Merge tag 'kvmarm-fixes-6.11-2' of...

Merge tag 'kvmarm-fixes-6.11-2' of git://git.kernel.org/pub/scm/linux/kernel/git/kvmarm/kvmarm into for-next/fixes

KVM/arm64 fixes for 6.11, round #2

 - Don't drop references on LPIs that weren't visited by the
   vgic-debug iterator

 - Cure lock ordering issue when unregistering vgic redistributors

 - Fix for misaligned stage-2 mappings when VMs are backed by hugetlb
   pages

 - Treat SGI registers as UNDEFINED if a VM hasn't been configured for
   GICv3

* tag 'kvmarm-fixes-6.11-2' of git://git.kernel.org/pub/scm/linux/kernel/git/kvmarm/kvmarm:
  KVM: arm64: Make ICC_*SGI*_EL1 undef in the absence of a vGICv3
  KVM: arm64: Ensure canonical IPA is hugepage-aligned when handling fault
  KVM: arm64: vgic: Don't hold config_lock while unregistering redistributors
  KVM: arm64: vgic-debug: Don't put unmarked LPIs
  KVM: arm64: vgic: Hold config_lock while tearing down a CPU interface
  KVM: selftests: arm64: Correct feature test for S1PIE in get-reg-list
  KVM: arm64: Tidying up PAuth code in KVM
  KVM: arm64: vgic-debug: Exit the iterator properly w/o LPI
  KVM: arm64: Enforce dependency on an ARMv8.4-aware toolchain
  docs: KVM: Fix register ID of SPSR_FIQ
  KVM: arm64: vgic: fix unexpected unlock sparse warnings
  KVM: arm64: fix kdoc warnings in W=1 builds
  KVM: arm64: fix override-init warnings in W=1 builds
  KVM: arm64: free kvm->arch.nested_mmus with kvfree()

Documentation/virt/kvm/api.rst

@@ -2592,7 +2592,7 @@ Specifically:
   0x6030 0000 0010 004a SPSR_ABT    64  spsr[KVM_SPSR_ABT]
   0x6030 0000 0010 004c SPSR_UND    64  spsr[KVM_SPSR_UND]
   0x6030 0000 0010 004e SPSR_IRQ    64  spsr[KVM_SPSR_IRQ]
-  0x6060 0000 0010 0050 SPSR_FIQ    64  spsr[KVM_SPSR_FIQ]
+  0x6030 0000 0010 0050 SPSR_FIQ    64  spsr[KVM_SPSR_FIQ]
   0x6040 0000 0010 0054 V0         128  fp_regs.vregs[0]    [1]_
   0x6040 0000 0010 0058 V1         128  fp_regs.vregs[1]    [1]_
   ...

arch/arm64/kvm/Kconfig

@@ -19,6 +19,7 @@ if VIRTUALIZATION
 
 menuconfig KVM
 	bool "Kernel-based Virtual Machine (KVM) support"
+	depends on AS_HAS_ARMV8_4
 	select KVM_COMMON
 	select KVM_GENERIC_HARDWARE_ENABLING
 	select KVM_GENERIC_MMU_NOTIFIER

arch/arm64/kvm/Makefile

@@ -10,6 +10,9 @@ include $(srctree)/virt/kvm/Makefile.kvm
 obj-$(CONFIG_KVM) += kvm.o
 obj-$(CONFIG_KVM) += hyp/
 
+CFLAGS_sys_regs.o += -Wno-override-init
+CFLAGS_handle_exit.o += -Wno-override-init
+
 kvm-y += arm.o mmu.o mmio.o psci.o hypercalls.o pvtime.o \
 	 inject_fault.o va_layout.o handle_exit.o \
 	 guest.o debug.o reset.o sys_regs.o stacktrace.o \

arch/arm64/kvm/arm.c

@@ -164,6 +164,7 @@ static int kvm_arm_default_max_vcpus(void)
 /**
  * kvm_arch_init_vm - initializes a VM data structure
  * @kvm:	pointer to the KVM struct
+ * @type:	kvm device type
  */
 int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 {
@@ -521,10 +522,10 @@ void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu)
 
