Merge branch 'master' into for-next

Sync with Linus' branch in order to be able to apply fixups
of more recent patches.

283 files changed, 32556 insertions, 13453 deletions

diff --git a/kernel/.gitignore b/kernel/.gitignore
index 34d1e77ee9df..78701ea37c97 100644
--- a/kernel/.gitignore
+++ b/kernel/.gitignore
@@ -1,6 +1,4 @@
-#
-# Generated files
-#
+# SPDX-License-Identifier: GPL-2.0-only
 kheaders.md5
 timeconst.h
 hz.bc
diff --git a/kernel/Makefile b/kernel/Makefile
index 4cb4130ced32..9a20016d4900 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -5,13 +5,14 @@
 
 obj-y     = fork.o exec_domain.o panic.o \
 	    cpu.o exit.o softirq.o resource.o \
-	    sysctl.o sysctl_binary.o capability.o ptrace.o user.o \
+	    sysctl.o capability.o ptrace.o user.o \
 	    signal.o sys.o umh.o workqueue.o pid.o task_work.o \
 	    extable.o params.o \
 	    kthread.o sys_ni.o nsproxy.o \
 	    notifier.o ksysfs.o cred.o reboot.o \
-	    async.o range.o smpboot.o ucount.o
+	    async.o range.o smpboot.o ucount.o regset.o
 
+obj-$(CONFIG_BPFILTER) += usermode_driver.o
 obj-$(CONFIG_MODULES) += kmod.o
 obj-$(CONFIG_MULTIUSER) += groups.o
 
@@ -23,6 +24,9 @@ endif
 # Prevents flicker of uninteresting __do_softirq()/__local_bh_disable_ip()
 # in coverage traces.
 KCOV_INSTRUMENT_softirq.o := n
+# Avoid KCSAN instrumentation in softirq ("No shared variables, all the data
+# are CPU local" => assume no data races), to reduce overhead in interrupts.
+KCSAN_SANITIZE_softirq.o = n
 # These are called from save_stack_trace() on slub debug path,
 # and produce insane amounts of uninteresting coverage.
 KCOV_INSTRUMENT_module.o := n
@@ -31,7 +35,8 @@ KCOV_INSTRUMENT_stacktrace.o := n
 # Don't self-instrument.
 KCOV_INSTRUMENT_kcov.o := n
 KASAN_SANITIZE_kcov.o := n
-CFLAGS_kcov.o := $(call cc-option, -fno-conserve-stack -fno-stack-protector)
+KCSAN_SANITIZE_kcov.o := n
+CFLAGS_kcov.o := $(call cc-option, -fno-conserve-stack) -fno-stack-protector
 
 # cond_syscall is currently not LTO compatible
 CFLAGS_sys_ni.o = $(DISABLE_LTO)
@@ -44,6 +49,7 @@ obj-y += irq/
 obj-y += rcu/
 obj-y += livepatch/
 obj-y += dma/
+obj-y += entry/
 
 obj-$(CONFIG_CHECKPOINT_RESTORE) += kcmp.o
 obj-$(CONFIG_FREEZER) += freezer.o
@@ -103,6 +109,8 @@ obj-$(CONFIG_TRACEPOINTS) += trace/
 obj-$(CONFIG_IRQ_WORK) += irq_work.o
 obj-$(CONFIG_CPU_PM) += cpu_pm.o
 obj-$(CONFIG_BPF) += bpf/
+obj-$(CONFIG_KCSAN) += kcsan/
+obj-$(CONFIG_SHADOW_CALL_STACK) += scs.o
 
 obj-$(CONFIG_PERF_EVENTS) += events/
 
@@ -115,11 +123,14 @@ obj-$(CONFIG_TORTURE_TEST) += torture.o
 
 obj-$(CONFIG_HAS_IOMEM) += iomem.o
 obj-$(CONFIG_RSEQ) += rseq.o
+obj-$(CONFIG_WATCH_QUEUE) += watch_queue.o
 
 obj-$(CONFIG_SYSCTL_KUNIT_TEST) += sysctl-test.o
 
+CFLAGS_stackleak.o += $(DISABLE_STACKLEAK_PLUGIN)
 obj-$(CONFIG_GCC_PLUGIN_STACKLEAK) += stackleak.o
 KASAN_SANITIZE_stackleak.o := n
+KCSAN_SANITIZE_stackleak.o := n
 KCOV_INSTRUMENT_stackleak.o := n
 
 $(obj)/configs.o: $(obj)/config_data.gz
diff --git a/kernel/acct.c b/kernel/acct.c
index 11ff4a596d6b..b0c5b3a9f5af 100644
--- a/kernel/acct.c
+++ b/kernel/acct.c
@@ -40,7 +40,7 @@
  *  is one more bug... 10/11/98, AV.
  *
  *	Oh, fsck... Oopsable SMP race in do_process_acct() - we must hold
- * ->mmap_sem to walk the vma list of current->mm. Nasty, since it leaks
+ * ->mmap_lock to walk the vma list of current->mm. Nasty, since it leaks
  * a struct file opened for write. Fixed. 2/6/2000, AV.
  */
 
@@ -541,13 +541,13 @@ void acct_collect(long exitcode, int group_dead)
 	if (group_dead && current->mm) {
 		struct vm_area_struct *vma;
 
-		down_read(&current->mm->mmap_sem);
+		mmap_read_lock(current->mm);
 		vma = current->mm->mmap;
 		while (vma) {
 			vsize += vma->vm_end - vma->vm_start;
 			vma = vma->vm_next;
 		}
-		up_read(&current->mm->mmap_sem);
+		mmap_read_unlock(current->mm);
 	}
 
 	spin_lock_irq(&current->sighand->siglock);
diff --git a/kernel/async.c b/kernel/async.c
index 4f9c1d614016..33258e6e20f8 100644
--- a/kernel/async.c
+++ b/kernel/async.c
@@ -111,7 +111,7 @@ static void async_run_entry_fn(struct work_struct *work)
 	struct async_entry *entry =
 		container_of(work, struct async_entry, work);
 	unsigned long flags;
-	ktime_t uninitialized_var(calltime), delta, rettime;
+	ktime_t calltime, delta, rettime;
 
 	/* 1) run (and print duration) */
 	if (initcall_debug && system_state < SYSTEM_RUNNING) {
@@ -287,7 +287,7 @@ EXPORT_SYMBOL_GPL(async_synchronize_full_domain);
  */
 void async_synchronize_cookie_domain(async_cookie_t cookie, struct async_domain *domain)
 {
-	ktime_t uninitialized_var(starttime), delta, endtime;
+	ktime_t starttime, delta, endtime;
 
 	if (initcall_debug && system_state < SYSTEM_RUNNING) {
 		pr_debug("async_waiting @ %i\n", task_pid_nr(current));
diff --git a/kernel/audit.c b/kernel/audit.c
index 9ddfe2aa6671..7efaece534a9 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -136,6 +136,11 @@ u32		audit_sig_sid = 0;
 */
 static atomic_t	audit_lost = ATOMIC_INIT(0);
 
+/* Monotonically increasing sum of time the kernel has spent
+ * waiting while the backlog limit is exceeded.
+ */
+static atomic_t audit_backlog_wait_time_actual = ATOMIC_INIT(0);
+
 /* Hash for inode-based rules */
 struct list_head audit_inode_hash[AUDIT_INODE_BUCKETS];
 
@@ -880,7 +885,7 @@ main_queue:
 	return 0;
 }
 
-int audit_send_list(void *_dest)
+int audit_send_list_thread(void *_dest)
 {
 	struct audit_netlink_list *dest = _dest;
 	struct sk_buff *skb;
@@ -924,19 +929,30 @@ out_kfree_skb:
 	return NULL;
 }
 
+static void audit_free_reply(struct audit_reply *reply)
+{
+	if (!reply)
+		return;
+
+	if (reply->skb)
+		kfree_skb(reply->skb);
+	if (reply->net)
+		put_net(reply->net);
+	kfree(reply);
+}
+
 static int audit_send_reply_thread(void *arg)
 {
 	struct audit_reply *reply = (struct audit_reply *)arg;
-	struct sock *sk = audit_get_sk(reply->net);
 
 	audit_ctl_lock();
 	audit_ctl_unlock();
 
 	/* Ignore failure. It'll only happen if the sender goes away,
 	   because our timeout is set to infinite. */
-	netlink_unicast(sk, reply->skb, reply->portid, 0);
-	put_net(reply->net);
-	kfree(reply);
+	netlink_unicast(audit_get_sk(reply->net), reply->skb, reply->portid, 0);
+	reply->skb = NULL;
+	audit_free_reply(reply);
 	return 0;
 }
 
@@ -950,35 +966,32 @@ static int audit_send_reply_thread(void *arg)
  * @payload: payload data
  * @size: payload size
  *
- * Allocates an skb, builds the netlink message, and sends it to the port id.
- * No failure notifications.
+ * Allocates a skb, builds the netlink message, and sends it to the port id.
  */
 static void audit_send_reply(struct sk_buff *request_skb, int seq, int type, int done,
 			     int multi, const void *payload, int size)
 {
-	struct net *net = sock_net(NETLINK_CB(request_skb).sk);
-	struct sk_buff *skb;
 	struct task_struct *tsk;
-	struct audit_reply *reply = kmalloc(sizeof(struct audit_reply),
-					    GFP_KERNEL);
+	struct audit_reply *reply;
 
+	reply = kzalloc(sizeof(*reply), GFP_KERNEL);
 	if (!reply)
 		return;
 
-	skb = audit_make_reply(seq, type, done, multi, payload, size);
-	if (!skb)
-		goto out;
-
-	reply->net = get_net(net);
+	reply->skb = audit_make_reply(seq, type, done, multi, payload, size);
+	if (!reply->skb)
+		goto err;
+	reply->net = get_net(sock_net(NETLINK_CB(request_skb).sk));
 	reply->portid = NETLINK_CB(request_skb).portid;
-	reply->skb = skb;
 
 	tsk = kthread_run(audit_send_reply_thread, reply, "audit_send_reply");
-	if (!IS_ERR(tsk))
-		return;
-	kfree_skb(skb);
-out:
-	kfree(reply);
+	if (IS_ERR(tsk))
+		goto err;
+
+	return;
+
+err:
+	audit_free_reply(reply);
 }
 
 /*
@@ -1193,17 +1206,18 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 	case AUDIT_GET: {
 		struct audit_status	s;
 		memset(&s, 0, sizeof(s));
-		s.enabled		= audit_enabled;
-		s.failure		= audit_failure;
+		s.enabled		   = audit_enabled;
+		s.failure		   = audit_failure;
 		/* NOTE: use pid_vnr() so the PID is relative to the current
 		 *       namespace */
-		s.pid			= auditd_pid_vnr();
-		s.rate_limit		= audit_rate_limit;
-		s.backlog_limit		= audit_backlog_limit;
-		s.lost			= atomic_read(&audit_lost);
-		s.backlog		= skb_queue_len(&audit_queue);
-		s.feature_bitmap	= AUDIT_FEATURE_BITMAP_ALL;
-		s.backlog_wait_time	= audit_backlog_wait_time;
+		s.pid			   = auditd_pid_vnr();
+		s.rate_limit		   = audit_rate_limit;
+		s.backlog_limit		   = audit_backlog_limit;
+		s.lost			   = atomic_read(&audit_lost);
+		s.backlog		   = skb_queue_len(&audit_queue);
+		s.feature_bitmap	   = AUDIT_FEATURE_BITMAP_ALL;
+		s.backlog_wait_time	   = audit_backlog_wait_time;
+		s.backlog_wait_time_actual = atomic_read(&audit_backlog_wait_time_actual);
 		audit_send_reply(skb, seq, AUDIT_GET, 0, 0, &s, sizeof(s));
 		break;
 	}
@@ -1307,6 +1321,12 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 			audit_log_config_change("lost", 0, lost, 1);
 			return lost;
 		}
+		if (s.mask == AUDIT_STATUS_BACKLOG_WAIT_TIME_ACTUAL) {
+			u32 actual = atomic_xchg(&audit_backlog_wait_time_actual, 0);
+
+			audit_log_config_change("backlog_wait_time_actual", 0, actual, 1);
+			return actual;
+		}
 		break;
 	}
 	case AUDIT_GET_FEATURE:
@@ -1326,6 +1346,9 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 	case AUDIT_FIRST_USER_MSG2 ... AUDIT_LAST_USER_MSG2:
 		if (!audit_enabled && msg_type != AUDIT_USER_AVC)
 			return 0;
+		/* exit early if there isn't at least one character to print */
+		if (data_len < 2)
+			return -EINVAL;
 
 		err = audit_filter(msg_type, AUDIT_FILTER_USER);
 		if (err == 1) { /* match or error */
@@ -1522,20 +1545,60 @@ static void audit_receive(struct sk_buff  *skb)
 	audit_ctl_unlock();
 }
 
+/* Log information about who is connecting to the audit multicast socket */
+static void audit_log_multicast(int group, const char *op, int err)
+{
+	const struct cred *cred;
+	struct tty_struct *tty;
+	char comm[sizeof(current->comm)];
+	struct audit_buffer *ab;
+
+	if (!audit_enabled)
+		return;
+
+	ab = audit_log_start(audit_context(), GFP_KERNEL, AUDIT_EVENT_LISTENER);
+	if (!ab)
+		return;
+
+	cred = current_cred();
+	tty = audit_get_tty();
+	audit_log_format(ab, "pid=%u uid=%u auid=%u tty=%s ses=%u",
+			 task_pid_nr(current),
+			 from_kuid(&init_user_ns, cred->uid),
+			 from_kuid(&init_user_ns, audit_get_loginuid(current)),
+			 tty ? tty_name(tty) : "(none)",
+			 audit_get_sessionid(current));
+	audit_put_tty(tty);
+	audit_log_task_context(ab); /* subj= */
+	audit_log_format(ab, " comm=");
+	audit_log_untrustedstring(ab, get_task_comm(comm, current));
+	audit_log_d_path_exe(ab, current->mm); /* exe= */
+	audit_log_format(ab, " nl-mcgrp=%d op=%s res=%d", group, op, !err);
+	audit_log_end(ab);
+}
+
 /* Run custom bind function on netlink socket group connect or bind requests. */
-static int audit_bind(struct net *net, int group)
+static int audit_multicast_bind(struct net *net, int group)
 {
+	int err = 0;
+
 	if (!capable(CAP_AUDIT_READ))
-		return -EPERM;
+		err = -EPERM;
+	audit_log_multicast(group, "connect", err);
+	return err;
+}
 
-	return 0;
+static void audit_multicast_unbind(struct net *net, int group)
+{
+	audit_log_multicast(group, "disconnect", 0);
 }
 
 static int __net_init audit_net_init(struct net *net)
 {
 	struct netlink_kernel_cfg cfg = {
 		.input	= audit_receive,
-		.bind	= audit_bind,
+		.bind	= audit_multicast_bind,
+		.unbind	= audit_multicast_unbind,
 		.flags	= NL_CFG_F_NONROOT_RECV,
 		.groups	= AUDIT_NLGRP_MAX,
 	};
@@ -1749,7 +1812,7 @@ struct audit_buffer *audit_log_start(struct audit_context *ctx, gfp_t gfp_mask,
 {
 	struct audit_buffer *ab;
 	struct timespec64 t;
-	unsigned int uninitialized_var(serial);
+	unsigned int serial;
 
 	if (audit_initialized != AUDIT_INITIALIZED)
 		return NULL;
@@ -1775,12 +1838,15 @@ struct audit_buffer *audit_log_start(struct audit_context *ctx, gfp_t gfp_mask,
 			/* sleep if we are allowed and we haven't exhausted our
 			 * backlog wait limit */
 			if (gfpflags_allow_blocking(gfp_mask) && (stime > 0)) {
+				long rtime = stime;
+
 				DECLARE_WAITQUEUE(wait, current);
 
 				add_wait_queue_exclusive(&audit_backlog_wait,
 							 &wait);
 				set_current_state(TASK_UNINTERRUPTIBLE);
-				stime = schedule_timeout(stime);
+				stime = schedule_timeout(rtime);
+				atomic_add(rtime - stime, &audit_backlog_wait_time_actual);
 				remove_wait_queue(&audit_backlog_wait, &wait);
 			} else {
 				if (audit_rate_check() && printk_ratelimit())
@@ -2028,13 +2094,13 @@ void audit_log_d_path(struct audit_buffer *ab, const char *prefix,
 	/* We will allow 11 spaces for ' (deleted)' to be appended */
 	pathname = kmalloc(PATH_MAX+11, ab->gfp_mask);
 	if (!pathname) {
-		audit_log_string(ab, "<no_memory>");
+		audit_log_format(ab, "\"<no_memory>\"");
 		return;
 	}
 	p = d_path(path, pathname, PATH_MAX+11);
 	if (IS_ERR(p)) { /* Should never happen since we send PATH_MAX */
 		/* FIXME: can we save some information here? */
-		audit_log_string(ab, "<too_long>");
+		audit_log_format(ab, "\"<too_long>\"");
 	} else
 		audit_log_untrustedstring(ab, p);
 	kfree(pathname);
diff --git a/kernel/audit.h b/kernel/audit.h
index 6fb7160412d4..ddc22878433d 100644
--- a/kernel/audit.h
+++ b/kernel/audit.h
@@ -229,7 +229,7 @@ struct audit_netlink_list {
 	struct sk_buff_head q;
 };
 
-int audit_send_list(void *_dest);
+int audit_send_list_thread(void *_dest);
 
 extern int selinux_audit_rule_update(void);
 
diff --git a/kernel/audit_fsnotify.c b/kernel/audit_fsnotify.c
index f0d243318452..bfcfcd61adb6 100644
--- a/kernel/audit_fsnotify.c
+++ b/kernel/audit_fsnotify.c
@@ -36,7 +36,7 @@ static struct fsnotify_group *audit_fsnotify_group;
 
 /* fsnotify events we care about. */
 #define AUDIT_FS_EVENTS (FS_MOVE | FS_CREATE | FS_DELETE | FS_DELETE_SELF |\
-			 FS_MOVE_SELF | FS_EVENT_ON_CHILD)
+			 FS_MOVE_SELF)
 
 static void audit_fsnotify_mark_free(struct audit_fsnotify_mark *audit_mark)
 {
@@ -152,44 +152,31 @@ static void audit_autoremove_mark_rule(struct audit_fsnotify_mark *audit_mark)
 }
 
 /* Update mark data in audit rules based on fsnotify events. */
-static int audit_mark_handle_event(struct fsnotify_group *group,
-				    struct inode *to_tell,
-				    u32 mask, const void *data, int data_type,
-				    const struct qstr *dname, u32 cookie,
-				    struct fsnotify_iter_info *iter_info)
+static int audit_mark_handle_event(struct fsnotify_mark *inode_mark, u32 mask,
+				   struct inode *inode, struct inode *dir,
+				   const struct qstr *dname)
 {
-	struct fsnotify_mark *inode_mark = fsnotify_iter_inode_mark(iter_info);
 	struct audit_fsnotify_mark *audit_mark;
-	const struct inode *inode = NULL;
 
 	audit_mark = container_of(inode_mark, struct audit_fsnotify_mark, mark);
 
-	BUG_ON(group != audit_fsnotify_group);
-
-	switch (data_type) {
-	case (FSNOTIFY_EVENT_PATH):
-		inode = ((const struct path *)data)->dentry->d_inode;
-		break;
-	case (FSNOTIFY_EVENT_INODE):
-		inode = (const struct inode *)data;
-		break;
-	default:
-		BUG();
+	if (WARN_ON_ONCE(inode_mark->group != audit_fsnotify_group) ||
+	    WARN_ON_ONCE(!inode))
 		return 0;
-	}
 
 	if (mask & (FS_CREATE|FS_MOVED_TO|FS_DELETE|FS_MOVED_FROM)) {
 		if (audit_compare_dname_path(dname, audit_mark->path, AUDIT_NAME_FULL))
 			return 0;
 		audit_update_mark(audit_mark, inode);
-	} else if (mask & (FS_DELETE_SELF|FS_UNMOUNT|FS_MOVE_SELF))
+	} else if (mask & (FS_DELETE_SELF|FS_UNMOUNT|FS_MOVE_SELF)) {
 		audit_autoremove_mark_rule(audit_mark);
+	}
 
 	return 0;
 }
 
 static const struct fsnotify_ops audit_mark_fsnotify_ops = {
-	.handle_event =	audit_mark_handle_event,
+	.handle_inode_event = audit_mark_handle_event,
 	.free_mark = audit_fsnotify_free_mark,
 };
 
diff --git a/kernel/audit_tree.c b/kernel/audit_tree.c
index e49c912f862d..83e1c07fc99e 100644
--- a/kernel/audit_tree.c
+++ b/kernel/audit_tree.c
@@ -188,11 +188,9 @@ static struct fsnotify_mark *alloc_mark(void)
 static struct audit_chunk *alloc_chunk(int count)
 {
 	struct audit_chunk *chunk;
-	size_t size;
 	int i;
 
-	size = offsetof(struct audit_chunk, owners) + count * sizeof(struct node);
-	chunk = kzalloc(size, GFP_KERNEL);
+	chunk = kzalloc(struct_size(chunk, owners, count), GFP_KERNEL);
 	if (!chunk)
 		return NULL;
 
@@ -1037,11 +1035,9 @@ static void evict_chunk(struct audit_chunk *chunk)
 		audit_schedule_prune();
 }
 
-static int audit_tree_handle_event(struct fsnotify_group *group,
-				   struct inode *to_tell,
-				   u32 mask, const void *data, int data_type,
-				   const struct qstr *file_name, u32 cookie,
-				   struct fsnotify_iter_info *iter_info)
+static int audit_tree_handle_event(struct fsnotify_mark *mark, u32 mask,
+				   struct inode *inode, struct inode *dir,
+				   const struct qstr *file_name)
 {
 	return 0;
 }
@@ -1070,7 +1066,7 @@ static void audit_tree_freeing_mark(struct fsnotify_mark *mark,
 }
 
 static const struct fsnotify_ops audit_tree_ops = {
-	.handle_event = audit_tree_handle_event,
+	.handle_inode_event = audit_tree_handle_event,
 	.freeing_mark = audit_tree_freeing_mark,
 	.free_mark = audit_tree_destroy_watch,
 };
diff --git a/kernel/audit_watch.c b/kernel/audit_watch.c
index 4508d5e0cf69..246e5ba704c0 100644
--- a/kernel/audit_watch.c
+++ b/kernel/audit_watch.c
@@ -53,7 +53,7 @@ static struct fsnotify_group *audit_watch_group;
 
 /* fsnotify events we care about. */
 #define AUDIT_FS_WATCH (FS_MOVE | FS_CREATE | FS_DELETE | FS_DELETE_SELF |\
-			FS_MOVE_SELF | FS_EVENT_ON_CHILD | FS_UNMOUNT)
+			FS_MOVE_SELF | FS_UNMOUNT)
 
 static void audit_free_parent(struct audit_parent *parent)
 {
@@ -302,8 +302,6 @@ static void audit_update_watch(struct audit_parent *parent,
 			if (oentry->rule.exe)
 				audit_remove_mark(oentry->rule.exe);
 
-			audit_watch_log_rule_change(r, owatch, "updated_rules");
-
 			call_rcu(&oentry->rcu, audit_free_rule_rcu);
 		}
 
@@ -466,32 +464,17 @@ void audit_remove_watch_rule(struct audit_krule *krule)
 }
 
 /* Update watch data in audit rules based on fsnotify events. */
-static int audit_watch_handle_event(struct fsnotify_group *group,
-				    struct inode *to_tell,
-				    u32 mask, const void *data, int data_type,
-				    const struct qstr *dname, u32 cookie,
-				    struct fsnotify_iter_info *iter_info)
+static int audit_watch_handle_event(struct fsnotify_mark *inode_mark, u32 mask,
+				    struct inode *inode, struct inode *dir,
+				    const struct qstr *dname)
 {
-	struct fsnotify_mark *inode_mark = fsnotify_iter_inode_mark(iter_info);
-	const struct inode *inode;
 	struct audit_parent *parent;
 
 	parent = container_of(inode_mark, struct audit_parent, mark);
 
-	BUG_ON(group != audit_watch_group);
-
-	switch (data_type) {
-	case (FSNOTIFY_EVENT_PATH):
-		inode = d_backing_inode(((const struct path *)data)->dentry);
-		break;
-	case (FSNOTIFY_EVENT_INODE):
-		inode = (const struct inode *)data;
-		break;
-	default:
-		BUG();
-		inode = NULL;
-		break;
-	}
+	if (WARN_ON_ONCE(inode_mark->group != audit_watch_group) ||
+	    WARN_ON_ONCE(!inode))
+		return 0;
 
 	if (mask & (FS_CREATE|FS_MOVED_TO) && inode)
 		audit_update_watch(parent, dname, inode->i_sb->s_dev, inode->i_ino, 0);
@@ -504,7 +487,7 @@ static int audit_watch_handle_event(struct fsnotify_group *group,
 }
 
 static const struct fsnotify_ops audit_watch_fsnotify_ops = {
-	.handle_event = 	audit_watch_handle_event,
+	.handle_inode_event =	audit_watch_handle_event,
 	.free_mark =		audit_watch_free_mark,
 };
 
diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c
index 026e34da4ace..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;
 		}
@@ -1161,11 +1161,8 @@ int audit_rule_change(int type, int seq, void *data, size_t datasz)
  */
 int audit_list_rules_send(struct sk_buff *request_skb, int seq)
 {
-	u32 portid = NETLINK_CB(request_skb).portid;
-	struct net *net = sock_net(NETLINK_CB(request_skb).sk);
 	struct task_struct *tsk;
 	struct audit_netlink_list *dest;
-	int err = 0;
 
 	/* We can't just spew out the rules here because we might fill
 	 * the available socket buffer space and deadlock waiting for
@@ -1173,25 +1170,26 @@ int audit_list_rules_send(struct sk_buff *request_skb, int seq)
 	 * happen if we're actually running in the context of auditctl
 	 * trying to _send_ the stuff */
 
-	dest = kmalloc(sizeof(struct audit_netlink_list), GFP_KERNEL);
+	dest = kmalloc(sizeof(*dest), GFP_KERNEL);
 	if (!dest)
 		return -ENOMEM;
-	dest->net = get_net(net);
-	dest->portid = portid;
+	dest->net = get_net(sock_net(NETLINK_CB(request_skb).sk));
+	dest->portid = NETLINK_CB(request_skb).portid;
 	skb_queue_head_init(&dest->q);
 
 	mutex_lock(&audit_filter_mutex);
 	audit_list_rules(seq, &dest->q);
 	mutex_unlock(&audit_filter_mutex);
 
-	tsk = kthread_run(audit_send_list, dest, "audit_send_list");
+	tsk = kthread_run(audit_send_list_thread, dest, "audit_send_list");
 	if (IS_ERR(tsk)) {
 		skb_queue_purge(&dest->q);
+		put_net(dest->net);
 		kfree(dest);
-		err = PTR_ERR(tsk);
+		return PTR_ERR(tsk);
 	}
 
-	return err;
+	return 0;
 }
 
 int audit_comparator(u32 left, u32 op, u32 right)
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index 4effe01ebbe2..8dba8f0983b5 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -75,6 +75,7 @@
 #include <linux/uaccess.h>
 #include <linux/fsnotify_backend.h>
 #include <uapi/linux/limits.h>
+#include <uapi/linux/netfilter/nf_tables.h>
 
 #include "audit.h"
 
@@ -130,6 +131,34 @@ struct audit_tree_refs {
 	struct audit_chunk *c[31];
 };
 
+struct audit_nfcfgop_tab {
+	enum audit_nfcfgop	op;
+	const char		*s;
+};
+
+static const struct audit_nfcfgop_tab audit_nfcfgs[] = {
+	{ AUDIT_XT_OP_REGISTER,			"xt_register"		   },
+	{ AUDIT_XT_OP_REPLACE,			"xt_replace"		   },
+	{ AUDIT_XT_OP_UNREGISTER,		"xt_unregister"		   },
+	{ AUDIT_NFT_OP_TABLE_REGISTER,		"nft_register_table"	   },
+	{ AUDIT_NFT_OP_TABLE_UNREGISTER,	"nft_unregister_table"	   },
+	{ AUDIT_NFT_OP_CHAIN_REGISTER,		"nft_register_chain"	   },
+	{ AUDIT_NFT_OP_CHAIN_UNREGISTER,	"nft_unregister_chain"	   },
+	{ AUDIT_NFT_OP_RULE_REGISTER,		"nft_register_rule"	   },
+	{ AUDIT_NFT_OP_RULE_UNREGISTER,		"nft_unregister_rule"	   },
+	{ AUDIT_NFT_OP_SET_REGISTER,		"nft_register_set"	   },
+	{ AUDIT_NFT_OP_SET_UNREGISTER,		"nft_unregister_set"	   },
+	{ AUDIT_NFT_OP_SETELEM_REGISTER,	"nft_register_setelem"	   },
+	{ AUDIT_NFT_OP_SETELEM_UNREGISTER,	"nft_unregister_setelem"   },
+	{ AUDIT_NFT_OP_GEN_REGISTER,		"nft_register_gen"	   },
+	{ AUDIT_NFT_OP_OBJ_REGISTER,		"nft_register_obj"	   },
+	{ AUDIT_NFT_OP_OBJ_UNREGISTER,		"nft_unregister_obj"	   },
+	{ AUDIT_NFT_OP_OBJ_RESET,		"nft_reset_obj"		   },
+	{ AUDIT_NFT_OP_FLOWTABLE_REGISTER,	"nft_register_flowtable"   },
+	{ AUDIT_NFT_OP_FLOWTABLE_UNREGISTER,	"nft_unregister_flowtable" },
+	{ AUDIT_NFT_OP_INVALID,			"nft_invalid"		   },
+};
+
 static int audit_match_perm(struct audit_context *ctx, int mask)
 {
 	unsigned n;
@@ -1865,6 +1894,20 @@ __audit_reusename(const __user char *uptr)
 	return NULL;
 }
 
+inline void _audit_getcwd(struct audit_context *context)
+{
+	if (!context->pwd.dentry)
+		get_fs_pwd(current->fs, &context->pwd);
+}
+
+void __audit_getcwd(void)
+{
+	struct audit_context *context = audit_context();
+
+	if (context->in_syscall)
+		_audit_getcwd(context);
+}
+
 /**
  * __audit_getname - add a name to the list
  * @name: name to add
@@ -1889,8 +1932,7 @@ void __audit_getname(struct filename *name)
 	name->aname = n;
 	name->refcnt++;
 
-	if (!context->pwd.dentry)
-		get_fs_pwd(current->fs, &context->pwd);
+	_audit_getcwd(context);
 }
 
 static inline int audit_copy_fcaps(struct audit_names *name,
@@ -2545,6 +2587,26 @@ void __audit_ntp_log(const struct audit_ntp_data *ad)
 	audit_log_ntp_val(ad, "adjust",	AUDIT_NTP_ADJUST);
 }
 
+void __audit_log_nfcfg(const char *name, u8 af, unsigned int nentries,
+		       enum audit_nfcfgop op, gfp_t gfp)
+{
+	struct audit_buffer *ab;
+	char comm[sizeof(current->comm)];
+
+	ab = audit_log_start(audit_context(), gfp, AUDIT_NETFILTER_CFG);
+	if (!ab)
+		return;
+	audit_log_format(ab, "table=%s family=%u entries=%u op=%s",
+			 name, af, nentries, audit_nfcfgs[op].s);
+
+	audit_log_format(ab, " pid=%u", task_pid_nr(current));
+	audit_log_task_context(ab); /* subj= */
+	audit_log_format(ab, " comm=");
+	audit_log_untrustedstring(ab, get_task_comm(comm, current));
+	audit_log_end(ab);
+}
+EXPORT_SYMBOL_GPL(__audit_log_nfcfg);
+
 static void audit_log_task(struct audit_buffer *ab)
 {
 	kuid_t auid, uid;
diff --git a/kernel/backtracetest.c b/kernel/backtracetest.c
index a2a97fa3071b..370217dd7e39 100644
--- a/kernel/backtracetest.c
+++ b/kernel/backtracetest.c
@@ -29,7 +29,7 @@ static void backtrace_test_irq_callback(unsigned long data)
 	complete(&backtrace_work);
 }
 
-static DECLARE_TASKLET(backtrace_tasklet, &backtrace_test_irq_callback, 0);
+static DECLARE_TASKLET_OLD(backtrace_tasklet, &backtrace_test_irq_callback);
 
 static void backtrace_test_irq(void)
 {
diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile
index 046ce5d98033..e6eb9c0402da 100644
--- a/kernel/bpf/Makefile
+++ b/kernel/bpf/Makefile
@@ -2,9 +2,9 @@
 obj-y := core.o
 CFLAGS_core.o += $(call cc-disable-warning, override-init)
 
-obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o
+obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o bpf_iter.o map_iter.o task_iter.o prog_iter.o
 obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list.o lpm_trie.o map_in_map.o
-obj-$(CONFIG_BPF_SYSCALL) += local_storage.o queue_stack_maps.o
+obj-$(CONFIG_BPF_SYSCALL) += local_storage.o queue_stack_maps.o ringbuf.o
 obj-$(CONFIG_BPF_SYSCALL) += disasm.o
 obj-$(CONFIG_BPF_JIT) += trampoline.o
 obj-$(CONFIG_BPF_SYSCALL) += btf.o
@@ -12,10 +12,8 @@ obj-$(CONFIG_BPF_JIT) += dispatcher.o
 ifeq ($(CONFIG_NET),y)
 obj-$(CONFIG_BPF_SYSCALL) += devmap.o
 obj-$(CONFIG_BPF_SYSCALL) += cpumap.o
-ifeq ($(CONFIG_XDP_SOCKETS),y)
-obj-$(CONFIG_BPF_SYSCALL) += xskmap.o
-endif
 obj-$(CONFIG_BPF_SYSCALL) += offload.o
+obj-$(CONFIG_BPF_SYSCALL) += net_namespace.o
 endif
 ifeq ($(CONFIG_PERF_EVENTS),y)
 obj-$(CONFIG_BPF_SYSCALL) += stackmap.o
@@ -29,4 +27,5 @@ obj-$(CONFIG_DEBUG_INFO_BTF) += sysfs_btf.o
 endif
 ifeq ($(CONFIG_BPF_JIT),y)
 obj-$(CONFIG_BPF_SYSCALL) += bpf_struct_ops.o
+obj-${CONFIG_BPF_LSM} += bpf_lsm.o
 endif
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index 95d77770353c..8ff419b632a6 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -77,7 +77,7 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr)
 	bool percpu = attr->map_type == BPF_MAP_TYPE_PERCPU_ARRAY;
 	int ret, numa_node = bpf_map_attr_numa_node(attr);
 	u32 elem_size, index_mask, max_entries;
-	bool unpriv = !capable(CAP_SYS_ADMIN);
+	bool bypass_spec_v1 = bpf_bypass_spec_v1();
 	u64 cost, array_size, mask64;
 	struct bpf_map_memory mem;
 	struct bpf_array *array;
@@ -95,7 +95,7 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr)
 	mask64 -= 1;
 
 	index_mask = mask64;
-	if (unpriv) {
+	if (!bypass_spec_v1) {
 		/* round up array size to nearest power of 2,
 		 * since cpu will speculate within index_mask limits
 		 */
@@ -149,7 +149,7 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr)
 		return ERR_PTR(-ENOMEM);
 	}
 	array->index_mask = index_mask;
-	array->map.unpriv_array = unpriv;
+	array->map.bypass_spec_v1 = bypass_spec_v1;
 
 	/* copy mandatory map attributes */
 	bpf_map_init_from_attr(&array->map, attr);
@@ -219,7 +219,7 @@ static u32 array_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf)
 
 	*insn++ = BPF_ALU64_IMM(BPF_ADD, map_ptr, offsetof(struct bpf_array, value));
 	*insn++ = BPF_LDX_MEM(BPF_W, ret, index, 0);
-	if (map->unpriv_array) {
+	if (!map->bypass_spec_v1) {
 		*insn++ = BPF_JMP_IMM(BPF_JGE, ret, map->max_entries, 4);
 		*insn++ = BPF_ALU32_IMM(BPF_AND, ret, array->index_mask);
 	} else {
@@ -386,13 +386,6 @@ static void array_map_free(struct bpf_map *map)
 {
 	struct bpf_array *array = container_of(map, struct bpf_array, map);
 
-	/* at this point bpf_prog->aux->refcnt == 0 and this map->refcnt == 0,
-	 * so the programs (can be more than one that used this map) were
-	 * disconnected from events. Wait for outstanding programs to complete
-	 * and free the array
-	 */
-	synchronize_rcu();
-
 	if (array->map.map_type == BPF_MAP_TYPE_PERCPU_ARRAY)
 		bpf_array_free_percpu(array);
 
@@ -486,9 +479,151 @@ static int array_map_mmap(struct bpf_map *map, struct vm_area_struct *vma)
 	if (!(map->map_flags & BPF_F_MMAPABLE))
 		return -EINVAL;
 
-	return remap_vmalloc_range(vma, array_map_vmalloc_addr(array), pgoff);
+	if (vma->vm_pgoff * PAGE_SIZE + (vma->vm_end - vma->vm_start) >
+	    PAGE_ALIGN((u64)array->map.max_entries * array->elem_size))
+		return -EINVAL;
+
+	return remap_vmalloc_range(vma, array_map_vmalloc_addr(array),
+				   vma->vm_pgoff + pgoff);
+}
+
+struct bpf_iter_seq_array_map_info {
+	struct bpf_map *map;
+	void *percpu_value_buf;
+	u32 index;
+};
+
+static void *bpf_array_map_seq_start(struct seq_file *seq, loff_t *pos)
+{
+	struct bpf_iter_seq_array_map_info *info = seq->private;
+	struct bpf_map *map = info->map;
+	struct bpf_array *array;
+	u32 index;
+
+	if (info->index >= map->max_entries)
+		return NULL;
+
+	if (*pos == 0)
+		++*pos;
+	array = container_of(map, struct bpf_array, map);
+	index = info->index & array->index_mask;
+	if (info->percpu_value_buf)
+	       return array->pptrs[index];
+	return array->value + array->elem_size * index;
+}
+
+static void *bpf_array_map_seq_next(struct seq_file *seq, void *v, loff_t *pos)
+{
+	struct bpf_iter_seq_array_map_info *info = seq->private;
+	struct bpf_map *map = info->map;
+	struct bpf_array *array;
+	u32 index;
+
+	++*pos;
+	++info->index;
+	if (info->index >= map->max_entries)
+		return NULL;
+
+	array = container_of(map, struct bpf_array, map);
+	index = info->index & array->index_mask;
+	if (info->percpu_value_buf)
+	       return array->pptrs[index];
+	return array->value + array->elem_size * index;
+}
+
+static int __bpf_array_map_seq_show(struct seq_file *seq, void *v)
+{
+	struct bpf_iter_seq_array_map_info *info = seq->private;
+	struct bpf_iter__bpf_map_elem ctx = {};
+	struct bpf_map *map = info->map;
+	struct bpf_iter_meta meta;
+	struct bpf_prog *prog;
+	int off = 0, cpu = 0;
+	void __percpu **pptr;
+	u32 size;
+
+	meta.seq = seq;
+	prog = bpf_iter_get_info(&meta, v == NULL);
+	if (!prog)
+		return 0;
+
+	ctx.meta = &meta;
+	ctx.map = info->map;
+	if (v) {
+		ctx.key = &info->index;
+
+		if (!info->percpu_value_buf) {
+			ctx.value = v;
+		} else {
+			pptr = v;
+			size = round_up(map->value_size, 8);
+			for_each_possible_cpu(cpu) {
+				bpf_long_memcpy(info->percpu_value_buf + off,
+						per_cpu_ptr(pptr, cpu),
+						size);
+				off += size;
+			}
+			ctx.value = info->percpu_value_buf;
+		}
+	}
+
+	return bpf_iter_run_prog(prog, &ctx);
+}
+
+static int bpf_array_map_seq_show(struct seq_file *seq, void *v)
+{
+	return __bpf_array_map_seq_show(seq, v);
+}
+
+static void bpf_array_map_seq_stop(struct seq_file *seq, void *v)
+{
+	if (!v)
+		(void)__bpf_array_map_seq_show(seq, NULL);
+}
+
+static int bpf_iter_init_array_map(void *priv_data,
+				   struct bpf_iter_aux_info *aux)
+{
+	struct bpf_iter_seq_array_map_info *seq_info = priv_data;
+	struct bpf_map *map = aux->map;
+	void *value_buf;
+	u32 buf_size;
+
+	if (map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) {
+		buf_size = round_up(map->value_size, 8) * num_possible_cpus();
+		value_buf = kmalloc(buf_size, GFP_USER | __GFP_NOWARN);
+		if (!value_buf)
+			return -ENOMEM;
+
+		seq_info->percpu_value_buf = value_buf;
+	}
+
+	seq_info->map = map;
+	return 0;
+}
+
+static void bpf_iter_fini_array_map(void *priv_data)
+{
+	struct bpf_iter_seq_array_map_info *seq_info = priv_data;
+
+	kfree(seq_info->percpu_value_buf);
 }
 
+static const struct seq_operations bpf_array_map_seq_ops = {
+	.start	= bpf_array_map_seq_start,
+	.next	= bpf_array_map_seq_next,
+	.stop	= bpf_array_map_seq_stop,
+	.show	= bpf_array_map_seq_show,
+};
+
+static const struct bpf_iter_seq_info iter_seq_info = {
+	.seq_ops		= &bpf_array_map_seq_ops,
+	.init_seq_private	= bpf_iter_init_array_map,
+	.fini_seq_private	= bpf_iter_fini_array_map,
+	.seq_priv_size		= sizeof(struct bpf_iter_seq_array_map_info),
+};
+
+static int array_map_btf_id;
 const struct bpf_map_ops array_map_ops = {
 	.map_alloc_check = array_map_alloc_check,
 	.map_alloc = array_map_alloc,
@@ -505,8 +640,12 @@ const struct bpf_map_ops array_map_ops = {
 	.map_check_btf = array_map_check_btf,
 	.map_lookup_batch = generic_map_lookup_batch,
 	.map_update_batch = generic_map_update_batch,
+	.map_btf_name = "bpf_array",
+	.map_btf_id = &array_map_btf_id,
+	.iter_seq_info = &iter_seq_info,
 };
 
+static int percpu_array_map_btf_id;
 const struct bpf_map_ops percpu_array_map_ops = {
 	.map_alloc_check = array_map_alloc_check,
 	.map_alloc = array_map_alloc,
@@ -517,6 +656,9 @@ const struct bpf_map_ops percpu_array_map_ops = {
 	.map_delete_elem = array_map_delete_elem,
 	.map_seq_show_elem = percpu_array_map_seq_show_elem,
 	.map_check_btf = array_map_check_btf,
+	.map_btf_name = "bpf_array",
+	.map_btf_id = &percpu_array_map_btf_id,
+	.iter_seq_info = &iter_seq_info,
 };
 
 static int fd_array_map_alloc_check(union bpf_attr *attr)
@@ -535,8 +677,6 @@ static void fd_array_map_free(struct bpf_map *map)
 	struct bpf_array *array = container_of(map, struct bpf_array, map);
 	int i;
 
-	synchronize_rcu();
-
 	/* make sure it's empty */
 	for (i = 0; i < array->map.max_entries; i++)
 		BUG_ON(array->ptrs[i] != NULL);
@@ -863,6 +1003,7 @@ static void prog_array_map_free(struct bpf_map *map)
 	fd_array_map_free(map);
 }
 
+static int prog_array_map_btf_id;
 const struct bpf_map_ops prog_array_map_ops = {
 	.map_alloc_check = fd_array_map_alloc_check,
 	.map_alloc = prog_array_map_alloc,
@@ -878,6 +1019,8 @@ const struct bpf_map_ops prog_array_map_ops = {
 	.map_fd_sys_lookup_elem = prog_fd_array_sys_lookup_elem,
 	.map_release_uref = prog_array_map_clear,
 	.map_seq_show_elem = prog_array_map_seq_show_elem,
+	.map_btf_name = "bpf_array",
+	.map_btf_id = &prog_array_map_btf_id,
 };
 
 static struct bpf_event_entry *bpf_event_entry_gen(struct file *perf_file,
@@ -956,6 +1099,7 @@ static void perf_event_fd_array_release(struct bpf_map *map,
 	rcu_read_unlock();
 }
 
+static int perf_event_array_map_btf_id;
 const struct bpf_map_ops perf_event_array_map_ops = {
 	.map_alloc_check = fd_array_map_alloc_check,
 	.map_alloc = array_map_alloc,
@@ -967,6 +1111,8 @@ const struct bpf_map_ops perf_event_array_map_ops = {
 	.map_fd_put_ptr = perf_event_fd_array_put_ptr,
 	.map_release = perf_event_fd_array_release,
 	.map_check_btf = map_check_no_btf,
+	.map_btf_name = "bpf_array",
+	.map_btf_id = &perf_event_array_map_btf_id,
 };
 
 #ifdef CONFIG_CGROUPS
@@ -989,6 +1135,7 @@ static void cgroup_fd_array_free(struct bpf_map *map)
 	fd_array_map_free(map);
 }
 
+static int cgroup_array_map_btf_id;
 const struct bpf_map_ops cgroup_array_map_ops = {
 	.map_alloc_check = fd_array_map_alloc_check,
 	.map_alloc = array_map_alloc,
@@ -999,6 +1146,8 @@ const struct bpf_map_ops cgroup_array_map_ops = {
 	.map_fd_get_ptr = cgroup_fd_array_get_ptr,
 	.map_fd_put_ptr = cgroup_fd_array_put_ptr,
 	.map_check_btf = map_check_no_btf,
+	.map_btf_name = "bpf_array",
+	.map_btf_id = &cgroup_array_map_btf_id,
 };
 #endif
 
@@ -1053,7 +1202,7 @@ static u32 array_of_map_gen_lookup(struct bpf_map *map,
 
 	*insn++ = BPF_ALU64_IMM(BPF_ADD, map_ptr, offsetof(struct bpf_array, value));
 	*insn++ = BPF_LDX_MEM(BPF_W, ret, index, 0);
-	if (map->unpriv_array) {
+	if (!map->bypass_spec_v1) {
 		*insn++ = BPF_JMP_IMM(BPF_JGE, ret, map->max_entries, 6);
 		*insn++ = BPF_ALU32_IMM(BPF_AND, ret, array->index_mask);
 	} else {
@@ -1072,6 +1221,7 @@ static u32 array_of_map_gen_lookup(struct bpf_map *map,
 	return insn - insn_buf;
 }
 
+static int array_of_maps_map_btf_id;
 const struct bpf_map_ops array_of_maps_map_ops = {
 	.map_alloc_check = fd_array_map_alloc_check,
 	.map_alloc = array_of_map_alloc,
@@ -1084,4 +1234,6 @@ const struct bpf_map_ops array_of_maps_map_ops = {
 	.map_fd_sys_lookup_elem = bpf_map_fd_sys_lookup_elem,
 	.map_gen_lookup = array_of_map_gen_lookup,
 	.map_check_btf = map_check_no_btf,
+	.map_btf_name = "bpf_array",
+	.map_btf_id = &array_of_maps_map_btf_id,
 };
diff --git a/kernel/bpf/bpf_iter.c b/kernel/bpf/bpf_iter.c
new file mode 100644
index 000000000000..8faa2ce89396
--- /dev/null
+++ b/kernel/bpf/bpf_iter.c
@@ -0,0 +1,605 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (c) 2020 Facebook */
+
+#include <linux/fs.h>
+#include <linux/anon_inodes.h>
+#include <linux/filter.h>
+#include <linux/bpf.h>
+
+struct bpf_iter_target_info {
+	struct list_head list;
+	const struct bpf_iter_reg *reg_info;
+	u32 btf_id;	/* cached value */
+};
+
+struct bpf_iter_link {
+	struct bpf_link link;
+	struct bpf_iter_aux_info aux;
+	struct bpf_iter_target_info *tinfo;
+};
+
+struct bpf_iter_priv_data {
+	struct bpf_iter_target_info *tinfo;
+	const struct bpf_iter_seq_info *seq_info;
+	struct bpf_prog *prog;
+	u64 session_id;
+	u64 seq_num;
+	bool done_stop;
+	u8 target_private[] __aligned(8);
+};
+
+static struct list_head targets = LIST_HEAD_INIT(targets);
+static DEFINE_MUTEX(targets_mutex);
+
+/* protect bpf_iter_link changes */
+static DEFINE_MUTEX(link_mutex);
+
+/* incremented on every opened seq_file */
+static atomic64_t session_id;
+
+static int prepare_seq_file(struct file *file, struct bpf_iter_link *link,
+			    const struct bpf_iter_seq_info *seq_info);
+
+static void bpf_iter_inc_seq_num(struct seq_file *seq)
+{
+	struct bpf_iter_priv_data *iter_priv;
+
+	iter_priv = container_of(seq->private, struct bpf_iter_priv_data,
+				 target_private);
+	iter_priv->seq_num++;
+}
+
+static void bpf_iter_dec_seq_num(struct seq_file *seq)
+{
+	struct bpf_iter_priv_data *iter_priv;
+
+	iter_priv = container_of(seq->private, struct bpf_iter_priv_data,
+				 target_private);
+	iter_priv->seq_num--;
+}
+
+static void bpf_iter_done_stop(struct seq_file *seq)
+{
+	struct bpf_iter_priv_data *iter_priv;
+
+	iter_priv = container_of(seq->private, struct bpf_iter_priv_data,
+				 target_private);
+	iter_priv->done_stop = true;
+}
+
+/* maximum visited objects before bailing out */
+#define MAX_ITER_OBJECTS	1000000
+
+/* bpf_seq_read, a customized and simpler version for bpf iterator.
+ * no_llseek is assumed for this file.
+ * The following are differences from seq_read():
+ *  . fixed buffer size (PAGE_SIZE)
+ *  . assuming no_llseek
+ *  . stop() may call bpf program, handling potential overflow there
+ */
+static ssize_t bpf_seq_read(struct file *file, char __user *buf, size_t size,
+			    loff_t *ppos)
+{
+	struct seq_file *seq = file->private_data;
+	size_t n, offs, copied = 0;
+	int err = 0, num_objs = 0;
+	void *p;
+
+	mutex_lock(&seq->lock);
+
+	if (!seq->buf) {
+		seq->size = PAGE_SIZE;
+		seq->buf = kmalloc(seq->size, GFP_KERNEL);
+		if (!seq->buf) {
+			err = -ENOMEM;
+			goto done;
+		}
+	}
+
+	if (seq->count) {
+		n = min(seq->count, size);
+		err = copy_to_user(buf, seq->buf + seq->from, n);
+		if (err) {
+			err = -EFAULT;
+			goto done;
+		}
+		seq->count -= n;
+		seq->from += n;
+		copied = n;
+		goto done;
+	}
+
+	seq->from = 0;
+	p = seq->op->start(seq, &seq->index);
+	if (!p)
+		goto stop;
+	if (IS_ERR(p)) {
+		err = PTR_ERR(p);
+		seq->op->stop(seq, p);
+		seq->count = 0;
+		goto done;
+	}
+
+	err = seq->op->show(seq, p);
+	if (err > 0) {
+		/* object is skipped, decrease seq_num, so next
+		 * valid object can reuse the same seq_num.
+		 */
+		bpf_iter_dec_seq_num(seq);
+		seq->count = 0;
+	} else if (err < 0 || seq_has_overflowed(seq)) {
+		if (!err)
+			err = -E2BIG;
+		seq->op->stop(seq, p);
+		seq->count = 0;
+		goto done;
+	}
+
+	while (1) {
+		loff_t pos = seq->index;
+
+		num_objs++;
+		offs = seq->count;
+		p = seq->op->next(seq, p, &seq->index);
+		if (pos == seq->index) {
+			pr_info_ratelimited("buggy seq_file .next function %ps "
+				"did not updated position index\n",
+				seq->op->next);
+			seq->index++;
+		}
+
+		if (IS_ERR_OR_NULL(p))
+			break;
+
+		/* got a valid next object, increase seq_num */
+		bpf_iter_inc_seq_num(seq);
+
+		if (seq->count >= size)
+			break;
+
+		if (num_objs >= MAX_ITER_OBJECTS) {
+			if (offs == 0) {
+				err = -EAGAIN;
+				seq->op->stop(seq, p);
+				goto done;
+			}
+			break;
+		}
+
+		err = seq->op->show(seq, p);
+		if (err > 0) {
+			bpf_iter_dec_seq_num(seq);
+			seq->count = offs;
+		} else if (err < 0 || seq_has_overflowed(seq)) {
+			seq->count = offs;
+			if (offs == 0) {
+				if (!err)
+					err = -E2BIG;
+				seq->op->stop(seq, p);
+				goto done;
+			}
+			break;
+		}
+	}
+stop:
+	offs = seq->count;
+	/* bpf program called if !p */
+	seq->op->stop(seq, p);
+	if (!p) {
+		if (!seq_has_overflowed(seq)) {
+			bpf_iter_done_stop(seq);
+		} else {
+			seq->count = offs;
+			if (offs == 0) {
+				err = -E2BIG;
+				goto done;
+			}
+		}
+	}
+
+	n = min(seq->count, size);
+	err = copy_to_user(buf, seq->buf, n);
+	if (err) {
+		err = -EFAULT;
+		goto done;
+	}
+	copied = n;
+	seq->count -= n;
+	seq->from = n;
+done:
+	if (!copied)
+		copied = err;
+	else
+		*ppos += copied;
+	mutex_unlock(&seq->lock);
+	return copied;
+}
+
+static const struct bpf_iter_seq_info *
+__get_seq_info(struct bpf_iter_link *link)
+{
+	const struct bpf_iter_seq_info *seq_info;
+
+	if (link->aux.map) {
+		seq_info = link->aux.map->ops->iter_seq_info;
+		if (seq_info)
+			return seq_info;
+	}
+
+	return link->tinfo->reg_info->seq_info;
+}
+
+static int iter_open(struct inode *inode, struct file *file)
+{
+	struct bpf_iter_link *link = inode->i_private;
+
+	return prepare_seq_file(file, link, __get_seq_info(link));
+}
+
+static int iter_release(struct inode *inode, struct file *file)
+{
+	struct bpf_iter_priv_data *iter_priv;
+	struct seq_file *seq;
+
+	seq = file->private_data;
+	if (!seq)
+		return 0;
+
+	iter_priv = container_of(seq->private, struct bpf_iter_priv_data,
+				 target_private);
+
+	if (iter_priv->seq_info->fini_seq_private)
+		iter_priv->seq_info->fini_seq_private(seq->private);
+
+	bpf_prog_put(iter_priv->prog);
+	seq->private = iter_priv;
+
+	return seq_release_private(inode, file);
+}
+
+const struct file_operations bpf_iter_fops = {
+	.open		= iter_open,
+	.llseek		= no_llseek,
+	.read		= bpf_seq_read,
+	.release	= iter_release,
+};
+
+/* The argument reg_info will be cached in bpf_iter_target_info.
+ * The common practice is to declare target reg_info as
+ * a const static variable and passed as an argument to
+ * bpf_iter_reg_target().
+ */
+int bpf_iter_reg_target(const struct bpf_iter_reg *reg_info)
+{
+	struct bpf_iter_target_info *tinfo;
+
+	tinfo = kmalloc(sizeof(*tinfo), GFP_KERNEL);
+	if (!tinfo)
+		return -ENOMEM;
+
+	tinfo->reg_info = reg_info;
+	INIT_LIST_HEAD(&tinfo->list);
+
+	mutex_lock(&targets_mutex);
+	list_add(&tinfo->list, &targets);
+	mutex_unlock(&targets_mutex);
+
+	return 0;
+}
+
+void bpf_iter_unreg_target(const struct bpf_iter_reg *reg_info)
+{
+	struct bpf_iter_target_info *tinfo;
+	bool found = false;
+
+	mutex_lock(&targets_mutex);
+	list_for_each_entry(tinfo, &targets, list) {
+		if (reg_info == tinfo->reg_info) {
+			list_del(&tinfo->list);
+			kfree(tinfo);
+			found = true;
+			break;
+		}
+	}
+	mutex_unlock(&targets_mutex);
+
+	WARN_ON(found == false);
+}
+
+static void cache_btf_id(struct bpf_iter_target_info *tinfo,
+			 struct bpf_prog *prog)
+{
+	tinfo->btf_id = prog->aux->attach_btf_id;
+}
+
+bool bpf_iter_prog_supported(struct bpf_prog *prog)
+{
+	const char *attach_fname = prog->aux->attach_func_name;
+	u32 prog_btf_id = prog->aux->attach_btf_id;
+	const char *prefix = BPF_ITER_FUNC_PREFIX;
+	struct bpf_iter_target_info *tinfo;
+	int prefix_len = strlen(prefix);
+	bool supported = false;
+
+	if (strncmp(attach_fname, prefix, prefix_len))
+		return false;
+
+	mutex_lock(&targets_mutex);
+	list_for_each_entry(tinfo, &targets, list) {
+		if (tinfo->btf_id && tinfo->btf_id == prog_btf_id) {
+			supported = true;
+			break;
+		}
+		if (!strcmp(attach_fname + prefix_len, tinfo->reg_info->target)) {
+			cache_btf_id(tinfo, prog);
+			supported = true;
+			break;
+		}
+	}
+	mutex_unlock(&targets_mutex);
+
+	if (supported) {
+		prog->aux->ctx_arg_info_size = tinfo->reg_info->ctx_arg_info_size;
+		prog->aux->ctx_arg_info = tinfo->reg_info->ctx_arg_info;
+	}
+
+	return supported;
+}
+
+static void bpf_iter_link_release(struct bpf_link *link)
+{
+	struct bpf_iter_link *iter_link =
+		container_of(link, struct bpf_iter_link, link);
+
+	if (iter_link->tinfo->reg_info->detach_target)
+		iter_link->tinfo->reg_info->detach_target(&iter_link->aux);
+}
+
+static void bpf_iter_link_dealloc(struct bpf_link *link)
+{
+	struct bpf_iter_link *iter_link =
+		container_of(link, struct bpf_iter_link, link);
+
+	kfree(iter_link);
+}
+
+static int bpf_iter_link_replace(struct bpf_link *link,
+				 struct bpf_prog *new_prog,
+				 struct bpf_prog *old_prog)
+{
+	int ret = 0;
+
+	mutex_lock(&link_mutex);
+	if (old_prog && link->prog != old_prog) {
+		ret = -EPERM;
+		goto out_unlock;
+	}
+
+	if (link->prog->type != new_prog->type ||
+	    link->prog->expected_attach_type != new_prog->expected_attach_type ||
+	    link->prog->aux->attach_btf_id != new_prog->aux->attach_btf_id) {
+		ret = -EINVAL;
+		goto out_unlock;
+	}
+
+	old_prog = xchg(&link->prog, new_prog);
+	bpf_prog_put(old_prog);
+
+out_unlock:
+	mutex_unlock(&link_mutex);
+	return ret;
+}
+
+static const struct bpf_link_ops bpf_iter_link_lops = {
+	.release = bpf_iter_link_release,
+	.dealloc = bpf_iter_link_dealloc,
+	.update_prog = bpf_iter_link_replace,
+};
+
+bool bpf_link_is_iter(struct bpf_link *link)
+{
+	return link->ops == &bpf_iter_link_lops;
+}
+
+int bpf_iter_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
+{
+	union bpf_iter_link_info __user *ulinfo;
+	struct bpf_link_primer link_primer;
+	struct bpf_iter_target_info *tinfo;
+	union bpf_iter_link_info linfo;
+	struct bpf_iter_link *link;
+	u32 prog_btf_id, linfo_len;
+	bool existed = false;
+	int err;
+
+	if (attr->link_create.target_fd || attr->link_create.flags)
+		return -EINVAL;
+
+	memset(&linfo, 0, sizeof(union bpf_iter_link_info));
+
+	ulinfo = u64_to_user_ptr(attr->link_create.iter_info);
+	linfo_len = attr->link_create.iter_info_len;
+	if (!ulinfo ^ !linfo_len)
+		return -EINVAL;
+
+	if (ulinfo) {
+		err = bpf_check_uarg_tail_zero(ulinfo, sizeof(linfo),
+					       linfo_len);
+		if (err)
+			return err;
+		linfo_len = min_t(u32, linfo_len, sizeof(linfo));
+		if (copy_from_user(&linfo, ulinfo, linfo_len))
+			return -EFAULT;
+	}
+
+	prog_btf_id = prog->aux->attach_btf_id;
+	mutex_lock(&targets_mutex);
+	list_for_each_entry(tinfo, &targets, list) {
+		if (tinfo->btf_id == prog_btf_id) {
+			existed = true;
+			break;
+		}
+	}
+	mutex_unlock(&targets_mutex);
+	if (!existed)
+		return -ENOENT;
+
+	link = kzalloc(sizeof(*link), GFP_USER | __GFP_NOWARN);
+	if (!link)
+		return -ENOMEM;
+
+	bpf_link_init(&link->link, BPF_LINK_TYPE_ITER, &bpf_iter_link_lops, prog);
+	link->tinfo = tinfo;
+
+	err  = bpf_link_prime(&link->link, &link_primer);
+	if (err) {
+		kfree(link);
+		return err;
+	}
+
+	if (tinfo->reg_info->attach_target) {
+		err = tinfo->reg_info->attach_target(prog, &linfo, &link->aux);
+		if (err) {
+			bpf_link_cleanup(&link_primer);
+			return err;
+		}
+	}
+
+	return bpf_link_settle(&link_primer);
+}
+
+static void init_seq_meta(struct bpf_iter_priv_data *priv_data,
+			  struct bpf_iter_target_info *tinfo,
+			  const struct bpf_iter_seq_info *seq_info,
+			  struct bpf_prog *prog)
+{
+	priv_data->tinfo = tinfo;
+	priv_data->seq_info = seq_info;
+	priv_data->prog = prog;
+	priv_data->session_id = atomic64_inc_return(&session_id);
+	priv_data->seq_num = 0;
+	priv_data->done_stop = false;
+}
+
+static int prepare_seq_file(struct file *file, struct bpf_iter_link *link,
+			    const struct bpf_iter_seq_info *seq_info)
+{
+	struct bpf_iter_priv_data *priv_data;
+	struct bpf_iter_target_info *tinfo;
+	struct bpf_prog *prog;
+	u32 total_priv_dsize;
+	struct seq_file *seq;
+	int err = 0;
+
+	mutex_lock(&link_mutex);
+	prog = link->link.prog;
+	bpf_prog_inc(prog);
+	mutex_unlock(&link_mutex);
+
+	tinfo = link->tinfo;
+	total_priv_dsize = offsetof(struct bpf_iter_priv_data, target_private) +
+			   seq_info->seq_priv_size;
+	priv_data = __seq_open_private(file, seq_info->seq_ops,
+				       total_priv_dsize);
+	if (!priv_data) {
+		err = -ENOMEM;
+		goto release_prog;
+	}
+
+	if (seq_info->init_seq_private) {
+		err = seq_info->init_seq_private(priv_data->target_private, &link->aux);
+		if (err)
+			goto release_seq_file;
+	}
+
+	init_seq_meta(priv_data, tinfo, seq_info, prog);
+	seq = file->private_data;
+	seq->private = priv_data->target_private;
+
+	return 0;
+
+release_seq_file:
+	seq_release_private(file->f_inode, file);
+	file->private_data = NULL;
+release_prog:
+	bpf_prog_put(prog);
+	return err;
+}
+
+int bpf_iter_new_fd(struct bpf_link *link)
+{
+	struct bpf_iter_link *iter_link;
+	struct file *file;
+	unsigned int flags;
+	int err, fd;
+
+	if (link->ops != &bpf_iter_link_lops)
+		return -EINVAL;
+
+	flags = O_RDONLY | O_CLOEXEC;
+	fd = get_unused_fd_flags(flags);
+	if (fd < 0)
+		return fd;
+
+	file = anon_inode_getfile("bpf_iter", &bpf_iter_fops, NULL, flags);
+	if (IS_ERR(file)) {
+		err = PTR_ERR(file);
+		goto free_fd;
+	}
+
+	iter_link = container_of(link, struct bpf_iter_link, link);
+	err = prepare_seq_file(file, iter_link, __get_seq_info(iter_link));
+	if (err)
+		goto free_file;
+
+	fd_install(fd, file);
+	return fd;
+
+free_file:
+	fput(file);
+free_fd:
+	put_unused_fd(fd);
+	return err;
+}
+
+struct bpf_prog *bpf_iter_get_info(struct bpf_iter_meta *meta, bool in_stop)
+{
+	struct bpf_iter_priv_data *iter_priv;
+	struct seq_file *seq;
+	void *seq_priv;
+
+	seq = meta->seq;
+	if (seq->file->f_op != &bpf_iter_fops)
+		return NULL;
+
+	seq_priv = seq->private;
+	iter_priv = container_of(seq_priv, struct bpf_iter_priv_data,
+				 target_private);
+
+	if (in_stop && iter_priv->done_stop)
+		return NULL;
+
+	meta->session_id = iter_priv->session_id;
+	meta->seq_num = iter_priv->seq_num;
+
+	return iter_priv->prog;
+}
+
+int bpf_iter_run_prog(struct bpf_prog *prog, void *ctx)
+{
+	int ret;
+
+	rcu_read_lock();
+	migrate_disable();
+	ret = BPF_PROG_RUN(prog, ctx);
+	migrate_enable();
+	rcu_read_unlock();
+
+	/* bpf program can only return 0 or 1:
+	 *  0 : okay
+	 *  1 : retry the same object
+	 * The bpf_iter_run_prog() return value
+	 * will be seq_ops->show() return value.
+	 */
+	return ret == 0 ? 0 : -EAGAIN;
+}
diff --git a/kernel/bpf/bpf_lru_list.h b/kernel/bpf/bpf_lru_list.h
index f02504640e18..6b12f06ee18c 100644
--- a/kernel/bpf/bpf_lru_list.h
+++ b/kernel/bpf/bpf_lru_list.h
@@ -30,7 +30,7 @@ struct bpf_lru_node {
 struct bpf_lru_list {
 	struct list_head lists[NR_BPF_LRU_LIST_T];
 	unsigned int counts[NR_BPF_LRU_LIST_COUNT];
-	/* The next inacitve list rotation starts from here */
+	/* The next inactive list rotation starts from here */
 	struct list_head *next_inactive_rotation;
 
 	raw_spinlock_t lock ____cacheline_aligned_in_smp;
diff --git a/kernel/bpf/bpf_lsm.c b/kernel/bpf/bpf_lsm.c
new file mode 100644
index 000000000000..fb278144e9fd
--- /dev/null
+++ b/kernel/bpf/bpf_lsm.c
@@ -0,0 +1,54 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Copyright (C) 2020 Google LLC.
+ */
+
+#include <linux/filter.h>
+#include <linux/bpf.h>
+#include <linux/btf.h>
+#include <linux/lsm_hooks.h>
+#include <linux/bpf_lsm.h>
+#include <linux/kallsyms.h>
+#include <linux/bpf_verifier.h>
+
+/* For every LSM hook that allows attachment of BPF programs, declare a nop
+ * function where a BPF program can be attached.
+ */
+#define LSM_HOOK(RET, DEFAULT, NAME, ...)	\
+noinline RET bpf_lsm_##NAME(__VA_ARGS__)	\
+{						\
+	return DEFAULT;				\
+}
+
+#include <linux/lsm_hook_defs.h>
+#undef LSM_HOOK
+
+#define BPF_LSM_SYM_PREFX  "bpf_lsm_"
+
+int bpf_lsm_verify_prog(struct bpf_verifier_log *vlog,
+			const struct bpf_prog *prog)
+{
+	if (!prog->gpl_compatible) {
+		bpf_log(vlog,
+			"LSM programs must have a GPL compatible license\n");
+		return -EINVAL;
+	}
+
+	if (strncmp(BPF_LSM_SYM_PREFX, prog->aux->attach_func_name,
+		    sizeof(BPF_LSM_SYM_PREFX) - 1)) {
+		bpf_log(vlog, "attach_btf_id %u points to wrong type name %s\n",
+			prog->aux->attach_btf_id, prog->aux->attach_func_name);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+const struct bpf_prog_ops lsm_prog_ops = {
+};
+
+const struct bpf_verifier_ops lsm_verifier_ops = {
+	.get_func_proto = tracing_prog_func_proto,
+	.is_valid_access = btf_ctx_access,
+};
diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c
index 042f95534f86..969c5d47f81f 100644
--- a/kernel/bpf/bpf_struct_ops.c
+++ b/kernel/bpf/bpf_struct_ops.c
@@ -23,7 +23,7 @@ enum bpf_struct_ops_state {
 
 struct bpf_struct_ops_value {
 	BPF_STRUCT_OPS_COMMON_VALUE;
-	char data[0] ____cacheline_aligned_in_smp;
+	char data[] ____cacheline_aligned_in_smp;
 };
 
 struct bpf_struct_ops_map {
@@ -320,6 +320,7 @@ static int bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key,
 	struct bpf_struct_ops_value *uvalue, *kvalue;
 	const struct btf_member *member;
 	const struct btf_type *t = st_ops->type;
+	struct bpf_tramp_progs *tprogs = NULL;
 	void *udata, *kdata;
 	int prog_fd, err = 0;
 	void *image;
@@ -343,6 +344,10 @@ static int bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key,
 	if (uvalue->state || refcount_read(&uvalue->refcnt))
 		return -EINVAL;
 
+	tprogs = kcalloc(BPF_TRAMP_MAX, sizeof(*tprogs), GFP_KERNEL);
+	if (!tprogs)
+		return -ENOMEM;
+
 	uvalue = (struct bpf_struct_ops_value *)st_map->uvalue;
 	kvalue = (struct bpf_struct_ops_value *)&st_map->kvalue;
 
@@ -425,10 +430,12 @@ static int bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key,
 			goto reset_unlock;
 		}
 
+		tprogs[BPF_TRAMP_FENTRY].progs[0] = prog;
+		tprogs[BPF_TRAMP_FENTRY].nr_progs = 1;
 		err = arch_prepare_bpf_trampoline(image,
 						  st_map->image + PAGE_SIZE,
 						  &st_ops->func_models[i], 0,
-						  &prog, 1, NULL, 0, NULL);
+						  tprogs, NULL);
 		if (err < 0)
 			goto reset_unlock;
 
@@ -469,6 +476,7 @@ reset_unlock:
 	memset(uvalue, 0, map->value_size);
 	memset(kvalue, 0, map->value_size);
 unlock:
+	kfree(tprogs);
 	mutex_unlock(&st_map->lock);
 	return err;
 }
@@ -482,13 +490,21 @@ static int bpf_struct_ops_map_delete_elem(struct bpf_map *map, void *key)
 	prev_state = cmpxchg(&st_map->kvalue.state,
 			     BPF_STRUCT_OPS_STATE_INUSE,
 			     BPF_STRUCT_OPS_STATE_TOBEFREE);
-	if (prev_state == BPF_STRUCT_OPS_STATE_INUSE) {
+	switch (prev_state) {
+	case BPF_STRUCT_OPS_STATE_INUSE:
 		st_map->st_ops->unreg(&st_map->kvalue.data);
 		if (refcount_dec_and_test(&st_map->kvalue.refcnt))
 			bpf_map_put(map);
+		return 0;
+	case BPF_STRUCT_OPS_STATE_TOBEFREE:
+		return -EINPROGRESS;
+	case BPF_STRUCT_OPS_STATE_INIT:
+		return -ENOENT;
+	default:
+		WARN_ON_ONCE(1);
+		/* Should never happen.  Treat it as not found. */
+		return -ENOENT;
 	}
-
-	return 0;
 }
 
 static void bpf_struct_ops_map_seq_show_elem(struct bpf_map *map, void *key,
@@ -541,7 +557,7 @@ static struct bpf_map *bpf_struct_ops_map_alloc(union bpf_attr *attr)
 	struct bpf_map *map;
 	int err;
 
-	if (!capable(CAP_SYS_ADMIN))
+	if (!bpf_capable())
 		return ERR_PTR(-EPERM);
 
 	st_ops = bpf_struct_ops_find_value(attr->btf_vmlinux_value_type_id);
@@ -595,6 +611,7 @@ static struct bpf_map *bpf_struct_ops_map_alloc(union bpf_attr *attr)
 	return map;
 }
 
+static int bpf_struct_ops_map_btf_id;
 const struct bpf_map_ops bpf_struct_ops_map_ops = {
 	.map_alloc_check = bpf_struct_ops_map_alloc_check,
 	.map_alloc = bpf_struct_ops_map_alloc,
@@ -604,6 +621,8 @@ const struct bpf_map_ops bpf_struct_ops_map_ops = {
 	.map_delete_elem = bpf_struct_ops_map_delete_elem,
 	.map_update_elem = bpf_struct_ops_map_update_elem,
 	.map_seq_show_elem = bpf_struct_ops_map_seq_show_elem,
+	.map_btf_name = "bpf_struct_ops_map",
+	.map_btf_id = &bpf_struct_ops_map_btf_id,
 };
 
 /* "const void *" because some subsystem is
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 787140095e58..91afdd4c82e3 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -18,6 +18,7 @@
 #include <linux/sort.h>
 #include <linux/bpf_verifier.h>
 #include <linux/btf.h>
+#include <linux/btf_ids.h>
 #include <linux/skmsg.h>
 #include <linux/perf_event.h>
 #include <net/sock.h>
@@ -2418,7 +2419,7 @@ static int btf_enum_check_member(struct btf_verifier_env *env,
 
 	struct_size = struct_type->size;
 	bytes_offset = BITS_ROUNDDOWN_BYTES(struct_bits_off);
-	if (struct_size - bytes_offset < sizeof(int)) {
+	if (struct_size - bytes_offset < member_type->size) {
 		btf_verifier_log_member(env, struct_type, member,
 					"Member exceeds struct_size");
 		return -EINVAL;
@@ -3477,11 +3478,12 @@ errout:
 	return ERR_PTR(err);
 }
 
-extern char __weak _binary__btf_vmlinux_bin_start[];
-extern char __weak _binary__btf_vmlinux_bin_end[];
+extern char __weak __start_BTF[];
+extern char __weak __stop_BTF[];
 extern struct btf *btf_vmlinux;
 
 #define BPF_MAP_TYPE(_id, _ops)
+#define BPF_LINK_TYPE(_id, _name)
 static union {
 	struct bpf_ctx_convert {
 #define BPF_PROG_TYPE(_id, _name, prog_ctx_type, kern_ctx_type) \
@@ -3508,6 +3510,7 @@ static u8 bpf_ctx_convert_map[] = {
 	0, /* avoid empty array */
 };
 #undef BPF_MAP_TYPE
+#undef BPF_LINK_TYPE
 
 static const struct btf_member *
 btf_get_prog_ctx_type(struct bpf_verifier_log *log, struct btf *btf,
@@ -3569,6 +3572,41 @@ btf_get_prog_ctx_type(struct bpf_verifier_log *log, struct btf *btf,
 	return ctx_type;
 }
 
+static const struct bpf_map_ops * const btf_vmlinux_map_ops[] = {
+#define BPF_PROG_TYPE(_id, _name, prog_ctx_type, kern_ctx_type)
+#define BPF_LINK_TYPE(_id, _name)
+#define BPF_MAP_TYPE(_id, _ops) \
+	[_id] = &_ops,
+#include <linux/bpf_types.h>
+#undef BPF_PROG_TYPE
+#undef BPF_LINK_TYPE
+#undef BPF_MAP_TYPE
+};
+
+static int btf_vmlinux_map_ids_init(const struct btf *btf,
+				    struct bpf_verifier_log *log)
+{
+	const struct bpf_map_ops *ops;
+	int i, btf_id;
+
+	for (i = 0; i < ARRAY_SIZE(btf_vmlinux_map_ops); ++i) {
+		ops = btf_vmlinux_map_ops[i];
+		if (!ops || (!ops->map_btf_name && !ops->map_btf_id))
+			continue;
+		if (!ops->map_btf_name || !ops->map_btf_id) {
+			bpf_log(log, "map type %d is misconfigured\n", i);
+			return -EINVAL;
+		}
+		btf_id = btf_find_by_name_kind(btf, ops->map_btf_name,
+					       BTF_KIND_STRUCT);
+		if (btf_id < 0)
+			return btf_id;
+		*ops->map_btf_id = btf_id;
+	}
+
+	return 0;
+}
+
 static int btf_translate_to_vmlinux(struct bpf_verifier_log *log,
 				     struct btf *btf,
 				     const struct btf_type *t,
@@ -3584,12 +3622,15 @@ static int btf_translate_to_vmlinux(struct bpf_verifier_log *log,
 	return kern_ctx_type->type;
 }
 
+BTF_ID_LIST(bpf_ctx_convert_btf_id)
+BTF_ID(struct, bpf_ctx_convert)
+
 struct btf *btf_parse_vmlinux(void)
 {
 	struct btf_verifier_env *env = NULL;
 	struct bpf_verifier_log *log;
 	struct btf *btf = NULL;
-	int err, i;
+	int err;
 
 	env = kzalloc(sizeof(*env), GFP_KERNEL | __GFP_NOWARN);
 	if (!env)
@@ -3605,9 +3646,8 @@ struct btf *btf_parse_vmlinux(void)
 	}
 	env->btf = btf;
 
-	btf->data = _binary__btf_vmlinux_bin_start;
-	btf->data_size = _binary__btf_vmlinux_bin_end -
-		_binary__btf_vmlinux_bin_start;
+	btf->data = __start_BTF;
+	btf->data_size = __stop_BTF - __start_BTF;
 
 	err = btf_parse_hdr(env);
 	if (err)
@@ -3623,25 +3663,13 @@ struct btf *btf_parse_vmlinux(void)
 	if (err)
 		goto errout;
 
-	/* find struct bpf_ctx_convert for type checking later */
-	for (i = 1; i <= btf->nr_types; i++) {
-		const struct btf_type *t;
-		const char *tname;
+	/* btf_parse_vmlinux() runs under bpf_verifier_lock */
+	bpf_ctx_convert.t = btf_type_by_id(btf, bpf_ctx_convert_btf_id[0]);
 
-		t = btf_type_by_id(btf, i);
-		if (!__btf_type_is_struct(t))
-			continue;
-		tname = __btf_name_by_offset(btf, t->name_off);
-		if (!strcmp(tname, "bpf_ctx_convert")) {
-			/* btf_parse_vmlinux() runs under bpf_verifier_lock */
-			bpf_ctx_convert.t = t;
-			break;
-		}
-	}
-	if (i > btf->nr_types) {
-		err = -ENOENT;
+	/* find bpf map structs for map_ptr access checking */
+	err = btf_vmlinux_map_ids_init(btf, log);
+	if (err < 0)
 		goto errout;
-	}
 
 	bpf_struct_ops_init(btf, log);
 
@@ -3693,7 +3721,7 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type,
 	struct bpf_verifier_log *log = info->log;
 	const struct btf_param *args;
 	u32 nr_args, arg;
-	int ret;
+	int i, ret;
 
 	if (off % 8) {
 		bpf_log(log, "func '%s' offset %d is not multiple of 8\n",
@@ -3710,27 +3738,64 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type,
 		nr_args--;
 	}
 
-	if (prog->expected_attach_type == BPF_TRACE_FEXIT &&
-	    arg == nr_args) {
-		if (!t)
-			/* Default prog with 5 args. 6th arg is retval. */
-			return true;
-		/* function return type */
-		t = btf_type_by_id(btf, t->type);
-	} else if (arg >= nr_args) {
+	if (arg > nr_args) {
 		bpf_log(log, "func '%s' doesn't have %d-th argument\n",
 			tname, arg + 1);
 		return false;
+	}
+
+	if (arg == nr_args) {
+		switch (prog->expected_attach_type) {
+		case BPF_LSM_MAC:
+		case BPF_TRACE_FEXIT:
+			/* When LSM programs are attached to void LSM hooks
+			 * they use FEXIT trampolines and when attached to
+			 * int LSM hooks, they use MODIFY_RETURN trampolines.
+			 *
+			 * While the LSM programs are BPF_MODIFY_RETURN-like
+			 * the check:
+			 *
+			 *	if (ret_type != 'int')
+			 *		return -EINVAL;
+			 *
+			 * is _not_ done here. This is still safe as LSM hooks
+			 * have only void and int return types.
+			 */
+			if (!t)
+				return true;
+			t = btf_type_by_id(btf, t->type);
+			break;
+		case BPF_MODIFY_RETURN:
+			/* For now the BPF_MODIFY_RETURN can only be attached to
+			 * functions that return an int.
+			 */
+			if (!t)
+				return false;
+
+			t = btf_type_skip_modifiers(btf, t->type, NULL);
+			if (!btf_type_is_small_int(t)) {
+				bpf_log(log,
+					"ret type %s not allowed for fmod_ret\n",
+					btf_kind_str[BTF_INFO_KIND(t->info)]);
+				return false;
+			}
+			break;
+		default:
+			bpf_log(log, "func '%s' doesn't have %d-th argument\n",
+				tname, arg + 1);
+			return false;
+		}
 	} else {
 		if (!t)
 			/* Default prog with 5 args */
 			return true;
 		t = btf_type_by_id(btf, args[arg].type);
 	}
+
 	/* skip modifiers */
 	while (btf_type_is_modifier(t))
 		t = btf_type_by_id(btf, t->type);
-	if (btf_type_is_int(t) || btf_type_is_enum(t))
+	if (btf_type_is_small_int(t) || btf_type_is_enum(t))
 		/* accessing a scalar */
 		return true;
 	if (!btf_type_is_ptr(t)) {
@@ -3741,6 +3806,19 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type,
 			btf_kind_str[BTF_INFO_KIND(t->info)]);
 		return false;
 	}
+
+	/* check for PTR_TO_RDONLY_BUF_OR_NULL or PTR_TO_RDWR_BUF_OR_NULL */
+	for (i = 0; i < prog->aux->ctx_arg_info_size; i++) {
+		const struct bpf_ctx_arg_aux *ctx_arg_info = &prog->aux->ctx_arg_info[i];
+
+		if (ctx_arg_info->offset == off &&
+		    (ctx_arg_info->reg_type == PTR_TO_RDONLY_BUF_OR_NULL ||
+		     ctx_arg_info->reg_type == PTR_TO_RDWR_BUF_OR_NULL)) {
+			info->reg_type = ctx_arg_info->reg_type;
+			return true;
+		}
+	}
+
 	if (t->type == 0)
 		/* This is a pointer to void.
 		 * It is the same as scalar from the verifier safety pov.
@@ -3752,8 +3830,17 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type,
 		return true;
 
 	/* this is a pointer to another type */
-	info->reg_type = PTR_TO_BTF_ID;
+	for (i = 0; i < prog->aux->ctx_arg_info_size; i++) {
+		const struct bpf_ctx_arg_aux *ctx_arg_info = &prog->aux->ctx_arg_info[i];
+
+		if (ctx_arg_info->offset == off) {
+			info->reg_type = ctx_arg_info->reg_type;
+			info->btf_id = ctx_arg_info->btf_id;
+			return true;
+		}
+	}
 
+	info->reg_type = PTR_TO_BTF_ID;
 	if (tgt_prog) {
 		ret = btf_translate_to_vmlinux(log, btf, t, tgt_prog->type, arg);
 		if (ret > 0) {
@@ -3792,6 +3879,7 @@ int btf_struct_access(struct bpf_verifier_log *log,
 	const struct btf_type *mtype, *elem_type = NULL;
 	const struct btf_member *member;
 	const char *tname, *mname;
+	u32 vlen;
 
 again:
 	tname = __btf_name_by_offset(btf_vmlinux, t->name_off);
@@ -3800,7 +3888,43 @@ again:
 		return -EINVAL;
 	}
 
+	vlen = btf_type_vlen(t);
 	if (off + size > t->size) {
+		/* If the last element is a variable size array, we may
+		 * need to relax the rule.
+		 */
+		struct btf_array *array_elem;
+
+		if (vlen == 0)
+			goto error;
+
+		member = btf_type_member(t) + vlen - 1;
+		mtype = btf_type_skip_modifiers(btf_vmlinux, member->type,
+						NULL);
+		if (!btf_type_is_array(mtype))
+			goto error;
+
+		array_elem = (struct btf_array *)(mtype + 1);
+		if (array_elem->nelems != 0)
+			goto error;
+
+		moff = btf_member_bit_offset(t, member) / 8;
+		if (off < moff)
+			goto error;
+
+		/* Only allow structure for now, can be relaxed for
+		 * other types later.
+		 */
+		elem_type = btf_type_skip_modifiers(btf_vmlinux,
+						    array_elem->type, NULL);
+		if (!btf_type_is_struct(elem_type))
+			goto error;
+
+		off = (off - moff) % elem_type->size;
+		return btf_struct_access(log, elem_type, off, size, atype,
+					 next_btf_id);
+
+error:
 		bpf_log(log, "access beyond struct %s at off %u size %u\n",
 			tname, off, size);
 		return -EACCES;
@@ -3966,96 +4090,17 @@ again:
 	return -EINVAL;
 }
 
-static int __btf_resolve_helper_id(struct bpf_verifier_log *log, void *fn,
-				   int arg)
-{
-	char fnname[KSYM_SYMBOL_LEN + 4] = "btf_";
-	const struct btf_param *args;
-	const struct btf_type *t;
-	const char *tname, *sym;
-	u32 btf_id, i;
-
-	if (IS_ERR(btf_vmlinux)) {
-		bpf_log(log, "btf_vmlinux is malformed\n");
-		return -EINVAL;
-	}
-
-	sym = kallsyms_lookup((long)fn, NULL, NULL, NULL, fnname + 4);
-	if (!sym) {
-		bpf_log(log, "kernel doesn't have kallsyms\n");
-		return -EFAULT;
-	}
-
-	for (i = 1; i <= btf_vmlinux->nr_types; i++) {
-		t = btf_type_by_id(btf_vmlinux, i);
-		if (BTF_INFO_KIND(t->info) != BTF_KIND_TYPEDEF)
-			continue;
-		tname = __btf_name_by_offset(btf_vmlinux, t->name_off);
-		if (!strcmp(tname, fnname))
-			break;
-	}
-	if (i > btf_vmlinux->nr_types) {
-		bpf_log(log, "helper %s type is not found\n", fnname);
-		return -ENOENT;
-	}
-
-	t = btf_type_by_id(btf_vmlinux, t->type);
-	if (!btf_type_is_ptr(t))
-		return -EFAULT;
-	t = btf_type_by_id(btf_vmlinux, t->type);
-	if (!btf_type_is_func_proto(t))
-		return -EFAULT;
-
-	args = (const struct btf_param *)(t + 1);
-	if (arg >= btf_type_vlen(t)) {
-		bpf_log(log, "bpf helper %s doesn't have %d-th argument\n",
-			fnname, arg);
-		return -EINVAL;
-	}
-
-	t = btf_type_by_id(btf_vmlinux, args[arg].type);
-	if (!btf_type_is_ptr(t) || !t->type) {
-		/* anything but the pointer to struct is a helper config bug */
-		bpf_log(log, "ARG_PTR_TO_BTF is misconfigured\n");
-		return -EFAULT;
-	}
-	btf_id = t->type;
-	t = btf_type_by_id(btf_vmlinux, t->type);
-	/* skip modifiers */
-	while (btf_type_is_modifier(t)) {
-		btf_id = t->type;
-		t = btf_type_by_id(btf_vmlinux, t->type);
-	}
-	if (!btf_type_is_struct(t)) {
-		bpf_log(log, "ARG_PTR_TO_BTF is not a struct\n");
-		return -EFAULT;
-	}
-	bpf_log(log, "helper %s arg%d has btf_id %d struct %s\n", fnname + 4,
-		arg, btf_id, __btf_name_by_offset(btf_vmlinux, t->name_off));
-	return btf_id;
-}
-
 int btf_resolve_helper_id(struct bpf_verifier_log *log,
 			  const struct bpf_func_proto *fn, int arg)
 {
-	int *btf_id = &fn->btf_id[arg];
-	int ret;
+	int id;
 
-	if (fn->arg_type[arg] != ARG_PTR_TO_BTF_ID)
+	if (fn->arg_type[arg] != ARG_PTR_TO_BTF_ID || !btf_vmlinux)
 		return -EINVAL;
-
-	ret = READ_ONCE(*btf_id);
-	if (ret)
-		return ret;
-	/* ok to race the search. The result is the same */
-	ret = __btf_resolve_helper_id(log, fn->func, arg);
-	if (!ret) {
-		/* Function argument cannot be type 'void' */
-		bpf_log(log, "BTF resolution bug\n");
-		return -EFAULT;
-	}
-	WRITE_ONCE(*btf_id, ret);
-	return ret;
+	id = fn->btf_id[arg];
+	if (!id || id > btf_vmlinux->nr_types)
+		return -EINVAL;
+	return id;
 }
 
 static int __get_type_size(struct btf *btf, u32 btf_id,
@@ -4564,7 +4609,7 @@ int btf_get_info_by_fd(const struct btf *btf,
 		       union bpf_attr __user *uattr)
 {
 	struct bpf_btf_info __user *uinfo;
-	struct bpf_btf_info info = {};
+	struct bpf_btf_info info;
 	u32 info_copy, btf_copy;
 	void __user *ubtf;
 	u32 uinfo_len;
@@ -4573,6 +4618,7 @@ int btf_get_info_by_fd(const struct btf *btf,
 	uinfo_len = attr->info.info_len;
 
 	info_copy = min_t(u32, uinfo_len, sizeof(info));
+	memset(&info, 0, sizeof(info));
 	if (copy_from_user(&info, uinfo, info_copy))
 		return -EFAULT;
 
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index 9a500fadbef5..e21de4f1754c 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -28,6 +28,78 @@ void cgroup_bpf_offline(struct cgroup *cgrp)
 	percpu_ref_kill(&cgrp->bpf.refcnt);
 }
 
+static void bpf_cgroup_storages_free(struct bpf_cgroup_storage *storages[])
+{
+	enum bpf_cgroup_storage_type stype;
+
+	for_each_cgroup_storage_type(stype)
+		bpf_cgroup_storage_free(storages[stype]);
+}
+
+static int bpf_cgroup_storages_alloc(struct bpf_cgroup_storage *storages[],
+				     struct bpf_cgroup_storage *new_storages[],
+				     enum bpf_attach_type type,
+				     struct bpf_prog *prog,
+				     struct cgroup *cgrp)
+{
+	enum bpf_cgroup_storage_type stype;
+	struct bpf_cgroup_storage_key key;
+	struct bpf_map *map;
+
+	key.cgroup_inode_id = cgroup_id(cgrp);
+	key.attach_type = type;
+
+	for_each_cgroup_storage_type(stype) {
+		map = prog->aux->cgroup_storage[stype];
+		if (!map)
+			continue;
+
+		storages[stype] = cgroup_storage_lookup((void *)map, &key, false);
+		if (storages[stype])
+			continue;
+
+		storages[stype] = bpf_cgroup_storage_alloc(prog, stype);
+		if (IS_ERR(storages[stype])) {
+			bpf_cgroup_storages_free(new_storages);
+			return -ENOMEM;
+		}
+
+		new_storages[stype] = storages[stype];
+	}
+
+	return 0;
+}
+
+static void bpf_cgroup_storages_assign(struct bpf_cgroup_storage *dst[],
+				       struct bpf_cgroup_storage *src[])
+{
+	enum bpf_cgroup_storage_type stype;
+
+	for_each_cgroup_storage_type(stype)
+		dst[stype] = src[stype];
+}
+
+static void bpf_cgroup_storages_link(struct bpf_cgroup_storage *storages[],
+				     struct cgroup *cgrp,
+				     enum bpf_attach_type attach_type)
+{
+	enum bpf_cgroup_storage_type stype;
+
+	for_each_cgroup_storage_type(stype)
+		bpf_cgroup_storage_link(storages[stype], cgrp, attach_type);
+}
+
+/* Called when bpf_cgroup_link is auto-detached from dying cgroup.
+ * It drops cgroup and bpf_prog refcounts, and marks bpf_link as defunct. It
+ * doesn't free link memory, which will eventually be done by bpf_link's
+ * release() callback, when its last FD is closed.
+ */
+static void bpf_cgroup_link_auto_detach(struct bpf_cgroup_link *link)
+{
+	cgroup_put(link->cgroup);
+	link->cgroup = NULL;
+}
+
 /**
  * cgroup_bpf_release() - put references of all bpf programs and
  *                        release all cgroup bpf data
@@ -37,23 +109,24 @@ static void cgroup_bpf_release(struct work_struct *work)
 {
 	struct cgroup *p, *cgrp = container_of(work, struct cgroup,
 					       bpf.release_work);
-	enum bpf_cgroup_storage_type stype;
 	struct bpf_prog_array *old_array;
+	struct list_head *storages = &cgrp->bpf.storages;
+	struct bpf_cgroup_storage *storage, *stmp;
+
 	unsigned int type;
 
 	mutex_lock(&cgroup_mutex);
 
 	for (type = 0; type < ARRAY_SIZE(cgrp->bpf.progs); type++) {
 		struct list_head *progs = &cgrp->bpf.progs[type];
-		struct bpf_prog_list *pl, *tmp;
+		struct bpf_prog_list *pl, *pltmp;
 
-		list_for_each_entry_safe(pl, tmp, progs, node) {
+		list_for_each_entry_safe(pl, pltmp, progs, node) {
 			list_del(&pl->node);
-			bpf_prog_put(pl->prog);
-			for_each_cgroup_storage_type(stype) {
-				bpf_cgroup_storage_unlink(pl->storage[stype]);
-				bpf_cgroup_storage_free(pl->storage[stype]);
-			}
+			if (pl->prog)
+				bpf_prog_put(pl->prog);
+			if (pl->link)
+				bpf_cgroup_link_auto_detach(pl->link);
 			kfree(pl);
 			static_branch_dec(&cgroup_bpf_enabled_key);
 		}
@@ -63,6 +136,11 @@ static void cgroup_bpf_release(struct work_struct *work)
 		bpf_prog_array_free(old_array);
 	}
 
+	list_for_each_entry_safe(storage, stmp, storages, list_cg) {
+		bpf_cgroup_storage_unlink(storage);
+		bpf_cgroup_storage_free(storage);
+	}
+
 	mutex_unlock(&cgroup_mutex);
 
 	for (p = cgroup_parent(cgrp); p; p = cgroup_parent(p))
@@ -85,6 +163,18 @@ static void cgroup_bpf_release_fn(struct percpu_ref *ref)
 	queue_work(system_wq, &cgrp->bpf.release_work);
 }
 
+/* Get underlying bpf_prog of bpf_prog_list entry, regardless if it's through
+ * link or direct prog.
+ */
+static struct bpf_prog *prog_list_prog(struct bpf_prog_list *pl)
+{
+	if (pl->prog)
+		return pl->prog;
+	if (pl->link)
+		return pl->link->link.prog;
+	return NULL;
+}
+
 /* count number of elements in the list.
  * it's slow but the list cannot be long
  */
@@ -94,7 +184,7 @@ static u32 prog_list_length(struct list_head *head)
 	u32 cnt = 0;
 
 	list_for_each_entry(pl, head, node) {
-		if (!pl->prog)
+		if (!prog_list_prog(pl))
 			continue;
 		cnt++;
 	}
@@ -138,7 +228,7 @@ static int compute_effective_progs(struct cgroup *cgrp,
 				   enum bpf_attach_type type,
 				   struct bpf_prog_array **array)
 {
-	enum bpf_cgroup_storage_type stype;
+	struct bpf_prog_array_item *item;
 	struct bpf_prog_array *progs;
 	struct bpf_prog_list *pl;
 	struct cgroup *p = cgrp;
@@ -163,13 +253,13 @@ static int compute_effective_progs(struct cgroup *cgrp,
 			continue;
 
 		list_for_each_entry(pl, &p->bpf.progs[type], node) {
-			if (!pl->prog)
+			if (!prog_list_prog(pl))
 				continue;
 
-			progs->items[cnt].prog = pl->prog;
-			for_each_cgroup_storage_type(stype)
-				progs->items[cnt].cgroup_storage[stype] =
-					pl->storage[stype];
+			item = &progs->items[cnt];
+			item->prog = prog_list_prog(pl);
+			bpf_cgroup_storages_assign(item->cgroup_storage,
+						   pl->storage);
 			cnt++;
 		}
 	} while ((p = cgroup_parent(p)));
@@ -215,6 +305,8 @@ int cgroup_bpf_inherit(struct cgroup *cgrp)
 	for (i = 0; i < NR; i++)
 		INIT_LIST_HEAD(&cgrp->bpf.progs[i]);
 
+	INIT_LIST_HEAD(&cgrp->bpf.storages);
+
 	for (i = 0; i < NR; i++)
 		if (compute_effective_progs(cgrp, i, &arrays[i]))
 			goto cleanup;
@@ -227,6 +319,9 @@ cleanup:
 	for (i = 0; i < NR; i++)
 		bpf_prog_array_free(arrays[i]);
 
+	for (p = cgroup_parent(cgrp); p; p = cgroup_parent(p))
+		cgroup_bpf_put(p);
+
 	percpu_ref_exit(&cgrp->bpf.refcnt);
 
 	return -ENOMEM;
@@ -284,34 +379,80 @@ cleanup:
 
 #define BPF_CGROUP_MAX_PROGS 64
 
+static struct bpf_prog_list *find_attach_entry(struct list_head *progs,
+					       struct bpf_prog *prog,
+					       struct bpf_cgroup_link *link,
+					       struct bpf_prog *replace_prog,
+					       bool allow_multi)
+{
+	struct bpf_prog_list *pl;
+
+	/* single-attach case */
+	if (!allow_multi) {
+		if (list_empty(progs))
+			return NULL;
+		return list_first_entry(progs, typeof(*pl), node);
+	}
+
+	list_for_each_entry(pl, progs, node) {
+		if (prog && pl->prog == prog && prog != replace_prog)
+			/* disallow attaching the same prog twice */
+			return ERR_PTR(-EINVAL);
+		if (link && pl->link == link)
+			/* disallow attaching the same link twice */
+			return ERR_PTR(-EINVAL);
+	}
+
+	/* direct prog multi-attach w/ replacement case */
+	if (replace_prog) {
+		list_for_each_entry(pl, progs, node) {
+			if (pl->prog == replace_prog)
+				/* a match found */
+				return pl;
+		}
+		/* prog to replace not found for cgroup */
+		return ERR_PTR(-ENOENT);
+	}
+
+	return NULL;
+}
+
 /**
- * __cgroup_bpf_attach() - Attach the program to a cgroup, and
+ * __cgroup_bpf_attach() - Attach the program or the link to a cgroup, and
  *                         propagate the change to descendants
  * @cgrp: The cgroup which descendants to traverse
  * @prog: A program to attach
+ * @link: A link to attach
  * @replace_prog: Previously attached program to replace if BPF_F_REPLACE is set
  * @type: Type of attach operation
  * @flags: Option flags
  *
+ * Exactly one of @prog or @link can be non-null.
  * Must be called with cgroup_mutex held.
  */
-int __cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog,
-			struct bpf_prog *replace_prog,
+int __cgroup_bpf_attach(struct cgroup *cgrp,
+			struct bpf_prog *prog, struct bpf_prog *replace_prog,
+			struct bpf_cgroup_link *link,
 			enum bpf_attach_type type, u32 flags)
 {
 	u32 saved_flags = (flags & (BPF_F_ALLOW_OVERRIDE | BPF_F_ALLOW_MULTI));
 	struct list_head *progs = &cgrp->bpf.progs[type];
 	struct bpf_prog *old_prog = NULL;
-	struct bpf_cgroup_storage *storage[MAX_BPF_CGROUP_STORAGE_TYPE],
-		*old_storage[MAX_BPF_CGROUP_STORAGE_TYPE] = {NULL};
-	struct bpf_prog_list *pl, *replace_pl = NULL;
-	enum bpf_cgroup_storage_type stype;
+	struct bpf_cgroup_storage *storage[MAX_BPF_CGROUP_STORAGE_TYPE] = {};
+	struct bpf_cgroup_storage *new_storage[MAX_BPF_CGROUP_STORAGE_TYPE] = {};
+	struct bpf_prog_list *pl;
 	int err;
 
 	if (((flags & BPF_F_ALLOW_OVERRIDE) && (flags & BPF_F_ALLOW_MULTI)) ||
 	    ((flags & BPF_F_REPLACE) && !(flags & BPF_F_ALLOW_MULTI)))
 		/* invalid combination */
 		return -EINVAL;
+	if (link && (prog || replace_prog))
+		/* only either link or prog/replace_prog can be specified */
+		return -EINVAL;
+	if (!!replace_prog != !!(flags & BPF_F_REPLACE))
+		/* replace_prog implies BPF_F_REPLACE, and vice versa */
+		return -EINVAL;
 
 	if (!hierarchy_allows_attach(cgrp, type))
 		return -EPERM;
@@ -326,140 +467,224 @@ int __cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog,
 	if (prog_list_length(progs) >= BPF_CGROUP_MAX_PROGS)
 		return -E2BIG;
 
-	if (flags & BPF_F_ALLOW_MULTI) {
-		list_for_each_entry(pl, progs, node) {
-			if (pl->prog == prog)
-				/* disallow attaching the same prog twice */
-				return -EINVAL;
-			if (pl->prog == replace_prog)
-				replace_pl = pl;
-		}
-		if ((flags & BPF_F_REPLACE) && !replace_pl)
-			/* prog to replace not found for cgroup */
-			return -ENOENT;
-	} else if (!list_empty(progs)) {
-		replace_pl = list_first_entry(progs, typeof(*pl), node);
-	}
+	pl = find_attach_entry(progs, prog, link, replace_prog,
+			       flags & BPF_F_ALLOW_MULTI);
+	if (IS_ERR(pl))
+		return PTR_ERR(pl);
 
-	for_each_cgroup_storage_type(stype) {
-		storage[stype] = bpf_cgroup_storage_alloc(prog, stype);
-		if (IS_ERR(storage[stype])) {
-			storage[stype] = NULL;
-			for_each_cgroup_storage_type(stype)
-				bpf_cgroup_storage_free(storage[stype]);
-			return -ENOMEM;
-		}
-	}
+	if (bpf_cgroup_storages_alloc(storage, new_storage, type,
+				      prog ? : link->link.prog, cgrp))
+		return -ENOMEM;
 
-	if (replace_pl) {
-		pl = replace_pl;
+	if (pl) {
 		old_prog = pl->prog;
-		for_each_cgroup_storage_type(stype) {
-			old_storage[stype] = pl->storage[stype];
-			bpf_cgroup_storage_unlink(old_storage[stype]);
-		}
 	} else {
 		pl = kmalloc(sizeof(*pl), GFP_KERNEL);
 		if (!pl) {
-			for_each_cgroup_storage_type(stype)
-				bpf_cgroup_storage_free(storage[stype]);
+			bpf_cgroup_storages_free(new_storage);
 			return -ENOMEM;
 		}
 		list_add_tail(&pl->node, progs);
 	}
 
 	pl->prog = prog;
-	for_each_cgroup_storage_type(stype)
-		pl->storage[stype] = storage[stype];
-
+	pl->link = link;
+	bpf_cgroup_storages_assign(pl->storage, storage);
 	cgrp->bpf.flags[type] = saved_flags;
 
 	err = update_effective_progs(cgrp, type);
 	if (err)
 		goto cleanup;
 
-	static_branch_inc(&cgroup_bpf_enabled_key);
-	for_each_cgroup_storage_type(stype) {
-		if (!old_storage[stype])
-			continue;
-		bpf_cgroup_storage_free(old_storage[stype]);
-	}
-	if (old_prog) {
+	if (old_prog)
 		bpf_prog_put(old_prog);
-		static_branch_dec(&cgroup_bpf_enabled_key);
-	}
-	for_each_cgroup_storage_type(stype)
-		bpf_cgroup_storage_link(storage[stype], cgrp, type);
+	else
+		static_branch_inc(&cgroup_bpf_enabled_key);
+	bpf_cgroup_storages_link(new_storage, cgrp, type);
 	return 0;
 
 cleanup:
-	/* and cleanup the prog list */
-	pl->prog = old_prog;
-	for_each_cgroup_storage_type(stype) {
-		bpf_cgroup_storage_free(pl->storage[stype]);
-		pl->storage[stype] = old_storage[stype];
-		bpf_cgroup_storage_link(old_storage[stype], cgrp, type);
+	if (old_prog) {
+		pl->prog = old_prog;
+		pl->link = NULL;
 	}
-	if (!replace_pl) {
+	bpf_cgroup_storages_free(new_storage);
+	if (!old_prog) {
 		list_del(&pl->node);
 		kfree(pl);
 	}
 	return err;
 }
 
+/* Swap updated BPF program for given link in effective program arrays across
+ * all descendant cgroups. This function is guaranteed to succeed.
+ */
+static void replace_effective_prog(struct cgroup *cgrp,
+				   enum bpf_attach_type type,
+				   struct bpf_cgroup_link *link)
+{
+	struct bpf_prog_array_item *item;
+	struct cgroup_subsys_state *css;
+	struct bpf_prog_array *progs;
+	struct bpf_prog_list *pl;
+	struct list_head *head;
+	struct cgroup *cg;
+	int pos;
+
+	css_for_each_descendant_pre(css, &cgrp->self) {
+		struct cgroup *desc = container_of(css, struct cgroup, self);
+
+		if (percpu_ref_is_zero(&desc->bpf.refcnt))
+			continue;
+
+		/* find position of link in effective progs array */
+		for (pos = 0, cg = desc; cg; cg = cgroup_parent(cg)) {
+			if (pos && !(cg->bpf.flags[type] & BPF_F_ALLOW_MULTI))
+				continue;
+
+			head = &cg->bpf.progs[type];
+			list_for_each_entry(pl, head, node) {
+				if (!prog_list_prog(pl))
+					continue;
+				if (pl->link == link)
+					goto found;
+				pos++;
+			}
+		}
+found:
+		BUG_ON(!cg);
+		progs = rcu_dereference_protected(
+				desc->bpf.effective[type],
+				lockdep_is_held(&cgroup_mutex));
+		item = &progs->items[pos];
+		WRITE_ONCE(item->prog, link->link.prog);
+	}
+}
+
 /**
- * __cgroup_bpf_detach() - Detach the program from a cgroup, and
+ * __cgroup_bpf_replace() - Replace link's program and propagate the change
+ *                          to descendants
+ * @cgrp: The cgroup which descendants to traverse
+ * @link: A link for which to replace BPF program
+ * @type: Type of attach operation
+ *
+ * Must be called with cgroup_mutex held.
+ */
+static int __cgroup_bpf_replace(struct cgroup *cgrp,
+				struct bpf_cgroup_link *link,
+				struct bpf_prog *new_prog)
+{
+	struct list_head *progs = &cgrp->bpf.progs[link->type];
+	struct bpf_prog *old_prog;
+	struct bpf_prog_list *pl;
+	bool found = false;
+
+	if (link->link.prog->type != new_prog->type)
+		return -EINVAL;
+
+	list_for_each_entry(pl, progs, node) {
+		if (pl->link == link) {
+			found = true;
+			break;
+		}
+	}
+	if (!found)
+		return -ENOENT;
+
+	old_prog = xchg(&link->link.prog, new_prog);
+	replace_effective_prog(cgrp, link->type, link);
+	bpf_prog_put(old_prog);
+	return 0;
+}
+
+static int cgroup_bpf_replace(struct bpf_link *link, struct bpf_prog *new_prog,
+			      struct bpf_prog *old_prog)
+{
+	struct bpf_cgroup_link *cg_link;
+	int ret;
+
+	cg_link = container_of(link, struct bpf_cgroup_link, link);
+
+	mutex_lock(&cgroup_mutex);
+	/* link might have been auto-released by dying cgroup, so fail */
+	if (!cg_link->cgroup) {
+		ret = -ENOLINK;
+		goto out_unlock;
+	}
+	if (old_prog && link->prog != old_prog) {
+		ret = -EPERM;
+		goto out_unlock;
+	}
+	ret = __cgroup_bpf_replace(cg_link->cgroup, cg_link, new_prog);
+out_unlock:
+	mutex_unlock(&cgroup_mutex);
+	return ret;
+}
+
+static struct bpf_prog_list *find_detach_entry(struct list_head *progs,
+					       struct bpf_prog *prog,
+					       struct bpf_cgroup_link *link,
+					       bool allow_multi)
+{
+	struct bpf_prog_list *pl;
+
+	if (!allow_multi) {
+		if (list_empty(progs))
+			/* report error when trying to detach and nothing is attached */
+			return ERR_PTR(-ENOENT);
+
+		/* to maintain backward compatibility NONE and OVERRIDE cgroups
+		 * allow detaching with invalid FD (prog==NULL) in legacy mode
+		 */
+		return list_first_entry(progs, typeof(*pl), node);
+	}
+
+	if (!prog && !link)
+		/* to detach MULTI prog the user has to specify valid FD
+		 * of the program or link to be detached
+		 */
+		return ERR_PTR(-EINVAL);
+
+	/* find the prog or link and detach it */
+	list_for_each_entry(pl, progs, node) {
+		if (pl->prog == prog && pl->link == link)
+			return pl;
+	}
+	return ERR_PTR(-ENOENT);
+}
+
+/**
+ * __cgroup_bpf_detach() - Detach the program or link from a cgroup, and
  *                         propagate the change to descendants
  * @cgrp: The cgroup which descendants to traverse
  * @prog: A program to detach or NULL
+ * @prog: A link to detach or NULL
  * @type: Type of detach operation
  *
+ * At most one of @prog or @link can be non-NULL.
  * Must be called with cgroup_mutex held.
  */
 int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog,
-			enum bpf_attach_type type)
+			struct bpf_cgroup_link *link, enum bpf_attach_type type)
 {
 	struct list_head *progs = &cgrp->bpf.progs[type];
-	enum bpf_cgroup_storage_type stype;
 	u32 flags = cgrp->bpf.flags[type];
-	struct bpf_prog *old_prog = NULL;
 	struct bpf_prog_list *pl;
+	struct bpf_prog *old_prog;
 	int err;
 
-	if (flags & BPF_F_ALLOW_MULTI) {
-		if (!prog)
-			/* to detach MULTI prog the user has to specify valid FD
-			 * of the program to be detached
-			 */
-			return -EINVAL;
-	} else {
-		if (list_empty(progs))
-			/* report error when trying to detach and nothing is attached */
-			return -ENOENT;
-	}
+	if (prog && link)
+		/* only one of prog or link can be specified */
+		return -EINVAL;
 
-	if (flags & BPF_F_ALLOW_MULTI) {
-		/* find the prog and detach it */
-		list_for_each_entry(pl, progs, node) {
-			if (pl->prog != prog)
-				continue;
-			old_prog = prog;
-			/* mark it deleted, so it's ignored while
-			 * recomputing effective
-			 */
-			pl->prog = NULL;
-			break;
-		}
-		if (!old_prog)
-			return -ENOENT;
-	} else {
-		/* to maintain backward compatibility NONE and OVERRIDE cgroups
-		 * allow detaching with invalid FD (prog==NULL)
-		 */
-		pl = list_first_entry(progs, typeof(*pl), node);
-		old_prog = pl->prog;
-		pl->prog = NULL;
-	}
+	pl = find_detach_entry(progs, prog, link, flags & BPF_F_ALLOW_MULTI);
+	if (IS_ERR(pl))
+		return PTR_ERR(pl);
+
+	/* mark it deleted, so it's ignored while recomputing effective */
+	old_prog = pl->prog;
+	pl->prog = NULL;
+	pl->link = NULL;
 
 	err = update_effective_progs(cgrp, type);
 	if (err)
@@ -467,22 +692,19 @@ int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog,
 
 	/* now can actually delete it from this cgroup list */
 	list_del(&pl->node);
-	for_each_cgroup_storage_type(stype) {
-		bpf_cgroup_storage_unlink(pl->storage[stype]);
-		bpf_cgroup_storage_free(pl->storage[stype]);
-	}
 	kfree(pl);
 	if (list_empty(progs))
 		/* last program was detached, reset flags to zero */
 		cgrp->bpf.flags[type] = 0;
-
-	bpf_prog_put(old_prog);
+	if (old_prog)
+		bpf_prog_put(old_prog);
 	static_branch_dec(&cgroup_bpf_enabled_key);
 	return 0;
 
 cleanup:
-	/* and restore back old_prog */
+	/* restore back prog or link */
 	pl->prog = old_prog;
+	pl->link = link;
 	return err;
 }
 
@@ -495,6 +717,7 @@ int __cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr,
 	struct list_head *progs = &cgrp->bpf.progs[type];
 	u32 flags = cgrp->bpf.flags[type];
 	struct bpf_prog_array *effective;
+	struct bpf_prog *prog;
 	int cnt, ret = 0, i;
 
 	effective = rcu_dereference_protected(cgrp->bpf.effective[type],
@@ -525,7 +748,8 @@ int __cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr,
 
 		i = 0;
 		list_for_each_entry(pl, progs, node) {
-			id = pl->prog->aux->id;
+			prog = prog_list_prog(pl);
+			id = prog->aux->id;
 			if (copy_to_user(prog_ids + i, &id, sizeof(id)))
 				return -EFAULT;
 			if (++i == cnt)
@@ -555,8 +779,8 @@ int cgroup_bpf_prog_attach(const union bpf_attr *attr,
 		}
 	}
 
-	ret = cgroup_bpf_attach(cgrp, prog, replace_prog, attr->attach_type,
-				attr->attach_flags);
+	ret = cgroup_bpf_attach(cgrp, prog, replace_prog, NULL,
+				attr->attach_type, attr->attach_flags);
 
 	if (replace_prog)
 		bpf_prog_put(replace_prog);
@@ -578,7 +802,7 @@ int cgroup_bpf_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype)
 	if (IS_ERR(prog))
 		prog = NULL;
 
-	ret = cgroup_bpf_detach(cgrp, prog, attr->attach_type, 0);
+	ret = cgroup_bpf_detach(cgrp, prog, attr->attach_type);
 	if (prog)
 		bpf_prog_put(prog);
 
@@ -586,6 +810,141 @@ int cgroup_bpf_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype)
 	return ret;
 }
 
+static void bpf_cgroup_link_release(struct bpf_link *link)
+{
+	struct bpf_cgroup_link *cg_link =
+		container_of(link, struct bpf_cgroup_link, link);
+	struct cgroup *cg;
+
+	/* link might have been auto-detached by dying cgroup already,
+	 * in that case our work is done here
+	 */
+	if (!cg_link->cgroup)
+		return;
+
+	mutex_lock(&cgroup_mutex);
+
+	/* re-check cgroup under lock again */
+	if (!cg_link->cgroup) {
+		mutex_unlock(&cgroup_mutex);
+		return;
+	}
+
+	WARN_ON(__cgroup_bpf_detach(cg_link->cgroup, NULL, cg_link,
+				    cg_link->type));
+
+	cg = cg_link->cgroup;
+	cg_link->cgroup = NULL;
+
+	mutex_unlock(&cgroup_mutex);
+
+	cgroup_put(cg);
+}
+
+static void bpf_cgroup_link_dealloc(struct bpf_link *link)
+{
+	struct bpf_cgroup_link *cg_link =
+		container_of(link, struct bpf_cgroup_link, link);
+
+	kfree(cg_link);
+}
+
+static int bpf_cgroup_link_detach(struct bpf_link *link)
+{
+	bpf_cgroup_link_release(link);
+
+	return 0;
+}
+
+static void bpf_cgroup_link_show_fdinfo(const struct bpf_link *link,
+					struct seq_file *seq)
+{
+	struct bpf_cgroup_link *cg_link =
+		container_of(link, struct bpf_cgroup_link, link);
+	u64 cg_id = 0;
+
+	mutex_lock(&cgroup_mutex);
+	if (cg_link->cgroup)
+		cg_id = cgroup_id(cg_link->cgroup);
+	mutex_unlock(&cgroup_mutex);
+
+	seq_printf(seq,
+		   "cgroup_id:\t%llu\n"
+		   "attach_type:\t%d\n",
+		   cg_id,
+		   cg_link->type);
+}
+
+static int bpf_cgroup_link_fill_link_info(const struct bpf_link *link,
+					  struct bpf_link_info *info)
+{
+	struct bpf_cgroup_link *cg_link =
+		container_of(link, struct bpf_cgroup_link, link);
+	u64 cg_id = 0;
+
+	mutex_lock(&cgroup_mutex);
+	if (cg_link->cgroup)
+		cg_id = cgroup_id(cg_link->cgroup);
+	mutex_unlock(&cgroup_mutex);
+
+	info->cgroup.cgroup_id = cg_id;
+	info->cgroup.attach_type = cg_link->type;
+	return 0;
+}
+
+static const struct bpf_link_ops bpf_cgroup_link_lops = {
+	.release = bpf_cgroup_link_release,
+	.dealloc = bpf_cgroup_link_dealloc,
+	.detach = bpf_cgroup_link_detach,
+	.update_prog = cgroup_bpf_replace,
+	.show_fdinfo = bpf_cgroup_link_show_fdinfo,
+	.fill_link_info = bpf_cgroup_link_fill_link_info,
+};
+
+int cgroup_bpf_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
+{
+	struct bpf_link_primer link_primer;
+	struct bpf_cgroup_link *link;
+	struct cgroup *cgrp;
+	int err;
+
+	if (attr->link_create.flags)
+		return -EINVAL;
+
+	cgrp = cgroup_get_from_fd(attr->link_create.target_fd);
+	if (IS_ERR(cgrp))
+		return PTR_ERR(cgrp);
+
+	link = kzalloc(sizeof(*link), GFP_USER);
+	if (!link) {
+		err = -ENOMEM;
+		goto out_put_cgroup;
+	}
+	bpf_link_init(&link->link, BPF_LINK_TYPE_CGROUP, &bpf_cgroup_link_lops,
+		      prog);
+	link->cgroup = cgrp;
+	link->type = attr->link_create.attach_type;
+
+	err  = bpf_link_prime(&link->link, &link_primer);
+	if (err) {
+		kfree(link);
+		goto out_put_cgroup;
+	}
+
+	err = cgroup_bpf_attach(cgrp, NULL, NULL, link, link->type,
+				BPF_F_ALLOW_MULTI);
+	if (err) {
+		bpf_link_cleanup(&link_primer);
+		goto out_put_cgroup;
+	}
+
+	return bpf_link_settle(&link_primer);
+
+out_put_cgroup:
+	cgroup_put(cgrp);
+	return err;
+}
+
 int cgroup_bpf_prog_query(const union bpf_attr *attr,
 			  union bpf_attr __user *uattr)
 {
@@ -782,36 +1141,21 @@ int __cgroup_bpf_check_dev_permission(short dev_type, u32 major, u32 minor,
 
 	return !allow;
 }
-EXPORT_SYMBOL(__cgroup_bpf_check_dev_permission);
 
 static const struct bpf_func_proto *
 cgroup_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 {
 	switch (func_id) {
-	case BPF_FUNC_map_lookup_elem:
-		return &bpf_map_lookup_elem_proto;
-	case BPF_FUNC_map_update_elem:
-		return &bpf_map_update_elem_proto;
-	case BPF_FUNC_map_delete_elem:
-		return &bpf_map_delete_elem_proto;
-	case BPF_FUNC_map_push_elem:
-		return &bpf_map_push_elem_proto;
-	case BPF_FUNC_map_pop_elem:
-		return &bpf_map_pop_elem_proto;
-	case BPF_FUNC_map_peek_elem:
-		return &bpf_map_peek_elem_proto;
 	case BPF_FUNC_get_current_uid_gid:
 		return &bpf_get_current_uid_gid_proto;
 	case BPF_FUNC_get_local_storage:
 		return &bpf_get_local_storage_proto;
 	case BPF_FUNC_get_current_cgroup_id:
 		return &bpf_get_current_cgroup_id_proto;
-	case BPF_FUNC_trace_printk:
-		if (capable(CAP_SYS_ADMIN))
-			return bpf_get_trace_printk_proto();
-		/* fall through */
+	case BPF_FUNC_perf_event_output:
+		return &bpf_event_output_data_proto;
 	default:
-		return NULL;
+		return bpf_base_func_proto(func_id);
 	}
 }
 
@@ -865,16 +1209,13 @@ const struct bpf_verifier_ops cg_dev_verifier_ops = {
  * @head: sysctl table header
  * @table: sysctl table
  * @write: sysctl is being read (= 0) or written (= 1)
- * @buf: pointer to buffer passed by user space
+ * @buf: pointer to buffer (in and out)
  * @pcount: value-result argument: value is size of buffer pointed to by @buf,
  *	result is size of @new_buf if program set new value, initial value
  *	otherwise
  * @ppos: value-result argument: value is position at which read from or write
  *	to sysctl is happening, result is new position if program overrode it,
  *	initial value otherwise
- * @new_buf: pointer to pointer to new buffer that will be allocated if program
- *	overrides new value provided by user space on sysctl write
- *	NOTE: it's caller responsibility to free *new_buf if it was set
  * @type: type of program to be executed
  *
  * Program is run when sysctl is being accessed, either read or written, and
@@ -885,8 +1226,7 @@ const struct bpf_verifier_ops cg_dev_verifier_ops = {
  */
 int __cgroup_bpf_run_filter_sysctl(struct ctl_table_header *head,
 				   struct ctl_table *table, int write,
-				   void __user *buf, size_t *pcount,
-				   loff_t *ppos, void **new_buf,
+				   void **buf, size_t *pcount, loff_t *ppos,
 				   enum bpf_attach_type type)
 {
 	struct bpf_sysctl_kern ctx = {
@@ -901,36 +1241,28 @@ int __cgroup_bpf_run_filter_sysctl(struct ctl_table_header *head,
 		.new_updated = 0,
 	};
 	struct cgroup *cgrp;
+	loff_t pos = 0;
 	int ret;
 
 	ctx.cur_val = kmalloc_track_caller(ctx.cur_len, GFP_KERNEL);
-	if (ctx.cur_val) {
-		mm_segment_t old_fs;
-		loff_t pos = 0;
-
-		old_fs = get_fs();
-		set_fs(KERNEL_DS);
-		if (table->proc_handler(table, 0, (void __user *)ctx.cur_val,
-					&ctx.cur_len, &pos)) {
-			/* Let BPF program decide how to proceed. */
-			ctx.cur_len = 0;
-		}
-		set_fs(old_fs);
-	} else {
+	if (!ctx.cur_val ||
+	    table->proc_handler(table, 0, ctx.cur_val, &ctx.cur_len, &pos)) {
 		/* Let BPF program decide how to proceed. */
 		ctx.cur_len = 0;
 	}
 
-	if (write && buf && *pcount) {
+	if (write && *buf && *pcount) {
 		/* BPF program should be able to override new value with a
 		 * buffer bigger than provided by user.
 		 */
 		ctx.new_val = kmalloc_track_caller(PAGE_SIZE, GFP_KERNEL);
 		ctx.new_len = min_t(size_t, PAGE_SIZE, *pcount);
-		if (!ctx.new_val ||
-		    copy_from_user(ctx.new_val, buf, ctx.new_len))
+		if (ctx.new_val) {
+			memcpy(ctx.new_val, *buf, ctx.new_len);
+		} else {
 			/* Let BPF program decide how to proceed. */
 			ctx.new_len = 0;
+		}
 	}
 
 	rcu_read_lock();
@@ -941,7 +1273,8 @@ int __cgroup_bpf_run_filter_sysctl(struct ctl_table_header *head,
 	kfree(ctx.cur_val);
 
 	if (ret == 1 && ctx.new_updated) {
-		*new_buf = ctx.new_val;
+		kfree(*buf);
+		*buf = ctx.new_val;
 		*pcount = ctx.new_len;
 	} else {
 		kfree(ctx.new_val);
@@ -949,7 +1282,6 @@ int __cgroup_bpf_run_filter_sysctl(struct ctl_table_header *head,
 
 	return ret == 1 ? 0 : -EPERM;
 }
-EXPORT_SYMBOL(__cgroup_bpf_run_filter_sysctl);
 
 #ifdef CONFIG_NET
 static bool __cgroup_bpf_prog_array_is_empty(struct cgroup *cgrp,
@@ -968,16 +1300,23 @@ static bool __cgroup_bpf_prog_array_is_empty(struct cgroup *cgrp,
 
 static int sockopt_alloc_buf(struct bpf_sockopt_kern *ctx, int max_optlen)
 {
-	if (unlikely(max_optlen > PAGE_SIZE) || max_optlen < 0)
+	if (unlikely(max_optlen < 0))
 		return -EINVAL;
 
+	if (unlikely(max_optlen > PAGE_SIZE)) {
+		/* We don't expose optvals that are greater than PAGE_SIZE
+		 * to the BPF program.
+		 */
+		max_optlen = PAGE_SIZE;
+	}
+
 	ctx->optval = kzalloc(max_optlen, GFP_USER);
 	if (!ctx->optval)
 		return -ENOMEM;
 
 	ctx->optval_end = ctx->optval + max_optlen;
 
-	return 0;
+	return max_optlen;
 }
 
 static void sockopt_free_buf(struct bpf_sockopt_kern *ctx)
@@ -1011,13 +1350,13 @@ int __cgroup_bpf_run_filter_setsockopt(struct sock *sk, int *level,
 	 */
 	max_optlen = max_t(int, 16, *optlen);
 
-	ret = sockopt_alloc_buf(&ctx, max_optlen);
-	if (ret)
-		return ret;
+	max_optlen = sockopt_alloc_buf(&ctx, max_optlen);
+	if (max_optlen < 0)
+		return max_optlen;
 
 	ctx.optlen = *optlen;
 
-	if (copy_from_user(ctx.optval, optval, *optlen) != 0) {
+	if (copy_from_user(ctx.optval, optval, min(*optlen, max_optlen)) != 0) {
 		ret = -EFAULT;
 		goto out;
 	}
@@ -1045,8 +1384,14 @@ int __cgroup_bpf_run_filter_setsockopt(struct sock *sk, int *level,
 		/* export any potential modifications */
 		*level = ctx.level;
 		*optname = ctx.optname;
-		*optlen = ctx.optlen;
-		*kernel_optval = ctx.optval;
+
+		/* optlen == 0 from BPF indicates that we should
+		 * use original userspace data.
+		 */
+		if (ctx.optlen != 0) {
+			*optlen = ctx.optlen;
+			*kernel_optval = ctx.optval;
+		}
 	}
 
 out:
@@ -1054,7 +1399,6 @@ out:
 		sockopt_free_buf(&ctx);
 	return ret;
 }
-EXPORT_SYMBOL(__cgroup_bpf_run_filter_setsockopt);
 
 int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level,
 				       int optname, char __user *optval,
@@ -1078,12 +1422,12 @@ int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level,
 	    __cgroup_bpf_prog_array_is_empty(cgrp, BPF_CGROUP_GETSOCKOPT))
 		return retval;
 
-	ret = sockopt_alloc_buf(&ctx, max_optlen);
-	if (ret)
-		return ret;
-
 	ctx.optlen = max_optlen;
 
+	max_optlen = sockopt_alloc_buf(&ctx, max_optlen);
+	if (max_optlen < 0)
+		return max_optlen;
+
 	if (!retval) {
 		/* If kernel getsockopt finished successfully,
 		 * copy whatever was returned to the user back
@@ -1097,10 +1441,8 @@ int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level,
 			goto out;
 		}
 
-		if (ctx.optlen > max_optlen)
-			ctx.optlen = max_optlen;
-
-		if (copy_from_user(ctx.optval, optval, ctx.optlen) != 0) {
+		if (copy_from_user(ctx.optval, optval,
+				   min(ctx.optlen, max_optlen)) != 0) {
 			ret = -EFAULT;
 			goto out;
 		}
@@ -1129,10 +1471,12 @@ int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level,
 		goto out;
 	}
 
-	if (copy_to_user(optval, ctx.optval, ctx.optlen) ||
-	    put_user(ctx.optlen, optlen)) {
-		ret = -EFAULT;
-		goto out;
+	if (ctx.optlen != 0) {
+		if (copy_to_user(optval, ctx.optval, ctx.optlen) ||
+		    put_user(ctx.optlen, optlen)) {
+			ret = -EFAULT;
+			goto out;
+		}
 	}
 
 	ret = ctx.retval;
@@ -1141,7 +1485,6 @@ out:
 	sockopt_free_buf(&ctx);
 	return ret;
 }
-EXPORT_SYMBOL(__cgroup_bpf_run_filter_getsockopt);
 #endif
 
 static ssize_t sysctl_cpy_dir(const struct ctl_dir *dir, char **bufp,
@@ -1451,7 +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/core.c b/kernel/bpf/core.c
index 973a20d49749..ed0b3578867c 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -82,7 +82,7 @@ struct bpf_prog *bpf_prog_alloc_no_stats(unsigned int size, gfp_t gfp_extra_flag
 	struct bpf_prog *fp;
 
 	size = round_up(size, PAGE_SIZE);
-	fp = __vmalloc(size, gfp_flags, PAGE_KERNEL);
+	fp = __vmalloc(size, gfp_flags);
 	if (fp == NULL)
 		return NULL;
 
@@ -97,7 +97,7 @@ struct bpf_prog *bpf_prog_alloc_no_stats(unsigned int size, gfp_t gfp_extra_flag
 	fp->aux->prog = fp;
 	fp->jit_requested = ebpf_jit_enabled();
 
-	INIT_LIST_HEAD_RCU(&fp->aux->ksym_lnode);
+	INIT_LIST_HEAD_RCU(&fp->aux->ksym.lnode);
 
 	return fp;
 }
@@ -232,7 +232,7 @@ struct bpf_prog *bpf_prog_realloc(struct bpf_prog *fp_old, unsigned int size,
 	if (ret)
 		return NULL;
 
-	fp = __vmalloc(size, gfp_flags, PAGE_KERNEL);
+	fp = __vmalloc(size, gfp_flags);
 	if (fp == NULL) {
 		__bpf_prog_uncharge(fp_old->aux->user, delta);
 	} else {
@@ -262,10 +262,10 @@ void __bpf_prog_free(struct bpf_prog *fp)
 
 int bpf_prog_calc_tag(struct bpf_prog *fp)
 {
-	const u32 bits_offset = SHA_MESSAGE_BYTES - sizeof(__be64);
+	const u32 bits_offset = SHA1_BLOCK_SIZE - sizeof(__be64);
 	u32 raw_size = bpf_prog_tag_scratch_size(fp);
-	u32 digest[SHA_DIGEST_WORDS];
-	u32 ws[SHA_WORKSPACE_WORDS];
+	u32 digest[SHA1_DIGEST_WORDS];
+	u32 ws[SHA1_WORKSPACE_WORDS];
 	u32 i, bsize, psize, blocks;
 	struct bpf_insn *dst;
 	bool was_ld_map;
@@ -277,7 +277,7 @@ int bpf_prog_calc_tag(struct bpf_prog *fp)
 	if (!raw)
 		return -ENOMEM;
 
-	sha_init(digest);
+	sha1_init(digest);
 	memset(ws, 0, sizeof(ws));
 
 	/* We need to take out the map fd for the digest calculation
@@ -308,8 +308,8 @@ int bpf_prog_calc_tag(struct bpf_prog *fp)
 	memset(&raw[psize], 0, raw_size - psize);
 	raw[psize++] = 0x80;
 
-	bsize  = round_up(psize, SHA_MESSAGE_BYTES);
-	blocks = bsize / SHA_MESSAGE_BYTES;
+	bsize  = round_up(psize, SHA1_BLOCK_SIZE);
+	blocks = bsize / SHA1_BLOCK_SIZE;
 	todo   = raw;
 	if (bsize - psize >= sizeof(__be64)) {
 		bits = (__be64 *)(todo + bsize - sizeof(__be64));
@@ -320,12 +320,12 @@ int bpf_prog_calc_tag(struct bpf_prog *fp)
 	*bits = cpu_to_be64((psize - 1) << 3);
 
 	while (blocks--) {
-		sha_transform(digest, todo, ws);
-		todo += SHA_MESSAGE_BYTES;
+		sha1_transform(digest, todo, ws);
+		todo += SHA1_BLOCK_SIZE;
 	}
 
 	result = (__force __be32 *)digest;
-	for (i = 0; i < SHA_DIGEST_WORDS; i++)
+	for (i = 0; i < SHA1_DIGEST_WORDS; i++)
 		result[i] = cpu_to_be32(digest[i]);
 	memcpy(fp->tag, result, sizeof(fp->tag));
 
@@ -523,22 +523,22 @@ int bpf_jit_kallsyms __read_mostly = IS_BUILTIN(CONFIG_BPF_JIT_DEFAULT_ON);
 int bpf_jit_harden   __read_mostly;
 long bpf_jit_limit   __read_mostly;
 
-static __always_inline void
-bpf_get_prog_addr_region(const struct bpf_prog *prog,
-			 unsigned long *symbol_start,
-			 unsigned long *symbol_end)
+static void
+bpf_prog_ksym_set_addr(struct bpf_prog *prog)
 {
 	const struct bpf_binary_header *hdr = bpf_jit_binary_hdr(prog);
 	unsigned long addr = (unsigned long)hdr;
 
 	WARN_ON_ONCE(!bpf_prog_ebpf_jited(prog));
 
-	*symbol_start = addr;
-	*symbol_end   = addr + hdr->pages * PAGE_SIZE;
+	prog->aux->ksym.start = (unsigned long) prog->bpf_func;
+	prog->aux->ksym.end   = addr + hdr->pages * PAGE_SIZE;
 }
 
-void bpf_get_prog_name(const struct bpf_prog *prog, char *sym)
+static void
+bpf_prog_ksym_set_name(struct bpf_prog *prog)
 {
+	char *sym = prog->aux->ksym.name;
 	const char *end = sym + KSYM_NAME_LEN;
 	const struct btf_type *type;
 	const char *func_name;
@@ -572,36 +572,27 @@ void bpf_get_prog_name(const struct bpf_prog *prog, char *sym)
 		*sym = 0;
 }
 
-static __always_inline unsigned long
-bpf_get_prog_addr_start(struct latch_tree_node *n)
+static unsigned long bpf_get_ksym_start(struct latch_tree_node *n)
 {
-	unsigned long symbol_start, symbol_end;
-	const struct bpf_prog_aux *aux;
-
-	aux = container_of(n, struct bpf_prog_aux, ksym_tnode);
-	bpf_get_prog_addr_region(aux->prog, &symbol_start, &symbol_end);
-
-	return symbol_start;
+	return container_of(n, struct bpf_ksym, tnode)->start;
 }
 
 static __always_inline bool bpf_tree_less(struct latch_tree_node *a,
 					  struct latch_tree_node *b)
 {
-	return bpf_get_prog_addr_start(a) < bpf_get_prog_addr_start(b);
+	return bpf_get_ksym_start(a) < bpf_get_ksym_start(b);
 }
 
 static __always_inline int bpf_tree_comp(void *key, struct latch_tree_node *n)
 {
 	unsigned long val = (unsigned long)key;
-	unsigned long symbol_start, symbol_end;
-	const struct bpf_prog_aux *aux;
+	const struct bpf_ksym *ksym;
 
-	aux = container_of(n, struct bpf_prog_aux, ksym_tnode);
-	bpf_get_prog_addr_region(aux->prog, &symbol_start, &symbol_end);
+	ksym = container_of(n, struct bpf_ksym, tnode);
 
-	if (val < symbol_start)
+	if (val < ksym->start)
 		return -1;
-	if (val >= symbol_end)
+	if (val >= ksym->end)
 		return  1;
 
 	return 0;
@@ -616,20 +607,29 @@ static DEFINE_SPINLOCK(bpf_lock);
 static LIST_HEAD(bpf_kallsyms);
 static struct latch_tree_root bpf_tree __cacheline_aligned;
 
-static void bpf_prog_ksym_node_add(struct bpf_prog_aux *aux)
+void bpf_ksym_add(struct bpf_ksym *ksym)
 {
-	WARN_ON_ONCE(!list_empty(&aux->ksym_lnode));
-	list_add_tail_rcu(&aux->ksym_lnode, &bpf_kallsyms);
-	latch_tree_insert(&aux->ksym_tnode, &bpf_tree, &bpf_tree_ops);
+	spin_lock_bh(&bpf_lock);
+	WARN_ON_ONCE(!list_empty(&ksym->lnode));
+	list_add_tail_rcu(&ksym->lnode, &bpf_kallsyms);
+	latch_tree_insert(&ksym->tnode, &bpf_tree, &bpf_tree_ops);
+	spin_unlock_bh(&bpf_lock);
 }
 
-static void bpf_prog_ksym_node_del(struct bpf_prog_aux *aux)
+static void __bpf_ksym_del(struct bpf_ksym *ksym)
 {
-	if (list_empty(&aux->ksym_lnode))
+	if (list_empty(&ksym->lnode))
 		return;
 
-	latch_tree_erase(&aux->ksym_tnode, &bpf_tree, &bpf_tree_ops);
-	list_del_rcu(&aux->ksym_lnode);
+	latch_tree_erase(&ksym->tnode, &bpf_tree, &bpf_tree_ops);
+	list_del_rcu(&ksym->lnode);
+}
+
+void bpf_ksym_del(struct bpf_ksym *ksym)
+{
+	spin_lock_bh(&bpf_lock);
+	__bpf_ksym_del(ksym);
+	spin_unlock_bh(&bpf_lock);
 }
 
 static bool bpf_prog_kallsyms_candidate(const struct bpf_prog *fp)
@@ -639,19 +639,21 @@ static bool bpf_prog_kallsyms_candidate(const struct bpf_prog *fp)
 
 static bool bpf_prog_kallsyms_verify_off(const struct bpf_prog *fp)
 {
-	return list_empty(&fp->aux->ksym_lnode) ||
-	       fp->aux->ksym_lnode.prev == LIST_POISON2;
+	return list_empty(&fp->aux->ksym.lnode) ||
+	       fp->aux->ksym.lnode.prev == LIST_POISON2;
 }
 
 void bpf_prog_kallsyms_add(struct bpf_prog *fp)
 {
 	if (!bpf_prog_kallsyms_candidate(fp) ||
-	    !capable(CAP_SYS_ADMIN))
+	    !bpf_capable())
 		return;
 
-	spin_lock_bh(&bpf_lock);
-	bpf_prog_ksym_node_add(fp->aux);
-	spin_unlock_bh(&bpf_lock);
+	bpf_prog_ksym_set_addr(fp);
+	bpf_prog_ksym_set_name(fp);
+	fp->aux->ksym.prog = true;
+
+	bpf_ksym_add(&fp->aux->ksym);
 }
 
 void bpf_prog_kallsyms_del(struct bpf_prog *fp)
@@ -659,33 +661,30 @@ void bpf_prog_kallsyms_del(struct bpf_prog *fp)
 	if (!bpf_prog_kallsyms_candidate(fp))
 		return;
 
-	spin_lock_bh(&bpf_lock);
-	bpf_prog_ksym_node_del(fp->aux);
-	spin_unlock_bh(&bpf_lock);
+	bpf_ksym_del(&fp->aux->ksym);
 }
 
-static struct bpf_prog *bpf_prog_kallsyms_find(unsigned long addr)
+static struct bpf_ksym *bpf_ksym_find(unsigned long addr)
 {
 	struct latch_tree_node *n;
 
 	n = latch_tree_find((void *)addr, &bpf_tree, &bpf_tree_ops);
-	return n ?
-	       container_of(n, struct bpf_prog_aux, ksym_tnode)->prog :
-	       NULL;
+	return n ? container_of(n, struct bpf_ksym, tnode) : NULL;
 }
 
 const char *__bpf_address_lookup(unsigned long addr, unsigned long *size,
 				 unsigned long *off, char *sym)
 {
-	unsigned long symbol_start, symbol_end;
-	struct bpf_prog *prog;
+	struct bpf_ksym *ksym;
 	char *ret = NULL;
 
 	rcu_read_lock();
-	prog = bpf_prog_kallsyms_find(addr);
-	if (prog) {
-		bpf_get_prog_addr_region(prog, &symbol_start, &symbol_end);
-		bpf_get_prog_name(prog, sym);
+	ksym = bpf_ksym_find(addr);
+	if (ksym) {
+		unsigned long symbol_start = ksym->start;
+		unsigned long symbol_end = ksym->end;
+
+		strncpy(sym, ksym->name, KSYM_NAME_LEN);
 
 		ret = sym;
 		if (size)
@@ -703,19 +702,28 @@ bool is_bpf_text_address(unsigned long addr)
 	bool ret;
 
 	rcu_read_lock();
-	ret = bpf_prog_kallsyms_find(addr) != NULL;
+	ret = bpf_ksym_find(addr) != NULL;
 	rcu_read_unlock();
 
 	return ret;
 }
 
+static struct bpf_prog *bpf_prog_ksym_find(unsigned long addr)
+{
+	struct bpf_ksym *ksym = bpf_ksym_find(addr);
+
+	return ksym && ksym->prog ?
+	       container_of(ksym, struct bpf_prog_aux, ksym)->prog :
+	       NULL;
+}
+
 const struct exception_table_entry *search_bpf_extables(unsigned long addr)
 {
 	const struct exception_table_entry *e = NULL;
 	struct bpf_prog *prog;
 
 	rcu_read_lock();
-	prog = bpf_prog_kallsyms_find(addr);
+	prog = bpf_prog_ksym_find(addr);
 	if (!prog)
 		goto out;
 	if (!prog->aux->num_exentries)
@@ -730,7 +738,7 @@ out:
 int bpf_get_kallsym(unsigned int symnum, unsigned long *value, char *type,
 		    char *sym)
 {
-	struct bpf_prog_aux *aux;
+	struct bpf_ksym *ksym;
 	unsigned int it = 0;
 	int ret = -ERANGE;
 
@@ -738,13 +746,13 @@ int bpf_get_kallsym(unsigned int symnum, unsigned long *value, char *type,
 		return ret;
 
 	rcu_read_lock();
-	list_for_each_entry_rcu(aux, &bpf_kallsyms, ksym_lnode) {
+	list_for_each_entry_rcu(ksym, &bpf_kallsyms, lnode) {
 		if (it++ != symnum)
 			continue;
 
-		bpf_get_prog_name(aux->prog, sym);
+		strncpy(sym, ksym->name, KSYM_NAME_LEN);
 
-		*value = (unsigned long)aux->prog->bpf_func;
+		*value = ksym->start;
 		*type  = BPF_SYM_ELF_TYPE;
 
 		ret = 0;
@@ -1081,7 +1089,7 @@ static struct bpf_prog *bpf_prog_clone_create(struct bpf_prog *fp_other,
 	gfp_t gfp_flags = GFP_KERNEL | __GFP_ZERO | gfp_extra_flags;
 	struct bpf_prog *fp;
 
-	fp = __vmalloc(fp_other->pages * PAGE_SIZE, gfp_flags, PAGE_KERNEL);
+	fp = __vmalloc(fp_other->pages * PAGE_SIZE, gfp_flags);
 	if (fp != NULL) {
 		/* aux->prog still points to the fp_other one, so
 		 * when promoting the clone to the real program,
@@ -1535,7 +1543,7 @@ select_insn:
 
 		/* ARG1 at this point is guaranteed to point to CTX from
 		 * the verifier side due to the fact that the tail call is
-		 * handeled like a helper, that is, bpf_tail_call_proto,
+		 * handled like a helper, that is, bpf_tail_call_proto,
 		 * where arg1_type is ARG_PTR_TO_CTX.
 		 */
 		insn = prog->insnsi;
@@ -1950,6 +1958,61 @@ void bpf_prog_array_delete_safe(struct bpf_prog_array *array,
 		}
 }
 
+/**
+ * bpf_prog_array_delete_safe_at() - Replaces the program at the given
+ *                                   index into the program array with
+ *                                   a dummy no-op program.
+ * @array: a bpf_prog_array
+ * @index: the index of the program to replace
+ *
+ * Skips over dummy programs, by not counting them, when calculating
+ * the position of the program to replace.
+ *
+ * Return:
+ * * 0		- Success
+ * * -EINVAL	- Invalid index value. Must be a non-negative integer.
+ * * -ENOENT	- Index out of range
+ */
+int bpf_prog_array_delete_safe_at(struct bpf_prog_array *array, int index)
+{
+	return bpf_prog_array_update_at(array, index, &dummy_bpf_prog.prog);
+}
+
+/**
+ * bpf_prog_array_update_at() - Updates the program at the given index
+ *                              into the program array.
+ * @array: a bpf_prog_array
+ * @index: the index of the program to update
+ * @prog: the program to insert into the array
+ *
+ * Skips over dummy programs, by not counting them, when calculating
+ * the position of the program to update.
+ *
+ * Return:
+ * * 0		- Success
+ * * -EINVAL	- Invalid index value. Must be a non-negative integer.
+ * * -ENOENT	- Index out of range
+ */
+int bpf_prog_array_update_at(struct bpf_prog_array *array, int index,
+			     struct bpf_prog *prog)
+{
+	struct bpf_prog_array_item *item;
+
+	if (unlikely(index < 0))
+		return -EINVAL;
+
+	for (item = array->items; item->prog; item++) {
+		if (item->prog == &dummy_bpf_prog.prog)
+			continue;
+		if (!index) {
+			WRITE_ONCE(item->prog, prog);
+			return 0;
+		}
+		index--;
+	}
+	return -ENOENT;
+}
+
 int bpf_prog_array_copy(struct bpf_prog_array *old_array,
 			struct bpf_prog *exclude_prog,
 			struct bpf_prog *include_prog,
@@ -2034,24 +2097,12 @@ int bpf_prog_array_copy_info(struct bpf_prog_array *array,
 								     : 0;
 }
 
-static void bpf_free_cgroup_storage(struct bpf_prog_aux *aux)
-{
-	enum bpf_cgroup_storage_type stype;
-
-	for_each_cgroup_storage_type(stype) {
-		if (!aux->cgroup_storage[stype])
-			continue;
-		bpf_cgroup_storage_release(aux, aux->cgroup_storage[stype]);
-	}
-}
-
 void __bpf_free_used_maps(struct bpf_prog_aux *aux,
 			  struct bpf_map **used_maps, u32 len)
 {
 	struct bpf_map *map;
 	u32 i;
 
-	bpf_free_cgroup_storage(aux);
 	for (i = 0; i < len; i++) {
 		map = used_maps[i];
 		if (map->ops->map_poke_untrack)
@@ -2128,6 +2179,11 @@ BPF_CALL_0(bpf_user_rnd_u32)
 	return res;
 }
 
+BPF_CALL_0(bpf_get_raw_cpu_id)
+{
+	return raw_smp_processor_id();
+}
+
 /* Weak definitions of helper functions in case we don't have bpf syscall. */
 const struct bpf_func_proto bpf_map_lookup_elem_proto __weak;
 const struct bpf_func_proto bpf_map_update_elem_proto __weak;
@@ -2143,12 +2199,15 @@ const struct bpf_func_proto bpf_get_prandom_u32_proto __weak;
 const struct bpf_func_proto bpf_get_smp_processor_id_proto __weak;
 const struct bpf_func_proto bpf_get_numa_node_id_proto __weak;
 const struct bpf_func_proto bpf_ktime_get_ns_proto __weak;
+const struct bpf_func_proto bpf_ktime_get_boot_ns_proto __weak;
 
 const struct bpf_func_proto bpf_get_current_pid_tgid_proto __weak;
 const struct bpf_func_proto bpf_get_current_uid_gid_proto __weak;
 const struct bpf_func_proto bpf_get_current_comm_proto __weak;
 const struct bpf_func_proto bpf_get_current_cgroup_id_proto __weak;
+const struct bpf_func_proto bpf_get_current_ancestor_cgroup_id_proto __weak;
 const struct bpf_func_proto bpf_get_local_storage_proto __weak;
+const struct bpf_func_proto bpf_get_ns_current_pid_tgid_proto __weak;
 
 const struct bpf_func_proto * __weak bpf_get_trace_printk_proto(void)
 {
diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c
index 70f71b154fa5..6386b7bb98f2 100644
--- a/kernel/bpf/cpumap.c
+++ b/kernel/bpf/cpumap.c
@@ -52,7 +52,6 @@ struct xdp_bulk_queue {
 struct bpf_cpu_map_entry {
 	u32 cpu;    /* kthread CPU and map index */
 	int map_id; /* Back reference to map */
-	u32 qsize;  /* Queue size placeholder for map lookup */
 
 	/* XDP can run multiple RX-ring queues, need __percpu enqueue store */
 	struct xdp_bulk_queue __percpu *bulkq;
@@ -62,10 +61,14 @@ struct bpf_cpu_map_entry {
 	/* Queue with potential multi-producers, and single-consumer kthread */
 	struct ptr_ring *queue;
 	struct task_struct *kthread;
-	struct work_struct kthread_stop_wq;
+
+	struct bpf_cpumap_val value;
+	struct bpf_prog *prog;
 
 	atomic_t refcnt; /* Control when this struct can be free'ed */
 	struct rcu_head rcu;
+
+	struct work_struct kthread_stop_wq;
 };
 
 struct bpf_cpu_map {
@@ -80,17 +83,20 @@ static int bq_flush_to_queue(struct xdp_bulk_queue *bq);
 
 static struct bpf_map *cpu_map_alloc(union bpf_attr *attr)
 {
+	u32 value_size = attr->value_size;
 	struct bpf_cpu_map *cmap;
 	int err = -ENOMEM;
 	u64 cost;
 	int ret;
 
-	if (!capable(CAP_SYS_ADMIN))
+	if (!bpf_capable())
 		return ERR_PTR(-EPERM);
 
 	/* check sanity of attributes */
 	if (attr->max_entries == 0 || attr->key_size != 4 ||
-	    attr->value_size != 4 || attr->map_flags & ~BPF_F_NUMA_NODE)
+	    (value_size != offsetofend(struct bpf_cpumap_val, qsize) &&
+	     value_size != offsetofend(struct bpf_cpumap_val, bpf_prog.fd)) ||
+	    attr->map_flags & ~BPF_F_NUMA_NODE)
 		return ERR_PTR(-EINVAL);
 
 	cmap = kzalloc(sizeof(*cmap), GFP_USER);
@@ -162,25 +168,10 @@ static struct sk_buff *cpu_map_build_skb(struct bpf_cpu_map_entry *rcpu,
 	/* Part of headroom was reserved to xdpf */
 	hard_start_headroom = sizeof(struct xdp_frame) +  xdpf->headroom;
 
-	/* build_skb need to place skb_shared_info after SKB end, and
-	 * also want to know the memory "truesize".  Thus, need to
-	 * know the memory frame size backing xdp_buff.
-	 *
-	 * XDP was designed to have PAGE_SIZE frames, but this
-	 * assumption is not longer true with ixgbe and i40e.  It
-	 * would be preferred to set frame_size to 2048 or 4096
-	 * depending on the driver.
-	 *   frame_size = 2048;
-	 *   frame_len  = frame_size - sizeof(*xdp_frame);
-	 *
-	 * Instead, with info avail, skb_shared_info in placed after
-	 * packet len.  This, unfortunately fakes the truesize.
-	 * Another disadvantage of this approach, the skb_shared_info
-	 * is not at a fixed memory location, with mixed length
-	 * packets, which is bad for cache-line hotness.
+	/* Memory size backing xdp_frame data already have reserved
+	 * room for build_skb to place skb_shared_info in tailroom.
 	 */
-	frame_size = SKB_DATA_ALIGN(xdpf->len + hard_start_headroom) +
-		SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
+	frame_size = xdpf->frame_sz;
 
 	pkt_data_start = xdpf->data - hard_start_headroom;
 	skb = build_skb_around(skb, pkt_data_start, frame_size);
@@ -227,6 +218,8 @@ static void __cpu_map_ring_cleanup(struct ptr_ring *ring)
 static void put_cpu_map_entry(struct bpf_cpu_map_entry *rcpu)
 {
 	if (atomic_dec_and_test(&rcpu->refcnt)) {
+		if (rcpu->prog)
+			bpf_prog_put(rcpu->prog);
 		/* The queue should be empty at this point */
 		__cpu_map_ring_cleanup(rcpu->queue);
 		ptr_ring_cleanup(rcpu->queue, NULL);
@@ -235,6 +228,75 @@ static void put_cpu_map_entry(struct bpf_cpu_map_entry *rcpu)
 	}
 }
 
+static int cpu_map_bpf_prog_run_xdp(struct bpf_cpu_map_entry *rcpu,
+				    void **frames, int n,
+				    struct xdp_cpumap_stats *stats)
+{
+	struct xdp_rxq_info rxq;
+	struct xdp_buff xdp;
+	int i, nframes = 0;
+
+	if (!rcpu->prog)
+		return n;
+
+	rcu_read_lock_bh();
+
+	xdp_set_return_frame_no_direct();
+	xdp.rxq = &rxq;
+
+	for (i = 0; i < n; i++) {
+		struct xdp_frame *xdpf = frames[i];
+		u32 act;
+		int err;
+
+		rxq.dev = xdpf->dev_rx;
+		rxq.mem = xdpf->mem;
+		/* TODO: report queue_index to xdp_rxq_info */
+
+		xdp_convert_frame_to_buff(xdpf, &xdp);
+
+		act = bpf_prog_run_xdp(rcpu->prog, &xdp);
+		switch (act) {
+		case XDP_PASS:
+			err = xdp_update_frame_from_buff(&xdp, xdpf);
+			if (err < 0) {
+				xdp_return_frame(xdpf);
+				stats->drop++;
+			} else {
+				frames[nframes++] = xdpf;
+				stats->pass++;
+			}
+			break;
+		case XDP_REDIRECT:
+			err = xdp_do_redirect(xdpf->dev_rx, &xdp,
+					      rcpu->prog);
+			if (unlikely(err)) {
+				xdp_return_frame(xdpf);
+				stats->drop++;
+			} else {
+				stats->redirect++;
+			}
+			break;
+		default:
+			bpf_warn_invalid_xdp_action(act);
+			fallthrough;
+		case XDP_DROP:
+			xdp_return_frame(xdpf);
+			stats->drop++;
+			break;
+		}
+	}
+
+	if (stats->redirect)
+		xdp_do_flush_map();
+
+	xdp_clear_return_frame_no_direct();
+
+	rcu_read_unlock_bh(); /* resched point, may call do_softirq() */
+
+	return nframes;
+}
+
 #define CPUMAP_BATCH 8
 
 static int cpu_map_kthread_run(void *data)
@@ -249,11 +311,12 @@ static int cpu_map_kthread_run(void *data)
 	 * kthread_stop signal until queue is empty.
 	 */
 	while (!kthread_should_stop() || !__ptr_ring_empty(rcpu->queue)) {
+		struct xdp_cpumap_stats stats = {}; /* zero stats */
+		gfp_t gfp = __GFP_ZERO | GFP_ATOMIC;
 		unsigned int drops = 0, sched = 0;
 		void *frames[CPUMAP_BATCH];
 		void *skbs[CPUMAP_BATCH];
-		gfp_t gfp = __GFP_ZERO | GFP_ATOMIC;
-		int i, n, m;
+		int i, n, m, nframes;
 
 		/* Release CPU reschedule checks */
 		if (__ptr_ring_empty(rcpu->queue)) {
@@ -274,8 +337,8 @@ static int cpu_map_kthread_run(void *data)
 		 * kthread CPU pinned. Lockless access to ptr_ring
 		 * consume side valid as no-resize allowed of queue.
 		 */
-		n = ptr_ring_consume_batched(rcpu->queue, frames, CPUMAP_BATCH);
-
+		n = __ptr_ring_consume_batched(rcpu->queue, frames,
+					       CPUMAP_BATCH);
 		for (i = 0; i < n; i++) {
 			void *f = frames[i];
 			struct page *page = virt_to_page(f);
@@ -287,15 +350,19 @@ static int cpu_map_kthread_run(void *data)
 			prefetchw(page);
 		}
 
-		m = kmem_cache_alloc_bulk(skbuff_head_cache, gfp, n, skbs);
-		if (unlikely(m == 0)) {
-			for (i = 0; i < n; i++)
-				skbs[i] = NULL; /* effect: xdp_return_frame */
-			drops = n;
+		/* Support running another XDP prog on this CPU */
+		nframes = cpu_map_bpf_prog_run_xdp(rcpu, frames, n, &stats);
+		if (nframes) {
+			m = kmem_cache_alloc_bulk(skbuff_head_cache, gfp, nframes, skbs);
+			if (unlikely(m == 0)) {
+				for (i = 0; i < nframes; i++)
+					skbs[i] = NULL; /* effect: xdp_return_frame */
+				drops += nframes;
+			}
 		}
 
 		local_bh_disable();
-		for (i = 0; i < n; i++) {
+		for (i = 0; i < nframes; i++) {
 			struct xdp_frame *xdpf = frames[i];
 			struct sk_buff *skb = skbs[i];
 			int ret;
@@ -312,7 +379,7 @@ static int cpu_map_kthread_run(void *data)
 				drops++;
 		}
 		/* Feedback loop via tracepoint */
-		trace_xdp_cpumap_kthread(rcpu->map_id, n, drops, sched);
+		trace_xdp_cpumap_kthread(rcpu->map_id, n, drops, sched, &stats);
 
 		local_bh_enable(); /* resched point, may call do_softirq() */
 	}
@@ -322,13 +389,38 @@ static int cpu_map_kthread_run(void *data)
 	return 0;
 }
 
-static struct bpf_cpu_map_entry *__cpu_map_entry_alloc(u32 qsize, u32 cpu,
-						       int map_id)
+bool cpu_map_prog_allowed(struct bpf_map *map)
+{
+	return map->map_type == BPF_MAP_TYPE_CPUMAP &&
+	       map->value_size != offsetofend(struct bpf_cpumap_val, qsize);
+}
+
+static int __cpu_map_load_bpf_program(struct bpf_cpu_map_entry *rcpu, int fd)
+{
+	struct bpf_prog *prog;
+
+	prog = bpf_prog_get_type(fd, BPF_PROG_TYPE_XDP);
+	if (IS_ERR(prog))
+		return PTR_ERR(prog);
+
+	if (prog->expected_attach_type != BPF_XDP_CPUMAP) {
+		bpf_prog_put(prog);
+		return -EINVAL;
+	}
+
+	rcpu->value.bpf_prog.id = prog->aux->id;
+	rcpu->prog = prog;
+
+	return 0;
+}
+
+static struct bpf_cpu_map_entry *
+__cpu_map_entry_alloc(struct bpf_cpumap_val *value, u32 cpu, int map_id)
 {
+	int numa, err, i, fd = value->bpf_prog.fd;
 	gfp_t gfp = GFP_KERNEL | __GFP_NOWARN;
 	struct bpf_cpu_map_entry *rcpu;
 	struct xdp_bulk_queue *bq;
-	int numa, err, i;
 
 	/* Have map->numa_node, but choose node of redirect target CPU */
 	numa = cpu_to_node(cpu);
@@ -353,19 +445,22 @@ static struct bpf_cpu_map_entry *__cpu_map_entry_alloc(u32 qsize, u32 cpu,
 	if (!rcpu->queue)
 		goto free_bulkq;
 
-	err = ptr_ring_init(rcpu->queue, qsize, gfp);
+	err = ptr_ring_init(rcpu->queue, value->qsize, gfp);
 	if (err)
 		goto free_queue;
 
 	rcpu->cpu    = cpu;
 	rcpu->map_id = map_id;
-	rcpu->qsize  = qsize;
+	rcpu->value.qsize  = value->qsize;
+
+	if (fd > 0 && __cpu_map_load_bpf_program(rcpu, fd))
+		goto free_ptr_ring;
 
 	/* Setup kthread */
 	rcpu->kthread = kthread_create_on_node(cpu_map_kthread_run, rcpu, numa,
 					       "cpumap/%d/map:%d", cpu, map_id);
 	if (IS_ERR(rcpu->kthread))
-		goto free_ptr_ring;
+		goto free_prog;
 
 	get_cpu_map_entry(rcpu); /* 1-refcnt for being in cmap->cpu_map[] */
 	get_cpu_map_entry(rcpu); /* 1-refcnt for kthread */
@@ -376,6 +471,9 @@ static struct bpf_cpu_map_entry *__cpu_map_entry_alloc(u32 qsize, u32 cpu,
 
 	return rcpu;
 
+free_prog:
+	if (rcpu->prog)
+		bpf_prog_put(rcpu->prog);
 free_ptr_ring:
 	ptr_ring_cleanup(rcpu->queue, NULL);
 free_queue:
@@ -452,12 +550,12 @@ static int cpu_map_update_elem(struct bpf_map *map, void *key, void *value,
 			       u64 map_flags)
 {
 	struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map);
+	struct bpf_cpumap_val cpumap_value = {};
 	struct bpf_cpu_map_entry *rcpu;
-
 	/* Array index key correspond to CPU number */
 	u32 key_cpu = *(u32 *)key;
-	/* Value is the queue size */
-	u32 qsize = *(u32 *)value;
+
+	memcpy(&cpumap_value, value, map->value_size);
 
 	if (unlikely(map_flags > BPF_EXIST))
 		return -EINVAL;
@@ -465,18 +563,18 @@ static int cpu_map_update_elem(struct bpf_map *map, void *key, void *value,
 		return -E2BIG;
 	if (unlikely(map_flags == BPF_NOEXIST))
 		return -EEXIST;
-	if (unlikely(qsize > 16384)) /* sanity limit on qsize */
+	if (unlikely(cpumap_value.qsize > 16384)) /* sanity limit on qsize */
 		return -EOVERFLOW;
 
 	/* Make sure CPU is a valid possible cpu */
-	if (!cpu_possible(key_cpu))
+	if (key_cpu >= nr_cpumask_bits || !cpu_possible(key_cpu))
 		return -ENODEV;
 
-	if (qsize == 0) {
+	if (cpumap_value.qsize == 0) {
 		rcpu = NULL; /* Same as deleting */
 	} else {
 		/* Updating qsize cause re-allocation of bpf_cpu_map_entry */
-		rcpu = __cpu_map_entry_alloc(qsize, key_cpu, map->id);
+		rcpu = __cpu_map_entry_alloc(&cpumap_value, key_cpu, map->id);
 		if (!rcpu)
 			return -ENOMEM;
 		rcpu->cmap = cmap;
@@ -538,7 +636,7 @@ static void *cpu_map_lookup_elem(struct bpf_map *map, void *key)
 	struct bpf_cpu_map_entry *rcpu =
 		__cpu_map_lookup_elem(map, *(u32 *)key);
 
-	return rcpu ? &rcpu->qsize : NULL;
+	return rcpu ? &rcpu->value : NULL;
 }
 
 static int cpu_map_get_next_key(struct bpf_map *map, void *key, void *next_key)
@@ -558,6 +656,7 @@ static int cpu_map_get_next_key(struct bpf_map *map, void *key, void *next_key)
 	return 0;
 }
 
+static int cpu_map_btf_id;
 const struct bpf_map_ops cpu_map_ops = {
 	.map_alloc		= cpu_map_alloc,
 	.map_free		= cpu_map_free,
@@ -566,6 +665,8 @@ const struct bpf_map_ops cpu_map_ops = {
 	.map_lookup_elem	= cpu_map_lookup_elem,
 	.map_get_next_key	= cpu_map_get_next_key,
 	.map_check_btf		= map_check_no_btf,
+	.map_btf_name		= "bpf_cpu_map",
+	.map_btf_id		= &cpu_map_btf_id,
 };
 
 static int bq_flush_to_queue(struct xdp_bulk_queue *bq)
@@ -636,7 +737,7 @@ int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_buff *xdp,
 {
 	struct xdp_frame *xdpf;
 
-	xdpf = convert_to_xdp_frame(xdp);
+	xdpf = xdp_convert_buff_to_frame(xdp);
 	if (unlikely(!xdpf))
 		return -EOVERFLOW;
 
diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c
index 58bdca5d978a..10abb06065bb 100644
--- a/kernel/bpf/devmap.c
+++ b/kernel/bpf/devmap.c
@@ -52,7 +52,6 @@
 #define DEV_CREATE_FLAG_MASK \
 	(BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY)
 
-#define DEV_MAP_BULK_SIZE 16
 struct xdp_dev_bulk_queue {
 	struct xdp_frame *q[DEV_MAP_BULK_SIZE];
 	struct list_head flush_node;
@@ -65,8 +64,10 @@ struct bpf_dtab_netdev {
 	struct net_device *dev; /* must be first member, due to tracepoint */
 	struct hlist_node index_hlist;
 	struct bpf_dtab *dtab;
+	struct bpf_prog *xdp_prog;
 	struct rcu_head rcu;
 	unsigned int idx;
+	struct bpf_devmap_val val;
 };
 
 struct bpf_dtab {
@@ -85,12 +86,13 @@ static DEFINE_PER_CPU(struct list_head, dev_flush_list);
 static DEFINE_SPINLOCK(dev_map_lock);
 static LIST_HEAD(dev_map_list);
 
-static struct hlist_head *dev_map_create_hash(unsigned int entries)
+static struct hlist_head *dev_map_create_hash(unsigned int entries,
+					      int numa_node)
 {
 	int i;
 	struct hlist_head *hash;
 
-	hash = kmalloc_array(entries, sizeof(*hash), GFP_KERNEL);
+	hash = bpf_map_area_alloc(entries * sizeof(*hash), numa_node);
 	if (hash != NULL)
 		for (i = 0; i < entries; i++)
 			INIT_HLIST_HEAD(&hash[i]);
@@ -106,12 +108,18 @@ static inline struct hlist_head *dev_map_index_hash(struct bpf_dtab *dtab,
 
 static int dev_map_init_map(struct bpf_dtab *dtab, union bpf_attr *attr)
 {
+	u32 valsize = attr->value_size;
 	u64 cost = 0;
 	int err;
 
-	/* check sanity of attributes */
+	/* check sanity of attributes. 2 value sizes supported:
+	 * 4 bytes: ifindex
+	 * 8 bytes: ifindex + prog fd
+	 */
 	if (attr->max_entries == 0 || attr->key_size != 4 ||
-	    attr->value_size != 4 || attr->map_flags & ~DEV_CREATE_FLAG_MASK)
+	    (valsize != offsetofend(struct bpf_devmap_val, ifindex) &&
+	     valsize != offsetofend(struct bpf_devmap_val, bpf_prog.fd)) ||
+	    attr->map_flags & ~DEV_CREATE_FLAG_MASK)
 		return -EINVAL;
 
 	/* Lookup returns a pointer straight to dev->ifindex, so make sure the
@@ -138,7 +146,8 @@ static int dev_map_init_map(struct bpf_dtab *dtab, union bpf_attr *attr)
 		return -EINVAL;
 
 	if (attr->map_type == BPF_MAP_TYPE_DEVMAP_HASH) {
-		dtab->dev_index_head = dev_map_create_hash(dtab->n_buckets);
+		dtab->dev_index_head = dev_map_create_hash(dtab->n_buckets,
+							   dtab->map.numa_node);
 		if (!dtab->dev_index_head)
 			goto free_charge;
 
@@ -218,12 +227,14 @@ static void dev_map_free(struct bpf_map *map)
 
 			hlist_for_each_entry_safe(dev, next, head, index_hlist) {
 				hlist_del_rcu(&dev->index_hlist);
+				if (dev->xdp_prog)
+					bpf_prog_put(dev->xdp_prog);
 				dev_put(dev->dev);
 				kfree(dev);
 			}
 		}
 
-		kfree(dtab->dev_index_head);
+		bpf_map_area_free(dtab->dev_index_head);
 	} else {
 		for (i = 0; i < dtab->map.max_entries; i++) {
 			struct bpf_dtab_netdev *dev;
@@ -232,6 +243,8 @@ static void dev_map_free(struct bpf_map *map)
 			if (!dev)
 				continue;
 
+			if (dev->xdp_prog)
+				bpf_prog_put(dev->xdp_prog);
 			dev_put(dev->dev);
 			kfree(dev);
 		}
@@ -318,6 +331,16 @@ static int dev_map_hash_get_next_key(struct bpf_map *map, void *key,
 	return -ENOENT;
 }
 
+bool dev_map_can_have_prog(struct bpf_map *map)
+{
+	if ((map->map_type == BPF_MAP_TYPE_DEVMAP ||
+	     map->map_type == BPF_MAP_TYPE_DEVMAP_HASH) &&
+	    map->value_size != offsetofend(struct bpf_devmap_val, ifindex))
+		return true;
+
+	return false;
+}
+
 static int bq_xmit_all(struct xdp_dev_bulk_queue *bq, u32 flags)
 {
 	struct net_device *dev = bq->dev;
@@ -435,13 +458,41 @@ static inline int __xdp_enqueue(struct net_device *dev, struct xdp_buff *xdp,
 	if (unlikely(err))
 		return err;
 
-	xdpf = convert_to_xdp_frame(xdp);
+	xdpf = xdp_convert_buff_to_frame(xdp);
 	if (unlikely(!xdpf))
 		return -EOVERFLOW;
 
 	return bq_enqueue(dev, xdpf, dev_rx);
 }
 
+static struct xdp_buff *dev_map_run_prog(struct net_device *dev,
+					 struct xdp_buff *xdp,
+					 struct bpf_prog *xdp_prog)
+{
+	struct xdp_txq_info txq = { .dev = dev };
+	u32 act;
+
+	xdp_set_data_meta_invalid(xdp);
+	xdp->txq = &txq;
+
+	act = bpf_prog_run_xdp(xdp_prog, xdp);
+	switch (act) {
+	case XDP_PASS:
+		return xdp;
+	case XDP_DROP:
+		break;
+	default:
+		bpf_warn_invalid_xdp_action(act);
+		fallthrough;
+	case XDP_ABORTED:
+		trace_xdp_exception(dev, xdp_prog, act);
+		break;
+	}
+
+	xdp_return_buff(xdp);
+	return NULL;
+}
+
 int dev_xdp_enqueue(struct net_device *dev, struct xdp_buff *xdp,
 		    struct net_device *dev_rx)
 {
@@ -453,6 +504,11 @@ int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp,
 {
 	struct net_device *dev = dst->dev;
 
+	if (dst->xdp_prog) {
+		xdp = dev_map_run_prog(dev, xdp, dst->xdp_prog);
+		if (!xdp)
+			return 0;
+	}
 	return __xdp_enqueue(dev, xdp, dev_rx);
 }
 
@@ -473,18 +529,15 @@ int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb,
 static void *dev_map_lookup_elem(struct bpf_map *map, void *key)
 {
 	struct bpf_dtab_netdev *obj = __dev_map_lookup_elem(map, *(u32 *)key);
-	struct net_device *dev = obj ? obj->dev : NULL;
 
-	return dev ? &dev->ifindex : NULL;
+	return obj ? &obj->val : NULL;
 }
 
 static void *dev_map_hash_lookup_elem(struct bpf_map *map, void *key)
 {
 	struct bpf_dtab_netdev *obj = __dev_map_hash_lookup_elem(map,
 								*(u32 *)key);
-	struct net_device *dev = obj ? obj->dev : NULL;
-
-	return dev ? &dev->ifindex : NULL;
+	return obj ? &obj->val : NULL;
 }
 
 static void __dev_map_entry_free(struct rcu_head *rcu)
@@ -492,6 +545,8 @@ static void __dev_map_entry_free(struct rcu_head *rcu)
 	struct bpf_dtab_netdev *dev;
 
 	dev = container_of(rcu, struct bpf_dtab_netdev, rcu);
+	if (dev->xdp_prog)
+		bpf_prog_put(dev->xdp_prog);
 	dev_put(dev->dev);
 	kfree(dev);
 }
@@ -542,9 +597,10 @@ static int dev_map_hash_delete_elem(struct bpf_map *map, void *key)
 
 static struct bpf_dtab_netdev *__dev_map_alloc_node(struct net *net,
 						    struct bpf_dtab *dtab,
-						    u32 ifindex,
+						    struct bpf_devmap_val *val,
 						    unsigned int idx)
 {
+	struct bpf_prog *prog = NULL;
 	struct bpf_dtab_netdev *dev;
 
 	dev = kmalloc_node(sizeof(*dev), GFP_ATOMIC | __GFP_NOWARN,
@@ -552,16 +608,38 @@ static struct bpf_dtab_netdev *__dev_map_alloc_node(struct net *net,
 	if (!dev)
 		return ERR_PTR(-ENOMEM);
 
-	dev->dev = dev_get_by_index(net, ifindex);
-	if (!dev->dev) {
-		kfree(dev);
-		return ERR_PTR(-EINVAL);
+	dev->dev = dev_get_by_index(net, val->ifindex);
+	if (!dev->dev)
+		goto err_out;
+
+	if (val->bpf_prog.fd > 0) {
+		prog = bpf_prog_get_type_dev(val->bpf_prog.fd,
+					     BPF_PROG_TYPE_XDP, false);
+		if (IS_ERR(prog))
+			goto err_put_dev;
+		if (prog->expected_attach_type != BPF_XDP_DEVMAP)
+			goto err_put_prog;
 	}
 
 	dev->idx = idx;
 	dev->dtab = dtab;
+	if (prog) {
+		dev->xdp_prog = prog;
+		dev->val.bpf_prog.id = prog->aux->id;
+	} else {
+		dev->xdp_prog = NULL;
+		dev->val.bpf_prog.id = 0;
+	}
+	dev->val.ifindex = val->ifindex;
 
 	return dev;
+err_put_prog:
+	bpf_prog_put(prog);
+err_put_dev:
+	dev_put(dev->dev);
+err_out:
+	kfree(dev);
+	return ERR_PTR(-EINVAL);
 }
 
 static int __dev_map_update_elem(struct net *net, struct bpf_map *map,
@@ -569,7 +647,7 @@ static int __dev_map_update_elem(struct net *net, struct bpf_map *map,
 {
 	struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map);
 	struct bpf_dtab_netdev *dev, *old_dev;
-	u32 ifindex = *(u32 *)value;
+	struct bpf_devmap_val val = {};
 	u32 i = *(u32 *)key;
 
 	if (unlikely(map_flags > BPF_EXIST))
@@ -579,10 +657,16 @@ static int __dev_map_update_elem(struct net *net, struct bpf_map *map,
 	if (unlikely(map_flags == BPF_NOEXIST))
 		return -EEXIST;
 
-	if (!ifindex) {
+	/* already verified value_size <= sizeof val */
+	memcpy(&val, value, map->value_size);
+
+	if (!val.ifindex) {
 		dev = NULL;
+		/* can not specify fd if ifindex is 0 */
+		if (val.bpf_prog.fd > 0)
+			return -EINVAL;
 	} else {
-		dev = __dev_map_alloc_node(net, dtab, ifindex, i);
+		dev = __dev_map_alloc_node(net, dtab, &val, i);
 		if (IS_ERR(dev))
 			return PTR_ERR(dev);
 	}
@@ -610,12 +694,15 @@ static int __dev_map_hash_update_elem(struct net *net, struct bpf_map *map,
 {
 	struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map);
 	struct bpf_dtab_netdev *dev, *old_dev;
-	u32 ifindex = *(u32 *)value;
+	struct bpf_devmap_val val = {};
 	u32 idx = *(u32 *)key;
 	unsigned long flags;
 	int err = -EEXIST;
 
-	if (unlikely(map_flags > BPF_EXIST || !ifindex))
+	/* already verified value_size <= sizeof val */
+	memcpy(&val, value, map->value_size);
+
+	if (unlikely(map_flags > BPF_EXIST || !val.ifindex))
 		return -EINVAL;
 
 	spin_lock_irqsave(&dtab->index_lock, flags);
@@ -624,7 +711,7 @@ static int __dev_map_hash_update_elem(struct net *net, struct bpf_map *map,
 	if (old_dev && (map_flags & BPF_NOEXIST))
 		goto out_err;
 
-	dev = __dev_map_alloc_node(net, dtab, ifindex, idx);
+	dev = __dev_map_alloc_node(net, dtab, &val, idx);
 	if (IS_ERR(dev)) {
 		err = PTR_ERR(dev);
 		goto out_err;
@@ -662,6 +749,7 @@ static int dev_map_hash_update_elem(struct bpf_map *map, void *key, void *value,
 					 map, key, value, map_flags);
 }
 
+static int dev_map_btf_id;
 const struct bpf_map_ops dev_map_ops = {
 	.map_alloc = dev_map_alloc,
 	.map_free = dev_map_free,
@@ -670,8 +758,11 @@ const struct bpf_map_ops dev_map_ops = {
 	.map_update_elem = dev_map_update_elem,
 	.map_delete_elem = dev_map_delete_elem,
 	.map_check_btf = map_check_no_btf,
+	.map_btf_name = "bpf_dtab",
+	.map_btf_id = &dev_map_btf_id,
 };
 
+static int dev_map_hash_map_btf_id;
 const struct bpf_map_ops dev_map_hash_ops = {
 	.map_alloc = dev_map_alloc,
 	.map_free = dev_map_free,
@@ -680,6 +771,8 @@ const struct bpf_map_ops dev_map_hash_ops = {
 	.map_update_elem = dev_map_hash_update_elem,
 	.map_delete_elem = dev_map_hash_delete_elem,
 	.map_check_btf = map_check_no_btf,
+	.map_btf_name = "bpf_dtab",
+	.map_btf_id = &dev_map_hash_map_btf_id,
 };
 
 static void dev_map_hash_remove_netdev(struct bpf_dtab *dtab,
diff --git a/kernel/bpf/dispatcher.c b/kernel/bpf/dispatcher.c
index b3e5b214fed8..2444bd15cc2d 100644
--- a/kernel/bpf/dispatcher.c
+++ b/kernel/bpf/dispatcher.c
@@ -113,7 +113,7 @@ static void bpf_dispatcher_update(struct bpf_dispatcher *d, int prev_num_progs)
 		noff = 0;
 	} else {
 		old = d->image + d->image_off;
-		noff = d->image_off ^ (BPF_IMAGE_SIZE / 2);
+		noff = d->image_off ^ (PAGE_SIZE / 2);
 	}
 
 	new = d->num_progs ? d->image + noff : NULL;
@@ -140,9 +140,10 @@ void bpf_dispatcher_change_prog(struct bpf_dispatcher *d, struct bpf_prog *from,
 
 	mutex_lock(&d->mutex);
 	if (!d->image) {
-		d->image = bpf_image_alloc();
+		d->image = bpf_jit_alloc_exec_page();
 		if (!d->image)
 			goto out;
+		bpf_image_ksym_add(d->image, &d->ksym);
 	}
 
 	prev_num_progs = d->num_progs;
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index a1468e3f5af2..78dfff6a501b 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -27,9 +27,62 @@
 	.map_delete_batch =			\
 	generic_map_delete_batch
 
+/*
+ * The bucket lock has two protection scopes:
+ *
+ * 1) Serializing concurrent operations from BPF programs on differrent
+ *    CPUs
+ *
+ * 2) Serializing concurrent operations from BPF programs and sys_bpf()
+ *
+ * BPF programs can execute in any context including perf, kprobes and
+ * tracing. As there are almost no limits where perf, kprobes and tracing
+ * can be invoked from the lock operations need to be protected against
+ * deadlocks. Deadlocks can be caused by recursion and by an invocation in
+ * the lock held section when functions which acquire this lock are invoked
+ * from sys_bpf(). BPF recursion is prevented by incrementing the per CPU
+ * variable bpf_prog_active, which prevents BPF programs attached to perf
+ * events, kprobes and tracing to be invoked before the prior invocation
+ * from one of these contexts completed. sys_bpf() uses the same mechanism
+ * by pinning the task to the current CPU and incrementing the recursion
+ * protection accross the map operation.
+ *
+ * This has subtle implications on PREEMPT_RT. PREEMPT_RT forbids certain
+ * operations like memory allocations (even with GFP_ATOMIC) from atomic
+ * contexts. This is required because even with GFP_ATOMIC the memory
+ * allocator calls into code pathes which acquire locks with long held lock
+ * sections. To ensure the deterministic behaviour these locks are regular
+ * spinlocks, which are converted to 'sleepable' spinlocks on RT. The only
+ * true atomic contexts on an RT kernel are the low level hardware
+ * handling, scheduling, low level interrupt handling, NMIs etc. None of
+ * these contexts should ever do memory allocations.
+ *
+ * As regular device interrupt handlers and soft interrupts are forced into
+ * thread context, the existing code which does
+ *   spin_lock*(); alloc(GPF_ATOMIC); spin_unlock*();
+ * just works.
+ *
+ * In theory the BPF locks could be converted to regular spinlocks as well,
+ * but the bucket locks and percpu_freelist locks can be taken from
+ * arbitrary contexts (perf, kprobes, tracepoints) which are required to be
+ * atomic contexts even on RT. These mechanisms require preallocated maps,
+ * so there is no need to invoke memory allocations within the lock held
+ * sections.
+ *
+ * BPF maps which need dynamic allocation are only used from (forced)
+ * thread context on RT and can therefore use regular spinlocks which in
+ * turn allows to invoke memory allocations from the lock held section.
+ *
+ * On a non RT kernel this distinction is neither possible nor required.
+ * spinlock maps to raw_spinlock and the extra code is optimized out by the
+ * compiler.
+ */
 struct bucket {
 	struct hlist_nulls_head head;
-	raw_spinlock_t lock;
+	union {
+		raw_spinlock_t raw_lock;
+		spinlock_t     lock;
+	};
 };
 
 struct bpf_htab {
@@ -65,9 +118,54 @@ struct htab_elem {
 		struct bpf_lru_node lru_node;
 	};
 	u32 hash;
-	char key[0] __aligned(8);
+	char key[] __aligned(8);
 };
 
+static inline bool htab_is_prealloc(const struct bpf_htab *htab)
+{
+	return !(htab->map.map_flags & BPF_F_NO_PREALLOC);
+}
+
+static inline bool htab_use_raw_lock(const struct bpf_htab *htab)
+{
+	return (!IS_ENABLED(CONFIG_PREEMPT_RT) || htab_is_prealloc(htab));
+}
+
+static void htab_init_buckets(struct bpf_htab *htab)
+{
+	unsigned i;
+
+	for (i = 0; i < htab->n_buckets; i++) {
+		INIT_HLIST_NULLS_HEAD(&htab->buckets[i].head, i);
+		if (htab_use_raw_lock(htab))
+			raw_spin_lock_init(&htab->buckets[i].raw_lock);
+		else
+			spin_lock_init(&htab->buckets[i].lock);
+	}
+}
+
+static inline unsigned long htab_lock_bucket(const struct bpf_htab *htab,
+					     struct bucket *b)
+{
+	unsigned long flags;
+
+	if (htab_use_raw_lock(htab))
+		raw_spin_lock_irqsave(&b->raw_lock, flags);
+	else
+		spin_lock_irqsave(&b->lock, flags);
+	return flags;
+}
+
+static inline void htab_unlock_bucket(const struct bpf_htab *htab,
+				      struct bucket *b,
+				      unsigned long flags)
+{
+	if (htab_use_raw_lock(htab))
+		raw_spin_unlock_irqrestore(&b->raw_lock, flags);
+	else
+		spin_unlock_irqrestore(&b->lock, flags);
+}
+
 static bool htab_lru_map_delete_node(void *arg, struct bpf_lru_node *node);
 
 static bool htab_is_lru(const struct bpf_htab *htab)
@@ -82,11 +180,6 @@ static bool htab_is_percpu(const struct bpf_htab *htab)
 		htab->map.map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH;
 }
 
-static bool htab_is_prealloc(const struct bpf_htab *htab)
-{
-	return !(htab->map.map_flags & BPF_F_NO_PREALLOC);
-}
-
 static inline void htab_elem_set_ptr(struct htab_elem *l, u32 key_size,
 				     void __percpu *pptr)
 {
@@ -266,9 +359,9 @@ static int htab_map_alloc_check(union bpf_attr *attr)
 	BUILD_BUG_ON(offsetof(struct htab_elem, fnode.next) !=
 		     offsetof(struct htab_elem, hash_node.pprev));
 
-	if (lru && !capable(CAP_SYS_ADMIN))
+	if (lru && !bpf_capable())
 		/* LRU implementation is much complicated than other
-		 * maps.  Hence, limit to CAP_SYS_ADMIN for now.
+		 * maps.  Hence, limit to CAP_BPF.
 		 */
 		return -EPERM;
 
@@ -328,8 +421,8 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr)
 	bool percpu_lru = (attr->map_flags & BPF_F_NO_COMMON_LRU);
 	bool prealloc = !(attr->map_flags & BPF_F_NO_PREALLOC);
 	struct bpf_htab *htab;
-	int err, i;
 	u64 cost;
+	int err;
 
 	htab = kzalloc(sizeof(*htab), GFP_USER);
 	if (!htab)
@@ -391,10 +484,7 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr)
 	else
 		htab->hashrnd = get_random_int();
 
-	for (i = 0; i < htab->n_buckets; i++) {
-		INIT_HLIST_NULLS_HEAD(&htab->buckets[i].head, i);
-		raw_spin_lock_init(&htab->buckets[i].lock);
-	}
+	htab_init_buckets(htab);
 
 	if (prealloc) {
 		err = prealloc_init(htab);
@@ -602,7 +692,7 @@ static bool htab_lru_map_delete_node(void *arg, struct bpf_lru_node *node)
 	b = __select_bucket(htab, tgt_l->hash);
 	head = &b->head;
 
-	raw_spin_lock_irqsave(&b->lock, flags);
+	flags = htab_lock_bucket(htab, b);
 
 	hlist_nulls_for_each_entry_rcu(l, n, head, hash_node)
 		if (l == tgt_l) {
@@ -610,7 +700,7 @@ static bool htab_lru_map_delete_node(void *arg, struct bpf_lru_node *node)
 			break;
 		}
 
-	raw_spin_unlock_irqrestore(&b->lock, flags);
+	htab_unlock_bucket(htab, b, flags);
 
 	return l == tgt_l;
 }
@@ -686,26 +776,23 @@ static void htab_elem_free_rcu(struct rcu_head *head)
 	struct htab_elem *l = container_of(head, struct htab_elem, rcu);
 	struct bpf_htab *htab = l->htab;
 
-	/* must increment bpf_prog_active to avoid kprobe+bpf triggering while
-	 * we're calling kfree, otherwise deadlock is possible if kprobes
-	 * are placed somewhere inside of slub
-	 */
-	preempt_disable();
-	__this_cpu_inc(bpf_prog_active);
 	htab_elem_free(htab, l);
-	__this_cpu_dec(bpf_prog_active);
-	preempt_enable();
 }
 
-static void free_htab_elem(struct bpf_htab *htab, struct htab_elem *l)
+static void htab_put_fd_value(struct bpf_htab *htab, struct htab_elem *l)
 {
 	struct bpf_map *map = &htab->map;
+	void *ptr;
 
 	if (map->ops->map_fd_put_ptr) {
-		void *ptr = fd_htab_map_get_ptr(map, l);
-
+		ptr = fd_htab_map_get_ptr(map, l);
 		map->ops->map_fd_put_ptr(ptr);
 	}
+}
+
+static void free_htab_elem(struct bpf_htab *htab, struct htab_elem *l)
+{
+	htab_put_fd_value(htab, l);
 
 	if (htab_is_prealloc(htab)) {
 		__pcpu_freelist_push(&htab->freelist, &l->fnode);
@@ -757,6 +844,7 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key,
 			 */
 			pl_new = this_cpu_ptr(htab->extra_elems);
 			l_new = *pl_new;
+			htab_put_fd_value(htab, old_elem);
 			*pl_new = old_elem;
 		} else {
 			struct pcpu_freelist_node *l;
@@ -884,8 +972,7 @@ static int htab_map_update_elem(struct bpf_map *map, void *key, void *value,
 		 */
 	}
 
-	/* bpf_map_update_elem() can be called in_irq() */
-	raw_spin_lock_irqsave(&b->lock, flags);
+	flags = htab_lock_bucket(htab, b);
 
 	l_old = lookup_elem_raw(head, hash, key, key_size);
 
@@ -926,7 +1013,7 @@ static int htab_map_update_elem(struct bpf_map *map, void *key, void *value,
 	}
 	ret = 0;
 err:
-	raw_spin_unlock_irqrestore(&b->lock, flags);
+	htab_unlock_bucket(htab, b, flags);
 	return ret;
 }
 
@@ -964,8 +1051,7 @@ static int htab_lru_map_update_elem(struct bpf_map *map, void *key, void *value,
 		return -ENOMEM;
 	memcpy(l_new->key + round_up(map->key_size, 8), value, map->value_size);
 
-	/* bpf_map_update_elem() can be called in_irq() */
-	raw_spin_lock_irqsave(&b->lock, flags);
+	flags = htab_lock_bucket(htab, b);
 
 	l_old = lookup_elem_raw(head, hash, key, key_size);
 
@@ -984,7 +1070,7 @@ static int htab_lru_map_update_elem(struct bpf_map *map, void *key, void *value,
 	ret = 0;
 
 err:
-	raw_spin_unlock_irqrestore(&b->lock, flags);
+	htab_unlock_bucket(htab, b, flags);
 
 	if (ret)
 		bpf_lru_push_free(&htab->lru, &l_new->lru_node);
@@ -1019,8 +1105,7 @@ static int __htab_percpu_map_update_elem(struct bpf_map *map, void *key,
 	b = __select_bucket(htab, hash);
 	head = &b->head;
 
-	/* bpf_map_update_elem() can be called in_irq() */
-	raw_spin_lock_irqsave(&b->lock, flags);
+	flags = htab_lock_bucket(htab, b);
 
 	l_old = lookup_elem_raw(head, hash, key, key_size);
 
@@ -1043,7 +1128,7 @@ static int __htab_percpu_map_update_elem(struct bpf_map *map, void *key,
 	}
 	ret = 0;
 err:
-	raw_spin_unlock_irqrestore(&b->lock, flags);
+	htab_unlock_bucket(htab, b, flags);
 	return ret;
 }
 
@@ -1083,8 +1168,7 @@ static int __htab_lru_percpu_map_update_elem(struct bpf_map *map, void *key,
 			return -ENOMEM;
 	}
 
-	/* bpf_map_update_elem() can be called in_irq() */
-	raw_spin_lock_irqsave(&b->lock, flags);
+	flags = htab_lock_bucket(htab, b);
 
 	l_old = lookup_elem_raw(head, hash, key, key_size);
 
