From 80a8c9fffa78f57d7d4351af2f15a56386805ceb Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Tue, 19 Aug 2008 03:13:38 +0200 Subject: x86: fix oprofile + hibernation badness Vegard Nossum reported oprofile + hibernation problems: > Now some warnings: > > ------------[ cut here ]------------ > WARNING: at /uio/arkimedes/s29/vegardno/git-working/linux-2.6/kernel/smp.c:328 s > mp_call_function_mask+0x194/0x1a0() The usual problem: the suspend function when interrupts are already disabled calls smp_call_function which is not allowed with interrupt off. But at this point all the other CPUs should be already down anyways, so it should be enough to just drop that. This patch should fix that problem at least by fixing cpu hotplug& suspend support. [ mingo@elte.hu: fixed 5 coding style errors. ] Signed-off-by: Andi Kleen Tested-by: Vegard Nossum Signed-off-by: Ingo Molnar --- arch/x86/oprofile/nmi_int.c | 39 ++++++++++++++++++++++++++++++++++++--- 1 file changed, 36 insertions(+), 3 deletions(-) (limited to 'arch/x86/oprofile/nmi_int.c') diff --git a/arch/x86/oprofile/nmi_int.c b/arch/x86/oprofile/nmi_int.c index 3f90289410e..0227694f7da 100644 --- a/arch/x86/oprofile/nmi_int.c +++ b/arch/x86/oprofile/nmi_int.c @@ -15,6 +15,7 @@ #include #include #include +#include #include #include #include @@ -28,23 +29,48 @@ static DEFINE_PER_CPU(unsigned long, saved_lvtpc); static int nmi_start(void); static void nmi_stop(void); +static void nmi_cpu_start(void *dummy); +static void nmi_cpu_stop(void *dummy); /* 0 == registered but off, 1 == registered and on */ static int nmi_enabled = 0; +#ifdef CONFIG_SMP +static int oprofile_cpu_notifier(struct notifier_block *b, unsigned long action, + void *data) +{ + int cpu = (unsigned long)data; + switch (action) { + case CPU_DOWN_FAILED: + case CPU_ONLINE: + smp_call_function_single(cpu, nmi_cpu_start, NULL, 0); + break; + case CPU_DOWN_PREPARE: + smp_call_function_single(cpu, nmi_cpu_stop, NULL, 1); + break; + } + return NOTIFY_DONE; +} + +static struct notifier_block oprofile_cpu_nb = { + .notifier_call = oprofile_cpu_notifier +}; +#endif + #ifdef CONFIG_PM static int nmi_suspend(struct sys_device *dev, pm_message_t state) { + /* Only one CPU left, just stop that one */ if (nmi_enabled == 1) - nmi_stop(); + nmi_cpu_stop(NULL); return 0; } static int nmi_resume(struct sys_device *dev) { if (nmi_enabled == 1) - nmi_start(); + nmi_cpu_start(NULL); return 0; } @@ -463,6 +489,9 @@ int __init op_nmi_init(struct oprofile_operations *ops) } init_sysfs(); +#ifdef CONFIG_SMP + register_cpu_notifier(&oprofile_cpu_nb); +#endif using_nmi = 1; ops->create_files = nmi_create_files; ops->setup = nmi_setup; @@ -476,6 +505,10 @@ int __init op_nmi_init(struct oprofile_operations *ops) void op_nmi_exit(void) { - if (using_nmi) + if (using_nmi) { exit_sysfs(); +#ifdef CONFIG_SMP + unregister_cpu_notifier(&oprofile_cpu_nb); +#endif + } } -- cgit v1.2.3 From b61e06f258e50b25c38a73bea782bdb6876f0f70 Mon Sep 17 00:00:00 