[PATCH 00/16] Adaptive read-ahead V7

[PATCH 00/16] Adaptive read-ahead V7

[Wu Fengguang]

This is the 7th version of adaptive read-ahead patch.

There are various code cleanups and polish ups:
- new tunable parameters: readahead_hit_rate/readahead_live_chunk
- support sparse sequential accesses
- delay look-ahead in laptop mode
- disable look-ahead for loopback file
- make mandatory thrashing protection more simple and robust
- attempt to improve responsiveness on large I/O request size

Support for sparse reads is disabled by default. One must increase
/proc/sys/vm/readahead_hit_rate to explicitly enable it. Please
refer to Documentation/sysctl/vm.txt for details.

Currently the linux kernel does not support inter-file read-ahead.
Tero Grundstr?m takes an intresting approach that achieves it: pack
a dir of small files into a loopback file with reiserfs filesystem, and
turn on sparse read support. But be prepared to waste some memory by
this way :(

For crazy laptop users who prefer aggressive read-ahead, here is the way:

# echo 10000 > /proc/sys/vm/readahead_ratio
# blockdev --setra 524280 /dev/hda      # this is the max possible value

Notes:
- It is still an untested feature.
- It is safer to use blockdev+fadvise to increase ra-max for a single file,
  which needs patching your movie player.
- Be sure to restore them to sane values in normal operations!

Regards,
Wu

[PATCH 01/16] mm: delayed page activation

[Wu Fengguang]

[-- Attachment #1: mm-delayed-activation.patch --]
[-- Type: text/plain, Size: 4732 bytes --]

When a page is referenced the second time in inactive_list, mark it with
PG_activate instead of moving it into active_list immediately. The actual
moving work is delayed to vmscan time.

This implies two essential changes:
- keeps the adjecency of pages in lru;
- lifts the page reference counter max from 1 to 3.

And leads to the following improvements:
- read-ahead for a leading reader will not be disturbed by a following reader;
- enables the thrashing protection logic to save pages for following readers;
- keeping relavant pages together helps improve I/O efficiency;
- and also helps decrease vm fragmantation;
- increased refcnt space might help page replacement algorithms.

Signed-off-by: Wu Fengguang <wfg@mail.ustc.edu.cn>
---

 include/linux/page-flags.h |   31 +++++++++++++++++++++++++++++++
 mm/page_alloc.c            |    1 +
 mm/swap.c                  |    9 ++++-----
 mm/vmscan.c                |    6 ++++++
 4 files changed, 42 insertions(+), 5 deletions(-)

--- linux-2.6.14-mm1.orig/include/linux/page-flags.h
+++ linux-2.6.14-mm1/include/linux/page-flags.h
@@ -76,6 +76,7 @@
 #define PG_reclaim		17	/* To be reclaimed asap */
 #define PG_nosave_free		18	/* Free, should not be written */
 #define PG_uncached		19	/* Page has been mapped as uncached */
+#define PG_activate		20	/* delayed activate */
 
 /*
  * Global page accounting.  One instance per CPU.  Only unsigned longs are
@@ -308,6 +309,12 @@ extern void __mod_page_state(unsigned lo
 #define SetPageUncached(page)	set_bit(PG_uncached, &(page)->flags)
 #define ClearPageUncached(page)	clear_bit(PG_uncached, &(page)->flags)
 
+#define PageActivate(page)	test_bit(PG_activate, &(page)->flags)
+#define SetPageActivate(page)	set_bit(PG_activate, &(page)->flags)
+#define ClearPageActivate(page)	clear_bit(PG_activate, &(page)->flags)
+#define TestClearPageActivate(page) test_and_clear_bit(PG_activate, &(page)->flags)
+#define TestSetPageActivate(page) test_and_set_bit(PG_activate, &(page)->flags)
+
 struct page;	/* forward declaration */
 
 int test_clear_page_dirty(struct page *page);
@@ -333,4 +340,28 @@ static inline void set_page_writeback(st
 #define ClearPageFsMisc(page)		clear_bit(PG_fs_misc, &(page)->flags)
 #define TestClearPageFsMisc(page)	test_and_clear_bit(PG_fs_misc, &(page)->flags)
 
+#if PG_activate < PG_referenced
+#error unexpected page flags order
+#endif
+
+#define PAGE_REFCNT_0		0
+#define PAGE_REFCNT_1		(1 << PG_referenced)
+#define PAGE_REFCNT_2		(1 << PG_activate)
+#define PAGE_REFCNT_3		((1 << PG_activate) | (1 << PG_referenced))
+#define PAGE_REFCNT_MASK	PAGE_REFCNT_3
+
+/*
+ * STATUS   REFERENCE COUNT
+ *  __                   0
+ *  _R       PAGE_REFCNT_1
+ *  A_       PAGE_REFCNT_2
+ *  AR       PAGE_REFCNT_3
+ *
+ *  A/R: Active / Referenced
+ */
+static inline unsigned long page_refcnt(struct page *page)
+{
+	return page->flags & PAGE_REFCNT_MASK;
+}
+
 #endif	/* PAGE_FLAGS_H */
--- linux-2.6.14-mm1.orig/mm/page_alloc.c
+++ linux-2.6.14-mm1/mm/page_alloc.c
@@ -488,6 +488,7 @@ static void prep_new_page(struct page *p
 
 	page->flags &= ~(1 << PG_uptodate | 1 << PG_error |
 			1 << PG_referenced | 1 << PG_arch_1 |
+			1 << PG_activate |
 			1 << PG_checked | 1 << PG_mappedtodisk);
 	set_page_private(page, 0);
 	set_page_refs(page, order);
--- linux-2.6.14-mm1.orig/mm/swap.c
+++ linux-2.6.14-mm1/mm/swap.c
@@ -29,7 +29,6 @@
 #include <linux/percpu.h>
 #include <linux/cpu.h>
 #include <linux/notifier.h>
-#include <linux/init.h>
 
 /* How many pages do we try to swap or page in/out together? */
 int page_cluster;
@@ -117,13 +116,13 @@ void fastcall activate_page(struct page 
  * Mark a page as having seen activity.
  *
  * inactive,unreferenced	->	inactive,referenced
- * inactive,referenced		->	active,unreferenced
- * active,unreferenced		->	active,referenced
+ * inactive,referenced		->	activate,unreferenced
+ * activate,unreferenced	->	activate,referenced
  */
 void fastcall mark_page_accessed(struct page *page)
 {
-	if (!PageActive(page) && PageReferenced(page) && PageLRU(page)) {
-		activate_page(page);
+	if (!PageActivate(page) && PageReferenced(page) && PageLRU(page)) {
+		SetPageActivate(page);
 		ClearPageReferenced(page);
 	} else if (!PageReferenced(page)) {
 		SetPageReferenced(page);
--- linux-2.6.14-mm1.orig/mm/vmscan.c
+++ linux-2.6.14-mm1/mm/vmscan.c
@@ -443,6 +443,12 @@ static int shrink_list(struct list_head 
 		if (PageWriteback(page))
 			goto keep_locked;
 
+		if (PageActivate(page)) {
+			ClearPageActivate(page);
+			ClearPageReferenced(page);
+			goto activate_locked;
+		}
+
 		referenced = page_referenced(page, 1, sc->priority <= 0);
 		/* In active use or really unfreeable?  Activate it. */
 		if (referenced && page_mapping_inuse(page))

--

Re: [PATCH 01/16] mm: delayed page activation

[Nick Piggin]

Wu Fengguang wrote:
> When a page is referenced the second time in inactive_list, mark it with
> PG_activate instead of moving it into active_list immediately. The actual
> moving work is delayed to vmscan time.
> 

This is something similar to what Rik and I have both wanted in the
past. In my case it was to simplify and improve the "use once"
streaming io mechanism.

I wouldn't feel comfortable lumping this together with your readahead
work all at once (ditto for some of the other vm changes).

Mabe we should look at making a decision on some of these peripheral
patches before readahead proper.

-- 
SUSE Labs, Novell Inc.

Send instant messages to your online friends http://au.messenger.yahoo.com 

Re: [PATCH 01/16] mm: delayed page activation

[Wu Fengguang]

On Thu, Nov 10, 2005 at 11:21:33AM +1100, Nick Piggin wrote:
> Wu Fengguang wrote:
> >When a page is referenced the second time in inactive_list, mark it with
> >PG_activate instead of moving it into active_list immediately. The actual
> >moving work is delayed to vmscan time.
> >
> 
> This is something similar to what Rik and I have both wanted in the
> past. In my case it was to simplify and improve the "use once"
> streaming io mechanism.
> 
> I wouldn't feel comfortable lumping this together with your readahead
> work all at once (ditto for some of the other vm changes).
> 
> Mabe we should look at making a decision on some of these peripheral
> patches before readahead proper.
Indeed I'm not quite sure about all the vm thing. One needs wide spread &
long term experiences to make good judgements in this area. But for the sake
of better read-ahead, I feel obliged to propose some read-ahead friendly vm
changes, and hope someone to consider and improve it with the whole picture
in mind.

So it's perfectly ok for me to leave the vm patches out for more discussion.

Regards,
Wu

Re: [PATCH 01/16] mm: delayed page activation

[Peter Zijlstra]

On Wed, 2005-11-09 at 21:49 +0800, Wu Fengguang wrote:
> plain text document attachment (mm-delayed-activation.patch)
> When a page is referenced the second time in inactive_list, mark it with
> PG_activate instead of moving it into active_list immediately. The actual
> moving work is delayed to vmscan time.
> 
> This implies two essential changes:
> - keeps the adjecency of pages in lru;
> - lifts the page reference counter max from 1 to 3.
> 
> And leads to the following improvements:
> - read-ahead for a leading reader will not be disturbed by a following reader;
> - enables the thrashing protection logic to save pages for following readers;
> - keeping relavant pages together helps improve I/O efficiency;
> - and also helps decrease vm fragmantation;
> - increased refcnt space might help page replacement algorithms.

I'm working on a clockpro implementation that essentialy keeps all
resident pages on 1 clock. In this case readahead pages will also not
fragment over the active/inactive lists but stay in order. Would that
also satisfy your requirements?

Code can be found at:
  http://programming.kicks-ass.net/kernel-patches/clockpro-2/

Note however that this is work in progress and rather unstable, there
are some livelock scenarios in there.

Kind regards,

Peter Zijlstra

Re: [PATCH 01/16] mm: delayed page activation

[Wu Fengguang]

On Thu, Nov 10, 2005 at 10:17:44AM +0100, Peter Zijlstra wrote:
> I'm working on a clockpro implementation that essentialy keeps all
> resident pages on 1 clock. In this case readahead pages will also not
> fragment over the active/inactive lists but stay in order. Would that
> also satisfy your requirements?

Thanks, it provides the first guarantee,
and the second one needs an extra bit anyway:
> > - keeps the adjecency of pages in lru;
> > - lifts the page reference counter max from 1 to 3.

> Code can be found at:
>   http://programming.kicks-ass.net/kernel-patches/clockpro-2/

Sorry, I failed connect to it:
ping: unknown host programming.kicks-ass.net

Regards,
Wu

[PATCH 02/16] mm: balance page aging between zones

[Wu Fengguang]

[-- Attachment #1: mm-balanced-aging.patch --]
[-- Type: text/plain, Size: 10985 bytes --]

The page aging rates are currently imbalanced, the gap can be as large as 3
times, which can severely damage read-ahead requests and shorten their
effective life time.

This patch adds three variables in struct zone to keep track of page aging
rate, and keeps them in sync on vmscan/pagealloc time. The nr_page_aging is
a per-zone counter-part to the per-cpu pgscan_{kswapd,direct}_{zone name}.

The direct page reclaim path is not touched, for it needs non-trival changes.
It is ok as long as (pgscan_kswapd_* > pgscan_direct_*).

__alloc_pages() is changed a lot, which needs comfirmation from NUMA gurus.
The basic idea is to do reclaim in batches, and keep the zones inside one
batch balanced.  There can be different policies in the partitioning.  One
obvious choice for the first batch would be the zones on current node and
nearby memory nodes without cpu.


Signed-off-by: Wu Fengguang <wfg@mail.ustc.edu.cn>
---

 include/linux/mmzone.h |   53 ++++++++++++++++++++++++++
 mm/page_alloc.c        |   97 ++++++++++++++++++++++++++++++++++++++++---------
 mm/vmscan.c            |   31 ++++++++++++---
 3 files changed, 159 insertions(+), 22 deletions(-)

--- linux-2.6.14-mm1.orig/include/linux/mmzone.h
+++ linux-2.6.14-mm1/include/linux/mmzone.h
@@ -161,6 +161,20 @@ struct zone {
 	unsigned long		pages_scanned;	   /* since last reclaim */
 	int			all_unreclaimable; /* All pages pinned */
 
+	/* Fields for balanced page aging:
+	 * nr_page_aging   - The accumulated number of activities that may
+	 *                   cause page aging, that is, make some pages closer
+	 *                   to the tail of inactive_list.
+	 * aging_milestone - A snapshot of nr_page_aging every time a full
+	 *                   inactive_list of pages become aged.
+	 * page_age        - A normalized value showing the percent of pages
+	 *                   have been aged.  It is compared between zones to
+	 *                   balance the rate of page aging.
+	 */
+	unsigned long		nr_page_aging;
+	unsigned long		aging_milestone;
+	unsigned long		page_age;
+
 	/*
 	 * Does the allocator try to reclaim pages from the zone as soon
 	 * as it fails a watermark_ok() in __alloc_pages?
@@ -344,6 +358,45 @@ static inline void memory_present(int ni
 unsigned long __init node_memmap_size_bytes(int, unsigned long, unsigned long);
 #endif
 
+#ifdef CONFIG_HIGHMEM64G
+#define		PAGE_AGE_SHIFT  8
+#elif BITS_PER_LONG == 32
+#define		PAGE_AGE_SHIFT  12
+#elif BITS_PER_LONG == 64
+#define		PAGE_AGE_SHIFT  20
+#else
+#error unknown BITS_PER_LONG
+#endif
+#define		PAGE_AGE_MASK   ((1 << PAGE_AGE_SHIFT) - 1)
+
+/*
+ * Keep track of the percent of pages in inactive_list that have been scanned
+ * / aged.  It's not really ##%, but a high resolution normalized value.
+ */
+static inline void update_page_age(struct zone *z, int nr_scan)
+{
+	z->nr_page_aging += nr_scan;
+
+	if (z->nr_page_aging - z->aging_milestone > z->nr_inactive)
+		z->aging_milestone += z->nr_inactive;
+
+	z->page_age = ((z->nr_page_aging - z->aging_milestone)
+				<< PAGE_AGE_SHIFT) / (1 + z->nr_inactive);
+}
+
+/*
+ * The simplified code is:
+ *         return (a->page_age > b->page_age);
+ * The complexity deals with the wrap-around problem.
+ * Two page ages not close enough should also be ignored:
+ * they are out of sync and the comparison may be nonsense.
+ */
+static inline int pages_more_aged(struct zone *a, struct zone *b)
+{
+	return ((b->page_age - a->page_age) & PAGE_AGE_MASK) >
+			PAGE_AGE_MASK - (1 << (PAGE_AGE_SHIFT - 2));
+}
+
 /*
  * zone_idx() returns 0 for the ZONE_DMA zone, 1 for the ZONE_NORMAL zone, etc.
  */
--- linux-2.6.14-mm1.orig/mm/page_alloc.c
+++ linux-2.6.14-mm1/mm/page_alloc.c
@@ -488,7 +488,7 @@ static void prep_new_page(struct page *p
 
 	page->flags &= ~(1 << PG_uptodate | 1 << PG_error |
 			1 << PG_referenced | 1 << PG_arch_1 |
-			1 << PG_activate |
+			1 << PG_activate | 1 << PG_readahead |
 			1 << PG_checked | 1 << PG_mappedtodisk);
 	set_page_private(page, 0);
 	set_page_refs(page, order);
@@ -871,9 +871,15 @@ __alloc_pages(gfp_t gfp_mask, unsigned i
 	struct task_struct *p = current;
 	int i;
 	int classzone_idx;
+	int do_reclaim;
 	int do_retry;
 	int can_try_harder;
 	int did_some_progress;
+	unsigned long zones_mask;
+	int left_count;
+	int batch_size;
+	int batch_base;
+	int batch_idx;
 
 	might_sleep_if(wait);
 
@@ -893,13 +899,62 @@ __alloc_pages(gfp_t gfp_mask, unsigned i
 
 	classzone_idx = zone_idx(zones[0]);
 
-restart:
 	/*
 	 * Go through the zonelist once, looking for a zone with enough free.
 	 * See also cpuset_zone_allowed() comment in kernel/cpuset.c.
 	 */
-	for (i = 0; (z = zones[i]) != NULL; i++) {
-		int do_reclaim = should_reclaim_zone(z, gfp_mask);
+restart:
+	/*
+	 * To fulfill three goals:
+	 * - balanced page aging
+	 * - locality
+	 * - predefined zonelist priority
+	 *
+	 * The logic employs the following rules:
+	 * 1. Zones are checked in predefined order in general.
+	 * 2. Skip to the next zone if it has lower page_age.
+	 * 3. Checkings are carried out in batch, all zones in a batch must be
+	 *    checked before entering the next batch.
+	 * 4. All local zones in the zonelist forms the first batch.
+	 */
+
+	/* TODO: Avoid this loop by putting the values into struct zonelist.
+	 * The (more general) desired batch counts can also go there.
+	 */
+	for (batch_size = 0, i = 0; (z = zones[i]) != NULL; i++) {
+		if (z->zone_pgdat == zones[0]->zone_pgdat)
+			batch_size++;
+	}
+	BUG_ON(!batch_size);
+
+	left_count = i - batch_size;
+	batch_base = 0;
+	batch_idx = 0;
+	zones_mask = 0;
+
+	for (;;) {
+		if (zones_mask == (1 << batch_size) - 1) {
+			if (left_count <= 0) {
+				break;
+			}
+			batch_base += batch_size;
+			batch_size = min(left_count, (int)sizeof(zones_mask) * 8);
+			left_count -= batch_size;
+			batch_idx = 0;
+			zones_mask = 0;
+		}
+
+		do {
+			i = batch_idx;
+			do {
+				if (++batch_idx >= batch_size)
+					batch_idx = 0;
+			} while (zones_mask & (1 << batch_idx));
+		} while (pages_more_aged(zones[batch_base + i],
+					 zones[batch_base + batch_idx]));
+
+		zones_mask |= (1 << i);
+		z = zones[batch_base + i];
 
 		if (!cpuset_zone_allowed(z, __GFP_HARDWALL))
 			continue;
@@ -909,11 +964,12 @@ restart:
 		 * will try to reclaim pages and check the watermark a second
 		 * time before giving up and falling back to the next zone.
 		 */
+		do_reclaim = should_reclaim_zone(z, gfp_mask);
 zone_reclaim_retry:
 		if (!zone_watermark_ok(z, order, z->pages_low,
 				       classzone_idx, 0, 0)) {
 			if (!do_reclaim)
-				continue;
+				goto try_harder;
 			else {
 				zone_reclaim(z, gfp_mask, order);
 				/* Only try reclaim once */
@@ -925,20 +981,18 @@ zone_reclaim_retry:
 		page = buffered_rmqueue(z, order, gfp_mask);
 		if (page)
 			goto got_pg;
-	}
 
-	for (i = 0; (z = zones[i]) != NULL; i++)
+try_harder:
 		wakeup_kswapd(z, order);
 
-	/*
-	 * Go through the zonelist again. Let __GFP_HIGH and allocations
-	 * coming from realtime tasks to go deeper into reserves
-	 *
-	 * This is the last chance, in general, before the goto nopage.
-	 * Ignore cpuset if GFP_ATOMIC (!wait) rather than fail alloc.
-	 * See also cpuset_zone_allowed() comment in kernel/cpuset.c.
-	 */
-	for (i = 0; (z = zones[i]) != NULL; i++) {
+		/*
+		 * Put stress on the zone. Let __GFP_HIGH and allocations
+		 * coming from realtime tasks to go deeper into reserves.
+		 *
+		 * This is the last chance, in general, before the goto nopage.
+		 * Ignore cpuset if GFP_ATOMIC (!wait) rather than fail alloc.
+		 * See also cpuset_zone_allowed() comment in kernel/cpuset.c.
+		 */
 		if (!zone_watermark_ok(z, order, z->pages_min,
 				       classzone_idx, can_try_harder,
 				       gfp_mask & __GFP_HIGH))
@@ -1447,6 +1501,8 @@ void show_free_areas(void)
 			" active:%lukB"
 			" inactive:%lukB"
 			" present:%lukB"
+			" aging:%lukB"
+			" age:%lu"
 			" pages_scanned:%lu"
 			" all_unreclaimable? %s"
 			"\n",
@@ -1458,6 +1514,8 @@ void show_free_areas(void)
 			K(zone->nr_active),
 			K(zone->nr_inactive),
 			K(zone->present_pages),
+			K(zone->nr_page_aging),
+			zone->page_age,
 			zone->pages_scanned,
 			(zone->all_unreclaimable ? "yes" : "no")
 			);
@@ -2075,6 +2133,9 @@ static void __init free_area_init_core(s
 		zone->nr_scan_inactive = 0;
 		zone->nr_active = 0;
 		zone->nr_inactive = 0;
+		zone->nr_page_aging = 0;
+		zone->aging_milestone = 0;
+		zone->page_age = 0;
 		atomic_set(&zone->reclaim_in_progress, 0);
 		if (!size)
 			continue;
@@ -2223,6 +2284,8 @@ static int zoneinfo_show(struct seq_file
 			   "\n        high     %lu"
 			   "\n        active   %lu"
 			   "\n        inactive %lu"
+			   "\n        aging    %lu"
+			   "\n        age      %lu"
 			   "\n        scanned  %lu (a: %lu i: %lu)"
 			   "\n        spanned  %lu"
 			   "\n        present  %lu",
@@ -2232,6 +2295,8 @@ static int zoneinfo_show(struct seq_file
 			   zone->pages_high,
 			   zone->nr_active,
 			   zone->nr_inactive,
+			   zone->nr_page_aging,
+			   zone->page_age,
 			   zone->pages_scanned,
 			   zone->nr_scan_active, zone->nr_scan_inactive,
 			   zone->spanned_pages,
--- linux-2.6.14-mm1.orig/mm/vmscan.c
+++ linux-2.6.14-mm1/mm/vmscan.c
@@ -839,6 +839,7 @@ static void shrink_cache(struct zone *zo
 			goto done;
 
 		max_scan -= nr_scan;
+		update_page_age(zone, nr_scan);
 		if (current_is_kswapd())
 			mod_page_state_zone(zone, pgscan_kswapd, nr_scan);
 		else
@@ -1286,6 +1287,7 @@ loop_again:
 
 	for (priority = DEF_PRIORITY; priority >= 0; priority--) {
 		int end_zone = 0;	/* Inclusive.  0 = ZONE_DMA */
+		int begin_zone = -1;
 		unsigned long lru_pages = 0;
 
 		all_zones_ok = 1;
@@ -1307,16 +1309,33 @@ loop_again:
 
 				if (!zone_watermark_ok(zone, order,
 						zone->pages_high, 0, 0, 0)) {
-					end_zone = i;
-					goto scan;
+					if (!end_zone)
+						begin_zone = end_zone = i;
+					else /* if (begin_zone == i + 1) */
+						begin_zone = i;
 				}
 			}
-			goto out;
+			if (begin_zone < 0)
+				goto out;
 		} else {
+			begin_zone = 0;
 			end_zone = pgdat->nr_zones - 1;
 		}
-scan:
-		for (i = 0; i <= end_zone; i++) {
+
+		/*
+		 * Prepare enough free pages for zones with small page_age,
+		 * they are going to be reclaimed in the page allocation.
+		 */
+		while (end_zone < pgdat->nr_zones - 1 &&
+			pages_more_aged(pgdat->node_zones + end_zone,
+					pgdat->node_zones + end_zone + 1))
+			end_zone++;
+		while (begin_zone &&
+			pages_more_aged(pgdat->node_zones + begin_zone,
+					pgdat->node_zones + begin_zone - 1))
+			begin_zone--;
+
+		for (i = begin_zone; i <= end_zone; i++) {
 			struct zone *zone = pgdat->node_zones + i;
 
 			lru_pages += zone->nr_active + zone->nr_inactive;
@@ -1331,7 +1350,7 @@ scan:
 		 * pages behind kswapd's direction of progress, which would
 		 * cause too much scanning of the lower zones.
 		 */
-		for (i = 0; i <= end_zone; i++) {
+		for (i = begin_zone; i <= end_zone; i++) {
 			struct zone *zone = pgdat->node_zones + i;
 			int nr_slab;
 

--

[PATCH 03/16] radixtree: sync with mainline

[Wu Fengguang]

[-- Attachment #1: radixtree-sync-with-mainline.patch --]
[-- Type: text/plain, Size: 1182 bytes --]

The patch from Christoph Lameter:

[PATCH] radix-tree: Remove unnecessary indirections and clean up code

is only partially merged into -mm tree. This patch completes it.

Signed-off-by: Christoph Lameter <clameter@sgi.com>
Signed-off-by: Wu Fengguang <wfg@mail.ustc.edu.cn>
---

 lib/radix-tree.c |   12 +++++-------
 1 files changed, 5 insertions(+), 7 deletions(-)

--- linux-2.6.14-mm1.orig/lib/radix-tree.c
+++ linux-2.6.14-mm1/lib/radix-tree.c
@@ -291,27 +291,25 @@ static inline void **__lookup_slot(struc
 				   unsigned long index)
 {
 	unsigned int height, shift;
-	struct radix_tree_node **slot;
+	struct radix_tree_node *slot;
 
 	height = root->height;
 	if (index > radix_tree_maxindex(height))
 		return NULL;
 
 	shift = (height-1) * RADIX_TREE_MAP_SHIFT;
-	slot = &root->rnode;
+	slot = root->rnode;
 
 	while (height > 0) {
-		if (*slot == NULL)
+		if (slot == NULL)
 			return NULL;
 
-		slot = (struct radix_tree_node **)
-			((*slot)->slots +
-				((index >> shift) & RADIX_TREE_MAP_MASK));
+		slot = slot->slots[(index >> shift) & RADIX_TREE_MAP_MASK];
 		shift -= RADIX_TREE_MAP_SHIFT;
 		height--;
 	}
 
-	return (void **)slot;
+	return slot;
 }
 
 /**

--

[PATCH 04/16] radix-tree: look-aside cache

[Wu Fengguang]

[-- Attachment #1: radixtree-lookaside-cache.patch --]
[-- Type: text/plain, Size: 11837 bytes --]

This introduces a set of lookup functions to radix tree for the read-ahead
logic.  Other access patterns with high locality may also benefit from them.

Most of them are best inlined, so some macros/structs in .c are moved into .h.

- radix_tree_lookup_node(root, index, level)
	Perform partial lookup, return the @level'th parent of the slot at
	@index.

- radix_tree_cache_lookup(root, cache, index)
	Perform lookup with the aid of a look-aside cache.
- radix_tree_cache_xxx()
	Init/Query the cache.

- radix_tree_lookup_head(root, index, max_scan)
- radix_tree_lookup_tail(root, index, max_scan)
	[head, tail) is a segment with continuous pages. The functions
	search for the head and tail index of the segment at @index.

Signed-off-by: Wu Fengguang <wfg@mail.ustc.edu.cn>
---

 include/linux/radix-tree.h |  150 ++++++++++++++++++++++++++++++++++++++++++++-
 lib/radix-tree.c           |  142 ++++++++++++++++++++++++++++++++----------
 2 files changed, 255 insertions(+), 37 deletions(-)

--- linux-2.6.14-mm1.orig/include/linux/radix-tree.h
+++ linux-2.6.14-mm1/include/linux/radix-tree.h
@@ -22,12 +22,39 @@
 #include <linux/preempt.h>
 #include <linux/types.h>
 
+#ifdef __KERNEL__
+#define RADIX_TREE_MAP_SHIFT	6
+#else
+#define RADIX_TREE_MAP_SHIFT	3	/* For more stressful testing */
+#endif
+#define RADIX_TREE_TAGS		2
+
+#define RADIX_TREE_MAP_SIZE	(1UL << RADIX_TREE_MAP_SHIFT)
+#define RADIX_TREE_MAP_MASK	(RADIX_TREE_MAP_SIZE-1)
+
+#define RADIX_TREE_TAG_LONGS	\
+	((RADIX_TREE_MAP_SIZE + BITS_PER_LONG - 1) / BITS_PER_LONG)
+
+struct radix_tree_node {
+	unsigned int	count;
+	void		*slots[RADIX_TREE_MAP_SIZE];
+	unsigned long	tags[RADIX_TREE_TAGS][RADIX_TREE_TAG_LONGS];
+};
+
 struct radix_tree_root {
 	unsigned int		height;
 	gfp_t			gfp_mask;
 	struct radix_tree_node	*rnode;
 };
 
+/*
+ * Support access patterns with strong locality.
+ */
+struct radix_tree_cache {
+	unsigned long first_index;
+	struct radix_tree_node *tree_node;
+};
+
 #define RADIX_TREE_INIT(mask)	{					\
 	.height = 0,							\
 	.gfp_mask = (mask),						\
@@ -45,9 +72,13 @@ do {									\
 } while (0)
 
 int radix_tree_insert(struct radix_tree_root *, unsigned long, void *);
-void *radix_tree_lookup(struct radix_tree_root *, unsigned long);
-void **radix_tree_lookup_slot(struct radix_tree_root *, unsigned long);
+void *radix_tree_lookup_node(struct radix_tree_root *, unsigned long,
+							unsigned int);
 void *radix_tree_delete(struct radix_tree_root *, unsigned long);
+unsigned long radix_tree_lookup_head(struct radix_tree_root *root,
+				unsigned long index, unsigned int max_scan);
+unsigned long radix_tree_lookup_tail(struct radix_tree_root *root,
+				unsigned long index, unsigned int max_scan);
 unsigned int
 radix_tree_gang_lookup(struct radix_tree_root *root, void **results,
 			unsigned long first_index, unsigned int max_items);
@@ -69,4 +100,119 @@ static inline void radix_tree_preload_en
 	preempt_enable();
 }
 
+/**
+ *	radix_tree_lookup    -    perform lookup operation on a radix tree
+ *	@root:		radix tree root
+ *	@index:		index key
+ *
+ *	Lookup the item at the position @index in the radix tree @root.
+ */
+static inline void *radix_tree_lookup(struct radix_tree_root *root,
+							unsigned long index)
+{
+	return radix_tree_lookup_node(root, index, 0);
+}
+
+/**
+ *	radix_tree_lookup_slot    -    lookup a slot in a radix tree
+ *	@root:		radix tree root
+ *	@index:		index key
+ *
+ *	Lookup the slot corresponding to the position @index in the radix tree
+ *	@root. This is useful for update-if-exists operations.
+ */
+static inline void **radix_tree_lookup_slot(struct radix_tree_root *root,
+							unsigned long index)
+{
+	struct radix_tree_node *node;
+
+	node = radix_tree_lookup_node(root, index, 1);
+	return node->slots + (index & RADIX_TREE_MAP_MASK);
+}
+
+/**
+ *	radix_tree_cache_lookup_node    -    cached lookup node
+ *	@root:		radix tree root
+ *	@cache:		look-aside cache
+ *	@index:		index key
+ *
+ *	Lookup the item at the position @index in the radix tree @root,
+ *	and return the node @level levels from the bottom in the search path.
+ *	@cache stores the last accessed upper level tree node by this
+ *	function, and is always checked first before searching in the tree.
+ *	It can improve speed for access patterns with strong locality.
+ *	NOTE:
+ *	- The cache becomes invalid on leaving the lock;
+ *	- Do not intermix calls with different @level.
+ */
+static inline void *radix_tree_cache_lookup_node(struct radix_tree_root *root,
+				struct radix_tree_cache *cache,
+				unsigned long index, unsigned int level)
+{
+	struct radix_tree_node *node;
+        unsigned long i;
+        unsigned long mask;
+
+        if (level && level >= root->height)
+                return root->rnode;
+
+        i = ((index >> (level * RADIX_TREE_MAP_SHIFT)) & RADIX_TREE_MAP_MASK);
+        mask = ~((RADIX_TREE_MAP_SIZE << (level * RADIX_TREE_MAP_SHIFT)) - 1);
+
+	if ((index & mask) == cache->first_index)
+                return cache->tree_node->slots[i];
+
+	node = radix_tree_lookup_node(root, index, level + 1);
+	if (!node)
+		return 0;
+
+	cache->tree_node = node;
+	cache->first_index = (index & mask);
+        return node->slots[i];
+}
+
+/**
+ *	radix_tree_cache_lookup    -    cached lookup page
+ *	@root:		radix tree root
+ *	@cache:		look-aside cache
+ *	@index:		index key
+ *
+ *	Lookup the item at the position @index in the radix tree @root.
+ */
+static inline void *radix_tree_cache_lookup(struct radix_tree_root *root,
+				struct radix_tree_cache *cache,
+				unsigned long index)
+{
+	return radix_tree_cache_lookup_node(root, cache, index, 0);
+}
+
+static inline void radix_tree_cache_init(struct radix_tree_cache *cache)
+{
+	cache->first_index = 0x77;
+	cache->tree_node = NULL;
+}
+
+static inline int radix_tree_cache_size(struct radix_tree_cache *cache)
+{
+	return RADIX_TREE_MAP_SIZE;
+}
+
+static inline int radix_tree_cache_count(struct radix_tree_cache *cache)
+{
+	if (cache->first_index != 0x77)
+		return cache->tree_node->count;
+	else
+		return 0;
+}
+
+static inline int radix_tree_cache_full(struct radix_tree_cache *cache)
+{
+	return radix_tree_cache_count(cache) == radix_tree_cache_size(cache);
+}
+
+static inline int radix_tree_cache_first_index(struct radix_tree_cache *cache)
+{
+	return cache->first_index;
+}
+
 #endif /* _LINUX_RADIX_TREE_H */
--- linux-2.6.14-mm1.orig/lib/radix-tree.c
+++ linux-2.6.14-mm1/lib/radix-tree.c
@@ -32,25 +32,6 @@
 #include <linux/bitops.h>
 
 
-#ifdef __KERNEL__
-#define RADIX_TREE_MAP_SHIFT	6
-#else
-#define RADIX_TREE_MAP_SHIFT	3	/* For more stressful testing */
-#endif
-#define RADIX_TREE_TAGS		2
-
-#define RADIX_TREE_MAP_SIZE	(1UL << RADIX_TREE_MAP_SHIFT)
-#define RADIX_TREE_MAP_MASK	(RADIX_TREE_MAP_SIZE-1)
-
-#define RADIX_TREE_TAG_LONGS	\
-	((RADIX_TREE_MAP_SIZE + BITS_PER_LONG - 1) / BITS_PER_LONG)
-
-struct radix_tree_node {
-	unsigned int	count;
-	void		*slots[RADIX_TREE_MAP_SIZE];
-	unsigned long	tags[RADIX_TREE_TAGS][RADIX_TREE_TAG_LONGS];
-};
-
 struct radix_tree_path {
 	struct radix_tree_node *node;
 	int offset;
@@ -287,8 +268,21 @@ int radix_tree_insert(struct radix_tree_
 }
 EXPORT_SYMBOL(radix_tree_insert);
 
-static inline void **__lookup_slot(struct radix_tree_root *root,
-				   unsigned long index)
+/**
+ *	radix_tree_lookup_node    -    low level lookup routine
+ *	@root:		radix tree root
+ *	@index:		index key
+ *	@level:		stop at that many levels from bottom
+ *
+ *	Lookup the item at the position @index in the radix tree @root.
+ *	The return value is:
+ *	@level == 0:      page at @index;
+ *	@level == 1:      the corresponding bottom level tree node;
+ *	@level < height:  (height - @level)th level tree node;
+ *	@level >= height: root node.
+ */
+void *radix_tree_lookup_node(struct radix_tree_root *root,
+				unsigned long index, unsigned int level)
 {
 	unsigned int height, shift;
 	struct radix_tree_node *slot;
@@ -300,7 +294,7 @@ static inline void **__lookup_slot(struc
 	shift = (height-1) * RADIX_TREE_MAP_SHIFT;
 	slot = root->rnode;
 
-	while (height > 0) {
+	while (height > level) {
 		if (slot == NULL)
 			return NULL;
 
@@ -311,36 +305,114 @@ static inline void **__lookup_slot(struc
 
 	return slot;
 }
+EXPORT_SYMBOL(radix_tree_lookup_node);
 
 /**
- *	radix_tree_lookup_slot    -    lookup a slot in a radix tree
+ *	radix_tree_lookup_head    -    lookup the head index
  *	@root:		radix tree root
  *	@index:		index key
+ *	@max_scan:      max items to scan
  *
- *	Lookup the slot corresponding to the position @index in the radix tree
- *	@root. This is useful for update-if-exists operations.
+ *      Lookup head index of the segment which contains @index. A segment is
+ *      a set of continuous pages in a file.
+ *      CASE                       RETURN VALUE
+ *      no page at @index          (not head) = @index + 1
+ *      found in the range         @index - @max_scan < (head index) <= @index
+ *      not found in range         (unfinished head) <= @index - @max_scan
  */
-void **radix_tree_lookup_slot(struct radix_tree_root *root, unsigned long index)
+unsigned long radix_tree_lookup_head(struct radix_tree_root *root,
+				unsigned long index, unsigned int max_scan)
 {
-	return __lookup_slot(root, index);
+	struct radix_tree_cache cache;
+	struct radix_tree_node *node;
+	int i;
+	unsigned long origin;
+
+	origin = index;
+	if (unlikely(max_scan > index))
+		max_scan = index;
+        radix_tree_cache_init(&cache);
+
+next_node:
+	if (origin - index > max_scan)
+		goto out;
+
+	node = radix_tree_cache_lookup_node(root, &cache, index, 1);
+	if (!node)
+		goto out;
+
+	if (node->count == RADIX_TREE_MAP_SIZE) {
+		if (index < RADIX_TREE_MAP_SIZE) {
+			index = -1;
+			goto out;
+		}
+		index = (index - RADIX_TREE_MAP_SIZE) | RADIX_TREE_MAP_MASK;
+		goto next_node;
+	}
+
+	for (i = index & RADIX_TREE_MAP_MASK; i >= 0; i--, index--) {
+		if (!node->slots[i])
+			goto out;
+	}
+
+	goto next_node;
+
+out:
+	return index + 1;
 }
-EXPORT_SYMBOL(radix_tree_lookup_slot);
+EXPORT_SYMBOL(radix_tree_lookup_head);
 
 /**
- *	radix_tree_lookup    -    perform lookup operation on a radix tree
+ *	radix_tree_lookup_tail    -    lookup the tail index
  *	@root:		radix tree root
  *	@index:		index key
+ *	@max_scan:      max items to scan
  *
- *	Lookup the item at the position @index in the radix tree @root.
+ *      Lookup tail(pass the end) index of the segment which contains @index.
+ *      A segment is a set of continuous pages in a file.
+ *      CASE                       RETURN VALUE
+ *      found in the range         @index <= (tail index) < @index + @max_scan
+ *      not found in range         @index + @max_scan <= (non tail)
  */
-void *radix_tree_lookup(struct radix_tree_root *root, unsigned long index)
+unsigned long radix_tree_lookup_tail(struct radix_tree_root *root,
+				unsigned long index, unsigned int max_scan)
 {
-	void **slot;
+	struct radix_tree_cache cache;
+	struct radix_tree_node *node;
+	int i;
+	unsigned long origin;
+
+	origin = index;
+	if (unlikely(index + max_scan < index))
+		max_scan = LONG_MAX - index;
+        radix_tree_cache_init(&cache);
+
+next_node:
+	if (index - origin >= max_scan)
+		goto out;
 
-	slot = __lookup_slot(root, index);
-	return slot != NULL ? *slot : NULL;
+	node = radix_tree_cache_lookup_node(root, &cache, index, 1);
+	if (!node)
+		goto out;
+
+	if (node->count == RADIX_TREE_MAP_SIZE) {
+		index = (index | RADIX_TREE_MAP_MASK) + 1;
+		if (unlikely(!index))
+			goto out;
+		goto next_node;
+	}
+
+	for (i = index & RADIX_TREE_MAP_MASK; i < RADIX_TREE_MAP_SIZE; i++, index++) {
+		if (!node->slots[i])
+			goto out;
+	}
+
+	goto next_node;
+
+out:
+	return index;
 }
-EXPORT_SYMBOL(radix_tree_lookup);
+EXPORT_SYMBOL(radix_tree_lookup_tail);
 
 /**
  *	radix_tree_tag_set - set a tag on a radix tree node

--

Re: [PATCH 04/16] radix-tree: look-aside cache

[Nick Piggin]

Wu Fengguang wrote:
> This introduces a set of lookup functions to radix tree for the read-ahead
> logic.  Other access patterns with high locality may also benefit from them.
> 

Hi Wu,

Does this cache add much performance compared with simple repeated
lookups? If the access patterns are highly local, the top of the
radix tree should be in cache.

I worry that it is a fair bit of extra complexity for something
slow like the IO path - however I haven't looked at how you use the
cache.

> Most of them are best inlined, so some macros/structs in .c are moved into .h.
> 

I would not inline them. You'd find that the extra icache misses
that costs outweighs the improvements for larger functions.

> +
> +struct radix_tree_node {
> +	unsigned int	count;
> +	void		*slots[RADIX_TREE_MAP_SIZE];
> +	unsigned long	tags[RADIX_TREE_TAGS][RADIX_TREE_TAG_LONGS];
> +};
> +

Would be much nicer if this weren't declared in the header file, so
people don't start trying to use the nodes where they shouldn't.
This ought to be possible after uninlining a couple of things.

>  struct radix_tree_root {
>  	unsigned int		height;
>  	gfp_t			gfp_mask;
>  	struct radix_tree_node	*rnode;
>  };
>  
> +/*
> + * Support access patterns with strong locality.
> + */

Do you think you could provide a simple 'use case' for an overview
of how you use the cache and what calls to make?

> +struct radix_tree_cache {
> +	unsigned long first_index;
> +	struct radix_tree_node *tree_node;
> +};
> +

> +static inline void radix_tree_cache_init(struct radix_tree_cache *cache)
> +{
> +	cache->first_index = 0x77;
> +	cache->tree_node = NULL;
> +}
> +
> +static inline int radix_tree_cache_size(struct radix_tree_cache *cache)
> +{
> +	return RADIX_TREE_MAP_SIZE;
> +}
> +
> +static inline int radix_tree_cache_count(struct radix_tree_cache *cache)
> +{
> +	if (cache->first_index != 0x77)
> +		return cache->tree_node->count;
> +	else
> +		return 0;
> +}
> +

What's 0x77 for? And what happens if your cache gets big enough that
the first index is 0x77?

Thanks,
Nick

-- 
SUSE Labs, Novell Inc.

Send instant messages to your online friends http://au.messenger.yahoo.com 

Re: [PATCH 04/16] radix-tree: look-aside cache

[Wu Fengguang]

Hi Nick,

On Thu, Nov 10, 2005 at 10:31:09AM +1100, Nick Piggin wrote:
> Does this cache add much performance compared with simple repeated
> lookups? If the access patterns are highly local, the top of the
> radix tree should be in cache.
It just guarantees constant lookup time for small/large files.

My context based read-ahead code has been quite tricky just to avoid many radix
tree lookups. I made it much simple and robust in the recent versions by just
scanning through the cache. With the help of look-aside cache, the performance
remains comparable with the tricky one. Sorry, the oprofile log was overwrote.
But if you do need some numbers about the cache, I'll make one.

> 
> I worry that it is a fair bit of extra complexity for something
> slow like the IO path - however I haven't looked at how you use the
> cache.
Most are one-liners, except radix_tree_cache_lookup_node(). Which is about 10
lines. Currently it is always called with a constant @level, where inline can
help. Only several speed critical functions call it, so I guess icache misses
will not be a big problem. But I do feel it ugly to expose internal data
structures in .h :(
> 
> >Most of them are best inlined, so some macros/structs in .c are moved into 
> >.h.
> >
> 
> I would not inline them. You'd find that the extra icache misses
> that costs outweighs the improvements for larger functions.
> 
> >+
> >+struct radix_tree_node {
> >+	unsigned int	count;
> >+	void		*slots[RADIX_TREE_MAP_SIZE];
> >+	unsigned long	tags[RADIX_TREE_TAGS][RADIX_TREE_TAG_LONGS];
> >+};
> >+
> 
> Would be much nicer if this weren't declared in the header file, so
> people don't start trying to use the nodes where they shouldn't.
> This ought to be possible after uninlining a couple of things.
Ok. I'll try it.
> 
> > struct radix_tree_root {
> > 	unsigned int		height;
> > 	gfp_t			gfp_mask;
> > 	struct radix_tree_node	*rnode;
> > };
> > 
> >+/*
> >+ * Support access patterns with strong locality.
> >+ */
> 
> Do you think you could provide a simple 'use case' for an overview
> of how you use the cache and what calls to make?
Ok, here it is:

 void func() {
+       struct radix_tree_cache cache;
+
+       radix_tree_cache_init(&cache);
        read_lock_irq(&mapping->tree_lock);
        for(;;) {
-               page = radix_tree_lookup(&mapping->page_tree, index);
+               page = radix_tree_cache_lookup(&mapping->page_tree, &cache, index);
        }
        read_unlock_irq(&mapping->tree_lock);
 }

> 
> >+struct radix_tree_cache {
> >+	unsigned long first_index;
> >+	struct radix_tree_node *tree_node;
> >+};
> >+
> 
> >+static inline void radix_tree_cache_init(struct radix_tree_cache *cache)
> >+{
> >+	cache->first_index = 0x77;
> >+	cache->tree_node = NULL;
> >+}
> >+
> >+static inline int radix_tree_cache_size(struct radix_tree_cache *cache)
> >+{
> >+	return RADIX_TREE_MAP_SIZE;
> >+}
> >+
> >+static inline int radix_tree_cache_count(struct radix_tree_cache *cache)
> >+{
> >+	if (cache->first_index != 0x77)
> >+		return cache->tree_node->count;
> >+	else
> >+		return 0;
> >+}
> >+
> 
> What's 0x77 for? And what happens if your cache gets big enough that
> the first index is 0x77?
Sorry for the ugly code. It is better written as:
        if (cache->first_index & RADIX_TREE_MAP_MASK)
                return 0;
        else
                return cache->tree_node->count;

The 0x77 is an invalid value that will be detected in radix_tree_cache_lookup_node():

        mask = ~((RADIX_TREE_MAP_SIZE << (level * RADIX_TREE_MAP_SHIFT)) - 1);

--->    if ((index & mask) == cache->first_index)
                return cache->tree_node->slots[i];

        node = radix_tree_lookup_node(root, index, level + 1);

It can be initialized to 1, 0xFF, or any i that (i & RADIX_TREE_MAP_MASK != 0).
I'd better just init it as RADIX_TREE_MAP_MASK.

Regards,
Wu

Re: [PATCH 04/16] radix-tree: look-aside cache

[Nick Piggin]

Wu Fengguang wrote:

>Hi Nick,
>
>On Thu, Nov 10, 2005 at 10:31:09AM +1100, Nick Piggin wrote:
>
>>Does this cache add much performance compared with simple repeated
>>lookups? If the access patterns are highly local, the top of the
>>radix tree should be in cache.
>>
>It just guarantees constant lookup time for small/large files.
>
>My context based read-ahead code has been quite tricky just to avoid many radix
>tree lookups. I made it much simple and robust in the recent versions by just
>scanning through the cache. With the help of look-aside cache, the performance
>remains comparable with the tricky one. Sorry, the oprofile log was overwrote.
>But if you do need some numbers about the cache, I'll make one.
>
>

But it isn't *really* constant time lookups? I mean you'll
always have the O(logn) lookup. Amortised I guess that
becomes insignificant?

Briefly: is there a reason why you couldn't use gang lookups
instead? (Sorry I haven't been able to read and understand your
actual readahead code).