@@ -1106,7 +1190,7 @@ static int __htab_lru_percpu_map_update_elem(struct bpf_map *map, void *key,
 	}
 	ret = 0;
 err:
-	raw_spin_unlock_irqrestore(&b->lock, flags);
+	htab_unlock_bucket(htab, b, flags);
 	if (l_new)
 		bpf_lru_push_free(&htab->lru, &l_new->lru_node);
 	return ret;
@@ -1144,7 +1228,7 @@ static int htab_map_delete_elem(struct bpf_map *map, void *key)
 	b = __select_bucket(htab, hash);
 	head = &b->head;
 
-	raw_spin_lock_irqsave(&b->lock, flags);
+	flags = htab_lock_bucket(htab, b);
 
 	l = lookup_elem_raw(head, hash, key, key_size);
 
@@ -1154,7 +1238,7 @@ static int htab_map_delete_elem(struct bpf_map *map, void *key)
 		ret = 0;
 	}
 
-	raw_spin_unlock_irqrestore(&b->lock, flags);
+	htab_unlock_bucket(htab, b, flags);
 	return ret;
 }
 
@@ -1176,7 +1260,7 @@ static int htab_lru_map_delete_elem(struct bpf_map *map, void *key)
 	b = __select_bucket(htab, hash);
 	head = &b->head;
 
-	raw_spin_lock_irqsave(&b->lock, flags);
+	flags = htab_lock_bucket(htab, b);
 
 	l = lookup_elem_raw(head, hash, key, key_size);
 
@@ -1185,7 +1269,7 @@ static int htab_lru_map_delete_elem(struct bpf_map *map, void *key)
 		ret = 0;
 	}
 
-	raw_spin_unlock_irqrestore(&b->lock, flags);
+	htab_unlock_bucket(htab, b, flags);
 	if (l)
 		bpf_lru_push_free(&htab->lru, &l->lru_node);
 	return ret;
@@ -1212,12 +1296,10 @@ static void htab_map_free(struct bpf_map *map)
 {
 	struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
 
-	/* at this point bpf_prog->aux->refcnt == 0 and this map->refcnt == 0,
-	 * so the programs (can be more than one that used this map) were
-	 * disconnected from events. Wait for outstanding critical sections in
-	 * these programs to complete
+	/* bpf_free_used_maps() or close(map_fd) will trigger this map_free callback.
+	 * bpf_free_used_maps() is called after bpf prog is no longer executing.
+	 * There is no need to synchronize_rcu() here to protect map elements.
 	 */
-	synchronize_rcu();
 
 	/* some of free_htab_elem() callbacks for elements of this map may
 	 * not have executed. Wait for them.
@@ -1325,8 +1407,7 @@ alloc:
 	}
 
 again:
-	preempt_disable();
-	this_cpu_inc(bpf_prog_active);
+	bpf_disable_instrumentation();
 	rcu_read_lock();
 again_nocopy:
 	dst_key = keys;
@@ -1335,7 +1416,7 @@ again_nocopy:
 	head = &b->head;
 	/* do not grab the lock unless need it (bucket_cnt > 0). */
 	if (locked)
-		raw_spin_lock_irqsave(&b->lock, flags);
+		flags = htab_lock_bucket(htab, b);
 
 	bucket_cnt = 0;
 	hlist_nulls_for_each_entry_rcu(l, n, head, hash_node)
@@ -1352,10 +1433,9 @@ again_nocopy:
 		/* Note that since bucket_cnt > 0 here, it is implicit
 		 * that the locked was grabbed, so release it.
 		 */
-		raw_spin_unlock_irqrestore(&b->lock, flags);
+		htab_unlock_bucket(htab, b, flags);
 		rcu_read_unlock();
-		this_cpu_dec(bpf_prog_active);
-		preempt_enable();
+		bpf_enable_instrumentation();
 		goto after_loop;
 	}
 
@@ -1364,10 +1444,9 @@ again_nocopy:
 		/* Note that since bucket_cnt > 0 here, it is implicit
 		 * that the locked was grabbed, so release it.
 		 */
-		raw_spin_unlock_irqrestore(&b->lock, flags);
+		htab_unlock_bucket(htab, b, flags);
 		rcu_read_unlock();
-		this_cpu_dec(bpf_prog_active);
-		preempt_enable();
+		bpf_enable_instrumentation();
 		kvfree(keys);
 		kvfree(values);
 		goto alloc;
@@ -1418,7 +1497,7 @@ again_nocopy:
 		dst_val += value_size;
 	}
 
-	raw_spin_unlock_irqrestore(&b->lock, flags);
+	htab_unlock_bucket(htab, b, flags);
 	locked = false;
 
 	while (node_to_free) {
@@ -1437,8 +1516,7 @@ next_batch:
 	}
 
 	rcu_read_unlock();
-	this_cpu_dec(bpf_prog_active);
-	preempt_enable();
+	bpf_enable_instrumentation();
 	if (bucket_cnt && (copy_to_user(ukeys + total * key_size, keys,
 	    key_size * bucket_cnt) ||
 	    copy_to_user(uvalues + total * value_size, values,
@@ -1540,6 +1618,197 @@ htab_lru_map_lookup_and_delete_batch(struct bpf_map *map,
 						  true, false);
 }
 
+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;
+};
+
+static struct htab_elem *
+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;
+	struct hlist_nulls_node *n;
+	struct htab_elem *elem;
+	struct bucket *b;
+	u32 i, count;
+
+	if (bucket_id >= htab->n_buckets)
+		return NULL;
+
+	/* try to find next elem in the same bucket */
+	if (prev_elem) {
+		/* no update/deletion on this bucket, prev_elem should be still valid
+		 * and we won't skip elements.
+		 */
+		n = rcu_dereference_raw(hlist_nulls_next_rcu(&prev_elem->hash_node));
+		elem = hlist_nulls_entry_safe(n, struct htab_elem, hash_node);
+		if (elem)
+			return elem;
+
+		/* not found, unlock and go to the next bucket */
+		b = &htab->buckets[bucket_id++];
+		htab_unlock_bucket(htab, b, flags);
+		skip_elems = 0;
+	}
+
+	for (i = bucket_id; i < htab->n_buckets; i++) {
+		b = &htab->buckets[i];
+		flags = htab_lock_bucket(htab, b);
+
+		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;
+			}
+			count++;
+		}
+
+		htab_unlock_bucket(htab, b, flags);
+		skip_elems = 0;
+	}
+
+	info->bucket_id = i;
+	info->skip_elems = 0;
+	return NULL;
+}
+
+static void *bpf_hash_map_seq_start(struct seq_file *seq, loff_t *pos)
+{
+	struct bpf_iter_seq_hash_map_info *info = seq->private;
+	struct htab_elem *elem;
+
+	elem = bpf_hash_map_seq_find_next(info, NULL);
+	if (!elem)
+		return NULL;
+
+	if (*pos == 0)
+		++*pos;
+	return elem;
+}
+
+static void *bpf_hash_map_seq_next(struct seq_file *seq, void *v, loff_t *pos)
+{
+	struct bpf_iter_seq_hash_map_info *info = seq->private;
+
+	++*pos;
+	++info->skip_elems;
+	return bpf_hash_map_seq_find_next(info, v);
+}
+
+static int __bpf_hash_map_seq_show(struct seq_file *seq, struct htab_elem *elem)
+{
+	struct bpf_iter_seq_hash_map_info *info = seq->private;
+	u32 roundup_key_size, roundup_value_size;
+	struct bpf_iter__bpf_map_elem ctx = {};
+	struct bpf_map *map = info->map;
+	struct bpf_iter_meta meta;
+	int ret = 0, off = 0, cpu;
+	struct bpf_prog *prog;
+	void __percpu *pptr;
+
+	meta.seq = seq;
+	prog = bpf_iter_get_info(&meta, elem == NULL);
+	if (prog) {
+		ctx.meta = &meta;
+		ctx.map = info->map;
+		if (elem) {
+			roundup_key_size = round_up(map->key_size, 8);
+			ctx.key = elem->key;
+			if (!info->percpu_value_buf) {
+				ctx.value = elem->key + roundup_key_size;
+			} else {
+				roundup_value_size = round_up(map->value_size, 8);
+				pptr = htab_elem_get_ptr(elem, map->key_size);
+				for_each_possible_cpu(cpu) {
+					bpf_long_memcpy(info->percpu_value_buf + off,
+							per_cpu_ptr(pptr, cpu),
+							roundup_value_size);
+					off += roundup_value_size;
+				}
+				ctx.value = info->percpu_value_buf;
+			}
+		}
+		ret = bpf_iter_run_prog(prog, &ctx);
+	}
+
+	return ret;
+}
+
+static int bpf_hash_map_seq_show(struct seq_file *seq, void *v)
+{
+	return __bpf_hash_map_seq_show(seq, 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);
+}
+
+static int bpf_iter_init_hash_map(void *priv_data,
+				  struct bpf_iter_aux_info *aux)
+{
+	struct bpf_iter_seq_hash_map_info *seq_info = priv_data;
+	struct bpf_map *map = aux->map;
+	void *value_buf;
+	u32 buf_size;
+
+	if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH ||
+	    map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH) {
+		buf_size = round_up(map->value_size, 8) * num_possible_cpus();
+		value_buf = kmalloc(buf_size, GFP_USER | __GFP_NOWARN);
+		if (!value_buf)
+			return -ENOMEM;
+
+		seq_info->percpu_value_buf = value_buf;
+	}
+
+	seq_info->map = map;
+	seq_info->htab = container_of(map, struct bpf_htab, map);
+	return 0;
+}
+
+static void bpf_iter_fini_hash_map(void *priv_data)
+{
+	struct bpf_iter_seq_hash_map_info *seq_info = priv_data;
+
+	kfree(seq_info->percpu_value_buf);
+}
+
+static const struct seq_operations bpf_hash_map_seq_ops = {
+	.start	= bpf_hash_map_seq_start,
+	.next	= bpf_hash_map_seq_next,
+	.stop	= bpf_hash_map_seq_stop,
+	.show	= bpf_hash_map_seq_show,
+};
+
+static const struct bpf_iter_seq_info iter_seq_info = {
+	.seq_ops		= &bpf_hash_map_seq_ops,
+	.init_seq_private	= bpf_iter_init_hash_map,
+	.fini_seq_private	= bpf_iter_fini_hash_map,
+	.seq_priv_size		= sizeof(struct bpf_iter_seq_hash_map_info),
+};
+
+static int htab_map_btf_id;
 const struct bpf_map_ops htab_map_ops = {
 	.map_alloc_check = htab_map_alloc_check,
 	.map_alloc = htab_map_alloc,
@@ -1551,8 +1820,12 @@ const struct bpf_map_ops htab_map_ops = {
 	.map_gen_lookup = htab_map_gen_lookup,
 	.map_seq_show_elem = htab_map_seq_show_elem,
 	BATCH_OPS(htab),
+	.map_btf_name = "bpf_htab",
+	.map_btf_id = &htab_map_btf_id,
+	.iter_seq_info = &iter_seq_info,
 };
 
+static int htab_lru_map_btf_id;
 const struct bpf_map_ops htab_lru_map_ops = {
 	.map_alloc_check = htab_map_alloc_check,
 	.map_alloc = htab_map_alloc,
@@ -1565,6 +1838,9 @@ const struct bpf_map_ops htab_lru_map_ops = {
 	.map_gen_lookup = htab_lru_map_gen_lookup,
 	.map_seq_show_elem = htab_map_seq_show_elem,
 	BATCH_OPS(htab_lru),
+	.map_btf_name = "bpf_htab",
+	.map_btf_id = &htab_lru_map_btf_id,
+	.iter_seq_info = &iter_seq_info,
 };
 
 /* Called from eBPF program */
@@ -1669,6 +1945,7 @@ static void htab_percpu_map_seq_show_elem(struct bpf_map *map, void *key,
 	rcu_read_unlock();
 }
 
+static int htab_percpu_map_btf_id;
 const struct bpf_map_ops htab_percpu_map_ops = {
 	.map_alloc_check = htab_map_alloc_check,
 	.map_alloc = htab_map_alloc,
@@ -1679,8 +1956,12 @@ const struct bpf_map_ops htab_percpu_map_ops = {
 	.map_delete_elem = htab_map_delete_elem,
 	.map_seq_show_elem = htab_percpu_map_seq_show_elem,
 	BATCH_OPS(htab_percpu),
+	.map_btf_name = "bpf_htab",
+	.map_btf_id = &htab_percpu_map_btf_id,
+	.iter_seq_info = &iter_seq_info,
 };
 
+static int htab_lru_percpu_map_btf_id;
 const struct bpf_map_ops htab_lru_percpu_map_ops = {
 	.map_alloc_check = htab_map_alloc_check,
 	.map_alloc = htab_map_alloc,
@@ -1691,6 +1972,9 @@ const struct bpf_map_ops htab_lru_percpu_map_ops = {
 	.map_delete_elem = htab_lru_map_delete_elem,
 	.map_seq_show_elem = htab_percpu_map_seq_show_elem,
 	BATCH_OPS(htab_lru_percpu),
+	.map_btf_name = "bpf_htab",
+	.map_btf_id = &htab_lru_percpu_map_btf_id,
+	.iter_seq_info = &iter_seq_info,
 };
 
 static int fd_htab_map_alloc_check(union bpf_attr *attr)
@@ -1813,6 +2097,7 @@ static void htab_of_map_free(struct bpf_map *map)
 	fd_htab_map_free(map);
 }
 
+static int htab_of_maps_map_btf_id;
 const struct bpf_map_ops htab_of_maps_map_ops = {
 	.map_alloc_check = fd_htab_map_alloc_check,
 	.map_alloc = htab_of_map_alloc,
@@ -1825,4 +2110,6 @@ const struct bpf_map_ops htab_of_maps_map_ops = {
 	.map_fd_sys_lookup_elem = bpf_map_fd_sys_lookup_elem,
 	.map_gen_lookup = htab_of_map_gen_lookup,
 	.map_check_btf = map_check_no_btf,
+	.map_btf_name = "bpf_htab",
+	.map_btf_id = &htab_of_maps_map_btf_id,
 };
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index d8b7b110a1c5..be43ab3e619f 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -12,6 +12,8 @@
 #include <linux/filter.h>
 #include <linux/ctype.h>
 #include <linux/jiffies.h>
+#include <linux/pid_namespace.h>
+#include <linux/proc_ns.h>
 
 #include "../../lib/kstrtox.h"
 
@@ -149,7 +151,19 @@ BPF_CALL_0(bpf_ktime_get_ns)
 
 const struct bpf_func_proto bpf_ktime_get_ns_proto = {
 	.func		= bpf_ktime_get_ns,
-	.gpl_only	= true,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+};
+
+BPF_CALL_0(bpf_ktime_get_boot_ns)
+{
+	/* NMI safe access to clock boottime */
+	return ktime_get_boot_fast_ns();
+}
+
+const struct bpf_func_proto bpf_ktime_get_boot_ns_proto = {
+	.func		= bpf_ktime_get_boot_ns,
+	.gpl_only	= false,
 	.ret_type	= RET_INTEGER,
 };
 
@@ -338,6 +352,24 @@ const struct bpf_func_proto bpf_get_current_cgroup_id_proto = {
 	.ret_type	= RET_INTEGER,
 };
 
+BPF_CALL_1(bpf_get_current_ancestor_cgroup_id, int, ancestor_level)
+{
+	struct cgroup *cgrp = task_dfl_cgroup(current);
+	struct cgroup *ancestor;
+
+	ancestor = cgroup_ancestor(cgrp, ancestor_level);
+	if (!ancestor)
+		return 0;
+	return cgroup_id(ancestor);
+}
+
+const struct bpf_func_proto bpf_get_current_ancestor_cgroup_id_proto = {
+	.func		= bpf_get_current_ancestor_cgroup_id,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_ANYTHING,
+};
+
 #ifdef CONFIG_CGROUP_BPF
 DECLARE_PER_CPU(struct bpf_cgroup_storage*,
 		bpf_cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE]);
@@ -499,3 +531,157 @@ const struct bpf_func_proto bpf_strtoul_proto = {
 	.arg4_type	= ARG_PTR_TO_LONG,
 };
 #endif
+
+BPF_CALL_4(bpf_get_ns_current_pid_tgid, u64, dev, u64, ino,
+	   struct bpf_pidns_info *, nsdata, u32, size)
+{
+	struct task_struct *task = current;
+	struct pid_namespace *pidns;
+	int err = -EINVAL;
+
+	if (unlikely(size != sizeof(struct bpf_pidns_info)))
+		goto clear;
+
+	if (unlikely((u64)(dev_t)dev != dev))
+		goto clear;
+
+	if (unlikely(!task))
+		goto clear;
+
+	pidns = task_active_pid_ns(task);
+	if (unlikely(!pidns)) {
+		err = -ENOENT;
+		goto clear;
+	}
+
+	if (!ns_match(&pidns->ns, (dev_t)dev, ino))
+		goto clear;
+
+	nsdata->pid = task_pid_nr_ns(task, pidns);
+	nsdata->tgid = task_tgid_nr_ns(task, pidns);
+	return 0;
+clear:
+	memset((void *)nsdata, 0, (size_t) size);
+	return err;
+}
+
+const struct bpf_func_proto bpf_get_ns_current_pid_tgid_proto = {
+	.func		= bpf_get_ns_current_pid_tgid,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_ANYTHING,
+	.arg2_type	= ARG_ANYTHING,
+	.arg3_type      = ARG_PTR_TO_UNINIT_MEM,
+	.arg4_type      = ARG_CONST_SIZE,
+};
+
+static const struct bpf_func_proto bpf_get_raw_smp_processor_id_proto = {
+	.func		= bpf_get_raw_cpu_id,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+};
+
+BPF_CALL_5(bpf_event_output_data, void *, ctx, struct bpf_map *, map,
+	   u64, flags, void *, data, u64, size)
+{
+	if (unlikely(flags & ~(BPF_F_INDEX_MASK)))
+		return -EINVAL;
+
+	return bpf_event_output(map, flags, data, size, NULL, 0, NULL);
+}
+
+const struct bpf_func_proto bpf_event_output_data_proto =  {
+	.func		= bpf_event_output_data,
+	.gpl_only       = true,
+	.ret_type       = RET_INTEGER,
+	.arg1_type      = ARG_PTR_TO_CTX,
+	.arg2_type      = ARG_CONST_MAP_PTR,
+	.arg3_type      = ARG_ANYTHING,
+	.arg4_type      = ARG_PTR_TO_MEM,
+	.arg5_type      = ARG_CONST_SIZE_OR_ZERO,
+};
+
+const struct bpf_func_proto bpf_get_current_task_proto __weak;
+const struct bpf_func_proto bpf_probe_read_user_proto __weak;
+const struct bpf_func_proto bpf_probe_read_user_str_proto __weak;
+const struct bpf_func_proto bpf_probe_read_kernel_proto __weak;
+const struct bpf_func_proto bpf_probe_read_kernel_str_proto __weak;
+
+const struct bpf_func_proto *
+bpf_base_func_proto(enum bpf_func_id func_id)
+{
+	switch (func_id) {
+	case BPF_FUNC_map_lookup_elem:
+		return &bpf_map_lookup_elem_proto;
+	case BPF_FUNC_map_update_elem:
+		return &bpf_map_update_elem_proto;
+	case BPF_FUNC_map_delete_elem:
+		return &bpf_map_delete_elem_proto;
+	case BPF_FUNC_map_push_elem:
+		return &bpf_map_push_elem_proto;
+	case BPF_FUNC_map_pop_elem:
+		return &bpf_map_pop_elem_proto;
+	case BPF_FUNC_map_peek_elem:
+		return &bpf_map_peek_elem_proto;
+	case BPF_FUNC_get_prandom_u32:
+		return &bpf_get_prandom_u32_proto;
+	case BPF_FUNC_get_smp_processor_id:
+		return &bpf_get_raw_smp_processor_id_proto;
+	case BPF_FUNC_get_numa_node_id:
+		return &bpf_get_numa_node_id_proto;
+	case BPF_FUNC_tail_call:
+		return &bpf_tail_call_proto;
+	case BPF_FUNC_ktime_get_ns:
+		return &bpf_ktime_get_ns_proto;
+	case BPF_FUNC_ktime_get_boot_ns:
+		return &bpf_ktime_get_boot_ns_proto;
+	case BPF_FUNC_ringbuf_output:
+		return &bpf_ringbuf_output_proto;
+	case BPF_FUNC_ringbuf_reserve:
+		return &bpf_ringbuf_reserve_proto;
+	case BPF_FUNC_ringbuf_submit:
+		return &bpf_ringbuf_submit_proto;
+	case BPF_FUNC_ringbuf_discard:
+		return &bpf_ringbuf_discard_proto;
+	case BPF_FUNC_ringbuf_query:
+		return &bpf_ringbuf_query_proto;
+	default:
+		break;
+	}
+
+	if (!bpf_capable())
+		return NULL;
+
+	switch (func_id) {
+	case BPF_FUNC_spin_lock:
+		return &bpf_spin_lock_proto;
+	case BPF_FUNC_spin_unlock:
+		return &bpf_spin_unlock_proto;
+	case BPF_FUNC_trace_printk:
+		if (!perfmon_capable())
+			return NULL;
+		return bpf_get_trace_printk_proto();
+	case BPF_FUNC_jiffies64:
+		return &bpf_jiffies64_proto;
+	default:
+		break;
+	}
+
+	if (!perfmon_capable())
+		return NULL;
+
+	switch (func_id) {
+	case BPF_FUNC_get_current_task:
+		return &bpf_get_current_task_proto;
+	case BPF_FUNC_probe_read_user:
+		return &bpf_probe_read_user_proto;
+	case BPF_FUNC_probe_read_kernel:
+		return &bpf_probe_read_kernel_proto;
+	case BPF_FUNC_probe_read_user_str:
+		return &bpf_probe_read_user_str_proto;
+	case BPF_FUNC_probe_read_kernel_str:
+		return &bpf_probe_read_kernel_str_proto;
+	default:
+		return NULL;
+	}
+}
diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c
index 5e40e7fccc21..fb878ba3f22f 100644
--- a/kernel/bpf/inode.c
+++ b/kernel/bpf/inode.c
@@ -25,6 +25,7 @@ enum bpf_type {
 	BPF_TYPE_UNSPEC	= 0,
 	BPF_TYPE_PROG,
 	BPF_TYPE_MAP,
+	BPF_TYPE_LINK,
 };
 
 static void *bpf_any_get(void *raw, enum bpf_type type)
@@ -36,6 +37,9 @@ static void *bpf_any_get(void *raw, enum bpf_type type)
 	case BPF_TYPE_MAP:
 		bpf_map_inc_with_uref(raw);
 		break;
+	case BPF_TYPE_LINK:
+		bpf_link_inc(raw);
+		break;
 	default:
 		WARN_ON_ONCE(1);
 		break;
@@ -53,6 +57,9 @@ static void bpf_any_put(void *raw, enum bpf_type type)
 	case BPF_TYPE_MAP:
 		bpf_map_put_with_uref(raw);
 		break;
+	case BPF_TYPE_LINK:
+		bpf_link_put(raw);
+		break;
 	default:
 		WARN_ON_ONCE(1);
 		break;
@@ -63,20 +70,32 @@ static void *bpf_fd_probe_obj(u32 ufd, enum bpf_type *type)
 {
 	void *raw;
 
-	*type = BPF_TYPE_MAP;
 	raw = bpf_map_get_with_uref(ufd);
-	if (IS_ERR(raw)) {
+	if (!IS_ERR(raw)) {
+		*type = BPF_TYPE_MAP;
+		return raw;
+	}
+
+	raw = bpf_prog_get(ufd);
+	if (!IS_ERR(raw)) {
 		*type = BPF_TYPE_PROG;
-		raw = bpf_prog_get(ufd);
+		return raw;
 	}
 
-	return raw;
+	raw = bpf_link_get_from_fd(ufd);
+	if (!IS_ERR(raw)) {
+		*type = BPF_TYPE_LINK;
+		return raw;
+	}
+
+	return ERR_PTR(-EINVAL);
 }
 
 static const struct inode_operations bpf_dir_iops;
 
 static const struct inode_operations bpf_prog_iops = { };
 static const struct inode_operations bpf_map_iops  = { };
+static const struct inode_operations bpf_link_iops  = { };
 
 static struct inode *bpf_get_inode(struct super_block *sb,
 				   const struct inode *dir,
@@ -114,6 +133,8 @@ static int bpf_inode_type(const struct inode *inode, enum bpf_type *type)
 		*type = BPF_TYPE_PROG;
 	else if (inode->i_op == &bpf_map_iops)
 		*type = BPF_TYPE_MAP;
+	else if (inode->i_op == &bpf_link_iops)
+		*type = BPF_TYPE_LINK;
 	else
 		return -EACCES;
 
@@ -335,6 +356,15 @@ static int bpf_mkmap(struct dentry *dentry, umode_t mode, void *arg)
 			     &bpffs_map_fops : &bpffs_obj_fops);
 }
 
+static int bpf_mklink(struct dentry *dentry, umode_t mode, void *arg)
+{
+	struct bpf_link *link = arg;
+
+	return bpf_mkobj_ops(dentry, mode, arg, &bpf_link_iops,
+			     bpf_link_is_iter(link) ?
+			     &bpf_iter_fops : &bpffs_obj_fops);
+}
+
 static struct dentry *
 bpf_lookup(struct inode *dir, struct dentry *dentry, unsigned flags)
 {
@@ -411,6 +441,9 @@ static int bpf_obj_do_pin(const char __user *pathname, void *raw,
 	case BPF_TYPE_MAP:
 		ret = vfs_mkobj(dentry, mode, bpf_mkmap, raw);
 		break;
+	case BPF_TYPE_LINK:
+		ret = vfs_mkobj(dentry, mode, bpf_mklink, raw);
+		break;
 	default:
 		ret = -EPERM;
 	}
@@ -487,6 +520,8 @@ int bpf_obj_get_user(const char __user *pathname, int flags)
 		ret = bpf_prog_new_fd(raw);
 	else if (type == BPF_TYPE_MAP)
 		ret = bpf_map_new_fd(raw, f_flags);
+	else if (type == BPF_TYPE_LINK)
+		ret = bpf_link_new_fd(raw);
 	else
 		return -ENOENT;
 
@@ -504,6 +539,8 @@ static struct bpf_prog *__get_prog_inode(struct inode *inode, enum bpf_prog_type
 
 	if (inode->i_op == &bpf_map_iops)
 		return ERR_PTR(-EINVAL);
+	if (inode->i_op == &bpf_link_iops)
+		return ERR_PTR(-EINVAL);
 	if (inode->i_op != &bpf_prog_iops)
 		return ERR_PTR(-EACCES);
 
diff --git a/kernel/bpf/local_storage.c b/kernel/bpf/local_storage.c
index 33d01866bcc2..571bb351ed3b 100644
--- a/kernel/bpf/local_storage.c
+++ b/kernel/bpf/local_storage.c
@@ -13,6 +13,8 @@ DEFINE_PER_CPU(struct bpf_cgroup_storage*, bpf_cgroup_storage[MAX_BPF_CGROUP_STO
 
 #ifdef CONFIG_CGROUP_BPF
 
+#include "../cgroup/cgroup-internal.h"
+
 #define LOCAL_STORAGE_CREATE_FLAG_MASK					\
 	(BPF_F_NUMA_NODE | BPF_F_ACCESS_MASK)
 
@@ -20,7 +22,6 @@ struct bpf_cgroup_storage_map {
 	struct bpf_map map;
 
 	spinlock_t lock;
-	struct bpf_prog_aux *aux;
 	struct rb_root root;
 	struct list_head list;
 };
@@ -30,24 +31,41 @@ static struct bpf_cgroup_storage_map *map_to_storage(struct bpf_map *map)
 	return container_of(map, struct bpf_cgroup_storage_map, map);
 }
 
-static int bpf_cgroup_storage_key_cmp(
-	const struct bpf_cgroup_storage_key *key1,
-	const struct bpf_cgroup_storage_key *key2)
+static bool attach_type_isolated(const struct bpf_map *map)
 {
-	if (key1->cgroup_inode_id < key2->cgroup_inode_id)
-		return -1;
-	else if (key1->cgroup_inode_id > key2->cgroup_inode_id)
-		return 1;
-	else if (key1->attach_type < key2->attach_type)
-		return -1;
-	else if (key1->attach_type > key2->attach_type)
-		return 1;
+	return map->key_size == sizeof(struct bpf_cgroup_storage_key);
+}
+
+static int bpf_cgroup_storage_key_cmp(const struct bpf_cgroup_storage_map *map,
+				      const void *_key1, const void *_key2)
+{
+	if (attach_type_isolated(&map->map)) {
+		const struct bpf_cgroup_storage_key *key1 = _key1;
+		const struct bpf_cgroup_storage_key *key2 = _key2;
+
+		if (key1->cgroup_inode_id < key2->cgroup_inode_id)
+			return -1;
+		else if (key1->cgroup_inode_id > key2->cgroup_inode_id)
+			return 1;
+		else if (key1->attach_type < key2->attach_type)
+			return -1;
+		else if (key1->attach_type > key2->attach_type)
+			return 1;
+	} else {
+		const __u64 *cgroup_inode_id1 = _key1;
+		const __u64 *cgroup_inode_id2 = _key2;
+
+		if (*cgroup_inode_id1 < *cgroup_inode_id2)
+			return -1;
+		else if (*cgroup_inode_id1 > *cgroup_inode_id2)
+			return 1;
+	}
 	return 0;
 }
 
-static struct bpf_cgroup_storage *cgroup_storage_lookup(
-	struct bpf_cgroup_storage_map *map, struct bpf_cgroup_storage_key *key,
-	bool locked)
+struct bpf_cgroup_storage *
+cgroup_storage_lookup(struct bpf_cgroup_storage_map *map,
+		      void *key, bool locked)
 {
 	struct rb_root *root = &map->root;
 	struct rb_node *node;
@@ -61,7 +79,7 @@ static struct bpf_cgroup_storage *cgroup_storage_lookup(
 
 		storage = container_of(node, struct bpf_cgroup_storage, node);
 
-		switch (bpf_cgroup_storage_key_cmp(key, &storage->key)) {
+		switch (bpf_cgroup_storage_key_cmp(map, key, &storage->key)) {
 		case -1:
 			node = node->rb_left;
 			break;
@@ -93,7 +111,7 @@ static int cgroup_storage_insert(struct bpf_cgroup_storage_map *map,
 		this = container_of(*new, struct bpf_cgroup_storage, node);
 
 		parent = *new;
-		switch (bpf_cgroup_storage_key_cmp(&storage->key, &this->key)) {
+		switch (bpf_cgroup_storage_key_cmp(map, &storage->key, &this->key)) {
 		case -1:
 			new = &((*new)->rb_left);
 			break;
@@ -111,10 +129,9 @@ static int cgroup_storage_insert(struct bpf_cgroup_storage_map *map,
 	return 0;
 }
 
-static void *cgroup_storage_lookup_elem(struct bpf_map *_map, void *_key)
+static void *cgroup_storage_lookup_elem(struct bpf_map *_map, void *key)
 {
 	struct bpf_cgroup_storage_map *map = map_to_storage(_map);
-	struct bpf_cgroup_storage_key *key = _key;
 	struct bpf_cgroup_storage *storage;
 
 	storage = cgroup_storage_lookup(map, key, false);
@@ -124,17 +141,13 @@ static void *cgroup_storage_lookup_elem(struct bpf_map *_map, void *_key)
 	return &READ_ONCE(storage->buf)->data[0];
 }
 
-static int cgroup_storage_update_elem(struct bpf_map *map, void *_key,
+static int cgroup_storage_update_elem(struct bpf_map *map, void *key,
 				      void *value, u64 flags)
 {
-	struct bpf_cgroup_storage_key *key = _key;
 	struct bpf_cgroup_storage *storage;
 	struct bpf_storage_buffer *new;
 
-	if (unlikely(flags & ~(BPF_F_LOCK | BPF_EXIST | BPF_NOEXIST)))
-		return -EINVAL;
-
-	if (unlikely(flags & BPF_NOEXIST))
+	if (unlikely(flags & ~(BPF_F_LOCK | BPF_EXIST)))
 		return -EINVAL;
 
 	if (unlikely((flags & BPF_F_LOCK) &&
@@ -167,11 +180,10 @@ static int cgroup_storage_update_elem(struct bpf_map *map, void *_key,
 	return 0;
 }
 
-int bpf_percpu_cgroup_storage_copy(struct bpf_map *_map, void *_key,
+int bpf_percpu_cgroup_storage_copy(struct bpf_map *_map, void *key,
 				   void *value)
 {
 	struct bpf_cgroup_storage_map *map = map_to_storage(_map);
-	struct bpf_cgroup_storage_key *key = _key;
 	struct bpf_cgroup_storage *storage;
 	int cpu, off = 0;
 	u32 size;
@@ -197,11 +209,10 @@ int bpf_percpu_cgroup_storage_copy(struct bpf_map *_map, void *_key,
 	return 0;
 }
 
-int bpf_percpu_cgroup_storage_update(struct bpf_map *_map, void *_key,
+int bpf_percpu_cgroup_storage_update(struct bpf_map *_map, void *key,
 				     void *value, u64 map_flags)
 {
 	struct bpf_cgroup_storage_map *map = map_to_storage(_map);
-	struct bpf_cgroup_storage_key *key = _key;
 	struct bpf_cgroup_storage *storage;
 	int cpu, off = 0;
 	u32 size;
@@ -232,12 +243,10 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *_map, void *_key,
 	return 0;
 }
 
-static int cgroup_storage_get_next_key(struct bpf_map *_map, void *_key,
+static int cgroup_storage_get_next_key(struct bpf_map *_map, void *key,
 				       void *_next_key)
 {
 	struct bpf_cgroup_storage_map *map = map_to_storage(_map);
-	struct bpf_cgroup_storage_key *key = _key;
-	struct bpf_cgroup_storage_key *next = _next_key;
 	struct bpf_cgroup_storage *storage;
 
 	spin_lock_bh(&map->lock);
@@ -250,17 +259,23 @@ static int cgroup_storage_get_next_key(struct bpf_map *_map, void *_key,
 		if (!storage)
 			goto enoent;
 
-		storage = list_next_entry(storage, list);
+		storage = list_next_entry(storage, list_map);
 		if (!storage)
 			goto enoent;
 	} else {
 		storage = list_first_entry(&map->list,
-					 struct bpf_cgroup_storage, list);
+					 struct bpf_cgroup_storage, list_map);
 	}
 
 	spin_unlock_bh(&map->lock);
-	next->attach_type = storage->key.attach_type;
-	next->cgroup_inode_id = storage->key.cgroup_inode_id;
+
+	if (attach_type_isolated(&map->map)) {
+		struct bpf_cgroup_storage_key *next = _next_key;
+		*next = storage->key;
+	} else {
+		__u64 *next = _next_key;
+		*next = storage->key.cgroup_inode_id;
+	}
 	return 0;
 
 enoent:
@@ -275,7 +290,8 @@ static struct bpf_map *cgroup_storage_map_alloc(union bpf_attr *attr)
 	struct bpf_map_memory mem;
 	int ret;
 
-	if (attr->key_size != sizeof(struct bpf_cgroup_storage_key))
+	if (attr->key_size != sizeof(struct bpf_cgroup_storage_key) &&
+	    attr->key_size != sizeof(__u64))
 		return ERR_PTR(-EINVAL);
 
 	if (attr->value_size == 0)
@@ -318,6 +334,17 @@ static struct bpf_map *cgroup_storage_map_alloc(union bpf_attr *attr)
 static void cgroup_storage_map_free(struct bpf_map *_map)
 {
 	struct bpf_cgroup_storage_map *map = map_to_storage(_map);
+	struct list_head *storages = &map->list;
+	struct bpf_cgroup_storage *storage, *stmp;
+
+	mutex_lock(&cgroup_mutex);
+
+	list_for_each_entry_safe(storage, stmp, storages, list_map) {
+		bpf_cgroup_storage_unlink(storage);
+		bpf_cgroup_storage_free(storage);
+	}
+
+	mutex_unlock(&cgroup_mutex);
 
 	WARN_ON(!RB_EMPTY_ROOT(&map->root));
 	WARN_ON(!list_empty(&map->list));
@@ -335,49 +362,63 @@ static int cgroup_storage_check_btf(const struct bpf_map *map,
 				    const struct btf_type *key_type,
 				    const struct btf_type *value_type)
 {
-	struct btf_member *m;
-	u32 offset, size;
-
-	/* Key is expected to be of struct bpf_cgroup_storage_key type,
-	 * which is:
-	 * struct bpf_cgroup_storage_key {
-	 *	__u64	cgroup_inode_id;
-	 *	__u32	attach_type;
-	 * };
-	 */
+	if (attach_type_isolated(map)) {
+		struct btf_member *m;
+		u32 offset, size;
+
+		/* Key is expected to be of struct bpf_cgroup_storage_key type,
+		 * which is:
+		 * struct bpf_cgroup_storage_key {
+		 *	__u64	cgroup_inode_id;
+		 *	__u32	attach_type;
+		 * };
+		 */
+
+		/*
+		 * Key_type must be a structure with two fields.
+		 */
+		if (BTF_INFO_KIND(key_type->info) != BTF_KIND_STRUCT ||
+		    BTF_INFO_VLEN(key_type->info) != 2)
+			return -EINVAL;
+
+		/*
+		 * The first field must be a 64 bit integer at 0 offset.
+		 */
+		m = (struct btf_member *)(key_type + 1);
+		size = sizeof_field(struct bpf_cgroup_storage_key, cgroup_inode_id);
+		if (!btf_member_is_reg_int(btf, key_type, m, 0, size))
+			return -EINVAL;
+
+		/*
+		 * The second field must be a 32 bit integer at 64 bit offset.
+		 */
+		m++;
+		offset = offsetof(struct bpf_cgroup_storage_key, attach_type);
+		size = sizeof_field(struct bpf_cgroup_storage_key, attach_type);
+		if (!btf_member_is_reg_int(btf, key_type, m, offset, size))
+			return -EINVAL;
+	} else {
+		u32 int_data;
 
-	/*
-	 * Key_type must be a structure with two fields.
-	 */
-	if (BTF_INFO_KIND(key_type->info) != BTF_KIND_STRUCT ||
-	    BTF_INFO_VLEN(key_type->info) != 2)
-		return -EINVAL;
+		/*
+		 * Key is expected to be u64, which stores the cgroup_inode_id
+		 */
 
-	/*
-	 * The first field must be a 64 bit integer at 0 offset.
-	 */
-	m = (struct btf_member *)(key_type + 1);
-	size = sizeof_field(struct bpf_cgroup_storage_key, cgroup_inode_id);
-	if (!btf_member_is_reg_int(btf, key_type, m, 0, size))
-		return -EINVAL;
+		if (BTF_INFO_KIND(key_type->info) != BTF_KIND_INT)
+			return -EINVAL;
 
-	/*
-	 * The second field must be a 32 bit integer at 64 bit offset.
-	 */
-	m++;
-	offset = offsetof(struct bpf_cgroup_storage_key, attach_type);
-	size = sizeof_field(struct bpf_cgroup_storage_key, attach_type);
-	if (!btf_member_is_reg_int(btf, key_type, m, offset, size))
-		return -EINVAL;
+		int_data = *(u32 *)(key_type + 1);
+		if (BTF_INT_BITS(int_data) != 64 || BTF_INT_OFFSET(int_data))
+			return -EINVAL;
+	}
 
 	return 0;
 }
 
-static void cgroup_storage_seq_show_elem(struct bpf_map *map, void *_key,
+static void cgroup_storage_seq_show_elem(struct bpf_map *map, void *key,
 					 struct seq_file *m)
 {
 	enum bpf_cgroup_storage_type stype = cgroup_storage_type(map);
-	struct bpf_cgroup_storage_key *key = _key;
 	struct bpf_cgroup_storage *storage;
 	int cpu;
 
@@ -409,6 +450,7 @@ static void cgroup_storage_seq_show_elem(struct bpf_map *map, void *_key,
 	rcu_read_unlock();
 }
 
+static int cgroup_storage_map_btf_id;
 const struct bpf_map_ops cgroup_storage_map_ops = {
 	.map_alloc = cgroup_storage_map_alloc,
 	.map_free = cgroup_storage_map_free,
@@ -418,43 +460,20 @@ const struct bpf_map_ops cgroup_storage_map_ops = {
 	.map_delete_elem = cgroup_storage_delete_elem,
 	.map_check_btf = cgroup_storage_check_btf,
 	.map_seq_show_elem = cgroup_storage_seq_show_elem,
+	.map_btf_name = "bpf_cgroup_storage_map",
+	.map_btf_id = &cgroup_storage_map_btf_id,
 };
 
 int bpf_cgroup_storage_assign(struct bpf_prog_aux *aux, struct bpf_map *_map)
 {
 	enum bpf_cgroup_storage_type stype = cgroup_storage_type(_map);
-	struct bpf_cgroup_storage_map *map = map_to_storage(_map);
-	int ret = -EBUSY;
-
-	spin_lock_bh(&map->lock);
 
-	if (map->aux && map->aux != aux)
-		goto unlock;
 	if (aux->cgroup_storage[stype] &&
 	    aux->cgroup_storage[stype] != _map)
-		goto unlock;
+		return -EBUSY;
 
-	map->aux = aux;
 	aux->cgroup_storage[stype] = _map;
-	ret = 0;
-unlock:
-	spin_unlock_bh(&map->lock);
-
-	return ret;
-}
-
-void bpf_cgroup_storage_release(struct bpf_prog_aux *aux, struct bpf_map *_map)
-{
-	enum bpf_cgroup_storage_type stype = cgroup_storage_type(_map);
-	struct bpf_cgroup_storage_map *map = map_to_storage(_map);
-
-	spin_lock_bh(&map->lock);
-	if (map->aux == aux) {
-		WARN_ON(aux->cgroup_storage[stype] != _map);
-		map->aux = NULL;
-		aux->cgroup_storage[stype] = NULL;
-	}
-	spin_unlock_bh(&map->lock);
+	return 0;
 }
 
 static size_t bpf_cgroup_storage_calculate_size(struct bpf_map *map, u32 *pages)
@@ -575,7 +594,8 @@ void bpf_cgroup_storage_link(struct bpf_cgroup_storage *storage,
 
 	spin_lock_bh(&map->lock);
 	WARN_ON(cgroup_storage_insert(map, storage));
-	list_add(&storage->list, &map->list);
+	list_add(&storage->list_map, &map->list);
+	list_add(&storage->list_cg, &cgroup->bpf.storages);
 	spin_unlock_bh(&map->lock);
 }
 
@@ -593,7 +613,8 @@ void bpf_cgroup_storage_unlink(struct bpf_cgroup_storage *storage)
 	root = &map->root;
 	rb_erase(&storage->node, root);
 
-	list_del(&storage->list);
+	list_del(&storage->list_map);
+	list_del(&storage->list_cg);
 	spin_unlock_bh(&map->lock);
 }
 
diff --git a/kernel/bpf/lpm_trie.c b/kernel/bpf/lpm_trie.c
index 56e6c75d354d..44474bf3ab7a 100644
--- a/kernel/bpf/lpm_trie.c
+++ b/kernel/bpf/lpm_trie.c
@@ -25,7 +25,7 @@ struct lpm_trie_node {
 	struct lpm_trie_node __rcu	*child[2];
 	u32				prefixlen;
 	u32				flags;
-	u8				data[0];
+	u8				data[];
 };
 
 struct lpm_trie {
@@ -34,7 +34,7 @@ struct lpm_trie {
 	size_t				n_entries;
 	size_t				max_prefixlen;
 	size_t				data_size;
-	raw_spinlock_t			lock;
+	spinlock_t			lock;
 };
 
 /* This trie implements a longest prefix match algorithm that can be used to
@@ -315,7 +315,7 @@ static int trie_update_elem(struct bpf_map *map,
 	if (key->prefixlen > trie->max_prefixlen)
 		return -EINVAL;
 
-	raw_spin_lock_irqsave(&trie->lock, irq_flags);
+	spin_lock_irqsave(&trie->lock, irq_flags);
 
 	/* Allocate and fill a new node */
 
@@ -422,7 +422,7 @@ out:
 		kfree(im_node);
 	}
 
-	raw_spin_unlock_irqrestore(&trie->lock, irq_flags);
+	spin_unlock_irqrestore(&trie->lock, irq_flags);
 
 	return ret;
 }
@@ -442,7 +442,7 @@ static int trie_delete_elem(struct bpf_map *map, void *_key)
 	if (key->prefixlen > trie->max_prefixlen)
 		return -EINVAL;
 
-	raw_spin_lock_irqsave(&trie->lock, irq_flags);
+	spin_lock_irqsave(&trie->lock, irq_flags);
 
 	/* Walk the tree looking for an exact key/length match and keeping
 	 * track of the path we traverse.  We will need to know the node
@@ -518,7 +518,7 @@ static int trie_delete_elem(struct bpf_map *map, void *_key)
 	kfree_rcu(node, rcu);
 
 out:
-	raw_spin_unlock_irqrestore(&trie->lock, irq_flags);
+	spin_unlock_irqrestore(&trie->lock, irq_flags);
 
 	return ret;
 }
@@ -543,7 +543,7 @@ static struct bpf_map *trie_alloc(union bpf_attr *attr)
 	u64 cost = sizeof(*trie), cost_per_node;
 	int ret;
 
-	if (!capable(CAP_SYS_ADMIN))
+	if (!bpf_capable())
 		return ERR_PTR(-EPERM);
 
 	/* check sanity of attributes */
@@ -575,7 +575,7 @@ static struct bpf_map *trie_alloc(union bpf_attr *attr)
 	if (ret)
 		goto out_err;
 
-	raw_spin_lock_init(&trie->lock);
+	spin_lock_init(&trie->lock);
 
 	return &trie->map;
 out_err:
@@ -589,11 +589,6 @@ static void trie_free(struct bpf_map *map)
 	struct lpm_trie_node __rcu **slot;
 	struct lpm_trie_node *node;
 
-	/* Wait for outstanding programs to complete
-	 * update/lookup/delete/get_next_key and free the trie.
-	 */
-	synchronize_rcu();
-
 	/* Always start at the root and walk down to a node that has no
 	 * children. Then free that node, nullify its reference in the parent
 	 * and start over.
@@ -735,6 +730,7 @@ static int trie_check_btf(const struct bpf_map *map,
 	       -EINVAL : 0;
 }
 
+static int trie_map_btf_id;
 const struct bpf_map_ops trie_map_ops = {
 	.map_alloc = trie_alloc,
 	.map_free = trie_free,
@@ -743,4 +739,6 @@ const struct bpf_map_ops trie_map_ops = {
 	.map_update_elem = trie_update_elem,
 	.map_delete_elem = trie_delete_elem,
 	.map_check_btf = trie_check_btf,
+	.map_btf_name = "lpm_trie",
+	.map_btf_id = &trie_map_btf_id,
 };
diff --git a/kernel/bpf/map_in_map.c b/kernel/bpf/map_in_map.c
index b3c48d1533cb..17738c93bec8 100644
--- a/kernel/bpf/map_in_map.c
+++ b/kernel/bpf/map_in_map.c
@@ -60,7 +60,7 @@ struct bpf_map *bpf_map_meta_alloc(int inner_map_ufd)
 	/* Misc members not needed in bpf_map_meta_equal() check. */
 	inner_map_meta->ops = inner_map->ops;
 	if (inner_map->ops == &array_map_ops) {
-		inner_map_meta->unpriv_array = inner_map->unpriv_array;
+		inner_map_meta->bypass_spec_v1 = inner_map->bypass_spec_v1;
 		container_of(inner_map_meta, struct bpf_array, map)->index_mask =
 		     container_of(inner_map, struct bpf_array, map)->index_mask;
 	}
diff --git a/kernel/bpf/map_iter.c b/kernel/bpf/map_iter.c
new file mode 100644
index 000000000000..af86048e5afd
--- /dev/null
+++ b/kernel/bpf/map_iter.c
@@ -0,0 +1,180 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (c) 2020 Facebook */
+#include <linux/bpf.h>
+#include <linux/fs.h>
+#include <linux/filter.h>
+#include <linux/kernel.h>
+#include <linux/btf_ids.h>
+
+struct bpf_iter_seq_map_info {
+	u32 map_id;
+};
+
+static void *bpf_map_seq_start(struct seq_file *seq, loff_t *pos)
+{
+	struct bpf_iter_seq_map_info *info = seq->private;
+	struct bpf_map *map;
+
+	map = bpf_map_get_curr_or_next(&info->map_id);
+	if (!map)
+		return NULL;
+
+	if (*pos == 0)
+		++*pos;
+	return map;
+}
+
+static void *bpf_map_seq_next(struct seq_file *seq, void *v, loff_t *pos)
+{
+	struct bpf_iter_seq_map_info *info = seq->private;
+
+	++*pos;
+	++info->map_id;
+	bpf_map_put((struct bpf_map *)v);
+	return bpf_map_get_curr_or_next(&info->map_id);
+}
+
+struct bpf_iter__bpf_map {
+	__bpf_md_ptr(struct bpf_iter_meta *, meta);
+	__bpf_md_ptr(struct bpf_map *, map);
+};
+
+DEFINE_BPF_ITER_FUNC(bpf_map, struct bpf_iter_meta *meta, struct bpf_map *map)
+
+static int __bpf_map_seq_show(struct seq_file *seq, void *v, bool in_stop)
+{
+	struct bpf_iter__bpf_map ctx;
+	struct bpf_iter_meta meta;
+	struct bpf_prog *prog;
+	int ret = 0;
+
+	ctx.meta = &meta;
+	ctx.map = v;
+	meta.seq = seq;
+	prog = bpf_iter_get_info(&meta, in_stop);
+	if (prog)
+		ret = bpf_iter_run_prog(prog, &ctx);
+
+	return ret;
+}
+
+static int bpf_map_seq_show(struct seq_file *seq, void *v)
+{
+	return __bpf_map_seq_show(seq, v, false);
+}
+
+static void bpf_map_seq_stop(struct seq_file *seq, void *v)
+{
+	if (!v)
+		(void)__bpf_map_seq_show(seq, v, true);
+	else
+		bpf_map_put((struct bpf_map *)v);
+}
+
+static const struct seq_operations bpf_map_seq_ops = {
+	.start	= bpf_map_seq_start,
+	.next	= bpf_map_seq_next,
+	.stop	= bpf_map_seq_stop,
+	.show	= bpf_map_seq_show,
+};
+
+BTF_ID_LIST(btf_bpf_map_id)
+BTF_ID(struct, bpf_map)
+
+static const struct bpf_iter_seq_info bpf_map_seq_info = {
+	.seq_ops		= &bpf_map_seq_ops,
+	.init_seq_private	= NULL,
+	.fini_seq_private	= NULL,
+	.seq_priv_size		= sizeof(struct bpf_iter_seq_map_info),
+};
+
+static struct bpf_iter_reg bpf_map_reg_info = {
+	.target			= "bpf_map",
+	.ctx_arg_info_size	= 1,
+	.ctx_arg_info		= {
+		{ offsetof(struct bpf_iter__bpf_map, map),
+		  PTR_TO_BTF_ID_OR_NULL },
+	},
+	.seq_info		= &bpf_map_seq_info,
+};
+
+static int bpf_iter_attach_map(struct bpf_prog *prog,
+			       union bpf_iter_link_info *linfo,
+			       struct bpf_iter_aux_info *aux)
+{
+	u32 key_acc_size, value_acc_size, key_size, value_size;
+	struct bpf_map *map;
+	bool is_percpu = false;
+	int err = -EINVAL;
+
+	if (!linfo->map.map_fd)
+		return -EBADF;
+
+	map = bpf_map_get_with_uref(linfo->map.map_fd);
+	if (IS_ERR(map))
+		return PTR_ERR(map);
+
+	if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH ||
+	    map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH ||
+	    map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY)
+		is_percpu = true;
+	else if (map->map_type != BPF_MAP_TYPE_HASH &&
+		 map->map_type != BPF_MAP_TYPE_LRU_HASH &&
+		 map->map_type != BPF_MAP_TYPE_ARRAY)
+		goto put_map;
+
+	key_acc_size = prog->aux->max_rdonly_access;
+	value_acc_size = prog->aux->max_rdwr_access;
+	key_size = map->key_size;
+	if (!is_percpu)
+		value_size = map->value_size;
+	else
+		value_size = round_up(map->value_size, 8) * num_possible_cpus();
+
+	if (key_acc_size > key_size || value_acc_size > value_size) {
+		err = -EACCES;
+		goto put_map;
+	}
+
+	aux->map = map;
+	return 0;
+
+put_map:
+	bpf_map_put_with_uref(map);
+	return err;
+}
+
+static void bpf_iter_detach_map(struct bpf_iter_aux_info *aux)
+{
+	bpf_map_put_with_uref(aux->map);
+}
+
+DEFINE_BPF_ITER_FUNC(bpf_map_elem, struct bpf_iter_meta *meta,
+		     struct bpf_map *map, void *key, void *value)
+
+static const struct bpf_iter_reg bpf_map_elem_reg_info = {
+	.target			= "bpf_map_elem",
+	.attach_target		= bpf_iter_attach_map,
+	.detach_target		= bpf_iter_detach_map,
+	.ctx_arg_info_size	= 2,
+	.ctx_arg_info		= {
+		{ offsetof(struct bpf_iter__bpf_map_elem, key),
+		  PTR_TO_RDONLY_BUF_OR_NULL },
+		{ offsetof(struct bpf_iter__bpf_map_elem, value),
+		  PTR_TO_RDWR_BUF_OR_NULL },
+	},
+};
+
+static int __init bpf_map_iter_init(void)
+{
+	int ret;
+
+	bpf_map_reg_info.ctx_arg_info[0].btf_id = *btf_bpf_map_id;
+	ret = bpf_iter_reg_target(&bpf_map_reg_info);
+	if (ret)
+		return ret;
+
+	return bpf_iter_reg_target(&bpf_map_elem_reg_info);
+}
+
+late_initcall(bpf_map_iter_init);
diff --git a/kernel/bpf/net_namespace.c b/kernel/bpf/net_namespace.c
new file mode 100644
index 000000000000..542f275bf252
--- /dev/null
+++ b/kernel/bpf/net_namespace.c
@@ -0,0 +1,566 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/bpf.h>
+#include <linux/filter.h>
+#include <net/net_namespace.h>
+
+/*
+ * Functions to manage BPF programs attached to netns
+ */
+
+struct bpf_netns_link {
+	struct bpf_link	link;
+	enum bpf_attach_type type;
+	enum netns_bpf_attach_type netns_type;
+
+	/* We don't hold a ref to net in order to auto-detach the link
+	 * when netns is going away. Instead we rely on pernet
+	 * pre_exit callback to clear this pointer. Must be accessed
+	 * with netns_bpf_mutex held.
+	 */
+	struct net *net;
+	struct list_head node; /* node in list of links attached to net */
+};
+
+/* Protects updates to netns_bpf */
+DEFINE_MUTEX(netns_bpf_mutex);
+
+static void netns_bpf_attach_type_unneed(enum netns_bpf_attach_type type)
+{
+	switch (type) {
+#ifdef CONFIG_INET
+	case NETNS_BPF_SK_LOOKUP:
+		static_branch_dec(&bpf_sk_lookup_enabled);
+		break;
+#endif
+	default:
+		break;
+	}
+}
+
+static void netns_bpf_attach_type_need(enum netns_bpf_attach_type type)
+{
+	switch (type) {
+#ifdef CONFIG_INET
+	case NETNS_BPF_SK_LOOKUP:
+		static_branch_inc(&bpf_sk_lookup_enabled);
+		break;
+#endif
+	default:
+		break;
+	}
+}
+
+/* Must be called with netns_bpf_mutex held. */
+static void netns_bpf_run_array_detach(struct net *net,
+				       enum netns_bpf_attach_type type)
+{
+	struct bpf_prog_array *run_array;
+
+	run_array = rcu_replace_pointer(net->bpf.run_array[type], NULL,
+					lockdep_is_held(&netns_bpf_mutex));
+	bpf_prog_array_free(run_array);
+}
+
+static int link_index(struct net *net, enum netns_bpf_attach_type type,
+		      struct bpf_netns_link *link)
+{
+	struct bpf_netns_link *pos;
+	int i = 0;
+
+	list_for_each_entry(pos, &net->bpf.links[type], node) {
+		if (pos == link)
+			return i;
+		i++;
+	}
+	return -ENOENT;
+}
+
+static int link_count(struct net *net, enum netns_bpf_attach_type type)
+{
+	struct list_head *pos;
+	int i = 0;
+
+	list_for_each(pos, &net->bpf.links[type])
+		i++;
+	return i;
+}
+
+static void fill_prog_array(struct net *net, enum netns_bpf_attach_type type,
+			    struct bpf_prog_array *prog_array)
+{
+	struct bpf_netns_link *pos;
+	unsigned int i = 0;
+
+	list_for_each_entry(pos, &net->bpf.links[type], node) {
+		prog_array->items[i].prog = pos->link.prog;
+		i++;
+	}
+}
+
+static void bpf_netns_link_release(struct bpf_link *link)
+{
+	struct bpf_netns_link *net_link =
+		container_of(link, struct bpf_netns_link, link);
+	enum netns_bpf_attach_type type = net_link->netns_type;
+	struct bpf_prog_array *old_array, *new_array;
+	struct net *net;
+	int cnt, idx;
+
+	mutex_lock(&netns_bpf_mutex);
+
+	/* We can race with cleanup_net, but if we see a non-NULL
+	 * struct net pointer, pre_exit has not run yet and wait for
+	 * netns_bpf_mutex.
+	 */
+	net = net_link->net;
+	if (!net)
+		goto out_unlock;
+
+	/* Mark attach point as unused */
+	netns_bpf_attach_type_unneed(type);
+
+	/* Remember link position in case of safe delete */
+	idx = link_index(net, type, net_link);
+	list_del(&net_link->node);
+
+	cnt = link_count(net, type);
+	if (!cnt) {
+		netns_bpf_run_array_detach(net, type);
+		goto out_unlock;
+	}
+
+	old_array = rcu_dereference_protected(net->bpf.run_array[type],
+					      lockdep_is_held(&netns_bpf_mutex));
+	new_array = bpf_prog_array_alloc(cnt, GFP_KERNEL);
+	if (!new_array) {
+		WARN_ON(bpf_prog_array_delete_safe_at(old_array, idx));
+		goto out_unlock;
+	}
+	fill_prog_array(net, type, new_array);
+	rcu_assign_pointer(net->bpf.run_array[type], new_array);
+	bpf_prog_array_free(old_array);
+
+out_unlock:
+	net_link->net = NULL;
+	mutex_unlock(&netns_bpf_mutex);
+}
+
+static int bpf_netns_link_detach(struct bpf_link *link)
+{
+	bpf_netns_link_release(link);
+	return 0;
+}
+
+static void bpf_netns_link_dealloc(struct bpf_link *link)
+{
+	struct bpf_netns_link *net_link =
+		container_of(link, struct bpf_netns_link, link);
+
+	kfree(net_link);
+}
+
+static int bpf_netns_link_update_prog(struct bpf_link *link,
+				      struct bpf_prog *new_prog,
+				      struct bpf_prog *old_prog)
+{
+	struct bpf_netns_link *net_link =
+		container_of(link, struct bpf_netns_link, link);
+	enum netns_bpf_attach_type type = net_link->netns_type;
+	struct bpf_prog_array *run_array;
+	struct net *net;
+	int idx, ret;
+
+	if (old_prog && old_prog != link->prog)
+		return -EPERM;
+	if (new_prog->type != link->prog->type)
+		return -EINVAL;
+
+	mutex_lock(&netns_bpf_mutex);
+
+	net = net_link->net;
+	if (!net || !check_net(net)) {
+		/* Link auto-detached or netns dying */
+		ret = -ENOLINK;
+		goto out_unlock;
+	}
+
+	run_array = rcu_dereference_protected(net->bpf.run_array[type],
+					      lockdep_is_held(&netns_bpf_mutex));
+	idx = link_index(net, type, net_link);
+	ret = bpf_prog_array_update_at(run_array, idx, new_prog);
+	if (ret)
+		goto out_unlock;
+
+	old_prog = xchg(&link->prog, new_prog);
+	bpf_prog_put(old_prog);
+
+out_unlock:
+	mutex_unlock(&netns_bpf_mutex);
+	return ret;
+}
+
+static int bpf_netns_link_fill_info(const struct bpf_link *link,
+				    struct bpf_link_info *info)
+{
+	const struct bpf_netns_link *net_link =
+		container_of(link, struct bpf_netns_link, link);
+	unsigned int inum = 0;
+	struct net *net;
+
+	mutex_lock(&netns_bpf_mutex);
+	net = net_link->net;
+	if (net && check_net(net))
+		inum = net->ns.inum;
+	mutex_unlock(&netns_bpf_mutex);
+
+	info->netns.netns_ino = inum;
+	info->netns.attach_type = net_link->type;
+	return 0;
+}
+
+static void bpf_netns_link_show_fdinfo(const struct bpf_link *link,
+				       struct seq_file *seq)
+{
+	struct bpf_link_info info = {};
+
+	bpf_netns_link_fill_info(link, &info);
+	seq_printf(seq,
+		   "netns_ino:\t%u\n"
+		   "attach_type:\t%u\n",
+		   info.netns.netns_ino,
+		   info.netns.attach_type);
+}
+
+static const struct bpf_link_ops bpf_netns_link_ops = {
+	.release = bpf_netns_link_release,
+	.dealloc = bpf_netns_link_dealloc,
+	.detach = bpf_netns_link_detach,
+	.update_prog = bpf_netns_link_update_prog,
+	.fill_link_info = bpf_netns_link_fill_info,
+	.show_fdinfo = bpf_netns_link_show_fdinfo,
+};
+
+/* Must be called with netns_bpf_mutex held. */
+static int __netns_bpf_prog_query(const union bpf_attr *attr,
+				  union bpf_attr __user *uattr,
+				  struct net *net,
+				  enum netns_bpf_attach_type type)
+{
+	__u32 __user *prog_ids = u64_to_user_ptr(attr->query.prog_ids);
+	struct bpf_prog_array *run_array;
+	u32 prog_cnt = 0, flags = 0;
+
+	run_array = rcu_dereference_protected(net->bpf.run_array[type],
+					      lockdep_is_held(&netns_bpf_mutex));
+	if (run_array)
+		prog_cnt = bpf_prog_array_length(run_array);
+
+	if (copy_to_user(&uattr->query.attach_flags, &flags, sizeof(flags)))
+		return -EFAULT;
+	if (copy_to_user(&uattr->query.prog_cnt, &prog_cnt, sizeof(prog_cnt)))
+		return -EFAULT;
+	if (!attr->query.prog_cnt || !prog_ids || !prog_cnt)
+		return 0;
+
+	return bpf_prog_array_copy_to_user(run_array, prog_ids,
+					   attr->query.prog_cnt);
+}
+
+int netns_bpf_prog_query(const union bpf_attr *attr,
+			 union bpf_attr __user *uattr)
+{
+	enum netns_bpf_attach_type type;
+	struct net *net;
+	int ret;
+
+	if (attr->query.query_flags)
+		return -EINVAL;
+
+	type = to_netns_bpf_attach_type(attr->query.attach_type);
+	if (type < 0)
+		return -EINVAL;
+
+	net = get_net_ns_by_fd(attr->query.target_fd);
+	if (IS_ERR(net))
+		return PTR_ERR(net);
+
+	mutex_lock(&netns_bpf_mutex);
+	ret = __netns_bpf_prog_query(attr, uattr, net, type);
+	mutex_unlock(&netns_bpf_mutex);
+
+	put_net(net);
+	return ret;
+}
+
+int netns_bpf_prog_attach(const union bpf_attr *attr, struct bpf_prog *prog)
+{
+	struct bpf_prog_array *run_array;
+	enum netns_bpf_attach_type type;
+	struct bpf_prog *attached;
+	struct net *net;
+	int ret;
+
+	if (attr->target_fd || attr->attach_flags || attr->replace_bpf_fd)
+		return -EINVAL;
+
+	type = to_netns_bpf_attach_type(attr->attach_type);
+	if (type < 0)
+		return -EINVAL;
+
+	net = current->nsproxy->net_ns;
+	mutex_lock(&netns_bpf_mutex);
+
+	/* Attaching prog directly is not compatible with links */
+	if (!list_empty(&net->bpf.links[type])) {
+		ret = -EEXIST;
+		goto out_unlock;
+	}
+
+	switch (type) {
+	case NETNS_BPF_FLOW_DISSECTOR:
+		ret = flow_dissector_bpf_prog_attach_check(net, prog);
+		break;
+	default:
+		ret = -EINVAL;
+		break;
+	}
+	if (ret)
+		goto out_unlock;
+
+	attached = net->bpf.progs[type];
+	if (attached == prog) {
+		/* The same program cannot be attached twice */
+		ret = -EINVAL;
+		goto out_unlock;
+	}
+
+	run_array = rcu_dereference_protected(net->bpf.run_array[type],
+					      lockdep_is_held(&netns_bpf_mutex));
+	if (run_array) {
+		WRITE_ONCE(run_array->items[0].prog, prog);
+	} else {
+		run_array = bpf_prog_array_alloc(1, GFP_KERNEL);
+		if (!run_array) {
+			ret = -ENOMEM;
+			goto out_unlock;
+		}
+		run_array->items[0].prog = prog;
+		rcu_assign_pointer(net->bpf.run_array[type], run_array);
+	}
+
+	net->bpf.progs[type] = prog;
+	if (attached)
+		bpf_prog_put(attached);
+
+out_unlock:
+	mutex_unlock(&netns_bpf_mutex);
+
+	return ret;
+}
+
+/* Must be called with netns_bpf_mutex held. */
+static int __netns_bpf_prog_detach(struct net *net,
+				   enum netns_bpf_attach_type type,
+				   struct bpf_prog *old)
+{
+	struct bpf_prog *attached;
+
+	/* Progs attached via links cannot be detached */
+	if (!list_empty(&net->bpf.links[type]))
+		return -EINVAL;
+
+	attached = net->bpf.progs[type];
+	if (!attached || attached != old)
+		return -ENOENT;
+	netns_bpf_run_array_detach(net, type);
+	net->bpf.progs[type] = NULL;
+	bpf_prog_put(attached);
+	return 0;
+}
+
+int netns_bpf_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype)
+{
+	enum netns_bpf_attach_type type;
+	struct bpf_prog *prog;
+	int ret;
+
+	if (attr->target_fd)
+		return -EINVAL;
+
+	type = to_netns_bpf_attach_type(attr->attach_type);
+	if (type < 0)
+		return -EINVAL;
+
+	prog = bpf_prog_get_type(attr->attach_bpf_fd, ptype);
+	if (IS_ERR(prog))
+		return PTR_ERR(prog);
+
+	mutex_lock(&netns_bpf_mutex);
+	ret = __netns_bpf_prog_detach(current->nsproxy->net_ns, type, prog);
+	mutex_unlock(&netns_bpf_mutex);
+
+	bpf_prog_put(prog);
+
+	return ret;
+}
+
+static int netns_bpf_max_progs(enum netns_bpf_attach_type type)
+{
+	switch (type) {
+	case NETNS_BPF_FLOW_DISSECTOR:
+		return 1;
+	case NETNS_BPF_SK_LOOKUP:
+		return 64;
+	default:
+		return 0;
+	}
+}
+
+static int netns_bpf_link_attach(struct net *net, struct bpf_link *link,
+				 enum netns_bpf_attach_type type)
+{
+	struct bpf_netns_link *net_link =
+		container_of(link, struct bpf_netns_link, link);
+	struct bpf_prog_array *run_array;
+	int cnt, err;
+
+	mutex_lock(&netns_bpf_mutex);
+
+	cnt = link_count(net, type);
+	if (cnt >= netns_bpf_max_progs(type)) {
+		err = -E2BIG;
+		goto out_unlock;
+	}
+	/* Links are not compatible with attaching prog directly */
+	if (net->bpf.progs[type]) {
+		err = -EEXIST;
+		goto out_unlock;
+	}
+
+	switch (type) {
+	case NETNS_BPF_FLOW_DISSECTOR:
+		err = flow_dissector_bpf_prog_attach_check(net, link->prog);
+		break;
+	case NETNS_BPF_SK_LOOKUP:
+		err = 0; /* nothing to check */
+		break;
+	default:
+		err = -EINVAL;
+		break;
+	}
+	if (err)
+		goto out_unlock;
+
+	run_array = bpf_prog_array_alloc(cnt + 1, GFP_KERNEL);
+	if (!run_array) {
+		err = -ENOMEM;
+		goto out_unlock;
+	}
+
+	list_add_tail(&net_link->node, &net->bpf.links[type]);
+
+	fill_prog_array(net, type, run_array);
+	run_array = rcu_replace_pointer(net->bpf.run_array[type], run_array,
+					lockdep_is_held(&netns_bpf_mutex));
+	bpf_prog_array_free(run_array);
+
+	/* Mark attach point as used */
+	netns_bpf_attach_type_need(type);
+
+out_unlock:
+	mutex_unlock(&netns_bpf_mutex);
+	return err;
+}
+
+int netns_bpf_link_create(const union bpf_attr *attr, struct bpf_prog *prog)
+{
+	enum netns_bpf_attach_type netns_type;
+	struct bpf_link_primer link_primer;
+	struct bpf_netns_link *net_link;
+	enum bpf_attach_type type;
+	struct net *net;
+	int err;
+
+	if (attr->link_create.flags)
+		return -EINVAL;
+
+	type = attr->link_create.attach_type;
+	netns_type = to_netns_bpf_attach_type(type);
+	if (netns_type < 0)
+		return -EINVAL;
+
+	net = get_net_ns_by_fd(attr->link_create.target_fd);
+	if (IS_ERR(net))
+		return PTR_ERR(net);
+
+	net_link = kzalloc(sizeof(*net_link), GFP_USER);
+	if (!net_link) {
+		err = -ENOMEM;
+		goto out_put_net;
+	}
+	bpf_link_init(&net_link->link, BPF_LINK_TYPE_NETNS,
+		      &bpf_netns_link_ops, prog);
+	net_link->net = net;
+	net_link->type = type;
+	net_link->netns_type = netns_type;
+
+	err = bpf_link_prime(&net_link->link, &link_primer);
+	if (err) {
+		kfree(net_link);
+		goto out_put_net;
+	}
+
+	err = netns_bpf_link_attach(net, &net_link->link, netns_type);
+	if (err) {
+		bpf_link_cleanup(&link_primer);
+		goto out_put_net;
+	}
+
+	put_net(net);
+	return bpf_link_settle(&link_primer);
+
+out_put_net:
+	put_net(net);
+	return err;
+}
+
+static int __net_init netns_bpf_pernet_init(struct net *net)
+{
+	int type;
+
+	for (type = 0; type < MAX_NETNS_BPF_ATTACH_TYPE; type++)
+		INIT_LIST_HEAD(&net->bpf.links[type]);
+
+	return 0;
+}
+
+static void __net_exit netns_bpf_pernet_pre_exit(struct net *net)
+{
+	enum netns_bpf_attach_type type;
+	struct bpf_netns_link *net_link;
+
+	mutex_lock(&netns_bpf_mutex);
+	for (type = 0; type < MAX_NETNS_BPF_ATTACH_TYPE; type++) {
+		netns_bpf_run_array_detach(net, type);
+		list_for_each_entry(net_link, &net->bpf.links[type], node) {
+			net_link->net = NULL; /* auto-detach link */
+			netns_bpf_attach_type_unneed(type);
+		}
+		if (net->bpf.progs[type])
+			bpf_prog_put(net->bpf.progs[type]);
+	}
+	mutex_unlock(&netns_bpf_mutex);
+}
+
+static struct pernet_operations netns_bpf_pernet_ops __net_initdata = {
+	.init = netns_bpf_pernet_init,
+	.pre_exit = netns_bpf_pernet_pre_exit,
+};
+
+static int __init netns_bpf_init(void)
+{
+	return register_pernet_subsys(&netns_bpf_pernet_ops);
+}
+
+subsys_initcall(netns_bpf_init);
diff --git a/kernel/bpf/percpu_freelist.c b/kernel/bpf/percpu_freelist.c
index 6e090140b924..b367430e611c 100644
--- a/kernel/bpf/percpu_freelist.c
+++ b/kernel/bpf/percpu_freelist.c
@@ -25,12 +25,18 @@ void pcpu_freelist_destroy(struct pcpu_freelist *s)
 	free_percpu(s->freelist);
 }
 
+static inline void pcpu_freelist_push_node(struct pcpu_freelist_head *head,
+					   struct pcpu_freelist_node *node)
+{
+	node->next = head->first;
+	head->first = node;
+}
+
 static inline void ___pcpu_freelist_push(struct pcpu_freelist_head *head,
 					 struct pcpu_freelist_node *node)
 {
 	raw_spin_lock(&head->lock);
-	node->next = head->first;
-	head->first = node;
+	pcpu_freelist_push_node(head, node);
 	raw_spin_unlock(&head->lock);
 }
 
@@ -56,21 +62,16 @@ void pcpu_freelist_populate(struct pcpu_freelist *s, void *buf, u32 elem_size,
 			    u32 nr_elems)
 {
 	struct pcpu_freelist_head *head;
-	unsigned long flags;
 	int i, cpu, pcpu_entries;
 
 	pcpu_entries = nr_elems / num_possible_cpus() + 1;
 	i = 0;
 
-	/* disable irq to workaround lockdep false positive
-	 * in bpf usage pcpu_freelist_populate() will never race
-	 * with pcpu_freelist_push()
-	 */
-	local_irq_save(flags);
 	for_each_possible_cpu(cpu) {
 again:
 		head = per_cpu_ptr(s->freelist, cpu);
-		___pcpu_freelist_push(head, buf);
+		/* No locking required as this is not visible yet. */
+		pcpu_freelist_push_node(head, buf);
 		i++;
 		buf += elem_size;
 		if (i == nr_elems)
@@ -78,7 +79,6 @@ again:
 		if (i % pcpu_entries)
 			goto again;
 	}
-	local_irq_restore(flags);
 }
 
 struct pcpu_freelist_node *__pcpu_freelist_pop(struct pcpu_freelist *s)
diff --git a/kernel/bpf/prog_iter.c b/kernel/bpf/prog_iter.c
new file mode 100644
index 000000000000..53a73c841c13
--- /dev/null
+++ b/kernel/bpf/prog_iter.c
@@ -0,0 +1,107 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (c) 2020 Facebook */
+#include <linux/bpf.h>
+#include <linux/fs.h>
+#include <linux/filter.h>
+#include <linux/kernel.h>
+#include <linux/btf_ids.h>
+
+struct bpf_iter_seq_prog_info {
+	u32 prog_id;
+};
+
+static void *bpf_prog_seq_start(struct seq_file *seq, loff_t *pos)
+{
+	struct bpf_iter_seq_prog_info *info = seq->private;
+	struct bpf_prog *prog;
+
+	prog = bpf_prog_get_curr_or_next(&info->prog_id);
+	if (!prog)
+		return NULL;
+
+	if (*pos == 0)
+		++*pos;
+	return prog;
+}
+
+static void *bpf_prog_seq_next(struct seq_file *seq, void *v, loff_t *pos)
+{
+	struct bpf_iter_seq_prog_info *info = seq->private;
+
+	++*pos;
+	++info->prog_id;
+	bpf_prog_put((struct bpf_prog *)v);
+	return bpf_prog_get_curr_or_next(&info->prog_id);
+}
+
+struct bpf_iter__bpf_prog {
+	__bpf_md_ptr(struct bpf_iter_meta *, meta);
+	__bpf_md_ptr(struct bpf_prog *, prog);
+};
+
+DEFINE_BPF_ITER_FUNC(bpf_prog, struct bpf_iter_meta *meta, struct bpf_prog *prog)
+
+static int __bpf_prog_seq_show(struct seq_file *seq, void *v, bool in_stop)
+{
+	struct bpf_iter__bpf_prog ctx;
+	struct bpf_iter_meta meta;
+	struct bpf_prog *prog;
+	int ret = 0;
+
+	ctx.meta = &meta;
+	ctx.prog = v;
+	meta.seq = seq;
+	prog = bpf_iter_get_info(&meta, in_stop);
+	if (prog)
+		ret = bpf_iter_run_prog(prog, &ctx);
+
+	return ret;
+}
+
+static int bpf_prog_seq_show(struct seq_file *seq, void *v)
+{
+	return __bpf_prog_seq_show(seq, v, false);
+}
+
+static void bpf_prog_seq_stop(struct seq_file *seq, void *v)
+{
+	if (!v)
+		(void)__bpf_prog_seq_show(seq, v, true);
+	else
+		bpf_prog_put((struct bpf_prog *)v);
+}
+
+static const struct seq_operations bpf_prog_seq_ops = {
+	.start	= bpf_prog_seq_start,
+	.next	= bpf_prog_seq_next,
+	.stop	= bpf_prog_seq_stop,
+	.show	= bpf_prog_seq_show,
+};
+
+BTF_ID_LIST(btf_bpf_prog_id)
+BTF_ID(struct, bpf_prog)
+
+static const struct bpf_iter_seq_info bpf_prog_seq_info = {
+	.seq_ops		= &bpf_prog_seq_ops,
+	.init_seq_private	= NULL,
+	.fini_seq_private	= NULL,
+	.seq_priv_size		= sizeof(struct bpf_iter_seq_prog_info),
+};
+
+static struct bpf_iter_reg bpf_prog_reg_info = {
+	.target			= "bpf_prog",
+	.ctx_arg_info_size	= 1,
+	.ctx_arg_info		= {
+		{ offsetof(struct bpf_iter__bpf_prog, prog),
+		  PTR_TO_BTF_ID_OR_NULL },
+	},
+	.seq_info		= &bpf_prog_seq_info,
+};
+
+static int __init bpf_prog_iter_init(void)
+{
+	bpf_prog_reg_info.ctx_arg_info[0].btf_id = *btf_bpf_prog_id;
+	return bpf_iter_reg_target(&bpf_prog_reg_info);
+}
+
+late_initcall(bpf_prog_iter_init);
diff --git a/kernel/bpf/queue_stack_maps.c b/kernel/bpf/queue_stack_maps.c
index f697647ceb54..44184f82916a 100644
--- a/kernel/bpf/queue_stack_maps.c
+++ b/kernel/bpf/queue_stack_maps.c
@@ -19,7 +19,7 @@ struct bpf_queue_stack {
 	u32 head, tail;
 	u32 size; /* max_entries + 1 */
 
-	char elements[0] __aligned(8);
+	char elements[] __aligned(8);
 };
 
 static struct bpf_queue_stack *bpf_queue_stack(struct bpf_map *map)
@@ -45,7 +45,7 @@ static bool queue_stack_map_is_full(struct bpf_queue_stack *qs)
 /* Called from syscall */
 static int queue_stack_map_alloc_check(union bpf_attr *attr)
 {
-	if (!capable(CAP_SYS_ADMIN))
+	if (!bpf_capable())
 		return -EPERM;
 
 	/* check sanity of attributes */
@@ -101,13 +101,6 @@ static void queue_stack_map_free(struct bpf_map *map)
 {
 	struct bpf_queue_stack *qs = bpf_queue_stack(map);
 
-	/* at this point bpf_prog->aux->refcnt == 0 and this map->refcnt == 0,
-	 * so the programs (can be more than one that used this map) were
-	 * disconnected from events. Wait for outstanding critical sections in
-	 * these programs to complete
-	 */
-	synchronize_rcu();
-
 	bpf_map_area_free(qs);
 }
 
@@ -262,6 +255,7 @@ static int queue_stack_map_get_next_key(struct bpf_map *map, void *key,
 	return -EINVAL;
 }
 
+static int queue_map_btf_id;
 const struct bpf_map_ops queue_map_ops = {
 	.map_alloc_check = queue_stack_map_alloc_check,
 	.map_alloc = queue_stack_map_alloc,
@@ -273,8 +267,11 @@ const struct bpf_map_ops queue_map_ops = {
 	.map_pop_elem = queue_map_pop_elem,
 	.map_peek_elem = queue_map_peek_elem,
 	.map_get_next_key = queue_stack_map_get_next_key,
+	.map_btf_name = "bpf_queue_stack",
+	.map_btf_id = &queue_map_btf_id,
 };
 
+static int stack_map_btf_id;
 const struct bpf_map_ops stack_map_ops = {
 	.map_alloc_check = queue_stack_map_alloc_check,
 	.map_alloc = queue_stack_map_alloc,
@@ -286,4 +283,6 @@ const struct bpf_map_ops stack_map_ops = {
 	.map_pop_elem = stack_map_pop_elem,
 	.map_peek_elem = stack_map_peek_elem,
 	.map_get_next_key = queue_stack_map_get_next_key,
+	.map_btf_name = "bpf_queue_stack",
+	.map_btf_id = &stack_map_btf_id,
 };
diff --git a/kernel/bpf/reuseport_array.c b/kernel/bpf/reuseport_array.c
index 50c083ba978c..90b29c5b1da7 100644
--- a/kernel/bpf/reuseport_array.c
+++ b/kernel/bpf/reuseport_array.c
@@ -20,11 +20,14 @@ static struct reuseport_array *reuseport_array(struct bpf_map *map)
 /* The caller must hold the reuseport_lock */
 void bpf_sk_reuseport_detach(struct sock *sk)
 {
-	struct sock __rcu **socks;
+	uintptr_t sk_user_data;
 
 	write_lock_bh(&sk->sk_callback_lock);
-	socks = sk->sk_user_data;
-	if (socks) {
+	sk_user_data = (uintptr_t)sk->sk_user_data;
+	if (sk_user_data & SK_USER_DATA_BPF) {
+		struct sock __rcu **socks;
+
+		socks = (void *)(sk_user_data & SK_USER_DATA_PTRMASK);
 		WRITE_ONCE(sk->sk_user_data, NULL);
 		/*
 		 * Do not move this NULL assignment outside of
@@ -96,8 +99,6 @@ static void reuseport_array_free(struct bpf_map *map)
 	struct sock *sk;
 	u32 i;
 
-	synchronize_rcu();
-
 	/*
 	 * ops->map_*_elem() will not be able to access this
 	 * array now. Hence, this function only races with
@@ -154,7 +155,7 @@ static struct bpf_map *reuseport_array_alloc(union bpf_attr *attr)
 	struct bpf_map_memory mem;
 	u64 array_size;
 
-	if (!capable(CAP_SYS_ADMIN))
+	if (!bpf_capable())
 		return ERR_PTR(-EPERM);
 
 	array_size = sizeof(*array);
@@ -252,6 +253,7 @@ int bpf_fd_reuseport_array_update_elem(struct bpf_map *map, void *key,
 	struct sock *free_osk = NULL, *osk, *nsk;
 	struct sock_reuseport *reuse;
 	u32 index = *(u32 *)key;
+	uintptr_t sk_user_data;
 	struct socket *socket;
 	int err, fd;
 
@@ -305,12 +307,9 @@ int bpf_fd_reuseport_array_update_elem(struct bpf_map *map, void *key,
 	if (err)
 		goto put_file_unlock;
 
-	/* Ensure reuse->reuseport_id is set */
-	err = reuseport_get_id(reuse);
-	if (err < 0)
-		goto put_file_unlock;
-
-	WRITE_ONCE(nsk->sk_user_data, &array->ptrs[index]);
+	sk_user_data = (uintptr_t)&array->ptrs[index] | SK_USER_DATA_NOCOPY |
+		SK_USER_DATA_BPF;
+	WRITE_ONCE(nsk->sk_user_data, (void *)sk_user_data);
 	rcu_assign_pointer(array->ptrs[index], nsk);
 	free_osk = osk;
 	err = 0;
@@ -350,6 +349,7 @@ static int reuseport_array_get_next_key(struct bpf_map *map, void *key,
 	return 0;
 }
 
+static int reuseport_array_map_btf_id;
 const struct bpf_map_ops reuseport_array_ops = {
 	.map_alloc_check = reuseport_array_alloc_check,
 	.map_alloc = reuseport_array_alloc,
@@ -357,4 +357,6 @@ const struct bpf_map_ops reuseport_array_ops = {
 	.map_lookup_elem = reuseport_array_lookup_elem,
 	.map_get_next_key = reuseport_array_get_next_key,
 	.map_delete_elem = reuseport_array_delete_elem,
+	.map_btf_name = "reuseport_array",
+	.map_btf_id = &reuseport_array_map_btf_id,
 };
diff --git a/kernel/bpf/ringbuf.c b/kernel/bpf/ringbuf.c
new file mode 100644
index 000000000000..002f8a5c9e51
--- /dev/null
+++ b/kernel/bpf/ringbuf.c
@@ -0,0 +1,495 @@
+#include <linux/bpf.h>
+#include <linux/btf.h>
+#include <linux/err.h>
+#include <linux/irq_work.h>
+#include <linux/slab.h>
+#include <linux/filter.h>
+#include <linux/mm.h>
+#include <linux/vmalloc.h>
+#include <linux/wait.h>
+#include <linux/poll.h>
+#include <uapi/linux/btf.h>
+
+#define RINGBUF_CREATE_FLAG_MASK (BPF_F_NUMA_NODE)
+
+/* non-mmap()'able part of bpf_ringbuf (everything up to consumer page) */
+#define RINGBUF_PGOFF \
+	(offsetof(struct bpf_ringbuf, consumer_pos) >> PAGE_SHIFT)
+/* consumer page and producer page */
+#define RINGBUF_POS_PAGES 2
+
+#define RINGBUF_MAX_RECORD_SZ (UINT_MAX/4)
+
+/* Maximum size of ring buffer area is limited by 32-bit page offset within
+ * record header, counted in pages. Reserve 8 bits for extensibility, and take
+ * into account few extra pages for consumer/producer pages and
+ * non-mmap()'able parts. This gives 64GB limit, which seems plenty for single
+ * ring buffer.
+ */
+#define RINGBUF_MAX_DATA_SZ \
+	(((1ULL << 24) - RINGBUF_POS_PAGES - RINGBUF_PGOFF) * PAGE_SIZE)
+
+struct bpf_ringbuf {
+	wait_queue_head_t waitq;
+	struct irq_work work;
+	u64 mask;
+	struct page **pages;
+	int nr_pages;
+	spinlock_t spinlock ____cacheline_aligned_in_smp;
+	/* Consumer and producer counters are put into separate pages to allow
+	 * mapping consumer page as r/w, but restrict producer page to r/o.
+	 * This protects producer position from being modified by user-space
+	 * application and ruining in-kernel position tracking.
+	 */
+	unsigned long consumer_pos __aligned(PAGE_SIZE);
+	unsigned long producer_pos __aligned(PAGE_SIZE);
+	char data[] __aligned(PAGE_SIZE);
+};
+
+struct bpf_ringbuf_map {
+	struct bpf_map map;
+	struct bpf_map_memory memory;
+	struct bpf_ringbuf *rb;
+};
+
+/* 8-byte ring buffer record header structure */
+struct bpf_ringbuf_hdr {
+	u32 len;
+	u32 pg_off;
+};
+
+static struct bpf_ringbuf *bpf_ringbuf_area_alloc(size_t data_sz, int numa_node)
+{
+	const gfp_t flags = GFP_KERNEL | __GFP_RETRY_MAYFAIL | __GFP_NOWARN |
+			    __GFP_ZERO;
+	int nr_meta_pages = RINGBUF_PGOFF + RINGBUF_POS_PAGES;
+	int nr_data_pages = data_sz >> PAGE_SHIFT;
+	int nr_pages = nr_meta_pages + nr_data_pages;
+	struct page **pages, *page;
+	struct bpf_ringbuf *rb;
+	size_t array_size;
+	int i;
+
+	/* Each data page is mapped twice to allow "virtual"
+	 * continuous read of samples wrapping around the end of ring
+	 * buffer area:
+	 * ------------------------------------------------------
+	 * | meta pages |  real data pages  |  same data pages  |
+	 * ------------------------------------------------------
+	 * |            | 1 2 3 4 5 6 7 8 9 | 1 2 3 4 5 6 7 8 9 |
+	 * ------------------------------------------------------
+	 * |            | TA             DA | TA             DA |
+	 * ------------------------------------------------------
+	 *                               ^^^^^^^
+	 *                                  |
+	 * Here, no need to worry about special handling of wrapped-around
+	 * data due to double-mapped data pages. This works both in kernel and
+	 * when mmap()'ed in user-space, simplifying both kernel and
+	 * user-space implementations significantly.
+	 */
+	array_size = (nr_meta_pages + 2 * nr_data_pages) * sizeof(*pages);
+	if (array_size > PAGE_SIZE)
+		pages = vmalloc_node(array_size, numa_node);
+	else
+		pages = kmalloc_node(array_size, flags, numa_node);
+	if (!pages)
+		return NULL;
+
+	for (i = 0; i < nr_pages; i++) {
+		page = alloc_pages_node(numa_node, flags, 0);
+		if (!page) {
+			nr_pages = i;
+			goto err_free_pages;
+		}
+		pages[i] = page;
+		if (i >= nr_meta_pages)
+			pages[nr_data_pages + i] = page;
+	}
+
+	rb = vmap(pages, nr_meta_pages + 2 * nr_data_pages,
+		  VM_ALLOC | VM_USERMAP, PAGE_KERNEL);
+	if (rb) {
+		rb->pages = pages;
+		rb->nr_pages = nr_pages;
+		return rb;
+	}
+
+err_free_pages:
+	for (i = 0; i < nr_pages; i++)
+		__free_page(pages[i]);
+	kvfree(pages);
+	return NULL;
+}
+
+static void bpf_ringbuf_notify(struct irq_work *work)
+{
+	struct bpf_ringbuf *rb = container_of(work, struct bpf_ringbuf, work);
+
+	wake_up_all(&rb->waitq);
+}
+
+static struct bpf_ringbuf *bpf_ringbuf_alloc(size_t data_sz, int numa_node)
+{
+	struct bpf_ringbuf *rb;
+
+	rb = bpf_ringbuf_area_alloc(data_sz, numa_node);
+	if (!rb)
+		return ERR_PTR(-ENOMEM);
+
+	spin_lock_init(&rb->spinlock);
+	init_waitqueue_head(&rb->waitq);
+	init_irq_work(&rb->work, bpf_ringbuf_notify);
+
+	rb->mask = data_sz - 1;
+	rb->consumer_pos = 0;
+	rb->producer_pos = 0;
+
+	return rb;
+}
+
+static struct bpf_map *ringbuf_map_alloc(union bpf_attr *attr)
+{
+	struct bpf_ringbuf_map *rb_map;
+	u64 cost;
+	int err;
+
+	if (attr->map_flags & ~RINGBUF_CREATE_FLAG_MASK)
+		return ERR_PTR(-EINVAL);
+
+	if (attr->key_size || attr->value_size ||
+	    !is_power_of_2(attr->max_entries) ||
+	    !PAGE_ALIGNED(attr->max_entries))
+		return ERR_PTR(-EINVAL);
+
+#ifdef CONFIG_64BIT
+	/* on 32-bit arch, it's impossible to overflow record's hdr->pgoff */
+	if (attr->max_entries > RINGBUF_MAX_DATA_SZ)
+		return ERR_PTR(-E2BIG);
+#endif
+
+	rb_map = kzalloc(sizeof(*rb_map), GFP_USER);
+	if (!rb_map)
+		return ERR_PTR(-ENOMEM);
+
+	bpf_map_init_from_attr(&rb_map->map, attr);
+
+	cost = sizeof(struct bpf_ringbuf_map) +
+	       sizeof(struct bpf_ringbuf) +
+	       attr->max_entries;
+	err = bpf_map_charge_init(&rb_map->map.memory, cost);
+	if (err)
+		goto err_free_map;
+
+	rb_map->rb = bpf_ringbuf_alloc(attr->max_entries, rb_map->map.numa_node);
+	if (IS_ERR(rb_map->rb)) {
+		err = PTR_ERR(rb_map->rb);
+		goto err_uncharge;
+	}
+
+	return &rb_map->map;
+
+err_uncharge:
+	bpf_map_charge_finish(&rb_map->map.memory);
+err_free_map:
+	kfree(rb_map);
+	return ERR_PTR(err);
+}
+
+static void bpf_ringbuf_free(struct bpf_ringbuf *rb)
+{
+	/* copy pages pointer and nr_pages to local variable, as we are going
+	 * to unmap rb itself with vunmap() below
+	 */
+	struct page **pages = rb->pages;
+	int i, nr_pages = rb->nr_pages;
+
+	vunmap(rb);
+	for (i = 0; i < nr_pages; i++)
+		__free_page(pages[i]);
+	kvfree(pages);
+}
+
+static void ringbuf_map_free(struct bpf_map *map)
+{
+	struct bpf_ringbuf_map *rb_map;
+
+	rb_map = container_of(map, struct bpf_ringbuf_map, map);
+	bpf_ringbuf_free(rb_map->rb);
+	kfree(rb_map);
+}
+
+static void *ringbuf_map_lookup_elem(struct bpf_map *map, void *key)
+{
+	return ERR_PTR(-ENOTSUPP);
+}
+
+static int ringbuf_map_update_elem(struct bpf_map *map, void *key, void *value,
+				   u64 flags)
+{
+	return -ENOTSUPP;
+}
+
+static int ringbuf_map_delete_elem(struct bpf_map *map, void *key)
+{
+	return -ENOTSUPP;
+}
+
+static int ringbuf_map_get_next_key(struct bpf_map *map, void *key,
+				    void *next_key)
+{
+	return -ENOTSUPP;
+}
+
+static size_t bpf_ringbuf_mmap_page_cnt(const struct bpf_ringbuf *rb)
+{
+	size_t data_pages = (rb->mask + 1) >> PAGE_SHIFT;
+
+	/* consumer page + producer page + 2 x data pages */
+	return RINGBUF_POS_PAGES + 2 * data_pages;
+}
+
+static int ringbuf_map_mmap(struct bpf_map *map, struct vm_area_struct *vma)
+{
+	struct bpf_ringbuf_map *rb_map;
+	size_t mmap_sz;
+
+	rb_map = container_of(map, struct bpf_ringbuf_map, map);
+	mmap_sz = bpf_ringbuf_mmap_page_cnt(rb_map->rb) << PAGE_SHIFT;
+
+	if (vma->vm_pgoff * PAGE_SIZE + (vma->vm_end - vma->vm_start) > mmap_sz)
+		return -EINVAL;
+
+	return remap_vmalloc_range(vma, rb_map->rb,
+				   vma->vm_pgoff + RINGBUF_PGOFF);
+}
+
+static unsigned long ringbuf_avail_data_sz(struct bpf_ringbuf *rb)
+{
+	unsigned long cons_pos, prod_pos;
+
+	cons_pos = smp_load_acquire(&rb->consumer_pos);
+	prod_pos = smp_load_acquire(&rb->producer_pos);
+	return prod_pos - cons_pos;
+}
+
+static __poll_t ringbuf_map_poll(struct bpf_map *map, struct file *filp,
+				 struct poll_table_struct *pts)
+{
+	struct bpf_ringbuf_map *rb_map;
+
+	rb_map = container_of(map, struct bpf_ringbuf_map, map);
+	poll_wait(filp, &rb_map->rb->waitq, pts);
+
+	if (ringbuf_avail_data_sz(rb_map->rb))
+		return EPOLLIN | EPOLLRDNORM;
+	return 0;
+}
+
+static int ringbuf_map_btf_id;
+const struct bpf_map_ops ringbuf_map_ops = {
+	.map_alloc = ringbuf_map_alloc,
+	.map_free = ringbuf_map_free,
+	.map_mmap = ringbuf_map_mmap,
+	.map_poll = ringbuf_map_poll,
+	.map_lookup_elem = ringbuf_map_lookup_elem,
+	.map_update_elem = ringbuf_map_update_elem,
+	.map_delete_elem = ringbuf_map_delete_elem,
+	.map_get_next_key = ringbuf_map_get_next_key,
+	.map_btf_name = "bpf_ringbuf_map",
+	.map_btf_id = &ringbuf_map_btf_id,
+};
+
+/* Given pointer to ring buffer record metadata and struct bpf_ringbuf itself,
+ * calculate offset from record metadata to ring buffer in pages, rounded
+ * down. This page offset is stored as part of record metadata and allows to
+ * restore struct bpf_ringbuf * from record pointer. This page offset is
+ * stored at offset 4 of record metadata header.
+ */
+static size_t bpf_ringbuf_rec_pg_off(struct bpf_ringbuf *rb,
+				     struct bpf_ringbuf_hdr *hdr)
+{
+	return ((void *)hdr - (void *)rb) >> PAGE_SHIFT;
+}
+
+/* Given pointer to ring buffer record header, restore pointer to struct
+ * bpf_ringbuf itself by using page offset stored at offset 4
+ */
+static struct bpf_ringbuf *
+bpf_ringbuf_restore_from_rec(struct bpf_ringbuf_hdr *hdr)
+{
+	unsigned long addr = (unsigned long)(void *)hdr;
+	unsigned long off = (unsigned long)hdr->pg_off << PAGE_SHIFT;
+
+	return (void*)((addr & PAGE_MASK) - off);
+}
+
+static void *__bpf_ringbuf_reserve(struct bpf_ringbuf *rb, u64 size)
+{
+	unsigned long cons_pos, prod_pos, new_prod_pos, flags;
+	u32 len, pg_off;
+	struct bpf_ringbuf_hdr *hdr;
+
+	if (unlikely(size > RINGBUF_MAX_RECORD_SZ))
+		return NULL;
+
+	len = round_up(size + BPF_RINGBUF_HDR_SZ, 8);
+	cons_pos = smp_load_acquire(&rb->consumer_pos);
+
+	if (in_nmi()) {
+		if (!spin_trylock_irqsave(&rb->spinlock, flags))
+			return NULL;
+	} else {
+		spin_lock_irqsave(&rb->spinlock, flags);
+	}
+
+	prod_pos = rb->producer_pos;
+	new_prod_pos = prod_pos + len;
+
+	/* check for out of ringbuf space by ensuring producer position
+	 * doesn't advance more than (ringbuf_size - 1) ahead
+	 */
+	if (new_prod_pos - cons_pos > rb->mask) {
+		spin_unlock_irqrestore(&rb->spinlock, flags);
+		return NULL;
+	}
+
+	hdr = (void *)rb->data + (prod_pos & rb->mask);
+	pg_off = bpf_ringbuf_rec_pg_off(rb, hdr);
+	hdr->len = size | BPF_RINGBUF_BUSY_BIT;
+	hdr->pg_off = pg_off;
+
+	/* pairs with consumer's smp_load_acquire() */
+	smp_store_release(&rb->producer_pos, new_prod_pos);
+
+	spin_unlock_irqrestore(&rb->spinlock, flags);
+
+	return (void *)hdr + BPF_RINGBUF_HDR_SZ;
+}
+
+BPF_CALL_3(bpf_ringbuf_reserve, struct bpf_map *, map, u64, size, u64, flags)
+{
+	struct bpf_ringbuf_map *rb_map;
+
+	if (unlikely(flags))
+		return 0;
+
+	rb_map = container_of(map, struct bpf_ringbuf_map, map);
+	return (unsigned long)__bpf_ringbuf_reserve(rb_map->rb, size);
+}
+
+const struct bpf_func_proto bpf_ringbuf_reserve_proto = {
+	.func		= bpf_ringbuf_reserve,
+	.ret_type	= RET_PTR_TO_ALLOC_MEM_OR_NULL,
+	.arg1_type	= ARG_CONST_MAP_PTR,
+	.arg2_type	= ARG_CONST_ALLOC_SIZE_OR_ZERO,
+	.arg3_type	= ARG_ANYTHING,
+};
+
+static void bpf_ringbuf_commit(void *sample, u64 flags, bool discard)
+{
+	unsigned long rec_pos, cons_pos;
+	struct bpf_ringbuf_hdr *hdr;
+	struct bpf_ringbuf *rb;
+	u32 new_len;
+
+	hdr = sample - BPF_RINGBUF_HDR_SZ;
+	rb = bpf_ringbuf_restore_from_rec(hdr);
+	new_len = hdr->len ^ BPF_RINGBUF_BUSY_BIT;
+	if (discard)
+		new_len |= BPF_RINGBUF_DISCARD_BIT;
+
+	/* update record header with correct final size prefix */
+	xchg(&hdr->len, new_len);
+
+	/* if consumer caught up and is waiting for our record, notify about
+	 * new data availability
+	 */
+	rec_pos = (void *)hdr - (void *)rb->data;
+	cons_pos = smp_load_acquire(&rb->consumer_pos) & rb->mask;
+
+	if (flags & BPF_RB_FORCE_WAKEUP)
+		irq_work_queue(&rb->work);
+	else if (cons_pos == rec_pos && !(flags & BPF_RB_NO_WAKEUP))
+		irq_work_queue(&rb->work);
+}
+
+BPF_CALL_2(bpf_ringbuf_submit, void *, sample, u64, flags)
+{
+	bpf_ringbuf_commit(sample, flags, false /* discard */);
+	return 0;
+}
+
+const struct bpf_func_proto bpf_ringbuf_submit_proto = {
+	.func		= bpf_ringbuf_submit,
+	.ret_type	= RET_VOID,
+	.arg1_type	= ARG_PTR_TO_ALLOC_MEM,
+	.arg2_type	= ARG_ANYTHING,
+};
+
+BPF_CALL_2(bpf_ringbuf_discard, void *, sample, u64, flags)
+{
+	bpf_ringbuf_commit(sample, flags, true /* discard */);
+	return 0;
+}
+
+const struct bpf_func_proto bpf_ringbuf_discard_proto = {
+	.func		= bpf_ringbuf_discard,
+	.ret_type	= RET_VOID,
+	.arg1_type	= ARG_PTR_TO_ALLOC_MEM,
+	.arg2_type	= ARG_ANYTHING,
+};
+
+BPF_CALL_4(bpf_ringbuf_output, struct bpf_map *, map, void *, data, u64, size,
+	   u64, flags)
+{
+	struct bpf_ringbuf_map *rb_map;
+	void *rec;
+
+	if (unlikely(flags & ~(BPF_RB_NO_WAKEUP | BPF_RB_FORCE_WAKEUP)))
+		return -EINVAL;
+
+	rb_map = container_of(map, struct bpf_ringbuf_map, map);
+	rec = __bpf_ringbuf_reserve(rb_map->rb, size);
+	if (!rec)
+		return -EAGAIN;
+
+	memcpy(rec, data, size);
+	bpf_ringbuf_commit(rec, flags, false /* discard */);
+	return 0;
+}
+
+const struct bpf_func_proto bpf_ringbuf_output_proto = {
+	.func		= bpf_ringbuf_output,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_CONST_MAP_PTR,
+	.arg2_type	= ARG_PTR_TO_MEM,
+	.arg3_type	= ARG_CONST_SIZE_OR_ZERO,
+	.arg4_type	= ARG_ANYTHING,
+};
+
+BPF_CALL_2(bpf_ringbuf_query, struct bpf_map *, map, u64, flags)
+{
+	struct bpf_ringbuf *rb;
+
+	rb = container_of(map, struct bpf_ringbuf_map, map)->rb;
+
+	switch (flags) {
+	case BPF_RB_AVAIL_DATA:
+		return ringbuf_avail_data_sz(rb);
+	case BPF_RB_RING_SIZE:
+		return rb->mask + 1;
+	case BPF_RB_CONS_POS:
+		return smp_load_acquire(&rb->consumer_pos);
+	case BPF_RB_PROD_POS:
+		return smp_load_acquire(&rb->producer_pos);
+	default:
+		return 0;
+	}
+}
+
+const struct bpf_func_proto bpf_ringbuf_query_proto = {
+	.func		= bpf_ringbuf_query,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_CONST_MAP_PTR,
+	.arg2_type	= ARG_ANYTHING,
+};
diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c
index 3f958b90d914..cfed0ac44d38 100644
--- a/kernel/bpf/stackmap.c
+++ b/kernel/bpf/stackmap.c
@@ -4,11 +4,13 @@
 #include <linux/bpf.h>
 #include <linux/jhash.h>
 #include <linux/filter.h>
+#include <linux/kernel.h>
 #include <linux/stacktrace.h>
 #include <linux/perf_event.h>
 #include <linux/elf.h>
 #include <linux/pagemap.h>
 #include <linux/irq_work.h>
+#include <linux/btf_ids.h>
 #include "percpu_freelist.h"
 
 #define STACK_CREATE_FLAG_MASK					\
@@ -33,16 +35,18 @@ struct bpf_stack_map {
 /* irq_work to run up_read() for build_id lookup in nmi context */
 struct stack_map_irq_work {
 	struct irq_work irq_work;
-	struct rw_semaphore *sem;
+	struct mm_struct *mm;
 };
 
 static void do_up_read(struct irq_work *entry)
 {
 	struct stack_map_irq_work *work;
 
+	if (WARN_ON_ONCE(IS_ENABLED(CONFIG_PREEMPT_RT)))
+		return;
+
 	work = container_of(entry, struct stack_map_irq_work, irq_work);
-	up_read_non_owner(work->sem);
-	work->sem = NULL;
+	mmap_read_unlock_non_owner(work->mm);
 }
 
 static DEFINE_PER_CPU(struct stack_map_irq_work, up_read_work);
@@ -90,7 +94,7 @@ static struct bpf_map *stack_map_alloc(union bpf_attr *attr)
 	u64 cost, n_buckets;
 	int err;
 
-	if (!capable(CAP_SYS_ADMIN))
+	if (!bpf_capable())
 		return ERR_PTR(-EPERM);
 
 	if (attr->map_flags & ~STACK_CREATE_FLAG_MASK)
@@ -209,11 +213,13 @@ static int stack_map_get_build_id_32(void *page_addr,
 
 	phdr = (Elf32_Phdr *)(page_addr + sizeof(Elf32_Ehdr));
 
-	for (i = 0; i < ehdr->e_phnum; ++i)
-		if (phdr[i].p_type == PT_NOTE)
-			return stack_map_parse_build_id(page_addr, build_id,
-					page_addr + phdr[i].p_offset,
-					phdr[i].p_filesz);
+	for (i = 0; i < ehdr->e_phnum; ++i) {
+		if (phdr[i].p_type == PT_NOTE &&
+		    !stack_map_parse_build_id(page_addr, build_id,
+					      page_addr + phdr[i].p_offset,
+					      phdr[i].p_filesz))
+			return 0;
+	}
 	return -EINVAL;
 }
 
@@ -232,11 +238,13 @@ static int stack_map_get_build_id_64(void *page_addr,
 
 	phdr = (Elf64_Phdr *)(page_addr + sizeof(Elf64_Ehdr));
 
-	for (i = 0; i < ehdr->e_phnum; ++i)
-		if (phdr[i].p_type == PT_NOTE)
-			return stack_map_parse_build_id(page_addr, build_id,
-					page_addr + phdr[i].p_offset,
-					phdr[i].p_filesz);
+	for (i = 0; i < ehdr->e_phnum; ++i) {
+		if (phdr[i].p_type == PT_NOTE &&
+		    !stack_map_parse_build_id(page_addr, build_id,
+					      page_addr + phdr[i].p_offset,
+					      phdr[i].p_filesz))
+			return 0;
+	}
 	return -EINVAL;
 }
 
@@ -288,10 +296,19 @@ static void stack_map_get_build_id_offset(struct bpf_stack_build_id *id_offs,
 	struct stack_map_irq_work *work = NULL;
 
 	if (irqs_disabled()) {
-		work = this_cpu_ptr(&up_read_work);
-		if (atomic_read(&work->irq_work.flags) & IRQ_WORK_BUSY)
-			/* cannot queue more up_read, fallback */
+		if (!IS_ENABLED(CONFIG_PREEMPT_RT)) {
+			work = this_cpu_ptr(&up_read_work);
+			if (atomic_read(&work->irq_work.flags) & IRQ_WORK_BUSY) {
+				/* cannot queue more up_read, fallback */
+				irq_work_busy = true;
+			}
+		} else {
+			/*
+			 * PREEMPT_RT does not allow to trylock mmap sem in
+			 * interrupt disabled context. Force the fallback code.
+			 */
 			irq_work_busy = true;
+		}
 	}
 
 	/*
@@ -305,7 +322,7 @@ static void stack_map_get_build_id_offset(struct bpf_stack_build_id *id_offs,
 	 * with build_id.
 	 */
 	if (!user || !current || !current->mm || irq_work_busy ||
-	    down_read_trylock(&current->mm->mmap_sem) == 0) {
+	    !mmap_read_trylock_non_owner(current->mm)) {
 		/* cannot access current->mm, fall back to ips */
 		for (i = 0; i < trace_nr; i++) {
 			id_offs[i].status = BPF_STACK_BUILD_ID_IP;
@@ -330,24 +347,55 @@ static void stack_map_get_build_id_offset(struct bpf_stack_build_id *id_offs,
 	}
 
 	if (!work) {
-		up_read(&current->mm->mmap_sem);
+		mmap_read_unlock_non_owner(current->mm);
 	} else {
-		work->sem = &current->mm->mmap_sem;
+		work->mm = current->mm;
 		irq_work_queue(&work->irq_work);
-		/*
-		 * The irq_work will release the mmap_sem with
-		 * up_read_non_owner(). The rwsem_release() is called
-		 * here to release the lock from lockdep's perspective.
-		 */
-		rwsem_release(&current->mm->mmap_sem.dep_map, _RET_IP_);
 	}
 }
 
-BPF_CALL_3(bpf_get_stackid, struct pt_regs *, regs, struct bpf_map *, map,
-	   u64, flags)
+static struct perf_callchain_entry *
+get_callchain_entry_for_task(struct task_struct *task, u32 init_nr)
+{
+#ifdef CONFIG_STACKTRACE
+	struct perf_callchain_entry *entry;
+	int rctx;
+
+	entry = get_callchain_entry(&rctx);
+
+	if (!entry)
+		return NULL;
+
+	entry->nr = init_nr +
+		stack_trace_save_tsk(task, (unsigned long *)(entry->ip + init_nr),
+				     sysctl_perf_event_max_stack - init_nr, 0);
+
+	/* stack_trace_save_tsk() works on unsigned long array, while
+	 * perf_callchain_entry uses u64 array. For 32-bit systems, it is
+	 * necessary to fix this mismatch.
+	 */
+	if (__BITS_PER_LONG != 64) {
+		unsigned long *from = (unsigned long *) entry->ip;
+		u64 *to = entry->ip;
+		int i;
+
+		/* copy data from the end to avoid using extra buffer */
+		for (i = entry->nr - 1; i >= (int)init_nr; i--)
+			to[i] = (u64)(from[i]);
+	}
+
+	put_callchain_entry(rctx);
+
+	return entry;
+#else /* CONFIG_STACKTRACE */
+	return NULL;
+#endif
+}
+
+static long __bpf_get_stackid(struct bpf_map *map,
+			      struct perf_callchain_entry *trace, u64 flags)
 {
 	struct bpf_stack_map *smap = container_of(map, struct bpf_stack_map, map);
-	struct perf_callchain_entry *trace;
 	struct stack_map_bucket *bucket, *new_bucket, *old_bucket;
 	u32 max_depth = map->value_size / stack_map_data_size(map);
 	/* stack_map_alloc() checks that max_depth <= sysctl_perf_event_max_stack */
@@ -355,21 +403,9 @@ BPF_CALL_3(bpf_get_stackid, struct pt_regs *, regs, struct bpf_map *, map,
 	u32 skip = flags & BPF_F_SKIP_FIELD_MASK;
 	u32 hash, id, trace_nr, trace_len;
 	bool user = flags & BPF_F_USER_STACK;
-	bool kernel = !user;
 	u64 *ips;
 	bool hash_matches;
 
-	if (unlikely(flags & ~(BPF_F_SKIP_FIELD_MASK | BPF_F_USER_STACK |
-			       BPF_F_FAST_STACK_CMP | BPF_F_REUSE_STACKID)))
-		return -EINVAL;
-
-	trace = get_perf_callchain(regs, init_nr, kernel, user,
-				   sysctl_perf_event_max_stack, false, false);
-
-	if (unlikely(!trace))
-		/* couldn't fetch the stack trace */
-		return -EFAULT;
-
 	/* get_perf_callchain() guarantees that trace->nr >= init_nr
 	 * and trace-nr <= sysctl_perf_event_max_stack, so trace_nr <= max_depth
 	 */
@@ -434,6 +470,30 @@ BPF_CALL_3(bpf_get_stackid, struct pt_regs *, regs, struct bpf_map *, map,
 	return id;
 }
 
+BPF_CALL_3(bpf_get_stackid, struct pt_regs *, regs, struct bpf_map *, map,
+	   u64, flags)
+{
+	u32 max_depth = map->value_size / stack_map_data_size(map);
+	/* stack_map_alloc() checks that max_depth <= sysctl_perf_event_max_stack */
+	u32 init_nr = sysctl_perf_event_max_stack - max_depth;
+	bool user = flags & BPF_F_USER_STACK;
+	struct perf_callchain_entry *trace;
+	bool kernel = !user;
+
+	if (unlikely(flags & ~(BPF_F_SKIP_FIELD_MASK | BPF_F_USER_STACK |
+			       BPF_F_FAST_STACK_CMP | BPF_F_REUSE_STACKID)))
+		return -EINVAL;
+
+	trace = get_perf_callchain(regs, init_nr, kernel, user,
+				   sysctl_perf_event_max_stack, false, false);
+
+	if (unlikely(!trace))
+		/* couldn't fetch the stack trace */
+		return -EFAULT;
+
+	return __bpf_get_stackid(map, trace, flags);
+}
+
 const struct bpf_func_proto bpf_get_stackid_proto = {
 	.func		= bpf_get_stackid,
 	.gpl_only	= true,
@@ -443,8 +503,78 @@ const struct bpf_func_proto bpf_get_stackid_proto = {
 	.arg3_type	= ARG_ANYTHING,
 };
 
-BPF_CALL_4(bpf_get_stack, struct pt_regs *, regs, void *, buf, u32, size,
-	   u64, flags)
+static __u64 count_kernel_ip(struct perf_callchain_entry *trace)
+{
+	__u64 nr_kernel = 0;
+
+	while (nr_kernel < trace->nr) {
+		if (trace->ip[nr_kernel] == PERF_CONTEXT_USER)
+			break;
+		nr_kernel++;
+	}
+	return nr_kernel;
+}
+
+BPF_CALL_3(bpf_get_stackid_pe, struct bpf_perf_event_data_kern *, ctx,
+	   struct bpf_map *, map, u64, flags)
+{
+	struct perf_event *event = ctx->event;
+	struct perf_callchain_entry *trace;
+	bool kernel, user;
+	__u64 nr_kernel;
+	int ret;
+
+	/* perf_sample_data doesn't have callchain, use bpf_get_stackid */
+	if (!(event->attr.sample_type & __PERF_SAMPLE_CALLCHAIN_EARLY))
+		return bpf_get_stackid((unsigned long)(ctx->regs),
+				       (unsigned long) map, flags, 0, 0);
+
+	if (unlikely(flags & ~(BPF_F_SKIP_FIELD_MASK | BPF_F_USER_STACK |
+			       BPF_F_FAST_STACK_CMP | BPF_F_REUSE_STACKID)))
+		return -EINVAL;
+
+	user = flags & BPF_F_USER_STACK;
+	kernel = !user;
+
+	trace = ctx->data->callchain;
+	if (unlikely(!trace))
+		return -EFAULT;
+
+	nr_kernel = count_kernel_ip(trace);
+
+	if (kernel) {
+		__u64 nr = trace->nr;
+
+		trace->nr = nr_kernel;
+		ret = __bpf_get_stackid(map, trace, flags);
+
+		/* restore nr */
+		trace->nr = nr;
+	} else { /* user */
+		u64 skip = flags & BPF_F_SKIP_FIELD_MASK;
+
+		skip += nr_kernel;
+		if (skip > BPF_F_SKIP_FIELD_MASK)
+			return -EFAULT;
+
+		flags = (flags & ~BPF_F_SKIP_FIELD_MASK) | skip;
+		ret = __bpf_get_stackid(map, trace, flags);
+	}
+	return ret;
+}
+
+const struct bpf_func_proto bpf_get_stackid_proto_pe = {
+	.func		= bpf_get_stackid_pe,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_CONST_MAP_PTR,
+	.arg3_type	= ARG_ANYTHING,
+};
+
+static long __bpf_get_stack(struct pt_regs *regs, struct task_struct *task,
+			    struct perf_callchain_entry *trace_in,
+			    void *buf, u32 size, u64 flags)
 {
 	u32 init_nr, trace_nr, copy_len, elem_size, num_elem;
 	bool user_build_id = flags & BPF_F_USER_BUILD_ID;
@@ -466,13 +596,24 @@ BPF_CALL_4(bpf_get_stack, struct pt_regs *, regs, void *, buf, u32, size,
 	if (unlikely(size % elem_size))
 		goto clear;
 
+	/* cannot get valid user stack for task without user_mode regs */
+	if (task && user && !user_mode(regs))
+		goto err_fault;
+
 	num_elem = size / elem_size;
 	if (sysctl_perf_event_max_stack < num_elem)
 		init_nr = 0;
 	else
 		init_nr = sysctl_perf_event_max_stack - num_elem;
-	trace = get_perf_callchain(regs, init_nr, kernel, user,
-				   sysctl_perf_event_max_stack, false, false);
+
+	if (trace_in)
+		trace = trace_in;
+	else if (kernel && task)
+		trace = get_callchain_entry_for_task(task, init_nr);
+	else
+		trace = get_perf_callchain(regs, init_nr, kernel, user,
+					   sysctl_perf_event_max_stack,
+					   false, false);
 	if (unlikely(!trace))
 		goto err_fault;
 
@@ -500,6 +641,12 @@ clear:
 	return err;
 }
 
+BPF_CALL_4(bpf_get_stack, struct pt_regs *, regs, void *, buf, u32, size,
+	   u64, flags)
+{
+	return __bpf_get_stack(regs, NULL, NULL, buf, size, flags);
+}
+
 const struct bpf_func_proto bpf_get_stack_proto = {
 	.func		= bpf_get_stack,
 	.gpl_only	= true,
@@ -510,6 +657,91 @@ const struct bpf_func_proto bpf_get_stack_proto = {
 	.arg4_type	= ARG_ANYTHING,
 };
 
+BPF_CALL_4(bpf_get_task_stack, struct task_struct *, task, void *, buf,
+	   u32, size, u64, flags)
+{
+	struct pt_regs *regs = task_pt_regs(task);
+
+	return __bpf_get_stack(regs, task, NULL, buf, size, flags);
+}
+
+BTF_ID_LIST(bpf_get_task_stack_btf_ids)
+BTF_ID(struct, task_struct)
+
+const struct bpf_func_proto bpf_get_task_stack_proto = {
+	.func		= bpf_get_task_stack,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_BTF_ID,
+	.arg2_type	= ARG_PTR_TO_UNINIT_MEM,
+	.arg3_type	= ARG_CONST_SIZE_OR_ZERO,
+	.arg4_type	= ARG_ANYTHING,
+	.btf_id		= bpf_get_task_stack_btf_ids,
+};
+
+BPF_CALL_4(bpf_get_stack_pe, struct bpf_perf_event_data_kern *, ctx,
+	   void *, buf, u32, size, u64, flags)
+{
+	struct pt_regs *regs = (struct pt_regs *)(ctx->regs);
+	struct perf_event *event = ctx->event;
+	struct perf_callchain_entry *trace;
+	bool kernel, user;
+	int err = -EINVAL;
+	__u64 nr_kernel;
+
+	if (!(event->attr.sample_type & __PERF_SAMPLE_CALLCHAIN_EARLY))
+		return __bpf_get_stack(regs, NULL, NULL, buf, size, flags);
+
+	if (unlikely(flags & ~(BPF_F_SKIP_FIELD_MASK | BPF_F_USER_STACK |
+			       BPF_F_USER_BUILD_ID)))
+		goto clear;
+
+	user = flags & BPF_F_USER_STACK;
+	kernel = !user;
+
+	err = -EFAULT;
+	trace = ctx->data->callchain;
+	if (unlikely(!trace))
+		goto clear;
+
+	nr_kernel = count_kernel_ip(trace);
+
+	if (kernel) {
+		__u64 nr = trace->nr;
+
+		trace->nr = nr_kernel;
+		err = __bpf_get_stack(regs, NULL, trace, buf, size, flags);
+
+		/* restore nr */
+		trace->nr = nr;
+	} else { /* user */
+		u64 skip = flags & BPF_F_SKIP_FIELD_MASK;
+
+		skip += nr_kernel;
+		if (skip > BPF_F_SKIP_FIELD_MASK)
+			goto clear;
+
+		flags = (flags & ~BPF_F_SKIP_FIELD_MASK) | skip;
+		err = __bpf_get_stack(regs, NULL, trace, buf, size, flags);
+	}
+	return err;
+
+clear:
+	memset(buf, 0, size);
+	return err;
+
+}
+
+const struct bpf_func_proto bpf_get_stack_proto_pe = {
+	.func		= bpf_get_stack_pe,
+	.gpl_only	= true,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_PTR_TO_UNINIT_MEM,
+	.arg3_type	= ARG_CONST_SIZE_OR_ZERO,
+	.arg4_type	= ARG_ANYTHING,
+};
+
 /* Called from eBPF program */
 static void *stack_map_lookup_elem(struct bpf_map *map, void *key)
 {
@@ -599,15 +831,13 @@ static void stack_map_free(struct bpf_map *map)
 {
 	struct bpf_stack_map *smap = container_of(map, struct bpf_stack_map, map);
 
-	/* wait for bpf programs to complete before freeing stack map */
-	synchronize_rcu();
-
 	bpf_map_area_free(smap->elems);
 	pcpu_freelist_destroy(&smap->freelist);
 	bpf_map_area_free(smap);
 	put_callchain_buffers();
 }
 
+static int stack_trace_map_btf_id;
 const struct bpf_map_ops stack_trace_map_ops = {
 	.map_alloc = stack_map_alloc,
 	.map_free = stack_map_free,
@@ -616,6 +846,8 @@ const struct bpf_map_ops stack_trace_map_ops = {
 	.map_update_elem = stack_map_update_elem,
 	.map_delete_elem = stack_map_delete_elem,
 	.map_check_btf = map_check_no_btf,
+	.map_btf_name = "bpf_stack_map",
+	.map_btf_id = &stack_trace_map_btf_id,
 };
 
 static int __init stack_map_init(void)
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index a91ad518c050..1bf960aa615c 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -25,6 +25,10 @@
 #include <linux/nospec.h>
 #include <linux/audit.h>
 #include <uapi/linux/btf.h>
+#include <linux/pgtable.h>
+#include <linux/bpf_lsm.h>
+#include <linux/poll.h>
+#include <linux/bpf-netns.h>
 
 #define IS_FD_ARRAY(map) ((map)->map_type == BPF_MAP_TYPE_PERF_EVENT_ARRAY || \
 			  (map)->map_type == BPF_MAP_TYPE_CGROUP_ARRAY || \
@@ -41,6 +45,8 @@ static DEFINE_IDR(prog_idr);
 static DEFINE_SPINLOCK(prog_idr_lock);
 static DEFINE_IDR(map_idr);
 static DEFINE_SPINLOCK(map_idr_lock);
+static DEFINE_IDR(link_idr);
+static DEFINE_SPINLOCK(link_idr_lock);
 
 int sysctl_unprivileged_bpf_disabled __read_mostly;
 
@@ -48,9 +54,11 @@ static const struct bpf_map_ops * const bpf_map_types[] = {
 #define BPF_PROG_TYPE(_id, _name, prog_ctx_type, kern_ctx_type)
 #define BPF_MAP_TYPE(_id, _ops) \
 	[_id] = &_ops,
+#define BPF_LINK_TYPE(_id, _name)
 #include <linux/bpf_types.h>
 #undef BPF_PROG_TYPE
 #undef BPF_MAP_TYPE
+#undef BPF_LINK_TYPE
 };
 
 /*
@@ -66,32 +74,19 @@ int bpf_check_uarg_tail_zero(void __user *uaddr,
 			     size_t expected_size,
 			     size_t actual_size)
 {
-	unsigned char __user *addr;
-	unsigned char __user *end;
-	unsigned char val;
-	int err;
+	unsigned char __user *addr = uaddr + expected_size;
+	int res;
 
 	if (unlikely(actual_size > PAGE_SIZE))	/* silly large */
 		return -E2BIG;
 
-	if (unlikely(!access_ok(uaddr, actual_size)))
-		return -EFAULT;
-
 	if (actual_size <= expected_size)
 		return 0;
 
-	addr = uaddr + expected_size;
-	end  = uaddr + actual_size;
-
-	for (; addr < end; addr++) {
-		err = get_user(val, addr);
-		if (err)
-			return err;
-		if (val)
-			return -E2BIG;
-	}
-
-	return 0;
+	res = check_zeroed_user(addr, actual_size - expected_size);
+	if (res < 0)
+		return res;
+	return res ? 0 : -E2BIG;
 }
 
 const struct bpf_map_ops bpf_map_offload_ops = {
@@ -171,11 +166,7 @@ static int bpf_map_update_value(struct bpf_map *map, struct fd f, void *key,
 						    flags);
 	}
 
-	/* must increment bpf_prog_active to avoid kprobe+bpf triggering from
-	 * inside bpf map update or delete otherwise deadlocks are possible
-	 */
-	preempt_disable();
-	__this_cpu_inc(bpf_prog_active);
+	bpf_disable_instrumentation();
 	if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH ||
 	    map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH) {
 		err = bpf_percpu_hash_update(map, key, value, flags);
@@ -206,8 +197,7 @@ static int bpf_map_update_value(struct bpf_map *map, struct fd f, void *key,
 		err = map->ops->map_update_elem(map, key, value, flags);
 		rcu_read_unlock();
 	}
-	__this_cpu_dec(bpf_prog_active);
-	preempt_enable();
+	bpf_enable_instrumentation();
 	maybe_wait_bpf_programs(map);
 
 	return err;
@@ -222,8 +212,7 @@ static int bpf_map_copy_value(struct bpf_map *map, void *key, void *value,
 	if (bpf_map_is_dev_bound(map))
 		return bpf_map_offload_lookup_elem(map, key, value);
 
-	preempt_disable();
-	this_cpu_inc(bpf_prog_active);
+	bpf_disable_instrumentation();
 	if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH ||
 	    map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH) {
 		err = bpf_percpu_hash_copy(map, key, value);
@@ -268,8 +257,7 @@ static int bpf_map_copy_value(struct bpf_map *map, void *key, void *value,
 		rcu_read_unlock();
 	}
 
-	this_cpu_dec(bpf_prog_active);
-	preempt_enable();
+	bpf_enable_instrumentation();
 	maybe_wait_bpf_programs(map);
 
 	return err;
@@ -287,27 +275,29 @@ static void *__bpf_map_area_alloc(u64 size, int numa_node, bool mmapable)
 	 * __GFP_RETRY_MAYFAIL to avoid such situations.
 	 */
 
-	const gfp_t flags = __GFP_NOWARN | __GFP_ZERO;
+	const gfp_t gfp = __GFP_NOWARN | __GFP_ZERO;
+	unsigned int flags = 0;
+	unsigned long align = 1;
 	void *area;
 
 	if (size >= SIZE_MAX)
 		return NULL;
 
 	/* kmalloc()'ed memory can't be mmap()'ed */
-	if (!mmapable && size <= (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER)) {
-		area = kmalloc_node(size, GFP_USER | __GFP_NORETRY | flags,
+	if (mmapable) {
+		BUG_ON(!PAGE_ALIGNED(size));
+		align = SHMLBA;
+		flags = VM_USERMAP;
+	} else if (size <= (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER)) {
+		area = kmalloc_node(size, gfp | GFP_USER | __GFP_NORETRY,
 				    numa_node);
 		if (area != NULL)
 			return area;
 	}
-	if (mmapable) {
-		BUG_ON(!PAGE_ALIGNED(size));
-		return vmalloc_user_node_flags(size, numa_node, GFP_KERNEL |
-					       __GFP_RETRY_MAYFAIL | flags);
-	}
-	return __vmalloc_node_flags_caller(size, numa_node,
-					   GFP_KERNEL | __GFP_RETRY_MAYFAIL |
-					   flags, __builtin_return_address(0));
+
+	return __vmalloc_node_range(size, align, VMALLOC_START, VMALLOC_END,
+			gfp | GFP_KERNEL | __GFP_RETRY_MAYFAIL, PAGE_KERNEL,
+			flags, numa_node, __builtin_return_address(0));
 }
 
 void *bpf_map_area_alloc(u64 size, int numa_node)
@@ -592,9 +582,7 @@ static void bpf_map_mmap_open(struct vm_area_struct *vma)
 {
 	struct bpf_map *map = vma->vm_file->private_data;
 
-	bpf_map_inc_with_uref(map);
-
-	if (vma->vm_flags & VM_WRITE) {
+	if (vma->vm_flags & VM_MAYWRITE) {
 		mutex_lock(&map->freeze_mutex);
 		map->writecnt++;
 		mutex_unlock(&map->freeze_mutex);
@@ -606,13 +594,11 @@ static void bpf_map_mmap_close(struct vm_area_struct *vma)
 {
 	struct bpf_map *map = vma->vm_file->private_data;
 
-	if (vma->vm_flags & VM_WRITE) {
+	if (vma->vm_flags & VM_MAYWRITE) {
 		mutex_lock(&map->freeze_mutex);
 		map->writecnt--;
 		mutex_unlock(&map->freeze_mutex);
 	}
-
-	bpf_map_put_with_uref(map);
 }
 
 static const struct vm_operations_struct bpf_map_default_vmops = {
@@ -633,28 +619,51 @@ static int bpf_map_mmap(struct file *filp, struct vm_area_struct *vma)
 
 	mutex_lock(&map->freeze_mutex);
 
-	if ((vma->vm_flags & VM_WRITE) && map->frozen) {
-		err = -EPERM;
-		goto out;
+	if (vma->vm_flags & VM_WRITE) {
+		if (map->frozen) {
+			err = -EPERM;
+			goto out;
+		}
+		/* map is meant to be read-only, so do not allow mapping as
+		 * writable, because it's possible to leak a writable page
+		 * reference and allows user-space to still modify it after
+		 * freezing, while verifier will assume contents do not change
+		 */
+		if (map->map_flags & BPF_F_RDONLY_PROG) {
+			err = -EACCES;
+			goto out;
+		}
 	}
 
 	/* set default open/close callbacks */
 	vma->vm_ops = &bpf_map_default_vmops;
 	vma->vm_private_data = map;
+	vma->vm_flags &= ~VM_MAYEXEC;
+	if (!(vma->vm_flags & VM_WRITE))
+		/* disallow re-mapping with PROT_WRITE */
+		vma->vm_flags &= ~VM_MAYWRITE;
 
 	err = map->ops->map_mmap(map, vma);
 	if (err)
 		goto out;
 
-	bpf_map_inc_with_uref(map);
-
-	if (vma->vm_flags & VM_WRITE)
+	if (vma->vm_flags & VM_MAYWRITE)
 		map->writecnt++;
 out:
 	mutex_unlock(&map->freeze_mutex);
 	return err;
 }
 
+static __poll_t bpf_map_poll(struct file *filp, struct poll_table_struct *pts)
+{
+	struct bpf_map *map = filp->private_data;
+
+	if (map->ops->map_poll)
+		return map->ops->map_poll(map, filp, pts);
+
+	return EPOLLERR;
+}
+
 const struct file_operations bpf_map_fops = {
 #ifdef CONFIG_PROC_FS
 	.show_fdinfo	= bpf_map_show_fdinfo,
@@ -663,6 +672,7 @@ const struct file_operations bpf_map_fops = {
 	.read		= bpf_dummy_read,
 	.write		= bpf_dummy_write,
 	.mmap		= bpf_map_mmap,
+	.poll		= bpf_map_poll,
 };
 
 int bpf_map_new_fd(struct bpf_map *map, int flags)
@@ -696,14 +706,15 @@ int bpf_get_file_flag(int flags)
 		   offsetof(union bpf_attr, CMD##_LAST_FIELD) - \
 		   sizeof(attr->CMD##_LAST_FIELD)) != NULL
 
-/* dst and src must have at least BPF_OBJ_NAME_LEN number of bytes.
- * Return 0 on success and < 0 on error.
+/* dst and src must have at least "size" number of bytes.
+ * Return strlen on success and < 0 on error.
  */
-static int bpf_obj_name_cpy(char *dst, const char *src)
+int bpf_obj_name_cpy(char *dst, const char *src, unsigned int size)
 {
-	const char *end = src + BPF_OBJ_NAME_LEN;
+	const char *end = src + size;
+	const char *orig_src = src;
 
-	memset(dst, 0, BPF_OBJ_NAME_LEN);
+	memset(dst, 0, size);
 	/* Copy all isalnum(), '_' and '.' chars. */
 	while (src < end && *src) {
 		if (!isalnum(*src) &&
@@ -712,11 +723,11 @@ static int bpf_obj_name_cpy(char *dst, const char *src)
 		*dst++ = *src++;
 	}
 
-	/* No '\0' found in BPF_OBJ_NAME_LEN number of bytes */
+	/* No '\0' found in "size" number of bytes */
 	if (src == end)
 		return -EINVAL;
 
-	return 0;
+	return src - orig_src;
 }
 
 int map_check_no_btf(const struct bpf_map *map,
@@ -810,8 +821,9 @@ static int map_create(union bpf_attr *attr)
 	if (IS_ERR(map))
 		return PTR_ERR(map);
 
-	err = bpf_obj_name_cpy(map->name, attr->map_name);
-	if (err)
+	err = bpf_obj_name_cpy(map->name, attr->map_name,
+			       sizeof(attr->map_name));
+	if (err < 0)
 		goto free_map;
 
 	atomic64_set(&map->refcnt, 1);
@@ -909,6 +921,21 @@ void bpf_map_inc_with_uref(struct bpf_map *map)
 }
 EXPORT_SYMBOL_GPL(bpf_map_inc_with_uref);
 
+struct bpf_map *bpf_map_get(u32 ufd)
+{
+	struct fd f = fdget(ufd);
+	struct bpf_map *map;
+
+	map = __bpf_map_get(f);
+	if (IS_ERR(map))
+		return map;
+
+	bpf_map_inc(map);
+	fdput(f);
+
+	return map;
+}
+
 struct bpf_map *bpf_map_get_with_uref(u32 ufd)
 {
 	struct fd f = fdget(ufd);
@@ -1136,13 +1163,11 @@ static int map_delete_elem(union bpf_attr *attr)
 		goto out;
 	}
 
-	preempt_disable();
-	__this_cpu_inc(bpf_prog_active);
+	bpf_disable_instrumentation();
 	rcu_read_lock();
 	err = map->ops->map_delete_elem(map, key);
 	rcu_read_unlock();
-	__this_cpu_dec(bpf_prog_active);
-	preempt_enable();
+	bpf_enable_instrumentation();
 	maybe_wait_bpf_programs(map);
 out:
 	kfree(key);
@@ -1254,13 +1279,11 @@ int generic_map_delete_batch(struct bpf_map *map,
 			break;
 		}
 
-		preempt_disable();
-		__this_cpu_inc(bpf_prog_active);
+		bpf_disable_instrumentation();
 		rcu_read_lock();
 		err = map->ops->map_delete_elem(map, key);
 		rcu_read_unlock();
-		__this_cpu_dec(bpf_prog_active);
-		preempt_enable();
+		bpf_enable_instrumentation();
 		maybe_wait_bpf_programs(map);
 		if (err)
 			break;
@@ -1367,7 +1390,7 @@ int generic_map_lookup_batch(struct bpf_map *map,
 
 	buf = kmalloc(map->key_size + value_size, GFP_USER | __GFP_NOWARN);
 	if (!buf) {
-		kvfree(buf_prevkey);
+		kfree(buf_prevkey);
 		return -ENOMEM;
 	}
 
@@ -1452,7 +1475,8 @@ static int map_lookup_and_delete_elem(union bpf_attr *attr)
 	map = __bpf_map_get(f);
 	if (IS_ERR(map))
 		return PTR_ERR(map);
-	if (!(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) {
+	if (!(map_get_sys_perms(map, f) & FMODE_CAN_READ) ||
+	    !(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) {
 		err = -EPERM;
 		goto err_put;
 	}
@@ -1480,8 +1504,10 @@ static int map_lookup_and_delete_elem(union bpf_attr *attr)
 	if (err)
 		goto free_value;
 
-	if (copy_to_user(uvalue, value, value_size) != 0)
+	if (copy_to_user(uvalue, value, value_size) != 0) {
+		err = -EFAULT;
 		goto free_value;
+	}
 
 	err = 0;
 
@@ -1510,6 +1536,11 @@ static int map_freeze(const union bpf_attr *attr)
 	if (IS_ERR(map))
 		return PTR_ERR(map);
 
+	if (map->map_type == BPF_MAP_TYPE_STRUCT_OPS) {
+		fdput(f);
+		return -ENOTSUPP;
+	}
+
 	mutex_lock(&map->freeze_mutex);
 
 	if (map->writecnt) {
@@ -1520,7 +1551,7 @@ static int map_freeze(const union bpf_attr *attr)
 		err = -EBUSY;
 		goto err_put;
 	}
-	if (!capable(CAP_SYS_ADMIN)) {
+	if (!bpf_capable()) {
 		err = -EPERM;
 		goto err_put;
 	}
@@ -1536,9 +1567,11 @@ static const struct bpf_prog_ops * const bpf_prog_types[] = {
 #define BPF_PROG_TYPE(_id, _name, prog_ctx_type, kern_ctx_type) \
 	[_id] = & _name ## _prog_ops,
 #define BPF_MAP_TYPE(_id, _ops)
+#define BPF_LINK_TYPE(_id, _name)
 #include <linux/bpf_types.h>
 #undef BPF_PROG_TYPE
 #undef BPF_MAP_TYPE
+#undef BPF_LINK_TYPE
 };
 
 static int find_prog_type(enum bpf_prog_type type, struct bpf_prog *prog)
@@ -1931,6 +1964,7 @@ bpf_prog_load_check_attach(enum bpf_prog_type prog_type,
 
 		switch (prog_type) {
 		case BPF_PROG_TYPE_TRACING:
+		case BPF_PROG_TYPE_LSM:
 		case BPF_PROG_TYPE_STRUCT_OPS:
 		case BPF_PROG_TYPE_EXT:
 			break;
@@ -1947,6 +1981,7 @@ bpf_prog_load_check_attach(enum bpf_prog_type prog_type,
 	case BPF_PROG_TYPE_CGROUP_SOCK:
 		switch (expected_attach_type) {
 		case BPF_CGROUP_INET_SOCK_CREATE:
+		case BPF_CGROUP_INET_SOCK_RELEASE:
 		case BPF_CGROUP_INET4_POST_BIND:
 		case BPF_CGROUP_INET6_POST_BIND:
 			return 0;
@@ -1959,6 +1994,10 @@ bpf_prog_load_check_attach(enum bpf_prog_type prog_type,
 		case BPF_CGROUP_INET6_BIND:
 		case BPF_CGROUP_INET4_CONNECT:
 		case BPF_CGROUP_INET6_CONNECT:
+		case BPF_CGROUP_INET4_GETPEERNAME:
+		case BPF_CGROUP_INET6_GETPEERNAME:
+		case BPF_CGROUP_INET4_GETSOCKNAME:
+		case BPF_CGROUP_INET6_GETSOCKNAME:
 		case BPF_CGROUP_UDP4_SENDMSG:
 		case BPF_CGROUP_UDP6_SENDMSG:
 		case BPF_CGROUP_UDP4_RECVMSG:
@@ -1983,15 +2022,68 @@ bpf_prog_load_check_attach(enum bpf_prog_type prog_type,
 		default:
 			return -EINVAL;
 		}
+	case BPF_PROG_TYPE_SK_LOOKUP:
+		if (expected_attach_type == BPF_SK_LOOKUP)
+			return 0;
+		return -EINVAL;
 	case BPF_PROG_TYPE_EXT:
 		if (expected_attach_type)
 			return -EINVAL;
-		/* fallthrough */
+		fallthrough;
 	default:
 		return 0;
 	}
 }
 
+static bool is_net_admin_prog_type(enum bpf_prog_type prog_type)
+{
+	switch (prog_type) {
+	case BPF_PROG_TYPE_SCHED_CLS:
+	case BPF_PROG_TYPE_SCHED_ACT:
+	case BPF_PROG_TYPE_XDP:
+	case BPF_PROG_TYPE_LWT_IN:
+	case BPF_PROG_TYPE_LWT_OUT:
+	case BPF_PROG_TYPE_LWT_XMIT:
+	case BPF_PROG_TYPE_LWT_SEG6LOCAL:
+	case BPF_PROG_TYPE_SK_SKB:
+	case BPF_PROG_TYPE_SK_MSG:
+	case BPF_PROG_TYPE_LIRC_MODE2:
+	case BPF_PROG_TYPE_FLOW_DISSECTOR:
+	case BPF_PROG_TYPE_CGROUP_DEVICE:
+	case BPF_PROG_TYPE_CGROUP_SOCK:
+	case BPF_PROG_TYPE_CGROUP_SOCK_ADDR:
+	case BPF_PROG_TYPE_CGROUP_SOCKOPT:
+	case BPF_PROG_TYPE_CGROUP_SYSCTL:
+	case BPF_PROG_TYPE_SOCK_OPS:
+	case BPF_PROG_TYPE_EXT: /* extends any prog */
+		return true;
+	case BPF_PROG_TYPE_CGROUP_SKB:
+		/* always unpriv */
+	case BPF_PROG_TYPE_SK_REUSEPORT:
+		/* equivalent to SOCKET_FILTER. need CAP_BPF only */
+	default:
+		return false;
+	}
+}
+
+static bool is_perfmon_prog_type(enum bpf_prog_type prog_type)
+{
+	switch (prog_type) {
+	case BPF_PROG_TYPE_KPROBE:
+	case BPF_PROG_TYPE_TRACEPOINT:
+	case BPF_PROG_TYPE_PERF_EVENT:
+	case BPF_PROG_TYPE_RAW_TRACEPOINT:
+	case BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE:
+	case BPF_PROG_TYPE_TRACING:
+	case BPF_PROG_TYPE_LSM:
+	case BPF_PROG_TYPE_STRUCT_OPS: /* has access to struct sock */
+	case BPF_PROG_TYPE_EXT: /* extends any prog */
+		return true;
+	default:
+		return false;
+	}
+}
+
 /* last field in 'union bpf_attr' used by this command */
 #define	BPF_PROG_LOAD_LAST_FIELD attach_prog_fd
 
@@ -2014,7 +2106,7 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr)
 
 	if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) &&
 	    (attr->prog_flags & BPF_F_ANY_ALIGNMENT) &&
-	    !capable(CAP_SYS_ADMIN))
+	    !bpf_capable())
 		return -EPERM;
 
 	/* copy eBPF program license from user space */
@@ -2027,11 +2119,16 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr)
 	is_gpl = license_is_gpl_compatible(license);
 
 	if (attr->insn_cnt == 0 ||
-	    attr->insn_cnt > (capable(CAP_SYS_ADMIN) ? BPF_COMPLEXITY_LIMIT_INSNS : BPF_MAXINSNS))
+	    attr->insn_cnt > (bpf_capable() ? BPF_COMPLEXITY_LIMIT_INSNS : BPF_MAXINSNS))
 		return -E2BIG;
 	if (type != BPF_PROG_TYPE_SOCKET_FILTER &&
 	    type != BPF_PROG_TYPE_CGROUP_SKB &&
-	    !capable(CAP_SYS_ADMIN))
+	    !bpf_capable())
+		return -EPERM;
+
+	if (is_net_admin_prog_type(type) && !capable(CAP_NET_ADMIN) && !capable(CAP_SYS_ADMIN))
+		return -EPERM;
+	if (is_perfmon_prog_type(type) && !perfmon_capable())
 		return -EPERM;
 
 	bpf_prog_load_fixup_attach_type(attr);
@@ -2093,8 +2190,9 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr)
 		goto free_prog;
 
 	prog->aux->load_time = ktime_get_boottime_ns();
-	err = bpf_obj_name_cpy(prog->aux->name, attr->prog_name);
-	if (err)
+	err = bpf_obj_name_cpy(prog->aux->name, attr->prog_name,
+			       sizeof(attr->prog_name));
+	if (err < 0)
 		goto free_prog;
 
 	/* run eBPF verifier */
@@ -2169,84 +2267,415 @@ static int bpf_obj_get(const union bpf_attr *attr)
 				attr->file_flags);
 }
 
-static int bpf_tracing_prog_release(struct inode *inode, struct file *filp)
+void bpf_link_init(struct bpf_link *link, enum bpf_link_type type,
+		   const struct bpf_link_ops *ops, struct bpf_prog *prog)
 {
-	struct bpf_prog *prog = filp->private_data;
+	atomic64_set(&link->refcnt, 1);
+	link->type = type;
+	link->id = 0;
+	link->ops = ops;
+	link->prog = prog;
+}
 
-	WARN_ON_ONCE(bpf_trampoline_unlink_prog(prog));
-	bpf_prog_put(prog);
+static void bpf_link_free_id(int id)
+{
+	if (!id)
+		return;
+
+	spin_lock_bh(&link_idr_lock);
+	idr_remove(&link_idr, id);
+	spin_unlock_bh(&link_idr_lock);
+}
+
+/* Clean up bpf_link and corresponding anon_inode file and FD. After
+ * anon_inode is created, bpf_link can't be just kfree()'d due to deferred
+ * anon_inode's release() call. This helper marksbpf_link as
+ * defunct, releases anon_inode file and puts reserved FD. bpf_prog's refcnt
+ * is not decremented, it's the responsibility of a calling code that failed
+ * to complete bpf_link initialization.
+ */
+void bpf_link_cleanup(struct bpf_link_primer *primer)
+{
+	primer->link->prog = NULL;
+	bpf_link_free_id(primer->id);
+	fput(primer->file);
+	put_unused_fd(primer->fd);
+}
+
+void bpf_link_inc(struct bpf_link *link)
+{
+	atomic64_inc(&link->refcnt);
+}
+
+/* bpf_link_free is guaranteed to be called from process context */
+static void bpf_link_free(struct bpf_link *link)
+{
+	bpf_link_free_id(link->id);
+	if (link->prog) {
+		/* detach BPF program, clean up used resources */
+		link->ops->release(link);
+		bpf_prog_put(link->prog);
+	}
+	/* free bpf_link and its containing memory */
+	link->ops->dealloc(link);
+}
+
+static void bpf_link_put_deferred(struct work_struct *work)
+{
+	struct bpf_link *link = container_of(work, struct bpf_link, work);
+
+	bpf_link_free(link);
+}
+
+/* bpf_link_put can be called from atomic context, but ensures that resources
+ * are freed from process context
+ */
+void bpf_link_put(struct bpf_link *link)
+{
+	if (!atomic64_dec_and_test(&link->refcnt))
+		return;
+
+	if (in_atomic()) {
+		INIT_WORK(&link->work, bpf_link_put_deferred);
+		schedule_work(&link->work);
+	} else {
+		bpf_link_free(link);
+	}
+}
+
+static int bpf_link_release(struct inode *inode, struct file *filp)
+{
+	struct bpf_link *link = filp->private_data;
+
+	bpf_link_put(link);
 	return 0;
 }
 
-static const struct file_operations bpf_tracing_prog_fops = {
-	.release	= bpf_tracing_prog_release,
+#ifdef CONFIG_PROC_FS
+#define BPF_PROG_TYPE(_id, _name, prog_ctx_type, kern_ctx_type)
+#define BPF_MAP_TYPE(_id, _ops)
+#define BPF_LINK_TYPE(_id, _name) [_id] = #_name,
+static const char *bpf_link_type_strs[] = {
+	[BPF_LINK_TYPE_UNSPEC] = "<invalid>",
+#include <linux/bpf_types.h>
+};
+#undef BPF_PROG_TYPE
+#undef BPF_MAP_TYPE
+#undef BPF_LINK_TYPE
+
+static void bpf_link_show_fdinfo(struct seq_file *m, struct file *filp)
+{
+	const struct bpf_link *link = filp->private_data;
+	const struct bpf_prog *prog = link->prog;
+	char prog_tag[sizeof(prog->tag) * 2 + 1] = { };
+
+	bin2hex(prog_tag, prog->tag, sizeof(prog->tag));
+	seq_printf(m,
+		   "link_type:\t%s\n"
+		   "link_id:\t%u\n"
+		   "prog_tag:\t%s\n"
+		   "prog_id:\t%u\n",
+		   bpf_link_type_strs[link->type],
+		   link->id,
+		   prog_tag,
+		   prog->aux->id);
+	if (link->ops->show_fdinfo)
+		link->ops->show_fdinfo(link, m);
+}
+#endif
+
+static const struct file_operations bpf_link_fops = {
+#ifdef CONFIG_PROC_FS
+	.show_fdinfo	= bpf_link_show_fdinfo,
+#endif
+	.release	= bpf_link_release,
 	.read		= bpf_dummy_read,
 	.write		= bpf_dummy_write,
 };
 
+static int bpf_link_alloc_id(struct bpf_link *link)
+{
+	int id;
+
+	idr_preload(GFP_KERNEL);
+	spin_lock_bh(&link_idr_lock);
+	id = idr_alloc_cyclic(&link_idr, link, 1, INT_MAX, GFP_ATOMIC);
+	spin_unlock_bh(&link_idr_lock);
+	idr_preload_end();
+
+	return id;
+}
+
+/* Prepare bpf_link to be exposed to user-space by allocating anon_inode file,
+ * reserving unused FD and allocating ID from link_idr. This is to be paired
+ * with bpf_link_settle() to install FD and ID and expose bpf_link to
+ * user-space, if bpf_link is successfully attached. If not, bpf_link and
+ * pre-allocated resources are to be freed with bpf_cleanup() call. All the
+ * transient state is passed around in struct bpf_link_primer.
+ * This is preferred way to create and initialize bpf_link, especially when
+ * there are complicated and expensive operations inbetween creating bpf_link
+ * itself and attaching it to BPF hook. By using bpf_link_prime() and
+ * bpf_link_settle() kernel code using bpf_link doesn't have to perform
+ * expensive (and potentially failing) roll back operations in a rare case
+ * that file, FD, or ID can't be allocated.
+ */
+int bpf_link_prime(struct bpf_link *link, struct bpf_link_primer *primer)
+{
+	struct file *file;
+	int fd, id;
+
+	fd = get_unused_fd_flags(O_CLOEXEC);
+	if (fd < 0)
+		return fd;
+
+
+	id = bpf_link_alloc_id(link);
+	if (id < 0) {
+		put_unused_fd(fd);
+		return id;
+	}
+
+	file = anon_inode_getfile("bpf_link", &bpf_link_fops, link, O_CLOEXEC);
+	if (IS_ERR(file)) {
+		bpf_link_free_id(id);
+		put_unused_fd(fd);
+		return PTR_ERR(file);
+	}
+
+	primer->link = link;
+	primer->file = file;
+	primer->fd = fd;
+	primer->id = id;
+	return 0;
+}
+
+int bpf_link_settle(struct bpf_link_primer *primer)
+{
+	/* make bpf_link fetchable by ID */
+	spin_lock_bh(&link_idr_lock);
+	primer->link->id = primer->id;
+	spin_unlock_bh(&link_idr_lock);
+	/* make bpf_link fetchable by FD */
+	fd_install(primer->fd, primer->file);
+	/* pass through installed FD */
+	return primer->fd;
+}
+
+int bpf_link_new_fd(struct bpf_link *link)
+{
+	return anon_inode_getfd("bpf-link", &bpf_link_fops, link, O_CLOEXEC);
+}
+
+struct bpf_link *bpf_link_get_from_fd(u32 ufd)
+{
+	struct fd f = fdget(ufd);
+	struct bpf_link *link;
+
+	if (!f.file)
+		return ERR_PTR(-EBADF);
+	if (f.file->f_op != &bpf_link_fops) {
+		fdput(f);
+		return ERR_PTR(-EINVAL);
+	}
+
+	link = f.file->private_data;
+	bpf_link_inc(link);
+	fdput(f);
+
+	return link;
+}
+
+struct bpf_tracing_link {
+	struct bpf_link link;
+	enum bpf_attach_type attach_type;
+};
+
+static void bpf_tracing_link_release(struct bpf_link *link)
+{
+	WARN_ON_ONCE(bpf_trampoline_unlink_prog(link->prog));
+}
+
+static void bpf_tracing_link_dealloc(struct bpf_link *link)
+{
+	struct bpf_tracing_link *tr_link =
+		container_of(link, struct bpf_tracing_link, link);
+
+	kfree(tr_link);
+}
+
+static void bpf_tracing_link_show_fdinfo(const struct bpf_link *link,
+					 struct seq_file *seq)
+{
+	struct bpf_tracing_link *tr_link =
+		container_of(link, struct bpf_tracing_link, link);
+
+	seq_printf(seq,
+		   "attach_type:\t%d\n",
+		   tr_link->attach_type);
+}
+
+static int bpf_tracing_link_fill_link_info(const struct bpf_link *link,
+					   struct bpf_link_info *info)
+{
+	struct bpf_tracing_link *tr_link =
+		container_of(link, struct bpf_tracing_link, link);
+
+	info->tracing.attach_type = tr_link->attach_type;
+
+	return 0;
+}
+
+static const struct bpf_link_ops bpf_tracing_link_lops = {
+	.release = bpf_tracing_link_release,
+	.dealloc = bpf_tracing_link_dealloc,
+	.show_fdinfo = bpf_tracing_link_show_fdinfo,
+	.fill_link_info = bpf_tracing_link_fill_link_info,
+};
+
 static int bpf_tracing_prog_attach(struct bpf_prog *prog)
 {
-	int tr_fd, err;
+	struct bpf_link_primer link_primer;
+	struct bpf_tracing_link *link;
+	int err;
 
-	if (prog->expected_attach_type != BPF_TRACE_FENTRY &&
-	    prog->expected_attach_type != BPF_TRACE_FEXIT &&
-	    prog->type != BPF_PROG_TYPE_EXT) {
+	switch (prog->type) {
+	case BPF_PROG_TYPE_TRACING:
+		if (prog->expected_attach_type != BPF_TRACE_FENTRY &&
+		    prog->expected_attach_type != BPF_TRACE_FEXIT &&
+		    prog->expected_attach_type != BPF_MODIFY_RETURN) {
+			err = -EINVAL;
+			goto out_put_prog;
+		}
+		break;
+	case BPF_PROG_TYPE_EXT:
+		if (prog->expected_attach_type != 0) {
+			err = -EINVAL;
+			goto out_put_prog;
+		}
+		break;
+	case BPF_PROG_TYPE_LSM:
+		if (prog->expected_attach_type != BPF_LSM_MAC) {
+			err = -EINVAL;
+			goto out_put_prog;
+		}
+		break;
+	default:
 		err = -EINVAL;
 		goto out_put_prog;
 	}
 
-	err = bpf_trampoline_link_prog(prog);
-	if (err)
+	link = kzalloc(sizeof(*link), GFP_USER);
+	if (!link) {
+		err = -ENOMEM;
 		goto out_put_prog;
+	}
+	bpf_link_init(&link->link, BPF_LINK_TYPE_TRACING,
+		      &bpf_tracing_link_lops, prog);
+	link->attach_type = prog->expected_attach_type;
 
-	tr_fd = anon_inode_getfd("bpf-tracing-prog", &bpf_tracing_prog_fops,
-				 prog, O_CLOEXEC);
-	if (tr_fd < 0) {
-		WARN_ON_ONCE(bpf_trampoline_unlink_prog(prog));
-		err = tr_fd;
+	err = bpf_link_prime(&link->link, &link_primer);
+	if (err) {
+		kfree(link);
+		goto out_put_prog;
+	}
+
+	err = bpf_trampoline_link_prog(prog);
+	if (err) {
+		bpf_link_cleanup(&link_primer);
 		goto out_put_prog;
 	}
-	return tr_fd;
 
+	return bpf_link_settle(&link_primer);
 out_put_prog:
 	bpf_prog_put(prog);
 	return err;
 }
 
-struct bpf_raw_tracepoint {
+struct bpf_raw_tp_link {
+	struct bpf_link link;
 	struct bpf_raw_event_map *btp;
-	struct bpf_prog *prog;
 };
 
-static int bpf_raw_tracepoint_release(struct inode *inode, struct file *filp)
+static void bpf_raw_tp_link_release(struct bpf_link *link)
 {
-	struct bpf_raw_tracepoint *raw_tp = filp->private_data;
+	struct bpf_raw_tp_link *raw_tp =
+		container_of(link, struct bpf_raw_tp_link, link);
 
-	if (raw_tp->prog) {
-		bpf_probe_unregister(raw_tp->btp, raw_tp->prog);
-		bpf_prog_put(raw_tp->prog);
-	}
+	bpf_probe_unregister(raw_tp->btp, raw_tp->link.prog);
 	bpf_put_raw_tracepoint(raw_tp->btp);
+}
+
+static void bpf_raw_tp_link_dealloc(struct bpf_link *link)
+{
+	struct bpf_raw_tp_link *raw_tp =
+		container_of(link, struct bpf_raw_tp_link, link);
+
 	kfree(raw_tp);
+}
+
+static void bpf_raw_tp_link_show_fdinfo(const struct bpf_link *link,
+					struct seq_file *seq)
+{
+	struct bpf_raw_tp_link *raw_tp_link =
+		container_of(link, struct bpf_raw_tp_link, link);
+
+	seq_printf(seq,
+		   "tp_name:\t%s\n",
+		   raw_tp_link->btp->tp->name);
+}
+
+static int bpf_raw_tp_link_fill_link_info(const struct bpf_link *link,
+					  struct bpf_link_info *info)
+{
+	struct bpf_raw_tp_link *raw_tp_link =
+		container_of(link, struct bpf_raw_tp_link, link);
+	char __user *ubuf = u64_to_user_ptr(info->raw_tracepoint.tp_name);
+	const char *tp_name = raw_tp_link->btp->tp->name;
+	u32 ulen = info->raw_tracepoint.tp_name_len;
+	size_t tp_len = strlen(tp_name);
+
+	if (ulen && !ubuf)
+		return -EINVAL;
+
+	info->raw_tracepoint.tp_name_len = tp_len + 1;
+
+	if (!ubuf)
+		return 0;
+
+	if (ulen >= tp_len + 1) {
+		if (copy_to_user(ubuf, tp_name, tp_len + 1))
+			return -EFAULT;
+	} else {
+		char zero = '\0';
+
+		if (copy_to_user(ubuf, tp_name, ulen - 1))
+			return -EFAULT;
+		if (put_user(zero, ubuf + ulen - 1))
+			return -EFAULT;
+		return -ENOSPC;
+	}
+
 	return 0;
 }
 
-static const struct file_operations bpf_raw_tp_fops = {
-	.release	= bpf_raw_tracepoint_release,
-	.read		= bpf_dummy_read,
-	.write		= bpf_dummy_write,
+static const struct bpf_link_ops bpf_raw_tp_link_lops = {
+	.release = bpf_raw_tp_link_release,
+	.dealloc = bpf_raw_tp_link_dealloc,
+	.show_fdinfo = bpf_raw_tp_link_show_fdinfo,
+	.fill_link_info = bpf_raw_tp_link_fill_link_info,
 };
 
 #define BPF_RAW_TRACEPOINT_OPEN_LAST_FIELD raw_tracepoint.prog_fd
 
 static int bpf_raw_tracepoint_open(const union bpf_attr *attr)
 {
-	struct bpf_raw_tracepoint *raw_tp;
+	struct bpf_link_primer link_primer;
+	struct bpf_raw_tp_link *link;
 	struct bpf_raw_event_map *btp;
 	struct bpf_prog *prog;
 	const char *tp_name;
 	char buf[128];
-	int tp_fd, err;
+	int err;
 
 	if (CHECK_ATTR(BPF_RAW_TRACEPOINT_OPEN))
 		return -EINVAL;
@@ -2255,16 +2684,10 @@ static int bpf_raw_tracepoint_open(const union bpf_attr *attr)
 	if (IS_ERR(prog))
 		return PTR_ERR(prog);
 
-	if (prog->type != BPF_PROG_TYPE_RAW_TRACEPOINT &&
-	    prog->type != BPF_PROG_TYPE_TRACING &&
-	    prog->type != BPF_PROG_TYPE_EXT &&
-	    prog->type != BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE) {
-		err = -EINVAL;
-		goto out_put_prog;
-	}
-
-	if (prog->type == BPF_PROG_TYPE_TRACING ||
-	    prog->type == BPF_PROG_TYPE_EXT) {
+	switch (prog->type) {
+	case BPF_PROG_TYPE_TRACING:
+	case BPF_PROG_TYPE_EXT:
+	case BPF_PROG_TYPE_LSM:
 		if (attr->raw_tracepoint.name) {
 			/* The attach point for this category of programs
 			 * should be specified via btf_id during program load.
@@ -2272,11 +2695,14 @@ static int bpf_raw_tracepoint_open(const union bpf_attr *attr)
 			err = -EINVAL;
 			goto out_put_prog;
 		}
-		if (prog->expected_attach_type == BPF_TRACE_RAW_TP)
+		if (prog->type == BPF_PROG_TYPE_TRACING &&
+		    prog->expected_attach_type == BPF_TRACE_RAW_TP) {
 			tp_name = prog->aux->attach_func_name;
-		else
-			return bpf_tracing_prog_attach(prog);
-	} else {
+			break;
+		}
+		return bpf_tracing_prog_attach(prog);
+	case BPF_PROG_TYPE_RAW_TRACEPOINT:
+	case BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE:
 		if (strncpy_from_user(buf,
 				      u64_to_user_ptr(attr->raw_tracepoint.name),
 				      sizeof(buf) - 1) < 0) {
@@ -2285,6 +2711,10 @@ static int bpf_raw_tracepoint_open(const union bpf_attr *attr)
 		}
 		buf[sizeof(buf) - 1] = 0;
 		tp_name = buf;
+		break;
+	default:
+		err = -EINVAL;
+		goto out_put_prog;
 	}
 
 	btp = bpf_get_raw_tracepoint(tp_name);
@@ -2293,29 +2723,29 @@ static int bpf_raw_tracepoint_open(const union bpf_attr *attr)
 		goto out_put_prog;
 	}
 
-	raw_tp = kzalloc(sizeof(*raw_tp), GFP_USER);
-	if (!raw_tp) {
+	link = kzalloc(sizeof(*link), GFP_USER);
+	if (!link) {
 		err = -ENOMEM;
 		goto out_put_btp;
 	}
-	raw_tp->btp = btp;
-	raw_tp->prog = prog;
+	bpf_link_init(&link->link, BPF_LINK_TYPE_RAW_TRACEPOINT,
+		      &bpf_raw_tp_link_lops, prog);
+	link->btp = btp;
 
-	err = bpf_probe_register(raw_tp->btp, prog);
-	if (err)
-		goto out_free_tp;
+	err = bpf_link_prime(&link->link, &link_primer);
+	if (err) {
+		kfree(link);
+		goto out_put_btp;
+	}
 
-	tp_fd = anon_inode_getfd("bpf-raw-tracepoint", &bpf_raw_tp_fops, raw_tp,
-				 O_CLOEXEC);
-	if (tp_fd < 0) {
-		bpf_probe_unregister(raw_tp->btp, prog);
-		err = tp_fd;
-		goto out_free_tp;
+	err = bpf_probe_register(link->btp, prog);
+	if (err) {
+		bpf_link_cleanup(&link_primer);
+		goto out_put_btp;
 	}
-	return tp_fd;
 
-out_free_tp:
-	kfree(raw_tp);
+	return bpf_link_settle(&link_primer);
+
 out_put_btp:
 	bpf_put_raw_tracepoint(btp);
 out_put_prog:
@@ -2330,8 +2760,14 @@ static int bpf_prog_attach_check_attach_type(const struct bpf_prog *prog,
 	case BPF_PROG_TYPE_CGROUP_SOCK:
 	case BPF_PROG_TYPE_CGROUP_SOCK_ADDR:
 	case BPF_PROG_TYPE_CGROUP_SOCKOPT:
+	case BPF_PROG_TYPE_SK_LOOKUP:
 		return attach_type == prog->expected_attach_type ? 0 : -EINVAL;
 	case BPF_PROG_TYPE_CGROUP_SKB:
+		if (!capable(CAP_NET_ADMIN))
+			/* cg-skb progs can be loaded by unpriv user.
+			 * check permissions at attach time.
+			 */
+			return -EPERM;
 		return prog->enforce_expected_attach_type &&
 			prog->expected_attach_type != attach_type ?
 			-EINVAL : 0;
@@ -2340,75 +2776,81 @@ static int bpf_prog_attach_check_attach_type(const struct bpf_prog *prog,
 	}
 }
 
-#define BPF_PROG_ATTACH_LAST_FIELD replace_bpf_fd
-
-#define BPF_F_ATTACH_MASK \
-	(BPF_F_ALLOW_OVERRIDE | BPF_F_ALLOW_MULTI | BPF_F_REPLACE)
-
-static int bpf_prog_attach(const union bpf_attr *attr)
+static enum bpf_prog_type
+attach_type_to_prog_type(enum bpf_attach_type attach_type)
 {
-	enum bpf_prog_type ptype;
-	struct bpf_prog *prog;
-	int ret;
-
-	if (!capable(CAP_NET_ADMIN))
-		return -EPERM;
-
-	if (CHECK_ATTR(BPF_PROG_ATTACH))
-		return -EINVAL;
-
-	if (attr->attach_flags & ~BPF_F_ATTACH_MASK)
-		return -EINVAL;
-
-	switch (attr->attach_type) {
+	switch (attach_type) {
 	case BPF_CGROUP_INET_INGRESS:
 	case BPF_CGROUP_INET_EGRESS:
-		ptype = BPF_PROG_TYPE_CGROUP_SKB;
+		return BPF_PROG_TYPE_CGROUP_SKB;
 		break;
 	case BPF_CGROUP_INET_SOCK_CREATE:
+	case BPF_CGROUP_INET_SOCK_RELEASE:
 	case BPF_CGROUP_INET4_POST_BIND:
 	case BPF_CGROUP_INET6_POST_BIND:
-		ptype = BPF_PROG_TYPE_CGROUP_SOCK;
-		break;
+		return BPF_PROG_TYPE_CGROUP_SOCK;
 	case BPF_CGROUP_INET4_BIND:
 	case BPF_CGROUP_INET6_BIND:
 	case BPF_CGROUP_INET4_CONNECT:
 	case BPF_CGROUP_INET6_CONNECT:
+	case BPF_CGROUP_INET4_GETPEERNAME:
+	case BPF_CGROUP_INET6_GETPEERNAME:
+	case BPF_CGROUP_INET4_GETSOCKNAME:
+	case BPF_CGROUP_INET6_GETSOCKNAME:
 	case BPF_CGROUP_UDP4_SENDMSG:
 	case BPF_CGROUP_UDP6_SENDMSG:
 	case BPF_CGROUP_UDP4_RECVMSG:
 	case BPF_CGROUP_UDP6_RECVMSG:
-		ptype = BPF_PROG_TYPE_CGROUP_SOCK_ADDR;
-		break;
+		return BPF_PROG_TYPE_CGROUP_SOCK_ADDR;
 	case BPF_CGROUP_SOCK_OPS:
-		ptype = BPF_PROG_TYPE_SOCK_OPS;
-		break;
+		return BPF_PROG_TYPE_SOCK_OPS;
 	case BPF_CGROUP_DEVICE:
-		ptype = BPF_PROG_TYPE_CGROUP_DEVICE;
-		break;
+		return BPF_PROG_TYPE_CGROUP_DEVICE;
 	case BPF_SK_MSG_VERDICT:
-		ptype = BPF_PROG_TYPE_SK_MSG;
-		break;
+		return BPF_PROG_TYPE_SK_MSG;
 	case BPF_SK_SKB_STREAM_PARSER:
 	case BPF_SK_SKB_STREAM_VERDICT:
-		ptype = BPF_PROG_TYPE_SK_SKB;
-		break;
+		return BPF_PROG_TYPE_SK_SKB;
 	case BPF_LIRC_MODE2:
-		ptype = BPF_PROG_TYPE_LIRC_MODE2;
-		break;
+		return BPF_PROG_TYPE_LIRC_MODE2;
 	case BPF_FLOW_DISSECTOR:
-		ptype = BPF_PROG_TYPE_FLOW_DISSECTOR;
-		break;
+		return BPF_PROG_TYPE_FLOW_DISSECTOR;
 	case BPF_CGROUP_SYSCTL:
-		ptype = BPF_PROG_TYPE_CGROUP_SYSCTL;
-		break;
+		return BPF_PROG_TYPE_CGROUP_SYSCTL;
 	case BPF_CGROUP_GETSOCKOPT:
 	case BPF_CGROUP_SETSOCKOPT:
-		ptype = BPF_PROG_TYPE_CGROUP_SOCKOPT;
-		break;
+		return BPF_PROG_TYPE_CGROUP_SOCKOPT;
+	case BPF_TRACE_ITER:
+		return BPF_PROG_TYPE_TRACING;
+	case BPF_SK_LOOKUP:
+		return BPF_PROG_TYPE_SK_LOOKUP;
+	case BPF_XDP:
+		return BPF_PROG_TYPE_XDP;
 	default:
-		return -EINVAL;
+		return BPF_PROG_TYPE_UNSPEC;
 	}
+}
+
+#define BPF_PROG_ATTACH_LAST_FIELD replace_bpf_fd
+
+#define BPF_F_ATTACH_MASK \
+	(BPF_F_ALLOW_OVERRIDE | BPF_F_ALLOW_MULTI | BPF_F_REPLACE)
+
+static int bpf_prog_attach(const union bpf_attr *attr)
+{
+	enum bpf_prog_type ptype;
+	struct bpf_prog *prog;
+	int ret;
+
+	if (CHECK_ATTR(BPF_PROG_ATTACH))
+		return -EINVAL;
+
+	if (attr->attach_flags & ~BPF_F_ATTACH_MASK)
+		return -EINVAL;
+
+	ptype = attach_type_to_prog_type(attr->attach_type);
+	if (ptype == BPF_PROG_TYPE_UNSPEC)
+		return -EINVAL;
 
 	prog = bpf_prog_get_type(attr->attach_bpf_fd, ptype);
 	if (IS_ERR(prog))
@@ -2428,10 +2870,19 @@ static int bpf_prog_attach(const union bpf_attr *attr)
 		ret = lirc_prog_attach(attr, prog);
 		break;
 	case BPF_PROG_TYPE_FLOW_DISSECTOR:
-		ret = skb_flow_dissector_bpf_prog_attach(attr, prog);
+		ret = netns_bpf_prog_attach(attr, prog);
 		break;
-	default:
+	case BPF_PROG_TYPE_CGROUP_DEVICE:
+	case BPF_PROG_TYPE_CGROUP_SKB:
+	case BPF_PROG_TYPE_CGROUP_SOCK:
+	case BPF_PROG_TYPE_CGROUP_SOCK_ADDR:
+	case BPF_PROG_TYPE_CGROUP_SOCKOPT:
+	case BPF_PROG_TYPE_CGROUP_SYSCTL:
+	case BPF_PROG_TYPE_SOCK_OPS:
 		ret = cgroup_bpf_prog_attach(attr, ptype, prog);
+		break;
+	default:
+		ret = -EINVAL;
 	}
 
 	if (ret)
@@ -2445,59 +2896,30 @@ static int bpf_prog_detach(const union bpf_attr *attr)
 {
 	enum bpf_prog_type ptype;
 
-	if (!capable(CAP_NET_ADMIN))
-		return -EPERM;
-
 	if (CHECK_ATTR(BPF_PROG_DETACH))
 		return -EINVAL;
 
-	switch (attr->attach_type) {
-	case BPF_CGROUP_INET_INGRESS:
-	case BPF_CGROUP_INET_EGRESS:
-		ptype = BPF_PROG_TYPE_CGROUP_SKB;
-		break;
-	case BPF_CGROUP_INET_SOCK_CREATE:
-	case BPF_CGROUP_INET4_POST_BIND:
-	case BPF_CGROUP_INET6_POST_BIND:
-		ptype = BPF_PROG_TYPE_CGROUP_SOCK;
-		break;
-	case BPF_CGROUP_INET4_BIND:
-	case BPF_CGROUP_INET6_BIND:
-	case BPF_CGROUP_INET4_CONNECT:
-	case BPF_CGROUP_INET6_CONNECT:
-	case BPF_CGROUP_UDP4_SENDMSG:
-	case BPF_CGROUP_UDP6_SENDMSG:
-	case BPF_CGROUP_UDP4_RECVMSG:
-	case BPF_CGROUP_UDP6_RECVMSG:
-		ptype = BPF_PROG_TYPE_CGROUP_SOCK_ADDR;
-		break;
-	case BPF_CGROUP_SOCK_OPS:
-		ptype = BPF_PROG_TYPE_SOCK_OPS;
-		break;
-	case BPF_CGROUP_DEVICE:
-		ptype = BPF_PROG_TYPE_CGROUP_DEVICE;
-		break;
-	case BPF_SK_MSG_VERDICT:
-		return sock_map_get_from_fd(attr, NULL);
-	case BPF_SK_SKB_STREAM_PARSER:
-	case BPF_SK_SKB_STREAM_VERDICT:
-		return sock_map_get_from_fd(attr, NULL);
-	case BPF_LIRC_MODE2:
+	ptype = attach_type_to_prog_type(attr->attach_type);
+
+	switch (ptype) {
+	case BPF_PROG_TYPE_SK_MSG:
+	case BPF_PROG_TYPE_SK_SKB:
+		return sock_map_prog_detach(attr, ptype);
+	case BPF_PROG_TYPE_LIRC_MODE2:
 		return lirc_prog_detach(attr);
-	case BPF_FLOW_DISSECTOR:
-		return skb_flow_dissector_bpf_prog_detach(attr);
-	case BPF_CGROUP_SYSCTL:
-		ptype = BPF_PROG_TYPE_CGROUP_SYSCTL;
-		break;
-	case BPF_CGROUP_GETSOCKOPT:
-	case BPF_CGROUP_SETSOCKOPT:
-		ptype = BPF_PROG_TYPE_CGROUP_SOCKOPT;
-		break;
+	case BPF_PROG_TYPE_FLOW_DISSECTOR:
+		return netns_bpf_prog_detach(attr, ptype);
+	case BPF_PROG_TYPE_CGROUP_DEVICE:
+	case BPF_PROG_TYPE_CGROUP_SKB:
+	case BPF_PROG_TYPE_CGROUP_SOCK:
+	case BPF_PROG_TYPE_CGROUP_SOCK_ADDR:
+	case BPF_PROG_TYPE_CGROUP_SOCKOPT:
+	case BPF_PROG_TYPE_CGROUP_SYSCTL:
+	case BPF_PROG_TYPE_SOCK_OPS:
+		return cgroup_bpf_prog_detach(attr, ptype);
 	default:
 		return -EINVAL;
 	}
-
-	return cgroup_bpf_prog_detach(attr, ptype);
 }
 
 #define BPF_PROG_QUERY_LAST_FIELD query.prog_cnt
@@ -2516,12 +2938,17 @@ static int bpf_prog_query(const union bpf_attr *attr,
 	case BPF_CGROUP_INET_INGRESS:
 	case BPF_CGROUP_INET_EGRESS:
 	case BPF_CGROUP_INET_SOCK_CREATE:
+	case BPF_CGROUP_INET_SOCK_RELEASE:
 	case BPF_CGROUP_INET4_BIND:
 	case BPF_CGROUP_INET6_BIND:
 	case BPF_CGROUP_INET4_POST_BIND:
 	case BPF_CGROUP_INET6_POST_BIND:
 	case BPF_CGROUP_INET4_CONNECT:
 	case BPF_CGROUP_INET6_CONNECT:
+	case BPF_CGROUP_INET4_GETPEERNAME:
+	case BPF_CGROUP_INET6_GETPEERNAME:
+	case BPF_CGROUP_INET4_GETSOCKNAME:
+	case BPF_CGROUP_INET6_GETSOCKNAME:
 	case BPF_CGROUP_UDP4_SENDMSG:
 	case BPF_CGROUP_UDP6_SENDMSG:
 	case BPF_CGROUP_UDP4_RECVMSG:
@@ -2531,16 +2958,15 @@ static int bpf_prog_query(const union bpf_attr *attr,
 	case BPF_CGROUP_SYSCTL:
 	case BPF_CGROUP_GETSOCKOPT:
 	case BPF_CGROUP_SETSOCKOPT:
-		break;
+		return cgroup_bpf_prog_query(attr, uattr);
 	case BPF_LIRC_MODE2:
 		return lirc_prog_query(attr, uattr);
 	case BPF_FLOW_DISSECTOR:
-		return skb_flow_dissector_prog_query(attr, uattr);
+	case BPF_SK_LOOKUP:
+		return netns_bpf_prog_query(attr, uattr);
 	default:
 		return -EINVAL;
 	}
-
-	return cgroup_bpf_prog_query(attr, uattr);
 }
 
 #define BPF_PROG_TEST_RUN_LAST_FIELD test.ctx_out
@@ -2551,8 +2977,6 @@ static int bpf_prog_test_run(const union bpf_attr *attr,
 	struct bpf_prog *prog;
 	int ret = -ENOTSUPP;
 
-	if (!capable(CAP_SYS_ADMIN))
-		return -EPERM;
 	if (CHECK_ATTR(BPF_PROG_TEST_RUN))
 		return -EINVAL;
 
@@ -2603,6 +3027,44 @@ static int bpf_obj_get_next_id(const union bpf_attr *attr,
 	return err;
 }
 
+struct bpf_map *bpf_map_get_curr_or_next(u32 *id)
+{
+	struct bpf_map *map;
+
+	spin_lock_bh(&map_idr_lock);
+again:
+	map = idr_get_next(&map_idr, id);
+	if (map) {
+		map = __bpf_map_inc_not_zero(map, false);
+		if (IS_ERR(map)) {
+			(*id)++;
+			goto again;
+		}
+	}
+	spin_unlock_bh(&map_idr_lock);
+
+	return map;
+}
+
+struct bpf_prog *bpf_prog_get_curr_or_next(u32 *id)
+{
+	struct bpf_prog *prog;
+
+	spin_lock_bh(&prog_idr_lock);
+again:
+	prog = idr_get_next(&prog_idr, id);
+	if (prog) {
+		prog = bpf_prog_inc_not_zero(prog);
+		if (IS_ERR(prog)) {
+			(*id)++;
+			goto again;
+		}
+	}
+	spin_unlock_bh(&prog_idr_lock);
+
+	return prog;
+}
+
 #define BPF_PROG_GET_FD_BY_ID_LAST_FIELD prog_id
 
 struct bpf_prog *bpf_prog_by_id(u32 id)
@@ -2707,12 +3169,14 @@ static const struct bpf_map *bpf_map_from_imm(const struct bpf_prog *prog,
 	return NULL;
 }
 
-static struct bpf_insn *bpf_insn_prepare_dump(const struct bpf_prog *prog)
+static struct bpf_insn *bpf_insn_prepare_dump(const struct bpf_prog *prog,
+					      const struct cred *f_cred)
 {
 	const struct bpf_map *map;
 	struct bpf_insn *insns;
 	u32 off, type;
 	u64 imm;
+	u8 code;
 	int i;
 
 	insns = kmemdup(prog->insnsi, bpf_prog_insn_size(prog),
@@ -2721,21 +3185,27 @@ static struct bpf_insn *bpf_insn_prepare_dump(const struct bpf_prog *prog)
 		return insns;
 
 	for (i = 0; i < prog->len; i++) {
-		if (insns[i].code == (BPF_JMP | BPF_TAIL_CALL)) {
+		code = insns[i].code;
+
+		if (code == (BPF_JMP | BPF_TAIL_CALL)) {
 			insns[i].code = BPF_JMP | BPF_CALL;
 			insns[i].imm = BPF_FUNC_tail_call;
 			/* fall-through */
 		}
-		if (insns[i].code == (BPF_JMP | BPF_CALL) ||
-		    insns[i].code == (BPF_JMP | BPF_CALL_ARGS)) {
-			if (insns[i].code == (BPF_JMP | BPF_CALL_ARGS))
+		if (code == (BPF_JMP | BPF_CALL) ||
+		    code == (BPF_JMP | BPF_CALL_ARGS)) {
+			if (code == (BPF_JMP | BPF_CALL_ARGS))
 				insns[i].code = BPF_JMP | BPF_CALL;
-			if (!bpf_dump_raw_ok())
+			if (!bpf_dump_raw_ok(f_cred))
 				insns[i].imm = 0;
 			continue;
 		}
+		if (BPF_CLASS(code) == BPF_LDX && BPF_MODE(code) == BPF_PROBE_MEM) {
+			insns[i].code = BPF_LDX | BPF_SIZE(code) | BPF_MEM;
+			continue;
+		}
 
-		if (insns[i].code != (BPF_LD | BPF_IMM | BPF_DW))
+		if (code != (BPF_LD | BPF_IMM | BPF_DW))
 			continue;
 
 		imm = ((u64)insns[i + 1].imm << 32) | (u32)insns[i].imm;
@@ -2782,12 +3252,13 @@ static int set_info_rec_size(struct bpf_prog_info *info)
 	return 0;
 }
 
-static int bpf_prog_get_info_by_fd(struct bpf_prog *prog,
+static int bpf_prog_get_info_by_fd(struct file *file,
+				   struct bpf_prog *prog,
 				   const union bpf_attr *attr,
 				   union bpf_attr __user *uattr)
 {
 	struct bpf_prog_info __user *uinfo = u64_to_user_ptr(attr->info.info);
-	struct bpf_prog_info info = {};
+	struct bpf_prog_info info;
 	u32 info_len = attr->info.info_len;
 	struct bpf_prog_stats stats;
 	char __user *uinsns;
@@ -2799,6 +3270,7 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog,
 		return err;
 	info_len = min_t(u32, sizeof(info), info_len);
 
+	memset(&info, 0, sizeof(info));
 	if (copy_from_user(&info, uinfo, info_len))
 		return -EFAULT;
 
@@ -2833,7 +3305,7 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog,
 	info.run_time_ns = stats.nsecs;
 	info.run_cnt = stats.cnt;
 
-	if (!capable(CAP_SYS_ADMIN)) {
+	if (!bpf_capable()) {
 		info.jited_prog_len = 0;
 		info.xlated_prog_len = 0;
 		info.nr_jited_ksyms = 0;
@@ -2850,11 +3322,11 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog,
 		struct bpf_insn *insns_sanitized;
 		bool fault;
 
-		if (prog->blinded && !bpf_dump_raw_ok()) {
+		if (prog->blinded && !bpf_dump_raw_ok(file->f_cred)) {
 			info.xlated_prog_insns = 0;
 			goto done;
 		}
-		insns_sanitized = bpf_insn_prepare_dump(prog);
+		insns_sanitized = bpf_insn_prepare_dump(prog, file->f_cred);
 		if (!insns_sanitized)
 			return -ENOMEM;
 		uinsns = u64_to_user_ptr(info.xlated_prog_insns);
@@ -2888,7 +3360,7 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog,
 	}
 
 	if (info.jited_prog_len && ulen) {
-		if (bpf_dump_raw_ok()) {
+		if (bpf_dump_raw_ok(file->f_cred)) {
 			uinsns = u64_to_user_ptr(info.jited_prog_insns);
 			ulen = min_t(u32, info.jited_prog_len, ulen);
 
@@ -2923,7 +3395,7 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog,
 	ulen = info.nr_jited_ksyms;
 	info.nr_jited_ksyms = prog->aux->func_cnt ? : 1;
 	if (ulen) {
-		if (bpf_dump_raw_ok()) {
+		if (bpf_dump_raw_ok(file->f_cred)) {
 			unsigned long ksym_addr;
 			u64 __user *user_ksyms;
 			u32 i;
@@ -2954,7 +3426,7 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog,
 	ulen = info.nr_jited_func_lens;
 	info.nr_jited_func_lens = prog->aux->func_cnt ? : 1;
 	if (ulen) {
-		if (bpf_dump_raw_ok()) {
+		if (bpf_dump_raw_ok(file->f_cred)) {
 			u32 __user *user_lens;
 			u32 func_len, i;
 
@@ -3011,7 +3483,7 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog,
 	else
 		info.nr_jited_line_info = 0;
 	if (info.nr_jited_line_info && ulen) {
-		if (bpf_dump_raw_ok()) {
+		if (bpf_dump_raw_ok(file->f_cred)) {
 			__u64 __user *user_linfo;
 			u32 i;
 
@@ -3057,12 +3529,13 @@ done:
 	return 0;
 }
 
-static int bpf_map_get_info_by_fd(struct bpf_map *map,
+static int bpf_map_get_info_by_fd(struct file *file,
+				  struct bpf_map *map,
 				  const union bpf_attr *attr,
 				  union bpf_attr __user *uattr)
 {
 	struct bpf_map_info __user *uinfo = u64_to_user_ptr(attr->info.info);
-	struct bpf_map_info info = {};
+	struct bpf_map_info info;
 	u32 info_len = attr->info.info_len;
 	int err;
 
@@ -3071,6 +3544,7 @@ static int bpf_map_get_info_by_fd(struct bpf_map *map,
 		return err;
 	info_len = min_t(u32, sizeof(info), info_len);
 
+	memset(&info, 0, sizeof(info));
 	info.type = map->map_type;
 	info.id = map->id;
 	info.key_size = map->key_size;
@@ -3099,7 +3573,8 @@ static int bpf_map_get_info_by_fd(struct bpf_map *map,
 	return 0;
 }
 
-static int bpf_btf_get_info_by_fd(struct btf *btf,
+static int bpf_btf_get_info_by_fd(struct file *file,
+				  struct btf *btf,
 				  const union bpf_attr *attr,
 				  union bpf_attr __user *uattr)
 {
@@ -3114,6 +3589,43 @@ static int bpf_btf_get_info_by_fd(struct btf *btf,
 	return btf_get_info_by_fd(btf, attr, uattr);
 }
 
+static int bpf_link_get_info_by_fd(struct file *file,
+				  struct bpf_link *link,
+				  const union bpf_attr *attr,
+				  union bpf_attr __user *uattr)
+{
+	struct bpf_link_info __user *uinfo = u64_to_user_ptr(attr->info.info);
+	struct bpf_link_info info;
+	u32 info_len = attr->info.info_len;
+	int err;
+
+	err = bpf_check_uarg_tail_zero(uinfo, sizeof(info), info_len);
+	if (err)
+		return err;
+	info_len = min_t(u32, sizeof(info), info_len);
+
+	memset(&info, 0, sizeof(info));
+	if (copy_from_user(&info, uinfo, info_len))
+		return -EFAULT;
+
+	info.type = link->type;
+	info.id = link->id;
+	info.prog_id = link->prog->aux->id;
+
+	if (link->ops->fill_link_info) {
+		err = link->ops->fill_link_info(link, &info);
+		if (err)
+			return err;
+	}
+
+	if (copy_to_user(uinfo, &info, info_len) ||
+	    put_user(info_len, &uattr->info.info_len))
+		return -EFAULT;
+
+	return 0;
+}
+
+
 #define BPF_OBJ_GET_INFO_BY_FD_LAST_FIELD info.info
 
 static int bpf_obj_get_info_by_fd(const union bpf_attr *attr,
@@ -3131,13 +3643,16 @@ static int bpf_obj_get_info_by_fd(const union bpf_attr *attr,
 		return -EBADFD;
 
 	if (f.file->f_op == &bpf_prog_fops)
-		err = bpf_prog_get_info_by_fd(f.file->private_data, attr,
+		err = bpf_prog_get_info_by_fd(f.file, f.file->private_data, attr,
 					      uattr);
 	else if (f.file->f_op == &bpf_map_fops)
-		err = bpf_map_get_info_by_fd(f.file->private_data, attr,
+		err = bpf_map_get_info_by_fd(f.file, f.file->private_data, attr,
 					     uattr);
 	else if (f.file->f_op == &btf_fops)
-		err = bpf_btf_get_info_by_fd(f.file->private_data, attr, uattr);
+		err = bpf_btf_get_info_by_fd(f.file, f.file->private_data, attr, uattr);
+	else if (f.file->f_op == &bpf_link_fops)
+		err = bpf_link_get_info_by_fd(f.file, f.file->private_data,
+					      attr, uattr);
 	else
 		err = -EINVAL;
 
@@ -3152,7 +3667,7 @@ static int bpf_btf_load(const union bpf_attr *attr)
 	if (CHECK_ATTR(BPF_BTF_LOAD))
 		return -EINVAL;
 
-	if (!capable(CAP_SYS_ADMIN))
+	if (!bpf_capable())
 		return -EPERM;
 
 	return btf_new_fd(attr);
@@ -3262,15 +3777,21 @@ static int bpf_task_fd_query(const union bpf_attr *attr,
 	if (err)
 		goto out;
 
-	if (file->f_op == &bpf_raw_tp_fops) {
-		struct bpf_raw_tracepoint *raw_tp = file->private_data;
-		struct bpf_raw_event_map *btp = raw_tp->btp;
+	if (file->f_op == &bpf_link_fops) {
+		struct bpf_link *link = file->private_data;
 
-		err = bpf_task_fd_query_copy(attr, uattr,
-					     raw_tp->prog->aux->id,
-					     BPF_FD_TYPE_RAW_TRACEPOINT,
-					     btp->tp->name, 0, 0);
-		goto put_file;
+		if (link->ops == &bpf_raw_tp_link_lops) {
+			struct bpf_raw_tp_link *raw_tp =
+				container_of(link, struct bpf_raw_tp_link, link);
+			struct bpf_raw_event_map *btp = raw_tp->btp;
+
+			err = bpf_task_fd_query_copy(attr, uattr,
+						     raw_tp->link.prog->aux->id,
+						     BPF_FD_TYPE_RAW_TRACEPOINT,
+						     btp->tp->name, 0, 0);
+			goto put_file;
+		}
+		goto out_not_supp;
 	}
 
 	event = perf_get_event(file);
@@ -3290,6 +3811,7 @@ static int bpf_task_fd_query(const union bpf_attr *attr,
 		goto put_file;
 	}
 
+out_not_supp:
 	err = -ENOTSUPP;
 put_file:
 	fput(file);
@@ -3352,12 +3874,271 @@ err_put:
 	return err;
 }
 
