[PATCH 2.6.24] mm: BadRAM support for broken memory

From: Rick van Rein
Date: Sun Mar 02 2008 - 09:15:45 EST

This is the latest version of the BadRAM patch, which makes it possible to
run Linux on broken memory. The patch supports the use of a lesser grade
of memory, which could be marketed more cheaply and which would thereby
decrease the environmental stress caused by the process of (memory) chip
manufacturing.

Over the years, feedback on this patch has invariably been positive and
enthousiastic. The patch, even though not part of mainstream Linux, still
managed to make lots of people happy:
- schools and other low-budget computer users
- people with partially defective RAM soldered onto laptop motherboards
- people with one faulty address due to wiring faults on their motherboard
- people who find it environmentally insane to toss out 99.99%-good hardware

The patch has been well-maintained over the years, mostly by volunteers
who keep track of kernel updates. The submitters have changed over the years,
but there have always been volunteers jumping in, sometimes within hours after
a new kernel appeared, and mostly within a day. I have processed support
requests and used them to learn and make the patch work optimally. It is
obvious to me that the patch is in good demand, and I think it earns to be
included in the mainstream kernel.

The current version supports ia32 and x86_64 architectures. Others would
be unpractical to add on a patch outside mainstream Linux, but it ought to
be straightforward to add support for other architectures as well.

For more information, read Documentation/badram.txt or visit the homepage
for the patch, http://rick.vanrein.org/linux/badram/

Signed-off-by: Rick van Rein <rick@xxxxxxxxxxx>

diff -pruN linux-2.6.24.orig/arch/x86/configs/i386_defconfig linux-2.6.24/arch/x86/configs/i386_defconfig
--- linux-2.6.24.orig/arch/x86/configs/i386_defconfig 2008-01-24 17:58:37.000000000 -0500
+++ linux-2.6.24/arch/x86/configs/i386_defconfig 2008-02-05 22:18:57.000000000 -0500
@@ -198,6 +198,7 @@ CONFIG_DMIID=y
# CONFIG_NOHIGHMEM is not set
CONFIG_HIGHMEM4G=y
# CONFIG_HIGHMEM64G is not set
+CONFIG_BADRAM=y
CONFIG_PAGE_OFFSET=0xC0000000
CONFIG_HIGHMEM=y
CONFIG_ARCH_POPULATES_NODE_MAP=y
diff -pruN linux-2.6.24.orig/arch/x86/configs/x86_64_defconfig linux-2.6.24/arch/x86/configs/x86_64_defconfig
--- linux-2.6.24.orig/arch/x86/configs/x86_64_defconfig 2008-01-24 17:58:37.000000000 -0500
+++ linux-2.6.24/arch/x86/configs/x86_64_defconfig 2008-02-05 23:15:17.000000000 -0500
@@ -132,6 +132,7 @@ CONFIG_X86_CPUID=y
CONFIG_X86_HT=y
CONFIG_X86_IO_APIC=y
CONFIG_X86_LOCAL_APIC=y
+CONFIG_BADRAM=y
CONFIG_MTRR=y
CONFIG_SMP=y
CONFIG_SCHED_SMT=y
diff -pruN linux-2.6.24.orig/arch/x86/Kconfig linux-2.6.24/arch/x86/Kconfig
--- linux-2.6.24.orig/arch/x86/Kconfig 2008-01-24 17:58:37.000000000 -0500
+++ linux-2.6.24/arch/x86/Kconfig 2008-02-05 22:52:33.000000000 -0500
@@ -813,6 +813,24 @@ config X86_PAE
has the cost of more pagetable lookup overhead, and also
consumes more pagetable space per process.

+
+config BADRAM
+ bool "Work around bad spots in RAM"
+ default y
+ help
+ This small kernel extension makes it possible to use memory chips
+ which are not entirely correct. It works by never allocating the
+ places that are wrong. Those places are specified with the badram
+ boot option to LILO. Read Documentation/badram.txt and/or visit
+ http://home.zonnet.nl/vanrein/badram for information.
+
+ This option co-operates well with a second boot option from LILO
+ that starts memtest86, which is able to automatically produce the
+ patterns for the commandline in case of memory trouble.
+
+ It is safe to say 'Y' here, and it is advised because there is no
+ performance impact.
+
# Common NUMA Features
config NUMA
bool "Numa Memory Allocation and Scheduler Support (EXPERIMENTAL)"
diff -pruN linux-2.6.24.orig/arch/x86/mm/init_32.c linux-2.6.24/arch/x86/mm/init_32.c
--- linux-2.6.24.orig/arch/x86/mm/init_32.c 2008-01-24 17:58:37.000000000 -0500
+++ linux-2.6.24/arch/x86/mm/init_32.c 2008-02-05 23:10:33.000000000 -0500
@@ -275,25 +275,31 @@ static void __init permanent_kmaps_init(
pkmap_page_table = pte;
}

-static void __meminit free_new_highpage(struct page *page)
+static void __meminit free_new_highpage(struct page *page, int* bad)
{
init_page_count(page);
- __free_page(page);
+ if (PageBad(page))
+ *bad=1;
+ else
+ __free_page(page);
totalhigh_pages++;
}

