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

Pull kvm fixes from Paolo Bonzini:
 "RISC-V:

   - Fix VM hang in case of timer delta being zero

 ARM:

   - MMU fixes:

      - Read the MMU notifier seq before dropping the mmap lock to guard
        against reading a potentially stale VMA

      - Disable interrupts when walking user page tables to protect
        against the page table being freed

      - Read the MTE permissions for the VMA within the mmap lock
        critical section, avoiding the use of a potentally stale VMA
        pointer

   - vPMU fixes:

      - Return the sum of the current perf event value and PMC snapshot
        for reads from userspace

      - Don't save the value of guest writes to PMCR_EL0.{C,P}, which
        could otherwise lead to userspace erroneously resetting the vPMU
        during VM save/restore"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
  riscv/kvm: Fix VM hang in case of timer delta being zero.
  KVM: arm64: Check for kvm_vma_mte_allowed in the critical section
  KVM: arm64: Disable interrupts while walking userspace PTs
  KVM: arm64: Retry fault if vma_lookup() results become invalid
  KVM: arm64: PMU: Don't save PMCR_EL0.{C,P} for the vCPU
  KVM: arm64: PMU: Fix GET_ONE_REG for vPMC regs to return the current value

arch/arm64/kvm/mmu.c

@@ -666,14 +666,33 @@ static int get_user_mapping_size(struct kvm *kvm, u64 addr)
 				   CONFIG_PGTABLE_LEVELS),
 		.mm_ops		= &kvm_user_mm_ops,
 	};
+	unsigned long flags;
 	kvm_pte_t pte = 0;	/* Keep GCC quiet... */
 	u32 level = ~0;
 	int ret;
 
+	/*
+	 * Disable IRQs so that we hazard against a concurrent
+	 * teardown of the userspace page tables (which relies on
+	 * IPI-ing threads).
+	 */
+	local_irq_save(flags);
 	ret = kvm_pgtable_get_leaf(&pgt, addr, &pte, &level);
-	VM_BUG_ON(ret);
-	VM_BUG_ON(level >= KVM_PGTABLE_MAX_LEVELS);
-	VM_BUG_ON(!(pte & PTE_VALID));
+	local_irq_restore(flags);
+
+	if (ret)
+		return ret;
+
+	/*
+	 * Not seeing an error, but not updating level? Something went
+	 * deeply wrong...
+	 */
+	if (WARN_ON(level >= KVM_PGTABLE_MAX_LEVELS))
+		return -EFAULT;
+
+	/* Oops, the userspace PTs are gone... Replay the fault */
+	if (!kvm_pte_valid(pte))
+		return -EAGAIN;
 
 	return BIT(ARM64_HW_PGTABLE_LEVEL_SHIFT(level));
 }
@@ -1079,7 +1098,7 @@ static bool fault_supports_stage2_huge_mapping(struct kvm_memory_slot *memslot,
  *
  * Returns the size of the mapping.
  */
-static unsigned long
+static long
 transparent_hugepage_adjust(struct kvm *kvm, struct kvm_memory_slot *memslot,
 			    unsigned long hva, kvm_pfn_t *pfnp,
 			    phys_addr_t *ipap)
@@ -1091,8 +1110,15 @@ transparent_hugepage_adjust(struct kvm *kvm, struct kvm_memory_slot *memslot,
 	 * sure that the HVA and IPA are sufficiently aligned and that the
 	 * block map is contained within the memslot.
 	 */
-	if (fault_supports_stage2_huge_mapping(memslot, hva, PMD_SIZE) &&
-	    get_user_mapping_size(kvm, hva) >= PMD_SIZE) {
+	if (fault_supports_stage2_huge_mapping(memslot, hva, PMD_SIZE)) {
+		int sz = get_user_mapping_size(kvm, hva);
+
+		if (sz < 0)
+			return sz;
+
+		if (sz < PMD_SIZE)
+			return PAGE_SIZE;
+
 		/*
 		 * The address we faulted on is backed by a transparent huge
 		 * page.  However, because we map the compound huge page and
@@ -1192,7 +1218,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 {
 	int ret = 0;
 	bool write_fault, writable, force_pte = false;
-	bool exec_fault;
+	bool exec_fault, mte_allowed;
 	bool device = false;
 	unsigned long mmu_seq;
 	struct kvm *kvm = vcpu->kvm;
@@ -1203,7 +1229,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	kvm_pfn_t pfn;
 	bool logging_active = memslot_is_logging(memslot);
 	unsigned long fault_level = kvm_vcpu_trap_get_fault_level(vcpu);
-	unsigned long vma_pagesize, fault_granule;
+	long vma_pagesize, fault_granule;
 	enum kvm_pgtable_prot prot = KVM_PGTABLE_PROT_R;
 	struct kvm_pgtable *pgt;
 