+static int tracing_bpf_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
+{
+	if (attr->link_create.attach_type == BPF_TRACE_ITER &&
+	    prog->expected_attach_type == BPF_TRACE_ITER)
+		return bpf_iter_link_attach(attr, prog);
+
+	return -EINVAL;
+}
+
+#define BPF_LINK_CREATE_LAST_FIELD link_create.iter_info_len
+static int link_create(union bpf_attr *attr)
+{
+	enum bpf_prog_type ptype;
+	struct bpf_prog *prog;
+	int ret;
+
+	if (CHECK_ATTR(BPF_LINK_CREATE))
+		return -EINVAL;
+
+	ptype = attach_type_to_prog_type(attr->link_create.attach_type);
+	if (ptype == BPF_PROG_TYPE_UNSPEC)
+		return -EINVAL;
+
+	prog = bpf_prog_get_type(attr->link_create.prog_fd, ptype);
+	if (IS_ERR(prog))
+		return PTR_ERR(prog);
+
+	ret = bpf_prog_attach_check_attach_type(prog,
+						attr->link_create.attach_type);
+	if (ret)
+		goto err_out;
+
+	switch (ptype) {
+	case BPF_PROG_TYPE_CGROUP_SKB:
+	case BPF_PROG_TYPE_CGROUP_SOCK:
+	case BPF_PROG_TYPE_CGROUP_SOCK_ADDR:
+	case BPF_PROG_TYPE_SOCK_OPS:
+	case BPF_PROG_TYPE_CGROUP_DEVICE:
+	case BPF_PROG_TYPE_CGROUP_SYSCTL:
+	case BPF_PROG_TYPE_CGROUP_SOCKOPT:
+		ret = cgroup_bpf_link_attach(attr, prog);
+		break;
+	case BPF_PROG_TYPE_TRACING:
+		ret = tracing_bpf_link_attach(attr, prog);
+		break;
+	case BPF_PROG_TYPE_FLOW_DISSECTOR:
+	case BPF_PROG_TYPE_SK_LOOKUP:
+		ret = netns_bpf_link_create(attr, prog);
+		break;
+#ifdef CONFIG_NET
+	case BPF_PROG_TYPE_XDP:
+		ret = bpf_xdp_link_attach(attr, prog);
+		break;
+#endif
+	default:
+		ret = -EINVAL;
+	}
+
+err_out:
+	if (ret < 0)
+		bpf_prog_put(prog);
+	return ret;
+}
+
+#define BPF_LINK_UPDATE_LAST_FIELD link_update.old_prog_fd
+
+static int link_update(union bpf_attr *attr)
+{
+	struct bpf_prog *old_prog = NULL, *new_prog;
+	struct bpf_link *link;
+	u32 flags;
+	int ret;
+
+	if (CHECK_ATTR(BPF_LINK_UPDATE))
+		return -EINVAL;
+
+	flags = attr->link_update.flags;
+	if (flags & ~BPF_F_REPLACE)
+		return -EINVAL;
+
+	link = bpf_link_get_from_fd(attr->link_update.link_fd);
+	if (IS_ERR(link))
+		return PTR_ERR(link);
+
+	new_prog = bpf_prog_get(attr->link_update.new_prog_fd);
+	if (IS_ERR(new_prog)) {
+		ret = PTR_ERR(new_prog);
+		goto out_put_link;
+	}
+
+	if (flags & BPF_F_REPLACE) {
+		old_prog = bpf_prog_get(attr->link_update.old_prog_fd);
+		if (IS_ERR(old_prog)) {
+			ret = PTR_ERR(old_prog);
+			old_prog = NULL;
+			goto out_put_progs;
+		}
+	} else if (attr->link_update.old_prog_fd) {
+		ret = -EINVAL;
+		goto out_put_progs;
+	}
+
+	if (link->ops->update_prog)
+		ret = link->ops->update_prog(link, new_prog, old_prog);
+	else
+		ret = -EINVAL;
+
+out_put_progs:
+	if (old_prog)
+		bpf_prog_put(old_prog);
+	if (ret)
+		bpf_prog_put(new_prog);
+out_put_link:
+	bpf_link_put(link);
+	return ret;
+}
+
+#define BPF_LINK_DETACH_LAST_FIELD link_detach.link_fd
+
+static int link_detach(union bpf_attr *attr)
+{
+	struct bpf_link *link;
+	int ret;
+
+	if (CHECK_ATTR(BPF_LINK_DETACH))
+		return -EINVAL;
+
+	link = bpf_link_get_from_fd(attr->link_detach.link_fd);
+	if (IS_ERR(link))
+		return PTR_ERR(link);
+
+	if (link->ops->detach)
+		ret = link->ops->detach(link);
+	else
+		ret = -EOPNOTSUPP;
+
+	bpf_link_put(link);
+	return ret;
+}
+
+static int bpf_link_inc_not_zero(struct bpf_link *link)
+{
+	return atomic64_fetch_add_unless(&link->refcnt, 1, 0) ? 0 : -ENOENT;
+}
+
+#define BPF_LINK_GET_FD_BY_ID_LAST_FIELD link_id
+
+static int bpf_link_get_fd_by_id(const union bpf_attr *attr)
+{
+	struct bpf_link *link;
+	u32 id = attr->link_id;
+	int fd, err;
+
+	if (CHECK_ATTR(BPF_LINK_GET_FD_BY_ID))
+		return -EINVAL;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	spin_lock_bh(&link_idr_lock);
+	link = idr_find(&link_idr, id);
+	/* before link is "settled", ID is 0, pretend it doesn't exist yet */
+	if (link) {
+		if (link->id)
+			err = bpf_link_inc_not_zero(link);
+		else
+			err = -EAGAIN;
+	} else {
+		err = -ENOENT;
+	}
+	spin_unlock_bh(&link_idr_lock);
+
+	if (err)
+		return err;
+
+	fd = bpf_link_new_fd(link);
+	if (fd < 0)
+		bpf_link_put(link);
+
+	return fd;
+}
+
+DEFINE_MUTEX(bpf_stats_enabled_mutex);
+
+static int bpf_stats_release(struct inode *inode, struct file *file)
+{
+	mutex_lock(&bpf_stats_enabled_mutex);
+	static_key_slow_dec(&bpf_stats_enabled_key.key);
+	mutex_unlock(&bpf_stats_enabled_mutex);
+	return 0;
+}
+
+static const struct file_operations bpf_stats_fops = {
+	.release = bpf_stats_release,
+};
+
+static int bpf_enable_runtime_stats(void)
+{
+	int fd;
+
+	mutex_lock(&bpf_stats_enabled_mutex);
+
+	/* Set a very high limit to avoid overflow */
+	if (static_key_count(&bpf_stats_enabled_key.key) > INT_MAX / 2) {
+		mutex_unlock(&bpf_stats_enabled_mutex);
+		return -EBUSY;
+	}
+
+	fd = anon_inode_getfd("bpf-stats", &bpf_stats_fops, NULL, O_CLOEXEC);
+	if (fd >= 0)
+		static_key_slow_inc(&bpf_stats_enabled_key.key);
+
+	mutex_unlock(&bpf_stats_enabled_mutex);
+	return fd;
+}
+
+#define BPF_ENABLE_STATS_LAST_FIELD enable_stats.type
+
+static int bpf_enable_stats(union bpf_attr *attr)
+{
+
+	if (CHECK_ATTR(BPF_ENABLE_STATS))
+		return -EINVAL;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	switch (attr->enable_stats.type) {
+	case BPF_STATS_RUN_TIME:
+		return bpf_enable_runtime_stats();
+	default:
+		break;
+	}
+	return -EINVAL;
+}
+
+#define BPF_ITER_CREATE_LAST_FIELD iter_create.flags
+
+static int bpf_iter_create(union bpf_attr *attr)
+{
+	struct bpf_link *link;
+	int err;
+
+	if (CHECK_ATTR(BPF_ITER_CREATE))
+		return -EINVAL;
+
+	if (attr->iter_create.flags)
+		return -EINVAL;
+
+	link = bpf_link_get_from_fd(attr->iter_create.link_fd);
+	if (IS_ERR(link))
+		return PTR_ERR(link);
+
+	err = bpf_iter_new_fd(link);
+	bpf_link_put(link);
+
+	return err;
+}
+
 SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, size)
 {
-	union bpf_attr attr = {};
+	union bpf_attr attr;
 	int err;
 
-	if (sysctl_unprivileged_bpf_disabled && !capable(CAP_SYS_ADMIN))
+	if (sysctl_unprivileged_bpf_disabled && !bpf_capable())
 		return -EPERM;
 
 	err = bpf_check_uarg_tail_zero(uattr, sizeof(attr), size);
@@ -3366,6 +4147,7 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz
 	size = min_t(u32, size, sizeof(attr));
 
 	/* copy attributes from user space, may be less than sizeof(bpf_attr) */
+	memset(&attr, 0, sizeof(attr));
 	if (copy_from_user(&attr, uattr, size) != 0)
 		return -EFAULT;
 
@@ -3462,6 +4244,28 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz
 	case BPF_MAP_DELETE_BATCH:
 		err = bpf_map_do_batch(&attr, uattr, BPF_MAP_DELETE_BATCH);
 		break;
+	case BPF_LINK_CREATE:
+		err = link_create(&attr);
+		break;
+	case BPF_LINK_UPDATE:
+		err = link_update(&attr);
+		break;
+	case BPF_LINK_GET_FD_BY_ID:
+		err = bpf_link_get_fd_by_id(&attr);
+		break;
+	case BPF_LINK_GET_NEXT_ID:
+		err = bpf_obj_get_next_id(&attr, uattr,
+					  &link_idr, &link_idr_lock);
+		break;
+	case BPF_ENABLE_STATS:
+		err = bpf_enable_stats(&attr);
+		break;
+	case BPF_ITER_CREATE:
+		err = bpf_iter_create(&attr);
+		break;
+	case BPF_LINK_DETACH:
+		err = link_detach(&attr);
+		break;
 	default:
 		err = -EINVAL;
 		break;
diff --git a/kernel/bpf/sysfs_btf.c b/kernel/bpf/sysfs_btf.c
index 7ae5dddd1fe6..3b495773de5a 100644
--- a/kernel/bpf/sysfs_btf.c
+++ b/kernel/bpf/sysfs_btf.c
@@ -9,15 +9,15 @@
 #include <linux/sysfs.h>
 
 /* See scripts/link-vmlinux.sh, gen_btf() func for details */
-extern char __weak _binary__btf_vmlinux_bin_start[];
-extern char __weak _binary__btf_vmlinux_bin_end[];
+extern char __weak __start_BTF[];
+extern char __weak __stop_BTF[];
 
 static ssize_t
 btf_vmlinux_read(struct file *file, struct kobject *kobj,
 		 struct bin_attribute *bin_attr,
 		 char *buf, loff_t off, size_t len)
 {
-	memcpy(buf, _binary__btf_vmlinux_bin_start + off, len);
+	memcpy(buf, __start_BTF + off, len);
 	return len;
 }
 
@@ -30,15 +30,14 @@ static struct kobject *btf_kobj;
 
 static int __init btf_vmlinux_init(void)
 {
-	if (!_binary__btf_vmlinux_bin_start)
+	if (!__start_BTF)
 		return 0;
 
 	btf_kobj = kobject_create_and_add("btf", kernel_kobj);
 	if (!btf_kobj)
 		return -ENOMEM;
 
-	bin_attr_btf_vmlinux.size = _binary__btf_vmlinux_bin_end -
-				    _binary__btf_vmlinux_bin_start;
+	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/task_iter.c b/kernel/bpf/task_iter.c
new file mode 100644
index 000000000000..99af4cea1102
--- /dev/null
+++ b/kernel/bpf/task_iter.c
@@ -0,0 +1,373 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (c) 2020 Facebook */
+
+#include <linux/init.h>
+#include <linux/namei.h>
+#include <linux/pid_namespace.h>
+#include <linux/fs.h>
+#include <linux/fdtable.h>
+#include <linux/filter.h>
+#include <linux/btf_ids.h>
+
+struct bpf_iter_seq_task_common {
+	struct pid_namespace *ns;
+};
+
+struct bpf_iter_seq_task_info {
+	/* The first field must be struct bpf_iter_seq_task_common.
+	 * this is assumed by {init, fini}_seq_pidns() callback functions.
+	 */
+	struct bpf_iter_seq_task_common common;
+	u32 tid;
+};
+
+static struct task_struct *task_seq_get_next(struct pid_namespace *ns,
+					     u32 *tid)
+{
+	struct task_struct *task = NULL;
+	struct pid *pid;
+
+	rcu_read_lock();
+retry:
+	pid = find_ge_pid(*tid, ns);
+	if (pid) {
+		*tid = pid_nr_ns(pid, ns);
+		task = get_pid_task(pid, PIDTYPE_PID);
+		if (!task) {
+			++*tid;
+			goto retry;
+		}
+	}
+	rcu_read_unlock();
+
+	return task;
+}
+
+static void *task_seq_start(struct seq_file *seq, loff_t *pos)
+{
+	struct bpf_iter_seq_task_info *info = seq->private;
+	struct task_struct *task;
+
+	task = task_seq_get_next(info->common.ns, &info->tid);
+	if (!task)
+		return NULL;
+
+	if (*pos == 0)
+		++*pos;
+	return task;
+}
+
+static void *task_seq_next(struct seq_file *seq, void *v, loff_t *pos)
+{
+	struct bpf_iter_seq_task_info *info = seq->private;
+	struct task_struct *task;
+
+	++*pos;
+	++info->tid;
+	put_task_struct((struct task_struct *)v);
+	task = task_seq_get_next(info->common.ns, &info->tid);
+	if (!task)
+		return NULL;
+
+	return task;
+}
+
+struct bpf_iter__task {
+	__bpf_md_ptr(struct bpf_iter_meta *, meta);
+	__bpf_md_ptr(struct task_struct *, task);
+};
+
+DEFINE_BPF_ITER_FUNC(task, struct bpf_iter_meta *meta, struct task_struct *task)
+
+static int __task_seq_show(struct seq_file *seq, struct task_struct *task,
+			   bool in_stop)
+{
+	struct bpf_iter_meta meta;
+	struct bpf_iter__task ctx;
+	struct bpf_prog *prog;
+
+	meta.seq = seq;
+	prog = bpf_iter_get_info(&meta, in_stop);
+	if (!prog)
+		return 0;
+
+	meta.seq = seq;
+	ctx.meta = &meta;
+	ctx.task = task;
+	return bpf_iter_run_prog(prog, &ctx);
+}
+
+static int task_seq_show(struct seq_file *seq, void *v)
+{
+	return __task_seq_show(seq, v, false);
+}
+
+static void task_seq_stop(struct seq_file *seq, void *v)
+{
+	if (!v)
+		(void)__task_seq_show(seq, v, true);
+	else
+		put_task_struct((struct task_struct *)v);
+}
+
+static const struct seq_operations task_seq_ops = {
+	.start	= task_seq_start,
+	.next	= task_seq_next,
+	.stop	= task_seq_stop,
+	.show	= task_seq_show,
+};
+
+struct bpf_iter_seq_task_file_info {
+	/* The first field must be struct bpf_iter_seq_task_common.
+	 * this is assumed by {init, fini}_seq_pidns() callback functions.
+	 */
+	struct bpf_iter_seq_task_common common;
+	struct task_struct *task;
+	struct files_struct *files;
+	u32 tid;
+	u32 fd;
+};
+
+static struct file *
+task_file_seq_get_next(struct bpf_iter_seq_task_file_info *info,
+		       struct task_struct **task, struct files_struct **fstruct)
+{
+	struct pid_namespace *ns = info->common.ns;
+	u32 curr_tid = info->tid, max_fds;
+	struct files_struct *curr_files;
+	struct task_struct *curr_task;
+	int curr_fd = info->fd;
+
+	/* If this function returns a non-NULL file object,
+	 * it held a reference to the task/files_struct/file.
+	 * Otherwise, it does not hold any reference.
+	 */
+again:
+	if (*task) {
+		curr_task = *task;
+		curr_files = *fstruct;
+		curr_fd = info->fd;
+	} else {
+		curr_task = task_seq_get_next(ns, &curr_tid);
+		if (!curr_task)
+			return NULL;
+
+		curr_files = get_files_struct(curr_task);
+		if (!curr_files) {
+			put_task_struct(curr_task);
+			curr_tid = ++(info->tid);
+			info->fd = 0;
+			goto again;
+		}
+
+		/* set *fstruct, *task and info->tid */
+		*fstruct = curr_files;
+		*task = curr_task;
+		if (curr_tid == info->tid) {
+			curr_fd = info->fd;
+		} else {
+			info->tid = curr_tid;
+			curr_fd = 0;
+		}
+	}
+
+	rcu_read_lock();
+	max_fds = files_fdtable(curr_files)->max_fds;
+	for (; curr_fd < max_fds; curr_fd++) {
+		struct file *f;
+
+		f = fcheck_files(curr_files, curr_fd);
+		if (!f)
+			continue;
+		if (!get_file_rcu(f))
+			continue;
+
+		/* set info->fd */
+		info->fd = curr_fd;
+		rcu_read_unlock();
+		return f;
+	}
+
+	/* the current task is done, go to the next task */
+	rcu_read_unlock();
+	put_files_struct(curr_files);
+	put_task_struct(curr_task);
+	*task = NULL;
+	*fstruct = NULL;
+	info->fd = 0;
+	curr_tid = ++(info->tid);
+	goto again;
+}
+
+static void *task_file_seq_start(struct seq_file *seq, loff_t *pos)
+{
+	struct bpf_iter_seq_task_file_info *info = seq->private;
+	struct files_struct *files = NULL;
+	struct task_struct *task = NULL;
+	struct file *file;
+
+	file = task_file_seq_get_next(info, &task, &files);
+	if (!file) {
+		info->files = NULL;
+		info->task = NULL;
+		return NULL;
+	}
+
+	if (*pos == 0)
+		++*pos;
+	info->task = task;
+	info->files = files;
+
+	return file;
+}
+
+static void *task_file_seq_next(struct seq_file *seq, void *v, loff_t *pos)
+{
+	struct bpf_iter_seq_task_file_info *info = seq->private;
+	struct files_struct *files = info->files;
+	struct task_struct *task = info->task;
+	struct file *file;
+
+	++*pos;
+	++info->fd;
+	fput((struct file *)v);
+	file = task_file_seq_get_next(info, &task, &files);
+	if (!file) {
+		info->files = NULL;
+		info->task = NULL;
+		return NULL;
+	}
+
+	info->task = task;
+	info->files = files;
+
+	return file;
+}
+
+struct bpf_iter__task_file {
+	__bpf_md_ptr(struct bpf_iter_meta *, meta);
+	__bpf_md_ptr(struct task_struct *, task);
+	u32 fd __aligned(8);
+	__bpf_md_ptr(struct file *, file);
+};
+
+DEFINE_BPF_ITER_FUNC(task_file, struct bpf_iter_meta *meta,
+		     struct task_struct *task, u32 fd,
+		     struct file *file)
+
+static int __task_file_seq_show(struct seq_file *seq, struct file *file,
+				bool in_stop)
+{
+	struct bpf_iter_seq_task_file_info *info = seq->private;
+	struct bpf_iter__task_file ctx;
+	struct bpf_iter_meta meta;
+	struct bpf_prog *prog;
+
+	meta.seq = seq;
+	prog = bpf_iter_get_info(&meta, in_stop);
+	if (!prog)
+		return 0;
+
+	ctx.meta = &meta;
+	ctx.task = info->task;
+	ctx.fd = info->fd;
+	ctx.file = file;
+	return bpf_iter_run_prog(prog, &ctx);
+}
+
+static int task_file_seq_show(struct seq_file *seq, void *v)
+{
+	return __task_file_seq_show(seq, v, false);
+}
+
+static void task_file_seq_stop(struct seq_file *seq, void *v)
+{
+	struct bpf_iter_seq_task_file_info *info = seq->private;
+
+	if (!v) {
+		(void)__task_file_seq_show(seq, v, true);
+	} else {
+		fput((struct file *)v);
+		put_files_struct(info->files);
+		put_task_struct(info->task);
+		info->files = NULL;
+		info->task = NULL;
+	}
+}
+
+static int init_seq_pidns(void *priv_data, struct bpf_iter_aux_info *aux)
+{
+	struct bpf_iter_seq_task_common *common = priv_data;
+
+	common->ns = get_pid_ns(task_active_pid_ns(current));
+	return 0;
+}
+
+static void fini_seq_pidns(void *priv_data)
+{
+	struct bpf_iter_seq_task_common *common = priv_data;
+
+	put_pid_ns(common->ns);
+}
+
+static const struct seq_operations task_file_seq_ops = {
+	.start	= task_file_seq_start,
+	.next	= task_file_seq_next,
+	.stop	= task_file_seq_stop,
+	.show	= task_file_seq_show,
+};
+
+BTF_ID_LIST(btf_task_file_ids)
+BTF_ID(struct, task_struct)
+BTF_ID(struct, file)
+
+static const struct bpf_iter_seq_info task_seq_info = {
+	.seq_ops		= &task_seq_ops,
+	.init_seq_private	= init_seq_pidns,
+	.fini_seq_private	= fini_seq_pidns,
+	.seq_priv_size		= sizeof(struct bpf_iter_seq_task_info),
+};
+
+static struct bpf_iter_reg task_reg_info = {
+	.target			= "task",
+	.ctx_arg_info_size	= 1,
+	.ctx_arg_info		= {
+		{ offsetof(struct bpf_iter__task, task),
+		  PTR_TO_BTF_ID_OR_NULL },
+	},
+	.seq_info		= &task_seq_info,
+};
+
+static const struct bpf_iter_seq_info task_file_seq_info = {
+	.seq_ops		= &task_file_seq_ops,
+	.init_seq_private	= init_seq_pidns,
+	.fini_seq_private	= fini_seq_pidns,
+	.seq_priv_size		= sizeof(struct bpf_iter_seq_task_file_info),
+};
+
+static struct bpf_iter_reg task_file_reg_info = {
+	.target			= "task_file",
+	.ctx_arg_info_size	= 2,
+	.ctx_arg_info		= {
+		{ offsetof(struct bpf_iter__task_file, task),
+		  PTR_TO_BTF_ID_OR_NULL },
+		{ offsetof(struct bpf_iter__task_file, file),
+		  PTR_TO_BTF_ID_OR_NULL },
+	},
+	.seq_info		= &task_file_seq_info,
+};
+
+static int __init task_iter_init(void)
+{
+	int ret;
+
+	task_reg_info.ctx_arg_info[0].btf_id = btf_task_file_ids[0];
+	ret = bpf_iter_reg_target(&task_reg_info);
+	if (ret)
+		return ret;
+
+	task_file_reg_info.ctx_arg_info[0].btf_id = btf_task_file_ids[0];
+	task_file_reg_info.ctx_arg_info[1].btf_id = btf_task_file_ids[1];
+	return bpf_iter_reg_target(&task_file_reg_info);
+}
+late_initcall(task_iter_init);
diff --git a/kernel/bpf/tnum.c b/kernel/bpf/tnum.c
index d4f335a9a899..ceac5281bd31 100644
--- a/kernel/bpf/tnum.c
+++ b/kernel/bpf/tnum.c
@@ -194,3 +194,18 @@ int tnum_sbin(char *str, size_t size, struct tnum a)
 	str[min(size - 1, (size_t)64)] = 0;
 	return 64;
 }
+
+struct tnum tnum_subreg(struct tnum a)
+{
+	return tnum_cast(a, 4);
+}
+
+struct tnum tnum_clear_subreg(struct tnum a)
+{
+	return tnum_lshift(tnum_rshift(a, 32), 32);
+}
+
+struct tnum tnum_const_subreg(struct tnum a, u32 value)
+{
+	return tnum_or(tnum_clear_subreg(a), tnum_const(value));
+}
diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c
index 6b264a92064b..9be85aa4ec5f 100644
--- a/kernel/bpf/trampoline.c
+++ b/kernel/bpf/trampoline.c
@@ -5,6 +5,8 @@
 #include <linux/filter.h>
 #include <linux/ftrace.h>
 #include <linux/rbtree_latch.h>
+#include <linux/perf_event.h>
+#include <linux/btf.h>
 
 /* dummy _ops. The verifier will operate on target program's ops. */
 const struct bpf_verifier_ops bpf_extension_verifier_ops = {
@@ -17,12 +19,11 @@ const struct bpf_prog_ops bpf_extension_prog_ops = {
 #define TRAMPOLINE_TABLE_SIZE (1 << TRAMPOLINE_HASH_BITS)
 
 static struct hlist_head trampoline_table[TRAMPOLINE_TABLE_SIZE];
-static struct latch_tree_root image_tree __cacheline_aligned;
 
-/* serializes access to trampoline_table and image_tree */
+/* serializes access to trampoline_table */
 static DEFINE_MUTEX(trampoline_mutex);
 
-static void *bpf_jit_alloc_exec_page(void)
+void *bpf_jit_alloc_exec_page(void)
 {
 	void *image;
 
@@ -38,62 +39,28 @@ static void *bpf_jit_alloc_exec_page(void)
 	return image;
 }
 
-static __always_inline bool image_tree_less(struct latch_tree_node *a,
-				      struct latch_tree_node *b)
+void bpf_image_ksym_add(void *data, struct bpf_ksym *ksym)
 {
-	struct bpf_image *ia = container_of(a, struct bpf_image, tnode);
-	struct bpf_image *ib = container_of(b, struct bpf_image, tnode);
-
-	return ia < ib;
-}
-
-static __always_inline int image_tree_comp(void *addr, struct latch_tree_node *n)
-{
-	void *image = container_of(n, struct bpf_image, tnode);
-
-	if (addr < image)
-		return -1;
-	if (addr >= image + PAGE_SIZE)
-		return 1;
-
-	return 0;
-}
-
-static const struct latch_tree_ops image_tree_ops = {
-	.less	= image_tree_less,
-	.comp	= image_tree_comp,
-};
-
-static void *__bpf_image_alloc(bool lock)
-{
-	struct bpf_image *image;
-
-	image = bpf_jit_alloc_exec_page();
-	if (!image)
-		return NULL;
-
-	if (lock)
-		mutex_lock(&trampoline_mutex);
-	latch_tree_insert(&image->tnode, &image_tree, &image_tree_ops);
-	if (lock)
-		mutex_unlock(&trampoline_mutex);
-	return image->data;
+	ksym->start = (unsigned long) data;
+	ksym->end = ksym->start + PAGE_SIZE;
+	bpf_ksym_add(ksym);
+	perf_event_ksymbol(PERF_RECORD_KSYMBOL_TYPE_BPF, ksym->start,
+			   PAGE_SIZE, false, ksym->name);
 }
 
-void *bpf_image_alloc(void)
+void bpf_image_ksym_del(struct bpf_ksym *ksym)
 {
-	return __bpf_image_alloc(true);
+	bpf_ksym_del(ksym);
+	perf_event_ksymbol(PERF_RECORD_KSYMBOL_TYPE_BPF, ksym->start,
+			   PAGE_SIZE, true, ksym->name);
 }
 
-bool is_bpf_image_address(unsigned long addr)
+static void bpf_trampoline_ksym_add(struct bpf_trampoline *tr)
 {
-	bool ret;
-
-	rcu_read_lock();
-	ret = latch_tree_find((void *) addr, &image_tree, &image_tree_ops) != NULL;
-	rcu_read_unlock();
+	struct bpf_ksym *ksym = &tr->ksym;
 
-	return ret;
+	snprintf(ksym->name, KSYM_NAME_LEN, "bpf_trampoline_%llu", tr->key);
+	bpf_image_ksym_add(tr->image, ksym);
 }
 
 struct bpf_trampoline *bpf_trampoline_lookup(u64 key)
@@ -116,7 +83,7 @@ struct bpf_trampoline *bpf_trampoline_lookup(u64 key)
 		goto out;
 
 	/* is_root was checked earlier. No need for bpf_jit_charge_modmem() */
-	image = __bpf_image_alloc(false);
+	image = bpf_jit_alloc_exec_page();
 	if (!image) {
 		kfree(tr);
 		tr = NULL;
@@ -131,6 +98,8 @@ struct bpf_trampoline *bpf_trampoline_lookup(u64 key)
 	for (i = 0; i < BPF_TRAMP_MAX; i++)
 		INIT_HLIST_HEAD(&tr->progs_hlist[i]);
 	tr->image = image;
+	INIT_LIST_HEAD_RCU(&tr->ksym.lnode);
+	bpf_trampoline_ksym_add(tr);
 out:
 	mutex_unlock(&trampoline_mutex);
 	return tr;
@@ -190,40 +159,50 @@ static int register_fentry(struct bpf_trampoline *tr, void *new_addr)
 	return ret;
 }
 
-/* Each call __bpf_prog_enter + call bpf_func + call __bpf_prog_exit is ~50
- * bytes on x86.  Pick a number to fit into BPF_IMAGE_SIZE / 2
- */
-#define BPF_MAX_TRAMP_PROGS 40
+static struct bpf_tramp_progs *
+bpf_trampoline_get_progs(const struct bpf_trampoline *tr, int *total)
+{
+	const struct bpf_prog_aux *aux;
+	struct bpf_tramp_progs *tprogs;
+	struct bpf_prog **progs;
+	int kind;
+
+	*total = 0;
+	tprogs = kcalloc(BPF_TRAMP_MAX, sizeof(*tprogs), GFP_KERNEL);
+	if (!tprogs)
+		return ERR_PTR(-ENOMEM);
+
+	for (kind = 0; kind < BPF_TRAMP_MAX; kind++) {
+		tprogs[kind].nr_progs = tr->progs_cnt[kind];
+		*total += tr->progs_cnt[kind];
+		progs = tprogs[kind].progs;
+
+		hlist_for_each_entry(aux, &tr->progs_hlist[kind], tramp_hlist)
+			*progs++ = aux->prog;
+	}
+	return tprogs;
+}
 
 static int bpf_trampoline_update(struct bpf_trampoline *tr)
 {
-	void *old_image = tr->image + ((tr->selector + 1) & 1) * BPF_IMAGE_SIZE/2;
-	void *new_image = tr->image + (tr->selector & 1) * BPF_IMAGE_SIZE/2;
-	struct bpf_prog *progs_to_run[BPF_MAX_TRAMP_PROGS];
-	int fentry_cnt = tr->progs_cnt[BPF_TRAMP_FENTRY];
-	int fexit_cnt = tr->progs_cnt[BPF_TRAMP_FEXIT];
-	struct bpf_prog **progs, **fentry, **fexit;
+	void *old_image = tr->image + ((tr->selector + 1) & 1) * PAGE_SIZE/2;
+	void *new_image = tr->image + (tr->selector & 1) * PAGE_SIZE/2;
+	struct bpf_tramp_progs *tprogs;
 	u32 flags = BPF_TRAMP_F_RESTORE_REGS;
-	struct bpf_prog_aux *aux;
-	int err;
+	int err, total;
+
+	tprogs = bpf_trampoline_get_progs(tr, &total);
+	if (IS_ERR(tprogs))
+		return PTR_ERR(tprogs);
 
-	if (fentry_cnt + fexit_cnt == 0) {
+	if (total == 0) {
 		err = unregister_fentry(tr, old_image);
 		tr->selector = 0;
 		goto out;
 	}
 
-	/* populate fentry progs */
-	fentry = progs = progs_to_run;
-	hlist_for_each_entry(aux, &tr->progs_hlist[BPF_TRAMP_FENTRY], tramp_hlist)
-		*progs++ = aux->prog;
-
-	/* populate fexit progs */
-	fexit = progs;
-	hlist_for_each_entry(aux, &tr->progs_hlist[BPF_TRAMP_FEXIT], tramp_hlist)
-		*progs++ = aux->prog;
-
-	if (fexit_cnt)
+	if (tprogs[BPF_TRAMP_FEXIT].nr_progs ||
+	    tprogs[BPF_TRAMP_MODIFY_RETURN].nr_progs)
 		flags = BPF_TRAMP_F_CALL_ORIG | BPF_TRAMP_F_SKIP_FRAME;
 
 	/* Though the second half of trampoline page is unused a task could be
@@ -232,12 +211,11 @@ static int bpf_trampoline_update(struct bpf_trampoline *tr)
 	 * preempted task. Hence wait for tasks to voluntarily schedule or go
 	 * to userspace.
 	 */
+
 	synchronize_rcu_tasks();
 
-	err = arch_prepare_bpf_trampoline(new_image, new_image + BPF_IMAGE_SIZE / 2,
-					  &tr->func.model, flags,
-					  fentry, fentry_cnt,
-					  fexit, fexit_cnt,
+	err = arch_prepare_bpf_trampoline(new_image, new_image + PAGE_SIZE / 2,
+					  &tr->func.model, flags, tprogs,
 					  tr->func.addr);
 	if (err < 0)
 		goto out;
@@ -252,16 +230,27 @@ static int bpf_trampoline_update(struct bpf_trampoline *tr)
 		goto out;
 	tr->selector++;
 out:
+	kfree(tprogs);
 	return err;
 }
 
-static enum bpf_tramp_prog_type bpf_attach_type_to_tramp(enum bpf_attach_type t)
+static enum bpf_tramp_prog_type bpf_attach_type_to_tramp(struct bpf_prog *prog)
 {
-	switch (t) {
+	switch (prog->expected_attach_type) {
 	case BPF_TRACE_FENTRY:
 		return BPF_TRAMP_FENTRY;
+	case BPF_MODIFY_RETURN:
+		return BPF_TRAMP_MODIFY_RETURN;
 	case BPF_TRACE_FEXIT:
 		return BPF_TRAMP_FEXIT;
+	case BPF_LSM_MAC:
+		if (!prog->aux->attach_func_proto->type)
+			/* The function returns void, we cannot modify its
+			 * return value.
+			 */
+			return BPF_TRAMP_FEXIT;
+		else
+			return BPF_TRAMP_MODIFY_RETURN;
 	default:
 		return BPF_TRAMP_REPLACE;
 	}
@@ -275,7 +264,7 @@ int bpf_trampoline_link_prog(struct bpf_prog *prog)
 	int cnt;
 
 	tr = prog->aux->trampoline;
-	kind = bpf_attach_type_to_tramp(prog->expected_attach_type);
+	kind = bpf_attach_type_to_tramp(prog);
 	mutex_lock(&tr->mutex);
 	if (tr->extension_prog) {
 		/* cannot attach fentry/fexit if extension prog is attached.
@@ -325,7 +314,7 @@ int bpf_trampoline_unlink_prog(struct bpf_prog *prog)
 	int err;
 
 	tr = prog->aux->trampoline;
-	kind = bpf_attach_type_to_tramp(prog->expected_attach_type);
+	kind = bpf_attach_type_to_tramp(prog);
 	mutex_lock(&tr->mutex);
 	if (kind == BPF_TRAMP_REPLACE) {
 		WARN_ON_ONCE(!tr->extension_prog);
@@ -344,8 +333,6 @@ out:
 
 void bpf_trampoline_put(struct bpf_trampoline *tr)
 {
-	struct bpf_image *image;
-
 	if (!tr)
 		return;
 	mutex_lock(&trampoline_mutex);
@@ -356,35 +343,37 @@ void bpf_trampoline_put(struct bpf_trampoline *tr)
 		goto out;
 	if (WARN_ON_ONCE(!hlist_empty(&tr->progs_hlist[BPF_TRAMP_FEXIT])))
 		goto out;
-	image = container_of(tr->image, struct bpf_image, data);
-	latch_tree_erase(&image->tnode, &image_tree, &image_tree_ops);
+	bpf_image_ksym_del(&tr->ksym);
 	/* wait for tasks to get out of trampoline before freeing it */
 	synchronize_rcu_tasks();
-	bpf_jit_free_exec(image);
+	bpf_jit_free_exec(tr->image);
 	hlist_del(&tr->hlist);
 	kfree(tr);
 out:
 	mutex_unlock(&trampoline_mutex);
 }
 
-/* The logic is similar to BPF_PROG_RUN, but with explicit rcu and preempt that
- * are needed for trampoline. The macro is split into
+/* The logic is similar to BPF_PROG_RUN, but with an explicit
+ * rcu_read_lock() and migrate_disable() which are required
+ * for the trampoline. The macro is split into
  * call _bpf_prog_enter
  * call prog->bpf_func
  * call __bpf_prog_exit
  */
 u64 notrace __bpf_prog_enter(void)
+	__acquires(RCU)
 {
 	u64 start = 0;
 
 	rcu_read_lock();
-	preempt_disable();
+	migrate_disable();
 	if (static_branch_unlikely(&bpf_stats_enabled_key))
 		start = sched_clock();
 	return start;
 }
 
 void notrace __bpf_prog_exit(struct bpf_prog *prog, u64 start)
+	__releases(RCU)
 {
 	struct bpf_prog_stats *stats;
 
@@ -401,15 +390,14 @@ void notrace __bpf_prog_exit(struct bpf_prog *prog, u64 start)
 		stats->nsecs += sched_clock() - start;
 		u64_stats_update_end(&stats->syncp);
 	}
-	preempt_enable();
+	migrate_enable();
 	rcu_read_unlock();
 }
 
 int __weak
 arch_prepare_bpf_trampoline(void *image, void *image_end,
 			    const struct btf_func_model *m, u32 flags,
-			    struct bpf_prog **fentry_progs, int fentry_cnt,
-			    struct bpf_prog **fexit_progs, int fexit_cnt,
+			    struct bpf_tramp_progs *tprogs,
 			    void *orig_call)
 {
 	return -ENOTSUPP;
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 1cc945daa9c8..47e74f09fa37 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -19,6 +19,8 @@
 #include <linux/sort.h>
 #include <linux/perf_event.h>
 #include <linux/ctype.h>
+#include <linux/error-injection.h>
+#include <linux/bpf_lsm.h>
 
 #include "disasm.h"
 
@@ -26,9 +28,11 @@ static const struct bpf_verifier_ops * const bpf_verifier_ops[] = {
 #define BPF_PROG_TYPE(_id, _name, prog_ctx_type, kern_ctx_type) \
 	[_id] = & _name ## _verifier_ops,
 #define BPF_MAP_TYPE(_id, _ops)
+#define BPF_LINK_TYPE(_id, _name)
 #include <linux/bpf_types.h>
 #undef BPF_PROG_TYPE
 #undef BPF_MAP_TYPE
+#undef BPF_LINK_TYPE
 };
 
 /* bpf_check() is a static code analyzer that walks eBPF program
@@ -166,6 +170,8 @@ struct bpf_verifier_stack_elem {
 	int insn_idx;
 	int prev_insn_idx;
 	struct bpf_verifier_stack_elem *next;
+	/* length of verifier log at the time this state was pushed on stack */
+	u32 log_pos;
 };
 
 #define BPF_COMPLEXITY_LIMIT_JMP_SEQ	8192
@@ -227,8 +233,8 @@ struct bpf_call_arg_meta {
 	bool pkt_access;
 	int regno;
 	int access_size;
-	s64 msize_smax_value;
-	u64 msize_umax_value;
+	int mem_size;
+	u64 msize_max_value;
 	int ref_obj_id;
 	int func_id;
 	u32 btf_id;
@@ -282,6 +288,18 @@ void bpf_verifier_vlog(struct bpf_verifier_log *log, const char *fmt,
 		log->ubuf = NULL;
 }
 
+static void bpf_vlog_reset(struct bpf_verifier_log *log, u32 new_pos)
+{
+	char zero = 0;
+
+	if (!bpf_verifier_log_needed(log))
+		return;
+
+	log->len_used = new_pos;
+	if (put_user(zero, log->ubuf + new_pos))
+		log->ubuf = NULL;
+}
+
 /* log_level controls verbosity level of eBPF verifier.
  * bpf_verifier_log_write() is used to dump the verification trace to the log,
  * so the user can figure out what's wrong with the program
@@ -376,12 +394,24 @@ static bool type_is_sk_pointer(enum bpf_reg_type type)
 		type == PTR_TO_XDP_SOCK;
 }
 
+static bool reg_type_not_null(enum bpf_reg_type type)
+{
+	return type == PTR_TO_SOCKET ||
+		type == PTR_TO_TCP_SOCK ||
+		type == PTR_TO_MAP_VALUE ||
+		type == PTR_TO_SOCK_COMMON;
+}
+
 static bool reg_type_may_be_null(enum bpf_reg_type type)
 {
 	return type == PTR_TO_MAP_VALUE_OR_NULL ||
 	       type == PTR_TO_SOCKET_OR_NULL ||
 	       type == PTR_TO_SOCK_COMMON_OR_NULL ||
-	       type == PTR_TO_TCP_SOCK_OR_NULL;
+	       type == PTR_TO_TCP_SOCK_OR_NULL ||
+	       type == PTR_TO_BTF_ID_OR_NULL ||
+	       type == PTR_TO_MEM_OR_NULL ||
+	       type == PTR_TO_RDONLY_BUF_OR_NULL ||
+	       type == PTR_TO_RDWR_BUF_OR_NULL;
 }
 
 static bool reg_may_point_to_spin_lock(const struct bpf_reg_state *reg)
@@ -395,7 +425,9 @@ static bool reg_type_may_be_refcounted_or_null(enum bpf_reg_type type)
 	return type == PTR_TO_SOCKET ||
 		type == PTR_TO_SOCKET_OR_NULL ||
 		type == PTR_TO_TCP_SOCK ||
-		type == PTR_TO_TCP_SOCK_OR_NULL;
+		type == PTR_TO_TCP_SOCK_OR_NULL ||
+		type == PTR_TO_MEM ||
+		type == PTR_TO_MEM_OR_NULL;
 }
 
 static bool arg_type_may_be_refcounted(enum bpf_arg_type type)
@@ -409,14 +441,37 @@ static bool arg_type_may_be_refcounted(enum bpf_arg_type type)
  */
 static bool is_release_function(enum bpf_func_id func_id)
 {
-	return func_id == BPF_FUNC_sk_release;
+	return func_id == BPF_FUNC_sk_release ||
+	       func_id == BPF_FUNC_ringbuf_submit ||
+	       func_id == BPF_FUNC_ringbuf_discard;
 }
 
-static bool is_acquire_function(enum bpf_func_id func_id)
+static bool may_be_acquire_function(enum bpf_func_id func_id)
 {
 	return func_id == BPF_FUNC_sk_lookup_tcp ||
 		func_id == BPF_FUNC_sk_lookup_udp ||
-		func_id == BPF_FUNC_skc_lookup_tcp;
+		func_id == BPF_FUNC_skc_lookup_tcp ||
+		func_id == BPF_FUNC_map_lookup_elem ||
+	        func_id == BPF_FUNC_ringbuf_reserve;
+}
+
+static bool is_acquire_function(enum bpf_func_id func_id,
+				const struct bpf_map *map)
+{
+	enum bpf_map_type map_type = map ? map->map_type : BPF_MAP_TYPE_UNSPEC;
+
+	if (func_id == BPF_FUNC_sk_lookup_tcp ||
+	    func_id == BPF_FUNC_sk_lookup_udp ||
+	    func_id == BPF_FUNC_skc_lookup_tcp ||
+	    func_id == BPF_FUNC_ringbuf_reserve)
+		return true;
+
+	if (func_id == BPF_FUNC_map_lookup_elem &&
+	    (map_type == BPF_MAP_TYPE_SOCKMAP ||
+	     map_type == BPF_MAP_TYPE_SOCKHASH))
+		return true;
+
+	return false;
 }
 
 static bool is_ptr_cast_function(enum bpf_func_id func_id)
@@ -447,6 +502,13 @@ static const char * const reg_type_str[] = {
 	[PTR_TO_TP_BUFFER]	= "tp_buffer",
 	[PTR_TO_XDP_SOCK]	= "xdp_sock",
 	[PTR_TO_BTF_ID]		= "ptr_",
+	[PTR_TO_BTF_ID_OR_NULL]	= "ptr_or_null_",
+	[PTR_TO_MEM]		= "mem",
+	[PTR_TO_MEM_OR_NULL]	= "mem_or_null",
+	[PTR_TO_RDONLY_BUF]	= "rdonly_buf",
+	[PTR_TO_RDONLY_BUF_OR_NULL] = "rdonly_buf_or_null",
+	[PTR_TO_RDWR_BUF]	= "rdwr_buf",
+	[PTR_TO_RDWR_BUF_OR_NULL] = "rdwr_buf_or_null",
 };
 
 static char slot_type_char[] = {
@@ -507,7 +569,7 @@ static void print_verifier_state(struct bpf_verifier_env *env,
 			/* reg->off should be 0 for SCALAR_VALUE */
 			verbose(env, "%lld", reg->var_off.value + reg->off);
 		} else {
-			if (t == PTR_TO_BTF_ID)
+			if (t == PTR_TO_BTF_ID || t == PTR_TO_BTF_ID_OR_NULL)
 				verbose(env, "%s", kernel_type_name(reg->btf_id));
 			verbose(env, "(id=%d", reg->id);
 			if (reg_type_may_be_refcounted_or_null(t))
@@ -549,6 +611,22 @@ static void print_verifier_state(struct bpf_verifier_env *env,
 					tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
 					verbose(env, ",var_off=%s", tn_buf);
 				}
+				if (reg->s32_min_value != reg->smin_value &&
+				    reg->s32_min_value != S32_MIN)
+					verbose(env, ",s32_min_value=%d",
+						(int)(reg->s32_min_value));
+				if (reg->s32_max_value != reg->smax_value &&
+				    reg->s32_max_value != S32_MAX)
+					verbose(env, ",s32_max_value=%d",
+						(int)(reg->s32_max_value));
+				if (reg->u32_min_value != reg->umin_value &&
+				    reg->u32_min_value != U32_MIN)
+					verbose(env, ",u32_min_value=%d",
+						(int)(reg->u32_min_value));
+				if (reg->u32_max_value != reg->umax_value &&
+				    reg->u32_max_value != U32_MAX)
+					verbose(env, ",u32_max_value=%d",
+						(int)(reg->u32_max_value));
 			}
 			verbose(env, ")");
 		}
@@ -829,7 +907,7 @@ static void update_branch_counts(struct bpf_verifier_env *env, struct bpf_verifi
 }
 
 static int pop_stack(struct bpf_verifier_env *env, int *prev_insn_idx,
-		     int *insn_idx)
+		     int *insn_idx, bool pop_log)
 {
 	struct bpf_verifier_state *cur = env->cur_state;
 	struct bpf_verifier_stack_elem *elem, *head = env->head;
@@ -843,6 +921,8 @@ static int pop_stack(struct bpf_verifier_env *env, int *prev_insn_idx,
 		if (err)
 			return err;
 	}
+	if (pop_log)
+		bpf_vlog_reset(&env->log, head->log_pos);
 	if (insn_idx)
 		*insn_idx = head->insn_idx;
 	if (prev_insn_idx)
@@ -870,6 +950,7 @@ static struct bpf_verifier_state *push_stack(struct bpf_verifier_env *env,
 	elem->insn_idx = insn_idx;
 	elem->prev_insn_idx = prev_insn_idx;
 	elem->next = env->head;
+	elem->log_pos = env->log.len_used;
 	env->head = elem;
 	env->stack_size++;
 	err = copy_verifier_state(&elem->st, cur);
@@ -898,7 +979,7 @@ err:
 	free_verifier_state(env->cur_state, true);
 	env->cur_state = NULL;
 	/* pop all elements and return */
-	while (!pop_stack(env, NULL, NULL));
+	while (!pop_stack(env, NULL, NULL, false));
 	return NULL;
 }
 
@@ -923,6 +1004,20 @@ static void __mark_reg_known(struct bpf_reg_state *reg, u64 imm)
 	reg->smax_value = (s64)imm;
 	reg->umin_value = imm;
 	reg->umax_value = imm;
+
+	reg->s32_min_value = (s32)imm;
+	reg->s32_max_value = (s32)imm;
+	reg->u32_min_value = (u32)imm;
+	reg->u32_max_value = (u32)imm;
+}
+
+static void __mark_reg32_known(struct bpf_reg_state *reg, u64 imm)
+{
+	reg->var_off = tnum_const_subreg(reg->var_off, imm);
+	reg->s32_min_value = (s32)imm;
+	reg->s32_max_value = (s32)imm;
+	reg->u32_min_value = (u32)imm;
+	reg->u32_max_value = (u32)imm;
 }
 
 /* Mark the 'variable offset' part of a register as zero.  This should be
@@ -977,8 +1072,52 @@ static bool reg_is_init_pkt_pointer(const struct bpf_reg_state *reg,
 	       tnum_equals_const(reg->var_off, 0);
 }
 
-/* Attempts to improve min/max values based on var_off information */
-static void __update_reg_bounds(struct bpf_reg_state *reg)
+/* Reset the min/max bounds of a register */
+static void __mark_reg_unbounded(struct bpf_reg_state *reg)
+{
+	reg->smin_value = S64_MIN;
+	reg->smax_value = S64_MAX;
+	reg->umin_value = 0;
+	reg->umax_value = U64_MAX;
+
+	reg->s32_min_value = S32_MIN;
+	reg->s32_max_value = S32_MAX;
+	reg->u32_min_value = 0;
+	reg->u32_max_value = U32_MAX;
+}
+
+static void __mark_reg64_unbounded(struct bpf_reg_state *reg)
+{
+	reg->smin_value = S64_MIN;
+	reg->smax_value = S64_MAX;
+	reg->umin_value = 0;
+	reg->umax_value = U64_MAX;
+}
+
+static void __mark_reg32_unbounded(struct bpf_reg_state *reg)
+{
+	reg->s32_min_value = S32_MIN;
+	reg->s32_max_value = S32_MAX;
+	reg->u32_min_value = 0;
+	reg->u32_max_value = U32_MAX;
+}
+
+static void __update_reg32_bounds(struct bpf_reg_state *reg)
+{
+	struct tnum var32_off = tnum_subreg(reg->var_off);
+
+	/* min signed is max(sign bit) | min(other bits) */
+	reg->s32_min_value = max_t(s32, reg->s32_min_value,
+			var32_off.value | (var32_off.mask & S32_MIN));
+	/* max signed is min(sign bit) | max(other bits) */
+	reg->s32_max_value = min_t(s32, reg->s32_max_value,
+			var32_off.value | (var32_off.mask & S32_MAX));
+	reg->u32_min_value = max_t(u32, reg->u32_min_value, (u32)var32_off.value);
+	reg->u32_max_value = min(reg->u32_max_value,
+				 (u32)(var32_off.value | var32_off.mask));
+}
+
+static void __update_reg64_bounds(struct bpf_reg_state *reg)
 {
 	/* min signed is max(sign bit) | min(other bits) */
 	reg->smin_value = max_t(s64, reg->smin_value,
@@ -991,8 +1130,48 @@ static void __update_reg_bounds(struct bpf_reg_state *reg)
 			      reg->var_off.value | reg->var_off.mask);
 }
 
+static void __update_reg_bounds(struct bpf_reg_state *reg)
+{
+	__update_reg32_bounds(reg);
+	__update_reg64_bounds(reg);
+}
+
 /* Uses signed min/max values to inform unsigned, and vice-versa */
-static void __reg_deduce_bounds(struct bpf_reg_state *reg)
+static void __reg32_deduce_bounds(struct bpf_reg_state *reg)
+{
+	/* Learn sign from signed bounds.
+	 * If we cannot cross the sign boundary, then signed and unsigned bounds
+	 * are the same, so combine.  This works even in the negative case, e.g.
+	 * -3 s<= x s<= -1 implies 0xf...fd u<= x u<= 0xf...ff.
+	 */
+	if (reg->s32_min_value >= 0 || reg->s32_max_value < 0) {
+		reg->s32_min_value = reg->u32_min_value =
+			max_t(u32, reg->s32_min_value, reg->u32_min_value);
+		reg->s32_max_value = reg->u32_max_value =
+			min_t(u32, reg->s32_max_value, reg->u32_max_value);
+		return;
+	}
+	/* Learn sign from unsigned bounds.  Signed bounds cross the sign
+	 * boundary, so we must be careful.
+	 */
+	if ((s32)reg->u32_max_value >= 0) {
+		/* Positive.  We can't learn anything from the smin, but smax
+		 * is positive, hence safe.
+		 */
+		reg->s32_min_value = reg->u32_min_value;
+		reg->s32_max_value = reg->u32_max_value =
+			min_t(u32, reg->s32_max_value, reg->u32_max_value);
+	} else if ((s32)reg->u32_min_value < 0) {
+		/* Negative.  We can't learn anything from the smax, but smin
+		 * is negative, hence safe.
+		 */
+		reg->s32_min_value = reg->u32_min_value =
+			max_t(u32, reg->s32_min_value, reg->u32_min_value);
+		reg->s32_max_value = reg->u32_max_value;
+	}
+}
+
+static void __reg64_deduce_bounds(struct bpf_reg_state *reg)
 {
 	/* Learn sign from signed bounds.
 	 * If we cannot cross the sign boundary, then signed and unsigned bounds
@@ -1026,32 +1205,106 @@ static void __reg_deduce_bounds(struct bpf_reg_state *reg)
 	}
 }
 
+static void __reg_deduce_bounds(struct bpf_reg_state *reg)
+{
+	__reg32_deduce_bounds(reg);
+	__reg64_deduce_bounds(reg);
+}
+
 /* Attempts to improve var_off based on unsigned min/max information */
 static void __reg_bound_offset(struct bpf_reg_state *reg)
 {
-	reg->var_off = tnum_intersect(reg->var_off,
-				      tnum_range(reg->umin_value,
-						 reg->umax_value));
+	struct tnum var64_off = tnum_intersect(reg->var_off,
+					       tnum_range(reg->umin_value,
+							  reg->umax_value));
+	struct tnum var32_off = tnum_intersect(tnum_subreg(reg->var_off),
+						tnum_range(reg->u32_min_value,
+							   reg->u32_max_value));
+
+	reg->var_off = tnum_or(tnum_clear_subreg(var64_off), var32_off);
 }
 
-static void __reg_bound_offset32(struct bpf_reg_state *reg)
+static void __reg_assign_32_into_64(struct bpf_reg_state *reg)
 {
-	u64 mask = 0xffffFFFF;
-	struct tnum range = tnum_range(reg->umin_value & mask,
-				       reg->umax_value & mask);
-	struct tnum lo32 = tnum_cast(reg->var_off, 4);
-	struct tnum hi32 = tnum_lshift(tnum_rshift(reg->var_off, 32), 32);
+	reg->umin_value = reg->u32_min_value;
+	reg->umax_value = reg->u32_max_value;
+	/* Attempt to pull 32-bit signed bounds into 64-bit bounds
+	 * but must be positive otherwise set to worse case bounds
+	 * and refine later from tnum.
+	 */
+	if (reg->s32_min_value >= 0 && reg->s32_max_value >= 0)
+		reg->smax_value = reg->s32_max_value;
+	else
+		reg->smax_value = U32_MAX;
+	if (reg->s32_min_value >= 0)
+		reg->smin_value = reg->s32_min_value;
+	else
+		reg->smin_value = 0;
+}
 
-	reg->var_off = tnum_or(hi32, tnum_intersect(lo32, range));
+static void __reg_combine_32_into_64(struct bpf_reg_state *reg)
+{
+	/* special case when 64-bit register has upper 32-bit register
+	 * zeroed. Typically happens after zext or <<32, >>32 sequence
+	 * allowing us to use 32-bit bounds directly,
+	 */
+	if (tnum_equals_const(tnum_clear_subreg(reg->var_off), 0)) {
+		__reg_assign_32_into_64(reg);
+	} else {
+		/* Otherwise the best we can do is push lower 32bit known and
+		 * unknown bits into register (var_off set from jmp logic)
+		 * then learn as much as possible from the 64-bit tnum
+		 * known and unknown bits. The previous smin/smax bounds are
+		 * invalid here because of jmp32 compare so mark them unknown
+		 * so they do not impact tnum bounds calculation.
+		 */
+		__mark_reg64_unbounded(reg);
+		__update_reg_bounds(reg);
+	}
+
+	/* Intersecting with the old var_off might have improved our bounds
+	 * slightly.  e.g. if umax was 0x7f...f and var_off was (0; 0xf...fc),
+	 * then new var_off is (0; 0x7f...fc) which improves our umax.
+	 */
+	__reg_deduce_bounds(reg);
+	__reg_bound_offset(reg);
+	__update_reg_bounds(reg);
 }
 
-/* Reset the min/max bounds of a register */
-static void __mark_reg_unbounded(struct bpf_reg_state *reg)
+static bool __reg64_bound_s32(s64 a)
 {
-	reg->smin_value = S64_MIN;
-	reg->smax_value = S64_MAX;
-	reg->umin_value = 0;
-	reg->umax_value = U64_MAX;
+	if (a > S32_MIN && a < S32_MAX)
+		return true;
+	return false;
+}
+
+static bool __reg64_bound_u32(u64 a)
+{
+	if (a > U32_MIN && a < U32_MAX)
+		return true;
+	return false;
+}
+
+static void __reg_combine_64_into_32(struct bpf_reg_state *reg)
+{
+	__mark_reg32_unbounded(reg);
+
+	if (__reg64_bound_s32(reg->smin_value))
+		reg->s32_min_value = (s32)reg->smin_value;
+	if (__reg64_bound_s32(reg->smax_value))
+		reg->s32_max_value = (s32)reg->smax_value;
+	if (__reg64_bound_u32(reg->umin_value))
+		reg->u32_min_value = (u32)reg->umin_value;
+	if (__reg64_bound_u32(reg->umax_value))
+		reg->u32_max_value = (u32)reg->umax_value;
+
+	/* Intersecting with the old var_off might have improved our bounds
+	 * slightly.  e.g. if umax was 0x7f...f and var_off was (0; 0xf...fc),
+	 * then new var_off is (0; 0x7f...fc) which improves our umax.
+	 */
+	__reg_deduce_bounds(reg);
+	__reg_bound_offset(reg);
+	__update_reg_bounds(reg);
 }
 
 /* Mark a register as having a completely unknown (scalar) value. */
@@ -1066,8 +1319,7 @@ static void __mark_reg_unknown(const struct bpf_verifier_env *env,
 	reg->type = SCALAR_VALUE;
 	reg->var_off = tnum_unknown;
 	reg->frameno = 0;
-	reg->precise = env->subprog_cnt > 1 || !env->allow_ptr_leaks ?
-		       true : false;
+	reg->precise = env->subprog_cnt > 1 || !env->bpf_capable;
 	__mark_reg_unbounded(reg);
 }
 
@@ -1104,6 +1356,19 @@ static void mark_reg_not_init(struct bpf_verifier_env *env,
 	__mark_reg_not_init(env, regs + regno);
 }
 
+static void mark_btf_ld_reg(struct bpf_verifier_env *env,
+			    struct bpf_reg_state *regs, u32 regno,
+			    enum bpf_reg_type reg_type, u32 btf_id)
+{
+	if (reg_type == SCALAR_VALUE) {
+		mark_reg_unknown(env, regs, regno);
+		return;
+	}
+	mark_reg_known_zero(env, regs, regno);
+	regs[regno].type = PTR_TO_BTF_ID;
+	regs[regno].btf_id = btf_id;
+}
+
 #define DEF_NOT_SUBREG	(0)
 static void init_reg_state(struct bpf_verifier_env *env,
 			   struct bpf_func_state *state)
@@ -1199,8 +1464,9 @@ static int check_subprogs(struct bpf_verifier_env *env)
 			continue;
 		if (insn[i].src_reg != BPF_PSEUDO_CALL)
 			continue;
-		if (!env->allow_ptr_leaks) {
-			verbose(env, "function calls to other bpf functions are allowed for root only\n");
+		if (!env->bpf_capable) {
+			verbose(env,
+				"function calls to other bpf functions are allowed for CAP_BPF and CAP_SYS_ADMIN\n");
 			return -EPERM;
 		}
 		ret = add_subprog(env, i + insn[i].imm + 1);
@@ -1734,8 +2000,7 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int regno,
 	bool new_marks = false;
 	int i, err;
 
-	if (!env->allow_ptr_leaks)
-		/* backtracking is root only for now */
+	if (!env->bpf_capable)
 		return 0;
 
 	func = st->frame[st->curframe];
@@ -1913,6 +2178,11 @@ static bool is_spillable_regtype(enum bpf_reg_type type)
 	case PTR_TO_TCP_SOCK_OR_NULL:
 	case PTR_TO_XDP_SOCK:
 	case PTR_TO_BTF_ID:
+	case PTR_TO_BTF_ID_OR_NULL:
+	case PTR_TO_RDONLY_BUF:
+	case PTR_TO_RDONLY_BUF_OR_NULL:
+	case PTR_TO_RDWR_BUF:
+	case PTR_TO_RDWR_BUF_OR_NULL:
 		return true;
 	default:
 		return false;
@@ -1930,6 +2200,15 @@ static bool register_is_const(struct bpf_reg_state *reg)
 	return reg->type == SCALAR_VALUE && tnum_is_const(reg->var_off);
 }
 
+static bool __is_pointer_value(bool allow_ptr_leaks,
+			       const struct bpf_reg_state *reg)
+{
+	if (allow_ptr_leaks)
+		return false;
+
+	return reg->type != SCALAR_VALUE;
+}
+
 static void save_register_state(struct bpf_func_state *state,
 				int spi, struct bpf_reg_state *reg)
 {
@@ -1973,7 +2252,7 @@ static int check_stack_write(struct bpf_verifier_env *env,
 		reg = &cur->regs[value_regno];
 
 	if (reg && size == BPF_REG_SIZE && register_is_const(reg) &&
-	    !register_is_null(reg) && env->allow_ptr_leaks) {
+	    !register_is_null(reg) && env->bpf_capable) {
 		if (dst_reg != BPF_REG_FP) {
 			/* The backtracking logic can only recognize explicit
 			 * stack slot address like [fp - 8]. Other spill of
@@ -1999,7 +2278,7 @@ static int check_stack_write(struct bpf_verifier_env *env,
 			return -EINVAL;
 		}
 
-		if (!env->allow_ptr_leaks) {
+		if (!env->bypass_spec_v4) {
 			bool sanitize = false;
 
 			if (state->stack[spi].slot_type[0] == STACK_SPILL &&
@@ -2120,6 +2399,16 @@ static int check_stack_read(struct bpf_verifier_env *env,
 			 * which resets stack/reg liveness for state transitions
 			 */
 			state->regs[value_regno].live |= REG_LIVE_WRITTEN;
+		} else if (__is_pointer_value(env->allow_ptr_leaks, reg)) {
+			/* If value_regno==-1, the caller is asking us whether
+			 * it is acceptable to use this value as a SCALAR_VALUE
+			 * (e.g. for XADD).
+			 * We must not allow unprivileged callers to do that
+			 * with spilled pointers.
+			 */
+			verbose(env, "leaking pointer from stack off %d\n",
+				off);
+			return -EACCES;
 		}
 		mark_reg_read(env, reg, reg->parent, REG_LIVE_READ64);
 	} else {
@@ -2211,32 +2500,49 @@ static int check_map_access_type(struct bpf_verifier_env *env, u32 regno,
 	return 0;
 }
 
-/* check read/write into map element returned by bpf_map_lookup_elem() */
-static int __check_map_access(struct bpf_verifier_env *env, u32 regno, int off,
-			      int size, bool zero_size_allowed)
+/* check read/write into memory region (e.g., map value, ringbuf sample, etc) */
+static int __check_mem_access(struct bpf_verifier_env *env, int regno,
+			      int off, int size, u32 mem_size,
+			      bool zero_size_allowed)
 {
-	struct bpf_reg_state *regs = cur_regs(env);
-	struct bpf_map *map = regs[regno].map_ptr;
+	bool size_ok = size > 0 || (size == 0 && zero_size_allowed);
+	struct bpf_reg_state *reg;
+
+	if (off >= 0 && size_ok && (u64)off + size <= mem_size)
+		return 0;
 
-	if (off < 0 || size < 0 || (size == 0 && !zero_size_allowed) ||
-	    off + size > map->value_size) {
+	reg = &cur_regs(env)[regno];
+	switch (reg->type) {
+	case PTR_TO_MAP_VALUE:
 		verbose(env, "invalid access to map value, value_size=%d off=%d size=%d\n",
-			map->value_size, off, size);
-		return -EACCES;
+			mem_size, off, size);
+		break;
+	case PTR_TO_PACKET:
+	case PTR_TO_PACKET_META:
+	case PTR_TO_PACKET_END:
+		verbose(env, "invalid access to packet, off=%d size=%d, R%d(id=%d,off=%d,r=%d)\n",
+			off, size, regno, reg->id, off, mem_size);
+		break;
+	case PTR_TO_MEM:
+	default:
+		verbose(env, "invalid access to memory, mem_size=%u off=%d size=%d\n",
+			mem_size, off, size);
 	}
-	return 0;
+
+	return -EACCES;
 }
 
-/* check read/write into a map element with possible variable offset */
-static int check_map_access(struct bpf_verifier_env *env, u32 regno,
-			    int off, int size, bool zero_size_allowed)
+/* check read/write into a memory region with possible variable offset */
+static int check_mem_region_access(struct bpf_verifier_env *env, u32 regno,
+				   int off, int size, u32 mem_size,
+				   bool zero_size_allowed)
 {
 	struct bpf_verifier_state *vstate = env->cur_state;
 	struct bpf_func_state *state = vstate->frame[vstate->curframe];
 	struct bpf_reg_state *reg = &state->regs[regno];
 	int err;
 
-	/* We may have adjusted the register to this map value, so we
+	/* We may have adjusted the register pointing to memory region, so we
 	 * need to try adding each of min_value and max_value to off
 	 * to make sure our theoretical access will be safe.
 	 */
@@ -2257,10 +2563,10 @@ static int check_map_access(struct bpf_verifier_env *env, u32 regno,
 			regno);
 		return -EACCES;
 	}
-	err = __check_map_access(env, regno, reg->smin_value + off, size,
-				 zero_size_allowed);
+	err = __check_mem_access(env, regno, reg->smin_value + off, size,
+				 mem_size, zero_size_allowed);
 	if (err) {
-		verbose(env, "R%d min value is outside of the array range\n",
+		verbose(env, "R%d min value is outside of the allowed memory range\n",
 			regno);
 		return err;
 	}
@@ -2270,18 +2576,38 @@ static int check_map_access(struct bpf_verifier_env *env, u32 regno,
 	 * If reg->umax_value + off could overflow, treat that as unbounded too.
 	 */
 	if (reg->umax_value >= BPF_MAX_VAR_OFF) {
-		verbose(env, "R%d unbounded memory access, make sure to bounds check any array access into a map\n",
+		verbose(env, "R%d unbounded memory access, make sure to bounds check any such access\n",
 			regno);
 		return -EACCES;
 	}
-	err = __check_map_access(env, regno, reg->umax_value + off, size,
-				 zero_size_allowed);
-	if (err)
-		verbose(env, "R%d max value is outside of the array range\n",
+	err = __check_mem_access(env, regno, reg->umax_value + off, size,
+				 mem_size, zero_size_allowed);
+	if (err) {
+		verbose(env, "R%d max value is outside of the allowed memory range\n",
 			regno);
+		return err;
+	}
 
-	if (map_value_has_spin_lock(reg->map_ptr)) {
-		u32 lock = reg->map_ptr->spin_lock_off;
+	return 0;
+}
+
+/* check read/write into a map element with possible variable offset */
+static int check_map_access(struct bpf_verifier_env *env, u32 regno,
+			    int off, int size, bool zero_size_allowed)
+{
+	struct bpf_verifier_state *vstate = env->cur_state;
+	struct bpf_func_state *state = vstate->frame[vstate->curframe];
+	struct bpf_reg_state *reg = &state->regs[regno];
+	struct bpf_map *map = reg->map_ptr;
+	int err;
+
+	err = check_mem_region_access(env, regno, off, size, map->value_size,
+				      zero_size_allowed);
+	if (err)
+		return err;
+
+	if (map_value_has_spin_lock(map)) {
+		u32 lock = map->spin_lock_off;
 
 		/* if any part of struct bpf_spin_lock can be touched by
 		 * load/store reject this program.
@@ -2339,21 +2665,6 @@ static bool may_access_direct_pkt_data(struct bpf_verifier_env *env,
 	}
 }
 
-static int __check_packet_access(struct bpf_verifier_env *env, u32 regno,
-				 int off, int size, bool zero_size_allowed)
-{
-	struct bpf_reg_state *regs = cur_regs(env);
-	struct bpf_reg_state *reg = &regs[regno];
-
-	if (off < 0 || size < 0 || (size == 0 && !zero_size_allowed) ||
-	    (u64)off + size > reg->range) {
-		verbose(env, "invalid access to packet, off=%d size=%d, R%d(id=%d,off=%d,r=%d)\n",
-			off, size, regno, reg->id, reg->off, reg->range);
-		return -EACCES;
-	}
-	return 0;
-}
-
 static int check_packet_access(struct bpf_verifier_env *env, u32 regno, int off,
 			       int size, bool zero_size_allowed)
 {
@@ -2374,16 +2685,17 @@ static int check_packet_access(struct bpf_verifier_env *env, u32 regno, int off,
 			regno);
 		return -EACCES;
 	}
-	err = __check_packet_access(env, regno, off, size, zero_size_allowed);
+	err = __check_mem_access(env, regno, off, size, reg->range,
+				 zero_size_allowed);
 	if (err) {
 		verbose(env, "R%d offset is outside of the packet\n", regno);
 		return err;
 	}
 
-	/* __check_packet_access has made sure "off + size - 1" is within u16.
+	/* __check_mem_access has made sure "off + size - 1" is within u16.
 	 * reg->umax_value can't be bigger than MAX_PACKET_OFF which is 0xffff,
 	 * otherwise find_good_pkt_pointers would have refused to set range info
-	 * that __check_packet_access would have rejected this pkt access.
+	 * that __check_mem_access would have rejected this pkt access.
 	 * Therefore, "off + reg->umax_value + size - 1" won't overflow u32.
 	 */
 	env->prog->aux->max_pkt_offset =
@@ -2414,7 +2726,7 @@ static int check_ctx_access(struct bpf_verifier_env *env, int insn_idx, int off,
 		 */
 		*reg_type = info.reg_type;
 
-		if (*reg_type == PTR_TO_BTF_ID)
+		if (*reg_type == PTR_TO_BTF_ID || *reg_type == PTR_TO_BTF_ID_OR_NULL)
 			*btf_id = info.btf_id;
 		else
 			env->insn_aux_data[insn_idx].ctx_field_size = info.ctx_field_size;
@@ -2485,15 +2797,6 @@ static int check_sock_access(struct bpf_verifier_env *env, int insn_idx,
 	return -EACCES;
 }
 
-static bool __is_pointer_value(bool allow_ptr_leaks,
-			       const struct bpf_reg_state *reg)
-{
-	if (allow_ptr_leaks)
-		return false;
-
-	return reg->type != SCALAR_VALUE;
-}
-
 static struct bpf_reg_state *reg_state(struct bpf_verifier_env *env, int regno)
 {
 	return cur_regs(env) + regno;
@@ -2759,14 +3062,15 @@ int check_ctx_reg(struct bpf_verifier_env *env,
 	return 0;
 }
 
-static int check_tp_buffer_access(struct bpf_verifier_env *env,
-				  const struct bpf_reg_state *reg,
-				  int regno, int off, int size)
+static int __check_buffer_access(struct bpf_verifier_env *env,
+				 const char *buf_info,
+				 const struct bpf_reg_state *reg,
+				 int regno, int off, int size)
 {
 	if (off < 0) {
 		verbose(env,
-			"R%d invalid tracepoint buffer access: off=%d, size=%d",
-			regno, off, size);
+			"R%d invalid %s buffer access: off=%d, size=%d\n",
+			regno, buf_info, off, size);
 		return -EACCES;
 	}
 	if (!tnum_is_const(reg->var_off) || reg->var_off.value) {
@@ -2774,16 +3078,55 @@ static int check_tp_buffer_access(struct bpf_verifier_env *env,
 
 		tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
 		verbose(env,
-			"R%d invalid variable buffer offset: off=%d, var_off=%s",
+			"R%d invalid variable buffer offset: off=%d, var_off=%s\n",
 			regno, off, tn_buf);
 		return -EACCES;
 	}
+
+	return 0;
+}
+
+static int check_tp_buffer_access(struct bpf_verifier_env *env,
+				  const struct bpf_reg_state *reg,
+				  int regno, int off, int size)
+{
+	int err;
+
+	err = __check_buffer_access(env, "tracepoint", reg, regno, off, size);
+	if (err)
+		return err;
+
 	if (off + size > env->prog->aux->max_tp_access)
 		env->prog->aux->max_tp_access = off + size;
 
 	return 0;
 }
 
+static int check_buffer_access(struct bpf_verifier_env *env,
+			       const struct bpf_reg_state *reg,
+			       int regno, int off, int size,
+			       bool zero_size_allowed,
+			       const char *buf_info,
+			       u32 *max_access)
+{
+	int err;
+
+	err = __check_buffer_access(env, buf_info, reg, regno, off, size);
+	if (err)
+		return err;
+
+	if (off + size > *max_access)
+		*max_access = off + size;
+
+	return 0;
+}
+
+/* BPF architecture zero extends alu32 ops into 64-bit registesr */
+static void zext_32_to_64(struct bpf_reg_state *reg)
+{
+	reg->var_off = tnum_subreg(reg->var_off);
+	__reg_assign_32_into_64(reg);
+}
 
 /* truncate register to smaller size (in bytes)
  * must be called with size < BPF_REG_SIZE
@@ -2806,6 +3149,14 @@ static void coerce_reg_to_size(struct bpf_reg_state *reg, int size)
 	}
 	reg->smin_value = reg->umin_value;
 	reg->smax_value = reg->umax_value;
+
+	/* If size is smaller than 32bit register the 32bit register
+	 * values are also truncated so we push 64-bit bounds into
+	 * 32-bit bounds. Above were truncated < 32-bits already.
+	 */
+	if (size >= 4)
+		return;
+	__reg_combine_64_into_32(reg);
 }
 
 static bool bpf_map_is_rdonly(const struct bpf_map *map)
@@ -2887,19 +3238,68 @@ static int check_ptr_to_btf_access(struct bpf_verifier_env *env,
 	if (ret < 0)
 		return ret;
 
-	if (atype == BPF_READ) {
-		if (ret == SCALAR_VALUE) {
-			mark_reg_unknown(env, regs, value_regno);
-			return 0;
-		}
-		mark_reg_known_zero(env, regs, value_regno);
-		regs[value_regno].type = PTR_TO_BTF_ID;
-		regs[value_regno].btf_id = btf_id;
+	if (atype == BPF_READ && value_regno >= 0)
+		mark_btf_ld_reg(env, regs, value_regno, ret, btf_id);
+
+	return 0;
+}
+
+static int check_ptr_to_map_access(struct bpf_verifier_env *env,
+				   struct bpf_reg_state *regs,
+				   int regno, int off, int size,
+				   enum bpf_access_type atype,
+				   int value_regno)
+{
+	struct bpf_reg_state *reg = regs + regno;
+	struct bpf_map *map = reg->map_ptr;
+	const struct btf_type *t;
+	const char *tname;
+	u32 btf_id;
+	int ret;
+
+	if (!btf_vmlinux) {
+		verbose(env, "map_ptr access not supported without CONFIG_DEBUG_INFO_BTF\n");
+		return -ENOTSUPP;
 	}
 
+	if (!map->ops->map_btf_id || !*map->ops->map_btf_id) {
+		verbose(env, "map_ptr access not supported for map type %d\n",
+			map->map_type);
+		return -ENOTSUPP;
+	}
+
+	t = btf_type_by_id(btf_vmlinux, *map->ops->map_btf_id);
+	tname = btf_name_by_offset(btf_vmlinux, t->name_off);
+
+	if (!env->allow_ptr_to_map_access) {
+		verbose(env,
+			"%s access is allowed only to CAP_PERFMON and CAP_SYS_ADMIN\n",
+			tname);
+		return -EPERM;
+	}
+
+	if (off < 0) {
+		verbose(env, "R%d is %s invalid negative access: off=%d\n",
+			regno, tname, off);
+		return -EACCES;
+	}
+
+	if (atype != BPF_READ) {
+		verbose(env, "only read from %s is supported\n", tname);
+		return -EACCES;
+	}
+
+	ret = btf_struct_access(&env->log, t, off, size, atype, &btf_id);
+	if (ret < 0)
+		return ret;
+
+	if (value_regno >= 0)
+		mark_btf_ld_reg(env, regs, value_regno, ret, btf_id);
+
 	return 0;
 }
 
+
 /* check whether memory at (regno + off) is accessible for t = (read | write)
  * if t==write, value_regno is a register which value is stored into memory
  * if t==read, value_regno is a register which will receive the value from memory
@@ -2958,6 +3358,16 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
 				mark_reg_unknown(env, regs, value_regno);
 			}
 		}
+	} else if (reg->type == PTR_TO_MEM) {
+		if (t == BPF_WRITE && value_regno >= 0 &&
+		    is_pointer_value(env, value_regno)) {
+			verbose(env, "R%d leaks addr into mem\n", value_regno);
+			return -EACCES;
+		}
+		err = check_mem_region_access(env, regno, off, size,
+					      reg->mem_size, false);
+		if (!err && t == BPF_READ && value_regno >= 0)
+			mark_reg_unknown(env, regs, value_regno);
 	} else if (reg->type == PTR_TO_CTX) {
 		enum bpf_reg_type reg_type = SCALAR_VALUE;
 		u32 btf_id = 0;
@@ -2993,7 +3403,8 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
 				 * a sub-register.
 				 */
 				regs[value_regno].subreg_def = DEF_NOT_SUBREG;
-				if (reg_type == PTR_TO_BTF_ID)
+				if (reg_type == PTR_TO_BTF_ID ||
+				    reg_type == PTR_TO_BTF_ID_OR_NULL)
 					regs[value_regno].btf_id = btf_id;
 			}
 			regs[value_regno].type = reg_type;
@@ -3057,6 +3468,26 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
 	} else if (reg->type == PTR_TO_BTF_ID) {
 		err = check_ptr_to_btf_access(env, regs, regno, off, size, t,
 					      value_regno);
+	} else if (reg->type == CONST_PTR_TO_MAP) {
+		err = check_ptr_to_map_access(env, regs, regno, off, size, t,
+					      value_regno);
+	} else if (reg->type == PTR_TO_RDONLY_BUF) {
+		if (t == BPF_WRITE) {
+			verbose(env, "R%d cannot write into %s\n",
+				regno, reg_type_str[reg->type]);
+			return -EACCES;
+		}
+		err = check_buffer_access(env, reg, regno, off, size, false,
+					  "rdonly",
+					  &env->prog->aux->max_rdonly_access);
+		if (!err && value_regno >= 0)
+			mark_reg_unknown(env, regs, value_regno);
+	} else if (reg->type == PTR_TO_RDWR_BUF) {
+		err = check_buffer_access(env, reg, regno, off, size, false,
+					  "rdwr",
+					  &env->prog->aux->max_rdwr_access);
+		if (!err && t == BPF_READ && value_regno >= 0)
+			mark_reg_unknown(env, regs, value_regno);
 	} else {
 		verbose(env, "R%d invalid mem access '%s'\n", regno,
 			reg_type_str[reg->type]);
@@ -3178,7 +3609,7 @@ static int check_stack_boundary(struct bpf_verifier_env *env, int regno,
 		 * Spectre masking for stack ALU.
 		 * See also retrieve_ptr_limit().
 		 */
-		if (!env->allow_ptr_leaks) {
+		if (!env->bypass_spec_v1) {
 			char tn_buf[48];
 
 			tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
@@ -3240,6 +3671,11 @@ static int check_stack_boundary(struct bpf_verifier_env *env, int regno,
 			*stype = STACK_MISC;
 			goto mark;
 		}
+
+		if (state->stack[spi].slot_type[0] == STACK_SPILL &&
+		    state->stack[spi].spilled_ptr.type == PTR_TO_BTF_ID)
+			goto mark;
+
 		if (state->stack[spi].slot_type[0] == STACK_SPILL &&
 		    state->stack[spi].spilled_ptr.type == SCALAR_VALUE) {
 			__mark_reg_unknown(env, &state->stack[spi].spilled_ptr);
@@ -3289,6 +3725,22 @@ static int check_helper_mem_access(struct bpf_verifier_env *env, int regno,
 			return -EACCES;
 		return check_map_access(env, regno, reg->off, access_size,
 					zero_size_allowed);
+	case PTR_TO_MEM:
+		return check_mem_region_access(env, regno, reg->off,
+					       access_size, reg->mem_size,
+					       zero_size_allowed);
+	case PTR_TO_RDONLY_BUF:
+		if (meta && meta->raw_mode)
+			return -EACCES;
+		return check_buffer_access(env, reg, regno, reg->off,
+					   access_size, zero_size_allowed,
+					   "rdonly",
+					   &env->prog->aux->max_rdonly_access);
+	case PTR_TO_RDWR_BUF:
+		return check_buffer_access(env, reg, regno, reg->off,
+					   access_size, zero_size_allowed,
+					   "rdwr",
+					   &env->prog->aux->max_rdwr_access);
 	default: /* scalar_value|ptr_to_stack or invalid ptr */
 		return check_stack_boundary(env, regno, access_size,
 					    zero_size_allowed, meta);
@@ -3393,6 +3845,17 @@ static bool arg_type_is_mem_size(enum bpf_arg_type type)
 	       type == ARG_CONST_SIZE_OR_ZERO;
 }
 
+static bool arg_type_is_alloc_mem_ptr(enum bpf_arg_type type)
+{
+	return type == ARG_PTR_TO_ALLOC_MEM ||
+	       type == ARG_PTR_TO_ALLOC_MEM_OR_NULL;
+}
+
+static bool arg_type_is_alloc_size(enum bpf_arg_type type)
+{
+	return type == ARG_CONST_ALLOC_SIZE_OR_ZERO;
+}
+
 static bool arg_type_is_int_ptr(enum bpf_arg_type type)
 {
 	return type == ARG_PTR_TO_INT ||
@@ -3409,12 +3872,14 @@ static int int_ptr_type_to_size(enum bpf_arg_type type)
 	return -EINVAL;
 }
 
-static int check_func_arg(struct bpf_verifier_env *env, u32 regno,
-			  enum bpf_arg_type arg_type,
-			  struct bpf_call_arg_meta *meta)
+static int check_func_arg(struct bpf_verifier_env *env, u32 arg,
+			  struct bpf_call_arg_meta *meta,
+			  const struct bpf_func_proto *fn)
 {
+	u32 regno = BPF_REG_1 + arg;
 	struct bpf_reg_state *regs = cur_regs(env), *reg = &regs[regno];
 	enum bpf_reg_type expected_type, type = reg->type;
+	enum bpf_arg_type arg_type = fn->arg_type[arg];
 	int err = 0;
 
 	if (arg_type == ARG_DONTCARE)
@@ -3452,7 +3917,8 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno,
 			 type != expected_type)
 			goto err_type;
 	} else if (arg_type == ARG_CONST_SIZE ||
-		   arg_type == ARG_CONST_SIZE_OR_ZERO) {
+		   arg_type == ARG_CONST_SIZE_OR_ZERO ||
+		   arg_type == ARG_CONST_ALLOC_SIZE_OR_ZERO) {
 		expected_type = SCALAR_VALUE;
 		if (type != expected_type)
 			goto err_type;
@@ -3460,13 +3926,17 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno,
 		expected_type = CONST_PTR_TO_MAP;
 		if (type != expected_type)
 			goto err_type;
-	} else if (arg_type == ARG_PTR_TO_CTX) {
+	} else if (arg_type == ARG_PTR_TO_CTX ||
+		   arg_type == ARG_PTR_TO_CTX_OR_NULL) {
 		expected_type = PTR_TO_CTX;
-		if (type != expected_type)
-			goto err_type;
-		err = check_ctx_reg(env, reg, regno);
-		if (err < 0)
-			return err;
+		if (!(register_is_null(reg) &&
+		      arg_type == ARG_PTR_TO_CTX_OR_NULL)) {
+			if (type != expected_type)
+				goto err_type;
+			err = check_ctx_reg(env, reg, regno);
+			if (err < 0)
+				return err;
+		}
 	} else if (arg_type == ARG_PTR_TO_SOCK_COMMON) {
 		expected_type = PTR_TO_SOCK_COMMON;
 		/* Any sk pointer can be ARG_PTR_TO_SOCK_COMMON */
@@ -3481,17 +3951,28 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno,
 			}
 			meta->ref_obj_id = reg->ref_obj_id;
 		}
-	} else if (arg_type == ARG_PTR_TO_SOCKET) {
+	} else if (arg_type == ARG_PTR_TO_SOCKET ||
+		   arg_type == ARG_PTR_TO_SOCKET_OR_NULL) {
 		expected_type = PTR_TO_SOCKET;
-		if (type != expected_type)
-			goto err_type;
+		if (!(register_is_null(reg) &&
+		      arg_type == ARG_PTR_TO_SOCKET_OR_NULL)) {
+			if (type != expected_type)
+				goto err_type;
+		}
 	} else if (arg_type == ARG_PTR_TO_BTF_ID) {
 		expected_type = PTR_TO_BTF_ID;
 		if (type != expected_type)
 			goto err_type;
-		if (reg->btf_id != meta->btf_id) {
-			verbose(env, "Helper has type %s got %s in R%d\n",
-				kernel_type_name(meta->btf_id),
+		if (!fn->check_btf_id) {
+			if (reg->btf_id != meta->btf_id) {
+				verbose(env, "Helper has type %s got %s in R%d\n",
+					kernel_type_name(meta->btf_id),
+					kernel_type_name(reg->btf_id), regno);
+
+				return -EACCES;
+			}
+		} else if (!fn->check_btf_id(reg->btf_id, arg)) {
+			verbose(env, "Helper does not support %s in R%d\n",
 				kernel_type_name(reg->btf_id), regno);
 
 			return -EACCES;
@@ -3519,13 +4000,31 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno,
 		 * happens during stack boundary checking.
 		 */
 		if (register_is_null(reg) &&
-		    arg_type == ARG_PTR_TO_MEM_OR_NULL)
+		    (arg_type == ARG_PTR_TO_MEM_OR_NULL ||
+		     arg_type == ARG_PTR_TO_ALLOC_MEM_OR_NULL))
 			/* final test in check_stack_boundary() */;
 		else if (!type_is_pkt_pointer(type) &&
 			 type != PTR_TO_MAP_VALUE &&
+			 type != PTR_TO_MEM &&
+			 type != PTR_TO_RDONLY_BUF &&
+			 type != PTR_TO_RDWR_BUF &&
 			 type != expected_type)
 			goto err_type;
 		meta->raw_mode = arg_type == ARG_PTR_TO_UNINIT_MEM;
+	} else if (arg_type_is_alloc_mem_ptr(arg_type)) {
+		expected_type = PTR_TO_MEM;
+		if (register_is_null(reg) &&
+		    arg_type == ARG_PTR_TO_ALLOC_MEM_OR_NULL)
+			/* final test in check_stack_boundary() */;
+		else if (type != expected_type)
+			goto err_type;
+		if (meta->ref_obj_id) {
+			verbose(env, "verifier internal error: more than one arg with ref_obj_id R%d %u %u\n",
+				regno, reg->ref_obj_id,
+				meta->ref_obj_id);
+			return -EFAULT;
+		}
+		meta->ref_obj_id = reg->ref_obj_id;
 	} else if (arg_type_is_int_ptr(arg_type)) {
 		expected_type = PTR_TO_STACK;
 		if (!type_is_pkt_pointer(type) &&
@@ -3576,11 +4075,15 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno,
 	} else if (arg_type_is_mem_size(arg_type)) {
 		bool zero_size_allowed = (arg_type == ARG_CONST_SIZE_OR_ZERO);
 
-		/* remember the mem_size which may be used later
-		 * to refine return values.
+		/* This is used to refine r0 return value bounds for helpers
+		 * that enforce this value as an upper bound on return values.
+		 * See do_refine_retval_range() for helpers that can refine
+		 * the return value. C type of helper is u32 so we pull register
+		 * bound from umax_value however, if negative verifier errors
+		 * out. Only upper bounds can be learned because retval is an
+		 * int type and negative retvals are allowed.
 		 */
-		meta->msize_smax_value = reg->smax_value;
-		meta->msize_umax_value = reg->umax_value;
+		meta->msize_max_value = reg->umax_value;
 
 		/* The register is SCALAR_VALUE; the access check
 		 * happens using its boundaries.
@@ -3617,6 +4120,13 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno,
 					      zero_size_allowed, meta);
 		if (!err)
 			err = mark_chain_precision(env, regno);
+	} else if (arg_type_is_alloc_size(arg_type)) {
+		if (!tnum_is_const(reg->var_off)) {
+			verbose(env, "R%d unbounded size, use 'var &= const' or 'if (var < const)'\n",
+				regno);
+			return -EACCES;
+		}
+		meta->mem_size = reg->var_off.value;
 	} else if (arg_type_is_int_ptr(arg_type)) {
 		int size = int_ptr_type_to_size(arg_type);
 
@@ -3649,7 +4159,16 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env,
 		if (func_id != BPF_FUNC_perf_event_read &&
 		    func_id != BPF_FUNC_perf_event_output &&
 		    func_id != BPF_FUNC_skb_output &&
-		    func_id != BPF_FUNC_perf_event_read_value)
+		    func_id != BPF_FUNC_perf_event_read_value &&
+		    func_id != BPF_FUNC_xdp_output)
+			goto error;
+		break;
+	case BPF_MAP_TYPE_RINGBUF:
+		if (func_id != BPF_FUNC_ringbuf_output &&
+		    func_id != BPF_FUNC_ringbuf_reserve &&
+		    func_id != BPF_FUNC_ringbuf_submit &&
+		    func_id != BPF_FUNC_ringbuf_discard &&
+		    func_id != BPF_FUNC_ringbuf_query)
 			goto error;
 		break;
 	case BPF_MAP_TYPE_STACK_TRACE:
@@ -3693,14 +4212,18 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env,
 		if (func_id != BPF_FUNC_sk_redirect_map &&
 		    func_id != BPF_FUNC_sock_map_update &&
 		    func_id != BPF_FUNC_map_delete_elem &&
-		    func_id != BPF_FUNC_msg_redirect_map)
+		    func_id != BPF_FUNC_msg_redirect_map &&
+		    func_id != BPF_FUNC_sk_select_reuseport &&
+		    func_id != BPF_FUNC_map_lookup_elem)
 			goto error;
 		break;
 	case BPF_MAP_TYPE_SOCKHASH:
 		if (func_id != BPF_FUNC_sk_redirect_hash &&
 		    func_id != BPF_FUNC_sock_hash_update &&
 		    func_id != BPF_FUNC_map_delete_elem &&
-		    func_id != BPF_FUNC_msg_redirect_hash)
+		    func_id != BPF_FUNC_msg_redirect_hash &&
+		    func_id != BPF_FUNC_sk_select_reuseport &&
+		    func_id != BPF_FUNC_map_lookup_elem)
 			goto error;
 		break;
 	case BPF_MAP_TYPE_REUSEPORT_SOCKARRAY:
@@ -3737,6 +4260,7 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env,
 	case BPF_FUNC_perf_event_output:
 	case BPF_FUNC_perf_event_read_value:
 	case BPF_FUNC_skb_output:
+	case BPF_FUNC_xdp_output:
 		if (map->map_type != BPF_MAP_TYPE_PERF_EVENT_ARRAY)
 			goto error;
 		break;
@@ -3774,7 +4298,9 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env,
 			goto error;
 		break;
 	case BPF_FUNC_sk_select_reuseport:
-		if (map->map_type != BPF_MAP_TYPE_REUSEPORT_SOCKARRAY)
+		if (map->map_type != BPF_MAP_TYPE_REUSEPORT_SOCKARRAY &&
+		    map->map_type != BPF_MAP_TYPE_SOCKMAP &&
+		    map->map_type != BPF_MAP_TYPE_SOCKHASH)
 			goto error;
 		break;
 	case BPF_FUNC_map_peek_elem:
@@ -3867,7 +4393,7 @@ static bool check_refcount_ok(const struct bpf_func_proto *fn, int func_id)
 	/* A reference acquiring function cannot acquire
 	 * another refcounted ptr.
 	 */
-	if (is_acquire_function(func_id) && count)
+	if (may_be_acquire_function(func_id) && count)
 		return false;
 
 	/* We only support one arg being unreferenced at the moment,
@@ -4114,13 +4640,16 @@ static void do_refine_retval_range(struct bpf_reg_state *regs, int ret_type,
 
 	if (ret_type != RET_INTEGER ||
 	    (func_id != BPF_FUNC_get_stack &&
-	     func_id != BPF_FUNC_probe_read_str))
+	     func_id != BPF_FUNC_probe_read_str &&
+	     func_id != BPF_FUNC_probe_read_kernel_str &&
+	     func_id != BPF_FUNC_probe_read_user_str))
 		return;
 
-	ret_reg->smax_value = meta->msize_smax_value;
-	ret_reg->umax_value = meta->msize_umax_value;
+	ret_reg->smax_value = meta->msize_max_value;
+	ret_reg->s32_max_value = meta->msize_max_value;
 	__reg_deduce_bounds(ret_reg);
 	__reg_bound_offset(ret_reg);
+	__update_reg_bounds(ret_reg);
 }
 
 static int
@@ -4159,10 +4688,10 @@ record_func_map(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta,
 
 	if (!BPF_MAP_PTR(aux->map_ptr_state))
 		bpf_map_ptr_store(aux, meta->map_ptr,
-				  meta->map_ptr->unpriv_array);
+				  !meta->map_ptr->bypass_spec_v1);
 	else if (BPF_MAP_PTR(aux->map_ptr_state) != meta->map_ptr)
 		bpf_map_ptr_store(aux, BPF_MAP_PTR_POISON,
-				  meta->map_ptr->unpriv_array);
+				  !meta->map_ptr->bypass_spec_v1);
 	return 0;
 }
 
@@ -4267,10 +4796,12 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn
 	meta.func_id = func_id;
 	/* check args */
 	for (i = 0; i < 5; i++) {
-		err = btf_resolve_helper_id(&env->log, fn, i);
-		if (err > 0)
-			meta.btf_id = err;
-		err = check_func_arg(env, BPF_REG_1 + i, fn->arg_type[i], &meta);
+		if (!fn->check_btf_id) {
+			err = btf_resolve_helper_id(&env->log, fn, i);
+			if (err > 0)
+				meta.btf_id = err;
+		}
+		err = check_func_arg(env, i, &meta, fn);
 		if (err)
 			return err;
 	}
@@ -4368,6 +4899,23 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn
 		mark_reg_known_zero(env, regs, BPF_REG_0);
 		regs[BPF_REG_0].type = PTR_TO_TCP_SOCK_OR_NULL;
 		regs[BPF_REG_0].id = ++env->id_gen;
+	} else if (fn->ret_type == RET_PTR_TO_ALLOC_MEM_OR_NULL) {
+		mark_reg_known_zero(env, regs, BPF_REG_0);
+		regs[BPF_REG_0].type = PTR_TO_MEM_OR_NULL;
+		regs[BPF_REG_0].id = ++env->id_gen;
+		regs[BPF_REG_0].mem_size = meta.mem_size;
+	} else if (fn->ret_type == RET_PTR_TO_BTF_ID_OR_NULL) {
+		int ret_btf_id;
+
+		mark_reg_known_zero(env, regs, BPF_REG_0);
+		regs[BPF_REG_0].type = PTR_TO_BTF_ID_OR_NULL;
+		ret_btf_id = *fn->ret_btf_id;
+		if (ret_btf_id == 0) {
+			verbose(env, "invalid return type %d of func %s#%d\n",
+				fn->ret_type, func_id_name(func_id), func_id);
+			return -EINVAL;
+		}
+		regs[BPF_REG_0].btf_id = ret_btf_id;
 	} else {
 		verbose(env, "unknown return type %d of func %s#%d\n",
 			fn->ret_type, func_id_name(func_id), func_id);
@@ -4377,7 +4925,7 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn
 	if (is_ptr_cast_function(func_id)) {
 		/* For release_reference() */
 		regs[BPF_REG_0].ref_obj_id = meta.ref_obj_id;
-	} else if (is_acquire_function(func_id)) {
+	} else if (is_acquire_function(func_id, meta.map_ptr)) {
 		int id = acquire_reference_state(env, insn_idx);
 
 		if (id < 0)
@@ -4394,7 +4942,9 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn
 	if (err)
 		return err;
 
-	if (func_id == BPF_FUNC_get_stack && !env->prog->has_callchain_buf) {
+	if ((func_id == BPF_FUNC_get_stack ||
+	     func_id == BPF_FUNC_get_task_stack) &&
+	    !env->prog->has_callchain_buf) {
 		const char *err_str;
 
 #ifdef CONFIG_PERF_EVENTS
@@ -4412,6 +4962,9 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn
 		env->prog->has_callchain_buf = true;
 	}
 
+	if (func_id == BPF_FUNC_get_stackid || func_id == BPF_FUNC_get_stack)
+		env->prog->call_get_stack = true;
+
 	if (changes_data)
 		clear_all_pkt_pointers(env);
 	return 0;
@@ -4427,7 +4980,17 @@ static bool signed_add_overflows(s64 a, s64 b)
 	return res < a;
 }
 
-static bool signed_sub_overflows(s64 a, s64 b)
+static bool signed_add32_overflows(s64 a, s64 b)
+{
+	/* Do the add in u32, where overflow is well-defined */
+	s32 res = (s32)((u32)a + (u32)b);
+
+	if (b < 0)
+		return res > a;
+	return res < a;
+}
+
+static bool signed_sub_overflows(s32 a, s32 b)
 {
 	/* Do the sub in u64, where overflow is well-defined */
 	s64 res = (s64)((u64)a - (u64)b);
@@ -4437,6 +5000,16 @@ static bool signed_sub_overflows(s64 a, s64 b)
 	return res > a;
 }
 
+static bool signed_sub32_overflows(s32 a, s32 b)
+{
+	/* Do the sub in u64, where overflow is well-defined */
+	s32 res = (s32)((u32)a - (u32)b);
+
+	if (b < 0)
+		return res < a;
+	return res > a;
+}
+
 static bool check_reg_sane_offset(struct bpf_verifier_env *env,
 				  const struct bpf_reg_state *reg,
 				  enum bpf_reg_type type)
@@ -4511,7 +5084,7 @@ static int retrieve_ptr_limit(const struct bpf_reg_state *ptr_reg,
 static bool can_skip_alu_sanitation(const struct bpf_verifier_env *env,
 				    const struct bpf_insn *insn)
 {
-	return env->allow_ptr_leaks || BPF_SRC(insn->code) == BPF_K;
+	return env->bypass_spec_v1 || BPF_SRC(insn->code) == BPF_K;
 }
 
 static int update_alu_sanitation_state(struct bpf_insn_aux_data *aux,
@@ -4629,6 +5202,11 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
 
 	if (BPF_CLASS(insn->code) != BPF_ALU64) {
 		/* 32-bit ALU ops on pointers produce (meaningless) scalars */
+		if (opcode == BPF_SUB && env->allow_ptr_leaks) {
+			__mark_reg_unknown(env, dst_reg);
+			return 0;
+		}
+
 		verbose(env,
 			"R%d 32-bit pointer arithmetic prohibited\n",
 			dst);
@@ -4658,7 +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;
 	}
@@ -4673,6 +5251,9 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
 	    !check_reg_sane_offset(env, ptr_reg, ptr_reg->type))
 		return -EINVAL;
 
+	/* pointer types do not carry 32-bit bounds at the moment. */
+	__mark_reg32_unbounded(dst_reg);
+
 	switch (opcode) {
 	case BPF_ADD:
 		ret = sanitize_ptr_alu(env, insn, ptr_reg, dst_reg, smin_val < 0);
@@ -4818,7 +5399,7 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
 	/* For unprivileged we require that resulting offset must be in bounds
 	 * in order to be able to sanitize access later on.
 	 */
-	if (!env->allow_ptr_leaks) {
+	if (!env->bypass_spec_v1) {
 		if (dst_reg->type == PTR_TO_MAP_VALUE &&
 		    check_map_access(env, dst, dst_reg->off, 1, false)) {
 			verbose(env, "R%d pointer arithmetic of map value goes out of range, "
@@ -4836,6 +5417,518 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
 	return 0;
 }
 
+static void scalar32_min_max_add(struct bpf_reg_state *dst_reg,
+				 struct bpf_reg_state *src_reg)
+{
+	s32 smin_val = src_reg->s32_min_value;
+	s32 smax_val = src_reg->s32_max_value;
+	u32 umin_val = src_reg->u32_min_value;
+	u32 umax_val = src_reg->u32_max_value;
+
+	if (signed_add32_overflows(dst_reg->s32_min_value, smin_val) ||
+	    signed_add32_overflows(dst_reg->s32_max_value, smax_val)) {
+		dst_reg->s32_min_value = S32_MIN;
+		dst_reg->s32_max_value = S32_MAX;
+	} else {
+		dst_reg->s32_min_value += smin_val;
+		dst_reg->s32_max_value += smax_val;
+	}
+	if (dst_reg->u32_min_value + umin_val < umin_val ||
+	    dst_reg->u32_max_value + umax_val < umax_val) {
+		dst_reg->u32_min_value = 0;
+		dst_reg->u32_max_value = U32_MAX;
+	} else {
+		dst_reg->u32_min_value += umin_val;
+		dst_reg->u32_max_value += umax_val;
+	}
+}
+
+static void scalar_min_max_add(struct bpf_reg_state *dst_reg,
+			       struct bpf_reg_state *src_reg)
+{
+	s64 smin_val = src_reg->smin_value;
+	s64 smax_val = src_reg->smax_value;
+	u64 umin_val = src_reg->umin_value;
+	u64 umax_val = src_reg->umax_value;
+
+	if (signed_add_overflows(dst_reg->smin_value, smin_val) ||
+	    signed_add_overflows(dst_reg->smax_value, smax_val)) {
+		dst_reg->smin_value = S64_MIN;
+		dst_reg->smax_value = S64_MAX;
+	} else {
+		dst_reg->smin_value += smin_val;
+		dst_reg->smax_value += smax_val;
+	}
+	if (dst_reg->umin_value + umin_val < umin_val ||
+	    dst_reg->umax_value + umax_val < umax_val) {
+		dst_reg->umin_value = 0;
+		dst_reg->umax_value = U64_MAX;
+	} else {
+		dst_reg->umin_value += umin_val;
+		dst_reg->umax_value += umax_val;
+	}
+}
+
+static void scalar32_min_max_sub(struct bpf_reg_state *dst_reg,
+				 struct bpf_reg_state *src_reg)
+{
+	s32 smin_val = src_reg->s32_min_value;
+	s32 smax_val = src_reg->s32_max_value;
+	u32 umin_val = src_reg->u32_min_value;
+	u32 umax_val = src_reg->u32_max_value;
+
+	if (signed_sub32_overflows(dst_reg->s32_min_value, smax_val) ||
+	    signed_sub32_overflows(dst_reg->s32_max_value, smin_val)) {
+		/* Overflow possible, we know nothing */
+		dst_reg->s32_min_value = S32_MIN;
+		dst_reg->s32_max_value = S32_MAX;
+	} else {
+		dst_reg->s32_min_value -= smax_val;
+		dst_reg->s32_max_value -= smin_val;
+	}
+	if (dst_reg->u32_min_value < umax_val) {
+		/* Overflow possible, we know nothing */
+		dst_reg->u32_min_value = 0;
+		dst_reg->u32_max_value = U32_MAX;
+	} else {
+		/* Cannot overflow (as long as bounds are consistent) */
+		dst_reg->u32_min_value -= umax_val;
+		dst_reg->u32_max_value -= umin_val;
+	}
+}
+
+static void scalar_min_max_sub(struct bpf_reg_state *dst_reg,
+			       struct bpf_reg_state *src_reg)
+{
+	s64 smin_val = src_reg->smin_value;
+	s64 smax_val = src_reg->smax_value;
+	u64 umin_val = src_reg->umin_value;
+	u64 umax_val = src_reg->umax_value;
+
+	if (signed_sub_overflows(dst_reg->smin_value, smax_val) ||
+	    signed_sub_overflows(dst_reg->smax_value, smin_val)) {
+		/* Overflow possible, we know nothing */
+		dst_reg->smin_value = S64_MIN;
+		dst_reg->smax_value = S64_MAX;
+	} else {
+		dst_reg->smin_value -= smax_val;
+		dst_reg->smax_value -= smin_val;
+	}
+	if (dst_reg->umin_value < umax_val) {
+		/* Overflow possible, we know nothing */
+		dst_reg->umin_value = 0;
+		dst_reg->umax_value = U64_MAX;
+	} else {
+		/* Cannot overflow (as long as bounds are consistent) */
+		dst_reg->umin_value -= umax_val;
+		dst_reg->umax_value -= umin_val;
+	}
+}
+
+static void scalar32_min_max_mul(struct bpf_reg_state *dst_reg,
+				 struct bpf_reg_state *src_reg)
+{
+	s32 smin_val = src_reg->s32_min_value;
+	u32 umin_val = src_reg->u32_min_value;
+	u32 umax_val = src_reg->u32_max_value;
+
+	if (smin_val < 0 || dst_reg->s32_min_value < 0) {
+		/* Ain't nobody got time to multiply that sign */
+		__mark_reg32_unbounded(dst_reg);
+		return;
+	}
+	/* Both values are positive, so we can work with unsigned and
+	 * copy the result to signed (unless it exceeds S32_MAX).
+	 */
+	if (umax_val > U16_MAX || dst_reg->u32_max_value > U16_MAX) {
+		/* Potential overflow, we know nothing */
+		__mark_reg32_unbounded(dst_reg);
+		return;
+	}
+	dst_reg->u32_min_value *= umin_val;
+	dst_reg->u32_max_value *= umax_val;
+	if (dst_reg->u32_max_value > S32_MAX) {
+		/* Overflow possible, we know nothing */
+		dst_reg->s32_min_value = S32_MIN;
+		dst_reg->s32_max_value = S32_MAX;
+	} else {
+		dst_reg->s32_min_value = dst_reg->u32_min_value;
+		dst_reg->s32_max_value = dst_reg->u32_max_value;
+	}
+}
+
+static void scalar_min_max_mul(struct bpf_reg_state *dst_reg,
+			       struct bpf_reg_state *src_reg)
+{
+	s64 smin_val = src_reg->smin_value;
+	u64 umin_val = src_reg->umin_value;
+	u64 umax_val = src_reg->umax_value;
+
+	if (smin_val < 0 || dst_reg->smin_value < 0) {
+		/* Ain't nobody got time to multiply that sign */
+		__mark_reg64_unbounded(dst_reg);
+		return;
+	}
+	/* Both values are positive, so we can work with unsigned and
+	 * copy the result to signed (unless it exceeds S64_MAX).
+	 */
+	if (umax_val > U32_MAX || dst_reg->umax_value > U32_MAX) {
+		/* Potential overflow, we know nothing */
+		__mark_reg64_unbounded(dst_reg);
+		return;
+	}
+	dst_reg->umin_value *= umin_val;
+	dst_reg->umax_value *= umax_val;
+	if (dst_reg->umax_value > S64_MAX) {
+		/* Overflow possible, we know nothing */
+		dst_reg->smin_value = S64_MIN;
+		dst_reg->smax_value = S64_MAX;
+	} else {
+		dst_reg->smin_value = dst_reg->umin_value;
+		dst_reg->smax_value = dst_reg->umax_value;
+	}
+}
+
+static void scalar32_min_max_and(struct bpf_reg_state *dst_reg,
+				 struct bpf_reg_state *src_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->s32_min_value;
+	u32 umax_val = src_reg->u32_max_value;
+
+	/* Assuming scalar64_min_max_and will be called so its safe
+	 * to skip updating register for known 32-bit case.
+	 */
+	if (src_known && dst_known)
+		return;
+
+	/* We get our minimum from the var_off, since that's inherently
+	 * bitwise.  Our maximum is the minimum of the operands' maxima.
+	 */
+	dst_reg->u32_min_value = var32_off.value;
+	dst_reg->u32_max_value = min(dst_reg->u32_max_value, umax_val);
+	if (dst_reg->s32_min_value < 0 || smin_val < 0) {
+		/* Lose signed bounds when ANDing negative numbers,
+		 * ain't nobody got time for that.
+		 */
+		dst_reg->s32_min_value = S32_MIN;
+		dst_reg->s32_max_value = S32_MAX;
+	} else {
+		/* ANDing two positives gives a positive, so safe to
+		 * cast result into s64.
+		 */
+		dst_reg->s32_min_value = dst_reg->u32_min_value;
+		dst_reg->s32_max_value = dst_reg->u32_max_value;
+	}
+
+}
+
+static void scalar_min_max_and(struct bpf_reg_state *dst_reg,
+			       struct bpf_reg_state *src_reg)
+{
+	bool src_known = tnum_is_const(src_reg->var_off);
+	bool dst_known = tnum_is_const(dst_reg->var_off);
+	s64 smin_val = src_reg->smin_value;
+	u64 umax_val = src_reg->umax_value;
+
+	if (src_known && dst_known) {
+		__mark_reg_known(dst_reg, dst_reg->var_off.value &
+					  src_reg->var_off.value);
+		return;
+	}
+
+	/* We get our minimum from the var_off, since that's inherently
+	 * bitwise.  Our maximum is the minimum of the operands' maxima.
+	 */
+	dst_reg->umin_value = dst_reg->var_off.value;
+	dst_reg->umax_value = min(dst_reg->umax_value, umax_val);
+	if (dst_reg->smin_value < 0 || smin_val < 0) {
+		/* Lose signed bounds when ANDing negative numbers,
+		 * ain't nobody got time for that.
+		 */
+		dst_reg->smin_value = S64_MIN;
+		dst_reg->smax_value = S64_MAX;
+	} else {
+		/* ANDing two positives gives a positive, so safe to
+		 * cast result into s64.
+		 */
+		dst_reg->smin_value = dst_reg->umin_value;
+		dst_reg->smax_value = dst_reg->umax_value;
+	}
+	/* We may learn something more from the var_off */
+	__update_reg_bounds(dst_reg);
+}
+
+static void scalar32_min_max_or(struct bpf_reg_state *dst_reg,
+				struct bpf_reg_state *src_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;
+
+	/* Assuming scalar64_min_max_or will be called so it is safe
+	 * to skip updating register for known case.
+	 */
+	if (src_known && dst_known)
+		return;
+
+	/* We get our maximum from the var_off, and our minimum is the
+	 * maximum of the operands' minima
+	 */
+	dst_reg->u32_min_value = max(dst_reg->u32_min_value, umin_val);
+	dst_reg->u32_max_value = var32_off.value | var32_off.mask;
+	if (dst_reg->s32_min_value < 0 || smin_val < 0) {
+		/* Lose signed bounds when ORing negative numbers,
+		 * ain't nobody got time for that.
+		 */
+		dst_reg->s32_min_value = S32_MIN;
+		dst_reg->s32_max_value = S32_MAX;
+	} else {
+		/* 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;
+	}
+}
+
+static void scalar_min_max_or(struct bpf_reg_state *dst_reg,
+			      struct bpf_reg_state *src_reg)
+{
+	bool src_known = tnum_is_const(src_reg->var_off);
+	bool dst_known = tnum_is_const(dst_reg->var_off);
+	s64 smin_val = src_reg->smin_value;
+	u64 umin_val = src_reg->umin_value;
+
+	if (src_known && dst_known) {
+		__mark_reg_known(dst_reg, dst_reg->var_off.value |
+					  src_reg->var_off.value);
+		return;
+	}
+
+	/* We get our maximum from the var_off, and our minimum is the
+	 * maximum of the operands' minima
+	 */
+	dst_reg->umin_value = max(dst_reg->umin_value, umin_val);
+	dst_reg->umax_value = dst_reg->var_off.value | dst_reg->var_off.mask;
+	if (dst_reg->smin_value < 0 || smin_val < 0) {
+		/* Lose signed bounds when ORing negative numbers,
+		 * ain't nobody got time for that.
+		 */
+		dst_reg->smin_value = S64_MIN;
+		dst_reg->smax_value = S64_MAX;
+	} else {
+		/* ORing two positives gives a positive, so safe to
+		 * cast result into s64.
+		 */
+		dst_reg->smin_value = dst_reg->umin_value;
+		dst_reg->smax_value = dst_reg->umax_value;
+	}
+	/* We may learn something more from the var_off */
+	__update_reg_bounds(dst_reg);
+}
+
+static void __scalar32_min_max_lsh(struct bpf_reg_state *dst_reg,
+				   u64 umin_val, u64 umax_val)
+{
+	/* We lose all sign bit information (except what we can pick
+	 * up from var_off)
+	 */
+	dst_reg->s32_min_value = S32_MIN;
+	dst_reg->s32_max_value = S32_MAX;
+	/* If we might shift our top bit out, then we know nothing */
+	if (umax_val > 31 || dst_reg->u32_max_value > 1ULL << (31 - umax_val)) {
+		dst_reg->u32_min_value = 0;
+		dst_reg->u32_max_value = U32_MAX;
+	} else {
+		dst_reg->u32_min_value <<= umin_val;
+		dst_reg->u32_max_value <<= umax_val;
+	}
+}
+
+static void scalar32_min_max_lsh(struct bpf_reg_state *dst_reg,
+				 struct bpf_reg_state *src_reg)
+{
+	u32 umax_val = src_reg->u32_max_value;
+	u32 umin_val = src_reg->u32_min_value;
+	/* u32 alu operation will zext upper bits */
+	struct tnum subreg = tnum_subreg(dst_reg->var_off);
+
+	__scalar32_min_max_lsh(dst_reg, umin_val, umax_val);
+	dst_reg->var_off = tnum_subreg(tnum_lshift(subreg, umin_val));
+	/* Not required but being careful mark reg64 bounds as unknown so
+	 * that we are forced to pick them up from tnum and zext later and
+	 * if some path skips this step we are still safe.
+	 */
+	__mark_reg64_unbounded(dst_reg);
+	__update_reg32_bounds(dst_reg);
+}
+
+static void __scalar64_min_max_lsh(struct bpf_reg_state *dst_reg,
+				   u64 umin_val, u64 umax_val)
+{
+	/* Special case <<32 because it is a common compiler pattern to sign
+	 * extend subreg by doing <<32 s>>32. In this case if 32bit bounds are
+	 * positive we know this shift will also be positive so we can track
+	 * bounds correctly. Otherwise we lose all sign bit information except
+	 * what we can pick up from var_off. Perhaps we can generalize this
+	 * later to shifts of any length.
+	 */
+	if (umin_val == 32 && umax_val == 32 && dst_reg->s32_max_value >= 0)
+		dst_reg->smax_value = (s64)dst_reg->s32_max_value << 32;
+	else
+		dst_reg->smax_value = S64_MAX;
+
+	if (umin_val == 32 && umax_val == 32 && dst_reg->s32_min_value >= 0)
+		dst_reg->smin_value = (s64)dst_reg->s32_min_value << 32;
+	else
+		dst_reg->smin_value = S64_MIN;
+
+	/* If we might shift our top bit out, then we know nothing */
+	if (dst_reg->umax_value > 1ULL << (63 - umax_val)) {
+		dst_reg->umin_value = 0;
+		dst_reg->umax_value = U64_MAX;
+	} else {
+		dst_reg->umin_value <<= umin_val;
+		dst_reg->umax_value <<= umax_val;
+	}
+}
+
+static void scalar_min_max_lsh(struct bpf_reg_state *dst_reg,
+			       struct bpf_reg_state *src_reg)
+{
+	u64 umax_val = src_reg->umax_value;
+	u64 umin_val = src_reg->umin_value;
+
+	/* scalar64 calc uses 32bit unshifted bounds so must be called first */
+	__scalar64_min_max_lsh(dst_reg, umin_val, umax_val);
+	__scalar32_min_max_lsh(dst_reg, umin_val, umax_val);
+
+	dst_reg->var_off = tnum_lshift(dst_reg->var_off, umin_val);
+	/* We may learn something more from the var_off */
+	__update_reg_bounds(dst_reg);
+}
+
+static void scalar32_min_max_rsh(struct bpf_reg_state *dst_reg,
+				 struct bpf_reg_state *src_reg)
+{
+	struct tnum subreg = tnum_subreg(dst_reg->var_off);
+	u32 umax_val = src_reg->u32_max_value;
+	u32 umin_val = src_reg->u32_min_value;
+
+	/* BPF_RSH is an unsigned shift.  If the value in dst_reg might
+	 * be negative, then either:
+	 * 1) src_reg might be zero, so the sign bit of the result is
+	 *    unknown, so we lose our signed bounds
+	 * 2) it's known negative, thus the unsigned bounds capture the
+	 *    signed bounds
+	 * 3) the signed bounds cross zero, so they tell us nothing
+	 *    about the result
+	 * If the value in dst_reg is known nonnegative, then again the
+	 * unsigned bounts capture the signed bounds.
+	 * Thus, in all cases it suffices to blow away our signed bounds
+	 * and rely on inferring new ones from the unsigned bounds and
+	 * var_off of the result.
+	 */
+	dst_reg->s32_min_value = S32_MIN;
+	dst_reg->s32_max_value = S32_MAX;
+
+	dst_reg->var_off = tnum_rshift(subreg, umin_val);
+	dst_reg->u32_min_value >>= umax_val;
+	dst_reg->u32_max_value >>= umin_val;
+
+	__mark_reg64_unbounded(dst_reg);
+	__update_reg32_bounds(dst_reg);
+}
+
+static void scalar_min_max_rsh(struct bpf_reg_state *dst_reg,
+			       struct bpf_reg_state *src_reg)
+{
+	u64 umax_val = src_reg->umax_value;
+	u64 umin_val = src_reg->umin_value;
+
+	/* BPF_RSH is an unsigned shift.  If the value in dst_reg might
+	 * be negative, then either:
+	 * 1) src_reg might be zero, so the sign bit of the result is
+	 *    unknown, so we lose our signed bounds
+	 * 2) it's known negative, thus the unsigned bounds capture the
+	 *    signed bounds
+	 * 3) the signed bounds cross zero, so they tell us nothing
+	 *    about the result
+	 * If the value in dst_reg is known nonnegative, then again the
+	 * unsigned bounts capture the signed bounds.
+	 * Thus, in all cases it suffices to blow away our signed bounds
+	 * and rely on inferring new ones from the unsigned bounds and
+	 * var_off of the result.
+	 */
+	dst_reg->smin_value = S64_MIN;
+	dst_reg->smax_value = S64_MAX;
+	dst_reg->var_off = tnum_rshift(dst_reg->var_off, umin_val);
+	dst_reg->umin_value >>= umax_val;
+	dst_reg->umax_value >>= umin_val;
+
+	/* Its not easy to operate on alu32 bounds here because it depends
+	 * on bits being shifted in. Take easy way out and mark unbounded
+	 * so we can recalculate later from tnum.
+	 */
+	__mark_reg32_unbounded(dst_reg);
+	__update_reg_bounds(dst_reg);
+}
+
+static void scalar32_min_max_arsh(struct bpf_reg_state *dst_reg,
+				  struct bpf_reg_state *src_reg)
+{
+	u64 umin_val = src_reg->u32_min_value;
+
+	/* Upon reaching here, src_known is true and
+	 * umax_val is equal to umin_val.
+	 */
+	dst_reg->s32_min_value = (u32)(((s32)dst_reg->s32_min_value) >> umin_val);
+	dst_reg->s32_max_value = (u32)(((s32)dst_reg->s32_max_value) >> umin_val);
+
+	dst_reg->var_off = tnum_arshift(tnum_subreg(dst_reg->var_off), umin_val, 32);
+
+	/* blow away the dst_reg umin_value/umax_value and rely on
+	 * dst_reg var_off to refine the result.
+	 */
+	dst_reg->u32_min_value = 0;
+	dst_reg->u32_max_value = U32_MAX;
+
+	__mark_reg64_unbounded(dst_reg);
+	__update_reg32_bounds(dst_reg);
+}
+
+static void scalar_min_max_arsh(struct bpf_reg_state *dst_reg,
+				struct bpf_reg_state *src_reg)
+{
+	u64 umin_val = src_reg->umin_value;
+
+	/* Upon reaching here, src_known is true and umax_val is equal
+	 * to umin_val.
+	 */
+	dst_reg->smin_value >>= umin_val;
+	dst_reg->smax_value >>= umin_val;
+
+	dst_reg->var_off = tnum_arshift(dst_reg->var_off, umin_val, 64);
+
+	/* blow away the dst_reg umin_value/umax_value and rely on
+	 * dst_reg var_off to refine the result.
+	 */
+	dst_reg->umin_value = 0;
+	dst_reg->umax_value = U64_MAX;
+
+	/* Its not easy to operate on alu32 bounds here because it depends
+	 * on bits being shifted in from upper 32-bits. Take easy way out
+	 * and mark unbounded so we can recalculate later from tnum.
+	 */
+	__mark_reg32_unbounded(dst_reg);
+	__update_reg_bounds(dst_reg);
+}
+
 /* WARNING: This function does calculations on 64-bit values, but the actual
  * execution may occur on 32-bit values. Therefore, things like bitshifts
  * need extra checks in the 32-bit case.
@@ -4847,36 +5940,48 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env,
 {
 	struct bpf_reg_state *regs = cur_regs(env);
 	u8 opcode = BPF_OP(insn->code);
-	bool src_known, dst_known;
+	bool src_known;
 	s64 smin_val, smax_val;
 	u64 umin_val, umax_val;
+	s32 s32_min_val, s32_max_val;
+	u32 u32_min_val, u32_max_val;
 	u64 insn_bitness = (BPF_CLASS(insn->code) == BPF_ALU64) ? 64 : 32;
 	u32 dst = insn->dst_reg;
 	int ret;
-
-	if (insn_bitness == 32) {
-		/* Relevant for 32-bit RSH: Information can propagate towards
-		 * LSB, so it isn't sufficient to only truncate the output to
-		 * 32 bits.
-		 */
-		coerce_reg_to_size(dst_reg, 4);
-		coerce_reg_to_size(&src_reg, 4);
-	}
+	bool alu32 = (BPF_CLASS(insn->code) != BPF_ALU64);
 
 	smin_val = src_reg.smin_value;
 	smax_val = src_reg.smax_value;
 	umin_val = src_reg.umin_value;
 	umax_val = src_reg.umax_value;
-	src_known = tnum_is_const(src_reg.var_off);
-	dst_known = tnum_is_const(dst_reg->var_off);
 
-	if ((src_known && (smin_val != smax_val || umin_val != umax_val)) ||
-	    smin_val > smax_val || umin_val > umax_val) {
-		/* Taint dst register if offset had invalid bounds derived from
-		 * e.g. dead branches.
-		 */
-		__mark_reg_unknown(env, dst_reg);
-		return 0;
+	s32_min_val = src_reg.s32_min_value;
+	s32_max_val = src_reg.s32_max_value;
+	u32_min_val = src_reg.u32_min_value;
+	u32_max_val = src_reg.u32_max_value;
+
+	if (alu32) {
+		src_known = tnum_subreg_is_const(src_reg.var_off);
+		if ((src_known &&
+		     (s32_min_val != s32_max_val || u32_min_val != u32_max_val)) ||
+		    s32_min_val > s32_max_val || u32_min_val > u32_max_val) {
+			/* Taint dst register if offset had invalid bounds
+			 * derived from e.g. dead branches.
+			 */
+			__mark_reg_unknown(env, dst_reg);
+			return 0;
+		}
+	} else {
+		src_known = tnum_is_const(src_reg.var_off);
+		if ((src_known &&
+		     (smin_val != smax_val || umin_val != umax_val)) ||
+		    smin_val > smax_val || umin_val > umax_val) {
+			/* Taint dst register if offset had invalid bounds
+			 * derived from e.g. dead branches.
+			 */
+			__mark_reg_unknown(env, dst_reg);
+			return 0;
+		}
 	}
 
 	if (!src_known &&
@@ -4885,6 +5990,20 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env,
 		return 0;
 	}
 
+	/* Calculate sign/unsigned bounds and tnum for alu32 and alu64 bit ops.
+	 * There are two classes of instructions: The first class we track both
+	 * alu32 and alu64 sign/unsigned bounds independently this provides the
+	 * greatest amount of precision when alu operations are mixed with jmp32
+	 * operations. These operations are BPF_ADD, BPF_SUB, BPF_MUL, BPF_ADD,
+	 * and BPF_OR. This is possible because these ops have fairly easy to
+	 * understand and calculate behavior in both 32-bit and 64-bit alu ops.
+	 * See alu32 verifier tests for examples. The second class of
+	 * operations, BPF_LSH, BPF_RSH, and BPF_ARSH, however are not so easy
+	 * with regards to tracking sign/unsigned bounds because the bits may
+	 * cross subreg boundaries in the alu64 case. When this happens we mark
+	 * the reg unbounded in the subreg bound space and use the resulting
+	 * tnum to calculate an approximation of the sign/unsigned bounds.
+	 */
 	switch (opcode) {
 	case BPF_ADD:
 		ret = sanitize_val_alu(env, insn);
@@ -4892,22 +6011,8 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env,
 			verbose(env, "R%d tried to add from different pointers or scalars\n", dst);
 			return ret;
 		}
-		if (signed_add_overflows(dst_reg->smin_value, smin_val) ||
-		    signed_add_overflows(dst_reg->smax_value, smax_val)) {
-			dst_reg->smin_value = S64_MIN;
-			dst_reg->smax_value = S64_MAX;
-		} else {
-			dst_reg->smin_value += smin_val;
-			dst_reg->smax_value += smax_val;
-		}
-		if (dst_reg->umin_value + umin_val < umin_val ||
-		    dst_reg->umax_value + umax_val < umax_val) {
-			dst_reg->umin_value = 0;
-			dst_reg->umax_value = U64_MAX;
-		} else {
-			dst_reg->umin_value += umin_val;
-			dst_reg->umax_value += umax_val;
-		}
+		scalar32_min_max_add(dst_reg, &src_reg);
+		scalar_min_max_add(dst_reg, &src_reg);
 		dst_reg->var_off = tnum_add(dst_reg->var_off, src_reg.var_off);
 		break;
 	case BPF_SUB:
@@ -4916,111 +6021,24 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env,
 			verbose(env, "R%d tried to sub from different pointers or scalars\n", dst);
 			return ret;
 		}
-		if (signed_sub_overflows(dst_reg->smin_value, smax_val) ||
-		    signed_sub_overflows(dst_reg->smax_value, smin_val)) {
-			/* Overflow possible, we know nothing */
-			dst_reg->smin_value = S64_MIN;
-			dst_reg->smax_value = S64_MAX;
-		} else {
-			dst_reg->smin_value -= smax_val;
-			dst_reg->smax_value -= smin_val;
-		}
-		if (dst_reg->umin_value < umax_val) {
-			/* Overflow possible, we know nothing */
-			dst_reg->umin_value = 0;
-			dst_reg->umax_value = U64_MAX;
-		} else {
-			/* Cannot overflow (as long as bounds are consistent) */
-			dst_reg->umin_value -= umax_val;
-			dst_reg->umax_value -= umin_val;
-		}
+		scalar32_min_max_sub(dst_reg, &src_reg);
+		scalar_min_max_sub(dst_reg, &src_reg);
 		dst_reg->var_off = tnum_sub(dst_reg->var_off, src_reg.var_off);
 		break;
 	case BPF_MUL:
 		dst_reg->var_off = tnum_mul(dst_reg->var_off, src_reg.var_off);
-		if (smin_val < 0 || dst_reg->smin_value < 0) {
-			/* Ain't nobody got time to multiply that sign */
-			__mark_reg_unbounded(dst_reg);
-			__update_reg_bounds(dst_reg);
-			break;
-		}
-		/* Both values are positive, so we can work with unsigned and
-		 * copy the result to signed (unless it exceeds S64_MAX).
-		 */
-		if (umax_val > U32_MAX || dst_reg->umax_value > U32_MAX) {
-			/* Potential overflow, we know nothing */
-			__mark_reg_unbounded(dst_reg);
-			/* (except what we can learn from the var_off) */
-			__update_reg_bounds(dst_reg);
-			break;
-		}
-		dst_reg->umin_value *= umin_val;
-		dst_reg->umax_value *= umax_val;
-		if (dst_reg->umax_value > S64_MAX) {
-			/* Overflow possible, we know nothing */
-			dst_reg->smin_value = S64_MIN;
-			dst_reg->smax_value = S64_MAX;
-		} else {
-			dst_reg->smin_value = dst_reg->umin_value;
-			dst_reg->smax_value = dst_reg->umax_value;
-		}
+		scalar32_min_max_mul(dst_reg, &src_reg);
+		scalar_min_max_mul(dst_reg, &src_reg);
 		break;
 	case BPF_AND:
-		if (src_known && dst_known) {
-			__mark_reg_known(dst_reg, dst_reg->var_off.value &
-						  src_reg.var_off.value);
-			break;
-		}
-		/* We get our minimum from the var_off, since that's inherently
-		 * bitwise.  Our maximum is the minimum of the operands' maxima.
-		 */
 		dst_reg->var_off = tnum_and(dst_reg->var_off, src_reg.var_off);
-		dst_reg->umin_value = dst_reg->var_off.value;
-		dst_reg->umax_value = min(dst_reg->umax_value, umax_val);
-		if (dst_reg->smin_value < 0 || smin_val < 0) {
-			/* Lose signed bounds when ANDing negative numbers,
-			 * ain't nobody got time for that.
-			 */
-			dst_reg->smin_value = S64_MIN;
-			dst_reg->smax_value = S64_MAX;
-		} else {
-			/* ANDing two positives gives a positive, so safe to
-			 * cast result into s64.
-			 */
-			dst_reg->smin_value = dst_reg->umin_value;
-			dst_reg->smax_value = dst_reg->umax_value;
-		}
-		/* We may learn something more from the var_off */
-		__update_reg_bounds(dst_reg);
+		scalar32_min_max_and(dst_reg, &src_reg);
+		scalar_min_max_and(dst_reg, &src_reg);
 		break;
 	case BPF_OR:
-		if (src_known && dst_known) {
-			__mark_reg_known(dst_reg, dst_reg->var_off.value |
-						  src_reg.var_off.value);
-			break;
-		}
-		/* We get our maximum from the var_off, and our minimum is the
-		 * maximum of the operands' minima
-		 */
 		dst_reg->var_off = tnum_or(dst_reg->var_off, src_reg.var_off);
-		dst_reg->umin_value = max(dst_reg->umin_value, umin_val);
-		dst_reg->umax_value = dst_reg->var_off.value |
-				      dst_reg->var_off.mask;
-		if (dst_reg->smin_value < 0 || smin_val < 0) {
-			/* Lose signed bounds when ORing negative numbers,
-			 * ain't nobody got time for that.
-			 */
-			dst_reg->smin_value = S64_MIN;
-			dst_reg->smax_value = S64_MAX;
-		} else {
-			/* ORing two positives gives a positive, so safe to
-			 * cast result into s64.
-			 */
-			dst_reg->smin_value = dst_reg->umin_value;
-			dst_reg->smax_value = dst_reg->umax_value;
-		}
-		/* We may learn something more from the var_off */
-		__update_reg_bounds(dst_reg);
+		scalar32_min_max_or(dst_reg, &src_reg);
+		scalar_min_max_or(dst_reg, &src_reg);
 		break;
 	case BPF_LSH:
 		if (umax_val >= insn_bitness) {
@@ -5030,22 +6048,10 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env,
 			mark_reg_unknown(env, regs, insn->dst_reg);
 			break;
 		}
-		/* We lose all sign bit information (except what we can pick
-		 * up from var_off)
-		 */
-		dst_reg->smin_value = S64_MIN;
-		dst_reg->smax_value = S64_MAX;
-		/* If we might shift our top bit out, then we know nothing */
-		if (dst_reg->umax_value > 1ULL << (63 - umax_val)) {
-			dst_reg->umin_value = 0;
-			dst_reg->umax_value = U64_MAX;
-		} else {
-			dst_reg->umin_value <<= umin_val;
-			dst_reg->umax_value <<= umax_val;
-		}
-		dst_reg->var_off = tnum_lshift(dst_reg->var_off, umin_val);
-		/* We may learn something more from the var_off */
-		__update_reg_bounds(dst_reg);
+		if (alu32)
+			scalar32_min_max_lsh(dst_reg, &src_reg);
+		else
+			scalar_min_max_lsh(dst_reg, &src_reg);
 		break;
 	case BPF_RSH:
 		if (umax_val >= insn_bitness) {
@@ -5055,27 +6061,10 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env,
 			mark_reg_unknown(env, regs, insn->dst_reg);
 			break;
 		}
-		/* BPF_RSH is an unsigned shift.  If the value in dst_reg might
-		 * be negative, then either:
-		 * 1) src_reg might be zero, so the sign bit of the result is
-		 *    unknown, so we lose our signed bounds
-		 * 2) it's known negative, thus the unsigned bounds capture the
-		 *    signed bounds
-		 * 3) the signed bounds cross zero, so they tell us nothing
-		 *    about the result
-		 * If the value in dst_reg is known nonnegative, then again the
-		 * unsigned bounts capture the signed bounds.
-		 * Thus, in all cases it suffices to blow away our signed bounds
-		 * and rely on inferring new ones from the unsigned bounds and
-		 * var_off of the result.
-		 */
-		dst_reg->smin_value = S64_MIN;
-		dst_reg->smax_value = S64_MAX;
-		dst_reg->var_off = tnum_rshift(dst_reg->var_off, umin_val);
-		dst_reg->umin_value >>= umax_val;
-		dst_reg->umax_value >>= umin_val;
-		/* We may learn something more from the var_off */
-		__update_reg_bounds(dst_reg);
+		if (alu32)
+			scalar32_min_max_rsh(dst_reg, &src_reg);
+		else
+			scalar_min_max_rsh(dst_reg, &src_reg);
 		break;
 	case BPF_ARSH:
 		if (umax_val >= insn_bitness) {
@@ -5085,38 +6074,21 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env,
 			mark_reg_unknown(env, regs, insn->dst_reg);
 			break;
 		}
-
-		/* Upon reaching here, src_known is true and
-		 * umax_val is equal to umin_val.
-		 */
-		if (insn_bitness == 32) {
-			dst_reg->smin_value = (u32)(((s32)dst_reg->smin_value) >> umin_val);
-			dst_reg->smax_value = (u32)(((s32)dst_reg->smax_value) >> umin_val);
-		} else {
-			dst_reg->smin_value >>= umin_val;
-			dst_reg->smax_value >>= umin_val;
-		}
-
-		dst_reg->var_off = tnum_arshift(dst_reg->var_off, umin_val,
-						insn_bitness);
-
-		/* blow away the dst_reg umin_value/umax_value and rely on
-		 * dst_reg var_off to refine the result.
-		 */
-		dst_reg->umin_value = 0;
-		dst_reg->umax_value = U64_MAX;
-		__update_reg_bounds(dst_reg);
+		if (alu32)
+			scalar32_min_max_arsh(dst_reg, &src_reg);
+		else
+			scalar_min_max_arsh(dst_reg, &src_reg);
 		break;
 	default:
 		mark_reg_unknown(env, regs, insn->dst_reg);
 		break;
 	}
 
-	if (BPF_CLASS(insn->code) != BPF_ALU64) {
-		/* 32-bit ALU ops are (32,32)->32 */
-		coerce_reg_to_size(dst_reg, 4);
-	}
+	/* ALU32 ops are zero extended into 64bit register */
+	if (alu32)
+		zext_32_to_64(dst_reg);
 
+	__update_reg_bounds(dst_reg);
 	__reg_deduce_bounds(dst_reg);
 	__reg_bound_offset(dst_reg);
 	return 0;
@@ -5290,7 +6262,7 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
 					mark_reg_unknown(env, regs,
 							 insn->dst_reg);
 				}
-				coerce_reg_to_size(dst_reg, 4);
+				zext_32_to_64(dst_reg);
 			}
 		} else {
 			/* case: R = imm
@@ -5460,55 +6432,83 @@ static void find_good_pkt_pointers(struct bpf_verifier_state *vstate,
 					 new_range);
 }
 
-/* compute branch direction of the expression "if (reg opcode val) goto target;"
- * and return:
- *  1 - branch will be taken and "goto target" will be executed
- *  0 - branch will not be taken and fall-through to next insn
- * -1 - unknown. Example: "if (reg < 5)" is unknown when register value range [0,10]
- */
-static int is_branch_taken(struct bpf_reg_state *reg, u64 val, u8 opcode,
-			   bool is_jmp32)
+static int is_branch32_taken(struct bpf_reg_state *reg, u32 val, u8 opcode)
 {
-	struct bpf_reg_state reg_lo;
-	s64 sval;
+	struct tnum subreg = tnum_subreg(reg->var_off);
+	s32 sval = (s32)val;
+
+	switch (opcode) {
+	case BPF_JEQ:
+		if (tnum_is_const(subreg))
+			return !!tnum_equals_const(subreg, val);
+		break;
+	case BPF_JNE:
+		if (tnum_is_const(subreg))
+			return !tnum_equals_const(subreg, val);
+		break;
+	case BPF_JSET:
+		if ((~subreg.mask & subreg.value) & val)
+			return 1;
+		if (!((subreg.mask | subreg.value) & val))
+			return 0;
+		break;
+	case BPF_JGT:
+		if (reg->u32_min_value > val)
+			return 1;
+		else if (reg->u32_max_value <= val)
+			return 0;
+		break;
+	case BPF_JSGT:
+		if (reg->s32_min_value > sval)
+			return 1;
+		else if (reg->s32_max_value < sval)
+			return 0;
+		break;
+	case BPF_JLT:
+		if (reg->u32_max_value < val)
+			return 1;
+		else if (reg->u32_min_value >= val)
+			return 0;
+		break;
+	case BPF_JSLT:
+		if (reg->s32_max_value < sval)
+			return 1;
+		else if (reg->s32_min_value >= sval)
+			return 0;
+		break;
+	case BPF_JGE:
+		if (reg->u32_min_value >= val)
+			return 1;
+		else if (reg->u32_max_value < val)
+			return 0;
+		break;
+	case BPF_JSGE:
+		if (reg->s32_min_value >= sval)
+			return 1;
+		else if (reg->s32_max_value < sval)
+			return 0;
+		break;
+	case BPF_JLE:
+		if (reg->u32_max_value <= val)
+			return 1;
+		else if (reg->u32_min_value > val)
+			return 0;
+		break;
+	case BPF_JSLE:
+		if (reg->s32_max_value <= sval)
+			return 1;
+		else if (reg->s32_min_value > sval)
+			return 0;
+		break;
+	}
 
-	if (__is_pointer_value(false, reg))
-		return -1;
+	return -1;
+}
 
-	if (is_jmp32) {
-		reg_lo = *reg;
-		reg = &reg_lo;
-		/* For JMP32, only low 32 bits are compared, coerce_reg_to_size
-		 * could truncate high bits and update umin/umax according to
-		 * information of low bits.
-		 */
-		coerce_reg_to_size(reg, 4);
-		/* smin/smax need special handling. For example, after coerce,
-		 * if smin_value is 0x00000000ffffffffLL, the value is -1 when
-		 * used as operand to JMP32. It is a negative number from s32's
-		 * point of view, while it is a positive number when seen as
-		 * s64. The smin/smax are kept as s64, therefore, when used with
-		 * JMP32, they need to be transformed into s32, then sign
-		 * extended back to s64.
-		 *
-		 * Also, smin/smax were copied from umin/umax. If umin/umax has
-		 * different sign bit, then min/max relationship doesn't
-		 * maintain after casting into s32, for this case, set smin/smax
-		 * to safest range.
-		 */
-		if ((reg->umax_value ^ reg->umin_value) &
-		    (1ULL << 31)) {
-			reg->smin_value = S32_MIN;
-			reg->smax_value = S32_MAX;
-		}
-		reg->smin_value = (s64)(s32)reg->smin_value;
-		reg->smax_value = (s64)(s32)reg->smax_value;
 
-		val = (u32)val;
-		sval = (s64)(s32)val;
-	} else {
-		sval = (s64)val;
-	}
+static int is_branch64_taken(struct bpf_reg_state *reg, u64 val, u8 opcode)
+{
+	s64 sval = (s64)val;
 
 	switch (opcode) {
 	case BPF_JEQ:
@@ -5578,27 +6578,39 @@ static int is_branch_taken(struct bpf_reg_state *reg, u64 val, u8 opcode,
 	return -1;
 }
 
-/* Generate min value of the high 32-bit from TNUM info. */
-static u64 gen_hi_min(struct tnum var)
+/* compute branch direction of the expression "if (reg opcode val) goto target;"
+ * and return:
+ *  1 - branch will be taken and "goto target" will be executed
+ *  0 - branch will not be taken and fall-through to next insn
+ * -1 - unknown. Example: "if (reg < 5)" is unknown when register value
+ *      range [0,10]
+ */
+static int is_branch_taken(struct bpf_reg_state *reg, u64 val, u8 opcode,
+			   bool is_jmp32)
 {
-	return var.value & ~0xffffffffULL;
-}
+	if (__is_pointer_value(false, reg)) {
+		if (!reg_type_not_null(reg->type))
+			return -1;
 
-/* Generate max value of the high 32-bit from TNUM info. */
-static u64 gen_hi_max(struct tnum var)
-{
-	return (var.value | var.mask) & ~0xffffffffULL;
-}
+		/* If pointer is valid tests against zero will fail so we can
+		 * use this to direct branch taken.
+		 */
+		if (val != 0)
+			return -1;
 
-/* Return true if VAL is compared with a s64 sign extended from s32, and they
- * are with the same signedness.
- */
-static bool cmp_val_with_extended_s64(s64 sval, struct bpf_reg_state *reg)
-{
-	return ((s32)sval >= 0 &&
-		reg->smin_value >= 0 && reg->smax_value <= S32_MAX) ||
-	       ((s32)sval < 0 &&
-		reg->smax_value <= 0 && reg->smin_value >= S32_MIN);
+		switch (opcode) {
+		case BPF_JEQ:
+			return 0;
+		case BPF_JNE:
+			return 1;
+		default:
+			return -1;
+		}
+	}
+
+	if (is_jmp32)
+		return is_branch32_taken(reg, val, opcode);
+	return is_branch64_taken(reg, val, opcode);
 }
 
 /* Adjusts the register min/max values in the case that the dst_reg is the
@@ -5607,10 +6619,16 @@ static bool cmp_val_with_extended_s64(s64 sval, struct bpf_reg_state *reg)
  * In JEQ/JNE cases we also adjust the var_off values.
  */
 static void reg_set_min_max(struct bpf_reg_state *true_reg,
-			    struct bpf_reg_state *false_reg, u64 val,
+			    struct bpf_reg_state *false_reg,
+			    u64 val, u32 val32,
 			    u8 opcode, bool is_jmp32)
 {
-	s64 sval;
+	struct tnum false_32off = tnum_subreg(false_reg->var_off);
+	struct tnum false_64off = false_reg->var_off;
+	struct tnum true_32off = tnum_subreg(true_reg->var_off);
+	struct tnum true_64off = true_reg->var_off;
+	s64 sval = (s64)val;
+	s32 sval32 = (s32)val32;
 
 	/* If the dst_reg is a pointer, we can't learn anything about its
 	 * variable offset from the compare (unless src_reg were a pointer into
@@ -5621,9 +6639,6 @@ static void reg_set_min_max(struct bpf_reg_state *true_reg,
 	if (__is_pointer_value(false, false_reg))
 		return;
 
-	val = is_jmp32 ? (u32)val : val;
-	sval = is_jmp32 ? (s64)(s32)val : (s64)val;
-
 	switch (opcode) {
 	case BPF_JEQ:
 	case BPF_JNE:
@@ -5635,211 +6650,150 @@ static void reg_set_min_max(struct bpf_reg_state *true_reg,
 		 * if it is true we know the value for sure. Likewise for
 		 * BPF_JNE.
 		 */
-		if (is_jmp32) {
-			u64 old_v = reg->var_off.value;
-			u64 hi_mask = ~0xffffffffULL;
-
-			reg->var_off.value = (old_v & hi_mask) | val;
-			reg->var_off.mask &= hi_mask;
-		} else {
+		if (is_jmp32)
+			__mark_reg32_known(reg, val32);
+		else
 			__mark_reg_known(reg, val);
-		}
 		break;
 	}
 	case BPF_JSET:
-		false_reg->var_off = tnum_and(false_reg->var_off,
-					      tnum_const(~val));
-		if (is_power_of_2(val))
-			true_reg->var_off = tnum_or(true_reg->var_off,
-						    tnum_const(val));
+		if (is_jmp32) {
+			false_32off = tnum_and(false_32off, tnum_const(~val32));
+			if (is_power_of_2(val32))
+				true_32off = tnum_or(true_32off,
+						     tnum_const(val32));
+		} else {
+			false_64off = tnum_and(false_64off, tnum_const(~val));
+			if (is_power_of_2(val))
+				true_64off = tnum_or(true_64off,
+						     tnum_const(val));
+		}
 		break;
 	case BPF_JGE:
 	case BPF_JGT:
 	{
-		u64 false_umax = opcode == BPF_JGT ? val    : val - 1;
-		u64 true_umin = opcode == BPF_JGT ? val + 1 : val;
-
 		if (is_jmp32) {
-			false_umax += gen_hi_max(false_reg->var_off);
-			true_umin += gen_hi_min(true_reg->var_off);
+			u32 false_umax = opcode == BPF_JGT ? val32  : val32 - 1;
+			u32 true_umin = opcode == BPF_JGT ? val32 + 1 : val32;
+
+			false_reg->u32_max_value = min(false_reg->u32_max_value,
+						       false_umax);
+			true_reg->u32_min_value = max(true_reg->u32_min_value,
+						      true_umin);
+		} else {
+			u64 false_umax = opcode == BPF_JGT ? val    : val - 1;
+			u64 true_umin = opcode == BPF_JGT ? val + 1 : val;
+
+			false_reg->umax_value = min(false_reg->umax_value, false_umax);
+			true_reg->umin_value = max(true_reg->umin_value, true_umin);
 		}
-		false_reg->umax_value = min(false_reg->umax_value, false_umax);
-		true_reg->umin_value = max(true_reg->umin_value, true_umin);
 		break;
 	}
 	case BPF_JSGE:
 	case BPF_JSGT:
 	{
-		s64 false_smax = opcode == BPF_JSGT ? sval    : sval - 1;
-		s64 true_smin = opcode == BPF_JSGT ? sval + 1 : sval;
+		if (is_jmp32) {
+			s32 false_smax = opcode == BPF_JSGT ? sval32    : sval32 - 1;
+			s32 true_smin = opcode == BPF_JSGT ? sval32 + 1 : sval32;
 
-		/* If the full s64 was not sign-extended from s32 then don't
-		 * deduct further info.
-		 */
-		if (is_jmp32 && !cmp_val_with_extended_s64(sval, false_reg))
-			break;
-		false_reg->smax_value = min(false_reg->smax_value, false_smax);
-		true_reg->smin_value = max(true_reg->smin_value, true_smin);
+			false_reg->s32_max_value = min(false_reg->s32_max_value, false_smax);
+			true_reg->s32_min_value = max(true_reg->s32_min_value, true_smin);
+		} else {
+			s64 false_smax = opcode == BPF_JSGT ? sval    : sval - 1;
+			s64 true_smin = opcode == BPF_JSGT ? sval + 1 : sval;
+
+			false_reg->smax_value = min(false_reg->smax_value, false_smax);
+			true_reg->smin_value = max(true_reg->smin_value, true_smin);
+		}
 		break;
 	}
 	case BPF_JLE:
 	case BPF_JLT:
 	{
-		u64 false_umin = opcode == BPF_JLT ? val    : val + 1;
-		u64 true_umax = opcode == BPF_JLT ? val - 1 : val;
-
 		if (is_jmp32) {
-			false_umin += gen_hi_min(false_reg->var_off);
-			true_umax += gen_hi_max(true_reg->var_off);
+			u32 false_umin = opcode == BPF_JLT ? val32  : val32 + 1;
+			u32 true_umax = opcode == BPF_JLT ? val32 - 1 : val32;
+
+			false_reg->u32_min_value = max(false_reg->u32_min_value,
+						       false_umin);
+			true_reg->u32_max_value = min(true_reg->u32_max_value,
+						      true_umax);
+		} else {
+			u64 false_umin = opcode == BPF_JLT ? val    : val + 1;
+			u64 true_umax = opcode == BPF_JLT ? val - 1 : val;
+
+			false_reg->umin_value = max(false_reg->umin_value, false_umin);
+			true_reg->umax_value = min(true_reg->umax_value, true_umax);
 		}
-		false_reg->umin_value = max(false_reg->umin_value, false_umin);
-		true_reg->umax_value = min(true_reg->umax_value, true_umax);
 		break;
 	}
 	case BPF_JSLE:
 	case BPF_JSLT:
 	{
-		s64 false_smin = opcode == BPF_JSLT ? sval    : sval + 1;
-		s64 true_smax = opcode == BPF_JSLT ? sval - 1 : sval;
+		if (is_jmp32) {
+			s32 false_smin = opcode == BPF_JSLT ? sval32    : sval32 + 1;
+			s32 true_smax = opcode == BPF_JSLT ? sval32 - 1 : sval32;
 
-		if (is_jmp32 && !cmp_val_with_extended_s64(sval, false_reg))
-			break;
-		false_reg->smin_value = max(false_reg->smin_value, false_smin);
-		true_reg->smax_value = min(true_reg->smax_value, true_smax);
+			false_reg->s32_min_value = max(false_reg->s32_min_value, false_smin);
+			true_reg->s32_max_value = min(true_reg->s32_max_value, true_smax);
+		} else {
+			s64 false_smin = opcode == BPF_JSLT ? sval    : sval + 1;
+			s64 true_smax = opcode == BPF_JSLT ? sval - 1 : sval;
+
+			false_reg->smin_value = max(false_reg->smin_value, false_smin);
+			true_reg->smax_value = min(true_reg->smax_value, true_smax);
+		}
 		break;
 	}
 	default:
-		break;
+		return;
 	}
 
-	__reg_deduce_bounds(false_reg);
-	__reg_deduce_bounds(true_reg);
-	/* We might have learned some bits from the bounds. */
-	__reg_bound_offset(false_reg);
-	__reg_bound_offset(true_reg);
 	if (is_jmp32) {
-		__reg_bound_offset32(false_reg);
-		__reg_bound_offset32(true_reg);
+		false_reg->var_off = tnum_or(tnum_clear_subreg(false_64off),
+					     tnum_subreg(false_32off));
+		true_reg->var_off = tnum_or(tnum_clear_subreg(true_64off),
+					    tnum_subreg(true_32off));
+		__reg_combine_32_into_64(false_reg);
+		__reg_combine_32_into_64(true_reg);
+	} else {
+		false_reg->var_off = false_64off;
+		true_reg->var_off = true_64off;
+		__reg_combine_64_into_32(false_reg);
+		__reg_combine_64_into_32(true_reg);
 	}
-	/* Intersecting with the old var_off might have improved our bounds
-	 * slightly.  e.g. if umax was 0x7f...f and var_off was (0; 0xf...fc),
-	 * then new var_off is (0; 0x7f...fc) which improves our umax.
-	 */
-	__update_reg_bounds(false_reg);
-	__update_reg_bounds(true_reg);
 }
 
 /* Same as above, but for the case that dst_reg holds a constant and src_reg is
  * the variable reg.
  */
 static void reg_set_min_max_inv(struct bpf_reg_state *true_reg,
-				struct bpf_reg_state *false_reg, u64 val,
+				struct bpf_reg_state *false_reg,
+				u64 val, u32 val32,
 				u8 opcode, bool is_jmp32)
 {
-	s64 sval;
-
-	if (__is_pointer_value(false, false_reg))
-		return;
-
-	val = is_jmp32 ? (u32)val : val;
-	sval = is_jmp32 ? (s64)(s32)val : (s64)val;
-
-	switch (opcode) {
-	case BPF_JEQ:
-	case BPF_JNE:
-	{
-		struct bpf_reg_state *reg =
-			opcode == BPF_JEQ ? true_reg : false_reg;
-
-		if (is_jmp32) {
-			u64 old_v = reg->var_off.value;
-			u64 hi_mask = ~0xffffffffULL;
-
-			reg->var_off.value = (old_v & hi_mask) | val;
-			reg->var_off.mask &= hi_mask;
-		} else {
-			__mark_reg_known(reg, val);
-		}
-		break;
-	}
-	case BPF_JSET:
-		false_reg->var_off = tnum_and(false_reg->var_off,
-					      tnum_const(~val));
-		if (is_power_of_2(val))
-			true_reg->var_off = tnum_or(true_reg->var_off,
-						    tnum_const(val));
-		break;
-	case BPF_JGE:
-	case BPF_JGT:
-	{
-		u64 false_umin = opcode == BPF_JGT ? val    : val + 1;
-		u64 true_umax = opcode == BPF_JGT ? val - 1 : val;
-
-		if (is_jmp32) {
-			false_umin += gen_hi_min(false_reg->var_off);
-			true_umax += gen_hi_max(true_reg->var_off);
-		}
-		false_reg->umin_value = max(false_reg->umin_value, false_umin);
-		true_reg->umax_value = min(true_reg->umax_value, true_umax);
-		break;
-	}
-	case BPF_JSGE:
-	case BPF_JSGT:
-	{
-		s64 false_smin = opcode == BPF_JSGT ? sval    : sval + 1;
-		s64 true_smax = opcode == BPF_JSGT ? sval - 1 : sval;
-
-		if (is_jmp32 && !cmp_val_with_extended_s64(sval, false_reg))
-			break;
-		false_reg->smin_value = max(false_reg->smin_value, false_smin);
-		true_reg->smax_value = min(true_reg->smax_value, true_smax);
-		break;
-	}
-	case BPF_JLE:
-	case BPF_JLT:
-	{
-		u64 false_umax = opcode == BPF_JLT ? val    : val - 1;
-		u64 true_umin = opcode == BPF_JLT ? val + 1 : val;
-
-		if (is_jmp32) {
-			false_umax += gen_hi_max(false_reg->var_off);
-			true_umin += gen_hi_min(true_reg->var_off);
-		}
-		false_reg->umax_value = min(false_reg->umax_value, false_umax);
-		true_reg->umin_value = max(true_reg->umin_value, true_umin);
-		break;
-	}
-	case BPF_JSLE:
-	case BPF_JSLT:
-	{
-		s64 false_smax = opcode == BPF_JSLT ? sval    : sval - 1;
-		s64 true_smin = opcode == BPF_JSLT ? sval + 1 : sval;
-
-		if (is_jmp32 && !cmp_val_with_extended_s64(sval, false_reg))
-			break;
-		false_reg->smax_value = min(false_reg->smax_value, false_smax);
-		true_reg->smin_value = max(true_reg->smin_value, true_smin);
-		break;
-	}
-	default:
-		break;
-	}
-
-	__reg_deduce_bounds(false_reg);
-	__reg_deduce_bounds(true_reg);
-	/* We might have learned some bits from the bounds. */
-	__reg_bound_offset(false_reg);
-	__reg_bound_offset(true_reg);
-	if (is_jmp32) {
-		__reg_bound_offset32(false_reg);
-		__reg_bound_offset32(true_reg);
-	}
-	/* Intersecting with the old var_off might have improved our bounds
-	 * slightly.  e.g. if umax was 0x7f...f and var_off was (0; 0xf...fc),
-	 * then new var_off is (0; 0x7f...fc) which improves our umax.
+	/* How can we transform "a <op> b" into "b <op> a"? */
+	static const u8 opcode_flip[16] = {
+		/* these stay the same */
+		[BPF_JEQ  >> 4] = BPF_JEQ,
+		[BPF_JNE  >> 4] = BPF_JNE,
+		[BPF_JSET >> 4] = BPF_JSET,
+		/* these swap "lesser" and "greater" (L and G in the opcodes) */
+		[BPF_JGE  >> 4] = BPF_JLE,
+		[BPF_JGT  >> 4] = BPF_JLT,
+		[BPF_JLE  >> 4] = BPF_JGE,
+		[BPF_JLT  >> 4] = BPF_JGT,
+		[BPF_JSGE >> 4] = BPF_JSLE,
+		[BPF_JSGT >> 4] = BPF_JSLT,
+		[BPF_JSLE >> 4] = BPF_JSGE,
+		[BPF_JSLT >> 4] = BPF_JSGT
+	};
+	opcode = opcode_flip[opcode >> 4];
+	/* This uses zero as "not present in table"; luckily the zero opcode,
+	 * BPF_JA, can't get here.
 	 */
-	__update_reg_bounds(false_reg);
-	__update_reg_bounds(true_reg);
+	if (opcode)
+		reg_set_min_max(true_reg, false_reg, val, val32, opcode, is_jmp32);
 }
 
 /* Regs are known to be equal, so intersect their min/max/var_off */
@@ -5907,12 +6861,16 @@ static void mark_ptr_or_null_reg(struct bpf_func_state *state,
 		if (is_null) {
 			reg->type = SCALAR_VALUE;
 		} else if (reg->type == PTR_TO_MAP_VALUE_OR_NULL) {
-			if (reg->map_ptr->inner_map_meta) {
+			const struct bpf_map *map = reg->map_ptr;
+
+			if (map->inner_map_meta) {
 				reg->type = CONST_PTR_TO_MAP;
-				reg->map_ptr = reg->map_ptr->inner_map_meta;
-			} else if (reg->map_ptr->map_type ==
-				   BPF_MAP_TYPE_XSKMAP) {
+				reg->map_ptr = map->inner_map_meta;
+			} else if (map->map_type == BPF_MAP_TYPE_XSKMAP) {
 				reg->type = PTR_TO_XDP_SOCK;
+			} else if (map->map_type == BPF_MAP_TYPE_SOCKMAP ||
+				   map->map_type == BPF_MAP_TYPE_SOCKHASH) {
+				reg->type = PTR_TO_SOCKET;
 			} else {
 				reg->type = PTR_TO_MAP_VALUE;
 			}
@@ -5922,6 +6880,14 @@ static void mark_ptr_or_null_reg(struct bpf_func_state *state,
 			reg->type = PTR_TO_SOCK_COMMON;
 		} else if (reg->type == PTR_TO_TCP_SOCK_OR_NULL) {
 			reg->type = PTR_TO_TCP_SOCK;
+		} else if (reg->type == PTR_TO_BTF_ID_OR_NULL) {
+			reg->type = PTR_TO_BTF_ID;
+		} else if (reg->type == PTR_TO_MEM_OR_NULL) {
+			reg->type = PTR_TO_MEM;
+		} else if (reg->type == PTR_TO_RDONLY_BUF_OR_NULL) {
+			reg->type = PTR_TO_RDONLY_BUF;
+		} else if (reg->type == PTR_TO_RDWR_BUF_OR_NULL) {
+			reg->type = PTR_TO_RDWR_BUF;
 		}
 		if (is_null) {
 			/* We don't need id and ref_obj_id from this point
@@ -6128,15 +7094,28 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env,
 	dst_reg = &regs[insn->dst_reg];
 	is_jmp32 = BPF_CLASS(insn->code) == BPF_JMP32;
 
-	if (BPF_SRC(insn->code) == BPF_K)
-		pred = is_branch_taken(dst_reg, insn->imm,
-				       opcode, is_jmp32);
-	else if (src_reg->type == SCALAR_VALUE &&
-		 tnum_is_const(src_reg->var_off))
-		pred = is_branch_taken(dst_reg, src_reg->var_off.value,
-				       opcode, is_jmp32);
+	if (BPF_SRC(insn->code) == BPF_K) {
+		pred = is_branch_taken(dst_reg, insn->imm, opcode, is_jmp32);
+	} else if (src_reg->type == SCALAR_VALUE &&
+		   is_jmp32 && tnum_is_const(tnum_subreg(src_reg->var_off))) {
+		pred = is_branch_taken(dst_reg,
+				       tnum_subreg(src_reg->var_off).value,
+				       opcode,
+				       is_jmp32);
+	} else if (src_reg->type == SCALAR_VALUE &&
+		   !is_jmp32 && tnum_is_const(src_reg->var_off)) {
+		pred = is_branch_taken(dst_reg,
+				       src_reg->var_off.value,
+				       opcode,
+				       is_jmp32);
+	}
+
 	if (pred >= 0) {
-		err = mark_chain_precision(env, insn->dst_reg);
+		/* If we get here with a dst_reg pointer type it is because
+		 * above is_branch_taken() special cased the 0 comparison.
+		 */
+		if (!__is_pointer_value(false, dst_reg))
+			err = mark_chain_precision(env, insn->dst_reg);
 		if (BPF_SRC(insn->code) == BPF_X && !err)
 			err = mark_chain_precision(env, insn->src_reg);
 		if (err)
@@ -6168,32 +7147,24 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env,
 	 */
 	if (BPF_SRC(insn->code) == BPF_X) {
 		struct bpf_reg_state *src_reg = &regs[insn->src_reg];
-		struct bpf_reg_state lo_reg0 = *dst_reg;
-		struct bpf_reg_state lo_reg1 = *src_reg;
-		struct bpf_reg_state *src_lo, *dst_lo;
-
-		dst_lo = &lo_reg0;
-		src_lo = &lo_reg1;
-		coerce_reg_to_size(dst_lo, 4);
-		coerce_reg_to_size(src_lo, 4);
 
 		if (dst_reg->type == SCALAR_VALUE &&
 		    src_reg->type == SCALAR_VALUE) {
 			if (tnum_is_const(src_reg->var_off) ||
-			    (is_jmp32 && tnum_is_const(src_lo->var_off)))
+			    (is_jmp32 &&
+			     tnum_is_const(tnum_subreg(src_reg->var_off))))
 				reg_set_min_max(&other_branch_regs[insn->dst_reg],
 						dst_reg,
-						is_jmp32
-						? src_lo->var_off.value
-						: src_reg->var_off.value,
+						src_reg->var_off.value,
+						tnum_subreg(src_reg->var_off).value,
 						opcode, is_jmp32);
 			else if (tnum_is_const(dst_reg->var_off) ||
-				 (is_jmp32 && tnum_is_const(dst_lo->var_off)))
+				 (is_jmp32 &&
+				  tnum_is_const(tnum_subreg(dst_reg->var_off))))
 				reg_set_min_max_inv(&other_branch_regs[insn->src_reg],
 						    src_reg,
-						    is_jmp32
-						    ? dst_lo->var_off.value
-						    : dst_reg->var_off.value,
+						    dst_reg->var_off.value,
+						    tnum_subreg(dst_reg->var_off).value,
 						    opcode, is_jmp32);
 			else if (!is_jmp32 &&
 				 (opcode == BPF_JEQ || opcode == BPF_JNE))
@@ -6204,7 +7175,8 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env,
 		}
 	} else if (dst_reg->type == SCALAR_VALUE) {
 		reg_set_min_max(&other_branch_regs[insn->dst_reg],
-					dst_reg, insn->imm, opcode, is_jmp32);
+					dst_reg, insn->imm, (u32)insn->imm,
+					opcode, is_jmp32);
 	}
 
 	/* detect if R == 0 where R is returned from bpf_map_lookup_elem().
@@ -6405,8 +7377,9 @@ static int check_return_code(struct bpf_verifier_env *env)
 	struct tnum range = tnum_range(0, 1);
 	int err;
 
-	/* The struct_ops func-ptr's return type could be "void" */
-	if (env->prog->type == BPF_PROG_TYPE_STRUCT_OPS &&
+	/* LSM and struct_ops func-ptr's return type could be "void" */
+	if ((env->prog->type == BPF_PROG_TYPE_STRUCT_OPS ||
+	     env->prog->type == BPF_PROG_TYPE_LSM) &&
 	    !prog->aux->attach_func_proto->type)
 		return 0;
 
@@ -6428,7 +7401,11 @@ static int check_return_code(struct bpf_verifier_env *env)
 	switch (env->prog->type) {
 	case BPF_PROG_TYPE_CGROUP_SOCK_ADDR:
 		if (env->prog->expected_attach_type == BPF_CGROUP_UDP4_RECVMSG ||
-		    env->prog->expected_attach_type == BPF_CGROUP_UDP6_RECVMSG)
+		    env->prog->expected_attach_type == BPF_CGROUP_UDP6_RECVMSG ||
+		    env->prog->expected_attach_type == BPF_CGROUP_INET4_GETPEERNAME ||
+		    env->prog->expected_attach_type == BPF_CGROUP_INET6_GETPEERNAME ||
+		    env->prog->expected_attach_type == BPF_CGROUP_INET4_GETSOCKNAME ||
+		    env->prog->expected_attach_type == BPF_CGROUP_INET6_GETSOCKNAME)
 			range = tnum_range(1, 1);
 		break;
 	case BPF_PROG_TYPE_CGROUP_SKB:
@@ -6448,6 +7425,28 @@ static int check_return_code(struct bpf_verifier_env *env)
 			return 0;
 		range = tnum_const(0);
 		break;
+	case BPF_PROG_TYPE_TRACING:
+		switch (env->prog->expected_attach_type) {
+		case BPF_TRACE_FENTRY:
+		case BPF_TRACE_FEXIT:
+			range = tnum_const(0);
+			break;
+		case BPF_TRACE_RAW_TP:
+		case BPF_MODIFY_RETURN:
+			return 0;
+		case BPF_TRACE_ITER:
+			break;
+		default:
+			return -ENOTSUPP;
+		}
+		break;
+	case BPF_PROG_TYPE_SK_LOOKUP:
+		range = tnum_range(SK_DROP, SK_PASS);
+		break;
+	case BPF_PROG_TYPE_EXT:
+		/* freplace program can return anything as its return value
+		 * depends on the to-be-replaced kernel func or bpf program.
+		 */
 	default:
 		return 0;
 	}
@@ -6576,7 +7575,7 @@ static int push_insn(int t, int w, int e, struct bpf_verifier_env *env,
 		insn_stack[env->cfg.cur_stack++] = w;
 		return 1;
 	} else if ((insn_state[w] & 0xF0) == DISCOVERED) {
-		if (loop_ok && env->allow_ptr_leaks)
+		if (loop_ok && env->bpf_capable)
 			return 0;
 		verbose_linfo(env, t, "%d: ", t);
 		verbose_linfo(env, w, "%d: ", w);
@@ -6736,7 +7735,7 @@ static int check_btf_func(struct bpf_verifier_env *env,
 	const struct btf *btf;
 	void __user *urecord;
 	u32 prev_offset = 0;
-	int ret = 0;
+	int ret = -ENOMEM;
 
 	nfuncs = attr->func_info_cnt;
 	if (!nfuncs)
@@ -7295,7 +8294,7 @@ static bool stacksafe(struct bpf_func_state *old,
 		if (old->stack[spi].slot_type[i % BPF_REG_SIZE] !=
 		    cur->stack[spi].slot_type[i % BPF_REG_SIZE])
 			/* Ex: old explored (safe) state has STACK_SPILL in
-			 * this stack slot, but current has has STACK_MISC ->
+			 * this stack slot, but current has STACK_MISC ->
 			 * this verifier states are not equivalent,
 			 * return false to continue verification of this path
 			 */
@@ -7685,7 +8684,7 @@ next:
 	if (env->max_states_per_insn < states_cnt)
 		env->max_states_per_insn = states_cnt;
 
-	if (!env->allow_ptr_leaks && states_cnt > BPF_COMPLEXITY_LIMIT_STATES)
+	if (!env->bpf_capable && states_cnt > BPF_COMPLEXITY_LIMIT_STATES)
 		return push_jmp_history(env, cur);
 
 	if (!add_new_state)
@@ -7772,6 +8771,7 @@ static bool reg_type_mismatch_ok(enum bpf_reg_type type)
 	case PTR_TO_TCP_SOCK_OR_NULL:
 	case PTR_TO_XDP_SOCK:
 	case PTR_TO_BTF_ID:
+	case PTR_TO_BTF_ID_OR_NULL:
 		return false;
 	default:
 		return true;
@@ -7798,6 +8798,7 @@ static bool reg_type_mismatch(enum bpf_reg_type src, enum bpf_reg_type prev)
 
 static int do_check(struct bpf_verifier_env *env)
 {
+	bool pop_log = !(env->log.level & BPF_LOG_LEVEL2);
 	struct bpf_verifier_state *state = env->cur_state;
 	struct bpf_insn *insns = env->prog->insnsi;
 	struct bpf_reg_state *regs;
@@ -8074,7 +9075,7 @@ static int do_check(struct bpf_verifier_env *env)
 process_bpf_exit:
 				update_branch_counts(env, env->cur_state);
 				err = pop_stack(env, &prev_insn_idx,
-						&env->insn_idx);
+						&env->insn_idx, pop_log);
 				if (err < 0) {
 					if (err != -ENOENT)
 						return err;
@@ -8139,26 +9140,48 @@ static bool is_tracing_prog_type(enum bpf_prog_type type)
 	}
 }
 
+static bool is_preallocated_map(struct bpf_map *map)
+{
+	if (!check_map_prealloc(map))
+		return false;
+	if (map->inner_map_meta && !check_map_prealloc(map->inner_map_meta))
+		return false;
+	return true;
+}
+
 static int check_map_prog_compatibility(struct bpf_verifier_env *env,
 					struct bpf_map *map,
 					struct bpf_prog *prog)
 
 {
-	/* Make sure that BPF_PROG_TYPE_PERF_EVENT programs only use
-	 * preallocated hash maps, since doing memory allocation
-	 * in overflow_handler can crash depending on where nmi got
-	 * triggered.
+	/*
+	 * Validate that trace type programs use preallocated hash maps.
+	 *
+	 * For programs attached to PERF events this is mandatory as the
+	 * perf NMI can hit any arbitrary code sequence.
+	 *
+	 * All other trace types using preallocated hash maps are unsafe as
+	 * well because tracepoint or kprobes can be inside locked regions
+	 * of the memory allocator or at a place where a recursion into the
+	 * memory allocator would see inconsistent state.
+	 *
+	 * On RT enabled kernels run-time allocation of all trace type
+	 * programs is strictly prohibited due to lock type constraints. On
+	 * !RT kernels it is allowed for backwards compatibility reasons for
+	 * now, but warnings are emitted so developers are made aware of
+	 * the unsafety and can fix their programs before this is enforced.
 	 */
-	if (prog->type == BPF_PROG_TYPE_PERF_EVENT) {
-		if (!check_map_prealloc(map)) {
+	if (is_tracing_prog_type(prog->type) && !is_preallocated_map(map)) {
+		if (prog->type == BPF_PROG_TYPE_PERF_EVENT) {
 			verbose(env, "perf_event programs can only use preallocated hash map\n");
 			return -EINVAL;
 		}
-		if (map->inner_map_meta &&
-		    !check_map_prealloc(map->inner_map_meta)) {
-			verbose(env, "perf_event programs can only use preallocated inner hash map\n");
+		if (IS_ENABLED(CONFIG_PREEMPT_RT)) {
+			verbose(env, "trace type programs can only use preallocated hash map\n");
 			return -EINVAL;
 		}
+		WARN_ONCE(1, "trace type BPF program uses run-time allocation\n");
+		verbose(env, "trace type programs with run-time allocated hash maps are unsafe. Switch to preallocated hash maps.\n");
 	}
 
 	if ((is_tracing_prog_type(prog->type) ||
@@ -8961,7 +9984,7 @@ static int jit_subprogs(struct bpf_verifier_env *env)
 	int i, j, subprog_start, subprog_end = 0, len, subprog;
 	struct bpf_insn *insn;
 	void *old_bpf_func;
-	int err;
+	int err, num_exentries;
 
 	if (env->subprog_cnt <= 1)
 		return 0;
@@ -9036,6 +10059,14 @@ static int jit_subprogs(struct bpf_verifier_env *env)
 		func[i]->aux->nr_linfo = prog->aux->nr_linfo;
 		func[i]->aux->jited_linfo = prog->aux->jited_linfo;
 		func[i]->aux->linfo_idx = env->subprog_info[i].linfo_idx;
+		num_exentries = 0;
+		insn = func[i]->insnsi;
+		for (j = 0; j < func[i]->len; j++, insn++) {
+			if (BPF_CLASS(insn->code) == BPF_LDX &&
+			    BPF_MODE(insn->code) == BPF_PROBE_MEM)
+				num_exentries++;
+		}
+		func[i]->aux->num_exentries = num_exentries;
 		func[i] = bpf_int_jit_compile(func[i]);
 		if (!func[i]->jited) {
 			err = -ENOTSUPP;
@@ -9322,7 +10353,7 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env)
 			insn->code = BPF_JMP | BPF_TAIL_CALL;
 
 			aux = &env->insn_aux_data[i + delta];
-			if (env->allow_ptr_leaks && !expect_blinding &&
+			if (env->bpf_capable && !expect_blinding &&
 			    prog->jit_requested &&
 			    !bpf_map_key_poisoned(aux) &&
 			    !bpf_map_ptr_poisoned(aux) &&
@@ -9575,6 +10606,7 @@ static void sanitize_insn_aux_data(struct bpf_verifier_env *env)
 
 static int do_check_common(struct bpf_verifier_env *env, int subprog)
 {
+	bool pop_log = !(env->log.level & BPF_LOG_LEVEL2);
 	struct bpf_verifier_state *state;
 	struct bpf_reg_state *regs;
 	int ret, i;
@@ -9637,7 +10669,9 @@ out:
 		free_verifier_state(env->cur_state, true);
 		env->cur_state = NULL;
 	}
-	while (!pop_stack(env, NULL, NULL));
+	while (!pop_stack(env, NULL, NULL, false));
+	if (!ret && pop_log)
+		bpf_vlog_reset(&env->log, 0);
 	free_states(env);
 	if (ret)
 		/* clean aux data in case subprog was rejected */
@@ -9774,6 +10808,17 @@ static int check_struct_ops_btf_id(struct bpf_verifier_env *env)
 
 	return 0;
 }
+#define SECURITY_PREFIX "security_"
+
+static int check_attach_modify_return(struct bpf_prog *prog, unsigned long addr)
+{
+	if (within_error_injection_list(addr) ||
+	    !strncmp(SECURITY_PREFIX, prog->aux->attach_func_name,
+		     sizeof(SECURITY_PREFIX) - 1))
+		return 0;
+
+	return -EINVAL;
+}
 
 static int check_attach_btf_id(struct bpf_verifier_env *env)
 {
@@ -9782,6 +10827,7 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
 	struct bpf_prog *tgt_prog = prog->aux->linked_prog;
 	u32 btf_id = prog->aux->attach_btf_id;
 	const char prefix[] = "btf_trace_";
+	struct btf_func_model fmodel;
 	int ret = 0, subprog = -1, i;
 	struct bpf_trampoline *tr;
 	const struct btf_type *t;
@@ -9794,7 +10840,9 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
 	if (prog->type == BPF_PROG_TYPE_STRUCT_OPS)
 		return check_struct_ops_btf_id(env);
 
-	if (prog->type != BPF_PROG_TYPE_TRACING && !prog_extension)
+	if (prog->type != BPF_PROG_TYPE_TRACING &&
+	    prog->type != BPF_PROG_TYPE_LSM &&
+	    !prog_extension)
 		return 0;
 
 	if (!btf_id) {
@@ -9842,6 +10890,7 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
 				return -EINVAL;
 			}
 			env->ops = bpf_verifier_ops[tgt_prog->type];
+			prog->expected_attach_type = tgt_prog->expected_attach_type;
 		}
 		if (!tgt_prog->jited) {
 			verbose(env, "Can attach to only JITed progs\n");
@@ -9920,12 +10969,37 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
 		prog->aux->attach_func_proto = t;
 		prog->aux->attach_btf_trace = true;
 		return 0;
+	case BPF_TRACE_ITER:
+		if (!btf_type_is_func(t)) {
+			verbose(env, "attach_btf_id %u is not a function\n",
+				btf_id);
+			return -EINVAL;
+		}
+		t = btf_type_by_id(btf, t->type);
+		if (!btf_type_is_func_proto(t))
+			return -EINVAL;
+		prog->aux->attach_func_name = tname;
+		prog->aux->attach_func_proto = t;
+		if (!bpf_iter_prog_supported(prog))
+			return -EINVAL;
+		ret = btf_distill_func_proto(&env->log, btf, t,
+					     tname, &fmodel);
+		return ret;
 	default:
 		if (!prog_extension)
 			return -EINVAL;
-		/* fallthrough */
+		fallthrough;
+	case BPF_MODIFY_RETURN:
+	case BPF_LSM_MAC:
 	case BPF_TRACE_FENTRY:
 	case BPF_TRACE_FEXIT:
+		prog->aux->attach_func_name = tname;
+		if (prog->type == BPF_PROG_TYPE_LSM) {
+			ret = bpf_lsm_verify_prog(&env->log, prog);
+			if (ret < 0)
+				return ret;
+		}
+
 		if (!btf_type_is_func(t)) {
 			verbose(env, "attach_btf_id %u is not a function\n",
 				btf_id);
@@ -9940,7 +11014,6 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
 		tr = bpf_trampoline_lookup(key);
 		if (!tr)
 			return -ENOMEM;
-		prog->aux->attach_func_name = tname;
 		/* t is either vmlinux type or another program's type */
 		prog->aux->attach_func_proto = t;
 		mutex_lock(&tr->mutex);
@@ -9971,6 +11044,16 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
 				goto out;
 			}
 		}
+
+		if (prog->expected_attach_type == BPF_MODIFY_RETURN) {
+			ret = check_attach_modify_return(prog, addr);
+			if (ret)
+				verbose(env, "%s() is not modifiable\n",
+					prog->aux->attach_func_name);
+		}
+
+		if (ret)
+			goto out;
 		tr->func.addr = (void *)addr;
 		prog->aux->trampoline = tr;
 out:
@@ -10012,7 +11095,7 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr,
 		env->insn_aux_data[i].orig_idx = i;
 	env->prog = *prog;
 	env->ops = bpf_verifier_ops[env->prog->type];
-	is_priv = capable(CAP_SYS_ADMIN);
+	is_priv = bpf_capable();
 
 	if (!btf_vmlinux && IS_ENABLED(CONFIG_DEBUG_INFO_BTF)) {
 		mutex_lock(&bpf_verifier_lock);
@@ -10053,7 +11136,11 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr,
 	if (attr->prog_flags & BPF_F_ANY_ALIGNMENT)
 		env->strict_alignment = false;
 
-	env->allow_ptr_leaks = is_priv;
+	env->allow_ptr_leaks = bpf_allow_ptr_leaks();
+	env->allow_ptr_to_map_access = bpf_allow_ptr_to_map_access();
+	env->bypass_spec_v1 = bpf_bypass_spec_v1();
+	env->bypass_spec_v4 = bpf_bypass_spec_v4();
+	env->bpf_capable = bpf_capable();
 
 	if (is_priv)
 		env->test_state_freq = attr->prog_flags & BPF_F_TEST_STATE_FREQ;
@@ -10175,6 +11262,13 @@ err_release_maps:
 		 * them now. Otherwise free_used_maps() will release them.
 		 */
 		release_maps(env);
+
+	/* extension progs temporarily inherit the attach_type of their targets
+	   for verification purposes, so set it back to zero before returning
+	 */
+	if (env->prog->type == BPF_PROG_TYPE_EXT)
+		env->prog->expected_attach_type = 0;
+
 	*prog = env->prog;
 err_unlock:
 	if (!is_priv)
diff --git a/kernel/bpf/xskmap.c b/kernel/bpf/xskmap.c
deleted file mode 100644
index 2cc5c8f4c800..000000000000
--- a/kernel/bpf/xskmap.c
+++ /dev/null
@@ -1,265 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/* XSKMAP used for AF_XDP sockets
- * Copyright(c) 2018 Intel Corporation.
- */
-
-#include <linux/bpf.h>
-#include <linux/capability.h>
-#include <net/xdp_sock.h>
-#include <linux/slab.h>
-#include <linux/sched.h>
-
-int xsk_map_inc(struct xsk_map *map)
-{
-	bpf_map_inc(&map->map);
-	return 0;
-}
-
-void xsk_map_put(struct xsk_map *map)
-{
-	bpf_map_put(&map->map);
-}
-
-static struct xsk_map_node *xsk_map_node_alloc(struct xsk_map *map,
-					       struct xdp_sock **map_entry)
-{
-	struct xsk_map_node *node;
-	int err;
-
-	node = kzalloc(sizeof(*node), GFP_ATOMIC | __GFP_NOWARN);
-	if (!node)
-		return ERR_PTR(-ENOMEM);
-
-	err = xsk_map_inc(map);
-	if (err) {
-		kfree(node);
-		return ERR_PTR(err);
-	}
-
-	node->map = map;
-	node->map_entry = map_entry;
-	return node;
-}
-
-static void xsk_map_node_free(struct xsk_map_node *node)
-{
-	xsk_map_put(node->map);
-	kfree(node);
-}
-
-static void xsk_map_sock_add(struct xdp_sock *xs, struct xsk_map_node *node)
-{
-	spin_lock_bh(&xs->map_list_lock);
-	list_add_tail(&node->node, &xs->map_list);
-	spin_unlock_bh(&xs->map_list_lock);
-}
-
-static void xsk_map_sock_delete(struct xdp_sock *xs,
-				struct xdp_sock **map_entry)
-{
-	struct xsk_map_node *n, *tmp;
-
-	spin_lock_bh(&xs->map_list_lock);
-	list_for_each_entry_safe(n, tmp, &xs->map_list, node) {
-		if (map_entry == n->map_entry) {
-			list_del(&n->node);
-			xsk_map_node_free(n);
-		}
-	}
-	spin_unlock_bh(&xs->map_list_lock);
-}
-
-static struct bpf_map *xsk_map_alloc(union bpf_attr *attr)
-{
-	struct bpf_map_memory mem;
-	int err, numa_node;
-	struct xsk_map *m;
-	u64 size;
-
-	if (!capable(CAP_NET_ADMIN))
-		return ERR_PTR(-EPERM);
-
-	if (attr->max_entries == 0 || attr->key_size != 4 ||
-	    attr->value_size != 4 ||
-	    attr->map_flags & ~(BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY))
-		return ERR_PTR(-EINVAL);
-
-	numa_node = bpf_map_attr_numa_node(attr);
-	size = struct_size(m, xsk_map, attr->max_entries);
-
-	err = bpf_map_charge_init(&mem, size);
-	if (err < 0)
-		return ERR_PTR(err);
-
-	m = bpf_map_area_alloc(size, numa_node);
-	if (!m) {
-		bpf_map_charge_finish(&mem);
-		return ERR_PTR(-ENOMEM);
-	}
-
-	bpf_map_init_from_attr(&m->map, attr);
-	bpf_map_charge_move(&m->map.memory, &mem);
-	spin_lock_init(&m->lock);
-
-	return &m->map;
-}
-
-static void xsk_map_free(struct bpf_map *map)
-{
-	struct xsk_map *m = container_of(map, struct xsk_map, map);
-
-	bpf_clear_redirect_map(map);
-	synchronize_net();
-	bpf_map_area_free(m);
-}
-
-static int xsk_map_get_next_key(struct bpf_map *map, void *key, void *next_key)
-{
-	struct xsk_map *m = container_of(map, struct xsk_map, map);
-	u32 index = key ? *(u32 *)key : U32_MAX;
-	u32 *next = next_key;
-
-	if (index >= m->map.max_entries) {
-		*next = 0;
-		return 0;
-	}
-
-	if (index == m->map.max_entries - 1)
-		return -ENOENT;
-	*next = index + 1;
-	return 0;
-}
-
-static u32 xsk_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf)
-{
-	const int ret = BPF_REG_0, mp = BPF_REG_1, index = BPF_REG_2;
-	struct bpf_insn *insn = insn_buf;
-
-	*insn++ = BPF_LDX_MEM(BPF_W, ret, index, 0);
-	*insn++ = BPF_JMP_IMM(BPF_JGE, ret, map->max_entries, 5);
-	*insn++ = BPF_ALU64_IMM(BPF_LSH, ret, ilog2(sizeof(struct xsk_sock *)));
-	*insn++ = BPF_ALU64_IMM(BPF_ADD, mp, offsetof(struct xsk_map, xsk_map));
-	*insn++ = BPF_ALU64_REG(BPF_ADD, ret, mp);
-	*insn++ = BPF_LDX_MEM(BPF_SIZEOF(struct xsk_sock *), ret, ret, 0);
-	*insn++ = BPF_JMP_IMM(BPF_JA, 0, 0, 1);
-	*insn++ = BPF_MOV64_IMM(ret, 0);
-	return insn - insn_buf;
-}
-
-static void *xsk_map_lookup_elem(struct bpf_map *map, void *key)
-{
-	WARN_ON_ONCE(!rcu_read_lock_held());
-	return __xsk_map_lookup_elem(map, *(u32 *)key);
-}
-
-static void *xsk_map_lookup_elem_sys_only(struct bpf_map *map, void *key)
-{
-	return ERR_PTR(-EOPNOTSUPP);
-}
-
-static int xsk_map_update_elem(struct bpf_map *map, void *key, void *value,
-			       u64 map_flags)
-{
-	struct xsk_map *m = container_of(map, struct xsk_map, map);
-	struct xdp_sock *xs, *old_xs, **map_entry;
-	u32 i = *(u32 *)key, fd = *(u32 *)value;
-	struct xsk_map_node *node;
-	struct socket *sock;
-	int err;
-
-	if (unlikely(map_flags > BPF_EXIST))
-		return -EINVAL;
-	if (unlikely(i >= m->map.max_entries))
-		return -E2BIG;
-
-	sock = sockfd_lookup(fd, &err);
-	if (!sock)
-		return err;
-
-	if (sock->sk->sk_family != PF_XDP) {
-		sockfd_put(sock);
-		return -EOPNOTSUPP;
-	}
-
-	xs = (struct xdp_sock *)sock->sk;
-
-	if (!xsk_is_setup_for_bpf_map(xs)) {
-		sockfd_put(sock);
-		return -EOPNOTSUPP;
-	}
-
-	map_entry = &m->xsk_map[i];
-	node = xsk_map_node_alloc(m, map_entry);
-	if (IS_ERR(node)) {
-		sockfd_put(sock);
-		return PTR_ERR(node);
-	}
-
-	spin_lock_bh(&m->lock);
-	old_xs = READ_ONCE(*map_entry);
-	if (old_xs == xs) {
-		err = 0;
-		goto out;
-	} else if (old_xs && map_flags == BPF_NOEXIST) {
-		err = -EEXIST;
-		goto out;
-	} else if (!old_xs && map_flags == BPF_EXIST) {
-		err = -ENOENT;
-		goto out;
-	}
-	xsk_map_sock_add(xs, node);
-	WRITE_ONCE(*map_entry, xs);
-	if (old_xs)
-		xsk_map_sock_delete(old_xs, map_entry);
-	spin_unlock_bh(&m->lock);
-	sockfd_put(sock);
-	return 0;
-
-out:
-	spin_unlock_bh(&m->lock);
-	sockfd_put(sock);
-	xsk_map_node_free(node);
-	return err;
-}
-
-static int xsk_map_delete_elem(struct bpf_map *map, void *key)
-{
-	struct xsk_map *m = container_of(map, struct xsk_map, map);
-	struct xdp_sock *old_xs, **map_entry;
-	int k = *(u32 *)key;
-
-	if (k >= map->max_entries)
-		return -EINVAL;
-
-	spin_lock_bh(&m->lock);
-	map_entry = &m->xsk_map[k];
-	old_xs = xchg(map_entry, NULL);
-	if (old_xs)
-		xsk_map_sock_delete(old_xs, map_entry);
-	spin_unlock_bh(&m->lock);
-
-	return 0;
-}
-
-void xsk_map_try_sock_delete(struct xsk_map *map, struct xdp_sock *xs,
-			     struct xdp_sock **map_entry)
-{
-	spin_lock_bh(&map->lock);
-	if (READ_ONCE(*map_entry) == xs) {
-		WRITE_ONCE(*map_entry, NULL);
-		xsk_map_sock_delete(xs, map_entry);
-	}
-	spin_unlock_bh(&map->lock);
-}
-
-const struct bpf_map_ops xsk_map_ops = {
-	.map_alloc = xsk_map_alloc,
-	.map_free = xsk_map_free,
-	.map_get_next_key = xsk_map_get_next_key,
-	.map_lookup_elem = xsk_map_lookup_elem,
-	.map_gen_lookup = xsk_map_gen_lookup,
-	.map_lookup_elem_sys_only = xsk_map_lookup_elem_sys_only,
-	.map_update_elem = xsk_map_update_elem,
-	.map_delete_elem = xsk_map_delete_elem,
-	.map_check_btf = map_check_no_btf,
-};
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/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c
index f2d7cea86ffe..191c329e482a 100644
--- a/kernel/cgroup/cgroup-v1.c
+++ b/kernel/cgroup/cgroup-v1.c
@@ -38,10 +38,7 @@ static bool cgroup_no_v1_named;
  */
 static struct workqueue_struct *cgroup_pidlist_destroy_wq;
 
-/*
- * Protects cgroup_subsys->release_agent_path.  Modifying it also requires
- * cgroup_mutex.  Reading requires either cgroup_mutex or this spinlock.
- */
+/* protects cgroup_subsys->release_agent_path */
 static DEFINE_SPINLOCK(release_agent_path_lock);
 
 bool cgroup1_ssid_disabled(int ssid)
@@ -775,22 +772,29 @@ void cgroup1_release_agent(struct work_struct *work)
 {
 	struct cgroup *cgrp =
 		container_of(work, struct cgroup, release_agent_work);
-	char *pathbuf = NULL, *agentbuf = NULL;
+	char *pathbuf, *agentbuf;
 	char *argv[3], *envp[3];
 	int ret;
 
-	mutex_lock(&cgroup_mutex);
+	/* snoop agent path and exit early if empty */
+	if (!cgrp->root->release_agent_path[0])
+		return;
 
+	/* prepare argument buffers */
 	pathbuf = kmalloc(PATH_MAX, GFP_KERNEL);
-	agentbuf = kstrdup(cgrp->root->release_agent_path, GFP_KERNEL);
-	if (!pathbuf || !agentbuf || !strlen(agentbuf))
-		goto out;
+	agentbuf = kmalloc(PATH_MAX, GFP_KERNEL);
+	if (!pathbuf || !agentbuf)
+		goto out_free;
 