-void __init add_one_highpage_init(struct page *page, int pfn, int bad_ppro)
+void __init add_one_highpage_init(struct page *page, int pfn, int bad_ppro,
+ int* bad)
{
+ *bad=0;
if (page_is_ram(pfn) && !(bad_ppro && page_kills_ppro(pfn))) {
ClearPageReserved(page);
- free_new_highpage(page);
+ free_new_highpage(page, bad);
} else
SetPageReserved(page);
}

static int __meminit add_one_highpage_hotplug(struct page *page, unsigned long pfn)
{
- free_new_highpage(page);
+ int dummy;
+ free_new_highpage(page, &dummy);
totalram_pages++;
#ifdef CONFIG_FLATMEM
max_mapnr = max(pfn, max_mapnr);
@@ -316,17 +322,21 @@ void __meminit online_page(struct page *


#ifdef CONFIG_NUMA
-extern void set_highmem_pages_init(int);
+extern void set_highmem_pages_init(int bad_ppro, int* pbad);
#else
-static void __init set_highmem_pages_init(int bad_ppro)
+static void __init set_highmem_pages_init(int bad_ppro, int* pbad)
{
- int pfn;
+ int pfn, bad;
for (pfn = highstart_pfn; pfn < highend_pfn; pfn++) {
/*
* Holes under sparsemem might not have no mem_map[]:
*/
- if (pfn_valid(pfn))
- add_one_highpage_init(pfn_to_page(pfn), pfn, bad_ppro);
+ if (pfn_valid(pfn)){
+ add_one_highpage_init(pfn_to_page(pfn), pfn, bad_ppro,
+ &bad);
+ if(bad)
+ (*pbad)++;
+ }
}
totalram_pages += totalhigh_pages;
}
@@ -335,7 +345,7 @@ static void __init set_highmem_pages_ini
#else
#define kmap_init() do { } while (0)
#define permanent_kmaps_init(pgd_base) do { } while (0)
-#define set_highmem_pages_init(bad_ppro) do { } while (0)
+#define set_highmem_pages_init(bad_ppro, pbad) do { } while (0)
#endif /* CONFIG_HIGHMEM */

unsigned long long __PAGE_KERNEL = _PAGE_KERNEL;
@@ -625,7 +635,7 @@ static struct kcore_list kcore_mem, kcor
void __init mem_init(void)
{
extern int ppro_with_ram_bug(void);
- int codesize, reservedpages, datasize, initsize;
+ int codesize, reservedpages, badpages, datasize, initsize;
int tmp;
int bad_ppro;

@@ -649,14 +659,18 @@ void __init mem_init(void)
totalram_pages += free_all_bootmem();

reservedpages = 0;
- for (tmp = 0; tmp < max_low_pfn; tmp++)
+ badpages = 0;
+ for (tmp = 0; tmp < max_low_pfn; tmp++){
/*
- * Only count reserved RAM pages
+ * Only count reserved and bad RAM pages
*/
if (page_is_ram(tmp) && PageReserved(pfn_to_page(tmp)))
reservedpages++;
+ if (page_is_ram(tmp) && PageBad(pfn_to_page(tmp)))
+ badpages++;
+ }

- set_highmem_pages_init(bad_ppro);
+ set_highmem_pages_init(bad_ppro, &badpages);

codesize = (unsigned long) &_etext - (unsigned long) &_text;
datasize = (unsigned long) &_edata - (unsigned long) &_etext;
@@ -665,6 +679,18 @@ void __init mem_init(void)
kclist_add(&kcore_mem, __va(0), max_low_pfn << PAGE_SHIFT);
kclist_add(&kcore_vmalloc, (void *)VMALLOC_START,
VMALLOC_END-VMALLOC_START);
+#ifdef CONFIG_BADRAM
+ printk(KERN_INFO "Memory: %luk/%luk available (%dk kernel code, %dk reserved, %dk data, %dk init, %ldk highmem, %dk BadRAM)\n",
+ (unsigned long) nr_free_pages() << (PAGE_SHIFT-10),
+ num_physpages << (PAGE_SHIFT-10),
+ codesize >> 10,
+ reservedpages << (PAGE_SHIFT-10),
+ datasize >> 10,
+ initsize >> 10,
+ (unsigned long) (totalhigh_pages << (PAGE_SHIFT-10)),
+ badpages << (PAGE_SHIFT-10)
+ );
+#else

printk(KERN_INFO "Memory: %luk/%luk available (%dk kernel code, %dk reserved, %dk data, %dk init, %ldk highmem)\n",
(unsigned long) nr_free_pages() << (PAGE_SHIFT-10),
@@ -675,6 +701,7 @@ void __init mem_init(void)
initsize >> 10,
(unsigned long) (totalhigh_pages << (PAGE_SHIFT-10))
);
+#endif

