Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull more kvm updates from Paolo Bonzini:
 "The main batch of ARM + RISC-V changes, and a few fixes and cleanups
  for x86 (PMU virtualization and selftests).

  ARM:

   - Fixes for single-stepping in the presence of an async exception as
     well as the preservation of PSTATE.SS

   - Better handling of AArch32 ID registers on AArch64-only systems

   - Fixes for the dirty-ring API, allowing it to work on architectures
     with relaxed memory ordering

   - Advertise the new kvmarm mailing list

   - Various minor cleanups and spelling fixes

  RISC-V:

   - Improved instruction encoding infrastructure for instructions not
     yet supported by binutils

   - Svinval support for both KVM Host and KVM Guest

   - Zihintpause support for KVM Guest

   - Zicbom support for KVM Guest

   - Record number of signal exits as a VCPU stat

   - Use generic guest entry infrastructure

  x86:

   - Misc PMU fixes and cleanups.

   - selftests: fixes for Hyper-V hypercall

   - selftests: fix nx_huge_pages_test on TDP-disabled hosts

   - selftests: cleanups for fix_hypercall_test"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (57 commits)
  riscv: select HAVE_POSIX_CPU_TIMERS_TASK_WORK
  RISC-V: KVM: Use generic guest entry infrastructure
  RISC-V: KVM: Record number of signal exits as a vCPU stat
  RISC-V: KVM: add __init annotation to riscv_kvm_init()
  RISC-V: KVM: Expose Zicbom to the guest
  RISC-V: KVM: Provide UAPI for Zicbom block size
  RISC-V: KVM: Make ISA ext mappings explicit
  RISC-V: KVM: Allow Guest use Zihintpause extension
  RISC-V: KVM: Allow Guest use Svinval extension
  RISC-V: KVM: Use Svinval for local TLB maintenance when available
  RISC-V: Probe Svinval extension form ISA string
  RISC-V: KVM: Change the SBI specification version to v1.0
  riscv: KVM: Apply insn-def to hlv encodings
  riscv: KVM: Apply insn-def to hfence encodings
  riscv: Introduce support for defining instructions
  riscv: Add X register names to gpr-nums
  KVM: arm64: Advertise new kvmarm mailing list
  kvm: vmx: keep constant definition format consistent
  kvm: mmu: fix typos in struct kvm_arch
  KVM: selftests: Fix nx_huge_pages_test on TDP-disabled hosts
  ...

6 files changed, 59 insertions, 124 deletions

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 61b9dd34d333..7551b6f9c31c 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1280,8 +1280,8 @@ struct kvm_arch {
 	bool tdp_mmu_enabled;
 
 	/*
-	 * List of struct kvm_mmu_pages being used as roots.
-	 * All struct kvm_mmu_pages in the list should have
+	 * List of kvm_mmu_page structs being used as roots.
+	 * All kvm_mmu_page structs in the list should have
 	 * tdp_mmu_page set.
 	 *
 	 * For reads, this list is protected by:
@@ -1300,8 +1300,8 @@ struct kvm_arch {
 	struct list_head tdp_mmu_roots;
 
 	/*
-	 * List of struct kvmp_mmu_pages not being used as roots.
-	 * All struct kvm_mmu_pages in the list should have
+	 * List of kvm_mmu_page structs not being used as roots.
+	 * All kvm_mmu_page structs in the list should have
 	 * tdp_mmu_page set and a tdp_mmu_root_count of 0.
 	 */
 	struct list_head tdp_mmu_pages;
@@ -1311,9 +1311,9 @@ struct kvm_arch {
 	 * is held in read mode:
 	 *  - tdp_mmu_roots (above)
 	 *  - tdp_mmu_pages (above)
-	 *  - the link field of struct kvm_mmu_pages used by the TDP MMU
+	 *  - the link field of kvm_mmu_page structs used by the TDP MMU
 	 *  - lpage_disallowed_mmu_pages
-	 *  - the lpage_disallowed_link field of struct kvm_mmu_pages used
+	 *  - the lpage_disallowed_link field of kvm_mmu_page structs used
 	 *    by the TDP MMU
 	 * It is acceptable, but not necessary, to acquire this lock when
 	 * the thread holds the MMU lock in write mode.
diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h
index c371ef695fcc..498dc600bd5c 100644
--- a/arch/x86/include/asm/vmx.h
+++ b/arch/x86/include/asm/vmx.h
@@ -309,7 +309,7 @@ enum vmcs_field {
 	GUEST_LDTR_AR_BYTES             = 0x00004820,
 	GUEST_TR_AR_BYTES               = 0x00004822,
 	GUEST_INTERRUPTIBILITY_INFO     = 0x00004824,
-	GUEST_ACTIVITY_STATE            = 0X00004826,
+	GUEST_ACTIVITY_STATE            = 0x00004826,
 	GUEST_SYSENTER_CS               = 0x0000482A,
 	VMX_PREEMPTION_TIMER_VALUE      = 0x0000482E,
 	HOST_IA32_SYSENTER_CS           = 0x00004c00,
diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
index e3cbd7706136..67be7f217e37 100644
--- a/arch/x86/kvm/Kconfig
+++ b/arch/x86/kvm/Kconfig
@@ -28,7 +28,8 @@ config KVM
 	select HAVE_KVM_IRQCHIP
 	select HAVE_KVM_PFNCACHE
 	select HAVE_KVM_IRQFD
-	select HAVE_KVM_DIRTY_RING
+	select HAVE_KVM_DIRTY_RING_TSO
+	select HAVE_KVM_DIRTY_RING_ACQ_REL
 	select IRQ_BYPASS_MANAGER
 	select HAVE_KVM_IRQ_BYPASS
 	select HAVE_KVM_IRQ_ROUTING
diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c
index 02f9e4f245bd..d9b9a0f0db17 100644
--- a/arch/x86/kvm/pmu.c
+++ b/arch/x86/kvm/pmu.c
@@ -106,9 +106,19 @@ static inline void __kvm_perf_overflow(struct kvm_pmc *pmc, bool in_pmi)
 		return;
 
