| Message ID | 1478823475-15087-1-git-send-email-yang.shi@linaro.org (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
On 2016-11-10 16:17:55 [-0800], Yang Shi wrote: > > Since patch_text_stop_machine() is called in stop_machine() which disables IRQ, > sleepable lock should be not used in this atomic context, so replace patch_lock > to raw lock. I am taking this one. Thank you. We have jump_labels() deactivated on ARM because stop_machine() may cause latencies at runtime. kprobe and kgdb is used by the user on purpose (and not because he changed some sched setting) I think we are fine. I am going to document this. > Signed-off-by: Yang Shi <yang.shi@linaro.org> Sebastian
On 2016-11-10 16:17:55 [-0800], Yang Shi wrote: > > Since patch_text_stop_machine() is called in stop_machine() which disables IRQ, > sleepable lock should be not used in this atomic context, so replace patch_lock > to raw lock. > > Signed-off-by: Yang Shi <yang.shi@linaro.org> This can also go upstream. Acked-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Sebastian
On 12/1/2016 6:13 AM, Sebastian Andrzej Siewior wrote: > On 2016-11-10 16:17:55 [-0800], Yang Shi wrote: >> >> Since patch_text_stop_machine() is called in stop_machine() which disables IRQ, >> sleepable lock should be not used in this atomic context, so replace patch_lock >> to raw lock. >> >> Signed-off-by: Yang Shi <yang.shi@linaro.org> > > This can also go upstream. > Acked-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Yes, thanks for acking. Russell, Could you please consider this patch? Thanks, Yang > > Sebastian >
diff --git a/arch/arm/kernel/patch.c b/arch/arm/kernel/patch.c index 69bda1a..1f665ac 100644 --- a/arch/arm/kernel/patch.c +++ b/arch/arm/kernel/patch.c @@ -15,7 +15,7 @@ struct patch { unsigned int insn; }; -static DEFINE_SPINLOCK(patch_lock); +static DEFINE_RAW_SPINLOCK(patch_lock); static void __kprobes *patch_map(void *addr, int fixmap, unsigned long *flags) __acquires(&patch_lock) @@ -32,7 +32,7 @@ static void __kprobes *patch_map(void *addr, int fixmap, unsigned long *flags) return addr; if (flags) - spin_lock_irqsave(&patch_lock, *flags); + raw_spin_lock_irqsave(&patch_lock, *flags); else __acquire(&patch_lock); @@ -47,7 +47,7 @@ static void __kprobes patch_unmap(int fixmap, unsigned long *flags) clear_fixmap(fixmap); if (flags) - spin_unlock_irqrestore(&patch_lock, *flags); + raw_spin_unlock_irqrestore(&patch_lock, *flags); else __release(&patch_lock); }
When running kprobe on -rt kernel, the below bug is caught: BUG: sleeping function called from invalid context at kernel/locking/rtmutex.c:931 in_atomic(): 1, irqs_disabled(): 128, pid: 14, name: migration/0 INFO: lockdep is turned off. irq event stamp: 238 hardirqs last enabled at (237): [<80b5aecc>] _raw_spin_unlock_irqrestore+0x88/0x90 hardirqs last disabled at (238): [<80b56d88>] __schedule+0xec/0x94c softirqs last enabled at (0): [<80225584>] copy_process.part.5+0x30c/0x1994 softirqs last disabled at (0): [< (null)>] (null) Preemption disabled at:[<802f2b98>] cpu_stopper_thread+0xc0/0x140 CPU: 0 PID: 14 Comm: migration/0 Tainted: G O 4.8.3-rt2 #1 Hardware name: Freescale LS1021A [<80212e7c>] (unwind_backtrace) from [<8020cd2c>] (show_stack+0x20/0x24) [<8020cd2c>] (show_stack) from [<80689e14>] (dump_stack+0xa0/0xcc) [<80689e14>] (dump_stack) from [<8025a43c>] (___might_sleep+0x1b8/0x2a4) [<8025a43c>] (___might_sleep) from [<80b5b324>] (rt_spin_lock+0x34/0x74) [<80b5b324>] (rt_spin_lock) from [<80b5c31c>] (__patch_text_real+0x70/0xe8) [<80b5c31c>] (__patch_text_real) from [<80b5c3ac>] (patch_text_stop_machine+0x18/0x20) [<80b5c3ac>] (patch_text_stop_machine) from [<802f2920>] (multi_cpu_stop+0xfc/0x134) [<802f2920>] (multi_cpu_stop) from [<802f2ba0>] (cpu_stopper_thread+0xc8/0x140) [<802f2ba0>] (cpu_stopper_thread) from [<802563a4>] (smpboot_thread_fn+0x1a4/0x354) [<802563a4>] (smpboot_thread_fn) from [<80251d38>] (kthread+0x104/0x11c) [<80251d38>] (kthread) from [<80207f70>] (ret_from_fork+0x14/0x24) Since patch_text_stop_machine() is called in stop_machine() which disables IRQ, sleepable lock should be not used in this atomic context, so replace patch_lock to raw lock. Signed-off-by: Yang Shi <yang.shi@linaro.org> --- arch/arm/kernel/patch.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)