being cleared. The assembly call + * below clobbers @page, so we perform unpoisoning before it. + */ + kmsan_unpoison_memory(page, PAGE_SIZE); alternative_call_2(clear_page_orig, clear_page_rep, X86_FEATURE_REP_GOOD, clear_page_erms, X86_FEATURE_ERMS, diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index 964442b99245..2a0b8dd4ec33 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -743,6 +743,7 @@ extern void default_banner(void); word 771b; \ .byte ptype; \ .byte 772b-771b; \ + _ASM_ALIGN; \ .popsection diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h index 89df6c6617f5..f3d601574730 100644 --- a/arch/x86/include/asm/paravirt_types.h +++ b/arch/x86/include/asm/paravirt_types.h @@ -294,6 +294,7 @@ extern struct paravirt_patch_template pv_ops; " .byte " type "\n" \ " .byte 772b-771b\n" \ " .short " clobber "\n" \ + _ASM_ALIGN "\n" \ ".popsection\n" /* Generate patchable code, with the default asm parameters. */ @@ -328,7 +329,7 @@ int paravirt_disable_iospace(void); * Unfortunately, this is a relatively slow operation for modern CPUs, * because it cannot necessarily determine what the destination * address is. In this case, the address is a runtime constant, so at - * the very least we can patch the call to e a simple direct call, or + * the very least we can patch the call to a simple direct call, or, * ideally, patch an inline implementation into the callsite. (Direct * calls are essentially free, because the call and return addresses * are completely predictable.) @@ -339,10 +340,10 @@ int paravirt_disable_iospace(void); * on the stack. All caller-save registers (eax,edx,ecx) are expected * to be modified (either clobbered or used for return values). * X86_64, on the other hand, already specifies a register-based calling - * conventions, returning at %rax, with parameters going on %rdi, %rsi, + * conventions, returning at %rax, with parameters going in %rdi, %rsi, * %rdx, and %rcx. Note that for this reason, x86_64 does not need any * special handling for dealing with 4 arguments, unlike i386. - * However, x86_64 also have to clobber all caller saved registers, which + * However, x86_64 also has to clobber all caller saved registers, which * unfortunately, are quite a bit (r8 - r11) * * The call instruction itself is marked by placing its start address @@ -360,22 +361,22 @@ int paravirt_disable_iospace(void); * There are 5 sets of PVOP_* macros for dealing with 0-4 arguments. * It could be extended to more arguments, but there would be little * to be gained from that. For each number of arguments, there are - * the two VCALL and CALL variants for void and non-void functions. + * two VCALL and CALL variants for void and non-void functions. * * When there is a return value, the invoker of the macro must specify * the return type. The macro then uses sizeof() on that type to - * determine whether its a 32 or 64 bit value, and places the return + * determine whether it's a 32 or 64 bit value and places the return * in the right register(s) (just %eax for 32-bit, and %edx:%eax for - * 64-bit). For x86_64 machines, it just returns at %rax regardless of + * 64-bit). For x86_64 machines, it just returns in %rax regardless of * the return value size. * - * 64-bit arguments are passed as a pair of adjacent 32-bit arguments + * 64-bit arguments are passed as a pair of adjacent 32-bit arguments; * i386 also passes 64-bit arguments as a pair of adjacent 32-bit arguments * in low,high order * * Small structures are passed and returned in registers. The macro * calling convention can't directly deal with this, so the wrapper - * functions must do this. + * functions must do it. * * These PVOP_* macros are only defined within this header. This * means that all uses must be wrapped in inline functions. This also @@ -414,8 +415,17 @@ int paravirt_disable_iospace(void); "=c" (__ecx) #define PVOP_CALL_CLOBBERS PVOP_VCALL_CLOBBERS, "=a" (__eax) -/* void functions are still allowed [re]ax for scratch */ +/* + * void functions are still allowed [re]ax for scratch. + * + * The ZERO_CALL_USED REGS feature may end up zeroing out callee-saved + * registers. Make sure we model this with the appropriate clobbers. + */ +#ifdef CONFIG_ZERO_CALL_USED_REGS +#define PVOP_VCALLEE_CLOBBERS "=a" (__eax), PVOP_VCALL_CLOBBERS +#else #define PVOP_VCALLEE_CLOBBERS "=a" (__eax) +#endif #define PVOP_CALLEE_CLOBBERS PVOP_VCALLEE_CLOBBERS #define EXTRA_CLOBBERS , "r8", "r9", "r10", "r11" diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h index f6fc8dd51ef4..9ac46dbe57d4 100644 --- a/arch/x86/include/asm/perf_event.h +++ b/arch/x86/include/asm/perf_event.h @@ -207,7 +207,8 @@ union cpuid_0x80000022_ebx { struct { /* Number of Core Performance Counters */ unsigned int num_core_pmc:4; - unsigned int reserved:6; + /* Number of available LBR Stack Entries */ + unsigned int lbr_v2_stack_sz:6; /* Number of Data Fabric Counters */ unsigned int num_df_pmc:6; } split; diff --git a/arch/x86/include/asm/pgtable-3level.h b/arch/x86/include/asm/pgtable-3level.h index e896ebef8c24..28421a887209 100644 --- a/arch/x86/include/asm/pgtable-3level.h +++ b/arch/x86/include/asm/pgtable-3level.h @@ -256,10 +256,10 @@ static inline pud_t native_pudp_get_and_clear(pud_t *pudp) /* We always extract/encode the offset by shifting it all the way up, and then down again */ #define SWP_OFFSET_SHIFT (SWP_OFFSET_FIRST_BIT + SWP_TYPE_BITS) -#define MAX_SWAPFILES_CHECK() BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > 5) -#define __swp_type(x) (((x).val) & 0x1f) -#define __swp_offset(x) ((x).val >> 5) -#define __swp_entry(type, offset) ((swp_entry_t){(type) | (offset) << 5}) +#define MAX_SWAPFILES_CHECK() BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > SWP_TYPE_BITS) +#define __swp_type(x) (((x).val) & ((1UL << SWP_TYPE_BITS) - 1)) +#define __swp_offset(x) ((x).val >> SWP_TYPE_BITS) +#define __swp_entry(type, offset) ((swp_entry_t){(type) | (offset) << SWP_TYPE_BITS}) /* * Normally, __swp_entry() converts from arch-independent swp_entry_t to diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index 44e2d6f1dbaa..5059799bebe3 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -815,7 +815,8 @@ static inline unsigned long pmd_page_vaddr(pmd_t pmd) static inline int pmd_bad(pmd_t pmd) { - return (pmd_flags(pmd) & ~_PAGE_USER) != _KERNPG_TABLE; + return (pmd_flags(pmd) & ~(_PAGE_USER | _PAGE_ACCESSED)) != + (_KERNPG_TABLE & ~_PAGE_ACCESSED); } static inline unsigned long pages_to_mb(unsigned long npg) @@ -1431,10 +1432,10 @@ static inline bool arch_has_pfn_modify_check(void) return boot_cpu_has_bug(X86_BUG_L1TF); } -#define arch_faults_on_old_pte arch_faults_on_old_pte -static inline bool arch_faults_on_old_pte(void) +#define arch_has_hw_pte_young arch_has_hw_pte_young +static inline bool arch_has_hw_pte_young(void) { - return false; + return true; } #ifdef CONFIG_PAGE_TABLE_CHECK diff --git a/arch/x86/include/asm/pgtable_64_types.h b/arch/x86/include/asm/pgtable_64_types.h index 70e360a2e5fb..04f36063ad54 100644 --- a/arch/x86/include/asm/pgtable_64_types.h +++ b/arch/x86/include/asm/pgtable_64_types.h @@ -139,7 +139,52 @@ extern unsigned int ptrs_per_p4d; # define VMEMMAP_START __VMEMMAP_BASE_L4 #endif /* CONFIG_DYNAMIC_MEMORY_LAYOUT */ -#define VMALLOC_END (VMALLOC_START + (VMALLOC_SIZE_TB << 40) - 1) +/* + * End of the region for which vmalloc page tables are pre-allocated. + * For non-KMSAN builds, this is the same as VMALLOC_END. + * For KMSAN builds, VMALLOC_START..VMEMORY_END is 4 times bigger than + * VMALLOC_START..VMALLOC_END (see below). + */ +#define VMEMORY_END (VMALLOC_START + (VMALLOC_SIZE_TB << 40) - 1) + +#ifndef CONFIG_KMSAN +#define VMALLOC_END VMEMORY_END +#else +/* + * In KMSAN builds vmalloc area is four times smaller, and the remaining 3/4 + * are used to keep the metadata for virtual pages. The memory formerly + * belonging to vmalloc area is now laid out as follows: + * + * 1st quarter: VMALLOC_START to VMALLOC_END - new vmalloc area + * 2nd quarter: KMSAN_VMALLOC_SHADOW_START to + * VMALLOC_END+KMSAN_VMALLOC_SHADOW_OFFSET - vmalloc area shadow + * 3rd quarter: KMSAN_VMALLOC_ORIGIN_START to + * VMALLOC_END+KMSAN_VMALLOC_ORIGIN_OFFSET - vmalloc area origins + * 4th quarter: KMSAN_MODULES_SHADOW_START to KMSAN_MODULES_ORIGIN_START + * - shadow for modules, + * KMSAN_MODULES_ORIGIN_START to + * KMSAN_MODULES_ORIGIN_START + MODULES_LEN - origins for modules. + */ +#define VMALLOC_QUARTER_SIZE ((VMALLOC_SIZE_TB << 40) >> 2) +#define VMALLOC_END (VMALLOC_START + VMALLOC_QUARTER_SIZE - 1) + +/* + * vmalloc metadata addresses are calculated by adding shadow/origin offsets + * to vmalloc address. + */ +#define KMSAN_VMALLOC_SHADOW_OFFSET VMALLOC_QUARTER_SIZE +#define KMSAN_VMALLOC_ORIGIN_OFFSET (VMALLOC_QUARTER_SIZE << 1) + +#define KMSAN_VMALLOC_SHADOW_START (VMALLOC_START + KMSAN_VMALLOC_SHADOW_OFFSET) +#define KMSAN_VMALLOC_ORIGIN_START (VMALLOC_START + KMSAN_VMALLOC_ORIGIN_OFFSET) + +/* + * The shadow/origin for modules are placed one by one in the last 1/4 of + * vmalloc space. + */ +#define KMSAN_MODULES_SHADOW_START (VMALLOC_END + KMSAN_VMALLOC_ORIGIN_OFFSET + 1) +#define KMSAN_MODULES_ORIGIN_START (KMSAN_MODULES_SHADOW_START + MODULES_LEN) +#endif /* CONFIG_KMSAN */ #define MODULES_VADDR (__START_KERNEL_map + KERNEL_IMAGE_SIZE) /* The module sections ends with the start of the fixmap */ diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 356308c73951..67c9d73b31fa 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -587,9 +587,6 @@ static inline void load_sp0(unsigned long sp0) #endif /* CONFIG_PARAVIRT_XXL */ -/* Free all resources held by a thread. */ -extern void release_thread(struct task_struct *); - unsigned long __get_wchan(struct task_struct *p); /* diff --git a/arch/x86/include/asm/qspinlock_paravirt.h b/arch/x86/include/asm/qspinlock_paravirt.h index 892fd8c3a6f7..dbb38a6b4dfb 100644 --- a/arch/x86/include/asm/qspinlock_paravirt.h +++ b/arch/x86/include/asm/qspinlock_paravirt.h @@ -12,7 +12,7 @@ */ #ifdef CONFIG_64BIT -PV_CALLEE_SAVE_REGS_THUNK(__pv_queued_spin_unlock_slowpath); +__PV_CALLEE_SAVE_REGS_THUNK(__pv_queued_spin_unlock_slowpath, ".spinlock.text"); #define __pv_queued_spin_unlock __pv_queued_spin_unlock #define PV_UNLOCK "__raw_callee_save___pv_queued_spin_unlock" #define PV_UNLOCK_SLOWPATH "__raw_callee_save___pv_queued_spin_unlock_slowpath" @@ -20,9 +20,10 @@ PV_CALLEE_SAVE_REGS_THUNK(__pv_queued_spin_unlock_slowpath); /* * Optimized assembly version of __raw_callee_save___pv_queued_spin_unlock * which combines the registers saving trunk and the body of the following - * C code: + * C code. Note that it puts the code in the .spinlock.text section which + * is equivalent to adding __lockfunc in the C code: * - * void __pv_queued_spin_unlock(struct qspinlock *lock) + * void __lockfunc __pv_queued_spin_unlock(struct qspinlock *lock) * { * u8 lockval = cmpxchg(&lock->locked, _Q_LOCKED_VAL, 0); * @@ -36,7 +37,7 @@ PV_CALLEE_SAVE_REGS_THUNK(__pv_queued_spin_unlock_slowpath); * rsi = lockval (second argument) * rdx = internal variable (set to 0) */ -asm (".pushsection .text;" +asm (".pushsection .spinlock.text, \"ax\";" ".globl " PV_UNLOCK ";" ".type " PV_UNLOCK ", @function;" ".align 4,0x90;" @@ -65,8 +66,8 @@ asm (".pushsection .text;" #else /* CONFIG_64BIT */ -extern void __pv_queued_spin_unlock(struct qspinlock *lock); -PV_CALLEE_SAVE_REGS_THUNK(__pv_queued_spin_unlock); +extern void __lockfunc __pv_queued_spin_unlock(struct qspinlock *lock); +__PV_CALLEE_SAVE_REGS_THUNK(__pv_queued_spin_unlock, ".spinlock.text"); #endif /* CONFIG_64BIT */ #endif diff --git a/arch/x86/include/asm/resctrl.h b/arch/x86/include/asm/resctrl.h index d60ed0668a59..d24b04ebf950 100644 --- a/arch/x86/include/asm/resctrl.h +++ b/arch/x86/include/asm/resctrl.h @@ -81,6 +81,15 @@ static void __resctrl_sched_in(void) } } +static inline unsigned int resctrl_arch_round_mon_val(unsigned int val) +{ + unsigned int scale = boot_cpu_data.x86_cache_occ_scale; + + /* h/w works in units of "boot_cpu_data.x86_cache_occ_scale" */ + val /= scale; + return val * scale; +} + static inline void resctrl_sched_in(void) { if (static_branch_likely(&rdt_enable_key)) diff --git a/arch/x86/include/asm/rmwcc.h b/arch/x86/include/asm/rmwcc.h index 8a9eba191516..7fa611216417 100644 --- a/arch/x86/include/asm/rmwcc.h +++ b/arch/x86/include/asm/rmwcc.h @@ -11,7 +11,7 @@ #define __CLOBBERS_MEM(clb...) "memory", ## clb -#if !defined(__GCC_ASM_FLAG_OUTPUTS__) && defined(CONFIG_CC_HAS_ASM_GOTO) +#ifndef __GCC_ASM_FLAG_OUTPUTS__ /* Use asm goto */ @@ -27,7 +27,7 @@ cc_label: c = true; \ c; \ }) -#else /* defined(__GCC_ASM_FLAG_OUTPUTS__) || !defined(CONFIG_CC_HAS_ASM_GOTO) */ +#else /* defined(__GCC_ASM_FLAG_OUTPUTS__) */ /* Use flags output or a set instruction */ @@ -40,7 +40,7 @@ cc_label: c = true; \ c; \ }) -#endif /* defined(__GCC_ASM_FLAG_OUTPUTS__) || !defined(CONFIG_CC_HAS_ASM_GOTO) */ +#endif /* defined(__GCC_ASM_FLAG_OUTPUTS__) */ #define GEN_UNARY_RMWcc_4(op, var, cc, arg0) \ __GEN_RMWcc(op " " arg0, var, cc, __CLOBBERS_MEM()) diff --git a/arch/x86/include/asm/sev.h b/arch/x86/include/asm/sev.h index 4a23e52fe0ee..ebc271bb6d8e 100644 --- a/arch/x86/include/asm/sev.h +++ b/arch/x86/include/asm/sev.h @@ -195,7 +195,7 @@ void snp_set_memory_shared(unsigned long vaddr, unsigned int npages); void snp_set_memory_private(unsigned long vaddr, unsigned int npages); void snp_set_wakeup_secondary_cpu(void); bool snp_init(struct boot_params *bp); -void snp_abort(void); +void __init __noreturn snp_abort(void); int snp_issue_guest_request(u64 exit_code, struct snp_req_data *input, unsigned long *fw_err); #else static inline void sev_es_ist_enter(struct pt_regs *regs) { } diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h index 81a0211a372d..a73bced40e24 100644 --- a/arch/x86/include/asm/smp.h +++ b/arch/x86/include/asm/smp.h @@ -21,16 +21,6 @@ DECLARE_PER_CPU_READ_MOSTLY(u16, cpu_llc_id); DECLARE_PER_CPU_READ_MOSTLY(u16, cpu_l2c_id); DECLARE_PER_CPU_READ_MOSTLY(int, cpu_number); -static inline struct cpumask *cpu_llc_shared_mask(int cpu) -{ - return per_cpu(cpu_llc_shared_map, cpu); -} - -static inline struct cpumask *cpu_l2c_shared_mask(int cpu) -{ - return per_cpu(cpu_l2c_shared_map, cpu); -} - DECLARE_EARLY_PER_CPU_READ_MOSTLY(u16, x86_cpu_to_apicid); DECLARE_EARLY_PER_CPU_READ_MOSTLY(u32, x86_cpu_to_acpiid); DECLARE_EARLY_PER_CPU_READ_MOSTLY(u16, x86_bios_cpu_apicid); @@ -172,6 +162,16 @@ extern int safe_smp_processor_id(void); # define safe_smp_processor_id() smp_processor_id() #endif +static inline struct cpumask *cpu_llc_shared_mask(int cpu) +{ + return per_cpu(cpu_llc_shared_map, cpu); +} + +static inline struct cpumask *cpu_l2c_shared_mask(int cpu) +{ + return per_cpu(cpu_l2c_shared_map, cpu); +} + #else /* !CONFIG_SMP */ #define wbinvd_on_cpu(cpu) wbinvd() static inline int wbinvd_on_all_cpus(void) @@ -179,6 +179,11 @@ static inline int wbinvd_on_all_cpus(void) wbinvd(); return 0; } + +static inline struct cpumask *cpu_llc_shared_mask(int cpu) +{ + return (struct cpumask *)cpumask_of(0); +} #endif /* CONFIG_SMP */ extern unsigned disabled_cpus; diff --git a/arch/x86/include/asm/sparsemem.h b/arch/x86/include/asm/sparsemem.h index 6a9ccc1b2be5..64df897c0ee3 100644 --- a/arch/x86/include/asm/sparsemem.h +++ b/arch/x86/include/asm/sparsemem.h @@ -2,6 +2,8 @@ #ifndef _ASM_X86_SPARSEMEM_H #define _ASM_X86_SPARSEMEM_H +#include <linux/types.h> + #ifdef CONFIG_SPARSEMEM /* * generic non-linear memory support: diff --git a/arch/x86/include/asm/spec-ctrl.h b/arch/x86/include/asm/spec-ctrl.h index 5393babc0598..cb0386fc4dc3 100644 --- a/arch/x86/include/asm/spec-ctrl.h +++ b/arch/x86/include/asm/spec-ctrl.h @@ -13,7 +13,7 @@ * Takes the guest view of SPEC_CTRL MSR as a parameter and also * the guest's version of VIRT_SPEC_CTRL, if emulated. */ -extern void x86_virt_spec_ctrl(u64 guest_spec_ctrl, u64 guest_virt_spec_ctrl, bool guest); +extern void x86_virt_spec_ctrl(u64 guest_virt_spec_ctrl, bool guest); /** * x86_spec_ctrl_set_guest - Set speculation control registers for the guest @@ -24,9 +24,9 @@ extern void x86_virt_spec_ctrl(u64 guest_spec_ctrl, u64 guest_virt_spec_ctrl, bo * Avoids writing to the MSR if the content/bits are the same */ static inline -void x86_spec_ctrl_set_guest(u64 guest_spec_ctrl, u64 guest_virt_spec_ctrl) +void x86_spec_ctrl_set_guest(u64 guest_virt_spec_ctrl) { - x86_virt_spec_ctrl(guest_spec_ctrl, guest_virt_spec_ctrl, true); + x86_virt_spec_ctrl(guest_virt_spec_ctrl, true); } /** @@ -38,9 +38,9 @@ void x86_spec_ctrl_set_guest(u64 guest_spec_ctrl, u64 guest_virt_spec_ctrl) * Avoids writing to the MSR if the content/bits are the same */ static inline -void x86_spec_ctrl_restore_host(u64 guest_spec_ctrl, u64 guest_virt_spec_ctrl) +void x86_spec_ctrl_restore_host(u64 guest_virt_spec_ctrl) { - x86_virt_spec_ctrl(guest_spec_ctrl, guest_virt_spec_ctrl, false); + x86_virt_spec_ctrl(guest_virt_spec_ctrl, false); } /* AMD specific Speculative Store Bypass MSR data */ diff --git a/arch/x86/include/asm/string_64.h b/arch/x86/include/asm/string_64.h index 6e450827f677..888731ccf1f6 100644 --- a/arch/x86/include/asm/string_64.h +++ b/arch/x86/include/asm/string_64.h @@ -10,12 +10,27 @@ /* Even with __builtin_ the compiler may decide to use the out of line function. */ +#if defined(__SANITIZE_MEMORY__) && defined(__NO_FORTIFY) +#include <linux/kmsan_string.h> +#endif + #define __HAVE_ARCH_MEMCPY 1 +#if defined(__SANITIZE_MEMORY__) && defined(__NO_FORTIFY) +#undef memcpy +#define memcpy __msan_memcpy +#else extern void *memcpy(void *to, const void *from, size_t len); +#endif extern void *__memcpy(void *to, const void *from, size_t len); #define __HAVE_ARCH_MEMSET +#if defined(__SANITIZE_MEMORY__) && defined(__NO_FORTIFY) +extern void *__msan_memset(void *s, int c, size_t n); +#undef memset +#define memset __msan_memset +#else void *memset(void *s, int c, size_t n); +#endif void *__memset(void *s, int c, size_t n); #define __HAVE_ARCH_MEMSET16 @@ -55,7 +70,13 @@ static inline void *memset64(uint64_t *s, uint64_t v, size_t n) } #define __HAVE_ARCH_MEMMOVE +#if defined(__SANITIZE_MEMORY__) && defined(__NO_FORTIFY) +#undef memmove +void *__msan_memmove(void *dest, const void *src, size_t len); +#define memmove __msan_memmove +#else void *memmove(void *dest, const void *src, size_t count); +#endif void *__memmove(void *dest, const void *src, size_t count); int memcmp(const void *cs, const void *ct, size_t count); @@ -64,8 +85,7 @@ char *strcpy(char *dest, const char *src); char *strcat(char *dest, const char *src); int strcmp(const char *cs, const char *ct); -#if defined(CONFIG_KASAN) && !defined(__SANITIZE_ADDRESS__) - +#if (defined(CONFIG_KASAN) && !defined(__SANITIZE_ADDRESS__)) /* * For files that not instrumented (e.g. mm/slub.c) we * should use not instrumented version of mem* functions. @@ -73,7 +93,9 @@ int strcmp(const char *cs, const char *ct); #undef memcpy #define memcpy(dst, src, len) __memcpy(dst, src, len) +#undef memmove #define memmove(dst, src, len) __memmove(dst, src, len) +#undef memset #define memset(s, c, n) __memset(s, c, n) #ifndef __NO_FORTIFY diff --git a/arch/x86/include/asm/syscall_wrapper.h b/arch/x86/include/asm/syscall_wrapper.h index 59358d1bf880..fd2669b1cb2d 100644 --- a/arch/x86/include/asm/syscall_wrapper.h +++ b/arch/x86/include/asm/syscall_wrapper.h @@ -6,7 +6,7 @@ #ifndef _ASM_X86_SYSCALL_WRAPPER_H #define _ASM_X86_SYSCALL_WRAPPER_H -struct pt_regs; +#include <asm/ptrace.h> extern long __x64_sys_ni_syscall(const struct pt_regs *regs); extern long __ia32_sys_ni_syscall(const struct pt_regs *regs); diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h index 913e593a3b45..1cc756eafa44 100644 --- a/arch/x86/include/asm/uaccess.h +++ b/arch/x86/include/asm/uaccess.h @@ -5,6 +5,7 @@ * User space memory access functions */ #include <linux/compiler.h> +#include <linux/instrumented.h> #include <linux/kasan-checks.h> #include <linux/string.h> #include <asm/asm.h> @@ -103,6 +104,7 @@ extern int __get_user_bad(void); : "=a" (__ret_gu), "=r" (__val_gu), \ ASM_CALL_CONSTRAINT \ : "0" (ptr), "i" (sizeof(*(ptr)))); \ + instrument_get_user(__val_gu); \ (x) = (__force __typeof__(*(ptr))) __val_gu; \ __builtin_expect(__ret_gu, 0); \ }) @@ -192,9 +194,11 @@ extern void __put_user_nocheck_8(void); int __ret_pu; \ void __user *__ptr_pu; \ register __typeof__(*(ptr)) __val_pu asm("%"_ASM_AX); \ - __chk_user_ptr(ptr); \ - __ptr_pu = (ptr); \ - __val_pu = (x); \ + __typeof__(*(ptr)) __x = (x); /* eval x once */ \ + __typeof__(ptr) __ptr = (ptr); /* eval ptr once */ \ + __chk_user_ptr(__ptr); \ + __ptr_pu = __ptr; \ + __val_pu = __x; \ asm volatile("call __" #fn "_%P[size]" \ : "=c" (__ret_pu), \ ASM_CALL_CONSTRAINT \ @@ -202,6 +206,7 @@ extern void __put_user_nocheck_8(void); "r" (__val_pu), \ [size] "i" (sizeof(*(ptr))) \ :"ebx"); \ + instrument_put_user(__x, __ptr, sizeof(*(ptr))); \ __builtin_expect(__ret_pu, 0); \ }) @@ -248,23 +253,26 @@ extern void __put_user_nocheck_8(void); #define __put_user_size(x, ptr, size, label) \ do { \ - __chk_user_ptr(ptr); \ + __typeof__(*(ptr)) __x = (x); /* eval x once */ \ + __typeof__(ptr) __ptr = (ptr); /* eval ptr once */ \ + __chk_user_ptr(__ptr); \ switch (size) { \ case 1: \ - __put_user_goto(x, ptr, "b", "iq", label); \ + __put_user_goto(__x, __ptr, "b", "iq", label); \ break; \ case 2: \ - __put_user_goto(x, ptr, "w", "ir", label); \ + __put_user_goto(__x, __ptr, "w", "ir", label); \ break; \ case 4: \ - __put_user_goto(x, ptr, "l", "ir", label); \ + __put_user_goto(__x, __ptr, "l", "ir", label); \ break; \ case 8: \ - __put_user_goto_u64(x, ptr, label); \ + __put_user_goto_u64(__x, __ptr, label); \ break; \ default: \ __put_user_bad(); \ } \ + instrument_put_user(__x, __ptr, size); \ } while (0) #ifdef CONFIG_CC_HAS_ASM_GOTO_OUTPUT @@ -305,6 +313,7 @@ do { \ default: \ (x) = __get_user_bad(); \ } \ + instrument_get_user(x); \ } while (0) #define __get_user_asm(x, addr, itype, ltype, label) \ @@ -448,7 +457,7 @@ do { \ #ifdef CONFIG_X86_32 /* - * Unlike the normal CMPXCHG, hardcode ECX for both success/fail and error. + * Unlike the normal CMPXCHG, use output GPR for both success/fail and error. * There are only six GPRs available and four (EAX, EBX, ECX, and EDX) are * hardcoded by CMPXCHG8B, leaving only ESI and EDI. If the compiler uses * both ESI and EDI for the memory operand, compilation will fail if the error @@ -461,11 +470,12 @@ do { \ __typeof__(*(_ptr)) __new = (_new); \ asm volatile("\n" \ "1: " LOCK_PREFIX "cmpxchg8b %[ptr]\n" \ - "mov $0, %%ecx\n\t" \ - "setz %%cl\n" \ + "mov $0, %[result]\n\t" \ + "setz %b[result]\n" \ "2:\n" \ - _ASM_EXTABLE_TYPE_REG(1b, 2b, EX_TYPE_EFAULT_REG, %%ecx) \ - : [result]"=c" (__result), \ + _ASM_EXTABLE_TYPE_REG(1b, 2b, EX_TYPE_EFAULT_REG, \ + %[result]) \ + : [result] "=q" (__result), \ "+A" (__old), \ [ptr] "+m" (*_ptr) \ : "b" ((u32)__new), \ @@ -502,9 +512,6 @@ strncpy_from_user(char *dst, const char __user *src, long count); extern __must_check long strnlen_user(const char __user *str, long n); -unsigned long __must_check clear_user(void __user *mem, unsigned long len); -unsigned long __must_check __clear_user(void __user *mem, unsigned long len); - #ifdef CONFIG_ARCH_HAS_COPY_MC unsigned long __must_check copy_mc_to_kernel(void *to, const void *from, unsigned len); @@ -526,6 +533,8 @@ extern struct movsl_mask { #define ARCH_HAS_NOCACHE_UACCESS 1 #ifdef CONFIG_X86_32 +unsigned long __must_check clear_user(void __user *mem, unsigned long len); +unsigned long __must_check __clear_user(void __user *mem, unsigned long len); # include <asm/uaccess_32.h> #else # include <asm/uaccess_64.h> diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h index 45697e04d771..d13d71af5cf6 100644 --- a/arch/x86/include/asm/uaccess_64.h +++ b/arch/x86/include/asm/uaccess_64.h @@ -79,4 +79,49 @@ __copy_from_user_flushcache(void *dst, const void __user *src, unsigned size) kasan_check_write(dst, size); return __copy_user_flushcache(dst, src, size); } + +/* + * Zero Userspace. + */ + +__must_check unsigned long +clear_user_original(void __user *addr, unsigned long len); +__must_check unsigned long +clear_user_rep_good(void __user *addr, unsigned long len); +__must_check unsigned long +clear_user_erms(void __user *addr, unsigned long len); + +static __always_inline __must_check unsigned long __clear_user(void __user *addr, unsigned long size) +{ + might_fault(); + stac(); + + /* + * No memory constraint because it doesn't change any memory gcc + * knows about. + */ + asm volatile( + "1:\n\t" + ALTERNATIVE_3("rep stosb", + "call clear_user_erms", ALT_NOT(X86_FEATURE_FSRM), + "call clear_user_rep_good", ALT_NOT(X86_FEATURE_ERMS), + "call clear_user_original", ALT_NOT(X86_FEATURE_REP_GOOD)) + "2:\n" + _ASM_EXTABLE_UA(1b, 2b) + : "+c" (size), "+D" (addr), ASM_CALL_CONSTRAINT + : "a" (0) + /* rep_good clobbers %rdx */ + : "rdx"); + + clac(); + + return size; +} + +static __always_inline unsigned long clear_user(void __user *to, unsigned long n) +{ + if (access_ok(to, n)) + return __clear_user(to, n); + return n; +} #endif /* _ASM_X86_UACCESS_64_H */ diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h index c371ef695fcc..498dc600bd5c 100644 --- a/arch/x86/include/asm/vmx.h +++ b/arch/x86/include/asm/vmx.h @@ -309,7 +309,7 @@ enum vmcs_field { GUEST_LDTR_AR_BYTES = 0x00004820, GUEST_TR_AR_BYTES = 0x00004822, GUEST_INTERRUPTIBILITY_INFO = 0x00004824, - GUEST_ACTIVITY_STATE = 0X00004826, + GUEST_ACTIVITY_STATE = 0x00004826, GUEST_SYSENTER_CS = 0x0000482A, VMX_PREEMPTION_TIMER_VALUE = 0x0000482E, HOST_IA32_SYSENTER_CS = 0x00004c00, diff --git a/arch/x86/include/asm/word-at-a-time.h b/arch/x86/include/asm/word-at-a-time.h index 8338b0432b50..46b4f1f7f354 100644 --- a/arch/x86/include/asm/word-at-a-time.h +++ b/arch/x86/include/asm/word-at-a-time.h @@ -77,58 +77,18 @@ static inline unsigned long find_zero(unsigned long mask) * and the next page not being mapped, take the exception and * return zeroes in the non-existing part. */ -#ifdef CONFIG_CC_HAS_ASM_GOTO_OUTPUT - static inline unsigned long load_unaligned_zeropad(const void *addr) { - unsigned long offset, data; unsigned long ret; - asm_volatile_goto( + asm volatile( "1: mov %[mem], %[ret]\n" - - _ASM_EXTABLE(1b, %l[do_exception]) - - : [ret] "=r" (ret) - : [mem] "m" (*(unsigned long *)addr) - : : do_exception); - - return ret; - -do_exception: - offset = (unsigned long)addr & (sizeof(long) - 1); - addr = (void *)((unsigned long)addr & ~(sizeof(long) - 1)); - data = *(unsigned long *)addr; - ret = data >> offset * 8; - - return ret; -} - -#else /* !CONFIG_CC_HAS_ASM_GOTO_OUTPUT */ - -static inline unsigned long load_unaligned_zeropad(const void *addr) -{ - unsigned long offset, data; - unsigned long ret, err = 0; - - asm( "1: mov %[mem], %[ret]\n" "2:\n" - - _ASM_EXTABLE_FAULT(1b, 2b) - - : [ret] "=&r" (ret), "+a" (err) + _ASM_EXTABLE_TYPE(1b, 2b, EX_TYPE_ZEROPAD) + : [ret] "=r" (ret) : [mem] "m" (*(unsigned long *)addr)); - if (unlikely(err)) { - offset = (unsigned long)addr & (sizeof(long) - 1); - addr = (void *)((unsigned long)addr & ~(sizeof(long) - 1)); - data = *(unsigned long *)addr; - ret = data >> offset * 8; - } - return ret; } -#endif /* CONFIG_CC_HAS_ASM_GOTO_OUTPUT */ - #endif /* _ASM_WORD_AT_A_TIME_H */ diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index a20a5ebfacd7..f901658d9f7c 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -3,10 +3,6 @@ # Makefile for the linux kernel. # -extra-y := head_$(BITS).o -extra-y += head$(BITS).o -extra-y += ebda.o -extra-y += platform-quirks.o extra-y += vmlinux.lds CPPFLAGS_vmlinux.lds += -U$(UTS_MACHINE) @@ -33,6 +29,8 @@ KASAN_SANITIZE_sev.o := n # With some compiler versions the generated code results in boot hangs, caused # by several compilation units. To be safe, disable all instrumentation. KCSAN_SANITIZE := n +KMSAN_SANITIZE_head$(BITS).o := n +KMSAN_SANITIZE_nmi.o := n # If instrumentation of this dir is enabled, boot hangs during first second. # Probably could be more selective here, but note that files related to irqs, @@ -42,7 +40,11 @@ KCOV_INSTRUMENT := n CFLAGS_irq.o := -I $(srctree)/$(src)/../include/asm/trace -obj-y := process_$(BITS).o signal.o +obj-y += head_$(BITS).o +obj-y += head$(BITS).o +obj-y += ebda.o +obj-y += platform-quirks.o +obj-y += process_$(BITS).o signal.o obj-$(CONFIG_COMPAT) += signal_compat.o obj-y += traps.o idt.o irq.o irq_$(BITS).o dumpstack_$(BITS).o obj-y += time.o ioport.o dumpstack.o nmi.o @@ -139,6 +141,8 @@ obj-$(CONFIG_UNWINDER_GUESS) += unwind_guess.o obj-$(CONFIG_AMD_MEM_ENCRYPT) += sev.o +obj-$(CONFIG_CFI_CLANG) += cfi.o + ### # 64 bit specific files ifeq ($(CONFIG_X86_64),y) diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 62f6b8b7c4a5..5cadcea035e0 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -453,6 +453,15 @@ static int patch_retpoline(void *addr, struct insn *insn, u8 *bytes) return ret; i += ret; + /* + * The compiler is supposed to EMIT an INT3 after every unconditional + * JMP instruction due to AMD BTC. However, if the compiler is too old + * or SLS isn't enabled, we still need an INT3 after indirect JMPs + * even on Intel. + */ + if (op == JMP32_INSN_OPCODE && i < insn->length) + bytes[i++] = INT3_INSN_OPCODE; + for (; i < insn->length;) bytes[i++] = BYTES_NOP1; @@ -1319,22 +1328,23 @@ struct bp_patching_desc { atomic_t refs; }; -static struct bp_patching_desc *bp_desc; +static struct bp_patching_desc bp_desc; static __always_inline -struct bp_patching_desc *try_get_desc(struct bp_patching_desc **descp) +struct bp_patching_desc *try_get_desc(void) { - /* rcu_dereference */ - struct bp_patching_desc *desc = __READ_ONCE(*descp); + struct bp_patching_desc *desc = &bp_desc; - if (!desc || !arch_atomic_inc_not_zero(&desc->refs)) + if (!arch_atomic_inc_not_zero(&desc->refs)) return NULL; return desc; } -static __always_inline void put_desc(struct bp_patching_desc *desc) +static __always_inline void put_desc(void) { + struct bp_patching_desc *desc = &bp_desc; + smp_mb__before_atomic(); arch_atomic_dec(&desc->refs); } @@ -1367,15 +1377,15 @@ noinstr int poke_int3_handler(struct pt_regs *regs) /* * Having observed our INT3 instruction, we now must observe - * bp_desc: + * bp_desc with non-zero refcount: * - * bp_desc = desc INT3 + * bp_desc.refs = 1 INT3 * WMB RMB - * write INT3 if (desc) + * write INT3 if (bp_desc.refs != 0) */ smp_rmb(); - desc = try_get_desc(&bp_desc); + desc = try_get_desc(); if (!desc) return 0; @@ -1429,7 +1439,7 @@ noinstr int poke_int3_handler(struct pt_regs *regs) ret = 1; out_put: - put_desc(desc); + put_desc(); return ret; } @@ -1460,18 +1470,20 @@ static int tp_vec_nr; */ static void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries) { - struct bp_patching_desc desc = { - .vec = tp, - .nr_entries = nr_entries, - .refs = ATOMIC_INIT(1), - }; unsigned char int3 = INT3_INSN_OPCODE; unsigned int i; int do_sync; lockdep_assert_held(&text_mutex); - smp_store_release(&bp_desc, &desc); /* rcu_assign_pointer */ + bp_desc.vec = tp; + bp_desc.nr_entries = nr_entries; + + /* + * Corresponds to the implicit memory barrier in try_get_desc() to + * ensure reading a non-zero refcount provides up to date bp_desc data. + */ + atomic_set_release(&bp_desc.refs, 1); /* * Corresponding read barrier in int3 notifier for making sure the @@ -1559,12 +1571,10 @@ static void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries text_poke_sync(); /* - * Remove and synchronize_rcu(), except we have a very primitive - * refcount based completion. + * Remove and wait for refs to be zero. */ - WRITE_ONCE(bp_desc, NULL); /* RCU_INIT_POINTER */ - if (!atomic_dec_and_test(&desc.refs)) - atomic_cond_read_acquire(&desc.refs, !VAL); + if (!atomic_dec_and_test(&bp_desc.refs)) + atomic_cond_read_acquire(&bp_desc.refs, !VAL); } static void text_poke_loc_init(struct text_poke_loc *tp, void *addr, diff --git a/arch/x86/kernel/amd_gart_64.c b/arch/x86/kernel/amd_gart_64.c index 194d54eed537..19a0207e529f 100644 --- a/arch/x86/kernel/amd_gart_64.c +++ b/arch/x86/kernel/amd_gart_64.c @@ -53,7 +53,7 @@ static u32 *iommu_gatt_base; /* Remapping table */ * of only flushing when an mapping is reused. With it true the GART is * flushed for every mapping. Problem is that doing the lazy flush seems * to trigger bugs with some popular PCI cards, in particular 3ware (but - * has been also also seen with Qlogic at least). + * has been also seen with Qlogic at least). */ static int iommu_fullflush = 1; diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c index 7a5630d904b2..4feaa670d578 100644 --- a/arch/x86/kernel/aperture_64.c +++ b/arch/x86/kernel/aperture_64.c @@ -36,7 +36,7 @@ /* * Using 512M as goal, in case kexec will load kernel_big * that will do the on-position decompress, and could overlap with - * with the gart aperture that is used. + * the gart aperture that is used. * Sequence: * kernel_small * ==> kexec (with kdump trigger path or gart still enabled) diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 6d303d1d276c..c6876d3ea4b1 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -61,6 +61,7 @@ #include <asm/cpu_device_id.h> #include <asm/intel-family.h> #include <asm/irq_regs.h> +#include <asm/cpu.h> unsigned int num_processors; @@ -1751,11 +1752,26 @@ EXPORT_SYMBOL_GPL(x2apic_mode); enum { X2APIC_OFF, - X2APIC_ON, X2APIC_DISABLED, + /* All states below here have X2APIC enabled */ + X2APIC_ON, + X2APIC_ON_LOCKED }; static int x2apic_state; +static bool x2apic_hw_locked(void) +{ + u64 ia32_cap; + u64 msr; + + ia32_cap = x86_read_arch_cap_msr(); + if (ia32_cap & ARCH_CAP_XAPIC_DISABLE) { + rdmsrl(MSR_IA32_XAPIC_DISABLE_STATUS, msr); + return (msr & LEGACY_XAPIC_DISABLED); + } + return false; +} + static void __x2apic_disable(void) { u64 msr; @@ -1793,6 +1809,10 @@ static int __init setup_nox2apic(char *str) apicid); return 0; } + if (x2apic_hw_locked()) { + pr_warn("APIC locked in x2apic mode, can't disable\n"); + return 0; + } pr_warn("x2apic already enabled.\n"); __x2apic_disable(); } @@ -1807,10 +1827,18 @@ early_param("nox2apic", setup_nox2apic); void x2apic_setup(void) { /* - * If x2apic is not in ON state, disable it if already enabled + * Try to make the AP's APIC state match that of the BSP, but if the + * BSP is unlocked and the AP is locked then there is a state mismatch. + * Warn about the mismatch in case a GP fault occurs due to a locked AP + * trying to be turned off. + */ + if (x2apic_state != X2APIC_ON_LOCKED && x2apic_hw_locked()) + pr_warn("x2apic lock mismatch between BSP and AP.\n"); + /* + * If x2apic is not in ON or LOCKED state, disable it if already enabled * from BIOS. */ - if (x2apic_state != X2APIC_ON) { + if (x2apic_state < X2APIC_ON) { __x2apic_disable(); return; } @@ -1831,6 +1859,11 @@ static __init void x2apic_disable(void) if (x2apic_id >= 255) panic("Cannot disable x2apic, id: %08x\n", x2apic_id); + if (x2apic_hw_locked()) { + pr_warn("Cannot disable locked x2apic, id: %08x\n", x2apic_id); + return; + } + __x2apic_disable(); register_lapic_address(mp_lapic_addr); } @@ -1889,7 +1922,10 @@ void __init check_x2apic(void) if (x2apic_enabled()) { pr_info("x2apic: enabled by BIOS, switching to x2apic ops\n"); x2apic_mode = 1; - x2apic_state = X2APIC_ON; + if (x2apic_hw_locked()) + x2apic_state = X2APIC_ON_LOCKED; + else + x2apic_state = X2APIC_ON; } else if (!boot_cpu_has(X86_FEATURE_X2APIC)) { x2apic_state = X2APIC_DISABLED; } diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c index cb50589a7102..437308004ef2 100644 --- a/arch/x86/kernel/asm-offsets.c +++ b/arch/x86/kernel/asm-offsets.c @@ -19,7 +19,6 @@ #include <asm/suspend.h> #include <asm/tlbflush.h> #include <asm/tdx.h> -#include "../kvm/vmx/vmx.h" #ifdef CONFIG_XEN #include <xen/interface/xen.h> @@ -108,9 +107,4 @@ static void __used common(void) OFFSET(TSS_sp0, tss_struct, x86_tss.sp0); OFFSET(TSS_sp1, tss_struct, x86_tss.sp1); OFFSET(TSS_sp2, tss_struct, x86_tss.sp2); - - if (IS_ENABLED(CONFIG_KVM_INTEL)) { - BLANK(); - OFFSET(VMX_spec_ctrl, vcpu_vmx, spec_ctrl); - } } diff --git a/arch/x86/kernel/cfi.c b/arch/x86/kernel/cfi.c new file mode 100644 index 000000000000..8674a5c0c031 --- /dev/null +++ b/arch/x86/kernel/cfi.c @@ -0,0 +1,86 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Clang Control Flow Integrity (CFI) support. + * + * Copyright (C) 2022 Google LLC + */ +#include <asm/cfi.h> +#include <asm/insn.h> +#include <asm/insn-eval.h> +#include <linux/string.h> + +/* + * Returns the target address and the expected type when regs->ip points + * to a compiler-generated CFI trap. + */ +static bool decode_cfi_insn(struct pt_regs *regs, unsigned long *target, + u32 *type) +{ + char buffer[MAX_INSN_SIZE]; + struct insn insn; + int offset = 0; + + *target = *type = 0; + + /* + * The compiler generates the following instruction sequence + * for indirect call checks: + * + * Â movl -<id>, %r10d ; 6 bytes + * addl -4(%reg), %r10d ; 4 bytes + * je .Ltmp1 ; 2 bytes + * ud2 ; <- regs->ip + * .Ltmp1: + * + * We can decode the expected type and the target address from the + * movl/addl instructions. + */ + if (copy_from_kernel_nofault(buffer, (void *)regs->ip - 12, MAX_INSN_SIZE)) + return false; + if (insn_decode_kernel(&insn, &buffer[offset])) + return false; + if (insn.opcode.value != 0xBA) + return false; + + *type = -(u32)insn.immediate.value; + + if (copy_from_kernel_nofault(buffer, (void *)regs->ip - 6, MAX_INSN_SIZE)) + return false; + if (insn_decode_kernel(&insn, &buffer[offset])) + return false; + if (insn.opcode.value != 0x3) + return false; + + /* Read the target address from the register. */ + offset = insn_get_modrm_rm_off(&insn, regs); + if (offset < 0) + return false; + + *target = *(unsigned long *)((void *)regs + offset); + + return true; +} + +/* + * Checks if a ud2 trap is because of a CFI failure, and handles the trap + * if needed. Returns a bug_trap_type value similarly to report_bug. + */ +enum bug_trap_type handle_cfi_failure(struct pt_regs *regs) +{ + unsigned long target; + u32 type; + + if (!is_cfi_trap(regs->ip)) + return BUG_TRAP_TYPE_NONE; + + if (!decode_cfi_insn(regs, &target, &type)) + return report_cfi_failure_noaddr(regs, regs->ip); + + return report_cfi_failure(regs, regs->ip, &target, type); +} + +/* + * Ensure that __kcfi_typeid_ symbols are emitted for functions that may + * not be indirectly called with all configurations. + */ +__ADDRESSABLE(__memcpy) diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile index 9661e3e802be..f10a921ee756 100644 --- a/arch/x86/kernel/cpu/Makefile +++ b/arch/x86/kernel/cpu/Makefile @@ -12,6 +12,7 @@ endif # If these files are instrumented, boot hangs during the first second. KCOV_INSTRUMENT_common.o := n KCOV_INSTRUMENT_perf_event.o := n +KMSAN_SANITIZE_common.o := n # As above, instrumenting secondary CPU boot code causes boot hangs. KCSAN_SANITIZE_common.o := n diff --git a/arch/x86/kernel/cpu/acrn.c b/arch/x86/kernel/cpu/acrn.c index 23f5f27b5a02..485441b7f030 100644 --- a/arch/x86/kernel/cpu/acrn.c +++ b/arch/x86/kernel/cpu/acrn.c @@ -28,6 +28,9 @@ static void __init acrn_init_platform(void) { /* Setup the IDT for ACRN hypervisor callback */ alloc_intr_gate(HYPERVISOR_CALLBACK_VECTOR, asm_sysvec_acrn_hv_callback); + + x86_platform.calibrate_tsc = acrn_get_tsc_khz; + x86_platform.calibrate_cpu = acrn_get_tsc_khz; } static bool acrn_x2apic_available(void) diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 48276c0e479d..c75d75b9f11a 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -503,7 +503,7 @@ static void bsp_init_amd(struct cpuinfo_x86 *c) va_align.flags = ALIGN_VA_32 | ALIGN_VA_64; /* A random value per boot for bit slice [12:upper_bit) */ - va_align.bits = get_random_int() & va_align.mask; + va_align.bits = get_random_u32() & va_align.mask; } if (cpu_has(c, X86_FEATURE_MWAITX)) @@ -770,8 +770,6 @@ static void init_amd_gh(struct cpuinfo_x86 *c) set_cpu_bug(c, X86_BUG_AMD_TLB_MMATCH); } -#define MSR_AMD64_DE_CFG 0xC0011029 - static void init_amd_ln(struct cpuinfo_x86 *c) { /* @@ -965,8 +963,8 @@ static void init_amd(struct cpuinfo_x86 *c) * msr_set_bit() uses the safe accessors, too, even if the MSR * is not present. */ - msr_set_bit(MSR_F10H_DECFG, - MSR_F10H_DECFG_LFENCE_SERIALIZE_BIT); + msr_set_bit(MSR_AMD64_DE_CFG, + MSR_AMD64_DE_CFG_LFENCE_SERIALIZE_BIT); /* A serializing LFENCE stops RDTSC speculation */ set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC); diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 510d85261132..3e3230cccaa7 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -196,22 +196,15 @@ void __init check_bugs(void) } /* - * NOTE: This function is *only* called for SVM. VMX spec_ctrl handling is - * done in vmenter.S. + * NOTE: This function is *only* called for SVM, since Intel uses + * MSR_IA32_SPEC_CTRL for SSBD. */ void -x86_virt_spec_ctrl(u64 guest_spec_ctrl, u64 guest_virt_spec_ctrl, bool setguest) +x86_virt_spec_ctrl(u64 guest_virt_spec_ctrl, bool setguest) { - u64 msrval, guestval = guest_spec_ctrl, hostval = spec_ctrl_current(); + u64 guestval, hostval; struct thread_info *ti = current_thread_info(); - if (static_cpu_has(X86_FEATURE_MSR_SPEC_CTRL)) { - if (hostval != guestval) { - msrval = setguest ? guestval : hostval; - wrmsrl(MSR_IA32_SPEC_CTRL, msrval); - } - } - /* * If SSBD is not handled in MSR_SPEC_CTRL on AMD, update * MSR_AMD64_L2_CFG or MSR_VIRT_SPEC_CTRL if supported. @@ -433,7 +426,8 @@ static void __init mmio_select_mitigation(void) u64 ia32_cap; if (!boot_cpu_has_bug(X86_BUG_MMIO_STALE_DATA) || - cpu_mitigations_off()) { + boot_cpu_has_bug(X86_BUG_MMIO_UNKNOWN) || + cpu_mitigations_off()) { mmio_mitigation = MMIO_MITIGATION_OFF; return; } @@ -538,6 +532,8 @@ out: pr_info("TAA: %s\n", taa_strings[taa_mitigation]); if (boot_cpu_has_bug(X86_BUG_MMIO_STALE_DATA)) pr_info("MMIO Stale Data: %s\n", mmio_strings[mmio_mitigation]); + else if (boot_cpu_has_bug(X86_BUG_MMIO_UNKNOWN)) + pr_info("MMIO Stale Data: Unknown: No mitigations\n"); } static void __init md_clear_select_mitigation(void) @@ -2275,6 +2271,9 @@ static ssize_t tsx_async_abort_show_state(char *buf) static ssize_t mmio_stale_data_show_state(char *buf) { + if (boot_cpu_has_bug(X86_BUG_MMIO_UNKNOWN)) + return sysfs_emit(buf, "Unknown: No mitigations\n"); + if (mmio_mitigation == MMIO_MITIGATION_OFF) return sysfs_emit(buf, "%s\n", mmio_strings[mmio_mitigation]); @@ -2421,6 +2420,7 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr return srbds_show_state(buf); case X86_BUG_MMIO_STALE_DATA: + case X86_BUG_MMIO_UNKNOWN: return mmio_stale_data_show_state(buf); case X86_BUG_RETBLEED: @@ -2480,7 +2480,10 @@ ssize_t cpu_show_srbds(struct device *dev, struct device_attribute *attr, char * ssize_t cpu_show_mmio_stale_data(struct device *dev, struct device_attribute *attr, char *buf) { - return cpu_show_common(dev, attr, buf, X86_BUG_MMIO_STALE_DATA); + if (boot_cpu_has_bug(X86_BUG_MMIO_UNKNOWN)) + return cpu_show_common(dev, attr, buf, X86_BUG_MMIO_UNKNOWN); + else + return cpu_show_common(dev, attr, buf, X86_BUG_MMIO_STALE_DATA); } ssize_t cpu_show_retbleed(struct device *dev, struct device_attribute *attr, char *buf) diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 64a73f415f03..3e508f239098 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1135,7 +1135,8 @@ static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c) #define NO_SWAPGS BIT(6) #define NO_ITLB_MULTIHIT BIT(7) #define NO_SPECTRE_V2 BIT(8) -#define NO_EIBRS_PBRSB BIT(9) +#define NO_MMIO BIT(9) +#define NO_EIBRS_PBRSB BIT(10) #define VULNWL(vendor, family, model, whitelist) \ X86_MATCH_VENDOR_FAM_MODEL(vendor, family, model, whitelist) @@ -1158,6 +1159,11 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = { VULNWL(VORTEX, 6, X86_MODEL_ANY, NO_SPECULATION), /* Intel Family 6 */ + VULNWL_INTEL(TIGERLAKE, NO_MMIO), + VULNWL_INTEL(TIGERLAKE_L, NO_MMIO), + VULNWL_INTEL(ALDERLAKE, NO_MMIO), + VULNWL_INTEL(ALDERLAKE_L, NO_MMIO), + VULNWL_INTEL(ATOM_SALTWELL, NO_SPECULATION | NO_ITLB_MULTIHIT), VULNWL_INTEL(ATOM_SALTWELL_TABLET, NO_SPECULATION | NO_ITLB_MULTIHIT), VULNWL_INTEL(ATOM_SALTWELL_MID, NO_SPECULATION | NO_ITLB_MULTIHIT), @@ -1176,9 +1182,9 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = { VULNWL_INTEL(ATOM_AIRMONT_MID, NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT), VULNWL_INTEL(ATOM_AIRMONT_NP, NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT), - VULNWL_INTEL(ATOM_GOLDMONT, NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT), - VULNWL_INTEL(ATOM_GOLDMONT_D, NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT), - VULNWL_INTEL(ATOM_GOLDMONT_PLUS, NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_EIBRS_PBRSB), + VULNWL_INTEL(ATOM_GOLDMONT, NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO), + VULNWL_INTEL(ATOM_GOLDMONT_D, NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO), + VULNWL_INTEL(ATOM_GOLDMONT_PLUS, NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_EIBRS_PBRSB), /* * Technically, swapgs isn't serializing on AMD (despite it previously @@ -1193,18 +1199,18 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = { VULNWL_INTEL(ATOM_TREMONT_D, NO_ITLB_MULTIHIT | NO_EIBRS_PBRSB), /* AMD Family 0xf - 0x12 */ - VULNWL_AMD(0x0f, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT), - VULNWL_AMD(0x10, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT), - VULNWL_AMD(0x11, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT), - VULNWL_AMD(0x12, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT), + VULNWL_AMD(0x0f, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO), + VULNWL_AMD(0x10, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO), + VULNWL_AMD(0x11, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO), + VULNWL_AMD(0x12, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO), /* FAMILY_ANY must be last, otherwise 0x0f - 0x12 matches won't work */ - VULNWL_AMD(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT), - VULNWL_HYGON(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT), + VULNWL_AMD(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO), + VULNWL_HYGON(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO), /* Zhaoxin Family 7 */ - VULNWL(CENTAUR, 7, X86_MODEL_ANY, NO_SPECTRE_V2 | NO_SWAPGS), - VULNWL(ZHAOXIN, 7, X86_MODEL_ANY, NO_SPECTRE_V2 | NO_SWAPGS), + VULNWL(CENTAUR, 7, X86_MODEL_ANY, NO_SPECTRE_V2 | NO_SWAPGS | NO_MMIO), + VULNWL(ZHAOXIN, 7, X86_MODEL_ANY, NO_SPECTRE_V2 | NO_SWAPGS | NO_MMIO), {} }; @@ -1358,10 +1364,16 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) * Affected CPU list is generally enough to enumerate the vulnerability, * but for virtualization case check for ARCH_CAP MSR bits also, VMM may * not want the guest to enumerate the bug. + * + * Set X86_BUG_MMIO_UNKNOWN for CPUs that are neither in the blacklist, + * nor in the whitelist and also don't enumerate MSR ARCH_CAP MMIO bits. */ - if (cpu_matches(cpu_vuln_blacklist, MMIO) && - !arch_cap_mmio_immune(ia32_cap)) - setup_force_cpu_bug(X86_BUG_MMIO_STALE_DATA); + if (!arch_cap_mmio_immune(ia32_cap)) { + if (cpu_matches(cpu_vuln_blacklist, MMIO)) + setup_force_cpu_bug(X86_BUG_MMIO_STALE_DATA); + else if (!cpu_matches(cpu_vuln_whitelist, NO_MMIO)) + setup_force_cpu_bug(X86_BUG_MMIO_UNKNOWN); + } if (!cpu_has(c, X86_FEATURE_BTC_NO)) { if (cpu_matches(cpu_vuln_blacklist, RETBLEED) || (ia32_cap & ARCH_CAP_RSBA)) diff --git a/arch/x86/kernel/cpu/feat_ctl.c b/arch/x86/kernel/cpu/feat_ctl.c index 993697e71854..03851240c3e3 100644 --- a/arch/x86/kernel/cpu/feat_ctl.c +++ b/arch/x86/kernel/cpu/feat_ctl.c @@ -1,11 +1,11 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/tboot.h> +#include <asm/cpu.h> #include <asm/cpufeature.h> #include <asm/msr-index.h> #include <asm/processor.h> #include <asm/vmx.h> -#include "cpu.h" #undef pr_fmt #define pr_fmt(fmt) "x86/cpu: " fmt diff --git a/arch/x86/kernel/cpu/hygon.c b/arch/x86/kernel/cpu/hygon.c index 21fd425088fe..c393b8773ace 100644 --- a/arch/x86/kernel/cpu/hygon.c +++ b/arch/x86/kernel/cpu/hygon.c @@ -326,8 +326,8 @@ static void init_hygon(struct cpuinfo_x86 *c) * msr_set_bit() uses the safe accessors, too, even if the MSR * is not present. */ - msr_set_bit(MSR_F10H_DECFG, - MSR_F10H_DECFG_LFENCE_SERIALIZE_BIT); + msr_set_bit(MSR_AMD64_DE_CFG, + MSR_AMD64_DE_CFG_LFENCE_SERIALIZE_BIT); /* A serializing LFENCE stops RDTSC speculation */ set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC); diff --git a/arch/x86/kernel/cpu/mce/apei.c b/arch/x86/kernel/cpu/mce/apei.c index 717192915f28..8ed341714686 100644 --- a/arch/x86/kernel/cpu/mce/apei.c +++ b/arch/x86/kernel/cpu/mce/apei.c @@ -29,15 +29,26 @@ void apei_mce_report_mem_error(int severity, struct cper_sec_mem_err *mem_err) { struct mce m; + int lsb; if (!(mem_err->validation_bits & CPER_MEM_VALID_PA)) return; + /* + * Even if the ->validation_bits are set for address mask, + * to be extra safe, check and reject an error radius '0', + * and fall back to the default page size. + */ + if (mem_err->validation_bits & CPER_MEM_VALID_PA_MASK) + lsb = find_first_bit((void *)&mem_err->physical_addr_mask, PAGE_SHIFT); + else + lsb = PAGE_SHIFT; + mce_setup(&m); m.bank = -1; /* Fake a memory read error with unknown channel */ m.status = MCI_STATUS_VAL | MCI_STATUS_EN | MCI_STATUS_ADDRV | MCI_STATUS_MISCV | 0x9f; - m.misc = (MCI_MISC_ADDR_PHYS << 6) | PAGE_SHIFT; + m.misc = (MCI_MISC_ADDR_PHYS << 6) | lsb; if (severity >= GHES_SEV_RECOVERABLE) m.status |= MCI_STATUS_UC; diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c index 8b2fcdfa6d31..3a35dec3ec55 100644 --- a/arch/x86/kernel/cpu/microcode/amd.c +++ b/arch/x86/kernel/cpu/microcode/amd.c @@ -440,7 +440,13 @@ apply_microcode_early_amd(u32 cpuid_1_eax, void *ucode, size_t size, bool save_p return ret; native_rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy); - if (rev >= mc->hdr.patch_id) + + /* + * Allow application of the same revision to pick up SMT-specific + * changes even if the revision of the other SMT thread is already + * up-to-date. + */ + if (rev > mc->hdr.patch_id) return ret; if (!