KVM: PPC: Book3S HV: Refine barriers in guest entry/exit

Some users have reported instances of the host hanging with secondary
threads of a core waiting for the primary thread to exit the guest,
and the primary thread stuck in nap mode.  This prompted a review of
the memory barriers in the guest entry/exit code, and this is the
result.  Most of these changes are the suggestions of Dean Burdick
<deanburdick@us.ibm.com>.

The barriers between updating napping_threads and reading the
entry_exit_count on the one hand, and updating entry_exit_count and
reading napping_threads on the other, need to be isync not lwsync,
since we need to ensure that either the napping_threads update or the
entry_exit_count update get seen.  It is not sufficient to order the
load vs. lwarx, as lwsync does; we need to order the load vs. the
stwcx., so we need isync.

In addition, we need a full sync before sending IPIs to wake other
threads from nap, to ensure that the write to the entry_exit_count is
visible before the IPI occurs.

Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>

diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index bc8de75b1925cd34ad1d11379fee8c09f1d275e5..bde28da696103963185197eac2756d14d56504cd 100644 (file)
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -153,7 +153,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
 
 13:    b       machine_check_fwnmi
 
-
 /*
  * We come in here when wakened from nap mode on a secondary hw thread.
  * Relocation is off and most register values are lost.
@@ -224,6 +223,11 @@ kvm_start_guest:
        /* Clear our vcpu pointer so we don't come back in early */
        li      r0, 0
        std     r0, HSTATE_KVM_VCPU(r13)
+       /*
+        * Make sure we clear HSTATE_KVM_VCPU(r13) before incrementing
+        * the nap_count, because once the increment to nap_count is
+        * visible we could be given another vcpu.
+        */
        lwsync
        /* Clear any pending IPI - we're an offline thread */
        ld      r5, HSTATE_XICS_PHYS(r13)
@@ -241,7 +245,6 @@ kvm_start_guest:
        /* increment the nap count and then go to nap mode */
        ld      r4, HSTATE_KVM_VCORE(r13)
        addi    r4, r4, VCORE_NAP_COUNT
-       lwsync                          /* make previous updates visible */
 51:    lwarx   r3, 0, r4
        addi    r3, r3, 1
        stwcx.  r3, 0, r4
@@ -990,14 +993,13 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
         */
        /* Increment the threads-exiting-guest count in the 0xff00
           bits of vcore->entry_exit_count */
-       lwsync
        ld      r5,HSTATE_KVM_VCORE(r13)
        addi    r6,r5,VCORE_ENTRY_EXIT
 41:    lwarx   r3,0,r6
        addi    r0,r3,0x100
        stwcx.  r0,0,r6
        bne     41b
-       lwsync
+       isync           /* order stwcx. vs. reading napping_threads */
 
        /*
         * At this point we have an interrupt that we have to pass
@@ -1030,6 +1032,8 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
        sld     r0,r0,r4
        andc.   r3,r3,r0                /* no sense IPI'ing ourselves */
        beq     43f
+       /* Order entry/exit update vs. IPIs */
+       sync
        mulli   r4,r4,PACA_SIZE         /* get paca for thread 0 */
        subf    r6,r4,r13
 42:    andi.   r0,r3,1
@@ -1638,10 +1642,10 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_206)
        bge     kvm_cede_exit
        stwcx.  r4,0,r6
        bne     31b
+       /* order napping_threads update vs testing entry_exit_count */
+       isync
        li      r0,1
        stb     r0,HSTATE_NAPPING(r13)
-       /* order napping_threads update vs testing entry_exit_count */
-       lwsync
        mr      r4,r3
        lwz     r7,VCORE_ENTRY_EXIT(r5)
        cmpwi   r7,0x100