16 files changed, 85 insertions, 46 deletions

diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index c9fab9a356df..8eb117c52817 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -1215,13 +1215,20 @@ static void bpf_wq_work(struct work_struct *work)
 	rcu_read_unlock_trace();
 }
 
+static void bpf_async_cb_rcu_free(struct rcu_head *rcu)
+{
+	struct bpf_async_cb *cb = container_of(rcu, struct bpf_async_cb, rcu);
+
+	kfree_nolock(cb);
+}
+
 static void bpf_wq_delete_work(struct work_struct *work)
 {
 	struct bpf_work *w = container_of(work, struct bpf_work, delete_work);
 
 	cancel_work_sync(&w->work);
 
-	kfree_rcu(w, cb.rcu);
+	call_rcu(&w->cb.rcu, bpf_async_cb_rcu_free);
 }
 
 static void bpf_timer_delete_work(struct work_struct *work)
@@ -1230,13 +1237,13 @@ static void bpf_timer_delete_work(struct work_struct *work)
 
 	/* Cancel the timer and wait for callback to complete if it was running.
 	 * If hrtimer_cancel() can be safely called it's safe to call
-	 * kfree_rcu(t) right after for both preallocated and non-preallocated
+	 * call_rcu() right after for both preallocated and non-preallocated
 	 * maps.  The async->cb = NULL was already done and no code path can see
 	 * address 't' anymore. Timer if armed for existing bpf_hrtimer before
 	 * bpf_timer_cancel_and_free will have been cancelled.
 	 */
 	hrtimer_cancel(&t->timer);
-	kfree_rcu(t, cb.rcu);
+	call_rcu(&t->cb.rcu, bpf_async_cb_rcu_free);
 }
 
 static int __bpf_async_init(struct bpf_async_kern *async, struct bpf_map *map, u64 flags,
@@ -1270,11 +1277,7 @@ static int __bpf_async_init(struct bpf_async_kern *async, struct bpf_map *map, u
 		goto out;
 	}
 
-	/* Allocate via bpf_map_kmalloc_node() for memcg accounting. Until
-	 * kmalloc_nolock() is available, avoid locking issues by using
-	 * __GFP_HIGH (GFP_ATOMIC & ~__GFP_RECLAIM).
-	 */
-	cb = bpf_map_kmalloc_node(map, size, __GFP_HIGH, map->numa_node);
+	cb = bpf_map_kmalloc_nolock(map, size, 0, map->numa_node);
 	if (!cb) {
 		ret = -ENOMEM;
 		goto out;
@@ -1315,7 +1318,7 @@ static int __bpf_async_init(struct bpf_async_kern *async, struct bpf_map *map, u
 		 * or pinned in bpffs.
 		 */
 		WRITE_ONCE(async->cb, NULL);
-		kfree(cb);
+		kfree_nolock(cb);
 		ret = -EPERM;
 	}
 out:
@@ -1580,7 +1583,7 @@ void bpf_timer_cancel_and_free(void *val)
 	 * timer _before_ calling us, such that failing to cancel it here will
 	 * cause it to possibly use struct hrtimer after freeing bpf_hrtimer.
 	 * Therefore, we _need_ to cancel any outstanding timers before we do
-	 * kfree_rcu, even though no more timers can be armed.
+	 * call_rcu, even though no more timers can be armed.
 	 *
 	 * Moreover, we need to schedule work even if timer does not belong to
 	 * the calling callback_fn, as on two different CPUs, we can end up in a
@@ -1607,7 +1610,7 @@ void bpf_timer_cancel_and_free(void *val)
 		 * completion.
 		 */
 		if (hrtimer_try_to_cancel(&t->timer) >= 0)
-			kfree_rcu(t, cb.rcu);
+			call_rcu(&t->cb.rcu, bpf_async_cb_rcu_free);
 		else
 			queue_work(system_dfl_wq, &t->cb.delete_work);
 	} else {
diff --git a/kernel/bpf/liveness.c b/kernel/bpf/liveness.c
index 3c611aba7f52..1e6538f59a78 100644
--- a/kernel/bpf/liveness.c
+++ b/kernel/bpf/liveness.c
@@ -195,8 +195,10 @@ static struct func_instance *__lookup_instance(struct bpf_verifier_env *env,
 		return ERR_PTR(-ENOMEM);
 	result->must_write_set = kvcalloc(subprog_sz, sizeof(*result->must_write_set),
 					  GFP_KERNEL_ACCOUNT);
-	if (!result->must_write_set)
+	if (!result->must_write_set) {
+		kvfree(result);
 		return ERR_PTR(-ENOMEM);
+	}
 	memcpy(&result->callchain, callchain, sizeof(*callchain));
 	result->insn_cnt = subprog_sz;
 	hash_add(liveness->func_instances, &result->hl_node, key);
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 2a9456a3e730..8a129746bd6c 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -520,6 +520,21 @@ void *bpf_map_kmalloc_node(const struct bpf_map *map, size_t size, gfp_t flags,
 	return ptr;
 }
 
