* [PATCH v2 25/60] KVM: PPC: Book3S HV: CTRL SPR does not require read-modify-write
From: Nicholas Piggin @ 2021-08-11 16:00 UTC (permalink / raw)
To: kvm-ppc; +Cc: linuxppc-dev, Nicholas Piggin
In-Reply-To: <20210811160134.904987-1-npiggin@gmail.com>
Processors that support KVM HV do not require read-modify-write of
the CTRL SPR to set/clear their thread's runlatch. Just write 1 or 0
to it.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/kvm/book3s_hv.c | 2 +-
arch/powerpc/kvm/book3s_hv_rmhandlers.S | 15 ++++++---------
2 files changed, 7 insertions(+), 10 deletions(-)
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index fa12a3efeeb2..f9942eeaefd3 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -4060,7 +4060,7 @@ static void load_spr_state(struct kvm_vcpu *vcpu)
*/
if (!(vcpu->arch.ctrl & 1))
- mtspr(SPRN_CTRLT, mfspr(SPRN_CTRLF) & ~1);
+ mtspr(SPRN_CTRLT, 0);
}
static void store_spr_state(struct kvm_vcpu *vcpu)
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 551ce223b40c..05be8648937d 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -775,12 +775,11 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
mtspr SPRN_AMR,r5
mtspr SPRN_UAMOR,r6
- /* Restore state of CTRL run bit; assume 1 on entry */
+ /* Restore state of CTRL run bit; the host currently has it set to 1 */
lwz r5,VCPU_CTRL(r4)
andi. r5,r5,1
bne 4f
- mfspr r6,SPRN_CTRLF
- clrrdi r6,r6,1
+ li r6,0
mtspr SPRN_CTRLT,r6
4:
/* Secondary threads wait for primary to have done partition switch */
@@ -1203,12 +1202,12 @@ guest_bypass:
stw r0, VCPU_CPU(r9)
stw r0, VCPU_THREAD_CPU(r9)
- /* Save guest CTRL register, set runlatch to 1 */
+ /* Save guest CTRL register, set runlatch to 1 if it was clear */
mfspr r6,SPRN_CTRLF
stw r6,VCPU_CTRL(r9)
andi. r0,r6,1
bne 4f
- ori r6,r6,1
+ li r6,1
mtspr SPRN_CTRLT,r6
4:
/*
@@ -2178,8 +2177,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_TM)
* Also clear the runlatch bit before napping.
*/
kvm_do_nap:
- mfspr r0, SPRN_CTRLF
- clrrdi r0, r0, 1
+ li r0,0
mtspr SPRN_CTRLT, r0
li r0,1
@@ -2198,8 +2196,7 @@ kvm_nap_sequence: /* desired LPCR value in r5 */
bl isa206_idle_insn_mayloss
- mfspr r0, SPRN_CTRLF
- ori r0, r0, 1
+ li r0,1
mtspr SPRN_CTRLT, r0
mtspr SPRN_SRR1, r3
--
2.23.0
^ permalink raw reply related
* [PATCH v2 24/60] KVM: PPC: Book3S HV P9: Factor out yield_count increment
From: Nicholas Piggin @ 2021-08-11 16:00 UTC (permalink / raw)
To: kvm-ppc; +Cc: linuxppc-dev, Nicholas Piggin, Fabiano Rosas
In-Reply-To: <20210811160134.904987-1-npiggin@gmail.com>
Factor duplicated code into a helper function.
Reviewed-by: Fabiano Rosas <farosas@linux.ibm.com>
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/kvm/book3s_hv.c | 24 ++++++++++++------------
1 file changed, 12 insertions(+), 12 deletions(-)
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 9ff7e3ea70f9..fa12a3efeeb2 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -4117,6 +4117,16 @@ static inline bool hcall_is_xics(unsigned long req)
req == H_IPOLL || req == H_XIRR || req == H_XIRR_X;
}
+static void vcpu_vpa_increment_dispatch(struct kvm_vcpu *vcpu)
+{
+ struct lppaca *lp = vcpu->arch.vpa.pinned_addr;
+ if (lp) {
+ u32 yield_count = be32_to_cpu(lp->yield_count) + 1;
+ lp->yield_count = cpu_to_be32(yield_count);
+ vcpu->arch.vpa.dirty = 1;
+ }
+}
+
/*
* Guest entry for POWER9 and later CPUs.
*/
@@ -4145,12 +4155,7 @@ static int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit,
vc->entry_exit_map = 1;
vc->in_guest = 1;
- if (vcpu->arch.vpa.pinned_addr) {
- struct lppaca *lp = vcpu->arch.vpa.pinned_addr;
- u32 yield_count = be32_to_cpu(lp->yield_count) + 1;
- lp->yield_count = cpu_to_be32(yield_count);
- vcpu->arch.vpa.dirty = 1;
- }
+ vcpu_vpa_increment_dispatch(vcpu);
if (cpu_has_feature(CPU_FTR_TM) ||
cpu_has_feature(CPU_FTR_P9_TM_HV_ASSIST))
@@ -4278,12 +4283,7 @@ static int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit,
cpu_has_feature(CPU_FTR_P9_TM_HV_ASSIST))
kvmppc_save_tm_hv(vcpu, vcpu->arch.shregs.msr, true);
- if (vcpu->arch.vpa.pinned_addr) {
- struct lppaca *lp = vcpu->arch.vpa.pinned_addr;
- u32 yield_count = be32_to_cpu(lp->yield_count) + 1;
- lp->yield_count = cpu_to_be32(yield_count);
- vcpu->arch.vpa.dirty = 1;
- }
+ vcpu_vpa_increment_dispatch(vcpu);
switch_pmu_to_host(vcpu, &host_os_sprs);
--
2.23.0
^ permalink raw reply related
* [PATCH v2 23/60] KVM: PPC: Book3S HV P9: Demand fault PMU SPRs when marked not inuse
From: Nicholas Piggin @ 2021-08-11 16:00 UTC (permalink / raw)
To: kvm-ppc; +Cc: Athira Jajeev, linuxppc-dev, Nicholas Piggin
In-Reply-To: <20210811160134.904987-1-npiggin@gmail.com>
The pmcregs_in_use field in the guest VPA can not be trusted to reflect
what the guest is doing with PMU SPRs, so the PMU must always be managed
(stopped) when exiting the guest, and SPR values set when entering the
guest to ensure it can't cause a covert channel or otherwise cause other
guests or the host to misbehave.
So prevent guest access to the PMU with HFSCR[PM] if pmcregs_in_use is
clear, and avoid the PMU SPR access on every partition switch. Guests
that set pmcregs_in_use incorrectly or when first setting it and using
the PMU will take a hypervisor facility unavailable interrupt that will
bring in the PMU SPRs.
Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com>
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/kvm/book3s_hv.c | 131 ++++++++++++++++++++++++++---------
1 file changed, 98 insertions(+), 33 deletions(-)
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 0ceb0bd28e13..9ff7e3ea70f9 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -1421,6 +1421,23 @@ static int kvmppc_emulate_doorbell_instr(struct kvm_vcpu *vcpu)
return RESUME_GUEST;
}
+/*
+ * If the lppaca had pmcregs_in_use clear when we exited the guest, then
+ * HFSCR_PM is cleared for next entry. If the guest then tries to access
+ * the PMU SPRs, we get this facility unavailable interrupt. Putting HFSCR_PM
+ * back in the guest HFSCR will cause the next entry to load the PMU SPRs and
+ * allow the guest access to continue.
+ */
+static int kvmppc_pmu_unavailable(struct kvm_vcpu *vcpu)
+{
+ if (!(vcpu->arch.hfscr_permitted & HFSCR_PM))
+ return EMULATE_FAIL;
+
+ vcpu->arch.hfscr |= HFSCR_PM;
+
+ return RESUME_GUEST;
+}
+
static int kvmppc_handle_exit_hv(struct kvm_vcpu *vcpu,
struct task_struct *tsk)
{
@@ -1705,16 +1722,22 @@ XXX benchmark guest exits
* to emulate.
* Otherwise, we just generate a program interrupt to the guest.
*/
- case BOOK3S_INTERRUPT_H_FAC_UNAVAIL:
+ case BOOK3S_INTERRUPT_H_FAC_UNAVAIL: {
+ u64 cause = vcpu->arch.hfscr >> 56;
+
r = EMULATE_FAIL;
- if (((vcpu->arch.hfscr >> 56) == FSCR_MSGP_LG) &&
- cpu_has_feature(CPU_FTR_ARCH_300))
- r = kvmppc_emulate_doorbell_instr(vcpu);
+ if (cpu_has_feature(CPU_FTR_ARCH_300)) {
+ if (cause == FSCR_MSGP_LG)
+ r = kvmppc_emulate_doorbell_instr(vcpu);
+ if (cause == FSCR_PM_LG)
+ r = kvmppc_pmu_unavailable(vcpu);
+ }
if (r == EMULATE_FAIL) {
kvmppc_core_queue_program(vcpu, SRR1_PROGILL);
r = RESUME_GUEST;
}
break;
+ }
case BOOK3S_INTERRUPT_HV_RM_HARD:
r = RESUME_PASSTHROUGH;
@@ -2753,6 +2776,11 @@ static int kvmppc_core_vcpu_create_hv(struct kvm_vcpu *vcpu)
vcpu->arch.hfscr_permitted = vcpu->arch.hfscr;
+ /*
+ * PM is demand-faulted so start with it clear.
+ */
+ vcpu->arch.hfscr &= ~HFSCR_PM;
+
kvmppc_mmu_book3s_hv_init(vcpu);
vcpu->arch.state = KVMPPC_VCPU_NOTREADY;
@@ -3823,6 +3851,14 @@ static void freeze_pmu(unsigned long mmcr0, unsigned long mmcra)
static void switch_pmu_to_guest(struct kvm_vcpu *vcpu,
struct p9_host_os_sprs *host_os_sprs)
{
+ struct lppaca *lp;
+ int load_pmu = 1;
+
+ lp = vcpu->arch.vpa.pinned_addr;
+ if (lp)
+ load_pmu = lp->pmcregs_in_use;
+
+ /* Save host */
if (ppc_get_pmu_inuse()) {
/*
* It might be better to put PMU handling (at least for the
@@ -3857,41 +3893,47 @@ static void switch_pmu_to_guest(struct kvm_vcpu *vcpu,
}
#ifdef CONFIG_PPC_PSERIES
+ /* After saving PMU, before loading guest PMU, flip pmcregs_in_use */
if (kvmhv_on_pseries()) {
barrier();
- if (vcpu->arch.vpa.pinned_addr) {
- struct lppaca *lp = vcpu->arch.vpa.pinned_addr;
- get_lppaca()->pmcregs_in_use = lp->pmcregs_in_use;
- } else {
- get_lppaca()->pmcregs_in_use = 1;
- }
+ get_lppaca()->pmcregs_in_use = load_pmu;
barrier();
}
#endif
- /* load guest */
- mtspr(SPRN_PMC1, vcpu->arch.pmc[0]);
- mtspr(SPRN_PMC2, vcpu->arch.pmc[1]);
- mtspr(SPRN_PMC3, vcpu->arch.pmc[2]);
- mtspr(SPRN_PMC4, vcpu->arch.pmc[3]);
- mtspr(SPRN_PMC5, vcpu->arch.pmc[4]);
- mtspr(SPRN_PMC6, vcpu->arch.pmc[5]);
- mtspr(SPRN_MMCR1, vcpu->arch.mmcr[1]);
- mtspr(SPRN_MMCR2, vcpu->arch.mmcr[2]);
- mtspr(SPRN_SDAR, vcpu->arch.sdar);
- mtspr(SPRN_SIAR, vcpu->arch.siar);
- mtspr(SPRN_SIER, vcpu->arch.sier[0]);
+ /*
+ * Load guest. If the VPA said the PMCs are not in use but the guest
+ * tried to access them anyway, HFSCR[PM] will be set by the HFAC
+ * fault so we can make forward progress.
+ */
+ if (load_pmu || (vcpu->arch.hfscr & HFSCR_PM)) {
+ mtspr(SPRN_PMC1, vcpu->arch.pmc[0]);
+ mtspr(SPRN_PMC2, vcpu->arch.pmc[1]);
+ mtspr(SPRN_PMC3, vcpu->arch.pmc[2]);
+ mtspr(SPRN_PMC4, vcpu->arch.pmc[3]);
+ mtspr(SPRN_PMC5, vcpu->arch.pmc[4]);
+ mtspr(SPRN_PMC6, vcpu->arch.pmc[5]);
+ mtspr(SPRN_MMCR1, vcpu->arch.mmcr[1]);
+ mtspr(SPRN_MMCR2, vcpu->arch.mmcr[2]);
+ mtspr(SPRN_SDAR, vcpu->arch.sdar);
+ mtspr(SPRN_SIAR, vcpu->arch.siar);
+ mtspr(SPRN_SIER, vcpu->arch.sier[0]);
+
+ if (cpu_has_feature(CPU_FTR_ARCH_31)) {
+ mtspr(SPRN_MMCR3, vcpu->arch.mmcr[3]);
+ mtspr(SPRN_SIER2, vcpu->arch.sier[1]);
+ mtspr(SPRN_SIER3, vcpu->arch.sier[2]);
+ }
- if (cpu_has_feature(CPU_FTR_ARCH_31)) {
- mtspr(SPRN_MMCR3, vcpu->arch.mmcr[3]);
- mtspr(SPRN_SIER2, vcpu->arch.sier[1]);
- mtspr(SPRN_SIER3, vcpu->arch.sier[2]);
- }
+ /* Set MMCRA then MMCR0 last */
+ mtspr(SPRN_MMCRA, vcpu->arch.mmcra);
+ mtspr(SPRN_MMCR0, vcpu->arch.mmcr[0]);
+ /* No isync necessary because we're starting counters */
- /* Set MMCRA then MMCR0 last */
- mtspr(SPRN_MMCRA, vcpu->arch.mmcra);
- mtspr(SPRN_MMCR0, vcpu->arch.mmcr[0]);
- /* No isync necessary because we're starting counters */
+ if (!vcpu->arch.nested &&
+ (vcpu->arch.hfscr_permitted & HFSCR_PM))
+ vcpu->arch.hfscr |= HFSCR_PM;
+ }
}
static void switch_pmu_to_host(struct kvm_vcpu *vcpu,
@@ -3935,9 +3977,32 @@ static void switch_pmu_to_host(struct kvm_vcpu *vcpu,
vcpu->arch.sier[1] = mfspr(SPRN_SIER2);
vcpu->arch.sier[2] = mfspr(SPRN_SIER3);
}
- } else {
+
+ } else if (vcpu->arch.hfscr & HFSCR_PM) {
+ /*
+ * The guest accessed PMC SPRs without specifying they should
+ * be preserved, or it cleared pmcregs_in_use after the last
+ * access. Just ensure they are frozen.
+ */
freeze_pmu(mfspr(SPRN_MMCR0), mfspr(SPRN_MMCRA));
- }
+
+ /*
+ * Demand-fault PMU register access in the guest.
+ *
+ * This is used to grab the guest's VPA pmcregs_in_use value
+ * and reflect it into the host's VPA in the case of a nested
+ * hypervisor.
+ *
+ * It also avoids having to zero-out SPRs after each guest
+ * exit to avoid side-channels when.
+ *
+ * This is cleared here when we exit the guest, so later HFSCR
+ * interrupt handling can add it back to run the guest with
+ * PM enabled next time.
