Merge tag 'v6.2' into iommufd.git for-next

Resolve conflicts from the signature change in iommu_map:

 - drivers/infiniband/hw/usnic/usnic_uiom.c
   Switch iommu_map_atomic() to iommu_map(.., GFP_ATOMIC)

 - drivers/vfio/vfio_iommu_type1.c
   Following indenting change for GFP_KERNEL

Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>

38 files changed, 374 insertions, 177 deletions

diff --git a/kernel/bpf/bpf_lsm.c b/kernel/bpf/bpf_lsm.c
index a4a41ee3e80b..e14c822f8911 100644
--- a/kernel/bpf/bpf_lsm.c
+++ b/kernel/bpf/bpf_lsm.c
@@ -51,7 +51,6 @@ BTF_SET_END(bpf_lsm_current_hooks)
  */
 BTF_SET_START(bpf_lsm_locked_sockopt_hooks)
 #ifdef CONFIG_SECURITY_NETWORK
-BTF_ID(func, bpf_lsm_socket_sock_rcv_skb)
 BTF_ID(func, bpf_lsm_sock_graft)
 BTF_ID(func, bpf_lsm_inet_csk_clone)
 BTF_ID(func, bpf_lsm_inet_conn_established)
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index f7dd8af06413..b7017cae6fd1 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -7782,9 +7782,9 @@ int register_btf_id_dtor_kfuncs(const struct btf_id_dtor_kfunc *dtors, u32 add_c
 
 	sort(tab->dtors, tab->cnt, sizeof(tab->dtors[0]), btf_id_cmp_func, NULL);
 
-	return 0;
 end:
-	btf_free_dtor_kfunc_tab(btf);
+	if (ret)
+		btf_free_dtor_kfunc_tab(btf);
 	btf_put(btf);
 	return ret;
 }
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/memalloc.c b/kernel/bpf/memalloc.c
index ebcc3dd0fa19..1db156405b68 100644
--- a/kernel/bpf/memalloc.c
+++ b/kernel/bpf/memalloc.c
@@ -71,7 +71,7 @@ static int bpf_mem_cache_idx(size_t size)
 	if (size <= 192)
 		return size_index[(size - 1) / 8] - 1;
 
-	return fls(size - 1) - 1;
+	return fls(size - 1) - 2;
 }
 
 #define NUM_CACHES 11
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/verifier.c b/kernel/bpf/verifier.c
index 85f96c1e9f62..7ee218827259 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -2748,6 +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) {
@@ -3237,13 +3243,24 @@ static bool __is_pointer_value(bool allow_ptr_leaks,
 	return reg->type != SCALAR_VALUE;
 }
 
+/* Copy src state preserving dst->parent and dst->live fields */
+static void copy_register_state(struct bpf_reg_state *dst, const struct bpf_reg_state *src)
+{
+	struct bpf_reg_state *parent = dst->parent;
+	enum bpf_reg_liveness live = dst->live;
+
+	*dst = *src;
+	dst->parent = parent;
+	dst->live = live;
+}
+
 static void save_register_state(struct bpf_func_state *state,
 				int spi, struct bpf_reg_state *reg,
 				int size)
 {
 	int i;
 
-	state->stack[spi].spilled_ptr = *reg;
+	copy_register_state(&state->stack[spi].spilled_ptr, reg);
 	if (size == BPF_REG_SIZE)
 		state->stack[spi].spilled_ptr.live |= REG_LIVE_WRITTEN;
 
@@ -3289,7 +3306,9 @@ 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;
 			}
@@ -3569,7 +3588,7 @@ static int check_stack_read_fixed_off(struct bpf_verifier_env *env,
 				 */
 				s32 subreg_def = state->regs[dst_regno].subreg_def;
 
