Merge drm/drm-next into drm-misc-next

Backmerging to get v6.2-rc6.

Signed-off-by: Thomas Zimmermann <tzimmermann@suse.de>

30 files changed, 257 insertions, 120 deletions

diff --git a/kernel/bpf/bpf_lsm.c b/kernel/bpf/bpf_lsm.c
index 9ea42a45da47..a4a41ee3e80b 100644
--- a/kernel/bpf/bpf_lsm.c
+++ b/kernel/bpf/bpf_lsm.c
@@ -351,8 +351,10 @@ BTF_ID(func, bpf_lsm_bpf_prog_alloc_security)
 BTF_ID(func, bpf_lsm_bpf_prog_free_security)
 BTF_ID(func, bpf_lsm_file_alloc_security)
 BTF_ID(func, bpf_lsm_file_free_security)
+#ifdef CONFIG_SECURITY_NETWORK
 BTF_ID(func, bpf_lsm_sk_alloc_security)
 BTF_ID(func, bpf_lsm_sk_free_security)
+#endif /* CONFIG_SECURITY_NETWORK */
 BTF_ID(func, bpf_lsm_task_free)
 BTF_SET_END(untrusted_lsm_hooks)
 
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index 5aa2b5525f79..66bded144377 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -152,7 +152,7 @@ static inline int htab_lock_bucket(const struct bpf_htab *htab,
 {
 	unsigned long flags;
 
-	hash = hash & HASHTAB_MAP_LOCK_MASK;
+	hash = hash & min_t(u32, HASHTAB_MAP_LOCK_MASK, htab->n_buckets - 1);
 
 	preempt_disable();
 	if (unlikely(__this_cpu_inc_return(*(htab->map_locked[hash])) != 1)) {
@@ -171,7 +171,7 @@ static inline void htab_unlock_bucket(const struct bpf_htab *htab,
 				      struct bucket *b, u32 hash,
 				      unsigned long flags)
 {
-	hash = hash & HASHTAB_MAP_LOCK_MASK;
+	hash = hash & min_t(u32, HASHTAB_MAP_LOCK_MASK, htab->n_buckets - 1);
 	raw_spin_unlock_irqrestore(&b->raw_lock, flags);
 	__this_cpu_dec(*(htab->map_locked[hash]));
 	preempt_enable();
diff --git a/kernel/bpf/offload.c b/kernel/bpf/offload.c
index 13e4efc971e6..190d9f9dc987 100644
--- a/kernel/bpf/offload.c
+++ b/kernel/bpf/offload.c
@@ -216,9 +216,6 @@ static void __bpf_prog_offload_destroy(struct bpf_prog *prog)
 	if (offload->dev_state)
 		offload->offdev->ops->destroy(prog);
 
-	/* Make sure BPF_PROG_GET_NEXT_ID can't find this dead program */
-	bpf_prog_free_id(prog, true);
-
 	list_del_init(&offload->offloads);
 	kfree(offload);
 	prog->aux->offload = NULL;
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 64131f88c553..ecca9366c7a6 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -1972,7 +1972,7 @@ static void bpf_audit_prog(const struct bpf_prog *prog, unsigned int op)
 		return;
 	if (audit_enabled == AUDIT_OFF)
 		return;
-	if (op == BPF_AUDIT_LOAD)
+	if (!in_irq() && !irqs_disabled())
 		ctx = audit_context();
 	ab = audit_log_start(ctx, GFP_ATOMIC, AUDIT_BPF);
 	if (unlikely(!ab))
@@ -2001,7 +2001,7 @@ static int bpf_prog_alloc_id(struct bpf_prog *prog)
 	return id > 0 ? 0 : id;
 }
 
-void bpf_prog_free_id(struct bpf_prog *prog, bool do_idr_lock)
+void bpf_prog_free_id(struct bpf_prog *prog)
 {
 	unsigned long flags;
 
@@ -2013,18 +2013,10 @@ void bpf_prog_free_id(struct bpf_prog *prog, bool do_idr_lock)
 	if (!prog->aux->id)
 		return;
 
-	if (do_idr_lock)
-		spin_lock_irqsave(&prog_idr_lock, flags);
-	else
-		__acquire(&prog_idr_lock);
-
+	spin_lock_irqsave(&prog_idr_lock, flags);
 	idr_remove(&prog_idr, prog->aux->id);
 	prog->aux->id = 0;
-
-	if (do_idr_lock)
-		spin_unlock_irqrestore(&prog_idr_lock, flags);
-	else
-		__release(&prog_idr_lock);
+	spin_unlock_irqrestore(&prog_idr_lock, flags);
 }
 
 static void __bpf_prog_put_rcu(struct rcu_head *rcu)
@@ -2067,17 +2059,15 @@ static void bpf_prog_put_deferred(struct work_struct *work)
 	prog = aux->prog;
 	perf_event_bpf_event(prog, PERF_BPF_EVENT_PROG_UNLOAD, 0);
 	bpf_audit_prog(prog, BPF_AUDIT_UNLOAD);
+	bpf_prog_free_id(prog);
 	__bpf_prog_put_noref(prog, true);
 }
 
