x86/entry: Fix NMI vs IRQ state tracking
While the nmi_enter() users did trace_hardirqs_{off_prepare,on_finish}() there was no matching lockdep_hardirqs_*() calls to complete the picture. Introduce idtentry_{enter,exit}_nmi() to enable proper IRQ state tracking across the NMIs. Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Reviewed-by: Ingo Molnar <mingo@kernel.org> Link: https://lkml.kernel.org/r/20200623083721.216740948@infradead.org
This commit is contained in:
parent
859d069ee1
commit
ba1f2b2eaa
|
@ -592,7 +592,7 @@ SYSCALL_DEFINE0(ni_syscall)
|
|||
* The return value must be fed into the state argument of
|
||||
* idtentry_exit().
|
||||
*/
|
||||
idtentry_state_t noinstr idtentry_enter(struct pt_regs *regs)
|
||||
noinstr idtentry_state_t idtentry_enter(struct pt_regs *regs)
|
||||
{
|
||||
idtentry_state_t ret = {
|
||||
.exit_rcu = false,
|
||||
|
@ -687,7 +687,7 @@ static void idtentry_exit_cond_resched(struct pt_regs *regs, bool may_sched)
|
|||
* Counterpart to idtentry_enter(). The return value of the entry
|
||||
* function must be fed into the @state argument.
|
||||
*/
|
||||
void noinstr idtentry_exit(struct pt_regs *regs, idtentry_state_t state)
|
||||
noinstr void idtentry_exit(struct pt_regs *regs, idtentry_state_t state)
|
||||
{
|
||||
lockdep_assert_irqs_disabled();
|
||||
|
||||
|
@ -731,7 +731,7 @@ void noinstr idtentry_exit(struct pt_regs *regs, idtentry_state_t state)
|
|||
* Invokes enter_from_user_mode() to establish the proper context for
|
||||
* NOHZ_FULL. Otherwise scheduling on exit would not be possible.
|
||||
*/
|
||||
void noinstr idtentry_enter_user(struct pt_regs *regs)
|
||||
noinstr void idtentry_enter_user(struct pt_regs *regs)
|
||||
{
|
||||
check_user_regs(regs);
|
||||
enter_from_user_mode();
|
||||
|
@ -749,13 +749,47 @@ void noinstr idtentry_enter_user(struct pt_regs *regs)
|
|||
*
|
||||
* Counterpart to idtentry_enter_user().
|
||||
*/
|
||||
void noinstr idtentry_exit_user(struct pt_regs *regs)
|
||||
noinstr void idtentry_exit_user(struct pt_regs *regs)
|
||||
{
|
||||
lockdep_assert_irqs_disabled();
|
||||
|
||||
prepare_exit_to_usermode(regs);
|
||||
}
|
||||
|
||||
noinstr bool idtentry_enter_nmi(struct pt_regs *regs)
|
||||
{
|
||||
bool irq_state = lockdep_hardirqs_enabled(current);
|
||||
|
||||
__nmi_enter();
|
||||
lockdep_hardirqs_off(CALLER_ADDR0);
|
||||
lockdep_hardirq_enter();
|
||||
rcu_nmi_enter();
|
||||
|
||||
instrumentation_begin();
|
||||
trace_hardirqs_off_finish();
|
||||
ftrace_nmi_enter();
|
||||
instrumentation_end();
|
||||
|
||||
return irq_state;
|
||||
}
|
||||
|
||||
noinstr void idtentry_exit_nmi(struct pt_regs *regs, bool restore)
|
||||
{
|
||||
instrumentation_begin();
