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

Pull kvm fixes from Paolo Bonzini:
 "ARM:

   - Fix the PMCR_EL0 reset value after the PMU rework

   - Correctly handle S2 fault triggered by a S1 page table walk by not
     always classifying it as a write, as this breaks on R/O memslots

   - Document why we cannot exit with KVM_EXIT_MMIO when taking a write
     fault from a S1 PTW on a R/O memslot

   - Put the Apple M2 on the naughty list for not being able to
     correctly implement the vgic SEIS feature, just like the M1 before
     it

   - Reviewer updates: Alex is stepping down, replaced by Zenghui

  x86:

   - Fix various rare locking issues in Xen emulation and teach lockdep
     to detect them

   - Documentation improvements

   - Do not return host topology information from KVM_GET_SUPPORTED_CPUID"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
  KVM: x86/xen: Avoid deadlock by adding kvm->arch.xen.xen_lock leaf node lock
  KVM: Ensure lockdep knows about kvm->lock vs. vcpu->mutex ordering rule
  KVM: x86/xen: Fix potential deadlock in kvm_xen_update_runstate_guest()
  KVM: x86/xen: Fix lockdep warning on "recursive" gpc locking
  Documentation: kvm: fix SRCU locking order docs
  KVM: x86: Do not return host topology information from KVM_GET_SUPPORTED_CPUID
  KVM: nSVM: clarify recalc_intercepts() wrt CR8
  MAINTAINERS: Remove myself as a KVM/arm64 reviewer
  MAINTAINERS: Add Zenghui Yu as a KVM/arm64 reviewer
  KVM: arm64: vgic: Add Apple M2 cpus to the list of broken SEIS implementations
  KVM: arm64: Convert FSC_* over to ESR_ELx_FSC_*
  KVM: arm64: Document the behaviour of S1PTW faults on RO memslots
  KVM: arm64: Fix S1PTW handling on RO memslots
  KVM: arm64: PMU: Fix PMCR_EL0 reset value

9 files changed, 60 insertions, 39 deletions

diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h
index 4e8b66c74ea2..683ca3af4084 100644
--- a/arch/arm64/include/asm/cputype.h
+++ b/arch/arm64/include/asm/cputype.h
@@ -124,6 +124,8 @@
 #define APPLE_CPU_PART_M1_FIRESTORM_PRO	0x025
 #define APPLE_CPU_PART_M1_ICESTORM_MAX	0x028
 #define APPLE_CPU_PART_M1_FIRESTORM_MAX	0x029
+#define APPLE_CPU_PART_M2_BLIZZARD	0x032
+#define APPLE_CPU_PART_M2_AVALANCHE	0x033
 
 #define AMPERE_CPU_PART_AMPERE1		0xAC3
 
@@ -177,6 +179,8 @@
 #define MIDR_APPLE_M1_FIRESTORM_PRO MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_FIRESTORM_PRO)
 #define MIDR_APPLE_M1_ICESTORM_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_ICESTORM_MAX)
 #define MIDR_APPLE_M1_FIRESTORM_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_FIRESTORM_MAX)
+#define MIDR_APPLE_M2_BLIZZARD MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_BLIZZARD)
+#define MIDR_APPLE_M2_AVALANCHE MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_AVALANCHE)
 #define MIDR_AMPERE1 MIDR_CPU_MODEL(ARM_CPU_IMP_AMPERE, AMPERE_CPU_PART_AMPERE1)
 