-static void __bpf_prog_put(struct bpf_prog *prog, bool do_idr_lock)
+static void __bpf_prog_put(struct bpf_prog *prog)
 {
 	struct bpf_prog_aux *aux = prog->aux;
 
 	if (atomic64_dec_and_test(&aux->refcnt)) {
-		/* bpf_prog_free_id() must be called first */
-		bpf_prog_free_id(prog, do_idr_lock);
-
 		if (in_irq() || irqs_disabled()) {
 			INIT_WORK(&aux->work, bpf_prog_put_deferred);
 			schedule_work(&aux->work);
@@ -2089,7 +2079,7 @@ static void __bpf_prog_put(struct bpf_prog *prog, bool do_idr_lock)
 
 void bpf_prog_put(struct bpf_prog *prog)
 {
-	__bpf_prog_put(prog, true);
+	__bpf_prog_put(prog);
 }
 EXPORT_SYMBOL_GPL(bpf_prog_put);
 
diff --git a/kernel/bpf/task_iter.c b/kernel/bpf/task_iter.c
index c2a2182ce570..c4ab9d6cdbe9 100644
--- a/kernel/bpf/task_iter.c
+++ b/kernel/bpf/task_iter.c
@@ -438,6 +438,7 @@ struct bpf_iter_seq_task_vma_info {
 	 */
 	struct bpf_iter_seq_task_common common;
 	struct task_struct *task;
+	struct mm_struct *mm;
 	struct vm_area_struct *vma;
 	u32 tid;
 	unsigned long prev_vm_start;
@@ -456,16 +457,19 @@ task_vma_seq_get_next(struct bpf_iter_seq_task_vma_info *info)
 	enum bpf_task_vma_iter_find_op op;
 	struct vm_area_struct *curr_vma;
 	struct task_struct *curr_task;
+	struct mm_struct *curr_mm;
 	u32 saved_tid = info->tid;
 
 	/* If this function returns a non-NULL vma, it holds a reference to
-	 * the task_struct, and holds read lock on vma->mm->mmap_lock.
+	 * the task_struct, holds a refcount on mm->mm_users, and holds
+	 * read lock on vma->mm->mmap_lock.
 	 * If this function returns NULL, it does not hold any reference or
 	 * lock.
 	 */
 	if (info->task) {
 		curr_task = info->task;
 		curr_vma = info->vma;
+		curr_mm = info->mm;
 		/* In case of lock contention, drop mmap_lock to unblock
 		 * the writer.
 		 *
@@ -504,13 +508,15 @@ task_vma_seq_get_next(struct bpf_iter_seq_task_vma_info *info)
 		 *    4.2) VMA2 and VMA2' covers different ranges, process
 		 *         VMA2'.
 		 */
-		if (mmap_lock_is_contended(curr_task->mm)) {
+		if (mmap_lock_is_contended(curr_mm)) {
 			info->prev_vm_start = curr_vma->vm_start;
 			info->prev_vm_end = curr_vma->vm_end;
 			op = task_vma_iter_find_vma;
-			mmap_read_unlock(curr_task->mm);
-			if (mmap_read_lock_killable(curr_task->mm))
+			mmap_read_unlock(curr_mm);
+			if (mmap_read_lock_killable(curr_mm)) {
+				mmput(curr_mm);
 				goto finish;
+			}
 		} else {
 			op = task_vma_iter_next_vma;
 		}
@@ -535,42 +541,47 @@ again:
 			op = task_vma_iter_find_vma;
 		}
 
-		if (!curr_task->mm)
+		curr_mm = get_task_mm(curr_task);
+		if (!curr_mm)
 			goto next_task;
 
-		if (mmap_read_lock_killable(curr_task->mm))
+		if (mmap_read_lock_killable(curr_mm)) {
+			mmput(curr_mm);
 			goto finish;
+		}
 	}
 
 	switch (op) {
 	case task_vma_iter_first_vma:
-		curr_vma = find_vma(curr_task->mm, 0);
+		curr_vma = find_vma(curr_mm, 0);
 		break;
 	case task_vma_iter_next_vma:
-		curr_vma = find_vma(curr_task->mm, curr_vma->vm_end);
+		curr_vma = find_vma(curr_mm, curr_vma->vm_end);
 		break;
 	case task_vma_iter_find_vma:
 		/* We dropped mmap_lock so it is necessary to use find_vma
 		 * to find the next vma. This is similar to the  mechanism
 		 * in show_smaps_rollup().
 		 */
-		curr_vma = find_vma(curr_task->mm, info->prev_vm_end - 1);
+		curr_vma = find_vma(curr_mm, info->prev_vm_end - 1);
 		/* case 1) and 4.2) above just use curr_vma */
 
 		/* check for case 2) or case 4.1) above */
 		if (curr_vma &&
 		    curr_vma->vm_start == info->prev_vm_start &&
 		    curr_vma->vm_end == info->prev_vm_end)
-			curr_vma = find_vma(curr_task->mm, curr_vma->vm_end);
+			curr_vma = find_vma(curr_mm, curr_vma->vm_end);
 		break;
 	}
 	if (!curr_vma) {
 		/* case 3) above, or case 2) 4.1) with vma->next == NULL */
-		mmap_read_unlock(curr_task->mm);
+		mmap_read_unlock(curr_mm);
+		mmput(curr_mm);
 		goto next_task;
 	}
 	info->task = curr_task;
 	info->vma = curr_vma;
+	info->mm = curr_mm;
 	return curr_vma;
 
 next_task:
@@ -579,6 +590,7 @@ next_task:
 
 	put_task_struct(curr_task);
 	info->task = NULL;
+	info->mm = NULL;
 	info->tid++;
 	goto again;
 
@@ -587,6 +599,7 @@ finish:
 		put_task_struct(curr_task);
 	info->task = NULL;
 	info->vma = NULL;
+	info->mm = NULL;
 	return NULL;
 }
 
