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

Documentation/virt/kvm/api.rst

@@ -1354,6 +1354,14 @@ the memory region are automatically reflected into the guest.  For example, an
 mmap() that affects the region will be made visible immediately.  Another
 example is madvise(MADV_DROP).
 
+Note: On arm64, a write generated by the page-table walker (to update
+the Access and Dirty flags, for example) never results in a
+KVM_EXIT_MMIO exit when the slot has the KVM_MEM_READONLY flag. This
+is because KVM cannot provide the data that would be written by the
+page-table walker, making it impossible to emulate the access.
+Instead, an abort (data abort if the cause of the page-table update
+was a load or a store, instruction abort if it was an instruction
+fetch) is injected in the guest.
 
 4.36 KVM_SET_TSS_ADDR
 ---------------------
@@ -8310,6 +8318,20 @@ CPU[EAX=1]:ECX[24] (TSC_DEADLINE) is not reported by ``KVM_GET_SUPPORTED_CPUID``
 It can be enabled if ``KVM_CAP_TSC_DEADLINE_TIMER`` is present and the kernel
 has enabled in-kernel emulation of the local APIC.
 
+CPU topology
+~~~~~~~~~~~~
+
+Several CPUID values include topology information for the host CPU:
+0x0b and 0x1f for Intel systems, 0x8000001e for AMD systems.  Different
+versions of KVM return different values for this information and userspace
+should not rely on it.  Currently they return all zeroes.
+
+If userspace wishes to set up a guest topology, it should be careful that
+the values of these three leaves differ for each CPU.  In particular,
+the APIC ID is found in EDX for all subleaves of 0x0b and 0x1f, and in EAX
+for 0x8000001e; the latter also encodes the core id and node id in bits
+7:0 of EBX and ECX respectively.
+
 Obsolete ioctls and capabilities
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 

Documentation/virt/kvm/locking.rst

@@ -24,21 +24,22 @@ The acquisition orders for mutexes are as follows:
 
 For SRCU:
 
-- ``synchronize_srcu(&kvm->srcu)`` is called _inside_
-  the kvm->slots_lock critical section, therefore kvm->slots_lock
-  cannot be taken inside a kvm->srcu read-side critical section.
-  Instead, kvm->slots_arch_lock is released before the call
-  to ``synchronize_srcu()`` and _can_ be taken inside a
-  kvm->srcu read-side critical section.
-
-- kvm->lock is taken inside kvm->srcu, therefore
-  ``synchronize_srcu(&kvm->srcu)`` cannot be called inside
-  a kvm->lock critical section.  If you cannot delay the
-  call until after kvm->lock is released, use ``call_srcu``.
+- ``synchronize_srcu(&kvm->srcu)`` is called inside critical sections
+  for kvm->lock, vcpu->mutex and kvm->slots_lock.  These locks _cannot_
+  be taken inside a kvm->srcu read-side critical section; that is, the
+  following is broken::
+
+      srcu_read_lock(&kvm->srcu);
+      mutex_lock(&kvm->slots_lock);
+
+- kvm->slots_arch_lock instead is released before the call to
+  ``synchronize_srcu()``.  It _can_ therefore be taken inside a
+  kvm->srcu read-side critical section, for example while processing
+  a vmexit.
 
 On x86:
 
-- vcpu->mutex is taken outside kvm->arch.hyperv.hv_lock
+- vcpu->mutex is taken outside kvm->arch.hyperv.hv_lock and kvm->arch.xen.xen_lock
 
 - kvm->arch.mmu_lock is an rwlock.  kvm->arch.tdp_mmu_pages_lock and
   kvm->arch.mmu_unsync_pages_lock are taken inside kvm->arch.mmu_lock, and

MAINTAINERS

@@ -11356,9 +11356,9 @@ F:	virt/kvm/*
 KERNEL VIRTUAL MACHINE FOR ARM64 (KVM/arm64)
 M:	Marc Zyngier <maz@kernel.org>
 R:	James Morse <james.morse@arm.com>
-R:	Alexandru Elisei <alexandru.elisei@arm.com>
 R:	Suzuki K Poulose <suzuki.poulose@arm.com>
 R:	Oliver Upton <oliver.upton@linux.dev>
+R:	Zenghui Yu <yuzenghui@huawei.com>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 L:	kvmarm@lists.linux.dev
 L:	kvmarm@lists.cs.columbia.edu (deprecated, moderated for non-subscribers)