|
||||
ftrace_nmi_exit();
|
||||
if (restore) {
|
||||
trace_hardirqs_on_prepare();
|
||||
lockdep_hardirqs_on_prepare(CALLER_ADDR0);
|
||||
}
|
||||
instrumentation_end();
|
||||
|
||||
rcu_nmi_exit();
|
||||
lockdep_hardirq_exit();
|
||||
if (restore)
|
||||
lockdep_hardirqs_on(CALLER_ADDR0);
|
||||
__nmi_exit();
|
||||
}
|
||||
|
||||
#ifdef CONFIG_XEN_PV
|
||||
#ifndef CONFIG_PREEMPTION
|
||||
/*
|
||||
|
|
|
@ -20,6 +20,9 @@ typedef struct idtentry_state {
|
|||
idtentry_state_t idtentry_enter(struct pt_regs *regs);
|
||||
void idtentry_exit(struct pt_regs *regs, idtentry_state_t state);
|
||||
|
||||
bool idtentry_enter_nmi(struct pt_regs *regs);
|
||||
void idtentry_exit_nmi(struct pt_regs *regs, bool irq_state);
|
||||
|
||||
/**
|
||||
* DECLARE_IDTENTRY - Declare functions for simple IDT entry points
|
||||
* No error code pushed by hardware
|
||||
|
|
|
@ -330,7 +330,6 @@ static noinstr void default_do_nmi(struct pt_regs *regs)
|
|||
__this_cpu_write(last_nmi_rip, regs->ip);
|
||||
|
||||
instrumentation_begin();
|
||||
trace_hardirqs_off_finish();
|
||||
|
||||
handled = nmi_handle(NMI_LOCAL, regs);
|
||||
__this_cpu_add(nmi_stats.normal, handled);
|
||||
|
@ -417,8 +416,6 @@ static noinstr void default_do_nmi(struct pt_regs *regs)
|
|||
unknown_nmi_error(reason, regs);
|
||||
|
||||
out:
|
||||
if (regs->flags & X86_EFLAGS_IF)
|
||||
trace_hardirqs_on_prepare();
|
||||
instrumentation_end();
|
||||
}
|
||||
|
||||
|
@ -478,6 +475,8 @@ static DEFINE_PER_CPU(unsigned long, nmi_dr7);
|
|||
|
||||
DEFINE_IDTENTRY_RAW(exc_nmi)
|
||||
{
|
||||
bool irq_state;
|
||||
|
||||
if (IS_ENABLED(CONFIG_SMP) && arch_cpu_is_offline(smp_processor_id()))
|
||||
return;
|
||||
|
||||
|
@ -491,14 +490,14 @@ nmi_restart:
|
|||
|
||||
this_cpu_write(nmi_dr7, local_db_save());
|
||||
|
||||
nmi_enter();
|
||||
irq_state = idtentry_enter_nmi(regs);
|
||||
|
||||
inc_irq_stat(__nmi_count);
|
||||
|
||||
if (!ignore_nmis)
|
||||
default_do_nmi(regs);
|
||||
|
||||
nmi_exit();
|
||||
idtentry_exit_nmi(regs, irq_state);
|
||||
|
||||
local_db_restore(this_cpu_read(nmi_dr7));
|
||||
|
||||
|
|
|
@ -403,7 +403,7 @@ DEFINE_IDTENTRY_DF(exc_double_fault)
|
|||
}
|
||||
#endif
|
||||
|
||||
nmi_enter();
|
||||
idtentry_enter_nmi(regs);
|
||||
instrumentation_begin();
|
||||
notify_die(DIE_TRAP, str, regs, error_code, X86_TRAP_DF, SIGSEGV);
|
||||
|
||||
|
@ -649,15 +649,12 @@ DEFINE_IDTENTRY_RAW(exc_int3)
|
|||
instrumentation_end();
|
||||
idtentry_exit_user(regs);
|
||||
} else {
|
||||
nmi_enter();
|
||||
bool irq_state = idtentry_enter_nmi(regs);
|
||||
instrumentation_begin();
|
||||
trace_hardirqs_off_finish();
|
||||
if (!do_int3(regs))
|
||||