>>Do you think you could provide a simple 'use case' for an overview
>>of how you use the cache and what calls to make?
>>
>Ok, here it is:
>
> void func() {
>+       struct radix_tree_cache cache;
>+
>+       radix_tree_cache_init(&cache);
>        read_lock_irq(&mapping->tree_lock);
>        for(;;) {
>-               page = radix_tree_lookup(&mapping->page_tree, index);
>+               page = radix_tree_cache_lookup(&mapping->page_tree, &cache, index);
>        }
>        read_unlock_irq(&mapping->tree_lock);
> }
>
>

OK, I guess that seems reasonable.
You have introduced some other APIs as well...

Profile numbers would be great for the cached / non-cached cases.


Send instant messages to your online friends http://au.messenger.yahoo.com 

Re: [PATCH 04/16] radix-tree: look-aside cache

[Wu Fengguang]

On Thu, Nov 10, 2005 at 05:50:09PM +1100, Nick Piggin wrote:
> But it isn't *really* constant time lookups? I mean you'll
> always have the O(logn) lookup. Amortised I guess that
> becomes insignificant?

For sequential scan, I get 64*O(1) + 1*O(logn), that's pretty much gain.

> Briefly: is there a reason why you couldn't use gang lookups
> instead? (Sorry I haven't been able to read and understand your
> actual readahead code).

Because they have different semantics, one cannot replace the another.

> Profile numbers would be great for the cached / non-cached cases.

Ok, I'll do it, but at some time later. Currently I have several tasks that
need immediate handling, and that will take about a week. See you then :)

Regards,
Wu

Re: [PATCH 04/16] radix-tree: look-aside cache

[Wu Fengguang]

Hi Nick,

On Thu, Nov 10, 2005 at 05:50:09PM +1100, Nick Piggin wrote:
> Profile numbers would be great for the cached / non-cached cases.

Sorry for the delay!

I run two rounds of oprofile on the context based method, which is the user of
radix_tree_lookup_{head,tail}, which take advantage of the look-aside cache.
This is the diffprofile grep output(disable vs. enable cache):

radixtree-lookaside-cache.diffprofile1:        -8   -53.3% radix_tree_lookup_head
radixtree-lookaside-cache.diffprofile1:       -30    -7.8% radix_tree_lookup_node
radixtree-lookaside-cache.diffprofile1:       -34   -18.9% radix_tree_insert

radixtree-lookaside-cache.diffprofile2:        16    10.9% radix_tree_insert
radixtree-lookaside-cache.diffprofile2:        12    18.8% radix_tree_preload
radixtree-lookaside-cache.diffprofile2:         6    42.9% radix_tree_lookup_tail
radixtree-lookaside-cache.diffprofile2:        -7   -63.6% radix_tree_lookup_head
radixtree-lookaside-cache.diffprofile2:       -23   -10.5% radix_tree_delete
radixtree-lookaside-cache.diffprofile2:       -29    -6.9% radix_tree_lookup_node

Regards,
Wu

Re: [PATCH 04/16] radix-tree: look-aside cache

[Wu Fengguang]

On Fri, Nov 18, 2005 at 07:25:01PM +0800, Wu Fengguang wrote:
> I run two rounds of oprofile on the context based method, which is the user of
> radix_tree_lookup_{head,tail}, which take advantage of the look-aside cache.
> This is the diffprofile grep output(disable vs. enable cache):
> 
> radixtree-lookaside-cache.diffprofile1:        -8   -53.3% radix_tree_lookup_head
> radixtree-lookaside-cache.diffprofile1:       -30    -7.8% radix_tree_lookup_node
> radixtree-lookaside-cache.diffprofile1:       -34   -18.9% radix_tree_insert
> 
> radixtree-lookaside-cache.diffprofile2:        16    10.9% radix_tree_insert
> radixtree-lookaside-cache.diffprofile2:        12    18.8% radix_tree_preload
> radixtree-lookaside-cache.diffprofile2:         6    42.9% radix_tree_lookup_tail
> radixtree-lookaside-cache.diffprofile2:        -7   -63.6% radix_tree_lookup_head
> radixtree-lookaside-cache.diffprofile2:       -23   -10.5% radix_tree_delete
> radixtree-lookaside-cache.diffprofile2:       -29    -6.9% radix_tree_lookup_node

The above profile data are gathered on comparing two big files:

# du /temp/kernel/bigfile*
626M    /temp/kernel/bigfile
626M    /temp/kernel/bigfile2

I run another real life test:

# grep -r 'asdfghjkl;' /backup/test/linux-2.6.14-rc4-git4-orig/

radixtree-lookaside-cache.diffprofile3:        16    43.2% radix_tree_tag_clear
radixtree-lookaside-cache.diffprofile3:         8    24.2% radix_tree_tag_set
radixtree-lookaside-cache.diffprofile3:        -9    -5.8% radix_tree_lookup_node

radixtree-lookaside-cache.diffprofile4:         7     4.5% radix_tree_lookup_node
radixtree-lookaside-cache.diffprofile4:        -8   -11.8% radix_tree_tag_clear

As expected, there's no noticable difference for small files.

Regards,
Wu

[PATCH 05/16] readahead: some preparation

[Wu Fengguang]

[-- Attachment #1: readahead-prepare.patch --]
[-- Type: text/plain, Size: 7934 bytes --]

Some random changes that do not fit in elsewhere.

Signed-off-by: Wu Fengguang <wfg@mail.ustc.edu.cn>
---

 mm/readahead.c |  176 ++++++++++++++++++++++++++++++++++++++++++++++++++++++---
 1 files changed, 167 insertions(+), 9 deletions(-)

--- linux-2.6.14-mm1.orig/mm/readahead.c
+++ linux-2.6.14-mm1/mm/readahead.c
@@ -15,13 +15,40 @@
 #include <linux/backing-dev.h>
 #include <linux/pagevec.h>
 
+/* The default max/min read-ahead pages. */
+#define KB(size)	(((size)*1024 + PAGE_CACHE_SIZE-1) / PAGE_CACHE_SIZE)
+#define MAX_RA_PAGES	KB(VM_MAX_READAHEAD)
+#define MIN_RA_PAGES	KB(VM_MIN_READAHEAD)
+
+/*
+ * Debug facilities.
+ */
+#ifdef CONFIG_DEBUG_FS
+#define DEBUG_READAHEAD
+#endif
+
+#ifdef DEBUG_READAHEAD
+
+#define dprintk(args...) \
+	if (readahead_ratio & 1) printk(KERN_DEBUG args)
+#define ddprintk(args...) \
+	if ((readahead_ratio & 3) == 3) printk(KERN_DEBUG args)
+
+#else /* !DEBUG_READAHEAD */
+
+#define dprintk(args...)     do {} while(0)
+#define ddprintk(args...)    do {} while(0)
+
+#endif /* DEBUG_READAHEAD */
+
+
 void default_unplug_io_fn(struct backing_dev_info *bdi, struct page *page)
 {
 }
 EXPORT_SYMBOL(default_unplug_io_fn);
 
 struct backing_dev_info default_backing_dev_info = {
-	.ra_pages	= (VM_MAX_READAHEAD * 1024) / PAGE_CACHE_SIZE,
+	.ra_pages	= MAX_RA_PAGES,
 	.state		= 0,
 	.capabilities	= BDI_CAP_MAP_COPY,
 	.unplug_io_fn	= default_unplug_io_fn,
@@ -50,7 +77,7 @@ static inline unsigned long get_max_read
 
 static inline unsigned long get_min_readahead(struct file_ra_state *ra)
 {
-	return (VM_MIN_READAHEAD * 1024) / PAGE_CACHE_SIZE;
+	return MIN_RA_PAGES;
 }
 
 static inline void ra_off(struct file_ra_state *ra)
@@ -255,10 +282,11 @@ out:
  */
 static int
 __do_page_cache_readahead(struct address_space *mapping, struct file *filp,
-			pgoff_t offset, unsigned long nr_to_read)
+			pgoff_t offset, unsigned long nr_to_read,
+			unsigned long lookahead_size)
 {
 	struct inode *inode = mapping->host;
-	struct page *page;
+	struct page *page = NULL;
 	unsigned long end_index;	/* The last page we want to read */
 	LIST_HEAD(page_pool);
 	int page_idx;
@@ -268,7 +296,7 @@ __do_page_cache_readahead(struct address
 	if (isize == 0)
 		goto out;
 
- 	end_index = ((isize - 1) >> PAGE_CACHE_SHIFT);
+	end_index = ((isize - 1) >> PAGE_CACHE_SHIFT);
 
 	/*
 	 * Preallocate as many pages as we will need.
@@ -281,8 +309,12 @@ __do_page_cache_readahead(struct address
 			break;
 
 		page = radix_tree_lookup(&mapping->page_tree, page_offset);
-		if (page)
+		if (page) {
+			if (readahead_ratio > 9 &&
+				page_idx == nr_to_read - lookahead_size)
+				SetPageReadahead(page);
 			continue;
+		}
 
 		read_unlock_irq(&mapping->tree_lock);
 		page = page_cache_alloc_cold(mapping);
@@ -291,6 +323,9 @@ __do_page_cache_readahead(struct address
 			break;
 		page->index = page_offset;
 		list_add(&page->lru, &page_pool);
+		if (readahead_ratio > 9 &&
+				page_idx == nr_to_read - lookahead_size)
+			SetPageReadahead(page);
 		ret++;
 	}
 	read_unlock_irq(&mapping->tree_lock);
@@ -327,7 +362,7 @@ int force_page_cache_readahead(struct ad
 		if (this_chunk > nr_to_read)
 			this_chunk = nr_to_read;
 		err = __do_page_cache_readahead(mapping, filp,
-						offset, this_chunk);
+						offset, this_chunk, 0);
 		if (err < 0) {
 			ret = err;
 			break;
@@ -374,7 +409,7 @@ int do_page_cache_readahead(struct addre
 	if (bdi_read_congested(mapping->backing_dev_info))
 		return -1;
 
-	return __do_page_cache_readahead(mapping, filp, offset, nr_to_read);
+	return __do_page_cache_readahead(mapping, filp, offset, nr_to_read, 0);
 }
 
 /*
@@ -394,7 +429,10 @@ blockable_page_cache_readahead(struct ad
 	if (!block && bdi_read_congested(mapping->backing_dev_info))
 		return 0;
 
-	actual = __do_page_cache_readahead(mapping, filp, offset, nr_to_read);
+	actual = __do_page_cache_readahead(mapping, filp, offset, nr_to_read, 0);
+
+	dprintk("blockable-readahead(ino=%lu, ra=%lu+%lu) = %d\n",
+			mapping->host->i_ino, offset, nr_to_read, actual);
 
 	return check_ra_success(ra, nr_to_read, actual);
 }
@@ -572,3 +610,123 @@ unsigned long max_sane_readahead(unsigne
 	__get_zone_counts(&active, &inactive, &free, NODE_DATA(numa_node_id()));
 	return min(nr, (inactive + free) / 2);
 }
+
+/*
+ * Adaptive read-ahead.
+ *
+ * Good read patterns are compact both in space and time. The read-ahead logic
+ * tries to grant larger read-ahead size to better readers under the constraint
+ * of system memory and load pressures.
+ *
+ * It employs two methods to estimate the max thrashing safe read-ahead size:
+ *   1. state based   - the default one
+ *   2. context based - the fail safe one
+ * The integration of the dual methods has the merit of being agile and robust.
+ * It makes the overall design clean: special cases are handled in general by
+ * the stateless method, leaving the stateful one simple and fast.
+ *
+ * To improve throughput and decrease read delay, the logic 'looks ahead'.
+ * In every read-ahead chunk, it selects one page and tag it with PG_readahead.
+ * Later when the page with PG_readahead is to be read, the logic knows that
+ * it's time to carry out the next read-ahead chunk in advance.
+ *
+ *                 a read-ahead chunk
+ *    +-----------------------------------------+
+ *    |       # PG_readahead                    |
+ *    +-----------------------------------------+
+ *            ^ When this page is read, we submit I/O for the next read-ahead.
+ *
+ *
+ * Here are some variable names used frequently:
+ *
+ *                                   |<------- la_size ------>|
+ *                  +-----------------------------------------+
+ *                  |                #                        |
+ *                  +-----------------------------------------+
+ *      ra_index -->|<---------------- ra_size -------------->|
+ *
+ */
+
+#define next_page(pg) (list_entry((pg)->lru.prev, struct page, lru))
+#define prev_page(pg) (list_entry((pg)->lru.next, struct page, lru))
+
+/*
+ * The nature of read-ahead allows most tests to fail or even be wrong.
+ * Here we just do not bother to call get_page(), it's meaningless anyway.
+ */
+static inline struct page *__find_page(struct address_space *mapping,
+							pgoff_t offset)
+{
+	return radix_tree_lookup(&mapping->page_tree, offset);
+}
+
+static inline struct page *find_page(struct address_space *mapping,
+							pgoff_t offset)
+{
+	struct page *page;
+
+	read_lock_irq(&mapping->tree_lock);
+	page = __find_page(mapping, offset);
+	read_unlock_irq(&mapping->tree_lock);
+#ifdef DEBUG_READAHEAD_RADIXTREE
+	if (page)
+		BUG_ON(page->index != offset);
+#endif
+	return page;
+}
+
+/*
+ * Move pages in danger (of thrashing) to the head of inactive_list.
+ * Not expected to happen frequently.
+ */
+static int rescue_pages(struct page *page, pgoff_t nr_pages)
+{
+	unsigned long pgrescue;
+	pgoff_t index;
+	struct address_space *mapping;
+	struct zone *zone;
+
+	BUG_ON(!nr_pages || !page);
+	pgrescue = 0;
+	index = page_index(page);
+	mapping = page_mapping(page);
+
+	dprintk("rescue_pages(ino=%lu, index=%lu nr=%lu)\n",
+			mapping->host->i_ino, index, nr_pages);
+
+	for(;;) {
+		zone = page_zone(page);
+		spin_lock_irq(&zone->lru_lock);
+
+		if (!PageLRU(page))
+			goto out_unlock;
+
+		while (page_mapping(page) == mapping &&
+				page_index(page) == index) {
+			struct page *the_page = page;
+			page = next_page(page);
+			if (!PageActive(the_page) &&
+					!PageActivate(the_page) &&
+					!PageLocked(the_page) &&
+					page_count(the_page) == 1) {
+				list_move(&the_page->lru, &zone->inactive_list);
+				pgrescue++;
+			}
+			index++;
+			if (!--nr_pages)
+				goto out_unlock;
+		}
+
+		spin_unlock_irq(&zone->lru_lock);
+
+		page = find_page(mapping, index);
+		if (!page)
+			goto out;
+	}
+out_unlock:
+	spin_unlock_irq(&zone->lru_lock);
+out:
+	ra_account(0, RA_EVENT_READAHEAD_RESCUE, pgrescue);
+
+	return nr_pages ? index : 0;
+}

--

2.6.15-rc1-mm2

[Andrew Morton]

ftp://ftp.kernel.org/pub/linux/kernel/people/akpm/patches/2.6/2.6.15-rc1/2.6.15-rc1-mm2/


- I'm releasing this so that Hugh's MM rework can get a spin.

  Anyone who had post-2.6.14 problems related to the VM_RESERVED changes
  (device drivers malfunctioning, obscure userspace hardware-poking
  applications stopped working, etc) please test.

  We'd especially like testing of the graphics DRM drivers across as many
  card types as poss.

- cifs is busted when built as a module.  Mysteriously.

- Added the parisc devel tree to the -mm lineup as git-parisc.patch (Kyle
  McMartin <kyle@mcmartin.ca>)

- Added the powerpc devel tree to the -mm lineup as git-powerpc.patch (Paul
  MacKerras).

- Dropped the powerpc devel tree again due to refusal to boot.  Next time
  for sure.

- The JSM driver is still busted.  Make sure that CONFIG_SERIAL_JSM=n

- The UML update here is reported to cause a compile failure.



Changes since 2.6.15-rc1-mm1:

 linus.patch
 git-acpi.patch
 git-agpgart.patch
 git-blktrace.patch
 git-block.patch
 git-cfq.patch
 git-cifs.patch
 git-drm.patch
 git-ia64.patch
 git-ieee1394.patch
 git-infiniband.patch
 git-libata-all.patch
 git-netdev-all.patch
 git-ocfs2.patch
 git-parisc.patch
 git-pcmcia.patch
 git-sas.patch
 git-cryptodev.patch

 Subsystem trees.

-cifs-build-fix.patch
-gregkh-usb-usb-fix-dummy_hcd-breakage.patch
-gregkh-usb-usb-serial-history-not-old.patch
-gregkh-usb-add-new-wacom-devices-to-usb-hid-core-list.patch
-gregkh-usb-usb-wacom-tablet-driver-update.patch
-gregkh-usb-usb-fix-unused-variable-warning.patch
-gregkh-usb-usb-delete-bluetty-leftovers.patch
-gregkh-usb-usbfs_dir_inode_operations-cleanup.patch
-gregkh-usb-usb-usbdevfs_ioctl-from-32bit-fix.patch
-gregkh-usb-usb-storage-blacklist-entry-removal.patch
-gregkh-usb-usb-cp2101-new-id.patch
-gregkh-usb-usb-onetouch-doesn-t-suspend-yet.patch
-gregkh-usb-usb-pl2303-adds-new-ids.patch
-gregkh-usb-usb-pl2303-updates-pl2303_update_line_status.patch
-gregkh-usb-usb-adapt-microtek-driver-to-new-scsi-features.patch
-gregkh-usb-usb-storage-fix-detection-of-kodak-flash-readers-in-shuttle_usbat-driver.patch
-gregkh-usb-usb-fix-race-in-kaweth-disconnect.patch
-gregkh-usb-usb-devio-warning-fix.patch
-gregkh-usb-usb-maxtor-onetouch-button-support-for-older-drives.patch
-gregkh-usb-usb-ohci-lh7a404-platform-device-conversion-fixup.patch
 gregkh-usb-usb-libusual.patch
-gregkh-usb-usb-serial-anydata.patch
-ipw2200-disallow-direct-scanning-when-device-is-down.patch
-cifs-read-write-operation-fixes-and-cleanups.patch
-parisc-remove-drm-compat-ioctls-handlers.patch
-parisc-implement-compat_ioctl-for-pa_perf.patch

 Merged

+tpm-remove-pci-kconfig-dependency.patch

 TPM driver cleanup

+ppc64-need-hpage_shift-when-huge-pages-disabled.patch

 ppc64 build fix

+s390-fix-class_device_create-calls-in-3270-the-driver.patch

 s390 driver fix

+uml-eliminate-use-of-local-in-clone-stub.patch
+uml-eliminate-anonymous-union-and-clean-up-symlink-lossage.patch
+uml-properly-invoke-x86_64-system-calls.patch
+uml-eliminate-use-of-libc-page_size.patch

 UML update

+unpaged-get_user_pages-vm_reserved.patch
+unpaged-private-write-vm_reserved.patch
+unpaged-sound-nopage-get_page.patch
+unpaged-unifdefed-pagecompound.patch
+unpaged-vm_unpaged.patch
+unpaged-vm_nonlinear-vm_reserved.patch
+unpaged-cow-on-vm_unpaged.patch
+unpaged-anon-in-vm_unpaged.patch
+unpaged-zero_page-in-vm_unpaged.patch
+unpaged-pg_reserved-bad_page.patch
+unpaged-copy_page_range-vma.patch

 VM_RESERVED fixes

+fix-error-handling-with-put_compat_statfs.patch

 compat handling fix

+fix-hugetlbfs_statfs-reporting-of-block-limits.patch

 Make hugetlbfs do statfs better

+git-libata-sata_mv-build-fix.patch

 Fix git-libata-all.patch

+backup-timer-for-uarts-that-lose-interrupts-take-3.patch

 Serial driver workaround for dodgy hardware.

+mm-remove-arch-independent-nodes_span_other_nodes.patch

 mm cleanup

+numa-policies-in-the-slab-allocator-v2.patch
+numa-policies-in-the-slab-allocator-v2-fix.patch

 Fix NUMA allocation via the slab allocator (still under discussion)

+mm-add-is_dma_zone-helper.patch
+mm-add-populated_zone-helper.patch

 mm cleanups

+swap-migration-v5-mpol_mf_move-interface-unpaged-fix.patch

 Fix swap-migration-v5-mpol_mf_move-interface.patch for Hugh's stuff.

+swapmig-config_migration-fixes.patch
+swapmig-add_to_swap-avoid-atomic-allocations.patch
+swapmig-drop-unused-pages-immediately.patch
+swapmig-extend-parameters-for-migrate_pages.patch

 Update the page-migration-via-swap feature.

+swsusp-remove-encryption.patch
+swsusp-introduce-the-swap-map-structure.patch
+swsusp-improve-freeing-of-memory.patch

 swsusp cleanups

+keys-permit-running-process-to-instantiate-keys-warning-fix.patch

 Fix keys-permit-running-process-to-instantiate-keys.patch

+sigaction-should-clear-all-signals-on-sig_ign-not-just-fix.patch

 Fix sigaction-should-clear-all-signals-on-sig_ign-not-just.patch

+optionally-skip-initramfs-check.patch

 Faster booting on embedded systems.

+docs-updated-some-code-docs.patch

 Documentation updates

+prefer-pkg-config-for-the-qt-check.patch

 Update `make pkg-config'.

-spufs-the-spu-file-system-base.patch
-spufs-make-all-exports-gpl-only.patch
-spufs-switchable-spu-contexts.patch
-kernel-side-context-switch-code-for-spufs.patch
-spufs-add-spu-side-context-switch-code.patch
-spufs-cooperative-scheduler-support.patch

 Dropped - these are in the git-powerpc tree which isn't here.

+kdump-i386-save-ss-esp-bug-fix.patch
+kdump-dynamic-per-cpu-allocation-of-memory-for-saving-cpu-registers.patch
+kdump-export-per-cpu-crash-notes-pointer-through-sysfs.patch
+kdump-save-registers-early-inline-functions.patch
+kdump-x86_64-add-memmmap-command-line-option.patch
+kdump-x86_64-add-elfcorehdr-command-line-option.patch
+kdump-x86_64-kexec-on-panic.patch
+kdump-x86_64-save-cpu-registers-upon-crash.patch
+kdump-read-previous-kernels-memory.patch
+kexec-increase-max-segment-limit.patch

 Kernel crashdumpiung update

-add-compat_ioctl-methods-to-dasd.patch
-add-compat_ioctl-methods-to-dasd-fix.patch

 Dropped - wrong.

+drivers-char-use-array_size-macro.patch

 Cleanup.


All 617 patches:

ftp://ftp.kernel.org/pub/linux/kernel/people/akpm/patches/2.6/2.6.15-rc1/2.6.15-rc1-mm2/patch-list

Re: 2.6.15-rc1-mm2

[Benoit Boissinot]

[-- Attachment #1: Type: text/plain, Size: 679 bytes --]

On 11/18/05, Andrew Morton <akpm@osdl.org> wrote:
>
> ftp://ftp.kernel.org/pub/linux/kernel/people/akpm/patches/2.6/2.6.15-rc1/2.6.15-rc1-mm2/
>
>
> - I'm releasing this so that Hugh's MM rework can get a spin.
>
>   Anyone who had post-2.6.14 problems related to the VM_RESERVED changes
>   (device drivers malfunctioning, obscure userspace hardware-poking
>   applications stopped working, etc) please test.
>
>   We'd especially like testing of the graphics DRM drivers across as many
>   card types as poss.
>
I tried running neverball and had "bad page state".

dmesg and lspci -v attached

Please ask if you need more informations.

regards,

Benoit

[-- Attachment #2: dmesg.log --]
[-- Type: application/octet-stream, Size: 0 bytes --]



[-- Attachment #3: lspci --]
[-- Type: application/octet-stream, Size: 0 bytes --]

Re: 2.6.15-rc1-mm2

[Andrew Morton]

Benoit Boissinot <benoit.boissinot@ens-lyon.fr> wrote:
>
> On 11/18/05, Andrew Morton <akpm@osdl.org> wrote:
> >
> > ftp://ftp.kernel.org/pub/linux/kernel/people/akpm/patches/2.6/2.6.15-rc1/2.6.15-rc1-mm2/
> >
> >
> > - I'm releasing this so that Hugh's MM rework can get a spin.
> >
> >   Anyone who had post-2.6.14 problems related to the VM_RESERVED changes
> >   (device drivers malfunctioning, obscure userspace hardware-poking
> >   applications stopped working, etc) please test.
> >
> >   We'd especially like testing of the graphics DRM drivers across as many
> >   card types as poss.
> >
> I tried running neverball and had "bad page state".

OK, thanks for that.

> dmesg and lspci -v attached

The attachments are empty.   Can you resend the dmesg one please?

Re: 2.6.15-rc1-mm2

[Benoit Boissinot]

[-- Attachment #1: Type: text/plain, Size: 982 bytes --]

On Fri, Nov 18, 2005 at 01:04:49AM -0800, Andrew Morton wrote:
> Benoit Boissinot <benoit.boissinot@ens-lyon.fr> wrote:
> >
> > On 11/18/05, Andrew Morton <akpm@osdl.org> wrote:
> > >
> > > ftp://ftp.kernel.org/pub/linux/kernel/people/akpm/patches/2.6/2.6.15-rc1/2.6.15-rc1-mm2/
> > >
> > >
> > > - I'm releasing this so that Hugh's MM rework can get a spin.
> > >
> > >   Anyone who had post-2.6.14 problems related to the VM_RESERVED changes
> > >   (device drivers malfunctioning, obscure userspace hardware-poking
> > >   applications stopped working, etc) please test.
> > >
> > >   We'd especially like testing of the graphics DRM drivers across as many
> > >   card types as poss.
> > >
> > I tried running neverball and had "bad page state".
> 
> OK, thanks for that.
> 
> > dmesg and lspci -v attached
> 
> The attachments are empty.   Can you resend the dmesg one please?
[this time with mutt :)]

-- 
powered by bash/screen/(urxvt/fvwm|linux-console)/gentoo/gnu/linux OS

[-- Attachment #2: dmesg.log --]
[-- Type: text/plain, Size: 33034 bytes --]

