Merge tag 'sched-urgent-2026-03-01' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler fixes from Ingo Molnar:

- Fix zero_vruntime tracking when there's a single task running

- Fix slice protection logic

- Fix the ->vprot logic for reniced tasks

- Fix lag clamping in mixed slice workloads

- Fix objtool uaccess warning (and bug) in the
!CONFIG_RSEQ_SLICE_EXTENSION case caused by unexpected un-inlining,
which triggers with older compilers

- Fix a comment in the rseq registration rseq_size bound check code

- Fix a legacy RSEQ ABI quirk that handled 32-byte area sizes
differently, which special size we now reached naturally and want to
avoid. The visible ugliness of the new reserved field will be avoided
the next time the RSEQ area is extended.

* tag 'sched-urgent-2026-03-01' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
rseq: slice ext: Ensure rseq feature size differs from original rseq size
rseq: Clarify rseq registration rseq_size bound check comment
sched/core: Fix wakeup_preempt's next_class tracking
rseq: Mark rseq_arm_slice_extension_timer() __always_inline
sched/fair: Fix lag clamp
sched/eevdf: Update se->vprot in reweight_entity()
sched/fair: Only set slice protection at pick time
sched/fair: Fix zero_vruntime tracking

fs/binfmt_elf.c

···
 #include <linux/dax.h>
 #include <linux/uaccess.h>
 #include <uapi/linux/rseq.h>
+#include <linux/rseq.h>
 #include <asm/param.h>
 #include <asm/page.h>
 
···
 	}
 #ifdef CONFIG_RSEQ
 	NEW_AUX_ENT(AT_RSEQ_FEATURE_SIZE, offsetof(struct rseq, end));
-	NEW_AUX_ENT(AT_RSEQ_ALIGN, __alignof__(struct rseq));
+	NEW_AUX_ENT(AT_RSEQ_ALIGN, rseq_alloc_align());
 #endif
 #undef NEW_AUX_ENT
 	/* AT_NULL is zero; clear the rest too */

include/linux/rseq.h

···
 		t->rseq = current->rseq;
 }
 
+/*
+ * Value returned by getauxval(AT_RSEQ_ALIGN) and expected by rseq
+ * registration. This is the active rseq area size rounded up to next
+ * power of 2, which guarantees that the rseq structure will always be
+ * aligned on the nearest power of two large enough to contain it, even
+ * as it grows.
+ */
+static inline unsigned int rseq_alloc_align(void)
+{
+	return 1U << get_count_order(offsetof(struct rseq, end));
+}
+
 #else /* CONFIG_RSEQ */
 static inline void rseq_handle_slowpath(struct pt_regs *regs) { }
 static inline void rseq_signal_deliver(struct ksignal *ksig, struct pt_regs *regs) { }

include/linux/rseq_entry.h

···
 }
 
 #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; }
+static __always_inline bool rseq_slice_extension_enabled(void) { return false; }
+static __always_inline bool rseq_arm_slice_extension_timer(void) { return false; }
+static __always_inline void rseq_slice_clear_grant(struct task_struct *t) { }
+static __always_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);

include/linux/sched.h

···
 	u64				deadline;
 	u64				min_vruntime;
 	u64				min_slice;
+	u64				max_slice;
 
 	struct list_head		group_node;
 	unsigned char			on_rq;

include/uapi/linux/rseq.h

···
 };
 
 /*
- * struct rseq is aligned on 4 * 8 bytes to ensure it is always
- * contained within a single cache-line.
+ * The original size and alignment of the allocation for struct rseq is
+ * 32 bytes.
  *
- * A single struct rseq per thread is allowed.
+ * The allocation size needs to be greater or equal to
+ * max(getauxval(AT_RSEQ_FEATURE_SIZE), 32), and the allocation needs to
+ * be aligned on max(getauxval(AT_RSEQ_ALIGN), 32).
+ *
+ * As an alternative, userspace is allowed to use both the original size
+ * and alignment of 32 bytes for backward compatibility.
+ *
+ * A single active struct rseq registration per thread is allowed.
  */
 struct rseq {
 	/*
···
 	struct rseq_slice_ctrl slice_ctrl;
 
