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

Pull kvm fixes from Paolo Bonzini:
 "ARM64:

   - Fix the guest view of the ID registers, making the relevant fields
     writable from userspace (affecting ID_AA64DFR0_EL1 and
     ID_AA64PFR1_EL1)

   - Correcly expose S1PIE to guests, fixing a regression introduced in
     6.12-rc1 with the S1POE support

   - Fix the recycling of stage-2 shadow MMUs by tracking the context
     (are we allowed to block or not) as well as the recycling state

   - Address a couple of issues with the vgic when userspace
     misconfigures the emulation, resulting in various splats. Headaches
     courtesy of our Syzkaller friends

   - Stop wasting space in the HYP idmap, as we are dangerously close to
     the 4kB limit, and this has already exploded in -next

   - Fix another race in vgic_init()

   - Fix a UBSAN error when faking the cache topology with MTE enabled

  RISCV:

   - RISCV: KVM: use raw_spinlock for critical section in imsic

  x86:

   - A bandaid for lack of XCR0 setup in selftests, which causes trouble
     if the compiler is configured to have x86-64-v3 (with AVX) as the
     default ISA. Proper XCR0 setup will come in the next merge window.

   - Fix an issue where KVM would not ignore low bits of the nested CR3
     and potentially leak up to 31 bytes out of the guest memory's
     bounds

   - Fix case in which an out-of-date cached value for the segments
     could by returned by KVM_GET_SREGS.

   - More cleanups for KVM_X86_QUIRK_SLOT_ZAP_ALL

   - Override MTRR state for KVM confidential guests, making it WB by
     default as is already the case for Hyper-V guests.

  Generic:

   - Remove a couple of unused functions"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (27 commits)
  RISCV: KVM: use raw_spinlock for critical section in imsic
  KVM: selftests: Fix out-of-bounds reads in CPUID test's array lookups
  KVM: selftests: x86: Avoid using SSE/AVX instructions
  KVM: nSVM: Ignore nCR3[4:0] when loading PDPTEs from memory
  KVM: VMX: reset the segment cache after segment init in vmx_vcpu_reset()
  KVM: x86: Clean up documentation for KVM_X86_QUIRK_SLOT_ZAP_ALL
  KVM: x86/mmu: Add lockdep assert to enforce safe usage of kvm_unmap_gfn_range()
  KVM: x86/mmu: Zap only SPs that shadow gPTEs when deleting memslot
  x86/kvm: Override default caching mode for SEV-SNP and TDX
  KVM: Remove unused kvm_vcpu_gfn_to_pfn_atomic
  KVM: Remove unused kvm_vcpu_gfn_to_pfn
  KVM: arm64: Ensure vgic_ready() is ordered against MMIO registration
  KVM: arm64: vgic: Don't check for vgic_ready() when setting NR_IRQS
  KVM: arm64: Fix shift-out-of-bounds bug
  KVM: arm64: Shave a few bytes from the EL2 idmap code
  KVM: arm64: Don't eagerly teardown the vgic on init error
  KVM: arm64: Expose S1PIE to guests
  KVM: arm64: nv: Clarify safety of allowing TLBI unmaps to reschedule
  KVM: arm64: nv: Punt stage-2 recycling to a vCPU request
  KVM: arm64: nv: Do not block when unmapping stage-2 if disallowed
  ...

Author: torvalds

Documentation/virt/kvm/api.rst

@@ -8098,13 +8098,15 @@ KVM_X86_QUIRK_MWAIT_NEVER_UD_FAULTS By default, KVM emulates MONITOR/MWAIT (if
                                     KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT is
                                     disabled.
 