 	if (pmc->perf_event && pmc->perf_event->attr.precise_ip) {
-		/* Indicate PEBS overflow PMI to guest. */
-		skip_pmi = __test_and_set_bit(GLOBAL_STATUS_BUFFER_OVF_BIT,
-					      (unsigned long *)&pmu->global_status);
+		if (!in_pmi) {
+			/*
+			 * TODO: KVM is currently _choosing_ to not generate records
+			 * for emulated instructions, avoiding BUFFER_OVF PMI when
+			 * there are no records. Strictly speaking, it should be done
+			 * as well in the right context to improve sampling accuracy.
+			 */
+			skip_pmi = true;
+		} else {
+			/* Indicate PEBS overflow PMI to guest. */
+			skip_pmi = __test_and_set_bit(GLOBAL_STATUS_BUFFER_OVF_BIT,
+						      (unsigned long *)&pmu->global_status);
+		}
 	} else {
 		__set_bit(pmc->idx, (unsigned long *)&pmu->global_status);
 	}
@@ -227,8 +237,8 @@ static bool pmc_resume_counter(struct kvm_pmc *pmc)
 			      get_sample_period(pmc, pmc->counter)))
 		return false;
 
-	if (!test_bit(pmc->idx, (unsigned long *)&pmc_to_pmu(pmc)->pebs_enable) &&
-	    pmc->perf_event->attr.precise_ip)
+	if (test_bit(pmc->idx, (unsigned long *)&pmc_to_pmu(pmc)->pebs_enable) !=
+	    (!!pmc->perf_event->attr.precise_ip))
 		return false;
 
 	/* reuse perf_event to serve as pmc_reprogram_counter() does*/
diff --git a/arch/x86/kvm/svm/pmu.c b/arch/x86/kvm/svm/pmu.c
index f24613a108c5..b68956299fa8 100644
--- a/arch/x86/kvm/svm/pmu.c
+++ b/arch/x86/kvm/svm/pmu.c
@@ -23,107 +23,52 @@ enum pmu_type {
 	PMU_TYPE_EVNTSEL,
 };
 
-enum index {
-	INDEX_ZERO = 0,
-	INDEX_ONE,
-	INDEX_TWO,
-	INDEX_THREE,
-	INDEX_FOUR,
-	INDEX_FIVE,
-	INDEX_ERROR,
-};
-
-static unsigned int get_msr_base(struct kvm_pmu *pmu, enum pmu_type type)
+static struct kvm_pmc *amd_pmc_idx_to_pmc(struct kvm_pmu *pmu, int pmc_idx)
 {
-	struct kvm_vcpu *vcpu = pmu_to_vcpu(pmu);
+	unsigned int num_counters = pmu->nr_arch_gp_counters;
 
-	if (guest_cpuid_has(vcpu, X86_FEATURE_PERFCTR_CORE)) {
-		if (type == PMU_TYPE_COUNTER)
-			return MSR_F15H_PERF_CTR;
-		else
-			return MSR_F15H_PERF_CTL;
-	} else {
-		if (type == PMU_TYPE_COUNTER)
-			return MSR_K7_PERFCTR0;
-		else
-			return MSR_K7_EVNTSEL0;
-	}
-}
+	if (pmc_idx >= num_counters)
+		return NULL;
 
