KVM: PPC: Book3S HV: Use decrementer to wake napping threads

This arranges for threads that are napping due to their vcpu having
ceded or due to not having a vcpu to wake up at the end of the guest's
timeslice without having to be poked with an IPI.  We do that by
arranging for the decrementer to contain a value no greater than the
number of timebase ticks remaining until the end of the timeslice.
In the case of a thread with no vcpu, this number is in the hypervisor
decrementer already.  In the case of a ceded vcpu, we use the smaller
of the HDEC value and the DEC value.

Using the DEC like this when ceded means we need to save and restore
the guest decrementer value around the nap.

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 12d7e4c..16719af 100644 (file)
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -172,6 +172,9 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
 
 kvmppc_primary_no_guest:
        /* We handle this much like a ceded vcpu */
+       /* put the HDEC into the DEC, since HDEC interrupts don't wake us */
+       mfspr   r3, SPRN_HDEC
+       mtspr   SPRN_DEC, r3
        /* set our bit in napping_threads */
        ld      r5, HSTATE_KVM_VCORE(r13)
        lbz     r7, HSTATE_PTID(r13)
@@ -223,6 +226,12 @@ kvm_novcpu_wakeup:
        cmpdi   r3, 0
        bge     kvm_novcpu_exit
 
+       /* See if our timeslice has expired (HDEC is negative) */
+       mfspr   r0, SPRN_HDEC
+       li      r12, BOOK3S_INTERRUPT_HV_DECREMENTER
+       cmpwi   r0, 0
+       blt     kvm_novcpu_exit
+
        /* Got an IPI but other vcpus aren't yet exiting, must be a latecomer */
        ld      r4, HSTATE_KVM_VCPU(r13)
        cmpdi   r4, 0
@@ -1493,10 +1502,10 @@ kvmhv_do_exit:                  /* r12 = trap, r13 = paca */
        cmpwi   r3,0x100        /* Are we the first here? */
        bge     43f
        cmpwi   r12,BOOK3S_INTERRUPT_HV_DECREMENTER
-       beq     40f
+       beq     43f
        li      r0,0
        mtspr   SPRN_HDEC,r0
-40:
+
        /*
         * Send an IPI to any napping threads, since an HDEC interrupt
         * doesn't wake CPUs up from nap.
@@ -2124,6 +2133,27 @@ _GLOBAL(kvmppc_h_cede)           /* r3 = vcpu pointer, r11 = msr, r13 = paca */
        /* save FP state */
        bl      kvmppc_save_fp
 
+       /*
+        * Set DEC to the smaller of DEC and HDEC, so that we wake
+        * no later than the end of our timeslice (HDEC interrupts
+        * don't wake us from nap).
+        */
+       mfspr   r3, SPRN_DEC
+       mfspr   r4, SPRN_HDEC
+       mftb    r5
+       cmpw    r3, r4
+       ble     67f
+       mtspr   SPRN_DEC, r4
+67:
+       /* save expiry time of guest decrementer */
+       extsw   r3, r3
+       add     r3, r3, r5
+       ld      r4, HSTATE_KVM_VCPU(r13)
+       ld      r5, HSTATE_KVM_VCORE(r13)
+       ld      r6, VCORE_TB_OFFSET(r5)
+       subf    r3, r6, r3      /* convert to host TB value */
+       std     r3, VCPU_DEC_EXPIRES(r4)
+
 #ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
        ld      r4, HSTATE_KVM_VCPU(r13)
        addi    r3, r4, VCPU_TB_CEDE
@@ -2181,6 +2211,15 @@ kvm_end_cede:
        /* load up FP state */
        bl      kvmppc_load_fp
 
+       /* Restore guest decrementer */
+       ld      r3, VCPU_DEC_EXPIRES(r4)
+       ld      r5, HSTATE_KVM_VCORE(r13)
+       ld      r6, VCORE_TB_OFFSET(r5)
+       add     r3, r3, r6      /* convert host TB to guest TB value */
+       mftb    r7
+       subf    r3, r7, r3
+       mtspr   SPRN_DEC, r3
+
        /* Load NV GPRS */
        ld      r14, VCPU_GPR(R14)(r4)
        ld      r15, VCPU_GPR(R15)(r4)