 /* Fujitsu Erratum 010001 affects A64FX 1.0 and 1.1, (v0r0 and v1r0) */
diff --git a/arch/arm64/include/asm/esr.h b/arch/arm64/include/asm/esr.h
index 15b34fbfca66..206de10524e3 100644
--- a/arch/arm64/include/asm/esr.h
+++ b/arch/arm64/include/asm/esr.h
@@ -114,6 +114,15 @@
 #define ESR_ELx_FSC_ACCESS	(0x08)
 #define ESR_ELx_FSC_FAULT	(0x04)
 #define ESR_ELx_FSC_PERM	(0x0C)
+#define ESR_ELx_FSC_SEA_TTW0	(0x14)
+#define ESR_ELx_FSC_SEA_TTW1	(0x15)
+#define ESR_ELx_FSC_SEA_TTW2	(0x16)
+#define ESR_ELx_FSC_SEA_TTW3	(0x17)
+#define ESR_ELx_FSC_SECC	(0x18)
+#define ESR_ELx_FSC_SECC_TTW0	(0x1c)
+#define ESR_ELx_FSC_SECC_TTW1	(0x1d)
+#define ESR_ELx_FSC_SECC_TTW2	(0x1e)
+#define ESR_ELx_FSC_SECC_TTW3	(0x1f)
 
 /* ISS field definitions for Data Aborts */
 #define ESR_ELx_ISV_SHIFT	(24)
diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index 0df3fc3a0173..26b0c97df986 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -319,21 +319,6 @@
 				 BIT(18) |		\
 				 GENMASK(16, 15))
 
-/* For compatibility with fault code shared with 32-bit */
-#define FSC_FAULT	ESR_ELx_FSC_FAULT
-#define FSC_ACCESS	ESR_ELx_FSC_ACCESS
-#define FSC_PERM	ESR_ELx_FSC_PERM
-#define FSC_SEA		ESR_ELx_FSC_EXTABT
-#define FSC_SEA_TTW0	(0x14)
-#define FSC_SEA_TTW1	(0x15)
-#define FSC_SEA_TTW2	(0x16)
-#define FSC_SEA_TTW3	(0x17)
-#define FSC_SECC	(0x18)
-#define FSC_SECC_TTW0	(0x1c)
-#define FSC_SECC_TTW1	(0x1d)
-#define FSC_SECC_TTW2	(0x1e)
-#define FSC_SECC_TTW3	(0x1f)
-
 /* Hyp Prefetch Fault Address Register (HPFAR/HDFAR) */
 #define HPFAR_MASK	(~UL(0xf))
 /*
diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index 9bdba47f7e14..193583df2d9c 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -349,16 +349,16 @@ static __always_inline u8 kvm_vcpu_trap_get_fault_level(const struct kvm_vcpu *v
 static __always_inline bool kvm_vcpu_abt_issea(const struct kvm_vcpu *vcpu)
 {
 	switch (kvm_vcpu_trap_get_fault(vcpu)) {
-	case FSC_SEA:
-	case FSC_SEA_TTW0:
-	case FSC_SEA_TTW1:
-	case FSC_SEA_TTW2:
-	case FSC_SEA_TTW3:
-	case FSC_SECC:
-	case FSC_SECC_TTW0:
-	case FSC_SECC_TTW1:
-	case FSC_SECC_TTW2:
-	case FSC_SECC_TTW3:
+	case ESR_ELx_FSC_EXTABT:
+	case ESR_ELx_FSC_SEA_TTW0:
+	case ESR_ELx_FSC_SEA_TTW1:
+	case ESR_ELx_FSC_SEA_TTW2:
+	case ESR_ELx_FSC_SEA_TTW3:
+	case ESR_ELx_FSC_SECC:
+	case ESR_ELx_FSC_SECC_TTW0:
+	case ESR_ELx_FSC_SECC_TTW1:
+	case ESR_ELx_FSC_SECC_TTW2:
+	case ESR_ELx_FSC_SECC_TTW3:
 		return true;
 	default:
 		return false;
@@ -373,8 +373,26 @@ static __always_inline int kvm_vcpu_sys_get_rt(struct kvm_vcpu *vcpu)
 
