Merge branch 'locking/urgent' into locking/core, to pick up fixes

Signed-off-by: Ingo Molnar <mingo@kernel.org>

50 files changed, 319 insertions, 182 deletions

diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c
index a10e2997aa6c..333b3bcfc545 100644
--- a/kernel/auditfilter.c
+++ b/kernel/auditfilter.c
@@ -681,7 +681,7 @@ static struct audit_rule_data *audit_krule_to_data(struct audit_krule *krule)
 				data->values[i] = AUDIT_UID_UNSET;
 				break;
 			}
-			/* fall through - if set */
+			fallthrough;	/* if set */
 		default:
 			data->values[i] = f->val;
 		}
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index 83ff127ef7ae..e21de4f1754c 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -1794,7 +1794,7 @@ static bool cg_sockopt_is_valid_access(int off, int size,
 			return prog->expected_attach_type ==
 				BPF_CGROUP_GETSOCKOPT;
 		case offsetof(struct bpf_sockopt, optname):
-			/* fallthrough */
+			fallthrough;
 		case offsetof(struct bpf_sockopt, level):
 			if (size != size_default)
 				return false;
diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c
index f1c46529929b..6386b7bb98f2 100644
--- a/kernel/bpf/cpumap.c
+++ b/kernel/bpf/cpumap.c
@@ -279,7 +279,7 @@ static int cpu_map_bpf_prog_run_xdp(struct bpf_cpu_map_entry *rcpu,
 			break;
 		default:
 			bpf_warn_invalid_xdp_action(act);
-			/* fallthrough */
+			fallthrough;
 		case XDP_DROP:
 			xdp_return_frame(xdpf);
 			stats->drop++;
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index 78dfff6a501b..7df28a45c66b 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -1622,7 +1622,6 @@ struct bpf_iter_seq_hash_map_info {
 	struct bpf_map *map;
 	struct bpf_htab *htab;
 	void *percpu_value_buf; // non-zero means percpu hash
-	unsigned long flags;
 	u32 bucket_id;
 	u32 skip_elems;
 };
@@ -1632,7 +1631,6 @@ bpf_hash_map_seq_find_next(struct bpf_iter_seq_hash_map_info *info,
 			   struct htab_elem *prev_elem)
 {
 	const struct bpf_htab *htab = info->htab;
-	unsigned long flags = info->flags;
 	u32 skip_elems = info->skip_elems;
 	u32 bucket_id = info->bucket_id;
 	struct hlist_nulls_head *head;
@@ -1656,19 +1654,18 @@ bpf_hash_map_seq_find_next(struct bpf_iter_seq_hash_map_info *info,
 
 		/* not found, unlock and go to the next bucket */
 		b = &htab->buckets[bucket_id++];
-		htab_unlock_bucket(htab, b, flags);
+		rcu_read_unlock();
 		skip_elems = 0;
 	}
 
 	for (i = bucket_id; i < htab->n_buckets; i++) {
 		b = &htab->buckets[i];
-		flags = htab_lock_bucket(htab, b);
+		rcu_read_lock();
 
 		count = 0;
 		head = &b->head;
 		hlist_nulls_for_each_entry_rcu(elem, n, head, hash_node) {
 			if (count >= skip_elems) {
-				info->flags = flags;
 				info->bucket_id = i;
 				info->skip_elems = count;
 				return elem;
@@ -1676,7 +1673,7 @@ bpf_hash_map_seq_find_next(struct bpf_iter_seq_hash_map_info *info,
 			count++;
 		}
 
-		htab_unlock_bucket(htab, b, flags);
+		rcu_read_unlock();
 		skip_elems = 0;
 	}
 
@@ -1754,14 +1751,10 @@ static int bpf_hash_map_seq_show(struct seq_file *seq, void *v)
 
 static void bpf_hash_map_seq_stop(struct seq_file *seq, void *v)
 {
-	struct bpf_iter_seq_hash_map_info *info = seq->private;
-
 	if (!v)
 		(void)__bpf_hash_map_seq_show(seq, NULL);
 	else
-		htab_unlock_bucket(info->htab,
-				   &info->htab->buckets[info->bucket_id],
-				   info->flags);
+		rcu_read_unlock();
 }
 
 static int bpf_iter_init_hash_map(void *priv_data,
diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c
index fb878ba3f22f..18f4969552ac 100644
--- a/kernel/bpf/inode.c
+++ b/kernel/bpf/inode.c
@@ -226,10 +226,12 @@ static void *map_seq_next(struct seq_file *m, void *v, loff_t *pos)
 	else
 		prev_key = key;
 
+	rcu_read_lock();
 	if (map->ops->map_get_next_key(map, prev_key, key)) {
 		map_iter(m)->done = true;
-		return NULL;
+		key = NULL;
 	}
+	rcu_read_unlock();
 	return key;
 }
 
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 86299a292214..b999e7ff2583 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -2029,7 +2029,7 @@ bpf_prog_load_check_attach(enum bpf_prog_type prog_type,
 	case BPF_PROG_TYPE_EXT:
 		if (expected_attach_type)
 			return -EINVAL;
-		/* fallthrough */
+		fallthrough;
 	default:
 		return 0;
 	}
@@ -2634,7 +2634,7 @@ static int bpf_raw_tp_link_fill_link_info(const struct bpf_link *link,
 	u32 ulen = info->raw_tracepoint.tp_name_len;
 	size_t tp_len = strlen(tp_name);
 
-	if (ulen && !ubuf)
+	if (!ulen ^ !ubuf)
 		return -EINVAL;
 
 	info->raw_tracepoint.tp_name_len = tp_len + 1;
diff --git a/kernel/bpf/sysfs_btf.c b/kernel/bpf/sysfs_btf.c
index 3b495773de5a..11b3380887fa 100644
--- a/kernel/bpf/sysfs_btf.c
+++ b/kernel/bpf/sysfs_btf.c
@@ -30,15 +30,15 @@ static struct kobject *btf_kobj;
 
 static int __init btf_vmlinux_init(void)
 {
-	if (!__start_BTF)
+	bin_attr_btf_vmlinux.size = __stop_BTF - __start_BTF;
+
+	if (!__start_BTF || bin_attr_btf_vmlinux.size == 0)
 		return 0;
 
 	btf_kobj = kobject_create_and_add("btf", kernel_kobj);
 	if (!btf_kobj)
 		return -ENOMEM;
 
-	bin_attr_btf_vmlinux.size = __stop_BTF - __start_BTF;
-
 	return sysfs_create_bin_file(btf_kobj, &bin_attr_btf_vmlinux);
 }
 
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index ef938f17b944..fba52d9ec8fc 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -5236,7 +5236,7 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
 				off_reg == dst_reg ? dst : src);
 			return -EACCES;
 		}
-		/* fall-through */
+		fallthrough;
 	default:
 		break;
 	}
@@ -5667,8 +5667,8 @@ static void scalar32_min_max_or(struct bpf_reg_state *dst_reg,
 	bool src_known = tnum_subreg_is_const(src_reg->var_off);
 	bool dst_known = tnum_subreg_is_const(dst_reg->var_off);
 	struct tnum var32_off = tnum_subreg(dst_reg->var_off);
-	s32 smin_val = src_reg->smin_value;
-	u32 umin_val = src_reg->umin_value;
+	s32 smin_val = src_reg->s32_min_value;
+	u32 umin_val = src_reg->u32_min_value;
 
 	/* Assuming scalar64_min_max_or will be called so it is safe
 	 * to skip updating register for known case.
@@ -5691,8 +5691,8 @@ static void scalar32_min_max_or(struct bpf_reg_state *dst_reg,
 		/* ORing two positives gives a positive, so safe to
 		 * cast result into s64.
 		 */
-		dst_reg->s32_min_value = dst_reg->umin_value;
-		dst_reg->s32_max_value = dst_reg->umax_value;
+		dst_reg->s32_min_value = dst_reg->u32_min_value;
+		dst_reg->s32_max_value = dst_reg->u32_max_value;
 	}
 }
 
