From: Borislav Petkov <bp@suse.de> Hi, here's the last pile that got ready. It is mostly SMCA enablement for future AMD F17h CPUs so the remaining families shouldn't be affected. Initial testing on what I have here looks ok, randconfigs pass too. All is ontop of tip:ras/core. Thanks. Borislav Petkov (1): x86/mce/AMD: Save an indentation level in prepare_threshold_block() Yazen Ghannam (6): x86/mce/AMD: Log Deferred Errors using SMCA MCA_DE{STAT,ADDR} registers x86/mce/AMD: Disable LogDeferredInMcaStat for SMCA systems x86/cpu: Add detection of AMD RAS Capabilities x86/mce: Update AMD mcheck init to use cpu_has() facilities EDAC, mce_amd: Detect SMCA using X86_FEATURE_SMCA x86/RAS: Add SMCA support to AMD Error Injector arch/x86/include/asm/cpufeature.h | 1 + arch/x86/include/asm/cpufeatures.h | 7 ++- arch/x86/include/asm/mce.h | 4 ++ arch/x86/kernel/cpu/common.c | 10 ++-- arch/x86/kernel/cpu/mcheck/mce.c | 8 ++-- arch/x86/kernel/cpu/mcheck/mce_amd.c | 92 ++++++++++++++++++++++++------------ arch/x86/ras/mce_amd_inj.c | 31 +++++++++--- drivers/edac/mce_amd.c | 9 ++-- 8 files changed, 112 insertions(+), 50 deletions(-) -- 2.7.3
From: Yazen Ghannam <Yazen.Ghannam@amd.com> Scalable MCA provides new registers for all banks for logging deferred errors: MCA_DESTAT and MCA_DEADDR. Deferred errors are always logged to these registers. Update the AMD deferred error handler to use these registers, if available. Signed-off-by: Yazen Ghannam <Yazen.Ghannam@amd.com> Cc: Aravind Gopalakrishnan <aravindksg.lkml@gmail.com> Cc: linux-edac <linux-edac@vger.kernel.org> Cc: Tony Luck <tony.luck@intel.com> Cc: x86-ml <x86@kernel.org> Link: http://lkml.kernel.org/r/1462377407-1446-2-git-send-email-Yazen.Ghannam@amd.com [ Sanity-check __log_error() args, massage a bit. ] Signed-off-by: Borislav Petkov <bp@suse.de> --- arch/x86/include/asm/mce.h | 4 ++++ arch/x86/kernel/cpu/mcheck/mce_amd.c | 32 ++++++++++++++++++++++++-------- 2 files changed, 28 insertions(+), 8 deletions(-) diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h index 53ab69704771..8bf766ef0e18 100644 --- a/arch/x86/include/asm/mce.h +++ b/arch/x86/include/asm/mce.h @@ -110,6 +110,8 @@ #define MSR_AMD64_SMCA_MC0_MISC0 0xc0002003 #define MSR_AMD64_SMCA_MC0_CONFIG 0xc0002004 #define MSR_AMD64_SMCA_MC0_IPID 0xc0002005 +#define MSR_AMD64_SMCA_MC0_DESTAT 0xc0002008 +#define MSR_AMD64_SMCA_MC0_DEADDR 0xc0002009 #define MSR_AMD64_SMCA_MC0_MISC1 0xc000200a #define MSR_AMD64_SMCA_MCx_CTL(x) (MSR_AMD64_SMCA_MC0_CTL + 0x10*(x)) #define MSR_AMD64_SMCA_MCx_STATUS(x) (MSR_AMD64_SMCA_MC0_STATUS + 0x10*(x)) @@ -117,6 +119,8 @@ #define MSR_AMD64_SMCA_MCx_MISC(x) (MSR_AMD64_SMCA_MC0_MISC0 + 0x10*(x)) #define MSR_AMD64_SMCA_MCx_CONFIG(x) (MSR_AMD64_SMCA_MC0_CONFIG + 0x10*(x)) #define MSR_AMD64_SMCA_MCx_IPID(x) (MSR_AMD64_SMCA_MC0_IPID + 0x10*(x)) +#define MSR_AMD64_SMCA_MCx_DESTAT(x) (MSR_AMD64_SMCA_MC0_DESTAT + 0x10*(x)) +#define MSR_AMD64_SMCA_MCx_DEADDR(x) (MSR_AMD64_SMCA_MC0_DEADDR + 0x10*(x)) #define MSR_AMD64_SMCA_MCx_MISCy(x, y) ((MSR_AMD64_SMCA_MC0_MISC1 + y) + (0x10*(x))) /* diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c index c594680c36f2..d1b1e62f7cb9 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_amd.c +++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c @@ -430,12 +430,23 @@ void mce_amd_feature_init(struct cpuinfo_x86 *c) deferred_error_interrupt_enable(c); } -static void __log_error(unsigned int bank, bool threshold_err, u64 misc) +static void +__log_error(unsigned int bank, bool deferred_err, bool threshold_err, u64 misc) { + u32 msr_status = msr_ops.status(bank); + u32 msr_addr = msr_ops.addr(bank); struct mce m; u64 status; - rdmsrl(msr_ops.status(bank), status); + WARN_ON_ONCE(deferred_err && threshold_err); + + if (deferred_err && mce_flags.smca) { + msr_status = MSR_AMD64_SMCA_MCx_DESTAT(bank); + msr_addr = MSR_AMD64_SMCA_MCx_DEADDR(bank); + } + + rdmsrl(msr_status, status); + if (!(status & MCI_STATUS_VAL)) return; @@ -448,10 +459,11 @@ static void __log_error(unsigned int bank, bool threshold_err, u64 misc) m.misc = misc; if (m.status & MCI_STATUS_ADDRV) - rdmsrl(msr_ops.addr(bank), m.addr); + rdmsrl(msr_addr, m.addr); mce_log(&m); - wrmsrl(msr_ops.status(bank), 0); + + wrmsrl(msr_status, 0); } static inline void __smp_deferred_error_interrupt(void) @@ -479,17 +491,21 @@ asmlinkage __visible void smp_trace_deferred_error_interrupt(void) /* APIC interrupt handler for deferred errors */ static void amd_deferred_error_interrupt(void) { - u64 status; unsigned int bank; + u32 msr_status; + u64 status; for (bank = 0; bank < mca_cfg.banks; ++bank) { - rdmsrl(msr_ops.status(bank), status); + msr_status = (mce_flags.smca) ? MSR_AMD64_SMCA_MCx_DESTAT(bank) + : msr_ops.status(bank); + + rdmsrl(msr_status, status); if (!(status & MCI_STATUS_VAL) || !(status & MCI_STATUS_DEFERRED)) continue; - __log_error(bank, false, 0); + __log_error(bank, true, false, 0); break; } } @@ -544,7 +560,7 @@ static void amd_threshold_interrupt(void) return; log: - __log_error(bank, true, ((u64)high << 32) | low); + __log_error(bank, false, true, ((u64)high << 32) | low); } /* -- 2.7.3