+ */
+ if (!vcpu->arch.nested)
+ vcpu->arch.hfscr &= ~HFSCR_PM;
+ } /* otherwise the PMU should still be frozen */
#ifdef CONFIG_PPC_PSERIES
if (kvmhv_on_pseries()) {
--
2.23.0
^ permalink raw reply related
* [PATCH v2 22/60] KVM: PPC: Book3S HV P9: Factor PMU save/load into context switch functions
From: Nicholas Piggin @ 2021-08-11 16:00 UTC (permalink / raw)
To: kvm-ppc; +Cc: Athira Jajeev, linuxppc-dev, Nicholas Piggin
In-Reply-To: <20210811160134.904987-1-npiggin@gmail.com>
Rather than guest/host save/retsore functions, implement context switch
functions that take care of details like the VPA update for nested.
The reason to split these kind of helpers into explicit save/load
functions is mainly to schedule SPR access nicely, but PMU is a special
case where the load requires mtSPR (to stop counters) and other
difficulties, so there's less possibility to schedule those nicely. The
SPR accesses also have side-effects if the PMU is running, and in later
changes we keep the host PMU running as long as possible so this code
can be better profiled, which also complicates scheduling.
Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com>
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/kvm/book3s_hv.c | 61 +++++++++++++++++-------------------
1 file changed, 28 insertions(+), 33 deletions(-)
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index c3fe05fe3c11..0ceb0bd28e13 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -3820,7 +3820,8 @@ static void freeze_pmu(unsigned long mmcr0, unsigned long mmcra)
isync();
}
-static void save_p9_host_pmu(struct p9_host_os_sprs *host_os_sprs)
+static void switch_pmu_to_guest(struct kvm_vcpu *vcpu,
+ struct p9_host_os_sprs *host_os_sprs)
{
if (ppc_get_pmu_inuse()) {
/*
@@ -3854,10 +3855,21 @@ static void save_p9_host_pmu(struct p9_host_os_sprs *host_os_sprs)
host_os_sprs->sier3 = mfspr(SPRN_SIER3);
}
}
-}
-static void load_p9_guest_pmu(struct kvm_vcpu *vcpu)
-{
+#ifdef CONFIG_PPC_PSERIES
+ if (kvmhv_on_pseries()) {
+ barrier();
+ if (vcpu->arch.vpa.pinned_addr) {
+ struct lppaca *lp = vcpu->arch.vpa.pinned_addr;
+ get_lppaca()->pmcregs_in_use = lp->pmcregs_in_use;
+ } else {
+ get_lppaca()->pmcregs_in_use = 1;
+ }
+ barrier();
+ }
+#endif
+
+ /* load guest */
mtspr(SPRN_PMC1, vcpu->arch.pmc[0]);
mtspr(SPRN_PMC2, vcpu->arch.pmc[1]);
mtspr(SPRN_PMC3, vcpu->arch.pmc[2]);
@@ -3882,7 +3894,8 @@ static void load_p9_guest_pmu(struct kvm_vcpu *vcpu)
/* No isync necessary because we're starting counters */
}
-static void save_p9_guest_pmu(struct kvm_vcpu *vcpu)
+static void switch_pmu_to_host(struct kvm_vcpu *vcpu,
+ struct p9_host_os_sprs *host_os_sprs)
{
struct lppaca *lp;
int save_pmu = 1;
@@ -3925,10 +3938,15 @@ static void save_p9_guest_pmu(struct kvm_vcpu *vcpu)
} else {
freeze_pmu(mfspr(SPRN_MMCR0), mfspr(SPRN_MMCRA));
}
-}
-static void load_p9_host_pmu(struct p9_host_os_sprs *host_os_sprs)
-{
+#ifdef CONFIG_PPC_PSERIES
+ if (kvmhv_on_pseries()) {
+ barrier();
+ get_lppaca()->pmcregs_in_use = ppc_get_pmu_inuse();
+ barrier();
+ }
+#endif
+
if (ppc_get_pmu_inuse()) {
mtspr(SPRN_PMC1, host_os_sprs->pmc1);
mtspr(SPRN_PMC2, host_os_sprs->pmc2);
@@ -4057,8 +4075,6 @@ static int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit,
save_p9_host_os_sprs(&host_os_sprs);
- save_p9_host_pmu(&host_os_sprs);
-
kvmppc_subcore_enter_guest();
vc->entry_exit_map = 1;
@@ -4075,19 +4091,7 @@ static int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit,
cpu_has_feature(CPU_FTR_P9_TM_HV_ASSIST))
kvmppc_restore_tm_hv(vcpu, vcpu->arch.shregs.msr, true);
-#ifdef CONFIG_PPC_PSERIES
- if (kvmhv_on_pseries()) {
- barrier();
- if (vcpu->arch.vpa.pinned_addr) {
- struct lppaca *lp = vcpu->arch.vpa.pinned_addr;
- get_lppaca()->pmcregs_in_use = lp->pmcregs_in_use;
- } else {
- get_lppaca()->pmcregs_in_use = 1;
- }
- barrier();
- }
-#endif
- load_p9_guest_pmu(vcpu);
+ switch_pmu_to_guest(vcpu, &host_os_sprs);
msr_check_and_set(MSR_FP | MSR_VEC | MSR_VSX);
load_fp_state(&vcpu->arch.fp);
@@ -4216,14 +4220,7 @@ static int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit,
vcpu->arch.vpa.dirty = 1;
}
- save_p9_guest_pmu(vcpu);
-#ifdef CONFIG_PPC_PSERIES
- if (kvmhv_on_pseries()) {
- barrier();
- get_lppaca()->pmcregs_in_use = ppc_get_pmu_inuse();
- barrier();
- }
-#endif
+ switch_pmu_to_host(vcpu, &host_os_sprs);
vc->entry_exit_map = 0x101;
vc->in_guest = 0;
@@ -4232,8 +4229,6 @@ static int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit,
mtspr(SPRN_SPRG_VDSO_WRITE, local_paca->sprg_vdso);
- load_p9_host_pmu(&host_os_sprs);
-
kvmppc_subcore_exit_guest();
return trap;
--
2.23.0
^ permalink raw reply related
* [PATCH v2 21/60] KVM: PPC: Book3S HV P9: Implement PMU save/restore in C
From: Nicholas Piggin @ 2021-08-11 16:00 UTC (permalink / raw)
To: kvm-ppc; +Cc: Athira Jajeev, linuxppc-dev, Nicholas Piggin, Madhavan Srinivasan
In-Reply-To: <20210811160134.904987-1-npiggin@gmail.com>
Implement the P9 path PMU save/restore code in C, and remove the
POWER9/10 code from the P7/8 path assembly.
Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com>
Cc: Madhavan Srinivasan <maddy@linux.vnet.ibm.com>
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/include/asm/asm-prototypes.h | 5 -
arch/powerpc/kvm/book3s_hv.c | 221 +++++++++++++++++++---
arch/powerpc/kvm/book3s_hv_interrupts.S | 13 +-
arch/powerpc/kvm/book3s_hv_rmhandlers.S | 43 +----
4 files changed, 208 insertions(+), 74 deletions(-)
diff --git a/arch/powerpc/include/asm/asm-prototypes.h b/arch/powerpc/include/asm/asm-prototypes.h
index 222823861a67..41b8a1e1144a 100644
--- a/arch/powerpc/include/asm/asm-prototypes.h
+++ b/arch/powerpc/include/asm/asm-prototypes.h
@@ -141,11 +141,6 @@ static inline void kvmppc_restore_tm_hv(struct kvm_vcpu *vcpu, u64 msr,
bool preserve_nv) { }
#endif /* CONFIG_PPC_TRANSACTIONAL_MEM */
-void kvmhv_save_host_pmu(void);
-void kvmhv_load_host_pmu(void);
-void kvmhv_save_guest_pmu(struct kvm_vcpu *vcpu, bool pmu_in_use);
-void kvmhv_load_guest_pmu(struct kvm_vcpu *vcpu);
-
void kvmppc_p9_enter_guest(struct kvm_vcpu *vcpu);
long kvmppc_h_set_dabr(struct kvm_vcpu *vcpu, unsigned long dabr);
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index e6cb923f91ff..c3fe05fe3c11 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -3765,6 +3765,196 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
trace_kvmppc_run_core(vc, 1);
}
+/*
+ * Privileged (non-hypervisor) host registers to save.
+ */
+struct p9_host_os_sprs {
+ unsigned long dscr;
+ unsigned long tidr;
+ unsigned long iamr;
+ unsigned long amr;
+ unsigned long fscr;
+
+ unsigned int pmc1;
+ unsigned int pmc2;
+ unsigned int pmc3;
+ unsigned int pmc4;
+ unsigned int pmc5;
+ unsigned int pmc6;
+ unsigned long mmcr0;
+ unsigned long mmcr1;
+ unsigned long mmcr2;
+ unsigned long mmcr3;
+ unsigned long mmcra;
+ unsigned long siar;
+ unsigned long sier1;
+ unsigned long sier2;
+ unsigned long sier3;
+ unsigned long sdar;
+};
+
+static void freeze_pmu(unsigned long mmcr0, unsigned long mmcra)
+{
+ if (!(mmcr0 & MMCR0_FC))
+ goto do_freeze;
+ if (mmcra & MMCRA_SAMPLE_ENABLE)
+ goto do_freeze;
+ if (cpu_has_feature(CPU_FTR_ARCH_31)) {
+ if (!(mmcr0 & MMCR0_PMCCEXT))
+ goto do_freeze;
+ if (!(mmcra & MMCRA_BHRB_DISABLE))
+ goto do_freeze;
+ }
+ return;
+
+do_freeze:
+ mmcr0 = MMCR0_FC;
+ mmcra = 0;
+ if (cpu_has_feature(CPU_FTR_ARCH_31)) {
+ mmcr0 |= MMCR0_PMCCEXT;
+ mmcra = MMCRA_BHRB_DISABLE;
+ }
+
+ mtspr(SPRN_MMCR0, mmcr0);
+ mtspr(SPRN_MMCRA, mmcra);
+ isync();
+}
+
+static void save_p9_host_pmu(struct p9_host_os_sprs *host_os_sprs)
+{
+ if (ppc_get_pmu_inuse()) {
+ /*
+ * It might be better to put PMU handling (at least for the
+ * host) in the perf subsystem because it knows more about what
+ * is being used.
+ */
+
+ /* POWER9, POWER10 do not implement HPMC or SPMC */
+
+ host_os_sprs->mmcr0 = mfspr(SPRN_MMCR0);
+ host_os_sprs->mmcra = mfspr(SPRN_MMCRA);
+
+ freeze_pmu(host_os_sprs->mmcr0, host_os_sprs->mmcra);
+
+ host_os_sprs->pmc1 = mfspr(SPRN_PMC1);
+ host_os_sprs->pmc2 = mfspr(SPRN_PMC2);
+ host_os_sprs->pmc3 = mfspr(SPRN_PMC3);
+ host_os_sprs->pmc4 = mfspr(SPRN_PMC4);
+ host_os_sprs->pmc5 = mfspr(SPRN_PMC5);
+ host_os_sprs->pmc6 = mfspr(SPRN_PMC6);
+ host_os_sprs->mmcr1 = mfspr(SPRN_MMCR1);
+ host_os_sprs->mmcr2 = mfspr(SPRN_MMCR2);
+ host_os_sprs->sdar = mfspr(SPRN_SDAR);
+ host_os_sprs->siar = mfspr(SPRN_SIAR);
+ host_os_sprs->sier1 = mfspr(SPRN_SIER);
+
+ if (cpu_has_feature(CPU_FTR_ARCH_31)) {
+ host_os_sprs->mmcr3 = mfspr(SPRN_MMCR3);
+ host_os_sprs->sier2 = mfspr(SPRN_SIER2);
+ host_os_sprs->sier3 = mfspr(SPRN_SIER3);
+ }
+ }
+}
+
+static void load_p9_guest_pmu(struct kvm_vcpu *vcpu)
+{
+ mtspr(SPRN_PMC1, vcpu->arch.pmc[0]);
+ mtspr(SPRN_PMC2, vcpu->arch.pmc[1]);
+ mtspr(SPRN_PMC3, vcpu->arch.pmc[2]);
+ mtspr(SPRN_PMC4, vcpu->arch.pmc[3]);
+ mtspr(SPRN_PMC5, vcpu->arch.pmc[4]);
+ mtspr(SPRN_PMC6, vcpu->arch.pmc[5]);
+ mtspr(SPRN_MMCR1, vcpu->arch.mmcr[1]);
+ mtspr(SPRN_MMCR2, vcpu->arch.mmcr[2]);
+ mtspr(SPRN_SDAR, vcpu->arch.sdar);
+ mtspr(SPRN_SIAR, vcpu->arch.siar);
+ mtspr(SPRN_SIER, vcpu->arch.sier[0]);
+
+ if (cpu_has_feature(CPU_FTR_ARCH_31)) {
+ mtspr(SPRN_MMCR3, vcpu->arch.mmcr[3]);
+ mtspr(SPRN_SIER2, vcpu->arch.sier[1]);
+ mtspr(SPRN_SIER3, vcpu->arch.sier[2]);
+ }
+
+ /* Set MMCRA then MMCR0 last */
+ mtspr(SPRN_MMCRA, vcpu->arch.mmcra);
+ mtspr(SPRN_MMCR0, vcpu->arch.mmcr[0]);
+ /* No isync necessary because we're starting counters */
+}
+
+static void save_p9_guest_pmu(struct kvm_vcpu *vcpu)
+{
+ struct lppaca *lp;
+ int save_pmu = 1;
+
+ lp = vcpu->arch.vpa.pinned_addr;
+ if (lp)
+ save_pmu = lp->pmcregs_in_use;
+ if (IS_ENABLED(CONFIG_KVM_BOOK3S_HV_NESTED_PMU_WORKAROUND)) {
+ /*
+ * Save pmu if this guest is capable of running nested guests.
+ * This is option is for old L1s that do not set their
+ * lppaca->pmcregs_in_use properly when entering their L2.
