11 files changed, 458 insertions, 50 deletions

diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h
index ea96a4466d82..26d322d43224 100644
--- a/include/linux/compiler_types.h
+++ b/include/linux/compiler_types.h
@@ -620,6 +620,25 @@ struct ftrace_likely_data {
 			 __scalar_type_to_expr_cases(long long),	\
 			 default: (x)))
 
+/*
+ * __signed_scalar_typeof(x) - Declare a signed scalar type, leaving
+ *			       non-scalar types unchanged.
+ */
+
+#define __scalar_type_to_signed_cases(type)				\
+		unsigned type:	(signed type)0,				\
+		signed type:	(signed type)0
+
+#define __signed_scalar_typeof(x) typeof(				\
+		_Generic((x),						\
+			 char:	(signed char)0,				\
+			 __scalar_type_to_signed_cases(char),		\
+			 __scalar_type_to_signed_cases(short),		\
+			 __scalar_type_to_signed_cases(int),		\
+			 __scalar_type_to_signed_cases(long),		\
+			 __scalar_type_to_signed_cases(long long),	\
+			 default: (x)))
+
 /* Is this type a native word size -- useful for atomic operations */
 #define __native_word(t) \
 	(sizeof(t) == sizeof(char) || sizeof(t) == sizeof(short) || \
diff --git a/include/linux/entry-common.h b/include/linux/entry-common.h
index 87efb38b7081..f83ca0abf2cd 100644
--- a/include/linux/entry-common.h
+++ b/include/linux/entry-common.h
@@ -2,6 +2,7 @@
 #ifndef __LINUX_ENTRYCOMMON_H
 #define __LINUX_ENTRYCOMMON_H
 
+#include <linux/audit.h>
 #include <linux/irq-entry-common.h>
 #include <linux/livepatch.h>
 #include <linux/ptrace.h>
@@ -36,8 +37,8 @@
 				 SYSCALL_WORK_SYSCALL_EMU |		\
 				 SYSCALL_WORK_SYSCALL_AUDIT |		\
 				 SYSCALL_WORK_SYSCALL_USER_DISPATCH |	\
+				 SYSCALL_WORK_SYSCALL_RSEQ_SLICE |	\
 				 ARCH_SYSCALL_WORK_ENTER)
-
 #define SYSCALL_WORK_EXIT	(SYSCALL_WORK_SYSCALL_TRACEPOINT |	\
 				 SYSCALL_WORK_SYSCALL_TRACE |		\
 				 SYSCALL_WORK_SYSCALL_AUDIT |		\
@@ -45,7 +46,84 @@
 				 SYSCALL_WORK_SYSCALL_EXIT_TRAP	|	\
 				 ARCH_SYSCALL_WORK_EXIT)
 
-long syscall_trace_enter(struct pt_regs *regs, long syscall, unsigned long work);
+/**
+ * arch_ptrace_report_syscall_entry - Architecture specific ptrace_report_syscall_entry() wrapper
+ *
+ * Invoked from syscall_trace_enter() to wrap ptrace_report_syscall_entry().
+ *
+ * This allows architecture specific ptrace_report_syscall_entry()
+ * implementations. If not defined by the architecture this falls back to
+ * to ptrace_report_syscall_entry().
+ */
+static __always_inline int arch_ptrace_report_syscall_entry(struct pt_regs *regs);
+
+#ifndef arch_ptrace_report_syscall_entry
+static __always_inline int arch_ptrace_report_syscall_entry(struct pt_regs *regs)
+{
+	return ptrace_report_syscall_entry(regs);
+}
+#endif
+
+bool syscall_user_dispatch(struct pt_regs *regs);
+long trace_syscall_enter(struct pt_regs *regs, long syscall);
+void trace_syscall_exit(struct pt_regs *regs, long ret);
+
+static inline void syscall_enter_audit(struct pt_regs *regs, long syscall)
+{
+	if (unlikely(audit_context())) {
+		unsigned long args[6];
+
+		syscall_get_arguments(current, regs, args);
+		audit_syscall_entry(syscall, args[0], args[1], args[2], args[3]);
+	}
+}
+
+static __always_inline long syscall_trace_enter(struct pt_regs *regs, unsigned long work)
+{
+	long syscall, ret = 0;
+
+	/*
+	 * Handle Syscall User Dispatch.  This must comes first, since
+	 * the ABI here can be something that doesn't make sense for
+	 * other syscall_work features.
+	 */
+	if (work & SYSCALL_WORK_SYSCALL_USER_DISPATCH) {
+		if (syscall_user_dispatch(regs))
+			return -1L;
+	}
+
+	/*
+	 * User space got a time slice extension granted and relinquishes
+	 * the CPU. The work stops the slice timer to avoid an extra round
+	 * through hrtimer_interrupt().
+	 */
+	if (work & SYSCALL_WORK_SYSCALL_RSEQ_SLICE)
+		rseq_syscall_enter_work(syscall_get_nr(current, regs));
+
+	/* Handle ptrace */
+	if (work & (SYSCALL_WORK_SYSCALL_TRACE | SYSCALL_WORK_SYSCALL_EMU)) {
+		ret = arch_ptrace_report_syscall_entry(regs);
+		if (ret || (work & SYSCALL_WORK_SYSCALL_EMU))
+			return -1L;
+	}
+
+	/* Do seccomp after ptrace, to catch any tracer changes. */
+	if (work & SYSCALL_WORK_SECCOMP) {
+		ret = __secure_computing();
+		if (ret == -1L)
+			return ret;
+	}
+
+	/* Either of the above might have changed the syscall number */
+	syscall = syscall_get_nr(current, regs);
+
+	if (unlikely(work & SYSCALL_WORK_SYSCALL_TRACEPOINT))
+		syscall = trace_syscall_enter(regs, syscall);
+
+	syscall_enter_audit(regs, syscall);
+
+	return ret ? : syscall;
+}
 