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) */

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)

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))
 /*

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;

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 {

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);

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;

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;
 

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),
 	{},
 };
 

arch/x86/include/asm/kvm_host.h

@@ -1111,6 +1111,7 @@ struct msr_bitmap_range {
 
 /* Xen emulation context */
 struct kvm_xen {
+	struct mutex xen_lock;
 	u32 xen_version;
 	bool long_mode;
 	bool runstate_update_flag;

arch/x86/kvm/cpuid.c

@@ -770,16 +770,22 @@ struct kvm_cpuid_array {
 	int nent;
 };
 
+static struct kvm_cpuid_entry2 *get_next_cpuid(struct kvm_cpuid_array *array)
+{
+	if (array->nent >= array->maxnent)
+		return NULL;
+
+	return &array->entries[array->nent++];
+}
+
 static struct kvm_cpuid_entry2 *do_host_cpuid(struct kvm_cpuid_array *array,
 					      u32 function, u32 index)
 {
-	struct kvm_cpuid_entry2 *entry;
+	struct kvm_cpuid_entry2 *entry = get_next_cpuid(array);
 
-	if (array->nent >= array->maxnent)
+	if (!entry)
 		return NULL;
 
-	entry = &array->entries[array->nent++];
-
 	memset(entry, 0, sizeof(*entry));
 	entry->function = function;
 	entry->index = index;
@@ -956,22 +962,13 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function)
 		entry->edx = edx.full;
 		break;
 	}
-	/*
-	 * Per Intel's SDM, the 0x1f is a superset of 0xb,
-	 * thus they can be handled by common code.
-	 */
 	case 0x1f:
 	case 0xb:
 		/*
-		 * Populate entries until the level type (ECX[15:8]) of the
-		 * previous entry is zero.  Note, CPUID EAX.{0x1f,0xb}.0 is
-		 * the starting entry, filled by the primary do_host_cpuid().
+		 * No topology; a valid topology is indicated by the presence
+		 * of subleaf 1.
 		 */
-		for (i = 1; entry->ecx & 0xff00; ++i) {
-			entry = do_host_cpuid(array, function, i);
-			if (!entry)
-				goto out;
-		}
+		entry->eax = entry->ebx = entry->ecx = 0;
 		break;
 	case 0xd: {
 		u64 permitted_xcr0 = kvm_caps.supported_xcr0 & xstate_get_guest_group_perm();
@@ -1202,6 +1199,9 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function)
 		entry->ebx = entry->ecx = entry->edx = 0;
 		break;
 	case 0x8000001e:
+		/* Do not return host topology information.  */
+		entry->eax = entry->ebx = entry->ecx = 0;
+		entry->edx = 0; /* reserved */
 		break;
 	case 0x8000001F:
 		if (!kvm_cpu_cap_has(X86_FEATURE_SEV)) {

arch/x86/kvm/svm/nested.c

@@ -138,15 +138,13 @@ void recalc_intercepts(struct vcpu_svm *svm)
 		c->intercepts[i] = h->intercepts[i];
 
 	if (g->int_ctl & V_INTR_MASKING_MASK) {
-		/* We only want the cr8 intercept bits of L1 */
-		vmcb_clr_intercept(c, INTERCEPT_CR8_READ);
-		vmcb_clr_intercept(c, INTERCEPT_CR8_WRITE);
-
 		/*
-		 * Once running L2 with HF_VINTR_MASK, EFLAGS.IF does not
-		 * affect any interrupt we may want to inject; therefore,
-		 * interrupt window vmexits are irrelevant to L0.
+		 * Once running L2 with HF_VINTR_MASK, EFLAGS.IF and CR8
+		 * does not affect any interrupt we may want to inject;
+		 * therefore, writes to CR8 are irrelevant to L0, as are
+		 * interrupt window vmexits.
 		 */
+		vmcb_clr_intercept(c, INTERCEPT_CR8_WRITE);
 		vmcb_clr_intercept(c, INTERCEPT_VINTR);
 	}
 

arch/x86/kvm/xen.c

@@ -271,7 +271,15 @@ static void kvm_xen_update_runstate_guest(struct kvm_vcpu *v, bool atomic)
 	 * Attempt to obtain the GPC lock on *both* (if there are two)
 	 * gfn_to_pfn caches that cover the region.
 	 */
-	read_lock_irqsave(&gpc1->lock, flags);
+	if (atomic) {
+		local_irq_save(flags);
+		if (!read_trylock(&gpc1->lock)) {
+			local_irq_restore(flags);
+			return;
+		}
+	} else {
+		read_lock_irqsave(&gpc1->lock, flags);
+	}
 	while (!kvm_gpc_check(gpc1, user_len1)) {
 		read_unlock_irqrestore(&gpc1->lock, flags);
 
