From 5c49d1850ddd3240d20dc40b01f593e35a184f38 Mon Sep 17 00:00:00 2001 From: Zhenzhong Duan Date: Sun, 26 Sep 2021 09:55:45 +0800 Subject: [PATCH 1/6] KVM: VMX: Fix a TSX_CTRL_CPUID_CLEAR field mask issue When updating the host's mask for its MSR_IA32_TSX_CTRL user return entry, clear the mask in the found uret MSR instead of vmx->guest_uret_msrs[i]. Modifying guest_uret_msrs directly is completely broken as 'i' does not point at the MSR_IA32_TSX_CTRL entry. In fact, it's guaranteed to be an out-of-bounds accesses as is always set to kvm_nr_uret_msrs in a prior loop. By sheer dumb luck, the fallout is limited to "only" failing to preserve the host's TSX_CTRL_CPUID_CLEAR. The out-of-bounds access is benign as it's guaranteed to clear a bit in a guest MSR value, which are always zero at vCPU creation on both x86-64 and i386. Cc: stable@vger.kernel.org Fixes: 8ea8b8d6f869 ("KVM: VMX: Use common x86's uret MSR list as the one true list") Signed-off-by: Zhenzhong Duan Reviewed-by: Sean Christopherson Message-Id: <20210926015545.281083-1-zhenzhong.duan@intel.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/vmx/vmx.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 9ecfcf13a046..116b08904ac3 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -6848,7 +6848,7 @@ static int vmx_create_vcpu(struct kvm_vcpu *vcpu) */ tsx_ctrl = vmx_find_uret_msr(vmx, MSR_IA32_TSX_CTRL); if (tsx_ctrl) - vmx->guest_uret_msrs[i].mask = ~(u64)TSX_CTRL_CPUID_CLEAR; + tsx_ctrl->mask = ~(u64)TSX_CTRL_CPUID_CLEAR; } err = alloc_loaded_vmcs(&vmx->vmcs01); From e02c16b9cd24925ea627f007df9ca9ee00eaaa62 Mon Sep 17 00:00:00 2001 From: Oliver Upton Date: Mon, 27 Sep 2021 22:36:21 +0000 Subject: [PATCH 2/6] selftests: KVM: Don't clobber XMM register when read There is no need to clobber a register that is only being read from. Oops. Drop the XMM register from the clobbers list. Signed-off-by: Oliver Upton Message-Id: <20210927223621.50178-1-oupton@google.com> Signed-off-by: Paolo Bonzini --- tools/testing/selftests/kvm/include/x86_64/processor.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h index eba8bd08293e..05e65ca1c30c 100644 --- a/tools/testing/selftests/kvm/include/x86_64/processor.h +++ b/tools/testing/selftests/kvm/include/x86_64/processor.h @@ -315,7 +315,7 @@ static inline void set_xmm(int n, unsigned long val) #define GET_XMM(__xmm) \ ({ \ unsigned long __val; \ - asm volatile("movq %%"#__xmm", %0" : "=r"(__val) : : #__xmm); \ + asm volatile("movq %%"#__xmm", %0" : "=r"(__val)); \ __val; \ }) From ad9af930680bb396c87582edc172b3a7cf2a3fbf Mon Sep 17 00:00:00 2001 From: Zelin Deng Date: Wed, 29 Sep 2021 13:13:48 +0800 Subject: [PATCH 3/6] x86/kvmclock: Move this_cpu_pvti into kvmclock.h There're other modules might use hv_clock_per_cpu variable like ptp_kvm, so move it into kvmclock.h and export the symbol to make it visiable to other modules. Signed-off-by: Zelin Deng Cc: Message-Id: <1632892429-101194-2-git-send-email-zelin.deng@linux.alibaba.com> Signed-off-by: Paolo Bonzini --- arch/x86/include/asm/kvmclock.h | 14 ++++++++++++++ arch/x86/kernel/kvmclock.c | 13 ++----------- 2 files changed, 16 insertions(+), 11 deletions(-) diff --git a/arch/x86/include/asm/kvmclock.h b/arch/x86/include/asm/kvmclock.h index eceea9299097..6c5765192102 100644 --- a/arch/x86/include/asm/kvmclock.h +++ b/arch/x86/include/asm/kvmclock.h @@ -2,6 +2,20 @@ #ifndef _ASM_X86_KVM_CLOCK_H #define _ASM_X86_KVM_CLOCK_H +#include + extern struct clocksource kvm_clock; +DECLARE_PER_CPU(struct pvclock_vsyscall_time_info *, hv_clock_per_cpu); + +static inline struct pvclock_vcpu_time_info *this_cpu_pvti(void) +{ + return &this_cpu_read(hv_clock_per_cpu)->pvti; +} + +static inline struct pvclock_vsyscall_time_info *this_cpu_hvclock(void) +{ + return this_cpu_read(hv_clock_per_cpu); +} + #endif /* _ASM_X86_KVM_CLOCK_H */ diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c index ad273e5861c1..73c74b961d0f 100644 --- a/arch/x86/kernel/kvmclock.c +++ b/arch/x86/kernel/kvmclock.c @@ -49,18 +49,9 @@ early_param("no-kvmclock-vsyscall", parse_no_kvmclock_vsyscall); static struct pvclock_vsyscall_time_info hv_clock_boot[HVC_BOOT_ARRAY_SIZE] __bss_decrypted __aligned(PAGE_SIZE); static struct pvclock_wall_clock wall_clock __bss_decrypted; -static DEFINE_PER_CPU(struct pvclock_vsyscall_time_info *, hv_clock_per_cpu); static struct pvclock_vsyscall_time_info *hvclock_mem; - -static inline struct pvclock_vcpu_time_info *this_cpu_pvti(void) -{ - return &this_cpu_read(hv_clock_per_cpu)->pvti; -} - -static inline struct pvclock_vsyscall_time_info *this_cpu_hvclock(void) -{ - return this_cpu_read(hv_clock_per_cpu); -} +DEFINE_PER_CPU(struct pvclock_vsyscall_time_info *, hv_clock_per_cpu); +EXPORT_PER_CPU_SYMBOL_GPL(hv_clock_per_cpu); /* * The wallclock is the time of day when we booted. Since then, some time may From 773e89ab0056aaa2baa1ffd9f044551654410104 Mon Sep 17 00:00:00 2001 From: Zelin Deng Date: Wed, 29 Sep 2021 13:13:49 +0800 Subject: [PATCH 4/6] ptp: Fix ptp_kvm_getcrosststamp issue for x86 ptp_kvm hv_clock is preallocated to have only HVC_BOOT_ARRAY_SIZE (64) elements; if the PTP_SYS_OFFSET_PRECISE ioctl is executed on vCPUs whose index is 64 of higher, retrieving the struct pvclock_vcpu_time_info pointer with "src = &hv_clock[cpu].pvti" will result in an out-of-bounds access and a wild pointer. Change it to "this_cpu_pvti()" which is guaranteed to be valid. Fixes: 95a3d4454bb1 ("Switch kvmclock data to a PER_CPU variable") Signed-off-by: Zelin Deng Cc: Message-Id: <1632892429-101194-3-git-send-email-zelin.deng@linux.alibaba.com> Signed-off-by: Paolo Bonzini --- drivers/ptp/ptp_kvm_x86.c | 9 ++------- 1 file changed, 2 insertions(+), 7 deletions(-) diff --git a/drivers/ptp/ptp_kvm_x86.c b/drivers/ptp/ptp_kvm_x86.c index 3dd519dfc473..d0096cd7096a 100644 --- a/drivers/ptp/ptp_kvm_x86.c +++ b/drivers/ptp/ptp_kvm_x86.c @@ -15,8 +15,6 @@ #include #include -struct pvclock_vsyscall_time_info *hv_clock; - static phys_addr_t clock_pair_gpa; static struct kvm_clock_pairing clock_pair; @@ -28,8 +26,7 @@ int kvm_arch_ptp_init(void) return -ENODEV; clock_pair_gpa = slow_virt_to_phys(&clock_pair); - hv_clock = pvclock_get_pvti_cpu0_va(); - if (!hv_clock) + if (!pvclock_get_pvti_cpu0_va()) return -ENODEV; ret = kvm_hypercall2(KVM_HC_CLOCK_PAIRING, clock_pair_gpa, @@ -64,10 +61,8 @@ int kvm_arch_ptp_get_crosststamp(u64 *cycle, struct timespec64 *tspec, struct pvclock_vcpu_time_info *src; unsigned int version; long ret; - int cpu; - cpu = smp_processor_id(); - src = &hv_clock[cpu].pvti; + src = this_cpu_pvti(); do { /* From e8a747d0884e554a8c1872da6c8f680a4f893c6d Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Wed, 29 Sep 2021 15:24:25 -0700 Subject: [PATCH 5/6] KVM: x86: Swap order of CPUID entry "index" vs. "significant flag" checks Check whether a CPUID entry's index is significant before checking for a matching index to hack-a-fix an undefined behavior bug due to consuming uninitialized data. RESET/INIT emulation uses kvm_cpuid() to retrieve CPUID.0x1, which does _not_ have a significant index, and fails to initialize the dummy variable that doubles as EBX/ECX/EDX output _and_ ECX, a.k.a. index, input. Practically speaking, it's _extremely_ unlikely any compiler will yield code that causes