* [PATCH 1/6] KVM: PPC: Book3S HV: Make sure we don't re-enter guest without XIVE loaded
2018-01-17 9:51 [PATCH 0/6] KVM: PPC: Book3S HV: Changes for POWER9 v2.2 support Paul Mackerras
@ 2018-01-17 9:51 ` Paul Mackerras
2018-01-17 9:51 ` [PATCH 2/6] KVM: PPC: Book3S HV: Do SLB load/unload with guest LPCR value loaded Paul Mackerras
` (4 subsequent siblings)
5 siblings, 0 replies; 11+ messages in thread
From: Paul Mackerras @ 2018-01-17 9:51 UTC (permalink / raw)
To: kvm, linuxppc-dev; +Cc: kvm-ppc
This fixes a bug where it is possible to enter a guest on a POWER9
system without having the XIVE (interrupt controller) context loaded.
This can happen because we unload the XIVE context from the CPU
before doing the real-mode handling for machine checks. After the
real-mode handler runs, it is possible that we re-enter the guest
via a fast path which does not load the XIVE context.
To fix this, we move the unloading of the XIVE context to come after
the real-mode machine check handler is called.
Fixes: 5af50993850a ("KVM: PPC: Book3S HV: Native usage of the XIVE interrupt controller")
Cc: stable@vger.kernel.org # v4.11+
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
---
arch/powerpc/kvm/book3s_hv_rmhandlers.S | 40 ++++++++++++++++-----------------
1 file changed, 20 insertions(+), 20 deletions(-)
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index c8ffd69..76332a3 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -1423,6 +1423,26 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
blt deliver_guest_interrupt
guest_exit_cont: /* r9 = vcpu, r12 = trap, r13 = paca */
+ /* Save more register state */
+ mfdar r6
+ mfdsisr r7
+ std r6, VCPU_DAR(r9)
+ stw r7, VCPU_DSISR(r9)
+ /* don't overwrite fault_dar/fault_dsisr if HDSI */
+ cmpwi r12,BOOK3S_INTERRUPT_H_DATA_STORAGE
+ beq mc_cont
+ std r6, VCPU_FAULT_DAR(r9)
+ stw r7, VCPU_FAULT_DSISR(r9)
+
+ /* See if it is a machine check */
+ cmpwi r12, BOOK3S_INTERRUPT_MACHINE_CHECK
+ beq machine_check_realmode
+mc_cont:
+#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
+ addi r3, r9, VCPU_TB_RMEXIT
+ mr r4, r9
+ bl kvmhv_accumulate_time
+#endif
#ifdef CONFIG_KVM_XICS
/* We are exiting, pull the VP from the XIVE */
lwz r0, VCPU_XIVE_PUSHED(r9)
@@ -1460,26 +1480,6 @@ guest_exit_cont: /* r9 = vcpu, r12 = trap, r13 = paca */
eieio
1:
#endif /* CONFIG_KVM_XICS */
- /* Save more register state */
- mfdar r6
- mfdsisr r7
- std r6, VCPU_DAR(r9)
- stw r7, VCPU_DSISR(r9)
- /* don't overwrite fault_dar/fault_dsisr if HDSI */
- cmpwi r12,BOOK3S_INTERRUPT_H_DATA_STORAGE
- beq mc_cont
- std r6, VCPU_FAULT_DAR(r9)
- stw r7, VCPU_FAULT_DSISR(r9)
-
- /* See if it is a machine check */
- cmpwi r12, BOOK3S_INTERRUPT_MACHINE_CHECK
- beq machine_check_realmode
-mc_cont:
-#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
- addi r3, r9, VCPU_TB_RMEXIT
- mr r4, r9
- bl kvmhv_accumulate_time
-#endif
mr r3, r12
/* Increment exit count, poke other threads to exit */
--
2.7.4
^ permalink raw reply related [flat|nested] 11+ messages in thread* [PATCH 2/6] KVM: PPC: Book3S HV: Do SLB load/unload with guest LPCR value loaded
2018-01-17 9:51 [PATCH 0/6] KVM: PPC: Book3S HV: Changes for POWER9 v2.2 support Paul Mackerras
2018-01-17 9:51 ` [PATCH 1/6] KVM: PPC: Book3S HV: Make sure we don't re-enter guest without XIVE loaded Paul Mackerras
@ 2018-01-17 9:51 ` Paul Mackerras
2018-01-17 9:51 ` [PATCH 3/6] KVM: PPC: Book3S HV: Allow HPT and radix on the same core for POWER9 v2.2 Paul Mackerras
` (3 subsequent siblings)
5 siblings, 0 replies; 11+ messages in thread
From: Paul Mackerras @ 2018-01-17 9:51 UTC (permalink / raw)
To: kvm, linuxppc-dev; +Cc: kvm-ppc
This moves the code that loads and unloads the guest SLB values so that
it is done while the guest LPCR value is loaded in the LPCR register.
The reason for doing this is that on POWER9, the behaviour of the
slbmte instruction depends on the LPCR[UPRT] bit. If UPRT is 1, as
it is for a radix host (or guest), the SLB index is truncated to
2 bits. This means that for a HPT guest on a radix host, the SLB
was not being loaded correctly, causing the guest to crash.
The SLB is now loaded much later in the guest entry path, after the
LPCR is loaded, which for a secondary thread is after it sees that
the primary thread has switched the MMU to the guest. The loop that
waits for the primary thread has a branch out to the exit code that
is taken if it sees that other threads have commenced exiting the
guest. Since we have now not loaded the SLB at this point, we make
this path branch to a new label 'guest_bypass' and we move the SLB
unload code to before this label.
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
---
arch/powerpc/kvm/book3s_hv_rmhandlers.S | 109 ++++++++++++++++----------------
1 file changed, 55 insertions(+), 54 deletions(-)
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 76332a3..30ece4c 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -617,13 +617,6 @@ kvmppc_hv_entry:
lbz r0, KVM_RADIX(r9)
cmpwi cr7, r0, 0
- /* Clear out SLB if hash */
- bne cr7, 2f
- li r6,0
- slbmte r6,r6
- slbia
- ptesync
-2:
/*
* POWER7/POWER8 host -> guest partition switch code.
* We don't have to lock against concurrent tlbies,
@@ -738,19 +731,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
10: cmpdi r4, 0
beq kvmppc_primary_no_guest
kvmppc_got_guest:
-
- /* Load up guest SLB entries (N.B. slb_max will be 0 for radix) */
- lwz r5,VCPU_SLB_MAX(r4)
- cmpwi r5,0
- beq 9f
- mtctr r5
- addi r6,r4,VCPU_SLB
-1: ld r8,VCPU_SLB_E(r6)
- ld r9,VCPU_SLB_V(r6)
- slbmte r9,r8
- addi r6,r6,VCPU_SLB_SIZE
- bdnz 1b
-9:
/* Increment yield count if they have a VPA */
ld r3, VCPU_VPA(r4)
cmpdi r3, 0
@@ -1017,6 +997,29 @@ ALT_FTR_SECTION_END_IFCLR(CPU_FTR_ARCH_300)
cmpdi r3, 512 /* 1 microsecond */
blt hdec_soon
+ /* For hash guest, clear out and reload the SLB */
+ ld r6, VCPU_KVM(r4)
+ lbz r0, KVM_RADIX(r6)
+ cmpwi r0, 0
+ bne 9f
+ li r6, 0
+ slbmte r6, r6
+ slbia
+ ptesync
+
+ /* Load up guest SLB entries (N.B. slb_max will be 0 for radix) */
+ lwz r5,VCPU_SLB_MAX(r4)
+ cmpwi r5,0
+ beq 9f
+ mtctr r5
+ addi r6,r4,VCPU_SLB
+1: ld r8,VCPU_SLB_E(r6)
+ ld r9,VCPU_SLB_V(r6)
+ slbmte r9,r8
+ addi r6,r6,VCPU_SLB_SIZE
+ bdnz 1b
+9:
+
#ifdef CONFIG_KVM_XICS
/* We are entering the guest on that thread, push VCPU to XIVE */
ld r10, HSTATE_XIVE_TIMA_PHYS(r13)
@@ -1193,7 +1196,7 @@ hdec_soon:
addi r3, r4, VCPU_TB_RMEXIT
bl kvmhv_accumulate_time
#endif
- b guest_exit_cont
+ b guest_bypass
/******************************************************************************
* *
@@ -1481,34 +1484,12 @@ mc_cont:
1:
#endif /* CONFIG_KVM_XICS */
- mr r3, r12
- /* Increment exit count, poke other threads to exit */
- bl kvmhv_commence_exit
- nop
- ld r9, HSTATE_KVM_VCPU(r13)
- lwz r12, VCPU_TRAP(r9)
-
- /* Stop others sending VCPU interrupts to this physical CPU */
- li r0, -1
- stw r0, VCPU_CPU(r9)
- stw r0, VCPU_THREAD_CPU(r9)
-
- /* Save guest CTRL register, set runlatch to 1 */
- mfspr r6,SPRN_CTRLF
- stw r6,VCPU_CTRL(r9)
- andi. r0,r6,1
- bne 4f
- ori r6,r6,1
- mtspr SPRN_CTRLT,r6
-4:
- /* Check if we are running hash or radix and store it in cr2 */
+ /* For hash guest, read the guest SLB and save it away */
ld r5, VCPU_KVM(r9)
lbz r0, KVM_RADIX(r5)
- cmpwi cr2,r0,0
-
- /* Read the guest SLB and save it away */
li r5, 0
- bne cr2, 3f /* for radix, save 0 entries */
+ cmpwi r0, 0
+ bne 3f /* for radix, save 0 entries */
lwz r0,VCPU_SLB_NR(r9) /* number of entries in SLB */
mtctr r0
li r6,0
@@ -1524,8 +1505,34 @@ mc_cont:
addi r5,r5,1
2: addi r6,r6,1
bdnz 1b
+ /* Finally clear out the SLB */
+ li r0,0
+ slbmte r0,r0
+ slbia
+ ptesync
3: stw r5,VCPU_SLB_MAX(r9)
+guest_bypass:
+ mr r3, r12
+ /* Increment exit count, poke other threads to exit */
+ bl kvmhv_commence_exit
+ nop
+ ld r9, HSTATE_KVM_VCPU(r13)
+ lwz r12, VCPU_TRAP(r9)
+
+ /* Stop others sending VCPU interrupts to this physical CPU */
+ li r0, -1
+ stw r0, VCPU_CPU(r9)
+ stw r0, VCPU_THREAD_CPU(r9)
+
+ /* Save guest CTRL register, set runlatch to 1 */
+ mfspr r6,SPRN_CTRLF
+ stw r6,VCPU_CTRL(r9)
+ andi. r0,r6,1
+ bne 4f
+ ori r6,r6,1
+ mtspr SPRN_CTRLT,r6
+4:
/*
* Save the guest PURR/SPURR
*/
@@ -1803,7 +1810,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
ld r5, VCPU_KVM(r9)
lbz r0, KVM_RADIX(r5)
cmpwi cr2, r0, 0
- beq cr2, 3f
+ beq cr2, 4f
/* Radix: Handle the case where the guest used an illegal PID */
LOAD_REG_ADDR(r4, mmu_base_pid)
@@ -1839,15 +1846,9 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
BEGIN_FTR_SECTION
PPC_INVALIDATE_ERAT
END_FTR_SECTION_IFSET(CPU_FTR_POWER9_DD1)
- b 4f
+4:
#endif /* CONFIG_PPC_RADIX_MMU */
- /* Hash: clear out SLB */
-3: li r5,0
- slbmte r5,r5
- slbia
- ptesync
-4:
/*
* POWER7/POWER8 guest -> host partition switch code.