79569.184000] Allocating PCI resources starting at 30000000 (gap: 20000000:deda0000)
[17179569.184000] Built 1 zonelists
[17179569.184000] Local APIC disabled by BIOS -- you can enable it with "lapic"
[17179569.184000] mapped APIC to ffffd000 (01401000)
[17179569.184000] Enabling fast FPU save and restore... done.
[17179569.184000] Enabling unmasked SIMD FPU exception support... done.
[17179569.184000] Initializing CPU#0
[17179569.184000] Kernel command line: root=/dev/hda5 video=vesa:mtrr vga=0x317 resume=/dev/hda3
[17179569.184000] CPU 0 irqstacks, hard=c03f6000 soft=c03f5000
[17179569.184000] PID hash table entries: 2048 (order: 11, 32768 bytes)
[    0.000000] Detected 1598.810 MHz processor.
[    7.254473] Using tsc for high-res timesource
[    7.254509] Console: colour dummy device 80x25
[    7.255211] Dentry cache hash table entries: 131072 (order: 7, 524288 bytes)
[    7.255967] Inode-cache hash table entries: 65536 (order: 6, 262144 bytes)
[    7.270625] Memory: 515192k/523960k available (2156k kernel code, 8200k reserved, 666k data, 180k init, 0k highmem)
[    7.270637] Checking if this processor honours the WP bit even in supervisor mode... Ok.
[    7.349085] Calibrating delay using timer specific routine.. 3201.13 BogoMIPS (lpj=6402260)
[    7.349127] Mount-cache hash table entries: 512
[    7.349227] CPU: After generic identify, caps: afe9f9bf 00000000 00000000 00000000 00000180 00000000 00000000
[    7.349235] CPU: After vendor identify, caps: afe9f9bf 00000000 00000000 00000000 00000180 00000000 00000000
[    7.349244] CPU: L1 I cache: 32K, L1 D cache: 32K
[    7.349249] CPU: L2 cache: 2048K
[    7.349252] CPU: After all inits, caps: afe9f9bf 00000000 00000000 00000040 00000180 00000000 00000000
[    7.349258] Intel machine check architecture supported.
[    7.349264] Intel machine check reporting enabled on CPU#0.
[    7.349276] mtrr: v2.0 (20020519)
[    7.349282] CPU: Intel(R) Pentium(R) M processor 1.60GHz stepping 06
[    7.349290] Checking 'hlt' instruction... OK.
[    7.377767] ACPI: setting ELCR to 0200 (from 0800)
[    7.380359] NET: Registered protocol family 16
[    7.380383] ACPI: bus type pci registered
[    7.380391] PCI: Using configuration type 1
[    7.380743] ACPI: Subsystem revision 20050916
[    7.396488] ACPI: Interpreter enabled
[    7.396493] ACPI: Using PIC for interrupt routing
[    7.397710] ACPI: PCI Root Bridge [PCI0] (0000:00)
[    7.397716] PCI: Probing PCI hardware (bus 00)
[    7.397839] ACPI: Assume root bridge [\_SB_.PCI0] bus is 0
[    7.408319] PCI quirk: region 0800-087f claimed by ICH4 ACPI/GPIO/TCO
[    7.408326] PCI quirk: region 0880-08bf claimed by ICH4 GPIO
[    7.408372] PCI: Ignoring BAR0-3 of IDE controller 0000:00:1f.1
[    7.408484] Boot video device is 0000:01:00.0
[    7.408715] PCI: Transparent bridge - 0000:00:1e.0
[    7.408814] ACPI: PCI Interrupt Routing Table [\_SB_.PCI0._PRT]
[    7.431144] ACPI: PCI Interrupt Link [LNKA] (IRQs 9 10 *11)
[    7.431385] ACPI: PCI Interrupt Link [LNKB] (IRQs 5 7) *11
[    7.431624] ACPI: PCI Interrupt Link [LNKC] (IRQs 9 10 *11)
[    7.431861] ACPI: PCI Interrupt Link [LNKD] (IRQs 5 7 9 10 *11)
[    7.432092] ACPI: PCI Interrupt Link [LNKE] (IRQs 3 4 5 6 7 9 10 11 12 14 15) *0, disabled.
[    7.432335] ACPI: PCI Interrupt Link [LNKH] (IRQs 3 4 5 6 7 9 10 *11 12 14 15)
[    7.433534] ACPI: PCI Interrupt Routing Table [\_SB_.PCI0.AGP_._PRT]
[    7.434240] ACPI: PCI Interrupt Routing Table [\_SB_.PCI0.PCIE._PRT]
[    7.435197] Linux Plug and Play Support v0.97 (c) Adam Belay
[    7.435208] pnp: PnP ACPI init
[    7.463911] pnp: PnP ACPI: found 13 devices
[    7.463954] Generic PHY: Registered new driver
[    7.464044] SCSI subsystem initialized
[    7.464073] PCI: Using ACPI for IRQ routing
[    7.464078] PCI: If a device doesn't work, try "pci=routeirq".  If it helps, post a report
[    7.469176] pnp: 00:02: ioport range 0x4d0-0x4d1 has been reserved
[    7.469181] pnp: 00:02: ioport range 0x800-0x805 could not be reserved
[    7.469186] pnp: 00:02: ioport range 0x808-0x80f could not be reserved
[    7.469193] pnp: 00:03: ioport range 0xf400-0xf4fe has been reserved
[    7.469197] pnp: 00:03: ioport range 0x806-0x807 has been reserved
[    7.469202] pnp: 00:03: ioport range 0x810-0x85f could not be reserved
[    7.469207] pnp: 00:03: ioport range 0x860-0x87f has been reserved
[    7.469211] pnp: 00:03: ioport range 0x880-0x8bf has been reserved
[    7.469216] pnp: 00:03: ioport range 0x8c0-0x8df has been reserved
[    7.469223] pnp: 00:08: ioport range 0x900-0x97f has been reserved
[    7.469394] PCI: Bridge: 0000:00:01.0
[    7.469398]   IO window: c000-cfff
[    7.469403]   MEM window: fc000000-fdffffff
[    7.469408]   PREFETCH window: e8000000-efffffff
[    7.469424] PCI: Bus 3, cardbus bridge: 0000:02:01.0
[    7.469427]   IO window: 0000d000-0000d0ff
[    7.469433]   IO window: 0000d400-0000d4ff
[    7.469438]   PREFETCH window: 30000000-31ffffff
[    7.469444]   MEM window: f6000000-f7ffffff
[    7.469449] PCI: Bus 7, cardbus bridge: 0000:02:01.1
[    7.469452]   IO window: 0000d800-0000d8ff
[    7.469458]   IO window: 0000dc00-0000dcff
[    7.469463]   PREFETCH window: 32000000-33ffffff
[    7.469469]   MEM window: f8000000-f9ffffff
[    7.469474] PCI: Bridge: 0000:00:1e.0
[    7.469478]   IO window: d000-efff
[    7.469484]   MEM window: f6000000-fbffffff
[    7.469490]   PREFETCH window: 30000000-33ffffff
[    7.469506] PCI: Setting latency timer of device 0000:00:1e.0 to 64
[    7.469518] PCI: Enabling device 0000:02:01.0 (0000 -> 0003)
[    7.469693] ACPI: PCI Interrupt Link [LNKD] enabled at IRQ 11
[    7.469698] PCI: setting IRQ 11 as level-triggered
[    7.469703] ACPI: PCI Interrupt 0000:02:01.0[A] -> Link [LNKD] -> GSI 11 (level, low) -> IRQ 11
[    7.469721] PCI: Enabling device 0000:02:01.1 (0000 -> 0003)
[    7.469726] ACPI: PCI Interrupt 0000:02:01.1[A] -> Link [LNKD] -> GSI 11 (level, low) -> IRQ 11
[    7.470225] Initializing Cryptographic API
[    7.470231] io scheduler noop registered
[    7.470237] io scheduler anticipatory registered
[    7.470243] io scheduler deadline registered
[    7.470252] io scheduler cfq registered
[    7.470537] ACPI: PCI Interrupt Link [LNKA] enabled at IRQ 11
[    7.470542] ACPI: PCI Interrupt 0000:01:00.0[A] -> Link [LNKA] -> GSI 11 (level, low) -> IRQ 11
[    7.470583] radeonfb: Retreived PLL infos from BIOS
[    7.470588] radeonfb: Reference=27.00 MHz (RefDiv=12) Memory=220.00 Mhz, System=200.00 MHz
[    7.470593] radeonfb: PLL min 20000 max 35000
[    8.404252] Non-DDC laptop panel detected
[    9.340510] radeonfb: Monitor 1 type LCD found
[    9.340513] radeonfb: Monitor 2 type no found
[    9.340518] radeonfb: panel ID string: 6J5644141XB
[    9.340519]             
[    9.340524] radeonfb: detected LVDS panel size from BIOS: 1024x768
[    9.340528] radeondb: BIOS provided dividers will be used
[    9.459414] radeonfb: Dynamic Clock Power Management enabled
[    9.489255] Console: switching to colour frame buffer device 128x48
[    9.490344] radeonfb (0000:01:00.0): ATI Radeon Lf 
[    9.490536] vesafb: cannot reserve video memory at 0xe8000000
[    9.490614] vesafb: framebuffer at 0xe8000000, mapped to 0xe1900000, using 3072k, total 32704k
[    9.490712] vesafb: mode is 1024x768x16, linelength=2048, pages=20
[    9.490790] vesafb: protected mode interface info at c000:57f3
[    9.490861] vesafb: scrolling: redraw
[    9.490912] vesafb: Truecolor: size=0:5:6:5, shift=0:11:5:0
[    9.491022] fb1: VESA VGA frame buffer device
[    9.505265] Real Time Clock Driver v1.12
[    9.505337] Linux agpgart interface v0.101 (c) Dave Jones
[    9.505443] agpgart: Detected an Intel 855PM Chipset.
[    9.514101] agpgart: AGP aperture is 128M @ 0xe0000000
[    9.514276] PNP: PS/2 Controller [PNP0303:KBC,PNP0f13:PS2M] at 0x60,0x64 irq 1,12
[    9.518178] serio: i8042 AUX port at 0x60,0x64 irq 12
[    9.518556] serio: i8042 KBD port at 0x60,0x64 irq 1
[    9.518695] mice: PS/2 mouse device common for all mice
[    9.528420] input: AT Translated Set 2 keyboard as /class/input/input0
[   12.528986] floppy0: no floppy controllers found
[   12.532694] RAMDISK driver initialized: 16 RAM disks of 4096K size 1024 blocksize
[   12.536317] loop: loaded (max 8 devices)
[   12.539824] Uniform Multi-Platform E-IDE driver Revision: 7.00alpha2
[   12.543262] ide: Assuming 33MHz system bus speed for PIO modes; override with idebus=xx
[   12.546773] ICH4: IDE controller at PCI slot 0000:00:1f.1
[   12.550289] PCI: Enabling device 0000:00:1f.1 (0005 -> 0007)
[   12.553860] ACPI: PCI Interrupt 0000:00:1f.1[A] -> Link [LNKA] -> GSI 11 (level, low) -> IRQ 11
[   12.557615] ICH4: chipset revision 1
[   12.561405] ICH4: not 100% native mode: will probe irqs later
[   12.565217]     ide0: BM-DMA at 0xbfa0-0xbfa7, BIOS settings: hda:DMA, hdb:pio
[   12.569094]     ide1: BM-DMA at 0xbfa8-0xbfaf, BIOS settings: hdc:DMA, hdd:pio
[   12.572849] Probing IDE interface ide0...
[   12.860876] hda: TOSHIBA MK4026GAX, ATA DISK drive
[   13.532258] ide0 at 0x1f0-0x1f7,0x3f6 on irq 14
[   13.536008] Probing IDE interface ide1...
[   14.271758] hdc: SAMSUNG CDRW/DVD SN-324S, ATAPI CD/DVD-ROM drive
[   14.943627] ide1 at 0x170-0x177,0x376 on irq 15
[   14.947743] hda: max request size: 128KiB
[   15.000365] hda: 78140160 sectors (40007 MB), CHS=65535/16/63, UDMA(100)
[   15.004225] hda: cache flushes supported
[   15.008063]  hda: hda1 hda2 hda3 hda4 < hda5 hda6 >
[   15.053371] i2c /dev entries driver
[   15.057345] NET: Registered protocol family 2
[   15.094991] IP route cache hash table entries: 8192 (order: 3, 32768 bytes)
[   15.098972] TCP established hash table entries: 32768 (order: 5, 131072 bytes)
[   15.102958] TCP bind hash table entries: 32768 (order: 5, 131072 bytes)
[   15.106925] TCP: Hash tables configured (established 32768 bind 32768)
[   15.110759] TCP reno registered
[   15.114648] TCP bic registered
[   15.118377] NET: Registered protocol family 1
[   15.122055] NET: Registered protocol family 17
[   15.125702] Using IPI Shortcut mode
[   15.143124] ACPI wakeup devices: 
[   15.146725]  LID PBTN PCI0 USB0 USB1 USB2 USB3 MODM PCIE 
[   15.150564] ACPI: (supports S0 S1 S3 S4 S5)
[   15.164554] ReiserFS: hda5: found reiserfs format "3.6" with standard journal
[   16.027363] ReiserFS: hda5: using ordered data mode
[   16.044862] ReiserFS: hda5: journal params: device hda5, size 8192, journal first block 18, max trans len 1024, max batch 900, max commit age 30, max trans age 30
[   16.053238] ReiserFS: hda5: checking transaction log (hda5)
[   16.131674] ReiserFS: hda5: Using r5 hash to sort names
[   16.135732] VFS: Mounted root (reiserfs filesystem) readonly.
[   16.139905] Freeing unused kernel memory: 180k freed
[   16.143918] Write protecting the kernel read-only data: 302k
[   18.963302] Adding 979956k swap on /dev/hda3.  Priority:-1 extents:1 across:979956k
[   20.248172] hdc: ATAPI 24X DVD-ROM CD-R/RW drive, 2048kB Cache, UDMA(33)
[   20.248182] Uniform CD-ROM driver Revision: 3.20
[   20.375037] ieee80211_crypt: registered algorithm 'NULL'
[   20.419247] ieee80211: 802.11 data/management/control stack, git-1.1.7
[   20.419252] ieee80211: Copyright (C) 2004-2005 Intel Corporation <jketreno@linux.intel.com>
[   20.477128] ipw2200: Intel(R) PRO/Wireless 2200/2915 Network Driver, git-1.0.8
[   20.477132] ipw2200: Copyright(c) 2003-2005 Intel Corporation
[   20.485526] ACPI: PCI Interrupt Link [LNKB] enabled at IRQ 5
[   20.485541] PCI: setting IRQ 5 as level-triggered
[   20.485545] ACPI: PCI Interrupt 0000:02:03.0[A] -> Link [LNKB] -> GSI 5 (level, low) -> IRQ 5
[   20.492556] ipw2200: Detected Intel PRO/Wireless 2200BG Network Connection
[   20.942724] tg3.c:v3.43 (Oct 24, 2005)
[   20.942992] ACPI: PCI Interrupt Link [LNKC] enabled at IRQ 11
[   20.942995] ACPI: PCI Interrupt 0000:02:00.0[A] -> Link [LNKC] -> GSI 11 (level, low) -> IRQ 11
[   20.975955] eth0: Tigon3 [partno(BCM95705A50) rev 3001 PHY(5705)] (PCI:33MHz:32-bit) 10/100/1000BaseT Ethernet 00:0f:1f:ca:d7:a8
[   20.975964] eth0: RXcsums[1] LinkChgREG[1] MIirq[1] ASF[0] Split[0] WireSpeed[1] TSOcap[1] 
[   20.975967] eth0: dma_rwctrl[763f0000]
[   21.022269] input: DualPoint Stick as /class/input/input1
[   21.045759] input: AlpsPS/2 ALPS DualPoint TouchPad as /class/input/input2
[   21.260531] usbcore: registered new driver usbfs
[   21.263548] usbcore: registered new driver hub
[   21.302250] ACPI: PCI Interrupt Link [LNKH] enabled at IRQ 11
[   21.302255] ACPI: PCI Interrupt 0000:00:1d.7[D] -> Link [LNKH] -> GSI 11 (level, low) -> IRQ 11
[   21.302271] PCI: Setting latency timer of device 0000:00:1d.7 to 64
[   21.302276] ehci_hcd 0000:00:1d.7: EHCI Host Controller
[   21.302293] ehci_hcd 0000:00:1d.7: debug port 1
[   21.302303] PCI: cache line size of 32 is not supported by device 0000:00:1d.7
[   21.306234] ehci_hcd 0000:00:1d.7: new USB bus registered, assigned bus number 1
[   21.306245] ehci_hcd 0000:00:1d.7: irq 11, io mem 0xf4fffc00
[   21.310127] ehci_hcd 0000:00:1d.7: USB 2.0 started, EHCI 1.00, driver 10 Dec 2004
[   21.311920] hub 1-0:1.0: USB hub found
[   21.311931] hub 1-0:1.0: 6 ports detected
[   21.457648] USB Universal Host Controller Interface driver v2.3
[   21.471725] ACPI: PCI Interrupt 0000:00:1d.0[A] -> Link [LNKA] -> GSI 11 (level, low) -> IRQ 11
[   21.471741] PCI: Setting latency timer of device 0000:00:1d.0 to 64
[   21.471745] uhci_hcd 0000:00:1d.0: UHCI Host Controller
[   21.472242] uhci_hcd 0000:00:1d.0: new USB bus registered, assigned bus number 2
[   21.472252] uhci_hcd 0000:00:1d.0: irq 11, io base 0x0000bf80
[   21.487627] hub 2-0:1.0: USB hub found
[   21.487642] hub 2-0:1.0: 2 ports detected
[   21.590272] ACPI: PCI Interrupt 0000:00:1d.1[B] -> Link [LNKD] -> GSI 11 (level, low) -> IRQ 11
[   21.590285] PCI: Setting latency timer of device 0000:00:1d.1 to 64
[   21.590289] uhci_hcd 0000:00:1d.1: UHCI Host Controller
[   21.597523] uhci_hcd 0000:00:1d.1: new USB bus registered, assigned bus number 3
[   21.597535] uhci_hcd 0000:00:1d.1: irq 11, io base 0x0000bf40
[   21.598488] hub 3-0:1.0: USB hub found
[   21.598495] hub 3-0:1.0: 2 ports detected
[   21.702201] ACPI: PCI Interrupt 0000:00:1d.2[C] -> Link [LNKC] -> GSI 11 (level, low) -> IRQ 11
[   21.702215] PCI: Setting latency timer of device 0000:00:1d.2 to 64
[   21.702219] uhci_hcd 0000:00:1d.2: UHCI Host Controller
[   21.709636] uhci_hcd 0000:00:1d.2: new USB bus registered, assigned bus number 4
[   21.709648] uhci_hcd 0000:00:1d.2: irq 11, io base 0x0000bf20
[   21.710639] hub 4-0:1.0: USB hub found
[   21.710647] hub 4-0:1.0: 2 ports detected
[   21.894807] ACPI: AC Adapter [AC] (on-line)
[   22.425249] ACPI: Battery Slot [BAT0] (battery present)
[   22.425324] ACPI: Battery Slot [BAT1] (battery absent)
[   22.949836] ACPI: CPU0 (power states: C1[C1] C2[C2] C3[C3] C4[C3])
[   22.949843] ACPI: Processor [CPU0] (supports 8 throttling states)
[   23.011806] ACPI: Thermal Zone [THM] (50 C)
[   23.106063] ACPI: Lid Switch [LID]
[   23.106072] ACPI: Power Button (CM) [PBTN]
[   23.106078] ACPI: Sleep Button (CM) [SBTN]
[   29.958765] kjournald starting.  Commit interval 5 seconds
[   29.958778] EXT3-fs: mounted filesystem with ordered data mode.
[   29.987017] ReiserFS: hda6: found reiserfs format "3.6" with standard journal
[   32.072568] ReiserFS: hda6: using ordered data mode
[   32.097509] ReiserFS: hda6: journal params: device hda6, size 8192, journal first block 18, max trans len 1024, max batch 900, max commit age 30, max trans age 30
[   32.097940] ReiserFS: hda6: checking transaction log (hda6)
[   32.140927] ReiserFS: hda6: Using r5 hash to sort names
init: Entering runlevel: 3
rc-scripts: Could not detect custom ALSA settings.  Loading all detected alsa drivers.
[   38.606919] ACPI: PCI Interrupt 0000:00:1f.5[B] -> Link [LNKB] -> GSI 5 (level, low) -> IRQ 5
[   38.606954] PCI: Setting latency timer of device 0000:00:1f.5 to 64
[   39.347491] intel8x0_measure_ac97_clock: measured 55460 usecs
[   39.347495] intel8x0: clocking to 48000
[   41.041433] Netfilter messages via NETLINK v0.30.
[   41.103149] ip_conntrack version 2.4 (4093 buckets, 32744 max) - 216 bytes per conntrack
[   41.237313] ip_tables: (C) 2000-2002 Netfilter core team
[   42.066955] hdc: drive_cmd: status=0x51 { DriveReady SeekComplete Error }
[   42.066965] hdc: drive_cmd: error=0x04 { AbortedCommand }
[   42.066968] ide: failed opcode was: 0xec
[   42.074856] hdc: drive_cmd: status=0x51 { DriveReady SeekComplete Error }
[   42.074863] hdc: drive_cmd: error=0x04 { AbortedCommand }
[   42.074867] ide: failed opcode was: 0xec
[   42.082636] hdc: drive_cmd: status=0x51 { DriveReady SeekComplete Error }
[   42.082643] hdc: drive_cmd: error=0x04 { AbortedCommand }
[   42.082647] ide: failed opcode was: 0xec
[   50.310273] [drm] Initialized drm 1.0.1 20051102
[   50.351137] ACPI: PCI Interrupt 0000:01:00.0[A] -> Link [LNKA] -> GSI 11 (level, low) -> IRQ 11
[   50.360327] [drm] Initialized radeon 1.19.0 20050911 on minor 0
[   50.360655] mtrr: 0xe8000000,0x8000000 overlaps existing 0xe8000000,0x2000000
[   50.361084] agpgart: Found an AGP 2.0 compliant device at 0000:00:00.0.
[   50.361096] agpgart: Putting AGP V2 device at 0000:00:00.0 into 1x mode
[   50.361121] agpgart: Putting AGP V2 device at 0000:01:00.0 into 1x mode
[   50.429460] [drm] Loading R200 Microcode
142.118190] Hexdump:
[  142.118192] 000: 04 04 00 80 ff ff ff ff ff ff ff ff 00 00 00 00
[  142.118200] 010: 00 00 00 00 2d 7c 0b 00 00 01 10 00 00 02 20 00
[  142.118209] 020: 04 04 00 80 ff ff ff ff ff ff ff ff 00 00 00 00
[  142.118217] 030: 00 00 00 00 2e 7c 0b 00 00 01 10 00 00 02 20 00
[  142.118226] 040: 14 04 00 80 ff ff ff ff ff ff ff ff 00 00 00 00
[  142.118234] 050: 00 00 00 00 2f 7c 0b 00 00 01 10 00 00 02 20 00
[  142.118242] 060: 04 04 00 80 00 00 00 00 00 00 00 00 00 00 00 00
[  142.118250] 070: 00 00 00 00 30 7c 0b 00 00 01 10 00 00 02 20 00
[  142.118259] 080: 04 04 00 80 00 00 00 00 00 00 00 00 00 00 00 00
[  142.118267] 090: 00 00 00 00 31 7c 0b 00 00 01 10 00 00 02 20 00
[  142.118275] 0a0: 04 04 00 80 00 00 00 00 00 00 00 00 00 00 00 00
[  142.118283] 0b0: 00 00 00 00 32 7c 0b 00 00 01 10 00 00 02 20 00
[  142.118292] Trying to fix it up, but a reboot is needed
[  142.118295] Bad page state at free_hot_cold_page (in process 'neverball', page c13a4f00)
[  142.118298] flags:0x80000414 mapping:00000000 mapcount:0 count:0
[  142.118300] Backtrace:
[  142.118301]  [<c0103d17>] dump_stack+0x17/0x20
[  142.118305]  [<c013c3d6>] bad_page+0x86/0x140
[  142.118308]  [<c013cd33>] free_hot_cold_page+0x43/0xf0
[  142.118312]  [<c013cdea>] free_hot_page+0xa/0x10
[  142.118316]  [<c0140311>] __page_cache_release+0x51/0xc0
[  142.118320]  [<c013ffa9>] put_page+0x39/0x80
[  142.118324]  [<c014c2e3>] free_page_and_swap_cache+0x23/0x40
[  142.118328]  [<c014460a>] zap_pte_range+0x11a/0x290
[  142.118331]  [<c0144869>] unmap_page_range+0xe9/0x120
[  142.118335]  [<c014495c>] unmap_vmas+0xbc/0x1c0
[  142.118338]  [<c01488a9>] unmap_region+0x79/0xf0
[  142.118342]  [<c0148b9e>] do_munmap+0xde/0x120
[  142.118345]  [<c0148c1f>] sys_munmap+0x3f/0x60
[  142.118349]  [<c0102e5f>] sysenter_past_esp+0x54/0x75
[  142.118352] Hexdump:
[  142.118354] 000: 04 04 00 80 ff ff ff ff ff ff ff ff 00 00 00 00
[  142.118362] 010: 00 00 00 00 2e 7c 0b 00 00 01 10 00 00 02 20 00
[  142.118371] 020: 04 04 00 80 ff ff ff ff ff ff ff ff 00 00 00 00
[  142.118379] 030: 00 00 00 00 2f 7c 0b 00 00 01 10 00 00 02 20 00
[  142.118387] 040: 14 04 00 80 ff ff ff ff ff ff ff ff 00 00 00 00
[  142.118396] 050: 00 00 00 00 30 7c 0b 00 00 01 10 00 00 02 20 00
[  142.118404] 060: 04 04 00 80 00 00 00 00 00 00 00 00 00 00 00 00
[  142.118412] 070: 00 00 00 00 31 7c 0b 00 00 01 10 00 00 02 20 00
[  142.118421] 080: 04 04 00 80 00 00 00 00 00 00 00 00 00 00 00 00
[  142.118429] 090: 00 00 00 00 32 7c 0b 00 00 01 10 00 00 02 20 00
[  142.118437] 0a0: 04 04 00 80 00 00 00 00 00 00 00 00 00 00 00 00
[  142.118445] 0b0: 00 00 00 00 33 7c 0b 00 00 01 10 00 00 02 20 00
[  142.118454] Trying to fix it up, but a reboot is needed
[  142.118456] Bad page state at free_hot_cold_page (in process 'neverball', page c13a4f20)
[  142.118460] flags:0x80000414 mapping:00000000 mapcount:0 count:0
[  142.118462] Backtrace:
[  142.118463]  [<c0103d17>] dump_stack+0x17/0x20
[  142.118467]  [<c013c3d6>] bad_page+0x86/0x140
[  142.118470]  [<c013cd33>] free_hot_cold_page+0x43/0xf0
[  142.118474]  [<c013cdea>] free_hot_page+0xa/0x10
[  142.118478]  [<c0140311>] __page_cache_release+0x51/0xc0
[  142.118482]  [<c013ffa9>] put_page+0x39/0x80
[  142.118485]  [<c014c2e3>] free_page_and_swap_cache+0x23/0x40
[  142.118490]  [<c014460a>] zap_pte_range+0x11a/0x290
[  142.118493]  [<c0144869>] unmap_page_range+0xe9/0x120
[  142.118497]  [<c014495c>] unmap_vmas+0xbc/0x1c0
[  142.118500]  [<c01488a9>] unmap_region+0x79/0xf0
[  142.118504]  [<c0148b9e>] do_munmap+0xde/0x120
[  142.118507]  [<c0148c1f>] sys_munmap+0x3f/0x60
[  142.118511]  [<c0102e5f>] sysenter_past_esp+0x54/0x75
[  142.118514] Hexdump:
[  142.118516] 000: 04 04 00 80 ff ff ff ff ff ff ff ff 00 00 00 00
[  142.118524] 010: 00 00 00 00 2f 7c 0b 00 00 01 10 00 00 02 20 00
[  142.118533] 020: 04 04 00 80 ff ff ff ff ff ff ff ff 00 00 00 00
[  142.118541] 030: 00 00 00 00 30 7c 0b 00 00 01 10 00 00 02 20 00
[  142.118549] 040: 14 04 00 80 ff ff ff ff ff ff ff ff 00 00 00 00
[  142.118558] 050: 00 00 00 00 31 7c 0b 00 00 01 10 00 00 02 20 00
[  142.118566] 060: 04 04 00 80 00 00 00 00 00 00 00 00 00 00 00 00
[  142.118574] 070: 00 00 00 00 32 7c 0b 00 00 01 10 00 00 02 20 00
[  142.118583] 080: 04 04 00 80 00 00 00 00 00 00 00 00 00 00 00 00
[  142.118591] 090: 00 00 00 00 33 7c 0b 00 00 01 10 00 00 02 20 00
[  142.118599] 0a0: 04 04 00 80 00 00 00 00 00 00 00 00 00 00 00 00
[  142.118607] 0b0: 00 00 00 00 34 7c 0b 00 00 01 10 00 00 02 20 00
[  142.118616] Trying to fix it up, but a reboot is needed
[  142.118618] Bad page state at free_hot_cold_page (in process 'neverball', page c13a4f40)
[  142.118622] flags:0x80000414 mapping:00000000 mapcount:0 count:0
[  142.118624] Backtrace:
[  142.118625]  [<c0103d17>] dump_stack+0x17/0x20
[  142.118629]  [<c013c3d6>] bad_page+0x86/0x140
[  142.118633]  [<c013cd33>] free_hot_cold_page+0x43/0xf0
[  142.118636]  [<c013cdea>] free_hot_page+0xa/0x10
[  142.118640]  [<c0140311>] __page_cache_release+0x51/0xc0
[  142.118644]  [<c013ffa9>] put_page+0x39/0x80
[  142.118648]  [<c014c2e3>] free_page_and_swap_cache+0x23/0x40
[  142.118652]  [<c014460a>] zap_pte_range+0x11a/0x290
[  142.118655]  [<c0144869>] unmap_page_range+0xe9/0x120
[  142.118659]  [<c014495c>] unmap_vmas+0xbc/0x1c0
[  142.118662]  [<c01488a9>] unmap_region+0x79/0xf0
[  142.118666]  [<c0148b9e>] do_munmap+0xde/0x120
[  142.118670]  [<c0148c1f>] sys_munmap+0x3f/0x60
[  142.118673]  [<c0102e5f>] sysenter_past_esp+0x54/0x75
[  142.118676] Hexdump:
[  142.118678] 000: 04 04 00 80 ff ff ff ff ff ff ff ff 00 00 00 00
[  142.118686] 010: 00 00 00 00 30 7c 0b 00 00 01 10 00 00 02 20 00
[  142.118695] 020: 04 04 00 80 ff ff ff ff ff ff ff ff 00 00 00 00
[  142.118703] 030: 00 00 00 00 31 7c 0b 00 00 01 10 00 00 02 20 00
[  142.118712] 040: 14 04 00 80 ff ff ff ff ff ff ff ff 00 00 00 00
[  142.118720] 050: 00 00 00 00 32 7c 0b 00 00 01 10 00 00 02 20 00
[  142.118728] 060: 04 04 00 80 00 00 00 00 00 00 00 00 00 00 00 00
[  142.118736] 070: 00 00 00 00 33 7c 0b 00 00 01 10 00 00 02 20 00
[  142.118745] 080: 04 04 00 80 00 00 00 00 00 00 00 00 00 00 00 00
[  142.118753] 090: 00 00 00 00 34 7c 0b 00 00 01 10 00 00 02 20 00
[  142.118761] 0a0: 04 04 00 80 00 00 00 00 00 00 00 00 00 00 00 00
[  142.118769] 0b0: 00 00 00 00 35 7c 0b 00 00 01 10 00 00 02 20 00
[  142.118778] Trying to fix it up, but a reboot is needed
[  142.118781] Bad page state at free_hot_cold_page (in process 'neverball', page c13a4f60)
[  142.118784] flags:0x80000414 mapping:00000000 mapcount:0 count:0
[  142.118786] Backtrace:
[  142.118787]  [<c0103d17>] dump_stack+0x17/0x20
[  142.118791]  [<c013c3d6>] bad_page+0x86/0x140
[  142.118795]  [<c013cd33>] free_hot_cold_page+0x43/0xf0
[  142.118798]  [<c013cdea>] free_hot_page+0xa/0x10
[  142.118802]  [<c0140311>] __page_cache_release+0x51/0xc0
[  142.118806]  [<c013ffa9>] put_page+0x39/0x80
[  142.118810]  [<c014c2e3>] free_page_and_swap_cache+0x23/0x40
[  142.118814]  [<c014460a>] zap_pte_range+0x11a/0x290
[  142.118817]  [<c0144869>] unmap_page_range+0xe9/0x120
[  142.118821]  [<c014495c>] unmap_vmas+0xbc/0x1c0
[  142.118825]  [<c01488a9>] unmap_region+0x79/0xf0
[  142.118828]  [<c0148b9e>] do_munmap+0xde/0x120
[  142.118832]  [<c0148c1f>] sys_munmap+0x3f/0x60
[  142.118835]  [<c0102e5f>] sysenter_past_esp+0x54/0x75
[  142.118838] Hexdump:
[  142.118840] 000: 04 04 00 80 ff ff ff ff ff ff ff ff 00 00 00 00
[  142.118849] 010: 00 00 00 00 31 7c 0b 00 00 01 10 00 00 02 20 00
[  142.118857] 020: 04 04 00 80 ff ff ff ff ff ff ff ff 00 00 00 00
[  142.118865] 030: 00 00 00 00 32 7c 0b 00 00 01 10 00 00 02 20 00
[  142.118874] 040: 14 04 00 80 ff ff ff ff ff ff ff ff 00 00 00 00
[  142.118882] 050: 00 00 00 00 33 7c 0b 00 00 01 10 00 00 02 20 00
[  142.118890] 060: 04 04 00 80 00 00 00 00 00 00 00 00 00 00 00 00
[  142.118898] 070: 00 00 00 00 34 7c 0b 00 00 01 10 00 00 02 20 00
[  142.118907] 080: 04 04 00 80 00 00 00 00 00 00 00 00 00 00 00 00
[  142.118915] 090: 00 00 00 00 35 7c 0b 00 00 01 10 00 00 02 20 00
[  142.118923] 0a0: 04 04 00 80 00 00 00 00 00 00 00 00 00 00 00 00
[  142.118931] 0b0: 00 00 00 00 36 7c 0b 00 00 01 10 00 00 02 20 00
[  142.118940] Trying to fix it up, but a reboot is needed
[  142.118943] Bad page state at free_hot_cold_page (in process 'neverball', page c13a4f80)
[  142.118946] flags:0x80000414 mapping:00000000 mapcount:0 count:0
[  142.118948] Backtrace:
[  142.118950]  [<c0103d17>] dump_stack+0x17/0x20
[  142.118953]  [<c013c3d6>] bad_page+0x86/0x140
[  142.118957]  [<c013cd33>] free_hot_cold_page+0x43/0xf0
[  142.118960]  [<c013cdea>] free_hot_page+0xa/0x10
[  142.118964]  [<c0140311>] __page_cache_release+0x51/0xc0
[  142.118968]  [<c013ffa9>] put_page+0x39/0x80
[  142.118972]  [<c014c2e3>] free_page_and_swap_cache+0x23/0x40
[  142.118976]  [<c014460a>] zap_pte_range+0x11a/0x290
[  142.118979]  [<c0144869>] unmap_page_range+0xe9/0x120
[  142.118983]  [<c014495c>] unmap_vmas+0xbc/0x1c0
[  142.118986]  [<c01488a9>] unmap_region+0x79/0xf0
[  142.118990]  [<c0148b9e>] do_munmap+0xde/0x120
[  142.118994]  [<c0148c1f>] sys_munmap+0x3f/0x60
[  142.118997]  [<c0102e5f>] sysenter_past_esp+0x54/0x75
[  142.119000] Hexdump:
[  142.119002] 000: 04 04 00 80 ff ff ff ff ff ff ff ff 00 00 00 00
[  142.119011] 010: 00 00 00 00 32 7c 0b 00 00 01 10 00 00 02 20 00
[  142.119019] 020: 04 04 00 80 ff ff ff ff ff ff ff ff 00 00 00 00
[  142.119027] 030: 00 00 00 00 33 7c 0b 00 00 01 10 00 00 02 20 00
[  142.119036] 040: 14 04 00 80 ff ff ff ff ff ff ff ff 00 00 00 00
[  142.119044] 050: 00 00 00 00 34 7c 0b 00 00 01 10 00 00 02 20 00
[  142.119052] 060: 04 04 00 80 00 00 00 00 00 00 00 00 00 00 00 00
[  142.119060] 070: 00 00 00 00 35 7c 0b 00 00 01 10 00 00 02 20 00
[  142.119069] 080: 04 04 00 80 00 00 00 00 00 00 00 00 00 00 00 00
[  142.119077] 090: 00 00 00 00 36 7c 0b 00 00 01 10 00 00 02 20 00
[  142.119085] 0a0: 04 04 00 80 00 00 00 00 00 00 00 00 00 00 00 00
[  142.119093] 0b0: 00 00 00 00 37 7c 0b 00 00 01 10 00 00 02 20 00
[  142.119102] Trying to fix it up, but a reboot is needed
[  142.119105] Bad page state at free_hot_cold_page (in process 'neverball', page c13a4fa0)
[  142.119108] flags:0x80000414 mapping:00000000 mapcount:0 count:0
[  142.119110] Backtrace:
[  142.119111]  [<c0103d17>] dump_stack+0x17/0x20
[  142.119115]  [<c013c3d6>] bad_page+0x86/0x140
[  142.119119]  [<c013cd33>] free_hot_cold_page+0x43/0xf0
[  142.119122]  [<c013cdea>] free_hot_page+0xa/0x10
[  142.119126]  [<c0140311>] __page_cache_release+0x51/0xc0
[  142.119130]  [<c013ffa9>] put_page+0x39/0x80
[  142.119134]  [<c014c2e3>] free_page_and_swap_cache+0x23/0x40
[  142.119138]  [<c014460a>] zap_pte_range+0x11a/0x290
[  142.119141]  [<c0144869>] unmap_page_range+0xe9/0x120
[  142.119145]  [<c014495c>] unmap_vmas+0xbc/0x1c0
[  142.119148]  [<c01488a9>] unmap_region+0x79/0xf0
[  142.119152]  [<c0148b9e>] do_munmap+0xde/0x120
[  142.119156]  [<c0148c1f>] sys_munmap+0x3f/0x60
[  142.119159]  [<c0102e5f>] sysenter_past_esp+0x54/0x75
[  142.119162] Hexdump:
[  142.119164] 000: 04 04 00 80 ff ff ff ff ff ff ff ff 00 00 00 00
[  142.119172] 010: 00 00 00 00 33 7c 0b 00 00 01 10 00 00 02 20 00
[  142.119181] 020: 04 04 00 80 ff ff ff ff ff ff ff ff 00 00 00 00
[  142.119189] 030: 00 00 00 00 34 7c 0b 00 00 01 10 00 00 02 20 00
[  142.119198] 040: 14 04 00 80 ff ff ff ff ff ff ff ff 00 00 00 00
[  142.119206] 050: 00 00 00 00 35 7c 0b 00 00 01 10 00 00 02 20 00
[  142.119225] 060: 04 04 00 80 00 00 00 00 00 00 00 00 00 00 00 00
[  142.119233] 070: 00 00 00 00 36 7c 0b 00 00 01 10 00 00 02 20 00
[  142.119241] 080: 04 04 00 80 00 00 00 00 00 00 00 00 00 00 00 00
[  142.119249] 090: 00 00 00 00 37 7c 0b 00 00 01 10 00 00 02 20 00
[  142.119258] 0a0: 2c 00 01 80 00 00 00 00 ff ff ff ff 00 00 00 00
[  142.119266] 0b0: f8 3e c9 dc 21 00 00 00 f8 a3 3c c1 38 50 3a c1
[  142.119274] Trying to fix it up, but a reboot is needed
[  142.119277] Bad page state at free_hot_cold_page (in process 'neverball', page c13a4fc0)
[  142.119281] flags:0x80000414 mapping:00000000 mapcount:0 count:0
[  142.119283] Backtrace:
[  142.119284]  [<c0103d17>] dump_stack+0x17/0x20
[  142.119288]  [<c013c3d6>] bad_page+0x86/0x140
[  142.119291]  [<c013cd33>] free_hot_cold_page+0x43/0xf0
[  142.119295]  [<c013cdea>] free_hot_page+0xa/0x10
[  142.119299]  [<c0140311>] __page_cache_release+0x51/0xc0
[  142.119303]  [<c013ffa9>] put_page+0x39/0x80
[  142.119307]  [<c014c2e3>] free_page_and_swap_cache+0x23/0x40
[  142.119311]  [<c014460a>] zap_pte_range+0x11a/0x290
[  142.119314]  [<c0144869>] unmap_page_range+0xe9/0x120
[  142.119318]  [<c014495c>] unmap_vmas+0xbc/0x1c0
[  142.119321]  [<c01488a9>] unmap_region+0x79/0xf0
[  142.119325]  [<c0148b9e>] do_munmap+0xde/0x120
[  142.119328]  [<c0148c1f>] sys_munmap+0x3f/0x60
[  142.119332]  [<c0102e5f>] sysenter_past_esp+0x54/0x75
[  142.119335] Hexdump:
[  142.119337] 000: 04 04 00 80 ff ff ff ff ff ff ff ff 00 00 00 00
[  142.119345] 010: 00 00 00 00 34 7c 0b 00 00 01 10 00 00 02 20 00
[  142.119354] 020: 04 04 00 80 ff ff ff ff ff ff ff ff 00 00 00 00
[  142.119362] 030: 00 00 00 00 35 7c 0b 00 00 01 10 00 00 02 20 00
[  142.119370] 040: 14 04 00 80 ff ff ff ff ff ff ff ff 00 00 00 00
[  142.119379] 050: 00 00 00 00 36 7c 0b 00 00 01 10 00 00 02 20 00
[  142.119387] 060: 04 04 00 80 00 00 00 00 00 00 00 00 00 00 00 00
[  142.119395] 070: 00 00 00 00 37 7c 0b 00 00 01 10 00 00 02 20 00
[  142.119404] 080: 2c 00 01 80 00 00 00 00 ff ff ff ff 00 00 00 00
[  142.119412] 090: f8 3e c9 dc 21 00 00 00 f8 a3 3c c1 38 50 3a c1
[  142.119420] 0a0: 2c 00 01 80 00 00 00 00 ff ff ff ff 00 00 00 00
[  142.119429] 0b0: f8 3e c9 dc 22 00 00 00 18 50 3a c1 58 50 3a c1
[  142.119437] Trying to fix it up, but a reboot is needed
[  142.119440] Bad page state at free_hot_cold_page (in process 'neverball', page c13a4fe0)
[  142.119443] flags:0x80000414 mapping:00000000 mapcount:0 count:0
[  142.119445] Backtrace:
[  142.119447]  [<c0103d17>] dump_stack+0x17/0x20
[  142.119450]  [<c013c3d6>] bad_page+0x86/0x140
[  142.119454]  [<c013cd33>] free_hot_cold_page+0x43/0xf0
[  142.119458]  [<c013cdea>] free_hot_page+0xa/0x10
[  142.119461]  [<c0140311>] __page_cache_release+0x51/0xc0
[  142.119465]  [<c013ffa9>] put_page+0x39/0x80
[  142.119469]  [<c014c2e3>] free_page_and_swap_cache+0x23/0x40
[  142.119473]  [<c014460a>] zap_pte_range+0x11a/0x290
[  142.119477]  [<c0144869>] unmap_page_range+0xe9/0x120
[  142.119480]  [<c014495c>] unmap_vmas+0xbc/0x1c0
[  142.119484]  [<c01488a9>] unmap_region+0x79/0xf0
[  142.119487]  [<c0148b9e>] do_munmap+0xde/0x120
[  142.119491]  [<c0148c1f>] sys_munmap+0x3f/0x60
[  142.119494]  [<c0102e5f>] sysenter_past_esp+0x54/0x75
[  142.119498] Hexdump:
[  142.119499] 000: 04 04 00 80 ff ff ff ff ff ff ff ff 00 00 00 00
[  142.119508] 010: 00 00 00 00 35 7c 0b 00 00 01 10 00 00 02 20 00
[  142.119516] 020: 04 04 00 80 ff ff ff ff ff ff ff ff 00 00 00 00
[  142.119525] 030: 00 00 00 00 36 7c 0b 00 00 01 10 00 00 02 20 00
[  142.119533] 040: 14 04 00 80 ff ff ff ff ff ff ff ff 00 00 00 00
[  142.119541] 050: 00 00 00 00 37 7c 0b 00 00 01 10 00 00 02 20 00
[  142.119550] 060: 2c 00 01 80 00 00 00 00 ff ff ff ff 00 00 00 00
[  142.119558] 070: f8 3e c9 dc 21 00 00 00 f8 a3 3c c1 38 50 3a c1
[  142.119566] 080: 2c 00 01 80 00 00 00 00 ff ff ff ff 00 00 00 00
[  142.119575] 090: f8 3e c9 dc 22 00 00 00 18 50 3a c1 58 50 3a c1
[  142.119583] 0a0: 2c 00 01 80 00 00 00 00 ff ff ff ff 00 00 00 00
[  142.119591] 0b0: f8 3e c9 dc 23 00 00 00 38 50 3a c1 78 50 3a c1
[  142.119600] Trying to fix it up, but a reboot is needed
[  171.963456] ipw2200: Unknown notification: subtype=40,flags=0xa0,size=40

Re: 2.6.15-rc1-mm2

[Rafael J. Wysocki]

[-- Attachment #1: Type: text/plain, Size: 3896 bytes --]

Hi,

On Friday, 18 of November 2005 10:04, Andrew Morton wrote:
> Benoit Boissinot <benoit.boissinot@ens-lyon.fr> wrote:
> >
> > On 11/18/05, Andrew Morton <akpm@osdl.org> wrote:
> > >
> > > ftp://ftp.kernel.org/pub/linux/kernel/people/akpm/patches/2.6/2.6.15-rc1/2.6.15-rc1-mm2/
> > >
> > >
> > > - I'm releasing this so that Hugh's MM rework can get a spin.
> > >
> > >   Anyone who had post-2.6.14 problems related to the VM_RESERVED changes
> > >   (device drivers malfunctioning, obscure userspace hardware-poking
> > >   applications stopped working, etc) please test.
> > >
> > >   We'd especially like testing of the graphics DRM drivers across as many
> > >   card types as poss.
> > >
> > I tried running neverball and had "bad page state".
> 
> OK, thanks for that.

I'm getting lots of similar things, apparently from artsd:

Nov 18 14:18:44 albercik kernel: Bad page state at free_hot_cold_page (in process 'artsd', page ffff810001996d38)
Nov 18 14:18:44 albercik kernel: flags:0x4000000000000414 mapping:0000000000000000 mapcount:0 count:0
Nov 18 14:18:44 albercik kernel: Backtrace:
Nov 18 14:18:44 albercik kernel: 
Nov 18 14:18:44 albercik kernel: Call Trace:<ffffffff8035f24e>{_spin_lock+30} <ffffffff801609f7>{bad_page+135}
Nov 18 14:18:44 albercik kernel:        <ffffffff80161034>{free_hot_cold_page+116} <ffffffff8016115b>{free_hot_page+11}
Nov 18 14:18:44 albercik kernel:        <ffffffff80163c69>{__page_cache_release+217} <ffffffff80163cf6>{put_page+118}
Nov 18 14:18:44 albercik kernel:        <ffffffff801724a8>{free_page_and_swap_cache+56} <ffffffff80168f7f>{unmap_vmas+1391}
Nov 18 14:18:44 albercik kernel:        <ffffffff8016c4c2>{unmap_region+178} <ffffffff8016d75e>{do_munmap+558}
Nov 18 14:18:44 albercik kernel:        <ffffffff8016d850>{sys_munmap+80} <ffffffff8010eb5e>{system_call+126}
Nov 18 14:18:44 albercik kernel:        
Nov 18 14:18:44 albercik kernel: ---------------------------
Nov 18 14:18:44 albercik kernel: | preempt count: 00000002 ]
Nov 18 14:18:45 albercik kernel: | 2 level deep critical section nesting:
Nov 18 14:18:45 albercik kernel: ----------------------------------------
Nov 18 14:18:46 albercik kernel: .. [<ffffffff8016c467>] .... unmap_region+0x57/0x150
Nov 18 14:18:46 albercik kernel: .....[<ffffffff8016d75e>] ..   ( <= do_munmap+0x22e/0x2d0)
Nov 18 14:18:46 albercik kernel: .. [<ffffffff8035f246>] .... _spin_lock+0x16/0x30
Nov 18 14:18:47 albercik kernel: .....[<ffffffff80168dc4>] ..   ( <= unmap_vmas+0x3b4/0x790)
Nov 18 14:18:47 albercik kernel: 
Nov 18 14:18:48 albercik kernel: Hexdump:
Nov 18 14:18:48 albercik kernel: 000: 00 f0 d5 2b 00 81 ff ff 14 04 00 00 00 00 00 40
Nov 18 14:18:48 albercik kernel: 010: 00 00 00 00 ff ff ff ff 00 00 00 00 00 00 00 00
Nov 18 14:18:49 albercik kernel: 020: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
Nov 18 14:18:50 albercik kernel: 030: 00 01 10 00 00 00 00 00 00 02 20 00 00 00 00 00
Nov 18 14:18:51 albercik kernel: 040: 14 04 00 00 00 00 00 40 ff ff ff ff ff ff ff ff
Nov 18 14:18:51 albercik kernel: 050: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
Nov 18 14:18:52 albercik kernel: 060: 00 00 00 00 00 00 00 00 60 6d 99 01 00 81 ff ff
Nov 18 14:18:53 albercik kernel: 070: 60 6d 99 01 00 81 ff ff 14 04 00 00 00 00 00 40
Nov 18 14:18:54 albercik kernel: 080: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
Nov 18 14:18:56 albercik kernel: 090: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
Nov 18 14:18:56 albercik kernel: 0a0: 98 6d 99 01 00 81 ff ff 98 6d 99 01 00 81 ff ff
Nov 18 14:19:00 albercik kernel: 0b0: 14 04 00 00 00 00 00 40 00 00 00 00 00 00 00 00
Nov 18 14:19:01 albercik kernel: Trying to fix it up, but a reboot is needed

on Asus L5D (x86-64).  This happens when artsd is started on KDE startup after a fresh
reboot and is 100% reproducible.  It did not happen on 2.6.15-rc1-mm1 with the same
.config, which is attached.

Greetings,
Rafael


[-- Attachment #2: L5D-config --]
[-- Type: text/plain, Size: 43873 bytes --]

#
# Automatically generated make config: don't edit
# Linux kernel version: 2.6.15-rc1-mm2
# Fri Nov 18 13:11:32 2005
#
CONFIG_X86_64=y
CONFIG_64BIT=y
CONFIG_X86=y
CONFIG_SEMAPHORE_SLEEPERS=y
CONFIG_MMU=y
CONFIG_RWSEM_GENERIC_SPINLOCK=y
CONFIG_GENERIC_CALIBRATE_DELAY=y
CONFIG_X86_CMPXCHG=y
CONFIG_EARLY_PRINTK=y
CONFIG_GENERIC_ISA_DMA=y
CONFIG_GENERIC_IOMAP=y
CONFIG_ARCH_MAY_HAVE_PC_FDC=y

#
# Code maturity level options
#
CONFIG_EXPERIMENTAL=y
CONFIG_CLEAN_COMPILE=y
CONFIG_BROKEN_ON_SMP=y
CONFIG_LOCK_KERNEL=y
CONFIG_INIT_ENV_ARG_LIMIT=32

#
# General setup
#
CONFIG_LOCALVERSION=""
CONFIG_LOCALVERSION_AUTO=y
CONFIG_SWAP=y
CONFIG_SWAP_PREFETCH=y
CONFIG_SYSVIPC=y
CONFIG_POSIX_MQUEUE=y
CONFIG_BSD_PROCESS_ACCT=y
CONFIG_BSD_PROCESS_ACCT_V3=y
CONFIG_SYSCTL=y
CONFIG_AUDIT=y
CONFIG_AUDITSYSCALL=y
CONFIG_HOTPLUG=y
# CONFIG_IKCONFIG is not set
CONFIG_INITRAMFS_SOURCE=""
# CONFIG_EMBEDDED is not set
CONFIG_KALLSYMS=y
CONFIG_KALLSYMS_ALL=y
# CONFIG_KALLSYMS_EXTRA_PASS is not set
CONFIG_PRINTK=y
CONFIG_BUG=y
CONFIG_DOUBLEFAULT=y
CONFIG_ELF_CORE=y
CONFIG_BASE_FULL=y
CONFIG_FUTEX=y
CONFIG_EPOLL=y
CONFIG_SHMEM=y
CONFIG_CC_ALIGN_FUNCTIONS=0
CONFIG_CC_ALIGN_LABELS=0
CONFIG_CC_ALIGN_LOOPS=0
CONFIG_CC_ALIGN_JUMPS=0
CONFIG_SLAB=y
# CONFIG_INITRAMFS_SKIP is not set
CONFIG_SERIAL_PCI=y
# CONFIG_TINY_SHMEM is not set
CONFIG_BASE_SMALL=0
# CONFIG_SLOB is not set

#
# Loadable module support
#
CONFIG_MODULES=y
CONFIG_MODULE_UNLOAD=y
CONFIG_MODULE_FORCE_UNLOAD=y
CONFIG_OBSOLETE_MODPARM=y
CONFIG_MODVERSIONS=y
# CONFIG_MODULE_SRCVERSION_ALL is not set
CONFIG_KMOD=y

#
# Block layer
#
CONFIG_LBD=y
# CONFIG_BLK_DEV_IO_TRACE is not set

#
# IO Schedulers
#
CONFIG_IOSCHED_NOOP=y
CONFIG_IOSCHED_AS=y
CONFIG_IOSCHED_DEADLINE=y
CONFIG_IOSCHED_CFQ=y
CONFIG_DEFAULT_AS=y
# CONFIG_DEFAULT_DEADLINE is not set
# CONFIG_DEFAULT_CFQ is not set
# CONFIG_DEFAULT_NOOP is not set
CONFIG_DEFAULT_IOSCHED="anticipatory"

#
# Processor type and features
#
CONFIG_MK8=y
# CONFIG_MPSC is not set
# CONFIG_GENERIC_CPU is not set
CONFIG_X86_L1_CACHE_BYTES=64
CONFIG_X86_L1_CACHE_SHIFT=6
CONFIG_X86_TSC=y
CONFIG_X86_GOOD_APIC=y
CONFIG_MICROCODE=m
CONFIG_X86_MSR=m
CONFIG_X86_CPUID=m
CONFIG_X86_IO_APIC=y
CONFIG_X86_LOCAL_APIC=y
CONFIG_MTRR=y
# CONFIG_SMP is not set
# CONFIG_PREEMPT_NONE is not set
# CONFIG_PREEMPT_VOLUNTARY is not set
CONFIG_PREEMPT=y
CONFIG_PREEMPT_BKL=y
CONFIG_ARCH_FLATMEM_ENABLE=y
CONFIG_SELECT_MEMORY_MODEL=y
CONFIG_FLATMEM_MANUAL=y
# CONFIG_DISCONTIGMEM_MANUAL is not set
# CONFIG_SPARSEMEM_MANUAL is not set
CONFIG_FLATMEM=y
CONFIG_FLAT_NODE_MEM_MAP=y
# CONFIG_SPARSEMEM_STATIC is not set
CONFIG_SPLIT_PTLOCK_CPUS=4
CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID=y
CONFIG_HPET_TIMER=y
CONFIG_X86_PM_TIMER=y
CONFIG_HPET_EMULATE_RTC=y
CONFIG_GART_IOMMU=y
CONFIG_SWIOTLB=y
CONFIG_X86_MCE=y
# CONFIG_X86_MCE_INTEL is not set
CONFIG_X86_MCE_AMD=y
CONFIG_PHYSICAL_START=0x100000
# CONFIG_KEXEC is not set
CONFIG_SECCOMP=y
# CONFIG_HZ_100 is not set
CONFIG_HZ_250=y
# CONFIG_HZ_1000 is not set
CONFIG_HZ=250
CONFIG_GENERIC_HARDIRQS=y
CONFIG_GENERIC_IRQ_PROBE=y
CONFIG_ISA_DMA_API=y

#
# Power management options
#
CONFIG_PM=y
CONFIG_PM_LEGACY=y
CONFIG_PM_DEBUG=y
CONFIG_SOFTWARE_SUSPEND=y
CONFIG_PM_STD_PARTITION=""

#
# ACPI (Advanced Configuration and Power Interface) Support
#
CONFIG_ACPI=y
CONFIG_ACPI_SLEEP=y
CONFIG_ACPI_SLEEP_PROC_FS=y
# CONFIG_ACPI_SLEEP_PROC_SLEEP is not set
CONFIG_ACPI_AC=m
CONFIG_ACPI_BATTERY=m
CONFIG_ACPI_BUTTON=m
CONFIG_ACPI_VIDEO=m
CONFIG_ACPI_HOTKEY=m
CONFIG_ACPI_FAN=m
CONFIG_ACPI_PROCESSOR=m
CONFIG_ACPI_THERMAL=m
CONFIG_ACPI_ASUS=m
# CONFIG_ACPI_IBM is not set
# CONFIG_ACPI_TOSHIBA is not set
# CONFIG_ACPI_CUSTOM_DSDT is not set
CONFIG_ACPI_BLACKLIST_YEAR=0
# CONFIG_ACPI_DEBUG is not set
CONFIG_ACPI_EC=y
CONFIG_ACPI_POWER=y
CONFIG_ACPI_SYSTEM=y
CONFIG_ACPI_CONTAINER=m

#
# CPU Frequency scaling
#
CONFIG_CPU_FREQ=y
CONFIG_CPU_FREQ_TABLE=y
CONFIG_CPU_FREQ_DEBUG=y
CONFIG_CPU_FREQ_STAT=y
CONFIG_CPU_FREQ_STAT_DETAILS=y
CONFIG_CPU_FREQ_DEFAULT_GOV_PERFORMANCE=y
# CONFIG_CPU_FREQ_DEFAULT_GOV_USERSPACE is not set
CONFIG_CPU_FREQ_GOV_PERFORMANCE=y
CONFIG_CPU_FREQ_GOV_POWERSAVE=y
CONFIG_CPU_FREQ_GOV_USERSPACE=y
CONFIG_CPU_FREQ_GOV_ONDEMAND=y
CONFIG_CPU_FREQ_GOV_CONSERVATIVE=y

#
# CPUFreq processor drivers
#
CONFIG_X86_POWERNOW_K8=y
# CONFIG_X86_SPEEDSTEP_CENTRINO is not set
CONFIG_X86_ACPI_CPUFREQ=m

#
# shared options
#
# CONFIG_X86_ACPI_CPUFREQ_PROC_INTF is not set
# CONFIG_X86_SPEEDSTEP_LIB is not set

#
# Bus options (PCI etc.)
#
CONFIG_PCI=y
CONFIG_PCI_DIRECT=y
CONFIG_PCI_MMCONFIG=y
# CONFIG_UNORDERED_IO is not set
# CONFIG_PCIEPORTBUS is not set
# CONFIG_PCI_MSI is not set
CONFIG_PCI_LEGACY_PROC=y
# CONFIG_PCI_DEBUG is not set

#
# PCCARD (PCMCIA/CardBus) support
#
CONFIG_PCCARD=m
CONFIG_PCMCIA_DEBUG=y
CONFIG_PCMCIA=m
CONFIG_PCMCIA_LOAD_CIS=y
CONFIG_PCMCIA_IOCTL=y
CONFIG_CARDBUS=y

#
# PC-card bridges
#
CONFIG_YENTA=m
CONFIG_YENTA_O2=y
CONFIG_YENTA_RICOH=y
CONFIG_YENTA_TI=y
CONFIG_YENTA_ENE_TUNE=y
CONFIG_YENTA_TOSHIBA=y
# CONFIG_PD6729 is not set
CONFIG_I82092=m
CONFIG_PCCARD_NONSTATIC=m

#
# PCI Hotplug Support
#
CONFIG_HOTPLUG_PCI=m
CONFIG_HOTPLUG_PCI_FAKE=m
CONFIG_HOTPLUG_PCI_ACPI=m
# CONFIG_HOTPLUG_PCI_ACPI_IBM is not set
CONFIG_HOTPLUG_PCI_CPCI=y
CONFIG_HOTPLUG_PCI_CPCI_ZT5550=m
CONFIG_HOTPLUG_PCI_CPCI_GENERIC=m
# CONFIG_HOTPLUG_PCI_SHPC is not set

#
# Executable file formats / Emulations
#
CONFIG_BINFMT_ELF=y
CONFIG_BINFMT_MISC=m
CONFIG_IA32_EMULATION=y
CONFIG_IA32_AOUT=y
CONFIG_COMPAT=y
CONFIG_SYSVIPC_COMPAT=y

#
# Networking
#
CONFIG_NET=y

#
# Networking options
#
CONFIG_PACKET=m
CONFIG_PACKET_MMAP=y
CONFIG_UNIX=y
CONFIG_XFRM=y
CONFIG_XFRM_USER=m
CONFIG_NET_KEY=m
CONFIG_INET=y
CONFIG_IP_MULTICAST=y
CONFIG_IP_ADVANCED_ROUTER=y
CONFIG_ASK_IP_FIB_HASH=y
# CONFIG_IP_FIB_TRIE is not set
CONFIG_IP_FIB_HASH=y
CONFIG_IP_MULTIPLE_TABLES=y
CONFIG_IP_ROUTE_FWMARK=y
CONFIG_IP_ROUTE_MULTIPATH=y
# CONFIG_IP_ROUTE_MULTIPATH_CACHED is not set
CONFIG_IP_ROUTE_VERBOSE=y
# CONFIG_IP_PNP is not set
CONFIG_NET_IPIP=m
CONFIG_NET_IPGRE=m
CONFIG_NET_IPGRE_BROADCAST=y
# CONFIG_IP_MROUTE is not set
# CONFIG_ARPD is not set
CONFIG_SYN_COOKIES=y
CONFIG_INET_AH=m
CONFIG_INET_ESP=m
CONFIG_INET_IPCOMP=m
CONFIG_INET_TUNNEL=m
CONFIG_INET_DIAG=y
CONFIG_INET_TCP_DIAG=y
# CONFIG_TCP_CONG_ADVANCED is not set
CONFIG_TCP_CONG_BIC=y

#
# IP: Virtual Server Configuration
#
# CONFIG_IP_VS is not set
CONFIG_IPV6=m
CONFIG_IPV6_PRIVACY=y
CONFIG_INET6_AH=m
CONFIG_INET6_ESP=m
CONFIG_INET6_IPCOMP=m
CONFIG_INET6_TUNNEL=m
CONFIG_IPV6_TUNNEL=m
CONFIG_NETFILTER=y
CONFIG_NETFILTER_DEBUG=y
CONFIG_BRIDGE_NETFILTER=y

#
# Core Netfilter Configuration
#
# CONFIG_NETFILTER_NETLINK is not set

#
# IP: Netfilter Configuration
#
CONFIG_IP_NF_CONNTRACK=m
CONFIG_IP_NF_CT_ACCT=y
CONFIG_IP_NF_CONNTRACK_MARK=y
CONFIG_IP_NF_CONNTRACK_EVENTS=y
CONFIG_IP_NF_CT_PROTO_SCTP=m
CONFIG_IP_NF_FTP=m
CONFIG_IP_NF_IRC=m
# CONFIG_IP_NF_NETBIOS_NS is not set
CONFIG_IP_NF_TFTP=m
CONFIG_IP_NF_AMANDA=m
# CONFIG_IP_NF_PPTP is not set
CONFIG_IP_NF_QUEUE=m
CONFIG_IP_NF_IPTABLES=m
CONFIG_IP_NF_MATCH_LIMIT=m
CONFIG_IP_NF_MATCH_IPRANGE=m
CONFIG_IP_NF_MATCH_MAC=m
CONFIG_IP_NF_MATCH_PKTTYPE=m
CONFIG_IP_NF_MATCH_MARK=m
CONFIG_IP_NF_MATCH_MULTIPORT=m
CONFIG_IP_NF_MATCH_TOS=m
CONFIG_IP_NF_MATCH_RECENT=m
CONFIG_IP_NF_MATCH_ECN=m
CONFIG_IP_NF_MATCH_DSCP=m
CONFIG_IP_NF_MATCH_AH_ESP=m
CONFIG_IP_NF_MATCH_LENGTH=m
CONFIG_IP_NF_MATCH_TTL=m
CONFIG_IP_NF_MATCH_TCPMSS=m
CONFIG_IP_NF_MATCH_HELPER=m
CONFIG_IP_NF_MATCH_STATE=m
CONFIG_IP_NF_MATCH_CONNTRACK=m
CONFIG_IP_NF_MATCH_OWNER=m
CONFIG_IP_NF_MATCH_PHYSDEV=m
CONFIG_IP_NF_MATCH_ADDRTYPE=m
CONFIG_IP_NF_MATCH_REALM=m
CONFIG_IP_NF_MATCH_SCTP=m
# CONFIG_IP_NF_MATCH_DCCP is not set
CONFIG_IP_NF_MATCH_COMMENT=m
CONFIG_IP_NF_MATCH_CONNMARK=m
# CONFIG_IP_NF_MATCH_CONNBYTES is not set
CONFIG_IP_NF_MATCH_HASHLIMIT=m
# CONFIG_IP_NF_MATCH_STRING is not set
CONFIG_IP_NF_FILTER=m
CONFIG_IP_NF_TARGET_REJECT=m
CONFIG_IP_NF_TARGET_LOG=m
CONFIG_IP_NF_TARGET_ULOG=m
CONFIG_IP_NF_TARGET_TCPMSS=m
# CONFIG_IP_NF_TARGET_NFQUEUE is not set
CONFIG_IP_NF_NAT=m
CONFIG_IP_NF_NAT_NEEDED=y
CONFIG_IP_NF_TARGET_MASQUERADE=m
CONFIG_IP_NF_TARGET_REDIRECT=m
CONFIG_IP_NF_TARGET_NETMAP=m
CONFIG_IP_NF_TARGET_SAME=m
CONFIG_IP_NF_NAT_SNMP_BASIC=m
CONFIG_IP_NF_NAT_IRC=m
CONFIG_IP_NF_NAT_FTP=m
CONFIG_IP_NF_NAT_TFTP=m
CONFIG_IP_NF_NAT_AMANDA=m
CONFIG_IP_NF_MANGLE=m
CONFIG_IP_NF_TARGET_TOS=m
CONFIG_IP_NF_TARGET_ECN=m
CONFIG_IP_NF_TARGET_DSCP=m
CONFIG_IP_NF_TARGET_MARK=m
CONFIG_IP_NF_TARGET_CLASSIFY=m
# CONFIG_IP_NF_TARGET_TTL is not set
CONFIG_IP_NF_TARGET_CONNMARK=m
CONFIG_IP_NF_TARGET_CLUSTERIP=m
CONFIG_IP_NF_RAW=m
CONFIG_IP_NF_TARGET_NOTRACK=m
CONFIG_IP_NF_ARPTABLES=m
CONFIG_IP_NF_ARPFILTER=m
CONFIG_IP_NF_ARP_MANGLE=m

#
# IPv6: Netfilter Configuration (EXPERIMENTAL)
#
CONFIG_IP6_NF_QUEUE=m
CONFIG_IP6_NF_IPTABLES=m
CONFIG_IP6_NF_MATCH_LIMIT=m
CONFIG_IP6_NF_MATCH_MAC=m
CONFIG_IP6_NF_MATCH_RT=m
CONFIG_IP6_NF_MATCH_OPTS=m
CONFIG_IP6_NF_MATCH_FRAG=m
CONFIG_IP6_NF_MATCH_HL=m
CONFIG_IP6_NF_MATCH_MULTIPORT=m
CONFIG_IP6_NF_MATCH_OWNER=m
CONFIG_IP6_NF_MATCH_MARK=m
CONFIG_IP6_NF_MATCH_IPV6HEADER=m
CONFIG_IP6_NF_MATCH_AHESP=m
CONFIG_IP6_NF_MATCH_LENGTH=m
CONFIG_IP6_NF_MATCH_EUI64=m
CONFIG_IP6_NF_MATCH_PHYSDEV=m
CONFIG_IP6_NF_FILTER=m
CONFIG_IP6_NF_TARGET_LOG=m
# CONFIG_IP6_NF_TARGET_REJECT is not set
# CONFIG_IP6_NF_TARGET_NFQUEUE is not set
CONFIG_IP6_NF_MANGLE=m
CONFIG_IP6_NF_TARGET_MARK=m
# CONFIG_IP6_NF_TARGET_HL is not set
CONFIG_IP6_NF_RAW=m

#
# DECnet: Netfilter Configuration
#
# CONFIG_DECNET_NF_GRABULATOR is not set

#
# Bridge: Netfilter Configuration
#
CONFIG_BRIDGE_NF_EBTABLES=m
CONFIG_BRIDGE_EBT_BROUTE=m
CONFIG_BRIDGE_EBT_T_FILTER=m
CONFIG_BRIDGE_EBT_T_NAT=m
CONFIG_BRIDGE_EBT_802_3=m
CONFIG_BRIDGE_EBT_AMONG=m
CONFIG_BRIDGE_EBT_ARP=m
CONFIG_BRIDGE_EBT_IP=m
CONFIG_BRIDGE_EBT_LIMIT=m
CONFIG_BRIDGE_EBT_MARK=m
CONFIG_BRIDGE_EBT_PKTTYPE=m
CONFIG_BRIDGE_EBT_STP=m
CONFIG_BRIDGE_EBT_VLAN=m
CONFIG_BRIDGE_EBT_ARPREPLY=m
CONFIG_BRIDGE_EBT_DNAT=m
CONFIG_BRIDGE_EBT_MARK_T=m
CONFIG_BRIDGE_EBT_REDIRECT=m
CONFIG_BRIDGE_EBT_SNAT=m
CONFIG_BRIDGE_EBT_LOG=m
# CONFIG_BRIDGE_EBT_ULOG is not set