__apply_microcode_amd(mc)) { @@ -528,8 +534,12 @@ void load_ucode_amd_ap(unsigned int cpuid_1_eax) native_rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy); - /* Check whether we have saved a new patch already: */ - if (*new_rev && rev < mc->hdr.patch_id) { + /* + * Check whether a new patch has been saved already. Also, allow application of + * the same revision in order to pick up SMT-thread-specific configuration even + * if the sibling SMT thread already has an up-to-date revision. + */ + if (*new_rev && rev <= mc->hdr.patch_id) { if (!__apply_microcode_amd(mc)) { *new_rev = mc->hdr.patch_id; return; @@ -788,6 +798,7 @@ static int verify_and_add_patch(u8 family, u8 *fw, unsigned int leftover, kfree(patch); return -EINVAL; } + patch->size = *patch_size; mc_hdr = (struct microcode_header_amd *)(fw + SECTION_HDR_SIZE); proc_id = mc_hdr->processor_rev_id; @@ -869,7 +880,7 @@ load_microcode_amd(bool save, u8 family, const u8 *data, size_t size) return ret; memset(amd_ucode_patch, 0, PATCH_MAX_SIZE); - memcpy(amd_ucode_patch, p->data, min_t(u32, ksize(p->data), PATCH_MAX_SIZE)); + memcpy(amd_ucode_patch, p->data, min_t(u32, p->size, PATCH_MAX_SIZE)); return ret; } @@ -924,12 +935,6 @@ static enum ucode_state request_microcode_amd(int cpu, struct device *device, return ret; } -static enum ucode_state -request_microcode_user(int cpu, const void __user *buf, size_t size) -{ - return UCODE_ERROR; -} - static void microcode_fini_cpu_amd(int cpu) { struct ucode_cpu_info *uci = ucode_cpu_info + cpu; @@ -938,7 +943,6 @@ static void microcode_fini_cpu_amd(int cpu) } static struct microcode_ops microcode_amd_ops = { - .request_microcode_user = request_microcode_user, .request_microcode_fw = request_microcode_amd, .collect_cpu_info = collect_cpu_info_amd, .apply_microcode = apply_microcode_amd, diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c index ad57e0e4d674..6a41cee242f6 100644 --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -491,7 +491,7 @@ wait_for_siblings: */ static int microcode_reload_late(void) { - int ret; + int old = boot_cpu_data.microcode, ret; pr_err("Attempting late microcode loading - it is dangerous and taints the kernel.\n"); pr_err("You should switch to early loading, if possible.\n"); @@ -503,7 +503,8 @@ static int microcode_reload_late(void) if (ret == 0) microcode_check(); - pr_info("Reload completed, microcode revision: 0x%x\n", boot_cpu_data.microcode); + pr_info("Reload completed, microcode revision: 0x%x -> 0x%x\n", + old, boot_cpu_data.microcode); return ret; } diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c index 025c8f0cd948..1fcbd671f1df 100644 --- a/arch/x86/kernel/cpu/microcode/intel.c +++ b/arch/x86/kernel/cpu/microcode/intel.c @@ -916,24 +916,7 @@ static enum ucode_state request_microcode_fw(int cpu, struct device *device, return ret; } -static enum ucode_state -request_microcode_user(int cpu, const void __user *buf, size_t size) -{ - struct iov_iter iter; - struct iovec iov; - - if (is_blacklisted(cpu)) - return UCODE_NFOUND; - - iov.iov_base = (void __user *)buf; - iov.iov_len = size; - iov_iter_init(&iter, WRITE, &iov, 1, size); - - return generic_load_microcode(cpu, &iter); -} - static struct microcode_ops microcode_intel_ops = { - .request_microcode_user = request_microcode_user, .request_microcode_fw = request_microcode_fw, .collect_cpu_info = collect_cpu_info, .apply_microcode = apply_microcode_intel, diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c index bb1c3f5f60c8..3266ea36667c 100644 --- a/arch/x86/kernel/cpu/resctrl/core.c +++ b/arch/x86/kernel/cpu/resctrl/core.c @@ -66,9 +66,6 @@ struct rdt_hw_resource rdt_resources_all[] = { .rid = RDT_RESOURCE_L3, .name = "L3", .cache_level = 3, - .cache = { - .min_cbm_bits = 1, - }, .domains = domain_init(RDT_RESOURCE_L3), .parse_ctrlval = parse_cbm, .format_str = "%d=%0*x", @@ -83,9 +80,6 @@ struct rdt_hw_resource rdt_resources_all[] = { .rid = RDT_RESOURCE_L2, .name = "L2", .cache_level = 2, - .cache = { - .min_cbm_bits = 1, - }, .domains = domain_init(RDT_RESOURCE_L2), .parse_ctrlval = parse_cbm, .format_str = "%d=%0*x", @@ -147,7 +141,6 @@ static inline void cache_alloc_hsw_probe(void) r->cache.shareable_bits = 0xc0000; r->cache.min_cbm_bits = 2; r->alloc_capable = true; - r->alloc_enabled = true; rdt_alloc_capable = true; } @@ -211,7 +204,6 @@ static bool __get_mem_config_intel(struct rdt_resource *r) thread_throttle_mode_init(); r->alloc_capable = true; - r->alloc_enabled = true; return true; } @@ -242,7 +234,6 @@ static bool __rdt_get_mem_config_amd(struct rdt_resource *r) r->data_width = 4; r->alloc_capable = true; - r->alloc_enabled = true; return true; } @@ -261,7 +252,6 @@ static void rdt_get_cache_alloc_cfg(int idx, struct rdt_resource *r) r->cache.shareable_bits = ebx & r->default_ctrl; r->data_width = (r->cache.cbm_len + 3) / 4; r->alloc_capable = true; - r->alloc_enabled = true; } static void rdt_get_cdp_config(int level) @@ -300,7 +290,7 @@ mba_wrmsr_amd(struct rdt_domain *d, struct msr_param *m, struct rdt_resource *r) * that can be written to QOS_MSRs. * There are currently no SKUs which support non linear delay values. */ -u32 delay_bw_map(unsigned long bw, struct rdt_resource *r) +static u32 delay_bw_map(unsigned long bw, struct rdt_resource *r) { if (r->membw.delay_linear) return MAX_MBA_BW - bw; @@ -401,7 +391,7 @@ struct rdt_domain *rdt_find_domain(struct rdt_resource *r, int id, return NULL; } -void setup_default_ctrlval(struct rdt_resource *r, u32 *dc, u32 *dm) +static void setup_default_ctrlval(struct rdt_resource *r, u32 *dc) { struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r); int i; @@ -410,12 +400,17 @@ void setup_default_ctrlval(struct rdt_resource *r, u32 *dc, u32 *dm) * Initialize the Control MSRs to having no control. * For Cache Allocation: Set all bits in cbm * For Memory Allocation: Set b/w requested to 100% - * and the bandwidth in MBps to U32_MAX */ - for (i = 0; i < hw_res->num_closid; i++, dc++, dm++) { + for (i = 0; i < hw_res->num_closid; i++, dc++) *dc = r->default_ctrl; - *dm = MBA_MAX_MBPS; - } +} + +static void domain_free(struct rdt_hw_domain *hw_dom) +{ + kfree(hw_dom->arch_mbm_total); + kfree(hw_dom->arch_mbm_local); + kfree(hw_dom->ctrl_val); + kfree(hw_dom); } static int domain_setup_ctrlval(struct rdt_resource *r, struct rdt_domain *d) @@ -423,23 +418,15 @@ static int domain_setup_ctrlval(struct rdt_resource *r, struct rdt_domain *d) struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r); struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d); struct msr_param m; - u32 *dc, *dm; + u32 *dc; dc = kmalloc_array(hw_res->num_closid, sizeof(*hw_dom->ctrl_val), GFP_KERNEL); if (!dc) return -ENOMEM; - dm = kmalloc_array(hw_res->num_closid, sizeof(*hw_dom->mbps_val), - GFP_KERNEL); - if (!dm) { - kfree(dc); - return -ENOMEM; - } - hw_dom->ctrl_val = dc; - hw_dom->mbps_val = dm; - setup_default_ctrlval(r, dc, dm); + setup_default_ctrlval(r, dc); m.low = 0; m.high = hw_res->num_closid; @@ -447,39 +434,31 @@ static int domain_setup_ctrlval(struct rdt_resource *r, struct rdt_domain *d) return 0; } -static int domain_setup_mon_state(struct rdt_resource *r, struct rdt_domain *d) +/** + * arch_domain_mbm_alloc() - Allocate arch private storage for the MBM counters + * @num_rmid: The size of the MBM counter array + * @hw_dom: The domain that owns the allocated arrays + */ +static int arch_domain_mbm_alloc(u32 num_rmid, struct rdt_hw_domain *hw_dom) { size_t tsize; - if (is_llc_occupancy_enabled()) { - d->rmid_busy_llc = bitmap_zalloc(r->num_rmid, GFP_KERNEL); - if (!d->rmid_busy_llc) - return -ENOMEM; - INIT_DELAYED_WORK(&d->cqm_limbo, cqm_handle_limbo); - } if (is_mbm_total_enabled()) { - tsize = sizeof(*d->mbm_total); - d->mbm_total = kcalloc(r->num_rmid, tsize, GFP_KERNEL); - if (!d->mbm_total) { - bitmap_free(d->rmid_busy_llc); + tsize = sizeof(*hw_dom->arch_mbm_total); + hw_dom->arch_mbm_total = kcalloc(num_rmid, tsize, GFP_KERNEL); + if (!hw_dom->arch_mbm_total) return -ENOMEM; - } } if (is_mbm_local_enabled()) { - tsize = sizeof(*d->mbm_local); - d->mbm_local = kcalloc(r->num_rmid, tsize, GFP_KERNEL); - if (!d->mbm_local) { - bitmap_free(d->rmid_busy_llc); - kfree(d->mbm_total); + tsize = sizeof(*hw_dom->arch_mbm_local); + hw_dom->arch_mbm_local = kcalloc(num_rmid, tsize, GFP_KERNEL); + if (!hw_dom->arch_mbm_local) { + kfree(hw_dom->arch_mbm_total); + hw_dom->arch_mbm_total = NULL; return -ENOMEM; } } - if (is_mbm_enabled()) { - INIT_DELAYED_WORK(&d->mbm_over, mbm_handle_overflow); - mbm_setup_overflow_handler(d, MBM_OVERFLOW_INTERVAL); - } - return 0; } @@ -502,6 +481,7 @@ static void domain_add_cpu(int cpu, struct rdt_resource *r) struct list_head *add_pos = NULL; struct rdt_hw_domain *hw_dom; struct rdt_domain *d; + int err; d = rdt_find_domain(r, id, &add_pos); if (IS_ERR(d)) { @@ -527,25 +507,22 @@ static void domain_add_cpu(int cpu, struct rdt_resource *r) rdt_domain_reconfigure_cdp(r); if (r->alloc_capable && domain_setup_ctrlval(r, d)) { - kfree(hw_dom); + domain_free(hw_dom); return; } - if (r->mon_capable && domain_setup_mon_state(r, d)) { - kfree(hw_dom->ctrl_val); - kfree(hw_dom->mbps_val); - kfree(hw_dom); + if (r->mon_capable && arch_domain_mbm_alloc(r->num_rmid, hw_dom)) { + domain_free(hw_dom); return; } list_add_tail(&d->list, add_pos); - /* - * If resctrl is mounted, add - * per domain monitor data directories. - */ - if (static_branch_unlikely(&rdt_mon_enable_key)) - mkdir_mondata_subdir_allrdtgrp(r, d); + err = resctrl_online_domain(r, d); + if (err) { + list_del(&d->list); + domain_free(hw_dom); + } } static void domain_remove_cpu(int cpu, struct rdt_resource *r) @@ -563,27 +540,8 @@ static void domain_remove_cpu(int cpu, struct rdt_resource *r) cpumask_clear_cpu(cpu, &d->cpu_mask); if (cpumask_empty(&d->cpu_mask)) { - /* - * If resctrl is mounted, remove all the - * per domain monitor data directories. - */ - if (static_branch_unlikely(&rdt_mon_enable_key)) - rmdir_mondata_subdir_allrdtgrp(r, d->id); + resctrl_offline_domain(r, d); list_del(&d->list); - if (r->mon_capable && is_mbm_enabled()) - cancel_delayed_work(&d->mbm_over); - if (is_llc_occupancy_enabled() && has_busy_rmid(r, d)) { - /* - * When a package is going down, forcefully - * decrement rmid->ebusy. There is no way to know - * that the L3 was flushed and hence may lead to - * incorrect counts in rare scenarios, but leaving - * the RMID as busy creates RMID leaks if the - * package never comes back. - */ - __check_limbo(d, true); - cancel_delayed_work(&d->cqm_limbo); - } /* * rdt_domain "d" is going to be freed below, so clear @@ -591,13 +549,8 @@ static void domain_remove_cpu(int cpu, struct rdt_resource *r) */ if (d->plr) d->plr->d = NULL; + domain_free(hw_dom); - kfree(hw_dom->ctrl_val); - kfree(hw_dom->mbps_val); - bitmap_free(d->rmid_busy_llc); - kfree(d->mbm_total); - kfree(d->mbm_local); - kfree(hw_dom); return; } @@ -877,6 +830,7 @@ static __init void rdt_init_res_defs_intel(void) r->cache.arch_has_sparse_bitmaps = false; r->cache.arch_has_empty_bitmaps = false; r->cache.arch_has_per_cpu_cfg = false; + r->cache.min_cbm_bits = 1; } else if (r->rid == RDT_RESOURCE_MBA) { hw_res->msr_base = MSR_IA32_MBA_THRTL_BASE; hw_res->msr_update = mba_wrmsr_intel; @@ -897,6 +851,7 @@ static __init void rdt_init_res_defs_amd(void) r->cache.arch_has_sparse_bitmaps = true; r->cache.arch_has_empty_bitmaps = true; r->cache.arch_has_per_cpu_cfg = true; + r->cache.min_cbm_bits = 0; } else if (r->rid == RDT_RESOURCE_MBA) { hw_res->msr_base = MSR_IA32_MBA_BW_BASE; hw_res->msr_update = mba_wrmsr_amd; diff --git a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c index 87666275eed9..1dafbdc5ac31 100644 --- a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c +++ b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c @@ -61,6 +61,7 @@ int parse_bw(struct rdt_parse_data *data, struct resctrl_schema *s, struct rdt_domain *d) { struct resctrl_staged_config *cfg; + u32 closid = data->rdtgrp->closid; struct rdt_resource *r = s->res; unsigned long bw_val; @@ -72,6 +73,12 @@ int parse_bw(struct rdt_parse_data *data, struct resctrl_schema *s, if (!bw_validate(data->buf, &bw_val, r)) return -EINVAL; + + if (is_mba_sc(r)) { + d->mbps_val[closid] = bw_val; + return 0; + } + cfg->new_ctrl = bw_val; cfg->have_new_ctrl = true; @@ -261,14 +268,13 @@ static u32 get_config_index(u32 closid, enum resctrl_conf_type type) static bool apply_config(struct rdt_hw_domain *hw_dom, struct resctrl_staged_config *cfg, u32 idx, - cpumask_var_t cpu_mask, bool mba_sc) + cpumask_var_t cpu_mask) { struct rdt_domain *dom = &hw_dom->d_resctrl; - u32 *dc = !mba_sc ? hw_dom->ctrl_val : hw_dom->mbps_val; - if (cfg->new_ctrl != dc[idx]) { + if (cfg->new_ctrl != hw_dom->ctrl_val[idx]) { cpumask_set_cpu(cpumask_any(&dom->cpu_mask), cpu_mask); - dc[idx] = cfg->new_ctrl; + hw_dom->ctrl_val[idx] = cfg->new_ctrl; return true; } @@ -276,6 +282,27 @@ static bool apply_config(struct rdt_hw_domain *hw_dom, return false; } +int resctrl_arch_update_one(struct rdt_resource *r, struct rdt_domain *d, + u32 closid, enum resctrl_conf_type t, u32 cfg_val) +{ + struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r); + struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d); + u32 idx = get_config_index(closid, t); + struct msr_param msr_param; + + if (!cpumask_test_cpu(smp_processor_id(), &d->cpu_mask)) + return -EINVAL; + + hw_dom->ctrl_val[idx] = cfg_val; + + msr_param.res = r; + msr_param.low = idx; + msr_param.high = idx + 1; + hw_res->msr_update(d, &msr_param, r); + + return 0; +} + int resctrl_arch_update_domains(struct rdt_resource *r, u32 closid) { struct resctrl_staged_config *cfg; @@ -284,14 +311,12 @@ int resctrl_arch_update_domains(struct rdt_resource *r, u32 closid) enum resctrl_conf_type t; cpumask_var_t cpu_mask; struct rdt_domain *d; - bool mba_sc; int cpu; u32 idx; if (!zalloc_cpumask_var(&cpu_mask, GFP_KERNEL)) return -ENOMEM; - mba_sc = is_mba_sc(r); msr_param.res = NULL; list_for_each_entry(d, &r->domains, list) { hw_dom = resctrl_to_arch_dom(d); @@ -301,7 +326,7 @@ int resctrl_arch_update_domains(struct rdt_resource *r, u32 closid) continue; idx = get_config_index(closid, t); - if (!apply_config(hw_dom, cfg, idx, cpu_mask, mba_sc)) + if (!apply_config(hw_dom, cfg, idx, cpu_mask)) continue; if (!msr_param.res) { @@ -315,11 +340,7 @@ int resctrl_arch_update_domains(struct rdt_resource *r, u32 closid) } } - /* - * Avoid writing the control msr with control values when - * MBA software controller is enabled - */ - if (cpumask_empty(cpu_mask) || mba_sc) + if (cpumask_empty(cpu_mask)) goto done; cpu = get_cpu(); /* Update resource control msr on this CPU if it's in cpu_mask. */ @@ -406,6 +427,14 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of, list_for_each_entry(s, &resctrl_schema_all, list) { r = s->res; + + /* + * Writes to mba_sc resources update the software controller, + * not the control MSR. + */ + if (is_mba_sc(r)) + continue; + ret = resctrl_arch_update_domains(r, rdtgrp->closid); if (ret) goto out; @@ -433,9 +462,7 @@ u32 resctrl_arch_get_config(struct rdt_resource *r, struct rdt_domain *d, struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d); u32 idx = get_config_index(closid, type); - if (!is_mba_sc(r)) - return hw_dom->ctrl_val[idx]; - return hw_dom->mbps_val[idx]; + return hw_dom->ctrl_val[idx]; } static void show_doms(struct seq_file *s, struct resctrl_schema *schema, int closid) @@ -450,8 +477,12 @@ static void show_doms(struct seq_file *s, struct resctrl_schema *schema, int clo if (sep) seq_puts(s, ";"); - ctrl_val = resctrl_arch_get_config(r, dom, closid, - schema->conf_type); + if (is_mba_sc(r)) + ctrl_val = dom->mbps_val[closid]; + else + ctrl_val = resctrl_arch_get_config(r, dom, closid, + schema->conf_type); + seq_printf(s, r->format_str, dom->id, max_data_width, ctrl_val); sep = true; @@ -518,7 +549,6 @@ void mon_event_read(struct rmid_read *rr, struct rdt_resource *r, int rdtgroup_mondata_show(struct seq_file *m, void *arg) { struct kernfs_open_file *of = m->private; - struct rdt_hw_resource *hw_res; u32 resid, evtid, domid; struct rdtgroup *rdtgrp; struct rdt_resource *r; @@ -538,8 +568,7 @@ int rdtgroup_mondata_show(struct seq_file *m, void *arg) domid = md.u.domid; evtid = md.u.evtid; - hw_res = &rdt_resources_all[resid]; - r = &hw_res->r_resctrl; + r = &rdt_resources_all[resid].r_resctrl; d = rdt_find_domain(r, domid, NULL); if (IS_ERR_OR_NULL(d)) { ret = -ENOENT; @@ -548,12 +577,12 @@ int rdtgroup_mondata_show(struct seq_file *m, void *arg) mon_event_read(&rr, r, d, rdtgrp, evtid, false); - if (rr.val & RMID_VAL_ERROR) + if (rr.err == -EIO) seq_puts(m, "Error\n"); - else if (rr.val & RMID_VAL_UNAVAIL) + else if (rr.err == -EINVAL) seq_puts(m, "Unavailable\n"); else - seq_printf(m, "%llu\n", rr.val * hw_res->mon_scale); + seq_printf(m, "%llu\n", rr.val); out: rdtgroup_kn_unlock(of->kn); diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h index 1d647188a43b..5f7128686cfd 100644 --- a/arch/x86/kernel/cpu/resctrl/internal.h +++ b/arch/x86/kernel/cpu/resctrl/internal.h @@ -22,21 +22,12 @@ #define L2_QOS_CDP_ENABLE 0x01ULL -/* - * Event IDs are used to program IA32_QM_EVTSEL before reading event - * counter from IA32_QM_CTR - */ -#define QOS_L3_OCCUP_EVENT_ID 0x01 -#define QOS_L3_MBM_TOTAL_EVENT_ID 0x02 -#define QOS_L3_MBM_LOCAL_EVENT_ID 0x03 - #define CQM_LIMBOCHECK_INTERVAL 1000 #define MBM_CNTR_WIDTH_BASE 24 #define MBM_OVERFLOW_INTERVAL 1000 #define MAX_MBA_BW 100u #define MBA_IS_LINEAR 0x4 -#define MBA_MAX_MBPS U32_MAX #define MAX_MBA_BW_AMD 0x800 #define MBM_CNTR_WIDTH_OFFSET_AMD 20 @@ -74,7 +65,7 @@ DECLARE_STATIC_KEY_FALSE(rdt_mon_enable_key); * @list: entry in &rdt_resource->evt_list */ struct mon_evt { - u32 evtid; + enum resctrl_event_id evtid; char *name; struct list_head list; }; @@ -91,9 +82,9 @@ struct mon_evt { union mon_data_bits { void *priv; struct { - unsigned int rid : 10; - unsigned int evtid : 8; - unsigned int domid : 14; + unsigned int rid : 10; + enum resctrl_event_id evtid : 8; + unsigned int domid : 14; } u; }; @@ -101,12 +92,12 @@ struct rmid_read { struct rdtgroup *rgrp; struct rdt_resource *r; struct rdt_domain *d; - int evtid; + enum resctrl_event_id evtid; bool first; + int err; u64 val; }; -extern unsigned int resctrl_cqm_threshold; extern bool rdt_alloc_capable; extern bool rdt_mon_capable; extern unsigned int rdt_mon_features; @@ -288,35 +279,45 @@ struct rftype { /** * struct mbm_state - status for each MBM counter in each domain - * @chunks: Total data moved (multiply by rdt_group.mon_scale to get bytes) - * @prev_msr: Value of IA32_QM_CTR for this RMID last time we read it - * @prev_bw_msr:Value of previous IA32_QM_CTR for bandwidth counting + * @prev_bw_bytes: Previous bytes value read for bandwidth calculation * @prev_bw: The most recent bandwidth in MBps * @delta_bw: Difference between the current and previous bandwidth * @delta_comp: Indicates whether to compute the delta_bw */ struct mbm_state { - u64 chunks; - u64 prev_msr; - u64 prev_bw_msr; + u64 prev_bw_bytes; u32 prev_bw; u32 delta_bw; bool delta_comp; }; /** + * struct arch_mbm_state - values used to compute resctrl_arch_rmid_read()s + * return value. + * @chunks: Total data moved (multiply by rdt_group.mon_scale to get bytes) + * @prev_msr: Value of IA32_QM_CTR last time it was read for the RMID used to + * find this struct. + */ +struct arch_mbm_state { + u64 chunks; + u64 prev_msr; +}; + +/** * struct rdt_hw_domain - Arch private attributes of a set of CPUs that share * a resource * @d_resctrl: Properties exposed to the resctrl file system * @ctrl_val: array of cache or mem ctrl values (indexed by CLOSID) - * @mbps_val: When mba_sc is enabled, this holds the bandwidth in MBps + * @arch_mbm_total: arch private state for MBM total bandwidth + * @arch_mbm_local: arch private state for MBM local bandwidth * * Members of this structure are accessed via helpers that provide abstraction. */ struct rdt_hw_domain { struct rdt_domain d_resctrl; u32 *ctrl_val; - u32 *mbps_val; + struct arch_mbm_state *arch_mbm_total; + struct arch_mbm_state *arch_mbm_local; }; static inline struct rdt_hw_domain *resctrl_to_arch_dom(struct rdt_domain *r) @@ -459,14 +460,6 @@ int resctrl_arch_set_cdp_enabled(enum resctrl_res_level l, bool enable); for_each_rdt_resource(r) \ if (r->mon_capable) -#define for_each_alloc_enabled_rdt_resource(r) \ - for_each_rdt_resource(r) \ - if (r->alloc_enabled) - -#define for_each_mon_enabled_rdt_resource(r) \ - for_each_rdt_resource(r) \ - if (r->mon_enabled) - /* CPUID.(EAX=10H, ECX=ResID=1).EAX */ union cpuid_0x10_1_eax { struct { @@ -530,10 +523,6 @@ void free_rmid(u32 rmid); int rdt_get_mon_l3_config(struct rdt_resource *r); void mon_event_count(void *info); int rdtgroup_mondata_show(struct seq_file *m, void *arg); -void rmdir_mondata_subdir_allrdtgrp(struct rdt_resource *r, - unsigned int dom_id); -void mkdir_mondata_subdir_allrdtgrp(struct rdt_resource *r, - struct rdt_domain *d); void mon_event_read(struct rmid_read *rr, struct rdt_resource *r, struct rdt_domain *d, struct rdtgroup *rdtgrp, int evtid, int first); @@ -542,8 +531,6 @@ void mbm_setup_overflow_handler(struct rdt_domain *dom, void mbm_handle_overflow(struct work_struct *work); void __init intel_rdt_mbm_apply_quirk(void); bool is_mba_sc(struct rdt_resource *r); -void setup_default_ctrlval(struct rdt_resource *r, u32 *dc, u32 *dm); -u32 delay_bw_map(unsigned long bw, struct rdt_resource *r); void cqm_setup_limbo_handler(struct rdt_domain *dom, unsigned long delay_ms); void cqm_handle_limbo(struct work_struct *work); bool has_busy_rmid(struct rdt_resource *r, struct rdt_domain *d); diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c index eaf25a234ff5..efe0c30d3a12 100644 --- a/arch/x86/kernel/cpu/resctrl/monitor.c +++ b/arch/x86/kernel/cpu/resctrl/monitor.c @@ -16,8 +16,12 @@ */ #include <linux/module.h> +#include <linux/sizes.h> #include <linux/slab.h> + #include <asm/cpu_device_id.h> +#include <asm/resctrl.h> + #include "internal.h" struct rmid_entry { @@ -37,8 +41,8 @@ static LIST_HEAD(rmid_free_lru); * @rmid_limbo_count count of currently unused but (potentially) * dirty RMIDs. * This counts RMIDs that no one is currently using but that - * may have a occupancy value > intel_cqm_threshold. User can change - * the threshold occupancy value. + * may have a occupancy value > resctrl_rmid_realloc_threshold. User can + * change the threshold occupancy value. */ static unsigned int rmid_limbo_count; @@ -59,10 +63,15 @@ bool rdt_mon_capable; unsigned int rdt_mon_features; /* - * This is the threshold cache occupancy at which we will consider an + * This is the threshold cache occupancy in bytes at which we will consider an * RMID available for re-allocation. */ -unsigned int resctrl_cqm_threshold; +unsigned int resctrl_rmid_realloc_threshold; + +/* + * This is the maximum value for the reallocation threshold, in bytes. + */ +unsigned int resctrl_rmid_realloc_limit; #define CF(cf) ((unsigned long)(1048576 * (cf) + 0.5)) @@ -137,9 +146,54 @@ static inline struct rmid_entry *__rmid_entry(u32 rmid) return entry; } -static u64 __rmid_read(u32 rmid, u32 eventid) +static struct arch_mbm_state *get_arch_mbm_state(struct rdt_hw_domain *hw_dom, + u32 rmid, + enum resctrl_event_id eventid) { - u64 val; + switch (eventid) { + case QOS_L3_OCCUP_EVENT_ID: + return NULL; + case QOS_L3_MBM_TOTAL_EVENT_ID: + return &hw_dom->arch_mbm_total[rmid]; + case QOS_L3_MBM_LOCAL_EVENT_ID: + return &hw_dom->arch_mbm_local[rmid]; + } + + /* Never expect to get here */ + WARN_ON_ONCE(1); + + return NULL; +} + +void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_domain *d, + u32 rmid, enum resctrl_event_id eventid) +{ + struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d); + struct arch_mbm_state *am; + + am = get_arch_mbm_state(hw_dom, rmid, eventid); + if (am) + memset(am, 0, sizeof(*am)); +} + +static u64 mbm_overflow_count(u64 prev_msr, u64 cur_msr, unsigned int width) +{ + u64 shift = 64 - width, chunks; + + chunks = (cur_msr << shift) - (prev_msr << shift); + return chunks >> shift; +} + +int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_domain *d, + u32 rmid, enum resctrl_event_id eventid, u64 *val) +{ + struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r); + struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d); + struct arch_mbm_state *am; + u64 msr_val, chunks; + + if (!cpumask_test_cpu(smp_processor_id(), &d->cpu_mask)) + return -EINVAL; /* * As per the SDM, when IA32_QM_EVTSEL.EvtID (bits 7:0) is configured @@ -150,16 +204,26 @@ static u64 __rmid_read(u32 rmid, u32 eventid) * are error bits. */ wrmsr(MSR_IA32_QM_EVTSEL, eventid, rmid); - rdmsrl(MSR_IA32_QM_CTR, val); - - return val; -} + rdmsrl(MSR_IA32_QM_CTR, msr_val); + + if (msr_val & RMID_VAL_ERROR) + return -EIO; + if (msr_val & RMID_VAL_UNAVAIL) + return -EINVAL; + + am = get_arch_mbm_state(hw_dom, rmid, eventid); + if (am) { + am->chunks += mbm_overflow_count(am->prev_msr, msr_val, + hw_res->mbm_width); + chunks = get_corrected_mbm_count(rmid, am->chunks); + am->prev_msr = msr_val; + } else { + chunks = msr_val; + } -static bool rmid_dirty(struct rmid_entry *entry) -{ - u64 val = __rmid_read(entry->rmid, QOS_L3_OCCUP_EVENT_ID); + *val = chunks * hw_res->mon_scale; - return val >= resctrl_cqm_threshold; + return 0; } /* @@ -170,11 +234,11 @@ static bool rmid_dirty(struct rmid_entry *entry) */ void __check_limbo(struct rdt_domain *d, bool force_free) { + struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl; struct rmid_entry *entry; - struct rdt_resource *r; u32 crmid = 1, nrmid; - - r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl; + bool rmid_dirty; + u64 val = 0; /* * Skip RMID 0 and start from RMID 1 and check all the RMIDs that @@ -188,7 +252,15 @@ void __check_limbo(struct rdt_domain *d, bool force_free) break; entry = __rmid_entry(nrmid); - if (force_free || !rmid_dirty(entry)) { + + if (resctrl_arch_rmid_read(r, d, entry->rmid, + QOS_L3_OCCUP_EVENT_ID, &val)) { + rmid_dirty = true; + } else { + rmid_dirty = (val >= resctrl_rmid_realloc_threshold); + } + + if (force_free || !rmid_dirty) { clear_bit(entry->rmid, d->rmid_busy_llc); if (!--entry->busy) { rmid_limbo_count--; @@ -227,19 +299,19 @@ int alloc_rmid(void) static void add_rmid_to_limbo(struct rmid_entry *entry) { - struct rdt_resource *r; + struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl; struct rdt_domain *d; - int cpu; - u64 val; - - r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl; + int cpu, err; + u64 val = 0; entry->busy = 0; cpu = get_cpu(); list_for_each_entry(d, &r->domains, list) { if (cpumask_test_cpu(cpu, &d->cpu_mask)) { - val = __rmid_read(entry->rmid, QOS_L3_OCCUP_EVENT_ID); - if (val <= resctrl_cqm_threshold) + err = resctrl_arch_rmid_read(r, d, entry->rmid, + QOS_L3_OCCUP_EVENT_ID, + &val); + if (err || val <= resctrl_rmid_realloc_threshold) continue; } @@ -277,24 +349,18 @@ void free_rmid(u32 rmid) list_add_tail(&entry->list, &rmid_free_lru); } -static u64 mbm_overflow_count(u64 prev_msr, u64 cur_msr, unsigned int width) +static int __mon_event_count(u32 rmid, struct rmid_read *rr) { - u64 shift = 64 - width, chunks; + struct mbm_state *m; + u64 tval = 0; - chunks = (cur_msr << shift) - (prev_msr << shift); - return chunks >> shift; -} + if (rr->first) + resctrl_arch_reset_rmid(rr->r, rr->d, rmid, rr->evtid); -static u64 __mon_event_count(u32 rmid, struct rmid_read *rr) -{ - struct rdt_hw_resource *hw_res = resctrl_to_arch_res(rr->r); - struct mbm_state *m; - u64 chunks, tval; + rr->err = resctrl_arch_rmid_read(rr->r, rr->d, rmid, rr->evtid, &tval); + if (rr->err) + return rr->err; - tval = __rmid_read(rmid, rr->evtid); - if (tval & (RMID_VAL_ERROR | RMID_VAL_UNAVAIL)) { - return tval; - } switch (rr->evtid) { case QOS_L3_OCCUP_EVENT_ID: rr->val += tval; @@ -308,48 +374,47 @@ static u64 __mon_event_count(u32 rmid, struct rmid_read *rr) default: /* * Code would never reach here because an invalid - * event id would fail the __rmid_read. + * event id would fail in resctrl_arch_rmid_read(). */ - return RMID_VAL_ERROR; + return -EINVAL; } if (rr->first) { memset(m, 0, sizeof(struct mbm_state)); - m->prev_bw_msr = m->prev_msr = tval; return 0; } - chunks = mbm_overflow_count(m->prev_msr, tval, hw_res->mbm_width); - m->chunks += chunks; - m->prev_msr = tval; - - rr->val += get_corrected_mbm_count(rmid, m->chunks); + rr->val += tval; return 0; } /* + * mbm_bw_count() - Update bw count from values previously read by + * __mon_event_count(). + * @rmid: The rmid used to identify the cached mbm_state. + * @rr: The struct rmid_read populated by __mon_event_count(). + * * Supporting function to calculate the memory bandwidth - * and delta bandwidth in MBps. + * and delta bandwidth in MBps. The chunks value previously read by + * __mon_event_count() is compared with the chunks value from the previous + * invocation. This must be called once per second to maintain values in MBps. */ static void mbm_bw_count(u32 rmid, struct rmid_read *rr) { - struct rdt_hw_resource *hw_res = resctrl_to_arch_res(rr->r); struct mbm_state *m = &rr->d->mbm_local[rmid]; - u64 tval, cur_bw, chunks; + u64 cur_bw, bytes, cur_bytes; - tval = __rmid_read(rmid, rr->evtid); - if (tval & (RMID_VAL_ERROR | RMID_VAL_UNAVAIL)) - return; + cur_bytes = rr->val; + bytes = cur_bytes - m->prev_bw_bytes; + m->prev_bw_bytes = cur_bytes; - chunks = mbm_overflow_count(m->prev_bw_msr, tval, hw_res->mbm_width); - cur_bw = (get_corrected_mbm_count(rmid, chunks) * hw_res->mon_scale) >> 20; + cur_bw = bytes / SZ_1M; if (m->delta_comp) m->delta_bw = abs(cur_bw - m->prev_bw); m->delta_comp = false; m->prev_bw = cur_bw; - m->prev_bw_msr = tval; } /* @@ -361,11 +426,11 @@ void mon_event_count(void *info) struct rdtgroup *rdtgrp, *entry; struct rmid_read *rr = info; struct list_head *head; - u64 ret_val; + int ret; rdtgrp = rr->rgrp; - ret_val = __mon_event_count(rdtgrp->mon.rmid, rr); + ret = __mon_event_count(rdtgrp->mon.rmid, rr); /* * For Ctrl groups read data from child monitor groups and @@ -377,13 +442,17 @@ void mon_event_count(void *info) if (rdtgrp->type == RDTCTRL_GROUP) { list_for_each_entry(entry, head, mon.crdtgrp_list) { if (__mon_event_count(entry->mon.rmid, rr) == 0) - ret_val = 0; + ret = 0; } } - /* Report error if none of rmid_reads are successful */ - if (ret_val) - rr->val = ret_val; + /* + * __mon_event_count() calls for newly created monitor groups may + * report -EINVAL/Unavailable if the monitor hasn't seen any traffic. + * Discard error if any of the monitor event reads succeeded. + */ + if (ret == 0) + rr->err = 0; } /* @@ -420,10 +489,8 @@ void mon_event_count(void *info) */ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_domain *dom_mbm) { - u32 closid, rmid, cur_msr, cur_msr_val, new_msr_val; + u32 closid, rmid, cur_msr_val, new_msr_val; struct mbm_state *pmbm_data, *cmbm_data; - struct rdt_hw_resource *hw_r_mba; - struct rdt_hw_domain *hw_dom_mba; u32 cur_bw, delta_bw, user_bw; struct rdt_resource *r_mba; struct rdt_domain *dom_mba; @@ -433,8 +500,8 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_domain *dom_mbm) if (!is_mbm_local_enabled()) return; - hw_r_mba = &rdt_resources_all[RDT_RESOURCE_MBA]; - r_mba = &hw_r_mba->r_resctrl; + r_mba = &rdt_resources_all[RDT_RESOURCE_MBA].r_resctrl; + closid = rgrp->closid; rmid = rgrp->mon.rmid; pmbm_data = &dom_mbm->mbm_local[rmid]; @@ -444,16 +511,13 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_domain *dom_mbm) pr_warn_once("Failure to get domain for MBA update\n"); return; } - hw_dom_mba = resctrl_to_arch_dom(dom_mba); cur_bw = pmbm_data->prev_bw; - user_bw = resctrl_arch_get_config(r_mba, dom_mba, closid, CDP_NONE); + user_bw = dom_mba->mbps_val[closid]; delta_bw = pmbm_data->delta_bw; - /* - * resctrl_arch_get_config() chooses the mbps/ctrl value to return - * based on is_mba_sc(). For now, reach into the hw_dom. - */ - cur_msr_val = hw_dom_mba->ctrl_val[closid]; + + /* MBA resource doesn't support CDP */ + cur_msr_val = resctrl_arch_get_config(r_mba, dom_mba, closid, CDP_NONE); /* * For Ctrl groups read data from child monitor groups. @@ -488,9 +552,7 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_domain *dom_mbm) return; } - cur_msr = hw_r_mba->msr_base + closid; - wrmsrl(cur_msr, delay_bw_map(new_msr_val, r_mba)); - hw_dom_mba->ctrl_val[closid] = new_msr_val; + resctrl_arch_update_one(r_mba, dom_mba, closid, CDP_NONE, new_msr_val); /* * Delta values are updated dynamically package wise for each @@ -523,10 +585,12 @@ static void mbm_update(struct rdt_resource *r, struct rdt_domain *d, int rmid) */ if (is_mbm_total_enabled()) { rr.evtid = QOS_L3_MBM_TOTAL_EVENT_ID; + rr.val = 0; __mon_event_count(rmid, &rr); } if (is_mbm_local_enabled()) { rr.evtid = QOS_L3_MBM_LOCAL_EVENT_ID; + rr.val = 0; __mon_event_count(rmid, &rr); /* @@ -686,9 +750,10 @@ int rdt_get_mon_l3_config(struct rdt_resource *r) { unsigned int mbm_offset = boot_cpu_data.x86_cache_mbm_width_offset; struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r); - unsigned int cl_size = boot_cpu_data.x86_cache_size; + unsigned int threshold; int ret; + resctrl_rmid_realloc_limit = boot_cpu_data.x86_cache_size * 1024; hw_res->mon_scale = boot_cpu_data.x86_cache_occ_scale; r->num_rmid = boot_cpu_data.x86_cache_max_rmid + 1; hw_res->mbm_width = MBM_CNTR_WIDTH_BASE; @@ -705,10 +770,14 @@ int rdt_get_mon_l3_config(struct rdt_resource *r) * * For a 35MB LLC and 56 RMIDs, this is ~1.8% of the LLC. */ - resctrl_cqm_threshold = cl_size * 1024 / r->num_rmid; + threshold = resctrl_rmid_realloc_limit / r->num_rmid; - /* h/w works in units of "boot_cpu_data.x86_cache_occ_scale" */ - resctrl_cqm_threshold /= hw_res->mon_scale; + /* + * Because num_rmid may not be a power of two, round the value + * to the nearest multiple of hw_res->mon_scale so it matches a + * value the hardware will measure. mon_scale may not be a power of 2. + */ + resctrl_rmid_realloc_threshold = resctrl_arch_round_mon_val(threshold); ret = dom_data_init(r); if (ret) @@ -717,7 +786,6 @@ int rdt_get_mon_l3_config(struct rdt_resource *r) l3_mon_evt_init(r); r->mon_capable = true; - r->mon_enabled = true; return 0; } diff --git a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c index db813f819ad6..d961ae3ed96e 100644 --- a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c +++ b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c @@ -420,6 +420,7 @@ static int pseudo_lock_fn(void *_rdtgrp) struct pseudo_lock_region *plr = rdtgrp->plr; u32 rmid_p, closid_p; unsigned long i; + u64 saved_msr; #ifdef CONFIG_KASAN /* * The registers used for local register variables are also used @@ -463,6 +464,7 @@ static int pseudo_lock_fn(void *_rdtgrp) * the buffer and evict pseudo-locked memory read earlier from the * cache. */ + saved_msr = __rdmsr(MSR_MISC_FEATURE_CONTROL); __wrmsr(MSR_MISC_FEATURE_CONTROL, prefetch_disable_bits, 0x0); closid_p = this_cpu_read(pqr_state.cur_closid); rmid_p = this_cpu_read(pqr_state.cur_rmid); @@ -514,7 +516,7 @@ static int pseudo_lock_fn(void *_rdtgrp) __wrmsr(IA32_PQR_ASSOC, rmid_p, closid_p); /* Re-enable the hardware prefetcher(s) */ - wrmsr(MSR_MISC_FEATURE_CONTROL, 0x0, 0x0); + wrmsrl(MSR_MISC_FEATURE_CONTROL, saved_msr); local_irq_enable(); plr->thread_done = 1; @@ -835,7 +837,7 @@ bool rdtgroup_pseudo_locked_in_hierarchy(struct rdt_domain *d) * First determine which cpus have pseudo-locked regions * associated with them. */ - for_each_alloc_enabled_rdt_resource(r) { + for_each_alloc_capable_rdt_resource(r) { list_for_each_entry(d_i, &r->domains, list) { if (d_i->plr) cpumask_or(cpu_with_psl, cpu_with_psl, @@ -871,6 +873,7 @@ bool rdtgroup_pseudo_locked_in_hierarchy(struct rdt_domain *d) static int measure_cycles_lat_fn(void *_plr) { struct pseudo_lock_region *plr = _plr; + u32 saved_low, saved_high; unsigned long i; u64 start, end; void *mem_r; @@ -879,6 +882,7 @@ static int measure_cycles_lat_fn(void *_plr) /* * Disable hardware prefetchers. */ + rdmsr(MSR_MISC_FEATURE_CONTROL, saved_low, saved_high); wrmsr(MSR_MISC_FEATURE_CONTROL, prefetch_disable_bits, 0x0); mem_r = READ_ONCE(plr->kmem); /* @@ -895,7 +899,7 @@ static int measure_cycles_lat_fn(void *_plr) end = rdtsc_ordered(); trace_pseudo_lock_mem_latency((u32)(end - start)); } - wrmsr(MSR_MISC_FEATURE_CONTROL, 0x0, 0x0); + wrmsr(MSR_MISC_FEATURE_CONTROL, saved_low, saved_high); local_irq_enable(); plr->thread_done = 1; wake_up_interruptible(&plr->lock_thread_wq); @@ -940,6 +944,7 @@ static int measure_residency_fn(struct perf_event_attr *miss_attr, u64 hits_before = 0, hits_after = 0, miss_before = 0, miss_after = 0; struct perf_event *miss_event, *hit_event; int hit_pmcnum, miss_pmcnum; + u32 saved_low, saved_high; unsigned int line_size; unsigned int size; unsigned long i; @@ -973,6 +978,7 @@ static int measure_residency_fn(struct perf_event_attr *miss_attr, /* * Disable hardware prefetchers. */ + rdmsr(MSR_MISC_FEATURE_CONTROL, saved_low, saved_high); wrmsr(MSR_MISC_FEATURE_CONTROL, prefetch_disable_bits, 0x0); /* Initialize rest of local variables */ @@ -1031,7 +1037,7 @@ static int measure_residency_fn(struct perf_event_attr *miss_attr, */ rmb(); /* Re-enable hardware prefetchers */ - wrmsr(MSR_MISC_FEATURE_CONTROL, 0x0, 0x0); + wrmsr(MSR_MISC_FEATURE_CONTROL, saved_low, saved_high); local_irq_enable(); out_hit: perf_event_release_kernel(hit_event); diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index f276aff521e8..e5a48f05e787 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -1030,10 +1030,7 @@ static int rdt_delay_linear_show(struct kernfs_open_file *of, static int max_threshold_occ_show(struct kernfs_open_file *of, struct seq_file *seq, void *v) { - struct rdt_resource *r = of->kn->parent->priv; - struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r); - - seq_printf(seq, "%u\n", resctrl_cqm_threshold * hw_res->mon_scale); + seq_printf(seq, "%u\n", resctrl_rmid_realloc_threshold); return 0; } @@ -1055,7 +1052,6 @@ static int rdt_thread_throttle_mode_show(struct kernfs_open_file *of, static ssize_t max_threshold_occ_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { - struct rdt_hw_resource *hw_res; unsigned int bytes; int ret; @@ -1063,11 +1059,10 @@ static ssize_t max_threshold_occ_write(struct kernfs_open_file *of, if (ret) return ret; - if (bytes > (boot_cpu_data.x86_cache_size * 1024)) + if (bytes > resctrl_rmid_realloc_limit) return -EINVAL; - hw_res = resctrl_to_arch_res(of->kn->parent->priv); - resctrl_cqm_threshold = bytes / hw_res->mon_scale; + resctrl_rmid_realloc_threshold = resctrl_arch_round_mon_val(bytes); return nbytes; } @@ -1356,11 +1351,13 @@ static int rdtgroup_size_show(struct kernfs_open_file *of, struct seq_file *s, void *v) { struct resctrl_schema *schema; + enum resctrl_conf_type type; struct rdtgroup *rdtgrp; struct rdt_resource *r; struct rdt_domain *d; unsigned int size; int ret = 0; + u32 closid; bool sep; u32 ctrl; @@ -1386,8 +1383,11 @@ static int rdtgroup_size_show(struct kernfs_open_file *of, goto out; } + closid = rdtgrp->closid; + list_for_each_entry(schema, &resctrl_schema_all, list) { r = schema->res; + type = schema->conf_type; sep = false; seq_printf(s, "%*s:", max_name_width, schema->name); list_for_each_entry(d, &r->domains, list) { @@ -1396,9 +1396,12 @@ static int rdtgroup_size_show(struct kernfs_open_file *of, if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) { size = 0; } else { - ctrl = resctrl_arch_get_config(r, d, - rdtgrp->closid, - schema->conf_type); + if (is_mba_sc(r)) + ctrl = d->mbps_val[closid]; + else + ctrl = resctrl_arch_get_config(r, d, + closid, + type); if (r->rid == RDT_RESOURCE_MBA) size = ctrl; else @@ -1756,7 +1759,7 @@ static int rdtgroup_create_info_dir(struct kernfs_node *parent_kn) if (ret) goto out_destroy; - /* loop over enabled controls, these are all alloc_enabled */ + /* loop over enabled controls, these are all alloc_capable */ list_for_each_entry(s, &resctrl_schema_all, list) { r = s->res; fflags = r->fflags | RF_CTRL_INFO; @@ -1765,7 +1768,7 @@ static int rdtgroup_create_info_dir(struct kernfs_node *parent_kn) goto out_destroy; } - for_each_mon_enabled_rdt_resource(r) { + for_each_mon_capable_rdt_resource(r) { fflags = r->fflags | RF_MON_INFO; sprintf(name, "%s_MON", r->name); ret = rdtgroup_mkdir_info_resdir(r, name, fflags); @@ -1889,26 +1892,61 @@ void rdt_domain_reconfigure_cdp(struct rdt_resource *r) l3_qos_cfg_update(&hw_res->cdp_enabled); } +static int mba_sc_domain_allocate(struct rdt_resource *r, struct rdt_domain *d) +{ + u32 num_closid = resctrl_arch_get_num_closid(r); + int cpu = cpumask_any(&d->cpu_mask); + int i; + + d->mbps_val = kcalloc_node(num_closid, sizeof(*d->mbps_val), + GFP_KERNEL, cpu_to_node(cpu)); + if (!d->mbps_val) + return -ENOMEM; + + for (i = 0; i < num_closid; i++) + d->mbps_val[i] = MBA_MAX_MBPS; + + return 0; +} + +static void mba_sc_domain_destroy(struct rdt_resource *r, + struct rdt_domain *d) +{ + kfree(d->mbps_val); + d->mbps_val = NULL; +} + /* - * Enable or disable the MBA software controller - * which helps user specify bandwidth in MBps. * MBA software controller is supported only if * MBM is supported and MBA is in linear scale. */ +static bool supports_mba_mbps(void) +{ + struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_MBA].r_resctrl; + + return (is_mbm_local_enabled() && + r->alloc_capable && is_mba_linear()); +} + +/* + * Enable or disable the MBA software controller + * which helps user specify bandwidth in MBps. + */ static int set_mba_sc(bool mba_sc) { struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_MBA].r_resctrl; - struct rdt_hw_domain *hw_dom; + u32 num_closid = resctrl_arch_get_num_closid(r); struct rdt_domain *d; + int i; - if (!is_mbm_enabled() || !is_mba_linear() || - mba_sc == is_mba_sc(r)) + if (!supports_mba_mbps() || mba_sc == is_mba_sc(r)) return -EINVAL; r->membw.mba_sc = mba_sc; + list_for_each_entry(d, &r->domains, list) { - hw_dom = resctrl_to_arch_dom(d); - setup_default_ctrlval(r, hw_dom->ctrl_val, hw_dom->mbps_val); + for (i = 0; i < num_closid; i++) + d->mbps_val[i] = MBA_MAX_MBPS; } return 0; @@ -2106,7 +2144,7 @@ static int schemata_list_create(void) struct rdt_resource *r; int ret = 0; - for_each_alloc_enabled_rdt_resource(r) { + for_each_alloc_capable_rdt_resource(r) { if (resctrl_arch_get_cdp_enabled(r->rid)) { ret = schemata_list_add(r, CDP_CODE); if (ret) @@ -2261,7 +2299,7 @@ static int rdt_parse_param(struct fs_context *fc, struct fs_parameter *param) ctx->enable_cdpl2 = true; return 0; case Opt_mba_mbps: - if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) + if (!supports_mba_mbps()) return -EINVAL; ctx->enable_mba_mbps = true; return 0; @@ -2452,7 +2490,7 @@ static void rdt_kill_sb(struct super_block *sb) set_mba_sc(false); /*Put everything back to default values. */ - for_each_alloc_enabled_rdt_resource(r) + for_each_alloc_capable_rdt_resource(r) reset_all_ctrls(r); cdp_disable_all(); rmdir_all_sub(); @@ -2499,14 +2537,12 @@ static int mon_addfile(struct kernfs_node *parent_kn, const char *name, * Remove all subdirectories of mon_data of ctrl_mon groups * and monitor groups with given domain id. */ -void rmdir_mondata_subdir_allrdtgrp(struct rdt_resource *r, unsigned int dom_id) +static void rmdir_mondata_subdir_allrdtgrp(struct rdt_resource *r, + unsigned int dom_id) { struct rdtgroup *prgrp, *crgrp; char name[32]; - if (!r->mon_enabled) - return; - list_for_each_entry(prgrp, &rdt_all_groups, rdtgroup_list) { sprintf(name, "mon_%s_%02d", r->name, dom_id); kernfs_remove_by_name(prgrp->mon.mon_data_kn, name); @@ -2565,16 +2601,13 @@ out_destroy: * Add all subdirectories of mon_data for "ctrl_mon" groups * and "monitor" groups with given domain id. */ -void mkdir_mondata_subdir_allrdtgrp(struct rdt_resource *r, - struct rdt_domain *d) +static void mkdir_mondata_subdir_allrdtgrp(struct rdt_resource *r, + struct rdt_domain *d) { struct kernfs_node *parent_kn; struct rdtgroup *prgrp, *crgrp; struct list_head *head; - if (!r->mon_enabled) - return; - list_for_each_entry(prgrp, &rdt_all_groups, rdtgroup_list) { parent_kn = prgrp->mon.mon_data_kn; mkdir_mondata_subdir(parent_kn, d, r, prgrp); @@ -2642,7 +2675,7 @@ static int mkdir_mondata_all(struct kernfs_node *parent_kn, * Create the subdirectories for each domain. Note that all events * in a domain like L3 are grouped into a resource whose domain is L3 */ - for_each_mon_enabled_rdt_resource(r) { + for_each_mon_capable_rdt_resource(r) { ret = mkdir_mondata_subdir_alldom(kn, r, prgrp); if (ret) goto out_destroy; @@ -2786,14 +2819,19 @@ static int rdtgroup_init_cat(struct resctrl_schema *s, u32 closid) } /* Initialize MBA resource with default values. */ -static void rdtgroup_init_mba(struct rdt_resource *r) +static void rdtgroup_init_mba(struct rdt_resource *r, u32 closid) { struct resctrl_staged_config *cfg; struct rdt_domain *d; list_for_each_entry(d, &r->domains, list) { + if (is_mba_sc(r)) { + d->mbps_val[closid] = MBA_MAX_MBPS; + continue; + } + cfg = &d->staged_config[CDP_NONE]; - cfg->new_ctrl = is_mba_sc(r) ? MBA_MAX_MBPS : r->default_ctrl; + cfg->new_ctrl = r->default_ctrl; cfg->have_new_ctrl = true; } } @@ -2808,7 +2846,9 @@ static int rdtgroup_init_alloc(struct rdtgroup *rdtgrp) list_for_each_entry(s, &resctrl_schema_all, list) { r = s->res; if (r->rid == RDT_RESOURCE_MBA) { - rdtgroup_init_mba(r); + rdtgroup_init_mba(r, rdtgrp->closid); + if (is_mba_sc(r)) + continue; } else { ret = rdtgroup_init_cat(s, rdtgrp->closid); if (ret < 0) @@ -3236,6 +3276,110 @@ out: return ret; } +static void domain_destroy_mon_state(struct rdt_domain *d) +{ + bitmap_free(d->rmid_busy_llc); + kfree(d->mbm_total); + kfree(d->mbm_local); +} + +void resctrl_offline_domain(struct rdt_resource *r, struct rdt_domain *d) +{ + lockdep_assert_held(&rdtgroup_mutex); + + if (supports_mba_mbps() && r->rid == RDT_RESOURCE_MBA) + mba_sc_domain_destroy(r, d); + + if (!r->mon_capable) + return; + + /* + * If resctrl is mounted, remove all the + * per domain monitor data directories. + */ + if (static_branch_unlikely(&rdt_mon_enable_key)) + rmdir_mondata_subdir_allrdtgrp(r, d->id); + + if (is_mbm_enabled()) + cancel_delayed_work(&d->mbm_over); + if (is_llc_occupancy_enabled() && has_busy_rmid(r, d)) { + /* + * When a package is going down, forcefully + * decrement rmid->ebusy. There is no way to know + * that the L3 was flushed and hence may lead to + * incorrect counts in rare scenarios, but leaving + * the RMID as busy creates RMID leaks if the + * package never comes back. + */ + __check_limbo(d, true); + cancel_delayed_work(&d->cqm_limbo); + } + + domain_destroy_mon_state(d); +} + +static int domain_setup_mon_state(struct rdt_resource *r, struct rdt_domain *d) +{ + size_t tsize; + + if (is_llc_occupancy_enabled()) { + d->rmid_busy_llc = bitmap_zalloc(r->num_rmid, GFP_KERNEL); + if (!d->rmid_busy_llc) + return -ENOMEM; + } + if (is_mbm_total_enabled()) { + tsize = sizeof(*d->mbm_total); + d->mbm_total = kcalloc(r->num_rmid, tsize, GFP_KERNEL); + if (!d->mbm_total) { + bitmap_free(d->rmid_busy_llc); + return -ENOMEM; + } + } + if (is_mbm_local_enabled()) { + tsize = sizeof(*d->mbm_local); + d->mbm_local = kcalloc(r->num_rmid, tsize, GFP_KERNEL); + if (!d->mbm_local) { + bitmap_free(d->rmid_busy_llc); + kfree(d->mbm_total); + return -ENOMEM; + } + } + + return 0; +} + +int resctrl_online_domain(struct rdt_resource *r, struct rdt_domain *d) +{ + int err; + + lockdep_assert_held(&rdtgroup_mutex); + + if (supports_mba_mbps() && r->rid == RDT_RESOURCE_MBA) + /* RDT_RESOURCE_MBA is never mon_capable */ + return mba_sc_domain_allocate(r, d); + + if (!r->mon_capable) + return 0; + + err = domain_setup_mon_state(r, d); + if (err) + return err; + + if (is_mbm_enabled()) { + INIT_DELAYED_WORK(&d->mbm_over, mbm_handle_overflow); + mbm_setup_overflow_handler(d, MBM_OVERFLOW_INTERVAL); + } + + if (is_llc_occupancy_enabled()) + INIT_DELAYED_WORK(&d->cqm_limbo, cqm_handle_limbo); + + /* If resctrl is mounted, add per domain monitor data directories. */ + if (static_branch_unlikely(&rdt_mon_enable_key)) + mkdir_mondata_subdir_allrdtgrp(r, d); + + return 0; +} + /* * rdtgroup_init - rdtgroup initialization * diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c index fd44b54c90d5..fc01f81f6e2a 100644 --- a/arch/x86/kernel/cpu/scattered.c +++ b/arch/x86/kernel/cpu/scattered.c @@ -45,6 +45,7 @@ static const struct cpuid_bit cpuid_bits[] = { { X86_FEATURE_PROC_FEEDBACK, CPUID_EDX, 11, 0x80000007, 0 }, { X86_FEATURE_MBA, CPUID_EBX, 6, 0x80000008, 0 }, { X86_FEATURE_PERFMON_V2, CPUID_EAX, 0, 0x80000022, 0 }, + { X86_FEATURE_AMD_LBR_V2, CPUID_EAX, 1, 0x80000022, 0 }, { 0, 0, 0, 0, 0 } }; diff --git a/arch/x86/kernel/cpu/sgx/encl.c b/arch/x86/kernel/cpu/sgx/encl.c index 24c1bb8eb196..1ec20807de1e 100644 --- a/arch/x86/kernel/cpu/sgx/encl.c +++ b/arch/x86/kernel/cpu/sgx/encl.c @@ -12,6 +12,9 @@ #include "encls.h" #include "sgx.h" +static int sgx_encl_lookup_backing(struct sgx_encl *encl, unsigned long page_index, + struct sgx_backing *backing); + #define PCMDS_PER_PAGE (PAGE_SIZE / sizeof(struct sgx_pcmd)) /* * 32 PCMD entries share a PCMD page. PCMD_FIRST_MASK is used to @@ -344,8 +347,11 @@ static vm_fault_t sgx_encl_eaug_page(struct vm_area_struct *vma, } va_page = sgx_encl_grow(encl, false); - if (IS_ERR(va_page)) + if (IS_ERR(va_page)) { + if (PTR_ERR(va_page) == -EBUSY) + vmret = VM_FAULT_NOPAGE; goto err_out_epc; + } if (va_page) list_add(&va_page->list, &encl->va_pages); @@ -906,15 +912,14 @@ const cpumask_t *sgx_encl_cpumask(struct sgx_encl *encl) static struct page *sgx_encl_get_backing_page(struct sgx_encl *encl, pgoff_t index) { - struct inode *inode = encl->backing->f_path.dentry->d_inode; - struct address_space *mapping = inode->i_mapping; + struct address_space *mapping = encl->backing->f_mapping; gfp_t gfpmask = mapping_gfp_mask(mapping); return