-KVM_X86_QUIRK_SLOT_ZAP_ALL          By default, KVM invalidates all SPTEs in
-                                    fast way for memslot deletion when VM type
-                                    is KVM_X86_DEFAULT_VM.
-                                    When this quirk is disabled or when VM type
-                                    is other than KVM_X86_DEFAULT_VM, KVM zaps
-                                    only leaf SPTEs that are within the range of
-                                    the memslot being deleted.
+KVM_X86_QUIRK_SLOT_ZAP_ALL          By default, for KVM_X86_DEFAULT_VM VMs, KVM
+                                    invalidates all SPTEs in all memslots and
+                                    address spaces when a memslot is deleted or
+                                    moved.  When this quirk is disabled (or the
+                                    VM type isn't KVM_X86_DEFAULT_VM), KVM only
+                                    ensures the backing memory of the deleted
+                                    or moved memslot isn't reachable, i.e KVM
+                                    _may_ invalidate only SPTEs related to the
+                                    memslot.
 =================================== ============================================
 
 7.32 KVM_CAP_MAX_VCPU_ID

Documentation/virt/kvm/locking.rst

@@ -136,7 +136,7 @@ For direct sp, we can easily avoid it since the spte of direct sp is fixed
 to gfn.  For indirect sp, we disabled fast page fault for simplicity.
 
 A solution for indirect sp could be to pin the gfn, for example via
-kvm_vcpu_gfn_to_pfn_atomic, before the cmpxchg.  After the pinning:
+gfn_to_pfn_memslot_atomic, before the cmpxchg.  After the pinning:
 
 - We have held the refcount of pfn; that means the pfn can not be freed and
   be reused for another gfn.

arch/arm64/include/asm/kvm_asm.h

@@ -178,6 +178,7 @@ struct kvm_nvhe_init_params {
 	unsigned long hcr_el2;
 	unsigned long vttbr;
 	unsigned long vtcr;
+	unsigned long tmp;
 };
 
 /*

arch/arm64/include/asm/kvm_host.h

@@ -51,6 +51,7 @@
 #define KVM_REQ_RELOAD_PMU	KVM_ARCH_REQ(5)
 #define KVM_REQ_SUSPEND		KVM_ARCH_REQ(6)
 #define KVM_REQ_RESYNC_PMU_EL0	KVM_ARCH_REQ(7)
+#define KVM_REQ_NESTED_S2_UNMAP	KVM_ARCH_REQ(8)
 
 #define KVM_DIRTY_LOG_MANUAL_CAPS   (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE | \
 				     KVM_DIRTY_LOG_INITIALLY_SET)
@@ -211,6 +212,12 @@ struct kvm_s2_mmu {
 	 */
 	bool	nested_stage2_enabled;
 
+	/*
+	 * true when this MMU needs to be unmapped before being used for a new
+	 * purpose.
+	 */
+	bool	pending_unmap;
+
 	/*
 	 *  0: Nobody is currently using this, check vttbr for validity
 	 * >0: Somebody is actively using this.

arch/arm64/include/asm/kvm_mmu.h

@@ -166,7 +166,8 @@ int create_hyp_exec_mappings(phys_addr_t phys_addr, size_t size,
 int create_hyp_stack(phys_addr_t phys_addr, unsigned long *haddr);
 void __init free_hyp_pgds(void);
 
-void kvm_stage2_unmap_range(struct kvm_s2_mmu *mmu, phys_addr_t start, u64 size);
+void kvm_stage2_unmap_range(struct kvm_s2_mmu *mmu, phys_addr_t start,
+			    u64 size, bool may_block);
 void kvm_stage2_flush_range(struct kvm_s2_mmu *mmu, phys_addr_t addr, phys_addr_t end);
 void kvm_stage2_wp_range(struct kvm_s2_mmu *mmu, phys_addr_t addr, phys_addr_t end);
 

arch/arm64/include/asm/kvm_nested.h

@@ -78,6 +78,8 @@ extern void kvm_s2_mmu_iterate_by_vmid(struct kvm *kvm, u16 vmid,
 extern void kvm_vcpu_load_hw_mmu(struct kvm_vcpu *vcpu);
 extern void kvm_vcpu_put_hw_mmu(struct kvm_vcpu *vcpu);
 
