From 3b5c082bbfa20d9a57924edd655bbe63fe98ab06 Mon Sep 17 00:00:00 2001 From: Oliver Upton Date: Fri, 7 Oct 2022 23:41:50 +0000 Subject: [PATCH 1/5] KVM: arm64: Work out supported block level at compile time Work out the minimum page table level where KVM supports block mappings at compile time. While at it, rewrite the comment around supported block mappings to directly describe what KVM supports instead of phrasing in terms of what it does not. Signed-off-by: Oliver Upton Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20221007234151.461779-2-oliver.upton@linux.dev --- arch/arm64/include/asm/kvm_pgtable.h | 18 +++++++++++++----- 1 file changed, 13 insertions(+), 5 deletions(-) diff --git a/arch/arm64/include/asm/kvm_pgtable.h b/arch/arm64/include/asm/kvm_pgtable.h index 1b098bd4cd37..3252eb50ecfe 100644 --- a/arch/arm64/include/asm/kvm_pgtable.h +++ b/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; } /** From 5994bc9e05c2f8811f233aa434e391cd2783f0f5 Mon Sep 17 00:00:00 2001 From: Oliver Upton Date: Fri, 7 Oct 2022 23:41:51 +0000 Subject: [PATCH 2/5] KVM: arm64: Limit stage2_apply_range() batch size to largest block Presently stage2_apply_range() works on a batch of memory addressed by a stage 2 root table entry for the VM. Depending on the IPA limit of the VM and PAGE_SIZE of the host, this could address a massive range of memory. Some examples: 4 level, 4K paging -> 512 GB batch size 3 level, 64K paging -> 4TB batch size Unsurprisingly, working on such a large range of memory can lead to soft lockups. When running dirty_log_perf_test: ./dirty_log_perf_test -m -2 -s anonymous_thp -b 4G -v 48 watchdog: BUG: soft lockup - CPU#0 stuck for 45s! [dirty_log_perf_:16703] Modules linked in: vfat fat cdc_ether usbnet mii xhci_pci xhci_hcd sha3_generic gq(O) CPU: 0 PID: 16703 Comm: dirty_log_perf_ Tainted: G O 6.0.0-smp-DEV #1 pstate: 80400009 (Nzcv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--) pc : dcache_clean_inval_poc+0x24/0x38 lr : clean_dcache_guest_page+0x28/0x4c sp : ffff800021763990 pmr_save: 000000e0 x29: ffff800021763990 x28: 0000000000000005 x27: 0000000000000de0 x26: 0000000000000001 x25: 00400830b13bc77f x24: ffffad4f91ead9c0 x23: 0000000000000000 x22: ffff8000082ad9c8 x21: 0000fffafa7bc000 x20: ffffad4f9066ce50 x19: 0000000000000003 x18: ffffad4f92402000 x17: 000000000000011b x16: 000000000000011b x15: 0000000000000124 x14: ffff07ff8301d280 x13: 0000000000000000 x12: 00000000ffffffff x11: 0000000000010001 x10: fffffc0000000000 x9 : ffffad4f9069e580 x8 : 000000000000000c x7 : 0000000000000000 x6 : 000000000000003f x5 : ffff07ffa2076980 x4 : 0000000000000001 x3 : 000000000000003f x2 : 0000000000000040 x1 : ffff0830313bd000 x0 : ffff0830313bcc40 Call trace: dcache_clean_inval_poc+0x24/0x38 stage2_unmap_walker+0x138/0x1ec __kvm_pgtable_walk+0x130/0x1d4 __kvm_pgtable_walk+0x170/0x1d4 __kvm_pgtable_walk+0x170/0x1d4 __kvm_pgtable_walk+0x170/0x1d4 kvm_pgtable_stage2_unmap+0xc4/0xf8 kvm_arch_flush_shadow_memslot+0xa4/0x10c kvm_set_memslot+0xb8/0x454 __kvm_set_memory_region+0x194/0x244 kvm_vm_ioctl_set_memory_region+0x58/0x7c kvm_vm_ioctl+0x49c/0x560 __arm64_sys_ioctl+0x9c/0xd4 invoke_syscall+0x4c/0x124 el0_svc_common+0xc8/0x194 do_el0_svc+0x38/0xc0 el0_svc+0x2c/0xa4 el0t_64_sync_handler+0x84/0xf0 el0t_64_sync+0x1a0/0x1a4 Use the largest supported block mapping for the configured page size as the batch granularity. In so doing the walker is guaranteed to visit a leaf only once. Signed-off-by: Oliver Upton Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20221007234151.461779-3-oliver.upton@linux.dev --- arch/arm64/include/asm/stage2_pgtable.h | 20 -------------------- arch/arm64/kvm/mmu.c | 9 ++++++++- 2 files changed, 8 insertions(+), 21 deletions(-) diff --git a/arch/arm64/include/asm/stage2_pgtable.h b/arch/arm64/include/asm/stage2_pgtable.h index fe341a6578c3..c8dca8ae359c 100644 --- a/arch/arm64/include/asm/stage2_pgtable.h +++ b/arch/arm64/include/asm/stage2_pgtable.h @@ -10,13 +10,6 @@ #include -/* - * 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 @@ -30,11 +23,6 @@ #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 @@ -42,12 +30,4 @@ */ #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_ */ diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c index c9a13e487187..caf6cfeff35b 100644 --- a/arch/arm64/kvm/mmu.c +++ b/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; From 837d632a383f13df7a67207a196d6eb4aeb4adca Mon Sep 17 00:00:00 2001 From: Vincent Donnefort Date: Tue, 4 Oct 2022 16:42:16 +0100 Subject: [PATCH 3/5] KVM: arm64: Enable stack protection and branch profiling for VHE For historical reasons, the VHE code inherited the build configuration from nVHE. Now those two parts have their own folder and makefile, we can enable stack protection and branch profiling for VHE. Signed-off-by: Vincent Donnefort Reviewed-by: Quentin Perret Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20221004154216.2833636-1-vdonnefort@google.com --- arch/arm64/kvm/hyp/Makefile | 5 +---- arch/arm64/kvm/hyp/nvhe/Makefile | 3 +++ 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/arch/arm64/kvm/hyp/Makefile b/arch/arm64/kvm/hyp/Makefile index 687598e41b21..a38dea6186c9 100644 --- a/arch/arm64/kvm/hyp/Makefile +++ b/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 diff --git a/arch/arm64/kvm/hyp/nvhe/Makefile b/arch/arm64/kvm/hyp/nvhe/Makefile index b5c5119c7396..48f6ae7cc6e6 100644 --- a/arch/arm64/kvm/hyp/nvhe/Makefile +++ b/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 From 8a6ffcbe26fd14d58075dcf3cbdf1b5b69b20402 Mon Sep 17 00:00:00 2001 From: Zenghui Yu Date: Sun, 9 Oct 2022 11:31:31 +0800 Subject: [PATCH 4/5] KVM: arm64: selftests: Fix multiple versions of GIC creation Commit 98f94ce42ac6 ("KVM: selftests: Move KVM_CREATE_DEVICE_TEST code to separate helper") wrongly converted a "real" GIC device creation to __kvm_test_create_device() and caused the test failure on my D05 (which supports v2 emulation). Fix it. Fixes: 98f94ce42ac6 ("KVM: selftests: Move KVM_CREATE_DEVICE_TEST code to separate helper") Signed-off-by: Zenghui Yu Reviewed-by: Oliver Upton Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20221009033131.365-1-yuzenghui@huawei.com --- tools/testing/selftests/kvm/aarch64/vgic_init.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/kvm/aarch64/vgic_init.c b/tools/testing/selftests/kvm/aarch64/vgic_init.c index e05ecb31823f..9c131d977a1b 100644 --- a/tools/testing/selftests/kvm/aarch64/vgic_init.c +++ b/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"); } From 05c2224d4b049406b0545a10be05280ff4b8ba0a Mon Sep 17 00:00:00 2001 From: Gavin Shan Date: Thu, 13 Oct 2022 14:30:20 +0800 Subject: [PATCH 5/5] KVM: selftests: Fix number of pages for memory slot in memslot_modification_stress_test It's required by vm_userspace_mem_region_add() that memory size should be aligned to host page size. However, one guest page is provided by memslot_modification_stress_test. It triggers failure in the scenario of 64KB-page-size-host and 4KB-page-size-guest, as the following messages indicate. # ./memslot_modification_stress_test Testing guest mode: PA-bits:40, VA-bits:48, 4K pages guest physical test memory: [0xffbfff0000, 0xffffff0000) Finished creating vCPUs Started all vCPUs ==== Test Assertion Failure ==== lib/kvm_util.c:824: vm_adjust_num_guest_pages(vm->mode, npages) == npages pid=5712 tid=5712 errno=0 - Success 1 0x0000000000404eeb: vm_userspace_mem_region_add at kvm_util.c:822 2 0x0000000000401a5b: add_remove_memslot at memslot_modification_stress_test.c:82 3 (inlined by) run_test at memslot_modification_stress_test.c:110 4 0x0000000000402417: for_each_guest_mode at guest_modes.c:100 5 0x00000000004016a7: main at memslot_modification_stress_test.c:187 6 0x0000ffffb8cd4383: ?? ??:0 7 0x0000000000401827: _start at :? Number of guest pages is not compatible with the host. Try npages=16 Fix the issue by providing 16 guest pages to the memory slot for this particular combination of 64KB-page-size-host and 4KB-page-size-guest on aarch64. Fixes: ef4c9f4f65462 ("KVM: selftests: Fix 32-bit truncation of vm_get_max_gfn()") Signed-off-by: Gavin Shan Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20221013063020.201856-1-gshan@redhat.com --- tools/testing/selftests/kvm/memslot_modification_stress_test.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/kvm/memslot_modification_stress_test.c b/tools/testing/selftests/kvm/memslot_modification_stress_test.c index 6ee7e1dde404..bb1d17a1171b 100644 --- a/tools/testing/selftests/kvm/memslot_modification_stress_test.c +++ b/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;