diff options
Diffstat (limited to 'arch/x86/kernel/nmi.c')
| -rw-r--r-- | arch/x86/kernel/nmi.c | 114 |
1 files changed, 92 insertions, 22 deletions
diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c index a0b2f84457b..c3e985d1751 100644 --- a/arch/x86/kernel/nmi.c +++ b/arch/x86/kernel/nmi.c @@ -14,6 +14,7 @@ #include <linux/kprobes.h> #include <linux/kdebug.h> #include <linux/nmi.h> +#include <linux/debugfs.h> #include <linux/delay.h> #include <linux/hardirq.h> #include <linux/slab.h> @@ -29,6 +30,9 @@ #include <asm/nmi.h> #include <asm/x86_init.h> +#define CREATE_TRACE_POINTS +#include <trace/events/nmi.h> + struct nmi_desc { spinlock_t lock; struct list_head head; @@ -82,7 +86,31 @@ __setup("unknown_nmi_panic", setup_unknown_nmi_panic); #define nmi_to_desc(type) (&nmi_desc[type]) -static int __kprobes nmi_handle(unsigned int type, struct pt_regs *regs, bool b2b) +static u64 nmi_longest_ns = 1 * NSEC_PER_MSEC; + +static int __init nmi_warning_debugfs(void) +{ + debugfs_create_u64("nmi_longest_ns", 0644, + arch_debugfs_dir, &nmi_longest_ns); + return 0; +} +fs_initcall(nmi_warning_debugfs); + +static void nmi_max_handler(struct irq_work *w) +{ + struct nmiaction *a = container_of(w, struct nmiaction, irq_work); + int remainder_ns, decimal_msecs; + u64 whole_msecs = ACCESS_ONCE(a->max_duration); + + remainder_ns = do_div(whole_msecs, (1000 * 1000)); + decimal_msecs = remainder_ns / 1000; + + printk_ratelimited(KERN_INFO + "INFO: NMI handler (%ps) took too long to run: %lld.%03d msecs\n", + a->handler, whole_msecs, decimal_msecs); +} + +static int nmi_handle(unsigned int type, struct pt_regs *regs, bool b2b) { struct nmi_desc *desc = nmi_to_desc(type); struct nmiaction *a; @@ -96,14 +124,29 @@ static int __kprobes nmi_handle(unsigned int type, struct pt_regs *regs, bool b2 * can be latched at any given time. Walk the whole list * to handle those situations. */ - list_for_each_entry_rcu(a, &desc->head, list) - handled += a->handler(type, regs); + list_for_each_entry_rcu(a, &desc->head, list) { + int thishandled; + u64 delta; + + delta = sched_clock(); + thishandled = a->handler(type, regs); + handled += thishandled; + delta = sched_clock() - delta; + trace_nmi_handler(a->handler, (int)delta, thishandled); + + if (delta < nmi_longest_ns || delta < a->max_duration) + continue; + + a->max_duration = delta; + irq_work_queue(&a->irq_work); + } rcu_read_unlock(); /* return total number of NMI events handled */ return handled; } +NOKPROBE_SYMBOL(nmi_handle); int __register_nmi_handler(unsigned int type, struct nmiaction *action) { @@ -113,6 +156,8 @@ int __register_nmi_handler(unsigned int type, struct nmiaction *action) if (!action->handler) return -EINVAL; + init_irq_work(&action->irq_work, nmi_max_handler); + spin_lock_irqsave(&desc->lock, flags); /* @@ -164,7 +209,7 @@ void unregister_nmi_handler(unsigned int type, const char *name) } EXPORT_SYMBOL_GPL(unregister_nmi_handler); -static __kprobes void +static void pci_serr_error(unsigned char reason, struct pt_regs *regs) { /* check to see if anyone registered against these types of errors */ @@ -194,8 +239,9 @@ pci_serr_error(unsigned char reason, struct pt_regs *regs) reason = (reason & NMI_REASON_CLEAR_MASK) | NMI_REASON_CLEAR_SERR; outb(reason, NMI_REASON_PORT); } +NOKPROBE_SYMBOL(pci_serr_error); -static __kprobes void +static void io_check_error(unsigned char reason, struct pt_regs *regs) { unsigned long i; @@ -225,8 +271,9 @@ io_check_error(unsigned char reason, struct pt_regs *regs) reason &= ~NMI_REASON_CLEAR_IOCHK; outb(reason, NMI_REASON_PORT); } +NOKPROBE_SYMBOL(io_check_error); -static __kprobes void +static void unknown_nmi_error(unsigned char reason, struct pt_regs *regs) { int handled; @@ -254,11 +301,12 @@ unknown_nmi_error(unsigned char reason, struct pt_regs *regs) pr_emerg("Dazed and confused, but trying to continue\n"); } +NOKPROBE_SYMBOL(unknown_nmi_error); static DEFINE_PER_CPU(bool, swallow_nmi); static