2.6.25 BUG: soft lockup
Subsystems (3)
On a Sempron laptop with kernel 2.6.24.4, I am getting this reliably after a few minutes of uptime. I am also seeing all accesses to /dev/hda stuck permanently in D state after that, though I don't know if that's related. Both are repeatable, though.
clipped from dmesg:
----------------------------------------------------
BUG: soft lockup - CPU#0 stuck for 61s! [swapper:0]
Pid: 0, comm: swapper Not tainted (2.6.25 #1)
EIP: 0060:[<c0132a9f>] EFLAGS: 00000293 CPU: 0 EIP is at tick_broadcast_oneshot_control+0xb8/0xc4
EAX: 00000293 EBX: c07020d0 ECX: 00000f6c EDX: c213edcf
ESI: 00000293 EDI: c0631460 EBP: 00000000 ESP: c0686f5c
DS: 007b ES: 007b FS: 0000 GS: 0000 SS: 0068
CR0: 8005003b CR2: 084b5e90 CR3: 0acd2000 CR4: 000006d0
DR0: 00000000 DR1: 00000000 DR2: 00000000 DR3: 00000000
DR6: ffff0ff0 DR7: 00000400
[<c0132572>] tick_notify+0x185/0x294 [<c0496e75>] notifier_call_chain+0x2a/0x47 [<c012ebe4>] raw_notifier_call_chain+0x9/0xc [<c0132116>] clockevents_notify+0x11/0x45 [<c02ab0dd>] acpi_idle_enter_simple+0x1b6/0x20d [<c039b66e>] cpuidle_idle_call+0x56/0x85 [<c039b618>] cpuidle_idle_call+0x0/0x85 [<c0105974>] default_idle+0x0/0x74 [<c010595b>] cpu_idle+0x49/0x62
and from Alt-SysRq-t:
------------------------------------------
cp D c063b34c 0 5813 1087
c062c320 00000082 00120050 c063b34c c5721c74 c074c980 00000282 003faf08
003faf08 c5721cb4 00000000 c049457e c074c9c8 c074c9c8 003faf08 c012413e
c9ee4590 c074c980 c070bd98 c063b480 c0493ff9 00000005 c014ea6c 00000000
Call Trace:
[<c049457e>] schedule_timeout+0x72/0x8d
[<c012413e>] process_timeout+0x0/0x5
[<c0493ff9>] __sched_text_start+0x11/0x19
[<c014ea6c>] congestion_wait+0x4c/0x60
[<c012bcbe>] autoremove_wake_function+0x0/0x2d
[<c0149f0b>] __alloc_pages+0x282/0x2cd
[<c0145e9d>] find_or_create_page+0x6d/0xa0
[<c017d190>] __getblk+0x135/0x2a7
[<c01bc24b>] ext3_mark_inode_dirty+0x29/0x30
[<c01b93a3>] read_block_bitmap+0x37/0x11f
[<c01b9e3e>] ext3_new_blocks+0x176/0x4b8
[<c01bd401>] ext3_get_blocks_handle+0x32f/0x777
[<c01c8e63>] do_get_write_access+0x2d2/0x30d
[<c01c83e8>] __journal_file_buffer+0x7d/0xfe
[<c01c84ea>] journal_dirty_metadata+0x7c/0x82
[<c01c5d3f>] __ext3_journal_dirty_metadata+0x13/0x32
[<c01bbb45>] ext3_mark_iloc_dirty+0x268/0x2c0
[<c01c0a59>] ext3_mkdir+0x0/0x23f
[<c01bd950>] ext3_getblk+0x4a/0x15c
[<c01c92aa>] start_this_handle+0x213/0x26e
[<c016965f>] permission+0x85/0xc1
[<c01c0a59>] ext3_mkdir+0x0/0x23f
[<c01bda75>] ext3_bread+0x13/0x63
[<c01c0a59>] ext3_mkdir+0x0/0x23f
[<c01c0b16>] ext3_mkdir+0xbd/0x23f
[<c01c8191>] ext3_permission+0x0/0xa
[<c01c0a59>] ext3_mkdir+0x0/0x23f
[<c016a1b3>] vfs_mkdir+0x54/0x91
[<c016bc67>] sys_mkdirat+0x84/0xb9
[<c016bcab>] sys_mkdir+0xf/0x13
[<c010681a>] syscall_call+0x7/0xb
=======================Quoted 67 lines · Eric Buddington
On a Sempron laptop with kernel 2.6.24.4, I am getting this reliably