From: Yazen Ghannam <Yazen.Ghannam@amd.com> Disable Deferred Error logging in MCA_{STATUS,ADDR} additionally for SMCA systems as this information will retrieved from MCA_DE{STAT,ADDR} on those systems. Signed-off-by: Yazen Ghannam <Yazen.Ghannam@amd.com> Cc: Aravind Gopalakrishnan <aravindksg.lkml@gmail.com> Cc: Tony Luck <tony.luck@intel.com> Cc: linux-edac <linux-edac@vger.kernel.org> Cc: x86-ml <x86@kernel.org> Link: http://lkml.kernel.org/r/1462377407-1446-3-git-send-email-Yazen.Ghannam@amd.com [ Simplify, drop SMCA_MCAX_EN_OFF define too. ] Signed-off-by: Borislav Petkov <bp@suse.de> --- arch/x86/kernel/cpu/mcheck/mce_amd.c | 38 +++++++++++++++++++++++++++--------- 1 file changed, 29 insertions(+), 9 deletions(-) diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c index d1b1e62f7cb9..527ddae3017b 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_amd.c +++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c @@ -54,14 +54,6 @@ /* Threshold LVT offset is at MSR0xC0000410[15:12] */ #define SMCA_THR_LVT_OFF 0xF000 -/* - * OS is required to set the MCAX bit to acknowledge that it is now using the - * new MSR ranges and new registers under each bank. It also means that the OS - * will configure deferred errors in the new MCx_CONFIG register. If the bit is - * not set, uncorrectable errors will cause a system panic. - */ -#define SMCA_MCAX_EN_OFF 0x1 - static const char * const th_names[] = { "load_store", "insn_fetch", @@ -374,7 +366,35 @@ prepare_threshold_block(unsigned int bank, unsigned int block, u32 addr, u32 smca_addr = MSR_AMD64_SMCA_MCx_CONFIG(bank); if (!rdmsr_safe(smca_addr, &smca_low, &smca_high)) { - smca_high |= SMCA_MCAX_EN_OFF; + /* + * OS is required to set the MCAX bit to acknowledge + * that it is now using the new MSR ranges and new + * registers under each bank. It also means that the OS + * will configure deferred errors in the new MCx_CONFIG + * register. If the bit is not set, uncorrectable errors + * will cause a system panic. + * + * MCA_CONFIG[MCAX] is bit 32 (0 in the high portion of + * the MSR.) + */ + smca_high |= BIT(0); + + /* + * SMCA logs Deferred Error information in + * MCA_DE{STAT,ADDR} registers with the option of + * additionally logging to MCA_{STATUS,ADDR} if + * MCA_CONFIG[LogDeferredInMcaStat] is set. + * + * This bit is usually set by BIOS to retain the old + * behavior for OSes that don't use the new registers. + * Linux supports the new registers so let's disable + * that additional logging here. + * + * MCA_CONFIG[LogDeferredInMcaStat] is bit 34 (bit 2 in + * the high portion of the MSR). + */ + smca_high &= ~BIT(2); + wrmsr(smca_addr, smca_low, smca_high); } -- 2.7.3
From: Borislav Petkov <bp@suse.de> Do the !SMCA work first and then save us an indentation level for the SMCA code. No functionality change. Signed-off-by: Borislav Petkov <bp@suse.de> Cc: Aravind Gopalakrishnan <aravindksg.lkml@gmail.com> Cc: Tony Luck <tony.luck@intel.com> Cc: linux-edac <linux-edac@vger.kernel.org> Cc: x86-ml <x86@kernel.org> Cc: Yazen Ghannam <Yazen.Ghannam@amd.com> --- arch/x86/kernel/cpu/mcheck/mce_amd.c | 78 ++++++++++++++++++------------------ 1 file changed, 38 insertions(+), 40 deletions(-) diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c index 527ddae3017b..10b0661651e0 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_amd.c +++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c @@ -343,6 +343,7 @@ prepare_threshold_block(unsigned int bank, unsigned int block, u32 addr, int offset, u32 misc_high) { unsigned int cpu = smp_processor_id(); + u32 smca_low, smca_high, smca_addr; struct threshold_block b; int new; @@ -361,52 +362,49 @@ prepare_threshold_block(unsigned int bank, unsigned int block, u32 addr, b.interrupt_enable = 1; - if (mce_flags.smca) { - u32 smca_low, smca_high; - u32 smca_addr = MSR_AMD64_SMCA_MCx_CONFIG(bank); - - if (!rdmsr_safe(smca_addr, &smca_low, &smca_high)) { - /* - * OS is required to set the MCAX bit to acknowledge - * that it is now using the new MSR ranges and new - * registers under each bank. It also means that the OS - * will configure deferred errors in the new MCx_CONFIG - * register. If the bit is not set, uncorrectable errors - * will cause a system panic. - * - * MCA_CONFIG[MCAX] is bit 32 (0 in the high portion of - * the MSR.) - */ - smca_high |= BIT(0); + if (!mce_flags.smca) { + new = (misc_high & MASK_LVTOFF_HI) >> 20; + goto set_offset; + } - /* - * SMCA logs Deferred Error information in - * MCA_DE{STAT,ADDR} registers with the option of - * additionally logging to MCA_{STATUS,ADDR} if - * MCA_CONFIG[LogDeferredInMcaStat] is set. - * - * This bit is usually set by BIOS to retain the old - * behavior for OSes that don't use the new registers. - * Linux supports the new registers so let's disable - * that additional logging here. - * - * MCA_CONFIG[LogDeferredInMcaStat] is bit 34 (bit 2 in - * the high portion of the MSR). - */ - smca_high &= ~BIT(2); + smca_addr = MSR_AMD64_SMCA_MCx_CONFIG(bank); - wrmsr(smca_addr, smca_low, smca_high); - } + if (!rdmsr_safe(smca_addr, &smca_low, &smca_high)) { + /* + * OS is required to set the MCAX bit to acknowledge that it is + * now using the new MSR ranges and new registers under each + * bank. It