From: Kamalesh Babulal Subject: [BUG] Linux 2.6.25-rc6 - kernel BUG at fs/mpage.c:476! on powerpc Date: Thu, 20 Mar 2008 13:13:01 +0530 Message-ID: <47E21585.1050603@linux.vnet.ibm.com> References: Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Cc: jfs-discussion@lists.sourceforge.net, linuxppc-dev@ozlabs.org, shaggy@austin.ibm.com, Andy Whitcroft , Andrew Morton , linux-ext4@vger.kernel.org, Balbir Singh To: Linux Kernel Mailing List Return-path: In-Reply-To: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Sender: jfs-discussion-bounces@lists.sourceforge.net Errors-To: jfs-discussion-bounces@lists.sourceforge.net List-Id: linux-ext4.vger.kernel.org When filesystem stress on ext2/3 mounted partition with the 2.6.25-rc6 kernel over the powerpc box, following calls traces are seen for more than 1000 times. And when the file system stress in run on jfs mounted partition kernel bug is seen. INFO: task fsstress:30559 blocked for more than 120 seconds. "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. Call Trace: [c0000000ec09f580] [c0000000ec09f620] 0xc0000000ec09f620 (unreliable) [c0000000ec09f750] [c0000000000108ec] .__switch_to+0x11c/0x154 [c0000000ec09f7e0] [c0000000004a644c] .schedule+0x7a4/0x888 [c0000000ec09f8d0] [c000000000111adc] .inode_wait+0x10/0x28multiple [c0000000ec09f950] [c0000000004a6e64] .__wait_on_bit+0xa0/0x114 [c0000000ec09fa00] [c00000000011fc10] .__writeback_single_inode+0x124/0x360 [c0000000ec09faf0] [c000000000120308] .sync_sb_inodes+0x220/0x358 [c0000000ec09fba0] [c00000000012051c] .sync_inodes_sb+0xdc/0x120 [c0000000ec09fc80] [c000000000120614] .__sync_inodes+0xb4/0x164 [c0000000ec09fd20] [c00000000012419c] .do_sync+0x74/0xc0 [c0000000ec09fdb0] [c0000000001241fc] .sys_sync+0x14/0x28 [c0000000ec09fe30] [c000000000008734] syscall_exit+0x0/0x40 INFO: task fsstress:30853 blocked for more than 120 seconds. "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. Call Trace: [c000000096f1f1c0] [c000000096f1f280] 0xc000000096f1f280 (unreliable) [c000000096f1f390] [c0000000000108ec] .__switch_to+0x11c/0x154 [c000000096f1f420] [c0000000004a644c] .schedule+0x7a4/0x888 [c000000096f1f510] [c0000000004a6a2c] .io_schedule+0x7c/0xe8 [c000000096f1f5a0] [c000000000126ce8] .sync_buffer+0x68/0x80 [c000000096f1f620] [c0000000004a6c80] .__wait_on_bit_lock+0x8c/0x110 [c000000096f1f6c0] [c0000000004a6d98] .out_of_line_wait_on_bit_lock+0x94/0xc0 [c000000096f1f7b0] [c000000000126fc0] .__lock_buffer+0x48/0x60 [c000000096f1f830] [c000000000128e24] .__bread+0x64/0x108 [c000000096f1f8b0] [c0000000001f0664] .ext2_get_inode+0xf8/0x194 [c000000096f1f950] [c0000000001f0764] .ext2_update_inode+0x64/0x4e4 [c000000096f1fa20] [c00000000011fcf0] .__writeback_single_inode+0x204/0x360 [c000000096f1fb10] [c000000000120af4] .sync_inode+0x44/0x88 [c000000096f1fba0] [c0000000001f0550] .ext2_sync_inode+0x44/0x60 [c000000096f1fc70] [c0000000001eee90] .ext2_sync_file+0x54/0x84 [c000000096f1fd00] [c000000000123f50] .do_fsync+0x90/0x10c [c000000096f1fda0] [c000000000124000] .