From e5d83c74a5800c2a1fa3ba982c1c4b2b39ae6db2 Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Thu, 16 Feb 2017 10:40:56 +0100 Subject: kvm: make KVM_CAP_ENABLE_CAP_VM architecture agnostic The first such capability to be handled in virt/kvm/ will be manual dirty page reprotection. Signed-off-by: Paolo Bonzini --- Documentation/virtual/kvm/api.txt | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) (limited to 'Documentation') diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt index cd209f7730af..1071c10cf1c7 100644 --- a/Documentation/virtual/kvm/api.txt +++ b/Documentation/virtual/kvm/api.txt @@ -1129,10 +1129,15 @@ documentation when it pops into existence). 4.37 KVM_ENABLE_CAP -Capability: KVM_CAP_ENABLE_CAP, KVM_CAP_ENABLE_CAP_VM -Architectures: x86 (only KVM_CAP_ENABLE_CAP_VM), - mips (only KVM_CAP_ENABLE_CAP), ppc, s390 -Type: vcpu ioctl, vm ioctl (with KVM_CAP_ENABLE_CAP_VM) +Capability: KVM_CAP_ENABLE_CAP +Architectures: mips, ppc, s390 +Type: vcpu ioctl +Parameters: struct kvm_enable_cap (in) +Returns: 0 on success; -1 on error + +Capability: KVM_CAP_ENABLE_CAP_VM +Architectures: all +Type: vcpu ioctl Parameters: struct kvm_enable_cap (in) Returns: 0 on success; -1 on error -- cgit v1.2.3 From 2a31b9db153530df4aa02dac8c32837bf5f47019 Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Tue, 23 Oct 2018 02:36:47 +0200 Subject: kvm: introduce manual dirty log reprotect There are two problems with KVM_GET_DIRTY_LOG. First, and less important, it can take kvm->mmu_lock for an extended period of time. Second, its user can actually see many false positives in some cases. The latter is due to a benign race like this: 1. KVM_GET_DIRTY_LOG returns a set of dirty pages and write protects them. 2. The guest modifies the pages, causing them to be marked ditry. 3. Userspace actually copies the pages. 4. KVM_GET_DIRTY_LOG returns those pages as dirty again, even though they were not written to since (3). This is especially a problem for large guests, where the time between (1) and (3) can be substantial. This patch introduces a new capability which, when enabled, makes KVM_GET_DIRTY_LOG not write-protect the pages it returns. Instead, userspace has to explicitly clear the dirty log bits just before using the content of the page. The new KVM_CLEAR_DIRTY_LOG ioctl can also operate on a 64-page granularity rather than requiring to sync a full memslot; this way, the mmu_lock is taken for small amounts of time, and only a small amount of time will pass between write protection of pages and the sending of their content. Signed-off-by: Paolo Bonzini --- Documentation/virtual/kvm/api.txt | 67 +++++++++++ arch/mips/kvm/mips.c | 23 ++++ arch/x86/kvm/x86.c | 27 +++++ include/linux/kvm_host.h | 5 + include/uapi/linux/kvm.h | 15 +++ tools/testing/selftests/kvm/Makefile | 2 + tools/testing/selftests/kvm/clear_dirty_log_test.c | 2 + tools/testing/selftests/kvm/dirty_log_test.c | 19 +++ tools/testing/selftests/kvm/include/kvm_util.h | 2 + tools/testing/selftests/kvm/lib/kvm_util.c | 13 ++ virt/kvm/arm/arm.c | 16 +++ virt/kvm/kvm_main.c | 132 ++++++++++++++++++--- 12 files changed, 306 insertions(+), 17 deletions(-) create mode 100644 tools/testing/selftests/kvm/clear_dirty_log_test.c (limited to 'Documentation') diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt index 1071c10cf1c7..f2c345f7b630 100644 --- a/Documentation/virtual/kvm/api.txt +++ b/Documentation/virtual/kvm/api.txt @@ -305,6 +305,9 @@ the address space for which you want to return the dirty bitmap. They must be less than the value that KVM_CHECK_EXTENSION returns for the KVM_CAP_MULTI_ADDRESS_SPACE capability. +The bits in the dirty bitmap are cleared before the ioctl returns, unless +KVM_CAP_MANUAL_DIRTY_LOG_PROTECT is enabled. For more information, +see the description of the capability. 