-	spin_lock_irq(&css_set_lock);
-	ret = cgroup_path_ns_locked(cgrp, pathbuf, PATH_MAX, &init_cgroup_ns);
-	spin_unlock_irq(&css_set_lock);
+	spin_lock(&release_agent_path_lock);
+	strlcpy(agentbuf, cgrp->root->release_agent_path, PATH_MAX);
+	spin_unlock(&release_agent_path_lock);
+	if (!agentbuf[0])
+		goto out_free;
+
+	ret = cgroup_path_ns(cgrp, pathbuf, PATH_MAX, &init_cgroup_ns);
 	if (ret < 0 || ret >= PATH_MAX)
-		goto out;
+		goto out_free;
 
 	argv[0] = agentbuf;
 	argv[1] = pathbuf;
@@ -801,11 +805,7 @@ void cgroup1_release_agent(struct work_struct *work)
 	envp[1] = "PATH=/sbin:/bin:/usr/sbin:/usr/bin";
 	envp[2] = NULL;
 
-	mutex_unlock(&cgroup_mutex);
 	call_usermodehelper(argv[0], argv, envp, UMH_WAIT_EXEC);
-	goto out_free;
-out:
-	mutex_unlock(&cgroup_mutex);
 out_free:
 	kfree(agentbuf);
 	kfree(pathbuf);
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 3dead0416b91..dd247747ec14 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -153,11 +153,7 @@ static struct static_key_true *cgroup_subsys_on_dfl_key[] = {
 
 static DEFINE_PER_CPU(struct cgroup_rstat_cpu, cgrp_dfl_root_rstat_cpu);
 
-/*
- * The default hierarchy, reserved for the subsystems that are otherwise
- * unattached - it never has more than a single cgroup, and all tasks are
- * part of that cgroup.
- */
+/* the default hierarchy */
 struct cgroup_root cgrp_dfl_root = { .cgrp.rstat_cpu = &cgrp_dfl_root_rstat_cpu };
 EXPORT_SYMBOL_GPL(cgrp_dfl_root);
 
@@ -251,9 +247,6 @@ bool cgroup_ssid_enabled(int ssid)
  * cases where a subsystem should behave differnetly depending on the
  * interface version.
  *
- * The set of behaviors which change on the default hierarchy are still
- * being determined and the mount option is prefixed with __DEVEL__.
- *
  * List of changed behaviors:
  *
  * - Mount options "noprefix", "xattr", "clone_children", "release_agent"
@@ -1813,12 +1806,14 @@ int cgroup_show_path(struct seq_file *sf, struct kernfs_node *kf_node,
 enum cgroup2_param {
 	Opt_nsdelegate,
 	Opt_memory_localevents,
+	Opt_memory_recursiveprot,
 	nr__cgroup2_params
 };
 
 static const struct fs_parameter_spec cgroup2_fs_parameters[] = {
 	fsparam_flag("nsdelegate",		Opt_nsdelegate),
 	fsparam_flag("memory_localevents",	Opt_memory_localevents),
+	fsparam_flag("memory_recursiveprot",	Opt_memory_recursiveprot),
 	{}
 };
 
@@ -1839,6 +1834,9 @@ static int cgroup2_parse_param(struct fs_context *fc, struct fs_parameter *param
 	case Opt_memory_localevents:
 		ctx->flags |= CGRP_ROOT_MEMORY_LOCAL_EVENTS;
 		return 0;
+	case Opt_memory_recursiveprot:
+		ctx->flags |= CGRP_ROOT_MEMORY_RECURSIVE_PROT;
+		return 0;
 	}
 	return -EINVAL;
 }
@@ -1855,6 +1853,11 @@ static void apply_cgroup_root_flags(unsigned int root_flags)
 			cgrp_dfl_root.flags |= CGRP_ROOT_MEMORY_LOCAL_EVENTS;
 		else
 			cgrp_dfl_root.flags &= ~CGRP_ROOT_MEMORY_LOCAL_EVENTS;
+
+		if (root_flags & CGRP_ROOT_MEMORY_RECURSIVE_PROT)
+			cgrp_dfl_root.flags |= CGRP_ROOT_MEMORY_RECURSIVE_PROT;
+		else
+			cgrp_dfl_root.flags &= ~CGRP_ROOT_MEMORY_RECURSIVE_PROT;
 	}
 }
 
@@ -1864,6 +1867,8 @@ static int cgroup_show_options(struct seq_file *seq, struct kernfs_root *kf_root
 		seq_puts(seq, ",nsdelegate");
 	if (cgrp_dfl_root.flags & CGRP_ROOT_MEMORY_LOCAL_EVENTS)
 		seq_puts(seq, ",memory_localevents");
+	if (cgrp_dfl_root.flags & CGRP_ROOT_MEMORY_RECURSIVE_PROT)
+		seq_puts(seq, ",memory_recursiveprot");
 	return 0;
 }
 
@@ -1954,7 +1959,8 @@ int cgroup_setup_root(struct cgroup_root *root, u16 ss_mask)
 
 	root->kf_root = kernfs_create_root(kf_sops,
 					   KERNFS_ROOT_CREATE_DEACTIVATED |
-					   KERNFS_ROOT_SUPPORT_EXPORTOP,
+					   KERNFS_ROOT_SUPPORT_EXPORTOP |
+					   KERNFS_ROOT_SUPPORT_USER_XATTR,
 					   root_cgrp);
 	if (IS_ERR(root->kf_root)) {
 		ret = PTR_ERR(root->kf_root);
@@ -2714,11 +2720,7 @@ int cgroup_attach_task(struct cgroup *dst_cgrp, struct task_struct *leader,
 {
 	DEFINE_CGROUP_MGCTX(mgctx);
 	struct task_struct *task;
-	int ret;
-
-	ret = cgroup_migrate_vet_dst(dst_cgrp);
-	if (ret)
-		return ret;
+	int ret = 0;
 
 	/* look up all src csets */
 	spin_lock_irq(&css_set_lock);
@@ -4148,7 +4150,8 @@ struct cgroup_subsys_state *css_next_child(struct cgroup_subsys_state *pos,
 	} else if (likely(!(pos->flags & CSS_RELEASED))) {
 		next = list_entry_rcu(pos->sibling.next, struct cgroup_subsys_state, sibling);
 	} else {
-		list_for_each_entry_rcu(next, &parent->children, sibling)
+		list_for_each_entry_rcu(next, &parent->children, sibling,
+					lockdep_is_held(&cgroup_mutex))
 			if (next->serial_nr > pos->serial_nr)
 				break;
 	}
@@ -4391,29 +4394,24 @@ static void css_task_iter_advance_css_set(struct css_task_iter *it)
 
 	lockdep_assert_held(&css_set_lock);
 
-	/* Advance to the next non-empty css_set */
-	do {
-		cset = css_task_iter_next_css_set(it);
-		if (!cset) {
-			it->task_pos = NULL;
-			return;
+	/* Advance to the next non-empty css_set and find first non-empty tasks list*/
+	while ((cset = css_task_iter_next_css_set(it))) {
+		if (!list_empty(&cset->tasks)) {
+			it->cur_tasks_head = &cset->tasks;
+			break;
+		} else if (!list_empty(&cset->mg_tasks)) {
+			it->cur_tasks_head = &cset->mg_tasks;
+			break;
+		} else if (!list_empty(&cset->dying_tasks)) {
+			it->cur_tasks_head = &cset->dying_tasks;
+			break;
 		}
-	} while (!css_set_populated(cset) && list_empty(&cset->dying_tasks));
-
-	if (!list_empty(&cset->tasks)) {
-		it->task_pos = cset->tasks.next;
-		it->cur_tasks_head = &cset->tasks;
-	} else if (!list_empty(&cset->mg_tasks)) {
-		it->task_pos = cset->mg_tasks.next;
-		it->cur_tasks_head = &cset->mg_tasks;
-	} else {
-		it->task_pos = cset->dying_tasks.next;
-		it->cur_tasks_head = &cset->dying_tasks;
 	}
-
-	it->tasks_head = &cset->tasks;
-	it->mg_tasks_head = &cset->mg_tasks;
-	it->dying_tasks_head = &cset->dying_tasks;
+	if (!cset) {
+		it->task_pos = NULL;
+		return;
+	}
+	it->task_pos = it->cur_tasks_head->next;
 
 	/*
 	 * We don't keep css_sets locked across iteration steps and thus
@@ -4458,24 +4456,24 @@ static void css_task_iter_advance(struct css_task_iter *it)
 repeat:
 	if (it->task_pos) {
 		/*
-		 * Advance iterator to find next entry.  cset->tasks is
-		 * consumed first and then ->mg_tasks.  After ->mg_tasks,
-		 * we move onto the next cset.
+		 * Advance iterator to find next entry. We go through cset
+		 * tasks, mg_tasks and dying_tasks, when consumed we move onto
+		 * the next cset.
 		 */
 		if (it->flags & CSS_TASK_ITER_SKIPPED)
 			it->flags &= ~CSS_TASK_ITER_SKIPPED;
 		else
 			it->task_pos = it->task_pos->next;
 
-		if (it->task_pos == it->tasks_head) {
-			it->task_pos = it->mg_tasks_head->next;
-			it->cur_tasks_head = it->mg_tasks_head;
+		if (it->task_pos == &it->cur_cset->tasks) {
+			it->cur_tasks_head = &it->cur_cset->mg_tasks;
+			it->task_pos = it->cur_tasks_head->next;
 		}
-		if (it->task_pos == it->mg_tasks_head) {
-			it->task_pos = it->dying_tasks_head->next;
-			it->cur_tasks_head = it->dying_tasks_head;
+		if (it->task_pos == &it->cur_cset->mg_tasks) {
+			it->cur_tasks_head = &it->cur_cset->dying_tasks;
+			it->task_pos = it->cur_tasks_head->next;
 		}
-		if (it->task_pos == it->dying_tasks_head)
+		if (it->task_pos == &it->cur_cset->dying_tasks)
 			css_task_iter_advance_css_set(it);
 	} else {
 		/* called from start, proceed to the first cset */
@@ -4493,12 +4491,12 @@ repeat:
 			goto repeat;
 
 		/* and dying leaders w/o live member threads */
-		if (it->cur_tasks_head == it->dying_tasks_head &&
+		if (it->cur_tasks_head == &it->cur_cset->dying_tasks &&
 		    !atomic_read(&task->signal->live))
 			goto repeat;
 	} else {
 		/* skip all dying ones */
-		if (it->cur_tasks_head == it->dying_tasks_head)
+		if (it->cur_tasks_head == &it->cur_cset->dying_tasks)
 			goto repeat;
 	}
 }
@@ -4662,13 +4660,28 @@ static int cgroup_procs_show(struct seq_file *s, void *v)
 	return 0;
 }
 
+static int cgroup_may_write(const struct cgroup *cgrp, struct super_block *sb)
+{
+	int ret;
+	struct inode *inode;
+
+	lockdep_assert_held(&cgroup_mutex);
+
+	inode = kernfs_get_inode(sb, cgrp->procs_file.kn);
+	if (!inode)
+		return -ENOMEM;
+
+	ret = inode_permission(inode, MAY_WRITE);
+	iput(inode);
+	return ret;
+}
+
 static int cgroup_procs_write_permission(struct cgroup *src_cgrp,
 					 struct cgroup *dst_cgrp,
 					 struct super_block *sb)
 {
 	struct cgroup_namespace *ns = current->nsproxy->cgroup_ns;
 	struct cgroup *com_cgrp = src_cgrp;
-	struct inode *inode;
 	int ret;
 
 	lockdep_assert_held(&cgroup_mutex);
@@ -4678,12 +4691,7 @@ static int cgroup_procs_write_permission(struct cgroup *src_cgrp,
 		com_cgrp = cgroup_parent(com_cgrp);
 
 	/* %current should be authorized to migrate to the common ancestor */
-	inode = kernfs_get_inode(sb, com_cgrp->procs_file.kn);
-	if (!inode)
-		return -ENOMEM;
-
-	ret = inode_permission(inode, MAY_WRITE);
-	iput(inode);
+	ret = cgroup_may_write(com_cgrp, sb);
 	if (ret)
 		return ret;
 
@@ -4699,6 +4707,26 @@ static int cgroup_procs_write_permission(struct cgroup *src_cgrp,
 	return 0;
 }
 
+static int cgroup_attach_permissions(struct cgroup *src_cgrp,
+				     struct cgroup *dst_cgrp,
+				     struct super_block *sb, bool threadgroup)
+{
+	int ret = 0;
+
+	ret = cgroup_procs_write_permission(src_cgrp, dst_cgrp, sb);
+	if (ret)
+		return ret;
+
+	ret = cgroup_migrate_vet_dst(dst_cgrp);
+	if (ret)
+		return ret;
+
+	if (!threadgroup && (src_cgrp->dom_cgrp != dst_cgrp->dom_cgrp))
+		ret = -EOPNOTSUPP;
+
+	return ret;
+}
+
 static ssize_t cgroup_procs_write(struct kernfs_open_file *of,
 				  char *buf, size_t nbytes, loff_t off)
 {
@@ -4721,8 +4749,8 @@ static ssize_t cgroup_procs_write(struct kernfs_open_file *of,
 	src_cgrp = task_cgroup_from_root(task, &cgrp_dfl_root);
 	spin_unlock_irq(&css_set_lock);
 
-	ret = cgroup_procs_write_permission(src_cgrp, dst_cgrp,
-					    of->file->f_path.dentry->d_sb);
+	ret = cgroup_attach_permissions(src_cgrp, dst_cgrp,
+					of->file->f_path.dentry->d_sb, true);
 	if (ret)
 		goto out_finish;
 
@@ -4766,16 +4794,11 @@ static ssize_t cgroup_threads_write(struct kernfs_open_file *of,
 	spin_unlock_irq(&css_set_lock);
 
 	/* thread migrations follow the cgroup.procs delegation rule */
-	ret = cgroup_procs_write_permission(src_cgrp, dst_cgrp,
-					    of->file->f_path.dentry->d_sb);
+	ret = cgroup_attach_permissions(src_cgrp, dst_cgrp,
+					of->file->f_path.dentry->d_sb, false);
 	if (ret)
 		goto out_finish;
 
-	/* and must be contained in the same domain */
-	ret = -EOPNOTSUPP;
-	if (src_cgrp->dom_cgrp != dst_cgrp->dom_cgrp)
-		goto out_finish;
-
 	ret = cgroup_attach_task(dst_cgrp, task, false);
 
 out_finish:
@@ -4851,7 +4874,6 @@ static struct cftype cgroup_base_files[] = {
 	},
 	{
 		.name = "cpu.stat",
-		.flags = CFTYPE_NOT_ON_ROOT,
 		.seq_show = cpu_stat_show,
 	},
 #ifdef CONFIG_PSI
@@ -5864,8 +5886,7 @@ out:
  * @child: pointer to task_struct of forking parent process.
  *
  * A task is associated with the init_css_set until cgroup_post_fork()
- * attaches it to the parent's css_set.  Empty cg_list indicates that
- * @child isn't holding reference to its css_set.
+ * attaches it to the target css_set.
  */
 void cgroup_fork(struct task_struct *child)
 {
@@ -5873,21 +5894,172 @@ void cgroup_fork(struct task_struct *child)
 	INIT_LIST_HEAD(&child->cg_list);
 }
 
+static struct cgroup *cgroup_get_from_file(struct file *f)
+{
+	struct cgroup_subsys_state *css;
+	struct cgroup *cgrp;
+
+	css = css_tryget_online_from_dir(f->f_path.dentry, NULL);
+	if (IS_ERR(css))
+		return ERR_CAST(css);
+
+	cgrp = css->cgroup;
+	if (!cgroup_on_dfl(cgrp)) {
+		cgroup_put(cgrp);
+		return ERR_PTR(-EBADF);
+	}
+
+	return cgrp;
+}
+
+/**
+ * cgroup_css_set_fork - find or create a css_set for a child process
+ * @kargs: the arguments passed to create the child process
+ *
+ * This functions finds or creates a new css_set which the child
+ * process will be attached to in cgroup_post_fork(). By default,
+ * the child process will be given the same css_set as its parent.
+ *
+ * If CLONE_INTO_CGROUP is specified this function will try to find an
+ * existing css_set which includes the requested cgroup and if not create
+ * a new css_set that the child will be attached to later. If this function
+ * succeeds it will hold cgroup_threadgroup_rwsem on return. If
+ * CLONE_INTO_CGROUP is requested this function will grab cgroup mutex
+ * before grabbing cgroup_threadgroup_rwsem and will hold a reference
+ * to the target cgroup.
+ */
+static int cgroup_css_set_fork(struct kernel_clone_args *kargs)
+	__acquires(&cgroup_mutex) __acquires(&cgroup_threadgroup_rwsem)
+{
+	int ret;
+	struct cgroup *dst_cgrp = NULL;
+	struct css_set *cset;
+	struct super_block *sb;
+	struct file *f;
+
+	if (kargs->flags & CLONE_INTO_CGROUP)
+		mutex_lock(&cgroup_mutex);
+
+	cgroup_threadgroup_change_begin(current);
+
+	spin_lock_irq(&css_set_lock);
+	cset = task_css_set(current);
+	get_css_set(cset);
+	spin_unlock_irq(&css_set_lock);
+
+	if (!(kargs->flags & CLONE_INTO_CGROUP)) {
+		kargs->cset = cset;
+		return 0;
+	}
+
+	f = fget_raw(kargs->cgroup);
+	if (!f) {
+		ret = -EBADF;
+		goto err;
+	}
+	sb = f->f_path.dentry->d_sb;
+
+	dst_cgrp = cgroup_get_from_file(f);
+	if (IS_ERR(dst_cgrp)) {
+		ret = PTR_ERR(dst_cgrp);
+		dst_cgrp = NULL;
+		goto err;
+	}
+
+	if (cgroup_is_dead(dst_cgrp)) {
+		ret = -ENODEV;
+		goto err;
+	}
+
+	/*
+	 * Verify that we the target cgroup is writable for us. This is
+	 * usually done by the vfs layer but since we're not going through
+	 * the vfs layer here we need to do it "manually".
+	 */
+	ret = cgroup_may_write(dst_cgrp, sb);
+	if (ret)
+		goto err;
+
+	ret = cgroup_attach_permissions(cset->dfl_cgrp, dst_cgrp, sb,
+					!(kargs->flags & CLONE_THREAD));
+	if (ret)
+		goto err;
+
+	kargs->cset = find_css_set(cset, dst_cgrp);
+	if (!kargs->cset) {
+		ret = -ENOMEM;
+		goto err;
+	}
+
+	put_css_set(cset);
+	fput(f);
+	kargs->cgrp = dst_cgrp;
+	return ret;
+
+err:
+	cgroup_threadgroup_change_end(current);
+	mutex_unlock(&cgroup_mutex);
+	if (f)
+		fput(f);
+	if (dst_cgrp)
+		cgroup_put(dst_cgrp);
+	put_css_set(cset);
+	if (kargs->cset)
+		put_css_set(kargs->cset);
+	return ret;
+}
+
+/**
+ * cgroup_css_set_put_fork - drop references we took during fork
+ * @kargs: the arguments passed to create the child process
+ *
+ * Drop references to the prepared css_set and target cgroup if
+ * CLONE_INTO_CGROUP was requested.
+ */
+static void cgroup_css_set_put_fork(struct kernel_clone_args *kargs)
+	__releases(&cgroup_threadgroup_rwsem) __releases(&cgroup_mutex)
+{
+	cgroup_threadgroup_change_end(current);
+
+	if (kargs->flags & CLONE_INTO_CGROUP) {
+		struct cgroup *cgrp = kargs->cgrp;
+		struct css_set *cset = kargs->cset;
+
+		mutex_unlock(&cgroup_mutex);
+
+		if (cset) {
+			put_css_set(cset);
+			kargs->cset = NULL;
+		}
+
+		if (cgrp) {
+			cgroup_put(cgrp);
+			kargs->cgrp = NULL;
+		}
+	}
+}
+
 /**
  * cgroup_can_fork - called on a new task before the process is exposed
- * @child: the task in question.
+ * @child: the child process
  *
- * This calls the subsystem can_fork() callbacks. If the can_fork() callback
- * returns an error, the fork aborts with that error code. This allows for
- * a cgroup subsystem to conditionally allow or deny new forks.
+ * This prepares a new css_set for the child process which the child will
+ * be attached to in cgroup_post_fork().
+ * This calls the subsystem can_fork() callbacks. If the cgroup_can_fork()
+ * callback returns an error, the fork aborts with that error code. This
+ * allows for a cgroup subsystem to conditionally allow or deny new forks.
  */
-int cgroup_can_fork(struct task_struct *child)
+int cgroup_can_fork(struct task_struct *child, struct kernel_clone_args *kargs)
 {
 	struct cgroup_subsys *ss;
 	int i, j, ret;
 
+	ret = cgroup_css_set_fork(kargs);
+	if (ret)
+		return ret;
+
 	do_each_subsys_mask(ss, i, have_canfork_callback) {
-		ret = ss->can_fork(child);
+		ret = ss->can_fork(child, kargs->cset);
 		if (ret)
 			goto out_revert;
 	} while_each_subsys_mask();
@@ -5899,54 +6071,64 @@ out_revert:
 		if (j >= i)
 			break;
 		if (ss->cancel_fork)
-			ss->cancel_fork(child);
+			ss->cancel_fork(child, kargs->cset);
 	}
 
+	cgroup_css_set_put_fork(kargs);
+
 	return ret;
 }
 
 /**
  * cgroup_cancel_fork - called if a fork failed after cgroup_can_fork()
- * @child: the task in question
+ * @child: the child process
+ * @kargs: the arguments passed to create the child process
  *
  * This calls the cancel_fork() callbacks if a fork failed *after*
- * cgroup_can_fork() succeded.
+ * cgroup_can_fork() succeded and cleans up references we took to
+ * prepare a new css_set for the child process in cgroup_can_fork().
  */
-void cgroup_cancel_fork(struct task_struct *child)
+void cgroup_cancel_fork(struct task_struct *child,
+			struct kernel_clone_args *kargs)
 {
 	struct cgroup_subsys *ss;
 	int i;
 
 	for_each_subsys(ss, i)
 		if (ss->cancel_fork)
-			ss->cancel_fork(child);
+			ss->cancel_fork(child, kargs->cset);
+
+	cgroup_css_set_put_fork(kargs);
 }
 
 /**
- * cgroup_post_fork - called on a new task after adding it to the task list
- * @child: the task in question
- *
- * Adds the task to the list running through its css_set if necessary and
- * call the subsystem fork() callbacks.  Has to be after the task is
- * visible on the task list in case we race with the first call to
- * cgroup_task_iter_start() - to guarantee that the new task ends up on its
- * list.
+ * cgroup_post_fork - finalize cgroup setup for the child process
+ * @child: the child process
+ *
+ * Attach the child process to its css_set calling the subsystem fork()
+ * callbacks.
  */
-void cgroup_post_fork(struct task_struct *child)
+void cgroup_post_fork(struct task_struct *child,
+		      struct kernel_clone_args *kargs)
+	__releases(&cgroup_threadgroup_rwsem) __releases(&cgroup_mutex)
 {
 	struct cgroup_subsys *ss;
 	struct css_set *cset;
 	int i;
 
+	cset = kargs->cset;
+	kargs->cset = NULL;
+
 	spin_lock_irq(&css_set_lock);
 
 	/* init tasks are special, only link regular threads */
 	if (likely(child->pid)) {
 		WARN_ON_ONCE(!list_empty(&child->cg_list));
-		cset = task_css_set(current); /* current is @child's parent */
-		get_css_set(cset);
 		cset->nr_tasks++;
 		css_set_move_task(child, NULL, cset, false);
+	} else {
+		put_css_set(cset);
+		cset = NULL;
 	}
 
 	/*
@@ -5978,6 +6160,17 @@ void cgroup_post_fork(struct task_struct *child)
 	do_each_subsys_mask(ss, i, have_fork_callback) {
 		ss->fork(child);
 	} while_each_subsys_mask();
+
+	/* Make the new cset the root_cset of the new cgroup namespace. */
+	if (kargs->flags & CLONE_NEWCGROUP) {
+		struct css_set *rcset = child->nsproxy->cgroup_ns->root_cset;
+
+		get_css_set(cset);
+		child->nsproxy->cgroup_ns->root_cset = cset;
+		put_css_set(rcset);
+	}
+
+	cgroup_css_set_put_fork(kargs);
 }
 
 /**
@@ -6164,7 +6357,6 @@ EXPORT_SYMBOL_GPL(cgroup_get_from_path);
  */
 struct cgroup *cgroup_get_from_fd(int fd)
 {
-	struct cgroup_subsys_state *css;
 	struct cgroup *cgrp;
 	struct file *f;
 
@@ -6172,17 +6364,8 @@ struct cgroup *cgroup_get_from_fd(int fd)
 	if (!f)
 		return ERR_PTR(-EBADF);
 
-	css = css_tryget_online_from_dir(f->f_path.dentry, NULL);
+	cgrp = cgroup_get_from_file(f);
 	fput(f);
-	if (IS_ERR(css))
-		return ERR_CAST(css);
-
-	cgrp = css->cgroup;
-	if (!cgroup_on_dfl(cgrp)) {
-		cgroup_put(cgrp);
-		return ERR_PTR(-EBADF);
-	}
-
 	return cgrp;
 }
 EXPORT_SYMBOL_GPL(cgroup_get_from_fd);
@@ -6256,18 +6439,8 @@ void cgroup_sk_alloc_disable(void)
 
 void cgroup_sk_alloc(struct sock_cgroup_data *skcd)
 {
-	if (cgroup_sk_alloc_disabled)
-		return;
-
-	/* Socket clone path */
-	if (skcd->val) {
-		/*
-		 * We might be cloning a socket which is left in an empty
-		 * cgroup and the cgroup might have already been rmdir'd.
-		 * Don't use cgroup_get_live().
-		 */
-		cgroup_get(sock_cgroup_ptr(skcd));
-		cgroup_bpf_get(sock_cgroup_ptr(skcd));
+	if (cgroup_sk_alloc_disabled) {
+		skcd->no_refcnt = 1;
 		return;
 	}
 
@@ -6292,10 +6465,27 @@ void cgroup_sk_alloc(struct sock_cgroup_data *skcd)
 	rcu_read_unlock();
 }
 
+void cgroup_sk_clone(struct sock_cgroup_data *skcd)
+{
+	if (skcd->val) {
+		if (skcd->no_refcnt)
+			return;
+		/*
+		 * We might be cloning a socket which is left in an empty
+		 * cgroup and the cgroup might have already been rmdir'd.
+		 * Don't use cgroup_get_live().
+		 */
+		cgroup_get(sock_cgroup_ptr(skcd));
+		cgroup_bpf_get(sock_cgroup_ptr(skcd));
+	}
+}
+
 void cgroup_sk_free(struct sock_cgroup_data *skcd)
 {
 	struct cgroup *cgrp = sock_cgroup_ptr(skcd);
 
+	if (skcd->no_refcnt)
+		return;
 	cgroup_bpf_put(cgrp);
 	cgroup_put(cgrp);
 }
@@ -6303,27 +6493,31 @@ void cgroup_sk_free(struct sock_cgroup_data *skcd)
 #endif	/* CONFIG_SOCK_CGROUP_DATA */
 
 #ifdef CONFIG_CGROUP_BPF
-int cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog,
-		      struct bpf_prog *replace_prog, enum bpf_attach_type type,
+int cgroup_bpf_attach(struct cgroup *cgrp,
+		      struct bpf_prog *prog, struct bpf_prog *replace_prog,
+		      struct bpf_cgroup_link *link,
+		      enum bpf_attach_type type,
 		      u32 flags)
 {
 	int ret;
 
 	mutex_lock(&cgroup_mutex);
-	ret = __cgroup_bpf_attach(cgrp, prog, replace_prog, type, flags);
+	ret = __cgroup_bpf_attach(cgrp, prog, replace_prog, link, type, flags);
 	mutex_unlock(&cgroup_mutex);
 	return ret;
 }
+
 int cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog,
-		      enum bpf_attach_type type, u32 flags)
+		      enum bpf_attach_type type)
 {
 	int ret;
 
 	mutex_lock(&cgroup_mutex);
-	ret = __cgroup_bpf_detach(cgrp, prog, type);
+	ret = __cgroup_bpf_detach(cgrp, prog, NULL, type);
 	mutex_unlock(&cgroup_mutex);
 	return ret;
 }
+
 int cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr,
 		     union bpf_attr __user *uattr)
 {
@@ -6381,7 +6575,10 @@ static struct kobj_attribute cgroup_delegate_attr = __ATTR_RO(delegate);
 static ssize_t features_show(struct kobject *kobj, struct kobj_attribute *attr,
 			     char *buf)
 {
-	return snprintf(buf, PAGE_SIZE, "nsdelegate\nmemory_localevents\n");
+	return snprintf(buf, PAGE_SIZE,
+			"nsdelegate\n"
+			"memory_localevents\n"
+			"memory_recursiveprot\n");
 }
 static struct kobj_attribute cgroup_features_attr = __ATTR_RO(features);
 
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index 58f5073acff7..642415b8c3c9 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -358,8 +358,12 @@ static DECLARE_WORK(cpuset_hotplug_work, cpuset_hotplug_workfn);
 static DECLARE_WAIT_QUEUE_HEAD(cpuset_attach_wq);
 
 /*
- * Cgroup v2 behavior is used when on default hierarchy or the
- * cgroup_v2_mode flag is set.
+ * Cgroup v2 behavior is used on the "cpus" and "mems" control files when
+ * on default hierarchy or when the cpuset_v2_mode flag is set by mounting
+ * the v1 cpuset cgroup filesystem with the "cpuset_v2_mode" mount option.
+ * With v2 behavior, "cpus" and "mems" are always what the users have
+ * requested and won't be changed by hotplug events. Only the effective
+ * cpus or mems will be affected.
  */
 static inline bool is_in_v2_mode(void)
 {
@@ -1651,7 +1655,7 @@ static void update_tasks_nodemask(struct cpuset *cs)
 	guarantee_online_mems(cs, &newmems);
 
 	/*
-	 * The mpol_rebind_mm() call takes mmap_sem, which we couldn't
+	 * The mpol_rebind_mm() call takes mmap_lock, which we couldn't
 	 * take while holding tasklist_lock.  Forks can happen - the
 	 * mpol_dup() cpuset_being_rebound check will catch such forks,
 	 * and rebind their vma mempolicies too.  Because we still hold
@@ -1756,7 +1760,7 @@ static void update_nodemasks_hier(struct cpuset *cs, nodemask_t *new_mems)
  *
  * Call with cpuset_mutex held. May take callback_lock during call.
  * Will take tasklist_lock, scan tasklist for tasks in cpuset cs,
- * lock each such tasks mm->mmap_sem, scan its vma's and rebind
+ * lock each such tasks mm->mmap_lock, scan its vma's and rebind
  * their mempolicies to the cpusets new mems_allowed.
  */
 static int update_nodemask(struct cpuset *cs, struct cpuset *trialcs,
diff --git a/kernel/cgroup/namespace.c b/kernel/cgroup/namespace.c
index b05f1dd58a62..812a61afd538 100644
--- a/kernel/cgroup/namespace.c
+++ b/kernel/cgroup/namespace.c
@@ -95,11 +95,12 @@ static inline struct cgroup_namespace *to_cg_ns(struct ns_common *ns)
 	return container_of(ns, struct cgroup_namespace, ns);
 }
 
-static int cgroupns_install(struct nsproxy *nsproxy, struct ns_common *ns)
+static int cgroupns_install(struct nsset *nsset, struct ns_common *ns)
 {
+	struct nsproxy *nsproxy = nsset->nsproxy;
 	struct cgroup_namespace *cgroup_ns = to_cg_ns(ns);
 
-	if (!ns_capable(current_user_ns(), CAP_SYS_ADMIN) ||
+	if (!ns_capable(nsset->cred->user_ns, CAP_SYS_ADMIN) ||
 	    !ns_capable(cgroup_ns->user_ns, CAP_SYS_ADMIN))
 		return -EPERM;
 
diff --git a/kernel/cgroup/pids.c b/kernel/cgroup/pids.c
index 138059eb730d..511af87f685e 100644
--- a/kernel/cgroup/pids.c
+++ b/kernel/cgroup/pids.c
@@ -33,6 +33,7 @@
 #include <linux/atomic.h>
 #include <linux/cgroup.h>
 #include <linux/slab.h>
+#include <linux/sched/task.h>
 
 #define PIDS_MAX (PID_MAX_LIMIT + 1ULL)
 #define PIDS_MAX_STR "max"
@@ -214,13 +215,16 @@ static void pids_cancel_attach(struct cgroup_taskset *tset)
  * task_css_check(true) in pids_can_fork() and pids_cancel_fork() relies
  * on cgroup_threadgroup_change_begin() held by the copy_process().
  */
-static int pids_can_fork(struct task_struct *task)
+static int pids_can_fork(struct task_struct *task, struct css_set *cset)
 {
 	struct cgroup_subsys_state *css;
 	struct pids_cgroup *pids;
 	int err;
 
-	css = task_css_check(current, pids_cgrp_id, true);
+	if (cset)
+		css = cset->subsys[pids_cgrp_id];
+	else
+		css = task_css_check(current, pids_cgrp_id, true);
 	pids = css_pids(css);
 	err = pids_try_charge(pids, 1);
 	if (err) {
@@ -235,12 +239,15 @@ static int pids_can_fork(struct task_struct *task)
 	return err;
 }
 
-static void pids_cancel_fork(struct task_struct *task)
+static void pids_cancel_fork(struct task_struct *task, struct css_set *cset)
 {
 	struct cgroup_subsys_state *css;
 	struct pids_cgroup *pids;
 
-	css = task_css_check(current, pids_cgrp_id, true);
+	if (cset)
+		css = cset->subsys[pids_cgrp_id];
+	else
+		css = task_css_check(current, pids_cgrp_id, true);
 	pids = css_pids(css);
 	pids_uncharge(pids, 1);
 }
diff --git a/kernel/cgroup/rstat.c b/kernel/cgroup/rstat.c
index 6f87352f8219..d51175cedfca 100644
--- a/kernel/cgroup/rstat.c
+++ b/kernel/cgroup/rstat.c
@@ -33,12 +33,9 @@ void cgroup_rstat_updated(struct cgroup *cgrp, int cpu)
 		return;
 
 	/*
-	 * Paired with the one in cgroup_rstat_cpu_pop_updated().  Either we
-	 * see NULL updated_next or they see our updated stat.
-	 */
-	smp_mb();
-
-	/*
+	 * Speculative already-on-list test. This may race leading to
+	 * temporary inaccuracies, which is fine.
+	 *
 	 * Because @parent's updated_children is terminated with @parent
 	 * instead of NULL, we can tell whether @cgrp is on the list by
 	 * testing the next pointer for NULL.
@@ -67,7 +64,6 @@ void cgroup_rstat_updated(struct cgroup *cgrp, int cpu)
 
 	raw_spin_unlock_irqrestore(cpu_lock, flags);
 }
-EXPORT_SYMBOL_GPL(cgroup_rstat_updated);
 
 /**
  * cgroup_rstat_cpu_pop_updated - iterate and dismantle rstat_cpu updated tree
@@ -134,13 +130,6 @@ static struct cgroup *cgroup_rstat_cpu_pop_updated(struct cgroup *pos,
 		*nextp = rstatc->updated_next;
 		rstatc->updated_next = NULL;
 
-		/*
-		 * Paired with the one in cgroup_rstat_cpu_updated().
-		 * Either they see NULL updated_next or we see their
-		 * updated stat.
-		 */
-		smp_mb();
-
 		return pos;
 	}
 
@@ -399,18 +388,62 @@ void __cgroup_account_cputime_field(struct cgroup *cgrp,
 	cgroup_base_stat_cputime_account_end(cgrp, rstatc);
 }
 
+/*
+ * compute the cputime for the root cgroup by getting the per cpu data
+ * at a global level, then categorizing the fields in a manner consistent
+ * with how it is done by __cgroup_account_cputime_field for each bit of
+ * cpu time attributed to a cgroup.
+ */
+static void root_cgroup_cputime(struct task_cputime *cputime)
+{
+	int i;
+
+	cputime->stime = 0;
+	cputime->utime = 0;
+	cputime->sum_exec_runtime = 0;
+	for_each_possible_cpu(i) {
+		struct kernel_cpustat kcpustat;
+		u64 *cpustat = kcpustat.cpustat;
+		u64 user = 0;
+		u64 sys = 0;
+
+		kcpustat_cpu_fetch(&kcpustat, i);
+
+		user += cpustat[CPUTIME_USER];
+		user += cpustat[CPUTIME_NICE];
+		cputime->utime += user;
+
+		sys += cpustat[CPUTIME_SYSTEM];
+		sys += cpustat[CPUTIME_IRQ];
+		sys += cpustat[CPUTIME_SOFTIRQ];
+		cputime->stime += sys;
+
+		cputime->sum_exec_runtime += user;
+		cputime->sum_exec_runtime += sys;
+		cputime->sum_exec_runtime += cpustat[CPUTIME_STEAL];
+		cputime->sum_exec_runtime += cpustat[CPUTIME_GUEST];
+		cputime->sum_exec_runtime += cpustat[CPUTIME_GUEST_NICE];
+	}
+}
+
 void cgroup_base_stat_cputime_show(struct seq_file *seq)
 {
 	struct cgroup *cgrp = seq_css(seq)->cgroup;
 	u64 usage, utime, stime;
-
-	if (!cgroup_parent(cgrp))
-		return;
-
-	cgroup_rstat_flush_hold(cgrp);
-	usage = cgrp->bstat.cputime.sum_exec_runtime;
-	cputime_adjust(&cgrp->bstat.cputime, &cgrp->prev_cputime, &utime, &stime);
-	cgroup_rstat_flush_release();
+	struct task_cputime cputime;
+
+	if (cgroup_parent(cgrp)) {
+		cgroup_rstat_flush_hold(cgrp);
+		usage = cgrp->bstat.cputime.sum_exec_runtime;
+		cputime_adjust(&cgrp->bstat.cputime, &cgrp->prev_cputime,
+			       &utime, &stime);
+		cgroup_rstat_flush_release();
+	} else {
+		root_cgroup_cputime(&cputime);
+		usage = cputime.sum_exec_runtime;
+		utime = cputime.utime;
+		stime = cputime.stime;
+	}
 
 	do_div(usage, NSEC_PER_USEC);
 	do_div(utime, NSEC_PER_USEC);
diff --git a/kernel/compat.c b/kernel/compat.c
index 843dd17e6078..05adfd6fa8bf 100644
--- a/kernel/compat.c
+++ b/kernel/compat.c
@@ -199,7 +199,7 @@ long compat_get_bitmap(unsigned long *mask, const compat_ulong_t __user *umask,
 	bitmap_size = ALIGN(bitmap_size, BITS_PER_COMPAT_LONG);
 	nr_compat_longs = BITS_TO_COMPAT_LONGS(bitmap_size);
 
-	if (!user_access_begin(umask, bitmap_size / 8))
+	if (!user_read_access_begin(umask, bitmap_size / 8))
 		return -EFAULT;
 
 	while (nr_compat_longs > 1) {
@@ -211,11 +211,11 @@ long compat_get_bitmap(unsigned long *mask, const compat_ulong_t __user *umask,
 	}
 	if (nr_compat_longs)
 		unsafe_get_user(*mask, umask++, Efault);
-	user_access_end();
+	user_read_access_end();
 	return 0;
 
 Efault:
-	user_access_end();
+	user_read_access_end();
 	return -EFAULT;
 }
 
@@ -228,7 +228,7 @@ long compat_put_bitmap(compat_ulong_t __user *umask, unsigned long *mask,
 	bitmap_size = ALIGN(bitmap_size, BITS_PER_COMPAT_LONG);
 	nr_compat_longs = BITS_TO_COMPAT_LONGS(bitmap_size);
 
-	if (!user_access_begin(umask, bitmap_size / 8))
+	if (!user_write_access_begin(umask, bitmap_size / 8))
 		return -EFAULT;
 
 	while (nr_compat_longs > 1) {
@@ -239,10 +239,10 @@ long compat_put_bitmap(compat_ulong_t __user *umask, unsigned long *mask,
 	}
 	if (nr_compat_longs)
 		unsafe_put_user((compat_ulong_t)*mask, umask++, Efault);
-	user_access_end();
+	user_write_access_end();
 	return 0;
 Efault:
-	user_access_end();
+	user_write_access_end();
 	return -EFAULT;
 }
 
@@ -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/configs/tiny.config b/kernel/configs/tiny.config
index 7fa0c4ae6394..8a44b93da0f3 100644
--- a/kernel/configs/tiny.config
+++ b/kernel/configs/tiny.config
@@ -6,7 +6,6 @@ CONFIG_CC_OPTIMIZE_FOR_SIZE=y
 CONFIG_KERNEL_XZ=y
 # CONFIG_KERNEL_LZO is not set
 # CONFIG_KERNEL_LZ4 is not set
-CONFIG_OPTIMIZE_INLINING=y
 # CONFIG_SLAB is not set
 # CONFIG_SLUB is not set
 CONFIG_SLOB=y
diff --git a/kernel/context_tracking.c b/kernel/context_tracking.c
index 0296b4bda8f1..36a98c48aedc 100644
--- a/kernel/context_tracking.c
+++ b/kernel/context_tracking.c
@@ -31,7 +31,7 @@ EXPORT_SYMBOL_GPL(context_tracking_key);
 DEFINE_PER_CPU(struct context_tracking, context_tracking);
 EXPORT_SYMBOL_GPL(context_tracking);
 
-static bool context_tracking_recursion_enter(void)
+static noinstr bool context_tracking_recursion_enter(void)
 {
 	int recursion;
 
@@ -45,7 +45,7 @@ static bool context_tracking_recursion_enter(void)
 	return false;
 }
 
-static void context_tracking_recursion_exit(void)
+static __always_inline void context_tracking_recursion_exit(void)
 {
 	__this_cpu_dec(context_tracking.recursion);
 }
@@ -59,7 +59,7 @@ static void context_tracking_recursion_exit(void)
  * instructions to execute won't use any RCU read side critical section
  * because this function sets RCU in extended quiescent state.
  */
-void __context_tracking_enter(enum ctx_state state)
+void noinstr __context_tracking_enter(enum ctx_state state)
 {
 	/* Kernel threads aren't supposed to go to userspace */
 	WARN_ON_ONCE(!current->mm);
@@ -77,8 +77,10 @@ void __context_tracking_enter(enum ctx_state state)
 			 * on the tick.
 			 */
 			if (state == CONTEXT_USER) {
+				instrumentation_begin();
 				trace_user_enter(0);
 				vtime_user_enter(current);
+				instrumentation_end();
 			}
 			rcu_user_enter();
 		}
@@ -99,7 +101,6 @@ void __context_tracking_enter(enum ctx_state state)
 	}
 	context_tracking_recursion_exit();
 }
-NOKPROBE_SYMBOL(__context_tracking_enter);
 EXPORT_SYMBOL_GPL(__context_tracking_enter);
 
 void context_tracking_enter(enum ctx_state state)
@@ -142,7 +143,7 @@ NOKPROBE_SYMBOL(context_tracking_user_enter);
  * This call supports re-entrancy. This way it can be called from any exception
  * handler without needing to know if we came from userspace or not.
  */
-void __context_tracking_exit(enum ctx_state state)
+void noinstr __context_tracking_exit(enum ctx_state state)
 {
 	if (!context_tracking_recursion_enter())
 		return;
@@ -155,15 +156,16 @@ void __context_tracking_exit(enum ctx_state state)
 			 */
 			rcu_user_exit();
 			if (state == CONTEXT_USER) {
+				instrumentation_begin();
 				vtime_user_exit(current);
 				trace_user_exit(0);
+				instrumentation_end();
 			}
 		}
 		__this_cpu_write(context_tracking.state, CONTEXT_KERNEL);
 	}
 	context_tracking_recursion_exit();
 }
-NOKPROBE_SYMBOL(__context_tracking_exit);
 EXPORT_SYMBOL_GPL(__context_tracking_exit);
 
 void context_tracking_exit(enum ctx_state state)
@@ -198,11 +200,13 @@ void __init context_tracking_cpu_set(int cpu)
 	if (initialized)
 		return;
 
+#ifdef CONFIG_HAVE_TIF_NOHZ
 	/*
 	 * Set TIF_NOHZ to init/0 and let it propagate to all tasks through fork
 	 * This assumes that init is the only task at this early boot stage.
 	 */
 	set_tsk_thread_flag(&init_task, TIF_NOHZ);
+#endif
 	WARN_ON_ONCE(!tasklist_empty());
 
 	initialized = true;
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 9c706af713fb..6ff2578ecf17 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -3,6 +3,7 @@
  *
  * This code is licenced under the GPL.
  */
+#include <linux/sched/mm.h>
 #include <linux/proc_fs.h>
 #include <linux/smp.h>
 #include <linux/init.h>
@@ -331,12 +332,12 @@ void lockdep_assert_cpus_held(void)
 
 static void lockdep_acquire_cpus_lock(void)
 {
-	rwsem_acquire(&cpu_hotplug_lock.rw_sem.dep_map, 0, 0, _THIS_IP_);
+	rwsem_acquire(&cpu_hotplug_lock.dep_map, 0, 0, _THIS_IP_);
 }
 
 static void lockdep_release_cpus_lock(void)
 {
-	rwsem_release(&cpu_hotplug_lock.rw_sem.dep_map, _THIS_IP_);
+	rwsem_release(&cpu_hotplug_lock.dep_map, _THIS_IP_);
 }
 
 /*
@@ -432,7 +433,7 @@ static inline bool cpu_smt_allowed(unsigned int cpu)
 	/*
 	 * On x86 it's required to boot all logical CPUs at least once so
 	 * that the init code can get a chance to set CR4.MCE on each
-	 * CPU. Otherwise, a broadacasted MCE observing CR4.MCE=0b on any
+	 * CPU. Otherwise, a broadcasted MCE observing CR4.MCE=0b on any
 	 * core will shutdown the machine.
 	 */
 	return !cpumask_test_cpu(cpu, &cpus_booted_once_mask);
@@ -564,6 +565,21 @@ static int bringup_cpu(unsigned int cpu)
 	return bringup_wait_for_ap(cpu);
 }
 
+static int finish_cpu(unsigned int cpu)
+{
+	struct task_struct *idle = idle_thread_get(cpu);
+	struct mm_struct *mm = idle->active_mm;
+
+	/*
+	 * idle_task_exit() will have switched to &init_mm, now
+	 * clean up any remaining active_mm state.
+	 */
+	if (mm != &init_mm)
+		idle->active_mm = &init_mm;
+	mmdrop(mm);
+	return 0;
+}
+
 /*
  * Hotplug state machine related functions
  */
@@ -1041,7 +1057,7 @@ static int cpu_down_maps_locked(unsigned int cpu, enum cpuhp_state target)
 	return _cpu_down(cpu, 0, target);
 }
 
-static int do_cpu_down(unsigned int cpu, enum cpuhp_state target)
+static int cpu_down(unsigned int cpu, enum cpuhp_state target)
 {
 	int err;
 
@@ -1051,11 +1067,72 @@ static int do_cpu_down(unsigned int cpu, enum cpuhp_state target)
 	return err;
 }
 
-int cpu_down(unsigned int cpu)
+/**
+ * cpu_device_down - Bring down a cpu device
+ * @dev: Pointer to the cpu device to offline
+ *
+ * This function is meant to be used by device core cpu subsystem only.
+ *
+ * Other subsystems should use remove_cpu() instead.
+ */
+int cpu_device_down(struct device *dev)
+{
+	return cpu_down(dev->id, CPUHP_OFFLINE);
+}
+
+int remove_cpu(unsigned int cpu)
 {
-	return do_cpu_down(cpu, CPUHP_OFFLINE);
+	int ret;
+
+	lock_device_hotplug();
+	ret = device_offline(get_cpu_device(cpu));
+	unlock_device_hotplug();
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(remove_cpu);
+
+void smp_shutdown_nonboot_cpus(unsigned int primary_cpu)
+{
+	unsigned int cpu;
+	int error;
+
+	cpu_maps_update_begin();
+
+	/*
+	 * Make certain the cpu I'm about to reboot on is online.
+	 *
+	 * This is inline to what migrate_to_reboot_cpu() already do.
+	 */
+	if (!cpu_online(primary_cpu))
+		primary_cpu = cpumask_first(cpu_online_mask);
+
+	for_each_online_cpu(cpu) {
+		if (cpu == primary_cpu)
+			continue;
+
+		error = cpu_down_maps_locked(cpu, CPUHP_OFFLINE);
+		if (error) {
+			pr_err("Failed to offline CPU%d - error=%d",
+				cpu, error);
+			break;
+		}
+	}
+
+	/*
+	 * Ensure all but the reboot CPU are offline.
+	 */
+	BUG_ON(num_online_cpus() > 1);
+
+	/*
+	 * Make sure the CPUs won't be enabled by someone else after this
+	 * point. Kexec will reboot to a new kernel shortly resetting
+	 * everything along the way.
+	 */
+	cpu_hotplug_disabled++;
+
+	cpu_maps_update_done();
 }
-EXPORT_SYMBOL(cpu_down);
 
 #else
 #define takedown_cpu		NULL
@@ -1124,8 +1201,8 @@ static int _cpu_up(unsigned int cpu, int tasks_frozen, enum cpuhp_state target)
 	}
 
 	/*
-	 * The caller of do_cpu_up might have raced with another
-	 * caller. Ignore it for now.
+	 * The caller of cpu_up() might have raced with another
+	 * caller. Nothing to do.
 	 */
 	if (st->state >= target)
 		goto out;
@@ -1169,7 +1246,7 @@ out:
 	return ret;
 }
 
-static int do_cpu_up(unsigned int cpu, enum cpuhp_state target)
+static int cpu_up(unsigned int cpu, enum cpuhp_state target)
 {
 	int err = 0;
 
@@ -1203,11 +1280,65 @@ out:
 	return err;
 }
 
-int cpu_up(unsigned int cpu)
+/**
+ * cpu_device_up - Bring up a cpu device
+ * @dev: Pointer to the cpu device to online
+ *
+ * This function is meant to be used by device core cpu subsystem only.
+ *
+ * Other subsystems should use add_cpu() instead.
+ */
+int cpu_device_up(struct device *dev)
+{
+	return cpu_up(dev->id, CPUHP_ONLINE);
+}
+
+int add_cpu(unsigned int cpu)
 {
-	return do_cpu_up(cpu, CPUHP_ONLINE);
+	int ret;
+
+	lock_device_hotplug();
+	ret = device_online(get_cpu_device(cpu));
+	unlock_device_hotplug();
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(add_cpu);
+
+/**
+ * bringup_hibernate_cpu - Bring up the CPU that we hibernated on
+ * @sleep_cpu: The cpu we hibernated on and should be brought up.
+ *
+ * On some architectures like arm64, we can hibernate on any CPU, but on
+ * wake up the CPU we hibernated on might be offline as a side effect of
+ * using maxcpus= for example.
+ */
+int bringup_hibernate_cpu(unsigned int sleep_cpu)
+{
+	int ret;
+
+	if (!cpu_online(sleep_cpu)) {
+		pr_info("Hibernated on a CPU that is offline! Bringing CPU up.\n");
+		ret = cpu_up(sleep_cpu, CPUHP_ONLINE);
+		if (ret) {
+			pr_err("Failed to bring hibernate-CPU up!\n");
+			return ret;
+		}
+	}
+	return 0;
+}
+
+void bringup_nonboot_cpus(unsigned int setup_max_cpus)
+{
+	unsigned int cpu;
+
+	for_each_present_cpu(cpu) {
+		if (num_online_cpus() >= setup_max_cpus)
+			break;
+		if (!cpu_online(cpu))
+			cpu_up(cpu, CPUHP_ONLINE);
+	}
 }
-EXPORT_SYMBOL_GPL(cpu_up);
 
 #ifdef CONFIG_PM_SLEEP_SMP
 static cpumask_var_t frozen_cpus;
@@ -1261,8 +1392,8 @@ int freeze_secondary_cpus(int primary)
 
 	/*
 	 * Make sure the CPUs won't be enabled by someone else. We need to do
-	 * this even in case of failure as all disable_nonboot_cpus() users are
-	 * supposed to do enable_nonboot_cpus() on the failure path.
+	 * this even in case of failure as all freeze_secondary_cpus() users are
+	 * supposed to do thaw_secondary_cpus() on the failure path.
 	 */
 	cpu_hotplug_disabled++;
 
@@ -1270,15 +1401,15 @@ int freeze_secondary_cpus(int primary)
 	return error;
 }
 
-void __weak arch_enable_nonboot_cpus_begin(void)
+void __weak arch_thaw_secondary_cpus_begin(void)
 {
 }
 
-void __weak arch_enable_nonboot_cpus_end(void)
+void __weak arch_thaw_secondary_cpus_end(void)
 {
 }
 
-void enable_nonboot_cpus(void)
+void thaw_secondary_cpus(void)
 {
 	int cpu, error;
 
@@ -1290,7 +1421,7 @@ void enable_nonboot_cpus(void)
 
 	pr_info("Enabling non-boot CPUs ...\n");
 
-	arch_enable_nonboot_cpus_begin();
+	arch_thaw_secondary_cpus_begin();
 
 	for_each_cpu(cpu, frozen_cpus) {
 		trace_suspend_resume(TPS("CPU_ON"), cpu, true);
@@ -1303,7 +1434,7 @@ void enable_nonboot_cpus(void)
 		pr_warn("Error taking CPU%d up: %d\n", cpu, error);
 	}
 
-	arch_enable_nonboot_cpus_end();
+	arch_thaw_secondary_cpus_end();
 
 	cpumask_clear(frozen_cpus);
 out:
@@ -1434,7 +1565,7 @@ static struct cpuhp_step cpuhp_hp_states[] = {
 	[CPUHP_BRINGUP_CPU] = {
 		.name			= "cpu:bringup",
 		.startup.single		= bringup_cpu,
-		.teardown.single	= NULL,
+		.teardown.single	= finish_cpu,
 		.cant_stop		= true,
 	},
 	/* Final state before CPU kills itself */
@@ -2028,9 +2159,9 @@ static ssize_t write_cpuhp_target(struct device *dev,
 		goto out;
 
 	if (st->state < target)
-		ret = do_cpu_up(dev->id, target);
+		ret = cpu_up(dev->id, target);
 	else
-		ret = do_cpu_down(dev->id, target);
+		ret = cpu_down(dev->id, target);
 out:
 	unlock_device_hotplug();
 	return ret ? ret : count;
diff --git a/kernel/cpu_pm.c b/kernel/cpu_pm.c
index cbca6879ab7d..44a259338e33 100644
--- a/kernel/cpu_pm.c
+++ b/kernel/cpu_pm.c
@@ -80,7 +80,7 @@ EXPORT_SYMBOL_GPL(cpu_pm_unregister_notifier);
  */
 int cpu_pm_enter(void)
 {
-	int nr_calls;
+	int nr_calls = 0;
 	int ret = 0;
 
 	ret = cpu_pm_notify(CPU_PM_ENTER, -1, &nr_calls);
@@ -131,7 +131,7 @@ EXPORT_SYMBOL_GPL(cpu_pm_exit);
  */
 int cpu_cluster_pm_enter(void)
 {
-	int nr_calls;
+	int nr_calls = 0;
 	int ret = 0;
 
 	ret = cpu_pm_notify(CPU_CLUSTER_PM_ENTER, -1, &nr_calls);
diff --git a/kernel/crash_core.c b/kernel/crash_core.c
index 9f1557b98468..106e4500fd53 100644
--- a/kernel/crash_core.c
+++ b/kernel/crash_core.c
@@ -11,6 +11,8 @@
 #include <asm/page.h>
 #include <asm/sections.h>
 
+#include <crypto/sha.h>
+
 /* vmcoreinfo stuff */
 unsigned char *vmcoreinfo_data;
 size_t vmcoreinfo_size;
@@ -376,6 +378,53 @@ phys_addr_t __weak paddr_vmcoreinfo_note(void)
 }
 EXPORT_SYMBOL(paddr_vmcoreinfo_note);
 
+#define NOTES_SIZE (&__stop_notes - &__start_notes)
+#define BUILD_ID_MAX SHA1_DIGEST_SIZE
+#define NT_GNU_BUILD_ID 3
+
+struct elf_note_section {
+	struct elf_note	n_hdr;
+	u8 n_data[];
+};
+
+/*
+ * Add build ID from .notes section as generated by the GNU ld(1)
+ * or LLVM lld(1) --build-id option.
+ */
+static void add_build_id_vmcoreinfo(void)
+{
+	char build_id[BUILD_ID_MAX * 2 + 1];
+	int n_remain = NOTES_SIZE;
+
+	while (n_remain >= sizeof(struct elf_note)) {
+		const struct elf_note_section *note_sec =
+			&__start_notes + NOTES_SIZE - n_remain;
+		const u32 n_namesz = note_sec->n_hdr.n_namesz;
+
+		if (note_sec->n_hdr.n_type == NT_GNU_BUILD_ID &&
+		    n_namesz != 0 &&
+		    !strcmp((char *)&note_sec->n_data[0], "GNU")) {
+			if (note_sec->n_hdr.n_descsz <= BUILD_ID_MAX) {
+				const u32 n_descsz = note_sec->n_hdr.n_descsz;
+				const u8 *s = &note_sec->n_data[n_namesz];
+
+				s = PTR_ALIGN(s, 4);
+				bin2hex(build_id, s, n_descsz);
+				build_id[2 * n_descsz] = '\0';
+				VMCOREINFO_BUILD_ID(build_id);
+				return;
+			}
+			pr_warn("Build ID is too large to include in vmcoreinfo: %u > %u\n",
+				note_sec->n_hdr.n_descsz,
+				BUILD_ID_MAX);
+			return;
+		}
+		n_remain -= sizeof(struct elf_note) +
+			ALIGN(note_sec->n_hdr.n_namesz, 4) +
+			ALIGN(note_sec->n_hdr.n_descsz, 4);
+	}
+}
+
 static int __init crash_save_vmcoreinfo_init(void)
 {
 	vmcoreinfo_data = (unsigned char *)get_zeroed_page(GFP_KERNEL);
@@ -394,6 +443,7 @@ static int __init crash_save_vmcoreinfo_init(void)
 	}
 
 	VMCOREINFO_OSRELEASE(init_uts_ns.name.release);
+	add_build_id_vmcoreinfo();
 	VMCOREINFO_PAGESIZE(PAGE_SIZE);
 
 	VMCOREINFO_SYMBOL(init_uts_ns);
@@ -413,6 +463,7 @@ static int __init crash_save_vmcoreinfo_init(void)
 	VMCOREINFO_LENGTH(mem_section, NR_SECTION_ROOTS);
 	VMCOREINFO_STRUCT_SIZE(mem_section);
 	VMCOREINFO_OFFSET(mem_section, section_mem_map);
+	VMCOREINFO_NUMBER(MAX_PHYSMEM_BITS);
 #endif
 	VMCOREINFO_STRUCT_SIZE(page);
 	VMCOREINFO_STRUCT_SIZE(pglist_data);
diff --git a/kernel/crash_dump.c b/kernel/crash_dump.c
index 9c23ae074b40..92da32275af5 100644
--- a/kernel/crash_dump.c
+++ b/kernel/crash_dump.c
@@ -6,12 +6,6 @@
 #include <linux/export.h>
 
 /*
- * If we have booted due to a crash, max_pfn will be a very low value. We need
- * to know the amount of memory that the previous kernel used.
- */
-unsigned long saved_max_pfn;
-
-/*
  * stores the physical address of elf header of crash image
  *
  * Note: elfcorehdr_addr is not just limited to vmcore. It is also used by
diff --git a/kernel/cred.c b/kernel/cred.c
index 809a985b1793..421b1149c651 100644
--- a/kernel/cred.c
+++ b/kernel/cred.c
@@ -315,6 +315,9 @@ struct cred *prepare_exec_creds(void)
 	new->process_keyring = NULL;
 #endif
 
+	new->suid = new->fsuid = new->euid;
+	new->sgid = new->fsgid = new->egid;
+
 	return new;
 }
 
@@ -675,8 +678,6 @@ void __init cred_init(void)
  * The caller may change these controls afterwards if desired.
  *
  * Returns the new credentials or NULL if out of memory.
- *
- * Does not take, and does not return holding current->cred_replace_mutex.
  */
 struct cred *prepare_kernel_cred(struct task_struct *daemon)
 {
diff --git a/kernel/debug/debug_core.c b/kernel/debug/debug_core.c
index 2b7c9b67931d..b16dbc1bf056 100644
--- a/kernel/debug/debug_core.c
+++ b/kernel/debug/debug_core.c
@@ -67,9 +67,7 @@ static int kgdb_break_asap;
 
 struct debuggerinfo_struct kgdb_info[NR_CPUS];
 
-/**
- * kgdb_connected - Is a host GDB connected to us?
- */
+/* kgdb_connected - Is a host GDB connected to us? */
 int				kgdb_connected;
 EXPORT_SYMBOL_GPL(kgdb_connected);
 
@@ -171,18 +169,18 @@ int __weak kgdb_arch_set_breakpoint(struct kgdb_bkpt *bpt)
 {
 	int err;
 
-	err = probe_kernel_read(bpt->saved_instr, (char *)bpt->bpt_addr,
+	err = copy_from_kernel_nofault(bpt->saved_instr, (char *)bpt->bpt_addr,
 				BREAK_INSTR_SIZE);
 	if (err)
 		return err;
-	err = probe_kernel_write((char *)bpt->bpt_addr,
+	err = copy_to_kernel_nofault((char *)bpt->bpt_addr,
 				 arch_kgdb_ops.gdb_bpt_instr, BREAK_INSTR_SIZE);
 	return err;
 }
 
 int __weak kgdb_arch_remove_breakpoint(struct kgdb_bkpt *bpt)
 {
-	return probe_kernel_write((char *)bpt->bpt_addr,
+	return copy_to_kernel_nofault((char *)bpt->bpt_addr,
 				  (char *)bpt->saved_instr, BREAK_INSTR_SIZE);
 }
 
@@ -417,6 +415,18 @@ int kgdb_isremovedbreak(unsigned long addr)
 	return 0;
 }
 
+int kgdb_has_hit_break(unsigned long addr)
+{
+	int i;
+
+	for (i = 0; i < KGDB_MAX_BREAKPOINTS; i++) {
+		if (kgdb_break[i].state == BP_ACTIVE &&
+		    kgdb_break[i].bpt_addr == addr)
+			return 1;
+	}
+	return 0;
+}
+
 int dbg_remove_all_break(void)
 {
 	int error;
@@ -532,6 +542,7 @@ static int kgdb_reenter_check(struct kgdb_state *ks)
 
 	if (exception_level > 1) {
 		dump_stack();
+		kgdb_io_module_registered = false;
 		panic("Recursive entry to debugger");
 	}
 
@@ -576,6 +587,7 @@ static int kgdb_cpu_enter(struct kgdb_state *ks, struct pt_regs *regs,
 		arch_kgdb_ops.disable_hw_break(regs);
 
 acquirelock:
+	rcu_read_lock();
 	/*
 	 * Interrupts will be restored by the 'trap return' code, except when
 	 * single stepping.
@@ -635,6 +647,7 @@ return_normal:
 			atomic_dec(&slaves_in_kgdb);
 			dbg_touch_watchdogs();
 			local_irq_restore(flags);
+			rcu_read_unlock();
 			return 0;
 		}
 		cpu_relax();
@@ -653,6 +666,7 @@ return_normal:
 		raw_spin_unlock(&dbg_master_lock);
 		dbg_touch_watchdogs();
 		local_irq_restore(flags);
+		rcu_read_unlock();
 
 		goto acquirelock;
 	}
@@ -668,6 +682,8 @@ return_normal:
 	if (kgdb_skipexception(ks->ex_vector, ks->linux_regs))
 		goto kgdb_restore;
 
+	atomic_inc(&ignore_console_lock_warning);
+
 	/* Call the I/O driver's pre_exception routine */
 	if (dbg_io_ops->pre_exception)
 		dbg_io_ops->pre_exception();
@@ -740,6 +756,8 @@ cpu_master_loop:
 	if (dbg_io_ops->post_exception)
 		dbg_io_ops->post_exception();
 
+	atomic_dec(&ignore_console_lock_warning);
+
 	if (!kgdb_single_step) {
 		raw_spin_unlock(&dbg_slave_lock);
 		/* Wait till all the CPUs have quit from the debugger. */
@@ -772,6 +790,7 @@ kgdb_restore:
 	raw_spin_unlock(&dbg_master_lock);
 	dbg_touch_watchdogs();
 	local_irq_restore(flags);
+	rcu_read_unlock();
 
 	return kgdb_info[cpu].ret_state;
 }
@@ -920,7 +939,7 @@ static void sysrq_handle_dbg(int key)
 	kgdb_breakpoint();
 }
 
-static struct sysrq_key_op sysrq_dbg_op = {
+static const struct sysrq_key_op sysrq_dbg_op = {
 	.handler	= sysrq_handle_dbg,
 	.help_msg	= "debug(g)",
 	.action_msg	= "DEBUG",
@@ -946,6 +965,14 @@ void kgdb_panic(const char *msg)
 	kgdb_breakpoint();
 }
 
+static void kgdb_initial_breakpoint(void)
+{
+	kgdb_break_asap = 0;
+
+	pr_crit("Waiting for connection from remote gdb...\n");
+	kgdb_breakpoint();
+}
+
 void __weak kgdb_arch_late(void)
 {
 }
@@ -956,6 +983,9 @@ void __init dbg_late_init(void)
 	if (kgdb_io_module_registered)
 		kgdb_arch_late();
 	kdb_init(KDB_INIT_FULL);
+
+	if (kgdb_io_module_registered && kgdb_break_asap)
+		kgdb_initial_breakpoint();
 }
 
 static int
@@ -1038,7 +1068,7 @@ static void kgdb_tasklet_bpt(unsigned long ing)
 	atomic_set(&kgdb_break_tasklet_var, 0);
 }
 
-static DECLARE_TASKLET(kgdb_tasklet_breakpoint, kgdb_tasklet_bpt, 0);
+static DECLARE_TASKLET_OLD(kgdb_tasklet_breakpoint, kgdb_tasklet_bpt);
 
 void kgdb_schedule_breakpoint(void)
 {
@@ -1051,14 +1081,6 @@ void kgdb_schedule_breakpoint(void)
 }
 EXPORT_SYMBOL_GPL(kgdb_schedule_breakpoint);
 
-static void kgdb_initial_breakpoint(void)
-{
-	kgdb_break_asap = 0;
-
-	pr_crit("Waiting for connection from remote gdb...\n");
-	kgdb_breakpoint();
-}
-
 /**
  *	kgdb_register_io_module - register KGDB IO module
  *	@new_dbg_io_ops: the io ops vector
@@ -1067,15 +1089,22 @@ static void kgdb_initial_breakpoint(void)
  */
 int kgdb_register_io_module(struct kgdb_io *new_dbg_io_ops)
 {
+	struct kgdb_io *old_dbg_io_ops;
 	int err;
 
 	spin_lock(&kgdb_registration_lock);
 
-	if (dbg_io_ops) {
-		spin_unlock(&kgdb_registration_lock);
+	old_dbg_io_ops = dbg_io_ops;
+	if (old_dbg_io_ops) {
+		if (!old_dbg_io_ops->deinit) {
+			spin_unlock(&kgdb_registration_lock);
 
-		pr_err("Another I/O driver is already registered with KGDB\n");
-		return -EBUSY;
+			pr_err("KGDB I/O driver %s can't replace %s.\n",
+				new_dbg_io_ops->name, old_dbg_io_ops->name);
+			return -EBUSY;
+		}
+		pr_info("Replacing I/O driver %s with %s\n",
+			old_dbg_io_ops->name, new_dbg_io_ops->name);
 	}
 
 	if (new_dbg_io_ops->init) {
@@ -1090,12 +1119,18 @@ int kgdb_register_io_module(struct kgdb_io *new_dbg_io_ops)
 
 	spin_unlock(&kgdb_registration_lock);
 
+	if (old_dbg_io_ops) {
+		old_dbg_io_ops->deinit();
+		return 0;
+	}
+
 	pr_info("Registered I/O driver %s\n", new_dbg_io_ops->name);
 
 	/* Arm KGDB now. */
 	kgdb_register_callbacks();
 
-	if (kgdb_break_asap)
+	if (kgdb_break_asap &&
+	    (!dbg_is_early || IS_ENABLED(CONFIG_ARCH_HAS_EARLY_DEBUG)))
 		kgdb_initial_breakpoint();
 
 	return 0;
@@ -1125,6 +1160,9 @@ void kgdb_unregister_io_module(struct kgdb_io *old_dbg_io_ops)
 
 	spin_unlock(&kgdb_registration_lock);
 
+	if (old_dbg_io_ops->deinit)
+		old_dbg_io_ops->deinit();
+
 	pr_info("Unregistered I/O driver %s, debugger disabled\n",
 		old_dbg_io_ops->name);
 }
@@ -1165,7 +1203,8 @@ static int __init opt_kgdb_wait(char *str)
 	kgdb_break_asap = 1;
 
 	kdb_init(KDB_INIT_EARLY);
-	if (kgdb_io_module_registered)
+	if (kgdb_io_module_registered &&
+	    IS_ENABLED(CONFIG_ARCH_HAS_EARLY_DEBUG))
 		kgdb_initial_breakpoint();
 
 	return 0;
diff --git a/kernel/debug/gdbstub.c b/kernel/debug/gdbstub.c
index 4b280fc7dd67..cc3c43dfec44 100644
--- a/kernel/debug/gdbstub.c
+++ b/kernel/debug/gdbstub.c
@@ -247,7 +247,7 @@ char *kgdb_mem2hex(char *mem, char *buf, int count)
 	 */
 	tmp = buf + count;
 
-	err = probe_kernel_read(tmp, mem, count);
+	err = copy_from_kernel_nofault(tmp, mem, count);
 	if (err)
 		return NULL;
 	while (count > 0) {
@@ -283,7 +283,7 @@ int kgdb_hex2mem(char *buf, char *mem, int count)
 		*tmp_raw |= hex_to_bin(*tmp_hex--) << 4;
 	}
 
-	return probe_kernel_write(mem, tmp_raw, count);
+	return copy_to_kernel_nofault(mem, tmp_raw, count);
 }
 
 /*
@@ -335,7 +335,7 @@ static int kgdb_ebin2mem(char *buf, char *mem, int count)
 		size++;
 	}
 
-	return probe_kernel_write(mem, c, size);
+	return copy_to_kernel_nofault(mem, c, size);
 }
 
 #if DBG_MAX_REG_NUM > 0
@@ -792,6 +792,19 @@ static void gdb_cmd_query(struct kgdb_state *ks)
 		}
 		break;
 #endif
+#ifdef CONFIG_HAVE_ARCH_KGDB_QXFER_PKT
+	case 'S':
+		if (!strncmp(remcom_in_buffer, "qSupported:", 11))
+			strcpy(remcom_out_buffer, kgdb_arch_gdb_stub_feature);
+		break;
+	case 'X':
+		if (!strncmp(remcom_in_buffer, "qXfer:", 6))
+			kgdb_arch_handle_qxfer_pkt(remcom_in_buffer,
+						   remcom_out_buffer);
+		break;
+#endif
+	default:
+		break;
 	}
 }
 
@@ -1033,14 +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) {
@@ -1049,7 +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/.gitignore b/kernel/debug/kdb/.gitignore
index 396d12eda9e8..df259542a236 100644
--- a/kernel/debug/kdb/.gitignore
+++ b/kernel/debug/kdb/.gitignore
@@ -1 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
 gen-kdb_cmds.c
diff --git a/kernel/debug/kdb/kdb_bt.c b/kernel/debug/kdb/kdb_bt.c
index 3de0cc780c16..18e03aba2cfc 100644
--- a/kernel/debug/kdb/kdb_bt.c
+++ b/kernel/debug/kdb/kdb_bt.c
@@ -21,17 +21,18 @@
 
 static void kdb_show_stack(struct task_struct *p, void *addr)
 {
-	int old_lvl = console_loglevel;
-
-	console_loglevel = CONSOLE_LOGLEVEL_MOTORMOUTH;
 	kdb_trap_printk++;
 
-	if (!addr && kdb_task_has_cpu(p))
+	if (!addr && kdb_task_has_cpu(p)) {
+		int old_lvl = console_loglevel;
+
+		console_loglevel = CONSOLE_LOGLEVEL_MOTORMOUTH;
 		kdb_dump_stack_on_cpu(kdb_process_cpu(p));
-	else
-		show_stack(p, addr);
+		console_loglevel = old_lvl;
+	} else {
+		show_stack(p, addr, KERN_EMERG);
+	}
 
-	console_loglevel = old_lvl;
 	kdb_trap_printk--;
 }
 
diff --git a/kernel/debug/kdb/kdb_io.c b/kernel/debug/kdb/kdb_io.c
index 924bc9298a42..9d847ab851db 100644
--- a/kernel/debug/kdb/kdb_io.c
+++ b/kernel/debug/kdb/kdb_io.c
@@ -542,6 +542,44 @@ static int kdb_search_string(char *searched, char *searchfor)
 	return 0;
 }
 
+static void kdb_msg_write(const char *msg, int msg_len)
+{
+	struct console *c;
+
+	if (msg_len == 0)
+		return;
+
+	if (dbg_io_ops) {
+		const char *cp = msg;
+		int len = msg_len;
+
+		while (len--) {
+			dbg_io_ops->write_char(*cp);
+			cp++;
+		}
+	}
+
+	for_each_console(c) {
+		if (!(c->flags & CON_ENABLED))
+			continue;
+		if (c == dbg_io_ops->cons)
+			continue;
+		/*
+		 * Set oops_in_progress to encourage the console drivers to
+		 * disregard their internal spin locks: in the current calling
+		 * context the risk of deadlock is a bigger problem than risks
+		 * due to re-entering the console driver. We operate directly on
+		 * oops_in_progress rather than using bust_spinlocks() because
+		 * the calls bust_spinlocks() makes on exit are not appropriate
+		 * for this calling context.
+		 */
+		++oops_in_progress;
+		c->write(c, msg, msg_len);
+		--oops_in_progress;
+		touch_nmi_watchdog();
+	}
+}
+
 int vkdb_printf(enum kdb_msgsrc src, const char *fmt, va_list ap)
 {
 	int diag;
@@ -553,8 +591,7 @@ int vkdb_printf(enum kdb_msgsrc src, const char *fmt, va_list ap)
 	int this_cpu, old_cpu;
 	char *cp, *cp2, *cphold = NULL, replaced_byte = ' ';
 	char *moreprompt = "more> ";
-	struct console *c;
-	unsigned long uninitialized_var(flags);
+	unsigned long flags;
 
 	/* Serialize kdb_printf if multiple cpus try to write at once.
 	 * But if any cpu goes recursive in kdb, just print the output,
@@ -687,22 +724,11 @@ kdb_printit:
 	 */
 	retlen = strlen(kdb_buffer);
 	cp = (char *) printk_skip_headers(kdb_buffer);
-	if (!dbg_kdb_mode && kgdb_connected) {
+	if (!dbg_kdb_mode && kgdb_connected)
 		gdbstub_msg_write(cp, retlen - (cp - kdb_buffer));
-	} else {
-		if (dbg_io_ops && !dbg_io_ops->is_console) {
-			len = retlen - (cp - kdb_buffer);
-			cp2 = cp;
-			while (len--) {
-				dbg_io_ops->write_char(*cp2);
-				cp2++;
-			}
-		}
-		for_each_console(c) {
-			c->write(c, cp, retlen - (cp - kdb_buffer));
-			touch_nmi_watchdog();
-		}
-	}
+	else
+		kdb_msg_write(cp, retlen - (cp - kdb_buffer));
+
 	if (logging) {
 		saved_loglevel = console_loglevel;
 		console_loglevel = CONSOLE_LOGLEVEL_SILENT;
@@ -751,19 +777,7 @@ kdb_printit:
 			moreprompt = "more> ";
 
 		kdb_input_flush();
-
-		if (dbg_io_ops && !dbg_io_ops->is_console) {
-			len = strlen(moreprompt);
-			cp = moreprompt;
-			while (len--) {
-				dbg_io_ops->write_char(*cp);
-				cp++;
-			}
-		}
-		for_each_console(c) {
-			c->write(c, moreprompt, strlen(moreprompt));
-			touch_nmi_watchdog();
-		}
+		kdb_msg_write(moreprompt, strlen(moreprompt));
 
 		if (logging)
 			printk("%s", moreprompt);
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_main.c b/kernel/debug/kdb/kdb_main.c
index ba12e9f4661e..5c7949061671 100644
--- a/kernel/debug/kdb/kdb_main.c
+++ b/kernel/debug/kdb/kdb_main.c
@@ -62,7 +62,7 @@ int kdb_grep_trailing;
 /*
  * Kernel debugger state flags
  */
-int kdb_flags;
+unsigned int kdb_flags;
 
 /*
  * kdb_lock protects updates to kdb_initial_cpu.  Used to
@@ -399,6 +399,13 @@ int kdb_set(int argc, const char **argv)
 		return KDB_ARGCOUNT;
 
 	/*
+	 * Censor sensitive variables
+	 */
+	if (strcmp(argv[1], "PROMPT") == 0 &&
+	    !kdb_check_flags(KDB_ENABLE_MEM_READ, kdb_cmd_enabled, false))
+		return KDB_NOPERM;
+
+	/*
 	 * Check for internal variables
 	 */
 	if (strcmp(argv[1], "KDBDEBUG") == 0) {
@@ -411,8 +418,7 @@ int kdb_set(int argc, const char **argv)
 				    argv[2]);
 			return 0;
 		}
-		kdb_flags = (kdb_flags &
-			     ~(KDB_DEBUG_FLAG_MASK << KDB_DEBUG_FLAG_SHIFT))
+		kdb_flags = (kdb_flags & ~KDB_DEBUG(MASK))
 			| (debugflags << KDB_DEBUG_FLAG_SHIFT);
 
 		return 0;
@@ -1101,13 +1107,14 @@ static int handle_ctrl_cmd(char *cmd)
 	switch (*cmd) {
 	case CTRL_P:
 		if (cmdptr != cmd_tail)
-			cmdptr = (cmdptr-1) % KDB_CMD_HISTORY_COUNT;
-		strncpy(cmd_cur, cmd_hist[cmdptr], CMD_BUFLEN);
+			cmdptr = (cmdptr + KDB_CMD_HISTORY_COUNT - 1) %
+				 KDB_CMD_HISTORY_COUNT;
+		strscpy(cmd_cur, cmd_hist[cmdptr], CMD_BUFLEN);
 		return 1;
 	case CTRL_N:
 		if (cmdptr != cmd_head)
 			cmdptr = (cmdptr+1) % KDB_CMD_HISTORY_COUNT;
-		strncpy(cmd_cur, cmd_hist[cmdptr], CMD_BUFLEN);
+		strscpy(cmd_cur, cmd_hist[cmdptr], CMD_BUFLEN);
 		return 1;
 	}
 	return 0;
@@ -1298,12 +1305,9 @@ static int kdb_local(kdb_reason_t reason, int error, struct pt_regs *regs,
 		*(cmd_hist[cmd_head]) = '\0';
 
 do_full_getstr:
-#if defined(CONFIG_SMP)
+		/* PROMPT can only be set if we have MEM_READ permission. */
 		snprintf(kdb_prompt_str, CMD_BUFLEN, kdbgetenv("PROMPT"),
 			 raw_smp_processor_id());
-#else
-		snprintf(kdb_prompt_str, CMD_BUFLEN, kdbgetenv("PROMPT"));
-#endif
 		if (defcmd_in_progress)
 			strncat(kdb_prompt_str, "[defcmd]", CMD_BUFLEN);
 
@@ -1314,7 +1318,7 @@ do_full_getstr:
 		if (*cmdbuf != '\n') {
 			if (*cmdbuf < 32) {
 				if (cmdptr == cmd_head) {
-					strncpy(cmd_hist[cmd_head], cmd_cur,
+					strscpy(cmd_hist[cmd_head], cmd_cur,
 						CMD_BUFLEN);
 					*(cmd_hist[cmd_head] +
 					  strlen(cmd_hist[cmd_head])-1) = '\0';
@@ -1324,7 +1328,7 @@ do_full_getstr:
 				cmdbuf = cmd_cur;
 				goto do_full_getstr;
 			} else {
-				strncpy(cmd_hist[cmd_head], cmd_cur,
+				strscpy(cmd_hist[cmd_head], cmd_cur,
 					CMD_BUFLEN);
 			}
 
@@ -2077,7 +2081,8 @@ static int kdb_env(int argc, const char **argv)
 	}
 
 	if (KDB_DEBUG(MASK))
-		kdb_printf("KDBFLAGS=0x%x\n", kdb_flags);
+		kdb_printf("KDBDEBUG=0x%x\n",
+			(kdb_flags & KDB_DEBUG(MASK)) >> KDB_DEBUG_FLAG_SHIFT);
 
 	return 0;
 }
@@ -2321,7 +2326,8 @@ void kdb_ps1(const struct task_struct *p)
 	int cpu;
 	unsigned long tmp;
 
-	if (!p || probe_kernel_read(&tmp, (char *)p, sizeof(unsigned long)))
+	if (!p ||
+	    copy_from_kernel_nofault(&tmp, (char *)p, sizeof(unsigned long)))
 		return;
 
 	cpu = kdb_process_cpu(p);
diff --git a/kernel/debug/kdb/kdb_support.c b/kernel/debug/kdb/kdb_support.c
index b8e6306e7e13..6226502ce049 100644
--- a/kernel/debug/kdb/kdb_support.c
+++ b/kernel/debug/kdb/kdb_support.c
@@ -325,7 +325,7 @@ char *kdb_strdup(const char *str, gfp_t type)
  */
 int kdb_getarea_size(void *res, unsigned long addr, size_t size)
 {
-	int ret = probe_kernel_read((char *)res, (char *)addr, size);
+	int ret = copy_from_kernel_nofault((char *)res, (char *)addr, size);
 	if (ret) {
 		if (!KDB_STATE(SUPPRESS)) {
 			kdb_printf("kdb_getarea: Bad address 0x%lx\n", addr);
@@ -350,7 +350,7 @@ int kdb_getarea_size(void *res, unsigned long addr, size_t size)
  */
 int kdb_putarea_size(unsigned long addr, void *res, size_t size)
 {
-	int ret = probe_kernel_read((char *)addr, (char *)res, size);
+	int ret = copy_from_kernel_nofault((char *)addr, (char *)res, size);
 	if (ret) {
 		if (!KDB_STATE(SUPPRESS)) {
 			kdb_printf("kdb_putarea: Bad address 0x%lx\n", addr);
@@ -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);
@@ -624,7 +624,8 @@ char kdb_task_state_char (const struct task_struct *p)
 	char state;
 	unsigned long tmp;
 
-	if (!p || probe_kernel_read(&tmp, (char *)p, sizeof(unsigned long)))
+	if (!p ||
+	    copy_from_kernel_nofault(&tmp, (char *)p, sizeof(unsigned long)))
 		return 'E';
 
 	cpu = kdb_process_cpu(p);
diff --git a/kernel/dma/Kconfig b/kernel/dma/Kconfig
index 4c103a24e380..847a9d1fa634 100644
--- a/kernel/dma/Kconfig
+++ b/kernel/dma/Kconfig
@@ -1,10 +1,24 @@
 # SPDX-License-Identifier: GPL-2.0-only
 
+config NO_DMA
+	bool
+
 config HAS_DMA
 	bool
 	depends on !NO_DMA
 	default y
 
+config DMA_OPS
+	bool
+
+#
+# IOMMU drivers that can bypass the IOMMU code and optionally use the direct
+# mapping fast path should select this option and set the dma_ops_bypass
+# flag in struct device where applicable
+#
+config DMA_OPS_BYPASS
+	bool
+
 config NEED_SG_DMA_LENGTH
 	bool
 
@@ -60,6 +74,7 @@ config DMA_NONCOHERENT_CACHE_SYNC
 config DMA_VIRT_OPS
 	bool
 	depends on HAS_DMA
+	select DMA_OPS
 
 config SWIOTLB
 	bool
@@ -71,17 +86,22 @@ config SWIOTLB
 # in the pagetables
 #
 config DMA_NONCOHERENT_MMAP
+	default y if !MMU
+	bool
+
+config DMA_COHERENT_POOL
+	select GENERIC_ALLOCATOR
 	bool
 
 config DMA_REMAP
+	bool
 	depends on MMU
-	select GENERIC_ALLOCATOR
 	select DMA_NONCOHERENT_MMAP
-	bool
 
 config DMA_DIRECT_REMAP
 	bool
 	select DMA_REMAP
+	select DMA_COHERENT_POOL
 
 config DMA_CMA
 	bool "DMA Contiguous Memory Allocator"
@@ -169,11 +189,6 @@ config DMA_API_DEBUG
 	  drivers like double-freeing of DMA mappings or freeing mappings that
 	  were never allocated.
 
-	  This also attempts to catch cases where a page owned by DMA is
-	  accessed by the cpu in a way that could cause data corruption.  For
-	  example, this enables cow_user_page() to check that the source page is
-	  not undergoing DMA.
-
 	  This option causes a performance degradation.  Use only if you want to
 	  debug device drivers and dma interactions.
 
diff --git a/kernel/dma/Makefile b/kernel/dma/Makefile
index d237cf3dc181..32c7c1942bbd 100644
--- a/kernel/dma/Makefile
+++ b/kernel/dma/Makefile
@@ -1,9 +1,11 @@
 # SPDX-License-Identifier: GPL-2.0
 
-obj-$(CONFIG_HAS_DMA)			+= mapping.o direct.o dummy.o
+obj-$(CONFIG_HAS_DMA)			+= mapping.o direct.o
+obj-$(CONFIG_DMA_OPS)			+= dummy.o
 obj-$(CONFIG_DMA_CMA)			+= contiguous.o
 obj-$(CONFIG_DMA_DECLARE_COHERENT)	+= coherent.o
 obj-$(CONFIG_DMA_VIRT_OPS)		+= virt.o
 obj-$(CONFIG_DMA_API_DEBUG)		+= debug.o
 obj-$(CONFIG_SWIOTLB)			+= swiotlb.o
+obj-$(CONFIG_DMA_COHERENT_POOL)		+= pool.o
 obj-$(CONFIG_DMA_REMAP)			+= remap.o
diff --git a/kernel/dma/coherent.c b/kernel/dma/coherent.c
index 551b0eb7028a..2a0c4985f38e 100644
--- a/kernel/dma/coherent.c
+++ b/kernel/dma/coherent.c
@@ -134,7 +134,7 @@ static void *__dma_alloc_from_coherent(struct device *dev,
 
 	spin_lock_irqsave(&mem->spinlock, flags);
 
-	if (unlikely(size > (mem->size << PAGE_SHIFT)))
+	if (unlikely(size > ((dma_addr_t)mem->size << PAGE_SHIFT)))
 		goto err;
 
 	pageno = bitmap_find_free_region(mem->bitmap, mem->size, order);
@@ -144,8 +144,9 @@ static void *__dma_alloc_from_coherent(struct device *dev,
 	/*
 	 * Memory was found in the coherent area.
 	 */
-	*dma_handle = dma_get_device_base(dev, mem) + (pageno << PAGE_SHIFT);
-	ret = mem->virt_base + (pageno << PAGE_SHIFT);
+	*dma_handle = dma_get_device_base(dev, mem) +
+			((dma_addr_t)pageno << PAGE_SHIFT);
+	ret = mem->virt_base + ((dma_addr_t)pageno << PAGE_SHIFT);
 	spin_unlock_irqrestore(&mem->spinlock, flags);
 	memset(ret, 0, size);
 	return ret;
@@ -194,7 +195,7 @@ static int __dma_release_from_coherent(struct dma_coherent_mem *mem,
 				       int order, void *vaddr)
 {
 	if (mem && vaddr >= mem->virt_base && vaddr <
-		   (mem->virt_base + (mem->size << PAGE_SHIFT))) {
+		   (mem->virt_base + ((dma_addr_t)mem->size << PAGE_SHIFT))) {
 		int page = (vaddr - mem->virt_base) >> PAGE_SHIFT;
 		unsigned long flags;
 
@@ -238,10 +239,10 @@ static int __dma_mmap_from_coherent(struct dma_coherent_mem *mem,
 		struct vm_area_struct *vma, void *vaddr, size_t size, int *ret)
 {
 	if (mem && vaddr >= mem->virt_base && vaddr + size <=
-		   (mem->virt_base + (mem->size << PAGE_SHIFT))) {
+		   (mem->virt_base + ((dma_addr_t)mem->size << PAGE_SHIFT))) {
 		unsigned long off = vma->vm_pgoff;
 		int start = (vaddr - mem->virt_base) >> PAGE_SHIFT;
-		int user_count = vma_pages(vma);
+		unsigned long user_count = vma_pages(vma);
 		int count = PAGE_ALIGN(size) >> PAGE_SHIFT;
 
 		*ret = -ENXIO;
diff --git a/kernel/dma/contiguous.c b/kernel/dma/contiguous.c
index 8bc6f2d670f9..cff7e60968b9 100644
--- a/kernel/dma/contiguous.c
+++ b/kernel/dma/contiguous.c
@@ -215,6 +215,13 @@ bool dma_release_from_contiguous(struct device *dev, struct page *pages,
 	return cma_release(dev_get_cma_area(dev), pages, count);
 }
 
+static struct page *cma_alloc_aligned(struct cma *cma, size_t size, gfp_t gfp)
+{
+	unsigned int align = min(get_order(size), CONFIG_CMA_ALIGNMENT);
+
+	return cma_alloc(cma, size >> PAGE_SHIFT, align, gfp & __GFP_NOWARN);
+}
+
 /**
  * dma_alloc_contiguous() - allocate contiguous pages
  * @dev:   Pointer to device for which the allocation is performed.
@@ -222,8 +229,8 @@ bool dma_release_from_contiguous(struct device *dev, struct page *pages,
  * @gfp:   Allocation flags.
  *
  * This function allocates contiguous memory buffer for specified device. It
- * first tries to use device specific contiguous memory area if available or
- * the default global one, then tries a fallback allocation of normal pages.
+ * tries to use device specific contiguous memory area if available, or the
+ * default global one.
  *
  * Note that it byapss one-page size of allocations from the global area as
  * the addresses within one page are always contiguous, so there is no need
@@ -231,24 +238,14 @@ bool dma_release_from_contiguous(struct device *dev, struct page *pages,
  */
 struct page *dma_alloc_contiguous(struct device *dev, size_t size, gfp_t gfp)
 {
-	size_t count = size >> PAGE_SHIFT;
-	struct page *page = NULL;
-	struct cma *cma = NULL;
-
-	if (dev && dev->cma_area)
-		cma = dev->cma_area;
-	else if (count > 1)
-		cma = dma_contiguous_default_area;
-
 	/* CMA can be used only in the context which permits sleeping */
-	if (cma && gfpflags_allow_blocking(gfp)) {
-		size_t align = get_order(size);
-		size_t cma_align = min_t(size_t, align, CONFIG_CMA_ALIGNMENT);
-
-		page = cma_alloc(cma, count, cma_align, gfp & __GFP_NOWARN);
-	}
-
-	return page;
+	if (!gfpflags_allow_blocking(gfp))
+		return NULL;
+	if (dev->cma_area)
+		return cma_alloc_aligned(dev->cma_area, size, gfp);
+	if (size <= PAGE_SIZE || !dma_contiguous_default_area)
+		return NULL;
+	return cma_alloc_aligned(dma_contiguous_default_area, size, gfp);
 }
 
 /**
diff --git a/kernel/dma/debug.c b/kernel/dma/debug.c
index 2031ed1ad7fa..8e9f7b301c6d 100644
--- a/kernel/dma/debug.c
+++ b/kernel/dma/debug.c
@@ -137,12 +137,19 @@ static const char *const maperr2str[] = {
 	[MAP_ERR_CHECKED] = "dma map error checked",
 };
 
-static const char *type2name[5] = { "single", "page",
-				    "scather-gather", "coherent",
-				    "resource" };
+static const char *type2name[] = {
+	[dma_debug_single] = "single",
+	[dma_debug_sg] = "scather-gather",
+	[dma_debug_coherent] = "coherent",
+	[dma_debug_resource] = "resource",
+};
 
-static const char *dir2name[4] = { "DMA_BIDIRECTIONAL", "DMA_TO_DEVICE",
-				   "DMA_FROM_DEVICE", "DMA_NONE" };
+static const char *dir2name[] = {
+	[DMA_BIDIRECTIONAL]	= "DMA_BIDIRECTIONAL",
+	[DMA_TO_DEVICE]		= "DMA_TO_DEVICE",
+	[DMA_FROM_DEVICE]	= "DMA_FROM_DEVICE",
+	[DMA_NONE]		= "DMA_NONE",
+};
 
 /*
  * The access to some variables in this macro is racy. We can't use atomic_t
@@ -441,9 +448,6 @@ void debug_dma_dump_mappings(struct device *dev)
  * dma_active_cacheline entry to track per event.  dma_map_sg(), on the
  * other hand, consumes a single dma_debug_entry, but inserts 'nents'
  * entries into the tree.
- *
- * At any time debug_dma_assert_idle() can be called to trigger a
- * warning if any cachelines in the given page are in the active set.
  */
 static RADIX_TREE(dma_active_cacheline, GFP_NOWAIT);
 static DEFINE_SPINLOCK(radix_lock);
@@ -490,10 +494,7 @@ static void active_cacheline_inc_overlap(phys_addr_t cln)
 	overlap = active_cacheline_set_overlap(cln, ++overlap);
 
 	/* If we overflowed the overlap counter then we're potentially
-	 * leaking dma-mappings.  Otherwise, if maps and unmaps are
-	 * balanced then this overflow may cause false negatives in
-	 * debug_dma_assert_idle() as the cacheline may be marked idle
-	 * prematurely.
+	 * leaking dma-mappings.
 	 */
 	WARN_ONCE(overlap > ACTIVE_CACHELINE_MAX_OVERLAP,
 		  pr_fmt("exceeded %d overlapping mappings of cacheline %pa\n"),
@@ -548,53 +549,6 @@ static void active_cacheline_remove(struct dma_debug_entry *entry)
 	spin_unlock_irqrestore(&radix_lock, flags);
 }
 
-/**
- * debug_dma_assert_idle() - assert that a page is not undergoing dma
- * @page: page to lookup in the dma_active_cacheline tree
- *
- * Place a call to this routine in cases where the cpu touching the page
- * before the dma completes (page is dma_unmapped) will lead to data
- * corruption.
- */
-void debug_dma_assert_idle(struct page *page)
-{
-	static struct dma_debug_entry *ents[CACHELINES_PER_PAGE];
-	struct dma_debug_entry *entry = NULL;
-	void **results = (void **) &ents;
-	unsigned int nents, i;
-	unsigned long flags;
-	phys_addr_t cln;
-
-	if (dma_debug_disabled())
-		return;
-
-	if (!page)
-		return;
-
-	cln = (phys_addr_t) page_to_pfn(page) << CACHELINE_PER_PAGE_SHIFT;
-	spin_lock_irqsave(&radix_lock, flags);
-	nents = radix_tree_gang_lookup(&dma_active_cacheline, results, cln,
-				       CACHELINES_PER_PAGE);
-	for (i = 0; i < nents; i++) {
-		phys_addr_t ent_cln = to_cacheline_number(ents[i]);
-
-		if (ent_cln == cln) {
-			entry = ents[i];
-			break;
-		} else if (ent_cln >= cln + CACHELINES_PER_PAGE)
-			break;
-	}
-	spin_unlock_irqrestore(&radix_lock, flags);
-
-	if (!entry)
-		return;
-
-	cln = to_cacheline_number(entry);
-	err_printk(entry->dev, entry,
-		   "cpu touching an active dma mapped cacheline [cln=%pa]\n",
-		   &cln);
-}
-
 /*
  * Wrapper function for adding an entry to the hash.
  * This function takes care of locking itself.
@@ -653,7 +607,7 @@ static struct dma_debug_entry *__dma_entry_alloc(void)
 	return entry;
 }
 
-void __dma_entry_alloc_check_leak(void)
+static void __dma_entry_alloc_check_leak(void)
 {
 	u32 tmp = nr_total_entries % nr_prealloc_entries;
 
@@ -879,7 +833,7 @@ static int device_dma_allocations(struct device *dev, struct dma_debug_entry **o
 static int dma_debug_device_change(struct notifier_block *nb, unsigned long action, void *data)
 {
 	struct device *dev = data;
-	struct dma_debug_entry *uninitialized_var(entry);
+	struct dma_debug_entry *entry;
 	int count;
 
 	if (dma_debug_disabled())
@@ -1068,7 +1022,7 @@ static void check_unmap(struct dma_debug_entry *ref)
 	/*
 	 * Drivers should use dma_mapping_error() to check the returned
 	 * addresses of dma_map_single() and dma_map_page().
-	 * If not, print this warning message. See Documentation/DMA-API.txt.
+	 * If not, print this warning message. See Documentation/core-api/dma-api.rst.
 	 */
 	if (entry->map_err_type == MAP_ERR_NOT_CHECKED) {
 		err_printk(ref->dev, entry,
diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index ac7956c38f69..db6ef07aec3b 100644
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -10,11 +10,9 @@
 #include <linux/dma-direct.h>
 #include <linux/scatterlist.h>
 #include <linux/dma-contiguous.h>
-#include <linux/dma-noncoherent.h>
 #include <linux/pfn.h>
 #include <linux/vmalloc.h>
 #include <linux/set_memory.h>
-#include <linux/swiotlb.h>
 
 /*
  * Most architectures use ZONE_DMA for the first 16 Megabytes, but some use it
@@ -39,13 +37,14 @@ static inline struct page *dma_direct_to_page(struct device *dev,
 
 u64 dma_direct_get_required_mask(struct device *dev)
 {
-	u64 max_dma = phys_to_dma_direct(dev, (max_pfn - 1) << PAGE_SHIFT);
+	phys_addr_t phys = (phys_addr_t)(max_pfn - 1) << PAGE_SHIFT;
+	u64 max_dma = phys_to_dma_direct(dev, phys);
 
 	return (1ULL << (fls64(max_dma) - 1)) * 2 - 1;
 }
 
-static gfp_t __dma_direct_optimal_gfp_mask(struct device *dev, u64 dma_mask,
-		u64 *phys_limit)
+static gfp_t dma_direct_optimal_gfp_mask(struct device *dev, u64 dma_mask,
+				  u64 *phys_limit)
 {
 	u64 dma_limit = min_not_zero(dma_mask, dev->bus_dma_limit);
 
@@ -75,29 +74,63 @@ static bool dma_coherent_ok(struct device *dev, phys_addr_t phys, size_t size)
 			min_not_zero(dev->coherent_dma_mask, dev->bus_dma_limit);
 }
 
-struct page *__dma_direct_alloc_pages(struct device *dev, size_t size,
+/*
+ * Decrypting memory is allowed to block, so if this device requires
+ * unencrypted memory it must come from atomic pools.
+ */
+static inline bool dma_should_alloc_from_pool(struct device *dev, gfp_t gfp,
+					      unsigned long attrs)
+{
+	if (!IS_ENABLED(CONFIG_DMA_COHERENT_POOL))
+		return false;
+	if (gfpflags_allow_blocking(gfp))
+		return false;
+	if (force_dma_unencrypted(dev))
+		return true;
+	if (!IS_ENABLED(CONFIG_DMA_DIRECT_REMAP))
+		return false;
+	if (dma_alloc_need_uncached(dev, attrs))
+		return true;
+	return false;
+}
+
+static inline bool dma_should_free_from_pool(struct device *dev,
+					     unsigned long attrs)
+{
+	if (IS_ENABLED(CONFIG_DMA_COHERENT_POOL))
+		return true;
+	if ((attrs & DMA_ATTR_NO_KERNEL_MAPPING) &&
+	    !force_dma_unencrypted(dev))
+		return false;
+	if (IS_ENABLED(CONFIG_DMA_DIRECT_REMAP))
+		return true;
+	return false;
+}
+
+static struct page *__dma_direct_alloc_pages(struct device *dev, size_t size,
 		gfp_t gfp, unsigned long attrs)
 {
-	size_t alloc_size = PAGE_ALIGN(size);
 	int node = dev_to_node(dev);
 	struct page *page = NULL;
 	u64 phys_limit;
 
+	WARN_ON_ONCE(!PAGE_ALIGNED(size));
+
 	if (attrs & DMA_ATTR_NO_WARN)
 		gfp |= __GFP_NOWARN;
 
 	/* we always manually zero the memory once we are done: */
 	gfp &= ~__GFP_ZERO;
-	gfp |= __dma_direct_optimal_gfp_mask(dev, dev->coherent_dma_mask,
-			&phys_limit);
-	page = dma_alloc_contiguous(dev, alloc_size, gfp);
+	gfp |= dma_direct_optimal_gfp_mask(dev, dev->coherent_dma_mask,
+					   &phys_limit);
+	page = dma_alloc_contiguous(dev, size, gfp);
 	if (page && !dma_coherent_ok(dev, page_to_phys(page), size)) {
-		dma_free_contiguous(dev, page, alloc_size);
+		dma_free_contiguous(dev, page, size);
 		page = NULL;
 	}
 again:
 	if (!page)
-		page = alloc_pages_node(node, gfp, get_order(alloc_size));
+		page = alloc_pages_node(node, gfp, get_order(size));
 	if (page && !dma_coherent_ok(dev, page_to_phys(page), size)) {
 		dma_free_contiguous(dev, page, size);
 		page = NULL;
@@ -123,12 +156,18 @@ void *dma_direct_alloc_pages(struct device *dev, size_t size,
 {
 	struct page *page;
 	void *ret;
+	int err;
 
-	if (IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) &&
-	    dma_alloc_need_uncached(dev, attrs) &&
-	    !gfpflags_allow_blocking(gfp)) {
-		ret = dma_alloc_from_pool(PAGE_ALIGN(size), &page, gfp);
-		if (!ret)
+	size = PAGE_ALIGN(size);
+
+	if (dma_should_alloc_from_pool(dev, gfp, attrs)) {
+		u64 phys_mask;
+
+		gfp |= dma_direct_optimal_gfp_mask(dev, dev->coherent_dma_mask,
+				&phys_mask);
+		page = dma_alloc_from_pool(dev, size, &ret, gfp,
+				dma_coherent_ok);
+		if (!page)
 			return NULL;
 		goto done;
 	}
@@ -151,17 +190,20 @@ void *dma_direct_alloc_pages(struct device *dev, size_t size,
 	     dma_alloc_need_uncached(dev, attrs)) ||
 	    (IS_ENABLED(CONFIG_DMA_REMAP) && PageHighMem(page))) {
 		/* remove any dirty cache lines on the kernel alias */
-		arch_dma_prep_coherent(page, PAGE_ALIGN(size));
+		arch_dma_prep_coherent(page, size);
 
 		/* create a coherent mapping */
-		ret = dma_common_contiguous_remap(page, PAGE_ALIGN(size),
+		ret = dma_common_contiguous_remap(page, size,
 				dma_pgprot(dev, PAGE_KERNEL, attrs),
 				__builtin_return_address(0));
-		if (!ret) {
-			dma_free_contiguous(dev, page, size);
-			return ret;
+		if (!ret)
+			goto out_free_pages;
+		if (force_dma_unencrypted(dev)) {
+			err = set_memory_decrypted((unsigned long)ret,
+						   1 << get_order(size));
+			if (err)
+				goto out_free_pages;
 		}
-
 		memset(ret, 0, size);
 		goto done;
 	}
@@ -174,20 +216,25 @@ void *dma_direct_alloc_pages(struct device *dev, size_t size,
 		 * so log an error and fail.
 		 */
 		dev_info(dev, "Rejecting highmem page from CMA.\n");
-		dma_free_contiguous(dev, page, size);
-		return NULL;
+		goto out_free_pages;
 	}
 
 	ret = page_address(page);
-	if (force_dma_unencrypted(dev))
-		set_memory_decrypted((unsigned long)ret, 1 << get_order(size));
+	if (force_dma_unencrypted(dev)) {
+		err = set_memory_decrypted((unsigned long)ret,
+					   1 << get_order(size));
+		if (err)
+			goto out_free_pages;
+	}
 
 	memset(ret, 0, size);
 
-	if (IS_ENABLED(CONFIG_ARCH_HAS_UNCACHED_SEGMENT) &&
+	if (IS_ENABLED(CONFIG_ARCH_HAS_DMA_SET_UNCACHED) &&
 	    dma_alloc_need_uncached(dev, attrs)) {
 		arch_dma_prep_coherent(page, size);
-		ret = uncached_kernel_address(ret);
+		ret = arch_dma_set_uncached(ret, size);
+		if (IS_ERR(ret))
+			goto out_encrypt_pages;
 	}
 done:
 	if (force_dma_unencrypted(dev))
@@ -195,6 +242,18 @@ done:
 	else
 		*dma_handle = phys_to_dma(dev, page_to_phys(page));
 	return ret;
+
+out_encrypt_pages:
+	if (force_dma_unencrypted(dev)) {
+		err = set_memory_encrypted((unsigned long)page_address(page),
+					   1 << get_order(size));
+		/* If memory cannot be re-encrypted, it must be leaked */
+		if (err)
+			return NULL;
+	}
+out_free_pages:
+	dma_free_contiguous(dev, page, size);
+	return NULL;
 }
 
 void dma_direct_free_pages(struct device *dev, size_t size, void *cpu_addr,
@@ -202,6 +261,11 @@ void dma_direct_free_pages(struct device *dev, size_t size, void *cpu_addr,
 {
 	unsigned int page_order = get_order(size);
 
+	/* If cpu_addr is not from an atomic pool, dma_free_from_pool() fails */
+	if (dma_should_free_from_pool(dev, attrs) &&
+	    dma_free_from_pool(dev, cpu_addr, PAGE_ALIGN(size)))
+		return;
+
 	if ((attrs & DMA_ATTR_NO_KERNEL_MAPPING) &&
 	    !force_dma_unencrypted(dev)) {
 		/* cpu_addr is a struct page cookie, not a kernel address */
@@ -209,15 +273,13 @@ void dma_direct_free_pages(struct device *dev, size_t size, void *cpu_addr,
 		return;
 	}
 
-	if (IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) &&
-	    dma_free_from_pool(cpu_addr, PAGE_ALIGN(size)))
-		return;
-
 	if (force_dma_unencrypted(dev))
 		set_memory_encrypted((unsigned long)cpu_addr, 1 << page_order);
 
 	if (IS_ENABLED(CONFIG_DMA_REMAP) && is_vmalloc_addr(cpu_addr))
 		vunmap(cpu_addr);
+	else if (IS_ENABLED(CONFIG_ARCH_HAS_DMA_CLEAR_UNCACHED))
+		arch_dma_clear_uncached(cpu_addr, size);
 
 	dma_free_contiguous(dev, dma_direct_to_page(dev, dma_addr), size);
 }
@@ -225,7 +287,7 @@ void dma_direct_free_pages(struct device *dev, size_t size, void *cpu_addr,
 void *dma_direct_alloc(struct device *dev, size_t size,
 		dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs)
 {
-	if (!IS_ENABLED(CONFIG_ARCH_HAS_UNCACHED_SEGMENT) &&
+	if (!IS_ENABLED(CONFIG_ARCH_HAS_DMA_SET_UNCACHED) &&
 	    !IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) &&
 	    dma_alloc_need_uncached(dev, attrs))
 		return arch_dma_alloc(dev, size, dma_handle, gfp, attrs);
@@ -235,7 +297,7 @@ void *dma_direct_alloc(struct device *dev, size_t size,
 void dma_direct_free(struct device *dev, size_t size,
 		void *cpu_addr, dma_addr_t dma_addr, unsigned long attrs)
 {
-	if (!IS_ENABLED(CONFIG_ARCH_HAS_UNCACHED_SEGMENT) &&
+	if (!IS_ENABLED(CONFIG_ARCH_HAS_DMA_SET_UNCACHED) &&
 	    !IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) &&
 	    dma_alloc_need_uncached(dev, attrs))
 		arch_dma_free(dev, size, cpu_addr, dma_addr, attrs);
@@ -245,19 +307,6 @@ void dma_direct_free(struct device *dev, size_t size,
 
 #if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE) || \
     defined(CONFIG_SWIOTLB)
-void dma_direct_sync_single_for_device(struct device *dev,
-		dma_addr_t addr, size_t size, enum dma_data_direction dir)
-{
-	phys_addr_t paddr = dma_to_phys(dev, addr);
-
-	if (unlikely(is_swiotlb_buffer(paddr)))
-		swiotlb_tbl_sync_single(dev, paddr, size, dir, SYNC_FOR_DEVICE);
-
-	if (!dev_is_dma_coherent(dev))
-		arch_sync_dma_for_device(paddr, size, dir);
-}
-EXPORT_SYMBOL(dma_direct_sync_single_for_device);
-
 void dma_direct_sync_sg_for_device(struct device *dev,
 		struct scatterlist *sgl, int nents, enum dma_data_direction dir)
 {
@@ -276,27 +325,11 @@ void dma_direct_sync_sg_for_device(struct device *dev,
 					dir);
 	}
 }
-EXPORT_SYMBOL(dma_direct_sync_sg_for_device);
 #endif
 
 #if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU) || \
     defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL) || \
     defined(CONFIG_SWIOTLB)
-void dma_direct_sync_single_for_cpu(struct device *dev,
-		dma_addr_t addr, size_t size, enum dma_data_direction dir)
-{
-	phys_addr_t paddr = dma_to_phys(dev, addr);
-
-	if (!dev_is_dma_coherent(dev)) {
-		arch_sync_dma_for_cpu(paddr, size, dir);
-		arch_sync_dma_for_cpu_all();
-	}
-
-	if (unlikely(is_swiotlb_buffer(paddr)))
-		swiotlb_tbl_sync_single(dev, paddr, size, dir, SYNC_FOR_CPU);
-}
-EXPORT_SYMBOL(dma_direct_sync_single_for_cpu);
-
 void dma_direct_sync_sg_for_cpu(struct device *dev,
 		struct scatterlist *sgl, int nents, enum dma_data_direction dir)
 {
@@ -317,20 +350,6 @@ void dma_direct_sync_sg_for_cpu(struct device *dev,
 	if (!dev_is_dma_coherent(dev))
 		arch_sync_dma_for_cpu_all();
 }
-EXPORT_SYMBOL(dma_direct_sync_sg_for_cpu);
-
-void dma_direct_unmap_page(struct device *dev, dma_addr_t addr,
-		size_t size, enum dma_data_direction dir, unsigned long attrs)
-{
-	phys_addr_t phys = dma_to_phys(dev, addr);
-
-	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
-		dma_direct_sync_single_for_cpu(dev, addr, size, dir);
-
-	if (unlikely(is_swiotlb_buffer(phys)))
-		swiotlb_tbl_unmap_single(dev, phys, size, size, dir, attrs);
-}
-EXPORT_SYMBOL(dma_direct_unmap_page);
 
 void dma_direct_unmap_sg(struct device *dev, struct scatterlist *sgl,
 		int nents, enum dma_data_direction dir, unsigned long attrs)
@@ -342,35 +361,8 @@ void dma_direct_unmap_sg(struct device *dev, struct scatterlist *sgl,
 		dma_direct_unmap_page(dev, sg->dma_address, sg_dma_len(sg), dir,
 			     attrs);
 }
-EXPORT_SYMBOL(dma_direct_unmap_sg);
 #endif
 
-dma_addr_t dma_direct_map_page(struct device *dev, struct page *page,
-		unsigned long offset, size_t size, enum dma_data_direction dir,
-		unsigned long attrs)
-{
-	phys_addr_t phys = page_to_phys(page) + offset;
-	dma_addr_t dma_addr = phys_to_dma(dev, phys);
-
-	if (unlikely(swiotlb_force == SWIOTLB_FORCE))
-		return swiotlb_map(dev, phys, size, dir, attrs);
-
-	if (unlikely(!dma_capable(dev, dma_addr, size, true))) {
-		if (swiotlb_force != SWIOTLB_NO_FORCE)
-			return swiotlb_map(dev, phys, size, dir, attrs);
-
-		dev_WARN_ONCE(dev, 1,
-			     "DMA addr %pad+%zu overflow (mask %llx, bus limit %llx).\n",
-			     &dma_addr, size, *dev->dma_mask, dev->bus_dma_limit);
-		return DMA_MAPPING_ERROR;
-	}
-
-	if (!dev_is_dma_coherent(dev) && !(attrs & DMA_ATTR_SKIP_CPU_SYNC))
-		arch_sync_dma_for_device(phys, size, dir);
-	return dma_addr;
-}
-EXPORT_SYMBOL(dma_direct_map_page);
-
 int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, int nents,
 		enum dma_data_direction dir, unsigned long attrs)
 {
@@ -391,7 +383,6 @@ out_unmap:
 	dma_direct_unmap_sg(dev, sgl, i, dir, attrs | DMA_ATTR_SKIP_CPU_SYNC);
 	return 0;
 }
-EXPORT_SYMBOL(dma_direct_map_sg);
 
 dma_addr_t dma_direct_map_resource(struct device *dev, phys_addr_t paddr,
 		size_t size, enum dma_data_direction dir, unsigned long attrs)
@@ -408,7 +399,6 @@ dma_addr_t dma_direct_map_resource(struct device *dev, phys_addr_t paddr,
 
 	return dma_addr;
 }
-EXPORT_SYMBOL(dma_direct_map_resource);
 
 int dma_direct_get_sgtable(struct device *dev, struct sg_table *sgt,
 		void *cpu_addr, dma_addr_t dma_addr, size_t size,
@@ -423,7 +413,6 @@ int dma_direct_get_sgtable(struct device *dev, struct sg_table *sgt,
 	return ret;
 }
 
-#ifdef CONFIG_MMU
 bool dma_direct_can_mmap(struct device *dev)
 {
 	return dev_is_dma_coherent(dev) ||
@@ -449,19 +438,6 @@ int dma_direct_mmap(struct device *dev, struct vm_area_struct *vma,
 	return remap_pfn_range(vma, vma->vm_start, pfn + vma->vm_pgoff,
 			user_count << PAGE_SHIFT, vma->vm_page_prot);
 }
-#else /* CONFIG_MMU */
-bool dma_direct_can_mmap(struct device *dev)
-{
-	return false;
-}
-
-int dma_direct_mmap(struct device *dev, struct vm_area_struct *vma,
-		void *cpu_addr, dma_addr_t dma_addr, size_t size,
-		unsigned long attrs)
-{
-	return -ENXIO;
-}
-#endif /* CONFIG_MMU */
 
 int dma_direct_supported(struct device *dev, u64 mask)
 {
@@ -494,3 +470,9 @@ size_t dma_direct_max_mapping_size(struct device *dev)
 		return swiotlb_max_mapping_size(dev);
 	return SIZE_MAX;
 }
+
+bool dma_direct_need_sync(struct device *dev, dma_addr_t dma_addr)
+{
+	return !dev_is_dma_coherent(dev) ||
+		is_swiotlb_buffer(dma_to_phys(dev, dma_addr));
+}
diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c
index 12ff766ec1fa..0d129421e75f 100644
--- a/kernel/dma/mapping.c
+++ b/kernel/dma/mapping.c
@@ -105,6 +105,196 @@ void *dmam_alloc_attrs(struct device *dev, size_t size, dma_addr_t *dma_handle,
 }
 EXPORT_SYMBOL(dmam_alloc_attrs);
 
+static bool dma_go_direct(struct device *dev, dma_addr_t mask,
+		const struct dma_map_ops *ops)
+{
+	if (likely(!ops))
+		return true;
+#ifdef CONFIG_DMA_OPS_BYPASS
+	if (dev->dma_ops_bypass)
+		return min_not_zero(mask, dev->bus_dma_limit) >=
+			    dma_direct_get_required_mask(dev);
+#endif
+	return false;
+}
+
+
+/*
+ * Check if the devices uses a direct mapping for streaming DMA operations.
+ * This allows IOMMU drivers to set a bypass mode if the DMA mask is large
+ * enough.
+ */
+static inline bool dma_alloc_direct(struct device *dev,
+		const struct dma_map_ops *ops)
+{
+	return dma_go_direct(dev, dev->coherent_dma_mask, ops);
+}
+
+static inline bool dma_map_direct(struct device *dev,
+		const struct dma_map_ops *ops)
+{
+	return dma_go_direct(dev, *dev->dma_mask, ops);
+}
+
+dma_addr_t dma_map_page_attrs(struct device *dev, struct page *page,
+		size_t offset, size_t size, enum dma_data_direction dir,
+		unsigned long attrs)
+{
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+	dma_addr_t addr;
+
+	BUG_ON(!valid_dma_direction(dir));
+	if (dma_map_direct(dev, ops))
+		addr = dma_direct_map_page(dev, page, offset, size, dir, attrs);
+	else
+		addr = ops->map_page(dev, page, offset, size, dir, attrs);
+	debug_dma_map_page(dev, page, offset, size, dir, addr);
+
+	return addr;
+}
+EXPORT_SYMBOL(dma_map_page_attrs);
+
+void dma_unmap_page_attrs(struct device *dev, dma_addr_t addr, size_t size,
+		enum dma_data_direction dir, unsigned long attrs)
+{
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+
+	BUG_ON(!valid_dma_direction(dir));
+	if (dma_map_direct(dev, ops))
+		dma_direct_unmap_page(dev, addr, size, dir, attrs);
+	else if (ops->unmap_page)
+		ops->unmap_page(dev, addr, size, dir, attrs);
+	debug_dma_unmap_page(dev, addr, size, dir);
+}
+EXPORT_SYMBOL(dma_unmap_page_attrs);
+
+/*
+ * dma_maps_sg_attrs returns 0 on error and > 0 on success.
+ * It should never return a value < 0.
+ */
+int dma_map_sg_attrs(struct device *dev, struct scatterlist *sg, int nents,
+		enum dma_data_direction dir, unsigned long attrs)
+{
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+	int ents;
+
+	BUG_ON(!valid_dma_direction(dir));
+	if (dma_map_direct(dev, ops))
+		ents = dma_direct_map_sg(dev, sg, nents, dir, attrs);
+	else
+		ents = ops->map_sg(dev, sg, nents, dir, attrs);
+	BUG_ON(ents < 0);
+	debug_dma_map_sg(dev, sg, nents, ents, dir);
+
+	return ents;
+}
+EXPORT_SYMBOL(dma_map_sg_attrs);
+
+void dma_unmap_sg_attrs(struct device *dev, struct scatterlist *sg,
+				      int nents, enum dma_data_direction dir,
+				      unsigned long attrs)
+{
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+
+	BUG_ON(!valid_dma_direction(dir));
+	debug_dma_unmap_sg(dev, sg, nents, dir);
+	if (dma_map_direct(dev, ops))
+		dma_direct_unmap_sg(dev, sg, nents, dir, attrs);
+	else if (ops->unmap_sg)
+		ops->unmap_sg(dev, sg, nents, dir, attrs);
+}
+EXPORT_SYMBOL(dma_unmap_sg_attrs);
+
+dma_addr_t dma_map_resource(struct device *dev, phys_addr_t phys_addr,
+		size_t size, enum dma_data_direction dir, unsigned long attrs)
+{
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+	dma_addr_t addr = DMA_MAPPING_ERROR;
+
+	BUG_ON(!valid_dma_direction(dir));
+
+	/* Don't allow RAM to be mapped */
+	if (WARN_ON_ONCE(pfn_valid(PHYS_PFN(phys_addr))))
+		return DMA_MAPPING_ERROR;
+
+	if (dma_map_direct(dev, ops))
+		addr = dma_direct_map_resource(dev, phys_addr, size, dir, attrs);
+	else if (ops->map_resource)
+		addr = ops->map_resource(dev, phys_addr, size, dir, attrs);
+
+	debug_dma_map_resource(dev, phys_addr, size, dir, addr);
+	return addr;
+}
+EXPORT_SYMBOL(dma_map_resource);
+
+void dma_unmap_resource(struct device *dev, dma_addr_t addr, size_t size,
+		enum dma_data_direction dir, unsigned long attrs)
+{
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+
+	BUG_ON(!valid_dma_direction(dir));
+	if (!dma_map_direct(dev, ops) && ops->unmap_resource)
+		ops->unmap_resource(dev, addr, size, dir, attrs);
+	debug_dma_unmap_resource(dev, addr, size, dir);
+}
+EXPORT_SYMBOL(dma_unmap_resource);
+
+void dma_sync_single_for_cpu(struct device *dev, dma_addr_t addr, size_t size,
+		enum dma_data_direction dir)
+{
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+
+	BUG_ON(!valid_dma_direction(dir));
+	if (dma_map_direct(dev, ops))
+		dma_direct_sync_single_for_cpu(dev, addr, size, dir);
+	else if (ops->sync_single_for_cpu)
+		ops->sync_single_for_cpu(dev, addr, size, dir);
+	debug_dma_sync_single_for_cpu(dev, addr, size, dir);
+}
+EXPORT_SYMBOL(dma_sync_single_for_cpu);
+
+void dma_sync_single_for_device(struct device *dev, dma_addr_t addr,
+		size_t size, enum dma_data_direction dir)
+{
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+
+	BUG_ON(!valid_dma_direction(dir));
+	if (dma_map_direct(dev, ops))
+		dma_direct_sync_single_for_device(dev, addr, size, dir);
+	else if (ops->sync_single_for_device)
+		ops->sync_single_for_device(dev, addr, size, dir);
+	debug_dma_sync_single_for_device(dev, addr, size, dir);
+}
+EXPORT_SYMBOL(dma_sync_single_for_device);
+
+void dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg,
+		    int nelems, enum dma_data_direction dir)
+{
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+
+	BUG_ON(!valid_dma_direction(dir));
+	if (dma_map_direct(dev, ops))
+		dma_direct_sync_sg_for_cpu(dev, sg, nelems, dir);
+	else if (ops->sync_sg_for_cpu)
+		ops->sync_sg_for_cpu(dev, sg, nelems, dir);
+	debug_dma_sync_sg_for_cpu(dev, sg, nelems, dir);
+}
+EXPORT_SYMBOL(dma_sync_sg_for_cpu);
+
+void dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg,
+		       int nelems, enum dma_data_direction dir)
+{
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+
+	BUG_ON(!valid_dma_direction(dir));
+	if (dma_map_direct(dev, ops))
+		dma_direct_sync_sg_for_device(dev, sg, nelems, dir);
+	else if (ops->sync_sg_for_device)
+		ops->sync_sg_for_device(dev, sg, nelems, dir);
+	debug_dma_sync_sg_for_device(dev, sg, nelems, dir);
+}
+EXPORT_SYMBOL(dma_sync_sg_for_device);
+
 /*
  * Create scatter-list for the already allocated DMA buffer.
  */
@@ -138,7 +328,7 @@ int dma_get_sgtable_attrs(struct device *dev, struct sg_table *sgt,
 {
 	const struct dma_map_ops *ops = get_dma_ops(dev);
 
-	if (dma_is_direct(ops))
+	if (dma_alloc_direct(dev, ops))
 		return dma_direct_get_sgtable(dev, sgt, cpu_addr, dma_addr,
 				size, attrs);
 	if (!ops->get_sgtable)
@@ -154,6 +344,8 @@ EXPORT_SYMBOL(dma_get_sgtable_attrs);
  */
 pgprot_t dma_pgprot(struct device *dev, pgprot_t prot, unsigned long attrs)
 {
+	if (force_dma_unencrypted(dev))
+		prot = pgprot_decrypted(prot);
 	if (dev_is_dma_coherent(dev) ||
 	    (IS_ENABLED(CONFIG_DMA_NONCOHERENT_CACHE_SYNC) &&
              (attrs & DMA_ATTR_NON_CONSISTENT)))
@@ -206,7 +398,7 @@ bool dma_can_mmap(struct device *dev)
 {
 	const struct dma_map_ops *ops = get_dma_ops(dev);
 
-	if (dma_is_direct(ops))
+	if (dma_alloc_direct(dev, ops))
 		return dma_direct_can_mmap(dev);
 	return ops->mmap != NULL;
 }
@@ -231,7 +423,7 @@ int dma_mmap_attrs(struct device *dev, struct vm_area_struct *vma,
 {
 	const struct dma_map_ops *ops = get_dma_ops(dev);
 
-	if (dma_is_direct(ops))
+	if (dma_alloc_direct(dev, ops))
 		return dma_direct_mmap(dev, vma, cpu_addr, dma_addr, size,
 				attrs);
 	if (!ops->mmap)
@@ -244,7 +436,7 @@ u64 dma_get_required_mask(struct device *dev)
 {
 	const struct dma_map_ops *ops = get_dma_ops(dev);
 
-	if (dma_is_direct(ops))
+	if (dma_alloc_direct(dev, ops))
 		return dma_direct_get_required_mask(dev);
 	if (ops->get_required_mask)
 		return ops->get_required_mask(dev);
@@ -275,7 +467,7 @@ void *dma_alloc_attrs(struct device *dev, size_t size, dma_addr_t *dma_handle,
 	/* let the implementation decide on the zone to allocate from: */
 	flag &= ~(__GFP_DMA | __GFP_DMA32 | __GFP_HIGHMEM);
 
-	if (dma_is_direct(ops))
+	if (dma_alloc_direct(dev, ops))
 		cpu_addr = dma_direct_alloc(dev, size, dma_handle, flag, attrs);
 	else if (ops->alloc)
 		cpu_addr = ops->alloc(dev, size, dma_handle, flag, attrs);
@@ -307,7 +499,7 @@ void dma_free_attrs(struct device *dev, size_t size, void *cpu_addr,
 		return;
 
 	debug_dma_free_coherent(dev, size, cpu_addr, dma_handle);
-	if (dma_is_direct(ops))
+	if (dma_alloc_direct(dev, ops))
 		dma_direct_free(dev, size, cpu_addr, dma_handle, attrs);
 	else if (ops->free)
 		ops->free(dev, size, cpu_addr, dma_handle, attrs);
@@ -318,7 +510,11 @@ int dma_supported(struct device *dev, u64 mask)
 {
 	const struct dma_map_ops *ops = get_dma_ops(dev);
 
-	if (dma_is_direct(ops))
+	/*
+	 * ->dma_supported sets the bypass flag, so we must always call
+	 * into the method here unless the device is truly direct mapped.
+	 */
+	if (!ops)
 		return dma_direct_supported(dev, mask);
 	if (!ops->dma_supported)
 		return 1;
@@ -374,7 +570,7 @@ void dma_cache_sync(struct device *dev, void *vaddr, size_t size,
 
 	BUG_ON(!valid_dma_direction(dir));
 
-	if (dma_is_direct(ops))
+	if (dma_alloc_direct(dev, ops))
 		arch_dma_cache_sync(dev, vaddr, size, dir);
 	else if (ops->cache_sync)
 		ops->cache_sync(dev, vaddr, size, dir);
@@ -386,7 +582,7 @@ size_t dma_max_mapping_size(struct device *dev)
 	const struct dma_map_ops *ops = get_dma_ops(dev);
 	size_t size = SIZE_MAX;
 
-	if (dma_is_direct(ops))
+	if (dma_map_direct(dev, ops))
 		size = dma_direct_max_mapping_size(dev);
 	else if (ops && ops->max_mapping_size)
 		size = ops->max_mapping_size(dev);
@@ -395,6 +591,16 @@ size_t dma_max_mapping_size(struct device *dev)
 }
 EXPORT_SYMBOL_GPL(dma_max_mapping_size);
 
+bool dma_need_sync(struct device *dev, dma_addr_t dma_addr)
+{
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+
+	if (dma_map_direct(dev, ops))
+		return dma_direct_need_sync(dev, dma_addr);
+	return ops->sync_single_for_cpu || ops->sync_single_for_device;
+}
+EXPORT_SYMBOL_GPL(dma_need_sync);
+
 unsigned long dma_get_merge_boundary(struct device *dev)
 {
 	const struct dma_map_ops *ops = get_dma_ops(dev);
diff --git a/kernel/dma/pool.c b/kernel/dma/pool.c
new file mode 100644
index 000000000000..1281c0f0442b
--- /dev/null
+++ b/kernel/dma/pool.c
@@ -0,0 +1,299 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2012 ARM Ltd.
+ * Copyright (C) 2020 Google LLC
+ */
+#include <linux/cma.h>
+#include <linux/debugfs.h>
+#include <linux/dma-contiguous.h>
+#include <linux/dma-direct.h>
+#include <linux/dma-noncoherent.h>
+#include <linux/init.h>
+#include <linux/genalloc.h>
+#include <linux/set_memory.h>
+#include <linux/slab.h>
+#include <linux/workqueue.h>
+
+static struct gen_pool *atomic_pool_dma __ro_after_init;
+static unsigned long pool_size_dma;
+static struct gen_pool *atomic_pool_dma32 __ro_after_init;
+static unsigned long pool_size_dma32;
+static struct gen_pool *atomic_pool_kernel __ro_after_init;
+static unsigned long pool_size_kernel;
+
+/* Size can be defined by the coherent_pool command line */
+static size_t atomic_pool_size;
+
+/* Dynamic background expansion when the atomic pool is near capacity */
+static struct work_struct atomic_pool_work;
+
+static int __init early_coherent_pool(char *p)
+{
+	atomic_pool_size = memparse(p, &p);
+	return 0;
+}
+early_param("coherent_pool", early_coherent_pool);
+
+static void __init dma_atomic_pool_debugfs_init(void)
+{
+	struct dentry *root;
+
+	root = debugfs_create_dir("dma_pools", NULL);
+	if (IS_ERR_OR_NULL(root))
+		return;
+
+	debugfs_create_ulong("pool_size_dma", 0400, root, &pool_size_dma);
+	debugfs_create_ulong("pool_size_dma32", 0400, root, &pool_size_dma32);
+	debugfs_create_ulong("pool_size_kernel", 0400, root, &pool_size_kernel);
+}
+
+static void dma_atomic_pool_size_add(gfp_t gfp, size_t size)
+{
+	if (gfp & __GFP_DMA)
+		pool_size_dma += size;
+	else if (gfp & __GFP_DMA32)
+		pool_size_dma32 += size;
+	else
+		pool_size_kernel += size;
+}
+
+static bool cma_in_zone(gfp_t gfp)
+{
+	unsigned long size;
+	phys_addr_t end;
+	struct cma *cma;
+
+	cma = dev_get_cma_area(NULL);
+	if (!cma)
+		return false;
+
+	size = cma_get_size(cma);
+	if (!size)
+		return false;
+
+	/* CMA can't cross zone boundaries, see cma_activate_area() */
+	end = cma_get_base(cma) + size - 1;
+	if (IS_ENABLED(CONFIG_ZONE_DMA) && (gfp & GFP_DMA))
+		return end <= DMA_BIT_MASK(zone_dma_bits);
+	if (IS_ENABLED(CONFIG_ZONE_DMA32) && (gfp & GFP_DMA32))
+		return end <= DMA_BIT_MASK(32);
+	return true;
+}
+
+static int atomic_pool_expand(struct gen_pool *pool, size_t pool_size,
+			      gfp_t gfp)
+{
+	unsigned int order;
+	struct page *page = NULL;
+	void *addr;
+	int ret = -ENOMEM;
+
+	/* Cannot allocate larger than MAX_ORDER-1 */
+	order = min(get_order(pool_size), MAX_ORDER-1);
+
+	do {
+		pool_size = 1 << (PAGE_SHIFT + order);
+		if (cma_in_zone(gfp))
+			page = dma_alloc_from_contiguous(NULL, 1 << order,
+							 order, false);
+		if (!page)
+			page = alloc_pages(gfp, order);
+	} while (!page && order-- > 0);
+	if (!page)
+		goto out;
+
+	arch_dma_prep_coherent(page, pool_size);
+
+#ifdef CONFIG_DMA_DIRECT_REMAP
+	addr = dma_common_contiguous_remap(page, pool_size,
+					   pgprot_dmacoherent(PAGE_KERNEL),
+					   __builtin_return_address(0));
+	if (!addr)
+		goto free_page;
+#else
+	addr = page_to_virt(page);
+#endif
+	/*
+	 * Memory in the atomic DMA pools must be unencrypted, the pools do not
+	 * shrink so no re-encryption occurs in dma_direct_free_pages().
+	 */
+	ret = set_memory_decrypted((unsigned long)page_to_virt(page),
+				   1 << order);
+	if (ret)
+		goto remove_mapping;
+	ret = gen_pool_add_virt(pool, (unsigned long)addr, page_to_phys(page),
+				pool_size, NUMA_NO_NODE);
+	if (ret)
+		goto encrypt_mapping;
+
+	dma_atomic_pool_size_add(gfp, pool_size);
+	return 0;
+
+encrypt_mapping:
+	ret = set_memory_encrypted((unsigned long)page_to_virt(page),
+				   1 << order);
+	if (WARN_ON_ONCE(ret)) {
+		/* Decrypt succeeded but encrypt failed, purposely leak */
+		goto out;
+	}
+remove_mapping:
+#ifdef CONFIG_DMA_DIRECT_REMAP
+	dma_common_free_remap(addr, pool_size);
+#endif
+free_page: __maybe_unused
+	__free_pages(page, order);
+out:
+	return ret;
+}
+
+static void atomic_pool_resize(struct gen_pool *pool, gfp_t gfp)
+{
+	if (pool && gen_pool_avail(pool) < atomic_pool_size)
+		atomic_pool_expand(pool, gen_pool_size(pool), gfp);
+}
+
+static void atomic_pool_work_fn(struct work_struct *work)
+{
+	if (IS_ENABLED(CONFIG_ZONE_DMA))
+		atomic_pool_resize(atomic_pool_dma,
+				   GFP_KERNEL | GFP_DMA);
+	if (IS_ENABLED(CONFIG_ZONE_DMA32))
+		atomic_pool_resize(atomic_pool_dma32,
+				   GFP_KERNEL | GFP_DMA32);
+	atomic_pool_resize(atomic_pool_kernel, GFP_KERNEL);
+}
+
+static __init struct gen_pool *__dma_atomic_pool_init(size_t pool_size,
+						      gfp_t gfp)
+{
+	struct gen_pool *pool;
+	int ret;
+
+	pool = gen_pool_create(PAGE_SHIFT, NUMA_NO_NODE);
+	if (!pool)
+		return NULL;
+
+	gen_pool_set_algo(pool, gen_pool_first_fit_order_align, NULL);
+
+	ret = atomic_pool_expand(pool, pool_size, gfp);
+	if (ret) {
+		gen_pool_destroy(pool);
+		pr_err("DMA: failed to allocate %zu KiB %pGg pool for atomic allocation\n",
+		       pool_size >> 10, &gfp);
+		return NULL;
+	}
+
+	pr_info("DMA: preallocated %zu KiB %pGg pool for atomic allocations\n",
+		gen_pool_size(pool) >> 10, &gfp);
+	return pool;
+}
+
+static int __init dma_atomic_pool_init(void)
+{
+	int ret = 0;
+
+	/*
+	 * If coherent_pool was not used on the command line, default the pool
+	 * sizes to 128KB per 1GB of memory, min 128KB, max MAX_ORDER-1.
+	 */
+	if (!atomic_pool_size) {
+		unsigned long pages = totalram_pages() / (SZ_1G / SZ_128K);
+		pages = min_t(unsigned long, pages, MAX_ORDER_NR_PAGES);
+		atomic_pool_size = max_t(size_t, pages << PAGE_SHIFT, SZ_128K);
+	}
+	INIT_WORK(&atomic_pool_work, atomic_pool_work_fn);
+
+	atomic_pool_kernel = __dma_atomic_pool_init(atomic_pool_size,
+						    GFP_KERNEL);
+	if (!atomic_pool_kernel)
+		ret = -ENOMEM;
+	if (IS_ENABLED(CONFIG_ZONE_DMA)) {
+		atomic_pool_dma = __dma_atomic_pool_init(atomic_pool_size,
+						GFP_KERNEL | GFP_DMA);
+		if (!atomic_pool_dma)
+			ret = -ENOMEM;
+	}
+	if (IS_ENABLED(CONFIG_ZONE_DMA32)) {
+		atomic_pool_dma32 = __dma_atomic_pool_init(atomic_pool_size,
+						GFP_KERNEL | GFP_DMA32);
+		if (!atomic_pool_dma32)
+			ret = -ENOMEM;
+	}
+
+	dma_atomic_pool_debugfs_init();
+	return ret;
+}
+postcore_initcall(dma_atomic_pool_init);
+
+static inline struct gen_pool *dma_guess_pool(struct gen_pool *prev, gfp_t gfp)
+{
+	if (prev == NULL) {
+		if (IS_ENABLED(CONFIG_ZONE_DMA32) && (gfp & GFP_DMA32))
+			return atomic_pool_dma32;
+		if (IS_ENABLED(CONFIG_ZONE_DMA) && (gfp & GFP_DMA))
+			return atomic_pool_dma;
+		return atomic_pool_kernel;
+	}
+	if (prev == atomic_pool_kernel)
+		return atomic_pool_dma32 ? atomic_pool_dma32 : atomic_pool_dma;
+	if (prev == atomic_pool_dma32)
+		return atomic_pool_dma;
+	return NULL;
+}
+
+static struct page *__dma_alloc_from_pool(struct device *dev, size_t size,
+		struct gen_pool *pool, void **cpu_addr,
+		bool (*phys_addr_ok)(struct device *, phys_addr_t, size_t))
+{
+	unsigned long addr;
+	phys_addr_t phys;
+
+	addr = gen_pool_alloc(pool, size);
+	if (!addr)
+		return NULL;
+
+	phys = gen_pool_virt_to_phys(pool, addr);
+	if (phys_addr_ok && !phys_addr_ok(dev, phys, size)) {
+		gen_pool_free(pool, addr, size);
+		return NULL;
+	}
+
+	if (gen_pool_avail(pool) < atomic_pool_size)
+		schedule_work(&atomic_pool_work);
+
+	*cpu_addr = (void *)addr;
+	memset(*cpu_addr, 0, size);
+	return pfn_to_page(__phys_to_pfn(phys));
+}
+
+struct page *dma_alloc_from_pool(struct device *dev, size_t size,
+		void **cpu_addr, gfp_t gfp,
+		bool (*phys_addr_ok)(struct device *, phys_addr_t, size_t))
+{
+	struct gen_pool *pool = NULL;
+	struct page *page;
+
+	while ((pool = dma_guess_pool(pool, gfp))) {
+		page = __dma_alloc_from_pool(dev, size, pool, cpu_addr,
+					     phys_addr_ok);
+		if (page)
+			return page;
+	}
+
+	WARN(1, "Failed to get suitable pool for %s\n", dev_name(dev));
+	return NULL;
+}
+
+bool dma_free_from_pool(struct device *dev, void *start, size_t size)
+{
+	struct gen_pool *pool = NULL;
+
+	while ((pool = dma_guess_pool(pool, 0))) {
+		if (!gen_pool_has_addr(pool, (unsigned long)start, size))
+			continue;
+		gen_pool_free(pool, (unsigned long)start, size);
+		return true;
+	}
+
+	return false;
+}
diff --git a/kernel/dma/remap.c b/kernel/dma/remap.c
index d14cbc83986a..78b23f089cf1 100644
--- a/kernel/dma/remap.c
+++ b/kernel/dma/remap.c
@@ -1,13 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0
 /*
- * Copyright (C) 2012 ARM Ltd.
  * Copyright (c) 2014 The Linux Foundation
  */
-#include <linux/dma-direct.h>
-#include <linux/dma-noncoherent.h>
-#include <linux/dma-contiguous.h>
-#include <linux/init.h>
-#include <linux/genalloc.h>
+#include <linux/dma-mapping.h>
 #include <linux/slab.h>
 #include <linux/vmalloc.h>
 
@@ -20,23 +15,6 @@ struct page **dma_common_find_pages(void *cpu_addr)
 	return area->pages;
 }
 
-static struct vm_struct *__dma_common_pages_remap(struct page **pages,
-			size_t size, pgprot_t prot, const void *caller)
-{
-	struct vm_struct *area;
-
-	area = get_vm_area_caller(size, VM_DMA_COHERENT, caller);
-	if (!area)
-		return NULL;
-
-	if (map_vm_area(area, prot, pages)) {
-		vunmap(area->addr);
-		return NULL;
-	}
-
-	return area;
-}
-
 /*
  * Remaps an array of PAGE_SIZE pages into another vm_area.
  * Cannot be used in non-sleeping contexts
@@ -44,15 +22,13 @@ static struct vm_struct *__dma_common_pages_remap(struct page **pages,
 void *dma_common_pages_remap(struct page **pages, size_t size,
 			 pgprot_t prot, const void *caller)
 {
-	struct vm_struct *area;
-
-	area = __dma_common_pages_remap(pages, size, prot, caller);
-	if (!area)
-		return NULL;
+	void *vaddr;
 
-	area->pages = pages;
-
-	return area->addr;
+	vaddr = vmap(pages, PAGE_ALIGN(size) >> PAGE_SHIFT,
+		     VM_DMA_COHERENT, prot);
+	if (vaddr)
+		find_vm_area(vaddr)->pages = pages;
+	return vaddr;
 }
 
 /*
@@ -62,24 +38,20 @@ void *dma_common_pages_remap(struct page **pages, size_t size,
 void *dma_common_contiguous_remap(struct page *page, size_t size,
 			pgprot_t prot, const void *caller)
 {
-	int i;
+	int count = PAGE_ALIGN(size) >> PAGE_SHIFT;
 	struct page **pages;
-	struct vm_struct *area;
+	void *vaddr;
+	int i;
 
-	pages = kmalloc(sizeof(struct page *) << get_order(size), GFP_KERNEL);
+	pages = kmalloc_array(count, sizeof(struct page *), GFP_KERNEL);
 	if (!pages)
 		return NULL;
-
-	for (i = 0; i < (size >> PAGE_SHIFT); i++)
+	for (i = 0; i < count; i++)
 		pages[i] = nth_page(page, i);
-
-	area = __dma_common_pages_remap(pages, size, prot, caller);
-
+	vaddr = vmap(pages, count, VM_DMA_COHERENT, prot);
 	kfree(pages);
 
-	if (!area)
-		return NULL;
-	return area->addr;
+	return vaddr;
 }
 
 /*
@@ -97,117 +69,3 @@ void dma_common_free_remap(void *cpu_addr, size_t size)
 	unmap_kernel_range((unsigned long)cpu_addr, PAGE_ALIGN(size));
 	vunmap(cpu_addr);
 }
-
-#ifdef CONFIG_DMA_DIRECT_REMAP
-static struct gen_pool *atomic_pool __ro_after_init;
-
-#define DEFAULT_DMA_COHERENT_POOL_SIZE  SZ_256K
-static size_t atomic_pool_size __initdata = DEFAULT_DMA_COHERENT_POOL_SIZE;
-
-static int __init early_coherent_pool(char *p)
-{
-	atomic_pool_size = memparse(p, &p);
-	return 0;
-}
-early_param("coherent_pool", early_coherent_pool);
-
-static gfp_t dma_atomic_pool_gfp(void)
-{
-	if (IS_ENABLED(CONFIG_ZONE_DMA))
-		return GFP_DMA;
-	if (IS_ENABLED(CONFIG_ZONE_DMA32))
-		return GFP_DMA32;
-	return GFP_KERNEL;
-}
-
-static int __init dma_atomic_pool_init(void)
-{
-	unsigned int pool_size_order = get_order(atomic_pool_size);
-	unsigned long nr_pages = atomic_pool_size >> PAGE_SHIFT;
-	struct page *page;
-	void *addr;
-	int ret;
-
-	if (dev_get_cma_area(NULL))
-		page = dma_alloc_from_contiguous(NULL, nr_pages,
-						 pool_size_order, false);
-	else
-		page = alloc_pages(dma_atomic_pool_gfp(), pool_size_order);
-	if (!page)
-		goto out;
-
-	arch_dma_prep_coherent(page, atomic_pool_size);
-
-	atomic_pool = gen_pool_create(PAGE_SHIFT, -1);
-	if (!atomic_pool)
-		goto free_page;
-
-	addr = dma_common_contiguous_remap(page, atomic_pool_size,
-					   pgprot_dmacoherent(PAGE_KERNEL),
-					   __builtin_return_address(0));
-	if (!addr)
-		goto destroy_genpool;
-
-	ret = gen_pool_add_virt(atomic_pool, (unsigned long)addr,
-				page_to_phys(page), atomic_pool_size, -1);
-	if (ret)
-		goto remove_mapping;
-	gen_pool_set_algo(atomic_pool, gen_pool_first_fit_order_align, NULL);
-
-	pr_info("DMA: preallocated %zu KiB pool for atomic allocations\n",
-		atomic_pool_size / 1024);
-	return 0;
-
-remove_mapping:
-	dma_common_free_remap(addr, atomic_pool_size);
-destroy_genpool:
-	gen_pool_destroy(atomic_pool);
-	atomic_pool = NULL;
-free_page:
-	if (!dma_release_from_contiguous(NULL, page, nr_pages))
-		__free_pages(page, pool_size_order);
-out:
-	pr_err("DMA: failed to allocate %zu KiB pool for atomic coherent allocation\n",
-		atomic_pool_size / 1024);
-	return -ENOMEM;
-}
-postcore_initcall(dma_atomic_pool_init);
-
-bool dma_in_atomic_pool(void *start, size_t size)
-{
-	if (unlikely(!atomic_pool))
-		return false;
-
-	return gen_pool_has_addr(atomic_pool, (unsigned long)start, size);
-}
-
-void *dma_alloc_from_pool(size_t size, struct page **ret_page, gfp_t flags)
-{
-	unsigned long val;
-	void *ptr = NULL;
-
-	if (!atomic_pool) {
-		WARN(1, "coherent pool not initialised!\n");
-		return NULL;
-	}
-
-	val = gen_pool_alloc(atomic_pool, size);
-	if (val) {
-		phys_addr_t phys = gen_pool_virt_to_phys(atomic_pool, val);
-
-		*ret_page = pfn_to_page(__phys_to_pfn(phys));
-		ptr = (void *)val;
-		memset(ptr, 0, size);
-	}
-
-	return ptr;
-}
-
-bool dma_free_from_pool(void *start, size_t size)
-{
-	if (!dma_in_atomic_pool(start, size))
-		return false;
-	gen_pool_free(atomic_pool, (unsigned long)start, size);
-	return true;
-}
-#endif /* CONFIG_DMA_DIRECT_REMAP */
diff --git a/kernel/entry/Makefile b/kernel/entry/Makefile
new file mode 100644
index 000000000000..34c8a3f1c735
--- /dev/null
+++ b/kernel/entry/Makefile
@@ -0,0 +1,13 @@
+# SPDX-License-Identifier: GPL-2.0
+
+# Prevent the noinstr section from being pestered by sanitizer and other goodies
+# as long as these things cannot be disabled per function.
+KASAN_SANITIZE := n
+UBSAN_SANITIZE := n
+KCOV_INSTRUMENT := n
+
+CFLAGS_REMOVE_common.o	 = -fstack-protector -fstack-protector-strong
+CFLAGS_common.o		+= -fno-stack-protector
+
+obj-$(CONFIG_GENERIC_ENTRY) 		+= common.o
+obj-$(CONFIG_KVM_XFER_TO_GUEST_WORK)	+= kvm.o
diff --git a/kernel/entry/common.c b/kernel/entry/common.c
new file mode 100644
index 000000000000..fcae019158ca
--- /dev/null
+++ b/kernel/entry/common.c
@@ -0,0 +1,375 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/context_tracking.h>
+#include <linux/entry-common.h>
+#include <linux/livepatch.h>
+#include <linux/audit.h>
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/syscalls.h>
+
+/**
+ * enter_from_user_mode - Establish state when coming from user mode
+ *
+ * Syscall/interrupt entry disables interrupts, but user mode is traced as
+ * interrupts enabled. Also with NO_HZ_FULL RCU might be idle.
+ *
+ * 1) Tell lockdep that interrupts are disabled
+ * 2) Invoke context tracking if enabled to reactivate RCU
+ * 3) Trace interrupts off state
+ */
+static __always_inline void enter_from_user_mode(struct pt_regs *regs)
+{
+	arch_check_user_regs(regs);
+	lockdep_hardirqs_off(CALLER_ADDR0);
+
+	CT_WARN_ON(ct_state() != CONTEXT_USER);
+	user_exit_irqoff();
+
+	instrumentation_begin();
+	trace_hardirqs_off_finish();
+	instrumentation_end();
+}
+
+static inline void syscall_enter_audit(struct pt_regs *regs, long syscall)
+{
+	if (unlikely(audit_context())) {
+		unsigned long args[6];
+
+		syscall_get_arguments(current, regs, args);
+		audit_syscall_entry(syscall, args[0], args[1], args[2], args[3]);
+	}
+}
+
+static long syscall_trace_enter(struct pt_regs *regs, long syscall,
+				unsigned long ti_work)
+{
+	long ret = 0;
+
+	/* Handle ptrace */
+	if (ti_work & (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_EMU)) {
+		ret = arch_syscall_enter_tracehook(regs);
+		if (ret || (ti_work & _TIF_SYSCALL_EMU))
+			return -1L;
+	}
+
+	/* Do seccomp after ptrace, to catch any tracer changes. */
+	if (ti_work & _TIF_SECCOMP) {
+		ret = __secure_computing(NULL);
+		if (ret == -1L)
+			return ret;
+	}
+
+	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);
+}
+
+noinstr long syscall_enter_from_user_mode(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;
+}
+
+/**
+ * exit_to_user_mode - Fixup state when exiting to user mode
+ *
+ * Syscall/interupt exit enables interrupts, but the kernel state is
+ * interrupts disabled when this is invoked. Also tell RCU about it.
+ *
+ * 1) Trace interrupts on state
+ * 2) Invoke context tracking if enabled to adjust RCU state
+ * 3) Invoke architecture specific last minute exit code, e.g. speculation
+ *    mitigations, etc.
+ * 4) Tell lockdep that interrupts are enabled
+ */
+static __always_inline void exit_to_user_mode(void)
+{
+	instrumentation_begin();
+	trace_hardirqs_on_prepare();
+	lockdep_hardirqs_on_prepare(CALLER_ADDR0);
+	instrumentation_end();
+
+	user_enter_irqoff();
+	arch_exit_to_user_mode();
+	lockdep_hardirqs_on(CALLER_ADDR0);
+}
+
+/* Workaround to allow gradual conversion of architecture code */
+void __weak arch_do_signal(struct pt_regs *regs) { }
+
+static unsigned long exit_to_user_mode_loop(struct pt_regs *regs,
+					    unsigned long ti_work)
+{
+	/*
+	 * Before returning to user space ensure that all pending work
+	 * items have been completed.
+	 */
+	while (ti_work & EXIT_TO_USER_MODE_WORK) {
+
+		local_irq_enable_exit_to_user(ti_work);
+
+		if (ti_work & _TIF_NEED_RESCHED)
+			schedule();
+
+		if (ti_work & _TIF_UPROBE)
+			uprobe_notify_resume(regs);
+
+		if (ti_work & _TIF_PATCH_PENDING)
+			klp_update_patch_state(current);
+
+		if (ti_work & _TIF_SIGPENDING)
+			arch_do_signal(regs);
+
+		if (ti_work & _TIF_NOTIFY_RESUME) {
+			clear_thread_flag(TIF_NOTIFY_RESUME);
+			tracehook_notify_resume(regs);
+			rseq_handle_notify_resume(NULL, regs);
+		}
+
+		/* Architecture specific TIF work */
+		arch_exit_to_user_mode_work(regs, ti_work);
+
+		/*
+		 * Disable interrupts and reevaluate the work flags as they
+		 * might have changed while interrupts and preemption was
+		 * enabled above.
+		 */
+		local_irq_disable_exit_to_user();
+		ti_work = READ_ONCE(current_thread_info()->flags);
+	}
+
+	/* Return the latest work state for arch_exit_to_user_mode() */
+	return ti_work;
+}
+
+static void exit_to_user_mode_prepare(struct pt_regs *regs)
+{
+	unsigned long ti_work = READ_ONCE(current_thread_info()->flags);
+
+	lockdep_assert_irqs_disabled();
+
+	if (unlikely(ti_work & EXIT_TO_USER_MODE_WORK))
+		ti_work = exit_to_user_mode_loop(regs, ti_work);
+
+	arch_exit_to_user_mode_prepare(regs, ti_work);
+
+	/* Ensure that the address limit is intact and no locks are held */
+	addr_limit_user_check();
+	lockdep_assert_irqs_disabled();
+	lockdep_sys_exit();
+}
+
+#ifndef _TIF_SINGLESTEP
+static inline bool report_single_step(unsigned long ti_work)
+{
+	return false;
+}
+#else
+/*
+ * If TIF_SYSCALL_EMU is set, then the only reason to report is when
+ * TIF_SINGLESTEP is set (i.e. PTRACE_SYSEMU_SINGLESTEP).  This syscall
+ * instruction has been already reported in syscall_enter_from_usermode().
+ */
+#define SYSEMU_STEP	(_TIF_SINGLESTEP | _TIF_SYSCALL_EMU)
+
+static inline bool report_single_step(unsigned long ti_work)
+{
+	return (ti_work & SYSEMU_STEP) == _TIF_SINGLESTEP;
+}
+#endif
+
+static void syscall_exit_work(struct pt_regs *regs, unsigned long ti_work)
+{
+	bool step;
+
+	audit_syscall_exit(regs);
+
+	if (ti_work & _TIF_SYSCALL_TRACEPOINT)
+		trace_sys_exit(regs, syscall_get_return_value(current, regs));
+
+	step = report_single_step(ti_work);
+	if (step || ti_work & _TIF_SYSCALL_TRACE)
+		arch_syscall_exit_tracehook(regs, step);
+}
+
+/*
+ * Syscall specific exit to user mode preparation. Runs with interrupts
+ * enabled.
+ */
+static void syscall_exit_to_user_mode_prepare(struct pt_regs *regs)
+{
+	u32 cached_flags = READ_ONCE(current_thread_info()->flags);
+	unsigned long nr = syscall_get_nr(current, regs);
+
+	CT_WARN_ON(ct_state() != CONTEXT_KERNEL);
+
+	if (IS_ENABLED(CONFIG_PROVE_LOCKING)) {
+		if (WARN(irqs_disabled(), "syscall %lu left IRQs disabled", nr))
+			local_irq_enable();
+	}
+
+	rseq_syscall(regs);
+
+	/*
+	 * Do one-time syscall specific work. If these work items are
+	 * enabled, we want to run them exactly once per syscall exit with
+	 * interrupts enabled.
+	 */
+	if (unlikely(cached_flags & SYSCALL_EXIT_WORK))
+		syscall_exit_work(regs, cached_flags);
+}
+
+__visible noinstr void syscall_exit_to_user_mode(struct pt_regs *regs)
+{
+	instrumentation_begin();
+	syscall_exit_to_user_mode_prepare(regs);
+	local_irq_disable_exit_to_user();
+	exit_to_user_mode_prepare(regs);
+	instrumentation_end();
+	exit_to_user_mode();
+}
+
+noinstr void irqentry_enter_from_user_mode(struct pt_regs *regs)
+{
+	enter_from_user_mode(regs);
+}
+
+noinstr void irqentry_exit_to_user_mode(struct pt_regs *regs)
+{
+	instrumentation_begin();
+	exit_to_user_mode_prepare(regs);
+	instrumentation_end();
+	exit_to_user_mode();
+}
+
+noinstr irqentry_state_t irqentry_enter(struct pt_regs *regs)
+{
+	irqentry_state_t ret = {
+		.exit_rcu = false,
+	};
+
+	if (user_mode(regs)) {
+		irqentry_enter_from_user_mode(regs);
+		return ret;
+	}
+
+	/*
+	 * If this entry hit the idle task invoke rcu_irq_enter() whether
+	 * RCU is watching or not.
+	 *
+	 * Interupts can nest when the first interrupt invokes softirq
+	 * processing on return which enables interrupts.
+	 *
+	 * Scheduler ticks in the idle task can mark quiescent state and
+	 * terminate a grace period, if and only if the timer interrupt is
+	 * not nested into another interrupt.
+	 *
+	 * Checking for __rcu_is_watching() here would prevent the nesting
+	 * interrupt to invoke rcu_irq_enter(). If that nested interrupt is
+	 * the tick then rcu_flavor_sched_clock_irq() would wrongfully
+	 * assume that it is the first interupt and eventually claim
+	 * quiescient state and end grace periods prematurely.
+	 *
+	 * Unconditionally invoke rcu_irq_enter() so RCU state stays
+	 * consistent.
+	 *
+	 * TINY_RCU does not support EQS, so let the compiler eliminate
+	 * this part when enabled.
+	 */
+	if (!IS_ENABLED(CONFIG_TINY_RCU) && is_idle_task(current)) {
+		/*
+		 * If RCU is not watching then the same careful
+		 * sequence vs. lockdep and tracing is required
+		 * as in irq_enter_from_user_mode().
+		 */
+		lockdep_hardirqs_off(CALLER_ADDR0);
+		rcu_irq_enter();
+		instrumentation_begin();
+		trace_hardirqs_off_finish();
+		instrumentation_end();
+
+		ret.exit_rcu = true;
+		return ret;
+	}
+
+	/*
+	 * If RCU is watching then RCU only wants to check whether it needs
+	 * to restart the tick in NOHZ mode. rcu_irq_enter_check_tick()
+	 * already contains a warning when RCU is not watching, so no point
+	 * in having another one here.
+	 */
+	instrumentation_begin();
+	rcu_irq_enter_check_tick();
+	/* Use the combo lockdep/tracing function */
+	trace_hardirqs_off();
+	instrumentation_end();
+
+	return ret;
+}
+
+void irqentry_exit_cond_resched(void)
+{
+	if (!preempt_count()) {
+		/* Sanity check RCU and thread stack */
+		rcu_irq_exit_check_preempt();
+		if (IS_ENABLED(CONFIG_DEBUG_ENTRY))
+			WARN_ON_ONCE(!on_thread_stack());
+		if (need_resched())
+			preempt_schedule_irq();
+	}
+}
+
+noinstr void irqentry_exit(struct pt_regs *regs, irqentry_state_t state)
+{
+	lockdep_assert_irqs_disabled();
+
+	/* Check whether this returns to user mode */
+	if (user_mode(regs)) {
+		irqentry_exit_to_user_mode(regs);
+	} else if (!regs_irqs_disabled(regs)) {
+		/*
+		 * If RCU was not watching on entry this needs to be done
+		 * carefully and needs the same ordering of lockdep/tracing
+		 * and RCU as the return to user mode path.
+		 */
+		if (state.exit_rcu) {
+			instrumentation_begin();
+			/* Tell the tracer that IRET will enable interrupts */
+			trace_hardirqs_on_prepare();
+			lockdep_hardirqs_on_prepare(CALLER_ADDR0);
+			instrumentation_end();
+			rcu_irq_exit();
+			lockdep_hardirqs_on(CALLER_ADDR0);
+			return;
+		}
+
+		instrumentation_begin();
+		if (IS_ENABLED(CONFIG_PREEMPTION))
+			irqentry_exit_cond_resched();
+		/* Covers both tracing and lockdep */
+		trace_hardirqs_on();
+		instrumentation_end();
+	} else {
+		/*
+		 * IRQ flags state is correct already. Just tell RCU if it
+		 * was not watching on entry.
+		 */
+		if (state.exit_rcu)
+			rcu_irq_exit();
+	}
+}
diff --git a/kernel/entry/kvm.c b/kernel/entry/kvm.c
new file mode 100644
index 000000000000..eb1a8a4c867c
--- /dev/null
+++ b/kernel/entry/kvm.c
@@ -0,0 +1,51 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/entry-kvm.h>
+#include <linux/kvm_host.h>
+
+static int xfer_to_guest_mode_work(struct kvm_vcpu *vcpu, unsigned long ti_work)
+{
+	do {
+		int ret;
+
+		if (ti_work & _TIF_SIGPENDING) {
+			kvm_handle_signal_exit(vcpu);
+			return -EINTR;
+		}
+
+		if (ti_work & _TIF_NEED_RESCHED)
+			schedule();
+
+		if (ti_work & _TIF_NOTIFY_RESUME) {
+			clear_thread_flag(TIF_NOTIFY_RESUME);
+			tracehook_notify_resume(NULL);
+		}
+
+		ret = arch_xfer_to_guest_mode_handle_work(vcpu, ti_work);
+		if (ret)
+			return ret;
+
+		ti_work = READ_ONCE(current_thread_info()->flags);
+	} while (ti_work & XFER_TO_GUEST_MODE_WORK || need_resched());
+	return 0;
+}
+
+int xfer_to_guest_mode_handle_work(struct kvm_vcpu *vcpu)
+{
+	unsigned long ti_work;
+
+	/*
+	 * This is invoked from the outer guest loop with interrupts and
+	 * preemption enabled.
+	 *
+	 * KVM invokes xfer_to_guest_mode_work_pending() with interrupts
+	 * disabled in the inner loop before going into guest mode. No need
+	 * to disable interrupts here.
+	 */
+	ti_work = READ_ONCE(current_thread_info()->flags);
+	if (!(ti_work & XFER_TO_GUEST_MODE_WORK))
+		return 0;
+
+	return xfer_to_guest_mode_work(vcpu, ti_work);
+}
+EXPORT_SYMBOL_GPL(xfer_to_guest_mode_handle_work);
diff --git a/kernel/events/callchain.c b/kernel/events/callchain.c
index c2b41a263166..58cbe357fb2b 100644
--- a/kernel/events/callchain.c
+++ b/kernel/events/callchain.c
@@ -16,7 +16,7 @@
 
 struct callchain_cpus_entries {
 	struct rcu_head			rcu_head;
-	struct perf_callchain_entry	*cpu_entries[0];
+	struct perf_callchain_entry	*cpu_entries[];
 };
 
 int sysctl_perf_event_max_stack __read_mostly = PERF_MAX_STACK_DEPTH;
@@ -149,7 +149,7 @@ void put_callchain_buffers(void)
 	}
 }
 
-static struct perf_callchain_entry *get_callchain_entry(int *rctx)
+struct perf_callchain_entry *get_callchain_entry(int *rctx)
 {
 	int cpu;
 	struct callchain_cpus_entries *entries;
@@ -159,8 +159,10 @@ static struct perf_callchain_entry *get_callchain_entry(int *rctx)
 		return NULL;
 
 	entries = rcu_dereference(callchain_cpus_entries);
-	if (!entries)
+	if (!entries) {
+		put_recursion_context(this_cpu_ptr(callchain_recursion), *rctx);
 		return NULL;
+	}
 
 	cpu = smp_processor_id();
 
@@ -168,7 +170,7 @@ static struct perf_callchain_entry *get_callchain_entry(int *rctx)
 		(*rctx * perf_callchain_entry__sizeof()));
 }
 
-static void
+void
 put_callchain_entry(int rctx)
 {
 	put_recursion_context(this_cpu_ptr(callchain_recursion), rctx);
@@ -183,11 +185,8 @@ get_perf_callchain(struct pt_regs *regs, u32 init_nr, bool kernel, bool user,
 	int rctx;
 
 	entry = get_callchain_entry(&rctx);
-	if (rctx == -1)
-		return NULL;
-
 	if (!entry)
-		goto exit_put;
+		return NULL;
 
 	ctx.entry     = entry;
 	ctx.max_stack = max_stack;
@@ -218,10 +217,9 @@ get_perf_callchain(struct pt_regs *regs, u32 init_nr, bool kernel, bool user,
 			if (add_mark)
 				perf_callchain_store_context(&ctx, PERF_CONTEXT_USER);
 
-			fs = get_fs();
-			set_fs(USER_DS);
+			fs = force_uaccess_begin();
 			perf_callchain_user(&ctx, regs);
-			set_fs(fs);
+			force_uaccess_end(fs);
 		}
 	}
 
@@ -236,7 +234,7 @@ exit_put:
  * sysctl_perf_event_max_contexts_per_stack.
  */
 int perf_event_max_stack_handler(struct ctl_table *table, int write,
-				 void __user *buffer, size_t *lenp, loff_t *ppos)
+				 void *buffer, size_t *lenp, loff_t *ppos)
 {
 	int *value = table->data;
 	int new_value = *value, ret;
diff --git a/kernel/events/core.c b/kernel/events/core.c
index e453589da97c..7ed5248f0445 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -28,6 +28,7 @@
 #include <linux/export.h>
 #include <linux/vmalloc.h>
 #include <linux/hardirq.h>
+#include <linux/hugetlb.h>
 #include <linux/rculist.h>
 #include <linux/uaccess.h>
 #include <linux/syscalls.h>
@@ -49,6 +50,7 @@
 #include <linux/sched/mm.h>
 #include <linux/proc_ns.h>
 #include <linux/mount.h>
+#include <linux/min_heap.h>
 
 #include "internal.h"
 
@@ -93,11 +95,11 @@ static void remote_function(void *data)
  * @info:	the function call argument
  *
  * Calls the function @func when the task is currently running. This might
- * be on the current CPU, which just calls the function directly
+ * be on the current CPU, which just calls the function directly.  This will
+ * retry due to any failures in smp_call_function_single(), such as if the
+ * task_cpu() goes offline concurrently.
  *
- * returns: @func return value, or
- *	    -ESRCH  - when the process isn't running
- *	    -EAGAIN - when the process moved away
+ * returns @func return value or -ESRCH when the process isn't running
  */
 static int
 task_function_call(struct task_struct *p, remote_function_f func, void *info)
@@ -110,11 +112,16 @@ task_function_call(struct task_struct *p, remote_function_f func, void *info)
 	};
 	int ret;
 
-	do {
-		ret = smp_call_function_single(task_cpu(p), remote_function, &data, 1);
-		if (!ret)
-			ret = data.ret;
-	} while (ret == -EAGAIN);
+	for (;;) {
+		ret = smp_call_function_single(task_cpu(p), remote_function,
+					       &data, 1);
+		ret = !ret ? data.ret : -EAGAIN;
+
+		if (ret != -EAGAIN)
+			break;
+
+		cond_resched();
+	}
 
 	return ret;
 }
@@ -386,6 +393,8 @@ static atomic_t nr_freq_events __read_mostly;
 static atomic_t nr_switch_events __read_mostly;
 static atomic_t nr_ksymbol_events __read_mostly;
 static atomic_t nr_bpf_events __read_mostly;
+static atomic_t nr_cgroup_events __read_mostly;
+static atomic_t nr_text_poke_events __read_mostly;
 
 static LIST_HEAD(pmus);
 static DEFINE_MUTEX(pmus_lock);
@@ -434,8 +443,7 @@ static void update_perf_cpu_limits(void)
 static bool perf_rotate_context(struct perf_cpu_context *cpuctx);
 
 int perf_proc_update_handler(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;
 	int perf_cpu = sysctl_perf_cpu_time_max_percent;
@@ -459,8 +467,7 @@ int perf_proc_update_handler(struct ctl_table *table, int write,
 int sysctl_perf_cpu_time_max_percent __read_mostly = DEFAULT_CPU_TIME_MAX_PERCENT;
 
 int perf_cpu_time_max_percent_handler(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 = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
 
@@ -891,6 +898,47 @@ static inline void perf_cgroup_sched_in(struct task_struct *prev,
 	rcu_read_unlock();
 }
 
+static int perf_cgroup_ensure_storage(struct perf_event *event,
+				struct cgroup_subsys_state *css)
+{
+	struct perf_cpu_context *cpuctx;
+	struct perf_event **storage;
+	int cpu, heap_size, ret = 0;
+
+	/*
+	 * Allow storage to have sufficent space for an iterator for each
+	 * possibly nested cgroup plus an iterator for events with no cgroup.
+	 */
+	for (heap_size = 1; css; css = css->parent)
+		heap_size++;
+
+	for_each_possible_cpu(cpu) {
+		cpuctx = per_cpu_ptr(event->pmu->pmu_cpu_context, cpu);
+		if (heap_size <= cpuctx->heap_size)
+			continue;
+
+		storage = kmalloc_node(heap_size * sizeof(struct perf_event *),
+				       GFP_KERNEL, cpu_to_node(cpu));
+		if (!storage) {
+			ret = -ENOMEM;
+			break;
+		}
+
+		raw_spin_lock_irq(&cpuctx->ctx.lock);
+		if (cpuctx->heap_size < heap_size) {
+			swap(cpuctx->heap, storage);
+			if (storage == cpuctx->heap_default)
+				storage = NULL;
+			cpuctx->heap_size = heap_size;
+		}
+		raw_spin_unlock_irq(&cpuctx->ctx.lock);
+
+		kfree(storage);
+	}
+
+	return ret;
+}
+
 static inline int perf_cgroup_connect(int fd, struct perf_event *event,
 				      struct perf_event_attr *attr,
 				      struct perf_event *group_leader)
@@ -910,6 +958,10 @@ static inline int perf_cgroup_connect(int fd, struct perf_event *event,
 		goto out;
 	}
 
+	ret = perf_cgroup_ensure_storage(event, css);
+	if (ret)
+		goto out;
+
 	cgrp = container_of(css, struct perf_cgroup, css);
 	event->cgrp = cgrp;
 
@@ -935,16 +987,10 @@ perf_cgroup_set_shadow_time(struct perf_event *event, u64 now)
 	event->shadow_ctx_time = now - t->timestamp;
 }
 
-/*
- * Update cpuctx->cgrp so that it is set when first cgroup event is added and
- * cleared when last cgroup event is removed.
- */
 static inline void
-list_update_cgroup_event(struct perf_event *event,
-			 struct perf_event_context *ctx, bool add)
+perf_cgroup_event_enable(struct perf_event *event, struct perf_event_context *ctx)
 {
 	struct perf_cpu_context *cpuctx;
-	struct list_head *cpuctx_entry;
 
 	if (!is_cgroup_event(event))
 		return;
@@ -961,28 +1007,41 @@ list_update_cgroup_event(struct perf_event *event,
 	 * because if the first would mismatch, the second would not try again
 	 * and we would leave cpuctx->cgrp unset.
 	 */
-	if (add && !cpuctx->cgrp) {
+	if (ctx->is_active && !cpuctx->cgrp) {
 		struct perf_cgroup *cgrp = perf_cgroup_from_task(current, ctx);
 
 		if (cgroup_is_descendant(cgrp->css.cgroup, event->cgrp->css.cgroup))
 			cpuctx->cgrp = cgrp;
 	}
 
-	if (add && ctx->nr_cgroups++)
+	if (ctx->nr_cgroups++)
 		return;
-	else if (!add && --ctx->nr_cgroups)
+
+	list_add(&cpuctx->cgrp_cpuctx_entry,
+			per_cpu_ptr(&cgrp_cpuctx_list, event->cpu));
+}
+
+static inline void
+perf_cgroup_event_disable(struct perf_event *event, struct perf_event_context *ctx)
+{
+	struct perf_cpu_context *cpuctx;
+
+	if (!is_cgroup_event(event))
 		return;
 
-	/* no cgroup running */
-	if (!add)
+	/*
+	 * Because cgroup events are always per-cpu events,
+	 * @ctx == &cpuctx->ctx.
+	 */
+	cpuctx = container_of(ctx, struct perf_cpu_context, ctx);
+
+	if (--ctx->nr_cgroups)
+		return;
+
+	if (ctx->is_active && cpuctx->cgrp)
 		cpuctx->cgrp = NULL;
 
-	cpuctx_entry = &cpuctx->cgrp_cpuctx_entry;
-	if (add)
-		list_add(cpuctx_entry,
-			 per_cpu_ptr(&cgrp_cpuctx_list, event->cpu));
-	else
-		list_del(cpuctx_entry);
+	list_del(&cpuctx->cgrp_cpuctx_entry);
 }
 
 #else /* !CONFIG_CGROUP_PERF */
@@ -1048,11 +1107,14 @@ static inline u64 perf_cgroup_event_time(struct perf_event *event)
 }
 
 static inline void
-list_update_cgroup_event(struct perf_event *event,
-			 struct perf_event_context *ctx, bool add)
+perf_cgroup_event_enable(struct perf_event *event, struct perf_event_context *ctx)
 {
 }
 
+static inline void
+perf_cgroup_event_disable(struct perf_event *event, struct perf_event_context *ctx)
+{
+}
 #endif
 
 /*
@@ -1176,12 +1238,26 @@ static void get_ctx(struct perf_event_context *ctx)
 	refcount_inc(&ctx->refcount);
 }
 
+static void *alloc_task_ctx_data(struct pmu *pmu)
+{
+	if (pmu->task_ctx_cache)
+		return kmem_cache_zalloc(pmu->task_ctx_cache, GFP_KERNEL);
+
+	return NULL;
+}
+
+static void free_task_ctx_data(struct pmu *pmu, void *task_ctx_data)
+{
+	if (pmu->task_ctx_cache && task_ctx_data)
+		kmem_cache_free(pmu->task_ctx_cache, task_ctx_data);
+}
+
 static void free_ctx(struct rcu_head *head)
 {
 	struct perf_event_context *ctx;
 
 	ctx = container_of(head, struct perf_event_context, rcu_head);
-	kfree(ctx->task_ctx_data);
+	free_task_ctx_data(ctx->pmu, ctx->task_ctx_data);
 	kfree(ctx);
 }
 
@@ -1249,13 +1325,13 @@ static void put_ctx(struct perf_event_context *ctx)
  * function.
  *
  * Lock order:
- *    cred_guard_mutex
+ *    exec_update_mutex
  *	task_struct::perf_event_mutex
  *	  perf_event_context::mutex
  *	    perf_event::child_mutex;
  *	      perf_event_context::lock
  *	    perf_event::mmap_mutex
- *	    mmap_sem
+ *	    mmap_lock
  *	      perf_addr_filters_head::lock
  *
  *    cpu_hotplug_lock
@@ -1531,6 +1607,30 @@ perf_event_groups_less(struct perf_event *left, struct perf_event *right)
 	if (left->cpu > right->cpu)
 		return false;
 
+#ifdef CONFIG_CGROUP_PERF
+	if (left->cgrp != right->cgrp) {
+		if (!left->cgrp || !left->cgrp->css.cgroup) {
+			/*
+			 * Left has no cgroup but right does, no cgroups come
+			 * first.
+			 */
+			return true;
+		}
+		if (!right->cgrp || !right->cgrp->css.cgroup) {
+			/*
+			 * Right has no cgroup but left does, no cgroups come
+			 * first.
+			 */
+			return false;
+		}
+		/* Two dissimilar cgroups, order by id. */
+		if (left->cgrp->css.cgroup->kn->id < right->cgrp->css.cgroup->kn->id)
+			return true;
+
+		return false;
+	}
+#endif
+
 	if (left->group_index < right->group_index)
 		return true;
 	if (left->group_index > right->group_index)
@@ -1610,25 +1710,48 @@ del_event_from_groups(struct perf_event *event, struct perf_event_context *ctx)
 }
 
 /*
- * Get the leftmost event in the @cpu subtree.
+ * Get the leftmost event in the cpu/cgroup subtree.
  */
 static struct perf_event *
-perf_event_groups_first(struct perf_event_groups *groups, int cpu)
+perf_event_groups_first(struct perf_event_groups *groups, int cpu,
+			struct cgroup *cgrp)
 {
 	struct perf_event *node_event = NULL, *match = NULL;
 	struct rb_node *node = groups->tree.rb_node;
+#ifdef CONFIG_CGROUP_PERF
+	u64 node_cgrp_id, cgrp_id = 0;
+
+	if (cgrp)
+		cgrp_id = cgrp->kn->id;
+#endif
 
 	while (node) {
 		node_event = container_of(node, struct perf_event, group_node);
 
 		if (cpu < node_event->cpu) {
 			node = node->rb_left;
-		} else if (cpu > node_event->cpu) {
+			continue;
+		}
+		if (cpu > node_event->cpu) {
 			node = node->rb_right;
-		} else {
-			match = node_event;
+			continue;
+		}
+#ifdef CONFIG_CGROUP_PERF
+		node_cgrp_id = 0;
+		if (node_event->cgrp && node_event->cgrp->css.cgroup)
+			node_cgrp_id = node_event->cgrp->css.cgroup->kn->id;
+
+		if (cgrp_id < node_cgrp_id) {
 			node = node->rb_left;
+			continue;
+		}
+		if (cgrp_id > node_cgrp_id) {
+			node = node->rb_right;
+			continue;
 		}
+#endif
+		match = node_event;
+		node = node->rb_left;
 	}
 
 	return match;
@@ -1641,12 +1764,26 @@ static struct perf_event *
 perf_event_groups_next(struct perf_event *event)
 {
 	struct perf_event *next;
+#ifdef CONFIG_CGROUP_PERF
+	u64 curr_cgrp_id = 0;
+	u64 next_cgrp_id = 0;
+#endif
 
 	next = rb_entry_safe(rb_next(&event->group_node), typeof(*event), group_node);
-	if (next && next->cpu == event->cpu)
-		return next;
+	if (next == NULL || next->cpu != event->cpu)
+		return NULL;
 
-	return NULL;
+#ifdef CONFIG_CGROUP_PERF
+	if (event->cgrp && event->cgrp->css.cgroup)
+		curr_cgrp_id = event->cgrp->css.cgroup->kn->id;
+
+	if (next->cgrp && next->cgrp->css.cgroup)
+		next_cgrp_id = next->cgrp->css.cgroup->kn->id;
+
+	if (curr_cgrp_id != next_cgrp_id)
+		return NULL;
+#endif
+	return next;
 }
 
 /*
@@ -1682,13 +1819,14 @@ list_add_event(struct perf_event *event, struct perf_event_context *ctx)
 		add_event_to_groups(event, ctx);
 	}
 
-	list_update_cgroup_event(event, ctx, true);
-
 	list_add_rcu(&event->event_entry, &ctx->event_list);
 	ctx->nr_events++;
 	if (event->attr.inherit_stat)
 		ctx->nr_stat++;
 
+	if (event->state > PERF_EVENT_STATE_OFF)
+		perf_cgroup_event_enable(event, ctx);
+
 	ctx->generation++;
 }
 
@@ -1754,6 +1892,9 @@ static void __perf_event_header_size(struct perf_event *event, u64 sample_type)
 	if (sample_type & PERF_SAMPLE_PHYS_ADDR)
 		size += sizeof(data->phys_addr);
 
+	if (sample_type & PERF_SAMPLE_CGROUP)
+		size += sizeof(data->cgroup);
+
 	event->header_size = size;
 }
 
@@ -1864,8 +2005,6 @@ list_del_event(struct perf_event *event, struct perf_event_context *ctx)
 
 	event->attach_state &= ~PERF_ATTACH_CONTEXT;
 
-	list_update_cgroup_event(event, ctx, false);
-
 	ctx->nr_events--;
 	if (event->attr.inherit_stat)
 		ctx->nr_stat--;
@@ -1882,8 +2021,10 @@ list_del_event(struct perf_event *event, struct perf_event_context *ctx)
 	 * of error state is by explicit re-enabling
 	 * of the event
 	 */
-	if (event->state > PERF_EVENT_STATE_OFF)
+	if (event->state > PERF_EVENT_STATE_OFF) {
+		perf_cgroup_event_disable(event, ctx);
 		perf_event_set_state(event, PERF_EVENT_STATE_OFF);
+	}
 
 	ctx->generation++;
 }
@@ -1986,6 +2127,12 @@ static int perf_get_aux_event(struct perf_event *event,
 	return 1;
 }
 
+static inline struct list_head *get_event_list(struct perf_event *event)
+{
+	struct perf_event_context *ctx = event->ctx;
+	return event->attr.pinned ? &ctx->pinned_active : &ctx->flexible_active;
+}
+
 static void perf_group_detach(struct perf_event *event)
 {
 	struct perf_event *sibling, *tmp;
@@ -2028,12 +2175,8 @@ static void perf_group_detach(struct perf_event *event)
 		if (!RB_EMPTY_NODE(&event->group_node)) {
 			add_event_to_groups(sibling, event->ctx);
 
-			if (sibling->state == PERF_EVENT_STATE_ACTIVE) {
-				struct list_head *list = sibling->attr.pinned ?
-					&ctx->pinned_active : &ctx->flexible_active;
-
-				list_add_tail(&sibling->active_list, list);
-			}
+			if (sibling->state == PERF_EVENT_STATE_ACTIVE)
+				list_add_tail(&sibling->active_list, get_event_list(sibling));
 		}
 
 		WARN_ON_ONCE(sibling->ctx != event->ctx);
@@ -2112,6 +2255,7 @@ event_sched_out(struct perf_event *event,
 
 	if (READ_ONCE(event->pending_disable) >= 0) {
 		WRITE_ONCE(event->pending_disable, -1);
+		perf_cgroup_event_disable(event, ctx);
 		state = PERF_EVENT_STATE_OFF;
 	}
 	perf_event_set_state(event, state);
@@ -2182,6 +2326,7 @@ __perf_remove_from_context(struct perf_event *event,
 
 	if (!ctx->nr_events && ctx->is_active) {
 		ctx->is_active = 0;
+		ctx->rotate_necessary = 0;
 		if (ctx->task) {
 			WARN_ON_ONCE(cpuctx->task_ctx != ctx);
 			cpuctx->task_ctx = NULL;
@@ -2248,6 +2393,7 @@ static void __perf_event_disable(struct perf_event *event,
 		event_sched_out(event, cpuctx, ctx);
 
 	perf_event_set_state(event, PERF_EVENT_STATE_OFF);
+	perf_cgroup_event_disable(event, ctx);
 }
 
 /*
@@ -2350,6 +2496,8 @@ event_sched_in(struct perf_event *event,
 {
 	int ret = 0;
 
+	WARN_ON_ONCE(event->ctx != ctx);
+
 	lockdep_assert_held(&ctx->lock);
 
 	if (event->state <= PERF_EVENT_STATE_OFF)
@@ -2629,7 +2777,7 @@ static int  __perf_install_in_context(void *info)
 	}
 
 #ifdef CONFIG_CGROUP_PERF
-	if (is_cgroup_event(event)) {
+	if (event->state > PERF_EVENT_STATE_OFF && is_cgroup_event(event)) {
 		/*
 		 * If the current cgroup doesn't match the event's
 		 * cgroup, we should not try to schedule it.
@@ -2789,6 +2937,7 @@ static void __perf_event_enable(struct perf_event *event,
 		ctx_sched_out(ctx, cpuctx, EVENT_TIME);
 
 	perf_event_set_state(event, PERF_EVENT_STATE_INACTIVE);
+	perf_cgroup_event_enable(event, ctx);
 
 	if (!ctx->is_active)
 		return;
@@ -2946,7 +3095,7 @@ static int perf_event_stop(struct perf_event *event, int restart)
  *     pre-existing mappings, called once when new filters arrive via SET_FILTER
  *     ioctl;
  * (2) perf_addr_filters_adjust(): adjusting filters' offsets based on newly
- *     registered mapping, called for every new mmap(), with mm::mmap_sem down
+ *     registered mapping, called for every new mmap(), with mm::mmap_lock down
  *     for reading;
  * (3) perf_event_addr_filters_exec(): clearing filters' offsets in the process
  *     of exec.
@@ -3077,12 +3226,6 @@ static void ctx_sched_out(struct perf_event_context *ctx,
 	if (!ctx->nr_active || !(is_active & EVENT_ALL))
 		return;
 
-	/*
-	 * If we had been multiplexing, no rotations are necessary, now no events
-	 * are active.
-	 */
-	ctx->rotate_necessary = 0;
-
 	perf_pmu_disable(ctx->pmu);
 	if (is_active & EVENT_PINNED) {
 		list_for_each_entry_safe(event, tmp, &ctx->pinned_active, active_list)
@@ -3092,6 +3235,13 @@ static void ctx_sched_out(struct perf_event_context *ctx,
 	if (is_active & EVENT_FLEXIBLE) {
 		list_for_each_entry_safe(event, tmp, &ctx->flexible_active, active_list)
 			group_sched_out(event, cpuctx, ctx);
+
+		/*
+		 * Since we cleared EVENT_FLEXIBLE, also clear
+		 * rotate_necessary, is will be reset by
+		 * ctx_flexible_sched_in() when needed.
+		 */
+		ctx->rotate_necessary = 0;
 	}
 	perf_pmu_enable(ctx->pmu);
 }
@@ -3388,71 +3538,104 @@ static void cpu_ctx_sched_out(struct perf_cpu_context *cpuctx,
 	ctx_sched_out(&cpuctx->ctx, cpuctx, event_type);
 }
 
-static int visit_groups_merge(struct perf_event_groups *groups, int cpu,
-			      int (*func)(struct perf_event *, void *), void *data)
+static bool perf_less_group_idx(const void *l, const void *r)
 {
-	struct perf_event **evt, *evt1, *evt2;
-	int ret;
-
-	evt1 = perf_event_groups_first(groups, -1);
-	evt2 = perf_event_groups_first(groups, cpu);
-
-	while (evt1 || evt2) {
-		if (evt1 && evt2) {
-			if (evt1->group_index < evt2->group_index)
-				evt = &evt1;
-			else
-				evt = &evt2;
-		} else if (evt1) {
-			evt = &evt1;
-		} else {
-			evt = &evt2;
-		}
+	const struct perf_event *le = *(const struct perf_event **)l;
+	const struct perf_event *re = *(const struct perf_event **)r;
 
-		ret = func(*evt, data);
-		if (ret)
-			return ret;
+	return le->group_index < re->group_index;
+}
 
-		*evt = perf_event_groups_next(*evt);
-	}
+static void swap_ptr(void *l, void *r)
+{
+	void **lp = l, **rp = r;
 
-	return 0;
+	swap(*lp, *rp);
 }
 
-struct sched_in_data {
-	struct perf_event_context *ctx;
-	struct perf_cpu_context *cpuctx;
-	int can_add_hw;
+static const struct min_heap_callbacks perf_min_heap = {
+	.elem_size = sizeof(struct perf_event *),
+	.less = perf_less_group_idx,
+	.swp = swap_ptr,
 };
 
-static int pinned_sched_in(struct perf_event *event, void *data)
+static void __heap_add(struct min_heap *heap, struct perf_event *event)
 {
-	struct sched_in_data *sid = data;
+	struct perf_event **itrs = heap->data;
 
-	if (event->state <= PERF_EVENT_STATE_OFF)
-		return 0;
+	if (event) {
+		itrs[heap->nr] = event;
+		heap->nr++;
+	}
+}
 
-	if (!event_filter_match(event))
-		return 0;
+static noinline int visit_groups_merge(struct perf_cpu_context *cpuctx,
+				struct perf_event_groups *groups, int cpu,
+				int (*func)(struct perf_event *, void *),
+				void *data)
+{
+#ifdef CONFIG_CGROUP_PERF
+	struct cgroup_subsys_state *css = NULL;
+#endif
+	/* Space for per CPU and/or any CPU event iterators. */
+	struct perf_event *itrs[2];
+	struct min_heap event_heap;
+	struct perf_event **evt;
+	int ret;
 
-	if (group_can_go_on(event, sid->cpuctx, sid->can_add_hw)) {
-		if (!group_sched_in(event, sid->cpuctx, sid->ctx))
-			list_add_tail(&event->active_list, &sid->ctx->pinned_active);
+	if (cpuctx) {
+		event_heap = (struct min_heap){
+			.data = cpuctx->heap,
+			.nr = 0,
+			.size = cpuctx->heap_size,
+		};
+
+		lockdep_assert_held(&cpuctx->ctx.lock);
+
+#ifdef CONFIG_CGROUP_PERF
+		if (cpuctx->cgrp)
+			css = &cpuctx->cgrp->css;
+#endif
+	} else {
+		event_heap = (struct min_heap){
+			.data = itrs,
+			.nr = 0,
+			.size = ARRAY_SIZE(itrs),
+		};
+		/* Events not within a CPU context may be on any CPU. */
+		__heap_add(&event_heap, perf_event_groups_first(groups, -1, NULL));
 	}
+	evt = event_heap.data;
 
-	/*
-	 * If this pinned group hasn't been scheduled,
-	 * put it in error state.
-	 */
-	if (event->state == PERF_EVENT_STATE_INACTIVE)
-		perf_event_set_state(event, PERF_EVENT_STATE_ERROR);
+	__heap_add(&event_heap, perf_event_groups_first(groups, cpu, NULL));
+
+#ifdef CONFIG_CGROUP_PERF
+	for (; css; css = css->parent)
+		__heap_add(&event_heap, perf_event_groups_first(groups, cpu, css->cgroup));
+#endif
+
+	min_heapify_all(&event_heap, &perf_min_heap);
+
+	while (event_heap.nr) {
+		ret = func(*evt, data);
+		if (ret)
+			return ret;
+
+		*evt = perf_event_groups_next(*evt);
+		if (*evt)
+			min_heapify(&event_heap, 0, &perf_min_heap);
+		else
+			min_heap_pop(&event_heap, &perf_min_heap);
+	}
 
 	return 0;
 }
 
-static int flexible_sched_in(struct perf_event *event, void *data)
+static int merge_sched_in(struct perf_event *event, void *data)
 {
-	struct sched_in_data *sid = data;
+	struct perf_event_context *ctx = event->ctx;
+	struct perf_cpu_context *cpuctx = __get_cpu_context(ctx);
+	int *can_add_hw = data;
 
 	if (event->state <= PERF_EVENT_STATE_OFF)
 		return 0;
@@ -3460,14 +3643,19 @@ static int flexible_sched_in(struct perf_event *event, void *data)
 	if (!event_filter_match(event))
 		return 0;
 
-	if (group_can_go_on(event, sid->cpuctx, sid->can_add_hw)) {
-		int ret = group_sched_in(event, sid->cpuctx, sid->ctx);
-		if (ret) {
-			sid->can_add_hw = 0;
-			sid->ctx->rotate_necessary = 1;
-			return 0;
+	if (group_can_go_on(event, cpuctx, *can_add_hw)) {
+		if (!group_sched_in(event, cpuctx, ctx))
+			list_add_tail(&event->active_list, get_event_list(event));
+	}
+
+	if (event->state == PERF_EVENT_STATE_INACTIVE) {
+		if (event->attr.pinned) {
+			perf_cgroup_event_disable(event, ctx);
+			perf_event_set_state(event, PERF_EVENT_STATE_ERROR);
 		}
-		list_add_tail(&event->active_list, &sid->ctx->flexible_active);
+
+		*can_add_hw = 0;
+		ctx->rotate_necessary = 1;
 	}
 
 	return 0;
@@ -3477,30 +3665,28 @@ static void
 ctx_pinned_sched_in(struct perf_event_context *ctx,
 		    struct perf_cpu_context *cpuctx)
 {
-	struct sched_in_data sid = {
-		.ctx = ctx,
-		.cpuctx = cpuctx,
-		.can_add_hw = 1,
-	};
+	int can_add_hw = 1;
+
+	if (ctx != &cpuctx->ctx)
+		cpuctx = NULL;
 