#if 1 /* double-sanity-check paranoia */
printk("virtual kernel memory layout:\n"
diff -pruN linux-2.6.24.orig/arch/x86/mm/init_64.c linux-2.6.24/arch/x86/mm/init_64.c
--- linux-2.6.24.orig/arch/x86/mm/init_64.c 2008-01-24 17:58:37.000000000 -0500
+++ linux-2.6.24/arch/x86/mm/init_64.c 2008-02-05 23:18:27.000000000 -0500
@@ -63,7 +63,7 @@ DEFINE_PER_CPU(struct mmu_gather, mmu_ga

void show_mem(void)
{
- long i, total = 0, reserved = 0;
+ long i, total = 0, reserved = 0, badram=0;
long shared = 0, cached = 0;
pg_data_t *pgdat;
struct page *page;
@@ -85,6 +85,8 @@ void show_mem(void)
total++;
if (PageReserved(page))
reserved++;
+ else if (PageBad(page))
+ badram++;
else if (PageSwapCache(page))
cached++;
else if (page_count(page))
@@ -93,6 +95,10 @@ void show_mem(void)
}
printk(KERN_INFO "%lu pages of RAM\n", total);
printk(KERN_INFO "%lu reserved pages\n",reserved);
+#ifdef CONFIG_BADRAM
+ printk(KERN_INFO "%lu pages of BadRAM\n",badram);
+#endif
+
printk(KERN_INFO "%lu pages shared\n",shared);
printk(KERN_INFO "%lu pages swap cached\n",cached);
}
diff -pruN linux-2.6.24.orig/arch/x86/mm/pgtable_32.c linux-2.6.24/arch/x86/mm/pgtable_32.c
--- linux-2.6.24.orig/arch/x86/mm/pgtable_32.c 2008-01-24 17:58:37.000000000 -0500
+++ linux-2.6.24/arch/x86/mm/pgtable_32.c 2008-02-05 23:14:12.000000000 -0500
@@ -26,7 +26,7 @@

void show_mem(void)
{
- int total = 0, reserved = 0;
+ int total = 0, reserved = 0, badram = 0;
int shared = 0, cached = 0;
int highmem = 0;
struct page *page;
@@ -48,6 +48,8 @@ void show_mem(void)
highmem++;
if (PageReserved(page))
reserved++;
+ if (PageBad(page))
+ badram++;
else if (PageSwapCache(page))
cached++;
else if (page_count(page))
@@ -58,6 +60,9 @@ void show_mem(void)
printk(KERN_INFO "%d pages of RAM\n", total);
printk(KERN_INFO "%d pages of HIGHMEM\n", highmem);
printk(KERN_INFO "%d reserved pages\n", reserved);
+#ifdef CONFIG_BADRAM
+ printk(KERN_INFO "%d pages of badRAM\n", badram);
+#endif
printk(KERN_INFO "%d pages shared\n", shared);
printk(KERN_INFO "%d pages swap cached\n", cached);

diff -pruN linux-2.6.24.orig/CREDITS linux-2.6.24/CREDITS
--- linux-2.6.24.orig/CREDITS 2008-01-24 17:58:37.000000000 -0500
+++ linux-2.6.24/CREDITS 2008-02-05 23:20:34.000000000 -0500
@@ -2840,6 +2840,16 @@ S: 6 Karen Drive
S: Malvern, Pennsylvania 19355
S: USA

