From: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
To: Thomas Gleixner <tglx@linutronix.de>,
LKML <linux-kernel@vger.kernel.org>
Cc: Michael Jeanson <mjeanson@efficios.com>,
Jens Axboe <axboe@kernel.dk>, Paolo Bonzini <pbonzini@redhat.com>,
Sean Christopherson <seanjc@google.com>,
Wei Liu <wei.liu@kernel.org>, Dexuan Cui <decui@microsoft.com>,
Peter Zijlstra <peterz@infradead.org>,
"Paul E. McKenney" <paulmck@kernel.org>,
Boqun Feng <boqun.feng@gmail.com>,
x86@kernel.org, Arnd Bergmann <arnd@arndb.de>,
Heiko Carstens <hca@linux.ibm.com>,
Christian Borntraeger <borntraeger@linux.ibm.com>,
Sven Schnelle <svens@linux.ibm.com>,
Huacai Chen <chenhuacai@kernel.org>,
Paul Walmsley <paul.walmsley@sifive.com>,
Palmer Dabbelt <palmer@dabbelt.com>
Subject: Re: [patch V4 07/36] rseq, virt: Retrigger RSEQ after vcpu_run()
Date: Tue, 9 Sep 2025 09:21:13 -0400 [thread overview]
Message-ID: <ee2c27ed-1c72-4fff-8798-1ad20016da95@efficios.com> (raw)
In-Reply-To: <20250908212925.708769718@linutronix.de>
On 2025-09-08 17:31, Thomas Gleixner wrote:
> Hypervisors invoke resume_user_mode_work() before entering the guest, which
> clears TIF_NOTIFY_RESUME. The @regs argument is NULL as there is no user
> space context available to them, so the rseq notify handler skips
> inspecting the critical section, but updates the CPU/MM CID values
> unconditionally so that the eventual pending rseq event is not lost on the
> way to user space.
>
> This is a pointless exercise as the task might be rescheduled before
> actually returning to user space and it creates unnecessary work in the
> vcpu_run() loops.
>
> It's way more efficient to ignore that invocation based on @regs == NULL
> and let the hypervisors re-raise TIF_NOTIFY_RESUME after returning from the
> vcpu_run() loop before returning from the ioctl().
>
> This ensures that a pending RSEQ update is not lost and the IDs are updated
> before returning to user space.
>
> Once the RSEQ handling is decoupled from TIF_NOTIFY_RESUME, this turns into
> a NOOP.
Reviewed-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
>
> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
> Cc: Paolo Bonzini <pbonzini@redhat.com>
> Cc: Sean Christopherson <seanjc@google.com>
> Cc: Wei Liu <wei.liu@kernel.org>
> Cc: Dexuan Cui <decui@microsoft.com>
> ---
> V3: Add the missing rseq.h include for HV - 0-day
> ---
> drivers/hv/mshv_root_main.c | 3 +
> include/linux/rseq.h | 17 +++++++++
> kernel/rseq.c | 76 +++++++++++++++++++++++---------------------
> virt/kvm/kvm_main.c | 3 +
> 4 files changed, 63 insertions(+), 36 deletions(-)
>
> --- a/drivers/hv/mshv_root_main.c
> +++ b/drivers/hv/mshv_root_main.c
> @@ -28,6 +28,7 @@
> #include <linux/crash_dump.h>
> #include <linux/panic_notifier.h>
> #include <linux/vmalloc.h>
> +#include <linux/rseq.h>
>
> #include "mshv_eventfd.h"
> #include "mshv.h"
> @@ -585,6 +586,8 @@ static long mshv_run_vp_with_root_schedu
> }
> } while (!vp->run.flags.intercept_suspend);
>
> + rseq_virt_userspace_exit();
> +
> return ret;
> }
>
> --- a/include/linux/rseq.h
> +++ b/include/linux/rseq.h
> @@ -38,6 +38,22 @@ static __always_inline void rseq_exit_to
> }
>
> /*
> + * KVM/HYPERV invoke resume_user_mode_work() before entering guest mode,
> + * which clears TIF_NOTIFY_RESUME. To avoid updating user space RSEQ in
> + * that case just to do it eventually again before returning to user space,
> + * the entry resume_user_mode_work() invocation is ignored as the register
> + * argument is NULL.
> + *
> + * After returning from guest mode, they have to invoke this function to
> + * re-raise TIF_NOTIFY_RESUME if necessary.
> + */
> +static inline void rseq_virt_userspace_exit(void)
> +{
> + if (current->rseq_event_pending)
> + set_tsk_thread_flag(current, TIF_NOTIFY_RESUME);
> +}
> +
> +/*
> * If parent process has a registered restartable sequences area, the
> * child inherits. Unregister rseq for a clone with CLONE_VM set.