also means that the OS will configure deferred + * errors in the new MCx_CONFIG register. If the bit is not set, + * uncorrectable errors will cause a system panic. + * + * MCA_CONFIG[MCAX] is bit 32 (0 in the high portion of the MSR.) + */ + smca_high |= BIT(0); - /* Gather LVT offset for thresholding: */ - if (rdmsr_safe(MSR_CU_DEF_ERR, &smca_low, &smca_high)) - goto out; + /* + * SMCA logs Deferred Error information in MCA_DE{STAT,ADDR} + * registers with the option of additionally logging to + * MCA_{STATUS,ADDR} if MCA_CONFIG[LogDeferredInMcaStat] is set. + * + * This bit is usually set by BIOS to retain the old behavior + * for OSes that don't use the new registers. Linux supports the + * new registers so let's disable that additional logging here. + * + * MCA_CONFIG[LogDeferredInMcaStat] is bit 34 (bit 2 in the high + * portion of the MSR). + */ + smca_high &= ~BIT(2); - new = (smca_low & SMCA_THR_LVT_OFF) >> 12; - } else { - new = (misc_high & MASK_LVTOFF_HI) >> 20; + wrmsr(smca_addr, smca_low, smca_high); } + /* Gather LVT offset for thresholding: */ + if (rdmsr_safe(MSR_CU_DEF_ERR, &smca_low, &smca_high)) + goto out; + + new = (smca_low & SMCA_THR_LVT_OFF) >> 12; + +set_offset: offset = setup_APIC_mce_threshold(offset, new); if ((offset == new) && (mce_threshold_vector != amd_threshold_interrupt)) -- 2.7.3
From: Yazen Ghannam <Yazen.Ghannam@amd.com> Add a new CPUID leaf to hold the contents of CPUID 0x80000007_EBX (RasCap). Define bits that are currently in use: Bit 0: McaOverflowRecov Bit 1: SUCCOR Bit 3: ScalableMca Signed-off-by: Yazen Ghannam <Yazen.Ghannam@amd.com> Cc: Tony Luck <tony.luck@intel.com> Cc: linux-edac <linux-edac@vger.kernel.org> Cc: x86-ml <x86@kernel.org> Link: http://lkml.kernel.org/r/1462914639-29513-3-git-send-email-Yazen.Ghannam@amd.com [ Shorten comment. ] Signed-off-by: Borislav Petkov <bp@suse.de> --- arch/x86/include/asm/cpufeature.h | 1 + arch/x86/include/asm/cpufeatures.h | 7 ++++++- arch/x86/kernel/cpu/common.c | 10 +++++++--- 3 files changed, 14 insertions(+), 4 deletions(-) diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index 3636ec06c887..53ac9bbf2064 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -27,6 +27,7 @@ enum cpuid_leafs CPUID_6_EAX, CPUID_8000_000A_EDX, CPUID_7_ECX, + CPUID_8000_0007_EBX, }; #ifdef CONFIG_X86_FEATURE_NAMES diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 8f9afefd2dc5..d4e5018e9a44 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -12,7 +12,7 @@ /* * Defines x86 CPU feature bits */ -#define NCAPINTS 17 /* N 32-bit words worth of info */ +#define NCAPINTS 18 /* N 32-bit words worth of info */ #define NBUGINTS 1 /* N 32-bit bug flags */ /* @@ -280,6 +280,11 @@ #define X86_FEATURE_PKU (16*32+ 3) /* Protection Keys for Userspace */ #define X86_FEATURE_OSPKE (16*32+ 4) /* OS Protection Keys Enable */ +/* AMD-defined CPU features, CPUID level 0x80000007 (ebx), word 17 */ +#define X86_FEATURE_OVERFLOW_RECOV (17*32+0) /* MCA overflow recovery support */ +#define X86_FEATURE_SUCCOR (17*32+1) /* Uncorrectable error containment and recovery */ +#define X86_FEATURE_SMCA (17*32+3) /* Scalable MCA */ + /* * BUG word(s) */ diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 8394b3d1f94f..dbc6f066e231 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -717,6 +717,13 @@ void get_cpu_cap(struct cpuinfo_x86 *c) } } + if (c->extended_cpuid_level >= 0x80000007) { + cpuid(0x80000007, &eax, &ebx, &ecx, &edx); + + c->x86_capability[CPUID_8000_0007_EBX] = ebx; + c->x86_power = edx; + } + if (c->extended_cpuid_level >= 0x80000008) { cpuid(0x80000008, &eax, &ebx, &ecx, &edx); @@ -729,9 +736,6 @@ void get_cpu_cap(struct cpuinfo_x86 *c) c->x86_phys_bits = 36; #endif - if (c->extended_cpuid_level >= 0x80000007) - c->x86_power = cpuid_edx(0x80000007); - if (c->extended_cpuid_level >= 0x8000000a) c->x86_capability[CPUID_8000_000A_EDX] = cpuid_edx(0x8000000a); -- 2.7.3
From: Yazen Ghannam <Yazen.Ghannam@amd.com> Use cpu_has() facilities to find available RAS features rather than directly reading CPUID 0x80000007_EBX. Signed-off-by: Yazen Ghannam <Yazen.Ghannam@amd.com> Cc: Tony Luck <tony.luck@intel.com> Cc: linux-edac <linux-edac@vger.kernel.org> Cc: x86-ml <x86@kernel.org> Link: http://lkml.kernel.org/r/1462914639-29513-4-git-send-email-Yazen.Ghannam@amd.com [ Use the struct cpuinfo_x86 ptr instead. ] Signed-off-by: Borislav Petkov <bp@suse.de> --- arch/x86/kernel/cpu/mcheck/mce.c | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index aeda44684758..92e5e37d97bf 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -1683,11 +1683,9 @@ static void __mcheck_cpu_init_vendor(struct cpuinfo_x86 *c) break; case X86_VENDOR_AMD: { - u32 ebx = cpuid_ebx(0x80000007); - - mce_flags.overflow_recov = !!(ebx & BIT(0)); - mce_flags.succor = !!(ebx & BIT(1)); - mce_flags.smca = !!(ebx & BIT(3)); + mce_flags.overflow_recov = !!cpu_has(c, X86_FEATURE_OVERFLOW_RECOV); + mce_flags.succor = !!cpu_has(c, X86_FEATURE_SUCCOR); + mce_flags.smca = !!cpu_has(c, X86_FEATURE_SMCA); /* * Install proper ops for Scalable MCA enabled processors -- 2.7.3
