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

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

- Fix compilation without RISCV_ISA_ZICBOM

- Fix kvm_riscv_vcpu_timer_pending() for Sstc

ARM:

- Fix a bug preventing restoring an ITS containing mappings for very
large and very sparse device topology

- Work around a relocation handling error when compiling the nVHE
object with profile optimisation

- Fix for stage-2 invalidation holding the VM MMU lock for too long
by limiting the walk to the largest block mapping size

- Enable stack protection and branch profiling for VHE

- Two selftest fixes

x86:

- add compat implementation for KVM_X86_SET_MSR_FILTER ioctl

selftests:

- synchronize includes between include/uapi and tools/include/uapi"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
tools: include: sync include/api/linux/kvm.h
KVM: x86: Add compat handler for KVM_X86_SET_MSR_FILTER
KVM: x86: Copy filter arg outside kvm_vm_ioctl_set_msr_filter()
kvm: Add support for arch compat vm ioctls
RISC-V: KVM: Fix kvm_riscv_vcpu_timer_pending() for Sstc
RISC-V: Fix compilation without RISCV_ISA_ZICBOM
KVM: arm64: vgic: Fix exit condition in scan_its_table()
KVM: arm64: nvhe: Fix build with profile optimization
KVM: selftests: Fix number of pages for memory slot in memslot_modification_stress_test
KVM: arm64: selftests: Fix multiple versions of GIC creation
KVM: arm64: Enable stack protection and branch profiling for VHE
KVM: arm64: Limit stage2_apply_range() batch size to largest block
KVM: arm64: Work out supported block level at compile time

arch/arm64/include/asm/kvm_pgtable.h

···
 
 #define KVM_PGTABLE_MAX_LEVELS		4U
 
+/*
+ * The largest supported block sizes for KVM (no 52-bit PA support):
+ *  - 4K (level 1):	1GB
+ *  - 16K (level 2):	32MB
+ *  - 64K (level 2):	512MB
+ */
+#ifdef CONFIG_ARM64_4K_PAGES
+#define KVM_PGTABLE_MIN_BLOCK_LEVEL	1U
+#else
+#define KVM_PGTABLE_MIN_BLOCK_LEVEL	2U
+#endif
+
 static inline u64 kvm_get_parange(u64 mmfr0)
 {
 	u64 parange = cpuid_feature_extract_unsigned_field(mmfr0,
···
 
 static inline bool kvm_level_supports_block_mapping(u32 level)
 {
-	/*
-	 * Reject invalid block mappings and don't bother with 4TB mappings for
-	 * 52-bit PAs.
-	 */
-	return !(level == 0 || (PAGE_SIZE != SZ_4K && level == 1));
+	return level >= KVM_PGTABLE_MIN_BLOCK_LEVEL;
 }
 
 /**

arch/arm64/include/asm/stage2_pgtable.h

···
 #include <linux/pgtable.h>
 
 /*
- * PGDIR_SHIFT determines the size a top-level page table entry can map
- * and depends on the number of levels in the page table. Compute the
- * PGDIR_SHIFT for a given number of levels.
- */
-#define pt_levels_pgdir_shift(lvls)	ARM64_HW_PGTABLE_LEVEL_SHIFT(4 - (lvls))
-
-/*
  * The hardware supports concatenation of up to 16 tables at stage2 entry
  * level and we use the feature whenever possible, which means we resolve 4
  * additional bits of address at the entry level.
···
 #define stage2_pgtable_levels(ipa)	ARM64_HW_PGTABLE_LEVELS((ipa) - 4)
 #define kvm_stage2_levels(kvm)		VTCR_EL2_LVLS(kvm->arch.vtcr)
 
-/* stage2_pgdir_shift() is the size mapped by top-level stage2 entry for the VM */
-#define stage2_pgdir_shift(kvm)		pt_levels_pgdir_shift(kvm_stage2_levels(kvm))
-#define stage2_pgdir_size(kvm)		(1ULL << stage2_pgdir_shift(kvm))
-#define stage2_pgdir_mask(kvm)		~(stage2_pgdir_size(kvm) - 1)
-
 /*
  * kvm_mmmu_cache_min_pages() is the number of pages required to install
  * a stage-2 translation. We pre-allocate the entry level page table at
  * the VM creation.
  */
 #define kvm_mmu_cache_min_pages(kvm)	(kvm_stage2_levels(kvm) - 1)
-
-static inline phys_addr_t
-stage2_pgd_addr_end(struct kvm *kvm, phys_addr_t addr, phys_addr_t end)
-{
-	phys_addr_t boundary = (addr + stage2_pgdir_size(kvm)) & stage2_pgdir_mask(kvm);
-
-	return (boundary - 1 < end - 1) ? boundary : end;
-}
 