+void *bpf_map_kmalloc_nolock(const struct bpf_map *map, size_t size, gfp_t flags,
+			     int node)
+{
+	struct mem_cgroup *memcg, *old_memcg;
+	void *ptr;
+
+	memcg = bpf_map_get_memcg(map);
+	old_memcg = set_active_memcg(memcg);
+	ptr = kmalloc_nolock(size, flags | __GFP_ACCOUNT, node);
+	set_active_memcg(old_memcg);
+	mem_cgroup_put(memcg);
+
+	return ptr;
+}
+
 void *bpf_map_kzalloc(const struct bpf_map *map, size_t size, gfp_t flags)
 {
 	struct mem_cgroup *memcg, *old_memcg;
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 6ae5f48cf64e..fdee387f0d6b 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -5892,7 +5892,7 @@ static struct cgroup *cgroup_create(struct cgroup *parent, const char *name,
 	 * if the parent has to be frozen, the child has too.
 	 */
 	cgrp->freezer.e_freeze = parent->freezer.e_freeze;
-	seqcount_init(&cgrp->freezer.freeze_seq);
+	seqcount_spinlock_init(&cgrp->freezer.freeze_seq, &css_set_lock);
 	if (cgrp->freezer.e_freeze) {
 		/*
 		 * Set the CGRP_FREEZE flag, so when a process will be
diff --git a/kernel/dma/debug.c b/kernel/dma/debug.c
index 1e5c64cb6a42..138ede653de4 100644
--- a/kernel/dma/debug.c
+++ b/kernel/dma/debug.c
@@ -23,6 +23,7 @@
 #include <linux/ctype.h>
 #include <linux/list.h>
 #include <linux/slab.h>
+#include <linux/swiotlb.h>
 #include <asm/sections.h>
 #include "debug.h"
 
@@ -594,7 +595,9 @@ static void add_dma_entry(struct dma_debug_entry *entry, unsigned long attrs)
 	if (rc == -ENOMEM) {
 		pr_err_once("cacheline tracking ENOMEM, dma-debug disabled\n");
 		global_disable = true;
-	} else if (rc == -EEXIST && !(attrs & DMA_ATTR_SKIP_CPU_SYNC)) {
+	} else if (rc == -EEXIST && !(attrs & DMA_ATTR_SKIP_CPU_SYNC) &&
+		   !(IS_ENABLED(CONFIG_DMA_BOUNCE_UNALIGNED_KMALLOC) &&
+		     is_swiotlb_active(entry->dev))) {
 		err_printk(entry->dev, entry,
 			"cacheline tracking EEXIST, overlapping mappings aren't supported\n");
 	}
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 7541f6f85fcb..177e57c1a362 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -9403,7 +9403,7 @@ static void perf_event_mmap_event(struct perf_mmap_event *mmap_event)
 		flags |= MAP_HUGETLB;
 
 	if (file) {
-		struct inode *inode;
+		const struct inode *inode;
 		dev_t dev;
 
 		buf = kmalloc(PATH_MAX, GFP_KERNEL);
@@ -9416,12 +9416,12 @@ static void perf_event_mmap_event(struct perf_mmap_event *mmap_event)
 		 * need to add enough zero bytes after the string to handle
 		 * the 64bit alignment we do later.
 		 */
-		name = file_path(file, buf, PATH_MAX - sizeof(u64));
+		name = d_path(file_user_path(file), buf, PATH_MAX - sizeof(u64));
 		if (IS_ERR(name)) {
 			name = "//toolong";
 			goto cpy_name;
 		}
-		inode = file_inode(vma->vm_file);
+		inode = file_user_inode(vma->vm_file);
 		dev = inode->i_sb->s_dev;
 		ino = inode->i_ino;
 		gen = inode->i_generation;
@@ -9492,7 +9492,7 @@ static bool perf_addr_filter_match(struct perf_addr_filter *filter,
 	if (!filter->path.dentry)
 		return false;
 
-	if (d_inode(filter->path.dentry) != file_inode(file))
+	if (d_inode(filter->path.dentry) != file_user_inode(file))
 		return false;
 
 	if (filter->offset > offset + size)
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index 8709c69118b5..f11ceb8be8c4 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -2765,6 +2765,9 @@ static void handle_swbp(struct pt_regs *regs)
 
 	handler_chain(uprobe, regs);
 