 	/*
+	 * Before rseq became extensible, its original size was 32 bytes even
+	 * though the active rseq area was only 20 bytes.
+	 * Exposing a 32 bytes feature size would make life needlessly painful
+	 * for userspace. Therefore, add a reserved byte after byte 32
+	 * to bump the rseq feature size from 32 to 33.
+	 * The next field to be added to the rseq area will be larger
+	 * than one byte, and will replace this reserved byte.
+	 */
+	__u8 __reserved;
+
+	/*
 	 * Flexible array member at end of structure, after last feature field.
 	 */
 	char end[];
-} __attribute__((aligned(4 * sizeof(__u64))));
+} __attribute__((aligned(32)));
 
 #endif /* _UAPI_LINUX_RSEQ_H */

kernel/rseq.c

···
 #include <linux/syscalls.h>
 #include <linux/uaccess.h>
 #include <linux/types.h>
+#include <linux/rseq.h>
 #include <asm/ptrace.h>
 
 #define CREATE_TRACE_POINTS
···
 	 * auxiliary vector AT_RSEQ_ALIGN. If rseq_len is the original rseq
 	 * size, the required alignment is the original struct rseq alignment.
 	 *
-	 * In order to be valid, rseq_len is either the original rseq size, or
-	 * large enough to contain all supported fields, as communicated to
+	 * The rseq_len is required to be greater or equal to the original rseq
+	 * size. In order to be valid, rseq_len is either the original rseq size,
+	 * or large enough to contain all supported fields, as communicated to
 	 * user-space through the ELF auxiliary vector AT_RSEQ_FEATURE_SIZE.
 	 */
 	if (rseq_len < ORIG_RSEQ_SIZE ||
 	    (rseq_len == ORIG_RSEQ_SIZE && !IS_ALIGNED((unsigned long)rseq, ORIG_RSEQ_SIZE)) ||
-	    (rseq_len != ORIG_RSEQ_SIZE && (!IS_ALIGNED((unsigned long)rseq, __alignof__(*rseq)) ||
+	    (rseq_len != ORIG_RSEQ_SIZE && (!IS_ALIGNED((unsigned long)rseq, rseq_alloc_align()) ||
 					    rseq_len < offsetof(struct rseq, end))))
 		return -EINVAL;
 	if (!access_ok(rseq, rseq_len))

kernel/sched/core.c

···
 		/* SCX must consult the BPF scheduler to tell if rq is empty */
 		if (!rq->nr_running && !scx_enabled()) {
 			next = prev;
+			rq->next_class = &idle_sched_class;
 			goto picked;
 		}
 	} else if (!preempt && prev_state) {

kernel/sched/ext.c

···
 	/* see kick_cpus_irq_workfn() */
 	smp_store_release(&rq->scx.kick_sync, rq->scx.kick_sync + 1);
 
-	rq->next_class = &ext_sched_class;
+	rq_modified_begin(rq, &ext_sched_class);
 
 	rq_unpin_lock(rq, rf);
 	balance_one(rq, prev);
···
 	 * If @force_scx is true, always try to pick a SCHED_EXT task,
 	 * regardless of any higher-priority sched classes activity.
 	 */
-	if (!force_scx && sched_class_above(rq->next_class, &ext_sched_class))
+	if (!force_scx && rq_modified_above(rq, &ext_sched_class))
 		return RETRY_TASK;
 
 	keep_prev = rq->scx.flags & SCX_RQ_BAL_KEEP;