-				state->regs[dst_regno] = *reg;
+				copy_register_state(&state->regs[dst_regno], reg);
 				state->regs[dst_regno].subreg_def = subreg_def;
 			} else {
 				for (i = 0; i < size; i++) {
@@ -3590,7 +3609,7 @@ static int check_stack_read_fixed_off(struct bpf_verifier_env *env,
 
 		if (dst_regno >= 0) {
 			/* restore register state from stack */
-			state->regs[dst_regno] = *reg;
+			copy_register_state(&state->regs[dst_regno], reg);
 			/* mark reg as written since spilled pointer state likely
 			 * has its liveness marks cleared by is_state_visited()
 			 * which resets stack/reg liveness for state transitions
@@ -9584,7 +9603,7 @@ do_sim:
 	 */
 	if (!ptr_is_dst_reg) {
 		tmp = *dst_reg;
-		*dst_reg = *ptr_reg;
+		copy_register_state(dst_reg, ptr_reg);
 	}
 	ret = sanitize_speculative_path(env, NULL, env->insn_idx + 1,
 					env->insn_idx);
@@ -10837,7 +10856,7 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
 					 * to propagate min/max range.
 					 */
 					src_reg->id = ++env->id_gen;
-				*dst_reg = *src_reg;
+				copy_register_state(dst_reg, src_reg);
 				dst_reg->live |= REG_LIVE_WRITTEN;
 				dst_reg->subreg_def = DEF_NOT_SUBREG;
 			} else {
@@ -10848,7 +10867,7 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
 						insn->src_reg);
 					return -EACCES;
 				} else if (src_reg->type == SCALAR_VALUE) {
-					*dst_reg = *src_reg;
+					copy_register_state(dst_reg, src_reg);
 					/* Make sure ID is cleared otherwise
 					 * dst_reg min/max could be incorrectly
 					 * propagated into src_reg by find_equal_scalars()
@@ -11647,7 +11666,7 @@ static void find_equal_scalars(struct bpf_verifier_state *vstate,
 
 	bpf_for_each_reg_in_vstate(vstate, state, reg, ({
 		if (reg->type == SCALAR_VALUE && reg->id == known_reg->id)
-			*reg = *known_reg;
+			copy_register_state(reg, known_reg);
 	}));
 }
 
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index a29c0b13706b..ca826bd1eba3 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -1205,12 +1205,13 @@ void rebuild_sched_domains(void)
 /**
  * update_tasks_cpumask - Update the cpumasks of tasks in the cpuset.
  * @cs: the cpuset in which each task's cpus_allowed mask needs to be changed
+ * @new_cpus: the temp variable for the new effective_cpus mask
  *
  * Iterate through each task of @cs updating its cpus_allowed to the
  * effective cpuset's.  As this function is called with cpuset_rwsem held,
  * cpuset membership stays stable.
  */
-static void update_tasks_cpumask(struct cpuset *cs)
+static void update_tasks_cpumask(struct cpuset *cs, struct cpumask *new_cpus)
 {
 	struct css_task_iter it;
 	struct task_struct *task;
@@ -1224,7 +1225,10 @@ static void update_tasks_cpumask(struct cpuset *cs)
 		if (top_cs && (task->flags & PF_KTHREAD) &&
 		    kthread_is_per_cpu(task))
 			continue;
-		set_cpus_allowed_ptr(task, cs->effective_cpus);
+
+		cpumask_and(new_cpus, cs->effective_cpus,
+			    task_cpu_possible_mask(task));
+		set_cpus_allowed_ptr(task, new_cpus);
 	}
 	css_task_iter_end(&it);
 }
@@ -1346,7 +1350,7 @@ static int update_parent_subparts_cpumask(struct cpuset *cs, int cmd,
 		 * A parent can be left with no CPU as long as there is no
 		 * task directly associated with the parent partition.
 		 */
-		if (!cpumask_intersects(cs->cpus_allowed, parent->effective_cpus) &&
+		if (cpumask_subset(parent->effective_cpus, cs->cpus_allowed) &&
 		    partition_is_populated(parent, cs))
 			return PERR_NOCPUS;
 
