Add support for a thread to request extending its execution time slice on
the cpu. The extra cpu time granted would help in allowing the thread to
complete executing the critical section and drop any locks without getting
preempted. The thread would request this cpu time extension, by setting a
bit in the restartable sequences(rseq) structure registered with the kernel.
Kernel will grant a 50us extension on the cpu, when it sees the bit set.
With the help of a timer, kernel force preempts the thread if it is still
running on the cpu when the 50us timer expires. The thread should yield
the cpu after completing the critical section.
Suggested-by: Peter Ziljstra <peterz@infradead.org>
Signed-off-by: Prakash Sangappa <prakash.sangappa@oracle.com>
---
include/linux/entry-common.h | 11 +++++--
include/linux/sched.h | 18 ++++++++++++
include/uapi/linux/rseq.h | 5 ++++
kernel/entry/common.c | 15 ++++++----
kernel/rseq.c | 56 ++++++++++++++++++++++++++++++++++++
kernel/sched/core.c | 16 +++++++++++
kernel/sched/syscalls.c | 5 ++++
7 files changed, 118 insertions(+), 8 deletions(-)
diff --git a/include/linux/entry-common.h b/include/linux/entry-common.h
index fc61d0205c97..cec343f95210 100644
--- a/include/linux/entry-common.h
+++ b/include/linux/entry-common.h
@@ -303,7 +303,8 @@ void arch_do_signal_or_restart(struct pt_regs *regs);
* exit_to_user_mode_loop - do any pending work before leaving to user space
*/
unsigned long exit_to_user_mode_loop(struct pt_regs *regs,
- unsigned long ti_work);
+ unsigned long ti_work,
+ bool irq);
/**
* exit_to_user_mode_prepare - call exit_to_user_mode_loop() if required
@@ -315,7 +316,8 @@ unsigned long exit_to_user_mode_loop(struct pt_regs *regs,
* EXIT_TO_USER_MODE_WORK are set
* 4) check that interrupts are still disabled
*/
-static __always_inline void exit_to_user_mode_prepare(struct pt_regs *regs)
+static __always_inline void exit_to_user_mode_prepare(struct pt_regs *regs,
+ bool irq)
{
unsigned long ti_work;
@@ -326,7 +328,10 @@ static __always_inline void exit_to_user_mode_prepare(struct pt_regs *regs)
ti_work = read_thread_flags();
if (unlikely(ti_work & EXIT_TO_USER_MODE_WORK))
- ti_work = exit_to_user_mode_loop(regs, ti_work);
+ ti_work = exit_to_user_mode_loop(regs, ti_work, irq);
+
+ if (irq)
+ rseq_delay_resched_fini();
arch_exit_to_user_mode_prepare(regs, ti_work);
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 599f077b8019..75abe260de72 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -326,6 +326,7 @@ extern int __must_check io_schedule_prepare(void);
extern void io_schedule_finish(int token);
extern long io_schedule_timeout(long timeout);
extern void io_schedule(void);
+extern void hrtick_local_start(u64 delay);
/**
* struct prev_cputime - snapshot of system and user cputime
@@ -930,6 +931,9 @@ struct task_struct {
struct plist_node pushable_tasks;
struct rb_node pushable_dl_tasks;
#endif
+#ifdef CONFIG_RSEQ
+ unsigned rseq_sched_delay:1;
+#endif
struct mm_struct *mm;
struct mm_struct *active_mm;
@@ -2221,6 +2225,20 @@ static inline bool owner_on_cpu(struct task_struct *owner)
unsigned long sched_cpu_util(int cpu);
#endif /* CONFIG_SMP */
+#ifdef CONFIG_RSEQ
+
+extern bool rseq_delay_resched(void);
+extern void rseq_delay_resched_fini(void);
+extern void rseq_delay_resched_tick(void);
+
+#else
+
+static inline bool rseq_delay_resched(void) { return false; }
+static inline void rseq_delay_resched_fini(void) { }
+static inline void rseq_delay_resched_tick(void) { }
+
+#endif
+
#ifdef CONFIG_SCHED_CORE