die("int3", regs, 0);
|
||||
if (regs->flags & X86_EFLAGS_IF)
|
||||
trace_hardirqs_on_prepare();
|
||||
instrumentation_end();
|
||||
nmi_exit();
|
||||
idtentry_exit_nmi(regs, irq_state);
|
||||
}
|
||||
}
|
||||
|
||||
|
@ -865,9 +862,8 @@ out:
|
|||
static __always_inline void exc_debug_kernel(struct pt_regs *regs,
|
||||
unsigned long dr6)
|
||||
{
|
||||
nmi_enter();
|
||||
bool irq_state = idtentry_enter_nmi(regs);
|
||||
instrumentation_begin();
|
||||
trace_hardirqs_off_finish();
|
||||
|
||||
/*
|
||||
* If something gets miswired and we end up here for a user mode
|
||||
|
@ -884,10 +880,8 @@ static __always_inline void exc_debug_kernel(struct pt_regs *regs,
|
|||
|
||||
handle_debug(regs, dr6, false);
|
||||
|
||||
if (regs->flags & X86_EFLAGS_IF)
|
||||
trace_hardirqs_on_prepare();
|
||||
instrumentation_end();
|
||||
nmi_exit();
|
||||
idtentry_exit_nmi(regs, irq_state);
|
||||
}
|
||||
|
||||
static __always_inline void exc_debug_user(struct pt_regs *regs,
|
||||
|
@ -903,6 +897,7 @@ static __always_inline void exc_debug_user(struct pt_regs *regs,
|
|||
instrumentation_begin();
|
||||
|
||||
handle_debug(regs, dr6, true);
|
||||
|
||||
instrumentation_end();
|
||||
idtentry_exit_user(regs);
|
||||
}
|
||||
|
|
|
@ -111,32 +111,42 @@ extern void rcu_nmi_exit(void);
|
|||
/*
|
||||
* nmi_enter() can nest up to 15 times; see NMI_BITS.
|
||||
*/
|
||||
#define nmi_enter() \
|
||||
#define __nmi_enter() \
|
||||
do { \
|
||||
lockdep_off(); \
|
||||
arch_nmi_enter(); \
|
||||
printk_nmi_enter(); \
|
||||
lockdep_off(); \
|
||||
BUG_ON(in_nmi() == NMI_MASK); \
|
||||
__preempt_count_add(NMI_OFFSET + HARDIRQ_OFFSET); \
|
||||
rcu_nmi_enter(); \
|
||||
} while (0)
|
||||
|
||||
#define nmi_enter() \
|
||||
do { \
|
||||
__nmi_enter(); \
|
||||
lockdep_hardirq_enter(); \
|
||||
rcu_nmi_enter(); \
|
||||
instrumentation_begin(); \
|
||||
ftrace_nmi_enter(); \
|
||||
instrumentation_end(); \
|
||||
} while (0)
|
||||
|
||||
#define __nmi_exit() \
|
||||
do { \
|
||||
BUG_ON(!in_nmi()); \
|
||||
__preempt_count_sub(NMI_OFFSET + HARDIRQ_OFFSET); \
|
||||
printk_nmi_exit(); \
|
||||
arch_nmi_exit(); \
|
||||
lockdep_on(); \
|
||||
} while (0)
|
||||
|
||||
#define nmi_exit() \
|
||||
do { \
|
||||
instrumentation_begin(); \
|
||||
ftrace_nmi_exit(); \
|
||||
instrumentation_end(); \
|
||||
lockdep_hardirq_exit(); \
|
||||
rcu_nmi_exit(); \
|
||||
BUG_ON(!in_nmi()); \
|
||||
__preempt_count_sub(NMI_OFFSET + HARDIRQ_OFFSET); \
|
||||
lockdep_on(); \
|
||||
printk_nmi_exit(); \
|
||||
arch_nmi_exit(); \
|
||||
lockdep_hardirq_exit(); \
|
||||
__nmi_exit(); \
|
||||
} while (0)
|
||||
|
||||
#endif /* LINUX_HARDIRQ_H */
|
||||
|
|
Loading…
Reference in New Issue