@@ -10988,7 +10988,7 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
 	default:
 		if (!prog_extension)
 			return -EINVAL;
-		/* fallthrough */
+		fallthrough;
 	case BPF_MODIFY_RETURN:
 	case BPF_LSM_MAC:
 	case BPF_TRACE_FENTRY:
diff --git a/kernel/capability.c b/kernel/capability.c
index 1444f3954d75..7c59b096c98a 100644
--- a/kernel/capability.c
+++ b/kernel/capability.c
@@ -93,7 +93,7 @@ static int cap_validate_magic(cap_user_header_t header, unsigned *tocopy)
 		break;
 	case _LINUX_CAPABILITY_VERSION_2:
 		warn_deprecated_v2();
-		/* fall through - v3 is otherwise equivalent to v2. */
+		fallthrough;	/* v3 is otherwise equivalent to v2 */
 	case _LINUX_CAPABILITY_VERSION_3:
 		*tocopy = _LINUX_CAPABILITY_U32S_3;
 		break;
diff --git a/kernel/compat.c b/kernel/compat.c
index b8d2800bb4b7..05adfd6fa8bf 100644
--- a/kernel/compat.c
+++ b/kernel/compat.c
@@ -255,11 +255,11 @@ get_compat_sigset(sigset_t *set, const compat_sigset_t __user *compat)
 		return -EFAULT;
 	switch (_NSIG_WORDS) {
 	case 4: set->sig[3] = v.sig[6] | (((long)v.sig[7]) << 32 );
-		/* fall through */
+		fallthrough;
 	case 3: set->sig[2] = v.sig[4] | (((long)v.sig[5]) << 32 );
-		/* fall through */
+		fallthrough;
 	case 2: set->sig[1] = v.sig[2] | (((long)v.sig[3]) << 32 );
-		/* fall through */
+		fallthrough;
 	case 1: set->sig[0] = v.sig[0] | (((long)v.sig[1]) << 32 );
 	}
 #else
diff --git a/kernel/debug/gdbstub.c b/kernel/debug/gdbstub.c
index a790026e42d0..cc3c43dfec44 100644
--- a/kernel/debug/gdbstub.c
+++ b/kernel/debug/gdbstub.c
@@ -1046,14 +1046,14 @@ int gdb_serial_stub(struct kgdb_state *ks)
 				return DBG_PASS_EVENT;
 			}
 #endif
-			/* Fall through */
+			fallthrough;
 		case 'C': /* Exception passing */
 			tmp = gdb_cmd_exception_pass(ks);
 			if (tmp > 0)
 				goto default_handle;
 			if (tmp == 0)
 				break;
-			/* Fall through - on tmp < 0 */
+			fallthrough;	/* on tmp < 0 */
 		case 'c': /* Continue packet */
 		case 's': /* Single step packet */
 			if (kgdb_contthread && kgdb_contthread != current) {
@@ -1062,7 +1062,7 @@ int gdb_serial_stub(struct kgdb_state *ks)
 				break;
 			}
 			dbg_activate_sw_breakpoints();
-			/* Fall through - to default processing */
+			fallthrough;	/* to default processing */
 		default:
 default_handle:
 			error = kgdb_arch_handle_exception(ks->ex_vector,
diff --git a/kernel/debug/kdb/kdb_keyboard.c b/kernel/debug/kdb/kdb_keyboard.c
index 750497b0003a..f877a0a0d7cf 100644
--- a/kernel/debug/kdb/kdb_keyboard.c
+++ b/kernel/debug/kdb/kdb_keyboard.c
@@ -173,11 +173,11 @@ int kdb_get_kbd_char(void)
 	case KT_LATIN:
 		if (isprint(keychar))
 			break;		/* printable characters */
-		/* fall through */
+		fallthrough;
 	case KT_SPEC:
 		if (keychar == K_ENTER)
 			break;
-		/* fall through */
+		fallthrough;
 	default:
 		return -1;	/* ignore unprintables */
 	}
diff --git a/kernel/debug/kdb/kdb_support.c b/kernel/debug/kdb/kdb_support.c
index 004c5b6c87f8..6226502ce049 100644
--- a/kernel/debug/kdb/kdb_support.c
+++ b/kernel/debug/kdb/kdb_support.c
@@ -432,7 +432,7 @@ int kdb_getphysword(unsigned long *word, unsigned long addr, size_t size)
 				*word = w8;
 			break;
 		}
-		/* fall through */
+		fallthrough;
 	default:
 		diag = KDB_BADWIDTH;
 		kdb_printf("kdb_getphysword: bad width %ld\n", (long) size);
@@ -481,7 +481,7 @@ int kdb_getword(unsigned long *word, unsigned long addr, size_t size)
 				*word = w8;
 			break;
 		}
-		/* fall through */
+		fallthrough;
 	default:
 		diag = KDB_BADWIDTH;
 		kdb_printf("kdb_getword: bad width %ld\n", (long) size);
@@ -525,7 +525,7 @@ int kdb_putword(unsigned long addr, unsigned long word, size_t size)
 			diag = kdb_putarea(addr, w8);
 			break;
 		}
-		/* fall through */
+		fallthrough;
 	default:
 		diag = KDB_BADWIDTH;
 		kdb_printf("kdb_putword: bad width %ld\n", (long) size);
diff --git a/kernel/dma/pool.c b/kernel/dma/pool.c
index 06582b488e31..1281c0f0442b 100644
--- a/kernel/dma/pool.c
+++ b/kernel/dma/pool.c
@@ -84,7 +84,7 @@ static int atomic_pool_expand(struct gen_pool *pool, size_t pool_size,
 			      gfp_t gfp)
 {
 	unsigned int order;
-	struct page *page;
+	struct page *page = NULL;
 	void *addr;
 	int ret = -ENOMEM;
 
diff --git a/kernel/entry/common.c b/kernel/entry/common.c
index fcae019158ca..6fdb6105e6d6 100644
--- a/kernel/entry/common.c
+++ b/kernel/entry/common.c
@@ -60,31 +60,56 @@ static long syscall_trace_enter(struct pt_regs *regs, long syscall,
 			return ret;
 	}
 
+	/* Either of the above might have changed the syscall number */
+	syscall = syscall_get_nr(current, regs);
+
 	if (unlikely(ti_work & _TIF_SYSCALL_TRACEPOINT))
 		trace_sys_enter(regs, syscall);
 
 	syscall_enter_audit(regs, syscall);
 
-	/* The above might have changed the syscall number */
-	return ret ? : syscall_get_nr(current, regs);
+	return ret ? : syscall;
 }
 
-noinstr long syscall_enter_from_user_mode(struct pt_regs *regs, long syscall)
+static __always_inline long
+__syscall_enter_from_user_work(struct pt_regs *regs, long syscall)
 {
 	unsigned long ti_work;
 
-	enter_from_user_mode(regs);
-	instrumentation_begin();
-
-	local_irq_enable();
 	ti_work = READ_ONCE(current_thread_info()->flags);
 	if (ti_work & SYSCALL_ENTER_WORK)
 		syscall = syscall_trace_enter(regs, syscall, ti_work);
-	instrumentation_end();
 
 	return syscall;
 }
 
+long syscall_enter_from_user_mode_work(struct pt_regs *regs, long syscall)
+{
+	return __syscall_enter_from_user_work(regs, syscall);
+}
+
+noinstr long syscall_enter_from_user_mode(struct pt_regs *regs, long syscall)
+{
+	long ret;
+
+	enter_from_user_mode(regs);
+
+	instrumentation_begin();
+	local_irq_enable();
+	ret = __syscall_enter_from_user_work(regs, syscall);
+	instrumentation_end();
+
+	return ret;
+}
+
+noinstr void syscall_enter_from_user_mode_prepare(struct pt_regs *regs)
+{
+	enter_from_user_mode(regs);
+	instrumentation_begin();
+	local_irq_enable();
+	instrumentation_end();
+}
+
 /**
  * exit_to_user_mode - Fixup state when exiting to user mode
  *
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 5bfe8e3c6e44..7ed5248f0445 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -10034,7 +10034,7 @@ perf_event_parse_addr_filter(struct perf_event *event, char *fstr,
 		case IF_SRC_KERNELADDR:
 		case IF_SRC_KERNEL:
 			kernel = 1;
-			/* fall through */
+			fallthrough;
 
 		case IF_SRC_FILEADDR:
 		case IF_SRC_FILE:
diff --git a/kernel/fork.c b/kernel/fork.c
index 4d32190861bd..da8d360fb032 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -589,7 +589,7 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
 