> */
> @@ -68,6 +84,7 @@ static inline void rseq_execve(struct ta
> static inline void rseq_handle_notify_resume(struct ksignal *ksig, struct pt_regs *regs) { }
> static inline void rseq_signal_deliver(struct ksignal *ksig, struct pt_regs *regs) { }
> static inline void rseq_sched_switch_event(struct task_struct *t) { }
> +static inline void rseq_virt_userspace_exit(void) { }
> static inline void rseq_fork(struct task_struct *t, unsigned long clone_flags) { }
> static inline void rseq_execve(struct task_struct *t) { }
> static inline void rseq_exit_to_user_mode(void) { }
> --- a/kernel/rseq.c
> +++ b/kernel/rseq.c
> @@ -422,50 +422,54 @@ void __rseq_handle_notify_resume(struct
> {
> struct task_struct *t = current;
> int ret, sig;
> + bool event;
> +
> + /*
> + * If invoked from hypervisors before entering the guest via
> + * resume_user_mode_work(), then @regs is a NULL pointer.
> + *
> + * resume_user_mode_work() clears TIF_NOTIFY_RESUME and re-raises
> + * it before returning from the ioctl() to user space when
> + * rseq_event.sched_switch is set.
> + *
> + * So it's safe to ignore here instead of pointlessly updating it
> + * in the vcpu_run() loop.
> + */
> + if (!regs)
> + return;
>
> if (unlikely(t->flags & PF_EXITING))
> return;
>
> /*
> - * If invoked from hypervisors or IO-URING, then @regs is a NULL
> - * pointer, so fixup cannot be done. If the syscall which led to
> - * this invocation was invoked inside a critical section, then it
> - * will either end up in this code again or a possible violation of
> - * a syscall inside a critical region can only be detected by the
> - * debug code in rseq_syscall() in a debug enabled kernel.
> + * Read and clear the event pending bit first. If the task
> + * was not preempted or migrated or a signal is on the way,
> + * there is no point in doing any of the heavy lifting here
> + * on production kernels. In that case TIF_NOTIFY_RESUME
> + * was raised by some other functionality.
> + *
> + * This is correct because the read/clear operation is
> + * guarded against scheduler preemption, which makes it CPU
> + * local atomic. If the task is preempted right after
> + * re-enabling preemption then TIF_NOTIFY_RESUME is set
> + * again and this function is invoked another time _before_
> + * the task is able to return to user mode.
> + *
> + * On a debug kernel, invoke the fixup code unconditionally
> + * with the result handed in to allow the detection of
> + * inconsistencies.
> */
> - if (regs) {
> - /*
> - * Read and clear the event pending bit first. If the task
> - * was not preempted or migrated or a signal is on the way,
> - * there is no point in doing any of the heavy lifting here
> - * on production kernels. In that case TIF_NOTIFY_RESUME
> - * was raised by some other functionality.
> - *
> - * This is correct because the read/clear operation is
> - * guarded against scheduler preemption, which makes it CPU
> - * local atomic. If the task is preempted right after
> - * re-enabling preemption then TIF_NOTIFY_RESUME is set
> - * again and this function is invoked another time _before_
> - * the task is able to return to user mode.
> - *
> - * On a debug kernel, invoke the fixup code unconditionally
> - * with the result handed in to allow the detection of
> - * inconsistencies.
> - */
> - bool event;
> -
> - scoped_guard(RSEQ_EVENT_GUARD) {
> - event = t->rseq_event_pending;
> - t->rseq_event_pending = false;
> - }
> + scoped_guard(RSEQ_EVENT_GUARD) {
> + event = t->rseq_event_pending;
> + t->rseq_event_pending = false;
> + }
>
> - if (IS_ENABLED(CONFIG_DEBUG_RSEQ) || event) {
> - ret = rseq_ip_fixup(regs, event);
> - if (unlikely(ret < 0))
> - goto error;
> - }
> + if (IS_ENABLED(CONFIG_DEBUG_RSEQ) || event) {
> + ret = rseq_ip_fixup(regs, event);
> + if (unlikely(ret < 0))
> + goto error;
> }
> +
> if (unlikely(rseq_update_cpu_node_id(t)))
> goto error;
> return;
> --- a/virt/kvm/kvm_main.c
> +++ b/virt/kvm/kvm_main.c
> @@ -49,6 +49,7 @@
> #include <linux/lockdep.h>
> #include <linux/kthread.h>
> #include <linux/suspend.h>
> +#include <linux/rseq.h>
>
> #include <asm/processor.h>
> #include <asm/ioctl.h>
> @@ -4466,6 +4467,8 @@ static long kvm_vcpu_ioctl(struct file *
> r = kvm_arch_vcpu_ioctl_run(vcpu);
> vcpu->wants_to_run = false;
>
> + rseq_virt_userspace_exit();
> +
> trace_kvm_userspace_exit(vcpu->run->exit_reason, r);
> break;
> }
>
--
Mathieu Desnoyers
EfficiOS Inc.
