do simple memtest after init_memory_mapping
use find_e820_area_size to find all ram range that is not reserved.
and do some simple bits test to find some bad ram.
if find some bad ram, use reserve_early to exclude that range.
Signed-off-by: Yinghai Lu <[email protected]>
Index: linux-2.6/arch/x86/kernel/e820_64.c
===================================================================
--- linux-2.6.orig/arch/x86/kernel/e820_64.c
+++ linux-2.6/arch/x86/kernel/e820_64.c
@@ -119,6 +119,40 @@ again:
return changed;
}
+/* Check for already reserved areas */
+static inline int
+bad_addr_size(unsigned long *addrp, unsigned long *sizep, unsigned long align)
+{
+ int i;
+ unsigned long addr = *addrp, last;
+ unsigned long size = *sizep;
+ int changed = 0;
+again:
+ last = addr + size;
+ for (i = 0; i < MAX_EARLY_RES && early_res[i].end; i++) {
+ struct early_res *r = &early_res[i];
+ if (last > r->start && addr < r->start) {
+ size = r->start - addr;
+ changed = 1;
+ goto again;
+ }
+ if (last > r->end && addr < r->end) {
+ addr = round_up(r->end, align);
+ size = last - addr;
+ changed = 1;
+ goto again;
+ }
+ if (last <= r->end && addr >= r->start) {
+ (*sizep)++;
+ return 0;
+ }
+ }
+ if (changed) {
+ *addrp = addr;
+ *sizep = size;
+ }
+ return changed;
+}
/*
* This function checks if any part of the range <start,end> is mapped
* with type.
@@ -195,7 +229,7 @@ unsigned long __init find_e820_area(unsi
ei_last = ei->addr + ei->size;
if (addr < start)
addr = round_up(start, align);
- if (addr > ei_last)
+ if (addr >= ei_last)
continue;
while (bad_addr(&addr, size, align) && addr+size <= ei_last)
;
@@ -210,6 +244,40 @@ unsigned long __init find_e820_area(unsi
}
/*
+ * Find next free range after *start
+ */
+unsigned long __init find_e820_area_size(unsigned long start, unsigned long *sizep, unsigned long align)
+{
+ int i;
+
+ for (i = 0; i < e820.nr_map; i++) {
+ struct e820entry *ei = &e820.map[i];
+ unsigned long addr, last;
+ unsigned long ei_last;
+
+ if (ei->type != E820_RAM)
+ continue;
+ addr = round_up(ei->addr, align);
+ ei_last = ei->addr + ei->size;
+// printk(KERN_DEBUG "find_e820_area_size : e820 %d [%llx, %lx]\n", i, ei->addr, ei_last);
+ if (addr < start)
+ addr = round_up(start, align);
+// printk(KERN_DEBUG "find_e820_area_size : 0 [%lx, %lx]\n", addr, ei_last);
+ if (addr >= ei_last)
+ continue;
+ *sizep = ei_last - addr;
+ while (bad_addr_size(&addr, sizep, align) && addr+ *sizep <= ei_last)
+ ;
+ last = addr + *sizep;
+// printk(KERN_DEBUG "find_e820_area_size : 1 [%lx, %lx]\n", addr, last);
+ if (last > ei_last)
+ continue;
+ return addr;
+ }
+ return -1UL;
+
+}
+/*
* Find the highest page frame number we have available
*/
unsigned long __init e820_end_of_ram(void)
Index: linux-2.6/arch/x86/mm/init_64.c
===================================================================
--- linux-2.6.orig/arch/x86/mm/init_64.c
+++ linux-2.6/arch/x86/mm/init_64.c
