x86/mce: Add wrapper for struct mce to export vendor specific info

Currently, exporting new additional machine check error information
involves adding new fields for the same at the end of the struct mce.
This additional information can then be consumed through mcelog or
tracepoint.

However, as new MSRs are being added (and will be added in the future)
by CPU vendors on their newer CPUs with additional machine check error
information to be exported, the size of struct mce will balloon on some
CPUs, unnecessarily, since those fields are vendor-specific. Moreover,
different CPU vendors may export the additional information in varying
sizes.

The problem particularly intensifies since struct mce is exposed to
userspace as part of UAPI. It's bloating through vendor-specific data
should be avoided to limit the information being sent out to userspace.

Add a new structure mce_hw_err to wrap the existing struct mce. The same
will prevent its ballooning since vendor-specifc data, if any, can now be
exported through a union within the wrapper structure and through
__dynamic_array in mce_record tracepoint.

Furthermore, new internal kernel fields can be added to the wrapper
struct without impacting the user space API.

  [ bp: Restore reverse x-mas tree order of function vars declarations. ]

Suggested-by: Borislav Petkov (AMD) <[email protected]>
Signed-off-by: Avadhut Naik <[email protected]>
Signed-off-by: Yazen Ghannam <[email protected]>
Signed-off-by: Borislav Petkov (AMD) <[email protected]>
Reviewed-by: Qiuxu Zhuo <[email protected]>
Link: https://lore.kernel.org/r/[email protected]

Author: Avadhut Naik

arch/x86/include/asm/mce.h

@@ -187,6 +187,16 @@ enum mce_notifier_prios {
 	MCE_PRIO_HIGHEST = MCE_PRIO_CEC
 };
 
+/**
+ * struct mce_hw_err - Hardware Error Record.
+ * @m:		Machine Check record.
+ */
+struct mce_hw_err {
+	struct mce m;
+};
+
+#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 +231,8 @@ static inline int apei_smca_report_x86_error(struct cper_ia_proc_ctx *ctx_info,
 					     u64 lapic_id) { return -EINVAL; }
 #endif
 
-void mce_prep_record(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/kernel/cpu/mce/amd.c

@@ -778,29 +778,30 @@ 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_prep_record(&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);
 	}
 
-	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))
@@ -44,31 +45,33 @@ void apei_mce_report_mem_error(int severity, struct cper_sec_mem_err *mem_err)
 	else
 		lsb = PAGE_SHIFT;
 
-	mce_prep_record(&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));
 	bool apicid_found = false;
+	struct mce_hw_err err;
 	unsigned int cpu;
-	struct mce m;
+	struct mce *m;
 
 	if (!boot_cpu_has(X86_FEATURE_SMCA))
 		return -EINVAL;
@@ -108,18 +111,20 @@ int apei_smca_report_x86_error(struct cper_ia_proc_ctx *ctx_info, u64 lapic_id)
 	if (!apicid_found)
 		return -EINVAL;
 
-	mce_prep_record_common(&m);
-	mce_prep_record_per_cpu(cpu, &m);
+	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;
-	m.status = *i_mce;
-	m.addr = *(i_mce + 1);
-	m.misc = *(i_mce + 2);
+	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);
+	m->ipid = *(i_mce + 4);
+	m->synd = *(i_mce + 5);
 
-	mce_log(&m);
+	mce_log(&err);
 
 	return 0;
 }