* We don't have to lock against tlbies but we do
--
2.7.4
^ permalink raw reply related [flat|nested] 11+ messages in thread* [PATCH 3/6] KVM: PPC: Book3S HV: Allow HPT and radix on the same core for POWER9 v2.2
2018-01-17 9:51 [PATCH 0/6] KVM: PPC: Book3S HV: Changes for POWER9 v2.2 support Paul Mackerras
2018-01-17 9:51 ` [PATCH 1/6] KVM: PPC: Book3S HV: Make sure we don't re-enter guest without XIVE loaded Paul Mackerras
2018-01-17 9:51 ` [PATCH 2/6] KVM: PPC: Book3S HV: Do SLB load/unload with guest LPCR value loaded Paul Mackerras
@ 2018-01-17 9:51 ` Paul Mackerras
2018-01-17 11:14 ` Benjamin Herrenschmidt
2018-01-17 9:51 ` [PATCH 4/6] KVM: PPC: Book3S HV: Improve handling of debug-trigger HMIs on POWER9 Paul Mackerras
` (2 subsequent siblings)
5 siblings, 1 reply; 11+ messages in thread
From: Paul Mackerras @ 2018-01-17 9:51 UTC (permalink / raw)
To: kvm, linuxppc-dev; +Cc: kvm-ppc
POWER9 chip versions starting with v2.2 can support running with some
threads of a core in HPT mode and others in radix mode. This means
that we don't have to prohibit independent-threads mode when running
a HPT guest on a radix host, and we don't have to do any of the
synchronization between threads that was introduced in commit
c01015091a77 ("KVM: PPC: Book3S HV: Run HPT guests on POWER9 radix
hosts", 2017-10-19).
Rather than using up another CPU feature bit, we just do an
explicit test on the PVR (processor version register) at module
startup time to determine whether we have to take steps to avoid
having some threads in HPT mode and some in radix mode (so-called
"mixed mode").
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
---
arch/powerpc/kvm/book3s_hv.c | 28 ++++++++++++++++++++++------
1 file changed, 22 insertions(+), 6 deletions(-)
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index b2d448c..99ed374 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -118,6 +118,9 @@ module_param_cb(h_ipi_redirect, &module_param_ops, &h_ipi_redirect,
MODULE_PARM_DESC(h_ipi_redirect, "Redirect H_IPI wakeup to a free host core");
#endif
+/* If set, the threads on each CPU core have to be in the same MMU mode */
+static bool no_mixing_hpt_and_radix;
+
static void kvmppc_end_cede(struct kvm_vcpu *vcpu);
static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu);
@@ -2386,8 +2389,8 @@ static void init_core_info(struct core_info *cip, struct kvmppc_vcore *vc)
static bool subcore_config_ok(int n_subcores, int n_threads)
{
/*
- * POWER9 "SMT4" cores are permanently in what is effectively a 4-way split-core
- * mode, with one thread per subcore.
+ * POWER9 "SMT4" cores are permanently in what is effectively a 4-way
+ * split-core mode, with one thread per subcore.
*/
if (cpu_has_feature(CPU_FTR_ARCH_300))
return n_subcores <= 4 && n_threads == 1;
@@ -2423,8 +2426,8 @@ static bool can_dynamic_split(struct kvmppc_vcore *vc, struct core_info *cip)
if (!cpu_has_feature(CPU_FTR_ARCH_207S))
return false;
- /* POWER9 currently requires all threads to be in the same MMU mode */
- if (cpu_has_feature(CPU_FTR_ARCH_300) &&
+ /* Some POWER9 chips require all threads to be in the same MMU mode */
+ if (no_mixing_hpt_and_radix &&
kvm_is_radix(vc->kvm) != kvm_is_radix(cip->vc[0]->kvm))
return false;
@@ -2687,9 +2690,11 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
* threads are offline. Also check if the number of threads in this
* guest are greater than the current system threads per guest.
* On POWER9, we need to be not in independent-threads mode if
- * this is a HPT guest on a radix host.
+ * this is a HPT guest on a radix host machine where the
+ * CPU threads may not be in different MMU modes.
*/
- hpt_on_radix = radix_enabled() && !kvm_is_radix(vc->kvm);
+ hpt_on_radix = no_mixing_hpt_and_radix && radix_enabled() &&
+ !kvm_is_radix(vc->kvm);
if (((controlled_threads > 1) &&
((vc->num_threads > threads_per_subcore) || !on_primary_thread())) ||
(hpt_on_radix && vc->kvm->arch.threads_indep)) {
@@ -4446,6 +4451,17 @@ static int kvmppc_book3s_init_hv(void)
if (kvmppc_radix_possible())
r = kvmppc_radix_init();
+
+ /*
+ * POWER9 chips before version 2.02 can't have some threads in
+ * HPT mode and some in radix mode on the same core.
+ */
+ if (cpu_has_feature(CPU_FTR_ARCH_300)) {
+ unsigned int pvr = mfspr(SPRN_PVR);
+ if ((pvr >> 16) == PVR_POWER9 && (pvr & 0xfff) < 0x202)
+ no_mixing_hpt_and_radix = true;
+ }
+
return r;
}
--
2.7.4
^ permalink raw reply related [flat|nested] 11+ messages in thread* Re: [PATCH 3/6] KVM: PPC: Book3S HV: Allow HPT and radix on the same core for POWER9 v2.2
2018-01-17 9:51 ` [PATCH 3/6] KVM: PPC: Book3S HV: Allow HPT and radix on the same core for POWER9 v2.2 Paul Mackerras
@ 2018-01-17 11:14 ` Benjamin Herrenschmidt
2018-01-18 1:27 ` Paul Mackerras
0 siblings, 1 reply; 11+ messages in thread
From: Benjamin Herrenschmidt @ 2018-01-17 11:14 UTC (permalink / raw)
To: Paul Mackerras, kvm, linuxppc-dev; +Cc: kvm-ppc
On Wed, 2018-01-17 at 20:51 +1100, Paul Mackerras wrote:
> +
> + /*
> + * POWER9 chips before version 2.02 can't have some threads in
> + * HPT mode and some in radix mode on the same core.
> + */
> + if (cpu_has_feature(CPU_FTR_ARCH_300)) {
> + unsigned int pvr = mfspr(SPRN_PVR);
> + if ((pvr >> 16) == PVR_POWER9 && (pvr & 0xfff) < 0x202)
> + no_mixing_hpt_and_radix = true;
> + }
> +
> return r;
> }
You need to check that it's a Nimbus using the top nimble of the bottom
16 bits of PVR. For Cumulus, the fixes are either in 1.0 or 1.1 (to
check).
Cheers,
Ben.
^ permalink raw reply [flat|nested] 11+ messages in thread* Re: [PATCH 3/6] KVM: PPC: Book3S HV: Allow HPT and radix on the same core for POWER9 v2.2
2018-01-17 11:14 ` Benjamin Herrenschmidt
@ 2018-01-18 1:27 ` Paul Mackerras
2018-01-18 1:51 ` Benjamin Herrenschmidt
0 siblings, 1 reply; 11+ messages in thread
From: Paul Mackerras @ 2018-01-18 1:27 UTC (permalink / raw)
To: Benjamin Herrenschmidt; +Cc: kvm, linuxppc-dev, kvm-ppc
On Wed, Jan 17, 2018 at 10:14:45PM +1100, Benjamin Herrenschmidt wrote:
> On Wed, 2018-01-17 at 20:51 +1100, Paul Mackerras wrote:
> > +
> > + /*
> > + * POWER9 chips before version 2.02 can't have some threads in
> > + * HPT mode and some in radix mode on the same core.
> > + */
> > + if (cpu_has_feature(CPU_FTR_ARCH_300)) {
> > + unsigned int pvr = mfspr(SPRN_PVR);
> > + if ((pvr >> 16) == PVR_POWER9 && (pvr & 0xfff) < 0x202)
> > + no_mixing_hpt_and_radix = true;
> > + }
> > +
> > return r;
> > }
>
> You need to check that it's a Nimbus using the top nimble of the bottom
> 16 bits of PVR. For Cumulus, the fixes are either in 1.0 or 1.1 (to
> check).
OK, how about this for the check:
if (cpu_has_feature(CPU_FTR_ARCH_300)) {
unsigned int pvr = mfspr(SPRN_PVR);
if ((pvr >> 16) == PVR_POWER9 &&
(((pvr & 0xe000) == 0 && (pvr & 0xfff) < 0x202) ||
((pvr & 0xe000) == 0x2000 && (pvr & 0xfff) < 0x101)))
no_mixing_hpt_and_radix = true;
}
Paul.
^ permalink raw reply [flat|nested] 11+ messages in thread* Re: [PATCH 3/6] KVM: PPC: Book3S HV: Allow HPT and radix on the same core for POWER9 v2.2
2018-01-18 1:27 ` Paul Mackerras
@ 2018-01-18 1:51 ` Benjamin Herrenschmidt
0 siblings, 0 replies; 11+ messages in thread
From: Benjamin Herrenschmidt @ 2018-01-18 1:51 UTC (permalink / raw)
To: Paul Mackerras; +Cc: kvm, linuxppc-dev, kvm-ppc
On Thu, 2018-01-18 at 12:27 +1100, Paul Mackerras wrote:
> > You need to check that it's a Nimbus using the top nimble of the bottom
> > 16 bits of PVR. For Cumulus, the fixes are either in 1.0 or 1.1 (to
> > check).
>
> OK, how about this for the check:
>
> if (cpu_has_feature(CPU_FTR_ARCH_300)) {
> unsigned int pvr = mfspr(SPRN_PVR);
> if ((pvr >> 16) == PVR_POWER9 &&
> (((pvr & 0xe000) == 0 && (pvr & 0xfff) < 0x202) ||
> ((pvr & 0xe000) == 0x2000 && (pvr & 0xfff) < 0x101)))
> no_mixing_hpt_and_radix = true;
> }
>
> Paul.
Looks good.
Cheers,
Ben.
