mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Thomas Gleixner <tglx@linutronix.de>
To: LKML <linux-kernel@vger.kernel.org>
Cc: Jens Axboe <axboe@kernel.dk>,
	Mathieu Desnoyers <mathieu.desnoyers@efficios.com>,
	Peter Zijlstra <peterz@infradead.org>,
	"Paul E. McKenney" <paulmck@kernel.org>,
	Boqun Feng <boqun.feng@gmail.com>,
	Paolo Bonzini <pbonzini@redhat.com>,
	Sean Christopherson <seanjc@google.com>,
	Wei Liu <wei.liu@kernel.org>, Dexuan Cui <decui@microsoft.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: [patch V2 36/37] rseq: Switch to TIF_RSEQ if supported
Date: Sat, 23 Aug 2025 18:40:39 +0200 (CEST)	[thread overview]
Message-ID: <20250823161655.586695263@linutronix.de> (raw)
In-Reply-To: <20250823161326.635281786@linutronix.de>

TIF_NOTIFY_RESUME is a multiplexing TIF bit, which is suboptimal especially
with the RSEQ fast path depending on it, but not really handling it.

Define a seperate TIF_RSEQ in the generic TIF space and enable the full
seperation of fast and slow path for architectures which utilize that.

That avoids the hassle with invocations of resume_user_mode_work() from
hypervisors, which clear TIF_NOTIFY_RESUME. It makes the therefore required
re-evaluation at the end of vcpu_run() a NOOP on architectures which
utilize the generic TIF space and have a seperate TIF_RSEQ.

The hypervisor TIF handling does not include the seperate TIF_RSEQ as there
is no point in doing so. The guest does neither know nor care about the VMM
host applications RSEQ state. That state is only relevant when the ioctl()
returns to user space.

The fastpath implementation still utilizes TIF_NOTIFY_RESUME for failure
handling, but this only happens within exit_to_user_mode_loop(), so
arguably the hypervisor ioctl() code is long done when this happens.

This allows further optimizations for blocking syscall heavy workloads in a
subsequent step.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 include/asm-generic/thread_info_tif.h |    3 +++
 include/linux/irq-entry-common.h      |    2 +-
 include/linux/rseq.h                  |   13 ++++++++++---
 include/linux/rseq_entry.h            |   23 +++++++++++++++++++----
 include/linux/thread_info.h           |    5 +++++
 5 files changed, 38 insertions(+), 8 deletions(-)

--- a/include/asm-generic/thread_info_tif.h
+++ b/include/asm-generic/thread_info_tif.h
@@ -45,4 +45,7 @@
 # define _TIF_RESTORE_SIGMASK	BIT(TIF_RESTORE_SIGMASK)
 #endif
 
+#define TIF_RSEQ		11	// Run RSEQ fast path
+#define _TIF_RSEQ		BIT(TIF_RSEQ)
+
 #endif /* _ASM_GENERIC_THREAD_INFO_TIF_H_ */
--- a/include/linux/irq-entry-common.h
+++ b/include/linux/irq-entry-common.h
@@ -30,7 +30,7 @@
 #define EXIT_TO_USER_MODE_WORK						\
 	(_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_UPROBE |		\
 	 _TIF_NEED_RESCHED | _TIF_NEED_RESCHED_LAZY |			\
-	 _TIF_PATCH_PENDING | _TIF_NOTIFY_SIGNAL |			\
+	 _TIF_PATCH_PENDING | _TIF_NOTIFY_SIGNAL | _TIF_RSEQ |		\
 	 ARCH_EXIT_TO_USER_MODE_WORK)
 
 /**
--- a/include/linux/rseq.h
+++ b/include/linux/rseq.h
@@ -40,7 +40,7 @@ static inline void rseq_signal_deliver(s
 
 static inline void rseq_raise_notify_resume(struct task_struct *t)
 {
-	set_tsk_thread_flag(t, TIF_NOTIFY_RESUME);
+	set_tsk_thread_flag(t, TIF_RSEQ);
 }
 