after a few minutes of uptime. I am also seeing all accesses to/dev/hdastuck permanently in D state after that, though I don't know if that's related. Both are repeatable, though.clipped from dmesg:
----------------------------------------------------BUG: soft lockup - CPU#0 stuck for 61s! [swapper:0]Pid: 0, comm: swapper Not tainted (2.6.25 #1)
EIP: 0060:[<c0132a9f>] EFLAGS: 00000293 CPU: 0 EIP is attick_broadcast_oneshot_control+0xb8/0xc4
EAX: 00000293 EBX:c07020d0ECX:00000f6cEDX:c213edcf
ESI: 00000293 EDI:c0631460EBP: 00000000 ESP:c0686f5c
DS: 007b ES: 007b FS: 0000 GS: 0000 SS: 0068
CR0:8005003bCR2:084b5e90CR3:0acd2000CR4:000006d0
DR0: 00000000 DR1: 00000000 DR2: 00000000 DR3: 00000000
DR6:ffff0ff0DR7: 00000400[<c0132572>] tick_notify+0x185/0x294 [<c0496e75>] notifier_call_chain+0x2a/0x47 [<c012ebe4>] raw_notifier_call_chain+0x9/0xc [<c0132116>] clockevents_notify+0x11/0x45 [<c02ab0dd>] acpi_idle_enter_simple+0x1b6/0x20d [<c039b66e>] cpuidle_idle_call+0x56/0x85 [<c039b618>] cpuidle_idle_call+0x0/0x85 [<c0105974>] default_idle+0x0/0x74 [<c010595b>] cpu_idle+0x49/0x62and from Alt-SysRq-t:
------------------------------------------
cp Dc063b34c0 5813 1087c062c320 00000082 00120050 c063b34c c5721c74 c074c980 00000282 003faf08 003faf08 c5721cb4 00000000 c049457e c074c9c8 c074c9c8 003faf08 c012413e c9ee4590 c074c980 c070bd98 c063b480 c0493ff9 00000005 c014ea6c 00000000 Call Trace: [<c049457e>] schedule_timeout+0x72/0x8d [<c012413e>] process_timeout+0x0/0x5 [<c0493ff9>] __sched_text_start+0x11/0x19 [<c014ea6c>] congestion_wait+0x4c/0x60 [<c012bcbe>] autoremove_wake_function+0x0/0x2d [<c0149f0b>] __alloc_pages+0x282/0x2cd [<c0145e9d>] find_or_create_page+0x6d/0xa0 [<c017d190>] __getblk+0x135/0x2a7 [<c01bc24b>] ext3_mark_inode_dirty+0x29/0x30 [<c01b93a3>] read_block_bitmap+0x37/0x11f [<c01b9e3e>] ext3_new_blocks+0x176/0x4b8 [<c01bd401>] ext3_get_blocks_handle+0x32f/0x777 [<c01c8e63>] do_get_write_access+0x2d2/0x30d [<c01c83e8>] __journal_file_buffer+0x7d/0xfe [<c01c84ea>] journal_dirty_metadata+0x7c/0x82 [<c01c5d3f>] __ext3_journal_dirty_metadata+0x13/0x32 [<c01bbb45>] ext3_mark_iloc_dirty+0x268/0x2c0 [<c01c0a59>] ext3_mkdir+0x0/0x23f [<c01bd950>] ext3_getblk+0x4a/0x15c [<c01c92aa>] start_this_handle+0x213/0x26e [<c016965f>] permission+0x85/0xc1 [<c01c0a59>] ext3_mkdir+0x0/0x23f [<c01bda75>] ext3_bread+0x13/0x63 [<c01c0a59>] ext3_mkdir+0x0/0x23f [<c01c0b16>] ext3_mkdir+0xbd/0x23f [<c01c8191>] ext3_permission+0x0/0xa [<c01c0a59>] ext3_mkdir+0x0/0x23f [<c016a1b3>] vfs_mkdir+0x54/0x91 [<c016bc67>] sys_mkdirat+0x84/0xb9
Quoted 9 lines
[<c016bcab>] sys_mkdir+0xf/0x13 [<c010681a>] syscall_call+0x7/0xb ======================= -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to [email protected] More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
Hello; This looks similar to what I was expireincing putting nohz=off keeps the system from freezing,
Peter Zijlstra gave me this patch to use, which worked for me. The only problem I had is patch -p1 < xxx.patch seemed to not work for me. but worked for Peter.