@@ -658,7 +671,9 @@ static void task_vma_seq_stop(struct seq_file *seq, void *v)
 		 */
 		info->prev_vm_start = ~0UL;
 		info->prev_vm_end = info->vma->vm_end;
-		mmap_read_unlock(info->task->mm);
+		mmap_read_unlock(info->mm);
+		mmput(info->mm);
+		info->mm = NULL;
 		put_task_struct(info->task);
 		info->task = NULL;
 	}
diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c
index 11f5ec0b8016..d0ed7d6f5eec 100644
--- a/kernel/bpf/trampoline.c
+++ b/kernel/bpf/trampoline.c
@@ -488,6 +488,10 @@ again:
 		/* reset fops->func and fops->trampoline for re-register */
 		tr->fops->func = NULL;
 		tr->fops->trampoline = 0;
+
+		/* reset im->image memory attr for arch_prepare_bpf_trampoline */
+		set_memory_nx((long)im->image, 1);
+		set_memory_rw((long)im->image, 1);
 		goto again;
 	}
 #endif
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index a5255a0dcbb6..dbef0b0967ae 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -1054,6 +1054,8 @@ static void print_insn_state(struct bpf_verifier_env *env,
  */
 static void *copy_array(void *dst, const void *src, size_t n, size_t size, gfp_t flags)
 {
+	size_t alloc_bytes;
+	void *orig = dst;
 	size_t bytes;
 
 	if (ZERO_OR_NULL_PTR(src))
@@ -1062,11 +1064,11 @@ static void *copy_array(void *dst, const void *src, size_t n, size_t size, gfp_t
 	if (unlikely(check_mul_overflow(n, size, &bytes)))
 		return NULL;
 
-	if (ksize(dst) < ksize(src)) {
-		kfree(dst);
-		dst = kmalloc_track_caller(kmalloc_size_roundup(bytes), flags);
-		if (!dst)
-			return NULL;
+	alloc_bytes = max(ksize(orig), kmalloc_size_roundup(bytes));
+	dst = krealloc(orig, alloc_bytes, flags);
+	if (!dst) {
+		kfree(orig);
+		return NULL;
 	}
 
 	memcpy(dst, src, bytes);
@@ -2746,6 +2748,12 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx,
 			 */
 			if (insn->src_reg == 0 && is_callback_calling_function(insn->imm))
 				return -ENOTSUPP;
+			/* kfunc with imm==0 is invalid and fixup_kfunc_call will
+			 * catch this error later. Make backtracking conservative
+			 * with ENOTSUPP.
+			 */
+			if (insn->src_reg == BPF_PSEUDO_KFUNC_CALL && insn->imm == 0)
+				return -ENOTSUPP;
 			/* regular helper call sets R0 */
 			*reg_mask &= ~1;
 			if (*reg_mask & 0x3f) {
@@ -3287,7 +3295,9 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env,
 		bool sanitize = reg && is_spillable_regtype(reg->type);
 
 		for (i = 0; i < size; i++) {
-			if (state->stack[spi].slot_type[i] == STACK_INVALID) {
+			u8 type = state->stack[spi].slot_type[i];
+
+			if (type != STACK_MISC && type != STACK_ZERO) {
 				sanitize = true;
 				break;
 			}
@@ -11822,10 +11832,17 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env,
 	 *      register B - not null
 	 * for JNE A, B, ... - A is not null in the false branch;
 	 * for JEQ A, B, ... - A is not null in the true branch.
+	 *
+	 * Since PTR_TO_BTF_ID points to a kernel struct that does
+	 * not need to be null checked by the BPF program, i.e.,
+	 * could be null even without PTR_MAYBE_NULL marking, so
+	 * only propagate nullness when neither reg is that type.
 	 */
 	if (!is_jmp32 && BPF_SRC(insn->code) == BPF_X &&
 	    __is_pointer_value(false, src_reg) && __is_pointer_value(false, dst_reg) &&
-	    type_may_be_null(src_reg->type) != type_may_be_null(dst_reg->type)) {
+	    type_may_be_null(src_reg->type) != type_may_be_null(dst_reg->type) &&
+	    base_type(src_reg->type) != PTR_TO_BTF_ID &&
+	    base_type(dst_reg->type) != PTR_TO_BTF_ID) {
 		eq_branch_regs = NULL;
 		switch (opcode) {
 		case BPF_JEQ:
diff --git a/kernel/gen_kheaders.sh b/kernel/gen_kheaders.sh
index 473036b43c83..81b97f0f6556 100755
--- a/kernel/gen_kheaders.sh
+++ b/kernel/gen_kheaders.sh
@@ -14,6 +14,8 @@ include/
 arch/$SRCARCH/include/
 "
 
+type cpio > /dev/null
+
 # Support incremental builds by skipping archive generation
 # if timestamps of files being archived are not changed.
 
diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c
index 8fe1da9614ee..5c3fb6168eef 100644
--- a/kernel/irq/irqdomain.c
+++ b/kernel/irq/irqdomain.c
@@ -114,7 +114,7 @@ void irq_domain_free_fwnode(struct fwnode_handle *fwnode)
 {
 	struct irqchip_fwid *fwid;
 
-	if (WARN_ON(!is_fwnode_irqchip(fwnode)))
+	if (!fwnode || WARN_ON(!is_fwnode_irqchip(fwnode)))
 		return;
 
 	fwid = container_of(fwnode, struct irqchip_fwid, fwnode);
diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c
index 955267bbc2be..783a3e6a0b10 100644
--- a/kernel/irq/msi.c
+++ b/kernel/irq/msi.c
@@ -1000,7 +1000,7 @@ bool msi_create_device_irq_domain(struct device *dev, unsigned int domid,
 fail:
 	msi_unlock_descs(dev);
 free_fwnode:
-	kfree(fwnode);
+	irq_domain_free_fwnode(fwnode);
 free_bundle:
 	kfree(bundle);
 	return false;
@@ -1013,6 +1013,7 @@ free_bundle:
  */
 void msi_remove_device_irq_domain(struct device *dev, unsigned int domid)
 {
+	struct fwnode_handle *fwnode = NULL;
 	struct msi_domain_info *info;
 	struct irq_domain *domain;
 