 #endif	/* __ARM64_S2_PGTABLE_H_ */

arch/arm64/kvm/hyp/Makefile

···
 
 incdir := $(srctree)/$(src)/include
 subdir-asflags-y := -I$(incdir)
-subdir-ccflags-y := -I$(incdir)				\
-		    -fno-stack-protector		\
-		    -DDISABLE_BRANCH_PROFILING		\
-		    $(DISABLE_STACKLEAK_PLUGIN)
+subdir-ccflags-y := -I$(incdir)
 
 obj-$(CONFIG_KVM) += vhe/ nvhe/ pgtable.o

arch/arm64/kvm/hyp/nvhe/Makefile

···
 # will explode instantly (Words of Marc Zyngier). So introduce a generic flag
 # __DISABLE_TRACE_MMIO__ to disable MMIO tracing for nVHE KVM.
 ccflags-y := -D__KVM_NVHE_HYPERVISOR__ -D__DISABLE_EXPORTS -D__DISABLE_TRACE_MMIO__
+ccflags-y += -fno-stack-protector	\
+	     -DDISABLE_BRANCH_PROFILING	\
+	     $(DISABLE_STACKLEAK_PLUGIN)
 
 hostprogs := gen-hyprel
 HOST_EXTRACFLAGS += -I$(objtree)/include
···
 # Remove ftrace, Shadow Call Stack, and CFI CFLAGS.
 # This is equivalent to the 'notrace', '__noscs', and '__nocfi' annotations.
 KBUILD_CFLAGS := $(filter-out $(CC_FLAGS_FTRACE) $(CC_FLAGS_SCS) $(CC_FLAGS_CFI), $(KBUILD_CFLAGS))
+# Starting from 13.0.0 llvm emits SHT_REL section '.llvm.call-graph-profile'
+# when profile optimization is applied. gen-hyprel does not support SHT_REL and
+# causes a build failure. Remove profile optimization flags.
+KBUILD_CFLAGS := $(filter-out -fprofile-sample-use=% -fprofile-use=%, $(KBUILD_CFLAGS))
 
 # KVM nVHE code is run at a different exception code with a different map, so
 # compiler instrumentation that inserts callbacks or checks into the code may

arch/arm64/kvm/mmu.c

···
 
 static unsigned long io_map_base;
 
+static phys_addr_t stage2_range_addr_end(phys_addr_t addr, phys_addr_t end)
+{
+	phys_addr_t size = kvm_granule_size(KVM_PGTABLE_MIN_BLOCK_LEVEL);
+	phys_addr_t boundary = ALIGN_DOWN(addr + size, size);
+
+	return (boundary - 1 < end - 1) ? boundary : end;
+}
 
 /*
  * Release kvm_mmu_lock periodically if the memory region is large. Otherwise,
···
 		if (!pgt)
 			return -EINVAL;
 
-		next = stage2_pgd_addr_end(kvm, addr, end);
+		next = stage2_range_addr_end(addr, end);
 		ret = fn(pgt, addr, next - addr);
 		if (ret)
 			break;

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

···
 
 	memset(entry, 0, esz);
 
-	while (len > 0) {
+	while (true) {
 		int next_offset;
 		size_t byte_offset;
 
···
 			return next_offset;
 
 		byte_offset = next_offset * esz;
+		if (byte_offset >= len)
+			break;
+
 		id += next_offset;
 		gpa += byte_offset;
 		len -= byte_offset;

arch/riscv/include/asm/cacheflush.h

···
 
 #endif /* CONFIG_SMP */
 
-/*
- * The T-Head CMO errata internally probe the CBOM block size, but otherwise
- * don't depend on Zicbom.
- */
 extern unsigned int riscv_cbom_block_size;
-#ifdef CONFIG_RISCV_ISA_ZICBOM
 void riscv_init_cbom_blocksize(void);
-#else
-static inline void riscv_init_cbom_blocksize(void) { }
-#endif
 