@@ -1509,7 +1513,7 @@ static int update_parent_subparts_cpumask(struct cpuset *cs, int cmd,
 	spin_unlock_irq(&callback_lock);
 
 	if (adding || deleting)
-		update_tasks_cpumask(parent);
+		update_tasks_cpumask(parent, tmp->new_cpus);
 
 	/*
 	 * Set or clear CS_SCHED_LOAD_BALANCE when partcmd_update, if necessary.
@@ -1661,7 +1665,7 @@ update_parent_subparts:
 		WARN_ON(!is_in_v2_mode() &&
 			!cpumask_equal(cp->cpus_allowed, cp->effective_cpus));
 
-		update_tasks_cpumask(cp);
+		update_tasks_cpumask(cp, tmp->new_cpus);
 
 		/*
 		 * On legacy hierarchy, if the effective cpumask of any non-
@@ -2309,7 +2313,7 @@ static int update_prstate(struct cpuset *cs, int new_prs)
 		}
 	}
 
-	update_tasks_cpumask(parent);
+	update_tasks_cpumask(parent, tmpmask.new_cpus);
 
 	if (parent->child_ecpus_count)
 		update_sibling_cpumasks(parent, cs, &tmpmask);
@@ -2324,6 +2328,7 @@ out:
 		new_prs = -new_prs;
 	spin_lock_irq(&callback_lock);
 	cs->partition_root_state = new_prs;
+	WRITE_ONCE(cs->prs_err, err);
 	spin_unlock_irq(&callback_lock);
 	/*
 	 * Update child cpusets, if present.
@@ -3347,7 +3352,7 @@ hotplug_update_tasks_legacy(struct cpuset *cs,
 	 * as the tasks will be migrated to an ancestor.
 	 */
 	if (cpus_updated && !cpumask_empty(cs->cpus_allowed))
-		update_tasks_cpumask(cs);
+		update_tasks_cpumask(cs, new_cpus);
 	if (mems_updated && !nodes_empty(cs->mems_allowed))
 		update_tasks_nodemask(cs);
 
@@ -3384,7 +3389,7 @@ hotplug_update_tasks(struct cpuset *cs,
 	spin_unlock_irq(&callback_lock);
 
 	if (cpus_updated)
-		update_tasks_cpumask(cs);
+		update_tasks_cpumask(cs, new_cpus);
 	if (mems_updated)
 		update_tasks_nodemask(cs);
 }
@@ -3691,15 +3696,38 @@ void __init cpuset_init_smp(void)
  * Description: Returns the cpumask_var_t cpus_allowed of the cpuset
  * attached to the specified @tsk.  Guaranteed to return some non-empty
  * subset of cpu_online_mask, even if this means going outside the
- * tasks cpuset.
+ * tasks cpuset, except when the task is in the top cpuset.
  **/
 
 void cpuset_cpus_allowed(struct task_struct *tsk, struct cpumask *pmask)
 {
 	unsigned long flags;
+	struct cpuset *cs;
 
 	spin_lock_irqsave(&callback_lock, flags);
-	guarantee_online_cpus(tsk, pmask);
+	rcu_read_lock();
+
+	cs = task_cs(tsk);
+	if (cs != &top_cpuset)
+		guarantee_online_cpus(tsk, pmask);
+	/*
+	 * Tasks in the top cpuset won't get update to their cpumasks
+	 * when a hotplug online/offline event happens. So we include all
+	 * offline cpus in the allowed cpu list.
+	 */
+	if ((cs == &top_cpuset) || cpumask_empty(pmask)) {
+		const struct cpumask *possible_mask = task_cpu_possible_mask(tsk);
+
+		/*
+		 * We first exclude cpus allocated to partitions. If there is no
+		 * allowable online cpu left, we fall back to all possible cpus.
+		 */
+		cpumask_andnot(pmask, possible_mask, top_cpuset.subparts_cpus);
+		if (!cpumask_intersects(pmask, cpu_online_mask))
+			cpumask_copy(pmask, possible_mask);
+	}
+
+	rcu_read_unlock();
 	spin_unlock_irqrestore(&callback_lock, flags);
 }
 