@@ -1025,7 +1026,10 @@ void msi_remove_device_irq_domain(struct device *dev, unsigned int domid)
 
 	dev->msi.data->__domains[domid].domain = NULL;
 	info = domain->host_data;
+	if (irq_domain_is_msi_device(domain))
+		fwnode = domain->fwnode;
 	irq_domain_remove(domain);
+	irq_domain_free_fwnode(fwnode);
 	kfree(container_of(info, struct msi_domain_template, info));
 
 unlock:
diff --git a/kernel/kallsyms_selftest.c b/kernel/kallsyms_selftest.c
index f35d9cc1aab1..bfbc12da3326 100644
--- a/kernel/kallsyms_selftest.c
+++ b/kernel/kallsyms_selftest.c
@@ -157,14 +157,11 @@ static void test_kallsyms_compression_ratio(void)
 static int lookup_name(void *data, const char *name, struct module *mod, unsigned long addr)
 {
 	u64 t0, t1, t;
-	unsigned long flags;
 	struct test_stat *stat = (struct test_stat *)data;
 
-	local_irq_save(flags);
-	t0 = sched_clock();
+	t0 = ktime_get_ns();
 	(void)kallsyms_lookup_name(name);
-	t1 = sched_clock();
-	local_irq_restore(flags);
+	t1 = ktime_get_ns();
 
 	t = t1 - t0;
 	if (t < stat->min)
@@ -234,18 +231,15 @@ static int find_symbol(void *data, const char *name, struct module *mod, unsigne
 static void test_perf_kallsyms_on_each_symbol(void)
 {
 	u64 t0, t1;
-	unsigned long flags;
 	struct test_stat stat;
 
 	memset(&stat, 0, sizeof(stat));
 	stat.max = INT_MAX;
 	stat.name = stub_name;
 	stat.perf = 1;
-	local_irq_save(flags);
-	t0 = sched_clock();
+	t0 = ktime_get_ns();
 	kallsyms_on_each_symbol(find_symbol, &stat);
-	t1 = sched_clock();
-	local_irq_restore(flags);
+	t1 = ktime_get_ns();
 	pr_info("kallsyms_on_each_symbol() traverse all: %lld ns\n", t1 - t0);
 }
 
@@ -270,17 +264,14 @@ static int match_symbol(void *data, unsigned long addr)
 static void test_perf_kallsyms_on_each_match_symbol(void)
 {
 	u64 t0, t1;
-	unsigned long flags;
 	struct test_stat stat;
 
 	memset(&stat, 0, sizeof(stat));
 	stat.max = INT_MAX;
 	stat.name = stub_name;
-	local_irq_save(flags);
-	t0 = sched_clock();
+	t0 = ktime_get_ns();
 	kallsyms_on_each_match_symbol(match_symbol, stat.name, &stat);
-	t1 = sched_clock();
-	local_irq_restore(flags);
+	t1 = ktime_get_ns();
 	pr_info("kallsyms_on_each_match_symbol() traverse all: %lld ns\n", t1 - t0);
 }
 
diff --git a/kernel/kcsan/kcsan_test.c b/kernel/kcsan/kcsan_test.c
index dcec1b743c69..a60c561724be 100644
--- a/kernel/kcsan/kcsan_test.c
+++ b/kernel/kcsan/kcsan_test.c
@@ -159,7 +159,7 @@ static bool __report_matches(const struct expect_report *r)
 	const bool is_assert = (r->access[0].type | r->access[1].type) & KCSAN_ACCESS_ASSERT;
 	bool ret = false;
 	unsigned long flags;
-	typeof(observed.lines) expect;
+	typeof(*observed.lines) *expect;
 	const char *end;
 	char *cur;
 	int i;
@@ -168,6 +168,10 @@ static bool __report_matches(const struct expect_report *r)
 	if (!report_available())
 		return false;
 
+	expect = kmalloc(sizeof(observed.lines), GFP_KERNEL);
+	if (WARN_ON(!expect))
+		return false;
+
 	/* Generate expected report contents. */
 
 	/* Title */
@@ -253,6 +257,7 @@ static bool __report_matches(const struct expect_report *r)
 		strstr(observed.lines[2], expect[1])));
 out:
 	spin_unlock_irqrestore(&observed.lock, flags);
+	kfree(expect);
 	return ret;
 }
 
diff --git a/kernel/module/main.c b/kernel/module/main.c
index 48568a0f5651..4ac3fe43e6c8 100644
--- a/kernel/module/main.c
+++ b/kernel/module/main.c
@@ -2393,7 +2393,8 @@ static bool finished_loading(const char *name)
 	sched_annotate_sleep();
 	mutex_lock(&module_mutex);
 	mod = find_module_all(name, strlen(name), true);
-	ret = !mod || mod->state == MODULE_STATE_LIVE;
+	ret = !mod || mod->state == MODULE_STATE_LIVE
+		|| mod->state == MODULE_STATE_GOING;
 	mutex_unlock(&module_mutex);
 
 	return ret;
@@ -2569,20 +2570,35 @@ static int add_unformed_module(struct module *mod)
 
 	mod->state = MODULE_STATE_UNFORMED;
 
-again:
 	mutex_lock(&module_mutex);
 	old = find_module_all(mod->name, strlen(mod->name), true);
 	if (old != NULL) {
-		if (old->state != MODULE_STATE_LIVE) {
+		if (old->state == MODULE_STATE_COMING
+		    || old->state == MODULE_STATE_UNFORMED) {
 			/* Wait in case it fails to load. */
 			mutex_unlock(&module_mutex);
 			err = wait_event_interruptible(module_wq,
 					       finished_loading(mod->name));
 			if (err)
 				goto out_unlocked;
-			goto again;
+
+			/* The module might have gone in the meantime. */
+			mutex_lock(&module_mutex);
+			old = find_module_all(mod->name, strlen(mod->name),
+					      true);
 		}
-		err = -EEXIST;
+
+		/*
+		 * We are here only when the same module was being loaded. Do
+		 * not try to load it again right now. It prevents long delays
+		 * caused by serialized module load failures. It might happen
+		 * when more devices of the same type trigger load of
+		 * a particular module.
+		 */
+		if (old && old->state == MODULE_STATE_LIVE)
+			err = -EEXIST;
+		else
+			err = -EBUSY;
 		goto out;
 	}
 	mod_update_bounds(mod);
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index 7decf1e9c486..a5ed2e53547c 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -123,6 +123,7 @@ bool console_srcu_read_lock_is_held(void)
 {
 	return srcu_read_lock_held(&console_srcu);
 }
+EXPORT_SYMBOL(console_srcu_read_lock_is_held);
 #endif
 