extern void sched_core_free(struct task_struct *tsk);
extern void sched_core_fork(struct task_struct *p);
diff --git a/include/uapi/linux/rseq.h b/include/uapi/linux/rseq.h
index c233aae5eac9..ec3b45f32bc8 100644
--- a/include/uapi/linux/rseq.h
+++ b/include/uapi/linux/rseq.h
@@ -26,6 +26,7 @@ enum rseq_cs_flags_bit {
RSEQ_CS_FLAG_NO_RESTART_ON_PREEMPT_BIT = 0,
RSEQ_CS_FLAG_NO_RESTART_ON_SIGNAL_BIT = 1,
RSEQ_CS_FLAG_NO_RESTART_ON_MIGRATE_BIT = 2,
+ RSEQ_CS_FLAG_DELAY_RESCHED_BIT = 3,
};
enum rseq_cs_flags {
@@ -35,6 +36,8 @@ enum rseq_cs_flags {
(1U << RSEQ_CS_FLAG_NO_RESTART_ON_SIGNAL_BIT),
RSEQ_CS_FLAG_NO_RESTART_ON_MIGRATE =
(1U << RSEQ_CS_FLAG_NO_RESTART_ON_MIGRATE_BIT),
+ RSEQ_CS_FLAG_DELAY_RESCHED =
+ (1U << RSEQ_CS_FLAG_DELAY_RESCHED_BIT),
};
/*
@@ -128,6 +131,8 @@ struct rseq {
* - RSEQ_CS_FLAG_NO_RESTART_ON_MIGRATE
* Inhibit instruction sequence block restart on migration for
* this thread.
+ * - RSEQ_CS_DELAY_RESCHED
+ * Try delay resched...
*/
__u32 flags;
diff --git a/kernel/entry/common.c b/kernel/entry/common.c
index 6b7ff1bc1b9b..0db3039345ac 100644
--- a/kernel/entry/common.c
+++ b/kernel/entry/common.c
@@ -89,7 +89,8 @@ void __weak arch_do_signal_or_restart(struct pt_regs *regs) { }
* @ti_work: TIF work flags as read by the caller
*/
__always_inline unsigned long exit_to_user_mode_loop(struct pt_regs *regs,
- unsigned long ti_work)
+ unsigned long ti_work,
+ bool irq)
{
/*
* Before returning to user space ensure that all pending work
@@ -99,8 +100,12 @@ __always_inline unsigned long exit_to_user_mode_loop(struct pt_regs *regs,
local_irq_enable_exit_to_user(ti_work);
- if (ti_work & (_TIF_NEED_RESCHED | _TIF_NEED_RESCHED_LAZY))
- schedule();
+ if (ti_work & (_TIF_NEED_RESCHED | _TIF_NEED_RESCHED_LAZY)) {
+ if (irq && rseq_delay_resched())
+ clear_tsk_need_resched(current);
+ else
+ schedule();
+ }
if (ti_work & _TIF_UPROBE)
uprobe_notify_resume(regs);
@@ -208,7 +213,7 @@ static __always_inline void __syscall_exit_to_user_mode_work(struct pt_regs *reg
{
syscall_exit_to_user_mode_prepare(regs);
local_irq_disable_exit_to_user();
- exit_to_user_mode_prepare(regs);
+ exit_to_user_mode_prepare(regs, false);
}
void syscall_exit_to_user_mode_work(struct pt_regs *regs)
@@ -232,7 +237,7 @@ noinstr void irqentry_enter_from_user_mode(struct pt_regs *regs)
noinstr void irqentry_exit_to_user_mode(struct pt_regs *regs)
{
instrumentation_begin();
- exit_to_user_mode_prepare(regs);
+ exit_to_user_mode_prepare(regs, true);
instrumentation_end();
exit_to_user_mode();
}
diff --git a/kernel/rseq.c b/kernel/rseq.c
index 442aba29bc4c..9f83d47253ce 100644
--- a/kernel/rseq.c
+++ b/kernel/rseq.c
@@ -426,6 +426,62 @@ void __rseq_handle_notify_resume(struct ksignal *ksig, struct pt_regs *regs)
force_sigsegv(sig);
}
+bool rseq_delay_resched(void)
+{
+ struct task_struct *t = current;
+ u32 flags;
+
+ if (!IS_ENABLED(CONFIG_SCHED_HRTICK))
+ return false;
+
+ if (!t->rseq)
+ return false;
+
+ if (t->rseq_sched_delay)
+ return false;
+
+ if (copy_from_user_nofault(&flags, &t->rseq->flags, sizeof(flags)))
+ return false;
+
+ if (!(flags & RSEQ_CS_FLAG_DELAY_RESCHED))
+ return false;
+
+ flags &= ~RSEQ_CS_FLAG_DELAY_RESCHED;
+ if (copy_to_user_nofault(&t->rseq->flags, &flags, sizeof(flags)))
+ return false;
+
+ t->rseq_sched_delay = 1;
+
+ return true;
+}
+
+void rseq_delay_resched_fini(void)
+{
+#ifdef CONFIG_SCHED_HRTICK
+ extern void hrtick_local_start(u64 delay);
+ struct task_struct *t = current;
+ /*
+ * IRQs off, guaranteed to return to userspace, start timer on this CPU
+ * to limit the resched-overdraft.
