powerpc/64s: Don't unbalance the return branch predictor in __replay_interrupt()

The __replay_interrupt() code is branched to with bl, but the caller is
returned to directly with rfid from the interrupt.

Instead, rfid to a stub that returns to the caller with blr, which
should keep the return branch predictor balanced.

Reviewed-by: Gautham R. Shenoy <ego@linux.vnet.ibm.com>
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
This commit is contained in:
Nicholas Piggin 2017-06-13 23:05:49 +10:00 committed by Michael Ellerman
parent a9af97aa0a
commit b48bbb82e2

View File

@ -1639,6 +1639,10 @@ doorbell_super_common_msgclr:
* Note: While MSR:EE is off, we need to make sure that _MSR * Note: While MSR:EE is off, we need to make sure that _MSR
* in the generated frame has EE set to 1 or the exception * in the generated frame has EE set to 1 or the exception
* handler will not properly re-enable them. * handler will not properly re-enable them.
*
* Note that we don't specify LR as the NIP (return address) for
* the interrupt because that would unbalance the return branch
* predictor.
*/ */
_GLOBAL(__replay_interrupt) _GLOBAL(__replay_interrupt)
/* We are going to jump to the exception common code which /* We are going to jump to the exception common code which
@ -1646,7 +1650,7 @@ _GLOBAL(__replay_interrupt)
* we don't give a damn about, so we don't bother storing them. * we don't give a damn about, so we don't bother storing them.
*/ */
mfmsr r12 mfmsr r12
mflr r11 LOAD_REG_ADDR(r11, .L__replay_interrupt_return)
mfcr r9 mfcr r9
ori r12,r12,MSR_EE ori r12,r12,MSR_EE
cmpwi r3,0x900 cmpwi r3,0x900
@ -1664,4 +1668,6 @@ FTR_SECTION_ELSE
cmpwi r3,0xa00 cmpwi r3,0xa00
beq doorbell_super_common_msgclr beq doorbell_super_common_msgclr
ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE) ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE)
.L__replay_interrupt_return:
blr blr