On Tuesday 07 October 2008 21:29:51 Bob Montgomery wrote:
> On Tue, 2008-10-07 at 13:24 +0000, Vivek Goyal wrote:
> > On Tue, Oct 07, 2008 at 06:21:52PM +0530, Chandru wrote:
> > > kdump on a quad core Opteron blade machine doesn't give a complete
> > > vmcore on the system. All works well until we attempt to copy
> > > /proc/vmcore to some target place ( disk , n/w ). The system
> > > immediately resets without any OS messages after having copied few mb's
> > > of vmcore file. Problem also occurs with 2.6.27-rc8 and latest
> > > kexec-tools. If we pass 'mem=4G' as boot parameter to the first
> > > kernel, then kdump succeeds in copying a readable vmcore to /var/crash.
> >
> > Hi Chandru,
> >
> > How much memory this system has got. Can you also paste the output of
> > /proc/iomem of first kernel.
> >
> > Does this system has GART? So looks like we are accessing some memory
> > area which platform does not like. (We saw issues with GART in the past.)
> >
> > Can you also provide /proc/vmcore ELF header (readelf output), in both
> > the cases (mem=4G and without that).
> >
> > You can try putting some printk in /proc/vmcore code and see which
> > physical memory area you are accessing when system goes bust. If in all
> > the failure cases it is same physical memory area, then we can try to
> > find what's so special about it.
>
> Or you can assume this is pretty much exactly the problem I ran into in
> August. I've attached the patch that I'm using with our 2.6.18 kernel
> to disable CPU-side access by the GART, which prevents the problem on
> our Family 10H systems. You'll need to fix the directory name for
> kernels newer than the arch/x86_64 merge.
>
> Now that someone else has seen the problem, if this fixes it, I'll
> submit the patch upstream.
>
> Here's the README for the patch:
>
> This patch changes the initialization of the GART (in
> pci-gart.c:init_k8_gatt) to set the DisGartCpu bit in the GART Aperture
> Control Register. Setting the bit Disables requests from the CPUs from
> accessing the GART. In other words, CPU memory accesses within the
> range of addresses in the aperture will not cause the GART to perform an
> address translation. The aperture area was already being unmapped at
> the kernel level with clear_kernel_mapping() to prevent accesses from
> the CPU, but that kernel level unmapping is not in effect in the kexec'd
> kdump kernel. By disabling the CPU-side accesses within the GART, which
> does persist through the kexec of the kdump kernel, the kdump kernel is
> prevented from interacting with the GART during accesses to the dump
> memory areas which include the address range of the GART aperture.
> Although the patch can be applied to the kdump kernel, it is not
> exercised there because the kdump kernel doesn't attempt to initialize
> the GART.
>
> Bob Montgomery
> working at HP
Hi Bob,
This problem was recently reported on a LS42 blade and the patch given by you
also resolved the issue here too. However I made couple of changes to
kexec-tools to ignore GART memory region and not have elf headers created to
it. This patch also seemed to work on a LS21.
Thanks,
Chandru
Signed-off-by: Chandru S <chandru at in.ibm.com>
---
--- kexec-tools/kexec/arch/x86_64/crashdump-x86_64.c.orig 2008-12-08
01:50:41.000000000 -0600
+++ kexec-tools/kexec/arch/x86_64/crashdump-x86_64.c 2008-12-08
03:02:45.000000000 -0600
@@ -47,7 +47,7 @@ static struct crash_elf_info elf_info =
};
/* Forward Declaration. */
-static int exclude_crash_reserve_region(int *nr_ranges);
+static int exclude_region(int *nr_ranges, uint64_t start, uint64_t end);
#define KERN_VADDR_ALIGN 0x100000 /* 1MB */
@@ -164,10 +164,11 @@ static struct memory_range crash_reserve
static int get_crash_memory_ranges(struct memory_range **range, int *ranges)
{
const char *iomem= proc_iomem();
- int memory_ranges = 0;
+ int memory_ranges = 0, gart = 0;
char line[MAX_LINE];
FILE *fp;
unsigned long long start, end;
+ uint64_t gart_start = 0, gart_end = 0;
fp = fopen(iomem, "r");
if (!fp) {
@@ -219,6 +220,10 @@ static int get_crash_memory_ranges(struc
type = RANGE_ACPI;
} else if(memcmp(str,"ACPI Non-volatile Storage\n",26) == 0 ) {
type = RANGE_ACPI_NVS;
+ } else if (memcmp(str, "GART\n", 5) == 0) {
+ gart_start = start;
+ gart_end = end;
+ gart = 1;
} else {
continue;
}
@@ -233,8 +238,14 @@ static int get_crash_memory_ranges(struc
memory_ranges++;
}
fclose(fp);
- if (exclude_crash_reserve_region(&memory_ranges) < 0)
+ if (exclude_region(&memory_ranges, crash_reserved_mem.start,
+ crash_reserved_mem.end) < 0)
return -1;
+ if (gart) {
+ /* exclude GART region if the system has one */
+ if (exclude_region(&memory_ranges, gart_start, gart_end) < 0)
+ return -1;
+ }
*range = crash_memory_range;
*ranges = memory_ranges;
#ifdef DEBUG
@@ -252,32 +263,27 @@ static int get_crash_memory_ranges(struc
/* Removes crash reserve region from list of memory chunks for whom elf
program
* headers have to be created. Assuming crash reserve region to be a single
* continuous area fully contained inside one of the memory chunks */
-static int exclude_crash_reserve_region(int *nr_ranges)
+static int exclude_region(int *nr_ranges, uint64_t start, uint64_t end)
{
int i, j, tidx = -1;
- unsigned long long cstart, cend;
struct memory_range temp_region;
- /* Crash reserved region. */
- cstart = crash_reserved_mem.start;
- cend = crash_reserved_mem.end;
-
for (i = 0; i < (*nr_ranges); i++) {
unsigned long long mstart, mend;
mstart = crash_memory_range[i].start;
mend = crash_memory_range[i].end;
- if (cstart < mend && cend > mstart) {
- if (cstart != mstart && cend != mend) {
+ if (start < mend && end > mstart) {
+ if (start != mstart && end != mend) {
/* Split memory region */
- crash_memory_range[i].end = cstart - 1;
- temp_region.start = cend + 1;
+ crash_memory_range[i].end = start - 1;
+ temp_region.start = end + 1;
temp_region.end = mend;
temp_region.type = RANGE_RAM;
tidx = i+1;
- } else if (cstart != mstart)
- crash_memory_range[i].end = cstart - 1;
+ } else if (start != mstart)
+ crash_memory_range[i].end = start - 1;
else
- crash_memory_range[i].start = cend + 1;
+ crash_memory_range[i].start = end + 1;
}
}
/* Insert split memory region, if any. */