@@ -427,6 +427,106 @@ static void __init init_gbpages(void)
direct_gbpages = 0;
}
+static void __init memtest(unsigned long start_phys, unsigned long size, unsigned pattern)
+{
+ unsigned long i;
+ unsigned long *start;
+ unsigned long start_bad;
+ unsigned long last_bad;
+ unsigned long val;
+ unsigned long start_phys_aligned;
+ unsigned long count;
+ unsigned long incr;
+
+ switch (pattern) {
+ case 0:
+ val = 0UL;
+ break;
+ case 1:
+ val = -1UL;
+ break;
+ case 2:
+ val = 0x5555555555555555UL;
+ break;
+ case 3:
+ val = 0xaaaaaaaaaaaaaaaaUL;
+ break;
+ default:
+ return;
+ }
+
+ incr = sizeof(unsigned long);
+ start_phys_aligned = ALIGN(start_phys, incr);
+ count = (size - (start_phys_aligned - start_phys))/incr;
+ start = __va(start_phys_aligned);
+ start_bad = 0;
+ last_bad = 0;
+
+ for (i = 0; i < count; i++)
+ start[i] = val;
+ for (i = 0; i < count; i++, start++, start_phys_aligned += incr) {
+ if (*start != val) {
+ if (start_phys_aligned == last_bad + incr) {
+ last_bad += incr;
+ } else {
+ if (start_bad) {
+ printk(KERN_INFO " %016lxx bad mem addr %016lx - %016lx reserved\n",
+ val, start_bad, last_bad + incr);
+ reserve_early(start_bad, last_bad - start_bad, "BAD RAM");
+ }
+ start_bad = last_bad = start_phys_aligned;
+ }
+ }
+ }
+ if (start_bad) {
+ printk(KERN_INFO " %016lx bad mem addr %016lx - %016lx reserved\n",
+ val, start_bad, last_bad + incr);
+ reserve_early(start_bad, last_bad - start_bad, "BAD RAM");
+ }
+
+}
+
+static int __initdata memtest_pattern;
+static int __init parse_memtest(char *arg)
+{
+ if (arg)
+ memtest_pattern = simple_strtoul(arg, NULL, 0) + 1;
+ return 0;
+}
+
+early_param("memtest", parse_memtest);
+
+static void __init early_memtest(unsigned long start, unsigned long end)
+{
+ unsigned long t_start, t_size;
+ unsigned pattern;
+
+ if (memtest_pattern)
+ printk(KERN_INFO "early_memtest: pattern num %d", memtest_pattern);
+ for (pattern = 0; pattern < memtest_pattern; pattern++) {
+ t_start = start;
+ t_size = 0;
+ while (t_start < end) {
+ t_start = find_e820_area_size(t_start, &t_size, 1);
+
+ /* done ? */
+ if (t_start >= end)
+ break;
+ if (t_start + t_size > end)
+ t_size = end - t_start;
+
+ printk(KERN_CONT "\n %016lx - %016lx pattern %d",
+ t_start, t_start + t_size, pattern);
+
+ memtest(t_start, t_size, pattern);
+
+ t_start += t_size;
+ }
+ }
+ if (memtest_pattern)
+ printk(KERN_CONT "\n");
+}
+
/*
* Setup the direct mapping of the physical memory at PAGE_OFFSET.
* This runs before bootmem is initialized and gets pages directly from
@@ -435,8 +535,9 @@ static void __init init_gbpages(void)
void __init_refok init_memory_mapping(unsigned long start, unsigned long end)
{
unsigned long next;
+ unsigned long start_phys = start, end_phys = end;
- pr_debug("init_memory_mapping\n");
+ printk(KERN_INFO "init_memory_mapping\n");
/*
* Find space for the kernel direct mapping tables.