 /**
  * syscall_enter_from_user_mode_work - Check and handle work before invoking
@@ -75,7 +153,7 @@ static __always_inline long syscall_enter_from_user_mode_work(struct pt_regs *re
 	unsigned long work = READ_ONCE(current_thread_info()->syscall_work);
 
 	if (work & SYSCALL_WORK_ENTER)
-		syscall = syscall_trace_enter(regs, syscall, work);
+		syscall = syscall_trace_enter(regs, work);
 
 	return syscall;
 }
@@ -112,6 +190,37 @@ static __always_inline long syscall_enter_from_user_mode(struct pt_regs *regs, l
 	return ret;
 }
 
+/*
+ * If SYSCALL_EMU is set, then the only reason to report is when
+ * SINGLESTEP is set (i.e. PTRACE_SYSEMU_SINGLESTEP).  This syscall
+ * instruction has been already reported in syscall_enter_from_user_mode().
+ */
+static __always_inline bool report_single_step(unsigned long work)
+{
+	if (work & SYSCALL_WORK_SYSCALL_EMU)
+		return false;
+
+	return work & SYSCALL_WORK_SYSCALL_EXIT_TRAP;
+}
+
+/**
+ * arch_ptrace_report_syscall_exit - Architecture specific ptrace_report_syscall_exit()
+ *
+ * This allows architecture specific ptrace_report_syscall_exit()
+ * implementations. If not defined by the architecture this falls back to
+ * to ptrace_report_syscall_exit().
+ */
+static __always_inline void arch_ptrace_report_syscall_exit(struct pt_regs *regs,
+							    int step);
+
+#ifndef arch_ptrace_report_syscall_exit
+static __always_inline void arch_ptrace_report_syscall_exit(struct pt_regs *regs,
+							    int step)
+{
+	ptrace_report_syscall_exit(regs, step);
+}
+#endif
+
 /**
  * syscall_exit_work - Handle work before returning to user mode
  * @regs:	Pointer to current pt_regs
@@ -119,20 +228,40 @@ static __always_inline long syscall_enter_from_user_mode(struct pt_regs *regs, l
  *
  * Do one-time syscall specific work.
  */
-void syscall_exit_work(struct pt_regs *regs, unsigned long work);
+static __always_inline void syscall_exit_work(struct pt_regs *regs, unsigned long work)
+{
+	bool step;
+
+	/*
+	 * If the syscall was rolled back due to syscall user dispatching,
+	 * then the tracers below are not invoked for the same reason as
+	 * the entry side was not invoked in syscall_trace_enter(): The ABI
+	 * of these syscalls is unknown.
+	 */
+	if (work & SYSCALL_WORK_SYSCALL_USER_DISPATCH) {
+		if (unlikely(current->syscall_dispatch.on_dispatch)) {
+			current->syscall_dispatch.on_dispatch = false;
+			return;
+		}
+	}
+
+	audit_syscall_exit(regs);
+
+	if (work & SYSCALL_WORK_SYSCALL_TRACEPOINT)
+		trace_syscall_exit(regs, syscall_get_return_value(current, regs));
+
+	step = report_single_step(work);
+	if (step || work & SYSCALL_WORK_SYSCALL_TRACE)
+		arch_ptrace_report_syscall_exit(regs, step);
+}
 
