diff options
| author | Nicholas Piggin <npiggin@gmail.com> | 2022-10-07 00:04:11 +1000 |
|---|---|---|
| committer | Michael Ellerman <mpe@ellerman.id.au> | 2022-10-18 22:46:19 +1100 |
| commit | dc398a084d459f065658855454e09f2778f8c5cc (patch) | |
| tree | dba45be1f6d86775998339cbebcdc038f931a203 /arch/powerpc | |
| parent | a073672eb09670540e95a2a4aa1c46f5da74159f (diff) | |
powerpc/64s/interrupt: Perf NMI should not take normal exit path
NMI interrupts should exit with EXCEPTION_RESTORE_REGS not with
interrupt_return_srr, which is what the perf NMI handler currently does.
This breaks if a PMI hits after interrupt_exit_user_prepare_main() has
switched the context tracking to user mode, then the CT_WARN_ON() in
interrupt_exit_kernel_prepare() fires because it returns to kernel with
context set to user.
This could possibly be solved by soft-disabling PMIs in the exit path,
but that reduces our ability to profile that code. The warning could be
removed, but it's potentially useful.
All other NMIs and soft-NMIs return using EXCEPTION_RESTORE_REGS, so
this makes perf interrupts consistent with that and seems like the best
fix.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
[mpe: Squash in fixups from Nick]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20221006140413.126443-3-npiggin@gmail.com
Diffstat (limited to 'arch/powerpc')
| -rw-r--r-- | arch/powerpc/kernel/exceptions-64s.S | 14 | ||||
| -rw-r--r-- | arch/powerpc/kernel/interrupt.c | 14 |
2 files changed, 21 insertions, 7 deletions
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index 5381a43e50fe..651c36b056bd 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -2357,9 +2357,21 @@ EXC_VIRT_END(performance_monitor, 0x4f00, 0x20) EXC_COMMON_BEGIN(performance_monitor_common) GEN_COMMON performance_monitor addi r3,r1,STACK_FRAME_OVERHEAD - bl performance_monitor_exception + lbz r4,PACAIRQSOFTMASK(r13) + cmpdi r4,IRQS_ENABLED + bne 1f + bl performance_monitor_exception_async b interrupt_return_srr +1: + bl performance_monitor_exception_nmi + /* Clear MSR_RI before setting SRR0 and SRR1. */ + li r9,0 + mtmsrd r9,1 + kuap_kernel_restore r9, r10 + + EXCEPTION_RESTORE_REGS hsrr=0 + RFI_TO_KERNEL /** * Interrupt 0xf20 - Vector Unavailable Interrupt. diff --git a/arch/powerpc/kernel/interrupt.c b/arch/powerpc/kernel/interrupt.c index 7bc93367de68..fc6631a80527 100644 --- a/arch/powerpc/kernel/interrupt.c +++ b/arch/powerpc/kernel/interrupt.c @@ -377,13 +377,15 @@ notrace unsigned long interrupt_exit_kernel_prepare(struct pt_regs *regs) * CT_WARN_ON comes here via program_check_exception, so avoid * recursion. * - * Skip the assertion on PMIs to work around a problem caused by NMI - * PMIs incorrectly taking this interrupt return path, it's possible - * for this to hit after interrupt exit to user switches context to - * user. See also the comment in the performance monitor handler in - * exceptions-64e/s.S + * Skip the assertion on PMIs on 64e to work around a problem caused + * by NMI PMIs incorrectly taking this interrupt return path, it's + * possible for this to hit after interrupt exit to user switches + * context to user. See also the comment in the performance monitor + * handler in exceptions-64e.S */ - if (TRAP(regs) != INTERRUPT_PROGRAM && TRAP(regs) != INTERRUPT_PERFMON) + if (!IS_ENABLED(CONFIG_PPC_BOOK3E_64) && + TRAP(regs) != INTERRUPT_PROGRAM && + TRAP(regs) != INTERRUPT_PERFMON) CT_WARN_ON(ct_state() == CONTEXT_USER); kuap = kuap_get_and_assert_locked(); |