From 2117654e806c08c343e3d0567bbedf33eab040c8 Mon Sep 17 00:00:00 2001 From: Smita Koralahalli Date: Tue, 6 Dec 2022 11:36:06 -0600 Subject: [PATCH 1/3] x86/mce: Define a function to extract ErrorAddr from MCA_ADDR Move MCA_ADDR[ErrorAddr] extraction into a separate helper function. This will be further refactored to support extended ErrorAddr bits in MCA_ADDR in newer AMD CPUs. [ bp: Massage. ] Signed-off-by: Smita Koralahalli Signed-off-by: Borislav Petkov Signed-off-by: Borislav Petkov (AMD) Reviewed-by: Yazen Ghannam Link: https://lore.kernel.org/all/20220225193342.215780-3-Smita.KoralahalliChannabasappa@amd.com/ --- arch/x86/kernel/cpu/mce/amd.c | 10 +--------- arch/x86/kernel/cpu/mce/core.c | 10 +--------- arch/x86/kernel/cpu/mce/internal.h | 15 +++++++++++++++ 3 files changed, 17 insertions(+), 18 deletions(-) diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c index 10fb5b5c9efa..c6b1fd5a34b8 100644 --- a/arch/x86/kernel/cpu/mce/amd.c +++ b/arch/x86/kernel/cpu/mce/amd.c @@ -736,15 +736,7 @@ static void __log_error(unsigned int bank, u64 status, u64 addr, u64 misc) if (m.status & MCI_STATUS_ADDRV) { m.addr = addr; - /* - * Extract [55:] where lsb is the least significant - * *valid* bit of the address bits. - */ - if (mce_flags.smca) { - u8 lsb = (m.addr >> 56) & 0x3f; - - m.addr &= GENMASK_ULL(55, lsb); - } + smca_extract_err_addr(&m); } if (mce_flags.smca) { diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c index 2c8ec5c71712..d0ade77c41f7 100644 --- a/arch/x86/kernel/cpu/mce/core.c +++ b/arch/x86/kernel/cpu/mce/core.c @@ -633,15 +633,7 @@ static noinstr void mce_read_aux(struct mce *m, int i) m->addr <<= shift; } - /* - * Extract [55:] where lsb is the least significant - * *valid* bit of the address bits. - */ - if (mce_flags.smca) { - u8 lsb = (m->addr >> 56) & 0x3f; - - m->addr &= GENMASK_ULL(55, lsb); - } + smca_extract_err_addr(m); } if (mce_flags.smca) { diff --git a/arch/x86/kernel/cpu/mce/internal.h b/arch/x86/kernel/cpu/mce/internal.h index 7e03f5b7f6bd..6dcb94fe0f65 100644 --- a/arch/x86/kernel/cpu/mce/internal.h +++ b/arch/x86/kernel/cpu/mce/internal.h @@ -189,8 +189,23 @@ extern bool filter_mce(struct mce *m); #ifdef CONFIG_X86_MCE_AMD extern bool amd_filter_mce(struct mce *m); + +/* Extract [55:] where lsb is the LS-*valid* bit of the address bits. */ +static __always_inline void smca_extract_err_addr(struct mce *m) +{ + u8 lsb; + + if (!mce_flags.smca) + return; + + lsb = (m->addr >> 56) & 0x3f; + + m->addr &= GENMASK_ULL(55, lsb); +} + #else static inline bool amd_filter_mce(struct mce *m) { return false; } +static inline void smca_extract_err_addr(struct mce *m) { } #endif #ifdef CONFIG_X86_ANCIENT_MCE From fcd343a285cb41894a7bd02dbd675042d394758d Mon Sep 17 00:00:00 2001 From: Smita Koralahalli Date: Tue, 6 Dec 2022 11:36:07 -0600 Subject: [PATCH 2/3] x86/mce: Add support for Extended Physical Address MCA changes Newer AMD CPUs support more physical address bits. That is, the MCA_ADDR registers on Scalable MCA systems contain the ErrorAddr in bits [56:0] instead of [55:0]. Hence, the existing LSB field from bits [61:56] in MCA_ADDR must be moved around to accommodate the larger ErrorAddr size. MCA_CONFIG[McaLsbInStatusSupported] indicates this change. If set, the LSB field will be found in MCA_STATUS rather than MCA_ADDR. Each logical CPU has unique MCA bank in hardware and is not shared with other logical CPUs. Additionally, on SMCA systems, each feature bit may be different for each bank within same logical CPU. Check for MCA_CONFIG[McaLsbInStatusSupported] for each MCA bank and for each CPU. Additionally, all MCA banks do not support maximum ErrorAddr bits in