From 8646e53633f314e4d746a988240d3b951a92f94a Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Wed, 1 Sep 2021 13:30:26 -0700 Subject: KVM: rseq: Update rseq when processing NOTIFY_RESUME on xfer to KVM guest Invoke rseq's NOTIFY_RESUME handler when processing the flag prior to transferring to a KVM guest, which is roughly equivalent to an exit to userspace and processes many of the same pending actions. While the task cannot be in an rseq critical section as the KVM path is reachable only by via ioctl(KVM_RUN), the side effects that apply to rseq outside of a critical section still apply, e.g. the current CPU needs to be updated if the task is migrated. Clearing TIF_NOTIFY_RESUME without informing rseq can lead to segfaults and other badness in userspace VMMs that use rseq in combination with KVM, e.g. due to the CPU ID being stale after task migration. Fixes: 72c3c0fe54a3 ("x86/kvm: Use generic xfer to guest work function") Reported-by: Peter Foley Bisected-by: Doug Evans Acked-by: Mathieu Desnoyers Cc: Shakeel Butt Cc: Thomas Gleixner Cc: stable@vger.kernel.org Signed-off-by: Sean Christopherson Message-Id: <20210901203030.1292304-2-seanjc@google.com> Signed-off-by: Paolo Bonzini --- kernel/entry/kvm.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'kernel/entry') diff --git a/kernel/entry/kvm.c b/kernel/entry/kvm.c index 49972ee99aff..049fd06b4c3d 100644 --- a/kernel/entry/kvm.c +++ b/kernel/entry/kvm.c @@ -19,8 +19,10 @@ static int xfer_to_guest_mode_work(struct kvm_vcpu *vcpu, unsigned long ti_work) if (ti_work & _TIF_NEED_RESCHED) schedule(); - if (ti_work & _TIF_NOTIFY_RESUME) + if (ti_work & _TIF_NOTIFY_RESUME) { tracehook_notify_resume(NULL); + rseq_handle_notify_resume(NULL, NULL); + } ret = arch_xfer_to_guest_mode_handle_work(vcpu, ti_work); if (ret) -- cgit v1.2.3 From a68de80f61f6af397bc06fb391ff2e571c9c4d80 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Wed, 1 Sep 2021 13:30:27 -0700 Subject: entry: rseq: Call rseq_handle_notify_resume() in tracehook_notify_resume() Invoke rseq_handle_notify_resume() from tracehook_notify_resume() now that the two function are always called back-to-back by architectures that have rseq. The rseq helper is stubbed out for architectures that don't support rseq, i.e. this is a nop across the board. Note, tracehook_notify_resume() is horribly named and arguably does not belong in tracehook.h as literally every line of code in it has nothing to do with tracing. But, that's been true since commit a42c6ded827d ("move key_repace_session_keyring() into tracehook_notify_resume()") first usurped tracehook_notify_resume() back in 2012. Punt cleaning that mess up to future patches. No functional change intended. Acked-by: Mathieu Desnoyers Signed-off-by: Sean Christopherson Message-Id: <20210901203030.1292304-3-seanjc@google.com> Signed-off-by: Paolo Bonzini --- arch/arm/kernel/signal.c | 1 - arch/arm64/kernel/signal.c | 4 +--- arch/csky/kernel/signal.c | 4 +--- arch/mips/kernel/signal.c | 4 +--- arch/powerpc/kernel/signal.c | 4 +--- include/linux/tracehook.h | 2 ++ kernel/entry/common.c | 4 +--- kernel/entry/kvm.c | 4 +--- 8 files changed, 8 insertions(+), 19 deletions(-) (limited to 'kernel/entry') diff --git a/arch/arm/kernel/signal.c b/arch/arm/kernel/signal.c index d0a800be0486..a41e27ace391 100644 --- a/arch/arm/kernel/signal.c +++ b/arch/arm/kernel/signal.c @@ -628,7 +628,6 @@ do_work_pending(struct pt_regs *regs, unsigned int thread_flags, int syscall) uprobe_notify_resume(regs); } else { tracehook_notify_resume(regs); - rseq_handle_notify_resume(NULL, regs); } } local_irq_disable(); diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c