@@ -304,9 +312,18 @@ static void kvm_xen_update_runstate_guest(struct kvm_vcpu *v, bool atomic)
 		 * The guest's runstate_info is split across two pages and we
 		 * need to hold and validate both GPCs simultaneously. We can
 		 * declare a lock ordering GPC1 > GPC2 because nothing else
-		 * takes them more than one at a time.
+		 * takes them more than one at a time. Set a subclass on the
+		 * gpc1 lock to make lockdep shut up about it.
 		 */
-		read_lock(&gpc2->lock);
+		lock_set_subclass(&gpc1->lock.dep_map, 1, _THIS_IP_);
+		if (atomic) {
+			if (!read_trylock(&gpc2->lock)) {
+				read_unlock_irqrestore(&gpc1->lock, flags);
+				return;
+			}
+		} else {
+			read_lock(&gpc2->lock);
+		}
 
 		if (!kvm_gpc_check(gpc2, user_len2)) {
 			read_unlock(&gpc2->lock);
@@ -590,26 +607,26 @@ int kvm_xen_hvm_set_attr(struct kvm *kvm, struct kvm_xen_hvm_attr *data)
 		if (!IS_ENABLED(CONFIG_64BIT) && data->u.long_mode) {
 			r = -EINVAL;
 		} else {
-			mutex_lock(&kvm->lock);
+			mutex_lock(&kvm->arch.xen.xen_lock);
 			kvm->arch.xen.long_mode = !!data->u.long_mode;
-			mutex_unlock(&kvm->lock);
+			mutex_unlock(&kvm->arch.xen.xen_lock);
 			r = 0;
 		}
 		break;
 
 	case KVM_XEN_ATTR_TYPE_SHARED_INFO:
-		mutex_lock(&kvm->lock);
+		mutex_lock(&kvm->arch.xen.xen_lock);
 		r = kvm_xen_shared_info_init(kvm, data->u.shared_info.gfn);
-		mutex_unlock(&kvm->lock);
+		mutex_unlock(&kvm->arch.xen.xen_lock);
 		break;
 
 	case KVM_XEN_ATTR_TYPE_UPCALL_VECTOR:
 		if (data->u.vector && data->u.vector < 0x10)
 			r = -EINVAL;
 		else {
-			mutex_lock(&kvm->lock);
+			mutex_lock(&kvm->arch.xen.xen_lock);
 			kvm->arch.xen.upcall_vector = data->u.vector;
-			mutex_unlock(&kvm->lock);
+			mutex_unlock(&kvm->arch.xen.xen_lock);
 			r = 0;
 		}
 		break;
@@ -619,9 +636,9 @@ int kvm_xen_hvm_set_attr(struct kvm *kvm, struct kvm_xen_hvm_attr *data)
 		break;
 
 	case KVM_XEN_ATTR_TYPE_XEN_VERSION:
-		mutex_lock(&kvm->lock);
+		mutex_lock(&kvm->arch.xen.xen_lock);
 		kvm->arch.xen.xen_version = data->u.xen_version;
-		mutex_unlock(&kvm->lock);
+		mutex_unlock(&kvm->arch.xen.xen_lock);
 		r = 0;
 		break;
 
@@ -630,9 +647,9 @@ int kvm_xen_hvm_set_attr(struct kvm *kvm, struct kvm_xen_hvm_attr *data)
 			r = -EOPNOTSUPP;
 			break;
 		}
-		mutex_lock(&kvm->lock);
+		mutex_lock(&kvm->arch.xen.xen_lock);
 		kvm->arch.xen.runstate_update_flag = !!data->u.runstate_update_flag;
-		mutex_unlock(&kvm->lock);
+		mutex_unlock(&kvm->arch.xen.xen_lock);
 		r = 0;
 		break;
 