 /**
- * syscall_exit_to_user_mode_work - Handle work before returning to user mode
+ * syscall_exit_to_user_mode_work - Handle one time work before returning to user mode
  * @regs:	Pointer to currents pt_regs
  *
- * Same as step 1 and 2 of syscall_exit_to_user_mode() but without calling
- * exit_to_user_mode() to perform the final transition to user mode.
+ * Step 1 of syscall_exit_to_user_mode() with the same calling convention.
  *
- * Calling convention is the same as for syscall_exit_to_user_mode() and it
- * returns with all work handled and interrupts disabled. The caller must
- * invoke exit_to_user_mode() before actually switching to user mode to
- * make the final state transitions. Interrupts must stay disabled between
- * return from this function and the invocation of exit_to_user_mode().
+ * The caller must invoke steps 2-3 of syscall_exit_to_user_mode() afterwards.
  */
 static __always_inline void syscall_exit_to_user_mode_work(struct pt_regs *regs)
 {
@@ -155,15 +284,13 @@ static __always_inline void syscall_exit_to_user_mode_work(struct pt_regs *regs)
 	 */
 	if (unlikely(work & SYSCALL_WORK_EXIT))
 		syscall_exit_work(regs, work);
-	local_irq_disable_exit_to_user();
-	syscall_exit_to_user_mode_prepare(regs);
 }
 
 /**
  * syscall_exit_to_user_mode - Handle work before returning to user mode
  * @regs:	Pointer to currents pt_regs
  *
- * Invoked with interrupts enabled and fully valid regs. Returns with all
+ * Invoked with interrupts enabled and fully valid @regs. Returns with all
  * work handled, interrupts disabled such that the caller can immediately
  * switch to user mode. Called from architecture specific syscall and ret
  * from fork code.
@@ -176,6 +303,7 @@ static __always_inline void syscall_exit_to_user_mode_work(struct pt_regs *regs)
  *	- ptrace (single stepping)
  *
  *  2) Preparatory work
+ *	- Disable interrupts
  *	- Exit to user mode loop (common TIF handling). Invokes
  *	  arch_exit_to_user_mode_work() for architecture specific TIF work
  *	- Architecture specific one time work arch_exit_to_user_mode_prepare()
@@ -184,14 +312,17 @@ static __always_inline void syscall_exit_to_user_mode_work(struct pt_regs *regs)
  *  3) Final transition (lockdep, tracing, context tracking, RCU), i.e. the
  *     functionality in exit_to_user_mode().
  *
- * This is a combination of syscall_exit_to_user_mode_work() (1,2) and
- * exit_to_user_mode(). This function is preferred unless there is a
- * compelling architectural reason to use the separate functions.
+ * This is a combination of syscall_exit_to_user_mode_work() (1), disabling
+ * interrupts followed by syscall_exit_to_user_mode_prepare() (2) and
+ * exit_to_user_mode() (3). This function is preferred unless there is a
+ * compelling architectural reason to invoke the functions separately.
  */
 static __always_inline void syscall_exit_to_user_mode(struct pt_regs *regs)
 {
 	instrumentation_begin();
 	syscall_exit_to_user_mode_work(regs);
+	local_irq_disable_exit_to_user();
+	syscall_exit_to_user_mode_prepare(regs);
 	instrumentation_end();
 	exit_to_user_mode();
 }
diff --git a/include/linux/rseq.h b/include/linux/rseq.h
index 2266f4dc77b6..7a01a0760405 100644
--- a/include/linux/rseq.h
+++ b/include/linux/rseq.h
@@ -163,4 +163,15 @@ void rseq_syscall(struct pt_regs *regs);
 static inline void rseq_syscall(struct pt_regs *regs) { }
 #endif /* !CONFIG_DEBUG_RSEQ */
 