shmem_read_mapping_page_gfp(mapping, index, gfpmask); } /** - * sgx_encl_get_backing() - Pin the backing storage + * __sgx_encl_get_backing() - Pin the backing storage * @encl: an enclave pointer * @page_index: enclave page index * @backing: data for accessing backing storage for the page @@ -926,7 +931,7 @@ static struct page *sgx_encl_get_backing_page(struct sgx_encl *encl, * 0 on success, * -errno otherwise. */ -static int sgx_encl_get_backing(struct sgx_encl *encl, unsigned long page_index, +static int __sgx_encl_get_backing(struct sgx_encl *encl, unsigned long page_index, struct sgx_backing *backing) { pgoff_t page_pcmd_off = sgx_encl_get_backing_page_pcmd_offset(encl, page_index); @@ -1001,7 +1006,7 @@ static struct mem_cgroup *sgx_encl_get_mem_cgroup(struct sgx_encl *encl) } /** - * sgx_encl_alloc_backing() - allocate a new backing storage page + * sgx_encl_alloc_backing() - create a new backing storage page * @encl: an enclave pointer * @page_index: enclave page index * @backing: data for accessing backing storage for the page @@ -1009,7 +1014,9 @@ static struct mem_cgroup *sgx_encl_get_mem_cgroup(struct sgx_encl *encl) * When called from ksgxd, sets the active memcg from one of the * mms in the enclave's mm_list prior to any backing page allocation, * in order to ensure that shmem page allocations are charged to the - * enclave. + * enclave. Create a backing page for loading data back into an EPC page with + * ELDU. This function takes a reference on a new backing page which + * must be dropped with a corresponding call to sgx_encl_put_backing(). * * Return: * 0 on success, @@ -1022,7 +1029,7 @@ int sgx_encl_alloc_backing(struct sgx_encl *encl, unsigned long page_index, struct mem_cgroup *memcg = set_active_memcg(encl_memcg); int ret; - ret = sgx_encl_get_backing(encl, page_index, backing); + ret = __sgx_encl_get_backing(encl, page_index, backing); set_active_memcg(memcg); mem_cgroup_put(encl_memcg); @@ -1040,15 +1047,17 @@ int sgx_encl_alloc_backing(struct sgx_encl *encl, unsigned long page_index, * It is the caller's responsibility to ensure that it is appropriate to use * sgx_encl_lookup_backing() rather than sgx_encl_alloc_backing(). If lookup is * not used correctly, this will cause an allocation which is not accounted for. + * This function takes a reference on an existing backing page which must be + * dropped with a corresponding call to sgx_encl_put_backing(). * * Return: * 0 on success, * -errno otherwise. */ -int sgx_encl_lookup_backing(struct sgx_encl *encl, unsigned long page_index, +static int sgx_encl_lookup_backing(struct sgx_encl *encl, unsigned long page_index, struct sgx_backing *backing) { - return sgx_encl_get_backing(encl, page_index, backing); + return __sgx_encl_get_backing(encl, page_index, backing); } /** diff --git a/arch/x86/kernel/cpu/sgx/encl.h b/arch/x86/kernel/cpu/sgx/encl.h index a65a952116fd..f94ff14c9486 100644 --- a/arch/x86/kernel/cpu/sgx/encl.h +++ b/arch/x86/kernel/cpu/sgx/encl.h @@ -107,8 +107,6 @@ bool current_is_ksgxd(void); void sgx_encl_release(struct kref *ref); int sgx_encl_mm_add(struct sgx_encl *encl, struct mm_struct *mm); const cpumask_t *sgx_encl_cpumask(struct sgx_encl *encl); -int sgx_encl_lookup_backing(struct sgx_encl *encl, unsigned long page_index, - struct sgx_backing *backing); int sgx_encl_alloc_backing(struct sgx_encl *encl, unsigned long page_index, struct sgx_backing *backing); void sgx_encl_put_backing(struct sgx_backing *backing); diff --git a/arch/x86/kernel/cpu/sgx/ioctl.c b/arch/x86/kernel/cpu/sgx/ioctl.c index ebe79d60619f..da8b8ea6b063 100644 --- a/arch/x86/kernel/cpu/sgx/ioctl.c +++ b/arch/x86/kernel/cpu/sgx/ioctl.c @@ -356,6 +356,9 @@ static int sgx_validate_offset_length(struct sgx_encl *encl, if (!length || !IS_ALIGNED(length, PAGE_SIZE)) return -EINVAL; + if (offset + length < offset) + return -EINVAL; + if (offset + length - PAGE_SIZE >= encl->size) return -EINVAL; diff --git a/arch/x86/kernel/cpu/sgx/main.c b/arch/x86/kernel/cpu/sgx/main.c index 515e2a5f25bb..0aad028f04d4 100644 --- a/arch/x86/kernel/cpu/sgx/main.c +++ b/arch/x86/kernel/cpu/sgx/main.c @@ -49,9 +49,13 @@ static LIST_HEAD(sgx_dirty_page_list); * Reset post-kexec EPC pages to the uninitialized state. The pages are removed * from the input list, and made available for the page allocator. SECS pages * prepending their children in the input list are left intact. + * + * Return 0 when sanitization was successful or kthread was stopped, and the + * number of unsanitized pages otherwise. */ -static void __sgx_sanitize_pages(struct list_head *dirty_page_list) +static unsigned long __sgx_sanitize_pages(struct list_head *dirty_page_list) { + unsigned long left_dirty = 0; struct sgx_epc_page *page; LIST_HEAD(dirty); int ret; @@ -59,7 +63,7 @@ static void __sgx_sanitize_pages(struct list_head *dirty_page_list) /* dirty_page_list is thread-local, no need for a lock: */ while (!list_empty(dirty_page_list)) { if (kthread_should_stop()) - return; + return 0; page = list_first_entry(dirty_page_list, struct sgx_epc_page, list); @@ -92,12 +96,14 @@ static void __sgx_sanitize_pages(struct list_head *dirty_page_list) } else { /* The page is not yet clean - move to the dirty list. */ list_move_tail(&page->list, &dirty); + left_dirty++; } cond_resched(); } list_splice(&dirty, dirty_page_list); + return left_dirty; } static bool sgx_reclaimer_age(struct sgx_epc_page *epc_page) @@ -395,10 +401,7 @@ static int ksgxd(void *p) * required for SECS pages, whose child pages blocked EREMOVE. */ __sgx_sanitize_pages(&sgx_dirty_page_list); - __sgx_sanitize_pages(&sgx_dirty_page_list); - - /* sanity check: */ - WARN_ON(!list_empty(&sgx_dirty_page_list)); + WARN_ON(__sgx_sanitize_pages(&sgx_dirty_page_list)); while (!kthread_should_stop()) { if (try_to_freeze()) diff --git a/arch/x86/kernel/cpu/topology.c b/arch/x86/kernel/cpu/topology.c index 132a2de44d2f..5e868b62a7c4 100644 --- a/arch/x86/kernel/cpu/topology.c +++ b/arch/x86/kernel/cpu/topology.c @@ -96,6 +96,7 @@ int detect_extended_topology(struct cpuinfo_x86 *c) unsigned int ht_mask_width, core_plus_mask_width, die_plus_mask_width; unsigned int core_select_mask, core_level_siblings; unsigned int die_select_mask, die_level_siblings; + unsigned int pkg_mask_width; bool die_level_present = false; int leaf; @@ -111,10 +112,10 @@ int detect_extended_topology(struct cpuinfo_x86 *c) core_level_siblings = smp_num_siblings = LEVEL_MAX_SIBLINGS(ebx); core_plus_mask_width = ht_mask_width = BITS_SHIFT_NEXT_LEVEL(eax); die_level_siblings = LEVEL_MAX_SIBLINGS(ebx); - die_plus_mask_width = BITS_SHIFT_NEXT_LEVEL(eax); + pkg_mask_width = die_plus_mask_width = BITS_SHIFT_NEXT_LEVEL(eax); sub_index = 1; - do { + while (true) { cpuid_count(leaf, sub_index, &eax, &ebx, &ecx, &edx); /* @@ -132,10 +133,15 @@ int detect_extended_topology(struct cpuinfo_x86 *c) die_plus_mask_width = BITS_SHIFT_NEXT_LEVEL(eax); } + if (LEAFB_SUBTYPE(ecx) != INVALID_TYPE) + pkg_mask_width = BITS_SHIFT_NEXT_LEVEL(eax); + else + break; + sub_index++; - } while (LEAFB_SUBTYPE(ecx) != INVALID_TYPE); + } - core_select_mask = (~(-1 << core_plus_mask_width)) >> ht_mask_width; + core_select_mask = (~(-1 << pkg_mask_width)) >> ht_mask_width; die_select_mask = (~(-1 << die_plus_mask_width)) >> core_plus_mask_width; @@ -148,7 +154,7 @@ int detect_extended_topology(struct cpuinfo_x86 *c) } c->phys_proc_id = apic->phys_pkg_id(c->initial_apicid, - die_plus_mask_width); + pkg_mask_width); /* * Reinit the apicid, now that we have extended initial_apicid. */ diff --git a/arch/x86/kernel/cpu/tsx.c b/arch/x86/kernel/cpu/tsx.c index ec7bbac3a9f2..8009c8346d8f 100644 --- a/arch/x86/kernel/cpu/tsx.c +++ b/arch/x86/kernel/cpu/tsx.c @@ -58,24 +58,6 @@ static void tsx_enable(void) wrmsrl(MSR_IA32_TSX_CTRL, tsx); } -static bool tsx_ctrl_is_supported(void) -{ - u64 ia32_cap = x86_read_arch_cap_msr(); - - /* - * TSX is controlled via MSR_IA32_TSX_CTRL. However, support for this - * MSR is enumerated by ARCH_CAP_TSX_MSR bit in MSR_IA32_ARCH_CAPABILITIES. - * - * TSX control (aka MSR_IA32_TSX_CTRL) is only available after a - * microcode update on CPUs that have their MSR_IA32_ARCH_CAPABILITIES - * bit MDS_NO=1. CPUs with MDS_NO=0 are not planned to get - * MSR_IA32_TSX_CTRL support even after a microcode update. Thus, - * tsx= cmdline requests will do nothing on CPUs without - * MSR_IA32_TSX_CTRL support. - */ - return !!(ia32_cap & ARCH_CAP_TSX_CTRL_MSR); -} - static enum tsx_ctrl_states x86_get_tsx_auto_mode(void) { if (boot_cpu_has_bug(X86_BUG_TAA)) @@ -135,7 +117,7 @@ static void tsx_clear_cpuid(void) rdmsrl(MSR_TSX_FORCE_ABORT, msr); msr |= MSR_TFA_TSX_CPUID_CLEAR; wrmsrl(MSR_TSX_FORCE_ABORT, msr); - } else if (tsx_ctrl_is_supported()) { + } else if (cpu_feature_enabled(X86_FEATURE_MSR_TSX_CTRL)) { rdmsrl(MSR_IA32_TSX_CTRL, msr); msr |= TSX_CTRL_CPUID_CLEAR; wrmsrl(MSR_IA32_TSX_CTRL, msr); @@ -158,7 +140,8 @@ static void tsx_dev_mode_disable(void) u64 mcu_opt_ctrl; /* Check if RTM_ALLOW exists */ - if (!boot_cpu_has_bug(X86_BUG_TAA) || !tsx_ctrl_is_supported() || + if (!boot_cpu_has_bug(X86_BUG_TAA) || + !cpu_feature_enabled(X86_FEATURE_MSR_TSX_CTRL) || !cpu_feature_enabled(X86_FEATURE_SRBDS_CTRL)) return; @@ -191,7 +174,20 @@ void __init tsx_init(void) return; } - if (!tsx_ctrl_is_supported()) { + /* + * TSX is controlled via MSR_IA32_TSX_CTRL. However, support for this + * MSR is enumerated by ARCH_CAP_TSX_MSR bit in MSR_IA32_ARCH_CAPABILITIES. + * + * TSX control (aka MSR_IA32_TSX_CTRL) is only available after a + * microcode update on CPUs that have their MSR_IA32_ARCH_CAPABILITIES + * bit MDS_NO=1. CPUs with MDS_NO=0 are not planned to get + * MSR_IA32_TSX_CTRL support even after a microcode update. Thus, + * tsx= cmdline requests will do nothing on CPUs without + * MSR_IA32_TSX_CTRL support. + */ + if (x86_read_arch_cap_msr() & ARCH_CAP_TSX_CTRL_MSR) { + setup_force_cpu_cap(X86_FEATURE_MSR_TSX_CTRL); + } else { tsx_ctrl_state = TSX_CTRL_NOT_SUPPORTED; return; } diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index afae4dd77495..0bf6779187dd 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -128,7 +128,7 @@ void show_opcodes(struct pt_regs *regs, const char *loglvl) /* No access to the user space stack of other tasks. Ignore. */ break; default: - printk("%sCode: Unable to access opcode bytes at RIP 0x%lx.\n", + printk("%sCode: Unable to access opcode bytes at 0x%lx.\n", loglvl, prologue); break; } @@ -177,6 +177,12 @@ static void show_regs_if_on_stack(struct stack_info *info, struct pt_regs *regs, } } +/* + * This function reads pointers from the stack and dereferences them. The + * pointers may not have their KMSAN shadow set up properly, which may result + * in false positive reports. Disable instrumentation to avoid those. + */ +__no_kmsan_checks static void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs, unsigned long *stack, const char *log_lvl) { diff --git a/arch/x86/kernel/early_printk.c b/arch/x86/kernel/early_printk.c index 68b38925a74f..44f937015e1e 100644 --- a/arch/x86/kernel/early_printk.c +++ b/arch/x86/kernel/early_printk.c @@ -264,11 +264,11 @@ static __init void early_pci_serial_init(char *s) bar0 = read_pci_config(bus, slot, func, PCI_BASE_ADDRESS_0); /* - * Verify it is a UART type device + * Verify it is a 16550-UART type device */ if (((classcode >> 16 != PCI_CLASS_COMMUNICATION_MODEM) && (classcode >> 16 != PCI_CLASS_COMMUNICATION_SERIAL)) || - (((classcode >> 8) & 0xff) != 0x02)) /* 16550 I/F at BAR0 */ { + (((classcode >> 8) & 0xff) != PCI_SERIAL_16550_COMPATIBLE)) { if (!force) return; } @@ -276,22 +276,22 @@ static __init void early_pci_serial_init(char *s) /* * Determine if it is IO or memory mapped */ - if (bar0 & 0x01) { + if ((bar0 & PCI_BASE_ADDRESS_SPACE) == PCI_BASE_ADDRESS_SPACE_IO) { /* it is IO mapped */ serial_in = io_serial_in; serial_out = io_serial_out; - early_serial_base = bar0&0xfffffffc; + early_serial_base = bar0 & PCI_BASE_ADDRESS_IO_MASK; write_pci_config(bus, slot, func, PCI_COMMAND, - cmdreg|PCI_COMMAND_IO); + cmdreg|PCI_COMMAND_IO); } else { /* It is memory mapped - assume 32-bit alignment */ serial_in = mem32_serial_in; serial_out = mem32_serial_out; /* WARNING! assuming the address is always in the first 4G */ early_serial_base = - (unsigned long)early_ioremap(bar0 & 0xfffffff0, 0x10); + (unsigned long)early_ioremap(bar0 & PCI_BASE_ADDRESS_MEM_MASK, 0x10); write_pci_config(bus, slot, func, PCI_COMMAND, - cmdreg|PCI_COMMAND_MEMORY); + cmdreg|PCI_COMMAND_MEMORY); } /* diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index 3b28c5b25e12..d00db56a8868 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -605,9 +605,9 @@ int fpu_clone(struct task_struct *dst, unsigned long clone_flags, bool minimal) if (test_thread_flag(TIF_NEED_FPU_LOAD)) fpregs_restore_userregs(); save_fpregs_to_fpstate(dst_fpu); + fpregs_unlock(); if (!(clone_flags & CLONE_THREAD)) fpu_inherit_perms(dst_fpu); - fpregs_unlock(); /* * Children never inherit PASID state. diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c index 621f4b6cac4a..8946f89761cc 100644 --- a/arch/x86/kernel/fpu/init.c +++ b/arch/x86/kernel/fpu/init.c @@ -210,13 +210,6 @@ static void __init fpu__init_system_xstate_size_legacy(void) fpstate_reset(¤t->thread.fpu); } -static void __init fpu__init_init_fpstate(void) -{ - /* Bring init_fpstate size and features up to date */ - init_fpstate.size = fpu_kernel_cfg.max_size; - init_fpstate.xfeatures = fpu_kernel_cfg.max_features; -} - /* * Called on the boot CPU once per system bootup, to set up the initial * FPU state that is later cloned into all processes: @@ -236,5 +229,4 @@ void __init fpu__init_system(struct cpuinfo_x86 *c) fpu__init_system_xstate_size_legacy(); fpu__init_system_xstate(fpu_kernel_cfg.max_size); fpu__init_task_struct_size(); - fpu__init_init_fpstate(); } diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index c8340156bfd2..59e543b95a3c 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -360,7 +360,7 @@ static void __init setup_init_fpu_buf(void) print_xstate_features(); - xstate_init_xcomp_bv(&init_fpstate.regs.xsave, fpu_kernel_cfg.max_features); + xstate_init_xcomp_bv(&init_fpstate.regs.xsave, init_fpstate.xfeatures); /* * Init all the features state with header.xfeatures being 0x0 @@ -678,20 +678,6 @@ static unsigned int __init get_xsave_size_user(void) return ebx; } -/* - * Will the runtime-enumerated 'xstate_size' fit in the init - * task's statically-allocated buffer? - */ -static bool __init is_supported_xstate_size(unsigned int test_xstate_size) -{ - if (test_xstate_size <= sizeof(init_fpstate.regs)) - return true; - - pr_warn("x86/fpu: xstate buffer too small (%zu < %d), disabling xsave\n", - sizeof(init_fpstate.regs), test_xstate_size); - return false; -} - static int __init init_xstate_size(void) { /* Recompute the context size for enabled features: */ @@ -717,10 +703,6 @@ static int __init init_xstate_size(void) kernel_default_size = xstate_calculate_size(fpu_kernel_cfg.default_features, compacted); - /* Ensure we have the space to store all default enabled features. */ - if (!is_supported_xstate_size(kernel_default_size)) - return -EINVAL; - if (!paranoid_xstate_size_valid(kernel_size)) return -EINVAL; @@ -875,6 +857,19 @@ void __init fpu__init_system_xstate(unsigned int legacy_size) update_regset_xstate_info(fpu_user_cfg.max_size, fpu_user_cfg.max_features); + /* + * init_fpstate excludes dynamic states as they are large but init + * state is zero. + */ + init_fpstate.size = fpu_kernel_cfg.default_size; + init_fpstate.xfeatures = fpu_kernel_cfg.default_features; + + if (init_fpstate.size > sizeof(init_fpstate.regs)) { + pr_warn("x86/fpu: init_fpstate buffer too small (%zu < %d), disabling XSAVE\n", + sizeof(init_fpstate.regs), init_fpstate.size); + goto out_disable; + } + setup_init_fpu_buf(); /* @@ -1130,6 +1125,15 @@ void __copy_xstate_to_uabi_buf(struct membuf to, struct fpstate *fpstate, */ mask = fpstate->user_xfeatures; + /* + * Dynamic features are not present in init_fpstate. When they are + * in an all zeros init state, remove those from 'mask' to zero + * those features in the user buffer instead of retrieving them + * from init_fpstate. + */ + if (fpu_state_size_dynamic()) + mask &= (header.xfeatures | xinit->header.xcomp_bv); + for_each_extended_xfeature(i, mask) { /* * If there was a feature or alignment gap, zero the space diff --git a/arch/x86/kernel/ftrace_64.S b/arch/x86/kernel/ftrace_64.S index dfeb227de561..2a4be92fd144 100644 --- a/arch/x86/kernel/ftrace_64.S +++ b/arch/x86/kernel/ftrace_64.S @@ -4,6 +4,7 @@ */ #include <linux/linkage.h> +#include <linux/cfi_types.h> #include <asm/ptrace.h> #include <asm/ftrace.h> #include <asm/export.h> @@ -129,6 +130,14 @@ .endm +SYM_TYPED_FUNC_START(ftrace_stub) + RET +SYM_FUNC_END(ftrace_stub) + +SYM_TYPED_FUNC_START(ftrace_stub_graph) + RET +SYM_FUNC_END(ftrace_stub_graph) + #ifdef CONFIG_DYNAMIC_FTRACE SYM_FUNC_START(__fentry__) @@ -172,21 +181,10 @@ SYM_INNER_LABEL(ftrace_call, SYM_L_GLOBAL) */ SYM_INNER_LABEL(ftrace_caller_end, SYM_L_GLOBAL) ANNOTATE_NOENDBR - - jmp ftrace_epilogue + RET SYM_FUNC_END(ftrace_caller); STACK_FRAME_NON_STANDARD_FP(ftrace_caller) -SYM_FUNC_START(ftrace_epilogue) -/* - * This is weak to keep gas from relaxing the jumps. - */ -SYM_INNER_LABEL_ALIGN(ftrace_stub, SYM_L_WEAK) - UNWIND_HINT_FUNC - ENDBR - RET -SYM_FUNC_END(ftrace_epilogue) - SYM_FUNC_START(ftrace_regs_caller) /* Save the current flags before any operations that can change them */ pushfq @@ -262,14 +260,11 @@ SYM_INNER_LABEL(ftrace_regs_caller_jmp, SYM_L_GLOBAL) popfq /* - * As this jmp to ftrace_epilogue can be a short jump - * it must not be copied into the trampoline. - * The trampoline will add the code to jump - * to the return. + * The trampoline will add the return. */ SYM_INNER_LABEL(ftrace_regs_caller_end, SYM_L_GLOBAL) ANNOTATE_NOENDBR - jmp ftrace_epilogue + RET /* Swap the flags with orig_rax */ 1: movq MCOUNT_REG_SIZE(%rsp), %rdi @@ -280,7 +275,7 @@ SYM_INNER_LABEL(ftrace_regs_caller_end, SYM_L_GLOBAL) /* Restore flags */ popfq UNWIND_HINT_FUNC - jmp ftrace_epilogue + RET SYM_FUNC_END(ftrace_regs_caller) STACK_FRAME_NON_STANDARD_FP(ftrace_regs_caller) @@ -291,9 +286,6 @@ STACK_FRAME_NON_STANDARD_FP(ftrace_regs_caller) SYM_FUNC_START(__fentry__) cmpq $ftrace_stub, ftrace_trace_function jnz trace - -SYM_INNER_LABEL(ftrace_stub, SYM_L_GLOBAL) - ENDBR RET trace: diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c index e5dd6da78713..01833ebf5e8e 100644 --- a/arch/x86/kernel/irq_32.c +++ b/arch/x86/kernel/irq_32.c @@ -132,7 +132,7 @@ int irq_init_percpu_irqstack(unsigned int cpu) return 0; } -#ifndef CONFIG_PREEMPT_RT +#ifdef CONFIG_SOFTIRQ_ON_OWN_STACK void do_softirq_own_stack(void) { struct irq_stack *irqstk; diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index 74167dc5f55e..eb8bc82846b9 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -59,8 +59,6 @@ DEFINE_PER_CPU(struct kprobe *, current_kprobe) = NULL; DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk); -#define stack_addr(regs) ((unsigned long *)regs->sp) - #define W(row, b0, b1, b2, b3, b4, b5, b6, b7, b8, b9, ba, bb, bc, bd, be, bf)\ (((b0##UL << 0x0)|(b1##UL << 0x1)|(b2##UL << 0x2)|(b3##UL << 0x3) | \ (b4##UL << 0x4)|(b5##UL << 0x5)|(b6##UL << 0x6)|(b7##UL << 0x7) | \ @@ -505,7 +503,7 @@ static void kprobe_emulate_jcc(struct kprobe *p, struct pt_regs *regs) match = ((regs->flags & X86_EFLAGS_SF) >> X86_EFLAGS_SF_BIT) ^ ((regs->flags & X86_EFLAGS_OF) >> X86_EFLAGS_OF_BIT); if (p->ainsn.jcc.type >= 0xe) - match = match && (regs->flags & X86_EFLAGS_ZF); + match = match || (regs->flags & X86_EFLAGS_ZF); } __kprobe_emulate_jmp(p, regs, (match && !invert) || (!match && invert)); } diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c index b1abf663417c..c032edcd3d95 100644 --- a/arch/x86/kernel/module.c +++ b/arch/x86/kernel/module.c @@ -53,7 +53,7 @@ static unsigned long int get_module_load_offset(void) */ if (module_load_offset == 0) module_load_offset = - (get_random_int() % 1024 + 1) * PAGE_SIZE; + (prandom_u32_max(1024) + 1) * PAGE_SIZE; mutex_unlock(&module_kaslr_mutex); } return module_load_offset; diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 58a6ea472db9..c21b7347a26d 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -965,7 +965,7 @@ early_param("idle", idle_setup); unsigned long arch_align_stack(unsigned long sp) { if (!(current->personality & ADDR_NO_RANDOMIZE) && randomize_va_space) - sp -= get_random_int() % 8192; + sp -= prandom_u32_max(8192); return sp & ~0xf; } diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 1962008fe743..6b3418bff326 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -553,6 +553,7 @@ void compat_start_thread(struct pt_regs *regs, u32 new_ip, u32 new_sp, bool x32) * Kprobes not supported here. Set the probe on schedule instead. * Function graph tracer not supported too. */ +__no_kmsan_checks __visible __notrace_funcgraph struct task_struct * __switch_to(struct task_struct *prev_p, struct task_struct *next_p) { diff --git a/arch/x86/kernel/rtc.c b/arch/x86/kernel/rtc.c index 586f718b8e95..349046434513 100644 --- a/arch/x86/kernel/rtc.c +++ b/arch/x86/kernel/rtc.c @@ -4,11 +4,8 @@ */ #include <linux/platform_device.h> #include <linux/mc146818rtc.h> -#include <linux/acpi.h> -#include <linux/bcd.h> #include <linux/export.h> #include <linux/pnp.h> -#include <linux/of.h> #include <asm/vsyscall.h> #include <asm/x86_init.h> @@ -20,26 +17,23 @@ /* * This is a special lock that is owned by the CPU and holds the index * register we are working with. It is required for NMI access to the - * CMOS/RTC registers. See include/asm-i386/mc146818rtc.h for details. + * CMOS/RTC registers. See arch/x86/include/asm/mc146818rtc.h for details. */ volatile unsigned long cmos_lock; EXPORT_SYMBOL(cmos_lock); #endif /* CONFIG_X86_32 */ -/* For two digit years assume time is always after that */ -#define CMOS_YEARS_OFFS 2000 - DEFINE_SPINLOCK(rtc_lock); EXPORT_SYMBOL(rtc_lock); /* - * In order to set the CMOS clock precisely, set_rtc_mmss has to be + * In order to set the CMOS clock precisely, mach_set_cmos_time has to be * called 500 ms after the second nowtime has started, because when * nowtime is written into the registers of the CMOS clock, it will * jump to the next second precisely 500 ms later. Check the Motorola * MC146818A or Dallas DS12887 data sheet for details. */ -int mach_set_rtc_mmss(const struct timespec64 *now) +int mach_set_cmos_time(const struct timespec64 *now) { unsigned long long nowtime = now->tv_sec; struct rtc_time tm; @@ -62,8 +56,7 @@ int mach_set_rtc_mmss(const struct timespec64 *now) void mach_get_cmos_time(struct timespec64 *now) { - unsigned int status, year, mon, day, hour, min, sec, century = 0; - unsigned long flags; + struct rtc_time tm; /* * If pm_trace abused the RTC as storage, set the timespec to 0, @@ -74,51 +67,13 @@ void mach_get_cmos_time(struct timespec64 *now) return; } - spin_lock_irqsave(&rtc_lock, flags); - - /* - * If UIP is clear, then we have >= 244 microseconds before - * RTC registers will be updated. Spec sheet says that this - * is the reliable way to read RTC - registers. If UIP is set - * then the register access might be invalid. - */ - while ((CMOS_READ(RTC_FREQ_SELECT) & RTC_UIP)) - cpu_relax(); - - sec = CMOS_READ(RTC_SECONDS); - min = CMOS_READ(RTC_MINUTES); - hour = CMOS_READ(RTC_HOURS); - day = CMOS_READ(RTC_DAY_OF_MONTH); - mon = CMOS_READ(RTC_MONTH); - year = CMOS_READ(RTC_YEAR); - -#ifdef CONFIG_ACPI - if (acpi_gbl_FADT.header.revision >= FADT2_REVISION_ID && - acpi_gbl_FADT.century) - century = CMOS_READ(acpi_gbl_FADT.century); -#endif - - status = CMOS_READ(RTC_CONTROL); - WARN_ON_ONCE(RTC_ALWAYS_BCD && (status & RTC_DM_BINARY)); - - spin_unlock_irqrestore(&rtc_lock, flags); - - if (RTC_ALWAYS_BCD || !(status & RTC_DM_BINARY)) { - sec = bcd2bin(sec); - min = bcd2bin(min); - hour = bcd2bin(hour); - day = bcd2bin(day); - mon = bcd2bin(mon); - year = bcd2bin(year); + if (mc146818_get_time(&tm)) { + pr_err("Unable to read current time from RTC\n"); + now->tv_sec = now->tv_nsec = 0; + return; } - if (century) { - century = bcd2bin(century); - year += century * 100; - } else - year += CMOS_YEARS_OFFS; - - now->tv_sec = mktime64(year, mon, day, hour, min, sec); + now->tv_sec = rtc_tm_to_time64(&tm); now->tv_nsec = 0; } diff --git a/arch/x86/kernel/sev.c b/arch/x86/kernel/sev.c index 63dc626627a0..a428c62330d3 100644 --- a/arch/x86/kernel/sev.c +++ b/arch/x86/kernel/sev.c @@ -701,7 +701,13 @@ e_term: void __init early_snp_set_memory_private(unsigned long vaddr, unsigned long paddr, unsigned int npages) { - if (!cc_platform_has(CC_ATTR_GUEST_SEV_SNP)) + /* + * This can be invoked in early boot while running identity mapped, so + * use an open coded check for SNP instead of using cc_platform_has(). + * This eliminates worries about jump tables or checking boot_cpu_data + * in the cc_platform_has() function. + */ + if (!(sev_status & MSR_AMD64_SEV_SNP_ENABLED)) return; /* @@ -717,7 +723,13 @@ void __init early_snp_set_memory_private(unsigned long vaddr, unsigned long padd void __init early_snp_set_memory_shared(unsigned long vaddr, unsigned long paddr, unsigned int npages) { - if (!cc_platform_has(CC_ATTR_GUEST_SEV_SNP)) + /* + * This can be invoked in early boot while running identity mapped, so + * use an open coded check for SNP instead of using cc_platform_has(). + * This eliminates worries about jump tables or checking boot_cpu_data + * in the cc_platform_has() function. + */ + if (!(sev_status & MSR_AMD64_SEV_SNP_ENABLED)) return; /* Invalidate the memory pages before they are marked shared in the RMP table. */ @@ -2100,7 +2112,7 @@ bool __init snp_init(struct boot_params *bp) return true; } -void __init snp_abort(void) +void __init __noreturn snp_abort(void) { sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SNP_UNSUPPORTED); } diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index f24227bc3220..3f3ea0287f69 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -1316,7 +1316,7 @@ static void __init smp_sanity_check(void) nr++; } - nr_cpu_ids = 8; + set_nr_cpu_ids(8); } #endif @@ -1569,7 +1569,7 @@ __init void prefill_possible_map(void) possible = i; } - nr_cpu_ids = possible; + set_nr_cpu_ids(possible); pr_info("Allowing %d CPUs, %d hotplug CPUs\n", possible, max_t(int, possible - num_processors, 0)); diff --git a/arch/x86/kernel/tboot.c b/arch/x86/kernel/tboot.c index 3bacd935f840..4c1bcb6053fc 100644 --- a/arch/x86/kernel/tboot.c +++ b/arch/x86/kernel/tboot.c @@ -95,7 +95,7 @@ void __init tboot_probe(void) static pgd_t *tboot_pg_dir; static struct mm_struct tboot_mm = { - .mm_rb = RB_ROOT, + .mm_mt = MTREE_INIT_EXT(mm_mt, MM_MT_FLAGS, tboot_mm.mmap_lock), .pgd = swapper_pg_dir, .mm_users = ATOMIC_INIT(2), .mm_count = ATOMIC_INIT(1), diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index d62b2cb85cea..d3fdec706f1d 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -15,6 +15,7 @@ #include <linux/context_tracking.h> #include <linux/interrupt.h> #include <linux/kallsyms.h> +#include <linux/kmsan.h> #include <linux/spinlock.h> #include <linux/kprobes.h> #include <linux/uaccess.h> @@ -63,6 +64,7 @@ #include <asm/insn-eval.h> #include <asm/vdso.h> #include <asm/tdx.h> +#include <asm/cfi.h> #ifdef CONFIG_X86_64 #include <asm/x86_init.h> @@ -300,6 +302,12 @@ static noinstr bool handle_bug(struct pt_regs *regs) { bool handled = false; + /* + * Normally @regs are unpoisoned by irqentry_enter(), but handle_bug() + * is a rare case that uses @regs without passing them to + * irqentry_enter(). + */ + kmsan_unpoison_entry_regs(regs); if (!is_valid_bugaddr(regs->ip)) return handled; @@ -313,7 +321,8 @@ static noinstr bool handle_bug(struct pt_regs *regs) */ if (regs->flags & X86_EFLAGS_IF) raw_local_irq_enable(); - if (report_bug(regs->ip, regs) == BUG_TRAP_TYPE_WARN) { + if (report_bug(regs->ip, regs) == BUG_TRAP_TYPE_WARN || + handle_cfi_failure(regs) == BUG_TRAP_TYPE_WARN) { regs->ip += LEN_UD2; handled = true; } diff --git a/arch/x86/kernel/unwind_frame.c b/arch/x86/kernel/unwind_frame.c index 8e1c50c86e5d..d8ba93778ae3 100644 --- a/arch/x86/kernel/unwind_frame.c +++ b/arch/x86/kernel/unwind_frame.c @@ -183,6 +183,16 @@ static struct pt_regs *decode_frame_pointer(unsigned long *bp) } #endif +/* + * While walking the stack, KMSAN may stomp on stale locals from other + * functions that were marked as uninitialized upon function exit, and + * now hold the call frame information for the current function (e.g. the frame + * pointer). Because KMSAN does not specifically mark call frames as + * initialized, false positive reports are possible. To prevent such reports, + * we mark the functions scanning the stack (here and below) with + * __no_kmsan_checks. + */ +__no_kmsan_checks static bool update_stack_state(struct unwind_state *state, unsigned long *next_bp) { @@ -250,6 +260,7 @@ static bool update_stack_state(struct unwind_state *state, return true; } +__no_kmsan_checks bool unwind_next_frame(struct unwind_state *state) { struct pt_regs *regs; diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c index 38185aedf7d1..c059820dfaea 100644 --- a/arch/x86/kernel/unwind_orc.c +++ b/arch/x86/kernel/unwind_orc.c @@ -93,22 +93,27 @@ static struct orc_entry *orc_find(unsigned long ip); static struct orc_entry *orc_ftrace_find(unsigned long ip) { struct ftrace_ops *ops; - unsigned long caller; + unsigned long tramp_addr, offset; ops = ftrace_ops_trampoline(ip); if (!ops) return NULL; + /* Set tramp_addr to the start of the code copied by the trampoline */ if (ops->flags & FTRACE_OPS_FL_SAVE_REGS) - caller = (unsigned long)ftrace_regs_call; + tramp_addr = (unsigned long)ftrace_regs_caller; else - caller = (unsigned long)ftrace_call; + tramp_addr = (unsigned long)ftrace_caller; + + /* Now place tramp_addr to the location within the trampoline ip is at */ + offset = ip - ops->trampoline; + tramp_addr += offset; /* Prevent unlikely recursion */ - if (ip == caller) + if (ip == tramp_addr) return NULL; - return orc_find(caller); + return orc_find(tramp_addr); } #else static struct orc_entry *orc_ftrace_find(unsigned long ip) @@ -708,7 +713,7 @@ void __unwind_start(struct unwind_state *state, struct task_struct *task, /* Otherwise, skip ahead to the user-specified starting frame: */ while (!unwind_done(state) && (!on_stack(&state->stack_info, first_frame, sizeof(long)) || - state->sp < (unsigned long)first_frame)) + state->sp <= (unsigned long)first_frame)) unwind_next_frame(state); return; diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c index e84ee5cdbd8c..57353519bc11 100644 --- a/arch/x86/kernel/x86_init.c +++ b/arch/x86/kernel/x86_init.c @@ -138,7 +138,7 @@ struct x86_platform_ops x86_platform __ro_after_init = { .calibrate_cpu = native_calibrate_cpu_early, .calibrate_tsc = native_calibrate_tsc, .get_wallclock = mach_get_cmos_time, - .set_wallclock = mach_set_rtc_mmss, + .set_wallclock = mach_set_cmos_time, .iommu_shutdown = iommu_shutdown_noop, .is_untracked_pat_range = is_ISA_range, .nmi_init = default_nmi_init, diff --git a/arch/x86/kvm/.gitignore b/arch/x86/kvm/.gitignore new file mode 100644 index 000000000000..615d6ff35c00 --- /dev/null +++ b/arch/x86/kvm/.gitignore @@ -0,0 +1,2 @@ +/kvm-asm-offsets.s +/kvm-asm-offsets.h diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig index e3cbd7706136..67be7f217e37 100644 --- a/arch/x86/kvm/Kconfig +++ b/arch/x86/kvm/Kconfig @@ -28,7 +28,8 @@ config KVM select HAVE_KVM_IRQCHIP select HAVE_KVM_PFNCACHE select HAVE_KVM_IRQFD - select HAVE_KVM_DIRTY_RING + select HAVE_KVM_DIRTY_RING_TSO + select HAVE_KVM_DIRTY_RING_ACQ_REL select IRQ_BYPASS_MANAGER select HAVE_KVM_IRQ_BYPASS select HAVE_KVM_IRQ_ROUTING diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile index 30f244b64523..f453a0f96e24 100644 --- a/arch/x86/kvm/Makefile +++ b/arch/x86/kvm/Makefile @@ -34,3 +34,15 @@ endif obj-$(CONFIG_KVM) += kvm.o obj-$(CONFIG_KVM_INTEL) += kvm-intel.o obj-$(CONFIG_KVM_AMD) += kvm-amd.o + +AFLAGS_svm/vmenter.o := -iquote $(obj) +$(obj)/svm/vmenter.o: $(obj)/kvm-asm-offsets.h + +AFLAGS_vmx/vmenter.o := -iquote $(obj) +$(obj)/vmx/vmenter.o: $(obj)/kvm-asm-offsets.h + +$(obj)/kvm-asm-offsets.h: $(obj)/kvm-asm-offsets.s FORCE + $(call filechk,offsets,__KVM_ASM_OFFSETS_H__) + +targets += kvm-asm-offsets.s +clean-files += kvm-asm-offsets.h diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 75dcf7a72605..62bc7a01cecc 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -311,11 +311,19 @@ void kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu) } EXPORT_SYMBOL_GPL(kvm_update_cpuid_runtime); +static bool kvm_cpuid_has_hyperv(struct kvm_cpuid_entry2 *entries, int nent) +{ + struct kvm_cpuid_entry2 *entry; + + entry = cpuid_entry2_find(entries, nent, HYPERV_CPUID_INTERFACE, + KVM_CPUID_INDEX_NOT_SIGNIFICANT); + return entry && entry->eax == HYPERV_CPUID_SIGNATURE_EAX; +} + static void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) { struct kvm_lapic *apic = vcpu->arch.apic; struct kvm_cpuid_entry2 *best; - u64 guest_supported_xcr0; best = kvm_find_cpuid_entry(vcpu, 1); if (best && apic) { @@ -327,10 +335,16 @@ static void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) kvm_apic_set_version(vcpu); } - guest_supported_xcr0 = + vcpu->arch.guest_supported_xcr0 = cpuid_get_supported_xcr0(vcpu->arch.cpuid_entries, vcpu->arch.cpuid_nent); - vcpu->arch.guest_fpu.fpstate->user_xfeatures = guest_supported_xcr0; + /* + * FP+SSE can always be saved/restored via KVM_{G,S}ET_XSAVE, even if + * XSAVE/XCRO are not exposed to the guest, and even if XSAVE isn't + * supported by the host. + */ + vcpu->arch.guest_fpu.fpstate->user_xfeatures = vcpu->arch.guest_supported_xcr0 | + XFEATURE_MASK_FPSSE; kvm_update_pv_runtime(vcpu); @@ -341,7 +355,8 @@ static void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) vcpu->arch.cr4_guest_rsvd_bits = __cr4_reserved_bits(guest_cpuid_has, vcpu); - kvm_hv_set_cpuid(vcpu); + kvm_hv_set_cpuid(vcpu, kvm_cpuid_has_hyperv(vcpu->arch.cpuid_entries, + vcpu->arch.cpuid_nent)); /* Invoke the vendor callback only after the above state is updated. */ static_call(kvm_x86_vcpu_after_set_cpuid)(vcpu); @@ -404,6 +419,12 @@ static int kvm_set_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid_entry2 *e2, return 0; } + if (kvm_cpuid_has_hyperv(e2, nent)) { + r = kvm_hv_vcpu_init(vcpu); + if (r) + return r; + } + r = kvm_check_cpuid(vcpu, e2, nent); if (r) return r; @@ -897,8 +918,6 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) entry->edx = 0; } break; - case 9: - break; case 0xa: { /* Architectural Performance Monitoring */ union cpuid10_eax eax; union cpuid10_edx edx; @@ -1114,11 +1133,13 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) entry->eax = max(entry->eax, 0x80000021); break; case 0x80000001: + entry->ebx &= ~GENMASK(27, 16); cpuid_entry_override(entry, CPUID_8000_0001_EDX); cpuid_entry_override(entry, CPUID_8000_0001_ECX); break; case 0x80000006: - /* L2 cache and TLB: pass through host info. */ + /* Drop reserved bits, pass host L2 cache and TLB info. */ + entry->edx &= ~GENMASK(17, 16); break; case 0x80000007: /* Advanced power management */ /* invariant TSC is CPUID.80000007H:EDX[8] */ @@ -1148,6 +1169,7 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) g_phys_as = phys_as; entry->eax = g_phys_as | (virt_as << 8); + entry->ecx &= ~(GENMASK(31, 16) | GENMASK(11, 8)); entry->edx = 0; cpuid_entry_override(entry, CPUID_8000_0008_EBX); break; @@ -1167,6 +1189,9 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) entry->ecx = entry->edx = 0; break; case 0x8000001a: + entry->eax &= GENMASK(2, 0); + entry->ebx = entry->ecx = entry->edx = 0; + break; case 0x8000001e: break; case 0x8000001F: @@ -1174,7 +1199,8 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) entry->eax = entry->ebx = entry->ecx = entry->edx = 0; } else { cpuid_entry_override(entry, CPUID_8000_001F_EAX); - + /* Clear NumVMPL since KVM does not support VMPL. */ + entry->ebx &= ~GENMASK(31, 12); /* * Enumerate '0' for "PA bits reduction", the adjusted * MAXPHYADDR is enumerated directly (see 0x80000008). @@ -1312,7 +1338,7 @@ int kvm_dev_ioctl_get_cpuid(struct kvm_cpuid2 *cpuid, if (sanity_check_entries(entries, cpuid->nent, type)) return -EINVAL; - array.entries = kvcalloc(sizeof(struct kvm_cpuid_entry2), cpuid->nent, GFP_KERNEL); + array.entries = kvcalloc(cpuid->nent, sizeof(struct kvm_cpuid_entry2), GFP_KERNEL); if (!array.entries) return -ENOMEM; diff --git a/arch/x86/kvm/debugfs.c b/arch/x86/kvm/debugfs.c index cfed36aba2f7..c1390357126a 100644 --- a/arch/x86/kvm/debugfs.c +++ b/arch/x86/kvm/debugfs.c @@ -158,11 +158,16 @@ out: static int kvm_mmu_rmaps_stat_open(struct inode *inode, struct file *file) { struct kvm *kvm = inode->i_private; + int r; if (!kvm_get_kvm_safe(kvm)) return -ENOENT; - return single_open(file, kvm_mmu_rmaps_stat_show, kvm); + r = single_open(file, kvm_mmu_rmaps_stat_show, kvm); + if (r < 0) + kvm_put_kvm(kvm); + + return r; } static int kvm_mmu_rmaps_stat_release(struct inode *inode, struct file *file) diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index b4eeb7c75dfa..4a43261d25a2 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -326,7 +326,8 @@ static int fastop(struct x86_emulate_ctxt *ctxt, fastop_t fop); ".align " __stringify(FASTOP_SIZE) " \n\t" \ ".type " name ", @function \n\t" \ name ":\n\t" \ - ASM_ENDBR + ASM_ENDBR \ + IBT_NOSEAL(name) #define FOP_FUNC(name) \ __FOP_FUNC(#name) @@ -446,27 +447,12 @@ static int fastop(struct x86_emulate_ctxt *ctxt, fastop_t fop); FOP_END /* Special case for SETcc - 1 instruction per cc */ - -/* - * Depending on .config the SETcc functions look like: - * - * ENDBR [4 bytes; CONFIG_X86_KERNEL_IBT] - * SETcc %al [3 bytes] - * RET | JMP __x86_return_thunk [1,5 bytes; CONFIG_RETHUNK] - * INT3 [1 byte; CONFIG_SLS] - */ -#define SETCC_ALIGN 16 - #define FOP_SETCC(op) \ - ".align " __stringify(SETCC_ALIGN) " \n\t" \ - ".type " #op ", @function \n\t" \ - #op ": \n\t" \ - ASM_ENDBR \ + FOP_FUNC(op) \ #op " %al \n\t" \ - __FOP_RET(#op) \ - ".skip " __stringify(SETCC_ALIGN) " - (.-" #op "), 0xcc \n\t" + FOP_RET(op) -__FOP_START(setcc, SETCC_ALIGN) +FOP_START(setcc) FOP_SETCC(seto) FOP_SETCC(setno) FOP_SETCC(setc) @@ -493,7 +479,7 @@ FOP_END; /* * XXX: inoutclob user must know where the argument is being expanded. - * Relying on CONFIG_CC_HAS_ASM_GOTO would allow us to remove _fault. + * Using asm goto would allow us to remove _fault. */ #define asm_safe(insn, inoutclob...) \ ({ \ @@ -805,8 +791,7 @@ static int linearize(struct x86_emulate_ctxt *ctxt, ctxt->mode, linear); } -static inline int assign_eip(struct x86_emulate_ctxt *ctxt, ulong dst, - enum x86emul_mode mode) +static inline int assign_eip(struct x86_emulate_ctxt *ctxt, ulong dst) { ulong linear; int rc; @@ -816,41 +801,71 @@ static inline int assign_eip(struct x86_emulate_ctxt *ctxt, ulong dst, if (ctxt->op_bytes != sizeof(unsigned long)) addr.ea = dst & ((1UL << (ctxt->op_bytes << 3)) - 1); - rc = __linearize(ctxt, addr, &max_size, 1, false, true, mode, &linear); + rc = __linearize(ctxt, addr, &max_size, 1, false, true, ctxt->mode, &linear); if (rc == X86EMUL_CONTINUE) ctxt->_eip = addr.ea; return rc; } +static inline int emulator_recalc_and_set_mode(struct x86_emulate_ctxt *ctxt) +{ + u64 efer; + struct desc_struct cs; + u16 selector; + u32 base3; + + ctxt->ops->get_msr(ctxt, MSR_EFER, &efer); + + if (!(ctxt->ops->get_cr(ctxt, 0) & X86_CR0_PE)) { + /* Real mode. cpu must not have long mode active */ + if (efer & EFER_LMA) + return X86EMUL_UNHANDLEABLE; + ctxt->mode = X86EMUL_MODE_REAL; + return X86EMUL_CONTINUE; + } + + if (ctxt->eflags & X86_EFLAGS_VM) { + /* Protected/VM86 mode. cpu must not have long mode active */ + if (efer & EFER_LMA) + return X86EMUL_UNHANDLEABLE; + ctxt->mode = X86EMUL_MODE_VM86; + return X86EMUL_CONTINUE; + } + + if (!ctxt->ops->get_segment(ctxt, &selector, &cs, &base3, VCPU_SREG_CS)) + return X86EMUL_UNHANDLEABLE; + + if (efer & EFER_LMA) { + if (cs.l) { + /* Proper long mode */ + ctxt->mode = X86EMUL_MODE_PROT64; + } else if (cs.d) { + /* 32 bit compatibility mode*/ + ctxt->mode = X86EMUL_MODE_PROT32; + } else { + ctxt->mode = X86EMUL_MODE_PROT16; + } + } else { + /* Legacy 32 bit / 16 bit mode */ + ctxt->mode = cs.d ? X86EMUL_MODE_PROT32 : X86EMUL_MODE_PROT16; + } + + return X86EMUL_CONTINUE; +} + static inline int assign_eip_near(struct x86_emulate_ctxt *ctxt, ulong dst) { - return assign_eip(ctxt, dst, ctxt->mode); + return assign_eip(ctxt, dst); } -static int assign_eip_far(struct x86_emulate_ctxt *ctxt, ulong dst, - const struct desc_struct *cs_desc) +static int assign_eip_far(struct x86_emulate_ctxt *ctxt, ulong dst) { - enum x86emul_mode mode = ctxt->mode; - int rc; + int rc = emulator_recalc_and_set_mode(ctxt); -#ifdef CONFIG_X86_64 - if (ctxt->mode >= X86EMUL_MODE_PROT16) { - if (cs_desc->l) { - u64 efer = 0; + if (rc != X86EMUL_CONTINUE) + return rc; - ctxt->ops->get_msr(ctxt, MSR_EFER, &efer); - if (efer & EFER_LMA) - mode = X86EMUL_MODE_PROT64; - } else - mode = X86EMUL_MODE_PROT32; /* temporary value */ - } -#endif - if (mode == X86EMUL_MODE_PROT16 || mode == X86EMUL_MODE_PROT32) - mode = cs_desc->d ? X86EMUL_MODE_PROT32 : X86EMUL_MODE_PROT16; - rc = assign_eip(ctxt, dst, mode); - if (rc == X86EMUL_CONTINUE) - ctxt->mode = mode; - return rc; + return assign_eip(ctxt, dst); } static inline int jmp_rel(struct x86_emulate_ctxt *ctxt, int rel) @@ -1079,7 +1094,7 @@ static int em_bsr_c(struct x86_emulate_ctxt *ctxt) static __always_inline u8 test_cc(unsigned int condition, unsigned long flags) { u8 rc; - void (*fop)(void) = (void *)em_setcc + SETCC_ALIGN * (condition & 0xf); + void (*fop)(void) = (void *)em_setcc + FASTOP_SIZE * (condition & 0xf); flags = (flags & EFLAGS_MASK) | X86_EFLAGS_IF; asm("push %[flags]; popf; " CALL_NOSPEC @@ -1151,9 +1166,11 @@ static int em_fnstsw(struct x86_emulate_ctxt *ctxt) static void decode_register_operand(struct x86_emulate_ctxt *ctxt, struct operand *op) { - unsigned reg = ctxt->modrm_reg; + unsigned int reg; - if (!(ctxt->d & ModRM)) + if (ctxt->d & ModRM) + reg = ctxt->modrm_reg; + else reg = (ctxt->b & 7) | ((ctxt->rex_prefix & 1) << 3); if (ctxt->d & Sse) { @@ -1967,7 +1984,7 @@ static int em_pop_sreg(struct x86_emulate_ctxt *ctxt) if (rc != X86EMUL_CONTINUE) return rc; - if (ctxt->modrm_reg == VCPU_SREG_SS) + if (seg == VCPU_SREG_SS) ctxt->interruptibility = KVM_X86_SHADOW_INT_MOV_SS; if (ctxt->op_bytes > 2) rsp_increment(ctxt, ctxt->op_bytes - 2); @@ -2184,7 +2201,7 @@ static int em_jmp_far(struct x86_emulate_ctxt *ctxt) if (rc != X86EMUL_CONTINUE) return rc; - rc = assign_eip_far(ctxt, ctxt->src.val, &new_desc); + rc = assign_eip_far(ctxt, ctxt->src.val); /* Error handling is not implemented. */ if (rc != X86EMUL_CONTINUE) return X86EMUL_UNHANDLEABLE; @@ -2262,7 +2279,7 @@ static int em_ret_far(struct x86_emulate_ctxt *ctxt) &new_desc); if (rc != X86EMUL_CONTINUE) return rc; - rc = assign_eip_far(ctxt, eip, &new_desc); + rc = assign_eip_far(ctxt, eip); /* Error handling is not implemented. */ if (rc != X86EMUL_CONTINUE) return X86EMUL_UNHANDLEABLE; @@ -2444,7 +2461,7 @@ static int rsm_load_state_32(struct x86_emulate_ctxt *ctxt, ctxt->eflags = GET_SMSTATE(u32, smstate, 0x7ff4) | X86_EFLAGS_FIXED; ctxt->_eip = GET_SMSTATE(u32, smstate, 0x7ff0); - for (i = 0; i < NR_EMULATOR_GPRS; i++) + for (i = 0; i < 8; i++) *reg_write(ctxt, i) = GET_SMSTATE(u32, smstate, 0x7fd0 + i * 4); val = GET_SMSTATE(u32, smstate, 0x7fcc); @@ -2501,7 +2518,7 @@ static int rsm_load_state_64(struct x86_emulate_ctxt *ctxt, u16 selector; int i, r; - for (i = 0; i < NR_EMULATOR_GPRS; i++) + for (i = 0; i < 16; i++) *reg_write(ctxt, i) = GET_SMSTATE(u64, smstate, 0x7ff8 - i * 8); ctxt->_eip = GET_SMSTATE(u64, smstate, 0x7f78); @@ -2645,7 +2662,7 @@ static int em_rsm(struct x86_emulate_ctxt *ctxt) * those side effects need to be explicitly handled for both success * and shutdown. */ - return X86EMUL_CONTINUE; + return emulator_recalc_and_set_mode(ctxt); emulate_shutdown: ctxt->ops->triple_fault(ctxt); @@ -2888,6 +2905,7 @@ static int em_sysexit(struct x86_emulate_ctxt *ctxt) ops->set_segment(ctxt, ss_sel, &ss, 0, VCPU_SREG_SS); ctxt->_eip = rdx; + ctxt->mode = usermode; *reg_write(ctxt, VCPU_REGS_RSP) = rcx; return X86EMUL_CONTINUE; @@ -3481,7 +3499,7 @@ static int em_call_far(struct x86_emulate_ctxt *ctxt) if (rc != X86EMUL_CONTINUE) return rc; - rc = assign_eip_far(ctxt, ctxt->src.val, &new_desc); + rc = assign_eip_far(ctxt, ctxt->src.val); if (rc != X86EMUL_CONTINUE) goto fail; @@ -3623,11 +3641,25 @@ static int em_movbe(struct x86_emulate_ctxt *ctxt) static int em_cr_write(struct x86_emulate_ctxt *ctxt) { - if (ctxt->ops->set_cr(ctxt, ctxt->modrm_reg, ctxt->src.val)) + int cr_num = ctxt->modrm_reg; + int r; + + if (ctxt->ops->set_cr(ctxt, cr_num, ctxt->src.val)) return emulate_gp(ctxt, 0); /* Disable writeback. */ ctxt->dst.type = OP_NONE; + + if (cr_num == 0) { + /* + * CR0 write might have updated CR0.PE and/or CR0.PG + * which can affect the cpu's execution mode. + */ + r = emulator_recalc_and_set_mode(ctxt); + if (r != X86EMUL_CONTINUE) + return r; + } + return X86EMUL_CONTINUE; } @@ -3659,13 +3691,10 @@ static int em_wrmsr(struct x86_emulate_ctxt *ctxt) | ((u64)reg_read(ctxt, VCPU_REGS_RDX) << 32); r = ctxt->ops->set_msr_with_filter(ctxt, msr_index, msr_data); - if (r == X86EMUL_IO_NEEDED) - return r; - - if (r > 0) + if (r == X86EMUL_PROPAGATE_FAULT) return emulate_gp(ctxt, 0); - return r < 0 ? X86EMUL_UNHANDLEABLE : X86EMUL_CONTINUE; + return r; } static int em_rdmsr(struct x86_emulate_ctxt *ctxt) @@ -3676,15 +3705,14 @@ static int em_rdmsr(struct x86_emulate_ctxt *ctxt) r = ctxt->ops->get_msr_with_filter(ctxt, msr_index, &msr_data); - if (r == X86EMUL_IO_NEEDED) - return r; - - if (r) + if (r == X86EMUL_PROPAGATE_FAULT) return emulate_gp(ctxt, 0); - *reg_write(ctxt, VCPU_REGS_RAX) = (u32)msr_data; - *reg_write(ctxt, VCPU_REGS_RDX) = msr_data >> 32; - return X86EMUL_CONTINUE; + if (r == X86EMUL_CONTINUE) { + *reg_write(ctxt, VCPU_REGS_RAX) = (u32)msr_data; + *reg_write(ctxt, VCPU_REGS_RDX) = msr_data >> 32; + } + return r; } static int em_store_sreg(struct x86_emulate_ctxt *ctxt, int segment) @@ -4146,6 +4174,9 @@ static int em_xsetbv(struct x86_emulate_ctxt *ctxt) { u32 eax, ecx, edx; + if (!(ctxt->ops->get_cr(ctxt, 4) & X86_CR4_OSXSAVE)) + return emulate_ud(ctxt); + eax = reg_read(ctxt, VCPU_REGS_RAX); edx = reg_read(ctxt, VCPU_REGS_RDX); ecx = reg_read(ctxt, VCPU_REGS_RCX); @@ -4182,8 +4213,7 @@ static int check_dr7_gd(struct x86_emulate_ctxt *ctxt) ctxt->ops->get_dr(ctxt, 7, &dr7); - /* Check if DR7.Global_Enable is set */ - return dr7 & (1 << 13); + return dr7 & DR7_GD; } static int check_dr_read(struct x86_emulate_ctxt *ctxt) diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index ed804447589c..0adf4a437e85 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -38,9 +38,6 @@ #include "irq.h" #include "fpu.h" -/* "Hv#1" signature */ -#define HYPERV_CPUID_SIGNATURE_EAX 0x31237648 - #define KVM_HV_MAX_SPARSE_VCPU_SET_BITS DIV_ROUND_UP(KVM_MAX_VCPUS, 64) static void stimer_mark_pending(struct kvm_vcpu_hv_stimer *stimer, @@ -934,11 +931,14 @@ static void stimer_init(struct kvm_vcpu_hv_stimer *stimer, int timer_index) stimer_prepare_msg(stimer); } -static int kvm_hv_vcpu_init(struct kvm_vcpu *vcpu) +int kvm_hv_vcpu_init(struct kvm_vcpu *vcpu) { - struct kvm_vcpu_hv *hv_vcpu; + struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu); int i; + if (hv_vcpu) + return 0; + hv_vcpu = kzalloc(sizeof(struct kvm_vcpu_hv), GFP_KERNEL_ACCOUNT); if (!hv_vcpu) return -ENOMEM; @@ -962,11 +962,9 @@ int kvm_hv_activate_synic(struct kvm_vcpu *vcpu, bool dont_zero_synic_pages) struct kvm_vcpu_hv_synic *synic; int r; - if (!to_hv_vcpu(vcpu)) { - r = kvm_hv_vcpu_init(vcpu); - if (r) - return r; - } + r = kvm_hv_vcpu_init(vcpu); + if (r) + return r; synic = to_hv_synic(vcpu); @@ -1660,10 +1658,8 @@ int kvm_hv_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host) if (!host && !vcpu->arch.hyperv_enabled) return 1; - if (!to_hv_vcpu(vcpu)) { - if (kvm_hv_vcpu_init(vcpu)) - return 1; - } + if (kvm_hv_vcpu_init(vcpu)) + return 1; if (kvm_hv_msr_partition_wide(msr)) { int r; @@ -1683,10 +1679,8 @@ int kvm_hv_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata, bool host) if (!host && !vcpu->arch.hyperv_enabled) return 1; - if (!to_hv_vcpu(vcpu)) { - if (kvm_hv_vcpu_init(vcpu)) - return 1; - } + if (kvm_hv_vcpu_init(vcpu)) + return 1; if (kvm_hv_msr_partition_wide(msr)) { int r; @@ -1987,49 +1981,49 @@ ret_success: return HV_STATUS_SUCCESS; } -void kvm_hv_set_cpuid(struct kvm_vcpu *vcpu) +void kvm_hv_set_cpuid(struct kvm_vcpu *vcpu, bool hyperv_enabled) { + struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu); struct kvm_cpuid_entry2 *entry; - struct kvm_vcpu_hv *hv_vcpu; - entry = kvm_find_cpuid_entry(vcpu, HYPERV_CPUID_INTERFACE); - if (entry && entry->eax == HYPERV_CPUID_SIGNATURE_EAX) { - vcpu->arch.hyperv_enabled = true; - } else { - vcpu->arch.hyperv_enabled = false; + vcpu->arch.hyperv_enabled = hyperv_enabled; + + if (!hv_vcpu) { + /* + * KVM should have already allocated kvm_vcpu_hv if Hyper-V is + * enabled in CPUID. + */ + WARN_ON_ONCE(vcpu->arch.hyperv_enabled); return; } - if (!to_hv_vcpu(vcpu) && kvm_hv_vcpu_init(vcpu)) - return; + memset(&hv_vcpu->cpuid_cache, 0, sizeof(hv_vcpu->cpuid_cache)); - hv_vcpu = to_hv_vcpu(vcpu); + if (!vcpu->arch.hyperv_enabled) + return; entry = kvm_find_cpuid_entry(vcpu, HYPERV_CPUID_FEATURES); if (entry) { hv_vcpu->cpuid_cache.features_eax = entry->eax; hv_vcpu->cpuid_cache.features_ebx = entry->ebx; hv_vcpu->cpuid_cache.features_edx = entry->edx; - } else { - hv_vcpu->cpuid_cache.features_eax = 0; - hv_vcpu->cpuid_cache.features_ebx = 0; - hv_vcpu->cpuid_cache.features_edx = 0; } entry = kvm_find_cpuid_entry(vcpu, HYPERV_CPUID_ENLIGHTMENT_INFO); if (entry) { hv_vcpu->cpuid_cache.enlightenments_eax = entry->eax; hv_vcpu->cpuid_cache.enlightenments_ebx = entry->ebx; - } else { - hv_vcpu->cpuid_cache.enlightenments_eax = 0; - hv_vcpu->cpuid_cache.enlightenments_ebx = 0; } entry = kvm_find_cpuid_entry(vcpu, HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES); if (entry) hv_vcpu->cpuid_cache.syndbg_cap_eax = entry->eax; - else - hv_vcpu->cpuid_cache.syndbg_cap_eax = 0; + + entry = kvm_find_cpuid_entry(vcpu, HYPERV_CPUID_NESTED_FEATURES); + if (entry) { + hv_vcpu->cpuid_cache.nested_eax = entry->eax; + hv_vcpu->cpuid_cache.nested_ebx = entry->ebx; + } } int kvm_hv_set_enforce_cpuid(struct kvm_vcpu *vcpu, bool enforce) @@ -2552,7 +2546,7 @@ int kvm_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid, case HYPERV_CPUID_NESTED_FEATURES: ent->eax = evmcs_ver; ent->eax |= HV_X64_NESTED_MSR_BITMAP; - + ent->ebx |= HV_X64_NESTED_EVMCS1_PERF_GLOBAL_CTRL; break; case HYPERV_CPUID_SYNDBG_VENDOR_AND_MAX_FUNCTIONS: diff --git a/arch/x86/kvm/hyperv.h b/arch/x86/kvm/hyperv.h index da2737f2a956..1030b1b50552 100644 --- a/arch/x86/kvm/hyperv.h +++ b/arch/x86/kvm/hyperv.h @@ -23,6 +23,9 @@ #include <linux/kvm_host.h> +/* "Hv#1" signature */ +#define HYPERV_CPUID_SIGNATURE_EAX 0x31237648 + /* * The #defines related to the synthetic debugger are required by KDNet, but * they are not documented in the Hyper-V TLFS because the synthetic debugger @@ -141,7 +144,8 @@ void kvm_hv_request_tsc_page_update(struct kvm *kvm); void kvm_hv_init_vm(struct kvm *kvm); void kvm_hv_destroy_vm(struct kvm *kvm); -void kvm_hv_set_cpuid(struct kvm_vcpu *vcpu); +int kvm_hv_vcpu_init(struct kvm_vcpu *vcpu); +void kvm_hv_set_cpuid(struct kvm_vcpu *vcpu, bool hyperv_enabled); int kvm_hv_set_enforce_cpuid(struct kvm_vcpu *vcpu, bool enforce); int kvm_vm_ioctl_hv_eventfd(struct kvm *kvm, struct kvm_hyperv_eventfd *args); int kvm_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid, diff --git a/arch/x86/kvm/kvm-asm-offsets.c b/arch/x86/kvm/kvm-asm-offsets.c new file mode 100644 index 000000000000..24a710d37323 --- /dev/null +++ b/arch/x86/kvm/kvm-asm-offsets.c @@ -0,0 +1,29 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Generate definitions needed by assembly language modules. + * This code generates raw asm output which is post-processed to extract + * and format the required data. + */ +#define COMPILE_OFFSETS + +#include <linux/kbuild.h> +#include "vmx/vmx.h" +#include "svm/svm.h" + +static void __used common(void) +{ + if (IS_ENABLED(CONFIG_KVM_AMD)) { + BLANK(); + OFFSET(SVM_vcpu_arch_regs, vcpu_svm, vcpu.arch.regs); + OFFSET(SVM_current_vmcb, vcpu_svm, current_vmcb); + OFFSET(SVM_spec_ctrl, vcpu_svm, spec_ctrl); + OFFSET(SVM_vmcb01, vcpu_svm, vmcb01); + OFFSET(KVM_VMCB_pa, kvm_vmcb_info, pa); + OFFSET(SD_save_area_pa, svm_cpu_data, save_area_pa); + } + + if (IS_ENABLED(CONFIG_KVM_INTEL)) { + BLANK(); + OFFSET(VMX_spec_ctrl, vcpu_vmx, spec_ctrl); + } +} diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 9dda989a1cf0..d7639d126e6c 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -3025,17 +3025,8 @@ int kvm_apic_accept_events(struct kvm_vcpu *vcpu) struct kvm_lapic *apic = vcpu->arch.apic; u8 sipi_vector; int r; - unsigned long pe; - if (!lapic_in_kernel(vcpu)) - return 0; - - /* - * Read pending events before calling the check_events - * callback. - */ - pe = smp_load_acquire(&apic->pending_events); - if (!pe) + if (!kvm_apic_has_pending_init_or_sipi(vcpu)) return 0; if (is_guest_mode(vcpu)) { @@ -3043,38 +3034,31 @@ int kvm_apic_accept_events(struct kvm_vcpu *vcpu) if (r < 0) return r == -EBUSY ? 