powerpc/64s/exception: Avoid touching the stack in hdecrementer

The hdec interrupt handler is reported to sometimes fire in Linux if
KVM leaves it pending after a guest exists. This is harmless, so there
is a no-op handler for it.

The interrupt handler currently uses the regular kernel stack. Change
this to avoid touching the stack entirely.

This should be the last place where the regular Linux stack can be
accessed with asynchronous interrupts (including PMI) soft-masked.
It might be possible to take advantage of this invariant, e.g., to
context switch the kernel stack SLB entry without clearing MSR[EE].

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20200225173541.1549955-17-npiggin@gmail.com

diff --git a/arch/powerpc/include/asm/time.h b/arch/powerpc/include/asm/time.h
index 08dbe3e..e010749 100644 (file)
--- a/arch/powerpc/include/asm/time.h
+++ b/arch/powerpc/include/asm/time.h
@@ -24,7 +24,6 @@ extern struct clock_event_device decrementer_clockevent;
 
 
 extern void generic_calibrate_decr(void);
-extern void hdec_interrupt(struct pt_regs *regs);
 
 /* Some sane defaults: 125 MHz timebase, 1GHz processor */
 extern unsigned long ppc_proc_freq;

diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index da15ec4..146afa0 100644 (file)
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -1507,6 +1507,8 @@ EXC_COMMON_BEGIN(decrementer_common)
 INT_DEFINE_BEGIN(hdecrementer)
        IVEC=0x980
        IHSRR=EXC_HV
+       ISTACK=0
+       IRECONCILE=0
        IKVM_REAL=1
        IKVM_VIRT=1
 INT_DEFINE_END(hdecrementer)
@@ -1518,11 +1520,24 @@ EXC_VIRT_BEGIN(hdecrementer, 0x4980, 0x80)
        GEN_INT_ENTRY hdecrementer, virt=1
 EXC_VIRT_END(hdecrementer, 0x4980, 0x80)
 EXC_COMMON_BEGIN(hdecrementer_common)
-       GEN_COMMON hdecrementer
-       bl      save_nvgprs
-       addi    r3,r1,STACK_FRAME_OVERHEAD
-       bl      hdec_interrupt
-       b       ret_from_except
+       __GEN_COMMON_ENTRY hdecrementer
+       /*
+        * Hypervisor decrementer interrupts not caught by the KVM test
+        * shouldn't occur but are sometimes left pending on exit from a KVM
+        * guest.  We don't need to do anything to clear them, as they are
+        * edge-triggered.
+        *
+        * Be careful to avoid touching the kernel stack.
+        */
+       ld      r10,PACA_EXGEN+EX_CTR(r13)
+       mtctr   r10
+       mtcrf   0x80,r9
+       ld      r9,PACA_EXGEN+EX_R9(r13)
+       ld      r10,PACA_EXGEN+EX_R10(r13)
+       ld      r11,PACA_EXGEN+EX_R11(r13)
+       ld      r12,PACA_EXGEN+EX_R12(r13)
+       ld      r13,PACA_EXGEN+EX_R13(r13)
+       HRFI_TO_KERNEL
 
        GEN_KVM hdecrementer
 

diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 1168e8b..bda9cb4 100644 (file)
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -663,15 +663,6 @@ void timer_broadcast_interrupt(void)
 }
 #endif
 
-/*
- * Hypervisor decrementer interrupts shouldn't occur but are sometimes
- * left pending on exit from a KVM guest.  We don't need to do anything
- * to clear them, as they are edge-triggered.
- */
-void hdec_interrupt(struct pt_regs *regs)
-{
-}
-
 #ifdef CONFIG_SUSPEND
 static void generic_suspend_disable_irqs(void)
 {