linux_dsm_epyc7002/arch/x86/kernel/check.c
Tony Luck fc6daaf931 mm/memblock: add extra "flags" to memblock to allow selection of memory based on attribute
Some high end Intel Xeon systems report uncorrectable memory errors as a
recoverable machine check.  Linux has included code for some time to
process these and just signal the affected processes (or even recover
completely if the error was in a read only page that can be replaced by
reading from disk).

But we have no recovery path for errors encountered during kernel code
execution.  Except for some very specific cases were are unlikely to ever
be able to recover.

Enter memory mirroring. Actually 3rd generation of memory mirroing.

Gen1: All memory is mirrored
	Pro: No s/w enabling - h/w just gets good data from other side of the
	     mirror
	Con: Halves effective memory capacity available to OS/applications

Gen2: Partial memory mirror - just mirror memory begind some memory controllers
	Pro: Keep more of the capacity
	Con: Nightmare to enable. Have to choose between allocating from
	     mirrored memory for safety vs. NUMA local memory for performance

Gen3: Address range partial memory mirror - some mirror on each memory
      controller
	Pro: Can tune the amount of mirror and keep NUMA performance
	Con: I have to write memory management code to implement

The current plan is just to use mirrored memory for kernel allocations.
This has been broken into two phases:

1) This patch series - find the mirrored memory, use it for boot time
   allocations

2) Wade into mm/page_alloc.c and define a ZONE_MIRROR to pick up the
   unused mirrored memory from mm/memblock.c and only give it out to
   select kernel allocations (this is still being scoped because
   page_alloc.c is scary).

This patch (of 3):

Add extra "flags" to memblock to allow selection of memory based on
attribute.  No functional changes

Signed-off-by: Tony Luck <tony.luck@intel.com>
Cc: Xishi Qiu <qiuxishi@huawei.com>
Cc: Hanjun Guo <guohanjun@huawei.com>
Cc: Xiexiuqi <xiexiuqi@huawei.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Yinghai Lu <yinghai@kernel.org>
Cc: Naoya Horiguchi <nao.horiguchi@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-06-24 17:49:44 -07:00

169 lines
3.8 KiB
C

#include <linux/module.h>
#include <linux/sched.h>
#include <linux/kthread.h>
#include <linux/workqueue.h>
#include <linux/memblock.h>
#include <asm/proto.h>
/*
* 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.
*/
#define MAX_SCAN_AREAS 8
static int __read_mostly memory_corruption_check = -1;
static unsigned __read_mostly corruption_check_size = 64*1024;
static unsigned __read_mostly corruption_check_period = 60; /* seconds */
static struct scan_area {
u64 addr;
u64 size;
} scan_areas[MAX_SCAN_AREAS];
static int num_scan_areas;
static __init int set_corruption_check(char *arg)
{
ssize_t ret;
unsigned long val;
ret = kstrtoul(arg, 10, &val);
if (ret)
return ret;
memory_corruption_check = val;
return 0;
}
early_param("memory_corruption_check", set_corruption_check);
static __init int set_corruption_check_period(char *arg)
{
ssize_t ret;
unsigned long val;
ret = kstrtoul(arg, 10, &val);
if (ret)
return ret;
corruption_check_period = val;
return 0;
}
early_param("memory_corruption_check_period", set_corruption_check_period);
static __init 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);
void __init setup_bios_corruption_check(void)
{
phys_addr_t start, end;
u64 i;
if (memory_corruption_check == -1) {
memory_corruption_check =
#ifdef CONFIG_X86_BOOTPARAM_MEMORY_CORRUPTION_CHECK
1
#else
0
#endif
;
}
if (corruption_check_size == 0)
memory_corruption_check = 0;
if (!memory_corruption_check)
return;
corruption_check_size = round_up(corruption_check_size, PAGE_SIZE);
for_each_free_mem_range(i, NUMA_NO_NODE, MEMBLOCK_NONE, &start, &end,
NULL) {
start = clamp_t(phys_addr_t, round_up(start, PAGE_SIZE),
PAGE_SIZE, corruption_check_size);
end = clamp_t(phys_addr_t, round_down(end, PAGE_SIZE),
PAGE_SIZE, corruption_check_size);
if (start >= end)
continue;
memblock_reserve(start, end - start);
scan_areas[num_scan_areas].addr = start;
scan_areas[num_scan_areas].size = end - start;
/* Assume we've already mapped this early memory */
memset(__va(start), 0, end - start);
if (++num_scan_areas >= MAX_SCAN_AREAS)
break;
}
if (num_scan_areas)
printk(KERN_INFO "Scanning %d areas for low memory corruption\n", num_scan_areas);
}
void check_for_bios_corruption(void)
{
int i;
int corruption = 0;
if (!memory_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;
}
}
WARN_ONCE(corruption, KERN_ERR "Memory corruption detected in low memory\n");
}
static void check_corruption(struct work_struct *dummy);
static DECLARE_DELAYED_WORK(bios_check_work, check_corruption);
static void check_corruption(struct work_struct *dummy)
{
check_for_bios_corruption();
schedule_delayed_work(&bios_check_work,
round_jiffies_relative(corruption_check_period*HZ));
}
static int start_periodic_check_for_corruption(void)
{
if (!num_scan_areas || !memory_corruption_check || corruption_check_period == 0)
return 0;
printk(KERN_INFO "Scanning for low memory corruption every %d seconds\n",
corruption_check_period);
/* First time we run the checks right away */
schedule_delayed_work(&bios_check_work, 0);
return 0;
}
module_init(start_periodic_check_for_corruption);