Skip to contentSkip to conversation

Kernel BUG at rmap:482

DISCUSSION hib2743 2 participants 2 messages Mar 19, 2005

Subsystems (4)
lore
Share & tools
lore

hib2743

author
#0 lore raw

Dear All,
I have seen discussion about this in recent months on the list, and
unfortunately I am experiencing the same problem myself now on a new machine. I have run memtest86 for some hours and there seems to be no problem. The machine has 1GB DDR PC3200 RAM/AMD Athlon(tm) 64 Processor 3500+/ASUS A8V motherboard/120GB Seagate SATA HDD. If you have a patch you would like me to try I am willing to have a go, this is a new machine which I waiting to deploy, so there is no production data on it at all yet. I can reproduce the problem fairly regularly, just set the machine to compile something big like glibc, and I get it within an hour usually...

Thanks a lot!
Regards,

Kernel: Linux newlog 2.6.11.4 #1 Sat Mar 19 15:10:16 CET 2005 x86_64 AMD Athlon(tm) 64 Processor 3500+ AuthenticAMD GNU/Linux

Report in log:

Kernel BUG at rmap:482
invalid operand: 0000 [1] 
CPU 0 
Modules linked in: usb_storage ohci_hcd uhci_hcd ehci_hcd
Pid: 16405, comm: sh Not tainted 2.6.11.4
RIP: 0010:[<ffffffff80162e25>] <ffffffff80162e25>{page_remove_rmap+37}
RSP: 0018:ffff810035fa3de0  EFLAGS: 00010296
RAX: 00000000ff000000 RBX: 0000000000006000 RCX: ffffffff804af3a0
RDX: 0000000000000000 RSI: 0000000000000001 RDI: ffff810001a7a928
RBP: ffff81003622f030 R08: ffff810001a7a928 R09: ffff810035fa3f00
R10: ffff81003196d7b8 R11: ffff81003196d7a8 R12: 0000000000041000
R13: 0000000000000020 R14: 0000000000000000 R15: 0000000000600000
FS:  00002aaaaaff36d0(0000) GS:ffffffff804eeb00(0000)

knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b
CR2: 00000000006367d8 CR3: 000000002ecb8000 CR4: 00000000000006e0 Process sh (pid: 16405, threadinfo ffff810035fa2000, task ffff81003f3cf680)

Stack: ffffffff8015bc86 0000000000000001 ffff810001a7a928
0000000000640fff 
       00000000405eb000 0000000000641000 ffff810035223018
ffff810035222000 
       000000008015f21c ffff81002ecb8000 
Call Trace:<ffffffff8015bc86>{unmap_vmas+1542}
<ffffffff8015fe51>{do_munmap+465} 
       <ffffffff80160b6f>{sys_brk+143} <ffffffff8010e1fa>{system_call

+126}

Code: 0f 0b 95 5e 39 80 ff ff ff ff e2 01 48 c7 c6 ff ff ff ff bf 

RIP <ffffffff80162e25>{page_remove_rmap+37} RSP <ffff810035fa3de0>

#1 lore raw
Quoted 10 lines · On Sat, 19 Mar 2005, hib2743 wrote:

I have seen discussion about this in recent months on the list, and
unfortunately I am experiencing the same problem myself now on a new machine. I have run memtest86 for some hours and there seems to be no problem. The machine has 1GB DDR PC3200 RAM/AMD Athlon(tm) 64 Processor 3500+/ASUS A8V motherboard/120GB Seagate SATA HDD. If you have a patch you would like me to try I am willing to have a go, this is a new machine which I waiting to deploy, so there is no production data on it at all yet. I can reproduce the problem fairly regularly, just set the machine to compile something big like glibc, and I get it within an hour usually...

That's the first sighting I've heard of on x86_64: I've only tried the patch on i386, but it should be good for x86_64 too. Please do give it a try, and report back (probably better just to me) what "Bad rmap" and "Bad page state" messages you then find. As a side-effect, it should allow you to go on running (showing more messages) for longer.