-static enum index msr_to_index(u32 msr)
-{
-	switch (msr) {
-	case MSR_F15H_PERF_CTL0:
-	case MSR_F15H_PERF_CTR0:
-	case MSR_K7_EVNTSEL0:
-	case MSR_K7_PERFCTR0:
-		return INDEX_ZERO;
-	case MSR_F15H_PERF_CTL1:
-	case MSR_F15H_PERF_CTR1:
-	case MSR_K7_EVNTSEL1:
-	case MSR_K7_PERFCTR1:
-		return INDEX_ONE;
-	case MSR_F15H_PERF_CTL2:
-	case MSR_F15H_PERF_CTR2:
-	case MSR_K7_EVNTSEL2:
-	case MSR_K7_PERFCTR2:
-		return INDEX_TWO;
-	case MSR_F15H_PERF_CTL3:
-	case MSR_F15H_PERF_CTR3:
-	case MSR_K7_EVNTSEL3:
-	case MSR_K7_PERFCTR3:
-		return INDEX_THREE;
-	case MSR_F15H_PERF_CTL4:
-	case MSR_F15H_PERF_CTR4:
-		return INDEX_FOUR;
-	case MSR_F15H_PERF_CTL5:
-	case MSR_F15H_PERF_CTR5:
-		return INDEX_FIVE;
-	default:
-		return INDEX_ERROR;
-	}
+	return &pmu->gp_counters[array_index_nospec(pmc_idx, num_counters)];
 }
 
 static inline struct kvm_pmc *get_gp_pmc_amd(struct kvm_pmu *pmu, u32 msr,
 					     enum pmu_type type)
 {
 	struct kvm_vcpu *vcpu = pmu_to_vcpu(pmu);
+	unsigned int idx;
 
 	if (!vcpu->kvm->arch.enable_pmu)
 		return NULL;
 
 	switch (msr) {
-	case MSR_F15H_PERF_CTL0:
-	case MSR_F15H_PERF_CTL1:
-	case MSR_F15H_PERF_CTL2:
-	case MSR_F15H_PERF_CTL3:
-	case MSR_F15H_PERF_CTL4:
-	case MSR_F15H_PERF_CTL5:
+	case MSR_F15H_PERF_CTL0 ... MSR_F15H_PERF_CTR5:
 		if (!guest_cpuid_has(vcpu, X86_FEATURE_PERFCTR_CORE))
 			return NULL;
-		fallthrough;
+		/*
+		 * Each PMU counter has a pair of CTL and CTR MSRs. CTLn
+		 * MSRs (accessed via EVNTSEL) are even, CTRn MSRs are odd.
+		 */
+		idx = (unsigned int)((msr - MSR_F15H_PERF_CTL0) / 2);
+		if (!(msr & 0x1) != (type == PMU_TYPE_EVNTSEL))
+			return NULL;
+		break;
 	case MSR_K7_EVNTSEL0 ... MSR_K7_EVNTSEL3:
 		if (type != PMU_TYPE_EVNTSEL)
 			return NULL;
+		idx = msr - MSR_K7_EVNTSEL0;
 		break;
-	case MSR_F15H_PERF_CTR0:
-	case MSR_F15H_PERF_CTR1:
-	case MSR_F15H_PERF_CTR2:
-	case MSR_F15H_PERF_CTR3:
-	case MSR_F15H_PERF_CTR4:
-	case MSR_F15H_PERF_CTR5:
-		if (!guest_cpuid_has(vcpu, X86_FEATURE_PERFCTR_CORE))
-			return NULL;
-		fallthrough;
 	case MSR_K7_PERFCTR0 ... MSR_K7_PERFCTR3:
 		if (type != PMU_TYPE_COUNTER)
 			return NULL;
+		idx = msr - MSR_K7_PERFCTR0;
 		break;
 	default:
 		return NULL;
 	}
 
-	return &pmu->gp_counters[msr_to_index(msr)];
+	return amd_pmc_idx_to_pmc(pmu, idx);
 }
 
 static bool amd_hw_event_available(struct kvm_pmc *pmc)
@@ -139,22 +84,6 @@ static bool amd_pmc_is_enabled(struct kvm_pmc *pmc)
 	return true;
 }
 
