Re: 2.6.16-rc1-mm3

[Nick Piggin]

Hi,

Michal Piotrowski wrote:
> ------------[ cut here ]------------
> kernel BUG at /usr/src/linux-mm/include/linux/mm.h:302!
> invalid opcode: 0000 [#1]
> PREEMPT SMP DEBUG_PAGEALLOC
> last sysfs file: /class/vc/vcsa7/dev
> Modules linked in: binfmt_misc thermal fan processor ipv6 w83627hf
> hwmon_vid hwmon i2c_isa snd_intel8x0 snd_ac97_codec snd_ac97_bus
> sk98lin snd_pcm_oss snd_mixer_oss skge intel_agp snd_pcm snd_timer snd
> soundcore i2c_i801 parport_pc parport snd_page_alloc 8250_pnp 8250
> serial_core agpgart rtc ide_cd cdrom hw_random unix
> CPU:    0
> EIP:    0060:[<b013fe81>]    Not tainted VLI
> EFLAGS: 00210246   (2.6.16-rc1-mm3 #1)
> EIP is at release_pages+0x33/0x15e

Is it repeatable?

If so, I'd imagine it must be a specific driver page which is not properly
refcounted somewhere. A bug in generic code would have shown up elsewhere
by now.

Can you try something like the attached patch and see what it gives you?

Thanks,
Nick

--
SUSE Labs, Novell Inc.

Index: linux-2.6/include/linux/mm.h
===================================================================
--- linux-2.6.orig/include/linux/mm.h
+++ linux-2.6/include/linux/mm.h
@@ -15,6 +15,7 @@
 #include <linux/prio_tree.h>
 #include <linux/fs.h>
 #include <linux/mutex.h>
+#include <linux/kallsyms.h>
 
 struct mempolicy;
 struct anon_vma;
@@ -264,6 +265,8 @@ struct page {
 	void *virtual;			/* Kernel virtual address (NULL if
 					   not kmapped, ie. highmem) */
 #endif /* WANT_PAGE_VIRTUAL */
+
+	void *debug;
 };
 
 #define page_private(page)		((page)->private)
@@ -294,8 +297,14 @@ struct page {
  */
 static inline int put_page_testzero(struct page *page)
 {
-	BUG_ON(atomic_read(&page->_count) == 0);
-	return atomic_dec_and_test(&page->_count);
+	if (unlikely(atomic_read(&page->_count) == 0)) {
+		printk(KERN_WARNING "put_page_testzero found free page (flags = %lx)\n", page->flags);
+		if (page->debug)
+			print_symbol(KERN_WARNING "nopage is %s\n", (unsigned long)page->debug);
+		WARN_ON(1);
+		return 0;
+	} else
+		return atomic_dec_and_test(&page->_count);
 }
 
 /*
Index: linux-2.6/mm/memory.c
===================================================================
--- linux-2.6.orig/mm/memory.c
+++ linux-2.6/mm/memory.c
@@ -2056,6 +2056,8 @@ retry:
 	if (new_page == NOPAGE_OOM)
 		return VM_FAULT_OOM;
 
+	new_page->debug = (struct address_space *)vma->vm_ops->nopage;
+
 	/*
 	 * Should we do an early C-O-W break?
 	 */
Index: linux-2.6/mm/page_alloc.c
===================================================================
--- linux-2.6.orig/mm/page_alloc.c
+++ linux-2.6/mm/page_alloc.c
@@ -521,6 +521,8 @@ static int prep_new_page(struct page *pa
 	if (PageReserved(page))
 		return 1;
 
+	page->debug = NULL;
+
 	page->flags &= ~(1 << PG_uptodate | 1 << PG_error |
 			1 << PG_referenced | 1 << PG_arch_1 |
 			1 << PG_checked | 1 << PG_mappedtodisk);