+N: Rick van Rein
+E: rick@xxxxxxxxxxx
+W: http://rick.vanrein.org/
+D: Memory, the BadRAM subsystem dealing with statically challanged RAM modules.
+S: Haarlebrink 5
+S: 7544 WP Enschede
+S: The Netherlands
+P: 1024D/89754606 CD46 B5F2 E876 A5EE 9A85 1735 1411 A9C2 8975 4606
+
+
N: Stefan Reinauer
E: stepan@xxxxxxxx
W: http://www.freiburg.linux.de/~stepan/
diff -pruN linux-2.6.24.orig/Documentation/badram.txt linux-2.6.24/Documentation/badram.txt
--- linux-2.6.24.orig/Documentation/badram.txt 1969-12-31 19:00:00.000000000 -0500
+++ linux-2.6.24/Documentation/badram.txt 2008-02-05 23:29:49.000000000 -0500
@@ -0,0 +1,275 @@
+INFORMATION ON USING BAD RAM MODULES
+====================================
+
+Introduction
+ RAM is getting smaller and smaller, and as a result, also more and more
+ vulnerable. This makes the manufacturing of hardware more expensive,
+ since an excessive amount of RAM chips must be discarded on account of
+ a single cell that is wrong. Similarly, static discharge may damage a
+ RAM module forever, which is usually remedied by replacing it
+ entirely.
+
+ This is not necessary, as the BadRAM code shows: By informing the Linux
+ kernel which addresses in a RAM are damaged, the kernel simply avoids
+ ever allocating such addresses but makes all the rest available.
+
+Reasons for this feature
+ There are many reasons why this kernel feature is useful:
+ - Chip manufacture is resource intensive; waste less and sleep better
+ - It's another chance to promote Linux as "the flexible OS"
+ - Some laptops have their RAM soldered in... and then it fails!
+ - It's plain cool ;-)
+
+Running example
+ To run this project, I was given two DIMMs, 32 MB each. One, that we
+ shall use as a running example in this text, contained 512 faulty bits,
+ spread over 1/4 of the address range in a regular pattern. Some tricks
+ with a RAM tester and a few binary calculations were sufficient to
+ write these faults down in 2 longword numbers.
+
+ The kernel recognised the correct number of pages with faults and did
+ not give them out for allocation. The allocation routines could
+ therefore progress as normally, without any adaption.
+ So, I gained 30 MB of DIMM which would otherwise have been thrown
+ away. After booting the kernel, the kernel behaved exactly as it
+ always had.
+
+Initial checks
+ If you experience RAM trouble, first read /usr/src/linux/memory.txt
+ and try out the mem=4M trick to see if at least some initial parts
+ of your RAM work well. The BadRAM routines halt the kernel in panic
+ if the reserved area of memory (containing kernel stuff) contains
+ a faulty address.
+
+Running a RAM checker
+ The memory checker is not built into the kernel, to avoid delays at
+ runtime. If you experience problems that may be caused by RAM, run
+ a good RAM checker, such as
+ http://reality.sgi.com/cbrady_denver/memtest86
+ The output of a RAM checker provides addresses that went wrong. In
+ the 32 MB chip with 512 faulty bits mentioned above, the errors were
+ found in the 8MB-16MB range (the DIMM was in slot #0) at addresses
+ xxx42f4
+ xxx62f4
+ xxxc2f4
+ xxxe2f4
+ and the error was a "sticky 1 bit", a memory bit that stayed "1" no
+ matter what was written to it. The regularity of this pattern
+ suggests the death of a buffer at the output stages of a row on one of
+ the chips. I expect such regularity to be commonplace. Finding this
+ regularity currently is human effort, but it should not be hard to
+ alter a RAM checker to capture it in some sort of pattern, possibly
+ the BadRAM patterns described below.
+
+ By the way, if you manage to get hold of memtest86 version 2.3 or
+ beyond, you can configure the printing mode to produce BadRAM patterns,
+ which find out exactly what you must enter on the LILO: commandline,
+ except that you shouldn't mention the added spacing. That means that
+ you can skip the following step, which saves you a *lot* of work.
+
+ Also by the way, if your machine has the ISA memory gap in the 15M-16M
+ range unstoppable, Linux can get in trouble. One way of handling that
+ situation is by specifying the total memory size to Linux with a boot
+ parameter mem=... and then to tell it to treat the 15M-16M range as
+ faulty with an additional boot parameter, for instance:
+ mem=24M badram=0x00f00000,0xfff00000
+ if you installed 24MB of RAM in total.
+
+ If you use this patch on an x86_64 architecture, your addresses are
+ twice as long. Fill up with zeroes in the address and with f's in
+ the mask. The latter example would thus become:
+ mem=24M badram=0x0000000000f00000,0xfffffffffff00000
+ The patch applies the changes to both x86 and x86_64 code bases
+ at the same time. Patching but not compiling maps the entire
+ source tree at once, which makes more sense than splitting the
+ patch into an x86 and x86_64 branch, because those two branches
+ could not be applied at the same time because they would overlap.
+
+Capturing errors in a pattern
+ Instead of manually providing all 512 errors to the kernel, it's nicer
+ to generate a pattern. Since the regularity is based on address decoding
+ software, which generally takes certain bits into account and ignores
+ others, we shall provide a faulty address F, together with a bit mask M
+ that specifies which bits must be equal to F. In C code, an address A
+ is faulty if and only if
+ (F & M) == (A & M)
+ or alternately (closer to a hardware implementation):
+ ~((F ^ A) & M)
+ In the example 32 MB chip, we had the faulty addresses in 8MB-16MB:
+ xxx42f4 ....0100....
+ xxx62f4 ....0110....
+ xxxc2f4 ....1100....
+ xxxe2f4 ....1110....
+ The second column represents the alternating hex digit in binary form.
+ Apperantly, the first and one-but last binary digit can be anything,
+ so the binary mask for that part is 0101. The mask for the part after
+ this is 0xfff, and the part before should select anything in the range
+ 8MB-16MB, or 0x00800000-0x01000000; this is done with a bitmask
+ 0xff80xxxx. Combining these partial masks, we get:
+ F=0x008042f4 M=0xff805fff
+ That covers everything for this DIMM; for more complicated failing
+ DIMMs, or for a combination of multiple failing DIMMs, it can be
+ necessary to set up a number of such F/M pairs.
+
+Rebooting Linux
+ Now that these patterns are known (and double-checked, the calculations
+ are highly error-prone... it would be neat to test them in the RAM
+ checker...) we simply restart Linux with these F/M pairs as a parameter
+ If you normally boot as follows:
+ LILO: linux
+ you should now boot with
+ LILO: linux badram=0x008042f4,0xff805fff
+ or perhaps by mentioning more F/M pairs in an order F0,M0,F1,M1,...
+ When you provide an odd number of arguments to badram, the default mask
+ 0xffffffff (only one address matched) is applied to the pattern.
+
+ Beware of the commandline length. At least up to LILO version 0.21,
+ the commandline is cut off after the 78th character; later versions
+ may go as far as the kernel goes, namely 255 characters. In no way is
+ it possible to enter more than 10 numbers to the badram boot option.
+
+ When the kernel now boots, it should not give any trouble with RAM.
+ Mind you, this is under the assumption that the kernel and its data
+ storage do not overlap an erroneous part. If this happens, and the
