KVM: PPC: Book3S HV: Cope with host using large decrementer mode

POWER9 introduces a new mode for the decrementer register, called
large decrementer mode, in which the decrementer counter is 56 bits
wide rather than 32, and reads are sign-extended rather than
zero-extended.  For the decrementer, this new mode is optional and
controlled by a bit in the LPCR.  The hypervisor decrementer (HDEC)
is 56 bits wide on POWER9 and has no mode control.

Since KVM code reads and writes the decrementer and hypervisor
decrementer registers in a few places, it needs to be aware of the
need to treat the decrementer value as a 64-bit quantity, and only do
a 32-bit sign extension when large decrementer mode is not in effect.
Similarly, the HDEC should always be treated as a 64-bit quantity on
POWER9.  We define a new EXTEND_HDEC macro to encapsulate the feature
test for POWER9 and the sign extension.

To enable the sign extension to be removed in large decrementer mode,
we test the LPCR_LD bit in the host LPCR image stored in the struct
kvm for the guest.  If is set then large decrementer mode is enabled
and the sign extension should be skipped.

This is partly based on an earlier patch by Oliver O'Halloran.

Cc: stable@vger.kernel.org # v4.10+
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>

diff --git a/arch/powerpc/kvm/book3s_hv_interrupts.S b/arch/powerpc/kvm/book3s_hv_interrupts.S
index 0fdc4a2..404deb5 100644 (file)
--- a/arch/powerpc/kvm/book3s_hv_interrupts.S
+++ b/arch/powerpc/kvm/book3s_hv_interrupts.S
@@ -121,10 +121,20 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
         * Put whatever is in the decrementer into the
         * hypervisor decrementer.
         */
+BEGIN_FTR_SECTION
+       ld      r5, HSTATE_KVM_VCORE(r13)
+       ld      r6, VCORE_KVM(r5)
+       ld      r9, KVM_HOST_LPCR(r6)
+       andis.  r9, r9, LPCR_LD@h
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
        mfspr   r8,SPRN_DEC
        mftb    r7
-       mtspr   SPRN_HDEC,r8
+BEGIN_FTR_SECTION
+       /* On POWER9, don't sign-extend if host LPCR[LD] bit is set */
+       bne     32f
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
        extsw   r8,r8
+32:    mtspr   SPRN_HDEC,r8
        add     r8,r8,r7
        std     r8,HSTATE_DECEXP(r13)
 

diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index bdb3f76..e390b38 100644 (file)
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -32,6 +32,12 @@
 #include <asm/opal.h>
 #include <asm/xive-regs.h>
 
+/* Sign-extend HDEC if not on POWER9 */
+#define EXTEND_HDEC(reg)                       \
+BEGIN_FTR_SECTION;                             \
+       extsw   reg, reg;                       \
+END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300)
+
 #define VCPU_GPRS_TM(reg) (((reg) * ULONG_SIZE) + VCPU_GPR_TM)
 
 /* Values in HSTATE_NAPPING(r13) */
@@ -214,6 +220,8 @@ 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 */
+       /* HDEC may be larger than DEC for arch >= v3.00, but since the */
+       /* HDEC value came from DEC in the first place, it will fit */
        mfspr   r3, SPRN_HDEC
        mtspr   SPRN_DEC, r3
        /*
@@ -295,8 +303,9 @@ kvm_novcpu_wakeup:
 
        /* See if our timeslice has expired (HDEC is negative) */
        mfspr   r0, SPRN_HDEC
+       EXTEND_HDEC(r0)
        li      r12, BOOK3S_INTERRUPT_HV_DECREMENTER
-       cmpwi   r0, 0
+       cmpdi   r0, 0
        blt     kvm_novcpu_exit
 
        /* Got an IPI but other vcpus aren't yet exiting, must be a latecomer */
@@ -390,8 +399,8 @@ kvm_secondary_got_guest:
        lbz     r4, HSTATE_PTID(r13)
        cmpwi   r4, 0
        bne     63f
-       lis     r6, 0x7fff
-       ori     r6, r6, 0xffff
+       LOAD_REG_ADDR(r6, decrementer_max)
+       ld      r6, 0(r6)
        mtspr   SPRN_HDEC, r6
        /* and set per-LPAR registers, if doing dynamic micro-threading */
        ld      r6, HSTATE_SPLIT_MODE(r13)
@@ -968,7 +977,8 @@ ALT_FTR_SECTION_END_IFCLR(CPU_FTR_ARCH_300)
 
        /* Check if HDEC expires soon */
        mfspr   r3, SPRN_HDEC
-       cmpwi   r3, 512         /* 1 microsecond */
+       EXTEND_HDEC(r3)
+       cmpdi   r3, 512         /* 1 microsecond */
        blt     hdec_soon
 
 #ifdef CONFIG_KVM_XICS
@@ -2366,12 +2376,13 @@ END_FTR_SECTION_IFSET(CPU_FTR_TM)
        mfspr   r3, SPRN_DEC
        mfspr   r4, SPRN_HDEC
        mftb    r5
-       cmpw    r3, r4
+       extsw   r3, r3
+       EXTEND_HDEC(r4)
+       cmpd    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)