MCA_ADDR. Some banks might support fewer bits but the remaining bits are marked as reserved. [ Yazen: Rebased and fixed up formatting. bp: Massage comments. ] Signed-off-by: Smita Koralahalli Signed-off-by: Yazen Ghannam Signed-off-by: Borislav Petkov (AMD) Link: https://lore.kernel.org/r/20221206173607.1185907-5-yazen.ghannam@amd.com --- arch/x86/kernel/cpu/mce/amd.c | 2 ++ arch/x86/kernel/cpu/mce/core.c | 8 +------- arch/x86/kernel/cpu/mce/internal.h | 31 +++++++++++++++++++++++++++++- 3 files changed, 33 insertions(+), 8 deletions(-) diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c index c6b1fd5a34b8..23c5072fbbb7 100644 --- a/arch/x86/kernel/cpu/mce/amd.c +++ b/arch/x86/kernel/cpu/mce/amd.c @@ -306,6 +306,8 @@ static void smca_configure(unsigned int bank, unsigned int cpu) if ((low & BIT(5)) && !((high >> 5) & 0x3)) high |= BIT(5); + this_cpu_ptr(mce_banks_array)[bank].lsb_in_status = !!(low & BIT(8)); + wrmsr(smca_config, low, high); } diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c index d0ade77c41f7..626a1c666252 100644 --- a/arch/x86/kernel/cpu/mce/core.c +++ b/arch/x86/kernel/cpu/mce/core.c @@ -67,13 +67,7 @@ DEFINE_PER_CPU(unsigned, mce_exception_count); DEFINE_PER_CPU_READ_MOSTLY(unsigned int, mce_num_banks); -struct mce_bank { - u64 ctl; /* subevents to enable */ - - __u64 init : 1, /* initialise bank? */ - __reserved_1 : 63; -}; -static DEFINE_PER_CPU_READ_MOSTLY(struct mce_bank[MAX_NR_BANKS], mce_banks_array); +DEFINE_PER_CPU_READ_MOSTLY(struct mce_bank[MAX_NR_BANKS], mce_banks_array); #define ATTR_LEN 16 /* One object for each MCE bank, shared by all CPUs */ diff --git a/arch/x86/kernel/cpu/mce/internal.h b/arch/x86/kernel/cpu/mce/internal.h index 6dcb94fe0f65..91a415553c27 100644 --- a/arch/x86/kernel/cpu/mce/internal.h +++ b/arch/x86/kernel/cpu/mce/internal.h @@ -177,6 +177,24 @@ struct mce_vendor_flags { extern struct mce_vendor_flags mce_flags; +struct mce_bank { + /* subevents to enable */ + u64 ctl; + + /* initialise bank? */ + __u64 init : 1, + + /* + * (AMD) MCA_CONFIG[McaLsbInStatusSupported]: When set, this bit indicates + * the LSB field is found in MCA_STATUS and not in MCA_ADDR. + */ + lsb_in_status : 1, + + __reserved_1 : 62; +}; + +DECLARE_PER_CPU_READ_MOSTLY(struct mce_bank[MAX_NR_BANKS], mce_banks_array); + enum mca_msr { MCA_CTL, MCA_STATUS, @@ -190,7 +208,10 @@ extern bool filter_mce(struct mce *m); #ifdef CONFIG_X86_MCE_AMD extern bool amd_filter_mce(struct mce *m); -/* Extract [55:] where lsb is the LS-*valid* bit of the address bits. */ +/* + * If MCA_CONFIG[McaLsbInStatusSupported] is set, extract ErrAddr in bits + * [56:0] of MCA_STATUS, else in bits [55:0] of MCA_ADDR. + */ static __always_inline void smca_extract_err_addr(struct mce *m) { u8 lsb; @@ -198,6 +219,14 @@ static __always_inline void smca_extract_err_addr(struct mce *m) if (!mce_flags.smca) return; + if (this_cpu_ptr(mce_banks_array)[m->bank].lsb_in_status) { + lsb = (m->status >> 24) & 0x3f; + + m->addr &= GENMASK_ULL(56, lsb); + + return; + } + lsb = (m->addr >> 56) & 0x3f; m->addr &= GENMASK_ULL(55, lsb); From 8a01ec97dc066009dd89e43bfcf55644f2dd6d19 Mon Sep 17 00:00:00 2001 From: Tony Luck Date: Mon, 9 Jan 2023 07:29:36 -0800 Subject: [PATCH 3/3] x86/mce: Mask out non-address bits from machine check bank Systems that support various memory encryption schemes (MKTME, TDX, SEV) use high order physical address bits to indicate which key should be used for a specific memory location. When a memory error is reported, some systems may report those key bits in the IA32_MCi_ADDR machine check MSR. The Intel SDM has a footnote for the contents of the address register that says: "Useful bits