@@ -479,6 +580,9 @@ void __init_refok init_memory_mapping(un
if (!after_bootmem)
reserve_early(table_start << PAGE_SHIFT,
table_end << PAGE_SHIFT, "PGTABLE");
+
+ if (!after_bootmem)
+ early_memtest(start_phys, end_phys);
}
#ifndef CONFIG_NUMA
Index: linux-2.6/include/asm-x86/e820_64.h
===================================================================
--- linux-2.6.orig/include/asm-x86/e820_64.h
+++ linux-2.6/include/asm-x86/e820_64.h
@@ -16,6 +16,9 @@
#ifndef __ASSEMBLY__
extern unsigned long find_e820_area(unsigned long start, unsigned long end,
unsigned long size, unsigned long align);
+extern unsigned long find_e820_area_size(unsigned long start,
+ unsigned long *sizep,
+ unsigned long align);
extern void add_memory_region(unsigned long start, unsigned long size,
int type);
extern void update_memory_range(u64 start, u64 size, unsigned old_type,
* Yinghai Lu <[email protected]> wrote:
> do simple memtest after init_memory_mapping
>
> use find_e820_area_size to find all ram range that is not reserved.
>
> and do some simple bits test to find some bad ram.
>
> if find some bad ram, use reserve_early to exclude that range.
very nice patch! I always thought that this was the proper way to do
memtest - and we could in fact also do something like this after SMP
bringup, and hit the memory bus via multiple CPUs. [that will need a
different enumeration though than e820 maps]
one structural observation: please make this unified functionality, so
that 32-bit kernels can make use of it too.
a small style nit from scripts/checkpatch.pl:
> +// printk(KERN_DEBUG "find_e820_area_size : e820 %d [%llx, %lx]\n", i, ei->addr, ei_last);
remove such lines or make them pr_debug(). (checkpatch also found more
such cases)
also, please add a CONFIG_BOOTPARAM_MEMTEST=y option so that
distributions can enable this by default in their debug kernels.
i've applied your current version to get some testing, please send delta
patches against x86/latest.
Ingo
Ingo Molnar wrote:
>
> very nice patch! I always thought that this was the proper way to do
> memtest - and we could in fact also do something like this after SMP
> bringup, and hit the memory bus via multiple CPUs. [that will need a
> different enumeration though than e820 maps]
>
> one structural observation: please make this unified functionality, so
> that 32-bit kernels can make use of it too.
>
Indeed. Of course, it would also be nice if distros shipped
bootloader-invoked prekernel test software, like memtest86+, by default.
-hpa
* H. Peter Anvin <[email protected]> wrote:
>> very nice patch! I always thought that this was the proper way to do
>> memtest - and we could in fact also do something like this after SMP
>> bringup, and hit the memory bus via multiple CPUs. [that will need a
>> different enumeration though than e820 maps]
>>
>> one structural observation: please make this unified functionality,
>> so that 32-bit kernels can make use of it too.
>>
>
> Indeed. Of course, it would also be nice if distros shipped
> bootloader-invoked prekernel test software, like memtest86+, by
> default.
some do (Fedora for example), but it's still a bit quirky for users to
invoke and it would be nice to see those results in the kernel log as
well and flag possibly flaky systems that way. (add a taint bit, etc.,
etc.)
Ingo
On Fri, Mar 21, 2008 at 6:08 AM, H. Peter Anvin <[email protected]> wrote:
> Ingo Molnar wrote:
> >
> > very nice patch! I always thought that this was the proper way to do
> > memtest - and we could in fact also do something like this after SMP
> > bringup, and hit the memory bus via multiple CPUs. [that will need a
> > different enumeration though than e820 maps]
> >
> > one structural observation: please make this unified functionality, so
> > that 32-bit kernels can make use of it too.
> >
>
> Indeed. Of course, it would also be nice if distros shipped
> bootloader-invoked prekernel test software, like memtest86+, by default.
the current memtest86 is running in 32 bit mode, and only support 64G ram.
I tried to expand that a bit, to support 1024g, but it only works on
some machine.
could be stack provide is not big enough?
YH
Yinghai Lu wrote:
> On Fri, Mar 21, 2008 at 6:08 AM, H. Peter Anvin <[email protected]> wrote:
>> Ingo Molnar wrote:
>> >
>> > very nice patch! I always thought that this was the proper way to do
>> > memtest - and we could in fact also do something like this after SMP
>> > bringup, and hit the memory bus via multiple CPUs. [that will need a
>> > different enumeration though than e820 maps]
>> >
>> > one structural observation: please make this unified functionality, so
>> > that 32-bit kernels can make use of it too.