4.9 KVM_SET_MEMORY_ALIAS @@ -3758,6 +3761,46 @@ Coalesced pio is based on coalesced mmio. There is little difference between coalesced mmio and pio except that coalesced pio records accesses to I/O ports. +4.117 KVM_CLEAR_DIRTY_LOG (vm ioctl) + +Capability: KVM_CAP_MANUAL_DIRTY_LOG_PROTECT +Architectures: x86 +Type: vm ioctl +Parameters: struct kvm_dirty_log (in) +Returns: 0 on success, -1 on error + +/* for KVM_CLEAR_DIRTY_LOG */ +struct kvm_clear_dirty_log { + __u32 slot; + __u32 num_pages; + __u64 first_page; + union { + void __user *dirty_bitmap; /* one bit per page */ + __u64 padding; + }; +}; + +The ioctl clears the dirty status of pages in a memory slot, according to +the bitmap that is passed in struct kvm_clear_dirty_log's dirty_bitmap +field. Bit 0 of the bitmap corresponds to page "first_page" in the +memory slot, and num_pages is the size in bits of the input bitmap. +Both first_page and num_pages must be a multiple of 64. For each bit +that is set in the input bitmap, the corresponding page is marked "clean" +in KVM's dirty bitmap, and dirty tracking is re-enabled for that page +(for example via write-protection, or by clearing the dirty bit in +a page table entry). + +If KVM_CAP_MULTI_ADDRESS_SPACE is available, bits 16-31 specifies +the address space for which you want to return the dirty bitmap. +They must be less than the value that KVM_CHECK_EXTENSION returns for +the KVM_CAP_MULTI_ADDRESS_SPACE capability. + +This ioctl is mostly useful when KVM_CAP_MANUAL_DIRTY_LOG_PROTECT +is enabled; for more information, see the description of the capability. +However, it can always be used as long as KVM_CHECK_EXTENSION confirms +that KVM_CAP_MANUAL_DIRTY_LOG_PROTECT is present. + + 5. The kvm_run structure ------------------------ @@ -4652,6 +4695,30 @@ and injected exceptions. * For the new DR6 bits, note that bit 16 is set iff the #DB exception will clear DR6.RTM. +7.18 KVM_CAP_MANUAL_DIRTY_LOG_PROTECT + +Architectures: all +Parameters: args[0] whether feature should be enabled or not + +With this capability enabled, KVM_GET_DIRTY_LOG will not automatically +clear and write-protect all pages that are returned as dirty. +Rather, userspace will have to do this operation separately using +KVM_CLEAR_DIRTY_LOG. + +At the cost of a slightly more complicated operation, this provides better +scalability and responsiveness for two reasons. First, +KVM_CLEAR_DIRTY_LOG ioctl can operate on a 64-page granularity rather +than requiring to sync a full memslot; this ensures that KVM does not +take spinlocks for an extended period of time. Second, in some cases a +large amount of time can pass between a call to KVM_GET_DIRTY_LOG and +userspace actually using the data in the page. Pages can be modified +during this time, which is inefficint for both the guest and userspace: +the guest will incur a higher penalty due to write protection faults, +while userspace can see false reports of dirty pages. Manual reprotection +helps reducing this time, improving guest performance and reducing the +number of dirty log false positives. + + 8. Other capabilities. ---------------------- diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c index 3898e657952e..3734cd58895e 100644 --- a/arch/mips/kvm/mips.c +++ b/arch/mips/kvm/mips.c @@ -1023,6 +1023,29 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log) return r; } +int kvm_vm_ioctl_clear_dirty_log(struct kvm *kvm, struct kvm_clear_dirty_log *log) +{ + struct kvm_memslots *slots; + struct kvm_memory_slot *memslot; + bool flush = false; + int r; + + mutex_lock(&kvm->slots_lock); + + r = kvm_clear_dirty_log_protect(kvm, log, &flush); + + if (flush) { + slots = kvm_memslots(kvm); + memslot = id_to_memslot(slots, log->slot); + + /* Let implementation handle TLB/GVA