From: Yazen Ghannam <Yazen.Ghannam@amd.com> Use X86_FEATURE_SMCA when detecting if SMCA is available instead of directly using CPUID 0x80000007_EBX. Signed-off-by: Yazen Ghannam <Yazen.Ghannam@amd.com> Cc: <x86@kernel.org> Cc: Tony Luck <tony.luck@intel.com> Cc: linux-edac <linux-edac@vger.kernel.org> Link: http://lkml.kernel.org/r/1462914639-29513-5-git-send-email-Yazen.Ghannam@amd.com Signed-off-by: Borislav Petkov <bp@suse.de> --- drivers/edac/mce_amd.c | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) diff --git a/drivers/edac/mce_amd.c b/drivers/edac/mce_amd.c index 49768c08ac07..9b6800a79c7f 100644 --- a/drivers/edac/mce_amd.c +++ b/drivers/edac/mce_amd.c @@ -1052,7 +1052,6 @@ int amd_decode_mce(struct notifier_block *nb, unsigned long val, void *data) struct mce *m = (struct mce *)data; struct cpuinfo_x86 *c = &cpu_data(m->extcpu); int ecc; - u32 ebx = cpuid_ebx(0x80000007); if (amd_filter_mce(m)) return NOTIFY_STOP; @@ -1075,7 +1074,7 @@ int amd_decode_mce(struct notifier_block *nb, unsigned long val, void *data) ((m->status & MCI_STATUS_DEFERRED) ? "Deferred" : "-"), ((m->status & MCI_STATUS_POISON) ? "Poison" : "-")); - if (!!(ebx & BIT(3))) { + if (boot_cpu_has(X86_FEATURE_SMCA)) { u32 low, high; u32 addr = MSR_AMD64_SMCA_MCx_CONFIG(m->bank); @@ -1094,7 +1093,7 @@ int amd_decode_mce(struct notifier_block *nb, unsigned long val, void *data) if (m->status & MCI_STATUS_ADDRV) pr_emerg(HW_ERR "MC%d Error Address: 0x%016llx\n", m->bank, m->addr); - if (!!(ebx & BIT(3))) { + if (boot_cpu_has(X86_FEATURE_SMCA)) { decode_smca_errors(m); goto err_code; } @@ -1149,7 +1148,6 @@ static struct notifier_block amd_mce_dec_nb = { static int __init mce_amd_init(void) { struct cpuinfo_x86 *c = &boot_cpu_data; - u32 ebx; if (c->x86_vendor != X86_VENDOR_AMD) return -ENODEV; @@ -1205,9 +1203,8 @@ static int __init mce_amd_init(void) break; case 0x17: - ebx = cpuid_ebx(0x80000007); xec_mask = 0x3f; - if (!(ebx & BIT(3))) { + if (!boot_cpu_has(X86_FEATURE_SMCA)) { printk(KERN_WARNING "Decoding supported only on Scalable MCA processors.\n"); goto err_out; } -- 2.7.3
From: Yazen Ghannam <Yazen.Ghannam@amd.com> Use SMCA MSRs when writing to MCA_{STATUS,ADDR,MISC} and MCA_DE{STAT,ADDR} when injecting Deferred Errors on SMCA platforms. Signed-off-by: Yazen Ghannam <Yazen.Ghannam@amd.com> Cc: Aravind Gopalakrishnan <aravindksg.lkml@gmail.com> Cc: Tony Luck <tony.luck@intel.com> Cc: linux-edac <linux-edac@vger.kernel.org> Cc: x86-ml <x86@kernel.org> Link: http://lkml.kernel.org/r/1462914639-29513-6-git-send-email-Yazen.Ghannam@amd.com Signed-off-by: Borislav Petkov <bp@suse.de> --- arch/x86/ras/mce_amd_inj.c | 31 +++++++++++++++++++++++++------ 1 file changed, 25 insertions(+), 6 deletions(-) diff --git a/arch/x86/ras/mce_amd_inj.c b/arch/x86/ras/mce_amd_inj.c index 9e02dcaef683..e69f4701a076 100644 --- a/arch/x86/ras/mce_amd_inj.c +++ b/arch/x86/ras/mce_amd_inj.c @@ -290,14 +290,33 @@ static void do_inject(void) wrmsr_on_cpu(cpu, MSR_IA32_MCG_STATUS, (u32)mcg_status, (u32)(mcg_status >> 32)); - wrmsr_on_cpu(cpu, MSR_IA32_MCx_STATUS(b), - (u32)i_mce.status, (u32)(i_mce.status >> 32)); + if (boot_cpu_has(X86_FEATURE_SMCA)) { + if (inj_type == DFR_INT_INJ) { + wrmsr_on_cpu(cpu, MSR_AMD64_SMCA_MCx_DESTAT(b), + (u32)i_mce.status, (u32)(i_mce.status >> 32)); + + wrmsr_on_cpu(cpu, MSR_AMD64_SMCA_MCx_DEADDR(b), + (u32)i_mce.addr, (u32)(i_mce.addr >> 32)); + } else { + wrmsr_on_cpu(cpu, MSR_AMD64_SMCA_MCx_STATUS(b), + (u32)i_mce.status, (u32)(i_mce.status >> 32)); + + wrmsr_on_cpu(cpu, MSR_AMD64_SMCA_MCx_ADDR(b), + (u32)i_mce.addr, (u32)(i_mce.addr >> 32)); + } + + wrmsr_on_cpu(cpu, MSR_AMD64_SMCA_MCx_MISC(b), + (u32)i_mce.misc, (u32)(i_mce.misc >> 32)); + } else { + wrmsr_on_cpu(cpu, MSR_IA32_MCx_STATUS(b), + (u32)i_mce.status, (u32)(i_mce.status >> 32)); - wrmsr_on_cpu(cpu, MSR_IA32_MCx_ADDR(b), - (u32)i_mce.addr, (u32)(i_mce.addr >> 32)); + wrmsr_on_cpu(cpu, MSR_IA32_MCx_ADDR(b), + (u32)i_mce.addr, (u32)(i_mce.addr >> 32)); - wrmsr_on_cpu(cpu, MSR_IA32_MCx_MISC(b), - (u32)i_mce.misc, (u32)(i_mce.misc >> 32)); + wrmsr_on_cpu(cpu, MSR_IA32_MCx_MISC(b), + (u32)i_mce.misc, (u32)(i_mce.misc >> 32)); + } toggle_hw_mce_inject(cpu, false); -- 2.7.3
Commit-ID: 34102009580a047c02b21f089f7fc7f65e605887 Gitweb: http://git.kernel.org/tip/34102009580a047c02b21f089f7fc7f65e605887 Author: Yazen Ghannam <Yazen.Ghannam@amd.com> AuthorDate: Wed, 11 May 2016 14:58:23 +0200 Committer: Ingo Molnar <mingo@kernel.org> CommitDate: Thu, 12 May 2016 09:08:19 +0200 x86/mce/AMD: Log Deferred Errors using SMCA MCA_DE{STAT,ADDR} registers Scalable MCA provides new registers for all banks for logging deferred errors: MCA_DESTAT and MCA_DEADDR. Deferred errors are always logged to these registers. Update the AMD deferred error handler to use these registers, if available. Signed-off-by: Yazen Ghannam <Yazen.Ghannam@amd.com> [ Sanity-check __log_error() args, massage a bit. ] Signed-off-by: Borislav Petkov <bp@suse.de> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Aravind Gopalakrishnan <aravindksg.lkml@gmail.com> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Gerst <brgerst@gmail.com> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Tony Luck <tony.luck@intel.com> Cc: linux-edac <linux-edac@vger.kernel.org> Link: http://lkml.kernel.org/r/1462971509-3856-2-git-send-email-bp@alien8.de Signed-off-by: Ingo Molnar <mingo@kernel.org> --- arch/x86/include/asm/mce.h | 4 ++++ arch/x86/kernel/cpu/mcheck/mce_amd.c | 32 ++++++++++++++++++++++++-------- 2 files changed, 28 insertions(+), 8 deletions(-) diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h index 53ab697..8bf766e 100644 --- a/arch/x86/include/asm/mce.h +++ b/arch/x86/include/asm/mce.h @@ -110,6 +110,8 @@ #define MSR_AMD64_SMCA_MC0_MISC0 0xc0002003 #define MSR_AMD64_SMCA_MC0_CONFIG 0xc0002004 #define MSR_AMD64_SMCA_MC0_IPID 0xc0002005 +#define MSR_AMD64_SMCA_MC0_DESTAT 0xc0002008 +#define MSR_AMD64_SMCA_MC0_DEADDR 0xc0002009 #define MSR_AMD64_SMCA_MC0_MISC1 0xc000200a #define MSR_AMD64_SMCA_MCx_CTL(x) (MSR_AMD64_SMCA_MC0_CTL + 0x10*(x)) #define MSR_AMD64_SMCA_MCx_STATUS(x) (MSR_AMD64_SMCA_MC0_STATUS + 0x10*(x)) @@ -117,6 +119,8 @@ #define MSR_AMD64_SMCA_MCx_MISC(x) (MSR_AMD64_SMCA_MC0_MISC0 + 0x10*(x)) #define MSR_AMD64_SMCA_MCx_CONFIG(x) (MSR_AMD64_SMCA_MC0_CONFIG + 0x10*(x)) #define MSR_AMD64_SMCA_MCx_IPID(x) (MSR_AMD64_SMCA_MC0_IPID + 0x10*(x)) +#define MSR_AMD64_SMCA_MCx_DESTAT(x) (MSR_AMD64_SMCA_MC0_DESTAT + 0x10*(x)) +#define MSR_AMD64_SMCA_MCx_DEADDR(x) (MSR_AMD64_SMCA_MC0_DEADDR + 0x10*(x)) #define MSR_AMD64_SMCA_MCx_MISCy(x, y) ((MSR_AMD64_SMCA_MC0_MISC1 + y) + (0x10*(x))) /* diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c index c594680..d1b1e62 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_amd.c +++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c @@ -430,12 +430,23 @@ void mce_amd_feature_init(struct cpuinfo_x86 *c) deferred_error_interrupt_enable(c); } -static void __log_error(unsigned int bank, bool threshold_err, u64 misc) +static void +__log_error(unsigned int bank, bool deferred_err, bool threshold_err, u64 misc) { + u32 msr_status = msr_ops.status(bank); + u32 msr_addr = msr_ops.addr(bank); struct mce m; u64 status; - rdmsrl(msr_ops.status(bank), status); + WARN_ON_ONCE(deferred_err && threshold_err); + + if (deferred_err && mce_flags.smca) { + msr_status = MSR_AMD64_SMCA_MCx_DESTAT(bank); + msr_addr = MSR_AMD64_SMCA_MCx_DEADDR(bank); + } + + rdmsrl(msr_status, status); + if (!(status & MCI_STATUS_VAL)) return; @@ -448,10 +459,11 @@ static void __log_error(unsigned int bank, bool threshold_err, u64 misc) m.misc = misc; if (m.status & MCI_STATUS_ADDRV) - rdmsrl(msr_ops.addr(bank), m.addr); + rdmsrl(msr_addr, m.addr); mce_log(&m); - wrmsrl(msr_ops.status(bank), 0); + + wrmsrl(msr_status, 0); } static inline void __smp_deferred_error_interrupt(void) @@ -479,17 +491,21 @@ asmlinkage __visible void smp_trace_deferred_error_interrupt(void) /* APIC interrupt handler for deferred errors */ static void amd_deferred_error_interrupt(void) { - u64 status; unsigned int bank; + u32 msr_status; + u64 status; for (bank = 0; bank < mca_cfg.banks; ++bank) { - rdmsrl(msr_ops.status(bank), status); + msr_status = (mce_flags.smca) ? MSR_AMD64_SMCA_MCx_DESTAT(bank) + : msr_ops.status(bank); + + rdmsrl(msr_status, status); if (!(status & MCI_STATUS_VAL) || !(status & MCI_STATUS_DEFERRED)) continue; - __log_error(bank, false, 0); + __log_error(bank, true, false, 0); break; } } @@ -544,7 +560,7 @@ static void amd_threshold_interrupt(void) return; log: - __log_error(bank, true, ((u64)high << 32) | low); + __log_error(bank, false, true, ((u64)high << 32) | low); } /*
Commit-ID: 32544f060326bffa60dade49ce4595652df4d3ab Gitweb: http://git.kernel.org/tip/32544f060326bffa60dade49ce4595652df4d3ab Author: Yazen Ghannam <Yazen.Ghannam@amd.com> AuthorDate: Wed, 11 May 2016 14:58:24 +0200 Committer: Ingo Molnar <mingo@kernel.org> CommitDate: Thu, 12 May 2016 09:08:20 +0200 x86/mce/AMD: Disable LogDeferredInMcaStat for SMCA systems Disable Deferred Error logging in MCA_{STATUS,ADDR} additionally for SMCA systems as this information will retrieved from MCA_DE{STAT,ADDR} on those systems. Signed-off-by: Yazen Ghannam <Yazen.Ghannam@amd.com> [ Simplify, drop SMCA_MCAX_EN_OFF define too. ] Signed-off-by: Borislav Petkov <bp@suse.de> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Aravind Gopalakrishnan <aravindksg.lkml@gmail.com> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Gerst <brgerst@gmail.com> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Tony Luck <tony.luck@intel.com> Cc: linux-edac <linux-edac@vger.kernel.org> Link: http://lkml.kernel.org/r/1462971509-3856-3-git-send-email-bp@alien8.de Signed-off-by: Ingo Molnar <mingo@kernel.org> --- arch/x86/kernel/cpu/mcheck/mce_amd.c | 38 +++++++++++++++++++++++++++--------- 1 file changed, 29 insertions(+), 9 deletions(-) diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c index d1b1e62..527ddae 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_amd.c +++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c @@ -54,14 +54,6 @@ /* Threshold LVT offset is at MSR0xC0000410[15:12] */ #define SMCA_THR_LVT_OFF 0xF000 -/* - * OS is required to set the MCAX bit to acknowledge that it is now using the - * new MSR ranges and new registers under each bank. It also means that the OS - * will configure deferred errors in the new MCx_CONFIG register. If the bit is - * not