>> >
>>
>> Indeed. Of course, it would also be nice if distros shipped
>> bootloader-invoked prekernel test software, like memtest86+, by default.
>
> the current memtest86 is running in 32 bit mode, and only support 64G ram.
>
> I tried to expand that a bit, to support 1024g, but it only works on
> some machine.
> could be stack provide is not big enough?
>
Wonder how hard it would be to make it run 64 bits...
-hpa
On Fri, Mar 21, 2008 at 12:58 PM, H. Peter Anvin <[email protected]> wrote:
>
> Yinghai Lu wrote:
> > On Fri, Mar 21, 2008 at 6:08 AM, H. Peter Anvin <[email protected]> wrote:
> >> Ingo Molnar wrote:
> >> >
> >> > very nice patch! I always thought that this was the proper way to do
> >> > memtest - and we could in fact also do something like this after SMP
> >> > bringup, and hit the memory bus via multiple CPUs. [that will need a
> >> > different enumeration though than e820 maps]
> >> >
> >> > one structural observation: please make this unified functionality, so
> >> > that 32-bit kernels can make use of it too.
> >> >
> >>
> >> Indeed. Of course, it would also be nice if distros shipped
> >> bootloader-invoked prekernel test software, like memtest86+, by default.
> >
> > the current memtest86 is running in 32 bit mode, and only support 64G ram.
> >
> > I tried to expand that a bit, to support 1024g, but it only works on
> > some machine.
> > could be stack provide is not big enough?
> >
>
> Wonder how hard it would be to make it run 64 bits...
1. in 32 bit test less than 4g in 32 bit mode
2. switch to 64 bit, set page table under 4g to cover all ram...
YH
On Mar 21 2008 13:03, Ingo Molnar wrote:
> * Yinghai Lu <[email protected]> wrote:
>
>> do simple memtest after init_memory_mapping
>> use find_e820_area_size to find all ram range that is not reserved.
>> and do some simple bits test to find some bad ram.
>> if find some bad ram, use reserve_early to exclude that range.
>
> very nice patch! I always thought that this was the proper way to do
> memtest - and we could in fact also do something like this after SMP
> bringup, and hit the memory bus via multiple CPUs. [that will need a
> different enumeration though than e820 maps]
Perhaps this can even be used to provide on-the-fly badram
patch semantics?
On Fri, Mar 21, 2008 at 2:22 PM, Jan Engelhardt <[email protected]> wrote:
>
> On Mar 21 2008 13:03, Ingo Molnar wrote:
> > * Yinghai Lu <[email protected]> wrote:
> >
> >> do simple memtest after init_memory_mapping
> >> use find_e820_area_size to find all ram range that is not reserved.
> >> and do some simple bits test to find some bad ram.
> >> if find some bad ram, use reserve_early to exclude that range.
> >
> > very nice patch! I always thought that this was the proper way to do
> > memtest - and we could in fact also do something like this after SMP
> > bringup, and hit the memory bus via multiple CPUs. [that will need a
> > different enumeration though than e820 maps]
>
> Perhaps this can even be used to provide on-the-fly badram
> patch semantics?
yes. but bad ranges can not be too many. otherwise early_res array
will overflow. then need to use memmap=nn$ss to exclude range already
found.
YH
On Thu, Mar 20, 2008 at 23:58:33 -0700, Yinghai Lu wrote:
>
> do simple memtest after init_memory_mapping
>
> use find_e820_area_size to find all ram range that is not reserved.
>
> and do some simple bits test to find some bad ram.
>
> if find some bad ram, use reserve_early to exclude that range.
Does somebody still remember the bug report in which the fault
was found to be in hardware? By bisecting, the user got "working"
kernel when movnti was not used to copy data.
Would be neat if also non-temporal moves were done in this early memtest.
