1 files changed, 53 insertions, 30 deletions

diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 3a8e88a611eb..42cf2880d0ed 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -56,6 +56,9 @@
 
 static DEFINE_MUTEX(mce_log_mutex);
 
+/* sysfs synchronization */
+static DEFINE_MUTEX(mce_sysfs_mutex);
+
 #define CREATE_TRACE_POINTS
 #include <trace/events/mce.h>
 
@@ -105,6 +108,10 @@ static struct irq_work mce_irq_work;
 
 static void (*quirk_no_way_out)(int bank, struct mce *m, struct pt_regs *regs);
 
+#ifndef mce_unmap_kpfn
+static void mce_unmap_kpfn(unsigned long pfn);
+#endif
+
 /*
  * CPU/chipset specific EDAC code can register a notifier call here to print
  * MCE errors in a human-readable form.
@@ -126,6 +133,8 @@ void mce_setup(struct mce *m)
 
 	if (this_cpu_has(X86_FEATURE_INTEL_PPIN))
 		rdmsrl(MSR_PPIN, m->ppin);
+
+	m->microcode = boot_cpu_data.microcode;
 }
 
 DEFINE_PER_CPU(struct mce, injectm);
@@ -234,7 +243,7 @@ static void __print_mce(struct mce *m)
 			m->cs, m->ip);
 
 		if (m->cs == __KERNEL_CS)
-			pr_cont("{%pS}", (void *)m->ip);
+			pr_cont("{%pS}", (void *)(unsigned long)m->ip);
 		pr_cont("\n");
 	}
 
@@ -258,13 +267,15 @@ static void __print_mce(struct mce *m)
 	 */
 	pr_emerg(HW_ERR "PROCESSOR %u:%x TIME %llu SOCKET %u APIC %x microcode %x\n",
 		m->cpuvendor, m->cpuid, m->time, m->socketid, m->apicid,
-		cpu_data(m->extcpu).microcode);
+		m->microcode);
 }
 
 static void print_mce(struct mce *m)
 {
 	__print_mce(m);
-	pr_emerg_ratelimited(HW_ERR "Run the above through 'mcelog --ascii'\n");
+
+	if (m->cpuvendor != X86_VENDOR_AMD)
+		pr_emerg_ratelimited(HW_ERR "Run the above through 'mcelog --ascii'\n");
 }
 
 #define PANIC_TIMEOUT 5 /* 5 seconds */
@@ -590,7 +601,8 @@ static int srao_decode_notifier(struct notifier_block *nb, unsigned long val,
 
 	if (mce_usable_address(mce) && (mce->severity == MCE_AO_SEVERITY)) {
 		pfn = mce->addr >> PAGE_SHIFT;
-		memory_failure(pfn, 0);
+		if (!memory_failure(pfn, 0))
+			mce_unmap_kpfn(pfn);
 	}
 
 	return NOTIFY_OK;
@@ -1057,12 +1069,13 @@ static int do_memory_failure(struct mce *m)
 	ret = memory_failure(m->addr >> PAGE_SHIFT, flags);
 	if (ret)
 		pr_err("Memory error not recovered");
+	else
+		mce_unmap_kpfn(m->addr >> PAGE_SHIFT);
 	return ret;
 }
 
-#if defined(arch_unmap_kpfn) && defined(CONFIG_MEMORY_FAILURE)
-
-void arch_unmap_kpfn(unsigned long pfn)
+#ifndef mce_unmap_kpfn
+static void mce_unmap_kpfn(unsigned long pfn)
 {
 	unsigned long decoy_addr;
 
@@ -1073,7 +1086,7 @@ void arch_unmap_kpfn(unsigned long pfn)
 	 * We would like to just call:
 	 *	set_memory_np((unsigned long)pfn_to_kaddr(pfn), 1);
 	 * but doing that would radically increase the odds of a
-	 * speculative access to the posion page because we'd have
+	 * speculative access to the poison page because we'd have
 	 * the virtual address of the kernel 1:1 mapping sitting
 	 * around in registers.
 	 * Instead we get tricky.  We create a non-canonical address
@@ -1082,23 +1095,10 @@ void arch_unmap_kpfn(unsigned long pfn)
 	 * a legal address.
 	 */
 
-/*
- * Build time check to see if we have a spare virtual bit. Don't want
- * to leave this until run time because most developers don't have a
- * system that can exercise this code path. This will only become a
- * problem if/when we move beyond 5-level page tables.
- *
- * Hard code "9" here because cpp doesn't grok ilog2(PTRS_PER_PGD)
- */
-#if PGDIR_SHIFT + 9 < 63
 	decoy_addr = (pfn << PAGE_SHIFT) + (PAGE_OFFSET ^ BIT(63));
-#else
-#error "no unused virtual bit available"
-#endif
 
 	if (set_memory_np(decoy_addr, 1))
 		pr_warn("Could not invalidate pfn=0x%lx from 1:1 map\n", pfn);
-
 }
 #endif
 