+ *
+ * If your critical section is longer than 50 us you get to keep the
+ * pieces.
+ */
+ if (t->rseq_sched_delay)
+ hrtick_local_start(50 * NSEC_PER_USEC);
+#endif
+}
+
+void rseq_delay_resched_tick(void)
+{
+#ifdef CONFIG_SCHED_HRTICK
+ struct task_struct *t = current;
+
+ if (t->rseq_sched_delay)
+ set_tsk_need_resched(t);
+#endif
+}
+
#ifdef CONFIG_DEBUG_RSEQ
/*
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 165c90ba64ea..cee50e139723 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -823,6 +823,7 @@ void update_rq_clock(struct rq *rq)
static void hrtick_clear(struct rq *rq)
{
+ rseq_delay_resched_tick();
if (hrtimer_active(&rq->hrtick_timer))
hrtimer_cancel(&rq->hrtick_timer);
}
@@ -838,6 +839,8 @@ static enum hrtimer_restart hrtick(struct hrtimer *timer)
WARN_ON_ONCE(cpu_of(rq) != smp_processor_id());
+ rseq_delay_resched_tick();
+
rq_lock(rq, &rf);
update_rq_clock(rq);
rq->donor->sched_class->task_tick(rq, rq->curr, 1);
@@ -911,6 +914,16 @@ void hrtick_start(struct rq *rq, u64 delay)
#endif /* CONFIG_SMP */
+void hrtick_local_start(u64 delay)
+{
+ struct rq *rq = this_rq();
+ struct rq_flags rf;
+
+ rq_lock(rq, &rf);
+ hrtick_start(rq, delay);
+ rq_unlock(rq, &rf);
+}
+
static void hrtick_rq_init(struct rq *rq)
{
#ifdef CONFIG_SMP
@@ -6718,6 +6731,9 @@ static void __sched notrace __schedule(int sched_mode)
picked:
clear_tsk_need_resched(prev);
clear_preempt_need_resched();
+#ifdef CONFIG_RSEQ
+ prev->rseq_sched_delay = 0;
+#endif
#ifdef CONFIG_SCHED_DEBUG
rq->last_seen_need_resched_ns = 0;
#endif
diff --git a/kernel/sched/syscalls.c b/kernel/sched/syscalls.c
index 3919f03fde57..f2ce1040b737 100644
--- a/kernel/sched/syscalls.c
+++ b/kernel/sched/syscalls.c
@@ -1378,6 +1378,11 @@ static void do_sched_yield(void)
*/
SYSCALL_DEFINE0(sched_yield)
{
+ if (current->rseq_sched_delay) {
+ schedule();
+ return 0;
+ }
+
do_sched_yield();
return 0;
}
--
2.43.5Hi Prakash,
kernel test robot noticed the following build errors:
[auto build test ERROR on tip/sched/core]
[also build test ERROR on peterz-queue/sched/core linus/master v6.14-rc2 next-20250214]
[cannot apply to tip/core/entry]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch#_base_tree_information]
url: https://github.com/intel-lab-lkp/linux/commits/Prakash-Sangappa/Sched-Scheduler-time-slice-extension/20250215-090421
base: tip/sched/core
patch link: https://lore.kernel.org/r/20250215005414.224409-2-prakash.sangappa%40oracle.com
patch subject: [PATCH 1/2] Sched: Scheduler time slice extension
config: alpha-allnoconfig (https://download.01.org/0day-ci/archive/20250216/202502160412.H5MjYC21-lkp@intel.com/config)
compiler: alpha-linux-gcc (GCC) 14.2.0
reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20250216/202502160412.H5MjYC21-lkp@intel.com/reproduce)
If you fix the issue in a separate patch/commit (i.e. not just a new version of
the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <lkp@intel.com>
