From 66c1b6d74cd7035e85c426f0af4aede19e805c8a Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Mon, 1 Feb 2021 18:46:49 +0100 Subject: x86: Move TS_COMPAT back to asm/thread_info.h Move TS_COMPAT back to asm/thread_info.h, close to TS_I386_REGS_POKED. It was moved to asm/processor.h by b9d989c7218a ("x86/asm: Move the thread_info::status field to thread_struct"), then later 37a8f7c38339 ("x86/asm: Move 'status' from thread_struct to thread_info") moved the 'status' field back but TS_COMPAT was forgotten. Preparatory patch to fix the COMPAT case for get_nr_restart_syscall() Fixes: 609c19a385c8 ("x86/ptrace: Stop setting TS_COMPAT in ptrace code") Signed-off-by: Oleg Nesterov Signed-off-by: Thomas Gleixner Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20210201174649.GA17880@redhat.com --- arch/x86/include/asm/processor.h | 9 --------- arch/x86/include/asm/thread_info.h | 9 +++++++++ 2 files changed, 9 insertions(+), 9 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index dc6d149bf851..f1b9ed5efaa9 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -551,15 +551,6 @@ static inline void arch_thread_struct_whitelist(unsigned long *offset, *size = fpu_kernel_xstate_size; } -/* - * Thread-synchronous status. - * - * This is different from the flags in that nobody else - * ever touches our thread-synchronous status, so we don't - * have to worry about atomic accesses. - */ -#define TS_COMPAT 0x0002 /* 32bit syscall active (64BIT)*/ - static inline void native_load_sp0(unsigned long sp0) { diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index 0d751d5da702..c2dc29e215ea 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -205,6 +205,15 @@ static inline int arch_within_stack_frames(const void * const stack, #endif +/* + * Thread-synchronous status. + * + * This is different from the flags in that nobody else + * ever touches our thread-synchronous status, so we don't + * have to worry about atomic accesses. + */ +#define TS_COMPAT 0x0002 /* 32bit syscall active (64BIT)*/ + #ifdef CONFIG_COMPAT #define TS_I386_REGS_POKED 0x0004 /* regs poked by 32-bit ptracer */ #endif -- cgit v1.2.3 From 8c150ba2fb5995c84a7a43848250d444a3329a7d Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Mon, 1 Feb 2021 18:47:09 +0100 Subject: x86: Introduce TS_COMPAT_RESTART to fix get_nr_restart_syscall() The comment in get_nr_restart_syscall() says: * The problem is that we can get here when ptrace pokes * syscall-like values into regs even if we're not in a syscall * at all. Yes, but if not in a syscall then the status & (TS_COMPAT|TS_I386_REGS_POKED) check below can't really help: - TS_COMPAT can't be set - TS_I386_REGS_POKED is only set if regs->orig_ax was changed by 32bit debugger; and even in this case get_nr_restart_syscall() is only correct if the tracee is 32bit too. Suppose that a 64bit debugger plays with a 32bit tracee and * Tracee calls sleep(2) // TS_COMPAT is set * User interrupts the tracee by CTRL-C after 1 sec and does "(gdb) call func()" * gdb saves the regs by PTRACE_GETREGS * does PTRACE_SETREGS to set %rip='func' and %orig_rax=-1 * PTRACE_CONT // TS_COMPAT is cleared * func() hits int3. * Debugger catches SIGTRAP. * Restore original regs by PTRACE_SETREGS. * PTRACE_CONT get_nr_restart_syscall() wrongly returns __NR_restart_syscall==219, the tracee calls ia32_sys_call_table[219] == sys_madvise. Add the sticky TS_COMPAT_RESTART flag which survives after return to user mode. It's going to be removed in the next step again by storing the information in the restart block. As a further cleanup it might be possible to remove also TS_I386_REGS_POKED with that. Test-case: $ cvs -d :pserver:anoncvs:anoncvs@sourceware.org:/cvs/systemtap co ptrace-tests $ gcc -o erestartsys-trap-debuggee ptrace-tests/tests/erestartsys-trap-debuggee.c --m32 $ gcc -o erestartsys-trap-debugger ptrace-tests/tests/erestartsys-trap-debugger.c -lutil $ ./erestartsys-trap-debugger Unexpected: retval 1, errno 22 erestartsys-trap-debugger: ptrace-tests/tests/erestartsys-trap-debugger.c:421 