Merge: edac: add FRU Text decoding support

MR: https://gitlab.com/redhat/centos-stream/src/kernel/centos-stream-9/-/merge_requests/5869

JIRA: https://issues.redhat.com/browse/RHEL-52657

Signed-off-by: Aristeu Rozanski <[email protected]>

Approved-by: Rafael Aquini <[email protected]>
Approved-by: Steve Best <[email protected]>
Approved-by: David Arcari <[email protected]>
Approved-by: CKI KWF Bot <[email protected]>

Merged-by: Augusto Caringi <[email protected]>

Author: caringi

arch/x86/include/asm/mce.h

@@ -61,6 +61,7 @@
  *  - TCC bit is present in MCx_STATUS.
  */
 #define MCI_CONFIG_MCAX		0x1
+#define MCI_CONFIG_FRUTEXT	BIT_ULL(9)
 #define MCI_IPID_MCATYPE	0xFFFF0000
 #define MCI_IPID_HWID		0xFFF
 
@@ -122,6 +123,9 @@
 #define MSR_AMD64_SMCA_MC0_DESTAT	0xc0002008
 #define MSR_AMD64_SMCA_MC0_DEADDR	0xc0002009
 #define MSR_AMD64_SMCA_MC0_MISC1	0xc000200a
+/* Registers MISC2 to MISC4 are at offsets B to D. */
+#define MSR_AMD64_SMCA_MC0_SYND1	0xc000200e
+#define MSR_AMD64_SMCA_MC0_SYND2	0xc000200f
 #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))
 #define MSR_AMD64_SMCA_MCx_ADDR(x)	(MSR_AMD64_SMCA_MC0_ADDR + 0x10*(x))
@@ -132,6 +136,8 @@
 #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)))
+#define MSR_AMD64_SMCA_MCx_SYND1(x)	(MSR_AMD64_SMCA_MC0_SYND1 + 0x10*(x))
+#define MSR_AMD64_SMCA_MCx_SYND2(x)	(MSR_AMD64_SMCA_MC0_SYND2 + 0x10*(x))
 
 #define XEC(x, mask)			(((x) >> 16) & mask)
 
@@ -187,6 +193,32 @@ enum mce_notifier_prios {
 	MCE_PRIO_HIGHEST = MCE_PRIO_CEC
 };
 
+/**
+ * struct mce_hw_err - Hardware Error Record.
+ * @m:		Machine Check record.
+ * @vendor:	Vendor-specific error information.
+ *
+ * Vendor-specific fields should not be added to struct mce. Instead, vendors
+ * should export their vendor-specific data through their structure in the
+ * vendor union below.
+ *
+ * AMD's vendor data is parsed by error decoding tools for supplemental error
+ * information. Thus, current offsets of existing fields must be maintained.
+ * Only add new fields at the end of AMD's vendor structure.
+ */
+struct mce_hw_err {
+	struct mce m;
+
+	union vendor_info {
+		struct {
+			u64 synd1;		/* MCA_SYND1 MSR */
+			u64 synd2;		/* MCA_SYND2 MSR */
+		} amd;
+	} vendor;
+};
+
+#define	to_mce_hw_err(mce) container_of(mce, struct mce_hw_err, m)
+
 struct notifier_block;
 extern void mce_register_decode_chain(struct notifier_block *nb);
 extern void mce_unregister_decode_chain(struct notifier_block *nb);
@@ -221,8 +253,8 @@ static inline int apei_smca_report_x86_error(struct cper_ia_proc_ctx *ctx_info,
 					     u64 lapic_id) { return -EINVAL; }
 #endif
 
-void mce_setup(struct mce *m);
-void mce_log(struct mce *m);
+void mce_prep_record(struct mce_hw_err *err);
+void mce_log(struct mce_hw_err *err);
 DECLARE_PER_CPU(struct device *, mce_device);
 