__do_fsync+0x34/0x60 [c000000096f1fe30] [c000000000008734] syscall_exit+0x0/0x40 INFO: task fsstress:30859 blocked for more than 120 seconds. "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. Call Trace: [c0000000b228f240] [c0000000b228f2e0] 0xc0000000b228f2e0 (unreliable) [c0000000b228f410] [c0000000000108ec] .__switch_to+0x11c/0x154 [c0000000b228f4a0] [c0000000004a644c] .schedule+0x7a4/0x888 [c0000000b228f590] [c0000000004a6a2c] .io_schedule+0x7c/0xe8 [c0000000b228f620] [c000000000126ce8] .sync_buffer+0x68/0x80 [c0000000b228f6a0] [c0000000004a6e64] .__wait_on_bit+0xa0/0x114 [c0000000b228f750] [c0000000004a6f6c] .out_of_line_wait_on_bit+0x94/0xc0 [c0000000b228f840] [c000000000126bac] .__wait_on_buffer+0x30/0x48 [c0000000b228f8c0] [c00000000012a30c] .sync_dirty_buffer+0xf0/0x160 [c0000000b228f950] [c0000000001f0af8] .ext2_update_inode+0x3f8/0x4e4 [c0000000b228fa20] [c00000000011fcf0] .__writeback_single_inode+0x204/0x360 [c0000000b228fb10] [c000000000120af4] .sync_inode+0x44/0x88 [c0000000b228fba0] [c0000000001f0550] .ext2_sync_inode+0x44/0x60 [c0000000b228fc70] [c0000000001eee90] .ext2_sync_file+0x54/0x84 [c0000000b228fd00] [c000000000123f50] .do_fsync+0x90/0x10c [c0000000b228fda0] [c000000000124000] .__do_fsync+0x34/0x60 [c0000000b228fe30] [c000000000008734] syscall_exit+0x0/0x40 INFO: task fsstress:30863 blocked for more than 120 seconds. "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. Call Trace: [c0000000b239f250] [c0000000b239f340] 0xc0000000b239f340 (unreliable) [c0000000b239f420] [c0000000000108ec] .__switch_to+0x11c/0x154 [c0000000b239f4b0] [c0000000004a644c] .schedule+0x7a4/0x888 [c0000000b239f5a0] [c0000000004a6a2c] .io_schedule+0x7c/0xe8 [c0000000b239f630] [c000000000126ce8] .sync_buffer+0x68/0x80 [c0000000b239f6b0] [c0000000004a6c80] .__wait_on_bit_lock+0x8c/0x110 [c0000000b239f750] [c0000000004a6d98] .out_of_line_wait_on_bit_lock+0x94/0xc0 [c0000000b239f840] [c000000000126fc0] .__lock_buffer+0x48/0x60 [c0000000b239f8c0] [c00000000012a28c] .sync_dirty_buffer+0x70/0x160 [c0000000b239f950] [c0000000001f0af8] .ext2_update_inode+0x3f8/0x4e4 [c0000000b239fa20] [c00000000011fcf0] .__writeback_single_inode+0x204/0x360 [c0000000b239fb10] [c000000000120af4] .sync_inode+0x44/0x88 [c0000000b239fba0] [c0000000001f0550] .ext2_sync_inode+0x44/0x60 [c0000000b239fc70] [c0000000001eee90] .ext2_sync_file+0x54/0x84 [c0000000b239fd00] [c000000000123f50] .do_fsync+0x90/0x10c [c0000000b239fda0] [c000000000124000] .__do_fsync+0x34/0x60 [c0000000b239fe30] [c000000000008734] syscall_exit+0x0/0x40 (gdb) p __switch_to $1 = {struct task_struct *(struct task_struct *, struct task_struct *)} 0xc0000000000107d0 <__switch_to> (gdb) p/x 0xc0000000000107d0+0x11c $2 = 0xc0000000000108ec (gdb) l *0xc0000000000108ec 0xc0000000000108ec is in __switch_to (arch/powerpc/kernel/process.c:356). 351 352 account_system_vtime(current); 353 account_process_vtime(current); 354 calculate_steal_time(); 355 356 last = _switch(old_thread, new_thread); 357 358 local_irq_restore(flags); 359 360 return last; (gdb) p schedule $3 = {void (void)} 0xc0000000004a5ca8 <.schedule> (gdb) p/x 0xc0000000004a5ca8+0x7a4 $4 = 0xc0000000004a644c (gdb) l *0xc0000000004a644c 0xc0000000004a644c is at include/asm/current.h:22. 