 static void vcpu_set_pauth_traps(struct kvm_vcpu *vcpu)
 {
-	if (vcpu_has_ptrauth(vcpu)) {
+	if (vcpu_has_ptrauth(vcpu) && !is_protected_kvm_enabled()) {
 		/*
-		 * Either we're running running an L2 guest, and the API/APK
-		 * bits come from L1's HCR_EL2, or API/APK are both set.
+		 * Either we're running an L2 guest, and the API/APK bits come
+		 * from L1's HCR_EL2, or API/APK are both set.
 		 */
 		if (unlikely(vcpu_has_nv(vcpu) && !is_hyp_ctxt(vcpu))) {
 			u64 val;
@@ -541,16 +542,10 @@ static void vcpu_set_pauth_traps(struct kvm_vcpu *vcpu)
 		 * Save the host keys if there is any chance for the guest
 		 * to use pauth, as the entry code will reload the guest
 		 * keys in that case.
-		 * Protected mode is the exception to that rule, as the
-		 * entry into the EL2 code eagerly switch back and forth
-		 * between host and hyp keys (and kvm_hyp_ctxt is out of
-		 * reach anyway).
 		 */
-		if (is_protected_kvm_enabled())
-			return;
-
 		if (vcpu->arch.hcr_el2 & (HCR_API | HCR_APK)) {
 			struct kvm_cpu_context *ctxt;
+
 			ctxt = this_cpu_ptr_hyp_sym(kvm_hyp_ctxt);
 			ptrauth_save_keys(ctxt);
 		}

arch/arm64/kvm/hyp/include/hyp/switch.h

@@ -27,7 +27,6 @@
 #include <asm/kvm_hyp.h>
 #include <asm/kvm_mmu.h>
 #include <asm/kvm_nested.h>
-#include <asm/kvm_ptrauth.h>
 #include <asm/fpsimd.h>
 #include <asm/debug-monitors.h>
 #include <asm/processor.h>

arch/arm64/kvm/hyp/nvhe/Makefile

@@ -20,6 +20,8 @@ HOST_EXTRACFLAGS += -I$(objtree)/include
 lib-objs := clear_page.o copy_page.o memcpy.o memset.o
 lib-objs := $(addprefix ../../../lib/, $(lib-objs))
 
+CFLAGS_switch.nvhe.o += -Wno-override-init
+
 hyp-obj-y := timer-sr.o sysreg-sr.o debug-sr.o switch.o tlb.o hyp-init.o host.o \
 	 hyp-main.o hyp-smp.o psci-relay.o early_alloc.o page_alloc.o \
 	 cache.o setup.o mm.o mem_protect.o sys_regs.o pkvm.o stacktrace.o ffa.o

arch/arm64/kvm/hyp/nvhe/switch.c

@@ -173,9 +173,8 @@ static void __pmu_switch_to_host(struct kvm_vcpu *vcpu)
 static bool kvm_handle_pvm_sys64(struct kvm_vcpu *vcpu, u64 *exit_code)
 {
 	/*
-	 * Make sure we handle the exit for workarounds and ptrauth
-	 * before the pKVM handling, as the latter could decide to
-	 * UNDEF.
+	 * Make sure we handle the exit for workarounds before the pKVM
+	 * handling, as the latter could decide to UNDEF.
 	 */
 	return (kvm_hyp_handle_sysreg(vcpu, exit_code) ||
 		kvm_handle_pvm_sysreg(vcpu, exit_code));

arch/arm64/kvm/hyp/vhe/Makefile

@@ -6,6 +6,8 @@
 asflags-y := -D__KVM_VHE_HYPERVISOR__
 ccflags-y := -D__KVM_VHE_HYPERVISOR__
 
+CFLAGS_switch.o += -Wno-override-init
+
 obj-y := timer-sr.o sysreg-sr.o debug-sr.o switch.o tlb.o
 obj-y += ../vgic-v3-sr.o ../aarch32.o ../vgic-v2-cpuif-proxy.o ../entry.o \
 	 ../fpsimd.o ../hyp-entry.o ../exception.o

arch/arm64/kvm/mmu.c

@@ -1540,8 +1540,15 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 		vma_pagesize = min(vma_pagesize, (long)max_map_size);
 	}
 