 /* Maximum number of MCA banks per CPU. */

arch/x86/include/uapi/asm/mce.h

@@ -8,7 +8,8 @@
 /*
  * Fields are zero when not available. Also, this struct is shared with
  * userspace mcelog and thus must keep existing fields at current offsets.
- * Only add new fields to the end of the structure
+ * Only add new, shared fields to the end of the structure.
+ * Do not add vendor-specific fields.
  */
 struct mce {
 	__u64 status;		/* Bank's MCi_STATUS MSR */

arch/x86/kernel/cpu/mce/amd.c

@@ -778,29 +778,33 @@ bool amd_mce_usable_address(struct mce *m)
 
 static void __log_error(unsigned int bank, u64 status, u64 addr, u64 misc)
 {
-	struct mce m;
+	struct mce_hw_err err;
+	struct mce *m = &err.m;
 
-	mce_setup(&m);
+	mce_prep_record(&err);
 
-	m.status = status;
-	m.misc   = misc;
-	m.bank   = bank;
-	m.tsc	 = rdtsc();
+	m->status = status;
+	m->misc   = misc;
+	m->bank   = bank;
+	m->tsc	 = rdtsc();
 
-	if (m.status & MCI_STATUS_ADDRV) {
-		m.addr = addr;
+	if (m->status & MCI_STATUS_ADDRV) {
+		m->addr = addr;
 
-		smca_extract_err_addr(&m);
+		smca_extract_err_addr(m);
 	}
 
 	if (mce_flags.smca) {
-		rdmsrl(MSR_AMD64_SMCA_MCx_IPID(bank), m.ipid);
+		rdmsrl(MSR_AMD64_SMCA_MCx_IPID(bank), m->ipid);
 
-		if (m.status & MCI_STATUS_SYNDV)
-			rdmsrl(MSR_AMD64_SMCA_MCx_SYND(bank), m.synd);
+		if (m->status & MCI_STATUS_SYNDV) {
+			rdmsrl(MSR_AMD64_SMCA_MCx_SYND(bank), m->synd);
+			rdmsrl(MSR_AMD64_SMCA_MCx_SYND1(bank), err.vendor.amd.synd1);
+			rdmsrl(MSR_AMD64_SMCA_MCx_SYND2(bank), err.vendor.amd.synd2);
+		}
 	}
 
-	mce_log(&m);
+	mce_log(&err);
 }
 
 DEFINE_IDTENTRY_SYSVEC(sysvec_deferred_error)

arch/x86/kernel/cpu/mce/apei.c

@@ -28,7 +28,8 @@
 
 void apei_mce_report_mem_error(int severity, struct cper_sec_mem_err *mem_err)
 {
-	struct mce m;
+	struct mce_hw_err err;
+	struct mce *m;
 	int lsb;
 
 	if (!(mem_err->validation_bits & CPER_MEM_VALID_PA))
@@ -44,30 +45,33 @@ void apei_mce_report_mem_error(int severity, struct cper_sec_mem_err *mem_err)
 	else
 		lsb = PAGE_SHIFT;
 
-	mce_setup(&m);
-	m.bank = -1;
+	mce_prep_record(&err);
+	m = &err.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) | lsb;
+	m->status = MCI_STATUS_VAL | MCI_STATUS_EN | MCI_STATUS_ADDRV | MCI_STATUS_MISCV | 0x9f;
+	m->misc = (MCI_MISC_ADDR_PHYS << 6) | lsb;
 
 	if (severity >= GHES_SEV_RECOVERABLE)
-		m.status |= MCI_STATUS_UC;
+		m->status |= MCI_STATUS_UC;
 
 	if (severity >= GHES_SEV_PANIC) {
-		m.status |= MCI_STATUS_PCC;
-		m.tsc = rdtsc();
+		m->status |= MCI_STATUS_PCC;
+		m->tsc = rdtsc();
 	}
 