 static inline bool kvm_is_write_fault(struct kvm_vcpu *vcpu)
 {
-	if (kvm_vcpu_abt_iss1tw(vcpu))
-		return true;
+	if (kvm_vcpu_abt_iss1tw(vcpu)) {
+		/*
+		 * Only a permission fault on a S1PTW should be
+		 * considered as a write. Otherwise, page tables baked
+		 * in a read-only memslot will result in an exception
+		 * being delivered in the guest.
+		 *
+		 * The drawback is that we end-up faulting twice if the
+		 * guest is using any of HW AF/DB: a translation fault
+		 * to map the page containing the PT (read only at
+		 * first), then a permission fault to allow the flags
+		 * to be set.
+		 */
+		switch (kvm_vcpu_trap_get_fault_type(vcpu)) {
+		case ESR_ELx_FSC_PERM:
+			return true;
+		default:
+			return false;
+		}
+	}
 
 	if (kvm_vcpu_trap_is_iabt(vcpu))
 		return false;
diff --git a/arch/arm64/kvm/hyp/include/hyp/fault.h b/arch/arm64/kvm/hyp/include/hyp/fault.h
index 1b8a2dcd712f..9ddcfe2c3e57 100644
--- a/arch/arm64/kvm/hyp/include/hyp/fault.h
+++ b/arch/arm64/kvm/hyp/include/hyp/fault.h
@@ -60,7 +60,7 @@ static inline bool __get_fault_info(u64 esr, struct kvm_vcpu_fault_info *fault)
 	 */
 	if (!(esr & ESR_ELx_S1PTW) &&
 	    (cpus_have_final_cap(ARM64_WORKAROUND_834220) ||
-	     (esr & ESR_ELx_FSC_TYPE) == FSC_PERM)) {
+	     (esr & ESR_ELx_FSC_TYPE) == ESR_ELx_FSC_PERM)) {
 		if (!__translate_far_to_hpfar(far, &hpfar))
 			return false;
 	} else {
diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h
index 3330d1b76bdd..07d37ff88a3f 100644
--- a/arch/arm64/kvm/hyp/include/hyp/switch.h
+++ b/arch/arm64/kvm/hyp/include/hyp/switch.h
@@ -367,7 +367,7 @@ static bool kvm_hyp_handle_dabt_low(struct kvm_vcpu *vcpu, u64 *exit_code)
 	if (static_branch_unlikely(&vgic_v2_cpuif_trap)) {
 		bool valid;
 
-		valid = kvm_vcpu_trap_get_fault_type(vcpu) == FSC_FAULT &&
+		valid = kvm_vcpu_trap_get_fault_type(vcpu) == ESR_ELx_FSC_FAULT &&
 			kvm_vcpu_dabt_isvalid(vcpu) &&
 			!kvm_vcpu_abt_issea(vcpu) &&
 			!kvm_vcpu_abt_iss1tw(vcpu);
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 31d7fa4c7c14..a3ee3b605c9b 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -1212,7 +1212,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	exec_fault = kvm_vcpu_trap_is_exec_fault(vcpu);
 	VM_BUG_ON(write_fault && exec_fault);
 
-	if (fault_status == FSC_PERM && !write_fault && !exec_fault) {
+	if (fault_status == ESR_ELx_FSC_PERM && !write_fault && !exec_fault) {
 		kvm_err("Unexpected L2 read permission error\n");
 		return -EFAULT;
 	}
@@ -1277,7 +1277,8 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	 * 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 != FSC_PERM || (logging_active && write_fault)) {
+	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)
@@ -1342,7 +1343,8 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	 * backed by a THP and thus use block mapping if possible.
 	 */
 	if (vma_pagesize == PAGE_SIZE && !(force_pte || device)) {
-		if (fault_status == FSC_PERM && fault_granule > PAGE_SIZE)
+		if (fault_status ==  ESR_ELx_FSC_PERM &&
+		    fault_granule > PAGE_SIZE)
 			vma_pagesize = fault_granule;
 		else
 			vma_pagesize = transparent_hugepage_adjust(kvm, memslot,
@@ -1350,7 +1352,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 								   &fault_ipa);
 	}
 