kernel/sched/fair.c

···
 	return vruntime_cmp(a->deadline, "<", b->deadline);
 }
 
+/*
+ * Per avg_vruntime() below, cfs_rq::zero_vruntime is only slightly stale
+ * and this value should be no more than two lag bounds. Which puts it in the
+ * general order of:
+ *
+ *	(slice + TICK_NSEC) << NICE_0_LOAD_SHIFT
+ *
+ * which is around 44 bits in size (on 64bit); that is 20 for
+ * NICE_0_LOAD_SHIFT, another 20 for NSEC_PER_MSEC and then a handful for
+ * however many msec the actual slice+tick ends up begin.
+ *
+ * (disregarding the actual divide-by-weight part makes for the worst case
+ * weight of 2, which nicely cancels vs the fuzz in zero_vruntime not actually
+ * being the zero-lag point).
+ */
 static inline s64 entity_key(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
 	return vruntime_op(se->vruntime, "-", cfs_rq->zero_vruntime);
···
 }
 
 static inline
-void sum_w_vruntime_update(struct cfs_rq *cfs_rq, s64 delta)
+void update_zero_vruntime(struct cfs_rq *cfs_rq, s64 delta)
 {
 	/*
-	 * v' = v + d ==> sum_w_vruntime' = sum_runtime - d*sum_weight
+	 * v' = v + d ==> sum_w_vruntime' = sum_w_vruntime - d*sum_weight
 	 */
 	cfs_rq->sum_w_vruntime -= cfs_rq->sum_weight * delta;
+	cfs_rq->zero_vruntime += delta;
 }
 
 /*
- * Specifically: avg_runtime() + 0 must result in entity_eligible() := true
+ * Specifically: avg_vruntime() + 0 must result in entity_eligible() := true
  * For this to be so, the result of this function must have a left bias.
+ *
+ * Called in:
+ *  - place_entity()      -- before enqueue
+ *  - update_entity_lag() -- before dequeue
+ *  - entity_tick()
+ *
+ * This means it is one entry 'behind' but that puts it close enough to where
+ * the bound on entity_key() is at most two lag bounds.
  */
 u64 avg_vruntime(struct cfs_rq *cfs_rq)
 {
 	struct sched_entity *curr = cfs_rq->curr;
-	s64 avg = cfs_rq->sum_w_vruntime;
-	long load = cfs_rq->sum_weight;
+	long weight = cfs_rq->sum_weight;
+	s64 delta = 0;
 
-	if (curr && curr->on_rq) {
-		unsigned long weight = scale_load_down(curr->load.weight);
+	if (curr && !curr->on_rq)
+		curr = NULL;
 
-		avg += entity_key(cfs_rq, curr) * weight;
-		load += weight;
-	}
+	if (weight) {
+		s64 runtime = cfs_rq->sum_w_vruntime;
 
-	if (load) {
+		if (curr) {
+			unsigned long w = scale_load_down(curr->load.weight);
+
+			runtime += entity_key(cfs_rq, curr) * w;
+			weight += w;
+		}
+
 		/* sign flips effective floor / ceiling */
-		if (avg < 0)
-			avg -= (load - 1);
-		avg = div_s64(avg, load);
+		if (runtime < 0)
+			runtime -= (weight - 1);
+
+		delta = div_s64(runtime, weight);
+	} else if (curr) {
+		/*
+		 * When there is but one element, it is the average.
+		 */
+		delta = curr->vruntime - cfs_rq->zero_vruntime;
 	}
 
-	return cfs_rq->zero_vruntime + avg;
+	update_zero_vruntime(cfs_rq, delta);
+
+	return cfs_rq->zero_vruntime;
 }
+
+static inline u64 cfs_rq_max_slice(struct cfs_rq *cfs_rq);
 
 /*
  * lag_i = S - s_i = w_i * (V - v_i)
···
  * EEVDF gives the following limit for a steady state system:
  *
  *   -r_max < lag < max(r_max, q)
- *
- * XXX could add max_slice to the augmented data to track this.
  */
 static void update_entity_lag(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
+	u64 max_slice = cfs_rq_max_slice(cfs_rq) + TICK_NSEC;
 	s64 vlag, limit;
 