 		mm->map_count++;
 		if (!(tmp->vm_flags & VM_WIPEONFORK))
-			retval = copy_page_range(mm, oldmm, mpnt);
+			retval = copy_page_range(mm, oldmm, mpnt, tmp);
 
 		if (tmp->vm_ops && tmp->vm_ops->open)
 			tmp->vm_ops->open(tmp);
@@ -1011,6 +1011,7 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p,
 	mm_pgtables_bytes_init(mm);
 	mm->map_count = 0;
 	mm->locked_vm = 0;
+	atomic_set(&mm->has_pinned, 0);
 	atomic64_set(&mm->pinned_vm, 0);
 	memset(&mm->rss_stat, 0, sizeof(mm->rss_stat));
 	spin_lock_init(&mm->page_table_lock);
@@ -3014,7 +3015,7 @@ int unshare_files(struct files_struct **displaced)
 }
 
 int sysctl_max_threads(struct ctl_table *table, int write,
-		       void __user *buffer, size_t *lenp, loff_t *ppos)
+		       void *buffer, size_t *lenp, loff_t *ppos)
 {
 	struct ctl_table t;
 	int ret;
diff --git a/kernel/gcov/gcc_4_7.c b/kernel/gcov/gcc_4_7.c
index 908fdf5098c3..53c67c87f141 100644
--- a/kernel/gcov/gcc_4_7.c
+++ b/kernel/gcov/gcc_4_7.c
@@ -19,7 +19,9 @@
 #include <linux/vmalloc.h>
 #include "gcov.h"
 
-#if (__GNUC__ >= 7)
+#if (__GNUC__ >= 10)
+#define GCOV_COUNTERS			8
+#elif (__GNUC__ >= 7)
 #define GCOV_COUNTERS			9
 #elif (__GNUC__ > 5) || (__GNUC__ == 5 && __GNUC_MINOR__ >= 1)
 #define GCOV_COUNTERS			10
diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c
index a8e14c80b405..762a928e18f9 100644
--- a/kernel/irq/handle.c
+++ b/kernel/irq/handle.c
@@ -173,7 +173,7 @@ irqreturn_t __handle_irq_event_percpu(struct irq_desc *desc, unsigned int *flags
 
 			__irq_wake_thread(desc, action);
 
-			/* Fall through - to add to randomness */
+			fallthrough;	/* to add to randomness */
 		case IRQ_HANDLED:
 			*flags |= action->flags;
 			break;
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 52ac5391dcc6..5df903fccb60 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -271,7 +271,7 @@ int irq_do_set_affinity(struct irq_data *data, const struct cpumask *mask,
 	case IRQ_SET_MASK_OK:
 	case IRQ_SET_MASK_OK_DONE:
 		cpumask_copy(desc->irq_common_data.affinity, mask);
-		/* fall through */
+		fallthrough;
 	case IRQ_SET_MASK_OK_NOCOPY:
 		irq_validate_effective_affinity(data);
 		irq_set_thread_affinity(desc);
@@ -868,7 +868,7 @@ int __irq_set_trigger(struct irq_desc *desc, unsigned long flags)
 	case IRQ_SET_MASK_OK_DONE:
 		irqd_clear(&desc->irq_data, IRQD_TRIGGER_MASK);
 		irqd_set(&desc->irq_data, flags);
-		/* fall through */
+		fallthrough;
 
 	case IRQ_SET_MASK_OK_NOCOPY:
 		flags = irqd_get_trigger_type(&desc->irq_data);
diff --git a/kernel/irq/matrix.c b/kernel/irq/matrix.c
index 30cc217b8631..651a4ad6d711 100644
--- a/kernel/irq/matrix.c
+++ b/kernel/irq/matrix.c
@@ -380,6 +380,13 @@ int irq_matrix_alloc(struct irq_matrix *m, const struct cpumask *msk,
 	unsigned int cpu, bit;
 	struct cpumap *cm;
 
+	/*
+	 * Not required in theory, but matrix_find_best_cpu() uses
+	 * for_each_cpu() which ignores the cpumask on UP .
+	 */
+	if (cpumask_empty(msk))
+		return -EINVAL;
+
 	cpu = matrix_find_best_cpu(m, msk);
 	if (cpu == UINT_MAX)
 		return -ENOSPC;
diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c
index 95cb74f73292..4fb15fa96734 100644
--- a/kernel/kallsyms.c
+++ b/kernel/kallsyms.c
@@ -684,12 +684,12 @@ bool kallsyms_show_value(const struct cred *cred)
 	case 0:
 		if (kallsyms_for_perf())
 			return true;
-	/* fallthrough */
+		fallthrough;
 	case 1:
 		if (security_capable(cred, &init_user_ns, CAP_SYSLOG,
 				     CAP_OPT_NOAUDIT) == 0)
 			return true;
-	/* fallthrough */
+		fallthrough;
 	default:
 		return false;
 	}
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 287b263c9cb9..e995541d277d 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -2140,6 +2140,9 @@ static void kill_kprobe(struct kprobe *p)
 
 	lockdep_assert_held(&kprobe_mutex);
 
+	if (WARN_ON_ONCE(kprobe_gone(p)))
+		return;
+
 	p->flags |= KPROBE_FLAG_GONE;
 	if (kprobe_aggrprobe(p)) {
 		/*
@@ -2159,9 +2162,10 @@ static void kill_kprobe(struct kprobe *p)
 
 	/*
 	 * The module is going away. We should disarm the kprobe which
-	 * is using ftrace.
+	 * is using ftrace, because ftrace framework is still available at
+	 * MODULE_STATE_GOING notification.
 	 */
-	if (kprobe_ftrace(p))
+	if (kprobe_ftrace(p) && !kprobe_disabled(p) && !kprobes_all_disarmed)
 		disarm_kprobe_ftrace(p);
 }
 
@@ -2419,7 +2423,10 @@ static int kprobes_module_callback(struct notifier_block *nb,
 	mutex_lock(&kprobe_mutex);
 	for (i = 0; i < KPROBE_TABLE_SIZE; i++) {
 		head = &kprobe_table[i];
-		hlist_for_each_entry(p, head, hlist)
+		hlist_for_each_entry(p, head, hlist) {
+			if (kprobe_gone(p))
+				continue;
+
 			if (within_module_init((unsigned long)p->addr, mod) ||
 			    (checkcore &&
 			     within_module_core((unsigned long)p->addr, mod))) {
@@ -2436,6 +2443,7 @@ static int kprobes_module_callback(struct notifier_block *nb,
 				 */
 				kill_kprobe(p);
 			}
+		}
 	}
 	if (val == MODULE_STATE_GOING)
 		remove_module_kprobe_blacklist(mod);
@@ -2452,6 +2460,28 @@ static struct notifier_block kprobe_module_nb = {
 extern unsigned long __start_kprobe_blacklist[];
 extern unsigned long __stop_kprobe_blacklist[];
 
+void kprobe_free_init_mem(void)
+{
+	void *start = (void *)(&__init_begin);
+	void *end = (void *)(&__init_end);
+	struct hlist_head *head;
+	struct kprobe *p;
+	int i;
+
+	mutex_lock(&kprobe_mutex);
+
+	/* Kill all kprobes on initmem */
+	for (i = 0; i < KPROBE_TABLE_SIZE; i++) {
+		head = &kprobe_table[i];
+		hlist_for_each_entry(p, head, hlist) {
+			if (start <= (void *)p->addr && (void *)p->addr < end)
+				kill_kprobe(p);
+		}
+	}
+
+	mutex_unlock(&kprobe_mutex);
+}
+
 static int __init init_kprobes(void)
 {
 	int i, err = 0;
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index 9560a4e55277..3e99dfef8408 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -76,6 +76,23 @@ module_param(lock_stat, int, 0644);
 #define lock_stat 0
 #endif
 