 #ifdef CONFIG_RISCV_DMA_NONCOHERENT
 void riscv_noncoherent_supported(void);

arch/riscv/include/asm/kvm_vcpu_timer.h

···
 int kvm_riscv_vcpu_timer_reset(struct kvm_vcpu *vcpu);
 void kvm_riscv_vcpu_timer_restore(struct kvm_vcpu *vcpu);
 void kvm_riscv_guest_timer_init(struct kvm *kvm);
+void kvm_riscv_vcpu_timer_sync(struct kvm_vcpu *vcpu);
 void kvm_riscv_vcpu_timer_save(struct kvm_vcpu *vcpu);
 bool kvm_riscv_vcpu_timer_pending(struct kvm_vcpu *vcpu);
 

arch/riscv/kvm/vcpu.c

···
 				clear_bit(IRQ_VS_SOFT, &v->irqs_pending);
 		}
 	}
+
+	/* Sync-up timer CSRs */
+	kvm_riscv_vcpu_timer_sync(vcpu);
 }
 
 int kvm_riscv_vcpu_set_interrupt(struct kvm_vcpu *vcpu, unsigned int irq)

arch/riscv/kvm/vcpu_timer.c

···
 	kvm_riscv_vcpu_timer_unblocking(vcpu);
 }
 
+void kvm_riscv_vcpu_timer_sync(struct kvm_vcpu *vcpu)
+{
+	struct kvm_vcpu_timer *t = &vcpu->arch.timer;
+
+	if (!t->sstc_enabled)
+		return;
+
+#if defined(CONFIG_32BIT)
+	t->next_cycles = csr_read(CSR_VSTIMECMP);
+	t->next_cycles |= (u64)csr_read(CSR_VSTIMECMPH) << 32;
+#else
+	t->next_cycles = csr_read(CSR_VSTIMECMP);
+#endif
+}
+
 void kvm_riscv_vcpu_timer_save(struct kvm_vcpu *vcpu)
 {
 	struct kvm_vcpu_timer *t = &vcpu->arch.timer;
···
 	if (!t->sstc_enabled)
 		return;
 
-	t = &vcpu->arch.timer;
-#if defined(CONFIG_32BIT)
-	t->next_cycles = csr_read(CSR_VSTIMECMP);
-	t->next_cycles |= (u64)csr_read(CSR_VSTIMECMPH) << 32;
-#else
-	t->next_cycles = csr_read(CSR_VSTIMECMP);
-#endif
+	/*
+	 * The vstimecmp CSRs are saved by kvm_riscv_vcpu_timer_sync()
+	 * upon every VM exit so no need to save here.
+	 */
+
 	/* timer should be enabled for the remaining operations */
 	if (unlikely(!t->init_done))
 		return;

arch/riscv/mm/cacheflush.c

···
  * Copyright (C) 2017 SiFive
  */
 
+#include <linux/of.h>
 #include <asm/cacheflush.h>
 
 #ifdef CONFIG_SMP
···
 		flush_icache_all();
 }
 #endif /* CONFIG_MMU */
+
+unsigned int riscv_cbom_block_size;
+EXPORT_SYMBOL_GPL(riscv_cbom_block_size);
+
+void riscv_init_cbom_blocksize(void)
+{
+	struct device_node *node;
+	unsigned long cbom_hartid;
+	u32 val, probed_block_size;
+	int ret;
+
+	probed_block_size = 0;
+	for_each_of_cpu_node(node) {
+		unsigned long hartid;
+
+		ret = riscv_of_processor_hartid(node, &hartid);
+		if (ret)
+			continue;
+
+		/* set block-size for cbom extension if available */
+		ret = of_property_read_u32(node, "riscv,cbom-block-size", &val);
+		if (ret)
+			continue;
+
+		if (!probed_block_size) {
+			probed_block_size = val;
+			cbom_hartid = hartid;
+		} else {
+			if (probed_block_size != val)
+				pr_warn("cbom-block-size mismatched between harts %lu and %lu\n",
+					cbom_hartid, hartid);
+		}
+	}
+
+	if (probed_block_size)
+		riscv_cbom_block_size = probed_block_size;
+}

arch/riscv/mm/dma-noncoherent.c

···
 #include <linux/dma-direct.h>
 #include <linux/dma-map-ops.h>
 #include <linux/mm.h>
-#include <linux/of.h>
-#include <linux/of_device.h>
 #include <asm/cacheflush.h>
-
-unsigned int riscv_cbom_block_size;
-EXPORT_SYMBOL_GPL(riscv_cbom_block_size);
 
 static bool noncoherent_supported;
 