-	m.addr = mem_err->physical_addr;
-	mce_log(&m);
+	m->addr = mem_err->physical_addr;
+	mce_log(&err);
 }
 EXPORT_SYMBOL_GPL(apei_mce_report_mem_error);
 
 int apei_smca_report_x86_error(struct cper_ia_proc_ctx *ctx_info, u64 lapic_id)
 {
 	const u64 *i_mce = ((const u64 *) (ctx_info + 1));
-	unsigned int cpu;
-	struct mce m;
+	unsigned int cpu, num_regs;
+	bool apicid_found = false;
+	struct mce_hw_err err;
+	struct mce *m;
 
 	if (!boot_cpu_has(X86_FEATURE_SMCA))
 		return -EINVAL;
@@ -85,41 +89,86 @@ int apei_smca_report_x86_error(struct cper_ia_proc_ctx *ctx_info, u64 lapic_id)
 		return -EINVAL;
 
 	/*
-	 * The register array size must be large enough to include all the
-	 * SMCA registers which need to be extracted.
-	 *
 	 * The number of registers in the register array is determined by
 	 * Register Array Size/8 as defined in UEFI spec v2.8, sec N.2.4.2.2.
-	 * The register layout is fixed and currently the raw data in the
-	 * register array includes 6 SMCA registers which the kernel can
-	 * extract.
+	 * Sanity-check registers array size.
 	 */
-	if (ctx_info->reg_arr_size < 48)
+	num_regs = ctx_info->reg_arr_size >> 3;
+	if (!num_regs)
 		return -EINVAL;
 
-	mce_setup(&m);
-
-	m.extcpu = -1;
-	m.socketid = -1;
-
 	for_each_possible_cpu(cpu) {
 		if (cpu_data(cpu).topo.initial_apicid == lapic_id) {
-			m.extcpu = cpu;
-			m.socketid = cpu_data(m.extcpu).topo.pkg_id;
+			apicid_found = true;
 			break;
 		}
 	}
 
-	m.apicid = lapic_id;
-	m.bank = (ctx_info->msr_addr >> 4) & 0xFF;
-	m.status = *i_mce;
-	m.addr = *(i_mce + 1);
-	m.misc = *(i_mce + 2);
-	/* Skipping MCA_CONFIG */
-	m.ipid = *(i_mce + 4);
-	m.synd = *(i_mce + 5);
+	if (!apicid_found)
+		return -EINVAL;
+
+	m = &err.m;
+	memset(&err, 0, sizeof(struct mce_hw_err));
+	mce_prep_record_common(m);
+	mce_prep_record_per_cpu(cpu, m);
+
+	m->bank = (ctx_info->msr_addr >> 4) & 0xFF;
+
+	/*
+	 * The SMCA register layout is fixed and includes 16 registers.
+	 * The end of the array may be variable, but the beginning is known.
+	 * Cap the number of registers to expected max (15).
+	 */
+	if (num_regs > 15)
+		num_regs = 15;
+
+	switch (num_regs) {
+	/* MCA_SYND2 */
+	case 15:
+		err.vendor.amd.synd2 = *(i_mce + 14);
+		fallthrough;
+	/* MCA_SYND1 */
+	case 14:
+		err.vendor.amd.synd1 = *(i_mce + 13);
+		fallthrough;
+	/* MCA_MISC4 */
+	case 13:
+	/* MCA_MISC3 */
+	case 12:
+	/* MCA_MISC2 */
+	case 11:
+	/* MCA_MISC1 */
+	case 10:
+	/* MCA_DEADDR */
+	case 9:
+	/* MCA_DESTAT */
+	case 8:
+	/* reserved */
+	case 7:
+	/* MCA_SYND */
+	case 6:
+		m->synd = *(i_mce + 5);
+		fallthrough;
+	/* MCA_IPID */
+	case 5:
+		m->ipid = *(i_mce + 4);
+		fallthrough;
+	/* MCA_CONFIG */
+	case 4:
+	/* MCA_MISC0 */
+	case 3:
+		m->misc = *(i_mce + 2);
+		fallthrough;
+	/* MCA_ADDR */
+	case 2:
+		m->addr = *(i_mce + 1);
+		fallthrough;
+	/* MCA_STATUS */
+	case 1:
+		m->status = *i_mce;
+	}
 
-	mce_log(&m);
+	mce_log(&err);
 
 	return 0;
 }