 enum devkmsg_log_bits {
@@ -1891,6 +1892,7 @@ static void console_lock_spinning_enable(void)
 /**
  * console_lock_spinning_disable_and_check - mark end of code where another
  *	thread was able to busy wait and check if there is a waiter
+ * @cookie: cookie returned from console_srcu_read_lock()
  *
  * This is called at the end of the section where spinning is allowed.
  * It has two functions. First, it is a signal that it is no longer
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 25b582b6ee5f..e838feb6adc5 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2604,27 +2604,71 @@ void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask)
 		.user_mask = NULL,
 		.flags     = SCA_USER,	/* clear the user requested mask */
 	};
+	union cpumask_rcuhead {
+		cpumask_t cpumask;
+		struct rcu_head rcu;
+	};
 
 	__do_set_cpus_allowed(p, &ac);
-	kfree(ac.user_mask);
+
+	/*
+	 * Because this is called with p->pi_lock held, it is not possible
+	 * to use kfree() here (when PREEMPT_RT=y), therefore punt to using
+	 * kfree_rcu().
+	 */
+	kfree_rcu((union cpumask_rcuhead *)ac.user_mask, rcu);
+}
+
+static cpumask_t *alloc_user_cpus_ptr(int node)
+{
+	/*
+	 * See do_set_cpus_allowed() above for the rcu_head usage.
+	 */
+	int size = max_t(int, cpumask_size(), sizeof(struct rcu_head));
+
+	return kmalloc_node(size, GFP_KERNEL, node);
 }
 
 int dup_user_cpus_ptr(struct task_struct *dst, struct task_struct *src,
 		      int node)
 {
+	cpumask_t *user_mask;
 	unsigned long flags;
 
-	if (!src->user_cpus_ptr)
+	/*
+	 * Always clear dst->user_cpus_ptr first as their user_cpus_ptr's
+	 * may differ by now due to racing.
+	 */
+	dst->user_cpus_ptr = NULL;
+
+	/*
+	 * This check is racy and losing the race is a valid situation.
+	 * It is not worth the extra overhead of taking the pi_lock on
+	 * every fork/clone.
+	 */
+	if (data_race(!src->user_cpus_ptr))
 		return 0;
 
-	dst->user_cpus_ptr = kmalloc_node(cpumask_size(), GFP_KERNEL, node);
-	if (!dst->user_cpus_ptr)
+	user_mask = alloc_user_cpus_ptr(node);
+	if (!user_mask)
 		return -ENOMEM;
 
-	/* Use pi_lock to protect content of user_cpus_ptr */
+	/*
+	 * Use pi_lock to protect content of user_cpus_ptr
+	 *
+	 * Though unlikely, user_cpus_ptr can be reset to NULL by a concurrent
+	 * do_set_cpus_allowed().
+	 */
 	raw_spin_lock_irqsave(&src->pi_lock, flags);
-	cpumask_copy(dst->user_cpus_ptr, src->user_cpus_ptr);
+	if (src->user_cpus_ptr) {
+		swap(dst->user_cpus_ptr, user_mask);
+		cpumask_copy(dst->user_cpus_ptr, src->user_cpus_ptr);
+	}
 	raw_spin_unlock_irqrestore(&src->pi_lock, flags);
+
+	if (unlikely(user_mask))
+		kfree(user_mask);
+
 	return 0;
 }
 
@@ -3581,6 +3625,11 @@ static inline bool rq_has_pinned_tasks(struct rq *rq)
 	return false;
 }
 
+static inline cpumask_t *alloc_user_cpus_ptr(int node)
+{
+	return NULL;
+}
+
 #endif /* !CONFIG_SMP */
 
 static void
@@ -5504,7 +5553,9 @@ void scheduler_tick(void)
 	unsigned long thermal_pressure;
 	u64 resched_latency;
 
-	arch_scale_freq_tick();
+	if (housekeeping_cpu(cpu, HK_TYPE_TICK))
+		arch_scale_freq_tick();
+
 	sched_clock_tick();
 
 	rq_lock(rq, &rf);
@@ -8239,12 +8290,18 @@ long sched_setaffinity(pid_t pid, const struct cpumask *in_mask)
 	if (retval)
 		goto out_put_task;
 
-	user_mask = kmalloc(cpumask_size(), GFP_KERNEL);
-	if (!user_mask) {
+	/*
+	 * With non-SMP configs, user_cpus_ptr/user_mask isn't used and
+	 * alloc_user_cpus_ptr() returns NULL.
+	 */
+	user_mask = alloc_user_cpus_ptr(NUMA_NO_NODE);
+	if (user_mask) {
+		cpumask_copy(user_mask, in_mask);
+	} else if (IS_ENABLED(CONFIG_SMP)) {
 		retval = -ENOMEM;
 		goto out_put_task;
 	}
-	cpumask_copy(user_mask, in_mask);
+
 	ac = (struct affinity_context){
 		.new_mask  = in_mask,
 		.user_mask = user_mask,
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index c36aa54ae071..0f8736991427 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -7229,10 +7229,10 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu)
 	eenv_task_busy_time(&eenv, p, prev_cpu);
 