problems, as the compiler would need to inline the kvm_cpuid() call to detect the uninitialized data, and intentionally hose the kernel, e.g. insert ud2, instead of simply ignoring the result of the index comparison. Although the sketchy "dummy" pattern was introduced in SVM by commit 66f7b72e1171 ("KVM: x86: Make register state after reset conform to specification"), it wasn't actually broken until commit 7ff6c0350315 ("KVM: x86: Remove stateful CPUID handling") arbitrarily swapped the order of operations such that "index" was checked before the significant flag. Avoid consuming uninitialized data by reverting to checking the flag before the index purely so that the fix can be easily backported; the offending RESET/INIT code has been refactored, moved, and consolidated from vendor code to common x86 since the bug was introduced. A future patch will directly address the bad RESET/INIT behavior. The undefined behavior was detected by syzbot + KernelMemorySanitizer. BUG: KMSAN: uninit-value in cpuid_entry2_find arch/x86/kvm/cpuid.c:68 BUG: KMSAN: uninit-value in kvm_find_cpuid_entry arch/x86/kvm/cpuid.c:1103 BUG: KMSAN: uninit-value in kvm_cpuid+0x456/0x28f0 arch/x86/kvm/cpuid.c:1183 cpuid_entry2_find arch/x86/kvm/cpuid.c:68 [inline] kvm_find_cpuid_entry arch/x86/kvm/cpuid.c:1103 [inline] kvm_cpuid+0x456/0x28f0 arch/x86/kvm/cpuid.c:1183 kvm_vcpu_reset+0x13fb/0x1c20 arch/x86/kvm/x86.c:10885 kvm_apic_accept_events+0x58f/0x8c0 arch/x86/kvm/lapic.c:2923 vcpu_enter_guest+0xfd2/0x6d80 arch/x86/kvm/x86.c:9534 vcpu_run+0x7f5/0x18d0 arch/x86/kvm/x86.c:9788 kvm_arch_vcpu_ioctl_run+0x245b/0x2d10 arch/x86/kvm/x86.c:10020 Local variable ----dummy@kvm_vcpu_reset created at: kvm_vcpu_reset+0x1fb/0x1c20 arch/x86/kvm/x86.c:10812 kvm_apic_accept_events+0x58f/0x8c0 arch/x86/kvm/lapic.c:2923 Reported-by: syzbot+f3985126b746b3d59c9d@syzkaller.appspotmail.com Reported-by: Alexander Potapenko Fixes: 2a24be79b6b7 ("KVM: VMX: Set EDX at INIT with CPUID.0x1, Family-Model-Stepping") Fixes: 7ff6c0350315 ("KVM: x86: Remove stateful CPUID handling") Cc: stable@vger.kernel.org Signed-off-by: Sean Christopherson Reviewed-by: Jim Mattson Message-Id: <20210929222426.1855730-2-seanjc@google.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/cpuid.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index fe03bd978761..751aa85a3001 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -65,8 +65,8 @@ static inline struct kvm_cpuid_entry2 *cpuid_entry2_find( for (i = 0; i < nent; i++) { e = &entries[i]; - if (e->function == function && (e->index == index || - !(e->flags & KVM_CPUID_FLAG_SIGNIFCANT_INDEX))) + if (e->function == function && + (!(e->flags & KVM_CPUID_FLAG_SIGNIFCANT_INDEX) || e->index == index)) return e; } From 7b0035eaa7dab9fd33d6658ad6a755024bdce26c Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Wed, 29 Sep 2021 16:41:12 -0700 Subject: [PATCH 6/6] KVM: selftests: Ensure all migrations are performed when test is affined Rework the CPU selection in the migration worker to ensure the specified number of migrations are performed when the test iteslf is affined to a subset of CPUs. The existing logic skips iterations if the target CPU is not in the original set of possible CPUs, which causes the test to fail if too many iterations are skipped. ==== Test Assertion Failure ==== rseq_test.c:228: i > (NR_TASK_MIGRATIONS / 2) pid=10127 tid=10127 errno=4 - Interrupted system call 1 0x00000000004018e5: main at rseq_test.c:227 2 0x00007fcc8fc66bf6: ?? ??:0 3 0x0000000000401959: _start at ??:? Only performed 4 KVM_RUNs, task stalled too much? Calculate the min/max possible CPUs as a cheap "best effort" to