-	visit_groups_merge(&ctx->pinned_groups,
+	visit_groups_merge(cpuctx, &ctx->pinned_groups,
 			   smp_processor_id(),
-			   pinned_sched_in, &sid);
+			   merge_sched_in, &can_add_hw);
 }
 
 static void
 ctx_flexible_sched_in(struct perf_event_context *ctx,
 		      struct perf_cpu_context *cpuctx)
 {
-	struct sched_in_data sid = {
-		.ctx = ctx,
-		.cpuctx = cpuctx,
-		.can_add_hw = 1,
-	};
+	int can_add_hw = 1;
+
+	if (ctx != &cpuctx->ctx)
+		cpuctx = NULL;
 
-	visit_groups_merge(&ctx->flexible_groups,
+	visit_groups_merge(cpuctx, &ctx->flexible_groups,
 			   smp_processor_id(),
-			   flexible_sched_in, &sid);
+			   merge_sched_in, &can_add_hw);
 }
 
 static void
@@ -3841,6 +4027,12 @@ ctx_event_to_rotate(struct perf_event_context *ctx)
 				      typeof(*event), group_node);
 	}
 
+	/*
+	 * Unconditionally clear rotate_necessary; if ctx_flexible_sched_in()
+	 * finds there are unschedulable events, it will set it again.
+	 */
+	ctx->rotate_necessary = 0;
+
 	return event;
 }
 
@@ -4293,7 +4485,7 @@ find_get_context(struct pmu *pmu, struct task_struct *task,
 		goto errout;
 
 	if (event->attach_state & PERF_ATTACH_TASK_DATA) {
-		task_ctx_data = kzalloc(pmu->task_ctx_size, GFP_KERNEL);
+		task_ctx_data = alloc_task_ctx_data(pmu);
 		if (!task_ctx_data) {
 			err = -ENOMEM;
 			goto errout;
@@ -4351,11 +4543,11 @@ retry:
 		}
 	}
 
-	kfree(task_ctx_data);
+	free_task_ctx_data(pmu, task_ctx_data);
 	return ctx;
 
 errout:
-	kfree(task_ctx_data);
+	free_task_ctx_data(pmu, task_ctx_data);
 	return ERR_PTR(err);
 }
 
@@ -4398,7 +4590,7 @@ static bool is_sb_event(struct perf_event *event)
 	if (attr->mmap || attr->mmap_data || attr->mmap2 ||
 	    attr->comm || attr->comm_exec ||
 	    attr->task || attr->ksymbol ||
-	    attr->context_switch ||
+	    attr->context_switch || attr->text_poke ||
 	    attr->bpf_event)
 		return true;
 	return false;
@@ -4456,6 +4648,8 @@ static void unaccount_event(struct perf_event *event)
 		atomic_dec(&nr_comm_events);
 	if (event->attr.namespaces)
 		atomic_dec(&nr_namespaces_events);
+	if (event->attr.cgroup)
+		atomic_dec(&nr_cgroup_events);
 	if (event->attr.task)
 		atomic_dec(&nr_task_events);
 	if (event->attr.freq)
@@ -4472,6 +4666,8 @@ static void unaccount_event(struct perf_event *event)
 		atomic_dec(&nr_ksymbol_events);
 	if (event->attr.bpf_event)
 		atomic_dec(&nr_bpf_events);
+	if (event->attr.text_poke)
+		atomic_dec(&nr_text_poke_events);
 
 	if (dec) {
 		if (!atomic_add_unless(&perf_sched_count, -1, 1))
@@ -6257,10 +6453,9 @@ perf_output_sample_ustack(struct perf_output_handle *handle, u64 dump_size,
 
 		/* Data. */
 		sp = perf_user_stack_pointer(regs);
-		fs = get_fs();
-		set_fs(USER_DS);
+		fs = force_uaccess_begin();
 		rem = __output_copy_user(handle, (void *) sp, dump_size);
-		set_fs(fs);
+		force_uaccess_end(fs);
 		dyn_size = dump_size - rem;
 
 		perf_output_skip(handle, rem);
@@ -6555,6 +6750,11 @@ static void perf_output_read(struct perf_output_handle *handle,
 		perf_output_read_one(handle, event, enabled, running);
 }
 
+static inline bool perf_sample_save_hw_index(struct perf_event *event)
+{
+	return event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_HW_INDEX;
+}
+
 void perf_output_sample(struct perf_output_handle *handle,
 			struct perf_event_header *header,
 			struct perf_sample_data *data,
@@ -6643,6 +6843,8 @@ void perf_output_sample(struct perf_output_handle *handle,
 			     * sizeof(struct perf_branch_entry);
 
 			perf_output_put(handle, data->br_stack->nr);
+			if (perf_sample_save_hw_index(event))
+				perf_output_put(handle, data->br_stack->hw_idx);
 			perf_output_copy(handle, data->br_stack->entries, size);
 		} else {
 			/*
@@ -6705,6 +6907,9 @@ void perf_output_sample(struct perf_output_handle *handle,
 	if (sample_type & PERF_SAMPLE_PHYS_ADDR)
 		perf_output_put(handle, data->phys_addr);
 
+	if (sample_type & PERF_SAMPLE_CGROUP)
+		perf_output_put(handle, data->cgroup);
+
 	if (sample_type & PERF_SAMPLE_AUX) {
 		perf_output_put(handle, data->aux_size);
 
@@ -6745,12 +6950,15 @@ static u64 perf_virt_to_phys(u64 virt)
 		 * Walking the pages tables for user address.
 		 * Interrupts are disabled, so it prevents any tear down
 		 * of the page tables.
-		 * Try IRQ-safe __get_user_pages_fast first.
+		 * Try IRQ-safe get_user_page_fast_only first.
 		 * If failed, leave phys_addr as 0.
 		 */
-		if ((current->mm != NULL) &&
-		    (__get_user_pages_fast(virt, 1, 0, &p) == 1))
-			phys_addr = page_to_phys(p) + virt % PAGE_SIZE;
+		if (current->mm != NULL) {
+			pagefault_disable();
+			if (get_user_page_fast_only(virt, 0, &p))
+				phys_addr = page_to_phys(p) + virt % PAGE_SIZE;
+			pagefault_enable();
+		}
 
 		if (p)
 			put_page(p);
@@ -6836,6 +7044,9 @@ void perf_prepare_sample(struct perf_event_header *header,
 	if (sample_type & PERF_SAMPLE_BRANCH_STACK) {
 		int size = sizeof(u64); /* nr */
 		if (data->br_stack) {
+			if (perf_sample_save_hw_index(event))
+				size += sizeof(u64);
+
 			size += data->br_stack->nr
 			      * sizeof(struct perf_branch_entry);
 		}
@@ -6901,6 +7112,16 @@ void perf_prepare_sample(struct perf_event_header *header,
 	if (sample_type & PERF_SAMPLE_PHYS_ADDR)
 		data->phys_addr = perf_virt_to_phys(data->addr);
 
+#ifdef CONFIG_CGROUP_PERF
+	if (sample_type & PERF_SAMPLE_CGROUP) {
+		struct cgroup *cgrp;
+
+		/* protected by RCU */
+		cgrp = task_css_check(current, perf_event_cgrp_id, 1)->cgroup;
+		data->cgroup = cgroup_id(cgrp);
+	}
+#endif
+
 	if (sample_type & PERF_SAMPLE_AUX) {
 		u64 size;
 
@@ -7289,10 +7510,17 @@ static void perf_event_task_output(struct perf_event *event,
 		goto out;
 
 	task_event->event_id.pid = perf_event_pid(event, task);
-	task_event->event_id.ppid = perf_event_pid(event, current);
-
 	task_event->event_id.tid = perf_event_tid(event, task);
-	task_event->event_id.ptid = perf_event_tid(event, current);
+
+	if (task_event->event_id.header.type == PERF_RECORD_EXIT) {
+		task_event->event_id.ppid = perf_event_pid(event,
+							task->real_parent);
+		task_event->event_id.ptid = perf_event_pid(event,
+							task->real_parent);
+	} else {  /* PERF_RECORD_FORK */
+		task_event->event_id.ppid = perf_event_pid(event, current);
+		task_event->event_id.ptid = perf_event_tid(event, current);
+	}
 
 	task_event->event_id.time = perf_event_clock(event);
 
@@ -7574,6 +7802,105 @@ void perf_event_namespaces(struct task_struct *task)
 }
 
 /*
+ * cgroup tracking
+ */
+#ifdef CONFIG_CGROUP_PERF
+
+struct perf_cgroup_event {
+	char				*path;
+	int				path_size;
+	struct {
+		struct perf_event_header	header;
+		u64				id;
+		char				path[];
+	} event_id;
+};
+
+static int perf_event_cgroup_match(struct perf_event *event)
+{
+	return event->attr.cgroup;
+}
+
+static void perf_event_cgroup_output(struct perf_event *event, void *data)
+{
+	struct perf_cgroup_event *cgroup_event = data;
+	struct perf_output_handle handle;
+	struct perf_sample_data sample;
+	u16 header_size = cgroup_event->event_id.header.size;
+	int ret;
+
+	if (!perf_event_cgroup_match(event))
+		return;
+
+	perf_event_header__init_id(&cgroup_event->event_id.header,
+				   &sample, event);
+	ret = perf_output_begin(&handle, event,
+				cgroup_event->event_id.header.size);
+	if (ret)
+		goto out;
+
+	perf_output_put(&handle, cgroup_event->event_id);
+	__output_copy(&handle, cgroup_event->path, cgroup_event->path_size);
+
+	perf_event__output_id_sample(event, &handle, &sample);
+
+	perf_output_end(&handle);
+out:
+	cgroup_event->event_id.header.size = header_size;
+}
+
+static void perf_event_cgroup(struct cgroup *cgrp)
+{
+	struct perf_cgroup_event cgroup_event;
+	char path_enomem[16] = "//enomem";
+	char *pathname;
+	size_t size;
+
+	if (!atomic_read(&nr_cgroup_events))
+		return;
+
+	cgroup_event = (struct perf_cgroup_event){
+		.event_id  = {
+			.header = {
+				.type = PERF_RECORD_CGROUP,
+				.misc = 0,
+				.size = sizeof(cgroup_event.event_id),
+			},
+			.id = cgroup_id(cgrp),
+		},
+	};
+
+	pathname = kmalloc(PATH_MAX, GFP_KERNEL);
+	if (pathname == NULL) {
+		cgroup_event.path = path_enomem;
+	} else {
+		/* just to be sure to have enough space for alignment */
+		cgroup_path(cgrp, pathname, PATH_MAX - sizeof(u64));
+		cgroup_event.path = pathname;
+	}
+
+	/*
+	 * Since our buffer works in 8 byte units we need to align our string
+	 * size to a multiple of 8. However, we must guarantee the tail end is
+	 * zero'd out to avoid leaking random bits to userspace.
+	 */
+	size = strlen(cgroup_event.path) + 1;
+	while (!IS_ALIGNED(size, sizeof(u64)))
+		cgroup_event.path[size++] = '\0';
+
+	cgroup_event.event_id.header.size += size;
+	cgroup_event.path_size = size;
+
+	perf_iterate_sb(perf_event_cgroup_output,
+			&cgroup_event,
+			NULL);
+
+	kfree(pathname);
+}
+
+#endif
+
+/*
  * mmap tracking
  */
 
@@ -7693,7 +8020,7 @@ static void perf_event_mmap_event(struct perf_mmap_event *mmap_event)
 		flags |= MAP_EXECUTABLE;
 	if (vma->vm_flags & VM_LOCKED)
 		flags |= MAP_LOCKED;
-	if (vma->vm_flags & VM_HUGETLB)
+	if (is_vm_hugetlb_page(vma))
 		flags |= MAP_HUGETLB;
 
 	if (file) {
@@ -8255,23 +8582,22 @@ static void perf_event_bpf_emit_ksymbols(struct bpf_prog *prog,
 					 enum perf_bpf_event_type type)
 {
 	bool unregister = type == PERF_BPF_EVENT_PROG_UNLOAD;
-	char sym[KSYM_NAME_LEN];
 	int i;
 
 	if (prog->aux->func_cnt == 0) {
-		bpf_get_prog_name(prog, sym);
 		perf_event_ksymbol(PERF_RECORD_KSYMBOL_TYPE_BPF,
 				   (u64)(unsigned long)prog->bpf_func,
-				   prog->jited_len, unregister, sym);
+				   prog->jited_len, unregister,
+				   prog->aux->ksym.name);
 	} else {
 		for (i = 0; i < prog->aux->func_cnt; i++) {
 			struct bpf_prog *subprog = prog->aux->func[i];
 
-			bpf_get_prog_name(subprog, sym);
 			perf_event_ksymbol(
 				PERF_RECORD_KSYMBOL_TYPE_BPF,
 				(u64)(unsigned long)subprog->bpf_func,
-				subprog->jited_len, unregister, sym);
+				subprog->jited_len, unregister,
+				prog->aux->ksym.name);
 		}
 	}
 }
@@ -8318,6 +8644,89 @@ void perf_event_bpf_event(struct bpf_prog *prog,
 	perf_iterate_sb(perf_event_bpf_output, &bpf_event, NULL);
 }
 
+struct perf_text_poke_event {
+	const void		*old_bytes;
+	const void		*new_bytes;
+	size_t			pad;
+	u16			old_len;
+	u16			new_len;
+
+	struct {
+		struct perf_event_header	header;
+
+		u64				addr;
+	} event_id;
+};
+
+static int perf_event_text_poke_match(struct perf_event *event)
+{
+	return event->attr.text_poke;
+}
+
+static void perf_event_text_poke_output(struct perf_event *event, void *data)
+{
+	struct perf_text_poke_event *text_poke_event = data;
+	struct perf_output_handle handle;
+	struct perf_sample_data sample;
+	u64 padding = 0;
+	int ret;
+
+	if (!perf_event_text_poke_match(event))
+		return;
+
+	perf_event_header__init_id(&text_poke_event->event_id.header, &sample, event);
+
+	ret = perf_output_begin(&handle, event, text_poke_event->event_id.header.size);
+	if (ret)
+		return;
+
+	perf_output_put(&handle, text_poke_event->event_id);
+	perf_output_put(&handle, text_poke_event->old_len);
+	perf_output_put(&handle, text_poke_event->new_len);
+
+	__output_copy(&handle, text_poke_event->old_bytes, text_poke_event->old_len);
+	__output_copy(&handle, text_poke_event->new_bytes, text_poke_event->new_len);
+
+	if (text_poke_event->pad)
+		__output_copy(&handle, &padding, text_poke_event->pad);
+
+	perf_event__output_id_sample(event, &handle, &sample);
+
+	perf_output_end(&handle);
+}
+
+void perf_event_text_poke(const void *addr, const void *old_bytes,
+			  size_t old_len, const void *new_bytes, size_t new_len)
+{
+	struct perf_text_poke_event text_poke_event;
+	size_t tot, pad;
+
+	if (!atomic_read(&nr_text_poke_events))
+		return;
+
+	tot  = sizeof(text_poke_event.old_len) + old_len;
+	tot += sizeof(text_poke_event.new_len) + new_len;
+	pad  = ALIGN(tot, sizeof(u64)) - tot;
+
+	text_poke_event = (struct perf_text_poke_event){
+		.old_bytes    = old_bytes,
+		.new_bytes    = new_bytes,
+		.pad          = pad,
+		.old_len      = old_len,
+		.new_len      = new_len,
+		.event_id  = {
+			.header = {
+				.type = PERF_RECORD_TEXT_POKE,
+				.misc = PERF_RECORD_MISC_KERNEL,
+				.size = sizeof(text_poke_event.event_id) + tot + pad,
+			},
+			.addr = (unsigned long)addr,
+		},
+	};
+
+	perf_iterate_sb(perf_event_text_poke_output, &text_poke_event, NULL);
+}
+
 void perf_event_itrace_started(struct perf_event *event)
 {
 	event->attach_state |= PERF_ATTACH_ITRACE;
@@ -9097,7 +9506,7 @@ static int perf_kprobe_event_init(struct perf_event *event)
 	if (event->attr.type != perf_kprobe.type)
 		return -ENOENT;
 
-	if (!capable(CAP_SYS_ADMIN))
+	if (!perfmon_capable())
 		return -EACCES;
 
 	/*
@@ -9157,7 +9566,7 @@ static int perf_uprobe_event_init(struct perf_event *event)
 	if (event->attr.type != perf_uprobe.type)
 		return -ENOENT;
 
-	if (!capable(CAP_SYS_ADMIN))
+	if (!perfmon_capable())
 		return -EACCES;
 
 	/*
@@ -9206,7 +9615,6 @@ static void bpf_overflow_handler(struct perf_event *event,
 	int ret = 0;
 
 	ctx.regs = perf_arch_bpf_user_pt_regs(regs);
-	preempt_disable();
 	if (unlikely(__this_cpu_inc_return(bpf_prog_active) != 1))
 		goto out;
 	rcu_read_lock();
@@ -9214,7 +9622,6 @@ static void bpf_overflow_handler(struct perf_event *event,
 	rcu_read_unlock();
 out:
 	__this_cpu_dec(bpf_prog_active);
-	preempt_enable();
 	if (!ret)
 		return;
 
@@ -9236,6 +9643,24 @@ static int perf_event_set_bpf_handler(struct perf_event *event, u32 prog_fd)
 	if (IS_ERR(prog))
 		return PTR_ERR(prog);
 
+	if (event->attr.precise_ip &&
+	    prog->call_get_stack &&
+	    (!(event->attr.sample_type & __PERF_SAMPLE_CALLCHAIN_EARLY) ||
+	     event->attr.exclude_callchain_kernel ||
+	     event->attr.exclude_callchain_user)) {
+		/*
+		 * On perf_event with precise_ip, calling bpf_get_stack()
+		 * may trigger unwinder warnings and occasional crashes.
+		 * bpf_get_[stack|stackid] works around this issue by using
+		 * callchain attached to perf_sample_data. If the
+		 * perf_event does not full (kernel and user) callchain
+		 * attached to perf_sample_data, do not allow attaching BPF
+		 * program that calls bpf_get_[stack|stackid].
+		 */
+		bpf_prog_put(prog);
+		return -EPROTO;
+	}
+
 	event->prog = prog;
 	event->orig_overflow_handler = READ_ONCE(event->overflow_handler);
 	WRITE_ONCE(event->overflow_handler, bpf_overflow_handler);
@@ -9434,7 +9859,7 @@ static void perf_addr_filters_splice(struct perf_event *event,
 /*
  * Scan through mm's vmas and see if one of them matches the
  * @filter; if so, adjust filter's address range.
- * Called with mm::mmap_sem down for reading.
+ * Called with mm::mmap_lock down for reading.
  */
 static void perf_addr_filter_apply(struct perf_addr_filter *filter,
 				   struct mm_struct *mm,
@@ -9476,7 +9901,7 @@ static void perf_event_addr_filters_apply(struct perf_event *event)
 		if (!mm)
 			goto restart;
 
-		down_read(&mm->mmap_sem);
+		mmap_read_lock(mm);
 	}
 
 	raw_spin_lock_irqsave(&ifh->lock, flags);
@@ -9502,7 +9927,7 @@ static void perf_event_addr_filters_apply(struct perf_event *event)
 	raw_spin_unlock_irqrestore(&ifh->lock, flags);
 
 	if (ifh->nr_file_filters) {
-		up_read(&mm->mmap_sem);
+		mmap_read_unlock(mm);
 
 		mmput(mm);
 	}
@@ -9609,7 +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:
@@ -10349,6 +10774,9 @@ skip_type:
 		cpuctx->online = cpumask_test_cpu(cpu, perf_online_mask);
 
 		__perf_mux_hrtimer_init(cpuctx, cpu);
+
+		cpuctx->heap_size = ARRAY_SIZE(cpuctx->heap_default);
+		cpuctx->heap = cpuctx->heap_default;
 	}
 
 got_cpu_context:
@@ -10616,6 +11044,8 @@ static void account_event(struct perf_event *event)
 		atomic_inc(&nr_comm_events);
 	if (event->attr.namespaces)
 		atomic_inc(&nr_namespaces_events);
+	if (event->attr.cgroup)
+		atomic_inc(&nr_cgroup_events);
 	if (event->attr.task)
 		atomic_inc(&nr_task_events);
 	if (event->attr.freq)
@@ -10632,6 +11062,8 @@ static void account_event(struct perf_event *event)
 		atomic_inc(&nr_ksymbol_events);
 	if (event->attr.bpf_event)
 		atomic_inc(&nr_bpf_events);
+	if (event->attr.text_poke)
+		atomic_inc(&nr_text_poke_events);
 
 	if (inc) {
 		/*
@@ -10794,12 +11226,6 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
 	if (!has_branch_stack(event))
 		event->attr.branch_sample_type = 0;
 
-	if (cgroup_fd != -1) {
-		err = perf_cgroup_connect(cgroup_fd, event, attr, group_leader);
-		if (err)
-			goto err_ns;
-	}
-
 	pmu = perf_init_event(event);
 	if (IS_ERR(pmu)) {
 		err = PTR_ERR(pmu);
@@ -10821,6 +11247,12 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
 		goto err_pmu;
 	}
 
+	if (cgroup_fd != -1) {
+		err = perf_cgroup_connect(cgroup_fd, event, attr, group_leader);
+		if (err)
+			goto err_pmu;
+	}
+
 	err = exclusive_event_init(event);
 	if (err)
 		goto err_pmu;
@@ -10881,12 +11313,12 @@ err_per_task:
 	exclusive_event_destroy(event);
 
 err_pmu:
+	if (is_cgroup_event(event))
+		perf_detach_cgroup(event);
 	if (event->destroy)
 		event->destroy(event);
 	module_put(pmu->module);
 err_ns:
-	if (is_cgroup_event(event))
-		perf_detach_cgroup(event);
 	if (event->ns)
 		put_pid_ns(event->ns);
 	if (event->hw.target)
@@ -10995,6 +11427,12 @@ static int perf_copy_attr(struct perf_event_attr __user *uattr,
 
 	if (attr->sample_type & PERF_SAMPLE_REGS_INTR)
 		ret = perf_reg_validate(attr->sample_regs_intr);
+
+#ifndef CONFIG_CGROUP_PERF
+	if (attr->sample_type & PERF_SAMPLE_CGROUP)
+		return -EINVAL;
+#endif
+
 out:
 	return ret;
 
@@ -11164,7 +11602,7 @@ SYSCALL_DEFINE5(perf_event_open,
 	struct perf_event *group_leader = NULL, *output_event = NULL;
 	struct perf_event *event, *sibling;
 	struct perf_event_attr attr;
-	struct perf_event_context *ctx, *uninitialized_var(gctx);
+	struct perf_event_context *ctx, *gctx;
 	struct file *event_file = NULL;
 	struct fd group = {NULL, 0};
 	struct task_struct *task = NULL;
@@ -11195,7 +11633,7 @@ SYSCALL_DEFINE5(perf_event_open,
 	}
 
 	if (attr.namespaces) {
-		if (!capable(CAP_SYS_ADMIN))
+		if (!perfmon_capable())
 			return -EACCES;
 	}
 
@@ -11263,20 +11701,20 @@ SYSCALL_DEFINE5(perf_event_open,
 	}
 
 	if (task) {
-		err = mutex_lock_interruptible(&task->signal->cred_guard_mutex);
+		err = mutex_lock_interruptible(&task->signal->exec_update_mutex);
 		if (err)
 			goto err_task;
 
 		/*
-		 * Reuse ptrace permission checks for now.
+		 * Preserve ptrace permission check for backwards compatibility.
 		 *
-		 * We must hold cred_guard_mutex across this and any potential
+		 * We must hold exec_update_mutex across this and any potential
 		 * perf_install_in_context() call for this new event to
 		 * serialize against exec() altering our credentials (and the
 		 * perf_event_exit_task() that could imply).
 		 */
 		err = -EACCES;
-		if (!ptrace_may_access(task, PTRACE_MODE_READ_REALCREDS))
+		if (!perfmon_capable() && !ptrace_may_access(task, PTRACE_MODE_READ_REALCREDS))
 			goto err_cred;
 	}
 
@@ -11559,7 +11997,7 @@ SYSCALL_DEFINE5(perf_event_open,
 	mutex_unlock(&ctx->mutex);
 
 	if (task) {
-		mutex_unlock(&task->signal->cred_guard_mutex);
+		mutex_unlock(&task->signal->exec_update_mutex);
 		put_task_struct(task);
 	}
 
@@ -11595,7 +12033,7 @@ err_alloc:
 		free_event(event);
 err_cred:
 	if (task)
-		mutex_unlock(&task->signal->cred_guard_mutex);
+		mutex_unlock(&task->signal->exec_update_mutex);
 err_task:
 	if (task)
 		put_task_struct(task);
@@ -11900,8 +12338,8 @@ static void perf_event_exit_task_context(struct task_struct *child, int ctxn)
 /*
  * When a child task exits, feed back event values to parent events.
  *
- * Can be called with cred_guard_mutex held when called from
- * install_exec_creds().
+ * Can be called with exec_update_mutex held when called from
+ * setup_new_exec().
  */
 void perf_event_exit_task(struct task_struct *child)
 {
@@ -12090,8 +12528,7 @@ inherit_event(struct perf_event *parent_event,
 	    !child_ctx->task_ctx_data) {
 		struct pmu *pmu = child_event->pmu;
 
-		child_ctx->task_ctx_data = kzalloc(pmu->task_ctx_size,
-						   GFP_KERNEL);
+		child_ctx->task_ctx_data = alloc_task_ctx_data(pmu);
 		if (!child_ctx->task_ctx_data) {
 			free_event(child_event);
 			return ERR_PTR(-ENOMEM);
@@ -12592,6 +13029,12 @@ static void perf_cgroup_css_free(struct cgroup_subsys_state *css)
 	kfree(jc);
 }
 
+static int perf_cgroup_css_online(struct cgroup_subsys_state *css)
+{
+	perf_event_cgroup(css->cgroup);
+	return 0;
+}
+
 static int __perf_cgroup_move(void *info)
 {
 	struct task_struct *task = info;
@@ -12613,6 +13056,7 @@ static void perf_cgroup_attach(struct cgroup_taskset *tset)
 struct cgroup_subsys perf_event_cgrp_subsys = {
 	.css_alloc	= perf_cgroup_css_alloc,
 	.css_free	= perf_cgroup_css_free,
+	.css_online	= perf_cgroup_css_online,
 	.attach		= perf_cgroup_attach,
 	/*
 	 * Implicitly enable on dfl hierarchy so that perf events can
diff --git a/kernel/events/hw_breakpoint.c b/kernel/events/hw_breakpoint.c
index 3cc8416ec844..b48d7039a015 100644
--- a/kernel/events/hw_breakpoint.c
+++ b/kernel/events/hw_breakpoint.c
@@ -213,6 +213,15 @@ toggle_bp_slot(struct perf_event *bp, bool enable, enum bp_type_idx type,
 		list_del(&bp->hw.bp_list);
 }
 
+__weak int arch_reserve_bp_slot(struct perf_event *bp)
+{
+	return 0;
+}
+
+__weak void arch_release_bp_slot(struct perf_event *bp)
+{
+}
+
 /*
  * Function to perform processor-specific cleanup during unregistration
  */
@@ -270,6 +279,7 @@ static int __reserve_bp_slot(struct perf_event *bp, u64 bp_type)
 	struct bp_busy_slots slots = {0};
 	enum bp_type_idx type;
 	int weight;
+	int ret;
 
 	/* We couldn't initialize breakpoint constraints on boot */
 	if (!constraints_initialized)
@@ -294,6 +304,10 @@ static int __reserve_bp_slot(struct perf_event *bp, u64 bp_type)
 	if (slots.pinned + (!!slots.flexible) > nr_slots[type])
 		return -ENOSPC;
 
+	ret = arch_reserve_bp_slot(bp);
+	if (ret)
+		return ret;
+
 	toggle_bp_slot(bp, true, type, weight);
 
 	return 0;
@@ -317,6 +331,8 @@ static void __release_bp_slot(struct perf_event *bp, u64 bp_type)
 	enum bp_type_idx type;
 	int weight;
 
+	arch_release_bp_slot(bp);
+
 	type = find_slot_idx(bp_type);
 	weight = hw_breakpoint_weight(bp);
 	toggle_bp_slot(bp, false, type, weight);
diff --git a/kernel/events/internal.h b/kernel/events/internal.h
index f16f66b6b655..fcbf5616a441 100644
--- a/kernel/events/internal.h
+++ b/kernel/events/internal.h
@@ -55,7 +55,7 @@ struct perf_buffer {
 	void				*aux_priv;
 
 	struct perf_event_mmap_page	*user_page;
-	void				*data_pages[0];
+	void				*data_pages[];
 };
 
 extern void rb_free(struct perf_buffer *rb);
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index ece7e13f6e4a..0e18aaf23a7b 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -162,14 +162,12 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr,
 	};
 	int err;
 	struct mmu_notifier_range range;
-	struct mem_cgroup *memcg;
 
 	mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, mm, addr,
 				addr + PAGE_SIZE);
 
 	if (new_page) {
-		err = mem_cgroup_try_charge(new_page, vma->vm_mm, GFP_KERNEL,
-					    &memcg, false);
+		err = mem_cgroup_charge(new_page, vma->vm_mm, GFP_KERNEL);
 		if (err)
 			return err;
 	}
@@ -179,18 +177,14 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr,
 
 	mmu_notifier_invalidate_range_start(&range);
 	err = -EAGAIN;
-	if (!page_vma_mapped_walk(&pvmw)) {
-		if (new_page)
-			mem_cgroup_cancel_charge(new_page, memcg, false);
+	if (!page_vma_mapped_walk(&pvmw))
 		goto unlock;
-	}
 	VM_BUG_ON_PAGE(addr != pvmw.address, old_page);
 
 	if (new_page) {
 		get_page(new_page);
 		page_add_new_anon_rmap(new_page, vma, addr, false);
-		mem_cgroup_commit_charge(new_page, memcg, false, false);
-		lru_cache_add_active_or_unevictable(new_page, vma);
+		lru_cache_add_inactive_or_unevictable(new_page, vma);
 	} else
 		/* no new page, just dec_mm_counter for old_page */
 		dec_mm_counter(mm, MM_ANONPAGES);
@@ -211,7 +205,7 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr,
 		try_to_free_swap(old_page);
 	page_vma_mapped_walk_done(&pvmw);
 
-	if (vma->vm_flags & VM_LOCKED)
+	if ((vma->vm_flags & VM_LOCKED) && !PageCompound(old_page))
 		munlock_vma_page(old_page);
 	put_page(old_page);
 
@@ -382,7 +376,7 @@ __update_ref_ctr(struct mm_struct *mm, unsigned long vaddr, short d)
 	if (!vaddr || !d)
 		return -EINVAL;
 
-	ret = get_user_pages_remote(NULL, mm, vaddr, 1,
+	ret = get_user_pages_remote(mm, vaddr, 1,
 			FOLL_WRITE, &page, &vma, NULL);
 	if (unlikely(ret <= 0)) {
 		/*
@@ -463,7 +457,7 @@ static int update_ref_ctr(struct uprobe *uprobe, struct mm_struct *mm,
  * @vaddr: the virtual address to store the opcode.
  * @opcode: opcode to be written at @vaddr.
  *
- * Called with mm->mmap_sem held for write.
+ * Called with mm->mmap_lock held for write.
  * Return 0 (success) or a negative errno.
  */
 int uprobe_write_opcode(struct arch_uprobe *auprobe, struct mm_struct *mm,
@@ -483,7 +477,7 @@ retry:
 	if (is_register)
 		gup_flags |= FOLL_SPLIT_PMD;
 	/* Read the page with vaddr into memory */
-	ret = get_user_pages_remote(NULL, mm, vaddr, 1, gup_flags,
+	ret = get_user_pages_remote(mm, vaddr, 1, gup_flags,
 				    &old_page, &vma, NULL);
 	if (ret <= 0)
 		return ret;
@@ -867,10 +861,6 @@ static int prepare_uprobe(struct uprobe *uprobe, struct file *file,
 	if (ret)
 		goto out;
 
-	/* uprobe_write_opcode() assumes we don't cross page boundary */
-	BUG_ON((uprobe->offset & ~PAGE_MASK) +
-			UPROBE_SWBP_INSN_SIZE > PAGE_SIZE);
-
 	smp_wmb(); /* pairs with the smp_rmb() in handle_swbp() */
 	set_bit(UPROBE_COPY_INSN, &uprobe->flags);
 
@@ -1064,7 +1054,7 @@ register_for_each_vma(struct uprobe *uprobe, struct uprobe_consumer *new)
 		if (err && is_register)
 			goto free;
 
-		down_write(&mm->mmap_sem);
+		mmap_write_lock(mm);
 		vma = find_vma(mm, info->vaddr);
 		if (!vma || !valid_vma(vma, is_register) ||
 		    file_inode(vma->vm_file) != uprobe->inode)
@@ -1086,7 +1076,7 @@ register_for_each_vma(struct uprobe *uprobe, struct uprobe_consumer *new)
 		}
 
  unlock:
-		up_write(&mm->mmap_sem);
+		mmap_write_unlock(mm);
  free:
 		mmput(mm);
 		info = free_map_info(info);
@@ -1166,6 +1156,15 @@ static int __uprobe_register(struct inode *inode, loff_t offset,
 	if (offset > i_size_read(inode))
 		return -EINVAL;
 
+	/*
+	 * This ensures that copy_from_page(), copy_to_page() and
+	 * __update_ref_ctr() can't cross page boundary.
+	 */
+	if (!IS_ALIGNED(offset, UPROBE_SWBP_INSN_SIZE))
+		return -EINVAL;
+	if (!IS_ALIGNED(ref_ctr_offset, sizeof(short)))
+		return -EINVAL;
+
  retry:
 	uprobe = alloc_uprobe(inode, offset, ref_ctr_offset);
 	if (!uprobe)
@@ -1241,7 +1240,7 @@ static int unapply_uprobe(struct uprobe *uprobe, struct mm_struct *mm)
 	struct vm_area_struct *vma;
 	int err = 0;
 
-	down_read(&mm->mmap_sem);
+	mmap_read_lock(mm);
 	for (vma = mm->mmap; vma; vma = vma->vm_next) {
 		unsigned long vaddr;
 		loff_t offset;
@@ -1258,7 +1257,7 @@ static int unapply_uprobe(struct uprobe *uprobe, struct mm_struct *mm)
 		vaddr = offset_to_vaddr(vma, uprobe->offset);
 		err |= remove_breakpoint(uprobe, mm, vaddr);
 	}
-	up_read(&mm->mmap_sem);
+	mmap_read_unlock(mm);
 
 	return err;
 }
@@ -1355,7 +1354,7 @@ static int delayed_ref_ctr_inc(struct vm_area_struct *vma)
 }
 
 /*
- * Called from mmap_region/vma_adjust with mm->mmap_sem acquired.
+ * Called from mmap_region/vma_adjust with mm->mmap_lock acquired.
  *
  * Currently we ignore all errors and always return 0, the callers
  * can't handle the failure anyway.
@@ -1445,7 +1444,7 @@ static int xol_add_vma(struct mm_struct *mm, struct xol_area *area)
 	struct vm_area_struct *vma;
 	int ret;
 
-	if (down_write_killable(&mm->mmap_sem))
+	if (mmap_write_lock_killable(mm))
 		return -EINTR;
 
 	if (mm->uprobes_state.xol_area) {
@@ -1475,7 +1474,7 @@ static int xol_add_vma(struct mm_struct *mm, struct xol_area *area)
 	/* pairs with get_xol_area() */
 	smp_store_release(&mm->uprobes_state.xol_area, area); /* ^^^ */
  fail:
-	up_write(&mm->mmap_sem);
+	mmap_write_unlock(mm);
 
 	return ret;
 }
@@ -1674,7 +1673,7 @@ void __weak arch_uprobe_copy_ixol(struct page *page, unsigned long vaddr,
 	copy_to_page(page, vaddr, src, len);
 
 	/*
-	 * We probably need flush_icache_user_range() but it needs vma.
+	 * We probably need flush_icache_user_page() but it needs vma.
 	 * This should work on most of architectures by default. If
 	 * architecture needs to do something different it can define
 	 * its own version of the function.
@@ -2014,6 +2013,9 @@ static int is_trap_at_addr(struct mm_struct *mm, unsigned long vaddr)
 	uprobe_opcode_t opcode;
 	int result;
 
+	if (WARN_ON_ONCE(!IS_ALIGNED(vaddr, UPROBE_SWBP_INSN_SIZE)))
+		return -EINVAL;
+
 	pagefault_disable();
 	result = __get_user(opcode, (uprobe_opcode_t __user *)vaddr);
 	pagefault_enable();
@@ -2027,7 +2029,7 @@ static int is_trap_at_addr(struct mm_struct *mm, unsigned long vaddr)
 	 * but we treat this as a 'remote' access since it is
 	 * essentially a kernel access to the memory.
 	 */
-	result = get_user_pages_remote(NULL, mm, vaddr, 1, FOLL_FORCE, &page,
+	result = get_user_pages_remote(mm, vaddr, 1, FOLL_FORCE, &page,
 			NULL, NULL);
 	if (result < 0)
 		return result;
@@ -2045,7 +2047,7 @@ static struct uprobe *find_active_uprobe(unsigned long bp_vaddr, int *is_swbp)
 	struct uprobe *uprobe = NULL;
 	struct vm_area_struct *vma;
 
-	down_read(&mm->mmap_sem);
+	mmap_read_lock(mm);
 	vma = find_vma(mm, bp_vaddr);
 	if (vma && vma->vm_start <= bp_vaddr) {
 		if (valid_vma(vma, false)) {
@@ -2063,7 +2065,7 @@ static struct uprobe *find_active_uprobe(unsigned long bp_vaddr, int *is_swbp)
 
 	if (!uprobe && test_and_clear_bit(MMF_RECALC_UPROBES, &mm->flags))
 		mmf_recalc_uprobes(mm);
-	up_read(&mm->mmap_sem);
+	mmap_read_unlock(mm);
 
 	return uprobe;
 }
@@ -2187,7 +2189,7 @@ static void handle_swbp(struct pt_regs *regs)
 {
 	struct uprobe *uprobe;
 	unsigned long bp_vaddr;
-	int uninitialized_var(is_swbp);
+	int is_swbp;
 
 	bp_vaddr = uprobe_get_swbp_addr(regs);
 	if (bp_vaddr == get_trampoline_vaddr())
@@ -2197,7 +2199,7 @@ static void handle_swbp(struct pt_regs *regs)
 	if (!uprobe) {
 		if (is_swbp > 0) {
 			/* No matching uprobe; signal SIGTRAP. */
-			send_sig(SIGTRAP, current, 0);
+			force_sig(SIGTRAP);
 		} else {
 			/*
 			 * Either we raced with uprobe_unregister() or we can't
diff --git a/kernel/exit.c b/kernel/exit.c
index 0b81b26a872a..733e80f334e7 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -66,7 +66,6 @@
 
 #include <linux/uaccess.h>
 #include <asm/unistd.h>
-#include <asm/pgtable.h>
 #include <asm/mmu_context.h>
 
 static void __unhash_process(struct task_struct *p, bool group_dead)
@@ -94,7 +93,7 @@ static void __exit_signal(struct task_struct *tsk)
 	struct signal_struct *sig = tsk->signal;
 	bool group_dead = thread_group_leader(tsk);
 	struct sighand_struct *sighand;
-	struct tty_struct *uninitialized_var(tty);
+	struct tty_struct *tty;
 	u64 utime, stime;
 
 	sighand = rcu_dereference_check(tsk->sighand,
@@ -103,17 +102,8 @@ static void __exit_signal(struct task_struct *tsk)
 
 #ifdef CONFIG_POSIX_TIMERS
 	posix_cpu_timers_exit(tsk);
-	if (group_dead) {
+	if (group_dead)
 		posix_cpu_timers_exit_group(tsk);
-	} else {
-		/*
-		 * This can only happen if the caller is de_thread().
-		 * FIXME: this is the temporary hack, we should teach
-		 * posix-cpu-timers to handle this case correctly.
-		 */
-		if (unlikely(has_group_leader_pid(tsk)))
-			posix_cpu_timers_exit_group(tsk);
-	}
 #endif
 
 	if (group_dead) {
@@ -191,6 +181,7 @@ void put_task_struct_rcu_user(struct task_struct *task)
 void release_task(struct task_struct *p)
 {
 	struct task_struct *leader;
+	struct pid *thread_pid;
 	int zap_leader;
 repeat:
 	/* don't need to get the RCU readlock here - the process is dead and
@@ -199,11 +190,11 @@ repeat:
 	atomic_dec(&__task_cred(p)->user->processes);
 	rcu_read_unlock();
 
-	proc_flush_task(p);
 	cgroup_release(p);
 
 	write_lock_irq(&tasklist_lock);
 	ptrace_release_task(p);
+	thread_pid = get_pid(p->thread_pid);
 	__exit_signal(p);
 
 	/*
@@ -226,6 +217,9 @@ repeat:
 	}
 
 	write_unlock_irq(&tasklist_lock);
+	seccomp_filter_release(p);
+	proc_flush_pid(thread_pid);
+	put_pid(thread_pid);
 	release_thread(p);
 	put_task_struct_rcu_user(p);
 
@@ -234,8 +228,9 @@ repeat:
 		goto repeat;
 }
 
-void rcuwait_wake_up(struct rcuwait *w)
+int rcuwait_wake_up(struct rcuwait *w)
 {
+	int ret = 0;
 	struct task_struct *task;
 
 	rcu_read_lock();
@@ -243,7 +238,7 @@ void rcuwait_wake_up(struct rcuwait *w)
 	/*
 	 * Order condition vs @task, such that everything prior to the load
 	 * of @task is visible. This is the condition as to why the user called
-	 * rcuwait_trywake() in the first place. Pairs with set_current_state()
+	 * rcuwait_wake() in the first place. Pairs with set_current_state()
 	 * barrier (A) in rcuwait_wait_event().
 	 *
 	 *    WAIT                WAKE
@@ -255,9 +250,12 @@ void rcuwait_wake_up(struct rcuwait *w)
 
 	task = rcu_dereference(w->task);
 	if (task)
-		wake_up_process(task);
+		ret = wake_up_process(task);
 	rcu_read_unlock();
+
+	return ret;
 }
+EXPORT_SYMBOL_GPL(rcuwait_wake_up);
 
 /*
  * Determine if a process group is "orphaned", according to the POSIX
@@ -443,17 +441,17 @@ static void exit_mm(void)
 	sync_mm_rss(mm);
 	/*
 	 * Serialize with any possible pending coredump.
-	 * We must hold mmap_sem around checking core_state
+	 * We must hold mmap_lock around checking core_state
 	 * and clearing tsk->mm.  The core-inducing thread
 	 * will increment ->nr_threads for each thread in the
 	 * group with ->mm != NULL.
 	 */
-	down_read(&mm->mmap_sem);
+	mmap_read_lock(mm);
 	core_state = mm->core_state;
 	if (core_state) {
 		struct core_thread self;
 
-		up_read(&mm->mmap_sem);
+		mmap_read_unlock(mm);
 
 		self.task = current;
 		self.next = xchg(&core_state->dumper.next, &self);
@@ -471,14 +469,14 @@ static void exit_mm(void)
 			freezable_schedule();
 		}
 		__set_current_state(TASK_RUNNING);
-		down_read(&mm->mmap_sem);
+		mmap_read_lock(mm);
 	}
 	mmgrab(mm);
 	BUG_ON(mm != current->active_mm);
 	/* more a memory barrier than a real lock */
 	task_lock(current);
 	current->mm = NULL;
-	up_read(&mm->mmap_sem);
+	mmap_read_unlock(mm);
 	enter_lazy_tlb(mm, current);
 	task_unlock(current);
 	mm_update_next_owner(mm);
@@ -713,8 +711,12 @@ void __noreturn do_exit(long code)
 	struct task_struct *tsk = current;
 	int group_dead;
 
-	profile_task_exit(tsk);
-	kcov_task_exit(tsk);
+	/*
+	 * We can get here from a kernel oops, sometimes with preemption off.
+	 * Start by checking for critical errors.
+	 * Then fix up important state like USER_DS and preemption.
+	 * Then do everything else.
+	 */
 
 	WARN_ON(blk_needs_flush_plug(tsk));
 
@@ -730,7 +732,17 @@ void __noreturn do_exit(long code)
 	 * mm_release()->clear_child_tid() from writing to a user-controlled
 	 * kernel address.
 	 */
-	set_fs(USER_DS);
+	force_uaccess_begin();
+
+	if (unlikely(in_atomic())) {
+		pr_info("note: %s[%d] exited with preempt_count %d\n",
+			current->comm, task_pid_nr(current),
+			preempt_count());
+		preempt_count_set(PREEMPT_ENABLED);
+	}
+
+	profile_task_exit(tsk);
+	kcov_task_exit(tsk);
 
 	ptrace_event(PTRACE_EVENT_EXIT, code);
 
@@ -749,13 +761,6 @@ void __noreturn do_exit(long code)
 
 	exit_signals(tsk);  /* sets PF_EXITING */
 
-	if (unlikely(in_atomic())) {
-		pr_info("note: %s[%d] exited with preempt_count %d\n",
-			current->comm, task_pid_nr(current),
-			preempt_count());
-		preempt_count_set(PREEMPT_ENABLED);
-	}
-
 	/* sync mm's RSS info before statistics gathering */
 	if (tsk->mm)
 		sync_mm_rss(tsk->mm);
@@ -800,7 +805,6 @@ void __noreturn do_exit(long code)
 	exit_task_namespaces(tsk);
 	exit_task_work(tsk);
 	exit_thread(tsk);
-	exit_umh(tsk);
 
 	/*
 	 * Flush inherited counters to the parent - before the parent
@@ -1563,7 +1567,7 @@ SYSCALL_DEFINE5(waitid, int, which, pid_t, upid, struct siginfo __user *,
 	if (!infop)
 		return err;
 
-	if (!user_access_begin(infop, sizeof(*infop)))
+	if (!user_write_access_begin(infop, sizeof(*infop)))
 		return -EFAULT;
 
 	unsafe_put_user(signo, &infop->si_signo, Efault);
@@ -1572,10 +1576,10 @@ SYSCALL_DEFINE5(waitid, int, which, pid_t, upid, struct siginfo __user *,
 	unsafe_put_user(info.pid, &infop->si_pid, Efault);
 	unsafe_put_user(info.uid, &infop->si_uid, Efault);
 	unsafe_put_user(info.status, &infop->si_status, Efault);
-	user_access_end();
+	user_write_access_end();
 	return err;
 Efault:
-	user_access_end();
+	user_write_access_end();
 	return -EFAULT;
 }
 
@@ -1622,6 +1626,22 @@ long kernel_wait4(pid_t upid, int __user *stat_addr, int options,
 	return ret;
 }
 
+int kernel_wait(pid_t pid, int *stat)
+{
+	struct wait_opts wo = {
+		.wo_type	= PIDTYPE_PID,
+		.wo_pid		= find_get_pid(pid),
+		.wo_flags	= WEXITED,
+	};
+	int ret;
+
+	ret = do_wait(&wo);
+	if (ret > 0 && wo.wo_stat)
+		*stat = wo.wo_stat;
+	put_pid(wo.wo_pid);
+	return ret;
+}
+
 SYSCALL_DEFINE4(wait4, pid_t, upid, int __user *, stat_addr,
 		int, options, struct rusage __user *, ru)
 {
@@ -1690,7 +1710,7 @@ COMPAT_SYSCALL_DEFINE5(waitid,
 	if (!infop)
 		return err;
 
-	if (!user_access_begin(infop, sizeof(*infop)))
+	if (!user_write_access_begin(infop, sizeof(*infop)))
 		return -EFAULT;
 
 	unsafe_put_user(signo, &infop->si_signo, Efault);
@@ -1699,14 +1719,38 @@ COMPAT_SYSCALL_DEFINE5(waitid,
 	unsafe_put_user(info.pid, &infop->si_pid, Efault);
 	unsafe_put_user(info.uid, &infop->si_uid, Efault);
 	unsafe_put_user(info.status, &infop->si_status, Efault);
-	user_access_end();
+	user_write_access_end();
 	return err;
 Efault:
-	user_access_end();
+	user_write_access_end();
 	return -EFAULT;
 }
 #endif
 
+/**
+ * thread_group_exited - check that a thread group has exited
+ * @pid: tgid of thread group to be checked.
+ *
+ * Test if the thread group represented by tgid has exited (all
+ * threads are zombies, dead or completely gone).
+ *
+ * Return: true if the thread group has exited. false otherwise.
+ */
+bool thread_group_exited(struct pid *pid)
+{
+	struct task_struct *task;
+	bool exited;
+
+	rcu_read_lock();
+	task = pid_task(pid, PIDTYPE_PID);
+	exited = !task ||
+		(READ_ONCE(task->exit_state) && thread_group_empty(task));
+	rcu_read_unlock();
+
+	return exited;
+}
+EXPORT_SYMBOL(thread_group_exited);
+
 __weak void abort(void)
 {
 	BUG();
diff --git a/kernel/extable.c b/kernel/extable.c
index a0024f27d3a1..b0ea5eb0c3b4 100644
--- a/kernel/extable.c
+++ b/kernel/extable.c
@@ -34,7 +34,8 @@ u32 __initdata __visible main_extable_sort_needed = 1;
 /* Sort the kernel's built-in exception table */
 void __init sort_main_extable(void)
 {
-	if (main_extable_sort_needed && __stop___ex_table > __start___ex_table) {
+	if (main_extable_sort_needed &&
+	    &__stop___ex_table > &__start___ex_table) {
 		pr_notice("Sorting __ex_table...\n");
 		sort_extable(__start___ex_table, __stop___ex_table);
 	}
@@ -149,8 +150,6 @@ int kernel_text_address(unsigned long addr)
 		goto out;
 	if (is_bpf_text_address(addr))
 		goto out;
-	if (is_bpf_image_address(addr))
-		goto out;
 	ret = 0;
 out:
 	if (no_rcu)
diff --git a/kernel/fork.c b/kernel/fork.c
index 86425305cd4a..4d32190861bd 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -94,8 +94,8 @@
 #include <linux/thread_info.h>
 #include <linux/stackleak.h>
 #include <linux/kasan.h>
+#include <linux/scs.h>
 
-#include <asm/pgtable.h>
 #include <asm/pgalloc.h>
 #include <linux/uaccess.h>
 #include <asm/mmu_context.h>
@@ -261,7 +261,7 @@ static unsigned long *alloc_thread_stack_node(struct task_struct *tsk, int node)
 					     THREAD_SIZE_ORDER);
 
 	if (likely(page)) {
-		tsk->stack = page_address(page);
+		tsk->stack = kasan_reset_tag(page_address(page));
 		return tsk->stack;
 	}
 	return NULL;
@@ -276,13 +276,8 @@ static inline void free_thread_stack(struct task_struct *tsk)
 	if (vm) {
 		int i;
 
-		for (i = 0; i < THREAD_SIZE / PAGE_SIZE; i++) {
-			mod_memcg_page_state(vm->pages[i],
-					     MEMCG_KERNEL_STACK_KB,
-					     -(int)(PAGE_SIZE / 1024));
-
-			memcg_kmem_uncharge(vm->pages[i], 0);
-		}
+		for (i = 0; i < THREAD_SIZE / PAGE_SIZE; i++)
+			memcg_kmem_uncharge_page(vm->pages[i], 0);
 
 		for (i = 0; i < NR_CACHED_STACKS; i++) {
 			if (this_cpu_cmpxchg(cached_stacks[i],
@@ -307,6 +302,7 @@ static unsigned long *alloc_thread_stack_node(struct task_struct *tsk,
 {
 	unsigned long *stack;
 	stack = kmem_cache_alloc_node(thread_stack_cache, THREADINFO_GFP, node);
+	stack = kasan_reset_tag(stack);
 	tsk->stack = stack;
 	return stack;
 }
@@ -359,8 +355,15 @@ struct vm_area_struct *vm_area_dup(struct vm_area_struct *orig)
 	struct vm_area_struct *new = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL);
 
 	if (new) {
-		*new = *orig;
+		ASSERT_EXCLUSIVE_WRITER(orig->vm_flags);
+		ASSERT_EXCLUSIVE_WRITER(orig->vm_file);
+		/*
+		 * orig->shared.rb may be modified concurrently, but the clone
+		 * will be reinitialized.
+		 */
+		*new = data_race(*orig);
 		INIT_LIST_HEAD(&new->anon_vma_chain);
+		new->vm_next = new->vm_prev = NULL;
 	}
 	return new;
 }
@@ -375,31 +378,14 @@ static void account_kernel_stack(struct task_struct *tsk, int account)
 	void *stack = task_stack_page(tsk);
 	struct vm_struct *vm = task_stack_vm_area(tsk);
 
-	BUILD_BUG_ON(IS_ENABLED(CONFIG_VMAP_STACK) && PAGE_SIZE % 1024 != 0);
-
-	if (vm) {
-		int i;
-
-		BUG_ON(vm->nr_pages != THREAD_SIZE / PAGE_SIZE);
-
-		for (i = 0; i < THREAD_SIZE / PAGE_SIZE; i++) {
-			mod_zone_page_state(page_zone(vm->pages[i]),
-					    NR_KERNEL_STACK_KB,
-					    PAGE_SIZE / 1024 * account);
-		}
-	} else {
-		/*
-		 * All stack pages are in the same zone and belong to the
-		 * same memcg.
-		 */
-		struct page *first_page = virt_to_page(stack);
-
-		mod_zone_page_state(page_zone(first_page), NR_KERNEL_STACK_KB,
-				    THREAD_SIZE / 1024 * account);
 
-		mod_memcg_page_state(first_page, MEMCG_KERNEL_STACK_KB,
-				     account * (THREAD_SIZE / 1024));
-	}
+	/* All stack pages are in the same node. */
+	if (vm)
+		mod_lruvec_page_state(vm->pages[0], NR_KERNEL_STACK_KB,
+				      account * (THREAD_SIZE / 1024));
+	else
+		mod_lruvec_slab_state(stack, NR_KERNEL_STACK_KB,
+				      account * (THREAD_SIZE / 1024));
 }
 
 static int memcg_charge_kernel_stack(struct task_struct *tsk)
@@ -408,23 +394,23 @@ static int memcg_charge_kernel_stack(struct task_struct *tsk)
 	struct vm_struct *vm = task_stack_vm_area(tsk);
 	int ret;
 
+	BUILD_BUG_ON(IS_ENABLED(CONFIG_VMAP_STACK) && PAGE_SIZE % 1024 != 0);
+
 	if (vm) {
 		int i;
 
+		BUG_ON(vm->nr_pages != THREAD_SIZE / PAGE_SIZE);
+
 		for (i = 0; i < THREAD_SIZE / PAGE_SIZE; i++) {
 			/*
-			 * If memcg_kmem_charge() fails, page->mem_cgroup
-			 * pointer is NULL, and both memcg_kmem_uncharge()
-			 * and mod_memcg_page_state() in free_thread_stack()
-			 * will ignore this page. So it's safe.
+			 * If memcg_kmem_charge_page() fails, page->mem_cgroup
+			 * pointer is NULL, and memcg_kmem_uncharge_page() in
+			 * free_thread_stack() will ignore this page.
 			 */
-			ret = memcg_kmem_charge(vm->pages[i], GFP_KERNEL, 0);
+			ret = memcg_kmem_charge_page(vm->pages[i], GFP_KERNEL,
+						     0);
 			if (ret)
 				return ret;
-
-			mod_memcg_page_state(vm->pages[i],
-					     MEMCG_KERNEL_STACK_KB,
-					     PAGE_SIZE / 1024);
 		}
 	}
 #endif
@@ -454,6 +440,8 @@ void put_task_stack(struct task_struct *tsk)
 
 void free_task(struct task_struct *tsk)
 {
+	scs_release(tsk);
+
 #ifndef CONFIG_THREAD_INFO_IN_TASK
 	/*
 	 * The task is finally done with both the stack and thread_info,
@@ -469,7 +457,6 @@ void free_task(struct task_struct *tsk)
 #endif
 	rt_mutex_debug_task_free(tsk);
 	ftrace_graph_exit_task(tsk);
-	put_seccomp_filter(tsk);
 	arch_release_task_struct(tsk);
 	if (tsk->flags & PF_KTHREAD)
 		free_kthread_struct(tsk);
@@ -488,7 +475,7 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
 	LIST_HEAD(uf);
 
 	uprobe_start_dup_mmap();
-	if (down_write_killable(&oldmm->mmap_sem)) {
+	if (mmap_write_lock_killable(oldmm)) {
 		retval = -EINTR;
 		goto fail_uprobe_end;
 	}
@@ -497,7 +484,7 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
 	/*
 	 * Not linked in yet - no deadlock potential:
 	 */
-	down_write_nested(&mm->mmap_sem, SINGLE_DEPTH_NESTING);
+	mmap_write_lock_nested(mm, SINGLE_DEPTH_NESTING);
 
 	/* No ordering required: file already has been exposed. */
 	RCU_INIT_POINTER(mm->exe_file, get_mm_exe_file(oldmm));
@@ -552,14 +539,15 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
 		if (retval)
 			goto fail_nomem_anon_vma_fork;
 		if (tmp->vm_flags & VM_WIPEONFORK) {
-			/* VM_WIPEONFORK gets a clean slate in the child. */
+			/*
+			 * VM_WIPEONFORK gets a clean slate in the child.
+			 * Don't prepare anon_vma until fault since we don't
+			 * copy page for current vma.
+			 */
 			tmp->anon_vma = NULL;
-			if (anon_vma_prepare(tmp))
-				goto fail_nomem_anon_vma_fork;
 		} else if (anon_vma_fork(tmp, mpnt))
 			goto fail_nomem_anon_vma_fork;
 		tmp->vm_flags &= ~(VM_LOCKED | VM_LOCKONFAULT);
-		tmp->vm_next = tmp->vm_prev = NULL;
 		file = tmp->vm_file;
 		if (file) {
 			struct inode *inode = file_inode(file);
@@ -612,9 +600,9 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
 	/* a new mm has just been created */
 	retval = arch_dup_mmap(oldmm, mm);
 out:
-	up_write(&mm->mmap_sem);
+	mmap_write_unlock(mm);
 	flush_tlb_mm(oldmm);
-	up_write(&oldmm->mmap_sem);
+	mmap_write_unlock(oldmm);
 	dup_userfaultfd_complete(&uf);
 fail_uprobe_end:
 	uprobe_end_dup_mmap();
@@ -644,9 +632,9 @@ static inline void mm_free_pgd(struct mm_struct *mm)
 #else
 static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
 {
-	down_write(&oldmm->mmap_sem);
+	mmap_write_lock(oldmm);
 	RCU_INIT_POINTER(mm->exe_file, get_mm_exe_file(oldmm));
-	up_write(&oldmm->mmap_sem);
+	mmap_write_unlock(oldmm);
 	return 0;
 }
 #define mm_alloc_pgd(mm)	(0)
@@ -837,6 +825,8 @@ void __init fork_init(void)
 			  NULL, free_vm_stack_cache);
 #endif
 
+	scs_init();
+
 	lockdep_init_task(&init_task);
 	uprobes_init();
 }
@@ -896,6 +886,10 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node)
 	if (err)
 		goto free_stack;
 
+	err = scs_prepare(tsk, node);
+	if (err)
+		goto free_stack;
+
 #ifdef CONFIG_SECCOMP
 	/*
 	 * We must handle setting up seccomp filters once we're under
@@ -1011,7 +1005,7 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p,
 	mm->vmacache_seqnum = 0;
 	atomic_set(&mm->mm_users, 1);
 	atomic_set(&mm->mm_count, 1);
-	init_rwsem(&mm->mmap_sem);
+	mmap_init_lock(mm);
 	INIT_LIST_HEAD(&mm->mmlist);
 	mm->core_state = NULL;
 	mm_pgtables_bytes_init(mm);
@@ -1224,7 +1218,7 @@ struct mm_struct *mm_access(struct task_struct *task, unsigned int mode)
 	struct mm_struct *mm;
 	int err;
 
-	err =  mutex_lock_killable(&task->signal->cred_guard_mutex);
+	err =  mutex_lock_killable(&task->signal->exec_update_mutex);
 	if (err)
 		return ERR_PTR(err);
 
@@ -1234,7 +1228,7 @@ struct mm_struct *mm_access(struct task_struct *task, unsigned int mode)
 		mmput(mm);
 		mm = ERR_PTR(-EACCES);
 	}
-	mutex_unlock(&task->signal->cred_guard_mutex);
+	mutex_unlock(&task->signal->exec_update_mutex);
 
 	return mm;
 }
@@ -1463,7 +1457,7 @@ static int copy_files(unsigned long clone_flags, struct task_struct *tsk)
 		goto out;
 	}
 
-	newf = dup_fd(oldf, &error);
+	newf = dup_fd(oldf, NR_OPEN_MAX, &error);
 	if (!newf)
 		goto out;
 
@@ -1594,6 +1588,7 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
 	sig->oom_score_adj_min = current->signal->oom_score_adj_min;
 
 	mutex_init(&sig->cred_guard_mutex);
+	mutex_init(&sig->exec_update_mutex);
 
 	return 0;
 }
@@ -1679,6 +1674,11 @@ static inline void rcu_copy_process(struct task_struct *p)
 	INIT_LIST_HEAD(&p->rcu_tasks_holdout_list);
 	p->rcu_tasks_idle_cpu = -1;
 #endif /* #ifdef CONFIG_TASKS_RCU */
+#ifdef CONFIG_TASKS_TRACE_RCU
+	p->trc_reader_nesting = 0;
+	p->trc_reader_special.s = 0;
+	INIT_LIST_HEAD(&p->trc_holdout_list);
+#endif /* #ifdef CONFIG_TASKS_TRACE_RCU */
 }
 
 struct pid *pidfd_pid(const struct file *file)
@@ -1741,7 +1741,7 @@ static void pidfd_show_fdinfo(struct seq_file *m, struct file *f)
 	pid_t nr = -1;
 
 	if (likely(pid_has_task(pid, PIDTYPE_PID))) {
-		ns = proc_pid_ns(file_inode(m->file));
+		ns = proc_pid_ns(file_inode(m->file)->i_sb);
 		nr = pid_nr_ns(pid, ns);
 	}
 
@@ -1770,22 +1770,18 @@ static void pidfd_show_fdinfo(struct seq_file *m, struct file *f)
  */
 static __poll_t pidfd_poll(struct file *file, struct poll_table_struct *pts)
 {
-	struct task_struct *task;
 	struct pid *pid = file->private_data;
 	__poll_t poll_flags = 0;
 
 	poll_wait(file, &pid->wait_pidfd, pts);
 
-	rcu_read_lock();
-	task = pid_task(pid, PIDTYPE_PID);
 	/*
 	 * Inform pollers only when the whole thread group exits.
 	 * If the thread group leader exits before all other threads in the
 	 * group, then poll(2) should block, similar to the wait(2) family.
 	 */
-	if (!task || (task->exit_state && thread_group_empty(task)))
+	if (thread_group_exited(pid))
 		poll_flags = EPOLLIN | EPOLLRDNORM;
-	rcu_read_unlock();
 
 	return poll_flags;
 }
@@ -1937,8 +1933,8 @@ static __latent_entropy struct task_struct *copy_process(
 
 	rt_mutex_init_task(p);
 
+	lockdep_assert_irqs_enabled();
 #ifdef CONFIG_PROVE_LOCKING
-	DEBUG_LOCKS_WARN_ON(!p->hardirqs_enabled);
 	DEBUG_LOCKS_WARN_ON(!p->softirqs_enabled);
 #endif
 	retval = -EAGAIN;
@@ -1960,7 +1956,7 @@ static __latent_entropy struct task_struct *copy_process(
 	 * to stop root fork bombs.
 	 */
 	retval = -EAGAIN;
-	if (nr_threads >= max_threads)
+	if (data_race(nr_threads >= max_threads))
 		goto bad_fork_cleanup_count;
 
 	delayacct_tsk_init(p);	/* Must remain after dup_task_struct() */
@@ -2015,22 +2011,14 @@ static __latent_entropy struct task_struct *copy_process(
 #ifdef CONFIG_CPUSETS
 	p->cpuset_mem_spread_rotor = NUMA_NO_NODE;
 	p->cpuset_slab_spread_rotor = NUMA_NO_NODE;
-	seqcount_init(&p->mems_allowed_seq);
+	seqcount_spinlock_init(&p->mems_allowed_seq, &p->alloc_lock);
 #endif
 #ifdef CONFIG_TRACE_IRQFLAGS
-	p->irq_events = 0;
-	p->hardirqs_enabled = 0;
-	p->hardirq_enable_ip = 0;
-	p->hardirq_enable_event = 0;
-	p->hardirq_disable_ip = _THIS_IP_;
-	p->hardirq_disable_event = 0;
-	p->softirqs_enabled = 1;
-	p->softirq_enable_ip = _THIS_IP_;
-	p->softirq_enable_event = 0;
-	p->softirq_disable_ip = 0;
-	p->softirq_disable_event = 0;
-	p->hardirq_context = 0;
-	p->softirq_context = 0;
+	memset(&p->irqtrace, 0, sizeof(p->irqtrace));
+	p->irqtrace.hardirq_disable_ip	= _THIS_IP_;
+	p->irqtrace.softirq_enable_ip	= _THIS_IP_;
+	p->softirqs_enabled		= 1;
+	p->softirq_context		= 0;
 #endif
 
 	p->pagefault_disabled = 0;
@@ -2087,8 +2075,7 @@ static __latent_entropy struct task_struct *copy_process(
 	retval = copy_io(clone_flags, p);
 	if (retval)
 		goto bad_fork_cleanup_namespaces;
-	retval = copy_thread_tls(clone_flags, args->stack, args->stack_size, p,
-				 args->tls);
+	retval = copy_thread(clone_flags, args->stack, args->stack_size, p, args->tls);
 	if (retval)
 		goto bad_fork_cleanup_io;
 
@@ -2174,16 +2161,15 @@ static __latent_entropy struct task_struct *copy_process(
 	INIT_LIST_HEAD(&p->thread_group);
 	p->task_works = NULL;
 
-	cgroup_threadgroup_change_begin(current);
 	/*
 	 * Ensure that the cgroup subsystem policies allow the new process to be
 	 * forked. It should be noted the the new process's css_set can be changed
 	 * between here and cgroup_post_fork() if an organisation operation is in
 	 * progress.
 	 */
-	retval = cgroup_can_fork(p);
+	retval = cgroup_can_fork(p, args);
 	if (retval)
-		goto bad_fork_cgroup_threadgroup_change_end;
+		goto bad_fork_put_pidfd;
 
 	/*
 	 * From this point on we must avoid any synchronous user-space
@@ -2288,8 +2274,8 @@ static __latent_entropy struct task_struct *copy_process(
 	write_unlock_irq(&tasklist_lock);
 
 	proc_fork_connector(p);
-	cgroup_post_fork(p);
-	cgroup_threadgroup_change_end(current);
+	sched_post_fork(p);
+	cgroup_post_fork(p, args);
 	perf_event_fork(p);
 
 	trace_task_newtask(p, clone_flags);
@@ -2300,9 +2286,7 @@ static __latent_entropy struct task_struct *copy_process(
 bad_fork_cancel_cgroup:
 	spin_unlock(&current->sighand->siglock);
 	write_unlock_irq(&tasklist_lock);
-	cgroup_cancel_fork(p);
-bad_fork_cgroup_threadgroup_change_end:
-	cgroup_threadgroup_change_end(current);
+	cgroup_cancel_fork(p, args);
 bad_fork_put_pidfd:
 	if (clone_flags & CLONE_PIDFD) {
 		fput(pidfile);
@@ -2410,6 +2394,20 @@ long _do_fork(struct kernel_clone_args *args)
 	long nr;
 
 	/*
+	 * For legacy clone() calls, CLONE_PIDFD uses the parent_tid argument
+	 * to return the pidfd. Hence, CLONE_PIDFD and CLONE_PARENT_SETTID are
+	 * mutually exclusive. With clone3() CLONE_PIDFD has grown a separate
+	 * field in struct clone_args and it still doesn't make sense to have
+	 * them both point at the same memory location. Performing this check
+	 * here has the advantage that we don't need to have a separate helper
+	 * to check for legacy clone().
+	 */
+	if ((args->flags & CLONE_PIDFD) &&
+	    (args->flags & CLONE_PARENT_SETTID) &&
+	    (args->pidfd == args->parent_tid))
+		return -EINVAL;
+
+	/*
 	 * Determine whether and which event to report to ptracer.  When
 	 * called from kernel_thread or CLONE_UNTRACED is explicitly
 	 * requested, no event is reported; otherwise, report if the event
@@ -2466,50 +2464,15 @@ long _do_fork(struct kernel_clone_args *args)
 	return nr;
 }
 
-bool legacy_clone_args_valid(const struct kernel_clone_args *kargs)
-{
-	/* clone(CLONE_PIDFD) uses parent_tidptr to return a pidfd */
-	if ((kargs->flags & CLONE_PIDFD) &&
-	    (kargs->flags & CLONE_PARENT_SETTID))
-		return false;
-
-	return true;
-}
-
-#ifndef CONFIG_HAVE_COPY_THREAD_TLS
-/* For compatibility with architectures that call do_fork directly rather than
- * using the syscall entry points below. */
-long do_fork(unsigned long clone_flags,
-	      unsigned long stack_start,
-	      unsigned long stack_size,
-	      int __user *parent_tidptr,
-	      int __user *child_tidptr)
-{
-	struct kernel_clone_args args = {
-		.flags		= (clone_flags & ~CSIGNAL),
-		.pidfd		= parent_tidptr,
-		.child_tid	= child_tidptr,
-		.parent_tid	= parent_tidptr,
-		.exit_signal	= (clone_flags & CSIGNAL),
-		.stack		= stack_start,
-		.stack_size	= stack_size,
-	};
-
-	if (!legacy_clone_args_valid(&args))
-		return -EINVAL;
-
-	return _do_fork(&args);
-}
-#endif
-
 /*
  * Create a kernel thread.
  */
 pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags)
 {
 	struct kernel_clone_args args = {
-		.flags		= ((flags | CLONE_VM | CLONE_UNTRACED) & ~CSIGNAL),
-		.exit_signal	= (flags & CSIGNAL),
+		.flags		= ((lower_32_bits(flags) | CLONE_VM |
+				    CLONE_UNTRACED) & ~CSIGNAL),
+		.exit_signal	= (lower_32_bits(flags) & CSIGNAL),
 		.stack		= (unsigned long)fn,
 		.stack_size	= (unsigned long)arg,
 	};
@@ -2570,33 +2533,21 @@ SYSCALL_DEFINE5(clone, unsigned long, clone_flags, unsigned long, newsp,
 #endif
 {
 	struct kernel_clone_args args = {
-		.flags		= (clone_flags & ~CSIGNAL),
+		.flags		= (lower_32_bits(clone_flags) & ~CSIGNAL),
 		.pidfd		= parent_tidptr,
 		.child_tid	= child_tidptr,
 		.parent_tid	= parent_tidptr,
-		.exit_signal	= (clone_flags & CSIGNAL),
+		.exit_signal	= (lower_32_bits(clone_flags) & CSIGNAL),
 		.stack		= newsp,
 		.tls		= tls,
 	};
 
-	if (!legacy_clone_args_valid(&args))
-		return -EINVAL;
-
 	return _do_fork(&args);
 }
 #endif
 
 #ifdef __ARCH_WANT_SYS_CLONE3
 
-/*
- * copy_thread implementations handle CLONE_SETTLS by reading the TLS value from
- * the registers containing the syscall arguments for clone. This doesn't work
- * with clone3 since the TLS value is passed in clone_args instead.
- */
-#ifndef CONFIG_HAVE_COPY_THREAD_TLS
-#error clone3 requires copy_thread_tls support in arch
-#endif
-
 noinline static int copy_clone_args_from_user(struct kernel_clone_args *kargs,
 					      struct clone_args __user *uargs,
 					      size_t usize)
@@ -2605,6 +2556,14 @@ noinline static int copy_clone_args_from_user(struct kernel_clone_args *kargs,
 	struct clone_args args;
 	pid_t *kset_tid = kargs->set_tid;
 
+	BUILD_BUG_ON(offsetofend(struct clone_args, tls) !=
+		     CLONE_ARGS_SIZE_VER0);
+	BUILD_BUG_ON(offsetofend(struct clone_args, set_tid_size) !=
+		     CLONE_ARGS_SIZE_VER1);
+	BUILD_BUG_ON(offsetofend(struct clone_args, cgroup) !=
+		     CLONE_ARGS_SIZE_VER2);
+	BUILD_BUG_ON(sizeof(struct clone_args) != CLONE_ARGS_SIZE_VER2);
+
 	if (unlikely(usize > PAGE_SIZE))
 		return -E2BIG;
 	if (unlikely(usize < CLONE_ARGS_SIZE_VER0))
@@ -2631,6 +2590,10 @@ noinline static int copy_clone_args_from_user(struct kernel_clone_args *kargs,
 		     !valid_signal(args.exit_signal)))
 		return -EINVAL;
 
+	if ((args.flags & CLONE_INTO_CGROUP) &&
+	    (args.cgroup > INT_MAX || usize < CLONE_ARGS_SIZE_VER2))
+		return -EINVAL;
+
 	*kargs = (struct kernel_clone_args){
 		.flags		= args.flags,
 		.pidfd		= u64_to_user_ptr(args.pidfd),
@@ -2641,6 +2604,7 @@ noinline static int copy_clone_args_from_user(struct kernel_clone_args *kargs,
 		.stack_size	= args.stack_size,
 		.tls		= args.tls,
 		.set_tid_size	= args.set_tid_size,
+		.cgroup		= args.cgroup,
 	};
 
 	if (args.set_tid &&
@@ -2684,7 +2648,8 @@ static inline bool clone3_stack_valid(struct kernel_clone_args *kargs)
 static bool clone3_args_valid(struct kernel_clone_args *kargs)
 {
 	/* Verify that no unknown flags are passed along. */
-	if (kargs->flags & ~(CLONE_LEGACY_FLAGS | CLONE_CLEAR_SIGHAND))
+	if (kargs->flags &
+	    ~(CLONE_LEGACY_FLAGS | CLONE_CLEAR_SIGHAND | CLONE_INTO_CGROUP))
 		return false;
 
 	/*
@@ -2879,14 +2844,15 @@ static int unshare_fs(unsigned long unshare_flags, struct fs_struct **new_fsp)
 /*
  * Unshare file descriptor table if it is being shared
  */
-static int unshare_fd(unsigned long unshare_flags, struct files_struct **new_fdp)
+int unshare_fd(unsigned long unshare_flags, unsigned int max_fds,
+	       struct files_struct **new_fdp)
 {
 	struct files_struct *fd = current->files;
 	int error = 0;
 
 	if ((unshare_flags & CLONE_FILES) &&
 	    (fd && atomic_read(&fd->count) > 1)) {
-		*new_fdp = dup_fd(fd, &error);
+		*new_fdp = dup_fd(fd, max_fds, &error);
 		if (!*new_fdp)
 			return error;
 	}
@@ -2897,7 +2863,7 @@ static int unshare_fd(unsigned long unshare_flags, struct files_struct **new_fdp
 /*
  * unshare allows a process to 'unshare' part of the process
  * context which was originally shared using clone.  copy_*
- * functions used by do_fork() cannot be used here directly
+ * functions used by _do_fork() cannot be used here directly
  * because they modify an inactive task_struct that is being
  * constructed. Here we are modifying the current, active,
  * task_struct.
@@ -2946,7 +2912,7 @@ int ksys_unshare(unsigned long unshare_flags)
 	err = unshare_fs(unshare_flags, &new_fs);
 	if (err)
 		goto bad_unshare_out;
-	err = unshare_fd(unshare_flags, &new_fd);
+	err = unshare_fd(unshare_flags, NR_OPEN_MAX, &new_fd);
 	if (err)
 		goto bad_unshare_cleanup_fs;
 	err = unshare_userns(unshare_flags, &new_cred);
@@ -3035,7 +3001,7 @@ int unshare_files(struct files_struct **displaced)
 	struct files_struct *copy = NULL;
 	int error;
 
-	error = unshare_fd(CLONE_FILES, &copy);
+	error = unshare_fd(CLONE_FILES, NR_OPEN_MAX, &copy);
 	if (error || !copy) {
 		*displaced = NULL;
 		return error;
diff --git a/kernel/futex.c b/kernel/futex.c
index 82dfacb3250e..a5876694a60e 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -32,30 +32,13 @@
  *  "But they come in a choice of three flavours!"
  */
 #include <linux/compat.h>
-#include <linux/slab.h>
-#include <linux/poll.h>
-#include <linux/fs.h>
-#include <linux/file.h>
 #include <linux/jhash.h>
-#include <linux/init.h>
-#include <linux/futex.h>
-#include <linux/mount.h>
 #include <linux/pagemap.h>
 #include <linux/syscalls.h>
-#include <linux/signal.h>
-#include <linux/export.h>
-#include <linux/magic.h>
-#include <linux/pid.h>
-#include <linux/nsproxy.h>
-#include <linux/ptrace.h>
-#include <linux/sched/rt.h>
-#include <linux/sched/wake_q.h>
-#include <linux/sched/mm.h>
 #include <linux/hugetlb.h>
 #include <linux/freezer.h>
 #include <linux/memblock.h>
 #include <linux/fault-inject.h>
-#include <linux/refcount.h>
 
 #include <asm/futex.h>
 
@@ -135,8 +118,7 @@
  *
  * Where (A) orders the waiters increment and the futex value read through
  * atomic operations (see hb_waiters_inc) and where (B) orders the write
- * to futex and the waiters read -- this is done by the barriers for both
- * shared and private futexes in get_futex_key_refs().
+ * to futex and the waiters read (see hb_waiters_pending()).
  *
  * This yields the following case (where X:=waiters, Y:=futex):
  *
@@ -331,17 +313,6 @@ static void compat_exit_robust_list(struct task_struct *curr);
 static inline void compat_exit_robust_list(struct task_struct *curr) { }
 #endif
 
-static inline void futex_get_mm(union futex_key *key)
-{
-	mmgrab(key->private.mm);
-	/*
-	 * Ensure futex_get_mm() implies a full barrier such that
-	 * get_futex_key() implies a full barrier. This is relied upon
-	 * as smp_mb(); (B), see the ordering comment above.
-	 */
-	smp_mb__after_atomic();
-}
-
 /*
  * Reflects a new waiter being added to the waitqueue.
  */
@@ -370,6 +341,10 @@ static inline void hb_waiters_dec(struct futex_hash_bucket *hb)
 static inline int hb_waiters_pending(struct futex_hash_bucket *hb)
 {
 #ifdef CONFIG_SMP
+	/*
+	 * Full barrier (B), see the ordering comment above.
+	 */
+	smp_mb();
 	return atomic_read(&hb->waiters);
 #else
 	return 1;
@@ -407,69 +382,6 @@ static inline int match_futex(union futex_key *key1, union futex_key *key2)
 		&& key1->both.offset == key2->both.offset);
 }
 
-/*
- * Take a reference to the resource addressed by a key.
- * Can be called while holding spinlocks.
- *
- */
-static void get_futex_key_refs(union futex_key *key)
-{
-	if (!key->both.ptr)
-		return;
-
-	/*
-	 * On MMU less systems futexes are always "private" as there is no per
-	 * process address space. We need the smp wmb nevertheless - yes,
-	 * arch/blackfin has MMU less SMP ...
-	 */
-	if (!IS_ENABLED(CONFIG_MMU)) {
-		smp_mb(); /* explicit smp_mb(); (B) */
-		return;
-	}
-
-	switch (key->both.offset & (FUT_OFF_INODE|FUT_OFF_MMSHARED)) {
-	case FUT_OFF_INODE:
-		smp_mb();		/* explicit smp_mb(); (B) */
-		break;
-	case FUT_OFF_MMSHARED:
-		futex_get_mm(key); /* implies smp_mb(); (B) */
-		break;
-	default:
-		/*
-		 * Private futexes do not hold reference on an inode or
-		 * mm, therefore the only purpose of calling get_futex_key_refs
-		 * is because we need the barrier for the lockless waiter check.
-		 */
-		smp_mb(); /* explicit smp_mb(); (B) */
-	}
-}
-
-/*
- * Drop a reference to the resource addressed by a key.
- * The hash bucket spinlock must not be held. This is
- * a no-op for private futexes, see comment in the get
- * counterpart.
- */
-static void drop_futex_key_refs(union futex_key *key)
-{
-	if (!key->both.ptr) {
-		/* If we're here then we tried to put a key we failed to get */
-		WARN_ON_ONCE(1);
-		return;
-	}
-
-	if (!IS_ENABLED(CONFIG_MMU))
-		return;
-
-	switch (key->both.offset & (FUT_OFF_INODE|FUT_OFF_MMSHARED)) {
-	case FUT_OFF_INODE:
-		break;
-	case FUT_OFF_MMSHARED:
-		mmdrop(key->private.mm);
-		break;
-	}
-}
-
 enum futex_access {
 	FUTEX_READ,
 	FUTEX_WRITE
@@ -547,7 +459,7 @@ static u64 get_inode_sequence_number(struct inode *inode)
 /**
  * get_futex_key() - Get parameters which are the keys for a futex
  * @uaddr:	virtual address of the futex
- * @fshared:	0 for a PROCESS_PRIVATE futex, 1 for PROCESS_SHARED
+ * @fshared:	false for a PROCESS_PRIVATE futex, true for PROCESS_SHARED
  * @key:	address where result is stored.
  * @rw:		mapping needs to be read/write (values: FUTEX_READ,
  *              FUTEX_WRITE)
@@ -557,10 +469,13 @@ static u64 get_inode_sequence_number(struct inode *inode)
  * The key words are stored in @key on success.
  *
  * For shared mappings (when @fshared), the key is:
+ *
  *   ( inode->i_sequence, page->index, offset_within_page )
+ *
  * [ also see get_inode_sequence_number() ]
  *
  * For private mappings (or when !@fshared), the key is:
+ *
  *   ( current->mm, address, 0 )
  *
  * This allows (cross process, where applicable) identification of the futex
@@ -568,8 +483,8 @@ static u64 get_inode_sequence_number(struct inode *inode)
  *
  * lock_page() might sleep, the caller should not hold a spinlock.
  */
-static int
-get_futex_key(u32 __user *uaddr, int fshared, union futex_key *key, enum futex_access rw)
+static int get_futex_key(u32 __user *uaddr, bool fshared, union futex_key *key,
+			 enum futex_access rw)
 {
 	unsigned long address = (unsigned long)uaddr;
 	struct mm_struct *mm = current->mm;
@@ -601,13 +516,12 @@ get_futex_key(u32 __user *uaddr, int fshared, union futex_key *key, enum futex_a
 	if (!fshared) {
 		key->private.mm = mm;
 		key->private.address = address;
-		get_futex_key_refs(key);  /* implies smp_mb(); (B) */
 		return 0;
 	}
 
 again:
 	/* Ignore any VERIFY_READ mapping (futex common case) */
-	if (unlikely(should_fail_futex(fshared)))
+	if (unlikely(should_fail_futex(true)))
 		return -EFAULT;
 
 	err = get_user_pages_fast(address, 1, FOLL_WRITE, &page);
@@ -695,7 +609,7 @@ again:
 		 * A RO anonymous page will never change and thus doesn't make
 		 * sense for futex operations.
 		 */
-		if (unlikely(should_fail_futex(fshared)) || ro) {
+		if (unlikely(should_fail_futex(true)) || ro) {
 			err = -EFAULT;
 			goto out;
 		}
@@ -741,18 +655,11 @@ again:
 		rcu_read_unlock();
 	}
 
-	get_futex_key_refs(key); /* implies smp_mb(); (B) */
-
 out:
 	put_page(page);
 	return err;
 }
 
-static inline void put_futex_key(union futex_key *key)
-{
-	drop_futex_key_refs(key);
-}
-
 /**
  * fault_in_user_writeable() - Fault in user address and verify RW access
  * @uaddr:	pointer to faulting user space address
@@ -770,10 +677,10 @@ static int fault_in_user_writeable(u32 __user *uaddr)
 	struct mm_struct *mm = current->mm;
 	int ret;
 
-	down_read(&mm->mmap_sem);
-	ret = fixup_user_fault(current, mm, (unsigned long)uaddr,
+	mmap_read_lock(mm);
+	ret = fixup_user_fault(mm, (unsigned long)uaddr,
 			       FAULT_FLAG_WRITE, NULL);
-	up_read(&mm->mmap_sem);
+	mmap_read_unlock(mm);
 
 	return ret < 0 ? ret : 0;
 }
@@ -1398,7 +1305,7 @@ static int lookup_pi_state(u32 __user *uaddr, u32 uval,
 static int lock_pi_update_atomic(u32 __user *uaddr, u32 uval, u32 newval)
 {
 	int err;
-	u32 uninitialized_var(curval);
+	u32 curval;
 
 	if (unlikely(should_fail_futex(true)))
 		return -EFAULT;
@@ -1568,7 +1475,7 @@ static void mark_wake_futex(struct wake_q_head *wake_q, struct futex_q *q)
  */
 static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_pi_state *pi_state)
 {
-	u32 uninitialized_var(curval), newval;
+	u32 curval, newval;
 	struct task_struct *new_owner;
 	bool postunlock = false;
 	DEFINE_WAKE_Q(wake_q);
@@ -1683,13 +1590,13 @@ futex_wake(u32 __user *uaddr, unsigned int flags, int nr_wake, u32 bitset)
 
 	ret = get_futex_key(uaddr, flags & FLAGS_SHARED, &key, FUTEX_READ);
 	if (unlikely(ret != 0))
-		goto out;
+		return ret;
 
 	hb = hash_futex(&key);
 
 	/* Make sure we really have tasks to wakeup */
 	if (!hb_waiters_pending(hb))
-		goto out_put_key;
+		return ret;
 
 	spin_lock(&hb->lock);
 
@@ -1712,9 +1619,6 @@ futex_wake(u32 __user *uaddr, unsigned int flags, int nr_wake, u32 bitset)
 
 	spin_unlock(&hb->lock);
 	wake_up_q(&wake_q);
-out_put_key:
-	put_futex_key(&key);
-out:
 	return ret;
 }
 
@@ -1740,10 +1644,9 @@ static int futex_atomic_op_inuser(unsigned int encoded_op, u32 __user *uaddr)
 		oparg = 1 << oparg;
 	}
 
-	if (!access_ok(uaddr, sizeof(u32)))
-		return -EFAULT;
-
+	pagefault_disable();
 	ret = arch_futex_atomic_op_inuser(op, oparg, &oldval, uaddr);
+	pagefault_enable();
 	if (ret)
 		return ret;
 
@@ -1782,10 +1685,10 @@ futex_wake_op(u32 __user *uaddr1, unsigned int flags, u32 __user *uaddr2,
 retry:
 	ret = get_futex_key(uaddr1, flags & FLAGS_SHARED, &key1, FUTEX_READ);
 	if (unlikely(ret != 0))
-		goto out;
+		return ret;
 	ret = get_futex_key(uaddr2, flags & FLAGS_SHARED, &key2, FUTEX_WRITE);
 	if (unlikely(ret != 0))
-		goto out_put_key1;
+		return ret;
 
 	hb1 = hash_futex(&key1);
 	hb2 = hash_futex(&key2);
@@ -1803,13 +1706,13 @@ retry_private:
 			 * an MMU, but we might get them from range checking
 			 */
 			ret = op_ret;
-			goto out_put_keys;
+			return ret;
 		}
 
 		if (op_ret == -EFAULT) {
 			ret = fault_in_user_writeable(uaddr2);
 			if (ret)
-				goto out_put_keys;
+				return ret;
 		}
 
 		if (!(flags & FLAGS_SHARED)) {
@@ -1817,8 +1720,6 @@ retry_private:
 			goto retry_private;
 		}
 
-		put_futex_key(&key2);
-		put_futex_key(&key1);
 		cond_resched();
 		goto retry;
 	}
@@ -1854,11 +1755,6 @@ retry_private:
 out_unlock:
 	double_unlock_hb(hb1, hb2);
 	wake_up_q(&wake_q);
-out_put_keys:
-	put_futex_key(&key2);
-out_put_key1:
-	put_futex_key(&key1);
-out:
 	return ret;
 }
 
@@ -1885,7 +1781,6 @@ void requeue_futex(struct futex_q *q, struct futex_hash_bucket *hb1,
 		plist_add(&q->list, &hb2->chain);
 		q->lock_ptr = &hb2->lock;
 	}
-	get_futex_key_refs(key2);
 	q->key = *key2;
 }
 
@@ -1907,7 +1802,6 @@ static inline
 void requeue_pi_wake_futex(struct futex_q *q, union futex_key *key,
 			   struct futex_hash_bucket *hb)
 {
-	get_futex_key_refs(key);
 	q->key = *key;
 
 	__unqueue_futex(q);
@@ -2018,7 +1912,7 @@ static int futex_requeue(u32 __user *uaddr1, unsigned int flags,
 			 u32 *cmpval, int requeue_pi)
 {
 	union futex_key key1 = FUTEX_KEY_INIT, key2 = FUTEX_KEY_INIT;
-	int drop_count = 0, task_count = 0, ret;
+	int task_count = 0, ret;
 	struct futex_pi_state *pi_state = NULL;
 	struct futex_hash_bucket *hb1, *hb2;
 	struct futex_q *this, *next;
@@ -2067,20 +1961,18 @@ static int futex_requeue(u32 __user *uaddr1, unsigned int flags,
 retry:
 	ret = get_futex_key(uaddr1, flags & FLAGS_SHARED, &key1, FUTEX_READ);
 	if (unlikely(ret != 0))
-		goto out;
+		return ret;
 	ret = get_futex_key(uaddr2, flags & FLAGS_SHARED, &key2,
 			    requeue_pi ? FUTEX_WRITE : FUTEX_READ);
 	if (unlikely(ret != 0))
-		goto out_put_key1;
+		return ret;
 
 	/*
 	 * The check above which compares uaddrs is not sufficient for
 	 * shared futexes. We need to compare the keys:
 	 */
-	if (requeue_pi && match_futex(&key1, &key2)) {
-		ret = -EINVAL;
-		goto out_put_keys;
-	}
+	if (requeue_pi && match_futex(&key1, &key2))
+		return -EINVAL;
 
 	hb1 = hash_futex(&key1);
 	hb2 = hash_futex(&key2);
@@ -2100,13 +1992,11 @@ retry_private:
 
 			ret = get_user(curval, uaddr1);
 			if (ret)
-				goto out_put_keys;
+				return ret;
 
 			if (!(flags & FLAGS_SHARED))
 				goto retry_private;
 
-			put_futex_key(&key2);
-			put_futex_key(&key1);
 			goto retry;
 		}
 		if (curval != *cmpval) {
@@ -2139,7 +2029,6 @@ retry_private:
 		 */
 		if (ret > 0) {
 			WARN_ON(pi_state);
-			drop_count++;
 			task_count++;
 			/*
 			 * If we acquired the lock, then the user space value
@@ -2166,12 +2055,10 @@ retry_private:
 		case -EFAULT:
 			double_unlock_hb(hb1, hb2);
 			hb_waiters_dec(hb2);
-			put_futex_key(&key2);
-			put_futex_key(&key1);
 			ret = fault_in_user_writeable(uaddr2);
 			if (!ret)
 				goto retry;
-			goto out;
+			return ret;
 		case -EBUSY:
 		case -EAGAIN:
 			/*
@@ -2182,8 +2069,6 @@ retry_private:
 			 */
 			double_unlock_hb(hb1, hb2);
 			hb_waiters_dec(hb2);
-			put_futex_key(&key2);
-			put_futex_key(&key1);
 			/*
 			 * Handle the case where the owner is in the middle of
 			 * exiting. Wait for the exit to complete otherwise
@@ -2259,7 +2144,6 @@ retry_private:
 				 * doing so.
 				 */
 				requeue_pi_wake_futex(this, &key2, hb2);
-				drop_count++;
 				continue;
 			} else if (ret) {
 				/*
@@ -2280,7 +2164,6 @@ retry_private:
 			}
 		}
 		requeue_futex(this, hb1, hb2, &key2);
-		drop_count++;
 	}
 
 	/*
@@ -2294,21 +2177,6 @@ out_unlock:
 	double_unlock_hb(hb1, hb2);
 	wake_up_q(&wake_q);
 	hb_waiters_dec(hb2);
-
-	/*
-	 * drop_futex_key_refs() must be called outside the spinlocks. During
-	 * the requeue we moved futex_q's from the hash bucket at key1 to the
-	 * one at key2 and updated their key pointer.  We no longer need to
-	 * hold the references to key1.
-	 */
-	while (--drop_count >= 0)
-		drop_futex_key_refs(&key1);
-
-out_put_keys:
-	put_futex_key(&key2);
-out_put_key1:
-	put_futex_key(&key1);
-out:
 	return ret ? ret : task_count;
 }
 
@@ -2433,7 +2301,6 @@ retry:
 		ret = 1;
 	}
 
-	drop_futex_key_refs(&q->key);
 	return ret;
 }
 
@@ -2458,7 +2325,7 @@ static int fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q,
 				struct task_struct *argowner)
 {
 	struct futex_pi_state *pi_state = q->pi_state;
-	u32 uval, uninitialized_var(curval), newval;
+	u32 uval, curval, newval;
 	struct task_struct *oldowner, *newowner;
 	u32 newtid;
 	int ret, err = 0;
@@ -2655,7 +2522,7 @@ static int fixup_owner(u32 __user *uaddr, struct futex_q *q, int locked)
 		 */
 		if (q->pi_state->owner != current)
 			ret = fixup_pi_state_owner(uaddr, q, current);
-		goto out;
+		return ret ? ret : locked;
 	}
 
 	/*
@@ -2668,7 +2535,7 @@ static int fixup_owner(u32 __user *uaddr, struct futex_q *q, int locked)
 	 */
 	if (q->pi_state->owner == current) {
 		ret = fixup_pi_state_owner(uaddr, q, NULL);
-		goto out;
+		return ret;
 	}
 
 	/*
@@ -2682,8 +2549,7 @@ static int fixup_owner(u32 __user *uaddr, struct futex_q *q, int locked)
 				q->pi_state->owner);
 	}
 
-out:
-	return ret ? ret : locked;
+	return ret;
 }
 
 /**
@@ -2780,12 +2646,11 @@ retry_private:
 
 		ret = get_user(uval, uaddr);
 		if (ret)
-			goto out;
+			return ret;
 
 		if (!(flags & FLAGS_SHARED))
 			goto retry_private;
 
-		put_futex_key(&q->key);
 		goto retry;
 	}
 
@@ -2794,9 +2659,6 @@ retry_private:
 		ret = -EWOULDBLOCK;
 	}
 
-out:
-	if (ret)
-		put_futex_key(&q->key);
 	return ret;
 }
 
@@ -2941,7 +2803,6 @@ retry_private:
 			 * - EAGAIN: The user space value changed.
 			 */
 			queue_unlock(hb);
-			put_futex_key(&q.key);
 			/*
 			 * Handle the case where the owner is in the middle of
 			 * exiting. Wait for the exit to complete otherwise
@@ -3049,13 +2910,11 @@ no_block:
 		put_pi_state(pi_state);
 	}
 
-	goto out_put_key;
+	goto out;
 
 out_unlock_put_key:
 	queue_unlock(hb);
 
-out_put_key:
-	put_futex_key(&q.key);
 out:
 	if (to) {
 		hrtimer_cancel(&to->timer);
@@ -3068,12 +2927,11 @@ uaddr_faulted:
 
 	ret = fault_in_user_writeable(uaddr);
 	if (ret)
-		goto out_put_key;
+		goto out;
 
 	if (!(flags & FLAGS_SHARED))
 		goto retry_private;
 
-	put_futex_key(&q.key);
 	goto retry;
 }
 
@@ -3084,7 +2942,7 @@ uaddr_faulted:
  */
 static int futex_unlock_pi(u32 __user *uaddr, unsigned int flags)
 {
-	u32 uninitialized_var(curval), uval, vpid = task_pid_vnr(current);
+	u32 curval, uval, vpid = task_pid_vnr(current);
 	union futex_key key = FUTEX_KEY_INIT;
 	struct futex_hash_bucket *hb;
 	struct futex_q *top_waiter;
@@ -3202,16 +3060,13 @@ retry:
 out_unlock:
 	spin_unlock(&hb->lock);
 out_putkey:
-	put_futex_key(&key);
 	return ret;
 
 pi_retry:
-	put_futex_key(&key);
 	cond_resched();
 	goto retry;
 
 pi_faulted:
-	put_futex_key(&key);
 
 	ret = fault_in_user_writeable(uaddr);
 	if (!ret)
@@ -3353,7 +3208,7 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
 	 */
 	ret = futex_wait_setup(uaddr, val, flags, &q, &hb);
 	if (ret)
-		goto out_key2;
+		goto out;
 
 	/*
 	 * The check above which compares uaddrs is not sufficient for
@@ -3362,7 +3217,7 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
 	if (match_futex(&q.key, &key2)) {
 		queue_unlock(hb);
 		ret = -EINVAL;
-		goto out_put_keys;
+		goto out;
 	}
 
 	/* Queue the futex_q, drop the hb lock, wait for wakeup. */
@@ -3372,7 +3227,7 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
 	ret = handle_early_requeue_pi_wakeup(hb, &q, &key2, to);
 	spin_unlock(&hb->lock);
 	if (ret)
-		goto out_put_keys;
+		goto out;
 
 	/*
 	 * In order for us to be here, we know our q.key == key2, and since
@@ -3462,11 +3317,6 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
 		ret = -EWOULDBLOCK;
 	}
 
-out_put_keys:
-	put_futex_key(&q.key);
-out_key2:
-	put_futex_key(&key2);
-
 out:
 	if (to) {
 		hrtimer_cancel(&to->timer);
@@ -3567,7 +3417,7 @@ err_unlock:
 static int handle_futex_death(u32 __user *uaddr, struct task_struct *curr,
 			      bool pi, bool pending_op)
 {
-	u32 uval, uninitialized_var(nval), mval;
+	u32 uval, nval, mval;
 	int err;
 
 	/* Futex address must be 32bit aligned */
@@ -3697,7 +3547,7 @@ static void exit_robust_list(struct task_struct *curr)
 	struct robust_list_head __user *head = curr->robust_list;
 	struct robust_list __user *entry, *next_entry, *pending;
 	unsigned int limit = ROBUST_LIST_LIMIT, pi, pip;
-	unsigned int uninitialized_var(next_pi);
+	unsigned int next_pi;
 	unsigned long futex_offset;
 	int rc;
 
@@ -3894,12 +3744,12 @@ long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout,
 	switch (cmd) {
 	case FUTEX_WAIT:
 		val3 = FUTEX_BITSET_MATCH_ANY;
-		/* fall through */
+		fallthrough;
 	case FUTEX_WAIT_BITSET:
 		return futex_wait(uaddr, flags, val, timeout, val3);
 	case FUTEX_WAKE:
 		val3 = FUTEX_BITSET_MATCH_ANY;
-		/* fall through */
+		fallthrough;
 	case FUTEX_WAKE_BITSET:
 		return futex_wake(uaddr, flags, val, val3);
 	case FUTEX_REQUEUE:
@@ -3997,7 +3847,7 @@ static void compat_exit_robust_list(struct task_struct *curr)
 	struct compat_robust_list_head __user *head = curr->compat_robust_list;
 	struct robust_list __user *entry, *next_entry, *pending;
 	unsigned int limit = ROBUST_LIST_LIMIT, pi, pip;
-	unsigned int uninitialized_var(next_pi);
+	unsigned int next_pi;
 	compat_uptr_t uentry, next_uentry, upending;
 	compat_long_t futex_offset;
 	int rc;
diff --git a/kernel/gcov/Kconfig b/kernel/gcov/Kconfig
index 3941a9c48f83..3110c77230c7 100644
--- a/kernel/gcov/Kconfig
+++ b/kernel/gcov/Kconfig
@@ -6,7 +6,7 @@ config GCOV_KERNEL
 	depends on DEBUG_FS
 	select CONSTRUCTORS if !UML
 	default n
-	---help---
+	help
 	This option enables gcov-based code profiling (e.g. for code coverage
 	measurements).
 
@@ -42,7 +42,7 @@ config GCOV_PROFILE_ALL
 	depends on GCOV_KERNEL
 	depends on ARCH_HAS_GCOV_PROFILE_ALL
 	default n
-	---help---
+	help
 	This options activates profiling for the entire kernel.
 
 	If unsure, say N.
@@ -51,28 +51,4 @@ config GCOV_PROFILE_ALL
 	larger and run slower. Also be sure to exclude files from profiling
 	which are not linked to the kernel image to prevent linker errors.
 
-choice
-	prompt "Specify GCOV format"
-	depends on GCOV_KERNEL
-	depends on CC_IS_GCC
-	---help---
-	The gcov format is usually determined by the GCC version, and the
-	default is chosen according to your GCC version. However, there are
-	exceptions where format changes are integrated in lower-version GCCs.
-	In such a case, change this option to adjust the format used in the
-	kernel accordingly.
-
-config GCOV_FORMAT_3_4
-	bool "GCC 3.4 format"
-	depends on GCC_VERSION < 40700
-	---help---
-	Select this option to use the format defined by GCC 3.4.
-
-config GCOV_FORMAT_4_7
-	bool "GCC 4.7 format"
-	---help---
-	Select this option to use the format defined by GCC 4.7.
-
-endchoice
-
 endmenu
diff --git a/kernel/gcov/Makefile b/kernel/gcov/Makefile
index d66a74b0f100..16f8ecc7d882 100644
--- a/kernel/gcov/Makefile
+++ b/kernel/gcov/Makefile
@@ -2,6 +2,5 @@
 ccflags-y := -DSRCTREE='"$(srctree)"' -DOBJTREE='"$(objtree)"'
 
 obj-y := base.o fs.o
-obj-$(CONFIG_GCOV_FORMAT_3_4) += gcc_base.o gcc_3_4.o
-obj-$(CONFIG_GCOV_FORMAT_4_7) += gcc_base.o gcc_4_7.o
+obj-$(CONFIG_CC_IS_GCC) += gcc_base.o gcc_4_7.o
 obj-$(CONFIG_CC_IS_CLANG) += clang.o
diff --git a/kernel/gcov/fs.c b/kernel/gcov/fs.c
index e5eb5ea7ea59..82babf5aa077 100644
--- a/kernel/gcov/fs.c
+++ b/kernel/gcov/fs.c
@@ -58,7 +58,7 @@ struct gcov_node {
 	struct dentry *dentry;
 	struct dentry **links;
 	int num_loaded;
-	char name[0];
+	char name[];
 };
 
 static const char objtree[] = OBJTREE;
@@ -108,9 +108,9 @@ static void *gcov_seq_next(struct seq_file *seq, void *data, loff_t *pos)
 {
 	struct gcov_iterator *iter = data;
 
+	(*pos)++;
 	if (gcov_iter_next(iter))
 		return NULL;
-	(*pos)++;
 
 	return iter;
 }
diff --git a/kernel/gcov/gcc_3_4.c b/kernel/gcov/gcc_3_4.c
deleted file mode 100644
index 801ee4b0b969..000000000000
--- a/kernel/gcov/gcc_3_4.c
+++ /dev/null
@@ -1,573 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- *  This code provides functions to handle gcc's profiling data format
- *  introduced with gcc 3.4. Future versions of gcc may change the gcov
- *  format (as happened before), so all format-specific information needs
- *  to be kept modular and easily exchangeable.
- *
- *  This file is based on gcc-internal definitions. Functions and data
- *  structures are defined to be compatible with gcc counterparts.
- *  For a better understanding, refer to gcc source: gcc/gcov-io.h.
- *
- *    Copyright IBM Corp. 2009
- *    Author(s): Peter Oberparleiter <oberpar@linux.vnet.ibm.com>
- *
- *    Uses gcc-internal data definitions.
- */
-
-#include <linux/errno.h>
-#include <linux/slab.h>
-#include <linux/string.h>
-#include <linux/seq_file.h>
-#include <linux/vmalloc.h>
-#include "gcov.h"
-
-#define GCOV_COUNTERS		5
-
-static struct gcov_info *gcov_info_head;
-
-/**
- * struct gcov_fn_info - profiling meta data per function
- * @ident: object file-unique function identifier
- * @checksum: function checksum
- * @n_ctrs: number of values per counter type belonging to this function
- *
- * This data is generated by gcc during compilation and doesn't change
- * at run-time.
- */
-struct gcov_fn_info {
-	unsigned int ident;
-	unsigned int checksum;
-	unsigned int n_ctrs[0];
-};
-
-/**
- * struct gcov_ctr_info - profiling data per counter type
- * @num: number of counter values for this type
- * @values: array of counter values for this type
- * @merge: merge function for counter values of this type (unused)
- *
- * This data is generated by gcc during compilation and doesn't change
- * at run-time with the exception of the values array.
- */
-struct gcov_ctr_info {
-	unsigned int	num;
-	gcov_type	*values;
-	void		(*merge)(gcov_type *, unsigned int);
-};
-
-/**
- * struct gcov_info - profiling data per object file
- * @version: gcov version magic indicating the gcc version used for compilation
- * @next: list head for a singly-linked list
- * @stamp: time stamp
- * @filename: name of the associated gcov data file
- * @n_functions: number of instrumented functions
- * @functions: function data
- * @ctr_mask: mask specifying which counter types are active
- * @counts: counter data per counter type
- *
- * This data is generated by gcc during compilation and doesn't change
- * at run-time with the exception of the next pointer.
- */
-struct gcov_info {
-	unsigned int			version;
-	struct gcov_info		*next;
-	unsigned int			stamp;
-	const char			*filename;
-	unsigned int			n_functions;
-	const struct gcov_fn_info	*functions;
-	unsigned int			ctr_mask;
-	struct gcov_ctr_info		counts[0];
-};
-
-/**
- * gcov_info_filename - return info filename
- * @info: profiling data set
- */
-const char *gcov_info_filename(struct gcov_info *info)
-{
-	return info->filename;
-}
-
-/**
- * gcov_info_version - return info version
- * @info: profiling data set
- */
-unsigned int gcov_info_version(struct gcov_info *info)
-{
-	return info->version;
-}
-
-/**
- * gcov_info_next - return next profiling data set
- * @info: profiling data set
- *
- * Returns next gcov_info following @info or first gcov_info in the chain if
- * @info is %NULL.
- */
-struct gcov_info *gcov_info_next(struct gcov_info *info)
-{
-	if (!info)
-		return gcov_info_head;
-
-	return info->next;
-}
-
-/**
- * gcov_info_link - link/add profiling data set to the list
- * @info: profiling data set
- */
-void gcov_info_link(struct gcov_info *info)
-{
-	info->next = gcov_info_head;
-	gcov_info_head = info;
-}
-
-/**
- * gcov_info_unlink - unlink/remove profiling data set from the list
- * @prev: previous profiling data set
- * @info: profiling data set
- */
-void gcov_info_unlink(struct gcov_info *prev, struct gcov_info *info)
-{
-	if (prev)
-		prev->next = info->next;
-	else
-		gcov_info_head = info->next;
-}
-
-/**
- * gcov_info_within_module - check if a profiling data set belongs to a module
- * @info: profiling data set
- * @mod: module
- *
- * Returns true if profiling data belongs module, false otherwise.
- */
-bool gcov_info_within_module(struct gcov_info *info, struct module *mod)
-{
-	return within_module((unsigned long)info, mod);
-}
-
-/* Symbolic links to be created for each profiling data file. */
-const struct gcov_link gcov_link[] = {
-	{ OBJ_TREE, "gcno" },	/* Link to .gcno file in $(objtree). */
-	{ 0, NULL},
-};
-
-/*
- * Determine whether a counter is active. Based on gcc magic. Doesn't change
- * at run-time.
- */
-static int counter_active(struct gcov_info *info, unsigned int type)
-{
-	return (1 << type) & info->ctr_mask;
-}
-
-/* Determine number of active counters. Based on gcc magic. */
-static unsigned int num_counter_active(struct gcov_info *info)
-{
-	unsigned int i;
-	unsigned int result = 0;
-
-	for (i = 0; i < GCOV_COUNTERS; i++) {
-		if (counter_active(info, i))
-			result++;
-	}
-	return result;
-}
-
-/**
- * gcov_info_reset - reset profiling data to zero
- * @info: profiling data set
- */
-void gcov_info_reset(struct gcov_info *info)
-{
-	unsigned int active = num_counter_active(info);
-	unsigned int i;
-
-	for (i = 0; i < active; i++) {
-		memset(info->counts[i].values, 0,
-		       info->counts[i].num * sizeof(gcov_type));
-	}
-}
-
-/**
- * gcov_info_is_compatible - check if profiling data can be added
- * @info1: first profiling data set
- * @info2: second profiling data set
- *
- * Returns non-zero if profiling data can be added, zero otherwise.
- */
-int gcov_info_is_compatible(struct gcov_info *info1, struct gcov_info *info2)
-{
-	return (info1->stamp == info2->stamp);
-}
-
-/**
- * gcov_info_add - add up profiling data
- * @dest: profiling data set to which data is added
- * @source: profiling data set which is added
- *
- * Adds profiling counts of @source to @dest.
- */
-void gcov_info_add(struct gcov_info *dest, struct gcov_info *source)
-{
-	unsigned int i;
-	unsigned int j;
-
-	for (i = 0; i < num_counter_active(dest); i++) {
-		for (j = 0; j < dest->counts[i].num; j++) {
-			dest->counts[i].values[j] +=
-				source->counts[i].values[j];
-		}
-	}
-}
-
-/* Get size of function info entry. Based on gcc magic. */
-static size_t get_fn_size(struct gcov_info *info)
-{
-	size_t size;
-
-	size = sizeof(struct gcov_fn_info) + num_counter_active(info) *
-	       sizeof(unsigned int);
-	if (__alignof__(struct gcov_fn_info) > sizeof(unsigned int))
-		size = ALIGN(size, __alignof__(struct gcov_fn_info));
-	return size;
-}
-
-/* Get address of function info entry. Based on gcc magic. */
-static struct gcov_fn_info *get_fn_info(struct gcov_info *info, unsigned int fn)
-{
-	return (struct gcov_fn_info *)
-		((char *) info->functions + fn * get_fn_size(info));
-}
-
-/**
- * gcov_info_dup - duplicate profiling data set
- * @info: profiling data set to duplicate
- *
- * Return newly allocated duplicate on success, %NULL on error.
- */
-struct gcov_info *gcov_info_dup(struct gcov_info *info)
-{
-	struct gcov_info *dup;
-	unsigned int i;
-	unsigned int active;
-
-	/* Duplicate gcov_info. */
-	active = num_counter_active(info);
-	dup = kzalloc(struct_size(dup, counts, active), GFP_KERNEL);
-	if (!dup)
-		return NULL;
-	dup->version		= info->version;
-	dup->stamp		= info->stamp;
-	dup->n_functions	= info->n_functions;
-	dup->ctr_mask		= info->ctr_mask;
-	/* Duplicate filename. */
-	dup->filename		= kstrdup(info->filename, GFP_KERNEL);
-	if (!dup->filename)
-		goto err_free;
-	/* Duplicate table of functions. */
-	dup->functions = kmemdup(info->functions, info->n_functions *
-				 get_fn_size(info), GFP_KERNEL);
-	if (!dup->functions)
-		goto err_free;
-	/* Duplicate counter arrays. */
-	for (i = 0; i < active ; i++) {
-		struct gcov_ctr_info *ctr = &info->counts[i];
-		size_t size = ctr->num * sizeof(gcov_type);
-
-		dup->counts[i].num = ctr->num;
-		dup->counts[i].merge = ctr->merge;
-		dup->counts[i].values = vmalloc(size);
-		if (!dup->counts[i].values)
-			goto err_free;
-		memcpy(dup->counts[i].values, ctr->values, size);
-	}
-	return dup;
-
-err_free:
-	gcov_info_free(dup);
-	return NULL;
-}
-
-/**
- * gcov_info_free - release memory for profiling data set duplicate
- * @info: profiling data set duplicate to free
- */
-void gcov_info_free(struct gcov_info *info)
-{
-	unsigned int active = num_counter_active(info);
-	unsigned int i;
-
-	for (i = 0; i < active ; i++)
-		vfree(info->counts[i].values);
-	kfree(info->functions);
-	kfree(info->filename);
-	kfree(info);
-}
-
-/**
- * struct type_info - iterator helper array
- * @ctr_type: counter type
- * @offset: index of the first value of the current function for this type
- *
- * This array is needed to convert the in-memory data format into the in-file
- * data format:
- *
- * In-memory:
- *   for each counter type
- *     for each function
- *       values
- *
- * In-file:
- *   for each function
- *     for each counter type
- *       values
- *
- * See gcc source gcc/gcov-io.h for more information on data organization.
- */
-struct type_info {
-	int ctr_type;
-	unsigned int offset;
-};
-
-/**
- * struct gcov_iterator - specifies current file position in logical records
- * @info: associated profiling data
- * @record: record type
- * @function: function number
- * @type: counter type
- * @count: index into values array
- * @num_types: number of counter types
- * @type_info: helper array to get values-array offset for current function
- */
-struct gcov_iterator {
-	struct gcov_info *info;
-
-	int record;
-	unsigned int function;
-	unsigned int type;
-	unsigned int count;
-
-	int num_types;
-	struct type_info type_info[0];
-};
-
-static struct gcov_fn_info *get_func(struct gcov_iterator *iter)
-{
-	return get_fn_info(iter->info, iter->function);
-}
-
-static struct type_info *get_type(struct gcov_iterator *iter)
-{
-	return &iter->type_info[iter->type];
-}
-
-/**
- * gcov_iter_new - allocate and initialize profiling data iterator
- * @info: profiling data set to be iterated
- *
- * Return file iterator on success, %NULL otherwise.
- */
-struct gcov_iterator *gcov_iter_new(struct gcov_info *info)
-{
-	struct gcov_iterator *iter;
-
-	iter = kzalloc(struct_size(iter, type_info, num_counter_active(info)),
-		       GFP_KERNEL);
-	if (iter)
-		iter->info = info;
-
-	return iter;
-}
-
-/**
- * gcov_iter_free - release memory for iterator
- * @iter: file iterator to free
- */
-void gcov_iter_free(struct gcov_iterator *iter)
-{
-	kfree(iter);
-}
-
-/**
- * gcov_iter_get_info - return profiling data set for given file iterator
- * @iter: file iterator
- */
-struct gcov_info *gcov_iter_get_info(struct gcov_iterator *iter)
-{
-	return iter->info;
-}
-
-/**
- * gcov_iter_start - reset file iterator to starting position
- * @iter: file iterator
- */
-void gcov_iter_start(struct gcov_iterator *iter)
-{
-	int i;
-
-	iter->record = 0;
-	iter->function = 0;
-	iter->type = 0;
-	iter->count = 0;
-	iter->num_types = 0;
-	for (i = 0; i < GCOV_COUNTERS; i++) {
-		if (counter_active(iter->info, i)) {
-			iter->type_info[iter->num_types].ctr_type = i;
-			iter->type_info[iter->num_types++].offset = 0;
-		}
-	}
-}
-
-/* Mapping of logical record number to actual file content. */
-#define RECORD_FILE_MAGIC	0
-#define RECORD_GCOV_VERSION	1
-#define RECORD_TIME_STAMP	2
-#define RECORD_FUNCTION_TAG	3
-#define RECORD_FUNCTON_TAG_LEN	4
-#define RECORD_FUNCTION_IDENT	5
-#define RECORD_FUNCTION_CHECK	6
-#define RECORD_COUNT_TAG	7
-#define RECORD_COUNT_LEN	8
-#define RECORD_COUNT		9
-
-/**
- * gcov_iter_next - advance file iterator to next logical record
- * @iter: file iterator
- *
- * Return zero if new position is valid, non-zero if iterator has reached end.
- */
-int gcov_iter_next(struct gcov_iterator *iter)
-{
-	switch (iter->record) {
-	case RECORD_FILE_MAGIC:
-	case RECORD_GCOV_VERSION:
-	case RECORD_FUNCTION_TAG:
-	case RECORD_FUNCTON_TAG_LEN:
-	case RECORD_FUNCTION_IDENT:
-	case RECORD_COUNT_TAG:
-		/* Advance to next record */
-		iter->record++;
-		break;
-	case RECORD_COUNT:
-		/* Advance to next count */
-		iter->count++;
-		/* fall through */
-	case RECORD_COUNT_LEN:
-		if (iter->count < get_func(iter)->n_ctrs[iter->type]) {
-			iter->record = 9;
-			break;
-		}
-		/* Advance to next counter type */
-		get_type(iter)->offset += iter->count;
-		iter->count = 0;
-		iter->type++;
-		/* fall through */
-	case RECORD_FUNCTION_CHECK:
-		if (iter->type < iter->num_types) {
-			iter->record = 7;
-			break;
-		}
-		/* Advance to next function */
-		iter->type = 0;
-		iter->function++;
-		/* fall through */
-	case RECORD_TIME_STAMP:
-		if (iter->function < iter->info->n_functions)
-			iter->record = 3;
-		else
-			iter->record = -1;
-		break;
-	}
-	/* Check for EOF. */
-	if (iter->record == -1)
-		return -EINVAL;
-	else
-		return 0;
-}
-
-/**
- * seq_write_gcov_u32 - write 32 bit number in gcov format to seq_file
- * @seq: seq_file handle
- * @v: value to be stored
- *
- * Number format defined by gcc: numbers are recorded in the 32 bit
- * unsigned binary form of the endianness of the machine generating the
- * file.
- */
-static int seq_write_gcov_u32(struct seq_file *seq, u32 v)
-{
-	return seq_write(seq, &v, sizeof(v));
-}
-
-/**
- * seq_write_gcov_u64 - write 64 bit number in gcov format to seq_file
- * @seq: seq_file handle
- * @v: value to be stored
- *
- * Number format defined by gcc: numbers are recorded in the 32 bit
- * unsigned binary form of the endianness of the machine generating the
- * file. 64 bit numbers are stored as two 32 bit numbers, the low part
- * first.
- */
-static int seq_write_gcov_u64(struct seq_file *seq, u64 v)
-{
-	u32 data[2];
-
-	data[0] = (v & 0xffffffffUL);
-	data[1] = (v >> 32);
-	return seq_write(seq, data, sizeof(data));
-}
-
-/**
- * gcov_iter_write - write data for current pos to seq_file
- * @iter: file iterator
- * @seq: seq_file handle
- *
- * Return zero on success, non-zero otherwise.
- */
-int gcov_iter_write(struct gcov_iterator *iter, struct seq_file *seq)
-{
-	int rc = -EINVAL;
-
-	switch (iter->record) {
-	case RECORD_FILE_MAGIC:
-		rc = seq_write_gcov_u32(seq, GCOV_DATA_MAGIC);
-		break;
-	case RECORD_GCOV_VERSION:
-		rc = seq_write_gcov_u32(seq, iter->info->version);
-		break;
-	case RECORD_TIME_STAMP:
-		rc = seq_write_gcov_u32(seq, iter->info->stamp);
-		break;
-	case RECORD_FUNCTION_TAG:
-		rc = seq_write_gcov_u32(seq, GCOV_TAG_FUNCTION);
-		break;
-	case RECORD_FUNCTON_TAG_LEN:
-		rc = seq_write_gcov_u32(seq, 2);
-		break;
-	case RECORD_FUNCTION_IDENT:
-		rc = seq_write_gcov_u32(seq, get_func(iter)->ident);
-		break;
-	case RECORD_FUNCTION_CHECK:
-		rc = seq_write_gcov_u32(seq, get_func(iter)->checksum);
-		break;
-	case RECORD_COUNT_TAG:
-		rc = seq_write_gcov_u32(seq,
-			GCOV_TAG_FOR_COUNTER(get_type(iter)->ctr_type));
-		break;
-	case RECORD_COUNT_LEN:
-		rc = seq_write_gcov_u32(seq,
-				get_func(iter)->n_ctrs[iter->type] * 2);
-		break;
-	case RECORD_COUNT:
-		rc = seq_write_gcov_u64(seq,
-			iter->info->counts[iter->type].
-				values[iter->count + get_type(iter)->offset]);
-		break;
-	}
-	return rc;
-}
diff --git a/kernel/gcov/gcc_4_7.c b/kernel/gcov/gcc_4_7.c
index ec37563674d6..908fdf5098c3 100644
--- a/kernel/gcov/gcc_4_7.c
+++ b/kernel/gcov/gcc_4_7.c
@@ -68,7 +68,7 @@ struct gcov_fn_info {
 	unsigned int ident;
 	unsigned int lineno_checksum;
 	unsigned int cfg_checksum;
-	struct gcov_ctr_info ctrs[0];
+	struct gcov_ctr_info ctrs[];
 };
 
 /**
diff --git a/kernel/gen_kheaders.sh b/kernel/gen_kheaders.sh
index e13ca842eb7e..c1510f0ab3ea 100755
--- a/kernel/gen_kheaders.sh
+++ b/kernel/gen_kheaders.sh
@@ -88,7 +88,7 @@ find $cpio_dir -type f -print0 |
 find $cpio_dir -printf "./%P\n" | LC_ALL=C sort | \
     tar "${KBUILD_BUILD_TIMESTAMP:+--mtime=$KBUILD_BUILD_TIMESTAMP}" \
     --owner=0 --group=0 --numeric-owner --no-recursion \
-    -Jcf $tarfile -C $cpio_dir/ -T - > /dev/null
+    -I $XZ -cf $tarfile -C $cpio_dir/ -T - > /dev/null
 
 echo $headers_md5 > kernel/kheaders.md5
 echo "$this_file_md5" >> kernel/kheaders.md5
diff --git a/kernel/groups.c b/kernel/groups.c
index daae2f2dc6d4..6ee6691f6839 100644
--- a/kernel/groups.c
+++ b/kernel/groups.c
@@ -20,7 +20,7 @@ struct group_info *groups_alloc(int gidsetsize)
 	len = sizeof(struct group_info) + sizeof(kgid_t) * gidsetsize;
 	gi = kmalloc(len, GFP_KERNEL_ACCOUNT|__GFP_NOWARN|__GFP_NORETRY);
 	if (!gi)
-		gi = __vmalloc(len, GFP_KERNEL_ACCOUNT, PAGE_KERNEL);
+		gi = __vmalloc(len, GFP_KERNEL_ACCOUNT);
 	if (!gi)
 		return NULL;
 
diff --git a/kernel/hung_task.c b/kernel/hung_task.c
index 14a625c16cb3..ce76f490126c 100644
--- a/kernel/hung_task.c
+++ b/kernel/hung_task.c
@@ -53,9 +53,18 @@ int __read_mostly sysctl_hung_task_warnings = 10;
 static int __read_mostly did_panic;
 static bool hung_task_show_lock;
 static bool hung_task_call_panic;
+static bool hung_task_show_all_bt;
 
 static struct task_struct *watchdog_task;
 
+#ifdef CONFIG_SMP
+/*
+ * Should we dump all CPUs backtraces in a hung task event?
+ * Defaults to 0, can be changed via sysctl.
+ */
+unsigned int __read_mostly sysctl_hung_task_all_cpu_backtrace;
+#endif /* CONFIG_SMP */
+
 /*
  * Should we panic (and reboot, if panic_timeout= is set) when a
  * hung task is detected:
@@ -63,16 +72,6 @@ static struct task_struct *watchdog_task;
 unsigned int __read_mostly sysctl_hung_task_panic =
 				CONFIG_BOOTPARAM_HUNG_TASK_PANIC_VALUE;
 
-static int __init hung_task_panic_setup(char *str)
-{
-	int rc = kstrtouint(str, 0, &sysctl_hung_task_panic);
-
-	if (rc)
-		return rc;
-	return 1;
-}
-__setup("hung_task_panic=", hung_task_panic_setup);
-
 static int
 hung_task_panic(struct notifier_block *this, unsigned long event, void *ptr)
 {
@@ -137,6 +136,9 @@ static void check_hung_task(struct task_struct *t, unsigned long timeout)
 			" disables this message.\n");
 		sched_show_task(t);
 		hung_task_show_lock = true;
+
+		if (sysctl_hung_task_all_cpu_backtrace)
+			hung_task_show_all_bt = true;
 	}
 
 	touch_nmi_watchdog();
@@ -201,10 +203,14 @@ static void check_hung_uninterruptible_tasks(unsigned long timeout)
 	rcu_read_unlock();
 	if (hung_task_show_lock)
 		debug_show_all_locks();
-	if (hung_task_call_panic) {
+
+	if (hung_task_show_all_bt) {
+		hung_task_show_all_bt = false;
 		trigger_all_cpu_backtrace();
-		panic("hung_task: blocked tasks");
 	}
+
+	if (hung_task_call_panic)
+		panic("hung_task: blocked tasks");
 }
 
 static long hung_timeout_jiffies(unsigned long last_checked,
diff --git a/kernel/irq/Kconfig b/kernel/irq/Kconfig
index f92d9a687372..10a5aff4eecc 100644
--- a/kernel/irq/Kconfig
+++ b/kernel/irq/Kconfig
@@ -43,14 +43,14 @@ config GENERIC_IRQ_MIGRATION
 config AUTO_IRQ_AFFINITY
        bool
 
+# Interrupt injection mechanism
+config GENERIC_IRQ_INJECTION
+	bool
+
 # Tasklet based software resend for pending interrupts on enable_irq()
 config HARDIRQS_SW_RESEND
        bool
 
-# Preflow handler support for fasteoi (sparc64)
-config IRQ_PREFLOW_FASTEOI
-       bool
-
 # Edge style eoi based handler (cell)
 config IRQ_EDGE_EOI_HANDLER
        bool
@@ -68,6 +68,7 @@ config IRQ_DOMAIN
 config IRQ_SIM
 	bool
 	select IRQ_WORK
+	select IRQ_DOMAIN
 
 # Support for hierarchical irq domains
 config IRQ_DOMAIN_HIERARCHY
@@ -113,7 +114,7 @@ config IRQ_FORCED_THREADING
 
 config SPARSE_IRQ
 	bool "Support sparse irq numbering" if MAY_HAVE_SPARSE_IRQ
-	---help---
+	help
 
 	  Sparse irq numbering is useful for distro kernels that want
 	  to define a high CONFIG_NR_CPUS value but still want to have
@@ -127,8 +128,9 @@ config SPARSE_IRQ
 config GENERIC_IRQ_DEBUGFS
 	bool "Expose irq internals in debugfs"
 	depends on DEBUG_FS
+	select GENERIC_IRQ_INJECTION
 	default n
-	---help---
+	help
 
 	  Exposes internal state information through debugfs. Mostly for
 	  developers and debugging of hard to diagnose interrupt problems.
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index b3fa2d87d2f3..857f5f4c8098 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -278,7 +278,7 @@ int irq_startup(struct irq_desc *desc, bool resend, bool force)
 		}
 	}
 	if (resend)
-		check_irq_resend(desc);
+		check_irq_resend(desc, false);
 
 	return ret;
 }
@@ -656,16 +656,6 @@ out_unlock:
 }
 EXPORT_SYMBOL_GPL(handle_level_irq);
 
-#ifdef CONFIG_IRQ_PREFLOW_FASTEOI
-static inline void preflow_handler(struct irq_desc *desc)
-{
-	if (desc->preflow_handler)
-		desc->preflow_handler(&desc->irq_data);
-}
-#else
-static inline void preflow_handler(struct irq_desc *desc) { }
-#endif
-
 static void cond_unmask_eoi_irq(struct irq_desc *desc, struct irq_chip *chip)
 {
 	if (!(desc->istate & IRQS_ONESHOT)) {
@@ -721,7 +711,6 @@ void handle_fasteoi_irq(struct irq_desc *desc)
 	if (desc->istate & IRQS_ONESHOT)
 		mask_irq(desc);
 
-	preflow_handler(desc);
 	handle_irq_event(desc);
 
 	cond_unmask_eoi_irq(desc, chip);
@@ -1231,7 +1220,6 @@ void handle_fasteoi_ack_irq(struct irq_desc *desc)
 	/* Start handling the irq */
 	desc->irq_data.chip->irq_ack(&desc->irq_data);
 
-	preflow_handler(desc);
 	handle_irq_event(desc);
 
 	cond_unmask_eoi_irq(desc, chip);
@@ -1281,7 +1269,6 @@ void handle_fasteoi_mask_irq(struct irq_desc *desc)
 	if (desc->istate & IRQS_ONESHOT)
 		mask_irq(desc);
 
-	preflow_handler(desc);
 	handle_irq_event(desc);
 
 	cond_unmask_eoi_irq(desc, chip);
@@ -1478,6 +1465,7 @@ int irq_chip_retrigger_hierarchy(struct irq_data *data)
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(irq_chip_retrigger_hierarchy);
 
 /**
  * irq_chip_set_vcpu_affinity_parent - Set vcpu affinity on the parent interrupt
@@ -1492,7 +1480,7 @@ int irq_chip_set_vcpu_affinity_parent(struct irq_data *data, void *vcpu_info)
 
 	return -ENOSYS;
 }
-
+EXPORT_SYMBOL_GPL(irq_chip_set_vcpu_affinity_parent);
 /**
  * irq_chip_set_wake_parent - Set/reset wake-up on the parent interrupt
  * @data:	Pointer to interrupt specific data
diff --git a/kernel/irq/debugfs.c b/kernel/irq/debugfs.c
index a949bd39e343..b95ff5d5f4bd 100644
--- a/kernel/irq/debugfs.c
+++ b/kernel/irq/debugfs.c
@@ -112,6 +112,7 @@ static const struct irq_bit_descr irqdata_states[] = {
 	BIT_MASK_DESCR(IRQD_AFFINITY_SET),
 	BIT_MASK_DESCR(IRQD_SETAFFINITY_PENDING),
 	BIT_MASK_DESCR(IRQD_AFFINITY_MANAGED),
+	BIT_MASK_DESCR(IRQD_AFFINITY_ON_ACTIVATE),
 	BIT_MASK_DESCR(IRQD_MANAGED_SHUTDOWN),
 	BIT_MASK_DESCR(IRQD_CAN_RESERVE),
 	BIT_MASK_DESCR(IRQD_MSI_NOMASK_QUIRK),
@@ -120,6 +121,10 @@ static const struct irq_bit_descr irqdata_states[] = {
 
 	BIT_MASK_DESCR(IRQD_WAKEUP_STATE),
 	BIT_MASK_DESCR(IRQD_WAKEUP_ARMED),
+
+	BIT_MASK_DESCR(IRQD_DEFAULT_TRIGGER_SET),
+
+	BIT_MASK_DESCR(IRQD_HANDLE_ENFORCE_IRQCTX),
 };
 
 static const struct irq_bit_descr irqdesc_states[] = {
@@ -190,33 +195,7 @@ static ssize_t irq_debug_write(struct file *file, const char __user *user_buf,
 		return -EFAULT;
 
 	if (!strncmp(buf, "trigger", size)) {
-		unsigned long flags;
-		int err;
-
-		/* Try the HW interface first */
-		err = irq_set_irqchip_state(irq_desc_get_irq(desc),
-					    IRQCHIP_STATE_PENDING, true);
-		if (!err)
-			return count;
-
-		/*
-		 * Otherwise, try to inject via the resend interface,
-		 * which may or may not succeed.
-		 */
-		chip_bus_lock(desc);
-		raw_spin_lock_irqsave(&desc->lock, flags);
-
-		if (irq_settings_is_level(desc) || desc->istate & IRQS_NMI) {
-			/* Can't do level nor NMIs, sorry */
-			err = -EINVAL;
-		} else {
-			desc->istate |= IRQS_PENDING;
-			check_irq_resend(desc);
-			err = 0;
-		}
-
-		raw_spin_unlock_irqrestore(&desc->lock, flags);
-		chip_bus_sync_unlock(desc);
+		int err = irq_inject_interrupt(irq_desc_get_irq(desc));
 
 		return err ? err : count;
 	}
diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c
index a4ace611f47f..762a928e18f9 100644
--- a/kernel/irq/handle.c
+++ b/kernel/irq/handle.c
@@ -145,6 +145,13 @@ irqreturn_t __handle_irq_event_percpu(struct irq_desc *desc, unsigned int *flags
 	for_each_action_of_desc(desc, action) {
 		irqreturn_t res;
 
+		/*
+		 * If this IRQ would be threaded under force_irqthreads, mark it so.
+		 */
+		if (irq_settings_can_thread(desc) &&
+		    !(action->flags & (IRQF_NO_THREAD | IRQF_PERCPU | IRQF_ONESHOT)))
+			lockdep_hardirq_threaded();
+
 		trace_irq_handler_entry(irq, action);
 		res = action->handler(irq, action->dev_id);
 		trace_irq_handler_exit(irq, action, res);
@@ -166,7 +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/internals.h b/kernel/irq/internals.h
index c9d8eb7f5c02..7db284b10ac9 100644
--- a/kernel/irq/internals.h
+++ b/kernel/irq/internals.h
@@ -108,7 +108,7 @@ irqreturn_t handle_irq_event_percpu(struct irq_desc *desc);
 irqreturn_t handle_irq_event(struct irq_desc *desc);
 
 /* Resending of interrupts :*/
-void check_irq_resend(struct irq_desc *desc);
+int check_irq_resend(struct irq_desc *desc, bool inject);
 bool irq_wait_for_poll(struct irq_desc *desc);
 void __irq_wake_thread(struct irq_desc *desc, struct irqaction *action);
 
@@ -425,6 +425,10 @@ static inline struct cpumask *irq_desc_get_pending_mask(struct irq_desc *desc)
 {
 	return desc->pending_mask;
 }
+static inline bool handle_enforce_irqctx(struct irq_data *data)
+{
+	return irqd_is_handle_enforce_irqctx(data);
+}
 bool irq_fixup_move_pending(struct irq_desc *desc, bool force_clear);
 #else /* CONFIG_GENERIC_PENDING_IRQ */
 static inline bool irq_can_move_pcntxt(struct irq_data *data)
@@ -451,6 +455,10 @@ static inline bool irq_fixup_move_pending(struct irq_desc *desc, bool fclear)
 {
 	return false;
 }
+static inline bool handle_enforce_irqctx(struct irq_data *data)
+{
+	return false;
+}
 #endif /* !CONFIG_GENERIC_PENDING_IRQ */
 
 #if !defined(CONFIG_IRQ_DOMAIN) || !defined(CONFIG_IRQ_DOMAIN_HIERARCHY)
diff --git a/kernel/irq/irq_sim.c b/kernel/irq/irq_sim.c
index b992f88c5613..48006608baf0 100644
--- a/kernel/irq/irq_sim.c
+++ b/kernel/irq/irq_sim.c
@@ -1,14 +1,31 @@
 // SPDX-License-Identifier: GPL-2.0+
 /*
  * Copyright (C) 2017-2018 Bartosz Golaszewski <brgl@bgdev.pl>
+ * Copyright (C) 2020 Bartosz Golaszewski <bgolaszewski@baylibre.com>
  */
 
-#include <linux/slab.h>
-#include <linux/irq_sim.h>
 #include <linux/irq.h>
+#include <linux/irq_sim.h>
+#include <linux/irq_work.h>
+#include <linux/interrupt.h>
+#include <linux/slab.h>
+
+struct irq_sim_work_ctx {
+	struct irq_work		work;
+	int			irq_base;
+	unsigned int		irq_count;
+	unsigned long		*pending;
+	struct irq_domain	*domain;
+};
+
+struct irq_sim_irq_ctx {
+	int			irqnum;
+	bool			enabled;
+	struct irq_sim_work_ctx	*work_ctx;
+};
 
 struct irq_sim_devres {
-	struct irq_sim		*sim;
+	struct irq_domain	*domain;
 };
 
 static void irq_sim_irqmask(struct irq_data *data)
@@ -36,159 +53,205 @@ static int irq_sim_set_type(struct irq_data *data, unsigned int type)
 	return 0;
 }
 
+static int irq_sim_get_irqchip_state(struct irq_data *data,
+				     enum irqchip_irq_state which, bool *state)
+{
+	struct irq_sim_irq_ctx *irq_ctx = irq_data_get_irq_chip_data(data);
+	irq_hw_number_t hwirq = irqd_to_hwirq(data);
+
+	switch (which) {
+	case IRQCHIP_STATE_PENDING:
+		if (irq_ctx->enabled)
+			*state = test_bit(hwirq, irq_ctx->work_ctx->pending);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int irq_sim_set_irqchip_state(struct irq_data *data,
+				     enum irqchip_irq_state which, bool state)
+{
+	struct irq_sim_irq_ctx *irq_ctx = irq_data_get_irq_chip_data(data);
+	irq_hw_number_t hwirq = irqd_to_hwirq(data);
+
+	switch (which) {
+	case IRQCHIP_STATE_PENDING:
+		if (irq_ctx->enabled) {
+			assign_bit(hwirq, irq_ctx->work_ctx->pending, state);
+			if (state)
+				irq_work_queue(&irq_ctx->work_ctx->work);
+		}
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 static struct irq_chip irq_sim_irqchip = {
-	.name		= "irq_sim",
-	.irq_mask	= irq_sim_irqmask,
-	.irq_unmask	= irq_sim_irqunmask,
-	.irq_set_type	= irq_sim_set_type,
+	.name			= "irq_sim",
+	.irq_mask		= irq_sim_irqmask,
+	.irq_unmask		= irq_sim_irqunmask,
+	.irq_set_type		= irq_sim_set_type,
+	.irq_get_irqchip_state	= irq_sim_get_irqchip_state,
+	.irq_set_irqchip_state	= irq_sim_set_irqchip_state,
 };
 
 static void irq_sim_handle_irq(struct irq_work *work)
 {
 	struct irq_sim_work_ctx *work_ctx;
 	unsigned int offset = 0;
-	struct irq_sim *sim;
 	int irqnum;
 
 	work_ctx = container_of(work, struct irq_sim_work_ctx, work);
-	sim = container_of(work_ctx, struct irq_sim, work_ctx);
 
-	while (!bitmap_empty(work_ctx->pending, sim->irq_count)) {
+	while (!bitmap_empty(work_ctx->pending, work_ctx->irq_count)) {
 		offset = find_next_bit(work_ctx->pending,
-				       sim->irq_count, offset);
+				       work_ctx->irq_count, offset);
 		clear_bit(offset, work_ctx->pending);
-		irqnum = irq_sim_irqnum(sim, offset);
+		irqnum = irq_find_mapping(work_ctx->domain, offset);
 		handle_simple_irq(irq_to_desc(irqnum));
 	}
 }
 
+static int irq_sim_domain_map(struct irq_domain *domain,
+			      unsigned int virq, irq_hw_number_t hw)
+{
+	struct irq_sim_work_ctx *work_ctx = domain->host_data;
+	struct irq_sim_irq_ctx *irq_ctx;
+
+	irq_ctx = kzalloc(sizeof(*irq_ctx), GFP_KERNEL);
+	if (!irq_ctx)
+		return -ENOMEM;
+
+	irq_set_chip(virq, &irq_sim_irqchip);
+	irq_set_chip_data(virq, irq_ctx);
+	irq_set_handler(virq, handle_simple_irq);
+	irq_modify_status(virq, IRQ_NOREQUEST | IRQ_NOAUTOEN, IRQ_NOPROBE);
+	irq_ctx->work_ctx = work_ctx;
+
+	return 0;
+}
+
+static void irq_sim_domain_unmap(struct irq_domain *domain, unsigned int virq)
+{
+	struct irq_sim_irq_ctx *irq_ctx;
+	struct irq_data *irqd;
+
+	irqd = irq_domain_get_irq_data(domain, virq);
+	irq_ctx = irq_data_get_irq_chip_data(irqd);
+
+	irq_set_handler(virq, NULL);
+	irq_domain_reset_irq_data(irqd);
+	kfree(irq_ctx);
+}
+
+static const struct irq_domain_ops irq_sim_domain_ops = {
+	.map		= irq_sim_domain_map,
+	.unmap		= irq_sim_domain_unmap,
+};
+
 /**
- * irq_sim_init - Initialize the interrupt simulator: allocate a range of
- *                dummy interrupts.
+ * irq_domain_create_sim - Create a new interrupt simulator irq_domain and
+ *                         allocate a range of dummy interrupts.
  *
- * @sim:        The interrupt simulator object to initialize.
- * @num_irqs:   Number of interrupts to allocate
+ * @fnode:      struct fwnode_handle to be associated with this domain.
+ * @num_irqs:   Number of interrupts to allocate.
  *
- * On success: return the base of the allocated interrupt range.
- * On failure: a negative errno.
+ * On success: return a new irq_domain object.
+ * On failure: a negative errno wrapped with ERR_PTR().
  */
-int irq_sim_init(struct irq_sim *sim, unsigned int num_irqs)
+struct irq_domain *irq_domain_create_sim(struct fwnode_handle *fwnode,
+					 unsigned int num_irqs)
 {
-	int i;
+	struct irq_sim_work_ctx *work_ctx;
 
-	sim->irqs = kmalloc_array(num_irqs, sizeof(*sim->irqs), GFP_KERNEL);
-	if (!sim->irqs)
-		return -ENOMEM;
+	work_ctx = kmalloc(sizeof(*work_ctx), GFP_KERNEL);
+	if (!work_ctx)
+		goto err_out;
 
-	sim->irq_base = irq_alloc_descs(-1, 0, num_irqs, 0);
-	if (sim->irq_base < 0) {
-		kfree(sim->irqs);
-		return sim->irq_base;
-	}
+	work_ctx->pending = bitmap_zalloc(num_irqs, GFP_KERNEL);
+	if (!work_ctx->pending)
+		goto err_free_work_ctx;
 
-	sim->work_ctx.pending = bitmap_zalloc(num_irqs, GFP_KERNEL);
-	if (!sim->work_ctx.pending) {
-		kfree(sim->irqs);
-		irq_free_descs(sim->irq_base, num_irqs);
-		return -ENOMEM;
-	}
+	work_ctx->domain = irq_domain_create_linear(fwnode, num_irqs,
+						    &irq_sim_domain_ops,
+						    work_ctx);
+	if (!work_ctx->domain)
+		goto err_free_bitmap;
 
-	for (i = 0; i < num_irqs; i++) {
-		sim->irqs[i].irqnum = sim->irq_base + i;
-		sim->irqs[i].enabled = false;
-		irq_set_chip(sim->irq_base + i, &irq_sim_irqchip);
-		irq_set_chip_data(sim->irq_base + i, &sim->irqs[i]);
-		irq_set_handler(sim->irq_base + i, &handle_simple_irq);
-		irq_modify_status(sim->irq_base + i,
-				  IRQ_NOREQUEST | IRQ_NOAUTOEN, IRQ_NOPROBE);
-	}
+	work_ctx->irq_count = num_irqs;
+	init_irq_work(&work_ctx->work, irq_sim_handle_irq);
 
-	init_irq_work(&sim->work_ctx.work, irq_sim_handle_irq);
-	sim->irq_count = num_irqs;
+	return work_ctx->domain;
 
-	return sim->irq_base;
+err_free_bitmap:
+	bitmap_free(work_ctx->pending);
+err_free_work_ctx:
+	kfree(work_ctx);
+err_out:
+	return ERR_PTR(-ENOMEM);
 }
-EXPORT_SYMBOL_GPL(irq_sim_init);
+EXPORT_SYMBOL_GPL(irq_domain_create_sim);
 
 /**
- * irq_sim_fini - Deinitialize the interrupt simulator: free the interrupt
- *                descriptors and allocated memory.
+ * irq_domain_remove_sim - Deinitialize the interrupt simulator domain: free
+ *                         the interrupt descriptors and allocated memory.
  *
- * @sim:        The interrupt simulator to tear down.
+ * @domain:     The interrupt simulator domain to tear down.
  */
-void irq_sim_fini(struct irq_sim *sim)
+void irq_domain_remove_sim(struct irq_domain *domain)
 {
-	irq_work_sync(&sim->work_ctx.work);
-	bitmap_free(sim->work_ctx.pending);
-	irq_free_descs(sim->irq_base, sim->irq_count);
-	kfree(sim->irqs);
+	struct irq_sim_work_ctx *work_ctx = domain->host_data;
+
+	irq_work_sync(&work_ctx->work);
+	bitmap_free(work_ctx->pending);
+	kfree(work_ctx);
+
+	irq_domain_remove(domain);
 }
-EXPORT_SYMBOL_GPL(irq_sim_fini);
+EXPORT_SYMBOL_GPL(irq_domain_remove_sim);
 
-static void devm_irq_sim_release(struct device *dev, void *res)
+static void devm_irq_domain_release_sim(struct device *dev, void *res)
 {
 	struct irq_sim_devres *this = res;
 
-	irq_sim_fini(this->sim);
+	irq_domain_remove_sim(this->domain);
 }
 
 /**
- * irq_sim_init - Initialize the interrupt simulator for a managed device.
+ * devm_irq_domain_create_sim - Create a new interrupt simulator for
+ *                              a managed device.
  *
  * @dev:        Device to initialize the simulator object for.
- * @sim:        The interrupt simulator object to initialize.
+ * @fnode:      struct fwnode_handle to be associated with this domain.
  * @num_irqs:   Number of interrupts to allocate
  *
- * On success: return the base of the allocated interrupt range.
- * On failure: a negative errno.
+ * On success: return a new irq_domain object.
+ * On failure: a negative errno wrapped with ERR_PTR().
  */
-int devm_irq_sim_init(struct device *dev, struct irq_sim *sim,
-		      unsigned int num_irqs)
+struct irq_domain *devm_irq_domain_create_sim(struct device *dev,
+					      struct fwnode_handle *fwnode,
+					      unsigned int num_irqs)
 {
 	struct irq_sim_devres *dr;
-	int rv;
 
-	dr = devres_alloc(devm_irq_sim_release, sizeof(*dr), GFP_KERNEL);
+	dr = devres_alloc(devm_irq_domain_release_sim,
+			  sizeof(*dr), GFP_KERNEL);
 	if (!dr)
-		return -ENOMEM;
+		return ERR_PTR(-ENOMEM);
 
-	rv = irq_sim_init(sim, num_irqs);
-	if (rv < 0) {
+	dr->domain = irq_domain_create_sim(fwnode, num_irqs);
+	if (IS_ERR(dr->domain)) {
 		devres_free(dr);
-		return rv;
+		return dr->domain;
 	}
 
-	dr->sim = sim;
 	devres_add(dev, dr);
-
-	return rv;
-}
-EXPORT_SYMBOL_GPL(devm_irq_sim_init);
-
-/**
- * irq_sim_fire - Enqueue an interrupt.
- *
- * @sim:        The interrupt simulator object.
- * @offset:     Offset of the simulated interrupt which should be fired.
- */
-void irq_sim_fire(struct irq_sim *sim, unsigned int offset)
-{
-	if (sim->irqs[offset].enabled) {
-		set_bit(offset, sim->work_ctx.pending);
-		irq_work_queue(&sim->work_ctx.work);
-	}
-}
-EXPORT_SYMBOL_GPL(irq_sim_fire);
-
-/**
- * irq_sim_irqnum - Get the allocated number of a dummy interrupt.
- *
- * @sim:        The interrupt simulator object.
- * @offset:     Offset of the simulated interrupt for which to retrieve
- *              the number.
- */
-int irq_sim_irqnum(struct irq_sim *sim, unsigned int offset)
-{
-	return sim->irqs[offset].irqnum;
+	return dr->domain;
 }
-EXPORT_SYMBOL_GPL(irq_sim_irqnum);
+EXPORT_SYMBOL_GPL(devm_irq_domain_create_sim);
diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c
index 98a5f10d1900..1a7723604399 100644
--- a/kernel/irq/irqdesc.c
+++ b/kernel/irq/irqdesc.c
@@ -638,9 +638,15 @@ void irq_init_desc(unsigned int irq)
 int generic_handle_irq(unsigned int irq)
 {
 	struct irq_desc *desc = irq_to_desc(irq);
+	struct irq_data *data;
 
 	if (!desc)
 		return -EINVAL;
+
+	data = irq_desc_get_irq_data(desc);
+	if (WARN_ON_ONCE(!in_irq() && handle_enforce_irqctx(data)))
+		return -EPERM;
+
 	generic_handle_irq_desc(desc);
 	return 0;
 }
diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c
index 7527e5ef6fe5..76cd7ebd1178 100644
--- a/kernel/irq/irqdomain.c
+++ b/kernel/irq/irqdomain.c
@@ -46,11 +46,11 @@ const struct fwnode_operations irqchip_fwnode_ops;
 EXPORT_SYMBOL_GPL(irqchip_fwnode_ops);
 
 /**
- * irq_domain_alloc_fwnode - Allocate a fwnode_handle suitable for
+ * __irq_domain_alloc_fwnode - Allocate a fwnode_handle suitable for
  *                           identifying an irq domain
  * @type:	Type of irqchip_fwnode. See linux/irqdomain.h
- * @name:	Optional user provided domain name
  * @id:		Optional user provided id if name != NULL
+ * @name:	Optional user provided domain name
  * @pa:		Optional user-provided physical address
  *
  * Allocate a struct irqchip_fwid, and return a poiner to the embedded
@@ -132,18 +132,17 @@ struct irq_domain *__irq_domain_add(struct fwnode_handle *fwnode, int size,
 				    const struct irq_domain_ops *ops,
 				    void *host_data)
 {
-	struct device_node *of_node = to_of_node(fwnode);
 	struct irqchip_fwid *fwid;
 	struct irq_domain *domain;
 
 	static atomic_t unknown_domains;
 
 	domain = kzalloc_node(sizeof(*domain) + (sizeof(unsigned int) * size),
-			      GFP_KERNEL, of_node_to_nid(of_node));
+			      GFP_KERNEL, of_node_to_nid(to_of_node(fwnode)));
 	if (!domain)
 		return NULL;
 
-	if (fwnode && is_fwnode_irqchip(fwnode)) {
+	if (is_fwnode_irqchip(fwnode)) {
 		fwid = container_of(fwnode, struct irqchip_fwid, fwnode);
 
 		switch (fwid->type) {
@@ -162,30 +161,16 @@ struct irq_domain *__irq_domain_add(struct fwnode_handle *fwnode, int size,
 			domain->name = fwid->name;
 			break;
 		}
-#ifdef CONFIG_ACPI
-	} else if (is_acpi_device_node(fwnode)) {
-		struct acpi_buffer buf = {
-			.length = ACPI_ALLOCATE_BUFFER,
-		};
-		acpi_handle handle;
-
-		handle = acpi_device_handle(to_acpi_device_node(fwnode));
-		if (acpi_get_name(handle, ACPI_FULL_PATHNAME, &buf) == AE_OK) {
-			domain->name = buf.pointer;
-			domain->flags |= IRQ_DOMAIN_NAME_ALLOCATED;
-		}
-
-		domain->fwnode = fwnode;
-#endif
-	} else if (of_node) {
+	} else if (is_of_node(fwnode) || is_acpi_device_node(fwnode) ||
+		   is_software_node(fwnode)) {
 		char *name;
 
 		/*
-		 * DT paths contain '/', which debugfs is legitimately
+		 * fwnode paths contain '/', which debugfs is legitimately
 		 * unhappy about. Replace them with ':', which does
 		 * the trick and is not as offensive as '\'...
 		 */
-		name = kasprintf(GFP_KERNEL, "%pOF", of_node);
+		name = kasprintf(GFP_KERNEL, "%pfw", fwnode);
 		if (!name) {
 			kfree(domain);
 			return NULL;
@@ -210,7 +195,7 @@ struct irq_domain *__irq_domain_add(struct fwnode_handle *fwnode, int size,
 		domain->flags |= IRQ_DOMAIN_NAME_ALLOCATED;
 	}
 
-	of_node_get(of_node);
+	fwnode_handle_get(fwnode);
 
 	/* Fill structure */
 	INIT_RADIX_TREE(&domain->revmap_tree, GFP_KERNEL);
@@ -259,7 +244,7 @@ void irq_domain_remove(struct irq_domain *domain)
 
 	pr_debug("Removed domain %s\n", domain->name);
 
-	of_node_put(irq_domain_get_of_node(domain));
+	fwnode_handle_put(domain->fwnode);
 	if (domain->flags & IRQ_DOMAIN_NAME_ALLOCATED)
 		kfree(domain->name);
 	kfree(domain);
@@ -296,6 +281,7 @@ void irq_domain_update_bus_token(struct irq_domain *domain,
 
 	mutex_unlock(&irq_domain_mutex);
 }
+EXPORT_SYMBOL_GPL(irq_domain_update_bus_token);
 
 /**
  * irq_domain_add_simple() - Register an irq_domain and optionally map a range of irqs
@@ -1047,6 +1033,18 @@ int irq_domain_alloc_descs(int virq, unsigned int cnt, irq_hw_number_t hwirq,
 	return virq;
 }
 
+/**
+ * irq_domain_reset_irq_data - Clear hwirq, chip and chip_data in @irq_data
+ * @irq_data:	The pointer to irq_data
+ */
+void irq_domain_reset_irq_data(struct irq_data *irq_data)
+{
+	irq_data->hwirq = 0;
+	irq_data->chip = &no_irq_chip;
+	irq_data->chip_data = NULL;
+}
+EXPORT_SYMBOL_GPL(irq_domain_reset_irq_data);
+
 #ifdef	CONFIG_IRQ_DOMAIN_HIERARCHY
 /**
  * irq_domain_create_hierarchy - Add a irqdomain into the hierarchy
@@ -1248,18 +1246,6 @@ void irq_domain_set_info(struct irq_domain *domain, unsigned int virq,
 EXPORT_SYMBOL(irq_domain_set_info);
 
 /**
- * irq_domain_reset_irq_data - Clear hwirq, chip and chip_data in @irq_data
- * @irq_data:	The pointer to irq_data
- */
-void irq_domain_reset_irq_data(struct irq_data *irq_data)
-{
-	irq_data->hwirq = 0;
-	irq_data->chip = &no_irq_chip;
-	irq_data->chip_data = NULL;
-}
-EXPORT_SYMBOL_GPL(irq_domain_reset_irq_data);
-
-/**
  * irq_domain_free_irqs_common - Clear irq_data and free the parent
  * @domain:	Interrupt domain to match
  * @virq:	IRQ number to start with
@@ -1310,6 +1296,11 @@ int irq_domain_alloc_irqs_hierarchy(struct irq_domain *domain,
 				    unsigned int irq_base,
 				    unsigned int nr_irqs, void *arg)
 {
+	if (!domain->ops->alloc) {
+		pr_debug("domain->ops->alloc() is NULL\n");
+		return -ENOSYS;
+	}
+
 	return domain->ops->alloc(domain, irq_base, nr_irqs, arg);
 }
 
@@ -1347,11 +1338,6 @@ int __irq_domain_alloc_irqs(struct irq_domain *domain, int irq_base,
 			return -EINVAL;
 	}
 
-	if (!domain->ops->alloc) {
-		pr_debug("domain->ops->alloc() is NULL\n");
-		return -ENOSYS;
-	}
-
 	if (realloc && irq_base >= 0) {
 		virq = irq_base;
 	} else {
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 7eee98c38f25..5df903fccb60 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -195,9 +195,9 @@ void irq_set_thread_affinity(struct irq_desc *desc)
 			set_bit(IRQTF_AFFINITY, &action->thread_flags);
 }
 
+#ifdef CONFIG_GENERIC_IRQ_EFFECTIVE_AFF_MASK
 static void irq_validate_effective_affinity(struct irq_data *data)
 {
-#ifdef CONFIG_GENERIC_IRQ_EFFECTIVE_AFF_MASK
 	const struct cpumask *m = irq_data_get_effective_affinity_mask(data);
 	struct irq_chip *chip = irq_data_get_irq_chip(data);
 
@@ -205,9 +205,19 @@ static void irq_validate_effective_affinity(struct irq_data *data)
 		return;
 	pr_warn_once("irq_chip %s did not update eff. affinity mask of irq %u\n",
 		     chip->name, data->irq);
-#endif
 }
 
+static inline void irq_init_effective_affinity(struct irq_data *data,
+					       const struct cpumask *mask)
+{
+	cpumask_copy(irq_data_get_effective_affinity_mask(data), mask);
+}
+#else
+static inline void irq_validate_effective_affinity(struct irq_data *data) { }
+static inline void irq_init_effective_affinity(struct irq_data *data,
+					       const struct cpumask *mask) { }
+#endif
+
 int irq_do_set_affinity(struct irq_data *data, const struct cpumask *mask,
 			bool force)
 {
@@ -261,7 +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);
@@ -304,6 +314,30 @@ static int irq_try_set_affinity(struct irq_data *data,
 	return ret;
 }
 
+static bool irq_set_affinity_deactivated(struct irq_data *data,
+					 const struct cpumask *mask, bool force)
+{
+	struct irq_desc *desc = irq_data_to_desc(data);
+
+	/*
+	 * Handle irq chips which can handle affinity only in activated
+	 * state correctly
+	 *
+	 * If the interrupt is not yet activated, just store the affinity
+	 * mask and do not call the chip driver at all. On activation the
+	 * driver has to make sure anyway that the interrupt is in a
+	 * useable state so startup works.
+	 */
+	if (!IS_ENABLED(CONFIG_IRQ_DOMAIN_HIERARCHY) ||
+	    irqd_is_activated(data) || !irqd_affinity_on_activate(data))
+		return false;
+
+	cpumask_copy(desc->irq_common_data.affinity, mask);
+	irq_init_effective_affinity(data, mask);
+	irqd_set(data, IRQD_AFFINITY_SET);
+	return true;
+}
+
 int irq_set_affinity_locked(struct irq_data *data, const struct cpumask *mask,
 			    bool force)
 {
@@ -314,6 +348,9 @@ int irq_set_affinity_locked(struct irq_data *data, const struct cpumask *mask,
 	if (!chip || !chip->irq_set_affinity)
 		return -EINVAL;
 
+	if (irq_set_affinity_deactivated(data, mask, force))
+		return 0;
+
 	if (irq_can_move_pcntxt(data) && !irqd_is_setaffinity_pending(data)) {
 		ret = irq_try_set_affinity(data, mask, force);
 	} else {
@@ -323,7 +360,11 @@ int irq_set_affinity_locked(struct irq_data *data, const struct cpumask *mask,
 
 	if (desc->affinity_notify) {
 		kref_get(&desc->affinity_notify->kref);
-		schedule_work(&desc->affinity_notify->work);
+		if (!schedule_work(&desc->affinity_notify->work)) {
+			/* Work was already scheduled, drop our extra ref */
+			kref_put(&desc->affinity_notify->kref,
+				 desc->affinity_notify->release);
+		}
 	}
 	irqd_set(data, IRQD_AFFINITY_SET);
 
@@ -423,7 +464,10 @@ irq_set_affinity_notifier(unsigned int irq, struct irq_affinity_notify *notify)
 	raw_spin_unlock_irqrestore(&desc->lock, flags);
 
 	if (old_notify) {
-		cancel_work_sync(&old_notify->work);
+		if (cancel_work_sync(&old_notify->work)) {
+			/* Pending work had a ref, put that one too */
+			kref_put(&old_notify->kref, old_notify->release);
+		}
 		kref_put(&old_notify->kref, old_notify->release);
 	}
 
@@ -824,7 +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);
@@ -1264,9 +1308,6 @@ static int
 setup_irq_thread(struct irqaction *new, unsigned int irq, bool secondary)
 {
 	struct task_struct *t;
-	struct sched_param param = {
-		.sched_priority = MAX_USER_RT_PRIO/2,
-	};
 
 	if (!secondary) {
 		t = kthread_create(irq_thread, new, "irq/%d-%s", irq,
@@ -1274,13 +1315,12 @@ setup_irq_thread(struct irqaction *new, unsigned int irq, bool secondary)
 	} else {
 		t = kthread_create(irq_thread, new, "irq/%d-s-%s", irq,
 				   new->name);
-		param.sched_priority -= 1;
 	}
 
 	if (IS_ERR(t))
 		return PTR_ERR(t);
 
-	sched_setscheduler_nocheck(t, SCHED_FIFO, &param);
+	sched_set_fifo(t);
 
 	/*
 	 * We keep the reference to the task struct even if
@@ -1683,34 +1723,6 @@ out_mput:
 	return ret;
 }
 
-/**
- *	setup_irq - setup an interrupt
- *	@irq: Interrupt line to setup
- *	@act: irqaction for the interrupt
- *
- * Used to statically setup interrupts in the early boot process.
- */
-int setup_irq(unsigned int irq, struct irqaction *act)
-{
-	int retval;
-	struct irq_desc *desc = irq_to_desc(irq);
-
-	if (!desc || WARN_ON(irq_settings_is_per_cpu_devid(desc)))
-		return -EINVAL;
-
-	retval = irq_chip_pm_get(&desc->irq_data);
-	if (retval < 0)
-		return retval;
-
-	retval = __setup_irq(irq, desc, act);
-
-	if (retval)
-		irq_chip_pm_put(&desc->irq_data);
-
-	return retval;
-}
-EXPORT_SYMBOL_GPL(setup_irq);
-
 /*
  * Internal function to unregister an irqaction - used to free
  * regular and special interrupts that are part of the architecture.
@@ -1852,22 +1864,6 @@ static struct irqaction *__free_irq(struct irq_desc *desc, void *dev_id)
 }
 
 /**
- *	remove_irq - free an interrupt
- *	@irq: Interrupt line to free
- *	@act: irqaction for the interrupt
- *
- * Used to remove interrupts statically setup by the early boot process.
- */
-void remove_irq(unsigned int irq, struct irqaction *act)
-{
-	struct irq_desc *desc = irq_to_desc(irq);
-
-	if (desc && !WARN_ON(irq_settings_is_per_cpu_devid(desc)))
-		__free_irq(desc, act->dev_id);
-}
-EXPORT_SYMBOL_GPL(remove_irq);
-
-/**
  *	free_irq - free an interrupt allocated with request_irq
  *	@irq: Interrupt line to free
  *	@dev_id: Device identity to free
@@ -2656,6 +2652,8 @@ int __irq_get_irqchip_state(struct irq_data *data, enum irqchip_irq_state which,
 
 	do {
 		chip = irq_data_get_irq_chip(data);
+		if (WARN_ON_ONCE(!chip))
+			return -ENODEV;
 		if (chip->irq_get_irqchip_state)
 			break;
 #ifdef CONFIG_IRQ_DOMAIN_HIERARCHY
@@ -2733,6 +2731,10 @@ int irq_set_irqchip_state(unsigned int irq, enum irqchip_irq_state which,
 
 	do {
 		chip = irq_data_get_irq_chip(data);
+		if (WARN_ON_ONCE(!chip)) {
+			err = -ENODEV;
+			goto out_unlock;
+		}
 		if (chip->irq_set_irqchip_state)
 			break;
 #ifdef CONFIG_IRQ_DOMAIN_HIERARCHY
@@ -2745,6 +2747,7 @@ int irq_set_irqchip_state(unsigned int irq, enum irqchip_irq_state which,
 	if (data)
 		err = chip->irq_set_irqchip_state(data, which, val);
 
+out_unlock:
 	irq_put_desc_busunlock(desc, flags);
 	return err;
 }
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/irq/pm.c b/kernel/irq/pm.c
index 8f557fa1f4fe..c6c7e187ae74 100644
--- a/kernel/irq/pm.c
+++ b/kernel/irq/pm.c
@@ -185,14 +185,18 @@ void rearm_wake_irq(unsigned int irq)
 	unsigned long flags;
 	struct irq_desc *desc = irq_get_desc_buslock(irq, &flags, IRQ_GET_DESC_CHECK_GLOBAL);
 
-	if (!desc || !(desc->istate & IRQS_SUSPENDED) ||
-	    !irqd_is_wakeup_set(&desc->irq_data))
+	if (!desc)
 		return;
 
+	if (!(desc->istate & IRQS_SUSPENDED) ||
+	    !irqd_is_wakeup_set(&desc->irq_data))
+		goto unlock;
+
 	desc->istate &= ~IRQS_SUSPENDED;
 	irqd_set(&desc->irq_data, IRQD_WAKEUP_ARMED);
 	__enable_irq(desc);
 
+unlock:
 	irq_put_desc_busunlock(desc, flags);
 }
 
diff --git a/kernel/irq/resend.c b/kernel/irq/resend.c
index 98c04ca5fa43..c48ce19a257f 100644
--- a/kernel/irq/resend.c
+++ b/kernel/irq/resend.c
@@ -45,8 +45,45 @@ static void resend_irqs(unsigned long arg)
 }
 
 /* Tasklet to handle resend: */
-static DECLARE_TASKLET(resend_tasklet, resend_irqs, 0);
+static DECLARE_TASKLET_OLD(resend_tasklet, resend_irqs);
 
+static int irq_sw_resend(struct irq_desc *desc)
+{
+	unsigned int irq = irq_desc_get_irq(desc);
+
+	/*
+	 * Validate whether this interrupt can be safely injected from
+	 * non interrupt context
+	 */
+	if (handle_enforce_irqctx(&desc->irq_data))
+		return -EINVAL;
+
+	/*
+	 * If the interrupt is running in the thread context of the parent
+	 * irq we need to be careful, because we cannot trigger it
+	 * directly.
+	 */
+	if (irq_settings_is_nested_thread(desc)) {
+		/*
+		 * If the parent_irq is valid, we retrigger the parent,
+		 * otherwise we do nothing.
+		 */
+		if (!desc->parent_irq)
+			return -EINVAL;
+		irq = desc->parent_irq;
+	}
+
+	/* Set it pending and activate the softirq: */
+	set_bit(irq, irqs_resend);
+	tasklet_schedule(&resend_tasklet);
+	return 0;
+}
+
+#else
+static int irq_sw_resend(struct irq_desc *desc)
+{
+	return -EINVAL;
+}
 #endif
 
 /*
@@ -54,49 +91,83 @@ static DECLARE_TASKLET(resend_tasklet, resend_irqs, 0);
  *
  * Is called with interrupts disabled and desc->lock held.
  */
-void check_irq_resend(struct irq_desc *desc)
+int check_irq_resend(struct irq_desc *desc, bool inject)
 {
+	int err = 0;
+
 	/*
-	 * We do not resend level type interrupts. Level type
-	 * interrupts are resent by hardware when they are still
-	 * active. Clear the pending bit so suspend/resume does not
-	 * get confused.
+	 * We do not resend level type interrupts. Level type interrupts
+	 * are resent by hardware when they are still active. Clear the
+	 * pending bit so suspend/resume does not get confused.
 	 */
 	if (irq_settings_is_level(desc)) {
 		desc->istate &= ~IRQS_PENDING;
-		return;
+		return -EINVAL;
 	}
+
 	if (desc->istate & IRQS_REPLAY)
-		return;
-	if (desc->istate & IRQS_PENDING) {
-		desc->istate &= ~IRQS_PENDING;
+		return -EBUSY;
+
+	if (!(desc->istate & IRQS_PENDING) && !inject)
+		return 0;
+
+	desc->istate &= ~IRQS_PENDING;
+
+	if (!desc->irq_data.chip->irq_retrigger ||
+	    !desc->irq_data.chip->irq_retrigger(&desc->irq_data))
+		err = irq_sw_resend(desc);
+
+	/* If the retrigger was successfull, mark it with the REPLAY bit */
+	if (!err)
 		desc->istate |= IRQS_REPLAY;
+	return err;
+}
 
-		if (!desc->irq_data.chip->irq_retrigger ||
-		    !desc->irq_data.chip->irq_retrigger(&desc->irq_data)) {
-#ifdef CONFIG_HARDIRQS_SW_RESEND
-			unsigned int irq = irq_desc_get_irq(desc);
-
-			/*
-			 * If the interrupt is running in the thread
-			 * context of the parent irq we need to be
-			 * careful, because we cannot trigger it
-			 * directly.
-			 */
-			if (irq_settings_is_nested_thread(desc)) {
-				/*
-				 * If the parent_irq is valid, we
-				 * retrigger the parent, otherwise we
-				 * do nothing.
-				 */
-				if (!desc->parent_irq)
-					return;
-				irq = desc->parent_irq;
-			}
-			/* Set it pending and activate the softirq: */
-			set_bit(irq, irqs_resend);
-			tasklet_schedule(&resend_tasklet);
-#endif
-		}
-	}
+#ifdef CONFIG_GENERIC_IRQ_INJECTION
+/**
+ * irq_inject_interrupt - Inject an interrupt for testing/error injection
+ * @irq:	The interrupt number
+ *
+ * This function must only be used for debug and testing purposes!
+ *
+ * Especially on x86 this can cause a premature completion of an interrupt
+ * affinity change causing the interrupt line to become stale. Very
+ * unlikely, but possible.
+ *
+ * The injection can fail for various reasons:
+ * - Interrupt is not activated
+ * - Interrupt is NMI type or currently replaying
+ * - Interrupt is level type
+ * - Interrupt does not support hardware retrigger and software resend is
+ *   either not enabled or not possible for the interrupt.
+ */
+int irq_inject_interrupt(unsigned int irq)
+{
+	struct irq_desc *desc;
+	unsigned long flags;
+	int err;
+
+	/* Try the state injection hardware interface first */
+	if (!irq_set_irqchip_state(irq, IRQCHIP_STATE_PENDING, true))
+		return 0;
+
+	/* That failed, try via the resend mechanism */
+	desc = irq_get_desc_buslock(irq, &flags, 0);
+	if (!desc)
+		return -EINVAL;
+
+	/*
+	 * Only try to inject when the interrupt is:
+	 *  - not NMI type
+	 *  - activated
+	 */
+	if ((desc->istate & IRQS_NMI) || !irqd_is_activated(&desc->irq_data))
+		err = -EINVAL;
+	else
+		err = check_irq_resend(desc, true);
+
+	irq_put_desc_busunlock(desc, flags);
+	return err;
 }
+EXPORT_SYMBOL_GPL(irq_inject_interrupt);
+#endif
diff --git a/kernel/irq_work.c b/kernel/irq_work.c
index 828cc30774bc..eca83965b631 100644
--- a/kernel/irq_work.c
+++ b/kernel/irq_work.c
@@ -31,7 +31,7 @@ static bool irq_work_claim(struct irq_work *work)
 {
 	int oflags;
 
-	oflags = atomic_fetch_or(IRQ_WORK_CLAIMED, &work->flags);
+	oflags = atomic_fetch_or(IRQ_WORK_CLAIMED | CSD_TYPE_IRQ_WORK, &work->flags);
 	/*
 	 * If the work is already pending, no need to raise the IPI.
 	 * The pairing atomic_fetch_andnot() in irq_work_run() makes sure
@@ -102,8 +102,7 @@ bool irq_work_queue_on(struct irq_work *work, int cpu)
 	if (cpu != smp_processor_id()) {
 		/* Arch remote IPI send/receive backend aren't NMI safe */
 		WARN_ON_ONCE(in_nmi());
-		if (llist_add(&work->llnode, &per_cpu(raised_list, cpu)))
-			arch_send_call_function_single_ipi(cpu);
+		__smp_call_single_queue(cpu, &work->llnode);
 	} else {
 		__irq_work_queue_local(work);
 	}
@@ -131,6 +130,31 @@ bool irq_work_needs_cpu(void)
 	return true;
 }
 
+void irq_work_single(void *arg)
+{
+	struct irq_work *work = arg;
+	int flags;
+
+	/*
+	 * Clear the PENDING bit, after this point the @work
+	 * can be re-used.
+	 * Make it immediately visible so that other CPUs trying
+	 * to claim that work don't rely on us to handle their data
+	 * while we are in the middle of the func.
+	 */
+	flags = atomic_fetch_andnot(IRQ_WORK_PENDING, &work->flags);
+
+	lockdep_irq_work_enter(work);
+	work->func(work);
+	lockdep_irq_work_exit(work);
+	/*
+	 * Clear the BUSY bit and return to the free state if
+	 * no-one else claimed it meanwhile.
+	 */
+	flags &= ~IRQ_WORK_PENDING;
+	(void)atomic_cmpxchg(&work->flags, flags, flags & ~IRQ_WORK_BUSY);
+}
+
 static void irq_work_run_list(struct llist_head *list)
 {
 	struct irq_work *work, *tmp;
@@ -142,25 +166,8 @@ static void irq_work_run_list(struct llist_head *list)
 		return;
 
 	llnode = llist_del_all(list);
-	llist_for_each_entry_safe(work, tmp, llnode, llnode) {
-		int flags;
-		/*
-		 * Clear the PENDING bit, after this point the @work
-		 * can be re-used.
-		 * Make it immediately visible so that other CPUs trying
-		 * to claim that work don't rely on us to handle their data
-		 * while we are in the middle of the func.
-		 */
-		flags = atomic_fetch_andnot(IRQ_WORK_PENDING, &work->flags);
-
-		work->func(work);
-		/*
-		 * Clear the BUSY bit and return to the free state if
-		 * no-one else claimed it meanwhile.
-		 */
-		flags &= ~IRQ_WORK_PENDING;
-		(void)atomic_cmpxchg(&work->flags, flags, flags & ~IRQ_WORK_BUSY);
-	}
+	llist_for_each_entry_safe(work, tmp, llnode, llnode)
+		irq_work_single(work);
 }
 
 /*
diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c
index a9b3f660dee7..4fb15fa96734 100644
--- a/kernel/kallsyms.c
+++ b/kernel/kallsyms.c
@@ -24,6 +24,7 @@
 #include <linux/slab.h>
 #include <linux/filter.h>
 #include <linux/ftrace.h>
+#include <linux/kprobes.h>
 #include <linux/compiler.h>
 
 /*
@@ -175,7 +176,6 @@ unsigned long kallsyms_lookup_name(const char *name)
 	}
 	return module_kallsyms_lookup_name(name);
 }
-EXPORT_SYMBOL_GPL(kallsyms_lookup_name);
 
 int kallsyms_on_each_symbol(int (*fn)(void *, const char *, struct module *,
 				      unsigned long),
@@ -194,7 +194,6 @@ int kallsyms_on_each_symbol(int (*fn)(void *, const char *, struct module *,
 	}
 	return module_kallsyms_on_each_symbol(fn, data);
 }
-EXPORT_SYMBOL_GPL(kallsyms_on_each_symbol);
 
 static unsigned long get_symbol_pos(unsigned long addr,
 				    unsigned long *symbolsize,
@@ -439,6 +438,7 @@ struct kallsym_iter {
 	loff_t pos_arch_end;
 	loff_t pos_mod_end;
 	loff_t pos_ftrace_mod_end;
+	loff_t pos_bpf_end;
 	unsigned long value;
 	unsigned int nameoff; /* If iterating in core kernel symbols. */
 	char type;
@@ -482,6 +482,11 @@ static int get_ksymbol_mod(struct kallsym_iter *iter)
 	return 1;
 }
 
+/*
+ * ftrace_mod_get_kallsym() may also get symbols for pages allocated for ftrace
+ * purposes. In that case "__builtin__ftrace" is used as a module name, even
+ * though "__builtin__ftrace" is not a module.
+ */
 static int get_ksymbol_ftrace_mod(struct kallsym_iter *iter)
 {
 	int ret = ftrace_mod_get_kallsym(iter->pos - iter->pos_mod_end,
@@ -498,11 +503,33 @@ static int get_ksymbol_ftrace_mod(struct kallsym_iter *iter)
 
 static int get_ksymbol_bpf(struct kallsym_iter *iter)
 {
+	int ret;
+
 	strlcpy(iter->module_name, "bpf", MODULE_NAME_LEN);
 	iter->exported = 0;
-	return bpf_get_kallsym(iter->pos - iter->pos_ftrace_mod_end,
-			       &iter->value, &iter->type,
-			       iter->name) < 0 ? 0 : 1;
+	ret = bpf_get_kallsym(iter->pos - iter->pos_ftrace_mod_end,
+			      &iter->value, &iter->type,
+			      iter->name);
+	if (ret < 0) {
+		iter->pos_bpf_end = iter->pos;
+		return 0;
+	}
+
+	return 1;
+}
+
+/*
+ * This uses "__builtin__kprobes" as a module name for symbols for pages
+ * allocated for kprobes' purposes, even though "__builtin__kprobes" is not a
+ * module.
+ */
+static int get_ksymbol_kprobe(struct kallsym_iter *iter)
+{
+	strlcpy(iter->module_name, "__builtin__kprobes", MODULE_NAME_LEN);
+	iter->exported = 0;
+	return kprobe_get_kallsym(iter->pos - iter->pos_bpf_end,
+				  &iter->value, &iter->type,
+				  iter->name) < 0 ? 0 : 1;
 }
 
 /* Returns space to next name. */
@@ -529,6 +556,7 @@ static void reset_iter(struct kallsym_iter *iter, loff_t new_pos)
 		iter->pos_arch_end = 0;
 		iter->pos_mod_end = 0;
 		iter->pos_ftrace_mod_end = 0;
+		iter->pos_bpf_end = 0;
 	}
 }
 
@@ -553,7 +581,11 @@ static int update_iter_mod(struct kallsym_iter *iter, loff_t pos)
 	    get_ksymbol_ftrace_mod(iter))
 		return 1;
 
-	return get_ksymbol_bpf(iter);
+	if ((!iter->pos_bpf_end || iter->pos_bpf_end > pos) &&
+	    get_ksymbol_bpf(iter))
+		return 1;
+
+	return get_ksymbol_kprobe(iter);
 }
 
 /* Returns false if pos at or past end of file. */
@@ -646,19 +678,20 @@ static inline int kallsyms_for_perf(void)
  * Otherwise, require CAP_SYSLOG (assuming kptr_restrict isn't set to
  * block even that).
  */
-int kallsyms_show_value(void)
+bool kallsyms_show_value(const struct cred *cred)
 {
 	switch (kptr_restrict) {
 	case 0:
 		if (kallsyms_for_perf())
-			return 1;
-	/* fallthrough */
+			return true;
+		fallthrough;
 	case 1:
-		if (has_capability_noaudit(current, CAP_SYSLOG))
-			return 1;
-	/* fallthrough */
+		if (security_capable(cred, &init_user_ns, CAP_SYSLOG,
+				     CAP_OPT_NOAUDIT) == 0)
+			return true;
+		fallthrough;
 	default:
-		return 0;
+		return false;
 	}
 }
 
@@ -675,7 +708,11 @@ static int kallsyms_open(struct inode *inode, struct file *file)
 		return -ENOMEM;
 	reset_iter(iter, 0);
 
-	iter->show_value = kallsyms_show_value();
+	/*
+	 * Instead of checking this on every s_show() call, cache
+	 * the result here at open time.
+	 */
+	iter->show_value = kallsyms_show_value(file->f_cred);
 	return 0;
 }
 
diff --git a/kernel/kcmp.c b/kernel/kcmp.c
index a0e3d7a0e8b8..b3ff9288c6cc 100644
--- a/kernel/kcmp.c
+++ b/kernel/kcmp.c
@@ -173,8 +173,8 @@ SYSCALL_DEFINE5(kcmp, pid_t, pid1, pid_t, pid2, int, type,
 	/*
 	 * One should have enough rights to inspect task details.
 	 */
-	ret = kcmp_lock(&task1->signal->cred_guard_mutex,
-			&task2->signal->cred_guard_mutex);
+	ret = kcmp_lock(&task1->signal->exec_update_mutex,
+			&task2->signal->exec_update_mutex);
 	if (ret)
 		goto err;
 	if (!ptrace_may_access(task1, PTRACE_MODE_READ_REALCREDS) ||
@@ -229,8 +229,8 @@ SYSCALL_DEFINE5(kcmp, pid_t, pid1, pid_t, pid2, int, type,
 	}
 
 err_unlock:
-	kcmp_unlock(&task1->signal->cred_guard_mutex,
-		    &task2->signal->cred_guard_mutex);
+	kcmp_unlock(&task1->signal->exec_update_mutex,
+		    &task2->signal->exec_update_mutex);
 err:
 	put_task_struct(task1);
 	put_task_struct(task2);
diff --git a/kernel/kcov.c b/kernel/kcov.c
index f50354202dbe..6b8368be89c8 100644
--- a/kernel/kcov.c
+++ b/kernel/kcov.c
@@ -86,6 +86,18 @@ static DEFINE_SPINLOCK(kcov_remote_lock);
 static DEFINE_HASHTABLE(kcov_remote_map, 4);
 static struct list_head kcov_remote_areas = LIST_HEAD_INIT(kcov_remote_areas);
 
+struct kcov_percpu_data {
+	void			*irq_area;
+
+	unsigned int		saved_mode;
+	unsigned int		saved_size;
+	void			*saved_area;
+	struct kcov		*saved_kcov;
+	int			saved_sequence;
+};
+
+static DEFINE_PER_CPU(struct kcov_percpu_data, kcov_percpu_data);
+
 /* Must be called with kcov_remote_lock locked. */
 static struct kcov_remote *kcov_remote_find(u64 handle)
 {
@@ -98,6 +110,7 @@ static struct kcov_remote *kcov_remote_find(u64 handle)
 	return NULL;
 }
 
+/* Must be called with kcov_remote_lock locked. */
 static struct kcov_remote *kcov_remote_add(struct kcov *kcov, u64 handle)
 {
 	struct kcov_remote *remote;
@@ -119,16 +132,13 @@ static struct kcov_remote_area *kcov_remote_area_get(unsigned int size)
 	struct kcov_remote_area *area;
 	struct list_head *pos;
 
-	kcov_debug("size = %u\n", size);
 	list_for_each(pos, &kcov_remote_areas) {
 		area = list_entry(pos, struct kcov_remote_area, list);
 		if (area->size == size) {
 			list_del(&area->list);
-			kcov_debug("rv = %px\n", area);
 			return area;
 		}
 	}
-	kcov_debug("rv = NULL\n");
 	return NULL;
 }
 
@@ -136,7 +146,6 @@ static struct kcov_remote_area *kcov_remote_area_get(unsigned int size)
 static void kcov_remote_area_put(struct kcov_remote_area *area,
 					unsigned int size)
 {
-	kcov_debug("area = %px, size = %u\n", area, size);
 	INIT_LIST_HEAD(&area->list);
 	area->size = size;
 	list_add(&area->list, &kcov_remote_areas);
@@ -148,9 +157,10 @@ static notrace bool check_kcov_mode(enum kcov_mode needed_mode, struct task_stru
 
 	/*
 	 * We are interested in code coverage as a function of a syscall inputs,
-	 * so we ignore code executed in interrupts.
+	 * so we ignore code executed in interrupts, unless we are in a remote
+	 * coverage collection section in a softirq.
 	 */
-	if (!in_task())
+	if (!in_task() && !(in_serving_softirq() && t->kcov_softirq))
 		return false;
 	mode = READ_ONCE(t->kcov_mode);
 	/*
@@ -312,23 +322,26 @@ void notrace __sanitizer_cov_trace_switch(u64 val, u64 *cases)
 EXPORT_SYMBOL(__sanitizer_cov_trace_switch);
 #endif /* ifdef CONFIG_KCOV_ENABLE_COMPARISONS */
 
-static void kcov_start(struct task_struct *t, unsigned int size,
-			void *area, enum kcov_mode mode, int sequence)
+static void kcov_start(struct task_struct *t, struct kcov *kcov,
+			unsigned int size, void *area, enum kcov_mode mode,
+			int sequence)
 {
 	kcov_debug("t = %px, size = %u, area = %px\n", t, size, area);
+	t->kcov = kcov;
 	/* Cache in task struct for performance. */
 	t->kcov_size = size;
 	t->kcov_area = area;
+	t->kcov_sequence = sequence;
 	/* See comment in check_kcov_mode(). */
 	barrier();
 	WRITE_ONCE(t->kcov_mode, mode);
-	t->kcov_sequence = sequence;
 }
 
 static void kcov_stop(struct task_struct *t)
 {
 	WRITE_ONCE(t->kcov_mode, KCOV_MODE_DISABLED);
 	barrier();
+	t->kcov = NULL;
 	t->kcov_size = 0;
 	t->kcov_area = NULL;
 }
@@ -336,7 +349,6 @@ static void kcov_stop(struct task_struct *t)
 static void kcov_task_reset(struct task_struct *t)
 {
 	kcov_stop(t);
-	t->kcov = NULL;
 	t->kcov_sequence = 0;
 	t->kcov_handle = 0;
 }
@@ -361,18 +373,18 @@ static void kcov_remote_reset(struct kcov *kcov)
 	int bkt;
 	struct kcov_remote *remote;
 	struct hlist_node *tmp;
+	unsigned long flags;
 
-	spin_lock(&kcov_remote_lock);
+	spin_lock_irqsave(&kcov_remote_lock, flags);
 	hash_for_each_safe(kcov_remote_map, bkt, tmp, remote, hnode) {
 		if (remote->kcov != kcov)
 			continue;
-		kcov_debug("removing handle %llx\n", remote->handle);
 		hash_del(&remote->hnode);
 		kfree(remote);
 	}
 	/* Do reset before unlock to prevent races with kcov_remote_start(). */
 	kcov_reset(kcov);
-	spin_unlock(&kcov_remote_lock);
+	spin_unlock_irqrestore(&kcov_remote_lock, flags);
 }
 
 static void kcov_disable(struct task_struct *t, struct kcov *kcov)
@@ -401,12 +413,13 @@ static void kcov_put(struct kcov *kcov)
 void kcov_task_exit(struct task_struct *t)
 {
 	struct kcov *kcov;
+	unsigned long flags;
 
 	kcov = t->kcov;
 	if (kcov == NULL)
 		return;
 
-	spin_lock(&kcov->lock);
+	spin_lock_irqsave(&kcov->lock, flags);
 	kcov_debug("t = %px, kcov->t = %px\n", t, kcov->t);
 	/*
 	 * For KCOV_ENABLE devices we want to make sure that t->kcov->t == t,
@@ -414,7 +427,8 @@ void kcov_task_exit(struct task_struct *t)
 	 *        WARN_ON(!kcov->remote && kcov->t != t);
 	 *
 	 * For KCOV_REMOTE_ENABLE devices, the exiting task is either:
-	 * 2. A remote task between kcov_remote_start() and kcov_remote_stop().
+	 *
+	 * 1. A remote task between kcov_remote_start() and kcov_remote_stop().
 	 *    In this case we should print a warning right away, since a task
 	 *    shouldn't be exiting when it's in a kcov coverage collection
 	 *    section. Here t points to the task that is collecting remote
@@ -424,18 +438,18 @@ void kcov_task_exit(struct task_struct *t)
 	 *        WARN_ON(kcov->remote && kcov->t != t);
 	 *
 	 * 2. The task that created kcov exiting without calling KCOV_DISABLE,
-	 *    and then again we can make sure that t->kcov->t == t:
+	 *    and then again we make sure that t->kcov->t == t:
 	 *        WARN_ON(kcov->remote && kcov->t != t);
 	 *
 	 * By combining all three checks into one we get:
 	 */
 	if (WARN_ON(kcov->t != t)) {
-		spin_unlock(&kcov->lock);
+		spin_unlock_irqrestore(&kcov->lock, flags);
 		return;
 	}
 	/* Just to not leave dangling references behind. */
 	kcov_disable(t, kcov);
-	spin_unlock(&kcov->lock);
+	spin_unlock_irqrestore(&kcov->lock, flags);
 	kcov_put(kcov);
 }
 
@@ -446,12 +460,13 @@ static int kcov_mmap(struct file *filep, struct vm_area_struct *vma)
 	struct kcov *kcov = vma->vm_file->private_data;
 	unsigned long size, off;
 	struct page *page;
+	unsigned long flags;
 
 	area = vmalloc_user(vma->vm_end - vma->vm_start);
 	if (!area)
 		return -ENOMEM;
 