 	for (; pd; pd = pd->next) {
+		unsigned long util_min = p_util_min, util_max = p_util_max;
 		unsigned long cpu_cap, cpu_thermal_cap, util;
 		unsigned long cur_delta, max_spare_cap = 0;
 		unsigned long rq_util_min, rq_util_max;
-		unsigned long util_min, util_max;
 		unsigned long prev_spare_cap = 0;
 		int max_spare_cap_cpu = -1;
 		unsigned long base_energy;
@@ -7251,6 +7251,8 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu)
 		eenv.pd_cap = 0;
 
 		for_each_cpu(cpu, cpus) {
+			struct rq *rq = cpu_rq(cpu);
+
 			eenv.pd_cap += cpu_thermal_cap;
 
 			if (!cpumask_test_cpu(cpu, sched_domain_span(sd)))
@@ -7269,24 +7271,19 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu)
 			 * much capacity we can get out of the CPU; this is
 			 * aligned with sched_cpu_util().
 			 */
-			if (uclamp_is_used()) {
-				if (uclamp_rq_is_idle(cpu_rq(cpu))) {
-					util_min = p_util_min;
-					util_max = p_util_max;
-				} else {
-					/*
-					 * Open code uclamp_rq_util_with() except for
-					 * the clamp() part. Ie: apply max aggregation
-					 * only. util_fits_cpu() logic requires to
-					 * operate on non clamped util but must use the
-					 * max-aggregated uclamp_{min, max}.
-					 */
-					rq_util_min = uclamp_rq_get(cpu_rq(cpu), UCLAMP_MIN);
-					rq_util_max = uclamp_rq_get(cpu_rq(cpu), UCLAMP_MAX);
-
-					util_min = max(rq_util_min, p_util_min);
-					util_max = max(rq_util_max, p_util_max);
-				}
+			if (uclamp_is_used() && !uclamp_rq_is_idle(rq)) {
+				/*
+				 * Open code uclamp_rq_util_with() except for
+				 * the clamp() part. Ie: apply max aggregation
+				 * only. util_fits_cpu() logic requires to
+				 * operate on non clamped util but must use the
+				 * max-aggregated uclamp_{min, max}.
+				 */
+				rq_util_min = uclamp_rq_get(rq, UCLAMP_MIN);
+				rq_util_max = uclamp_rq_get(rq, UCLAMP_MAX);
+
+				util_min = max(rq_util_min, p_util_min);
+				util_max = max(rq_util_max, p_util_max);
 			}
 			if (!util_fits_cpu(util, util_min, util_max, cpu))
 				continue;
@@ -8871,16 +8868,23 @@ static void update_cpu_capacity(struct sched_domain *sd, int cpu)
 	 *   * Thermal pressure will impact all cpus in this perf domain
 	 *     equally.
 	 */
-	if (static_branch_unlikely(&sched_asym_cpucapacity)) {
+	if (sched_energy_enabled()) {
 		unsigned long inv_cap = capacity_orig - thermal_load_avg(rq);
-		struct perf_domain *pd = rcu_dereference(rq->rd->pd);
+		struct perf_domain *pd;
 
+		rcu_read_lock();
+
+		pd = rcu_dereference(rq->rd->pd);
 		rq->cpu_capacity_inverted = 0;
 
 		for (; pd; pd = pd->next) {
 			struct cpumask *pd_span = perf_domain_span(pd);
 			unsigned long pd_cap_orig, pd_cap;
 
+			/* We can't be inverted against our own pd */
+			if (cpumask_test_cpu(cpu_of(rq), pd_span))
+				continue;
+
 			cpu = cpumask_any(pd_span);
 			pd_cap_orig = arch_scale_cpu_capacity(cpu);
 
@@ -8905,6 +8909,8 @@ static void update_cpu_capacity(struct sched_domain *sd, int cpu)
 				break;
 			}
 		}
+
+		rcu_read_unlock();
 	}
 
 	trace_sched_cpu_capacity_tp(rq);
diff --git a/kernel/sys.c b/kernel/sys.c
index 5fd54bf0e886..88b31f096fb2 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -1442,6 +1442,8 @@ static int do_prlimit(struct task_struct *tsk, unsigned int resource,
 
 	if (resource >= RLIM_NLIMITS)
 		return -EINVAL;
+	resource = array_index_nospec(resource, RLIM_NLIMITS);
+
 	if (new_rlim) {
 		if (new_rlim->rlim_cur > new_rlim->rlim_max)
 			return -EINVAL;
diff --git a/kernel/time/tick-oneshot.c b/kernel/time/tick-oneshot.c
index 475ecceda768..5e2c2c26b3cc 100644
--- a/kernel/time/tick-oneshot.c
+++ b/kernel/time/tick-oneshot.c
@@ -18,7 +18,7 @@
 #include "tick-internal.h"
 
 /**
- * tick_program_event
+ * tick_program_event - program the CPU local timer device for the next event
  */
 int tick_program_event(ktime_t expires, int force)
 {
@@ -99,7 +99,7 @@ int tick_switch_to_oneshot(void (*handler)(struct clock_event_device *))
 }
 
 /**
- * tick_check_oneshot_mode - check whether the system is in oneshot mode
+ * tick_oneshot_mode_active - check whether the system is in oneshot mode
  *
  * returns 1 when either nohz or highres are enabled. otherwise 0.
  */
diff --git a/kernel/time/time.c b/kernel/time/time.c
index 526257b3727c..f4198af60fee 100644
--- a/kernel/time/time.c
+++ b/kernel/time/time.c
@@ -462,7 +462,7 @@ struct __kernel_old_timeval ns_to_kernel_old_timeval(s64 nsec)
 EXPORT_SYMBOL(ns_to_kernel_old_timeval);
 
 /**
- * set_normalized_timespec - set timespec sec and nsec parts and normalize
+ * set_normalized_timespec64 - set timespec sec and nsec parts and normalize
  *
  * @ts:		pointer to timespec variable to be set
  * @sec:	seconds to set
@@ -526,7 +526,7 @@ struct timespec64 ns_to_timespec64(s64 nsec)
 EXPORT_SYMBOL(ns_to_timespec64);
 
