x86: clean up memory corruption check and add more kernel parameters

The corruption check is enabled in Kconfig by default, but disabled at runtime.

This patch adds several kernel parameters to control the corruption
check's behaviour; these are documented in kernel-parameters.txt.

Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

3 files changed, 106 insertions, 28 deletions

diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index df48af505d15..6a2629d00598 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -360,11 +360,6 @@ 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).
@@ -1233,6 +1228,29 @@ and is between 256 and 4096 characters. It is defined in the file
 			         or
 			         memmap=0x10000$0x18690000
 
+	memory_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.  Enabling this will
+			both detect corruption and prevent the kernel
+			from using the memory being corrupted.
+			However, its intended as a diagnostic tool; if
+			repeatable BIOS-originated corruption always
+			affects the same memory, you can use memmap=
+			to prevent the kernel from using that memory.
+
+	memory_corruption_check_size=size [X86]
+			By default it checks for corruption in the low
+			64k, making this memory unavailable for normal
+			use.  Use this parameter to scan for
+			corruption in more or less memory.
+
+	memory_corruption_check_period=seconds [X86]
+			By default it checks for corruption every 60
+			seconds.  Use this parameter to check at some
+			other rate.  0 disables periodic checking.
+
 	memtest=	[KNL,X86] Enable memtest
 			Format: <integer>
 			range: 0,4 : pattern number
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 1bb52e2ca02e..cbee4199689c 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -201,9 +201,6 @@ 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"
@@ -1062,6 +1059,29 @@ config HIGHPTE
 	  low memory.  Setting this option will put user-space page table
 	  entries in high memory.
 
+config X86_CHECK_BIOS_CORRUPTION
+        bool "Check for low memory corruption"
+	default y
+	help
+	 Periodically check for memory corruption in low memory, which
+	 is suspected to be caused by BIOS.  Even when enabled in the
+	 configuration, it is disabled at runtime.  Enable it by
+	 setting "memory_corruption_check=1" on the kernel command
+	 line.  By default it scans the low 64k of memory every 60
+	 seconds; see the memory_corruption_check_size and
+	 memory_corruption_check_period parameters in
+	 Documentation/kernel-parameters.txt to adjust this.
+
+	 When enabled with the default parameters, this option has
+	 almost no overhead, as it reserves a relatively small amount
+	 of memory and scans it infrequently.  It both detects corruption
+	 and prevents it from affecting the running system.
+
+	 It is, however, intended as a diagnostic tool; if repeatable
+	 BIOS-originated corruption always affects the same memory,
+	 you can use memmap= to prevent the kernel from using that
+	 memory.
+
 config MATH_EMULATION
 	bool
 	prompt "Math emulation" if X86_32
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index c239b3780973..27ae91288855 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -586,22 +586,71 @@ struct x86_quirks *x86_quirks __initdata = &default_x86_quirks;
  */
 #ifdef CONFIG_X86_CHECK_BIOS_CORRUPTION
 #define MAX_SCAN_AREAS	8
+
+static int __read_mostly memory_corruption_check = 0;
+static unsigned __read_mostly corruption_check_size = 64*1024;
+static unsigned __read_mostly corruption_check_period = 60; /* seconds */
+
 static struct e820entry scan_areas[MAX_SCAN_AREAS];
 static int num_scan_areas;
 
+
+static int set_corruption_check(char *arg)
+{
+	char *end;
+
+	memory_corruption_check = simple_strtol(arg, &end, 10);
+
+	return (*end == 0) ? 0 : -EINVAL;
+}
+early_param("memory_corruption_check", set_corruption_check);
+
+static int set_corruption_check_period(char *arg)
+{
+	char *end;
+
+	corruption_check_period = simple_strtoul(arg, &end, 10);
+
+	return (*end == 0) ? 0 : -EINVAL;
+}
+early_param("memory_corruption_check_period", set_corruption_check_period);
+
+static int set_corruption_check_size(char *arg)
+{
+	char *end;
+	unsigned size;
+
+	size = memparse(arg, &end);
+
+	if (*end == '\0')
+		corruption_check_size = size;
+
+	return (size == corruption_check_size) ? 0 : -EINVAL;
+}
+early_param("memory_corruption_check_size", set_corruption_check_size);
+
+
 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) {
+	if (corruption_check_size == 0)
+		memory_corruption_check = 0;
+
+	if (!memory_corruption_check)
+		return;
+
+	corruption_check_size = round_up(corruption_check_size, PAGE_SIZE);
+
+	while(addr < corruption_check_size && 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 ((addr + size) > corruption_check_size)
+			size = corruption_check_size - addr;
 
 		if (size == 0)
 			break;
@@ -617,12 +666,11 @@ static void __init setup_bios_corruption_check(void)
 		addr += size;
 	}
 
-	printk(KERN_INFO "scanning %d areas for BIOS corruption\n",
+	printk(KERN_INFO "Scanning %d areas for low memory corruption\n",
 	       num_scan_areas);
 	update_e820();
 }
 
-static int __read_mostly bios_corruption_check = 1;
 static struct timer_list periodic_check_timer;
 
 void check_for_bios_corruption(void)
@@ -630,7 +678,7 @@ void check_for_bios_corruption(void)
 	int i;
 	int corruption = 0;
 
-	if (!bios_corruption_check)
+	if (!memory_corruption_check)
 		return;
 
 	for(i = 0; i < num_scan_areas; i++) {
@@ -647,35 +695,27 @@ void check_for_bios_corruption(void)
 		}
 	}
 
-	if (corruption)
-		dump_stack();
+	WARN(corruption, KERN_ERR "Memory corruption detected in low memory\n");
 }
 
 static void periodic_check_for_corruption(unsigned long data)
 {
 	check_for_bios_corruption();
-	mod_timer(&periodic_check_timer, jiffies + 60*HZ);
+	mod_timer(&periodic_check_timer, jiffies + corruption_check_period*HZ);
 }
 
 void start_periodic_check_for_corruption(void)
 {
-	if (!bios_corruption_check)
+	if (!memory_corruption_check || corruption_check_period == 0)
 		return;
 
+	printk(KERN_INFO "Scanning for low memory corruption every %d seconds\n",
+	       corruption_check_period);
+
 	init_timer(&periodic_check_timer);
 	periodic_check_timer.function = &periodic_check_for_corruption;
 	periodic_check_for_corruption(0);
 }
-
-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
 
 /*