^ permalink raw reply [flat|nested] 11+ messages in thread
* [PATCH 4/6] KVM: PPC: Book3S HV: Improve handling of debug-trigger HMIs on POWER9
2018-01-17 9:51 [PATCH 0/6] KVM: PPC: Book3S HV: Changes for POWER9 v2.2 support Paul Mackerras
` (2 preceding siblings ...)
2018-01-17 9:51 ` [PATCH 3/6] KVM: PPC: Book3S HV: Allow HPT and radix on the same core for POWER9 v2.2 Paul Mackerras
@ 2018-01-17 9:51 ` Paul Mackerras
2018-01-22 3:34 ` [4/6] " Michael Ellerman
2018-01-17 9:51 ` [PATCH 5/6] powerpc: Add a CPU feature bit for TM bug workarounds on POWER9 v2.2 Paul Mackerras
2018-01-17 9:51 ` [PATCH 6/6] KVM: PPC: Book3S HV: Work around transactional memory bugs in POWER9 Paul Mackerras
5 siblings, 1 reply; 11+ messages in thread
From: Paul Mackerras @ 2018-01-17 9:51 UTC (permalink / raw)
To: kvm, linuxppc-dev; +Cc: kvm-ppc
Hypervisor maintenance interrupts (HMIs) are generated by various
causes, signalled by bits in the hypervisor maintenance exception
register (HMER). In most cases calling OPAL to handle the interrupt
is the correct thing to do, but the "debug trigger" HMIs signalled by
PPC bit 17 (bit 46) of HMER are used to invoke software workarounds
for hardware bugs, and OPAL does not have any code to handle this
cause. The debug trigger HMI is used in POWER9 DD2.0 and DD2.1 chips
to work around a hardware bug in executing vector load instructions to
cache inhibited memory. In POWER9 DD2.2 chips, it is generated when
conditions are detected relating to threads being in TM (transactional
memory) suspended mode when the core SMT configuration needs to be
reconfigured.
The kernel currently has code to detect the vector CI load condition,
but only when the HMI occurs in the host, not when it occurs in a
guest. If a HMI occurs in the guest, it is always passed to OPAL, and
then we always re-sync the timebase, because the HMI cause might have
been a timebase error, for which OPAL would re-sync the timebase, thus
removing the timebase offset which KVM applied for the guest. Since
we don't know what OPAL did, we don't know whether to subtract the
timebase offset from the timebase, so instead we re-sync the timebase.
This adds code to determine explicitly what the cause of a debug
trigger HMI will be. This is based on a new device-tree property
under the CPU nodes called ibm,hmi-special-triggers, if it is
present, or otherwise based on the PVR (processor version register).
The handling of debug trigger HMIs is pulled out into a separate
function which can be called from the KVM guest exit code. If this
function handles and clears the HMI, and no other HMI causes remain,
then we skip calling OPAL and we proceed to subtract the guest
timebase offset from the timebase.
The overall handling for HMIs that occur in the host (i.e. not in a
KVM guest) is largely unchanged, except that we now don't set the flag
for the vector CI load workaround on DD2.2 processors.
This also removes a BUG_ON in the KVM code. BUG_ON is generally not
useful in KVM guest entry/exit code since it is difficult to handle
the resulting trap gracefully.
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
---
arch/powerpc/include/asm/hmi.h | 4 +
arch/powerpc/include/asm/reg.h | 5 +-
arch/powerpc/kernel/mce.c | 142 +++++++++++++++++++++++++-------
arch/powerpc/kvm/book3s_hv_ras.c | 8 +-
arch/powerpc/kvm/book3s_hv_rmhandlers.S | 9 +-
5 files changed, 131 insertions(+), 37 deletions(-)
diff --git a/arch/powerpc/include/asm/hmi.h b/arch/powerpc/include/asm/hmi.h
index 85b7a1a..9c14f7b 100644
--- a/arch/powerpc/include/asm/hmi.h
+++ b/arch/powerpc/include/asm/hmi.h
@@ -42,4 +42,8 @@ extern void wait_for_tb_resync(void);
static inline void wait_for_subcore_guest_exit(void) { }
static inline void wait_for_tb_resync(void) { }
#endif
+
+struct pt_regs;
+extern long hmi_handle_debugtrig(struct pt_regs *regs);
+
#endif /* __ASM_PPC64_HMI_H__ */
diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index b779f3c..14e41b8 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -432,8 +432,9 @@
#define SPRN_LPID 0x13F /* Logical Partition Identifier */
#endif
#define LPID_RSVD 0x3ff /* Reserved LPID for partn switching */
-#define SPRN_HMER 0x150 /* Hardware m? error recovery */
-#define SPRN_HMEER 0x151 /* Hardware m? enable error recovery */
+#define SPRN_HMER 0x150 /* Hypervisor maintenance exception reg */
+#define HMER_DEBUG_TRIG (1ul << (63 - 17)) /* Debug trigger */
+#define SPRN_HMEER 0x151 /* Hyp maintenance exception enable reg */
#define SPRN_PCR 0x152 /* Processor compatibility register */
#define PCR_VEC_DIS (1ul << (63-0)) /* Vec. disable (bit NA since POWER8) */
#define PCR_VSX_DIS (1ul << (63-1)) /* VSX disable (bit NA since POWER8) */
diff --git a/arch/powerpc/kernel/mce.c b/arch/powerpc/kernel/mce.c
index 742e465..d2fecae 100644
--- a/arch/powerpc/kernel/mce.c
+++ b/arch/powerpc/kernel/mce.c
@@ -495,37 +495,123 @@ long machine_check_early(struct pt_regs *regs)
return handled;
}
-long hmi_exception_realmode(struct pt_regs *regs)
+/* Possible meanings for HMER_DEBUG_TRIG bit being set on POWER9 */
+static enum {
+ DTRIG_UNKNOWN,
+ DTRIG_VECTOR_CI, /* need to emulate vector CI load instr */
+ DTRIG_SUSPEND_ESCAPE, /* need to escape from TM suspend mode */
+} hmer_debug_trig_function;
+
+static int init_debug_trig_function(void)
{
- __this_cpu_inc(irq_stat.hmi_exceptions);
-
-#ifdef CONFIG_PPC_BOOK3S_64
- /* Workaround for P9 vector CI loads (see p9_hmi_special_emu) */
- if (pvr_version_is(PVR_POWER9)) {
- unsigned long hmer = mfspr(SPRN_HMER);
-
- /* Do we have the debug bit set */
- if (hmer & PPC_BIT(17)) {
- hmer &= ~PPC_BIT(17);
- mtspr(SPRN_HMER, hmer);
-
- /*
- * Now to avoid problems with soft-disable we
- * only do the emulation if we are coming from
- * user space
- */
- if (user_mode(regs))
- local_paca->hmi_p9_special_emu = 1;
-
- /*
- * Don't bother going to OPAL if that's the
- * only relevant bit.
- */
- if (!(hmer & mfspr(SPRN_HMEER)))
- return local_paca->hmi_p9_special_emu;
+ int pvr;
+ struct device_node *cpun;
+ struct property *prop = NULL;
+ const char *str;
+
+ /* First look in the device tree */
+ preempt_disable();
+ cpun = of_get_cpu_node(smp_processor_id(), NULL);
+ if (cpun) {
+ of_property_for_each_string(cpun, "ibm,hmi-special-triggers",
+ prop, str) {
+ if (strcmp(str, "bit17-vector-ci-load") == 0)
+ hmer_debug_trig_function = DTRIG_VECTOR_CI;
+ else if (strcmp(str, "bit17-tm-suspend-escape") == 0)
+ hmer_debug_trig_function = DTRIG_SUSPEND_ESCAPE;
}
+ of_node_put(cpun);
+ }
+ preempt_enable();
+
+ /* If we found the property, don't look at PVR */
+ if (prop)
+ goto out;
+
+ pvr = mfspr(SPRN_PVR);
+ /* Check for POWER9 Nimbus (scale-out) */
+ if ((PVR_VER(pvr) == PVR_POWER9) && (pvr & 0xe000) == 0) {
+ /* DD2.2 and later */
+ if ((pvr & 0xfff) >= 0x202)
+ hmer_debug_trig_function = DTRIG_SUSPEND_ESCAPE;
+ /* DD2.0 and DD2.1 - used for vector CI load emulation */
+ else if ((pvr & 0xfff) >= 0x200)
+ hmer_debug_trig_function = DTRIG_VECTOR_CI;
+ }
+
+ out:
+ switch (hmer_debug_trig_function) {
+ case DTRIG_VECTOR_CI:
+ pr_debug("HMI debug trigger used for vector CI load\n");
+ break;
+ case DTRIG_SUSPEND_ESCAPE:
+ pr_debug("HMI debug trigger used for TM suspend escape\n");
+ break;
+ default:
+ break;
}
-#endif /* CONFIG_PPC_BOOK3S_64 */
+ return 0;
+}
+__initcall(init_debug_trig_function);
+
+/*
+ * Handle HMIs that occur as a result of a debug trigger.
+ * Return values:
+ * -1 means this is not a HMI cause that we know about
+ * 0 means no further handling is required
+ * 1 means further handling is required
+ */
+long hmi_handle_debugtrig(struct pt_regs *regs)
+{
+ unsigned long hmer = mfspr(SPRN_HMER);
+ long ret = 0;
+
+ /* HMER_DEBUG_TRIG bit is used for various workarounds on P9 */
+ if (!((hmer & HMER_DEBUG_TRIG)
+ && hmer_debug_trig_function != DTRIG_UNKNOWN))
+ return -1;
+
+ hmer &= ~HMER_DEBUG_TRIG;
+ /* HMER is a write-AND register */
+ mtspr(SPRN_HMER, ~HMER_DEBUG_TRIG);
+
+ switch (hmer_debug_trig_function) {
+ case DTRIG_VECTOR_CI:
+ /*
+ * Now to avoid problems with soft-disable we
+ * only do the emulation if we are coming from
+ * host user space
+ */
+ if (regs && user_mode(regs))
+ ret = local_paca->hmi_p9_special_emu = 1;
+
+ break;
+
+ default:
+ break;
+ }
+
+ /*
+ * See if any other HMI causes remain to be handled
+ */
+ if (hmer & mfspr(SPRN_HMEER))
+ return -1;
+
+ return ret;
+}
+
+/*
+ * Return values:
+ */
+long hmi_exception_realmode(struct pt_regs *regs)
+{
+ int ret;
+
+ __this_cpu_inc(irq_stat.hmi_exceptions);
+
+ ret = hmi_handle_debugtrig(regs);
+ if (ret >= 0)
+ return ret;
wait_for_subcore_guest_exit();
diff --git a/arch/powerpc/kvm/book3s_hv_ras.c b/arch/powerpc/kvm/book3s_hv_ras.c
index c356f9a..c296343 100644
--- a/arch/powerpc/kvm/book3s_hv_ras.c
+++ b/arch/powerpc/kvm/book3s_hv_ras.c
@@ -268,17 +268,19 @@ static void kvmppc_tb_resync_done(void)
* secondary threads to proceed.