 /**
- * msecs_to_jiffies: - convert milliseconds to jiffies
+ * __msecs_to_jiffies: - convert milliseconds to jiffies
  * @m:	time in milliseconds
  *
  * conversion is done as follows:
@@ -541,12 +541,12 @@ EXPORT_SYMBOL(ns_to_timespec64);
  *   handling any 32-bit overflows.
  *   for the details see __msecs_to_jiffies()
  *
- * msecs_to_jiffies() checks for the passed in value being a constant
+ * __msecs_to_jiffies() checks for the passed in value being a constant
  * via __builtin_constant_p() allowing gcc to eliminate most of the
  * code, __msecs_to_jiffies() is called if the value passed does not
  * allow constant folding and the actual conversion must be done at
  * runtime.
- * the _msecs_to_jiffies helpers are the HZ dependent conversion
+ * The _msecs_to_jiffies helpers are the HZ dependent conversion
  * routines found in include/linux/jiffies.h
  */
 unsigned long __msecs_to_jiffies(const unsigned int m)
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index f72b9f1de178..5579ead449f2 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -1590,10 +1590,10 @@ void __weak read_persistent_clock64(struct timespec64 *ts)
 /**
  * read_persistent_wall_and_boot_offset - Read persistent clock, and also offset
  *                                        from the boot.
+ * @wall_time:	  current time as returned by persistent clock
+ * @boot_offset:  offset that is defined as wall_time - boot_time
  *
  * Weak dummy function for arches that do not yet support it.
- * @wall_time:	- current time as returned by persistent clock
- * @boot_offset: - offset that is defined as wall_time - boot_time
  *
  * The default function calculates offset based on the current value of
  * local_clock(). This way architectures that support sched_clock() but don't
@@ -1701,7 +1701,7 @@ static void __timekeeping_inject_sleeptime(struct timekeeper *tk,
 }
 
 #if defined(CONFIG_PM_SLEEP) && defined(CONFIG_RTC_HCTOSYS_DEVICE)
-/**
+/*
  * We have three kinds of time sources to use for sleep time
  * injection, the preference order is:
  * 1) non-stop clocksource
@@ -1722,7 +1722,7 @@ bool timekeeping_rtc_skipresume(void)
 	return !suspend_timing_needed;
 }
 
-/**
+/*
  * 1) can be determined whether to use or not only when doing
  * timekeeping_resume() which is invoked after rtc_suspend(),
  * so we can't skip rtc_suspend() surely if system has 1).
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 197545241ab8..d7043043f59c 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -933,8 +933,8 @@ config RING_BUFFER_RECORD_RECURSION
 	default y
 	help
 	  The ring buffer has its own internal recursion. Although when
-	  recursion happens it wont cause harm because of the protection,
-	  but it does cause an unwanted overhead. Enabling this option will
+	  recursion happens it won't cause harm because of the protection,
+	  but it does cause unwanted overhead. Enabling this option will
 	  place where recursion was detected into the ftrace "recursed_functions"
 	  file.
 
@@ -1017,8 +1017,8 @@ config RING_BUFFER_STARTUP_TEST
 	 The test runs for 10 seconds. This will slow your boot time
 	 by at least 10 more seconds.
 
-	 At the end of the test, statics and more checks are done.
-	 It will output the stats of each per cpu buffer. What
+	 At the end of the test, statistics and more checks are done.
+	 It will output the stats of each per cpu buffer: What
 	 was written, the sizes, what was read, what was lost, and
 	 other similar details.
 
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 3bbd3f0c810c..f47274de012b 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -848,6 +848,9 @@ static int bpf_send_signal_common(u32 sig, enum pid_type type)
 		return -EPERM;
 	if (unlikely(!nmi_uaccess_okay()))
 		return -EPERM;
+	/* Task should not be pid=1 to avoid kernel panic. */
+	if (unlikely(is_global_init(current)))
+		return -EPERM;
 
 	if (irqs_disabled()) {
 		/* Do an early check on signal validity. Otherwise,
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 442438b93fe9..750aa3f08b25 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -1248,12 +1248,17 @@ static void free_ftrace_hash_rcu(struct ftrace_hash *hash)
 	call_rcu(&hash->rcu, __free_ftrace_hash_rcu);
 }
 
+/**
+ * ftrace_free_filter - remove all filters for an ftrace_ops
+ * @ops - the ops to remove the filters from
+ */
 void ftrace_free_filter(struct ftrace_ops *ops)
 {
 	ftrace_ops_init(ops);
 	free_ftrace_hash(ops->func_hash->filter_hash);
 	free_ftrace_hash(ops->func_hash->notrace_hash);
 }
+EXPORT_SYMBOL_GPL(ftrace_free_filter);
 