 /* Invoked from context switch to force evaluation on exit to user */
@@ -122,7 +122,7 @@ static inline void rseq_force_update(voi
  */
 static inline void rseq_virt_userspace_exit(void)
 {
-	if (current->rseq_event.sched_switch)
+	if (!IS_ENABLED(CONFIG_HAVE_GENERIC_TIF_BITS) && current->rseq_event.sched_switch)
 		rseq_raise_notify_resume(current);
 }
 
@@ -147,9 +147,16 @@ static inline void rseq_fork(struct task
 		/*
 		 * If it has rseq, force it into the slow path right away
 		 * because it is guaranteed to fault.
+		 *
+		 * Setting TIF_NOTIFY_RESUME is redundant but harmless for
+		 * architectures which do not have a seperate TIF_RSEQ, but
+		 * for those who do it's required to enforce the slow path
+		 * as the scheduler sets only TIF_RSEQ.
 		 */
-		if (t->rseq_event.has_rseq)
+		if (t->rseq_event.has_rseq) {
 			t->rseq_event.slowpath = true;
+			set_tsk_thread_flag(t, TIF_NOTIFY_RESUME);
+		}
 	}
 }
 
--- a/include/linux/rseq_entry.h
+++ b/include/linux/rseq_entry.h
@@ -502,18 +502,33 @@ static __always_inline bool __rseq_exit_
 	return true;
 }
 
+#ifdef CONFIG_HAVE_GENERIC_TIF_BITS
+# define CHECK_TIF_RSEQ		_TIF_RSEQ
+static __always_inline void clear_tif_rseq(void)
+{
+	clear_thread_flag(TIF_RSEQ);
+}
+#else
+# define CHECK_TIF_RSEQ		0UL
+static inline void clear_tif_rseq(void) { }
+#endif
+
 static __always_inline unsigned long
 rseq_exit_to_user_mode_work(struct pt_regs *regs, unsigned long ti_work, const unsigned long mask)
 {
 	/*
 	 * Check if all work bits have been cleared before handling rseq.
+	 *
+	 * In case of a seperate TIF_RSEQ this checks for all other bits to
+	 * be cleared and TIF_RSEQ to be set.
 	 */
-	if ((ti_work & mask) != 0)
-		return ti_work;
-
-	if (likely(!__rseq_exit_to_user_mode_restart(regs)))
+	if ((ti_work & mask) != CHECK_TIF_RSEQ)
 		return ti_work;
 
+	if (likely(!__rseq_exit_to_user_mode_restart(regs))) {
+		clear_tif_rseq();
+		return ti_work & ~CHECK_TIF_RSEQ;
+	}
 	return ti_work | _TIF_NOTIFY_RESUME;
 }
 
--- a/include/linux/thread_info.h
+++ b/include/linux/thread_info.h
@@ -67,6 +67,11 @@ enum syscall_work_bit {
 #define _TIF_NEED_RESCHED_LAZY _TIF_NEED_RESCHED
 #endif
 
+#ifndef TIF_RSEQ
+# define TIF_RSEQ	TIF_NOTIFY_RESUME
+# define _TIF_RSEQ	_TIF_NOTIFY_RESUME
+#endif
+
 #ifdef __KERNEL__
 
 #ifndef arch_set_restart_data


  parent reply	other threads:[~2025-08-23 16:40 UTC|newest]