 	WARN_ON_ONCE(!se->on_rq);
 
 	vlag = avg_vruntime(cfs_rq) - se->vruntime;
-	limit = calc_delta_fair(max_t(u64, 2*se->slice, TICK_NSEC), se);
+	limit = calc_delta_fair(max_slice, se);
 
 	se->vlag = clamp(vlag, -limit, limit);
 }
···
 	return vruntime_eligible(cfs_rq, se->vruntime);
 }
 
-static void update_zero_vruntime(struct cfs_rq *cfs_rq)
-{
-	u64 vruntime = avg_vruntime(cfs_rq);
-	s64 delta = vruntime_op(vruntime, "-", cfs_rq->zero_vruntime);
-
-	sum_w_vruntime_update(cfs_rq, delta);
-
-	cfs_rq->zero_vruntime = vruntime;
-}
-
 static inline u64 cfs_rq_min_slice(struct cfs_rq *cfs_rq)
 {
 	struct sched_entity *root = __pick_root_entity(cfs_rq);
···
 		min_slice = min(min_slice, root->min_slice);
 
 	return min_slice;
+}
+
+static inline u64 cfs_rq_max_slice(struct cfs_rq *cfs_rq)
+{
+	struct sched_entity *root = __pick_root_entity(cfs_rq);
+	struct sched_entity *curr = cfs_rq->curr;
+	u64 max_slice = 0ULL;
+
+	if (curr && curr->on_rq)
+		max_slice = curr->slice;
+
+	if (root)
+		max_slice = max(max_slice, root->max_slice);
+
+	return max_slice;
 }
 
 static inline bool __entity_less(struct rb_node *a, const struct rb_node *b)
···
 	}
 }
 
+static inline void __max_slice_update(struct sched_entity *se, struct rb_node *node)
+{
+	if (node) {
+		struct sched_entity *rse = __node_2_se(node);
+		if (rse->max_slice > se->max_slice)
+			se->max_slice = rse->max_slice;
+	}
+}
+
 /*
  * se->min_vruntime = min(se->vruntime, {left,right}->min_vruntime)
  */
···
 {
 	u64 old_min_vruntime = se->min_vruntime;
 	u64 old_min_slice = se->min_slice;
+	u64 old_max_slice = se->max_slice;
 	struct rb_node *node = &se->run_node;
 
 	se->min_vruntime = se->vruntime;
···
 	__min_slice_update(se, node->rb_right);
 	__min_slice_update(se, node->rb_left);
 
+	se->max_slice = se->slice;
+	__max_slice_update(se, node->rb_right);
+	__max_slice_update(se, node->rb_left);
+
 	return se->min_vruntime == old_min_vruntime &&
-	       se->min_slice == old_min_slice;
+	       se->min_slice == old_min_slice &&
+	       se->max_slice == old_max_slice;
 }
 
 RB_DECLARE_CALLBACKS(static, min_vruntime_cb, struct sched_entity,
···
 static void __enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
 	sum_w_vruntime_add(cfs_rq, se);
-	update_zero_vruntime(cfs_rq);
 	se->min_vruntime = se->vruntime;
 	se->min_slice = se->slice;
 	rb_add_augmented_cached(&se->run_node, &cfs_rq->tasks_timeline,
···
 	rb_erase_augmented_cached(&se->run_node, &cfs_rq->tasks_timeline,
 				  &min_vruntime_cb);
 	sum_w_vruntime_sub(cfs_rq, se);
-	update_zero_vruntime(cfs_rq);
 }
 
 struct sched_entity *__pick_root_entity(struct cfs_rq *cfs_rq)
···
 			    unsigned long weight)
 {
 	bool curr = cfs_rq->curr == se;
+	bool rel_vprot = false;
+	u64 vprot;
 
 	if (se->on_rq) {
 		/* commit outstanding execution time */
···
 		update_entity_lag(cfs_rq, se);
 		se->deadline -= se->vruntime;
 		se->rel_deadline = 1;
+		if (curr && protect_slice(se)) {
+			vprot = se->vprot - se->vruntime;
+			rel_vprot = true;
+		}
+
 		cfs_rq->nr_queued--;
 		if (!curr)
 			__dequeue_entity(cfs_rq, se);
···
 	if (se->rel_deadline)
 		se->deadline = div_s64(se->deadline * se->load.weight, weight);
 