* - All secondary threads will eventually call opal hmi handler on
* their exit path.
+ *
+ * Returns 1 if the timebase offset should be applied, 0 if not.
*/
long kvmppc_realmode_hmi_handler(void)
{
- int ptid = local_paca->kvm_hstate.ptid;
bool resync_req;
- /* This is only called on primary thread. */
- BUG_ON(ptid != 0);
__this_cpu_inc(irq_stat.hmi_exceptions);
+ if (hmi_handle_debugtrig(NULL) >= 0)
+ return 1;
+
/*
* By now primary thread has already completed guest->host
* partition switch but haven't signaled secondaries yet.
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 30ece4c..7daf21b 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -1909,16 +1909,17 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
bne 27f
bl kvmppc_realmode_hmi_handler
nop
+ cmpdi r3, 0
li r12, BOOK3S_INTERRUPT_HMI
/*
- * At this point kvmppc_realmode_hmi_handler would have resync-ed
- * the TB. Hence it is not required to subtract guest timebase
- * offset from timebase. So, skip it.
+ * At this point kvmppc_realmode_hmi_handler may have resync-ed
+ * the TB, and if it has, we must not subtract the guest timebase
+ * offset from the timebase. So, skip it.
*
* Also, do not call kvmppc_subcore_exit_guest() because it has
* been invoked as part of kvmppc_realmode_hmi_handler().
*/
- b 30f
+ beq 30f
27:
/* Subtract timebase offset from timebase */
--
2.7.4
^ permalink raw reply related [flat|nested] 11+ messages in thread* Re: [4/6] KVM: PPC: Book3S HV: Improve handling of debug-trigger HMIs on POWER9
2018-01-17 9:51 ` [PATCH 4/6] KVM: PPC: Book3S HV: Improve handling of debug-trigger HMIs on POWER9 Paul Mackerras
@ 2018-01-22 3:34 ` Michael Ellerman
0 siblings, 0 replies; 11+ messages in thread
From: Michael Ellerman @ 2018-01-22 3:34 UTC (permalink / raw)
To: Paul Mackerras, kvm, linuxppc-dev; +Cc: kvm-ppc
On Wed, 2018-01-17 at 09:51:13 UTC, Paul Mackerras wrote:
> Hypervisor maintenance interrupts (HMIs) are generated by various
> causes, signalled by bits in the hypervisor maintenance exception
> register (HMER). In most cases calling OPAL to handle the interrupt
> is the correct thing to do, but the "debug trigger" HMIs signalled by
> PPC bit 17 (bit 46) of HMER are used to invoke software workarounds
> for hardware bugs, and OPAL does not have any code to handle this
> cause. The debug trigger HMI is used in POWER9 DD2.0 and DD2.1 chips
> to work around a hardware bug in executing vector load instructions to
> cache inhibited memory. In POWER9 DD2.2 chips, it is generated when
> conditions are detected relating to threads being in TM (transactional
> memory) suspended mode when the core SMT configuration needs to be
> reconfigured.
>
> The kernel currently has code to detect the vector CI load condition,
> but only when the HMI occurs in the host, not when it occurs in a
> guest. If a HMI occurs in the guest, it is always passed to OPAL, and
> then we always re-sync the timebase, because the HMI cause might have
> been a timebase error, for which OPAL would re-sync the timebase, thus
> removing the timebase offset which KVM applied for the guest. Since
> we don't know what OPAL did, we don't know whether to subtract the
> timebase offset from the timebase, so instead we re-sync the timebase.
>
> This adds code to determine explicitly what the cause of a debug
> trigger HMI will be. This is based on a new device-tree property
> under the CPU nodes called ibm,hmi-special-triggers, if it is
> present, or otherwise based on the PVR (processor version register).
> The handling of debug trigger HMIs is pulled out into a separate
> function which can be called from the KVM guest exit code. If this
> function handles and clears the HMI, and no other HMI causes remain,
> then we skip calling OPAL and we proceed to subtract the guest
> timebase offset from the timebase.
>
> The overall handling for HMIs that occur in the host (i.e. not in a
> KVM guest) is largely unchanged, except that we now don't set the flag
> for the vector CI load workaround on DD2.2 processors.
>
> This also removes a BUG_ON in the KVM code. BUG_ON is generally not
> useful in KVM guest entry/exit code since it is difficult to handle
> the resulting trap gracefully.
>
> Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
Applied to powerpc next, thanks.
https://git.kernel.org/powerpc/c/d075745d893c78730e4a3b7a60fca2
cheers
^ permalink raw reply [flat|nested] 11+ messages in thread
* [PATCH 5/6] powerpc: Add a CPU feature bit for TM bug workarounds on POWER9 v2.2
2018-01-17 9:51 [PATCH 0/6] KVM: PPC: Book3S HV: Changes for POWER9 v2.2 support Paul Mackerras
` (3 preceding siblings ...)
2018-01-17 9:51 ` [PATCH 4/6] KVM: PPC: Book3S HV: Improve handling of debug-trigger HMIs on POWER9 Paul Mackerras
@ 2018-01-17 9:51 ` Paul Mackerras
2018-01-17 9:51 ` [PATCH 6/6] KVM: PPC: Book3S HV: Work around transactional memory bugs in POWER9 Paul Mackerras
5 siblings, 0 replies; 11+ messages in thread
From: Paul Mackerras @ 2018-01-17 9:51 UTC (permalink / raw)
To: kvm, linuxppc-dev; +Cc: kvm-ppc
This adds a CPU feature bit which is set for POWER9 "Nimbus" DD2.2
processors which will be used to enable software emulation for some
transactional memory instructions, in order to work around hardware
bugs.
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
---
arch/powerpc/include/asm/cputable.h | 5 ++++-
arch/powerpc/kernel/cputable.c | 24 ++++++++++++++++++++++--
2 files changed, 26 insertions(+), 3 deletions(-)
diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h
index 0546663..ecef718 100644
--- a/arch/powerpc/include/asm/cputable.h
+++ b/arch/powerpc/include/asm/cputable.h
@@ -215,6 +215,7 @@ enum {
#define CPU_FTR_DAWR LONG_ASM_CONST(0x0400000000000000)
#define CPU_FTR_DABRX LONG_ASM_CONST(0x0800000000000000)
#define CPU_FTR_PMAO_BUG LONG_ASM_CONST(0x1000000000000000)
+#define CPU_FTR_P9_TM_EMUL LONG_ASM_CONST(0x2000000000000000)
#define CPU_FTR_POWER9_DD1 LONG_ASM_CONST(0x4000000000000000)
#define CPU_FTR_POWER9_DD2_1 LONG_ASM_CONST(0x8000000000000000)
@@ -481,6 +482,7 @@ enum {
(~CPU_FTR_SAO))
#define CPU_FTRS_POWER9_DD2_0 CPU_FTRS_POWER9
#define CPU_FTRS_POWER9_DD2_1 (CPU_FTRS_POWER9 | CPU_FTR_POWER9_DD2_1)
+#define CPU_FTRS_POWER9_DD2_2 (CPU_FTRS_POWER9 | CPU_FTR_P9_TM_EMUL)
#define CPU_FTRS_CELL (CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \
CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \
CPU_FTR_ALTIVEC_COMP | CPU_FTR_MMCRA | CPU_FTR_SMT | \
@@ -500,7 +502,8 @@ enum {
CPU_FTRS_POWER6 | CPU_FTRS_POWER7 | CPU_FTRS_POWER8E | \
CPU_FTRS_POWER8 | CPU_FTRS_POWER8_DD1 | CPU_FTRS_CELL | \
CPU_FTRS_PA6T | CPU_FTR_VSX | CPU_FTRS_POWER9 | \
- CPU_FTRS_POWER9_DD1 | CPU_FTRS_POWER9_DD2_1)
+ CPU_FTRS_POWER9_DD1 | CPU_FTRS_POWER9_DD2_1 | \
+ CPU_FTRS_POWER9_DD2_2)
#endif
#else
enum {
diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c
index 1350f49..307f019 100644
--- a/arch/powerpc/kernel/cputable.c
+++ b/arch/powerpc/kernel/cputable.c
@@ -567,11 +567,31 @@ static struct cpu_spec __initdata cpu_specs[] = {
.machine_check_early = __machine_check_early_realmode_p9,
.platform = "power9",
},
- { /* Power9 DD 2.1 or later (see DD2.0 above) */
+ { /* Power9 DD 2.1 */
+ .pvr_mask = 0xffffefff,
+ .pvr_value = 0x004e0201,
+ .cpu_name = "POWER9 (raw)",
+ .cpu_features = CPU_FTRS_POWER9_DD2_1,
+ .cpu_user_features = COMMON_USER_POWER9,
+ .cpu_user_features2 = COMMON_USER2_POWER9,
+ .mmu_features = MMU_FTRS_POWER9,
+ .icache_bsize = 128,
+ .dcache_bsize = 128,
+ .num_pmcs = 6,
+ .pmc_type = PPC_PMC_IBM,
+ .oprofile_cpu_type = "ppc64/power9",
+ .oprofile_type = PPC_OPROFILE_INVALID,
+ .cpu_setup = __setup_cpu_power9,
+ .cpu_restore = __restore_cpu_power9,
+ .flush_tlb = __flush_tlb_power9,
+ .machine_check_early = __machine_check_early_realmode_p9,
+ .platform = "power9",
+ },
+ { /* Power9 DD2.2 or later */
.pvr_mask = 0xffff0000,
.pvr_value = 0x004e0000,
.cpu_name = "POWER9 (raw)",
- .cpu_features = CPU_FTRS_POWER9_DD2_1,
+ .cpu_features = CPU_FTRS_POWER9_DD2_2,
.cpu_user_features = COMMON_USER_POWER9,
.cpu_user_features2 = COMMON_USER2_POWER9,
.mmu_features = MMU_FTRS_POWER9,
--
2.7.4
^ permalink raw reply related [flat|nested] 11+ messages in thread* [PATCH 6/6] KVM: PPC: Book3S HV: Work around transactional memory bugs in POWER9
2018-01-17 9:51 [PATCH 0/6] KVM: PPC: Book3S HV: Changes for POWER9 v2.2 support Paul Mackerras
` (4 preceding siblings ...)
2018-01-17 9:51 ` [PATCH 5/6] powerpc: Add a CPU feature bit for TM bug workarounds on POWER9 v2.2 Paul Mackerras
@ 2018-01-17 9:51 ` Paul Mackerras
5 siblings, 0 replies; 11+ messages in thread
From: Paul Mackerras @ 2018-01-17 9:51 UTC (permalink / raw)
To: kvm, linuxppc-dev; +Cc: kvm-ppc
POWER9 has hardware bugs relating to transactional memory and thread
reconfiguration (changes to hardware SMT mode). Specifically, the core
does not have enough storage to store a complete checkpoint of all the
architected state for all four threads. The DD2.2 version of POWER9
includes hardware modifications designed to allow hypervisor software
to implement workarounds for these problems. This patch implements
those workarounds in KVM code so that KVM guests see a full, working
transactional memory implementation.
