sched_ext: Merge branch 'for-6.16-fixes' into for-6.17

Pull sched_ext/for-6.16-fixes to receive:

 c50784e99f0e ("sched_ext: Make scx_group_set_weight() always update tg->scx.weight")
 33796b91871a ("sched_ext, sched/core: Don't call scx_group_set_weight() prematurely from sched_create_group()")

which are needed to implement CPU bandwidth control interface support.

Signed-off-by: Tejun Heo <tj@kernel.org>

10 files changed, 37 insertions, 17 deletions

diff --git a/MAINTAINERS b/MAINTAINERS
index a92290fffa16..8841f24d408b 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -22171,7 +22171,7 @@ R:	Tejun Heo <tj@kernel.org>
 R:	David Vernet <void@manifault.com>
 R:	Andrea Righi <arighi@nvidia.com>
 R:	Changwoo Min <changwoo@igalia.com>
-L:	linux-kernel@vger.kernel.org
+L:	sched-ext@lists.linux.dev
 S:	Maintained
 W:	https://github.com/sched-ext/scx
 T:	git://git.kernel.org/pub/scm/linux/kernel/git/tj/sched_ext.git
diff --git a/arch/powerpc/platforms/book3s/vas-api.c b/arch/powerpc/platforms/book3s/vas-api.c
index 0b6365d85d11..dc6f75d3ac6e 100644
--- a/arch/powerpc/platforms/book3s/vas-api.c
+++ b/arch/powerpc/platforms/book3s/vas-api.c
@@ -521,6 +521,15 @@ static int coproc_mmap(struct file *fp, struct vm_area_struct *vma)
 		return -EINVAL;
 	}
 
+	/*
+	 * Map complete page to the paste address. So the user
+	 * space should pass 0ULL to the offset parameter.
+	 */
+	if (vma->vm_pgoff) {
+		pr_debug("Page offset unsupported to map paste address\n");
+		return -EINVAL;
+	}
+
 	/* Ensure instance has an open send window */
 	if (!txwin) {
 		pr_err("No send window open?\n");
diff --git a/arch/powerpc/platforms/powernv/memtrace.c b/arch/powerpc/platforms/powernv/memtrace.c
index 4ac9808e55a4..2ea30b343354 100644
--- a/arch/powerpc/platforms/powernv/memtrace.c
+++ b/arch/powerpc/platforms/powernv/memtrace.c
@@ -48,11 +48,15 @@ static ssize_t memtrace_read(struct file *filp, char __user *ubuf,
 static int memtrace_mmap(struct file *filp, struct vm_area_struct *vma)
 {
 	struct memtrace_entry *ent = filp->private_data;
+	unsigned long ent_nrpages = ent->size >> PAGE_SHIFT;
+	unsigned long vma_nrpages = vma_pages(vma);
 
-	if (ent->size < vma->vm_end - vma->vm_start)
+	/* The requested page offset should be within object's page count */
+	if (vma->vm_pgoff >= ent_nrpages)
 		return -EINVAL;
 
-	if (vma->vm_pgoff << PAGE_SHIFT >= ent->size)
+	/* The requested mapping range should remain within the bounds */
+	if (vma_nrpages > ent_nrpages - vma->vm_pgoff)
 		return -EINVAL;
 
 	vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
diff --git a/include/linux/key.h b/include/linux/key.h
index ba05de8579ec..81b8f05c6898 100644
--- a/include/linux/key.h
+++ b/include/linux/key.h
@@ -236,7 +236,7 @@ struct key {
 #define KEY_FLAG_ROOT_CAN_INVAL	7	/* set if key can be invalidated by root without permission */
 #define KEY_FLAG_KEEP		8	/* set if key should not be removed */
 #define KEY_FLAG_UID_KEYRING	9	/* set if key is a user or user session keyring */
-#define KEY_FLAG_FINAL_PUT	10	/* set if final put has happened on key */
+#define KEY_FLAG_USER_ALIVE	10	/* set if final put has not happened on key yet */
 
 	/* the key type and key description string
 	 * - the desc is used to match a key against search criteria
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 2f8caa9db78d..0e3a00e2a2cc 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -8437,7 +8437,7 @@ void __init sched_init(void)
 		init_cfs_bandwidth(&root_task_group.cfs_bandwidth, NULL);
 #endif /* CONFIG_FAIR_GROUP_SCHED */
 #ifdef CONFIG_EXT_GROUP_SCHED
-		root_task_group.scx_weight = CGROUP_WEIGHT_DFL;
+		scx_tg_init(&root_task_group);
 #endif /* CONFIG_EXT_GROUP_SCHED */
 #ifdef CONFIG_RT_GROUP_SCHED
 		root_task_group.rt_se = (struct sched_rt_entity **)ptr;
@@ -8872,7 +8872,7 @@ struct task_group *sched_create_group(struct task_group *parent)
 	if (!alloc_rt_sched_group(tg, parent))
 		goto err;
 
-	scx_group_set_weight(tg, CGROUP_WEIGHT_DFL);
+	scx_tg_init(tg);
 	alloc_uclamp_sched_group(tg, parent);
 
 	return tg;
diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index 28bb6810e5d1..4db51e708f86 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -4056,6 +4056,11 @@ bool scx_can_stop_tick(struct rq *rq)
 DEFINE_STATIC_PERCPU_RWSEM(scx_cgroup_rwsem);
 static bool scx_cgroup_enabled;
 