DEFINE_PER_CPU(unsigned long, last_nmi_rip); -static __kprobes void default_do_nmi(struct pt_regs *regs) +static void default_do_nmi(struct pt_regs *regs) { unsigned char reason = 0; int handled; @@ -357,6 +405,7 @@ static __kprobes void default_do_nmi(struct pt_regs *regs) else unknown_nmi_error(reason, regs); } +NOKPROBE_SYMBOL(default_do_nmi); /* * NMIs can hit breakpoints which will cause it to lose its @@ -365,8 +414,9 @@ static __kprobes void default_do_nmi(struct pt_regs *regs) #ifdef CONFIG_X86_32 /* * For i386, NMIs use the same stack as the kernel, and we can - * add a workaround to the iret problem in C. Simply have 3 states - * the NMI can be in. + * add a workaround to the iret problem in C (preventing nested + * NMIs if an NMI takes a trap). Simply have 3 states the NMI + * can be in: * * 1) not running * 2) executing @@ -383,32 +433,50 @@ static __kprobes void default_do_nmi(struct pt_regs *regs) * If an NMI hits a breakpoint that executes an iret, another * NMI can preempt it. We do not want to allow this new NMI * to run, but we want to execute it when the first one finishes. - * We set the state to "latched", and the first NMI will perform - * an cmpxchg on the state, and if it doesn't successfully - * reset the state to "not running" it will restart the next - * NMI. + * We set the state to "latched", and the exit of the first NMI will + * perform a dec_return, if the result is zero (NOT_RUNNING), then + * it will simply exit the NMI handler. If not, the dec_return + * would have set the state to NMI_EXECUTING (what we want it to + * be when we are running). In this case, we simply jump back + * to rerun the NMI handler again, and restart the 'latched' NMI. + * + * No trap (breakpoint or page fault) should be hit before nmi_restart, + * thus there is no race between the first check of state for NOT_RUNNING + * and setting it to NMI_EXECUTING. The HW will prevent nested NMIs + * at this point. + * + * In case the NMI takes a page fault, we need to save off the CR2 + * because the NMI could have preempted another page fault and corrupt + * the CR2 that is about to be read. As nested NMIs must be restarted + * and they can not take breakpoints or page faults, the update of the + * CR2 must be done before converting the nmi state back to NOT_RUNNING. + * Otherwise, there would be a race of another nested NMI coming in + * after setting state to NOT_RUNNING but before updating the nmi_cr2. */ enum nmi_states { - NMI_NOT_RUNNING, + NMI_NOT_RUNNING = 0, NMI_EXECUTING, NMI_LATCHED, }; static DEFINE_PER_CPU(enum nmi_states, nmi_state); +static DEFINE_PER_CPU(unsigned long, nmi_cr2); #define nmi_nesting_preprocess(regs) \ do { \ - if (__get_cpu_var(nmi_state) != NMI_NOT_RUNNING) { \ - __get_cpu_var(nmi_state) = NMI_LATCHED; \ + if (this_cpu_read(nmi_state) != NMI_NOT_RUNNING) { \ + this_cpu_write(nmi_state, NMI_LATCHED); \ return; \ } \ - nmi_restart: \ - __get_cpu_var(nmi_state) = NMI_EXECUTING; \ - } while (0) + this_cpu_write(nmi_state, NMI_EXECUTING); \ + this_cpu_write(nmi_cr2, read_cr2()); \ + } while (0); \ + nmi_restart: #define nmi_nesting_postprocess() \ do { \ - if (cmpxchg(&__get_cpu_var(nmi_state), \ - NMI_EXECUTING, NMI_NOT_RUNNING) != NMI_EXECUTING) \ + if (unlikely(this_cpu_read(nmi_cr2) != read_cr2())) \ + write_cr2(this_cpu_read(nmi_cr2)); \ + if (this_cpu_dec_return(nmi_state)) \ goto nmi_restart; \ } while (0) #else /* x86_64 */ @@ -457,7 +525,7 @@ static inline void nmi_nesting_postprocess(void) } #endif -dotraplinkage notrace __kprobes void +dotraplinkage notrace void do_nmi(struct pt_regs *regs, long error_code) { nmi_nesting_preprocess(regs); @@ -474,6 +542,7 @@ do_nmi(struct pt_regs *regs, long error_code) /* On i386, may loop back to preprocess */ nmi_nesting_postprocess(); } +NOKPROBE_SYMBOL(do_nmi); void stop_nmi(void) { @@ -490,3 +559,4 @@ void local_touch_nmi(void) { __this_cpu_write(last_nmi_rip, 0); } +EXPORT_SYMBOL_GPL(local_touch_nmi); |