The problems center around the use of TM suspended state, where the
CPU has a checkpointed state but execution is not transactional. The
workaround is to implement a "fake suspend" state, which looks to the
guest like suspended state but the CPU does not store a checkpoint.
In this state, any instruction that would cause a transition to
transactional state (rfid, rfebb, mtmsrd, tresume) or would use the
checkpointed state (treclaim) causes a "soft patch" interrupt (vector
0x1500) to the hypervisor so that it can be emulated. The trechkpt
instruction also causes a soft patch interrupt.
On POWER9 DD2.2, we avoid returning to the guest in any state which
would require a checkpoint to be present. The trechkpt in the guest
entry path which would normally create that checkpoint is replaced by
either a transition to fake suspend state, if the guest is in suspend
state, or a rollback to the pre-transactional state if the guest is in
transactional state. Fake suspend state is indicated by a flag in the
PACA plus a new bit in the PSSCR. The new PSSCR bit is write-only and
reads back as 0.
On exit from the guest, if the guest is in fake suspend state, we still
do the treclaim instruction as we would in real suspend state, in order
to get into non-transactional state, but we do not save the resulting
register state since there was no checkpoint.
Emulation of the instructions that cause a softpatch interrupt is
handled in two paths. If the guest is in real suspend mode, we call
kvmhv_p9_tm_emulation_early() to handle the cases where the guest is
transitioning to transactional state. This is called before we do the
treclaim in the guest exit path; because we haven't done treclaim, we
can get back to the guest with the transaction still active. If the
instruction is a case that kvmhv_p9_tm_emulation_early() doesn't
handle, or if the guest is in fake suspend state, then we proceed to
do the complete guest exit path and subsequently call
kvmhv_p9_tm_emulation() in host context with the MMU on. This handles
all the cases including the cases that generate program interrupts
(illegal instruction or TM Bad Thing) and facility unavailable
interrupts.
The emulation is reasonably straightforward and is mostly concerned
with checking for exception conditions and updating the state of
registers such as MSR and CR0. The treclaim emulation takes care to
ensure that the TEXASR register gets updated as if it were the guest
treclaim instruction that had done failure recording, not the treclaim
done in hypervisor state in the guest exit path.
With this, the KVM_CAP_PPC_HTM capability returns true (1) even if
transactional memory is not available to host userspace.
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
---
arch/powerpc/include/asm/kvm_asm.h | 2 +
arch/powerpc/include/asm/kvm_book3s.h | 4 +
arch/powerpc/include/asm/kvm_book3s_64.h | 43 ++++++
arch/powerpc/include/asm/kvm_book3s_asm.h | 1 +
arch/powerpc/include/asm/kvm_host.h | 1 +
arch/powerpc/include/asm/ppc-opcode.h | 4 +
arch/powerpc/include/asm/reg.h | 6 +
arch/powerpc/kernel/asm-offsets.c | 2 +
arch/powerpc/kernel/exceptions-64s.S | 4 +-
arch/powerpc/kvm/Makefile | 7 +
arch/powerpc/kvm/book3s_hv.c | 18 ++-
arch/powerpc/kvm/book3s_hv_rmhandlers.S | 131 +++++++++++++++++-
arch/powerpc/kvm/book3s_hv_tm.c | 216 ++++++++++++++++++++++++++++++
arch/powerpc/kvm/book3s_hv_tm_builtin.c | 109 +++++++++++++++
arch/powerpc/kvm/powerpc.c | 5 +-
15 files changed, 544 insertions(+), 9 deletions(-)
create mode 100644 arch/powerpc/kvm/book3s_hv_tm.c
create mode 100644 arch/powerpc/kvm/book3s_hv_tm_builtin.c
diff --git a/arch/powerpc/include/asm/kvm_asm.h b/arch/powerpc/include/asm/kvm_asm.h
index 09a802b..a790d5c 100644
--- a/arch/powerpc/include/asm/kvm_asm.h
+++ b/arch/powerpc/include/asm/kvm_asm.h
@@ -108,6 +108,8 @@
/* book3s_hv */
+#define BOOK3S_INTERRUPT_HV_SOFTPATCH 0x1500
+
/*
* Special trap used to indicate to host that this is a
* passthrough interrupt that could not be handled
diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h
index 9a66700..b3889a9 100644
--- a/arch/powerpc/include/asm/kvm_book3s.h
+++ b/arch/powerpc/include/asm/kvm_book3s.h
@@ -241,6 +241,10 @@ extern void kvmppc_update_lpcr(struct kvm *kvm, unsigned long lpcr,
unsigned long mask);
extern void kvmppc_set_fscr(struct kvm_vcpu *vcpu, u64 fscr);
+extern int kvmhv_p9_tm_emulation_early(struct kvm_vcpu *vcpu);
+extern int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu);
+extern void kvmhv_emulate_tm_rollback(struct kvm_vcpu *vcpu);
+
extern void kvmppc_entry_trampoline(void);
extern void kvmppc_hv_entry_trampoline(void);
extern u32 kvmppc_alignment_dsisr(struct kvm_vcpu *vcpu, unsigned int inst);
diff --git a/arch/powerpc/include/asm/kvm_book3s_64.h b/arch/powerpc/include/asm/kvm_book3s_64.h
index 998f7b7..c424e44 100644
--- a/arch/powerpc/include/asm/kvm_book3s_64.h
+++ b/arch/powerpc/include/asm/kvm_book3s_64.h
@@ -472,6 +472,49 @@ static inline void set_dirty_bits_atomic(unsigned long *map, unsigned long i,
set_bit_le(i, map);
}
+static inline u64 sanitize_msr(u64 msr)
+{
+ msr &= ~MSR_HV;
+ msr |= MSR_ME;
+ return msr;
+}
+
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+static inline void copy_from_checkpoint(struct kvm_vcpu *vcpu)
+{
+ vcpu->arch.cr = vcpu->arch.cr_tm;
+ vcpu->arch.xer = vcpu->arch.xer_tm;
+ vcpu->arch.lr = vcpu->arch.lr_tm;
+ vcpu->arch.ctr = vcpu->arch.ctr_tm;
+ vcpu->arch.amr = vcpu->arch.amr_tm;
+ vcpu->arch.ppr = vcpu->arch.ppr_tm;
+ vcpu->arch.dscr = vcpu->arch.dscr_tm;
+ vcpu->arch.tar = vcpu->arch.tar_tm;
+ memcpy(vcpu->arch.gpr, vcpu->arch.gpr_tm,
+ sizeof(vcpu->arch.gpr));
+ vcpu->arch.fp = vcpu->arch.fp_tm;
+ vcpu->arch.vr = vcpu->arch.vr_tm;
+ vcpu->arch.vrsave = vcpu->arch.vrsave_tm;
+}
+
+static inline void copy_to_checkpoint(struct kvm_vcpu *vcpu)
+{
+ vcpu->arch.cr_tm = vcpu->arch.cr;
+ vcpu->arch.xer_tm = vcpu->arch.xer;
+ vcpu->arch.lr_tm = vcpu->arch.lr;
+ vcpu->arch.ctr_tm = vcpu->arch.ctr;
+ vcpu->arch.amr_tm = vcpu->arch.amr;
+ vcpu->arch.ppr_tm = vcpu->arch.ppr;
+ vcpu->arch.dscr_tm = vcpu->arch.dscr;
+ vcpu->arch.tar_tm = vcpu->arch.tar;
+ memcpy(vcpu->arch.gpr_tm, vcpu->arch.gpr,
+ sizeof(vcpu->arch.gpr));
+ vcpu->arch.fp_tm = vcpu->arch.fp;
+ vcpu->arch.vr_tm = vcpu->arch.vr;
+ vcpu->arch.vrsave_tm = vcpu->arch.vrsave;
+}
+#endif /* CONFIG_PPC_TRANSACTIONAL_MEM */
+
#endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */
#endif /* __ASM_KVM_BOOK3S_64_H__ */
diff --git a/arch/powerpc/include/asm/kvm_book3s_asm.h b/arch/powerpc/include/asm/kvm_book3s_asm.h
index ab386af..d978fdf 100644
--- a/arch/powerpc/include/asm/kvm_book3s_asm.h
+++ b/arch/powerpc/include/asm/kvm_book3s_asm.h
@@ -119,6 +119,7 @@ struct kvmppc_host_state {
u8 host_ipi;
u8 ptid; /* thread number within subcore when split */
u8 tid; /* thread number within whole core */
+ u8 fake_suspend;
struct kvm_vcpu *kvm_vcpu;
struct kvmppc_vcore *kvm_vcore;
void __iomem *xics_phys;
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 3aa5b57..6e4cbc0 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -610,6 +610,7 @@ struct kvm_vcpu_arch {
u64 tfhar;
u64 texasr;
u64 tfiar;
+ u64 orig_texasr;
u32 cr_tm;
u64 xer_tm;
diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h
index ce0930d..15d4fde 100644
--- a/arch/powerpc/include/asm/ppc-opcode.h
+++ b/arch/powerpc/include/asm/ppc-opcode.h
@@ -226,6 +226,7 @@
#define PPC_INST_MSGSYNC 0x7c0006ec
#define PPC_INST_MSGSNDP 0x7c00011c
#define PPC_INST_MSGCLRP 0x7c00015c
+#define PPC_INST_MTMSRD 0x7c000164
#define PPC_INST_MTTMR 0x7c0003dc
#define PPC_INST_NOP 0x60000000
#define PPC_INST_PASTE 0x7c20070d
@@ -233,8 +234,10 @@
#define PPC_INST_POPCNTB_MASK 0xfc0007fe
#define PPC_INST_POPCNTD 0x7c0003f4
#define PPC_INST_POPCNTW 0x7c0002f4
+#define PPC_INST_RFEBB 0x4c000124
#define PPC_INST_RFCI 0x4c000066
#define PPC_INST_RFDI 0x4c00004e
+#define PPC_INST_RFID 0x4c000024
#define PPC_INST_RFMCI 0x4c00004c
#define PPC_INST_MFSPR_DSCR 0x7c1102a6
#define PPC_INST_MFSPR_DSCR_MASK 0xfc1ffffe
@@ -270,6 +273,7 @@
