Merge tag 'ras_core_for_v6.3_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull RAS updates from Borislav Petkov:

 - Add support for reporting more bits of the physical address on error,
   on newer AMD CPUs

 - Mask out bits which don't belong to the address of the error being
   reported

* tag 'ras_core_for_v6.3_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/mce: Mask out non-address bits from machine check bank
  x86/mce: Add support for Extended Physical Address MCA changes
  x86/mce: Define a function to extract ErrorAddr from MCA_ADDR

Author: torvalds

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

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);
 	}
 
@@ -736,15 +738,7 @@ static void __log_error(unsigned int bank, u64 status, u64 addr, u64 misc)
 	if (m.status & MCI_STATUS_ADDRV) {
 		m.addr = addr;
 
-		/*
-		 * Extract [55:<lsb>] 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) {

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 */
@@ -579,7 +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;
@@ -633,15 +627,7 @@ static noinstr void mce_read_aux(struct mce *m, int i)
 			m->addr <<= shift;
 		}
 
-		/*
-		 * Extract [55:<lsb>] 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) {
@@ -1308,6 +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;
@@ -1316,9 +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;
 	}
@@ -1340,11 +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 *))

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,
@@ -189,8 +207,34 @@ extern bool filter_mce(struct mce *m);
 
 #ifdef CONFIG_X86_MCE_AMD
 extern bool amd_filter_mce(struct mce *m);
+
+/*
+ * 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;
+
+	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);
+}
+
 #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

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))) {