+ kernel does not choke on it right away, it will stop with a panic.
+ You will need to provide a RAM where the initial, say 2MB, is faultless
+
+ Now look up your memory status with
+ dmesg | grep ^Memory:
+ which prints a single line with information like
+ Memory: 158524k/163840k available
+ (940k kernel code,
+ 412k reserved,
+ 1856k data,
+ 60k init,
+ 0k highmem,
+ 2048k BadRAM)
+ The latter entry, the badram, is 2048k to represent the loss of 2MB
+ of general purpose RAM due to the errors. Or, positively rephrased,
+ instead of throwing out 32MB as useless, you only throw out 2MB.
+
+ If the system is stable (try compiling a few kernels, and do a few
+ finds in / or so) you may add the boot parameter to /etc/lilo.conf
+ as a line to _all_ the kernels that handle this trouble with a line
+ append="badram=0x008042f4,0xff805fff"
+ after which you run "lilo".
+ Warning: Don't experiment with these settings on your only boot image.
+ If the BadRAM overlays kernel code, data, init, or other reserved
+ memory, the kernel will halt in panic. Try settings on a test boot
+ image first, and if you get a panic you should change the order of
+ your DIMMs [which may involve buying a new one just to be able to
+ change the order].
+
+ You are allowed to enter any number of BadRAM patterns in all the
+ places documented in this file. They will all apply. It is even
+ possible to mention several BadRAM patterns in a single place. The
+ completion of an odd number of arguments with the default mask is
+ done separately for each badram=... option.
+
+Kernel Customisation
+ Some people prefer to enter their badram patterns in the kernel, and
+ this is also possible. In mm/page_alloc.c there is an array of unsigned
+ long integers into which the parameters can be entered, prefixed with
+ the number of integers (twice the number of patterns). The array is
+ named badram_custom and it will be added to the BadRAM list whenever an
+ option 'badram' is provided on the commandline when booting, either
+ with or without additional patterns.
+
+ For the previous example, the code would become
+
+ static unsigned long __initdata badram_custom[] = {
+ 2, // Number of longwords that follow, as F/M pairs
+ 0x008042f4L, 0xff805fffL,
+ };
+
+ Even on this place you may assume the default mask to be filled in
+ when you enter an odd number of longwords. Specify the number of
+ longwords to be 0 to avoid influence of this custom BadRAM list.
+
+BadRAM classification
+ This technique may start a lively market for "dead" RAM. It is important
+ to realise that some RAMs are more dead than others. So, instead of
+ just providing a RAM size, it is also important to know the BadRAM
+ class, which is defined as follows:
+
+ A BadRAM class N means that at most 2^N bytes have a problem,
+ and that all problems with the RAMs are persistent: They
+ are predictable and always show up.
+
+ The DIMM that serves as an example here was of class 9, since 512=2^9
+ errors were found. Higher classes are worse, "correct" RAM is of class
+ -1 (or even less, at your choice).
+ Class N also means that the bitmask for your chip (if there's just one,
+ that is) counts N bits "0" and it means that (if no faults fall in the
+ same page) an amount of 2^N*PAGESIZE memory is lost, in the example on
+ an x86 architecture that would be 2^9*4k=2MB, which accounts for the
+ initial claim of 30MB RAM gained with this DIMM.
+
+ Note that this scheme has deliberately been defined to be independent
+ of memory technology and of computer architecture.
+
+Known Bugs
+ LILO is known to cut off commandlines which are too long. For the
+ lilo-0.21 distribution, a commandline may not exceed 78 characters,
+ while actually, 255 would be possible [on x86, kernel 2.2.16].
+ LILO does _not_ report too-long commandlines, but the error will
+ show up as either a panic at boot time, stating
+ panic: BadRAM page in initial area
+ or the dmesg line starting with Memory: will mention an unpredicted
+ number of kilobytes. (Note that the latter number only includes
+ errors in accessed memory.)
+
+Future Possibilities
+ It would be possible to use even more of the faulty RAMs by employing
+ them for slabs. The smaller allocation granularity of slabs makes it
+ possible to throw out just, say, 32 bytes surrounding an error. This
+ would mean that the example DIMM only looses 16kB instead of 2MB.
+ It might even be possible to allocate the slabs in such a way that,
+ where possible, the remaining bytes in a slab structure are allocated
+ around the error, reducing the RAM loss to 0 in the optimal situation!
+
+ However, this yield is somewhat faked: It is possible to provide 512
+ pages of 32-byte slabs, but it is not certain that anyone would use
+ that many 32-byte slabs at any time.
+
+ A better solution might be to alter the page allocation for a slab to
+ have a preference for BadRAM pages, and given those a special treatment.
+ This way, the BadRAM would be spread over all the slabs, which seems
+ more likely to be a `true' pay-off. This would yield more overhead at
+ slab allocation time, but on the other hand, by the nature of slabs,
+ such allocations are made as rare as possible, so it might not matter
+ that much. I am uncertain where to go.
+
+ Many suggestions have been made to insert a RAM checker at boot time;
+ since this would leave the time to do only very meager checking, it
+ is not a reasonable option; we already have a BIOS doing that in most
+ systems!
+
+ It would be interesting to integrate this functionality with the
+ self-verifying nature of ECC RAM. These memories can even distinguish
+ between recorable and unrecoverable errors! Such memory has been
+ handled in older operating systems by `testing' once-failed memory
+ blocks for a while, by placing only (reloadable) program code in it.
+ Unfortunately, I possess no faulty ECC modules to work this out.
+
+Names and Places
+ The home page of this project is on
+ http://rick.vanrein.org/linux/badram
+ This page also links to Nico Schmoigl's experimental extensions to
+ this patch (with debugging and a few other fancy things).
+
+ In case you have experiences with the BadRAM software which differ from
+ the test reportings on that site, I hope you will mail me with that
+ new information.
+
+ The BadRAM project is an idea and implementation by
+ Rick van Rein
+ Haarlebrink 5
+ 7544 WP Enschede
+ The Netherlands
+ rick@xxxxxxxxxxx
+ If you like it, a postcard would be much appreciated ;-)
+
+
+ Enjoy,
+ -Rick.
diff -pruN linux-2.6.24.orig/Documentation/kernel-parameters.txt linux-2.6.24/Documentation/kernel-parameters.txt
--- linux-2.6.24.orig/Documentation/kernel-parameters.txt 2008-01-24 17:58:37.000000000 -0500
+++ linux-2.6.24/Documentation/kernel-parameters.txt 2008-02-05 23:33:55.000000000 -0500
@@ -35,6 +35,7 @@ parameter is applicable:
APIC APIC support is enabled.
APM Advanced Power Management support is enabled.
AX25 Appropriate AX.25 support is enabled.
+ BADRAM Support for faulty RAM chips is enabled.
BLACKFIN Blackfin architecture is enabled.
DRM Direct Rendering Management support is enabled.
EDD BIOS Enhanced Disk Drive Services (EDD) is enabled
@@ -322,6 +323,8 @@ and is between 256 and 4096 characters.