+#ifdef CONFIG_RSEQ_SLICE_EXTENSION
+void rseq_syscall_enter_work(long syscall);
+int rseq_slice_extension_prctl(unsigned long arg2, unsigned long arg3);
+#else /* CONFIG_RSEQ_SLICE_EXTENSION */
+static inline void rseq_syscall_enter_work(long syscall) { }
+static inline int rseq_slice_extension_prctl(unsigned long arg2, unsigned long arg3)
+{
+	return -ENOTSUPP;
+}
+#endif /* !CONFIG_RSEQ_SLICE_EXTENSION */
+
 #endif /* _LINUX_RSEQ_H */
diff --git a/include/linux/rseq_entry.h b/include/linux/rseq_entry.h
index a36b472627de..cbc4a791618b 100644
--- a/include/linux/rseq_entry.h
+++ b/include/linux/rseq_entry.h
@@ -15,6 +15,11 @@ struct rseq_stats {
 	unsigned long	cs;
 	unsigned long	clear;
 	unsigned long	fixup;
+	unsigned long	s_granted;
+	unsigned long	s_expired;
+	unsigned long	s_revoked;
+	unsigned long	s_yielded;
+	unsigned long	s_aborted;
 };
 
 DECLARE_PER_CPU(struct rseq_stats, rseq_stats);
@@ -37,6 +42,7 @@ DECLARE_PER_CPU(struct rseq_stats, rseq_stats);
 #ifdef CONFIG_RSEQ
 #include <linux/jump_label.h>
 #include <linux/rseq.h>
+#include <linux/sched/signal.h>
 #include <linux/uaccess.h>
 
 #include <linux/tracepoint-defs.h>
@@ -75,6 +81,147 @@ DECLARE_STATIC_KEY_MAYBE(CONFIG_RSEQ_DEBUG_DEFAULT_ENABLE, rseq_debug_enabled);
 #define rseq_inline __always_inline
 #endif
 