invalidation */ + kvm_mips_callbacks->flush_shadow_memslot(kvm, memslot); + } + + mutex_unlock(&kvm->slots_lock); + return r; +} + long kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { long r; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 448f011aa317..6af846c54660 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -4418,6 +4418,33 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log) return r; } +int kvm_vm_ioctl_clear_dirty_log(struct kvm *kvm, struct kvm_clear_dirty_log *log) +{ + bool flush = false; + int r; + + mutex_lock(&kvm->slots_lock); + + /* + * Flush potentially hardware-cached dirty pages to dirty_bitmap. + */ + if (kvm_x86_ops->flush_log_dirty) + kvm_x86_ops->flush_log_dirty(kvm); + + r = kvm_clear_dirty_log_protect(kvm, log, &flush); + + /* + * All the TLBs can be flushed out of mmu lock, see the comments in + * kvm_mmu_slot_remove_write_access(). + */ + lockdep_assert_held(&kvm->slots_lock); + if (flush) + kvm_flush_remote_tlbs(kvm); + + mutex_unlock(&kvm->slots_lock); + return r; +} + int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_event, bool line_status) { diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 8c56b2873b13..e065aeaae29e 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -449,6 +449,7 @@ struct kvm { #endif long tlbs_dirty; struct list_head devices; + bool manual_dirty_log_protect; struct dentry *debugfs_dentry; struct kvm_stat_data **debugfs_stat_data; struct srcu_struct srcu; @@ -754,6 +755,8 @@ int kvm_get_dirty_log(struct kvm *kvm, int kvm_get_dirty_log_protect(struct kvm *kvm, struct kvm_dirty_log *log, bool *flush); +int kvm_clear_dirty_log_protect(struct kvm *kvm, + struct kvm_clear_dirty_log *log, bool *flush); void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm, struct kvm_memory_slot *slot, @@ -762,6 +765,8 @@ void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm, int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log); +int kvm_vm_ioctl_clear_dirty_log(struct kvm *kvm, + struct kvm_clear_dirty_log *log); int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_level, bool line_status); diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 2b7a652c9fa4..9fe35f1ac938 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -492,6 +492,17 @@ struct kvm_dirty_log { }; }; +/* for KVM_CLEAR_DIRTY_LOG */ +struct kvm_clear_dirty_log { + __u32 slot; + __u32 num_pages; + __u64 first_page; + union { + void __user *dirty_bitmap; /* one bit per page */ + __u64 padding2; + }; +}; + /* for KVM_SET_SIGNAL_MASK */ struct kvm_signal_mask { __u32 len; @@ -975,6 +986,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_HYPERV_ENLIGHTENED_VMCS 163 #define KVM_CAP_EXCEPTION_PAYLOAD 164 #define KVM_CAP_ARM_VM_IPA_SIZE 165 +#define KVM_CAP_MANUAL_DIRTY_LOG_PROTECT 166 #ifdef KVM_CAP_IRQ_ROUTING @@ -1421,6 +1433,9 @@ struct kvm_enc_region { #define KVM_GET_NESTED_STATE _IOWR(KVMIO, 0xbe, struct kvm_nested_state) #define KVM_SET_NESTED_STATE _IOW(KVMIO, 0xbf, struct kvm_nested_state) +/* Available with KVM_CAP_MANUAL_DIRTY_LOG_PROTECT */ +#define KVM_CLEAR_DIRTY_LOG _IOWR(KVMIO, 0xc0, struct kvm_clear_dirty_log) + /* Secure Encrypted Virtualization command */ enum sev_cmd_id { /* Guest initialization commands */ diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index 52bfe5e76907..caaa0d5eba92 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -16,8 +16,10 @@ TEST_GEN_PROGS_x86_64 += x86_64/cr4_cpuid_sync_test TEST_GEN_PROGS_x86_64 += x86_64/state_test TEST_GEN_PROGS_x86_64 += x86_64/evmcs_test TEST_GEN_PROGS_x86_64 += dirty_log_test +TEST_GEN_PROGS_x86_64 += clear_dirty_log_test TEST_GEN_PROGS_aarch64 += dirty_log_test +TEST_GEN_PROGS_aarch64 += clear_dirty_log_test TEST_GEN_PROGS += $(TEST_GEN_PROGS_$(UNAME_M)) LIBKVM += $(LIBKVM_$(UNAME_M)) diff --git a/tools/testing/selftests/kvm/clear_dirty_log_test.c b/tools/testing/selftests/kvm/clear_dirty_log_test.c new file mode 100644 index 000000000000..749336937d37 --- /dev/null +++ b/tools/testing/selftests/kvm/clear_dirty_log_test.c @@ -0,0 +1,2 @@ +#define USE_CLEAR_DIRTY_LOG +#include "dirty_log_test.c" diff --git a/tools/testing/selftests/kvm/dirty_log_test.c b/tools/testing/selftests/kvm/dirty_log_test.c index aeff95a91b15..4629c7ccfa28 100644 --- a/tools/testing/selftests/kvm/dirty_log_test.c +++ b/tools/testing/selftests/kvm/dirty_log_test.c @@ -275,6 +275,14 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations, vm = create_vm(mode, VCPU_ID, guest_num_pages, guest_code); +#ifdef USE_CLEAR_DIRTY_LOG + struct kvm_enable_cap cap = {}; + + cap.cap = KVM_CAP_MANUAL_DIRTY_LOG_PROTECT; + cap.args[0] = 1; + vm_enable_cap(vm, &cap); +#endif + /* Add an extra memory slot for testing dirty logging */ vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, guest_test_mem, @@ -316,6 +324,10 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations, /* Give the vcpu thread some time to dirty some pages */ usleep(interval * 1000); kvm_vm_get_dirty_log(vm, TEST_MEM_SLOT_INDEX, bmap); +#ifdef USE_CLEAR_DIRTY_LOG + kvm_vm_clear_dirty_log(vm, TEST_MEM_SLOT_INDEX, bmap, 0, + DIV_ROUND_UP(host_num_pages, 64) * 64); +#endif vm_dirty_log_verify(bmap); iteration++; sync_global_to_guest(vm, iteration); @@ -392,6 +404,13 @@ int main(int argc, char *argv[]) unsigned int mode; int opt, i; +#ifdef USE_CLEAR_DIRTY_LOG + if (!kvm_check_cap(KVM_CAP_MANUAL_DIRTY_LOG_PROTECT)) { + fprintf(stderr, "KVM_CLEAR_DIRTY_LOG not available, skipping tests\n"); + exit(KSFT_SKIP); + } +#endif + while ((opt = getopt(argc, argv, "hi:I:o:tm:")) != -1) { switch (opt) { case 'i': diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h index a4e59e3b4826..c51bfaba017a 100644 --- a/tools/testing/selftests/kvm/include/kvm_util.h +++ b/tools/testing/selftests/kvm/include/kvm_util.h @@ -58,6 +58,8 @@ void kvm_vm_free(struct kvm_vm *vmp); void kvm_vm_restart(struct kvm_vm *vmp, int perm); void kvm_vm_release(struct kvm_vm *vmp); void kvm_vm_get_dirty_log(struct kvm_vm *vm, int slot, void *log); +void kvm_vm_clear_dirty_log(struct kvm_vm *vm, int slot, void *log, + uint64_t first_page, uint32_t num_pages); int kvm_memcmp_hva_gva(void *hva, struct kvm_vm *vm, const vm_vaddr_t gva, size_t len); diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c index 1b41e71283d5..c9e94d6503af 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util.c +++ b/tools/testing/selftests/kvm/lib/kvm_util.c @@ -231,6 +231,19 @@ void kvm_vm_get_dirty_log(struct kvm_vm *vm, int slot, void *log) strerror(-ret)); } +void kvm_vm_clear_dirty_log(struct kvm_vm *vm, int slot, void *log, + uint64_t first_page, uint32_t num_pages) +{ + struct kvm_clear_dirty_log args = { .dirty_bitmap = log, .slot = slot, + .first_page = first_page, + .num_pages = num_pages }; + int ret; + + ret = ioctl(vm->fd, KVM_CLEAR_DIRTY_LOG, &args); + TEST_ASSERT(ret == 0, "%s: KVM_CLEAR_DIRTY_LOG failed: %s", + strerror(-ret)); +} + /* * Userspace Memory Region Find * diff --git a/virt/kvm/arm/arm.c b/virt/kvm/arm/arm.c index 120a2663dab9..e91adf77d99a 100644 --- a/virt/kvm/arm/arm.c +++ b/virt/kvm/arm/arm.c @@ -1219,6 +1219,22 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log) return r; } +int kvm_vm_ioctl_clear_dirty_log(struct kvm *kvm, struct kvm_clear_dirty_log *log) +{ + bool flush = false; + int r; + + mutex_lock(&kvm->slots_lock); + + r = kvm_clear_dirty_log_protect(kvm, log, &flush); + + if (flush) + kvm_flush_remote_tlbs(kvm); + + mutex_unlock(&kvm->slots_lock); + return r; +} + static int kvm_vm_ioctl_set_device_addr(struct kvm *kvm, struct kvm_arm_device_addr *dev_addr) { diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 