-	if (vma_pagesize == PMD_SIZE || vma_pagesize == PUD_SIZE)
+	/*
+	 * Both the canonical IPA and fault IPA must be hugepage-aligned to
+	 * ensure we find the right PFN and lay down the mapping in the right
+	 * place.
+	 */
+	if (vma_pagesize == PMD_SIZE || vma_pagesize == PUD_SIZE) {
 		fault_ipa &= ~(vma_pagesize - 1);
+		ipa &= ~(vma_pagesize - 1);
+	}
 
 	gfn = ipa >> PAGE_SHIFT;
 	mte_allowed = kvm_vma_mte_allowed(vma);

arch/arm64/kvm/nested.c

@@ -786,7 +786,7 @@ void kvm_arch_flush_shadow_all(struct kvm *kvm)
 		if (!WARN_ON(atomic_read(&mmu->refcnt)))
 			kvm_free_stage2_pgd(mmu);
 	}
-	kfree(kvm->arch.nested_mmus);
+	kvfree(kvm->arch.nested_mmus);
 	kvm->arch.nested_mmus = NULL;
 	kvm->arch.nested_mmus_size = 0;
 	kvm_uninit_stage2_mmu(kvm);

arch/arm64/kvm/sys_regs.c

@@ -33,6 +33,7 @@
 #include <trace/events/kvm.h>
 
 #include "sys_regs.h"
+#include "vgic/vgic.h"
 
 #include "trace.h"
 
@@ -435,6 +436,11 @@ static bool access_gic_sgi(struct kvm_vcpu *vcpu,
 {
 	bool g1;
 
+	if (!kvm_has_gicv3(vcpu->kvm)) {
+		kvm_inject_undefined(vcpu);
+		return false;
+	}
+
 	if (!p->is_write)
 		return read_from_write_only(vcpu, p, r);
 

arch/arm64/kvm/vgic/vgic-debug.c

@@ -45,7 +45,8 @@ static void iter_next(struct kvm *kvm, struct vgic_state_iter *iter)
 	 * Let the xarray drive the iterator after the last SPI, as the iterator
 	 * has exhausted the sequentially-allocated INTID space.
 	 */
-	if (iter->intid >= (iter->nr_spis + VGIC_NR_PRIVATE_IRQS - 1)) {
+	if (iter->intid >= (iter->nr_spis + VGIC_NR_PRIVATE_IRQS - 1) &&
+	    iter->nr_lpis) {
 		if (iter->lpi_idx < iter->nr_lpis)
 			xa_find_after(&dist->lpi_xa, &iter->intid,
 				      VGIC_LPI_MAX_INTID,
@@ -84,7 +85,7 @@ static void iter_unmark_lpis(struct kvm *kvm)
 	struct vgic_irq *irq;
 	unsigned long intid;
 
-	xa_for_each(&dist->lpi_xa, intid, irq) {
+	xa_for_each_marked(&dist->lpi_xa, intid, irq, LPI_XA_MARK_DEBUG_ITER) {
 		xa_clear_mark(&dist->lpi_xa, intid, LPI_XA_MARK_DEBUG_ITER);
 		vgic_put_irq(kvm, irq);
 	}
@@ -112,7 +113,7 @@ static bool end_of_vgic(struct vgic_state_iter *iter)
 	return iter->dist_id > 0 &&
 		iter->vcpu_id == iter->nr_cpus &&
 		iter->intid >= (iter->nr_spis + VGIC_NR_PRIVATE_IRQS) &&
-		iter->lpi_idx > iter->nr_lpis;
+		(!iter->nr_lpis || iter->lpi_idx > iter->nr_lpis);
 }
 
 static void *vgic_debug_start(struct seq_file *s, loff_t *pos)

arch/arm64/kvm/vgic/vgic-init.c

@@ -417,10 +417,8 @@ static void __kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu)
 	kfree(vgic_cpu->private_irqs);
 	vgic_cpu->private_irqs = NULL;
 
-	if (vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3) {
-		vgic_unregister_redist_iodev(vcpu);
+	if (vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3)
 		vgic_cpu->rd_iodev.base_addr = VGIC_ADDR_UNDEF;
-	}
 }
 
 void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu)
@@ -438,17 +436,21 @@ void kvm_vgic_destroy(struct kvm *kvm)
 	unsigned long i;
 
 	mutex_lock(&kvm->slots_lock);
+	mutex_lock(&kvm->arch.config_lock);
 
 	vgic_debug_destroy(kvm);
 
 	kvm_for_each_vcpu(i, vcpu, kvm)
 		__kvm_vgic_vcpu_destroy(vcpu);
 
