diff mbox

KVM: PPC: Book3S HV: Add more barriers in XIVE load/unload code

Message ID 20171015214559.GA11757@fergus.ozlabs.ibm.com (mailing list archive)
State New, archived
Headers show

Commit Message

Paul Mackerras Oct. 15, 2017, 9:45 p.m. UTC
From: Benjamin Herrenschmidt <benh@kernel.crashing.org>

On POWER9 systems, we push the VCPU context onto the XIVE (eXternal
Interrupt Virtualization Engine) hardware when entering a guest,
and pull the context off the XIVE when exiting the guest.  The push
is done with cache-inhibited stores, and the pull with cache-inhibited
loads.

Testing has revealed that it is possible (though very rare) for
the stores to get reordered with the loads so that we end up with the
guest VCPU context still loaded on the XIVE after we have exited the
guest.  When that happens, it is possible for the same VCPU context
to then get loaded on another CPU, which causes the machine to
checkstop.

To fix this, we add I/O barrier instructions (eieio) before and
after the push and pull operations.  As partial compensation for the
potential slowdown caused by the extra barriers, we remove the eieio
instructions between the two stores in the push operation, and between
the two loads in the pull operation.  (The architecture requires
loads to cache-inhibited, guarded storage to be kept in order, and
requires stores to cache-inhibited, guarded storage likewise to be
kept in order, but allows such loads and stores to be reordered with
respect to each other.)

Reported-by: Carol L Soto <clsoto@us.ibm.com>
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
---
 arch/powerpc/kvm/book3s_hv_rmhandlers.S | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)
diff mbox

Patch

diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index c700bed..42639fb 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -989,13 +989,14 @@  ALT_FTR_SECTION_END_IFCLR(CPU_FTR_ARCH_300)
 	beq	no_xive
 	ld	r11, VCPU_XIVE_SAVED_STATE(r4)
 	li	r9, TM_QW1_OS
-	stdcix	r11,r9,r10
 	eieio
+	stdcix	r11,r9,r10
 	lwz	r11, VCPU_XIVE_CAM_WORD(r4)
 	li	r9, TM_QW1_OS + TM_WORD2
 	stwcix	r11,r9,r10
 	li	r9, 1
 	stw	r9, VCPU_XIVE_PUSHED(r4)
+	eieio
 no_xive:
 #endif /* CONFIG_KVM_XICS */
 
@@ -1401,8 +1402,8 @@  guest_exit_cont:		/* r9 = vcpu, r12 = trap, r13 = paca */
 	cmpldi	cr0, r10, 0
 	beq	1f
 	/* First load to pull the context, we ignore the value */
-	lwzx	r11, r7, r10
 	eieio
+	lwzx	r11, r7, r10
 	/* Second load to recover the context state (Words 0 and 1) */
 	ldx	r11, r6, r10
 	b	3f
@@ -1410,8 +1411,8 @@  guest_exit_cont:		/* r9 = vcpu, r12 = trap, r13 = paca */
 	cmpldi	cr0, r10, 0
 	beq	1f
 	/* First load to pull the context, we ignore the value */
-	lwzcix	r11, r7, r10
 	eieio
+	lwzcix	r11, r7, r10
 	/* Second load to recover the context state (Words 0 and 1) */
 	ldcix	r11, r6, r10
 3:	std	r11, VCPU_XIVE_SAVED_STATE(r9)
@@ -1421,6 +1422,7 @@  guest_exit_cont:		/* r9 = vcpu, r12 = trap, r13 = paca */
 	stw	r10, VCPU_XIVE_PUSHED(r9)
 	stb	r10, (VCPU_XIVE_SAVED_STATE+3)(r9)
 	stb	r0, (VCPU_XIVE_SAVED_STATE+4)(r9)
+	eieio
 1:
 #endif /* CONFIG_KVM_XICS */
 	/* Save more register state  */