···
 
 	dev->dma_coherent = coherent;
 }
-
-#ifdef CONFIG_RISCV_ISA_ZICBOM
-void riscv_init_cbom_blocksize(void)
-{
-	struct device_node *node;
-	unsigned long cbom_hartid;
-	u32 val, probed_block_size;
-	int ret;
-
-	probed_block_size = 0;
-	for_each_of_cpu_node(node) {
-		unsigned long hartid;
-
-		ret = riscv_of_processor_hartid(node, &hartid);
-		if (ret)
-			continue;
-
-		/* set block-size for cbom extension if available */
-		ret = of_property_read_u32(node, "riscv,cbom-block-size", &val);
-		if (ret)
-			continue;
-
-		if (!probed_block_size) {
-			probed_block_size = val;
-			cbom_hartid = hartid;
-		} else {
-			if (probed_block_size != val)
-				pr_warn("cbom-block-size mismatched between harts %lu and %lu\n",
-					cbom_hartid, hartid);
-		}
-	}
-
-	if (probed_block_size)
-		riscv_cbom_block_size = probed_block_size;
-}
-#endif
 
 void riscv_noncoherent_supported(void)
 {

arch/x86/kvm/x86.c

···
 	return 0;
 }
 
-static int kvm_vm_ioctl_set_msr_filter(struct kvm *kvm, void __user *argp)
+static int kvm_vm_ioctl_set_msr_filter(struct kvm *kvm,
+				       struct kvm_msr_filter *filter)
 {
-	struct kvm_msr_filter __user *user_msr_filter = argp;
 	struct kvm_x86_msr_filter *new_filter, *old_filter;
-	struct kvm_msr_filter filter;
 	bool default_allow;
 	bool empty = true;
 	int r = 0;
 	u32 i;
 
-	if (copy_from_user(&filter, user_msr_filter, sizeof(filter)))
-		return -EFAULT;
-
-	if (filter.flags & ~KVM_MSR_FILTER_DEFAULT_DENY)
+	if (filter->flags & ~KVM_MSR_FILTER_DEFAULT_DENY)
 		return -EINVAL;
 
-	for (i = 0; i < ARRAY_SIZE(filter.ranges); i++)
-		empty &= !filter.ranges[i].nmsrs;
+	for (i = 0; i < ARRAY_SIZE(filter->ranges); i++)
+		empty &= !filter->ranges[i].nmsrs;
 
-	default_allow = !(filter.flags & KVM_MSR_FILTER_DEFAULT_DENY);
+	default_allow = !(filter->flags & KVM_MSR_FILTER_DEFAULT_DENY);
 	if (empty && !default_allow)
 		return -EINVAL;
 
···
 	if (!new_filter)
 		return -ENOMEM;
 
-	for (i = 0; i < ARRAY_SIZE(filter.ranges); i++) {
-		r = kvm_add_msr_filter(new_filter, &filter.ranges[i]);
+	for (i = 0; i < ARRAY_SIZE(filter->ranges); i++) {
+		r = kvm_add_msr_filter(new_filter, &filter->ranges[i]);
 		if (r) {
 			kvm_free_msr_filter(new_filter);
 			return r;
···
 
 	return 0;
 }
+
+#ifdef CONFIG_KVM_COMPAT
+/* for KVM_X86_SET_MSR_FILTER */
+struct kvm_msr_filter_range_compat {
+	__u32 flags;
+	__u32 nmsrs;
+	__u32 base;
+	__u32 bitmap;
+};
+
+struct kvm_msr_filter_compat {
+	__u32 flags;
+	struct kvm_msr_filter_range_compat ranges[KVM_MSR_FILTER_MAX_RANGES];
+};
+
+#define KVM_X86_SET_MSR_FILTER_COMPAT _IOW(KVMIO, 0xc6, struct kvm_msr_filter_compat)
+
+long kvm_arch_vm_compat_ioctl(struct file *filp, unsigned int ioctl,
+			      unsigned long arg)
+{
+	void __user *argp = (void __user *)arg;
+	struct kvm *kvm = filp->private_data;
+	long r = -ENOTTY;
+
+	switch (ioctl) {
+	case KVM_X86_SET_MSR_FILTER_COMPAT: {
+		struct kvm_msr_filter __user *user_msr_filter = argp;
+		struct kvm_msr_filter_compat filter_compat;
+		struct kvm_msr_filter filter;
+		int i;
+
+		if (copy_from_user(&filter_compat, user_msr_filter,
+				   sizeof(filter_compat)))
+			return -EFAULT;
+
+		filter.flags = filter_compat.flags;
+		for (i = 0; i < ARRAY_SIZE(filter.ranges); i++) {
+			struct kvm_msr_filter_range_compat *cr;
+
+			cr = &filter_compat.ranges[i];
+			filter.ranges[i] = (struct kvm_msr_filter_range) {
+				.flags = cr->flags,
+				.nmsrs = cr->nmsrs,
+				.base = cr->base,
+				.bitmap = (__u8 *)(ulong)cr->bitmap,
+			};
+		}
+
+		r = kvm_vm_ioctl_set_msr_filter(kvm, &filter);
+		break;
+	}
+	}
+
+	return r;
+}
+#endif
 