-	mutex_lock(&kvm->arch.config_lock);
-
 	kvm_vgic_dist_destroy(kvm);
 
 	mutex_unlock(&kvm->arch.config_lock);
+
+	if (kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3)
+		kvm_for_each_vcpu(i, vcpu, kvm)
+			vgic_unregister_redist_iodev(vcpu);
+
 	mutex_unlock(&kvm->slots_lock);
 }
 

arch/arm64/kvm/vgic/vgic-irqfd.c

@@ -9,7 +9,7 @@
 #include <kvm/arm_vgic.h>
 #include "vgic.h"
 
-/**
+/*
  * vgic_irqfd_set_irq: inject the IRQ corresponding to the
  * irqchip routing entry
  *
@@ -75,7 +75,8 @@ static void kvm_populate_msi(struct kvm_kernel_irq_routing_entry *e,
 	msi->flags = e->msi.flags;
 	msi->devid = e->msi.devid;
 }
-/**
+
+/*
  * kvm_set_msi: inject the MSI corresponding to the
  * MSI routing entry
  *
@@ -98,7 +99,7 @@ int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e,
 	return vgic_its_inject_msi(kvm, &msi);
 }
 
-/**
+/*
  * kvm_arch_set_irq_inatomic: fast-path for irqfd injection
  */
 int kvm_arch_set_irq_inatomic(struct kvm_kernel_irq_routing_entry *e,

arch/arm64/kvm/vgic/vgic-its.c

@@ -2040,6 +2040,7 @@ typedef int (*entry_fn_t)(struct vgic_its *its, u32 id, void *entry,
  * @start_id: the ID of the first entry in the table
  * (non zero for 2d level tables)
  * @fn: function to apply on each entry
+ * @opaque: pointer to opaque data
  *
  * Return: < 0 on error, 0 if last element was identified, 1 otherwise
  * (the last element may not be found on second level tables)
@@ -2079,7 +2080,7 @@ static int scan_its_table(struct vgic_its *its, gpa_t base, int size, u32 esz,
 	return 1;
 }
 
-/**
+/*
  * vgic_its_save_ite - Save an interrupt translation entry at @gpa
  */
 static int vgic_its_save_ite(struct vgic_its *its, struct its_device *dev,
@@ -2099,6 +2100,8 @@ static int vgic_its_save_ite(struct vgic_its *its, struct its_device *dev,
 
 /**
  * vgic_its_restore_ite - restore an interrupt translation entry
+ *
+ * @its: its handle
  * @event_id: id used for indexing
  * @ptr: pointer to the ITE entry
  * @opaque: pointer to the its_device
@@ -2231,6 +2234,7 @@ static int vgic_its_restore_itt(struct vgic_its *its, struct its_device *dev)
  * @its: ITS handle
  * @dev: ITS device
  * @ptr: GPA
+ * @dte_esz: device table entry size
  */
 static int vgic_its_save_dte(struct vgic_its *its, struct its_device *dev,
 			     gpa_t ptr, int dte_esz)
@@ -2313,7 +2317,7 @@ static int vgic_its_device_cmp(void *priv, const struct list_head *a,
 		return 1;
 }
 
-/**
+/*
  * vgic_its_save_device_tables - Save the device table and all ITT
  * into guest RAM
  *
@@ -2386,7 +2390,7 @@ static int handle_l1_dte(struct vgic_its *its, u32 id, void *addr,
 	return ret;
 }
 
-/**
+/*
  * vgic_its_restore_device_tables - Restore the device table and all ITT
  * from guest RAM to internal data structs
  */
@@ -2478,7 +2482,7 @@ static int vgic_its_restore_cte(struct vgic_its *its, gpa_t gpa, int esz)
 	return 1;
 }
 
-/**
+/*
  * vgic_its_save_collection_table - Save the collection table into
  * guest RAM
  */
@@ -2518,7 +2522,7 @@ static int vgic_its_save_collection_table(struct vgic_its *its)
 	return ret;
 }
 