 static struct ftrace_hash *alloc_ftrace_hash(int size_bits)
 {
@@ -5839,6 +5844,10 @@ EXPORT_SYMBOL_GPL(modify_ftrace_direct_multi);
  *
  * Filters denote which functions should be enabled when tracing is enabled
  * If @ip is NULL, it fails to update filter.
+ *
+ * This can allocate memory which must be freed before @ops can be freed,
+ * either by removing each filtered addr or by using
+ * ftrace_free_filter(@ops).
  */
 int ftrace_set_filter_ip(struct ftrace_ops *ops, unsigned long ip,
 			 int remove, int reset)
@@ -5858,7 +5867,11 @@ EXPORT_SYMBOL_GPL(ftrace_set_filter_ip);
  *
  * Filters denote which functions should be enabled when tracing is enabled
  * If @ips array or any ip specified within is NULL , it fails to update filter.
- */
+ *
+ * This can allocate memory which must be freed before @ops can be freed,
+ * either by removing each filtered addr or by using
+ * ftrace_free_filter(@ops).
+*/
 int ftrace_set_filter_ips(struct ftrace_ops *ops, unsigned long *ips,
 			  unsigned int cnt, int remove, int reset)
 {
@@ -5900,6 +5913,10 @@ ftrace_set_regex(struct ftrace_ops *ops, unsigned char *buf, int len,
  *
  * Filters denote which functions should be enabled when tracing is enabled.
  * If @buf is NULL and reset is set, all functions will be enabled for tracing.
+ *
+ * This can allocate memory which must be freed before @ops can be freed,
+ * either by removing each filtered addr or by using
+ * ftrace_free_filter(@ops).
  */
 int ftrace_set_filter(struct ftrace_ops *ops, unsigned char *buf,
 		       int len, int reset)
@@ -5919,6 +5936,10 @@ EXPORT_SYMBOL_GPL(ftrace_set_filter);
  * Notrace Filters denote which functions should not be enabled when tracing
  * is enabled. If @buf is NULL and reset is set, all functions will be enabled
  * for tracing.
+ *
+ * This can allocate memory which must be freed before @ops can be freed,
+ * either by removing each filtered addr or by using
+ * ftrace_free_filter(@ops).
  */
 int ftrace_set_notrace(struct ftrace_ops *ops, unsigned char *buf,
 			int len, int reset)
diff --git a/kernel/trace/rv/rv.c b/kernel/trace/rv/rv.c
index 6c97cc2d754a..7e9061828c24 100644
--- a/kernel/trace/rv/rv.c
+++ b/kernel/trace/rv/rv.c
@@ -516,7 +516,7 @@ static ssize_t enabled_monitors_write(struct file *filp, const char __user *user
 	struct rv_monitor_def *mdef;
 	int retval = -EINVAL;
 	bool enable = true;
-	char *ptr = buff;
+	char *ptr;
 	int len;
 
 	if (count < 1 || count > MAX_RV_MONITOR_NAME_SIZE + 1)
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index a555a861b978..78ed5f1baa8c 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -10295,6 +10295,8 @@ void __init early_trace_init(void)
 			static_key_enable(&tracepoint_printk_key.key);
 	}
 	tracer_alloc_buffers();
+
+	init_events();
 }
 
 void __init trace_init(void)
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index e46a49269be2..4eb6d6b97a9f 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -1490,6 +1490,7 @@ extern void trace_event_enable_cmd_record(bool enable);
 extern void trace_event_enable_tgid_record(bool enable);
 
 extern int event_trace_init(void);
+extern int init_events(void);
 extern int event_trace_add_tracer(struct dentry *parent, struct trace_array *tr);
 extern int event_trace_del_tracer(struct trace_array *tr);
 extern void __trace_early_add_events(struct trace_array *tr);
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index 96acc2b71ac7..e095c3b3a50d 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -128,7 +128,7 @@ static bool is_not(const char *str)
 }
 
 /**
- * prog_entry - a singe entry in the filter program
+ * struct prog_entry - a singe entry in the filter program
  * @target:	     Index to jump to on a branch (actually one minus the index)
  * @when_to_branch:  The value of the result of the predicate to do a branch
  * @pred:	     The predicate to execute.
@@ -140,16 +140,16 @@ struct prog_entry {
 };
 
 /**
- * update_preds- assign a program entry a label target
+ * update_preds - assign a program entry a label target
  * @prog: The program array
  * @N: The index of the current entry in @prog
- * @when_to_branch: What to assign a program entry for its branch condition
+ * @invert: What to assign a program entry for its branch condition
  *
  * The program entry at @N has a target that points to the index of a program
  * entry that can have its target and when_to_branch fields updated.
  * Update the current program entry denoted by index @N target field to be
  * that of the updated entry. This will denote the entry to update if
- * we are processing an "||" after an "&&"
+ * we are processing an "||" after an "&&".
  */
 static void update_preds(struct prog_entry *prog, int N, int invert)
 {
diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
index fcaf226b7744..5edbf6b1da3f 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -1988,6 +1988,8 @@ static struct hist_field *create_hist_field(struct hist_trigger_data *hist_data,
 		hist_field->fn_num = flags & HIST_FIELD_FL_LOG2 ? HIST_FIELD_FN_LOG2 :
 			HIST_FIELD_FN_BUCKET;
 		hist_field->operands[0] = create_hist_field(hist_data, field, fl, NULL);
+		if (!hist_field->operands[0])
+			goto free;
 		hist_field->size = hist_field->operands[0]->size;
 		hist_field->type = kstrdup_const(hist_field->operands[0]->type, GFP_KERNEL);
 		if (!hist_field->type)
diff --git a/kernel/trace/trace_osnoise.c b/kernel/trace/trace_osnoise.c
index 94c1b5eb1dc0..210e1f168392 100644
--- a/kernel/trace/trace_osnoise.c
+++ b/kernel/trace/trace_osnoise.c
@@ -147,9 +147,8 @@ static void osnoise_unregister_instance(struct trace_array *tr)
 	 * register/unregister serialization is provided by trace's
 	 * trace_types_lock.
 	 */
-	lockdep_assert_held(&trace_types_lock);
-
-	list_for_each_entry_rcu(inst, &osnoise_instances, list) {
+	list_for_each_entry_rcu(inst, &osnoise_instances, list,
+				lockdep_is_held(&trace_types_lock)) {
 		if (inst->tr == tr) {
 			list_del_rcu(&inst->list);
 			found = 1;
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index 57a13b61f186..bd475a00f96d 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -1535,7 +1535,7 @@ static struct trace_event *events[] __initdata = {
 	NULL
 };
 
-__init static int init_events(void)
+__init int init_events(void)
 {
 	struct trace_event *event;
 	int i, ret;
@@ -1548,4 +1548,3 @@ __init static int init_events(void)
 
 	return 0;
 }
-early_initcall(init_events);