Thread overview: 102+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-08-23 16:39 [patch V2 00/37] rseq: Optimize exit to user space Thomas Gleixner
2025-08-23 16:39 ` [patch V2 01/37] rseq: Avoid pointless evaluation in __rseq_notify_resume() Thomas Gleixner
2025-08-25 15:39   ` Mathieu Desnoyers
2025-08-23 16:39 ` [patch V2 02/37] rseq: Condense the inline stubs Thomas Gleixner
2025-08-25 15:40   ` Mathieu Desnoyers
2025-08-23 16:39 ` [patch V2 03/37] resq: Move algorithm comment to top Thomas Gleixner
2025-08-25 15:41   ` Mathieu Desnoyers
2025-08-23 16:39 ` [patch V2 04/37] rseq: Remove the ksig argument from rseq_handle_notify_resume() Thomas Gleixner
2025-08-25 15:43   ` Mathieu Desnoyers
2025-08-23 16:39 ` [patch V2 05/37] rseq: Simplify registration Thomas Gleixner
2025-08-25 15:44   ` Mathieu Desnoyers
2025-08-23 16:39 ` [patch V2 06/37] rseq: Simplify the event notification Thomas Gleixner
2025-08-25 17:36   ` Mathieu Desnoyers
2025-09-02 13:39     ` Thomas Gleixner
2025-09-04 17:19       ` Mathieu Desnoyers
2025-08-23 16:39 ` [patch V2 07/37] rseq, virt: Retrigger RSEQ after vcpu_run() Thomas Gleixner
2025-08-25 17:54   ` Mathieu Desnoyers
2025-08-25 20:24     ` Sean Christopherson
2025-09-02 15:37       ` Thomas Gleixner
2025-08-23 16:39 ` [patch V2 08/37] rseq: Avoid CPU/MM CID updates when no event pending Thomas Gleixner
2025-08-25 18:02   ` Mathieu Desnoyers
2025-09-02 13:41     ` Thomas Gleixner
2025-09-04 17:20       ` Mathieu Desnoyers
2025-08-23 16:39 ` [patch V2 09/37] rseq: Introduce struct rseq_event Thomas Gleixner
2025-08-25 18:11   ` Mathieu Desnoyers
2025-09-02 13:45     ` Thomas Gleixner
2025-08-23 16:39 ` [patch V2 10/37] entry: Cleanup header Thomas Gleixner
2025-08-25 18:13   ` Mathieu Desnoyers
2025-08-23 16:39 ` [patch V2 11/37] entry: Remove syscall_enter_from_user_mode_prepare() Thomas Gleixner
2025-08-23 16:39 ` [patch V2 12/37] entry: Inline irqentry_enter/exit_from/to_user_mode() Thomas Gleixner
2025-08-23 16:39 ` [patch V2 13/37] sched: Move MM CID related functions to sched.h Thomas Gleixner
2025-08-25 18:14   ` Mathieu Desnoyers
2025-08-23 16:39 ` [patch V2 14/37] rseq: Cache CPU ID and MM CID values Thomas Gleixner
2025-08-25 18:19   ` Mathieu Desnoyers
2025-09-02 13:48     ` Thomas Gleixner
2025-09-04 17:21       ` Mathieu Desnoyers
2025-08-23 16:39 ` [patch V2 15/37] rseq: Record interrupt from user space Thomas Gleixner
2025-08-25 18:29   ` Mathieu Desnoyers
2025-09-02 13:54     ` Thomas Gleixner
2025-08-23 16:39 ` [patch V2 16/37] rseq: Provide tracepoint wrappers for inline code Thomas Gleixner
2025-08-25 18:32   ` Mathieu Desnoyers
2025-08-23 16:39 ` [patch V2 17/37] rseq: Expose lightweight statistics in debugfs Thomas Gleixner
2025-08-25 18:34   ` Mathieu Desnoyers
2025-08-23 16:39 ` [patch V2 18/37] rseq: Provide static branch for runtime debugging Thomas Gleixner
2025-08-25 18:36   ` Mathieu Desnoyers
2025-08-25 20:30   ` Michael Jeanson
2025-09-02 13:56     ` Thomas Gleixner
2025-08-23 16:39 ` [patch V2 19/37] rseq: Provide and use rseq_update_user_cs() Thomas Gleixner
2025-08-25 19:16   ` Mathieu Desnoyers
2025-09-02 15:19     ` Thomas Gleixner
2025-08-23 16:39 ` [patch V2 20/37] rseq: Replace the debug crud Thomas Gleixner