set, uncorrectable errors will cause a system panic. - */ -#define SMCA_MCAX_EN_OFF 0x1 - static const char * const th_names[] = { "load_store", "insn_fetch", @@ -374,7 +366,35 @@ prepare_threshold_block(unsigned int bank, unsigned int block, u32 addr, u32 smca_addr = MSR_AMD64_SMCA_MCx_CONFIG(bank); if (!rdmsr_safe(smca_addr, &smca_low, &smca_high)) { - smca_high |= SMCA_MCAX_EN_OFF; + /* + * OS is required to set the MCAX bit to acknowledge + * that it is now using the new MSR ranges and new + * registers under each bank. It also means that the OS + * will configure deferred errors in the new MCx_CONFIG + * register. If the bit is not set, uncorrectable errors + * will cause a system panic. + * + * MCA_CONFIG[MCAX] is bit 32 (0 in the high portion of + * the MSR.) + */ + smca_high |= BIT(0); + + /* + * SMCA logs Deferred Error information in + * MCA_DE{STAT,ADDR} registers with the option of + * additionally logging to MCA_{STATUS,ADDR} if + * MCA_CONFIG[LogDeferredInMcaStat] is set. + * + * This bit is usually set by BIOS to retain the old + * behavior for OSes that don't use the new registers. + * Linux supports the new registers so let's disable + * that additional logging here. + * + * MCA_CONFIG[LogDeferredInMcaStat] is bit 34 (bit 2 in + * the high portion of the MSR). + */ + smca_high &= ~BIT(2); + wrmsr(smca_addr, smca_low, smca_high); }
Commit-ID: e128b4f4833cc1e0ce46dfb978763b260f166188 Gitweb: http://git.kernel.org/tip/e128b4f4833cc1e0ce46dfb978763b260f166188 Author: Borislav Petkov <bp@suse.de> AuthorDate: Wed, 11 May 2016 14:58:25 +0200 Committer: Ingo Molnar <mingo@kernel.org> CommitDate: Thu, 12 May 2016 09:08:21 +0200 x86/mce/AMD: Save an indentation level in prepare_threshold_block() Do the !SMCA work first and then save us an indentation level for the SMCA code. No functionality change. Signed-off-by: Borislav Petkov <bp@suse.de> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Aravind Gopalakrishnan <aravindksg.lkml@gmail.com> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Gerst <brgerst@gmail.com> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Tony Luck <tony.luck@intel.com> Cc: Yazen Ghannam <Yazen.Ghannam@amd.com> Cc: linux-edac <linux-edac@vger.kernel.org> Link: http://lkml.kernel.org/r/1462971509-3856-4-git-send-email-bp@alien8.de Signed-off-by: Ingo Molnar <mingo@kernel.org> --- arch/x86/kernel/cpu/mcheck/mce_amd.c | 78 ++++++++++++++++++------------------ 1 file changed, 38 insertions(+), 40 deletions(-) diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c index 527ddae..10b0661 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_amd.c +++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c @@ -343,6 +343,7 @@ prepare_threshold_block(unsigned int bank, unsigned int block, u32 addr, int offset, u32 misc_high) { unsigned int cpu = smp_processor_id(); + u32 smca_low, smca_high, smca_addr; struct threshold_block b; int new; @@ -361,52 +362,49 @@ prepare_threshold_block(unsigned int bank, unsigned int block, u32 addr, b.interrupt_enable = 1; - if (mce_flags.smca) { - u32 smca_low, smca_high; - u32 smca_addr = MSR_AMD64_SMCA_MCx_CONFIG(bank); - - if (!rdmsr_safe(smca_addr, &smca_low, &smca_high)) { - /* - * OS is required to set the MCAX bit to acknowledge - * that it is now using the new MSR ranges and new - * registers under each bank. It also means that the OS - * will configure deferred errors in the new MCx_CONFIG - * register. If the bit is not set, uncorrectable errors - * will cause a system panic. - * - * MCA_CONFIG[MCAX] is bit 32 (0 in the high portion of - * the MSR.) - */ - smca_high |= BIT(0); + if (!mce_flags.smca) { + new = (misc_high & MASK_LVTOFF_HI) >> 20; + goto set_offset; + } - /* - * SMCA logs Deferred Error information in - * MCA_DE{STAT,ADDR} registers with the option of - * additionally logging to MCA_{STATUS,ADDR} if - * MCA_CONFIG[LogDeferredInMcaStat] is set. - * - * This bit is usually set by BIOS to retain the old - * behavior for OSes that don't use the new registers. - * Linux supports the new registers so let's disable - * that additional logging here. - * - * MCA_CONFIG[LogDeferredInMcaStat] is bit 34 (bit 2 in - * the high portion of the MSR). - */ - smca_high &= ~BIT(2); + smca_addr = MSR_AMD64_SMCA_MCx_CONFIG(bank); - wrmsr(smca_addr, smca_low, smca_high); - } + if (!rdmsr_safe(smca_addr, &smca_low, &smca_high)) { + /* + * OS is required to set the MCAX bit to acknowledge that it is + * now using the new MSR ranges and new registers under each + * bank. It also means that the OS will configure deferred + * errors in the new MCx_CONFIG register. If the bit is not set, + * uncorrectable errors will cause a system panic. + * + * MCA_CONFIG[MCAX] is bit 32 (0 in the high portion of the MSR.) + */ + smca_high |= BIT(0); - /* Gather LVT offset for thresholding: */ - if (rdmsr_safe(MSR_CU_DEF_ERR, &smca_low, &smca_high)) - goto out; + /* + * SMCA logs Deferred Error information in MCA_DE{STAT,ADDR} + * registers with the option of additionally logging to + * MCA_{STATUS,ADDR} if MCA_CONFIG[LogDeferredInMcaStat] is set. + * + * This bit is usually set by BIOS to retain the old behavior + * for OSes that don't use the new registers. Linux supports the + * new registers so let's disable that additional logging here. + * + * MCA_CONFIG[LogDeferredInMcaStat] is bit 34 (bit 2 in the high + * portion of the MSR). + */ + smca_high &= ~BIT(2); - new = (smca_low & SMCA_THR_LVT_OFF) >> 12; - } else { - new = (misc_high & MASK_LVTOFF_HI) >> 20; + wrmsr(smca_addr, smca_low, smca_high); } + /* Gather LVT offset for thresholding: */ + if (rdmsr_safe(MSR_CU_DEF_ERR, &smca_low, &smca_high)) + goto out; + + new = (smca_low & SMCA_THR_LVT_OFF) >> 12; + +set_offset: offset = setup_APIC_mce_threshold(offset, new); if ((offset == new) && (mce_threshold_vector != amd_threshold_interrupt))