index 9fe70b12b34f..c287b9407f28 100644 --- a/arch/arm64/kernel/signal.c +++ b/arch/arm64/kernel/signal.c @@ -940,10 +940,8 @@ void do_notify_resume(struct pt_regs *regs, unsigned long thread_flags) if (thread_flags & (_TIF_SIGPENDING | _TIF_NOTIFY_SIGNAL)) do_signal(regs); - if (thread_flags & _TIF_NOTIFY_RESUME) { + if (thread_flags & _TIF_NOTIFY_RESUME) tracehook_notify_resume(regs); - rseq_handle_notify_resume(NULL, regs); - } if (thread_flags & _TIF_FOREIGN_FPSTATE) fpsimd_restore_current_state(); diff --git a/arch/csky/kernel/signal.c b/arch/csky/kernel/signal.c index 312f046d452d..bc4238b9f709 100644 --- a/arch/csky/kernel/signal.c +++ b/arch/csky/kernel/signal.c @@ -260,8 +260,6 @@ asmlinkage void do_notify_resume(struct pt_regs *regs, if (thread_info_flags & (_TIF_SIGPENDING | _TIF_NOTIFY_SIGNAL)) do_signal(regs); - if (thread_info_flags & _TIF_NOTIFY_RESUME) { + if (thread_info_flags & _TIF_NOTIFY_RESUME) tracehook_notify_resume(regs); - rseq_handle_notify_resume(NULL, regs); - } } diff --git a/arch/mips/kernel/signal.c b/arch/mips/kernel/signal.c index f1e985109da0..c9b2a75563e1 100644 --- a/arch/mips/kernel/signal.c +++ b/arch/mips/kernel/signal.c @@ -906,10 +906,8 @@ asmlinkage void do_notify_resume(struct pt_regs *regs, void *unused, if (thread_info_flags & (_TIF_SIGPENDING | _TIF_NOTIFY_SIGNAL)) do_signal(regs); - if (thread_info_flags & _TIF_NOTIFY_RESUME) { + if (thread_info_flags & _TIF_NOTIFY_RESUME) tracehook_notify_resume(regs); - rseq_handle_notify_resume(NULL, regs); - } user_enter(); } diff --git a/arch/powerpc/kernel/signal.c b/arch/powerpc/kernel/signal.c index e600764a926c..b93b87df499d 100644 --- a/arch/powerpc/kernel/signal.c +++ b/arch/powerpc/kernel/signal.c @@ -293,10 +293,8 @@ void do_notify_resume(struct pt_regs *regs, unsigned long thread_info_flags) do_signal(current); } - if (thread_info_flags & _TIF_NOTIFY_RESUME) { + if (thread_info_flags & _TIF_NOTIFY_RESUME) tracehook_notify_resume(regs); - rseq_handle_notify_resume(NULL, regs); - } } static unsigned long get_tm_stackpointer(struct task_struct *tsk) diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h index 3e80c4bc66f7..2564b7434b4d 100644 --- a/include/linux/tracehook.h +++ b/include/linux/tracehook.h @@ -197,6 +197,8 @@ static inline void tracehook_notify_resume(struct pt_regs *regs) mem_cgroup_handle_over_high(); blkcg_maybe_throttle_current(); + + rseq_handle_notify_resume(NULL, regs); } /* diff --git a/kernel/entry/common.c b/kernel/entry/common.c index bf16395b9e13..d5a61d565ad5 100644 --- a/kernel/entry/common.c +++ b/kernel/entry/common.c @@ -171,10 +171,8 @@ static unsigned long exit_to_user_mode_loop(struct pt_regs *regs, if (ti_work & (_TIF_SIGPENDING | _TIF_NOTIFY_SIGNAL)) handle_signal_work(regs, ti_work); - if (ti_work & _TIF_NOTIFY_RESUME) { + if (ti_work & _TIF_NOTIFY_RESUME) tracehook_notify_resume(regs); - rseq_handle_notify_resume(NULL, regs); - } /* Architecture specific TIF work */ arch_exit_to_user_mode_work(regs, ti_work); diff --git a/kernel/entry/kvm.c b/kernel/entry/kvm.c index 049fd06b4c3d..49972ee99aff 100644 --- a/kernel/entry/kvm.c +++ b/kernel/entry/kvm.c @@ -19,10 +19,8 @@ static int xfer_to_guest_mode_work(struct kvm_vcpu *vcpu, unsigned long ti_work) if (ti_work & _TIF_NEED_RESCHED) schedule(); - if (ti_work & _TIF_NOTIFY_RESUME) { + if (ti_work & _TIF_NOTIFY_RESUME) tracehook_notify_resume(NULL); - rseq_handle_notify_resume(NULL, NULL); - } ret = arch_xfer_to_guest_mode_handle_work(vcpu, ti_work); if (ret) -- cgit v1.2.3