autotest [IA64]

+ badram= [BADRAM] Avoid allocating faulty RAM addresses.
+
baycom_epp= [HW,AX25]
Format: <io>,<mode>

diff -pruN linux-2.6.24.orig/Documentation/memory.txt linux-2.6.24/Documentation/memory.txt
--- linux-2.6.24.orig/Documentation/memory.txt 2008-01-24 17:58:37.000000000 -0500
+++ linux-2.6.24/Documentation/memory.txt 2008-02-05 23:39:04.000000000 -0500
@@ -18,11 +18,22 @@ systems.
as you add more memory. Consider exchanging your
motherboard.

+ 4) A static discharge or production fault causes a RAM module
+ to have (predictable) errors, usually meaning that certain
+ bits cannot be set or reset. Instead of throwing away your
+ RAM module, you may read /usr/src/linux/Documentation/badram.txt
+ to learn how to detect, locate and circuimvent such errors
+ in your RAM module.
+
+
+
All of these problems can be addressed with the "mem=XXXM" boot option
(where XXX is the size of RAM to use in megabytes).
It can also tell Linux to use less memory than is actually installed.
If you use "mem=" on a machine with PCI, consider using "memmap=" to avoid
physical address space collisions.
+If this helps, read Documentation/badram.txt to learn how to
+find and circumvent memory errors.

See the documentation of your boot loader (LILO, loadlin, etc.) about
how to pass options to the kernel.
diff -pruN linux-2.6.24.orig/include/asm-x86/page_32.h linux-2.6.24/include/asm-x86/page_32.h
--- linux-2.6.24.orig/include/asm-x86/page_32.h 2008-01-24 17:58:37.000000000 -0500
+++ linux-2.6.24/include/asm-x86/page_32.h 2008-02-05 23:43:00.000000000 -0500
@@ -189,6 +189,7 @@ extern int page_is_ram(unsigned long pag
#define pfn_valid(pfn) ((pfn) < max_mapnr)
#endif /* CONFIG_FLATMEM */
#define virt_to_page(kaddr) pfn_to_page(__pa(kaddr) >> PAGE_SHIFT)
+#define phys_to_page(x) pfn_to_page((unsigned long)(x) >> PAGE_SHIFT)

#define virt_addr_valid(kaddr) pfn_valid(__pa(kaddr) >> PAGE_SHIFT)

diff -pruN linux-2.6.24.orig/include/asm-x86/page_64.h linux-2.6.24/include/asm-x86/page_64.h
--- linux-2.6.24.orig/include/asm-x86/page_64.h 2008-01-24 17:58:37.000000000 -0500
+++ linux-2.6.24/include/asm-x86/page_64.h 2008-02-05 23:44:26.000000000 -0500
@@ -126,6 +126,7 @@ extern unsigned long __phys_addr(unsigne
#endif