arch/x86/kernel/apm_32.c | 3 + arch/x86/kernel/process.c | 117 +++++++++++++++++++++++++++++++++++++++ arch/x86/kernel/process_32.c | 118 +--------------------------------------- arch/x86/kernel/process_64.c | 123 +----------------------------------------- drivers/acpi/processor_idle.c | 19 +++--- include/asm-x86/processor.h | 1 6 files changed, 137 insertions(+), 244 deletions(-)
arch/x86/kernel/process_32.c +4 -114
@@ -111,12 +111,10 @@ void default_idle(void)*/ smp_mb (); -local_irq_disable (); -if (!need_resched ()) { +if (!need_resched ())safe_halt ();/* enables interrupts racelessly */ -local_irq_disable (); - } -local_irq_enable (); +else +local_irq_enable ();current_thread_info ()->status |=TS_POLLING ; }else {local_irq_enable ();
@@ -128,17 +126,6 @@ void default_idle(void)EXPORT_SYMBOL (default_idle);#endif -/* -* On SMP it's slightly faster (but much more power-consuming!) -* to poll the ->work.need_resched flag instead of waiting for the -* cross-CPU IPI to arrive. Use this option with caution. -*/ -static void poll_idle (void ) -{ -local_irq_enable (); -cpu_relax (); -} -#ifdef CONFIG_HOTPLUG_CPU #include <asm/nmi.h> /* We don't actually take CPU down, just spin without interrupts. */
@@ -196,6 +183,7 @@ void cpu_idle(void)if (cpu_is_offline (cpu))play_dead (); +local_irq_disable ();__get_cpu_var (irq_stat).idle_timestamp = jiffies;idle (); }
@@ -206,104 +194,6 @@ void cpu_idle(void) } } -static void do_nothing (void *unused) -{ -} - -/* -* cpu_idle_wait - Used to ensure that all the CPUs discard old value of -* pm_idle and update to new pm_idle value. Required while changing pm_idle -* handler on SMP systems. -* -* Caller must have changed pm_idle to the new value before the call. Old -* pm_idle value will not be used by any CPU after the return of this function. -*/ -void cpu_idle_wait (void ) -{ -smp_mb (); -/* kick all the CPUs so that they exit out of pm_idle */ -smp_call_function (do_nothing,NULL ,0 ,1 ); -} -EXPORT_SYMBOL_GPL (cpu_idle_wait); - -/* -* This uses new MONITOR/MWAIT instructions on P4 processors with PNI, -* which can obviate IPI to trigger checking of need_resched. -* We execute MONITOR against need_resched and enter optimized wait state -* through MWAIT. Whenever someone changes need_resched, we would be woken -* up from MWAIT (without an IPI). -* -* New with Core Duo processors, MWAIT can take some hints based on CPU -* capability. -*/ -void mwait_idle_with_hints (unsigned long ax,unsigned long cx) -{ -if (!need_resched ()) { -__monitor ((void *)¤t_thread_info ()->flags,0 ,0 ); -smp_mb (); -if (!need_resched ()) -__sti_mwait (ax, cx); -else -local_irq_enable (); - }else -local_irq_enable (); -} - -/* Default MONITOR/MWAIT with no hints, used for default C1 state */ -static void mwait_idle (void ) -{ -local_irq_enable (); -mwait_idle_with_hints (0 ,0 ); -} - -static int __cpuinit