+ */
+ save_pmu |= nesting_enabled(vcpu->kvm);
+ }
+
+ if (save_pmu) {
+ vcpu->arch.mmcr[0] = mfspr(SPRN_MMCR0);
+ vcpu->arch.mmcra = mfspr(SPRN_MMCRA);
+
+ freeze_pmu(vcpu->arch.mmcr[0], vcpu->arch.mmcra);
+
+ vcpu->arch.pmc[0] = mfspr(SPRN_PMC1);
+ vcpu->arch.pmc[1] = mfspr(SPRN_PMC2);
+ vcpu->arch.pmc[2] = mfspr(SPRN_PMC3);
+ vcpu->arch.pmc[3] = mfspr(SPRN_PMC4);
+ vcpu->arch.pmc[4] = mfspr(SPRN_PMC5);
+ vcpu->arch.pmc[5] = mfspr(SPRN_PMC6);
+ vcpu->arch.mmcr[1] = mfspr(SPRN_MMCR1);
+ vcpu->arch.mmcr[2] = mfspr(SPRN_MMCR2);
+ vcpu->arch.sdar = mfspr(SPRN_SDAR);
+ vcpu->arch.siar = mfspr(SPRN_SIAR);
+ vcpu->arch.sier[0] = mfspr(SPRN_SIER);
+
+ if (cpu_has_feature(CPU_FTR_ARCH_31)) {
+ vcpu->arch.mmcr[3] = mfspr(SPRN_MMCR3);
+ vcpu->arch.sier[1] = mfspr(SPRN_SIER2);
+ vcpu->arch.sier[2] = mfspr(SPRN_SIER3);
+ }
+ } else {
+ freeze_pmu(mfspr(SPRN_MMCR0), mfspr(SPRN_MMCRA));
+ }
+}
+
+static void load_p9_host_pmu(struct p9_host_os_sprs *host_os_sprs)
+{
+ if (ppc_get_pmu_inuse()) {
+ mtspr(SPRN_PMC1, host_os_sprs->pmc1);
+ mtspr(SPRN_PMC2, host_os_sprs->pmc2);
+ mtspr(SPRN_PMC3, host_os_sprs->pmc3);
+ mtspr(SPRN_PMC4, host_os_sprs->pmc4);
+ mtspr(SPRN_PMC5, host_os_sprs->pmc5);
+ mtspr(SPRN_PMC6, host_os_sprs->pmc6);
+ mtspr(SPRN_MMCR1, host_os_sprs->mmcr1);
+ mtspr(SPRN_MMCR2, host_os_sprs->mmcr2);
+ mtspr(SPRN_SDAR, host_os_sprs->sdar);
+ mtspr(SPRN_SIAR, host_os_sprs->siar);
+ mtspr(SPRN_SIER, host_os_sprs->sier1);
+
+ if (cpu_has_feature(CPU_FTR_ARCH_31)) {
+ mtspr(SPRN_MMCR3, host_os_sprs->mmcr3);
+ mtspr(SPRN_SIER2, host_os_sprs->sier2);
+ mtspr(SPRN_SIER3, host_os_sprs->sier3);
+ }
+
+ /* Set MMCRA then MMCR0 last */
+ mtspr(SPRN_MMCRA, host_os_sprs->mmcra);
+ mtspr(SPRN_MMCR0, host_os_sprs->mmcr0);
+ isync();
+ }
+}
+
static void load_spr_state(struct kvm_vcpu *vcpu)
{
mtspr(SPRN_DSCR, vcpu->arch.dscr);
@@ -3807,17 +3997,6 @@ static void store_spr_state(struct kvm_vcpu *vcpu)
vcpu->arch.dscr = mfspr(SPRN_DSCR);
}
-/*
- * Privileged (non-hypervisor) host registers to save.
- */
-struct p9_host_os_sprs {
- unsigned long dscr;
- unsigned long tidr;
- unsigned long iamr;
- unsigned long amr;
- unsigned long fscr;
-};
-
static void save_p9_host_os_sprs(struct p9_host_os_sprs *host_os_sprs)
{
host_os_sprs->dscr = mfspr(SPRN_DSCR);
@@ -3865,7 +4044,7 @@ static int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit,
struct p9_host_os_sprs host_os_sprs;
s64 dec;
u64 tb, next_timer;
- int trap, save_pmu;
+ int trap;
WARN_ON_ONCE(vcpu->arch.ceded);
@@ -3878,7 +4057,7 @@ static int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit,
save_p9_host_os_sprs(&host_os_sprs);
- kvmhv_save_host_pmu(); /* saves it to PACA kvm_hstate */
+ save_p9_host_pmu(&host_os_sprs);
kvmppc_subcore_enter_guest();
@@ -3908,7 +4087,7 @@ static int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit,
barrier();
}
#endif
- kvmhv_load_guest_pmu(vcpu);
+ load_p9_guest_pmu(vcpu);
msr_check_and_set(MSR_FP | MSR_VEC | MSR_VSX);
load_fp_state(&vcpu->arch.fp);
@@ -4030,24 +4209,14 @@ static int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit,
cpu_has_feature(CPU_FTR_P9_TM_HV_ASSIST))
kvmppc_save_tm_hv(vcpu, vcpu->arch.shregs.msr, true);
- save_pmu = 1;
if (vcpu->arch.vpa.pinned_addr) {
struct lppaca *lp = vcpu->arch.vpa.pinned_addr;
u32 yield_count = be32_to_cpu(lp->yield_count) + 1;
lp->yield_count = cpu_to_be32(yield_count);
vcpu->arch.vpa.dirty = 1;
- save_pmu = lp->pmcregs_in_use;
- }
- if (IS_ENABLED(CONFIG_KVM_BOOK3S_HV_NESTED_PMU_WORKAROUND)) {
- /*
- * Save pmu if this guest is capable of running nested guests.
- * This is option is for old L1s that do not set their
- * lppaca->pmcregs_in_use properly when entering their L2.
- */
- save_pmu |= nesting_enabled(vcpu->kvm);
}
- kvmhv_save_guest_pmu(vcpu, save_pmu);
+ save_p9_guest_pmu(vcpu);
#ifdef CONFIG_PPC_PSERIES
if (kvmhv_on_pseries()) {
barrier();
@@ -4063,7 +4232,7 @@ static int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit,
mtspr(SPRN_SPRG_VDSO_WRITE, local_paca->sprg_vdso);
- kvmhv_load_host_pmu();
+ load_p9_host_pmu(&host_os_sprs);
kvmppc_subcore_exit_guest();
diff --git a/arch/powerpc/kvm/book3s_hv_interrupts.S b/arch/powerpc/kvm/book3s_hv_interrupts.S
index 4444f83cb133..59d89e4b154a 100644
--- a/arch/powerpc/kvm/book3s_hv_interrupts.S
+++ b/arch/powerpc/kvm/book3s_hv_interrupts.S
@@ -104,7 +104,10 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
mtlr r0
blr
-_GLOBAL(kvmhv_save_host_pmu)
+/*
+ * void kvmhv_save_host_pmu(void)
+ */
+kvmhv_save_host_pmu:
BEGIN_FTR_SECTION
/* Work around P8 PMAE bug */
li r3, -1
@@ -138,14 +141,6 @@ BEGIN_FTR_SECTION
std r8, HSTATE_MMCR2(r13)
std r9, HSTATE_SIER(r13)
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
-BEGIN_FTR_SECTION
- mfspr r5, SPRN_MMCR3
- mfspr r6, SPRN_SIER2
- mfspr r7, SPRN_SIER3
- std r5, HSTATE_MMCR3(r13)
- std r6, HSTATE_SIER2(r13)
- std r7, HSTATE_SIER3(r13)
-END_FTR_SECTION_IFSET(CPU_FTR_ARCH_31)
mfspr r3, SPRN_PMC1
mfspr r5, SPRN_PMC2
mfspr r6, SPRN_PMC3
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 9021052f1579..551ce223b40c 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -2738,10 +2738,11 @@ kvmppc_msr_interrupt:
blr
/*
+ * void kvmhv_load_guest_pmu(struct kvm_vcpu *vcpu)
+ *
* Load up guest PMU state. R3 points to the vcpu struct.
*/
-_GLOBAL(kvmhv_load_guest_pmu)
-EXPORT_SYMBOL_GPL(kvmhv_load_guest_pmu)
+kvmhv_load_guest_pmu:
mr r4, r3
mflr r0
li r3, 1
@@ -2775,27 +2776,17 @@ END_FTR_SECTION_IFSET(CPU_FTR_PMAO_BUG)
mtspr SPRN_MMCRA, r6
mtspr SPRN_SIAR, r7
mtspr SPRN_SDAR, r8
-BEGIN_FTR_SECTION
- ld r5, VCPU_MMCR + 24(r4)
- ld r6, VCPU_SIER + 8(r4)
- ld r7, VCPU_SIER + 16(r4)
- mtspr SPRN_MMCR3, r5
- mtspr SPRN_SIER2, r6
- mtspr SPRN_SIER3, r7
-END_FTR_SECTION_IFSET(CPU_FTR_ARCH_31)
BEGIN_FTR_SECTION
ld r5, VCPU_MMCR + 16(r4)
ld r6, VCPU_SIER(r4)
mtspr SPRN_MMCR2, r5
mtspr SPRN_SIER, r6
-BEGIN_FTR_SECTION_NESTED(96)
lwz r7, VCPU_PMC + 24(r4)
lwz r8, VCPU_PMC + 28(r4)
ld r9, VCPU_MMCRS(r4)
mtspr SPRN_SPMC1, r7
mtspr SPRN_SPMC2, r8
mtspr SPRN_MMCRS, r9
-END_FTR_SECTION_NESTED(CPU_FTR_ARCH_300, 0, 96)
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
mtspr SPRN_MMCR0, r3
isync
@@ -2803,10 +2794,11 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
blr
/*
+ * void kvmhv_load_host_pmu(void)
+ *
* Reload host PMU state saved in the PACA by kvmhv_save_host_pmu.
*/
-_GLOBAL(kvmhv_load_host_pmu)
-EXPORT_SYMBOL_GPL(kvmhv_load_host_pmu)
+kvmhv_load_host_pmu:
mflr r0
lbz r4, PACA_PMCINUSE(r13) /* is the host using the PMU? */
cmpwi r4, 0
@@ -2844,25 +2836,18 @@ BEGIN_FTR_SECTION
mtspr SPRN_MMCR2, r8
mtspr SPRN_SIER, r9
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
-BEGIN_FTR_SECTION
- ld r5, HSTATE_MMCR3(r13)
- ld r6, HSTATE_SIER2(r13)
- ld r7, HSTATE_SIER3(r13)
- mtspr SPRN_MMCR3, r5
- mtspr SPRN_SIER2, r6
- mtspr SPRN_SIER3, r7
-END_FTR_SECTION_IFSET(CPU_FTR_ARCH_31)
mtspr SPRN_MMCR0, r3
isync
mtlr r0
23: blr
/*
+ * void kvmhv_save_guest_pmu(struct kvm_vcpu *vcpu, bool pmu_in_use)
+ *
* Save guest PMU state into the vcpu struct.
* r3 = vcpu, r4 = full save flag (PMU in use flag set in VPA)
*/
-_GLOBAL(kvmhv_save_guest_pmu)
-EXPORT_SYMBOL_GPL(kvmhv_save_guest_pmu)
+kvmhv_save_guest_pmu:
mr r9, r3
mr r8, r4
BEGIN_FTR_SECTION
@@ -2911,14 +2896,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
BEGIN_FTR_SECTION
std r10, VCPU_MMCR + 16(r9)
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
-BEGIN_FTR_SECTION
- mfspr r5, SPRN_MMCR3
- mfspr r6, SPRN_SIER2
- mfspr r7, SPRN_SIER3
- std r5, VCPU_MMCR + 24(r9)
- std r6, VCPU_SIER + 8(r9)
- std r7, VCPU_SIER + 16(r9)
-END_FTR_SECTION_IFSET(CPU_FTR_ARCH_31)
std r7, VCPU_SIAR(r9)
std r8, VCPU_SDAR(r9)
mfspr r3, SPRN_PMC1
@@ -2936,7 +2913,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_31)
BEGIN_FTR_SECTION
mfspr r5, SPRN_SIER
std r5, VCPU_SIER(r9)
-BEGIN_FTR_SECTION_NESTED(96)
mfspr r6, SPRN_SPMC1
mfspr r7, SPRN_SPMC2
mfspr r8, SPRN_MMCRS
@@ -2945,7 +2921,6 @@ BEGIN_FTR_SECTION_NESTED(96)
std r8, VCPU_MMCRS(r9)
lis r4, 0x8000
mtspr SPRN_MMCRS, r4
-END_FTR_SECTION_NESTED(CPU_FTR_ARCH_300, 0, 96)
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
22: blr
--
2.23.0
^ permalink raw reply related
* [PATCH v2 20/60] powerpc/64s: Implement PMU override command line option
From: Nicholas Piggin @ 2021-08-11 16:00 UTC (permalink / raw)
To: kvm-ppc; +Cc: Athira Jajeev, linuxppc-dev, Nicholas Piggin, Madhavan Srinivasan
In-Reply-To: <20210811160134.904987-1-npiggin@gmail.com>
It can be useful in simulators (with very constrained environments)
to allow some PMCs to run from boot so they can be sampled directly
by a test harness, rather than having to run perf.
A previous change freezes counters at boot by default, so provide
a boot time option to un-freeze (plus a bit more flexibility).
Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com>
Cc: Madhavan Srinivasan <maddy@linux.vnet.ibm.com>
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
.../admin-guide/kernel-parameters.txt | 8 +++++
arch/powerpc/perf/core-book3s.c | 35 +++++++++++++++++++
2 files changed, 43 insertions(+)
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index bdb22006f713..f8ef1fc2ee9e 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -4089,6 +4089,14 @@
Override pmtimer IOPort with a hex value.
e.g. pmtmr=0x508
+ pmu_override= [PPC] Override the PMU.
+ This option takes over the PMU facility, so it is no
+ longer usable by perf. Setting this option starts the
+ PMU counters by setting MMCR0 to 0 (the FC bit is
+ cleared). If a number is given, then MMCR1 is set to
+ that number, otherwise (e.g., 'pmu_override=on'), MMCR1
+ remains 0.
+
pm_debug_messages [SUSPEND,KNL]
Enable suspend/resume debug messages during boot up.
diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index 65795cadb475..45d894d85966 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -2428,8 +2428,24 @@ int register_power_pmu(struct power_pmu *pmu)
}
#ifdef CONFIG_PPC64
+static bool pmu_override = false;
+static unsigned long pmu_override_val;
+static void do_pmu_override(void *data)
+{
+ ppc_set_pmu_inuse(1);
+ if (pmu_override_val)
+ mtspr(SPRN_MMCR1, pmu_override_val);
+ mtspr(SPRN_MMCR0, mfspr(SPRN_MMCR0) & ~MMCR0_FC);
+}
+
static int __init init_ppc64_pmu(void)
{
+ if (cpu_has_feature(CPU_FTR_HVMODE) && pmu_override) {
+ printk(KERN_WARNING "perf: disabling perf due to pmu_override= command line option.\n");
+ on_each_cpu(do_pmu_override, NULL, 1);
+ return 0;
+ }
+
/* run through all the pmu drivers one at a time */
if (!init_power5_pmu())
return 0;
@@ -2451,4 +2467,23 @@ static int __init init_ppc64_pmu(void)
return init_generic_compat_pmu();
}
early_initcall(init_ppc64_pmu);
+
+static int __init pmu_setup(char *str)
+{
+ unsigned long val;
+
+ if (!early_cpu_has_feature(CPU_FTR_HVMODE))
+ return 0;
+
+ pmu_override = true;
+
+ if (kstrtoul(str, 0, &val))
+ val = 0;
+
+ pmu_override_val = val;
+
+ return 1;
+}
+__setup("pmu_override=", pmu_setup);
+
#endif
--
2.23.0
^ permalink raw reply related
* [PATCH v2 19/60] powerpc/64s: Always set PMU control registers to frozen/disabled when not in use
From: Nicholas Piggin @ 2021-08-11 16:00 UTC (permalink / raw)
To: kvm-ppc; +Cc: Athira Jajeev, linuxppc-dev, Nicholas Piggin, Madhavan Srinivasan
In-Reply-To: <20210811160134.904987-1-npiggin@gmail.com>
KVM PMU management code looks for particular frozen/disabled bits in
the PMU registers so it knows whether it must clear them when coming
out of a guest or not. Setting this up helps KVM make these optimisations
without getting confused. Longer term the better approach might be to
move guest/host PMU switching to the perf subsystem.
Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com>
Cc: Madhavan Srinivasan <maddy@linux.vnet.ibm.com>
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/kernel/cpu_setup_power.c | 4 ++--
arch/powerpc/kernel/dt_cpu_ftrs.c | 6 +++---
arch/powerpc/kvm/book3s_hv.c | 5 +++++
3 files changed, 10 insertions(+), 5 deletions(-)
diff --git a/arch/powerpc/kernel/cpu_setup_power.c b/arch/powerpc/kernel/cpu_setup_power.c
index a29dc8326622..3dc61e203f37 100644
--- a/arch/powerpc/kernel/cpu_setup_power.c
+++ b/arch/powerpc/kernel/cpu_setup_power.c
@@ -109,7 +109,7 @@ static void init_PMU_HV_ISA207(void)
static void init_PMU(void)
{
mtspr(SPRN_MMCRA, 0);
- mtspr(SPRN_MMCR0, 0);
+ mtspr(SPRN_MMCR0, MMCR0_FC);
mtspr(SPRN_MMCR1, 0);
mtspr(SPRN_MMCR2, 0);
}
@@ -123,7 +123,7 @@ static void init_PMU_ISA31(void)
{
mtspr(SPRN_MMCR3, 0);
mtspr(SPRN_MMCRA, MMCRA_BHRB_DISABLE);
- mtspr(SPRN_MMCR0, MMCR0_PMCCEXT);
+ mtspr(SPRN_MMCR0, MMCR0_FC | MMCR0_PMCCEXT);
}
/*
diff --git a/arch/powerpc/kernel/dt_cpu_ftrs.c b/arch/powerpc/kernel/dt_cpu_ftrs.c
index 38ea20fadc4a..a6bb0ee179cd 100644
--- a/arch/powerpc/kernel/dt_cpu_ftrs.c
+++ b/arch/powerpc/kernel/dt_cpu_ftrs.c
@@ -353,7 +353,7 @@ static void init_pmu_power8(void)
}
mtspr(SPRN_MMCRA, 0);
- mtspr(SPRN_MMCR0, 0);
+ mtspr(SPRN_MMCR0, MMCR0_FC);
mtspr(SPRN_MMCR1, 0);
mtspr(SPRN_MMCR2, 0);
mtspr(SPRN_MMCRS, 0);
@@ -392,7 +392,7 @@ static void init_pmu_power9(void)
mtspr(SPRN_MMCRC, 0);
mtspr(SPRN_MMCRA, 0);
- mtspr(SPRN_MMCR0, 0);
+ mtspr(SPRN_MMCR0, MMCR0_FC);
mtspr(SPRN_MMCR1, 0);
mtspr(SPRN_MMCR2, 0);
}
@@ -428,7 +428,7 @@ static void init_pmu_power10(void)
mtspr(SPRN_MMCR3, 0);
mtspr(SPRN_MMCRA, MMCRA_BHRB_DISABLE);
- mtspr(SPRN_MMCR0, MMCR0_PMCCEXT);
+ mtspr(SPRN_MMCR0, MMCR0_FC | MMCR0_PMCCEXT);
}
static int __init feat_enable_pmu_power10(struct dt_cpu_feature *f)
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 197665c1a1cd..e6cb923f91ff 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -2718,6 +2718,11 @@ static int kvmppc_core_vcpu_create_hv(struct kvm_vcpu *vcpu)
#endif
#endif
vcpu->arch.mmcr[0] = MMCR0_FC;
+ if (cpu_has_feature(CPU_FTR_ARCH_31)) {
+ vcpu->arch.mmcr[0] |= MMCR0_PMCCEXT;
+ vcpu->arch.mmcra = MMCRA_BHRB_DISABLE;
+ }
+
vcpu->arch.ctrl = CTRL_RUNLATCH;
/* default to host PVR, since we can't spoof it */
kvmppc_set_pvr_hv(vcpu, mfspr(SPRN_PVR));
--
2.23.0
^ permalink raw reply related
* [PATCH v2 18/60] KVM: PPC: Book3S HV: Don't always save PMU for guest capable of nesting
From: Nicholas Piggin @ 2021-08-11 16:00 UTC (permalink / raw)
To: kvm-ppc; +Cc: linuxppc-dev, Nicholas Piggin
In-Reply-To: <20210811160134.904987-1-npiggin@gmail.com>
Provide a config option that controls the the workaround added by commit
63279eeb7f93a ("KVM: PPC: Book3S HV: Always save guest pmu for guest
capable of nesting"). The option defaults to y for now, but is expected
to go away within a few releases.
Nested capable guests running with the earlier commit ("KVM: PPC: Book3S
HV Nested: Indicate guest PMU in-use in VPA") will now indicate the PMU
in-use status of their guests, which means the parent does not need to
unconditionally save the PMU for nested capable guests.
After this latest round of performance optimisations, this option costs
about 540 cycles or 10% entry/exit performance on a POWER9 nested-capable
guest.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/kvm/Kconfig | 15 +++++++++++++++
arch/powerpc/kvm/book3s_hv.c | 10 ++++++++--
2 files changed, 23 insertions(+), 2 deletions(-)
diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig
index e45644657d49..d57dcbc4eb0f 100644
--- a/arch/powerpc/kvm/Kconfig
+++ b/arch/powerpc/kvm/Kconfig
@@ -131,6 +131,21 @@ config KVM_BOOK3S_HV_EXIT_TIMING
If unsure, say N.
+config KVM_BOOK3S_HV_NESTED_PMU_WORKAROUND
+ bool "Nested L0 host workaround for L1 KVM host PMU handling bug" if EXPERT
+ depends on KVM_BOOK3S_HV_POSSIBLE
+ default !EXPERT
+ help
+ Old nested HV capable Linux guests have a bug where the don't
+ reflect the PMU in-use status of their L2 guest to the L0 host
+ while the L2 PMU registers are live. This can result in loss
+ of L2 PMU register state, causing perf to not work correctly in
+ L2 guests.
+
+ Selecting this option for the L0 host implements a workaround for
+ those buggy L1s which saves the L2 state, at the cost of performance
+ in all nested-capable guest entry/exit.
+
config KVM_BOOKE_HV
bool
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 2fe01dc2062f..197665c1a1cd 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -4033,8 +4033,14 @@ static int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit,
vcpu->arch.vpa.dirty = 1;
save_pmu = lp->pmcregs_in_use;
}
- /* Must save pmu if this guest is capable of running nested guests */
- save_pmu |= nesting_enabled(vcpu->kvm);
+ if (IS_ENABLED(CONFIG_KVM_BOOK3S_HV_NESTED_PMU_WORKAROUND)) {
+ /*
+ * Save pmu if this guest is capable of running nested guests.
+ * This is option is for old L1s that do not set their
+ * lppaca->pmcregs_in_use properly when entering their L2.
+ */
+ save_pmu |= nesting_enabled(vcpu->kvm);
+ }
kvmhv_save_guest_pmu(vcpu, save_pmu);
#ifdef CONFIG_PPC_PSERIES
--
2.23.0
^ permalink raw reply related
* [PATCH v2 17/60] powerpc/64s: Keep AMOR SPR a constant ~0 at runtime
From: Nicholas Piggin @ 2021-08-11 16:00 UTC (permalink / raw)
To: kvm-ppc; +Cc: linuxppc-dev, Nicholas Piggin, Fabiano Rosas
In-Reply-To: <20210811160134.904987-1-npiggin@gmail.com>
This register controls supervisor SPR modifications, and as such is only
relevant for KVM. KVM always sets AMOR to ~0 on guest entry, and never
restores it coming back out to the host, so it can be kept constant and
avoid the mtSPR in KVM guest entry.
Reviewed-by: Fabiano Rosas <farosas@linux.ibm.com>
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/kernel/cpu_setup_power.c | 8 ++++++++
arch/powerpc/kernel/dt_cpu_ftrs.c | 2 ++
arch/powerpc/kvm/book3s_hv_p9_entry.c | 2 --
arch/powerpc/kvm/book3s_hv_rmhandlers.S | 2 --
arch/powerpc/mm/book3s64/radix_pgtable.c | 15 ---------------
arch/powerpc/platforms/powernv/idle.c | 8 +++-----
6 files changed, 13 insertions(+), 24 deletions(-)
diff --git a/arch/powerpc/kernel/cpu_setup_power.c b/arch/powerpc/kernel/cpu_setup_power.c
index 3cca88ee96d7..a29dc8326622 100644
--- a/arch/powerpc/kernel/cpu_setup_power.c
+++ b/arch/powerpc/kernel/cpu_setup_power.c
@@ -137,6 +137,7 @@ void __setup_cpu_power7(unsigned long offset, struct cpu_spec *t)
return;
mtspr(SPRN_LPID, 0);
+ mtspr(SPRN_AMOR, ~0);
mtspr(SPRN_PCR, PCR_MASK);
init_LPCR_ISA206(mfspr(SPRN_LPCR), LPCR_LPES1 >> LPCR_LPES_SH);
}
@@ -150,6 +151,7 @@ void __restore_cpu_power7(void)
return;
mtspr(SPRN_LPID, 0);
+ mtspr(SPRN_AMOR, ~0);
mtspr(SPRN_PCR, PCR_MASK);
init_LPCR_ISA206(mfspr(SPRN_LPCR), LPCR_LPES1 >> LPCR_LPES_SH);
}
@@ -164,6 +166,7 @@ void __setup_cpu_power8(unsigned long offset, struct cpu_spec *t)
return;
mtspr(SPRN_LPID, 0);
+ mtspr(SPRN_AMOR, ~0);
mtspr(SPRN_PCR, PCR_MASK);
init_LPCR_ISA206(mfspr(SPRN_LPCR) | LPCR_PECEDH, 0); /* LPES = 0 */
init_HFSCR();
@@ -184,6 +187,7 @@ void __restore_cpu_power8(void)
return;
mtspr(SPRN_LPID, 0);
+ mtspr(SPRN_AMOR, ~0);
mtspr(SPRN_PCR, PCR_MASK);
init_LPCR_ISA206(mfspr(SPRN_LPCR) | LPCR_PECEDH, 0); /* LPES = 0 */
init_HFSCR();
@@ -202,6 +206,7 @@ void __setup_cpu_power9(unsigned long offset, struct cpu_spec *t)
mtspr(SPRN_PSSCR, 0);
mtspr(SPRN_LPID, 0);
mtspr(SPRN_PID, 0);
+ mtspr(SPRN_AMOR, ~0);
mtspr(SPRN_PCR, PCR_MASK);
init_LPCR_ISA300((mfspr(SPRN_LPCR) | LPCR_PECEDH | LPCR_PECE_HVEE |\
LPCR_HVICE | LPCR_HEIC) & ~(LPCR_UPRT | LPCR_HR), 0);
@@ -223,6 +228,7 @@ void __restore_cpu_power9(void)
mtspr(SPRN_PSSCR, 0);
mtspr(SPRN_LPID, 0);
mtspr(SPRN_PID, 0);
+ mtspr(SPRN_AMOR, ~0);
mtspr(SPRN_PCR, PCR_MASK);
init_LPCR_ISA300((mfspr(SPRN_LPCR) | LPCR_PECEDH | LPCR_PECE_HVEE |\
LPCR_HVICE | LPCR_HEIC) & ~(LPCR_UPRT | LPCR_HR), 0);
@@ -242,6 +248,7 @@ void __setup_cpu_power10(unsigned long offset, struct cpu_spec *t)
mtspr(SPRN_PSSCR, 0);
mtspr(SPRN_LPID, 0);
mtspr(SPRN_PID, 0);
+ mtspr(SPRN_AMOR, ~0);
mtspr(SPRN_PCR, PCR_MASK);
init_LPCR_ISA300((mfspr(SPRN_LPCR) | LPCR_PECEDH | LPCR_PECE_HVEE |\
LPCR_HVICE | LPCR_HEIC) & ~(LPCR_UPRT | LPCR_HR), 0);
@@ -264,6 +271,7 @@ void __restore_cpu_power10(void)
mtspr(SPRN_PSSCR, 0);
mtspr(SPRN_LPID, 0);
mtspr(SPRN_PID, 0);
+ mtspr(SPRN_AMOR, ~0);
mtspr(SPRN_PCR, PCR_MASK);
init_LPCR_ISA300((mfspr(SPRN_LPCR) | LPCR_PECEDH | LPCR_PECE_HVEE |\
LPCR_HVICE | LPCR_HEIC) & ~(LPCR_UPRT | LPCR_HR), 0);
diff --git a/arch/powerpc/kernel/dt_cpu_ftrs.c b/arch/powerpc/kernel/dt_cpu_ftrs.c
index af95f337e54b..38ea20fadc4a 100644
--- a/arch/powerpc/kernel/dt_cpu_ftrs.c
+++ b/arch/powerpc/kernel/dt_cpu_ftrs.c
@@ -80,6 +80,7 @@ static void __restore_cpu_cpufeatures(void)
mtspr(SPRN_LPCR, system_registers.lpcr);
if (hv_mode) {
mtspr(SPRN_LPID, 0);
+ mtspr(SPRN_AMOR, ~0);
mtspr(SPRN_HFSCR, system_registers.hfscr);
mtspr(SPRN_PCR, system_registers.pcr);
}
@@ -216,6 +217,7 @@ static int __init feat_enable_hv(struct dt_cpu_feature *f)
}
mtspr(SPRN_LPID, 0);
+ mtspr(SPRN_AMOR, ~0);
lpcr = mfspr(SPRN_LPCR);
lpcr &= ~LPCR_LPES0; /* HV external interrupts */
diff --git a/arch/powerpc/kvm/book3s_hv_p9_entry.c b/arch/powerpc/kvm/book3s_hv_p9_entry.c
index bd8cf0a65ce8..a7f63082b4e3 100644
--- a/arch/powerpc/kvm/book3s_hv_p9_entry.c
+++ b/arch/powerpc/kvm/book3s_hv_p9_entry.c
@@ -286,8 +286,6 @@ int kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpc
mtspr(SPRN_SPRG2, vcpu->arch.shregs.sprg2);
mtspr(SPRN_SPRG3, vcpu->arch.shregs.sprg3);
- mtspr(SPRN_AMOR, ~0UL);
-
local_paca->kvm_hstate.in_guest = KVM_GUEST_MODE_HV_P9;
/*
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 75079397c2a5..9021052f1579 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -772,10 +772,8 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
/* Restore AMR and UAMOR, set AMOR to all 1s */
ld r5,VCPU_AMR(r4)
ld r6,VCPU_UAMOR(r4)
- li r7,-1
mtspr SPRN_AMR,r5
mtspr SPRN_UAMOR,r6
- mtspr SPRN_AMOR,r7
/* Restore state of CTRL run bit; assume 1 on entry */
lwz r5,VCPU_CTRL(r4)
diff --git a/arch/powerpc/mm/book3s64/radix_pgtable.c b/arch/powerpc/mm/book3s64/radix_pgtable.c
index e50ddf129c15..5aebd70ef66a 100644
--- a/arch/powerpc/mm/book3s64/radix_pgtable.c
+++ b/arch/powerpc/mm/book3s64/radix_pgtable.c
@@ -572,18 +572,6 @@ void __init radix__early_init_devtree(void)
return;
}
-static void radix_init_amor(void)
-{
- /*
- * In HV mode, we init AMOR (Authority Mask Override Register) so that
- * the hypervisor and guest can setup IAMR (Instruction Authority Mask
- * Register), enable key 0 and set it to 1.