+DEFINE_PER_CPU(unsigned int, lockdep_recursion);
+EXPORT_PER_CPU_SYMBOL_GPL(lockdep_recursion);
+
+static inline bool lockdep_enabled(void)
+{
+	if (!debug_locks)
+		return false;
+
+	if (raw_cpu_read(lockdep_recursion))
+		return false;
+
+	if (current->lockdep_recursion)
+		return false;
+
+	return true;
+}
+
 /*
  * lockdep_lock: protects the lockdep graph, the hashes and the
  *               class/list/hash allocators.
@@ -93,7 +110,7 @@ static inline void lockdep_lock(void)
 
 	arch_spin_lock(&__lock);
 	__owner = current;
-	current->lockdep_recursion++;
+	__this_cpu_inc(lockdep_recursion);
 }
 
 static inline void lockdep_unlock(void)
@@ -101,7 +118,7 @@ static inline void lockdep_unlock(void)
 	if (debug_locks && DEBUG_LOCKS_WARN_ON(__owner != current))
 		return;
 
-	current->lockdep_recursion--;
+	__this_cpu_dec(lockdep_recursion);
 	__owner = NULL;
 	arch_spin_unlock(&__lock);
 }
@@ -408,10 +425,15 @@ void lockdep_init_task(struct task_struct *task)
 	task->lockdep_recursion = 0;
 }
 
+static __always_inline void lockdep_recursion_inc(void)
+{
+	__this_cpu_inc(lockdep_recursion);
+}
+
 static __always_inline void lockdep_recursion_finish(void)
 {
-	if (WARN_ON_ONCE((--current->lockdep_recursion) & LOCKDEP_RECURSION_MASK))
-		current->lockdep_recursion = 0;
+	if (WARN_ON_ONCE(__this_cpu_dec_return(lockdep_recursion)))
+		__this_cpu_write(lockdep_recursion, 0);
 }
 
 void lockdep_set_selftest_task(struct task_struct *task)
@@ -600,6 +622,8 @@ static const char *usage_str[] =
 #include "lockdep_states.h"
 #undef LOCKDEP_STATE
 	[LOCK_USED] = "INITIAL USE",
+	[LOCK_USED_READ] = "INITIAL READ USE",
+	/* abused as string storage for verify_lock_unused() */
 	[LOCK_USAGE_STATES] = "IN-NMI",
 };
 #endif
@@ -2252,7 +2276,7 @@ static void print_lock_class_header(struct lock_class *class, int depth)
 #endif
 	printk(KERN_CONT " {\n");
 
-	for (bit = 0; bit < LOCK_USAGE_STATES; bit++) {
+	for (bit = 0; bit < LOCK_TRACE_STATES; bit++) {
 		if (class->usage_mask & (1 << bit)) {
 			int len = depth;
 
@@ -4033,7 +4057,7 @@ void lockdep_hardirqs_on_prepare(unsigned long ip)
 	if (unlikely(in_nmi()))
 		return;
 
-	if (unlikely(current->lockdep_recursion & LOCKDEP_RECURSION_MASK))
+	if (unlikely(__this_cpu_read(lockdep_recursion)))
 		return;
 
 	if (unlikely(lockdep_hardirqs_enabled())) {
@@ -4069,7 +4093,7 @@ void lockdep_hardirqs_on_prepare(unsigned long ip)
 
 	current->hardirq_chain_key = current->curr_chain_key;
 
-	current->lockdep_recursion++;
+	lockdep_recursion_inc();
 	__trace_hardirqs_on_caller();
 	lockdep_recursion_finish();
 }
@@ -4102,7 +4126,7 @@ void noinstr lockdep_hardirqs_on(unsigned long ip)
 		goto skip_checks;
 	}
 
-	if (unlikely(current->lockdep_recursion & LOCKDEP_RECURSION_MASK))
+	if (unlikely(__this_cpu_read(lockdep_recursion)))
 		return;
 
 	if (lockdep_hardirqs_enabled()) {
@@ -4155,7 +4179,7 @@ void noinstr lockdep_hardirqs_off(unsigned long ip)
 	if (in_nmi()) {
 		if (!IS_ENABLED(CONFIG_TRACE_IRQFLAGS_NMI))
 			return;
-	} else if (current->lockdep_recursion & LOCKDEP_RECURSION_MASK)
+	} else if (__this_cpu_read(lockdep_recursion))
 		return;
 
 	/*
@@ -4188,7 +4212,7 @@ void lockdep_softirqs_on(unsigned long ip)
 {
 	struct irqtrace_events *trace = &current->irqtrace;
 
-	if (unlikely(!debug_locks || current->lockdep_recursion))
+	if (unlikely(!lockdep_enabled()))
 		return;
 
 	/*
@@ -4203,7 +4227,7 @@ void lockdep_softirqs_on(unsigned long ip)
 		return;
 	}
 
-	current->lockdep_recursion++;
+	lockdep_recursion_inc();
 	/*
 	 * We'll do an OFF -> ON transition:
 	 */
@@ -4226,7 +4250,7 @@ void lockdep_softirqs_on(unsigned long ip)
  */
 void lockdep_softirqs_off(unsigned long ip)
 {
-	if (unlikely(!debug_locks || current->lockdep_recursion))
+	if (unlikely(!lockdep_enabled()))
 		return;
 
 	/*
@@ -4345,13 +4369,18 @@ static int separate_irq_context(struct task_struct *curr,
 static int mark_lock(struct task_struct *curr, struct held_lock *this,
 			     enum lock_usage_bit new_bit)
 {
-	unsigned int new_mask = 1 << new_bit, ret = 1;
+	unsigned int new_mask, ret = 1;
 
 	if (new_bit >= LOCK_USAGE_STATES) {
 		DEBUG_LOCKS_WARN_ON(1);
 		return 0;
 	}
 
+	if (new_bit == LOCK_USED && this->read)
+		new_bit = LOCK_USED_READ;
+
+	new_mask = 1 << new_bit;
+
 	/*
 	 * If already set then do not dirty the cacheline,
 	 * nor do any checks:
@@ -4364,26 +4393,32 @@ static int mark_lock(struct task_struct *curr, struct held_lock *this,
 	/*
 	 * Make sure we didn't race:
 	 */
-	if (unlikely(hlock_class(this)->usage_mask & new_mask)) {
-		graph_unlock();
-		return 1;
-	}
+	if (unlikely(hlock_class(this)->usage_mask & new_mask))
+		goto unlock;
 
 	hlock_class(this)->usage_mask |= new_mask;
 
-	if (!(hlock_class(this)->usage_traces[new_bit] = save_trace()))
-		return 0;
+	if (new_bit < LOCK_TRACE_STATES) {
+		if (!(hlock_class(this)->usage_traces[new_bit] = save_trace()))
+			return 0;
+	}
 
 	switch (new_bit) {
+	case 0 ... LOCK_USED-1:
+		ret = mark_lock_irq(curr, this, new_bit);
+		if (!ret)
+			return 0;
+		break;
+
 	case LOCK_USED:
 		debug_atomic_dec(nr_unused_locks);
 		break;
+
 	default:
-		ret = mark_lock_irq(curr, this, new_bit);
-		if (!ret)
-			return 0;
+		break;
 	}
 
+unlock:
 	graph_unlock();
 
 	/*
@@ -4596,11 +4631,11 @@ void lockdep_init_map_waits(struct lockdep_map *lock, const char *name,
 	if (subclass) {
 		unsigned long flags;
 
-		if (DEBUG_LOCKS_WARN_ON(current->lockdep_recursion))
+		if (DEBUG_LOCKS_WARN_ON(!lockdep_enabled()))
 			return;
 
 		raw_local_irq_save(flags);
-		current->lockdep_recursion++;
+		lockdep_recursion_inc();
 		register_lock_class(lock, subclass, 1);
 		lockdep_recursion_finish();
 		raw_local_irq_restore(flags);
@@ -5283,11 +5318,11 @@ void lock_set_class(struct lockdep_map *lock, const char *name,
 {
 	unsigned long flags;
 
-	if (unlikely(current->lockdep_recursion))
+	if (unlikely(!lockdep_enabled()))
 		return;
 
 	raw_local_irq_save(flags);
-	current->lockdep_recursion++;
+	lockdep_recursion_inc();
 	check_flags(flags);
 	if (__lock_set_class(lock, name, key, subclass, ip))
 		check_chain_key(current);
@@ -5300,11 +5335,11 @@ void lock_downgrade(struct lockdep_map *lock, unsigned long ip)
 {
 	unsigned long flags;
 