https://www.efficios.com
next prev parent reply other threads:[~2025-09-09 13:21 UTC|newest]
Thread overview: 83+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-09-08 21:31 [patch V4 00/36] rseq: Optimize exit to user space Thomas Gleixner
2025-09-08 21:31 ` [patch V4 01/36] rseq: Avoid pointless evaluation in __rseq_notify_resume() Thomas Gleixner
2025-09-08 21:31 ` [patch V4 02/36] rseq: Condense the inline stubs Thomas Gleixner
2025-09-08 21:31 ` [patch V4 03/36] rseq: Move algorithm comment to top Thomas Gleixner
2025-09-08 21:31 ` [patch V4 04/36] rseq: Remove the ksig argument from rseq_handle_notify_resume() Thomas Gleixner
2025-09-08 21:31 ` [patch V4 05/36] rseq: Simplify registration Thomas Gleixner
2025-09-08 21:31 ` [patch V4 06/36] rseq: Simplify the event notification Thomas Gleixner
2025-09-09 13:18 ` Mathieu Desnoyers
2025-09-08 21:31 ` [patch V4 07/36] rseq, virt: Retrigger RSEQ after vcpu_run() Thomas Gleixner
2025-09-09 0:00 ` Sean Christopherson
2025-09-09 12:10 ` Thomas Gleixner
2025-09-09 13:21 ` Mathieu Desnoyers [this message]
2025-09-08 21:31 ` [patch V4 08/36] rseq: Avoid CPU/MM CID updates when no event pending Thomas Gleixner
2025-09-09 13:25 ` Mathieu Desnoyers
2025-09-08 21:31 ` [patch V4 09/36] rseq: Introduce struct rseq_data Thomas Gleixner
2025-09-09 13:30 ` Mathieu Desnoyers
2025-09-12 20:44 ` Thomas Gleixner
2025-09-12 21:33 ` Mathieu Desnoyers
2025-09-08 21:31 ` [patch V4 10/36] entry: Cleanup header Thomas Gleixner
2025-09-08 21:31 ` [patch V4 11/36] entry: Remove syscall_enter_from_user_mode_prepare() Thomas Gleixner
2025-09-09 13:33 ` Mathieu Desnoyers
2025-09-08 21:31 ` [patch V4 12/36] entry: Inline irqentry_enter/exit_from/to_user_mode() Thomas Gleixner
2025-09-09 13:38 ` Mathieu Desnoyers
2025-09-09 14:10 ` Thomas Gleixner
2025-09-09 14:59 ` Mathieu Desnoyers
2025-09-08 21:31 ` [patch V4 13/36] sched: Move MM CID related functions to sched.h Thomas Gleixner
2025-09-08 21:31 ` [patch V4 14/36] rseq: Cache CPU ID and MM CID values Thomas Gleixner
2025-09-09 13:43 ` Mathieu Desnoyers
2025-09-09 14:13 ` Thomas Gleixner
2025-09-09 15:01 ` Mathieu Desnoyers
2025-09-08 21:31 ` [patch V4 15/36] rseq: Record interrupt from user space Thomas Gleixner
2025-09-09 13:53 ` Mathieu Desnoyers
2025-09-09 14:17 ` Thomas Gleixner
2025-09-09 15:05 ` Mathieu Desnoyers
2025-09-08 21:31 ` [patch V4 16/36] rseq: Provide tracepoint wrappers for inline code Thomas Gleixner
2025-09-08 21:31 ` [patch V4 17/36] rseq: Expose lightweight statistics in debugfs Thomas Gleixner
2025-09-08 21:32 ` [patch V4 18/36] rseq: Provide static branch for runtime debugging Thomas Gleixner
2025-09-08 21:32 ` [patch V4 19/36] rseq: Provide and use rseq_update_user_cs() Thomas Gleixner
2025-09-09 15:11 ` Mathieu Desnoyers
2025-09-08 21:32 ` [patch V4 20/36] rseq: Replace the original debug implementation Thomas Gleixner
2025-09-08 21:32 ` [patch V4 21/36] rseq: Make exit debugging static branch based Thomas Gleixner
2025-09-08 21:32 ` [patch V4 22/36] rseq: Use static branch for syscall exit debug when GENERIC_IRQ_ENTRY=y Thomas Gleixner