- *
- * AMOR = 0b1100 .... 0000 (Mask for key 0 is 11)
- */
- mtspr(SPRN_AMOR, (3ul << 62));
-}
-
void __init radix__early_init_mmu(void)
{
unsigned long lpcr;
@@ -644,7 +632,6 @@ void __init radix__early_init_mmu(void)
lpcr = mfspr(SPRN_LPCR);
mtspr(SPRN_LPCR, lpcr | LPCR_UPRT | LPCR_HR);
radix_init_partition_table();
- radix_init_amor();
} else {
radix_init_pseries();
}
@@ -668,8 +655,6 @@ void radix__early_init_mmu_secondary(void)
set_ptcr_when_no_uv(__pa(partition_tb) |
(PATB_SIZE_SHIFT - 12));
-
- radix_init_amor();
}
radix__switch_mmu_context(NULL, &init_mm);
diff --git a/arch/powerpc/platforms/powernv/idle.c b/arch/powerpc/platforms/powernv/idle.c
index df19e2ff9d3c..721ac4f7e2d1 100644
--- a/arch/powerpc/platforms/powernv/idle.c
+++ b/arch/powerpc/platforms/powernv/idle.c
@@ -306,8 +306,8 @@ struct p7_sprs {
/* per thread SPRs that get lost in shallow states */
u64 amr;
u64 iamr;
- u64 amor;
u64 uamor;
+ /* amor is restored to constant ~0 */
};
static unsigned long power7_idle_insn(unsigned long type)
@@ -378,7 +378,6 @@ static unsigned long power7_idle_insn(unsigned long type)
if (cpu_has_feature(CPU_FTR_ARCH_207S)) {
sprs.amr = mfspr(SPRN_AMR);
sprs.iamr = mfspr(SPRN_IAMR);
- sprs.amor = mfspr(SPRN_AMOR);
sprs.uamor = mfspr(SPRN_UAMOR);
}
@@ -397,7 +396,7 @@ static unsigned long power7_idle_insn(unsigned long type)
*/
mtspr(SPRN_AMR, sprs.amr);
mtspr(SPRN_IAMR, sprs.iamr);
- mtspr(SPRN_AMOR, sprs.amor);
+ mtspr(SPRN_AMOR, ~0);
mtspr(SPRN_UAMOR, sprs.uamor);
}
}
@@ -687,7 +686,6 @@ static unsigned long power9_idle_stop(unsigned long psscr)
sprs.amr = mfspr(SPRN_AMR);
sprs.iamr = mfspr(SPRN_IAMR);
- sprs.amor = mfspr(SPRN_AMOR);
sprs.uamor = mfspr(SPRN_UAMOR);
srr1 = isa300_idle_stop_mayloss(psscr); /* go idle */
@@ -708,7 +706,7 @@ static unsigned long power9_idle_stop(unsigned long psscr)
*/
mtspr(SPRN_AMR, sprs.amr);
mtspr(SPRN_IAMR, sprs.iamr);
- mtspr(SPRN_AMOR, sprs.amor);
+ mtspr(SPRN_AMOR, ~0);
mtspr(SPRN_UAMOR, sprs.uamor);
/*
--
2.23.0
^ permalink raw reply related
* [PATCH v2 16/60] KVM: PPC: Book3S HV: POWER10 enable HAIL when running radix guests
From: Nicholas Piggin @ 2021-08-11 16:00 UTC (permalink / raw)
To: kvm-ppc; +Cc: linuxppc-dev, Nicholas Piggin, Fabiano Rosas
In-Reply-To: <20210811160134.904987-1-npiggin@gmail.com>
HV interrupts may be taken with the MMU enabled when radix guests are
running. Enable LPCR[HAIL] on ISA v3.1 processors for radix guests.
Make this depend on the host LPCR[HAIL] being enabled. Currently that is
always enabled, but having this test means any issue that might require
LPCR[HAIL] to be disabled in the host will not have to be duplicated in
KVM.
This optimisation takes 1380 cycles off a NULL hcall entry+exit micro
benchmark on a POWER10.
Reviewed-by: Fabiano Rosas <farosas@linux.ibm.com>
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/kvm/book3s_hv.c | 29 +++++++++++++++++++++++++----
1 file changed, 25 insertions(+), 4 deletions(-)
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 5e48a929d670..2fe01dc2062f 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -5034,6 +5034,8 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu)
*/
int kvmppc_switch_mmu_to_hpt(struct kvm *kvm)
{
+ unsigned long lpcr, lpcr_mask;
+
if (nesting_enabled(kvm))
kvmhv_release_all_nested(kvm);
kvmppc_rmap_reset(kvm);
@@ -5043,8 +5045,13 @@ int kvmppc_switch_mmu_to_hpt(struct kvm *kvm)
kvm->arch.radix = 0;
spin_unlock(&kvm->mmu_lock);
kvmppc_free_radix(kvm);
- kvmppc_update_lpcr(kvm, LPCR_VPM1,
- LPCR_VPM1 | LPCR_UPRT | LPCR_GTSE | LPCR_HR);
+
+ lpcr = LPCR_VPM1;
+ lpcr_mask = LPCR_VPM1 | LPCR_UPRT | LPCR_GTSE | LPCR_HR;
+ if (cpu_has_feature(CPU_FTR_ARCH_31))
+ lpcr_mask |= LPCR_HAIL;
+ kvmppc_update_lpcr(kvm, lpcr, lpcr_mask);
+
return 0;
}
@@ -5054,6 +5061,7 @@ int kvmppc_switch_mmu_to_hpt(struct kvm *kvm)
*/
int kvmppc_switch_mmu_to_radix(struct kvm *kvm)
{
+ unsigned long lpcr, lpcr_mask;
int err;
err = kvmppc_init_vm_radix(kvm);
@@ -5065,8 +5073,17 @@ int kvmppc_switch_mmu_to_radix(struct kvm *kvm)
kvm->arch.radix = 1;
spin_unlock(&kvm->mmu_lock);
kvmppc_free_hpt(&kvm->arch.hpt);
- kvmppc_update_lpcr(kvm, LPCR_UPRT | LPCR_GTSE | LPCR_HR,
- LPCR_VPM1 | LPCR_UPRT | LPCR_GTSE | LPCR_HR);
+
+ lpcr = LPCR_UPRT | LPCR_GTSE | LPCR_HR;
+ lpcr_mask = LPCR_VPM1 | LPCR_UPRT | LPCR_GTSE | LPCR_HR;
+ if (cpu_has_feature(CPU_FTR_ARCH_31)) {
+ lpcr_mask |= LPCR_HAIL;
+ if (cpu_has_feature(CPU_FTR_HVMODE) &&
+ (kvm->arch.host_lpcr & LPCR_HAIL))
+ lpcr |= LPCR_HAIL;
+ }
+ kvmppc_update_lpcr(kvm, lpcr, lpcr_mask);
+
return 0;
}
@@ -5230,6 +5247,10 @@ static int kvmppc_core_init_vm_hv(struct kvm *kvm)
kvm->arch.mmu_ready = 1;
lpcr &= ~LPCR_VPM1;
lpcr |= LPCR_UPRT | LPCR_GTSE | LPCR_HR;
+ if (cpu_has_feature(CPU_FTR_HVMODE) &&
+ cpu_has_feature(CPU_FTR_ARCH_31) &&
+ (kvm->arch.host_lpcr & LPCR_HAIL))
+ lpcr |= LPCR_HAIL;
ret = kvmppc_init_vm_radix(kvm);
if (ret) {
kvmppc_free_lpid(kvm->arch.lpid);
--
2.23.0
^ permalink raw reply related
* [PATCH v2 15/60] powerpc/time: add API for KVM to re-arm the host timer/decrementer
From: Nicholas Piggin @ 2021-08-11 16:00 UTC (permalink / raw)
To: kvm-ppc; +Cc: linuxppc-dev, Nicholas Piggin
In-Reply-To: <20210811160134.904987-1-npiggin@gmail.com>
Rather than have KVM look up the host timer and fiddle with the
irq-work internal details, have the powerpc/time.c code provide a
function for KVM to re-arm the Linux timer code when exiting a
guest.
This is implementation has an improvement over existing code of
marking a decrementer interrupt as soft-pending if a timer has
expired, rather than setting DEC to a -ve value, which tended to
cause host timers to take two interrupts (first hdec to exit the
guest, then the immediate dec).
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/include/asm/time.h | 16 +++-------
arch/powerpc/kernel/time.c | 52 +++++++++++++++++++++++++++------
arch/powerpc/kvm/book3s_hv.c | 7 ++---
3 files changed, 49 insertions(+), 26 deletions(-)
diff --git a/arch/powerpc/include/asm/time.h b/arch/powerpc/include/asm/time.h
index 69b6be617772..924b2157882f 100644
--- a/arch/powerpc/include/asm/time.h
+++ b/arch/powerpc/include/asm/time.h
@@ -99,18 +99,6 @@ extern void div128_by_32(u64 dividend_high, u64 dividend_low,
extern void secondary_cpu_time_init(void);
extern void __init time_init(void);
-#ifdef CONFIG_PPC64
-static inline unsigned long test_irq_work_pending(void)
-{
- unsigned long x;
-
- asm volatile("lbz %0,%1(13)"
- : "=r" (x)
- : "i" (offsetof(struct paca_struct, irq_work_pending)));
- return x;
-}
-#endif
-
DECLARE_PER_CPU(u64, decrementers_next_tb);
static inline u64 timer_get_next_tb(void)
@@ -118,6 +106,10 @@ static inline u64 timer_get_next_tb(void)
return __this_cpu_read(decrementers_next_tb);
}
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+void timer_rearm_host_dec(u64 now);
+#endif
+
/* Convert timebase ticks to nanoseconds */
unsigned long long tb_to_ns(unsigned long long tb_ticks);
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 72d872b49167..016828b7401b 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -499,6 +499,16 @@ EXPORT_SYMBOL(profile_pc);
* 64-bit uses a byte in the PACA, 32-bit uses a per-cpu variable...
*/
#ifdef CONFIG_PPC64
+static inline unsigned long test_irq_work_pending(void)
+{
+ unsigned long x;
+
+ asm volatile("lbz %0,%1(13)"
+ : "=r" (x)
+ : "i" (offsetof(struct paca_struct, irq_work_pending)));
+ return x;
+}
+
static inline void set_irq_work_pending_flag(void)
{
asm volatile("stb %0,%1(13)" : :
@@ -542,13 +552,44 @@ void arch_irq_work_raise(void)
preempt_enable();
}
+static void set_dec_or_work(u64 val)
+{
+ set_dec(val);
+ /* We may have raced with new irq work */
+ if (unlikely(test_irq_work_pending()))
+ set_dec(1);
+}
+
#else /* CONFIG_IRQ_WORK */
#define test_irq_work_pending() 0
#define clear_irq_work_pending()
+static void set_dec_or_work(u64 val)
+{
+ set_dec(val);
+}
#endif /* CONFIG_IRQ_WORK */
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+void timer_rearm_host_dec(u64 now)
+{
+ u64 *next_tb = this_cpu_ptr(&decrementers_next_tb);
+
+ WARN_ON_ONCE(!arch_irqs_disabled());
+ WARN_ON_ONCE(mfmsr() & MSR_EE);
+
+ if (now >= *next_tb) {
+ local_paca->irq_happened |= PACA_IRQ_DEC;
+ } else {
+ now = *next_tb - now;
+ if (now <= decrementer_max)
+ set_dec_or_work(now);
+ }
+}
+EXPORT_SYMBOL_GPL(timer_rearm_host_dec);
+#endif
+
/*
* timer_interrupt - gets called when the decrementer overflows,
* with interrupts disabled.
@@ -609,10 +650,7 @@ DEFINE_INTERRUPT_HANDLER_ASYNC(timer_interrupt)
} else {
now = *next_tb - now;
if (now <= decrementer_max)
- set_dec(now);
- /* We may have raced with new irq work */
- if (test_irq_work_pending())
- set_dec(1);
+ set_dec_or_work(now);
__this_cpu_inc(irq_stat.timer_irqs_others);
}
@@ -854,11 +892,7 @@ static int decrementer_set_next_event(unsigned long evt,
struct clock_event_device *dev)
{
__this_cpu_write(decrementers_next_tb, get_tb() + evt);
- set_dec(evt);
-
- /* We may have raced with new irq work */
- if (test_irq_work_pending())
- set_dec(1);
+ set_dec_or_work(evt);
return 0;
}
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 49a3c1e6a544..5e48a929d670 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -4048,11 +4048,8 @@ static int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit,
vc->entry_exit_map = 0x101;
vc->in_guest = 0;
- next_timer = timer_get_next_tb();
- set_dec(next_timer - tb);
- /* We may have raced with new irq work */
- if (test_irq_work_pending())
- set_dec(1);
+ timer_rearm_host_dec(tb);
+
mtspr(SPRN_SPRG_VDSO_WRITE, local_paca->sprg_vdso);
kvmhv_load_host_pmu();
--
2.23.0
^ permalink raw reply related
* [PATCH v2 14/60] KVM: PPC: Book3S HV P9: Reduce mftb per guest entry/exit
From: Nicholas Piggin @ 2021-08-11 16:00 UTC (permalink / raw)
To: kvm-ppc; +Cc: linuxppc-dev, Nicholas Piggin, Fabiano Rosas
In-Reply-To: <20210811160134.904987-1-npiggin@gmail.com>
mftb is serialising (dispatch next-to-complete) so it is heavy weight
for a mfspr. Avoid reading it multiple times in the entry or exit paths.
A small number of cycles delay to timers is tolerable.
Reviewed-by: Fabiano Rosas <farosas@linux.ibm.com>
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/kvm/book3s_hv.c | 4 ++--
arch/powerpc/kvm/book3s_hv_p9_entry.c | 5 +++--
2 files changed, 5 insertions(+), 4 deletions(-)
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 34e95d3c89e5..49a3c1e6a544 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -3926,7 +3926,7 @@ static int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit,
*
* XXX: Another day's problem.
*/
- mtspr(SPRN_DEC, vcpu->arch.dec_expires - mftb());
+ mtspr(SPRN_DEC, vcpu->arch.dec_expires - tb);
if (kvmhv_on_pseries()) {
/*
@@ -4049,7 +4049,7 @@ static int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit,
vc->in_guest = 0;
next_timer = timer_get_next_tb();
- set_dec(next_timer - mftb());
+ set_dec(next_timer - tb);
/* We may have raced with new irq work */
if (test_irq_work_pending())
set_dec(1);
diff --git a/arch/powerpc/kvm/book3s_hv_p9_entry.c b/arch/powerpc/kvm/book3s_hv_p9_entry.c
index 0ff9ddb5e7ca..bd8cf0a65ce8 100644
--- a/arch/powerpc/kvm/book3s_hv_p9_entry.c
+++ b/arch/powerpc/kvm/book3s_hv_p9_entry.c
@@ -203,7 +203,8 @@ int kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpc
unsigned long host_dawr1;
unsigned long host_dawrx1;
- hdec = time_limit - mftb();
+ tb = mftb();
+ hdec = time_limit - tb;
if (hdec < 0)
return BOOK3S_INTERRUPT_HV_DECREMENTER;
@@ -215,7 +216,7 @@ int kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpc
vcpu->arch.ceded = 0;
if (vc->tb_offset) {
- u64 new_tb = mftb() + vc->tb_offset;
+ u64 new_tb = tb + vc->tb_offset;
mtspr(SPRN_TBU40, new_tb);
tb = mftb();
if ((tb & 0xffffff) < (new_tb & 0xffffff))
--
2.23.0
^ permalink raw reply related
* [PATCH v2 13/60] KVM: PPC: Book3S HV P9: Use large decrementer for HDEC
From: Nicholas Piggin @ 2021-08-11 16:00 UTC (permalink / raw)
To: kvm-ppc; +Cc: Alexey Kardashevskiy, linuxppc-dev, Nicholas Piggin
In-Reply-To: <20210811160134.904987-1-npiggin@gmail.com>
On processors that don't suppress the HDEC exceptions when LPCR[HDICE]=0,
this could help reduce needless guest exits due to leftover exceptions on
entering the guest.