+	if (rel_vprot)
+		vprot = div_s64(vprot * se->load.weight, weight);
+
 	update_load_set(&se->load, weight);
 
 	do {
···
 	enqueue_load_avg(cfs_rq, se);
 	if (se->on_rq) {
 		place_entity(cfs_rq, se, 0);
+		if (rel_vprot)
+			se->vprot = se->vruntime + vprot;
 		update_load_add(&cfs_rq->load, se->load.weight);
 		if (!curr)
 			__enqueue_entity(cfs_rq, se);
···
 }
 
 static void
-set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
+set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, bool first)
 {
 	clear_buddies(cfs_rq, se);
 
···
 		__dequeue_entity(cfs_rq, se);
 		update_load_avg(cfs_rq, se, UPDATE_TG);
 
-		set_protect_slice(cfs_rq, se);
+		if (first)
+			set_protect_slice(cfs_rq, se);
 	}
 
 	update_stats_curr_start(cfs_rq, se);
···
 	 */
 	update_load_avg(cfs_rq, curr, UPDATE_TG);
 	update_cfs_group(curr);
+
+	/*
+	 * Pulls along cfs_rq::zero_vruntime.
+	 */
+	avg_vruntime(cfs_rq);
 
 #ifdef CONFIG_SCHED_HRTICK
 	/*
···
 				pse = parent_entity(pse);
 			}
 			if (se_depth >= pse_depth) {
-				set_next_entity(cfs_rq_of(se), se);
+				set_next_entity(cfs_rq_of(se), se, true);
 				se = parent_entity(se);
 			}
 		}
 
 		put_prev_entity(cfs_rq, pse);
-		set_next_entity(cfs_rq, se);
+		set_next_entity(cfs_rq, se, true);
 
 		__set_next_task_fair(rq, p, true);
 	}
···
 	t0 = sched_clock_cpu(this_cpu);
 	__sched_balance_update_blocked_averages(this_rq);
 
-	this_rq->next_class = &fair_sched_class;
+	rq_modified_begin(this_rq, &fair_sched_class);
 	raw_spin_rq_unlock(this_rq);
 
 	for_each_domain(this_cpu, sd) {
···
 		pulled_task = 1;
 
 	/* If a higher prio class was modified, restart the pick */
-	if (sched_class_above(this_rq->next_class, &fair_sched_class))
+	if (rq_modified_above(this_rq, &fair_sched_class))
 		pulled_task = -1;
 
 out:
···
 	for_each_sched_entity(se) {
 		struct cfs_rq *cfs_rq = cfs_rq_of(se);
 
-		set_next_entity(cfs_rq, se);
+		set_next_entity(cfs_rq, se, first);
 		/* ensure bandwidth has been allocated on our new cfs_rq */
 		account_cfs_rq_runtime(cfs_rq, 0);
 	}

kernel/sched/sched.h

···
 
 #define sched_class_above(_a, _b)	((_a) < (_b))
 
+static inline void rq_modified_begin(struct rq *rq, const struct sched_class *class)
+{
+	if (sched_class_above(rq->next_class, class))
+		rq->next_class = class;
+}
+
+static inline bool rq_modified_above(struct rq *rq, const struct sched_class *class)
+{
+	return sched_class_above(rq->next_class, class);
+}
+
 static inline bool sched_stop_runnable(struct rq *rq)
 {
 	return rq->stop && task_on_rq_queued(rq->stop);