mwait_usable (const struct cpuinfo_x86 *c) -{ -if (force_mwait) -return 1 ; -/* Any C1 states supported? */ -return c->cpuid_level >=5 && ((cpuid_edx (5 ) >>4 ) &0xf ) >0 ; -} - -void __cpuinit select_idle_routine (const struct cpuinfo_x86 *c) -{ -static int selected; - -if (selected) -return ; -#ifdef CONFIG_X86_SMP -if (pm_idle == poll_idle && smp_num_siblings >1 ) { -printk (KERN_WARNING "WARNING: polling idle and HT enabled," -" performance may degrade.\n" ); - } -#endif -if (cpu_has (c,X86_FEATURE_MWAIT ) &&mwait_usable (c)) { -/* -* Skip, if setup has overridden idle. -* One CPU supports mwait => All CPUs supports mwait -*/ -if (!pm_idle) { -printk (KERN_INFO "using mwait in idle threads.\n" ); - pm_idle = mwait_idle; - } - } - selected =1 ; -} - -static int __init idle_setup (char *str) -{ -if (!strcmp (str,"poll" )) { -printk ("using polling idle threads.\n" ); - pm_idle = poll_idle; - }else if (!strcmp (str,"mwait" )) - force_mwait =1 ; -else -return -1 ; - - boot_option_idle_override =1 ; -return 0 ; -} -early_param ("idle" , idle_setup); -void __show_registers (struct pt_regs *regs,int all) {unsigned long cr0 =0L , cr2 =0L , cr3 =0L , cr4 =0L ;
arch/x86/kernel/process_64.c +3 -120
139 lines not on this page · raw message
drivers/acpi/processor_idle.c +9 -10
@@ -418,13 +418,12 @@ static void acpi_processor_idle(void) cx = pr->power.state;if (!cx || acpi_idle_suspend) { -if (pm_idle_save) -pm_idle_save (); -else +if (pm_idle_save) { +pm_idle_save ();/* enables IRQs */ + }else {acpi_safe_halt (); - -if (irqs_disabled ())local_irq_enable (); + }return ; }
@@ -520,10 +519,12 @@ static void acpi_processor_idle(void)* Use the appropriate idle routine, the one that would * be used without acpi C-states. */ -if (pm_idle_save) -pm_idle_save (); -else +if (pm_idle_save) { +pm_idle_save ();/* enables IRQs */ + }else {acpi_safe_halt (); +local_irq_enable (); + }/* * TBD: Can't get time duration while in C1, as resumes
@@ -534,8 +535,6 @@ static void acpi_processor_idle(void)* skew otherwise. */ sleep_ticks =0xFFFFFFFF ; -if (irqs_disabled ()) -local_irq_enable ();break ;
arch/x86/kernel/apm_32.c +3 -0
@@ -904,6 +904,7 @@ recalc:original_pm_idle (); elsedefault_idle (); +local_irq_disable (); jiffies_since_last_check = jiffies - last_jiffies;if (jiffies_since_last_check > idle_period) goto recalc;
@@ -911,6 +912,8 @@ recalc:if (apm_idle_done)apm_do_busy (); + +local_irq_enable (); }/**
include/asm-x86/processor.h +1 -0
@@ -723,6 +723,7 @@ static inline void __mwait(unsigned longstatic inline void __sti_mwait (unsigned long eax,unsigned long ecx) { +trace_hardirqs_on ();/* "mwait %eax, %ecx;" */ asmvolatile ("sti; .byte 0x0f, 0x01, 0xc9;" ::"a" (eax),"c" (ecx));
arch/x86/kernel/process.c +117 -0
126 lines not on this page · raw message
Hope this helps unfreeze you're computer
regards;
Signature · 1 line
Justin P. Mattock