2001 From: Andrea Righi Date: Sat, 20 Sep 2008 18:02:27 +0200 Subject: x86, oprofile: BUG scheduling while atomic nmi_shutdown() calls unregister_die_notifier() from an atomic context after setting preempt_disable() via get_cpu_var(): [ 1049.404154] BUG: scheduling while atomic: oprofiled/7796/0x00000002 [ 1049.404171] INFO: lockdep is turned off. [ 1049.404176] Modules linked in: oprofile af_packet rfcomm l2cap kvm_intel kvm i915 drm acpi_cpufreq cpufreq_userspace cpufreq_conservative cpufreq_ondemand cpufreq_powersave freq_table container sbs sbshc dm_mod arc4 ecb cryptomgr aead snd_hda_intel crypto_blkcipher snd_pcm_oss crypto_algapi snd_pcm iwlagn iwlcore snd_timer iTCO_wdt led_class btusb iTCO_vendor_support snd psmouse bluetooth mac80211 soundcore cfg80211 snd_page_alloc intel_agp video output button battery ac dcdbas evdev ext3 jbd mbcache sg sd_mod piix ata_piix libata scsi_mod dock tg3 libphy ehci_hcd uhci_hcd usbcore thermal processor fan fuse [ 1049.404362] Pid: 7796, comm: oprofiled Not tainted 2.6.27-rc5-mm1 #30 [ 1049.404368] Call Trace: [ 1049.404384] [] thread_return+0x4a0/0x7d3 [ 1049.404396] [] generic_exec_single+0x52/0xe0 [ 1049.404405] [] generic_exec_single+0xda/0xe0 [ 1049.404414] [] smp_call_function_single+0x73/0x150 [ 1049.404423] [] schedule_timeout+0x95/0xd0 [ 1049.404430] [] wait_for_common+0x43/0x180 [ 1049.404438] [] wait_for_common+0x114/0x180 [ 1049.404448] [] default_wake_function+0x0/0x10 [ 1049.404457] [] synchronize_rcu+0x30/0x40 [ 1049.404463] [] wakeme_after_rcu+0x0/0x10 [ 1049.404472] [] _spin_unlock_irqrestore+0x40/0x80 [ 1049.404482] [] atomic_notifier_chain_unregister+0x3f/0x60 [ 1049.404501] [] nmi_shutdown+0x51/0x90 [oprofile] [ 1049.404517] [] oprofile_shutdown+0x34/0x70 [oprofile] [ 1049.404532] [] event_buffer_release+0xe/0x40 [oprofile] [ 1049.404543] [] __fput+0xcd/0x240 [ 1049.404551] [] filp_close+0x54/0x90 [ 1049.404560] [] put_files_struct+0xb1/0xd0 [ 1049.404568] [] do_exit+0x18f/0x930 [ 1049.404576] [] restore_args+0x0/0x30 [ 1049.404584] [] do_group_exit+0x36/0xa0 [ 1049.404592] [] system_call_fastpath+0x16/0x1b This can be easily triggered with 'opcontrol --shutdown'. Simply move get_cpu_var() above unregister_die_notifier(). Signed-off-by: Andrea Righi Acked-by: Robert Richter Signed-off-by: Ingo Molnar --- arch/x86/oprofile/nmi_int.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'arch/x86/oprofile/nmi_int.c') diff --git a/arch/x86/oprofile/nmi_int.c b/arch/x86/oprofile/nmi_int.c index 0227694f7da..8a5f1614a3d 100644 --- a/arch/x86/oprofile/nmi_int.c +++ b/arch/x86/oprofile/nmi_int.c @@ -295,10 +295,12 @@ static void nmi_cpu_shutdown(void *dummy) static void nmi_shutdown(void) { - struct op_msrs *msrs = &get_cpu_var(cpu_msrs); + struct op_msrs *msrs; + nmi_enabled = 0; on_each_cpu(nmi_cpu_shutdown, NULL, 1); unregister_die_notifier(&profile_exceptions_nb); + msrs = &get_cpu_var(cpu_msrs); model->shutdown(msrs); free_msrs(); put_cpu_var(cpu_msrs); -- cgit v1.2.3