+#ifdef CONFIG_RSEQ_SLICE_EXTENSION
+DECLARE_STATIC_KEY_TRUE(rseq_slice_extension_key);
+
+static __always_inline bool rseq_slice_extension_enabled(void)
+{
+	return static_branch_likely(&rseq_slice_extension_key);
+}
+
+extern unsigned int rseq_slice_ext_nsecs;
+bool __rseq_arm_slice_extension_timer(void);
+
+static __always_inline bool rseq_arm_slice_extension_timer(void)
+{
+	if (!rseq_slice_extension_enabled())
+		return false;
+
+	if (likely(!current->rseq.slice.state.granted))
+		return false;
+
+	return __rseq_arm_slice_extension_timer();
+}
+
+static __always_inline void rseq_slice_clear_grant(struct task_struct *t)
+{
+	if (IS_ENABLED(CONFIG_RSEQ_STATS) && t->rseq.slice.state.granted)
+		rseq_stat_inc(rseq_stats.s_revoked);
+	t->rseq.slice.state.granted = false;
+}
+
+static __always_inline bool rseq_grant_slice_extension(bool work_pending)
+{
+	struct task_struct *curr = current;
+	struct rseq_slice_ctrl usr_ctrl;
+	union rseq_slice_state state;
+	struct rseq __user *rseq;
+
+	if (!rseq_slice_extension_enabled())
+		return false;
+
+	/* If not enabled or not a return from interrupt, nothing to do. */
+	state = curr->rseq.slice.state;
+	state.enabled &= curr->rseq.event.user_irq;
+	if (likely(!state.state))
+		return false;
+
+	rseq = curr->rseq.usrptr;
+	scoped_user_rw_access(rseq, efault) {
+
+		/*
+		 * Quick check conditions where a grant is not possible or
+		 * needs to be revoked.
+		 *
+		 *  1) Any TIF bit which needs to do extra work aside of
+		 *     rescheduling prevents a grant.
+		 *
+		 *  2) A previous rescheduling request resulted in a slice
+		 *     extension grant.
+		 */
+		if (unlikely(work_pending || state.granted)) {
+			/* Clear user control unconditionally. No point for checking */
+			unsafe_put_user(0U, &rseq->slice_ctrl.all, efault);
+			rseq_slice_clear_grant(curr);
+			return false;
+		}
+
+		unsafe_get_user(usr_ctrl.all, &rseq->slice_ctrl.all, efault);
+		if (likely(!(usr_ctrl.request)))
+			return false;
+
+		/* Grant the slice extention */
+		usr_ctrl.request = 0;
+		usr_ctrl.granted = 1;
+		unsafe_put_user(usr_ctrl.all, &rseq->slice_ctrl.all, efault);
+	}
+
+	rseq_stat_inc(rseq_stats.s_granted);
+
+	curr->rseq.slice.state.granted = true;
+	/* Store expiry time for arming the timer on the way out */
+	curr->rseq.slice.expires = data_race(rseq_slice_ext_nsecs) + ktime_get_mono_fast_ns();
+	/*
+	 * This is racy against a remote CPU setting TIF_NEED_RESCHED in
+	 * several ways:
+	 *
+	 * 1)
+	 *	CPU0			CPU1
+	 *	clear_tsk()
+	 *				set_tsk()
+	 *	clear_preempt()
+	 *				Raise scheduler IPI on CPU0
+	 *	--> IPI
+	 *	    fold_need_resched() -> Folds correctly
+	 * 2)
+	 *	CPU0			CPU1
+	 *				set_tsk()
+	 *	clear_tsk()
+	 *	clear_preempt()
+	 *				Raise scheduler IPI on CPU0
+	 *	--> IPI
+	 *	    fold_need_resched() <- NOOP as TIF_NEED_RESCHED is false
+	 *
+	 * #1 is not any different from a regular remote reschedule as it
+	 *    sets the previously not set bit and then raises the IPI which
+	 *    folds it into the preempt counter
+	 *
+	 * #2 is obviously incorrect from a scheduler POV, but it's not
+	 *    differently incorrect than the code below clearing the
+	 *    reschedule request with the safety net of the timer.
+	 *
+	 * The important part is that the clearing is protected against the
+	 * scheduler IPI and also against any other interrupt which might
+	 * end up waking up a task and setting the bits in the middle of
+	 * the operation:
+	 *
+	 *	clear_tsk()
+	 *	---> Interrupt
+	 *		wakeup_on_this_cpu()
+	 *		set_tsk()
+	 *		set_preempt()
+	 *	clear_preempt()
+	 *
+	 * which would be inconsistent state.
+	 */
+	scoped_guard(irq) {
+		clear_tsk_need_resched(curr);
+		clear_preempt_need_resched();
+	}
+	return true;
+
+efault:
+	force_sig(SIGSEGV);
+	return false;
+}
+
+#else /* CONFIG_RSEQ_SLICE_EXTENSION */
+static inline bool rseq_slice_extension_enabled(void) { return false; }
+static inline bool rseq_arm_slice_extension_timer(void) { return false; }
+static inline void rseq_slice_clear_grant(struct task_struct *t) { }
+static inline bool rseq_grant_slice_extension(bool work_pending) { return false; }
+#endif /* !CONFIG_RSEQ_SLICE_EXTENSION */
+
 bool rseq_debug_update_user_cs(struct task_struct *t, struct pt_regs *regs, unsigned long csaddr);
 bool rseq_debug_validate_ids(struct task_struct *t);
 
@@ -359,8 +506,15 @@ bool rseq_set_ids_get_csaddr(struct task_struct *t, struct rseq_ids *ids,
 		unsafe_put_user(ids->mm_cid, &rseq->mm_cid, efault);
 		if (csaddr)
 			unsafe_get_user(*csaddr, &rseq->rseq_cs, efault);
+
+		/* Open coded, so it's in the same user access region */
+		if (rseq_slice_extension_enabled()) {
+			/* Unconditionally clear it, no point in conditionals */
+			unsafe_put_user(0U, &rseq->slice_ctrl.all, efault);
+		}
 	}
 
+	rseq_slice_clear_grant(t);
 	/* Cache the new values */
 	t->rseq.ids.cpu_cid = ids->cpu_cid;
 	rseq_stat_inc(rseq_stats.ids);
@@ -456,8 +610,17 @@ static __always_inline bool rseq_exit_user_update(struct pt_regs *regs, struct t
 		 */
 		u64 csaddr;
 