#define PPC_INST_TRECHKPT 0x7c0007dd
#define PPC_INST_TRECLAIM 0x7c00075d
#define PPC_INST_TABORT 0x7c00071d
+#define PPC_INST_TSR 0x7c0005dd
#define PPC_INST_NAP 0x4c000364
#define PPC_INST_SLEEP 0x4c0003a4
diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index 14e41b8..da76a45 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -156,6 +156,7 @@
#define PSSCR_SD 0x00400000 /* Status Disable */
#define PSSCR_PLS 0xf000000000000000 /* Power-saving Level Status */
#define PSSCR_GUEST_VIS 0xf0000000000003ff /* Guest-visible PSSCR fields */
+#define PSSCR_FAKE_SUSPEND 0x00000400 /* Fake-suspend bit (P9 DD2.2) */
/* Floating Point Status and Control Register (FPSCR) Fields */
#define FPSCR_FX 0x80000000 /* FPU exception summary */
@@ -237,7 +238,12 @@
#define SPRN_TFIAR 0x81 /* Transaction Failure Inst Addr */
#define SPRN_TEXASR 0x82 /* Transaction EXception & Summary */
#define SPRN_TEXASRU 0x83 /* '' '' '' Upper 32 */
+#define TEXASR_ABORT __MASK(63-31) /* terminated by tabort or treclaim */
+#define TEXASR_SUSP __MASK(63-32) /* tx failed in suspended state */
+#define TEXASR_HV __MASK(63-34) /* MSR[HV] when failure occurred */
+#define TEXASR_PR __MASK(63-35) /* MSR[PR] when failure occurred */
#define TEXASR_FS __MASK(63-36) /* TEXASR Failure Summary */
+#define TEXASR_EXACT __MASK(63-37) /* TFIAR value is exact */
#define SPRN_TFHAR 0x80 /* Transaction Failure Handler Addr */
#define SPRN_TIDR 144 /* Thread ID register */
#define SPRN_CTRLF 0x088
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 6b95841..10c5351 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -561,6 +561,7 @@ int main(void)
OFFSET(VCPU_TFHAR, kvm_vcpu, arch.tfhar);
OFFSET(VCPU_TFIAR, kvm_vcpu, arch.tfiar);
OFFSET(VCPU_TEXASR, kvm_vcpu, arch.texasr);
+ OFFSET(VCPU_ORIG_TEXASR, kvm_vcpu, arch.orig_texasr);
OFFSET(VCPU_GPR_TM, kvm_vcpu, arch.gpr_tm);
OFFSET(VCPU_FPRS_TM, kvm_vcpu, arch.fp_tm.fpr);
OFFSET(VCPU_VRS_TM, kvm_vcpu, arch.vr_tm.vr);
@@ -643,6 +644,7 @@ int main(void)
HSTATE_FIELD(HSTATE_HOST_IPI, host_ipi);
HSTATE_FIELD(HSTATE_PTID, ptid);
HSTATE_FIELD(HSTATE_TID, tid);
+ HSTATE_FIELD(HSTATE_FAKE_SUSPEND, fake_suspend);
HSTATE_FIELD(HSTATE_MMCR0, host_mmcr[0]);
HSTATE_FIELD(HSTATE_MMCR1, host_mmcr[1]);
HSTATE_FIELD(HSTATE_MMCRA, host_mmcr[2]);
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index e441b46..aefc945 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -1240,7 +1240,7 @@ EXC_REAL_BEGIN(denorm_exception_hv, 0x1500, 0x100)
bne+ denorm_assist
#endif
- KVMTEST_PR(0x1500)
+ KVMTEST_HV(0x1500)
EXCEPTION_PROLOG_PSERIES_1(denorm_common, EXC_HV)
EXC_REAL_END(denorm_exception_hv, 0x1500, 0x100)
@@ -1252,7 +1252,7 @@ EXC_VIRT_END(denorm_exception, 0x5500, 0x100)
EXC_VIRT_NONE(0x5500, 0x100)
#endif
-TRAMP_KVM_SKIP(PACA_EXGEN, 0x1500)
+TRAMP_KVM_HV(PACA_EXGEN, 0x1500)
#ifdef CONFIG_PPC_DENORMALISATION
TRAMP_REAL_BEGIN(denorm_assist)
diff --git a/arch/powerpc/kvm/Makefile b/arch/powerpc/kvm/Makefile
index 85ba80d..4b19da8 100644
--- a/arch/powerpc/kvm/Makefile
+++ b/arch/powerpc/kvm/Makefile
@@ -74,9 +74,15 @@ kvm-hv-y += \
book3s_64_mmu_hv.o \
book3s_64_mmu_radix.o
+kvm-hv-$(CONFIG_PPC_TRANSACTIONAL_MEM) += \
+ book3s_hv_tm.o
+
kvm-book3s_64-builtin-xics-objs-$(CONFIG_KVM_XICS) := \
book3s_hv_rm_xics.o book3s_hv_rm_xive.o
+kvm-book3s_64-builtin-tm-objs-$(CONFIG_PPC_TRANSACTIONAL_MEM) += \
+ book3s_hv_tm_builtin.o
+
ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
kvm-book3s_64-builtin-objs-$(CONFIG_KVM_BOOK3S_64_HANDLER) += \
book3s_hv_hmi.o \
@@ -84,6 +90,7 @@ kvm-book3s_64-builtin-objs-$(CONFIG_KVM_BOOK3S_64_HANDLER) += \
book3s_hv_rm_mmu.o \
book3s_hv_ras.o \
book3s_hv_builtin.o \
+ $(kvm-book3s_64-builtin-tm-objs-y) \
$(kvm-book3s_64-builtin-xics-objs-y)
endif
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 99ed374..3d4aca9 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -1201,6 +1201,19 @@ static int kvmppc_handle_exit_hv(struct kvm_run *run, struct kvm_vcpu *vcpu,
r = RESUME_GUEST;
}
break;
+
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+ case BOOK3S_INTERRUPT_HV_SOFTPATCH:
+ /*
+ * This occurs for various TM-related instructions that
+ * we need to emulate on POWER9 DD2.2. We have already
+ * handled the cases where the guest was in real-suspend
+ * mode and was transitioning to transactional state.
+ */
+ r = kvmhv_p9_tm_emulation(vcpu);
+ break;
+#endif
+
case BOOK3S_INTERRUPT_HV_RM_HARD:
r = RESUME_PASSTHROUGH;
break;
@@ -1973,7 +1986,9 @@ static struct kvm_vcpu *kvmppc_core_vcpu_create_hv(struct kvm *kvm,
* turn off the HFSCR bit, which causes those instructions to trap.
*/
vcpu->arch.hfscr = mfspr(SPRN_HFSCR);
- if (!cpu_has_feature(CPU_FTR_TM))
+ if (cpu_has_feature(CPU_FTR_P9_TM_EMUL))
+ vcpu->arch.hfscr |= HFSCR_TM;
+ else if (!cpu_has_feature(CPU_FTR_TM_COMP))
vcpu->arch.hfscr &= ~HFSCR_TM;
if (cpu_has_feature(CPU_FTR_ARCH_300))
vcpu->arch.hfscr &= ~HFSCR_MSGP;
@@ -2237,6 +2252,7 @@ static void kvmppc_start_thread(struct kvm_vcpu *vcpu, struct kvmppc_vcore *vc)
tpaca = &paca[cpu];
tpaca->kvm_hstate.kvm_vcpu = vcpu;
tpaca->kvm_hstate.ptid = cpu - vc->pcpu;
+ tpaca->kvm_hstate.fake_suspend = 0;
/* Order stores to hstate.kvm_vcpu etc. before store to kvm_vcore */
smp_wmb();
tpaca->kvm_hstate.kvm_vcore = vc;
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 7daf21b..3b3a01a 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -786,12 +786,15 @@ BEGIN_FTR_SECTION
END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+/* Branch around the call if both CPU_FTR_TM and CPU_FTR_P9_TM_EMUL are off */
BEGIN_FTR_SECTION
+ b 91f
+END_FTR_SECTION(CPU_FTR_TM | CPU_FTR_P9_TM_EMUL, 0)
/*
* NOTE THAT THIS TRASHES ALL NON-VOLATILE REGISTERS INCLUDING CR
*/
bl kvmppc_restore_tm
-END_FTR_SECTION_IFSET(CPU_FTR_TM)
+91:
#endif
/* Load guest PMU registers */
@@ -1325,6 +1328,12 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
std r3, VCPU_CTR(r9)
std r4, VCPU_XER(r9)
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+ /* For softpatch interrupt, go off and do TM instruction emulation */
+ cmpwi r12, BOOK3S_INTERRUPT_HV_SOFTPATCH
+ beq kvmppc_tm_emul
+#endif
+
/* If this is a page table miss then see if it's theirs or ours */
cmpwi r12, BOOK3S_INTERRUPT_H_DATA_STORAGE
beq kvmppc_hdsi
@@ -1684,12 +1693,15 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300)
bl kvmppc_save_fp
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+/* Branch around the call if both CPU_FTR_TM and CPU_FTR_P9_TM_EMUL are off */
BEGIN_FTR_SECTION
+ b 91f
+END_FTR_SECTION(CPU_FTR_TM | CPU_FTR_P9_TM_EMUL, 0)
/*
* NOTE THAT THIS TRASHES ALL NON-VOLATILE REGISTERS INCLUDING CR
*/
bl kvmppc_save_tm
-END_FTR_SECTION_IFSET(CPU_FTR_TM)
+91:
#endif
/* Increment yield count if they have a VPA */
@@ -2009,6 +2021,42 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_TYPE_RADIX)
mtlr r0
blr
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+/*
+ * Softpatch interrupt for transactional memory emulation cases
+ * on POWER9 DD2.2. This is early in the guest exit path - we
+ * haven't saved registers or done a treclaim yet.
+ */
+kvmppc_tm_emul:
+ /* Save instruction image in HEIR */
+ mfspr r3, SPRN_HEIR
+ stw r3, VCPU_HEIR(r9)
+
+ /*
+ * The cases we want to handle here are those where the guest
+ * is in real suspend mode and is trying to transition to
+ * transactional mode.
+ */
+ lbz r0, HSTATE_FAKE_SUSPEND(r13)
+ cmpwi r0, 0 /* keep exiting guest if in fake suspend */
+ bne guest_exit_cont
+ rldicl r3, r11, 64 - MSR_TS_S_LG, 62
+ cmpwi r3, 1 /* or if not in suspend state */
+ bne guest_exit_cont
+
+ /* Call C code to do the emulation */
+ mr r3, r9
+ bl kvmhv_p9_tm_emulation_early
+ nop
+ ld r9, HSTATE_KVM_VCPU(r13)
+ li r12, BOOK3S_INTERRUPT_HV_SOFTPATCH
+ cmpwi r3, 0
+ beq guest_exit_cont /* continue exiting if not handled */
+ ld r10, VCPU_PC(r9)
+ ld r11, VCPU_MSR(r9)
+ b fast_interrupt_c_return /* go back to guest if handled */
+#endif /* CONFIG_PPC_TRANSACTIONAL_MEM */
+
/*
* Check whether an HDSI is an HPTE not found fault or something else.