diff --git a/kernel/events/core.c b/kernel/events/core.c
index d56328e5080e..c4be13e50547 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -4813,19 +4813,17 @@ find_get_pmu_context(struct pmu *pmu, struct perf_event_context *ctx,
 
 		cpc = per_cpu_ptr(pmu->cpu_pmu_context, event->cpu);
 		epc = &cpc->epc;
-
+		raw_spin_lock_irq(&ctx->lock);
 		if (!epc->ctx) {
 			atomic_set(&epc->refcount, 1);
 			epc->embedded = 1;
-			raw_spin_lock_irq(&ctx->lock);
 			list_add(&epc->pmu_ctx_entry, &ctx->pmu_ctx_list);
 			epc->ctx = ctx;
-			raw_spin_unlock_irq(&ctx->lock);
 		} else {
 			WARN_ON_ONCE(epc->ctx != ctx);
 			atomic_inc(&epc->refcount);
 		}
-
+		raw_spin_unlock_irq(&ctx->lock);
 		return epc;
 	}
 
@@ -4896,33 +4894,30 @@ static void free_epc_rcu(struct rcu_head *head)
 
 static void put_pmu_ctx(struct perf_event_pmu_context *epc)
 {
+	struct perf_event_context *ctx = epc->ctx;
 	unsigned long flags;
 
-	if (!atomic_dec_and_test(&epc->refcount))
+	/*
+	 * XXX
+	 *
+	 * lockdep_assert_held(&ctx->mutex);
+	 *
+	 * can't because of the call-site in _free_event()/put_event()
+	 * which isn't always called under ctx->mutex.
+	 */
+	if (!atomic_dec_and_raw_lock_irqsave(&epc->refcount, &ctx->lock, flags))
 		return;
 
-	if (epc->ctx) {
-		struct perf_event_context *ctx = epc->ctx;
+	WARN_ON_ONCE(list_empty(&epc->pmu_ctx_entry));
 
-		/*
-		 * XXX
-		 *
-		 * lockdep_assert_held(&ctx->mutex);
-		 *
-		 * can't because of the call-site in _free_event()/put_event()
-		 * which isn't always called under ctx->mutex.
-		 */
-
-		WARN_ON_ONCE(list_empty(&epc->pmu_ctx_entry));
-		raw_spin_lock_irqsave(&ctx->lock, flags);
-		list_del_init(&epc->pmu_ctx_entry);
-		epc->ctx = NULL;
-		raw_spin_unlock_irqrestore(&ctx->lock, flags);
-	}
+	list_del_init(&epc->pmu_ctx_entry);
+	epc->ctx = NULL;
 
 	WARN_ON_ONCE(!list_empty(&epc->pinned_active));
 	WARN_ON_ONCE(!list_empty(&epc->flexible_active));
 
+	raw_spin_unlock_irqrestore(&ctx->lock, flags);
+
 	if (epc->embedded)
 		return;
 
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 104954951582..9d1b3ab07a16 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);
@@ -1876,7 +1876,7 @@ static void debugfs_add_domain_dir(struct irq_domain *d)
 
 static void debugfs_remove_domain_dir(struct irq_domain *d)
 {
-	debugfs_remove(debugfs_lookup(d->name, domain_dir));
+	debugfs_lookup_and_remove(d->name, domain_dir);
 }
 
 void __init irq_domain_debugfs_init(struct dentry *root)
diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c
index 4dec57fc4ea6..d0f0389920c1 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/locking/rtmutex.c b/kernel/locking/rtmutex.c
index 010cf4e6d0b8..728f434de2bb 100644
--- a/kernel/locking/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -901,8 +901,9 @@ static int __sched rt_mutex_adjust_prio_chain(struct task_struct *task,
 		 * then we need to wake the new top waiter up to try
 		 * to get the lock.
 		 */
-		if (prerequeue_top_waiter != rt_mutex_top_waiter(lock))
-			wake_up_state(waiter->task, waiter->wake_state);
+		top_waiter = rt_mutex_top_waiter(lock);
+		if (prerequeue_top_waiter != top_waiter)
+			wake_up_state(top_waiter->task, top_waiter->wake_state);
 		raw_spin_unlock_irq(&lock->wait_lock);
 		return 0;
 	}
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..2a4918a1faa9 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;
 }
 