#
# DCCP Configuration (EXPERIMENTAL)
#
# CONFIG_IP_DCCP is not set

#
# SCTP Configuration (EXPERIMENTAL)
#
CONFIG_IP_SCTP=m
# CONFIG_SCTP_DBG_MSG is not set
# CONFIG_SCTP_DBG_OBJCNT is not set
# CONFIG_SCTP_HMAC_NONE is not set
# CONFIG_SCTP_HMAC_SHA1 is not set
CONFIG_SCTP_HMAC_MD5=y
# CONFIG_ATM is not set
CONFIG_BRIDGE=m
CONFIG_VLAN_8021Q=m
CONFIG_DECNET=m
# CONFIG_DECNET_ROUTER is not set
CONFIG_LLC=m
CONFIG_LLC2=m
CONFIG_IPX=m
CONFIG_IPX_INTERN=y
CONFIG_ATALK=m
CONFIG_DEV_APPLETALK=y
CONFIG_IPDDP=m
CONFIG_IPDDP_ENCAP=y
CONFIG_IPDDP_DECAP=y
CONFIG_X25=m
CONFIG_LAPB=m
# CONFIG_NET_DIVERT is not set
CONFIG_ECONET=m
# CONFIG_ECONET_AUNUDP is not set
# CONFIG_ECONET_NATIVE is not set
CONFIG_WAN_ROUTER=m

#
# QoS and/or fair queueing
#
CONFIG_NET_SCHED=y
CONFIG_NET_SCH_CLK_JIFFIES=y
# CONFIG_NET_SCH_CLK_GETTIMEOFDAY is not set
# CONFIG_NET_SCH_CLK_CPU is not set

#
# Queueing/Scheduling
#
CONFIG_NET_SCH_CBQ=m
CONFIG_NET_SCH_HTB=m
CONFIG_NET_SCH_HFSC=m
CONFIG_NET_SCH_PRIO=m
CONFIG_NET_SCH_RED=m
CONFIG_NET_SCH_SFQ=m
CONFIG_NET_SCH_TEQL=m
CONFIG_NET_SCH_TBF=m
CONFIG_NET_SCH_GRED=m
CONFIG_NET_SCH_DSMARK=m
# CONFIG_NET_SCH_NETEM is not set
CONFIG_NET_SCH_INGRESS=m

#
# Classification
#
CONFIG_NET_CLS=y
# CONFIG_NET_CLS_BASIC is not set
CONFIG_NET_CLS_TCINDEX=m
CONFIG_NET_CLS_ROUTE4=m
CONFIG_NET_CLS_ROUTE=y
CONFIG_NET_CLS_FW=m
CONFIG_NET_CLS_U32=m
# CONFIG_CLS_U32_PERF is not set
# CONFIG_CLS_U32_MARK is not set
CONFIG_NET_CLS_RSVP=m
CONFIG_NET_CLS_RSVP6=m
# CONFIG_NET_EMATCH is not set
# CONFIG_NET_CLS_ACT is not set
CONFIG_NET_CLS_POLICE=y
# CONFIG_NET_CLS_IND is not set
CONFIG_NET_ESTIMATOR=y

#
# Network testing
#
CONFIG_NET_PKTGEN=m
# CONFIG_HAMRADIO is not set
# CONFIG_IRDA is not set
# CONFIG_BT is not set
CONFIG_IEEE80211=m
CONFIG_IEEE80211_DEBUG=y
CONFIG_IEEE80211_CRYPT_WEP=m
CONFIG_IEEE80211_CRYPT_CCMP=m
CONFIG_IEEE80211_CRYPT_TKIP=m

#
# Device Drivers
#

#
# Generic Driver Options
#
# CONFIG_STANDALONE is not set
# CONFIG_PREVENT_FIRMWARE_BUILD is not set
CONFIG_FW_LOADER=m
# CONFIG_DEBUG_DRIVER is not set

#
# Connector - unified userspace <-> kernelspace linker
#
# CONFIG_CONNECTOR is not set

#
# Memory Technology Devices (MTD)
#
CONFIG_MTD=m
CONFIG_MTD_DEBUG=y
CONFIG_MTD_DEBUG_VERBOSE=0
CONFIG_MTD_CONCAT=m
CONFIG_MTD_PARTITIONS=y
CONFIG_MTD_REDBOOT_PARTS=m
CONFIG_MTD_REDBOOT_DIRECTORY_BLOCK=-1
# CONFIG_MTD_REDBOOT_PARTS_UNALLOCATED is not set
# CONFIG_MTD_REDBOOT_PARTS_READONLY is not set
CONFIG_MTD_CMDLINE_PARTS=y

#
# User Modules And Translation Layers
#
CONFIG_MTD_CHAR=m
CONFIG_MTD_BLOCK=m
CONFIG_MTD_BLOCK_RO=m
CONFIG_FTL=m
CONFIG_NFTL=m
CONFIG_NFTL_RW=y
CONFIG_INFTL=m
# CONFIG_RFD_FTL is not set

#
# RAM/ROM/Flash chip drivers
#
CONFIG_MTD_CFI=m
CONFIG_MTD_JEDECPROBE=m
CONFIG_MTD_GEN_PROBE=m
CONFIG_MTD_CFI_ADV_OPTIONS=y
CONFIG_MTD_CFI_NOSWAP=y
# CONFIG_MTD_CFI_BE_BYTE_SWAP is not set
# CONFIG_MTD_CFI_LE_BYTE_SWAP is not set
# CONFIG_MTD_CFI_GEOMETRY is not set
CONFIG_MTD_MAP_BANK_WIDTH_1=y
CONFIG_MTD_MAP_BANK_WIDTH_2=y
CONFIG_MTD_MAP_BANK_WIDTH_4=y
# CONFIG_MTD_MAP_BANK_WIDTH_8 is not set
# CONFIG_MTD_MAP_BANK_WIDTH_16 is not set
# CONFIG_MTD_MAP_BANK_WIDTH_32 is not set
CONFIG_MTD_CFI_I1=y
CONFIG_MTD_CFI_I2=y
# CONFIG_MTD_CFI_I4 is not set
# CONFIG_MTD_CFI_I8 is not set
# CONFIG_MTD_OTP is not set
CONFIG_MTD_CFI_INTELEXT=m
CONFIG_MTD_CFI_AMDSTD=m
CONFIG_MTD_CFI_AMDSTD_RETRY=0
CONFIG_MTD_CFI_STAA=m
CONFIG_MTD_CFI_UTIL=m
# CONFIG_MTD_RAM is not set
# CONFIG_MTD_ROM is not set
CONFIG_MTD_ABSENT=m

#
# Mapping drivers for chip access
#
CONFIG_MTD_COMPLEX_MAPPINGS=y
CONFIG_MTD_PHYSMAP=m
CONFIG_MTD_PHYSMAP_START=0x8000000
CONFIG_MTD_PHYSMAP_LEN=0x4000000
CONFIG_MTD_PHYSMAP_BANKWIDTH=2
# CONFIG_MTD_PNC2000 is not set
CONFIG_MTD_SC520CDP=m
# CONFIG_MTD_NETSC520 is not set
# CONFIG_MTD_TS5500 is not set
# CONFIG_MTD_SBC_GXX is not set
CONFIG_MTD_AMD76XROM=m
# CONFIG_MTD_ICHXROM is not set
CONFIG_MTD_SCB2_FLASH=m
# CONFIG_MTD_NETtel is not set
# CONFIG_MTD_DILNETPC is not set
CONFIG_MTD_L440GX=m
CONFIG_MTD_PCI=m
# CONFIG_MTD_PLATRAM is not set

#
# Self-contained MTD device drivers
#
CONFIG_MTD_PMC551=m
CONFIG_MTD_PMC551_BUGFIX=y
# CONFIG_MTD_PMC551_DEBUG is not set
CONFIG_MTD_SLRAM=m
# CONFIG_MTD_PHRAM is not set
CONFIG_MTD_MTDRAM=m
CONFIG_MTDRAM_TOTAL_SIZE=4096
CONFIG_MTDRAM_ERASE_SIZE=128
CONFIG_MTD_BLKMTD=m
# CONFIG_MTD_BLOCK2MTD is not set

#
# Disk-On-Chip Device Drivers
#
CONFIG_MTD_DOC2000=m
CONFIG_MTD_DOC2001=m
CONFIG_MTD_DOC2001PLUS=m
CONFIG_MTD_DOCPROBE=m
CONFIG_MTD_DOCECC=m
CONFIG_MTD_DOCPROBE_ADVANCED=y
CONFIG_MTD_DOCPROBE_ADDRESS=0x0000
CONFIG_MTD_DOCPROBE_HIGH=y
CONFIG_MTD_DOCPROBE_55AA=y

#
# NAND Flash Device Drivers
#
CONFIG_MTD_NAND=m
CONFIG_MTD_NAND_VERIFY_WRITE=y
CONFIG_MTD_NAND_IDS=m
CONFIG_MTD_NAND_DISKONCHIP=m
CONFIG_MTD_NAND_DISKONCHIP_PROBE_ADVANCED=y
CONFIG_MTD_NAND_DISKONCHIP_PROBE_ADDRESS=0x0
CONFIG_MTD_NAND_DISKONCHIP_PROBE_HIGH=y
CONFIG_MTD_NAND_DISKONCHIP_BBTWRITE=y
# CONFIG_MTD_NAND_NANDSIM is not set

#
# OneNAND Flash Device Drivers
#
# CONFIG_MTD_ONENAND is not set

#
# Parallel port support
#
CONFIG_PARPORT=m
CONFIG_PARPORT_PC=m
CONFIG_PARPORT_SERIAL=m
CONFIG_PARPORT_PC_FIFO=y
CONFIG_PARPORT_PC_SUPERIO=y
# CONFIG_PARPORT_PC_PCMCIA is not set
# CONFIG_PARPORT_GSC is not set
CONFIG_PARPORT_1284=y

#
# Plug and Play support
#
# CONFIG_PNP is not set

#
# Block devices
#
# CONFIG_BLK_DEV_FD is not set
# CONFIG_PARIDE is not set
# CONFIG_BLK_CPQ_DA is not set
# CONFIG_BLK_CPQ_CISS_DA is not set
# CONFIG_BLK_DEV_DAC960 is not set
# CONFIG_BLK_DEV_UMEM is not set
# CONFIG_BLK_DEV_COW_COMMON is not set
CONFIG_BLK_DEV_LOOP=y
CONFIG_BLK_DEV_CRYPTOLOOP=m
# CONFIG_BLK_DEV_NBD is not set
# CONFIG_BLK_DEV_SX8 is not set
# CONFIG_BLK_DEV_UB is not set
CONFIG_BLK_DEV_RAM=y
CONFIG_BLK_DEV_RAM_COUNT=16
CONFIG_BLK_DEV_RAM_SIZE=128000
CONFIG_BLK_DEV_INITRD=y
# CONFIG_CDROM_PKTCDVD is not set
CONFIG_ATA_OVER_ETH=m

#
# ATA/ATAPI/MFM/RLL support
#
CONFIG_IDE=y
CONFIG_BLK_DEV_IDE=y

#
# Please see Documentation/ide.txt for help/info on IDE drives
#
# CONFIG_BLK_DEV_IDE_SATA is not set
# CONFIG_BLK_DEV_HD_IDE is not set
CONFIG_BLK_DEV_IDEDISK=y
CONFIG_IDEDISK_MULTI_MODE=y
# CONFIG_BLK_DEV_IDECS is not set
CONFIG_BLK_DEV_IDECD=m
# CONFIG_BLK_DEV_IDETAPE is not set
# CONFIG_BLK_DEV_IDEFLOPPY is not set
CONFIG_BLK_DEV_IDESCSI=m
# CONFIG_IDE_TASK_IOCTL is not set

#
# IDE chipset support/bugfixes
#
CONFIG_IDE_GENERIC=y
# CONFIG_BLK_DEV_CMD640 is not set
CONFIG_BLK_DEV_IDEPCI=y
CONFIG_IDEPCI_SHARE_IRQ=y
CONFIG_BLK_DEV_OFFBOARD=y
CONFIG_BLK_DEV_GENERIC=y
# CONFIG_BLK_DEV_OPTI621 is not set
# CONFIG_BLK_DEV_RZ1000 is not set
CONFIG_BLK_DEV_IDEDMA_PCI=y
# CONFIG_BLK_DEV_IDEDMA_FORCED is not set
CONFIG_IDEDMA_PCI_AUTO=y
# CONFIG_IDEDMA_ONLYDISK is not set
# CONFIG_BLK_DEV_AEC62XX is not set
# CONFIG_BLK_DEV_ALI15X3 is not set
CONFIG_BLK_DEV_AMD74XX=y
# CONFIG_BLK_DEV_ATIIXP is not set
# CONFIG_BLK_DEV_CMD64X is not set
# CONFIG_BLK_DEV_TRIFLEX is not set
# CONFIG_BLK_DEV_CY82C693 is not set
# CONFIG_BLK_DEV_CS5520 is not set
# CONFIG_BLK_DEV_CS5530 is not set
# CONFIG_BLK_DEV_HPT34X is not set
# CONFIG_BLK_DEV_HPT366 is not set
# CONFIG_BLK_DEV_SC1200 is not set
# CONFIG_BLK_DEV_PIIX is not set
# CONFIG_BLK_DEV_IT821X is not set
# CONFIG_BLK_DEV_NS87415 is not set
# CONFIG_BLK_DEV_PDC202XX_OLD is not set
# CONFIG_BLK_DEV_PDC202XX_NEW is not set
# CONFIG_BLK_DEV_SVWKS is not set
# CONFIG_BLK_DEV_SIIMAGE is not set
# CONFIG_BLK_DEV_SIS5513 is not set
# CONFIG_BLK_DEV_SLC90E66 is not set
# CONFIG_BLK_DEV_TRM290 is not set
# CONFIG_BLK_DEV_VIA82CXXX is not set
# CONFIG_IDE_ARM is not set
CONFIG_BLK_DEV_IDEDMA=y
# CONFIG_IDEDMA_IVB is not set
CONFIG_IDEDMA_AUTO=y
# CONFIG_BLK_DEV_HD is not set

#
# SCSI device support
#
# CONFIG_RAID_ATTRS is not set
CONFIG_SCSI=m
CONFIG_SCSI_PROC_FS=y

#
# SCSI support type (disk, tape, CD-ROM)
#
CONFIG_BLK_DEV_SD=m
CONFIG_CHR_DEV_ST=m
CONFIG_CHR_DEV_OSST=m
CONFIG_BLK_DEV_SR=m
CONFIG_BLK_DEV_SR_VENDOR=y
CONFIG_CHR_DEV_SG=m
# CONFIG_CHR_DEV_SCH is not set

#
# Some SCSI devices (e.g. CD jukebox) support multiple LUNs
#
CONFIG_SCSI_MULTI_LUN=y
CONFIG_SCSI_CONSTANTS=y
CONFIG_SCSI_LOGGING=y

#
# SCSI Transport Attributes
#
CONFIG_SCSI_SPI_ATTRS=m
CONFIG_SCSI_FC_ATTRS=m
# CONFIG_SCSI_ISCSI_ATTRS is not set
# CONFIG_SCSI_SAS_ATTRS is not set

#
# SCSI Transport Layers
#
# CONFIG_SAS_CLASS is not set

#
# SCSI low-level drivers
#
# CONFIG_ISCSI_TCP is not set
# CONFIG_SCSI_ARCMSR is not set
# CONFIG_BLK_DEV_3W_XXXX_RAID is not set
# CONFIG_SCSI_3W_9XXX is not set
# CONFIG_SCSI_ACARD is not set
# CONFIG_SCSI_AACRAID is not set
# CONFIG_SCSI_AIC7XXX is not set
# CONFIG_SCSI_AIC7XXX_OLD is not set
# CONFIG_SCSI_AIC79XX is not set
# CONFIG_MEGARAID_NEWGEN is not set
# CONFIG_MEGARAID_LEGACY is not set
# CONFIG_MEGARAID_SAS is not set
# CONFIG_SCSI_SATA is not set
# CONFIG_SCSI_BUSLOGIC is not set
# CONFIG_SCSI_DMX3191D is not set
# CONFIG_SCSI_EATA is not set
# CONFIG_SCSI_FUTURE_DOMAIN is not set
# CONFIG_SCSI_GDTH is not set
# CONFIG_SCSI_IPS is not set
# CONFIG_SCSI_INITIO is not set
# CONFIG_SCSI_INIA100 is not set
# CONFIG_SCSI_PPA is not set
# CONFIG_SCSI_IMM is not set
# CONFIG_SCSI_SYM53C8XX_2 is not set
# CONFIG_SCSI_IPR is not set
# CONFIG_SCSI_QLOGIC_FC is not set
# CONFIG_SCSI_QLOGIC_1280 is not set
CONFIG_SCSI_QLA2XXX=m
# CONFIG_SCSI_QLA21XX is not set
# CONFIG_SCSI_QLA22XX is not set
# CONFIG_SCSI_QLA2300 is not set
# CONFIG_SCSI_QLA2322 is not set
# CONFIG_SCSI_QLA6312 is not set
# CONFIG_SCSI_QLA24XX is not set
# CONFIG_SCSI_LPFC is not set
# CONFIG_SCSI_DC395x is not set
# CONFIG_SCSI_DC390T is not set
CONFIG_SCSI_DEBUG=m

#
# PCMCIA SCSI adapter support
#
# CONFIG_PCMCIA_FDOMAIN is not set
# CONFIG_PCMCIA_QLOGIC is not set
# CONFIG_PCMCIA_SYM53C500 is not set

#
# Multi-device support (RAID and LVM)
#
CONFIG_MD=y
# CONFIG_BLK_DEV_MD is not set
CONFIG_BLK_DEV_DM=m
CONFIG_DM_CRYPT=m
CONFIG_DM_SNAPSHOT=m
CONFIG_DM_MIRROR=m
CONFIG_DM_ZERO=m
# CONFIG_DM_MULTIPATH is not set

#
# Fusion MPT device support
#
# CONFIG_FUSION is not set
# CONFIG_FUSION_SPI is not set
# CONFIG_FUSION_FC is not set
# CONFIG_FUSION_SAS is not set

#
# IEEE 1394 (FireWire) support
#
CONFIG_IEEE1394=m

#
# Subsystem Options
#
# CONFIG_IEEE1394_VERBOSEDEBUG is not set
CONFIG_IEEE1394_OUI_DB=y
CONFIG_IEEE1394_EXTRA_CONFIG_ROMS=y
CONFIG_IEEE1394_CONFIG_ROM_IP1394=y
# CONFIG_IEEE1394_EXPORT_FULL_API is not set

#
# Device Drivers
#
CONFIG_IEEE1394_PCILYNX=m
CONFIG_IEEE1394_OHCI1394=m

#
# Protocol Drivers
#
CONFIG_IEEE1394_VIDEO1394=m
CONFIG_IEEE1394_SBP2=m
CONFIG_IEEE1394_SBP2_PHYS_DMA=y
CONFIG_IEEE1394_ETH1394=m
CONFIG_IEEE1394_DV1394=m
CONFIG_IEEE1394_RAWIO=m
CONFIG_IEEE1394_CMP=m
CONFIG_IEEE1394_AMDTP=m

#
# I2O device support
#
# CONFIG_I2O is not set

#
# Network device support
#
CONFIG_NETDEVICES=y
CONFIG_DUMMY=m
CONFIG_BONDING=m
CONFIG_EQUALIZER=m
CONFIG_TUN=m

#
# ARCnet devices
#
# CONFIG_ARCNET is not set

#
# PHY device support
#
# CONFIG_PHYLIB is not set

#
# Ethernet (10 or 100Mbit)
#
CONFIG_NET_ETHERNET=y
CONFIG_MII=m
# CONFIG_HAPPYMEAL is not set
# CONFIG_SUNGEM is not set
# CONFIG_CASSINI is not set
# CONFIG_NET_VENDOR_3COM is not set

#
# Tulip family network device support
#
# CONFIG_NET_TULIP is not set
# CONFIG_HP100 is not set
CONFIG_NET_PCI=y
# CONFIG_PCNET32 is not set
# CONFIG_AMD8111_ETH is not set
# CONFIG_ADAPTEC_STARFIRE is not set
# CONFIG_B44 is not set
# CONFIG_FORCEDETH is not set
# CONFIG_DGRS is not set
# CONFIG_EEPRO100 is not set
# CONFIG_E100 is not set
# CONFIG_FEALNX is not set
# CONFIG_NATSEMI is not set
# CONFIG_NE2K_PCI is not set
# CONFIG_8139CP is not set
CONFIG_8139TOO=m
CONFIG_8139TOO_PIO=y
# CONFIG_8139TOO_TUNE_TWISTER is not set
# CONFIG_8139TOO_8129 is not set
# CONFIG_8139_OLD_RX_RESET is not set
# CONFIG_SIS900 is not set
# CONFIG_EPIC100 is not set
# CONFIG_SUNDANCE is not set
# CONFIG_VIA_RHINE is not set
# CONFIG_NET_POCKET is not set

#
# Ethernet (1000 Mbit)
#
# CONFIG_ACENIC is not set
# CONFIG_DL2K is not set
# CONFIG_E1000 is not set
# CONFIG_NS83820 is not set
# CONFIG_HAMACHI is not set
# CONFIG_YELLOWFIN is not set
# CONFIG_R8169 is not set
# CONFIG_SIS190 is not set
# CONFIG_SKGE is not set
# CONFIG_SKY2 is not set
CONFIG_SK98LIN=m
# CONFIG_VIA_VELOCITY is not set
# CONFIG_TIGON3 is not set
# CONFIG_BNX2 is not set

#
# Ethernet (10000 Mbit)
#
# CONFIG_CHELSIO_T1 is not set
# CONFIG_IXGB is not set
# CONFIG_S2IO is not set

#
# Token Ring devices
#
# CONFIG_TR is not set

#
# Wireless LAN (non-hamradio)
#
CONFIG_NET_RADIO=y

#
# Obsolete Wireless cards support (pre-802.11)
#
# CONFIG_STRIP is not set
# CONFIG_PCMCIA_WAVELAN is not set
# CONFIG_PCMCIA_NETWAVE is not set

#
# Wireless 802.11 Frequency Hopping cards support
#
# CONFIG_PCMCIA_RAYCS is not set

#
# Wireless 802.11b ISA/PCI cards support
#
# CONFIG_IPW2100 is not set
# CONFIG_IPW2200 is not set
# CONFIG_AIRO is not set
CONFIG_HERMES=m
CONFIG_PLX_HERMES=m
CONFIG_TMD_HERMES=m
# CONFIG_NORTEL_HERMES is not set
CONFIG_PCI_HERMES=m
CONFIG_ATMEL=m
CONFIG_PCI_ATMEL=m

#
# Wireless 802.11b Pcmcia/Cardbus cards support
#
# CONFIG_PCMCIA_HERMES is not set
# CONFIG_PCMCIA_SPECTRUM is not set
# CONFIG_AIRO_CS is not set
# CONFIG_PCMCIA_ATMEL is not set
# CONFIG_PCMCIA_WL3501 is not set

#
# Prism GT/Duette 802.11(a/b/g) PCI/Cardbus support
#
CONFIG_PRISM54=m
# CONFIG_HOSTAP is not set
CONFIG_ACX=m
CONFIG_ACX_PCI=y
CONFIG_ACX_USB=y
CONFIG_NET_WIRELESS=y

#
# PCMCIA network device support
#
# CONFIG_NET_PCMCIA is not set

#
# Wan interfaces
#
# CONFIG_WAN is not set
# CONFIG_FDDI is not set
# CONFIG_HIPPI is not set
# CONFIG_PLIP is not set
CONFIG_PPP=m
CONFIG_PPP_MULTILINK=y
CONFIG_PPP_FILTER=y
CONFIG_PPP_ASYNC=m
CONFIG_PPP_SYNC_TTY=m
CONFIG_PPP_DEFLATE=m
CONFIG_PPP_BSDCOMP=m
# CONFIG_PPP_MPPE is not set
CONFIG_PPPOE=m
# CONFIG_SLIP is not set
# CONFIG_NET_FC is not set
CONFIG_SHAPER=m
CONFIG_NETCONSOLE=m
# CONFIG_KGDBOE is not set
CONFIG_NETPOLL=y
# CONFIG_NETPOLL_RX is not set
# CONFIG_NETPOLL_TRAP is not set
CONFIG_NET_POLL_CONTROLLER=y

#
# ISDN subsystem
#
# CONFIG_ISDN is not set

#
# Telephony Support
#
# CONFIG_PHONE is not set

#
# Input device support
#
CONFIG_INPUT=y

#
# Userland interfaces
#
CONFIG_INPUT_MOUSEDEV=y
CONFIG_INPUT_MOUSEDEV_PSAUX=y
CONFIG_INPUT_MOUSEDEV_SCREEN_X=1024
CONFIG_INPUT_MOUSEDEV_SCREEN_Y=768
CONFIG_INPUT_JOYDEV=m
CONFIG_INPUT_TSDEV=m
CONFIG_INPUT_TSDEV_SCREEN_X=240
CONFIG_INPUT_TSDEV_SCREEN_Y=320
CONFIG_INPUT_EVDEV=m
# CONFIG_INPUT_EVBUG is not set

#
# Input Device Drivers
#
CONFIG_INPUT_KEYBOARD=y
CONFIG_KEYBOARD_ATKBD=y
CONFIG_KEYBOARD_SUNKBD=m
# CONFIG_KEYBOARD_LKKBD is not set
CONFIG_KEYBOARD_XTKBD=m
CONFIG_KEYBOARD_NEWTON=m
CONFIG_INPUT_MOUSE=y
CONFIG_MOUSE_PS2=y
CONFIG_MOUSE_SERIAL=m
# CONFIG_MOUSE_VSXXXAA is not set
# CONFIG_INPUT_JOYSTICK is not set
# CONFIG_INPUT_TOUCHSCREEN is not set
CONFIG_INPUT_MISC=y
CONFIG_INPUT_PCSPKR=y
CONFIG_INPUT_UINPUT=m

#
# Hardware I/O ports
#
CONFIG_SERIO=y
CONFIG_SERIO_I8042=y
CONFIG_SERIO_SERPORT=m
CONFIG_SERIO_CT82C710=m
CONFIG_SERIO_PARKBD=m
CONFIG_SERIO_PCIPS2=m
CONFIG_SERIO_LIBPS2=y
# CONFIG_SERIO_RAW is not set
CONFIG_GAMEPORT=m
CONFIG_GAMEPORT_NS558=m
CONFIG_GAMEPORT_L4=m
CONFIG_GAMEPORT_EMU10K1=m
CONFIG_GAMEPORT_FM801=m

#
# Character devices
#
CONFIG_VT=y
CONFIG_VT_CONSOLE=y
CONFIG_HW_CONSOLE=y
CONFIG_SERIAL_NONSTANDARD=y
# CONFIG_COMPUTONE is not set
# CONFIG_ROCKETPORT is not set
# CONFIG_CYCLADES is not set
# CONFIG_DIGIEPCA is not set
# CONFIG_MOXA_INTELLIO is not set
# CONFIG_MOXA_SMARTIO is not set
# CONFIG_ISI is not set
# CONFIG_SYNCLINK is not set
# CONFIG_SYNCLINKMP is not set
# CONFIG_SYNCLINK_GT is not set
CONFIG_N_HDLC=m
# CONFIG_RISCOM8 is not set
# CONFIG_SPECIALIX is not set
# CONFIG_SX is not set
# CONFIG_RIO is not set
# CONFIG_STALDRV is not set

#
# Serial drivers
#
CONFIG_SERIAL_8250=y
CONFIG_SERIAL_8250_CONSOLE=y
# CONFIG_SERIAL_8250_CS is not set
CONFIG_SERIAL_8250_ACPI=y
CONFIG_SERIAL_8250_NR_UARTS=4
CONFIG_SERIAL_8250_EXTENDED=y
# CONFIG_SERIAL_8250_MANY_PORTS is not set
CONFIG_SERIAL_8250_SHARE_IRQ=y
# CONFIG_SERIAL_8250_DETECT_IRQ is not set
# CONFIG_SERIAL_8250_RSA is not set

#
# Non-8250 serial port support
#
CONFIG_SERIAL_CORE=y
CONFIG_SERIAL_CORE_CONSOLE=y
# CONFIG_SERIAL_JSM is not set
CONFIG_UNIX98_PTYS=y
CONFIG_LEGACY_PTYS=y
CONFIG_LEGACY_PTY_COUNT=256
CONFIG_PRINTER=m
# CONFIG_LP_CONSOLE is not set
CONFIG_PPDEV=m
CONFIG_TIPAR=m

#
# IPMI
#
CONFIG_IPMI_HANDLER=m
CONFIG_IPMI_PANIC_EVENT=y
CONFIG_IPMI_PANIC_STRING=y
CONFIG_IPMI_DEVICE_INTERFACE=m
CONFIG_IPMI_SI=m
CONFIG_IPMI_WATCHDOG=m
# CONFIG_IPMI_POWEROFF is not set

#
# Watchdog Cards
#
# CONFIG_WATCHDOG is not set
CONFIG_HW_RANDOM=m
CONFIG_NVRAM=m
CONFIG_RTC=y
# CONFIG_DTLK is not set
# CONFIG_R3964 is not set
# CONFIG_APPLICOM is not set

#
# Ftape, the floppy tape device driver
#
# CONFIG_FTAPE is not set
CONFIG_AGP=y
CONFIG_AGP_AMD64=y
# CONFIG_AGP_INTEL is not set
# CONFIG_DRM is not set

#
# PCMCIA character devices
#
# CONFIG_SYNCLINK_CS is not set
# CONFIG_CARDMAN_4000 is not set
# CONFIG_CARDMAN_4040 is not set
# CONFIG_MWAVE is not set
CONFIG_RAW_DRIVER=m
CONFIG_HPET=y
# CONFIG_HPET_RTC_IRQ is not set
CONFIG_HPET_MMAP=y
CONFIG_MAX_RAW_DEVS=4096
CONFIG_HANGCHECK_TIMER=m

#
# TPM devices
#
# CONFIG_TCG_TPM is not set
# CONFIG_TELCLOCK is not set

#
# I2C support
#
CONFIG_I2C=m
CONFIG_I2C_CHARDEV=m

#
# I2C Algorithms
#
CONFIG_I2C_ALGOBIT=m
CONFIG_I2C_ALGOPCF=m
# CONFIG_I2C_ALGOPCA is not set

#
# I2C Hardware Bus support
#
CONFIG_I2C_ALI1535=m
# CONFIG_I2C_ALI1563 is not set
CONFIG_I2C_ALI15X3=m
CONFIG_I2C_AMD756=m
# CONFIG_I2C_AMD756_S4882 is not set
CONFIG_I2C_AMD8111=m
CONFIG_I2C_I801=m
CONFIG_I2C_I810=m
# CONFIG_I2C_PIIX4 is not set
CONFIG_I2C_ISA=m
CONFIG_I2C_NFORCE2=m
CONFIG_I2C_PARPORT=m
CONFIG_I2C_PARPORT_LIGHT=m
CONFIG_I2C_PROSAVAGE=m
CONFIG_I2C_SAVAGE4=m
CONFIG_SCx200_ACB=m
CONFIG_I2C_SIS5595=m
CONFIG_I2C_SIS630=m
CONFIG_I2C_SIS96X=m
# CONFIG_I2C_STUB is not set
CONFIG_I2C_VIA=m
CONFIG_I2C_VIAPRO=m
CONFIG_I2C_VOODOO3=m
# CONFIG_I2C_PCA_ISA is not set

#
# Miscellaneous I2C Chip support
#
# CONFIG_SENSORS_DS1337 is not set
# CONFIG_SENSORS_DS1374 is not set
CONFIG_SENSORS_EEPROM=m
# CONFIG_SENSORS_PCF8574 is not set
# CONFIG_SENSORS_PCA9539 is not set
# CONFIG_SENSORS_PCF8591 is not set
# CONFIG_SENSORS_RTC8564 is not set
# CONFIG_SENSORS_MAX6875 is not set
# CONFIG_RTC_X1205_I2C is not set
CONFIG_I2C_DEBUG_CORE=y
CONFIG_I2C_DEBUG_ALGO=y
CONFIG_I2C_DEBUG_BUS=y
CONFIG_I2C_DEBUG_CHIP=y

#
# Dallas's 1-wire bus
#
# CONFIG_W1 is not set

#
# Hardware Monitoring support
#
CONFIG_HWMON=y
CONFIG_HWMON_VID=m
CONFIG_SENSORS_ADM1021=m
# CONFIG_SENSORS_ADM1025 is not set
# CONFIG_SENSORS_ADM1026 is not set
# CONFIG_SENSORS_ADM1031 is not set
# CONFIG_SENSORS_ADM9240 is not set
CONFIG_SENSORS_ASB100=m
# CONFIG_SENSORS_ATXP1 is not set
CONFIG_SENSORS_DS1621=m
CONFIG_SENSORS_FSCHER=m
# CONFIG_SENSORS_FSCPOS is not set
CONFIG_SENSORS_GL518SM=m
# CONFIG_SENSORS_GL520SM is not set
CONFIG_SENSORS_IT87=m
# CONFIG_SENSORS_LM63 is not set
CONFIG_SENSORS_LM75=m
# CONFIG_SENSORS_LM77 is not set
CONFIG_SENSORS_LM78=m
CONFIG_SENSORS_LM80=m
CONFIG_SENSORS_LM83=m
CONFIG_SENSORS_LM85=m
# CONFIG_SENSORS_LM87 is not set
CONFIG_SENSORS_LM90=m
# CONFIG_SENSORS_LM92 is not set
# CONFIG_SENSORS_MAX1619 is not set
# CONFIG_SENSORS_PC87360 is not set
# CONFIG_SENSORS_SIS5595 is not set
# CONFIG_SENSORS_SMSC47M1 is not set
# CONFIG_SENSORS_SMSC47B397 is not set
CONFIG_SENSORS_VIA686A=m
CONFIG_SENSORS_W83781D=m
# CONFIG_SENSORS_W83792D is not set
CONFIG_SENSORS_W83L785TS=m
CONFIG_SENSORS_W83627HF=m
# CONFIG_SENSORS_W83627EHF is not set
# CONFIG_SENSORS_HDAPS is not set
# CONFIG_HWMON_DEBUG_CHIP is not set

#
# Misc devices
#
# CONFIG_IBM_ASM is not set

#
# Multimedia Capabilities Port drivers
#

#
# Multimedia devices
#
# CONFIG_VIDEO_DEV is not set

#
# Digital Video Broadcasting Devices
#
# CONFIG_DVB is not set

#
# Graphics support
#
CONFIG_FB=y
CONFIG_FB_CFB_FILLRECT=y
CONFIG_FB_CFB_COPYAREA=y
CONFIG_FB_CFB_IMAGEBLIT=y
# CONFIG_FB_MACMODES is not set
CONFIG_FB_MODE_HELPERS=y
# CONFIG_FB_TILEBLITTING is not set
# CONFIG_FB_CIRRUS is not set
# CONFIG_FB_PM2 is not set
# CONFIG_FB_CYBER2000 is not set
# CONFIG_FB_ARC is not set
# CONFIG_FB_ASILIANT is not set
# CONFIG_FB_IMSTT is not set
# CONFIG_FB_VGA16 is not set
CONFIG_FB_VESA=y
CONFIG_VIDEO_SELECT=y
# CONFIG_FB_HGA is not set
# CONFIG_FB_S1D13XXX is not set
# CONFIG_FB_NVIDIA is not set
# CONFIG_FB_RIVA is not set
# CONFIG_FB_MATROX is not set
# CONFIG_FB_RADEON_OLD is not set
# CONFIG_FB_RADEON is not set
# CONFIG_FB_ATY128 is not set
# CONFIG_FB_ATY is not set
# CONFIG_FB_SAVAGE is not set
# CONFIG_FB_SIS is not set
# CONFIG_FB_NEOMAGIC is not set
# CONFIG_FB_KYRO is not set
# CONFIG_FB_3DFX is not set
# CONFIG_FB_VOODOO1 is not set
# CONFIG_FB_CYBLA is not set
# CONFIG_FB_TRIDENT is not set
# CONFIG_FB_GEODE is not set
# CONFIG_FB_VIRTUAL is not set

#
# Console display driver support
#
CONFIG_VGA_CONSOLE=y
CONFIG_DUMMY_CONSOLE=y
CONFIG_FRAMEBUFFER_CONSOLE=y
# CONFIG_FRAMEBUFFER_CONSOLE_ROTATION is not set
CONFIG_FONTS=y
CONFIG_FONT_8x8=y
CONFIG_FONT_8x16=y
# CONFIG_FONT_6x11 is not set
# CONFIG_FONT_7x14 is not set
# CONFIG_FONT_PEARL_8x8 is not set
# CONFIG_FONT_ACORN_8x8 is not set
# CONFIG_FONT_MINI_4x6 is not set
# CONFIG_FONT_SUN8x16 is not set
# CONFIG_FONT_SUN12x22 is not set
# CONFIG_FONT_10x18 is not set

#
# Logo configuration
#
CONFIG_LOGO=y
# CONFIG_LOGO_LINUX_MONO is not set
# CONFIG_LOGO_LINUX_VGA16 is not set
CONFIG_LOGO_LINUX_CLUT224=y
# CONFIG_BACKLIGHT_LCD_SUPPORT is not set

#
# Speakup console speech
#
# CONFIG_SPEAKUP is not set

#
# Sound
#
CONFIG_SOUND=m

#
# Advanced Linux Sound Architecture
#
CONFIG_SND=m
CONFIG_SND_AC97_CODEC=m
CONFIG_SND_AC97_BUS=m
CONFIG_SND_TIMER=m
CONFIG_SND_PCM=m
CONFIG_SND_HWDEP=m
CONFIG_SND_RAWMIDI=m
CONFIG_SND_SEQUENCER=m
CONFIG_SND_SEQ_DUMMY=m
CONFIG_SND_OSSEMUL=y
CONFIG_SND_MIXER_OSS=m
CONFIG_SND_PCM_OSS=m
CONFIG_SND_SEQUENCER_OSS=y
CONFIG_SND_RTCTIMER=m
CONFIG_SND_SEQ_RTCTIMER_DEFAULT=y
CONFIG_SND_VERBOSE_PRINTK=y
CONFIG_SND_DEBUG=y
CONFIG_SND_DEBUG_DETECT=y
CONFIG_SND_GENERIC_DRIVER=y

#
# Generic devices
#
CONFIG_SND_MPU401_UART=m
CONFIG_SND_DUMMY=m
CONFIG_SND_VIRMIDI=m
CONFIG_SND_MTPAV=m
CONFIG_SND_SERIAL_U16550=m
CONFIG_SND_MPU401=m

#
# PCI devices
#
# CONFIG_SND_ALI5451 is not set
# CONFIG_SND_ATIIXP is not set
# CONFIG_SND_ATIIXP_MODEM is not set
# CONFIG_SND_AU8810 is not set
# CONFIG_SND_AU8820 is not set
# CONFIG_SND_AU8830 is not set
# CONFIG_SND_AZT3328 is not set
# CONFIG_SND_BT87X is not set
# CONFIG_SND_CS46XX is not set
# CONFIG_SND_CS4281 is not set
# CONFIG_SND_EMU10K1 is not set
# CONFIG_SND_EMU10K1X is not set
# CONFIG_SND_CA0106 is not set
# CONFIG_SND_KORG1212 is not set
# CONFIG_SND_MIXART is not set
# CONFIG_SND_NM256 is not set
# CONFIG_SND_RME32 is not set
# CONFIG_SND_RME96 is not set
# CONFIG_SND_RME9652 is not set
# CONFIG_SND_HDSP is not set
# CONFIG_SND_HDSPM is not set
# CONFIG_SND_TRIDENT is not set
# CONFIG_SND_YMFPCI is not set
# CONFIG_SND_AD1889 is not set
# CONFIG_SND_ALS4000 is not set
# CONFIG_SND_CMIPCI is not set
# CONFIG_SND_ENS1370 is not set
# CONFIG_SND_ENS1371 is not set
# CONFIG_SND_ES1938 is not set
# CONFIG_SND_ES1968 is not set
# CONFIG_SND_MAESTRO3 is not set
# CONFIG_SND_FM801 is not set
# CONFIG_SND_ICE1712 is not set
# CONFIG_SND_ICE1724 is not set
CONFIG_SND_INTEL8X0=m
CONFIG_SND_INTEL8X0M=m
# CONFIG_SND_SONICVIBES is not set
# CONFIG_SND_VIA82XX is not set
# CONFIG_SND_VIA82XX_MODEM is not set
# CONFIG_SND_VX222 is not set
# CONFIG_SND_HDA_INTEL is not set

#
# USB devices
#
CONFIG_SND_USB_AUDIO=m
# CONFIG_SND_USB_USX2Y is not set

#
# PCMCIA devices
#

#
# Open Sound System
#
# CONFIG_SOUND_PRIME is not set

#
# USB support
#
CONFIG_USB_ARCH_HAS_HCD=y
CONFIG_USB_ARCH_HAS_OHCI=y
CONFIG_USB=y
CONFIG_USB_DEBUG=y

#
# Miscellaneous USB options
#
CONFIG_USB_DEVICEFS=y
CONFIG_USB_BANDWIDTH=y
CONFIG_USB_DYNAMIC_MINORS=y
# CONFIG_USB_SUSPEND is not set
# CONFIG_USB_OTG is not set

#
# USB Host Controller Drivers
#
CONFIG_USB_EHCI_HCD=m
CONFIG_USB_EHCI_SPLIT_ISO=y
# CONFIG_USB_EHCI_ROOT_HUB_TT is not set
# CONFIG_USB_ISP116X_HCD is not set
CONFIG_USB_OHCI_HCD=m
# CONFIG_USB_OHCI_BIG_ENDIAN is not set
CONFIG_USB_OHCI_LITTLE_ENDIAN=y
# CONFIG_USB_UHCI_HCD is not set
# CONFIG_USB_SL811_HCD is not set

#
# USB Device Class drivers
#
CONFIG_USB_ACM=m
CONFIG_USB_PRINTER=m

#
# NOTE: USB_STORAGE enables SCSI, and 'SCSI disk support'
#

#
# may also be needed; see USB_STORAGE Help for more information
#
CONFIG_USB_STORAGE=m
# CONFIG_USB_STORAGE_DEBUG is not set
CONFIG_USB_STORAGE_DATAFAB=y
CONFIG_USB_STORAGE_FREECOM=y
CONFIG_USB_STORAGE_ISD200=y
CONFIG_USB_STORAGE_DPCM=y
CONFIG_USB_STORAGE_USBAT=y
CONFIG_USB_STORAGE_SDDR09=y
CONFIG_USB_STORAGE_SDDR55=y
CONFIG_USB_STORAGE_JUMPSHOT=y
# CONFIG_USB_LIBUSUAL is not set

#
# USB Input Devices
#
CONFIG_USB_HID=m
CONFIG_USB_HIDINPUT=y
CONFIG_HID_FF=y
CONFIG_HID_PID=y
CONFIG_LOGITECH_FF=y
CONFIG_THRUSTMASTER_FF=y
CONFIG_USB_HIDDEV=y

#
# USB HID Boot Protocol drivers
#
# CONFIG_USB_KBD is not set
# CONFIG_USB_MOUSE is not set
# CONFIG_USB_AIPTEK is not set
# CONFIG_USB_WACOM is not set
# CONFIG_USB_ACECAD is not set
# CONFIG_USB_KBTAB is not set
# CONFIG_USB_POWERMATE is not set
# CONFIG_USB_MTOUCH is not set
# CONFIG_USB_ITMTOUCH is not set
# CONFIG_USB_EGALAX is not set
# CONFIG_USB_YEALINK is not set
# CONFIG_USB_XPAD is not set
# CONFIG_USB_ATI_REMOTE is not set
# CONFIG_USB_KEYSPAN_REMOTE is not set
# CONFIG_USB_APPLETOUCH is not set

#
# USB Imaging devices
#
# CONFIG_USB_MDC800 is not set
# CONFIG_USB_MICROTEK is not set

#
# USB Multimedia devices
#
# CONFIG_USB_DABUSB is not set

#
# Video4Linux support is needed for USB Multimedia device support
#

#
# USB Network Adapters
#
# CONFIG_USB_CATC is not set
# CONFIG_USB_KAWETH is not set
# CONFIG_USB_PEGASUS is not set
# CONFIG_USB_RTL8150 is not set
# CONFIG_USB_USBNET is not set
# CONFIG_USB_ZD1201 is not set
CONFIG_USB_MON=y

#
# USB port drivers
#
# CONFIG_USB_USS720 is not set

#
# USB Serial Converter support
#
CONFIG_USB_SERIAL=m
CONFIG_USB_SERIAL_GENERIC=y
# CONFIG_USB_SERIAL_AIRPRIME is not set
# CONFIG_USB_SERIAL_ANYDATA is not set
# CONFIG_USB_SERIAL_BELKIN is not set
# CONFIG_USB_SERIAL_WHITEHEAT is not set
# CONFIG_USB_SERIAL_DIGI_ACCELEPORT is not set
# CONFIG_USB_SERIAL_CP2101 is not set
# CONFIG_USB_SERIAL_CYPRESS_M8 is not set
# CONFIG_USB_SERIAL_EMPEG is not set
# CONFIG_USB_SERIAL_FTDI_SIO is not set
# CONFIG_USB_SERIAL_VISOR is not set
# CONFIG_USB_SERIAL_IPAQ is not set
# CONFIG_USB_SERIAL_IR is not set
# CONFIG_USB_SERIAL_EDGEPORT is not set
# CONFIG_USB_SERIAL_EDGEPORT_TI is not set
# CONFIG_USB_SERIAL_GARMIN is not set
# CONFIG_USB_SERIAL_IPW is not set
# CONFIG_USB_SERIAL_KEYSPAN_PDA is not set
# CONFIG_USB_SERIAL_KEYSPAN is not set
# CONFIG_USB_SERIAL_KLSI is not set
# CONFIG_USB_SERIAL_KOBIL_SCT is not set
# CONFIG_USB_SERIAL_MCT_U232 is not set
CONFIG_USB_SERIAL_PL2303=m
# CONFIG_USB_SERIAL_HP4X is not set
# CONFIG_USB_SERIAL_SAFE is not set
# CONFIG_USB_SERIAL_TI is not set
# CONFIG_USB_SERIAL_CYBERJACK is not set
# CONFIG_USB_SERIAL_XIRCOM is not set
# CONFIG_USB_SERIAL_OPTION is not set
# CONFIG_USB_SERIAL_OMNINET is not set

#
# USB Miscellaneous drivers
#
# CONFIG_USB_EMI62 is not set
# CONFIG_USB_EMI26 is not set
# CONFIG_USB_AUERSWALD is not set
# CONFIG_USB_RIO500 is not set
# CONFIG_USB_LEGOTOWER is not set
# CONFIG_USB_LCD is not set
# CONFIG_USB_LED is not set
# CONFIG_USB_CYTHERM is not set
# CONFIG_USB_GOTEMP is not set
# CONFIG_USB_PHIDGETKIT is not set
# CONFIG_USB_PHIDGETSERVO is not set
# CONFIG_USB_IDMOUSE is not set
# CONFIG_USB_SISUSBVGA is not set
# CONFIG_USB_LD is not set
CONFIG_USB_TEST=m