54f0fcfd431e..0041947b7390 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -1133,7 +1133,7 @@ EXPORT_SYMBOL_GPL(kvm_get_dirty_log); #ifdef CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT /** * kvm_get_dirty_log_protect - get a snapshot of dirty pages, and if any pages - * are dirty write protect them for next write. + * and reenable dirty page tracking for the corresponding pages. * @kvm: pointer to kvm instance * @log: slot id and address to which we copy the log * @is_dirty: flag set if any page is dirty @@ -1176,37 +1176,114 @@ int kvm_get_dirty_log_protect(struct kvm *kvm, return -ENOENT; n = kvm_dirty_bitmap_bytes(memslot); + *flush = false; + if (kvm->manual_dirty_log_protect) { + /* + * Unlike kvm_get_dirty_log, we always return false in *flush, + * because no flush is needed until KVM_CLEAR_DIRTY_LOG. There + * is some code duplication between this function and + * kvm_get_dirty_log, but hopefully all architecture + * transition to kvm_get_dirty_log_protect and kvm_get_dirty_log + * can be eliminated. + */ + dirty_bitmap_buffer = dirty_bitmap; + } else { + dirty_bitmap_buffer = kvm_second_dirty_bitmap(memslot); + memset(dirty_bitmap_buffer, 0, n); - dirty_bitmap_buffer = kvm_second_dirty_bitmap(memslot); - memset(dirty_bitmap_buffer, 0, n); + spin_lock(&kvm->mmu_lock); + for (i = 0; i < n / sizeof(long); i++) { + unsigned long mask; + gfn_t offset; - spin_lock(&kvm->mmu_lock); + if (!dirty_bitmap[i]) + continue; + + *flush = true; + mask = xchg(&dirty_bitmap[i], 0); + dirty_bitmap_buffer[i] = mask; + + if (mask) { + offset = i * BITS_PER_LONG; + kvm_arch_mmu_enable_log_dirty_pt_masked(kvm, memslot, + offset, mask); + } + } + spin_unlock(&kvm->mmu_lock); + } + + if (copy_to_user(log->dirty_bitmap, dirty_bitmap_buffer, n)) + return -EFAULT; + return 0; +} +EXPORT_SYMBOL_GPL(kvm_get_dirty_log_protect); + +/** + * kvm_clear_dirty_log_protect - clear dirty bits in the bitmap + * and reenable dirty page tracking for the corresponding pages. + * @kvm: pointer to kvm instance + * @log: slot id and address from which to fetch the bitmap of dirty pages + */ +int kvm_clear_dirty_log_protect(struct kvm *kvm, + struct kvm_clear_dirty_log *log, bool *flush) +{ + struct kvm_memslots *slots; + struct kvm_memory_slot *memslot; + int as_id, id, n; + gfn_t offset; + unsigned long i; + unsigned long *dirty_bitmap; + unsigned long *dirty_bitmap_buffer; + + as_id = log->slot >> 16; + id = (u16)log->slot; + if (as_id >= KVM_ADDRESS_SPACE_NUM || id >= KVM_USER_MEM_SLOTS) + return -EINVAL; + + if ((log->first_page & 63) || (log->num_pages & 63)) + return -EINVAL; + + slots = __kvm_memslots(kvm, as_id); + memslot = id_to_memslot(slots, id); + + dirty_bitmap = memslot->dirty_bitmap; + if (!dirty_bitmap) + return -ENOENT; + + n = kvm_dirty_bitmap_bytes(memslot); *flush = false; - for (i = 0; i < n / sizeof(long); i++) { - unsigned long mask; - gfn_t offset; + dirty_bitmap_buffer = kvm_second_dirty_bitmap(memslot); + if (copy_from_user(dirty_bitmap_buffer, log->dirty_bitmap, n)) + return -EFAULT; - if (!dirty_bitmap[i]) + spin_lock(&kvm->mmu_lock); + for (offset = log->first_page, + i = offset / BITS_PER_LONG, n = log->num_pages / BITS_PER_LONG; n--; + i++, offset += BITS_PER_LONG) { + unsigned long mask = *dirty_bitmap_buffer++; + atomic_long_t *p = (atomic_long_t *) &dirty_bitmap[i]; + if (!mask) continue; - *flush = true; - - mask = xchg(&dirty_bitmap[i], 0); - dirty_bitmap_buffer[i] = mask; + mask &= atomic_long_fetch_andnot(mask, p); + /* + * mask contains the bits that really have been cleared. This + * never includes any bits beyond the length of the memslot (if + * the length is not aligned to 64 pages), therefore it is not + * a problem if userspace sets them in log->dirty_bitmap. + */ if (mask) { - offset = i * BITS_PER_LONG; + *flush = true; kvm_arch_mmu_enable_log_dirty_pt_masked(kvm, memslot, offset, mask); } } - spin_unlock(&kvm->mmu_lock); - if (copy_to_user(log->dirty_bitmap, dirty_bitmap_buffer, n)) - return -EFAULT; + return 0; } -EXPORT_SYMBOL_GPL(kvm_get_dirty_log_protect); +EXPORT_SYMBOL_GPL(kvm_clear_dirty_log_protect); #endif bool kvm_largepages_enabled(void) @@ -2949,6 +3026,9 @@ static long kvm_vm_ioctl_check_extension_generic(struct kvm *kvm, long arg) case KVM_CAP_IOEVENTFD_ANY_LENGTH: case KVM_CAP_CHECK_EXTENSION_VM: case KVM_CAP_ENABLE_CAP_VM: +#ifdef CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT + case KVM_CAP_MANUAL_DIRTY_LOG_PROTECT: +#endif return 1; #ifdef CONFIG_KVM_MMIO case KVM_CAP_COALESCED_MMIO: @@ -2982,6 +3062,13 @@ static int kvm_vm_ioctl_enable_cap_generic(struct kvm *kvm, struct kvm_enable_cap *cap) { switch (cap->cap) { +#ifdef CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT + case KVM_CAP_MANUAL_DIRTY_LOG_PROTECT: + if (cap->flags || (cap->args[0] & ~1)) + return -EINVAL; + kvm->manual_dirty_log_protect = cap->args[0]; + return 0; +#endif default: return kvm_vm_ioctl_enable_cap(kvm, cap); } @@ -3029,6 +3116,17 @@ static long kvm_vm_ioctl(struct file *filp, r = kvm_vm_ioctl_get_dirty_log(kvm, &log); break; } +#ifdef CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT + case KVM_CLEAR_DIRTY_LOG: { + struct kvm_clear_dirty_log log; + + r = -EFAULT; + if (copy_from_user(&log, argp, sizeof(log))) + goto out; + r = kvm_vm_ioctl_clear_dirty_log(kvm, &log); + break; + } +#endif #ifdef CONFIG_KVM_MMIO case KVM_REGISTER_COALESCED_MMIO: { struct kvm_coalesced_mmio_zone zone; -- cgit v1.2.3 From 2bc39970e9327ceb06cb210f86ba35f81d00e350 Mon Sep 17 00:00:00 2001 From: Vitaly Kuznetsov Date: Mon, 10 Dec 2018 18:21:56 +0100 Subject: x86/kvm/hyper-v: Introduce KVM_GET_SUPPORTED_HV_CPUID With every new Hyper-V Enlightenment we implement we're forced to add a KVM_CAP_HYPERV_* capability. While this approach works it is fairly inconvenient: the majority of the enlightenments we do have corresponding CPUID feature bit(s) and userspace has to know this anyways to be able to expose the feature to the guest. Add KVM_GET_SUPPORTED_HV_CPUID ioctl (backed by KVM_CAP_HYPERV_CPUID, "one cap to rule them all!") returning all Hyper-V CPUID feature leaves. Using the existing KVM_GET_SUPPORTED_CPUID doesn't seem to be possible: Hyper-V CPUID feature leaves intersect with KVM's (e.g. 0x40000000, 0x40000001) and we would probably confuse userspace in case we decide to return these twice. KVM_CAP_HYPERV_CPUID's number is interim: we're intended to drop KVM_CAP_HYPERV_STIMER_DIRECT and use its number instead. Suggested-by: Paolo Bonzini Signed-off-by: Vitaly Kuznetsov Signed-off-by: Paolo Bonzini --- Documentation/virtual/kvm/api.txt | 56 ++++++++++++++++++ arch/x86/kvm/hyperv.c | 121 ++++++++++++++++++++++++++++++++++++++ arch/x86/kvm/hyperv.h | 2 + arch/x86/kvm/x86.c | 20 +++++++ include/uapi/linux/kvm.h | 4 ++ 5 files changed, 203 insertions(+) (limited to 'Documentation') diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt index f2c345f7b630..356156f5c52d 100644 --- a/Documentation/virtual/kvm/api.txt +++ b/Documentation/virtual/kvm/api.txt @@ -3800,6 +3800,62 @@ is enabled; for more information, see the description of the capability. However, it can always be used as long as KVM_CHECK_EXTENSION confirms that KVM_CAP_MANUAL_DIRTY_LOG_PROTECT is present. +4.118 KVM_GET_SUPPORTED_HV_CPUID + +Capability: KVM_CAP_HYPERV_CPUID +Architectures: x86 +Type: vcpu ioctl +Parameters: struct kvm_cpuid2 (in/out) +Returns: 0 on success, -1 on error + +struct kvm_cpuid2 { + __u32 nent; + __u32 padding; + struct kvm_cpuid_entry2 entries[0]; +}; + +struct kvm_cpuid_entry2 { + __u32 function; + __u32 