-	if (fault_status != FSC_PERM && !device && kvm_has_mte(kvm)) {
+	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)) {
 			sanitise_mte_tags(kvm, pfn, vma_pagesize);
@@ -1376,7 +1378,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	 * permissions only if vma_pagesize equals fault_granule. Otherwise,
 	 * kvm_pgtable_stage2_map() should be called to change block size.
 	 */
-	if (fault_status == FSC_PERM && vma_pagesize == fault_granule)
+	if (fault_status == ESR_ELx_FSC_PERM && vma_pagesize == fault_granule)
 		ret = kvm_pgtable_stage2_relax_perms(pgt, fault_ipa, prot);
 	else
 		ret = kvm_pgtable_stage2_map(pgt, fault_ipa, vma_pagesize,
@@ -1441,7 +1443,7 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu)
 	fault_ipa = kvm_vcpu_get_fault_ipa(vcpu);
 	is_iabt = kvm_vcpu_trap_is_iabt(vcpu);
 
-	if (fault_status == FSC_FAULT) {
+	if (fault_status == ESR_ELx_FSC_FAULT) {
 		/* Beyond sanitised PARange (which is the IPA limit) */
 		if (fault_ipa >= BIT_ULL(get_kvm_ipa_limit())) {
 			kvm_inject_size_fault(vcpu);
@@ -1476,8 +1478,9 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu)
 			      kvm_vcpu_get_hfar(vcpu), fault_ipa);
 
 	/* Check the stage-2 fault is trans. fault or write fault */
-	if (fault_status != FSC_FAULT && fault_status != FSC_PERM &&
-	    fault_status != FSC_ACCESS) {
+	if (fault_status != ESR_ELx_FSC_FAULT &&
+	    fault_status != ESR_ELx_FSC_PERM &&
+	    fault_status != ESR_ELx_FSC_ACCESS) {
 		kvm_err("Unsupported FSC: EC=%#x xFSC=%#lx ESR_EL2=%#lx\n",
 			kvm_vcpu_trap_get_class(vcpu),
 			(unsigned long)kvm_vcpu_trap_get_fault(vcpu),
@@ -1539,7 +1542,7 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu)
 	/* Userspace should not be able to register out-of-bounds IPAs */
 	VM_BUG_ON(fault_ipa >= kvm_phys_size(vcpu->kvm));
 
-	if (fault_status == FSC_ACCESS) {
+	if (fault_status == ESR_ELx_FSC_ACCESS) {
 		handle_access_fault(vcpu, fault_ipa);
 		ret = 1;
 		goto out_unlock;
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index d5ee52d6bf73..c6cbfe6b854b 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -646,7 +646,7 @@ static void reset_pmcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
 		return;
 
 	/* Only preserve PMCR_EL0.N, and reset the rest to 0 */
-	pmcr = read_sysreg(pmcr_el0) & ARMV8_PMU_PMCR_N_MASK;
+	pmcr = read_sysreg(pmcr_el0) & (ARMV8_PMU_PMCR_N_MASK << ARMV8_PMU_PMCR_N_SHIFT);
 	if (!kvm_supports_32bit_el0())
 		pmcr |= ARMV8_PMU_PMCR_LC;
 
diff --git a/arch/arm64/kvm/vgic/vgic-v3.c b/arch/arm64/kvm/vgic/vgic-v3.c
index 826ff6f2a4e7..2074521d4a8c 100644
--- a/arch/arm64/kvm/vgic/vgic-v3.c
+++ b/arch/arm64/kvm/vgic/vgic-v3.c
@@ -616,6 +616,8 @@ static const struct midr_range broken_seis[] = {
 	MIDR_ALL_VERSIONS(MIDR_APPLE_M1_FIRESTORM_PRO),
 	MIDR_ALL_VERSIONS(MIDR_APPLE_M1_ICESTORM_MAX),
 	MIDR_ALL_VERSIONS(MIDR_APPLE_M1_FIRESTORM_MAX),
+	MIDR_ALL_VERSIONS(MIDR_APPLE_M2_BLIZZARD),
+	MIDR_ALL_VERSIONS(MIDR_APPLE_M2_AVALANCHE),
 	{},
 };