@@ -2907,8 +2951,11 @@ static int __set_cpus_allowed_ptr_locked(struct task_struct *p,
 	}
 
 	if (!(ctx->flags & SCA_MIGRATE_ENABLE)) {
-		if (cpumask_equal(&p->cpus_mask, ctx->new_mask))
+		if (cpumask_equal(&p->cpus_mask, ctx->new_mask)) {
+			if (ctx->flags & SCA_USER)
+				swap(p->user_cpus_ptr, ctx->user_mask);
 			goto out;
+		}
 
 		if (WARN_ON_ONCE(p == current &&
 				 is_migration_disabled(p) &&
@@ -3581,6 +3628,11 @@ 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 +5556,9 @@ 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 +8293,18 @@ 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/sched/psi.c b/kernel/sched/psi.c
index 8ac8b81bfee6..02e011cabe91 100644
--- a/kernel/sched/psi.c
+++ b/kernel/sched/psi.c
@@ -1343,10 +1343,11 @@ void psi_trigger_destroy(struct psi_trigger *t)
 
 	group = t->group;
 	/*
-	 * Wakeup waiters to stop polling. Can happen if cgroup is deleted
-	 * from under a polling process.
+	 * Wakeup waiters to stop polling and clear the queue to prevent it from
+	 * being accessed later. Can happen if cgroup is deleted from under a
+	 * polling process.
 	 */
-	wake_up_interruptible(&t->event_wait);
+	wake_up_pollfree(&t->event_wait);
 
 	mutex_lock(&group->trigger_lock);
 
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/alarmtimer.c b/kernel/time/alarmtimer.c
index 5897828b9d7e..7e5dff602585 100644
--- a/kernel/time/alarmtimer.c
+++ b/kernel/time/alarmtimer.c
@@ -470,11 +470,35 @@ u64 alarm_forward(struct alarm *alarm, ktime_t now, ktime_t interval)
 }
 EXPORT_SYMBOL_GPL(alarm_forward);
 
-u64 alarm_forward_now(struct alarm *alarm, ktime_t interval)
+static u64 __alarm_forward_now(struct alarm *alarm, ktime_t interval, bool throttle)
 {
 	struct alarm_base *base = &alarm_bases[alarm->type];
+	ktime_t now = base->get_ktime();
+
+	if (IS_ENABLED(CONFIG_HIGH_RES_TIMERS) && throttle) {
+		/*
+		 * Same issue as with posix_timer_fn(). Timers which are
+		 * periodic but the signal is ignored can starve the system
+		 * with a very small interval. The real fix which was
+		 * promised in the context of posix_timer_fn() never
+		 * materialized, but someone should really work on it.
+		 *
+		 * To prevent DOS fake @now to be 1 jiffie out which keeps
+		 * the overrun accounting correct but creates an
+		 * inconsistency vs. timer_gettime(2).
+		 */
+		ktime_t kj = NSEC_PER_SEC / HZ;
+
+		if (interval < kj)
+			now = ktime_add(now, kj);
+	}
+
+	return alarm_forward(alarm, now, interval);
+}
 
-	return alarm_forward(alarm, base->get_ktime(), interval);
+u64 alarm_forward_now(struct alarm *alarm, ktime_t interval)
+{
+	return __alarm_forward_now(alarm, interval, false);
 }
 EXPORT_SYMBOL_GPL(alarm_forward_now);
 