Thanks,
Hugh

include/linux/rmap.h +1 -1
@@ -72,7 +72,7 @@ void __anon_vma_link(struct vm_area_stru
  */
 void page_add_anon_rmap(struct page *, struct vm_area_struct *, unsigned long);
 void page_add_file_rmap(struct page *);
-void page_remove_rmap(struct page *);
+void page_remove_rmap(struct page *, struct vm_area_struct *, unsigned long);
 
 /**
  * page_dup_rmap - duplicate pte mapping to a page
mm/fremap.c +1 -1
@@ -37,7 +37,7 @@ static inline void zap_pte(struct mm_str
 			if (!PageReserved(page)) {
 				if (pte_dirty(pte))
 					set_page_dirty(page);
-				page_remove_rmap(page);
+				page_remove_rmap(page, vma, addr);
 				page_cache_release(page);
 				mm->rss--;
 			}
mm/memory.c +8 -5
@@ -452,6 +452,7 @@ next_pgd:
 }
 
 static void zap_pte_range(struct mmu_gather *tlb,
+		struct vm_area_struct *vma,
 		pmd_t *pmd, unsigned long address,
 		unsigned long size, struct zap_details *details)
 {
@@ -517,7 +518,7 @@ static void zap_pte_range(struct mmu_gat
 			else if (pte_young(pte))
 				mark_page_accessed(page);
 			tlb->freed++;
-			page_remove_rmap(page);
+			page_remove_rmap(page, vma, address+offset);
 			tlb_remove_page(tlb, page);
 			continue;
 		}
@@ -535,6 +536,7 @@ static void zap_pte_range(struct mmu_gat
 }
 
 static void zap_pmd_range(struct mmu_gather *tlb,
+		struct vm_area_struct *vma,
 		pud_t *pud, unsigned long address,
 		unsigned long size, struct zap_details *details)
 {
@@ -553,13 +555,14 @@ static void zap_pmd_range(struct mmu_gat
 	if (end > ((address + PUD_SIZE) & PUD_MASK))
 		end = ((address + PUD_SIZE) & PUD_MASK);
 	do {
-		zap_pte_range(tlb, pmd, address, end - address, details);
+		zap_pte_range(tlb, vma, pmd, address, end - address, details);
 		address = (address + PMD_SIZE) & PMD_MASK; 
 		pmd++;
 	} while (address && (address < end));
 }
 
 static void zap_pud_range(struct mmu_gather *tlb,
+		struct vm_area_struct *vma,
 		pgd_t * pgd, unsigned long address,
 		unsigned long end, struct zap_details *details)
 {
@@ -574,7 +577,7 @@ static void zap_pud_range(struct mmu_gat
 	}
 	pud = pud_offset(pgd, address);
 	do {
-		zap_pmd_range(tlb, pud, address, end - address, details);
+		zap_pmd_range(tlb, vma, pud, address, end - address, details);
 		address = (address + PUD_SIZE) & PUD_MASK; 
 		pud++;
 	} while (address && (address < end));
@@ -595,7 +598,7 @@ static void unmap_page_range(struct mmu_
 		next = (address + PGDIR_SIZE) & PGDIR_MASK;
 		if (next <= address || next > end)
 			next = end;
-		zap_pud_range(tlb, pgd, address, next, details);
+		zap_pud_range(tlb, vma, pgd, address, next, details);
 		address = next;
 		pgd++;
 	}
@@ -1343,7 +1346,7 @@ static int do_wp_page(struct mm_struct *
 			acct_update_integrals();
 			update_mem_hiwater();
 		} else
-			page_remove_rmap(old_page);
+			page_remove_rmap(old_page, vma, address);
 		break_cow(vma, new_page, address, page_table);
 		lru_cache_add_active(new_page);
 		page_add_anon_rmap(new_page, vma, address);
mm/page_alloc.c +2 -2
@@ -276,7 +276,7 @@ static inline void __free_pages_bulk (st
 
 static inline void free_pages_check(const char *function, struct page *page)
 {
-	if (	page_mapped(page) ||
+	if (	page_mapcount(page) ||
 		page->mapping != NULL ||
 		page_count(page) != 0 ||
 		(page->flags & (
@@ -404,7 +404,7 @@ void set_page_refs(struct page *page, in
  */
 static void prep_new_page(struct page *page, int order)
 {
-	if (page->mapping || page_mapped(page) ||
+	if (page->mapping || page_mapcount(page) ||
 	    (page->flags & (
 			1 << PG_private	|
 			1 << PG_locked	|
mm/rmap.c +40 -5

74 lines not on this page · raw message