-		if (unlikely(get_user_inline(csaddr, &rseq->rseq_cs)))
-			return false;
+		scoped_user_rw_access(rseq, efault) {
+			unsafe_get_user(csaddr, &rseq->rseq_cs, efault);
+
+			/* Open coded, so it's in the same user access region */
+			if (rseq_slice_extension_enabled()) {
+				/* Unconditionally clear it, no point in conditionals */
+				unsafe_put_user(0U, &rseq->slice_ctrl.all, efault);
+			}
+		}
+
+		rseq_slice_clear_grant(t);
 
 		if (static_branch_unlikely(&rseq_debug_enabled) || unlikely(csaddr)) {
 			if (unlikely(!rseq_update_user_cs(t, regs, csaddr)))
@@ -473,6 +636,8 @@ static __always_inline bool rseq_exit_user_update(struct pt_regs *regs, struct t
 	u32 node_id = cpu_to_node(ids.cpu_id);
 
 	return rseq_update_usr(t, regs, &ids, node_id);
+efault:
+	return false;
 }
 
 static __always_inline bool __rseq_exit_to_user_mode_restart(struct pt_regs *regs)
@@ -527,17 +692,19 @@ static __always_inline void clear_tif_rseq(void) { }
 static __always_inline bool
 rseq_exit_to_user_mode_restart(struct pt_regs *regs, unsigned long ti_work)
 {
-	if (likely(!test_tif_rseq(ti_work)))
-		return false;
-
-	if (unlikely(__rseq_exit_to_user_mode_restart(regs))) {
-		current->rseq.event.slowpath = true;
-		set_tsk_thread_flag(current, TIF_NOTIFY_RESUME);
-		return true;
+	if (unlikely(test_tif_rseq(ti_work))) {
+		if (unlikely(__rseq_exit_to_user_mode_restart(regs))) {
+			current->rseq.event.slowpath = true;
+			set_tsk_thread_flag(current, TIF_NOTIFY_RESUME);
+			return true;
+		}
+		clear_tif_rseq();
 	}
-
-	clear_tif_rseq();
-	return false;
+	/*
+	 * Arm the slice extension timer if nothing to do anymore and the
+	 * task really goes out to user space.
+	 */
+	return rseq_arm_slice_extension_timer();
 }
 
 #else /* CONFIG_GENERIC_ENTRY */
@@ -611,6 +778,7 @@ static inline void rseq_syscall_exit_to_user_mode(void) { }
 static inline void rseq_irqentry_exit_to_user_mode(void) { }
 static inline void rseq_exit_to_user_mode_legacy(void) { }
 static inline void rseq_debug_syscall_return(struct pt_regs *regs) { }
+static inline bool rseq_grant_slice_extension(bool work_pending) { return false; }
 #endif /* !CONFIG_RSEQ */
 
 #endif /* _LINUX_RSEQ_ENTRY_H */
diff --git a/include/linux/rseq_types.h b/include/linux/rseq_types.h
index ef0811379c54..da5fa6f40294 100644
--- a/include/linux/rseq_types.h
+++ b/include/linux/rseq_types.h
@@ -73,12 +73,39 @@ struct rseq_ids {
 };
 
 /**
+ * union rseq_slice_state - Status information for rseq time slice extension
+ * @state:	Compound to access the overall state
+ * @enabled:	Time slice extension is enabled for the task
+ * @granted:	Time slice extension was granted to the task
+ */
+union rseq_slice_state {
+	u16			state;
+	struct {
+		u8		enabled;
+		u8		granted;
+	};
+};
+
+/**
+ * struct rseq_slice - Status information for rseq time slice extension
+ * @state:	Time slice extension state
+ * @expires:	The time when a grant expires
+ * @yielded:	Indicator for rseq_slice_yield()
+ */
+struct rseq_slice {
+	union rseq_slice_state	state;
+	u64			expires;
+	u8			yielded;
+};
+
+/**
  * struct rseq_data - Storage for all rseq related data
  * @usrptr:	Pointer to the registered user space RSEQ memory
  * @len:	Length of the RSEQ region
- * @sig:	Signature of critial section abort IPs
+ * @sig:	Signature of critical section abort IPs
  * @event:	Storage for event management
  * @ids:	Storage for cached CPU ID and MM CID
+ * @slice:	Storage for time slice extension data
  */
 struct rseq_data {
 	struct rseq __user		*usrptr;
@@ -86,6 +113,9 @@ struct rseq_data {
 	u32				sig;
 	struct rseq_event		event;
 	struct rseq_ids			ids;
+#ifdef CONFIG_RSEQ_SLICE_EXTENSION
+	struct rseq_slice		slice;
+#endif
 };
 