#
# USB DSL modem support
#

#
# USB Gadget Support
#
# CONFIG_USB_GADGET is not set

#
# MMC/SD Card support
#
# CONFIG_MMC is not set

#
# InfiniBand support
#
# CONFIG_INFINIBAND is not set

#
# SN Devices
#

#
# EDAC - error detection and reporting (RAS)
#
# CONFIG_EDAC is not set

#
# Distributed Lock Manager
#
# CONFIG_DLM is not set

#
# Firmware Drivers
#
# CONFIG_EDD is not set
CONFIG_DELL_RBU=m
CONFIG_DCDBAS=m

#
# File systems
#
CONFIG_EXT2_FS=y
CONFIG_EXT2_FS_XATTR=y
CONFIG_EXT2_FS_POSIX_ACL=y
CONFIG_EXT2_FS_SECURITY=y
# CONFIG_EXT2_FS_XIP is not set
CONFIG_EXT3_FS=y
CONFIG_EXT3_FS_XATTR=y
CONFIG_EXT3_FS_POSIX_ACL=y
CONFIG_EXT3_FS_SECURITY=y
CONFIG_JBD=y
CONFIG_JBD_DEBUG=y
CONFIG_FS_MBCACHE=y
# CONFIG_REISER4_FS is not set
CONFIG_REISERFS_FS=y
# CONFIG_REISERFS_CHECK is not set
CONFIG_REISERFS_PROC_INFO=y
CONFIG_REISERFS_FS_XATTR=y
CONFIG_REISERFS_FS_POSIX_ACL=y
CONFIG_REISERFS_FS_SECURITY=y
# CONFIG_JFS_FS is not set
CONFIG_FS_POSIX_ACL=y
# CONFIG_XFS_FS is not set
# CONFIG_OCFS2_FS is not set
# CONFIG_MINIX_FS is not set
# CONFIG_ROMFS_FS is not set
CONFIG_INOTIFY=y
CONFIG_QUOTA=y
CONFIG_QFMT_V1=m
CONFIG_QFMT_V2=m
CONFIG_QUOTACTL=y
CONFIG_DNOTIFY=y
CONFIG_AUTOFS_FS=m
CONFIG_AUTOFS4_FS=m
# CONFIG_FUSE_FS is not set

#
# CD-ROM/DVD Filesystems
#
CONFIG_ISO9660_FS=m
CONFIG_JOLIET=y
CONFIG_ZISOFS=y
CONFIG_ZISOFS_FS=m
CONFIG_UDF_FS=m
CONFIG_UDF_NLS=y

#
# DOS/FAT/NT Filesystems
#
CONFIG_FAT_FS=m
CONFIG_MSDOS_FS=m
CONFIG_VFAT_FS=m
CONFIG_FAT_DEFAULT_CODEPAGE=437
CONFIG_FAT_DEFAULT_IOCHARSET="iso8859-1"
CONFIG_NTFS_FS=m
CONFIG_NTFS_DEBUG=y
CONFIG_NTFS_RW=y

#
# Pseudo filesystems
#
CONFIG_PROC_FS=y
CONFIG_PROC_KCORE=y
CONFIG_SYSFS=y
CONFIG_TMPFS=y
CONFIG_HUGETLBFS=y
CONFIG_HUGETLB_PAGE=y
CONFIG_RAMFS=y
# CONFIG_RELAYFS_FS is not set
# CONFIG_CONFIGFS_FS is not set

#
# Miscellaneous filesystems
#
# CONFIG_ADFS_FS is not set
# CONFIG_AFFS_FS is not set
# CONFIG_ASFS_FS is not set
# CONFIG_HFS_FS is not set
# CONFIG_HFSPLUS_FS is not set
# CONFIG_BEFS_FS is not set
# CONFIG_BFS_FS is not set
# CONFIG_EFS_FS is not set
# CONFIG_JFFS_FS is not set
# CONFIG_JFFS2_FS is not set
# CONFIG_CRAMFS is not set
# CONFIG_VXFS_FS is not set
# CONFIG_HPFS_FS is not set
# CONFIG_QNX4FS_FS is not set
# CONFIG_SYSV_FS is not set
# CONFIG_UFS_FS is not set

#
# Network File Systems
#
CONFIG_NFS_FS=m
CONFIG_NFS_V3=y
# CONFIG_NFS_V3_ACL is not set
CONFIG_NFS_V4=y
# CONFIG_NFS_DIRECTIO is not set
CONFIG_NFSD=m
CONFIG_NFSD_V3=y
# CONFIG_NFSD_V3_ACL is not set
CONFIG_NFSD_V4=y
CONFIG_NFSD_TCP=y
CONFIG_LOCKD=m
CONFIG_LOCKD_V4=y
CONFIG_EXPORTFS=m
CONFIG_NFS_COMMON=y
CONFIG_SUNRPC=m
CONFIG_SUNRPC_GSS=m
CONFIG_RPCSEC_GSS_KRB5=m
CONFIG_RPCSEC_GSS_SPKM3=m
CONFIG_SMB_FS=m
CONFIG_SMB_NLS_DEFAULT=y
CONFIG_SMB_NLS_REMOTE="cp852"
CONFIG_CIFS=m
CONFIG_CIFS_STATS=y
# CONFIG_CIFS_STATS2 is not set
CONFIG_CIFS_XATTR=y
CONFIG_CIFS_POSIX=y
# CONFIG_CIFS_EXPERIMENTAL is not set
CONFIG_NCP_FS=m
CONFIG_NCPFS_PACKET_SIGNING=y
CONFIG_NCPFS_IOCTL_LOCKING=y
CONFIG_NCPFS_STRONG=y
CONFIG_NCPFS_NFS_NS=y
CONFIG_NCPFS_OS2_NS=y
CONFIG_NCPFS_SMALLDOS=y
CONFIG_NCPFS_NLS=y
CONFIG_NCPFS_EXTRAS=y
# CONFIG_CODA_FS is not set
# CONFIG_AFS_FS is not set
# CONFIG_9P_FS is not set

#
# Partition Types
#
# CONFIG_PARTITION_ADVANCED is not set
CONFIG_MSDOS_PARTITION=y

#
# Native Language Support
#
CONFIG_NLS=y
CONFIG_NLS_DEFAULT="iso8859-2"
CONFIG_NLS_CODEPAGE_437=m
CONFIG_NLS_CODEPAGE_737=m
CONFIG_NLS_CODEPAGE_775=m
CONFIG_NLS_CODEPAGE_850=m
CONFIG_NLS_CODEPAGE_852=m
CONFIG_NLS_CODEPAGE_855=m
CONFIG_NLS_CODEPAGE_857=m
CONFIG_NLS_CODEPAGE_860=m
CONFIG_NLS_CODEPAGE_861=m
CONFIG_NLS_CODEPAGE_862=m
CONFIG_NLS_CODEPAGE_863=m
CONFIG_NLS_CODEPAGE_864=m
CONFIG_NLS_CODEPAGE_865=m
CONFIG_NLS_CODEPAGE_866=m
CONFIG_NLS_CODEPAGE_869=m
CONFIG_NLS_CODEPAGE_936=m
CONFIG_NLS_CODEPAGE_950=m
CONFIG_NLS_CODEPAGE_932=m
CONFIG_NLS_CODEPAGE_949=m
CONFIG_NLS_CODEPAGE_874=m
CONFIG_NLS_ISO8859_8=m
CONFIG_NLS_CODEPAGE_1250=m
CONFIG_NLS_CODEPAGE_1251=m
# CONFIG_NLS_ASCII is not set
CONFIG_NLS_ISO8859_1=m
CONFIG_NLS_ISO8859_2=m
CONFIG_NLS_ISO8859_3=m
CONFIG_NLS_ISO8859_4=m
CONFIG_NLS_ISO8859_5=m
CONFIG_NLS_ISO8859_6=m
CONFIG_NLS_ISO8859_7=m
CONFIG_NLS_ISO8859_9=m
CONFIG_NLS_ISO8859_13=m
CONFIG_NLS_ISO8859_14=m
CONFIG_NLS_ISO8859_15=m
CONFIG_NLS_KOI8_R=m
CONFIG_NLS_KOI8_U=m
CONFIG_NLS_UTF8=m

#
# Instrumentation Support
#
CONFIG_PROFILING=y
CONFIG_OPROFILE=y
# CONFIG_KPROBES is not set

#
# Kernel hacking
#
# CONFIG_PRINTK_TIME is not set
CONFIG_DEBUG_KERNEL=y
CONFIG_MAGIC_SYSRQ=y
CONFIG_LOG_BUF_SHIFT=18
CONFIG_DETECT_SOFTLOCKUP=y
CONFIG_SCHEDSTATS=y
CONFIG_DEBUG_SLAB=y
CONFIG_DEBUG_PREEMPT=y
CONFIG_DEBUG_SPINLOCK=y
# CONFIG_DEBUG_SPINLOCK_SLEEP is not set
# CONFIG_DEBUG_KOBJECT is not set
# CONFIG_DEBUG_INFO is not set
# CONFIG_PAGE_OWNER is not set
# CONFIG_DEBUG_FS is not set
CONFIG_DEBUG_VM=y
CONFIG_FRAME_POINTER=y
# CONFIG_RCU_TORTURE_TEST is not set
CONFIG_INIT_DEBUG=y
# CONFIG_DEBUG_RODATA is not set
# CONFIG_IOMMU_DEBUG is not set
# CONFIG_KGDB is not set

#
# Security options
#
# CONFIG_KEYS is not set
CONFIG_SECURITY=y
CONFIG_SECURITY_NETWORK=y
CONFIG_SECURITY_CAPABILITIES=y
CONFIG_SECURITY_ROOTPLUG=m
CONFIG_SECURITY_SECLVL=m
CONFIG_SECURITY_SELINUX=y
CONFIG_SECURITY_SELINUX_BOOTPARAM=y
CONFIG_SECURITY_SELINUX_BOOTPARAM_VALUE=1
CONFIG_SECURITY_SELINUX_DISABLE=y
CONFIG_SECURITY_SELINUX_DEVELOP=y
CONFIG_SECURITY_SELINUX_AVC_STATS=y
CONFIG_SECURITY_SELINUX_CHECKREQPROT_VALUE=1

#
# Cryptographic options
#
CONFIG_CRYPTO=y
CONFIG_CRYPTO_HMAC=y
CONFIG_CRYPTO_NULL=m
CONFIG_CRYPTO_MD4=m
CONFIG_CRYPTO_MD5=y
CONFIG_CRYPTO_SHA1=m
CONFIG_CRYPTO_SHA256=m
CONFIG_CRYPTO_SHA512=m
CONFIG_CRYPTO_WP512=m
CONFIG_CRYPTO_TGR192=m
CONFIG_CRYPTO_DES=y
CONFIG_CRYPTO_BLOWFISH=m
CONFIG_CRYPTO_TWOFISH=m
CONFIG_CRYPTO_SERPENT=m
CONFIG_CRYPTO_AES=m
CONFIG_CRYPTO_AES_X86_64=m
CONFIG_CRYPTO_CAST5=m
CONFIG_CRYPTO_CAST6=m
CONFIG_CRYPTO_TEA=m
CONFIG_CRYPTO_ARC4=m
CONFIG_CRYPTO_KHAZAD=m
CONFIG_CRYPTO_ANUBIS=m
CONFIG_CRYPTO_DEFLATE=m
CONFIG_CRYPTO_MICHAEL_MIC=m
CONFIG_CRYPTO_CRC32C=m
CONFIG_CRYPTO_TEST=m

#
# Hardware crypto devices
#

#
# Library routines
#
CONFIG_CRC_CCITT=m
# CONFIG_CRC16 is not set
CONFIG_CRC32=y
CONFIG_LIBCRC32C=m
CONFIG_ZLIB_INFLATE=m
CONFIG_ZLIB_DEFLATE=m
CONFIG_REED_SOLOMON=m
CONFIG_REED_SOLOMON_DEC16=y

Re: 2.6.15-rc1-mm2

[Mauro Carvalho Chehab]

Em Qui, 2005-11-17 às 23:46 -0800, Andrew Morton escreveu:
> ftp://ftp.kernel.org/pub/linux/kernel/people/akpm/patches/2.6/2.6.15-rc1/2.6.15-rc1-mm2/
> 
> 
> - I'm releasing this so that Hugh's MM rework can get a spin.
> 
>   Anyone who had post-2.6.14 problems related to the VM_RESERVED changes
>   (device drivers malfunctioning, obscure userspace hardware-poking
>   applications stopped working, etc) please test.
> 
>   We'd especially like testing of the graphics DRM drivers across as many
>   card types as poss.
	Also V4L users should test. We had lots of complain or malfunctioning
on x32 and non-functioning on x64 archtectures that seems to be related
to VM_RESERVED.
> 

Cheers, 
Mauro.

Re: 2.6.15-rc1-mm2

[Wu Fengguang]

Hi,

This patch should fix a link error:

arch/i386/kernel/built-in.o: In function `parse_cmdline_early':
: undefined reference to `elfcorehdr_addr'
arch/i386/kernel/built-in.o: In function `parse_cmdline_early':
: undefined reference to `elfcorehdr_addr'

Regards,
Wu
---

 arch/i386/kernel/setup.c   |    2 +-
 arch/x86_64/kernel/setup.c |    2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

--- linux-2.6.15-rc1-mm2.orig/arch/i386/kernel/setup.c
+++ linux-2.6.15-rc1-mm2/arch/i386/kernel/setup.c
@@ -898,7 +898,7 @@ static void __init parse_cmdline_early (
 			}
 		}
 #endif
-#ifdef CONFIG_CRASH_DUMP
+#ifdef CONFIG_PROC_VMCORE
 		/* elfcorehdr= specifies the location of elf core header
 		 * stored by the crashed kernel.
 		 */
--- linux-2.6.15-rc1-mm2.orig/arch/x86_64/kernel/setup.c
+++ linux-2.6.15-rc1-mm2/arch/x86_64/kernel/setup.c
@@ -418,7 +418,7 @@ static __init void parse_cmdline_early (
 		}
 #endif
 
-#ifdef CONFIG_CRASH_DUMP
+#ifdef CONFIG_PROC_VMCORE
 		/* elfcorehdr= specifies the location of elf core header
 		 * stored by the crashed kernel. This option will be passed
 		 * by kexec loader to the capture kernel.

Re: 2.6.15-rc1-mm2

[Andy Whitcroft]

Andrew Morton wrote:

> - cifs is busted when built as a module.  Mysteriously.

Don't know if this is related, but it appears that there is a problem
linking it static.  Specifically when you enable CONFIG_CIFS but not
CONFIG_CIFS_XATTR.  It seems that get_sfu_uid_mode() uses
CIFSSMBQueryEA() which is only available when CIFS_XATTR is defined.
Oddly the error seems to be reported against the function which follows:

  fs/built-in.o(.text+0x131520): In function `.cifs_get_inode_info':
  : undefined reference to `.CIFSSMBQueryEA'
  make: *** [.tmp_vmlinux1] Error 1

-apw

Re: 2.6.15-rc1-mm2

[Michael Krufky]

Andrew Morton wrote:

>ftp://ftp.kernel.org/pub/linux/kernel/people/akpm/patches/2.6/2.6.15-rc1/2.6.15-rc1-mm2/
>
>
>- I'm releasing this so that Hugh's MM rework can get a spin.
>
>  Anyone who had post-2.6.14 problems related to the VM_RESERVED changes
>  (device drivers malfunctioning, obscure userspace hardware-poking
>  applications stopped working, etc) please test.
>
I gave it a quick test before leaving the house this morning... Here is 
an exerp from an oops I got after closing mplayer, watching an ATSC (dvb 
in USA) stream, using AverTVHD a180 (saa7134 + nxt200x).

[snip]

Bad page state at free_hot_cold_page (in process 'mplayer', page c15c03e0)
flags:0x80000414 mapping:00000000 mapcount:0 count:0
Backtrace:
 [<c0103b53>] dump_stack+0x16/0x1a
 [<c0134db9>] bad_page+0x5f/0xe9
 [<c0135519>] free_hot_cold_page+0x58/0xf7
 [<c01355c2>] free_hot_page+0xa/0xc
 [<c0138367>] __page_cache_release+0xab/0xb0
 [<c0137fe0>] put_page+0x5c/0x5e
 [<c01428d7>] free_page_and_swap_cache+0x2c/0x32
 [<c013bd02>] zap_pte_range+0x1b1/0x249
 [<c013be5f>] unmap_page_range+0xc5/0xd6
 [<c013bf10>] unmap_vmas+0xa0/0x171
 [<c013f73c>] unmap_region+0x76/0xf2
 [<c013f9c8>] do_munmap+0xdd/0x100
 [<c013fa25>] sys_munmap+0x3a/0x56
 [<c0102d05>] syscall_call+0x7/0xb
---------------------------
| preempt count: 00000002 ]
| 2 level deep critical section nesting:
----------------------------------------
.. [<c013bf92>] .... unmap_vmas+0x122/0x171
.....[<c013f73c>] ..   ( <= unmap_region+0x76/0xf2)
.. [<c013bb89>] .... zap_pte_range+0x38/0x249
.....[<c013be5f>] ..   ( <= unmap_page_range+0xc5/0xd6)

Hexdump:
000: 04 04 00 80 ff ff ff ff ff ff ff ff 00 00 00 00
010: 00 00 00 00 00 00 00 00 b8 03 5c c1 b8 03 5c c1
020: 04 04 00 80 ff ff ff ff ff ff ff ff 00 00 00 00
030: 00 00 00 00 00 00 00 00 d8 03 5c c1 d8 03 5c c1
040: 14 04 00 80 ff ff ff ff ff ff ff ff 00 00 00 00
050: 00 00 00 00 00 00 00 00 f8 03 5c c1 f8 03 5c c1
060: 00 04 00 80 00 00 00 00 ff ff ff ff 00 00 00 00
070: 00 00 00 00 00 00 00 00 00 01 10 00 00 02 20 00
080: 00 04 00 80 ff ff ff ff ff ff ff ff 00 00 00 00
090: 00 00 00 00 00 00 00 00 38 04 5c c1 38 04 5c c1
0a0: 00 04 00 80 ff ff ff ff ff ff ff ff 00 00 00 00
0b0: 00 00 00 00 00 00 00 00 58 04 5c c1 58 04 5c c1
Trying to fix it up, but a reboot is needed

[snip]

More detailed log at:
http://techsounds.org/v4l/2.6.15-rc1-mm2-error.log

The oops spammed the entire log, so if you need to see what I have 
running on my system, here is a working dmesg (only v4l+dvb parts) from 
2.6.14 + hybrid (v4l+dvb) merged cvs, almost equivalent code to what we 
have in the current kernel:
http://techsounds.orgdotorg.org/v4l/dmesg.txt

I understand that you might need some more info.... Email me if you need 
something else... I'll be around for the next 5 hours.... After that, I 
will be away for the weekend, and I can do more tests on Monday 
evening.  This was on an intel p4, 2.53 GHz, 533 FSB, 768 MB ram, using 
Intel D845PEBT2 motherboard.

-Michael Krufky


-- 
Michael Krufky

Re: 2.6.15-rc1-mm2

[Michal Piotrowski]

Hi,

On 18/11/05, Andrew Morton <akpm@osdl.org> wrote:
>
> ftp://ftp.kernel.org/pub/linux/kernel/people/akpm/patches/2.6/2.6.15-rc1/2.6.15-rc1-mm2/
>

It looks similar to Rafael J. Wysocki report. It's full reproductible
and appears when playing mp3's in totem.

debian:/home/michal# cat /var/log/kern.log | grep -c "Bad page state
at free_hot_cold_page"
90

[1.] One line summary of the problem:
Bad page state at free_hot_cold_page

[4.] Kernel version (from /proc/version):
Linux version 2.6.15-rc1-mm2 (michal@debian) (gcc version 4.1.0
20051112 (experimental)) #10 SMP PREEMPT Fri Nov 18 23:40:46 CET 2005

[5.] Output of Oops
Nov 19 16:14:55 localhost kernel: Bad page state at free_hot_cold_page
(in process 'totem', page c1f52278)
Nov 19 16:14:55 localhost kernel: flags:0x80000414 mapping:00000000
mapcount:0 count:0
Nov 19 16:14:55 localhost kernel: Backtrace:
Nov 19 16:14:55 localhost kernel:  [<c0103b7c>] dump_stack+0x17/0x19
Nov 19 16:14:55 localhost kernel:  [<c01428a7>] bad_page+0x8c/0x12f
Nov 19 16:14:55 localhost kernel:  [<c01431ef>] free_hot_cold_page+0x4a/0x130
Nov 19 16:14:55 localhost kernel:  [<c0143a4c>] __pagevec_free+0x2c/0x3e
Nov 19 16:14:55 localhost kernel:  [<c0146a2d>] release_pages+0xf1/0x183
Nov 19 16:14:55 localhost kernel:  [<c0152b1b>]
free_pages_and_swap_cache+0x7d/0x98
Nov 19 16:14:55 localhost kernel:  [<c014b425>] unmap_vmas+0x196/0x20b
Nov 19 16:14:55 localhost kernel:  [<c014f245>] unmap_region+0xa2/0x134
Nov 19 16:14:55 localhost kernel:  [<c014f50b>] do_munmap+0xcb/0x102
Nov 19 16:14:55 localhost kernel:  [<c014f592>] sys_munmap+0x50/0x6a
Nov 19 16:14:55 localhost kernel:  [<c0102c67>] sysenter_past_esp+0x54/0x75
Nov 19 16:14:55 localhost kernel: ---------------------------
Nov 19 16:14:55 localhost kernel: | preempt count: 00000001 ]
Nov 19 16:14:55 localhost kernel: | 1 level deep critical section nesting:
Nov 19 16:14:55 localhost kernel: ----------------------------------------
Nov 19 16:14:55 localhost kernel: .. [<c014f1d7>] .... unmap_region+0x34/0x134
Nov 19 16:14:55 localhost kernel: .....[<c014f50b>] ..   ( <=
do_munmap+0xcb/0x102)
Nov 19 16:14:55 localhost kernel:
Nov 19 16:14:55 localhost kernel: Hexdump:
Nov 19 16:14:55 localhost kernel: 000: ff ff ff ff 00 00 00 00 00 00
00 00 00 00 00 00
Nov 19 16:14:55 localhost kernel: 010: 48 22 f5 c1 48 22 f5 c1 ff ff
ff ff 00 00 00 00
Nov 19 16:14:55 localhost kernel: 020: 00 00 00 00 00 00 00 00 00 00
00 00 00 00 00 00
Nov 19 16:14:55 localhost kernel: 030: 00 00 00 00 00 00 00 00 00 00
00 00 00 00 00 00
Nov 19 16:14:55 localhost kernel: 040: 14 04 00 80 ff ff ff ff ff ff
ff ff 00 00 00 00
Nov 19 16:14:55 localhost kernel: 050: 00 00 00 00 00 00 00 00 90 22
f5 c1 90 22 f5 c1
Nov 19 16:14:55 localhost kernel: 060: ff ff ff ff 00 00 00 00 00 00
00 00 00 00 00 00
Nov 19 16:14:56 localhost kernel: 070: 00 00 00 00 00 00 00 00 00 00
00 00 00 00 00 00
Nov 19 16:14:56 localhost kernel: 080: 00 00 00 00 00 00 00 00 00 04
00 80 00 00 00 00
Nov 19 16:14:56 localhost kernel: 090: 00 00 00 00 00 00 00 00 00 00
00 00 00 00 00 00
Nov 19 16:14:56 localhost kernel: 0a0: d8 22 f5 c1 d8 22 f5 c1 ff ff
ff ff 00 00 00 00
Nov 19 16:14:56 localhost kernel: 0b0: 00 00 00 00 00 00 00 00 00 00
00 00 00 00 00 00
Nov 19 16:14:56 localhost kernel: Trying to fix it up, but a reboot is needed

[7.] Environment

[7.1.] Software
If some fields are empty or look unusual you may have an old version.
Compare to the current minimal requirements in Documentation/Changes.

Linux debian 2.6.15-rc1-mm2 #10 SMP PREEMPT Fri Nov 18 23:40:46 CET
2005 i686 GNU/Linux

Gnu C                  4.0.3
Gnu make               3.80
binutils               2.16.91
util-linux             2.12p
mount                  2.12p
module-init-tools      3.2-pre9
e2fsprogs              1.38
jfsutils               1.1.8
reiserfsprogs          3.6.19
reiser4progs           1.0.5
xfsprogs               2.7.7
Linux C Library        2.3.5
Dynamic linker (ldd)   2.3.5
Procps                 3.2.6
Net-tools              1.60
Console-tools          0.2.3
Sh-utils               5.93
udev                   074
Modules Loaded         binfmt_misc ipv6 ipt_limit ipt_LOG ipt_REJECT
ip_conntrack_ftp ipt_state ip_conntrack iptable_filter ip_tables
af_packet ide_generic ide_cd cdrom ide_disk generic snd_intel8x0
snd_ac97_codec snd_ac97_bus snd_pcm_oss snd_mixer_oss psmouse snd_pcm
snd_timer parport_pc sk98lin snd 8250_pnp 8250 serial_core parport
piix ehci_hcd rtc uhci_hcd soundcore snd_page_alloc ide_core usbcore
hw_random intel_agp agpgart unix

[7.3.] Module information
binfmt_misc 9480 1 - Live 0xfd967000
ipv6 226240 15 - Live 0xfd99f000
ipt_limit 2432 8 - Live 0xfd95e000
ipt_LOG 6528 8 - Live 0xfd95b000
ipt_REJECT 4736 1 - Live 0xfd958000
ip_conntrack_ftp 6256 0 - Live 0xfd93d000
ipt_state 2048 6 - Live 0xf98b3000
ip_conntrack 40984 2 ip_conntrack_ftp,ipt_state, Live 0xfd94c000
iptable_filter 2688 1 - Live 0xf98b1000
ip_tables 20736 5
ipt_limit,ipt_LOG,ipt_REJECT,ipt_state,iptable_filter, Live 0xfd945000
af_packet 13832 2 - Live 0xfd96e000
ide_generic 1536 0 [permanent], Live 0xf8835000
ide_cd 34948 0 - Live 0xfd933000
cdrom 34848 1 ide_cd, Live 0xfd929000
ide_disk 14336 0 - Live 0xfd924000
generic 4612 0 [permanent], Live 0xf98ec000
snd_intel8x0 27676 0 - Live 0xf98f6000
snd_ac97_codec 85408 1 snd_intel8x0, Live 0xfd90e000
snd_ac97_bus 2432 1 snd_ac97_codec, Live 0xf8878000
snd_pcm_oss 45216 0 - Live 0xfd901000
snd_mixer_oss 16000 1 snd_pcm_oss, Live 0xf98e7000
psmouse 37284 0 - Live 0xfd994000
snd_pcm 75524 3 snd_intel8x0,snd_ac97_codec,snd_pcm_oss, Live 0xf98d3000
snd_timer 20996 1 snd_pcm, Live 0xf98cc000
parport_pc 22212 0 - Live 0xf98b5000
sk98lin 157024 0 - Live 0xfdb1f000
snd 46820 6 snd_intel8x0,snd_ac97_codec,snd_pcm_oss,snd_mixer_oss,snd_pcm,snd_timer,
Live 0xf98a4000
8250_pnp 8832 0 - Live 0xf98c8000
8250 24484 1 8250_pnp, Live 0xf989d000
serial_core 17792 1 8250, Live 0xf98c2000
parport 21568 1 parport_pc, Live 0xf98ef000
piix 9348 0 [permanent], Live 0xf887a000
ehci_hcd 27528 0 - Live 0xf8870000
rtc 10420 0 - Live 0xf8837000
uhci_hcd 29456 0 - Live 0xf885d000
soundcore 8160 1 snd, Live 0xf8804000
snd_page_alloc 8584 2 snd_intel8x0,snd_pcm, Live 0xf8831000
ide_core 108964 5 ide_generic,ide_cd,ide_disk,generic,piix, Live 0xf9881000
usbcore 109188 3 ehci_hcd,uhci_hcd, Live 0xf8841000
hw_random 4756 0 - Live 0xf881a000
intel_agp 19356 1 - Live 0xf883b000
agpgart 27868 1 intel_agp, Live 0xf880d000
unix 24080 228 - Live 0xf8869000

[7.4.] Loaded driver and hardware information
0000-001f : dma1
0020-0021 : pic1
0040-0043 : timer0
0050-0053 : timer1
0060-006f : keyboard
0070-0077 : rtc
0080-008f : dma page reg
00a0-00a1 : pic2
00c0-00df : dma2
00f0-00ff : fpu
0170-0177 : ide1
01f0-01f7 : ide0
0290-0297 : pnp 00:0a
02f8-02ff : serial
0376-0376 : ide1
0378-037a : parport0
03c0-03df : vga+
03f6-03f6 : ide0
03f8-03ff : serial
0400-041f : 0000:00:1f.3
0480-04bf : 0000:00:1f.0
0680-06ff : pnp 00:0a
0800-087f : 0000:00:1f.0
  0800-0803 : PM1a_EVT_BLK
  0804-0805 : PM1a_CNT_BLK
  0808-080b : PM_TMR
  0828-082f : GPE0_BLK
0cf8-0cff : PCI conf1
c400-c40f : 0000:00:1f.2
  c400-c40f : libata
c480-c483 : 0000:00:1f.2
  c480-c483 : libata
c800-c807 : 0000:00:1f.2
  c800-c807 : libata
c880-c883 : 0000:00:1f.2
  c880-c883 : libata
cc00-cc07 : 0000:00:1f.2
  cc00-cc07 : libata
d000-d0ff : 0000:00:1f.5
  d000-d0ff : Intel ICH5
d400-d43f : 0000:00:1f.5
  d400-d43f : Intel ICH5
d480-d49f : 0000:00:1d.0
  d480-d49f : uhci_hcd
d800-d81f : 0000:00:1d.1
  d800-d81f : uhci_hcd
d880-d89f : 0000:00:1d.2
  d880-d89f : uhci_hcd
dc00-dc1f : 0000:00:1d.3
  dc00-dc1f : uhci_hcd
e000-efff : PCI Bus #02
  e800-e8ff : 0000:02:05.0
    e800-e8ff : SysKonnect SK-98xx
fc00-fc0f : 0000:00:1f.1
  fc00-fc07 : ide0
  fc08-fc0f : ide1
00000000-0009fbff : System RAM
  00000000-00000000 : Crash kernel
0009fc00-0009ffff : reserved
000a0000-000bffff : Video RAM area
000c0000-000cf3ff : Video ROM
000f0000-000fffff : System ROM
00100000-3ff2ffff : System RAM
  00100000-00298a68 : Kernel code
  00298a69-003420b3 : Kernel data
3ff30000-3ff3ffff : ACPI Tables
3ff40000-3ffeffff : ACPI Non-volatile Storage
3fff0000-3fffffff : reserved
50000000-500003ff : 0000:00:1f.1
54000000-57ffffff : 0000:00:00.0
e8000000-f4ffffff : PCI Bus #01
  e8000000-efffffff : 0000:01:00.0
    e8000000-efffffff : nvidiafb
f5fff400-f5fff4ff : 0000:00:1f.5
  f5fff400-f5fff4ff : Intel ICH5
f5fff800-f5fff9ff : 0000:00:1f.5
  f5fff800-f5fff9ff : Intel ICH5
f5fffc00-f5ffffff : 0000:00:1d.7
  f5fffc00-f5ffffff : ehci_hcd
f6000000-f7efffff : PCI Bus #01
  f6000000-f6ffffff : 0000:01:00.0
    f6000000-f6ffffff : nvidiafb
  f7ee0000-f7efffff : 0000:01:00.0
f7f00000-fbffffff : PCI Bus #02
  f7ffc000-f7ffffff : 0000:02:05.0
    f7ffc000-f7ffffff : SysKonnect SK-98xx
ffb80000-ffffffff : reserved

[8.] Config file
#
# Automatically generated make config: don't edit
# Linux kernel version: 2.6.15-rc1-mm2
# Fri Nov 18 13:12:45 2005
#
CONFIG_X86_32=y
CONFIG_SEMAPHORE_SLEEPERS=y
CONFIG_X86=y
CONFIG_MMU=y
CONFIG_GENERIC_ISA_DMA=y
CONFIG_GENERIC_IOMAP=y
CONFIG_ARCH_MAY_HAVE_PC_FDC=y

#
# Code maturity level options
#
CONFIG_EXPERIMENTAL=y
CONFIG_CLEAN_COMPILE=y
CONFIG_LOCK_KERNEL=y
CONFIG_INIT_ENV_ARG_LIMIT=32

#
# General setup
#
CONFIG_LOCALVERSION=""
CONFIG_LOCALVERSION_AUTO=y
CONFIG_SWAP=y
CONFIG_SWAP_PREFETCH=y
CONFIG_SYSVIPC=y
CONFIG_POSIX_MQUEUE=y
CONFIG_BSD_PROCESS_ACCT=y
CONFIG_BSD_PROCESS_ACCT_V3=y
CONFIG_SYSCTL=y
CONFIG_AUDIT=y
CONFIG_AUDITSYSCALL=y
CONFIG_HOTPLUG=y
CONFIG_IKCONFIG=y
CONFIG_IKCONFIG_PROC=y
# CONFIG_CPUSETS is not set
CONFIG_INITRAMFS_SOURCE=""
# CONFIG_EMBEDDED is not set
CONFIG_KALLSYMS=y
CONFIG_KALLSYMS_ALL=y
# CONFIG_KALLSYMS_EXTRA_PASS is not set
CONFIG_PRINTK=y
CONFIG_BUG=y
CONFIG_DOUBLEFAULT=y
CONFIG_ELF_CORE=y
CONFIG_BASE_FULL=y
CONFIG_FUTEX=y
CONFIG_EPOLL=y
CONFIG_SHMEM=y
CONFIG_CC_ALIGN_FUNCTIONS=0
CONFIG_CC_ALIGN_LABELS=0
CONFIG_CC_ALIGN_LOOPS=0
CONFIG_CC_ALIGN_JUMPS=0
CONFIG_SLAB=y
# CONFIG_INITRAMFS_SKIP is not set
CONFIG_SERIAL_PCI=y
# CONFIG_TINY_SHMEM is not set
CONFIG_BASE_SMALL=0
# CONFIG_SLOB is not set

#
# Loadable module support
#
CONFIG_MODULES=y
CONFIG_MODULE_UNLOAD=y
CONFIG_MODULE_FORCE_UNLOAD=y
CONFIG_OBSOLETE_MODPARM=y
# CONFIG_MODVERSIONS is not set
CONFIG_MODULE_SRCVERSION_ALL=y
CONFIG_KMOD=y
CONFIG_STOP_MACHINE=y

#
# Block layer
#
# CONFIG_LBD is not set
CONFIG_BLK_DEV_IO_TRACE=y

#
# IO Schedulers
#
CONFIG_IOSCHED_NOOP=y
CONFIG_IOSCHED_AS=y
CONFIG_IOSCHED_DEADLINE=m
CONFIG_IOSCHED_CFQ=m
CONFIG_DEFAULT_AS=y
# CONFIG_DEFAULT_DEADLINE is not set
# CONFIG_DEFAULT_CFQ is not set
# CONFIG_DEFAULT_NOOP is not set
CONFIG_DEFAULT_IOSCHED="anticipatory"

#
# Processor type and features
#
CONFIG_X86_PC=y
# CONFIG_X86_ELAN is not set
# CONFIG_X86_VOYAGER is not set
# CONFIG_X86_NUMAQ is not set
# CONFIG_X86_SUMMIT is not set
# CONFIG_X86_BIGSMP is not set
# CONFIG_X86_VISWS is not set
# CONFIG_X86_GENERICARCH is not set
# CONFIG_X86_ES7000 is not set
# CONFIG_M386 is not set
# CONFIG_M486 is not set
# CONFIG_M586 is not set
# CONFIG_M586TSC is not set
# CONFIG_M586MMX is not set
# CONFIG_M686 is not set
# CONFIG_MPENTIUMII is not set
# CONFIG_MPENTIUMIII is not set
# CONFIG_MPENTIUMM is not set
CONFIG_MPENTIUM4=y
# CONFIG_MK6 is not set
# CONFIG_MK7 is not set
# CONFIG_MK8 is not set
# CONFIG_MCRUSOE is not set
# CONFIG_MEFFICEON is not set
# CONFIG_MWINCHIPC6 is not set
# CONFIG_MWINCHIP2 is not set
# CONFIG_MWINCHIP3D is not set
# CONFIG_MGEODEGX1 is not set
# CONFIG_MCYRIXIII is not set
# CONFIG_MVIAC3_2 is not set
# CONFIG_X86_GENERIC is not set
CONFIG_X86_CMPXCHG=y
CONFIG_X86_XADD=y
CONFIG_X86_L1_CACHE_SHIFT=7
CONFIG_RWSEM_XCHGADD_ALGORITHM=y
CONFIG_GENERIC_CALIBRATE_DELAY=y
CONFIG_X86_WP_WORKS_OK=y
CONFIG_X86_INVLPG=y
CONFIG_X86_BSWAP=y
CONFIG_X86_POPAD_OK=y
CONFIG_X86_CMPXCHG64=y
CONFIG_X86_GOOD_APIC=y
CONFIG_X86_INTEL_USERCOPY=y
CONFIG_X86_USE_PPRO_CHECKSUM=y
CONFIG_X86_TSC=y
# CONFIG_HPET_TIMER is not set
CONFIG_SMP=y
CONFIG_NR_CPUS=2
CONFIG_SCHED_SMT=y
# CONFIG_PREEMPT_NONE is not set
# CONFIG_PREEMPT_VOLUNTARY is not set
CONFIG_PREEMPT=y
CONFIG_PREEMPT_BKL=y
CONFIG_X86_LOCAL_APIC=y
CONFIG_X86_IO_APIC=y
CONFIG_X86_MCE=y
CONFIG_X86_MCE_NONFATAL=m
CONFIG_X86_MCE_P4THERMAL=y
# CONFIG_TOSHIBA is not set
# CONFIG_I8K is not set
# CONFIG_X86_REBOOTFIXUPS is not set
CONFIG_MICROCODE=m
CONFIG_X86_MSR=m
CONFIG_X86_CPUID=m

#
# Firmware Drivers
#
# CONFIG_EDD is not set
# CONFIG_DELL_RBU is not set
# CONFIG_DCDBAS is not set
# CONFIG_NOHIGHMEM is not set
CONFIG_HIGHMEM4G=y
# CONFIG_HIGHMEM64G is not set
CONFIG_HIGHMEM=y
CONFIG_ARCH_FLATMEM_ENABLE=y
CONFIG_ARCH_SPARSEMEM_ENABLE=y
CONFIG_ARCH_SELECT_MEMORY_MODEL=y
CONFIG_SELECT_MEMORY_MODEL=y
CONFIG_FLATMEM_MANUAL=y
# CONFIG_DISCONTIGMEM_MANUAL is not set
# CONFIG_SPARSEMEM_MANUAL is not set
CONFIG_FLATMEM=y
CONFIG_FLAT_NODE_MEM_MAP=y
CONFIG_SPARSEMEM_STATIC=y
CONFIG_SPLIT_PTLOCK_CPUS=4
# CONFIG_HIGHPTE is not set
# CONFIG_MATH_EMULATION is not set
CONFIG_MTRR=y
# CONFIG_EFI is not set
CONFIG_IRQBALANCE=y
CONFIG_REGPARM=y
CONFIG_SECCOMP=y
# CONFIG_HZ_100 is not set
# CONFIG_HZ_250 is not set
CONFIG_HZ_1000=y
CONFIG_HZ=1000
CONFIG_PHYSICAL_START=0x100000
CONFIG_KEXEC=y

#
# Power management options (ACPI, APM)
#
CONFIG_PM=y
# CONFIG_PM_LEGACY is not set
# CONFIG_PM_DEBUG is not set

#
# ACPI (Advanced Configuration and Power Interface) Support
#
CONFIG_ACPI=y
# CONFIG_ACPI_AC is not set
# CONFIG_ACPI_BATTERY is not set
# CONFIG_ACPI_BUTTON is not set
# CONFIG_ACPI_VIDEO is not set
# CONFIG_ACPI_HOTKEY is not set
CONFIG_ACPI_FAN=m
CONFIG_ACPI_PROCESSOR=m
CONFIG_ACPI_THERMAL=m
# CONFIG_ACPI_ASUS is not set
# CONFIG_ACPI_IBM is not set
# CONFIG_ACPI_TOSHIBA is not set
CONFIG_ACPI_BLACKLIST_YEAR=0
# CONFIG_ACPI_DEBUG is not set
CONFIG_ACPI_EC=y
CONFIG_ACPI_POWER=y
CONFIG_ACPI_SYSTEM=y
# CONFIG_X86_PM_TIMER is not set
# CONFIG_ACPI_CONTAINER is not set

#
# APM (Advanced Power Management) BIOS Support
#

#
# CPU Frequency scaling
#
# CONFIG_CPU_FREQ is not set

#
# Bus options (PCI, PCMCIA, EISA, MCA, ISA)
#
CONFIG_PCI=y
# CONFIG_PCI_GOBIOS is not set
# CONFIG_PCI_GOMMCONFIG is not set
# CONFIG_PCI_GODIRECT is not set
CONFIG_PCI_GOANY=y
CONFIG_PCI_BIOS=y
CONFIG_PCI_DIRECT=y
CONFIG_PCI_MMCONFIG=y
# CONFIG_PCIEPORTBUS is not set
# CONFIG_PCI_MSI is not set
CONFIG_PCI_LEGACY_PROC=y
# CONFIG_PCI_DEBUG is not set
CONFIG_ISA_DMA_API=y
# CONFIG_ISA is not set
# CONFIG_MCA is not set
# CONFIG_SCx200 is not set
# CONFIG_HOTPLUG_CPU is not set

#
# PCCARD (PCMCIA/CardBus) support
#
# CONFIG_PCCARD is not set

#
# PCI Hotplug Support
#
# CONFIG_HOTPLUG_PCI is not set

#
# Executable file formats
#
CONFIG_BINFMT_ELF=y
CONFIG_BINFMT_AOUT=m
CONFIG_BINFMT_MISC=m

#
# Networking
#
CONFIG_NET=y

#
# Networking options
#
CONFIG_PACKET=m
# CONFIG_PACKET_MMAP is not set
CONFIG_UNIX=m
# CONFIG_NET_KEY is not set
CONFIG_INET=y
# CONFIG_IP_MULTICAST is not set
# CONFIG_IP_ADVANCED_ROUTER is not set
CONFIG_IP_FIB_HASH=y
# CONFIG_IP_PNP is not set
# CONFIG_NET_IPIP is not set
# CONFIG_NET_IPGRE is not set
# CONFIG_ARPD is not set
CONFIG_SYN_COOKIES=y
# CONFIG_INET_AH is not set
# CONFIG_INET_ESP is not set
# CONFIG_INET_IPCOMP is not set
# CONFIG_INET_TUNNEL is not set
CONFIG_INET_DIAG=m
CONFIG_INET_TCP_DIAG=m
# CONFIG_TCP_CONG_ADVANCED is not set
CONFIG_TCP_CONG_BIC=y

#
# IP: Virtual Server Configuration
#
# CONFIG_IP_VS is not set
CONFIG_IPV6=m
# CONFIG_IPV6_PRIVACY is not set
# CONFIG_INET6_AH is not set
# CONFIG_INET6_ESP is not set
# CONFIG_INET6_IPCOMP is not set
# CONFIG_INET6_TUNNEL is not set
# CONFIG_IPV6_TUNNEL is not set
CONFIG_NETFILTER=y
# CONFIG_NETFILTER_DEBUG is not set

#
# Core Netfilter Configuration
#
CONFIG_NETFILTER_NETLINK=m
CONFIG_NETFILTER_NETLINK_QUEUE=m
CONFIG_NETFILTER_NETLINK_LOG=m

#
# IP: Netfilter Configuration
#
CONFIG_IP_NF_CONNTRACK=m
# CONFIG_IP_NF_CT_ACCT is not set
# CONFIG_IP_NF_CONNTRACK_MARK is not set
# CONFIG_IP_NF_CONNTRACK_EVENTS is not set
# CONFIG_IP_NF_CONNTRACK_NETLINK is not set
# CONFIG_IP_NF_CT_PROTO_SCTP is not set
CONFIG_IP_NF_FTP=m
# CONFIG_IP_NF_IRC is not set
# CONFIG_IP_NF_NETBIOS_NS is not set
# CONFIG_IP_NF_TFTP is not set
# CONFIG_IP_NF_AMANDA is not set
# CONFIG_IP_NF_PPTP is not set
# CONFIG_IP_NF_QUEUE is not set
CONFIG_IP_NF_IPTABLES=m
CONFIG_IP_NF_MATCH_LIMIT=m
CONFIG_IP_NF_MATCH_IPRANGE=m
CONFIG_IP_NF_MATCH_MAC=m
CONFIG_IP_NF_MATCH_PKTTYPE=m
CONFIG_IP_NF_MATCH_MARK=m
CONFIG_IP_NF_MATCH_MULTIPORT=m
CONFIG_IP_NF_MATCH_TOS=m
CONFIG_IP_NF_MATCH_RECENT=m
CONFIG_IP_NF_MATCH_ECN=m
CONFIG_IP_NF_MATCH_DSCP=m
CONFIG_IP_NF_MATCH_AH_ESP=m
CONFIG_IP_NF_MATCH_LENGTH=m
CONFIG_IP_NF_MATCH_TTL=m
CONFIG_IP_NF_MATCH_TCPMSS=m
CONFIG_IP_NF_MATCH_HELPER=m
CONFIG_IP_NF_MATCH_STATE=m
CONFIG_IP_NF_MATCH_CONNTRACK=m
CONFIG_IP_NF_MATCH_OWNER=m
CONFIG_IP_NF_MATCH_ADDRTYPE=m
CONFIG_IP_NF_MATCH_REALM=m
# CONFIG_IP_NF_MATCH_SCTP is not set
# CONFIG_IP_NF_MATCH_DCCP is not set
CONFIG_IP_NF_MATCH_COMMENT=m
CONFIG_IP_NF_MATCH_HASHLIMIT=m
CONFIG_IP_NF_MATCH_STRING=m
CONFIG_IP_NF_FILTER=m
CONFIG_IP_NF_TARGET_REJECT=m
CONFIG_IP_NF_TARGET_LOG=m
# CONFIG_IP_NF_TARGET_ULOG is not set
CONFIG_IP_NF_TARGET_TCPMSS=m
CONFIG_IP_NF_TARGET_NFQUEUE=m
# CONFIG_IP_NF_NAT is not set
# CONFIG_IP_NF_MANGLE is not set
# CONFIG_IP_NF_RAW is not set
# CONFIG_IP_NF_ARPTABLES is not set

#
# IPv6: Netfilter Configuration (EXPERIMENTAL)
#
# CONFIG_IP6_NF_QUEUE is not set
# CONFIG_IP6_NF_IPTABLES is not set
# CONFIG_IP6_NF_TARGET_NFQUEUE is not set

#
# DCCP Configuration (EXPERIMENTAL)
#
# CONFIG_IP_DCCP is not set

#
# SCTP Configuration (EXPERIMENTAL)
#
# CONFIG_IP_SCTP is not set
# CONFIG_ATM is not set
# CONFIG_BRIDGE is not set
# CONFIG_VLAN_8021Q is not set
# CONFIG_DECNET is not set
# CONFIG_LLC2 is not set
# CONFIG_IPX is not set
# CONFIG_ATALK is not set
# CONFIG_X25 is not set
# CONFIG_LAPB is not set
# CONFIG_NET_DIVERT is not set
# CONFIG_ECONET is not set
# CONFIG_WAN_ROUTER is not set

#
# QoS and/or fair queueing
#
# CONFIG_NET_SCHED is not set
CONFIG_NET_CLS_ROUTE=y

#
# Network testing
#
# CONFIG_NET_PKTGEN is not set
# CONFIG_HAMRADIO is not set
# CONFIG_IRDA is not set
# CONFIG_BT is not set
# CONFIG_IEEE80211 is not set

#
# Device Drivers
#

#
# Generic Driver Options
#
CONFIG_STANDALONE=y
# CONFIG_PREVENT_FIRMWARE_BUILD is not set
# CONFIG_FW_LOADER is not set
# CONFIG_DEBUG_DRIVER is not set

#
# Connector - unified userspace <-> kernelspace linker
#
CONFIG_CONNECTOR=m

#
# Memory Technology Devices (MTD)
#
# CONFIG_MTD is not set

#
# Parallel port support
#
CONFIG_PARPORT=m
CONFIG_PARPORT_PC=m
# CONFIG_PARPORT_SERIAL is not set
# CONFIG_PARPORT_PC_FIFO is not set
# CONFIG_PARPORT_PC_SUPERIO is not set
# CONFIG_PARPORT_GSC is not set
# CONFIG_PARPORT_1284 is not set