in this field depend on the address methodology in use when the register state is saved." AMD Processor Programming Reference has a more explicit description of the MCA_ADDR register: "For physical addresses, the most significant bit is given by Core::X86::Cpuid::LongModeInfo[PhysAddrSize]." Add a new #define MCI_ADDR_PHYSADDR for the mask of valid physical address bits within the machine check bank address register. Use this mask for recoverable machine check handling and in the EDAC driver to ignore any key bits that may be present. [ Tony: Based on independent fixes proposed by Fan Du and Isaku Yamahata ] Reported-by: Isaku Yamahata Reported-by: Fan Du Signed-off-by: Tony Luck Signed-off-by: Borislav Petkov (AMD) Reviewed-by: Yazen Ghannam Link: https://lore.kernel.org/r/20230109152936.397862-1-tony.luck@intel.com --- arch/x86/include/asm/mce.h | 3 +++ arch/x86/kernel/cpu/mce/core.c | 14 +++++++++----- drivers/edac/skx_common.c | 2 +- 3 files changed, 13 insertions(+), 6 deletions(-) diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h index 6e986088817d..9646ed6e8c0b 100644 --- a/arch/x86/include/asm/mce.h +++ b/arch/x86/include/asm/mce.h @@ -88,6 +88,9 @@ #define MCI_MISC_ADDR_MEM 3 /* memory address */ #define MCI_MISC_ADDR_GENERIC 7 /* generic */ +/* MCi_ADDR register defines */ +#define MCI_ADDR_PHYSADDR GENMASK_ULL(boot_cpu_data.x86_phys_bits - 1, 0) + /* CTL2 register defines */ #define MCI_CTL2_CMCI_EN BIT_ULL(30) #define MCI_CTL2_CMCI_THRESHOLD_MASK 0x7fffULL diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c index 626a1c666252..7832a69d170e 100644 --- a/arch/x86/kernel/cpu/mce/core.c +++ b/arch/x86/kernel/cpu/mce/core.c @@ -573,7 +573,7 @@ static int uc_decode_notifier(struct notifier_block *nb, unsigned long val, mce->severity != MCE_DEFERRED_SEVERITY) return NOTIFY_DONE; - pfn = mce->addr >> PAGE_SHIFT; + pfn = (mce->addr & MCI_ADDR_PHYSADDR) >> PAGE_SHIFT; if (!memory_failure(pfn, 0)) { set_mce_nospec(pfn); mce->kflags |= MCE_HANDLED_UC; @@ -1294,6 +1294,7 @@ static void kill_me_maybe(struct callback_head *cb) { struct task_struct *p = container_of(cb, struct task_struct, mce_kill_me); int flags = MF_ACTION_REQUIRED; + unsigned long pfn; int ret; p->mce_count = 0; @@ -1302,9 +1303,10 @@ static void kill_me_maybe(struct callback_head *cb) if (!p->mce_ripv) flags |= MF_MUST_KILL; - ret = memory_failure(p->mce_addr >> PAGE_SHIFT, flags); + pfn = (p->mce_addr & MCI_ADDR_PHYSADDR) >> PAGE_SHIFT; + ret = memory_failure(pfn, flags); if (!ret) { - set_mce_nospec(p->mce_addr >> PAGE_SHIFT); + set_mce_nospec(pfn); sync_core(); return; } @@ -1326,11 +1328,13 @@ static void kill_me_maybe(struct callback_head *cb) static void kill_me_never(struct callback_head *cb) { struct task_struct *p = container_of(cb, struct task_struct, mce_kill_me); + unsigned long pfn; p->mce_count = 0; pr_err("Kernel accessed poison in user space at %llx\n", p->mce_addr); - if (!memory_failure(p->mce_addr >> PAGE_SHIFT, 0)) - set_mce_nospec(p->mce_addr >> PAGE_SHIFT); + pfn = (p->mce_addr & MCI_ADDR_PHYSADDR) >> PAGE_SHIFT; + if (!memory_failure(pfn, 0)) + set_mce_nospec(pfn); } static void queue_task_work(struct mce *m, char *msg, void (*func)(struct callback_head *)) diff --git a/drivers/edac/skx_common.c b/drivers/edac/skx_common.c index f0f8e98f6efb..806986f03177 100644 --- a/drivers/edac/skx_common.c +++ b/drivers/edac/skx_common.c @@ -657,7 +657,7 @@ int skx_mce_check_error(struct notifier_block *nb, unsigned long val, memset(&res, 0, sizeof(res)); res.mce = mce; - res.addr = mce->addr; + res.addr = mce->addr & MCI_ADDR_PHYSADDR; /* Try driver decoder first */ if (!(driver_decode && driver_decode(&res))) {