+	/* Try to optimize after first hit. */
+	arch_uprobe_optimize(&uprobe->arch, bp_vaddr);
+
 	/*
 	 * If user decided to take execution elsewhere, it makes little sense
 	 * to execute the original instruction, so let's skip it.
@@ -2772,9 +2775,6 @@ static void handle_swbp(struct pt_regs *regs)
 	if (instruction_pointer(regs) != bp_vaddr)
 		goto out;
 
-	/* Try to optimize after first hit. */
-	arch_uprobe_optimize(&uprobe->arch, bp_vaddr);
-
 	if (arch_uprobe_skip_sstep(&uprobe->arch, regs))
 		goto out;
 
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index 3ffa0d80ddd1..d1917b28761a 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -1030,7 +1030,7 @@ __irq_do_set_handler(struct irq_desc *desc, irq_flow_handler_t handle,
 void __irq_set_handler(unsigned int irq, irq_flow_handler_t handle, int is_chained,
 		       const char *name)
 {
-	scoped_irqdesc_get_and_lock(irq, 0)
+	scoped_irqdesc_get_and_buslock(irq, 0)
 		__irq_do_set_handler(scoped_irqdesc, handle, is_chained, name);
 }
 EXPORT_SYMBOL_GPL(__irq_set_handler);
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index c94837382037..400856abf672 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -659,7 +659,7 @@ void __disable_irq(struct irq_desc *desc)
 
 static int __disable_irq_nosync(unsigned int irq)
 {
-	scoped_irqdesc_get_and_lock(irq, IRQ_GET_DESC_CHECK_GLOBAL) {
+	scoped_irqdesc_get_and_buslock(irq, IRQ_GET_DESC_CHECK_GLOBAL) {
 		__disable_irq(scoped_irqdesc);
 		return 0;
 	}
@@ -789,7 +789,7 @@ void __enable_irq(struct irq_desc *desc)
  */
 void enable_irq(unsigned int irq)
 {
-	scoped_irqdesc_get_and_lock(irq, IRQ_GET_DESC_CHECK_GLOBAL) {
+	scoped_irqdesc_get_and_buslock(irq, IRQ_GET_DESC_CHECK_GLOBAL) {
 		struct irq_desc *desc = scoped_irqdesc;
 
 		if (WARN(!desc->irq_data.chip, "enable_irq before setup/request_irq: irq %u\n", irq))
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 198d2dd45f59..f1ebf67b48e2 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -8571,10 +8571,12 @@ int sched_cpu_dying(unsigned int cpu)
 	sched_tick_stop(cpu);
 
 	rq_lock_irqsave(rq, &rf);
+	update_rq_clock(rq);
 	if (rq->nr_running != 1 || rq_has_pinned_tasks(rq)) {
 		WARN(true, "Dying CPU not properly vacated!");
 		dump_rq_tasks(rq, KERN_WARNING);
 	}
+	dl_server_stop(&rq->fair_server);
 	rq_unlock_irqrestore(rq, &rf);
 
 	calc_load_migrate(rq);
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 615411a0a881..7b7671060bf9 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -1582,6 +1582,9 @@ void dl_server_start(struct sched_dl_entity *dl_se)
 	if (!dl_server(dl_se) || dl_se->dl_server_active)
 		return;
 
+	if (WARN_ON_ONCE(!cpu_online(cpu_of(rq))))
+		return;
+
 	dl_se->dl_server_active = 1;
 	enqueue_dl_entity(dl_se, ENQUEUE_WAKEUP);
 	if (!dl_task(dl_se->rq->curr) || dl_entity_preempt(dl_se, &rq->curr->dl))
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index bc0b7ce8a65d..25970dbbb279 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -6437,6 +6437,16 @@ static void sync_throttle(struct task_group *tg, int cpu)
 
 	cfs_rq->throttle_count = pcfs_rq->throttle_count;
 	cfs_rq->throttled_clock_pelt = rq_clock_pelt(cpu_rq(cpu));
+
+	/*
+	 * It is not enough to sync the "pelt_clock_throttled" indicator
+	 * with the parent cfs_rq when the hierarchy is not queued.
+	 * Always join a throttled hierarchy with PELT clock throttled
+	 * and leaf it to the first enqueue, or distribution to
+	 * unthrottle the PELT clock.
+	 */
+	if (cfs_rq->throttle_count)
+		cfs_rq->pelt_clock_throttled = 1;
 }
 
 /* conditionally throttle active cfs_rq's from put_prev_entity() */
@@ -8920,21 +8930,21 @@ simple:
 	return p;
 
 idle:
-	if (!rf)
-		return NULL;
-
-	new_tasks = sched_balance_newidle(rq, rf);
+	if (rf) {
+		new_tasks = sched_balance_newidle(rq, rf);
 