Having the memtest feature in kernel is useful,
considering my grub can not load memtest86+ binary, failing with error
"Selected item cannot fit into memory",
with or without the patch at
https://bugzilla.redhat.com/show_bug.cgi?id=237279
I have user-space app to test movnti... ask if you want it.
--
Do what you love because life is too short for anything else.
On Fri, Mar 21, 2008 at 5:03 AM, Ingo Molnar <[email protected]> wrote:
>
> * Yinghai Lu <[email protected]> wrote:
>
> > do simple memtest after init_memory_mapping
> >
> > use find_e820_area_size to find all ram range that is not reserved.
> >
> > and do some simple bits test to find some bad ram.
> >
> > if find some bad ram, use reserve_early to exclude that range.
>
> very nice patch! I always thought that this was the proper way to do
> memtest - and we could in fact also do something like this after SMP
> bringup, and hit the memory bus via multiple CPUs. [that will need a
> different enumeration though than e820 maps]
or
1. core0/node0 check all memory at first
2. every core0 will check all memory later one by one.
>
> one structural observation: please make this unified functionality, so
> that 32-bit kernels can make use of it too.
that will need to use PAE to switch 2G windows ....
>
> a small style nit from scripts/checkpatch.pl:
>
>
> > +// printk(KERN_DEBUG "find_e820_area_size : e820 %d [%llx, %lx]\n", i, ei->addr, ei_last);
>
> remove such lines or make them pr_debug(). (checkpatch also found more
> such cases)
>
> also, please add a CONFIG_BOOTPARAM_MEMTEST=y option so that
> distributions can enable this by default in their debug kernels.
>
> i've applied your current version to get some testing, please send delta
> patches against x86/latest.
thanks. will submit delta patch.
YH
On Fri, Mar 21, 2008 at 03:29:19PM +0100, Ingo Molnar wrote:
>
> * H. Peter Anvin <[email protected]> wrote:
>
> >> very nice patch! I always thought that this was the proper way to do
> >> memtest - and we could in fact also do something like this after SMP
> >> bringup, and hit the memory bus via multiple CPUs. [that will need a
> >> different enumeration though than e820 maps]
> >>
> >> one structural observation: please make this unified functionality,
> >> so that 32-bit kernels can make use of it too.
> >>
> >
> > Indeed. Of course, it would also be nice if distros shipped
> > bootloader-invoked prekernel test software, like memtest86+, by
> > default.
>
> some do (Fedora for example), but it's still a bit quirky for users to
> invoke and it would be nice to see those results in the kernel log as
> well and flag possibly flaky systems that way. (add a taint bit, etc.,
> etc.)
It may even make sense to merge in the full memtest86. The code is small
(both source and binary) and IIRC it shares a lot of init code with x86.
The remaining problem would then be how to maintain its tests up do date.
Willy
On Fri, Mar 21, 2008 at 10:45 PM, Willy Tarreau <[email protected]> wrote:
>
> On Fri, Mar 21, 2008 at 03:29:19PM +0100, Ingo Molnar wrote:
> >
> > * H. Peter Anvin <[email protected]> wrote:
> >
> > >> very nice patch! I always thought that this was the proper way to do
> > >> memtest - and we could in fact also do something like this after SMP
> > >> bringup, and hit the memory bus via multiple CPUs. [that will need a
> > >> different enumeration though than e820 maps]
> > >>
> > >> one structural observation: please make this unified functionality,
> > >> so that 32-bit kernels can make use of it too.
> > >>
> > >
> > > Indeed. Of course, it would also be nice if distros shipped
> > > bootloader-invoked prekernel test software, like memtest86+, by
> > > default.
> >
> > some do (Fedora for example), but it's still a bit quirky for users to
> > invoke and it would be nice to see those results in the kernel log as
> > well and flag possibly flaky systems that way. (add a taint bit, etc.,
> > etc.)
>
> It may even make sense to merge in the full memtest86. The code is small
> (both source and binary) and IIRC it shares a lot of init code with x86.
> The remaining problem would then be how to maintain its tests up do date.
memtester is another choice, and it is more easy to be merged.
