File: BadRAM-2.6.26.1.patch

package info (click to toggle)
kernel-patch-badram 2.6.28.2-1.1
  • links: PTS
  • area: main
  • in suites: squeeze
  • size: 152 kB
  • ctags: 3
  • sloc: makefile: 26
file content (860 lines) | stat: -rw-r--r-- 35,363 bytes parent folder | download | duplicates (2)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
diff -pruN a/arch/x86/configs/i386_defconfig b/arch/x86/configs/i386_defconfig
--- a/arch/x86/configs/i386_defconfig	2008-07-13 17:51:29.000000000 -0400
+++ b/arch/x86/configs/i386_defconfig	2008-07-14 13:55:23.000000000 -0400
@@ -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 a/arch/x86/configs/x86_64_defconfig b/arch/x86/configs/x86_64_defconfig
--- a/arch/x86/configs/x86_64_defconfig	2008-07-13 17:51:29.000000000 -0400
+++ b/arch/x86/configs/x86_64_defconfig	2008-07-14 13:55:23.000000000 -0400
@@ -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 a/arch/x86/Kconfig b/arch/x86/Kconfig
--- a/arch/x86/Kconfig	2008-07-13 17:51:29.000000000 -0400
+++ b/arch/x86/Kconfig	2008-07-14 13:55:23.000000000 -0400
@@ -907,6 +907,24 @@ 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 a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
--- a/arch/x86/mm/init_32.c	2008-07-13 17:51:29.000000000 -0400
+++ b/arch/x86/mm/init_32.c	2008-07-14 13:55:23.000000000 -0400
@@ -287,11 +287,16 @@ static void __init permanent_kmaps_init(
 	pkmap_page_table = pte;
 }
 
-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);
 		init_page_count(page);
+ 		if (PageBad(page))
+ 			*bad=1;
+ 		else
 		__free_page(page);
 		totalhigh_pages++;
 	} else
@@ -299,16 +304,20 @@ void __init add_one_highpage_init(struct
 }
 
 #ifndef CONFIG_NUMA
-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;
 }
@@ -317,7 +326,7 @@ 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 */
 
 pteval_t __PAGE_KERNEL = _PAGE_KERNEL;
@@ -563,7 +572,8 @@ static struct kcore_list kcore_mem, kcor
 
 void __init mem_init(void)
 {
-	int codesize, reservedpages, datasize, initsize;
+	int codesize, reservedpages, badpages, datasize, initsize;
+
 	int tmp, bad_ppro;
 
 #ifdef CONFIG_FLATMEM
@@ -586,14 +596,18 @@ 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;
@@ -602,6 +616,18 @@ 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",
@@ -613,6 +639,7 @@ void __init mem_init(void)
 		initsize >> 10,
 		(unsigned long) (totalhigh_pages << (PAGE_SHIFT-10))
 	       );
+#endif
 
 #if 1 /* double-sanity-check paranoia */
 	printk(KERN_INFO "virtual kernel memory layout:\n"
diff -pruN a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
--- a/arch/x86/mm/init_64.c	2008-07-13 17:51:29.000000000 -0400
+++ b/arch/x86/mm/init_64.c	2008-07-14 13:55:23.000000000 -0400
@@ -79,7 +79,7 @@ early_param("gbpages", parse_direct_gbpa
 
 void show_mem(void)
 {
-	long i, total = 0, reserved = 0;
+	long i, total = 0, reserved = 0, badram=0;
 	long shared = 0, cached = 0;
 	struct page *page;
 	pg_data_t *pgdat;
@@ -102,6 +102,8 @@ void show_mem(void)
 			total++;
 			if (PageReserved(page))
 				reserved++;
+			else if (PageBad(page))
+				badram++;
 			else if (PageSwapCache(page))
 				cached++;
 			else if (page_count(page))
@@ -110,6 +112,9 @@ 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 a/arch/x86/mm/pgtable_32.c b/arch/x86/mm/pgtable_32.c
--- a/arch/x86/mm/pgtable_32.c	2008-07-13 17:51:29.000000000 -0400
+++ b/arch/x86/mm/pgtable_32.c	2008-07-14 13:55:23.000000000 -0400
@@ -22,7 +22,7 @@
 
 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;
@@ -43,6 +43,8 @@ void show_mem(void)
 				highmem++;
 			if (PageReserved(page))
 				reserved++;
+			if (PageBad(page))
+				badram++;
 			else if (PageSwapCache(page))
 				cached++;
 			else if (page_count(page))
@@ -53,6 +55,9 @@ 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 a/CREDITS b/CREDITS
--- a/CREDITS	2008-07-13 17:51:29.000000000 -0400
+++ b/CREDITS	2008-07-14 13:55:23.000000000 -0400
@@ -2850,6 +2850,16 @@ S: 6 Karen Drive
 S: Malvern, Pennsylvania 19355
 S: USA
 