+extern void check_nested_vcpu_requests(struct kvm_vcpu *vcpu);
+
 struct kvm_s2_trans {
 	phys_addr_t output;
 	unsigned long block_size;
@@ -124,7 +126,7 @@ extern int kvm_s2_handle_perm_fault(struct kvm_vcpu *vcpu,
 				    struct kvm_s2_trans *trans);
 extern int kvm_inject_s2_fault(struct kvm_vcpu *vcpu, u64 esr_el2);
 extern void kvm_nested_s2_wp(struct kvm *kvm);
-extern void kvm_nested_s2_unmap(struct kvm *kvm);
+extern void kvm_nested_s2_unmap(struct kvm *kvm, bool may_block);
 extern void kvm_nested_s2_flush(struct kvm *kvm);
 
 unsigned long compute_tlb_inval_range(struct kvm_s2_mmu *mmu, u64 val);

arch/arm64/kernel/asm-offsets.c

@@ -146,6 +146,7 @@ int main(void)
   DEFINE(NVHE_INIT_HCR_EL2,	offsetof(struct kvm_nvhe_init_params, hcr_el2));
   DEFINE(NVHE_INIT_VTTBR,	offsetof(struct kvm_nvhe_init_params, vttbr));
   DEFINE(NVHE_INIT_VTCR,	offsetof(struct kvm_nvhe_init_params, vtcr));
+  DEFINE(NVHE_INIT_TMP,		offsetof(struct kvm_nvhe_init_params, tmp));
 #endif
 #ifdef CONFIG_CPU_PM
   DEFINE(CPU_CTX_SP,		offsetof(struct cpu_suspend_ctx, sp));

arch/arm64/kvm/arm.c

@@ -997,6 +997,9 @@ static int kvm_vcpu_suspend(struct kvm_vcpu *vcpu)
 static int check_vcpu_requests(struct kvm_vcpu *vcpu)
 {
 	if (kvm_request_pending(vcpu)) {
+		if (kvm_check_request(KVM_REQ_VM_DEAD, vcpu))
+			return -EIO;
+
 		if (kvm_check_request(KVM_REQ_SLEEP, vcpu))
 			kvm_vcpu_sleep(vcpu);
 
@@ -1031,6 +1034,8 @@ static int check_vcpu_requests(struct kvm_vcpu *vcpu)
 
 		if (kvm_dirty_ring_check_request(vcpu))
 			return 0;
+
+		check_nested_vcpu_requests(vcpu);
 	}
 
 	return 1;

arch/arm64/kvm/hyp/nvhe/hyp-init.S

@@ -24,28 +24,25 @@
 	.align	11
 
 SYM_CODE_START(__kvm_hyp_init)
-	ventry	__invalid		// Synchronous EL2t
-	ventry	__invalid		// IRQ EL2t
-	ventry	__invalid		// FIQ EL2t
-	ventry	__invalid		// Error EL2t
+	ventry	.			// Synchronous EL2t
+	ventry	.			// IRQ EL2t
+	ventry	.			// FIQ EL2t
+	ventry	.			// Error EL2t
 
-	ventry	__invalid		// Synchronous EL2h
-	ventry	__invalid		// IRQ EL2h
-	ventry	__invalid		// FIQ EL2h
-	ventry	__invalid		// Error EL2h
+	ventry	.			// Synchronous EL2h
+	ventry	.			// IRQ EL2h
+	ventry	.			// FIQ EL2h
+	ventry	.			// Error EL2h
 
 	ventry	__do_hyp_init		// Synchronous 64-bit EL1
-	ventry	__invalid		// IRQ 64-bit EL1
-	ventry	__invalid		// FIQ 64-bit EL1
-	ventry	__invalid		// Error 64-bit EL1
+	ventry	.			// IRQ 64-bit EL1
+	ventry	.			// FIQ 64-bit EL1
+	ventry	.			// Error 64-bit EL1
 
-	ventry	__invalid		// Synchronous 32-bit EL1
-	ventry	__invalid		// IRQ 32-bit EL1
-	ventry	__invalid		// FIQ 32-bit EL1
-	ventry	__invalid		// Error 32-bit EL1
-
-__invalid:
-	b	.
+	ventry	.			// Synchronous 32-bit EL1
+	ventry	.			// IRQ 32-bit EL1
+	ventry	.			// FIQ 32-bit EL1
+	ventry	.			// Error 32-bit EL1
 
 	/*
 	 * Only uses x0..x3 so as to not clobber callee-saved SMCCC registers.
@@ -76,6 +73,13 @@ __do_hyp_init:
 	eret
 SYM_CODE_END(__kvm_hyp_init)
 