@@ -1217,6 +1243,20 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 		return -EFAULT;
 	}
 
+	/*
+	 * Permission faults just need to update the existing leaf entry,
+	 * and so normally don't require allocations from the memcache. The
+	 * only exception to this is when dirty logging is enabled at runtime
+	 * and a write fault needs to collapse a block entry into a table.
+	 */
+	if (fault_status != ESR_ELx_FSC_PERM ||
+	    (logging_active && write_fault)) {
+		ret = kvm_mmu_topup_memory_cache(memcache,
+						 kvm_mmu_cache_min_pages(kvm));
+		if (ret)
+			return ret;
+	}
+
 	/*
 	 * Let's check if we will get back a huge page backed by hugetlbfs, or
 	 * get block mapping for device MMIO region.
@@ -1269,37 +1309,21 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 		fault_ipa &= ~(vma_pagesize - 1);
 
 	gfn = fault_ipa >> PAGE_SHIFT;
-	mmap_read_unlock(current->mm);
+	mte_allowed = kvm_vma_mte_allowed(vma);
 
-	/*
-	 * Permission faults just need to update the existing leaf entry,
-	 * and so normally don't require allocations from the memcache. The
-	 * only exception to this is when dirty logging is enabled at runtime
-	 * and a write fault needs to collapse a block entry into a table.
-	 */
-	if (fault_status != ESR_ELx_FSC_PERM ||
-	    (logging_active && write_fault)) {
-		ret = kvm_mmu_topup_memory_cache(memcache,
-						 kvm_mmu_cache_min_pages(kvm));
-		if (ret)
-			return ret;
-	}
+	/* Don't use the VMA after the unlock -- it may have vanished */
+	vma = NULL;
 
-	mmu_seq = vcpu->kvm->mmu_invalidate_seq;
 	/*
-	 * Ensure the read of mmu_invalidate_seq happens before we call
-	 * gfn_to_pfn_prot (which calls get_user_pages), so that we don't risk
-	 * the page we just got a reference to gets unmapped before we have a
-	 * chance to grab the mmu_lock, which ensure that if the page gets
-	 * unmapped afterwards, the call to kvm_unmap_gfn will take it away
-	 * from us again properly. This smp_rmb() interacts with the smp_wmb()
-	 * in kvm_mmu_notifier_invalidate_<page|range_end>.
+	 * Read mmu_invalidate_seq so that KVM can detect if the results of
+	 * vma_lookup() or __gfn_to_pfn_memslot() become stale prior to
+	 * acquiring kvm->mmu_lock.
 	 *
-	 * Besides, __gfn_to_pfn_memslot() instead of gfn_to_pfn_prot() is
-	 * used to avoid unnecessary overhead introduced to locate the memory
-	 * slot because it's always fixed even @gfn is adjusted for huge pages.
+	 * Rely on mmap_read_unlock() for an implicit smp_rmb(), which pairs
+	 * with the smp_wmb() in kvm_mmu_invalidate_end().
 	 */
-	smp_rmb();
+	mmu_seq = vcpu->kvm->mmu_invalidate_seq;
+	mmap_read_unlock(current->mm);
 
 	pfn = __gfn_to_pfn_memslot(memslot, gfn, false, false, NULL,
 				   write_fault, &writable, NULL);
@@ -1350,11 +1374,16 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 			vma_pagesize = transparent_hugepage_adjust(kvm, memslot,
 								   hva, &pfn,
 								   &fault_ipa);
+
+		if (vma_pagesize < 0) {
+			ret = vma_pagesize;
+			goto out_unlock;
+		}
 	}
 