+N: Rick van Rein
+E: rick@vanrein.org
+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@linux.de
 W: http://www.freiburg.linux.de/~stepan/
diff -pruN a/Documentation/badram.txt b/Documentation/badram.txt
--- a/Documentation/badram.txt	1969-12-31 19:00:00.000000000 -0500
+++ b/Documentation/badram.txt	2008-07-14 13:55:23.000000000 -0400
@@ -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@vanrein.org
+       If you like it, a postcard would be much appreciated ;-)
+
+
+                                                              Enjoy,
+                                                               -Rick.
diff -pruN a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
--- a/Documentation/kernel-parameters.txt	2008-07-13 17:51:29.000000000 -0400
+++ b/Documentation/kernel-parameters.txt	2008-07-14 13:55:23.000000000 -0400
@@ -36,6 +36,7 @@ parameter is applicable:
 	APM	Advanced Power Management support is enabled.
 	AVR32	AVR32 architecture 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
@@ -325,6 +326,8 @@ 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 a/Documentation/memory.txt b/Documentation/memory.txt
--- a/Documentation/memory.txt	2008-07-13 17:51:29.000000000 -0400
+++ b/Documentation/memory.txt	2008-07-14 13:55:23.000000000 -0400
@@ -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 a/include/asm-x86/page_32.h b/include/asm-x86/page_32.h
--- a/include/asm-x86/page_32.h	2008-07-13 17:51:29.000000000 -0400
+++ b/include/asm-x86/page_32.h	2008-07-14 13:55:23.000000000 -0400
@@ -72,6 +72,8 @@ typedef struct page *pgtable_t;
 #define pfn_valid(pfn)		((pfn) < max_mapnr)
 #endif /* CONFIG_FLATMEM */
 
+#define phys_to_page(x)         pfn_to_page((unsigned long)(x) >> PAGE_SHIFT)
+
 extern int nx_enabled;
 
 /*
diff -pruN a/include/linux/kernel.h b/include/linux/kernel.h
--- a/include/linux/kernel.h	2008-07-13 17:51:29.000000000 -0400
+++ b/include/linux/kernel.h	2008-07-14 13:55:23.000000000 -0400
@@ -174,6 +174,8 @@ 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 a/include/linux/page-flags.h b/include/linux/page-flags.h
--- a/include/linux/page-flags.h	2008-07-13 17:51:29.000000000 -0400
+++ b/include/linux/page-flags.h	2008-07-14 13:55:23.000000000 -0400
@@ -93,6 +93,9 @@ enum pageflags {
 	PG_mappedtodisk,	/* Has blocks allocated on-disk */
 	PG_reclaim,		/* To be reclaimed asap */
 	PG_buddy,		/* Page is free, on buddy lists */
+#ifdef CONFIG_BADRAM
+	PG_badram,              /* BadRam page */
+#endif
 #ifdef CONFIG_IA64_UNCACHED_ALLOCATOR
 	PG_uncached,		/* Page has been mapped as uncached */
 #endif
@@ -101,6 +104,7 @@ enum pageflags {
 
 #ifndef __GENERATING_BOUNDS_H
 
+
 /*
  * Macros to create function definitions for page flags
  */
@@ -150,6 +154,7 @@ struct page;	/* forward declaration */
 
 PAGEFLAG(Locked, locked) TESTSCFLAG(Locked, locked)
 PAGEFLAG(Error, error)
+
 PAGEFLAG(Referenced, referenced) TESTCLEARFLAG(Referenced, referenced)
 PAGEFLAG(Dirty, dirty) TESTSCFLAG(Dirty, dirty) __CLEARPAGEFLAG(Dirty, dirty)
 PAGEFLAG(LRU, lru) __CLEARPAGEFLAG(LRU, lru)
@@ -161,6 +166,14 @@ PAGEFLAG(Reserved, reserved) __CLEARPAGE
 PAGEFLAG(Private, private) __CLEARPAGEFLAG(Private, private)
 	__SETPAGEFLAG(Private, private)
 
+#ifdef CONFIG_BADRAM
+TESTPAGEFLAG(Bad, badram)
+SETPAGEFLAG(Bad, badram)
+TESTSETFLAG(Bad, badram)
+#else
+#define PageBad(page)          0
+#endif
+
 /*
  * Only test-and-set exist for PG_writeback.  The unconditional operators are
  * risky: they bypass page accounting.
@@ -173,6 +186,7 @@ PAGEFLAG(MappedToDisk, mappedtodisk)
 PAGEFLAG(Reclaim, reclaim) TESTCLEARFLAG(Reclaim, reclaim)
 PAGEFLAG(Readahead, reclaim)		/* Reminder to do async read-ahead */
 
+
 #ifdef CONFIG_HIGHMEM
 /*
  * Must use a macro here due to header dependency issues. page_zone() is not
diff -pruN a/lib/cmdline.c b/lib/cmdline.c
--- a/lib/cmdline.c	2008-07-13 17:51:29.000000000 -0400
+++ b/lib/cmdline.c	2008-07-14 13:55:23.000000000 -0400
@@ -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 a/mm/bootmem.c b/mm/bootmem.c
--- a/mm/bootmem.c	2008-07-13 17:51:29.000000000 -0400
+++ b/mm/bootmem.c	2008-07-14 13:55:23.000000000 -0400
@@ -386,10 +386,12 @@ 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 a/mm/page_alloc.c b/mm/page_alloc.c
--- a/mm/page_alloc.c	2008-07-13 17:51:29.000000000 -0400
+++ b/mm/page_alloc.c	2008-07-14 13:56:24.000000000 -0400
@@ -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)
  */
@@ -536,9 +537,11 @@ void __free_pages_bootmem(struct page *p
 {
 	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;
 
@@ -4396,6 +4399,91 @@ 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 (TestSetPageBad (pg))
+                               reserve_bootmem (addr, PAGE_SIZE, BOOTMEM_DEFAULT);
+               } 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)