-	/*
-	 * Because sched_balance_newidle() releases (and re-acquires) rq->lock, it is
-	 * possible for any higher priority task to appear. In that case we
-	 * must re-start the pick_next_entity() loop.
-	 */
-	if (new_tasks < 0)
-		return RETRY_TASK;
+		/*
+		 * Because sched_balance_newidle() releases (and re-acquires)
+		 * rq->lock, it is possible for any higher priority task to
+		 * appear. In that case we must re-start the pick_next_entity()
+		 * loop.
+		 */
+		if (new_tasks < 0)
+			return RETRY_TASK;
 
-	if (new_tasks > 0)
-		goto again;
+		if (new_tasks > 0)
+			goto again;
+	}
 
 	/*
 	 * rq is about to be idle, check if we need to update the
@@ -13187,6 +13197,8 @@ static void propagate_entity_cfs_rq(struct sched_entity *se)
 		if (!cfs_rq_pelt_clock_throttled(cfs_rq))
 			list_add_leaf_cfs_rq(cfs_rq);
 	}
+
+	assert_list_leaf_cfs_rq(rq_of(cfs_rq));
 }
 #else /* !CONFIG_FAIR_GROUP_SCHED: */
 static void propagate_entity_cfs_rq(struct sched_entity *se) { }
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 1f5d07067f60..361f9101cef9 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -3740,11 +3740,9 @@ static inline int mm_cid_get(struct rq *rq, struct task_struct *t,
 			     struct mm_struct *mm)
 {
 	struct mm_cid __percpu *pcpu_cid = mm->pcpu_cid;
-	struct cpumask *cpumask;
 	int cid;
 
 	lockdep_assert_rq_held(rq);
-	cpumask = mm_cidmask(mm);
 	cid = __this_cpu_read(pcpu_cid->cid);
 	if (mm_cid_is_valid(cid)) {
 		mm_cid_snapshot_time(rq, mm);
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index b6974fce800c..3a4d3b2e3f74 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -3070,7 +3070,7 @@ static int __init tk_aux_sysfs_init(void)
 		return -ENOMEM;
 	}
 
-	for (int i = 0; i <= MAX_AUX_CLOCKS; i++) {
+	for (int i = 0; i < MAX_AUX_CLOCKS; i++) {
 		char id[2] = { [0] = '0' + i, };
 		struct kobject *clk = kobject_create_and_add(id, auxo);
 
diff --git a/kernel/trace/rv/monitors/pagefault/Kconfig b/kernel/trace/rv/monitors/pagefault/Kconfig
index 5e16625f1653..0e013f00c33b 100644
--- a/kernel/trace/rv/monitors/pagefault/Kconfig
+++ b/kernel/trace/rv/monitors/pagefault/Kconfig
@@ -5,6 +5,7 @@ config RV_MON_PAGEFAULT
 	select RV_LTL_MONITOR
 	depends on RV_MON_RTAPP
 	depends on X86 || RISCV
+	depends on MMU
 	default y
 	select LTL_MON_EVENTS_ID
 	bool "pagefault monitor"
diff --git a/kernel/trace/rv/rv.c b/kernel/trace/rv/rv.c
index 48338520376f..43e9ea473cda 100644
--- a/kernel/trace/rv/rv.c
+++ b/kernel/trace/rv/rv.c
@@ -501,7 +501,7 @@ static void *enabled_monitors_next(struct seq_file *m, void *p, loff_t *pos)
 
 	list_for_each_entry_continue(mon, &rv_monitors_list, list) {
 		if (mon->enabled)
-			return mon;
+			return &mon->list;
 	}
 
 	return NULL;
@@ -509,7 +509,7 @@ static void *enabled_monitors_next(struct seq_file *m, void *p, loff_t *pos)
 
 static void *enabled_monitors_start(struct seq_file *m, loff_t *pos)
 {
-	struct rv_monitor *mon;
+	struct list_head *head;
 	loff_t l;
 
 	mutex_lock(&rv_interface_lock);
@@ -517,15 +517,15 @@ static void *enabled_monitors_start(struct seq_file *m, loff_t *pos)
 	if (list_empty(&rv_monitors_list))
 		return NULL;
 
-	mon = list_entry(&rv_monitors_list, struct rv_monitor, list);
+	head = &rv_monitors_list;
 
 	for (l = 0; l <= *pos; ) {
-		mon = enabled_monitors_next(m, mon, &l);
-		if (!mon)
+		head = enabled_monitors_next(m, head, &l);
+		if (!head)
 			break;
 	}
 
-	return mon;
+	return head;
 }
 
 /*