x86: check for and defend against BIOS memory corruption

Some BIOSes have been observed to corrupt memory in the low 64k.  This
change:
 - Reserves all memory which does not have to be in that area, to
   prevent it from being used as general memory by the kernel.  Things
   like the SMP trampoline are still in the memory, however.
 - Clears the reserved memory so we can observe changes to it.
 - Adds a function check_for_bios_corruption() which checks and reports on
   memory becoming unexpectedly non-zero.  Currently it's called in the
   x86 fault handler, and the powermanagement debug output.

Signed-off-by: Jeremy Fitzhardinge <jeremy@goop.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

Documentation/kernel-parameters.txt

@@ -360,6 +360,11 @@ and is between 256 and 4096 characters. It is defined in the file
 			Format: <io>,<irq>,<mode>
 			See header of drivers/net/hamradio/baycom_ser_hdx.c.
 
+	bios_corruption_check=0/1 [X86]
+			Some BIOSes seem to corrupt the first 64k of memory
+			when doing things like suspend/resume.  Setting this
+			option will scan the memory looking for corruption.
+
 	boot_delay=	Milliseconds to delay each printk during boot.
 			Values larger than 10 seconds (10000) are changed to
 			no delay (0).

arch/x86/Kconfig

@@ -201,6 +201,9 @@ config X86_TRAMPOLINE
 	depends on X86_SMP || (X86_VOYAGER && SMP) || (64BIT && ACPI_SLEEP)
 	default y
 
+config X86_CHECK_BIOS_CORRUPTION
+        def_bool y
+
 config KTIME_SCALAR
 	def_bool X86_32
 source "init/Kconfig"

arch/x86/kernel/setup.c

@@ -578,6 +578,89 @@ static struct x86_quirks default_x86_quirks __initdata;
 
 struct x86_quirks *x86_quirks __initdata = &default_x86_quirks;
 
+/*
+ * Some BIOSes seem to corrupt the low 64k of memory during events
+ * like suspend/resume and unplugging an HDMI cable.  Reserve all
+ * remaining free memory in that area and fill it with a distinct
+ * pattern.
+ */
+#ifdef CONFIG_X86_CHECK_BIOS_CORRUPTION
+#define MAX_SCAN_AREAS	8
+static struct e820entry scan_areas[MAX_SCAN_AREAS];
+static int num_scan_areas;
+
+static void __init setup_bios_corruption_check(void)
+{
+	u64 addr = PAGE_SIZE;	/* assume first page is reserved anyway */
+
+	while(addr < 0x10000 && num_scan_areas < MAX_SCAN_AREAS) {
+		u64 size;
+		addr = find_e820_area_size(addr, &size, PAGE_SIZE);
+
+		if (addr == 0)
+			break;
+
+		if ((addr + size) > 0x10000)
+			size = 0x10000 - addr;
+
+		if (size == 0)
+			break;
+
+		e820_update_range(addr, size, E820_RAM, E820_RESERVED);
+		scan_areas[num_scan_areas].addr = addr;
+		scan_areas[num_scan_areas].size = size;
+		num_scan_areas++;
+
+		/* Assume we've already mapped this early memory */
+		memset(__va(addr), 0, size);
+
+		addr += size;
+	}
+
+	printk(KERN_INFO "scanning %d areas for BIOS corruption\n",
+	       num_scan_areas);
+	update_e820();
+}
+
+static int __read_mostly bios_corruption_check = 1;
+
+void check_for_bios_corruption(void)
+{
+	int i;
+	int corruption = 0;
+
+	if (!bios_corruption_check)
+		return;
+
+	for(i = 0; i < num_scan_areas; i++) {
+		unsigned long *addr = __va(scan_areas[i].addr);
+		unsigned long size = scan_areas[i].size;
+
+		for(; size; addr++, size -= sizeof(unsigned long)) {
+			if (!*addr)
+				continue;
+			printk(KERN_ERR "Corrupted low memory at %p (%lx phys) = %08lx\n",
+			       addr, __pa(addr), *addr);
+			corruption = 1;
+			*addr = 0;
+		}
+	}
+
+	if (corruption)
+		dump_stack();
+}
+
+static int set_bios_corruption_check(char *arg)
+{
+	char *end;
+
+	bios_corruption_check = simple_strtol(arg, &end, 10);
+
+	return (*end == 0) ? 0 : -EINVAL;
+}
+early_param("bios_corruption_check", set_bios_corruption_check);
+#endif
+
 /*
  * Determine if we were loaded by an EFI loader.  If so, then we have also been
  * passed the efi memmap, systab, etc., so we should use these data structures
@@ -750,6 +833,10 @@ void __init setup_arch(char **cmdline_p)
 	high_memory = (void *)__va(max_pfn * PAGE_SIZE - 1) + 1;
 #endif
 
+#ifdef CONFIG_X86_CHECK_BIOS_CORRUPTION
+	setup_bios_corruption_check();
+#endif
+
 	/* max_pfn_mapped is updated here */
 	max_low_pfn_mapped = init_memory_mapping(0, max_low_pfn<<PAGE_SHIFT);
 	max_pfn_mapped = max_low_pfn_mapped;

arch/x86/mm/fault.c

@@ -848,6 +848,8 @@ no_context:
  * Oops. The kernel tried to access some bad page. We'll have to
  * terminate things with extreme prejudice.
  */
+	check_for_bios_corruption();
+
 #ifdef CONFIG_X86_32
 	bust_spinlocks(1);
 #else

drivers/base/power/main.c

@@ -254,6 +254,7 @@ static char *pm_verb(int event)
 
 static void pm_dev_dbg(struct device *dev, pm_message_t state, char *info)
 {
+	check_for_bios_corruption();
 	dev_dbg(dev, "%s%s%s\n", info, pm_verb(state.event),
 		((state.event & PM_EVENT_SLEEP) && device_may_wakeup(dev)) ?
 		", may wakeup" : "");

include/linux/kernel.h

@@ -240,6 +240,18 @@ extern const char *print_tainted(void);
 extern void add_taint(unsigned);
 extern int root_mountflags;
 
+#ifdef CONFIG_X86_CHECK_BIOS_CORRUPTION
+/*
+ * This is obviously not a great place for this, but we want to be
+ * able to scatter it around anywhere in the kernel.
+ */
+void check_for_bios_corruption(void);
+#else
+static inline void check_for_bios_corruption(void)
+{
+}
+#endif
+
 /* Values used for system_state */
 extern enum system_states {
 	SYSTEM_BOOTING,