@@ -551,9 +575,10 @@ static enum alarmtimer_restart alarm_handle_timer(struct alarm *alarm,
 	if (posix_timer_event(ptr, si_private) && ptr->it_interval) {
 		/*
 		 * Handle ignored signals and rearm the timer. This will go
-		 * away once we handle ignored signals proper.
+		 * away once we handle ignored signals proper. Ensure that
+		 * small intervals cannot starve the system.
 		 */
-		ptr->it_overrun += alarm_forward_now(alarm, ptr->it_interval);
+		ptr->it_overrun += __alarm_forward_now(alarm, ptr->it_interval, true);
 		++ptr->it_requeue_pending;
 		ptr->it_active = 1;
 		result = ALARMTIMER_RESTART;
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..c09792c551bf 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -833,6 +833,7 @@ static void do_bpf_send_signal(struct irq_work *entry)
 
 	work = container_of(entry, struct send_signal_irq_work, irq_work);
 	group_send_sig_info(work->sig, SEND_SIG_PRIV, work->task, work->type);
+	put_task_struct(work->task);
 }
 
 static int bpf_send_signal_common(u32 sig, enum pid_type type)
@@ -848,6 +849,9 @@ 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,
@@ -864,7 +868,7 @@ static int bpf_send_signal_common(u32 sig, enum pid_type type)
 		 * to the irq_work. The current task may change when queued
 		 * irq works get executed.
 		 */
-		work->task = current;
+		work->task = get_task_struct(current);
 		work->sig = sig;
 		work->type = type;
 		irq_work_queue(&work->irq_work);
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..c9e40f692650 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -9148,9 +9148,6 @@ buffer_percent_write(struct file *filp, const char __user *ubuf,
 	if (val > 100)
 		return -EINVAL;
 
-	if (!val)
-		val = 1;
-
 	tr->buffer_percent = val;
 
 	(*ppos)++;
@@ -10295,6 +10292,8 @@ 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..085a31b978a5 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -1282,6 +1282,7 @@ struct ftrace_event_field {
 	int			offset;
 	int			size;
 	int			is_signed;
+	int			len;
 };
 
 struct prog_entry;
@@ -1490,6 +1491,7 @@ 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.c b/kernel/trace/trace_events.c
index 33e0b4f8ebe6..6a942fa275c7 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -114,7 +114,7 @@ trace_find_event_field(struct trace_event_call *call, char *name)
 
 static int __trace_define_field(struct list_head *head, const char *type,
 				const char *name, int offset, int size,
-				int is_signed, int filter_type)
+				int is_signed, int filter_type, int len)
 {
 	struct ftrace_event_field *field;
 
@@ -133,6 +133,7 @@ static int __trace_define_field(struct list_head *head, const char *type,
 	field->offset = offset;
 	field->size = size;
 	field->is_signed = is_signed;
+	field->len = len;
 
 	list_add(&field->link, head);
 
@@ -150,14 +151,28 @@ int trace_define_field(struct trace_event_call *call, const char *type,
 
 	head = trace_get_fields(call);
 	return __trace_define_field(head, type, name, offset, size,
-				    is_signed, filter_type);
+				    is_signed, filter_type, 0);
 }
 EXPORT_SYMBOL_GPL(trace_define_field);
 
+static int trace_define_field_ext(struct trace_event_call *call, const char *type,
+		       const char *name, int offset, int size, int is_signed,
+		       int filter_type, int len)
+{
+	struct list_head *head;
+
+	if (WARN_ON(!call->class))
+		return 0;
+
+	head = trace_get_fields(call);
+	return __trace_define_field(head, type, name, offset, size,
+				    is_signed, filter_type, len);
+}
+
 #define __generic_field(type, item, filter_type)			\
 	ret = __trace_define_field(&ftrace_generic_fields, #type,	\
 				   #item, 0, 0, is_signed_type(type),	\
-				   filter_type);			\
+				   filter_type, 0);			\
 	if (ret)							\
 		return ret;
 
@@ -166,7 +181,7 @@ EXPORT_SYMBOL_GPL(trace_define_field);
 				   "common_" #item,			\
 				   offsetof(typeof(ent), item),		\
 				   sizeof(ent.item),			\
-				   is_signed_type(type), FILTER_OTHER);	\
+				   is_signed_type(type), FILTER_OTHER, 0);	\
 	if (ret)							\
 		return ret;
 