@@ -647,7 +664,7 @@ int kvm_xen_hvm_get_attr(struct kvm *kvm, struct kvm_xen_hvm_attr *data)
 {
 	int r = -ENOENT;
 
-	mutex_lock(&kvm->lock);
+	mutex_lock(&kvm->arch.xen.xen_lock);
 
 	switch (data->type) {
 	case KVM_XEN_ATTR_TYPE_LONG_MODE:
@@ -686,7 +703,7 @@ int kvm_xen_hvm_get_attr(struct kvm *kvm, struct kvm_xen_hvm_attr *data)
 		break;
 	}
 
-	mutex_unlock(&kvm->lock);
+	mutex_unlock(&kvm->arch.xen.xen_lock);
 	return r;
 }
 
@@ -694,7 +711,7 @@ int kvm_xen_vcpu_set_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data)
 {
 	int idx, r = -ENOENT;
 
-	mutex_lock(&vcpu->kvm->lock);
+	mutex_lock(&vcpu->kvm->arch.xen.xen_lock);
 	idx = srcu_read_lock(&vcpu->kvm->srcu);
 
 	switch (data->type) {
@@ -922,7 +939,7 @@ int kvm_xen_vcpu_set_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data)
 	}
 
 	srcu_read_unlock(&vcpu->kvm->srcu, idx);
-	mutex_unlock(&vcpu->kvm->lock);
+	mutex_unlock(&vcpu->kvm->arch.xen.xen_lock);
 	return r;
 }
 
@@ -930,7 +947,7 @@ int kvm_xen_vcpu_get_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data)
 {
 	int r = -ENOENT;
 
-	mutex_lock(&vcpu->kvm->lock);
+	mutex_lock(&vcpu->kvm->arch.xen.xen_lock);
 
 	switch (data->type) {
 	case KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO:
@@ -1013,7 +1030,7 @@ int kvm_xen_vcpu_get_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data)
 		break;
 	}
 
-	mutex_unlock(&vcpu->kvm->lock);
+	mutex_unlock(&vcpu->kvm->arch.xen.xen_lock);
 	return r;
 }
 
@@ -1106,7 +1123,7 @@ int kvm_xen_hvm_config(struct kvm *kvm, struct kvm_xen_hvm_config *xhc)
 	     xhc->blob_size_32 || xhc->blob_size_64))
 		return -EINVAL;
 
-	mutex_lock(&kvm->lock);
+	mutex_lock(&kvm->arch.xen.xen_lock);
 
 	if (xhc->msr && !kvm->arch.xen_hvm_config.msr)
 		static_branch_inc(&kvm_xen_enabled.key);
@@ -1115,7 +1132,7 @@ int kvm_xen_hvm_config(struct kvm *kvm, struct kvm_xen_hvm_config *xhc)
 
 	memcpy(&kvm->arch.xen_hvm_config, xhc, sizeof(*xhc));
 
-	mutex_unlock(&kvm->lock);
+	mutex_unlock(&kvm->arch.xen.xen_lock);
 	return 0;
 }
 
@@ -1658,15 +1675,7 @@ static int kvm_xen_set_evtchn(struct kvm_xen_evtchn *xe, struct kvm *kvm)
 		mm_borrowed = true;
 	}
 
-	/*
-	 * For the irqfd workqueue, using the main kvm->lock mutex is
-	 * fine since this function is invoked from kvm_set_irq() with
-	 * no other lock held, no srcu. In future if it will be called
-	 * directly from a vCPU thread (e.g. on hypercall for an IPI)
-	 * then it may need to switch to using a leaf-node mutex for
-	 * serializing the shared_info mapping.
-	 */
-	mutex_lock(&kvm->lock);
+	mutex_lock(&kvm->arch.xen.xen_lock);
 
 	/*
 	 * It is theoretically possible for the page to be unmapped
@@ -1695,7 +1704,7 @@ static int kvm_xen_set_evtchn(struct kvm_xen_evtchn *xe, struct kvm *kvm)
 		srcu_read_unlock(&kvm->srcu, idx);
 	} while(!rc);
 
-	mutex_unlock(&kvm->lock);
+	mutex_unlock(&kvm->arch.xen.xen_lock);
 
 	if (mm_borrowed)
 		kthread_unuse_mm(kvm->mm);
@@ -1811,7 +1820,7 @@ static int kvm_xen_eventfd_update(struct kvm *kvm,
 	int ret;
 