 #else /* CONFIG_RSEQ */
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 8faf653803a1..36ae08ca0c62 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -586,15 +586,10 @@ struct sched_entity {
 	u64				sum_exec_runtime;
 	u64				prev_sum_exec_runtime;
 	u64				vruntime;
-	union {
-		/*
-		 * When !@on_rq this field is vlag.
-		 * When cfs_rq->curr == se (which implies @on_rq)
-		 * this field is vprot. See protect_slice().
-		 */
-		s64                     vlag;
-		u64                     vprot;
-	};
+	/* Approximated virtual lag: */
+	s64				vlag;
+	/* 'Protected' deadline, to give out minimum quantums: */
+	u64				vprot;
 	u64				slice;
 
 	u64				nr_migrations;
@@ -956,7 +951,6 @@ struct task_struct {
 
 	struct mm_struct		*mm;
 	struct mm_struct		*active_mm;
-	struct address_space		*faults_disabled_mapping;
 
 	int				exit_state;
 	int				exit_code;
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index cf84d98964b2..6c8a570cf44a 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -961,6 +961,7 @@ asmlinkage long sys_statx(int dfd, const char __user *path, unsigned flags,
 			  unsigned mask, struct statx __user *buffer);
 asmlinkage long sys_rseq(struct rseq __user *rseq, uint32_t rseq_len,
 			 int flags, uint32_t sig);
+asmlinkage long sys_rseq_slice_yield(void);
 asmlinkage long sys_open_tree(int dfd, const char __user *path, unsigned flags);
 asmlinkage long sys_open_tree_attr(int dfd, const char __user *path,
 				   unsigned flags,
diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h
index b40de9bab4b7..051e42902690 100644
--- a/include/linux/thread_info.h
+++ b/include/linux/thread_info.h
@@ -46,15 +46,17 @@ enum syscall_work_bit {
 	SYSCALL_WORK_BIT_SYSCALL_AUDIT,
 	SYSCALL_WORK_BIT_SYSCALL_USER_DISPATCH,
 	SYSCALL_WORK_BIT_SYSCALL_EXIT_TRAP,
+	SYSCALL_WORK_BIT_SYSCALL_RSEQ_SLICE,
 };
 
-#define SYSCALL_WORK_SECCOMP		BIT(SYSCALL_WORK_BIT_SECCOMP)
-#define SYSCALL_WORK_SYSCALL_TRACEPOINT	BIT(SYSCALL_WORK_BIT_SYSCALL_TRACEPOINT)
-#define SYSCALL_WORK_SYSCALL_TRACE	BIT(SYSCALL_WORK_BIT_SYSCALL_TRACE)
-#define SYSCALL_WORK_SYSCALL_EMU	BIT(SYSCALL_WORK_BIT_SYSCALL_EMU)
-#define SYSCALL_WORK_SYSCALL_AUDIT	BIT(SYSCALL_WORK_BIT_SYSCALL_AUDIT)
-#define SYSCALL_WORK_SYSCALL_USER_DISPATCH BIT(SYSCALL_WORK_BIT_SYSCALL_USER_DISPATCH)
-#define SYSCALL_WORK_SYSCALL_EXIT_TRAP	BIT(SYSCALL_WORK_BIT_SYSCALL_EXIT_TRAP)
+#define SYSCALL_WORK_SECCOMP			BIT(SYSCALL_WORK_BIT_SECCOMP)
+#define SYSCALL_WORK_SYSCALL_TRACEPOINT		BIT(SYSCALL_WORK_BIT_SYSCALL_TRACEPOINT)
+#define SYSCALL_WORK_SYSCALL_TRACE		BIT(SYSCALL_WORK_BIT_SYSCALL_TRACE)
+#define SYSCALL_WORK_SYSCALL_EMU		BIT(SYSCALL_WORK_BIT_SYSCALL_EMU)
+#define SYSCALL_WORK_SYSCALL_AUDIT		BIT(SYSCALL_WORK_BIT_SYSCALL_AUDIT)
+#define SYSCALL_WORK_SYSCALL_USER_DISPATCH	BIT(SYSCALL_WORK_BIT_SYSCALL_USER_DISPATCH)
+#define SYSCALL_WORK_SYSCALL_EXIT_TRAP		BIT(SYSCALL_WORK_BIT_SYSCALL_EXIT_TRAP)
+#define SYSCALL_WORK_SYSCALL_RSEQ_SLICE		BIT(SYSCALL_WORK_BIT_SYSCALL_RSEQ_SLICE)
 #endif
 