Fixes: 609c19a385c8 ("x86/ptrace: Stop setting TS_COMPAT in ptrace code") Reported-by: Jan Kratochvil Signed-off-by: Oleg Nesterov Signed-off-by: Thomas Gleixner Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20210201174709.GA17895@redhat.com --- arch/x86/include/asm/thread_info.h | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index c2dc29e215ea..30d1d187019f 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -214,10 +214,22 @@ static inline int arch_within_stack_frames(const void * const stack, */ #define TS_COMPAT 0x0002 /* 32bit syscall active (64BIT)*/ +#ifndef __ASSEMBLY__ #ifdef CONFIG_COMPAT #define TS_I386_REGS_POKED 0x0004 /* regs poked by 32-bit ptracer */ +#define TS_COMPAT_RESTART 0x0008 + +#define arch_set_restart_data arch_set_restart_data + +static inline void arch_set_restart_data(struct restart_block *restart) +{ + struct thread_info *ti = current_thread_info(); + if (ti->status & TS_COMPAT) + ti->status |= TS_COMPAT_RESTART; + else + ti->status &= ~TS_COMPAT_RESTART; +} #endif -#ifndef __ASSEMBLY__ #ifdef CONFIG_X86_32 #define in_ia32_syscall() true -- cgit v1.2.3 From b2e9df850c58c2b36e915e7d3bed3f6107cccba6 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Mon, 1 Feb 2021 18:47:16 +0100 Subject: x86: Introduce restart_block->arch_data to remove TS_COMPAT_RESTART Save the current_thread_info()->status of X86 in the new restart_block->arch_data field so TS_COMPAT_RESTART can be removed again. Signed-off-by: Oleg Nesterov Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/20210201174716.GA17898@redhat.com --- arch/x86/include/asm/thread_info.h | 12 ++---------- 1 file changed, 2 insertions(+), 10 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index 30d1d187019f..06b740bae431 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -217,18 +217,10 @@ static inline int arch_within_stack_frames(const void * const stack, #ifndef __ASSEMBLY__ #ifdef CONFIG_COMPAT #define TS_I386_REGS_POKED 0x0004 /* regs poked by 32-bit ptracer */ -#define TS_COMPAT_RESTART 0x0008 -#define arch_set_restart_data arch_set_restart_data +#define arch_set_restart_data(restart) \ + do { restart->arch_data = current_thread_info()->status; } while (0) -static inline void arch_set_restart_data(struct restart_block *restart) -{ - struct thread_info *ti = current_thread_info(); - if (ti->status & TS_COMPAT) - ti->status |= TS_COMPAT_RESTART; - else - ti->status &= ~TS_COMPAT_RESTART; -} #endif #ifdef CONFIG_X86_32 -- cgit v1.2.3 From cc9cfddb0433961107bb156fa769fdd7eb6718de Mon Sep 17 00:00:00 2001 From: Vitaly Kuznetsov Date: Tue, 16 Mar 2021 15:37:35 +0100 Subject: KVM: x86: hyper-v: Track Hyper-V TSC page status Create an infrastructure for tracking Hyper-V TSC page status, i.e. if it was updated from guest/host side or if we've failed to set it up (because e.g. guest wrote some garbage to HV_X64_MSR_REFERENCE_TSC) and there's no need to retry. Also, in a hypothetical situation when we are in 'always catchup' mode for TSC we can now avoid contending 'hv->hv_lock' on every guest enter by setting the state to HV_TSC_PAGE_BROKEN after compute_tsc_page_parameters() returns false. Check for HV_TSC_PAGE_SET state instead of '!hv->tsc_ref.tsc_sequence' in get_time_ref_counter() to properly handle the situation when we failed to write the updated TSC page values to the guest. Signed-off-by: Vitaly Kuznetsov Message-Id: <20210316143736.964151-4-vkuznets@redhat.com> Signed-off-by: Paolo Bonzini --- arch/x86/include/asm/kvm_host.