-/**
+/*
  * vgic_its_restore_collection_table - reads the collection table
  * in guest memory and restores the ITS internal state. Requires the
  * BASER registers to be restored before.
@@ -2556,7 +2560,7 @@ static int vgic_its_restore_collection_table(struct vgic_its *its)
 	return ret;
 }
 
-/**
+/*
  * vgic_its_save_tables_v0 - Save the ITS tables into guest ARM
  * according to v0 ABI
  */
@@ -2571,7 +2575,7 @@ static int vgic_its_save_tables_v0(struct vgic_its *its)
 	return vgic_its_save_collection_table(its);
 }
 
-/**
+/*
  * vgic_its_restore_tables_v0 - Restore the ITS tables from guest RAM
  * to internal data structs according to V0 ABI
  *

arch/arm64/kvm/vgic/vgic-v3.c

@@ -370,7 +370,7 @@ static void map_all_vpes(struct kvm *kvm)
 						dist->its_vm.vpes[i]->irq));
 }
 
-/**
+/*
  * vgic_v3_save_pending_tables - Save the pending tables into guest RAM
  * kvm lock and all vcpu lock must be held
  */

arch/arm64/kvm/vgic/vgic.c

@@ -36,6 +36,11 @@ struct vgic_global kvm_vgic_global_state __ro_after_init = {
  * we have to disable IRQs before taking this lock and everything lower
  * than it.
  *
+ * The config_lock has additional ordering requirements:
+ * kvm->slots_lock
+ *   kvm->srcu
+ *     kvm->arch.config_lock
+ *
  * If you need to take multiple locks, always take the upper lock first,
  * then the lower ones, e.g. first take the its_lock, then the irq_lock.
  * If you are already holding a lock and need to take a higher one, you
@@ -313,7 +318,7 @@ static bool vgic_validate_injection(struct vgic_irq *irq, bool level, void *owne
  * with all locks dropped.
  */
 bool vgic_queue_irq_unlock(struct kvm *kvm, struct vgic_irq *irq,
-			   unsigned long flags)
+			   unsigned long flags) __releases(&irq->irq_lock)
 {
 	struct kvm_vcpu *vcpu;
 

arch/arm64/kvm/vgic/vgic.h

@@ -186,7 +186,7 @@ bool vgic_get_phys_line_level(struct vgic_irq *irq);
 void vgic_irq_set_phys_pending(struct vgic_irq *irq, bool pending);
 void vgic_irq_set_phys_active(struct vgic_irq *irq, bool active);
 bool vgic_queue_irq_unlock(struct kvm *kvm, struct vgic_irq *irq,
-			   unsigned long flags);
+			   unsigned long flags) __releases(&irq->irq_lock);
 void vgic_kick_vcpus(struct kvm *kvm);
 void vgic_irq_handle_resampling(struct vgic_irq *irq,
 				bool lr_deactivated, bool lr_pending);
@@ -346,4 +346,11 @@ void vgic_v4_configure_vsgis(struct kvm *kvm);
 void vgic_v4_get_vlpi_state(struct vgic_irq *irq, bool *val);
 int vgic_v4_request_vpe_irq(struct kvm_vcpu *vcpu, int irq);
 
+static inline bool kvm_has_gicv3(struct kvm *kvm)
+{
+	return (static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif) &&
+		irqchip_in_kernel(kvm) &&
+		kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3);
+}
+
 #endif

tools/testing/selftests/kvm/aarch64/get-reg-list.c

@@ -32,13 +32,13 @@ static struct feature_id_reg feat_id_regs[] = {
 	{
 		ARM64_SYS_REG(3, 0, 10, 2, 2),	/* PIRE0_EL1 */
 		ARM64_SYS_REG(3, 0, 0, 7, 3),	/* ID_AA64MMFR3_EL1 */
-		4,
+		8,
 		1
 	},
 	{
 		ARM64_SYS_REG(3, 0, 10, 2, 3),	/* PIR_EL1 */
 		ARM64_SYS_REG(3, 0, 0, 7, 3),	/* ID_AA64MMFR3_EL1 */
-		4,
+		8,
 		1
 	}
 };