avoid high runtimes when the test is affined to a small percentage of CPUs. Alternatively, a list or xarray of the possible CPUs could be used, but even in a horrendously inefficient setup, such optimizations are not needed because the runtime is completely dominated by the cost of migrating the task, and the absolute runtime is well under a minute in even truly absurd setups, e.g. running on a subset of vCPUs in a VM that is heavily overcommited (16 vCPUs per pCPU). Fixes: 61e52f1630f5 ("KVM: selftests: Add a test for KVM_RUN+rseq to detect task migration bugs") Reported-by: Dongli Zhang Signed-off-by: Sean Christopherson Message-Id: <20210929234112.1862848-1-seanjc@google.com> Signed-off-by: Paolo Bonzini --- tools/testing/selftests/kvm/rseq_test.c | 69 +++++++++++++++++++++---- 1 file changed, 59 insertions(+), 10 deletions(-) diff --git a/tools/testing/selftests/kvm/rseq_test.c b/tools/testing/selftests/kvm/rseq_test.c index c5e0dd664a7b..4158da0da2bb 100644 --- a/tools/testing/selftests/kvm/rseq_test.c +++ b/tools/testing/selftests/kvm/rseq_test.c @@ -10,6 +10,7 @@ #include #include #include +#include #include #include #include @@ -39,6 +40,7 @@ static __thread volatile struct rseq __rseq = { static pthread_t migration_thread; static cpu_set_t possible_mask; +static int min_cpu, max_cpu; static bool done; static atomic_t seq_cnt; @@ -57,20 +59,37 @@ static void sys_rseq(int flags) TEST_ASSERT(!r, "rseq failed, errno = %d (%s)", errno, strerror(errno)); } +static int next_cpu(int cpu) +{ + /* + * Advance to the next CPU, skipping those that weren't in the original + * affinity set. Sadly, there is no CPU_SET_FOR_EACH, and cpu_set_t's + * data storage is considered as opaque. Note, if this task is pinned + * to a small set of discontigous CPUs, e.g. 2 and 1023, this loop will + * burn a lot cycles and the test will take longer than normal to + * complete. + */ + do { + cpu++; + if (cpu > max_cpu) { + cpu = min_cpu; + TEST_ASSERT(CPU_ISSET(cpu, &possible_mask), + "Min CPU = %d must always be usable", cpu); + break; + } + } while (!CPU_ISSET(cpu, &possible_mask)); + + return cpu; +} + static void *migration_worker(void *ign) { cpu_set_t allowed_mask; - int r, i, nr_cpus, cpu; + int r, i, cpu; CPU_ZERO(&allowed_mask); - nr_cpus = CPU_COUNT(&possible_mask); - - for (i = 0; i < NR_TASK_MIGRATIONS; i++) { - cpu = i % nr_cpus; - if (!CPU_ISSET(cpu, &possible_mask)) - continue; - + for (i = 0, cpu = min_cpu; i < NR_TASK_MIGRATIONS; i++, cpu = next_cpu(cpu)) { CPU_SET(cpu, &allowed_mask); /* @@ -154,6 +173,36 @@ static void *migration_worker(void *ign) return NULL; } +static int calc_min_max_cpu(void) +{ + int i, cnt, nproc; + + if (CPU_COUNT(&possible_mask) < 2) + return -EINVAL; + + /* + * CPU_SET doesn't provide a FOR_EACH helper, get the min/max CPU that + * this task is affined to in order to reduce the time spent querying + * unusable CPUs, e.g. if this task is pinned to a small percentage of + * total CPUs. + */ + nproc = get_nprocs_conf(); + min_cpu = -1; + max_cpu = -1; + cnt = 0; + + for (i = 0; i < nproc; i++) { + if (!CPU_ISSET(i, &possible_mask)) + continue; + if (min_cpu == -1) + min_cpu = i; + max_cpu = i; + cnt++; + } + + return (cnt < 2) ? -EINVAL : 0; +} + int main(int argc, char *argv[]) { int r, i, snapshot; @@ -167,8 +216,8 @@ int main(int argc, char *argv[]) TEST_ASSERT(!r, "sched_getaffinity failed, errno = %d (%s)", errno, strerror(errno)); - if (CPU_COUNT(&possible_mask) < 2) { - print_skip("Only one CPU, task migration not possible\n"); + if (calc_min_max_cpu()) { + print_skip("Only one usable CPU, task migration not possible"); exit(KSFT_SKIP); }