Commit-ID: 71faad43060d3d2040583635fbf7d1bdb3d04118 Gitweb: http://git.kernel.org/tip/71faad43060d3d2040583635fbf7d1bdb3d04118 Author: Yazen Ghannam <Yazen.Ghannam@amd.com> AuthorDate: Wed, 11 May 2016 14:58:26 +0200 Committer: Ingo Molnar <mingo@kernel.org> CommitDate: Thu, 12 May 2016 09:08:22 +0200 x86/cpu: Add detection of AMD RAS Capabilities Add a new CPUID leaf to hold the contents of CPUID 0x80000007_EBX (RasCap). Define bits that are currently in use: Bit 0: McaOverflowRecov Bit 1: SUCCOR Bit 3: ScalableMca Signed-off-by: Yazen Ghannam <Yazen.Ghannam@amd.com> [ Shorten comment. ] Signed-off-by: Borislav Petkov <bp@suse.de> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Gerst <brgerst@gmail.com> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Tony Luck <tony.luck@intel.com> Cc: linux-edac <linux-edac@vger.kernel.org> Link: http://lkml.kernel.org/r/1462971509-3856-5-git-send-email-bp@alien8.de Signed-off-by: Ingo Molnar <mingo@kernel.org> --- arch/x86/include/asm/cpufeature.h | 1 + arch/x86/include/asm/cpufeatures.h | 7 ++++++- arch/x86/kernel/cpu/common.c | 10 +++++++--- 3 files changed, 14 insertions(+), 4 deletions(-) diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index 3636ec0..53ac9bb 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -27,6 +27,7 @@ enum cpuid_leafs CPUID_6_EAX, CPUID_8000_000A_EDX, CPUID_7_ECX, + CPUID_8000_0007_EBX, }; #ifdef CONFIG_X86_FEATURE_NAMES diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 8f9afef..d4e5018 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -12,7 +12,7 @@ /* * Defines x86 CPU feature bits */ -#define NCAPINTS 17 /* N 32-bit words worth of info */ +#define NCAPINTS 18 /* N 32-bit words worth of info */ #define NBUGINTS 1 /* N 32-bit bug flags */ /* @@ -280,6 +280,11 @@ #define X86_FEATURE_PKU (16*32+ 3) /* Protection Keys for Userspace */ #define X86_FEATURE_OSPKE (16*32+ 4) /* OS Protection Keys Enable */ +/* AMD-defined CPU features, CPUID level 0x80000007 (ebx), word 17 */ +#define X86_FEATURE_OVERFLOW_RECOV (17*32+0) /* MCA overflow recovery support */ +#define X86_FEATURE_SUCCOR (17*32+1) /* Uncorrectable error containment and recovery */ +#define X86_FEATURE_SMCA (17*32+3) /* Scalable MCA */ + /* * BUG word(s) */ diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 8394b3d..dbc6f06 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -717,6 +717,13 @@ void get_cpu_cap(struct cpuinfo_x86 *c) } } + if (c->extended_cpuid_level >= 0x80000007) { + cpuid(0x80000007, &eax, &ebx, &ecx, &edx); + + c->x86_capability[CPUID_8000_0007_EBX] = ebx; + c->x86_power = edx; + } + if (c->extended_cpuid_level >= 0x80000008) { cpuid(0x80000008, &eax, &ebx, &ecx, &edx); @@ -729,9 +736,6 @@ void get_cpu_cap(struct cpuinfo_x86 *c) c->x86_phys_bits = 36; #endif - if (c->extended_cpuid_level >= 0x80000007) - c->x86_power = cpuid_edx(0x80000007); - if (c->extended_cpuid_level >= 0x8000000a) c->x86_capability[CPUID_8000_000A_EDX] = cpuid_edx(0x8000000a);
Commit-ID: 14cddfd5308b0880abd6e58b6660f5cc8e8020f9 Gitweb: http://git.kernel.org/tip/14cddfd5308b0880abd6e58b6660f5cc8e8020f9 Author: Yazen Ghannam <Yazen.Ghannam@amd.com> AuthorDate: Wed, 11 May 2016 14:58:27 +0200 Committer: Ingo Molnar <mingo@kernel.org> CommitDate: Thu, 12 May 2016 09:08:22 +0200 x86/mce: Update AMD mcheck init to use cpu_has() facilities Use cpu_has() facilities to find available RAS features rather than directly reading CPUID 0x80000007_EBX. Signed-off-by: Yazen Ghannam <Yazen.Ghannam@amd.com> [ Use the struct cpuinfo_x86 ptr instead. ] Signed-off-by: Borislav Petkov <bp@suse.de> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Gerst <brgerst@gmail.com> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Tony Luck <tony.luck@intel.com> Cc: linux-edac <linux-edac@vger.kernel.org> Link: http://lkml.kernel.org/r/1462971509-3856-6-git-send-email-bp@alien8.de Signed-off-by: Ingo Molnar <mingo@kernel.org> --- arch/x86/kernel/cpu/mcheck/mce.c | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index aeda446..92e5e37 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -1683,11 +1683,9 @@ static void __mcheck_cpu_init_vendor(struct cpuinfo_x86 *c) break; case X86_VENDOR_AMD: { - u32 ebx = cpuid_ebx(0x80000007); - - mce_flags.overflow_recov = !!(ebx & BIT(0)); - mce_flags.succor = !!(ebx & BIT(1)); - mce_flags.smca = !!(ebx & BIT(3)); + mce_flags.overflow_recov = !!cpu_has(c, X86_FEATURE_OVERFLOW_RECOV); + mce_flags.succor = !!cpu_has(c, X86_FEATURE_SUCCOR); + mce_flags.smca = !!cpu_has(c, X86_FEATURE_SMCA); /* * Install proper ops for Scalable MCA enabled processors