| Closes: https://lore.kernel.org/oe-kbuild-all/202502160412.H5MjYC21-lkp@intel.com/
All errors (new ones prefixed by >>):
In file included from kernel/sched/build_policy.c:66:
kernel/sched/syscalls.c: In function 'sys_sched_yield':
>> kernel/sched/syscalls.c:1372:20: error: 'struct task_struct' has no member named 'rseq_sched_delay'
1372 | if (current->rseq_sched_delay) {
| ^~
vim +1372 kernel/sched/syscalls.c
1361
1362 /**
1363 * sys_sched_yield - yield the current processor to other threads.
1364 *
1365 * This function yields the current CPU to other tasks. If there are no
1366 * other threads running on this CPU then this function will return.
1367 *
1368 * Return: 0.
1369 */
1370 SYSCALL_DEFINE0(sched_yield)
1371 {
> 1372 if (current->rseq_sched_delay) {
1373 schedule();
1374 return 0;
1375 }
1376
1377 do_sched_yield();
1378 return 0;
1379 }
1380
--
0-DAY CI Kernel Test Service
https://github.com/intel/lkp-tests/wiki
Hi Prakash,
kernel test robot noticed the following build errors:
[auto build test ERROR on tip/sched/core]
[also build test ERROR on peterz-queue/sched/core linus/master v6.14-rc2 next-20250214]
[cannot apply to tip/core/entry]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch#_base_tree_information]
url: https://github.com/intel-lab-lkp/linux/commits/Prakash-Sangappa/Sched-Scheduler-time-slice-extension/20250215-090421
base: tip/sched/core
patch link: https://lore.kernel.org/r/20250215005414.224409-2-prakash.sangappa%40oracle.com
patch subject: [PATCH 1/2] Sched: Scheduler time slice extension
config: hexagon-allnoconfig (https://download.01.org/0day-ci/archive/20250216/202502160310.ZHjm28qH-lkp@intel.com/config)
compiler: clang version 21.0.0git (https://github.com/llvm/llvm-project 910be4ff90d7d07bd4518ea03b85c0974672bf9c)
reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20250216/202502160310.ZHjm28qH-lkp@intel.com/reproduce)
If you fix the issue in a separate patch/commit (i.e. not just a new version of
the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <lkp@intel.com>
| Closes: https://lore.kernel.org/oe-kbuild-all/202502160310.ZHjm28qH-lkp@intel.com/
All errors (new ones prefixed by >>):
In file included from kernel/sched/build_policy.c:66:
>> kernel/sched/syscalls.c:1372:15: error: no member named 'rseq_sched_delay' in 'struct task_struct'
1372 | if (current->rseq_sched_delay) {
| ~~~~~~~ ^
1 error generated.
vim +1372 kernel/sched/syscalls.c
1361
1362 /**
1363 * sys_sched_yield - yield the current processor to other threads.
1364 *
1365 * This function yields the current CPU to other tasks. If there are no
1366 * other threads running on this CPU then this function will return.
1367 *
1368 * Return: 0.
1369 */
1370 SYSCALL_DEFINE0(sched_yield)
1371 {
> 1372 if (current->rseq_sched_delay) {
1373 schedule();
1374 return 0;
1375 }
1376
1377 do_sched_yield();
1378 return 0;
1379 }
1380
--
0-DAY CI Kernel Test Service
https://github.com/intel/lkp-tests/wiki
© 2016 - 2025 Red Hat, Inc.