index; + __u32 flags; + __u32 eax; + __u32 ebx; + __u32 ecx; + __u32 edx; + __u32 padding[3]; +}; + +This ioctl returns x86 cpuid features leaves related to Hyper-V emulation in +KVM. Userspace can use the information returned by this ioctl to construct +cpuid information presented to guests consuming Hyper-V enlightenments (e.g. +Windows or Hyper-V guests). + +CPUID feature leaves returned by this ioctl are defined by Hyper-V Top Level +Functional Specification (TLFS). These leaves can't be obtained with +KVM_GET_SUPPORTED_CPUID ioctl because some of them intersect with KVM feature +leaves (0x40000000, 0x40000001). + +Currently, the following list of CPUID leaves are returned: + HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS + HYPERV_CPUID_INTERFACE + HYPERV_CPUID_VERSION + HYPERV_CPUID_FEATURES + HYPERV_CPUID_ENLIGHTMENT_INFO + HYPERV_CPUID_IMPLEMENT_LIMITS + HYPERV_CPUID_NESTED_FEATURES + +HYPERV_CPUID_NESTED_FEATURES leaf is only exposed when Enlightened VMCS was +enabled on the corresponding vCPU (KVM_CAP_HYPERV_ENLIGHTENED_VMCS). + +Userspace invokes KVM_GET_SUPPORTED_CPUID by passing a kvm_cpuid2 structure +with the 'nent' field indicating the number of entries in the variable-size +array 'entries'. If the number of entries is too low to describe all Hyper-V +feature leaves, an error (E2BIG) is returned. If the number is more or equal +to the number of Hyper-V feature leaves, the 'nent' field is adjusted to the +number of valid entries in the 'entries' array, which is then filled. + +'index' and 'flags' fields in 'struct kvm_cpuid_entry2' are currently reserved, +userspace should not expect to get any particular value there. 5. The kvm_run structure ------------------------ diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index a9b5d6c4e3eb..e3c076020d4e 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -1752,3 +1752,124 @@ int kvm_vm_ioctl_hv_eventfd(struct kvm *kvm, struct kvm_hyperv_eventfd *args) return kvm_hv_eventfd_deassign(kvm, args->conn_id); return kvm_hv_eventfd_assign(kvm, args->conn_id, args->fd); } + +int kvm_vcpu_ioctl_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid, + struct kvm_cpuid_entry2 __user *entries) +{ + uint16_t evmcs_ver = kvm_x86_ops->nested_get_evmcs_version(vcpu); + struct kvm_cpuid_entry2 cpuid_entries[] = { + { .function = HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS }, + { .function = HYPERV_CPUID_INTERFACE }, + { .function = HYPERV_CPUID_VERSION }, + { .function = HYPERV_CPUID_FEATURES }, + { .function = HYPERV_CPUID_ENLIGHTMENT_INFO }, + { .function = HYPERV_CPUID_IMPLEMENT_LIMITS }, + { .function = HYPERV_CPUID_NESTED_FEATURES }, + }; + int i, nent = ARRAY_SIZE(cpuid_entries); + + /* Skip NESTED_FEATURES if eVMCS is not supported */ + if (!evmcs_ver) + --nent; + + if (cpuid->nent < nent) + return -E2BIG; + + if (cpuid->nent > nent) + cpuid->nent = nent; + + for (i = 0; i < nent; i++) { + struct kvm_cpuid_entry2 *ent = &cpuid_entries[i]; + u32 signature[3]; + + switch (ent->function) { + case HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS: + memcpy(signature, "Linux KVM Hv", 12); + + ent->eax = HYPERV_CPUID_NESTED_FEATURES; + ent->ebx = signature[0]; + ent->ecx = signature[1]; + ent->edx = signature[2]; + break; + + case HYPERV_CPUID_INTERFACE: + memcpy(signature, "Hv#1\0\0\0\0\0\0\0\0", 12); + ent->eax = signature[0]; + break; + + case HYPERV_CPUID_VERSION: + /* + * We implement some Hyper-V 2016 functions so let's use + * this version. + */ + ent->eax = 0x00003839; + ent->ebx = 0x000A0000; + break; + + case HYPERV_CPUID_FEATURES: + ent->eax |= HV_X64_MSR_VP_RUNTIME_AVAILABLE; + ent->eax |= HV_MSR_TIME_REF_COUNT_AVAILABLE; + ent->eax |= HV_X64_MSR_SYNIC_AVAILABLE; + ent->eax |= HV_MSR_SYNTIMER_AVAILABLE; + ent->eax |= HV_X64_MSR_APIC_ACCESS_AVAILABLE; + ent->eax |= HV_X64_MSR_HYPERCALL_AVAILABLE; + ent->eax |= HV_X64_MSR_VP_INDEX_AVAILABLE; + ent->eax |= HV_X64_MSR_RESET_AVAILABLE; + ent->eax |= HV_MSR_REFERENCE_TSC_AVAILABLE; + ent->eax |= HV_X64_MSR_GUEST_IDLE_AVAILABLE; + ent->eax |= HV_X64_ACCESS_FREQUENCY_MSRS; + ent->eax |= HV_X64_ACCESS_REENLIGHTENMENT; + + ent->ebx |= HV_X64_POST_MESSAGES; + ent->ebx |= HV_X64_SIGNAL_EVENTS; + + ent->edx |= HV_FEATURE_FREQUENCY_MSRS_AVAILABLE; + ent->edx |= HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE; + ent->edx |= HV_STIMER_DIRECT_MODE_AVAILABLE; + + break; + + case HYPERV_CPUID_ENLIGHTMENT_INFO: + ent->eax |= HV_X64_REMOTE_TLB_FLUSH_RECOMMENDED; + ent->eax |= HV_X64_APIC_ACCESS_RECOMMENDED; + ent->eax |= HV_X64_SYSTEM_RESET_RECOMMENDED; + ent->eax |= HV_X64_RELAXED_TIMING_RECOMMENDED; + ent->eax |= HV_X64_CLUSTER_IPI_RECOMMENDED; + ent->eax |= HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED; + ent->eax |= HV_X64_ENLIGHTENED_VMCS_RECOMMENDED; + + /* + * Default number of spinlock retry attempts, matches + * HyperV 2016. + */ + ent->ebx = 0x00000FFF; + + break; + + case HYPERV_CPUID_IMPLEMENT_LIMITS: + /* Maximum number of virtual processors */ + ent->eax = KVM_MAX_VCPUS; + /* + * Maximum number of logical processors, matches + * HyperV 2016. + */ + ent->ebx = 64; + + break; + + case HYPERV_CPUID_NESTED_FEATURES: + ent->eax = evmcs_ver; + + break; + + default: + break; + } + } + + if (copy_to_user(entries, cpuid_entries, + nent * sizeof(struct kvm_cpuid_entry2))) + return -EFAULT; + + return 0; +} diff --git a/arch/x86/kvm/hyperv.h b/arch/x86/kvm/hyperv.h index 9c21c3479899..fd7cf13a2144 100644 --- a/arch/x86/kvm/hyperv.h +++ b/arch/x86/kvm/hyperv.h @@ -97,5 +97,7 @@ void kvm_hv_setup_tsc_page(struct kvm *kvm, void kvm_hv_init_vm(struct kvm *kvm); void kvm_hv_destroy_vm(struct kvm *kvm); int kvm_vm_ioctl_hv_eventfd(struct kvm *kvm, struct kvm_hyperv_eventfd *args); +int kvm_vcpu_ioctl_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid, + struct kvm_cpuid_entry2 __user *entries); #endif diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 54ef79421c6b..18b7817af2bc 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -2997,6 +2997,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_HYPERV_TLBFLUSH: case KVM_CAP_HYPERV_SEND_IPI: case KVM_CAP_HYPERV_ENLIGHTENED_VMCS: + case KVM_CAP_HYPERV_CPUID: case KVM_CAP_PCI_SEGMENT: case KVM_CAP_DEBUGREGS: case KVM_CAP_X86_ROBUST_SINGLESTEP: @@ -4191,6 +4192,25 @@ long kvm_arch_vcpu_ioctl(struct file *filp, r = kvm_x86_ops->set_nested_state(vcpu, user_kvm_nested_state, &kvm_state); break; } + case KVM_GET_SUPPORTED_HV_CPUID: { + struct kvm_cpuid2 __user *cpuid_arg = argp; + struct kvm_cpuid2 cpuid; + + r = -EFAULT; + if (copy_from_user(&cpuid, cpuid_arg, sizeof(cpuid))) + goto out; + + r = kvm_vcpu_ioctl_get_hv_cpuid(vcpu, &cpuid, + cpuid_arg->entries); + if (r) + goto out; + + r = -EFAULT; + if (copy_to_user(cpuid_arg, &cpuid, sizeof(cpuid))) + goto out; + r = 0; + break; + } default: r = -EINVAL; } diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 9fe35f1ac938..6d4ea4b6c922 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -987,6 +987,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_EXCEPTION_PAYLOAD 164 #define KVM_CAP_ARM_VM_IPA_SIZE 165 #define KVM_CAP_MANUAL_DIRTY_LOG_PROTECT 166 +#define KVM_CAP_HYPERV_CPUID 167 #ifdef KVM_CAP_IRQ_ROUTING @@ -1436,6 +1437,9 @@ struct kvm_enc_region { /* Available with KVM_CAP_MANUAL_DIRTY_LOG_PROTECT */ #define KVM_CLEAR_DIRTY_LOG _IOWR(KVMIO, 0xc0, struct kvm_clear_dirty_log) +/* Available with KVM_CAP_HYPERV_CPUID */ +#define KVM_GET_SUPPORTED_HV_CPUID _IOWR(KVMIO, 0xc1, struct kvm_cpuid2) + /* Secure Encrypted Virtualization command */ enum sev_cmd_id { /* Guest initialization commands */ -- cgit v1.2.3