 #ifdef CONFIG_HAVE_KVM_PM_NOTIFIER
 static int kvm_arch_suspend_notifier(struct kvm *kvm)
···
 	case KVM_SET_PMU_EVENT_FILTER:
 		r = kvm_vm_ioctl_set_pmu_event_filter(kvm, argp);
 		break;
-	case KVM_X86_SET_MSR_FILTER:
-		r = kvm_vm_ioctl_set_msr_filter(kvm, argp);
+	case KVM_X86_SET_MSR_FILTER: {
+		struct kvm_msr_filter __user *user_msr_filter = argp;
+		struct kvm_msr_filter filter;
+
+		if (copy_from_user(&filter, user_msr_filter, sizeof(filter)))
+			return -EFAULT;
+
+		r = kvm_vm_ioctl_set_msr_filter(kvm, &filter);
 		break;
+	}
 	default:
 		r = -ENOTTY;
 	}

include/linux/kvm_host.h

···
 			    struct kvm_enable_cap *cap);
 long kvm_arch_vm_ioctl(struct file *filp,
 		       unsigned int ioctl, unsigned long arg);
+long kvm_arch_vm_compat_ioctl(struct file *filp, unsigned int ioctl,
+			      unsigned long arg);
 
 int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu);
 int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu);

tools/include/uapi/linux/kvm.h

···
 #define KVM_CAP_VM_DISABLE_NX_HUGE_PAGES 220
 #define KVM_CAP_S390_ZPCI_OP 221
 #define KVM_CAP_S390_CPU_TOPOLOGY 222
+#define KVM_CAP_DIRTY_LOG_RING_ACQ_REL 223
 
 #ifdef KVM_CAP_IRQ_ROUTING
 

tools/testing/selftests/kvm/aarch64/vgic_init.c

···
 					     : KVM_DEV_TYPE_ARM_VGIC_V2;
 
 	if (!__kvm_test_create_device(v.vm, other)) {
-		ret = __kvm_test_create_device(v.vm, other);
-		TEST_ASSERT(ret && (errno == EINVAL || errno == EEXIST),
+		ret = __kvm_create_device(v.vm, other);
+		TEST_ASSERT(ret < 0 && (errno == EINVAL || errno == EEXIST),
 				"create GIC device while other version exists");
 	}
 

tools/testing/selftests/kvm/memslot_modification_stress_test.c

···
 static void add_remove_memslot(struct kvm_vm *vm, useconds_t delay,
 			       uint64_t nr_modifications)
 {
-	const uint64_t pages = 1;
+	uint64_t pages = max_t(int, vm->page_size, getpagesize()) / vm->page_size;
 	uint64_t gpa;
 	int i;
 

virt/kvm/kvm_main.c

···
 	};
 };
 
+long __weak kvm_arch_vm_compat_ioctl(struct file *filp, unsigned int ioctl,
+				     unsigned long arg)
+{
+	return -ENOTTY;
+}
+
 static long kvm_vm_compat_ioctl(struct file *filp,
 			   unsigned int ioctl, unsigned long arg)
 {
···
 
 	if (kvm->mm != current->mm || kvm->vm_dead)
 		return -EIO;
+
+	r = kvm_arch_vm_compat_ioctl(filp, ioctl, arg);
+	if (r != -ENOTTY)
+		return r;
+
 	switch (ioctl) {
 #ifdef CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT
 	case KVM_CLEAR_DIRTY_LOG: {