Merge tag 'kvmarm-fixes-6.1-1' of git://git.kernel.org/pub/scm/linux/kernel/git/kvmarm/kvmarm into HEAD

KVM/arm64 fixes for 6.1, take #1

- 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

Author: bonzini

arch/arm64/include/asm/kvm_pgtable.h

@@ -13,6 +13,18 @@
 
 #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,
@@ -58,11 +70,7 @@ static inline u64 kvm_granule_size(u32 level)
 
 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

@@ -10,13 +10,6 @@
 
 #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
@@ -30,24 +23,11 @@
 #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

@@ -5,9 +5,6 @@
 
 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

@@ -10,6 +10,9 @@ asflags-y := -D__KVM_NVHE_HYPERVISOR__ -D__DISABLE_EXPORTS
 # 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

arch/arm64/kvm/mmu.c

@@ -31,6 +31,13 @@ static phys_addr_t hyp_idmap_vector;
 
 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,
@@ -52,7 +59,7 @@ static int stage2_apply_range(struct kvm *kvm, phys_addr_t addr,
 		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;

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

@@ -662,8 +662,8 @@ int test_kvm_device(uint32_t gic_dev_type)
 					     : 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

@@ -67,7 +67,7 @@ struct memslot_antagonist_args {
 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;