* If it is an HPTE not found fault that is due to the guest accessing
@@ -2542,13 +2590,16 @@ _GLOBAL(kvmppc_h_cede) /* r3 = vcpu pointer, r11 = msr, r13 = paca */
bl kvmppc_save_fp
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+/* Branch around the call if both CPU_FTR_TM and CPU_FTR_P9_TM_EMUL are off */
BEGIN_FTR_SECTION
+ b 91f
+END_FTR_SECTION(CPU_FTR_TM | CPU_FTR_P9_TM_EMUL, 0)
/*
* NOTE THAT THIS TRASHES ALL NON-VOLATILE REGISTERS INCLUDING CR
*/
ld r9, HSTATE_KVM_VCPU(r13)
bl kvmppc_save_tm
-END_FTR_SECTION_IFSET(CPU_FTR_TM)
+91:
#endif
/*
@@ -2655,12 +2706,15 @@ kvm_end_cede:
#endif
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+/* Branch around the call if both CPU_FTR_TM and CPU_FTR_P9_TM_EMUL are off */
BEGIN_FTR_SECTION
+ b 91f
+END_FTR_SECTION(CPU_FTR_TM | CPU_FTR_P9_TM_EMUL, 0)
/*
* NOTE THAT THIS TRASHES ALL NON-VOLATILE REGISTERS INCLUDING CR
*/
bl kvmppc_restore_tm
-END_FTR_SECTION_IFSET(CPU_FTR_TM)
+91:
#endif
/* load up FP state */
@@ -2976,6 +3030,15 @@ kvmppc_save_tm:
std r1, HSTATE_HOST_R1(r13)
li r3, TM_CAUSE_KVM_RESCHED
+BEGIN_FTR_SECTION
+ /* Emulation of the treclaim instruction needs TEXASR before treclaim */
+ mfspr r6, SPRN_TEXASR
+ std r6, VCPU_ORIG_TEXASR(r9)
+
+ rldicl. r8, r8, 64 - MSR_TS_S_LG, 62
+ beq 3f
+END_FTR_SECTION_IFSET(CPU_FTR_P9_TM_EMUL)
+
/* Clear the MSR RI since r1, r13 are all going to be foobar. */
li r5, 0
mtmsrd r5, 1
@@ -2987,6 +3050,38 @@ kvmppc_save_tm:
SET_SCRATCH0(r13)
GET_PACA(r13)
std r9, PACATMSCRATCH(r13)
+
+ /* If doing TM emulation on POWER9 DD2.2, check for fake suspend mode */
+BEGIN_FTR_SECTION
+3:
+ lbz r9, HSTATE_FAKE_SUSPEND(r13)
+ cmpwi r9, 0
+ beq 2f
+ /*
+ * We were in fake suspend, so we are not going to save the
+ * register state as the guest checkpointed state (since
+ * we already have it), therefore we can now use any volatile GPR.
+ */
+ /* Reload stack pointer and TOC. */
+ ld r1, HSTATE_HOST_R1(r13)
+ ld r2, PACATOC(r13)
+ li r5, MSR_RI
+ mtmsrd r5, 1
+ HMT_MEDIUM
+ ld r6, HSTATE_DSCR(r13)
+ mtspr SPRN_DSCR, r6
+ li r0, 0
+ stb r0, HSTATE_FAKE_SUSPEND(r13)
+ mfspr r3, SPRN_PSSCR
+ /* PSSCR_FAKE_SUSPEND is a write-only bit, but clear it anyway */
+ li r0, PSSCR_FAKE_SUSPEND
+ andc r3, r3, r0
+ mtspr SPRN_PSSCR, r3
+ ld r9, HSTATE_KVM_VCPU(r13)
+ b 1f
+2:
+END_FTR_SECTION_IFSET(CPU_FTR_P9_TM_EMUL)
+
ld r9, HSTATE_KVM_VCPU(r13)
/* Get a few more GPRs free. */
@@ -3112,6 +3207,15 @@ kvmppc_restore_tm:
mtspr SPRN_TEXASR, r7
/*
+ * If we are doing TM emulation for the guest on a POWER9 DD2,
+ * then we don't actually do a trechkpt -- we either set up
+ * fake-suspend mode, or emulate a TM rollback.
+ */
+BEGIN_FTR_SECTION
+ b .Ldo_tm_fake_load
+END_FTR_SECTION_IFSET(CPU_FTR_P9_TM_EMUL)
+
+ /*
* We need to load up the checkpointed state for the guest.
* We need to do this early as it will blow away any GPRs, VSRs and
* some SPRs.
@@ -3183,10 +3287,27 @@ kvmppc_restore_tm:
/* Set the MSR RI since we have our registers back. */
li r5, MSR_RI
mtmsrd r5, 1
-
+9:
ld r0, PPC_LR_STKOFF(r1)
mtlr r0
blr
+
+.Ldo_tm_fake_load:
+ cmpwi r5, 1 /* check for suspended state */
+ bgt 10f
+ stb r5, HSTATE_FAKE_SUSPEND(r13)
+ mfspr r6, SPRN_PSSCR
+ ori r6, r6, PSSCR_FAKE_SUSPEND
+ mtspr SPRN_PSSCR, r6 /* set it in HW too */
+ b 9b /* and return */
+10: stdu r1, -PPC_MIN_STKFRM(r1)
+ /* guest is in transactional state, so simulate rollback */
+ mr r3, r4
+ bl kvmhv_emulate_tm_rollback
+ nop
+ ld r4, HSTATE_KVM_VCPU(r13) /* our vcpu pointer has been trashed */
+ addi r1, r1, PPC_MIN_STKFRM
+ b 9b
#endif
/*
diff --git a/arch/powerpc/kvm/book3s_hv_tm.c b/arch/powerpc/kvm/book3s_hv_tm.c
new file mode 100644
index 0000000..bf710ad
--- /dev/null
+++ b/arch/powerpc/kvm/book3s_hv_tm.c
@@ -0,0 +1,216 @@
+/*
+ * Copyright 2017 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/kvm_host.h>
+
+#include <asm/kvm_ppc.h>
+#include <asm/kvm_book3s.h>
+#include <asm/kvm_book3s_64.h>
+#include <asm/reg.h>
+#include <asm/ppc-opcode.h>
+
+static void emulate_tx_failure(struct kvm_vcpu *vcpu, u64 failure_cause)
+{
+ u64 texasr, tfiar;
+ u64 msr = vcpu->arch.shregs.msr;
+
+ tfiar = vcpu->arch.pc & ~0x3ull;
+ texasr = (failure_cause << 56) | TEXASR_ABORT | TEXASR_FS | TEXASR_EXACT;
+ if (MSR_TM_SUSPENDED(vcpu->arch.shregs.msr))
+ texasr |= TEXASR_SUSP;
+ if (msr & MSR_PR) {
+ texasr |= TEXASR_PR;
+ tfiar |= 1;
+ }
+ vcpu->arch.tfiar = tfiar;
+ /* Preserve ROT and TL fields of existing TEXASR */
+ vcpu->arch.texasr = (vcpu->arch.texasr & 0x3ffffff) | texasr;
+}
+
+/*
+ * This gets called on a softpatch interrupt on POWER9 DD2.2 processors.
+ * We expect to find a TM-related instruction to be emulated. The
+ * instruction image is in vcpu->arch.emul_inst. If the guest was in
+ * TM suspended or transactional state, the checkpointed state has been
+ * reclaimed and is in the vcpu struct. The CPU is in virtual mode in
+ * host context.
+ */
+int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu)
+{
+ u32 instr = vcpu->arch.emul_inst;
+ u64 msr = vcpu->arch.shregs.msr;
+ u64 newmsr, bescr;
+ int ra, rs;
+
+ switch (instr & 0xfc0007ff) {
+ case PPC_INST_RFID:
+ /* XXX do we need to check for PR=0 here? */
+ newmsr = vcpu->arch.shregs.srr1;
+ /* should only get here for Sx -> T1 transition */
+ WARN_ON_ONCE(!(MSR_TM_SUSPENDED(msr) &&
+ MSR_TM_TRANSACTIONAL(newmsr) &&
+ (newmsr & MSR_TM)));
+ newmsr = sanitize_msr(newmsr);
+ vcpu->arch.shregs.msr = newmsr;
+ vcpu->arch.cfar = vcpu->arch.pc - 4;
+ vcpu->arch.pc = vcpu->arch.shregs.srr0;
+ return RESUME_GUEST;
+
+ case PPC_INST_RFEBB:
+ if ((msr & MSR_PR) && (vcpu->arch.vcore->pcr & PCR_ARCH_206)) {
+ /* generate an illegal instruction interrupt */
+ kvmppc_core_queue_program(vcpu, SRR1_PROGILL);
+ return RESUME_GUEST;
+ }
+ /* check EBB facility is available */
+ if (!(vcpu->arch.hfscr & HFSCR_EBB)) {
+ /* generate an illegal instruction interrupt */
+ kvmppc_core_queue_program(vcpu, SRR1_PROGILL);
+ return RESUME_GUEST;
+ }
+ if ((msr & MSR_PR) && !(vcpu->arch.fscr & FSCR_EBB)) {
+ /* generate a facility unavailable interrupt */
+ vcpu->arch.fscr = (vcpu->arch.fscr & ~(0xffull << 56)) |
+ ((u64)FSCR_EBB_LG << 56);
+ kvmppc_book3s_queue_irqprio(vcpu, BOOK3S_INTERRUPT_FAC_UNAVAIL);
+ return RESUME_GUEST;
+ }
+ bescr = vcpu->arch.bescr;
+ /* expect to see a S->T transition requested */
+ WARN_ON_ONCE(!(MSR_TM_SUSPENDED(msr) &&
+ ((bescr >> 30) & 3) == 2));
+ bescr &= ~BESCR_GE;
+ if (instr & (1 << 11))
+ bescr |= BESCR_GE;
+ vcpu->arch.bescr = bescr;
+ msr = (msr & ~MSR_TS_MASK) | MSR_TS_T;
+ vcpu->arch.shregs.msr = msr;
+ vcpu->arch.cfar = vcpu->arch.pc - 4;
+ vcpu->arch.pc = vcpu->arch.ebbrr;
+ return RESUME_GUEST;
+
+ case PPC_INST_MTMSRD:
+ /* XXX do we need to check for PR=0 here? */
+ rs = (instr >> 21) & 0x1f;
+ newmsr = kvmppc_get_gpr(vcpu, rs);
+ /* check this is a Sx -> T1 transition */
+ WARN_ON_ONCE(!(MSR_TM_SUSPENDED(msr) &&
+ MSR_TM_TRANSACTIONAL(newmsr) &&
+ (newmsr & MSR_TM)));
+ /* mtmsrd doesn't change LE */
+ newmsr = (newmsr & ~MSR_LE) | (msr & MSR_LE);
+ newmsr = sanitize_msr(newmsr);
+ vcpu->arch.shregs.msr = newmsr;
+ return RESUME_GUEST;
+
+ case PPC_INST_TSR:
+ /* check for PR=1 and arch 2.06 bit set in PCR */
+ if ((msr & MSR_PR) && (vcpu->arch.vcore->pcr & PCR_ARCH_206)) {
+ /* generate an illegal instruction interrupt */