17 18 static inline struct task_struct *get_current(void) 19 { 20 struct task_struct *task; 21 22 __asm__ __volatile__("ld %0,%1(13)" 23 : "=r" (task) 24 : "i" (offsetof(struct paca_struct, __current))); 25 26 return task; kernel BUG at fs/mpage.c:476! cpu 0x0: Vector: 700 (Program Check) at [c0000000c28debd0] pc: c00000000012f588: .__mpage_writepage+0xd0/0x618 lr: c0000000000c79c0: .write_cache_pages+0x228/0x3e8 sp: c0000000c28dee50 msr: 8000000000029032 current = 0xc000000060ac5850 paca = 0xc000000000663b00 pid = 5254, comm = fsstress kernel BUG at fs/mpage.c:476! enter ? for help [c0000000c28df3d0] c0000000000c79c0 .write_cache_pages+0x228/0x3e8 [c0000000c28df540] c00000000012fb84 .mpage_writepages+0x54/0x8c [c0000000c28df5e0] c0000000001fe748 .jfs_writepages+0x1c/0x34 [c0000000c28df660] c0000000000c7c20 .do_writepages+0x68/0xa4 [c0000000c28df6e0] c0000000000bfbc0 .__filemap_fdatawrite_range+0x88/0xb8 [c0000000c28df7d0] c0000000000bfe9c .filemap_write_and_wait+0x2c/0x68 [c0000000c28df860] c0000000000c0848 .generic_file_buffered_write+0x65c/0x6c8 [c0000000c28df9a0] c0000000000c0bb4 .__generic_file_aio_write_nolock+0x300/0x3ec [c0000000c28dfaa0] c0000000000c0d20 .generic_file_aio_write+0x80/0x114 [c0000000c28dfb60] c0000000000f7d7c .do_sync_write+0xc4/0x124 [c0000000c28dfcf0] c0000000000f85b0 .vfs_write+0xd8/0x1a4 [c0000000c28dfd90] c0000000000f8f3c .sys_write+0x4c/0x8c [c0000000c28dfe30] c000000000008734 syscall_exit+0x0/0x40 --- Exception: c01 (System Call) at 000000000ff0d8c8 SP (ffb4c8a0) is in userspace (gdb) p write_cache_pages $1 = {int (struct address_space *, struct writeback_control *, writepage_t, void *)} 0xc0000000000c7798 (gdb) p/x 0xc0000000000c7798+0x228 $2 = 0xc0000000000c79c0 (gdb) l *0xc0000000000c79c0 0xc0000000000c79c0 is in write_cache_pages (mm/page-writeback.c:867). 862 !clear_page_dirty_for_io(page)) { 863 unlock_page(page); 864 continue; 865 } 866 867 ret = (*writepage)(page, wbc, data); 868 869 if (unlikely(ret == AOP_WRITEPAGE_ACTIVATE)) { 870 unlock_page(page); 871 ret = 0; (gdb) p __mpage_writepage $3 = {int (struct page *, struct writeback_control *, void *)} 0xc00000000012f4b8 <__mpage_writepage> (gdb) p/x 0xc00000000012f4b8+0xd0 $4 = 0xc00000000012f588 (gdb) l *0xc00000000012f588 0xc00000000012f588 is in __mpage_writepage (fs/mpage.c:476). 471 struct buffer_head *bh = head; 472 473 /* If they're all mapped and dirty, do it */ 474 page_block = 0; 475 do { 476 BUG_ON(buffer_locked(bh)); 477 if (!buffer_mapped(bh)) { 478 /* 479 * unmapped dirty buffers are created by 480 * __set_page_dirty_buffers -> mmapped data (gdb) -- Thanks & Regards, Kamalesh Babulal, Linux Technology Center, IBM, ISTL. ------------------------------------------------------------------------- This SF.net email is sponsored by: Microsoft Defy all challenges. Microsoft(R) Visual Studio 2008. http://clk.atdmt.com/MRT/go/vse0120000070mrt/direct/01/