2025-08-26 14:21   ` Mathieu Desnoyers
2025-08-23 16:39 ` [patch V2 21/37] rseq: Make exit debugging static branch based Thomas Gleixner
2025-08-26 14:23   ` Mathieu Desnoyers
2025-08-23 16:40 ` [patch V2 22/37] rseq: Use static branch for syscall exit debug when GENERIC_IRQ_ENTRY=y Thomas Gleixner
2025-08-26 14:28   ` Mathieu Desnoyers
2025-08-23 16:40 ` [patch V2 23/37] rseq: Provide and use rseq_set_uids() Thomas Gleixner
2025-08-26 14:52   ` Mathieu Desnoyers
2025-09-02 14:08     ` Thomas Gleixner
2025-09-02 16:33       ` Thomas Gleixner
2025-09-04 17:25         ` Mathieu Desnoyers
2025-08-23 16:40 ` [patch V2 24/37] rseq: Seperate the signal delivery path Thomas Gleixner
2025-08-26 15:08   ` Mathieu Desnoyers
2025-08-23 16:40 ` [patch V2 25/37] rseq: Rework the TIF_NOTIFY handler Thomas Gleixner
2025-08-26 15:12   ` Mathieu Desnoyers
2025-09-02 17:32     ` Thomas Gleixner
2025-09-04  9:52       ` Sean Christopherson
2025-09-04 10:53         ` Thomas Gleixner
2025-09-04 17:07           ` Mathieu Desnoyers
2025-08-23 16:40 ` [patch V2 26/37] rseq: Optimize event setting Thomas Gleixner
2025-08-26 15:26   ` Mathieu Desnoyers
2025-09-02 14:17     ` Thomas Gleixner
2025-08-23 16:40 ` [patch V2 27/37] rseq: Implement fast path for exit to user Thomas Gleixner
2025-08-26 15:33   ` Mathieu Desnoyers
2025-09-02 18:31     ` Thomas Gleixner
2025-08-23 16:40 ` [patch V2 28/37] rseq: Switch to fast path processing on " Thomas Gleixner
2025-08-26 15:40   ` Mathieu Desnoyers
2025-08-27 13:45     ` Mathieu Desnoyers
2025-09-02 18:36       ` Thomas Gleixner
2025-09-04 17:54         ` Mathieu Desnoyers
2025-09-04 21:31           ` Thomas Gleixner
2025-08-23 16:40 ` [patch V2 29/37] entry: Split up exit_to_user_mode_prepare() Thomas Gleixner
2025-08-26 15:41   ` Mathieu Desnoyers
2025-08-23 16:40 ` [patch V2 30/37] rseq: Split up rseq_exit_to_user_mode() Thomas Gleixner
2025-08-26 15:45   ` Mathieu Desnoyers
2025-08-23 16:40 ` [patch V2 31/37] asm-generic: Provide generic TIF infrastructure Thomas Gleixner
2025-08-23 20:37   ` Arnd Bergmann
2025-08-25 19:33   ` Mathieu Desnoyers
2025-08-23 16:40 ` [patch V2 32/37] x86: Use generic TIF bits Thomas Gleixner
2025-08-25 19:34   ` Mathieu Desnoyers
2025-08-23 16:40 ` [patch V2 33/37] s390: " Thomas Gleixner
2025-08-23 16:40 ` [patch V2 34/37] loongarch: " Thomas Gleixner
2025-08-23 16:40 ` [patch V2 35/37] riscv: " Thomas Gleixner
2025-08-23 16:40 ` Thomas Gleixner [this message]
2025-08-25 19:39   ` [patch V2 36/37] rseq: Switch to TIF_RSEQ if supported Mathieu Desnoyers
2025-08-25 20:02   ` Sean Christopherson
2025-09-02 11:03     ` Thomas Gleixner
2025-09-04 10:08       ` Sean Christopherson
2025-09-04 12:26         ` Thomas Gleixner
2025-08-23 16:40 ` [patch V2 37/37] entry/rseq: Optimize for TIF_RSEQ on exit Thomas Gleixner
2025-08-25 19:43   ` Mathieu Desnoyers
2025-08-25 15:10 ` [patch V2 00/37] rseq: Optimize exit to user space Mathieu Desnoyers

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=20250823161655.586695263@linutronix.de \
    --to=tglx@linutronix.de \
    --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=mathieu.desnoyers@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=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®