Commit-ID: a348ed83d9efe8c11ecc85c15d7329825b97431e Gitweb: http://git.kernel.org/tip/a348ed83d9efe8c11ecc85c15d7329825b97431e Author: Yazen Ghannam <Yazen.Ghannam@amd.com> AuthorDate: Wed, 11 May 2016 14:58:28 +0200 Committer: Ingo Molnar <mingo@kernel.org> CommitDate: Thu, 12 May 2016 09:08:23 +0200 EDAC, mce_amd: Detect SMCA using X86_FEATURE_SMCA Use X86_FEATURE_SMCA when detecting if SMCA is available instead of directly using CPUID 0x80000007_EBX. Signed-off-by: Yazen Ghannam <Yazen.Ghannam@amd.com> Signed-off-by: Borislav Petkov <bp@suse.de> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Gerst <brgerst@gmail.com> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Tony Luck <tony.luck@intel.com> Cc: linux-edac <linux-edac@vger.kernel.org> Link: http://lkml.kernel.org/r/1462971509-3856-7-git-send-email-bp@alien8.de Signed-off-by: Ingo Molnar <mingo@kernel.org> --- drivers/edac/mce_amd.c | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) diff --git a/drivers/edac/mce_amd.c b/drivers/edac/mce_amd.c index 49768c0..9b6800a 100644 --- a/drivers/edac/mce_amd.c +++ b/drivers/edac/mce_amd.c @@ -1052,7 +1052,6 @@ int amd_decode_mce(struct notifier_block *nb, unsigned long val, void *data) struct mce *m = (struct mce *)data; struct cpuinfo_x86 *c = &cpu_data(m->extcpu); int ecc; - u32 ebx = cpuid_ebx(0x80000007); if (amd_filter_mce(m)) return NOTIFY_STOP; @@ -1075,7 +1074,7 @@ int amd_decode_mce(struct notifier_block *nb, unsigned long val, void *data) ((m->status & MCI_STATUS_DEFERRED) ? "Deferred" : "-"), ((m->status & MCI_STATUS_POISON) ? "Poison" : "-")); - if (!!(ebx & BIT(3))) { + if (boot_cpu_has(X86_FEATURE_SMCA)) { u32 low, high; u32 addr = MSR_AMD64_SMCA_MCx_CONFIG(m->bank); @@ -1094,7 +1093,7 @@ int amd_decode_mce(struct notifier_block *nb, unsigned long val, void *data) if (m->status & MCI_STATUS_ADDRV) pr_emerg(HW_ERR "MC%d Error Address: 0x%016llx\n", m->bank, m->addr); - if (!!(ebx & BIT(3))) { + if (boot_cpu_has(X86_FEATURE_SMCA)) { decode_smca_errors(m); goto err_code; } @@ -1149,7 +1148,6 @@ static struct notifier_block amd_mce_dec_nb = { static int __init mce_amd_init(void) { struct cpuinfo_x86 *c = &boot_cpu_data; - u32 ebx; if (c->x86_vendor != X86_VENDOR_AMD) return -ENODEV; @@ -1205,9 +1203,8 @@ static int __init mce_amd_init(void) break; case 0x17: - ebx = cpuid_ebx(0x80000007); xec_mask = 0x3f; - if (!(ebx & BIT(3))) { + if (!boot_cpu_has(X86_FEATURE_SMCA)) { printk(KERN_WARNING "Decoding supported only on Scalable MCA processors.\n"); goto err_out; }
Commit-ID: 754a92305980b1fecffe033dd3fdc49c37f8e4b0 Gitweb: http://git.kernel.org/tip/754a92305980b1fecffe033dd3fdc49c37f8e4b0 Author: Yazen Ghannam <Yazen.Ghannam@amd.com> AuthorDate: Wed, 11 May 2016 14:58:29 +0200 Committer: Ingo Molnar <mingo@kernel.org> CommitDate: Thu, 12 May 2016 09:08:23 +0200 x86/RAS: Add SMCA support to AMD Error Injector Use SMCA MSRs when writing to MCA_{STATUS,ADDR,MISC} and MCA_DE{STAT,ADDR} when injecting Deferred Errors on SMCA platforms. Signed-off-by: Yazen Ghannam <Yazen.Ghannam@amd.com> Signed-off-by: Borislav Petkov <bp@suse.de> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Aravind Gopalakrishnan <aravindksg.lkml@gmail.com> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Gerst <brgerst@gmail.com> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Tony Luck <tony.luck@intel.com> Cc: linux-edac <linux-edac@vger.kernel.org> Link: http://lkml.kernel.org/r/1462971509-3856-8-git-send-email-bp@alien8.de Signed-off-by: Ingo Molnar <mingo@kernel.org> --- arch/x86/ras/mce_amd_inj.c | 31 +++++++++++++++++++++++++------ 1 file changed, 25 insertions(+), 6 deletions(-) diff --git a/arch/x86/ras/mce_amd_inj.c b/arch/x86/ras/mce_amd_inj.c index 9e02dca..e69f470 100644 --- a/arch/x86/ras/mce_amd_inj.c +++ b/arch/x86/ras/mce_amd_inj.c @@ -290,14 +290,33 @@ static void do_inject(void) wrmsr_on_cpu(cpu, MSR_IA32_MCG_STATUS, (u32)mcg_status, (u32)(mcg_status >> 32)); - wrmsr_on_cpu(cpu, MSR_IA32_MCx_STATUS(b), - (u32)i_mce.status, (u32)(i_mce.status >> 32)); + if (boot_cpu_has(X86_FEATURE_SMCA)) { + if (inj_type == DFR_INT_INJ) { + wrmsr_on_cpu(cpu, MSR_AMD64_SMCA_MCx_DESTAT(b), + (u32)i_mce.status, (u32)(i_mce.status >> 32)); + + wrmsr_on_cpu(cpu, MSR_AMD64_SMCA_MCx_DEADDR(b), + (u32)i_mce.addr, (u32)(i_mce.addr >> 32)); + } else { + wrmsr_on_cpu(cpu, MSR_AMD64_SMCA_MCx_STATUS(b), + (u32)i_mce.status, (u32)(i_mce.status >> 32)); + + wrmsr_on_cpu(cpu, MSR_AMD64_SMCA_MCx_ADDR(b), + (u32)i_mce.addr, (u32)(i_mce.addr >> 32)); + } + + wrmsr_on_cpu(cpu, MSR_AMD64_SMCA_MCx_MISC(b), + (u32)i_mce.misc, (u32)(i_mce.misc >> 32)); + } else { + wrmsr_on_cpu(cpu, MSR_IA32_MCx_STATUS(b), + (u32)i_mce.status, (u32)(i_mce.status >> 32)); - wrmsr_on_cpu(cpu, MSR_IA32_MCx_ADDR(b), - (u32)i_mce.addr, (u32)(i_mce.addr >> 32)); + wrmsr_on_cpu(cpu, MSR_IA32_MCx_ADDR(b), + (u32)i_mce.addr, (u32)(i_mce.addr >> 32)); - wrmsr_on_cpu(cpu, MSR_IA32_MCx_MISC(b), - (u32)i_mce.misc, (u32)(i_mce.misc >> 32)); + wrmsr_on_cpu(cpu, MSR_IA32_MCx_MISC(b), + (u32)i_mce.misc, (u32)(i_mce.misc >> 32)); + } toggle_hw_mce_inject(cpu, false);