-static struct kvm_pmc *amd_pmc_idx_to_pmc(struct kvm_pmu *pmu, int pmc_idx)
-{
-	unsigned int base = get_msr_base(pmu, PMU_TYPE_COUNTER);
-	struct kvm_vcpu *vcpu = pmu_to_vcpu(pmu);
-
-	if (guest_cpuid_has(vcpu, X86_FEATURE_PERFCTR_CORE)) {
-		/*
-		 * The idx is contiguous. The MSRs are not. The counter MSRs
-		 * are interleaved with the event select MSRs.
-		 */
-		pmc_idx *= 2;
-	}
-
-	return get_gp_pmc_amd(pmu, base + pmc_idx, PMU_TYPE_COUNTER);
-}
-
 static bool amd_is_valid_rdpmc_ecx(struct kvm_vcpu *vcpu, unsigned int idx)
 {
 	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
@@ -168,15 +97,7 @@ static bool amd_is_valid_rdpmc_ecx(struct kvm_vcpu *vcpu, unsigned int idx)
 static struct kvm_pmc *amd_rdpmc_ecx_to_pmc(struct kvm_vcpu *vcpu,
 	unsigned int idx, u64 *mask)
 {
-	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
-	struct kvm_pmc *counters;
-
-	idx &= ~(3u << 30);
-	if (idx >= pmu->nr_arch_gp_counters)
-		return NULL;
-	counters = pmu->gp_counters;
-
-	return &counters[idx];
+	return amd_pmc_idx_to_pmc(vcpu_to_pmu(vcpu), idx & ~(3u << 30));
 }
 
 static bool amd_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr)
diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c
index c399637a3a79..25b70a85bef5 100644
--- a/arch/x86/kvm/vmx/pmu_intel.c
+++ b/arch/x86/kvm/vmx/pmu_intel.c
@@ -68,15 +68,11 @@ static struct kvm_pmc *intel_pmc_idx_to_pmc(struct kvm_pmu *pmu, int pmc_idx)
 	}
 }
 
-/* function is called when global control register has been updated. */
-static void global_ctrl_changed(struct kvm_pmu *pmu, u64 data)
+static void reprogram_counters(struct kvm_pmu *pmu, u64 diff)
 {
 	int bit;
-	u64 diff = pmu->global_ctrl ^ data;
 	struct kvm_pmc *pmc;
 
-	pmu->global_ctrl = data;
-
 	for_each_set_bit(bit, (unsigned long *)&diff, X86_PMC_IDX_MAX) {
 		pmc = intel_pmc_idx_to_pmc(pmu, bit);
 		if (pmc)
@@ -397,7 +393,7 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	struct kvm_pmc *pmc;
 	u32 msr = msr_info->index;
 	u64 data = msr_info->data;
-	u64 reserved_bits;
+	u64 reserved_bits, diff;
 
 	switch (msr) {
 	case MSR_CORE_PERF_FIXED_CTR_CTRL:
@@ -418,7 +414,9 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		if (pmu->global_ctrl == data)
 			return 0;
 		if (kvm_valid_perf_global_ctrl(pmu, data)) {
-			global_ctrl_changed(pmu, data);
+			diff = pmu->global_ctrl ^ data;
+			pmu->global_ctrl = data;
+			reprogram_counters(pmu, diff);
 			return 0;
 		}
 		break;
@@ -433,7 +431,9 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		if (pmu->pebs_enable == data)
 			return 0;
 		if (!(data & pmu->pebs_enable_mask)) {
+			diff = pmu->pebs_enable ^ data;
 			pmu->pebs_enable = data;
+			reprogram_counters(pmu, diff);
 			return 0;
 		}
 		break;
@@ -776,20 +776,23 @@ static void intel_pmu_cleanup(struct kvm_vcpu *vcpu)
 void intel_pmu_cross_mapped_check(struct kvm_pmu *pmu)
 {
 	struct kvm_pmc *pmc = NULL;
-	int bit;
+	int bit, hw_idx;
 
 	for_each_set_bit(bit, (unsigned long *)&pmu->global_ctrl,
 			 X86_PMC_IDX_MAX) {
 		pmc = intel_pmc_idx_to_pmc(pmu, bit);
 
 		if (!pmc || !pmc_speculative_in_use(pmc) ||
-		    !intel_pmc_is_enabled(pmc))
+		    !intel_pmc_is_enabled(pmc) || !pmc->perf_event)
 			continue;
 
-		if (pmc->perf_event && pmc->idx != pmc->perf_event->hw.idx) {
-			pmu->host_cross_mapped_mask |=
-				BIT_ULL(pmc->perf_event->hw.idx);
-		}
+		/*
+		 * A negative index indicates the event isn't mapped to a
+		 * physical counter in the host, e.g. due to contention.
+		 */
+		hw_idx = pmc->perf_event->hw.idx;
+		if (hw_idx != pmc->idx && hw_idx > -1)
+			pmu->host_cross_mapped_mask |= BIT_ULL(hw_idx);
 	}
 }