 #include <asm/thread_info.h>
diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h
index 942370b3f5d2..a627acc8fb5f 100644
--- a/include/uapi/asm-generic/unistd.h
+++ b/include/uapi/asm-generic/unistd.h
@@ -860,8 +860,11 @@ __SYSCALL(__NR_file_setattr, sys_file_setattr)
 #define __NR_listns 470
 __SYSCALL(__NR_listns, sys_listns)
 
+#define __NR_rseq_slice_yield 471
+__SYSCALL(__NR_rseq_slice_yield, sys_rseq_slice_yield)
+
 #undef __NR_syscalls
-#define __NR_syscalls 471
+#define __NR_syscalls 472
 
 /*
  * 32 bit systems traditionally used different
diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h
index 51c4e8c82b1e..79944b7ae50a 100644
--- a/include/uapi/linux/prctl.h
+++ b/include/uapi/linux/prctl.h
@@ -386,4 +386,14 @@ struct prctl_mm_map {
 # define PR_FUTEX_HASH_SET_SLOTS	1
 # define PR_FUTEX_HASH_GET_SLOTS	2
 
+/* RSEQ time slice extensions */
+#define PR_RSEQ_SLICE_EXTENSION			79
+# define PR_RSEQ_SLICE_EXTENSION_GET		1
+# define PR_RSEQ_SLICE_EXTENSION_SET		2
+/*
+ * Bits for RSEQ_SLICE_EXTENSION_GET/SET
+ * PR_RSEQ_SLICE_EXT_ENABLE:	Enable
+ */
+# define PR_RSEQ_SLICE_EXT_ENABLE		0x01
+
 #endif /* _LINUX_PRCTL_H */
diff --git a/include/uapi/linux/rseq.h b/include/uapi/linux/rseq.h
index 1b76d508400c..863c4a00a66b 100644
--- a/include/uapi/linux/rseq.h
+++ b/include/uapi/linux/rseq.h
@@ -19,13 +19,20 @@ enum rseq_cpu_id_state {
 };
 
 enum rseq_flags {
-	RSEQ_FLAG_UNREGISTER = (1 << 0),
+	RSEQ_FLAG_UNREGISTER			= (1 << 0),
+	RSEQ_FLAG_SLICE_EXT_DEFAULT_ON		= (1 << 1),
 };
 
 enum rseq_cs_flags_bit {
+	/* Historical and unsupported bits */
 	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,
+	/* (3) Intentional gap to put new bits into a separate byte */
+
+	/* User read only feature flags */
+	RSEQ_CS_FLAG_SLICE_EXT_AVAILABLE_BIT	= 4,
+	RSEQ_CS_FLAG_SLICE_EXT_ENABLED_BIT	= 5,
 };
 
 enum rseq_cs_flags {
@@ -35,6 +42,11 @@ 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_SLICE_EXT_AVAILABLE	=
+		(1U << RSEQ_CS_FLAG_SLICE_EXT_AVAILABLE_BIT),
+	RSEQ_CS_FLAG_SLICE_EXT_ENABLED		=
+		(1U << RSEQ_CS_FLAG_SLICE_EXT_ENABLED_BIT),
 };
 
 /*
@@ -53,6 +65,27 @@ struct rseq_cs {
 	__u64 abort_ip;
 } __attribute__((aligned(4 * sizeof(__u64))));
 
+/**
+ * rseq_slice_ctrl - Time slice extension control structure
+ * @all:	Compound value
+ * @request:	Request for a time slice extension
+ * @granted:	Granted time slice extension
+ *
+ * @request is set by user space and can be cleared by user space or kernel
+ * space.  @granted is set and cleared by the kernel and must only be read
+ * by user space.
+ */
+struct rseq_slice_ctrl {
+	union {
+		__u32		all;
+		struct {
+			__u8	request;
+			__u8	granted;
+			__u16	__reserved;
+		};
+	};
+};
+
 /*
  * struct rseq is aligned on 4 * 8 bytes to ensure it is always
  * contained within a single cache-line.
@@ -142,6 +175,12 @@ struct rseq {
 	__u32 mm_cid;
 
 	/*
+	 * Time slice extension control structure. CPU local updates from
+	 * kernel and user space.
+	 */
+	struct rseq_slice_ctrl slice_ctrl;
+
+	/*
 	 * Flexible array member at end of structure, after last feature field.
 	 */
 	char end[];