#
# Plug and Play support
#
CONFIG_PNP=y
# CONFIG_PNP_DEBUG is not set

#
# Protocols
#
CONFIG_PNPACPI=y

#
# Block devices
#
# CONFIG_BLK_DEV_FD is not set
# CONFIG_PARIDE is not set
# CONFIG_BLK_CPQ_DA is not set
# CONFIG_BLK_CPQ_CISS_DA is not set
# CONFIG_BLK_DEV_DAC960 is not set
# CONFIG_BLK_DEV_UMEM is not set
# CONFIG_BLK_DEV_COW_COMMON is not set
CONFIG_BLK_DEV_LOOP=m
# CONFIG_BLK_DEV_CRYPTOLOOP is not set
# CONFIG_BLK_DEV_NBD is not set
# CONFIG_BLK_DEV_SX8 is not set
# CONFIG_BLK_DEV_UB is not set
# CONFIG_BLK_DEV_RAM is not set
CONFIG_BLK_DEV_RAM_COUNT=16
CONFIG_CDROM_PKTCDVD=m
CONFIG_CDROM_PKTCDVD_BUFFERS=8
CONFIG_CDROM_PKTCDVD_WCACHE=y
# CONFIG_ATA_OVER_ETH is not set

#
# ATA/ATAPI/MFM/RLL support
#
CONFIG_IDE=m
CONFIG_BLK_DEV_IDE=m

#
# Please see Documentation/ide.txt for help/info on IDE drives
#
# CONFIG_BLK_DEV_IDE_SATA is not set
# CONFIG_BLK_DEV_HD_IDE is not set
CONFIG_BLK_DEV_IDEDISK=m
# CONFIG_IDEDISK_MULTI_MODE is not set
CONFIG_BLK_DEV_IDECD=m
# CONFIG_BLK_DEV_IDETAPE is not set
# CONFIG_BLK_DEV_IDEFLOPPY is not set
# CONFIG_BLK_DEV_IDESCSI is not set
# CONFIG_IDE_TASK_IOCTL is not set

#
# IDE chipset support/bugfixes
#
CONFIG_IDE_GENERIC=m
# CONFIG_BLK_DEV_CMD640 is not set
# CONFIG_BLK_DEV_IDEPNP is not set
CONFIG_BLK_DEV_IDEPCI=y
CONFIG_IDEPCI_SHARE_IRQ=y
# CONFIG_BLK_DEV_OFFBOARD is not set
CONFIG_BLK_DEV_GENERIC=m
# CONFIG_BLK_DEV_OPTI621 is not set
# CONFIG_BLK_DEV_RZ1000 is not set
CONFIG_BLK_DEV_IDEDMA_PCI=y
# CONFIG_BLK_DEV_IDEDMA_FORCED is not set
CONFIG_IDEDMA_PCI_AUTO=y
# CONFIG_IDEDMA_ONLYDISK is not set
# CONFIG_BLK_DEV_AEC62XX is not set
# CONFIG_BLK_DEV_ALI15X3 is not set
# CONFIG_BLK_DEV_AMD74XX is not set
# CONFIG_BLK_DEV_ATIIXP is not set
# CONFIG_BLK_DEV_CMD64X is not set
# CONFIG_BLK_DEV_TRIFLEX is not set
# CONFIG_BLK_DEV_CY82C693 is not set
# CONFIG_BLK_DEV_CS5520 is not set
# CONFIG_BLK_DEV_CS5530 is not set
# CONFIG_BLK_DEV_CS5535 is not set
# CONFIG_BLK_DEV_HPT34X is not set
# CONFIG_BLK_DEV_HPT366 is not set
# CONFIG_BLK_DEV_SC1200 is not set
CONFIG_BLK_DEV_PIIX=m
# CONFIG_BLK_DEV_IT821X is not set
# CONFIG_BLK_DEV_NS87415 is not set
# CONFIG_BLK_DEV_PDC202XX_OLD is not set
# CONFIG_BLK_DEV_PDC202XX_NEW is not set
# CONFIG_BLK_DEV_SVWKS is not set
# CONFIG_BLK_DEV_SIIMAGE is not set
# CONFIG_BLK_DEV_SIS5513 is not set
# CONFIG_BLK_DEV_SLC90E66 is not set
# CONFIG_BLK_DEV_TRM290 is not set
# CONFIG_BLK_DEV_VIA82CXXX is not set
# CONFIG_IDE_ARM is not set
CONFIG_BLK_DEV_IDEDMA=y
# CONFIG_IDEDMA_IVB is not set
CONFIG_IDEDMA_AUTO=y
# CONFIG_BLK_DEV_HD is not set

#
# SCSI device support
#
# CONFIG_RAID_ATTRS is not set
CONFIG_SCSI=y
CONFIG_SCSI_PROC_FS=y

#
# SCSI support type (disk, tape, CD-ROM)
#
CONFIG_BLK_DEV_SD=y
# CONFIG_CHR_DEV_ST is not set
# CONFIG_CHR_DEV_OSST is not set
# CONFIG_BLK_DEV_SR is not set
# CONFIG_CHR_DEV_SG is not set
# CONFIG_CHR_DEV_SCH is not set

#
# Some SCSI devices (e.g. CD jukebox) support multiple LUNs
#
# CONFIG_SCSI_MULTI_LUN is not set
# CONFIG_SCSI_CONSTANTS is not set
# CONFIG_SCSI_LOGGING is not set

#
# SCSI Transport Attributes
#
# CONFIG_SCSI_SPI_ATTRS is not set
# CONFIG_SCSI_FC_ATTRS is not set
# CONFIG_SCSI_ISCSI_ATTRS is not set
# CONFIG_SCSI_SAS_ATTRS is not set

#
# SCSI Transport Layers
#
# CONFIG_SAS_CLASS is not set

#
# SCSI low-level drivers
#
# CONFIG_ISCSI_TCP is not set
# CONFIG_SCSI_ARCMSR is not set
# CONFIG_BLK_DEV_3W_XXXX_RAID is not set
# CONFIG_SCSI_3W_9XXX is not set
# CONFIG_SCSI_ACARD is not set
# CONFIG_SCSI_AACRAID is not set
# CONFIG_SCSI_AIC7XXX is not set
# CONFIG_SCSI_AIC7XXX_OLD is not set
# CONFIG_SCSI_AIC79XX is not set
# CONFIG_SCSI_DPT_I2O is not set
# CONFIG_MEGARAID_NEWGEN is not set
# CONFIG_MEGARAID_LEGACY is not set
# CONFIG_MEGARAID_SAS is not set
CONFIG_SCSI_SATA=y
# CONFIG_SCSI_SATA_AHCI is not set
# CONFIG_SCSI_PATA_AMD is not set
# CONFIG_SCSI_SATA_SVW is not set
# CONFIG_SCSI_PATA_TRIFLEX is not set
CONFIG_SCSI_ATA_PIIX=y
# CONFIG_SCSI_SATA_MV is not set
# CONFIG_SCSI_SATA_NV is not set
# CONFIG_SCSI_PATA_OPTI is not set
# CONFIG_SCSI_PDC_ADMA is not set
# CONFIG_SCSI_SATA_QSTOR is not set
# CONFIG_SCSI_PATA_PDC2027X is not set
# CONFIG_SCSI_SATA_PROMISE is not set
# CONFIG_SCSI_SATA_SX4 is not set
# CONFIG_SCSI_SATA_SIL is not set
# CONFIG_SCSI_SATA_SIL24 is not set
# CONFIG_SCSI_PATA_SIL680 is not set
# CONFIG_SCSI_SATA_SIS is not set
# CONFIG_SCSI_SATA_ULI is not set
# CONFIG_SCSI_PATA_VIA is not set
# CONFIG_SCSI_SATA_VIA is not set
# CONFIG_SCSI_SATA_VITESSE is not set
# CONFIG_SCSI_BUSLOGIC is not set
# CONFIG_SCSI_DMX3191D is not set
# CONFIG_SCSI_EATA is not set
# CONFIG_SCSI_FUTURE_DOMAIN is not set
# CONFIG_SCSI_GDTH is not set
# CONFIG_SCSI_IPS is not set
# CONFIG_SCSI_INITIO is not set
# CONFIG_SCSI_INIA100 is not set
# CONFIG_SCSI_PPA is not set
# CONFIG_SCSI_IMM is not set
# CONFIG_SCSI_SYM53C8XX_2 is not set
# CONFIG_SCSI_IPR is not set
# CONFIG_SCSI_QLOGIC_FC is not set
# CONFIG_SCSI_QLOGIC_1280 is not set
CONFIG_SCSI_QLA2XXX=y
# CONFIG_SCSI_QLA21XX is not set
# CONFIG_SCSI_QLA22XX is not set
# CONFIG_SCSI_QLA2300 is not set
# CONFIG_SCSI_QLA2322 is not set
# CONFIG_SCSI_QLA6312 is not set
# CONFIG_SCSI_QLA24XX is not set
# CONFIG_SCSI_LPFC is not set
# CONFIG_SCSI_DC395x is not set
# CONFIG_SCSI_DC390T is not set
# CONFIG_SCSI_NSP32 is not set
# CONFIG_SCSI_DEBUG is not set

#
# Multi-device support (RAID and LVM)
#
# CONFIG_MD is not set

#
# Fusion MPT device support
#
# CONFIG_FUSION is not set
# CONFIG_FUSION_SPI is not set
# CONFIG_FUSION_FC is not set
# CONFIG_FUSION_SAS is not set

#
# IEEE 1394 (FireWire) support
#
# CONFIG_IEEE1394 is not set

#
# I2O device support
#
# CONFIG_I2O is not set

#
# Network device support
#
CONFIG_NETDEVICES=y
# CONFIG_DUMMY is not set
# CONFIG_BONDING is not set
# CONFIG_EQUALIZER is not set
CONFIG_TUN=m
# CONFIG_NET_SB1000 is not set

#
# ARCnet devices
#
# CONFIG_ARCNET is not set

#
# PHY device support
#

#
# Ethernet (10 or 100Mbit)
#
# CONFIG_NET_ETHERNET is not set

#
# Ethernet (1000 Mbit)
#
# CONFIG_ACENIC is not set
# CONFIG_DL2K is not set
# CONFIG_E1000 is not set
# CONFIG_NS83820 is not set
# CONFIG_HAMACHI is not set
# CONFIG_YELLOWFIN is not set
# CONFIG_R8169 is not set
# CONFIG_SIS190 is not set
# CONFIG_SKGE is not set
# CONFIG_SKY2 is not set
CONFIG_SK98LIN=m
# CONFIG_TIGON3 is not set
# CONFIG_BNX2 is not set

#
# Ethernet (10000 Mbit)
#
# CONFIG_CHELSIO_T1 is not set
# CONFIG_IXGB is not set
# CONFIG_S2IO is not set

#
# Token Ring devices
#
# CONFIG_TR is not set

#
# Wireless LAN (non-hamradio)
#
# CONFIG_NET_RADIO is not set

#
# Wan interfaces
#
# CONFIG_WAN is not set
# CONFIG_FDDI is not set
# CONFIG_HIPPI is not set
# CONFIG_PLIP is not set
# CONFIG_PPP is not set
# CONFIG_SLIP is not set
# CONFIG_NET_FC is not set
# CONFIG_SHAPER is not set
# CONFIG_NETCONSOLE is not set
# CONFIG_KGDBOE is not set
# CONFIG_NETPOLL is not set
# CONFIG_NETPOLL_RX is not set
# CONFIG_NETPOLL_TRAP is not set
# CONFIG_NET_POLL_CONTROLLER is not set

#
# ISDN subsystem
#
# CONFIG_ISDN is not set

#
# Telephony Support
#
# CONFIG_PHONE is not set

#
# Input device support
#
CONFIG_INPUT=y

#
# Userland interfaces
#
CONFIG_INPUT_MOUSEDEV=y
CONFIG_INPUT_MOUSEDEV_PSAUX=y
CONFIG_INPUT_MOUSEDEV_SCREEN_X=1024
CONFIG_INPUT_MOUSEDEV_SCREEN_Y=768
# CONFIG_INPUT_JOYDEV is not set
# CONFIG_INPUT_TSDEV is not set
CONFIG_INPUT_EVDEV=m
# CONFIG_INPUT_EVBUG is not set

#
# Input Device Drivers
#
CONFIG_INPUT_KEYBOARD=y
CONFIG_KEYBOARD_ATKBD=y
# CONFIG_KEYBOARD_SUNKBD is not set
# CONFIG_KEYBOARD_LKKBD is not set
# CONFIG_KEYBOARD_XTKBD is not set
# CONFIG_KEYBOARD_NEWTON is not set
CONFIG_INPUT_MOUSE=y
CONFIG_MOUSE_PS2=m
# CONFIG_MOUSE_SERIAL is not set
# CONFIG_MOUSE_VSXXXAA is not set
# CONFIG_INPUT_JOYSTICK is not set
# CONFIG_INPUT_TOUCHSCREEN is not set
# CONFIG_INPUT_MISC is not set

#
# Hardware I/O ports
#
CONFIG_SERIO=y
CONFIG_SERIO_I8042=y
# CONFIG_SERIO_SERPORT is not set
# CONFIG_SERIO_CT82C710 is not set
# CONFIG_SERIO_PARKBD is not set
# CONFIG_SERIO_PCIPS2 is not set
CONFIG_SERIO_LIBPS2=y
# CONFIG_SERIO_RAW is not set
# CONFIG_GAMEPORT is not set

#
# Character devices
#
CONFIG_VT=y
CONFIG_VT_CONSOLE=y
CONFIG_HW_CONSOLE=y
# CONFIG_SERIAL_NONSTANDARD is not set

#
# Serial drivers
#
CONFIG_SERIAL_8250=m
# CONFIG_SERIAL_8250_ACPI is not set
CONFIG_SERIAL_8250_NR_UARTS=4
# CONFIG_SERIAL_8250_EXTENDED is not set

#
# Non-8250 serial port support
#
CONFIG_SERIAL_CORE=m
# CONFIG_SERIAL_JSM is not set
CONFIG_UNIX98_PTYS=y
# CONFIG_LEGACY_PTYS is not set
# CONFIG_PRINTER is not set
# CONFIG_PPDEV is not set
# CONFIG_TIPAR is not set

#
# IPMI
#
# CONFIG_IPMI_HANDLER is not set

#
# Watchdog Cards
#
# CONFIG_WATCHDOG is not set
CONFIG_HW_RANDOM=m
CONFIG_NVRAM=m
CONFIG_RTC=m
CONFIG_GEN_RTC=m
CONFIG_GEN_RTC_X=y
# CONFIG_DTLK is not set
# CONFIG_R3964 is not set
# CONFIG_APPLICOM is not set
# CONFIG_SONYPI is not set

#
# Ftape, the floppy tape device driver
#
CONFIG_AGP=m
# CONFIG_AGP_ALI is not set
# CONFIG_AGP_ATI is not set
# CONFIG_AGP_AMD is not set
# CONFIG_AGP_AMD64 is not set
CONFIG_AGP_INTEL=m
# CONFIG_AGP_NVIDIA is not set
# CONFIG_AGP_SIS is not set
# CONFIG_AGP_SWORKS is not set
# CONFIG_AGP_VIA is not set
# CONFIG_AGP_EFFICEON is not set
# CONFIG_DRM is not set
# CONFIG_MWAVE is not set
# CONFIG_RAW_DRIVER is not set
# CONFIG_HPET is not set
# CONFIG_HANGCHECK_TIMER is not set

#
# TPM devices
#
# CONFIG_TCG_TPM is not set
# CONFIG_TELCLOCK is not set

#
# I2C support
#
CONFIG_I2C=y
# CONFIG_I2C_CHARDEV is not set

#
# I2C Algorithms
#
CONFIG_I2C_ALGOBIT=y
# CONFIG_I2C_ALGOPCF is not set
# CONFIG_I2C_ALGOPCA is not set

#
# I2C Hardware Bus support
#
# CONFIG_I2C_ALI1535 is not set
# CONFIG_I2C_ALI1563 is not set
# CONFIG_I2C_ALI15X3 is not set
# CONFIG_I2C_AMD756 is not set
# CONFIG_I2C_AMD8111 is not set
# CONFIG_I2C_I801 is not set
# CONFIG_I2C_I810 is not set
# CONFIG_I2C_PIIX4 is not set
# CONFIG_I2C_NFORCE2 is not set
# CONFIG_I2C_PARPORT is not set
# CONFIG_I2C_PARPORT_LIGHT is not set
# CONFIG_I2C_PROSAVAGE is not set
# CONFIG_I2C_SAVAGE4 is not set
# CONFIG_SCx200_ACB is not set
# CONFIG_I2C_SIS5595 is not set
# CONFIG_I2C_SIS630 is not set
# CONFIG_I2C_SIS96X is not set
# CONFIG_I2C_STUB is not set
# CONFIG_I2C_VIA is not set
# CONFIG_I2C_VIAPRO is not set
# CONFIG_I2C_VOODOO3 is not set
# CONFIG_I2C_PCA_ISA is not set

#
# Miscellaneous I2C Chip support
#
# CONFIG_SENSORS_DS1337 is not set
# CONFIG_SENSORS_DS1374 is not set
# CONFIG_SENSORS_EEPROM is not set
# CONFIG_SENSORS_PCF8574 is not set
# CONFIG_SENSORS_PCA9539 is not set
# CONFIG_SENSORS_PCF8591 is not set
# CONFIG_SENSORS_RTC8564 is not set
# CONFIG_SENSORS_MAX6875 is not set
# CONFIG_RTC_X1205_I2C is not set
# CONFIG_I2C_DEBUG_CORE is not set
# CONFIG_I2C_DEBUG_ALGO is not set
# CONFIG_I2C_DEBUG_BUS is not set
# CONFIG_I2C_DEBUG_CHIP is not set

#
# Dallas's 1-wire bus
#
# CONFIG_W1 is not set

#
# Hardware Monitoring support
#
# CONFIG_HWMON is not set
# CONFIG_HWMON_VID is not set

#
# Misc devices
#
# CONFIG_IBM_ASM is not set

#
# Multimedia Capabilities Port drivers
#

#
# Multimedia devices
#
# CONFIG_VIDEO_DEV is not set

#
# Digital Video Broadcasting Devices
#
# CONFIG_DVB is not set

#
# Graphics support
#
CONFIG_FB=y
CONFIG_FB_CFB_FILLRECT=y
CONFIG_FB_CFB_COPYAREA=y
CONFIG_FB_CFB_IMAGEBLIT=y
# CONFIG_FB_MACMODES is not set
CONFIG_FB_MODE_HELPERS=y
CONFIG_FB_TILEBLITTING=y
# CONFIG_FB_CIRRUS is not set
# CONFIG_FB_PM2 is not set
# CONFIG_FB_CYBER2000 is not set
# CONFIG_FB_ARC is not set
# CONFIG_FB_ASILIANT is not set
# CONFIG_FB_IMSTT is not set
# CONFIG_FB_VGA16 is not set
# CONFIG_FB_VESA is not set
CONFIG_VIDEO_SELECT=y
# CONFIG_FB_HGA is not set
# CONFIG_FB_S1D13XXX is not set
CONFIG_FB_NVIDIA=y
CONFIG_FB_NVIDIA_I2C=y
# CONFIG_FB_RIVA is not set
# CONFIG_FB_I810 is not set
# CONFIG_FB_INTEL is not set
# CONFIG_FB_MATROX is not set
# CONFIG_FB_RADEON_OLD is not set
# CONFIG_FB_RADEON is not set
# CONFIG_FB_ATY128 is not set
# CONFIG_FB_ATY is not set
# CONFIG_FB_SAVAGE is not set
# CONFIG_FB_SIS is not set
# CONFIG_FB_NEOMAGIC is not set
# CONFIG_FB_KYRO is not set
# CONFIG_FB_3DFX is not set
# CONFIG_FB_VOODOO1 is not set
# CONFIG_FB_CYBLA is not set
# CONFIG_FB_TRIDENT is not set
# CONFIG_FB_GEODE is not set
# CONFIG_FB_VIRTUAL is not set

#
# Console display driver support
#
CONFIG_VGA_CONSOLE=y
CONFIG_DUMMY_CONSOLE=y
CONFIG_FRAMEBUFFER_CONSOLE=y
# CONFIG_FRAMEBUFFER_CONSOLE_ROTATION is not set
# CONFIG_FONTS is not set
CONFIG_FONT_8x8=y
CONFIG_FONT_8x16=y

#
# Logo configuration
#
# CONFIG_LOGO is not set
CONFIG_BACKLIGHT_LCD_SUPPORT=y
CONFIG_BACKLIGHT_CLASS_DEVICE=m
CONFIG_BACKLIGHT_DEVICE=y
CONFIG_LCD_CLASS_DEVICE=m
CONFIG_LCD_DEVICE=y

#
# Speakup console speech
#
# CONFIG_SPEAKUP is not set

#
# Sound
#
CONFIG_SOUND=m

#
# Advanced Linux Sound Architecture
#
CONFIG_SND=m
CONFIG_SND_AC97_CODEC=m
CONFIG_SND_AC97_BUS=m
CONFIG_SND_TIMER=m
CONFIG_SND_PCM=m
CONFIG_SND_RAWMIDI=m
CONFIG_SND_SEQUENCER=m
CONFIG_SND_SEQ_DUMMY=m
CONFIG_SND_OSSEMUL=y
CONFIG_SND_MIXER_OSS=m
CONFIG_SND_PCM_OSS=m
CONFIG_SND_SEQUENCER_OSS=y
CONFIG_SND_RTCTIMER=m
CONFIG_SND_SEQ_RTCTIMER_DEFAULT=y
# CONFIG_SND_VERBOSE_PRINTK is not set
# CONFIG_SND_DEBUG is not set
CONFIG_SND_GENERIC_DRIVER=y

#
# Generic devices
#
CONFIG_SND_DUMMY=m
CONFIG_SND_VIRMIDI=m
# CONFIG_SND_MTPAV is not set
# CONFIG_SND_SERIAL_U16550 is not set
# CONFIG_SND_MPU401 is not set

#
# PCI devices
#
# CONFIG_SND_ALI5451 is not set
# CONFIG_SND_ATIIXP is not set
# CONFIG_SND_ATIIXP_MODEM is not set
# CONFIG_SND_AU8810 is not set
# CONFIG_SND_AU8820 is not set
# CONFIG_SND_AU8830 is not set
# CONFIG_SND_AZT3328 is not set
# CONFIG_SND_BT87X is not set
# CONFIG_SND_CS46XX is not set
# CONFIG_SND_CS4281 is not set
# CONFIG_SND_EMU10K1 is not set
# CONFIG_SND_EMU10K1X is not set
# CONFIG_SND_CA0106 is not set
# CONFIG_SND_KORG1212 is not set
# CONFIG_SND_MIXART is not set
# CONFIG_SND_NM256 is not set
# CONFIG_SND_RME32 is not set
# CONFIG_SND_RME96 is not set
# CONFIG_SND_RME9652 is not set
# CONFIG_SND_HDSP is not set
# CONFIG_SND_HDSPM is not set
# CONFIG_SND_TRIDENT is not set
# CONFIG_SND_YMFPCI is not set
# CONFIG_SND_AD1889 is not set
# CONFIG_SND_ALS4000 is not set
# CONFIG_SND_CMIPCI is not set
# CONFIG_SND_ENS1370 is not set
# CONFIG_SND_CS5535AUDIO is not set
# CONFIG_SND_ENS1371 is not set
# CONFIG_SND_ES1938 is not set
# CONFIG_SND_ES1968 is not set
# CONFIG_SND_MAESTRO3 is not set
# CONFIG_SND_FM801 is not set
# CONFIG_SND_ICE1712 is not set
# CONFIG_SND_ICE1724 is not set
CONFIG_SND_INTEL8X0=m
# CONFIG_SND_INTEL8X0M is not set
# CONFIG_SND_SONICVIBES is not set
# CONFIG_SND_VIA82XX is not set
# CONFIG_SND_VIA82XX_MODEM is not set
# CONFIG_SND_VX222 is not set
# CONFIG_SND_HDA_INTEL is not set

#
# USB devices
#
# CONFIG_SND_USB_AUDIO is not set
# CONFIG_SND_USB_USX2Y is not set

#
# Open Sound System
#
# CONFIG_SOUND_PRIME is not set

#
# USB support
#
CONFIG_USB_ARCH_HAS_HCD=y
CONFIG_USB_ARCH_HAS_OHCI=y
CONFIG_USB=m
# CONFIG_USB_DEBUG is not set

#
# Miscellaneous USB options
#
CONFIG_USB_DEVICEFS=y
# CONFIG_USB_BANDWIDTH is not set
# CONFIG_USB_DYNAMIC_MINORS is not set
# CONFIG_USB_SUSPEND is not set
# CONFIG_USB_OTG is not set

#
# USB Host Controller Drivers
#
CONFIG_USB_EHCI_HCD=m
# CONFIG_USB_EHCI_SPLIT_ISO is not set
# CONFIG_USB_EHCI_ROOT_HUB_TT is not set
# CONFIG_USB_ISP116X_HCD is not set
# CONFIG_USB_OHCI_HCD is not set
CONFIG_USB_UHCI_HCD=m
# CONFIG_USB_SL811_HCD is not set

#
# USB Device Class drivers
#
# CONFIG_USB_ACM is not set
# CONFIG_USB_PRINTER is not set

#
# NOTE: USB_STORAGE enables SCSI, and 'SCSI disk support'
#

#
# may also be needed; see USB_STORAGE Help for more information
#
# CONFIG_USB_STORAGE is not set
# CONFIG_USB_LIBUSUAL is not set

#
# USB Input Devices
#
# CONFIG_USB_HID is not set

#
# USB HID Boot Protocol drivers
#
# CONFIG_USB_KBD is not set
# CONFIG_USB_MOUSE is not set
# CONFIG_USB_AIPTEK is not set
# CONFIG_USB_WACOM is not set
# CONFIG_USB_ACECAD is not set
# CONFIG_USB_KBTAB is not set
# CONFIG_USB_POWERMATE is not set
# CONFIG_USB_MTOUCH is not set
# CONFIG_USB_ITMTOUCH is not set
# CONFIG_USB_EGALAX is not set
# CONFIG_USB_YEALINK is not set
# CONFIG_USB_XPAD is not set
# CONFIG_USB_ATI_REMOTE is not set
# CONFIG_USB_KEYSPAN_REMOTE is not set
# CONFIG_USB_APPLETOUCH is not set

#
# USB Imaging devices
#
# CONFIG_USB_MDC800 is not set
# CONFIG_USB_MICROTEK is not set

#
# USB Multimedia devices
#
# CONFIG_USB_DABUSB is not set

#
# Video4Linux support is needed for USB Multimedia device support
#

#
# USB Network Adapters
#
# CONFIG_USB_CATC is not set
# CONFIG_USB_KAWETH is not set
# CONFIG_USB_PEGASUS is not set
# CONFIG_USB_RTL8150 is not set
# CONFIG_USB_USBNET is not set
# CONFIG_USB_MON is not set

#
# USB port drivers
#
# CONFIG_USB_USS720 is not set

#
# USB Serial Converter support
#
# CONFIG_USB_SERIAL is not set

#
# USB Miscellaneous drivers
#
# CONFIG_USB_EMI62 is not set
# CONFIG_USB_EMI26 is not set
# CONFIG_USB_AUERSWALD is not set
# CONFIG_USB_RIO500 is not set
# CONFIG_USB_LEGOTOWER is not set
# CONFIG_USB_LCD is not set
# CONFIG_USB_LED is not set
# CONFIG_USB_CYTHERM is not set
# CONFIG_USB_GOTEMP is not set
# CONFIG_USB_PHIDGETKIT is not set
# CONFIG_USB_PHIDGETSERVO is not set
# CONFIG_USB_IDMOUSE is not set
# CONFIG_USB_SISUSBVGA is not set
# CONFIG_USB_LD is not set
# CONFIG_USB_TEST is not set

#
# USB DSL modem support
#

#
# USB Gadget Support
#
# CONFIG_USB_GADGET is not set

#
# MMC/SD Card support
#
# CONFIG_MMC is not set

#
# InfiniBand support
#
# CONFIG_INFINIBAND is not set

#
# SN Devices
#

#
# EDAC - error detection and reporting (RAS)
#
# CONFIG_EDAC is not set

#
# Distributed Lock Manager
#
# CONFIG_DLM is not set

#
# File systems
#
CONFIG_EXT2_FS=m
CONFIG_EXT2_FS_XATTR=y
CONFIG_EXT2_FS_POSIX_ACL=y
CONFIG_EXT2_FS_SECURITY=y
CONFIG_EXT2_FS_XIP=y
CONFIG_FS_XIP=y
CONFIG_EXT3_FS=y
CONFIG_EXT3_FS_XATTR=y
CONFIG_EXT3_FS_POSIX_ACL=y
CONFIG_EXT3_FS_SECURITY=y
CONFIG_JBD=y
# CONFIG_JBD_DEBUG is not set
CONFIG_FS_MBCACHE=y
CONFIG_REISER4_FS=m
# CONFIG_REISER4_DEBUG is not set
CONFIG_REISERFS_FS=m
# CONFIG_REISERFS_CHECK is not set
CONFIG_REISERFS_PROC_INFO=y
CONFIG_REISERFS_FS_XATTR=y
CONFIG_REISERFS_FS_POSIX_ACL=y
CONFIG_REISERFS_FS_SECURITY=y
CONFIG_JFS_FS=m
CONFIG_JFS_POSIX_ACL=y
CONFIG_JFS_SECURITY=y
# CONFIG_JFS_DEBUG is not set
CONFIG_JFS_STATISTICS=y
CONFIG_FS_POSIX_ACL=y
CONFIG_XFS_FS=m
CONFIG_XFS_QUOTA=y
CONFIG_XFS_SECURITY=y
CONFIG_XFS_POSIX_ACL=y
# CONFIG_XFS_RT is not set
# CONFIG_OCFS2_FS is not set
# CONFIG_MINIX_FS is not set
# CONFIG_ROMFS_FS is not set
CONFIG_INOTIFY=y
CONFIG_QUOTA=y
# CONFIG_QFMT_V1 is not set
CONFIG_QFMT_V2=m
CONFIG_QUOTACTL=y
CONFIG_DNOTIFY=y
# CONFIG_AUTOFS_FS is not set
CONFIG_AUTOFS4_FS=m
CONFIG_FUSE_FS=m

#
# CD-ROM/DVD Filesystems
#
CONFIG_ISO9660_FS=m
CONFIG_JOLIET=y
CONFIG_ZISOFS=y
CONFIG_ZISOFS_FS=m
CONFIG_UDF_FS=m
CONFIG_UDF_NLS=y

#
# DOS/FAT/NT Filesystems
#
CONFIG_FAT_FS=m
CONFIG_MSDOS_FS=m
CONFIG_VFAT_FS=m
CONFIG_FAT_DEFAULT_CODEPAGE=437
CONFIG_FAT_DEFAULT_IOCHARSET="iso8859-1"
CONFIG_NTFS_FS=m
# CONFIG_NTFS_DEBUG is not set
CONFIG_NTFS_RW=y

#
# Pseudo filesystems
#
CONFIG_PROC_FS=y
# CONFIG_PROC_KCORE is not set
CONFIG_SYSFS=y
CONFIG_TMPFS=y
# CONFIG_HUGETLBFS is not set
# CONFIG_HUGETLB_PAGE is not set
CONFIG_RAMFS=y
CONFIG_RELAYFS_FS=y
CONFIG_CONFIGFS_FS=m

#
# Miscellaneous filesystems
#
# CONFIG_ADFS_FS is not set
# CONFIG_AFFS_FS is not set
# CONFIG_ASFS_FS is not set
# CONFIG_HFS_FS is not set
# CONFIG_HFSPLUS_FS is not set
# CONFIG_BEFS_FS is not set
# CONFIG_BFS_FS is not set
# CONFIG_EFS_FS is not set
# CONFIG_CRAMFS is not set
# CONFIG_VXFS_FS is not set
# CONFIG_HPFS_FS is not set
# CONFIG_QNX4FS_FS is not set
# CONFIG_SYSV_FS is not set
# CONFIG_UFS_FS is not set

#
# Network File Systems
#
# CONFIG_NFS_FS is not set
# CONFIG_NFSD is not set
# CONFIG_SMB_FS is not set
# CONFIG_CIFS is not set
# CONFIG_NCP_FS is not set
# CONFIG_CODA_FS is not set
# CONFIG_AFS_FS is not set
# CONFIG_9P_FS is not set

#
# Partition Types
#
# CONFIG_PARTITION_ADVANCED is not set
CONFIG_MSDOS_PARTITION=y

#
# Native Language Support
#
CONFIG_NLS=m
CONFIG_NLS_DEFAULT="iso8859-1"
CONFIG_NLS_CODEPAGE_437=m
# CONFIG_NLS_CODEPAGE_737 is not set
# CONFIG_NLS_CODEPAGE_775 is not set
# CONFIG_NLS_CODEPAGE_850 is not set
CONFIG_NLS_CODEPAGE_852=m
# CONFIG_NLS_CODEPAGE_855 is not set
# CONFIG_NLS_CODEPAGE_857 is not set
# CONFIG_NLS_CODEPAGE_860 is not set
# CONFIG_NLS_CODEPAGE_861 is not set
# CONFIG_NLS_CODEPAGE_862 is not set
# CONFIG_NLS_CODEPAGE_863 is not set
# CONFIG_NLS_CODEPAGE_864 is not set
# CONFIG_NLS_CODEPAGE_865 is not set
# CONFIG_NLS_CODEPAGE_866 is not set
# CONFIG_NLS_CODEPAGE_869 is not set
# CONFIG_NLS_CODEPAGE_936 is not set
# CONFIG_NLS_CODEPAGE_950 is not set
# CONFIG_NLS_CODEPAGE_932 is not set
# CONFIG_NLS_CODEPAGE_949 is not set
# CONFIG_NLS_CODEPAGE_874 is not set
# CONFIG_NLS_ISO8859_8 is not set
CONFIG_NLS_CODEPAGE_1250=m
# CONFIG_NLS_CODEPAGE_1251 is not set
# CONFIG_NLS_ASCII is not set
CONFIG_NLS_ISO8859_1=m
CONFIG_NLS_ISO8859_2=m
# CONFIG_NLS_ISO8859_3 is not set
# CONFIG_NLS_ISO8859_4 is not set
# CONFIG_NLS_ISO8859_5 is not set
# CONFIG_NLS_ISO8859_6 is not set
# CONFIG_NLS_ISO8859_7 is not set
# CONFIG_NLS_ISO8859_9 is not set
# CONFIG_NLS_ISO8859_13 is not set
# CONFIG_NLS_ISO8859_14 is not set
# CONFIG_NLS_ISO8859_15 is not set
# CONFIG_NLS_KOI8_R is not set
# CONFIG_NLS_KOI8_U is not set
CONFIG_NLS_UTF8=m

#
# Instrumentation Support
#
CONFIG_PROFILING=y
CONFIG_OPROFILE=m
CONFIG_KPROBES=y

#
# Kernel hacking
#
# CONFIG_PRINTK_TIME is not set
CONFIG_DEBUG_KERNEL=y
CONFIG_MAGIC_SYSRQ=y
CONFIG_LOG_BUF_SHIFT=20
CONFIG_DETECT_SOFTLOCKUP=y
CONFIG_SCHEDSTATS=y
CONFIG_DEBUG_SLAB=y
CONFIG_DEBUG_PREEMPT=y
CONFIG_DEBUG_SPINLOCK=y
CONFIG_DEBUG_SPINLOCK_SLEEP=y
# CONFIG_DEBUG_KOBJECT is not set
CONFIG_DEBUG_HIGHMEM=y
CONFIG_DEBUG_BUGVERBOSE=y
CONFIG_DEBUG_INFO=y
CONFIG_PAGE_OWNER=y
CONFIG_DEBUG_FS=y
CONFIG_DEBUG_VM=y
CONFIG_FRAME_POINTER=y
CONFIG_RCU_TORTURE_TEST=m
CONFIG_EARLY_PRINTK=y
CONFIG_DEBUG_STACKOVERFLOW=y
CONFIG_DEBUG_STACK_USAGE=y
CONFIG_DEBUG_PAGEALLOC=y
# CONFIG_DEBUG_RODATA is not set
CONFIG_4KSTACKS=y
CONFIG_X86_FIND_SMP_CONFIG=y
CONFIG_X86_MPPARSE=y

#
# Security options
#
# CONFIG_KEYS is not set
# CONFIG_SECURITY is not set

#
# Cryptographic options
#
# CONFIG_CRYPTO is not set

#
# Hardware crypto devices
#

#
# Library routines
#
CONFIG_CRC_CCITT=m
CONFIG_CRC16=m
CONFIG_CRC32=y
CONFIG_LIBCRC32C=m
CONFIG_ZLIB_INFLATE=m
CONFIG_ZLIB_DEFLATE=m
CONFIG_TEXTSEARCH=y
CONFIG_TEXTSEARCH_KMP=m
CONFIG_TEXTSEARCH_BM=m
CONFIG_TEXTSEARCH_FSM=m
CONFIG_GENERIC_HARDIRQS=y
CONFIG_GENERIC_IRQ_PROBE=y
CONFIG_GENERIC_PENDING_IRQ=y
CONFIG_X86_SMP=y
CONFIG_X86_HT=y
CONFIG_X86_BIOS_REBOOT=y
CONFIG_X86_TRAMPOLINE=y


OOPS Reporting Tool v.b6
www.wsi.edu.pl/~piotrowskim/
/files/ort/beta/

Regards,
Michal Piotrowski

Re: 2.6.15-rc1-mm2

[Hugh Dickins]

On Sun, 20 Nov 2005, Michal Piotrowski wrote:
> 
> It looks similar to Rafael J. Wysocki report. It's full reproductible
> and appears when playing mp3's in totem.
> 
> debian:/home/michal# cat /var/log/kern.log | grep -c "Bad page state
> at free_hot_cold_page"

Please let me know if it's not fixed by:

--- 2.6.15-rc1-mm2/sound/core/memalloc.c	2005-11-12 09:01:28.000000000 +0000
+++ linux/sound/core/memalloc.c	2005-11-19 19:03:32.000000000 +0000
@@ -197,6 +197,7 @@ void *snd_malloc_pages(size_t size, gfp_
 
 	snd_assert(size > 0, return NULL);
 	snd_assert(gfp_flags != 0, return NULL);
+	gfp_flags |= __GFP_COMP;	/* compound page lets parts be mapped */
 	pg = get_order(size);
 	if ((res = (void *) __get_free_pages(gfp_flags, pg)) != NULL) {
 		mark_pages(virt_to_page(res), pg);
@@ -241,6 +242,7 @@ static void *snd_malloc_dev_pages(struct
 	snd_assert(dma != NULL, return NULL);
 	pg = get_order(size);
 	gfp_flags = GFP_KERNEL
+		| __GFP_COMP	/* compound page lets parts be mapped */
 		| __GFP_NORETRY /* don't trigger OOM-killer */
 		| __GFP_NOWARN; /* no stack trace print - this call is non-critical */
 	res = dma_alloc_coherent(dev, PAGE_SIZE << pg, dma, gfp_flags);

Re: 2.6.15-rc1-mm2

[Michal Piotrowski]

Hi,

On 20/11/05, Hugh Dickins <hugh@veritas.com> wrote:
> On Sun, 20 Nov 2005, Michal Piotrowski wrote:
> >
> > It looks similar to Rafael J. Wysocki report. It's full reproductible
> > and appears when playing mp3's in totem.
> >
> > debian:/home/michal# cat /var/log/kern.log | grep -c "Bad page state
> > at free_hot_cold_page"
>
> Please let me know if it's not fixed by:
>
> --- 2.6.15-rc1-mm2/sound/core/memalloc.c        2005-11-12 09:01:28.000000000 +0000
> +++ linux/sound/core/memalloc.c 2005-11-19 19:03:32.000000000 +0000
> @@ -197,6 +197,7 @@ void *snd_malloc_pages(size_t size, gfp_
>
>         snd_assert(size > 0, return NULL);
>         snd_assert(gfp_flags != 0, return NULL);
> +       gfp_flags |= __GFP_COMP;        /* compound page lets parts be mapped */
>         pg = get_order(size);
>         if ((res = (void *) __get_free_pages(gfp_flags, pg)) != NULL) {
>                 mark_pages(virt_to_page(res), pg);
> @@ -241,6 +242,7 @@ static void *snd_malloc_dev_pages(struct
>         snd_assert(dma != NULL, return NULL);
>         pg = get_order(size);
>         gfp_flags = GFP_KERNEL
> +               | __GFP_COMP    /* compound page lets parts be mapped */
>                 | __GFP_NORETRY /* don't trigger OOM-killer */
>                 | __GFP_NOWARN; /* no stack trace print - this call is non-critical */
>         res = dma_alloc_coherent(dev, PAGE_SIZE << pg, dma, gfp_flags);
>

Patch has fixed problem. Thanks.

Regards,
Michal Piotrowski

[PATCH 06/16] readahead: call scheme

[Wu Fengguang]

[-- Attachment #1: readahead-call-scheme.patch --]
[-- Type: text/plain, Size: 12914 bytes --]

An new page flag PG_readahead is introduced as a look-ahead mark.
The look-ahead mark corresponds to `ahead_start' of the current logic.

The read-ahead logic is called when
        - read reaches a look-ahead mark;
        - read on a non-present page.

And ra_access() is called on every page reference to maintain the cache_hit
counter.

This scheme has the following benefits:
        - makes all stateful/stateless methods happy;
        - eliminates the cache hit problem naturally;
        - lives in harmony with application managed read-aheads via
          fadvise/madvise.

