1 files changed, 36 insertions, 18 deletions

diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index 8a2b8e791314..f7e0c9549bb9 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -42,6 +42,7 @@
 #include <linux/export.h>
 #include <linux/jump_label.h>
 #include <linux/set_memory.h>
+#include <linux/kexec.h>
 
 #include <asm/intel-family.h>
 #include <asm/processor.h>
@@ -315,6 +316,7 @@ static noinstr void mce_panic(const char *msg, struct mce *final, char *exp)
 	struct llist_node *pending;
 	struct mce_evt_llist *l;
 	int apei_err = 0;
+	struct page *p;
 
 	/*
 	 * Allow instrumentation around external facilities usage. Not that it
@@ -370,6 +372,20 @@ static noinstr void mce_panic(const char *msg, struct mce *final, char *exp)
 	if (!fake_panic) {
 		if (panic_timeout == 0)
 			panic_timeout = mca_cfg.panic_timeout;
+
+		/*
+		 * Kdump skips the poisoned page in order to avoid
+		 * touching the error bits again. Poison the page even
+		 * if the error is fatal and the machine is about to
+		 * panic.
+		 */
+		if (kexec_crash_loaded()) {
+			if (final && (final->status & MCI_STATUS_ADDRV)) {
+				p = pfn_to_online_page(final->addr >> PAGE_SHIFT);
+				if (p)
+					SetPageHWPoison(p);
+			}
+		}
 		panic(msg);
 	} else
 		pr_emerg(HW_ERR "Fake kernel panic: %s\n", msg);
@@ -397,13 +413,16 @@ static int msr_to_offset(u32 msr)
 	return -1;
 }
 
-__visible bool ex_handler_rdmsr_fault(const struct exception_table_entry *fixup,
-				      struct pt_regs *regs, int trapnr,
-				      unsigned long error_code,
-				      unsigned long fault_addr)
+static void ex_handler_msr_mce(struct pt_regs *regs, bool wrmsr)
 {
-	pr_emerg("MSR access error: RDMSR from 0x%x at rIP: 0x%lx (%pS)\n",
-		 (unsigned int)regs->cx, regs->ip, (void *)regs->ip);
+	if (wrmsr) {
+		pr_emerg("MSR access error: WRMSR to 0x%x (tried to write 0x%08x%08x) at rIP: 0x%lx (%pS)\n",
+			 (unsigned int)regs->cx, (unsigned int)regs->dx, (unsigned int)regs->ax,
+			 regs->ip, (void *)regs->ip);
+	} else {
+		pr_emerg("MSR access error: RDMSR from 0x%x at rIP: 0x%lx (%pS)\n",
+			 (unsigned int)regs->cx, regs->ip, (void *)regs->ip);
+	}
 
 	show_stack_regs(regs);
 
@@ -411,7 +430,14 @@ __visible bool ex_handler_rdmsr_fault(const struct exception_table_entry *fixup,
 
 	while (true)
 		cpu_relax();
+}
 
+__visible bool ex_handler_rdmsr_fault(const struct exception_table_entry *fixup,
+				      struct pt_regs *regs, int trapnr,
+				      unsigned long error_code,
+				      unsigned long fault_addr)
+{
+	ex_handler_msr_mce(regs, false);
 	return true;
 }
 
@@ -447,17 +473,7 @@ __visible bool ex_handler_wrmsr_fault(const struct exception_table_entry *fixup,
 				      unsigned long error_code,
 				      unsigned long fault_addr)
 {
-	pr_emerg("MSR access error: WRMSR to 0x%x (tried to write 0x%08x%08x) at rIP: 0x%lx (%pS)\n",
-		 (unsigned int)regs->cx, (unsigned int)regs->dx, (unsigned int)regs->ax,
-		  regs->ip, (void *)regs->ip);
-
-	show_stack_regs(regs);
-
-	panic("MCA architectural violation!\n");
-
-	while (true)
-		cpu_relax();
-
+	ex_handler_msr_mce(regs, true);
 	return true;
 }
 
@@ -2212,12 +2228,14 @@ static ssize_t set_bank(struct device *s, struct device_attribute *attr,
 		return -EINVAL;
 
 	b = &per_cpu(mce_banks_array, s->id)[bank];
-
 	if (!b->init)
 		return -ENODEV;
 
 	b->ctl = new;
+
+	mutex_lock(&mce_sysfs_mutex);
 	mce_restart();
+	mutex_unlock(&mce_sysfs_mutex);
 
 	return size;
 }