+ kvmppc_core_queue_program(vcpu, SRR1_PROGILL);
+ return RESUME_GUEST;
+ }
+ /* check for TM disabled in the HFSCR or MSR */
+ if (!(vcpu->arch.hfscr & HFSCR_TM)) {
+ /* generate an illegal instruction interrupt */
+ kvmppc_core_queue_program(vcpu, SRR1_PROGILL);
+ return RESUME_GUEST;
+ }
+ if (!(msr & MSR_TM)) {
+ /* generate a facility unavailable interrupt */
+ vcpu->arch.fscr = (vcpu->arch.fscr & ~(0xffull << 56)) |
+ ((u64)FSCR_TM_LG << 56);
+ kvmppc_book3s_queue_irqprio(vcpu,
+ BOOK3S_INTERRUPT_FAC_UNAVAIL);
+ return RESUME_GUEST;
+ }
+ /* Set CR0 to indicate previous transactional state */
+ vcpu->arch.cr = (vcpu->arch.cr & 0x0fffffff) |
+ (((msr & MSR_TS_MASK) >> MSR_TS_S_LG) << 28);
+ /* L=1 => tresume, L=0 => tsuspend */
+ if (instr & (1 << 21)) {
+ if (MSR_TM_SUSPENDED(msr))
+ msr = (msr & ~MSR_TS_MASK) | MSR_TS_T;
+ } else {
+ if (MSR_TM_TRANSACTIONAL(msr))
+ msr = (msr & ~MSR_TS_MASK) | MSR_TS_S;
+ }
+ vcpu->arch.shregs.msr = msr;
+ return RESUME_GUEST;
+
+ case PPC_INST_TRECLAIM:
+ /* check for TM disabled in the HFSCR or MSR */
+ if (!(vcpu->arch.hfscr & HFSCR_TM)) {
+ /* generate an illegal instruction interrupt */
+ kvmppc_core_queue_program(vcpu, SRR1_PROGILL);
+ return RESUME_GUEST;
+ }
+ if (!(msr & MSR_TM)) {
+ /* generate a facility unavailable interrupt */
+ vcpu->arch.fscr = (vcpu->arch.fscr & ~(0xffull << 56)) |
+ ((u64)FSCR_TM_LG << 56);
+ kvmppc_book3s_queue_irqprio(vcpu,
+ BOOK3S_INTERRUPT_FAC_UNAVAIL);
+ return RESUME_GUEST;
+ }
+ /* If no transaction active, generate TM bad thing */
+ if (!MSR_TM_ACTIVE(msr)) {
+ kvmppc_core_queue_program(vcpu, SRR1_PROGTM);
+ return RESUME_GUEST;
+ }
+ /* If failure was not previously recorded, recompute TEXASR */
+ if (!(vcpu->arch.orig_texasr & TEXASR_FS)) {
+ ra = (instr >> 16) & 0x1f;
+ if (ra)
+ ra = kvmppc_get_gpr(vcpu, ra) & 0xff;
+ emulate_tx_failure(vcpu, ra);
+ }
+
+ copy_from_checkpoint(vcpu);
+
+ /* Set CR0 to indicate previous transactional state */
+ vcpu->arch.cr = (vcpu->arch.cr & 0x0fffffff) |
+ (((msr & MSR_TS_MASK) >> MSR_TS_S_LG) << 28);
+ vcpu->arch.shregs.msr &= ~MSR_TS_MASK;
+ return RESUME_GUEST;
+
+ case PPC_INST_TRECHKPT:
+ /* XXX do we need to check for PR=0 here? */
+ /* check for TM disabled in the HFSCR or MSR */
+ if (!(vcpu->arch.hfscr & HFSCR_TM)) {
+ /* generate an illegal instruction interrupt */
+ kvmppc_core_queue_program(vcpu, SRR1_PROGILL);
+ return RESUME_GUEST;
+ }
+ if (!(msr & MSR_TM)) {
+ /* generate a facility unavailable interrupt */
+ vcpu->arch.fscr = (vcpu->arch.fscr & ~(0xffull << 56)) |
+ ((u64)FSCR_TM_LG << 56);
+ kvmppc_book3s_queue_irqprio(vcpu,
+ BOOK3S_INTERRUPT_FAC_UNAVAIL);
+ return RESUME_GUEST;
+ }
+ /* If transaction active or TEXASR[FS] = 0, bad thing */
+ if (MSR_TM_ACTIVE(msr) || !(vcpu->arch.texasr & TEXASR_FS)) {
+ kvmppc_core_queue_program(vcpu, SRR1_PROGTM);
+ return RESUME_GUEST;
+ }
+
+ copy_to_checkpoint(vcpu);
+
+ /* Set CR0 to indicate previous transactional state */
+ vcpu->arch.cr = (vcpu->arch.cr & 0x0fffffff) |
+ (((msr & MSR_TS_MASK) >> MSR_TS_S_LG) << 28);
+ vcpu->arch.shregs.msr = msr | MSR_TS_S;
+ return RESUME_GUEST;
+ }
+
+ /* What should we do here? We didn't recognize the instruction */
+ WARN_ON_ONCE(1);
+ return RESUME_GUEST;
+}
diff --git a/arch/powerpc/kvm/book3s_hv_tm_builtin.c b/arch/powerpc/kvm/book3s_hv_tm_builtin.c
new file mode 100644
index 0000000..d98ccfd
--- /dev/null
+++ b/arch/powerpc/kvm/book3s_hv_tm_builtin.c
@@ -0,0 +1,109 @@
+/*
+ * Copyright 2017 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/kvm_host.h>
+
+#include <asm/kvm_ppc.h>
+#include <asm/kvm_book3s.h>
+#include <asm/kvm_book3s_64.h>
+#include <asm/reg.h>
+#include <asm/ppc-opcode.h>
+
+/*
+ * This handles the cases where the guest is in real suspend mode
+ * and we want to get back to the guest without dooming the transaction.
+ * The caller has checked that the guest is in real-suspend mode
+ * (MSR[TS] = S and the fake-suspend flag is not set).
+ */
+int kvmhv_p9_tm_emulation_early(struct kvm_vcpu *vcpu)
+{
+ u32 instr = vcpu->arch.emul_inst;
+ u64 newmsr, msr, bescr;
+ int rs;
+
+ switch (instr & 0xfc0007ff) {
+ case PPC_INST_RFID:
+ /* XXX do we need to check for PR=0 here? */
+ newmsr = vcpu->arch.shregs.srr1;
+ /* should only get here for Sx -> T1 transition */
+ if (!(MSR_TM_TRANSACTIONAL(newmsr) && (newmsr & MSR_TM)))
+ return 0;
+ newmsr = sanitize_msr(newmsr);
+ vcpu->arch.shregs.msr = newmsr;
+ vcpu->arch.cfar = vcpu->arch.pc - 4;
+ vcpu->arch.pc = vcpu->arch.shregs.srr0;
+ return 1;
+
+ case PPC_INST_RFEBB:
+ /* check for PR=1 and arch 2.06 bit set in PCR */
+ msr = vcpu->arch.shregs.msr;
+ if ((msr & MSR_PR) && (vcpu->arch.vcore->pcr & PCR_ARCH_206))
+ return 0;
+ /* check EBB facility is available */
+ if (!(vcpu->arch.hfscr & HFSCR_EBB) ||
+ ((msr & MSR_PR) && !(mfspr(SPRN_FSCR) & FSCR_EBB)))
+ return 0;
+ bescr = mfspr(SPRN_BESCR);
+ /* expect to see a S->T transition requested */
+ if (((bescr >> 30) & 3) != 2)
+ return 0;
+ bescr &= ~BESCR_GE;
+ if (instr & (1 << 11))
+ bescr |= BESCR_GE;
+ mtspr(SPRN_BESCR, bescr);
+ msr = (msr & ~MSR_TS_MASK) | MSR_TS_T;
+ vcpu->arch.shregs.msr = msr;
+ vcpu->arch.cfar = vcpu->arch.pc - 4;
+ vcpu->arch.pc = mfspr(SPRN_EBBRR);
+ return 1;
+
+ case PPC_INST_MTMSRD:
+ /* XXX do we need to check for PR=0 here? */
+ rs = (instr >> 21) & 0x1f;
+ newmsr = kvmppc_get_gpr(vcpu, rs);
+ msr = vcpu->arch.shregs.msr;
+ /* check this is a Sx -> T1 transition */
+ if (!(MSR_TM_TRANSACTIONAL(newmsr) && (newmsr & MSR_TM)))
+ return 0;
+ /* mtmsrd doesn't change LE */
+ newmsr = (newmsr & ~MSR_LE) | (msr & MSR_LE);
+ newmsr = sanitize_msr(newmsr);
+ vcpu->arch.shregs.msr = newmsr;
+ return 1;
+
+ case PPC_INST_TSR:
+ /* we know the MSR has the TS field = S (0b01) here */
+ msr = vcpu->arch.shregs.msr;
+ /* check for PR=1 and arch 2.06 bit set in PCR */
+ if ((msr & MSR_PR) && (vcpu->arch.vcore->pcr & PCR_ARCH_206))
+ return 0;
+ /* check for TM disabled in the HFSCR or MSR */
+ if (!(vcpu->arch.hfscr & HFSCR_TM) || !(msr & MSR_TM))
+ return 0;
+ /* L=1 => tresume => set TS to T (0b10) */
+ if (instr & (1 << 21))
+ vcpu->arch.shregs.msr = (msr & ~MSR_TS_MASK) | MSR_TS_T;
+ /* Set CR0 to 0b0010 */
+ vcpu->arch.cr = (vcpu->arch.cr & 0x0fffffff) | 0x20000000;
+ return 1;
+ }
+
+ return 0;
+}
+
+/*
+ * This is called when we are returning to a guest in TM transactional
+ * state. We roll the guest state back to the checkpointed state.
+ */
+void kvmhv_emulate_tm_rollback(struct kvm_vcpu *vcpu)
+{
+ vcpu->arch.shregs.msr &= ~MSR_TS_MASK; /* go to N state */
+ vcpu->arch.pc = vcpu->arch.tfhar;
+ copy_from_checkpoint(vcpu);
+ vcpu->arch.cr = (vcpu->arch.cr & 0x0fffffff) | 0xa0000000;
+}
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 7c9e45f..b1985a5 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -642,10 +642,13 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
r = hv_enabled;
break;
#endif
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
case KVM_CAP_PPC_HTM:
r = hv_enabled &&
- (cur_cpu_spec->cpu_user_features2 & PPC_FEATURE2_HTM_COMP);
+ (!!(cur_cpu_spec->cpu_user_features2 & PPC_FEATURE2_HTM) ||
+ cpu_has_feature(CPU_FTR_P9_TM_EMUL));
break;
+#endif
default:
r = 0;
break;
--
2.7.4
^ permalink raw reply related [flat|nested] 11+ messages in thread