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 9bc091ecaaeb..e1b6e2edc828 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -884,12 +884,29 @@ struct kvm_hv_syndbg { u64 options; }; +/* Current state of Hyper-V TSC page clocksource */ +enum hv_tsc_page_status { + /* TSC page was not set up or disabled */ + HV_TSC_PAGE_UNSET = 0, + /* TSC page MSR was written by the guest, update pending */ + HV_TSC_PAGE_GUEST_CHANGED, + /* TSC page MSR was written by KVM userspace, update pending */ + HV_TSC_PAGE_HOST_CHANGED, + /* TSC page was properly set up and is currently active */ + HV_TSC_PAGE_SET, + /* TSC page is currently being updated and therefore is inactive */ + HV_TSC_PAGE_UPDATING, + /* TSC page was set up with an inaccessible GPA */ + HV_TSC_PAGE_BROKEN, +}; + /* Hyper-V emulation context */ struct kvm_hv { struct mutex hv_lock; u64 hv_guest_os_id; u64 hv_hypercall; u64 hv_tsc_page; + enum hv_tsc_page_status hv_tsc_page_status; /* Hyper-v based guest crash (NT kernel bugcheck) parameters */ u64 hv_crash_param[HV_X64_MSR_CRASH_PARAMS]; -- cgit v1.2.3 From b318e8decf6b9ef1bcf4ca06fae6d6a2cb5d5c5c Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Tue, 16 Mar 2021 11:44:33 -0700 Subject: KVM: x86: Protect userspace MSR filter with SRCU, and set atomically-ish Fix a plethora of issues with MSR filtering by installing the resulting filter as an atomic bundle instead of updating the live filter one range at a time. The KVM_X86_SET_MSR_FILTER ioctl() isn't truly atomic, as the hardware MSR bitmaps won't be updated until the next VM-Enter, but the relevant software struct is atomically updated, which is what KVM really needs. Similar to the approach used for modifying memslots, make arch.msr_filter a SRCU-protected pointer, do all the work configuring the new filter outside of kvm->lock, and then acquire kvm->lock only when the new filter has been vetted and created. That way vCPU readers either see the old filter or the new filter in their entirety, not some half-baked state. Yuan Yao pointed out a use-after-free in ksm_msr_allowed() due to a TOCTOU bug, but that's just the tip of the iceberg... - Nothing is __rcu annotated, making it nigh impossible to audit the code for correctness. - kvm_add_msr_filter() has an unpaired smp_wmb(). Violation of kernel coding style aside, the lack of a smb_rmb() anywhere casts all code into doubt. - kvm_clear_msr_filter() has a double free TOCTOU bug, as it grabs count before taking the lock. - kvm_clear_msr_filter() also has memory leak due to the same TOCTOU bug. The entire approach of updating the live filter is also flawed. While installing a new filter is inherently racy if vCPUs are running, fixing the above issues also makes it trivial to ensure certain behavior is deterministic, e.g. KVM can provide deterministic behavior for MSRs with identical settings in the old and new filters. An atomic update of the filter also prevents KVM from getting into a half-baked state, e.g. if installing a filter fails, the existing approach would leave the filter in a half-baked state, having already committed whatever bits of the filter were already processed. [*] https://lkml.kernel.org/r/20210312083157.25403-1-yaoyuan0329os@gmail.com Fixes: 1a155254ff93 ("KVM: x86: Introduce MSR filtering") Cc: stable@vger.kernel.org Cc: Alexander Graf Reported-by: Yuan Yao Signed-off-by: Sean Christopherson Message-Id: <20210316184436.2544875-2-seanjc@google.com> Signed-off-by: Paolo Bonzini --- arch/x86/include/asm/kvm_host.h | 17 +++++++++-------- 1 file changed, 9 insertions(+), 8 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index e1b6e2edc828..3768819693e5 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -948,6 +948,12 @@ enum kvm_irqchip_mode { KVM_IRQCHIP_SPLIT, /* created with KVM_CAP_SPLIT_IRQCHIP */ }; +struct kvm_x86_msr_filter { + u8 count; + bool default_allow:1; + struct msr_bitmap_range ranges[16]; +}; + #define APICV_INHIBIT_REASON_DISABLE 0 #define APICV_INHIBIT_REASON_HYPERV 1 #define APICV_INHIBIT_REASON_NESTED 2 @@ -1042,16 +1048,11 @@ struct kvm_arch { bool guest_can_read_msr_platform_info; bool exception_payload_enabled; + bool bus_lock_detection_enabled; + /* Deflect RDMSR and WRMSR to user space when they trigger a #GP */ u32 user_space_msr_mask; - - struct { - u8 count; - bool default_allow:1; - struct msr_bitmap_range ranges[16]; - } msr_filter; - - bool bus_lock_detection_enabled; + struct kvm_x86_msr_filter __rcu *msr_filter; struct kvm_pmu_event_filter __rcu *pmu_event_filter; struct task_struct *nx_lpage_recovery_thread; -- cgit v1.2.3