-	spin_lock(&kcov->lock);
+	spin_lock_irqsave(&kcov->lock, flags);
 	size = kcov->size * sizeof(unsigned long);
 	if (kcov->mode != KCOV_MODE_INIT || vma->vm_pgoff != 0 ||
 	    vma->vm_end - vma->vm_start != size) {
@@ -461,7 +476,7 @@ static int kcov_mmap(struct file *filep, struct vm_area_struct *vma)
 	if (!kcov->area) {
 		kcov->area = area;
 		vma->vm_flags |= VM_DONTEXPAND;
-		spin_unlock(&kcov->lock);
+		spin_unlock_irqrestore(&kcov->lock, flags);
 		for (off = 0; off < size; off += PAGE_SIZE) {
 			page = vmalloc_to_page(kcov->area + off);
 			if (vm_insert_page(vma, vma->vm_start + off, page))
@@ -470,7 +485,7 @@ static int kcov_mmap(struct file *filep, struct vm_area_struct *vma)
 		return 0;
 	}
 exit:
-	spin_unlock(&kcov->lock);
+	spin_unlock_irqrestore(&kcov->lock, flags);
 	vfree(area);
 	return res;
 }
@@ -550,10 +565,10 @@ static int kcov_ioctl_locked(struct kcov *kcov, unsigned int cmd,
 	int mode, i;
 	struct kcov_remote_arg *remote_arg;
 	struct kcov_remote *remote;
+	unsigned long flags;
 
 	switch (cmd) {
 	case KCOV_INIT_TRACE:
-		kcov_debug("KCOV_INIT_TRACE\n");
 		/*
 		 * Enable kcov in trace mode and setup buffer size.
 		 * Must happen before anything else.
@@ -572,7 +587,6 @@ static int kcov_ioctl_locked(struct kcov *kcov, unsigned int cmd,
 		kcov->mode = KCOV_MODE_INIT;
 		return 0;
 	case KCOV_ENABLE:
-		kcov_debug("KCOV_ENABLE\n");
 		/*
 		 * Enable coverage for the current task.
 		 * At this point user must have been enabled trace mode,
@@ -590,15 +604,13 @@ static int kcov_ioctl_locked(struct kcov *kcov, unsigned int cmd,
 			return mode;
 		kcov_fault_in_area(kcov);
 		kcov->mode = mode;
-		kcov_start(t, kcov->size, kcov->area, kcov->mode,
+		kcov_start(t, kcov, kcov->size, kcov->area, kcov->mode,
 				kcov->sequence);
-		t->kcov = kcov;
 		kcov->t = t;
 		/* Put either in kcov_task_exit() or in KCOV_DISABLE. */
 		kcov_get(kcov);
 		return 0;
 	case KCOV_DISABLE:
-		kcov_debug("KCOV_DISABLE\n");
 		/* Disable coverage for the current task. */
 		unused = arg;
 		if (unused != 0 || current->kcov != kcov)
@@ -610,7 +622,6 @@ static int kcov_ioctl_locked(struct kcov *kcov, unsigned int cmd,
 		kcov_put(kcov);
 		return 0;
 	case KCOV_REMOTE_ENABLE:
-		kcov_debug("KCOV_REMOTE_ENABLE\n");
 		if (kcov->mode != KCOV_MODE_INIT || !kcov->area)
 			return -EINVAL;
 		t = current;
@@ -627,41 +638,42 @@ static int kcov_ioctl_locked(struct kcov *kcov, unsigned int cmd,
 		kcov->t = t;
 		kcov->remote = true;
 		kcov->remote_size = remote_arg->area_size;
-		spin_lock(&kcov_remote_lock);
+		spin_lock_irqsave(&kcov_remote_lock, flags);
 		for (i = 0; i < remote_arg->num_handles; i++) {
-			kcov_debug("handle %llx\n", remote_arg->handles[i]);
 			if (!kcov_check_handle(remote_arg->handles[i],
 						false, true, false)) {
-				spin_unlock(&kcov_remote_lock);
+				spin_unlock_irqrestore(&kcov_remote_lock,
+							flags);
 				kcov_disable(t, kcov);
 				return -EINVAL;
 			}
 			remote = kcov_remote_add(kcov, remote_arg->handles[i]);
 			if (IS_ERR(remote)) {
-				spin_unlock(&kcov_remote_lock);
+				spin_unlock_irqrestore(&kcov_remote_lock,
+							flags);
 				kcov_disable(t, kcov);
 				return PTR_ERR(remote);
 			}
 		}
 		if (remote_arg->common_handle) {
-			kcov_debug("common handle %llx\n",
-					remote_arg->common_handle);
 			if (!kcov_check_handle(remote_arg->common_handle,
 						true, false, false)) {
-				spin_unlock(&kcov_remote_lock);
+				spin_unlock_irqrestore(&kcov_remote_lock,
+							flags);
 				kcov_disable(t, kcov);
 				return -EINVAL;
 			}
 			remote = kcov_remote_add(kcov,
 					remote_arg->common_handle);
 			if (IS_ERR(remote)) {
-				spin_unlock(&kcov_remote_lock);
+				spin_unlock_irqrestore(&kcov_remote_lock,
+							flags);
 				kcov_disable(t, kcov);
 				return PTR_ERR(remote);
 			}
 			t->kcov_handle = remote_arg->common_handle;
 		}
-		spin_unlock(&kcov_remote_lock);
+		spin_unlock_irqrestore(&kcov_remote_lock, flags);
 		/* Put either in kcov_task_exit() or in KCOV_DISABLE. */
 		kcov_get(kcov);
 		return 0;
@@ -677,6 +689,7 @@ static long kcov_ioctl(struct file *filep, unsigned int cmd, unsigned long arg)
 	struct kcov_remote_arg *remote_arg = NULL;
 	unsigned int remote_num_handles;
 	unsigned long remote_arg_size;
+	unsigned long flags;
 
 	if (cmd == KCOV_REMOTE_ENABLE) {
 		if (get_user(remote_num_handles, (unsigned __user *)(arg +
@@ -697,9 +710,9 @@ static long kcov_ioctl(struct file *filep, unsigned int cmd, unsigned long arg)
 	}
 
 	kcov = filep->private_data;
-	spin_lock(&kcov->lock);
+	spin_lock_irqsave(&kcov->lock, flags);
 	res = kcov_ioctl_locked(kcov, cmd, arg);
-	spin_unlock(&kcov->lock);
+	spin_unlock_irqrestore(&kcov->lock, flags);
 
 	kfree(remote_arg);
 
@@ -716,8 +729,8 @@ static const struct file_operations kcov_fops = {
 
 /*
  * kcov_remote_start() and kcov_remote_stop() can be used to annotate a section
- * of code in a kernel background thread to allow kcov to be used to collect
- * coverage from that part of code.
+ * of code in a kernel background thread or in a softirq to allow kcov to be
+ * used to collect coverage from that part of code.
  *
  * The handle argument of kcov_remote_start() identifies a code section that is
  * used for coverage collection. A userspace process passes this handle to
@@ -728,9 +741,9 @@ static const struct file_operations kcov_fops = {
  * the type of the kernel thread whose code is being annotated.
  *
  * For global kernel threads that are spawned in a limited number of instances
- * (e.g. one USB hub_event() worker thread is spawned per USB HCD), each
- * instance must be assigned a unique 4-byte instance id. The instance id is
- * then combined with a 1-byte subsystem id to get a handle via
+ * (e.g. one USB hub_event() worker thread is spawned per USB HCD) and for
+ * softirqs, each instance must be assigned a unique 4-byte instance id. The
+ * instance id is then combined with a 1-byte subsystem id to get a handle via
  * kcov_remote_handle(subsystem_id, instance_id).
  *
  * For local kernel threads that are spawned from system calls handler when a
@@ -740,8 +753,8 @@ static const struct file_operations kcov_fops = {
  * kcov_remote_handle() with KCOV_SUBSYSTEM_COMMON as the subsystem id and an
  * arbitrary 4-byte non-zero number as the instance id). This common handle
  * then gets saved into the task_struct of the process that issued the
- * KCOV_REMOTE_ENABLE ioctl. When this proccess issues system calls that spawn
- * kernel threads, the common handle must be retrived via kcov_common_handle()
+ * KCOV_REMOTE_ENABLE ioctl. When this process issues system calls that spawn
+ * kernel threads, the common handle must be retrieved via kcov_common_handle()
  * and passed to the spawned threads via custom annotations. Those kernel
  * threads must in turn be annotated with kcov_remote_start(common_handle) and
  * kcov_remote_stop(). All of the threads that are spawned by the same process
@@ -749,70 +762,136 @@ static const struct file_operations kcov_fops = {
  *
  * See Documentation/dev-tools/kcov.rst for more details.
  *
- * Internally, this function looks up the kcov device associated with the
+ * Internally, kcov_remote_start() looks up the kcov device associated with the
  * provided handle, allocates an area for coverage collection, and saves the
  * pointers to kcov and area into the current task_struct to allow coverage to
- * be collected via __sanitizer_cov_trace_pc()
+ * be collected via __sanitizer_cov_trace_pc().
  * In turns kcov_remote_stop() clears those pointers from task_struct to stop
  * collecting coverage and copies all collected coverage into the kcov area.
  */
+
+static inline bool kcov_mode_enabled(unsigned int mode)
+{
+	return (mode & ~KCOV_IN_CTXSW) != KCOV_MODE_DISABLED;
+}
+
+static void kcov_remote_softirq_start(struct task_struct *t)
+{
+	struct kcov_percpu_data *data = this_cpu_ptr(&kcov_percpu_data);
+	unsigned int mode;
+
+	mode = READ_ONCE(t->kcov_mode);
+	barrier();
+	if (kcov_mode_enabled(mode)) {
+		data->saved_mode = mode;
+		data->saved_size = t->kcov_size;
+		data->saved_area = t->kcov_area;
+		data->saved_sequence = t->kcov_sequence;
+		data->saved_kcov = t->kcov;
+		kcov_stop(t);
+	}
+}
+
+static void kcov_remote_softirq_stop(struct task_struct *t)
+{
+	struct kcov_percpu_data *data = this_cpu_ptr(&kcov_percpu_data);
+
+	if (data->saved_kcov) {
+		kcov_start(t, data->saved_kcov, data->saved_size,
+				data->saved_area, data->saved_mode,
+				data->saved_sequence);
+		data->saved_mode = 0;
+		data->saved_size = 0;
+		data->saved_area = NULL;
+		data->saved_sequence = 0;
+		data->saved_kcov = NULL;
+	}
+}
+
 void kcov_remote_start(u64 handle)
 {
+	struct task_struct *t = current;
 	struct kcov_remote *remote;
+	struct kcov *kcov;
+	unsigned int mode;
 	void *area;
-	struct task_struct *t;
 	unsigned int size;
-	enum kcov_mode mode;
 	int sequence;
+	unsigned long flags;
 
 	if (WARN_ON(!kcov_check_handle(handle, true, true, true)))
 		return;
-	if (WARN_ON(!in_task()))
+	if (!in_task() && !in_serving_softirq())
 		return;
-	t = current;
+
+	local_irq_save(flags);
+
 	/*
-	 * Check that kcov_remote_start is not called twice
-	 * nor called by user tasks (with enabled kcov).
+	 * Check that kcov_remote_start() is not called twice in background
+	 * threads nor called by user tasks (with enabled kcov).
 	 */
-	if (WARN_ON(t->kcov))
+	mode = READ_ONCE(t->kcov_mode);
+	if (WARN_ON(in_task() && kcov_mode_enabled(mode))) {
+		local_irq_restore(flags);
 		return;
-
-	kcov_debug("handle = %llx\n", handle);
+	}
+	/*
+	 * Check that kcov_remote_start() is not called twice in softirqs.
+	 * Note, that kcov_remote_start() can be called from a softirq that
+	 * happened while collecting coverage from a background thread.
+	 */
+	if (WARN_ON(in_serving_softirq() && t->kcov_softirq)) {
+		local_irq_restore(flags);
+		return;
+	}
 
 	spin_lock(&kcov_remote_lock);
 	remote = kcov_remote_find(handle);
 	if (!remote) {
-		kcov_debug("no remote found");
-		spin_unlock(&kcov_remote_lock);
+		spin_unlock_irqrestore(&kcov_remote_lock, flags);
 		return;
 	}
+	kcov_debug("handle = %llx, context: %s\n", handle,
+			in_task() ? "task" : "softirq");
+	kcov = remote->kcov;
 	/* Put in kcov_remote_stop(). */
-	kcov_get(remote->kcov);
-	t->kcov = remote->kcov;
+	kcov_get(kcov);
 	/*
 	 * Read kcov fields before unlock to prevent races with
 	 * KCOV_DISABLE / kcov_remote_reset().
 	 */
-	size = remote->kcov->remote_size;
-	mode = remote->kcov->mode;
-	sequence = remote->kcov->sequence;
-	area = kcov_remote_area_get(size);
-	spin_unlock(&kcov_remote_lock);
+	mode = kcov->mode;
+	sequence = kcov->sequence;
+	if (in_task()) {
+		size = kcov->remote_size;
+		area = kcov_remote_area_get(size);
+	} else {
+		size = CONFIG_KCOV_IRQ_AREA_SIZE;
+		area = this_cpu_ptr(&kcov_percpu_data)->irq_area;
+	}
+	spin_unlock_irqrestore(&kcov_remote_lock, flags);
 
+	/* Can only happen when in_task(). */
 	if (!area) {
 		area = vmalloc(size * sizeof(unsigned long));
 		if (!area) {
-			t->kcov = NULL;
-			kcov_put(remote->kcov);
+			kcov_put(kcov);
 			return;
 		}
 	}
+
+	local_irq_save(flags);
+
 	/* Reset coverage size. */
 	*(u64 *)area = 0;
 
-	kcov_debug("area = %px, size = %u", area, size);
+	if (in_serving_softirq()) {
+		kcov_remote_softirq_start(t);
+		t->kcov_softirq = 1;
+	}
+	kcov_start(t, kcov, size, area, mode, sequence);
 
-	kcov_start(t, size, area, mode, sequence);
+	local_irq_restore(flags);
 
 }
 EXPORT_SYMBOL(kcov_remote_start);
@@ -876,34 +955,67 @@ static void kcov_move_area(enum kcov_mode mode, void *dst_area,
 void kcov_remote_stop(void)
 {
 	struct task_struct *t = current;
-	struct kcov *kcov = t->kcov;
-	void *area = t->kcov_area;
-	unsigned int size = t->kcov_size;
-	int sequence = t->kcov_sequence;
+	struct kcov *kcov;
+	unsigned int mode;
+	void *area;
+	unsigned int size;
+	int sequence;
+	unsigned long flags;
 
-	if (!kcov) {
-		kcov_debug("no kcov found\n");
+	if (!in_task() && !in_serving_softirq())
+		return;
+
+	local_irq_save(flags);
+
+	mode = READ_ONCE(t->kcov_mode);
+	barrier();
+	if (!kcov_mode_enabled(mode)) {
+		local_irq_restore(flags);
+		return;
+	}
+	/*
+	 * When in softirq, check if the corresponding kcov_remote_start()
+	 * actually found the remote handle and started collecting coverage.
+	 */
+	if (in_serving_softirq() && !t->kcov_softirq) {
+		local_irq_restore(flags);
+		return;
+	}
+	/* Make sure that kcov_softirq is only set when in softirq. */
+	if (WARN_ON(!in_serving_softirq() && t->kcov_softirq)) {
+		local_irq_restore(flags);
 		return;
 	}
 
+	kcov = t->kcov;
+	area = t->kcov_area;
+	size = t->kcov_size;
+	sequence = t->kcov_sequence;
+
 	kcov_stop(t);
-	t->kcov = NULL;
+	if (in_serving_softirq()) {
+		t->kcov_softirq = 0;
+		kcov_remote_softirq_stop(t);
+	}
 
 	spin_lock(&kcov->lock);
 	/*
 	 * KCOV_DISABLE could have been called between kcov_remote_start()
-	 * and kcov_remote_stop(), hence the check.
+	 * and kcov_remote_stop(), hence the sequence check.
 	 */
-	kcov_debug("move if: %d == %d && %d\n",
-		sequence, kcov->sequence, (int)kcov->remote);
 	if (sequence == kcov->sequence && kcov->remote)
 		kcov_move_area(kcov->mode, kcov->area, kcov->size, area);
 	spin_unlock(&kcov->lock);
 
-	spin_lock(&kcov_remote_lock);
-	kcov_remote_area_put(area, size);
-	spin_unlock(&kcov_remote_lock);
+	if (in_task()) {
+		spin_lock(&kcov_remote_lock);
+		kcov_remote_area_put(area, size);
+		spin_unlock(&kcov_remote_lock);
+	}
+
+	local_irq_restore(flags);
 
+	/* Get in kcov_remote_start(). */
 	kcov_put(kcov);
 }
 EXPORT_SYMBOL(kcov_remote_stop);
@@ -917,6 +1029,16 @@ EXPORT_SYMBOL(kcov_common_handle);
 
 static int __init kcov_init(void)
 {
+	int cpu;
+
+	for_each_possible_cpu(cpu) {
+		void *area = vmalloc(CONFIG_KCOV_IRQ_AREA_SIZE *
+				sizeof(unsigned long));
+		if (!area)
+			return -ENOMEM;
+		per_cpu_ptr(&kcov_percpu_data, cpu)->irq_area = area;
+	}
+
 	/*
 	 * The kcov debugfs file won't ever get removed and thus,
 	 * there is no need to protect it against removal races. The
diff --git a/kernel/kcsan/Makefile b/kernel/kcsan/Makefile
new file mode 100644
index 000000000000..65ca5539c470
--- /dev/null
+++ b/kernel/kcsan/Makefile
@@ -0,0 +1,17 @@
+# SPDX-License-Identifier: GPL-2.0
+KCSAN_SANITIZE := n
+KCOV_INSTRUMENT := n
+UBSAN_SANITIZE := n
+
+CFLAGS_REMOVE_core.o = $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_debugfs.o = $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_report.o = $(CC_FLAGS_FTRACE)
+
+CFLAGS_core.o := $(call cc-option,-fno-conserve-stack) \
+	-fno-stack-protector -DDISABLE_BRANCH_PROFILING
+
+obj-y := core.o debugfs.o report.o
+obj-$(CONFIG_KCSAN_SELFTEST) += selftest.o
+
+CFLAGS_kcsan-test.o := $(CFLAGS_KCSAN) -g -fno-omit-frame-pointer
+obj-$(CONFIG_KCSAN_TEST) += kcsan-test.o
diff --git a/kernel/kcsan/atomic.h b/kernel/kcsan/atomic.h
new file mode 100644
index 000000000000..75fe701f4127
--- /dev/null
+++ b/kernel/kcsan/atomic.h
@@ -0,0 +1,18 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef _KERNEL_KCSAN_ATOMIC_H
+#define _KERNEL_KCSAN_ATOMIC_H
+
+#include <linux/types.h>
+
+/*
+ * Special rules for certain memory where concurrent conflicting accesses are
+ * common, however, the current convention is to not mark them; returns true if
+ * access to @ptr should be considered atomic. Called from slow-path.
+ */
+static bool kcsan_is_atomic_special(const volatile void *ptr)
+{
+	return false;
+}
+
+#endif /* _KERNEL_KCSAN_ATOMIC_H */
diff --git a/kernel/kcsan/core.c b/kernel/kcsan/core.c
new file mode 100644
index 000000000000..9147ff6a12e5
--- /dev/null
+++ b/kernel/kcsan/core.c
@@ -0,0 +1,881 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/atomic.h>
+#include <linux/bug.h>
+#include <linux/delay.h>
+#include <linux/export.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <linux/moduleparam.h>
+#include <linux/percpu.h>
+#include <linux/preempt.h>
+#include <linux/random.h>
+#include <linux/sched.h>
+#include <linux/uaccess.h>
+
+#include "atomic.h"
+#include "encoding.h"
+#include "kcsan.h"
+
+static bool kcsan_early_enable = IS_ENABLED(CONFIG_KCSAN_EARLY_ENABLE);
+unsigned int kcsan_udelay_task = CONFIG_KCSAN_UDELAY_TASK;
+unsigned int kcsan_udelay_interrupt = CONFIG_KCSAN_UDELAY_INTERRUPT;
+static long kcsan_skip_watch = CONFIG_KCSAN_SKIP_WATCH;
+static bool kcsan_interrupt_watcher = IS_ENABLED(CONFIG_KCSAN_INTERRUPT_WATCHER);
+
+#ifdef MODULE_PARAM_PREFIX
+#undef MODULE_PARAM_PREFIX
+#endif
+#define MODULE_PARAM_PREFIX "kcsan."
+module_param_named(early_enable, kcsan_early_enable, bool, 0);
+module_param_named(udelay_task, kcsan_udelay_task, uint, 0644);
+module_param_named(udelay_interrupt, kcsan_udelay_interrupt, uint, 0644);
+module_param_named(skip_watch, kcsan_skip_watch, long, 0644);
+module_param_named(interrupt_watcher, kcsan_interrupt_watcher, bool, 0444);
+
+bool kcsan_enabled;
+
+/* Per-CPU kcsan_ctx for interrupts */
+static DEFINE_PER_CPU(struct kcsan_ctx, kcsan_cpu_ctx) = {
+	.disable_count		= 0,
+	.atomic_next		= 0,
+	.atomic_nest_count	= 0,
+	.in_flat_atomic		= false,
+	.access_mask		= 0,
+	.scoped_accesses	= {LIST_POISON1, NULL},
+};
+
+/*
+ * Helper macros to index into adjacent slots, starting from address slot
+ * itself, followed by the right and left slots.
+ *
+ * The purpose is 2-fold:
+ *
+ *	1. if during insertion the address slot is already occupied, check if
+ *	   any adjacent slots are free;
+ *	2. accesses that straddle a slot boundary due to size that exceeds a
+ *	   slot's range may check adjacent slots if any watchpoint matches.
+ *
+ * Note that accesses with very large size may still miss a watchpoint; however,
+ * given this should be rare, this is a reasonable trade-off to make, since this
+ * will avoid:
+ *
+ *	1. excessive contention between watchpoint checks and setup;
+ *	2. larger number of simultaneous watchpoints without sacrificing
+ *	   performance.
+ *
+ * Example: SLOT_IDX values for KCSAN_CHECK_ADJACENT=1, where i is [0, 1, 2]:
+ *
+ *   slot=0:  [ 1,  2,  0]
+ *   slot=9:  [10, 11,  9]
+ *   slot=63: [64, 65, 63]
+ */
+#define SLOT_IDX(slot, i) (slot + ((i + KCSAN_CHECK_ADJACENT) % NUM_SLOTS))
+
+/*
+ * SLOT_IDX_FAST is used in the fast-path. Not first checking the address's primary
+ * slot (middle) is fine if we assume that races occur rarely. The set of
+ * indices {SLOT_IDX(slot, i) | i in [0, NUM_SLOTS)} is equivalent to
+ * {SLOT_IDX_FAST(slot, i) | i in [0, NUM_SLOTS)}.
+ */
+#define SLOT_IDX_FAST(slot, i) (slot + i)
+
+/*
+ * Watchpoints, with each entry encoded as defined in encoding.h: in order to be
+ * able to safely update and access a watchpoint without introducing locking
+ * overhead, we encode each watchpoint as a single atomic long. The initial
+ * zero-initialized state matches INVALID_WATCHPOINT.
+ *
+ * Add NUM_SLOTS-1 entries to account for overflow; this helps avoid having to
+ * use more complicated SLOT_IDX_FAST calculation with modulo in the fast-path.
+ */
+static atomic_long_t watchpoints[CONFIG_KCSAN_NUM_WATCHPOINTS + NUM_SLOTS-1];
+
+/*
+ * Instructions to skip watching counter, used in should_watch(). We use a
+ * per-CPU counter to avoid excessive contention.
+ */
+static DEFINE_PER_CPU(long, kcsan_skip);
+
+static __always_inline atomic_long_t *find_watchpoint(unsigned long addr,
+						      size_t size,
+						      bool expect_write,
+						      long *encoded_watchpoint)
+{
+	const int slot = watchpoint_slot(addr);
+	const unsigned long addr_masked = addr & WATCHPOINT_ADDR_MASK;
+	atomic_long_t *watchpoint;
+	unsigned long wp_addr_masked;
+	size_t wp_size;
+	bool is_write;
+	int i;
+
+	BUILD_BUG_ON(CONFIG_KCSAN_NUM_WATCHPOINTS < NUM_SLOTS);
+
+	for (i = 0; i < NUM_SLOTS; ++i) {
+		watchpoint = &watchpoints[SLOT_IDX_FAST(slot, i)];
+		*encoded_watchpoint = atomic_long_read(watchpoint);
+		if (!decode_watchpoint(*encoded_watchpoint, &wp_addr_masked,
+				       &wp_size, &is_write))
+			continue;
+
+		if (expect_write && !is_write)
+			continue;
+
+		/* Check if the watchpoint matches the access. */
+		if (matching_access(wp_addr_masked, wp_size, addr_masked, size))
+			return watchpoint;
+	}
+
+	return NULL;
+}
+
+static inline atomic_long_t *
+insert_watchpoint(unsigned long addr, size_t size, bool is_write)
+{
+	const int slot = watchpoint_slot(addr);
+	const long encoded_watchpoint = encode_watchpoint(addr, size, is_write);
+	atomic_long_t *watchpoint;
+	int i;
+
+	/* Check slot index logic, ensuring we stay within array bounds. */
+	BUILD_BUG_ON(SLOT_IDX(0, 0) != KCSAN_CHECK_ADJACENT);
+	BUILD_BUG_ON(SLOT_IDX(0, KCSAN_CHECK_ADJACENT+1) != 0);
+	BUILD_BUG_ON(SLOT_IDX(CONFIG_KCSAN_NUM_WATCHPOINTS-1, KCSAN_CHECK_ADJACENT) != ARRAY_SIZE(watchpoints)-1);
+	BUILD_BUG_ON(SLOT_IDX(CONFIG_KCSAN_NUM_WATCHPOINTS-1, KCSAN_CHECK_ADJACENT+1) != ARRAY_SIZE(watchpoints) - NUM_SLOTS);
+
+	for (i = 0; i < NUM_SLOTS; ++i) {
+		long expect_val = INVALID_WATCHPOINT;
+
+		/* Try to acquire this slot. */
+		watchpoint = &watchpoints[SLOT_IDX(slot, i)];
+		if (atomic_long_try_cmpxchg_relaxed(watchpoint, &expect_val, encoded_watchpoint))
+			return watchpoint;
+	}
+
+	return NULL;
+}
+
+/*
+ * Return true if watchpoint was successfully consumed, false otherwise.
+ *
+ * This may return false if:
+ *
+ *	1. another thread already consumed the watchpoint;
+ *	2. the thread that set up the watchpoint already removed it;
+ *	3. the watchpoint was removed and then re-used.
+ */
+static __always_inline bool
+try_consume_watchpoint(atomic_long_t *watchpoint, long encoded_watchpoint)
+{
+	return atomic_long_try_cmpxchg_relaxed(watchpoint, &encoded_watchpoint, CONSUMED_WATCHPOINT);
+}
+
+/* Return true if watchpoint was not touched, false if already consumed. */
+static inline bool consume_watchpoint(atomic_long_t *watchpoint)
+{
+	return atomic_long_xchg_relaxed(watchpoint, CONSUMED_WATCHPOINT) != CONSUMED_WATCHPOINT;
+}
+
+/* Remove the watchpoint -- its slot may be reused after. */
+static inline void remove_watchpoint(atomic_long_t *watchpoint)
+{
+	atomic_long_set(watchpoint, INVALID_WATCHPOINT);
+}
+
+static __always_inline struct kcsan_ctx *get_ctx(void)
+{
+	/*
+	 * In interrupts, use raw_cpu_ptr to avoid unnecessary checks, that would
+	 * also result in calls that generate warnings in uaccess regions.
+	 */
+	return in_task() ? &current->kcsan_ctx : raw_cpu_ptr(&kcsan_cpu_ctx);
+}
+
+/* Check scoped accesses; never inline because this is a slow-path! */
+static noinline void kcsan_check_scoped_accesses(void)
+{
+	struct kcsan_ctx *ctx = get_ctx();
+	struct list_head *prev_save = ctx->scoped_accesses.prev;
+	struct kcsan_scoped_access *scoped_access;
+
+	ctx->scoped_accesses.prev = NULL;  /* Avoid recursion. */
+	list_for_each_entry(scoped_access, &ctx->scoped_accesses, list)
+		__kcsan_check_access(scoped_access->ptr, scoped_access->size, scoped_access->type);
+	ctx->scoped_accesses.prev = prev_save;
+}
+
+/* Rules for generic atomic accesses. Called from fast-path. */
+static __always_inline bool
+is_atomic(const volatile void *ptr, size_t size, int type, struct kcsan_ctx *ctx)
+{
+	if (type & KCSAN_ACCESS_ATOMIC)
+		return true;
+
+	/*
+	 * Unless explicitly declared atomic, never consider an assertion access
+	 * as atomic. This allows using them also in atomic regions, such as
+	 * seqlocks, without implicitly changing their semantics.
+	 */
+	if (type & KCSAN_ACCESS_ASSERT)
+		return false;
+
+	if (IS_ENABLED(CONFIG_KCSAN_ASSUME_PLAIN_WRITES_ATOMIC) &&
+	    (type & KCSAN_ACCESS_WRITE) && size <= sizeof(long) &&
+	    IS_ALIGNED((unsigned long)ptr, size))
+		return true; /* Assume aligned writes up to word size are atomic. */
+
+	if (ctx->atomic_next > 0) {
+		/*
+		 * Because we do not have separate contexts for nested
+		 * interrupts, in case atomic_next is set, we simply assume that
+		 * the outer interrupt set atomic_next. In the worst case, we
+		 * will conservatively consider operations as atomic. This is a
+		 * reasonable trade-off to make, since this case should be
+		 * extremely rare; however, even if extremely rare, it could
+		 * lead to false positives otherwise.
+		 */
+		if ((hardirq_count() >> HARDIRQ_SHIFT) < 2)
+			--ctx->atomic_next; /* in task, or outer interrupt */
+		return true;
+	}
+
+	return ctx->atomic_nest_count > 0 || ctx->in_flat_atomic;
+}
+
+static __always_inline bool
+should_watch(const volatile void *ptr, size_t size, int type, struct kcsan_ctx *ctx)
+{
+	/*
+	 * Never set up watchpoints when memory operations are atomic.
+	 *
+	 * Need to check this first, before kcsan_skip check below: (1) atomics
+	 * should not count towards skipped instructions, and (2) to actually
+	 * decrement kcsan_atomic_next for consecutive instruction stream.
+	 */
+	if (is_atomic(ptr, size, type, ctx))
+		return false;
+
+	if (this_cpu_dec_return(kcsan_skip) >= 0)
+		return false;
+
+	/*
+	 * NOTE: If we get here, kcsan_skip must always be reset in slow path
+	 * via reset_kcsan_skip() to avoid underflow.
+	 */
+
+	/* this operation should be watched */
+	return true;
+}
+
+static inline void reset_kcsan_skip(void)
+{
+	long skip_count = kcsan_skip_watch -
+			  (IS_ENABLED(CONFIG_KCSAN_SKIP_WATCH_RANDOMIZE) ?
+				   prandom_u32_max(kcsan_skip_watch) :
+				   0);
+	this_cpu_write(kcsan_skip, skip_count);
+}
+
+static __always_inline bool kcsan_is_enabled(void)
+{
+	return READ_ONCE(kcsan_enabled) && get_ctx()->disable_count == 0;
+}
+
+static inline unsigned int get_delay(void)
+{
+	unsigned int delay = in_task() ? kcsan_udelay_task : kcsan_udelay_interrupt;
+	return delay - (IS_ENABLED(CONFIG_KCSAN_DELAY_RANDOMIZE) ?
+				prandom_u32_max(delay) :
+				0);
+}
+
+void kcsan_save_irqtrace(struct task_struct *task)
+{
+#ifdef CONFIG_TRACE_IRQFLAGS
+	task->kcsan_save_irqtrace = task->irqtrace;
+#endif
+}
+
+void kcsan_restore_irqtrace(struct task_struct *task)
+{
+#ifdef CONFIG_TRACE_IRQFLAGS
+	task->irqtrace = task->kcsan_save_irqtrace;
+#endif
+}
+
+/*
+ * Pull everything together: check_access() below contains the performance
+ * critical operations; the fast-path (including check_access) functions should
+ * all be inlinable by the instrumentation functions.
+ *
+ * The slow-path (kcsan_found_watchpoint, kcsan_setup_watchpoint) are
+ * non-inlinable -- note that, we prefix these with "kcsan_" to ensure they can
+ * be filtered from the stacktrace, as well as give them unique names for the
+ * UACCESS whitelist of objtool. Each function uses user_access_save/restore(),
+ * since they do not access any user memory, but instrumentation is still
+ * emitted in UACCESS regions.
+ */
+
+static noinline void kcsan_found_watchpoint(const volatile void *ptr,
+					    size_t size,
+					    int type,
+					    atomic_long_t *watchpoint,
+					    long encoded_watchpoint)
+{
+	unsigned long flags;
+	bool consumed;
+
+	if (!kcsan_is_enabled())
+		return;
+
+	/*
+	 * The access_mask check relies on value-change comparison. To avoid
+	 * reporting a race where e.g. the writer set up the watchpoint, but the
+	 * reader has access_mask!=0, we have to ignore the found watchpoint.
+	 */
+	if (get_ctx()->access_mask != 0)
+		return;
+
+	/*
+	 * Consume the watchpoint as soon as possible, to minimize the chances
+	 * of !consumed. Consuming the watchpoint must always be guarded by
+	 * kcsan_is_enabled() check, as otherwise we might erroneously
+	 * triggering reports when disabled.
+	 */
+	consumed = try_consume_watchpoint(watchpoint, encoded_watchpoint);
+
+	/* keep this after try_consume_watchpoint */
+	flags = user_access_save();
+
+	if (consumed) {
+		kcsan_save_irqtrace(current);
+		kcsan_report(ptr, size, type, KCSAN_VALUE_CHANGE_MAYBE,
+			     KCSAN_REPORT_CONSUMED_WATCHPOINT,
+			     watchpoint - watchpoints);
+		kcsan_restore_irqtrace(current);
+	} else {
+		/*
+		 * The other thread may not print any diagnostics, as it has
+		 * already removed the watchpoint, or another thread consumed
+		 * the watchpoint before this thread.
+		 */
+		kcsan_counter_inc(KCSAN_COUNTER_REPORT_RACES);
+	}
+
+	if ((type & KCSAN_ACCESS_ASSERT) != 0)
+		kcsan_counter_inc(KCSAN_COUNTER_ASSERT_FAILURES);
+	else
+		kcsan_counter_inc(KCSAN_COUNTER_DATA_RACES);
+
+	user_access_restore(flags);
+}
+
+static noinline void
+kcsan_setup_watchpoint(const volatile void *ptr, size_t size, int type)
+{
+	const bool is_write = (type & KCSAN_ACCESS_WRITE) != 0;
+	const bool is_assert = (type & KCSAN_ACCESS_ASSERT) != 0;
+	atomic_long_t *watchpoint;
+	union {
+		u8 _1;
+		u16 _2;
+		u32 _4;
+		u64 _8;
+	} expect_value;
+	unsigned long access_mask;
+	enum kcsan_value_change value_change = KCSAN_VALUE_CHANGE_MAYBE;
+	unsigned long ua_flags = user_access_save();
+	unsigned long irq_flags = 0;
+
+	/*
+	 * Always reset kcsan_skip counter in slow-path to avoid underflow; see
+	 * should_watch().
+	 */
+	reset_kcsan_skip();
+
+	if (!kcsan_is_enabled())
+		goto out;
+
+	/*
+	 * Special atomic rules: unlikely to be true, so we check them here in
+	 * the slow-path, and not in the fast-path in is_atomic(). Call after
+	 * kcsan_is_enabled(), as we may access memory that is not yet
+	 * initialized during early boot.
+	 */
+	if (!is_assert && kcsan_is_atomic_special(ptr))
+		goto out;
+
+	if (!check_encodable((unsigned long)ptr, size)) {
+		kcsan_counter_inc(KCSAN_COUNTER_UNENCODABLE_ACCESSES);
+		goto out;
+	}
+
+	/*
+	 * Save and restore the IRQ state trace touched by KCSAN, since KCSAN's
+	 * runtime is entered for every memory access, and potentially useful
+	 * information is lost if dirtied by KCSAN.
+	 */
+	kcsan_save_irqtrace(current);
+	if (!kcsan_interrupt_watcher)
+		local_irq_save(irq_flags);
+
+	watchpoint = insert_watchpoint((unsigned long)ptr, size, is_write);
+	if (watchpoint == NULL) {
+		/*
+		 * Out of capacity: the size of 'watchpoints', and the frequency
+		 * with which should_watch() returns true should be tweaked so
+		 * that this case happens very rarely.
+		 */
+		kcsan_counter_inc(KCSAN_COUNTER_NO_CAPACITY);
+		goto out_unlock;
+	}
+
+	kcsan_counter_inc(KCSAN_COUNTER_SETUP_WATCHPOINTS);
+	kcsan_counter_inc(KCSAN_COUNTER_USED_WATCHPOINTS);
+
+	/*
+	 * Read the current value, to later check and infer a race if the data
+	 * was modified via a non-instrumented access, e.g. from a device.
+	 */
+	expect_value._8 = 0;
+	switch (size) {
+	case 1:
+		expect_value._1 = READ_ONCE(*(const u8 *)ptr);
+		break;
+	case 2:
+		expect_value._2 = READ_ONCE(*(const u16 *)ptr);
+		break;
+	case 4:
+		expect_value._4 = READ_ONCE(*(const u32 *)ptr);
+		break;
+	case 8:
+		expect_value._8 = READ_ONCE(*(const u64 *)ptr);
+		break;
+	default:
+		break; /* ignore; we do not diff the values */
+	}
+
+	if (IS_ENABLED(CONFIG_KCSAN_DEBUG)) {
+		kcsan_disable_current();
+		pr_err("KCSAN: watching %s, size: %zu, addr: %px [slot: %d, encoded: %lx]\n",
+		       is_write ? "write" : "read", size, ptr,
+		       watchpoint_slot((unsigned long)ptr),
+		       encode_watchpoint((unsigned long)ptr, size, is_write));
+		kcsan_enable_current();
+	}
+
+	/*
+	 * Delay this thread, to increase probability of observing a racy
+	 * conflicting access.
+	 */
+	udelay(get_delay());
+
+	/*
+	 * Re-read value, and check if it is as expected; if not, we infer a
+	 * racy access.
+	 */
+	access_mask = get_ctx()->access_mask;
+	switch (size) {
+	case 1:
+		expect_value._1 ^= READ_ONCE(*(const u8 *)ptr);
+		if (access_mask)
+			expect_value._1 &= (u8)access_mask;
+		break;
+	case 2:
+		expect_value._2 ^= READ_ONCE(*(const u16 *)ptr);
+		if (access_mask)
+			expect_value._2 &= (u16)access_mask;
+		break;
+	case 4:
+		expect_value._4 ^= READ_ONCE(*(const u32 *)ptr);
+		if (access_mask)
+			expect_value._4 &= (u32)access_mask;
+		break;
+	case 8:
+		expect_value._8 ^= READ_ONCE(*(const u64 *)ptr);
+		if (access_mask)
+			expect_value._8 &= (u64)access_mask;
+		break;
+	default:
+		break; /* ignore; we do not diff the values */
+	}
+
+	/* Were we able to observe a value-change? */
+	if (expect_value._8 != 0)
+		value_change = KCSAN_VALUE_CHANGE_TRUE;
+
+	/* Check if this access raced with another. */
+	if (!consume_watchpoint(watchpoint)) {
+		/*
+		 * Depending on the access type, map a value_change of MAYBE to
+		 * TRUE (always report) or FALSE (never report).
+		 */
+		if (value_change == KCSAN_VALUE_CHANGE_MAYBE) {
+			if (access_mask != 0) {
+				/*
+				 * For access with access_mask, we require a
+				 * value-change, as it is likely that races on
+				 * ~access_mask bits are expected.
+				 */
+				value_change = KCSAN_VALUE_CHANGE_FALSE;
+			} else if (size > 8 || is_assert) {
+				/* Always assume a value-change. */
+				value_change = KCSAN_VALUE_CHANGE_TRUE;
+			}
+		}
+
+		/*
+		 * No need to increment 'data_races' counter, as the racing
+		 * thread already did.
+		 *
+		 * Count 'assert_failures' for each failed ASSERT access,
+		 * therefore both this thread and the racing thread may
+		 * increment this counter.
+		 */
+		if (is_assert && value_change == KCSAN_VALUE_CHANGE_TRUE)
+			kcsan_counter_inc(KCSAN_COUNTER_ASSERT_FAILURES);
+
+		kcsan_report(ptr, size, type, value_change, KCSAN_REPORT_RACE_SIGNAL,
+			     watchpoint - watchpoints);
+	} else if (value_change == KCSAN_VALUE_CHANGE_TRUE) {
+		/* Inferring a race, since the value should not have changed. */
+
+		kcsan_counter_inc(KCSAN_COUNTER_RACES_UNKNOWN_ORIGIN);
+		if (is_assert)
+			kcsan_counter_inc(KCSAN_COUNTER_ASSERT_FAILURES);
+
+		if (IS_ENABLED(CONFIG_KCSAN_REPORT_RACE_UNKNOWN_ORIGIN) || is_assert)
+			kcsan_report(ptr, size, type, KCSAN_VALUE_CHANGE_TRUE,
+				     KCSAN_REPORT_RACE_UNKNOWN_ORIGIN,
+				     watchpoint - watchpoints);
+	}
+
+	/*
+	 * Remove watchpoint; must be after reporting, since the slot may be
+	 * reused after this point.
+	 */
+	remove_watchpoint(watchpoint);
+	kcsan_counter_dec(KCSAN_COUNTER_USED_WATCHPOINTS);
+out_unlock:
+	if (!kcsan_interrupt_watcher)
+		local_irq_restore(irq_flags);
+	kcsan_restore_irqtrace(current);
+out:
+	user_access_restore(ua_flags);
+}
+
+static __always_inline void check_access(const volatile void *ptr, size_t size,
+					 int type)
+{
+	const bool is_write = (type & KCSAN_ACCESS_WRITE) != 0;
+	atomic_long_t *watchpoint;
+	long encoded_watchpoint;
+
+	/*
+	 * Do nothing for 0 sized check; this comparison will be optimized out
+	 * for constant sized instrumentation (__tsan_{read,write}N).
+	 */
+	if (unlikely(size == 0))
+		return;
+
+	/*
+	 * Avoid user_access_save in fast-path: find_watchpoint is safe without
+	 * user_access_save, as the address that ptr points to is only used to
+	 * check if a watchpoint exists; ptr is never dereferenced.
+	 */
+	watchpoint = find_watchpoint((unsigned long)ptr, size, !is_write,
+				     &encoded_watchpoint);
+	/*
+	 * It is safe to check kcsan_is_enabled() after find_watchpoint in the
+	 * slow-path, as long as no state changes that cause a race to be
+	 * detected and reported have occurred until kcsan_is_enabled() is
+	 * checked.
+	 */
+
+	if (unlikely(watchpoint != NULL))
+		kcsan_found_watchpoint(ptr, size, type, watchpoint,
+				       encoded_watchpoint);
+	else {
+		struct kcsan_ctx *ctx = get_ctx(); /* Call only once in fast-path. */
+
+		if (unlikely(should_watch(ptr, size, type, ctx)))
+			kcsan_setup_watchpoint(ptr, size, type);
+		else if (unlikely(ctx->scoped_accesses.prev))
+			kcsan_check_scoped_accesses();
+	}
+}
+
+/* === Public interface ===================================================== */
+
+void __init kcsan_init(void)
+{
+	BUG_ON(!in_task());
+
+	kcsan_debugfs_init();
+
+	/*
+	 * We are in the init task, and no other tasks should be running;
+	 * WRITE_ONCE without memory barrier is sufficient.
+	 */
+	if (kcsan_early_enable)
+		WRITE_ONCE(kcsan_enabled, true);
+}
+
+/* === Exported interface =================================================== */
+
+void kcsan_disable_current(void)
+{
+	++get_ctx()->disable_count;
+}
+EXPORT_SYMBOL(kcsan_disable_current);
+
+void kcsan_enable_current(void)
+{
+	if (get_ctx()->disable_count-- == 0) {
+		/*
+		 * Warn if kcsan_enable_current() calls are unbalanced with
+		 * kcsan_disable_current() calls, which causes disable_count to
+		 * become negative and should not happen.
+		 */
+		kcsan_disable_current(); /* restore to 0, KCSAN still enabled */
+		kcsan_disable_current(); /* disable to generate warning */
+		WARN(1, "Unbalanced %s()", __func__);
+		kcsan_enable_current();
+	}
+}
+EXPORT_SYMBOL(kcsan_enable_current);
+
+void kcsan_enable_current_nowarn(void)
+{
+	if (get_ctx()->disable_count-- == 0)
+		kcsan_disable_current();
+}
+EXPORT_SYMBOL(kcsan_enable_current_nowarn);
+
+void kcsan_nestable_atomic_begin(void)
+{
+	/*
+	 * Do *not* check and warn if we are in a flat atomic region: nestable
+	 * and flat atomic regions are independent from each other.
+	 * See include/linux/kcsan.h: struct kcsan_ctx comments for more
+	 * comments.
+	 */
+
+	++get_ctx()->atomic_nest_count;
+}
+EXPORT_SYMBOL(kcsan_nestable_atomic_begin);
+
+void kcsan_nestable_atomic_end(void)
+{
+	if (get_ctx()->atomic_nest_count-- == 0) {
+		/*
+		 * Warn if kcsan_nestable_atomic_end() calls are unbalanced with
+		 * kcsan_nestable_atomic_begin() calls, which causes
+		 * atomic_nest_count to become negative and should not happen.
+		 */
+		kcsan_nestable_atomic_begin(); /* restore to 0 */
+		kcsan_disable_current(); /* disable to generate warning */
+		WARN(1, "Unbalanced %s()", __func__);
+		kcsan_enable_current();
+	}
+}
+EXPORT_SYMBOL(kcsan_nestable_atomic_end);
+
+void kcsan_flat_atomic_begin(void)
+{
+	get_ctx()->in_flat_atomic = true;
+}
+EXPORT_SYMBOL(kcsan_flat_atomic_begin);
+
+void kcsan_flat_atomic_end(void)
+{
+	get_ctx()->in_flat_atomic = false;
+}
+EXPORT_SYMBOL(kcsan_flat_atomic_end);
+
+void kcsan_atomic_next(int n)
+{
+	get_ctx()->atomic_next = n;
+}
+EXPORT_SYMBOL(kcsan_atomic_next);
+
+void kcsan_set_access_mask(unsigned long mask)
+{
+	get_ctx()->access_mask = mask;
+}
+EXPORT_SYMBOL(kcsan_set_access_mask);
+
+struct kcsan_scoped_access *
+kcsan_begin_scoped_access(const volatile void *ptr, size_t size, int type,
+			  struct kcsan_scoped_access *sa)
+{
+	struct kcsan_ctx *ctx = get_ctx();
+
+	__kcsan_check_access(ptr, size, type);
+
+	ctx->disable_count++; /* Disable KCSAN, in case list debugging is on. */
+
+	INIT_LIST_HEAD(&sa->list);
+	sa->ptr = ptr;
+	sa->size = size;
+	sa->type = type;
+
+	if (!ctx->scoped_accesses.prev) /* Lazy initialize list head. */
+		INIT_LIST_HEAD(&ctx->scoped_accesses);
+	list_add(&sa->list, &ctx->scoped_accesses);
+
+	ctx->disable_count--;
+	return sa;
+}
+EXPORT_SYMBOL(kcsan_begin_scoped_access);
+
+void kcsan_end_scoped_access(struct kcsan_scoped_access *sa)
+{
+	struct kcsan_ctx *ctx = get_ctx();
+
+	if (WARN(!ctx->scoped_accesses.prev, "Unbalanced %s()?", __func__))
+		return;
+
+	ctx->disable_count++; /* Disable KCSAN, in case list debugging is on. */
+
+	list_del(&sa->list);
+	if (list_empty(&ctx->scoped_accesses))
+		/*
+		 * Ensure we do not enter kcsan_check_scoped_accesses()
+		 * slow-path if unnecessary, and avoids requiring list_empty()
+		 * in the fast-path (to avoid a READ_ONCE() and potential
+		 * uaccess warning).
+		 */
+		ctx->scoped_accesses.prev = NULL;
+
+	ctx->disable_count--;
+
+	__kcsan_check_access(sa->ptr, sa->size, sa->type);
+}
+EXPORT_SYMBOL(kcsan_end_scoped_access);
+
+void __kcsan_check_access(const volatile void *ptr, size_t size, int type)
+{
+	check_access(ptr, size, type);
+}
+EXPORT_SYMBOL(__kcsan_check_access);
+
+/*
+ * KCSAN uses the same instrumentation that is emitted by supported compilers
+ * for ThreadSanitizer (TSAN).
+ *
+ * When enabled, the compiler emits instrumentation calls (the functions
+ * prefixed with "__tsan" below) for all loads and stores that it generated;
+ * inline asm is not instrumented.
+ *
+ * Note that, not all supported compiler versions distinguish aligned/unaligned
+ * accesses, but e.g. recent versions of Clang do. We simply alias the unaligned
+ * version to the generic version, which can handle both.
+ */
+
+#define DEFINE_TSAN_READ_WRITE(size)                                           \
+	void __tsan_read##size(void *ptr);                                     \
+	void __tsan_read##size(void *ptr)                                      \
+	{                                                                      \
+		check_access(ptr, size, 0);                                    \
+	}                                                                      \
+	EXPORT_SYMBOL(__tsan_read##size);                                      \
+	void __tsan_unaligned_read##size(void *ptr)                            \
+		__alias(__tsan_read##size);                                    \
+	EXPORT_SYMBOL(__tsan_unaligned_read##size);                            \
+	void __tsan_write##size(void *ptr);                                    \
+	void __tsan_write##size(void *ptr)                                     \
+	{                                                                      \
+		check_access(ptr, size, KCSAN_ACCESS_WRITE);                   \
+	}                                                                      \
+	EXPORT_SYMBOL(__tsan_write##size);                                     \
+	void __tsan_unaligned_write##size(void *ptr)                           \
+		__alias(__tsan_write##size);                                   \
+	EXPORT_SYMBOL(__tsan_unaligned_write##size)
+
+DEFINE_TSAN_READ_WRITE(1);
+DEFINE_TSAN_READ_WRITE(2);
+DEFINE_TSAN_READ_WRITE(4);
+DEFINE_TSAN_READ_WRITE(8);
+DEFINE_TSAN_READ_WRITE(16);
+
+void __tsan_read_range(void *ptr, size_t size);
+void __tsan_read_range(void *ptr, size_t size)
+{
+	check_access(ptr, size, 0);
+}
+EXPORT_SYMBOL(__tsan_read_range);
+
+void __tsan_write_range(void *ptr, size_t size);
+void __tsan_write_range(void *ptr, size_t size)
+{
+	check_access(ptr, size, KCSAN_ACCESS_WRITE);
+}
+EXPORT_SYMBOL(__tsan_write_range);
+
+/*
+ * Use of explicit volatile is generally disallowed [1], however, volatile is
+ * still used in various concurrent context, whether in low-level
+ * synchronization primitives or for legacy reasons.
+ * [1] https://lwn.net/Articles/233479/
+ *
+ * We only consider volatile accesses atomic if they are aligned and would pass
+ * the size-check of compiletime_assert_rwonce_type().
+ */
+#define DEFINE_TSAN_VOLATILE_READ_WRITE(size)                                  \
+	void __tsan_volatile_read##size(void *ptr);                            \
+	void __tsan_volatile_read##size(void *ptr)                             \
+	{                                                                      \
+		const bool is_atomic = size <= sizeof(long long) &&            \
+				       IS_ALIGNED((unsigned long)ptr, size);   \
+		if (IS_ENABLED(CONFIG_KCSAN_IGNORE_ATOMICS) && is_atomic)      \
+			return;                                                \
+		check_access(ptr, size, is_atomic ? KCSAN_ACCESS_ATOMIC : 0);  \
+	}                                                                      \
+	EXPORT_SYMBOL(__tsan_volatile_read##size);                             \
+	void __tsan_unaligned_volatile_read##size(void *ptr)                   \
+		__alias(__tsan_volatile_read##size);                           \
+	EXPORT_SYMBOL(__tsan_unaligned_volatile_read##size);                   \
+	void __tsan_volatile_write##size(void *ptr);                           \
+	void __tsan_volatile_write##size(void *ptr)                            \
+	{                                                                      \
+		const bool is_atomic = size <= sizeof(long long) &&            \
+				       IS_ALIGNED((unsigned long)ptr, size);   \
+		if (IS_ENABLED(CONFIG_KCSAN_IGNORE_ATOMICS) && is_atomic)      \
+			return;                                                \
+		check_access(ptr, size,                                        \
+			     KCSAN_ACCESS_WRITE |                              \
+				     (is_atomic ? KCSAN_ACCESS_ATOMIC : 0));   \
+	}                                                                      \
+	EXPORT_SYMBOL(__tsan_volatile_write##size);                            \
+	void __tsan_unaligned_volatile_write##size(void *ptr)                  \
+		__alias(__tsan_volatile_write##size);                          \
+	EXPORT_SYMBOL(__tsan_unaligned_volatile_write##size)
+
+DEFINE_TSAN_VOLATILE_READ_WRITE(1);
+DEFINE_TSAN_VOLATILE_READ_WRITE(2);
+DEFINE_TSAN_VOLATILE_READ_WRITE(4);
+DEFINE_TSAN_VOLATILE_READ_WRITE(8);
+DEFINE_TSAN_VOLATILE_READ_WRITE(16);
+
+/*
+ * The below are not required by KCSAN, but can still be emitted by the
+ * compiler.
+ */
+void __tsan_func_entry(void *call_pc);
+void __tsan_func_entry(void *call_pc)
+{
+}
+EXPORT_SYMBOL(__tsan_func_entry);
+void __tsan_func_exit(void);
+void __tsan_func_exit(void)
+{
+}
+EXPORT_SYMBOL(__tsan_func_exit);
+void __tsan_init(void);
+void __tsan_init(void)
+{
+}
+EXPORT_SYMBOL(__tsan_init);
diff --git a/kernel/kcsan/debugfs.c b/kernel/kcsan/debugfs.c
new file mode 100644
index 000000000000..023e49c58d55
--- /dev/null
+++ b/kernel/kcsan/debugfs.c
@@ -0,0 +1,349 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/atomic.h>
+#include <linux/bsearch.h>
+#include <linux/bug.h>
+#include <linux/debugfs.h>
+#include <linux/init.h>
+#include <linux/kallsyms.h>
+#include <linux/sched.h>
+#include <linux/seq_file.h>
+#include <linux/slab.h>
+#include <linux/sort.h>
+#include <linux/string.h>
+#include <linux/uaccess.h>
+
+#include "kcsan.h"
+
+/*
+ * Statistics counters.
+ */
+static atomic_long_t counters[KCSAN_COUNTER_COUNT];
+
+/*
+ * Addresses for filtering functions from reporting. This list can be used as a
+ * whitelist or blacklist.
+ */
+static struct {
+	unsigned long	*addrs;		/* array of addresses */
+	size_t		size;		/* current size */
+	int		used;		/* number of elements used */
+	bool		sorted;		/* if elements are sorted */
+	bool		whitelist;	/* if list is a blacklist or whitelist */
+} report_filterlist = {
+	.addrs		= NULL,
+	.size		= 8,		/* small initial size */
+	.used		= 0,
+	.sorted		= false,
+	.whitelist	= false,	/* default is blacklist */
+};
+static DEFINE_SPINLOCK(report_filterlist_lock);
+
+static const char *counter_to_name(enum kcsan_counter_id id)
+{
+	switch (id) {
+	case KCSAN_COUNTER_USED_WATCHPOINTS:		return "used_watchpoints";
+	case KCSAN_COUNTER_SETUP_WATCHPOINTS:		return "setup_watchpoints";
+	case KCSAN_COUNTER_DATA_RACES:			return "data_races";
+	case KCSAN_COUNTER_ASSERT_FAILURES:		return "assert_failures";
+	case KCSAN_COUNTER_NO_CAPACITY:			return "no_capacity";
+	case KCSAN_COUNTER_REPORT_RACES:		return "report_races";
+	case KCSAN_COUNTER_RACES_UNKNOWN_ORIGIN:	return "races_unknown_origin";
+	case KCSAN_COUNTER_UNENCODABLE_ACCESSES:	return "unencodable_accesses";
+	case KCSAN_COUNTER_ENCODING_FALSE_POSITIVES:	return "encoding_false_positives";
+	case KCSAN_COUNTER_COUNT:
+		BUG();
+	}
+	return NULL;
+}
+
+void kcsan_counter_inc(enum kcsan_counter_id id)
+{
+	atomic_long_inc(&counters[id]);
+}
+
+void kcsan_counter_dec(enum kcsan_counter_id id)
+{
+	atomic_long_dec(&counters[id]);
+}
+
+/*
+ * The microbenchmark allows benchmarking KCSAN core runtime only. To run
+ * multiple threads, pipe 'microbench=<iters>' from multiple tasks into the
+ * debugfs file. This will not generate any conflicts, and tests fast-path only.
+ */
+static noinline void microbenchmark(unsigned long iters)
+{
+	const struct kcsan_ctx ctx_save = current->kcsan_ctx;
+	const bool was_enabled = READ_ONCE(kcsan_enabled);
+	cycles_t cycles;
+
+	/* We may have been called from an atomic region; reset context. */
+	memset(&current->kcsan_ctx, 0, sizeof(current->kcsan_ctx));
+	/*
+	 * Disable to benchmark fast-path for all accesses, and (expected
+	 * negligible) call into slow-path, but never set up watchpoints.
+	 */
+	WRITE_ONCE(kcsan_enabled, false);
+
+	pr_info("KCSAN: %s begin | iters: %lu\n", __func__, iters);
+
+	cycles = get_cycles();
+	while (iters--) {
+		unsigned long addr = iters & ((PAGE_SIZE << 8) - 1);
+		int type = !(iters & 0x7f) ? KCSAN_ACCESS_ATOMIC :
+				(!(iters & 0xf) ? KCSAN_ACCESS_WRITE : 0);
+		__kcsan_check_access((void *)addr, sizeof(long), type);
+	}
+	cycles = get_cycles() - cycles;
+
+	pr_info("KCSAN: %s end   | cycles: %llu\n", __func__, cycles);
+
+	WRITE_ONCE(kcsan_enabled, was_enabled);
+	/* restore context */
+	current->kcsan_ctx = ctx_save;
+}
+
+/*
+ * Simple test to create conflicting accesses. Write 'test=<iters>' to KCSAN's
+ * debugfs file from multiple tasks to generate real conflicts and show reports.
+ */
+static long test_dummy;
+static long test_flags;
+static long test_scoped;
+static noinline void test_thread(unsigned long iters)
+{
+	const long CHANGE_BITS = 0xff00ff00ff00ff00L;
+	const struct kcsan_ctx ctx_save = current->kcsan_ctx;
+	cycles_t cycles;
+
+	/* We may have been called from an atomic region; reset context. */
+	memset(&current->kcsan_ctx, 0, sizeof(current->kcsan_ctx));
+
+	pr_info("KCSAN: %s begin | iters: %lu\n", __func__, iters);
+	pr_info("test_dummy@%px, test_flags@%px, test_scoped@%px,\n",
+		&test_dummy, &test_flags, &test_scoped);
+
+	cycles = get_cycles();
+	while (iters--) {
+		/* These all should generate reports. */
+		__kcsan_check_read(&test_dummy, sizeof(test_dummy));
+		ASSERT_EXCLUSIVE_WRITER(test_dummy);
+		ASSERT_EXCLUSIVE_ACCESS(test_dummy);
+
+		ASSERT_EXCLUSIVE_BITS(test_flags, ~CHANGE_BITS); /* no report */
+		__kcsan_check_read(&test_flags, sizeof(test_flags)); /* no report */
+
+		ASSERT_EXCLUSIVE_BITS(test_flags, CHANGE_BITS); /* report */
+		__kcsan_check_read(&test_flags, sizeof(test_flags)); /* no report */
+
+		/* not actually instrumented */
+		WRITE_ONCE(test_dummy, iters);  /* to observe value-change */
+		__kcsan_check_write(&test_dummy, sizeof(test_dummy));
+
+		test_flags ^= CHANGE_BITS; /* generate value-change */
+		__kcsan_check_write(&test_flags, sizeof(test_flags));
+
+		BUG_ON(current->kcsan_ctx.scoped_accesses.prev);
+		{
+			/* Should generate reports anywhere in this block. */
+			ASSERT_EXCLUSIVE_WRITER_SCOPED(test_scoped);
+			ASSERT_EXCLUSIVE_ACCESS_SCOPED(test_scoped);
+			BUG_ON(!current->kcsan_ctx.scoped_accesses.prev);
+			/* Unrelated accesses. */
+			__kcsan_check_access(&cycles, sizeof(cycles), 0);
+			__kcsan_check_access(&cycles, sizeof(cycles), KCSAN_ACCESS_ATOMIC);
+		}
+		BUG_ON(current->kcsan_ctx.scoped_accesses.prev);
+	}
+	cycles = get_cycles() - cycles;
+
+	pr_info("KCSAN: %s end   | cycles: %llu\n", __func__, cycles);
+
+	/* restore context */
+	current->kcsan_ctx = ctx_save;
+}
+
+static int cmp_filterlist_addrs(const void *rhs, const void *lhs)
+{
+	const unsigned long a = *(const unsigned long *)rhs;
+	const unsigned long b = *(const unsigned long *)lhs;
+
+	return a < b ? -1 : a == b ? 0 : 1;
+}
+
+bool kcsan_skip_report_debugfs(unsigned long func_addr)
+{
+	unsigned long symbolsize, offset;
+	unsigned long flags;
+	bool ret = false;
+
+	if (!kallsyms_lookup_size_offset(func_addr, &symbolsize, &offset))
+		return false;
+	func_addr -= offset; /* Get function start */
+
+	spin_lock_irqsave(&report_filterlist_lock, flags);
+	if (report_filterlist.used == 0)
+		goto out;
+
+	/* Sort array if it is unsorted, and then do a binary search. */
+	if (!report_filterlist.sorted) {
+		sort(report_filterlist.addrs, report_filterlist.used,
+		     sizeof(unsigned long), cmp_filterlist_addrs, NULL);
+		report_filterlist.sorted = true;
+	}
+	ret = !!bsearch(&func_addr, report_filterlist.addrs,
+			report_filterlist.used, sizeof(unsigned long),
+			cmp_filterlist_addrs);
+	if (report_filterlist.whitelist)
+		ret = !ret;
+
+out:
+	spin_unlock_irqrestore(&report_filterlist_lock, flags);
+	return ret;
+}
+
+static void set_report_filterlist_whitelist(bool whitelist)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&report_filterlist_lock, flags);
+	report_filterlist.whitelist = whitelist;
+	spin_unlock_irqrestore(&report_filterlist_lock, flags);
+}
+
+/* Returns 0 on success, error-code otherwise. */
+static ssize_t insert_report_filterlist(const char *func)
+{
+	unsigned long flags;
+	unsigned long addr = kallsyms_lookup_name(func);
+	ssize_t ret = 0;
+
+	if (!addr) {
+		pr_err("KCSAN: could not find function: '%s'\n", func);
+		return -ENOENT;
+	}
+
+	spin_lock_irqsave(&report_filterlist_lock, flags);
+
+	if (report_filterlist.addrs == NULL) {
+		/* initial allocation */
+		report_filterlist.addrs =
+			kmalloc_array(report_filterlist.size,
+				      sizeof(unsigned long), GFP_ATOMIC);
+		if (report_filterlist.addrs == NULL) {
+			ret = -ENOMEM;
+			goto out;
+		}
+	} else if (report_filterlist.used == report_filterlist.size) {
+		/* resize filterlist */
+		size_t new_size = report_filterlist.size * 2;
+		unsigned long *new_addrs =
+			krealloc(report_filterlist.addrs,
+				 new_size * sizeof(unsigned long), GFP_ATOMIC);
+
+		if (new_addrs == NULL) {
+			/* leave filterlist itself untouched */
+			ret = -ENOMEM;
+			goto out;
+		}
+
+		report_filterlist.size = new_size;
+		report_filterlist.addrs = new_addrs;
+	}
+
+	/* Note: deduplicating should be done in userspace. */
+	report_filterlist.addrs[report_filterlist.used++] =
+		kallsyms_lookup_name(func);
+	report_filterlist.sorted = false;
+
+out:
+	spin_unlock_irqrestore(&report_filterlist_lock, flags);
+
+	return ret;
+}
+
+static int show_info(struct seq_file *file, void *v)
+{
+	int i;
+	unsigned long flags;
+
+	/* show stats */
+	seq_printf(file, "enabled: %i\n", READ_ONCE(kcsan_enabled));
+	for (i = 0; i < KCSAN_COUNTER_COUNT; ++i)
+		seq_printf(file, "%s: %ld\n", counter_to_name(i),
+			   atomic_long_read(&counters[i]));
+
+	/* show filter functions, and filter type */
+	spin_lock_irqsave(&report_filterlist_lock, flags);
+	seq_printf(file, "\n%s functions: %s\n",
+		   report_filterlist.whitelist ? "whitelisted" : "blacklisted",
+		   report_filterlist.used == 0 ? "none" : "");
+	for (i = 0; i < report_filterlist.used; ++i)
+		seq_printf(file, " %ps\n", (void *)report_filterlist.addrs[i]);
+	spin_unlock_irqrestore(&report_filterlist_lock, flags);
+
+	return 0;
+}
+
+static int debugfs_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, show_info, NULL);
+}
+
+static ssize_t
+debugfs_write(struct file *file, const char __user *buf, size_t count, loff_t *off)
+{
+	char kbuf[KSYM_NAME_LEN];
+	char *arg;
+	int read_len = count < (sizeof(kbuf) - 1) ? count : (sizeof(kbuf) - 1);
+
+	if (copy_from_user(kbuf, buf, read_len))
+		return -EFAULT;
+	kbuf[read_len] = '\0';
+	arg = strstrip(kbuf);
+
+	if (!strcmp(arg, "on")) {
+		WRITE_ONCE(kcsan_enabled, true);
+	} else if (!strcmp(arg, "off")) {
+		WRITE_ONCE(kcsan_enabled, false);
+	} else if (!strncmp(arg, "microbench=", sizeof("microbench=") - 1)) {
+		unsigned long iters;
+
+		if (kstrtoul(&arg[sizeof("microbench=") - 1], 0, &iters))
+			return -EINVAL;
+		microbenchmark(iters);
+	} else if (!strncmp(arg, "test=", sizeof("test=") - 1)) {
+		unsigned long iters;
+
+		if (kstrtoul(&arg[sizeof("test=") - 1], 0, &iters))
+			return -EINVAL;
+		test_thread(iters);
+	} else if (!strcmp(arg, "whitelist")) {
+		set_report_filterlist_whitelist(true);
+	} else if (!strcmp(arg, "blacklist")) {
+		set_report_filterlist_whitelist(false);
+	} else if (arg[0] == '!') {
+		ssize_t ret = insert_report_filterlist(&arg[1]);
+
+		if (ret < 0)
+			return ret;
+	} else {
+		return -EINVAL;
+	}
+
+	return count;
+}
+
+static const struct file_operations debugfs_ops =
+{
+	.read	 = seq_read,
+	.open	 = debugfs_open,
+	.write	 = debugfs_write,
+	.release = single_release
+};
+
+void __init kcsan_debugfs_init(void)
+{
+	debugfs_create_file("kcsan", 0644, NULL, NULL, &debugfs_ops);
+}
diff --git a/kernel/kcsan/encoding.h b/kernel/kcsan/encoding.h
new file mode 100644
index 000000000000..f03562aaf2eb
--- /dev/null
+++ b/kernel/kcsan/encoding.h
@@ -0,0 +1,95 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef _KERNEL_KCSAN_ENCODING_H
+#define _KERNEL_KCSAN_ENCODING_H
+
+#include <linux/bits.h>
+#include <linux/log2.h>
+#include <linux/mm.h>
+
+#include "kcsan.h"
+
+#define SLOT_RANGE PAGE_SIZE
+
+#define INVALID_WATCHPOINT  0
+#define CONSUMED_WATCHPOINT 1
+
+/*
+ * The maximum useful size of accesses for which we set up watchpoints is the
+ * max range of slots we check on an access.
+ */
+#define MAX_ENCODABLE_SIZE (SLOT_RANGE * (1 + KCSAN_CHECK_ADJACENT))
+
+/*
+ * Number of bits we use to store size info.
+ */
+#define WATCHPOINT_SIZE_BITS bits_per(MAX_ENCODABLE_SIZE)
+/*
+ * This encoding for addresses discards the upper (1 for is-write + SIZE_BITS);
+ * however, most 64-bit architectures do not use the full 64-bit address space.
+ * Also, in order for a false positive to be observable 2 things need to happen:
+ *
+ *	1. different addresses but with the same encoded address race;
+ *	2. and both map onto the same watchpoint slots;
+ *
+ * Both these are assumed to be very unlikely. However, in case it still happens
+ * happens, the report logic will filter out the false positive (see report.c).
+ */
+#define WATCHPOINT_ADDR_BITS (BITS_PER_LONG-1 - WATCHPOINT_SIZE_BITS)
+
+/*
+ * Masks to set/retrieve the encoded data.
+ */
+#define WATCHPOINT_WRITE_MASK BIT(BITS_PER_LONG-1)
+#define WATCHPOINT_SIZE_MASK                                                   \
+	GENMASK(BITS_PER_LONG-2, BITS_PER_LONG-2 - WATCHPOINT_SIZE_BITS)
+#define WATCHPOINT_ADDR_MASK                                                   \
+	GENMASK(BITS_PER_LONG-3 - WATCHPOINT_SIZE_BITS, 0)
+
+static inline bool check_encodable(unsigned long addr, size_t size)
+{
+	return size <= MAX_ENCODABLE_SIZE;
+}
+
+static inline long
+encode_watchpoint(unsigned long addr, size_t size, bool is_write)
+{
+	return (long)((is_write ? WATCHPOINT_WRITE_MASK : 0) |
+		      (size << WATCHPOINT_ADDR_BITS) |
+		      (addr & WATCHPOINT_ADDR_MASK));
+}
+
+static __always_inline bool decode_watchpoint(long watchpoint,
+					      unsigned long *addr_masked,
+					      size_t *size,
+					      bool *is_write)
+{
+	if (watchpoint == INVALID_WATCHPOINT ||
+	    watchpoint == CONSUMED_WATCHPOINT)
+		return false;
+
+	*addr_masked =    (unsigned long)watchpoint & WATCHPOINT_ADDR_MASK;
+	*size	     =   ((unsigned long)watchpoint & WATCHPOINT_SIZE_MASK) >> WATCHPOINT_ADDR_BITS;
+	*is_write    = !!((unsigned long)watchpoint & WATCHPOINT_WRITE_MASK);
+
+	return true;
+}
+
+/*
+ * Return watchpoint slot for an address.
+ */
+static __always_inline int watchpoint_slot(unsigned long addr)
+{
+	return (addr / PAGE_SIZE) % CONFIG_KCSAN_NUM_WATCHPOINTS;
+}
+
+static __always_inline bool matching_access(unsigned long addr1, size_t size1,
+					    unsigned long addr2, size_t size2)
+{
+	unsigned long end_range1 = addr1 + size1 - 1;
+	unsigned long end_range2 = addr2 + size2 - 1;
+
+	return addr1 <= end_range2 && addr2 <= end_range1;
+}
+
+#endif /* _KERNEL_KCSAN_ENCODING_H */
diff --git a/kernel/kcsan/kcsan-test.c b/kernel/kcsan/kcsan-test.c
new file mode 100644
index 000000000000..fed6fcb5768c
--- /dev/null
+++ b/kernel/kcsan/kcsan-test.c
@@ -0,0 +1,1107 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * KCSAN test with various race scenarious to test runtime behaviour. Since the
+ * interface with which KCSAN's reports are obtained is via the console, this is
+ * the output we should verify. For each test case checks the presence (or
+ * absence) of generated reports. Relies on 'console' tracepoint to capture
+ * reports as they appear in the kernel log.
+ *
+ * Makes use of KUnit for test organization, and the Torture framework for test
+ * thread control.
+ *
+ * Copyright (C) 2020, Google LLC.
+ * Author: Marco Elver <elver@google.com>
+ */
+
+#include <kunit/test.h>
+#include <linux/jiffies.h>
+#include <linux/kcsan-checks.h>
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/seqlock.h>
+#include <linux/spinlock.h>
+#include <linux/string.h>
+#include <linux/timer.h>
+#include <linux/torture.h>
+#include <linux/tracepoint.h>
+#include <linux/types.h>
+#include <trace/events/printk.h>
+
+/* Points to current test-case memory access "kernels". */
+static void (*access_kernels[2])(void);
+
+static struct task_struct **threads; /* Lists of threads. */
+static unsigned long end_time;       /* End time of test. */
+
+/* Report as observed from console. */
+static struct {
+	spinlock_t lock;
+	int nlines;
+	char lines[3][512];
+} observed = {
+	.lock = __SPIN_LOCK_UNLOCKED(observed.lock),
+};
+
+/* Setup test checking loop. */
+static __no_kcsan inline void
+begin_test_checks(void (*func1)(void), void (*func2)(void))
+{
+	kcsan_disable_current();
+
+	/*
+	 * Require at least as long as KCSAN_REPORT_ONCE_IN_MS, to ensure at
+	 * least one race is reported.
+	 */
+	end_time = jiffies + msecs_to_jiffies(CONFIG_KCSAN_REPORT_ONCE_IN_MS + 500);
+
+	/* Signal start; release potential initialization of shared data. */
+	smp_store_release(&access_kernels[0], func1);
+	smp_store_release(&access_kernels[1], func2);
+}
+
+/* End test checking loop. */
+static __no_kcsan inline bool
+end_test_checks(bool stop)
+{
+	if (!stop && time_before(jiffies, end_time)) {
+		/* Continue checking */
+		might_sleep();
+		return false;
+	}
+
+	kcsan_enable_current();
+	return true;
+}
+
+/*
+ * Probe for console output: checks if a race was reported, and obtains observed
+ * lines of interest.
+ */
+__no_kcsan
+static void probe_console(void *ignore, const char *buf, size_t len)
+{
+	unsigned long flags;
+	int nlines;
+
+	/*
+	 * Note that KCSAN reports under a global lock, so we do not risk the
+	 * possibility of having multiple reports interleaved. If that were the
+	 * case, we'd expect tests to fail.
+	 */
+
+	spin_lock_irqsave(&observed.lock, flags);
+	nlines = observed.nlines;
+
+	if (strnstr(buf, "BUG: KCSAN: ", len) && strnstr(buf, "test_", len)) {
+		/*
+		 * KCSAN report and related to the test.
+		 *
+		 * The provided @buf is not NUL-terminated; copy no more than
+		 * @len bytes and let strscpy() add the missing NUL-terminator.
+		 */
+		strscpy(observed.lines[0], buf, min(len + 1, sizeof(observed.lines[0])));
+		nlines = 1;
+	} else if ((nlines == 1 || nlines == 2) && strnstr(buf, "bytes by", len)) {
+		strscpy(observed.lines[nlines++], buf, min(len + 1, sizeof(observed.lines[0])));
+
+		if (strnstr(buf, "race at unknown origin", len)) {
+			if (WARN_ON(nlines != 2))
+				goto out;
+
+			/* No second line of interest. */
+			strcpy(observed.lines[nlines++], "<none>");
+		}
+	}
+
+out:
+	WRITE_ONCE(observed.nlines, nlines); /* Publish new nlines. */
+	spin_unlock_irqrestore(&observed.lock, flags);
+}
+
+/* Check if a report related to the test exists. */
+__no_kcsan
+static bool report_available(void)
+{
+	return READ_ONCE(observed.nlines) == ARRAY_SIZE(observed.lines);
+}
+
+/* Report information we expect in a report. */
+struct expect_report {
+	/* Access information of both accesses. */
+	struct {
+		void *fn;    /* Function pointer to expected function of top frame. */
+		void *addr;  /* Address of access; unchecked if NULL. */
+		size_t size; /* Size of access; unchecked if @addr is NULL. */
+		int type;    /* Access type, see KCSAN_ACCESS definitions. */
+	} access[2];
+};
+
+/* Check observed report matches information in @r. */
+__no_kcsan
+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;
+	const char *end;
+	char *cur;
+	int i;
+
+	/* Doubled-checked locking. */
+	if (!report_available())
+		return false;
+
+	/* Generate expected report contents. */
+
+	/* Title */
+	cur = expect[0];
+	end = &expect[0][sizeof(expect[0]) - 1];
+	cur += scnprintf(cur, end - cur, "BUG: KCSAN: %s in ",
+			 is_assert ? "assert: race" : "data-race");
+	if (r->access[1].fn) {
+		char tmp[2][64];
+		int cmp;
+
+		/* Expect lexographically sorted function names in title. */
+		scnprintf(tmp[0], sizeof(tmp[0]), "%pS", r->access[0].fn);
+		scnprintf(tmp[1], sizeof(tmp[1]), "%pS", r->access[1].fn);
+		cmp = strcmp(tmp[0], tmp[1]);
+		cur += scnprintf(cur, end - cur, "%ps / %ps",
+				 cmp < 0 ? r->access[0].fn : r->access[1].fn,
+				 cmp < 0 ? r->access[1].fn : r->access[0].fn);
+	} else {
+		scnprintf(cur, end - cur, "%pS", r->access[0].fn);
+		/* The exact offset won't match, remove it. */
+		cur = strchr(expect[0], '+');
+		if (cur)
+			*cur = '\0';
+	}
+
+	/* Access 1 */
+	cur = expect[1];
+	end = &expect[1][sizeof(expect[1]) - 1];
+	if (!r->access[1].fn)
+		cur += scnprintf(cur, end - cur, "race at unknown origin, with ");
+
+	/* Access 1 & 2 */
+	for (i = 0; i < 2; ++i) {
+		const char *const access_type =
+			(r->access[i].type & KCSAN_ACCESS_ASSERT) ?
+				((r->access[i].type & KCSAN_ACCESS_WRITE) ?
+					 "assert no accesses" :
+					 "assert no writes") :
+				((r->access[i].type & KCSAN_ACCESS_WRITE) ?
+					 "write" :
+					 "read");
+		const char *const access_type_aux =
+			(r->access[i].type & KCSAN_ACCESS_ATOMIC) ?
+				" (marked)" :
+				((r->access[i].type & KCSAN_ACCESS_SCOPED) ?
+					 " (scoped)" :
+					 "");
+
+		if (i == 1) {
+			/* Access 2 */
+			cur = expect[2];
+			end = &expect[2][sizeof(expect[2]) - 1];
+
+			if (!r->access[1].fn) {
+				/* Dummy string if no second access is available. */
+				strcpy(cur, "<none>");
+				break;
+			}
+		}
+
+		cur += scnprintf(cur, end - cur, "%s%s to ", access_type,
+				 access_type_aux);
+
+		if (r->access[i].addr) /* Address is optional. */
+			cur += scnprintf(cur, end - cur, "0x%px of %zu bytes",
+					 r->access[i].addr, r->access[i].size);
+	}
+
+	spin_lock_irqsave(&observed.lock, flags);
+	if (!report_available())
+		goto out; /* A new report is being captured. */
+
+	/* Finally match expected output to what we actually observed. */
+	ret = strstr(observed.lines[0], expect[0]) &&
+	      /* Access info may appear in any order. */
+	      ((strstr(observed.lines[1], expect[1]) &&
+		strstr(observed.lines[2], expect[2])) ||
+	       (strstr(observed.lines[1], expect[2]) &&
+		strstr(observed.lines[2], expect[1])));
+out:
+	spin_unlock_irqrestore(&observed.lock, flags);
+	return ret;
+}
+
+/* ===== Test kernels ===== */
+
+static long test_sink;
+static long test_var;
+/* @test_array should be large enough to fall into multiple watchpoint slots. */
+static long test_array[3 * PAGE_SIZE / sizeof(long)];
+static struct {
+	long val[8];
+} test_struct;
+static DEFINE_SEQLOCK(test_seqlock);
+
+/*
+ * Helper to avoid compiler optimizing out reads, and to generate source values
+ * for writes.
+ */
+__no_kcsan
+static noinline void sink_value(long v) { WRITE_ONCE(test_sink, v); }
+
+static noinline void test_kernel_read(void) { sink_value(test_var); }
+
+static noinline void test_kernel_write(void)
+{
+	test_var = READ_ONCE_NOCHECK(test_sink) + 1;
+}
+
+static noinline void test_kernel_write_nochange(void) { test_var = 42; }
+
+/* Suffixed by value-change exception filter. */
+static noinline void test_kernel_write_nochange_rcu(void) { test_var = 42; }
+
+static noinline void test_kernel_read_atomic(void)
+{
+	sink_value(READ_ONCE(test_var));
+}
+
+static noinline void test_kernel_write_atomic(void)
+{
+	WRITE_ONCE(test_var, READ_ONCE_NOCHECK(test_sink) + 1);
+}
+
+__no_kcsan
+static noinline void test_kernel_write_uninstrumented(void) { test_var++; }
+
+static noinline void test_kernel_data_race(void) { data_race(test_var++); }
+
+static noinline void test_kernel_assert_writer(void)
+{
+	ASSERT_EXCLUSIVE_WRITER(test_var);
+}
+
+static noinline void test_kernel_assert_access(void)
+{
+	ASSERT_EXCLUSIVE_ACCESS(test_var);
+}
+
+#define TEST_CHANGE_BITS 0xff00ff00
+
+static noinline void test_kernel_change_bits(void)
+{
+	if (IS_ENABLED(CONFIG_KCSAN_IGNORE_ATOMICS)) {
+		/*
+		 * Avoid race of unknown origin for this test, just pretend they
+		 * are atomic.
+		 */
+		kcsan_nestable_atomic_begin();
+		test_var ^= TEST_CHANGE_BITS;
+		kcsan_nestable_atomic_end();
+	} else
+		WRITE_ONCE(test_var, READ_ONCE(test_var) ^ TEST_CHANGE_BITS);
+}
+
+static noinline void test_kernel_assert_bits_change(void)
+{
+	ASSERT_EXCLUSIVE_BITS(test_var, TEST_CHANGE_BITS);
+}
+
+static noinline void test_kernel_assert_bits_nochange(void)
+{
+	ASSERT_EXCLUSIVE_BITS(test_var, ~TEST_CHANGE_BITS);
+}
+
+/* To check that scoped assertions do trigger anywhere in scope. */
+static noinline void test_enter_scope(void)
+{
+	int x = 0;
+
+	/* Unrelated accesses to scoped assert. */
+	READ_ONCE(test_sink);
+	kcsan_check_read(&x, sizeof(x));
+}
+
+static noinline void test_kernel_assert_writer_scoped(void)
+{
+	ASSERT_EXCLUSIVE_WRITER_SCOPED(test_var);
+	test_enter_scope();
+}
+
+static noinline void test_kernel_assert_access_scoped(void)
+{
+	ASSERT_EXCLUSIVE_ACCESS_SCOPED(test_var);
+	test_enter_scope();
+}
+
+static noinline void test_kernel_rmw_array(void)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(test_array); ++i)
+		test_array[i]++;
+}
+
+static noinline void test_kernel_write_struct(void)
+{
+	kcsan_check_write(&test_struct, sizeof(test_struct));
+	kcsan_disable_current();
+	test_struct.val[3]++; /* induce value change */
+	kcsan_enable_current();
+}
+
+static noinline void test_kernel_write_struct_part(void)
+{
+	test_struct.val[3] = 42;
+}
+
+static noinline void test_kernel_read_struct_zero_size(void)
+{
+	kcsan_check_read(&test_struct.val[3], 0);
+}
+
+static noinline void test_kernel_jiffies_reader(void)
+{
+	sink_value((long)jiffies);
+}
+
+static noinline void test_kernel_seqlock_reader(void)
+{
+	unsigned int seq;
+
+	do {
+		seq = read_seqbegin(&test_seqlock);
+		sink_value(test_var);
+	} while (read_seqretry(&test_seqlock, seq));
+}
+
+static noinline void test_kernel_seqlock_writer(void)
+{
+	unsigned long flags;
+
+	write_seqlock_irqsave(&test_seqlock, flags);
+	test_var++;
+	write_sequnlock_irqrestore(&test_seqlock, flags);
+}
+
+/* ===== Test cases ===== */
+
+/* Simple test with normal data race. */
+__no_kcsan
+static void test_basic(struct kunit *test)
+{
+	const struct expect_report expect = {
+		.access = {
+			{ test_kernel_write, &test_var, sizeof(test_var), KCSAN_ACCESS_WRITE },
+			{ test_kernel_read, &test_var, sizeof(test_var), 0 },
+		},
+	};
+	static const struct expect_report never = {
+		.access = {
+			{ test_kernel_read, &test_var, sizeof(test_var), 0 },
+			{ test_kernel_read, &test_var, sizeof(test_var), 0 },
+		},
+	};
+	bool match_expect = false;
+	bool match_never = false;
+
+	begin_test_checks(test_kernel_write, test_kernel_read);
+	do {
+		match_expect |= report_matches(&expect);
+		match_never = report_matches(&never);
+	} while (!end_test_checks(match_never));
+	KUNIT_EXPECT_TRUE(test, match_expect);
+	KUNIT_EXPECT_FALSE(test, match_never);
+}
+
+/*
+ * Stress KCSAN with lots of concurrent races on different addresses until
+ * timeout.
+ */
+__no_kcsan
+static void test_concurrent_races(struct kunit *test)
+{
+	const struct expect_report expect = {
+		.access = {
+			/* NULL will match any address. */
+			{ test_kernel_rmw_array, NULL, 0, KCSAN_ACCESS_WRITE },
+			{ test_kernel_rmw_array, NULL, 0, 0 },
+		},
+	};
+	static const struct expect_report never = {
+		.access = {
+			{ test_kernel_rmw_array, NULL, 0, 0 },
+			{ test_kernel_rmw_array, NULL, 0, 0 },
+		},
+	};
+	bool match_expect = false;
+	bool match_never = false;
+
+	begin_test_checks(test_kernel_rmw_array, test_kernel_rmw_array);
+	do {
+		match_expect |= report_matches(&expect);
+		match_never |= report_matches(&never);
+	} while (!end_test_checks(false));
+	KUNIT_EXPECT_TRUE(test, match_expect); /* Sanity check matches exist. */
+	KUNIT_EXPECT_FALSE(test, match_never);
+}
+
+/* Test the KCSAN_REPORT_VALUE_CHANGE_ONLY option. */
+__no_kcsan
+static void test_novalue_change(struct kunit *test)
+{
+	const struct expect_report expect = {
+		.access = {
+			{ test_kernel_write_nochange, &test_var, sizeof(test_var), KCSAN_ACCESS_WRITE },
+			{ test_kernel_read, &test_var, sizeof(test_var), 0 },
+		},
+	};
+	bool match_expect = false;
+
+	begin_test_checks(test_kernel_write_nochange, test_kernel_read);
+	do {
+		match_expect = report_matches(&expect);
+	} while (!end_test_checks(match_expect));
+	if (IS_ENABLED(CONFIG_KCSAN_REPORT_VALUE_CHANGE_ONLY))
+		KUNIT_EXPECT_FALSE(test, match_expect);
+	else
+		KUNIT_EXPECT_TRUE(test, match_expect);
+}
+
+/*
+ * Test that the rules where the KCSAN_REPORT_VALUE_CHANGE_ONLY option should
+ * never apply work.
+ */
+__no_kcsan
+static void test_novalue_change_exception(struct kunit *test)
+{
+	const struct expect_report expect = {
+		.access = {
+			{ test_kernel_write_nochange_rcu, &test_var, sizeof(test_var), KCSAN_ACCESS_WRITE },
+			{ test_kernel_read, &test_var, sizeof(test_var), 0 },
+		},
+	};
+	bool match_expect = false;
+
+	begin_test_checks(test_kernel_write_nochange_rcu, test_kernel_read);
+	do {
+		match_expect = report_matches(&expect);
+	} while (!end_test_checks(match_expect));
+	KUNIT_EXPECT_TRUE(test, match_expect);
+}
+
+/* Test that data races of unknown origin are reported. */
+__no_kcsan
+static void test_unknown_origin(struct kunit *test)
+{
+	const struct expect_report expect = {
+		.access = {
+			{ test_kernel_read, &test_var, sizeof(test_var), 0 },
+			{ NULL },
+		},
+	};
+	bool match_expect = false;
+
+	begin_test_checks(test_kernel_write_uninstrumented, test_kernel_read);
+	do {
+		match_expect = report_matches(&expect);
+	} while (!end_test_checks(match_expect));
+	if (IS_ENABLED(CONFIG_KCSAN_REPORT_RACE_UNKNOWN_ORIGIN))
+		KUNIT_EXPECT_TRUE(test, match_expect);
+	else
+		KUNIT_EXPECT_FALSE(test, match_expect);
+}
+
+/* Test KCSAN_ASSUME_PLAIN_WRITES_ATOMIC if it is selected. */
+__no_kcsan
+static void test_write_write_assume_atomic(struct kunit *test)
+{
+	const struct expect_report expect = {
+		.access = {
+			{ test_kernel_write, &test_var, sizeof(test_var), KCSAN_ACCESS_WRITE },
+			{ test_kernel_write, &test_var, sizeof(test_var), KCSAN_ACCESS_WRITE },
+		},
+	};
+	bool match_expect = false;
+
+	begin_test_checks(test_kernel_write, test_kernel_write);
+	do {
+		sink_value(READ_ONCE(test_var)); /* induce value-change */
+		match_expect = report_matches(&expect);
+	} while (!end_test_checks(match_expect));
+	if (IS_ENABLED(CONFIG_KCSAN_ASSUME_PLAIN_WRITES_ATOMIC))
+		KUNIT_EXPECT_FALSE(test, match_expect);
+	else
+		KUNIT_EXPECT_TRUE(test, match_expect);
+}
+
+/*
+ * Test that data races with writes larger than word-size are always reported,
+ * even if KCSAN_ASSUME_PLAIN_WRITES_ATOMIC is selected.
+ */
+__no_kcsan
+static void test_write_write_struct(struct kunit *test)
+{
+	const struct expect_report expect = {
+		.access = {
+			{ test_kernel_write_struct, &test_struct, sizeof(test_struct), KCSAN_ACCESS_WRITE },
+			{ test_kernel_write_struct, &test_struct, sizeof(test_struct), KCSAN_ACCESS_WRITE },
+		},
+	};
+	bool match_expect = false;
+
+	begin_test_checks(test_kernel_write_struct, test_kernel_write_struct);
+	do {
+		match_expect = report_matches(&expect);
+	} while (!end_test_checks(match_expect));
+	KUNIT_EXPECT_TRUE(test, match_expect);
+}
+
+/*
+ * Test that data races where only one write is larger than word-size are always
+ * reported, even if KCSAN_ASSUME_PLAIN_WRITES_ATOMIC is selected.
+ */
+__no_kcsan
+static void test_write_write_struct_part(struct kunit *test)
+{
+	const struct expect_report expect = {
+		.access = {
+			{ test_kernel_write_struct, &test_struct, sizeof(test_struct), KCSAN_ACCESS_WRITE },
+			{ test_kernel_write_struct_part, &test_struct.val[3], sizeof(test_struct.val[3]), KCSAN_ACCESS_WRITE },
+		},
+	};
+	bool match_expect = false;
+
+	begin_test_checks(test_kernel_write_struct, test_kernel_write_struct_part);
+	do {
+		match_expect = report_matches(&expect);
+	} while (!end_test_checks(match_expect));
+	KUNIT_EXPECT_TRUE(test, match_expect);
+}
+
+/* Test that races with atomic accesses never result in reports. */
+__no_kcsan
+static void test_read_atomic_write_atomic(struct kunit *test)
+{
+	bool match_never = false;
+
+	begin_test_checks(test_kernel_read_atomic, test_kernel_write_atomic);
+	do {
+		match_never = report_available();
+	} while (!end_test_checks(match_never));
+	KUNIT_EXPECT_FALSE(test, match_never);
+}
+
+/* Test that a race with an atomic and plain access result in reports. */
+__no_kcsan
+static void test_read_plain_atomic_write(struct kunit *test)
+{
+	const struct expect_report expect = {
+		.access = {
+			{ test_kernel_read, &test_var, sizeof(test_var), 0 },
+			{ test_kernel_write_atomic, &test_var, sizeof(test_var), KCSAN_ACCESS_WRITE | KCSAN_ACCESS_ATOMIC },
+		},
+	};
+	bool match_expect = false;
+
+	if (IS_ENABLED(CONFIG_KCSAN_IGNORE_ATOMICS))
+		return;
+
+	begin_test_checks(test_kernel_read, test_kernel_write_atomic);
+	do {
+		match_expect = report_matches(&expect);
+	} while (!end_test_checks(match_expect));
+	KUNIT_EXPECT_TRUE(test, match_expect);
+}
+
+/* Zero-sized accesses should never cause data race reports. */
+__no_kcsan
+static void test_zero_size_access(struct kunit *test)
+{
+	const struct expect_report expect = {
+		.access = {
+			{ test_kernel_write_struct, &test_struct, sizeof(test_struct), KCSAN_ACCESS_WRITE },
+			{ test_kernel_write_struct, &test_struct, sizeof(test_struct), KCSAN_ACCESS_WRITE },
+		},
+	};
+	const struct expect_report never = {
+		.access = {
+			{ test_kernel_write_struct, &test_struct, sizeof(test_struct), KCSAN_ACCESS_WRITE },
+			{ test_kernel_read_struct_zero_size, &test_struct.val[3], 0, 0 },
+		},
+	};
+	bool match_expect = false;
+	bool match_never = false;
+
+	begin_test_checks(test_kernel_write_struct, test_kernel_read_struct_zero_size);
+	do {
+		match_expect |= report_matches(&expect);
+		match_never = report_matches(&never);
+	} while (!end_test_checks(match_never));
+	KUNIT_EXPECT_TRUE(test, match_expect); /* Sanity check. */
+	KUNIT_EXPECT_FALSE(test, match_never);
+}
+
+/* Test the data_race() macro. */
+__no_kcsan
+static void test_data_race(struct kunit *test)
+{
+	bool match_never = false;
+
+	begin_test_checks(test_kernel_data_race, test_kernel_data_race);
+	do {
+		match_never = report_available();
+	} while (!end_test_checks(match_never));
+	KUNIT_EXPECT_FALSE(test, match_never);
+}
+
+__no_kcsan
+static void test_assert_exclusive_writer(struct kunit *test)
+{
+	const struct expect_report expect = {
+		.access = {
+			{ test_kernel_assert_writer, &test_var, sizeof(test_var), KCSAN_ACCESS_ASSERT },
+			{ test_kernel_write_nochange, &test_var, sizeof(test_var), KCSAN_ACCESS_WRITE },
+		},
+	};
+	bool match_expect = false;
+
+	begin_test_checks(test_kernel_assert_writer, test_kernel_write_nochange);
+	do {
+		match_expect = report_matches(&expect);
+	} while (!end_test_checks(match_expect));
+	KUNIT_EXPECT_TRUE(test, match_expect);
+}
+
+__no_kcsan
+static void test_assert_exclusive_access(struct kunit *test)
+{
+	const struct expect_report expect = {
+		.access = {
+			{ test_kernel_assert_access, &test_var, sizeof(test_var), KCSAN_ACCESS_ASSERT | KCSAN_ACCESS_WRITE },
+			{ test_kernel_read, &test_var, sizeof(test_var), 0 },
+		},
+	};
+	bool match_expect = false;
+
+	begin_test_checks(test_kernel_assert_access, test_kernel_read);
+	do {
+		match_expect = report_matches(&expect);
+	} while (!end_test_checks(match_expect));
+	KUNIT_EXPECT_TRUE(test, match_expect);
+}
+
+__no_kcsan
+static void test_assert_exclusive_access_writer(struct kunit *test)
+{
+	const struct expect_report expect_access_writer = {
+		.access = {
+			{ test_kernel_assert_access, &test_var, sizeof(test_var), KCSAN_ACCESS_ASSERT | KCSAN_ACCESS_WRITE },
+			{ test_kernel_assert_writer, &test_var, sizeof(test_var), KCSAN_ACCESS_ASSERT },
+		},
+	};
+	const struct expect_report expect_access_access = {
+		.access = {
+			{ test_kernel_assert_access, &test_var, sizeof(test_var), KCSAN_ACCESS_ASSERT | KCSAN_ACCESS_WRITE },
+			{ test_kernel_assert_access, &test_var, sizeof(test_var), KCSAN_ACCESS_ASSERT | KCSAN_ACCESS_WRITE },
+		},
+	};
+	const struct expect_report never = {
+		.access = {
+			{ test_kernel_assert_writer, &test_var, sizeof(test_var), KCSAN_ACCESS_ASSERT },
+			{ test_kernel_assert_writer, &test_var, sizeof(test_var), KCSAN_ACCESS_ASSERT },
+		},
+	};
+	bool match_expect_access_writer = false;
+	bool match_expect_access_access = false;
+	bool match_never = false;
+
+	begin_test_checks(test_kernel_assert_access, test_kernel_assert_writer);
+	do {
+		match_expect_access_writer |= report_matches(&expect_access_writer);
+		match_expect_access_access |= report_matches(&expect_access_access);
+		match_never |= report_matches(&never);
+	} while (!end_test_checks(match_never));
+	KUNIT_EXPECT_TRUE(test, match_expect_access_writer);
+	KUNIT_EXPECT_TRUE(test, match_expect_access_access);
+	KUNIT_EXPECT_FALSE(test, match_never);
+}
+
+__no_kcsan
+static void test_assert_exclusive_bits_change(struct kunit *test)
+{
+	const struct expect_report expect = {
+		.access = {
+			{ test_kernel_assert_bits_change, &test_var, sizeof(test_var), KCSAN_ACCESS_ASSERT },
+			{ test_kernel_change_bits, &test_var, sizeof(test_var),
+				KCSAN_ACCESS_WRITE | (IS_ENABLED(CONFIG_KCSAN_IGNORE_ATOMICS) ? 0 : KCSAN_ACCESS_ATOMIC) },
+		},
+	};
+	bool match_expect = false;
+
+	begin_test_checks(test_kernel_assert_bits_change, test_kernel_change_bits);
+	do {
+		match_expect = report_matches(&expect);
+	} while (!end_test_checks(match_expect));
+	KUNIT_EXPECT_TRUE(test, match_expect);
+}
+
+__no_kcsan
+static void test_assert_exclusive_bits_nochange(struct kunit *test)
+{
+	bool match_never = false;
+
+	begin_test_checks(test_kernel_assert_bits_nochange, test_kernel_change_bits);
+	do {
+		match_never = report_available();
+	} while (!end_test_checks(match_never));
+	KUNIT_EXPECT_FALSE(test, match_never);
+}
+
+__no_kcsan
+static void test_assert_exclusive_writer_scoped(struct kunit *test)
+{
+	const struct expect_report expect_start = {
+		.access = {
+			{ test_kernel_assert_writer_scoped, &test_var, sizeof(test_var), KCSAN_ACCESS_ASSERT | KCSAN_ACCESS_SCOPED },
+			{ test_kernel_write_nochange, &test_var, sizeof(test_var), KCSAN_ACCESS_WRITE },
+		},
+	};
+	const struct expect_report expect_anywhere = {
+		.access = {
+			{ test_enter_scope, &test_var, sizeof(test_var), KCSAN_ACCESS_ASSERT | KCSAN_ACCESS_SCOPED },
+			{ test_kernel_write_nochange, &test_var, sizeof(test_var), KCSAN_ACCESS_WRITE },
+		},
+	};
+	bool match_expect_start = false;
+	bool match_expect_anywhere = false;
+
+	begin_test_checks(test_kernel_assert_writer_scoped, test_kernel_write_nochange);
+	do {
+		match_expect_start |= report_matches(&expect_start);
+		match_expect_anywhere |= report_matches(&expect_anywhere);
+	} while (!end_test_checks(match_expect_start && match_expect_anywhere));
+	KUNIT_EXPECT_TRUE(test, match_expect_start);
+	KUNIT_EXPECT_TRUE(test, match_expect_anywhere);
+}
+
+__no_kcsan
+static void test_assert_exclusive_access_scoped(struct kunit *test)
+{
+	const struct expect_report expect_start1 = {
+		.access = {
+			{ test_kernel_assert_access_scoped, &test_var, sizeof(test_var), KCSAN_ACCESS_ASSERT | KCSAN_ACCESS_WRITE | KCSAN_ACCESS_SCOPED },
+			{ test_kernel_read, &test_var, sizeof(test_var), 0 },
+		},
+	};
+	const struct expect_report expect_start2 = {
+		.access = { expect_start1.access[0], expect_start1.access[0] },
+	};
+	const struct expect_report expect_inscope = {
+		.access = {
+			{ test_enter_scope, &test_var, sizeof(test_var), KCSAN_ACCESS_ASSERT | KCSAN_ACCESS_WRITE | KCSAN_ACCESS_SCOPED },
+			{ test_kernel_read, &test_var, sizeof(test_var), 0 },
+		},
+	};
+	bool match_expect_start = false;
+	bool match_expect_inscope = false;
+
+	begin_test_checks(test_kernel_assert_access_scoped, test_kernel_read);
+	end_time += msecs_to_jiffies(1000); /* This test requires a bit more time. */
+	do {
+		match_expect_start |= report_matches(&expect_start1) || report_matches(&expect_start2);
+		match_expect_inscope |= report_matches(&expect_inscope);
+	} while (!end_test_checks(match_expect_start && match_expect_inscope));
+	KUNIT_EXPECT_TRUE(test, match_expect_start);
+	KUNIT_EXPECT_TRUE(test, match_expect_inscope);
+}
+
+/*
+ * jiffies is special (declared to be volatile) and its accesses are typically
+ * not marked; this test ensures that the compiler nor KCSAN gets confused about
+ * jiffies's declaration on different architectures.
+ */
+__no_kcsan
+static void test_jiffies_noreport(struct kunit *test)
+{
+	bool match_never = false;
+
+	begin_test_checks(test_kernel_jiffies_reader, test_kernel_jiffies_reader);
+	do {
+		match_never = report_available();
+	} while (!end_test_checks(match_never));
+	KUNIT_EXPECT_FALSE(test, match_never);
+}
+
+/* Test that racing accesses in seqlock critical sections are not reported. */
+__no_kcsan
+static void test_seqlock_noreport(struct kunit *test)
+{
+	bool match_never = false;
+
+	begin_test_checks(test_kernel_seqlock_reader, test_kernel_seqlock_writer);
+	do {
+		match_never = report_available();
+	} while (!end_test_checks(match_never));
+	KUNIT_EXPECT_FALSE(test, match_never);
+}
+
+/*
+ * Each test case is run with different numbers of threads. Until KUnit supports
+ * passing arguments for each test case, we encode #threads in the test case
+ * name (read by get_num_threads()). [The '-' was chosen as a stylistic
+ * preference to separate test name and #threads.]
+ *
+ * The thread counts are chosen to cover potentially interesting boundaries and
+ * corner cases (range 2-5), and then stress the system with larger counts.
+ */
+#define KCSAN_KUNIT_CASE(test_name)                                            \
+	{ .run_case = test_name, .name = #test_name "-02" },                   \
+	{ .run_case = test_name, .name = #test_name "-03" },                   \
+	{ .run_case = test_name, .name = #test_name "-04" },                   \
+	{ .run_case = test_name, .name = #test_name "-05" },                   \
+	{ .run_case = test_name, .name = #test_name "-08" },                   \
+	{ .run_case = test_name, .name = #test_name "-16" }
+
+static struct kunit_case kcsan_test_cases[] = {
+	KCSAN_KUNIT_CASE(test_basic),
+	KCSAN_KUNIT_CASE(test_concurrent_races),
+	KCSAN_KUNIT_CASE(test_novalue_change),
+	KCSAN_KUNIT_CASE(test_novalue_change_exception),
+	KCSAN_KUNIT_CASE(test_unknown_origin),
+	KCSAN_KUNIT_CASE(test_write_write_assume_atomic),
+	KCSAN_KUNIT_CASE(test_write_write_struct),
+	KCSAN_KUNIT_CASE(test_write_write_struct_part),
+	KCSAN_KUNIT_CASE(test_read_atomic_write_atomic),
+	KCSAN_KUNIT_CASE(test_read_plain_atomic_write),
+	KCSAN_KUNIT_CASE(test_zero_size_access),
+	KCSAN_KUNIT_CASE(test_data_race),
+	KCSAN_KUNIT_CASE(test_assert_exclusive_writer),
+	KCSAN_KUNIT_CASE(test_assert_exclusive_access),
+	KCSAN_KUNIT_CASE(test_assert_exclusive_access_writer),
+	KCSAN_KUNIT_CASE(test_assert_exclusive_bits_change),
+	KCSAN_KUNIT_CASE(test_assert_exclusive_bits_nochange),
+	KCSAN_KUNIT_CASE(test_assert_exclusive_writer_scoped),
+	KCSAN_KUNIT_CASE(test_assert_exclusive_access_scoped),
+	KCSAN_KUNIT_CASE(test_jiffies_noreport),
+	KCSAN_KUNIT_CASE(test_seqlock_noreport),
+	{},
+};
+
+/* ===== End test cases ===== */
+
+/* Get number of threads encoded in test name. */
+static bool __no_kcsan
+get_num_threads(const char *test, int *nthreads)
+{
+	int len = strlen(test);
+
+	if (WARN_ON(len < 3))
+		return false;
+
+	*nthreads = test[len - 1] - '0';
+	*nthreads += (test[len - 2] - '0') * 10;
+
+	if (WARN_ON(*nthreads < 0))
+		return false;
+
+	return true;
+}
+
+/* Concurrent accesses from interrupts. */
+__no_kcsan
+static void access_thread_timer(struct timer_list *timer)
+{
+	static atomic_t cnt = ATOMIC_INIT(0);
+	unsigned int idx;
+	void (*func)(void);
+
+	idx = (unsigned int)atomic_inc_return(&cnt) % ARRAY_SIZE(access_kernels);
+	/* Acquire potential initialization. */
+	func = smp_load_acquire(&access_kernels[idx]);
+	if (func)
+		func();
+}
+
+/* The main loop for each thread. */
+__no_kcsan
+static int access_thread(void *arg)
+{
+	struct timer_list timer;
+	unsigned int cnt = 0;
+	unsigned int idx;
+	void (*func)(void);
+
+	timer_setup_on_stack(&timer, access_thread_timer, 0);
+	do {
+		might_sleep();
+
+		if (!timer_pending(&timer))
+			mod_timer(&timer, jiffies + 1);
+		else {
+			/* Iterate through all kernels. */
+			idx = cnt++ % ARRAY_SIZE(access_kernels);
+			/* Acquire potential initialization. */
+			func = smp_load_acquire(&access_kernels[idx]);
+			if (func)
+				func();
+		}
+	} while (!torture_must_stop());
+	del_timer_sync(&timer);
+	destroy_timer_on_stack(&timer);
+
+	torture_kthread_stopping("access_thread");
+	return 0;
+}
+
+__no_kcsan
+static int test_init(struct kunit *test)
+{
+	unsigned long flags;
+	int nthreads;
+	int i;
+
+	spin_lock_irqsave(&observed.lock, flags);
+	for (i = 0; i < ARRAY_SIZE(observed.lines); ++i)
+		observed.lines[i][0] = '\0';
+	observed.nlines = 0;
+	spin_unlock_irqrestore(&observed.lock, flags);
+
+	if (!torture_init_begin((char *)test->name, 1))
+		return -EBUSY;
+
+	if (!get_num_threads(test->name, &nthreads))
+		goto err;
+
+	if (WARN_ON(threads))
+		goto err;
+
+	for (i = 0; i < ARRAY_SIZE(access_kernels); ++i) {
+		if (WARN_ON(access_kernels[i]))
+			goto err;
+	}
+
+	if (!IS_ENABLED(CONFIG_PREEMPT) || !IS_ENABLED(CONFIG_KCSAN_INTERRUPT_WATCHER)) {
+		/*
+		 * Without any preemption, keep 2 CPUs free for other tasks, one
+		 * of which is the main test case function checking for
+		 * completion or failure.
+		 */
+		const int min_unused_cpus = IS_ENABLED(CONFIG_PREEMPT_NONE) ? 2 : 0;
+		const int min_required_cpus = 2 + min_unused_cpus;
+
+		if (num_online_cpus() < min_required_cpus) {
+			pr_err("%s: too few online CPUs (%u < %d) for test",
+			       test->name, num_online_cpus(), min_required_cpus);
+			goto err;
+		} else if (nthreads > num_online_cpus() - min_unused_cpus) {
+			nthreads = num_online_cpus() - min_unused_cpus;
+			pr_warn("%s: limiting number of threads to %d\n",
+				test->name, nthreads);
+		}
+	}
+
+	if (nthreads) {
+		threads = kcalloc(nthreads + 1, sizeof(struct task_struct *),
+				  GFP_KERNEL);
+		if (WARN_ON(!threads))
+			goto err;
+
+		threads[nthreads] = NULL;
+		for (i = 0; i < nthreads; ++i) {
+			if (torture_create_kthread(access_thread, NULL,
+						   threads[i]))
+				goto err;
+		}
+	}
+
+	torture_init_end();
+
+	return 0;
+
+err:
+	kfree(threads);
+	threads = NULL;
+	torture_init_end();
+	return -EINVAL;
+}
+
+__no_kcsan
+static void test_exit(struct kunit *test)
+{
+	struct task_struct **stop_thread;
+	int i;
+
+	if (torture_cleanup_begin())
+		return;
+
+	for (i = 0; i < ARRAY_SIZE(access_kernels); ++i)
+		WRITE_ONCE(access_kernels[i], NULL);
+
+	if (threads) {
+		for (stop_thread = threads; *stop_thread; stop_thread++)
+			torture_stop_kthread(reader_thread, *stop_thread);
+
+		kfree(threads);
+		threads = NULL;
+	}
+
+	torture_cleanup_end();
+}
+
+static struct kunit_suite kcsan_test_suite = {
+	.name = "kcsan-test",
+	.test_cases = kcsan_test_cases,
+	.init = test_init,
+	.exit = test_exit,
+};
+static struct kunit_suite *kcsan_test_suites[] = { &kcsan_test_suite, NULL };
+
+__no_kcsan
+static void register_tracepoints(struct tracepoint *tp, void *ignore)
+{
+	check_trace_callback_type_console(probe_console);
+	if (!strcmp(tp->name, "console"))
+		WARN_ON(tracepoint_probe_register(tp, probe_console, NULL));
+}
+
+__no_kcsan
+static void unregister_tracepoints(struct tracepoint *tp, void *ignore)
+{
+	if (!strcmp(tp->name, "console"))
+		tracepoint_probe_unregister(tp, probe_console, NULL);
+}
+
+/*
+ * We only want to do tracepoints setup and teardown once, therefore we have to
+ * customize the init and exit functions and cannot rely on kunit_test_suite().
+ */
+static int __init kcsan_test_init(void)
+{
+	/*
+	 * Because we want to be able to build the test as a module, we need to
+	 * iterate through all known tracepoints, since the static registration
+	 * won't work here.
+	 */
+	for_each_kernel_tracepoint(register_tracepoints, NULL);
+	return __kunit_test_suites_init(kcsan_test_suites);
+}
+
+static void kcsan_test_exit(void)
+{
+	__kunit_test_suites_exit(kcsan_test_suites);
+	for_each_kernel_tracepoint(unregister_tracepoints, NULL);
+	tracepoint_synchronize_unregister();
+}
+
+late_initcall(kcsan_test_init);
+module_exit(kcsan_test_exit);
+
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Marco Elver <elver@google.com>");
diff --git a/kernel/kcsan/kcsan.h b/kernel/kcsan/kcsan.h
new file mode 100644
index 000000000000..29480010dc30
--- /dev/null
+++ b/kernel/kcsan/kcsan.h
@@ -0,0 +1,149 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+/*
+ * The Kernel Concurrency Sanitizer (KCSAN) infrastructure. For more info please
+ * see Documentation/dev-tools/kcsan.rst.
+ */
+
+#ifndef _KERNEL_KCSAN_KCSAN_H
+#define _KERNEL_KCSAN_KCSAN_H
+
+#include <linux/kcsan.h>
+#include <linux/sched.h>
+
+/* The number of adjacent watchpoints to check. */
+#define KCSAN_CHECK_ADJACENT 1
+#define NUM_SLOTS (1 + 2*KCSAN_CHECK_ADJACENT)
+
+extern unsigned int kcsan_udelay_task;
+extern unsigned int kcsan_udelay_interrupt;
+
+/*
+ * Globally enable and disable KCSAN.
+ */
+extern bool kcsan_enabled;
+
+/*
+ * Save/restore IRQ flags state trace dirtied by KCSAN.
+ */
+void kcsan_save_irqtrace(struct task_struct *task);
+void kcsan_restore_irqtrace(struct task_struct *task);
+
+/*
+ * Initialize debugfs file.
+ */
+void kcsan_debugfs_init(void);
+
+enum kcsan_counter_id {
+	/*
+	 * Number of watchpoints currently in use.
+	 */
+	KCSAN_COUNTER_USED_WATCHPOINTS,
+
+	/*
+	 * Total number of watchpoints set up.
+	 */
+	KCSAN_COUNTER_SETUP_WATCHPOINTS,
+
+	/*
+	 * Total number of data races.
+	 */
+	KCSAN_COUNTER_DATA_RACES,
+
+	/*
+	 * Total number of ASSERT failures due to races. If the observed race is
+	 * due to two conflicting ASSERT type accesses, then both will be
+	 * counted.
+	 */
+	KCSAN_COUNTER_ASSERT_FAILURES,
+
+	/*
+	 * Number of times no watchpoints were available.
+	 */
+	KCSAN_COUNTER_NO_CAPACITY,
+
+	/*
+	 * A thread checking a watchpoint raced with another checking thread;
+	 * only one will be reported.
+	 */
+	KCSAN_COUNTER_REPORT_RACES,
+
+	/*
+	 * Observed data value change, but writer thread unknown.
+	 */
+	KCSAN_COUNTER_RACES_UNKNOWN_ORIGIN,
+
+	/*
+	 * The access cannot be encoded to a valid watchpoint.
+	 */
+	KCSAN_COUNTER_UNENCODABLE_ACCESSES,
+
+	/*
+	 * Watchpoint encoding caused a watchpoint to fire on mismatching
+	 * accesses.
+	 */
+	KCSAN_COUNTER_ENCODING_FALSE_POSITIVES,
+
+	KCSAN_COUNTER_COUNT, /* number of counters */
+};
+
+/*
+ * Increment/decrement counter with given id; avoid calling these in fast-path.
+ */
+extern void kcsan_counter_inc(enum kcsan_counter_id id);
+extern void kcsan_counter_dec(enum kcsan_counter_id id);
+
+/*
+ * Returns true if data races in the function symbol that maps to func_addr
+ * (offsets are ignored) should *not* be reported.
+ */
+extern bool kcsan_skip_report_debugfs(unsigned long func_addr);
+
+/*
+ * Value-change states.
+ */
+enum kcsan_value_change {
+	/*
+	 * Did not observe a value-change, however, it is valid to report the
+	 * race, depending on preferences.
+	 */
+	KCSAN_VALUE_CHANGE_MAYBE,
+
+	/*
+	 * Did not observe a value-change, and it is invalid to report the race.
+	 */
+	KCSAN_VALUE_CHANGE_FALSE,
+
+	/*
+	 * The value was observed to change, and the race should be reported.
+	 */
+	KCSAN_VALUE_CHANGE_TRUE,
+};
+
+enum kcsan_report_type {
+	/*
+	 * The thread that set up the watchpoint and briefly stalled was
+	 * signalled that another thread triggered the watchpoint.
+	 */
+	KCSAN_REPORT_RACE_SIGNAL,
+
+	/*
+	 * A thread found and consumed a matching watchpoint.
+	 */
+	KCSAN_REPORT_CONSUMED_WATCHPOINT,
+
+	/*
+	 * No other thread was observed to race with the access, but the data
+	 * value before and after the stall differs.
+	 */
+	KCSAN_REPORT_RACE_UNKNOWN_ORIGIN,
+};
+
+/*
+ * Print a race report from thread that encountered the race.
+ */
+extern void kcsan_report(const volatile void *ptr, size_t size, int access_type,
+			 enum kcsan_value_change value_change,
+			 enum kcsan_report_type type, int watchpoint_idx);
+
+#endif /* _KERNEL_KCSAN_KCSAN_H */
diff --git a/kernel/kcsan/report.c b/kernel/kcsan/report.c
new file mode 100644
index 000000000000..9d07e175de0f
--- /dev/null
+++ b/kernel/kcsan/report.c
@@ -0,0 +1,638 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/debug_locks.h>
+#include <linux/delay.h>
+#include <linux/jiffies.h>
+#include <linux/kernel.h>
+#include <linux/lockdep.h>
+#include <linux/preempt.h>
+#include <linux/printk.h>
+#include <linux/sched.h>
+#include <linux/spinlock.h>
+#include <linux/stacktrace.h>
+
+#include "kcsan.h"
+#include "encoding.h"
+
+/*
+ * Max. number of stack entries to show in the report.
+ */
+#define NUM_STACK_ENTRIES 64
+
+/* Common access info. */
+struct access_info {
+	const volatile void	*ptr;
+	size_t			size;
+	int			access_type;
+	int			task_pid;
+	int			cpu_id;
+};
+
+/*
+ * Other thread info: communicated from other racing thread to thread that set
+ * up the watchpoint, which then prints the complete report atomically.
+ */
+struct other_info {
+	struct access_info	ai;
+	unsigned long		stack_entries[NUM_STACK_ENTRIES];
+	int			num_stack_entries;
+
+	/*
+	 * Optionally pass @current. Typically we do not need to pass @current
+	 * via @other_info since just @task_pid is sufficient. Passing @current
+	 * has additional overhead.
+	 *
+	 * To safely pass @current, we must either use get_task_struct/
+	 * put_task_struct, or stall the thread that populated @other_info.
+	 *
+	 * We cannot rely on get_task_struct/put_task_struct in case
+	 * release_report() races with a task being released, and would have to
+	 * free it in release_report(). This may result in deadlock if we want
+	 * to use KCSAN on the allocators.
+	 *
+	 * Since we also want to reliably print held locks for
+	 * CONFIG_KCSAN_VERBOSE, the current implementation stalls the thread
+	 * that populated @other_info until it has been consumed.
+	 */
+	struct task_struct	*task;
+};
+
+/*
+ * To never block any producers of struct other_info, we need as many elements
+ * as we have watchpoints (upper bound on concurrent races to report).
+ */
+static struct other_info other_infos[CONFIG_KCSAN_NUM_WATCHPOINTS + NUM_SLOTS-1];
+
+/*
+ * Information about reported races; used to rate limit reporting.
+ */
+struct report_time {
+	/*
+	 * The last time the race was reported.
+	 */
+	unsigned long time;
+
+	/*
+	 * The frames of the 2 threads; if only 1 thread is known, one frame
+	 * will be 0.
+	 */
+	unsigned long frame1;
+	unsigned long frame2;
+};
+
+/*
+ * Since we also want to be able to debug allocators with KCSAN, to avoid
+ * deadlock, report_times cannot be dynamically resized with krealloc in
+ * rate_limit_report.
+ *
+ * Therefore, we use a fixed-size array, which at most will occupy a page. This
+ * still adequately rate limits reports, assuming that a) number of unique data
+ * races is not excessive, and b) occurrence of unique races within the
+ * same time window is limited.
+ */
+#define REPORT_TIMES_MAX (PAGE_SIZE / sizeof(struct report_time))
+#define REPORT_TIMES_SIZE                                                      \
+	(CONFIG_KCSAN_REPORT_ONCE_IN_MS > REPORT_TIMES_MAX ?                   \
+		 REPORT_TIMES_MAX :                                            \
+		 CONFIG_KCSAN_REPORT_ONCE_IN_MS)
+static struct report_time report_times[REPORT_TIMES_SIZE];
+
+/*
+ * Spinlock serializing report generation, and access to @other_infos. Although
+ * it could make sense to have a finer-grained locking story for @other_infos,
+ * report generation needs to be serialized either way, so not much is gained.
+ */
+static DEFINE_RAW_SPINLOCK(report_lock);
+
+/*
+ * Checks if the race identified by thread frames frame1 and frame2 has
+ * been reported since (now - KCSAN_REPORT_ONCE_IN_MS).
+ */
+static bool rate_limit_report(unsigned long frame1, unsigned long frame2)
+{
+	struct report_time *use_entry = &report_times[0];
+	unsigned long invalid_before;
+	int i;
+
+	BUILD_BUG_ON(CONFIG_KCSAN_REPORT_ONCE_IN_MS != 0 && REPORT_TIMES_SIZE == 0);
+
+	if (CONFIG_KCSAN_REPORT_ONCE_IN_MS == 0)
+		return false;
+
+	invalid_before = jiffies - msecs_to_jiffies(CONFIG_KCSAN_REPORT_ONCE_IN_MS);
+
+	/* Check if a matching race report exists. */
+	for (i = 0; i < REPORT_TIMES_SIZE; ++i) {
+		struct report_time *rt = &report_times[i];
+
+		/*
+		 * Must always select an entry for use to store info as we
+		 * cannot resize report_times; at the end of the scan, use_entry
+		 * will be the oldest entry, which ideally also happened before
+		 * KCSAN_REPORT_ONCE_IN_MS ago.
+		 */
+		if (time_before(rt->time, use_entry->time))
+			use_entry = rt;
+
+		/*
+		 * Initially, no need to check any further as this entry as well
+		 * as following entries have never been used.
+		 */
+		if (rt->time == 0)
+			break;
+
+		/* Check if entry expired. */
+		if (time_before(rt->time, invalid_before))
+			continue; /* before KCSAN_REPORT_ONCE_IN_MS ago */
+
+		/* Reported recently, check if race matches. */
+		if ((rt->frame1 == frame1 && rt->frame2 == frame2) ||
+		    (rt->frame1 == frame2 && rt->frame2 == frame1))
+			return true;
+	}
+
+	use_entry->time = jiffies;
+	use_entry->frame1 = frame1;
+	use_entry->frame2 = frame2;
+	return false;
+}
+
+/*
+ * Special rules to skip reporting.
+ */
+static bool
+skip_report(enum kcsan_value_change value_change, unsigned long top_frame)
+{
+	/* Should never get here if value_change==FALSE. */
+	WARN_ON_ONCE(value_change == KCSAN_VALUE_CHANGE_FALSE);
+
+	/*
+	 * The first call to skip_report always has value_change==TRUE, since we
+	 * cannot know the value written of an instrumented access. For the 2nd
+	 * call there are 6 cases with CONFIG_KCSAN_REPORT_VALUE_CHANGE_ONLY:
+	 *
+	 * 1. read watchpoint, conflicting write (value_change==TRUE): report;
+	 * 2. read watchpoint, conflicting write (value_change==MAYBE): skip;
+	 * 3. write watchpoint, conflicting write (value_change==TRUE): report;
+	 * 4. write watchpoint, conflicting write (value_change==MAYBE): skip;
+	 * 5. write watchpoint, conflicting read (value_change==MAYBE): skip;
+	 * 6. write watchpoint, conflicting read (value_change==TRUE): report;
+	 *
+	 * Cases 1-4 are intuitive and expected; case 5 ensures we do not report
+	 * data races where the write may have rewritten the same value; case 6
+	 * is possible either if the size is larger than what we check value
+	 * changes for or the access type is KCSAN_ACCESS_ASSERT.
+	 */
+	if (IS_ENABLED(CONFIG_KCSAN_REPORT_VALUE_CHANGE_ONLY) &&
+	    value_change == KCSAN_VALUE_CHANGE_MAYBE) {
+		/*
+		 * The access is a write, but the data value did not change.
+		 *
+		 * We opt-out of this filter for certain functions at request of
+		 * maintainers.
+		 */
+		char buf[64];
+		int len = scnprintf(buf, sizeof(buf), "%ps", (void *)top_frame);
+
+		if (!strnstr(buf, "rcu_", len) &&
+		    !strnstr(buf, "_rcu", len) &&
+		    !strnstr(buf, "_srcu", len))
+			return true;
+	}
+
+	return kcsan_skip_report_debugfs(top_frame);
+}
+
+static const char *get_access_type(int type)
+{
+	if (type & KCSAN_ACCESS_ASSERT) {
+		if (type & KCSAN_ACCESS_SCOPED) {
+			if (type & KCSAN_ACCESS_WRITE)
+				return "assert no accesses (scoped)";
+			else
+				return "assert no writes (scoped)";
+		} else {
+			if (type & KCSAN_ACCESS_WRITE)
+				return "assert no accesses";
+			else
+				return "assert no writes";
+		}
+	}
+
+	switch (type) {
+	case 0:
+		return "read";
+	case KCSAN_ACCESS_ATOMIC:
+		return "read (marked)";
+	case KCSAN_ACCESS_WRITE:
+		return "write";
+	case KCSAN_ACCESS_WRITE | KCSAN_ACCESS_ATOMIC:
+		return "write (marked)";
+	case KCSAN_ACCESS_SCOPED:
+		return "read (scoped)";
+	case KCSAN_ACCESS_SCOPED | KCSAN_ACCESS_ATOMIC:
+		return "read (marked, scoped)";
+	case KCSAN_ACCESS_SCOPED | KCSAN_ACCESS_WRITE:
+		return "write (scoped)";
+	case KCSAN_ACCESS_SCOPED | KCSAN_ACCESS_WRITE | KCSAN_ACCESS_ATOMIC:
+		return "write (marked, scoped)";
+	default:
+		BUG();
+	}
+}
+
+static const char *get_bug_type(int type)
+{
+	return (type & KCSAN_ACCESS_ASSERT) != 0 ? "assert: race" : "data-race";
+}
+
+/* Return thread description: in task or interrupt. */
+static const char *get_thread_desc(int task_id)
+{
+	if (task_id != -1) {
+		static char buf[32]; /* safe: protected by report_lock */
+
+		snprintf(buf, sizeof(buf), "task %i", task_id);
+		return buf;
+	}
+	return "interrupt";
+}
+
+/* Helper to skip KCSAN-related functions in stack-trace. */
+static int get_stack_skipnr(const unsigned long stack_entries[], int num_entries)
+{
+	char buf[64];
+	char *cur;
+	int len, skip;
+
+	for (skip = 0; skip < num_entries; ++skip) {
+		len = scnprintf(buf, sizeof(buf), "%ps", (void *)stack_entries[skip]);
+
+		/* Never show tsan_* or {read,write}_once_size. */
+		if (strnstr(buf, "tsan_", len) ||
+		    strnstr(buf, "_once_size", len))
+			continue;
+
+		cur = strnstr(buf, "kcsan_", len);
+		if (cur) {
+			cur += sizeof("kcsan_") - 1;
+			if (strncmp(cur, "test", sizeof("test") - 1))
+				continue; /* KCSAN runtime function. */
+			/* KCSAN related test. */
+		}
+
+		/*
+		 * No match for runtime functions -- @skip entries to skip to
+		 * get to first frame of interest.
+		 */
+		break;
+	}
+
+	return skip;
+}
+
+/* Compares symbolized strings of addr1 and addr2. */
+static int sym_strcmp(void *addr1, void *addr2)
+{
+	char buf1[64];
+	char buf2[64];
+
+	snprintf(buf1, sizeof(buf1), "%pS", addr1);
+	snprintf(buf2, sizeof(buf2), "%pS", addr2);
+
+	return strncmp(buf1, buf2, sizeof(buf1));
+}
+
+static void print_verbose_info(struct task_struct *task)
+{
+	if (!task)
+		return;
+
+	/* Restore IRQ state trace for printing. */
+	kcsan_restore_irqtrace(task);
+
+	pr_err("\n");
+	debug_show_held_locks(task);
+	print_irqtrace_events(task);
+}
+
+/*
+ * Returns true if a report was generated, false otherwise.
+ */
+static bool print_report(enum kcsan_value_change value_change,
+			 enum kcsan_report_type type,
+			 const struct access_info *ai,
+			 const struct other_info *other_info)
+{
+	unsigned long stack_entries[NUM_STACK_ENTRIES] = { 0 };
+	int num_stack_entries = stack_trace_save(stack_entries, NUM_STACK_ENTRIES, 1);
+	int skipnr = get_stack_skipnr(stack_entries, num_stack_entries);
+	unsigned long this_frame = stack_entries[skipnr];
+	unsigned long other_frame = 0;
+	int other_skipnr = 0; /* silence uninit warnings */
+
+	/*
+	 * Must check report filter rules before starting to print.
+	 */
+	if (skip_report(KCSAN_VALUE_CHANGE_TRUE, stack_entries[skipnr]))
+		return false;
+
+	if (type == KCSAN_REPORT_RACE_SIGNAL) {
+		other_skipnr = get_stack_skipnr(other_info->stack_entries,
+						other_info->num_stack_entries);
+		other_frame = other_info->stack_entries[other_skipnr];
+
+		/* @value_change is only known for the other thread */
+		if (skip_report(value_change, other_frame))
+			return false;
+	}
+
+	if (rate_limit_report(this_frame, other_frame))
+		return false;
+
+	/* Print report header. */
+	pr_err("==================================================================\n");
+	switch (type) {
+	case KCSAN_REPORT_RACE_SIGNAL: {
+		int cmp;
+
+		/*
+		 * Order functions lexographically for consistent bug titles.
+		 * Do not print offset of functions to keep title short.
+		 */
+		cmp = sym_strcmp((void *)other_frame, (void *)this_frame);
+		pr_err("BUG: KCSAN: %s in %ps / %ps\n",
+		       get_bug_type(ai->access_type | other_info->ai.access_type),
+		       (void *)(cmp < 0 ? other_frame : this_frame),
+		       (void *)(cmp < 0 ? this_frame : other_frame));
+	} break;
+
+	case KCSAN_REPORT_RACE_UNKNOWN_ORIGIN:
+		pr_err("BUG: KCSAN: %s in %pS\n", get_bug_type(ai->access_type),
+		       (void *)this_frame);
+		break;
+
+	default:
+		BUG();
+	}
+
+	pr_err("\n");
+
+	/* Print information about the racing accesses. */
+	switch (type) {
+	case KCSAN_REPORT_RACE_SIGNAL:
+		pr_err("%s to 0x%px of %zu bytes by %s on cpu %i:\n",
+		       get_access_type(other_info->ai.access_type), other_info->ai.ptr,
+		       other_info->ai.size, get_thread_desc(other_info->ai.task_pid),
+		       other_info->ai.cpu_id);
+
+		/* Print the other thread's stack trace. */
+		stack_trace_print(other_info->stack_entries + other_skipnr,
+				  other_info->num_stack_entries - other_skipnr,
+				  0);
+
+		if (IS_ENABLED(CONFIG_KCSAN_VERBOSE))
+			print_verbose_info(other_info->task);
+
+		pr_err("\n");
+		pr_err("%s to 0x%px of %zu bytes by %s on cpu %i:\n",
+		       get_access_type(ai->access_type), ai->ptr, ai->size,
+		       get_thread_desc(ai->task_pid), ai->cpu_id);
+		break;
+
+	case KCSAN_REPORT_RACE_UNKNOWN_ORIGIN:
+		pr_err("race at unknown origin, with %s to 0x%px of %zu bytes by %s on cpu %i:\n",
+		       get_access_type(ai->access_type), ai->ptr, ai->size,
+		       get_thread_desc(ai->task_pid), ai->cpu_id);
+		break;
+
+	default:
+		BUG();
+	}
+	/* Print stack trace of this thread. */
+	stack_trace_print(stack_entries + skipnr, num_stack_entries - skipnr,
+			  0);
+
+	if (IS_ENABLED(CONFIG_KCSAN_VERBOSE))
+		print_verbose_info(current);
+
+	/* Print report footer. */
+	pr_err("\n");
+	pr_err("Reported by Kernel Concurrency Sanitizer on:\n");
+	dump_stack_print_info(KERN_DEFAULT);
+	pr_err("==================================================================\n");
+
+	return true;
+}
+
+static void release_report(unsigned long *flags, struct other_info *other_info)
+{
+	if (other_info)
+		/*
+		 * Use size to denote valid/invalid, since KCSAN entirely
+		 * ignores 0-sized accesses.
+		 */
+		other_info->ai.size = 0;
+
+	raw_spin_unlock_irqrestore(&report_lock, *flags);
+}
+
+/*
+ * Sets @other_info->task and awaits consumption of @other_info.
+ *
+ * Precondition: report_lock is held.
+ * Postcondition: report_lock is held.
+ */
+static void set_other_info_task_blocking(unsigned long *flags,
+					 const struct access_info *ai,
+					 struct other_info *other_info)
+{
+	/*
+	 * We may be instrumenting a code-path where current->state is already
+	 * something other than TASK_RUNNING.
+	 */
+	const bool is_running = current->state == TASK_RUNNING;
+	/*
+	 * To avoid deadlock in case we are in an interrupt here and this is a
+	 * race with a task on the same CPU (KCSAN_INTERRUPT_WATCHER), provide a
+	 * timeout to ensure this works in all contexts.
+	 *
+	 * Await approximately the worst case delay of the reporting thread (if
+	 * we are not interrupted).
+	 */
+	int timeout = max(kcsan_udelay_task, kcsan_udelay_interrupt);
+
+	other_info->task = current;
+	do {
+		if (is_running) {
+			/*
+			 * Let lockdep know the real task is sleeping, to print
+			 * the held locks (recall we turned lockdep off, so
+			 * locking/unlocking @report_lock won't be recorded).
+			 */
+			set_current_state(TASK_UNINTERRUPTIBLE);
+		}
+		raw_spin_unlock_irqrestore(&report_lock, *flags);
+		/*
+		 * We cannot call schedule() since we also cannot reliably
+		 * determine if sleeping here is permitted -- see in_atomic().
+		 */
+
+		udelay(1);
+		raw_spin_lock_irqsave(&report_lock, *flags);
+		if (timeout-- < 0) {
+			/*
+			 * Abort. Reset @other_info->task to NULL, since it
+			 * appears the other thread is still going to consume
+			 * it. It will result in no verbose info printed for
+			 * this task.
+			 */
+			other_info->task = NULL;
+			break;
+		}
+		/*
+		 * If invalid, or @ptr nor @current matches, then @other_info
+		 * has been consumed and we may continue. If not, retry.
+		 */
+	} while (other_info->ai.size && other_info->ai.ptr == ai->ptr &&
+		 other_info->task == current);
+	if (is_running)
+		set_current_state(TASK_RUNNING);
+}
+
+/* Populate @other_info; requires that the provided @other_info not in use. */
+static void prepare_report_producer(unsigned long *flags,
+				    const struct access_info *ai,
+				    struct other_info *other_info)
+{
+	raw_spin_lock_irqsave(&report_lock, *flags);
+
+	/*
+	 * The same @other_infos entry cannot be used concurrently, because
+	 * there is a one-to-one mapping to watchpoint slots (@watchpoints in
+	 * core.c), and a watchpoint is only released for reuse after reporting
+	 * is done by the consumer of @other_info. Therefore, it is impossible
+	 * for another concurrent prepare_report_producer() to set the same
+	 * @other_info, and are guaranteed exclusivity for the @other_infos
+	 * entry pointed to by @other_info.
+	 *
+	 * To check this property holds, size should never be non-zero here,
+	 * because every consumer of struct other_info resets size to 0 in
+	 * release_report().
+	 */
+	WARN_ON(other_info->ai.size);
+
+	other_info->ai = *ai;
+	other_info->num_stack_entries = stack_trace_save(other_info->stack_entries, NUM_STACK_ENTRIES, 2);
+
+	if (IS_ENABLED(CONFIG_KCSAN_VERBOSE))
+		set_other_info_task_blocking(flags, ai, other_info);
+
+	raw_spin_unlock_irqrestore(&report_lock, *flags);
+}
+
+/* Awaits producer to fill @other_info and then returns. */
+static bool prepare_report_consumer(unsigned long *flags,
+				    const struct access_info *ai,
+				    struct other_info *other_info)
+{
+
+	raw_spin_lock_irqsave(&report_lock, *flags);
+	while (!other_info->ai.size) { /* Await valid @other_info. */
+		raw_spin_unlock_irqrestore(&report_lock, *flags);
+		cpu_relax();
+		raw_spin_lock_irqsave(&report_lock, *flags);
+	}
+
+	/* Should always have a matching access based on watchpoint encoding. */
+	if (WARN_ON(!matching_access((unsigned long)other_info->ai.ptr & WATCHPOINT_ADDR_MASK, other_info->ai.size,
+				     (unsigned long)ai->ptr & WATCHPOINT_ADDR_MASK, ai->size)))
+		goto discard;
+
+	if (!matching_access((unsigned long)other_info->ai.ptr, other_info->ai.size,
+			     (unsigned long)ai->ptr, ai->size)) {
+		/*
+		 * If the actual accesses to not match, this was a false
+		 * positive due to watchpoint encoding.
+		 */
+		kcsan_counter_inc(KCSAN_COUNTER_ENCODING_FALSE_POSITIVES);
+		goto discard;
+	}
+
+	return true;
+
+discard:
+	release_report(flags, other_info);
+	return false;
+}
+
+/*
+ * Depending on the report type either sets @other_info and returns false, or
+ * awaits @other_info and returns true. If @other_info is not required for the
+ * report type, simply acquires @report_lock and returns true.
+ */
+static noinline bool prepare_report(unsigned long *flags,
+				    enum kcsan_report_type type,
+				    const struct access_info *ai,
+				    struct other_info *other_info)
+{
+	switch (type) {
+	case KCSAN_REPORT_CONSUMED_WATCHPOINT:
+		prepare_report_producer(flags, ai, other_info);
+		return false;
+	case KCSAN_REPORT_RACE_SIGNAL:
+		return prepare_report_consumer(flags, ai, other_info);
+	default:
+		/* @other_info not required; just acquire @report_lock. */
+		raw_spin_lock_irqsave(&report_lock, *flags);
+		return true;
+	}
+}
+
+void kcsan_report(const volatile void *ptr, size_t size, int access_type,
+		  enum kcsan_value_change value_change,
+		  enum kcsan_report_type type, int watchpoint_idx)
+{
+	unsigned long flags = 0;
+	const struct access_info ai = {
+		.ptr		= ptr,
+		.size		= size,
+		.access_type	= access_type,
+		.task_pid	= in_task() ? task_pid_nr(current) : -1,
+		.cpu_id		= raw_smp_processor_id()
+	};
+	struct other_info *other_info = type == KCSAN_REPORT_RACE_UNKNOWN_ORIGIN
+					? NULL : &other_infos[watchpoint_idx];
+
+	kcsan_disable_current();
+	if (WARN_ON(watchpoint_idx < 0 || watchpoint_idx >= ARRAY_SIZE(other_infos)))
+		goto out;
+
+	/*
+	 * Because we may generate reports when we're in scheduler code, the use
+	 * of printk() could deadlock. Until such time that all printing code
+	 * called in print_report() is scheduler-safe, accept the risk, and just
+	 * get our message out. As such, also disable lockdep to hide the
+	 * warning, and avoid disabling lockdep for the rest of the kernel.
+	 */
+	lockdep_off();
+
+	if (prepare_report(&flags, type, &ai, other_info)) {
+		/*
+		 * Never report if value_change is FALSE, only if we it is
+		 * either TRUE or MAYBE. In case of MAYBE, further filtering may
+		 * be done once we know the full stack trace in print_report().
+		 */
+		bool reported = value_change != KCSAN_VALUE_CHANGE_FALSE &&
+				print_report(value_change, type, &ai, other_info);
+
+		if (reported && panic_on_warn)
+			panic("panic_on_warn set ...\n");
+
+		release_report(&flags, other_info);
+	}
+
+	lockdep_on();
+out:
+	kcsan_enable_current();
+}
diff --git a/kernel/kcsan/selftest.c b/kernel/kcsan/selftest.c
new file mode 100644
index 000000000000..d26a052d3383
--- /dev/null
+++ b/kernel/kcsan/selftest.c
@@ -0,0 +1,131 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/printk.h>
+#include <linux/random.h>
+#include <linux/types.h>
+
+#include "encoding.h"
+
+#define ITERS_PER_TEST 2000
+
+/* Test requirements. */
+static bool test_requires(void)
+{
+	/* random should be initialized for the below tests */
+	return prandom_u32() + prandom_u32() != 0;
+}
+
+/*
+ * Test watchpoint encode and decode: check that encoding some access's info,
+ * and then subsequent decode preserves the access's info.
+ */
+static bool test_encode_decode(void)
+{
+	int i;
+
+	for (i = 0; i < ITERS_PER_TEST; ++i) {
+		size_t size = prandom_u32_max(MAX_ENCODABLE_SIZE) + 1;
+		bool is_write = !!prandom_u32_max(2);
+		unsigned long addr;
+
+		prandom_bytes(&addr, sizeof(addr));
+		if (WARN_ON(!check_encodable(addr, size)))
+			return false;
+
+		/* Encode and decode */
+		{
+			const long encoded_watchpoint =
+				encode_watchpoint(addr, size, is_write);
+			unsigned long verif_masked_addr;
+			size_t verif_size;
+			bool verif_is_write;
+
+			/* Check special watchpoints */
+			if (WARN_ON(decode_watchpoint(
+				    INVALID_WATCHPOINT, &verif_masked_addr,
+				    &verif_size, &verif_is_write)))
+				return false;
+			if (WARN_ON(decode_watchpoint(
+				    CONSUMED_WATCHPOINT, &verif_masked_addr,
+				    &verif_size, &verif_is_write)))
+				return false;
+
+			/* Check decoding watchpoint returns same data */
+			if (WARN_ON(!decode_watchpoint(
+				    encoded_watchpoint, &verif_masked_addr,
+				    &verif_size, &verif_is_write)))
+				return false;
+			if (WARN_ON(verif_masked_addr !=
+				    (addr & WATCHPOINT_ADDR_MASK)))
+				goto fail;
+			if (WARN_ON(verif_size != size))
+				goto fail;
+			if (WARN_ON(is_write != verif_is_write))
+				goto fail;
+
+			continue;
+fail:
+			pr_err("%s fail: %s %zu bytes @ %lx -> encoded: %lx -> %s %zu bytes @ %lx\n",
+			       __func__, is_write ? "write" : "read", size,
+			       addr, encoded_watchpoint,
+			       verif_is_write ? "write" : "read", verif_size,
+			       verif_masked_addr);
+			return false;
+		}
+	}
+
+	return true;
+}
+
+/* Test access matching function. */
+static bool test_matching_access(void)
+{
+	if (WARN_ON(!matching_access(10, 1, 10, 1)))
+		return false;
+	if (WARN_ON(!matching_access(10, 2, 11, 1)))
+		return false;
+	if (WARN_ON(!matching_access(10, 1, 9, 2)))
+		return false;
+	if (WARN_ON(matching_access(10, 1, 11, 1)))
+		return false;
+	if (WARN_ON(matching_access(9, 1, 10, 1)))
+		return false;
+
+	/*
+	 * An access of size 0 could match another access, as demonstrated here.
+	 * Rather than add more comparisons to 'matching_access()', which would
+	 * end up in the fast-path for *all* checks, check_access() simply
+	 * returns for all accesses of size 0.
+	 */
+	if (WARN_ON(!matching_access(8, 8, 12, 0)))
+		return false;
+
+	return true;
+}
+
+static int __init kcsan_selftest(void)
+{
+	int passed = 0;
+	int total = 0;
+
+#define RUN_TEST(do_test)                                                      \
+	do {                                                                   \
+		++total;                                                       \
+		if (do_test())                                                 \
+			++passed;                                              \
+		else                                                           \
+			pr_err("KCSAN selftest: " #do_test " failed");         \
+	} while (0)
+
+	RUN_TEST(test_requires);
+	RUN_TEST(test_encode_decode);
+	RUN_TEST(test_matching_access);
+
+	pr_info("KCSAN selftest: %d/%d tests passed\n", passed, total);
+	if (passed != total)
+		panic("KCSAN selftests failed");
+	return 0;
+}
+postcore_initcall(kcsan_selftest);
diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c
index faa74d5f6941..ca40bef75a61 100644
--- a/kernel/kexec_file.c
+++ b/kernel/kexec_file.c
@@ -181,34 +181,19 @@ void kimage_file_post_load_cleanup(struct kimage *image)
 static int
 kimage_validate_signature(struct kimage *image)
 {
-	const char *reason;
 	int ret;
 
 	ret = arch_kexec_kernel_verify_sig(image, image->kernel_buf,
 					   image->kernel_buf_len);
-	switch (ret) {
-	case 0:
-		break;
+	if (ret) {
 
-		/* Certain verification errors are non-fatal if we're not
-		 * checking errors, provided we aren't mandating that there
-		 * must be a valid signature.
-		 */
-	case -ENODATA:
-		reason = "kexec of unsigned image";
-		goto decide;
-	case -ENOPKG:
-		reason = "kexec of image with unsupported crypto";
-		goto decide;
-	case -ENOKEY:
-		reason = "kexec of image with unavailable key";
-	decide:
 		if (IS_ENABLED(CONFIG_KEXEC_SIG_FORCE)) {
-			pr_notice("%s rejected\n", reason);
+			pr_notice("Enforced kernel signature verification failed (%d).\n", ret);
 			return ret;
 		}
 
-		/* If IMA is guaranteed to appraise a signature on the kexec
+		/*
+		 * If IMA is guaranteed to appraise a signature on the kexec
 		 * image, permit it even if the kernel is otherwise locked
 		 * down.
 		 */
@@ -216,17 +201,10 @@ kimage_validate_signature(struct kimage *image)
 		    security_locked_down(LOCKDOWN_KEXEC))
 			return -EPERM;
 
-		return 0;
-
-		/* All other errors are fatal, including nomem, unparseable
-		 * signatures and signature check failures - even if signatures
-		 * aren't required.
-		 */
-	default:
-		pr_notice("kernel signature verification failed (%d).\n", ret);
+		pr_debug("kernel signature verification failed (%d).\n", ret);
 	}
 
-	return ret;
+	return 0;
 }
 #endif
 
@@ -287,7 +265,7 @@ kimage_file_prepare_segments(struct kimage *image, int kernel_fd, int initrd_fd,
 			goto out;
 		}
 
-		ima_kexec_cmdline(image->cmdline_buf,
+		ima_kexec_cmdline(kernel_fd, image->cmdline_buf,
 				  image->cmdline_buf_len - 1);
 	}
 
@@ -540,6 +518,11 @@ static int locate_mem_hole_callback(struct resource *res, void *arg)
 	unsigned long sz = end - start + 1;
 
 	/* Returning 0 will take to next memory range */
+
+	/* Don't use memory that will be detected and handled by a driver. */
+	if (res->flags & IORESOURCE_MEM_DRIVER_MANAGED)
+		return 0;
+
 	if (sz < kbuf->memsz)
 		return 0;
 
@@ -653,6 +636,19 @@ int kexec_locate_mem_hole(struct kexec_buf *kbuf)
 }
 
 /**
+ * arch_kexec_locate_mem_hole - Find free memory to place the segments.
+ * @kbuf:                       Parameters for the memory search.
+ *
+ * On success, kbuf->mem will have the start address of the memory region found.
+ *
+ * Return: 0 on success, negative errno on error.
+ */
+int __weak arch_kexec_locate_mem_hole(struct kexec_buf *kbuf)
+{
+	return kexec_locate_mem_hole(kbuf);
+}
+
+/**
  * kexec_add_buffer - place a buffer in a kexec segment
  * @kbuf:	Buffer contents and memory parameters.
  *
@@ -664,7 +660,6 @@ int kexec_locate_mem_hole(struct kexec_buf *kbuf)
  */
 int kexec_add_buffer(struct kexec_buf *kbuf)
 {
-
 	struct kexec_segment *ksegment;
 	int ret;
 
@@ -692,7 +687,7 @@ int kexec_add_buffer(struct kexec_buf *kbuf)
 	kbuf->buf_align = max(kbuf->buf_align, PAGE_SIZE);
 
 	/* Walk the RAM ranges and allocate a suitable range for the buffer */
-	ret = kexec_locate_mem_hole(kbuf);
+	ret = arch_kexec_locate_mem_hole(kbuf);
 	if (ret)
 		return ret;
 
@@ -1174,24 +1169,26 @@ int crash_exclude_mem_range(struct crash_mem *mem,
 			    unsigned long long mstart, unsigned long long mend)
 {
 	int i, j;
-	unsigned long long start, end;
+	unsigned long long start, end, p_start, p_end;
 	struct crash_mem_range temp_range = {0, 0};
 
 	for (i = 0; i < mem->nr_ranges; i++) {
 		start = mem->ranges[i].start;
 		end = mem->ranges[i].end;
+		p_start = mstart;
+		p_end = mend;
 
 		if (mstart > end || mend < start)
 			continue;
 
 		/* Truncate any area outside of range */
 		if (mstart < start)
-			mstart = start;
+			p_start = start;
 		if (mend > end)
-			mend = end;
+			p_end = end;
 
 		/* Found completely overlapping range */
-		if (mstart == start && mend == end) {
+		if (p_start == start && p_end == end) {
 			mem->ranges[i].start = 0;
 			mem->ranges[i].end = 0;
 			if (i < mem->nr_ranges - 1) {
@@ -1202,20 +1199,29 @@ int crash_exclude_mem_range(struct crash_mem *mem,
 					mem->ranges[j].end =
 							mem->ranges[j+1].end;
 				}
+
+				/*
+				 * Continue to check if there are another overlapping ranges
+				 * from the current position because of shifting the above
+				 * mem ranges.
+				 */
+				i--;
+				mem->nr_ranges--;
+				continue;
 			}
 			mem->nr_ranges--;
 			return 0;
 		}
 
-		if (mstart > start && mend < end) {
+		if (p_start > start && p_end < end) {
 			/* Split original range */
-			mem->ranges[i].end = mstart - 1;
-			temp_range.start = mend + 1;
+			mem->ranges[i].end = p_start - 1;
+			temp_range.start = p_end + 1;
 			temp_range.end = end;
-		} else if (mstart != start)
-			mem->ranges[i].end = mstart - 1;
+		} else if (p_start != start)
+			mem->ranges[i].end = p_start - 1;
 		else
-			mem->ranges[i].start = mend + 1;
+			mem->ranges[i].start = p_end + 1;
 		break;
 	}
 
@@ -1252,7 +1258,7 @@ int crash_prepare_elf64_headers(struct crash_mem *mem, int kernel_map,
 	unsigned long long notes_addr;
 	unsigned long mstart, mend;
 
-	/* extra phdr for vmcoreinfo elf note */
+	/* extra phdr for vmcoreinfo ELF note */
 	nr_phdr = nr_cpus + 1;
 	nr_phdr += mem->nr_ranges;
 
@@ -1260,7 +1266,7 @@ int crash_prepare_elf64_headers(struct crash_mem *mem, int kernel_map,
 	 * kexec-tools creates an extra PT_LOAD phdr for kernel text mapping
 	 * area (for example, ffffffff80000000 - ffffffffa0000000 on x86_64).
 	 * I think this is required by tools like gdb. So same physical
-	 * memory will be mapped in two elf headers. One will contain kernel
+	 * memory will be mapped in two ELF headers. One will contain kernel
 	 * text virtual addresses and other will have __va(physical) addresses.
 	 */
 
@@ -1287,7 +1293,7 @@ int crash_prepare_elf64_headers(struct crash_mem *mem, int kernel_map,
 	ehdr->e_ehsize = sizeof(Elf64_Ehdr);
 	ehdr->e_phentsize = sizeof(Elf64_Phdr);
 
-	/* Prepare one phdr of type PT_NOTE for each present cpu */
+	/* Prepare one phdr of type PT_NOTE for each present CPU */
 	for_each_present_cpu(cpu) {
 		phdr->p_type = PT_NOTE;
 		notes_addr = per_cpu_ptr_to_phys(per_cpu_ptr(crash_notes, cpu));
@@ -1329,10 +1335,10 @@ int crash_prepare_elf64_headers(struct crash_mem *mem, int kernel_map,
 		phdr->p_filesz = phdr->p_memsz = mend - mstart + 1;
 		phdr->p_align = 0;
 		ehdr->e_phnum++;
-		phdr++;
-		pr_debug("Crash PT_LOAD elf header. phdr=%p vaddr=0x%llx, paddr=0x%llx, sz=0x%llx e_phnum=%d p_offset=0x%llx\n",
+		pr_debug("Crash PT_LOAD ELF header. phdr=%p vaddr=0x%llx, paddr=0x%llx, sz=0x%llx e_phnum=%d p_offset=0x%llx\n",
 			phdr, phdr->p_vaddr, phdr->p_paddr, phdr->p_filesz,
 			ehdr->e_phnum, phdr->p_offset);
+		phdr++;
 	}
 
 	*addr = buf;
diff --git a/kernel/kmod.c b/kernel/kmod.c
index bc6addd9152b..3cd075ce2a1e 100644
--- a/kernel/kmod.c
+++ b/kernel/kmod.c
@@ -35,10 +35,9 @@
  *		       (u64) THREAD_SIZE * 8UL);
  *
  * If you need less than 50 threads would mean we're dealing with systems
- * smaller than 3200 pages. This assuems you are capable of having ~13M memory,
- * and this would only be an be an upper limit, after which the OOM killer
- * would take effect. Systems like these are very unlikely if modules are
- * enabled.
+ * smaller than 3200 pages. This assumes you are capable of having ~13M memory,
+ * and this would only be an upper limit, after which the OOM killer would take
+ * effect. Systems like these are very unlikely if modules are enabled.
  */
 #define MAX_KMOD_CONCURRENT 50
 static atomic_t kmod_concurrent_max = ATOMIC_INIT(MAX_KMOD_CONCURRENT);
@@ -120,7 +119,7 @@ out:
  * invoke it.
  *
  * If module auto-loading support is disabled then this function
- * becomes a no-operation.
+ * simply returns -ENOENT.
  */
 int __request_module(bool wait, const char *fmt, ...)
 {
@@ -137,7 +136,7 @@ int __request_module(bool wait, const char *fmt, ...)
 	WARN_ON_ONCE(wait && current_is_async());
 
 	if (!modprobe_path[0])
-		return 0;
+		return -ENOENT;
 
 	va_start(args, fmt);
 	ret = vsnprintf(module_name, MODULE_NAME_LEN, fmt, args);
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 2625c241ac00..287b263c9cb9 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -35,6 +35,7 @@
 #include <linux/ftrace.h>
 #include <linux/cpu.h>
 #include <linux/jump_label.h>
+#include <linux/perf_event.h>
 
 #include <asm/sections.h>
 #include <asm/cacheflush.h>
@@ -46,6 +47,11 @@
 
 
 static int kprobes_initialized;
+/* kprobe_table can be accessed by
+ * - Normal hlist traversal and RCU add/del under kprobe_mutex is held.
+ * Or
+ * - RCU hlist traversal under disabling preempt (breakpoint handlers)
+ */
 static struct hlist_head kprobe_table[KPROBE_TABLE_SIZE];
 static struct hlist_head kretprobe_inst_table[KPROBE_TABLE_SIZE];
 
@@ -118,6 +124,7 @@ struct kprobe_insn_cache kprobe_insn_slots = {
 	.mutex = __MUTEX_INITIALIZER(kprobe_insn_slots.mutex),
 	.alloc = alloc_insn_page,
 	.free = free_insn_page,
+	.sym = KPROBE_INSN_PAGE_SYM,
 	.pages = LIST_HEAD_INIT(kprobe_insn_slots.pages),
 	.insn_size = MAX_INSN_SIZE,
 	.nr_garbage = 0,
@@ -183,6 +190,10 @@ kprobe_opcode_t *__get_insn_slot(struct kprobe_insn_cache *c)
 	kip->cache = c;
 	list_add_rcu(&kip->list, &c->pages);
 	slot = kip->insns;
+
+	/* Record the perf ksymbol register event after adding the page */
+	perf_event_ksymbol(PERF_RECORD_KSYMBOL_TYPE_OOL, (unsigned long)kip->insns,
+			   PAGE_SIZE, false, c->sym);
 out:
 	mutex_unlock(&c->mutex);
 	return slot;
@@ -201,6 +212,13 @@ static int collect_one_slot(struct kprobe_insn_page *kip, int idx)
 		 * next time somebody inserts a probe.
 		 */
 		if (!list_is_singular(&kip->list)) {
+			/*
+			 * Record perf ksymbol unregister event before removing
+			 * the page.
+			 */
+			perf_event_ksymbol(PERF_RECORD_KSYMBOL_TYPE_OOL,
+					   (unsigned long)kip->insns, PAGE_SIZE, true,
+					   kip->cache->sym);
 			list_del_rcu(&kip->list);
 			synchronize_rcu();
 			kip->cache->free(kip->insns);
@@ -290,12 +308,34 @@ bool __is_insn_slot_addr(struct kprobe_insn_cache *c, unsigned long addr)
 	return ret;
 }
 
+int kprobe_cache_get_kallsym(struct kprobe_insn_cache *c, unsigned int *symnum,
+			     unsigned long *value, char *type, char *sym)
+{
+	struct kprobe_insn_page *kip;
+	int ret = -ERANGE;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(kip, &c->pages, list) {
+		if ((*symnum)--)
+			continue;
+		strlcpy(sym, c->sym, KSYM_NAME_LEN);
+		*type = 't';
+		*value = (unsigned long)kip->insns;
+		ret = 0;
+		break;
+	}
+	rcu_read_unlock();
+
+	return ret;
+}
+
 #ifdef CONFIG_OPTPROBES
 /* For optimized_kprobe buffer */
 struct kprobe_insn_cache kprobe_optinsn_slots = {
 	.mutex = __MUTEX_INITIALIZER(kprobe_optinsn_slots.mutex),
 	.alloc = alloc_insn_page,
 	.free = free_insn_page,
+	.sym = KPROBE_OPTINSN_PAGE_SYM,
 	.pages = LIST_HEAD_INIT(kprobe_optinsn_slots.pages),
 	/* .insn_size is initialized later */
 	.nr_garbage = 0,
@@ -326,7 +366,8 @@ struct kprobe *get_kprobe(void *addr)
 	struct kprobe *p;
 
 	head = &kprobe_table[hash_ptr(addr, KPROBE_HASH_BITS)];
-	hlist_for_each_entry_rcu(p, head, hlist) {
+	hlist_for_each_entry_rcu(p, head, hlist,
+				 lockdep_is_held(&kprobe_mutex)) {
 		if (p->addr == addr)
 			return p;
 	}
@@ -557,8 +598,6 @@ static void kprobe_optimizer(struct work_struct *work)
 	mutex_lock(&kprobe_mutex);
 	cpus_read_lock();
 	mutex_lock(&text_mutex);
-	/* Lock modules while optimizing kprobes */
-	mutex_lock(&module_mutex);
 
 	/*
 	 * Step 1: Unoptimize kprobes and collect cleaned (unused and disarmed)
@@ -583,14 +622,14 @@ static void kprobe_optimizer(struct work_struct *work)
 	/* Step 4: Free cleaned kprobes after quiesence period */
 	do_free_cleaned_kprobes();
 
-	mutex_unlock(&module_mutex);
 	mutex_unlock(&text_mutex);
 	cpus_read_unlock();
-	mutex_unlock(&kprobe_mutex);
 
 	/* Step 5: Kick optimizer again if needed */
 	if (!list_empty(&optimizing_list) || !list_empty(&unoptimizing_list))
 		kick_kprobe_optimizer();
+
+	mutex_unlock(&kprobe_mutex);
 }
 
 /* Wait for completing optimization and unoptimization */
@@ -668,8 +707,6 @@ static void force_unoptimize_kprobe(struct optimized_kprobe *op)
 	lockdep_assert_cpus_held();
 	arch_unoptimize_kprobe(op);
 	op->kp.flags &= ~KPROBE_FLAG_OPTIMIZED;
-	if (kprobe_disabled(&op->kp))
-		arch_disarm_kprobe(&op->kp);
 }
 
 /* Unoptimize a kprobe if p is optimized */
@@ -849,7 +886,7 @@ static void optimize_all_kprobes(void)
 	kprobes_allow_optimization = true;
 	for (i = 0; i < KPROBE_TABLE_SIZE; i++) {
 		head = &kprobe_table[i];
-		hlist_for_each_entry_rcu(p, head, hlist)
+		hlist_for_each_entry(p, head, hlist)
 			if (!kprobe_disabled(p))
 				optimize_kprobe(p);
 	}
@@ -876,7 +913,7 @@ static void unoptimize_all_kprobes(void)
 	kprobes_allow_optimization = false;
 	for (i = 0; i < KPROBE_TABLE_SIZE; i++) {
 		head = &kprobe_table[i];
-		hlist_for_each_entry_rcu(p, head, hlist) {
+		hlist_for_each_entry(p, head, hlist) {
 			if (!kprobe_disabled(p))
 				unoptimize_kprobe(p, false);
 		}
@@ -892,7 +929,7 @@ static void unoptimize_all_kprobes(void)
 static DEFINE_MUTEX(kprobe_sysctl_mutex);
 int sysctl_kprobes_optimization;
 int proc_kprobes_optimization_handler(struct ctl_table *table, int write,
-				      void __user *buffer, size_t *length,
+				      void *buffer, size_t *length,
 				      loff_t *ppos)
 {
 	int ret;
@@ -1074,9 +1111,20 @@ static int disarm_kprobe_ftrace(struct kprobe *p)
 		ipmodify ? &kprobe_ipmodify_enabled : &kprobe_ftrace_enabled);
 }
 #else	/* !CONFIG_KPROBES_ON_FTRACE */
-#define prepare_kprobe(p)	arch_prepare_kprobe(p)
-#define arm_kprobe_ftrace(p)	(-ENODEV)
-#define disarm_kprobe_ftrace(p)	(-ENODEV)
+static inline int prepare_kprobe(struct kprobe *p)
+{
+	return arch_prepare_kprobe(p);
+}
+
+static inline int arm_kprobe_ftrace(struct kprobe *p)
+{
+	return -ENODEV;
+}
+
+static inline int disarm_kprobe_ftrace(struct kprobe *p)
+{
+	return -ENODEV;
+}
 #endif
 
 /* Arm a kprobe with text_mutex */
@@ -1236,6 +1284,26 @@ __releases(hlist_lock)
 }
 NOKPROBE_SYMBOL(kretprobe_table_unlock);
 
+struct kprobe kprobe_busy = {
+	.addr = (void *) get_kprobe,
+};
+
+void kprobe_busy_begin(void)
+{
+	struct kprobe_ctlblk *kcb;
+
+	preempt_disable();
+	__this_cpu_write(current_kprobe, &kprobe_busy);
+	kcb = get_kprobe_ctlblk();
+	kcb->kprobe_status = KPROBE_HIT_ACTIVE;
+}
+
+void kprobe_busy_end(void)
+{
+	__this_cpu_write(current_kprobe, NULL);
+	preempt_enable();
+}
+
 /*
  * This function is called from finish_task_switch when task tk becomes dead,
  * so that we can recycle any function-return probe instances associated
@@ -1253,6 +1321,8 @@ void kprobe_flush_task(struct task_struct *tk)
 		/* Early boot.  kretprobe_table_locks not yet initialized. */
 		return;
 
+	kprobe_busy_begin();
+
 	INIT_HLIST_HEAD(&empty_rp);
 	hash = hash_ptr(tk, KPROBE_HASH_BITS);
 	head = &kretprobe_inst_table[hash];
@@ -1266,6 +1336,8 @@ void kprobe_flush_task(struct task_struct *tk)
 		hlist_del(&ri->hlist);
 		kfree(ri);
 	}
+
+	kprobe_busy_end();
 }
 NOKPROBE_SYMBOL(kprobe_flush_task);
 
@@ -1499,12 +1571,14 @@ static struct kprobe *__get_valid_kprobe(struct kprobe *p)
 {
 	struct kprobe *ap, *list_p;
 
+	lockdep_assert_held(&kprobe_mutex);
+
 	ap = get_kprobe(p->addr);
 	if (unlikely(!ap))
 		return NULL;
 
 	if (p != ap) {
-		list_for_each_entry_rcu(list_p, &ap->list, list)
+		list_for_each_entry(list_p, &ap->list, list)
 			if (list_p == p)
 			/* kprobe p is a valid probe */
 				goto valid;
@@ -1669,7 +1743,9 @@ static int aggr_kprobe_disabled(struct kprobe *ap)
 {
 	struct kprobe *kp;
 
-	list_for_each_entry_rcu(kp, &ap->list, list)
+	lockdep_assert_held(&kprobe_mutex);
+
+	list_for_each_entry(kp, &ap->list, list)
 		if (!kprobe_disabled(kp))
 			/*
 			 * There is an active probe on the list.
@@ -1748,7 +1824,7 @@ static int __unregister_kprobe_top(struct kprobe *p)
 	else {
 		/* If disabling probe has special handlers, update aggrprobe */
 		if (p->post_handler && !kprobe_gone(p)) {
-			list_for_each_entry_rcu(list_p, &ap->list, list) {
+			list_for_each_entry(list_p, &ap->list, list) {
 				if ((list_p != p) && (list_p->post_handler))
 					goto noclean;
 			}
@@ -2062,13 +2138,15 @@ static void kill_kprobe(struct kprobe *p)
 {
 	struct kprobe *kp;
 
+	lockdep_assert_held(&kprobe_mutex);
+
 	p->flags |= KPROBE_FLAG_GONE;
 	if (kprobe_aggrprobe(p)) {
 		/*
 		 * If this is an aggr_kprobe, we have to list all the
 		 * chained probes and mark them GONE.
 		 */
-		list_for_each_entry_rcu(kp, &p->list, list)
+		list_for_each_entry(kp, &p->list, list)
 			kp->flags |= KPROBE_FLAG_GONE;
 		p->post_handler = NULL;
 		kill_optimized_kprobe(p);
@@ -2078,6 +2156,13 @@ static void kill_kprobe(struct kprobe *p)
 	 * the original probed function (which will be freed soon) any more.
 	 */
 	arch_remove_kprobe(p);
+
+	/*
+	 * The module is going away. We should disarm the kprobe which
+	 * is using ftrace.
+	 */
+	if (kprobe_ftrace(p))
+		disarm_kprobe_ftrace(p);
 }
 
 /* Disable one kprobe */
@@ -2179,6 +2264,46 @@ int kprobe_add_area_blacklist(unsigned long start, unsigned long end)
 	return 0;
 }
 
+/* Remove all symbols in given area from kprobe blacklist */
+static void kprobe_remove_area_blacklist(unsigned long start, unsigned long end)
+{
+	struct kprobe_blacklist_entry *ent, *n;
+
+	list_for_each_entry_safe(ent, n, &kprobe_blacklist, list) {
+		if (ent->start_addr < start || ent->start_addr >= end)
+			continue;
+		list_del(&ent->list);
+		kfree(ent);
+	}
+}
+
+static void kprobe_remove_ksym_blacklist(unsigned long entry)
+{
+	kprobe_remove_area_blacklist(entry, entry + 1);
+}
+
+int __weak arch_kprobe_get_kallsym(unsigned int *symnum, unsigned long *value,
+				   char *type, char *sym)
+{
+	return -ERANGE;
+}
+
+int kprobe_get_kallsym(unsigned int symnum, unsigned long *value, char *type,
+		       char *sym)
+{
+#ifdef __ARCH_WANT_KPROBES_INSN_SLOT
+	if (!kprobe_cache_get_kallsym(&kprobe_insn_slots, &symnum, value, type, sym))
+		return 0;
+#ifdef CONFIG_OPTPROBES
+	if (!kprobe_cache_get_kallsym(&kprobe_optinsn_slots, &symnum, value, type, sym))
+		return 0;
+#endif
+#endif
+	if (!arch_kprobe_get_kallsym(&symnum, value, type, sym))
+		return 0;
+	return -ERANGE;
+}
+
 int __init __weak arch_populate_kprobe_blacklist(void)
 {
 	return 0;
@@ -2211,10 +2336,62 @@ static int __init populate_kprobe_blacklist(unsigned long *start,
 	/* Symbols in __kprobes_text are blacklisted */
 	ret = kprobe_add_area_blacklist((unsigned long)__kprobes_text_start,
 					(unsigned long)__kprobes_text_end);
+	if (ret)
+		return ret;
+
+	/* Symbols in noinstr section are blacklisted */
+	ret = kprobe_add_area_blacklist((unsigned long)__noinstr_text_start,
+					(unsigned long)__noinstr_text_end);
 
 	return ret ? : arch_populate_kprobe_blacklist();
 }
 
+static void add_module_kprobe_blacklist(struct module *mod)
+{
+	unsigned long start, end;
+	int i;
+
+	if (mod->kprobe_blacklist) {
+		for (i = 0; i < mod->num_kprobe_blacklist; i++)
+			kprobe_add_ksym_blacklist(mod->kprobe_blacklist[i]);
+	}
+
+	start = (unsigned long)mod->kprobes_text_start;
+	if (start) {
+		end = start + mod->kprobes_text_size;
+		kprobe_add_area_blacklist(start, end);
+	}
+
+	start = (unsigned long)mod->noinstr_text_start;
+	if (start) {
+		end = start + mod->noinstr_text_size;
+		kprobe_add_area_blacklist(start, end);
+	}
+}
+
+static void remove_module_kprobe_blacklist(struct module *mod)
+{
+	unsigned long start, end;
+	int i;
+
+	if (mod->kprobe_blacklist) {
+		for (i = 0; i < mod->num_kprobe_blacklist; i++)
+			kprobe_remove_ksym_blacklist(mod->kprobe_blacklist[i]);
+	}
+
+	start = (unsigned long)mod->kprobes_text_start;
+	if (start) {
+		end = start + mod->kprobes_text_size;
+		kprobe_remove_area_blacklist(start, end);
+	}
+
+	start = (unsigned long)mod->noinstr_text_start;
+	if (start) {
+		end = start + mod->noinstr_text_size;
+		kprobe_remove_area_blacklist(start, end);
+	}
+}
+
 /* Module notifier call back, checking kprobes on the module */
 static int kprobes_module_callback(struct notifier_block *nb,
 				   unsigned long val, void *data)
@@ -2225,6 +2402,11 @@ static int kprobes_module_callback(struct notifier_block *nb,
 	unsigned int i;
 	int checkcore = (val == MODULE_STATE_GOING);
 
+	if (val == MODULE_STATE_COMING) {
+		mutex_lock(&kprobe_mutex);
+		add_module_kprobe_blacklist(mod);
+		mutex_unlock(&kprobe_mutex);
+	}
 	if (val != MODULE_STATE_GOING && val != MODULE_STATE_LIVE)
 		return NOTIFY_DONE;
 
@@ -2237,7 +2419,7 @@ 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_rcu(p, head, hlist)
+		hlist_for_each_entry(p, head, hlist)
 			if (within_module_init((unsigned long)p->addr, mod) ||
 			    (checkcore &&
 			     within_module_core((unsigned long)p->addr, mod))) {
@@ -2255,6 +2437,8 @@ static int kprobes_module_callback(struct notifier_block *nb,
 				kill_kprobe(p);
 			}
 	}
+	if (val == MODULE_STATE_GOING)
+		remove_module_kprobe_blacklist(mod);
 	mutex_unlock(&kprobe_mutex);
 	return NOTIFY_DONE;
 }
@@ -2336,7 +2520,7 @@ static void report_probe(struct seq_file *pi, struct kprobe *p,
 	else
 		kprobe_type = "k";
 
-	if (!kallsyms_show_value())
+	if (!kallsyms_show_value(pi->file->f_cred))
 		addr = NULL;
 
 	if (sym)
@@ -2398,28 +2582,19 @@ static int show_kprobe_addr(struct seq_file *pi, void *v)
 	return 0;
 }
 
-static const struct seq_operations kprobes_seq_ops = {
+static const struct seq_operations kprobes_sops = {
 	.start = kprobe_seq_start,
 	.next  = kprobe_seq_next,
 	.stop  = kprobe_seq_stop,
 	.show  = show_kprobe_addr
 };
 
-static int kprobes_open(struct inode *inode, struct file *filp)
-{
-	return seq_open(filp, &kprobes_seq_ops);
-}
-
-static const struct file_operations debugfs_kprobes_operations = {
-	.open           = kprobes_open,
-	.read           = seq_read,
-	.llseek         = seq_lseek,
-	.release        = seq_release,
-};
+DEFINE_SEQ_ATTRIBUTE(kprobes);
 
 /* kprobes/blacklist -- shows which functions can not be probed */
 static void *kprobe_blacklist_seq_start(struct seq_file *m, loff_t *pos)
 {
+	mutex_lock(&kprobe_mutex);
 	return seq_list_start(&kprobe_blacklist, *pos);
 }
 
@@ -2437,7 +2612,7 @@ static int kprobe_blacklist_seq_show(struct seq_file *m, void *v)
 	 * If /proc/kallsyms is not showing kernel address, we won't
 	 * show them here either.
 	 */
-	if (!kallsyms_show_value())
+	if (!kallsyms_show_value(m->file->f_cred))
 		seq_printf(m, "0x%px-0x%px\t%ps\n", NULL, NULL,
 			   (void *)ent->start_addr);
 	else
@@ -2446,24 +2621,18 @@ static int kprobe_blacklist_seq_show(struct seq_file *m, void *v)
 	return 0;
 }
 
-static const struct seq_operations kprobe_blacklist_seq_ops = {
-	.start = kprobe_blacklist_seq_start,
-	.next  = kprobe_blacklist_seq_next,
-	.stop  = kprobe_seq_stop,	/* Reuse void function */
-	.show  = kprobe_blacklist_seq_show,
-};
-
-static int kprobe_blacklist_open(struct inode *inode, struct file *filp)
+static void kprobe_blacklist_seq_stop(struct seq_file *f, void *v)
 {
-	return seq_open(filp, &kprobe_blacklist_seq_ops);
+	mutex_unlock(&kprobe_mutex);
 }
 
-static const struct file_operations debugfs_kprobe_blacklist_ops = {
-	.open           = kprobe_blacklist_open,
-	.read           = seq_read,
-	.llseek         = seq_lseek,
-	.release        = seq_release,
+static const struct seq_operations kprobe_blacklist_sops = {
+	.start = kprobe_blacklist_seq_start,
+	.next  = kprobe_blacklist_seq_next,
+	.stop  = kprobe_blacklist_seq_stop,
+	.show  = kprobe_blacklist_seq_show,
 };
+DEFINE_SEQ_ATTRIBUTE(kprobe_blacklist);
 
 static int arm_all_kprobes(void)
 {
@@ -2488,7 +2657,7 @@ static int arm_all_kprobes(void)
 	for (i = 0; i < KPROBE_TABLE_SIZE; i++) {
 		head = &kprobe_table[i];
 		/* Arm all kprobes on a best-effort basis */
-		hlist_for_each_entry_rcu(p, head, hlist) {
+		hlist_for_each_entry(p, head, hlist) {
 			if (!kprobe_disabled(p)) {
 				err = arm_kprobe(p);
 				if (err)  {
@@ -2531,7 +2700,7 @@ static int disarm_all_kprobes(void)
 	for (i = 0; i < KPROBE_TABLE_SIZE; i++) {
 		head = &kprobe_table[i];
 		/* Disarm all kprobes on a best-effort basis */
-		hlist_for_each_entry_rcu(p, head, hlist) {
+		hlist_for_each_entry(p, head, hlist) {
 			if (!arch_trampoline_kprobe(p) && !kprobe_disabled(p)) {
 				err = disarm_kprobe(p, false);
 				if (err) {
@@ -2622,13 +2791,12 @@ static int __init debugfs_kprobe_init(void)
 
 	dir = debugfs_create_dir("kprobes", NULL);
 
-	debugfs_create_file("list", 0400, dir, NULL,
-			    &debugfs_kprobes_operations);
+	debugfs_create_file("list", 0400, dir, NULL, &kprobes_fops);
 
 	debugfs_create_file("enabled", 0600, dir, &value, &fops_kp);
 
 	debugfs_create_file("blacklist", 0400, dir, NULL,
-			    &debugfs_kprobe_blacklist_ops);
+			    &kprobe_blacklist_fops);
 
 	return 0;
 }
diff --git a/kernel/kthread.c b/kernel/kthread.c
index b262f47046ca..3edaa380dc7b 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -1,13 +1,17 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /* Kernel thread helper functions.
  *   Copyright (C) 2004 IBM Corporation, Rusty Russell.
+ *   Copyright (C) 2009 Red Hat, Inc.
  *
  * Creation is done via kthreadd, so that we get a clean environment
  * even if we're invoked from userspace (think modprobe, hotplug cpu,
  * etc.).
  */
 #include <uapi/linux/sched/types.h>
+#include <linux/mm.h>
+#include <linux/mmu_context.h>
 #include <linux/sched.h>
+#include <linux/sched/mm.h>
 #include <linux/sched/task.h>
 #include <linux/kthread.h>
 #include <linux/completion.h>
@@ -23,8 +27,10 @@
 #include <linux/ptrace.h>
 #include <linux/uaccess.h>
 #include <linux/numa.h>
+#include <linux/sched/isolation.h>
 #include <trace/events/sched.h>
 
+
 static DEFINE_SPINLOCK(kthread_create_lock);
 static LIST_HEAD(kthread_create_list);
 struct task_struct *kthreadd_task;
@@ -46,7 +52,9 @@ struct kthread_create_info
 struct kthread {
 	unsigned long flags;
 	unsigned int cpu;
+	int (*threadfn)(void *);
 	void *data;
+	mm_segment_t oldfs;
 	struct completion parked;
 	struct completion exited;
 #ifdef CONFIG_BLK_CGROUP
@@ -153,6 +161,20 @@ bool kthread_freezable_should_stop(bool *was_frozen)
 EXPORT_SYMBOL_GPL(kthread_freezable_should_stop);
 
 /**
+ * kthread_func - return the function specified on kthread creation
+ * @task: kthread task in question
+ *
+ * Returns NULL if the task is not a kthread.
+ */
+void *kthread_func(struct task_struct *task)
+{
+	if (task->flags & PF_KTHREAD)
+		return to_kthread(task)->threadfn;
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(kthread_func);
+
+/**
  * kthread_data - return data value specified on kthread creation
  * @task: kthread task in question
  *
@@ -164,6 +186,7 @@ void *kthread_data(struct task_struct *task)
 {
 	return to_kthread(task)->data;
 }
+EXPORT_SYMBOL_GPL(kthread_data);
 
 /**
  * kthread_probe_data - speculative version of kthread_data()
@@ -179,7 +202,7 @@ void *kthread_probe_data(struct task_struct *task)
 	struct kthread *kthread = to_kthread(task);
 	void *data = NULL;
 
-	probe_kernel_read(&data, &kthread->data, sizeof(data));
+	copy_from_kernel_nofault(&data, &kthread->data, sizeof(data));
 	return data;
 }
 
@@ -199,8 +222,15 @@ static void __kthread_parkme(struct kthread *self)
 		if (!test_bit(KTHREAD_SHOULD_PARK, &self->flags))
 			break;
 
+		/*
+		 * Thread is going to call schedule(), do not preempt it,
+		 * or the caller of kthread_park() may spend more time in
+		 * wait_task_inactive().
+		 */
+		preempt_disable();
 		complete(&self->parked);
-		schedule();
+		schedule_preempt_disabled();
+		preempt_enable();
 	}
 	__set_current_state(TASK_RUNNING);
 }
@@ -237,6 +267,7 @@ static int kthread(void *_create)
 		do_exit(-ENOMEM);
 	}
 
+	self->threadfn = threadfn;
 	self->data = data;
 	init_completion(&self->exited);
 	init_completion(&self->parked);
@@ -245,8 +276,14 @@ static int kthread(void *_create)
 	/* OK, tell user we're spawned, wait for stop or wakeup */
 	__set_current_state(TASK_UNINTERRUPTIBLE);
 	create->result = current;
+	/*
+	 * Thread is going to call schedule(), do not preempt it,
+	 * or the creator may spend more time in wait_task_inactive().
+	 */
+	preempt_disable();
 	complete(done);
-	schedule();
+	schedule_preempt_disabled();
+	preempt_enable();
 
 	ret = -EINTR;
 	if (!test_bit(KTHREAD_SHOULD_STOP, &self->flags)) {
@@ -347,7 +384,8 @@ struct task_struct *__kthread_create_on_node(int (*threadfn)(void *data),
 		 * The kernel thread should not inherit these properties.
 		 */
 		sched_setscheduler_nocheck(task, SCHED_NORMAL, &param);
-		set_cpus_allowed_ptr(task, cpu_all_mask);
+		set_cpus_allowed_ptr(task,
+				     housekeeping_cpumask(HK_FLAG_KTHREAD));
 	}
 	kfree(create);
 	return task;
@@ -442,7 +480,6 @@ EXPORT_SYMBOL(kthread_bind);
  *	     to "name.*%u". Code fills in cpu number.
  *
  * Description: This helper function creates and names a kernel thread
- * The thread will be woken and put into park mode.
  */
 struct task_struct *kthread_create_on_cpu(int (*threadfn)(void *data),
 					  void *data, unsigned int cpu,
@@ -572,7 +609,7 @@ int kthreadd(void *unused)
 	/* Setup a clean context for our children to inherit. */
 	set_task_comm(tsk, "kthreadd");
 	ignore_signals(tsk);
-	set_cpus_allowed_ptr(tsk, cpu_all_mask);
+	set_cpus_allowed_ptr(tsk, housekeeping_cpumask(HK_FLAG_KTHREAD));
 	set_mems_allowed(node_states[N_MEMORY]);
 
 	current->flags |= PF_NOFREEZE;
@@ -1190,6 +1227,65 @@ void kthread_destroy_worker(struct kthread_worker *worker)
 }
 EXPORT_SYMBOL(kthread_destroy_worker);
 
+/**
+ * kthread_use_mm - make the calling kthread operate on an address space
+ * @mm: address space to operate on
+ */
+void kthread_use_mm(struct mm_struct *mm)
+{
+	struct mm_struct *active_mm;
+	struct task_struct *tsk = current;
+
+	WARN_ON_ONCE(!(tsk->flags & PF_KTHREAD));
+	WARN_ON_ONCE(tsk->mm);
+
+	task_lock(tsk);
+	/* Hold off tlb flush IPIs while switching mm's */
+	local_irq_disable();
+	active_mm = tsk->active_mm;
+	if (active_mm != mm) {
+		mmgrab(mm);
+		tsk->active_mm = mm;
+	}
+	tsk->mm = mm;
+	switch_mm_irqs_off(active_mm, mm, tsk);
+	local_irq_enable();
+	task_unlock(tsk);
+#ifdef finish_arch_post_lock_switch
+	finish_arch_post_lock_switch();
+#endif
+
+	if (active_mm != mm)
+		mmdrop(active_mm);
+
+	to_kthread(tsk)->oldfs = force_uaccess_begin();
+}
+EXPORT_SYMBOL_GPL(kthread_use_mm);
+
+/**
+ * kthread_unuse_mm - reverse the effect of kthread_use_mm()
+ * @mm: address space to operate on
+ */
+void kthread_unuse_mm(struct mm_struct *mm)
+{
+	struct task_struct *tsk = current;
+
+	WARN_ON_ONCE(!(tsk->flags & PF_KTHREAD));
+	WARN_ON_ONCE(!tsk->mm);
+
+	force_uaccess_end(to_kthread(tsk)->oldfs);
+
+	task_lock(tsk);
+	sync_mm_rss(mm);
+	local_irq_disable();
+	tsk->mm = NULL;
+	/* active_mm is still 'mm' */
+	enter_lazy_tlb(mm, tsk);
+	local_irq_enable();
+	task_unlock(tsk);
+}
+EXPORT_SYMBOL_GPL(kthread_unuse_mm);
+
 #ifdef CONFIG_BLK_CGROUP
 /**
  * kthread_associate_blkcg - associate blkcg to current kthread
diff --git a/kernel/latencytop.c b/kernel/latencytop.c
index 8d1c15832e55..166d7bf49666 100644
--- a/kernel/latencytop.c
+++ b/kernel/latencytop.c
@@ -269,8 +269,8 @@ static int __init init_lstats_procfs(void)
 	return 0;
 }
 
-int sysctl_latencytop(struct ctl_table *table, int write,
-			void __user *buffer, size_t *lenp, loff_t *ppos)
+int sysctl_latencytop(struct ctl_table *table, int write, void *buffer,
+		size_t *lenp, loff_t *ppos)
 {
 	int err;
 
diff --git a/kernel/livepatch/core.c b/kernel/livepatch/core.c
index c3512e7e0801..f76fdb925532 100644
--- a/kernel/livepatch/core.c
+++ b/kernel/livepatch/core.c
@@ -191,18 +191,21 @@ static int klp_find_object_symbol(const char *objname, const char *name,
 	return -EINVAL;
 }
 
-static int klp_resolve_symbols(Elf_Shdr *relasec, struct module *pmod)
+static int klp_resolve_symbols(Elf64_Shdr *sechdrs, const char *strtab,
+			       unsigned int symndx, Elf_Shdr *relasec,
+			       const char *sec_objname)
 {
-	int i, cnt, vmlinux, ret;
-	char objname[MODULE_NAME_LEN];
-	char symname[KSYM_NAME_LEN];
-	char *strtab = pmod->core_kallsyms.strtab;
+	int i, cnt, ret;
+	char sym_objname[MODULE_NAME_LEN];
+	char sym_name[KSYM_NAME_LEN];
 	Elf_Rela *relas;
 	Elf_Sym *sym;
 	unsigned long sympos, addr;
+	bool sym_vmlinux;
+	bool sec_vmlinux = !strcmp(sec_objname, "vmlinux");
 
 	/*
-	 * Since the field widths for objname and symname in the sscanf()
+	 * Since the field widths for sym_objname and sym_name in the sscanf()
 	 * call are hard-coded and correspond to MODULE_NAME_LEN and
 	 * KSYM_NAME_LEN respectively, we must make sure that MODULE_NAME_LEN
 	 * and KSYM_NAME_LEN have the values we expect them to have.
@@ -216,27 +219,40 @@ static int klp_resolve_symbols(Elf_Shdr *relasec, struct module *pmod)
 	relas = (Elf_Rela *) relasec->sh_addr;
 	/* For each rela in this klp relocation section */
 	for (i = 0; i < relasec->sh_size / sizeof(Elf_Rela); i++) {
-		sym = pmod->core_kallsyms.symtab + ELF_R_SYM(relas[i].r_info);
+		sym = (Elf64_Sym *)sechdrs[symndx].sh_addr + ELF_R_SYM(relas[i].r_info);
 		if (sym->st_shndx != SHN_LIVEPATCH) {
 			pr_err("symbol %s is not marked as a livepatch symbol\n",
 			       strtab + sym->st_name);
 			return -EINVAL;
 		}
 
-		/* Format: .klp.sym.objname.symname,sympos */
+		/* Format: .klp.sym.sym_objname.sym_name,sympos */
 		cnt = sscanf(strtab + sym->st_name,
 			     ".klp.sym.%55[^.].%127[^,],%lu",
-			     objname, symname, &sympos);
+			     sym_objname, sym_name, &sympos);
 		if (cnt != 3) {
 			pr_err("symbol %s has an incorrectly formatted name\n",
 			       strtab + sym->st_name);
 			return -EINVAL;
 		}
 
+		sym_vmlinux = !strcmp(sym_objname, "vmlinux");
+
+		/*
+		 * Prevent module-specific KLP rela sections from referencing
+		 * vmlinux symbols.  This helps prevent ordering issues with
+		 * module special section initializations.  Presumably such
+		 * symbols are exported and normal relas can be used instead.
+		 */
+		if (!sec_vmlinux && sym_vmlinux) {
+			pr_err("invalid access to vmlinux symbol '%s' from module-specific livepatch relocation section",
+			       sym_name);
+			return -EINVAL;
+		}
+
 		/* klp_find_object_symbol() treats a NULL objname as vmlinux */
-		vmlinux = !strcmp(objname, "vmlinux");
-		ret = klp_find_object_symbol(vmlinux ? NULL : objname,
-					     symname, sympos, &addr);
+		ret = klp_find_object_symbol(sym_vmlinux ? NULL : sym_objname,
+					     sym_name, sympos, &addr);
 		if (ret)
 			return ret;
 
@@ -246,54 +262,59 @@ static int klp_resolve_symbols(Elf_Shdr *relasec, struct module *pmod)
 	return 0;
 }
 
-static int klp_write_object_relocations(struct module *pmod,
-					struct klp_object *obj)
+/*
+ * At a high-level, there are two types of klp relocation sections: those which
+ * reference symbols which live in vmlinux; and those which reference symbols
+ * which live in other modules.  This function is called for both types:
+ *
+ * 1) When a klp module itself loads, the module code calls this function to
+ *    write vmlinux-specific klp relocations (.klp.rela.vmlinux.* sections).
+ *    These relocations are written to the klp module text to allow the patched
+ *    code/data to reference unexported vmlinux symbols.  They're written as
+ *    early as possible to ensure that other module init code (.e.g.,
+ *    jump_label_apply_nops) can access any unexported vmlinux symbols which
+ *    might be referenced by the klp module's special sections.
+ *
+ * 2) When a to-be-patched module loads -- or is already loaded when a
+ *    corresponding klp module loads -- klp code calls this function to write
+ *    module-specific klp relocations (.klp.rela.{module}.* sections).  These
+ *    are written to the klp module text to allow the patched code/data to
+ *    reference symbols which live in the to-be-patched module or one of its
+ *    module dependencies.  Exported symbols are supported, in addition to
+ *    unexported symbols, in order to enable late module patching, which allows
+ *    the to-be-patched module to be loaded and patched sometime *after* the
+ *    klp module is loaded.
+ */
+int klp_apply_section_relocs(struct module *pmod, Elf_Shdr *sechdrs,
+			     const char *shstrtab, const char *strtab,
+			     unsigned int symndx, unsigned int secndx,
+			     const char *objname)
 {
-	int i, cnt, ret = 0;
-	const char *objname, *secname;
+	int cnt, ret;
 	char sec_objname[MODULE_NAME_LEN];
-	Elf_Shdr *sec;
+	Elf_Shdr *sec = sechdrs + secndx;
 
-	if (WARN_ON(!klp_is_object_loaded(obj)))
+	/*
+	 * Format: .klp.rela.sec_objname.section_name
+	 * See comment in klp_resolve_symbols() for an explanation
+	 * of the selected field width value.
+	 */
+	cnt = sscanf(shstrtab + sec->sh_name, ".klp.rela.%55[^.]",
+		     sec_objname);
+	if (cnt != 1) {
+		pr_err("section %s has an incorrectly formatted name\n",
+		       shstrtab + sec->sh_name);
 		return -EINVAL;
+	}
 
-	objname = klp_is_module(obj) ? obj->name : "vmlinux";
-
-	/* For each klp relocation section */
-	for (i = 1; i < pmod->klp_info->hdr.e_shnum; i++) {
-		sec = pmod->klp_info->sechdrs + i;
-		secname = pmod->klp_info->secstrings + sec->sh_name;
-		if (!(sec->sh_flags & SHF_RELA_LIVEPATCH))
-			continue;
-
-		/*
-		 * Format: .klp.rela.sec_objname.section_name
-		 * See comment in klp_resolve_symbols() for an explanation
-		 * of the selected field width value.
-		 */
-		cnt = sscanf(secname, ".klp.rela.%55[^.]", sec_objname);
-		if (cnt != 1) {
-			pr_err("section %s has an incorrectly formatted name\n",
-			       secname);
-			ret = -EINVAL;
-			break;
-		}
-
-		if (strcmp(objname, sec_objname))
-			continue;
-
-		ret = klp_resolve_symbols(sec, pmod);
-		if (ret)
-			break;
+	if (strcmp(objname ? objname : "vmlinux", sec_objname))
+		return 0;
 
-		ret = apply_relocate_add(pmod->klp_info->sechdrs,
-					 pmod->core_kallsyms.strtab,
-					 pmod->klp_info->symndx, i, pmod);
-		if (ret)
-			break;
-	}
+	ret = klp_resolve_symbols(sechdrs, strtab, symndx, sec, sec_objname);
+	if (ret)
+		return ret;
 