#define virt_to_page(kaddr) pfn_to_page(__pa(kaddr) >> PAGE_SHIFT)
+#define phys_to_page(x) pfn_to_page((unsigned long)(x) >> PAGE_SHIFT)
#define virt_addr_valid(kaddr) pfn_valid(__pa(kaddr) >> PAGE_SHIFT)
#define pfn_to_kaddr(pfn) __va((pfn) << PAGE_SHIFT)

diff -pruN linux-2.6.24.orig/include/linux/kernel.h linux-2.6.24/include/linux/kernel.h
--- linux-2.6.24.orig/include/linux/kernel.h 2008-01-24 17:58:37.000000000 -0500
+++ linux-2.6.24/include/linux/kernel.h 2008-02-05 23:45:34.000000000 -0500
@@ -164,6 +164,8 @@ extern int vsscanf(const char *, const c

extern int get_option(char **str, int *pint);
extern char *get_options(const char *str, int nints, int *ints);
+extern int get_longoption (char **str, long *plong);
+extern char *get_longoptions(const char *str, int nlongs, long *longs);
extern unsigned long long memparse(char *ptr, char **retptr);

extern int core_kernel_text(unsigned long addr);
diff -pruN linux-2.6.24.orig/include/linux/page-flags.h linux-2.6.24/include/linux/page-flags.h
--- linux-2.6.24.orig/include/linux/page-flags.h 2008-01-24 17:58:37.000000000 -0500
+++ linux-2.6.24/include/linux/page-flags.h 2008-02-05 23:47:58.000000000 -0500
@@ -93,6 +93,9 @@
/* PG_readahead is only used for file reads; PG_reclaim is only for writes */
#define PG_readahead PG_reclaim /* Reminder to do async read-ahead */

+#define PG_badram 20 /* BadRam page */
+
+
/* PG_owner_priv_1 users should have descriptive aliases */
#define PG_checked PG_owner_priv_1 /* Used by some filesystems */
#define PG_pinned PG_owner_priv_1 /* Xen pinned pagetable */
@@ -108,6 +111,15 @@
#define PG_uncached 31 /* Page has been mapped as uncached */
#endif

+#ifdef CONFIG_BADRAM
+#define PageBad(page) test_bit(PG_badram, &(page)->flags)
+#define PageSetBad(page) set_bit(PG_badram, &(page)->flags)
+#define PageTestandSetBad(page) test_and_set_bit(PG_badram, &(page)->flags)
+#else
+#define PageBad(page) 0
+#endif
+
+
/*
* Manipulation of page state flags
*/
diff -pruN linux-2.6.24.orig/lib/cmdline.c linux-2.6.24/lib/cmdline.c
--- linux-2.6.24.orig/lib/cmdline.c 2008-01-24 17:58:37.000000000 -0500
+++ linux-2.6.24/lib/cmdline.c 2008-02-05 23:51:47.000000000 -0500
@@ -114,6 +114,70 @@ char *get_options(const char *str, int n
}

/**
+ * get_longoption - Parse long from an option string
+ * @str: option string
+ * @plong: (output) long value parsed from @str
+ *
+ * Read a long from an option string; if available accept a subsequent
+ * comma as well.
+ *
+ * Return values:
+ * 0 : no long in string
+ * 1 : long found, no subsequent comma
+ * 2 : long found including a subsequent comma
+ */
+
+int get_longoption (char **str, long *plong)
+{
+ char *cur = *str;
+
+ if (!cur || !(*cur))
+ return 0;
+ *plong = simple_strtol (cur, str, 0);
+ if (cur == *str)
+ return 0;
+ if (**str == ',') {
+ (*str)++;
+ return 2;
+ }
+
+ return 1;
+}
+
+/**
+ * get_longoptions - Parse a string into a list of longs
+ * @str: String to be parsed
+ * @nlongs: size of long array
+ * @longs: long array
+ *
+ * This function parses a string containing a comma-separated
+ * list of longs. The parse halts when the array is
+ * full, or when no more numbers can be retrieved from the
+ * string.
+ *
+ * Return value is the character in the string which caused
+ * the parse to end (typically a null terminator, if @str is
+ * completely parseable).
+ */
+
+char *get_longoptions(const char *str, int nlongs, long *longs)
+{
+ int res, i = 1;
+
+ while (i < nlongs) {
+ res = get_longoption ((char **)&str, longs + i);
+ if (res == 0)
+ break;
+ i++;
+ if (res == 1)
+ break;
+ }
+ longs[0] = i - 1;
+ return (char *)str;
+}
+
+
+/**
* memparse - parse a string with mem suffixes into a number
* @ptr: Where parse begins
* @retptr: (output) Pointer to next char after parse completes
@@ -151,3 +215,5 @@ unsigned long long memparse (char *ptr,
EXPORT_SYMBOL(memparse);
EXPORT_SYMBOL(get_option);
EXPORT_SYMBOL(get_options);
+EXPORT_SYMBOL(get_longoption);
+EXPORT_SYMBOL(get_longoptions);
diff -pruN linux-2.6.24.orig/mm/bootmem.c linux-2.6.24/mm/bootmem.c
--- linux-2.6.24.orig/mm/bootmem.c 2008-01-24 17:58:37.000000000 -0500
+++ linux-2.6.24/mm/bootmem.c 2008-02-05 23:53:57.000000000 -0500
@@ -317,10 +317,12 @@ static unsigned long __init free_all_boo
pfn = PFN_DOWN(bdata->node_boot_start);
idx = bdata->node_low_pfn - pfn;
map = bdata->node_bootmem_map;
+#ifndef CONFIG_BADRAM /* no idea if this is really needed */
/* Check physaddr is O(LOG2(BITS_PER_LONG)) page aligned */
if (bdata->node_boot_start == 0 ||
ffs(bdata->node_boot_start) - PAGE_SHIFT > ffs(BITS_PER_LONG))
gofast = 1;
+#endif
for (i = 0; i < idx; ) {
unsigned long v = ~map[i / BITS_PER_LONG];