Signed-off-by: Wu Fengguang <wfg@mail.ustc.edu.cn>
---

 include/linux/mm.h         |    7 +
 include/linux/page-flags.h |    5 +
 mm/filemap.c               |   66 ++++++++++++++---
 mm/readahead.c             |  172 +++++++++++++++++++++++++++++++++++++++++++++
 4 files changed, 239 insertions(+), 11 deletions(-)

--- linux-2.6.14-mm1.orig/include/linux/page-flags.h
+++ linux-2.6.14-mm1/include/linux/page-flags.h
@@ -77,6 +77,7 @@
 #define PG_nosave_free		18	/* Free, should not be written */
 #define PG_uncached		19	/* Page has been mapped as uncached */
 #define PG_activate		20	/* delayed activate */
+#define PG_readahead		21	/* check readahead when reading this page */
 
 /*
  * Global page accounting.  One instance per CPU.  Only unsigned longs are
@@ -315,6 +316,10 @@ extern void __mod_page_state(unsigned lo
 #define TestClearPageActivate(page) test_and_clear_bit(PG_activate, &(page)->flags)
 #define TestSetPageActivate(page) test_and_set_bit(PG_activate, &(page)->flags)
 
+#define PageReadahead(page)	test_bit(PG_readahead, &(page)->flags)
+#define SetPageReadahead(page)	set_bit(PG_readahead, &(page)->flags)
+#define TestClearPageReadahead(page) test_and_clear_bit(PG_readahead, &(page)->flags)
+
 struct page;	/* forward declaration */
 
 int test_clear_page_dirty(struct page *page);
--- linux-2.6.14-mm1.orig/include/linux/mm.h
+++ linux-2.6.14-mm1/include/linux/mm.h
@@ -985,6 +985,13 @@ unsigned long page_cache_readahead(struc
 void handle_ra_miss(struct address_space *mapping, 
 		    struct file_ra_state *ra, pgoff_t offset);
 unsigned long max_sane_readahead(unsigned long nr);
+unsigned long
+page_cache_readahead_adaptive(struct address_space *mapping,
+			struct file_ra_state *ra, struct file *filp,
+			struct page *prev_page, struct page *page,
+			pgoff_t first_index,
+			pgoff_t index, pgoff_t last_index);
+void fastcall ra_access(struct file_ra_state *ra, struct page *page);
 
 /* Do stack extension */
 extern int expand_stack(struct vm_area_struct *vma, unsigned long address);
--- linux-2.6.14-mm1.orig/mm/filemap.c
+++ linux-2.6.14-mm1/mm/filemap.c
@@ -724,6 +724,8 @@ grab_cache_page_nowait(struct address_sp
 
 EXPORT_SYMBOL(grab_cache_page_nowait);
 
+extern int readahead_ratio;
+
 /*
  * This is a generic file read routine, and uses the
  * mapping->a_ops->readpage() function for the actual low-level
@@ -751,10 +753,12 @@ void do_generic_mapping_read(struct addr
 	unsigned long prev_index;
 	loff_t isize;
 	struct page *cached_page;
+	struct page *prev_page;
 	int error;
 	struct file_ra_state ra = *_ra;
 
 	cached_page = NULL;
+	prev_page = NULL;
 	index = *ppos >> PAGE_CACHE_SHIFT;
 	next_index = index;
 	prev_index = ra.prev_page;
@@ -783,16 +787,36 @@ void do_generic_mapping_read(struct addr
 		nr = nr - offset;
 
 		cond_resched();
-		if (index == next_index)
+
+		if (readahead_ratio <= 9 && index == next_index)
 			next_index = page_cache_readahead(mapping, &ra, filp,
 					index, last_index - index);
 
 find_page:
 		page = find_get_page(mapping, index);
+		if (readahead_ratio > 9) {
+			if (unlikely(page == NULL)) {
+				page_cache_readahead_adaptive(mapping, &ra,
+						filp, prev_page, NULL,
+						*ppos >> PAGE_CACHE_SHIFT,
+						index, last_index);
+				page = find_get_page(mapping, index);
+			} else if (PageReadahead(page)) {
+				page_cache_readahead_adaptive(mapping, &ra,
+						filp, prev_page, page,
+						*ppos >> PAGE_CACHE_SHIFT,
+						index, last_index);
+			}
+		}
 		if (unlikely(page == NULL)) {
-			handle_ra_miss(mapping, &ra, index);
+			if (readahead_ratio <= 9)
+				handle_ra_miss(mapping, &ra, index);
 			goto no_cached_page;
 		}
+		if (prev_page)
+			page_cache_release(prev_page);
+		prev_page = page;
+		ra_access(&ra, page);
 		if (!PageUptodate(page))
 			goto page_not_up_to_date;
 page_ok:
@@ -808,8 +832,9 @@ page_ok:
 		 * When (part of) the same page is read multiple times
 		 * in succession, only mark it as accessed the first time.
 		 */
-		if (prev_index != index)
+		if (prev_index != index) {
 			mark_page_accessed(page);
+		}
 		prev_index = index;
 
 		/*
@@ -827,7 +852,6 @@ page_ok:
 		index += offset >> PAGE_CACHE_SHIFT;
 		offset &= ~PAGE_CACHE_MASK;
 
-		page_cache_release(page);
 		if (ret == nr && desc->count)
 			continue;
 		goto out;
@@ -839,7 +863,6 @@ page_not_up_to_date:
 		/* Did it get unhashed before we got the lock? */
 		if (!page->mapping) {
 			unlock_page(page);
-			page_cache_release(page);
 			continue;
 		}
 
@@ -864,7 +887,6 @@ readpage:
 					 * invalidate_inode_pages got it
 					 */
 					unlock_page(page);
-					page_cache_release(page);
 					goto find_page;
 				}
 				unlock_page(page);
@@ -885,7 +907,6 @@ readpage:
 		isize = i_size_read(inode);
 		end_index = (isize - 1) >> PAGE_CACHE_SHIFT;
 		if (unlikely(!isize || index > end_index)) {
-			page_cache_release(page);
 			goto out;
 		}
 
@@ -894,7 +915,6 @@ readpage:
 		if (index == end_index) {
 			nr = ((isize - 1) & ~PAGE_CACHE_MASK) + 1;
 			if (nr <= offset) {
-				page_cache_release(page);
 				goto out;
 			}
 		}
@@ -904,7 +924,6 @@ readpage:
 readpage_error:
 		/* UHHUH! A synchronous read error occurred. Report it */
 		desc->error = error;
-		page_cache_release(page);
 		goto out;
 
 no_cached_page:
@@ -929,15 +948,22 @@ no_cached_page:
 		}
 		page = cached_page;
 		cached_page = NULL;
+		if (prev_page)
+			page_cache_release(prev_page);
+		prev_page = page;
 		goto readpage;
 	}
 
 out:
 	*_ra = ra;
+	if (readahead_ratio > 9)
+		_ra->prev_page = prev_index;
 
 	*ppos = ((loff_t) index << PAGE_CACHE_SHIFT) + offset;
 	if (cached_page)
 		page_cache_release(cached_page);
+	if (prev_page)
+		page_cache_release(prev_page);
 	if (filp)
 		file_accessed(filp);
 }
@@ -1235,19 +1261,33 @@ retry_all:
 	 *
 	 * For sequential accesses, we use the generic readahead logic.
 	 */
-	if (VM_SequentialReadHint(area))
+	if (readahead_ratio <= 9 && VM_SequentialReadHint(area))
 		page_cache_readahead(mapping, ra, file, pgoff, 1);
 
+
 	/*
 	 * Do we have something in the page cache already?
 	 */
 retry_find:
 	page = find_get_page(mapping, pgoff);
+	if (VM_SequentialReadHint(area) && readahead_ratio > 9) {
+		if (!page) {
+			page_cache_readahead_adaptive(mapping, ra,
+						file, NULL, NULL,
+						pgoff, pgoff, pgoff + 1);
+			page = find_get_page(mapping, pgoff);
+		} else if (PageReadahead(page)) {
+			page_cache_readahead_adaptive(mapping, ra,
+						file, NULL, page,
+						pgoff, pgoff, pgoff + 1);
+		}
+	}
 	if (!page) {
 		unsigned long ra_pages;
 
 		if (VM_SequentialReadHint(area)) {
-			handle_ra_miss(mapping, ra, pgoff);
+			if (readahead_ratio <= 9)
+				handle_ra_miss(mapping, ra, pgoff);
 			goto no_cached_page;
 		}
 		ra->mmap_miss++;
@@ -1284,6 +1324,8 @@ retry_find:
 	if (!did_readaround)
 		ra->mmap_hit++;
 
+	ra_access(ra, page);
+
 	/*
 	 * Ok, found a page in the page cache, now we need to check
 	 * that it's up-to-date.
@@ -1298,6 +1340,8 @@ success:
 	mark_page_accessed(page);
 	if (type)
 		*type = majmin;
+	if (readahead_ratio > 9)
+		ra->prev_page = page->index;
 	return page;
 
 outside_data_content:
--- linux-2.6.14-mm1.orig/mm/readahead.c
+++ linux-2.6.14-mm1/mm/readahead.c
@@ -20,6 +20,43 @@
 #define MAX_RA_PAGES	KB(VM_MAX_READAHEAD)
 #define MIN_RA_PAGES	KB(VM_MIN_READAHEAD)
 
+/* Detailed classification of read-ahead behaviors. */
+#define RA_CLASS_SHIFT 3
+#define RA_CLASS_MASK  ((1 << RA_CLASS_SHIFT) - 1)
+enum ra_class {
+	RA_CLASS_ALL,
+	RA_CLASS_NEWFILE,
+	RA_CLASS_STATE,
+	RA_CLASS_CONTEXT,
+	RA_CLASS_CONTEXT_ACCELERATED,
+	RA_CLASS_BACKWARD,
+	RA_CLASS_RANDOM_THRASHING,
+	RA_CLASS_RANDOM_SEEK,
+	RA_CLASS_END,
+};
+
+/* Read-ahead events to be accounted. */
+enum ra_event {
+	RA_EVENT_CACHE_MISS,		/* read cache misses */
+	RA_EVENT_READRANDOM,		/* random reads */
+	RA_EVENT_IO_CONGESTION,		/* io congestion */
+	RA_EVENT_IO_CACHE_HIT,		/* canceled io due to cache hit */
+	RA_EVENT_IO_BLOCK,		/* read on locked page */
+
+	RA_EVENT_READAHEAD,		/* read-ahead issued */
+	RA_EVENT_READAHEAD_HIT,		/* read-ahead page hit */
+	RA_EVENT_LOOKAHEAD,		/* look-ahead issued */
+	RA_EVENT_LOOKAHEAD_HIT,		/* look-ahead mark hit */
+	RA_EVENT_LOOKAHEAD_NOACTION,	/* look-ahead mark ignored */
+	RA_EVENT_READAHEAD_EOF,		/* read-ahead reaches EOF */
+	RA_EVENT_READAHEAD_SHRINK,	/* ra_size decreased, reflects var. */
+	RA_EVENT_READAHEAD_THRASHING,	/* read-ahead thrashing happened */
+	RA_EVENT_READAHEAD_MUTILATE,	/* read-ahead request mutilated */
+	RA_EVENT_READAHEAD_RESCUE,	/* read-ahead rescued */
+
+	RA_EVENT_END
+};
+
 /*
  * Debug facilities.
  */
@@ -310,9 +347,11 @@ __do_page_cache_readahead(struct address
 
 		page = radix_tree_lookup(&mapping->page_tree, page_offset);
 		if (page) {
+#ifdef READAHEAD_STREAMING
 			if (readahead_ratio > 9 &&
 				page_idx == nr_to_read - lookahead_size)
 				SetPageReadahead(page);
+#endif
 			continue;
 		}
 
@@ -730,3 +769,136 @@ out:
 
 	return nr_pages ? index : 0;
 }
+
+/*
+ * This is the entry point of the adaptive read-ahead logic.
+ *
+ * It is only called on two conditions:
+ * 1. page == NULL
+ *    A cache miss happened, it can be either a random read or a sequential one.
+ * 2. page != NULL
+ *    There is a look-ahead mark(PG_readahead) from a previous sequential read.
+ *    It's time to do some checking and submit the next read-ahead IO.
+ *
+ * That has the merits of:
+ * - makes all stateful/stateless methods happy;
+ * - eliminates the cache hit problem naturally;
+ * - lives in harmony with application managed read-aheads via fadvise/madvise.
+ */
+unsigned long
+page_cache_readahead_adaptive(struct address_space *mapping,
+			struct file_ra_state *ra, struct file *filp,
+			struct page *prev_page, struct page *page,
+			pgoff_t begin_index,
+			pgoff_t index, pgoff_t end_index)
+{
+	unsigned long size;
+	unsigned long ra_min;
+	unsigned long ra_max;
+	int ret;
+
+	if (page) {
+		if(!TestClearPageReadahead(page))
+			return 0;
+		if (bdi_read_congested(mapping->backing_dev_info))
+			return 0;
+	}
+
+	if (page)
+		ra_account(ra, RA_EVENT_LOOKAHEAD_HIT,
+				ra->readahead_index - ra->lookahead_index);
+	else if (index)
+		ra_account(ra, RA_EVENT_CACHE_MISS, end_index - begin_index);
+
+	size = end_index - index;
+	get_readahead_bounds(ra, &ra_min, &ra_max);
+
+	/* readahead disabled? */
+	if (unlikely(!ra_min || !readahead_ratio)) {
+		size = max_sane_readahead(size);
+		goto readit;
+	}
+
+	/*
+	 * Start of file.
+	 */
+	if (index == 0)
+		return newfile_readahead(mapping, filp, ra, end_index, ra_min);
+
+	/*
+	 * State based sequential read-ahead.
+	 */
+	if ((readahead_ratio % 5) == 0 &&
+		index == ra->lookahead_index &&
+		(page || index == ra->readahead_index) &&
+		(ra_cache_hit_ok(ra) ||
+		 end_index - begin_index >= ra_max))
+		return state_based_readahead(mapping, filp, ra, page, ra_max);
+
+	/*
+	 * Backward read-ahead.
+	 */
+	if (try_read_backward(ra, begin_index, end_index, size, ra_min, ra_max))
+		return ra_dispatch(ra, mapping, filp);
+
+	/*
+	 * Context based sequential read-ahead.
+	 */
+	ret = try_context_based_readahead(mapping, ra, prev_page, page,
+						index, ra_min, ra_max);
+	if (ret > 0)
+		return ra_dispatch(ra, mapping, filp);
+	if (ret < 0)
+		return 0;
+
+	/* No action on look ahead time? */
+	if (page) {
+		ra_account(ra, RA_EVENT_LOOKAHEAD_NOACTION,
+					ra->readahead_index - index);
+		return 0;
+	}
+
+	/*
+	 * Random read that follows a sequential one.
+	 */
+	if (try_random_readahead(ra, index, size, ra_max))
+		return ra_dispatch(ra, mapping, filp);
+
+	/*
+	 * Random read.
+	 */
+	if (size > ra_max)
+		size = ra_max;
+
+readit:
+	size = __do_page_cache_readahead(mapping, filp, index, size, 0);
+
+	ra_account(ra, RA_EVENT_READRANDOM, size);
+	dprintk("readrandom(ino=%lu, pages=%lu, index=%lu-%lu-%lu) = %lu\n",
+			mapping->host->i_ino, mapping->nrpages,
+			begin_index, index, end_index, size);
+
+	return size;
+}
+
+/*
+ * Call me!
+ */
+void fastcall ra_access(struct file_ra_state *ra, struct page *page)
+{
+	if (page->flags & ((1 << PG_active)   |
+			   (1 << PG_activate) |
+			   (1 << PG_referenced)))
+		return;
+
+	if (!ra_has_index(ra, page->index))
+		return;
+
+	ra->cache_hit++;
+
+	if (page->index >= ra->ra_index)
+		ra_account(ra, RA_EVENT_READAHEAD_HIT, 1);
+	else
+		ra_account(ra, RA_EVENT_READAHEAD_HIT, -1);
+}
+

--

[PATCH 07/16] readahead: tunable parameters

[Wu Fengguang]

[-- Attachment #1: readahead-parameter.patch --]
[-- Type: text/plain, Size: 8435 bytes --]

- new entry in /proc/sys/vm/readahead_ratio with default value of 50;
- new entry in /proc/sys/vm/readahead_hit_rate with default value of 2;
- new entry in /proc/sys/vm/readahead_live_chunk with default value of 2M;
- limit mmap read-around size to 256kb;
- dynamic minimal/initial read-ahead size.

Signed-off-by: Wu Fengguang <wfg@mail.ustc.edu.cn>
---

 Documentation/sysctl/vm.txt |   51 ++++++++++++++++++++++++++++++++++++++++++++
 include/linux/mm.h          |    5 +++-
 include/linux/sysctl.h      |    3 ++
 kernel/sysctl.c             |   34 +++++++++++++++++++++++++++++
 mm/filemap.c                |    7 ++++++
 mm/readahead.c              |   41 ++++++++++++++++++++++++++++++++++-
 6 files changed, 139 insertions(+), 2 deletions(-)

--- linux-2.6.14-mm1.orig/Documentation/sysctl/vm.txt
+++ linux-2.6.14-mm1/Documentation/sysctl/vm.txt
@@ -27,6 +27,9 @@ Currently, these files are in /proc/sys/
 - laptop_mode
 - block_dump
 - swap_prefetch
+- readahead_ratio
+- readahead_hit_rate
+- readahead_live_chunk
 
 ==============================================================
 
@@ -114,3 +117,51 @@ except when laptop_mode is enabled and t
 Setting it to 0 disables prefetching entirely.
 
 The default value is dependant on ramsize.
+
+==============================================================
+
+readahead_ratio
+
+This limits read-ahead size to percent of the thrashing-threshold.
+The thrashing-threshold is dynamicly estimated according to the
+_history_ read speed and system load, and used to limit the
+_future_ read-ahead request size.
+
+Set it to a low value if you have not enough memory to counteract
+the I/O load fluctuations. But if there's plenty of memory, set it
+to a larger value might help increase read speed. Also note that a
+value >= 80 activates mandatory thrashing protection(see
+readahead_live_chunk).
+
+The default value is 50.
+
+==============================================================
+
+readahead_hit_rate
+
+This is the max allowed value of (read-ahead-pages : accessed-pages).
+If the previous read-ahead request has bad hit rate, kernel will be
+very conservative to issue the next read-ahead.
+
+A large value helps speedup some sparse access patterns, at the cost
+of more memory consumption. It is recommended to keep the value below
+(max-readahead-pages / 8).
+
+The default value is 2.
+
+==============================================================
+
+readahead_live_chunk
+
+In a file server, there are typically one or more sequential
+readers working on a file. The kernel can detect most live
+chunks(a sequence of pages to be accessed by an active reader),
+and save them for their imminent readers. This is called
+mandatory thrashing protection, and is only in effect when
+(readahead_ratio >= 80).
+
+This parameter controls the max allowed chunk size, i.e. the max
+number of pages pinned for an active reader.
+
+The default value is 2MB size of pages. That is 512 on most archs.
+Increase it if you have enough memory.
--- linux-2.6.14-mm1.orig/include/linux/mm.h
+++ linux-2.6.14-mm1/include/linux/mm.h
@@ -968,11 +968,14 @@ extern int filemap_populate(struct vm_ar
 int write_one_page(struct page *page, int wait);
 
 /* readahead.c */
-#define VM_MAX_READAHEAD	128	/* kbytes */
+#define VM_MAX_READAHEAD	1024	/* kbytes */
 #define VM_MIN_READAHEAD	16	/* kbytes (includes current page) */
 #define VM_MAX_CACHE_HIT    	256	/* max pages in a row in cache before
 					 * turning readahead off */
 
+/* turn on read-ahead thrashing protection if (readahead_ratio >= ##) */
+#define VM_READAHEAD_PROTECT_RATIO	80
+
 int do_page_cache_readahead(struct address_space *mapping, struct file *filp,
 			pgoff_t offset, unsigned long nr_to_read);
 int force_page_cache_readahead(struct address_space *mapping, struct file *filp,
--- linux-2.6.14-mm1.orig/include/linux/sysctl.h
+++ linux-2.6.14-mm1/include/linux/sysctl.h
@@ -182,6 +182,9 @@ enum
 	VM_LEGACY_VA_LAYOUT=27, /* legacy/compatibility virtual address space layout */
 	VM_SWAP_TOKEN_TIMEOUT=28, /* default time for token time out */
 	VM_SWAP_PREFETCH=29,	/* int: amount to swap prefetch */
+	VM_READAHEAD_RATIO=30, /* percent of read-ahead size to thrashing-threshold */
+	VM_READAHEAD_HIT_RATE=31, /* one accessed page legitimizes so many read-ahead pages */
+	VM_READAHEAD_LIVE_CHUNK=32, /* pin no more than that many pages for a live reader */
 };
 
 
--- linux-2.6.14-mm1.orig/kernel/sysctl.c
+++ linux-2.6.14-mm1/kernel/sysctl.c
@@ -67,6 +67,9 @@ extern int min_free_kbytes;
 extern int printk_ratelimit_jiffies;
 extern int printk_ratelimit_burst;
 extern int pid_max_min, pid_max_max;
+extern int readahead_ratio;
+extern int readahead_hit_rate;
+extern int readahead_live_chunk;
 
 #if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86)
 int unknown_nmi_panic;
@@ -670,6 +673,7 @@ static ctl_table kern_table[] = {
 /* Constants for minimum and maximum testing in vm_table.
    We use these as one-element integer vectors. */
 static int zero;
+static int one = 1;
 static int one_hundred = 100;
 
 
@@ -869,6 +873,36 @@ static ctl_table vm_table[] = {
 	},
 #endif
 #endif
+	{
+		.ctl_name	= VM_READAHEAD_RATIO,
+		.procname	= "readahead_ratio",
+		.data		= &readahead_ratio,
+		.maxlen		= sizeof(readahead_ratio),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec,
+		.strategy	= &sysctl_intvec,
+		.extra1		= &zero,
+	},
+	{
+		.ctl_name	= VM_READAHEAD_HIT_RATE,
+		.procname	= "readahead_hit_rate",
+		.data		= &readahead_hit_rate,
+		.maxlen		= sizeof(readahead_hit_rate),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec,
+		.strategy	= &sysctl_intvec,
+		.extra1		= &one,
+	},
+	{
+		.ctl_name	= VM_READAHEAD_LIVE_CHUNK,
+		.procname	= "readahead_live_chunk",
+		.data		= &readahead_live_chunk,
+		.maxlen		= sizeof(readahead_live_chunk),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec,
+		.strategy	= &sysctl_intvec,
+		.extra1		= &zero,
+	},
 	{ .ctl_name = 0 }
 };
 
--- linux-2.6.14-mm1.orig/mm/filemap.c
+++ linux-2.6.14-mm1/mm/filemap.c
@@ -1312,6 +1312,13 @@ retry_find:
 		if (ra_pages) {
 			pgoff_t start = 0;
 
+			/*
+			 * Max read-around should be much smaller than
+			 * max read-ahead.
+			 * How about adding a tunable parameter for this?
+			 */
+			if (ra_pages > 64)
+				ra_pages = 64;
 			if (pgoff > ra_pages / 2)
 				start = pgoff - ra_pages / 2;
 			do_page_cache_readahead(mapping, file, start, ra_pages);
--- linux-2.6.14-mm1.orig/mm/readahead.c
+++ linux-2.6.14-mm1/mm/readahead.c
@@ -15,11 +15,29 @@
 #include <linux/backing-dev.h>
 #include <linux/pagevec.h>
 
-/* The default max/min read-ahead pages. */
+/* The default number of max/min read-ahead pages. */
 #define KB(size)	(((size)*1024 + PAGE_CACHE_SIZE-1) / PAGE_CACHE_SIZE)
 #define MAX_RA_PAGES	KB(VM_MAX_READAHEAD)
 #define MIN_RA_PAGES	KB(VM_MIN_READAHEAD)
 
+/* In laptop mode, poll delayed look-ahead on every ## pages read. */
+#define LAPTOP_POLL_INTERVAL 16
+
+/* Set look-ahead size to 1/# of the thrashing-threshold. */
+#define LOOKAHEAD_RATIO 8
+
+/* Set read-ahead size to ##% of the thrashing-threshold. */
+int readahead_ratio = 50;
+EXPORT_SYMBOL(readahead_ratio);
+
+/* Readahead as long as cache hit ratio keeps above 1/##. */
+int readahead_hit_rate = 2;
+EXPORT_SYMBOL(readahead_hit_rate);
+
+/* Scan backward ## pages to find a live reader. */
+int readahead_live_chunk = 2 * MAX_RA_PAGES;
+EXPORT_SYMBOL(readahead_live_chunk);
+
 /* Detailed classification of read-ahead behaviors. */
 #define RA_CLASS_SHIFT 3
 #define RA_CLASS_MASK  ((1 << RA_CLASS_SHIFT) - 1)
@@ -771,6 +789,27 @@ out:
 }
 
 /*
+ * ra_size is mainly determined by:
+ * 1. sequential-start: min(MIN_RA_PAGES + (pages>>14), KB(128))
+ * 2. sequential-max:	min(ra->ra_pages, 0xFFFF)
+ * 3. sequential:	(thrashing-threshold) * readahead_ratio / 100
+ *
+ * Table of concrete numbers for 4KB page size:
+ *  (inactive + free) (in MB):    4   8   16   32   64  128  256  512 1024
+ *    initial ra_size (in KB):   16  16   16   16   20   24   32   48   64
+ */
+static inline void get_readahead_bounds(struct file_ra_state *ra,
+					unsigned long *ra_min,
+					unsigned long *ra_max)
+{
+	unsigned long pages;
+
+	pages = nr_free_inactive();
+	*ra_max = min(min(pages/2, 0xFFFFUL), ra->ra_pages);
+	*ra_min = min(min(MIN_RA_PAGES + (pages>>14), KB(128)), *ra_max/2);
+}
+
+/*
  * This is the entry point of the adaptive read-ahead logic.
  *
  * It is only called on two conditions:

--

[PATCH 08/16] readahead: state based method

[Wu Fengguang]

[-- Attachment #1: readahead-method-stateful.patch --]
[-- Type: text/plain, Size: 12855 bytes --]

This is the fast code path.

Major steps:
        - estimate a thrashing safe ra_size;
        - assemble the next read-ahead request in file_ra_state;
        - submit it.

Signed-off-by: Wu Fengguang <wfg@mail.ustc.edu.cn>
---

 include/linux/fs.h |    8 +
 mm/readahead.c     |  340 +++++++++++++++++++++++++++++++++++++++++++++++++++++
 mm/swap.c          |    3 
 mm/vmscan.c        |    5 
 4 files changed, 355 insertions(+), 1 deletion(-)

--- linux-2.6.14-mm1.orig/include/linux/fs.h
+++ linux-2.6.14-mm1/include/linux/fs.h
@@ -569,13 +569,19 @@ struct file_ra_state {
 	unsigned long start;		/* Current window */
 	unsigned long size;
 	unsigned long flags;		/* ra flags RA_FLAG_xxx*/
-	unsigned long cache_hit;	/* cache hit count*/
+	uint64_t      cache_hit;	/* cache hit count*/
 	unsigned long prev_page;	/* Cache last read() position */
 	unsigned long ahead_start;	/* Ahead window */
 	unsigned long ahead_size;
 	unsigned long ra_pages;		/* Maximum readahead window */
 	unsigned long mmap_hit;		/* Cache hit stat for mmap accesses */
 	unsigned long mmap_miss;	/* Cache miss stat for mmap accesses */
+
+	unsigned long age;
+	pgoff_t la_index;
+	pgoff_t ra_index;
+	pgoff_t lookahead_index;
+	pgoff_t readahead_index;
 };
 #define RA_FLAG_MISS 0x01	/* a cache miss occured against this file */
 #define RA_FLAG_INCACHE 0x02	/* file is already in cache */
--- linux-2.6.14-mm1.orig/mm/vmscan.c
+++ linux-2.6.14-mm1/mm/vmscan.c
@@ -406,6 +406,8 @@ cannot_free:
 	return 0;
 }
 
+DECLARE_PER_CPU(unsigned long, smooth_aging);
+
 /*
  * shrink_list adds the number of reclaimed pages to sc->nr_reclaimed
  */
@@ -453,6 +455,8 @@ static int shrink_list(struct list_head 
 		/* In active use or really unfreeable?  Activate it. */
 		if (referenced && page_mapping_inuse(page))
 			goto activate_locked;
+		if (!referenced)
+			__get_cpu_var(smooth_aging)++;
 
 #ifdef CONFIG_SWAP
 		/*
@@ -991,6 +995,7 @@ refill_inactive_zone(struct zone *zone, 
 				list_add(&page->lru, &l_active);
 				continue;
 			}
+			__get_cpu_var(smooth_aging)++;
 		}
 		list_add(&page->lru, &l_inactive);
 	}
--- linux-2.6.14-mm1.orig/mm/swap.c
+++ linux-2.6.14-mm1/mm/swap.c
@@ -112,6 +112,8 @@ void fastcall activate_page(struct page 
 	spin_unlock_irq(&zone->lru_lock);
 }
 
+DECLARE_PER_CPU(unsigned long, smooth_aging);
+
 /*
  * Mark a page as having seen activity.
  *
@@ -126,6 +128,7 @@ void fastcall mark_page_accessed(struct 
 		ClearPageReferenced(page);
 	} else if (!PageReferenced(page)) {
 		SetPageReferenced(page);
+		__get_cpu_var(smooth_aging)++;
 	}
 }
 
--- linux-2.6.14-mm1.orig/mm/readahead.c
+++ linux-2.6.14-mm1/mm/readahead.c
@@ -38,6 +38,12 @@ EXPORT_SYMBOL(readahead_hit_rate);
 int readahead_live_chunk = 2 * MAX_RA_PAGES;
 EXPORT_SYMBOL(readahead_live_chunk);
 
+/* Analog to zone->nr_page_aging.
+ * But mainly increased on fresh page references, so is much more smoother.
+ */
+DEFINE_PER_CPU(unsigned long, smooth_aging);
+EXPORT_PER_CPU_SYMBOL(smooth_aging);
+
 /* Detailed classification of read-ahead behaviors. */
 #define RA_CLASS_SHIFT 3
 #define RA_CLASS_MASK  ((1 << RA_CLASS_SHIFT) - 1)
@@ -789,6 +795,340 @@ out:
 }
 
 /*
+ * State based calculation of read-ahead request.
+ *
+ * This figure shows the meaning of file_ra_state members:
+ *
+ *             chunk A                            chunk B
+ *  +---------------------------+-------------------------------------------+
+ *  |             #             |                   #                       |
+ *  +---------------------------+-------------------------------------------+
+ *                ^             ^                   ^                       ^
+ *              la_index      ra_index     lookahead_index         readahead_index
+ */
+
+/*
+ * The global effective length of the inactive_list(s).
+ */
+static unsigned long nr_free_inactive(void)
+{
+	unsigned int i;
+	unsigned long sum = 0;
+	struct zone *zones = NODE_DATA(numa_node_id())->node_zones;
+
+	for (i = 0; i < MAX_NR_ZONES; i++)
+		sum += zones[i].nr_inactive +
+			zones[i].free_pages - zones[i].pages_low;
+
+	return sum;
+}
+
+/*
+ * A much smoother analog to nr_page_aging.
+ */
+static unsigned long nr_smooth_aging(void)
+{
+	unsigned long cpu;
+	unsigned long sum = 0;
+	cpumask_t mask = node_to_cpumask(numa_node_id());
+
+	for_each_cpu_mask(cpu, mask)
+		sum += per_cpu(smooth_aging, cpu);
+
+	return sum;
+}
+
+/*
+ * Set class of read-ahead
+ */
+static inline void set_ra_class(struct file_ra_state *ra,
+				enum ra_class ra_class)
+{
+	unsigned long FLAGS_MASK;
+	unsigned long flags;
+	unsigned long old_ra_class;
+
+	FLAGS_MASK = ~(RA_CLASS_MASK | (RA_CLASS_MASK << RA_CLASS_SHIFT));
+	flags = ra->flags & FLAGS_MASK;
+
+	old_ra_class = (ra->flags & RA_CLASS_MASK) << RA_CLASS_SHIFT;
+
+	ra->flags = flags | old_ra_class | ra_class;
+}
+
+/*
+ * The 64bit cache_hit stores three accumulated value and one counter value.
+ * MSB                                                                   LSB
+ * 3333333333333333 : 2222222222222222 : 1111111111111111 : 0000000000000000
+ */
+static inline int ra_cache_hit(struct file_ra_state *ra, int nr)
+{
+	return (ra->cache_hit >> (nr * 16)) & 0xFFFF;
+}
+
+/*
+ * Something like:
+ * ra_cache_hit(ra, 1) += ra_cache_hit(ra, 0);
+ * ra_cache_hit(ra, 0) = 0;
+ */
+static inline void ra_addup_cache_hit(struct file_ra_state *ra)
+{
+	int n;
+
+	n = ra_cache_hit(ra, 0);
+	ra->cache_hit -= n;
+	n <<= 16;
+	ra->cache_hit += n;
+}
+
+/*
+ * The read-ahead is deemed success if cache-hit-rate > 50%.
+ */
+static inline int ra_cache_hit_ok(struct file_ra_state *ra)
+{
+	return ra_cache_hit(ra, 0) * readahead_hit_rate >=
+					(ra->lookahead_index - ra->la_index);
+}
+
+/*
+ * Check if @index falls in the ra request.
+ */
+static inline int ra_has_index(struct file_ra_state *ra, pgoff_t index)
+{
+	if (index < ra->la_index || index >= ra->readahead_index)
+		return 0;
+
+	if (index >= ra->ra_index)
+		return 1;
+	else
+		return -1;
+}
+
+/*
+ * Prepare file_ra_state for a new read-ahead sequence.
+ */
+static inline void ra_state_init(struct file_ra_state *ra,
+				pgoff_t la_index, pgoff_t ra_index)
+{
+	ra_addup_cache_hit(ra);
+	ra->cache_hit <<= 16;
+	ra->lookahead_index = la_index;
+	ra->readahead_index = ra_index;
+}
+
+/*
+ * Take down a new read-ahead request in file_ra_state.
+ */
+static inline void ra_state_update(struct file_ra_state *ra,
+				unsigned long ra_size, unsigned long la_size)
+{
+#ifdef DEBUG_READAHEAD
+	unsigned long old_ra = ra->readahead_index - ra->ra_index;
+	if (ra_size < old_ra && ra_cache_hit(ra, 0))
+		ra_account(ra, RA_EVENT_READAHEAD_SHRINK, old_ra - ra_size);
+#endif
+	ra_addup_cache_hit(ra);
+	ra->ra_index = ra->readahead_index;
+	ra->la_index = ra->lookahead_index;
+	ra->readahead_index += ra_size;
+	ra->lookahead_index = ra->readahead_index - la_size;
+	ra->age = nr_smooth_aging();
+}
+
+/*
+ * Adjust the read-ahead request in file_ra_state.
+ */
+static inline void ra_state_adjust(struct file_ra_state *ra,
+				unsigned long ra_size, unsigned long la_size)
+{
+	ra->readahead_index = ra->ra_index + ra_size;
+	ra->lookahead_index = ra->readahead_index - la_size;
+}
+
+/*
+ * Submit IO for the read-ahead request in file_ra_state.
+ */
+static int ra_dispatch(struct file_ra_state *ra,
+			struct address_space *mapping, struct file *filp)
+{
+	pgoff_t eof_index;
+	unsigned long ra_size;
+	unsigned long la_size;
+	int actual;
+	enum ra_class ra_class;
+
+	ra_class = (ra->flags & RA_CLASS_MASK);
+	BUG_ON(ra_class == 0 || ra_class > RA_CLASS_END);
+
+	eof_index = ((i_size_read(mapping->host) - 1) >> PAGE_CACHE_SHIFT) + 1;
+	ra_size = ra->readahead_index - ra->ra_index;
+	la_size = ra->readahead_index - ra->lookahead_index;
+
+	/* Snap to EOF. */
+	if (unlikely(ra->ra_index >= eof_index))
+		return 0;
+	if (ra->readahead_index + ra_size / 2 > eof_index) {
+		if (ra_class == RA_CLASS_CONTEXT_ACCELERATED &&
+				eof_index > ra->lookahead_index + 1)
+			la_size = eof_index - ra->lookahead_index;
+		else
+			la_size = 0;
+		ra_size = eof_index - ra->ra_index;
+		ra_state_adjust(ra, ra_size, la_size);
+	}
+
+	actual = __do_page_cache_readahead(mapping, filp,
+					ra->ra_index, ra_size, la_size);
+
+#ifdef READAHEAD_STREAMING
+	if (actual < ra_size) {
+		struct page *page = find_page(mapping, ra->ra_index + actual);
+		if (page)
+			rescue_pages(page, ra_size);
+	}
+#endif
+
+	if (ra->readahead_index == eof_index)
+		ra_account(ra, RA_EVENT_READAHEAD_EOF, actual);
+	if (la_size)
+		ra_account(ra, RA_EVENT_LOOKAHEAD, la_size);
+	ra_account(ra, RA_EVENT_READAHEAD, actual);
+
+	dprintk("readahead-%s(ino=%lu, index=%lu, ra=%lu+%lu-%lu) = %d\n",
+			ra_class_name[ra_class],
+			mapping->host->i_ino, ra->la_index,
+			ra->ra_index, ra_size, la_size, actual);
+
+	return actual;
+}
+
+/*
+ * Determine the request parameters from primitive values.
+ *
+ * It applies the following rules:
+ *   - Substract ra_size by the old look-ahead to get real safe read-ahead;
+ *   - Set new la_size according to the (still large) ra_size;
+ *   - Apply upper limits;
+ *   - Make sure stream_shift is not too small.
+ *     (So that the next global_shift will not be too small.)
+ *
+ * Input:
+ * ra_size stores the estimated thrashing-threshold.
+ * la_size stores the look-ahead size of previous request.
+ */
+static inline int adjust_rala(unsigned long ra_max,
+				unsigned long *ra_size, unsigned long *la_size)
+{
+	unsigned long stream_shift = *la_size;
+
+	if (*ra_size > *la_size)
+		*ra_size -= *la_size;
+	else
+		return 0;
+
+	*la_size = *ra_size / LOOKAHEAD_RATIO;
+
+	if (*ra_size > ra_max)
+		*ra_size = ra_max;
+	if (*la_size > *ra_size)
+		*la_size = *ra_size;
+
+	stream_shift += (*ra_size - *la_size);
+	if (stream_shift < *ra_size / 4)
+		*la_size -= (*ra_size / 4 - stream_shift);
+
+	return 1;
+}
+
+/*
+ * The function estimates two values:
+ * 1. thrashing-threshold for the current stream
+ *    It is returned to make the next read-ahead request.
+ * 2. the remained space for the current chunk
+ *    It will be checked to ensure that the current chunk is safe.
+ *
+ * The computation will be pretty accurate under heavy load, and will change
+ * vastly with light load(small global_shift), so the grow speed of ra_size
+ * must be limited, and a moderate large stream_shift must be insured.
+ *
+ * This figure illustrates the formula:
+ * While the stream reads stream_shift pages inside the chunks,
+ * the chunks are shifted global_shift pages inside inactive_list.
+ *
+ *      chunk A                    chunk B
+ *                          |<=============== global_shift ================|
+ *  +-------------+         +-------------------+                          |
+ *  |       #     |         |           #       |            inactive_list |
+ *  +-------------+         +-------------------+                     head |
+ *          |---->|         |---------->|
+ *             |                  |
+ *             +-- stream_shift --+
+ */
+static inline unsigned long compute_thrashing_threshold(
+						struct file_ra_state *ra,
+						unsigned long *remain)
+{
+	unsigned long global_size;
+	unsigned long global_shift;
+	unsigned long stream_shift;
+	unsigned long ra_size;
+
+	global_size = nr_free_inactive();
+	global_shift = nr_smooth_aging() - ra->age;
+	stream_shift = ra_cache_hit(ra, 0);
+
+	ra_size = stream_shift *
+			global_size * readahead_ratio / (100 * global_shift);
+
+	if (global_size > global_shift)
+		*remain = stream_shift *
+				(global_size - global_shift) / global_shift;
+	else
+		*remain = 0;
+
+	ddprintk("compute_thrashing_threshold: "
+			"ra=%lu=%lu*%lu/%lu, remain %lu for %lu\n",
+			ra_size, stream_shift, global_size, global_shift,
+			*remain, ra->readahead_index - ra->lookahead_index);
+
+	return ra_size;
+}
+
+/*
+ * Main function for file_ra_state based read-ahead.
+ */
+static inline unsigned long
+state_based_readahead(struct address_space *mapping, struct file *filp,
+			struct file_ra_state *ra, struct page *page,
+			unsigned long ra_max)
+{
+	unsigned long ra_old;
+	unsigned long ra_size;
+	unsigned long la_size;
+	unsigned long remain_space;
+
+	la_size = ra->readahead_index - ra->lookahead_index;
+	ra_old = ra->readahead_index - ra->ra_index;
+	ra_size = compute_thrashing_threshold(ra, &remain_space);
+
+	if (readahead_ratio < VM_READAHEAD_PROTECT_RATIO &&
+			remain_space <= la_size && la_size > 1) {
+		rescue_pages(page, la_size);
+		return 0;
+	}
+
+	if (!adjust_rala(min(ra_max, 2 * ra_old + (ra_max - ra_old) / 16),
+				&ra_size, &la_size))
+		return 0;
+
+	set_ra_class(ra, RA_CLASS_STATE);
+	ra_state_update(ra, ra_size, la_size);
+
+	return ra_dispatch(ra, mapping, filp);
+}
+
+
+/*
  * ra_size is mainly determined by:
  * 1. sequential-start: min(MIN_RA_PAGES + (pages>>14), KB(128))
  * 2. sequential-max:	min(ra->ra_pages, 0xFFFF)

--

[PATCH 09/16] readahead: context based method

[Wu Fengguang]

[-- Attachment #1: readahead-method-context.patch --]
[-- Type: text/plain, Size: 10405 bytes --]

This is the slow code path.

No valid state info is available, so the page cache is queried to abtain the
required position/timing infomation.

Major steps:
        - look back/forward to find the ra_index;
        - look back to estimate a thrashing safe ra_size;
        - assemble the next read-ahead request in file_ra_state;
        - submit it.

Signed-off-by: Wu Fengguang <wfg@mail.ustc.edu.cn>
---

 mm/readahead.c |  342 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++
 1 files changed, 342 insertions(+)

--- linux-2.6.14-mm1.orig/mm/readahead.c
+++ linux-2.6.14-mm1/mm/readahead.c
@@ -1127,6 +1127,348 @@ state_based_readahead(struct address_spa
 	return ra_dispatch(ra, mapping, filp);
 }
 
+/*
+ * Page cache context based estimation of read-ahead/look-ahead size/index.
+ *
+ * The logic first looks backward in the inactive_list to get an estimation of
+ * the thrashing-threshold, and then, if necessary, looks forward to determine
+ * the start point of next read-ahead.
+ *
+ * The estimation theory can be illustrated with figure:
+ *
+ *   chunk A           chunk B                      chunk C                 head
+ *
+ *   l01 l11           l12   l21                    l22
+ *| |-->|-->|       |------>|-->|                |------>|
+ *| +-------+       +-----------+                +-------------+               |
+ *| |   #   |       |       #   |                |       #     |               |
+ *| +-------+       +-----------+                +-------------+               |
+ *| |<==============|<===========================|<============================|
+ *        L0                     L1                            L2
+ *
+ * Let f(l) = L be a map from
+ * 	l: the number of pages read by the stream
+ * to
+ * 	L: the number of pages pushed into inactive_list in the mean time
+ * then
+ * 	f(l01) <= L0
+ * 	f(l11 + l12) = L1
+ * 	f(l21 + l22) = L2
+ * 	...
+ * 	f(l01 + l11 + ...) <= Sum(L0 + L1 + ...)
+ *                         <= Length(inactive_list) = f(thrashing-threshold)
+ *
+ * So the count of countinuous history pages left in the inactive_list is always
+ * a lower estimation of the true thrashing-threshold.
+ */
+
+/*
+ * STATUS   REFERENCE COUNT      TYPE
+ *  A__                   0      not in inactive list
+ *  ___                   0      fresh
+ *  __R       PAGE_REFCNT_1      stale
+ *  _a_       PAGE_REFCNT_2      disturbed once
+ *  _aR       PAGE_REFCNT_3      disturbed twice
+ *
+ *  A/a/R: Active / aCTIVATE / Referenced
+ */
+static inline unsigned long cold_page_refcnt(struct page *page)
+{
+	if (!page || PageActive(page))
+		return 0;
+
+	return page_refcnt(page);
+}
+
+static inline char page_refcnt_symbol(struct page *page)
+{
+	if (!page)
+		return 'X';
+	if (PageActive(page))
+		return 'A';
+	switch (page_refcnt(page)) {
+		case 0:
+			return '_';
+		case PAGE_REFCNT_1:
+			return '-';
+		case PAGE_REFCNT_2:
+			return '=';
+		case PAGE_REFCNT_3:
+			return '#';
+	}
+	return '?';
+}
+
+/*
+ * Count/estimate cache hits in range [first_index, last_index].
+ * The estimation is simple and optimistic.
+ */
+static int count_cache_hit(struct address_space *mapping,
+				pgoff_t first_index, pgoff_t last_index)
+{
+	struct page *page;
+	int size = last_index - first_index + 1;
+	int count = 0;
+	int i;
+
+	read_lock_irq(&mapping->tree_lock);
+
+	/*
+	 * The first page may well is chunk head and has been accessed,
+	 * so it is index 0 that makes the estimation optimistic. This
+	 * behavior guarantees a readahead when (size < ra_max) and
+	 * (readahead_hit_rate >= 16).
+	 */
+	for (i = 0; i < 16;) {
+		page = __find_page(mapping, first_index +
+						size * ((i++ * 29) & 15) / 16);
+		if (cold_page_refcnt(page) >= PAGE_REFCNT_1 && ++count >= 2)
+			break;
+	}
+
+	read_unlock_irq(&mapping->tree_lock);
+
+	return size * count / i;
+}
+
+/*
+ * Look back and check history pages to estimate thrashing-threshold.
+ */
+static int query_page_cache(struct address_space *mapping,
+			struct file_ra_state *ra,
+			unsigned long *remain, pgoff_t offset,
+			unsigned long ra_min, unsigned long ra_max)
+{
+	int count;
+	pgoff_t index;
+	unsigned long nr_lookback;
+	struct radix_tree_cache cache;
+
+	/*
+	 * Scan backward and check the near @ra_max pages.
+	 * The count here determines ra_size.
+	 */
+	read_lock_irq(&mapping->tree_lock);
+	index = radix_tree_lookup_head(&mapping->page_tree, offset, ra_max);
+	read_unlock_irq(&mapping->tree_lock);
+#ifdef DEBUG_READAHEAD_RADIXTREE
+	if (index <= offset) {
+		WARN_ON(!find_page(mapping, index));
+		if (index + ra_max > offset)
+			WARN_ON(find_page(mapping, index - 1));
+	} else {
+		BUG_ON(index > offset + 1);
+		WARN_ON(find_page(mapping, offset));
+	}
+#endif
+
+	*remain = offset - index + 1;
+
+	if (unlikely(*remain <= ra_min))
+		return ra_min;
+
+	if (offset + 1 == ra->readahead_index && ra_cache_hit_ok(ra))
+		count = *remain;
+	else if (count_cache_hit(mapping, index, offset) *
+						readahead_hit_rate >= *remain)
+		count = *remain;
+	else
+		return ra_min;
+
+	if (count < ra_max)
+		goto out;
+
+	/*
+	 * Check the far pages coarsely.
+	 * The big count here helps increase la_size.
+	 */
+	nr_lookback = ra_max * (LOOKAHEAD_RATIO + 1) *
+						100 / (readahead_ratio + 1);
+	if (nr_lookback > offset)
+		nr_lookback = offset;
+
+        radix_tree_cache_init(&cache);
+	read_lock_irq(&mapping->tree_lock);
+	for (count += ra_max; count < nr_lookback; count += ra_max) {
+		struct radix_tree_node *node;
+		node = radix_tree_cache_lookup_node(&mapping->page_tree,
+                                                &cache, offset - count, 1);
+		if (!node)
+			break;
+#ifdef DEBUG_READAHEAD_RADIXTREE
+		if (node != radix_tree_lookup_node(&mapping->page_tree,
+							offset - count, 1)) {
+			read_unlock_irq(&mapping->tree_lock);
+			printk(KERN_ERR "check radix_tree_cache_lookup_node!\n");
+			return 1;
+		}
+#endif
+	}
+	read_unlock_irq(&mapping->tree_lock);
+
+	/*
+	 *  For sequential read that extends from index 0, the counted value
+	 *  may well be far under the true threshold, so return it unmodified
+	 *  for further process in adjust_rala_accelerated().
+	 */
+	if (count >= offset)
+		return offset;
+
+out:
+	count = count * readahead_ratio / 100;
+	return count;
+}
+
+/*
+ * Scan backward in the file for the first non-present page.
+ */
+static inline pgoff_t first_absent_page_bw(struct address_space *mapping,
+					pgoff_t index, unsigned long max_scan)
+{
+	struct radix_tree_cache cache;
+	struct page *page;
+	pgoff_t origin;
+
+	origin = index;
+	if (max_scan > index)
+		max_scan = index;
+
+	radix_tree_cache_init(&cache);
+	read_lock_irq(&mapping->tree_lock);
+	for (; origin - index <= max_scan;) {
+		page = radix_tree_cache_lookup(&mapping->page_tree,
+							&cache, --index);
+		if (page) {
+			index++;
+			break;
+		}
+	}
+	read_unlock_irq(&mapping->tree_lock);
+
+	return index;
+}
+
+/*
+ * Scan forward in the file for the first non-present page.
+ */
+static inline pgoff_t first_absent_page(struct address_space *mapping,
+					pgoff_t index, unsigned long max_scan)
+{
+	pgoff_t ra_index;
+
+	read_lock_irq(&mapping->tree_lock);
+	ra_index = radix_tree_lookup_tail(&mapping->page_tree,
+					index + 1, max_scan);
+	read_unlock_irq(&mapping->tree_lock);
+
+#ifdef DEBUG_READAHEAD_RADIXTREE
+	BUG_ON(ra_index <= index);
+	if (index + max_scan > index) {
+		if (ra_index <= index + max_scan)
+			WARN_ON(find_page(mapping, ra_index));
+		WARN_ON(!find_page(mapping, ra_index - 1));
+	}
+#endif
+
+	if (ra_index <= index + max_scan)
+		return ra_index;
+	else
+		return 0;
+}
+
+/*
+ * Determine the request parameters for context based read-ahead that extends
+ * from start of file.
+ *
+ * The major weakness of stateless method is perhaps the slow grow up speed of
+ * ra_size. The logic tries to make up for this in the important case of
+ * sequential reads that extend from start of file. In this case, the ra_size
+ * is not choosed to make the whole next chunk safe(as in normal ones). Only
+ * half of which is safe. The added 'unsafe' half is the look-ahead part. It
+ * is expected to be safeguarded by rescue_pages() when the previous chunks are
+ * lost.
+ */
+static inline int adjust_rala_accelerated(unsigned long ra_max,
+				unsigned long *ra_size, unsigned long *la_size)
+{
+	if (*ra_size <= *la_size)
+		return 0;
+
+	*la_size = (*ra_size - *la_size) * readahead_ratio / 100;
+	*ra_size = *la_size * 2;
+
+	if (*ra_size > ra_max)
+		*ra_size = ra_max;
+	if (*la_size > *ra_size)
+		*la_size = *ra_size;
+
+	return 1;
+}
+
+/*
+ * Main function for page context based read-ahead.
+ */
+static inline int
+try_context_based_readahead(struct address_space *mapping,
+			struct file_ra_state *ra,
+			struct page *prev_page, struct page *page,
+			pgoff_t index,
+			unsigned long ra_min, unsigned long ra_max)
+{
+	pgoff_t ra_index;
+	unsigned long ra_size;
+	unsigned long la_size;
+	unsigned long remain_pages;
+
+	/* Where to start read-ahead?
+	 * NFSv3 daemons may process adjecent requests in parallel,
+	 * leading to many locally disordered, globally sequential reads.
+	 * So do not require nearby history pages to be present or accessed.
+	 */
+	if (page) {
+		ra_index = first_absent_page(mapping, index, ra_max * 5 / 4);
+		if (unlikely(!ra_index))
+			return -1;
+	} else if (!prev_page) {
+		ra_index = first_absent_page_bw(mapping, index,
+						readahead_hit_rate + ra_min);
+		if (index - ra_index > readahead_hit_rate + ra_min)
+			return 0;
+		ra_min += 2 * (index - ra_index);
+		index = ra_index;
+	} else {
+		ra_index = index;
+		if (ra_has_index(ra, index))
+			ra_account(ra, RA_EVENT_READAHEAD_MUTILATE,
+						ra->readahead_index - index);
+	}
+
+	ra_size = query_page_cache(mapping, ra, &remain_pages,
+						index - 1, ra_min, ra_max);
+
+	la_size = ra_index - index;
+	if (readahead_ratio < VM_READAHEAD_PROTECT_RATIO &&
+			remain_pages <= la_size && la_size > 1) {
+		rescue_pages(page, la_size);
+		return -1;
+	}
+
+	if (ra_size == index) {
+		if (!adjust_rala_accelerated(ra_max, &ra_size, &la_size))
+			return -1;
+		set_ra_class(ra, RA_CLASS_CONTEXT_ACCELERATED);
+	} else {
+		if (!adjust_rala(ra_max, &ra_size, &la_size))
+			return -1;
+		set_ra_class(ra, RA_CLASS_CONTEXT);
+	}
+
+	ra_state_init(ra, index, ra_index);
+	ra_state_update(ra, ra_size, la_size);
+
+	return 1;
+}
+
 
 /*
  * ra_size is mainly determined by:

--

[PATCH 10/16] readahead: other methods

[Wu Fengguang]

[-- Attachment #1: readahead-method-others.patch --]
[-- Type: text/plain, Size: 3625 bytes --]

Various read-ahead strategies for:
	- fresh read from start of file
	- backward prefetching
	- seek and read one record pattern(db workload)
	- quick recover from thrashing

Signed-off-by: Wu Fengguang <wfg@mail.ustc.edu.cn>
---

 mm/readahead.c |  111 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++
 1 files changed, 111 insertions(+)

--- linux-2.6.14-mm1.orig/mm/readahead.c
+++ linux-2.6.14-mm1/mm/readahead.c
@@ -1469,6 +1469,117 @@ try_context_based_readahead(struct addre
 	return 1;
 }
 
+/*
+ * Read-ahead on start of file.
+ *
+ * It is most important for small files.
+ * 1. Set a moderate large read-ahead size;
+ * 2. Issue the next read-ahead request as soon as possible.
+ *
+ * But be careful, there are some applications that dip into only the very head
+ * of a file. The most important thing is to prevent them from triggering the
+ * next (much larger) read-ahead request, which leads to lots of cache misses.
+ * Two pages should be enough for them, correct me if I'm wrong.
+ */
+static inline unsigned long
+newfile_readahead(struct address_space *mapping,
+		struct file *filp, struct file_ra_state *ra,
+		unsigned long req_size, unsigned long ra_min)
+{
+	unsigned long ra_size;
+	unsigned long la_size;
+
+	if (req_size > ra_min)
+		req_size = ra_min;
+
+	ra_size = 4 * req_size;
+	la_size = 2 * req_size;
+
+	set_ra_class(ra, RA_CLASS_NEWFILE);
+	ra_state_init(ra, 0, 0);
+	ra_state_update(ra, ra_size, la_size);
+
+	return ra_dispatch(ra, mapping, filp);
+}
+
+/*
+ * Backward prefetching.
+ * No look ahead and thrashing threshold estimation for stepping backward
+ * pattern: should be unnecessary.
+ */
+static inline int
+try_read_backward(struct file_ra_state *ra,
+			pgoff_t begin_index, pgoff_t end_index,
+			unsigned long ra_size,
+			unsigned long ra_min, unsigned long ra_max)
+{
+	if (ra_size > ra_max || end_index > ra->prev_page)
+		return 0;
+
+	if (ra_has_index(ra, ra->prev_page)) {
+		if (end_index > ra->la_index)
+			return 0;
+		ra_size += 2 * ra_cache_hit(ra, 0);
+		end_index = ra->la_index;
+	} else {
+		ra_size += readahead_hit_rate + ra_min;
+		end_index = ra->prev_page;
+	}
+
+	if (ra_size > ra_max)
+		ra_size = ra_max;
+
+	if (end_index > begin_index + ra_size)
+		return 0;
+
+	begin_index = end_index - ra_size;
+
+	set_ra_class(ra, RA_CLASS_BACKWARD);
+	ra_state_init(ra, begin_index, begin_index);
+	ra_state_update(ra, ra_size, 0);
+
+	return 1;
+}
+
+/*
+ * If there is a previous sequential read, it is likely to be another
+ * sequential read at the new position.
+ * Databases are known to have this seek-and-read-one-record pattern.
+ */
+static inline int
+try_random_readahead(struct file_ra_state *ra, pgoff_t index,
+			unsigned long ra_size, unsigned long ra_max)
+{
+	unsigned long hit0 = ra_cache_hit(ra, 0);
+	unsigned long hit1 = ra_cache_hit(ra, 1) + hit0;
+	unsigned long hit2 = ra_cache_hit(ra, 2);
+	unsigned long hit3 = ra_cache_hit(ra, 3);
+
+	if (!ra_has_index(ra, ra->prev_page))
+		return 0;
+
+	if (index == ra->prev_page + 1) {    /* read after thrashing */
+		ra_size = hit0;
+		set_ra_class(ra, RA_CLASS_RANDOM_THRASHING);
+		ra_account(ra, RA_EVENT_READAHEAD_THRASHING,
+						ra->readahead_index - index);
+	} else if (ra_size < hit1 &&         /* read after seeking   */
+			hit1 > hit2 / 2 &&
+			hit2 > hit3 / 2 &&
+			hit3 > hit1 / 2) {
+		ra_size = max(hit1, hit2);
+		set_ra_class(ra, RA_CLASS_RANDOM_SEEK);
+	} else
+		return 0;
+
+	if (ra_size > ra_max)
+		ra_size = ra_max;
+
+	ra_state_init(ra, index, index);
+	ra_state_update(ra, ra_size, 0);
+
+	return 1;
+}
 
 /*
  * ra_size is mainly determined by:

--

[PATCH 11/16] readahead: mandatory thrashing protection

[Wu Fengguang]

[-- Attachment #1: readahead-thrashing-protection.patch --]
[-- Type: text/plain, Size: 13378 bytes --]

It tries to identify and protect live pages (sequential pages that are going
to be accessed in the near future) on vmscan time. Almost all live pages can
be sorted out and saved.

