ARM: entry: instrument usr exception handlers with irqsoff tracing

As we no longer re-enable interrupts in these exception handlers, add
the irqsoff tracing calls to them so that the kernel tracks the state
more accurately.

Note that these calls are conditional on IRQSOFF_TRACER:

  kernel ----------> user ---------> kernel
          ^ irqs enabled   ^ irqs disabled

No kernel code can run on the local CPU until we've re-entered the
kernel through one of the exception handlers - and userspace can not
take any locks etc.  So, the kernel doesn't care about the IRQ mask
state while userspace is running unless we're doing IRQ off latency
tracing.  So, we can (and do) avoid the overhead of updating the IRQ
mask state on every kernel->user and user->kernel transition.

Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
This commit is contained in:
Russell King 2011-06-25 18:28:19 +01:00
parent df295df6c3
commit bc089602d2

View File

@ -421,6 +421,11 @@ ENDPROC(__pabt_svc)
.align 5
__dabt_usr:
usr_entry
#ifdef CONFIG_IRQSOFF_TRACER
bl trace_hardirqs_off
#endif
kuser_cmpxchg_check
dabt_helper
@ -433,12 +438,12 @@ ENDPROC(__dabt_usr)
.align 5
__irq_usr:
usr_entry
kuser_cmpxchg_check
#ifdef CONFIG_IRQSOFF_TRACER
bl trace_hardirqs_off
#endif
kuser_cmpxchg_check
irq_handler
get_thread_info tsk
mov why, #0
@ -451,6 +456,11 @@ ENDPROC(__irq_usr)
.align 5
__und_usr:
usr_entry
#ifdef CONFIG_IRQSOFF_TRACER
bl trace_hardirqs_off
#endif
mov r2, r4
mov r3, r5
@ -669,6 +679,11 @@ ENDPROC(__und_usr_unknown)
.align 5
__pabt_usr:
usr_entry
#ifdef CONFIG_IRQSOFF_TRACER
bl trace_hardirqs_off
#endif
pabt_helper
mov r2, sp @ regs
bl do_PrefetchAbort @ call abort handler