 	/* Protect writes to evtchnfd as well as the idr lookup.  */
-	mutex_lock(&kvm->lock);
+	mutex_lock(&kvm->arch.xen.xen_lock);
 	evtchnfd = idr_find(&kvm->arch.xen.evtchn_ports, port);
 
 	ret = -ENOENT;
@@ -1842,7 +1851,7 @@ static int kvm_xen_eventfd_update(struct kvm *kvm,
 	}
 	ret = 0;
 out_unlock:
-	mutex_unlock(&kvm->lock);
+	mutex_unlock(&kvm->arch.xen.xen_lock);
 	return ret;
 }
 
@@ -1905,10 +1914,10 @@ static int kvm_xen_eventfd_assign(struct kvm *kvm,
 		evtchnfd->deliver.port.priority = data->u.evtchn.deliver.port.priority;
 	}
 
-	mutex_lock(&kvm->lock);
+	mutex_lock(&kvm->arch.xen.xen_lock);
 	ret = idr_alloc(&kvm->arch.xen.evtchn_ports, evtchnfd, port, port + 1,
 			GFP_KERNEL);
-	mutex_unlock(&kvm->lock);
+	mutex_unlock(&kvm->arch.xen.xen_lock);
 	if (ret >= 0)
 		return 0;
 
@@ -1926,9 +1935,9 @@ static int kvm_xen_eventfd_deassign(struct kvm *kvm, u32 port)
 {
 	struct evtchnfd *evtchnfd;
 
-	mutex_lock(&kvm->lock);
+	mutex_lock(&kvm->arch.xen.xen_lock);
 	evtchnfd = idr_remove(&kvm->arch.xen.evtchn_ports, port);
-	mutex_unlock(&kvm->lock);
+	mutex_unlock(&kvm->arch.xen.xen_lock);
 
 	if (!evtchnfd)
 		return -ENOENT;
@@ -1946,7 +1955,7 @@ static int kvm_xen_eventfd_reset(struct kvm *kvm)
 	int i;
 	int n = 0;
 
-	mutex_lock(&kvm->lock);
+	mutex_lock(&kvm->arch.xen.xen_lock);
 
 	/*
 	 * Because synchronize_srcu() cannot be called inside the
@@ -1958,7 +1967,7 @@ static int kvm_xen_eventfd_reset(struct kvm *kvm)
 
 	all_evtchnfds = kmalloc_array(n, sizeof(struct evtchnfd *), GFP_KERNEL);
 	if (!all_evtchnfds) {
-		mutex_unlock(&kvm->lock);
+		mutex_unlock(&kvm->arch.xen.xen_lock);
 		return -ENOMEM;
 	}
 
@@ -1967,7 +1976,7 @@ static int kvm_xen_eventfd_reset(struct kvm *kvm)
 		all_evtchnfds[n++] = evtchnfd;
 		idr_remove(&kvm->arch.xen.evtchn_ports, evtchnfd->send_port);
 	}
-	mutex_unlock(&kvm->lock);
+	mutex_unlock(&kvm->arch.xen.xen_lock);
 
 	synchronize_srcu(&kvm->srcu);
 
@@ -2069,6 +2078,7 @@ void kvm_xen_destroy_vcpu(struct kvm_vcpu *vcpu)
 
 void kvm_xen_init_vm(struct kvm *kvm)
 {
+	mutex_init(&kvm->arch.xen.xen_lock);
 	idr_init(&kvm->arch.xen.evtchn_ports);
 	kvm_gpc_init(&kvm->arch.xen.shinfo_cache, kvm, NULL, KVM_HOST_USES_PFN);
 }

virt/kvm/kvm_main.c

@@ -3954,6 +3954,13 @@ static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, u32 id)
 	}
 
 	mutex_lock(&kvm->lock);
+
+#ifdef CONFIG_LOCKDEP
+	/* Ensure that lockdep knows vcpu->mutex is taken *inside* kvm->lock */
+	mutex_lock(&vcpu->mutex);
+	mutex_unlock(&vcpu->mutex);
+#endif
+
 	if (kvm_get_vcpu_by_id(kvm, id)) {
 		r = -EEXIST;
 		goto unlock_vcpu_destroy;