Reviewed-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/include/asm/time.h | 2 ++
arch/powerpc/kernel/time.c | 1 +
arch/powerpc/kvm/book3s_hv_p9_entry.c | 3 ++-
3 files changed, 5 insertions(+), 1 deletion(-)
diff --git a/arch/powerpc/include/asm/time.h b/arch/powerpc/include/asm/time.h
index fd09b4797fd7..69b6be617772 100644
--- a/arch/powerpc/include/asm/time.h
+++ b/arch/powerpc/include/asm/time.h
@@ -18,6 +18,8 @@
#include <asm/vdso/timebase.h>
/* time.c */
+extern u64 decrementer_max;
+
extern unsigned long tb_ticks_per_jiffy;
extern unsigned long tb_ticks_per_usec;
extern unsigned long tb_ticks_per_sec;
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 01df89918aa4..72d872b49167 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -89,6 +89,7 @@ static struct clocksource clocksource_timebase = {
#define DECREMENTER_DEFAULT_MAX 0x7FFFFFFF
u64 decrementer_max = DECREMENTER_DEFAULT_MAX;
+EXPORT_SYMBOL_GPL(decrementer_max); /* for KVM HDEC */
static int decrementer_set_next_event(unsigned long evt,
struct clock_event_device *dev);
diff --git a/arch/powerpc/kvm/book3s_hv_p9_entry.c b/arch/powerpc/kvm/book3s_hv_p9_entry.c
index 961b3d70483c..0ff9ddb5e7ca 100644
--- a/arch/powerpc/kvm/book3s_hv_p9_entry.c
+++ b/arch/powerpc/kvm/book3s_hv_p9_entry.c
@@ -504,7 +504,8 @@ int kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpc
vc->tb_offset_applied = 0;
}
- mtspr(SPRN_HDEC, 0x7fffffff);
+ /* HDEC must be at least as large as DEC, so decrementer_max fits */
+ mtspr(SPRN_HDEC, decrementer_max);
save_clear_guest_mmu(kvm, vcpu);
switch_mmu_to_host(kvm, host_pidr);
--
2.23.0
^ permalink raw reply related
* [PATCH v2 12/60] KVM: PPC: Book3S HV P9: Use host timer accounting to avoid decrementer read
From: Nicholas Piggin @ 2021-08-11 16:00 UTC (permalink / raw)
To: kvm-ppc; +Cc: linuxppc-dev, Nicholas Piggin
In-Reply-To: <20210811160134.904987-1-npiggin@gmail.com>
There is no need to save away the host DEC value, as it is derived
from the host timer subsystem which maintains the next timer time,
so it can be restored from there.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/include/asm/time.h | 5 +++++
arch/powerpc/kernel/time.c | 1 +
arch/powerpc/kvm/book3s_hv.c | 14 +++++++-------
3 files changed, 13 insertions(+), 7 deletions(-)
diff --git a/arch/powerpc/include/asm/time.h b/arch/powerpc/include/asm/time.h
index 8c2c3dd4ddba..fd09b4797fd7 100644
--- a/arch/powerpc/include/asm/time.h
+++ b/arch/powerpc/include/asm/time.h
@@ -111,6 +111,11 @@ static inline unsigned long test_irq_work_pending(void)
DECLARE_PER_CPU(u64, decrementers_next_tb);
+static inline u64 timer_get_next_tb(void)
+{
+ return __this_cpu_read(decrementers_next_tb);
+}
+
/* Convert timebase ticks to nanoseconds */
unsigned long long tb_to_ns(unsigned long long tb_ticks);
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index e45ce427bffb..01df89918aa4 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -108,6 +108,7 @@ struct clock_event_device decrementer_clockevent = {
EXPORT_SYMBOL(decrementer_clockevent);
DEFINE_PER_CPU(u64, decrementers_next_tb);
+EXPORT_SYMBOL_GPL(decrementers_next_tb);
static DEFINE_PER_CPU(struct clock_event_device, decrementers);
#define XSEC_PER_SEC (1024*1024)
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index b60a70177507..34e95d3c89e5 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -3859,18 +3859,17 @@ static int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit,
struct kvmppc_vcore *vc = vcpu->arch.vcore;
struct p9_host_os_sprs host_os_sprs;
s64 dec;
- u64 tb;
+ u64 tb, next_timer;
int trap, save_pmu;
WARN_ON_ONCE(vcpu->arch.ceded);
- dec = mfspr(SPRN_DEC);
tb = mftb();
- if (dec < 0)
+ next_timer = timer_get_next_tb();
+ if (tb >= next_timer)
return BOOK3S_INTERRUPT_HV_DECREMENTER;
- local_paca->kvm_hstate.dec_expires = dec + tb;
- if (local_paca->kvm_hstate.dec_expires < time_limit)
- time_limit = local_paca->kvm_hstate.dec_expires;
+ if (next_timer < time_limit)
+ time_limit = next_timer;
save_p9_host_os_sprs(&host_os_sprs);
@@ -4049,7 +4048,8 @@ static int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit,
vc->entry_exit_map = 0x101;
vc->in_guest = 0;
- set_dec(local_paca->kvm_hstate.dec_expires - mftb());
+ next_timer = timer_get_next_tb();
+ set_dec(next_timer - mftb());
/* We may have raced with new irq work */
if (test_irq_work_pending())
set_dec(1);
--
2.23.0
^ permalink raw reply related
* [PATCH v2 11/60] KMV: PPC: Book3S HV P9: Use set_dec to set decrementer to host
From: Nicholas Piggin @ 2021-08-11 16:00 UTC (permalink / raw)
To: kvm-ppc; +Cc: Alexey Kardashevskiy, linuxppc-dev, Nicholas Piggin
In-Reply-To: <20210811160134.904987-1-npiggin@gmail.com>
The host Linux timer code arms the decrementer with the value
'decrementers_next_tb - current_tb' using set_dec(), which stores
val - 1 on Book3S-64, which is not quite the same as what KVM does
to re-arm the host decrementer when exiting the guest.
This shouldn't be a significant change, but it makes the logic match
and avoids this small extra change being brought into the next patch.
Suggested-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/kvm/book3s_hv.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 3198f79572d8..b60a70177507 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -4049,7 +4049,7 @@ static int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit,
vc->entry_exit_map = 0x101;
vc->in_guest = 0;
- mtspr(SPRN_DEC, local_paca->kvm_hstate.dec_expires - mftb());
+ set_dec(local_paca->kvm_hstate.dec_expires - mftb());
/* We may have raced with new irq work */
if (test_irq_work_pending())
set_dec(1);
--
2.23.0
^ permalink raw reply related
* [PATCH v2 10/60] powerpc/64s: Remove WORT SPR from POWER9/10
From: Nicholas Piggin @ 2021-08-11 16:00 UTC (permalink / raw)
To: kvm-ppc; +Cc: linuxppc-dev, Nicholas Piggin, Fabiano Rosas
In-Reply-To: <20210811160134.904987-1-npiggin@gmail.com>
This register is not architected and not implemented in POWER9 or 10,
it just reads back zeroes for compatibility.
Reviewed-by: Fabiano Rosas <farosas@linux.ibm.com>
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/kvm/book3s_hv.c | 3 ---
arch/powerpc/platforms/powernv/idle.c | 2 --
2 files changed, 5 deletions(-)
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 1a3ea0ea7514..3198f79572d8 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -3770,7 +3770,6 @@ static void load_spr_state(struct kvm_vcpu *vcpu)
mtspr(SPRN_EBBHR, vcpu->arch.ebbhr);
mtspr(SPRN_EBBRR, vcpu->arch.ebbrr);
mtspr(SPRN_BESCR, vcpu->arch.bescr);
- mtspr(SPRN_WORT, vcpu->arch.wort);
mtspr(SPRN_TIDR, vcpu->arch.tid);
mtspr(SPRN_AMR, vcpu->arch.amr);
mtspr(SPRN_UAMOR, vcpu->arch.uamor);
@@ -3797,7 +3796,6 @@ static void store_spr_state(struct kvm_vcpu *vcpu)
vcpu->arch.ebbhr = mfspr(SPRN_EBBHR);
vcpu->arch.ebbrr = mfspr(SPRN_EBBRR);
vcpu->arch.bescr = mfspr(SPRN_BESCR);
- vcpu->arch.wort = mfspr(SPRN_WORT);
vcpu->arch.tid = mfspr(SPRN_TIDR);
vcpu->arch.amr = mfspr(SPRN_AMR);
vcpu->arch.uamor = mfspr(SPRN_UAMOR);
@@ -3829,7 +3827,6 @@ static void restore_p9_host_os_sprs(struct kvm_vcpu *vcpu,
struct p9_host_os_sprs *host_os_sprs)
{
mtspr(SPRN_PSPB, 0);
- mtspr(SPRN_WORT, 0);
mtspr(SPRN_UAMOR, 0);
mtspr(SPRN_DSCR, host_os_sprs->dscr);
diff --git a/arch/powerpc/platforms/powernv/idle.c b/arch/powerpc/platforms/powernv/idle.c
index 1e908536890b..df19e2ff9d3c 100644
--- a/arch/powerpc/platforms/powernv/idle.c
+++ b/arch/powerpc/platforms/powernv/idle.c
@@ -667,7 +667,6 @@ static unsigned long power9_idle_stop(unsigned long psscr)
sprs.purr = mfspr(SPRN_PURR);
sprs.spurr = mfspr(SPRN_SPURR);
sprs.dscr = mfspr(SPRN_DSCR);
- sprs.wort = mfspr(SPRN_WORT);
sprs.ciabr = mfspr(SPRN_CIABR);
sprs.mmcra = mfspr(SPRN_MMCRA);
@@ -785,7 +784,6 @@ static unsigned long power9_idle_stop(unsigned long psscr)
mtspr(SPRN_PURR, sprs.purr);
mtspr(SPRN_SPURR, sprs.spurr);
mtspr(SPRN_DSCR, sprs.dscr);
- mtspr(SPRN_WORT, sprs.wort);
mtspr(SPRN_CIABR, sprs.ciabr);
mtspr(SPRN_MMCRA, sprs.mmcra);
--
2.23.0
^ permalink raw reply related
* [PATCH v2 09/60] KVM: PPC: Book3S HV Nested: Reflect guest PMU in-use to L0 when guest SPRs are live
From: Nicholas Piggin @ 2021-08-11 16:00 UTC (permalink / raw)
To: kvm-ppc; +Cc: linuxppc-dev, Nicholas Piggin, Fabiano Rosas
In-Reply-To: <20210811160134.904987-1-npiggin@gmail.com>
After the L1 saves its PMU SPRs but before loading the L2's PMU SPRs,
switch the pmcregs_in_use field in the L1 lppaca to the value advertised
by the L2 in its VPA. On the way out of the L2, set it back after saving
the L2 PMU registers (if they were in-use).
This transfers the PMU liveness indication between the L1 and L2 at the
points where the registers are not live.
This fixes the nested HV bug for which a workaround was added to the L0
HV by commit 63279eeb7f93a ("KVM: PPC: Book3S HV: Always save guest pmu
for guest capable of nesting"), which explains the problem in detail.
That workaround is no longer required for guests that include this bug
fix.
Fixes: 360cae313702 ("KVM: PPC: Book3S HV: Nested guest entry via hypercall")
Reviewed-by: Fabiano Rosas <farosas@linux.ibm.com>
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/include/asm/pmc.h | 7 +++++++
arch/powerpc/kvm/book3s_hv.c | 20 ++++++++++++++++++++
2 files changed, 27 insertions(+)
diff --git a/arch/powerpc/include/asm/pmc.h b/arch/powerpc/include/asm/pmc.h
index c6bbe9778d3c..3c09109e708e 100644
--- a/arch/powerpc/include/asm/pmc.h
+++ b/arch/powerpc/include/asm/pmc.h
@@ -34,6 +34,13 @@ static inline void ppc_set_pmu_inuse(int inuse)
#endif
}
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+static inline int ppc_get_pmu_inuse(void)
+{
+ return get_paca()->pmcregs_in_use;
+}
+#endif
+
extern void power4_enable_pmcs(void);
#else /* CONFIG_PPC64 */
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 7bc9d487bc1a..1a3ea0ea7514 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -59,6 +59,7 @@
#include <asm/kvm_book3s.h>
#include <asm/mmu_context.h>
#include <asm/lppaca.h>
+#include <asm/pmc.h>
#include <asm/processor.h>
#include <asm/cputhreads.h>
#include <asm/page.h>
@@ -3894,6 +3895,18 @@ static int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit,
cpu_has_feature(CPU_FTR_P9_TM_HV_ASSIST))
kvmppc_restore_tm_hv(vcpu, vcpu->arch.shregs.msr, true);
+#ifdef CONFIG_PPC_PSERIES
+ if (kvmhv_on_pseries()) {
+ barrier();
+ if (vcpu->arch.vpa.pinned_addr) {
+ struct lppaca *lp = vcpu->arch.vpa.pinned_addr;
+ get_lppaca()->pmcregs_in_use = lp->pmcregs_in_use;
+ } else {
+ get_lppaca()->pmcregs_in_use = 1;
+ }
+ barrier();
+ }
+#endif
kvmhv_load_guest_pmu(vcpu);
msr_check_and_set(MSR_FP | MSR_VEC | MSR_VSX);
@@ -4028,6 +4041,13 @@ static int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit,
save_pmu |= nesting_enabled(vcpu->kvm);
kvmhv_save_guest_pmu(vcpu, save_pmu);
+#ifdef CONFIG_PPC_PSERIES
+ if (kvmhv_on_pseries()) {
+ barrier();
+ get_lppaca()->pmcregs_in_use = ppc_get_pmu_inuse();
+ barrier();
+ }
+#endif
vc->entry_exit_map = 0x101;
vc->in_guest = 0;
--
2.23.0
^ permalink raw reply related
* [PATCH v2 08/60] KVM: PPC: Book3S HV Nested: save_hv_return_state does not require trap argument
From: Nicholas Piggin @ 2021-08-11 16:00 UTC (permalink / raw)
To: kvm-ppc; +Cc: linuxppc-dev, Nicholas Piggin, Fabiano Rosas
In-Reply-To: <20210811160134.904987-1-npiggin@gmail.com>
From: Fabiano Rosas <farosas@linux.ibm.com>
vcpu is already anargument so vcpu->arch.trap can be used directly.