diff -pruN linux-2.6.24.orig/mm/page_alloc.c linux-2.6.24/mm/page_alloc.c
--- linux-2.6.24.orig/mm/page_alloc.c 2008-01-24 17:58:37.000000000 -0500
+++ linux-2.6.24/mm/page_alloc.c 2008-02-06 00:03:28.000000000 -0500
@@ -10,6 +10,7 @@
* Reshaped it to be a zoned allocator, Ingo Molnar, Red Hat, 1999
* Discontiguous memory support, Kanoj Sarcar, SGI, Nov 1999
* Zone balancing, Kanoj Sarcar, SGI, Jan 2000
+ * BadRAM handling, Rick van Rein, Feb 2001
* Per cpu hot/cold page lists, bulk allocation, Martin J. Bligh, Sept 2002
* (lots of bits borrowed from Ingo Molnar & Andrew Morton)
*/
@@ -540,9 +541,11 @@ static void __free_pages_ok(struct page
void fastcall __init __free_pages_bootmem(struct page *page, unsigned int order)
{
if (order == 0) {
__ClearPageReserved(page);
- set_page_count(page, 0);
- set_page_refcounted(page);
+ if(!PageBad(page)){
+ set_page_count(page, 0);
+ set_page_refcounted(page);
__free_page(page);
+ }
} else {
int loop;
@@ -4378,6 +4381,91 @@ EXPORT_SYMBOL(pfn_to_page);
EXPORT_SYMBOL(page_to_pfn);
#endif /* CONFIG_OUT_OF_LINE_PFN_TO_PAGE */

+
+#ifdef CONFIG_BADRAM
+
+/* Given a pointed-at address and a mask, increment the page so that the
+ * mask hides the increment. Return 0 if no increment is possible.
+ */
+static int __init next_masked_address (unsigned long *addrp, unsigned long mask)
+{
+ unsigned long inc=1;
+ unsigned long newval = *addrp;
+ while (inc & mask)
+ inc += inc;
+ while (inc != 0) {
+ newval += inc;
+ newval &= ~mask;
+ newval |= ((*addrp) & mask);
+ if (newval > *addrp) {
+ *addrp = newval;
+ return 1;
+ }
+ do {
+ inc += inc;
+ } while (inc & ~mask);
+ while (inc & mask)
+ inc += inc;
+ }
+ return 0;
+}
+
+
+void __init badram_markpages (int argc, unsigned long *argv) {
+ unsigned long addr, mask;
+ while (argc-- > 0) {
+ addr = *argv++;
+ mask = (argc-- > 0) ? *argv++ : ~0L;
+ mask |= ~PAGE_MASK; /* Optimalisation */
+ addr &= mask; /* Normalisation */
+ do {
+ struct page *pg = phys_to_page(addr);
+ printk(KERN_DEBUG "%016lx =%016lx\n",
+ addr >> PAGE_SHIFT,
+ (unsigned long)(pg-mem_map));
+ if (PageTestandSetBad (pg))
+ reserve_bootmem (addr, PAGE_SIZE);
+ } while (next_masked_address (&addr,mask));
+ }
+}
+
+
+/*********** CONFIG_BADRAM: CUSTOMISABLE SECTION STARTS HERE *****************/
+/* Enter your custom BadRAM patterns here as pairs of unsigned long integers. */
+/* For more information on these F/M pairs, refer to Documentation/badram.txt */
+
+static unsigned long __initdata badram_custom[] = {
+ 0, /* Number of longwords that follow, as F/M pairs */
+};
+
+
+/*********** CONFIG_BADRAM: CUSTOMISABLE SECTION ENDS HERE *******************/
+
+static int __init badram_setup (char *str)
+{
+ unsigned long opts[3];
+ BUG_ON(!mem_map);
+ printk (KERN_INFO "PAGE_OFFSET=0x%08lx\n", PAGE_OFFSET);
+ printk (KERN_INFO "BadRAM option is %s\n", str);
+ if (*str++ == '=')
+ while ((str = get_longoptions (str, 3, (long *) opts), *opts)) {
+ printk (KERN_INFO " --> marking 0x%08lx, 0x%08lx [%ld]\n",
+ opts[1], opts[2], opts[0]);
+ badram_markpages (*opts, opts+1);
+ if (*opts == 1)
+ break;
+ };
+ badram_markpages (*badram_custom, badram_custom+1);
+ return 0;
+}
+
+__setup("badram", badram_setup);
+
+#endif /* CONFIG_BADRAM */
+
+
+
+
/* Return a pointer to the bitmap storing bits affecting a block of pages */
static inline unsigned long *get_pageblock_bitmap(struct zone *zone,
unsigned long pfn)
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/