+SYM_CODE_START_LOCAL(__kvm_init_el2_state)
+	/* Initialize EL2 CPU state to sane values. */
+	init_el2_state				// Clobbers x0..x2
+	finalise_el2_state
+	ret
+SYM_CODE_END(__kvm_init_el2_state)
+
 /*
  * Initialize the hypervisor in EL2.
  *
@@ -102,9 +106,12 @@ SYM_CODE_START_LOCAL(___kvm_hyp_init)
 	// TPIDR_EL2 is used to preserve x0 across the macro maze...
 	isb
 	msr	tpidr_el2, x0
-	init_el2_state
-	finalise_el2_state
+	str	lr, [x0, #NVHE_INIT_TMP]
+
+	bl	__kvm_init_el2_state
+
 	mrs	x0, tpidr_el2
+	ldr	lr, [x0, #NVHE_INIT_TMP]
 
 1:
 	ldr	x1, [x0, #NVHE_INIT_TPIDR_EL2]
@@ -199,9 +206,8 @@ SYM_CODE_START_LOCAL(__kvm_hyp_init_cpu)
 
 2:	msr	SPsel, #1			// We want to use SP_EL{1,2}
 
-	/* Initialize EL2 CPU state to sane values. */
-	init_el2_state				// Clobbers x0..x2
-	finalise_el2_state
+	bl	__kvm_init_el2_state
+
 	__init_el2_nvhe_prepare_eret
 
 	/* Enable MMU, set vectors and stack. */

arch/arm64/kvm/hypercalls.c

@@ -317,7 +317,7 @@ int kvm_smccc_call_handler(struct kvm_vcpu *vcpu)
 				 * to the guest, and hide SSBS so that the
 				 * guest stays protected.
 				 */
-				if (cpus_have_final_cap(ARM64_SSBS))
+				if (kvm_has_feat(vcpu->kvm, ID_AA64PFR1_EL1, SSBS, IMP))
 					break;
 				fallthrough;
 			case SPECTRE_UNAFFECTED:
@@ -428,7 +428,7 @@ int kvm_arm_copy_fw_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices)
  * Convert the workaround level into an easy-to-compare number, where higher
  * values mean better protection.
  */
-static int get_kernel_wa_level(u64 regid)
+static int get_kernel_wa_level(struct kvm_vcpu *vcpu, u64 regid)
 {
 	switch (regid) {
 	case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1:
@@ -449,7 +449,7 @@ static int get_kernel_wa_level(u64 regid)
 			 * don't have any FW mitigation if SSBS is there at
 			 * all times.
 			 */
-			if (cpus_have_final_cap(ARM64_SSBS))
+			if (kvm_has_feat(vcpu->kvm, ID_AA64PFR1_EL1, SSBS, IMP))
 				return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL;
 			fallthrough;
 		case SPECTRE_UNAFFECTED:
@@ -486,7 +486,7 @@ int kvm_arm_get_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 	case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1:
 	case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2:
 	case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3:
-		val = get_kernel_wa_level(reg->id) & KVM_REG_FEATURE_LEVEL_MASK;
+		val = get_kernel_wa_level(vcpu, reg->id) & KVM_REG_FEATURE_LEVEL_MASK;
 		break;
 	case KVM_REG_ARM_STD_BMAP:
 		val = READ_ONCE(smccc_feat->std_bmap);
@@ -588,7 +588,7 @@ int kvm_arm_set_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 		if (val & ~KVM_REG_FEATURE_LEVEL_MASK)
 			return -EINVAL;
 
-		if (get_kernel_wa_level(reg->id) < val)
+		if (get_kernel_wa_level(vcpu, reg->id) < val)
 			return -EINVAL;
 
 		return 0;
@@ -624,7 +624,7 @@ int kvm_arm_set_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 		 * We can deal with NOT_AVAIL on NOT_REQUIRED, but not the
 		 * other way around.
 		 */
-		if (get_kernel_wa_level(reg->id) < wa_level)
+		if (get_kernel_wa_level(vcpu, reg->id) < wa_level)
 			return -EINVAL;
 
 		return 0;