Signed-off-by: Fabiano Rosas <farosas@linux.ibm.com>
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/kvm/book3s_hv_nested.c | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/arch/powerpc/kvm/book3s_hv_nested.c b/arch/powerpc/kvm/book3s_hv_nested.c
index 5ad5014c6f68..ed8a2c9f5629 100644
--- a/arch/powerpc/kvm/book3s_hv_nested.c
+++ b/arch/powerpc/kvm/book3s_hv_nested.c
@@ -99,7 +99,7 @@ static void byteswap_hv_regs(struct hv_guest_state *hr)
hr->dawrx1 = swab64(hr->dawrx1);
}
-static void save_hv_return_state(struct kvm_vcpu *vcpu, int trap,
+static void save_hv_return_state(struct kvm_vcpu *vcpu,
struct hv_guest_state *hr)
{
struct kvmppc_vcore *vc = vcpu->arch.vcore;
@@ -118,7 +118,7 @@ static void save_hv_return_state(struct kvm_vcpu *vcpu, int trap,
hr->pidr = vcpu->arch.pid;
hr->cfar = vcpu->arch.cfar;
hr->ppr = vcpu->arch.ppr;
- switch (trap) {
+ switch (vcpu->arch.trap) {
case BOOK3S_INTERRUPT_H_DATA_STORAGE:
hr->hdar = vcpu->arch.fault_dar;
hr->hdsisr = vcpu->arch.fault_dsisr;
@@ -389,7 +389,7 @@ long kvmhv_enter_nested_guest(struct kvm_vcpu *vcpu)
delta_spurr = vcpu->arch.spurr - l2_hv.spurr;
delta_ic = vcpu->arch.ic - l2_hv.ic;
delta_vtb = vc->vtb - l2_hv.vtb;
- save_hv_return_state(vcpu, vcpu->arch.trap, &l2_hv);
+ save_hv_return_state(vcpu, &l2_hv);
/* restore L1 state */
vcpu->arch.nested = NULL;
--
2.23.0
^ permalink raw reply related
* [PATCH v2 07/60] KVM: PPC: Book3S HV Nested: Stop forwarding all HFUs to L1
From: Nicholas Piggin @ 2021-08-11 16:00 UTC (permalink / raw)
To: kvm-ppc; +Cc: linuxppc-dev, Nicholas Piggin, Fabiano Rosas
In-Reply-To: <20210811160134.904987-1-npiggin@gmail.com>
From: Fabiano Rosas <farosas@linux.ibm.com>
If the nested hypervisor has no access to a facility because it has
been disabled by the host, it should also not be able to see the
Hypervisor Facility Unavailable that arises from one of its guests
trying to access the facility.
This patch turns a HFU that happened in L2 into a Hypervisor Emulation
Assistance interrupt and forwards it to L1 for handling. The ones that
happened because L1 explicitly disabled the facility for L2 are still
let through, along with the corresponding Cause bits in the HFSCR.
Signed-off-by: Fabiano Rosas <farosas@linux.ibm.com>
[np: move handling into kvmppc_handle_nested_exit]
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/kvm/book3s_hv.c | 31 +++++++++++++++++++++++++++++--
1 file changed, 29 insertions(+), 2 deletions(-)
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index c65bd8fa4368..7bc9d487bc1a 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -1733,6 +1733,7 @@ XXX benchmark guest exits
static int kvmppc_handle_nested_exit(struct kvm_vcpu *vcpu)
{
+ struct kvm_nested_guest *nested = vcpu->arch.nested;
int r;
int srcu_idx;
@@ -1822,9 +1823,35 @@ static int kvmppc_handle_nested_exit(struct kvm_vcpu *vcpu)
fallthrough; /* go to facility unavailable handler */
#endif
- case BOOK3S_INTERRUPT_H_FAC_UNAVAIL:
- r = RESUME_HOST;
+ case BOOK3S_INTERRUPT_H_FAC_UNAVAIL: {
+ u64 cause = vcpu->arch.hfscr >> 56;
+
+ /*
+ * Only pass HFU interrupts to the L1 if the facility is
+ * permitted but disabled by the L1's HFSCR, otherwise
+ * the interrupt does not make sense to the L1 so turn
+ * it into a HEAI.
+ */
+ if (!(vcpu->arch.hfscr_permitted & (1UL << cause)) ||
+ (nested->hfscr & (1UL << cause))) {
+ vcpu->arch.trap = BOOK3S_INTERRUPT_H_EMUL_ASSIST;
+
+ /*
+ * If the fetch failed, return to guest and
+ * try executing it again.
+ */
+ r = kvmppc_get_last_inst(vcpu, INST_GENERIC,
+ &vcpu->arch.emul_inst);
+ if (r != EMULATE_DONE)
+ r = RESUME_GUEST;
+ else
+ r = RESUME_HOST;
+ } else {
+ r = RESUME_HOST;
+ }
+
break;
+ }
case BOOK3S_INTERRUPT_HV_RM_HARD:
vcpu->arch.trap = 0;
--
2.23.0
^ permalink raw reply related
* [PATCH v2 06/60] KVM: PPC: Book3S HV Nested: Make nested HFSCR state accessible
From: Nicholas Piggin @ 2021-08-11 16:00 UTC (permalink / raw)
To: kvm-ppc; +Cc: linuxppc-dev, Nicholas Piggin
In-Reply-To: <20210811160134.904987-1-npiggin@gmail.com>
When the L0 runs a nested L2, there are several permutations of HFSCR
that can be relevant. The HFSCR that the L1 vcpu L1 requested, the
HFSCR that the L1 vcpu may use, and the HFSCR that is actually being
used to run the L2.
The L1 requested HFSCR is not accessible outside the nested hcall
handler, so copy that into a new kvm_nested_guest.hfscr field.
The permitted HFSCR is taken from the HFSCR that the L1 runs with,
which is also not accessible while the hcall is being made. Move
this into a new kvm_vcpu_arch.hfscr_permitted field.
These will be used by the next patch to improve facility handling
for nested guests, and later by facility demand faulting patches.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/include/asm/kvm_book3s_64.h | 1 +
arch/powerpc/include/asm/kvm_host.h | 2 ++
arch/powerpc/kvm/book3s_hv.c | 2 ++
arch/powerpc/kvm/book3s_hv_nested.c | 5 +++--
4 files changed, 8 insertions(+), 2 deletions(-)
diff --git a/arch/powerpc/include/asm/kvm_book3s_64.h b/arch/powerpc/include/asm/kvm_book3s_64.h
index eaf3a562bf1e..19b6942c6969 100644
--- a/arch/powerpc/include/asm/kvm_book3s_64.h
+++ b/arch/powerpc/include/asm/kvm_book3s_64.h
@@ -39,6 +39,7 @@ struct kvm_nested_guest {
pgd_t *shadow_pgtable; /* our page table for this guest */
u64 l1_gr_to_hr; /* L1's addr of part'n-scoped table */
u64 process_table; /* process table entry for this guest */
+ u64 hfscr; /* HFSCR that the L1 requested for this nested guest */
long refcnt; /* number of pointers to this struct */
struct mutex tlb_lock; /* serialize page faults and tlbies */
struct kvm_nested_guest *next;
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 9f52f282b1aa..a779f7849cfb 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -811,6 +811,8 @@ struct kvm_vcpu_arch {
u32 online;
+ u64 hfscr_permitted; /* A mask of permitted HFSCR facilities */
+
/* For support of nested guests */
struct kvm_nested_guest *nested;
u32 nested_vcpu_id;
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index e79eedb65e6b..c65bd8fa4368 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -2718,6 +2718,8 @@ static int kvmppc_core_vcpu_create_hv(struct kvm_vcpu *vcpu)
if (cpu_has_feature(CPU_FTR_TM_COMP))
vcpu->arch.hfscr |= HFSCR_TM;
+ vcpu->arch.hfscr_permitted = vcpu->arch.hfscr;
+
kvmppc_mmu_book3s_hv_init(vcpu);
vcpu->arch.state = KVMPPC_VCPU_NOTREADY;
diff --git a/arch/powerpc/kvm/book3s_hv_nested.c b/arch/powerpc/kvm/book3s_hv_nested.c
index 1eb4e989edc7..5ad5014c6f68 100644
--- a/arch/powerpc/kvm/book3s_hv_nested.c
+++ b/arch/powerpc/kvm/book3s_hv_nested.c
@@ -272,10 +272,10 @@ static void load_l2_hv_regs(struct kvm_vcpu *vcpu,
(vc->lpcr & ~mask) | (*lpcr & mask));
/*
- * Don't let L1 enable features for L2 which we've disabled for L1,
+ * Don't let L1 enable features for L2 which we don't allow for L1,
* but preserve the interrupt cause field.
*/
- vcpu->arch.hfscr = l2_hv->hfscr & (HFSCR_INTR_CAUSE | vcpu->arch.hfscr);
+ vcpu->arch.hfscr = l2_hv->hfscr & (HFSCR_INTR_CAUSE | vcpu->arch.hfscr_permitted);
/* Don't let data address watchpoint match in hypervisor state */
vcpu->arch.dawrx0 = l2_hv->dawrx0 & ~DAWRX_HYP;
@@ -362,6 +362,7 @@ long kvmhv_enter_nested_guest(struct kvm_vcpu *vcpu)
/* set L1 state to L2 state */
vcpu->arch.nested = l2;
vcpu->arch.nested_vcpu_id = l2_hv.vcpu_token;
+ l2->hfscr = l2_hv.hfscr;
vcpu->arch.regs = l2_regs;
/* Guest must always run with ME enabled, HV disabled. */
--
2.23.0
^ permalink raw reply related
* [PATCH v2 05/60] KVM: PPC: Book3S HV Nested: Sanitise vcpu registers
From: Nicholas Piggin @ 2021-08-11 16:00 UTC (permalink / raw)
To: kvm-ppc; +Cc: linuxppc-dev, Nicholas Piggin, Fabiano Rosas
In-Reply-To: <20210811160134.904987-1-npiggin@gmail.com>
From: Fabiano Rosas <farosas@linux.ibm.com>
As one of the arguments of the H_ENTER_NESTED hypercall, the nested
hypervisor (L1) prepares a structure containing the values of various
hypervisor-privileged registers with which it wants the nested guest
(L2) to run. Since the nested HV runs in supervisor mode it needs the
host to write to these registers.
To stop a nested HV manipulating this mechanism and using a nested
guest as a proxy to access a facility that has been made unavailable
to it, we have a routine that sanitises the values of the HV registers
before copying them into the nested guest's vcpu struct.
However, when coming out of the guest the values are copied as they
were back into L1 memory, which means that any sanitisation we did
during guest entry will be exposed to L1 after H_ENTER_NESTED returns.
This patch alters this sanitisation to have effect on the vcpu->arch
registers directly before entering and after exiting the guest,
leaving the structure that is copied back into L1 unchanged (except
when we really want L1 to access the value, e.g the Cause bits of
HFSCR).
Signed-off-by: Fabiano Rosas <farosas@linux.ibm.com>
Reviewed-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/kvm/book3s_hv_nested.c | 94 ++++++++++++++---------------
1 file changed, 46 insertions(+), 48 deletions(-)
diff --git a/arch/powerpc/kvm/book3s_hv_nested.c b/arch/powerpc/kvm/book3s_hv_nested.c
index 898f942eb198..1eb4e989edc7 100644
--- a/arch/powerpc/kvm/book3s_hv_nested.c
+++ b/arch/powerpc/kvm/book3s_hv_nested.c
@@ -105,7 +105,6 @@ static void save_hv_return_state(struct kvm_vcpu *vcpu, int trap,
struct kvmppc_vcore *vc = vcpu->arch.vcore;
hr->dpdes = vc->dpdes;
- hr->hfscr = vcpu->arch.hfscr;
hr->purr = vcpu->arch.purr;
hr->spurr = vcpu->arch.spurr;
hr->ic = vcpu->arch.ic;
@@ -128,55 +127,17 @@ static void save_hv_return_state(struct kvm_vcpu *vcpu, int trap,
case BOOK3S_INTERRUPT_H_INST_STORAGE:
hr->asdr = vcpu->arch.fault_gpa;
break;
+ case BOOK3S_INTERRUPT_H_FAC_UNAVAIL:
+ hr->hfscr = ((~HFSCR_INTR_CAUSE & hr->hfscr) |
+ (HFSCR_INTR_CAUSE & vcpu->arch.hfscr));
+ break;
case BOOK3S_INTERRUPT_H_EMUL_ASSIST:
hr->heir = vcpu->arch.emul_inst;
break;
}
}
-/*
- * This can result in some L0 HV register state being leaked to an L1
- * hypervisor when the hv_guest_state is copied back to the guest after
- * being modified here.
- *
- * There is no known problem with such a leak, and in many cases these
- * register settings could be derived by the guest by observing behaviour
- * and timing, interrupts, etc., but it is an issue to consider.
- */
-static void sanitise_hv_regs(struct kvm_vcpu *vcpu, struct hv_guest_state *hr)
-{
- struct kvmppc_vcore *vc = vcpu->arch.vcore;
- u64 mask;
-
- /*
- * Don't let L1 change LPCR bits for the L2 except these:
- */
- mask = LPCR_DPFD | LPCR_ILE | LPCR_TC | LPCR_AIL | LPCR_LD |
- LPCR_LPES | LPCR_MER;
-
- /*
- * Additional filtering is required depending on hardware
- * and configuration.
- */
- hr->lpcr = kvmppc_filter_lpcr_hv(vcpu->kvm,
- (vc->lpcr & ~mask) | (hr->lpcr & mask));
-
- /*
- * Don't let L1 enable features for L2 which we've disabled for L1,
- * but preserve the interrupt cause field.
- */
- hr->hfscr &= (HFSCR_INTR_CAUSE | vcpu->arch.hfscr);
-
- /* Don't let data address watchpoint match in hypervisor state */
- hr->dawrx0 &= ~DAWRX_HYP;
- hr->dawrx1 &= ~DAWRX_HYP;
-
- /* Don't let completed instruction address breakpt match in HV state */
- if ((hr->ciabr & CIABR_PRIV) == CIABR_PRIV_HYPER)
- hr->ciabr &= ~CIABR_PRIV;
-}
-
-static void restore_hv_regs(struct kvm_vcpu *vcpu, struct hv_guest_state *hr)
+static void restore_hv_regs(struct kvm_vcpu *vcpu, const struct hv_guest_state *hr)
{
struct kvmppc_vcore *vc = vcpu->arch.vcore;
@@ -288,6 +249,43 @@ static int kvmhv_write_guest_state_and_regs(struct kvm_vcpu *vcpu,
sizeof(struct pt_regs));
}
+static void load_l2_hv_regs(struct kvm_vcpu *vcpu,
+ const struct hv_guest_state *l2_hv,
+ const struct hv_guest_state *l1_hv, u64 *lpcr)
+{
+ struct kvmppc_vcore *vc = vcpu->arch.vcore;
+ u64 mask;
+
+ restore_hv_regs(vcpu, l2_hv);
+
+ /*
+ * Don't let L1 change LPCR bits for the L2 except these:
+ */
+ mask = LPCR_DPFD | LPCR_ILE | LPCR_TC | LPCR_AIL | LPCR_LD |
+ LPCR_LPES | LPCR_MER;
+
+ /*
+ * Additional filtering is required depending on hardware
+ * and configuration.
+ */
+ *lpcr = kvmppc_filter_lpcr_hv(vcpu->kvm,
+ (vc->lpcr & ~mask) | (*lpcr & mask));
+
+ /*
+ * Don't let L1 enable features for L2 which we've disabled for L1,
+ * but preserve the interrupt cause field.