0 : r; /* - * If an event has happened and caused a vmexit, - * we know INITs are latched and therefore - * we will not incorrectly deliver an APIC - * event instead of a vmexit. + * Continue processing INIT/SIPI even if a nested VM-Exit + * occurred, e.g. pending SIPIs should be dropped if INIT+SIPI + * are blocked as a result of transitioning to VMX root mode. */ } /* - * INITs are latched while CPU is in specific states - * (SMM, VMX root mode, SVM with GIF=0). - * Because a CPU cannot be in these states immediately - * after it has processed an INIT signal (and thus in - * KVM_MP_STATE_INIT_RECEIVED state), just eat SIPIs - * and leave the INIT pending. + * INITs are blocked while CPU is in specific states (SMM, VMX root + * mode, SVM with GIF=0), while SIPIs are dropped if the CPU isn't in + * wait-for-SIPI (WFS). */ - if (kvm_vcpu_latch_init(vcpu)) { + if (!kvm_apic_init_sipi_allowed(vcpu)) { WARN_ON_ONCE(vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED); - if (test_bit(KVM_APIC_SIPI, &pe)) - clear_bit(KVM_APIC_SIPI, &apic->pending_events); + clear_bit(KVM_APIC_SIPI, &apic->pending_events); return 0; } - if (test_bit(KVM_APIC_INIT, &pe)) { - clear_bit(KVM_APIC_INIT, &apic->pending_events); + if (test_and_clear_bit(KVM_APIC_INIT, &apic->pending_events)) { kvm_vcpu_reset(vcpu, true); if (kvm_vcpu_is_bsp(apic->vcpu)) vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; else vcpu->arch.mp_state = KVM_MP_STATE_INIT_RECEIVED; } - if (test_bit(KVM_APIC_SIPI, &pe)) { - clear_bit(KVM_APIC_SIPI, &apic->pending_events); + if (test_and_clear_bit(KVM_APIC_SIPI, &apic->pending_events)) { if (vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED) { /* evaluate pending_events before reading the vector */ smp_rmb(); diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h index 117a46df5cc1..a5ac4a5a5179 100644 --- a/arch/x86/kvm/lapic.h +++ b/arch/x86/kvm/lapic.h @@ -7,6 +7,7 @@ #include <linux/kvm_host.h> #include "hyperv.h" +#include "kvm_cache_regs.h" #define KVM_APIC_INIT 0 #define KVM_APIC_SIPI 1 @@ -223,11 +224,17 @@ static inline bool kvm_vcpu_apicv_active(struct kvm_vcpu *vcpu) return lapic_in_kernel(vcpu) && vcpu->arch.apic->apicv_active; } -static inline bool kvm_apic_has_events(struct kvm_vcpu *vcpu) +static inline bool kvm_apic_has_pending_init_or_sipi(struct kvm_vcpu *vcpu) { return lapic_in_kernel(vcpu) && vcpu->arch.apic->pending_events; } +static inline bool kvm_apic_init_sipi_allowed(struct kvm_vcpu *vcpu) +{ + return !is_smm(vcpu) && + !static_call(kvm_x86_apic_init_signal_blocked)(vcpu); +} + static inline bool kvm_lowest_prio_delivery(struct kvm_lapic_irq *irq) { return (irq->delivery_mode == APIC_DM_LOWEST || diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index eccddb136954..b6f96d47e596 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -1596,6 +1596,8 @@ static void __rmap_add(struct kvm *kvm, rmap_head = gfn_to_rmap(gfn, sp->role.level, slot); rmap_count = pte_list_add(cache, spte, rmap_head); + if (rmap_count > kvm->stat.max_mmu_rmap_size) + kvm->stat.max_mmu_rmap_size = rmap_count; if (rmap_count > RMAP_RECYCLE_THRESHOLD) { kvm_zap_all_rmap_sptes(kvm, rmap_head); kvm_flush_remote_tlbs_with_address( @@ -1665,6 +1667,18 @@ static inline void kvm_mod_used_mmu_pages(struct kvm *kvm, long nr) percpu_counter_add(&kvm_total_used_mmu_pages, nr); } +static void kvm_account_mmu_page(struct kvm *kvm, struct kvm_mmu_page *sp) +{ + kvm_mod_used_mmu_pages(kvm, +1); + kvm_account_pgtable_pages((void *)sp->spt, +1); +} + +static void kvm_unaccount_mmu_page(struct kvm *kvm, struct kvm_mmu_page *sp) +{ + kvm_mod_used_mmu_pages(kvm, -1); + kvm_account_pgtable_pages((void *)sp->spt, -1); +} + static void kvm_mmu_free_shadow_page(struct kvm_mmu_page *sp) { MMU_WARN_ON(!is_empty_shadow_page(sp->spt)); @@ -2122,7 +2136,7 @@ static struct kvm_mmu_page *kvm_mmu_alloc_shadow_page(struct kvm *kvm, */ sp->mmu_valid_gen = kvm->arch.mmu_valid_gen; list_add(&sp->link, &kvm->arch.active_mmu_pages); - kvm_mod_used_mmu_pages(kvm, +1); + kvm_account_mmu_page(kvm, sp); sp->gfn = gfn; sp->role = role; @@ -2429,6 +2443,7 @@ static bool __kvm_mmu_prepare_zap_page(struct kvm *kvm, { bool list_unstable, zapped_root = false; + lockdep_assert_held_write(&kvm->mmu_lock); trace_kvm_mmu_prepare_zap_page(sp); ++kvm->stat.mmu_shadow_zapped; *nr_zapped = mmu_zap_unsync_children(kvm, sp, invalid_list); @@ -2456,7 +2471,7 @@ static bool __kvm_mmu_prepare_zap_page(struct kvm *kvm, list_add(&sp->link, invalid_list); else list_move(&sp->link, invalid_list); - kvm_mod_used_mmu_pages(kvm, -1); + kvm_unaccount_mmu_page(kvm, sp); } else { /* * Remove the active root from the active page list, the root @@ -2914,7 +2929,7 @@ static void direct_pte_prefetch(struct kvm_vcpu *vcpu, u64 *sptep) * If addresses are being invalidated, skip prefetching to avoid * accidentally prefetching those addresses. */ - if (unlikely(vcpu->kvm->mmu_notifier_count)) + if (unlikely(vcpu->kvm->mmu_invalidate_in_progress)) return; __direct_pte_prefetch(vcpu, sp, sptep); @@ -2928,7 +2943,7 @@ static void direct_pte_prefetch(struct kvm_vcpu *vcpu, u64 *sptep) * * There are several ways to safely use this helper: * - * - Check mmu_notifier_retry_hva() after grabbing the mapping level, before + * - Check mmu_invalidate_retry_hva() after grabbing the mapping level, before * consuming it. In this case, mmu_lock doesn't need to be held during the * lookup, but it does need to be held while checking the MMU notifier. * @@ -3056,7 +3071,7 @@ void kvm_mmu_hugepage_adjust(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault return; /* - * mmu_notifier_retry() was successful and mmu_lock is held, so + * mmu_invalidate_retry() was successful and mmu_lock is held, so * the pmd can't be split from under us. */ fault->goal_level = fault->req_level; @@ -4203,7 +4218,7 @@ static bool is_page_fault_stale(struct kvm_vcpu *vcpu, return true; return fault->slot && - mmu_notifier_retry_hva(vcpu->kvm, mmu_seq, fault->hva); + mmu_invalidate_retry_hva(vcpu->kvm, mmu_seq, fault->hva); } static int direct_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) @@ -4227,7 +4242,7 @@ static int direct_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault if (r) return r; - mmu_seq = vcpu->kvm->mmu_notifier_seq; + mmu_seq = vcpu->kvm->mmu_invalidate_seq; smp_rmb(); r = kvm_faultin_pfn(vcpu, fault); @@ -4248,14 +4263,14 @@ static int direct_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault if (is_page_fault_stale(vcpu, fault, mmu_seq)) goto out_unlock; - r = make_mmu_pages_available(vcpu); - if (r) - goto out_unlock; - - if (is_tdp_mmu_fault) + if (is_tdp_mmu_fault) { r = kvm_tdp_mmu_map(vcpu, fault); - else + } else { + r = make_mmu_pages_available(vcpu); + if (r) + goto out_unlock; r = __direct_map(vcpu, fault); + } out_unlock: if (is_tdp_mmu_fault) @@ -4290,7 +4305,7 @@ int kvm_handle_page_fault(struct kvm_vcpu *vcpu, u64 error_code, vcpu->arch.l1tf_flush_l1d = true; if (!flags) { - trace_kvm_page_fault(fault_address, error_code); + trace_kvm_page_fault(vcpu, fault_address, error_code); if (kvm_event_needs_reinjection(vcpu)) kvm_mmu_unprotect_page_virt(vcpu, fault_address); @@ -5361,19 +5376,6 @@ void kvm_mmu_free_obsolete_roots(struct kvm_vcpu *vcpu) __kvm_mmu_free_obsolete_roots(vcpu->kvm, &vcpu->arch.guest_mmu); } -static bool need_remote_flush(u64 old, u64 new) -{ - if (!is_shadow_present_pte(old)) - return false; - if (!is_shadow_present_pte(new)) - return true; - if ((old ^ new) & SPTE_BASE_ADDR_MASK) - return true; - old ^= shadow_nx_mask; - new ^= shadow_nx_mask; - return (old & ~new & SPTE_PERM_MASK) != 0; -} - static u64 mmu_pte_write_fetch_gpte(struct kvm_vcpu *vcpu, gpa_t *gpa, int *bytes) { @@ -5519,7 +5521,7 @@ static void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, mmu_page_zap_pte(vcpu->kvm, sp, spte, NULL); if (gentry && sp->role.level != PG_LEVEL_4K) ++vcpu->kvm->stat.mmu_pde_zapped; - if (need_remote_flush(entry, *spte)) + if (is_shadow_present_pte(entry)) flush = true; ++spte; } @@ -6055,7 +6057,7 @@ void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end) write_lock(&kvm->mmu_lock); - kvm_inc_notifier_count(kvm, gfn_start, gfn_end); + kvm_mmu_invalidate_begin(kvm, 0, -1ul); flush = kvm_rmap_zap_gfn_range(kvm, gfn_start, gfn_end); @@ -6069,7 +6071,7 @@ void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end) kvm_flush_remote_tlbs_with_address(kvm, gfn_start, gfn_end - gfn_start); - kvm_dec_notifier_count(kvm, gfn_start, gfn_end); + kvm_mmu_invalidate_end(kvm, 0, -1ul); write_unlock(&kvm->mmu_lock); } @@ -6085,47 +6087,18 @@ void kvm_mmu_slot_remove_write_access(struct kvm *kvm, const struct kvm_memory_slot *memslot, int start_level) { - bool flush = false; - if (kvm_memslots_have_rmaps(kvm)) { write_lock(&kvm->mmu_lock); - flush = slot_handle_level(kvm, memslot, slot_rmap_write_protect, - start_level, KVM_MAX_HUGEPAGE_LEVEL, - false); + slot_handle_level(kvm, memslot, slot_rmap_write_protect, + start_level, KVM_MAX_HUGEPAGE_LEVEL, false); write_unlock(&kvm->mmu_lock); } if (is_tdp_mmu_enabled(kvm)) { read_lock(&kvm->mmu_lock); - flush |= kvm_tdp_mmu_wrprot_slot(kvm, memslot, start_level); + kvm_tdp_mmu_wrprot_slot(kvm, memslot, start_level); read_unlock(&kvm->mmu_lock); } - - /* - * Flush TLBs if any SPTEs had to be write-protected to ensure that - * guest writes are reflected in the dirty bitmap before the memslot - * update completes, i.e. before enabling dirty logging is visible to - * userspace. - * - * Perform the TLB flush outside the mmu_lock to reduce the amount of - * time the lock is held. However, this does mean that another CPU can - * now grab mmu_lock and encounter a write-protected SPTE while CPUs - * still have a writable mapping for the associated GFN in their TLB. - * - * This is safe but requires KVM to be careful when making decisions - * based on the write-protection status of an SPTE. Specifically, KVM - * also write-protects SPTEs to monitor changes to guest page tables - * during shadow paging, and must guarantee no CPUs can write to those - * page before the lock is dropped. As mentioned in the previous - * paragraph, a write-protected SPTE is no guarantee that CPU cannot - * perform writes. So to determine if a TLB flush is truly required, KVM - * will clear a separate software-only bit (MMU-writable) and skip the - * flush if-and-only-if this bit was already clear. - * - * See is_writable_pte() for more details. - */ - if (flush) - kvm_arch_flush_remote_tlbs_memslot(kvm, memslot); } static inline bool need_topup(struct kvm_mmu_memory_cache *cache, int min) @@ -6493,32 +6466,30 @@ void kvm_arch_flush_remote_tlbs_memslot(struct kvm *kvm, void kvm_mmu_slot_leaf_clear_dirty(struct kvm *kvm, const struct kvm_memory_slot *memslot) { - bool flush = false; - if (kvm_memslots_have_rmaps(kvm)) { write_lock(&kvm->mmu_lock); /* * Clear dirty bits only on 4k SPTEs since the legacy MMU only * support dirty logging at a 4k granularity. */ - flush = slot_handle_level_4k(kvm, memslot, __rmap_clear_dirty, false); + slot_handle_level_4k(kvm, memslot, __rmap_clear_dirty, false); write_unlock(&kvm->mmu_lock); } if (is_tdp_mmu_enabled(kvm)) { read_lock(&kvm->mmu_lock); - flush |= kvm_tdp_mmu_clear_dirty_slot(kvm, memslot); + kvm_tdp_mmu_clear_dirty_slot(kvm, memslot); read_unlock(&kvm->mmu_lock); } /* + * The caller will flush the TLBs after this function returns. + * * It's also safe to flush TLBs out of mmu lock here as currently this * function is only used for dirty logging, in which case flushing TLB * out of mmu lock also guarantees no dirty pages will be lost in * dirty_bitmap. */ - if (flush) - kvm_arch_flush_remote_tlbs_memslot(kvm, memslot); } void kvm_mmu_zap_all(struct kvm *kvm) @@ -6746,10 +6717,12 @@ int kvm_mmu_vendor_module_init(void) ret = register_shrinker(&mmu_shrinker, "x86-mmu"); if (ret) - goto out; + goto out_shrinker; return 0; +out_shrinker: + percpu_counter_destroy(&kvm_total_used_mmu_pages); out: mmu_destroy_caches(); return ret; diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h index f5958071220c..5ab5f94dcb6f 100644 --- a/arch/x86/kvm/mmu/paging_tmpl.h +++ b/arch/x86/kvm/mmu/paging_tmpl.h @@ -472,7 +472,7 @@ error: #if PTTYPE == PTTYPE_EPT /* - * Use PFERR_RSVD_MASK in error_code to to tell if EPT + * Use PFERR_RSVD_MASK in error_code to tell if EPT * misconfiguration requires to be injected. The detection is * done by is_rsvd_bits_set() above. * @@ -589,7 +589,7 @@ static void FNAME(pte_prefetch)(struct kvm_vcpu *vcpu, struct guest_walker *gw, * If addresses are being invalidated, skip prefetching to avoid * accidentally prefetching those addresses. */ - if (unlikely(vcpu->kvm->mmu_notifier_count)) + if (unlikely(vcpu->kvm->mmu_invalidate_in_progress)) return; if (sp->role.direct) @@ -838,7 +838,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault else fault->max_level = walker.level; - mmu_seq = vcpu->kvm->mmu_notifier_seq; + mmu_seq = vcpu->kvm->mmu_invalidate_seq; smp_rmb(); r = kvm_faultin_pfn(vcpu, fault); diff --git a/arch/x86/kvm/mmu/spte.h b/arch/x86/kvm/mmu/spte.h index f3744eea45f5..7670c13ce251 100644 --- a/arch/x86/kvm/mmu/spte.h +++ b/arch/x86/kvm/mmu/spte.h @@ -343,7 +343,7 @@ static __always_inline bool is_rsvd_spte(struct rsvd_bits_validate *rsvd_check, } /* - * An shadow-present leaf SPTE may be non-writable for 3 possible reasons: + * A shadow-present leaf SPTE may be non-writable for 4 possible reasons: * * 1. To intercept writes for dirty logging. KVM write-protects huge pages * so that they can be split be split down into the dirty logging @@ -361,8 +361,13 @@ static __always_inline bool is_rsvd_spte(struct rsvd_bits_validate *rsvd_check, * read-only memslot or guest memory backed by a read-only VMA. Writes to * such pages are disallowed entirely. * - * To keep track of why a given SPTE is write-protected, KVM uses 2 - * software-only bits in the SPTE: + * 4. To emulate the Accessed bit for SPTEs without A/D bits. Note, in this + * case, the SPTE is access-protected, not just write-protected! + * + * For cases #1 and #4, KVM can safely make such SPTEs writable without taking + * mmu_lock as capturing the Accessed/Dirty state doesn't require taking it. + * To differentiate #1 and #4 from #2 and #3, KVM uses two software-only bits + * in the SPTE: * * shadow_mmu_writable_mask, aka MMU-writable - * Cleared on SPTEs that KVM is currently write-protecting for shadow paging @@ -391,7 +396,8 @@ static __always_inline bool is_rsvd_spte(struct rsvd_bits_validate *rsvd_check, * shadow page tables between vCPUs. Write-protecting an SPTE for dirty logging * (which does not clear the MMU-writable bit), does not flush TLBs before * dropping the lock, as it only needs to synchronize guest writes with the - * dirty bitmap. + * dirty bitmap. Similarly, making the SPTE inaccessible (and non-writable) for + * access-tracking via the clear_young() MMU notifier also does not flush TLBs. * * So, there is the problem: clearing the MMU-writable bit can encounter a * write-protected SPTE while CPUs still have writable mappings for that SPTE diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index bf2ccf9debca..672f0432d777 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -372,6 +372,16 @@ static void handle_changed_spte_dirty_log(struct kvm *kvm, int as_id, gfn_t gfn, } } +static void tdp_account_mmu_page(struct kvm *kvm, struct kvm_mmu_page *sp) +{ + kvm_account_pgtable_pages((void *)sp->spt, +1); +} + +static void tdp_unaccount_mmu_page(struct kvm *kvm, struct kvm_mmu_page *sp) +{ + kvm_account_pgtable_pages((void *)sp->spt, -1); +} + /** * tdp_mmu_unlink_sp() - Remove a shadow page from the list of used pages * @@ -384,6 +394,7 @@ static void handle_changed_spte_dirty_log(struct kvm *kvm, int as_id, gfn_t gfn, static void tdp_mmu_unlink_sp(struct kvm *kvm, struct kvm_mmu_page *sp, bool shared) { + tdp_unaccount_mmu_page(kvm, sp); if (shared) spin_lock(&kvm->arch.tdp_mmu_pages_lock); else @@ -1132,6 +1143,7 @@ static int tdp_mmu_link_sp(struct kvm *kvm, struct tdp_iter *iter, if (account_nx) account_huge_nx_page(kvm, sp); spin_unlock(&kvm->arch.tdp_mmu_pages_lock); + tdp_account_mmu_page(kvm, sp); return 0; } diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c index 02f9e4f245bd..de1fd7369736 100644 --- a/arch/x86/kvm/pmu.c +++ b/arch/x86/kvm/pmu.c @@ -56,7 +56,7 @@ static const struct x86_cpu_id vmx_icl_pebs_cpu[] = { * code. Each pmc, stored in kvm_pmc.idx field, is unique across * all perf counters (both gp and fixed). The mapping relationship * between pmc and perf counters is as the following: - * * Intel: [0 .. INTEL_PMC_MAX_GENERIC-1] <=> gp counters + * * Intel: [0 .. KVM_INTEL_PMC_MAX_GENERIC-1] <=> gp counters * [INTEL_PMC_IDX_FIXED .. INTEL_PMC_IDX_FIXED + 2] <=> fixed * * AMD: [0 .. AMD64_NUM_COUNTERS-1] and, for families 15H * and later, [0 .. AMD64_NUM_COUNTERS_CORE-1] <=> gp counters @@ -106,9 +106,19 @@ static inline void __kvm_perf_overflow(struct kvm_pmc *pmc, bool in_pmi) return; if (pmc->perf_event && pmc->perf_event->attr.precise_ip) { - /* Indicate PEBS overflow PMI to guest. */ - skip_pmi = __test_and_set_bit(GLOBAL_STATUS_BUFFER_OVF_BIT, - (unsigned long *)&pmu->global_status); + if (!in_pmi) { + /* + * TODO: KVM is currently _choosing_ to not generate records + * for emulated instructions, avoiding BUFFER_OVF PMI when + * there are no records. Strictly speaking, it should be done + * as well in the right context to improve sampling accuracy. + */ + skip_pmi = true; + } else { + /* Indicate PEBS overflow PMI to guest. */ + skip_pmi = __test_and_set_bit(GLOBAL_STATUS_BUFFER_OVF_BIT, + (unsigned long *)&pmu->global_status); + } } else { __set_bit(pmc->idx, (unsigned long *)&pmu->global_status); } @@ -227,8 +237,8 @@ static bool pmc_resume_counter(struct kvm_pmc *pmc) get_sample_period(pmc, pmc->counter))) return false; - if (!test_bit(pmc->idx, (unsigned long *)&pmc_to_pmu(pmc)->pebs_enable) && - pmc->perf_event->attr.precise_ip) + if (test_bit(pmc->idx, (unsigned long *)&pmc_to_pmu(pmc)->pebs_enable) != + (!!pmc->perf_event->attr.precise_ip)) return false; /* reuse perf_event to serve as pmc_reprogram_counter() does*/ diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index 76dcc8a3e849..995bc0f90759 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -55,28 +55,6 @@ static void nested_svm_inject_npf_exit(struct kvm_vcpu *vcpu, nested_svm_vmexit(svm); } -static bool nested_svm_handle_page_fault_workaround(struct kvm_vcpu *vcpu, - struct x86_exception *fault) -{ - struct vcpu_svm *svm = to_svm(vcpu); - struct vmcb *vmcb = svm->vmcb; - - WARN_ON(!is_guest_mode(vcpu)); - - if (vmcb12_is_intercept(&svm->nested.ctl, - INTERCEPT_EXCEPTION_OFFSET + PF_VECTOR) && - !WARN_ON_ONCE(svm->nested.nested_run_pending)) { - vmcb->control.exit_code = SVM_EXIT_EXCP_BASE + PF_VECTOR; - vmcb->control.exit_code_hi = 0; - vmcb->control.exit_info_1 = fault->error_code; - vmcb->control.exit_info_2 = fault->address; - nested_svm_vmexit(svm); - return true; - } - - return false; -} - static u64 nested_svm_get_tdp_pdptr(struct kvm_vcpu *vcpu, int index) { struct vcpu_svm *svm = to_svm(vcpu); @@ -468,7 +446,7 @@ static void nested_save_pending_event_to_vmcb12(struct vcpu_svm *svm, unsigned int nr; if (vcpu->arch.exception.injected) { - nr = vcpu->arch.exception.nr; + nr = vcpu->arch.exception.vector; exit_int_info = nr | SVM_EVTINJ_VALID | SVM_EVTINJ_TYPE_EXEPT; if (vcpu->arch.exception.has_error_code) { @@ -781,11 +759,15 @@ int enter_svm_guest_mode(struct kvm_vcpu *vcpu, u64 vmcb12_gpa, struct vcpu_svm *svm = to_svm(vcpu); int ret; - trace_kvm_nested_vmrun(svm->vmcb->save.rip, vmcb12_gpa, - vmcb12->save.rip, - vmcb12->control.int_ctl, - vmcb12->control.event_inj, - vmcb12->control.nested_ctl); + trace_kvm_nested_vmenter(svm->vmcb->save.rip, + vmcb12_gpa, + vmcb12->save.rip, + vmcb12->control.int_ctl, + vmcb12->control.event_inj, + vmcb12->control.nested_ctl, + vmcb12->control.nested_cr3, + vmcb12->save.cr3, + KVM_ISA_SVM); trace_kvm_nested_intercepts(vmcb12->control.intercepts[INTERCEPT_CR] & 0xffff, vmcb12->control.intercepts[INTERCEPT_CR] >> 16, @@ -1109,6 +1091,12 @@ int nested_svm_vmexit(struct vcpu_svm *svm) static void nested_svm_triple_fault(struct kvm_vcpu *vcpu) { + struct vcpu_svm *svm = to_svm(vcpu); + + if (!vmcb12_is_intercept(&svm->nested.ctl, INTERCEPT_SHUTDOWN)) + return; + + kvm_clear_request(KVM_REQ_TRIPLE_FAULT, vcpu); nested_svm_simple_vmexit(to_svm(vcpu), SVM_EXIT_SHUTDOWN); } @@ -1143,6 +1131,9 @@ void svm_free_nested(struct vcpu_svm *svm) if (!svm->nested.initialized) return; + if (WARN_ON_ONCE(svm->vmcb != svm->vmcb01.ptr)) + svm_switch_vmcb(svm, &svm->vmcb01); + svm_vcpu_free_msrpm(svm->nested.msrpm); svm->nested.msrpm = NULL; @@ -1161,9 +1152,6 @@ void svm_free_nested(struct vcpu_svm *svm) svm->nested.initialized = false; } -/* - * Forcibly leave nested mode in order to be able to reset the VCPU later on. - */ void svm_leave_nested(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); @@ -1304,44 +1292,46 @@ int nested_svm_check_permissions(struct kvm_vcpu *vcpu) return 0; } -static bool nested_exit_on_exception(struct vcpu_svm *svm) +static bool nested_svm_is_exception_vmexit(struct kvm_vcpu *vcpu, u8 vector, + u32 error_code) { - unsigned int nr = svm->vcpu.arch.exception.nr; + struct vcpu_svm *svm = to_svm(vcpu); - return (svm->nested.ctl.intercepts[INTERCEPT_EXCEPTION] & BIT(nr)); + return (svm->nested.ctl.intercepts[INTERCEPT_EXCEPTION] & BIT(vector)); } -static void nested_svm_inject_exception_vmexit(struct vcpu_svm *svm) +static void nested_svm_inject_exception_vmexit(struct kvm_vcpu *vcpu) { - unsigned int nr = svm->vcpu.arch.exception.nr; + struct kvm_queued_exception *ex = &vcpu->arch.exception_vmexit; + struct vcpu_svm *svm = to_svm(vcpu); struct vmcb *vmcb = svm->vmcb; - vmcb->control.exit_code = SVM_EXIT_EXCP_BASE + nr; + vmcb->control.exit_code = SVM_EXIT_EXCP_BASE + ex->vector; vmcb->control.exit_code_hi = 0; - if (svm->vcpu.arch.exception.has_error_code) - vmcb->control.exit_info_1 = svm->vcpu.arch.exception.error_code; + if (ex->has_error_code) + vmcb->control.exit_info_1 = ex->error_code; /* * EXITINFO2 is undefined for all exception intercepts other * than #PF. */ - if (nr == PF_VECTOR) { - if (svm->vcpu.arch.exception.nested_apf) - vmcb->control.exit_info_2 = svm->vcpu.arch.apf.nested_apf_token; - else if (svm->vcpu.arch.exception.has_payload) - vmcb->control.exit_info_2 = svm->vcpu.arch.exception.payload; + if (ex->vector == PF_VECTOR) { + if (ex->has_payload) + vmcb->control.exit_info_2 = ex->payload; else - vmcb->control.exit_info_2 = svm->vcpu.arch.cr2; - } else if (nr == DB_VECTOR) { - /* See inject_pending_event. */ - kvm_deliver_exception_payload(&svm->vcpu); - if (svm->vcpu.arch.dr7 & DR7_GD) { - svm->vcpu.arch.dr7 &= ~DR7_GD; - kvm_update_dr7(&svm->vcpu); + vmcb->control.exit_info_2 = vcpu->arch.cr2; + } else if (ex->vector == DB_VECTOR) { + /* See kvm_check_and_inject_events(). */ + kvm_deliver_exception_payload(vcpu, ex); + + if (vcpu->arch.dr7 & DR7_GD) { + vcpu->arch.dr7 &= ~DR7_GD; + kvm_update_dr7(vcpu); } - } else - WARN_ON(svm->vcpu.arch.exception.has_payload); + } else { + WARN_ON(ex->has_payload); + } nested_svm_vmexit(svm); } @@ -1353,10 +1343,22 @@ static inline bool nested_exit_on_init(struct vcpu_svm *svm) 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.nested_run_pending; struct kvm_lapic *apic = vcpu->arch.apic; + struct vcpu_svm *svm = to_svm(vcpu); + /* + * Only a pending nested run blocks a pending exception. If there is a + * previously injected event, the pending exception occurred while said + * event was being delivered and thus needs to be handled. + */ + bool block_nested_exceptions = svm->nested.nested_run_pending; + /* + * New events (not exceptions) are only recognized at instruction + * boundaries. If an event needs reinjection, then KVM is handling a + * VM-Exit that occurred _during_ instruction execution; new events are + * blocked until the instruction completes. + */ + bool block_nested_events = block_nested_exceptions || + kvm_event_needs_reinjection(vcpu); if (lapic_in_kernel(vcpu) && test_bit(KVM_APIC_INIT, &apic->pending_events)) { @@ -1368,18 +1370,16 @@ static int svm_check_nested_events(struct kvm_vcpu *vcpu) return 0; } - if (vcpu->arch.exception.pending) { - /* - * Only a pending nested run can block a pending exception. - * Otherwise an injected NMI/interrupt should either be - * lost or delivered to the nested hypervisor in the EXITINTINFO - * vmcb field, while delivering the pending exception. - */ - if (svm->nested.nested_run_pending) + if (vcpu->arch.exception_vmexit.pending) { + if (block_nested_exceptions) return -EBUSY; - if (!nested_exit_on_exception(svm)) - return 0; - nested_svm_inject_exception_vmexit(svm); + nested_svm_inject_exception_vmexit(vcpu); + return 0; + } + + if (vcpu->arch.exception.pending) { + if (block_nested_exceptions) + return -EBUSY; return 0; } @@ -1720,8 +1720,8 @@ static bool svm_get_nested_state_pages(struct kvm_vcpu *vcpu) struct kvm_x86_nested_ops svm_nested_ops = { .leave_nested = svm_leave_nested, + .is_exception_vmexit = nested_svm_is_exception_vmexit, .check_events = svm_check_nested_events, - .handle_page_fault_workaround = nested_svm_handle_page_fault_workaround, .triple_fault = nested_svm_triple_fault, .get_nested_state_pages = svm_get_nested_state_pages, .get_state = svm_get_nested_state, diff --git a/arch/x86/kvm/svm/pmu.c b/arch/x86/kvm/svm/pmu.c index f24613a108c5..9d65cd095691 100644 --- a/arch/x86/kvm/svm/pmu.c +++ b/arch/x86/kvm/svm/pmu.c @@ -23,107 +23,52 @@ enum pmu_type { PMU_TYPE_EVNTSEL, }; -enum index { - INDEX_ZERO = 0, - INDEX_ONE, - INDEX_TWO, - INDEX_THREE, - INDEX_FOUR, - INDEX_FIVE, - INDEX_ERROR, -}; - -static unsigned int get_msr_base(struct kvm_pmu *pmu, enum pmu_type type) +static struct kvm_pmc *amd_pmc_idx_to_pmc(struct kvm_pmu *pmu, int pmc_idx) { - struct kvm_vcpu *vcpu = pmu_to_vcpu(pmu); + unsigned int num_counters = pmu->nr_arch_gp_counters; - if (guest_cpuid_has(vcpu, X86_FEATURE_PERFCTR_CORE)) { - if (type == PMU_TYPE_COUNTER) - return MSR_F15H_PERF_CTR; - else - return MSR_F15H_PERF_CTL; - } else { - if (type == PMU_TYPE_COUNTER) - return MSR_K7_PERFCTR0; - else - return MSR_K7_EVNTSEL0; - } -} + if (pmc_idx >= num_counters) + return NULL; -static enum index msr_to_index(u32 msr) -{ - switch (msr) { - case MSR_F15H_PERF_CTL0: - case MSR_F15H_PERF_CTR0: - case MSR_K7_EVNTSEL0: - case MSR_K7_PERFCTR0: - return INDEX_ZERO; - case MSR_F15H_PERF_CTL1: - case MSR_F15H_PERF_CTR1: - case MSR_K7_EVNTSEL1: - case MSR_K7_PERFCTR1: - return INDEX_ONE; - case MSR_F15H_PERF_CTL2: - case MSR_F15H_PERF_CTR2: - case MSR_K7_EVNTSEL2: - case MSR_K7_PERFCTR2: - return INDEX_TWO; - case MSR_F15H_PERF_CTL3: - case MSR_F15H_PERF_CTR3: - case MSR_K7_EVNTSEL3: - case MSR_K7_PERFCTR3: - return INDEX_THREE; - case MSR_F15H_PERF_CTL4: - case MSR_F15H_PERF_CTR4: - return INDEX_FOUR; - case MSR_F15H_PERF_CTL5: - case MSR_F15H_PERF_CTR5: - return INDEX_FIVE; - default: - return INDEX_ERROR; - } + return &pmu->gp_counters[array_index_nospec(pmc_idx, num_counters)]; } static inline struct kvm_pmc *get_gp_pmc_amd(struct kvm_pmu *pmu, u32 msr, enum pmu_type type) { struct kvm_vcpu *vcpu = pmu_to_vcpu(pmu); + unsigned int idx; if (!vcpu->kvm->arch.enable_pmu) return NULL; switch (msr) { - case MSR_F15H_PERF_CTL0: - case MSR_F15H_PERF_CTL1: - case MSR_F15H_PERF_CTL2: - case MSR_F15H_PERF_CTL3: - case MSR_F15H_PERF_CTL4: - case MSR_F15H_PERF_CTL5: + case MSR_F15H_PERF_CTL0 ... MSR_F15H_PERF_CTR5: if (!guest_cpuid_has(vcpu, X86_FEATURE_PERFCTR_CORE)) return NULL; - fallthrough; + /* + * Each PMU counter has a pair of CTL and CTR MSRs. CTLn + * MSRs (accessed via EVNTSEL) are even, CTRn MSRs are odd. + */ + idx = (unsigned int)((msr - MSR_F15H_PERF_CTL0) / 2); + if (!(msr & 0x1) != (type == PMU_TYPE_EVNTSEL)) + return NULL; + break; case MSR_K7_EVNTSEL0 ... MSR_K7_EVNTSEL3: if (type != PMU_TYPE_EVNTSEL) return NULL; + idx = msr - MSR_K7_EVNTSEL0; break; - case MSR_F15H_PERF_CTR0: - case MSR_F15H_PERF_CTR1: - case MSR_F15H_PERF_CTR2: - case MSR_F15H_PERF_CTR3: - case MSR_F15H_PERF_CTR4: - case MSR_F15H_PERF_CTR5: - if (!guest_cpuid_has(vcpu, X86_FEATURE_PERFCTR_CORE)) - return NULL; - fallthrough; case MSR_K7_PERFCTR0 ... MSR_K7_PERFCTR3: if (type != PMU_TYPE_COUNTER) return NULL; + idx = msr - MSR_K7_PERFCTR0; break; default: return NULL; } - return &pmu->gp_counters[msr_to_index(msr)]; + return amd_pmc_idx_to_pmc(pmu, idx); } static bool amd_hw_event_available(struct kvm_pmc *pmc) @@ -139,22 +84,6 @@ static bool amd_pmc_is_enabled(struct kvm_pmc *pmc) return true; } -static struct kvm_pmc *amd_pmc_idx_to_pmc(struct kvm_pmu *pmu, int pmc_idx) -{ - unsigned int base = get_msr_base(pmu, PMU_TYPE_COUNTER); - struct kvm_vcpu *vcpu = pmu_to_vcpu(pmu); - - if (guest_cpuid_has(vcpu, X86_FEATURE_PERFCTR_CORE)) { - /* - * The idx is contiguous. The MSRs are not. The counter MSRs - * are interleaved with the event select MSRs. - */ - pmc_idx *= 2; - } - - return get_gp_pmc_amd(pmu, base + pmc_idx, PMU_TYPE_COUNTER); -} - static bool amd_is_valid_rdpmc_ecx(struct kvm_vcpu *vcpu, unsigned int idx) { struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); @@ -168,15 +97,7 @@ static bool amd_is_valid_rdpmc_ecx(struct kvm_vcpu *vcpu, unsigned int idx) static struct kvm_pmc *amd_rdpmc_ecx_to_pmc(struct kvm_vcpu *vcpu, unsigned int idx, u64 *mask) { - struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); - struct kvm_pmc *counters; - - idx &= ~(3u << 30); - if (idx >= pmu->nr_arch_gp_counters) - return NULL; - counters = pmu->gp_counters; - - return &counters[idx]; + return amd_pmc_idx_to_pmc(vcpu_to_pmu(vcpu), idx & ~(3u << 30)); } static bool amd_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr) @@ -271,9 +192,10 @@ static void amd_pmu_init(struct kvm_vcpu *vcpu) struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); int i; - BUILD_BUG_ON(AMD64_NUM_COUNTERS_CORE > INTEL_PMC_MAX_GENERIC); + BUILD_BUG_ON(KVM_AMD_PMC_MAX_GENERIC > AMD64_NUM_COUNTERS_CORE); + BUILD_BUG_ON(KVM_AMD_PMC_MAX_GENERIC > INTEL_PMC_MAX_GENERIC); - for (i = 0; i < AMD64_NUM_COUNTERS_CORE ; i++) { + for (i = 0; i < KVM_AMD_PMC_MAX_GENERIC ; i++) { pmu->gp_counters[i].type = KVM_PMC_GP; pmu->gp_counters[i].vcpu = vcpu; pmu->gp_counters[i].idx = i; @@ -286,7 +208,7 @@ static void amd_pmu_reset(struct kvm_vcpu *vcpu) struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); int i; - for (i = 0; i < AMD64_NUM_COUNTERS_CORE; i++) { + for (i = 0; i < KVM_AMD_PMC_MAX_GENERIC; i++) { struct kvm_pmc *pmc = &pmu->gp_counters[i]; pmc_stop_counter(pmc); diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 28064060413a..efaaef2b7ae1 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -196,7 +196,7 @@ static void sev_asid_free(struct kvm_sev_info *sev) __set_bit(sev->asid, sev_reclaim_asid_bitmap); for_each_possible_cpu(cpu) { - sd = per_cpu(svm_data, cpu); + sd = per_cpu_ptr(&svm_data, cpu); sd->sev_vmcbs[sev->asid] = NULL; } @@ -605,7 +605,7 @@ static int sev_es_sync_vmsa(struct vcpu_svm *svm) save->dr6 = svm->vcpu.arch.dr6; pr_debug("Virtual Machine Save Area (VMSA):\n"); - print_hex_dump(KERN_CONT, "", DUMP_PREFIX_NONE, 16, 1, save, sizeof(*save), false); + print_hex_dump_debug("", DUMP_PREFIX_NONE, 16, 1, save, sizeof(*save), false); return 0; } @@ -2600,7 +2600,7 @@ void sev_es_unmap_ghcb(struct vcpu_svm *svm) void pre_sev_run(struct vcpu_svm *svm, int cpu) { - struct svm_cpu_data *sd = per_cpu(svm_data, cpu); + struct svm_cpu_data *sd = per_cpu_ptr(&svm_data, cpu); int asid = sev_get_asid(svm->vcpu.kvm); /* Assign the asid allocated with this SEV guest */ diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index f3813dbacb9f..ce362e88a567 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -245,7 +245,7 @@ struct kvm_ldttss_desc { u32 zero1; } __attribute__((packed)); -DEFINE_PER_CPU(struct svm_cpu_data *, svm_data); +DEFINE_PER_CPU(struct svm_cpu_data, svm_data); /* * Only MSR_TSC_AUX is switched via the user return hook. EFER is switched via @@ -346,12 +346,6 @@ int svm_set_efer(struct kvm_vcpu *vcpu, u64 efer) return 0; } -static int is_external_interrupt(u32 info) -{ - info &= SVM_EVTINJ_TYPE_MASK | SVM_EVTINJ_VALID; - return info == (SVM_EVTINJ_VALID | SVM_EVTINJ_TYPE_INTR); -} - static u32 svm_get_interrupt_shadow(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); @@ -461,24 +455,22 @@ static int svm_update_soft_interrupt_rip(struct kvm_vcpu *vcpu) return 0; } -static void svm_queue_exception(struct kvm_vcpu *vcpu) +static void svm_inject_exception(struct kvm_vcpu *vcpu) { + struct kvm_queued_exception *ex = &vcpu->arch.exception; struct vcpu_svm *svm = to_svm(vcpu); - unsigned nr = vcpu->arch.exception.nr; - bool has_error_code = vcpu->arch.exception.has_error_code; - u32 error_code = vcpu->arch.exception.error_code; - kvm_deliver_exception_payload(vcpu); + kvm_deliver_exception_payload(vcpu, ex); - if (kvm_exception_is_soft(nr) && + if (kvm_exception_is_soft(ex->vector) && svm_update_soft_interrupt_rip(vcpu)) return; - svm->vmcb->control.event_inj = nr + svm->vmcb->control.event_inj = ex->vector | SVM_EVTINJ_VALID - | (has_error_code ? SVM_EVTINJ_VALID_ERR : 0) + | (ex->has_error_code ? SVM_EVTINJ_VALID_ERR : 0) | SVM_EVTINJ_TYPE_EXEPT; - svm->vmcb->control.event_inj_err = error_code; + svm->vmcb->control.event_inj_err = ex->error_code; } static void svm_init_erratum_383(void) @@ -583,12 +575,7 @@ static int svm_hardware_enable(void) pr_err("%s: err EOPNOTSUPP on %d\n", __func__, me); return -EINVAL; } - sd = per_cpu(svm_data, me); - if (!sd) { - pr_err("%s: svm_data is NULL on %d\n", __func__, me); - return -EINVAL; - } - + sd = per_cpu_ptr(&svm_data, me); sd->asid_generation = 1; sd->max_asid = cpuid_ebx(SVM_CPUID_FUNC) - 1; sd->next_asid = sd->max_asid + 1; @@ -599,7 +586,7 @@ static int svm_hardware_enable(void) wrmsrl(MSR_EFER, efer | EFER_SVME); - wrmsrl(MSR_VM_HSAVE_PA, __sme_page_pa(sd->save_area)); + wrmsrl(MSR_VM_HSAVE_PA, sd->save_area_pa); if (static_cpu_has(X86_FEATURE_TSCRATEMSR)) { /* @@ -648,42 +635,37 @@ static int svm_hardware_enable(void) static void svm_cpu_uninit(int cpu) { - struct svm_cpu_data *sd = per_cpu(svm_data, cpu); + struct svm_cpu_data *sd = per_cpu_ptr(&svm_data, cpu); - if (!sd) + if (!sd->save_area) return; - per_cpu(svm_data, cpu) = NULL; kfree(sd->sev_vmcbs); __free_page(sd->save_area); - kfree(sd); + sd->save_area_pa = 0; + sd->save_area = NULL; } static int svm_cpu_init(int cpu) { - struct svm_cpu_data *sd; + struct svm_cpu_data *sd = per_cpu_ptr(&svm_data, cpu); int ret = -ENOMEM; - sd = kzalloc(sizeof(struct svm_cpu_data), GFP_KERNEL); - if (!sd) - return ret; - sd->cpu = cpu; + memset(sd, 0, sizeof(struct svm_cpu_data)); sd->save_area = alloc_page(GFP_KERNEL | __GFP_ZERO); if (!sd->save_area) - goto free_cpu_data; + return ret; ret = sev_cpu_init(sd); if (ret) goto free_save_area; - per_cpu(svm_data, cpu) = sd; - + sd->save_area_pa = __sme_page_pa(sd->save_area); return 0; free_save_area: __free_page(sd->save_area); -free_cpu_data: - kfree(sd); + sd->save_area = NULL; return ret; } @@ -732,6 +714,15 @@ static bool msr_write_intercepted(struct kvm_vcpu *vcpu, u32 msr) u32 offset; u32 *msrpm; + /* + * For non-nested case: + * If the L01 MSR bitmap does not intercept the MSR, then we need to + * save it. + * + * For nested case: + * If the L02 MSR bitmap does not intercept the MSR, then we need to + * save it. + */ msrpm = is_guest_mode(vcpu) ? to_svm(vcpu)->nested.msrpm: to_svm(vcpu)->msrpm; @@ -1427,7 +1418,7 @@ static void svm_clear_current_vmcb(struct vmcb *vmcb) int i; for_each_online_cpu(i) - cmpxchg(&per_cpu(svm_data, i)->current_vmcb, vmcb, NULL); + cmpxchg(per_cpu_ptr(&svm_data.current_vmcb, i), vmcb, NULL); } static void svm_vcpu_free(struct kvm_vcpu *vcpu) @@ -1441,6 +1432,7 @@ static void svm_vcpu_free(struct kvm_vcpu *vcpu) */ svm_clear_current_vmcb(svm->vmcb); + svm_leave_nested(vcpu); svm_free_nested(svm); sev_free_vcpu(vcpu); @@ -1452,7 +1444,7 @@ static void svm_vcpu_free(struct kvm_vcpu *vcpu) static void svm_prepare_switch_to_guest(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); - struct svm_cpu_data *sd = per_cpu(svm_data, vcpu->cpu); + struct svm_cpu_data *sd = per_cpu_ptr(&svm_data, vcpu->cpu); if (sev_es_guest(vcpu->kvm)) sev_es_unmap_ghcb(svm); @@ -1464,7 +1456,7 @@ static void svm_prepare_switch_to_guest(struct kvm_vcpu *vcpu) * Save additional host state that will be restored on VMEXIT (sev-es) * or subsequent vmload of host save area. */ - vmsave(__sme_page_pa(sd->save_area)); + vmsave(sd->save_area_pa); if (sev_es_guest(vcpu->kvm)) { struct sev_es_save_area *hostsa; hostsa = (struct sev_es_save_area *)(page_address(sd->save_area) + 0x400); @@ -1489,7 +1481,7 @@ static void svm_prepare_host_switch(struct kvm_vcpu *vcpu) static void svm_vcpu_load(struct kvm_vcpu *vcpu, int cpu) { struct vcpu_svm *svm = to_svm(vcpu); - struct svm_cpu_data *sd = per_cpu(svm_data, cpu); + struct svm_cpu_data *sd = per_cpu_ptr(&svm_data, cpu); if (sd->current_vmcb != svm->vmcb) { sd->current_vmcb = svm->vmcb; @@ -1975,7 +1967,7 @@ static int npf_interception(struct kvm_vcpu *vcpu) u64 fault_address = svm->vmcb->control.exit_info_2; u64 error_code = svm->vmcb->control.exit_info_1; - trace_kvm_page_fault(fault_address, error_code); + trace_kvm_page_fault(vcpu, fault_address, error_code); return kvm_mmu_page_fault(vcpu, fault_address, error_code, static_cpu_has(X86_FEATURE_DECODEASSISTS) ? svm->vmcb->control.insn_bytes : NULL, @@ -2341,7 +2333,8 @@ void svm_set_gif(struct vcpu_svm *svm, bool value) enable_gif(svm); if (svm->vcpu.arch.smi_pending || svm->vcpu.arch.nmi_pending || - kvm_cpu_has_injectable_intr(&svm->vcpu)) + kvm_cpu_has_injectable_intr(&svm->vcpu) || + kvm_apic_has_pending_init_or_sipi(&svm->vcpu)) kvm_make_request(KVM_REQ_EVENT, &svm->vcpu); } else { disable_gif(svm); @@ -2711,9 +2704,9 @@ static int svm_get_msr_feature(struct kvm_msr_entry *msr) msr->data = 0; switch (msr->index) { - case MSR_F10H_DECFG: - if (boot_cpu_has(X86_FEATURE_LFENCE_RDTSC)) - msr->data |= MSR_F10H_DECFG_LFENCE_SERIALIZE; + case MSR_AMD64_DE_CFG: + if (cpu_feature_enabled(X86_FEATURE_LFENCE_RDTSC)) + msr->data |= MSR_AMD64_DE_CFG_LFENCE_SERIALIZE; break; case MSR_IA32_PERF_CAPABILITIES: return 0; @@ -2814,7 +2807,7 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) msr_info->data = 0x1E; } break; - case MSR_F10H_DECFG: + case MSR_AMD64_DE_CFG: msr_info->data = svm->msr_decfg; break; default: @@ -3043,7 +3036,7 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) case MSR_VM_IGNNE: vcpu_unimpl(vcpu, "unimplemented wrmsr: 0x%x data 0x%llx\n", ecx, data); break; - case MSR_F10H_DECFG: { + case MSR_AMD64_DE_CFG: { struct kvm_msr_entry msr_entry; msr_entry.index = msr->index; @@ -3427,15 +3420,6 @@ static int svm_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath) return 0; } - if (is_external_interrupt(svm->vmcb->control.exit_int_info) && - exit_code != SVM_EXIT_EXCP_BASE + PF_VECTOR && - exit_code != SVM_EXIT_NPF && exit_code != SVM_EXIT_TASK_SWITCH && - exit_code != SVM_EXIT_INTR && exit_code != SVM_EXIT_NMI) - printk(KERN_ERR "%s: unexpected exit_int_info 0x%x " - "exit_code 0x%x\n", - __func__, svm->vmcb->control.exit_int_info, - exit_code); - if (exit_fastpath != EXIT_FASTPATH_NONE) return 1; @@ -3444,7 +3428,7 @@ static int svm_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath) static void reload_tss(struct kvm_vcpu *vcpu) { - struct svm_cpu_data *sd = per_cpu(svm_data, vcpu->cpu); + struct svm_cpu_data *sd = per_cpu_ptr(&svm_data, vcpu->cpu); sd->tss_desc->type = 9; /* available 32/64-bit TSS */ load_TR_desc(); @@ -3452,7 +3436,7 @@ static void reload_tss(struct kvm_vcpu *vcpu) static void pre_svm_run(struct kvm_vcpu *vcpu) { - struct svm_cpu_data *sd = per_cpu(svm_data, vcpu->cpu); + struct svm_cpu_data *sd = per_cpu_ptr(&svm_data, vcpu->cpu); struct vcpu_svm *svm = to_svm(vcpu); /* @@ -3522,7 +3506,7 @@ void svm_complete_interrupt_delivery(struct kvm_vcpu *vcpu, int delivery_mode, /* Note, this is called iff the local APIC is in-kernel. */ if (!READ_ONCE(vcpu->arch.apic->apicv_active)) { - /* Process the interrupt via inject_pending_event */ + /* Process the interrupt via kvm_check_and_inject_events(). */ kvm_make_request(KVM_REQ_EVENT, vcpu); kvm_vcpu_kick(vcpu); return; @@ -3912,30 +3896,16 @@ static fastpath_t svm_exit_handlers_fastpath(struct kvm_vcpu *vcpu) return EXIT_FASTPATH_NONE; } -static noinstr void svm_vcpu_enter_exit(struct kvm_vcpu *vcpu) +static noinstr void svm_vcpu_enter_exit(struct kvm_vcpu *vcpu, bool spec_ctrl_intercepted) { struct vcpu_svm *svm = to_svm(vcpu); - unsigned long vmcb_pa = svm->current_vmcb->pa; guest_state_enter_irqoff(); - if (sev_es_guest(vcpu->kvm)) { - __svm_sev_es_vcpu_run(vmcb_pa); - } else { - struct svm_cpu_data *sd = per_cpu(svm_data, vcpu->cpu); - - /* - * Use a single vmcb (vmcb01 because it's always valid) for - * context switching guest state via VMLOAD/VMSAVE, that way - * the state doesn't need to be copied between vmcb01 and - * vmcb02 when switching vmcbs for nested virtualization. - */ - vmload(svm->vmcb01.pa); - __svm_vcpu_run(vmcb_pa, (unsigned long *)&vcpu->arch.regs); - vmsave(svm->vmcb01.pa); - - vmload(__sme_page_pa(sd->save_area)); - } + if (sev_es_guest(vcpu->kvm)) + __svm_sev_es_vcpu_run(svm, spec_ctrl_intercepted); + else + __svm_vcpu_run(svm, spec_ctrl_intercepted); guest_state_exit_irqoff(); } @@ -3943,6 +3913,7 @@ static noinstr void svm_vcpu_enter_exit(struct kvm_vcpu *vcpu) static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); + bool spec_ctrl_intercepted = msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL); trace_kvm_entry(vcpu); @@ -3999,34 +3970,15 @@ static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu) * being speculatively taken. */ if (!static_cpu_has(X86_FEATURE_V_SPEC_CTRL)) - x86_spec_ctrl_set_guest(svm->spec_ctrl, svm->virt_spec_ctrl); + x86_spec_ctrl_set_guest(svm->virt_spec_ctrl); - svm_vcpu_enter_exit(vcpu); - - /* - * We do not use IBRS in the kernel. If this vCPU has used the - * SPEC_CTRL MSR it may have left it on; save the value and - * turn it off. This is much more efficient than blindly adding - * it to the atomic save/restore list. Especially as the former - * (Saving guest MSRs on vmexit) doesn't even exist in KVM. - * - * For non-nested case: - * If the L01 MSR bitmap does not intercept the MSR, then we need to - * save it. - * - * For nested case: - * If the L02 MSR bitmap does not intercept the MSR, then we need to - * save it. - */ - if (!static_cpu_has(X86_FEATURE_V_SPEC_CTRL) && - unlikely(!msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL))) - svm->spec_ctrl = native_read_msr(MSR_IA32_SPEC_CTRL); + svm_vcpu_enter_exit(vcpu, spec_ctrl_intercepted); if (!sev_es_guest(vcpu->kvm)) reload_tss(vcpu); if (!static_cpu_has(X86_FEATURE_V_SPEC_CTRL)) - x86_spec_ctrl_restore_host(svm->spec_ctrl, svm->virt_spec_ctrl); + x86_spec_ctrl_restore_host(svm->virt_spec_ctrl); if (!sev_es_guest(vcpu->kvm)) { vcpu->arch.cr2 = svm->vmcb->save.cr2; @@ -4697,15 +4649,7 @@ static bool svm_apic_init_signal_blocked(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); - /* - * TODO: Last condition latch INIT signals on vCPU when - * vCPU is in guest-mode and vmcb12 defines intercept on INIT. - * To properly emulate the INIT intercept, - * svm_check_nested_events() should call nested_svm_vmexit() - * if an INIT signal is pending. - */ - return !gif_set(svm) || - (vmcb_is_intercept(&svm->vmcb->control, INTERCEPT_INIT)); + return !gif_set(svm); } static void svm_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector) @@ -4798,7 +4742,7 @@ static struct kvm_x86_ops svm_x86_ops __initdata = { .patch_hypercall = svm_patch_hypercall, .inject_irq = svm_inject_irq, .inject_nmi = svm_inject_nmi, - .queue_exception = svm_queue_exception, + .inject_exception = svm_inject_exception, .cancel_injection = svm_cancel_injection, .interrupt_allowed = svm_interrupt_allowed, .nmi_allowed = svm_nmi_allowed, diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index 6a7686bf6900..199a2ecef1ce 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -209,7 +209,6 @@ struct vcpu_svm { struct vmcb *vmcb; struct kvm_vmcb_info vmcb01; struct kvm_vmcb_info *current_vmcb; - struct svm_cpu_data *svm_data; u32 asid; u32 sysenter_esp_hi; u32 sysenter_eip_hi; @@ -281,8 +280,6 @@ struct vcpu_svm { }; struct svm_cpu_data { - int cpu; - u64 asid_generation; u32 max_asid; u32 next_asid; @@ -290,13 +287,15 @@ struct svm_cpu_data { struct kvm_ldttss_desc *tss_desc; struct page *save_area; + unsigned long save_area_pa; + struct vmcb *current_vmcb; /* index = sev_asid, value = vmcb pointer */ struct vmcb **sev_vmcbs; }; -DECLARE_PER_CPU(struct svm_cpu_data *, svm_data); +DECLARE_PER_CPU(struct svm_cpu_data, svm_data); void recalc_intercepts(struct vcpu_svm *svm); @@ -683,7 +682,7 @@ void sev_es_unmap_ghcb(struct vcpu_svm *svm); /* vmenter.S */ -void __svm_sev_es_vcpu_run(unsigned long vmcb_pa); -void __svm_vcpu_run(unsigned long vmcb_pa, unsigned long *regs); +void __svm_sev_es_vcpu_run(struct vcpu_svm *svm, bool spec_ctrl_intercepted); +void __svm_vcpu_run(struct vcpu_svm *svm, bool spec_ctrl_intercepted); #endif diff --git a/arch/x86/kvm/svm/svm_ops.h b/arch/x86/kvm/svm/svm_ops.h index 9430d6437c9f..36c8af87a707 100644 --- a/arch/x86/kvm/svm/svm_ops.h +++ b/arch/x86/kvm/svm/svm_ops.h @@ -61,9 +61,4 @@ static __always_inline void vmsave(unsigned long pa) svm_asm1(vmsave, "a" (pa), "memory"); } -static __always_inline void vmload(unsigned long pa) -{ - svm_asm1(vmload, "a" (pa), "memory"); -} - #endif /* __KVM_X86_SVM_OPS_H */ diff --git a/arch/x86/kvm/svm/vmenter.S b/arch/x86/kvm/svm/vmenter.S index 723f8534986c..34367dc203f2 100644 --- a/arch/x86/kvm/svm/vmenter.S +++ b/arch/x86/kvm/svm/vmenter.S @@ -4,35 +4,97 @@ #include <asm/bitsperlong.h> #include <asm/kvm_vcpu_regs.h> #include <asm/nospec-branch.h> +#include "kvm-asm-offsets.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 +#define VCPU_RCX (SVM_vcpu_arch_regs + __VCPU_REGS_RCX * WORD_SIZE) +#define VCPU_RDX (SVM_vcpu_arch_regs + __VCPU_REGS_RDX * WORD_SIZE) +#define VCPU_RBX (SVM_vcpu_arch_regs + __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 +#define VCPU_RBP (SVM_vcpu_arch_regs + __VCPU_REGS_RBP * WORD_SIZE) +#define VCPU_RSI (SVM_vcpu_arch_regs + __VCPU_REGS_RSI * WORD_SIZE) +#define VCPU_RDI (SVM_vcpu_arch_regs + __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 +#define VCPU_R8 (SVM_vcpu_arch_regs + __VCPU_REGS_R8 * WORD_SIZE) +#define VCPU_R9 (SVM_vcpu_arch_regs + __VCPU_REGS_R9 * WORD_SIZE) +#define VCPU_R10 (SVM_vcpu_arch_regs + __VCPU_REGS_R10 * WORD_SIZE) +#define VCPU_R11 (SVM_vcpu_arch_regs + __VCPU_REGS_R11 * WORD_SIZE) +#define VCPU_R12 (SVM_vcpu_arch_regs + __VCPU_REGS_R12 * WORD_SIZE) +#define VCPU_R13 (SVM_vcpu_arch_regs + __VCPU_REGS_R13 * WORD_SIZE) +#define VCPU_R14 (SVM_vcpu_arch_regs + __VCPU_REGS_R14 * WORD_SIZE) +#define VCPU_R15 (SVM_vcpu_arch_regs + __VCPU_REGS_R15 * WORD_SIZE) #endif +#define SVM_vmcb01_pa (SVM_vmcb01 + KVM_VMCB_pa) + .section .noinstr.text, "ax" +.macro RESTORE_GUEST_SPEC_CTRL + /* No need to do anything if SPEC_CTRL is unset or V_SPEC_CTRL is set */ + ALTERNATIVE_2 "", \ + "jmp 800f", X86_FEATURE_MSR_SPEC_CTRL, \ + "", X86_FEATURE_V_SPEC_CTRL +801: +.endm +.macro RESTORE_GUEST_SPEC_CTRL_BODY +800: + /* + * SPEC_CTRL handling: if the guest's SPEC_CTRL value differs from the + * host's, write the MSR. This is kept out-of-line so that the common + * case does not have to jump. + * + * IMPORTANT: To avoid RSB underflow attacks and any other nastiness, + * there must not be any returns or indirect branches between this code + * and vmentry. + */ + movl SVM_spec_ctrl(%_ASM_DI), %eax + cmp PER_CPU_VAR(x86_spec_ctrl_current), %eax + je 801b + mov $MSR_IA32_SPEC_CTRL, %ecx + xor %edx, %edx + wrmsr + jmp 801b +.endm + +.macro RESTORE_HOST_SPEC_CTRL + /* No need to do anything if SPEC_CTRL is unset or V_SPEC_CTRL is set */ + ALTERNATIVE_2 "", \ + "jmp 900f", X86_FEATURE_MSR_SPEC_CTRL, \ + "", X86_FEATURE_V_SPEC_CTRL +901: +.endm +.macro RESTORE_HOST_SPEC_CTRL_BODY +900: + /* Same for after vmexit. */ + mov $MSR_IA32_SPEC_CTRL, %ecx + + /* + * Load the value that the guest had written into MSR_IA32_SPEC_CTRL, + * if it was not intercepted during guest execution. + */ + cmpb $0, (%_ASM_SP) + jnz 998f + rdmsr + movl %eax, SVM_spec_ctrl(%_ASM_DI) +998: + + /* Now restore the host value of the MSR if different from the guest's. */ + movl PER_CPU_VAR(x86_spec_ctrl_current), %eax + cmp SVM_spec_ctrl(%_ASM_DI), %eax + je 901b + xor %edx, %edx + wrmsr + jmp 901b +.endm + + /** * __svm_vcpu_run - Run a vCPU via a transition to SVM guest mode - * @vmcb_pa: unsigned long - * @regs: unsigned long * (to guest registers) + * @svm: struct vcpu_svm * + * @spec_ctrl_intercepted: bool */ SYM_FUNC_START(__svm_vcpu_run) push %_ASM_BP @@ -47,49 +109,71 @@ SYM_FUNC_START(__svm_vcpu_run) #endif push %_ASM_BX - /* Save @regs. */ + /* + * Save variables needed after vmexit on the stack, in inverse + * order compared to when they are needed. + */ + + /* Accessed directly from the stack in RESTORE_HOST_SPEC_CTRL. */ push %_ASM_ARG2 - /* Save @vmcb. */ + /* Needed to restore access to percpu variables. */ + __ASM_SIZE(push) PER_CPU_VAR(svm_data + SD_save_area_pa) + + /* Finally save @svm. */ push %_ASM_ARG1 - /* Move @regs to RAX. */ - mov %_ASM_ARG2, %_ASM_AX +.ifnc _ASM_ARG1, _ASM_DI + /* + * Stash @svm in RDI early. On 32-bit, arguments are in RAX, RCX + * and RDX which are clobbered by RESTORE_GUEST_SPEC_CTRL. + */ + mov %_ASM_ARG1, %_ASM_DI +.endif + + /* Clobbers RAX, RCX, RDX. */ + RESTORE_GUEST_SPEC_CTRL + + /* + * Use a single vmcb (vmcb01 because it's always valid) for + * context switching guest state via VMLOAD/VMSAVE, that way + * the state doesn't need to be copied between vmcb01 and + * vmcb02 when switching vmcbs for nested virtualization. + */ + mov SVM_vmcb01_pa(%_ASM_DI), %_ASM_AX +1: vmload %_ASM_AX +2: + + /* Get svm->current_vmcb->pa into RAX. */ + mov SVM_current_vmcb(%_ASM_DI), %_ASM_AX + mov KVM_VMCB_pa(%_ASM_AX), %_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 + mov VCPU_RCX(%_ASM_DI), %_ASM_CX + mov VCPU_RDX(%_ASM_DI), %_ASM_DX + mov VCPU_RBX(%_ASM_DI), %_ASM_BX + mov VCPU_RBP(%_ASM_DI), %_ASM_BP + mov VCPU_RSI(%_ASM_DI), %_ASM_SI #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 + mov VCPU_R8 (%_ASM_DI), %r8 + mov VCPU_R9 (%_ASM_DI), %r9 + mov VCPU_R10(%_ASM_DI), %r10 + mov VCPU_R11(%_ASM_DI), %r11 + mov VCPU_R12(%_ASM_DI), %r12 + mov VCPU_R13(%_ASM_DI), %r13 + mov VCPU_R14(%_ASM_DI), %r14 + mov VCPU_R15(%_ASM_DI), %r15 #endif - - /* "POP" @vmcb to RAX. */ - pop %_ASM_AX + mov VCPU_RDI(%_ASM_DI), %_ASM_DI /* Enter guest mode */ sti -1: vmrun %_ASM_AX - -2: cli - -#ifdef CONFIG_RETPOLINE - /* IMPORTANT: Stuff the RSB immediately after VM-Exit, before RET! */ - FILL_RETURN_BUFFER %_ASM_AX, RSB_CLEAR_LOOPS, X86_FEATURE_RETPOLINE -#endif +3: vmrun %_ASM_AX +4: + cli - /* "POP" @regs to RAX. */ + /* Pop @svm to RAX while it's the only available register. */ pop %_ASM_AX /* Save all guest registers. */ @@ -110,6 +194,26 @@ SYM_FUNC_START(__svm_vcpu_run) mov %r15, VCPU_R15(%_ASM_AX) #endif + /* @svm can stay in RDI from now on. */ + mov %_ASM_AX, %_ASM_DI + + mov SVM_vmcb01_pa(%_ASM_DI), %_ASM_AX +5: vmsave %_ASM_AX +6: + + /* Restores GSBASE among other things, allowing access to percpu data. */ + pop %_ASM_AX +7: vmload %_ASM_AX +8: + +#ifdef CONFIG_RETPOLINE + /* IMPORTANT: Stuff the RSB immediately after VM-Exit, before RET! */ + FILL_RETURN_BUFFER %_ASM_AX, RSB_CLEAR_LOOPS, X86_FEATURE_RETPOLINE +#endif + + /* Clobbers RAX, RCX, RDX. */ + RESTORE_HOST_SPEC_CTRL + /* * Mitigate RETBleed for AMD/Hygon Zen uarch. RET should be * untrained as soon as we exit the VM and are back to the @@ -145,6 +249,9 @@ SYM_FUNC_START(__svm_vcpu_run) xor %r15d, %r15d #endif + /* "Pop" @spec_ctrl_intercepted. */ + pop %_ASM_BX + pop %_ASM_BX #ifdef CONFIG_X86_64 @@ -159,17 +266,33 @@ SYM_FUNC_START(__svm_vcpu_run) pop %_ASM_BP RET -3: cmpb $0, kvm_rebooting + RESTORE_GUEST_SPEC_CTRL_BODY + RESTORE_HOST_SPEC_CTRL_BODY + +10: cmpb $0, kvm_rebooting jne 2b ud2 +30: cmpb $0, kvm_rebooting + jne 4b + ud2 +50: cmpb $0, kvm_rebooting + jne 6b + ud2 +70: cmpb $0, kvm_rebooting + jne 8b + ud2 - _ASM_EXTABLE(1b, 3b) + _ASM_EXTABLE(1b, 10b) + _ASM_EXTABLE(3b, 30b) + _ASM_EXTABLE(5b, 50b) + _ASM_EXTABLE(7b, 70b) SYM_FUNC_END(__svm_vcpu_run) /** * __svm_sev_es_vcpu_run - Run a SEV-ES vCPU via a transition to SVM guest mode - * @vmcb_pa: unsigned long + * @svm: struct vcpu_svm * + * @spec_ctrl_intercepted: bool */ SYM_FUNC_START(__svm_sev_es_vcpu_run) push %_ASM_BP @@ -184,8 +307,31 @@ SYM_FUNC_START(__svm_sev_es_vcpu_run) #endif push %_ASM_BX - /* Move @vmcb to RAX. */ - mov %_ASM_ARG1, %_ASM_AX + /* + * Save variables needed after vmexit on the stack, in inverse + * order compared to when they are needed. + */ + + /* Accessed directly from the stack in RESTORE_HOST_SPEC_CTRL. */ + push %_ASM_ARG2 + + /* Save @svm. */ + push %_ASM_ARG1 + +.ifnc _ASM_ARG1, _ASM_DI + /* + * Stash @svm in RDI early. On 32-bit, arguments are in RAX, RCX + * and RDX which are clobbered by RESTORE_GUEST_SPEC_CTRL. + */ + mov %_ASM_ARG1, %_ASM_DI +.endif + + /* Clobbers RAX, RCX, RDX. */ + RESTORE_GUEST_SPEC_CTRL + + /* Get svm->current_vmcb->pa into RAX. */ + mov SVM_current_vmcb(%_ASM_DI), %_ASM_AX + mov KVM_VMCB_pa(%_ASM_AX), %_ASM_AX /* Enter guest mode */ sti @@ -194,11 +340,17 @@ SYM_FUNC_START(__svm_sev_es_vcpu_run) 2: cli + /* Pop @svm to RDI, guest registers have been saved already. */ + pop %_ASM_DI + #ifdef CONFIG_RETPOLINE /* IMPORTANT: Stuff the RSB immediately after VM-Exit, before RET! */ FILL_RETURN_BUFFER %_ASM_AX, RSB_CLEAR_LOOPS, X86_FEATURE_RETPOLINE #endif + /* Clobbers RAX, RCX, RDX. */ + RESTORE_HOST_SPEC_CTRL + /* * Mitigate RETBleed for AMD/Hygon Zen uarch. RET should be * untrained as soon as we exit the VM and are back to the @@ -208,6 +360,9 @@ SYM_FUNC_START(__svm_sev_es_vcpu_run) */ UNTRAIN_RET + /* "Pop" @spec_ctrl_intercepted. */ + pop %_ASM_BX + pop %_ASM_BX #ifdef CONFIG_X86_64 @@ -222,6 +377,9 @@ SYM_FUNC_START(__svm_sev_es_vcpu_run) pop %_ASM_BP RET + RESTORE_GUEST_SPEC_CTRL_BODY + RESTORE_HOST_SPEC_CTRL_BODY + 3: cmpb $0, kvm_rebooting jne 2b ud2 diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h index 2120d7c060a9..bc25589ad588 100644 --- a/arch/x86/kvm/trace.h +++ b/arch/x86/kvm/trace.h @@ -394,20 +394,25 @@ TRACE_EVENT(kvm_inj_exception, * Tracepoint for page fault. */ TRACE_EVENT(kvm_page_fault, - TP_PROTO(unsigned long fault_address, unsigned int error_code), - TP_ARGS(fault_address, error_code), + TP_PROTO(struct kvm_vcpu *vcpu, u64 fault_address, u64 error_code), + TP_ARGS(vcpu, fault_address, error_code), TP_STRUCT__entry( - __field( unsigned long, fault_address ) - __field( unsigned int, error_code ) + __field( unsigned int, vcpu_id ) + __field( unsigned long, guest_rip ) + __field( u64, fault_address ) + __field( u64, error_code ) ), TP_fast_assign( + __entry->vcpu_id = vcpu->vcpu_id; + __entry->guest_rip = kvm_rip_read(vcpu); __entry->fault_address = fault_address; __entry->error_code = error_code; ), - TP_printk("address %lx error_code %x", + TP_printk("vcpu %u rip 0x%lx address 0x%016llx error_code 0x%llx", + __entry->vcpu_id, __entry->guest_rip, __entry->fault_address, __entry->error_code) ); @@ -589,10 +594,12 @@ TRACE_EVENT(kvm_pv_eoi, /* * Tracepoint for nested VMRUN */ -TRACE_EVENT(kvm_nested_vmrun, +TRACE_EVENT(kvm_nested_vmenter, TP_PROTO(__u64 rip, __u64 vmcb, __u64 nested_rip, __u32 int_ctl, - __u32 event_inj, bool npt), - TP_ARGS(rip, vmcb, nested_rip, int_ctl, event_inj, npt), + __u32 event_inj, bool tdp_enabled, __u64 guest_tdp_pgd, + __u64 guest_cr3, __u32 isa), + TP_ARGS(rip, vmcb, nested_rip, int_ctl, event_inj, tdp_enabled, + guest_tdp_pgd, guest_cr3, isa), TP_STRUCT__entry( __field( __u64, rip ) @@ -600,7 +607,9 @@ TRACE_EVENT(kvm_nested_vmrun, __field( __u64, nested_rip ) __field( __u32, int_ctl ) __field( __u32, event_inj ) - __field( bool, npt ) + __field( bool, tdp_enabled ) + __field( __u64, guest_pgd ) + __field( __u32, isa ) ), TP_fast_assign( @@ -609,14 +618,24 @@ TRACE_EVENT(kvm_nested_vmrun, __entry->nested_rip = nested_rip; __entry->int_ctl = int_ctl; __entry->event_inj = event_inj; - __entry->npt = npt; - ), - - TP_printk("rip: 0x%016llx vmcb: 0x%016llx nrip: 0x%016llx int_ctl: 0x%08x " - "event_inj: 0x%08x npt: %s", - __entry->rip, __entry->vmcb, __entry->nested_rip, - __entry->int_ctl, __entry->event_inj, - __entry->npt ? "on" : "off") + __entry->tdp_enabled = tdp_enabled; + __entry->guest_pgd = tdp_enabled ? guest_tdp_pgd : guest_cr3; + __entry->isa = isa; + ), + + TP_printk("rip: 0x%016llx %s: 0x%016llx nested_rip: 0x%016llx " + "int_ctl: 0x%08x event_inj: 0x%08x nested_%s=%s %s: 0x%016llx", + __entry->rip, + __entry->isa == KVM_ISA_VMX ? "vmcs" : "vmcb", + __entry->vmcb, + __entry->nested_rip, + __entry->int_ctl, + __entry->event_inj, + __entry->isa == KVM_ISA_VMX ? "ept" : "npt", + __entry->tdp_enabled ? "y" : "n", + !__entry->tdp_enabled ? "guest_cr3" : + __entry->isa == KVM_ISA_VMX ? "nested_eptp" : "nested_cr3", + __entry->guest_pgd) ); TRACE_EVENT(kvm_nested_intercepts, diff --git a/arch/x86/kvm/vmx/capabilities.h b/arch/x86/kvm/vmx/capabilities.h index c5e5dfef69c7..07254314f3dd 100644 --- a/arch/x86/kvm/vmx/capabilities.h +++ b/arch/x86/kvm/vmx/capabilities.h @@ -24,8 +24,6 @@ extern int __read_mostly pt_mode; #define PMU_CAP_FW_WRITES (1ULL << 13) #define PMU_CAP_LBR_FMT 0x3f -#define DEBUGCTLMSR_LBR_MASK (DEBUGCTLMSR_LBR | DEBUGCTLMSR_FREEZE_LBRS_ON_PMI) - struct nested_vmx_msrs { /* * We only store the "true" versions of the VMX capability MSRs. We @@ -65,6 +63,7 @@ struct vmcs_config { u64 cpu_based_3rd_exec_ctrl; u32 vmexit_ctrl; u32 vmentry_ctrl; + u64 misc; struct nested_vmx_msrs nested; }; extern struct vmcs_config vmcs_config; @@ -82,7 +81,8 @@ static inline bool cpu_has_vmx_basic_inout(void) static inline bool cpu_has_virtual_nmis(void) { - return vmcs_config.pin_based_exec_ctrl & PIN_BASED_VIRTUAL_NMIS; + return vmcs_config.pin_based_exec_ctrl & PIN_BASED_VIRTUAL_NMIS && + vmcs_config.cpu_based_exec_ctrl & CPU_BASED_NMI_WINDOW_EXITING; } static inline bool cpu_has_vmx_preemption_timer(void) @@ -224,11 +224,8 @@ static inline bool cpu_has_vmx_vmfunc(void) static inline bool cpu_has_vmx_shadow_vmcs(void) { - u64 vmx_msr; - /* check if the cpu supports writing r/o exit information fields */ - rdmsrl(MSR_IA32_VMX_MISC, vmx_msr); - if (!(vmx_msr & MSR_IA32_VMX_MISC_VMWRITE_SHADOW_RO_FIELDS)) + if (!(vmcs_config.misc & MSR_IA32_VMX_MISC_VMWRITE_SHADOW_RO_FIELDS)) return false; return vmcs_config.cpu_based_2nd_exec_ctrl & @@ -370,10 +367,7 @@ static inline bool cpu_has_vmx_invvpid_global(void) static inline bool cpu_has_vmx_intel_pt(void) { - u64 vmx_msr; - - rdmsrl(MSR_IA32_VMX_MISC, vmx_msr); - return (vmx_msr & MSR_IA32_VMX_MISC_INTEL_PT) && + return (vmcs_config.misc & MSR_IA32_VMX_MISC_INTEL_PT) && (vmcs_config.cpu_based_2nd_exec_ctrl & SECONDARY_EXEC_PT_USE_GPA) && (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_RTIT_CTL); } @@ -404,6 +398,7 @@ static inline bool vmx_pebs_supported(void) static inline u64 vmx_get_perf_capabilities(void) { u64 perf_cap = PMU_CAP_FW_WRITES; + struct x86_pmu_lbr lbr; u64 host_perf_cap = 0; if (!enable_pmu) @@ -412,7 +407,8 @@ static inline u64 vmx_get_perf_capabilities(void) if (boot_cpu_has(X86_FEATURE_PDCM)) rdmsrl(MSR_IA32_PERF_CAPABILITIES, host_perf_cap); - perf_cap |= host_perf_cap & PMU_CAP_LBR_FMT; + if (x86_perf_get_lbr(&lbr) >= 0 && lbr.nr) + perf_cap |= host_perf_cap & PMU_CAP_LBR_FMT; if (vmx_pebs_supported()) { perf_cap |= host_perf_cap & PERF_CAP_PEBS_MASK; @@ -423,19 +419,6 @@ static inline u64 vmx_get_perf_capabilities(void) return perf_cap; } -static inline u64 vmx_supported_debugctl(void) -{ - u64 debugctl = 0; - - if (boot_cpu_has(X86_FEATURE_BUS_LOCK_DETECT)) - debugctl |= DEBUGCTLMSR_BUS_LOCK_DETECT; - - if (vmx_get_perf_capabilities() & PMU_CAP_LBR_FMT) - debugctl |= DEBUGCTLMSR_LBR_MASK; - - return debugctl; -} - static inline bool cpu_has_notify_vmexit(void) { return vmcs_config.cpu_based_2nd_exec_ctrl & diff --git a/arch/x86/kvm/vmx/evmcs.c b/arch/x86/kvm/vmx/evmcs.c index 6a61b1ae7942..d8b23c96d627 100644 --- a/arch/x86/kvm/vmx/evmcs.c +++ b/arch/x86/kvm/vmx/evmcs.c @@ -10,6 +10,8 @@ #include "vmx.h" #include "trace.h" +#define CC KVM_NESTED_VMENTER_CONSISTENCY_CHECK + DEFINE_STATIC_KEY_FALSE(enable_evmcs); #define EVMCS1_OFFSET(x) offsetof(struct hv_enlightened_vmcs, x) @@ -28,6 +30,8 @@ const struct evmcs_field vmcs_field_to_evmcs_1[] = { HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), EVMCS1_FIELD(HOST_IA32_EFER, host_ia32_efer, HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), + EVMCS1_FIELD(HOST_IA32_PERF_GLOBAL_CTRL, host_ia32_perf_global_ctrl, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), EVMCS1_FIELD(HOST_CR0, host_cr0, HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), EVMCS1_FIELD(HOST_CR3, host_cr3, @@ -78,6 +82,8 @@ const struct evmcs_field vmcs_field_to_evmcs_1[] = { HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), EVMCS1_FIELD(GUEST_IA32_EFER, guest_ia32_efer, HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), + EVMCS1_FIELD(GUEST_IA32_PERF_GLOBAL_CTRL, guest_ia32_perf_global_ctrl, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), EVMCS1_FIELD(GUEST_PDPTR0, guest_pdptr0, HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), EVMCS1_FIELD(GUEST_PDPTR1, guest_pdptr1, @@ -126,6 +132,28 @@ const struct evmcs_field vmcs_field_to_evmcs_1[] = { HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), EVMCS1_FIELD(XSS_EXIT_BITMAP, xss_exit_bitmap, HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP2), + EVMCS1_FIELD(ENCLS_EXITING_BITMAP, encls_exiting_bitmap, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP2), + EVMCS1_FIELD(TSC_MULTIPLIER, tsc_multiplier, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP2), + /* + * Not used by KVM: + * + * EVMCS1_FIELD(0x00006828, guest_ia32_s_cet, + * HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), + * EVMCS1_FIELD(0x0000682A, guest_ssp, + * HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_BASIC), + * EVMCS1_FIELD(0x0000682C, guest_ia32_int_ssp_table_addr, + * HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), + * EVMCS1_FIELD(0x00002816, guest_ia32_lbr_ctl, + * HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), + * EVMCS1_FIELD(0x00006C18, host_ia32_s_cet, + * HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), + * EVMCS1_FIELD(0x00006C1A, host_ssp, + * HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), + * EVMCS1_FIELD(0x00006C1C, host_ia32_int_ssp_table_addr, + * HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), + */ /* 64 bit read only */ EVMCS1_FIELD(GUEST_PHYSICAL_ADDRESS, guest_physical_address, @@ -294,19 +322,6 @@ const struct evmcs_field vmcs_field_to_evmcs_1[] = { }; const unsigned int nr_evmcs_1_fields = ARRAY_SIZE(vmcs_field_to_evmcs_1); -#if IS_ENABLED(CONFIG_HYPERV) -__init void evmcs_sanitize_exec_ctrls(struct vmcs_config *vmcs_conf) -{ - vmcs_conf->cpu_based_exec_ctrl &= ~EVMCS1_UNSUPPORTED_EXEC_CTRL; - vmcs_conf->pin_based_exec_ctrl &= ~EVMCS1_UNSUPPORTED_PINCTRL; - vmcs_conf->cpu_based_2nd_exec_ctrl &= ~EVMCS1_UNSUPPORTED_2NDEXEC; - vmcs_conf->cpu_based_3rd_exec_ctrl = 0; - - vmcs_conf->vmexit_ctrl &= ~EVMCS1_UNSUPPORTED_VMEXIT_CTRL; - vmcs_conf->vmentry_ctrl &= ~EVMCS1_UNSUPPORTED_VMENTRY_CTRL; -} -#endif - bool nested_enlightened_vmentry(struct kvm_vcpu *vcpu, u64 *evmcs_gpa) { struct hv_vp_assist_page assist_page; @@ -334,6 +349,9 @@ uint16_t nested_get_evmcs_version(struct kvm_vcpu *vcpu) * versions: lower 8 bits is the minimal version, higher 8 bits is the * maximum supported version. KVM supports versions from 1 to * KVM_EVMCS_VERSION. + * + * Note, do not check the Hyper-V is fully enabled in guest CPUID, this + * helper is used to _get_ the vCPU's supported CPUID. */ if (kvm_cpu_cap_get(X86_FEATURE_VMX) && (!vcpu || to_vmx(vcpu)->nested.enlightened_vmcs_enabled)) @@ -342,10 +360,67 @@ uint16_t nested_get_evmcs_version(struct kvm_vcpu *vcpu) return 0; } -void nested_evmcs_filter_control_msr(u32 msr_index, u64 *pdata) +enum evmcs_revision { + EVMCSv1_LEGACY, + NR_EVMCS_REVISIONS, +}; + +enum evmcs_ctrl_type { + EVMCS_EXIT_CTRLS, + EVMCS_ENTRY_CTRLS, + EVMCS_2NDEXEC, + EVMCS_PINCTRL, + EVMCS_VMFUNC, + NR_EVMCS_CTRLS, +}; + +static const u32 evmcs_unsupported_ctrls[NR_EVMCS_CTRLS][NR_EVMCS_REVISIONS] = { + [EVMCS_EXIT_CTRLS] = { + [EVMCSv1_LEGACY] = EVMCS1_UNSUPPORTED_VMEXIT_CTRL, + }, + [EVMCS_ENTRY_CTRLS] = { + [EVMCSv1_LEGACY] = EVMCS1_UNSUPPORTED_VMENTRY_CTRL, + }, + [EVMCS_2NDEXEC] = { + [EVMCSv1_LEGACY] = EVMCS1_UNSUPPORTED_2NDEXEC, + }, + [EVMCS_PINCTRL] = { + [EVMCSv1_LEGACY] = EVMCS1_UNSUPPORTED_PINCTRL, + }, + [EVMCS_VMFUNC] = { + [EVMCSv1_LEGACY] = EVMCS1_UNSUPPORTED_VMFUNC, + }, +}; + +static u32 evmcs_get_unsupported_ctls(enum evmcs_ctrl_type ctrl_type) +{ + enum evmcs_revision evmcs_rev = EVMCSv1_LEGACY; + + return evmcs_unsupported_ctrls[ctrl_type][evmcs_rev]; +} + +static bool evmcs_has_perf_global_ctrl(struct kvm_vcpu *vcpu) +{ + struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu); + + /* + * PERF_GLOBAL_CTRL has a quirk where some Windows guests may fail to + * boot if a PV CPUID feature flag is not also set. Treat the fields + * as unsupported if the flag is not set in guest CPUID. This should + * be called only for guest accesses, and all guest accesses should be + * gated on Hyper-V being enabled and initialized. + */ + if (WARN_ON_ONCE(!hv_vcpu)) + return false; + + return hv_vcpu->cpuid_cache.nested_ebx & HV_X64_NESTED_EVMCS1_PERF_GLOBAL_CTRL; +} + +void nested_evmcs_filter_control_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata) { u32 ctl_low = (u32)*pdata; u32 ctl_high = (u32)(*pdata >> 32); + u32 unsupported_ctrls; /* * Hyper-V 2016 and 2019 try using these features even when eVMCS @@ -354,77 +429,70 @@ void nested_evmcs_filter_control_msr(u32 msr_index, u64 *pdata) switch (msr_index) { case MSR_IA32_VMX_EXIT_CTLS: case MSR_IA32_VMX_TRUE_EXIT_CTLS: - ctl_high &= ~EVMCS1_UNSUPPORTED_VMEXIT_CTRL; + unsupported_ctrls = evmcs_get_unsupported_ctls(EVMCS_EXIT_CTRLS); + if (!evmcs_has_perf_global_ctrl(vcpu)) + unsupported_ctrls |= VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL; + ctl_high &= ~unsupported_ctrls; break; case MSR_IA32_VMX_ENTRY_CTLS: case MSR_IA32_VMX_TRUE_ENTRY_CTLS: - ctl_high &= ~EVMCS1_UNSUPPORTED_VMENTRY_CTRL; + unsupported_ctrls = evmcs_get_unsupported_ctls(EVMCS_ENTRY_CTRLS); + if (!evmcs_has_perf_global_ctrl(vcpu)) + unsupported_ctrls |= VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL; + ctl_high &= ~unsupported_ctrls; break; case MSR_IA32_VMX_PROCBASED_CTLS2: - ctl_high &= ~EVMCS1_UNSUPPORTED_2NDEXEC; + ctl_high &= ~evmcs_get_unsupported_ctls(EVMCS_2NDEXEC); break; case MSR_IA32_VMX_TRUE_PINBASED_CTLS: case MSR_IA32_VMX_PINBASED_CTLS: - ctl_high &= ~EVMCS1_UNSUPPORTED_PINCTRL; + ctl_high &= ~evmcs_get_unsupported_ctls(EVMCS_PINCTRL); break; case MSR_IA32_VMX_VMFUNC: - ctl_low &= ~EVMCS1_UNSUPPORTED_VMFUNC; + ctl_low &= ~evmcs_get_unsupported_ctls(EVMCS_VMFUNC); break; } *pdata = ctl_low | ((u64)ctl_high << 32); } +static bool nested_evmcs_is_valid_controls(enum evmcs_ctrl_type ctrl_type, + u32 val) +{ + return !(val & evmcs_get_unsupported_ctls(ctrl_type)); +} + int nested_evmcs_check_controls(struct vmcs12 *vmcs12) { - int ret = 0; - u32 unsupp_ctl; - - unsupp_ctl = vmcs12->pin_based_vm_exec_control & - EVMCS1_UNSUPPORTED_PINCTRL; - if (unsupp_ctl) { - trace_kvm_nested_vmenter_failed( - "eVMCS: unsupported pin-based VM-execution controls", - unsupp_ctl); - ret = -EINVAL; - } + if (CC(!nested_evmcs_is_valid_controls(EVMCS_PINCTRL, + vmcs12->pin_based_vm_exec_control))) + return -EINVAL; - unsupp_ctl = vmcs12->secondary_vm_exec_control & - EVMCS1_UNSUPPORTED_2NDEXEC; - if (unsupp_ctl) { - trace_kvm_nested_vmenter_failed( - "eVMCS: unsupported secondary VM-execution controls", - unsupp_ctl); - ret = -EINVAL; - } + if (CC(!nested_evmcs_is_valid_controls(EVMCS_2NDEXEC, + vmcs12->secondary_vm_exec_control))) + return -EINVAL; - unsupp_ctl = vmcs12->vm_exit_controls & - EVMCS1_UNSUPPORTED_VMEXIT_CTRL; - if (unsupp_ctl) { - trace_kvm_nested_vmenter_failed( - "eVMCS: unsupported VM-exit controls", - unsupp_ctl); - ret = -EINVAL; - } + if (CC(!nested_evmcs_is_valid_controls(EVMCS_EXIT_CTRLS, + vmcs12->vm_exit_controls))) + return -EINVAL; - unsupp_ctl = vmcs12->vm_entry_controls & - EVMCS1_UNSUPPORTED_VMENTRY_CTRL; - if (unsupp_ctl) { - trace_kvm_nested_vmenter_failed( - "eVMCS: unsupported VM-entry controls", - unsupp_ctl); - ret = -EINVAL; - } + if (CC(!nested_evmcs_is_valid_controls(EVMCS_ENTRY_CTRLS, + vmcs12->vm_entry_controls))) + return -EINVAL; - unsupp_ctl = vmcs12->vm_function_control & EVMCS1_UNSUPPORTED_VMFUNC; - if (unsupp_ctl) { - trace_kvm_nested_vmenter_failed( - "eVMCS: unsupported VM-function controls", - unsupp_ctl); - ret = -EINVAL; - } + /* + * VM-Func controls are 64-bit, but KVM currently doesn't support any + * controls in bits 63:32, i.e. dropping those bits on the consistency + * check is intentional. + */ + if (WARN_ON_ONCE(vmcs12->vm_function_control >> 32)) + return -EINVAL; - return ret; + if (CC(!nested_evmcs_is_valid_controls(EVMCS_VMFUNC, + vmcs12->vm_function_control))) + return -EINVAL; + + return 0; } int nested_enable_evmcs(struct kvm_vcpu *vcpu, diff --git a/arch/x86/kvm/vmx/evmcs.h b/arch/x86/kvm/vmx/evmcs.h index f886a8ff0342..6f746ef3c038 100644 --- a/arch/x86/kvm/vmx/evmcs.h +++ b/arch/x86/kvm/vmx/evmcs.h @@ -42,8 +42,6 @@ DECLARE_STATIC_KEY_FALSE(enable_evmcs); * PLE_GAP = 0x00004020, * PLE_WINDOW = 0x00004022, * VMX_PREEMPTION_TIMER_VALUE = 0x0000482E, - * GUEST_IA32_PERF_GLOBAL_CTRL = 0x00002808, - * HOST_IA32_PERF_GLOBAL_CTRL = 0x00002c04, * * Currently unsupported in KVM: * GUEST_IA32_RTIT_CTL = 0x00002814, @@ -61,9 +59,8 @@ DECLARE_STATIC_KEY_FALSE(enable_evmcs); SECONDARY_EXEC_TSC_SCALING | \ SECONDARY_EXEC_PAUSE_LOOP_EXITING) #define EVMCS1_UNSUPPORTED_VMEXIT_CTRL \ - (VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL | \ - VM_EXIT_SAVE_VMX_PREEMPTION_TIMER) -#define EVMCS1_UNSUPPORTED_VMENTRY_CTRL (VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL) + (VM_EXIT_SAVE_VMX_PREEMPTION_TIMER) +#define EVMCS1_UNSUPPORTED_VMENTRY_CTRL (0) #define EVMCS1_UNSUPPORTED_VMFUNC (VMX_VMFUNC_EPTP_SWITCHING) struct evmcs_field { @@ -212,7 +209,6 @@ static inline void evmcs_load(u64 phys_addr) vp_ap->enlighten_vmentry = 1; } -__init void evmcs_sanitize_exec_ctrls(struct vmcs_config *vmcs_conf); #else /* !IS_ENABLED(CONFIG_HYPERV) */ static __always_inline void evmcs_write64(unsigned long field, u64 value) {} static inline void evmcs_write32(unsigned long field, u32 value) {} @@ -243,7 +239,7 @@ bool nested_enlightened_vmentry(struct kvm_vcpu *vcpu, u64 *evmcs_gpa); uint16_t nested_get_evmcs_version(struct kvm_vcpu *vcpu); int nested_enable_evmcs(struct kvm_vcpu *vcpu, uint16_t *vmcs_version); -void nested_evmcs_filter_control_msr(u32 msr_index, u64 *pdata); +void nested_evmcs_filter_control_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata); int nested_evmcs_check_controls(struct vmcs12 *vmcs12); #endif /* __KVM_X86_VMX_EVMCS_H */ diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index ddd4367d4826..5b0d4859e4b7 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -439,61 +439,22 @@ static bool nested_vmx_is_page_fault_vmexit(struct vmcs12 *vmcs12, return inequality ^ bit; } - -/* - * KVM wants to inject page-faults which it got to the guest. This function - * checks whether in a nested guest, we need to inject them to L1 or L2. - */ -static int nested_vmx_check_exception(struct kvm_vcpu *vcpu, unsigned long *exit_qual) +static bool nested_vmx_is_exception_vmexit(struct kvm_vcpu *vcpu, u8 vector, + u32 error_code) { struct vmcs12 *vmcs12 = get_vmcs12(vcpu); - unsigned int nr = vcpu->arch.exception.nr; - bool has_payload = vcpu->arch.exception.has_payload; - unsigned long payload = vcpu->arch.exception.payload; - - if (nr == PF_VECTOR) { - if (vcpu->arch.exception.nested_apf) { - *exit_qual = vcpu->arch.apf.nested_apf_token; - return 1; - } - if (nested_vmx_is_page_fault_vmexit(vmcs12, - vcpu->arch.exception.error_code)) { - *exit_qual = has_payload ? payload : vcpu->arch.cr2; - return 1; - } - } else if (vmcs12->exception_bitmap & (1u << nr)) { - if (nr == DB_VECTOR) { - if (!has_payload) { - payload = vcpu->arch.dr6; - payload &= ~DR6_BT; - payload ^= DR6_ACTIVE_LOW; - } - *exit_qual = payload; - } else - *exit_qual = 0; - return 1; - } - return 0; -} - -static bool nested_vmx_handle_page_fault_workaround(struct kvm_vcpu *vcpu, - struct x86_exception *fault) -{ - struct vmcs12 *vmcs12 = get_vmcs12(vcpu); - - WARN_ON(!is_guest_mode(vcpu)); + /* + * Drop bits 31:16 of the error code when performing the #PF mask+match + * check. All VMCS fields involved are 32 bits, but Intel CPUs never + * set bits 31:16 and VMX disallows setting bits 31:16 in the injected + * error code. Including the to-be-dropped bits in the check might + * result in an "impossible" or missed exit from L1's perspective. + */ + if (vector == PF_VECTOR) + return nested_vmx_is_page_fault_vmexit(vmcs12, (u16)error_code); - if (nested_vmx_is_page_fault_vmexit(vmcs12, fault->error_code) && - !WARN_ON_ONCE(to_vmx(vcpu)->nested.nested_run_pending)) { - vmcs12->vm_exit_intr_error_code = fault->error_code; - nested_vmx_vmexit(vcpu, EXIT_REASON_EXCEPTION_NMI, - PF_VECTOR | INTR_TYPE_HARD_EXCEPTION | - INTR_INFO_DELIVER_CODE_MASK | INTR_INFO_VALID_MASK, - fault->address); - return true; - } - return false; + return (vmcs12->exception_bitmap & (1u << vector)); } static int nested_vmx_check_io_bitmap_controls(struct kvm_vcpu *vcpu, @@ -1607,6 +1568,10 @@ static void copy_enlightened_to_vmcs12(struct vcpu_vmx *vmx, u32 hv_clean_fields vmcs12->guest_rflags = evmcs->guest_rflags; vmcs12->guest_interruptibility_info = evmcs->guest_interruptibility_info; + /* + * Not present in struct vmcs12: + * vmcs12->guest_ssp = evmcs->guest_ssp; + */ } if (unlikely(!(hv_clean_fields & @@ -1653,6 +1618,13 @@ static void copy_enlightened_to_vmcs12(struct vcpu_vmx *vmx, u32 hv_clean_fields vmcs12->host_fs_selector = evmcs->host_fs_selector; vmcs12->host_gs_selector = evmcs->host_gs_selector; vmcs12->host_tr_selector = evmcs->host_tr_selector; + vmcs12->host_ia32_perf_global_ctrl = evmcs->host_ia32_perf_global_ctrl; + /* + * Not present in struct vmcs12: + * vmcs12->host_ia32_s_cet = evmcs->host_ia32_s_cet; + * vmcs12->host_ssp = evmcs->host_ssp; + * vmcs12->host_ia32_int_ssp_table_addr = evmcs->host_ia32_int_ssp_table_addr; + */ } if (unlikely(!(hv_clean_fields & @@ -1720,6 +1692,8 @@ static void copy_enlightened_to_vmcs12(struct vcpu_vmx *vmx, u32 hv_clean_fields vmcs12->tsc_offset = evmcs->tsc_offset; vmcs12->virtual_apic_page_addr = evmcs->virtual_apic_page_addr; vmcs12->xss_exit_bitmap = evmcs->xss_exit_bitmap; + vmcs12->encls_exiting_bitmap = evmcs->encls_exiting_bitmap; + vmcs12->tsc_multiplier = evmcs->tsc_multiplier; } if (unlikely(!(hv_clean_fields & @@ -1767,6 +1741,13 @@ static void copy_enlightened_to_vmcs12(struct vcpu_vmx *vmx, u32 hv_clean_fields vmcs12->guest_bndcfgs = evmcs->guest_bndcfgs; vmcs12->guest_activity_state = evmcs->guest_activity_state; vmcs12->guest_sysenter_cs = evmcs->guest_sysenter_cs; + vmcs12->guest_ia32_perf_global_ctrl = evmcs->guest_ia32_perf_global_ctrl; + /* + * Not present in struct vmcs12: + * vmcs12->guest_ia32_s_cet = evmcs->guest_ia32_s_cet; + * vmcs12->guest_ia32_lbr_ctl = evmcs->guest_ia32_lbr_ctl; + * vmcs12->guest_ia32_int_ssp_table_addr = evmcs->guest_ia32_int_ssp_table_addr; + */ } /* @@ -1869,12 +1850,23 @@ static void copy_vmcs12_to_enlightened(struct vcpu_vmx *vmx) * evmcs->vm_exit_msr_store_count = vmcs12->vm_exit_msr_store_count; * evmcs->vm_exit_msr_load_count = vmcs12->vm_exit_msr_load_count; * evmcs->vm_entry_msr_load_count = vmcs12->vm_entry_msr_load_count; + * evmcs->guest_ia32_perf_global_ctrl = vmcs12->guest_ia32_perf_global_ctrl; + * evmcs->host_ia32_perf_global_ctrl = vmcs12->host_ia32_perf_global_ctrl; + * evmcs->encls_exiting_bitmap = vmcs12->encls_exiting_bitmap; + * evmcs->tsc_multiplier = vmcs12->tsc_multiplier; * * Not present in struct vmcs12: * evmcs->exit_io_instruction_ecx = vmcs12->exit_io_instruction_ecx; * evmcs->exit_io_instruction_esi = vmcs12->exit_io_instruction_esi; * evmcs->exit_io_instruction_edi = vmcs12->exit_io_instruction_edi; * evmcs->exit_io_instruction_eip = vmcs12->exit_io_instruction_eip; + * evmcs->host_ia32_s_cet = vmcs12->host_ia32_s_cet; + * evmcs->host_ssp = vmcs12->host_ssp; + * evmcs->host_ia32_int_ssp_table_addr = vmcs12->host_ia32_int_ssp_table_addr; + * evmcs->guest_ia32_s_cet = vmcs12->guest_ia32_s_cet; + * evmcs->guest_ia32_lbr_ctl = vmcs12->guest_ia32_lbr_ctl; + * evmcs->guest_ia32_int_ssp_table_addr = vmcs12->guest_ia32_int_ssp_table_addr; + * evmcs->guest_ssp = vmcs12->guest_ssp; */ evmcs->guest_es_selector = vmcs12->guest_es_selector; @@ -1982,7 +1974,7 @@ static enum nested_evmptrld_status nested_vmx_handle_enlightened_vmptrld( bool evmcs_gpa_changed = false; u64 evmcs_gpa; - if (likely(!vmx->nested.enlightened_vmcs_enabled)) + if (likely(!guest_cpuid_has_evmcs(vcpu))) return EVMPTRLD_DISABLED; if (!nested_enlightened_vmentry(vcpu, &evmcs_gpa)) { @@ -2328,9 +2320,14 @@ static void prepare_vmcs02_early(struct vcpu_vmx *vmx, struct loaded_vmcs *vmcs0 * are emulated by vmx_set_efer() in prepare_vmcs02(), but speculate * on the related bits (if supported by the CPU) in the hope that * we can avoid VMWrites during vmx_set_efer(). + * + * Similarly, take vmcs01's PERF_GLOBAL_CTRL in the hope that if KVM is + * loading PERF_GLOBAL_CTRL via the VMCS for L1, then KVM will want to + * do the same for L2. */ exec_control = __vm_entry_controls_get(vmcs01); - exec_control |= vmcs12->vm_entry_controls; + exec_control |= (vmcs12->vm_entry_controls & + ~VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL); exec_control &= ~(VM_ENTRY_IA32E_MODE | VM_ENTRY_LOAD_IA32_EFER); if (cpu_has_load_ia32_efer()) { if (guest_efer & EFER_LMA) @@ -2570,7 +2567,7 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, * bits which we consider mandatory enabled. * The CR0_READ_SHADOW is what L2 should have expected to read given * the specifications by L1; It's not enough to take - * vmcs12->cr0_read_shadow because on our cr0_guest_host_mask we we + * vmcs12->cr0_read_shadow because on our cr0_guest_host_mask we * have more bits than L1 expected. */ vmx_set_cr0(vcpu, vmcs12->guest_cr0); @@ -2863,7 +2860,7 @@ static int nested_vmx_check_controls(struct kvm_vcpu *vcpu, nested_check_vm_entry_controls(vcpu, vmcs12)) return -EINVAL; - if (to_vmx(vcpu)->nested.enlightened_vmcs_enabled) + if (guest_cpuid_has_evmcs(vcpu)) return nested_evmcs_check_controls(vmcs12); return 0; @@ -3145,7 +3142,7 @@ static bool nested_get_evmcs_page(struct kvm_vcpu *vcpu) * L2 was running), map it here to make sure vmcs12 changes are * properly reflected. */ - if (vmx->nested.enlightened_vmcs_enabled && + if (guest_cpuid_has_evmcs(vcpu) && vmx->nested.hv_evmcs_vmptr == EVMPTR_MAP_PENDING) { enum nested_evmptrld_status evmptrld_status = nested_vmx_handle_enlightened_vmptrld(vcpu, false); @@ -3364,12 +3361,24 @@ enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, }; u32 failed_index; + trace_kvm_nested_vmenter(kvm_rip_read(vcpu), + vmx->nested.current_vmptr, + vmcs12->guest_rip, + vmcs12->guest_intr_status, + vmcs12->vm_entry_intr_info_field, + vmcs12->secondary_vm_exec_control & SECONDARY_EXEC_ENABLE_EPT, + vmcs12->ept_pointer, + vmcs12->guest_cr3, + KVM_ISA_VMX); + kvm_service_local_tlb_flush_requests(vcpu); evaluate_pending_interrupts = exec_controls_get(vmx) & (CPU_BASED_INTR_WINDOW_EXITING | CPU_BASED_NMI_WINDOW_EXITING); if (likely(!evaluate_pending_interrupts) && kvm_vcpu_apicv_active(vcpu)) evaluate_pending_interrupts |= vmx_has_apicv_interrupt(vcpu); + if (!evaluate_pending_interrupts) + evaluate_pending_interrupts |= kvm_apic_has_pending_init_or_sipi(vcpu); if (!vmx->nested.nested_run_pending || !(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS)) @@ -3450,18 +3459,10 @@ enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, } /* - * If L1 had a pending IRQ/NMI until it executed - * VMLAUNCH/VMRESUME 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 delivered directly to L2 (e.g. In case L1 don't - * intercept EXTERNAL_INTERRUPT). - * - * Usually this would be handled by the processor noticing an - * IRQ/NMI window request, or checking RVI during evaluation of - * pending virtual interrupts. However, this setting was done - * on VMCS01 and now VMCS02 is active instead. Thus, we force L0 - * to perform pending event evaluation by requesting a KVM_REQ_EVENT. + * Re-evaluate pending events if L1 had a pending IRQ/NMI/INIT/SIPI + * when it executed VMLAUNCH/VMRESUME, as entering non-root mode can + * effectively unblock various events, e.g. INIT/SIPI cause VM-Exit + * unconditionally. */ if (unlikely(evaluate_pending_interrupts)) kvm_make_request(KVM_REQ_EVENT, vcpu); @@ -3718,7 +3719,7 @@ static void vmcs12_save_pending_event(struct kvm_vcpu *vcpu, is_double_fault(exit_intr_info))) { vmcs12->idt_vectoring_info_field = 0; } else if (vcpu->arch.exception.injected) { - nr = vcpu->arch.exception.nr; + nr = vcpu->arch.exception.vector; idt_vectoring = nr | VECTORING_INFO_VALID_MASK; if (kvm_exception_is_soft(nr)) { @@ -3819,19 +3820,40 @@ mmio_needed: return -ENXIO; } -static void nested_vmx_inject_exception_vmexit(struct kvm_vcpu *vcpu, - unsigned long exit_qual) +static void nested_vmx_inject_exception_vmexit(struct kvm_vcpu *vcpu) { + struct kvm_queued_exception *ex = &vcpu->arch.exception_vmexit; + u32 intr_info = ex->vector | INTR_INFO_VALID_MASK; struct vmcs12 *vmcs12 = get_vmcs12(vcpu); - unsigned int nr = vcpu->arch.exception.nr; - u32 intr_info = nr | INTR_INFO_VALID_MASK; + unsigned long exit_qual; + + if (ex->has_payload) { + exit_qual = ex->payload; + } else if (ex->vector == PF_VECTOR) { + exit_qual = vcpu->arch.cr2; + } else if (ex->vector == DB_VECTOR) { + exit_qual = vcpu->arch.dr6; + exit_qual &= ~DR6_BT; + exit_qual ^= DR6_ACTIVE_LOW; + } else { + exit_qual = 0; + } - if (vcpu->arch.exception.has_error_code) { - vmcs12->vm_exit_intr_error_code = vcpu->arch.exception.error_code; + if (ex->has_error_code) { + /* + * Intel CPUs do not generate error codes with bits 31:16 set, + * and more importantly VMX disallows setting bits 31:16 in the + * injected error code for VM-Entry. Drop the bits to mimic + * hardware and avoid inducing failure on nested VM-Entry if L1 + * chooses to inject the exception back to L2. AMD CPUs _do_ + * generate "full" 32-bit error codes, so KVM allows userspace + * to inject exception error codes with bits 31:16 set. + */ + vmcs12->vm_exit_intr_error_code = (u16)ex->error_code; intr_info |= INTR_INFO_DELIVER_CODE_MASK; } - if (kvm_exception_is_soft(nr)) + if (kvm_exception_is_soft(ex->vector)) intr_info |= INTR_TYPE_SOFT_EXCEPTION; else intr_info |= INTR_TYPE_HARD_EXCEPTION; @@ -3844,16 +3866,39 @@ static void nested_vmx_inject_exception_vmexit(struct kvm_vcpu *vcpu, } /* - * Returns true if a debug trap is pending delivery. + * Returns true if a debug trap is (likely) pending delivery. Infer the class + * of a #DB (trap-like vs. fault-like) from the exception payload (to-be-DR6). + * Using the payload is flawed because code breakpoints (fault-like) and data + * breakpoints (trap-like) set the same bits in DR6 (breakpoint detected), i.e. + * this will return false positives if a to-be-injected code breakpoint #DB is + * pending (from KVM's perspective, but not "pending" across an instruction + * boundary). ICEBP, a.k.a. INT1, is also not reflected here even though it + * too is trap-like. * - * In KVM, debug traps bear an exception payload. As such, the class of a #DB - * exception may be inferred from the presence of an exception payload. + * KVM "works" despite these flaws as ICEBP isn't currently supported by the + * emulator, Monitor Trap Flag is not marked pending on intercepted #DBs (the + * #DB has already happened), and MTF isn't marked pending on code breakpoints + * from the emulator (because such #DBs are fault-like and thus don't trigger + * actions that fire on instruction retire). + */ +static unsigned long vmx_get_pending_dbg_trap(struct kvm_queued_exception *ex) +{ + if (!ex->pending || ex->vector != DB_VECTOR) + return 0; + + /* General Detect #DBs are always fault-like. */ + return ex->payload & ~DR6_BD; +} + +/* + * Returns true if there's a pending #DB exception that is lower priority than + * a pending Monitor Trap Flag VM-Exit. TSS T-flag #DBs are not emulated by + * KVM, but could theoretically be injected by userspace. Note, this code is + * imperfect, see above. */ -static inline bool vmx_pending_dbg_trap(struct kvm_vcpu *vcpu) +static bool vmx_is_low_priority_db_trap(struct kvm_queued_exception *ex) { - return vcpu->arch.exception.pending && - vcpu->arch.exception.nr == DB_VECTOR && - vcpu->arch.exception.payload; + return vmx_get_pending_dbg_trap(ex) & ~DR6_BT; } /* @@ -3865,9 +3910,11 @@ static inline bool vmx_pending_dbg_trap(struct kvm_vcpu *vcpu) */ static void nested_vmx_update_pending_dbg(struct kvm_vcpu *vcpu) { - if (vmx_pending_dbg_trap(vcpu)) - vmcs_writel(GUEST_PENDING_DBG_EXCEPTIONS, - vcpu->arch.exception.payload); + unsigned long pending_dbg; + + pending_dbg = vmx_get_pending_dbg_trap(&vcpu->arch.exception); + if (pending_dbg) + vmcs_writel(GUEST_PENDING_DBG_EXCEPTIONS, pending_dbg); } static bool nested_vmx_preemption_timer_pending(struct kvm_vcpu *vcpu) @@ -3876,21 +3923,113 @@ static bool nested_vmx_preemption_timer_pending(struct kvm_vcpu *vcpu) to_vmx(vcpu)->nested.preemption_timer_expired; } +static bool vmx_has_nested_events(struct kvm_vcpu *vcpu) +{ + return nested_vmx_preemption_timer_pending(vcpu) || + to_vmx(vcpu)->nested.mtf_pending; +} + +/* + * Per the Intel SDM's table "Priority Among Concurrent Events", with minor + * edits to fill in missing examples, e.g. #DB due to split-lock accesses, + * and less minor edits to splice in the priority of VMX Non-Root specific + * events, e.g. MTF and NMI/INTR-window exiting. + * + * 1 Hardware Reset and Machine Checks + * - RESET + * - Machine Check + * + * 2 Trap on Task Switch + * - T flag in TSS is set (on task switch) + * + * 3 External Hardware Interventions + * - FLUSH + * - STOPCLK + * - SMI + * - INIT + * + * 3.5 Monitor Trap Flag (MTF) VM-exit[1] + * + * 4 Traps on Previous Instruction + * - Breakpoints + * - Trap-class Debug Exceptions (#DB due to TF flag set, data/I-O + * breakpoint, or #DB due to a split-lock access) + * + * 4.3 VMX-preemption timer expired VM-exit + * + * 4.6 NMI-window exiting VM-exit[2] + * + * 5 Nonmaskable Interrupts (NMI) + * + * 5.5 Interrupt-window exiting VM-exit and Virtual-interrupt delivery + * + * 6 Maskable Hardware Interrupts + * + * 7 Code Breakpoint Fault + * + * 8 Faults from Fetching Next Instruction + * - Code-Segment Limit Violation + * - Code Page Fault + * - Control protection exception (missing ENDBRANCH at target of indirect + * call or jump) + * + * 9 Faults from Decoding Next Instruction + * - Instruction length > 15 bytes + * - Invalid Opcode + * - Coprocessor Not Available + * + *10 Faults on Executing Instruction + * - Overflow + * - Bound error + * - Invalid TSS + * - Segment Not Present + * - Stack fault + * - General Protection + * - Data Page Fault + * - Alignment Check + * - x86 FPU Floating-point exception + * - SIMD floating-point exception + * - Virtualization exception + * - Control protection exception + * + * [1] Per the "Monitor Trap Flag" section: System-management interrupts (SMIs), + * INIT signals, and higher priority events take priority over MTF VM exits. + * MTF VM exits take priority over debug-trap exceptions and lower priority + * events. + * + * [2] Debug-trap exceptions and higher priority events take priority over VM exits + * caused by the VMX-preemption timer. VM exits caused by the VMX-preemption + * timer take priority over VM exits caused by the "NMI-window exiting" + * VM-execution control and lower priority events. + * + * [3] Debug-trap exceptions and higher priority events take priority over VM exits + * caused by "NMI-window exiting". VM exits caused by this control take + * priority over non-maskable interrupts (NMIs) and lower priority events. + * + * [4] Virtual-interrupt delivery has the same priority as that of VM exits due to + * the 1-setting of the "interrupt-window exiting" VM-execution control. Thus, + * non-maskable interrupts (NMIs) and higher priority events take priority over + * delivery of a virtual interrupt; delivery of a virtual interrupt takes + * priority over external interrupts and lower priority events. + */ static int vmx_check_nested_events(struct kvm_vcpu *vcpu) { - struct vcpu_vmx *vmx = to_vmx(vcpu); - unsigned long exit_qual; - bool block_nested_events = - vmx->nested.nested_run_pending || kvm_event_needs_reinjection(vcpu); - bool mtf_pending = vmx->nested.mtf_pending; struct kvm_lapic *apic = vcpu->arch.apic; - + struct vcpu_vmx *vmx = to_vmx(vcpu); /* - * Clear the MTF state. If a higher priority VM-exit is delivered first, - * this state is discarded. + * Only a pending nested run blocks a pending exception. If there is a + * previously injected event, the pending exception occurred while said + * event was being delivered and thus needs to be handled. */ - if (!block_nested_events) - vmx->nested.mtf_pending = false; + bool block_nested_exceptions = vmx->nested.nested_run_pending; + /* + * New events (not exceptions) are only recognized at instruction + * boundaries. If an event needs reinjection, then KVM is handling a + * VM-Exit that occurred _during_ instruction execution; new events are + * blocked until the instruction completes. + */ + bool block_nested_events = block_nested_exceptions || + kvm_event_needs_reinjection(vcpu); if (lapic_in_kernel(vcpu) && test_bit(KVM_APIC_INIT, &apic->pending_events)) { @@ -3900,6 +4039,9 @@ static int vmx_check_nested_events(struct kvm_vcpu *vcpu) clear_bit(KVM_APIC_INIT, &apic->pending_events); if (vcpu->arch.mp_state != KVM_MP_STATE_INIT_RECEIVED) nested_vmx_vmexit(vcpu, EXIT_REASON_INIT_SIGNAL, 0, 0); + + /* MTF is discarded if the vCPU is in WFS. */ + vmx->nested.mtf_pending = false; return 0; } @@ -3909,31 +4051,41 @@ static int vmx_check_nested_events(struct kvm_vcpu *vcpu) return -EBUSY; clear_bit(KVM_APIC_SIPI, &apic->pending_events); - if (vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED) + if (vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED) { nested_vmx_vmexit(vcpu, EXIT_REASON_SIPI_SIGNAL, 0, apic->sipi_vector & 0xFFUL); - return 0; + return 0; + } + /* Fallthrough, the SIPI is completely ignored. */ } /* - * Process any exceptions that are not debug traps before MTF. + * Process exceptions that are higher priority than Monitor Trap Flag: + * fault-like exceptions, TSS T flag #DB (not emulated by KVM, but + * could theoretically come in from userspace), and ICEBP (INT1). * - * Note that only a pending nested run can block a pending exception. - * Otherwise an injected NMI/interrupt should either be - * lost or delivered to the nested hypervisor in the IDT_VECTORING_INFO, - * while delivering the pending exception. + * TODO: SMIs have higher priority than MTF and trap-like #DBs (except + * for TSS T flag #DBs). KVM also doesn't save/restore pending MTF + * across SMI/RSM as it should; that needs to be addressed in order to + * prioritize SMI over MTF and trap-like #DBs. */ - - if (vcpu->arch.exception.pending && !vmx_pending_dbg_trap(vcpu)) { - if (vmx->nested.nested_run_pending) + if (vcpu->arch.exception_vmexit.pending && + !vmx_is_low_priority_db_trap(&vcpu->arch.exception_vmexit)) { + if (block_nested_exceptions) return -EBUSY; - if (!nested_vmx_check_exception(vcpu, &exit_qual)) - goto no_vmexit; - nested_vmx_inject_exception_vmexit(vcpu, exit_qual); + + nested_vmx_inject_exception_vmexit(vcpu); return 0; } - if (mtf_pending) { + if (vcpu->arch.exception.pending && + !vmx_is_low_priority_db_trap(&vcpu->arch.exception)) { + if (block_nested_exceptions) + return -EBUSY; + goto no_vmexit; + } + + if (vmx->nested.mtf_pending) { if (block_nested_events) return -EBUSY; nested_vmx_update_pending_dbg(vcpu); @@ -3941,15 +4093,20 @@ static int vmx_check_nested_events(struct kvm_vcpu *vcpu) return 0; } - if (vcpu->arch.exception.pending) { - if (vmx->nested.nested_run_pending) + if (vcpu->arch.exception_vmexit.pending) { + if (block_nested_exceptions) return -EBUSY; - if (!nested_vmx_check_exception(vcpu, &exit_qual)) - goto no_vmexit; - nested_vmx_inject_exception_vmexit(vcpu, exit_qual); + + nested_vmx_inject_exception_vmexit(vcpu); return 0; } + if (vcpu->arch.exception.pending) { + if (block_nested_exceptions) + return -EBUSY; + goto no_vmexit; + } + if (nested_vmx_preemption_timer_pending(vcpu)) { if (block_nested_events) return -EBUSY; @@ -4255,14 +4412,6 @@ static void prepare_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, nested_vmx_abort(vcpu, VMX_ABORT_SAVE_GUEST_MSR_FAIL); } - - /* - * Drop what we picked up for L2 via vmx_complete_interrupts. It is - * preserved above and would only end up incorrectly in L1. - */ - vcpu->arch.nmi_injected = false; - kvm_clear_exception_queue(vcpu); - kvm_clear_interrupt_queue(vcpu); } /* @@ -4538,6 +4687,9 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason, struct vcpu_vmx *vmx = to_vmx(vcpu); struct vmcs12 *vmcs12 = get_vmcs12(vcpu); + /* Pending MTF traps are discarded on VM-Exit. */ + vmx->nested.mtf_pending = false; + /* trying to cancel vmlaunch/vmresume is a bug */ WARN_ON_ONCE(vmx->nested.nested_run_pending); @@ -4602,6 +4754,17 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason, WARN_ON_ONCE(nested_early_check); } + /* + * Drop events/exceptions that were queued for re-injection to L2 + * (picked up via vmx_complete_interrupts()), as well as exceptions + * that were pending for L2. Note, this must NOT be hoisted above + * prepare_vmcs12(), events/exceptions queued for re-injection need to + * be captured in vmcs12 (see vmcs12_save_pending_event()). + */ + vcpu->arch.nmi_injected = false; + kvm_clear_exception_queue(vcpu); + kvm_clear_interrupt_queue(vcpu); + vmx_switch_vmcs(vcpu, &vmx->vmcs01); /* Update any VMCS fields that might have changed while L2 ran */ @@ -4691,6 +4854,7 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason, static void nested_vmx_triple_fault(struct kvm_vcpu *vcpu) { + kvm_clear_request(KVM_REQ_TRIPLE_FAULT, vcpu); nested_vmx_vmexit(vcpu, EXIT_REASON_TRIPLE_FAULT, 0, 0); } @@ -5030,8 +5194,8 @@ static int handle_vmxoff(struct kvm_vcpu *vcpu) free_nested(vcpu); - /* Process a latched INIT during time CPU was in VMX operation */ - kvm_make_request(KVM_REQ_EVENT, vcpu); + if (kvm_apic_has_pending_init_or_sipi(vcpu)) + kvm_make_request(KVM_REQ_EVENT, vcpu); return nested_vmx_succeed(vcpu); } @@ -5067,7 +5231,7 @@ static int handle_vmclear(struct kvm_vcpu *vcpu) * state. It is possible that the area will stay mapped as * vmx->nested.hv_evmcs but this shouldn't be a problem. */ - if (likely(!vmx->nested.enlightened_vmcs_enabled || + if (likely(!guest_cpuid_has_evmcs(vcpu) || !nested_enlightened_vmentry(vcpu, &evmcs_gpa))) { if (vmptr == vmx->nested.current_vmptr) nested_release_vmcs12(vcpu); @@ -6277,9 +6441,6 @@ out: return kvm_state.size; } -/* - * Forcibly leave nested mode in order to be able to reset the VCPU later on. - */ void vmx_leave_nested(struct kvm_vcpu *vcpu) { if (is_guest_mode(vcpu)) { @@ -6463,6 +6624,9 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu, if (ret) goto error_guest_mode; + if (vmx->nested.mtf_pending) + kvm_make_request(KVM_REQ_EVENT, vcpu); + return 0; error_guest_mode: @@ -6522,8 +6686,10 @@ static u64 nested_vmx_calc_vmcs_enum_msr(void) * bit in the high half is on if the corresponding bit in the control field * may be on. See also vmx_control_verify(). */ -void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps) +void nested_vmx_setup_ctls_msrs(struct vmcs_config *vmcs_conf, u32 ept_caps) { + struct nested_vmx_msrs *msrs = &vmcs_conf->nested; + /* * Note that as a general rule, the high half of the MSRs (bits in * the control fields which may be 1) should be initialized by the @@ -6540,11 +6706,10 @@ void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps) */ /* pin-based controls */ - rdmsr(MSR_IA32_VMX_PINBASED_CTLS, - msrs->pinbased_ctls_low, - msrs->pinbased_ctls_high); - msrs->pinbased_ctls_low |= + msrs->pinbased_ctls_low = PIN_BASED_ALWAYSON_WITHOUT_TRUE_MSR; + + msrs->pinbased_ctls_high = vmcs_conf->pin_based_exec_ctrl; msrs->pinbased_ctls_high &= PIN_BASED_EXT_INTR_MASK | PIN_BASED_NMI_EXITING | @@ -6555,50 +6720,47 @@ void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps) PIN_BASED_VMX_PREEMPTION_TIMER; /* exit controls */ - rdmsr(MSR_IA32_VMX_EXIT_CTLS, - msrs->exit_ctls_low, - msrs->exit_ctls_high); msrs->exit_ctls_low = VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR; + msrs->exit_ctls_high = vmcs_conf->vmexit_ctrl; msrs->exit_ctls_high &= #ifdef CONFIG_X86_64 VM_EXIT_HOST_ADDR_SPACE_SIZE | #endif VM_EXIT_LOAD_IA32_PAT | VM_EXIT_SAVE_IA32_PAT | - VM_EXIT_CLEAR_BNDCFGS | VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL; + VM_EXIT_CLEAR_BNDCFGS; msrs->exit_ctls_high |= VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR | VM_EXIT_LOAD_IA32_EFER | VM_EXIT_SAVE_IA32_EFER | - VM_EXIT_SAVE_VMX_PREEMPTION_TIMER | VM_EXIT_ACK_INTR_ON_EXIT; + VM_EXIT_SAVE_VMX_PREEMPTION_TIMER | VM_EXIT_ACK_INTR_ON_EXIT | + VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL; /* We support free control of debug control saving. */ msrs->exit_ctls_low &= ~VM_EXIT_SAVE_DEBUG_CONTROLS; /* entry controls */ - rdmsr(MSR_IA32_VMX_ENTRY_CTLS, - msrs->entry_ctls_low, - msrs->entry_ctls_high); msrs->entry_ctls_low = VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR; + + msrs->entry_ctls_high = vmcs_conf->vmentry_ctrl; msrs->entry_ctls_high &= #ifdef CONFIG_X86_64 VM_ENTRY_IA32E_MODE | #endif - VM_ENTRY_LOAD_IA32_PAT | VM_ENTRY_LOAD_BNDCFGS | - VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL; + VM_ENTRY_LOAD_IA32_PAT | VM_ENTRY_LOAD_BNDCFGS; msrs->entry_ctls_high |= - (VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR | VM_ENTRY_LOAD_IA32_EFER); + (VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR | VM_ENTRY_LOAD_IA32_EFER | + VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL); /* We support free control of debug control loading. */ msrs->entry_ctls_low &= ~VM_ENTRY_LOAD_DEBUG_CONTROLS; /* cpu-based controls */ - rdmsr(MSR_IA32_VMX_PROCBASED_CTLS, - msrs->procbased_ctls_low, - msrs->procbased_ctls_high); msrs->procbased_ctls_low = CPU_BASED_ALWAYSON_WITHOUT_TRUE_MSR; + + msrs->procbased_ctls_high = vmcs_conf->cpu_based_exec_ctrl; msrs->procbased_ctls_high &= CPU_BASED_INTR_WINDOW_EXITING | CPU_BASED_NMI_WINDOW_EXITING | CPU_BASED_USE_TSC_OFFSETTING | @@ -6632,12 +6794,9 @@ void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps) * depend on CPUID bits, they are added later by * vmx_vcpu_after_set_cpuid. */ - if (msrs->procbased_ctls_high & CPU_BASED_ACTIVATE_SECONDARY_CONTROLS) - rdmsr(MSR_IA32_VMX_PROCBASED_CTLS2, - msrs->secondary_ctls_low, - msrs->secondary_ctls_high); - msrs->secondary_ctls_low = 0; + + msrs->secondary_ctls_high = vmcs_conf->cpu_based_2nd_exec_ctrl; msrs->secondary_ctls_high &= SECONDARY_EXEC_DESC | SECONDARY_EXEC_ENABLE_RDTSCP | @@ -6717,10 +6876,7 @@ void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps) msrs->secondary_ctls_high |= SECONDARY_EXEC_ENCLS_EXITING; /* miscellaneous data */ - rdmsr(MSR_IA32_VMX_MISC, - msrs->misc_low, - msrs->misc_high); - msrs->misc_low &= VMX_MISC_SAVE_EFER_LMA; + msrs->misc_low = (u32)vmcs_conf->misc & VMX_MISC_SAVE_EFER_LMA; msrs->misc_low |= MSR_IA32_VMX_MISC_VMWRITE_SHADOW_RO_FIELDS | VMX_MISC_EMULATED_PREEMPTION_TIMER_RATE | @@ -6814,9 +6970,9 @@ __init int nested_vmx_hardware_setup(int (*exit_handlers[])(struct kvm_vcpu *)) struct kvm_x86_nested_ops vmx_nested_ops = { .leave_nested = vmx_leave_nested, + .is_exception_vmexit = nested_vmx_is_exception_vmexit, .check_events = vmx_check_nested_events, - .handle_page_fault_workaround = nested_vmx_handle_page_fault_workaround, - .hv_timer_pending = nested_vmx_preemption_timer_pending, + .has_events = vmx_has_nested_events, .triple_fault = nested_vmx_triple_fault, .get_state = vmx_get_nested_state, .set_state = vmx_set_nested_state, diff --git a/arch/x86/kvm/vmx/nested.h b/arch/x86/kvm/vmx/nested.h index 88b00a7359e4..6312c9541c3c 100644 --- a/arch/x86/kvm/vmx/nested.h +++ b/arch/x86/kvm/vmx/nested.h @@ -17,7 +17,7 @@ enum nvmx_vmentry_status { }; void vmx_leave_nested(struct kvm_vcpu *vcpu); -void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps); +void nested_vmx_setup_ctls_msrs(struct vmcs_config *vmcs_conf, u32 ept_caps); void nested_vmx_hardware_unsetup(void); __init int nested_vmx_hardware_setup(int (*exit_handlers[])(struct kvm_vcpu *)); void nested_vmx_set_vmcs_shadowing_bitmap(void); diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c index c399637a3a79..10b33da9bd05 100644 --- a/arch/x86/kvm/vmx/pmu_intel.c +++ b/arch/x86/kvm/vmx/pmu_intel.c @@ -68,15 +68,11 @@ static struct kvm_pmc *intel_pmc_idx_to_pmc(struct kvm_pmu *pmu, int pmc_idx) } } -/* function is called when global control register has been updated. */ -static void global_ctrl_changed(struct kvm_pmu *pmu, u64 data) +static void reprogram_counters(struct kvm_pmu *pmu, u64 diff) { int bit; - u64 diff = pmu->global_ctrl ^ data; struct kvm_pmc *pmc; - pmu->global_ctrl = data; - for_each_set_bit(bit, (unsigned long *)&diff, X86_PMC_IDX_MAX) { pmc = intel_pmc_idx_to_pmc(pmu, bit); if (pmc) @@ -397,7 +393,7 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) struct kvm_pmc *pmc; u32 msr = msr_info->index; u64 data = msr_info->data; - u64 reserved_bits; + u64 reserved_bits, diff; switch (msr) { case MSR_CORE_PERF_FIXED_CTR_CTRL: @@ -418,7 +414,9 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if (pmu->global_ctrl == data) return 0; if (kvm_valid_perf_global_ctrl(pmu, data)) { - global_ctrl_changed(pmu, data); + diff = pmu->global_ctrl ^ data; + pmu->global_ctrl = data; + reprogram_counters(pmu, diff); return 0; } break; @@ -433,7 +431,9 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if (pmu->pebs_enable == data) return 0; if (!(data & pmu->pebs_enable_mask)) { + diff = pmu->pebs_enable ^ data; pmu->pebs_enable = data; + reprogram_counters(pmu, diff); return 0; } break; @@ -617,7 +617,7 @@ static void intel_pmu_init(struct kvm_vcpu *vcpu) struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); struct lbr_desc *lbr_desc = vcpu_to_lbr_desc(vcpu); - for (i = 0; i < INTEL_PMC_MAX_GENERIC; i++) { + for (i = 0; i < KVM_INTEL_PMC_MAX_GENERIC; i++) { pmu->gp_counters[i].type = KVM_PMC_GP; pmu->gp_counters[i].vcpu = vcpu; pmu->gp_counters[i].idx = i; @@ -643,7 +643,7 @@ static void intel_pmu_reset(struct kvm_vcpu *vcpu) struct kvm_pmc *pmc = NULL; int i; - for (i = 0; i < INTEL_PMC_MAX_GENERIC; i++) { + for (i = 0; i < KVM_INTEL_PMC_MAX_GENERIC; i++) { pmc = &pmu->gp_counters[i]; pmc_stop_counter(pmc); @@ -776,20 +776,23 @@ static void intel_pmu_cleanup(struct kvm_vcpu *vcpu) void intel_pmu_cross_mapped_check(struct kvm_pmu *pmu) { struct kvm_pmc *pmc = NULL; - int bit; + int bit, hw_idx; for_each_set_bit(bit, (unsigned long *)&pmu->global_ctrl, X86_PMC_IDX_MAX) { pmc = intel_pmc_idx_to_pmc(pmu, bit); if (!pmc || !pmc_speculative_in_use(pmc) || - !intel_pmc_is_enabled(pmc)) + !intel_pmc_is_enabled(pmc) || !pmc->perf_event) continue; - if (pmc->perf_event && pmc->idx != pmc->perf_event->hw.idx) { - pmu->host_cross_mapped_mask |= - BIT_ULL(pmc->perf_event->hw.idx); - } + /* + * A negative index indicates the event isn't mapped to a + * physical counter in the host, e.g. due to contention. + */ + hw_idx = pmc->perf_event->hw.idx; + if (hw_idx != pmc->idx && hw_idx > -1) + pmu->host_cross_mapped_mask |= BIT_ULL(hw_idx); } } diff --git a/arch/x86/kvm/vmx/sgx.c b/arch/x86/kvm/vmx/sgx.c index aba8cebdc587..8f95c7c01433 100644 --- a/arch/x86/kvm/vmx/sgx.c +++ b/arch/x86/kvm/vmx/sgx.c @@ -129,7 +129,7 @@ static int sgx_inject_fault(struct kvm_vcpu *vcpu, gva_t gva, int trapnr) ex.address = gva; ex.error_code_valid = true; ex.nested_page_fault = false; - kvm_inject_page_fault(vcpu, &ex); + kvm_inject_emulated_page_fault(vcpu, &ex); } else { kvm_inject_gp(vcpu, 0); } diff --git a/arch/x86/kvm/vmx/vmenter.S b/arch/x86/kvm/vmx/vmenter.S index 6de96b943804..0b5db4de4d09 100644 --- a/arch/x86/kvm/vmx/vmenter.S +++ b/arch/x86/kvm/vmx/vmenter.S @@ -1,12 +1,12 @@ /* SPDX-License-Identifier: GPL-2.0 */ #include <linux/linkage.h> #include <asm/asm.h> -#include <asm/asm-offsets.h> #include <asm/bitsperlong.h> #include <asm/kvm_vcpu_regs.h> #include <asm/nospec-branch.h> #include <asm/percpu.h> #include <asm/segment.h> +#include "kvm-asm-offsets.h" #include "run_flags.h" #define WORD_SIZE (BITS_PER_LONG / 8) @@ -189,13 +189,16 @@ SYM_INNER_LABEL(vmx_vmexit, SYM_L_GLOBAL) xor %ebx, %ebx .Lclear_regs: + /* Discard @regs. The register is irrelevant, it just can't be RBX. */ + pop %_ASM_AX + /* * Clear all general purpose registers except RSP and RBX 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 RSP is restored by hardware during + * free. RSP and RBX are exempt as RSP is restored by hardware during * VM-Exit and RBX is explicitly loaded with 0 or 1 to hold the return * value. */ @@ -216,9 +219,6 @@ SYM_INNER_LABEL(vmx_vmexit, SYM_L_GLOBAL) xor %r15d, %r15d #endif - /* "POP" @regs. */ - add $WORD_SIZE, %_ASM_SP - /* * IMPORTANT: RSB filling and SPEC_CTRL handling must be done before * the first unbalanced RET after vmexit! @@ -234,7 +234,6 @@ SYM_INNER_LABEL(vmx_vmexit, SYM_L_GLOBAL) FILL_RETURN_BUFFER %_ASM_CX, RSB_CLEAR_LOOPS, X86_FEATURE_RSB_VMEXIT,\ X86_FEATURE_RSB_VMEXIT_LITE - pop %_ASM_ARG2 /* @flags */ pop %_ASM_ARG1 /* @vmx */ @@ -293,22 +292,13 @@ SYM_FUNC_START(vmread_error_trampoline) push %r10 push %r11 #endif -#ifdef CONFIG_X86_64 + /* Load @field and @fault to arg1 and arg2 respectively. */ - mov 3*WORD_SIZE(%rbp), %_ASM_ARG2 - mov 2*WORD_SIZE(%rbp), %_ASM_ARG1 -#else - /* Parameters are passed on the stack for 32-bit (see asmlinkage). */ - push 3*WORD_SIZE(%ebp) - push 2*WORD_SIZE(%ebp) -#endif + mov 3*WORD_SIZE(%_ASM_BP), %_ASM_ARG2 + mov 2*WORD_SIZE(%_ASM_BP), %_ASM_ARG1 call vmread_error -#ifndef CONFIG_X86_64 - add $8, %esp -#endif - /* Zero out @fault, which will be popped into the result register. */ _ASM_MOV $0, 3*WORD_SIZE(%_ASM_BP) diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index d7f8331d6f7e..63247c57c72c 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -439,7 +439,7 @@ do { \ pr_warn_ratelimited(fmt); \ } while (0) -asmlinkage void vmread_error(unsigned long field, bool fault) +void vmread_error(unsigned long field, bool fault) { if (fault) kvm_spurious_fault(); @@ -843,8 +843,7 @@ static bool msr_write_intercepted(struct vcpu_vmx *vmx, u32 msr) if (!(exec_controls_get(vmx) & CPU_BASED_USE_MSR_BITMAPS)) return true; - return vmx_test_msr_bitmap_write(vmx->loaded_vmcs->msr_bitmap, - MSR_IA32_SPEC_CTRL); + return vmx_test_msr_bitmap_write(vmx->loaded_vmcs->msr_bitmap, msr); } unsigned int __vmx_vcpu_run_flags(struct vcpu_vmx *vmx) @@ -865,7 +864,7 @@ unsigned int __vmx_vcpu_run_flags(struct vcpu_vmx *vmx) return flags; } -static void clear_atomic_switch_msr_special(struct vcpu_vmx *vmx, +static __always_inline void clear_atomic_switch_msr_special(struct vcpu_vmx *vmx, unsigned long entry, unsigned long exit) { vm_entry_controls_clearbit(vmx, entry); @@ -923,7 +922,7 @@ skip_guest: vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, m->host.nr); } -static void add_atomic_switch_msr_special(struct vcpu_vmx *vmx, +static __always_inline void add_atomic_switch_msr_special(struct vcpu_vmx *vmx, unsigned long entry, unsigned long exit, unsigned long guest_val_vmcs, unsigned long host_val_vmcs, u64 guest_val, u64 host_val) @@ -1653,17 +1652,25 @@ static void vmx_update_emulated_instruction(struct kvm_vcpu *vcpu) /* * Per the SDM, MTF takes priority over debug-trap exceptions besides - * T-bit traps. As instruction emulation is completed (i.e. at the - * instruction boundary), any #DB exception pending delivery must be a - * debug-trap. Record the pending MTF state to be delivered in + * TSS T-bit traps and ICEBP (INT1). KVM doesn't emulate T-bit traps + * or ICEBP (in the emulator proper), and skipping of ICEBP after an + * intercepted #DB deliberately avoids single-step #DB and MTF updates + * as ICEBP is higher priority than both. As instruction emulation is + * completed at this point (i.e. KVM is at the instruction boundary), + * any #DB exception pending delivery must be a debug-trap of lower + * priority than MTF. Record the pending MTF state to be delivered in * vmx_check_nested_events(). */ if (nested_cpu_has_mtf(vmcs12) && (!vcpu->arch.exception.pending || - vcpu->arch.exception.nr == DB_VECTOR)) + vcpu->arch.exception.vector == DB_VECTOR) && + (!vcpu->arch.exception_vmexit.pending || + vcpu->arch.exception_vmexit.vector == DB_VECTOR)) { vmx->nested.mtf_pending = true; - else + kvm_make_request(KVM_REQ_EVENT, vcpu); + } else { vmx->nested.mtf_pending = false; + } } static int vmx_skip_emulated_instruction(struct kvm_vcpu *vcpu) @@ -1685,32 +1692,40 @@ static void vmx_clear_hlt(struct kvm_vcpu *vcpu) vmcs_write32(GUEST_ACTIVITY_STATE, GUEST_ACTIVITY_ACTIVE); } -static void vmx_queue_exception(struct kvm_vcpu *vcpu) +static void vmx_inject_exception(struct kvm_vcpu *vcpu) { + struct kvm_queued_exception *ex = &vcpu->arch.exception; + u32 intr_info = ex->vector | INTR_INFO_VALID_MASK; struct vcpu_vmx *vmx = to_vmx(vcpu); - unsigned nr = vcpu->arch.exception.nr; - bool has_error_code = vcpu->arch.exception.has_error_code; - u32 error_code = vcpu->arch.exception.error_code; - u32 intr_info = nr | INTR_INFO_VALID_MASK; - kvm_deliver_exception_payload(vcpu); + kvm_deliver_exception_payload(vcpu, ex); - if (has_error_code) { - vmcs_write32(VM_ENTRY_EXCEPTION_ERROR_CODE, error_code); + if (ex->has_error_code) { + /* + * Despite the error code being architecturally defined as 32 + * bits, and the VMCS field being 32 bits, Intel CPUs and thus + * VMX don't actually supporting setting bits 31:16. Hardware + * will (should) never provide a bogus error code, but AMD CPUs + * do generate error codes with bits 31:16 set, and so KVM's + * ABI lets userspace shove in arbitrary 32-bit values. Drop + * the upper bits to avoid VM-Fail, losing information that + * does't really exist is preferable to killing the VM. + */ + vmcs_write32(VM_ENTRY_EXCEPTION_ERROR_CODE, (u16)ex->error_code); intr_info |= INTR_INFO_DELIVER_CODE_MASK; } if (vmx->rmode.vm86_active) { int inc_eip = 0; - if (kvm_exception_is_soft(nr)) + if (kvm_exception_is_soft(ex->vector)) inc_eip = vcpu->arch.event_exit_inst_len; - kvm_inject_realmode_interrupt(vcpu, nr, inc_eip); + kvm_inject_realmode_interrupt(vcpu, ex->vector, inc_eip); return; } WARN_ON_ONCE(vmx->emulation_required); - if (kvm_exception_is_soft(nr)) { + if (kvm_exception_is_soft(ex->vector)) { vmcs_write32(VM_ENTRY_INSTRUCTION_LEN, vmx->vcpu.arch.event_exit_inst_len); intr_info |= INTR_TYPE_SOFT_EXCEPTION; @@ -1931,9 +1946,8 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) * sanity checking and refuse to boot. Filter all unsupported * features out. */ - if (!msr_info->host_initiated && - vmx->nested.enlightened_vmcs_enabled) - nested_evmcs_filter_control_msr(msr_info->index, + if (!msr_info->host_initiated && guest_cpuid_has_evmcs(vcpu)) + nested_evmcs_filter_control_msr(vcpu, msr_info->index, &msr_info->data); break; case MSR_IA32_RTIT_CTL: @@ -2007,15 +2021,17 @@ static u64 nested_vmx_truncate_sysenter_addr(struct kvm_vcpu *vcpu, return (unsigned long)data; } -static u64 vcpu_supported_debugctl(struct kvm_vcpu *vcpu) +static u64 vmx_get_supported_debugctl(struct kvm_vcpu *vcpu, bool host_initiated) { - u64 debugctl = vmx_supported_debugctl(); + u64 debugctl = 0; - if (!intel_pmu_lbr_is_enabled(vcpu)) - debugctl &= ~DEBUGCTLMSR_LBR_MASK; + if (boot_cpu_has(X86_FEATURE_BUS_LOCK_DETECT) && + (host_initiated || guest_cpuid_has(vcpu, X86_FEATURE_BUS_LOCK_DETECT))) + debugctl |= DEBUGCTLMSR_BUS_LOCK_DETECT; - if (!guest_cpuid_has(vcpu, X86_FEATURE_BUS_LOCK_DETECT)) - debugctl &= ~DEBUGCTLMSR_BUS_LOCK_DETECT; + if ((vmx_get_perf_capabilities() & PMU_CAP_LBR_FMT) && + (host_initiated || intel_pmu_lbr_is_enabled(vcpu))) + debugctl |= DEBUGCTLMSR_LBR | DEBUGCTLMSR_FREEZE_LBRS_ON_PMI; return debugctl; } @@ -2089,7 +2105,9 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) vmcs_writel(GUEST_SYSENTER_ESP, data); break; case MSR_IA32_DEBUGCTLMSR: { - u64 invalid = data & ~vcpu_supported_debugctl(vcpu); + u64 invalid; + + invalid = data & ~vmx_get_supported_debugctl(vcpu, msr_info->host_initiated); if (invalid & (DEBUGCTLMSR_BTF|DEBUGCTLMSR_LBR)) { if (report_ignored_msrs) vcpu_unimpl(vcpu, "%s: BTF|LBR in IA32_DEBUGCTLMSR 0x%llx, nop\n", @@ -2495,6 +2513,30 @@ static bool cpu_has_sgx(void) return cpuid_eax(0) >= 0x12 && (cpuid_eax(0x12) & BIT(0)); } +/* + * Some cpus support VM_{ENTRY,EXIT}_IA32_PERF_GLOBAL_CTRL but they + * can't be used due to errata where VM Exit may incorrectly clear + * IA32_PERF_GLOBAL_CTRL[34:32]. Work around the errata by using the + * MSR load mechanism to switch IA32_PERF_GLOBAL_CTRL. + */ +static bool cpu_has_perf_global_ctrl_bug(void) +{ + if (boot_cpu_data.x86 == 0x6) { + switch (boot_cpu_data.x86_model) { + case INTEL_FAM6_NEHALEM_EP: /* AAK155 */ + case INTEL_FAM6_NEHALEM: /* AAP115 */ + case INTEL_FAM6_WESTMERE: /* AAT100 */ + case INTEL_FAM6_WESTMERE_EP: /* BC86,AAY89,BD102 */ + case INTEL_FAM6_NEHALEM_EX: /* BA97 */ + return true; + default: + break; + } + } + + return false; +} + static __init int adjust_vmx_controls(u32 ctl_min, u32 ctl_opt, u32 msr, u32 *result) { @@ -2527,13 +2569,13 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf, struct vmx_capability *vmx_cap) { u32 vmx_msr_low, vmx_msr_high; - u32 min, opt, min2, opt2; u32 _pin_based_exec_control = 0; u32 _cpu_based_exec_control = 0; u32 _cpu_based_2nd_exec_control = 0; u64 _cpu_based_3rd_exec_control = 0; u32 _vmexit_control = 0; u32 _vmentry_control = 0; + u64 misc_msr; int i; /* @@ -2553,64 +2595,17 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf, }; memset(vmcs_conf, 0, sizeof(*vmcs_conf)); - min = CPU_BASED_HLT_EXITING | -#ifdef CONFIG_X86_64 - CPU_BASED_CR8_LOAD_EXITING | - CPU_BASED_CR8_STORE_EXITING | -#endif - CPU_BASED_CR3_LOAD_EXITING | - CPU_BASED_CR3_STORE_EXITING | - CPU_BASED_UNCOND_IO_EXITING | - CPU_BASED_MOV_DR_EXITING | - CPU_BASED_USE_TSC_OFFSETTING | - CPU_BASED_MWAIT_EXITING | - CPU_BASED_MONITOR_EXITING | - CPU_BASED_INVLPG_EXITING | - CPU_BASED_RDPMC_EXITING; - - opt = CPU_BASED_TPR_SHADOW | - CPU_BASED_USE_MSR_BITMAPS | - CPU_BASED_ACTIVATE_SECONDARY_CONTROLS | - CPU_BASED_ACTIVATE_TERTIARY_CONTROLS; - if (adjust_vmx_controls(min, opt, MSR_IA32_VMX_PROCBASED_CTLS, - &_cpu_based_exec_control) < 0) + + if (adjust_vmx_controls(KVM_REQUIRED_VMX_CPU_BASED_VM_EXEC_CONTROL, + KVM_OPTIONAL_VMX_CPU_BASED_VM_EXEC_CONTROL, + MSR_IA32_VMX_PROCBASED_CTLS, + &_cpu_based_exec_control)) return -EIO; -#ifdef CONFIG_X86_64 - if (_cpu_based_exec_control & CPU_BASED_TPR_SHADOW) - _cpu_based_exec_control &= ~CPU_BASED_CR8_LOAD_EXITING & - ~CPU_BASED_CR8_STORE_EXITING; -#endif if (_cpu_based_exec_control & CPU_BASED_ACTIVATE_SECONDARY_CONTROLS) { - min2 = 0; - opt2 = SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES | - SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE | - SECONDARY_EXEC_WBINVD_EXITING | - SECONDARY_EXEC_ENABLE_VPID | - SECONDARY_EXEC_ENABLE_EPT | - SECONDARY_EXEC_UNRESTRICTED_GUEST | - SECONDARY_EXEC_PAUSE_LOOP_EXITING | - SECONDARY_EXEC_DESC | - SECONDARY_EXEC_ENABLE_RDTSCP | - SECONDARY_EXEC_ENABLE_INVPCID | - SECONDARY_EXEC_APIC_REGISTER_VIRT | - SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY | - SECONDARY_EXEC_SHADOW_VMCS | - SECONDARY_EXEC_XSAVES | - SECONDARY_EXEC_RDSEED_EXITING | - SECONDARY_EXEC_RDRAND_EXITING | - SECONDARY_EXEC_ENABLE_PML | - SECONDARY_EXEC_TSC_SCALING | - SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE | - SECONDARY_EXEC_PT_USE_GPA | - SECONDARY_EXEC_PT_CONCEAL_VMX | - SECONDARY_EXEC_ENABLE_VMFUNC | - SECONDARY_EXEC_BUS_LOCK_DETECTION | - SECONDARY_EXEC_NOTIFY_VM_EXITING; - if (cpu_has_sgx()) - opt2 |= SECONDARY_EXEC_ENCLS_EXITING; - if (adjust_vmx_controls(min2, opt2, + if (adjust_vmx_controls(KVM_REQUIRED_VMX_SECONDARY_VM_EXEC_CONTROL, + KVM_OPTIONAL_VMX_SECONDARY_VM_EXEC_CONTROL, MSR_IA32_VMX_PROCBASED_CTLS2, - &_cpu_based_2nd_exec_control) < 0) + &_cpu_based_2nd_exec_control)) return -EIO; } #ifndef CONFIG_X86_64 @@ -2628,13 +2623,8 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf, rdmsr_safe(MSR_IA32_VMX_EPT_VPID_CAP, &vmx_cap->ept, &vmx_cap->vpid); - if (_cpu_based_2nd_exec_control & SECONDARY_EXEC_ENABLE_EPT) { - /* CR3 accesses and invlpg don't need to cause VM Exits when EPT - enabled */ - _cpu_based_exec_control &= ~(CPU_BASED_CR3_LOAD_EXITING | - CPU_BASED_CR3_STORE_EXITING | - CPU_BASED_INVLPG_EXITING); - } else if (vmx_cap->ept) { + if (!(_cpu_based_2nd_exec_control & SECONDARY_EXEC_ENABLE_EPT) && + vmx_cap->ept) { pr_warn_once("EPT CAP should not exist if not support " "1-setting enable EPT VM-execution control\n"); @@ -2654,32 +2644,24 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf, vmx_cap->vpid = 0; } - if (_cpu_based_exec_control & CPU_BASED_ACTIVATE_TERTIARY_CONTROLS) { - u64 opt3 = TERTIARY_EXEC_IPI_VIRT; + if (!cpu_has_sgx()) + _cpu_based_2nd_exec_control &= ~SECONDARY_EXEC_ENCLS_EXITING; - _cpu_based_3rd_exec_control = adjust_vmx_controls64(opt3, + if (_cpu_based_exec_control & CPU_BASED_ACTIVATE_TERTIARY_CONTROLS) + _cpu_based_3rd_exec_control = + adjust_vmx_controls64(KVM_OPTIONAL_VMX_TERTIARY_VM_EXEC_CONTROL, MSR_IA32_VMX_PROCBASED_CTLS3); - } - min = VM_EXIT_SAVE_DEBUG_CONTROLS | VM_EXIT_ACK_INTR_ON_EXIT; -#ifdef CONFIG_X86_64 - min |= VM_EXIT_HOST_ADDR_SPACE_SIZE; -#endif - opt = VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL | - VM_EXIT_LOAD_IA32_PAT | - VM_EXIT_LOAD_IA32_EFER | - VM_EXIT_CLEAR_BNDCFGS | - VM_EXIT_PT_CONCEAL_PIP | - VM_EXIT_CLEAR_IA32_RTIT_CTL; - if (adjust_vmx_controls(min, opt, MSR_IA32_VMX_EXIT_CTLS, - &_vmexit_control) < 0) + if (adjust_vmx_controls(KVM_REQUIRED_VMX_VM_EXIT_CONTROLS, + KVM_OPTIONAL_VMX_VM_EXIT_CONTROLS, + MSR_IA32_VMX_EXIT_CTLS, + &_vmexit_control)) return -EIO; - min = PIN_BASED_EXT_INTR_MASK | PIN_BASED_NMI_EXITING; - opt = PIN_BASED_VIRTUAL_NMIS | PIN_BASED_POSTED_INTR | - PIN_BASED_VMX_PREEMPTION_TIMER; - if (adjust_vmx_controls(min, opt, MSR_IA32_VMX_PINBASED_CTLS, - &_pin_based_exec_control) < 0) + if (adjust_vmx_controls(KVM_REQUIRED_VMX_PIN_BASED_VM_EXEC_CONTROL, + KVM_OPTIONAL_VMX_PIN_BASED_VM_EXEC_CONTROL, + MSR_IA32_VMX_PINBASED_CTLS, + &_pin_based_exec_control)) return -EIO; if (cpu_has_broken_vmx_preemption_timer()) @@ -2688,15 +2670,10 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf, SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY)) _pin_based_exec_control &= ~PIN_BASED_POSTED_INTR; - min = VM_ENTRY_LOAD_DEBUG_CONTROLS; - opt = VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL | - VM_ENTRY_LOAD_IA32_PAT | - VM_ENTRY_LOAD_IA32_EFER | - VM_ENTRY_LOAD_BNDCFGS | - VM_ENTRY_PT_CONCEAL_PIP | - VM_ENTRY_LOAD_IA32_RTIT_CTL; - if (adjust_vmx_controls(min, opt, MSR_IA32_VMX_ENTRY_CTLS, - &_vmentry_control) < 0) + if (adjust_vmx_controls(KVM_REQUIRED_VMX_VM_ENTRY_CONTROLS, + KVM_OPTIONAL_VMX_VM_ENTRY_CONTROLS, + MSR_IA32_VMX_ENTRY_CTLS, + &_vmentry_control)) return -EIO; for (i = 0; i < ARRAY_SIZE(vmcs_entry_exit_pairs); i++) { @@ -2716,30 +2693,6 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf, _vmexit_control &= ~x_ctrl; } - /* - * Some cpus support VM_{ENTRY,EXIT}_IA32_PERF_GLOBAL_CTRL but they - * can't be used due to an errata where VM Exit may incorrectly clear - * IA32_PERF_GLOBAL_CTRL[34:32]. Workaround the errata by using the - * MSR load mechanism to switch IA32_PERF_GLOBAL_CTRL. - */ - if (boot_cpu_data.x86 == 0x6) { - switch (boot_cpu_data.x86_model) { - case 26: /* AAK155 */ - case 30: /* AAP115 */ - case 37: /* AAT100 */ - case 44: /* BC86,AAY89,BD102 */ - case 46: /* BA97 */ - _vmentry_control &= ~VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL; - _vmexit_control &= ~VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL; - pr_warn_once("kvm: VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL " - "does not work properly. Using workaround\n"); - break; - default: - break; - } - } - - rdmsr(MSR_IA32_VMX_BASIC, vmx_msr_low, vmx_msr_high); /* IA-32 SDM Vol 3B: VMCS size is never greater than 4kB. */ @@ -2756,6 +2709,8 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf, if (((vmx_msr_high >> 18) & 15) != 6) return -EIO; + rdmsrl(MSR_IA32_VMX_MISC, misc_msr); + vmcs_conf->size = vmx_msr_high & 0x1fff; vmcs_conf->basic_cap = vmx_msr_high & ~0x1fff; @@ -2767,11 +2722,7 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf, vmcs_conf->cpu_based_3rd_exec_ctrl = _cpu_based_3rd_exec_control; vmcs_conf->vmexit_ctrl = _vmexit_control; vmcs_conf->vmentry_ctrl = _vmentry_control; - -#if IS_ENABLED(CONFIG_HYPERV) - if (enlightened_vmcs) - evmcs_sanitize_exec_ctrls(vmcs_conf); -#endif + vmcs_conf->misc = misc_msr; return 0; } @@ -3038,10 +2989,15 @@ int vmx_set_efer(struct kvm_vcpu *vcpu, u64 efer) return 0; vcpu->arch.efer = efer; +#ifdef CONFIG_X86_64 if (efer & EFER_LMA) vm_entry_controls_setbit(vmx, VM_ENTRY_IA32E_MODE); else vm_entry_controls_clearbit(vmx, VM_ENTRY_IA32E_MODE); +#else + if (KVM_BUG_ON(efer & EFER_LMA, vcpu->kvm)) + return 1; +#endif vmx_setup_uret_msrs(vmx); return 0; @@ -4328,18 +4284,37 @@ static u32 vmx_vmentry_ctrl(void) if (vmx_pt_mode_is_system()) vmentry_ctrl &= ~(VM_ENTRY_PT_CONCEAL_PIP | VM_ENTRY_LOAD_IA32_RTIT_CTL); - /* Loading of EFER and PERF_GLOBAL_CTRL are toggled dynamically */ - return vmentry_ctrl & - ~(VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL | VM_ENTRY_LOAD_IA32_EFER); + /* + * IA32e mode, and loading of EFER and PERF_GLOBAL_CTRL are toggled dynamically. + */ + vmentry_ctrl &= ~(VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL | + VM_ENTRY_LOAD_IA32_EFER | + VM_ENTRY_IA32E_MODE); + + if (cpu_has_perf_global_ctrl_bug()) + vmentry_ctrl &= ~VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL; + + return vmentry_ctrl; } static u32 vmx_vmexit_ctrl(void) { u32 vmexit_ctrl = vmcs_config.vmexit_ctrl; + /* + * Not used by KVM and never set in vmcs01 or vmcs02, but emulated for + * nested virtualization and thus allowed to be set in vmcs12. + */ + vmexit_ctrl &= ~(VM_EXIT_SAVE_IA32_PAT | VM_EXIT_SAVE_IA32_EFER | + VM_EXIT_SAVE_VMX_PREEMPTION_TIMER); + if (vmx_pt_mode_is_system()) vmexit_ctrl &= ~(VM_EXIT_PT_CONCEAL_PIP | VM_EXIT_CLEAR_IA32_RTIT_CTL); + + if (cpu_has_perf_global_ctrl_bug()) + vmexit_ctrl &= ~VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL; + /* Loading of EFER and PERF_GLOBAL_CTRL are toggled dynamically */ return vmexit_ctrl & ~(VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL | VM_EXIT_LOAD_IA32_EFER); @@ -4377,20 +4352,38 @@ static u32 vmx_exec_control(struct vcpu_vmx *vmx) { u32 exec_control = vmcs_config.cpu_based_exec_ctrl; + /* + * Not used by KVM, but fully supported for nesting, i.e. are allowed in + * vmcs12 and propagated to vmcs02 when set in vmcs12. + */ + exec_control &= ~(CPU_BASED_RDTSC_EXITING | + CPU_BASED_USE_IO_BITMAPS | + CPU_BASED_MONITOR_TRAP_FLAG | + CPU_BASED_PAUSE_EXITING); + + /* INTR_WINDOW_EXITING and NMI_WINDOW_EXITING are toggled dynamically */ + exec_control &= ~(CPU_BASED_INTR_WINDOW_EXITING | + CPU_BASED_NMI_WINDOW_EXITING); + if (vmx->vcpu.arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT) exec_control &= ~CPU_BASED_MOV_DR_EXITING; - if (!cpu_need_tpr_shadow(&vmx->vcpu)) { + if (!cpu_need_tpr_shadow(&vmx->vcpu)) exec_control &= ~CPU_BASED_TPR_SHADOW; + #ifdef CONFIG_X86_64 + if (exec_control & CPU_BASED_TPR_SHADOW) + exec_control &= ~(CPU_BASED_CR8_LOAD_EXITING | + CPU_BASED_CR8_STORE_EXITING); + else exec_control |= CPU_BASED_CR8_STORE_EXITING | CPU_BASED_CR8_LOAD_EXITING; #endif - } - if (!enable_ept) - exec_control |= CPU_BASED_CR3_STORE_EXITING | - CPU_BASED_CR3_LOAD_EXITING | - CPU_BASED_INVLPG_EXITING; + /* No need to intercept CR3 access or INVPLG when using EPT. */ + if (enable_ept) + exec_control &= ~(CPU_BASED_CR3_LOAD_EXITING | + CPU_BASED_CR3_STORE_EXITING | + CPU_BASED_INVLPG_EXITING); if (kvm_mwait_in_guest(vmx->vcpu.kvm)) exec_control &= ~(CPU_BASED_MWAIT_EXITING | CPU_BASED_MONITOR_EXITING); @@ -5156,8 +5149,10 @@ static int handle_exception_nmi(struct kvm_vcpu *vcpu) * instruction. ICEBP generates a trap-like #DB, but * despite its interception control being tied to #DB, * is an instruction intercept, i.e. the VM-Exit occurs - * on the ICEBP itself. Note, skipping ICEBP also - * clears STI and MOVSS blocking. + * on the ICEBP itself. Use the inner "skip" helper to + * avoid single-step #DB and MTF updates, as ICEBP is + * higher priority. Note, skipping ICEBP still clears + * STI and MOVSS blocking. * * For all other #DBs, set vmcs.PENDING_DBG_EXCEPTIONS.BS * if single-step is enabled in RFLAGS and STI or MOVSS @@ -5639,7 +5634,7 @@ static int handle_ept_violation(struct kvm_vcpu *vcpu) vmcs_set_bits(GUEST_INTERRUPTIBILITY_INFO, GUEST_INTR_STATE_NMI); gpa = vmcs_read64(GUEST_PHYSICAL_ADDRESS); - trace_kvm_page_fault(gpa, exit_qualification); + trace_kvm_page_fault(vcpu, gpa, exit_qualification); /* Is it a read fault? */ error_code = (exit_qualification & EPT_VIOLATION_ACC_READ) @@ -5711,7 +5706,7 @@ static bool vmx_emulation_required_with_pending_exception(struct kvm_vcpu *vcpu) struct vcpu_vmx *vmx = to_vmx(vcpu); return vmx->emulation_required && !vmx->rmode.vm86_active && - (vcpu->arch.exception.pending || vcpu->arch.exception.injected); + (kvm_is_exception_pending(vcpu) || vcpu->arch.exception.injected); } static int handle_invalid_guest_state(struct kvm_vcpu *vcpu) @@ -7431,7 +7426,7 @@ static int __init vmx_check_processor_compat(void) if (setup_vmcs_config(&vmcs_conf, &vmx_cap) < 0) return -EIO; if (nested) - nested_vmx_setup_ctls_msrs(&vmcs_conf.nested, vmx_cap.ept); + nested_vmx_setup_ctls_msrs(&vmcs_conf, vmx_cap.ept); if (memcmp(&vmcs_config, &vmcs_conf, sizeof(struct vmcs_config)) != 0) { printk(KERN_ERR "kvm: CPU %d feature inconsistency!\n", smp_processor_id()); @@ -8071,7 +8066,7 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = { .patch_hypercall = vmx_patch_hypercall, .inject_irq = vmx_inject_irq, .inject_nmi = vmx_inject_nmi, - .queue_exception = vmx_queue_exception, + .inject_exception = vmx_inject_exception, .cancel_injection = vmx_cancel_injection, .interrupt_allowed = vmx_interrupt_allowed, .nmi_allowed = vmx_nmi_allowed, @@ -8228,6 +8223,10 @@ static __init int hardware_setup(void) if (setup_vmcs_config(&vmcs_config, &vmx_capability) < 0) return -EIO; + if (cpu_has_perf_global_ctrl_bug()) + pr_warn_once("kvm: VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL " + "does not work properly. Using workaround\n"); + if (boot_cpu_has(X86_FEATURE_NX)) kvm_enable_efer_bits(EFER_NX); @@ -8268,6 +8267,11 @@ static __init int hardware_setup(void) if (!cpu_has_virtual_nmis()) enable_vnmi = 0; +#ifdef CONFIG_X86_SGX_KVM + if (!cpu_has_vmx_encls_vmexit()) + enable_sgx = false; +#endif + /* * set_apic_access_page_addr() is used to reload apic access * page upon invalidation. No need to do anything if not @@ -8342,11 +8346,9 @@ static __init int hardware_setup(void) if (enable_preemption_timer) { u64 use_timer_freq = 5000ULL * 1000 * 1000; - u64 vmx_msr; - rdmsrl(MSR_IA32_VMX_MISC, vmx_msr); cpu_preemption_timer_multi = - vmx_msr & VMX_MISC_PREEMPTION_TIMER_RATE_MASK; + vmcs_config.misc & VMX_MISC_PREEMPTION_TIMER_RATE_MASK; if (tsc_khz) use_timer_freq = (u64)tsc_khz * 1000; @@ -8382,8 +8384,7 @@ static __init int hardware_setup(void) setup_default_sgx_lepubkeyhash(); if (nested) { - nested_vmx_setup_ctls_msrs(&vmcs_config.nested, - vmx_capability.ept); + nested_vmx_setup_ctls_msrs(&vmcs_config, vmx_capability.ept); r = nested_vmx_hardware_setup(kvm_vmx_exit_handlers); if (r) diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index 24d58c2ffaa3..a3da84f4ea45 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -477,29 +477,145 @@ static inline u8 vmx_get_rvi(void) return vmcs_read16(GUEST_INTR_STATUS) & 0xff; } -#define BUILD_CONTROLS_SHADOW(lname, uname, bits) \ -static inline void lname##_controls_set(struct vcpu_vmx *vmx, u##bits val) \ -{ \ - if (vmx->loaded_vmcs->controls_shadow.lname != val) { \ - vmcs_write##bits(uname, val); \ - vmx->loaded_vmcs->controls_shadow.lname = val; \ - } \ -} \ -static inline u##bits __##lname##_controls_get(struct loaded_vmcs *vmcs) \ -{ \ - return vmcs->controls_shadow.lname; \ -} \ -static inline u##bits lname##_controls_get(struct vcpu_vmx *vmx) \ -{ \ - return __##lname##_controls_get(vmx->loaded_vmcs); \ -} \ -static inline void lname##_controls_setbit(struct vcpu_vmx *vmx, u##bits val) \ -{ \ - lname##_controls_set(vmx, lname##_controls_get(vmx) | val); \ -} \ -static inline void lname##_controls_clearbit(struct vcpu_vmx *vmx, u##bits val) \ -{ \ - lname##_controls_set(vmx, lname##_controls_get(vmx) & ~val); \ +#define __KVM_REQUIRED_VMX_VM_ENTRY_CONTROLS \ + (VM_ENTRY_LOAD_DEBUG_CONTROLS) +#ifdef CONFIG_X86_64 + #define KVM_REQUIRED_VMX_VM_ENTRY_CONTROLS \ + (__KVM_REQUIRED_VMX_VM_ENTRY_CONTROLS | \ + VM_ENTRY_IA32E_MODE) +#else + #define KVM_REQUIRED_VMX_VM_ENTRY_CONTROLS \ + __KVM_REQUIRED_VMX_VM_ENTRY_CONTROLS +#endif +#define KVM_OPTIONAL_VMX_VM_ENTRY_CONTROLS \ + (VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL | \ + VM_ENTRY_LOAD_IA32_PAT | \ + VM_ENTRY_LOAD_IA32_EFER | \ + VM_ENTRY_LOAD_BNDCFGS | \ + VM_ENTRY_PT_CONCEAL_PIP | \ + VM_ENTRY_LOAD_IA32_RTIT_CTL) + +#define __KVM_REQUIRED_VMX_VM_EXIT_CONTROLS \ + (VM_EXIT_SAVE_DEBUG_CONTROLS | \ + VM_EXIT_ACK_INTR_ON_EXIT) +#ifdef CONFIG_X86_64 + #define KVM_REQUIRED_VMX_VM_EXIT_CONTROLS \ + (__KVM_REQUIRED_VMX_VM_EXIT_CONTROLS | \ + VM_EXIT_HOST_ADDR_SPACE_SIZE) +#else + #define KVM_REQUIRED_VMX_VM_EXIT_CONTROLS \ + __KVM_REQUIRED_VMX_VM_EXIT_CONTROLS +#endif +#define KVM_OPTIONAL_VMX_VM_EXIT_CONTROLS \ + (VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL | \ + VM_EXIT_SAVE_IA32_PAT | \ + VM_EXIT_LOAD_IA32_PAT | \ + VM_EXIT_SAVE_IA32_EFER | \ + VM_EXIT_SAVE_VMX_PREEMPTION_TIMER | \ + VM_EXIT_LOAD_IA32_EFER | \ + VM_EXIT_CLEAR_BNDCFGS | \ + VM_EXIT_PT_CONCEAL_PIP | \ + VM_EXIT_CLEAR_IA32_RTIT_CTL) + +#define KVM_REQUIRED_VMX_PIN_BASED_VM_EXEC_CONTROL \ + (PIN_BASED_EXT_INTR_MASK | \ + PIN_BASED_NMI_EXITING) +#define KVM_OPTIONAL_VMX_PIN_BASED_VM_EXEC_CONTROL \ + (PIN_BASED_VIRTUAL_NMIS | \ + PIN_BASED_POSTED_INTR | \ + PIN_BASED_VMX_PREEMPTION_TIMER) + +#define __KVM_REQUIRED_VMX_CPU_BASED_VM_EXEC_CONTROL \ + (CPU_BASED_HLT_EXITING | \ + CPU_BASED_CR3_LOAD_EXITING | \ + CPU_BASED_CR3_STORE_EXITING | \ + CPU_BASED_UNCOND_IO_EXITING | \ + CPU_BASED_MOV_DR_EXITING | \ + CPU_BASED_USE_TSC_OFFSETTING | \ + CPU_BASED_MWAIT_EXITING | \ + CPU_BASED_MONITOR_EXITING | \ + CPU_BASED_INVLPG_EXITING | \ + CPU_BASED_RDPMC_EXITING | \ + CPU_BASED_INTR_WINDOW_EXITING) + +#ifdef CONFIG_X86_64 + #define KVM_REQUIRED_VMX_CPU_BASED_VM_EXEC_CONTROL \ + (__KVM_REQUIRED_VMX_CPU_BASED_VM_EXEC_CONTROL | \ + CPU_BASED_CR8_LOAD_EXITING | \ + CPU_BASED_CR8_STORE_EXITING) +#else + #define KVM_REQUIRED_VMX_CPU_BASED_VM_EXEC_CONTROL \ + __KVM_REQUIRED_VMX_CPU_BASED_VM_EXEC_CONTROL +#endif + +#define KVM_OPTIONAL_VMX_CPU_BASED_VM_EXEC_CONTROL \ + (CPU_BASED_RDTSC_EXITING | \ + CPU_BASED_TPR_SHADOW | \ + CPU_BASED_USE_IO_BITMAPS | \ + CPU_BASED_MONITOR_TRAP_FLAG | \ + CPU_BASED_USE_MSR_BITMAPS | \ + CPU_BASED_NMI_WINDOW_EXITING | \ + CPU_BASED_PAUSE_EXITING | \ + CPU_BASED_ACTIVATE_SECONDARY_CONTROLS | \ + CPU_BASED_ACTIVATE_TERTIARY_CONTROLS) + +#define KVM_REQUIRED_VMX_SECONDARY_VM_EXEC_CONTROL 0 +#define KVM_OPTIONAL_VMX_SECONDARY_VM_EXEC_CONTROL \ + (SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES | \ + SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE | \ + SECONDARY_EXEC_WBINVD_EXITING | \ + SECONDARY_EXEC_ENABLE_VPID | \ + SECONDARY_EXEC_ENABLE_EPT | \ + SECONDARY_EXEC_UNRESTRICTED_GUEST | \ + SECONDARY_EXEC_PAUSE_LOOP_EXITING | \ + SECONDARY_EXEC_DESC | \ + SECONDARY_EXEC_ENABLE_RDTSCP | \ + SECONDARY_EXEC_ENABLE_INVPCID | \ + SECONDARY_EXEC_APIC_REGISTER_VIRT | \ + SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY | \ + SECONDARY_EXEC_SHADOW_VMCS | \ + SECONDARY_EXEC_XSAVES | \ + SECONDARY_EXEC_RDSEED_EXITING | \ + SECONDARY_EXEC_RDRAND_EXITING | \ + SECONDARY_EXEC_ENABLE_PML | \ + SECONDARY_EXEC_TSC_SCALING | \ + SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE | \ + SECONDARY_EXEC_PT_USE_GPA | \ + SECONDARY_EXEC_PT_CONCEAL_VMX | \ + SECONDARY_EXEC_ENABLE_VMFUNC | \ + SECONDARY_EXEC_BUS_LOCK_DETECTION | \ + SECONDARY_EXEC_NOTIFY_VM_EXITING | \ + SECONDARY_EXEC_ENCLS_EXITING) + +#define KVM_REQUIRED_VMX_TERTIARY_VM_EXEC_CONTROL 0 +#define KVM_OPTIONAL_VMX_TERTIARY_VM_EXEC_CONTROL \ + (TERTIARY_EXEC_IPI_VIRT) + +#define BUILD_CONTROLS_SHADOW(lname, uname, bits) \ +static inline void lname##_controls_set(struct vcpu_vmx *vmx, u##bits val) \ +{ \ + if (vmx->loaded_vmcs->controls_shadow.lname != val) { \ + vmcs_write##bits(uname, val); \ + vmx->loaded_vmcs->controls_shadow.lname = val; \ + } \ +} \ +static inline u##bits __##lname##_controls_get(struct loaded_vmcs *vmcs) \ +{ \ + return vmcs->controls_shadow.lname; \ +} \ +static inline u##bits lname##_controls_get(struct vcpu_vmx *vmx) \ +{ \ + return __##lname##_controls_get(vmx->loaded_vmcs); \ +} \ +static __always_inline void lname##_controls_setbit(struct vcpu_vmx *vmx, u##bits val) \ +{ \ + BUILD_BUG_ON(!(val & (KVM_REQUIRED_VMX_##uname | KVM_OPTIONAL_VMX_##uname))); \ + lname##_controls_set(vmx, lname##_controls_get(vmx) | val); \ +} \ +static __always_inline void lname##_controls_clearbit(struct vcpu_vmx *vmx, u##bits val) \ +{ \ + BUILD_BUG_ON(!(val & (KVM_REQUIRED_VMX_##uname | KVM_OPTIONAL_VMX_##uname))); \ + lname##_controls_set(vmx, lname##_controls_get(vmx) & ~val); \ } BUILD_CONTROLS_SHADOW(vm_entry, VM_ENTRY_CONTROLS, 32) BUILD_CONTROLS_SHADOW(vm_exit, VM_EXIT_CONTROLS, 32) @@ -626,4 +742,14 @@ static inline bool vmx_can_use_ipiv(struct kvm_vcpu *vcpu) return lapic_in_kernel(vcpu) && enable_ipiv; } +static inline bool guest_cpuid_has_evmcs(struct kvm_vcpu *vcpu) +{ + /* + * eVMCS is exposed to the guest if Hyper-V is enabled in CPUID and + * eVMCS has been explicitly enabled by userspace. + */ + return vcpu->arch.hyperv_enabled && + to_vmx(vcpu)->nested.enlightened_vmcs_enabled; +} + #endif /* __KVM_X86_VMX_H */ diff --git a/arch/x86/kvm/vmx/vmx_ops.h b/arch/x86/kvm/vmx/vmx_ops.h index 5cfc49ddb1b4..ec268df83ed6 100644 --- a/arch/x86/kvm/vmx/vmx_ops.h +++ b/arch/x86/kvm/vmx/vmx_ops.h @@ -10,7 +10,7 @@ #include "vmcs.h" #include "../x86.h" -asmlinkage void vmread_error(unsigned long field, bool fault); +void vmread_error(unsigned long field, bool fault); __attribute__((regparm(0))) void vmread_error_trampoline(unsigned long field, bool fault); void vmwrite_error(unsigned long field, unsigned long value); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 205ebdc2b11b..2835bd796639 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -173,8 +173,13 @@ bool __read_mostly enable_vmware_backdoor = false; module_param(enable_vmware_backdoor, bool, S_IRUGO); EXPORT_SYMBOL_GPL(enable_vmware_backdoor); -static bool __read_mostly force_emulation_prefix = false; -module_param(force_emulation_prefix, bool, S_IRUGO); +/* + * Flags to manipulate forced emulation behavior (any non-zero value will + * enable forced emulation). + */ +#define KVM_FEP_CLEAR_RFLAGS_RF BIT(1) +static int __read_mostly force_emulation_prefix; +module_param(force_emulation_prefix, int, 0644); int __read_mostly pi_inject_timer = -1; module_param(pi_inject_timer, bint, S_IRUGO | S_IWUSR); @@ -528,6 +533,7 @@ static int exception_class(int vector) #define EXCPT_TRAP 1 #define EXCPT_ABORT 2 #define EXCPT_INTERRUPT 3 +#define EXCPT_DB 4 static int exception_type(int vector) { @@ -538,8 +544,14 @@ static int exception_type(int vector) mask = 1 << vector; - /* #DB is trap, as instruction watchpoints are handled elsewhere */ - if (mask & ((1 << DB_VECTOR) | (1 << BP_VECTOR) | (1 << OF_VECTOR))) + /* + * #DBs can be trap-like or fault-like, the caller must check other CPU + * state, e.g. DR6, to determine whether a #DB is a trap or fault. + */ + if (mask & (1 << DB_VECTOR)) + return EXCPT_DB; + + if (mask & ((1 << BP_VECTOR) | (1 << OF_VECTOR))) return EXCPT_TRAP; if (mask & ((1 << DF_VECTOR) | (1 << MC_VECTOR))) @@ -549,16 +561,13 @@ static int exception_type(int vector) return EXCPT_FAULT; } -void kvm_deliver_exception_payload(struct kvm_vcpu *vcpu) +void kvm_deliver_exception_payload(struct kvm_vcpu *vcpu, + struct kvm_queued_exception *ex) { - unsigned nr = vcpu->arch.exception.nr; - bool has_payload = vcpu->arch.exception.has_payload; - unsigned long payload = vcpu->arch.exception.payload; - - if (!has_payload) + if (!ex->has_payload) return; - switch (nr) { + switch (ex->vector) { case DB_VECTOR: /* * "Certain debug exceptions may clear bit 0-3. The @@ -583,8 +592,8 @@ void kvm_deliver_exception_payload(struct kvm_vcpu *vcpu) * So they need to be flipped for DR6. */ vcpu->arch.dr6 |= DR6_ACTIVE_LOW; - vcpu->arch.dr6 |= payload; - vcpu->arch.dr6 ^= payload & DR6_ACTIVE_LOW; + vcpu->arch.dr6 |= ex->payload; + vcpu->arch.dr6 ^= ex->payload & DR6_ACTIVE_LOW; /* * The #DB payload is defined as compatible with the 'pending @@ -595,15 +604,36 @@ void kvm_deliver_exception_payload(struct kvm_vcpu *vcpu) vcpu->arch.dr6 &= ~BIT(12); break; case PF_VECTOR: - vcpu->arch.cr2 = payload; + vcpu->arch.cr2 = ex->payload; break; } - vcpu->arch.exception.has_payload = false; - vcpu->arch.exception.payload = 0; + ex->has_payload = false; + ex->payload = 0; } EXPORT_SYMBOL_GPL(kvm_deliver_exception_payload); +static void kvm_queue_exception_vmexit(struct kvm_vcpu *vcpu, unsigned int vector, + bool has_error_code, u32 error_code, + bool has_payload, unsigned long payload) +{ + struct kvm_queued_exception *ex = &vcpu->arch.exception_vmexit; + + ex->vector = vector; + ex->injected = false; + ex->pending = true; + ex->has_error_code = has_error_code; + ex->error_code = error_code; + ex->has_payload = has_payload; + ex->payload = payload; +} + +/* Forcibly leave the nested mode in cases like a vCPU reset */ +static void kvm_leave_nested(struct kvm_vcpu *vcpu) +{ + kvm_x86_ops.nested_ops->leave_nested(vcpu); +} + static void kvm_multiple_exception(struct kvm_vcpu *vcpu, unsigned nr, bool has_error, u32 error_code, bool has_payload, unsigned long payload, bool reinject) @@ -613,18 +643,31 @@ static void kvm_multiple_exception(struct kvm_vcpu *vcpu, kvm_make_request(KVM_REQ_EVENT, vcpu); + /* + * If the exception is destined for L2 and isn't being reinjected, + * morph it to a VM-Exit if L1 wants to intercept the exception. A + * previously injected exception is not checked because it was checked + * when it was original queued, and re-checking is incorrect if _L1_ + * injected the exception, in which case it's exempt from interception. + */ + if (!reinject && is_guest_mode(vcpu) && + kvm_x86_ops.nested_ops->is_exception_vmexit(vcpu, nr, error_code)) { + kvm_queue_exception_vmexit(vcpu, nr, has_error, error_code, + has_payload, payload); + return; + } + if (!vcpu->arch.exception.pending && !vcpu->arch.exception.injected) { queue: if (reinject) { /* - * On vmentry, vcpu->arch.exception.pending is only - * true if an event injection was blocked by - * nested_run_pending. In that case, however, - * vcpu_enter_guest requests an immediate exit, - * and the guest shouldn't proceed far enough to - * need reinjection. + * On VM-Entry, an exception can be pending if and only + * if event injection was blocked by nested_run_pending. + * In that case, however, vcpu_enter_guest() requests an + * immediate exit, and the guest shouldn't proceed far + * enough to need reinjection. */ - WARN_ON_ONCE(vcpu->arch.exception.pending); + WARN_ON_ONCE(kvm_is_exception_pending(vcpu)); vcpu->arch.exception.injected = true; if (WARN_ON_ONCE(has_payload)) { /* @@ -639,17 +682,18 @@ static void kvm_multiple_exception(struct kvm_vcpu *vcpu, vcpu->arch.exception.injected = false; } vcpu->arch.exception.has_error_code = has_error; - vcpu->arch.exception.nr = nr; + vcpu->arch.exception.vector = nr; vcpu->arch.exception.error_code = error_code; vcpu->arch.exception.has_payload = has_payload; vcpu->arch.exception.payload = payload; if (!is_guest_mode(vcpu)) - kvm_deliver_exception_payload(vcpu); + kvm_deliver_exception_payload(vcpu, + &vcpu->arch.exception); return; } /* to check exception */ - prev_nr = vcpu->arch.exception.nr; + prev_nr = vcpu->arch.exception.vector; if (prev_nr == DF_VECTOR) { /* triple fault -> shutdown */ kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu); @@ -657,25 +701,22 @@ static void kvm_multiple_exception(struct kvm_vcpu *vcpu, } class1 = exception_class(prev_nr); class2 = exception_class(nr); - if ((class1 == EXCPT_CONTRIBUTORY && class2 == EXCPT_CONTRIBUTORY) - || (class1 == EXCPT_PF && class2 != EXCPT_BENIGN)) { + if ((class1 == EXCPT_CONTRIBUTORY && class2 == EXCPT_CONTRIBUTORY) || + (class1 == EXCPT_PF && class2 != EXCPT_BENIGN)) { /* - * Generate double fault per SDM Table 5-5. Set - * exception.pending = true so that the double fault - * can trigger a nested vmexit. + * Synthesize #DF. Clear the previously injected or pending + * exception so as not to incorrectly trigger shutdown. */ - vcpu->arch.exception.pending = true; vcpu->arch.exception.injected = false; - vcpu->arch.exception.has_error_code = true; - vcpu->arch.exception.nr = DF_VECTOR; - vcpu->arch.exception.error_code = 0; - vcpu->arch.exception.has_payload = false; - vcpu->arch.exception.payload = 0; - } else + vcpu->arch.exception.pending = false; + + kvm_queue_exception_e(vcpu, DF_VECTOR, 0); + } else { /* replace previous exception with a new one in a hope that instruction re-execution will regenerate lost exception */ goto queue; + } } void kvm_queue_exception(struct kvm_vcpu *vcpu, unsigned nr) @@ -729,20 +770,22 @@ static int complete_emulated_insn_gp(struct kvm_vcpu *vcpu, int err) void kvm_inject_page_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault) { ++vcpu->stat.pf_guest; - vcpu->arch.exception.nested_apf = - is_guest_mode(vcpu) && fault->async_page_fault; - if (vcpu->arch.exception.nested_apf) { - vcpu->arch.apf.nested_apf_token = fault->address; - kvm_queue_exception_e(vcpu, PF_VECTOR, fault->error_code); - } else { + + /* + * Async #PF in L2 is always forwarded to L1 as a VM-Exit regardless of + * whether or not L1 wants to intercept "regular" #PF. + */ + if (is_guest_mode(vcpu) && fault->async_page_fault) + kvm_queue_exception_vmexit(vcpu, PF_VECTOR, + true, fault->error_code, + true, fault->address); + else kvm_queue_exception_e_p(vcpu, PF_VECTOR, fault->error_code, fault->address); - } } EXPORT_SYMBOL_GPL(kvm_inject_page_fault); -/* Returns true if the page fault was immediately morphed into a VM-Exit. */ -bool kvm_inject_emulated_page_fault(struct kvm_vcpu *vcpu, +void kvm_inject_emulated_page_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault) { struct kvm_mmu *fault_mmu; @@ -760,26 +803,7 @@ bool kvm_inject_emulated_page_fault(struct kvm_vcpu *vcpu, kvm_mmu_invalidate_gva(vcpu, fault_mmu, fault->address, fault_mmu->root.hpa); - /* - * A workaround for KVM's bad exception handling. If KVM injected an - * exception into L2, and L2 encountered a #PF while vectoring the - * injected exception, manually check to see if L1 wants to intercept - * #PF, otherwise queuing the #PF will lead to #DF or a lost exception. - * In all other cases, defer the check to nested_ops->check_events(), - * which will correctly handle priority (this does not). Note, other - * exceptions, e.g. #GP, are theoretically affected, #PF is simply the - * most problematic, e.g. when L0 and L1 are both intercepting #PF for - * shadow paging. - * - * TODO: Rewrite exception handling to track injected and pending - * (VM-Exit) exceptions separately. - */ - if (unlikely(vcpu->arch.exception.injected && is_guest_mode(vcpu)) && - kvm_x86_ops.nested_ops->handle_page_fault_workaround(vcpu, fault)) - return true; - fault_mmu->inject_page_fault(vcpu, fault); - return false; } EXPORT_SYMBOL_GPL(kvm_inject_emulated_page_fault); @@ -1011,15 +1035,10 @@ void kvm_load_host_xsave_state(struct kvm_vcpu *vcpu) } EXPORT_SYMBOL_GPL(kvm_load_host_xsave_state); -static inline u64 kvm_guest_supported_xcr0(struct kvm_vcpu *vcpu) -{ - return vcpu->arch.guest_fpu.fpstate->user_xfeatures; -} - #ifdef CONFIG_X86_64 static inline u64 kvm_guest_supported_xfd(struct kvm_vcpu *vcpu) { - return kvm_guest_supported_xcr0(vcpu) & XFEATURE_MASK_USER_DYNAMIC; + return vcpu->arch.guest_supported_xcr0 & XFEATURE_MASK_USER_DYNAMIC; } #endif @@ -1042,7 +1061,7 @@ static int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr) * saving. However, xcr0 bit 0 is always set, even if the * emulated CPU does not support XSAVE (see kvm_vcpu_reset()). */ - valid_bits = kvm_guest_supported_xcr0(vcpu) | XFEATURE_MASK_FP; + valid_bits = vcpu->arch.guest_supported_xcr0 | XFEATURE_MASK_FP; if (xcr0 & ~valid_bits) return 1; @@ -1070,6 +1089,7 @@ static int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr) int kvm_emulate_xsetbv(struct kvm_vcpu *vcpu) { + /* Note, #UD due to CR4.OSXSAVE=0 has priority over the intercept. */ if (static_call(kvm_x86_get_cpl)(vcpu) != 0 || __kvm_set_xcr(vcpu, kvm_rcx_read(vcpu), kvm_read_edx_eax(vcpu))) { kvm_inject_gp(vcpu, 0); @@ -1424,32 +1444,27 @@ static const u32 msrs_to_save_all[] = { MSR_ARCH_PERFMON_FIXED_CTR0 + 2, MSR_CORE_PERF_FIXED_CTR_CTRL, MSR_CORE_PERF_GLOBAL_STATUS, MSR_CORE_PERF_GLOBAL_CTRL, MSR_CORE_PERF_GLOBAL_OVF_CTRL, + MSR_IA32_PEBS_ENABLE, MSR_IA32_DS_AREA, MSR_PEBS_DATA_CFG, + + /* This part of MSRs should match KVM_INTEL_PMC_MAX_GENERIC. */ MSR_ARCH_PERFMON_PERFCTR0, MSR_ARCH_PERFMON_PERFCTR1, MSR_ARCH_PERFMON_PERFCTR0 + 2, MSR_ARCH_PERFMON_PERFCTR0 + 3, MSR_ARCH_PERFMON_PERFCTR0 + 4, MSR_ARCH_PERFMON_PERFCTR0 + 5, MSR_ARCH_PERFMON_PERFCTR0 + 6, MSR_ARCH_PERFMON_PERFCTR0 + 7, - MSR_ARCH_PERFMON_PERFCTR0 + 8, MSR_ARCH_PERFMON_PERFCTR0 + 9, - MSR_ARCH_PERFMON_PERFCTR0 + 10, MSR_ARCH_PERFMON_PERFCTR0 + 11, - MSR_ARCH_PERFMON_PERFCTR0 + 12, MSR_ARCH_PERFMON_PERFCTR0 + 13, - MSR_ARCH_PERFMON_PERFCTR0 + 14, MSR_ARCH_PERFMON_PERFCTR0 + 15, - MSR_ARCH_PERFMON_PERFCTR0 + 16, MSR_ARCH_PERFMON_PERFCTR0 + 17, MSR_ARCH_PERFMON_EVENTSEL0, MSR_ARCH_PERFMON_EVENTSEL1, MSR_ARCH_PERFMON_EVENTSEL0 + 2, MSR_ARCH_PERFMON_EVENTSEL0 + 3, MSR_ARCH_PERFMON_EVENTSEL0 + 4, MSR_ARCH_PERFMON_EVENTSEL0 + 5, MSR_ARCH_PERFMON_EVENTSEL0 + 6, MSR_ARCH_PERFMON_EVENTSEL0 + 7, - MSR_ARCH_PERFMON_EVENTSEL0 + 8, MSR_ARCH_PERFMON_EVENTSEL0 + 9, - MSR_ARCH_PERFMON_EVENTSEL0 + 10, MSR_ARCH_PERFMON_EVENTSEL0 + 11, - MSR_ARCH_PERFMON_EVENTSEL0 + 12, MSR_ARCH_PERFMON_EVENTSEL0 + 13, - MSR_ARCH_PERFMON_EVENTSEL0 + 14, MSR_ARCH_PERFMON_EVENTSEL0 + 15, - MSR_ARCH_PERFMON_EVENTSEL0 + 16, MSR_ARCH_PERFMON_EVENTSEL0 + 17, - MSR_IA32_PEBS_ENABLE, MSR_IA32_DS_AREA, MSR_PEBS_DATA_CFG, MSR_K7_EVNTSEL0, MSR_K7_EVNTSEL1, MSR_K7_EVNTSEL2, MSR_K7_EVNTSEL3, MSR_K7_PERFCTR0, MSR_K7_PERFCTR1, MSR_K7_PERFCTR2, MSR_K7_PERFCTR3, + + /* This part of MSRs should match KVM_AMD_PMC_MAX_GENERIC. */ MSR_F15H_PERF_CTL0, MSR_F15H_PERF_CTL1, MSR_F15H_PERF_CTL2, MSR_F15H_PERF_CTL3, MSR_F15H_PERF_CTL4, MSR_F15H_PERF_CTL5, MSR_F15H_PERF_CTR0, MSR_F15H_PERF_CTR1, MSR_F15H_PERF_CTR2, MSR_F15H_PERF_CTR3, MSR_F15H_PERF_CTR4, MSR_F15H_PERF_CTR5, + MSR_IA32_XFD, MSR_IA32_XFD_ERR, }; @@ -1548,7 +1563,7 @@ static const u32 msr_based_features_all[] = { MSR_IA32_VMX_EPT_VPID_CAP, MSR_IA32_VMX_VMFUNC, - MSR_F10H_DECFG, + MSR_AMD64_DE_CFG, MSR_IA32_UCODE_REV, MSR_IA32_ARCH_CAPABILITIES, MSR_IA32_PERF_CAPABILITIES, @@ -1557,12 +1572,32 @@ static const u32 msr_based_features_all[] = { static u32 msr_based_features[ARRAY_SIZE(msr_based_features_all)]; static unsigned int num_msr_based_features; +/* + * Some IA32_ARCH_CAPABILITIES bits have dependencies on MSRs that KVM + * does not yet virtualize. These include: + * 10 - MISC_PACKAGE_CTRLS + * 11 - ENERGY_FILTERING_CTL + * 12 - DOITM + * 18 - FB_CLEAR_CTRL + * 21 - XAPIC_DISABLE_STATUS + * 23 - OVERCLOCKING_STATUS + */ + +#define KVM_SUPPORTED_ARCH_CAP \ + (ARCH_CAP_RDCL_NO | ARCH_CAP_IBRS_ALL | ARCH_CAP_RSBA | \ + ARCH_CAP_SKIP_VMENTRY_L1DFLUSH | ARCH_CAP_SSB_NO | ARCH_CAP_MDS_NO | \ + ARCH_CAP_PSCHANGE_MC_NO | ARCH_CAP_TSX_CTRL_MSR | ARCH_CAP_TAA_NO | \ + ARCH_CAP_SBDR_SSDP_NO | ARCH_CAP_FBSDP_NO | ARCH_CAP_PSDP_NO | \ + ARCH_CAP_FB_CLEAR | ARCH_CAP_RRSBA | ARCH_CAP_PBRSB_NO) + static u64 kvm_get_arch_capabilities(void) { u64 data = 0; - if (boot_cpu_has(X86_FEATURE_ARCH_CAPABILITIES)) + if (boot_cpu_has(X86_FEATURE_ARCH_CAPABILITIES)) { rdmsrl(MSR_IA32_ARCH_CAPABILITIES, data); + data &= KVM_SUPPORTED_ARCH_CAP; + } /* * If nx_huge_pages is enabled, KVM's shadow paging will ensure that @@ -1610,9 +1645,6 @@ static u64 kvm_get_arch_capabilities(void) */ } - /* Guests don't need to know "Fill buffer clear control" exists */ - data &= ~ARCH_CAP_FB_CLEAR_CTRL; - return data; } @@ -2284,11 +2316,11 @@ static void kvm_write_system_time(struct kvm_vcpu *vcpu, gpa_t system_time, /* we verify if the enable bit is set... */ if (system_time & 1) { - kvm_gfn_to_pfn_cache_init(vcpu->kvm, &vcpu->arch.pv_time, vcpu, - KVM_HOST_USES_PFN, system_time & ~1ULL, - sizeof(struct pvclock_vcpu_time_info)); + kvm_gpc_activate(vcpu->kvm, &vcpu->arch.pv_time, vcpu, + KVM_HOST_USES_PFN, system_time & ~1ULL, + sizeof(struct pvclock_vcpu_time_info)); } else { - kvm_gfn_to_pfn_cache_destroy(vcpu->kvm, &vcpu->arch.pv_time); + kvm_gpc_deactivate(vcpu->kvm, &vcpu->arch.pv_time); } return; @@ -3357,7 +3389,7 @@ static int kvm_pv_enable_async_pf_int(struct kvm_vcpu *vcpu, u64 data) static void kvmclock_reset(struct kvm_vcpu *vcpu) { - kvm_gfn_to_pfn_cache_destroy(vcpu->kvm, &vcpu->arch.pv_time); + kvm_gpc_deactivate(vcpu->kvm, &vcpu->arch.pv_time); vcpu->arch.time = 0; } @@ -4828,7 +4860,7 @@ static int kvm_vcpu_ready_for_interrupt_injection(struct kvm_vcpu *vcpu) return (kvm_arch_interrupt_allowed(vcpu) && kvm_cpu_accept_dm_intr(vcpu) && !kvm_event_needs_reinjection(vcpu) && - !vcpu->arch.exception.pending); + !kvm_is_exception_pending(vcpu)); } static int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu, @@ -5003,25 +5035,38 @@ static int kvm_vcpu_ioctl_x86_set_mce(struct kvm_vcpu *vcpu, static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu, struct kvm_vcpu_events *events) { + struct kvm_queued_exception *ex; + process_nmi(vcpu); if (kvm_check_request(KVM_REQ_SMI, vcpu)) process_smi(vcpu); /* - * In guest mode, payload delivery should be deferred, - * so that the L1 hypervisor can intercept #PF before - * CR2 is modified (or intercept #DB before DR6 is - * modified under nVMX). Unless the per-VM capability, - * KVM_CAP_EXCEPTION_PAYLOAD, is set, we may not defer the delivery of - * an exception payload and handle after a KVM_GET_VCPU_EVENTS. Since we - * opportunistically defer the exception payload, deliver it if the - * capability hasn't been requested before processing a - * KVM_GET_VCPU_EVENTS. + * KVM's ABI only allows for one exception to be migrated. Luckily, + * the only time there can be two queued exceptions is if there's a + * non-exiting _injected_ exception, and a pending exiting exception. + * In that case, ignore the VM-Exiting exception as it's an extension + * of the injected exception. + */ + if (vcpu->arch.exception_vmexit.pending && + !vcpu->arch.exception.pending && + !vcpu->arch.exception.injected) + ex = &vcpu->arch.exception_vmexit; + else + ex = &vcpu->arch.exception; + + /* + * In guest mode, payload delivery should be deferred if the exception + * will be intercepted by L1, e.g. KVM should not modifying CR2 if L1 + * intercepts #PF, ditto for DR6 and #DBs. If the per-VM capability, + * KVM_CAP_EXCEPTION_PAYLOAD, is not set, userspace may or may not + * propagate the payload and so it cannot be safely deferred. Deliver + * the payload if the capability hasn't been requested. */ if (!vcpu->kvm->arch.exception_payload_enabled && - vcpu->arch.exception.pending && vcpu->arch.exception.has_payload) - kvm_deliver_exception_payload(vcpu); + ex->pending && ex->has_payload) + kvm_deliver_exception_payload(vcpu, ex); /* * The API doesn't provide the instruction length for software @@ -5029,26 +5074,25 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu, * isn't advanced, we should expect to encounter the exception * again. */ - if (kvm_exception_is_soft(vcpu->arch.exception.nr)) { + if (kvm_exception_is_soft(ex->vector)) { events->exception.injected = 0; events->exception.pending = 0; } else { - events->exception.injected = vcpu->arch.exception.injected; - events->exception.pending = vcpu->arch.exception.pending; + events->exception.injected = ex->injected; + events->exception.pending = ex->pending; /* * For ABI compatibility, deliberately conflate * pending and injected exceptions when * KVM_CAP_EXCEPTION_PAYLOAD isn't enabled. */ if (!vcpu->kvm->arch.exception_payload_enabled) - events->exception.injected |= - vcpu->arch.exception.pending; + events->exception.injected |= ex->pending; } - events->exception.nr = vcpu->arch.exception.nr; - events->exception.has_error_code = vcpu->arch.exception.has_error_code; - events->exception.error_code = vcpu->arch.exception.error_code; - events->exception_has_payload = vcpu->arch.exception.has_payload; - events->exception_payload = vcpu->arch.exception.payload; + events->exception.nr = ex->vector; + events->exception.has_error_code = ex->has_error_code; + events->exception.error_code = ex->error_code; + events->exception_has_payload = ex->has_payload; + events->exception_payload = ex->payload; events->interrupt.injected = vcpu->arch.interrupt.injected && !vcpu->arch.interrupt.soft; @@ -5118,9 +5162,22 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu, return -EINVAL; process_nmi(vcpu); + + /* + * Flag that userspace is stuffing an exception, the next KVM_RUN will + * morph the exception to a VM-Exit if appropriate. Do this only for + * pending exceptions, already-injected exceptions are not subject to + * intercpetion. Note, userspace that conflates pending and injected + * is hosed, and will incorrectly convert an injected exception into a + * pending exception, which in turn may cause a spurious VM-Exit. + */ + vcpu->arch.exception_from_userspace = events->exception.pending; + + vcpu->arch.exception_vmexit.pending = false; + vcpu->arch.exception.injected = events->exception.injected; vcpu->arch.exception.pending = events->exception.pending; - vcpu->arch.exception.nr = events->exception.nr; + vcpu->arch.exception.vector = events->exception.nr; vcpu->arch.exception.has_error_code = events->exception.has_error_code; vcpu->arch.exception.error_code = events->exception.error_code; vcpu->arch.exception.has_payload = events->exception_has_payload; @@ -5144,7 +5201,7 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu, if (events->flags & KVM_VCPUEVENT_VALID_SMM) { if (!!(vcpu->arch.hflags & HF_SMM_MASK) != events->smi.smm) { - kvm_x86_ops.nested_ops->leave_nested(vcpu); + kvm_leave_nested(vcpu); kvm_smm_changed(vcpu, events->smi.smm); } @@ -6386,26 +6443,22 @@ static int kvm_add_msr_filter(struct kvm_x86_msr_filter *msr_filter, return 0; } -static int kvm_vm_ioctl_set_msr_filter(struct kvm *kvm, void __user *argp) +static int kvm_vm_ioctl_set_msr_filter(struct kvm *kvm, + struct kvm_msr_filter *filter) { - struct kvm_msr_filter __user *user_msr_filter = argp; struct kvm_x86_msr_filter *new_filter, *old_filter; - struct kvm_msr_filter filter; bool default_allow; bool empty = true; int r = 0; u32 i; - if (copy_from_user(&filter, user_msr_filter, sizeof(filter))) - return -EFAULT; - - if (filter.flags & ~KVM_MSR_FILTER_DEFAULT_DENY) + if (filter->flags & ~KVM_MSR_FILTER_DEFAULT_DENY) return -EINVAL; - for (i = 0; i < ARRAY_SIZE(filter.ranges); i++) - empty &= !filter.ranges[i].nmsrs; + for (i = 0; i < ARRAY_SIZE(filter->ranges); i++) + empty &= !filter->ranges[i].nmsrs; - default_allow = !(filter.flags & KVM_MSR_FILTER_DEFAULT_DENY); + default_allow = !(filter->flags & KVM_MSR_FILTER_DEFAULT_DENY); if (empty && !default_allow) return -EINVAL; @@ -6413,8 +6466,8 @@ static int kvm_vm_ioctl_set_msr_filter(struct kvm *kvm, void __user *argp) if (!new_filter) return -ENOMEM; - for (i = 0; i < ARRAY_SIZE(filter.ranges); i++) { - r = kvm_add_msr_filter(new_filter, &filter.ranges[i]); + for (i = 0; i < ARRAY_SIZE(filter->ranges); i++) { + r = kvm_add_msr_filter(new_filter, &filter->ranges[i]); if (r) { kvm_free_msr_filter(new_filter); return r; @@ -6437,6 +6490,62 @@ static int kvm_vm_ioctl_set_msr_filter(struct kvm *kvm, void __user *argp) return 0; } +#ifdef CONFIG_KVM_COMPAT +/* for KVM_X86_SET_MSR_FILTER */ +struct kvm_msr_filter_range_compat { + __u32 flags; + __u32 nmsrs; + __u32 base; + __u32 bitmap; +}; + +struct kvm_msr_filter_compat { + __u32 flags; + struct kvm_msr_filter_range_compat ranges[KVM_MSR_FILTER_MAX_RANGES]; +}; + +#define KVM_X86_SET_MSR_FILTER_COMPAT _IOW(KVMIO, 0xc6, struct kvm_msr_filter_compat) + +long kvm_arch_vm_compat_ioctl(struct file *filp, unsigned int ioctl, + unsigned long arg) +{ + void __user *argp = (void __user *)arg; + struct kvm *kvm = filp->private_data; + long r = -ENOTTY; + + switch (ioctl) { + case KVM_X86_SET_MSR_FILTER_COMPAT: { + struct kvm_msr_filter __user *user_msr_filter = argp; + struct kvm_msr_filter_compat filter_compat; + struct kvm_msr_filter filter; + int i; + + if (copy_from_user(&filter_compat, user_msr_filter, + sizeof(filter_compat))) + return -EFAULT; + + filter.flags = filter_compat.flags; + for (i = 0; i < ARRAY_SIZE(filter.ranges); i++) { + struct kvm_msr_filter_range_compat *cr; + + cr = &filter_compat.ranges[i]; + filter.ranges[i] = (struct kvm_msr_filter_range) { + .flags = cr->flags, + .nmsrs = cr->nmsrs, + .base = cr->base, + .bitmap = (__u8 *)(ulong)cr->bitmap, + }; + } + + r = kvm_vm_ioctl_set_msr_filter(kvm, &filter); + break; + } + } + + return r; +} +#endif + #ifdef CONFIG_HAVE_KVM_PM_NOTIFIER static int kvm_arch_suspend_notifier(struct kvm *kvm) { @@ -6859,9 +6968,16 @@ set_pit2_out: case KVM_SET_PMU_EVENT_FILTER: r = kvm_vm_ioctl_set_pmu_event_filter(kvm, argp); break; - case KVM_X86_SET_MSR_FILTER: - r = kvm_vm_ioctl_set_msr_filter(kvm, argp); + case KVM_X86_SET_MSR_FILTER: { + struct kvm_msr_filter __user *user_msr_filter = argp; + struct kvm_msr_filter filter; + + if (copy_from_user(&filter, user_msr_filter, sizeof(filter))) + return -EFAULT; + + r = kvm_vm_ioctl_set_msr_filter(kvm, &filter); break; + } default: r = -ENOTTY; } @@ -6926,14 +7042,14 @@ static void kvm_init_msr_list(void) intel_pt_validate_hw_cap(PT_CAP_num_address_ranges) * 2) continue; break; - case MSR_ARCH_PERFMON_PERFCTR0 ... MSR_ARCH_PERFMON_PERFCTR0 + 17: + case MSR_ARCH_PERFMON_PERFCTR0 ... MSR_ARCH_PERFMON_PERFCTR_MAX: if (msrs_to_save_all[i] - MSR_ARCH_PERFMON_PERFCTR0 >= - min(INTEL_PMC_MAX_GENERIC, kvm_pmu_cap.num_counters_gp)) + min(KVM_INTEL_PMC_MAX_GENERIC, kvm_pmu_cap.num_counters_gp)) continue; break; - case MSR_ARCH_PERFMON_EVENTSEL0 ... MSR_ARCH_PERFMON_EVENTSEL0 + 17: + case MSR_ARCH_PERFMON_EVENTSEL0 ... MSR_ARCH_PERFMON_EVENTSEL_MAX: if (msrs_to_save_all[i] - MSR_ARCH_PERFMON_EVENTSEL0 >= - min(INTEL_PMC_MAX_GENERIC, kvm_pmu_cap.num_counters_gp)) + min(KVM_INTEL_PMC_MAX_GENERIC, kvm_pmu_cap.num_counters_gp)) continue; break; case MSR_IA32_XFD: @@ -7244,6 +7360,7 @@ static int kvm_can_emulate_insn(struct kvm_vcpu *vcpu, int emul_type, int handle_ud(struct kvm_vcpu *vcpu) { static const char kvm_emulate_prefix[] = { __KVM_EMULATE_PREFIX }; + int fep_flags = READ_ONCE(force_emulation_prefix); int emul_type = EMULTYPE_TRAP_UD; char sig[5]; /* ud2; .ascii "kvm" */ struct x86_exception e; @@ -7251,10 +7368,12 @@ int handle_ud(struct kvm_vcpu *vcpu) if (unlikely(!kvm_can_emulate_insn(vcpu, emul_type, NULL, 0))) return 1; - if (force_emulation_prefix && + if (fep_flags && kvm_read_guest_virt(vcpu, kvm_get_linear_rip(vcpu), sig, sizeof(sig), &e) == 0 && memcmp(sig, kvm_emulate_prefix, sizeof(sig)) == 0) { + if (fep_flags & KVM_FEP_CLEAR_RFLAGS_RF) + kvm_set_rflags(vcpu, kvm_get_rflags(vcpu) & ~X86_EFLAGS_RF); kvm_rip_write(vcpu, kvm_rip_read(vcpu) + sizeof(sig)); emul_type = EMULTYPE_TRAP_UD_FORCED; } @@ -7920,14 +8039,20 @@ static int emulator_get_msr_with_filter(struct x86_emulate_ctxt *ctxt, int r; r = kvm_get_msr_with_filter(vcpu, msr_index, pdata); + if (r < 0) + return X86EMUL_UNHANDLEABLE; - if (r && kvm_msr_user_space(vcpu, msr_index, KVM_EXIT_X86_RDMSR, 0, - complete_emulated_rdmsr, r)) { - /* Bounce to user space */ - return X86EMUL_IO_NEEDED; + if (r) { + if (kvm_msr_user_space(vcpu, msr_index, KVM_EXIT_X86_RDMSR, 0, + complete_emulated_rdmsr, r)) + return X86EMUL_IO_NEEDED; + + trace_kvm_msr_read_ex(msr_index); + return X86EMUL_PROPAGATE_FAULT; } - return r; + trace_kvm_msr_read(msr_index, *pdata); + return X86EMUL_CONTINUE; } static int emulator_set_msr_with_filter(struct x86_emulate_ctxt *ctxt, @@ -7937,14 +8062,20 @@ static int emulator_set_msr_with_filter(struct x86_emulate_ctxt *ctxt, int r; r = kvm_set_msr_with_filter(vcpu, msr_index, data); + if (r < 0) + return X86EMUL_UNHANDLEABLE; - if (r && kvm_msr_user_space(vcpu, msr_index, KVM_EXIT_X86_WRMSR, data, - complete_emulated_msr_access, r)) { - /* Bounce to user space */ - return X86EMUL_IO_NEEDED; + if (r) { + if (kvm_msr_user_space(vcpu, msr_index, KVM_EXIT_X86_WRMSR, data, + complete_emulated_msr_access, r)) + return X86EMUL_IO_NEEDED; + + trace_kvm_msr_write_ex(msr_index, data); + return X86EMUL_PROPAGATE_FAULT; } - return r; + trace_kvm_msr_write(msr_index, data); + return X86EMUL_CONTINUE; } static int emulator_get_msr(struct x86_emulate_ctxt *ctxt, @@ -8148,18 +8279,17 @@ static void toggle_interruptibility(struct kvm_vcpu *vcpu, u32 mask) } } -static bool inject_emulated_exception(struct kvm_vcpu *vcpu) +static void inject_emulated_exception(struct kvm_vcpu *vcpu) { struct x86_emulate_ctxt *ctxt = vcpu->arch.emulate_ctxt; - if (ctxt->exception.vector == PF_VECTOR) - return kvm_inject_emulated_page_fault(vcpu, &ctxt->exception); - if (ctxt->exception.error_code_valid) + if (ctxt->exception.vector == PF_VECTOR) + kvm_inject_emulated_page_fault(vcpu, &ctxt->exception); + else if (ctxt->exception.error_code_valid) kvm_queue_exception_e(vcpu, ctxt->exception.vector, ctxt->exception.error_code); else kvm_queue_exception(vcpu, ctxt->exception.vector); - return false; } static struct x86_emulate_ctxt *alloc_emulate_ctxt(struct kvm_vcpu *vcpu) @@ -8535,8 +8665,46 @@ int kvm_skip_emulated_instruction(struct kvm_vcpu *vcpu) } EXPORT_SYMBOL_GPL(kvm_skip_emulated_instruction); -static bool kvm_vcpu_check_code_breakpoint(struct kvm_vcpu *vcpu, int *r) +static bool kvm_is_code_breakpoint_inhibited(struct kvm_vcpu *vcpu) { + u32 shadow; + + if (kvm_get_rflags(vcpu) & X86_EFLAGS_RF) + return true; + + /* + * Intel CPUs inhibit code #DBs when MOV/POP SS blocking is active, + * but AMD CPUs do not. MOV/POP SS blocking is rare, check that first + * to avoid the relatively expensive CPUID lookup. + */ + shadow = static_call(kvm_x86_get_interrupt_shadow)(vcpu); + return (shadow & KVM_X86_SHADOW_INT_MOV_SS) && + guest_cpuid_is_intel(vcpu); +} + +static bool kvm_vcpu_check_code_breakpoint(struct kvm_vcpu *vcpu, + int emulation_type, int *r) +{ + WARN_ON_ONCE(emulation_type & EMULTYPE_NO_DECODE); + + /* + * Do not check for code breakpoints if hardware has already done the + * checks, as inferred from the emulation type. On NO_DECODE and SKIP, + * the instruction has passed all exception checks, and all intercepted + * exceptions that trigger emulation have lower priority than code + * breakpoints, i.e. the fact that the intercepted exception occurred + * means any code breakpoints have already been serviced. + * + * Note, KVM needs to check for code #DBs on EMULTYPE_TRAP_UD_FORCED as + * hardware has checked the RIP of the magic prefix, but not the RIP of + * the instruction being emulated. The intent of forced emulation is + * to behave as if KVM intercepted the instruction without an exception + * and without a prefix. + */ + if (emulation_type & (EMULTYPE_NO_DECODE | EMULTYPE_SKIP | + EMULTYPE_TRAP_UD | EMULTYPE_VMWARE_GP | EMULTYPE_PF)) + return false; + if (unlikely(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP) && (vcpu->arch.guest_debug_dr7 & DR7_BP_EN_MASK)) { struct kvm_run *kvm_run = vcpu->run; @@ -8556,7 +8724,7 @@ static bool kvm_vcpu_check_code_breakpoint(struct kvm_vcpu *vcpu, int *r) } if (unlikely(vcpu->arch.dr7 & DR7_BP_EN_MASK) && - !(kvm_get_rflags(vcpu) & X86_EFLAGS_RF)) { + !kvm_is_code_breakpoint_inhibited(vcpu)) { unsigned long eip = kvm_get_linear_rip(vcpu); u32 dr6 = kvm_vcpu_check_hw_bp(eip, 0, vcpu->arch.dr7, @@ -8658,8 +8826,7 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, * are fault-like and are higher priority than any faults on * the code fetch itself. */ - if (!(emulation_type & EMULTYPE_SKIP) && - kvm_vcpu_check_code_breakpoint(vcpu, &r)) + if (kvm_vcpu_check_code_breakpoint(vcpu, emulation_type, &r)) return r; r = x86_decode_emulated_instruction(vcpu, emulation_type, @@ -8757,8 +8924,7 @@ restart: if (ctxt->have_exception) { r = 1; - if (inject_emulated_exception(vcpu)) - return r; + inject_emulated_exception(vcpu); } else if (vcpu->arch.pio.count) { if (!vcpu->arch.pio.in) { /* FIXME: return into emulator if single-stepping. */ @@ -8788,6 +8954,12 @@ writeback: unsigned long rflags = static_call(kvm_x86_get_rflags)(vcpu); toggle_interruptibility(vcpu, ctxt->interruptibility); vcpu->arch.emulate_regs_need_sync_to_vcpu = false; + + /* + * Note, EXCPT_DB is assumed to be fault-like as the emulator + * only supports code breakpoints and general detect #DB, both + * of which are fault-like. + */ if (!ctxt->have_exception || exception_type(ctxt->exception.vector) == EXCPT_TRAP) { kvm_pmu_trigger_event(vcpu, PERF_COUNT_HW_INSTRUCTIONS); @@ -9639,7 +9811,7 @@ static void update_cr8_intercept(struct kvm_vcpu *vcpu) int kvm_check_nested_events(struct kvm_vcpu *vcpu) { - if (kvm_check_request(KVM_REQ_TRIPLE_FAULT, vcpu)) { + if (kvm_test_request(KVM_REQ_TRIPLE_FAULT, vcpu)) { kvm_x86_ops.nested_ops->triple_fault(vcpu); return 1; } @@ -9649,74 +9821,155 @@ int kvm_check_nested_events(struct kvm_vcpu *vcpu) static void kvm_inject_exception(struct kvm_vcpu *vcpu) { - trace_kvm_inj_exception(vcpu->arch.exception.nr, + trace_kvm_inj_exception(vcpu->arch.exception.vector, vcpu->arch.exception.has_error_code, vcpu->arch.exception.error_code, vcpu->arch.exception.injected); if (vcpu->arch.exception.error_code && !is_protmode(vcpu)) vcpu->arch.exception.error_code = false; - static_call(kvm_x86_queue_exception)(vcpu); + static_call(kvm_x86_inject_exception)(vcpu); } -static int inject_pending_event(struct kvm_vcpu *vcpu, bool *req_immediate_exit) +/* + * Check for any event (interrupt or exception) that is ready to be injected, + * and if there is at least one event, inject the event with the highest + * priority. This handles both "pending" events, i.e. events that have never + * been injected into the guest, and "injected" events, i.e. events that were + * injected as part of a previous VM-Enter, but weren't successfully delivered + * and need to be re-injected. + * + * Note, this is not guaranteed to be invoked on a guest instruction boundary, + * i.e. doesn't guarantee that there's an event window in the guest. KVM must + * be able to inject exceptions in the "middle" of an instruction, and so must + * also be able to re-inject NMIs and IRQs in the middle of an instruction. + * I.e. for exceptions and re-injected events, NOT invoking this on instruction + * boundaries is necessary and correct. + * + * For simplicity, KVM uses a single path to inject all events (except events + * that are injected directly from L1 to L2) and doesn't explicitly track + * instruction boundaries for asynchronous events. However, because VM-Exits + * that can occur during instruction execution typically result in KVM skipping + * the instruction or injecting an exception, e.g. instruction and exception + * intercepts, and because pending exceptions have higher priority than pending + * interrupts, KVM still honors instruction boundaries in most scenarios. + * + * But, if a VM-Exit occurs during instruction execution, and KVM does NOT skip + * the instruction or inject an exception, then KVM can incorrecty inject a new + * asynchrounous event if the event became pending after the CPU fetched the + * instruction (in the guest). E.g. if a page fault (#PF, #NPF, EPT violation) + * occurs and is resolved by KVM, a coincident NMI, SMI, IRQ, etc... can be + * injected on the restarted instruction instead of being deferred until the + * instruction completes. + * + * In practice, this virtualization hole is unlikely to be observed by the + * guest, and even less likely to cause functional problems. To detect the + * hole, the guest would have to trigger an event on a side effect of an early + * phase of instruction execution, e.g. on the instruction fetch from memory. + * And for it to be a functional problem, the guest would need to depend on the + * ordering between that side effect, the instruction completing, _and_ the + * delivery of the asynchronous event. + */ +static int kvm_check_and_inject_events(struct kvm_vcpu *vcpu, + bool *req_immediate_exit) { + bool can_inject; int r; - bool can_inject = true; - /* try to reinject previous events if any */ + /* + * Process nested events first, as nested VM-Exit supercedes event + * re-injection. If there's an event queued for re-injection, it will + * be saved into the appropriate vmc{b,s}12 fields on nested VM-Exit. + */ + if (is_guest_mode(vcpu)) + r = kvm_check_nested_events(vcpu); + else + r = 0; - if (vcpu->arch.exception.injected) { - kvm_inject_exception(vcpu); - can_inject = false; - } /* - * Do not inject an NMI or interrupt if there is a pending - * exception. Exceptions and interrupts are recognized at - * instruction boundaries, i.e. the start of an instruction. - * Trap-like exceptions, e.g. #DB, have higher priority than - * NMIs and interrupts, i.e. traps are recognized before an - * NMI/interrupt that's pending on the same instruction. - * Fault-like exceptions, e.g. #GP and #PF, are the lowest - * priority, but are only generated (pended) during instruction - * execution, i.e. a pending fault-like exception means the - * fault occurred on the *previous* instruction and must be - * serviced prior to recognizing any new events in order to - * fully complete the previous instruction. + * Re-inject exceptions and events *especially* if immediate entry+exit + * to/from L2 is needed, as any event that has already been injected + * into L2 needs to complete its lifecycle before injecting a new event. + * + * Don't re-inject an NMI or interrupt if there is a pending exception. + * This collision arises if an exception occurred while vectoring the + * injected event, KVM intercepted said exception, and KVM ultimately + * determined the fault belongs to the guest and queues the exception + * for injection back into the guest. + * + * "Injected" interrupts can also collide with pending exceptions if + * userspace ignores the "ready for injection" flag and blindly queues + * an interrupt. In that case, prioritizing the exception is correct, + * as the exception "occurred" before the exit to userspace. Trap-like + * exceptions, e.g. most #DBs, have higher priority than interrupts. + * And while fault-like exceptions, e.g. #GP and #PF, are the lowest + * priority, they're only generated (pended) during instruction + * execution, and interrupts are recognized at instruction boundaries. + * Thus a pending fault-like exception means the fault occurred on the + * *previous* instruction and must be serviced prior to recognizing any + * new events in order to fully complete the previous instruction. */ - else if (!vcpu->arch.exception.pending) { - if (vcpu->arch.nmi_injected) { - static_call(kvm_x86_inject_nmi)(vcpu); - can_inject = false; - } else if (vcpu->arch.interrupt.injected) { - static_call(kvm_x86_inject_irq)(vcpu, true); - can_inject = false; - } - } + if (vcpu->arch.exception.injected) + kvm_inject_exception(vcpu); + else if (kvm_is_exception_pending(vcpu)) + ; /* see above */ + else if (vcpu->arch.nmi_injected) + static_call(kvm_x86_inject_nmi)(vcpu); + else if (vcpu->arch.interrupt.injected) + static_call(kvm_x86_inject_irq)(vcpu, true); + /* + * Exceptions that morph to VM-Exits are handled above, and pending + * exceptions on top of injected exceptions that do not VM-Exit should + * either morph to #DF or, sadly, override the injected exception. + */ WARN_ON_ONCE(vcpu->arch.exception.injected && vcpu->arch.exception.pending); /* - * Call check_nested_events() even if we reinjected a previous event - * in order for caller to determine if it should require immediate-exit - * from L2 to L1 due to pending L1 events which require exit - * from L2 to L1. + * Bail if immediate entry+exit to/from the guest is needed to complete + * nested VM-Enter or event re-injection so that a different pending + * event can be serviced (or if KVM needs to exit to userspace). + * + * Otherwise, continue processing events even if VM-Exit occurred. The + * VM-Exit will have cleared exceptions that were meant for L2, but + * there may now be events that can be injected into L1. */ - if (is_guest_mode(vcpu)) { - r = kvm_check_nested_events(vcpu); - if (r < 0) - goto out; - } + if (r < 0) + goto out; + + /* + * A pending exception VM-Exit should either result in nested VM-Exit + * or force an immediate re-entry and exit to/from L2, and exception + * VM-Exits cannot be injected (flag should _never_ be set). + */ + WARN_ON_ONCE(vcpu->arch.exception_vmexit.injected || + vcpu->arch.exception_vmexit.pending); + + /* + * New events, other than exceptions, cannot be injected if KVM needs + * to re-inject a previous event. See above comments on re-injecting + * for why pending exceptions get priority. + */ + can_inject = !kvm_event_needs_reinjection(vcpu); - /* try to inject new event if pending */ if (vcpu->arch.exception.pending) { - if (exception_type(vcpu->arch.exception.nr) == EXCPT_FAULT) + /* + * Fault-class exceptions, except #DBs, set RF=1 in the RFLAGS + * value pushed on the stack. Trap-like exception and all #DBs + * leave RF as-is (KVM follows Intel's behavior in this regard; + * AMD states that code breakpoint #DBs excplitly clear RF=0). + * + * Note, most versions of Intel's SDM and AMD's APM incorrectly + * describe the behavior of General Detect #DBs, which are + * fault-like. They do _not_ set RF, a la code breakpoints. + */ + if (exception_type(vcpu->arch.exception.vector) == EXCPT_FAULT) __kvm_set_rflags(vcpu, kvm_get_rflags(vcpu) | X86_EFLAGS_RF); - if (vcpu->arch.exception.nr == DB_VECTOR) { - kvm_deliver_exception_payload(vcpu); + if (vcpu->arch.exception.vector == DB_VECTOR) { + kvm_deliver_exception_payload(vcpu, &vcpu->arch.exception); if (vcpu->arch.dr7 & DR7_GD) { vcpu->arch.dr7 &= ~DR7_GD; kvm_update_dr7(vcpu); @@ -9788,11 +10041,24 @@ static int inject_pending_event(struct kvm_vcpu *vcpu, bool *req_immediate_exit) } if (is_guest_mode(vcpu) && - kvm_x86_ops.nested_ops->hv_timer_pending && - kvm_x86_ops.nested_ops->hv_timer_pending(vcpu)) + kvm_x86_ops.nested_ops->has_events && + kvm_x86_ops.nested_ops->has_events(vcpu)) *req_immediate_exit = true; - WARN_ON(vcpu->arch.exception.pending); + /* + * KVM must never queue a new exception while injecting an event; KVM + * is done emulating and should only propagate the to-be-injected event + * to the VMCS/VMCB. Queueing a new exception can put the vCPU into an + * infinite loop as KVM will bail from VM-Enter to inject the pending + * exception and start the cycle all over. + * + * Exempt triple faults as they have special handling and won't put the + * vCPU into an infinite loop. Triple fault can be queued when running + * VMX without unrestricted guest, as that requires KVM to emulate Real + * Mode events (see kvm_inject_realmode_interrupt()). + */ + WARN_ON_ONCE(vcpu->arch.exception.pending || + vcpu->arch.exception_vmexit.pending); return 0; out: @@ -10097,7 +10363,7 @@ void kvm_vcpu_update_apicv(struct kvm_vcpu *vcpu) * When APICv gets disabled, we may still have injected interrupts * pending. At the same time, KVM_REQ_EVENT may not be set as APICv was * still active when the interrupt got accepted. Make sure - * inject_pending_event() is called to check for that. + * kvm_check_and_inject_events() is called to check for that. */ if (!apic->apicv_active) kvm_make_request(KVM_REQ_EVENT, vcpu); @@ -10139,7 +10405,10 @@ void __kvm_set_or_clear_apicv_inhibit(struct kvm *kvm, kvm->arch.apicv_inhibit_reasons = new; if (new) { unsigned long gfn = gpa_to_gfn(APIC_DEFAULT_PHYS_BASE); + int idx = srcu_read_lock(&kvm->srcu); + kvm_zap_gfn_range(kvm, gfn, gfn+1); + srcu_read_unlock(&kvm->srcu, idx); } } else { kvm->arch.apicv_inhibit_reasons = new; @@ -10297,15 +10566,16 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) r = 0; goto out; } - if (kvm_check_request(KVM_REQ_TRIPLE_FAULT, vcpu)) { - if (is_guest_mode(vcpu)) { + if (kvm_test_request(KVM_REQ_TRIPLE_FAULT, vcpu)) { + if (is_guest_mode(vcpu)) kvm_x86_ops.nested_ops->triple_fault(vcpu); - } else { + + if (kvm_check_request(KVM_REQ_TRIPLE_FAULT, vcpu)) { vcpu->run->exit_reason = KVM_EXIT_SHUTDOWN; vcpu->mmio_needed = 0; r = 0; - goto out; } + goto out; } if (kvm_check_request(KVM_REQ_APF_HALT, vcpu)) { /* Page is swapped out. Do synthetic halt */ @@ -10394,7 +10664,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) goto out; } - r = inject_pending_event(vcpu, &req_immediate_exit); + r = kvm_check_and_inject_events(vcpu, &req_immediate_exit); if (r < 0) { r = 0; goto out; @@ -10633,10 +10903,26 @@ static inline int vcpu_block(struct kvm_vcpu *vcpu) if (hv_timer) kvm_lapic_switch_to_hv_timer(vcpu); - if (!kvm_check_request(KVM_REQ_UNHALT, vcpu)) + /* + * If the vCPU is not runnable, a signal or another host event + * of some kind is pending; service it without changing the + * vCPU's activity state. + */ + if (!kvm_arch_vcpu_runnable(vcpu)) return 1; } + /* + * Evaluate nested events before exiting the halted state. This allows + * the halt state to be recorded properly in the VMCS12's activity + * state field (AMD does not have a similar field and a VM-Exit always + * causes a spurious wakeup from HLT). + */ + if (is_guest_mode(vcpu)) { + if (kvm_check_nested_events(vcpu) < 0) + return 0; + } + if (kvm_apic_accept_events(vcpu) < 0) return 0; switch(vcpu->arch.mp_state) { @@ -10652,16 +10938,14 @@ static inline int vcpu_block(struct kvm_vcpu *vcpu) case KVM_MP_STATE_INIT_RECEIVED: break; default: - return -EINTR; + WARN_ON_ONCE(1); + break; } return 1; } static inline bool kvm_vcpu_running(struct kvm_vcpu *vcpu) { - if (is_guest_mode(vcpu)) - kvm_check_nested_events(vcpu); - return (vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE && !vcpu->arch.apf.halted); } @@ -10810,6 +11094,7 @@ static void kvm_put_guest_fpu(struct kvm_vcpu *vcpu) int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) { + struct kvm_queued_exception *ex = &vcpu->arch.exception; struct kvm_run *kvm_run = vcpu->run; int r; @@ -10838,7 +11123,6 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) r = 0; goto out; } - kvm_clear_request(KVM_REQ_UNHALT, vcpu); r = -EAGAIN; if (signal_pending(current)) { r = -EINTR; @@ -10868,6 +11152,21 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) } } + /* + * If userspace set a pending exception and L2 is active, convert it to + * a pending VM-Exit if L1 wants to intercept the exception. + */ + if (vcpu->arch.exception_from_userspace && is_guest_mode(vcpu) && + kvm_x86_ops.nested_ops->is_exception_vmexit(vcpu, ex->vector, + ex->error_code)) { + kvm_queue_exception_vmexit(vcpu, ex->vector, + ex->has_error_code, ex->error_code, + ex->has_payload, ex->payload); + ex->injected = false; + ex->pending = false; + } + vcpu->arch.exception_from_userspace = false; + if (unlikely(vcpu->arch.complete_userspace_io)) { int (*cui)(struct kvm_vcpu *) = vcpu->arch.complete_userspace_io; vcpu->arch.complete_userspace_io = NULL; @@ -10974,6 +11273,7 @@ static void __set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) kvm_set_rflags(vcpu, regs->rflags | X86_EFLAGS_FIXED); vcpu->arch.exception.pending = false; + vcpu->arch.exception_vmexit.pending = false; kvm_make_request(KVM_REQ_EVENT, vcpu); } @@ -11093,16 +11393,30 @@ int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu, vcpu_load(vcpu); - if (!lapic_in_kernel(vcpu) && - mp_state->mp_state != KVM_MP_STATE_RUNNABLE) + switch (mp_state->mp_state) { + case KVM_MP_STATE_UNINITIALIZED: + case KVM_MP_STATE_HALTED: + case KVM_MP_STATE_AP_RESET_HOLD: + case KVM_MP_STATE_INIT_RECEIVED: + case KVM_MP_STATE_SIPI_RECEIVED: + if (!lapic_in_kernel(vcpu)) + goto out; + break; + + case KVM_MP_STATE_RUNNABLE: + break; + + default: goto out; + } /* - * KVM_MP_STATE_INIT_RECEIVED means the processor is in - * INIT state; latched init should be reported using - * KVM_SET_VCPU_EVENTS, so reject it here. + * Pending INITs are reported using KVM_SET_VCPU_EVENTS, disallow + * forcing the guest into INIT/SIPI if those events are supposed to be + * blocked. KVM prioritizes SMI over INIT, so reject INIT/SIPI state + * if an SMI is pending as well. */ - if ((kvm_vcpu_latch_init(vcpu) || vcpu->arch.smi_pending) && + if ((!kvm_apic_init_sipi_allowed(vcpu) || vcpu->arch.smi_pending) && (mp_state->mp_state == KVM_MP_STATE_SIPI_RECEIVED || mp_state->mp_state == KVM_MP_STATE_INIT_RECEIVED)) goto out; @@ -11341,7 +11655,7 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, if (dbg->control & (KVM_GUESTDBG_INJECT_DB | KVM_GUESTDBG_INJECT_BP)) { r = -EBUSY; - if (vcpu->arch.exception.pending) + if (kvm_is_exception_pending(vcpu)) goto out; if (dbg->control & KVM_GUESTDBG_INJECT_DB) kvm_queue_exception(vcpu, DB_VECTOR); @@ -11520,6 +11834,8 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) vcpu->arch.regs_avail = ~0; vcpu->arch.regs_dirty = ~0; + kvm_gpc_init(&vcpu->arch.pv_time); + if (!irqchip_in_kernel(vcpu->kvm) || kvm_vcpu_is_reset_bsp(vcpu)) vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; else @@ -11563,7 +11879,7 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) vcpu->arch.mci_ctl2_banks = kcalloc(KVM_MAX_MCE_BANKS, sizeof(u64), GFP_KERNEL_ACCOUNT); if (!vcpu->arch.mce_banks || !vcpu->arch.mci_ctl2_banks) - goto fail_free_pio_data; + goto fail_free_mce_banks; vcpu->arch.mcg_cap = KVM_MAX_MCE_BANKS; if (!zalloc_cpumask_var(&vcpu->arch.wbinvd_dirty_mask, @@ -11617,7 +11933,6 @@ free_wbinvd_dirty_mask: fail_free_mce_banks: kfree(vcpu->arch.mce_banks); kfree(vcpu->arch.mci_ctl2_banks); -fail_free_pio_data: free_page((unsigned long)vcpu->arch.pio_data); fail_free_lapic: kvm_free_lapic(vcpu); @@ -11689,8 +12004,18 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) WARN_ON_ONCE(!init_event && (old_cr0 || kvm_read_cr3(vcpu) || kvm_read_cr4(vcpu))); + /* + * SVM doesn't unconditionally VM-Exit on INIT and SHUTDOWN, thus it's + * possible to INIT the vCPU while L2 is active. Force the vCPU back + * into L1 as EFER.SVME is cleared on INIT (along with all other EFER + * bits), i.e. virtualization is disabled. + */ + if (is_guest_mode(vcpu)) + kvm_leave_nested(vcpu); + kvm_lapic_reset(vcpu, init_event); + WARN_ON_ONCE(is_guest_mode(vcpu) || is_smm(vcpu)); vcpu->arch.hflags = 0; vcpu->arch.smi_pending = 0; @@ -11724,8 +12049,8 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) struct fpstate *fpstate = vcpu->arch.guest_fpu.fpstate; /* - * To avoid have the INIT path from kvm_apic_has_events() that be - * called with loaded FPU and does not let userspace fix the state. + * All paths that lead to INIT are required to load the guest's + * FPU state (because most paths are buried in KVM_RUN). */ if (init_event) kvm_put_guest_fpu(vcpu); @@ -12054,6 +12379,10 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) if (ret) goto out_page_track; + ret = static_call(kvm_x86_vm_init)(kvm); + if (ret) + goto out_uninit_mmu; + INIT_HLIST_HEAD(&kvm->arch.mask_notifier_list); INIT_LIST_HEAD(&kvm->arch.assigned_dev_head); atomic_set(&kvm->arch.noncoherent_dma_count, 0); @@ -12089,8 +12418,10 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) kvm_hv_init_vm(kvm); kvm_xen_init_vm(kvm); - return static_call(kvm_x86_vm_init)(kvm); + return 0; +out_uninit_mmu: + kvm_mmu_uninit_vm(kvm); out_page_track: kvm_page_track_cleanup(kvm); out: @@ -12473,6 +12804,50 @@ static void kvm_mmu_slot_apply_flags(struct kvm *kvm, } else { kvm_mmu_slot_remove_write_access(kvm, new, PG_LEVEL_4K); } + + /* + * Unconditionally flush the TLBs after enabling dirty logging. + * A flush is almost always going to be necessary (see below), + * and unconditionally flushing allows the helpers to omit + * the subtly complex checks when removing write access. + * + * Do the flush outside of mmu_lock to reduce the amount of + * time mmu_lock is held. Flushing after dropping mmu_lock is + * safe as KVM only needs to guarantee the slot is fully + * write-protected before returning to userspace, i.e. before + * userspace can consume the dirty status. + * + * Flushing outside of mmu_lock requires KVM to be careful when + * making decisions based on writable status of an SPTE, e.g. a + * !writable SPTE doesn't guarantee a CPU can't perform writes. + * + * Specifically, KVM also write-protects guest page tables to + * monitor changes when using shadow paging, and must guarantee + * no CPUs can write to those page before mmu_lock is dropped. + * Because CPUs may have stale TLB entries at this point, a + * !writable SPTE doesn't guarantee CPUs can't perform writes. + * + * KVM also allows making SPTES writable outside of mmu_lock, + * e.g. to allow dirty logging without taking mmu_lock. + * + * To handle these scenarios, KVM uses a separate software-only + * bit (MMU-writable) to track if a SPTE is !writable due to + * a guest page table being write-protected (KVM clears the + * MMU-writable flag when write-protecting for shadow paging). + * + * The use of MMU-writable is also the primary motivation for + * the unconditional flush. Because KVM must guarantee that a + * CPU doesn't contain stale, writable TLB entries for a + * !MMU-writable SPTE, KVM must flush if it encounters any + * MMU-writable SPTE regardless of whether the actual hardware + * writable bit was set. I.e. KVM is almost guaranteed to need + * to flush, while unconditionally flushing allows the "remove + * write access" helpers to ignore MMU-writable entirely. + * + * See is_writable_pte() for more details (the case involving + * access-tracked SPTEs is particularly relevant). + */ + kvm_arch_flush_remote_tlbs_memslot(kvm, new); } } @@ -12519,13 +12894,14 @@ static inline bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu) if (!list_empty_careful(&vcpu->async_pf.done)) return true; - if (kvm_apic_has_events(vcpu)) + if (kvm_apic_has_pending_init_or_sipi(vcpu) && + kvm_apic_init_sipi_allowed(vcpu)) return true; if (vcpu->arch.pv.pv_unhalted) return true; - if (vcpu->arch.exception.pending) + if (kvm_is_exception_pending(vcpu)) return true; if (kvm_test_request(KVM_REQ_NMI, vcpu) || @@ -12547,16 +12923,13 @@ static inline bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu) return true; if (is_guest_mode(vcpu) && - kvm_x86_ops.nested_ops->hv_timer_pending && - kvm_x86_ops.nested_ops->hv_timer_pending(vcpu)) + kvm_x86_ops.nested_ops->has_events && + kvm_x86_ops.nested_ops->has_events(vcpu)) return true; if (kvm_xen_has_pending_events(vcpu)) return true; - if (kvm_test_request(KVM_REQ_TRIPLE_FAULT, vcpu)) - return true; - return false; } @@ -12780,7 +13153,7 @@ bool kvm_can_do_async_pf(struct kvm_vcpu *vcpu) { if (unlikely(!lapic_in_kernel(vcpu) || kvm_event_needs_reinjection(vcpu) || - vcpu->arch.exception.pending)) + kvm_is_exception_pending(vcpu))) return false; if (kvm_hlt_in_guest(vcpu->kvm) && !kvm_can_deliver_async_pf(vcpu)) @@ -13331,7 +13704,7 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_inj_virq); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_page_fault); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_msr); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_cr); -EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_vmrun); +EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_vmenter); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_vmexit); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_vmexit_inject); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_intr_vmexit); diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index 1926d2cb8e79..829d3134c1eb 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -82,10 +82,18 @@ static inline unsigned int __shrink_ple_window(unsigned int val, void kvm_service_local_tlb_flush_requests(struct kvm_vcpu *vcpu); int kvm_check_nested_events(struct kvm_vcpu *vcpu); +static inline bool kvm_is_exception_pending(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.exception.pending || + vcpu->arch.exception_vmexit.pending || + kvm_test_request(KVM_REQ_TRIPLE_FAULT, vcpu); +} + static inline void kvm_clear_exception_queue(struct kvm_vcpu *vcpu) { vcpu->arch.exception.pending = false; vcpu->arch.exception.injected = false; + vcpu->arch.exception_vmexit.pending = false; } static inline void kvm_queue_interrupt(struct kvm_vcpu *vcpu, u8 vector, @@ -267,11 +275,6 @@ static inline bool kvm_check_has_quirk(struct kvm *kvm, u64 quirk) return !(kvm->arch.disabled_quirks & quirk); } -static inline bool kvm_vcpu_latch_init(struct kvm_vcpu *vcpu) -{ - return is_smm(vcpu) || static_call(kvm_x86_apic_init_signal_blocked)(vcpu); -} - void kvm_inject_realmode_interrupt(struct kvm_vcpu *vcpu, int irq, int inc_eip); u64 get_kvmclock_ns(struct kvm *kvm); @@ -286,7 +289,8 @@ int kvm_write_guest_virt_system(struct kvm_vcpu *vcpu, int handle_ud(struct kvm_vcpu *vcpu); -void kvm_deliver_exception_payload(struct kvm_vcpu *vcpu); +void kvm_deliver_exception_payload(struct kvm_vcpu *vcpu, + struct kvm_queued_exception *ex); void kvm_vcpu_mtrr_init(struct kvm_vcpu *vcpu); u8 kvm_mtrr_get_guest_memory_type(struct kvm_vcpu *vcpu, gfn_t gfn); diff --git a/arch/x86/kvm/xen.c b/arch/x86/kvm/xen.c index 280cb5dc7341..f3098c0e386a 100644 --- a/arch/x86/kvm/xen.c +++ b/arch/x86/kvm/xen.c @@ -42,13 +42,13 @@ static int kvm_xen_shared_info_init(struct kvm *kvm, gfn_t gfn) int idx = srcu_read_lock(&kvm->srcu); if (gfn == GPA_INVALID) { - kvm_gfn_to_pfn_cache_destroy(kvm, gpc); + kvm_gpc_deactivate(kvm, gpc); goto out; } do { - ret = kvm_gfn_to_pfn_cache_init(kvm, gpc, NULL, KVM_HOST_USES_PFN, - gpa, PAGE_SIZE); + ret = kvm_gpc_activate(kvm, gpc, NULL, KVM_HOST_USES_PFN, gpa, + PAGE_SIZE); if (ret) goto out; @@ -554,15 +554,15 @@ int kvm_xen_vcpu_set_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data) offsetof(struct compat_vcpu_info, time)); if (data->u.gpa == GPA_INVALID) { - kvm_gfn_to_pfn_cache_destroy(vcpu->kvm, &vcpu->arch.xen.vcpu_info_cache); + kvm_gpc_deactivate(vcpu->kvm, &vcpu->arch.xen.vcpu_info_cache); r = 0; break; } - r = kvm_gfn_to_pfn_cache_init(vcpu->kvm, - &vcpu->arch.xen.vcpu_info_cache, - NULL, KVM_HOST_USES_PFN, data->u.gpa, - sizeof(struct vcpu_info)); + r = kvm_gpc_activate(vcpu->kvm, + &vcpu->arch.xen.vcpu_info_cache, NULL, + KVM_HOST_USES_PFN, data->u.gpa, + sizeof(struct vcpu_info)); if (!r) kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu); @@ -570,16 +570,16 @@ int kvm_xen_vcpu_set_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data) case KVM_XEN_VCPU_ATTR_TYPE_VCPU_TIME_INFO: if (data->u.gpa == GPA_INVALID) { - kvm_gfn_to_pfn_cache_destroy(vcpu->kvm, - &vcpu->arch.xen.vcpu_time_info_cache); + kvm_gpc_deactivate(vcpu->kvm, + &vcpu->arch.xen.vcpu_time_info_cache); r = 0; break; } - r = kvm_gfn_to_pfn_cache_init(vcpu->kvm, - &vcpu->arch.xen.vcpu_time_info_cache, - NULL, KVM_HOST_USES_PFN, data->u.gpa, - sizeof(struct pvclock_vcpu_time_info)); + r = kvm_gpc_activate(vcpu->kvm, + &vcpu->arch.xen.vcpu_time_info_cache, + NULL, KVM_HOST_USES_PFN, data->u.gpa, + sizeof(struct pvclock_vcpu_time_info)); if (!r) kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu); break; @@ -590,16 +590,15 @@ int kvm_xen_vcpu_set_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data) break; } if (data->u.gpa == GPA_INVALID) { - kvm_gfn_to_pfn_cache_destroy(vcpu->kvm, - &vcpu->arch.xen.runstate_cache); + kvm_gpc_deactivate(vcpu->kvm, + &vcpu->arch.xen.runstate_cache); r = 0; break; } - r = kvm_gfn_to_pfn_cache_init(vcpu->kvm, - &vcpu->arch.xen.runstate_cache, - NULL, KVM_HOST_USES_PFN, data->u.gpa, - sizeof(struct vcpu_runstate_info)); + r = kvm_gpc_activate(vcpu->kvm, &vcpu->arch.xen.runstate_cache, + NULL, KVM_HOST_USES_PFN, data->u.gpa, + sizeof(struct vcpu_runstate_info)); break; case KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_CURRENT: @@ -955,6 +954,14 @@ static int kvm_xen_hypercall_complete_userspace(struct kvm_vcpu *vcpu) return kvm_xen_hypercall_set_result(vcpu, run->xen.u.hcall.result); } +static inline int max_evtchn_port(struct kvm *kvm) +{ + if (IS_ENABLED(CONFIG_64BIT) && kvm->arch.xen.long_mode) + return EVTCHN_2L_NR_CHANNELS; + else + return COMPAT_EVTCHN_2L_NR_CHANNELS; +} + static bool wait_pending_event(struct kvm_vcpu *vcpu, int nr_ports, evtchn_port_t *ports) { @@ -1043,6 +1050,10 @@ static bool kvm_xen_schedop_poll(struct kvm_vcpu *vcpu, bool longmode, *r = -EFAULT; goto out; } + if (ports[i] >= max_evtchn_port(vcpu->kvm)) { + *r = -EINVAL; + goto out; + } } if (sched_poll.nr_ports == 1) @@ -1065,7 +1076,6 @@ static bool kvm_xen_schedop_poll(struct kvm_vcpu *vcpu, bool longmode, del_timer(&vcpu->arch.xen.poll_timer); vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; - kvm_clear_request(KVM_REQ_UNHALT, vcpu); } vcpu->arch.xen.poll_evtchn = 0; @@ -1217,6 +1227,7 @@ int kvm_xen_hypercall(struct kvm_vcpu *vcpu) bool longmode; u64 input, params[6], r = -ENOSYS; bool handled = false; + u8 cpl; input = (u64)kvm_register_read(vcpu, VCPU_REGS_RAX); @@ -1244,9 +1255,17 @@ int kvm_xen_hypercall(struct kvm_vcpu *vcpu) params[5] = (u64)kvm_r9_read(vcpu); } #endif + cpl = static_call(kvm_x86_get_cpl)(vcpu); trace_kvm_xen_hypercall(input, params[0], params[1], params[2], params[3], params[4], params[5]); + /* + * Only allow hypercall acceleration for CPL0. The rare hypercalls that + * are permitted in guest userspace can be handled by the VMM. + */ + if (unlikely(cpl > 0)) + goto handle_in_userspace; + switch (input) { case __HYPERVISOR_xen_version: if (params[0] == XENVER_version && vcpu->kvm->arch.xen.xen_version) { @@ -1281,10 +1300,11 @@ int kvm_xen_hypercall(struct kvm_vcpu *vcpu) if (handled) return kvm_xen_hypercall_set_result(vcpu, r); +handle_in_userspace: vcpu->run->exit_reason = KVM_EXIT_XEN; vcpu->run->xen.type = KVM_EXIT_XEN_HCALL; vcpu->run->xen.u.hcall.longmode = longmode; - vcpu->run->xen.u.hcall.cpl = static_call(kvm_x86_get_cpl)(vcpu); + vcpu->run->xen.u.hcall.cpl = cpl; vcpu->run->xen.u.hcall.input = input; vcpu->run->xen.u.hcall.params[0] = params[0]; vcpu->run->xen.u.hcall.params[1] = params[1]; @@ -1299,14 +1319,6 @@ int kvm_xen_hypercall(struct kvm_vcpu *vcpu) return 0; } -static inline int max_evtchn_port(struct kvm *kvm) -{ - if (IS_ENABLED(CONFIG_64BIT) && kvm->arch.xen.long_mode) - return EVTCHN_2L_NR_CHANNELS; - else - return COMPAT_EVTCHN_2L_NR_CHANNELS; -} - static void kvm_xen_check_poller(struct kvm_vcpu *vcpu, int port) { int poll_evtchn = vcpu->arch.xen.poll_evtchn; @@ -1668,18 +1680,18 @@ static int kvm_xen_eventfd_assign(struct kvm *kvm, case EVTCHNSTAT_ipi: /* IPI must map back to the same port# */ if (data->u.evtchn.deliver.port.port != data->u.evtchn.send_port) - goto out; /* -EINVAL */ + goto out_noeventfd; /* -EINVAL */ break; case EVTCHNSTAT_interdomain: if (data->u.evtchn.deliver.port.port) { if (data->u.evtchn.deliver.port.port >= max_evtchn_port(kvm)) - goto out; /* -EINVAL */ + goto out_noeventfd; /* -EINVAL */ } else { eventfd = eventfd_ctx_fdget(data->u.evtchn.deliver.eventfd.fd); if (IS_ERR(eventfd)) { ret = PTR_ERR(eventfd); - goto out; + goto out_noeventfd; } } break; @@ -1719,6 +1731,7 @@ static int kvm_xen_eventfd_assign(struct kvm *kvm, out: if (eventfd) eventfd_ctx_put(eventfd); +out_noeventfd: kfree(evtchnfd); return ret; } @@ -1817,7 +1830,12 @@ void kvm_xen_init_vcpu(struct kvm_vcpu *vcpu) { vcpu->arch.xen.vcpu_id = vcpu->vcpu_idx; vcpu->arch.xen.poll_evtchn = 0; + timer_setup(&vcpu->arch.xen.poll_timer, cancel_evtchn_poll, 0); + + kvm_gpc_init(&vcpu->arch.xen.runstate_cache); + kvm_gpc_init(&vcpu->arch.xen.vcpu_info_cache); + kvm_gpc_init(&vcpu->arch.xen.vcpu_time_info_cache); } void kvm_xen_destroy_vcpu(struct kvm_vcpu *vcpu) @@ -1825,18 +1843,17 @@ void kvm_xen_destroy_vcpu(struct kvm_vcpu *vcpu) if (kvm_xen_timer_enabled(vcpu)) kvm_xen_stop_timer(vcpu); - kvm_gfn_to_pfn_cache_destroy(vcpu->kvm, - &vcpu->arch.xen.runstate_cache); - kvm_gfn_to_pfn_cache_destroy(vcpu->kvm, - &vcpu->arch.xen.vcpu_info_cache); - kvm_gfn_to_pfn_cache_destroy(vcpu->kvm, - &vcpu->arch.xen.vcpu_time_info_cache); + kvm_gpc_deactivate(vcpu->kvm, &vcpu->arch.xen.runstate_cache); + kvm_gpc_deactivate(vcpu->kvm, &vcpu->arch.xen.vcpu_info_cache); + kvm_gpc_deactivate(vcpu->kvm, &vcpu->arch.xen.vcpu_time_info_cache); + del_timer_sync(&vcpu->arch.xen.poll_timer); } void kvm_xen_init_vm(struct kvm *kvm) { idr_init(&kvm->arch.xen.evtchn_ports); + kvm_gpc_init(&kvm->arch.xen.shinfo_cache); } void kvm_xen_destroy_vm(struct kvm *kvm) @@ -1844,7 +1861,7 @@ void kvm_xen_destroy_vm(struct kvm *kvm) struct evtchnfd *evtchnfd; int i; - kvm_gfn_to_pfn_cache_destroy(kvm, &kvm->arch.xen.shinfo_cache); + kvm_gpc_deactivate(kvm, &kvm->arch.xen.shinfo_cache); idr_for_each_entry(&kvm->arch.xen.evtchn_ports, evtchnfd, i) { if (!evtchnfd->deliver.port.port) diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile index f76747862bd2..7ba5f61d7273 100644 --- a/arch/x86/lib/Makefile +++ b/arch/x86/lib/Makefile @@ -65,7 +65,9 @@ ifneq ($(CONFIG_X86_CMPXCHG64),y) endif else obj-y += iomap_copy_64.o +ifneq ($(CONFIG_GENERIC_CSUM),y) lib-y += csum-partial_64.o csum-copy_64.o csum-wrappers_64.o +endif lib-y += clear_page_64.o copy_page_64.o lib-y += memmove_64.o memset_64.o lib-y += copy_user_64.o diff --git a/arch/x86/lib/clear_page_64.S b/arch/x86/lib/clear_page_64.S index fe59b8ac4fcc..ecbfb4dd3b01 100644 --- a/arch/x86/lib/clear_page_64.S +++ b/arch/x86/lib/clear_page_64.S @@ -1,5 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0-only */ #include <linux/linkage.h> +#include <asm/asm.h> #include <asm/export.h> /* @@ -50,3 +51,140 @@ SYM_FUNC_START(clear_page_erms) RET SYM_FUNC_END(clear_page_erms) EXPORT_SYMBOL_GPL(clear_page_erms) + +/* + * Default clear user-space. + * Input: + * rdi destination + * rcx count + * + * Output: + * rcx: uncleared bytes or 0 if successful. + */ +SYM_FUNC_START(clear_user_original) + /* + * Copy only the lower 32 bits of size as that is enough to handle the rest bytes, + * i.e., no need for a 'q' suffix and thus a REX prefix. + */ + mov %ecx,%eax + shr $3,%rcx + jz .Lrest_bytes + + # do the qwords first + .p2align 4 +.Lqwords: + movq $0,(%rdi) + lea 8(%rdi),%rdi + dec %rcx + jnz .Lqwords + +.Lrest_bytes: + and $7, %eax + jz .Lexit + + # now do the rest bytes +.Lbytes: + movb $0,(%rdi) + inc %rdi + dec %eax + jnz .Lbytes + +.Lexit: + /* + * %rax still needs to be cleared in the exception case because this function is called + * from inline asm and the compiler expects %rax to be zero when exiting the inline asm, + * in case it might reuse it somewhere. + */ + xor %eax,%eax + RET + +.Lqwords_exception: + # convert remaining qwords back into bytes to return to caller + shl $3, %rcx + and $7, %eax + add %rax,%rcx + jmp .Lexit + +.Lbytes_exception: + mov %eax,%ecx + jmp .Lexit + + _ASM_EXTABLE_UA(.Lqwords, .Lqwords_exception) + _ASM_EXTABLE_UA(.Lbytes, .Lbytes_exception) +SYM_FUNC_END(clear_user_original) +EXPORT_SYMBOL(clear_user_original) + +/* + * Alternative clear user-space when CPU feature X86_FEATURE_REP_GOOD is + * present. + * Input: + * rdi destination + * rcx count + * + * Output: + * rcx: uncleared bytes or 0 if successful. + */ +SYM_FUNC_START(clear_user_rep_good) + # call the original thing for less than a cacheline + cmp $64, %rcx + jb clear_user_original + +.Lprep: + # copy lower 32-bits for rest bytes + mov %ecx, %edx + shr $3, %rcx + jz .Lrep_good_rest_bytes + +.Lrep_good_qwords: + rep stosq + +.Lrep_good_rest_bytes: + and $7, %edx + jz .Lrep_good_exit + +.Lrep_good_bytes: + mov %edx, %ecx + rep stosb + +.Lrep_good_exit: + # see .Lexit comment above + xor %eax, %eax + RET + +.Lrep_good_qwords_exception: + # convert remaining qwords back into bytes to return to caller + shl $3, %rcx + and $7, %edx + add %rdx, %rcx + jmp .Lrep_good_exit + + _ASM_EXTABLE_UA(.Lrep_good_qwords, .Lrep_good_qwords_exception) + _ASM_EXTABLE_UA(.Lrep_good_bytes, .Lrep_good_exit) +SYM_FUNC_END(clear_user_rep_good) +EXPORT_SYMBOL(clear_user_rep_good) + +/* + * Alternative clear user-space when CPU feature X86_FEATURE_ERMS is present. + * Input: + * rdi destination + * rcx count + * + * Output: + * rcx: uncleared bytes or 0 if successful. + * + */ +SYM_FUNC_START(clear_user_erms) + # call the original thing for less than a cacheline + cmp $64, %rcx + jb clear_user_original + +.Lerms_bytes: + rep stosb + +.Lerms_exit: + xorl %eax,%eax + RET + + _ASM_EXTABLE_UA(.Lerms_bytes, .Lerms_exit) +SYM_FUNC_END(clear_user_erms) +EXPORT_SYMBOL(clear_user_erms) diff --git a/arch/x86/lib/iomem.c b/arch/x86/lib/iomem.c index 3e2f33fc33de..e0411a3774d4 100644 --- a/arch/x86/lib/iomem.c +++ b/arch/x86/lib/iomem.c @@ -1,6 +1,7 @@ #include <linux/string.h> #include <linux/module.h> #include <linux/io.h> +#include <linux/kmsan-checks.h> #define movs(type,to,from) \ asm volatile("movs" type:"=&D" (to), "=&S" (from):"0" (to), "1" (from):"memory") @@ -37,6 +38,8 @@ static void string_memcpy_fromio(void *to, const volatile void __iomem *from, si n-=2; } rep_movs(to, (const void *)from, n); + /* KMSAN must treat values read from devices as initialized. */ + kmsan_unpoison_memory(to, n); } static void string_memcpy_toio(volatile void __iomem *to, const void *from, size_t n) @@ -44,6 +47,8 @@ static void string_memcpy_toio(volatile void __iomem *to, const void *from, size if (unlikely(!n)) return; + /* Make sure uninitialized memory isn't copied to devices. */ + kmsan_check_memory(from, n); /* Align any unaligned destination IO */ if (unlikely(1 & (unsigned long)to)) { movs("b", to, from); diff --git a/arch/x86/lib/memcpy_64.S b/arch/x86/lib/memcpy_64.S index d0d7b9bc6cad..dd8cd8831251 100644 --- a/arch/x86/lib/memcpy_64.S +++ b/arch/x86/lib/memcpy_64.S @@ -2,6 +2,7 @@ /* Copyright 2002 Andi Kleen */ #include <linux/linkage.h> +#include <linux/cfi_types.h> #include <asm/errno.h> #include <asm/cpufeatures.h> #include <asm/alternative.h> @@ -27,7 +28,7 @@ * Output: * rax original destination */ -SYM_FUNC_START(__memcpy) +SYM_TYPED_FUNC_START(__memcpy) ALTERNATIVE_2 "jmp memcpy_orig", "", X86_FEATURE_REP_GOOD, \ "jmp memcpy_erms", X86_FEATURE_ERMS diff --git a/arch/x86/lib/usercopy.c b/arch/x86/lib/usercopy.c index ad0139d25401..24b48af27417 100644 --- a/arch/x86/lib/usercopy.c +++ b/arch/x86/lib/usercopy.c @@ -6,6 +6,7 @@ #include <linux/uaccess.h> #include <linux/export.h> +#include <linux/instrumented.h> #include <asm/tlbflush.h> @@ -44,7 +45,9 @@ copy_from_user_nmi(void *to, const void __user *from, unsigned long n) * called from other contexts. */ pagefault_disable(); - ret = __copy_from_user_inatomic(to, from, n); + instrument_copy_from_user_before(to, from, n); + ret = raw_copy_from_user(to, from, n); + instrument_copy_from_user_after(to, from, n, ret); pagefault_enable(); return ret; diff --git a/arch/x86/lib/usercopy_64.c b/arch/x86/lib/usercopy_64.c index 0ae6cf804197..6c1f8ac5e721 100644 --- a/arch/x86/lib/usercopy_64.c +++ b/arch/x86/lib/usercopy_64.c @@ -14,46 +14,6 @@ * Zero Userspace */ -unsigned long __clear_user(void __user *addr, unsigned long size) -{ - long __d0; - might_fault(); - /* no memory constraint because it doesn't change any memory gcc knows - about */ - stac(); - asm volatile( - " testq %[size8],%[size8]\n" - " jz 4f\n" - " .align 16\n" - "0: movq $0,(%[dst])\n" - " addq $8,%[dst]\n" - " decl %%ecx ; jnz 0b\n" - "4: movq %[size1],%%rcx\n" - " testl %%ecx,%%ecx\n" - " jz 2f\n" - "1: movb $0,(%[dst])\n" - " incq %[dst]\n" - " decl %%ecx ; jnz 1b\n" - "2:\n" - - _ASM_EXTABLE_TYPE_REG(0b, 2b, EX_TYPE_UCOPY_LEN8, %[size1]) - _ASM_EXTABLE_UA(1b, 2b) - - : [size8] "=&c"(size), [dst] "=&D" (__d0) - : [size1] "r"(size & 7), "[size8]" (size / 8), "[dst]"(addr)); - clac(); - return size; -} -EXPORT_SYMBOL(__clear_user); - -unsigned long clear_user(void __user *to, unsigned long n) -{ - if (access_ok(to, n)) - return __clear_user(to, n); - return n; -} -EXPORT_SYMBOL(clear_user); - #ifdef CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE /** * clean_cache_range - write back a cache range with CLWB diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile index f8220fd2c169..c80febc44cd2 100644 --- a/arch/x86/mm/Makefile +++ b/arch/x86/mm/Makefile @@ -4,19 +4,24 @@ KCOV_INSTRUMENT_tlb.o := n KCOV_INSTRUMENT_mem_encrypt.o := n KCOV_INSTRUMENT_mem_encrypt_amd.o := n KCOV_INSTRUMENT_mem_encrypt_identity.o := n +KCOV_INSTRUMENT_pgprot.o := n KASAN_SANITIZE_mem_encrypt.o := n KASAN_SANITIZE_mem_encrypt_amd.o := n KASAN_SANITIZE_mem_encrypt_identity.o := n +KASAN_SANITIZE_pgprot.o := n # Disable KCSAN entirely, because otherwise we get warnings that some functions # reference __initdata sections. KCSAN_SANITIZE := n +# Avoid recursion by not calling KMSAN hooks for CEA code. +KMSAN_SANITIZE_cpu_entry_area.o := n ifdef CONFIG_FUNCTION_TRACER CFLAGS_REMOVE_mem_encrypt.o = -pg CFLAGS_REMOVE_mem_encrypt_amd.o = -pg CFLAGS_REMOVE_mem_encrypt_identity.o = -pg +CFLAGS_REMOVE_pgprot.o = -pg endif obj-y := init.o init_$(BITS).o fault.o ioremap.o extable.o mmap.o \ @@ -41,6 +46,9 @@ obj-$(CONFIG_HIGHMEM) += highmem_32.o KASAN_SANITIZE_kasan_init_$(BITS).o := n obj-$(CONFIG_KASAN) += kasan_init_$(BITS).o +KMSAN_SANITIZE_kmsan_shadow.o := n +obj-$(CONFIG_KMSAN) += kmsan_shadow.o + obj-$(CONFIG_MMIOTRACE) += mmiotrace.o mmiotrace-y := kmmio.o pf_in.o mmio-mod.o obj-$(CONFIG_MMIOTRACE_TEST) += testmmiotrace.o diff --git a/arch/x86/mm/extable.c b/arch/x86/mm/extable.c index 331310c29349..60814e110a54 100644 --- a/arch/x86/mm/extable.c +++ b/arch/x86/mm/extable.c @@ -41,6 +41,59 @@ static bool ex_handler_default(const struct exception_table_entry *e, return true; } +/* + * This is the *very* rare case where we do a "load_unaligned_zeropad()" + * and it's a page crosser into a non-existent page. + * + * This happens when we optimistically load a pathname a word-at-a-time + * and the name is less than the full word and the next page is not + * mapped. Typically that only happens for CONFIG_DEBUG_PAGEALLOC. + * + * NOTE! The faulting address is always a 'mov mem,reg' type instruction + * of size 'long', and the exception fixup must always point to right + * after the instruction. + */ +static bool ex_handler_zeropad(const struct exception_table_entry *e, + struct pt_regs *regs, + unsigned long fault_addr) +{ + struct insn insn; + const unsigned long mask = sizeof(long) - 1; + unsigned long offset, addr, next_ip, len; + unsigned long *reg; + + next_ip = ex_fixup_addr(e); + len = next_ip - regs->ip; + if (len > MAX_INSN_SIZE) + return false; + + if (insn_decode(&insn, (void *) regs->ip, len, INSN_MODE_KERN)) + return false; + if (insn.length != len) + return false; + + if (insn.opcode.bytes[0] != 0x8b) + return false; + if (insn.opnd_bytes != sizeof(long)) + return false; + + addr = (unsigned long) insn_get_addr_ref(&insn, regs); + if (addr == ~0ul) + return false; + + offset = addr & mask; + addr = addr & ~mask; + if (fault_addr != addr + sizeof(long)) + return false; + + reg = insn_get_modrm_reg_ptr(&insn, regs); + if (!reg) + return false; + + *reg = *(unsigned long *)addr >> (offset * 8); + return ex_handler_default(e, regs); +} + static bool ex_handler_fault(const struct exception_table_entry *fixup, struct pt_regs *regs, int trapnr) { @@ -217,6 +270,8 @@ int fixup_exception(struct pt_regs *regs, int trapnr, unsigned long error_code, return ex_handler_sgx(e, regs, trapnr); case EX_TYPE_UCOPY_LEN: return ex_handler_ucopy_len(e, regs, trapnr, reg, imm); + case EX_TYPE_ZEROPAD: + return ex_handler_zeropad(e, regs, fault_addr); } BUG(); } diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index fa71a5d12e87..7b0d4ab894c8 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -260,7 +260,7 @@ static noinline int vmalloc_fault(unsigned long address) } NOKPROBE_SYMBOL(vmalloc_fault); -void arch_sync_kernel_mappings(unsigned long start, unsigned long end) +static void __arch_sync_kernel_mappings(unsigned long start, unsigned long end) { unsigned long addr; @@ -284,6 +284,27 @@ void arch_sync_kernel_mappings(unsigned long start, unsigned long end) } } +void arch_sync_kernel_mappings(unsigned long start, unsigned long end) +{ + __arch_sync_kernel_mappings(start, end); +#ifdef CONFIG_KMSAN + /* + * KMSAN maintains two additional metadata page mappings for the + * [VMALLOC_START, VMALLOC_END) range. These mappings start at + * KMSAN_VMALLOC_SHADOW_START and KMSAN_VMALLOC_ORIGIN_START and + * have to be synced together with the vmalloc memory mapping. + */ + if (start >= VMALLOC_START && end < VMALLOC_END) { + __arch_sync_kernel_mappings( + start - VMALLOC_START + KMSAN_VMALLOC_SHADOW_START, + end - VMALLOC_START + KMSAN_VMALLOC_SHADOW_START); + __arch_sync_kernel_mappings( + start - VMALLOC_START + KMSAN_VMALLOC_ORIGIN_START, + end - VMALLOC_START + KMSAN_VMALLOC_ORIGIN_START); + } +#endif +} + static bool low_pfn(unsigned long pfn) { return pfn < max_low_pfn; @@ -769,6 +790,8 @@ show_signal_msg(struct pt_regs *regs, unsigned long error_code, unsigned long address, struct task_struct *tsk) { const char *loglvl = task_pid_nr(tsk) > 1 ? KERN_INFO : KERN_EMERG; + /* This is a racy snapshot, but it's better than nothing. */ + int cpu = raw_smp_processor_id(); if (!unhandled_signal(tsk, SIGSEGV)) return; @@ -782,6 +805,14 @@ show_signal_msg(struct pt_regs *regs, unsigned long error_code, print_vma_addr(KERN_CONT " in ", regs->ip); + /* + * Dump the likely CPU where the fatal segfault happened. + * This can help identify faulty hardware. + */ + printk(KERN_CONT " likely on CPU %d (core %d, socket %d)", cpu, + topology_core_id(cpu), topology_physical_package_id(cpu)); + + printk(KERN_CONT "\n"); show_opcodes(regs, loglvl); diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c index 6b3033845c6d..5804bbae4f01 100644 --- a/arch/x86/mm/hugetlbpage.c +++ b/arch/x86/mm/hugetlbpage.c @@ -37,8 +37,12 @@ int pmd_huge(pmd_t pmd) */ int pud_huge(pud_t pud) { +#if CONFIG_PGTABLE_LEVELS > 2 return !pud_none(pud) && (pud_val(pud) & (_PAGE_PRESENT|_PAGE_PSE)) != _PAGE_PRESENT; +#else + return 0; +#endif } #ifdef CONFIG_HUGETLB_PAGE diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index 82a042c03824..9121bc1b9453 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -1054,7 +1054,7 @@ void update_cache_mode_entry(unsigned entry, enum page_cache_mode cache) } #ifdef CONFIG_SWAP -unsigned long max_swapfile_size(void) +unsigned long arch_max_swapfile_size(void) { unsigned long pages; diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 39c5246964a9..3f040c6e5d13 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -90,6 +90,12 @@ DEFINE_ENTRY(pud, pud, init) DEFINE_ENTRY(pmd, pmd, init) DEFINE_ENTRY(pte, pte, init) +static inline pgprot_t prot_sethuge(pgprot_t prot) +{ + WARN_ON_ONCE(pgprot_val(prot) & _PAGE_PAT); + + return __pgprot(pgprot_val(prot) | _PAGE_PSE); +} /* * NOTE: pagetable_init alloc all the fixmap pagetables contiguous on the @@ -557,9 +563,8 @@ phys_pmd_init(pmd_t *pmd_page, unsigned long paddr, unsigned long paddr_end, if (page_size_mask & (1<<PG_LEVEL_2M)) { pages++; spin_lock(&init_mm.page_table_lock); - set_pte_init((pte_t *)pmd, - pfn_pte((paddr & PMD_MASK) >> PAGE_SHIFT, - __pgprot(pgprot_val(prot) | _PAGE_PSE)), + set_pmd_init(pmd, + pfn_pmd(paddr >> PAGE_SHIFT, prot_sethuge(prot)), init); spin_unlock(&init_mm.page_table_lock); paddr_last = paddr_next; @@ -644,12 +649,8 @@ 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, - prot), + set_pud_init(pud, + pfn_pud(paddr >> PAGE_SHIFT, prot_sethuge(prot)), init); spin_unlock(&init_mm.page_table_lock); paddr_last = paddr_next; @@ -1287,7 +1288,7 @@ static void __init preallocate_vmalloc_pages(void) unsigned long addr; const char *lvl; - for (addr = VMALLOC_START; addr <= VMALLOC_END; addr = ALIGN(addr + 1, PGDIR_SIZE)) { + for (addr = VMALLOC_START; addr <= VMEMORY_END; addr = ALIGN(addr + 1, PGDIR_SIZE)) { pgd_t *pgd = pgd_offset_k(addr); p4d_t *p4d; pud_t *pud; diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index 1ad0228f8ceb..6453fbaedb08 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -17,6 +17,7 @@ #include <linux/cc_platform.h> #include <linux/efi.h> #include <linux/pgtable.h> +#include <linux/kmsan.h> #include <asm/set_memory.h> #include <asm/e820/api.h> @@ -216,9 +217,15 @@ __ioremap_caller(resource_size_t phys_addr, unsigned long size, * Mappings have to be page-aligned */ offset = phys_addr & ~PAGE_MASK; - phys_addr &= PHYSICAL_PAGE_MASK; + phys_addr &= PAGE_MASK; size = PAGE_ALIGN(last_addr+1) - phys_addr; + /* + * Mask out any bits not part of the actual physical + * address, like memory encryption bits. + */ + phys_addr &= PHYSICAL_PAGE_MASK; + retval = memtype_reserve(phys_addr, (u64)phys_addr + size, pcm, &new_pcm); if (retval) { @@ -479,6 +486,8 @@ void iounmap(volatile void __iomem *addr) return; } + kmsan_iounmap_page_range((unsigned long)addr, + (unsigned long)addr + get_vm_area_size(p)); memtype_free(p->phys_addr, p->phys_addr + get_vm_area_size(p)); /* Finally remove it */ diff --git a/arch/x86/mm/kmsan_shadow.c b/arch/x86/mm/kmsan_shadow.c new file mode 100644 index 000000000000..bee2ec4a3bfa --- /dev/null +++ b/arch/x86/mm/kmsan_shadow.c @@ -0,0 +1,20 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * x86-specific bits of KMSAN shadow implementation. + * + * Copyright (C) 2022 Google LLC + * Author: Alexander Potapenko <[email protected]> + */ + +#include <asm/cpu_entry_area.h> +#include <linux/percpu-defs.h> + +/* + * Addresses within the CPU entry area (including e.g. exception stacks) do not + * have struct page entries corresponding to them, so they need separate + * handling. + * arch_kmsan_get_meta_or_null() (declared in the header) maps the addresses in + * CPU entry area to addresses in cpu_entry_area_shadow/cpu_entry_area_origin. + */ +DEFINE_PER_CPU(char[CPU_ENTRY_AREA_SIZE], cpu_entry_area_shadow); +DEFINE_PER_CPU(char[CPU_ENTRY_AREA_SIZE], cpu_entry_area_origin); diff --git a/arch/x86/mm/pat/cpa-test.c b/arch/x86/mm/pat/cpa-test.c index 0612a73638a8..423b21e80929 100644 --- a/arch/x86/mm/pat/cpa-test.c +++ b/arch/x86/mm/pat/cpa-test.c @@ -136,10 +136,10 @@ static int pageattr_test(void) failed += print_split(&sa); for (i = 0; i < NTEST; i++) { - unsigned long pfn = prandom_u32() % max_pfn_mapped; + unsigned long pfn = prandom_u32_max(max_pfn_mapped); addr[i] = (unsigned long)__va(pfn << PAGE_SHIFT); - len[i] = prandom_u32() % NPAGES; + len[i] = prandom_u32_max(NPAGES); len[i] = min_t(unsigned long, len[i], max_pfn_mapped - pfn - 1); if (len[i] == 0) diff --git a/arch/x86/mm/pat/memtype.c b/arch/x86/mm/pat/memtype.c index d5ef64ddd35e..66a209f7eb86 100644 --- a/arch/x86/mm/pat/memtype.c +++ b/arch/x86/mm/pat/memtype.c @@ -62,6 +62,7 @@ static bool __read_mostly pat_bp_initialized; static bool __read_mostly pat_disabled = !IS_ENABLED(CONFIG_X86_PAT); +static bool __initdata pat_force_disabled = !IS_ENABLED(CONFIG_X86_PAT); static bool __read_mostly pat_bp_enabled; static bool __read_mostly pat_cm_initialized; @@ -86,6 +87,7 @@ void pat_disable(const char *msg_reason) static int __init nopat(char *str) { pat_disable("PAT support disabled via boot option."); + pat_force_disabled = true; return 0; } early_param("nopat", nopat); @@ -272,7 +274,7 @@ static void pat_ap_init(u64 pat) wrmsrl(MSR_IA32_CR_PAT, pat); } -void init_cache_modes(void) +void __init init_cache_modes(void) { u64 pat = 0; @@ -313,6 +315,12 @@ void init_cache_modes(void) */ pat = PAT(0, WB) | PAT(1, WT) | PAT(2, UC_MINUS) | PAT(3, UC) | PAT(4, WB) | PAT(5, WT) | PAT(6, UC_MINUS) | PAT(7, UC); + } else if (!pat_force_disabled && cpu_feature_enabled(X86_FEATURE_HYPERVISOR)) { + /* + * Clearly PAT is enabled underneath. Allow pat_enabled() to + * reflect this. + */ + pat_bp_enabled = true; } __init_cache_modes(pat); diff --git a/arch/x86/mm/pat/set_memory.c b/arch/x86/mm/pat/set_memory.c index 1abd5438f126..2e5a045731de 100644 --- a/arch/x86/mm/pat/set_memory.c +++ b/arch/x86/mm/pat/set_memory.c @@ -580,6 +580,50 @@ static inline pgprot_t static_protections(pgprot_t prot, unsigned long start, } /* + * Validate strict W^X semantics. + */ +static inline pgprot_t verify_rwx(pgprot_t old, pgprot_t new, unsigned long start, + unsigned long pfn, unsigned long npg) +{ + unsigned long end; + + /* Kernel text is rw at boot up */ + if (system_state == SYSTEM_BOOTING) + return new; + + /* + * 32-bit has some unfixable W+X issues, like EFI code + * and writeable data being in the same page. Disable + * detection and enforcement there. + */ + if (IS_ENABLED(CONFIG_X86_32)) + return new; + + /* Only verify when NX is supported: */ + if (!(__supported_pte_mask & _PAGE_NX)) + return new; + + if (!((pgprot_val(old) ^ pgprot_val(new)) & (_PAGE_RW | _PAGE_NX))) + return new; + + if ((pgprot_val(new) & (_PAGE_RW | _PAGE_NX)) != _PAGE_RW) + return new; + + end = start + npg * PAGE_SIZE - 1; + WARN_ONCE(1, "CPA detected W^X violation: %016llx -> %016llx range: 0x%016lx - 0x%016lx PFN %lx\n", + (unsigned long long)pgprot_val(old), + (unsigned long long)pgprot_val(new), + start, end, pfn); + + /* + * For now, allow all permission change attempts by returning the + * attempted permissions. This can 'return old' to actively + * refuse the permission change at a later time. + */ + return new; +} + +/* * Lookup the page table entry for a virtual address in a specific pgd. * Return a pointer to the entry and the level of the mapping. */ @@ -885,6 +929,8 @@ static int __should_split_large_page(pte_t *kpte, unsigned long address, new_prot = static_protections(req_prot, lpaddr, old_pfn, numpages, psize, CPA_DETECT); + new_prot = verify_rwx(old_prot, new_prot, lpaddr, old_pfn, numpages); + /* * If there is a conflict, split the large page. * @@ -1525,6 +1571,7 @@ repeat: if (level == PG_LEVEL_4K) { pte_t new_pte; + pgprot_t old_prot = pte_pgprot(old_pte); pgprot_t new_prot = pte_pgprot(old_pte); unsigned long pfn = pte_pfn(old_pte); @@ -1536,6 +1583,8 @@ repeat: new_prot = static_protections(new_prot, address, pfn, 1, 0, CPA_PROTECT); + new_prot = verify_rwx(old_prot, new_prot, address, pfn, 1); + new_prot = pgprot_clear_protnone_bits(new_prot); /* @@ -1944,7 +1993,7 @@ int set_mce_nospec(unsigned long pfn) return rc; } -static int set_memory_present(unsigned long *addr, int numpages) +static int set_memory_p(unsigned long *addr, int numpages) { return change_page_attr_set(addr, numpages, __pgprot(_PAGE_PRESENT), 0); } @@ -1954,7 +2003,7 @@ int clear_mce_nospec(unsigned long pfn) { unsigned long addr = (unsigned long) pfn_to_kaddr(pfn); - return set_memory_present(&addr, 1); + return set_memory_p(&addr, 1); } EXPORT_SYMBOL_GPL(clear_mce_nospec); #endif /* CONFIG_X86_64 */ diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index a932d7712d85..8525f2876fb4 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -550,7 +550,7 @@ int ptep_test_and_clear_young(struct vm_area_struct *vma, return ret; } -#ifdef CONFIG_TRANSPARENT_HUGEPAGE +#if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG) int pmdp_test_and_clear_young(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmdp) { @@ -562,6 +562,9 @@ int pmdp_test_and_clear_young(struct vm_area_struct *vma, return ret; } +#endif + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE int pudp_test_and_clear_young(struct vm_area_struct *vma, unsigned long addr, pud_t *pudp) { diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index c1f6c1c51d99..99620428ad78 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -419,7 +419,9 @@ static void emit_indirect_jump(u8 **pprog, int reg, u8 *ip) OPTIMIZER_HIDE_VAR(reg); emit_jump(&prog, &__x86_indirect_thunk_array[reg], ip); } else { - EMIT2(0xFF, 0xE0 + reg); + EMIT2(0xFF, 0xE0 + reg); /* jmp *%\reg */ + if (IS_ENABLED(CONFIG_RETPOLINE) || IS_ENABLED(CONFIG_SLS)) + EMIT1(0xCC); /* int3 */ } *pprog = prog; @@ -662,7 +664,7 @@ static void emit_mov_imm64(u8 **pprog, u32 dst_reg, */ emit_mov_imm32(&prog, false, dst_reg, imm32_lo); } else { - /* movabsq %rax, imm64 */ + /* movabsq rax, imm64 */ EMIT2(add_1mod(0x48, dst_reg), add_1reg(0xB8, dst_reg)); EMIT(imm32_lo, 4); EMIT(imm32_hi, 4); @@ -1751,34 +1753,60 @@ emit_jmp: static void save_regs(const struct btf_func_model *m, u8 **prog, int nr_args, int stack_size) { - int i; + int i, j, arg_size, nr_regs; /* Store function arguments to stack. * For a function that accepts two pointers the sequence will be: * mov QWORD PTR [rbp-0x10],rdi * mov QWORD PTR [rbp-0x8],rsi */ - for (i = 0; i < min(nr_args, 6); i++) - emit_stx(prog, bytes_to_bpf_size(m->arg_size[i]), - BPF_REG_FP, - i == 5 ? X86_REG_R9 : BPF_REG_1 + i, - -(stack_size - i * 8)); + for (i = 0, j = 0; i < min(nr_args, 6); i++) { + if (m->arg_flags[i] & BTF_FMODEL_STRUCT_ARG) { + nr_regs = (m->arg_size[i] + 7) / 8; + arg_size = 8; + } else { + nr_regs = 1; + arg_size = m->arg_size[i]; + } + + while (nr_regs) { + emit_stx(prog, bytes_to_bpf_size(arg_size), + BPF_REG_FP, + j == 5 ? X86_REG_R9 : BPF_REG_1 + j, + -(stack_size - j * 8)); + nr_regs--; + j++; + } + } } static void restore_regs(const struct btf_func_model *m, u8 **prog, int nr_args, int stack_size) { - int i; + int i, j, arg_size, nr_regs; /* Restore function arguments from stack. * For a function that accepts two pointers the sequence will be: * EMIT4(0x48, 0x8B, 0x7D, 0xF0); mov rdi,QWORD PTR [rbp-0x10] * EMIT4(0x48, 0x8B, 0x75, 0xF8); mov rsi,QWORD PTR [rbp-0x8] */ - for (i = 0; i < min(nr_args, 6); i++) - emit_ldx(prog, bytes_to_bpf_size(m->arg_size[i]), - i == 5 ? X86_REG_R9 : BPF_REG_1 + i, - BPF_REG_FP, - -(stack_size - i * 8)); + for (i = 0, j = 0; i < min(nr_args, 6); i++) { + if (m->arg_flags[i] & BTF_FMODEL_STRUCT_ARG) { + nr_regs = (m->arg_size[i] + 7) / 8; + arg_size = 8; + } else { + nr_regs = 1; + arg_size = m->arg_size[i]; + } + + while (nr_regs) { + emit_ldx(prog, bytes_to_bpf_size(arg_size), + j == 5 ? X86_REG_R9 : BPF_REG_1 + j, + BPF_REG_FP, + -(stack_size - j * 8)); + nr_regs--; + j++; + } + } } static int invoke_bpf_prog(const struct btf_func_model *m, u8 **pprog, @@ -1810,6 +1838,9 @@ static int invoke_bpf_prog(const struct btf_func_model *m, u8 **pprog, if (p->aux->sleepable) { enter = __bpf_prog_enter_sleepable; exit = __bpf_prog_exit_sleepable; + } else if (p->type == BPF_PROG_TYPE_STRUCT_OPS) { + enter = __bpf_prog_enter_struct_ops; + exit = __bpf_prog_exit_struct_ops; } else if (p->expected_attach_type == BPF_LSM_CGROUP) { enter = __bpf_prog_enter_lsm_cgroup; exit = __bpf_prog_exit_lsm_cgroup; @@ -2013,13 +2044,14 @@ static int invoke_bpf_mod_ret(const struct btf_func_model *m, u8 **pprog, int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *image_end, const struct btf_func_model *m, u32 flags, struct bpf_tramp_links *tlinks, - void *orig_call) + void *func_addr) { - int ret, i, nr_args = m->nr_args; + int ret, i, nr_args = m->nr_args, extra_nregs = 0; int regs_off, ip_off, args_off, stack_size = nr_args * 8, run_ctx_off; struct bpf_tramp_links *fentry = &tlinks[BPF_TRAMP_FENTRY]; struct bpf_tramp_links *fexit = &tlinks[BPF_TRAMP_FEXIT]; struct bpf_tramp_links *fmod_ret = &tlinks[BPF_TRAMP_MODIFY_RETURN]; + void *orig_call = func_addr; u8 **branches = NULL; u8 *prog; bool save_ret; @@ -2028,6 +2060,14 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i if (nr_args > 6) return -ENOTSUPP; + for (i = 0; i < MAX_BPF_FUNC_ARGS; i++) { + if (m->arg_flags[i] & BTF_FMODEL_STRUCT_ARG) + extra_nregs += (m->arg_size[i] + 7) / 8 - 1; + } + if (nr_args + extra_nregs > 6) + return -ENOTSUPP; + stack_size += extra_nregs * 8; + /* Generated trampoline stack layout: * * RBP + 8 [ return address ] @@ -2040,7 +2080,7 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i * [ ... ] * RBP - regs_off [ reg_arg1 ] program's ctx pointer * - * RBP - args_off [ args count ] always + * RBP - args_off [ arg regs count ] always * * RBP - ip_off [ traced function ] BPF_TRAMP_F_IP_ARG flag * @@ -2083,21 +2123,19 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i EMIT4(0x48, 0x83, 0xEC, stack_size); /* sub rsp, stack_size */ EMIT1(0x53); /* push rbx */ - /* Store number of arguments of the traced function: - * mov rax, nr_args + /* Store number of argument registers of the traced function: + * mov rax, nr_args + extra_nregs * mov QWORD PTR [rbp - args_off], rax */ - emit_mov_imm64(&prog, BPF_REG_0, 0, (u32) nr_args); + emit_mov_imm64(&prog, BPF_REG_0, 0, (u32) nr_args + extra_nregs); emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_0, -args_off); if (flags & BPF_TRAMP_F_IP_ARG) { /* Store IP address of the traced function: - * mov rax, QWORD PTR [rbp + 8] - * sub rax, X86_PATCH_SIZE + * movabsq rax, func_addr * mov QWORD PTR [rbp - ip_off], rax */ - emit_ldx(&prog, BPF_DW, BPF_REG_0, BPF_REG_FP, 8); - EMIT4(0x48, 0x83, 0xe8, X86_PATCH_SIZE); + emit_mov_imm64(&prog, BPF_REG_0, (long) func_addr >> 32, (u32) (long) func_addr); emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_0, -ip_off); } @@ -2209,7 +2247,7 @@ cleanup: return ret; } -static int emit_bpf_dispatcher(u8 **pprog, int a, int b, s64 *progs) +static int emit_bpf_dispatcher(u8 **pprog, int a, int b, s64 *progs, u8 *image, u8 *buf) { u8 *jg_reloc, *prog = *pprog; int pivot, err, jg_bytes = 1; @@ -2225,12 +2263,12 @@ static int emit_bpf_dispatcher(u8 **pprog, int a, int b, s64 *progs) EMIT2_off32(0x81, add_1reg(0xF8, BPF_REG_3), progs[a]); err = emit_cond_near_jump(&prog, /* je func */ - (void *)progs[a], prog, + (void *)progs[a], image + (prog - buf), X86_JE); if (err) return err; - emit_indirect_jump(&prog, 2 /* rdx */, prog); + emit_indirect_jump(&prog, 2 /* rdx */, image + (prog - buf)); *pprog = prog; return 0; @@ -2255,7 +2293,7 @@ static int emit_bpf_dispatcher(u8 **pprog, int a, int b, s64 *progs) jg_reloc = prog; err = emit_bpf_dispatcher(&prog, a, a + pivot, /* emit lower_part */ - progs); + progs, image, buf); if (err) return err; @@ -2269,7 +2307,7 @@ static int emit_bpf_dispatcher(u8 **pprog, int a, int b, s64 *progs) emit_code(jg_reloc - jg_bytes, jg_offset, jg_bytes); err = emit_bpf_dispatcher(&prog, a + pivot + 1, /* emit upper_part */ - b, progs); + b, progs, image, buf); if (err) return err; @@ -2289,12 +2327,12 @@ static int cmp_ips(const void *a, const void *b) return 0; } -int arch_prepare_bpf_dispatcher(void *image, s64 *funcs, int num_funcs) +int arch_prepare_bpf_dispatcher(void *image, void *buf, s64 *funcs, int num_funcs) { - u8 *prog = image; + u8 *prog = buf; sort(funcs, num_funcs, sizeof(funcs[0]), cmp_ips, NULL); - return emit_bpf_dispatcher(&prog, 0, num_funcs - 1, funcs); + return emit_bpf_dispatcher(&prog, 0, num_funcs - 1, funcs, image, buf); } struct x64_jit_data { diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c index 6e598bd78eef..ebc98a68c400 100644 --- a/arch/x86/platform/efi/efi.c +++ b/arch/x86/platform/efi/efi.c @@ -169,7 +169,7 @@ static void __init do_add_efi_memmap(void) } /* - * Given add_efi_memmap defaults to 0 and there there is no alternative + * Given add_efi_memmap defaults to 0 and there is no alternative * e820 mechanism for soft-reserved memory, import the full EFI memory * map if soft reservations are present and enabled. Otherwise, the * mechanism to disable the kernel's consideration of EFI_MEMORY_SP is diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c index 1f3675453a57..b36596bf0fc3 100644 --- a/arch/x86/platform/efi/efi_64.c +++ b/arch/x86/platform/efi/efi_64.c @@ -176,7 +176,8 @@ 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, rodata; + extern const u8 __efi64_thunk_ret_tramp[]; + unsigned long pfn, text, pf, rodata, tramp; struct page *page; unsigned npages; pgd_t *pgd = efi_mm.pgd; @@ -238,11 +239,9 @@ int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages) npages = (_etext - _text) >> PAGE_SHIFT; text = __pa(_text); - pfn = text >> PAGE_SHIFT; - pf = _PAGE_ENC; - if (kernel_map_pages_in_pgd(pgd, pfn, text, npages, pf)) { - pr_err("Failed to map kernel text 1:1\n"); + if (kernel_unmap_pages_in_pgd(pgd, text, npages)) { + pr_err("Failed to unmap kernel text 1:1 mapping\n"); return 1; } @@ -256,6 +255,15 @@ int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages) return 1; } + tramp = __pa(__efi64_thunk_ret_tramp); + pfn = tramp >> PAGE_SHIFT; + + pf = _PAGE_ENC; + if (kernel_map_pages_in_pgd(pgd, pfn, tramp, 1, pf)) { + pr_err("Failed to map mixed mode return trampoline\n"); + return 1; + } + return 0; } diff --git a/arch/x86/platform/efi/efi_thunk_64.S b/arch/x86/platform/efi/efi_thunk_64.S index 4e5257a4811b..c4b1144f99f6 100644 --- a/arch/x86/platform/efi/efi_thunk_64.S +++ b/arch/x86/platform/efi/efi_thunk_64.S @@ -23,7 +23,6 @@ #include <linux/objtool.h> #include <asm/page_types.h> #include <asm/segment.h> -#include <asm/nospec-branch.h> .text .code64 @@ -73,10 +72,18 @@ STACK_FRAME_NON_STANDARD __efi64_thunk pushq %rdi /* EFI runtime service address */ lretq + // This return instruction is not needed for correctness, as it will + // never be reached. It only exists to make objtool happy, which will + // otherwise complain about unreachable instructions in the callers. + RET +SYM_FUNC_END(__efi64_thunk) + + .section ".rodata", "a", @progbits + .balign 16 +SYM_DATA_START(__efi64_thunk_ret_tramp) 1: movq 0x20(%rsp), %rsp pop %rbx pop %rbp - ANNOTATE_UNRET_SAFE ret int3 @@ -84,7 +91,7 @@ STACK_FRAME_NON_STANDARD __efi64_thunk 2: pushl $__KERNEL_CS pushl %ebp lret -SYM_FUNC_END(__efi64_thunk) +SYM_DATA_END(__efi64_thunk_ret_tramp) .bss .balign 8 diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c index bb176c72891c..93ae33248f42 100644 --- a/arch/x86/power/cpu.c +++ b/arch/x86/power/cpu.c @@ -513,15 +513,23 @@ static int pm_cpu_check(const struct x86_cpu_id *c) static void pm_save_spec_msr(void) { - u32 spec_msr_id[] = { - MSR_IA32_SPEC_CTRL, - MSR_IA32_TSX_CTRL, - MSR_TSX_FORCE_ABORT, - MSR_IA32_MCU_OPT_CTRL, - MSR_AMD64_LS_CFG, + struct msr_enumeration { + u32 msr_no; + u32 feature; + } msr_enum[] = { + { MSR_IA32_SPEC_CTRL, X86_FEATURE_MSR_SPEC_CTRL }, + { MSR_IA32_TSX_CTRL, X86_FEATURE_MSR_TSX_CTRL }, + { MSR_TSX_FORCE_ABORT, X86_FEATURE_TSX_FORCE_ABORT }, + { MSR_IA32_MCU_OPT_CTRL, X86_FEATURE_SRBDS_CTRL }, + { MSR_AMD64_LS_CFG, X86_FEATURE_LS_CFG_SSBD }, + { MSR_AMD64_DE_CFG, X86_FEATURE_LFENCE_RDTSC }, }; + int i; - msr_build_context(spec_msr_id, ARRAY_SIZE(spec_msr_id)); + for (i = 0; i < ARRAY_SIZE(msr_enum); i++) { + if (boot_cpu_has(msr_enum[i].feature)) + msr_build_context(&msr_enum[i].msr_no, 1); + } } static int pm_check_save_msr(void) diff --git a/arch/x86/purgatory/Makefile b/arch/x86/purgatory/Makefile index 31c634a22818..17f09dc26381 100644 --- a/arch/x86/purgatory/Makefile +++ b/arch/x86/purgatory/Makefile @@ -26,6 +26,7 @@ GCOV_PROFILE := n KASAN_SANITIZE := n UBSAN_SANITIZE := n KCSAN_SANITIZE := n +KMSAN_SANITIZE := n KCOV_INSTRUMENT := n # These are adjustments to the compiler flags used for objects that @@ -55,6 +56,10 @@ ifdef CONFIG_RETPOLINE PURGATORY_CFLAGS_REMOVE += $(RETPOLINE_CFLAGS) endif +ifdef CONFIG_CFI_CLANG +PURGATORY_CFLAGS_REMOVE += $(CC_FLAGS_CFI) +endif + CFLAGS_REMOVE_purgatory.o += $(PURGATORY_CFLAGS_REMOVE) CFLAGS_purgatory.o += $(PURGATORY_CFLAGS) diff --git a/arch/x86/realmode/rm/Makefile b/arch/x86/realmode/rm/Makefile index 83f1b6a56449..f614009d3e4e 100644 --- a/arch/x86/realmode/rm/Makefile +++ b/arch/x86/realmode/rm/Makefile @@ -10,6 +10,7 @@ # Sanitizer runtimes are unavailable and cannot be linked here. KASAN_SANITIZE := n KCSAN_SANITIZE := n +KMSAN_SANITIZE := n OBJECT_FILES_NON_STANDARD := y # Prevents link failures: __sanitizer_cov_trace_pc() is not linked in. diff --git a/arch/x86/tools/relocs.c b/arch/x86/tools/relocs.c index e2c5b296120d..2925074b9a58 100644 --- a/arch/x86/tools/relocs.c +++ b/arch/x86/tools/relocs.c @@ -56,6 +56,7 @@ static const char * const sym_regex_kernel[S_NSYMTYPES] = { "^(xen_irq_disable_direct_reloc$|" "xen_save_fl_direct_reloc$|" "VDSO|" + "__kcfi_typeid_|" "__crc_)", /* diff --git a/arch/x86/um/shared/sysdep/syscalls_32.h b/arch/x86/um/shared/sysdep/syscalls_32.h index 68fd2cf526fd..f6e9f84397e7 100644 --- a/arch/x86/um/shared/sysdep/syscalls_32.h +++ b/arch/x86/um/shared/sysdep/syscalls_32.h @@ -6,10 +6,9 @@ #include <asm/unistd.h> #include <sysdep/ptrace.h> -typedef long syscall_handler_t(struct pt_regs); +typedef long syscall_handler_t(struct syscall_args); extern syscall_handler_t *sys_call_table[]; #define EXECUTE_SYSCALL(syscall, regs) \ - ((long (*)(struct syscall_args)) \ - (*sys_call_table[syscall]))(SYSCALL_ARGS(®s->regs)) + ((*sys_call_table[syscall]))(SYSCALL_ARGS(®s->regs)) diff --git a/arch/x86/um/tls_32.c b/arch/x86/um/tls_32.c index ac8eee093f9c..66162eafd8e8 100644 --- a/arch/x86/um/tls_32.c +++ b/arch/x86/um/tls_32.c @@ -65,9 +65,6 @@ static int get_free_idx(struct task_struct* task) struct thread_struct *t = &task->thread; int idx; - if (!t->arch.tls_array) - return GDT_ENTRY_TLS_MIN; - for (idx = 0; idx < GDT_ENTRY_TLS_ENTRIES; idx++) if (!t->arch.tls_array[idx].present) return idx + GDT_ENTRY_TLS_MIN; @@ -240,9 +237,6 @@ static int get_tls_entry(struct task_struct *task, struct user_desc *info, { struct thread_struct *t = &task->thread; - if (!t->arch.tls_array) - goto clear; - if (idx < GDT_ENTRY_TLS_MIN || idx > GDT_ENTRY_TLS_MAX) return -EINVAL; diff --git a/arch/x86/um/vdso/Makefile b/arch/x86/um/vdso/Makefile index 8c0396fd0e6f..6fbe97c52c99 100644 --- a/arch/x86/um/vdso/Makefile +++ b/arch/x86/um/vdso/Makefile @@ -65,7 +65,7 @@ quiet_cmd_vdso = VDSO $@ -Wl,-T,$(filter %.lds,$^) $(filter %.o,$^) && \ sh $(srctree)/$(src)/checkundef.sh '$(NM)' '$@' -VDSO_LDFLAGS = -fPIC -shared -Wl,--hash-style=sysv +VDSO_LDFLAGS = -fPIC -shared -Wl,--hash-style=sysv -z noexecstack GCOV_PROFILE := n # diff --git a/arch/x86/xen/Kconfig b/arch/x86/xen/Kconfig index 85246dd9faa1..9b1ec5d8c99c 100644 --- a/arch/x86/xen/Kconfig +++ b/arch/x86/xen/Kconfig @@ -92,3 +92,12 @@ config XEN_DOM0 select X86_X2APIC if XEN_PVH && X86_64 help Support running as a Xen Dom0 guest. + +config XEN_PV_MSR_SAFE + bool "Always use safe MSR accesses in PV guests" + default y + depends on XEN_PV + help + Use safe (not faulting) MSR access functions even if the MSR access + should not fault anyway. + The default can be changed by using the "xen_msr_safe" boot parameter. diff --git a/arch/x86/xen/enlighten_hvm.c b/arch/x86/xen/enlighten_hvm.c index 1c1ac418484b..c1cd28e915a3 100644 --- a/arch/x86/xen/enlighten_hvm.c +++ b/arch/x86/xen/enlighten_hvm.c @@ -212,7 +212,7 @@ static void __init xen_hvm_guest_init(void) return; if (IS_ENABLED(CONFIG_XEN_VIRTIO_FORCE_GRANT)) - virtio_set_mem_acc_cb(virtio_require_restricted_mem_acc); + virtio_set_mem_acc_cb(xen_virtio_restricted_mem_acc); init_hvm_pv_info(); diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c index 0ed2e487a693..038da45f057a 100644 --- a/arch/x86/xen/enlighten_pv.c +++ b/arch/x86/xen/enlighten_pv.c @@ -23,6 +23,7 @@ #include <linux/start_kernel.h> #include <linux/sched.h> #include <linux/kprobes.h> +#include <linux/kstrtox.h> #include <linux/memblock.h> #include <linux/export.h> #include <linux/mm.h> @@ -108,11 +109,21 @@ struct tls_descs { */ static DEFINE_PER_CPU(struct tls_descs, shadow_tls_desc); +static __read_mostly bool xen_msr_safe = IS_ENABLED(CONFIG_XEN_PV_MSR_SAFE); + +static int __init parse_xen_msr_safe(char *str) +{ + if (str) + return kstrtobool(str, &xen_msr_safe); + return -EINVAL; +} +early_param("xen_msr_safe", parse_xen_msr_safe); + static void __init xen_pv_init_platform(void) { /* PV guests can't operate virtio devices without grants. */ if (IS_ENABLED(CONFIG_XEN_VIRTIO)) - virtio_set_mem_acc_cb(virtio_require_restricted_mem_acc); + virtio_set_mem_acc_cb(xen_virtio_restricted_mem_acc); populate_extra_pte(fix_to_virt(FIX_PARAVIRT_BOOTMAP)); @@ -765,6 +776,7 @@ static void xen_load_idt(const struct desc_ptr *desc) { static DEFINE_SPINLOCK(lock); static struct trap_info traps[257]; + static const struct trap_info zero = { }; unsigned out; trace_xen_cpu_load_idt(desc); @@ -774,7 +786,7 @@ static void xen_load_idt(const struct desc_ptr *desc) memcpy(this_cpu_ptr(&idt_desc), desc, sizeof(idt_desc)); out = xen_convert_trap_info(desc, traps, false); - memset(&traps[out], 0, sizeof(traps[0])); + traps[out] = zero; xen_mc_flush(); if (HYPERVISOR_set_trap_table(traps)) @@ -916,14 +928,18 @@ static void xen_write_cr4(unsigned long cr4) native_write_cr4(cr4); } -static u64 xen_read_msr_safe(unsigned int msr, int *err) +static u64 xen_do_read_msr(unsigned int msr, int *err) { - u64 val; + u64 val = 0; /* Avoid uninitialized value for safe variant. */ if (pmu_msr_read(msr, &val, err)) return val; - val = native_read_msr_safe(msr, err); + if (err) + val = native_read_msr_safe(msr, err); + else + val = native_read_msr(msr); + switch (msr) { case MSR_IA32_APICBASE: val &= ~X2APIC_ENABLE; @@ -932,23 +948,39 @@ static u64 xen_read_msr_safe(unsigned int msr, int *err) return val; } -static int xen_write_msr_safe(unsigned int msr, unsigned low, unsigned high) +static void set_seg(unsigned int which, unsigned int low, unsigned int high, + int *err) { - int ret; - unsigned int which; - u64 base; + u64 base = ((u64)high << 32) | low; - ret = 0; + if (HYPERVISOR_set_segment_base(which, base) == 0) + return; + if (err) + *err = -EIO; + else + WARN(1, "Xen set_segment_base(%u, %llx) failed\n", which, base); +} + +/* + * Support write_msr_safe() and write_msr() semantics. + * With err == NULL write_msr() semantics are selected. + * Supplying an err pointer requires err to be pre-initialized with 0. + */ +static void xen_do_write_msr(unsigned int msr, unsigned int low, + unsigned int high, int *err) +{ switch (msr) { - case MSR_FS_BASE: which = SEGBASE_FS; goto set; - case MSR_KERNEL_GS_BASE: which = SEGBASE_GS_USER; goto set; - case MSR_GS_BASE: which = SEGBASE_GS_KERNEL; goto set; - - set: - base = ((u64)high << 32) | low; - if (HYPERVISOR_set_segment_base(which, base) != 0) - ret = -EIO; + case MSR_FS_BASE: + set_seg(SEGBASE_FS, low, high, err); + break; + + case MSR_KERNEL_GS_BASE: + set_seg(SEGBASE_GS_USER, low, high, err); + break; + + case MSR_GS_BASE: + set_seg(SEGBASE_GS_KERNEL, low, high, err); break; case MSR_STAR: @@ -964,31 +996,42 @@ static int xen_write_msr_safe(unsigned int msr, unsigned low, unsigned high) break; default: - if (!pmu_msr_write(msr, low, high, &ret)) - ret = native_write_msr_safe(msr, low, high); + if (!pmu_msr_write(msr, low, high, err)) { + if (err) + *err = native_write_msr_safe(msr, low, high); + else + native_write_msr(msr, low, high); + } } +} - return ret; +static u64 xen_read_msr_safe(unsigned int msr, int *err) +{ + return xen_do_read_msr(msr, err); +} + +static int xen_write_msr_safe(unsigned int msr, unsigned int low, + unsigned int high) +{ + int err = 0; + + xen_do_write_msr(msr, low, high, &err); + + return err; } static u64 xen_read_msr(unsigned int msr) { - /* - * This will silently swallow a #GP from RDMSR. It may be worth - * changing that. - */ int err; - return xen_read_msr_safe(msr, &err); + return xen_do_read_msr(msr, xen_msr_safe ? &err : NULL); } static void xen_write_msr(unsigned int msr, unsigned low, unsigned high) { - /* - * This will silently swallow a #GP from WRMSR. It may be worth - * changing that. - */ - xen_write_msr_safe(msr, low, high); + int err; + + xen_do_write_msr(msr, low, high, xen_msr_safe ? &err : NULL); } /* This is called once we have the cpu_possible_mask */ diff --git a/arch/x86/xen/pmu.c b/arch/x86/xen/pmu.c index 21ecbe754cb2..246d67dab510 100644 --- a/arch/x86/xen/pmu.c +++ b/arch/x86/xen/pmu.c @@ -131,6 +131,10 @@ static inline uint32_t get_fam15h_addr(u32 addr) static inline bool is_amd_pmu_msr(unsigned int msr) { + if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD && + boot_cpu_data.x86_vendor != X86_VENDOR_HYGON) + return false; + if ((msr >= MSR_F15H_PERF_CTL && msr < MSR_F15H_PERF_CTR + (amd_num_counters * 2)) || (msr >= MSR_K7_EVNTSEL0 && @@ -140,10 +144,15 @@ static inline bool is_amd_pmu_msr(unsigned int msr) return false; } -static int is_intel_pmu_msr(u32 msr_index, int *type, int *index) +static bool is_intel_pmu_msr(u32 msr_index, int *type, int *index) { u32 msr_index_pmc; + if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL && + boot_cpu_data.x86_vendor != X86_VENDOR_CENTAUR && + boot_cpu_data.x86_vendor != X86_VENDOR_ZHAOXIN) + return false; + switch (msr_index) { case MSR_CORE_PERF_FIXED_CTR_CTRL: case MSR_IA32_DS_AREA: @@ -290,48 +299,52 @@ static bool xen_amd_pmu_emulate(unsigned int msr, u64 *val, bool is_read) return false; } +static bool pmu_msr_chk_emulated(unsigned int msr, uint64_t *val, bool is_read, + bool *emul) +{ + int type, index = 0; + + if (is_amd_pmu_msr(msr)) + *emul = xen_amd_pmu_emulate(msr, val, is_read); + else if (is_intel_pmu_msr(msr, &type, &index)) + *emul = xen_intel_pmu_emulate(msr, val, type, index, is_read); + else + return false; + + return true; +} + bool pmu_msr_read(unsigned int msr, uint64_t *val, int *err) { - if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) { - if (is_amd_pmu_msr(msr)) { - if (!xen_amd_pmu_emulate(msr, val, 1)) - *val = native_read_msr_safe(msr, err); - return true; - } - } else { - int type, index; + bool emulated; - if (is_intel_pmu_msr(msr, &type, &index)) { - if (!xen_intel_pmu_emulate(msr, val, type, index, 1)) - *val = native_read_msr_safe(msr, err); - return true; - } + if (!pmu_msr_chk_emulated(msr, val, true, &emulated)) + return false; + + if (!emulated) { + *val = err ? native_read_msr_safe(msr, err) + : native_read_msr(msr); } - return false; + return true; } bool pmu_msr_write(unsigned int msr, uint32_t low, uint32_t high, int *err) { uint64_t val = ((uint64_t)high << 32) | low; + bool emulated; - if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) { - if (is_amd_pmu_msr(msr)) { - if (!xen_amd_pmu_emulate(msr, &val, 0)) - *err = native_write_msr_safe(msr, low, high); - return true; - } - } else { - int type, index; + if (!pmu_msr_chk_emulated(msr, &val, false, &emulated)) + return false; - if (is_intel_pmu_msr(msr, &type, &index)) { - if (!xen_intel_pmu_emulate(msr, &val, type, index, 0)) - *err = native_write_msr_safe(msr, low, high); - return true; - } + if (!emulated) { + if (err) + *err = native_write_msr_safe(msr, low, high); + else + native_write_msr(msr, low, high); } - return false; + return true; } static unsigned long long xen_amd_read_pmc(int counter) diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c index cfa99e8f054b..8db26f10fb1d 100644 --- a/arch/x86/xen/setup.c +++ b/arch/x86/xen/setup.c @@ -7,6 +7,7 @@ #include <linux/init.h> #include <linux/sched.h> +#include <linux/kstrtox.h> #include <linux/mm.h> #include <linux/pm.h> #include <linux/memblock.h> @@ -85,7 +86,7 @@ static void __init xen_parse_512gb(void) arg = strstr(xen_start_info->cmd_line, "xen_512gb_limit="); if (!arg) val = true; - else if (strtobool(arg + strlen("xen_512gb_limit="), &val)) + else if (kstrtobool(arg + strlen("xen_512gb_limit="), &val)) return; xen_512gb_limit = val; @@ -910,17 +911,9 @@ static int register_callback(unsigned type, const void *func) void xen_enable_sysenter(void) { - int ret; - unsigned sysenter_feature; - - sysenter_feature = X86_FEATURE_SYSENTER32; - - if (!boot_cpu_has(sysenter_feature)) - return; - - ret = register_callback(CALLBACKTYPE_sysenter, xen_entry_SYSENTER_compat); - if(ret != 0) - setup_clear_cpu_cap(sysenter_feature); + if (cpu_feature_enabled(X86_FEATURE_SYSENTER32) && + register_callback(CALLBACKTYPE_sysenter, xen_entry_SYSENTER_compat)) + setup_clear_cpu_cap(X86_FEATURE_SYSENTER32); } void xen_enable_syscall(void) @@ -934,12 +927,9 @@ void xen_enable_syscall(void) mechanism for syscalls. */ } - if (boot_cpu_has(X86_FEATURE_SYSCALL32)) { - ret = register_callback(CALLBACKTYPE_syscall32, - xen_entry_SYSCALL_compat); - if (ret != 0) - setup_clear_cpu_cap(X86_FEATURE_SYSCALL32); - } + if (cpu_feature_enabled(X86_FEATURE_SYSCALL32) && + register_callback(CALLBACKTYPE_syscall32, xen_entry_SYSCALL_compat)) + setup_clear_cpu_cap(X86_FEATURE_SYSCALL32); } static void __init xen_pvmmu_arch_setup(void) diff --git a/arch/x86/xen/smp_pv.c b/arch/x86/xen/smp_pv.c index ba7af2eca755..480be82e9b7b 100644 --- a/arch/x86/xen/smp_pv.c +++ b/arch/x86/xen/smp_pv.c @@ -179,7 +179,7 @@ static void __init _get_smp_config(unsigned int early) * hypercall to expand the max number of VCPUs an already * running guest has. So cap it up to X. */ if (subtract) - nr_cpu_ids = nr_cpu_ids - subtract; + set_nr_cpu_ids(nr_cpu_ids - subtract); #endif } |