+void scx_tg_init(struct task_group *tg)
+{
+	tg->scx_weight = CGROUP_WEIGHT_DFL;
+}
+
 int scx_tg_online(struct task_group *tg)
 {
 	struct scx_sched *sch = scx_root;
@@ -4205,12 +4210,12 @@ void scx_group_set_weight(struct task_group *tg, unsigned long weight)
 
 	percpu_down_read(&scx_cgroup_rwsem);
 
-	if (scx_cgroup_enabled && tg->scx_weight != weight) {
-		if (SCX_HAS_OP(sch, cgroup_set_weight))
-			SCX_CALL_OP(sch, SCX_KF_UNLOCKED, cgroup_set_weight, NULL,
-				    tg_cgrp(tg), weight);
-		tg->scx_weight = weight;
-	}
+	if (scx_cgroup_enabled && SCX_HAS_OP(sch, cgroup_set_weight) &&
+	    tg->scx_weight != weight)
+		SCX_CALL_OP(sch, SCX_KF_UNLOCKED, cgroup_set_weight, NULL,
+			    tg_cgrp(tg), weight);
+
+	tg->scx_weight = weight;
 
 	percpu_up_read(&scx_cgroup_rwsem);
 }
diff --git a/kernel/sched/ext.h b/kernel/sched/ext.h
index 621efa8f0fe9..e7bcaa02ea56 100644
--- a/kernel/sched/ext.h
+++ b/kernel/sched/ext.h
@@ -95,6 +95,7 @@ static inline void scx_update_idle(struct rq *rq, bool idle, bool do_notify) {}
 
 #ifdef CONFIG_CGROUP_SCHED
 #ifdef CONFIG_EXT_GROUP_SCHED
+void scx_tg_init(struct task_group *tg);
 int scx_tg_online(struct task_group *tg);
 void scx_tg_offline(struct task_group *tg);
 int scx_cgroup_can_attach(struct cgroup_taskset *tset);
@@ -104,6 +105,7 @@ void scx_cgroup_cancel_attach(struct cgroup_taskset *tset);
 void scx_group_set_weight(struct task_group *tg, unsigned long cgrp_weight);
 void scx_group_set_idle(struct task_group *tg, bool idle);
 #else	/* CONFIG_EXT_GROUP_SCHED */
+static inline void scx_tg_init(struct task_group *tg) {}
 static inline int scx_tg_online(struct task_group *tg) { return 0; }
 static inline void scx_tg_offline(struct task_group *tg) {}
 static inline int scx_cgroup_can_attach(struct cgroup_taskset *tset) { return 0; }
diff --git a/mm/damon/Kconfig b/mm/damon/Kconfig
index 551745df011b..c93d0c56b963 100644
--- a/mm/damon/Kconfig
+++ b/mm/damon/Kconfig
@@ -4,7 +4,6 @@ menu "Data Access Monitoring"
 
 config DAMON
 	bool "DAMON: Data Access Monitoring Framework"
-	default y
 	help
 	  This builds a framework that allows kernel subsystems to monitor
 	  access frequency of each memory region. The information can be useful
diff --git a/security/keys/gc.c b/security/keys/gc.c
index f27223ea4578..748e83818a76 100644
--- a/security/keys/gc.c
+++ b/security/keys/gc.c
@@ -218,8 +218,8 @@ continue_scanning:
 		key = rb_entry(cursor, struct key, serial_node);
 		cursor = rb_next(cursor);
 
-		if (test_bit(KEY_FLAG_FINAL_PUT, &key->flags)) {
-			smp_mb(); /* Clobber key->user after FINAL_PUT seen. */
+		if (!test_bit_acquire(KEY_FLAG_USER_ALIVE, &key->flags)) {
+			/* Clobber key->user after final put seen. */
 			goto found_unreferenced_key;
 		}
 
diff --git a/security/keys/key.c b/security/keys/key.c
index 7198cd2ac3a3..3bbdde778631 100644
--- a/security/keys/key.c
+++ b/security/keys/key.c
@@ -298,6 +298,7 @@ struct key *key_alloc(struct key_type *type, const char *desc,
 	key->restrict_link = restrict_link;
 	key->last_used_at = ktime_get_real_seconds();
 
+	key->flags |= 1 << KEY_FLAG_USER_ALIVE;
 	if (!(flags & KEY_ALLOC_NOT_IN_QUOTA))
 		key->flags |= 1 << KEY_FLAG_IN_QUOTA;
 	if (flags & KEY_ALLOC_BUILT_IN)
@@ -658,8 +659,8 @@ void key_put(struct key *key)
 				key->user->qnbytes -= key->quotalen;
 				spin_unlock_irqrestore(&key->user->lock, flags);
 			}
-			smp_mb(); /* key->user before FINAL_PUT set. */
-			set_bit(KEY_FLAG_FINAL_PUT, &key->flags);
+			/* Mark key as safe for GC after key->user done. */
+			clear_bit_unlock(KEY_FLAG_USER_ALIVE, &key->flags);
 			schedule_work(&key_gc_work);
 		}
 	}