2025-09-08 21:32 ` [patch V4 23/36] rseq: Provide and use rseq_set_ids() Thomas Gleixner
2025-09-11 13:40 ` Mathieu Desnoyers
2025-09-11 16:02 ` Thomas Gleixner
2025-09-11 17:13 ` Mathieu Desnoyers
2025-09-08 21:32 ` [patch V4 24/36] rseq: Separate the signal delivery path Thomas Gleixner
2025-09-08 21:32 ` [patch V4 25/36] rseq: Rework the TIF_NOTIFY handler Thomas Gleixner
2025-09-08 21:32 ` [patch V4 26/36] rseq: Optimize event setting Thomas Gleixner
2025-09-11 14:03 ` Mathieu Desnoyers
2025-09-11 16:06 ` Thomas Gleixner
2025-09-11 17:15 ` Mathieu Desnoyers
2025-09-12 6:58 ` Thomas Gleixner
2025-09-08 21:32 ` [patch V4 27/36] rseq: Implement fast path for exit to user Thomas Gleixner
2025-09-11 14:27 ` Mathieu Desnoyers
2025-09-11 16:08 ` Thomas Gleixner
2025-09-08 21:32 ` [patch V4 28/36] rseq: Switch to fast path processing on " Thomas Gleixner
2025-09-11 14:44 ` Mathieu Desnoyers
2025-09-11 14:45 ` Mathieu Desnoyers
2025-09-11 16:50 ` Thomas Gleixner
2025-09-11 16:47 ` Thomas Gleixner
2025-09-11 20:00 ` Mathieu Desnoyers
2025-09-12 14:22 ` Thomas Gleixner
2025-09-12 15:44 ` Mathieu Desnoyers
2025-09-08 21:32 ` [patch V4 29/36] entry: Split up exit_to_user_mode_prepare() Thomas Gleixner
2025-09-08 21:32 ` [patch V4 30/36] rseq: Split up rseq_exit_to_user_mode() Thomas Gleixner
2025-09-08 21:32 ` [patch V4 31/36] asm-generic: Provide generic TIF infrastructure Thomas Gleixner
2025-09-17 6:16 ` [tip: core/core] " tip-bot2 for Thomas Gleixner
2025-09-08 21:32 ` [patch V4 32/36] x86: Use generic TIF bits Thomas Gleixner
2025-09-17 6:16 ` [tip: core/core] " tip-bot2 for Thomas Gleixner
2025-09-08 21:32 ` [patch V4 33/36] s390: " Thomas Gleixner
2025-09-11 9:11 ` Sven Schnelle
2025-09-11 11:03 ` Heiko Carstens
2025-09-17 6:16 ` [tip: core/core] " tip-bot2 for Thomas Gleixner
2025-09-08 21:32 ` [patch V4 34/36] loongarch: " Thomas Gleixner
2025-09-17 6:16 ` [tip: core/core] " tip-bot2 for Thomas Gleixner
2025-09-08 21:32 ` [patch V4 35/36] riscv: " Thomas Gleixner
2025-09-17 6:16 ` [tip: core/core] " tip-bot2 for Thomas Gleixner
2025-09-08 21:32 ` [patch V4 36/36] rseq: Switch to TIF_RSEQ if supported Thomas Gleixner
2025-09-10 13:55 ` [patch V4 00/36] rseq: Optimize exit to user space Jens Axboe
2025-09-10 14:45 ` Michael Jeanson
2025-09-10 15:34 ` Jens Axboe
2025-09-10 14:54 ` Thomas Gleixner
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=ee2c27ed-1c72-4fff-8798-1ad20016da95@efficios.com \
--to=mathieu.desnoyers@efficios.com \
--cc=arnd@arndb.de \
--cc=axboe@kernel.dk \
--cc=boqun.feng@gmail.com \
--cc=borntraeger@linux.ibm.com \
--cc=chenhuacai@kernel.org \
--cc=decui@microsoft.com \
--cc=hca@linux.ibm.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mjeanson@efficios.com \
--cc=palmer@dabbelt.com \
--cc=paul.walmsley@sifive.com \
--cc=paulmck@kernel.org \
--cc=pbonzini@redhat.com \
--cc=peterz@infradead.org \
--cc=seanjc@google.com \
--cc=svens@linux.ibm.com \
--cc=tglx@linutronix.de \
--cc=wei.liu@kernel.org \
--cc=x86@kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox
all inboxes | Powered by JetHome®