 	if (fault_status != ESR_ELx_FSC_PERM && !device && kvm_has_mte(kvm)) {
 		/* Check the VMM hasn't introduced a new disallowed VMA */
-		if (kvm_vma_mte_allowed(vma)) {
+		if (mte_allowed) {
 			sanitise_mte_tags(kvm, pfn, vma_pagesize);
 		} else {
 			ret = -EFAULT;

arch/arm64/kvm/pmu-emul.c

@@ -538,7 +538,8 @@ void kvm_pmu_handle_pmcr(struct kvm_vcpu *vcpu, u64 val)
 	if (!kvm_pmu_is_3p5(vcpu))
 		val &= ~ARMV8_PMU_PMCR_LP;
 
-	__vcpu_sys_reg(vcpu, PMCR_EL0) = val;
+	/* The reset bits don't indicate any state, and shouldn't be saved. */
+	__vcpu_sys_reg(vcpu, PMCR_EL0) = val & ~(ARMV8_PMU_PMCR_C | ARMV8_PMU_PMCR_P);
 
 	if (val & ARMV8_PMU_PMCR_E) {
 		kvm_pmu_enable_counter_mask(vcpu,

arch/arm64/kvm/sys_regs.c

@@ -856,6 +856,22 @@ static bool pmu_counter_idx_valid(struct kvm_vcpu *vcpu, u64 idx)
 	return true;
 }
 
+static int get_pmu_evcntr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r,
+			  u64 *val)
+{
+	u64 idx;
+
+	if (r->CRn == 9 && r->CRm == 13 && r->Op2 == 0)
+		/* PMCCNTR_EL0 */
+		idx = ARMV8_PMU_CYCLE_IDX;
+	else
+		/* PMEVCNTRn_EL0 */
+		idx = ((r->CRm & 3) << 3) | (r->Op2 & 7);
+
+	*val = kvm_pmu_get_counter_value(vcpu, idx);
+	return 0;
+}
+
 static bool access_pmu_evcntr(struct kvm_vcpu *vcpu,
 			      struct sys_reg_params *p,
 			      const struct sys_reg_desc *r)
@@ -1072,7 +1088,7 @@ static bool access_pmuserenr(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 /* Macro to expand the PMEVCNTRn_EL0 register */
 #define PMU_PMEVCNTR_EL0(n)						\
 	{ PMU_SYS_REG(SYS_PMEVCNTRn_EL0(n)),				\
-	  .reset = reset_pmevcntr,					\
+	  .reset = reset_pmevcntr, .get_user = get_pmu_evcntr,		\
 	  .access = access_pmu_evcntr, .reg = (PMEVCNTR0_EL0 + n), }
 
 /* Macro to expand the PMEVTYPERn_EL0 register */
@@ -1982,7 +1998,8 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	{ PMU_SYS_REG(SYS_PMCEID1_EL0),
 	  .access = access_pmceid, .reset = NULL },
 	{ PMU_SYS_REG(SYS_PMCCNTR_EL0),
-	  .access = access_pmu_evcntr, .reset = reset_unknown, .reg = PMCCNTR_EL0 },
+	  .access = access_pmu_evcntr, .reset = reset_unknown,
+	  .reg = PMCCNTR_EL0, .get_user = get_pmu_evcntr},
 	{ PMU_SYS_REG(SYS_PMXEVTYPER_EL0),
 	  .access = access_pmu_evtyper, .reset = NULL },
 	{ PMU_SYS_REG(SYS_PMXEVCNTR_EL0),

arch/riscv/kvm/vcpu_timer.c

@@ -147,10 +147,8 @@ static void kvm_riscv_vcpu_timer_blocking(struct kvm_vcpu *vcpu)
 		return;
 
 	delta_ns = kvm_riscv_delta_cycles2ns(t->next_cycles, gt, t);
-	if (delta_ns) {
-		hrtimer_start(&t->hrt, ktime_set(0, delta_ns), HRTIMER_MODE_REL);
-		t->next_set = true;
-	}
+	hrtimer_start(&t->hrt, ktime_set(0, delta_ns), HRTIMER_MODE_REL);
+	t->next_set = true;
 }
 
 static void kvm_riscv_vcpu_timer_unblocking(struct kvm_vcpu *vcpu)