@@ -1506,7 +1506,7 @@ static int __mcheck_cpu_cap_init(void)
 		mca_cfg.rip_msr = MSR_IA32_MCG_EIP;
 
 	if (cap & MCG_SER_P)
-		mca_cfg.ser = true;
+		mca_cfg.ser = 1;
 
 	return 0;
 }
@@ -1814,12 +1814,12 @@ void mcheck_cpu_init(struct cpuinfo_x86 *c)
 		return;
 
 	if (__mcheck_cpu_cap_init() < 0 || __mcheck_cpu_apply_quirks(c) < 0) {
-		mca_cfg.disabled = true;
+		mca_cfg.disabled = 1;
 		return;
 	}
 
 	if (mce_gen_pool_init()) {
-		mca_cfg.disabled = true;
+		mca_cfg.disabled = 1;
 		pr_emerg("Couldn't allocate MCE records pool!\n");
 		return;
 	}
@@ -1897,11 +1897,11 @@ static int __init mcheck_enable(char *str)
 	if (*str == '=')
 		str++;
 	if (!strcmp(str, "off"))
-		cfg->disabled = true;
+		cfg->disabled = 1;
 	else if (!strcmp(str, "no_cmci"))
 		cfg->cmci_disabled = true;
 	else if (!strcmp(str, "no_lmce"))
-		cfg->lmce_disabled = true;
+		cfg->lmce_disabled = 1;
 	else if (!strcmp(str, "dont_log_ce"))
 		cfg->dont_log_ce = true;
 	else if (!strcmp(str, "ignore_ce"))
@@ -1909,9 +1909,9 @@ static int __init mcheck_enable(char *str)
 	else if (!strcmp(str, "bootlog") || !strcmp(str, "nobootlog"))
 		cfg->bootlog = (str[0] == 'b');
 	else if (!strcmp(str, "bios_cmci_threshold"))
-		cfg->bios_cmci_threshold = true;
+		cfg->bios_cmci_threshold = 1;
 	else if (!strcmp(str, "recovery"))
-		cfg->recovery = true;
+		cfg->recovery = 1;
 	else if (isdigit(str[0])) {
 		if (get_option(&str, &cfg->tolerant) == 2)
 			get_option(&str, &(cfg->monarch_timeout));
@@ -2081,6 +2081,7 @@ static ssize_t set_ignore_ce(struct device *s,
 	if (kstrtou64(buf, 0, &new) < 0)
 		return -EINVAL;
 
+	mutex_lock(&mce_sysfs_mutex);
 	if (mca_cfg.ignore_ce ^ !!new) {
 		if (new) {
 			/* disable ce features */
@@ -2093,6 +2094,8 @@ static ssize_t set_ignore_ce(struct device *s,
 			on_each_cpu(mce_enable_ce, (void *)1, 1);
 		}
 	}
+	mutex_unlock(&mce_sysfs_mutex);
+
 	return size;
 }
 
@@ -2105,6 +2108,7 @@ static ssize_t set_cmci_disabled(struct device *s,
 	if (kstrtou64(buf, 0, &new) < 0)
 		return -EINVAL;
 
+	mutex_lock(&mce_sysfs_mutex);
 	if (mca_cfg.cmci_disabled ^ !!new) {
 		if (new) {
 			/* disable cmci */
@@ -2116,6 +2120,8 @@ static ssize_t set_cmci_disabled(struct device *s,
 			on_each_cpu(mce_enable_ce, NULL, 1);
 		}
 	}
+	mutex_unlock(&mce_sysfs_mutex);
+
 	return size;
 }
 
@@ -2123,8 +2129,19 @@ static ssize_t store_int_with_restart(struct device *s,
 				      struct device_attribute *attr,
 				      const char *buf, size_t size)
 {
-	ssize_t ret = device_store_int(s, attr, buf, size);
+	unsigned long old_check_interval = check_interval;
+	ssize_t ret = device_store_ulong(s, attr, buf, size);
+
+	if (check_interval == old_check_interval)
+		return ret;
+
+	if (check_interval < 1)
+		check_interval = 1;
+
+	mutex_lock(&mce_sysfs_mutex);
 	mce_restart();
+	mutex_unlock(&mce_sysfs_mutex);
+
 	return ret;
 }
 
@@ -2328,6 +2345,12 @@ static __init int mcheck_init_device(void)
 {
 	int err;
 
+	/*
+	 * Check if we have a spare virtual bit. This will only become
+	 * a problem if/when we move beyond 5-level page tables.
+	 */
+	MAYBE_BUILD_BUG_ON(__VIRTUAL_MASK_SHIFT >= 63);
+
 	if (!mce_available(&boot_cpu_data)) {
 		err = -EIO;
 		goto err_out;
@@ -2376,7 +2399,7 @@ device_initcall_sync(mcheck_init_device);
  */
 static int __init mcheck_disable(char *str)
 {
-	mca_cfg.disabled = true;
+	mca_cfg.disabled = 1;
 	return 1;
 }
 __setup("nomce", mcheck_disable);