-	return ret;
+	return apply_relocate_add(sechdrs, strtab, symndx, secndx, pmod);
 }
 
 /*
@@ -724,10 +745,27 @@ static int klp_init_func(struct klp_object *obj, struct klp_func *func)
 			   func->old_sympos ? func->old_sympos : 1);
 }
 
-/* Arches may override this to finish any remaining arch-specific tasks */
-void __weak arch_klp_init_object_loaded(struct klp_patch *patch,
-					struct klp_object *obj)
+static int klp_apply_object_relocs(struct klp_patch *patch,
+				   struct klp_object *obj)
 {
+	int i, ret;
+	struct klp_modinfo *info = patch->mod->klp_info;
+
+	for (i = 1; i < info->hdr.e_shnum; i++) {
+		Elf_Shdr *sec = info->sechdrs + i;
+
+		if (!(sec->sh_flags & SHF_RELA_LIVEPATCH))
+			continue;
+
+		ret = klp_apply_section_relocs(patch->mod, info->sechdrs,
+					       info->secstrings,
+					       patch->mod->core_kallsyms.strtab,
+					       info->symndx, i, obj->name);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
 }
 
 /* parts of the initialization that is done only when the object is loaded */
@@ -737,21 +775,18 @@ static int klp_init_object_loaded(struct klp_patch *patch,
 	struct klp_func *func;
 	int ret;
 
-	mutex_lock(&text_mutex);
-
-	module_disable_ro(patch->mod);
-	ret = klp_write_object_relocations(patch->mod, obj);
-	if (ret) {
-		module_enable_ro(patch->mod, true);
-		mutex_unlock(&text_mutex);
-		return ret;
+	if (klp_is_module(obj)) {
+		/*
+		 * Only write module-specific relocations here
+		 * (.klp.rela.{module}.*).  vmlinux-specific relocations were
+		 * written earlier during the initialization of the klp module
+		 * itself.
+		 */
+		ret = klp_apply_object_relocs(patch, obj);
+		if (ret)
+			return ret;
 	}
 
-	arch_klp_init_object_loaded(patch, obj);
-	module_enable_ro(patch->mod, true);
-
-	mutex_unlock(&text_mutex);
-
 	klp_for_each_func(obj, func) {
 		ret = klp_find_object_symbol(obj->name, func->old_name,
 					     func->old_sympos,
@@ -1139,6 +1174,11 @@ int klp_module_coming(struct module *mod)
 	if (WARN_ON(mod->state != MODULE_STATE_COMING))
 		return -EINVAL;
 
+	if (!strcmp(mod->name, "vmlinux")) {
+		pr_err("vmlinux.ko: invalid module name");
+		return -EINVAL;
+	}
+
 	mutex_lock(&klp_mutex);
 	/*
 	 * Each module has to know that klp_module_coming()
diff --git a/kernel/locking/Makefile b/kernel/locking/Makefile
index 45452facff3b..6d11cfb9b41f 100644
--- a/kernel/locking/Makefile
+++ b/kernel/locking/Makefile
@@ -5,6 +5,9 @@ KCOV_INSTRUMENT		:= n
 
 obj-y += mutex.o semaphore.o rwsem.o percpu-rwsem.o
 
+# Avoid recursion lockdep -> KCSAN -> ... -> lockdep.
+KCSAN_SANITIZE_lockdep.o := n
+
 ifdef CONFIG_FUNCTION_TRACER
 CFLAGS_REMOVE_lockdep.o = $(CC_FLAGS_FTRACE)
 CFLAGS_REMOVE_lockdep_proc.o = $(CC_FLAGS_FTRACE)
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index 32406ef0d6a2..54b74fabf40c 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -84,12 +84,39 @@ module_param(lock_stat, int, 0644);
  * to use a raw spinlock - we really dont want the spinlock
  * code to recurse back into the lockdep code...
  */
-static arch_spinlock_t lockdep_lock = (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED;
+static arch_spinlock_t __lock = (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED;
+static struct task_struct *__owner;
+
+static inline void lockdep_lock(void)
+{
+	DEBUG_LOCKS_WARN_ON(!irqs_disabled());
+
+	arch_spin_lock(&__lock);
+	__owner = current;
+	current->lockdep_recursion++;
+}
+
+static inline void lockdep_unlock(void)
+{
+	if (debug_locks && DEBUG_LOCKS_WARN_ON(__owner != current))
+		return;
+
+	current->lockdep_recursion--;
+	__owner = NULL;
+	arch_spin_unlock(&__lock);
+}
+
+static inline bool lockdep_assert_locked(void)
+{
+	return DEBUG_LOCKS_WARN_ON(__owner != current);
+}
+
 static struct task_struct *lockdep_selftest_task_struct;
 
+
 static int graph_lock(void)
 {
-	arch_spin_lock(&lockdep_lock);
+	lockdep_lock();
 	/*
 	 * Make sure that if another CPU detected a bug while
 	 * walking the graph we dont change it (while the other
@@ -97,27 +124,15 @@ static int graph_lock(void)
 	 * dropped already)
 	 */
 	if (!debug_locks) {
-		arch_spin_unlock(&lockdep_lock);
+		lockdep_unlock();
 		return 0;
 	}
-	/* prevent any recursions within lockdep from causing deadlocks */
-	current->lockdep_recursion++;
 	return 1;
 }
 
-static inline int graph_unlock(void)
+static inline void graph_unlock(void)
 {
-	if (debug_locks && !arch_spin_is_locked(&lockdep_lock)) {
-		/*
-		 * The lockdep graph lock isn't locked while we expect it to
-		 * be, we're confused now, bye!
-		 */
-		return DEBUG_LOCKS_WARN_ON(1);
-	}
-
-	current->lockdep_recursion--;
-	arch_spin_unlock(&lockdep_lock);
-	return 0;
+	lockdep_unlock();
 }
 
 /*
@@ -128,7 +143,7 @@ static inline int debug_locks_off_graph_unlock(void)
 {
 	int ret = debug_locks_off();
 
-	arch_spin_unlock(&lockdep_lock);
+	lockdep_unlock();
 
 	return ret;
 }
@@ -147,6 +162,7 @@ static DECLARE_BITMAP(list_entries_in_use, MAX_LOCKDEP_ENTRIES);
 #define KEYHASH_SIZE		(1UL << KEYHASH_BITS)
 static struct hlist_head lock_keys_hash[KEYHASH_SIZE];
 unsigned long nr_lock_classes;
+unsigned long nr_zapped_classes;
 #ifndef CONFIG_DEBUG_LOCKDEP
 static
 #endif
@@ -377,17 +393,11 @@ void lockdep_init_task(struct task_struct *task)
 	task->lockdep_recursion = 0;
 }
 
-void lockdep_off(void)
-{
-	current->lockdep_recursion++;
-}
-EXPORT_SYMBOL(lockdep_off);
-
-void lockdep_on(void)
+static __always_inline void lockdep_recursion_finish(void)
 {
-	current->lockdep_recursion--;
+	if (WARN_ON_ONCE((--current->lockdep_recursion) & LOCKDEP_RECURSION_MASK))
+		current->lockdep_recursion = 0;
 }
-EXPORT_SYMBOL(lockdep_on);
 
 void lockdep_set_selftest_task(struct task_struct *task)
 {
@@ -460,7 +470,7 @@ struct lock_trace {
 	struct hlist_node	hash_entry;
 	u32			hash;
 	u32			nr_entries;
-	unsigned long		entries[0] __aligned(sizeof(unsigned long));
+	unsigned long		entries[] __aligned(sizeof(unsigned long));
 };
 #define LOCK_TRACE_SIZE_IN_LONGS				\
 	(sizeof(struct lock_trace) / sizeof(unsigned long))
@@ -575,6 +585,7 @@ static const char *usage_str[] =
 #include "lockdep_states.h"
 #undef LOCKDEP_STATE
 	[LOCK_USED] = "INITIAL USE",
+	[LOCK_USAGE_STATES] = "IN-NMI",
 };
 #endif
 
@@ -653,7 +664,9 @@ static void print_lock_name(struct lock_class *class)
 
 	printk(KERN_CONT " (");
 	__print_lock_name(class);
-	printk(KERN_CONT "){%s}", usage);
+	printk(KERN_CONT "){%s}-{%hd:%hd}", usage,
+			class->wait_type_outer ?: class->wait_type_inner,
+			class->wait_type_inner);
 }
 
 static void print_lockdep_cache(struct lockdep_map *lock)
@@ -787,7 +800,8 @@ static int count_matching_names(struct lock_class *new_class)
 	return count + 1;
 }
 
-static inline struct lock_class *
+/* used from NMI context -- must be lockless */
+static __always_inline struct lock_class *
 look_up_lock_class(const struct lockdep_map *lock, unsigned int subclass)
 {
 	struct lockdep_subclass_key *key;
@@ -1070,13 +1084,15 @@ static inline void check_data_structures(void) { }
 
 #endif /* CONFIG_DEBUG_LOCKDEP */
 
+static void init_chain_block_buckets(void);
+
 /*
  * Initialize the lock_classes[] array elements, the free_lock_classes list
  * and also the delayed_free structure.
  */
 static void init_data_structures_once(void)
 {
-	static bool ds_initialized, rcu_head_initialized;
+	static bool __read_mostly ds_initialized, rcu_head_initialized;
 	int i;
 
 	if (likely(rcu_head_initialized))
@@ -1100,6 +1116,7 @@ static void init_data_structures_once(void)
 		INIT_LIST_HEAD(&lock_classes[i].locks_after);
 		INIT_LIST_HEAD(&lock_classes[i].locks_before);
 	}
+	init_chain_block_buckets();
 }
 
 static inline struct hlist_head *keyhashentry(const struct lock_class_key *key)
@@ -1230,6 +1247,8 @@ register_lock_class(struct lockdep_map *lock, unsigned int subclass, int force)
 	WARN_ON_ONCE(!list_empty(&class->locks_before));
 	WARN_ON_ONCE(!list_empty(&class->locks_after));
 	class->name_version = count_matching_names(class);
+	class->wait_type_inner = lock->wait_type_inner;
+	class->wait_type_outer = lock->wait_type_outer;
 	/*
 	 * We use RCU's safe list-add method to make
 	 * parallel walking of the hash-list safe:
@@ -1469,6 +1488,8 @@ static int __bfs(struct lock_list *source_entry,
 	struct circular_queue *cq = &lock_cq;
 	int ret = 1;
 
+	lockdep_assert_locked();
+
 	if (match(source_entry, data)) {
 		*target_entry = source_entry;
 		ret = 0;
@@ -1491,8 +1512,6 @@ static int __bfs(struct lock_list *source_entry,
 
 		head = get_dep_list(lock, offset);
 
-		DEBUG_LOCKS_WARN_ON(!irqs_disabled());
-
 		list_for_each_entry_rcu(entry, head, entry) {
 			if (!lock_accessed(entry)) {
 				unsigned int cq_depth;
@@ -1704,7 +1723,7 @@ static int noop_count(struct lock_list *entry, void *data)
 static unsigned long __lockdep_count_forward_deps(struct lock_list *this)
 {
 	unsigned long  count = 0;
-	struct lock_list *uninitialized_var(target_entry);
+	struct lock_list *target_entry;
 
 	__bfs_forwards(this, (void *)&count, noop_count, &target_entry);
 
@@ -1719,9 +1738,9 @@ unsigned long lockdep_count_forward_deps(struct lock_class *class)
 	this.class = class;
 
 	raw_local_irq_save(flags);
-	arch_spin_lock(&lockdep_lock);
+	lockdep_lock();
 	ret = __lockdep_count_forward_deps(&this);
-	arch_spin_unlock(&lockdep_lock);
+	lockdep_unlock();
 	raw_local_irq_restore(flags);
 
 	return ret;
@@ -1730,7 +1749,7 @@ unsigned long lockdep_count_forward_deps(struct lock_class *class)
 static unsigned long __lockdep_count_backward_deps(struct lock_list *this)
 {
 	unsigned long  count = 0;
-	struct lock_list *uninitialized_var(target_entry);
+	struct lock_list *target_entry;
 
 	__bfs_backwards(this, (void *)&count, noop_count, &target_entry);
 
@@ -1746,9 +1765,9 @@ unsigned long lockdep_count_backward_deps(struct lock_class *class)
 	this.class = class;
 
 	raw_local_irq_save(flags);
-	arch_spin_lock(&lockdep_lock);
+	lockdep_lock();
 	ret = __lockdep_count_backward_deps(&this);
-	arch_spin_unlock(&lockdep_lock);
+	lockdep_unlock();
 	raw_local_irq_restore(flags);
 
 	return ret;
@@ -1785,7 +1804,7 @@ check_noncircular(struct held_lock *src, struct held_lock *target,
 		  struct lock_trace **const trace)
 {
 	int ret;
-	struct lock_list *uninitialized_var(target_entry);
+	struct lock_list *target_entry;
 	struct lock_list src_entry = {
 		.class = hlock_class(src),
 		.parent = NULL,
@@ -1823,7 +1842,7 @@ static noinline int
 check_redundant(struct held_lock *src, struct held_lock *target)
 {
 	int ret;
-	struct lock_list *uninitialized_var(target_entry);
+	struct lock_list *target_entry;
 	struct lock_list src_entry = {
 		.class = hlock_class(src),
 		.parent = NULL,
@@ -2043,9 +2062,9 @@ print_bad_irq_dependency(struct task_struct *curr,
 	pr_warn("-----------------------------------------------------\n");
 	pr_warn("%s/%d [HC%u[%lu]:SC%u[%lu]:HE%u:SE%u] is trying to acquire:\n",
 		curr->comm, task_pid_nr(curr),
-		curr->hardirq_context, hardirq_count() >> HARDIRQ_SHIFT,
+		lockdep_hardirq_context(), hardirq_count() >> HARDIRQ_SHIFT,
 		curr->softirq_context, softirq_count() >> SOFTIRQ_SHIFT,
-		curr->hardirqs_enabled,
+		lockdep_hardirqs_enabled(),
 		curr->softirqs_enabled);
 	print_lock(next);
 
@@ -2225,8 +2244,8 @@ static int check_irq_usage(struct task_struct *curr, struct held_lock *prev,
 {
 	unsigned long usage_mask = 0, forward_mask, backward_mask;
 	enum lock_usage_bit forward_bit = 0, backward_bit = 0;
-	struct lock_list *uninitialized_var(target_entry1);
-	struct lock_list *uninitialized_var(target_entry);
+	struct lock_list *target_entry1;
+	struct lock_list *target_entry;
 	struct lock_list this, that;
 	int ret;
 
@@ -2298,18 +2317,6 @@ static int check_irq_usage(struct task_struct *curr, struct held_lock *prev,
 	return 0;
 }
 
-static void inc_chains(void)
-{
-	if (current->hardirq_context)
-		nr_hardirq_chains++;
-	else {
-		if (current->softirq_context)
-			nr_softirq_chains++;
-		else
-			nr_process_chains++;
-	}
-}
-
 #else
 
 static inline int check_irq_usage(struct task_struct *curr,
@@ -2317,13 +2324,27 @@ static inline int check_irq_usage(struct task_struct *curr,
 {
 	return 1;
 }
+#endif /* CONFIG_TRACE_IRQFLAGS */
 
-static inline void inc_chains(void)
+static void inc_chains(int irq_context)
 {
-	nr_process_chains++;
+	if (irq_context & LOCK_CHAIN_HARDIRQ_CONTEXT)
+		nr_hardirq_chains++;
+	else if (irq_context & LOCK_CHAIN_SOFTIRQ_CONTEXT)
+		nr_softirq_chains++;
+	else
+		nr_process_chains++;
 }
 
-#endif /* CONFIG_TRACE_IRQFLAGS */
+static void dec_chains(int irq_context)
+{
+	if (irq_context & LOCK_CHAIN_HARDIRQ_CONTEXT)
+		nr_hardirq_chains--;
+	else if (irq_context & LOCK_CHAIN_SOFTIRQ_CONTEXT)
+		nr_softirq_chains--;
+	else
+		nr_process_chains--;
+}
 
 static void
 print_deadlock_scenario(struct held_lock *nxt, struct held_lock *prv)
@@ -2622,8 +2643,235 @@ out_bug:
 
 struct lock_chain lock_chains[MAX_LOCKDEP_CHAINS];
 static DECLARE_BITMAP(lock_chains_in_use, MAX_LOCKDEP_CHAINS);
-int nr_chain_hlocks;
 static u16 chain_hlocks[MAX_LOCKDEP_CHAIN_HLOCKS];
+unsigned long nr_zapped_lock_chains;
+unsigned int nr_free_chain_hlocks;	/* Free chain_hlocks in buckets */
+unsigned int nr_lost_chain_hlocks;	/* Lost chain_hlocks */
+unsigned int nr_large_chain_blocks;	/* size > MAX_CHAIN_BUCKETS */
+
+/*
+ * The first 2 chain_hlocks entries in the chain block in the bucket
+ * list contains the following meta data:
+ *
+ *   entry[0]:
+ *     Bit    15 - always set to 1 (it is not a class index)
+ *     Bits 0-14 - upper 15 bits of the next block index
+ *   entry[1]    - lower 16 bits of next block index
+ *
+ * A next block index of all 1 bits means it is the end of the list.
+ *
+ * On the unsized bucket (bucket-0), the 3rd and 4th entries contain
+ * the chain block size:
+ *
+ *   entry[2] - upper 16 bits of the chain block size
+ *   entry[3] - lower 16 bits of the chain block size
+ */
+#define MAX_CHAIN_BUCKETS	16
+#define CHAIN_BLK_FLAG		(1U << 15)
+#define CHAIN_BLK_LIST_END	0xFFFFU
+
+static int chain_block_buckets[MAX_CHAIN_BUCKETS];
+
+static inline int size_to_bucket(int size)
+{
+	if (size > MAX_CHAIN_BUCKETS)
+		return 0;
+
+	return size - 1;
+}
+
+/*
+ * Iterate all the chain blocks in a bucket.
+ */
+#define for_each_chain_block(bucket, prev, curr)		\
+	for ((prev) = -1, (curr) = chain_block_buckets[bucket];	\
+	     (curr) >= 0;					\
+	     (prev) = (curr), (curr) = chain_block_next(curr))
+
+/*
+ * next block or -1
+ */
+static inline int chain_block_next(int offset)
+{
+	int next = chain_hlocks[offset];
+
+	WARN_ON_ONCE(!(next & CHAIN_BLK_FLAG));
+
+	if (next == CHAIN_BLK_LIST_END)
+		return -1;
+
+	next &= ~CHAIN_BLK_FLAG;
+	next <<= 16;
+	next |= chain_hlocks[offset + 1];
+
+	return next;
+}
+
+/*
+ * bucket-0 only
+ */
+static inline int chain_block_size(int offset)
+{
+	return (chain_hlocks[offset + 2] << 16) | chain_hlocks[offset + 3];
+}
+
+static inline void init_chain_block(int offset, int next, int bucket, int size)
+{
+	chain_hlocks[offset] = (next >> 16) | CHAIN_BLK_FLAG;
+	chain_hlocks[offset + 1] = (u16)next;
+
+	if (size && !bucket) {
+		chain_hlocks[offset + 2] = size >> 16;
+		chain_hlocks[offset + 3] = (u16)size;
+	}
+}
+
+static inline void add_chain_block(int offset, int size)
+{
+	int bucket = size_to_bucket(size);
+	int next = chain_block_buckets[bucket];
+	int prev, curr;
+
+	if (unlikely(size < 2)) {
+		/*
+		 * We can't store single entries on the freelist. Leak them.
+		 *
+		 * One possible way out would be to uniquely mark them, other
+		 * than with CHAIN_BLK_FLAG, such that we can recover them when
+		 * the block before it is re-added.
+		 */
+		if (size)
+			nr_lost_chain_hlocks++;
+		return;
+	}
+
+	nr_free_chain_hlocks += size;
+	if (!bucket) {
+		nr_large_chain_blocks++;
+
+		/*
+		 * Variable sized, sort large to small.
+		 */
+		for_each_chain_block(0, prev, curr) {
+			if (size >= chain_block_size(curr))
+				break;
+		}
+		init_chain_block(offset, curr, 0, size);
+		if (prev < 0)
+			chain_block_buckets[0] = offset;
+		else
+			init_chain_block(prev, offset, 0, 0);
+		return;
+	}
+	/*
+	 * Fixed size, add to head.
+	 */
+	init_chain_block(offset, next, bucket, size);
+	chain_block_buckets[bucket] = offset;
+}
+
+/*
+ * Only the first block in the list can be deleted.
+ *
+ * For the variable size bucket[0], the first block (the largest one) is
+ * returned, broken up and put back into the pool. So if a chain block of
+ * length > MAX_CHAIN_BUCKETS is ever used and zapped, it will just be
+ * queued up after the primordial chain block and never be used until the
+ * hlock entries in the primordial chain block is almost used up. That
+ * causes fragmentation and reduce allocation efficiency. That can be
+ * monitored by looking at the "large chain blocks" number in lockdep_stats.
+ */
+static inline void del_chain_block(int bucket, int size, int next)
+{
+	nr_free_chain_hlocks -= size;
+	chain_block_buckets[bucket] = next;
+
+	if (!bucket)
+		nr_large_chain_blocks--;
+}
+
+static void init_chain_block_buckets(void)
+{
+	int i;
+
+	for (i = 0; i < MAX_CHAIN_BUCKETS; i++)
+		chain_block_buckets[i] = -1;
+
+	add_chain_block(0, ARRAY_SIZE(chain_hlocks));
+}
+
+/*
+ * Return offset of a chain block of the right size or -1 if not found.
+ *
+ * Fairly simple worst-fit allocator with the addition of a number of size
+ * specific free lists.
+ */
+static int alloc_chain_hlocks(int req)
+{
+	int bucket, curr, size;
+
+	/*
+	 * We rely on the MSB to act as an escape bit to denote freelist
+	 * pointers. Make sure this bit isn't set in 'normal' class_idx usage.
+	 */
+	BUILD_BUG_ON((MAX_LOCKDEP_KEYS-1) & CHAIN_BLK_FLAG);
+
+	init_data_structures_once();
+
+	if (nr_free_chain_hlocks < req)
+		return -1;
+
+	/*
+	 * We require a minimum of 2 (u16) entries to encode a freelist
+	 * 'pointer'.
+	 */
+	req = max(req, 2);
+	bucket = size_to_bucket(req);
+	curr = chain_block_buckets[bucket];
+
+	if (bucket) {
+		if (curr >= 0) {
+			del_chain_block(bucket, req, chain_block_next(curr));
+			return curr;
+		}
+		/* Try bucket 0 */
+		curr = chain_block_buckets[0];
+	}
+
+	/*
+	 * The variable sized freelist is sorted by size; the first entry is
+	 * the largest. Use it if it fits.
+	 */
+	if (curr >= 0) {
+		size = chain_block_size(curr);
+		if (likely(size >= req)) {
+			del_chain_block(0, size, chain_block_next(curr));
+			add_chain_block(curr + req, size - req);
+			return curr;
+		}
+	}
+
+	/*
+	 * Last resort, split a block in a larger sized bucket.
+	 */
+	for (size = MAX_CHAIN_BUCKETS; size > req; size--) {
+		bucket = size_to_bucket(size);
+		curr = chain_block_buckets[bucket];
+		if (curr < 0)
+			continue;
+
+		del_chain_block(bucket, size, chain_block_next(curr));
+		add_chain_block(curr + req, size - req);
+		return curr;
+	}
+
+	return -1;
+}
+
+static inline void free_chain_hlocks(int base, int size)
+{
+	add_chain_block(base, max(size, 2));
+}
 
 struct lock_class *lock_chain_get_class(struct lock_chain *chain, int i)
 {
@@ -2803,7 +3051,7 @@ static inline int add_chain_cache(struct task_struct *curr,
 	 * disabled to make this an IRQ-safe lock.. for recursion reasons
 	 * lockdep won't complain about its own locking errors.
 	 */
-	if (DEBUG_LOCKS_WARN_ON(!irqs_disabled()))
+	if (lockdep_assert_locked())
 		return 0;
 
 	chain = alloc_lock_chain();
@@ -2824,15 +3072,8 @@ static inline int add_chain_cache(struct task_struct *curr,
 	BUILD_BUG_ON((1UL << 6)  <= ARRAY_SIZE(curr->held_locks));
 	BUILD_BUG_ON((1UL << 8*sizeof(chain_hlocks[0])) <= ARRAY_SIZE(lock_classes));
 
-	if (likely(nr_chain_hlocks + chain->depth <= MAX_LOCKDEP_CHAIN_HLOCKS)) {
-		chain->base = nr_chain_hlocks;
-		for (j = 0; j < chain->depth - 1; j++, i++) {
-			int lock_id = curr->held_locks[i].class_idx;
-			chain_hlocks[chain->base + j] = lock_id;
-		}
-		chain_hlocks[chain->base + j] = class - lock_classes;
-		nr_chain_hlocks += chain->depth;
-	} else {
+	j = alloc_chain_hlocks(chain->depth);
+	if (j < 0) {
 		if (!debug_locks_off_graph_unlock())
 			return 0;
 
@@ -2841,9 +3082,16 @@ static inline int add_chain_cache(struct task_struct *curr,
 		return 0;
 	}
 
+	chain->base = j;
+	for (j = 0; j < chain->depth - 1; j++, i++) {
+		int lock_id = curr->held_locks[i].class_idx;
+
+		chain_hlocks[chain->base + j] = lock_id;
+	}
+	chain_hlocks[chain->base + j] = class - lock_classes;
 	hlist_add_head_rcu(&chain->entry, hash_head);
 	debug_atomic_inc(chain_lookup_misses);
-	inc_chains();
+	inc_chains(chain->irq_context);
 
 	return 1;
 }
@@ -2987,6 +3235,8 @@ static inline int validate_chain(struct task_struct *curr,
 {
 	return 1;
 }
+
+static void init_chain_block_buckets(void)	{ }
 #endif /* CONFIG_PROVE_LOCKING */
 
 /*
@@ -3081,10 +3331,10 @@ print_usage_bug(struct task_struct *curr, struct held_lock *this,
 
 	pr_warn("%s/%d [HC%u[%lu]:SC%u[%lu]:HE%u:SE%u] takes:\n",
 		curr->comm, task_pid_nr(curr),
-		trace_hardirq_context(curr), hardirq_count() >> HARDIRQ_SHIFT,
-		trace_softirq_context(curr), softirq_count() >> SOFTIRQ_SHIFT,
-		trace_hardirqs_enabled(curr),
-		trace_softirqs_enabled(curr));
+		lockdep_hardirq_context(), hardirq_count() >> HARDIRQ_SHIFT,
+		lockdep_softirq_context(curr), softirq_count() >> SOFTIRQ_SHIFT,
+		lockdep_hardirqs_enabled(),
+		lockdep_softirqs_enabled(curr));
 	print_lock(this);
 
 	pr_warn("{%s} state was registered at:\n", usage_str[prev_bit]);
@@ -3188,7 +3438,7 @@ check_usage_forwards(struct task_struct *curr, struct held_lock *this,
 {
 	int ret;
 	struct lock_list root;
-	struct lock_list *uninitialized_var(target_entry);
+	struct lock_list *target_entry;
 
 	root.parent = NULL;
 	root.class = hlock_class(this);
@@ -3215,7 +3465,7 @@ check_usage_backwards(struct task_struct *curr, struct held_lock *this,
 {
 	int ret;
 	struct lock_list root;
-	struct lock_list *uninitialized_var(target_entry);
+	struct lock_list *target_entry;
 
 	root.parent = NULL;
 	root.class = hlock_class(this);
@@ -3234,19 +3484,21 @@ check_usage_backwards(struct task_struct *curr, struct held_lock *this,
 
 void print_irqtrace_events(struct task_struct *curr)
 {
-	printk("irq event stamp: %u\n", curr->irq_events);
+	const struct irqtrace_events *trace = &curr->irqtrace;
+
+	printk("irq event stamp: %u\n", trace->irq_events);
 	printk("hardirqs last  enabled at (%u): [<%px>] %pS\n",
-		curr->hardirq_enable_event, (void *)curr->hardirq_enable_ip,
-		(void *)curr->hardirq_enable_ip);
+		trace->hardirq_enable_event, (void *)trace->hardirq_enable_ip,
+		(void *)trace->hardirq_enable_ip);
 	printk("hardirqs last disabled at (%u): [<%px>] %pS\n",
-		curr->hardirq_disable_event, (void *)curr->hardirq_disable_ip,
-		(void *)curr->hardirq_disable_ip);
+		trace->hardirq_disable_event, (void *)trace->hardirq_disable_ip,
+		(void *)trace->hardirq_disable_ip);
 	printk("softirqs last  enabled at (%u): [<%px>] %pS\n",
-		curr->softirq_enable_event, (void *)curr->softirq_enable_ip,
-		(void *)curr->softirq_enable_ip);
+		trace->softirq_enable_event, (void *)trace->softirq_enable_ip,
+		(void *)trace->softirq_enable_ip);
 	printk("softirqs last disabled at (%u): [<%px>] %pS\n",
-		curr->softirq_disable_event, (void *)curr->softirq_disable_ip,
-		(void *)curr->softirq_disable_ip);
+		trace->softirq_disable_event, (void *)trace->softirq_disable_ip,
+		(void *)trace->softirq_disable_ip);
 }
 
 static int HARDIRQ_verbose(struct lock_class *class)
@@ -3366,13 +3618,10 @@ mark_held_locks(struct task_struct *curr, enum lock_usage_bit base_bit)
 /*
  * Hardirqs will be enabled:
  */
-static void __trace_hardirqs_on_caller(unsigned long ip)
+static void __trace_hardirqs_on_caller(void)
 {
 	struct task_struct *curr = current;
 
-	/* we'll do an OFF -> ON transition: */
-	curr->hardirqs_enabled = 1;
-
 	/*
 	 * We are going to turn hardirqs on, so set the
 	 * usage bit for all held locks:
@@ -3385,20 +3634,33 @@ static void __trace_hardirqs_on_caller(unsigned long ip)
 	 * this bit from being set before)
 	 */
 	if (curr->softirqs_enabled)
-		if (!mark_held_locks(curr, LOCK_ENABLED_SOFTIRQ))
-			return;
-
-	curr->hardirq_enable_ip = ip;
-	curr->hardirq_enable_event = ++curr->irq_events;
-	debug_atomic_inc(hardirqs_on_events);
+		mark_held_locks(curr, LOCK_ENABLED_SOFTIRQ);
 }
 
-void lockdep_hardirqs_on(unsigned long ip)
+/**
+ * lockdep_hardirqs_on_prepare - Prepare for enabling interrupts
+ * @ip:		Caller address
+ *
+ * Invoked before a possible transition to RCU idle from exit to user or
+ * guest mode. This ensures that all RCU operations are done before RCU
+ * stops watching. After the RCU transition lockdep_hardirqs_on() has to be
+ * invoked to set the final state.
+ */
+void lockdep_hardirqs_on_prepare(unsigned long ip)
 {
-	if (unlikely(!debug_locks || current->lockdep_recursion))
+	if (unlikely(!debug_locks))
+		return;
+
+	/*
+	 * NMIs do not (and cannot) track lock dependencies, nothing to do.
+	 */
+	if (unlikely(in_nmi()))
 		return;
 
-	if (unlikely(current->hardirqs_enabled)) {
+	if (unlikely(current->lockdep_recursion & LOCKDEP_RECURSION_MASK))
+		return;
+
+	if (unlikely(lockdep_hardirqs_enabled())) {
 		/*
 		 * Neither irq nor preemption are disabled here
 		 * so this is racy by nature but losing one hit
@@ -3426,23 +3688,98 @@ void lockdep_hardirqs_on(unsigned long ip)
 	 * Can't allow enabling interrupts while in an interrupt handler,
 	 * that's general bad form and such. Recursion, limited stack etc..
 	 */
-	if (DEBUG_LOCKS_WARN_ON(current->hardirq_context))
+	if (DEBUG_LOCKS_WARN_ON(lockdep_hardirq_context()))
 		return;
 
-	current->lockdep_recursion = 1;
-	__trace_hardirqs_on_caller(ip);
-	current->lockdep_recursion = 0;
+	current->hardirq_chain_key = current->curr_chain_key;
+
+	current->lockdep_recursion++;
+	__trace_hardirqs_on_caller();
+	lockdep_recursion_finish();
 }
-NOKPROBE_SYMBOL(lockdep_hardirqs_on);
+EXPORT_SYMBOL_GPL(lockdep_hardirqs_on_prepare);
+
+void noinstr lockdep_hardirqs_on(unsigned long ip)
+{
+	struct irqtrace_events *trace = &current->irqtrace;
+
+	if (unlikely(!debug_locks))
+		return;
+
+	/*
+	 * NMIs can happen in the middle of local_irq_{en,dis}able() where the
+	 * tracking state and hardware state are out of sync.
+	 *
+	 * NMIs must save lockdep_hardirqs_enabled() to restore IRQ state from,
+	 * and not rely on hardware state like normal interrupts.
+	 */
+	if (unlikely(in_nmi())) {
+		if (!IS_ENABLED(CONFIG_TRACE_IRQFLAGS_NMI))
+			return;
+
+		/*
+		 * Skip:
+		 *  - recursion check, because NMI can hit lockdep;
+		 *  - hardware state check, because above;
+		 *  - chain_key check, see lockdep_hardirqs_on_prepare().
+		 */
+		goto skip_checks;
+	}
+
+	if (unlikely(current->lockdep_recursion & LOCKDEP_RECURSION_MASK))
+		return;
+
+	if (lockdep_hardirqs_enabled()) {
+		/*
+		 * Neither irq nor preemption are disabled here
+		 * so this is racy by nature but losing one hit
+		 * in a stat is not a big deal.
+		 */
+		__debug_atomic_inc(redundant_hardirqs_on);
+		return;
+	}
+
+	/*
+	 * We're enabling irqs and according to our state above irqs weren't
+	 * already enabled, yet we find the hardware thinks they are in fact
+	 * enabled.. someone messed up their IRQ state tracing.
+	 */
+	if (DEBUG_LOCKS_WARN_ON(!irqs_disabled()))
+		return;
+
+	/*
+	 * Ensure the lock stack remained unchanged between
+	 * lockdep_hardirqs_on_prepare() and lockdep_hardirqs_on().
+	 */
+	DEBUG_LOCKS_WARN_ON(current->hardirq_chain_key !=
+			    current->curr_chain_key);
+
+skip_checks:
+	/* we'll do an OFF -> ON transition: */
+	__this_cpu_write(hardirqs_enabled, 1);
+	trace->hardirq_enable_ip = ip;
+	trace->hardirq_enable_event = ++trace->irq_events;
+	debug_atomic_inc(hardirqs_on_events);
+}
+EXPORT_SYMBOL_GPL(lockdep_hardirqs_on);
 
 /*
  * Hardirqs were disabled:
  */
-void lockdep_hardirqs_off(unsigned long ip)
+void noinstr lockdep_hardirqs_off(unsigned long ip)
 {
-	struct task_struct *curr = current;
+	if (unlikely(!debug_locks))
+		return;
 
-	if (unlikely(!debug_locks || current->lockdep_recursion))
+	/*
+	 * Matching lockdep_hardirqs_on(), allow NMIs in the middle of lockdep;
+	 * they will restore the software state. This ensures the software
+	 * state is consistent inside NMIs as well.
+	 */
+	if (in_nmi()) {
+		if (!IS_ENABLED(CONFIG_TRACE_IRQFLAGS_NMI))
+			return;
+	} else if (current->lockdep_recursion & LOCKDEP_RECURSION_MASK)
 		return;
 
 	/*
@@ -3452,25 +3789,28 @@ void lockdep_hardirqs_off(unsigned long ip)
 	if (DEBUG_LOCKS_WARN_ON(!irqs_disabled()))
 		return;
 
-	if (curr->hardirqs_enabled) {
+	if (lockdep_hardirqs_enabled()) {
+		struct irqtrace_events *trace = &current->irqtrace;
+
 		/*
 		 * We have done an ON -> OFF transition:
 		 */
-		curr->hardirqs_enabled = 0;
-		curr->hardirq_disable_ip = ip;
-		curr->hardirq_disable_event = ++curr->irq_events;
+		__this_cpu_write(hardirqs_enabled, 0);
+		trace->hardirq_disable_ip = ip;
+		trace->hardirq_disable_event = ++trace->irq_events;
 		debug_atomic_inc(hardirqs_off_events);
-	} else
+	} else {
 		debug_atomic_inc(redundant_hardirqs_off);
+	}
 }
-NOKPROBE_SYMBOL(lockdep_hardirqs_off);
+EXPORT_SYMBOL_GPL(lockdep_hardirqs_off);
 
 /*
  * Softirqs will be enabled:
  */
-void trace_softirqs_on(unsigned long ip)
+void lockdep_softirqs_on(unsigned long ip)
 {
-	struct task_struct *curr = current;
+	struct irqtrace_events *trace = &current->irqtrace;
 
 	if (unlikely(!debug_locks || current->lockdep_recursion))
 		return;
@@ -3482,36 +3822,34 @@ void trace_softirqs_on(unsigned long ip)
 	if (DEBUG_LOCKS_WARN_ON(!irqs_disabled()))
 		return;
 
-	if (curr->softirqs_enabled) {
+	if (current->softirqs_enabled) {
 		debug_atomic_inc(redundant_softirqs_on);
 		return;
 	}
 
-	current->lockdep_recursion = 1;
+	current->lockdep_recursion++;
 	/*
 	 * We'll do an OFF -> ON transition:
 	 */
-	curr->softirqs_enabled = 1;
-	curr->softirq_enable_ip = ip;
-	curr->softirq_enable_event = ++curr->irq_events;
+	current->softirqs_enabled = 1;
+	trace->softirq_enable_ip = ip;
+	trace->softirq_enable_event = ++trace->irq_events;
 	debug_atomic_inc(softirqs_on_events);
 	/*
 	 * We are going to turn softirqs on, so set the
 	 * usage bit for all held locks, if hardirqs are
 	 * enabled too:
 	 */
-	if (curr->hardirqs_enabled)
-		mark_held_locks(curr, LOCK_ENABLED_SOFTIRQ);
-	current->lockdep_recursion = 0;
+	if (lockdep_hardirqs_enabled())
+		mark_held_locks(current, LOCK_ENABLED_SOFTIRQ);
+	lockdep_recursion_finish();
 }
 
 /*
  * Softirqs were disabled:
  */
-void trace_softirqs_off(unsigned long ip)
+void lockdep_softirqs_off(unsigned long ip)
 {
-	struct task_struct *curr = current;
-
 	if (unlikely(!debug_locks || current->lockdep_recursion))
 		return;
 
@@ -3521,13 +3859,15 @@ void trace_softirqs_off(unsigned long ip)
 	if (DEBUG_LOCKS_WARN_ON(!irqs_disabled()))
 		return;
 
-	if (curr->softirqs_enabled) {
+	if (current->softirqs_enabled) {
+		struct irqtrace_events *trace = &current->irqtrace;
+
 		/*
 		 * We have done an ON -> OFF transition:
 		 */
-		curr->softirqs_enabled = 0;
-		curr->softirq_disable_ip = ip;
-		curr->softirq_disable_event = ++curr->irq_events;
+		current->softirqs_enabled = 0;
+		trace->softirq_disable_ip = ip;
+		trace->softirq_disable_event = ++trace->irq_events;
 		debug_atomic_inc(softirqs_off_events);
 		/*
 		 * Whoops, we wanted softirqs off, so why aren't they?
@@ -3549,7 +3889,7 @@ mark_usage(struct task_struct *curr, struct held_lock *hlock, int check)
 	 */
 	if (!hlock->trylock) {
 		if (hlock->read) {
-			if (curr->hardirq_context)
+			if (lockdep_hardirq_context())
 				if (!mark_lock(curr, hlock,
 						LOCK_USED_IN_HARDIRQ_READ))
 					return 0;
@@ -3558,7 +3898,7 @@ mark_usage(struct task_struct *curr, struct held_lock *hlock, int check)
 						LOCK_USED_IN_SOFTIRQ_READ))
 					return 0;
 		} else {
-			if (curr->hardirq_context)
+			if (lockdep_hardirq_context())
 				if (!mark_lock(curr, hlock, LOCK_USED_IN_HARDIRQ))
 					return 0;
 			if (curr->softirq_context)
@@ -3596,7 +3936,8 @@ lock_used:
 
 static inline unsigned int task_irq_context(struct task_struct *task)
 {
-	return 2 * !!task->hardirq_context + !!task->softirq_context;
+	return LOCK_CHAIN_HARDIRQ_CONTEXT * !!lockdep_hardirq_context() +
+	       LOCK_CHAIN_SOFTIRQ_CONTEXT * !!task->softirq_context;
 }
 
 static int separate_irq_context(struct task_struct *curr,
@@ -3682,6 +4023,124 @@ static int mark_lock(struct task_struct *curr, struct held_lock *this,
 	return ret;
 }
 
+static inline short task_wait_context(struct task_struct *curr)
+{
+	/*
+	 * Set appropriate wait type for the context; for IRQs we have to take
+	 * into account force_irqthread as that is implied by PREEMPT_RT.
+	 */
+	if (lockdep_hardirq_context()) {
+		/*
+		 * Check if force_irqthreads will run us threaded.
+		 */
+		if (curr->hardirq_threaded || curr->irq_config)
+			return LD_WAIT_CONFIG;
+
+		return LD_WAIT_SPIN;
+	} else if (curr->softirq_context) {
+		/*
+		 * Softirqs are always threaded.
+		 */
+		return LD_WAIT_CONFIG;
+	}
+
+	return LD_WAIT_MAX;
+}
+
+static int
+print_lock_invalid_wait_context(struct task_struct *curr,
+				struct held_lock *hlock)
+{
+	short curr_inner;
+
+	if (!debug_locks_off())
+		return 0;
+	if (debug_locks_silent)
+		return 0;
+
+	pr_warn("\n");
+	pr_warn("=============================\n");
+	pr_warn("[ BUG: Invalid wait context ]\n");
+	print_kernel_ident();
+	pr_warn("-----------------------------\n");
+
+	pr_warn("%s/%d is trying to lock:\n", curr->comm, task_pid_nr(curr));
+	print_lock(hlock);
+
+	pr_warn("other info that might help us debug this:\n");
+
+	curr_inner = task_wait_context(curr);
+	pr_warn("context-{%d:%d}\n", curr_inner, curr_inner);
+
+	lockdep_print_held_locks(curr);
+
+	pr_warn("stack backtrace:\n");
+	dump_stack();
+
+	return 0;
+}
+
+/*
+ * Verify the wait_type context.
+ *
+ * This check validates we takes locks in the right wait-type order; that is it
+ * ensures that we do not take mutexes inside spinlocks and do not attempt to
+ * acquire spinlocks inside raw_spinlocks and the sort.
+ *
+ * The entire thing is slightly more complex because of RCU, RCU is a lock that
+ * can be taken from (pretty much) any context but also has constraints.
+ * However when taken in a stricter environment the RCU lock does not loosen
+ * the constraints.
+ *
+ * Therefore we must look for the strictest environment in the lock stack and
+ * compare that to the lock we're trying to acquire.
+ */
+static int check_wait_context(struct task_struct *curr, struct held_lock *next)
+{
+	short next_inner = hlock_class(next)->wait_type_inner;
+	short next_outer = hlock_class(next)->wait_type_outer;
+	short curr_inner;
+	int depth;
+
+	if (!curr->lockdep_depth || !next_inner || next->trylock)
+		return 0;
+
+	if (!next_outer)
+		next_outer = next_inner;
+
+	/*
+	 * Find start of current irq_context..
+	 */
+	for (depth = curr->lockdep_depth - 1; depth >= 0; depth--) {
+		struct held_lock *prev = curr->held_locks + depth;
+		if (prev->irq_context != next->irq_context)
+			break;
+	}
+	depth++;
+
+	curr_inner = task_wait_context(curr);
+
+	for (; depth < curr->lockdep_depth; depth++) {
+		struct held_lock *prev = curr->held_locks + depth;
+		short prev_inner = hlock_class(prev)->wait_type_inner;
+
+		if (prev_inner) {
+			/*
+			 * We can have a bigger inner than a previous one
+			 * when outer is smaller than inner, as with RCU.
+			 *
+			 * Also due to trylocks.
+			 */
+			curr_inner = min(curr_inner, prev_inner);
+		}
+	}
+
+	if (next_outer > curr_inner)
+		return print_lock_invalid_wait_context(curr, next);
+
+	return 0;
+}
+
 #else /* CONFIG_PROVE_LOCKING */
 
 static inline int
@@ -3701,13 +4160,20 @@ static inline int separate_irq_context(struct task_struct *curr,
 	return 0;
 }
 
+static inline int check_wait_context(struct task_struct *curr,
+				     struct held_lock *next)
+{
+	return 0;
+}
+
 #endif /* CONFIG_PROVE_LOCKING */
 
 /*
  * Initialize a lock instance's lock-class mapping info:
  */
-void lockdep_init_map(struct lockdep_map *lock, const char *name,
-		      struct lock_class_key *key, int subclass)
+void lockdep_init_map_waits(struct lockdep_map *lock, const char *name,
+			    struct lock_class_key *key, int subclass,
+			    short inner, short outer)
 {
 	int i;
 
@@ -3728,6 +4194,9 @@ void lockdep_init_map(struct lockdep_map *lock, const char *name,
 
 	lock->name = name;
 
+	lock->wait_type_outer = outer;
+	lock->wait_type_inner = inner;
+
 	/*
 	 * No key, no joy, we need to hash something.
 	 */
@@ -3755,13 +4224,13 @@ void lockdep_init_map(struct lockdep_map *lock, const char *name,
 			return;
 
 		raw_local_irq_save(flags);
-		current->lockdep_recursion = 1;
+		current->lockdep_recursion++;
 		register_lock_class(lock, subclass, 1);
-		current->lockdep_recursion = 0;
+		lockdep_recursion_finish();
 		raw_local_irq_restore(flags);
 	}
 }
-EXPORT_SYMBOL_GPL(lockdep_init_map);
+EXPORT_SYMBOL_GPL(lockdep_init_map_waits);
 
 struct lock_class_key __lockdep_no_validate__;
 EXPORT_SYMBOL_GPL(__lockdep_no_validate__);
@@ -3862,7 +4331,7 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass,
 
 	class_idx = class - lock_classes;
 
-	if (depth) {
+	if (depth) { /* we're holding locks */
 		hlock = curr->held_locks + depth - 1;
 		if (hlock->class_idx == class_idx && nest_lock) {
 			if (!references)
@@ -3904,6 +4373,9 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass,
 #endif
 	hlock->pin_count = pin_count;
 
+	if (check_wait_context(curr, hlock))
+		return 0;
+
 	/* Initialize the lock usage bit */
 	if (!mark_usage(curr, hlock, check))
 		return 0;
@@ -3998,7 +4470,7 @@ static void print_unlock_imbalance_bug(struct task_struct *curr,
 		curr->comm, task_pid_nr(curr));
 	print_lockdep_cache(lock);
 	pr_cont(") at:\n");
-	print_ip_sym(ip);
+	print_ip_sym(KERN_WARNING, ip);
 	pr_warn("but there are no more locks to release!\n");
 	pr_warn("\nother info that might help us debug this:\n");
 	lockdep_print_held_locks(curr);
@@ -4007,8 +4479,8 @@ static void print_unlock_imbalance_bug(struct task_struct *curr,
 	dump_stack();
 }
 
-static int match_held_lock(const struct held_lock *hlock,
-					const struct lockdep_map *lock)
+static noinstr int match_held_lock(const struct held_lock *hlock,
+				   const struct lockdep_map *lock)
 {
 	if (hlock->instance == lock)
 		return 1;
@@ -4139,7 +4611,9 @@ __lock_set_class(struct lockdep_map *lock, const char *name,
 		return 0;
 	}
 
-	lockdep_init_map(lock, name, key, 0);
+	lockdep_init_map_waits(lock, name, key, 0,
+			       lock->wait_type_inner,
+			       lock->wait_type_outer);
 	class = register_lock_class(lock, subclass, 0);
 	hlock->class_idx = class - lock_classes;
 
@@ -4293,7 +4767,7 @@ __lock_release(struct lockdep_map *lock, unsigned long ip)
 	return 0;
 }
 
-static nokprobe_inline
+static __always_inline
 int __lock_is_held(const struct lockdep_map *lock, int read)
 {
 	struct task_struct *curr = current;
@@ -4398,11 +4872,11 @@ static void check_flags(unsigned long flags)
 		return;
 
 	if (irqs_disabled_flags(flags)) {
-		if (DEBUG_LOCKS_WARN_ON(current->hardirqs_enabled)) {
+		if (DEBUG_LOCKS_WARN_ON(lockdep_hardirqs_enabled())) {
 			printk("possible reason: unannotated irqs-off.\n");
 		}
 	} else {
-		if (DEBUG_LOCKS_WARN_ON(!current->hardirqs_enabled)) {
+		if (DEBUG_LOCKS_WARN_ON(!lockdep_hardirqs_enabled())) {
 			printk("possible reason: unannotated irqs-on.\n");
 		}
 	}
@@ -4437,11 +4911,11 @@ void lock_set_class(struct lockdep_map *lock, const char *name,
 		return;
 
 	raw_local_irq_save(flags);
-	current->lockdep_recursion = 1;
+	current->lockdep_recursion++;
 	check_flags(flags);
 	if (__lock_set_class(lock, name, key, subclass, ip))
 		check_chain_key(current);
-	current->lockdep_recursion = 0;
+	lockdep_recursion_finish();
 	raw_local_irq_restore(flags);
 }
 EXPORT_SYMBOL_GPL(lock_set_class);
@@ -4454,15 +4928,45 @@ void lock_downgrade(struct lockdep_map *lock, unsigned long ip)
 		return;
 
 	raw_local_irq_save(flags);
-	current->lockdep_recursion = 1;
+	current->lockdep_recursion++;
 	check_flags(flags);
 	if (__lock_downgrade(lock, ip))
 		check_chain_key(current);
-	current->lockdep_recursion = 0;
+	lockdep_recursion_finish();
 	raw_local_irq_restore(flags);
 }
 EXPORT_SYMBOL_GPL(lock_downgrade);
 
+/* NMI context !!! */
+static void verify_lock_unused(struct lockdep_map *lock, struct held_lock *hlock, int subclass)
+{
+#ifdef CONFIG_PROVE_LOCKING
+	struct lock_class *class = look_up_lock_class(lock, subclass);
+
+	/* if it doesn't have a class (yet), it certainly hasn't been used yet */
+	if (!class)
+		return;
+
+	if (!(class->usage_mask & LOCK_USED))
+		return;
+
+	hlock->class_idx = class - lock_classes;
+
+	print_usage_bug(current, hlock, LOCK_USED, LOCK_USAGE_STATES);
+#endif
+}
+
+static bool lockdep_nmi(void)
+{
+	if (current->lockdep_recursion & LOCKDEP_RECURSION_MASK)
+		return false;
+
+	if (!in_nmi())
+		return false;
+
+	return true;
+}
+
 /*
  * We are not always called with irqs disabled - do that here,
  * and also avoid lockdep recursion:
@@ -4473,17 +4977,35 @@ void lock_acquire(struct lockdep_map *lock, unsigned int subclass,
 {
 	unsigned long flags;
 
-	if (unlikely(current->lockdep_recursion))
+	trace_lock_acquire(lock, subclass, trylock, read, check, nest_lock, ip);
+
+	if (unlikely(current->lockdep_recursion)) {
+		/* XXX allow trylock from NMI ?!? */
+		if (lockdep_nmi() && !trylock) {
+			struct held_lock hlock;
+
+			hlock.acquire_ip = ip;
+			hlock.instance = lock;
+			hlock.nest_lock = nest_lock;
+			hlock.irq_context = 2; // XXX
+			hlock.trylock = trylock;
+			hlock.read = read;
+			hlock.check = check;
+			hlock.hardirqs_off = true;
+			hlock.references = 0;
+
+			verify_lock_unused(lock, &hlock, subclass);
+		}
 		return;
+	}
 
 	raw_local_irq_save(flags);
 	check_flags(flags);
 
-	current->lockdep_recursion = 1;
-	trace_lock_acquire(lock, subclass, trylock, read, check, nest_lock, ip);
+	current->lockdep_recursion++;
 	__lock_acquire(lock, subclass, trylock, read, check,
 		       irqs_disabled_flags(flags), nest_lock, ip, 0, 0);
-	current->lockdep_recursion = 0;
+	lockdep_recursion_finish();
 	raw_local_irq_restore(flags);
 }
 EXPORT_SYMBOL_GPL(lock_acquire);
@@ -4492,21 +5014,23 @@ void lock_release(struct lockdep_map *lock, unsigned long ip)
 {
 	unsigned long flags;
 
+	trace_lock_release(lock, ip);
+
 	if (unlikely(current->lockdep_recursion))
 		return;
 
 	raw_local_irq_save(flags);
 	check_flags(flags);
-	current->lockdep_recursion = 1;
-	trace_lock_release(lock, ip);
+
+	current->lockdep_recursion++;
 	if (__lock_release(lock, ip))
 		check_chain_key(current);
-	current->lockdep_recursion = 0;
+	lockdep_recursion_finish();
 	raw_local_irq_restore(flags);
 }
 EXPORT_SYMBOL_GPL(lock_release);
 
-int lock_is_held_type(const struct lockdep_map *lock, int read)
+noinstr int lock_is_held_type(const struct lockdep_map *lock, int read)
 {
 	unsigned long flags;
 	int ret = 0;
@@ -4517,9 +5041,9 @@ int lock_is_held_type(const struct lockdep_map *lock, int read)
 	raw_local_irq_save(flags);
 	check_flags(flags);
 
-	current->lockdep_recursion = 1;
+	current->lockdep_recursion++;
 	ret = __lock_is_held(lock, read);
-	current->lockdep_recursion = 0;
+	lockdep_recursion_finish();
 	raw_local_irq_restore(flags);
 
 	return ret;
@@ -4538,9 +5062,9 @@ struct pin_cookie lock_pin_lock(struct lockdep_map *lock)
 	raw_local_irq_save(flags);
 	check_flags(flags);
 
-	current->lockdep_recursion = 1;
+	current->lockdep_recursion++;
 	cookie = __lock_pin_lock(lock);
-	current->lockdep_recursion = 0;
+	lockdep_recursion_finish();
 	raw_local_irq_restore(flags);
 
 	return cookie;
@@ -4557,9 +5081,9 @@ void lock_repin_lock(struct lockdep_map *lock, struct pin_cookie cookie)
 	raw_local_irq_save(flags);
 	check_flags(flags);
 
-	current->lockdep_recursion = 1;
+	current->lockdep_recursion++;
 	__lock_repin_lock(lock, cookie);
-	current->lockdep_recursion = 0;
+	lockdep_recursion_finish();
 	raw_local_irq_restore(flags);
 }
 EXPORT_SYMBOL_GPL(lock_repin_lock);
@@ -4574,9 +5098,9 @@ void lock_unpin_lock(struct lockdep_map *lock, struct pin_cookie cookie)
 	raw_local_irq_save(flags);
 	check_flags(flags);
 
-	current->lockdep_recursion = 1;
+	current->lockdep_recursion++;
 	__lock_unpin_lock(lock, cookie);
-	current->lockdep_recursion = 0;
+	lockdep_recursion_finish();
 	raw_local_irq_restore(flags);
 }
 EXPORT_SYMBOL_GPL(lock_unpin_lock);
@@ -4600,7 +5124,7 @@ static void print_lock_contention_bug(struct task_struct *curr,
 		curr->comm, task_pid_nr(curr));
 	print_lockdep_cache(lock);
 	pr_cont(") at:\n");
-	print_ip_sym(ip);
+	print_ip_sym(KERN_WARNING, ip);
 	pr_warn("but there are no locks held!\n");
 	pr_warn("\nother info that might help us debug this:\n");
 	lockdep_print_held_locks(curr);
@@ -4684,8 +5208,6 @@ __lock_acquired(struct lockdep_map *lock, unsigned long ip)
 		hlock->holdtime_stamp = now;
 	}
 
-	trace_lock_acquired(lock, ip);
-
 	stats = get_lock_stats(hlock_class(hlock));
 	if (waittime) {
 		if (hlock->read)
@@ -4704,6 +5226,8 @@ void lock_contended(struct lockdep_map *lock, unsigned long ip)
 {
 	unsigned long flags;
 
+	trace_lock_acquired(lock, ip);
+
 	if (unlikely(!lock_stat || !debug_locks))
 		return;
 
@@ -4712,10 +5236,9 @@ void lock_contended(struct lockdep_map *lock, unsigned long ip)
 
 	raw_local_irq_save(flags);
 	check_flags(flags);
-	current->lockdep_recursion = 1;
-	trace_lock_contended(lock, ip);
+	current->lockdep_recursion++;
 	__lock_contended(lock, ip);
-	current->lockdep_recursion = 0;
+	lockdep_recursion_finish();
 	raw_local_irq_restore(flags);
 }
 EXPORT_SYMBOL_GPL(lock_contended);
@@ -4724,6 +5247,8 @@ void lock_acquired(struct lockdep_map *lock, unsigned long ip)
 {
 	unsigned long flags;
 
+	trace_lock_contended(lock, ip);
+
 	if (unlikely(!lock_stat || !debug_locks))
 		return;
 
@@ -4732,9 +5257,9 @@ void lock_acquired(struct lockdep_map *lock, unsigned long ip)
 
 	raw_local_irq_save(flags);
 	check_flags(flags);
-	current->lockdep_recursion = 1;
+	current->lockdep_recursion++;
 	__lock_acquired(lock, ip);
-	current->lockdep_recursion = 0;
+	lockdep_recursion_finish();
 	raw_local_irq_restore(flags);
 }
 EXPORT_SYMBOL_GPL(lock_acquired);
@@ -4768,57 +5293,33 @@ static void remove_class_from_lock_chain(struct pending_free *pf,
 					 struct lock_class *class)
 {
 #ifdef CONFIG_PROVE_LOCKING
-	struct lock_chain *new_chain;
-	u64 chain_key;
 	int i;
 
 	for (i = chain->base; i < chain->base + chain->depth; i++) {
 		if (chain_hlocks[i] != class - lock_classes)
 			continue;
-		/* The code below leaks one chain_hlock[] entry. */
-		if (--chain->depth > 0) {
-			memmove(&chain_hlocks[i], &chain_hlocks[i + 1],
-				(chain->base + chain->depth - i) *
-				sizeof(chain_hlocks[0]));
-		}
 		/*
 		 * Each lock class occurs at most once in a lock chain so once
 		 * we found a match we can break out of this loop.
 		 */
-		goto recalc;
+		goto free_lock_chain;
 	}
 	/* Since the chain has not been modified, return. */
 	return;
 
-recalc:
-	chain_key = INITIAL_CHAIN_KEY;
-	for (i = chain->base; i < chain->base + chain->depth; i++)
-		chain_key = iterate_chain_key(chain_key, chain_hlocks[i]);
-	if (chain->depth && chain->chain_key == chain_key)
-		return;
+free_lock_chain:
+	free_chain_hlocks(chain->base, chain->depth);
 	/* Overwrite the chain key for concurrent RCU readers. */
-	WRITE_ONCE(chain->chain_key, chain_key);
+	WRITE_ONCE(chain->chain_key, INITIAL_CHAIN_KEY);
+	dec_chains(chain->irq_context);
+
 	/*
 	 * Note: calling hlist_del_rcu() from inside a
 	 * hlist_for_each_entry_rcu() loop is safe.
 	 */
 	hlist_del_rcu(&chain->entry);
 	__set_bit(chain - lock_chains, pf->lock_chains_being_freed);
-	if (chain->depth == 0)
-		return;
-	/*
-	 * If the modified lock chain matches an existing lock chain, drop
-	 * the modified lock chain.
-	 */
-	if (lookup_chain_cache(chain_key))
-		return;
-	new_chain = alloc_lock_chain();
-	if (WARN_ON_ONCE(!new_chain)) {
-		debug_locks_off();
-		return;
-	}
-	*new_chain = *chain;
-	hlist_add_head_rcu(&new_chain->entry, chainhashentry(chain_key));
+	nr_zapped_lock_chains++;
 #endif
 }
 
@@ -4874,6 +5375,7 @@ static void zap_class(struct pending_free *pf, struct lock_class *class)
 	}
 
 	remove_class_from_lock_chains(pf, class);
+	nr_zapped_classes++;
 }
 
 static void reinit_class(struct lock_class *class)
@@ -4958,8 +5460,7 @@ static void free_zapped_rcu(struct rcu_head *ch)
 		return;
 
 	raw_local_irq_save(flags);
-	arch_spin_lock(&lockdep_lock);
-	current->lockdep_recursion = 1;
+	lockdep_lock();
 
 	/* closed head */
 	pf = delayed_free.pf + (delayed_free.index ^ 1);
@@ -4971,8 +5472,7 @@ static void free_zapped_rcu(struct rcu_head *ch)
 	 */
 	call_rcu_zapped(delayed_free.pf + delayed_free.index);
 
-	current->lockdep_recursion = 0;
-	arch_spin_unlock(&lockdep_lock);
+	lockdep_unlock();
 	raw_local_irq_restore(flags);
 }
 
@@ -5017,13 +5517,11 @@ static void lockdep_free_key_range_reg(void *start, unsigned long size)
 	init_data_structures_once();
 
 	raw_local_irq_save(flags);
-	arch_spin_lock(&lockdep_lock);
-	current->lockdep_recursion = 1;
+	lockdep_lock();
 	pf = get_pending_free();
 	__lockdep_free_key_range(pf, start, size);
 	call_rcu_zapped(pf);
-	current->lockdep_recursion = 0;
-	arch_spin_unlock(&lockdep_lock);
+	lockdep_unlock();
 	raw_local_irq_restore(flags);
 
 	/*
@@ -5045,10 +5543,10 @@ static void lockdep_free_key_range_imm(void *start, unsigned long size)
 	init_data_structures_once();
 
 	raw_local_irq_save(flags);
-	arch_spin_lock(&lockdep_lock);
+	lockdep_lock();
 	__lockdep_free_key_range(pf, start, size);
 	__free_zapped_classes(pf);
-	arch_spin_unlock(&lockdep_lock);
+	lockdep_unlock();
 	raw_local_irq_restore(flags);
 }
 
@@ -5144,10 +5642,10 @@ static void lockdep_reset_lock_imm(struct lockdep_map *lock)
 	unsigned long flags;
 
 	raw_local_irq_save(flags);
-	arch_spin_lock(&lockdep_lock);
+	lockdep_lock();
 	__lockdep_reset_lock(pf, lock);
 	__free_zapped_classes(pf);
-	arch_spin_unlock(&lockdep_lock);
+	lockdep_unlock();
 	raw_local_irq_restore(flags);
 }
 
@@ -5403,9 +5901,7 @@ void lockdep_rcu_suspicious(const char *file, const int line, const char *s)
 	pr_warn("\n%srcu_scheduler_active = %d, debug_locks = %d\n",
 	       !rcu_lockdep_current_cpu_online()
 			? "RCU used illegally from offline CPU!\n"
-			: !rcu_is_watching()
-				? "RCU used illegally from idle CPU!\n"
-				: "",
+			: "",
 	       rcu_scheduler_active, debug_locks);
 
 	/*
diff --git a/kernel/locking/lockdep_internals.h b/kernel/locking/lockdep_internals.h
index 18d85aebbb57..baca699b94e9 100644
--- a/kernel/locking/lockdep_internals.h
+++ b/kernel/locking/lockdep_internals.h
@@ -106,6 +106,12 @@ static const unsigned long LOCKF_USED_IN_IRQ_READ =
 #define STACK_TRACE_HASH_SIZE	16384
 #endif
 
+/*
+ * Bit definitions for lock_chain.irq_context
+ */
+#define LOCK_CHAIN_SOFTIRQ_CONTEXT	(1 << 0)
+#define LOCK_CHAIN_HARDIRQ_CONTEXT	(1 << 1)
+
 #define MAX_LOCKDEP_CHAINS	(1UL << MAX_LOCKDEP_CHAINS_BITS)
 
 #define MAX_LOCKDEP_CHAIN_HLOCKS (MAX_LOCKDEP_CHAINS*5)
@@ -124,17 +130,21 @@ extern const char *__get_key_name(const struct lockdep_subclass_key *key,
 struct lock_class *lock_chain_get_class(struct lock_chain *chain, int i);
 
 extern unsigned long nr_lock_classes;
+extern unsigned long nr_zapped_classes;
+extern unsigned long nr_zapped_lock_chains;
 extern unsigned long nr_list_entries;
 long lockdep_next_lockchain(long i);
 unsigned long lock_chain_count(void);
-extern int nr_chain_hlocks;
 extern unsigned long nr_stack_trace_entries;
 
 extern unsigned int nr_hardirq_chains;
 extern unsigned int nr_softirq_chains;
 extern unsigned int nr_process_chains;
-extern unsigned int max_lockdep_depth;
+extern unsigned int nr_free_chain_hlocks;
+extern unsigned int nr_lost_chain_hlocks;
+extern unsigned int nr_large_chain_blocks;
 
+extern unsigned int max_lockdep_depth;
 extern unsigned int max_bfs_queue_depth;
 
 #ifdef CONFIG_PROVE_LOCKING
diff --git a/kernel/locking/lockdep_proc.c b/kernel/locking/lockdep_proc.c
index 231684cfc5ae..02ef87f50df2 100644
--- a/kernel/locking/lockdep_proc.c
+++ b/kernel/locking/lockdep_proc.c
@@ -128,15 +128,22 @@ static int lc_show(struct seq_file *m, void *v)
 	struct lock_chain *chain = v;
 	struct lock_class *class;
 	int i;
+	static const char * const irq_strs[] = {
+		[0]			     = "0",
+		[LOCK_CHAIN_HARDIRQ_CONTEXT] = "hardirq",
+		[LOCK_CHAIN_SOFTIRQ_CONTEXT] = "softirq",
+		[LOCK_CHAIN_SOFTIRQ_CONTEXT|
+		 LOCK_CHAIN_HARDIRQ_CONTEXT] = "hardirq|softirq",
+	};
 
 	if (v == SEQ_START_TOKEN) {
-		if (nr_chain_hlocks > MAX_LOCKDEP_CHAIN_HLOCKS)
+		if (!nr_free_chain_hlocks)
 			seq_printf(m, "(buggered) ");
 		seq_printf(m, "all lock chains:\n");
 		return 0;
 	}
 
-	seq_printf(m, "irq_context: %d\n", chain->irq_context);
+	seq_printf(m, "irq_context: %s\n", irq_strs[chain->irq_context]);
 
 	for (i = 0; i < chain->depth; i++) {
 		class = lock_chain_get_class(chain, i);
@@ -271,8 +278,12 @@ static int lockdep_stats_show(struct seq_file *m, void *v)
 #ifdef CONFIG_PROVE_LOCKING
 	seq_printf(m, " dependency chains:             %11lu [max: %lu]\n",
 			lock_chain_count(), MAX_LOCKDEP_CHAINS);
-	seq_printf(m, " dependency chain hlocks:       %11d [max: %lu]\n",
-			nr_chain_hlocks, MAX_LOCKDEP_CHAIN_HLOCKS);
+	seq_printf(m, " dependency chain hlocks used:  %11lu [max: %lu]\n",
+			MAX_LOCKDEP_CHAIN_HLOCKS -
+			(nr_free_chain_hlocks + nr_lost_chain_hlocks),
+			MAX_LOCKDEP_CHAIN_HLOCKS);
+	seq_printf(m, " dependency chain hlocks lost:  %11u\n",
+			nr_lost_chain_hlocks);
 #endif
 
 #ifdef CONFIG_TRACE_IRQFLAGS
@@ -336,6 +347,18 @@ static int lockdep_stats_show(struct seq_file *m, void *v)
 	seq_printf(m, " debug_locks:                   %11u\n",
 			debug_locks);
 
+	/*
+	 * Zappped classes and lockdep data buffers reuse statistics.
+	 */
+	seq_puts(m, "\n");
+	seq_printf(m, " zapped classes:                %11lu\n",
+			nr_zapped_classes);
+#ifdef CONFIG_PROVE_LOCKING
+	seq_printf(m, " zapped lock chains:            %11lu\n",
+			nr_zapped_lock_chains);
+	seq_printf(m, " large chain blocks:            %11u\n",
+			nr_large_chain_blocks);
+#endif
 	return 0;
 }
 
@@ -400,7 +423,7 @@ static void seq_lock_time(struct seq_file *m, struct lock_time *lt)
 	seq_time(m, lt->min);
 	seq_time(m, lt->max);
 	seq_time(m, lt->total);
-	seq_time(m, lt->nr ? div_s64(lt->total, lt->nr) : 0);
+	seq_time(m, lt->nr ? div64_u64(lt->total, lt->nr) : 0);
 }
 
 static void seq_stats(struct seq_file *m, struct lock_stat_data *data)
diff --git a/kernel/locking/locktorture.c b/kernel/locking/locktorture.c
index 99475a66c94f..9cfa5e89cff7 100644
--- a/kernel/locking/locktorture.c
+++ b/kernel/locking/locktorture.c
@@ -436,8 +436,6 @@ static int torture_rtmutex_lock(void) __acquires(torture_rtmutex)
 
 static void torture_rtmutex_boost(struct torture_random_state *trsp)
 {
-	int policy;
-	struct sched_param param;
 	const unsigned int factor = 50000; /* yes, quite arbitrary */
 
 	if (!rt_task(current)) {
@@ -448,8 +446,7 @@ static void torture_rtmutex_boost(struct torture_random_state *trsp)
 		 */
 		if (trsp && !(torture_random(trsp) %
 			      (cxt.nrealwriters_stress * factor))) {
-			policy = SCHED_FIFO;
-			param.sched_priority = MAX_RT_PRIO - 1;
+			sched_set_fifo(current);
 		} else /* common case, do nothing */
 			return;
 	} else {
@@ -462,13 +459,10 @@ static void torture_rtmutex_boost(struct torture_random_state *trsp)
 		 */
 		if (!trsp || !(torture_random(trsp) %
 			       (cxt.nrealwriters_stress * factor * 2))) {
-			policy = SCHED_NORMAL;
-			param.sched_priority = 0;
+			sched_set_normal(current, 0);
 		} else /* common case, do nothing */
 			return;
 	}
-
-	sched_setscheduler_nocheck(current, policy, &param);
 }
 
 static void torture_rtmutex_delay(struct torture_random_state *trsp)
@@ -618,7 +612,7 @@ static struct lock_torture_ops percpu_rwsem_lock_ops = {
 static int lock_torture_writer(void *arg)
 {
 	struct lock_stress_stats *lwsp = arg;
-	static DEFINE_TORTURE_RANDOM(rand);
+	DEFINE_TORTURE_RANDOM(rand);
 
 	VERBOSE_TOROUT_STRING("lock_torture_writer task started");
 	set_user_nice(current, MAX_NICE);
@@ -631,13 +625,13 @@ static int lock_torture_writer(void *arg)
 		cxt.cur_ops->writelock();
 		if (WARN_ON_ONCE(lock_is_write_held))
 			lwsp->n_lock_fail++;
-		lock_is_write_held = 1;
+		lock_is_write_held = true;
 		if (WARN_ON_ONCE(lock_is_read_held))
 			lwsp->n_lock_fail++; /* rare, but... */
 
 		lwsp->n_lock_acquired++;
 		cxt.cur_ops->write_delay(&rand);
-		lock_is_write_held = 0;
+		lock_is_write_held = false;
 		cxt.cur_ops->writeunlock();
 
 		stutter_wait("lock_torture_writer");
@@ -655,7 +649,7 @@ static int lock_torture_writer(void *arg)
 static int lock_torture_reader(void *arg)
 {
 	struct lock_stress_stats *lrsp = arg;
-	static DEFINE_TORTURE_RANDOM(rand);
+	DEFINE_TORTURE_RANDOM(rand);
 
 	VERBOSE_TOROUT_STRING("lock_torture_reader task started");
 	set_user_nice(current, MAX_NICE);
@@ -665,13 +659,13 @@ static int lock_torture_reader(void *arg)
 			schedule_timeout_uninterruptible(1);
 
 		cxt.cur_ops->readlock();
-		lock_is_read_held = 1;
+		lock_is_read_held = true;
 		if (WARN_ON_ONCE(lock_is_write_held))
 			lrsp->n_lock_fail++; /* rare, but... */
 
 		lrsp->n_lock_acquired++;
 		cxt.cur_ops->read_delay(&rand);
-		lock_is_read_held = 0;
+		lock_is_read_held = false;
 		cxt.cur_ops->readunlock();
 
 		stutter_wait("lock_torture_reader");
@@ -686,7 +680,7 @@ static int lock_torture_reader(void *arg)
 static void __torture_print_stats(char *page,
 				  struct lock_stress_stats *statp, bool write)
 {
-	bool fail = 0;
+	bool fail = false;
 	int i, n_stress;
 	long max = 0, min = statp ? statp[0].n_lock_acquired : 0;
 	long long sum = 0;
@@ -696,15 +690,16 @@ static void __torture_print_stats(char *page,
 		if (statp[i].n_lock_fail)
 			fail = true;
 		sum += statp[i].n_lock_acquired;
-		if (max < statp[i].n_lock_fail)
-			max = statp[i].n_lock_fail;
-		if (min > statp[i].n_lock_fail)
-			min = statp[i].n_lock_fail;
+		if (max < statp[i].n_lock_acquired)
+			max = statp[i].n_lock_acquired;
+		if (min > statp[i].n_lock_acquired)
+			min = statp[i].n_lock_acquired;
 	}
 	page += sprintf(page,
 			"%s:  Total: %lld  Max/Min: %ld/%ld %s  Fail: %d %s\n",
 			write ? "Writes" : "Reads ",
-			sum, max, min, max / 2 > min ? "???" : "",
+			sum, max, min,
+			!onoff_interval && max / 2 > min ? "???" : "",
 			fail, fail ? "!!!" : "");
 	if (fail)
 		atomic_inc(&cxt.n_lock_torture_errors);
@@ -903,7 +898,7 @@ static int __init lock_torture_init(void)
 
 	/* Initialize the statistics so that each run gets its own numbers. */
 	if (nwriters_stress) {
-		lock_is_write_held = 0;
+		lock_is_write_held = false;
 		cxt.lwsa = kmalloc_array(cxt.nrealwriters_stress,
 					 sizeof(*cxt.lwsa),
 					 GFP_KERNEL);
@@ -934,7 +929,7 @@ static int __init lock_torture_init(void)
 		}
 
 		if (nreaders_stress) {
-			lock_is_read_held = 0;
+			lock_is_read_held = false;
 			cxt.lrsa = kmalloc_array(cxt.nrealreaders_stress,
 						 sizeof(*cxt.lrsa),
 						 GFP_KERNEL);
diff --git a/kernel/locking/mutex-debug.c b/kernel/locking/mutex-debug.c
index 771d4ca96dda..a7276aaf2abc 100644
--- a/kernel/locking/mutex-debug.c
+++ b/kernel/locking/mutex-debug.c
@@ -85,7 +85,7 @@ void debug_mutex_init(struct mutex *lock, const char *name,
 	 * Make sure we are not reinitializing a held lock:
 	 */
 	debug_check_no_locks_freed((void *)lock, sizeof(*lock));
-	lockdep_init_map(&lock->dep_map, name, key, 0);
+	lockdep_init_map_wait(&lock->dep_map, name, key, 0, LD_WAIT_SLEEP);
 #endif
 	lock->magic = lock;
 }
diff --git a/kernel/locking/osq_lock.c b/kernel/locking/osq_lock.c
index 1f7734949ac8..1de006ed3aa8 100644
--- a/kernel/locking/osq_lock.c
+++ b/kernel/locking/osq_lock.c
@@ -154,7 +154,11 @@ bool osq_lock(struct optimistic_spin_queue *lock)
 	 */
 
 	for (;;) {
-		if (prev->next == node &&
+		/*
+		 * cpu_relax() below implies a compiler barrier which would
+		 * prevent this comparison being optimized away.
+		 */
+		if (data_race(prev->next) == node &&
 		    cmpxchg(&prev->next, node, NULL) == node)
 			break;
 
diff --git a/kernel/locking/percpu-rwsem.c b/kernel/locking/percpu-rwsem.c
index 364d38a0c444..8bbafe3e5203 100644
--- a/kernel/locking/percpu-rwsem.c
+++ b/kernel/locking/percpu-rwsem.c
@@ -1,27 +1,29 @@
 // SPDX-License-Identifier: GPL-2.0-only
 #include <linux/atomic.h>
-#include <linux/rwsem.h>
 #include <linux/percpu.h>
+#include <linux/wait.h>
 #include <linux/lockdep.h>
 #include <linux/percpu-rwsem.h>
 #include <linux/rcupdate.h>
 #include <linux/sched.h>
+#include <linux/sched/task.h>
 #include <linux/errno.h>
 
-#include "rwsem.h"
-
 int __percpu_init_rwsem(struct percpu_rw_semaphore *sem,
-			const char *name, struct lock_class_key *rwsem_key)
+			const char *name, struct lock_class_key *key)
 {
 	sem->read_count = alloc_percpu(int);
 	if (unlikely(!sem->read_count))
 		return -ENOMEM;
 
-	/* ->rw_sem represents the whole percpu_rw_semaphore for lockdep */
 	rcu_sync_init(&sem->rss);
-	__init_rwsem(&sem->rw_sem, name, rwsem_key);
 	rcuwait_init(&sem->writer);
-	sem->readers_block = 0;
+	init_waitqueue_head(&sem->waiters);
+	atomic_set(&sem->block, 0);
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+	debug_check_no_locks_freed((void *)sem, sizeof(*sem));
+	lockdep_init_map(&sem->dep_map, name, key, 0);
+#endif
 	return 0;
 }
 EXPORT_SYMBOL_GPL(__percpu_init_rwsem);
@@ -41,73 +43,140 @@ void percpu_free_rwsem(struct percpu_rw_semaphore *sem)
 }
 EXPORT_SYMBOL_GPL(percpu_free_rwsem);
 
-int __percpu_down_read(struct percpu_rw_semaphore *sem, int try)
+static bool __percpu_down_read_trylock(struct percpu_rw_semaphore *sem)
 {
+	__this_cpu_inc(*sem->read_count);
+
 	/*
 	 * Due to having preemption disabled the decrement happens on
 	 * the same CPU as the increment, avoiding the
 	 * increment-on-one-CPU-and-decrement-on-another problem.
 	 *
-	 * If the reader misses the writer's assignment of readers_block, then
-	 * the writer is guaranteed to see the reader's increment.
+	 * If the reader misses the writer's assignment of sem->block, then the
+	 * writer is guaranteed to see the reader's increment.
 	 *
 	 * Conversely, any readers that increment their sem->read_count after
-	 * the writer looks are guaranteed to see the readers_block value,
-	 * which in turn means that they are guaranteed to immediately
-	 * decrement their sem->read_count, so that it doesn't matter that the
-	 * writer missed them.
+	 * the writer looks are guaranteed to see the sem->block value, which
+	 * in turn means that they are guaranteed to immediately decrement
+	 * their sem->read_count, so that it doesn't matter that the writer
+	 * missed them.
 	 */
 
 	smp_mb(); /* A matches D */
 
 	/*
-	 * If !readers_block the critical section starts here, matched by the
+	 * If !sem->block the critical section starts here, matched by the
 	 * release in percpu_up_write().
 	 */
-	if (likely(!smp_load_acquire(&sem->readers_block)))
+	if (likely(!atomic_read_acquire(&sem->block)))
+		return true;
+
+	__this_cpu_dec(*sem->read_count);
+
+	/* Prod writer to re-evaluate readers_active_check() */
+	rcuwait_wake_up(&sem->writer);
+
+	return false;
+}
+
+static inline bool __percpu_down_write_trylock(struct percpu_rw_semaphore *sem)
+{
+	if (atomic_read(&sem->block))
+		return false;
+
+	return atomic_xchg(&sem->block, 1) == 0;
+}
+
+static bool __percpu_rwsem_trylock(struct percpu_rw_semaphore *sem, bool reader)
+{
+	if (reader) {
+		bool ret;
+
+		preempt_disable();
+		ret = __percpu_down_read_trylock(sem);
+		preempt_enable();
+
+		return ret;
+	}
+	return __percpu_down_write_trylock(sem);
+}
+
+/*
+ * The return value of wait_queue_entry::func means:
+ *
+ *  <0 - error, wakeup is terminated and the error is returned
+ *   0 - no wakeup, a next waiter is tried
+ *  >0 - woken, if EXCLUSIVE, counted towards @nr_exclusive.
+ *
+ * We use EXCLUSIVE for both readers and writers to preserve FIFO order,
+ * and play games with the return value to allow waking multiple readers.
+ *
+ * Specifically, we wake readers until we've woken a single writer, or until a
+ * trylock fails.
+ */
+static int percpu_rwsem_wake_function(struct wait_queue_entry *wq_entry,
+				      unsigned int mode, int wake_flags,
+				      void *key)
+{
+	bool reader = wq_entry->flags & WQ_FLAG_CUSTOM;
+	struct percpu_rw_semaphore *sem = key;
+	struct task_struct *p;
+
+	/* concurrent against percpu_down_write(), can get stolen */
+	if (!__percpu_rwsem_trylock(sem, reader))
 		return 1;
 
-	/*
-	 * Per the above comment; we still have preemption disabled and
-	 * will thus decrement on the same CPU as we incremented.
-	 */
-	__percpu_up_read(sem);
+	p = get_task_struct(wq_entry->private);
+	list_del_init(&wq_entry->entry);
+	smp_store_release(&wq_entry->private, NULL);
 
-	if (try)
-		return 0;
+	wake_up_process(p);
+	put_task_struct(p);
 
-	/*
-	 * We either call schedule() in the wait, or we'll fall through
-	 * and reschedule on the preempt_enable() in percpu_down_read().
-	 */
-	preempt_enable_no_resched();
+	return !reader; /* wake (readers until) 1 writer */
+}
+
+static void percpu_rwsem_wait(struct percpu_rw_semaphore *sem, bool reader)
+{
+	DEFINE_WAIT_FUNC(wq_entry, percpu_rwsem_wake_function);
+	bool wait;
 
+	spin_lock_irq(&sem->waiters.lock);
 	/*
-	 * Avoid lockdep for the down/up_read() we already have them.
+	 * Serialize against the wakeup in percpu_up_write(), if we fail
+	 * the trylock, the wakeup must see us on the list.
 	 */
-	__down_read(&sem->rw_sem);
-	this_cpu_inc(*sem->read_count);
-	__up_read(&sem->rw_sem);
+	wait = !__percpu_rwsem_trylock(sem, reader);
+	if (wait) {
+		wq_entry.flags |= WQ_FLAG_EXCLUSIVE | reader * WQ_FLAG_CUSTOM;
+		__add_wait_queue_entry_tail(&sem->waiters, &wq_entry);
+	}
+	spin_unlock_irq(&sem->waiters.lock);
 
-	preempt_disable();
-	return 1;
+	while (wait) {
+		set_current_state(TASK_UNINTERRUPTIBLE);
+		if (!smp_load_acquire(&wq_entry.private))
+			break;
+		schedule();
+	}
+	__set_current_state(TASK_RUNNING);
 }
-EXPORT_SYMBOL_GPL(__percpu_down_read);
 
-void __percpu_up_read(struct percpu_rw_semaphore *sem)
+bool __percpu_down_read(struct percpu_rw_semaphore *sem, bool try)
 {
-	smp_mb(); /* B matches C */
-	/*
-	 * In other words, if they see our decrement (presumably to aggregate
-	 * zero, as that is the only time it matters) they will also see our
-	 * critical section.
-	 */
-	__this_cpu_dec(*sem->read_count);
+	if (__percpu_down_read_trylock(sem))
+		return true;
 
-	/* Prod writer to recheck readers_active */
-	rcuwait_wake_up(&sem->writer);
+	if (try)
+		return false;
+
+	preempt_enable();
+	percpu_rwsem_wait(sem, /* .reader = */ true);
+	preempt_disable();
+
+	return true;
 }
-EXPORT_SYMBOL_GPL(__percpu_up_read);
+EXPORT_SYMBOL_GPL(__percpu_down_read);
 
 #define per_cpu_sum(var)						\
 ({									\
@@ -124,6 +193,8 @@ EXPORT_SYMBOL_GPL(__percpu_up_read);
  * zero.  If this sum is zero, then it is stable due to the fact that if any
  * newly arriving readers increment a given counter, they will immediately
  * decrement that same counter.
+ *
+ * Assumes sem->block is set.
  */
 static bool readers_active_check(struct percpu_rw_semaphore *sem)
 {
@@ -142,32 +213,36 @@ static bool readers_active_check(struct percpu_rw_semaphore *sem)
 
 void percpu_down_write(struct percpu_rw_semaphore *sem)
 {
+	might_sleep();
+	rwsem_acquire(&sem->dep_map, 0, 0, _RET_IP_);
+
 	/* Notify readers to take the slow path. */
 	rcu_sync_enter(&sem->rss);
 
-	down_write(&sem->rw_sem);
-
 	/*
-	 * Notify new readers to block; up until now, and thus throughout the
-	 * longish rcu_sync_enter() above, new readers could still come in.
+	 * Try set sem->block; this provides writer-writer exclusion.
+	 * Having sem->block set makes new readers block.
 	 */
-	WRITE_ONCE(sem->readers_block, 1);
+	if (!__percpu_down_write_trylock(sem))
+		percpu_rwsem_wait(sem, /* .reader = */ false);
 
-	smp_mb(); /* D matches A */
+	/* smp_mb() implied by __percpu_down_write_trylock() on success -- D matches A */
 
 	/*
-	 * If they don't see our writer of readers_block, then we are
-	 * guaranteed to see their sem->read_count increment, and therefore
-	 * will wait for them.
+	 * If they don't see our store of sem->block, then we are guaranteed to
+	 * see their sem->read_count increment, and therefore will wait for
+	 * them.
 	 */
 
-	/* Wait for all now active readers to complete. */
-	rcuwait_wait_event(&sem->writer, readers_active_check(sem));
+	/* Wait for all active readers to complete. */
+	rcuwait_wait_event(&sem->writer, readers_active_check(sem), TASK_UNINTERRUPTIBLE);
 }
 EXPORT_SYMBOL_GPL(percpu_down_write);
 
 void percpu_up_write(struct percpu_rw_semaphore *sem)
 {
+	rwsem_release(&sem->dep_map, _RET_IP_);
+
 	/*
 	 * Signal the writer is done, no fast path yet.
 	 *
@@ -178,12 +253,12 @@ void percpu_up_write(struct percpu_rw_semaphore *sem)
 	 * Therefore we force it through the slow path which guarantees an
 	 * acquire and thereby guarantees the critical section's consistency.
 	 */
-	smp_store_release(&sem->readers_block, 0);
+	atomic_set_release(&sem->block, 0);
 
 	/*
-	 * Release the write lock, this will allow readers back in the game.
+	 * Prod any pending reader/writer to make progress.
 	 */
-	up_write(&sem->rw_sem);
+	__wake_up(&sem->waiters, TASK_NORMAL, 1, sem);
 
 	/*
 	 * Once this completes (at least one RCU-sched grace period hence) the
diff --git a/kernel/locking/qspinlock.c b/kernel/locking/qspinlock.c
index b9515fcc9b29..cbff6ba53d56 100644
--- a/kernel/locking/qspinlock.c
+++ b/kernel/locking/qspinlock.c
@@ -581,4 +581,11 @@ EXPORT_SYMBOL(queued_spin_lock_slowpath);
 #include "qspinlock_paravirt.h"
 #include "qspinlock.c"
 
+bool nopvspin __initdata;
+static __init int parse_nopvspin(char *arg)
+{
+	nopvspin = true;
+	return 0;
+}
+early_param("nopvspin", parse_nopvspin);
 #endif
diff --git a/kernel/locking/rtmutex-debug.c b/kernel/locking/rtmutex-debug.c
index fd4fe1f5b458..36e69100e8e0 100644
--- a/kernel/locking/rtmutex-debug.c
+++ b/kernel/locking/rtmutex-debug.c
@@ -125,7 +125,7 @@ void debug_rt_mutex_print_deadlock(struct rt_mutex_waiter *waiter)
 
 	printk("\n%s/%d's [blocked] stackdump:\n\n",
 		task->comm, task_pid_nr(task));
-	show_stack(task, NULL);
+	show_stack(task, NULL, KERN_DEFAULT);
 	printk("\n%s/%d's [current] stackdump:\n\n",
 		current->comm, task_pid_nr(current));
 	dump_stack();
diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c
index 851bbb10819d..cfdd5b93264d 100644
--- a/kernel/locking/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -57,7 +57,7 @@ rt_mutex_set_owner(struct rt_mutex *lock, struct task_struct *owner)
 	if (rt_mutex_has_waiters(lock))
 		val |= RT_MUTEX_HAS_WAITERS;
 
-	lock->owner = (struct task_struct *)val;
+	WRITE_ONCE(lock->owner, (struct task_struct *)val);
 }
 
 static inline void clear_rt_mutex_waiters(struct rt_mutex *lock)
@@ -141,7 +141,6 @@ static void fixup_rt_mutex_waiters(struct rt_mutex *lock)
  * set up.
  */
 #ifndef CONFIG_DEBUG_RT_MUTEXES
-# define rt_mutex_cmpxchg_relaxed(l,c,n) (cmpxchg_relaxed(&l->owner, c, n) == c)
 # define rt_mutex_cmpxchg_acquire(l,c,n) (cmpxchg_acquire(&l->owner, c, n) == c)
 # define rt_mutex_cmpxchg_release(l,c,n) (cmpxchg_release(&l->owner, c, n) == c)
 
@@ -202,7 +201,6 @@ static inline bool unlock_rt_mutex_safe(struct rt_mutex *lock,
 }
 
 #else
-# define rt_mutex_cmpxchg_relaxed(l,c,n)	(0)
 # define rt_mutex_cmpxchg_acquire(l,c,n)	(0)
 # define rt_mutex_cmpxchg_release(l,c,n)	(0)
 
diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c
index 0d9b6be9ecc8..f11b9bd3431d 100644
--- a/kernel/locking/rwsem.c
+++ b/kernel/locking/rwsem.c
@@ -28,7 +28,6 @@
 #include <linux/rwsem.h>
 #include <linux/atomic.h>
 
-#include "rwsem.h"
 #include "lock_events.h"
 
 /*
@@ -329,7 +328,7 @@ void __init_rwsem(struct rw_semaphore *sem, const char *name,
 	 * Make sure we are not reinitializing a held semaphore:
 	 */
 	debug_check_no_locks_freed((void *)sem, sizeof(*sem));
-	lockdep_init_map(&sem->dep_map, name, key, 0);
+	lockdep_init_map_wait(&sem->dep_map, name, key, 0, LD_WAIT_SLEEP);
 #endif
 #ifdef CONFIG_DEBUG_RWSEMS
 	sem->magic = sem;
@@ -660,8 +659,6 @@ static inline bool rwsem_can_spin_on_owner(struct rw_semaphore *sem,
 	unsigned long flags;
 	bool ret = true;
 
-	BUILD_BUG_ON(!(RWSEM_OWNER_UNKNOWN & RWSEM_NONSPINNABLE));
-
 	if (need_resched()) {
 		lockevent_inc(rwsem_opt_fail);
 		return false;
@@ -1338,7 +1335,7 @@ static struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem)
 /*
  * lock for reading
  */
-inline void __down_read(struct rw_semaphore *sem)
+static inline void __down_read(struct rw_semaphore *sem)
 {
 	if (!rwsem_read_trylock(sem)) {
 		rwsem_down_read_slowpath(sem, TASK_UNINTERRUPTIBLE);
@@ -1426,7 +1423,7 @@ static inline int __down_write_trylock(struct rw_semaphore *sem)
 /*
  * unlock after reading
  */
-inline void __up_read(struct rw_semaphore *sem)
+static inline void __up_read(struct rw_semaphore *sem)
 {
 	long tmp;
 
diff --git a/kernel/locking/rwsem.h b/kernel/locking/rwsem.h
index 2534ce49f648..e69de29bb2d1 100644
--- a/kernel/locking/rwsem.h
+++ b/kernel/locking/rwsem.h
@@ -1,10 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-
-#ifndef __INTERNAL_RWSEM_H
-#define __INTERNAL_RWSEM_H
-#include <linux/rwsem.h>
-
-extern void __down_read(struct rw_semaphore *sem);
-extern void __up_read(struct rw_semaphore *sem);
-
-#endif /* __INTERNAL_RWSEM_H */
diff --git a/kernel/locking/spinlock_debug.c b/kernel/locking/spinlock_debug.c
index 472dd462a40c..b9d93087ee66 100644
--- a/kernel/locking/spinlock_debug.c
+++ b/kernel/locking/spinlock_debug.c
@@ -14,14 +14,14 @@
 #include <linux/export.h>
 
 void __raw_spin_lock_init(raw_spinlock_t *lock, const char *name,
-			  struct lock_class_key *key)
+			  struct lock_class_key *key, short inner)
 {
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 	/*
 	 * Make sure we are not reinitializing a held lock:
 	 */
 	debug_check_no_locks_freed((void *)lock, sizeof(*lock));
-	lockdep_init_map(&lock->dep_map, name, key, 0);
+	lockdep_init_map_wait(&lock->dep_map, name, key, 0, inner);
 #endif
 	lock->raw_lock = (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED;
 	lock->magic = SPINLOCK_MAGIC;
@@ -39,7 +39,7 @@ void __rwlock_init(rwlock_t *lock, const char *name,
 	 * Make sure we are not reinitializing a held lock:
 	 */
 	debug_check_no_locks_freed((void *)lock, sizeof(*lock));
-	lockdep_init_map(&lock->dep_map, name, key, 0);
+	lockdep_init_map_wait(&lock->dep_map, name, key, 0, LD_WAIT_CONFIG);
 #endif
 	lock->raw_lock = (arch_rwlock_t) __ARCH_RW_LOCK_UNLOCKED;
 	lock->magic = RWLOCK_MAGIC;
diff --git a/kernel/module.c b/kernel/module.c
index 33569a01d6e1..1c5cff34d9f2 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -4,6 +4,9 @@
    Copyright (C) 2001 Rusty Russell, 2002, 2010 Rusty Russell IBM.
 
 */
+
+#define INCLUDE_VERMAGIC
+
 #include <linux/export.h>
 #include <linux/extable.h>
 #include <linux/moduleloader.h>
@@ -419,7 +422,7 @@ static bool each_symbol_in_section(const struct symsearch *arr,
 }
 
 /* Returns true as soon as fn returns true, otherwise false. */
-bool each_symbol_section(bool (*fn)(const struct symsearch *arr,
+static bool each_symbol_section(bool (*fn)(const struct symsearch *arr,
 				    struct module *owner,
 				    void *data),
 			 void *data)
@@ -481,7 +484,6 @@ bool each_symbol_section(bool (*fn)(const struct symsearch *arr,
 	}
 	return false;
 }
-EXPORT_SYMBOL_GPL(each_symbol_section);
 
 struct find_symbol_arg {
 	/* Input */
@@ -493,6 +495,7 @@ struct find_symbol_arg {
 	struct module *owner;
 	const s32 *crc;
 	const struct kernel_symbol *sym;
+	enum mod_license license;
 };
 
 static bool check_exported_symbol(const struct symsearch *syms,
@@ -502,9 +505,9 @@ static bool check_exported_symbol(const struct symsearch *syms,
 	struct find_symbol_arg *fsa = data;
 
 	if (!fsa->gplok) {
-		if (syms->licence == GPL_ONLY)
+		if (syms->license == GPL_ONLY)
 			return false;
-		if (syms->licence == WILL_BE_GPL_ONLY && fsa->warn) {
+		if (syms->license == WILL_BE_GPL_ONLY && fsa->warn) {
 			pr_warn("Symbol %s is being used by a non-GPL module, "
 				"which will not be allowed in the future\n",
 				fsa->name);
@@ -526,6 +529,7 @@ static bool check_exported_symbol(const struct symsearch *syms,
 	fsa->owner = owner;
 	fsa->crc = symversion(syms->crcs, symnum);
 	fsa->sym = &syms->start[symnum];
+	fsa->license = syms->license;
 	return true;
 }
 
@@ -582,9 +586,10 @@ static bool find_exported_symbol_in_section(const struct symsearch *syms,
 
 /* Find an exported symbol and return it, along with, (optional) crc and
  * (optional) module which owns it.  Needs preempt disabled or module_mutex. */
-const struct kernel_symbol *find_symbol(const char *name,
+static const struct kernel_symbol *find_symbol(const char *name,
 					struct module **owner,
 					const s32 **crc,
+					enum mod_license *license,
 					bool gplok,
 					bool warn)
 {
@@ -599,13 +604,14 @@ const struct kernel_symbol *find_symbol(const char *name,
 			*owner = fsa.owner;
 		if (crc)
 			*crc = fsa.crc;
+		if (license)
+			*license = fsa.license;
 		return fsa.sym;
 	}
 
 	pr_debug("Failed to find symbol %s\n", name);
 	return NULL;
 }
-EXPORT_SYMBOL_GPL(find_symbol);
 
 /*
  * Search for module by name: must hold module_mutex (or preempt disabled
@@ -866,7 +872,7 @@ static int add_module_usage(struct module *a, struct module *b)
 }
 
 /* Module a uses b: caller needs module_mutex() */
-int ref_module(struct module *a, struct module *b)
+static int ref_module(struct module *a, struct module *b)
 {
 	int err;
 
@@ -885,7 +891,6 @@ int ref_module(struct module *a, struct module *b)
 	}
 	return 0;
 }
-EXPORT_SYMBOL_GPL(ref_module);
 
 /* Clear the unload stuff of the module. */
 static void module_unload_free(struct module *mod)
@@ -1074,7 +1079,7 @@ void __symbol_put(const char *symbol)
 	struct module *owner;
 
 	preempt_disable();
-	if (!find_symbol(symbol, &owner, NULL, true, false))
+	if (!find_symbol(symbol, &owner, NULL, NULL, true, false))
 		BUG();
 	module_put(owner);
 	preempt_enable();
@@ -1166,11 +1171,10 @@ static inline void module_unload_free(struct module *mod)
 {
 }
 
-int ref_module(struct module *a, struct module *b)
+static int ref_module(struct module *a, struct module *b)
 {
 	return strong_try_module_get(b);
 }
-EXPORT_SYMBOL_GPL(ref_module);
 
 static inline int module_unload_init(struct module *mod)
 {
@@ -1353,7 +1357,7 @@ static inline int check_modstruct_version(const struct load_info *info,
 	 * locking is necessary -- use preempt_disable() to placate lockdep.
 	 */
 	preempt_disable();
-	if (!find_symbol("module_layout", NULL, &crc, true, false)) {
+	if (!find_symbol("module_layout", NULL, &crc, NULL, true, false)) {
 		preempt_enable();
 		BUG();
 	}
@@ -1427,6 +1431,24 @@ static int verify_namespace_is_imported(const struct load_info *info,
 	return 0;
 }
 
+static bool inherit_taint(struct module *mod, struct module *owner)
+{
+	if (!owner || !test_bit(TAINT_PROPRIETARY_MODULE, &owner->taints))
+		return true;
+
+	if (mod->using_gplonly_symbols) {
+		pr_err("%s: module using GPL-only symbols uses symbols from proprietary module %s.\n",
+			mod->name, owner->name);
+		return false;
+	}
+
+	if (!test_bit(TAINT_PROPRIETARY_MODULE, &mod->taints)) {
+		pr_warn("%s: module uses symbols from proprietary module %s, inheriting taint.\n",
+			mod->name, owner->name);
+		set_bit(TAINT_PROPRIETARY_MODULE, &mod->taints);
+	}
+	return true;
+}
 
 /* Resolve a symbol for this module.  I.e. if we find one, record usage. */
 static const struct kernel_symbol *resolve_symbol(struct module *mod,
@@ -1437,6 +1459,7 @@ static const struct kernel_symbol *resolve_symbol(struct module *mod,
 	struct module *owner;
 	const struct kernel_symbol *sym;
 	const s32 *crc;
+	enum mod_license license;
 	int err;
 
 	/*
@@ -1446,11 +1469,19 @@ static const struct kernel_symbol *resolve_symbol(struct module *mod,
 	 */
 	sched_annotate_sleep();
 	mutex_lock(&module_mutex);
-	sym = find_symbol(name, &owner, &crc,
+	sym = find_symbol(name, &owner, &crc, &license,
 			  !(mod->taints & (1 << TAINT_PROPRIETARY_MODULE)), true);
 	if (!sym)
 		goto unlock;
 
+	if (license == GPL_ONLY)
+		mod->using_gplonly_symbols = true;
+
+	if (!inherit_taint(mod, owner)) {
+		sym = NULL;
+		goto getname;
+	}
+
 	if (!check_version(info, name, mod, crc)) {
 		sym = ERR_PTR(-EINVAL);
 		goto getname;
@@ -1507,24 +1538,44 @@ static inline bool sect_empty(const Elf_Shdr *sect)
 }
 
 struct module_sect_attr {
-	struct module_attribute mattr;
-	char *name;
+	struct bin_attribute battr;
 	unsigned long address;
 };
 
 struct module_sect_attrs {
 	struct attribute_group grp;
 	unsigned int nsections;
-	struct module_sect_attr attrs[0];
+	struct module_sect_attr attrs[];
 };
 
-static ssize_t module_sect_show(struct module_attribute *mattr,
-				struct module_kobject *mk, char *buf)
+#define MODULE_SECT_READ_SIZE (3 /* "0x", "\n" */ + (BITS_PER_LONG / 4))
+static ssize_t module_sect_read(struct file *file, struct kobject *kobj,
+				struct bin_attribute *battr,
+				char *buf, loff_t pos, size_t count)
 {
 	struct module_sect_attr *sattr =
-		container_of(mattr, struct module_sect_attr, mattr);
-	return sprintf(buf, "0x%px\n", kptr_restrict < 2 ?
-		       (void *)sattr->address : NULL);
+		container_of(battr, struct module_sect_attr, battr);
+	char bounce[MODULE_SECT_READ_SIZE + 1];
+	size_t wrote;
+
+	if (pos != 0)
+		return -EINVAL;
+
+	/*
+	 * Since we're a binary read handler, we must account for the
+	 * trailing NUL byte that sprintf will write: if "buf" is
+	 * too small to hold the NUL, or the NUL is exactly the last
+	 * byte, the read will look like it got truncated by one byte.
+	 * Since there is no way to ask sprintf nicely to not write
+	 * the NUL, we have to use a bounce buffer.
+	 */
+	wrote = scnprintf(bounce, sizeof(bounce), "0x%px\n",
+			 kallsyms_show_value(file->f_cred)
+				? (void *)sattr->address : NULL);
+	count = min(count, wrote);
+	memcpy(buf, bounce, count);
+
+	return count;
 }
 
 static void free_sect_attrs(struct module_sect_attrs *sect_attrs)
@@ -1532,7 +1583,7 @@ static void free_sect_attrs(struct module_sect_attrs *sect_attrs)
 	unsigned int section;
 
 	for (section = 0; section < sect_attrs->nsections; section++)
-		kfree(sect_attrs->attrs[section].name);
+		kfree(sect_attrs->attrs[section].battr.attr.name);
 	kfree(sect_attrs);
 }
 
@@ -1541,42 +1592,41 @@ static void add_sect_attrs(struct module *mod, const struct load_info *info)
 	unsigned int nloaded = 0, i, size[2];
 	struct module_sect_attrs *sect_attrs;
 	struct module_sect_attr *sattr;
-	struct attribute **gattr;
+	struct bin_attribute **gattr;
 
 	/* Count loaded sections and allocate structures */
 	for (i = 0; i < info->hdr->e_shnum; i++)
 		if (!sect_empty(&info->sechdrs[i]))
 			nloaded++;
 	size[0] = ALIGN(struct_size(sect_attrs, attrs, nloaded),
-			sizeof(sect_attrs->grp.attrs[0]));
-	size[1] = (nloaded + 1) * sizeof(sect_attrs->grp.attrs[0]);
+			sizeof(sect_attrs->grp.bin_attrs[0]));
+	size[1] = (nloaded + 1) * sizeof(sect_attrs->grp.bin_attrs[0]);
 	sect_attrs = kzalloc(size[0] + size[1], GFP_KERNEL);
 	if (sect_attrs == NULL)
 		return;
 
 	/* Setup section attributes. */
 	sect_attrs->grp.name = "sections";
-	sect_attrs->grp.attrs = (void *)sect_attrs + size[0];
+	sect_attrs->grp.bin_attrs = (void *)sect_attrs + size[0];
 
 	sect_attrs->nsections = 0;
 	sattr = &sect_attrs->attrs[0];
-	gattr = &sect_attrs->grp.attrs[0];
+	gattr = &sect_attrs->grp.bin_attrs[0];
 	for (i = 0; i < info->hdr->e_shnum; i++) {
 		Elf_Shdr *sec = &info->sechdrs[i];
 		if (sect_empty(sec))
 			continue;
+		sysfs_bin_attr_init(&sattr->battr);
 		sattr->address = sec->sh_addr;
-		sattr->name = kstrdup(info->secstrings + sec->sh_name,
-					GFP_KERNEL);
-		if (sattr->name == NULL)
+		sattr->battr.attr.name =
+			kstrdup(info->secstrings + sec->sh_name, GFP_KERNEL);
+		if (sattr->battr.attr.name == NULL)
 			goto out;
 		sect_attrs->nsections++;
-		sysfs_attr_init(&sattr->mattr.attr);
-		sattr->mattr.show = module_sect_show;
-		sattr->mattr.store = NULL;
-		sattr->mattr.attr.name = sattr->name;
-		sattr->mattr.attr.mode = S_IRUSR;
-		*(gattr++) = &(sattr++)->mattr.attr;
+		sattr->battr.read = module_sect_read;
+		sattr->battr.size = MODULE_SECT_READ_SIZE;
+		sattr->battr.attr.mode = 0400;
+		*(gattr++) = &(sattr++)->battr;
 	}
 	*gattr = NULL;
 
@@ -1608,7 +1658,7 @@ static void remove_sect_attrs(struct module *mod)
 struct module_notes_attrs {
 	struct kobject *dir;
 	unsigned int notes;
-	struct bin_attribute attrs[0];
+	struct bin_attribute attrs[];
 };
 
 static ssize_t module_notes_read(struct file *filp, struct kobject *kobj,
@@ -1666,7 +1716,7 @@ static void add_notes_attrs(struct module *mod, const struct load_info *info)
 			continue;
 		if (info->sechdrs[i].sh_type == SHT_NOTE) {
 			sysfs_bin_attr_init(nattr);
-			nattr->attr.name = mod->sect_attrs->attrs[loaded].name;
+			nattr->attr.name = mod->sect_attrs->attrs[loaded].battr.attr.name;
 			nattr->attr.mode = S_IRUGO;
 			nattr->size = info->sechdrs[i].sh_size;
 			nattr->private = (void *) info->sechdrs[i].sh_addr;
@@ -1943,7 +1993,6 @@ static void mod_sysfs_teardown(struct module *mod)
 	mod_sysfs_fini(mod);
 }
 
-#ifdef CONFIG_ARCH_HAS_STRICT_MODULE_RWX
 /*
  * LKM RO/NX protection: protect module's text/ro-data
  * from modification and any data from execution.
@@ -1957,6 +2006,14 @@ static void mod_sysfs_teardown(struct module *mod)
  *
  * These values are always page-aligned (as is base)
  */
+
+/*
+ * Since some arches are moving towards PAGE_KERNEL module allocations instead
+ * of PAGE_KERNEL_EXEC, keep frob_text() and module_enable_x() outside of the
+ * CONFIG_STRICT_MODULE_RWX block below because they are needed regardless of
+ * whether we are strict.
+ */
+#ifdef CONFIG_ARCH_HAS_STRICT_MODULE_RWX
 static void frob_text(const struct module_layout *layout,
 		      int (*set_memory)(unsigned long start, int num_pages))
 {
@@ -1966,6 +2023,15 @@ static void frob_text(const struct module_layout *layout,
 		   layout->text_size >> PAGE_SHIFT);
 }
 
+static void module_enable_x(const struct module *mod)
+{
+	frob_text(&mod->core_layout, set_memory_x);
+	frob_text(&mod->init_layout, set_memory_x);
+}
+#else /* !CONFIG_ARCH_HAS_STRICT_MODULE_RWX */
+static void module_enable_x(const struct module *mod) { }
+#endif /* CONFIG_ARCH_HAS_STRICT_MODULE_RWX */
+
 #ifdef CONFIG_STRICT_MODULE_RWX
 static void frob_rodata(const struct module_layout *layout,
 			int (*set_memory)(unsigned long start, int num_pages))
@@ -1997,20 +2063,7 @@ static void frob_writable_data(const struct module_layout *layout,
 		   (layout->size - layout->ro_after_init_size) >> PAGE_SHIFT);
 }
 
-/* livepatching wants to disable read-only so it can frob module. */
-void module_disable_ro(const struct module *mod)
-{
-	if (!rodata_enabled)
-		return;
-
-	frob_text(&mod->core_layout, set_memory_rw);
-	frob_rodata(&mod->core_layout, set_memory_rw);
-	frob_ro_after_init(&mod->core_layout, set_memory_rw);
-	frob_text(&mod->init_layout, set_memory_rw);
-	frob_rodata(&mod->init_layout, set_memory_rw);
-}
-
-void module_enable_ro(const struct module *mod, bool after_init)
+static void module_enable_ro(const struct module *mod, bool after_init)
 {
 	if (!rodata_enabled)
 		return;
@@ -2036,19 +2089,29 @@ static void module_enable_nx(const struct module *mod)
 	frob_writable_data(&mod->init_layout, set_memory_nx);
 }
 
+static int module_enforce_rwx_sections(Elf_Ehdr *hdr, Elf_Shdr *sechdrs,
+				       char *secstrings, struct module *mod)
+{
+	const unsigned long shf_wx = SHF_WRITE|SHF_EXECINSTR;
+	int i;
+
+	for (i = 0; i < hdr->e_shnum; i++) {
+		if ((sechdrs[i].sh_flags & shf_wx) == shf_wx)
+			return -ENOEXEC;
+	}
+
+	return 0;
+}
+
 #else /* !CONFIG_STRICT_MODULE_RWX */
 static void module_enable_nx(const struct module *mod) { }
-#endif /*  CONFIG_STRICT_MODULE_RWX */
-static void module_enable_x(const struct module *mod)
+static void module_enable_ro(const struct module *mod, bool after_init) {}
+static int module_enforce_rwx_sections(Elf_Ehdr *hdr, Elf_Shdr *sechdrs,
+				       char *secstrings, struct module *mod)
 {
-	frob_text(&mod->core_layout, set_memory_x);
-	frob_text(&mod->init_layout, set_memory_x);
+	return 0;
 }
-#else /* !CONFIG_ARCH_HAS_STRICT_MODULE_RWX */
-static void module_enable_nx(const struct module *mod) { }
-static void module_enable_x(const struct module *mod) { }
-#endif /* CONFIG_ARCH_HAS_STRICT_MODULE_RWX */
-
+#endif /*  CONFIG_STRICT_MODULE_RWX */
 
 #ifdef CONFIG_LIVEPATCH
 /*
@@ -2201,7 +2264,7 @@ void *__symbol_get(const char *symbol)
 	const struct kernel_symbol *sym;
 
 	preempt_disable();
-	sym = find_symbol(symbol, &owner, NULL, true, true);
+	sym = find_symbol(symbol, &owner, NULL, NULL, true, true);
 	if (sym && strong_try_module_get(owner))
 		sym = NULL;
 	preempt_enable();
@@ -2237,7 +2300,7 @@ static int verify_exported_symbols(struct module *mod)
 	for (i = 0; i < ARRAY_SIZE(arr); i++) {
 		for (s = arr[i].sym; s < arr[i].sym + arr[i].num; s++) {
 			if (find_symbol(kernel_symbol_name(s), &owner, NULL,
-					true, false)) {
+					NULL, true, false)) {
 				pr_err("%s: exports duplicate symbol %s"
 				       " (owned by %s)\n",
 				       mod->name, kernel_symbol_name(s),
@@ -2334,11 +2397,13 @@ static int apply_relocations(struct module *mod, const struct load_info *info)
 		if (!(info->sechdrs[infosec].sh_flags & SHF_ALLOC))
 			continue;
 
-		/* Livepatch relocation sections are applied by livepatch */
 		if (info->sechdrs[i].sh_flags & SHF_RELA_LIVEPATCH)
-			continue;
-
-		if (info->sechdrs[i].sh_type == SHT_REL)
+			err = klp_apply_section_relocs(mod, info->sechdrs,
+						       info->secstrings,
+						       info->strtab,
+						       info->index.sym, i,
+						       NULL);
+		else if (info->sechdrs[i].sh_type == SHT_REL)
 			err = apply_relocate(info->sechdrs, info->strtab,
 					     info->index.sym, i, mod);
 		else if (info->sechdrs[i].sh_type == SHT_RELA)
@@ -2400,7 +2465,7 @@ static void layout_sections(struct module *mod, struct load_info *info)
 			if ((s->sh_flags & masks[m][0]) != masks[m][0]
 			    || (s->sh_flags & masks[m][1])
 			    || s->sh_entsize != ~0UL
-			    || strstarts(sname, ".init"))
+			    || module_init_section(sname))
 				continue;
 			s->sh_entsize = get_offset(mod, &mod->core_layout.size, s, i);
 			pr_debug("\t%s\n", sname);
@@ -2433,7 +2498,7 @@ static void layout_sections(struct module *mod, struct load_info *info)
 			if ((s->sh_flags & masks[m][0]) != masks[m][0]
 			    || (s->sh_flags & masks[m][1])
 			    || s->sh_entsize != ~0UL
-			    || !strstarts(sname, ".init"))
+			    || !module_init_section(sname))
 				continue;
 			s->sh_entsize = (get_offset(mod, &mod->init_layout.size, s, i)
 					 | INIT_OFFSET_MASK);
@@ -2765,7 +2830,14 @@ static void dynamic_debug_remove(struct module *mod, struct _ddebug *debug)
 
 void * __weak module_alloc(unsigned long size)
 {
-	return vmalloc_exec(size);
+	return __vmalloc_node_range(size, 1, VMALLOC_START, VMALLOC_END,
+			GFP_KERNEL, PAGE_KERNEL_EXEC, VM_FLUSH_RESET_PERMS,
+			NUMA_NO_NODE, __builtin_return_address(0));
+}
+
+bool __weak module_init_section(const char *name)
+{
+	return strstarts(name, ".init");
 }
 
 bool __weak module_exit_section(const char *name)
@@ -2946,8 +3018,7 @@ static int copy_module_from_user(const void __user *umod, unsigned long len,
 		return err;
 
 	/* Suck in entire file: we'll want most of it. */
-	info->hdr = __vmalloc(info->len,
-			GFP_KERNEL | __GFP_NOWARN, PAGE_KERNEL);
+	info->hdr = __vmalloc(info->len, GFP_KERNEL | __GFP_NOWARN);
 	if (!info->hdr)
 		return -ENOMEM;
 
@@ -3150,6 +3221,9 @@ static int find_module_sections(struct module *mod, struct load_info *info)
 	}
 #endif
 
+	mod->noinstr_text_start = section_objs(info, ".noinstr.text", 1,
+						&mod->noinstr_text_size);
+
 #ifdef CONFIG_TRACEPOINTS
 	mod->tracepoints_ptrs = section_objs(info, "__tracepoints_ptrs",
 					     sizeof(*mod->tracepoints_ptrs),
@@ -3194,13 +3268,20 @@ static int find_module_sections(struct module *mod, struct load_info *info)
 					    sizeof(*mod->ei_funcs),
 					    &mod->num_ei_funcs);
 #endif
+#ifdef CONFIG_KPROBES
+	mod->kprobes_text_start = section_objs(info, ".kprobes.text", 1,
+						&mod->kprobes_text_size);
+	mod->kprobe_blacklist = section_objs(info, "_kprobe_blacklist",
+						sizeof(unsigned long),
+						&mod->num_kprobe_blacklist);
+#endif
 	mod->extable = section_objs(info, "__ex_table",
 				    sizeof(*mod->extable), &mod->num_exentries);
 
 	if (section_addr(info, "__obsparm"))
 		pr_warn("%s: Ignoring obsolete parameters\n", mod->name);
 
-	info->debug = section_objs(info, "__verbose",
+	info->debug = section_objs(info, "__dyndbg",
 				   sizeof(*info->debug), &info->num_debug);
 
 	return 0;
@@ -3312,12 +3393,6 @@ static int check_module_license_and_versions(struct module *mod)
 
 static void flush_module_icache(const struct module *mod)
 {
-	mm_segment_t old_fs;
-
-	/* flush the icache in correct context */
-	old_fs = get_fs();
-	set_fs(KERNEL_DS);
-
 	/*
 	 * Flush the instruction cache, since we've played with text.
 	 * Do it before processing of module parameters, so the module
@@ -3329,8 +3404,6 @@ static void flush_module_icache(const struct module *mod)
 				   + mod->init_layout.size);
 	flush_icache_range((unsigned long)mod->core_layout.base,
 			   (unsigned long)mod->core_layout.base + mod->core_layout.size);
-
-	set_fs(old_fs);
 }
 
 int __weak module_frob_arch_sections(Elf_Ehdr *hdr,
@@ -3378,6 +3451,11 @@ static struct module *layout_and_allocate(struct load_info *info, int flags)
 	if (err < 0)
 		return ERR_PTR(err);
 
+	err = module_enforce_rwx_sections(info->hdr, info->sechdrs,
+					  info->secstrings, info->mod);
+	if (err < 0)
+		return ERR_PTR(err);
+
 	/* We will do a special allocation for per-cpu sections later. */
 	info->sechdrs[info->index.pcpu].sh_flags &= ~(unsigned long)SHF_ALLOC;
 
@@ -4348,13 +4426,14 @@ static int modules_open(struct inode *inode, struct file *file)
 
 	if (!err) {
 		struct seq_file *m = file->private_data;
-		m->private = kallsyms_show_value() ? NULL : (void *)8ul;
+		m->private = kallsyms_show_value(file->f_cred) ? NULL : (void *)8ul;
 	}
 
 	return err;
 }
 
 static const struct proc_ops modules_proc_ops = {
+	.proc_flags	= PROC_ENTRY_PERMANENT,
 	.proc_open	= modules_open,
 	.proc_read	= seq_read,
 	.proc_lseek	= seq_lseek,
@@ -4438,7 +4517,6 @@ struct module *__module_address(unsigned long addr)
 	}
 	return mod;
 }
-EXPORT_SYMBOL_GPL(__module_address);
 
 /*
  * is_module_text_address - is this address inside module code?
@@ -4477,7 +4555,6 @@ struct module *__module_text_address(unsigned long addr)
 	}
 	return mod;
 }
-EXPORT_SYMBOL_GPL(__module_text_address);
 
 /* Don't grab lock, we're oopsing. */
 void print_modules(void)
diff --git a/kernel/notifier.c b/kernel/notifier.c
index 63d7501ac638..84c987dfbe03 100644
--- a/kernel/notifier.c
+++ b/kernel/notifier.c
@@ -519,7 +519,6 @@ NOKPROBE_SYMBOL(notify_die);
 
 int register_die_notifier(struct notifier_block *nb)
 {
-	vmalloc_sync_all();
 	return atomic_notifier_chain_register(&die_chain, nb);
 }
 EXPORT_SYMBOL_GPL(register_die_notifier);
diff --git a/kernel/nsproxy.c b/kernel/nsproxy.c
index ed9882108cd2..12dd41b39a7f 100644
--- a/kernel/nsproxy.c
+++ b/kernel/nsproxy.c
@@ -19,6 +19,8 @@
 #include <net/net_namespace.h>
 #include <linux/ipc_namespace.h>
 #include <linux/time_namespace.h>
+#include <linux/fs_struct.h>
+#include <linux/proc_fs.h>
 #include <linux/proc_ns.h>
 #include <linux/file.h>
 #include <linux/syscalls.h>
@@ -257,37 +259,313 @@ void exit_task_namespaces(struct task_struct *p)
 	switch_task_namespaces(p, NULL);
 }
 
-SYSCALL_DEFINE2(setns, int, fd, int, nstype)
+static int check_setns_flags(unsigned long flags)
 {
-	struct task_struct *tsk = current;
-	struct nsproxy *new_nsproxy;
-	struct file *file;
-	struct ns_common *ns;
-	int err;
+	if (!flags || (flags & ~(CLONE_NEWNS | CLONE_NEWUTS | CLONE_NEWIPC |
+				 CLONE_NEWNET | CLONE_NEWTIME | CLONE_NEWUSER |
+				 CLONE_NEWPID | CLONE_NEWCGROUP)))
+		return -EINVAL;
+
+#ifndef CONFIG_USER_NS
+	if (flags & CLONE_NEWUSER)
+		return -EINVAL;
+#endif
+#ifndef CONFIG_PID_NS
+	if (flags & CLONE_NEWPID)
+		return -EINVAL;
+#endif
+#ifndef CONFIG_UTS_NS
+	if (flags & CLONE_NEWUTS)
+		return -EINVAL;
+#endif
+#ifndef CONFIG_IPC_NS
+	if (flags & CLONE_NEWIPC)
+		return -EINVAL;
+#endif
+#ifndef CONFIG_CGROUPS
+	if (flags & CLONE_NEWCGROUP)
+		return -EINVAL;
+#endif
+#ifndef CONFIG_NET_NS
+	if (flags & CLONE_NEWNET)
+		return -EINVAL;
+#endif
+#ifndef CONFIG_TIME_NS
+	if (flags & CLONE_NEWTIME)
+		return -EINVAL;
+#endif
 
-	file = proc_ns_fget(fd);
-	if (IS_ERR(file))
-		return PTR_ERR(file);
+	return 0;
+}
 
-	err = -EINVAL;
-	ns = get_proc_ns(file_inode(file));
-	if (nstype && (ns->ops->type != nstype))
-		goto out;
+static void put_nsset(struct nsset *nsset)
+{
+	unsigned flags = nsset->flags;
+
+	if (flags & CLONE_NEWUSER)
+		put_cred(nsset_cred(nsset));
+	/*
+	 * We only created a temporary copy if we attached to more than just
+	 * the mount namespace.
+	 */
+	if (nsset->fs && (flags & CLONE_NEWNS) && (flags & ~CLONE_NEWNS))
+		free_fs_struct(nsset->fs);
+	if (nsset->nsproxy)
+		free_nsproxy(nsset->nsproxy);
+}
+
+static int prepare_nsset(unsigned flags, struct nsset *nsset)
+{
+	struct task_struct *me = current;
 
-	new_nsproxy = create_new_namespaces(0, tsk, current_user_ns(), tsk->fs);
-	if (IS_ERR(new_nsproxy)) {
-		err = PTR_ERR(new_nsproxy);
+	nsset->nsproxy = create_new_namespaces(0, me, current_user_ns(), me->fs);
+	if (IS_ERR(nsset->nsproxy))
+		return PTR_ERR(nsset->nsproxy);
+
+	if (flags & CLONE_NEWUSER)
+		nsset->cred = prepare_creds();
+	else
+		nsset->cred = current_cred();
+	if (!nsset->cred)
 		goto out;
+
+	/* Only create a temporary copy of fs_struct if we really need to. */
+	if (flags == CLONE_NEWNS) {
+		nsset->fs = me->fs;
+	} else if (flags & CLONE_NEWNS) {
+		nsset->fs = copy_fs_struct(me->fs);
+		if (!nsset->fs)
+			goto out;
 	}
 
-	err = ns->ops->install(new_nsproxy, ns);
-	if (err) {
-		free_nsproxy(new_nsproxy);
-		goto out;
+	nsset->flags = flags;
+	return 0;
+
+out:
+	put_nsset(nsset);
+	return -ENOMEM;
+}
+
+static inline int validate_ns(struct nsset *nsset, struct ns_common *ns)
+{
+	return ns->ops->install(nsset, ns);
+}
+
+/*
+ * This is the inverse operation to unshare().
+ * Ordering is equivalent to the standard ordering used everywhere else
+ * during unshare and process creation. The switch to the new set of
+ * namespaces occurs at the point of no return after installation of
+ * all requested namespaces was successful in commit_nsset().
+ */
+static int validate_nsset(struct nsset *nsset, struct pid *pid)
+{
+	int ret = 0;
+	unsigned flags = nsset->flags;
+	struct user_namespace *user_ns = NULL;
+	struct pid_namespace *pid_ns = NULL;
+	struct nsproxy *nsp;
+	struct task_struct *tsk;
+
+	/* Take a "snapshot" of the target task's namespaces. */
+	rcu_read_lock();
+	tsk = pid_task(pid, PIDTYPE_PID);
+	if (!tsk) {
+		rcu_read_unlock();
+		return -ESRCH;
 	}
-	switch_task_namespaces(tsk, new_nsproxy);
 
-	perf_event_namespaces(tsk);
+	if (!ptrace_may_access(tsk, PTRACE_MODE_READ_REALCREDS)) {
+		rcu_read_unlock();
+		return -EPERM;
+	}
+
+	task_lock(tsk);
+	nsp = tsk->nsproxy;
+	if (nsp)
+		get_nsproxy(nsp);
+	task_unlock(tsk);
+	if (!nsp) {
+		rcu_read_unlock();
+		return -ESRCH;
+	}
+
+#ifdef CONFIG_PID_NS
+	if (flags & CLONE_NEWPID) {
+		pid_ns = task_active_pid_ns(tsk);
+		if (unlikely(!pid_ns)) {
+			rcu_read_unlock();
+			ret = -ESRCH;
+			goto out;
+		}
+		get_pid_ns(pid_ns);
+	}
+#endif
+
+#ifdef CONFIG_USER_NS
+	if (flags & CLONE_NEWUSER)
+		user_ns = get_user_ns(__task_cred(tsk)->user_ns);
+#endif
+	rcu_read_unlock();
+
+	/*
+	 * Install requested namespaces. The caller will have
+	 * verified earlier that the requested namespaces are
+	 * supported on this kernel. We don't report errors here
+	 * if a namespace is requested that isn't supported.
+	 */
+#ifdef CONFIG_USER_NS
+	if (flags & CLONE_NEWUSER) {
+		ret = validate_ns(nsset, &user_ns->ns);
+		if (ret)
+			goto out;
+	}
+#endif
+
+	if (flags & CLONE_NEWNS) {
+		ret = validate_ns(nsset, from_mnt_ns(nsp->mnt_ns));
+		if (ret)
+			goto out;
+	}
+
+#ifdef CONFIG_UTS_NS
+	if (flags & CLONE_NEWUTS) {
+		ret = validate_ns(nsset, &nsp->uts_ns->ns);
+		if (ret)
+			goto out;
+	}
+#endif
+
+#ifdef CONFIG_IPC_NS
+	if (flags & CLONE_NEWIPC) {
+		ret = validate_ns(nsset, &nsp->ipc_ns->ns);
+		if (ret)
+			goto out;
+	}
+#endif
+
+#ifdef CONFIG_PID_NS
+	if (flags & CLONE_NEWPID) {
+		ret = validate_ns(nsset, &pid_ns->ns);
+		if (ret)
+			goto out;
+	}
+#endif
+
+#ifdef CONFIG_CGROUPS
+	if (flags & CLONE_NEWCGROUP) {
+		ret = validate_ns(nsset, &nsp->cgroup_ns->ns);
+		if (ret)
+			goto out;
+	}
+#endif
+
+#ifdef CONFIG_NET_NS
+	if (flags & CLONE_NEWNET) {
+		ret = validate_ns(nsset, &nsp->net_ns->ns);
+		if (ret)
+			goto out;
+	}
+#endif
+
+#ifdef CONFIG_TIME_NS
+	if (flags & CLONE_NEWTIME) {
+		ret = validate_ns(nsset, &nsp->time_ns->ns);
+		if (ret)
+			goto out;
+	}
+#endif
+
+out:
+	if (pid_ns)
+		put_pid_ns(pid_ns);
+	if (nsp)
+		put_nsproxy(nsp);
+	put_user_ns(user_ns);
+
+	return ret;
+}
+
+/*
+ * This is the point of no return. There are just a few namespaces
+ * that do some actual work here and it's sufficiently minimal that
+ * a separate ns_common operation seems unnecessary for now.
+ * Unshare is doing the same thing. If we'll end up needing to do
+ * more in a given namespace or a helper here is ultimately not
+ * exported anymore a simple commit handler for each namespace
+ * should be added to ns_common.
+ */
+static void commit_nsset(struct nsset *nsset)
+{
+	unsigned flags = nsset->flags;
+	struct task_struct *me = current;
+
+#ifdef CONFIG_USER_NS
+	if (flags & CLONE_NEWUSER) {
+		/* transfer ownership */
+		commit_creds(nsset_cred(nsset));
+		nsset->cred = NULL;
+	}
+#endif
+
+	/* We only need to commit if we have used a temporary fs_struct. */
+	if ((flags & CLONE_NEWNS) && (flags & ~CLONE_NEWNS)) {
+		set_fs_root(me->fs, &nsset->fs->root);
+		set_fs_pwd(me->fs, &nsset->fs->pwd);
+	}
+
+#ifdef CONFIG_IPC_NS
+	if (flags & CLONE_NEWIPC)
+		exit_sem(me);
+#endif
+
+#ifdef CONFIG_TIME_NS
+	if (flags & CLONE_NEWTIME)
+		timens_commit(me, nsset->nsproxy->time_ns);
+#endif
+
+	/* transfer ownership */
+	switch_task_namespaces(me, nsset->nsproxy);
+	nsset->nsproxy = NULL;
+}
+
+SYSCALL_DEFINE2(setns, int, fd, int, flags)
+{
+	struct file *file;
+	struct ns_common *ns = NULL;
+	struct nsset nsset = {};
+	int err = 0;
+
+	file = fget(fd);
+	if (!file)
+		return -EBADF;
+
+	if (proc_ns_file(file)) {
+		ns = get_proc_ns(file_inode(file));
+		if (flags && (ns->ops->type != flags))
+			err = -EINVAL;
+		flags = ns->ops->type;
+	} else if (!IS_ERR(pidfd_pid(file))) {
+		err = check_setns_flags(flags);
+	} else {
+		err = -EINVAL;
+	}
+	if (err)
+		goto out;
+
+	err = prepare_nsset(flags, &nsset);
+	if (err)
+		goto out;
+
+	if (proc_ns_file(file))
+		err = validate_ns(&nsset, ns);
+	else
+		err = validate_nsset(&nsset, file->private_data);
+	if (!err) {
+		commit_nsset(&nsset);
+		perf_event_namespaces(current);
+	}
+	put_nsset(&nsset);
 out:
 	fput(file);
 	return err;
diff --git a/kernel/padata.c b/kernel/padata.c
index 72777c10bb9c..16cb894dc272 100644
--- a/kernel/padata.c
+++ b/kernel/padata.c
@@ -7,6 +7,9 @@
  * Copyright (C) 2008, 2009 secunet Security Networks AG
  * Copyright (C) 2008, 2009 Steffen Klassert <steffen.klassert@secunet.com>
  *
+ * Copyright (c) 2020 Oracle and/or its affiliates.
+ * Author: Daniel Jordan <daniel.m.jordan@oracle.com>
+ *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms and conditions of the GNU General Public License,
  * version 2, as published by the Free Software Foundation.
@@ -21,6 +24,7 @@
  * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
  */
 
+#include <linux/completion.h>
 #include <linux/export.h>
 #include <linux/cpumask.h>
 #include <linux/err.h>
@@ -31,11 +35,30 @@
 #include <linux/slab.h>
 #include <linux/sysfs.h>
 #include <linux/rcupdate.h>
-#include <linux/module.h>
 
-#define MAX_OBJ_NUM 1000
+#define	PADATA_WORK_ONSTACK	1	/* Work's memory is on stack */
+
+struct padata_work {
+	struct work_struct	pw_work;
+	struct list_head	pw_list;  /* padata_free_works linkage */
+	void			*pw_data;
+};
+
+static DEFINE_SPINLOCK(padata_works_lock);
+static struct padata_work *padata_works;
+static LIST_HEAD(padata_free_works);
+
+struct padata_mt_job_state {
+	spinlock_t		lock;
+	struct completion	completion;
+	struct padata_mt_job	*job;
+	int			nworks;
+	int			nworks_fini;
+	unsigned long		chunk_size;
+};
 
 static void padata_free_pd(struct parallel_data *pd);
+static void __init padata_mt_helper(struct work_struct *work);
 
 static int padata_index_to_cpu(struct parallel_data *pd, int cpu_index)
 {
@@ -59,30 +82,82 @@ static int padata_cpu_hash(struct parallel_data *pd, unsigned int seq_nr)
 	return padata_index_to_cpu(pd, cpu_index);
 }
 
-static void padata_parallel_worker(struct work_struct *parallel_work)
+static struct padata_work *padata_work_alloc(void)
 {
-	struct padata_parallel_queue *pqueue;
-	LIST_HEAD(local_list);
+	struct padata_work *pw;
 
-	local_bh_disable();
-	pqueue = container_of(parallel_work,
-			      struct padata_parallel_queue, work);
+	lockdep_assert_held(&padata_works_lock);
 
-	spin_lock(&pqueue->parallel.lock);
-	list_replace_init(&pqueue->parallel.list, &local_list);
-	spin_unlock(&pqueue->parallel.lock);
+	if (list_empty(&padata_free_works))
+		return NULL;	/* No more work items allowed to be queued. */
 
-	while (!list_empty(&local_list)) {
-		struct padata_priv *padata;
+	pw = list_first_entry(&padata_free_works, struct padata_work, pw_list);
+	list_del(&pw->pw_list);
+	return pw;
+}
 
-		padata = list_entry(local_list.next,
-				    struct padata_priv, list);
+static void padata_work_init(struct padata_work *pw, work_func_t work_fn,
+			     void *data, int flags)
+{
+	if (flags & PADATA_WORK_ONSTACK)
+		INIT_WORK_ONSTACK(&pw->pw_work, work_fn);
+	else
+		INIT_WORK(&pw->pw_work, work_fn);
+	pw->pw_data = data;
+}
 
-		list_del_init(&padata->list);
+static int __init padata_work_alloc_mt(int nworks, void *data,
+				       struct list_head *head)
+{
+	int i;
 
-		padata->parallel(padata);
+	spin_lock(&padata_works_lock);
+	/* Start at 1 because the current task participates in the job. */
+	for (i = 1; i < nworks; ++i) {
+		struct padata_work *pw = padata_work_alloc();
+
+		if (!pw)
+			break;
+		padata_work_init(pw, padata_mt_helper, data, 0);
+		list_add(&pw->pw_list, head);
 	}
+	spin_unlock(&padata_works_lock);
+
+	return i;
+}
+
+static void padata_work_free(struct padata_work *pw)
+{
+	lockdep_assert_held(&padata_works_lock);
+	list_add(&pw->pw_list, &padata_free_works);
+}
+
+static void __init padata_works_free(struct list_head *works)
+{
+	struct padata_work *cur, *next;
+
+	if (list_empty(works))
+		return;
 
+	spin_lock(&padata_works_lock);
+	list_for_each_entry_safe(cur, next, works, pw_list) {
+		list_del(&cur->pw_list);
+		padata_work_free(cur);
+	}
+	spin_unlock(&padata_works_lock);
+}
+
+static void padata_parallel_worker(struct work_struct *parallel_work)
+{
+	struct padata_work *pw = container_of(parallel_work, struct padata_work,
+					      pw_work);
+	struct padata_priv *padata = pw->pw_data;
+
+	local_bh_disable();
+	padata->parallel(padata);
+	spin_lock(&padata_works_lock);
+	padata_work_free(pw);
+	spin_unlock(&padata_works_lock);
 	local_bh_enable();
 }
 
@@ -106,9 +181,9 @@ int padata_do_parallel(struct padata_shell *ps,
 		       struct padata_priv *padata, int *cb_cpu)
 {
 	struct padata_instance *pinst = ps->pinst;
-	int i, cpu, cpu_index, target_cpu, err;
-	struct padata_parallel_queue *queue;
+	int i, cpu, cpu_index, err;
 	struct parallel_data *pd;
+	struct padata_work *pw;
 
 	rcu_read_lock_bh();
 
@@ -136,25 +211,25 @@ int padata_do_parallel(struct padata_shell *ps,
 	if ((pinst->flags & PADATA_RESET))
 		goto out;
 
-	if (atomic_read(&pd->refcnt) >= MAX_OBJ_NUM)
-		goto out;
-
-	err = 0;
 	atomic_inc(&pd->refcnt);
 	padata->pd = pd;
 	padata->cb_cpu = *cb_cpu;
 
-	padata->seq_nr = atomic_inc_return(&pd->seq_nr);
-	target_cpu = padata_cpu_hash(pd, padata->seq_nr);
-	padata->cpu = target_cpu;
-	queue = per_cpu_ptr(pd->pqueue, target_cpu);
-
-	spin_lock(&queue->parallel.lock);
-	list_add_tail(&padata->list, &queue->parallel.list);
-	spin_unlock(&queue->parallel.lock);
+	rcu_read_unlock_bh();
 
-	queue_work(pinst->parallel_wq, &queue->work);
+	spin_lock(&padata_works_lock);
+	padata->seq_nr = ++pd->seq_nr;
+	pw = padata_work_alloc();
+	spin_unlock(&padata_works_lock);
+	if (pw) {
+		padata_work_init(pw, padata_parallel_worker, padata, 0);
+		queue_work(pinst->parallel_wq, &pw->pw_work);
+	} else {
+		/* Maximum works limit exceeded, run in the current task. */
+		padata->parallel(padata);
+	}
 
+	return 0;
 out:
 	rcu_read_unlock_bh();
 
@@ -175,13 +250,11 @@ EXPORT_SYMBOL(padata_do_parallel);
 static struct padata_priv *padata_find_next(struct parallel_data *pd,
 					    bool remove_object)
 {
-	struct padata_parallel_queue *next_queue;
 	struct padata_priv *padata;
 	struct padata_list *reorder;
 	int cpu = pd->cpu;
 
-	next_queue = per_cpu_ptr(pd->pqueue, cpu);
-	reorder = &next_queue->reorder;
+	reorder = per_cpu_ptr(pd->reorder_list, cpu);
 
 	spin_lock(&reorder->lock);
 	if (list_empty(&reorder->list)) {
@@ -216,7 +289,7 @@ static void padata_reorder(struct parallel_data *pd)
 	int cb_cpu;
 	struct padata_priv *padata;
 	struct padata_serial_queue *squeue;
-	struct padata_parallel_queue *next_queue;
+	struct padata_list *reorder;
 
 	/*
 	 * We need to ensure that only one cpu can work on dequeueing of
@@ -260,13 +333,12 @@ static void padata_reorder(struct parallel_data *pd)
 	 *
 	 * Ensure reorder queue is read after pd->lock is dropped so we see
 	 * new objects from another task in padata_do_serial.  Pairs with
-	 * smp_mb__after_atomic in padata_do_serial.
+	 * smp_mb in padata_do_serial.
 	 */
 	smp_mb();
 
-	next_queue = per_cpu_ptr(pd->pqueue, pd->cpu);
-	if (!list_empty(&next_queue->reorder.list) &&
-	    padata_find_next(pd, false))
+	reorder = per_cpu_ptr(pd->reorder_list, pd->cpu);
+	if (!list_empty(&reorder->list) && padata_find_next(pd, false))
 		queue_work(pinst->serial_wq, &pd->reorder_work);
 }
 
@@ -325,24 +397,24 @@ static void padata_serial_worker(struct work_struct *serial_work)
 void padata_do_serial(struct padata_priv *padata)
 {
 	struct parallel_data *pd = padata->pd;
-	struct padata_parallel_queue *pqueue = per_cpu_ptr(pd->pqueue,
-							   padata->cpu);
+	int hashed_cpu = padata_cpu_hash(pd, padata->seq_nr);
+	struct padata_list *reorder = per_cpu_ptr(pd->reorder_list, hashed_cpu);
 	struct padata_priv *cur;
 
-	spin_lock(&pqueue->reorder.lock);
+	spin_lock(&reorder->lock);
 	/* Sort in ascending order of sequence number. */
-	list_for_each_entry_reverse(cur, &pqueue->reorder.list, list)
+	list_for_each_entry_reverse(cur, &reorder->list, list)
 		if (cur->seq_nr < padata->seq_nr)
 			break;
 	list_add(&padata->list, &cur->list);
-	spin_unlock(&pqueue->reorder.lock);
+	spin_unlock(&reorder->lock);
 
 	/*
 	 * Ensure the addition to the reorder list is ordered correctly
 	 * with the trylock of pd->lock in padata_reorder.  Pairs with smp_mb
 	 * in padata_reorder.
 	 */
-	smp_mb__after_atomic();
+	smp_mb();
 
 	padata_reorder(pd);
 }
@@ -365,26 +437,96 @@ static int padata_setup_cpumasks(struct padata_instance *pinst)
 	return err;
 }
 
-static int pd_setup_cpumasks(struct parallel_data *pd,
-			     const struct cpumask *pcpumask,
-			     const struct cpumask *cbcpumask)
+static void __init padata_mt_helper(struct work_struct *w)
 {
-	int err = -ENOMEM;
+	struct padata_work *pw = container_of(w, struct padata_work, pw_work);
+	struct padata_mt_job_state *ps = pw->pw_data;
+	struct padata_mt_job *job = ps->job;
+	bool done;
 
-	if (!alloc_cpumask_var(&pd->cpumask.pcpu, GFP_KERNEL))
-		goto out;
-	if (!alloc_cpumask_var(&pd->cpumask.cbcpu, GFP_KERNEL))
-		goto free_pcpu_mask;
+	spin_lock(&ps->lock);
 
-	cpumask_copy(pd->cpumask.pcpu, pcpumask);
-	cpumask_copy(pd->cpumask.cbcpu, cbcpumask);
+	while (job->size > 0) {
+		unsigned long start, size, end;
 
-	return 0;
+		start = job->start;
+		/* So end is chunk size aligned if enough work remains. */
+		size = roundup(start + 1, ps->chunk_size) - start;
+		size = min(size, job->size);
+		end = start + size;
 
-free_pcpu_mask:
-	free_cpumask_var(pd->cpumask.pcpu);
-out:
-	return err;
+		job->start = end;
+		job->size -= size;
+
+		spin_unlock(&ps->lock);
+		job->thread_fn(start, end, job->fn_arg);
+		spin_lock(&ps->lock);
+	}
+
+	++ps->nworks_fini;
+	done = (ps->nworks_fini == ps->nworks);
+	spin_unlock(&ps->lock);
+
+	if (done)
+		complete(&ps->completion);
+}
+
+/**
+ * padata_do_multithreaded - run a multithreaded job
+ * @job: Description of the job.
+ *
+ * See the definition of struct padata_mt_job for more details.
+ */
+void __init padata_do_multithreaded(struct padata_mt_job *job)
+{
+	/* In case threads finish at different times. */
+	static const unsigned long load_balance_factor = 4;
+	struct padata_work my_work, *pw;
+	struct padata_mt_job_state ps;
+	LIST_HEAD(works);
+	int nworks;
+
+	if (job->size == 0)
+		return;
+
+	/* Ensure at least one thread when size < min_chunk. */
+	nworks = max(job->size / job->min_chunk, 1ul);
+	nworks = min(nworks, job->max_threads);
+
+	if (nworks == 1) {
+		/* Single thread, no coordination needed, cut to the chase. */
+		job->thread_fn(job->start, job->start + job->size, job->fn_arg);
+		return;
+	}
+
+	spin_lock_init(&ps.lock);
+	init_completion(&ps.completion);
+	ps.job	       = job;
+	ps.nworks      = padata_work_alloc_mt(nworks, &ps, &works);
+	ps.nworks_fini = 0;
+
+	/*
+	 * Chunk size is the amount of work a helper does per call to the
+	 * thread function.  Load balance large jobs between threads by
+	 * increasing the number of chunks, guarantee at least the minimum
+	 * chunk size from the caller, and honor the caller's alignment.
+	 */
+	ps.chunk_size = job->size / (ps.nworks * load_balance_factor);
+	ps.chunk_size = max(ps.chunk_size, job->min_chunk);
+	ps.chunk_size = roundup(ps.chunk_size, job->align);
+
+	list_for_each_entry(pw, &works, pw_list)
+		queue_work(system_unbound_wq, &pw->pw_work);
+
+	/* Use the current thread, which saves starting a workqueue worker. */
+	padata_work_init(&my_work, padata_mt_helper, &ps, PADATA_WORK_ONSTACK);
+	padata_mt_helper(&my_work.pw_work);
+
+	/* Wait for all the helpers to finish. */
+	wait_for_completion(&ps.completion);
+
+	destroy_work_on_stack(&my_work.pw_work);
+	padata_works_free(&works);
 }
 
 static void __padata_list_init(struct padata_list *pd_list)
@@ -407,19 +549,15 @@ static void padata_init_squeues(struct parallel_data *pd)
 	}
 }
 
-/* Initialize all percpu queues used by parallel workers */
-static void padata_init_pqueues(struct parallel_data *pd)
+/* Initialize per-CPU reorder lists */
+static void padata_init_reorder_list(struct parallel_data *pd)
 {
 	int cpu;
-	struct padata_parallel_queue *pqueue;
+	struct padata_list *list;
 
 	for_each_cpu(cpu, pd->cpumask.pcpu) {
-		pqueue = per_cpu_ptr(pd->pqueue, cpu);
-
-		__padata_list_init(&pqueue->reorder);
-		__padata_list_init(&pqueue->parallel);
-		INIT_WORK(&pqueue->work, padata_parallel_worker);
-		atomic_set(&pqueue->num_obj, 0);
+		list = per_cpu_ptr(pd->reorder_list, cpu);
+		__padata_list_init(list);
 	}
 }
 
@@ -427,32 +565,33 @@ static void padata_init_pqueues(struct parallel_data *pd)
 static struct parallel_data *padata_alloc_pd(struct padata_shell *ps)
 {
 	struct padata_instance *pinst = ps->pinst;
-	const struct cpumask *cbcpumask;
-	const struct cpumask *pcpumask;
 	struct parallel_data *pd;
 
-	cbcpumask = pinst->rcpumask.cbcpu;
-	pcpumask = pinst->rcpumask.pcpu;
-
 	pd = kzalloc(sizeof(struct parallel_data), GFP_KERNEL);
 	if (!pd)
 		goto err;
 
-	pd->pqueue = alloc_percpu(struct padata_parallel_queue);
-	if (!pd->pqueue)
+	pd->reorder_list = alloc_percpu(struct padata_list);
+	if (!pd->reorder_list)
 		goto err_free_pd;
 
 	pd->squeue = alloc_percpu(struct padata_serial_queue);
 	if (!pd->squeue)
-		goto err_free_pqueue;
+		goto err_free_reorder_list;
 
 	pd->ps = ps;
-	if (pd_setup_cpumasks(pd, pcpumask, cbcpumask))
+
+	if (!alloc_cpumask_var(&pd->cpumask.pcpu, GFP_KERNEL))
 		goto err_free_squeue;
+	if (!alloc_cpumask_var(&pd->cpumask.cbcpu, GFP_KERNEL))
+		goto err_free_pcpu;
+
+	cpumask_and(pd->cpumask.pcpu, pinst->cpumask.pcpu, cpu_online_mask);
+	cpumask_and(pd->cpumask.cbcpu, pinst->cpumask.cbcpu, cpu_online_mask);
 
-	padata_init_pqueues(pd);
+	padata_init_reorder_list(pd);
 	padata_init_squeues(pd);
-	atomic_set(&pd->seq_nr, -1);
+	pd->seq_nr = -1;
 	atomic_set(&pd->refcnt, 1);
 	spin_lock_init(&pd->lock);
 	pd->cpu = cpumask_first(pd->cpumask.pcpu);
@@ -460,10 +599,12 @@ static struct parallel_data *padata_alloc_pd(struct padata_shell *ps)
 
 	return pd;
 
+err_free_pcpu:
+	free_cpumask_var(pd->cpumask.pcpu);
 err_free_squeue:
 	free_percpu(pd->squeue);
-err_free_pqueue:
-	free_percpu(pd->pqueue);
+err_free_reorder_list:
+	free_percpu(pd->reorder_list);
 err_free_pd:
 	kfree(pd);
 err:
@@ -474,7 +615,7 @@ static void padata_free_pd(struct parallel_data *pd)
 {
 	free_cpumask_var(pd->cpumask.pcpu);
 	free_cpumask_var(pd->cpumask.cbcpu);
-	free_percpu(pd->pqueue);
+	free_percpu(pd->reorder_list);
 	free_percpu(pd->squeue);
 	kfree(pd);
 }
@@ -512,16 +653,10 @@ static int padata_replace_one(struct padata_shell *ps)
 static int padata_replace(struct padata_instance *pinst)
 {
 	struct padata_shell *ps;
-	int err;
+	int err = 0;
 
 	pinst->flags |= PADATA_RESET;
 
-	cpumask_and(pinst->rcpumask.pcpu, pinst->cpumask.pcpu,
-		    cpu_online_mask);
-
-	cpumask_and(pinst->rcpumask.cbcpu, pinst->cpumask.cbcpu,
-		    cpu_online_mask);
-
 	list_for_each_entry(ps, &pinst->pslist, list) {
 		err = padata_replace_one(ps);
 		if (err)
@@ -623,43 +758,6 @@ out:
 }
 EXPORT_SYMBOL(padata_set_cpumask);
 
-/**
- * padata_start - start the parallel processing
- *
- * @pinst: padata instance to start
- *
- * Return: 0 on success or negative error code
- */
-int padata_start(struct padata_instance *pinst)
-{
-	int err = 0;
-
-	mutex_lock(&pinst->lock);
-
-	if (pinst->flags & PADATA_INVALID)
-		err = -EINVAL;
-
-	__padata_start(pinst);
-
-	mutex_unlock(&pinst->lock);
-
-	return err;
-}
-EXPORT_SYMBOL(padata_start);
-
-/**
- * padata_stop - stop the parallel processing
- *
- * @pinst: padata instance to stop
- */
-void padata_stop(struct padata_instance *pinst)
-{
-	mutex_lock(&pinst->lock);
-	__padata_stop(pinst);
-	mutex_unlock(&pinst->lock);
-}
-EXPORT_SYMBOL(padata_stop);
-
 #ifdef CONFIG_HOTPLUG_CPU
 
 static int __padata_add_cpu(struct padata_instance *pinst, int cpu)
@@ -703,7 +801,7 @@ static int padata_cpu_online(unsigned int cpu, struct hlist_node *node)
 	struct padata_instance *pinst;
 	int ret;
 
-	pinst = hlist_entry_safe(node, struct padata_instance, node);
+	pinst = hlist_entry_safe(node, struct padata_instance, cpu_online_node);
 	if (!pinst_has_cpu(pinst, cpu))
 		return 0;
 
@@ -718,7 +816,7 @@ static int padata_cpu_dead(unsigned int cpu, struct hlist_node *node)
 	struct padata_instance *pinst;
 	int ret;
 
-	pinst = hlist_entry_safe(node, struct padata_instance, node);
+	pinst = hlist_entry_safe(node, struct padata_instance, cpu_dead_node);
 	if (!pinst_has_cpu(pinst, cpu))
 		return 0;
 
@@ -734,15 +832,13 @@ static enum cpuhp_state hp_online;
 static void __padata_free(struct padata_instance *pinst)
 {
 #ifdef CONFIG_HOTPLUG_CPU
-	cpuhp_state_remove_instance_nocalls(CPUHP_PADATA_DEAD, &pinst->node);
-	cpuhp_state_remove_instance_nocalls(hp_online, &pinst->node);
+	cpuhp_state_remove_instance_nocalls(CPUHP_PADATA_DEAD,
+					    &pinst->cpu_dead_node);
+	cpuhp_state_remove_instance_nocalls(hp_online, &pinst->cpu_online_node);
 #endif
 
 	WARN_ON(!list_empty(&pinst->pslist));
 
-	padata_stop(pinst);
-	free_cpumask_var(pinst->rcpumask.cbcpu);
-	free_cpumask_var(pinst->rcpumask.pcpu);
 	free_cpumask_var(pinst->cpumask.pcpu);
 	free_cpumask_var(pinst->cpumask.cbcpu);
 	destroy_workqueue(pinst->serial_wq);
@@ -877,18 +973,12 @@ static struct kobj_type padata_attr_type = {
 };
 
 /**
- * padata_alloc - allocate and initialize a padata instance and specify
- *                cpumasks for serial and parallel workers.
- *
+ * padata_alloc - allocate and initialize a padata instance
  * @name: used to identify the instance
- * @pcpumask: cpumask that will be used for padata parallelization
- * @cbcpumask: cpumask that will be used for padata serialization
  *
  * Return: new instance on success, NULL on error
  */
-static struct padata_instance *padata_alloc(const char *name,
-					    const struct cpumask *pcpumask,
-					    const struct cpumask *cbcpumask)
+struct padata_instance *padata_alloc(const char *name)
 {
 	struct padata_instance *pinst;
 
@@ -914,44 +1004,31 @@ static struct padata_instance *padata_alloc(const char *name,
 		free_cpumask_var(pinst->cpumask.pcpu);
 		goto err_free_serial_wq;
 	}
-	if (!padata_validate_cpumask(pinst, pcpumask) ||
-	    !padata_validate_cpumask(pinst, cbcpumask))
-		goto err_free_masks;
-
-	if (!alloc_cpumask_var(&pinst->rcpumask.pcpu, GFP_KERNEL))
-		goto err_free_masks;
-	if (!alloc_cpumask_var(&pinst->rcpumask.cbcpu, GFP_KERNEL))
-		goto err_free_rcpumask_pcpu;
 
 	INIT_LIST_HEAD(&pinst->pslist);
 
-	cpumask_copy(pinst->cpumask.pcpu, pcpumask);
-	cpumask_copy(pinst->cpumask.cbcpu, cbcpumask);
-	cpumask_and(pinst->rcpumask.pcpu, pcpumask, cpu_online_mask);
-	cpumask_and(pinst->rcpumask.cbcpu, cbcpumask, cpu_online_mask);
+	cpumask_copy(pinst->cpumask.pcpu, cpu_possible_mask);
+	cpumask_copy(pinst->cpumask.cbcpu, cpu_possible_mask);
 
 	if (padata_setup_cpumasks(pinst))
-		goto err_free_rcpumask_cbcpu;
+		goto err_free_masks;
 
-	pinst->flags = 0;
+	__padata_start(pinst);
 
 	kobject_init(&pinst->kobj, &padata_attr_type);
 	mutex_init(&pinst->lock);
 
 #ifdef CONFIG_HOTPLUG_CPU
-	cpuhp_state_add_instance_nocalls_cpuslocked(hp_online, &pinst->node);
+	cpuhp_state_add_instance_nocalls_cpuslocked(hp_online,
+						    &pinst->cpu_online_node);
 	cpuhp_state_add_instance_nocalls_cpuslocked(CPUHP_PADATA_DEAD,
-						    &pinst->node);
+						    &pinst->cpu_dead_node);
 #endif
 
 	put_online_cpus();
 
 	return pinst;
 
-err_free_rcpumask_cbcpu:
-	free_cpumask_var(pinst->rcpumask.cbcpu);
-err_free_rcpumask_pcpu:
-	free_cpumask_var(pinst->rcpumask.pcpu);
 err_free_masks:
 	free_cpumask_var(pinst->cpumask.pcpu);
 	free_cpumask_var(pinst->cpumask.cbcpu);
@@ -965,21 +1042,7 @@ err_free_inst:
 err:
 	return NULL;
 }
-
-/**
- * padata_alloc_possible - Allocate and initialize padata instance.
- *                         Use the cpu_possible_mask for serial and
- *                         parallel workers.
- *
- * @name: used to identify the instance
- *
- * Return: new instance on success, NULL on error
- */
-struct padata_instance *padata_alloc_possible(const char *name)
-{
-	return padata_alloc(name, cpu_possible_mask, cpu_possible_mask);
-}
-EXPORT_SYMBOL(padata_alloc_possible);
+EXPORT_SYMBOL(padata_alloc);
 
 /**
  * padata_free - free a padata instance
@@ -1038,43 +1101,53 @@ EXPORT_SYMBOL(padata_alloc_shell);
  */
 void padata_free_shell(struct padata_shell *ps)
 {
-	struct padata_instance *pinst = ps->pinst;
+	if (!ps)
+		return;
 
-	mutex_lock(&pinst->lock);
+	mutex_lock(&ps->pinst->lock);
 	list_del(&ps->list);
 	padata_free_pd(rcu_dereference_protected(ps->pd, 1));
-	mutex_unlock(&pinst->lock);
+	mutex_unlock(&ps->pinst->lock);
 
 	kfree(ps);
 }
 EXPORT_SYMBOL(padata_free_shell);
 
-#ifdef CONFIG_HOTPLUG_CPU
-
-static __init int padata_driver_init(void)
+void __init padata_init(void)
 {
+	unsigned int i, possible_cpus;
+#ifdef CONFIG_HOTPLUG_CPU
 	int ret;
 
 	ret = cpuhp_setup_state_multi(CPUHP_AP_ONLINE_DYN, "padata:online",
 				      padata_cpu_online, NULL);
 	if (ret < 0)
-		return ret;
+		goto err;
 	hp_online = ret;
 
 	ret = cpuhp_setup_state_multi(CPUHP_PADATA_DEAD, "padata:dead",
 				      NULL, padata_cpu_dead);
-	if (ret < 0) {
-		cpuhp_remove_multi_state(hp_online);
-		return ret;
-	}
-	return 0;
-}
-module_init(padata_driver_init);
+	if (ret < 0)
+		goto remove_online_state;
+#endif
 
-static __exit void padata_driver_exit(void)
-{
+	possible_cpus = num_possible_cpus();
+	padata_works = kmalloc_array(possible_cpus, sizeof(struct padata_work),
+				     GFP_KERNEL);
+	if (!padata_works)
+		goto remove_dead_state;
+
+	for (i = 0; i < possible_cpus; ++i)
+		list_add(&padata_works[i].pw_list, &padata_free_works);
+
+	return;
+
+remove_dead_state:
+#ifdef CONFIG_HOTPLUG_CPU
 	cpuhp_remove_multi_state(CPUHP_PADATA_DEAD);
+remove_online_state:
 	cpuhp_remove_multi_state(hp_online);
-}
-module_exit(padata_driver_exit);
+err:
 #endif
+	pr_warn("padata: initialization failed\n");
+}
diff --git a/kernel/panic.c b/kernel/panic.c
index b69ee9e76cb2..aef8872ba843 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -36,6 +36,14 @@
 #define PANIC_TIMER_STEP 100
 #define PANIC_BLINK_SPD 18
 
+#ifdef CONFIG_SMP
+/*
+ * Should we dump all CPUs backtraces in an oops event?
+ * Defaults to 0, can be changed via sysctl.
+ */
+unsigned int __read_mostly sysctl_oops_all_cpu_backtrace;
+#endif /* CONFIG_SMP */
+
 int panic_on_oops = CONFIG_PANIC_ON_OOPS_VALUE;
 static unsigned long tainted_mask =
 	IS_ENABLED(CONFIG_GCC_PLUGIN_RANDSTRUCT) ? (1 << TAINT_RANDSTRUCT) : 0;
@@ -44,6 +52,8 @@ static int pause_on_oops_flag;
 static DEFINE_SPINLOCK(pause_on_oops_lock);
 bool crash_kexec_post_notifiers;
 int panic_on_warn __read_mostly;
+unsigned long panic_on_taint;
+bool panic_on_taint_nousertaint = false;
 
 int panic_timeout = CONFIG_PANIC_TIMEOUT;
 EXPORT_SYMBOL_GPL(panic_timeout);
@@ -434,6 +444,11 @@ void add_taint(unsigned flag, enum lockdep_ok lockdep_ok)
 		pr_warn("Disabling lock debugging due to kernel taint\n");
 
 	set_bit(flag, &tainted_mask);
+
+	if (tainted_mask & panic_on_taint) {
+		panic_on_taint = 0;
+		panic("panic_on_taint set ...");
+	}
 }
 EXPORT_SYMBOL(add_taint);
 
@@ -490,7 +505,7 @@ static void do_oops_enter_exit(void)
  * Return true if the calling CPU is allowed to print oops-related info.
  * This is a bit racy..
  */
-int oops_may_print(void)
+bool oops_may_print(void)
 {
 	return pause_on_oops_flag == 0;
 }
@@ -515,6 +530,9 @@ void oops_enter(void)
 	/* can't trust the integrity of the kernel anymore: */
 	debug_locks_off();
 	do_oops_enter_exit();
+
+	if (sysctl_oops_all_cpu_backtrace)
+		trigger_all_cpu_backtrace();
 }
 
 /*
@@ -533,7 +551,7 @@ static int init_oops_id(void)
 }
 late_initcall(init_oops_id);
 
-void print_oops_end_marker(void)
+static void print_oops_end_marker(void)
 {
 	init_oops_id();
 	pr_warn("---[ end trace %016llx ]---\n", (unsigned long long)oops_id);
@@ -662,10 +680,12 @@ device_initcall(register_warn_debugfs);
  * Called when gcc's -fstack-protector feature is used, and
  * gcc detects corruption of the on-stack canary value
  */
-__visible void __stack_chk_fail(void)
+__visible noinstr void __stack_chk_fail(void)
 {
+	instrumentation_begin();
 	panic("stack-protector: Kernel stack is corrupted in: %pB",
 		__builtin_return_address(0));
+	instrumentation_end();
 }
 EXPORT_SYMBOL(__stack_chk_fail);
 
@@ -686,3 +706,30 @@ static int __init oops_setup(char *s)
 	return 0;
 }
 early_param("oops", oops_setup);
+
+static int __init panic_on_taint_setup(char *s)
+{
+	char *taint_str;
+
+	if (!s)
+		return -EINVAL;
+
+	taint_str = strsep(&s, ",");
+	if (kstrtoul(taint_str, 16, &panic_on_taint))
+		return -EINVAL;
+
+	/* make sure panic_on_taint doesn't hold out-of-range TAINT flags */
+	panic_on_taint &= TAINT_FLAGS_MAX;
+
+	if (!panic_on_taint)
+		return -EINVAL;
+
+	if (s && !strcmp(s, "nousertaint"))
+		panic_on_taint_nousertaint = true;
+
+	pr_info("panic_on_taint: bitmask=0x%lx nousertaint_mode=%sabled\n",
+		panic_on_taint, panic_on_taint_nousertaint ? "en" : "dis");
+
+	return 0;
+}
+early_param("panic_on_taint", panic_on_taint_setup);
diff --git a/kernel/pid.c b/kernel/pid.c
index 647b4bb457b5..b2562a7ce525 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -42,6 +42,7 @@
 #include <linux/sched/signal.h>
 #include <linux/sched/task.h>
 #include <linux/idr.h>
+#include <net/sock.h>
 
 struct pid init_struct_pid = {
 	.count		= REFCOUNT_INIT(1),
@@ -144,9 +145,6 @@ void free_pid(struct pid *pid)
 			/* Handle a fork failure of the first process */
 			WARN_ON(ns->child_reaper);
 			ns->pid_allocated = 0;
-			/* fall through */
-		case 0:
-			schedule_work(&ns->proc_work);
 			break;
 		}
 
@@ -201,7 +199,7 @@ struct pid *alloc_pid(struct pid_namespace *ns, pid_t *set_tid,
 			if (tid != 1 && !tmp->child_reaper)
 				goto out_free;
 			retval = -EPERM;
-			if (!ns_capable(tmp->user_ns, CAP_SYS_ADMIN))
+			if (!checkpoint_restore_ns_capable(tmp->user_ns))
 				goto out_free;
 			set_tid_size--;
 		}
@@ -257,17 +255,14 @@ struct pid *alloc_pid(struct pid_namespace *ns, pid_t *set_tid,
 	 */
 	retval = -ENOMEM;
 
-	if (unlikely(is_child_reaper(pid))) {
-		if (pid_ns_prepare_proc(ns))
-			goto out_free;
-	}
-
 	get_pid_ns(ns);
 	refcount_set(&pid->count, 1);
+	spin_lock_init(&pid->lock);
 	for (type = 0; type < PIDTYPE_MAX; ++type)
 		INIT_HLIST_HEAD(&pid->tasks[type]);
 
 	init_waitqueue_head(&pid->wait_pidfd);
+	INIT_HLIST_HEAD(&pid->inodes);
 
 	upid = pid->numbers + ns->level;
 	spin_lock_irq(&pidmap_lock);
@@ -369,6 +364,25 @@ void change_pid(struct task_struct *task, enum pid_type type,
 	attach_pid(task, type);
 }
 
+void exchange_tids(struct task_struct *left, struct task_struct *right)
+{
+	struct pid *pid1 = left->thread_pid;
+	struct pid *pid2 = right->thread_pid;
+	struct hlist_head *head1 = &pid1->tasks[PIDTYPE_PID];
+	struct hlist_head *head2 = &pid2->tasks[PIDTYPE_PID];
+
+	/* Swap the single entry tid lists */
+	hlists_swap_heads_rcu(head1, head2);
+
+	/* Swap the per task_struct pid */
+	rcu_assign_pointer(left->thread_pid, pid2);
+	rcu_assign_pointer(right->thread_pid, pid1);
+
+	/* Swap the cached value */
+	WRITE_ONCE(left->pid, pid_nr(pid2));
+	WRITE_ONCE(right->pid, pid_nr(pid1));
+}
+
 /* transfer_pid is an optimization of attach_pid(new), detach_pid(old) */
 void transfer_pid(struct task_struct *old, struct task_struct *new,
 			   enum pid_type type)
@@ -482,8 +496,7 @@ pid_t __task_pid_nr_ns(struct task_struct *task, enum pid_type type,
 	rcu_read_lock();
 	if (!ns)
 		ns = task_active_pid_ns(current);
-	if (likely(pid_alive(task)))
-		nr = pid_nr_ns(rcu_dereference(*task_pid_ptr(task, type)), ns);
+	nr = pid_nr_ns(rcu_dereference(*task_pid_ptr(task, type)), ns);
 	rcu_read_unlock();
 
 	return nr;
@@ -594,7 +607,7 @@ static struct file *__pidfd_fget(struct task_struct *task, int fd)
 	struct file *file;
 	int ret;
 
-	ret = mutex_lock_killable(&task->signal->cred_guard_mutex);
+	ret = mutex_lock_killable(&task->signal->exec_update_mutex);
 	if (ret)
 		return ERR_PTR(ret);
 
@@ -603,7 +616,7 @@ static struct file *__pidfd_fget(struct task_struct *task, int fd)
 	else
 		file = ERR_PTR(-EPERM);
 
-	mutex_unlock(&task->signal->cred_guard_mutex);
+	mutex_unlock(&task->signal->exec_update_mutex);
 
 	return file ?: ERR_PTR(-EBADF);
 }
@@ -623,17 +636,8 @@ static int pidfd_getfd(struct pid *pid, int fd)
 	if (IS_ERR(file))
 		return PTR_ERR(file);
 
-	ret = security_file_receive(file);
-	if (ret) {
-		fput(file);
-		return ret;
-	}
-
-	ret = get_unused_fd_flags(O_CLOEXEC);
-	if (ret < 0)
-		fput(file);
-	else
-		fd_install(ret, file);
+	ret = receive_fd(file, O_CLOEXEC);
+	fput(file);
 
 	return ret;
 }
diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c
index d40017e79ebe..ac135bd600eb 100644
--- a/kernel/pid_namespace.c
+++ b/kernel/pid_namespace.c
@@ -57,12 +57,6 @@ static struct kmem_cache *create_pid_cachep(unsigned int level)
 	return READ_ONCE(*pkc);
 }
 
-static void proc_cleanup_work(struct work_struct *work)
-{
-	struct pid_namespace *ns = container_of(work, struct pid_namespace, proc_work);
-	pid_ns_release_proc(ns);
-}
-
 static struct ucounts *inc_pid_namespaces(struct user_namespace *ns)
 {
 	return inc_ucount(ns, current_euid(), UCOUNT_PID_NAMESPACES);
@@ -114,7 +108,6 @@ static struct pid_namespace *create_pid_namespace(struct user_namespace *user_ns
 	ns->user_ns = get_user_ns(user_ns);
 	ns->ucounts = ucounts;
 	ns->pid_allocated = PIDNS_ADDING;
-	INIT_WORK(&ns->proc_work, proc_cleanup_work);
 
 	return ns;
 
@@ -231,20 +224,27 @@ void zap_pid_ns_processes(struct pid_namespace *pid_ns)
 	} while (rc != -ECHILD);
 
 	/*
-	 * kernel_wait4() above can't reap the EXIT_DEAD children but we do not
-	 * really care, we could reparent them to the global init. We could
-	 * exit and reap ->child_reaper even if it is not the last thread in
-	 * this pid_ns, free_pid(pid_allocated == 0) calls proc_cleanup_work(),
-	 * pid_ns can not go away until proc_kill_sb() drops the reference.
+	 * kernel_wait4() misses EXIT_DEAD children, and EXIT_ZOMBIE
+	 * process whose parents processes are outside of the pid
+	 * namespace.  Such processes are created with setns()+fork().
+	 *
+	 * If those EXIT_ZOMBIE processes are not reaped by their
+	 * parents before their parents exit, they will be reparented
+	 * to pid_ns->child_reaper.  Thus pidns->child_reaper needs to
+	 * stay valid until they all go away.
+	 *
+	 * The code relies on the the pid_ns->child_reaper ignoring
+	 * SIGCHILD to cause those EXIT_ZOMBIE processes to be
+	 * autoreaped if reparented.
 	 *
-	 * But this ns can also have other tasks injected by setns()+fork().
-	 * Again, ignoring the user visible semantics we do not really need
-	 * to wait until they are all reaped, but they can be reparented to
-	 * us and thus we need to ensure that pid->child_reaper stays valid
-	 * until they all go away. See free_pid()->wake_up_process().
+	 * Semantically it is also desirable to wait for EXIT_ZOMBIE
+	 * processes before allowing the child_reaper to be reaped, as
+	 * that gives the invariant that when the init process of a
+	 * pid namespace is reaped all of the processes in the pid
+	 * namespace are gone.
 	 *
-	 * We rely on ignored SIGCHLD, an injected zombie must be autoreaped
-	 * if reparented.
+	 * Once all of the other tasks are gone from the pid_namespace
+	 * free_pid() will awaken this task.
 	 */
 	for (;;) {
 		set_current_state(TASK_INTERRUPTIBLE);
@@ -263,13 +263,13 @@ void zap_pid_ns_processes(struct pid_namespace *pid_ns)
 
 #ifdef CONFIG_CHECKPOINT_RESTORE
 static int pid_ns_ctl_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 pid_namespace *pid_ns = task_active_pid_ns(current);
 	struct ctl_table tmp = *table;
 	int ret, next;
 
-	if (write && !ns_capable(pid_ns->user_ns, CAP_SYS_ADMIN))
+	if (write && !checkpoint_restore_ns_capable(pid_ns->user_ns))
 		return -EPERM;
 
 	/*
@@ -378,13 +378,14 @@ static void pidns_put(struct ns_common *ns)
 	put_pid_ns(to_pid_ns(ns));
 }
 
-static int pidns_install(struct nsproxy *nsproxy, struct ns_common *ns)
+static int pidns_install(struct nsset *nsset, struct ns_common *ns)
 {
+	struct nsproxy *nsproxy = nsset->nsproxy;
 	struct pid_namespace *active = task_active_pid_ns(current);
 	struct pid_namespace *ancestor, *new = to_pid_ns(ns);
 
 	if (!ns_capable(new->user_ns, CAP_SYS_ADMIN) ||
-	    !ns_capable(current_user_ns(), CAP_SYS_ADMIN))
+	    !ns_capable(nsset->cred->user_ns, CAP_SYS_ADMIN))
 		return -EPERM;
 
 	/*
diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig
index 7cbfbeacd68a..a7320f07689d 100644
--- a/kernel/power/Kconfig
+++ b/kernel/power/Kconfig
@@ -3,7 +3,7 @@ config SUSPEND
 	bool "Suspend to RAM and standby"
 	depends on ARCH_SUSPEND_POSSIBLE
 	default y
-	---help---
+	help
 	  Allow the system to enter sleep states in which main memory is
 	  powered and thus its contents are preserved, such as the
 	  suspend-to-RAM state (e.g. the ACPI S3 state).
@@ -42,7 +42,7 @@ config HIBERNATION
 	select LZO_COMPRESS
 	select LZO_DECOMPRESS
 	select CRC32
-	---help---
+	help
 	  Enable the suspend to disk (STD) functionality, which is usually
 	  called "hibernation" in user interfaces.  STD checkpoints the
 	  system and powers it off; and restores that checkpoint on reboot.
@@ -80,14 +80,23 @@ config HIBERNATION
 
 	  For more information take a look at <file:Documentation/power/swsusp.rst>.
 
-config ARCH_SAVE_PAGE_KEYS
-	bool
+config HIBERNATION_SNAPSHOT_DEV
+	bool "Userspace snapshot device"
+	depends on HIBERNATION
+	default y
+	help
+	  Device used by the uswsusp tools.
+
+	  Say N if no snapshotting from userspace is needed, this also
+	  reduces the attack surface of the kernel.
+
+	  If in doubt, say Y.
 
 config PM_STD_PARTITION
 	string "Default resume partition"
 	depends on HIBERNATION
 	default ""
-	---help---
+	help
 	  The default resume partition is the partition that the suspend-
 	  to-disk implementation will look for a suspended disk image. 
 
@@ -122,7 +131,7 @@ config PM_SLEEP_SMP_NONZERO_CPU
 	def_bool y
 	depends on PM_SLEEP_SMP
 	depends on ARCH_SUSPEND_NONZERO_CPU
-	---help---
+	help
 	If an arch can suspend (for suspend, hibernate, kexec, etc) on a
 	non-zero numbered CPU, it may define ARCH_SUSPEND_NONZERO_CPU. This
 	will allow nohz_full mask to include CPU0.
@@ -131,7 +140,7 @@ config PM_AUTOSLEEP
 	bool "Opportunistic sleep"
 	depends on PM_SLEEP
 	default n
-	---help---
+	help
 	Allow the kernel to trigger a system transition into a global sleep
 	state automatically whenever there are no active wakeup sources.
 
@@ -139,7 +148,7 @@ config PM_WAKELOCKS
 	bool "User space wakeup sources interface"
 	depends on PM_SLEEP
 	default n
-	---help---
+	help
 	Allow user space to create, activate and deactivate wakeup source
 	objects with the help of a sysfs-based interface.
 