-	if (unlikely(current->lockdep_recursion))
+	if (unlikely(!lockdep_enabled()))
 		return;
 
 	raw_local_irq_save(flags);
-	current->lockdep_recursion++;
+	lockdep_recursion_inc();
 	check_flags(flags);
 	if (__lock_downgrade(lock, ip))
 		check_chain_key(current);
@@ -5318,12 +5353,20 @@ static void verify_lock_unused(struct lockdep_map *lock, struct held_lock *hlock
 {
 #ifdef CONFIG_PROVE_LOCKING
 	struct lock_class *class = look_up_lock_class(lock, subclass);
+	unsigned long mask = LOCKF_USED;
 
 	/* if it doesn't have a class (yet), it certainly hasn't been used yet */
 	if (!class)
 		return;
 
-	if (!(class->usage_mask & LOCK_USED))
+	/*
+	 * READ locks only conflict with USED, such that if we only ever use
+	 * READ locks, there is no deadlock possible -- RCU.
+	 */
+	if (!hlock->read)
+		mask |= LOCKF_USED_READ;
+
+	if (!(class->usage_mask & mask))
 		return;
 
 	hlock->class_idx = class - lock_classes;
@@ -5334,7 +5377,7 @@ static void verify_lock_unused(struct lockdep_map *lock, struct held_lock *hlock
 
 static bool lockdep_nmi(void)
 {
-	if (current->lockdep_recursion & LOCKDEP_RECURSION_MASK)
+	if (raw_cpu_read(lockdep_recursion))
 		return false;
 
 	if (!in_nmi())
@@ -5369,7 +5412,10 @@ void lock_acquire(struct lockdep_map *lock, unsigned int subclass,
 
 	trace_lock_acquire(lock, subclass, trylock, read, check, nest_lock, ip);
 
-	if (unlikely(current->lockdep_recursion)) {
+	if (!debug_locks)
+		return;
+
+	if (unlikely(!lockdep_enabled())) {
 		/* XXX allow trylock from NMI ?!? */
 		if (lockdep_nmi() && !trylock) {
 			struct held_lock hlock;
@@ -5392,7 +5438,7 @@ void lock_acquire(struct lockdep_map *lock, unsigned int subclass,
 	raw_local_irq_save(flags);
 	check_flags(flags);
 
-	current->lockdep_recursion++;
+	lockdep_recursion_inc();
 	__lock_acquire(lock, subclass, trylock, read, check,
 		       irqs_disabled_flags(flags), nest_lock, ip, 0, 0);
 	lockdep_recursion_finish();
@@ -5406,13 +5452,13 @@ void lock_release(struct lockdep_map *lock, unsigned long ip)
 
 	trace_lock_release(lock, ip);
 
-	if (unlikely(current->lockdep_recursion))
+	if (unlikely(!lockdep_enabled()))
 		return;
 
 	raw_local_irq_save(flags);
 	check_flags(flags);
 
-	current->lockdep_recursion++;
+	lockdep_recursion_inc();
 	if (__lock_release(lock, ip))
 		check_chain_key(current);
 	lockdep_recursion_finish();
@@ -5425,13 +5471,13 @@ noinstr int lock_is_held_type(const struct lockdep_map *lock, int read)
 	unsigned long flags;
 	int ret = 0;
 
-	if (unlikely(current->lockdep_recursion))
+	if (unlikely(!lockdep_enabled()))
 		return 1; /* avoid false negative lockdep_assert_held() */
 
 	raw_local_irq_save(flags);
 	check_flags(flags);
 
-	current->lockdep_recursion++;
+	lockdep_recursion_inc();
 	ret = __lock_is_held(lock, read);
 	lockdep_recursion_finish();
 	raw_local_irq_restore(flags);
@@ -5446,13 +5492,13 @@ struct pin_cookie lock_pin_lock(struct lockdep_map *lock)
 	struct pin_cookie cookie = NIL_COOKIE;
 	unsigned long flags;
 
-	if (unlikely(current->lockdep_recursion))
+	if (unlikely(!lockdep_enabled()))
 		return cookie;
 
 	raw_local_irq_save(flags);
 	check_flags(flags);
 
-	current->lockdep_recursion++;
+	lockdep_recursion_inc();
 	cookie = __lock_pin_lock(lock);
 	lockdep_recursion_finish();
 	raw_local_irq_restore(flags);
@@ -5465,13 +5511,13 @@ void lock_repin_lock(struct lockdep_map *lock, struct pin_cookie cookie)
 {
 	unsigned long flags;
 
-	if (unlikely(current->lockdep_recursion))
+	if (unlikely(!lockdep_enabled()))
 		return;
 
 	raw_local_irq_save(flags);
 	check_flags(flags);
 
-	current->lockdep_recursion++;
+	lockdep_recursion_inc();
 	__lock_repin_lock(lock, cookie);
 	lockdep_recursion_finish();
 	raw_local_irq_restore(flags);
@@ -5482,13 +5528,13 @@ void lock_unpin_lock(struct lockdep_map *lock, struct pin_cookie cookie)
 {
 	unsigned long flags;
 
-	if (unlikely(current->lockdep_recursion))
+	if (unlikely(!lockdep_enabled()))
 		return;
 
 	raw_local_irq_save(flags);
 	check_flags(flags);
 
-	current->lockdep_recursion++;
+	lockdep_recursion_inc();
 	__lock_unpin_lock(lock, cookie);
 	lockdep_recursion_finish();
 	raw_local_irq_restore(flags);
@@ -5618,15 +5664,12 @@ void lock_contended(struct lockdep_map *lock, unsigned long ip)
 
 	trace_lock_acquired(lock, ip);
 
-	if (unlikely(!lock_stat || !debug_locks))
-		return;
-
-	if (unlikely(current->lockdep_recursion))
+	if (unlikely(!lock_stat || !lockdep_enabled()))
 		return;
 
 	raw_local_irq_save(flags);
 	check_flags(flags);
-	current->lockdep_recursion++;
+	lockdep_recursion_inc();
 	__lock_contended(lock, ip);
 	lockdep_recursion_finish();
 	raw_local_irq_restore(flags);
@@ -5639,15 +5682,12 @@ void lock_acquired(struct lockdep_map *lock, unsigned long ip)
 
 	trace_lock_contended(lock, ip);
 
-	if (unlikely(!lock_stat || !debug_locks))
-		return;
-
-	if (unlikely(current->lockdep_recursion))
+	if (unlikely(!lock_stat || !lockdep_enabled()))
 		return;
 
 	raw_local_irq_save(flags);
 	check_flags(flags);
-	current->lockdep_recursion++;
+	lockdep_recursion_inc();
 	__lock_acquired(lock, ip);
 	lockdep_recursion_finish();
 	raw_local_irq_restore(flags);
diff --git a/kernel/locking/lockdep_internals.h b/kernel/locking/lockdep_internals.h
index baca699b94e9..de49f9e1c11b 100644
--- a/kernel/locking/lockdep_internals.h
+++ b/kernel/locking/lockdep_internals.h
@@ -19,9 +19,13 @@ enum lock_usage_bit {
 #include "lockdep_states.h"
 #undef LOCKDEP_STATE
 	LOCK_USED,
-	LOCK_USAGE_STATES
+	LOCK_USED_READ,
+	LOCK_USAGE_STATES,
 };
 
+/* states after LOCK_USED_READ are not traced and printed */
+static_assert(LOCK_TRACE_STATES == LOCK_USAGE_STATES);
+
 #define LOCK_USAGE_READ_MASK 1
 #define LOCK_USAGE_DIR_MASK  2
 #define LOCK_USAGE_STATE_MASK (~(LOCK_USAGE_READ_MASK | LOCK_USAGE_DIR_MASK))
@@ -40,6 +44,7 @@ enum {
 #include "lockdep_states.h"
 #undef LOCKDEP_STATE
 	__LOCKF(USED)
+	__LOCKF(USED_READ)
 };
 
 #define LOCKDEP_STATE(__STATE)	LOCKF_ENABLED_##__STATE |
@@ -119,7 +124,7 @@ static const unsigned long LOCKF_USED_IN_IRQ_READ =
 extern struct list_head all_lock_classes;
 extern struct lock_chain lock_chains[];
 
-#define LOCK_USAGE_CHARS (1+LOCK_USAGE_STATES/2)
+#define LOCK_USAGE_CHARS (2*XXX_LOCK_USAGE_STATES + 1)
 
 extern void get_usage_chars(struct lock_class *class,
 			    char usage[LOCK_USAGE_CHARS]);
diff --git a/kernel/locking/percpu-rwsem.c b/kernel/locking/percpu-rwsem.c
index 8bbafe3e5203..70a32a576f3f 100644
--- a/kernel/locking/percpu-rwsem.c
+++ b/kernel/locking/percpu-rwsem.c
@@ -45,7 +45,7 @@ EXPORT_SYMBOL_GPL(percpu_free_rwsem);
 
 static bool __percpu_down_read_trylock(struct percpu_rw_semaphore *sem)
 {
-	__this_cpu_inc(*sem->read_count);
+	this_cpu_inc(*sem->read_count);
 
 	/*
 	 * Due to having preemption disabled the decrement happens on
@@ -71,7 +71,7 @@ static bool __percpu_down_read_trylock(struct percpu_rw_semaphore *sem)
 	if (likely(!atomic_read_acquire(&sem->block)))
 		return true;
 
-	__this_cpu_dec(*sem->read_count);
+	this_cpu_dec(*sem->read_count);
 
 	/* Prod writer to re-evaluate readers_active_check() */
 	rcuwait_wake_up(&sem->writer);
diff --git a/kernel/padata.c b/kernel/padata.c
index 16cb894dc272..d4d3ba6e1728 100644
--- a/kernel/padata.c
+++ b/kernel/padata.c
@@ -215,12 +215,13 @@ int padata_do_parallel(struct padata_shell *ps,
 	padata->pd = pd;
 	padata->cb_cpu = *cb_cpu;
 
-	rcu_read_unlock_bh();
-
 	spin_lock(&padata_works_lock);
 	padata->seq_nr = ++pd->seq_nr;
 	pw = padata_work_alloc();
 	spin_unlock(&padata_works_lock);
+
+	rcu_read_unlock_bh();
+
 	if (pw) {
 		padata_work_init(pw, padata_parallel_worker, padata, 0);
 		queue_work(pinst->parallel_wq, &pw->pw_work);
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index f33769f97aca..e7aa57fb2fdc 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -659,7 +659,7 @@ static void power_down(void)
 		break;
 	case HIBERNATION_PLATFORM:
 		hibernation_platform_enter();
-		/* Fall through */
+		fallthrough;
 	case HIBERNATION_SHUTDOWN:
 		if (pm_power_off)
 			kernel_power_off();
diff --git a/kernel/power/qos.c b/kernel/power/qos.c
index db0bed2cae26..ec7e1e85923e 100644
--- a/kernel/power/qos.c
+++ b/kernel/power/qos.c
@@ -119,7 +119,7 @@ int pm_qos_update_target(struct pm_qos_constraints *c, struct plist_node *node,
 		 * and add, then see if the aggregate has changed.
 		 */
 		plist_del(node, &c->list);
-		/* fall through */
+		fallthrough;
 	case PM_QOS_ADD_REQ:
 		plist_node_init(node, new_value);
 		plist_add(node, &c->list);
@@ -188,7 +188,7 @@ bool pm_qos_update_flags(struct pm_qos_flags *pqf,
 		break;
 	case PM_QOS_UPDATE_REQ:
 		pm_qos_flags_remove_req(pqf, req);
-		/* fall through */
+		fallthrough;
 	case PM_QOS_ADD_REQ:
 		req->flags = val;
 		INIT_LIST_HEAD(&req->node);
diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h
index 835e2df8590a..05d3e1375e4c 100644
--- a/kernel/rcu/tasks.h
+++ b/kernel/rcu/tasks.h
@@ -590,7 +590,7 @@ void exit_tasks_rcu_finish(void) __releases(&tasks_rcu_exit_srcu)
 }
 
 #else /* #ifdef CONFIG_TASKS_RCU */
-static void show_rcu_tasks_classic_gp_kthread(void) { }
+static inline void show_rcu_tasks_classic_gp_kthread(void) { }
 void exit_tasks_rcu_start(void) { }
 void exit_tasks_rcu_finish(void) { exit_tasks_rcu_finish_trace(current); }
 #endif /* #else #ifdef CONFIG_TASKS_RCU */
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 8ce77d9ac716..f78ee759af9c 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -673,6 +673,7 @@ void rcu_idle_enter(void)
 	lockdep_assert_irqs_disabled();
 	rcu_eqs_enter(false);
 }
+EXPORT_SYMBOL_GPL(rcu_idle_enter);
 
 #ifdef CONFIG_NO_HZ_FULL
 /**
@@ -886,6 +887,7 @@ void rcu_idle_exit(void)
 	rcu_eqs_exit(false);
 	local_irq_restore(flags);
 }
+EXPORT_SYMBOL_GPL(rcu_idle_exit);
 
 #ifdef CONFIG_NO_HZ_FULL
 /**
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 8471a0f7eb32..2d95dc3f4644 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2320,7 +2320,7 @@ static int select_fallback_rq(int cpu, struct task_struct *p)
 				state = possible;
 				break;
 			}
-			/* Fall-through */
+			fallthrough;
 		case possible:
 			do_set_cpus_allowed(p, cpu_possible_mask);
 			state = fail;
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index 007b0a6b0152..1bd7e3af904f 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -1219,13 +1219,13 @@ static void __free_domain_allocs(struct s_data *d, enum s_alloc what,
 	case sa_rootdomain:
 		if (!atomic_read(&d->rd->refcount))
 			free_rootdomain(&d->rd->rcu);
-		/* Fall through */
+		fallthrough;
 	case sa_sd:
 		free_percpu(d->sd);
-		/* Fall through */
+		fallthrough;
 	case sa_sd_storage:
 		__sdt_free(cpu_map);
-		/* Fall through */
+		fallthrough;
 	case sa_none:
 		break;
 	}
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index 3ee59ce0a323..676d4af62103 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -1109,13 +1109,18 @@ out:
 }
 
 #ifdef CONFIG_SECCOMP_FILTER
-static int seccomp_notify_release(struct inode *inode, struct file *file)
+static void seccomp_notify_free(struct seccomp_filter *filter)
+{
+	kfree(filter->notif);
+	filter->notif = NULL;
+}
+
+static void seccomp_notify_detach(struct seccomp_filter *filter)
 {
-	struct seccomp_filter *filter = file->private_data;
 	struct seccomp_knotif *knotif;
 
 	if (!filter)
-		return 0;
+		return;
 
 	mutex_lock(&filter->notify_lock);
 
@@ -1139,9 +1144,15 @@ static int seccomp_notify_release(struct inode *inode, struct file *file)
 		complete(&knotif->ready);
 	}
 
-	kfree(filter->notif);
-	filter->notif = NULL;
+	seccomp_notify_free(filter);
 	mutex_unlock(&filter->notify_lock);
+}
+
+static int seccomp_notify_release(struct inode *inode, struct file *file)
+{
+	struct seccomp_filter *filter = file->private_data;
+
+	seccomp_notify_detach(filter);
 	__put_seccomp_filter(filter);
 	return 0;
 }
@@ -1488,7 +1499,7 @@ static struct file *init_listener(struct seccomp_filter *filter)
 
 out_notif:
 	if (IS_ERR(ret))
-		kfree(filter->notif);
+		seccomp_notify_free(filter);
 out:
 	return ret;
 }
@@ -1581,6 +1592,7 @@ out_put_fd:
 			listener_f->private_data = NULL;
 			fput(listener_f);
 			put_unused_fd(listener);
+			seccomp_notify_detach(prepared);
 		} else {
 			fd_install(listener, listener_f);
 			ret = listener;
diff --git a/kernel/signal.c b/kernel/signal.c
index 42b67d2cea37..a38b3edc6851 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -851,7 +851,7 @@ static int check_kill_permission(int sig, struct kernel_siginfo *info,
 			 */
 			if (!sid || sid == task_session(current))
 				break;
-			/* fall through */
+			fallthrough;
 		default:
 			return -EPERM;
 		}
diff --git a/kernel/stackleak.c b/kernel/stackleak.c
index a8fc9ae1d03d..ce161a8e8d97 100644
--- a/kernel/stackleak.c
+++ b/kernel/stackleak.c
@@ -20,7 +20,7 @@
 static DEFINE_STATIC_KEY_FALSE(stack_erasing_bypass);
 
 int stack_erasing_sysctl(struct ctl_table *table, int write,
-			void __user *buffer, size_t *lenp, loff_t *ppos)
+			void *buffer, size_t *lenp, loff_t *ppos)
 {
 	int ret = 0;
 	int state = !static_branch_unlikely(&stack_erasing_bypass);
diff --git a/kernel/sys.c b/kernel/sys.c
index ca11af9d815d..ab6c409b1159 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -1753,7 +1753,7 @@ void getrusage(struct task_struct *p, int who, struct rusage *r)
 
 		if (who == RUSAGE_CHILDREN)
 			break;
-		/* fall through */
+		fallthrough;
 
 	case RUSAGE_SELF:
 		thread_group_cputime_adjusted(p, &tgutime, &tgstime);
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 287862f91717..afad085960b8 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -204,8 +204,7 @@ static int max_extfrag_threshold = 1000;
 
 #if defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_SYSCTL)
 static int bpf_stats_handler(struct ctl_table *table, int write,
-			     void __user *buffer, size_t *lenp,
-			     loff_t *ppos)
+			     void *buffer, size_t *lenp, loff_t *ppos)
 {
 	struct static_key *key = (struct static_key *)table->data;
 	static int saved_val;
@@ -2913,6 +2912,14 @@ static struct ctl_table vm_table[] = {
 		.proc_handler	= percpu_pagelist_fraction_sysctl_handler,
 		.extra1		= SYSCTL_ZERO,
 	},
+	{
+		.procname	= "page_lock_unfairness",
+		.data		= &sysctl_page_lock_unfairness,
+		.maxlen		= sizeof(sysctl_page_lock_unfairness),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= SYSCTL_ZERO,
+	},
 #ifdef CONFIG_MMU
 	{
 		.procname	= "max_map_count",
diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index c4038511d5c9..95b6a708b040 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -377,7 +377,7 @@ static bool hrtimer_fixup_activate(void *addr, enum debug_obj_state state)
 	switch (state) {
 	case ODEBUG_STATE_ACTIVE:
 		WARN_ON(1);
-		/* fall through */
+		fallthrough;
 	default:
 		return false;
 	}
diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c
index 07709ac30439..bf540f5a4115 100644
--- a/kernel/time/posix-timers.c
+++ b/kernel/time/posix-timers.c
@@ -439,12 +439,12 @@ static struct pid *good_sigevent(sigevent_t * event)
 		rtn = pid_task(pid, PIDTYPE_PID);
 		if (!rtn || !same_thread_group(rtn, current))
 			return NULL;
-		/* FALLTHRU */
+		fallthrough;
 	case SIGEV_SIGNAL:
 	case SIGEV_THREAD:
 		if (event->sigev_signo <= 0 || event->sigev_signo > SIGRTMAX)
 			return NULL;
-		/* FALLTHRU */
+		fallthrough;
 	case SIGEV_NONE:
 		return pid;
 	default:
diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
index e51778c312f1..36d7464c8962 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -381,7 +381,7 @@ void tick_broadcast_control(enum tick_broadcast_mode mode)
 	switch (mode) {
 	case TICK_BROADCAST_FORCE:
 		tick_broadcast_forced = 1;
-		/* fall through */
+		fallthrough;
 	case TICK_BROADCAST_ON:
 		cpumask_set_cpu(cpu, tick_broadcast_on);
 		if (!cpumask_test_and_set_cpu(cpu, tick_broadcast_mask)) {
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index a16764b0116e..a50364df1054 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -666,7 +666,7 @@ static bool timer_fixup_activate(void *addr, enum debug_obj_state state)
 
 	case ODEBUG_STATE_ACTIVE:
 		WARN_ON(1);
-		/* fall through */
+		fallthrough;
 	default:
 		return false;
 	}
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index 7ba62d68885a..4b3a42fc3b24 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -745,7 +745,7 @@ int blk_trace_ioctl(struct block_device *bdev, unsigned cmd, char __user *arg)
 #endif
 	case BLKTRACESTART:
 		start = 1;
-		/* fall through */
+		fallthrough;
 	case BLKTRACESTOP:
 		ret = __blk_trace_startstop(q, start);
 		break;
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 275441254bb5..541453927c82 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -2782,6 +2782,7 @@ static void ftrace_remove_trampoline_from_kallsyms(struct ftrace_ops *ops)
 {
 	lockdep_assert_held(&ftrace_lock);
 	list_del_rcu(&ops->list);
+	synchronize_rcu();
 }
 
 /*
@@ -2862,6 +2863,8 @@ int ftrace_startup(struct ftrace_ops *ops, int command)
 		__unregister_ftrace_function(ops);
 		ftrace_start_up--;
 		ops->flags &= ~FTRACE_OPS_FL_ENABLED;
+		if (ops->flags & FTRACE_OPS_FL_DYNAMIC)
+			ftrace_trampoline_free(ops);
 		return ret;
 	}
 
@@ -6990,16 +6993,14 @@ static void ftrace_ops_assist_func(unsigned long ip, unsigned long parent_ip,
 {
 	int bit;
 
-	if ((op->flags & FTRACE_OPS_FL_RCU) && !rcu_is_watching())
-		return;
-
 	bit = trace_test_and_set_recursion(TRACE_LIST_START, TRACE_LIST_MAX);
 	if (bit < 0)
 		return;
 
 	preempt_disable_notrace();
 
-	op->func(ip, parent_ip, op, regs);
+	if (!(op->flags & FTRACE_OPS_FL_RCU) || rcu_is_watching())
+		op->func(ip, parent_ip, op, regs);
 
 	preempt_enable_notrace();
 	trace_clear_recursion(bit);
@@ -7531,8 +7532,7 @@ static bool is_permanent_ops_registered(void)
 
 int
 ftrace_enable_sysctl(struct ctl_table *table, int write,
-		     void __user *buffer, size_t *lenp,
-		     loff_t *ppos)
+		     void *buffer, size_t *lenp, loff_t *ppos)
 {
 	int ret = -ENODEV;
 
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index f40d850ebabc..d3e5de717df2 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -3546,13 +3546,15 @@ struct trace_entry *trace_find_next_entry(struct trace_iterator *iter,
 	if (iter->ent && iter->ent != iter->temp) {
 		if ((!iter->temp || iter->temp_size < iter->ent_size) &&
 		    !WARN_ON_ONCE(iter->temp == static_temp_buf)) {
-			kfree(iter->temp);
-			iter->temp = kmalloc(iter->ent_size, GFP_KERNEL);
-			if (!iter->temp)
+			void *temp;
+			temp = kmalloc(iter->ent_size, GFP_KERNEL);
+			if (!temp)
 				return NULL;
+			kfree(iter->temp);
+			iter->temp = temp;
+			iter->temp_size = iter->ent_size;
 		}
 		memcpy(iter->temp, iter->ent, iter->ent_size);
-		iter->temp_size = iter->ent_size;
 		iter->ent = iter->temp;
 	}
 	entry = __find_next_entry(iter, ent_cpu, NULL, ent_ts);
@@ -3782,14 +3784,14 @@ unsigned long trace_total_entries(struct trace_array *tr)
 
 static void print_lat_help_header(struct seq_file *m)
 {
-	seq_puts(m, "#                  _------=> CPU#            \n"
-		    "#                 / _-----=> irqs-off        \n"
-		    "#                | / _----=> need-resched    \n"
-		    "#                || / _---=> hardirq/softirq \n"
-		    "#                ||| / _--=> preempt-depth   \n"
-		    "#                |||| /     delay            \n"
-		    "#  cmd     pid   ||||| time  |   caller      \n"
-		    "#     \\   /      |||||  \\    |   /         \n");
+	seq_puts(m, "#                    _------=> CPU#            \n"
+		    "#                   / _-----=> irqs-off        \n"
+		    "#                  | / _----=> need-resched    \n"
+		    "#                  || / _---=> hardirq/softirq \n"
+		    "#                  ||| / _--=> preempt-depth   \n"
+		    "#                  |||| /     delay            \n"
+		    "#  cmd     pid     ||||| time  |   caller      \n"
+		    "#     \\   /        |||||  \\    |   /         \n");
 }
 
 static void print_event_info(struct array_buffer *buf, struct seq_file *m)
@@ -3810,26 +3812,26 @@ static void print_func_help_header(struct array_buffer *buf, struct seq_file *m,
 
 	print_event_info(buf, m);
 