YH
* Yinghai Lu <[email protected]> wrote:
> > one structural observation: please make this unified functionality,
> > so that 32-bit kernels can make use of it too.
>
> that will need to use PAE to switch 2G windows ....
well, please try some non-PAE, checks-direct-mappings approach - if
someone wants to extend it to the highmem bits i'm sure it will be done.
Ingo
On Sat, Mar 22, 2008 at 5:04 AM, Ingo Molnar <[email protected]> wrote:
>
> * Yinghai Lu <[email protected]> wrote:
>
> > > one structural observation: please make this unified functionality,
> > > so that 32-bit kernels can make use of it too.
> >
> > that will need to use PAE to switch 2G windows ....
>
> well, please try some non-PAE, checks-direct-mappings approach - if
> someone wants to extend it to the highmem bits i'm sure it will be done.
OK, First need to move some early_res code from e820_64.c to e820_32.c
or we can start to merge them. anyone is working on that?
YH
On Thu, 20 Mar 2008 23:58:33 -0700
Yinghai Lu <[email protected]> wrote:
>
> do simple memtest after init_memory_mapping
>
> use find_e820_area_size to find all ram range that is not reserved.
be careful, there's some special memory that e820 right now says is not reserved,
but still has bios data (the first 4Kb of memory come to mind)
--
If you want to reach me at my work email, use [email protected]
For development, discussion and tips for power savings,
visit http://www.lesswatts.org
Arjan van de Ven wrote:
> On Thu, 20 Mar 2008 23:58:33 -0700
> Yinghai Lu <[email protected]> wrote:
>
>> do simple memtest after init_memory_mapping
>>
>> use find_e820_area_size to find all ram range that is not reserved.
>
> be careful, there's some special memory that e820 right now says is not reserved,
> but still has bios data (the first 4Kb of memory come to mind)
>
Is that true even after Yinghai's changes? I have lost track of all the
patches...
-hpa
On Sat, Mar 22, 2008 at 1:48 PM, Arjan van de Ven <[email protected]> wrote:
> On Thu, 20 Mar 2008 23:58:33 -0700
>
> Yinghai Lu <[email protected]> wrote:
>
> >
>
> > do simple memtest after init_memory_mapping
> >
> > use find_e820_area_size to find all ram range that is not reserved.
>
> be careful, there's some special memory that e820 right now says is not reserved,
> but still has bios data (the first 4Kb of memory come to mind)
only test ranges that have E820_RAM and exclude range that is early_reserved...
so it is safe.
YH
On Sat, Mar 22, 2008 at 2:01 PM, H. Peter Anvin <[email protected]> wrote:
> Arjan van de Ven wrote:
> > On Thu, 20 Mar 2008 23:58:33 -0700
> > Yinghai Lu <[email protected]> wrote:
> >
> >> do simple memtest after init_memory_mapping
> >>
> >> use find_e820_area_size to find all ram range that is not reserved.
> >
> > be careful, there's some special memory that e820 right now says is not reserved,
> > but still has bios data (the first 4Kb of memory come to mind)
> >
>
> Is that true even after Yinghai's changes? I have lost track of all the
> patches...
find_e820_area_size should be safe.
YH
* Yinghai Lu <[email protected]> wrote:
> On Sat, Mar 22, 2008 at 5:04 AM, Ingo Molnar <[email protected]> wrote:
> >
> > * Yinghai Lu <[email protected]> wrote:
> >
> > > > one structural observation: please make this unified functionality,
> > > > so that 32-bit kernels can make use of it too.
> > >
> > > that will need to use PAE to switch 2G windows ....
> >
> > well, please try some non-PAE, checks-direct-mappings approach - if
> > someone wants to extend it to the highmem bits i'm sure it will be
> > done.
>
> OK, First need to move some early_res code from e820_64.c to e820_32.c
yeah, please do that.
> or we can start to merge them. anyone is working on that?
not that i know of - feel free.
Ingo