+ */
+ vcpu->arch.hfscr = l2_hv->hfscr & (HFSCR_INTR_CAUSE | vcpu->arch.hfscr);
+
+ /* Don't let data address watchpoint match in hypervisor state */
+ vcpu->arch.dawrx0 = l2_hv->dawrx0 & ~DAWRX_HYP;
+ vcpu->arch.dawrx1 = l2_hv->dawrx1 & ~DAWRX_HYP;
+
+ /* Don't let completed instruction address breakpt match in HV state */
+ if ((l2_hv->ciabr & CIABR_PRIV) == CIABR_PRIV_HYPER)
+ vcpu->arch.ciabr = l2_hv->ciabr & ~CIABR_PRIV;
+}
+
long kvmhv_enter_nested_guest(struct kvm_vcpu *vcpu)
{
long int err, r;
@@ -296,7 +294,7 @@ long kvmhv_enter_nested_guest(struct kvm_vcpu *vcpu)
struct hv_guest_state l2_hv = {0}, saved_l1_hv;
struct kvmppc_vcore *vc = vcpu->arch.vcore;
u64 hv_ptr, regs_ptr;
- u64 hdec_exp;
+ u64 hdec_exp, lpcr;
s64 delta_purr, delta_spurr, delta_ic, delta_vtb;
if (vcpu->kvm->arch.l1_ptcr == 0)
@@ -369,8 +367,8 @@ long kvmhv_enter_nested_guest(struct kvm_vcpu *vcpu)
/* Guest must always run with ME enabled, HV disabled. */
vcpu->arch.shregs.msr = (vcpu->arch.regs.msr | MSR_ME) & ~MSR_HV;
- sanitise_hv_regs(vcpu, &l2_hv);
- restore_hv_regs(vcpu, &l2_hv);
+ lpcr = l2_hv.lpcr;
+ load_l2_hv_regs(vcpu, &l2_hv, &saved_l1_hv, &lpcr);
vcpu->arch.ret = RESUME_GUEST;
vcpu->arch.trap = 0;
@@ -380,7 +378,7 @@ long kvmhv_enter_nested_guest(struct kvm_vcpu *vcpu)
r = RESUME_HOST;
break;
}
- r = kvmhv_run_single_vcpu(vcpu, hdec_exp, l2_hv.lpcr);
+ r = kvmhv_run_single_vcpu(vcpu, hdec_exp, lpcr);
} while (is_kvmppc_resume_guest(r));
/* save L2 state for return */
--
2.23.0
^ permalink raw reply related
* [PATCH v2 04/60] KVM: PPC: Book3S HV Nested: Fix TM softpatch HFAC interrupt emulation
From: Nicholas Piggin @ 2021-08-11 16:00 UTC (permalink / raw)
To: kvm-ppc; +Cc: linuxppc-dev, Nicholas Piggin
In-Reply-To: <20210811160134.904987-1-npiggin@gmail.com>
Have the TM softpatch emulation code set up the HFAC interrupt and
return -1 in case an instruction was executed with HFSCR bits clear,
and have the interrupt exit handler fall through to the HFAC handler.
When the L0 is running a nested guest, this ensures the HFAC interrupt
is correctly passed up to the L1.
The "direct guest" exit handler will turn these into PROGILL program
interrupts so functionality in practice will be unchanged. But it's
possible an L1 would want to handle these in a different way.
Also rearrange the FAC interrupt emulation code to match the HFAC format
while here (mainly, adding the FSCR_INTR_CAUSE mask).
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/include/asm/reg.h | 3 ++-
arch/powerpc/kvm/book3s_hv.c | 35 ++++++++++++++++----------
arch/powerpc/kvm/book3s_hv_tm.c | 44 ++++++++++++++++++---------------
3 files changed, 48 insertions(+), 34 deletions(-)
diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index be85cf156a1f..e9d27265253b 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -415,6 +415,7 @@
#define FSCR_TAR __MASK(FSCR_TAR_LG)
#define FSCR_EBB __MASK(FSCR_EBB_LG)
#define FSCR_DSCR __MASK(FSCR_DSCR_LG)
+#define FSCR_INTR_CAUSE (ASM_CONST(0xFF) << 56) /* interrupt cause */
#define SPRN_HFSCR 0xbe /* HV=1 Facility Status & Control Register */
#define HFSCR_PREFIX __MASK(FSCR_PREFIX_LG)
#define HFSCR_MSGP __MASK(FSCR_MSGP_LG)
@@ -426,7 +427,7 @@
#define HFSCR_DSCR __MASK(FSCR_DSCR_LG)
#define HFSCR_VECVSX __MASK(FSCR_VECVSX_LG)
#define HFSCR_FP __MASK(FSCR_FP_LG)
-#define HFSCR_INTR_CAUSE (ASM_CONST(0xFF) << 56) /* interrupt cause */
+#define HFSCR_INTR_CAUSE FSCR_INTR_CAUSE
#define SPRN_TAR 0x32f /* Target Address Register */
#define SPRN_LPCR 0x13E /* LPAR Control Register */
#define LPCR_VPM0 ASM_CONST(0x8000000000000000)
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 2afe7a95fc9c..e79eedb65e6b 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -1682,6 +1682,21 @@ XXX benchmark guest exits
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);
+ if (r != -1)
+ break;
+ fallthrough; /* go to facility unavailable handler */
+#endif
+
/*
* This occurs if the guest (kernel or userspace), does something that
* is prohibited by HFSCR.
@@ -1700,18 +1715,6 @@ XXX benchmark guest exits
}
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;
@@ -1814,9 +1817,15 @@ static int kvmppc_handle_nested_exit(struct kvm_vcpu *vcpu)
* mode and was transitioning to transactional state.
*/
r = kvmhv_p9_tm_emulation(vcpu);
- break;
+ if (r != -1)
+ break;
+ fallthrough; /* go to facility unavailable handler */
#endif
+ case BOOK3S_INTERRUPT_H_FAC_UNAVAIL:
+ r = RESUME_HOST;
+ break;
+
case BOOK3S_INTERRUPT_HV_RM_HARD:
vcpu->arch.trap = 0;
r = RESUME_GUEST;
diff --git a/arch/powerpc/kvm/book3s_hv_tm.c b/arch/powerpc/kvm/book3s_hv_tm.c
index e7c36f8bf205..866cadd70094 100644
--- a/arch/powerpc/kvm/book3s_hv_tm.c
+++ b/arch/powerpc/kvm/book3s_hv_tm.c
@@ -88,14 +88,15 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu)
}
/* 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;
+ vcpu->arch.hfscr &= ~HFSCR_INTR_CAUSE;
+ vcpu->arch.hfscr |= (u64)FSCR_EBB_LG << 56;
+ vcpu->arch.trap = BOOK3S_INTERRUPT_H_FAC_UNAVAIL;
+ return -1; /* rerun host interrupt handler */
}
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);
+ vcpu->arch.fscr &= ~FSCR_INTR_CAUSE;
+ vcpu->arch.fscr |= (u64)FSCR_EBB_LG << 56;
kvmppc_book3s_queue_irqprio(vcpu, BOOK3S_INTERRUPT_FAC_UNAVAIL);
return RESUME_GUEST;
}
@@ -138,14 +139,15 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu)
}
/* 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;
+ vcpu->arch.hfscr &= ~HFSCR_INTR_CAUSE;
+ vcpu->arch.hfscr |= (u64)FSCR_TM_LG << 56;
+ vcpu->arch.trap = BOOK3S_INTERRUPT_H_FAC_UNAVAIL;
+ return -1; /* rerun host interrupt handler */
}
if (!(msr & MSR_TM)) {
/* generate a facility unavailable interrupt */
- vcpu->arch.fscr = (vcpu->arch.fscr & ~(0xffull << 56)) |
- ((u64)FSCR_TM_LG << 56);
+ vcpu->arch.fscr &= ~FSCR_INTR_CAUSE;
+ vcpu->arch.fscr |= (u64)FSCR_TM_LG << 56;
kvmppc_book3s_queue_irqprio(vcpu,
BOOK3S_INTERRUPT_FAC_UNAVAIL);
return RESUME_GUEST;
@@ -169,14 +171,15 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu)
case (PPC_INST_TRECLAIM & PO_XOP_OPCODE_MASK):
/* 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;
+ vcpu->arch.hfscr &= ~HFSCR_INTR_CAUSE;
+ vcpu->arch.hfscr |= (u64)FSCR_TM_LG << 56;
+ vcpu->arch.trap = BOOK3S_INTERRUPT_H_FAC_UNAVAIL;
+ return -1; /* rerun host interrupt handler */
}
if (!(msr & MSR_TM)) {
/* generate a facility unavailable interrupt */
- vcpu->arch.fscr = (vcpu->arch.fscr & ~(0xffull << 56)) |
- ((u64)FSCR_TM_LG << 56);
+ vcpu->arch.fscr &= ~FSCR_INTR_CAUSE;
+ vcpu->arch.fscr |= (u64)FSCR_TM_LG << 56;
kvmppc_book3s_queue_irqprio(vcpu,
BOOK3S_INTERRUPT_FAC_UNAVAIL);
return RESUME_GUEST;
@@ -208,14 +211,15 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu)
/* 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;
+ vcpu->arch.hfscr &= ~HFSCR_INTR_CAUSE;
+ vcpu->arch.hfscr |= (u64)FSCR_TM_LG << 56;
+ vcpu->arch.trap = BOOK3S_INTERRUPT_H_FAC_UNAVAIL;
+ return -1; /* rerun host interrupt handler */
}
if (!(msr & MSR_TM)) {
/* generate a facility unavailable interrupt */
- vcpu->arch.fscr = (vcpu->arch.fscr & ~(0xffull << 56)) |
- ((u64)FSCR_TM_LG << 56);
+ vcpu->arch.fscr &= ~FSCR_INTR_CAUSE;
+ vcpu->arch.fscr |= (u64)FSCR_TM_LG << 56;
kvmppc_book3s_queue_irqprio(vcpu,
BOOK3S_INTERRUPT_FAC_UNAVAIL);
return RESUME_GUEST;
--
2.23.0
^ permalink raw reply related
* [PATCH v2 03/60] KVM: PPC: Book3S HV P9: Fixes for TM softpatch interrupt NIP
From: Nicholas Piggin @ 2021-08-11 16:00 UTC (permalink / raw)
To: kvm-ppc; +Cc: linuxppc-dev, Nicholas Piggin
In-Reply-To: <20210811160134.904987-1-npiggin@gmail.com>
The softpatch interrupt sets HSRR0 to the faulting instruction +4, so
it should subtract 4 for the faulting instruction address in the case
it is a TM softpatch interrupt (the instruction was not executed) and
it was not emulated.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/kvm/book3s_hv_tm.c | 17 +++++++++++++++--
1 file changed, 15 insertions(+), 2 deletions(-)
diff --git a/arch/powerpc/kvm/book3s_hv_tm.c b/arch/powerpc/kvm/book3s_hv_tm.c
index cc90b8b82329..e7c36f8bf205 100644
--- a/arch/powerpc/kvm/book3s_hv_tm.c
+++ b/arch/powerpc/kvm/book3s_hv_tm.c
@@ -46,6 +46,15 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu)
u64 newmsr, bescr;
int ra, rs;
+ /*
+ * The TM softpatch interrupt sets NIP to the instruction following
+ * the faulting instruction, which is not executed. Rewind nip to the
+ * faulting instruction so it looks like a normal synchronous
+ * interrupt, then update nip in the places where the instruction is
+ * emulated.
+ */
+ vcpu->arch.regs.nip -= 4;
+
/*
* rfid, rfebb, and mtmsrd encode bit 31 = 0 since it's a reserved bit
* in these instructions, so masking bit 31 out doesn't change these
@@ -67,7 +76,7 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu)
(newmsr & MSR_TM)));
newmsr = sanitize_msr(newmsr);
vcpu->arch.shregs.msr = newmsr;
- vcpu->arch.cfar = vcpu->arch.regs.nip - 4;
+ vcpu->arch.cfar = vcpu->arch.regs.nip;
vcpu->arch.regs.nip = vcpu->arch.shregs.srr0;
return RESUME_GUEST;
@@ -100,7 +109,7 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu)
vcpu->arch.bescr = bescr;
msr = (msr & ~MSR_TS_MASK) | MSR_TS_T;
vcpu->arch.shregs.msr = msr;
- vcpu->arch.cfar = vcpu->arch.regs.nip - 4;
+ vcpu->arch.cfar = vcpu->arch.regs.nip;
vcpu->arch.regs.nip = vcpu->arch.ebbrr;
return RESUME_GUEST;
@@ -116,6 +125,7 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu)
newmsr = (newmsr & ~MSR_LE) | (msr & MSR_LE);
newmsr = sanitize_msr(newmsr);
vcpu->arch.shregs.msr = newmsr;
+ vcpu->arch.regs.nip += 4;
return RESUME_GUEST;
/* ignore bit 31, see comment above */
@@ -152,6 +162,7 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu)
msr = (msr & ~MSR_TS_MASK) | MSR_TS_S;
}
vcpu->arch.shregs.msr = msr;
+ vcpu->arch.regs.nip += 4;
return RESUME_GUEST;
/* ignore bit 31, see comment above */
@@ -189,6 +200,7 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu)
vcpu->arch.regs.ccr = (vcpu->arch.regs.ccr & 0x0fffffff) |
(((msr & MSR_TS_MASK) >> MSR_TS_S_LG) << 29);
vcpu->arch.shregs.msr &= ~MSR_TS_MASK;
+ vcpu->arch.regs.nip += 4;
return RESUME_GUEST;
/* ignore bit 31, see comment above */
@@ -220,6 +232,7 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu)
vcpu->arch.regs.ccr = (vcpu->arch.regs.ccr & 0x0fffffff) |
(((msr & MSR_TS_MASK) >> MSR_TS_S_LG) << 29);
vcpu->arch.shregs.msr = msr | MSR_TS_S;
+ vcpu->arch.regs.nip += 4;
return RESUME_GUEST;
}
--
2.23.0
^ permalink raw reply related
* [PATCH v2 02/60] KVM: PPC: Book3S HV: Remove TM emulation from POWER7/8 path
From: Nicholas Piggin @ 2021-08-11 16:00 UTC (permalink / raw)
To: kvm-ppc; +Cc: linuxppc-dev, Nicholas Piggin
In-Reply-To: <20210811160134.904987-1-npiggin@gmail.com>
TM fake-suspend emulation is only used by POWER9. Remove it from the old
code path.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/kvm/book3s_hv_rmhandlers.S | 42 -------------------------
1 file changed, 42 deletions(-)
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 8dd437d7a2c6..75079397c2a5 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -1088,12 +1088,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
cmpwi r12, BOOK3S_INTERRUPT_H_INST_STORAGE
beq kvmppc_hisi
-#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
-
/* See if this is a leftover HDEC interrupt */
cmpwi r12,BOOK3S_INTERRUPT_HV_DECREMENTER
bne 2f
@@ -1599,42 +1593,6 @@ maybe_reenter_guest:
blt deliver_guest_interrupt
b guest_exit_cont
-#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
--
2.23.0
^ permalink raw reply related
* [PATCH v2 01/60] KVM: PPC: Book3S HV: Initialise vcpu MSR with MSR_ME
From: Nicholas Piggin @ 2021-08-11 16:00 UTC (permalink / raw)
To: kvm-ppc; +Cc: Alexey Kardashevskiy, linuxppc-dev, Nicholas Piggin
In-Reply-To: <20210811160134.904987-1-npiggin@gmail.com>
It is possible to create a VCPU without setting the MSR before running
it, which results in a warning in kvmhv_vcpu_entry_p9() that MSR_ME is
not set. This is pretty harmless because the MSR_ME bit is added to
HSRR1 before HRFID to guest, and a normal qemu guest doesn't hit it.
Initialise the vcpu MSR with MSR_ME set.
Reported-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/kvm/book3s_hv.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index ce7ff12cfc03..2afe7a95fc9c 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -2687,6 +2687,7 @@ static int kvmppc_core_vcpu_create_hv(struct kvm_vcpu *vcpu)
spin_lock_init(&vcpu->arch.vpa_update_lock);
spin_lock_init(&vcpu->arch.tbacct_lock);
vcpu->arch.busy_preempt = TB_NIL;
+ vcpu->arch.shregs.msr = MSR_ME;
vcpu->arch.intr_msr = MSR_SF | MSR_ME;
/*
--
2.23.0
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox