From 454de1e7d970d6bc567686052329e4814842867c Mon Sep 17 00:00:00 2001 From: Janakarajan Natarajan Date: Mon, 7 Oct 2019 19:00:22 +0000 Subject: [PATCH 1/4] x86/asm: Fix MWAITX C-state hint value As per "AMD64 Architecture Programmer's Manual Volume 3: General-Purpose and System Instructions", MWAITX EAX[7:4]+1 specifies the optional hint of the optimized C-state. For C0 state, EAX[7:4] should be set to 0xf. Currently, a value of 0xf is set for EAX[3:0] instead of EAX[7:4]. Fix this by changing MWAITX_DISABLE_CSTATES from 0xf to 0xf0. This hasn't had any implications so far because setting reserved bits in EAX is simply ignored by the CPU. [ bp: Fixup comment in delay_mwaitx() and massage. ] Signed-off-by: Janakarajan Natarajan Signed-off-by: Borislav Petkov Cc: Frederic Weisbecker Cc: Greg Kroah-Hartman Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Thomas Gleixner Cc: "x86@kernel.org" Cc: Zhenzhong Duan Cc: Link: https://lkml.kernel.org/r/20191007190011.4859-1-Janakarajan.Natarajan@amd.com Signed-off-by: Ingo Molnar --- arch/x86/include/asm/mwait.h | 2 +- arch/x86/lib/delay.c | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/x86/include/asm/mwait.h b/arch/x86/include/asm/mwait.h index e28f8b723b5c..9d5252c9685c 100644 --- a/arch/x86/include/asm/mwait.h +++ b/arch/x86/include/asm/mwait.h @@ -21,7 +21,7 @@ #define MWAIT_ECX_INTERRUPT_BREAK 0x1 #define MWAITX_ECX_TIMER_ENABLE BIT(1) #define MWAITX_MAX_LOOPS ((u32)-1) -#define MWAITX_DISABLE_CSTATES 0xf +#define MWAITX_DISABLE_CSTATES 0xf0 static inline void __monitor(const void *eax, unsigned long ecx, unsigned long edx) diff --git a/arch/x86/lib/delay.c b/arch/x86/lib/delay.c index b7375dc6898f..c126571e5e2e 100644 --- a/arch/x86/lib/delay.c +++ b/arch/x86/lib/delay.c @@ -113,8 +113,8 @@ static void delay_mwaitx(unsigned long __loops) __monitorx(raw_cpu_ptr(&cpu_tss_rw), 0, 0); /* - * AMD, like Intel, supports the EAX hint and EAX=0xf - * means, do not enter any deep C-state and we use it + * AMD, like Intel's MWAIT version, supports the EAX hint and + * EAX=0xf0 means, do not enter any deep C-state and we use it * here in delay() to minimize wakeup latency. */ __mwaitx(MWAITX_DISABLE_CSTATES, delay, MWAITX_ECX_TIMER_ENABLE); From fbcfb8f0270bf24fe348393540b17a7f2ba577d7 Mon Sep 17 00:00:00 2001 From: Sami Tolvanen Date: Mon, 7 Oct 2019 12:21:29 -0700 Subject: [PATCH 2/4] x86/cpu/vmware: Use the full form of INL in VMWARE_PORT LLVM's assembler doesn't accept the short form INL instruction: inl (%%dx) but instead insists on the output register to be explicitly specified: :1:7: error: invalid operand for instruction inl (%dx) ^ LLVM ERROR: Error parsing inline asm Use the full form of the instruction to fix the build. Signed-off-by: Sami Tolvanen Signed-off-by: Borislav Petkov Reviewed-by: Nick Desaulniers Reviewed-by: Kees Cook Acked-by: Thomas Hellstrom Cc: clang-built-linux@googlegroups.com Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Thomas Gleixner Cc: virtualization@lists.linux-foundation.org Cc: "VMware, Inc." Cc: x86-ml Link: https://github.com/ClangBuiltLinux/linux/issues/734 Link: https://lkml.kernel.org/r/20191007192129.104336-1-samitolvanen@google.com Signed-off-by: Ingo Molnar --- arch/x86/kernel/cpu/vmware.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/kernel/cpu/vmware.c b/arch/x86/kernel/cpu/vmware.c index 9735139cfdf8..46d732696c1c 100644 --- a/arch/x86/kernel/cpu/vmware.c +++ b/arch/x86/kernel/cpu/vmware.c @@ -49,7 +49,7 @@ #define VMWARE_CMD_VCPU_RESERVED 31 #define VMWARE_PORT(cmd, eax, ebx, ecx, edx) \ - __asm__("inl (%%dx)" : \ + __asm__("inl (%%dx), %%eax" : \ "=a"(eax), "=c"(ecx), "=d"(edx), "=b"(ebx) : \ "a"(VMWARE_HYPERVISOR_MAGIC), \ "c"(VMWARE_CMD_##cmd), \ From bec500777089b3c96c53681fc0aa6fee59711d4a Mon Sep 17 00:00:00 2001 From: Arvind Sankar Date: Mon, 7 Oct 2019 18:00:02 -0400 Subject: [PATCH 3/4] lib/string: Make memzero_explicit() inline instead of external With the use of the barrier implied by barrier_data(), there is no need for memzero_explicit() to be extern. Making it inline saves the overhead of a function call, and allows the code to be reused in arch/*/purgatory without having to duplicate the implementation. Tested-by: Hans de Goede Signed-off-by: Arvind Sankar Reviewed-by: Hans de Goede Cc: Ard Biesheuvel Cc: Borislav Petkov Cc: H . Peter Anvin Cc: Herbert Xu Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Stephan Mueller Cc: Thomas Gleixner Cc: linux-crypto@vger.kernel.org Cc: linux-s390@vger.kernel.org Fixes: 906a4bb97f5d ("crypto: sha256 - Use get/put_unaligned_be32 to get input, memzero_explicit") Link: https://lkml.kernel.org/r/20191007220000.GA408752@rani.riverdale.lan Signed-off-by: Ingo Molnar --- include/linux/string.h | 21 ++++++++++++++++++++- lib/string.c | 21 --------------------- 2 files changed, 20 insertions(+), 22 deletions(-) diff --git a/include/linux/string.h b/include/linux/string.h index b2f9df7f0761..b6ccdc2c7f02 100644 --- a/include/linux/string.h +++ b/include/linux/string.h @@ -227,7 +227,26 @@ static inline bool strstarts(const char *str, const char *prefix) } size_t memweight(const void *ptr, size_t bytes); -void memzero_explicit(void *s, size_t count); + +/** + * memzero_explicit - Fill a region of memory (e.g. sensitive + * keying data) with 0s. + * @s: Pointer to the start of the area. + * @count: The size of the area. + * + * Note: usually using memset() is just fine (!), but in cases + * where clearing out _local_ data at the end of a scope is + * necessary, memzero_explicit() should be used instead in + * order to prevent the compiler from optimising away zeroing. + * + * memzero_explicit() doesn't need an arch-specific version as + * it just invokes the one of memset() implicitly. + */ +static inline void memzero_explicit(void *s, size_t count) +{ + memset(s, 0, count); + barrier_data(s); +} /** * kbasename - return the last part of a pathname. diff --git a/lib/string.c b/lib/string.c index cd7a10c19210..08ec58cc673b 100644 --- a/lib/string.c +++ b/lib/string.c @@ -748,27 +748,6 @@ void *memset(void *s, int c, size_t count) EXPORT_SYMBOL(memset); #endif -/** - * memzero_explicit - Fill a region of memory (e.g. sensitive - * keying data) with 0s. - * @s: Pointer to the start of the area. - * @count: The size of the area. - * - * Note: usually using memset() is just fine (!), but in cases - * where clearing out _local_ data at the end of a scope is - * necessary, memzero_explicit() should be used instead in - * order to prevent the compiler from optimising away zeroing. - * - * memzero_explicit() doesn't need an arch-specific version as - * it just invokes the one of memset() implicitly. - */ -void memzero_explicit(void *s, size_t count) -{ - memset(s, 0, count); - barrier_data(s); -} -EXPORT_SYMBOL(memzero_explicit); - #ifndef __HAVE_ARCH_MEMSET16 /** * memset16() - Fill a memory area with a uint16_t From 8d7c6ac3b2371eb1cbc9925a88f4d10efff374de Mon Sep 17 00:00:00 2001 From: Kan Liang Date: Tue, 8 Oct 2019 08:50:02 -0700 Subject: [PATCH 4/4] x86/cpu: Add Comet Lake to the Intel CPU models header Comet Lake is the new 10th Gen Intel processor. Add two new CPU model numbers to the Intel family list. The CPU model numbers are not published in the SDM yet but they come from an authoritative internal source. [ bp: Touch up commit message. ] Signed-off-by: Kan Liang Signed-off-by: Borislav Petkov Reviewed-by: Tony Luck Cc: ak@linux.intel.com Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: x86-ml Link: https://lkml.kernel.org/r/1570549810-25049-2-git-send-email-kan.liang@linux.intel.com --- arch/x86/include/asm/intel-family.h | 3 +++ 1 file changed, 3 insertions(+) diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h index f04622500da3..c606c0b70738 100644 --- a/arch/x86/include/asm/intel-family.h +++ b/arch/x86/include/asm/intel-family.h @@ -83,6 +83,9 @@ #define INTEL_FAM6_TIGERLAKE_L 0x8C #define INTEL_FAM6_TIGERLAKE 0x8D +#define INTEL_FAM6_COMETLAKE 0xA5 +#define INTEL_FAM6_COMETLAKE_L 0xA6 + /* "Small Core" Processors (Atom) */ #define INTEL_FAM6_ATOM_BONNELL 0x1C /* Diamondville, Pineview */