-	seq_printf(m, "#           TASK-PID   %s  CPU#   TIMESTAMP  FUNCTION\n", tgid ? "TGID     " : "");
-	seq_printf(m, "#              | |     %s    |       |         |\n",	 tgid ? "  |      " : "");
+	seq_printf(m, "#           TASK-PID    %s CPU#     TIMESTAMP  FUNCTION\n", tgid ? "   TGID   " : "");
+	seq_printf(m, "#              | |      %s   |         |         |\n",      tgid ? "     |    " : "");
 }
 
 static void print_func_help_header_irq(struct array_buffer *buf, struct seq_file *m,
 				       unsigned int flags)
 {
 	bool tgid = flags & TRACE_ITER_RECORD_TGID;
-	const char *space = "          ";
-	int prec = tgid ? 10 : 2;
+	const char *space = "            ";
+	int prec = tgid ? 12 : 2;
 
 	print_event_info(buf, m);
 
-	seq_printf(m, "#                          %.*s  _-----=> irqs-off\n", prec, space);
-	seq_printf(m, "#                          %.*s / _----=> need-resched\n", prec, space);
-	seq_printf(m, "#                          %.*s| / _---=> hardirq/softirq\n", prec, space);
-	seq_printf(m, "#                          %.*s|| / _--=> preempt-depth\n", prec, space);
-	seq_printf(m, "#                          %.*s||| /     delay\n", prec, space);
-	seq_printf(m, "#           TASK-PID %.*sCPU#  ||||    TIMESTAMP  FUNCTION\n", prec, "   TGID   ");
-	seq_printf(m, "#              | |   %.*s  |   ||||       |         |\n", prec, "     |    ");
+	seq_printf(m, "#                            %.*s  _-----=> irqs-off\n", prec, space);
+	seq_printf(m, "#                            %.*s / _----=> need-resched\n", prec, space);
+	seq_printf(m, "#                            %.*s| / _---=> hardirq/softirq\n", prec, space);
+	seq_printf(m, "#                            %.*s|| / _--=> preempt-depth\n", prec, space);
+	seq_printf(m, "#                            %.*s||| /     delay\n", prec, space);
+	seq_printf(m, "#           TASK-PID  %.*s CPU#  ||||   TIMESTAMP  FUNCTION\n", prec, "     TGID   ");
+	seq_printf(m, "#              | |    %.*s   |   ||||      |         |\n", prec, "       |    ");
 }
 
 void
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index bf44f6bbd0c3..78a678eeb140 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -499,7 +499,7 @@ predicate_parse(const char *str, int nr_parens, int nr_preds,
 					ptr++;
 					break;
 				}
-				/* fall through */
+				fallthrough;
 			default:
 				parse_error(pe, FILT_ERR_TOO_MANY_PREDS,
 					    next - str);
@@ -1273,7 +1273,7 @@ static int parse_pred(const char *str, void *data,
 		switch (op) {
 		case OP_NE:
 			pred->not = 1;
-			/* Fall through */
+			fallthrough;
 		case OP_GLOB:
 		case OP_EQ:
 			break;
diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
index 0b933546142e..1b2ef6490229 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -3865,7 +3865,6 @@ static int parse_var_defs(struct hist_trigger_data *hist_data)
 
 			s = kstrdup(field_str, GFP_KERNEL);
 			if (!s) {
-				kfree(hist_data->attrs->var_defs.name[n_vars]);
 				ret = -ENOMEM;
 				goto free;
 			}
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index 4d1893564912..000e9dc224c6 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -497,7 +497,7 @@ lat_print_generic(struct trace_seq *s, struct trace_entry *entry, int cpu)
 
 	trace_find_cmdline(entry->pid, comm);
 
-	trace_seq_printf(s, "%8.8s-%-5d %3d",
+	trace_seq_printf(s, "%8.8s-%-7d %3d",
 			 comm, entry->pid, cpu);
 
 	return trace_print_lat_fmt(s, entry);
@@ -588,15 +588,15 @@ int trace_print_context(struct trace_iterator *iter)
 
 	trace_find_cmdline(entry->pid, comm);
 
-	trace_seq_printf(s, "%16s-%-5d ", comm, entry->pid);
+	trace_seq_printf(s, "%16s-%-7d ", comm, entry->pid);
 
 	if (tr->trace_flags & TRACE_ITER_RECORD_TGID) {
 		unsigned int tgid = trace_find_tgid(entry->pid);
 
 		if (!tgid)
-			trace_seq_printf(s, "(-----) ");
+			trace_seq_printf(s, "(-------) ");
 		else
-			trace_seq_printf(s, "(%5d) ", tgid);
+			trace_seq_printf(s, "(%7d) ", tgid);
 	}
 
 	trace_seq_printf(s, "[%03d] ", iter->cpu);
@@ -636,7 +636,7 @@ int trace_print_lat_context(struct trace_iterator *iter)
 		trace_find_cmdline(entry->pid, comm);
 
 		trace_seq_printf(
-			s, "%16s %5d %3d %d %08x %08lx ",
+			s, "%16s %7d %3d %d %08x %08lx ",
 			comm, entry->pid, iter->cpu, entry->flags,
 			entry->preempt_count, iter->idx);
 	} else {
@@ -917,7 +917,7 @@ static enum print_line_t trace_ctxwake_print(struct trace_iterator *iter,
 	S = task_index_to_char(field->prev_state);
 	trace_find_cmdline(field->next_pid, comm);
 	trace_seq_printf(&iter->seq,
-			 " %5d:%3d:%c %s [%03d] %5d:%3d:%c %s\n",
+			 " %7d:%3d:%c %s [%03d] %7d:%3d:%c %s\n",
 			 field->prev_pid,
 			 field->prev_prio,
 			 S, delim,
diff --git a/kernel/trace/trace_preemptirq.c b/kernel/trace/trace_preemptirq.c
index f10073e62603..f4938040c228 100644
--- a/kernel/trace/trace_preemptirq.c
+++ b/kernel/trace/trace_preemptirq.c
@@ -102,14 +102,14 @@ NOKPROBE_SYMBOL(trace_hardirqs_on_caller);
 
 __visible void trace_hardirqs_off_caller(unsigned long caller_addr)
 {
+	lockdep_hardirqs_off(CALLER_ADDR0);
+
 	if (!this_cpu_read(tracing_irq_cpu)) {
 		this_cpu_write(tracing_irq_cpu, 1);
 		tracer_hardirqs_off(CALLER_ADDR0, caller_addr);
 		if (!in_nmi())
 			trace_irq_disable_rcuidle(CALLER_ADDR0, caller_addr);
 	}
-
-	lockdep_hardirqs_off(CALLER_ADDR0);
 }
 EXPORT_SYMBOL(trace_hardirqs_off_caller);
 NOKPROBE_SYMBOL(trace_hardirqs_off_caller);
diff --git a/kernel/umh.c b/kernel/umh.c
index fcf3ee803630..3f646613a9d3 100644
--- a/kernel/umh.c
+++ b/kernel/umh.c
@@ -14,6 +14,7 @@
 #include <linux/cred.h>
 #include <linux/file.h>
 #include <linux/fdtable.h>
+#include <linux/fs_struct.h>
 #include <linux/workqueue.h>
 #include <linux/security.h>
 #include <linux/mount.h>
@@ -72,6 +73,14 @@ static int call_usermodehelper_exec_async(void *data)
 	spin_unlock_irq(&current->sighand->siglock);
 
 	/*
+	 * Initial kernel threads share ther FS with init, in order to
+	 * get the init root directory. But we've now created a new
+	 * thread that is going to execve a user process and has its own
+	 * 'struct fs_struct'. Reset umask to the default.
+	 */
+	current->fs->umask = 0022;
+
+	/*
 	 * Our parent (unbound workqueue) runs with elevated scheduling
 	 * priority. Avoid propagating that into the userspace child.
 	 */