The cost: dead pages that won't be read will be kept in inactive_list for
another round. Hopefully there won't be much.

This feature is greatly demanded by file servers, though should be useless
for desktop. It saves the case when one fast reader flushes the cache and
strips the read-ahead size of slow readers, or the case where caching is just
a wasting of memory. Then you can raise readahead_ratio to 200 or more to
enforce a larger read-ahead size and strip the useless cached data out of lru.

Its use is currently limited, for the context based method is not ready for
the case. This problem will be solved when the timing info of evicted pages
are available. It can also be extended to further benefit large memory
systems.  I'll leave them as future work.

Signed-off-by: Wu Fengguang <wfg@mail.ustc.edu.cn>
---

 include/linux/mm.h         |    2 
 include/linux/page-flags.h |    2 
 mm/page_alloc.c            |    2 
 mm/readahead.c             |  319 ++++++++++++++++++++++++++++++++++++++++++++-
 mm/vmscan.c                |   10 +
 5 files changed, 334 insertions(+), 1 deletion(-)

--- linux-2.6.14-mm1.orig/include/linux/page-flags.h
+++ linux-2.6.14-mm1/include/linux/page-flags.h
@@ -107,6 +107,8 @@ struct page_state {
 	unsigned long pgfree;		/* page freeings */
 	unsigned long pgactivate;	/* pages moved inactive->active */
 	unsigned long pgdeactivate;	/* pages moved active->inactive */
+	unsigned long pgkeephot;	/* pages sent back to active */
+	unsigned long pgkeepcold;	/* pages sent back to inactive */
 
 	unsigned long pgfault;		/* faults (major+minor) */
 	unsigned long pgmajfault;	/* faults (major only) */
--- linux-2.6.14-mm1.orig/include/linux/mm.h
+++ linux-2.6.14-mm1/include/linux/mm.h
@@ -995,6 +995,8 @@ page_cache_readahead_adaptive(struct add
 			pgoff_t first_index,
 			pgoff_t index, pgoff_t last_index);
 void fastcall ra_access(struct file_ra_state *ra, struct page *page);
+int rescue_ra_pages(struct list_head *page_list, struct list_head *save_list);
+
 
 /* Do stack extension */
 extern int expand_stack(struct vm_area_struct *vma, unsigned long address);
--- linux-2.6.14-mm1.orig/mm/page_alloc.c
+++ linux-2.6.14-mm1/mm/page_alloc.c
@@ -2391,6 +2391,8 @@ static char *vmstat_text[] = {
 	"pgfree",
 	"pgactivate",
 	"pgdeactivate",
+	"pgkeephot",
+	"pgkeepcold",
 
 	"pgfault",
 	"pgmajfault",
--- linux-2.6.14-mm1.orig/mm/vmscan.c
+++ linux-2.6.14-mm1/mm/vmscan.c
@@ -406,6 +406,8 @@ cannot_free:
 	return 0;
 }
 
+extern int readahead_ratio;
+extern int readahead_live_chunk;
 DECLARE_PER_CPU(unsigned long, smooth_aging);
 
 /*
@@ -416,10 +418,15 @@ static int shrink_list(struct list_head 
 	LIST_HEAD(ret_pages);
 	struct pagevec freed_pvec;
 	int pgactivate = 0;
+	int pgkeep = 0;
 	int reclaimed = 0;
 
 	cond_resched();
 
+	if (readahead_ratio >= VM_READAHEAD_PROTECT_RATIO &&
+							readahead_live_chunk)
+		pgkeep += rescue_ra_pages(page_list, &ret_pages);
+
 	pagevec_init(&freed_pvec, 1);
 	while (!list_empty(page_list)) {
 		struct address_space *mapping;
@@ -572,11 +579,13 @@ keep_locked:
 keep:
 		list_add(&page->lru, &ret_pages);
 		BUG_ON(PageLRU(page));
+		pgkeep++;
 	}
 	list_splice(&ret_pages, page_list);
 	if (pagevec_count(&freed_pvec))
 		__pagevec_release_nonlru(&freed_pvec);
 	mod_page_state(pgactivate, pgactivate);
+	mod_page_state(pgkeepcold, pgkeep - pgactivate);
 	sc->nr_reclaimed += reclaimed;
 	return reclaimed;
 }
@@ -1054,6 +1063,7 @@ refill_inactive_zone(struct zone *zone, 
 
 	mod_page_state_zone(zone, pgrefill, pgscanned);
 	mod_page_state(pgdeactivate, pgdeactivate);
+	mod_page_state(pgkeephot, pgmoved);
 }
 
 /*
--- linux-2.6.14-mm1.orig/mm/readahead.c
+++ linux-2.6.14-mm1/mm/readahead.c
@@ -365,7 +365,7 @@ __do_page_cache_readahead(struct address
 	read_lock_irq(&mapping->tree_lock);
 	for (page_idx = 0; page_idx < nr_to_read; page_idx++) {
 		pgoff_t page_offset = offset + page_idx;
-		
+
 		if (page_offset > end_index)
 			break;
 
@@ -1734,3 +1734,320 @@ void fastcall ra_access(struct file_ra_s
 		ra_account(ra, RA_EVENT_READAHEAD_HIT, -1);
 }
 
+/*
+ * Detect and protect live read-ahead pages.
+ *
+ * This function provides safty guarantee for file servers with big
+ * readahead_ratio(>=VM_READAHEAD_PROTECT_RATIO) set.  The goal is to save all
+ * and only the sequential pages that are to be accessed in the near future.
+ *
+ * This function is called when pages in @page_list are to be freed,
+ * it protects live read-ahead pages by moving them into @save_list.
+ *
+ * The general idea is to classify pages of a file into groups of sequential
+ * accessed pages. Dead sequential pages are left over, live sequential pages
+ * are saved.
+ *
+ * Live read-ahead pages are defined as sequential pages that have reading in
+ * progress. They are detected by reference count pattern of:
+ *
+ *                        live head       live pages
+ *  ra pages group -->   ------------___________________
+ *                                   [  pages to save  ] (*)
+ *
+ * (*) for now, an extra page from the live head may also be saved.
+ *
+ * In pratical, the group of pages are fragmented into chunks. To tell whether
+ * pages inside a chunk are alive, we must check:
+ * 1) Are there any live heads inside the chunk?
+ * 2) Are there any live heads in the group before the chunk?
+ * 3) Sepcial case: live head just sits on the boundary of current chunk?
+ *
+ * The detailed rules employed must ensure:
+ * - no page is pinned in inactive_list.
+ * - no excessive pages are saved.
+ *
+ * A picture of common cases:
+ *             back search            chunk             case
+ *           -----___________|[____________________]    Normal
+ *           ----------------|----[________________]    Normal
+ *                           |----[________________]    Normal
+ *           ----------------|----------------------    Normal
+ *                           |----------------------    Normal
+ *           ________________|______________________    ra miss
+ *                           |______________________    ra miss
+ *           ________________|_______--------[_____]    two readers
+ *           ----____________|[______--------______]    two readers
+ *                           |_______--------[_____]    two readers
+ *                           |----[____------______]    two readers
+ *           ----------------|----[____------______]    two readers
+ *           _______---------|---------------[_____]    two readers
+ *           ----___---------|[--------------______]    two readers
+ *           ________________|---------------[_____]    two readers
+ *           ----____________|[--------------______]    two readers
+ *           ====------------|[---_________________]    two readers
+ *                           |====[----------______]    two readers
+ *                           |###======[-----------]    three readers
+ */
+static int save_chunk(struct page *head, struct page *live_head,
+			struct page *tail, struct list_head *save_list)
+{
+	struct page *page;
+	struct address_space *mapping;
+	struct radix_tree_cache cache;
+	int i;
+	pgoff_t index;
+	pgoff_t head_index;
+	unsigned long refcnt;
+
+#ifdef DEBUG_READAHEAD
+	static char static_buf[PAGE_SIZE];
+	static char *zone_names[] = {"DMA", "DMA32", "Normal", "HighMem"};
+	char *pat = static_buf;
+	int pidx = 0;
+#define	log_symbol(symbol)					\
+	do { 							\
+		if ((readahead_ratio & 3) == 3 &&		\
+				pidx < PAGE_SIZE - 1)	\
+			pat[pidx++] = symbol; 			\
+	} while (0)
+
+	if ((readahead_ratio & 3) == 3) {
+		pat = (char *)get_zeroed_page(GFP_KERNEL);
+		if (!pat)
+			pat = static_buf;
+	}
+#else
+#define log_symbol(symbol) do {} while (0)
+#endif
+#define	log_page(page)	log_symbol(page_refcnt_symbol(page))
+
+	head_index = head->index;
+	mapping = head->mapping;
+	radix_tree_cache_init(&cache);
+
+	BUG_ON(!mapping); /* QUESTION: in what case mapping will be NULL ? */
+	read_lock_irq(&mapping->tree_lock);
+
+	/*
+	 * Common case test.
+	 * Does the far end indicates a leading live head?
+	 */
+	index = radix_tree_lookup_head(&mapping->page_tree,
+					head_index, readahead_live_chunk);
+	if (index >= head_index)
+		goto skip_scan_locked;
+
+	page = __find_page(mapping, index);
+	BUG_ON(!page);
+	log_symbol('|');
+	log_page(page);
+	refcnt = cold_page_refcnt(page);
+	if (head_index - index < readahead_live_chunk &&
+			refcnt > page_refcnt(head)) {
+		live_head = head;
+		goto skip_scan_locked;
+	}
+
+	/*
+	 * The slow path.
+	 * Scan page by page to see if the whole chunk should be saved.
+	 */
+	if (next_page(head) != tail)
+		head_index = next_page(head)->index;
+	else
+		head_index++;
+	for (i = 0, index++; index <= head_index; index++) {
+		page = radix_tree_cache_lookup(&mapping->page_tree, &cache,
+									index);
+		if (index == head->index)
+			log_symbol('|');
+		log_page(page);
+
+		if (!page) {
+			WARN_ON(index < head->index);
+			break;
+		}
+
+		if (refcnt == page_refcnt(page))
+			i++;
+		else if (refcnt < page_refcnt(page))
+			i = 0;
+		else if (i < 1)
+			i = INT_MIN;
+		else {
+			live_head = head;
+			break;
+		}
+
+		refcnt = page_refcnt(page);
+	}
+
+skip_scan_locked:
+#ifdef DEBUG_READAHEAD
+	if (index < head->index)
+		log_symbol('*');
+	index = prev_page(tail)->index;
+
+	log_symbol('|');
+	for (page = head; page != tail; page = next_page(page)) {
+		BUG_ON(PageAnon(page));
+		BUG_ON(PageSwapCache(page));
+		/* BUG_ON(page_mapped(page)); */
+
+		if (page == live_head)
+			log_symbol('[');
+		log_page(page);
+	}
+	if (live_head)
+		log_symbol(']');
+#endif
+
+	/*
+	 * Special case work around.
+	 *
+	 * Save one extra page if it is a live head of the following chunk.
+	 * Just to be safe.  It protects the rare situation when the reader
+	 * is just crossing the chunk boundary, and the following chunk is not
+	 * far away from tail of inactive_list.
+	 *
+	 * The special case is awkwardly delt with for now. They will be all set
+	 * when the timing information of recently evicted pages are available.
+	 * Dead pages can also be purged earlier with the timing info.
+	 */
+	if (live_head != head) {
+		struct page *last_page = prev_page(tail);
+		page = radix_tree_cache_lookup(&mapping->page_tree, &cache,
+						last_page->index + 1);
+		log_symbol('|');
+		log_page(page);
+		if (page && !live_head) {
+			refcnt = page_refcnt(last_page);
+			if (page_refcnt(page) >= refcnt)
+				page = radix_tree_cache_lookup(
+						&mapping->page_tree, &cache,
+						last_page->index + 2);
+			log_page(page);
+			if (page && page_refcnt(page) < refcnt) {
+				live_head = last_page;
+				log_symbol('I');
+			}
+		} else if (!page && live_head) {
+			live_head = next_page(live_head);
+				log_symbol('D');
+		}
+	}
+	log_symbol('\0');
+
+	read_unlock_irq(&mapping->tree_lock);
+
+	/*
+	 * Now save the alive pages.
+	 */
+	i = 0;
+	if (live_head) {
+		for (; live_head != tail;) { /* never dereference tail! */
+			page = next_page(live_head);
+			if (!PageActivate(live_head)) {
+				list_move(&live_head->lru, save_list);
+				i++;
+				if (!page_refcnt(live_head))
+					__get_cpu_var(smooth_aging)++;
+			}
+			live_head = page;
+		}
+
+		if (i)
+			ra_account(0, RA_EVENT_READAHEAD_RESCUE, i);
+	}
+
+#ifdef DEBUG_READAHEAD
+	if ((readahead_ratio & 3) == 3) {
+		ddprintk("save_chunk(ino=%lu, idx=%lu-%lu, %s@%s:%s)"
+				" = %d\n",
+				mapping->host->i_ino,
+				head->index, index,
+				mapping_mapped(mapping) ? "mmap" : "file",
+				zone_names[page_zonenum(head)], pat, i);
+		if (pat != static_buf)
+			free_page((unsigned long)pat);
+	}
+#endif
+
+	return i;
+}
+
+int rescue_ra_pages(struct list_head *page_list, struct list_head *save_list)
+{
+	struct address_space *mapping;
+	struct page *chunk_head;
+	struct page *live_head;
+	struct page *page;
+	unsigned long refcnt;
+	unsigned long min_refcnt;
+	int n;
+	int ret = 0;
+
+	page = list_to_page(page_list);
+
+next_chunk:
+	chunk_head = page;
+	live_head = NULL;
+	mapping = page->mapping;
+	n = 0;
+	min_refcnt = LONG_MAX;
+
+next_head_page:
+	refcnt = page_refcnt(page);
+	if (min_refcnt > refcnt)
+		min_refcnt = refcnt;
+	page = next_page(page);
+
+	if (mapping != page->mapping || &page->lru == page_list)
+		goto save_chunk;
+
+	/* At least 2 pages followed by a fall in refcnt makes a live head:
+	 *               --_
+	 *                ^ live_head
+	 */
+	if (refcnt == page_refcnt(page))
+		n++;
+	else if (refcnt < page_refcnt(page))
+		n = 0;
+	else if (n < 1)
+		n = INT_MIN;
+	else
+		goto got_live_head;
+
+	goto next_head_page;
+
+got_live_head:
+	n = 0;
+	live_head = prev_page(page);
+
+next_page:
+	if (refcnt < page_refcnt(page)) /* limit the number of rises */
+		n++;
+	refcnt = page_refcnt(page);
+	if (min_refcnt > refcnt)
+		min_refcnt = refcnt;
+	page = next_page(page);
+
+	if (mapping != page->mapping || &page->lru == page_list)
+		goto save_chunk;
+
+	goto next_page;
+
+save_chunk:
+	if (mapping && !PageAnon(chunk_head) &&
+			!PageSwapCache(chunk_head) &&
+			/* !page_mapped(chunk_head) && */
+			min_refcnt < PAGE_REFCNT_2 &&
+			n <= 3)
+		ret += save_chunk(chunk_head, live_head, page, save_list);
+
+	if (&page->lru != page_list)
+		goto next_chunk;
+
+	return ret;
+}

--

[PATCH 12/16] readahead: events accounting

[Wu Fengguang]

[-- Attachment #1: readahead-account-events.patch --]
[-- Type: text/plain, Size: 9267 bytes --]

A debugfs file named `readahead' is created according to advices from
J?rn Engel, Andrew Morton and Ingo Oeser. It yields to much better
readability than the preious /proc/vmstat interface :)

It reveals various read-ahead activities/events, and is vital to the testing.
Compile with 'Kernel hacking  --->  Debug Filesystem' to enable it.

This is a trimmed down output on my PC:
# cat /debugfs/readahead
[table requests]      total    newfile      state    context      none
cache_miss              403         56         12         69       263
read_random             260         37          5         17       201
io_congestion             0          0          0          0         0
io_cache_hit             85          0         24         46         0
io_block               9796       5613        822        143      3203
readahead              5956       5418        383        139         0
lookahead               961        650        212         98         0
lookahead_hit           449        181        164         58        41
lookahead_ignore          0          0          0          0         0
readahead_eof          4981       4768        171         28         0
readahead_shrink          0          0          0          0         0
readahead_thrash          0          0          0          0         0
readahead_mutilt          0          0          0          0         0
readahead_rescue         45          0          0          0        45

[table pages]         total    newfile      state    context      none
cache_miss             5590         72       2506        181      2826
read_random             265         37          5         17       206
io_congestion             0          0          0          0         0
io_cache_hit           2440          0       1054       1366         0
io_block             165848      11117     147794       3668      3203
readahead             43080      11360      28949       2621         0
readahead_hit         38251      10716      25669       1818         9
lookahead             24013       1718      21641        647         0
lookahead_hit         20161        770      18679        712         0
lookahead_ignore          0          0          0          0         0
readahead_eof         15961       7924       7440        461         0
readahead_shrink          0          0          0          0         0
readahead_thrash          0          0          0          0         0
readahead_mutilt          0          0          0          0         0
readahead_rescue        240          0          0          0       240

[table summary]       total    newfile      state    context      none
random_rate              4%         0%         1%        10%       99%
ra_hit_rate             88%        94%        88%        69%      900%
la_hit_rate             46%        27%        76%        58%     4100%
avg_ra_size               7          2         75         19         0
avg_la_size              25          3        102          7         0

Signed-off-by: Wu Fengguang <wfg@mail.ustc.edu.cn>
---

 mm/readahead.c |  193 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++-
 1 files changed, 191 insertions(+), 2 deletions(-)

--- linux-2.6.14-mm1.orig/mm/readahead.c
+++ linux-2.6.14-mm1/mm/readahead.c
@@ -89,6 +89,179 @@ enum ra_event {
 #endif
 
 #ifdef DEBUG_READAHEAD
+#include <linux/jiffies.h>
+#include <linux/debugfs.h>
+#include <linux/seq_file.h>
+#include <linux/init.h>
+
+static char *ra_class_name[] = {
+	"total",
+	"newfile",
+	"state",
+	"context",
+	"contexta",
+	"backward",
+	"onthrash",
+	"onraseek",
+	"none",
+};
+
+static char *ra_event_name[] = {
+	"cache_miss",
+	"read_random",
+	"io_congestion",
+	"io_cache_hit",
+	"io_block",
+	"readahead",
+	"readahead_hit",
+	"lookahead",
+	"lookahead_hit",
+	"lookahead_ignore",
+	"readahead_eof",
+	"readahead_shrink",
+	"readahead_thrash",
+	"readahead_mutilt",
+	"readahead_rescue",
+};
+
+static unsigned long ra_event_count[RA_CLASS_END+1][RA_EVENT_END][2];
+
+static inline void ra_account(struct file_ra_state *ra,
+				enum ra_event e, int pages)
+{
+	enum ra_class c;
+
+	c = (ra ? ra->flags & RA_CLASS_MASK : RA_CLASS_END);
+	if (e == RA_EVENT_READAHEAD_HIT && pages < 0) {
+		c = (ra->flags >> RA_CLASS_SHIFT) & RA_CLASS_MASK;
+		pages = -pages;
+	}
+	if (!c)
+		c = RA_CLASS_END;
+	BUG_ON(c > RA_CLASS_END);
+
+	ra_event_count[c][e][0] += 1;
+	ra_event_count[c][e][1] += pages;
+}
+
+static int ra_account_show(struct seq_file *s, void *_)
+{
+	int i;
+	int c;
+	int e;
+	static char event_fmt[] = "%-16s";
+	static char class_fmt[] = "%11s";
+	static char item_fmt[] = "%11lu";
+	static char percent_format[] = "%10lu%%";
+	static char *table_name[] = {
+		"[table requests]",
+		"[table pages]",
+		"[table summary]"};
+
+	for (i = 0; i <= 1; i++) {
+		for (e = 0; e < RA_EVENT_END; e++) {
+			ra_event_count[0][e][i] = 0;
+			for (c = 1; c <= RA_CLASS_END; c++)
+				ra_event_count[0][e][i] +=
+							ra_event_count[c][e][i];
+		}
+
+		seq_printf(s, event_fmt, table_name[i]);
+		for (c = 0; c <= RA_CLASS_END; c++)
+			seq_printf(s, class_fmt, ra_class_name[c]);
+		seq_puts(s, "\n");
+
+		for (e = 0; e < RA_EVENT_END; e++) {
+			if (e == RA_EVENT_READAHEAD_HIT && i == 0)
+				continue;
+
+			seq_printf(s, event_fmt, ra_event_name[e]);
+			for (c = 0; c <= RA_CLASS_END; c++)
+				seq_printf(s, item_fmt,
+						ra_event_count[c][e][i]);
+			seq_puts(s, "\n");
+		}
+		seq_puts(s, "\n");
+	}
+
+	seq_printf(s, event_fmt, table_name[2]);
+	for (c = 0; c <= RA_CLASS_END; c++)
+		seq_printf(s, class_fmt, ra_class_name[c]);
+	seq_puts(s, "\n");
+
+	seq_printf(s, event_fmt, "random_rate");
+	for (c = 0; c <= RA_CLASS_END; c++)
+		seq_printf(s, percent_format,
+			(ra_event_count[c][RA_EVENT_READRANDOM][0] * 100) /
+			(ra_event_count[c][RA_EVENT_READRANDOM][0] +
+			 ra_event_count[c][RA_EVENT_READAHEAD][0] + 1));
+	seq_puts(s, "\n");
+
+	seq_printf(s, event_fmt, "ra_hit_rate");
+	for (c = 0; c <= RA_CLASS_END; c++)
+		seq_printf(s, percent_format,
+			(ra_event_count[c][RA_EVENT_READAHEAD_HIT][1] * 100) /
+			(ra_event_count[c][RA_EVENT_READAHEAD][1] + 1));
+	seq_puts(s, "\n");
+
+	seq_printf(s, event_fmt, "la_hit_rate");
+	for (c = 0; c <= RA_CLASS_END; c++)
+		seq_printf(s, percent_format,
+			(ra_event_count[c][RA_EVENT_LOOKAHEAD_HIT][0] * 100) /
+			(ra_event_count[c][RA_EVENT_LOOKAHEAD][0] + 1));
+	seq_puts(s, "\n");
+
+	seq_printf(s, event_fmt, "avg_ra_size");
+	for (c = 0; c <= RA_CLASS_END; c++)
+		seq_printf(s, item_fmt,
+			(ra_event_count[c][RA_EVENT_READAHEAD][1] +
+			 ra_event_count[c][RA_EVENT_READAHEAD][0] / 2) /
+			(ra_event_count[c][RA_EVENT_READAHEAD][0] + 1));
+	seq_puts(s, "\n");
+
+	seq_printf(s, event_fmt, "avg_la_size");
+	for (c = 0; c <= RA_CLASS_END; c++)
+		seq_printf(s, item_fmt,
+			(ra_event_count[c][RA_EVENT_LOOKAHEAD][1] +
+			 ra_event_count[c][RA_EVENT_LOOKAHEAD][0] / 2) /
+			(ra_event_count[c][RA_EVENT_LOOKAHEAD][0] + 1));
+	seq_puts(s, "\n");
+
+	return 0;
+}
+
+static struct dentry *readahead_dentry;
+
+static int ra_debug_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, ra_account_show, NULL);
+}
+
+static ssize_t ra_debug_write(struct file *file, const char __user *buf,
+				size_t size, loff_t *offset)
+{
+	if (file->f_dentry == readahead_dentry)
+		memset(ra_event_count, 0, sizeof(ra_event_count));
+	return 1;
+}
+
+static struct file_operations ra_debug_fops = {
+	.owner		= THIS_MODULE,
+	.open		= ra_debug_open,
+	.write		= ra_debug_write,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static int __init readahead_init(void)
+{
+	readahead_dentry = debugfs_create_file("readahead",
+					0644, NULL, NULL, &ra_debug_fops);
+	return 0;
+}
+
+module_init(readahead_init)
 
 #define dprintk(args...) \
 	if (readahead_ratio & 1) printk(KERN_DEBUG args)
@@ -97,6 +270,10 @@ enum ra_event {
 
 #else /* !DEBUG_READAHEAD */
 
+static inline void ra_account(struct file_ra_state *ra,
+				enum ra_event e, int pages)
+{
+}
 #define dprintk(args...)     do {} while(0)
 #define ddprintk(args...)    do {} while(0)
 
@@ -992,6 +1169,8 @@ static int ra_dispatch(struct file_ra_st
 		ra_account(ra, RA_EVENT_READAHEAD_EOF, actual);
 	if (la_size)
 		ra_account(ra, RA_EVENT_LOOKAHEAD, la_size);
+	if (ra_size > actual)
+		ra_account(ra, RA_EVENT_IO_CACHE_HIT, ra_size - actual);
 	ra_account(ra, RA_EVENT_READAHEAD, actual);
 
 	dprintk("readahead-%s(ino=%lu, index=%lu, ra=%lu+%lu-%lu) = %d\n",
@@ -1632,8 +1811,11 @@ page_cache_readahead_adaptive(struct add
 	if (page) {
 		if(!TestClearPageReadahead(page))
 			return 0;
-		if (bdi_read_congested(mapping->backing_dev_info))
+		if (bdi_read_congested(mapping->backing_dev_info)) {
+			ra_account(ra, RA_EVENT_IO_CONGESTION,
+							end_index - index);
 			return 0;
+		}
 	}
 
 	if (page)
@@ -1723,8 +1905,15 @@ void fastcall ra_access(struct file_ra_s
 			   (1 << PG_referenced)))
 		return;
 
-	if (!ra_has_index(ra, page->index))
+	if (ra_has_index(ra, page->index)) {
+		if (PageLocked(page))
+			ra_account(ra, RA_EVENT_IO_BLOCK,
+					ra->readahead_index - page->index);
+	} else {
+		if (PageLocked(page))
+			ra_account(0, RA_EVENT_IO_BLOCK, 1);
 		return;
+	}
 
 	ra->cache_hit++;
 

--

[PATCH 13/16] readahead: page aging accounting

[Wu Fengguang]

[-- Attachment #1: readahead-account-aging.patch --]
[-- Type: text/plain, Size: 7504 bytes --]

The accuracy of stateful thrashing-threshold estimation depends largely on the
measurement of cold page aging speed.

A file named `pageaging' is created in debugfs to monitor the trace of two
measurement variables: per-zone `nr_page_aging' and per-cpu `smooth_aging'.
Their values and the jiffies are recorded each time one of them has a delta
of 1, 1/2, 1/4, 1/16, 1/256, 1/4096 (nr_inactive + nr_free).

Sample series of collected data shows that smooth_aging is more stable in
small sampling granularity:

  time         dt         page_aging8       smooth_aging8
872765         26     520056       33     653782      163
872791         12     520089      132     653945       51
872803          4     520221      132     653996       66
872807         17     520353      165     654062      107
872824         22     520518       99     654169       74
872846        372     520617       99     654243       78
873218        294     520716       99     654321       73
873512        196     520815       99     654394      130
873708         15     520914      231     654524       28
873723         15     521145      198     654552        9
873738        881     521343       99     654561      182
874619        700     521442        0     654743      198
875319        384     521442       66     654941      110
875703       2119     521508       99     655051     1632
877822       3960     521607        0     656683      980
881782        904     521607        0     657663      216

  time         dt         page_aging1       smooth_aging1
-90822      12418       5775    12999      33302    10767
-78404      17510      18774    10303      44069    10345
-60894      24757      29077     9871      54414    14615
-36137      19194      38948    10404      69029    13726
-16943      19636      49352    10440      82755    12865
  2693      16299      59792    12453      95620    10734
 18992      19851      72245    10073     106354    15960
 38843      16099      82318    10767     122314    14059
 54942      16094      93085    10041     136373    12117
 71036      19888     103126    12595     148490    16155
 90924      18452     115721     9782     164645    11705
109376      22395     125503    10214     176350    13679
131771      19310     135717    10759     190029    11843
151081      20793     146476    10699     201872    12595
171874      22308     157175    10321     214467    13157
194182      17954     167496    10773     227624    14803
212136      19946     178269    10554     242427    13391
232082      21051     188823    11179     255818    11783

Signed-off-by: Wu Fengguang <wfg@mail.ustc.edu.cn>
---

 mm/readahead.c |  148 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++-
 1 files changed, 147 insertions(+), 1 deletion(-)

--- linux-2.6.14-mm1.orig/mm/readahead.c
+++ linux-2.6.14-mm1/mm/readahead.c
@@ -230,11 +230,144 @@ static int ra_account_show(struct seq_fi
 	return 0;
 }
 
+/*
+ * Measure the aging progress of cold pages over time.
+ */
+#define AGING_INFO_SIZE	(1 << 8)
+#define AGING_INFO_MASK	(AGING_INFO_SIZE - 1)
+static int aging_info_shift[] = {0, 1, 2, 4, 8, 12};
+#define AGING_INFO_SHIFTS	(sizeof(aging_info_shift)/\
+				 sizeof(aging_info_shift[0]))
+static int aging_info_index[AGING_INFO_SHIFTS];
+static unsigned long aging_info[AGING_INFO_SIZE][AGING_INFO_SHIFTS*3];
+static spinlock_t aging_info_lock = SPIN_LOCK_UNLOCKED;
+
+static unsigned long nr_free_inactive(void);
+static unsigned long nr_smooth_aging(void);
+
+/*
+ * The accumulated count of pages pushed into inactive_list(s).
+ */
+static unsigned long nr_page_aging(void)
+{
+	unsigned int i;
+	unsigned long sum = 0;
+	struct zone *zones = NODE_DATA(numa_node_id())->node_zones;
+
+	for (i = 0; i < MAX_NR_ZONES; i++)
+		sum += zones[i].nr_page_aging;
+
+	return sum;
+}
+
+static void collect_aging_info(void)
+{
+	int i;
+	unsigned long mem;
+	unsigned long page_aging;
+	unsigned long smooth_aging;
+
+	mem = nr_free_inactive();
+	page_aging = nr_page_aging();
+	smooth_aging = nr_smooth_aging();
+
+	spin_lock_irq(&aging_info_lock);
+
+	for (i = AGING_INFO_SHIFTS - 1; i >= 0; i--) {
+		if (smooth_aging - aging_info[aging_info_index[i]][i*3+2] +
+		      page_aging - aging_info[aging_info_index[i]][i*3+1] >
+					2 * (mem >> aging_info_shift[i])) {
+			aging_info_index[i]++;
+			aging_info_index[i] &= AGING_INFO_MASK;
+			aging_info[aging_info_index[i]][i*3] = jiffies;
+			aging_info[aging_info_index[i]][i*3+1] = page_aging;
+			aging_info[aging_info_index[i]][i*3+2] = smooth_aging;
+		} else
+			break;
+	}
+
+	spin_unlock_irq(&aging_info_lock);
+}
+
+static void *aginginfo_start(struct seq_file *s, loff_t *pos)
+{
+	int n = *pos;
+	int i;
+
+	spin_lock_irq(&aging_info_lock);
+
+	if (!n) {
+		for (i = 0; i < AGING_INFO_SHIFTS; i++) {
+			seq_printf(s, "%12s %10s %18s%d %18s%d\t", "time","dt",
+                                        "page_aging", aging_info_shift[i],
+                                        "smooth_aging", aging_info_shift[i]);
+		}
+		seq_puts(s, "\n");
+	}
+
+	if (++n < AGING_INFO_SIZE)
+		return (void *)n;
+	else
+		return NULL;
+}
+
+static void *aginginfo_next(struct seq_file *s, void *p, loff_t *pos)
+{
+	int n = (int)p;
+
+	++*pos;
+	return (void *)(++n < AGING_INFO_SIZE ? n : 0);
+}
+
+static void aginginfo_stop(struct seq_file *s, void *p)
+{
+	spin_unlock_irq(&aging_info_lock);
+}
+
+static int aginginfo_show(struct seq_file *s, void *p)
+{
+	int n = (int)p;
+	int i;
+	int index0;
+	int index1;
+	long time;
+	unsigned long nr1;
+	unsigned long nr2;
+
+	for (i = 0; i < AGING_INFO_SHIFTS; i++) {
+		index0 = aging_info_index[i] + n;
+		index1 = aging_info_index[i] + n + 1;
+		index0 &= AGING_INFO_MASK;
+		index1 &= AGING_INFO_MASK;
+		time = aging_info[index0][i*3];
+		nr1 = aging_info[index1][i*3+1] - aging_info[index0][i*3+1];
+		nr2 = aging_info[index1][i*3+2] - aging_info[index0][i*3+2];
+		seq_printf(s, "%12ld %10lu %10lu %8lu %10lu %8lu\t",
+				time,  aging_info[index1][i*3] - time,
+				aging_info[index0][i*3+1], nr1,
+				aging_info[index0][i*3+2], nr2);
+	}
+	seq_puts(s, "\n");
+
+	return 0;
+}
+
 static struct dentry *readahead_dentry;
+static struct dentry *pageaging_dentry;
+
+struct seq_operations aginginfo_ops = {
+	.start	= aginginfo_start,
+	.next	= aginginfo_next,
+	.stop	= aginginfo_stop,
+	.show	= aginginfo_show,
+};
 
 static int ra_debug_open(struct inode *inode, struct file *file)
 {
-	return single_open(file, ra_account_show, NULL);
+	if (file->f_dentry == readahead_dentry)
+		return single_open(file, ra_account_show, NULL);
+	else
+		return seq_open(file, &aginginfo_ops);
 }
 
 static ssize_t ra_debug_write(struct file *file, const char __user *buf,
@@ -254,10 +387,20 @@ static struct file_operations ra_debug_f
 	.release	= single_release,
 };
 
+static struct file_operations aginginfo_fops = {
+	.open		= ra_debug_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= seq_release,
+};
+
+
 static int __init readahead_init(void)
 {
 	readahead_dentry = debugfs_create_file("readahead",
 					0644, NULL, NULL, &ra_debug_fops);
+	pageaging_dentry = debugfs_create_file("pageaging",
+					0644, NULL, NULL, &aginginfo_fops);
 	return 0;
 }
 
@@ -1265,6 +1408,9 @@ static inline unsigned long compute_thra
 	else
 		*remain = 0;
 
+#ifdef DEBUG_READAHEAD
+	collect_aging_info();
+#endif
 	ddprintk("compute_thrashing_threshold: "
 			"ra=%lu=%lu*%lu/%lu, remain %lu for %lu\n",
 			ra_size, stream_shift, global_size, global_shift,

--

[PATCH 14/16] readahead: laptop mode support

[Wu Fengguang]

[-- Attachment #1: readahead-laptop-mode.patch --]
[-- Type: text/plain, Size: 2720 bytes --]

When the laptop drive is spinned down, defer look-ahead to spin up time.

The implementation employs a poll based method, for performance is not a
concern in this code path. The poll interval is set to 64KB, which should
be small enough for movies/musics.

Signed-off-by: Wu Fengguang <wfg@mail.ustc.edu.cn>
---

 include/linux/writeback.h |    6 ++++++
 mm/page-writeback.c       |    2 +-
 mm/readahead.c            |   30 ++++++++++++++++++++++++++++++
 3 files changed, 37 insertions(+), 1 deletion(-)

--- linux-2.6.14-mm1.orig/include/linux/writeback.h
+++ linux-2.6.14-mm1/include/linux/writeback.h
@@ -90,6 +90,12 @@ void laptop_io_completion(void);
 void laptop_sync_completion(void);
 void throttle_vm_writeout(void);
 
+extern struct timer_list laptop_mode_wb_timer;
+static inline int laptop_spinned_down(void)
+{
+	return !timer_pending(&laptop_mode_wb_timer);
+}
+
 /* These are exported to sysctl. */
 extern int dirty_background_ratio;
 extern int vm_dirty_ratio;
--- linux-2.6.14-mm1.orig/mm/page-writeback.c
+++ linux-2.6.14-mm1/mm/page-writeback.c
@@ -369,7 +369,7 @@ static void wb_timer_fn(unsigned long un
 static void laptop_timer_fn(unsigned long unused);
 
 static DEFINE_TIMER(wb_timer, wb_timer_fn, 0, 0);
-static DEFINE_TIMER(laptop_mode_wb_timer, laptop_timer_fn, 0, 0);
+DEFINE_TIMER(laptop_mode_wb_timer, laptop_timer_fn, 0, 0);
 
 /*
  * Periodic writeback of "old" data.
--- linux-2.6.14-mm1.orig/mm/readahead.c
+++ linux-2.6.14-mm1/mm/readahead.c
@@ -14,6 +14,7 @@
 #include <linux/blkdev.h>
 #include <linux/backing-dev.h>
 #include <linux/pagevec.h>
+#include <linux/writeback.h>
 
 /* The default number of max/min read-ahead pages. */
 #define KB(size)	(((size)*1024 + PAGE_CACHE_SIZE-1) / PAGE_CACHE_SIZE)
@@ -1115,6 +1116,30 @@ out:
 }
 
 /*
+ * Set a new look-ahead mark at @new_index.
+ * Return 0 if the new mark is successfully set.
+ */
+static inline int renew_lookahead(struct address_space *mapping,
+				struct file_ra_state *ra,
+				pgoff_t index, pgoff_t new_index)
+{
+	struct page *page;
+
+	if (index == ra->lookahead_index &&
+			new_index >= ra->readahead_index)
+		return 1;
+
+	page = find_page(mapping, new_index);
+	if (!page)
+		return 1;
+
+	SetPageReadahead(page);
+	if (ra->lookahead_index == index)
+		ra->lookahead_index = new_index;
+	return 0;
+}
+
+/*
  * State based calculation of read-ahead request.
  *
  * This figure shows the meaning of file_ra_state members:
@@ -1962,6 +1987,11 @@ page_cache_readahead_adaptive(struct add
 							end_index - index);
 			return 0;
 		}
+		if (laptop_mode && laptop_spinned_down()) {
+			if (!renew_lookahead(mapping, ra, index,
+						index + LAPTOP_POLL_INTERVAL))
+				return 0;
+		}
 	}
 
 	if (page)

--

[PATCH 15/16] readahead: disable look-ahead for loopback file

[Wu Fengguang]

[-- Attachment #1: readahead-disable-lookahead-for-loopback.patch --]
[-- Type: text/plain, Size: 2000 bytes --]

Loopback files normally contain filesystem, in which case there are already
proper look-aheads in the upper layer, more look-aheads on the loopback file
only ruin the read-ahead hit rate.

Signed-off-by: Wu Fengguang <wfg@mail.ustc.edu.cn>
---

I'd like to thank Tero Grundstr?m for uncovering the loopback problem.

 drivers/block/loop.c |    6 ++++++
 include/linux/fs.h   |    1 +
 mm/readahead.c       |    8 ++++++++
 3 files changed, 15 insertions(+)

--- linux-2.6.14-mm1.orig/include/linux/fs.h
+++ linux-2.6.14-mm1/include/linux/fs.h
@@ -585,6 +585,7 @@ struct file_ra_state {
 };
 #define RA_FLAG_MISS 0x01	/* a cache miss occured against this file */
 #define RA_FLAG_INCACHE 0x02	/* file is already in cache */
+#define RA_FLAG_NO_LOOKAHEAD	(1<<31)	/* disable look-ahead */
 
 struct file {
 	/*
--- linux-2.6.14-mm1.orig/drivers/block/loop.c
+++ linux-2.6.14-mm1/drivers/block/loop.c
@@ -769,6 +769,12 @@ static int loop_set_fd(struct loop_devic
 	mapping = file->f_mapping;
 	inode = mapping->host;
 
+	/*
+	 * The upper layer should already do proper look-ahead,
+	 * one more look-ahead here only ruins the cache hit rate.
+	 */
+	file->f_ra.flags |= RA_FLAG_NO_LOOKAHEAD;
+
 	if (!(file->f_mode & FMODE_WRITE))
 		lo_flags |= LO_FLAGS_READ_ONLY;
 
--- linux-2.6.14-mm1.orig/mm/readahead.c
+++ linux-2.6.14-mm1/mm/readahead.c
@@ -1272,6 +1272,11 @@ static inline void ra_state_update(struc
 	if (ra_size < old_ra && ra_cache_hit(ra, 0))
 		ra_account(ra, RA_EVENT_READAHEAD_SHRINK, old_ra - ra_size);
 #endif
+
+	/* Disable look-ahead for loopback file. */
+	if (unlikely(ra->flags & RA_FLAG_NO_LOOKAHEAD))
+		la_size = 0;
+
 	ra_addup_cache_hit(ra);
 	ra->ra_index = ra->readahead_index;
 	ra->la_index = ra->lookahead_index;
@@ -1628,6 +1633,9 @@ static int query_page_cache(struct addre
 	if (count < ra_max)
 		goto out;
 
+	if (unlikely(ra->flags & RA_FLAG_NO_LOOKAHEAD))
+		goto out;
+
 	/*
 	 * Check the far pages coarsely.
 	 * The big count here helps increase la_size.

--

[PATCH 16/16] io: reduce lantency

[Wu Fengguang]

[-- Attachment #1: io-low-delay.patch --]
[-- Type: text/plain, Size: 1490 bytes --]

This is recommended by Con Kolivas to improve respond time for desktop.

Since the VM_MAX_READAHEAD is greatly enlarged, it may be necessary to insert
some cond_resched() calls. Correct me, I'm not quite sure about the effects.

Signed-off-by: Wu Fengguang <wfg@mail.ustc.edu.cn>
---


 fs/mpage.c     |    4 +++-
 mm/readahead.c |    5 ++++-
 2 files changed, 7 insertions(+), 2 deletions(-)

--- linux-2.6.14-mm1.orig/mm/readahead.c
+++ linux-2.6.14-mm1/mm/readahead.c
@@ -582,8 +582,10 @@ static int read_pages(struct address_spa
 		if (!add_to_page_cache(page, mapping,
 					page->index, GFP_KERNEL)) {
 			mapping->a_ops->readpage(filp, page);
-			if (!pagevec_add(&lru_pvec, page))
+			if (!pagevec_add(&lru_pvec, page)) {
 				__pagevec_lru_add(&lru_pvec);
+				cond_resched();
+			}
 		} else {
 			page_cache_release(page);
 		}
@@ -701,6 +703,7 @@ __do_page_cache_readahead(struct address
 		}
 
 		read_unlock_irq(&mapping->tree_lock);
+		cond_resched();
 		page = page_cache_alloc_cold(mapping);
 		read_lock_irq(&mapping->tree_lock);
 		if (!page)
--- linux-2.6.14-mm1.orig/fs/mpage.c
+++ linux-2.6.14-mm1/fs/mpage.c
@@ -343,8 +343,10 @@ mpage_readpages(struct address_space *ma
 			bio = do_mpage_readpage(bio, page,
 					nr_pages - page_idx,
 					&last_block_in_bio, get_block);
-			if (!pagevec_add(&lru_pvec, page))
+			if (!pagevec_add(&lru_pvec, page)) {
 				__pagevec_lru_add(&lru_pvec);
+				cond_resched();
+			}
 		} else {
 			page_cache_release(page);
 		}

--

Re: [PATCH 00/16] Adaptive read-ahead V7

[Christoph Lameter]

Would you cc Nick Piggin on the radix tree patches? He has some work in 
progress that may have to be synced between both of you.

Re: [PATCH 00/16] Adaptive read-ahead V7

[Wu Fengguang]

On Wed, Nov 09, 2005 at 12:39:56PM -0800, Christoph Lameter wrote:
> Would you cc Nick Piggin on the radix tree patches? He has some work in 
> progress that may have to be synced between both of you.
Ok, I should have cc'ed him, but thanks for your reminding anyway :)

Regards,
Wu