From 49f683b41f28918df3e51ddc0d928cb2e934ccdb Mon Sep 17 00:00:00 2001 From: Breno Leitao Date: Fri, 10 May 2024 02:23:52 -0700 Subject: KVM: Fix a data race on last_boosted_vcpu in kvm_vcpu_on_spin() Use {READ,WRITE}_ONCE() to access kvm->last_boosted_vcpu to ensure the loads and stores are atomic. In the extremely unlikely scenario the compiler tears the stores, it's theoretically possible for KVM to attempt to get a vCPU using an out-of-bounds index, e.g. if the write is split into multiple 8-bit stores, and is paired with a 32-bit load on a VM with 257 vCPUs: CPU0 CPU1 last_boosted_vcpu = 0xff; (last_boosted_vcpu = 0x100) last_boosted_vcpu[15:8] = 0x01; i = (last_boosted_vcpu = 0x1ff) last_boosted_vcpu[7:0] = 0x00; vcpu = kvm->vcpu_array[0x1ff]; As detected by KCSAN: BUG: KCSAN: data-race in kvm_vcpu_on_spin [kvm] / kvm_vcpu_on_spin [kvm] write to 0xffffc90025a92344 of 4 bytes by task 4340 on cpu 16: kvm_vcpu_on_spin (arch/x86/kvm/../../../virt/kvm/kvm_main.c:4112) kvm handle_pause (arch/x86/kvm/vmx/vmx.c:5929) kvm_intel vmx_handle_exit (arch/x86/kvm/vmx/vmx.c:? arch/x86/kvm/vmx/vmx.c:6606) kvm_intel vcpu_run (arch/x86/kvm/x86.c:11107 arch/x86/kvm/x86.c:11211) kvm kvm_arch_vcpu_ioctl_run (arch/x86/kvm/x86.c:?) kvm kvm_vcpu_ioctl (arch/x86/kvm/../../../virt/kvm/kvm_main.c:?) kvm __se_sys_ioctl (fs/ioctl.c:52 fs/ioctl.c:904 fs/ioctl.c:890) __x64_sys_ioctl (fs/ioctl.c:890) x64_sys_call (arch/x86/entry/syscall_64.c:33) do_syscall_64 (arch/x86/entry/common.c:?) entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:130) read to 0xffffc90025a92344 of 4 bytes by task 4342 on cpu 4: kvm_vcpu_on_spin (arch/x86/kvm/../../../virt/kvm/kvm_main.c:4069) kvm handle_pause (arch/x86/kvm/vmx/vmx.c:5929) kvm_intel vmx_handle_exit (arch/x86/kvm/vmx/vmx.c:? arch/x86/kvm/vmx/vmx.c:6606) kvm_intel vcpu_run (arch/x86/kvm/x86.c:11107 arch/x86/kvm/x86.c:11211) kvm kvm_arch_vcpu_ioctl_run (arch/x86/kvm/x86.c:?) kvm kvm_vcpu_ioctl (arch/x86/kvm/../../../virt/kvm/kvm_main.c:?) kvm __se_sys_ioctl (fs/ioctl.c:52 fs/ioctl.c:904 fs/ioctl.c:890) __x64_sys_ioctl (fs/ioctl.c:890) x64_sys_call (arch/x86/entry/syscall_64.c:33) do_syscall_64 (arch/x86/entry/common.c:?) entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:130) value changed: 0x00000012 -> 0x00000000 Fixes: 217ece6129f2 ("KVM: use yield_to instead of sleep in kvm_vcpu_on_spin") Cc: stable@vger.kernel.org Signed-off-by: Breno Leitao Link: https://lore.kernel.org/r/20240510092353.2261824-1-leitao@debian.org Signed-off-by: Sean Christopherson --- virt/kvm/kvm_main.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'virt/kvm') diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 14841acb8b95..843aa68cbcd0 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -4025,12 +4025,13 @@ void kvm_vcpu_on_spin(struct kvm_vcpu *me, bool yield_to_kernel_mode) { struct kvm *kvm = me->kvm; struct kvm_vcpu *vcpu; - int last_boosted_vcpu = me->kvm->last_boosted_vcpu; + int last_boosted_vcpu; unsigned long i; int yielded = 0; int try = 3; int pass; + last_boosted_vcpu = READ_ONCE(kvm->last_boosted_vcpu); kvm_vcpu_set_in_spin_loop(me, true); /* * We boost the priority of a VCPU that is runnable but not @@ -4068,7 +4069,7 @@ void kvm_vcpu_on_spin(struct kvm_vcpu *me, bool yield_to_kernel_mode) yielded = kvm_vcpu_yield_to(vcpu); if (yielded > 0) { - kvm->last_boosted_vcpu = i; + WRITE_ONCE(kvm->last_boosted_vcpu, i); break; } else if (yielded < 0) { try--; -- cgit v1.2.3 From c3f3edf73a8f854f8766a69d2734198a58762e33 Mon Sep 17 00:00:00 2001 From: Babu Moger Date: Wed, 12 Jun 2024 09:41:51 -0500 Subject: KVM: Stop processing *all* memslots when "null" mmu_notifier handler is found Bail from outer address space loop, not just the inner memslot loop, when a "null" handler is encountered by __kvm_handle_hva_range(), which is the intended behavior. On x86, which has multiple address spaces thanks to SMM emulation, breaking from just the memslot loop results in undefined behavior due to assigning the non-existent return value from kvm_null_fn() to a bool. In practice, the bug is benign as kvm_mmu_notifier_invalidate_range_end() is the only caller that passes handler=kvm_null_fn, and it doesn't set flush_on_ret, i.e. assigning garbage to r.ret is ultimately ignored. And for most configuration the compiler elides the entire sequence, i.e. there is no undefined behavior at runtime. ------------[ cut here ]------------ UBSAN: invalid-load in arch/x86/kvm/../../../virt/kvm/kvm_main.c:655:10 load of value 160 is not a valid value for type '_Bool' CPU: 370 PID: 8246 Comm: CPU 0/KVM Not tainted 6.8.2-amdsos-build58-ubuntu-22.04+ #1 Hardware name: AMD Corporation Sh54p/Sh54p, BIOS WPC4429N 04/25/2024 Call Trace: dump_stack_lvl+0x48/0x60 ubsan_epilogue+0x5/0x30 __ubsan_handle_load_invalid_value+0x79/0x80 kvm_mmu_notifier_invalidate_range_end.cold+0x18/0x4f [kvm] __mmu_notifier_invalidate_range_end+0x63/0xe0 __split_huge_pmd+0x367/0xfc0 do_huge_pmd_wp_page+0x1cc/0x380 __handle_mm_fault+0x8ee/0xe50 handle_mm_fault+0xe4/0x4a0 __get_user_pages+0x190/0x840 get_user_pages_unlocked+0xe0/0x590 hva_to_pfn+0x114/0x550 [kvm] kvm_faultin_pfn+0xed/0x5b0 [kvm] kvm_tdp_page_fault+0x123/0x170 [kvm] kvm_mmu_page_fault+0x244/0xaa0 [kvm] vcpu_enter_guest+0x592/0x1070 [kvm] kvm_arch_vcpu_ioctl_run+0x145/0x8a0 [kvm] kvm_vcpu_ioctl+0x288/0x6d0 [kvm] __x64_sys_ioctl+0x8f/0xd0 do_syscall_64+0x77/0x120 entry_SYSCALL_64_after_hwframe+0x6e/0x76 ---[ end trace ]--- Fixes: 071064f14d87 ("KVM: Don't take mmu_lock for range invalidation unless necessary") Signed-off-by: Babu Moger Link: https://lore.kernel.org/r/b8723d39903b64c241c50f5513f804390c7b5eec.1718203311.git.babu.moger@amd.com [sean: massage changelog] Signed-off-by: Sean Christopherson --- virt/kvm/kvm_main.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'virt/kvm') diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 843aa68cbcd0..68be4be5d846 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -651,7 +651,7 @@ static __always_inline kvm_mn_ret_t __kvm_handle_hva_range(struct kvm *kvm, range->on_lock(kvm); if (IS_KVM_NULL_FN(range->handler)) - break; + goto mmu_unlock; } r.ret |= range->handler(kvm, &gfn_range); } @@ -660,6 +660,7 @@ static __always_inline kvm_mn_ret_t __kvm_handle_hva_range(struct kvm *kvm, if (range->flush_on_ret && r.ret) kvm_flush_remote_tlbs(kvm); +mmu_unlock: if (r.found_memslot) KVM_MMU_UNLOCK(kvm); -- cgit v1.2.3