@@ -1588,12 +1603,17 @@ static int f_show(struct seq_file *m, void *v)
 		seq_printf(m, "\tfield:%s %s;\toffset:%u;\tsize:%u;\tsigned:%d;\n",
 			   field->type, field->name, field->offset,
 			   field->size, !!field->is_signed);
-	else
-		seq_printf(m, "\tfield:%.*s %s%s;\toffset:%u;\tsize:%u;\tsigned:%d;\n",
+	else if (field->len)
+		seq_printf(m, "\tfield:%.*s %s[%d];\toffset:%u;\tsize:%u;\tsigned:%d;\n",
 			   (int)(array_descriptor - field->type),
 			   field->type, field->name,
-			   array_descriptor, field->offset,
+			   field->len, field->offset,
 			   field->size, !!field->is_signed);
+	else
+		seq_printf(m, "\tfield:%.*s %s[];\toffset:%u;\tsize:%u;\tsigned:%d;\n",
+				(int)(array_descriptor - field->type),
+				field->type, field->name,
+				field->offset, field->size, !!field->is_signed);
 
 	return 0;
 }
@@ -2379,9 +2399,10 @@ event_define_fields(struct trace_event_call *call)
 			}
 
 			offset = ALIGN(offset, field->align);
-			ret = trace_define_field(call, field->type, field->name,
+			ret = trace_define_field_ext(call, field->type, field->name,
 						 offset, field->size,
-						 field->is_signed, field->filter_type);
+						 field->is_signed, field->filter_type,
+						 field->len);
 			if (WARN_ON_ONCE(ret)) {
 				pr_err("error code is %d\n", ret);
 				break;
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_export.c b/kernel/trace/trace_export.c
index d960f6b11b5e..58f3946081e2 100644
--- a/kernel/trace/trace_export.c
+++ b/kernel/trace/trace_export.c
@@ -111,7 +111,8 @@ static void __always_unused ____ftrace_check_##name(void)		\
 #define __array(_type, _item, _len) {					\
 	.type = #_type"["__stringify(_len)"]", .name = #_item,		\
 	.size = sizeof(_type[_len]), .align = __alignof__(_type),	\
-	is_signed_type(_type), .filter_type = FILTER_OTHER },
+	is_signed_type(_type), .filter_type = FILTER_OTHER,			\
+	.len = _len },
 
 #undef __array_desc
 #define __array_desc(_type, _container, _item, _len) __array(_type, _item, _len)
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);
diff --git a/kernel/umh.c b/kernel/umh.c
index 850631518665..fbf872c624cb 100644
--- a/kernel/umh.c
+++ b/kernel/umh.c
@@ -438,21 +438,27 @@ int call_usermodehelper_exec(struct subprocess_info *sub_info, int wait)
 	if (wait == UMH_NO_WAIT)	/* task has freed sub_info */
 		goto unlock;
 
-	if (wait & UMH_KILLABLE)
-		state |= TASK_KILLABLE;
-
 	if (wait & UMH_FREEZABLE)
 		state |= TASK_FREEZABLE;
 
-	retval = wait_for_completion_state(&done, state);
-	if (!retval)
-		goto wait_done;
-
 	if (wait & UMH_KILLABLE) {
+		retval = wait_for_completion_state(&done, state | TASK_KILLABLE);
+		if (!retval)
+			goto wait_done;
+
 		/* umh_complete() will see NULL and free sub_info */
 		if (xchg(&sub_info->complete, NULL))
 			goto unlock;
+
+		/*
+		 * fallthrough; in case of -ERESTARTSYS now do uninterruptible
+		 * wait_for_completion_state(). Since umh_complete() shall call
+		 * complete() in a moment if xchg() above returned NULL, this
+		 * uninterruptible wait_for_completion_state() will not block
+		 * SIGKILL'ed processes for long.
+		 */
 	}
+	wait_for_completion_state(&done, state);
 
 wait_done:
 	retval = sub_info->retval;