x86/mce: Define amd_mce_usable_address()

Currently, all valid MCA_ADDR values are assumed to be usable on AMD
systems. However, this is not correct in most cases. Notifiers expecting
usable addresses may then operate on inappropriate values.

Define a helper function to do AMD-specific checks for a usable memory
address. List out all known cases.

  [ bp: Tone down the capitalized words. ]

Signed-off-by: Yazen Ghannam <yazen.ghannam@amd.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Link: https://lore.kernel.org/r/20230613141142.36801-3-yazen.ghannam@amd.com

Author: yghannam

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

@@ -746,6 +746,44 @@ bool amd_mce_is_memory_error(struct mce *m)
 		return legacy_mce_is_memory_error(m);
 }
 
+/*
+ * AMD systems do not have an explicit indicator that the value in MCA_ADDR is
+ * a system physical address. Therefore, individual cases need to be detected.
+ * Future cases and checks will be added as needed.
+ *
+ * 1) General case
+ *	a) Assume address is not usable.
+ * 2) Poison errors
+ *	a) Indicated by MCA_STATUS[43]: poison. Defined for all banks except legacy
+ *	   northbridge (bank 4).
+ *	b) Refers to poison consumption in the core. Does not include "no action",
+ *	   "action optional", or "deferred" error severities.
+ *	c) Will include a usable address so that immediate action can be taken.
+ * 3) Northbridge DRAM ECC errors
+ *	a) Reported in legacy bank 4 with extended error code (XEC) 8.
+ *	b) MCA_STATUS[43] is *not* defined as poison in legacy bank 4. Therefore,
+ *	   this bit should not be checked.
+ *
+ * NOTE: SMCA UMC memory errors fall into case #1.
+ */
+bool amd_mce_usable_address(struct mce *m)
+{
+	/* Check special northbridge case 3) first. */
+	if (!mce_flags.smca) {
+		if (legacy_mce_is_memory_error(m))
+			return true;
+		else if (m->bank == 4)
+			return false;
+	}
+
+	/* Check poison bit for all other bank types. */
+	if (m->status & MCI_STATUS_POISON)
+		return true;
+
+	/* Assume address is not usable for all others. */
+	return false;
+}
+
 static void __log_error(unsigned int bank, u64 status, u64 addr, u64 misc)
 {
 	struct mce m;

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

@@ -464,6 +464,9 @@ int mce_usable_address(struct mce *m)
 	if (!(m->status & MCI_STATUS_ADDRV))
 		return 0;
 
+	if (m->cpuvendor == X86_VENDOR_AMD)
+		return amd_mce_usable_address(m);
+
 	/* Checks after this one are Intel/Zhaoxin-specific: */
 	if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL &&
 	    boot_cpu_data.x86_vendor != X86_VENDOR_ZHAOXIN)

arch/x86/kernel/cpu/mce/internal.h

@@ -210,6 +210,7 @@ extern bool filter_mce(struct mce *m);
 
 #ifdef CONFIG_X86_MCE_AMD
 extern bool amd_filter_mce(struct mce *m);
+bool amd_mce_usable_address(struct mce *m);
 
 /*
  * If MCA_CONFIG[McaLsbInStatusSupported] is set, extract ErrAddr in bits
@@ -237,6 +238,7 @@ static __always_inline void smca_extract_err_addr(struct mce *m)
 
 #else
 static inline bool amd_filter_mce(struct mce *m) { return false; }
+static inline bool amd_mce_usable_address(struct mce *m) { return false; }
 static inline void smca_extract_err_addr(struct mce *m) { }
 #endif