@@ -156,7 +165,7 @@ config PM_WAKELOCKS_GC
 
 config PM
 	bool "Device power management core functionality"
-	---help---
+	help
 	  Enable functionality allowing I/O devices to be put into energy-saving
 	  (low power) states, for example after a specified period of inactivity
 	  (autosuspended), and woken up in response to a hardware-generated
@@ -170,7 +179,7 @@ config PM
 config PM_DEBUG
 	bool "Power Management Debug Support"
 	depends on PM
-	---help---
+	help
 	This option enables various debugging support in the Power Management
 	code. This is helpful when debugging and reporting PM bugs, like
 	suspend support.
@@ -178,7 +187,7 @@ config PM_DEBUG
 config PM_ADVANCED_DEBUG
 	bool "Extra PM attributes in sysfs for low-level debugging/testing"
 	depends on PM_DEBUG
-	---help---
+	help
 	Add extra sysfs attributes allowing one to access some Power Management
 	fields of device objects from user space.  If you are not a kernel
 	developer interested in debugging/testing Power Management, say "no".
@@ -186,7 +195,7 @@ config PM_ADVANCED_DEBUG
 config PM_TEST_SUSPEND
 	bool "Test suspend/resume and wakealarm during bootup"
 	depends on SUSPEND && PM_DEBUG && RTC_CLASS=y
-	---help---
+	help
 	This option will let you suspend your machine during bootup, and
 	make it wake up a few seconds later using an RTC wakeup alarm.
 	Enable this with a kernel parameter like "test_suspend=mem".
@@ -201,7 +210,7 @@ config PM_SLEEP_DEBUG
 config DPM_WATCHDOG
 	bool "Device suspend/resume watchdog"
 	depends on PM_DEBUG && PSTORE && EXPERT
-	---help---
+	help
 	  Sets up a watchdog timer to capture drivers that are
 	  locked up attempting to suspend/resume a device.
 	  A detected lockup causes system panic with message
@@ -234,7 +243,7 @@ config PM_TRACE_RTC
 	depends on PM_SLEEP_DEBUG
 	depends on X86
 	select PM_TRACE
-	---help---
+	help
 	This enables some cheesy code to save the last PM event point in the
 	RTC across reboots, so that you can debug a machine that just hangs
 	during suspend (or more commonly, during resume).
diff --git a/kernel/power/Makefile b/kernel/power/Makefile
index e7e47d9be1e5..5899260a8bef 100644
--- a/kernel/power/Makefile
+++ b/kernel/power/Makefile
@@ -10,7 +10,8 @@ obj-$(CONFIG_VT_CONSOLE_SLEEP)	+= console.o
 obj-$(CONFIG_FREEZER)		+= process.o
 obj-$(CONFIG_SUSPEND)		+= suspend.o
 obj-$(CONFIG_PM_TEST_SUSPEND)	+= suspend_test.o
-obj-$(CONFIG_HIBERNATION)	+= hibernate.o snapshot.o swap.o user.o
+obj-$(CONFIG_HIBERNATION)	+= hibernate.o snapshot.o swap.o
+obj-$(CONFIG_HIBERNATION_SNAPSHOT_DEV) += user.o
 obj-$(CONFIG_PM_AUTOSLEEP)	+= autosleep.o
 obj-$(CONFIG_PM_WAKELOCKS)	+= wakelock.o
 
diff --git a/kernel/power/energy_model.c b/kernel/power/energy_model.c
index 0a9326f5f421..c1ff7fa030ab 100644
--- a/kernel/power/energy_model.c
+++ b/kernel/power/energy_model.c
@@ -1,9 +1,10 @@
 // SPDX-License-Identifier: GPL-2.0
 /*
- * Energy Model of CPUs
+ * Energy Model of devices
  *
- * Copyright (c) 2018, Arm ltd.
+ * Copyright (c) 2018-2020, Arm ltd.
  * Written by: Quentin Perret, Arm ltd.
+ * Improvements provided by: Lukasz Luba, Arm ltd.
  */
 
 #define pr_fmt(fmt) "energy_model: " fmt
@@ -15,30 +16,32 @@
 #include <linux/sched/topology.h>
 #include <linux/slab.h>
 
-/* Mapping of each CPU to the performance domain to which it belongs. */
-static DEFINE_PER_CPU(struct em_perf_domain *, em_data);
-
 /*
  * Mutex serializing the registrations of performance domains and letting
  * callbacks defined by drivers sleep.
  */
 static DEFINE_MUTEX(em_pd_mutex);
 
+static bool _is_cpu_device(struct device *dev)
+{
+	return (dev->bus == &cpu_subsys);
+}
+
 #ifdef CONFIG_DEBUG_FS
 static struct dentry *rootdir;
 
-static void em_debug_create_cs(struct em_cap_state *cs, struct dentry *pd)
+static void em_debug_create_ps(struct em_perf_state *ps, struct dentry *pd)
 {
 	struct dentry *d;
 	char name[24];
 
-	snprintf(name, sizeof(name), "cs:%lu", cs->frequency);
+	snprintf(name, sizeof(name), "ps:%lu", ps->frequency);
 
-	/* Create per-cs directory */
+	/* Create per-ps directory */
 	d = debugfs_create_dir(name, pd);
-	debugfs_create_ulong("frequency", 0444, d, &cs->frequency);
-	debugfs_create_ulong("power", 0444, d, &cs->power);
-	debugfs_create_ulong("cost", 0444, d, &cs->cost);
+	debugfs_create_ulong("frequency", 0444, d, &ps->frequency);
+	debugfs_create_ulong("power", 0444, d, &ps->power);
+	debugfs_create_ulong("cost", 0444, d, &ps->cost);
 }
 
 static int em_debug_cpus_show(struct seq_file *s, void *unused)
@@ -49,22 +52,30 @@ static int em_debug_cpus_show(struct seq_file *s, void *unused)
 }
 DEFINE_SHOW_ATTRIBUTE(em_debug_cpus);
 
-static void em_debug_create_pd(struct em_perf_domain *pd, int cpu)
+static void em_debug_create_pd(struct device *dev)
 {
 	struct dentry *d;
-	char name[8];
 	int i;
 
-	snprintf(name, sizeof(name), "pd%d", cpu);
-
 	/* Create the directory of the performance domain */
-	d = debugfs_create_dir(name, rootdir);
+	d = debugfs_create_dir(dev_name(dev), rootdir);
 
-	debugfs_create_file("cpus", 0444, d, pd->cpus, &em_debug_cpus_fops);
+	if (_is_cpu_device(dev))
+		debugfs_create_file("cpus", 0444, d, dev->em_pd->cpus,
+				    &em_debug_cpus_fops);
+
+	/* Create a sub-directory for each performance state */
+	for (i = 0; i < dev->em_pd->nr_perf_states; i++)
+		em_debug_create_ps(&dev->em_pd->table[i], d);
 
-	/* Create a sub-directory for each capacity state */
-	for (i = 0; i < pd->nr_cap_states; i++)
-		em_debug_create_cs(&pd->table[i], d);
+}
+
+static void em_debug_remove_pd(struct device *dev)
+{
+	struct dentry *debug_dir;
+
+	debug_dir = debugfs_lookup(dev_name(dev), rootdir);
+	debugfs_remove_recursive(debug_dir);
 }
 
 static int __init em_debug_init(void)
@@ -76,58 +87,55 @@ static int __init em_debug_init(void)
 }
 core_initcall(em_debug_init);
 #else /* CONFIG_DEBUG_FS */
-static void em_debug_create_pd(struct em_perf_domain *pd, int cpu) {}
+static void em_debug_create_pd(struct device *dev) {}
+static void em_debug_remove_pd(struct device *dev) {}
 #endif
-static struct em_perf_domain *em_create_pd(cpumask_t *span, int nr_states,
-						struct em_data_callback *cb)
+
+static int em_create_perf_table(struct device *dev, struct em_perf_domain *pd,
+				int nr_states, struct em_data_callback *cb)
 {
 	unsigned long opp_eff, prev_opp_eff = ULONG_MAX;
 	unsigned long power, freq, prev_freq = 0;
-	int i, ret, cpu = cpumask_first(span);
-	struct em_cap_state *table;
-	struct em_perf_domain *pd;
+	struct em_perf_state *table;
+	int i, ret;
 	u64 fmax;
 
-	if (!cb->active_power)
-		return NULL;
-
-	pd = kzalloc(sizeof(*pd) + cpumask_size(), GFP_KERNEL);
-	if (!pd)
-		return NULL;
-
 	table = kcalloc(nr_states, sizeof(*table), GFP_KERNEL);
 	if (!table)
-		goto free_pd;
+		return -ENOMEM;
 
-	/* Build the list of capacity states for this performance domain */
+	/* Build the list of performance states for this performance domain */
 	for (i = 0, freq = 0; i < nr_states; i++, freq++) {
 		/*
 		 * active_power() is a driver callback which ceils 'freq' to
-		 * lowest capacity state of 'cpu' above 'freq' and updates
+		 * lowest performance state of 'dev' above 'freq' and updates
 		 * 'power' and 'freq' accordingly.
 		 */
-		ret = cb->active_power(&power, &freq, cpu);
+		ret = cb->active_power(&power, &freq, dev);
 		if (ret) {
-			pr_err("pd%d: invalid cap. state: %d\n", cpu, ret);
-			goto free_cs_table;
+			dev_err(dev, "EM: invalid perf. state: %d\n",
+				ret);
+			goto free_ps_table;
 		}
 
 		/*
 		 * We expect the driver callback to increase the frequency for
-		 * higher capacity states.
+		 * higher performance states.
 		 */
 		if (freq <= prev_freq) {
-			pr_err("pd%d: non-increasing freq: %lu\n", cpu, freq);
-			goto free_cs_table;
+			dev_err(dev, "EM: non-increasing freq: %lu\n",
+				freq);
+			goto free_ps_table;
 		}
 
 		/*
 		 * The power returned by active_state() is expected to be
 		 * positive, in milli-watts and to fit into 16 bits.
 		 */
-		if (!power || power > EM_CPU_MAX_POWER) {
-			pr_err("pd%d: invalid power: %lu\n", cpu, power);
-			goto free_cs_table;
+		if (!power || power > EM_MAX_POWER) {
+			dev_err(dev, "EM: invalid power: %lu\n",
+				power);
+			goto free_ps_table;
 		}
 
 		table[i].power = power;
@@ -141,12 +149,12 @@ static struct em_perf_domain *em_create_pd(cpumask_t *span, int nr_states,
 		 */
 		opp_eff = freq / power;
 		if (opp_eff >= prev_opp_eff)
-			pr_warn("pd%d: hertz/watts ratio non-monotonically decreasing: em_cap_state %d >= em_cap_state%d\n",
-					cpu, i, i - 1);
+			dev_dbg(dev, "EM: hertz/watts ratio non-monotonically decreasing: em_perf_state %d >= em_perf_state%d\n",
+					i, i - 1);
 		prev_opp_eff = opp_eff;
 	}
 
-	/* Compute the cost of each capacity_state. */
+	/* Compute the cost of each performance state. */
 	fmax = (u64) table[nr_states - 1].frequency;
 	for (i = 0; i < nr_states; i++) {
 		table[i].cost = div64_u64(fmax * table[i].power,
@@ -154,39 +162,94 @@ static struct em_perf_domain *em_create_pd(cpumask_t *span, int nr_states,
 	}
 
 	pd->table = table;
-	pd->nr_cap_states = nr_states;
-	cpumask_copy(to_cpumask(pd->cpus), span);
-
-	em_debug_create_pd(pd, cpu);
+	pd->nr_perf_states = nr_states;
 
-	return pd;
+	return 0;
 
-free_cs_table:
+free_ps_table:
 	kfree(table);
-free_pd:
-	kfree(pd);
+	return -EINVAL;
+}
+
+static int em_create_pd(struct device *dev, int nr_states,
+			struct em_data_callback *cb, cpumask_t *cpus)
+{
+	struct em_perf_domain *pd;
+	struct device *cpu_dev;
+	int cpu, ret;
+
+	if (_is_cpu_device(dev)) {
+		pd = kzalloc(sizeof(*pd) + cpumask_size(), GFP_KERNEL);
+		if (!pd)
+			return -ENOMEM;
+
+		cpumask_copy(em_span_cpus(pd), cpus);
+	} else {
+		pd = kzalloc(sizeof(*pd), GFP_KERNEL);
+		if (!pd)
+			return -ENOMEM;
+	}
+
+	ret = em_create_perf_table(dev, pd, nr_states, cb);
+	if (ret) {
+		kfree(pd);
+		return ret;
+	}
+
+	if (_is_cpu_device(dev))
+		for_each_cpu(cpu, cpus) {
+			cpu_dev = get_cpu_device(cpu);
+			cpu_dev->em_pd = pd;
+		}
+
+	dev->em_pd = pd;
+
+	return 0;
+}
+
+/**
+ * em_pd_get() - Return the performance domain for a device
+ * @dev : Device to find the performance domain for
+ *
+ * Returns the performance domain to which @dev belongs, or NULL if it doesn't
+ * exist.
+ */
+struct em_perf_domain *em_pd_get(struct device *dev)
+{
+	if (IS_ERR_OR_NULL(dev))
+		return NULL;
 
-	return NULL;
+	return dev->em_pd;
 }
+EXPORT_SYMBOL_GPL(em_pd_get);
 
 /**
  * em_cpu_get() - Return the performance domain for a CPU
  * @cpu : CPU to find the performance domain for
  *
- * Return: the performance domain to which 'cpu' belongs, or NULL if it doesn't
+ * Returns the performance domain to which @cpu belongs, or NULL if it doesn't
  * exist.
  */
 struct em_perf_domain *em_cpu_get(int cpu)
 {
-	return READ_ONCE(per_cpu(em_data, cpu));
+	struct device *cpu_dev;
+
+	cpu_dev = get_cpu_device(cpu);
+	if (!cpu_dev)
+		return NULL;
+
+	return em_pd_get(cpu_dev);
 }
 EXPORT_SYMBOL_GPL(em_cpu_get);
 
 /**
- * em_register_perf_domain() - Register the Energy Model of a performance domain
- * @span	: Mask of CPUs in the performance domain
- * @nr_states	: Number of capacity states to register
+ * em_dev_register_perf_domain() - Register the Energy Model (EM) for a device
+ * @dev		: Device for which the EM is to register
+ * @nr_states	: Number of performance states to register
  * @cb		: Callback functions providing the data of the Energy Model
+ * @cpus	: Pointer to cpumask_t, which in case of a CPU device is
+ *		obligatory. It can be taken from i.e. 'policy->cpus'. For other
+ *		type of devices this should be set to NULL.
  *
  * Create Energy Model tables for a performance domain using the callbacks
  * defined in cb.
@@ -196,14 +259,13 @@ EXPORT_SYMBOL_GPL(em_cpu_get);
  *
  * Return 0 on success
  */
-int em_register_perf_domain(cpumask_t *span, unsigned int nr_states,
-						struct em_data_callback *cb)
+int em_dev_register_perf_domain(struct device *dev, unsigned int nr_states,
+				struct em_data_callback *cb, cpumask_t *cpus)
 {
 	unsigned long cap, prev_cap = 0;
-	struct em_perf_domain *pd;
-	int cpu, ret = 0;
+	int cpu, ret;
 
-	if (!span || !nr_states || !cb)
+	if (!dev || !nr_states || !cb)
 		return -EINVAL;
 
 	/*
@@ -212,47 +274,79 @@ int em_register_perf_domain(cpumask_t *span, unsigned int nr_states,
 	 */
 	mutex_lock(&em_pd_mutex);
 
-	for_each_cpu(cpu, span) {
-		/* Make sure we don't register again an existing domain. */
-		if (READ_ONCE(per_cpu(em_data, cpu))) {
-			ret = -EEXIST;
-			goto unlock;
-		}
+	if (dev->em_pd) {
+		ret = -EEXIST;
+		goto unlock;
+	}
 
-		/*
-		 * All CPUs of a domain must have the same micro-architecture
-		 * since they all share the same table.
-		 */
-		cap = arch_scale_cpu_capacity(cpu);
-		if (prev_cap && prev_cap != cap) {
-			pr_err("CPUs of %*pbl must have the same capacity\n",
-							cpumask_pr_args(span));
+	if (_is_cpu_device(dev)) {
+		if (!cpus) {
+			dev_err(dev, "EM: invalid CPU mask\n");
 			ret = -EINVAL;
 			goto unlock;
 		}
-		prev_cap = cap;
+
+		for_each_cpu(cpu, cpus) {
+			if (em_cpu_get(cpu)) {
+				dev_err(dev, "EM: exists for CPU%d\n", cpu);
+				ret = -EEXIST;
+				goto unlock;
+			}
+			/*
+			 * All CPUs of a domain must have the same
+			 * micro-architecture since they all share the same
+			 * table.
+			 */
+			cap = arch_scale_cpu_capacity(cpu);
+			if (prev_cap && prev_cap != cap) {
+				dev_err(dev, "EM: CPUs of %*pbl must have the same capacity\n",
+					cpumask_pr_args(cpus));
+
+				ret = -EINVAL;
+				goto unlock;
+			}
+			prev_cap = cap;
+		}
 	}
 
-	/* Create the performance domain and add it to the Energy Model. */
-	pd = em_create_pd(span, nr_states, cb);
-	if (!pd) {
-		ret = -EINVAL;
+	ret = em_create_pd(dev, nr_states, cb, cpus);
+	if (ret)
 		goto unlock;
-	}
 
-	for_each_cpu(cpu, span) {
-		/*
-		 * The per-cpu array can be read concurrently from em_cpu_get().
-		 * The barrier enforces the ordering needed to make sure readers
-		 * can only access well formed em_perf_domain structs.
-		 */
-		smp_store_release(per_cpu_ptr(&em_data, cpu), pd);
-	}
+	em_debug_create_pd(dev);
+	dev_info(dev, "EM: created perf domain\n");
 
-	pr_debug("Created perf domain %*pbl\n", cpumask_pr_args(span));
 unlock:
 	mutex_unlock(&em_pd_mutex);
-
 	return ret;
 }
-EXPORT_SYMBOL_GPL(em_register_perf_domain);
+EXPORT_SYMBOL_GPL(em_dev_register_perf_domain);
+
+/**
+ * em_dev_unregister_perf_domain() - Unregister Energy Model (EM) for a device
+ * @dev		: Device for which the EM is registered
+ *
+ * Unregister the EM for the specified @dev (but not a CPU device).
+ */
+void em_dev_unregister_perf_domain(struct device *dev)
+{
+	if (IS_ERR_OR_NULL(dev) || !dev->em_pd)
+		return;
+
+	if (_is_cpu_device(dev))
+		return;
+
+	/*
+	 * The mutex separates all register/unregister requests and protects
+	 * from potential clean-up/setup issues in the debugfs directories.
+	 * The debugfs directory name is the same as device's name.
+	 */
+	mutex_lock(&em_pd_mutex);
+	em_debug_remove_pd(dev);
+
+	kfree(dev->em_pd->table);
+	kfree(dev->em_pd);
+	dev->em_pd = NULL;
+	mutex_unlock(&em_pd_mutex);
+}
+EXPORT_SYMBOL_GPL(em_dev_unregister_perf_domain);
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index 6dbeedb7354c..e7aa57fb2fdc 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -67,6 +67,18 @@ bool freezer_test_done;
 
 static const struct platform_hibernation_ops *hibernation_ops;
 
+static atomic_t hibernate_atomic = ATOMIC_INIT(1);
+
+bool hibernate_acquire(void)
+{
+	return atomic_add_unless(&hibernate_atomic, -1, 0);
+}
+
+void hibernate_release(void)
+{
+	atomic_inc(&hibernate_atomic);
+}
+
 bool hibernation_available(void)
 {
 	return nohibernate == 0 && !security_locked_down(LOCKDOWN_HIBERNATION);
@@ -647,7 +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();
@@ -678,7 +690,7 @@ static int load_image_and_restore(void)
 	error = swsusp_read(&flags);
 	swsusp_close(FMODE_READ);
 	if (!error)
-		hibernation_restore(flags & SF_PLATFORM_MODE);
+		error = hibernation_restore(flags & SF_PLATFORM_MODE);
 
 	pr_err("Failed to load image, recovering.\n");
 	swsusp_free();
@@ -704,7 +716,7 @@ int hibernate(void)
 
 	lock_system_sleep();
 	/* The snapshot device should not be opened while we're running */
-	if (!atomic_add_unless(&snapshot_device_available, -1, 0)) {
+	if (!hibernate_acquire()) {
 		error = -EBUSY;
 		goto Unlock;
 	}
@@ -775,7 +787,7 @@ int hibernate(void)
  Exit:
 	__pm_notifier_call_chain(PM_POST_HIBERNATION, nr_calls, NULL);
 	pm_restore_console();
-	atomic_inc(&snapshot_device_available);
+	hibernate_release();
  Unlock:
 	unlock_system_sleep();
 	pr_info("hibernation exit\n");
@@ -783,6 +795,103 @@ int hibernate(void)
 	return error;
 }
 
+/**
+ * hibernate_quiet_exec - Execute a function with all devices frozen.
+ * @func: Function to execute.
+ * @data: Data pointer to pass to @func.
+ *
+ * Return the @func return value or an error code if it cannot be executed.
+ */
+int hibernate_quiet_exec(int (*func)(void *data), void *data)
+{
+	int error, nr_calls = 0;
+
+	lock_system_sleep();
+
+	if (!hibernate_acquire()) {
+		error = -EBUSY;
+		goto unlock;
+	}
+
+	pm_prepare_console();
+
+	error = __pm_notifier_call_chain(PM_HIBERNATION_PREPARE, -1, &nr_calls);
+	if (error) {
+		nr_calls--;
+		goto exit;
+	}
+
+	error = freeze_processes();
+	if (error)
+		goto exit;
+
+	lock_device_hotplug();
+
+	pm_suspend_clear_flags();
+
+	error = platform_begin(true);
+	if (error)
+		goto thaw;
+
+	error = freeze_kernel_threads();
+	if (error)
+		goto thaw;
+
+	error = dpm_prepare(PMSG_FREEZE);
+	if (error)
+		goto dpm_complete;
+
+	suspend_console();
+
+	error = dpm_suspend(PMSG_FREEZE);
+	if (error)
+		goto dpm_resume;
+
+	error = dpm_suspend_end(PMSG_FREEZE);
+	if (error)
+		goto dpm_resume;
+
+	error = platform_pre_snapshot(true);
+	if (error)
+		goto skip;
+
+	error = func(data);
+
+skip:
+	platform_finish(true);
+
+	dpm_resume_start(PMSG_THAW);
+
+dpm_resume:
+	dpm_resume(PMSG_THAW);
+
+	resume_console();
+
+dpm_complete:
+	dpm_complete(PMSG_THAW);
+
+	thaw_kernel_threads();
+
+thaw:
+	platform_end(true);
+
+	unlock_device_hotplug();
+
+	thaw_processes();
+
+exit:
+	__pm_notifier_call_chain(PM_POST_HIBERNATION, nr_calls, NULL);
+
+	pm_restore_console();
+
+	hibernate_release();
+
+unlock:
+	unlock_system_sleep();
+
+	return error;
+}
+EXPORT_SYMBOL_GPL(hibernate_quiet_exec);
 
 /**
  * software_resume - Resume from a saved hibernation image.
@@ -880,7 +989,7 @@ static int software_resume(void)
 		goto Unlock;
 
 	/* The snapshot device should not be opened while we're running */
-	if (!atomic_add_unless(&snapshot_device_available, -1, 0)) {
+	if (!hibernate_acquire()) {
 		error = -EBUSY;
 		swsusp_close(FMODE_READ);
 		goto Unlock;
@@ -898,13 +1007,20 @@ static int software_resume(void)
 	error = freeze_processes();
 	if (error)
 		goto Close_Finish;
+
+	error = freeze_kernel_threads();
+	if (error) {
+		thaw_processes();
+		goto Close_Finish;
+	}
+
 	error = load_image_and_restore();
 	thaw_processes();
  Finish:
 	__pm_notifier_call_chain(PM_POST_RESTORE, nr_calls, NULL);
 	pm_restore_console();
 	pr_info("resume failed (%d)\n", error);
-	atomic_inc(&snapshot_device_available);
+	hibernate_release();
 	/* For success case, the suspend path will release the lock */
  Unlock:
 	mutex_unlock(&system_transition_mutex);
@@ -1043,7 +1159,7 @@ power_attr(disk);
 static ssize_t resume_show(struct kobject *kobj, struct kobj_attribute *attr,
 			   char *buf)
 {
-	return sprintf(buf,"%d:%d\n", MAJOR(swsusp_resume_device),
+	return sprintf(buf, "%d:%d\n", MAJOR(swsusp_resume_device),
 		       MINOR(swsusp_resume_device));
 }
 
@@ -1143,7 +1259,7 @@ static ssize_t reserved_size_store(struct kobject *kobj,
 
 power_attr(reserved_size);
 
-static struct attribute * g[] = {
+static struct attribute *g[] = {
 	&disk_attr.attr,
 	&resume_offset_attr.attr,
 	&resume_attr.attr,
@@ -1171,7 +1287,7 @@ static int __init resume_setup(char *str)
 	if (noresume)
 		return 1;
 
-	strncpy( resume_file, str, 255 );
+	strncpy(resume_file, str, 255);
 	return 1;
 }
 
diff --git a/kernel/power/main.c b/kernel/power/main.c
index 69b7a8aeca3b..40f86ec4ab30 100644
--- a/kernel/power/main.c
+++ b/kernel/power/main.c
@@ -535,6 +535,13 @@ static ssize_t pm_debug_messages_store(struct kobject *kobj,
 
 power_attr(pm_debug_messages);
 
+static int __init pm_debug_messages_setup(char *str)
+{
+	pm_debug_messages_on = true;
+	return 1;
+}
+__setup("pm_debug_messages", pm_debug_messages_setup);
+
 /**
  * __pm_pr_dbg - Print a suspend debug message to the kernel log.
  * @defer: Whether or not to use printk_deferred() to print the message.
diff --git a/kernel/power/power.h b/kernel/power/power.h
index 7cdc64dc2373..32fc89ac96c3 100644
--- a/kernel/power/power.h
+++ b/kernel/power/power.h
@@ -32,7 +32,7 @@ static inline int init_header_complete(struct swsusp_info *info)
 	return arch_hibernation_header_save(info, MAX_ARCH_HEADER_SIZE);
 }
 
-static inline char *check_image_kernel(struct swsusp_info *info)
+static inline const char *check_image_kernel(struct swsusp_info *info)
 {
 	return arch_hibernation_header_restore(info) ?
 			"architecture specific data" : NULL;
@@ -154,8 +154,8 @@ extern int snapshot_write_next(struct snapshot_handle *handle);
 extern void snapshot_write_finalize(struct snapshot_handle *handle);
 extern int snapshot_image_loaded(struct snapshot_handle *handle);
 
-/* If unset, the snapshot device cannot be open. */
-extern atomic_t snapshot_device_available;
+extern bool hibernate_acquire(void);
+extern void hibernate_release(void);
 
 extern sector_t alloc_swapdev_block(int swap);
 extern void free_all_swap_pages(int swap);
diff --git a/kernel/power/poweroff.c b/kernel/power/poweroff.c
index 6d475281c730..562aa0e450ed 100644
--- a/kernel/power/poweroff.c
+++ b/kernel/power/poweroff.c
@@ -29,7 +29,7 @@ static void handle_poweroff(int key)
 	schedule_work_on(cpumask_first(cpu_online_mask), &poweroff_work);
 }
 
-static struct sysrq_key_op	sysrq_poweroff_op = {
+static const struct sysrq_key_op	sysrq_poweroff_op = {
 	.handler        = handle_poweroff,
 	.help_msg       = "poweroff(o)",
 	.action_msg     = "Power Off",
diff --git a/kernel/power/qos.c b/kernel/power/qos.c
index 83edf8698118..ec7e1e85923e 100644
--- a/kernel/power/qos.c
+++ b/kernel/power/qos.c
@@ -1,31 +1,21 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /*
- * This module exposes the interface to kernel space for specifying
- * QoS dependencies.  It provides infrastructure for registration of:
+ * Power Management Quality of Service (PM QoS) support base.
  *
- * Dependents on a QoS value : register requests
- * Watchers of QoS value : get notified when target QoS value changes
+ * Copyright (C) 2020 Intel Corporation
  *
- * This QoS design is best effort based.  Dependents register their QoS needs.
- * Watchers register to keep track of the current QoS needs of the system.
+ * Authors:
+ *	Mark Gross <mgross@linux.intel.com>
+ *	Rafael J. Wysocki <rafael.j.wysocki@intel.com>
  *
- * There are 3 basic classes of QoS parameter: latency, timeout, throughput
- * each have defined units:
- * latency: usec
- * timeout: usec <-- currently not used.
- * throughput: kbs (kilo byte / sec)
+ * Provided here is an interface for specifying PM QoS dependencies.  It allows
+ * entities depending on QoS constraints to register their requests which are
+ * aggregated as appropriate to produce effective constraints (target values)
+ * that can be monitored by entities needing to respect them, either by polling
+ * or through a built-in notification mechanism.
  *
- * There are lists of pm_qos_objects each one wrapping requests, notifiers
- *
- * User mode requests on a QOS parameter register themselves to the
- * subsystem by opening the device node /dev/... and writing there request to
- * the node.  As long as the process holds a file handle open to the node the
- * client continues to be accounted for.  Upon file release the usermode
- * request is removed and a new qos target is computed.  This way when the
- * request that the application has is cleaned up when closes the file
- * pointer or exits the pm_qos_object will get an opportunity to clean up.
- *
- * Mark Gross <mgross@linux.intel.com>
+ * In addition to the basic functionality, more specific interfaces for managing
+ * global CPU latency QoS requests and frequency QoS requests are provided.
  */
 
 /*#define DEBUG*/
@@ -54,56 +44,19 @@
  * or pm_qos_object list and pm_qos_objects need to happen with pm_qos_lock
  * held, taken with _irqsave.  One lock to rule them all
  */
-struct pm_qos_object {
-	struct pm_qos_constraints *constraints;
-	struct miscdevice pm_qos_power_miscdev;
-	char *name;
-};
-
 static DEFINE_SPINLOCK(pm_qos_lock);
 
-static struct pm_qos_object null_pm_qos;
-
-static BLOCKING_NOTIFIER_HEAD(cpu_dma_lat_notifier);
-static struct pm_qos_constraints cpu_dma_constraints = {
-	.list = PLIST_HEAD_INIT(cpu_dma_constraints.list),
-	.target_value = PM_QOS_CPU_DMA_LAT_DEFAULT_VALUE,
-	.default_value = PM_QOS_CPU_DMA_LAT_DEFAULT_VALUE,
-	.no_constraint_value = PM_QOS_CPU_DMA_LAT_DEFAULT_VALUE,
-	.type = PM_QOS_MIN,
-	.notifiers = &cpu_dma_lat_notifier,
-};
-static struct pm_qos_object cpu_dma_pm_qos = {
-	.constraints = &cpu_dma_constraints,
-	.name = "cpu_dma_latency",
-};
-
-static struct pm_qos_object *pm_qos_array[] = {
-	&null_pm_qos,
-	&cpu_dma_pm_qos,
-};
-
-static ssize_t pm_qos_power_write(struct file *filp, const char __user *buf,
-		size_t count, loff_t *f_pos);
-static ssize_t pm_qos_power_read(struct file *filp, char __user *buf,
-		size_t count, loff_t *f_pos);
-static int pm_qos_power_open(struct inode *inode, struct file *filp);
-static int pm_qos_power_release(struct inode *inode, struct file *filp);
-
-static const struct file_operations pm_qos_power_fops = {
-	.write = pm_qos_power_write,
-	.read = pm_qos_power_read,
-	.open = pm_qos_power_open,
-	.release = pm_qos_power_release,
-	.llseek = noop_llseek,
-};
-
-/* unlocked internal variant */
-static inline int pm_qos_get_value(struct pm_qos_constraints *c)
+/**
+ * pm_qos_read_value - Return the current effective constraint value.
+ * @c: List of PM QoS constraint requests.
+ */
+s32 pm_qos_read_value(struct pm_qos_constraints *c)
 {
-	struct plist_node *node;
-	int total_value = 0;
+	return READ_ONCE(c->target_value);
+}
 
+static int pm_qos_get_value(struct pm_qos_constraints *c)
+{
 	if (plist_head_empty(&c->list))
 		return c->no_constraint_value;
 
@@ -114,111 +67,42 @@ static inline int pm_qos_get_value(struct pm_qos_constraints *c)
 	case PM_QOS_MAX:
 		return plist_last(&c->list)->prio;
 
-	case PM_QOS_SUM:
-		plist_for_each(node, &c->list)
-			total_value += node->prio;
-
-		return total_value;
-
 	default:
-		/* runtime check for not using enum */
-		BUG();
+		WARN(1, "Unknown PM QoS type in %s\n", __func__);
 		return PM_QOS_DEFAULT_VALUE;
 	}
 }
 
-s32 pm_qos_read_value(struct pm_qos_constraints *c)
-{
-	return c->target_value;
-}
-
-static inline void pm_qos_set_value(struct pm_qos_constraints *c, s32 value)
+static void pm_qos_set_value(struct pm_qos_constraints *c, s32 value)
 {
-	c->target_value = value;
+	WRITE_ONCE(c->target_value, value);
 }
 
-static int pm_qos_debug_show(struct seq_file *s, void *unused)
-{
-	struct pm_qos_object *qos = (struct pm_qos_object *)s->private;
-	struct pm_qos_constraints *c;
-	struct pm_qos_request *req;
-	char *type;
-	unsigned long flags;
-	int tot_reqs = 0;
-	int active_reqs = 0;
-
-	if (IS_ERR_OR_NULL(qos)) {
-		pr_err("%s: bad qos param!\n", __func__);
-		return -EINVAL;
-	}
-	c = qos->constraints;
-	if (IS_ERR_OR_NULL(c)) {
-		pr_err("%s: Bad constraints on qos?\n", __func__);
-		return -EINVAL;
-	}
-
-	/* Lock to ensure we have a snapshot */
-	spin_lock_irqsave(&pm_qos_lock, flags);
-	if (plist_head_empty(&c->list)) {
-		seq_puts(s, "Empty!\n");
-		goto out;
-	}
-
-	switch (c->type) {
-	case PM_QOS_MIN:
-		type = "Minimum";
-		break;
-	case PM_QOS_MAX:
-		type = "Maximum";
-		break;
-	case PM_QOS_SUM:
-		type = "Sum";
-		break;
-	default:
-		type = "Unknown";
-	}
-
-	plist_for_each_entry(req, &c->list, node) {
-		char *state = "Default";
-
-		if ((req->node).prio != c->default_value) {
-			active_reqs++;
-			state = "Active";
-		}
-		tot_reqs++;
-		seq_printf(s, "%d: %d: %s\n", tot_reqs,
-			   (req->node).prio, state);
-	}
-
-	seq_printf(s, "Type=%s, Value=%d, Requests: active=%d / total=%d\n",
-		   type, pm_qos_get_value(c), active_reqs, tot_reqs);
-
-out:
-	spin_unlock_irqrestore(&pm_qos_lock, flags);
-	return 0;
-}
-
-DEFINE_SHOW_ATTRIBUTE(pm_qos_debug);
-
 /**
- * pm_qos_update_target - manages the constraints list and calls the notifiers
- *  if needed
- * @c: constraints data struct
- * @node: request to add to the list, to update or to remove
- * @action: action to take on the constraints list
- * @value: value of the request to add or update
+ * pm_qos_update_target - Update a list of PM QoS constraint requests.
+ * @c: List of PM QoS requests.
+ * @node: Target list entry.
+ * @action: Action to carry out (add, update or remove).
+ * @value: New request value for the target list entry.
  *
- * This function returns 1 if the aggregated constraint value has changed, 0
- *  otherwise.
+ * Update the given list of PM QoS constraint requests, @c, by carrying an
+ * @action involving the @node list entry and @value on it.
+ *
+ * The recognized values of @action are PM_QOS_ADD_REQ (store @value in @node
+ * and add it to the list), PM_QOS_UPDATE_REQ (remove @node from the list, store
+ * @value in it and add it to the list again), and PM_QOS_REMOVE_REQ (remove
+ * @node from the list, ignore @value).
+ *
+ * Return: 1 if the aggregate constraint value has changed, 0  otherwise.
  */
 int pm_qos_update_target(struct pm_qos_constraints *c, struct plist_node *node,
 			 enum pm_qos_req_action action, int value)
 {
-	unsigned long flags;
 	int prev_value, curr_value, new_value;
-	int ret;
+	unsigned long flags;
 
 	spin_lock_irqsave(&pm_qos_lock, flags);
+
 	prev_value = pm_qos_get_value(c);
 	if (value == PM_QOS_DEFAULT_VALUE)
 		new_value = c->default_value;
@@ -231,12 +115,11 @@ int pm_qos_update_target(struct pm_qos_constraints *c, struct plist_node *node,
 		break;
 	case PM_QOS_UPDATE_REQ:
 		/*
-		 * to change the list, we atomically remove, reinit
-		 * with new value and add, then see if the extremal
-		 * changed
+		 * To change the list, atomically remove, reinit with new value
+		 * 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);
@@ -252,16 +135,14 @@ int pm_qos_update_target(struct pm_qos_constraints *c, struct plist_node *node,
 	spin_unlock_irqrestore(&pm_qos_lock, flags);
 
 	trace_pm_qos_update_target(action, prev_value, curr_value);
-	if (prev_value != curr_value) {
-		ret = 1;
-		if (c->notifiers)
-			blocking_notifier_call_chain(c->notifiers,
-						     (unsigned long)curr_value,
-						     NULL);
-	} else {
-		ret = 0;
-	}
-	return ret;
+
+	if (prev_value == curr_value)
+		return 0;
+
+	if (c->notifiers)
+		blocking_notifier_call_chain(c->notifiers, curr_value, NULL);
+
+	return 1;
 }
 
 /**
@@ -283,14 +164,12 @@ static void pm_qos_flags_remove_req(struct pm_qos_flags *pqf,
 
 /**
  * pm_qos_update_flags - Update a set of PM QoS flags.
- * @pqf: Set of flags to update.
+ * @pqf: Set of PM QoS flags to update.
  * @req: Request to add to the set, to modify, or to remove from the set.
  * @action: Action to take on the set.
  * @val: Value of the request to add or modify.
  *
- * Update the given set of PM QoS flags and call notifiers if the aggregate
- * value has changed.  Returns 1 if the aggregate constraint value has changed,
- * 0 otherwise.
+ * Return: 1 if the aggregate constraint value has changed, 0 otherwise.
  */
 bool pm_qos_update_flags(struct pm_qos_flags *pqf,
 			 struct pm_qos_flags_request *req,
@@ -309,7 +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);
@@ -326,288 +205,180 @@ bool pm_qos_update_flags(struct pm_qos_flags *pqf,
 	spin_unlock_irqrestore(&pm_qos_lock, irqflags);
 
 	trace_pm_qos_update_flags(action, prev_value, curr_value);
-	return prev_value != curr_value;
-}
 
-/**
- * pm_qos_request - returns current system wide qos expectation
- * @pm_qos_class: identification of which qos value is requested
- *
- * This function returns the current target value.
- */
-int pm_qos_request(int pm_qos_class)
-{
-	return pm_qos_read_value(pm_qos_array[pm_qos_class]->constraints);
-}
-EXPORT_SYMBOL_GPL(pm_qos_request);
-
-int pm_qos_request_active(struct pm_qos_request *req)
-{
-	return req->pm_qos_class != 0;
+	return prev_value != curr_value;
 }
-EXPORT_SYMBOL_GPL(pm_qos_request_active);
 
-static void __pm_qos_update_request(struct pm_qos_request *req,
-			   s32 new_value)
-{
-	trace_pm_qos_update_request(req->pm_qos_class, new_value);
+#ifdef CONFIG_CPU_IDLE
+/* Definitions related to the CPU latency QoS. */
 
-	if (new_value != req->node.prio)
-		pm_qos_update_target(
-			pm_qos_array[req->pm_qos_class]->constraints,
-			&req->node, PM_QOS_UPDATE_REQ, new_value);
-}
+static struct pm_qos_constraints cpu_latency_constraints = {
+	.list = PLIST_HEAD_INIT(cpu_latency_constraints.list),
+	.target_value = PM_QOS_CPU_LATENCY_DEFAULT_VALUE,
+	.default_value = PM_QOS_CPU_LATENCY_DEFAULT_VALUE,
+	.no_constraint_value = PM_QOS_CPU_LATENCY_DEFAULT_VALUE,
+	.type = PM_QOS_MIN,
+};
 
 /**
- * pm_qos_work_fn - the timeout handler of pm_qos_update_request_timeout
- * @work: work struct for the delayed work (timeout)
- *
- * This cancels the timeout request by falling back to the default at timeout.
+ * cpu_latency_qos_limit - Return current system-wide CPU latency QoS limit.
  */
-static void pm_qos_work_fn(struct work_struct *work)
+s32 cpu_latency_qos_limit(void)
 {
-	struct pm_qos_request *req = container_of(to_delayed_work(work),
-						  struct pm_qos_request,
-						  work);
-
-	__pm_qos_update_request(req, PM_QOS_DEFAULT_VALUE);
+	return pm_qos_read_value(&cpu_latency_constraints);
 }
 
 /**
- * pm_qos_add_request - inserts new qos request into the list
- * @req: pointer to a preallocated handle
- * @pm_qos_class: identifies which list of qos request to use
- * @value: defines the qos request
+ * cpu_latency_qos_request_active - Check the given PM QoS request.
+ * @req: PM QoS request to check.
  *
- * This function inserts a new entry in the pm_qos_class list of requested qos
- * performance characteristics.  It recomputes the aggregate QoS expectations
- * for the pm_qos_class of parameters and initializes the pm_qos_request
- * handle.  Caller needs to save this handle for later use in updates and
- * removal.
+ * Return: 'true' if @req has been added to the CPU latency QoS list, 'false'
+ * otherwise.
  */
-
-void pm_qos_add_request(struct pm_qos_request *req,
-			int pm_qos_class, s32 value)
+bool cpu_latency_qos_request_active(struct pm_qos_request *req)
 {
-	if (!req) /*guard against callers passing in null */
-		return;
+	return req->qos == &cpu_latency_constraints;
+}
+EXPORT_SYMBOL_GPL(cpu_latency_qos_request_active);
 
-	if (pm_qos_request_active(req)) {
-		WARN(1, KERN_ERR "pm_qos_add_request() called for already added request\n");
-		return;
-	}
-	req->pm_qos_class = pm_qos_class;
-	INIT_DELAYED_WORK(&req->work, pm_qos_work_fn);
-	trace_pm_qos_add_request(pm_qos_class, value);
-	pm_qos_update_target(pm_qos_array[pm_qos_class]->constraints,
-			     &req->node, PM_QOS_ADD_REQ, value);
+static void cpu_latency_qos_apply(struct pm_qos_request *req,
+				  enum pm_qos_req_action action, s32 value)
+{
+	int ret = pm_qos_update_target(req->qos, &req->node, action, value);
+	if (ret > 0)
+		wake_up_all_idle_cpus();
 }
-EXPORT_SYMBOL_GPL(pm_qos_add_request);
 
 /**
- * pm_qos_update_request - modifies an existing qos request
- * @req : handle to list element holding a pm_qos request to use
- * @value: defines the qos request
+ * cpu_latency_qos_add_request - Add new CPU latency QoS request.
+ * @req: Pointer to a preallocated handle.
+ * @value: Requested constraint value.
  *
- * Updates an existing qos request for the pm_qos_class of parameters along
- * with updating the target pm_qos_class value.
+ * Use @value to initialize the request handle pointed to by @req, insert it as
+ * a new entry to the CPU latency QoS list and recompute the effective QoS
+ * constraint for that list.
  *
- * Attempts are made to make this code callable on hot code paths.
+ * Callers need to save the handle for later use in updates and removal of the
+ * QoS request represented by it.
  */
-void pm_qos_update_request(struct pm_qos_request *req,
-			   s32 new_value)
+void cpu_latency_qos_add_request(struct pm_qos_request *req, s32 value)
 {
-	if (!req) /*guard against callers passing in null */
+	if (!req)
 		return;
 
-	if (!pm_qos_request_active(req)) {
-		WARN(1, KERN_ERR "pm_qos_update_request() called for unknown object\n");
+	if (cpu_latency_qos_request_active(req)) {
+		WARN(1, KERN_ERR "%s called for already added request\n", __func__);
 		return;
 	}
 
-	cancel_delayed_work_sync(&req->work);
-	__pm_qos_update_request(req, new_value);
+	trace_pm_qos_add_request(value);
+
+	req->qos = &cpu_latency_constraints;
+	cpu_latency_qos_apply(req, PM_QOS_ADD_REQ, value);
 }
-EXPORT_SYMBOL_GPL(pm_qos_update_request);
+EXPORT_SYMBOL_GPL(cpu_latency_qos_add_request);
 
 /**
- * pm_qos_update_request_timeout - modifies an existing qos request temporarily.
- * @req : handle to list element holding a pm_qos request to use
- * @new_value: defines the temporal qos request
- * @timeout_us: the effective duration of this qos request in usecs.
+ * cpu_latency_qos_update_request - Modify existing CPU latency QoS request.
+ * @req : QoS request to update.
+ * @new_value: New requested constraint value.
  *
- * After timeout_us, this qos request is cancelled automatically.
+ * Use @new_value to update the QoS request represented by @req in the CPU
+ * latency QoS list along with updating the effective constraint value for that
+ * list.
  */
-void pm_qos_update_request_timeout(struct pm_qos_request *req, s32 new_value,
-				   unsigned long timeout_us)
+void cpu_latency_qos_update_request(struct pm_qos_request *req, s32 new_value)
 {
 	if (!req)
 		return;
-	if (WARN(!pm_qos_request_active(req),
-		 "%s called for unknown object.", __func__))
+
+	if (!cpu_latency_qos_request_active(req)) {
+		WARN(1, KERN_ERR "%s called for unknown object\n", __func__);
 		return;
+	}
 
-	cancel_delayed_work_sync(&req->work);
+	trace_pm_qos_update_request(new_value);
 
-	trace_pm_qos_update_request_timeout(req->pm_qos_class,
-					    new_value, timeout_us);
-	if (new_value != req->node.prio)
-		pm_qos_update_target(
-			pm_qos_array[req->pm_qos_class]->constraints,
-			&req->node, PM_QOS_UPDATE_REQ, new_value);
+	if (new_value == req->node.prio)
+		return;
 
-	schedule_delayed_work(&req->work, usecs_to_jiffies(timeout_us));
+	cpu_latency_qos_apply(req, PM_QOS_UPDATE_REQ, new_value);
 }
+EXPORT_SYMBOL_GPL(cpu_latency_qos_update_request);
 
 /**
- * pm_qos_remove_request - modifies an existing qos request
- * @req: handle to request list element
+ * cpu_latency_qos_remove_request - Remove existing CPU latency QoS request.
+ * @req: QoS request to remove.
  *
- * Will remove pm qos request from the list of constraints and
- * recompute the current target value for the pm_qos_class.  Call this
- * on slow code paths.
+ * Remove the CPU latency QoS request represented by @req from the CPU latency
+ * QoS list along with updating the effective constraint value for that list.
  */
-void pm_qos_remove_request(struct pm_qos_request *req)
+void cpu_latency_qos_remove_request(struct pm_qos_request *req)
 {
-	if (!req) /*guard against callers passing in null */
+	if (!req)
 		return;
-		/* silent return to keep pcm code cleaner */
 
-	if (!pm_qos_request_active(req)) {
-		WARN(1, KERN_ERR "pm_qos_remove_request() called for unknown object\n");
+	if (!cpu_latency_qos_request_active(req)) {
+		WARN(1, KERN_ERR "%s called for unknown object\n", __func__);
 		return;
 	}
 
-	cancel_delayed_work_sync(&req->work);
+	trace_pm_qos_remove_request(PM_QOS_DEFAULT_VALUE);
 
-	trace_pm_qos_remove_request(req->pm_qos_class, PM_QOS_DEFAULT_VALUE);
-	pm_qos_update_target(pm_qos_array[req->pm_qos_class]->constraints,
-			     &req->node, PM_QOS_REMOVE_REQ,
-			     PM_QOS_DEFAULT_VALUE);
+	cpu_latency_qos_apply(req, PM_QOS_REMOVE_REQ, PM_QOS_DEFAULT_VALUE);
 	memset(req, 0, sizeof(*req));
 }
-EXPORT_SYMBOL_GPL(pm_qos_remove_request);
-
-/**
- * pm_qos_add_notifier - sets notification entry for changes to target value
- * @pm_qos_class: identifies which qos target changes should be notified.
- * @notifier: notifier block managed by caller.
- *
- * will register the notifier into a notification chain that gets called
- * upon changes to the pm_qos_class target value.
- */
-int pm_qos_add_notifier(int pm_qos_class, struct notifier_block *notifier)
-{
-	int retval;
-
-	retval = blocking_notifier_chain_register(
-			pm_qos_array[pm_qos_class]->constraints->notifiers,
-			notifier);
-
-	return retval;
-}
-EXPORT_SYMBOL_GPL(pm_qos_add_notifier);
-
-/**
- * pm_qos_remove_notifier - deletes notification entry from chain.
- * @pm_qos_class: identifies which qos target changes are notified.
- * @notifier: notifier block to be removed.
- *
- * will remove the notifier from the notification chain that gets called
- * upon changes to the pm_qos_class target value.
- */
-int pm_qos_remove_notifier(int pm_qos_class, struct notifier_block *notifier)
-{
-	int retval;
+EXPORT_SYMBOL_GPL(cpu_latency_qos_remove_request);
 
-	retval = blocking_notifier_chain_unregister(
-			pm_qos_array[pm_qos_class]->constraints->notifiers,
-			notifier);
+/* User space interface to the CPU latency QoS via misc device. */
 
-	return retval;
-}
-EXPORT_SYMBOL_GPL(pm_qos_remove_notifier);
-
-/* User space interface to PM QoS classes via misc devices */
-static int register_pm_qos_misc(struct pm_qos_object *qos, struct dentry *d)
+static int cpu_latency_qos_open(struct inode *inode, struct file *filp)
 {
-	qos->pm_qos_power_miscdev.minor = MISC_DYNAMIC_MINOR;
-	qos->pm_qos_power_miscdev.name = qos->name;
-	qos->pm_qos_power_miscdev.fops = &pm_qos_power_fops;
-
-	debugfs_create_file(qos->name, S_IRUGO, d, (void *)qos,
-			    &pm_qos_debug_fops);
+	struct pm_qos_request *req;
 
-	return misc_register(&qos->pm_qos_power_miscdev);
-}
+	req = kzalloc(sizeof(*req), GFP_KERNEL);
+	if (!req)
+		return -ENOMEM;
 
-static int find_pm_qos_object_by_minor(int minor)
-{
-	int pm_qos_class;
+	cpu_latency_qos_add_request(req, PM_QOS_DEFAULT_VALUE);
+	filp->private_data = req;
 
-	for (pm_qos_class = PM_QOS_CPU_DMA_LATENCY;
-		pm_qos_class < PM_QOS_NUM_CLASSES; pm_qos_class++) {
-		if (minor ==
-			pm_qos_array[pm_qos_class]->pm_qos_power_miscdev.minor)
-			return pm_qos_class;
-	}
-	return -1;
+	return 0;
 }
 
-static int pm_qos_power_open(struct inode *inode, struct file *filp)
+static int cpu_latency_qos_release(struct inode *inode, struct file *filp)
 {
-	long pm_qos_class;
-
-	pm_qos_class = find_pm_qos_object_by_minor(iminor(inode));
-	if (pm_qos_class >= PM_QOS_CPU_DMA_LATENCY) {
-		struct pm_qos_request *req = kzalloc(sizeof(*req), GFP_KERNEL);
-		if (!req)
-			return -ENOMEM;
-
-		pm_qos_add_request(req, pm_qos_class, PM_QOS_DEFAULT_VALUE);
-		filp->private_data = req;
-
-		return 0;
-	}
-	return -EPERM;
-}
+	struct pm_qos_request *req = filp->private_data;
 
-static int pm_qos_power_release(struct inode *inode, struct file *filp)
-{
-	struct pm_qos_request *req;
+	filp->private_data = NULL;
 
-	req = filp->private_data;
-	pm_qos_remove_request(req);
+	cpu_latency_qos_remove_request(req);
 	kfree(req);
 
 	return 0;
 }
 
-
-static ssize_t pm_qos_power_read(struct file *filp, char __user *buf,
-		size_t count, loff_t *f_pos)
+static ssize_t cpu_latency_qos_read(struct file *filp, char __user *buf,
+				    size_t count, loff_t *f_pos)
 {
-	s32 value;
-	unsigned long flags;
 	struct pm_qos_request *req = filp->private_data;
+	unsigned long flags;
+	s32 value;
 
-	if (!req)
-		return -EINVAL;
-	if (!pm_qos_request_active(req))
+	if (!req || !cpu_latency_qos_request_active(req))
 		return -EINVAL;
 
 	spin_lock_irqsave(&pm_qos_lock, flags);
-	value = pm_qos_get_value(pm_qos_array[req->pm_qos_class]->constraints);
+	value = pm_qos_get_value(&cpu_latency_constraints);
 	spin_unlock_irqrestore(&pm_qos_lock, flags);
 
 	return simple_read_from_buffer(buf, count, f_pos, &value, sizeof(s32));
 }
 
-static ssize_t pm_qos_power_write(struct file *filp, const char __user *buf,
-		size_t count, loff_t *f_pos)
+static ssize_t cpu_latency_qos_write(struct file *filp, const char __user *buf,
+				     size_t count, loff_t *f_pos)
 {
 	s32 value;
-	struct pm_qos_request *req;
 
 	if (count == sizeof(s32)) {
 		if (copy_from_user(&value, buf, sizeof(s32)))
@@ -620,36 +391,38 @@ static ssize_t pm_qos_power_write(struct file *filp, const char __user *buf,
 			return ret;
 	}
 
-	req = filp->private_data;
-	pm_qos_update_request(req, value);
+	cpu_latency_qos_update_request(filp->private_data, value);
 
 	return count;
 }
 
+static const struct file_operations cpu_latency_qos_fops = {
+	.write = cpu_latency_qos_write,
+	.read = cpu_latency_qos_read,
+	.open = cpu_latency_qos_open,
+	.release = cpu_latency_qos_release,
+	.llseek = noop_llseek,
+};
 
-static int __init pm_qos_power_init(void)
-{
-	int ret = 0;
-	int i;
-	struct dentry *d;
-
-	BUILD_BUG_ON(ARRAY_SIZE(pm_qos_array) != PM_QOS_NUM_CLASSES);
+static struct miscdevice cpu_latency_qos_miscdev = {
+	.minor = MISC_DYNAMIC_MINOR,
+	.name = "cpu_dma_latency",
+	.fops = &cpu_latency_qos_fops,
+};
 
-	d = debugfs_create_dir("pm_qos", NULL);
+static int __init cpu_latency_qos_init(void)
+{
+	int ret;
 
-	for (i = PM_QOS_CPU_DMA_LATENCY; i < PM_QOS_NUM_CLASSES; i++) {
-		ret = register_pm_qos_misc(pm_qos_array[i], d);
-		if (ret < 0) {
-			pr_err("%s: %s setup failed\n",
-			       __func__, pm_qos_array[i]->name);
-			return ret;
-		}
-	}
+	ret = misc_register(&cpu_latency_qos_miscdev);
+	if (ret < 0)
+		pr_err("%s: %s setup failed\n", __func__,
+		       cpu_latency_qos_miscdev.name);
 
 	return ret;
 }
-
-late_initcall(pm_qos_power_init);
+late_initcall(cpu_latency_qos_init);
+#endif /* CONFIG_CPU_IDLE */
 
 /* Definitions related to the frequency QoS below. */
 
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index d82b7b88d616..d25749bce7cf 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -34,7 +34,6 @@
 
 #include <linux/uaccess.h>
 #include <asm/mmu_context.h>
-#include <asm/pgtable.h>
 #include <asm/tlbflush.h>
 #include <asm/io.h>
 
@@ -1664,7 +1663,7 @@ static unsigned long minimum_image_size(unsigned long saveable)
 {
 	unsigned long size;
 
-	size = global_node_page_state(NR_SLAB_RECLAIMABLE)
+	size = global_node_page_state_pages(NR_SLAB_RECLAIMABLE_B)
 		+ global_node_page_state(NR_ACTIVE_ANON)
 		+ global_node_page_state(NR_INACTIVE_ANON)
 		+ global_node_page_state(NR_ACTIVE_FILE)
@@ -1744,9 +1743,6 @@ int hibernate_preallocate_memory(void)
 	count += highmem;
 	count -= totalreserve_pages;
 
-	/* Add number of pages required for page keys (s390 only). */
-	size += page_key_additional_pages(saveable);
-
 	/* Compute the maximum number of saveable pages to leave in memory. */
 	max_size = (count - (size + PAGES_FOR_IO)) / 2
 			- 2 * DIV_ROUND_UP(reserved_size, PAGE_SIZE);
@@ -2027,7 +2023,7 @@ static int init_header_complete(struct swsusp_info *info)
 	return 0;
 }
 
-static char *check_image_kernel(struct swsusp_info *info)
+static const char *check_image_kernel(struct swsusp_info *info)
 {
 	if (info->version_code != LINUX_VERSION_CODE)
 		return "kernel version";
@@ -2075,8 +2071,6 @@ static inline void pack_pfns(unsigned long *buf, struct memory_bitmap *bm)
 		buf[j] = memory_bm_next_pfn(bm);
 		if (unlikely(buf[j] == BM_END_OF_MAP))
 			break;
-		/* Save page key for data page (s390 only). */
-		page_key_read(buf + j);
 	}
 }
 
@@ -2182,7 +2176,7 @@ static void mark_unsafe_pages(struct memory_bitmap *bm)
 
 static int check_header(struct swsusp_info *info)
 {
-	char *reason;
+	const char *reason;
 
 	reason = check_image_kernel(info);
 	if (!reason && info->num_physpages != get_num_physpages())
@@ -2226,9 +2220,6 @@ static int unpack_orig_pfns(unsigned long *buf, struct memory_bitmap *bm)
 		if (unlikely(buf[j] == BM_END_OF_MAP))
 			break;
 
-		/* Extract and buffer page key for data page (s390 only). */
-		page_key_memorize(buf + j);
-
 		if (pfn_valid(buf[j]) && memory_bm_pfn_present(bm, buf[j]))
 			memory_bm_set_bit(bm, buf[j]);
 		else
@@ -2623,11 +2614,6 @@ int snapshot_write_next(struct snapshot_handle *handle)
 		if (error)
 			return error;
 
-		/* Allocate buffer for page keys. */
-		error = page_key_alloc(nr_copy_pages);
-		if (error)
-			return error;
-
 		hibernate_restore_protection_begin();
 	} else if (handle->cur <= nr_meta_pages + 1) {
 		error = unpack_orig_pfns(buffer, &copy_bm);
@@ -2649,8 +2635,6 @@ int snapshot_write_next(struct snapshot_handle *handle)
 		}
 	} else {
 		copy_last_highmem_page();
-		/* Restore page key for data page (s390 only). */
-		page_key_write(handle->buffer);
 		hibernate_restore_protect_page(handle->buffer);
 		handle->buffer = get_buffer(&orig_bm, &ca);
 		if (IS_ERR(handle->buffer))
@@ -2673,9 +2657,6 @@ int snapshot_write_next(struct snapshot_handle *handle)
 void snapshot_write_finalize(struct snapshot_handle *handle)
 {
 	copy_last_highmem_page();
-	/* Restore page key for data page (s390 only). */
-	page_key_write(handle->buffer);
-	page_key_free();
 	hibernate_restore_protect_page(handle->buffer);
 	/* Do that only if we have loaded the image entirely */
 	if (handle->cur > 1 && handle->cur > nr_meta_pages + nr_copy_pages) {
diff --git a/kernel/power/swap.c b/kernel/power/swap.c
index ca0fcb5ced71..01e2858b5fe3 100644
--- a/kernel/power/swap.c
+++ b/kernel/power/swap.c
@@ -1590,7 +1590,7 @@ int swsusp_unmark(void)
 }
 #endif
 
-static int swsusp_header_init(void)
+static int __init swsusp_header_init(void)
 {
 	swsusp_header = (struct swsusp_header*) __get_free_page(GFP_KERNEL);
 	if (!swsusp_header)
diff --git a/kernel/power/user.c b/kernel/power/user.c
index 77438954cc2b..d5eedc2baa2a 100644
--- a/kernel/power/user.c
+++ b/kernel/power/user.c
@@ -27,8 +27,6 @@
 #include "power.h"
 
 
-#define SNAPSHOT_MINOR	231
-
 static struct snapshot_data {
 	struct snapshot_handle handle;
 	int swap;
@@ -37,9 +35,13 @@ static struct snapshot_data {
 	bool ready;
 	bool platform_support;
 	bool free_bitmaps;
+	struct inode *bd_inode;
 } snapshot_state;
 
-atomic_t snapshot_device_available = ATOMIC_INIT(1);
+int is_hibernate_resume_dev(const struct inode *bd_inode)
+{
+	return hibernation_available() && snapshot_state.bd_inode == bd_inode;
+}
 
 static int snapshot_open(struct inode *inode, struct file *filp)
 {
@@ -51,13 +53,13 @@ static int snapshot_open(struct inode *inode, struct file *filp)
 
 	lock_system_sleep();
 
-	if (!atomic_add_unless(&snapshot_device_available, -1, 0)) {
+	if (!hibernate_acquire()) {
 		error = -EBUSY;
 		goto Unlock;
 	}
 
 	if ((filp->f_flags & O_ACCMODE) == O_RDWR) {
-		atomic_inc(&snapshot_device_available);
+		hibernate_release();
 		error = -ENOSYS;
 		goto Unlock;
 	}
@@ -94,11 +96,12 @@ static int snapshot_open(struct inode *inode, struct file *filp)
 			__pm_notifier_call_chain(PM_POST_RESTORE, nr_calls, NULL);
 	}
 	if (error)
-		atomic_inc(&snapshot_device_available);
+		hibernate_release();
 
 	data->frozen = false;
 	data->ready = false;
 	data->platform_support = false;
+	data->bd_inode = NULL;
 
  Unlock:
 	unlock_system_sleep();
@@ -114,6 +117,7 @@ static int snapshot_release(struct inode *inode, struct file *filp)
 
 	swsusp_free();
 	data = filp->private_data;
+	data->bd_inode = NULL;
 	free_all_swap_pages(data->swap);
 	if (data->frozen) {
 		pm_restore_gfp_mask();
@@ -124,7 +128,7 @@ static int snapshot_release(struct inode *inode, struct file *filp)
 	}
 	pm_notifier_call_chain(data->mode == O_RDONLY ?
 			PM_POST_HIBERNATION : PM_POST_RESTORE);
-	atomic_inc(&snapshot_device_available);
+	hibernate_release();
 
 	unlock_system_sleep();
 
@@ -198,6 +202,54 @@ unlock:
 	return res;
 }
 
+struct compat_resume_swap_area {
+	compat_loff_t offset;
+	u32 dev;
+} __packed;
+
+static int snapshot_set_swap_area(struct snapshot_data *data,
+		void __user *argp)
+{
+	struct block_device *bdev;
+	sector_t offset;
+	dev_t swdev;
+
+	if (swsusp_swap_in_use())
+		return -EPERM;
+
+	if (in_compat_syscall()) {
+		struct compat_resume_swap_area swap_area;
+
+		if (copy_from_user(&swap_area, argp, sizeof(swap_area)))
+			return -EFAULT;
+		swdev = new_decode_dev(swap_area.dev);
+		offset = swap_area.offset;
+	} else {
+		struct resume_swap_area swap_area;
+
+		if (copy_from_user(&swap_area, argp, sizeof(swap_area)))
+			return -EFAULT;
+		swdev = new_decode_dev(swap_area.dev);
+		offset = swap_area.offset;
+	}
+
+	/*
+	 * User space encodes device types as two-byte values,
+	 * so we need to recode them
+	 */
+	if (!swdev) {
+		data->swap = -1;
+		return -EINVAL;
+	}
+	data->swap = swap_type_of(swdev, offset, &bdev);
+	if (data->swap < 0)
+		return -ENODEV;
+
+	data->bd_inode = bdev->bd_inode;
+	bdput(bdev);
+	return 0;
+}
+
 static long snapshot_ioctl(struct file *filp, unsigned int cmd,
 							unsigned long arg)
 {
@@ -353,34 +405,7 @@ static long snapshot_ioctl(struct file *filp, unsigned int cmd,
 		break;
 
 	case SNAPSHOT_SET_SWAP_AREA:
-		if (swsusp_swap_in_use()) {
-			error = -EPERM;
-		} else {
-			struct resume_swap_area swap_area;
-			dev_t swdev;
-
-			error = copy_from_user(&swap_area, (void __user *)arg,
-					sizeof(struct resume_swap_area));
-			if (error) {
-				error = -EFAULT;
-				break;
-			}
-
-			/*
-			 * User space encodes device types as two-byte values,
-			 * so we need to recode them
-			 */
-			swdev = new_decode_dev(swap_area.dev);
-			if (swdev) {
-				offset = swap_area.offset;
-				data->swap = swap_type_of(swdev, offset, NULL);
-				if (data->swap < 0)
-					error = -ENODEV;
-			} else {
-				data->swap = -1;
-				error = -EINVAL;
-			}
-		}
+		error = snapshot_set_swap_area(data, (void __user *)arg);
 		break;
 
 	default:
@@ -395,12 +420,6 @@ static long snapshot_ioctl(struct file *filp, unsigned int cmd,
 }
 
 #ifdef CONFIG_COMPAT
-
-struct compat_resume_swap_area {
-	compat_loff_t offset;
-	u32 dev;
-} __packed;
-
 static long
 snapshot_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 {
@@ -409,49 +428,15 @@ snapshot_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 	switch (cmd) {
 	case SNAPSHOT_GET_IMAGE_SIZE:
 	case SNAPSHOT_AVAIL_SWAP_SIZE:
-	case SNAPSHOT_ALLOC_SWAP_PAGE: {
-		compat_loff_t __user *uoffset = compat_ptr(arg);
-		loff_t offset;
-		mm_segment_t old_fs;
-		int err;
-
-		old_fs = get_fs();
-		set_fs(KERNEL_DS);
-		err = snapshot_ioctl(file, cmd, (unsigned long) &offset);
-		set_fs(old_fs);
-		if (!err && put_user(offset, uoffset))
-			err = -EFAULT;
-		return err;
-	}
-
+	case SNAPSHOT_ALLOC_SWAP_PAGE:
 	case SNAPSHOT_CREATE_IMAGE:
+	case SNAPSHOT_SET_SWAP_AREA:
 		return snapshot_ioctl(file, cmd,
 				      (unsigned long) compat_ptr(arg));
-
-	case SNAPSHOT_SET_SWAP_AREA: {
-		struct compat_resume_swap_area __user *u_swap_area =
-			compat_ptr(arg);
-		struct resume_swap_area swap_area;
-		mm_segment_t old_fs;
-		int err;
-
-		err = get_user(swap_area.offset, &u_swap_area->offset);
-		err |= get_user(swap_area.dev, &u_swap_area->dev);
-		if (err)
-			return -EFAULT;
-		old_fs = get_fs();
-		set_fs(KERNEL_DS);
-		err = snapshot_ioctl(file, SNAPSHOT_SET_SWAP_AREA,
-				     (unsigned long) &swap_area);
-		set_fs(old_fs);
-		return err;
-	}
-
 	default:
 		return snapshot_ioctl(file, cmd, arg);
 	}
 }
-
 #endif /* CONFIG_COMPAT */
 
 static const struct file_operations snapshot_fops = {
diff --git a/kernel/printk/console_cmdline.h b/kernel/printk/console_cmdline.h
index 11f19c466af5..3ca74ad391d6 100644
--- a/kernel/printk/console_cmdline.h
+++ b/kernel/printk/console_cmdline.h
@@ -6,6 +6,7 @@ struct console_cmdline
 {
 	char	name[16];			/* Name of the driver	    */
 	int	index;				/* Minor dev. to use	    */
+	bool	user_specified;			/* Specified by command line vs. platform */
 	char	*options;			/* Options for the driver   */
 #ifdef CONFIG_A11Y_BRAILLE_CONSOLE
 	char	*brl_options;			/* Options for braille driver */
diff --git a/kernel/printk/internal.h b/kernel/printk/internal.h
index c8e6ab689d42..660f9a6bf73a 100644
--- a/kernel/printk/internal.h
+++ b/kernel/printk/internal.h
@@ -6,9 +6,11 @@
 
 #ifdef CONFIG_PRINTK
 
-#define PRINTK_SAFE_CONTEXT_MASK	 0x3fffffff
-#define PRINTK_NMI_DIRECT_CONTEXT_MASK	 0x40000000
-#define PRINTK_NMI_CONTEXT_MASK		 0x80000000
+#define PRINTK_SAFE_CONTEXT_MASK	0x007ffffff
+#define PRINTK_NMI_DIRECT_CONTEXT_MASK	0x008000000
+#define PRINTK_NMI_CONTEXT_MASK		0xff0000000
+
+#define PRINTK_NMI_CONTEXT_OFFSET	0x010000000
 
 extern raw_spinlock_t logbuf_lock;
 
@@ -23,6 +25,9 @@ __printf(1, 0) int vprintk_func(const char *fmt, va_list args);
 void __printk_safe_enter(void);
 void __printk_safe_exit(void);
 
+void printk_safe_init(void);
+bool printk_percpu_data_ready(void);
+
 #define printk_safe_enter_irqsave(flags)	\
 	do {					\
 		local_irq_save(flags);		\
@@ -64,4 +69,6 @@ __printf(1, 0) int vprintk_func(const char *fmt, va_list args) { return 0; }
 #define printk_safe_enter_irq() local_irq_disable()
 #define printk_safe_exit_irq() local_irq_enable()
 
+static inline void printk_safe_init(void) { }
+static inline bool printk_percpu_data_ready(void) { return false; }
 #endif /* CONFIG_PRINTK */
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index fada22dc4ab6..9b75f6bfc333 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -35,7 +35,6 @@
 #include <linux/memblock.h>
 #include <linux/syscalls.h>
 #include <linux/crash_core.h>
-#include <linux/kdb.h>
 #include <linux/ratelimit.h>
 #include <linux/kmsg_dump.h>
 #include <linux/syslog.h>
@@ -173,7 +172,7 @@ __setup("printk.devkmsg=", control_devkmsg);
 char devkmsg_log_str[DEVKMSG_STR_MAX_SIZE] = "ratelimit";
 
 int devkmsg_sysctl_set_loglvl(struct ctl_table *table, int write,
-			      void __user *buffer, size_t *lenp, loff_t *ppos)
+			      void *buffer, size_t *lenp, loff_t *ppos)
 {
 	char old_str[DEVKMSG_STR_MAX_SIZE];
 	unsigned int old;
@@ -280,6 +279,7 @@ static struct console *exclusive_console;
 static struct console_cmdline console_cmdline[MAX_CMDLINECONSOLES];
 
 static int preferred_console = -1;
+static bool has_preferred_console;
 int console_set_on_cmdline;
 EXPORT_SYMBOL(console_set_on_cmdline);
 
@@ -460,6 +460,18 @@ static char __log_buf[__LOG_BUF_LEN] __aligned(LOG_ALIGN);
 static char *log_buf = __log_buf;
 static u32 log_buf_len = __LOG_BUF_LEN;
 
+/*
+ * We cannot access per-CPU data (e.g. per-CPU flush irq_work) before
+ * per_cpu_areas are initialised. This variable is set to true when
+ * it's safe to access per-CPU data.
+ */
+static bool __printk_percpu_data_ready __read_mostly;
+
+bool printk_percpu_data_ready(void)
+{
+	return __printk_percpu_data_ready;
+}
+
 /* Return log buffer address */
 char *log_buf_addr_get(void)
 {
@@ -931,6 +943,14 @@ out:
 	return ret;
 }
 
+/*
+ * Be careful when modifying this function!!!
+ *
+ * Only few operations are supported because the device works only with the
+ * entire variable length messages (records). Non-standard values are
+ * returned in the other cases and has been this way for quite some time.
+ * User space applications might depend on this behavior.
+ */
 static loff_t devkmsg_llseek(struct file *file, loff_t offset, int whence)
 {
 	struct devkmsg_user *user = file->private_data;
@@ -1146,12 +1166,28 @@ static void __init log_buf_add_cpu(void)
 static inline void log_buf_add_cpu(void) {}
 #endif /* CONFIG_SMP */
 
+static void __init set_percpu_data_ready(void)
+{
+	printk_safe_init();
+	/* Make sure we set this flag only after printk_safe() init is done */
+	barrier();
+	__printk_percpu_data_ready = true;
+}
+
 void __init setup_log_buf(int early)
 {
 	unsigned long flags;
 	char *new_log_buf;
 	unsigned int free;
 
+	/*
+	 * Some archs call setup_log_buf() multiple times - first is very
+	 * early, e.g. from setup_arch(), and second - when percpu_areas
+	 * are initialised.
+	 */
+	if (!early)
+		set_percpu_data_ready();
+
 	if (log_buf != __log_buf)
 		return;
 
@@ -1772,9 +1808,6 @@ static void call_console_drivers(const char *ext_text, size_t ext_len,
 
 	trace_console_rcuidle(text, len);
 
-	if (!console_drivers)
-		return;
-
 	for_each_console(con) {
 		if (exclusive_console && con != exclusive_console)
 			continue;
@@ -2011,18 +2044,7 @@ EXPORT_SYMBOL(vprintk);
 
 int vprintk_default(const char *fmt, va_list args)
 {
-	int r;
-
-#ifdef CONFIG_KGDB_KDB
-	/* Allow to pass printk() to kdb but avoid a recursion. */
-	if (unlikely(kdb_trap_printk && kdb_printf_cpu < 0)) {
-		r = vkdb_printf(KDB_MSGSRC_PRINTK, fmt, args);
-		return r;
-	}
-#endif
-	r = vprintk_emit(0, LOGLEVEL_DEFAULT, NULL, 0, fmt, args);
-
-	return r;
+	return vprintk_emit(0, LOGLEVEL_DEFAULT, NULL, 0, fmt, args);
 }
 EXPORT_SYMBOL_GPL(vprintk_default);
 
@@ -2115,7 +2137,7 @@ asmlinkage __visible void early_printk(const char *fmt, ...)
 #endif
 
 static int __add_preferred_console(char *name, int idx, char *options,
-				   char *brl_options)
+				   char *brl_options, bool user_specified)
 {
 	struct console_cmdline *c;
 	int i;
@@ -2130,6 +2152,8 @@ static int __add_preferred_console(char *name, int idx, char *options,
 		if (strcmp(c->name, name) == 0 && c->index == idx) {
 			if (!brl_options)
 				preferred_console = i;
+			if (user_specified)
+				c->user_specified = true;
 			return 0;
 		}
 	}
@@ -2139,6 +2163,7 @@ static int __add_preferred_console(char *name, int idx, char *options,
 		preferred_console = i;
 	strlcpy(c->name, name, sizeof(c->name));
 	c->options = options;
+	c->user_specified = user_specified;
 	braille_set_options(c, brl_options);
 
 	c->index = idx;
@@ -2165,6 +2190,9 @@ static int __init console_setup(char *str)
 	char *s, *options, *brl_options = NULL;
 	int idx;
 
+	if (str[0] == 0)
+		return 1;
+
 	if (_braille_console_setup(&str, &brl_options))
 		return 1;
 
@@ -2193,7 +2221,7 @@ static int __init console_setup(char *str)
 	idx = simple_strtoul(s, NULL, 10);
 	*s = 0;
 
-	__add_preferred_console(buf, idx, options, brl_options);
+	__add_preferred_console(buf, idx, options, brl_options, true);
 	console_set_on_cmdline = 1;
 	return 1;
 }
@@ -2214,7 +2242,7 @@ __setup("console=", console_setup);
  */
 int add_preferred_console(char *name, int idx, char *options)
 {
-	return __add_preferred_console(name, idx, options, NULL);
+	return __add_preferred_console(name, idx, options, NULL, false);
 }
 
 bool console_suspend_enabled = true;
@@ -2413,9 +2441,9 @@ again:
 		printk_safe_enter_irqsave(flags);
 		raw_spin_lock(&logbuf_lock);
 		if (console_seq < log_first_seq) {
-			len = sprintf(text,
-				      "** %llu printk messages dropped **\n",
-				      log_first_seq - console_seq);
+			len = snprintf(text, sizeof(text),
+				       "** %llu printk messages dropped **\n",
+				       log_first_seq - console_seq);
 
 			/* messages are gone, move to first one */
 			console_seq = log_first_seq;
@@ -2627,6 +2655,63 @@ static int __init keep_bootcon_setup(char *str)
 early_param("keep_bootcon", keep_bootcon_setup);
 
 /*
+ * This is called by register_console() to try to match
+ * the newly registered console with any of the ones selected
+ * by either the command line or add_preferred_console() and
+ * setup/enable it.
+ *
+ * Care need to be taken with consoles that are statically
+ * enabled such as netconsole
+ */
+static int try_enable_new_console(struct console *newcon, bool user_specified)
+{
+	struct console_cmdline *c;
+	int i, err;
+
+	for (i = 0, c = console_cmdline;
+	     i < MAX_CMDLINECONSOLES && c->name[0];
+	     i++, c++) {
+		if (c->user_specified != user_specified)
+			continue;
+		if (!newcon->match ||
+		    newcon->match(newcon, c->name, c->index, c->options) != 0) {
+			/* default matching */
+			BUILD_BUG_ON(sizeof(c->name) != sizeof(newcon->name));
+			if (strcmp(c->name, newcon->name) != 0)
+				continue;
+			if (newcon->index >= 0 &&
+			    newcon->index != c->index)
+				continue;
+			if (newcon->index < 0)
+				newcon->index = c->index;
+
+			if (_braille_register_console(newcon, c))
+				return 0;
+
+			if (newcon->setup &&
+			    (err = newcon->setup(newcon, c->options)) != 0)
+				return err;
+		}
+		newcon->flags |= CON_ENABLED;
+		if (i == preferred_console) {
+			newcon->flags |= CON_CONSDEV;
+			has_preferred_console = true;
+		}
+		return 0;
+	}
+
+	/*
+	 * Some consoles, such as pstore and netconsole, can be enabled even
+	 * without matching. Accept the pre-enabled consoles only when match()
+	 * and setup() had a chance to be called.
+	 */
+	if (newcon->flags & CON_ENABLED && c->user_specified ==	user_specified)
+		return 0;
+
+	return -ENOENT;
+}
+
+/*
  * The console driver calls this routine during kernel initialization
  * to register the console printing procedure with printk() and to
  * print any messages that were printed by the kernel before the
@@ -2647,25 +2732,21 @@ early_param("keep_bootcon", keep_bootcon_setup);
  */
 void register_console(struct console *newcon)
 {
-	int i;
 	unsigned long flags;
 	struct console *bcon = NULL;
-	struct console_cmdline *c;
-	static bool has_preferred;
+	int err;
 
-	if (console_drivers)
-		for_each_console(bcon)
-			if (WARN(bcon == newcon,
-					"console '%s%d' already registered\n",
-					bcon->name, bcon->index))
-				return;
+	for_each_console(bcon) {
+		if (WARN(bcon == newcon, "console '%s%d' already registered\n",
+					 bcon->name, bcon->index))
+			return;
+	}
 
 	/*
 	 * before we register a new CON_BOOT console, make sure we don't
 	 * already have a valid console
 	 */
-	if (console_drivers && newcon->flags & CON_BOOT) {
-		/* find the last or real console */
+	if (newcon->flags & CON_BOOT) {
 		for_each_console(bcon) {
 			if (!(bcon->flags & CON_BOOT)) {
 				pr_info("Too late to register bootconsole %s%d\n",
@@ -2678,15 +2759,15 @@ void register_console(struct console *newcon)
 	if (console_drivers && console_drivers->flags & CON_BOOT)
 		bcon = console_drivers;
 
-	if (!has_preferred || bcon || !console_drivers)
-		has_preferred = preferred_console >= 0;
+	if (!has_preferred_console || bcon || !console_drivers)
+		has_preferred_console = preferred_console >= 0;
 
 	/*
 	 *	See if we want to use this console driver. If we
 	 *	didn't select a console we take the first one
 	 *	that registers here.
 	 */
-	if (!has_preferred) {
+	if (!has_preferred_console) {
 		if (newcon->index < 0)
 			newcon->index = 0;
 		if (newcon->setup == NULL ||
@@ -2694,47 +2775,20 @@ void register_console(struct console *newcon)
 			newcon->flags |= CON_ENABLED;
 			if (newcon->device) {
 				newcon->flags |= CON_CONSDEV;
-				has_preferred = true;
+				has_preferred_console = true;
 			}
 		}
 	}
 
-	/*
-	 *	See if this console matches one we selected on
-	 *	the command line.
-	 */
-	for (i = 0, c = console_cmdline;
-	     i < MAX_CMDLINECONSOLES && c->name[0];
-	     i++, c++) {
-		if (!newcon->match ||
-		    newcon->match(newcon, c->name, c->index, c->options) != 0) {
-			/* default matching */
-			BUILD_BUG_ON(sizeof(c->name) != sizeof(newcon->name));
-			if (strcmp(c->name, newcon->name) != 0)
-				continue;
-			if (newcon->index >= 0 &&
-			    newcon->index != c->index)
-				continue;
-			if (newcon->index < 0)
-				newcon->index = c->index;
-
-			if (_braille_register_console(newcon, c))
-				return;
+	/* See if this console matches one we selected on the command line */
+	err = try_enable_new_console(newcon, true);
 
-			if (newcon->setup &&
-			    newcon->setup(newcon, c->options) != 0)
-				break;
-		}
+	/* If not, try to match against the platform default(s) */
+	if (err == -ENOENT)
+		err = try_enable_new_console(newcon, false);
 
-		newcon->flags |= CON_ENABLED;
-		if (i == preferred_console) {
-			newcon->flags |= CON_CONSDEV;
-			has_preferred = true;
-		}
-		break;
-	}
-
-	if (!(newcon->flags & CON_ENABLED))
+	/* printk() messages are not printed to the Braille console. */
+	if (err || newcon->flags & CON_BRL)
 		return;
 
 	/*
@@ -2756,6 +2810,8 @@ void register_console(struct console *newcon)
 		console_drivers = newcon;
 		if (newcon->next)
 			newcon->next->flags &= ~CON_CONSDEV;
+		/* Ensure this flag is always set for the head of the list */
+		newcon->flags |= CON_CONSDEV;
 	} else {
 		newcon->next = console_drivers->next;
 		console_drivers->next = newcon;
@@ -2813,7 +2869,7 @@ EXPORT_SYMBOL(register_console);
 
 int unregister_console(struct console *console)
 {
-        struct console *a, *b;
+	struct console *con;
 	int res;
 
 	pr_info("%sconsole [%s%d] disabled\n",
@@ -2821,26 +2877,30 @@ int unregister_console(struct console *console)
 		console->name, console->index);
 
 	res = _braille_unregister_console(console);
-	if (res)
+	if (res < 0)
 		return res;
+	if (res > 0)
+		return 0;
 
-	res = 1;
+	res = -ENODEV;
 	console_lock();
 	if (console_drivers == console) {
 		console_drivers=console->next;
 		res = 0;
-	} else if (console_drivers) {
-		for (a=console_drivers->next, b=console_drivers ;
-		     a; b=a, a=b->next) {
-			if (a == console) {
-				b->next = a->next;
+	} else {
+		for_each_console(con) {
+			if (con->next == console) {
+				con->next = console->next;
 				res = 0;
 				break;
 			}
 		}
 	}
 
-	if (!res && (console->flags & CON_EXTENDED))
+	if (res)
+		goto out_disable_unlock;
+
+	if (console->flags & CON_EXTENDED)
 		nr_ext_console_drivers--;
 
 	/*
@@ -2853,6 +2913,16 @@ int unregister_console(struct console *console)
 	console->flags &= ~CON_ENABLED;
 	console_unlock();
 	console_sysfs_notify();
+
+	if (console->exit)
+		res = console->exit(console);
+
+	return res;
+
+out_disable_unlock:
+	console->flags &= ~CON_ENABLED;
+	console_unlock();
+
 	return res;
 }
 EXPORT_SYMBOL(unregister_console);
@@ -2966,6 +3036,9 @@ static DEFINE_PER_CPU(struct irq_work, wake_up_klogd_work) = {
 
 void wake_up_klogd(void)
 {
+	if (!printk_percpu_data_ready())
+		return;
+
 	preempt_disable();
 	if (waitqueue_active(&log_wait)) {
 		this_cpu_or(printk_pending, PRINTK_PENDING_WAKEUP);
@@ -2976,6 +3049,9 @@ void wake_up_klogd(void)
 
 void defer_console_output(void)
 {
+	if (!printk_percpu_data_ready())
+		return;
+
 	preempt_disable();
 	__this_cpu_or(printk_pending, PRINTK_PENDING_OUTPUT);
 	irq_work_queue(this_cpu_ptr(&wake_up_klogd_work));
@@ -3101,6 +3177,23 @@ EXPORT_SYMBOL_GPL(kmsg_dump_unregister);
 static bool always_kmsg_dump;
 module_param_named(always_kmsg_dump, always_kmsg_dump, bool, S_IRUGO | S_IWUSR);
 
+const char *kmsg_dump_reason_str(enum kmsg_dump_reason reason)
+{
+	switch (reason) {
+	case KMSG_DUMP_PANIC:
+		return "Panic";
+	case KMSG_DUMP_OOPS:
+		return "Oops";
+	case KMSG_DUMP_EMERG:
+		return "Emergency";
+	case KMSG_DUMP_SHUTDOWN:
+		return "Shutdown";
+	default:
+		return "Unknown";
+	}
+}
+EXPORT_SYMBOL_GPL(kmsg_dump_reason_str);
+
 /**
  * kmsg_dump - dump kernel log to kernel message dumpers.
  * @reason: the reason (oops, panic etc) for dumping
@@ -3114,12 +3207,19 @@ void kmsg_dump(enum kmsg_dump_reason reason)
 	struct kmsg_dumper *dumper;
 	unsigned long flags;
 
-	if ((reason > KMSG_DUMP_OOPS) && !always_kmsg_dump)
-		return;
-
 	rcu_read_lock();
 	list_for_each_entry_rcu(dumper, &dump_list, list) {
-		if (dumper->max_reason && reason > dumper->max_reason)
+		enum kmsg_dump_reason max_reason = dumper->max_reason;
+
+		/*
+		 * If client has not provided a specific max_reason, default
+		 * to KMSG_DUMP_OOPS, unless always_kmsg_dump was set.
+		 */
+		if (max_reason == KMSG_DUMP_UNDEF) {
+			max_reason = always_kmsg_dump ? KMSG_DUMP_MAX :
+							KMSG_DUMP_OOPS;
+		}
+		if (reason > max_reason)
 			continue;
 
 		/* initialize iterator with data about the stored records */
@@ -3317,7 +3417,7 @@ out:
 EXPORT_SYMBOL_GPL(kmsg_dump_get_buffer);
 
 /**
- * kmsg_dump_rewind_nolock - reset the interator (unlocked version)
+ * kmsg_dump_rewind_nolock - reset the iterator (unlocked version)
  * @dumper: registered kmsg dumper
  *
  * Reset the dumper's iterator so that kmsg_dump_get_line() and
@@ -3335,7 +3435,7 @@ void kmsg_dump_rewind_nolock(struct kmsg_dumper *dumper)
 }
 
 /**
- * kmsg_dump_rewind - reset the interator
+ * kmsg_dump_rewind - reset the iterator
  * @dumper: registered kmsg dumper
  *
  * Reset the dumper's iterator so that kmsg_dump_get_line() and
diff --git a/kernel/printk/printk_safe.c b/kernel/printk/printk_safe.c
index 08a8bf778990..e95d2a517244 100644
--- a/kernel/printk/printk_safe.c
+++ b/kernel/printk/printk_safe.c
@@ -6,10 +6,12 @@
 #include <linux/preempt.h>
 #include <linux/spinlock.h>
 #include <linux/debug_locks.h>
+#include <linux/kdb.h>
 #include <linux/smp.h>
 #include <linux/cpumask.h>
 #include <linux/irq_work.h>
 #include <linux/printk.h>
+#include <linux/kprobes.h>
 
 #include "internal.h"
 
@@ -27,7 +29,6 @@
  * There are situations when we want to make sure that all buffers
  * were handled or when IRQs are blocked.
  */
-static int printk_safe_irq_ready __read_mostly;
 
 #define SAFE_LOG_BUF_LEN ((1 << CONFIG_PRINTK_SAFE_LOG_BUF_SHIFT) -	\
 				sizeof(atomic_t) -			\
@@ -51,7 +52,7 @@ static DEFINE_PER_CPU(struct printk_safe_seq_buf, nmi_print_seq);
 /* Get flushed in a more safe context. */
 static void queue_flush_work(struct printk_safe_seq_buf *s)
 {
-	if (printk_safe_irq_ready)
+	if (printk_percpu_data_ready())
 		irq_work_queue(&s->work);
 }
 
@@ -294,14 +295,14 @@ static __printf(1, 0) int vprintk_nmi(const char *fmt, va_list args)
 	return printk_safe_log_store(s, fmt, args);
 }
 
-void notrace printk_nmi_enter(void)
+void noinstr printk_nmi_enter(void)
 {
-	this_cpu_or(printk_context, PRINTK_NMI_CONTEXT_MASK);
+	this_cpu_add(printk_context, PRINTK_NMI_CONTEXT_OFFSET);
 }
 
-void notrace printk_nmi_exit(void)
+void noinstr printk_nmi_exit(void)
 {
-	this_cpu_and(printk_context, ~PRINTK_NMI_CONTEXT_MASK);
+	this_cpu_sub(printk_context, PRINTK_NMI_CONTEXT_OFFSET);
 }
 
 /*
@@ -360,6 +361,12 @@ void __printk_safe_exit(void)
 
 __printf(1, 0) int vprintk_func(const char *fmt, va_list args)
 {
+#ifdef CONFIG_KGDB_KDB
+	/* Allow to pass printk() to kdb but avoid a recursion. */
+	if (unlikely(kdb_trap_printk && kdb_printf_cpu < 0))
+		return vkdb_printf(KDB_MSGSRC_PRINTK, fmt, args);
+#endif
+
 	/*
 	 * Try to use the main logbuf even in NMI. But avoid calling console
 	 * drivers that might have their own locks.
@@ -402,14 +409,6 @@ void __init printk_safe_init(void)
 #endif
 	}
 
-	/*
-	 * In the highly unlikely event that a NMI were to trigger at
-	 * this moment. Make sure IRQ work is set up before this
-	 * variable is set.
-	 */
-	barrier();
-	printk_safe_irq_ready = 1;
-
 	/* Flush pending messages that did not have scheduled IRQ works. */
 	printk_safe_flush();
 }
diff --git a/kernel/rcu/Kconfig b/kernel/rcu/Kconfig
index 1cc940fef17c..0ebe15a84985 100644
--- a/kernel/rcu/Kconfig
+++ b/kernel/rcu/Kconfig
@@ -70,13 +70,37 @@ config TREE_SRCU
 	help
 	  This option selects the full-fledged version of SRCU.
 
+config TASKS_RCU_GENERIC
+	def_bool TASKS_RCU || TASKS_RUDE_RCU || TASKS_TRACE_RCU
+	select SRCU
+	help
+	  This option enables generic infrastructure code supporting
+	  task-based RCU implementations.  Not for manual selection.
+
 config TASKS_RCU
 	def_bool PREEMPTION
-	select SRCU
 	help
 	  This option enables a task-based RCU implementation that uses
 	  only voluntary context switch (not preemption!), idle, and
-	  user-mode execution as quiescent states.
+	  user-mode execution as quiescent states.  Not for manual selection.
+
+config TASKS_RUDE_RCU
+	def_bool 0
+	help
+	  This option enables a task-based RCU implementation that uses
+	  only context switch (including preemption) and user-mode
+	  execution as quiescent states.  It forces IPIs and context
+	  switches on all online CPUs, including idle ones, so use
+	  with caution.
+
+config TASKS_TRACE_RCU
+	def_bool 0
+	help
+	  This option enables a task-based RCU implementation that uses
+	  explicit rcu_read_lock_trace() read-side markers, and allows
+	  these readers to appear in the idle loop as well as on the CPU
+	  hotplug code paths.  It can force IPIs on online CPUs, including
+	  idle ones, so use with caution.
 
 config RCU_STALL_COMMON
 	def_bool TREE_RCU
@@ -210,4 +234,22 @@ config RCU_NOCB_CPU
 	  Say Y here if you want to help to debug reduced OS jitter.
 	  Say N here if you are unsure.
 
+config TASKS_TRACE_RCU_READ_MB
+	bool "Tasks Trace RCU readers use memory barriers in user and idle"
+	depends on RCU_EXPERT
+	default PREEMPT_RT || NR_CPUS < 8
+	help
+	  Use this option to further reduce the number of IPIs sent
+	  to CPUs executing in userspace or idle during tasks trace
+	  RCU grace periods.  Given that a reasonable setting of
+	  the rcupdate.rcu_task_ipi_delay kernel boot parameter
+	  eliminates such IPIs for many workloads, proper setting
+	  of this Kconfig option is important mostly for aggressive
+	  real-time installations and for battery-powered devices,
+	  hence the default chosen above.
+
+	  Say Y here if you hate IPIs.
+	  Say N here if you hate read-side memory barriers.
+	  Take the default if you are unsure.
+
 endmenu # "RCU Subsystem"
diff --git a/kernel/rcu/Kconfig.debug b/kernel/rcu/Kconfig.debug
index 4aa02eee8f6c..3cf6132a4bb9 100644
--- a/kernel/rcu/Kconfig.debug
+++ b/kernel/rcu/Kconfig.debug
@@ -29,6 +29,8 @@ config RCU_PERF_TEST
 	select TORTURE_TEST
 	select SRCU
 	select TASKS_RCU
+	select TASKS_RUDE_RCU
+	select TASKS_TRACE_RCU
 	default n
 	help
 	  This option provides a kernel module that runs performance
@@ -46,6 +48,8 @@ config RCU_TORTURE_TEST
 	select TORTURE_TEST
 	select SRCU
 	select TASKS_RCU
+	select TASKS_RUDE_RCU
+	select TASKS_TRACE_RCU
 	default n
 	help
 	  This option provides a kernel module that runs torture tests
@@ -57,6 +61,25 @@ config RCU_TORTURE_TEST
 	  Say M if you want the RCU torture tests to build as a module.
 	  Say N if you are unsure.
 
+config RCU_REF_SCALE_TEST
+	tristate "Scalability tests for read-side synchronization (RCU and others)"
+	depends on DEBUG_KERNEL
+	select TORTURE_TEST
+	select SRCU
+	select TASKS_RCU
+	select TASKS_RUDE_RCU
+	select TASKS_TRACE_RCU
+	default n
+	help
+	  This option provides a kernel module that runs performance tests
+	  useful comparing RCU with various read-side synchronization mechanisms.
+	  The kernel module may be built after the fact on the running kernel to be
+	  tested, if desired.
+
+	  Say Y here if you want these performance tests built into the kernel.
+	  Say M if you want to build it as a module instead.
+	  Say N if you are unsure.
+
 config RCU_CPU_STALL_TIMEOUT
 	int "RCU CPU stall timeout in seconds"
 	depends on RCU_STALL_COMMON
diff --git a/kernel/rcu/Makefile b/kernel/rcu/Makefile
index 82d5fba48b2f..95f5117ef8da 100644
--- a/kernel/rcu/Makefile
+++ b/kernel/rcu/Makefile
@@ -3,11 +3,16 @@
 # and is generally not a function of system call inputs.
 KCOV_INSTRUMENT := n
 
+ifeq ($(CONFIG_KCSAN),y)
+KBUILD_CFLAGS += -g -fno-omit-frame-pointer
+endif
+
 obj-y += update.o sync.o
 obj-$(CONFIG_TREE_SRCU) += srcutree.o
 obj-$(CONFIG_TINY_SRCU) += srcutiny.o
 obj-$(CONFIG_RCU_TORTURE_TEST) += rcutorture.o
 obj-$(CONFIG_RCU_PERF_TEST) += rcuperf.o
+obj-$(CONFIG_RCU_REF_SCALE_TEST) += refscale.o
 obj-$(CONFIG_TREE_RCU) += tree.o
 obj-$(CONFIG_TINY_RCU) += tiny.o
 obj-$(CONFIG_RCU_NEED_SEGCBLIST) += rcu_segcblist.o
diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h
index 05f936ed167a..cf66a3ccd757 100644
--- a/kernel/rcu/rcu.h
+++ b/kernel/rcu/rcu.h
@@ -198,6 +198,13 @@ static inline void debug_rcu_head_unqueue(struct rcu_head *head)
 }
 #endif	/* #else !CONFIG_DEBUG_OBJECTS_RCU_HEAD */
 
+extern int rcu_cpu_stall_suppress_at_boot;
+
+static inline bool rcu_stall_is_suppressed_at_boot(void)
+{
+	return rcu_cpu_stall_suppress_at_boot && !rcu_inkernel_boot_has_ended();
+}
+
 #ifdef CONFIG_RCU_STALL_COMMON
 
 extern int rcu_cpu_stall_ftrace_dump;
@@ -205,6 +212,11 @@ extern int rcu_cpu_stall_suppress;
 extern int rcu_cpu_stall_timeout;
 int rcu_jiffies_till_stall_check(void);
 
+static inline bool rcu_stall_is_suppressed(void)
+{
+	return rcu_stall_is_suppressed_at_boot() || rcu_cpu_stall_suppress;
+}
+
 #define rcu_ftrace_dump_stall_suppress() \
 do { \
 	if (!rcu_cpu_stall_suppress) \
@@ -218,6 +230,11 @@ do { \
 } while (0)
 
 #else /* #endif #ifdef CONFIG_RCU_STALL_COMMON */
+
+static inline bool rcu_stall_is_suppressed(void)
+{
+	return rcu_stall_is_suppressed_at_boot();
+}
 #define rcu_ftrace_dump_stall_suppress()
 #define rcu_ftrace_dump_stall_unsuppress()
 #endif /* #ifdef CONFIG_RCU_STALL_COMMON */
@@ -325,7 +342,8 @@ static inline void rcu_init_levelspread(int *levelspread, const int *levelcnt)
  * Iterate over all possible CPUs in a leaf RCU node.
  */
 #define for_each_leaf_node_possible_cpu(rnp, cpu) \
-	for ((cpu) = cpumask_next((rnp)->grplo - 1, cpu_possible_mask); \
+	for (WARN_ON_ONCE(!rcu_is_leaf_node(rnp)), \
+	     (cpu) = cpumask_next((rnp)->grplo - 1, cpu_possible_mask); \
 	     (cpu) <= rnp->grphi; \
 	     (cpu) = cpumask_next((cpu), cpu_possible_mask))
 
@@ -335,7 +353,8 @@ static inline void rcu_init_levelspread(int *levelspread, const int *levelcnt)
 #define rcu_find_next_bit(rnp, cpu, mask) \
 	((rnp)->grplo + find_next_bit(&(mask), BITS_PER_LONG, (cpu)))
 #define for_each_leaf_node_cpu_mask(rnp, cpu, mask) \
-	for ((cpu) = rcu_find_next_bit((rnp), 0, (mask)); \
+	for (WARN_ON_ONCE(!rcu_is_leaf_node(rnp)), \
+	     (cpu) = rcu_find_next_bit((rnp), 0, (mask)); \
 	     (cpu) <= rnp->grphi; \
 	     (cpu) = rcu_find_next_bit((rnp), (cpu) + 1 - (rnp->grplo), (mask)))
 
@@ -412,6 +431,7 @@ bool rcu_gp_is_expedited(void);  /* Internal RCU use. */
 void rcu_expedite_gp(void);
 void rcu_unexpedite_gp(void);
 void rcupdate_announce_bootup_oddness(void);
+void show_rcu_tasks_gp_kthreads(void);
 void rcu_request_urgent_qs_task(struct task_struct *t);
 #endif /* #else #ifdef CONFIG_TINY_RCU */
 
@@ -422,6 +442,8 @@ void rcu_request_urgent_qs_task(struct task_struct *t);
 enum rcutorture_type {
 	RCU_FLAVOR,
 	RCU_TASKS_FLAVOR,
+	RCU_TASKS_RUDE_FLAVOR,
+	RCU_TASKS_TRACING_FLAVOR,
 	RCU_TRIVIAL_FLAVOR,
 	SRCU_FLAVOR,
 	INVALID_RCU_FLAVOR
@@ -435,6 +457,7 @@ void do_trace_rcu_torture_read(const char *rcutorturename,
 			       unsigned long secs,
 			       unsigned long c_old,
 			       unsigned long c);
+void rcu_gp_set_torture_wait(int duration);
 #else
 static inline void rcutorture_get_gp_data(enum rcutorture_type test_type,
 					  int *flags, unsigned long *gp_seq)
@@ -452,6 +475,7 @@ void do_trace_rcu_torture_read(const char *rcutorturename,
 #define do_trace_rcu_torture_read(rcutorturename, rhp, secs, c_old, c) \
 	do { } while (0)
 #endif
+static inline void rcu_gp_set_torture_wait(int duration) { }
 #endif
 
 #if IS_ENABLED(CONFIG_RCU_TORTURE_TEST) || IS_MODULE(CONFIG_RCU_TORTURE_TEST)
@@ -479,6 +503,7 @@ void srcutorture_get_gp_data(enum rcutorture_type test_type,
 #endif
 
 #ifdef CONFIG_TINY_RCU
+static inline bool rcu_dynticks_zero_in_eqs(int cpu, int *vp) { return false; }
 static inline unsigned long rcu_get_gp_seq(void) { return 0; }
 static inline unsigned long rcu_exp_batches_completed(void) { return 0; }
 static inline unsigned long
@@ -488,6 +513,7 @@ static inline void show_rcu_gp_kthreads(void) { }
 static inline int rcu_get_gp_kthreads_prio(void) { return 0; }
 static inline void rcu_fwd_progress_check(unsigned long j) { }
 #else /* #ifdef CONFIG_TINY_RCU */
+bool rcu_dynticks_zero_in_eqs(int cpu, int *vp);
 unsigned long rcu_get_gp_seq(void);
 unsigned long rcu_exp_batches_completed(void);
 unsigned long srcu_batches_completed(struct srcu_struct *sp);
diff --git a/kernel/rcu/rcu_segcblist.c b/kernel/rcu/rcu_segcblist.c
index 5f4fd3b8777c..9a0f66133b4b 100644
--- a/kernel/rcu/rcu_segcblist.c
+++ b/kernel/rcu/rcu_segcblist.c
@@ -182,7 +182,7 @@ void rcu_segcblist_offload(struct rcu_segcblist *rsclp)
 bool rcu_segcblist_ready_cbs(struct rcu_segcblist *rsclp)
 {
 	return rcu_segcblist_is_enabled(rsclp) &&
-	       &rsclp->head != rsclp->tails[RCU_DONE_TAIL];
+	       &rsclp->head != READ_ONCE(rsclp->tails[RCU_DONE_TAIL]);
 }
 
 /*
@@ -381,8 +381,6 @@ void rcu_segcblist_insert_pend_cbs(struct rcu_segcblist *rsclp,
 		return; /* Nothing to do. */
 	WRITE_ONCE(*rsclp->tails[RCU_NEXT_TAIL], rclp->head);
 	WRITE_ONCE(rsclp->tails[RCU_NEXT_TAIL], rclp->tail);
-	rclp->head = NULL;
-	rclp->tail = &rclp->head;
 }
 
 /*
diff --git a/kernel/rcu/rcuperf.c b/kernel/rcu/rcuperf.c
index da94b89cd531..21448d3374e2 100644
--- a/kernel/rcu/rcuperf.c
+++ b/kernel/rcu/rcuperf.c
@@ -12,6 +12,7 @@
 #include <linux/types.h>
 #include <linux/kernel.h>
 #include <linux/init.h>
+#include <linux/mm.h>
 #include <linux/module.h>
 #include <linux/kthread.h>
 #include <linux/err.h>
@@ -68,6 +69,11 @@ MODULE_AUTHOR("Paul E. McKenney <paulmck@linux.ibm.com>");
  *	value specified by nr_cpus for a read-only test.
  *
  * Various other use cases may of course be specified.
+ *
+ * Note that this test's readers are intended only as a test load for
+ * the writers.  The reader performance statistics will be overly
+ * pessimistic due to the per-critical-section interrupt disabling,
+ * test-end checks, and the pair of calls through pointers.
  */
 
 #ifdef MODULE
@@ -87,6 +93,7 @@ torture_param(bool, shutdown, RCUPERF_SHUTDOWN,
 torture_param(int, verbose, 1, "Enable verbose debugging printk()s");
 torture_param(int, writer_holdoff, 0, "Holdoff (us) between GPs, zero to disable");
 torture_param(int, kfree_rcu_test, 0, "Do we run a kfree_rcu() perf test?");
+torture_param(int, kfree_mult, 1, "Multiple of kfree_obj size to allocate.");
 
 static char *perf_type = "rcu";
 module_param(perf_type, charp, 0444);
@@ -307,8 +314,10 @@ static void rcu_perf_wait_shutdown(void)
 }
 
 /*
- * RCU perf reader kthread.  Repeatedly does empty RCU read-side
- * critical section, minimizing update-side interference.
+ * RCU perf reader kthread.  Repeatedly does empty RCU read-side critical
+ * section, minimizing update-side interference.  However, the point of
+ * this test is not to evaluate reader performance, but instead to serve
+ * as a test load for update-side performance testing.
  */
 static int
 rcu_perf_reader(void *arg)
@@ -352,7 +361,6 @@ rcu_perf_writer(void *arg)
 	int i_max;
 	long me = (long)arg;
 	struct rcu_head *rhp = NULL;
-	struct sched_param sp;
 	bool started = false, done = false, alldone = false;
 	u64 t;
 	u64 *wdp;
@@ -361,8 +369,7 @@ rcu_perf_writer(void *arg)
 	VERBOSE_PERFOUT_STRING("rcu_perf_writer task started");
 	WARN_ON(!wdpp);
 	set_cpus_allowed_ptr(current, cpumask_of(me % nr_cpu_ids));
-	sp.sched_priority = 1;
-	sched_setscheduler_nocheck(current, SCHED_FIFO, &sp);
+	sched_set_fifo_low(current);
 
 	if (holdoff)
 		schedule_timeout_uninterruptible(holdoff * HZ);
@@ -418,9 +425,7 @@ retry:
 			started = true;
 		if (!done && i >= MIN_MEAS) {
 			done = true;
-			sp.sched_priority = 0;
-			sched_setscheduler_nocheck(current,
-						   SCHED_NORMAL, &sp);
+			sched_set_normal(current, 0);
 			pr_alert("%s%s rcu_perf_writer %ld has %d measurements\n",
 				 perf_type, PERF_FLAG, me, MIN_MEAS);
 			if (atomic_inc_return(&n_rcu_perf_writer_finished) >=
@@ -574,11 +579,8 @@ static int compute_real(int n)
 static int
 rcu_perf_shutdown(void *arg)
 {
-	do {
-		wait_event(shutdown_wq,
-			   atomic_read(&n_rcu_perf_writer_finished) >=
-			   nrealwriters);
-	} while (atomic_read(&n_rcu_perf_writer_finished) < nrealwriters);
+	wait_event(shutdown_wq,
+		   atomic_read(&n_rcu_perf_writer_finished) >= nrealwriters);
 	smp_mb(); /* Wake before output. */
 	rcu_perf_cleanup();
 	kernel_power_off();
@@ -611,6 +613,7 @@ kfree_perf_thread(void *arg)
 	long me = (long)arg;
 	struct kfree_obj *alloc_ptr;
 	u64 start_time, end_time;
+	long long mem_begin, mem_during = 0;
 
 	VERBOSE_PERFOUT_STRING("kfree_perf_thread task started");
 	set_cpus_allowed_ptr(current, cpumask_of(me % nr_cpu_ids));
@@ -626,8 +629,14 @@ kfree_perf_thread(void *arg)
 	}
 
 	do {
+		if (!mem_during) {
+			mem_during = mem_begin = si_mem_available();
+		} else if (loop % (kfree_loops / 4) == 0) {
+			mem_during = (mem_during + si_mem_available()) / 2;
+		}
+
 		for (i = 0; i < kfree_alloc_num; i++) {
-			alloc_ptr = kmalloc(sizeof(struct kfree_obj), GFP_KERNEL);
+			alloc_ptr = kmalloc(kfree_mult * sizeof(struct kfree_obj), GFP_KERNEL);
 			if (!alloc_ptr)
 				return -ENOMEM;
 
@@ -645,9 +654,11 @@ kfree_perf_thread(void *arg)
 		else
 			b_rcu_gp_test_finished = cur_ops->get_gp_seq();
 
-		pr_alert("Total time taken by all kfree'ers: %llu ns, loops: %d, batches: %ld\n",
+		pr_alert("Total time taken by all kfree'ers: %llu ns, loops: %d, batches: %ld, memory footprint: %lldMB\n",
 		       (unsigned long long)(end_time - start_time), kfree_loops,
-		       rcuperf_seq_diff(b_rcu_gp_test_finished, b_rcu_gp_test_started));
+		       rcuperf_seq_diff(b_rcu_gp_test_finished, b_rcu_gp_test_started),
+		       (mem_begin - mem_during) >> (20 - PAGE_SHIFT));
+
 		if (shutdown) {
 			smp_mb(); /* Assign before wake. */
 			wake_up(&shutdown_wq);
@@ -682,11 +693,8 @@ kfree_perf_cleanup(void)
 static int
 kfree_perf_shutdown(void *arg)
 {
-	do {
-		wait_event(shutdown_wq,
-			   atomic_read(&n_kfree_perf_thread_ended) >=
-			   kfree_nrealthreads);
-	} while (atomic_read(&n_kfree_perf_thread_ended) < kfree_nrealthreads);
+	wait_event(shutdown_wq,
+		   atomic_read(&n_kfree_perf_thread_ended) >= kfree_nrealthreads);
 
 	smp_mb(); /* Wake before output. */
 
@@ -712,6 +720,8 @@ kfree_perf_init(void)
 		schedule_timeout_uninterruptible(1);
 	}
 
+	pr_alert("kfree object size=%zu\n", kfree_mult * sizeof(struct kfree_obj));
+
 	kfree_reader_tasks = kcalloc(kfree_nrealthreads, sizeof(kfree_reader_tasks[0]),
 			       GFP_KERNEL);
 	if (kfree_reader_tasks == NULL) {
diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index 1aeecc165b21..f453bf8d2f1e 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -7,7 +7,7 @@
  * Authors: Paul E. McKenney <paulmck@linux.ibm.com>
  *	  Josh Triplett <josh@joshtriplett.org>
  *
- * See also:  Documentation/RCU/torture.txt
+ * See also:  Documentation/RCU/torture.rst
  */
 
 #define pr_fmt(fmt) fmt
@@ -20,7 +20,7 @@
 #include <linux/err.h>
 #include <linux/spinlock.h>
 #include <linux/smp.h>
-#include <linux/rcupdate.h>
+#include <linux/rcupdate_wait.h>
 #include <linux/interrupt.h>
 #include <linux/sched/signal.h>
 #include <uapi/linux/sched/types.h>
@@ -45,12 +45,25 @@
 #include <linux/sched/sysctl.h>
 #include <linux/oom.h>
 #include <linux/tick.h>
+#include <linux/rcupdate_trace.h>
 
 #include "rcu.h"
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Paul E. McKenney <paulmck@linux.ibm.com> and Josh Triplett <josh@joshtriplett.org>");
 
+#ifndef data_race
+#define data_race(expr)							\
+	({								\
+		expr;							\
+	})
+#endif
+#ifndef ASSERT_EXCLUSIVE_WRITER
+#define ASSERT_EXCLUSIVE_WRITER(var) do { } while (0)
+#endif
+#ifndef ASSERT_EXCLUSIVE_ACCESS
+#define ASSERT_EXCLUSIVE_ACCESS(var) do { } while (0)
+#endif
 
 /* Bits for ->extendables field, extendables param, and related definitions. */
 #define RCUTORTURE_RDR_SHIFT	 8	/* Put SRCU index in upper bits. */
@@ -96,12 +109,19 @@ torture_param(int, object_debug, 0,
 torture_param(int, onoff_holdoff, 0, "Time after boot before CPU hotplugs (s)");
 torture_param(int, onoff_interval, 0,
 	     "Time between CPU hotplugs (jiffies), 0=disable");
+torture_param(int, read_exit_delay, 13,
+	      "Delay between read-then-exit episodes (s)");
+torture_param(int, read_exit_burst, 16,
+	      "# of read-then-exit bursts per episode, zero to disable");
 torture_param(int, shuffle_interval, 3, "Number of seconds between shuffles");
 torture_param(int, shutdown_secs, 0, "Shutdown time (s), <= zero to disable.");
 torture_param(int, stall_cpu, 0, "Stall duration (s), zero to disable.");
 torture_param(int, stall_cpu_holdoff, 10,
 	     "Time to wait before starting stall (s).");
 torture_param(int, stall_cpu_irqsoff, 0, "Disable interrupts while stalling.");
+torture_param(int, stall_cpu_block, 0, "Sleep while stalling.");
+torture_param(int, stall_gp_kthread, 0,
+	      "Grace-period kthread stall duration (s).");
 torture_param(int, stat_interval, 60,
 	     "Number of seconds between stats printk()s");
 torture_param(int, stutter, 5, "Number of seconds to run/halt test");
@@ -130,6 +150,7 @@ static struct task_struct *stall_task;
 static struct task_struct *fwd_prog_task;
 static struct task_struct **barrier_cbs_tasks;
 static struct task_struct *barrier_task;
+static struct task_struct *read_exit_task;
 
 #define RCU_TORTURE_PIPE_LEN 10
 
@@ -161,6 +182,7 @@ static long n_rcu_torture_boosts;
 static atomic_long_t n_rcu_torture_timers;
 static long n_barrier_attempts;
 static long n_barrier_successes; /* did rcu_barrier test succeed? */
+static unsigned long n_read_exits;
 static struct list_head rcu_torture_removed;
 static unsigned long shutdown_jiffies;
 
@@ -339,7 +361,7 @@ rcu_read_delay(struct torture_random_state *rrsp, struct rt_read_seg *rtrsp)
 	 * period, and we want a long delay occasionally to trigger
 	 * force_quiescent_state. */
 
-	if (!rcu_fwd_cb_nodelay &&
+	if (!READ_ONCE(rcu_fwd_cb_nodelay) &&
 	    !(torture_random(rrsp) % (nrealreaders * 2000 * longdelay_ms))) {
 		started = cur_ops->get_gp_seq();
 		ts = rcu_trace_clock_local();
@@ -375,11 +397,12 @@ rcu_torture_pipe_update_one(struct rcu_torture *rp)
 {
 	int i;
 
-	i = rp->rtort_pipe_count;
+	i = READ_ONCE(rp->rtort_pipe_count);
 	if (i > RCU_TORTURE_PIPE_LEN)
 		i = RCU_TORTURE_PIPE_LEN;
 	atomic_inc(&rcu_torture_wcount[i]);
-	if (++rp->rtort_pipe_count >= RCU_TORTURE_PIPE_LEN) {
+	WRITE_ONCE(rp->rtort_pipe_count, i + 1);
+	if (rp->rtort_pipe_count >= RCU_TORTURE_PIPE_LEN) {
 		rp->rtort_mbtest = 0;
 		return true;
 	}
@@ -664,6 +687,11 @@ static void rcu_tasks_torture_deferred_free(struct rcu_torture *p)
 	call_rcu_tasks(&p->rtort_rcu, rcu_torture_cb);
 }
 
+static void synchronize_rcu_mult_test(void)
+{
+	synchronize_rcu_mult(call_rcu_tasks, call_rcu);
+}
+
 static struct rcu_torture_ops tasks_ops = {
 	.ttype		= RCU_TASKS_FLAVOR,
 	.init		= rcu_sync_torture_init,
@@ -673,7 +701,7 @@ static struct rcu_torture_ops tasks_ops = {
 	.get_gp_seq	= rcu_no_completed,
 	.deferred_free	= rcu_tasks_torture_deferred_free,
 	.sync		= synchronize_rcu_tasks,
-	.exp_sync	= synchronize_rcu_tasks,
+	.exp_sync	= synchronize_rcu_mult_test,
 	.call		= call_rcu_tasks,
 	.cb_barrier	= rcu_barrier_tasks,
 	.fqs		= NULL,
@@ -724,6 +752,72 @@ static struct rcu_torture_ops trivial_ops = {
 	.name		= "trivial"
 };
 
+/*
+ * Definitions for rude RCU-tasks torture testing.
+ */
+
+static void rcu_tasks_rude_torture_deferred_free(struct rcu_torture *p)
+{
+	call_rcu_tasks_rude(&p->rtort_rcu, rcu_torture_cb);
+}
+
+static struct rcu_torture_ops tasks_rude_ops = {
+	.ttype		= RCU_TASKS_RUDE_FLAVOR,
+	.init		= rcu_sync_torture_init,
+	.readlock	= rcu_torture_read_lock_trivial,
+	.read_delay	= rcu_read_delay,  /* just reuse rcu's version. */
+	.readunlock	= rcu_torture_read_unlock_trivial,
+	.get_gp_seq	= rcu_no_completed,
+	.deferred_free	= rcu_tasks_rude_torture_deferred_free,
+	.sync		= synchronize_rcu_tasks_rude,
+	.exp_sync	= synchronize_rcu_tasks_rude,
+	.call		= call_rcu_tasks_rude,
+	.cb_barrier	= rcu_barrier_tasks_rude,
+	.fqs		= NULL,
+	.stats		= NULL,
+	.irq_capable	= 1,
+	.name		= "tasks-rude"
+};
+
+/*
+ * Definitions for tracing RCU-tasks torture testing.
+ */
+
+static int tasks_tracing_torture_read_lock(void)
+{
+	rcu_read_lock_trace();
+	return 0;
+}
+
+static void tasks_tracing_torture_read_unlock(int idx)
+{
+	rcu_read_unlock_trace();
+}
+
+static void rcu_tasks_tracing_torture_deferred_free(struct rcu_torture *p)
+{
+	call_rcu_tasks_trace(&p->rtort_rcu, rcu_torture_cb);
+}
+
+static struct rcu_torture_ops tasks_tracing_ops = {
+	.ttype		= RCU_TASKS_TRACING_FLAVOR,
+	.init		= rcu_sync_torture_init,
+	.readlock	= tasks_tracing_torture_read_lock,
+	.read_delay	= srcu_read_delay,  /* just reuse srcu's version. */
+	.readunlock	= tasks_tracing_torture_read_unlock,
+	.get_gp_seq	= rcu_no_completed,
+	.deferred_free	= rcu_tasks_tracing_torture_deferred_free,
+	.sync		= synchronize_rcu_tasks_trace,
+	.exp_sync	= synchronize_rcu_tasks_trace,
+	.call		= call_rcu_tasks_trace,
+	.cb_barrier	= rcu_barrier_tasks_trace,
+	.fqs		= NULL,
+	.stats		= NULL,
+	.irq_capable	= 1,
+	.slow_gps	= 1,
+	.name		= "tasks-tracing"
+};
+
 static unsigned long rcutorture_seq_diff(unsigned long new, unsigned long old)
 {
 	if (!cur_ops->gp_diff)
@@ -733,7 +827,7 @@ static unsigned long rcutorture_seq_diff(unsigned long new, unsigned long old)
 
 static bool __maybe_unused torturing_tasks(void)
 {
-	return cur_ops == &tasks_ops;
+	return cur_ops == &tasks_ops || cur_ops == &tasks_rude_ops;
 }
 
 /*
@@ -801,16 +895,11 @@ static int rcu_torture_boost(void *arg)
 	unsigned long endtime;
 	unsigned long oldstarttime;
 	struct rcu_boost_inflight rbi = { .inflight = 0 };
-	struct sched_param sp;
 
 	VERBOSE_TOROUT_STRING("rcu_torture_boost started");
 
 	/* Set real-time priority. */
-	sp.sched_priority = 1;
-	if (sched_setscheduler(current, SCHED_FIFO, &sp) < 0) {
-		VERBOSE_TOROUT_STRING("rcu_torture_boost RT prio failed!");
-		n_rcu_torture_boost_rterror++;
-	}
+	sched_set_fifo_low(current);
 
 	init_rcu_head_on_stack(&rbi.rcu);
 	/* Each pass through the following loop does one boost-test cycle. */
@@ -832,7 +921,7 @@ static int rcu_torture_boost(void *arg)
 
 		/* Wait for the next test interval. */
 		oldstarttime = boost_starttime;
-		while (ULONG_CMP_LT(jiffies, oldstarttime)) {
+		while (time_before(jiffies, oldstarttime)) {
 			schedule_timeout_interruptible(oldstarttime - jiffies);
 			stutter_wait("rcu_torture_boost");
 			if (torture_must_stop())
@@ -842,7 +931,7 @@ static int rcu_torture_boost(void *arg)
 		/* Do one boost-test interval. */
 		endtime = oldstarttime + test_boost_duration * HZ;
 		call_rcu_time = jiffies;
-		while (ULONG_CMP_LT(jiffies, endtime)) {
+		while (time_before(jiffies, endtime)) {
 			/* If we don't have a callback in flight, post one. */
 			if (!smp_load_acquire(&rbi.inflight)) {
 				/* RCU core before ->inflight = 1. */
@@ -913,7 +1002,7 @@ rcu_torture_fqs(void *arg)
 	VERBOSE_TOROUT_STRING("rcu_torture_fqs task started");
 	do {
 		fqs_resume_time = jiffies + fqs_stutter * HZ;
-		while (ULONG_CMP_LT(jiffies, fqs_resume_time) &&
+		while (time_before(jiffies, fqs_resume_time) &&
 		       !kthread_should_stop()) {
 			schedule_timeout_interruptible(1);
 		}
@@ -1015,7 +1104,8 @@ rcu_torture_writer(void *arg)
 			if (i > RCU_TORTURE_PIPE_LEN)
 				i = RCU_TORTURE_PIPE_LEN;
 			atomic_inc(&rcu_torture_wcount[i]);
-			old_rp->rtort_pipe_count++;
+			WRITE_ONCE(old_rp->rtort_pipe_count,
+				   old_rp->rtort_pipe_count + 1);
 			switch (synctype[torture_random(&rand) % nsynctypes]) {
 			case RTWS_DEF_FREE:
 				rcu_torture_writer_state = RTWS_DEF_FREE;
@@ -1067,7 +1157,8 @@ rcu_torture_writer(void *arg)
 		if (stutter_wait("rcu_torture_writer") &&
 		    !READ_ONCE(rcu_fwd_cb_nodelay) &&
 		    !cur_ops->slow_gps &&
-		    !torture_must_stop())
+		    !torture_must_stop() &&
+		    rcu_inkernel_boot_has_ended())
 			for (i = 0; i < ARRAY_SIZE(rcu_tortures); i++)
 				if (list_empty(&rcu_tortures[i].rtort_free) &&
 				    rcu_access_pointer(rcu_torture_current) !=
@@ -1076,6 +1167,7 @@ rcu_torture_writer(void *arg)
 					WARN(1, "%s: rtort_pipe_count: %d\n", __func__, rcu_tortures[i].rtort_pipe_count);
 				}
 	} while (!torture_must_stop());
+	rcu_torture_current = NULL;  // Let stats task know that we are done.
 	/* Reset expediting back to unexpedited. */
 	if (expediting > 0)
 		expediting = -expediting;
@@ -1144,6 +1236,7 @@ static void rcutorture_one_extend(int *readstate, int newstate,
 				  struct torture_random_state *trsp,
 				  struct rt_read_seg *rtrsp)
 {
+	unsigned long flags;
 	int idxnew = -1;
 	int idxold = *readstate;
 	int statesnew = ~*readstate & newstate;
@@ -1178,8 +1271,15 @@ static void rcutorture_one_extend(int *readstate, int newstate,
 		rcu_read_unlock_bh();
 	if (statesold & RCUTORTURE_RDR_SCHED)
 		rcu_read_unlock_sched();
-	if (statesold & RCUTORTURE_RDR_RCU)
+	if (statesold & RCUTORTURE_RDR_RCU) {
+		bool lockit = !statesnew && !(torture_random(trsp) & 0xffff);
+
+		if (lockit)
+			raw_spin_lock_irqsave(&current->pi_lock, flags);
 		cur_ops->readunlock(idxold >> RCUTORTURE_RDR_SHIFT);
+		if (lockit)
+			raw_spin_unlock_irqrestore(&current->pi_lock, flags);
+	}
 
 	/* Delay if neither beginning nor end and there was a change. */
 	if ((statesnew || statesold) && *readstate && newstate)
@@ -1272,6 +1372,7 @@ static bool rcu_torture_one_read(struct torture_random_state *trsp)
 	struct rt_read_seg *rtrsp1;
 	unsigned long long ts;
 
+	WARN_ON_ONCE(!rcu_is_watching());
 	newstate = rcutorture_extend_mask(readstate, trsp);
 	rcutorture_one_extend(&readstate, newstate, trsp, rtrsp++);
 	started = cur_ops->get_gp_seq();
@@ -1280,6 +1381,7 @@ static bool rcu_torture_one_read(struct torture_random_state *trsp)
 				  rcu_read_lock_bh_held() ||
 				  rcu_read_lock_sched_held() ||
 				  srcu_read_lock_held(srcu_ctlp) ||
+				  rcu_read_lock_trace_held() ||
 				  torturing_tasks());
 	if (p == NULL) {
 		/* Wait for rcu_torture_writer to get underway */
@@ -1290,7 +1392,7 @@ static bool rcu_torture_one_read(struct torture_random_state *trsp)
 		atomic_inc(&n_rcu_torture_mberror);
 	rtrsp = rcutorture_loop_extend(&readstate, trsp, rtrsp);
 	preempt_disable();
-	pipe_count = p->rtort_pipe_count;
+	pipe_count = READ_ONCE(p->rtort_pipe_count);
 	if (pipe_count > RCU_TORTURE_PIPE_LEN) {
 		/* Should not happen, but... */
 		pipe_count = RCU_TORTURE_PIPE_LEN;
@@ -1404,14 +1506,15 @@ rcu_torture_stats_print(void)
 	int i;
 	long pipesummary[RCU_TORTURE_PIPE_LEN + 1] = { 0 };
 	long batchsummary[RCU_TORTURE_PIPE_LEN + 1] = { 0 };
+	struct rcu_torture *rtcp;
 	static unsigned long rtcv_snap = ULONG_MAX;
 	static bool splatted;
 	struct task_struct *wtp;
 
 	for_each_possible_cpu(cpu) {
 		for (i = 0; i < RCU_TORTURE_PIPE_LEN + 1; i++) {
-			pipesummary[i] += per_cpu(rcu_torture_count, cpu)[i];
-			batchsummary[i] += per_cpu(rcu_torture_batch, cpu)[i];
+			pipesummary[i] += READ_ONCE(per_cpu(rcu_torture_count, cpu)[i]);
+			batchsummary[i] += READ_ONCE(per_cpu(rcu_torture_batch, cpu)[i]);
 		}
 	}
 	for (i = RCU_TORTURE_PIPE_LEN - 1; i >= 0; i--) {
@@ -1420,9 +1523,10 @@ rcu_torture_stats_print(void)
 	}
 
 	pr_alert("%s%s ", torture_type, TORTURE_FLAG);
+	rtcp = rcu_access_pointer(rcu_torture_current);
 	pr_cont("rtc: %p %s: %lu tfle: %d rta: %d rtaf: %d rtf: %d ",
-		rcu_torture_current,
-		rcu_torture_current ? "ver" : "VER",
+		rtcp,
+		rtcp && !rcu_stall_is_suppressed_at_boot() ? "ver" : "VER",
 		rcu_torture_current_version,
 		list_empty(&rcu_torture_freelist),
 		atomic_read(&n_rcu_torture_alloc),
@@ -1438,10 +1542,11 @@ rcu_torture_stats_print(void)
 		n_rcu_torture_boosts,
 		atomic_long_read(&n_rcu_torture_timers));
 	torture_onoff_stats();
-	pr_cont("barrier: %ld/%ld:%ld\n",
-		n_barrier_successes,
-		n_barrier_attempts,
-		n_rcu_torture_barrier_error);
+	pr_cont("barrier: %ld/%ld:%ld ",
+		data_race(n_barrier_successes),
+		data_race(n_barrier_attempts),
+		data_race(n_rcu_torture_barrier_error));
+	pr_cont("read-exits: %ld\n", data_race(n_read_exits));
 
 	pr_alert("%s%s ", torture_type, TORTURE_FLAG);
 	if (atomic_read(&n_rcu_torture_mberror) ||
@@ -1478,7 +1583,8 @@ rcu_torture_stats_print(void)
 	if (cur_ops->stats)
 		cur_ops->stats();
 	if (rtcv_snap == rcu_torture_current_version &&
-	    rcu_torture_current != NULL) {
+	    rcu_access_pointer(rcu_torture_current) &&
+	    !rcu_stall_is_suppressed()) {
 		int __maybe_unused flags = 0;
 		unsigned long __maybe_unused gp_seq = 0;
 
@@ -1530,16 +1636,20 @@ rcu_torture_print_module_parms(struct rcu_torture_ops *cur_ops, const char *tag)
 		 "test_boost=%d/%d test_boost_interval=%d "
 		 "test_boost_duration=%d shutdown_secs=%d "
 		 "stall_cpu=%d stall_cpu_holdoff=%d stall_cpu_irqsoff=%d "
+		 "stall_cpu_block=%d "
 		 "n_barrier_cbs=%d "
-		 "onoff_interval=%d onoff_holdoff=%d\n",
+		 "onoff_interval=%d onoff_holdoff=%d "
+		 "read_exit_delay=%d read_exit_burst=%d\n",
 		 torture_type, tag, nrealreaders, nfakewriters,
 		 stat_interval, verbose, test_no_idle_hz, shuffle_interval,
 		 stutter, irqreader, fqs_duration, fqs_holdoff, fqs_stutter,
 		 test_boost, cur_ops->can_boost,
 		 test_boost_interval, test_boost_duration, shutdown_secs,
 		 stall_cpu, stall_cpu_holdoff, stall_cpu_irqsoff,
+		 stall_cpu_block,
 		 n_barrier_cbs,
-		 onoff_interval, onoff_holdoff);
+		 onoff_interval, onoff_holdoff,
+		 read_exit_delay, read_exit_burst);
 }
 
 static int rcutorture_booster_cleanup(unsigned int cpu)
@@ -1593,6 +1703,7 @@ static int rcutorture_booster_init(unsigned int cpu)
  */
 static int rcu_torture_stall(void *args)
 {
+	int idx;
 	unsigned long stop_at;
 
 	VERBOSE_TOROUT_STRING("rcu_torture_stall task started");
@@ -1601,26 +1712,37 @@ static int rcu_torture_stall(void *args)
 		schedule_timeout_interruptible(stall_cpu_holdoff * HZ);
 		VERBOSE_TOROUT_STRING("rcu_torture_stall end holdoff");
 	}
-	if (!kthread_should_stop()) {
+	if (!kthread_should_stop() && stall_gp_kthread > 0) {
+		VERBOSE_TOROUT_STRING("rcu_torture_stall begin GP stall");
+		rcu_gp_set_torture_wait(stall_gp_kthread * HZ);
+		for (idx = 0; idx < stall_gp_kthread + 2; idx++) {
+			if (kthread_should_stop())
+				break;
+			schedule_timeout_uninterruptible(HZ);
+		}
+	}
+	if (!kthread_should_stop() && stall_cpu > 0) {
+		VERBOSE_TOROUT_STRING("rcu_torture_stall begin CPU stall");
 		stop_at = ktime_get_seconds() + stall_cpu;
 		/* RCU CPU stall is expected behavior in following code. */
-		rcu_read_lock();
+		idx = cur_ops->readlock();
 		if (stall_cpu_irqsoff)
 			local_irq_disable();
-		else
+		else if (!stall_cpu_block)
 			preempt_disable();
 		pr_alert("rcu_torture_stall start on CPU %d.\n",
-			 smp_processor_id());
+			 raw_smp_processor_id());
 		while (ULONG_CMP_LT((unsigned long)ktime_get_seconds(),
 				    stop_at))
-			continue;  /* Induce RCU CPU stall warning. */
+			if (stall_cpu_block)
+				schedule_timeout_uninterruptible(HZ);
 		if (stall_cpu_irqsoff)
 			local_irq_enable();
-		else
+		else if (!stall_cpu_block)
 			preempt_enable();
-		rcu_read_unlock();
-		pr_alert("rcu_torture_stall end.\n");
+		cur_ops->readunlock(idx);
 	}
+	pr_alert("rcu_torture_stall end.\n");
 	torture_shutdown_absorb("rcu_torture_stall");
 	while (!kthread_should_stop())
 		schedule_timeout_interruptible(10 * HZ);
@@ -1630,7 +1752,7 @@ static int rcu_torture_stall(void *args)
 /* Spawn CPU-stall kthread, if stall_cpu specified. */
 static int __init rcu_torture_stall_init(void)
 {
-	if (stall_cpu <= 0)
+	if (stall_cpu <= 0 && stall_gp_kthread <= 0)
 		return 0;
 	return torture_create_kthread(rcu_torture_stall, NULL, stall_task);
 }
@@ -1686,8 +1808,8 @@ struct rcu_fwd {
 	unsigned long rcu_launder_gp_seq_start;
 };
 
-struct rcu_fwd *rcu_fwds;
-bool rcu_fwd_emergency_stop;
+static struct rcu_fwd *rcu_fwds;
+static bool rcu_fwd_emergency_stop;
 
 static void rcu_torture_fwd_cb_hist(struct rcu_fwd *rfp)
 {
@@ -1993,8 +2115,11 @@ static int rcu_torture_fwd_prog(void *args)
 		schedule_timeout_interruptible(fwd_progress_holdoff * HZ);
 		WRITE_ONCE(rcu_fwd_emergency_stop, false);
 		register_oom_notifier(&rcutorture_oom_nb);
-		rcu_torture_fwd_prog_nr(rfp, &tested, &tested_tries);
-		rcu_torture_fwd_prog_cr(rfp);
+		if (!IS_ENABLED(CONFIG_TINY_RCU) ||
+		    rcu_inkernel_boot_has_ended())
+			rcu_torture_fwd_prog_nr(rfp, &tested, &tested_tries);
+		if (rcu_inkernel_boot_has_ended())
+			rcu_torture_fwd_prog_cr(rfp);
 		unregister_oom_notifier(&rcutorture_oom_nb);
 
 		/* Avoid slow periods, better to test when busy. */
@@ -2044,11 +2169,19 @@ static void rcu_torture_barrier_cbf(struct rcu_head *rcu)
 	atomic_inc(&barrier_cbs_invoked);
 }
 
+/* IPI handler to get callback posted on desired CPU, if online. */
+static void rcu_torture_barrier1cb(void *rcu_void)
+{
+	struct rcu_head *rhp = rcu_void;
+
+	cur_ops->call(rhp, rcu_torture_barrier_cbf);
+}
+
 /* kthread function to register callbacks used to test RCU barriers. */
 static int rcu_torture_barrier_cbs(void *arg)
 {
 	long myid = (long)arg;
-	bool lastphase = 0;
+	bool lastphase = false;
 	bool newphase;
 	struct rcu_head rcu;
 
@@ -2067,9 +2200,11 @@ static int rcu_torture_barrier_cbs(void *arg)
 		 * The above smp_load_acquire() ensures barrier_phase load
 		 * is ordered before the following ->call().
 		 */
-		local_irq_disable(); /* Just to test no-irq call_rcu(). */
-		cur_ops->call(&rcu, rcu_torture_barrier_cbf);
-		local_irq_enable();
+		if (smp_call_function_single(myid, rcu_torture_barrier1cb,
+					     &rcu, 1)) {
+			// IPI failed, so use direct call from current CPU.
+			cur_ops->call(&rcu, rcu_torture_barrier_cbf);
+		}
 		if (atomic_dec_and_test(&barrier_cbs_count))
 			wake_up(&barrier_wq);
 	} while (!torture_must_stop());
@@ -2105,7 +2240,21 @@ static int rcu_torture_barrier(void *arg)
 			pr_err("barrier_cbs_invoked = %d, n_barrier_cbs = %d\n",
 			       atomic_read(&barrier_cbs_invoked),
 			       n_barrier_cbs);
-			WARN_ON_ONCE(1);
+			WARN_ON(1);
+			// Wait manually for the remaining callbacks
+			i = 0;
+			do {
+				if (WARN_ON(i++ > HZ))
+					i = INT_MIN;
+				schedule_timeout_interruptible(1);
+				cur_ops->cb_barrier();
+			} while (atomic_read(&barrier_cbs_invoked) !=
+				 n_barrier_cbs &&
+				 !torture_must_stop());
+			smp_mb(); // Can't trust ordering if broken.
+			if (!torture_must_stop())
+				pr_err("Recovered: barrier_cbs_invoked = %d\n",
+				       atomic_read(&barrier_cbs_invoked));
 		} else {
 			n_barrier_successes++;
 		}
@@ -2195,6 +2344,99 @@ static bool rcu_torture_can_boost(void)
 	return true;
 }
 
+static bool read_exit_child_stop;
+static bool read_exit_child_stopped;
+static wait_queue_head_t read_exit_wq;
+
+// Child kthread which just does an rcutorture reader and exits.
+static int rcu_torture_read_exit_child(void *trsp_in)
+{
+	struct torture_random_state *trsp = trsp_in;
+
+	set_user_nice(current, MAX_NICE);
+	// Minimize time between reading and exiting.
+	while (!kthread_should_stop())
+		schedule_timeout_uninterruptible(1);
+	(void)rcu_torture_one_read(trsp);
+	return 0;
+}
+
+// Parent kthread which creates and destroys read-exit child kthreads.
+static int rcu_torture_read_exit(void *unused)
+{
+	int count = 0;
+	bool errexit = false;
+	int i;
+	struct task_struct *tsp;
+	DEFINE_TORTURE_RANDOM(trs);
+
+	// Allocate and initialize.
+	set_user_nice(current, MAX_NICE);
+	VERBOSE_TOROUT_STRING("rcu_torture_read_exit: Start of test");
+
+	// Each pass through this loop does one read-exit episode.
+	do {
+		if (++count > read_exit_burst) {
+			VERBOSE_TOROUT_STRING("rcu_torture_read_exit: End of episode");
+			rcu_barrier(); // Wait for task_struct free, avoid OOM.
+			for (i = 0; i < read_exit_delay; i++) {
+				schedule_timeout_uninterruptible(HZ);
+				if (READ_ONCE(read_exit_child_stop))
+					break;
+			}
+			if (!READ_ONCE(read_exit_child_stop))
+				VERBOSE_TOROUT_STRING("rcu_torture_read_exit: Start of episode");
+			count = 0;
+		}
+		if (READ_ONCE(read_exit_child_stop))
+			break;
+		// Spawn child.
+		tsp = kthread_run(rcu_torture_read_exit_child,
+				     &trs, "%s",
+				     "rcu_torture_read_exit_child");
+		if (IS_ERR(tsp)) {
+			VERBOSE_TOROUT_ERRSTRING("out of memory");
+			errexit = true;
+			tsp = NULL;
+			break;
+		}
+		cond_resched();
+		kthread_stop(tsp);
+		n_read_exits ++;
+		stutter_wait("rcu_torture_read_exit");
+	} while (!errexit && !READ_ONCE(read_exit_child_stop));
+
+	// Clean up and exit.
+	smp_store_release(&read_exit_child_stopped, true); // After reaping.
+	smp_mb(); // Store before wakeup.
+	wake_up(&read_exit_wq);
+	while (!torture_must_stop())
+		schedule_timeout_uninterruptible(1);
+	torture_kthread_stopping("rcu_torture_read_exit");
+	return 0;
+}
+
+static int rcu_torture_read_exit_init(void)
+{
+	if (read_exit_burst <= 0)
+		return -EINVAL;
+	init_waitqueue_head(&read_exit_wq);
+	read_exit_child_stop = false;
+	read_exit_child_stopped = false;
+	return torture_create_kthread(rcu_torture_read_exit, NULL,
+				      read_exit_task);
+}
+
+static void rcu_torture_read_exit_cleanup(void)
+{
+	if (!read_exit_task)
+		return;
+	WRITE_ONCE(read_exit_child_stop, true);
+	smp_mb(); // Above write before wait.
+	wait_event(read_exit_wq, smp_load_acquire(&read_exit_child_stopped));
+	torture_stop_kthread(rcutorture_read_exit, read_exit_task);
+}
+
 static enum cpuhp_state rcutor_hp;
 
 static void
@@ -2216,6 +2458,7 @@ rcu_torture_cleanup(void)
 	}
 
 	show_rcu_gp_kthreads();
+	rcu_torture_read_exit_cleanup();
 	rcu_torture_barrier_cleanup();
 	torture_stop_kthread(rcu_torture_fwd_prog, fwd_prog_task);
 	torture_stop_kthread(rcu_torture_stall, stall_task);
@@ -2227,7 +2470,6 @@ rcu_torture_cleanup(void)
 					     reader_tasks[i]);
 		kfree(reader_tasks);
 	}
-	rcu_torture_current = NULL;
 
 	if (fakewriter_tasks) {
 		for (i = 0; i < nfakewriters; i++) {
@@ -2367,7 +2609,8 @@ rcu_torture_init(void)
 	int firsterr = 0;
 	static struct rcu_torture_ops *torture_ops[] = {
 		&rcu_ops, &rcu_busted_ops, &srcu_ops, &srcud_ops,
-		&busted_srcud_ops, &tasks_ops, &trivial_ops,
+		&busted_srcud_ops, &tasks_ops, &tasks_rude_ops,
+		&tasks_tracing_ops, &trivial_ops,
 	};
 
 	if (!torture_init_begin(torture_type, verbose))
@@ -2538,6 +2781,9 @@ rcu_torture_init(void)
 	firsterr = rcu_torture_barrier_init();
 	if (firsterr)
 		goto unwind;
+	firsterr = rcu_torture_read_exit_init();
+	if (firsterr)
+		goto unwind;
 	if (object_debug)
 		rcu_test_debug_objects();
 	torture_init_end();
diff --git a/kernel/rcu/refscale.c b/kernel/rcu/refscale.c
new file mode 100644
index 000000000000..d9291f883b54
--- /dev/null
+++ b/kernel/rcu/refscale.c
@@ -0,0 +1,717 @@
+// SPDX-License-Identifier: GPL-2.0+
+//
+// Scalability test comparing RCU vs other mechanisms
+// for acquiring references on objects.
+//
+// Copyright (C) Google, 2020.
+//
+// Author: Joel Fernandes <joel@joelfernandes.org>
+
+#define pr_fmt(fmt) fmt
+
+#include <linux/atomic.h>
+#include <linux/bitops.h>
+#include <linux/completion.h>
+#include <linux/cpu.h>
+#include <linux/delay.h>
+#include <linux/err.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/kthread.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/module.h>
+#include <linux/moduleparam.h>
+#include <linux/notifier.h>
+#include <linux/percpu.h>
+#include <linux/rcupdate.h>
+#include <linux/rcupdate_trace.h>
+#include <linux/reboot.h>
+#include <linux/sched.h>
+#include <linux/spinlock.h>
+#include <linux/smp.h>
+#include <linux/stat.h>
+#include <linux/srcu.h>
+#include <linux/slab.h>
+#include <linux/torture.h>
+#include <linux/types.h>
+
+#include "rcu.h"
+
+#define SCALE_FLAG "-ref-scale: "
+
+#define SCALEOUT(s, x...) \
+	pr_alert("%s" SCALE_FLAG s, scale_type, ## x)
+
+#define VERBOSE_SCALEOUT(s, x...) \
+	do { if (verbose) pr_alert("%s" SCALE_FLAG s, scale_type, ## x); } while (0)
+
+#define VERBOSE_SCALEOUT_ERRSTRING(s, x...) \
+	do { if (verbose) pr_alert("%s" SCALE_FLAG "!!! " s, scale_type, ## x); } while (0)
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Joel Fernandes (Google) <joel@joelfernandes.org>");
+
+static char *scale_type = "rcu";
+module_param(scale_type, charp, 0444);
+MODULE_PARM_DESC(scale_type, "Type of test (rcu, srcu, refcnt, rwsem, rwlock.");
+
+torture_param(int, verbose, 0, "Enable verbose debugging printk()s");
+
+// Wait until there are multiple CPUs before starting test.
+torture_param(int, holdoff, IS_BUILTIN(CONFIG_RCU_REF_SCALE_TEST) ? 10 : 0,
+	      "Holdoff time before test start (s)");
+// Number of loops per experiment, all readers execute operations concurrently.
+torture_param(long, loops, 10000, "Number of loops per experiment.");
+// Number of readers, with -1 defaulting to about 75% of the CPUs.
+torture_param(int, nreaders, -1, "Number of readers, -1 for 75% of CPUs.");
+// Number of runs.
+torture_param(int, nruns, 30, "Number of experiments to run.");
+// Reader delay in nanoseconds, 0 for no delay.
+torture_param(int, readdelay, 0, "Read-side delay in nanoseconds.");
+
+#ifdef MODULE
+# define REFSCALE_SHUTDOWN 0
+#else
+# define REFSCALE_SHUTDOWN 1
+#endif
+
+torture_param(bool, shutdown, REFSCALE_SHUTDOWN,
+	      "Shutdown at end of scalability tests.");
+
+struct reader_task {
+	struct task_struct *task;
+	int start_reader;
+	wait_queue_head_t wq;
+	u64 last_duration_ns;
+};
+
+static struct task_struct *shutdown_task;
+static wait_queue_head_t shutdown_wq;
+
+static struct task_struct *main_task;
+static wait_queue_head_t main_wq;
+static int shutdown_start;
+
+static struct reader_task *reader_tasks;
+
+// Number of readers that are part of the current experiment.
+static atomic_t nreaders_exp;
+
+// Use to wait for all threads to start.
+static atomic_t n_init;
+static atomic_t n_started;
+static atomic_t n_warmedup;
+static atomic_t n_cooleddown;
+
+// Track which experiment is currently running.
+static int exp_idx;
+
+// Operations vector for selecting different types of tests.
+struct ref_scale_ops {
+	void (*init)(void);
+	void (*cleanup)(void);
+	void (*readsection)(const int nloops);
+	void (*delaysection)(const int nloops, const int udl, const int ndl);
+	const char *name;
+};
+
+static struct ref_scale_ops *cur_ops;
+
+static void un_delay(const int udl, const int ndl)
+{
+	if (udl)
+		udelay(udl);
+	if (ndl)
+		ndelay(ndl);
+}
+
+static void ref_rcu_read_section(const int nloops)
+{
+	int i;
+
+	for (i = nloops; i >= 0; i--) {
+		rcu_read_lock();
+		rcu_read_unlock();
+	}
+}
+
+static void ref_rcu_delay_section(const int nloops, const int udl, const int ndl)
+{
+	int i;
+
+	for (i = nloops; i >= 0; i--) {
+		rcu_read_lock();
+		un_delay(udl, ndl);
+		rcu_read_unlock();
+	}
+}
+
+static void rcu_sync_scale_init(void)
+{
+}
+
+static struct ref_scale_ops rcu_ops = {
+	.init		= rcu_sync_scale_init,
+	.readsection	= ref_rcu_read_section,
+	.delaysection	= ref_rcu_delay_section,
+	.name		= "rcu"
+};
+
+// Definitions for SRCU ref scale testing.
+DEFINE_STATIC_SRCU(srcu_refctl_scale);
+static struct srcu_struct *srcu_ctlp = &srcu_refctl_scale;
+
+static void srcu_ref_scale_read_section(const int nloops)
+{
+	int i;
+	int idx;
+
+	for (i = nloops; i >= 0; i--) {
+		idx = srcu_read_lock(srcu_ctlp);
+		srcu_read_unlock(srcu_ctlp, idx);
+	}
+}
+
+static void srcu_ref_scale_delay_section(const int nloops, const int udl, const int ndl)
+{
+	int i;
+	int idx;
+
+	for (i = nloops; i >= 0; i--) {
+		idx = srcu_read_lock(srcu_ctlp);
+		un_delay(udl, ndl);
+		srcu_read_unlock(srcu_ctlp, idx);
+	}
+}
+
+static struct ref_scale_ops srcu_ops = {
+	.init		= rcu_sync_scale_init,
+	.readsection	= srcu_ref_scale_read_section,
+	.delaysection	= srcu_ref_scale_delay_section,
+	.name		= "srcu"
+};
+
+// Definitions for RCU Tasks ref scale testing: Empty read markers.
+// These definitions also work for RCU Rude readers.
+static void rcu_tasks_ref_scale_read_section(const int nloops)
+{
+	int i;
+
+	for (i = nloops; i >= 0; i--)
+		continue;
+}
+
+static void rcu_tasks_ref_scale_delay_section(const int nloops, const int udl, const int ndl)
+{
+	int i;
+
+	for (i = nloops; i >= 0; i--)
+		un_delay(udl, ndl);
+}
+
+static struct ref_scale_ops rcu_tasks_ops = {
+	.init		= rcu_sync_scale_init,
+	.readsection	= rcu_tasks_ref_scale_read_section,
+	.delaysection	= rcu_tasks_ref_scale_delay_section,
+	.name		= "rcu-tasks"
+};
+
+// Definitions for RCU Tasks Trace ref scale testing.
+static void rcu_trace_ref_scale_read_section(const int nloops)
+{
+	int i;
+
+	for (i = nloops; i >= 0; i--) {
+		rcu_read_lock_trace();
+		rcu_read_unlock_trace();
+	}
+}
+
+static void rcu_trace_ref_scale_delay_section(const int nloops, const int udl, const int ndl)
+{
+	int i;
+
+	for (i = nloops; i >= 0; i--) {
+		rcu_read_lock_trace();
+		un_delay(udl, ndl);
+		rcu_read_unlock_trace();
+	}
+}
+
+static struct ref_scale_ops rcu_trace_ops = {
+	.init		= rcu_sync_scale_init,
+	.readsection	= rcu_trace_ref_scale_read_section,
+	.delaysection	= rcu_trace_ref_scale_delay_section,
+	.name		= "rcu-trace"
+};
+
+// Definitions for reference count
+static atomic_t refcnt;
+
+static void ref_refcnt_section(const int nloops)
+{
+	int i;
+
+	for (i = nloops; i >= 0; i--) {
+		atomic_inc(&refcnt);
+		atomic_dec(&refcnt);
+	}
+}
+
+static void ref_refcnt_delay_section(const int nloops, const int udl, const int ndl)
+{
+	int i;
+
+	for (i = nloops; i >= 0; i--) {
+		atomic_inc(&refcnt);
+		un_delay(udl, ndl);
+		atomic_dec(&refcnt);
+	}
+}
+
+static struct ref_scale_ops refcnt_ops = {
+	.init		= rcu_sync_scale_init,
+	.readsection	= ref_refcnt_section,
+	.delaysection	= ref_refcnt_delay_section,
+	.name		= "refcnt"
+};
+
+// Definitions for rwlock
+static rwlock_t test_rwlock;
+
+static void ref_rwlock_init(void)
+{
+	rwlock_init(&test_rwlock);
+}
+
+static void ref_rwlock_section(const int nloops)
+{
+	int i;
+
+	for (i = nloops; i >= 0; i--) {
+		read_lock(&test_rwlock);
+		read_unlock(&test_rwlock);
+	}
+}
+
+static void ref_rwlock_delay_section(const int nloops, const int udl, const int ndl)
+{
+	int i;
+
+	for (i = nloops; i >= 0; i--) {
+		read_lock(&test_rwlock);
+		un_delay(udl, ndl);
+		read_unlock(&test_rwlock);
+	}
+}
+
+static struct ref_scale_ops rwlock_ops = {
+	.init		= ref_rwlock_init,
+	.readsection	= ref_rwlock_section,
+	.delaysection	= ref_rwlock_delay_section,
+	.name		= "rwlock"
+};
+
+// Definitions for rwsem
+static struct rw_semaphore test_rwsem;
+
+static void ref_rwsem_init(void)
+{
+	init_rwsem(&test_rwsem);
+}
+
+static void ref_rwsem_section(const int nloops)
+{
+	int i;
+
+	for (i = nloops; i >= 0; i--) {
+		down_read(&test_rwsem);
+		up_read(&test_rwsem);
+	}
+}
+
+static void ref_rwsem_delay_section(const int nloops, const int udl, const int ndl)
+{
+	int i;
+
+	for (i = nloops; i >= 0; i--) {
+		down_read(&test_rwsem);
+		un_delay(udl, ndl);
+		up_read(&test_rwsem);
+	}
+}
+
+static struct ref_scale_ops rwsem_ops = {
+	.init		= ref_rwsem_init,
+	.readsection	= ref_rwsem_section,
+	.delaysection	= ref_rwsem_delay_section,
+	.name		= "rwsem"
+};
+
+static void rcu_scale_one_reader(void)
+{
+	if (readdelay <= 0)
+		cur_ops->readsection(loops);
+	else
+		cur_ops->delaysection(loops, readdelay / 1000, readdelay % 1000);
+}
+
+// Reader kthread.  Repeatedly does empty RCU read-side
+// critical section, minimizing update-side interference.
+static int
+ref_scale_reader(void *arg)
+{
+	unsigned long flags;
+	long me = (long)arg;
+	struct reader_task *rt = &(reader_tasks[me]);
+	u64 start;
+	s64 duration;
+
+	VERBOSE_SCALEOUT("ref_scale_reader %ld: task started", me);
+	set_cpus_allowed_ptr(current, cpumask_of(me % nr_cpu_ids));
+	set_user_nice(current, MAX_NICE);
+	atomic_inc(&n_init);
+	if (holdoff)
+		schedule_timeout_interruptible(holdoff * HZ);
+repeat:
+	VERBOSE_SCALEOUT("ref_scale_reader %ld: waiting to start next experiment on cpu %d", me, smp_processor_id());
+
+	// Wait for signal that this reader can start.
+	wait_event(rt->wq, (atomic_read(&nreaders_exp) && smp_load_acquire(&rt->start_reader)) ||
+			   torture_must_stop());
+
+	if (torture_must_stop())
+		goto end;
+
+	// Make sure that the CPU is affinitized appropriately during testing.
+	WARN_ON_ONCE(smp_processor_id() != me);
+
+	WRITE_ONCE(rt->start_reader, 0);
+	if (!atomic_dec_return(&n_started))
+		while (atomic_read_acquire(&n_started))
+			cpu_relax();
+
+	VERBOSE_SCALEOUT("ref_scale_reader %ld: experiment %d started", me, exp_idx);
+
+
+	// To reduce noise, do an initial cache-warming invocation, check
+	// in, and then keep warming until everyone has checked in.
+	rcu_scale_one_reader();
+	if (!atomic_dec_return(&n_warmedup))
+		while (atomic_read_acquire(&n_warmedup))
+			rcu_scale_one_reader();
+	// Also keep interrupts disabled.  This also has the effect
+	// of preventing entries into slow path for rcu_read_unlock().
+	local_irq_save(flags);
+	start = ktime_get_mono_fast_ns();
+
+	rcu_scale_one_reader();
+
+	duration = ktime_get_mono_fast_ns() - start;
+	local_irq_restore(flags);
+
+	rt->last_duration_ns = WARN_ON_ONCE(duration < 0) ? 0 : duration;
+	// To reduce runtime-skew noise, do maintain-load invocations until
+	// everyone is done.
+	if (!atomic_dec_return(&n_cooleddown))
+		while (atomic_read_acquire(&n_cooleddown))
+			rcu_scale_one_reader();
+
+	if (atomic_dec_and_test(&nreaders_exp))
+		wake_up(&main_wq);
+
+	VERBOSE_SCALEOUT("ref_scale_reader %ld: experiment %d ended, (readers remaining=%d)",
+			me, exp_idx, atomic_read(&nreaders_exp));
+
+	if (!torture_must_stop())
+		goto repeat;
+end:
+	torture_kthread_stopping("ref_scale_reader");
+	return 0;
+}
+
+static void reset_readers(void)
+{
+	int i;
+	struct reader_task *rt;
+
+	for (i = 0; i < nreaders; i++) {
+		rt = &(reader_tasks[i]);
+
+		rt->last_duration_ns = 0;
+	}
+}
+
+// Print the results of each reader and return the sum of all their durations.
+static u64 process_durations(int n)
+{
+	int i;
+	struct reader_task *rt;
+	char buf1[64];
+	char *buf;
+	u64 sum = 0;
+
+	buf = kmalloc(128 + nreaders * 32, GFP_KERNEL);
+	if (!buf)
+		return 0;
+	buf[0] = 0;
+	sprintf(buf, "Experiment #%d (Format: <THREAD-NUM>:<Total loop time in ns>)",
+		exp_idx);
+
+	for (i = 0; i < n && !torture_must_stop(); i++) {
+		rt = &(reader_tasks[i]);
+		sprintf(buf1, "%d: %llu\t", i, rt->last_duration_ns);
+
+		if (i % 5 == 0)
+			strcat(buf, "\n");
+		strcat(buf, buf1);
+
+		sum += rt->last_duration_ns;
+	}
+	strcat(buf, "\n");
+
+	SCALEOUT("%s\n", buf);
+
+	kfree(buf);
+	return sum;
+}
+
+// The main_func is the main orchestrator, it performs a bunch of
+// experiments.  For every experiment, it orders all the readers
+// involved to start and waits for them to finish the experiment. It
+// then reads their timestamps and starts the next experiment. Each
+// experiment progresses from 1 concurrent reader to N of them at which
+// point all the timestamps are printed.
+static int main_func(void *arg)
+{
+	bool errexit = false;
+	int exp, r;
+	char buf1[64];
+	char *buf;
+	u64 *result_avg;
+
+	set_cpus_allowed_ptr(current, cpumask_of(nreaders % nr_cpu_ids));
+	set_user_nice(current, MAX_NICE);
+
+	VERBOSE_SCALEOUT("main_func task started");
+	result_avg = kzalloc(nruns * sizeof(*result_avg), GFP_KERNEL);
+	buf = kzalloc(64 + nruns * 32, GFP_KERNEL);
+	if (!result_avg || !buf) {
+		VERBOSE_SCALEOUT_ERRSTRING("out of memory");
+		errexit = true;
+	}
+	if (holdoff)
+		schedule_timeout_interruptible(holdoff * HZ);
+
+	// Wait for all threads to start.
+	atomic_inc(&n_init);
+	while (atomic_read(&n_init) < nreaders + 1)
+		schedule_timeout_uninterruptible(1);
+
+	// Start exp readers up per experiment
+	for (exp = 0; exp < nruns && !torture_must_stop(); exp++) {
+		if (errexit)
+			break;
+		if (torture_must_stop())
+			goto end;
+
+		reset_readers();
+		atomic_set(&nreaders_exp, nreaders);
+		atomic_set(&n_started, nreaders);
+		atomic_set(&n_warmedup, nreaders);
+		atomic_set(&n_cooleddown, nreaders);
+
+		exp_idx = exp;
+
+		for (r = 0; r < nreaders; r++) {
+			smp_store_release(&reader_tasks[r].start_reader, 1);
+			wake_up(&reader_tasks[r].wq);
+		}
+
+		VERBOSE_SCALEOUT("main_func: experiment started, waiting for %d readers",
+				nreaders);
+
+		wait_event(main_wq,
+			   !atomic_read(&nreaders_exp) || torture_must_stop());
+
+		VERBOSE_SCALEOUT("main_func: experiment ended");
+
+		if (torture_must_stop())
+			goto end;
+
+		result_avg[exp] = div_u64(1000 * process_durations(nreaders), nreaders * loops);
+	}
+
+	// Print the average of all experiments
+	SCALEOUT("END OF TEST. Calculating average duration per loop (nanoseconds)...\n");
+
+	buf[0] = 0;
+	strcat(buf, "\n");
+	strcat(buf, "Runs\tTime(ns)\n");
+
+	for (exp = 0; exp < nruns; exp++) {
+		u64 avg;
+		u32 rem;
+
+		if (errexit)
+			break;
+		avg = div_u64_rem(result_avg[exp], 1000, &rem);
+		sprintf(buf1, "%d\t%llu.%03u\n", exp + 1, avg, rem);
+		strcat(buf, buf1);
+	}
+
+	if (!errexit)
+		SCALEOUT("%s", buf);
+
+	// This will shutdown everything including us.
+	if (shutdown) {
+		shutdown_start = 1;
+		wake_up(&shutdown_wq);
+	}
+
+	// Wait for torture to stop us
+	while (!torture_must_stop())
+		schedule_timeout_uninterruptible(1);
+
+end:
+	torture_kthread_stopping("main_func");
+	kfree(result_avg);
+	kfree(buf);
+	return 0;
+}
+
+static void
+ref_scale_print_module_parms(struct ref_scale_ops *cur_ops, const char *tag)
+{
+	pr_alert("%s" SCALE_FLAG
+		 "--- %s:  verbose=%d shutdown=%d holdoff=%d loops=%ld nreaders=%d nruns=%d readdelay=%d\n", scale_type, tag,
+		 verbose, shutdown, holdoff, loops, nreaders, nruns, readdelay);
+}
+
+static void
+ref_scale_cleanup(void)
+{
+	int i;
+
+	if (torture_cleanup_begin())
+		return;
+
+	if (!cur_ops) {
+		torture_cleanup_end();
+		return;
+	}
+
+	if (reader_tasks) {
+		for (i = 0; i < nreaders; i++)
+			torture_stop_kthread("ref_scale_reader",
+					     reader_tasks[i].task);
+	}
+	kfree(reader_tasks);
+
+	torture_stop_kthread("main_task", main_task);
+	kfree(main_task);
+
+	// Do scale-type-specific cleanup operations.
+	if (cur_ops->cleanup != NULL)
+		cur_ops->cleanup();
+
+	torture_cleanup_end();
+}
+
+// Shutdown kthread.  Just waits to be awakened, then shuts down system.
+static int
+ref_scale_shutdown(void *arg)
+{
+	wait_event(shutdown_wq, shutdown_start);
+
+	smp_mb(); // Wake before output.
+	ref_scale_cleanup();
+	kernel_power_off();
+
+	return -EINVAL;
+}
+
+static int __init
+ref_scale_init(void)
+{
+	long i;
+	int firsterr = 0;
+	static struct ref_scale_ops *scale_ops[] = {
+		&rcu_ops, &srcu_ops, &rcu_trace_ops, &rcu_tasks_ops,
+		&refcnt_ops, &rwlock_ops, &rwsem_ops,
+	};
+
+	if (!torture_init_begin(scale_type, verbose))
+		return -EBUSY;
+
+	for (i = 0; i < ARRAY_SIZE(scale_ops); i++) {
+		cur_ops = scale_ops[i];
+		if (strcmp(scale_type, cur_ops->name) == 0)
+			break;
+	}
+	if (i == ARRAY_SIZE(scale_ops)) {
+		pr_alert("rcu-scale: invalid scale type: \"%s\"\n", scale_type);
+		pr_alert("rcu-scale types:");
+		for (i = 0; i < ARRAY_SIZE(scale_ops); i++)
+			pr_cont(" %s", scale_ops[i]->name);
+		pr_cont("\n");
+		WARN_ON(!IS_MODULE(CONFIG_RCU_REF_SCALE_TEST));
+		firsterr = -EINVAL;
+		cur_ops = NULL;
+		goto unwind;
+	}
+	if (cur_ops->init)
+		cur_ops->init();
+
+	ref_scale_print_module_parms(cur_ops, "Start of test");
+
+	// Shutdown task
+	if (shutdown) {
+		init_waitqueue_head(&shutdown_wq);
+		firsterr = torture_create_kthread(ref_scale_shutdown, NULL,
+						  shutdown_task);
+		if (firsterr)
+			goto unwind;
+		schedule_timeout_uninterruptible(1);
+	}
+
+	// Reader tasks (default to ~75% of online CPUs).
+	if (nreaders < 0)
+		nreaders = (num_online_cpus() >> 1) + (num_online_cpus() >> 2);
+	reader_tasks = kcalloc(nreaders, sizeof(reader_tasks[0]),
+			       GFP_KERNEL);
+	if (!reader_tasks) {
+		VERBOSE_SCALEOUT_ERRSTRING("out of memory");
+		firsterr = -ENOMEM;
+		goto unwind;
+	}
+
+	VERBOSE_SCALEOUT("Starting %d reader threads\n", nreaders);
+
+	for (i = 0; i < nreaders; i++) {
+		firsterr = torture_create_kthread(ref_scale_reader, (void *)i,
+						  reader_tasks[i].task);
+		if (firsterr)
+			goto unwind;
+
+		init_waitqueue_head(&(reader_tasks[i].wq));
+	}
+
+	// Main Task
+	init_waitqueue_head(&main_wq);
+	firsterr = torture_create_kthread(main_func, NULL, main_task);
+	if (firsterr)
+		goto unwind;
+
+	torture_init_end();
+	return 0;
+
+unwind:
+	torture_init_end();
+	ref_scale_cleanup();
+	return firsterr;
+}
+
+module_init(ref_scale_init);
+module_exit(ref_scale_cleanup);
diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c
index 657e6a7d1c03..c100acf332ed 100644
--- a/kernel/rcu/srcutree.c
+++ b/kernel/rcu/srcutree.c
@@ -5,7 +5,7 @@
  * Copyright (C) IBM Corporation, 2006
  * Copyright (C) Fujitsu, 2012
  *
- * Author: Paul McKenney <paulmck@linux.ibm.com>
+ * Authors: Paul McKenney <paulmck@linux.ibm.com>
  *	   Lai Jiangshan <laijs@cn.fujitsu.com>
  *
  * For detailed explanation of Read-Copy Update mechanism see -
@@ -29,6 +29,19 @@
 #include "rcu.h"
 #include "rcu_segcblist.h"
 
+#ifndef data_race
+#define data_race(expr)							\
+	({								\
+		expr;							\
+	})
+#endif
+#ifndef ASSERT_EXCLUSIVE_WRITER
+#define ASSERT_EXCLUSIVE_WRITER(var) do { } while (0)
+#endif
+#ifndef ASSERT_EXCLUSIVE_ACCESS
+#define ASSERT_EXCLUSIVE_ACCESS(var) do { } while (0)
+#endif
+
 /* Holdoff in nanoseconds for auto-expediting. */
 #define DEFAULT_SRCU_EXP_HOLDOFF (25 * 1000)
 static ulong exp_holdoff = DEFAULT_SRCU_EXP_HOLDOFF;
@@ -450,7 +463,7 @@ static void srcu_gp_start(struct srcu_struct *ssp)
 	spin_unlock_rcu_node(sdp);  /* Interrupts remain disabled. */
 	smp_mb(); /* Order prior store to ->srcu_gp_seq_needed vs. GP start. */
 	rcu_seq_start(&ssp->srcu_gp_seq);
-	state = rcu_seq_state(READ_ONCE(ssp->srcu_gp_seq));
+	state = rcu_seq_state(ssp->srcu_gp_seq);
 	WARN_ON_ONCE(state != SRCU_STATE_SCAN1);
 }
 
@@ -534,7 +547,7 @@ static void srcu_gp_end(struct srcu_struct *ssp)
 	rcu_seq_end(&ssp->srcu_gp_seq);
 	gpseq = rcu_seq_current(&ssp->srcu_gp_seq);
 	if (ULONG_CMP_LT(ssp->srcu_gp_seq_needed_exp, gpseq))
-		ssp->srcu_gp_seq_needed_exp = gpseq;
+		WRITE_ONCE(ssp->srcu_gp_seq_needed_exp, gpseq);
 	spin_unlock_irq_rcu_node(ssp);
 	mutex_unlock(&ssp->srcu_gp_mutex);
 	/* A new grace period can start at this point.  But only one. */
@@ -550,7 +563,7 @@ static void srcu_gp_end(struct srcu_struct *ssp)
 		snp->srcu_have_cbs[idx] = gpseq;
 		rcu_seq_set_state(&snp->srcu_have_cbs[idx], 1);
 		if (ULONG_CMP_LT(snp->srcu_gp_seq_needed_exp, gpseq))
-			snp->srcu_gp_seq_needed_exp = gpseq;
+			WRITE_ONCE(snp->srcu_gp_seq_needed_exp, gpseq);
 		mask = snp->srcu_data_have_cbs[idx];
 		snp->srcu_data_have_cbs[idx] = 0;
 		spin_unlock_irq_rcu_node(snp);
@@ -614,7 +627,7 @@ static void srcu_funnel_exp_start(struct srcu_struct *ssp, struct srcu_node *snp
 	}
 	spin_lock_irqsave_rcu_node(ssp, flags);
 	if (ULONG_CMP_LT(ssp->srcu_gp_seq_needed_exp, s))
-		ssp->srcu_gp_seq_needed_exp = s;
+		WRITE_ONCE(ssp->srcu_gp_seq_needed_exp, s);
 	spin_unlock_irqrestore_rcu_node(ssp, flags);
 }
 
@@ -660,7 +673,7 @@ static void srcu_funnel_gp_start(struct srcu_struct *ssp, struct srcu_data *sdp,
 		if (snp == sdp->mynode)
 			snp->srcu_data_have_cbs[idx] |= sdp->grpmask;
 		if (!do_norm && ULONG_CMP_LT(snp->srcu_gp_seq_needed_exp, s))
-			snp->srcu_gp_seq_needed_exp = s;
+			WRITE_ONCE(snp->srcu_gp_seq_needed_exp, s);
 		spin_unlock_irqrestore_rcu_node(snp, flags);
 	}
 
@@ -674,7 +687,7 @@ static void srcu_funnel_gp_start(struct srcu_struct *ssp, struct srcu_data *sdp,
 		smp_store_release(&ssp->srcu_gp_seq_needed, s); /*^^^*/
 	}
 	if (!do_norm && ULONG_CMP_LT(ssp->srcu_gp_seq_needed_exp, s))
-		ssp->srcu_gp_seq_needed_exp = s;
+		WRITE_ONCE(ssp->srcu_gp_seq_needed_exp, s);
 
 	/* If grace period not already done and none in progress, start it. */
 	if (!rcu_seq_done(&ssp->srcu_gp_seq, s) &&
@@ -753,7 +766,7 @@ static void srcu_flip(struct srcu_struct *ssp)
  * it, if this function was preempted for enough time for the counters
  * to wrap, it really doesn't matter whether or not we expedite the grace
  * period.  The extra overhead of a needlessly expedited grace period is
- * negligible when amoritized over that time period, and the extra latency
+ * negligible when amortized over that time period, and the extra latency
  * of a needlessly non-expedited grace period is similarly negligible.
  */
 static bool srcu_might_be_idle(struct srcu_struct *ssp)
@@ -764,14 +777,15 @@ static bool srcu_might_be_idle(struct srcu_struct *ssp)
 	unsigned long t;
 	unsigned long tlast;
 
+	check_init_srcu_struct(ssp);
 	/* If the local srcu_data structure has callbacks, not idle.  */
-	local_irq_save(flags);
-	sdp = this_cpu_ptr(ssp->sda);
+	sdp = raw_cpu_ptr(ssp->sda);
+	spin_lock_irqsave_rcu_node(sdp, flags);
 	if (rcu_segcblist_pend_cbs(&sdp->srcu_cblist)) {
-		local_irq_restore(flags);
+		spin_unlock_irqrestore_rcu_node(sdp, flags);
 		return false; /* Callbacks already present, so not idle. */
 	}
-	local_irq_restore(flags);
+	spin_unlock_irqrestore_rcu_node(sdp, flags);
 
 	/*
 	 * No local callbacks, so probabalistically probe global state.
@@ -851,9 +865,8 @@ static void __call_srcu(struct srcu_struct *ssp, struct rcu_head *rhp,
 	}
 	rhp->func = func;
 	idx = srcu_read_lock(ssp);
-	local_irq_save(flags);
-	sdp = this_cpu_ptr(ssp->sda);
-	spin_lock_rcu_node(sdp);
+	sdp = raw_cpu_ptr(ssp->sda);
+	spin_lock_irqsave_rcu_node(sdp, flags);
 	rcu_segcblist_enqueue(&sdp->srcu_cblist, rhp);
 	rcu_segcblist_advance(&sdp->srcu_cblist,
 			      rcu_seq_current(&ssp->srcu_gp_seq));
@@ -1079,7 +1092,7 @@ EXPORT_SYMBOL_GPL(srcu_barrier);
  */
 unsigned long srcu_batches_completed(struct srcu_struct *ssp)
 {
-	return ssp->srcu_idx;
+	return READ_ONCE(ssp->srcu_idx);
 }
 EXPORT_SYMBOL_GPL(srcu_batches_completed);
 
@@ -1130,7 +1143,9 @@ static void srcu_advance_state(struct srcu_struct *ssp)
 			return; /* readers present, retry later. */
 		}
 		srcu_flip(ssp);
+		spin_lock_irq_rcu_node(ssp);
 		rcu_seq_set_state(&ssp->srcu_gp_seq, SRCU_STATE_SCAN2);
+		spin_unlock_irq_rcu_node(ssp);
 	}
 
 	if (rcu_seq_state(READ_ONCE(ssp->srcu_gp_seq)) == SRCU_STATE_SCAN2) {
@@ -1266,8 +1281,8 @@ void srcu_torture_stats_print(struct srcu_struct *ssp, char *tt, char *tf)
 		struct srcu_data *sdp;
 
 		sdp = per_cpu_ptr(ssp->sda, cpu);
-		u0 = sdp->srcu_unlock_count[!idx];
-		u1 = sdp->srcu_unlock_count[idx];
+		u0 = data_race(sdp->srcu_unlock_count[!idx]);
+		u1 = data_race(sdp->srcu_unlock_count[idx]);
 
 		/*
 		 * Make sure that a lock is always counted if the corresponding
@@ -1275,8 +1290,8 @@ void srcu_torture_stats_print(struct srcu_struct *ssp, char *tt, char *tf)
 		 */
 		smp_rmb();
 
-		l0 = sdp->srcu_lock_count[!idx];
-		l1 = sdp->srcu_lock_count[idx];
+		l0 = data_race(sdp->srcu_lock_count[!idx]);
+		l1 = data_race(sdp->srcu_lock_count[idx]);
 
 		c0 = l0 - u0;
 		c1 = l1 - u1;
diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h
new file mode 100644
index 000000000000..835e2df8590a
--- /dev/null
+++ b/kernel/rcu/tasks.h
@@ -0,0 +1,1206 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+/*
+ * Task-based RCU implementations.
+ *
+ * Copyright (C) 2020 Paul E. McKenney
+ */
+
+#ifdef CONFIG_TASKS_RCU_GENERIC
+
+////////////////////////////////////////////////////////////////////////
+//
+// Generic data structures.
+
+struct rcu_tasks;
+typedef void (*rcu_tasks_gp_func_t)(struct rcu_tasks *rtp);
+typedef void (*pregp_func_t)(void);
+typedef void (*pertask_func_t)(struct task_struct *t, struct list_head *hop);
+typedef void (*postscan_func_t)(struct list_head *hop);
+typedef void (*holdouts_func_t)(struct list_head *hop, bool ndrpt, bool *frptp);
+typedef void (*postgp_func_t)(struct rcu_tasks *rtp);
+
+/**
+ * Definition for a Tasks-RCU-like mechanism.
+ * @cbs_head: Head of callback list.
+ * @cbs_tail: Tail pointer for callback list.
+ * @cbs_wq: Wait queue allowning new callback to get kthread's attention.
+ * @cbs_lock: Lock protecting callback list.
+ * @kthread_ptr: This flavor's grace-period/callback-invocation kthread.
+ * @gp_func: This flavor's grace-period-wait function.
+ * @gp_state: Grace period's most recent state transition (debugging).
+ * @gp_jiffies: Time of last @gp_state transition.
+ * @gp_start: Most recent grace-period start in jiffies.
+ * @n_gps: Number of grace periods completed since boot.
+ * @n_ipis: Number of IPIs sent to encourage grace periods to end.
+ * @n_ipis_fails: Number of IPI-send failures.
+ * @pregp_func: This flavor's pre-grace-period function (optional).
+ * @pertask_func: This flavor's per-task scan function (optional).
+ * @postscan_func: This flavor's post-task scan function (optional).
+ * @holdout_func: This flavor's holdout-list scan function (optional).
+ * @postgp_func: This flavor's post-grace-period function (optional).
+ * @call_func: This flavor's call_rcu()-equivalent function.
+ * @name: This flavor's textual name.
+ * @kname: This flavor's kthread name.
+ */
+struct rcu_tasks {
+	struct rcu_head *cbs_head;
+	struct rcu_head **cbs_tail;
+	struct wait_queue_head cbs_wq;
+	raw_spinlock_t cbs_lock;
+	int gp_state;
+	unsigned long gp_jiffies;
+	unsigned long gp_start;
+	unsigned long n_gps;
+	unsigned long n_ipis;
+	unsigned long n_ipis_fails;
+	struct task_struct *kthread_ptr;
+	rcu_tasks_gp_func_t gp_func;
+	pregp_func_t pregp_func;
+	pertask_func_t pertask_func;
+	postscan_func_t postscan_func;
+	holdouts_func_t holdouts_func;
+	postgp_func_t postgp_func;
+	call_rcu_func_t call_func;
+	char *name;
+	char *kname;
+};
+
+#define DEFINE_RCU_TASKS(rt_name, gp, call, n)				\
+static struct rcu_tasks rt_name =					\
+{									\
+	.cbs_tail = &rt_name.cbs_head,					\
+	.cbs_wq = __WAIT_QUEUE_HEAD_INITIALIZER(rt_name.cbs_wq),	\
+	.cbs_lock = __RAW_SPIN_LOCK_UNLOCKED(rt_name.cbs_lock),		\
+	.gp_func = gp,							\
+	.call_func = call,						\
+	.name = n,							\
+	.kname = #rt_name,						\
+}
+
+/* Track exiting tasks in order to allow them to be waited for. */
+DEFINE_STATIC_SRCU(tasks_rcu_exit_srcu);
+
+/* Avoid IPIing CPUs early in the grace period. */
+#define RCU_TASK_IPI_DELAY (HZ / 2)
+static int rcu_task_ipi_delay __read_mostly = RCU_TASK_IPI_DELAY;
+module_param(rcu_task_ipi_delay, int, 0644);
+
+/* Control stall timeouts.  Disable with <= 0, otherwise jiffies till stall. */
+#define RCU_TASK_STALL_TIMEOUT (HZ * 60 * 10)
+static int rcu_task_stall_timeout __read_mostly = RCU_TASK_STALL_TIMEOUT;
+module_param(rcu_task_stall_timeout, int, 0644);
+
+/* RCU tasks grace-period state for debugging. */
+#define RTGS_INIT		 0
+#define RTGS_WAIT_WAIT_CBS	 1
+#define RTGS_WAIT_GP		 2
+#define RTGS_PRE_WAIT_GP	 3
+#define RTGS_SCAN_TASKLIST	 4
+#define RTGS_POST_SCAN_TASKLIST	 5
+#define RTGS_WAIT_SCAN_HOLDOUTS	 6
+#define RTGS_SCAN_HOLDOUTS	 7
+#define RTGS_POST_GP		 8
+#define RTGS_WAIT_READERS	 9
+#define RTGS_INVOKE_CBS		10
+#define RTGS_WAIT_CBS		11
+#ifndef CONFIG_TINY_RCU
+static const char * const rcu_tasks_gp_state_names[] = {
+	"RTGS_INIT",
+	"RTGS_WAIT_WAIT_CBS",
+	"RTGS_WAIT_GP",
+	"RTGS_PRE_WAIT_GP",
+	"RTGS_SCAN_TASKLIST",
+	"RTGS_POST_SCAN_TASKLIST",
+	"RTGS_WAIT_SCAN_HOLDOUTS",
+	"RTGS_SCAN_HOLDOUTS",
+	"RTGS_POST_GP",
+	"RTGS_WAIT_READERS",
+	"RTGS_INVOKE_CBS",
+	"RTGS_WAIT_CBS",
+};
+#endif /* #ifndef CONFIG_TINY_RCU */
+
+////////////////////////////////////////////////////////////////////////
+//
+// Generic code.
+
+/* Record grace-period phase and time. */
+static void set_tasks_gp_state(struct rcu_tasks *rtp, int newstate)
+{
+	rtp->gp_state = newstate;
+	rtp->gp_jiffies = jiffies;
+}
+
+#ifndef CONFIG_TINY_RCU
+/* Return state name. */
+static const char *tasks_gp_state_getname(struct rcu_tasks *rtp)
+{
+	int i = data_race(rtp->gp_state); // Let KCSAN detect update races
+	int j = READ_ONCE(i); // Prevent the compiler from reading twice
+
+	if (j >= ARRAY_SIZE(rcu_tasks_gp_state_names))
+		return "???";
+	return rcu_tasks_gp_state_names[j];
+}
+#endif /* #ifndef CONFIG_TINY_RCU */
+
+// Enqueue a callback for the specified flavor of Tasks RCU.
+static void call_rcu_tasks_generic(struct rcu_head *rhp, rcu_callback_t func,
+				   struct rcu_tasks *rtp)
+{
+	unsigned long flags;
+	bool needwake;
+
+	rhp->next = NULL;
+	rhp->func = func;
+	raw_spin_lock_irqsave(&rtp->cbs_lock, flags);
+	needwake = !rtp->cbs_head;
+	WRITE_ONCE(*rtp->cbs_tail, rhp);
+	rtp->cbs_tail = &rhp->next;
+	raw_spin_unlock_irqrestore(&rtp->cbs_lock, flags);
+	/* We can't create the thread unless interrupts are enabled. */
+	if (needwake && READ_ONCE(rtp->kthread_ptr))
+		wake_up(&rtp->cbs_wq);
+}
+
+// Wait for a grace period for the specified flavor of Tasks RCU.
+static void synchronize_rcu_tasks_generic(struct rcu_tasks *rtp)
+{
+	/* Complain if the scheduler has not started.  */
+	RCU_LOCKDEP_WARN(rcu_scheduler_active == RCU_SCHEDULER_INACTIVE,
+			 "synchronize_rcu_tasks called too soon");
+
+	/* Wait for the grace period. */
+	wait_rcu_gp(rtp->call_func);
+}
+
+/* RCU-tasks kthread that detects grace periods and invokes callbacks. */
+static int __noreturn rcu_tasks_kthread(void *arg)
+{
+	unsigned long flags;
+	struct rcu_head *list;
+	struct rcu_head *next;
+	struct rcu_tasks *rtp = arg;
+
+	/* Run on housekeeping CPUs by default.  Sysadm can move if desired. */
+	housekeeping_affine(current, HK_FLAG_RCU);
+	WRITE_ONCE(rtp->kthread_ptr, current); // Let GPs start!
+
+	/*
+	 * Each pass through the following loop makes one check for
+	 * newly arrived callbacks, and, if there are some, waits for
+	 * one RCU-tasks grace period and then invokes the callbacks.
+	 * This loop is terminated by the system going down.  ;-)
+	 */
+	for (;;) {
+
+		/* Pick up any new callbacks. */
+		raw_spin_lock_irqsave(&rtp->cbs_lock, flags);
+		smp_mb__after_spinlock(); // Order updates vs. GP.
+		list = rtp->cbs_head;
+		rtp->cbs_head = NULL;
+		rtp->cbs_tail = &rtp->cbs_head;
+		raw_spin_unlock_irqrestore(&rtp->cbs_lock, flags);
+
+		/* If there were none, wait a bit and start over. */
+		if (!list) {
+			wait_event_interruptible(rtp->cbs_wq,
+						 READ_ONCE(rtp->cbs_head));
+			if (!rtp->cbs_head) {
+				WARN_ON(signal_pending(current));
+				set_tasks_gp_state(rtp, RTGS_WAIT_WAIT_CBS);
+				schedule_timeout_idle(HZ/10);
+			}
+			continue;
+		}
+
+		// Wait for one grace period.
+		set_tasks_gp_state(rtp, RTGS_WAIT_GP);
+		rtp->gp_start = jiffies;
+		rtp->gp_func(rtp);
+		rtp->n_gps++;
+
+		/* Invoke the callbacks. */
+		set_tasks_gp_state(rtp, RTGS_INVOKE_CBS);
+		while (list) {
+			next = list->next;
+			local_bh_disable();
+			list->func(list);
+			local_bh_enable();
+			list = next;
+			cond_resched();
+		}
+		/* Paranoid sleep to keep this from entering a tight loop */
+		schedule_timeout_idle(HZ/10);
+
+		set_tasks_gp_state(rtp, RTGS_WAIT_CBS);
+	}
+}
+
+/* Spawn RCU-tasks grace-period kthread, e.g., at core_initcall() time. */
+static void __init rcu_spawn_tasks_kthread_generic(struct rcu_tasks *rtp)
+{
+	struct task_struct *t;
+
+	t = kthread_run(rcu_tasks_kthread, rtp, "%s_kthread", rtp->kname);
+	if (WARN_ONCE(IS_ERR(t), "%s: Could not start %s grace-period kthread, OOM is now expected behavior\n", __func__, rtp->name))
+		return;
+	smp_mb(); /* Ensure others see full kthread. */
+}
+
+#ifndef CONFIG_TINY_RCU
+
+/*
+ * Print any non-default Tasks RCU settings.
+ */
+static void __init rcu_tasks_bootup_oddness(void)
+{
+#if defined(CONFIG_TASKS_RCU) || defined(CONFIG_TASKS_TRACE_RCU)
+	if (rcu_task_stall_timeout != RCU_TASK_STALL_TIMEOUT)
+		pr_info("\tTasks-RCU CPU stall warnings timeout set to %d (rcu_task_stall_timeout).\n", rcu_task_stall_timeout);
+#endif /* #ifdef CONFIG_TASKS_RCU */
+#ifdef CONFIG_TASKS_RCU
+	pr_info("\tTrampoline variant of Tasks RCU enabled.\n");
+#endif /* #ifdef CONFIG_TASKS_RCU */
+#ifdef CONFIG_TASKS_RUDE_RCU
+	pr_info("\tRude variant of Tasks RCU enabled.\n");
+#endif /* #ifdef CONFIG_TASKS_RUDE_RCU */
+#ifdef CONFIG_TASKS_TRACE_RCU
+	pr_info("\tTracing variant of Tasks RCU enabled.\n");
+#endif /* #ifdef CONFIG_TASKS_TRACE_RCU */
+}
+
+#endif /* #ifndef CONFIG_TINY_RCU */
+
+#ifndef CONFIG_TINY_RCU
+/* Dump out rcutorture-relevant state common to all RCU-tasks flavors. */
+static void show_rcu_tasks_generic_gp_kthread(struct rcu_tasks *rtp, char *s)
+{
+	pr_info("%s: %s(%d) since %lu g:%lu i:%lu/%lu %c%c %s\n",
+		rtp->kname,
+		tasks_gp_state_getname(rtp), data_race(rtp->gp_state),
+		jiffies - data_race(rtp->gp_jiffies),
+		data_race(rtp->n_gps),
+		data_race(rtp->n_ipis_fails), data_race(rtp->n_ipis),
+		".k"[!!data_race(rtp->kthread_ptr)],
+		".C"[!!data_race(rtp->cbs_head)],
+		s);
+}
+#endif /* #ifndef CONFIG_TINY_RCU */
+
+static void exit_tasks_rcu_finish_trace(struct task_struct *t);
+
+#if defined(CONFIG_TASKS_RCU) || defined(CONFIG_TASKS_TRACE_RCU)
+
+////////////////////////////////////////////////////////////////////////
+//
+// Shared code between task-list-scanning variants of Tasks RCU.
+
+/* Wait for one RCU-tasks grace period. */
+static void rcu_tasks_wait_gp(struct rcu_tasks *rtp)
+{
+	struct task_struct *g, *t;
+	unsigned long lastreport;
+	LIST_HEAD(holdouts);
+	int fract;
+
+	set_tasks_gp_state(rtp, RTGS_PRE_WAIT_GP);
+	rtp->pregp_func();
+
+	/*
+	 * There were callbacks, so we need to wait for an RCU-tasks
+	 * grace period.  Start off by scanning the task list for tasks
+	 * that are not already voluntarily blocked.  Mark these tasks
+	 * and make a list of them in holdouts.
+	 */
+	set_tasks_gp_state(rtp, RTGS_SCAN_TASKLIST);
+	rcu_read_lock();
+	for_each_process_thread(g, t)
+		rtp->pertask_func(t, &holdouts);
+	rcu_read_unlock();
+
+	set_tasks_gp_state(rtp, RTGS_POST_SCAN_TASKLIST);
+	rtp->postscan_func(&holdouts);
+
+	/*
+	 * Each pass through the following loop scans the list of holdout
+	 * tasks, removing any that are no longer holdouts.  When the list
+	 * is empty, we are done.
+	 */
+	lastreport = jiffies;
+
+	/* Start off with HZ/10 wait and slowly back off to 1 HZ wait. */
+	fract = 10;
+
+	for (;;) {
+		bool firstreport;
+		bool needreport;
+		int rtst;
+
+		if (list_empty(&holdouts))
+			break;
+
+		/* Slowly back off waiting for holdouts */
+		set_tasks_gp_state(rtp, RTGS_WAIT_SCAN_HOLDOUTS);
+		schedule_timeout_idle(HZ/fract);
+
+		if (fract > 1)
+			fract--;
+
+		rtst = READ_ONCE(rcu_task_stall_timeout);
+		needreport = rtst > 0 && time_after(jiffies, lastreport + rtst);
+		if (needreport)
+			lastreport = jiffies;
+		firstreport = true;
+		WARN_ON(signal_pending(current));
+		set_tasks_gp_state(rtp, RTGS_SCAN_HOLDOUTS);
+		rtp->holdouts_func(&holdouts, needreport, &firstreport);
+	}
+
+	set_tasks_gp_state(rtp, RTGS_POST_GP);
+	rtp->postgp_func(rtp);
+}
+
+#endif /* #if defined(CONFIG_TASKS_RCU) || defined(CONFIG_TASKS_TRACE_RCU) */
+
+#ifdef CONFIG_TASKS_RCU
+
+////////////////////////////////////////////////////////////////////////
+//
+// Simple variant of RCU whose quiescent states are voluntary context
+// switch, cond_resched_rcu_qs(), user-space execution, and idle.
+// As such, grace periods can take one good long time.  There are no
+// read-side primitives similar to rcu_read_lock() and rcu_read_unlock()
+// because this implementation is intended to get the system into a safe
+// state for some of the manipulations involved in tracing and the like.
+// Finally, this implementation does not support high call_rcu_tasks()
+// rates from multiple CPUs.  If this is required, per-CPU callback lists
+// will be needed.
+
+/* Pre-grace-period preparation. */
+static void rcu_tasks_pregp_step(void)
+{
+	/*
+	 * Wait for all pre-existing t->on_rq and t->nvcsw transitions
+	 * to complete.  Invoking synchronize_rcu() suffices because all
+	 * these transitions occur with interrupts disabled.  Without this
+	 * synchronize_rcu(), a read-side critical section that started
+	 * before the grace period might be incorrectly seen as having
+	 * started after the grace period.
+	 *
+	 * This synchronize_rcu() also dispenses with the need for a
+	 * memory barrier on the first store to t->rcu_tasks_holdout,
+	 * as it forces the store to happen after the beginning of the
+	 * grace period.
+	 */
+	synchronize_rcu();
+}
+
+/* Per-task initial processing. */
+static void rcu_tasks_pertask(struct task_struct *t, struct list_head *hop)
+{
+	if (t != current && READ_ONCE(t->on_rq) && !is_idle_task(t)) {
+		get_task_struct(t);
+		t->rcu_tasks_nvcsw = READ_ONCE(t->nvcsw);
+		WRITE_ONCE(t->rcu_tasks_holdout, true);
+		list_add(&t->rcu_tasks_holdout_list, hop);
+	}
+}
+
+/* Processing between scanning taskslist and draining the holdout list. */
+static void rcu_tasks_postscan(struct list_head *hop)
+{
+	/*
+	 * Wait for tasks that are in the process of exiting.  This
+	 * does only part of the job, ensuring that all tasks that were
+	 * previously exiting reach the point where they have disabled
+	 * preemption, allowing the later synchronize_rcu() to finish
+	 * the job.
+	 */
+	synchronize_srcu(&tasks_rcu_exit_srcu);
+}
+
+/* See if tasks are still holding out, complain if so. */
+static void check_holdout_task(struct task_struct *t,
+			       bool needreport, bool *firstreport)
+{
+	int cpu;
+
+	if (!READ_ONCE(t->rcu_tasks_holdout) ||
+	    t->rcu_tasks_nvcsw != READ_ONCE(t->nvcsw) ||
+	    !READ_ONCE(t->on_rq) ||
+	    (IS_ENABLED(CONFIG_NO_HZ_FULL) &&
+	     !is_idle_task(t) && t->rcu_tasks_idle_cpu >= 0)) {
+		WRITE_ONCE(t->rcu_tasks_holdout, false);
+		list_del_init(&t->rcu_tasks_holdout_list);
+		put_task_struct(t);
+		return;
+	}
+	rcu_request_urgent_qs_task(t);
+	if (!needreport)
+		return;
+	if (*firstreport) {
+		pr_err("INFO: rcu_tasks detected stalls on tasks:\n");
+		*firstreport = false;
+	}
+	cpu = task_cpu(t);
+	pr_alert("%p: %c%c nvcsw: %lu/%lu holdout: %d idle_cpu: %d/%d\n",
+		 t, ".I"[is_idle_task(t)],
+		 "N."[cpu < 0 || !tick_nohz_full_cpu(cpu)],
+		 t->rcu_tasks_nvcsw, t->nvcsw, t->rcu_tasks_holdout,
+		 t->rcu_tasks_idle_cpu, cpu);
+	sched_show_task(t);
+}
+
+/* Scan the holdout lists for tasks no longer holding out. */
+static void check_all_holdout_tasks(struct list_head *hop,
+				    bool needreport, bool *firstreport)
+{
+	struct task_struct *t, *t1;
+
+	list_for_each_entry_safe(t, t1, hop, rcu_tasks_holdout_list) {
+		check_holdout_task(t, needreport, firstreport);
+		cond_resched();
+	}
+}
+
+/* Finish off the Tasks-RCU grace period. */
+static void rcu_tasks_postgp(struct rcu_tasks *rtp)
+{
+	/*
+	 * Because ->on_rq and ->nvcsw are not guaranteed to have a full
+	 * memory barriers prior to them in the schedule() path, memory
+	 * reordering on other CPUs could cause their RCU-tasks read-side
+	 * critical sections to extend past the end of the grace period.
+	 * However, because these ->nvcsw updates are carried out with
+	 * interrupts disabled, we can use synchronize_rcu() to force the
+	 * needed ordering on all such CPUs.
+	 *
+	 * This synchronize_rcu() also confines all ->rcu_tasks_holdout
+	 * accesses to be within the grace period, avoiding the need for
+	 * memory barriers for ->rcu_tasks_holdout accesses.
+	 *
+	 * In addition, this synchronize_rcu() waits for exiting tasks
+	 * to complete their final preempt_disable() region of execution,
+	 * cleaning up after the synchronize_srcu() above.
+	 */
+	synchronize_rcu();
+}
+
+void call_rcu_tasks(struct rcu_head *rhp, rcu_callback_t func);
+DEFINE_RCU_TASKS(rcu_tasks, rcu_tasks_wait_gp, call_rcu_tasks, "RCU Tasks");
+
+/**
+ * call_rcu_tasks() - Queue an RCU for invocation task-based grace period
+ * @rhp: structure to be used for queueing the RCU updates.
+ * @func: actual callback function to be invoked after the grace period
+ *
+ * The callback function will be invoked some time after a full grace
+ * period elapses, in other words after all currently executing RCU
+ * read-side critical sections have completed. call_rcu_tasks() assumes
+ * that the read-side critical sections end at a voluntary context
+ * switch (not a preemption!), cond_resched_rcu_qs(), entry into idle,
+ * or transition to usermode execution.  As such, there are no read-side
+ * primitives analogous to rcu_read_lock() and rcu_read_unlock() because
+ * this primitive is intended to determine that all tasks have passed
+ * through a safe state, not so much for data-strcuture synchronization.
+ *
+ * See the description of call_rcu() for more detailed information on
+ * memory ordering guarantees.
+ */
+void call_rcu_tasks(struct rcu_head *rhp, rcu_callback_t func)
+{
+	call_rcu_tasks_generic(rhp, func, &rcu_tasks);
+}
+EXPORT_SYMBOL_GPL(call_rcu_tasks);
+
+/**
+ * synchronize_rcu_tasks - wait until an rcu-tasks grace period has elapsed.
+ *
+ * Control will return to the caller some time after a full rcu-tasks
+ * grace period has elapsed, in other words after all currently
+ * executing rcu-tasks read-side critical sections have elapsed.  These
+ * read-side critical sections are delimited by calls to schedule(),
+ * cond_resched_tasks_rcu_qs(), idle execution, userspace execution, calls
+ * to synchronize_rcu_tasks(), and (in theory, anyway) cond_resched().
+ *
+ * This is a very specialized primitive, intended only for a few uses in
+ * tracing and other situations requiring manipulation of function
+ * preambles and profiling hooks.  The synchronize_rcu_tasks() function
+ * is not (yet) intended for heavy use from multiple CPUs.
+ *
+ * See the description of synchronize_rcu() for more detailed information
+ * on memory ordering guarantees.
+ */
+void synchronize_rcu_tasks(void)
+{
+	synchronize_rcu_tasks_generic(&rcu_tasks);
+}
+EXPORT_SYMBOL_GPL(synchronize_rcu_tasks);
+
+/**
+ * rcu_barrier_tasks - Wait for in-flight call_rcu_tasks() callbacks.
+ *
+ * Although the current implementation is guaranteed to wait, it is not
+ * obligated to, for example, if there are no pending callbacks.
+ */
+void rcu_barrier_tasks(void)
+{
+	/* There is only one callback queue, so this is easy.  ;-) */
+	synchronize_rcu_tasks();
+}
+EXPORT_SYMBOL_GPL(rcu_barrier_tasks);
+
+static int __init rcu_spawn_tasks_kthread(void)
+{
+	rcu_tasks.pregp_func = rcu_tasks_pregp_step;
+	rcu_tasks.pertask_func = rcu_tasks_pertask;
+	rcu_tasks.postscan_func = rcu_tasks_postscan;
+	rcu_tasks.holdouts_func = check_all_holdout_tasks;
+	rcu_tasks.postgp_func = rcu_tasks_postgp;
+	rcu_spawn_tasks_kthread_generic(&rcu_tasks);
+	return 0;
+}
+core_initcall(rcu_spawn_tasks_kthread);
+
+#ifndef CONFIG_TINY_RCU
+static void show_rcu_tasks_classic_gp_kthread(void)
+{
+	show_rcu_tasks_generic_gp_kthread(&rcu_tasks, "");
+}
+#endif /* #ifndef CONFIG_TINY_RCU */
+
+/* Do the srcu_read_lock() for the above synchronize_srcu().  */
+void exit_tasks_rcu_start(void) __acquires(&tasks_rcu_exit_srcu)
+{
+	preempt_disable();
+	current->rcu_tasks_idx = __srcu_read_lock(&tasks_rcu_exit_srcu);
+	preempt_enable();
+}
+
+/* Do the srcu_read_unlock() for the above synchronize_srcu().  */
+void exit_tasks_rcu_finish(void) __releases(&tasks_rcu_exit_srcu)
+{
+	struct task_struct *t = current;
+
+	preempt_disable();
+	__srcu_read_unlock(&tasks_rcu_exit_srcu, t->rcu_tasks_idx);
+	preempt_enable();
+	exit_tasks_rcu_finish_trace(t);
+}
+
+#else /* #ifdef CONFIG_TASKS_RCU */
+static 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 */
+
+#ifdef CONFIG_TASKS_RUDE_RCU
+
+////////////////////////////////////////////////////////////////////////
+//
+// "Rude" variant of Tasks RCU, inspired by Steve Rostedt's trick of
+// passing an empty function to schedule_on_each_cpu().  This approach
+// provides an asynchronous call_rcu_tasks_rude() API and batching
+// of concurrent calls to the synchronous synchronize_rcu_rude() API.
+// This sends IPIs far and wide and induces otherwise unnecessary context
+// switches on all online CPUs, whether idle or not.
+
+// Empty function to allow workqueues to force a context switch.
+static void rcu_tasks_be_rude(struct work_struct *work)
+{
+}
+
+// Wait for one rude RCU-tasks grace period.
+static void rcu_tasks_rude_wait_gp(struct rcu_tasks *rtp)
+{
+	rtp->n_ipis += cpumask_weight(cpu_online_mask);
+	schedule_on_each_cpu(rcu_tasks_be_rude);
+}
+
+void call_rcu_tasks_rude(struct rcu_head *rhp, rcu_callback_t func);
+DEFINE_RCU_TASKS(rcu_tasks_rude, rcu_tasks_rude_wait_gp, call_rcu_tasks_rude,
+		 "RCU Tasks Rude");
+
+/**
+ * call_rcu_tasks_rude() - Queue a callback rude task-based grace period
+ * @rhp: structure to be used for queueing the RCU updates.
+ * @func: actual callback function to be invoked after the grace period
+ *
+ * The callback function will be invoked some time after a full grace
+ * period elapses, in other words after all currently executing RCU
+ * read-side critical sections have completed. call_rcu_tasks_rude()
+ * assumes that the read-side critical sections end at context switch,
+ * cond_resched_rcu_qs(), or transition to usermode execution.  As such,
+ * there are no read-side primitives analogous to rcu_read_lock() and
+ * rcu_read_unlock() because this primitive is intended to determine
+ * that all tasks have passed through a safe state, not so much for
+ * data-strcuture synchronization.
+ *
+ * See the description of call_rcu() for more detailed information on
+ * memory ordering guarantees.
+ */
+void call_rcu_tasks_rude(struct rcu_head *rhp, rcu_callback_t func)
+{
+	call_rcu_tasks_generic(rhp, func, &rcu_tasks_rude);
+}
+EXPORT_SYMBOL_GPL(call_rcu_tasks_rude);
+
+/**
+ * synchronize_rcu_tasks_rude - wait for a rude rcu-tasks grace period
+ *
+ * Control will return to the caller some time after a rude rcu-tasks
+ * grace period has elapsed, in other words after all currently
+ * executing rcu-tasks read-side critical sections have elapsed.  These
+ * read-side critical sections are delimited by calls to schedule(),
+ * cond_resched_tasks_rcu_qs(), userspace execution, and (in theory,
+ * anyway) cond_resched().
+ *
+ * This is a very specialized primitive, intended only for a few uses in
+ * tracing and other situations requiring manipulation of function preambles
+ * and profiling hooks.  The synchronize_rcu_tasks_rude() function is not
+ * (yet) intended for heavy use from multiple CPUs.
+ *
+ * See the description of synchronize_rcu() for more detailed information
+ * on memory ordering guarantees.
+ */
+void synchronize_rcu_tasks_rude(void)
+{
+	synchronize_rcu_tasks_generic(&rcu_tasks_rude);
+}
+EXPORT_SYMBOL_GPL(synchronize_rcu_tasks_rude);
+
+/**
+ * rcu_barrier_tasks_rude - Wait for in-flight call_rcu_tasks_rude() callbacks.
+ *
+ * Although the current implementation is guaranteed to wait, it is not
+ * obligated to, for example, if there are no pending callbacks.
+ */
+void rcu_barrier_tasks_rude(void)
+{
+	/* There is only one callback queue, so this is easy.  ;-) */
+	synchronize_rcu_tasks_rude();
+}
+EXPORT_SYMBOL_GPL(rcu_barrier_tasks_rude);
+
+static int __init rcu_spawn_tasks_rude_kthread(void)
+{
+	rcu_spawn_tasks_kthread_generic(&rcu_tasks_rude);
+	return 0;
+}
+core_initcall(rcu_spawn_tasks_rude_kthread);
+
+#ifndef CONFIG_TINY_RCU
+static void show_rcu_tasks_rude_gp_kthread(void)
+{
+	show_rcu_tasks_generic_gp_kthread(&rcu_tasks_rude, "");
+}
+#endif /* #ifndef CONFIG_TINY_RCU */
+
+#else /* #ifdef CONFIG_TASKS_RUDE_RCU */
+static void show_rcu_tasks_rude_gp_kthread(void) {}
+#endif /* #else #ifdef CONFIG_TASKS_RUDE_RCU */
+
+////////////////////////////////////////////////////////////////////////
+//
+// Tracing variant of Tasks RCU.  This variant is designed to be used
+// to protect tracing hooks, including those of BPF.  This variant
+// therefore:
+//
+// 1.	Has explicit read-side markers to allow finite grace periods
+//	in the face of in-kernel loops for PREEMPT=n builds.
+//
+// 2.	Protects code in the idle loop, exception entry/exit, and
+//	CPU-hotplug code paths, similar to the capabilities of SRCU.
+//
+// 3.	Avoids expensive read-side instruction, having overhead similar
+//	to that of Preemptible RCU.
+//
+// There are of course downsides.  The grace-period code can send IPIs to
+// CPUs, even when those CPUs are in the idle loop or in nohz_full userspace.
+// It is necessary to scan the full tasklist, much as for Tasks RCU.  There
+// is a single callback queue guarded by a single lock, again, much as for
+// Tasks RCU.  If needed, these downsides can be at least partially remedied.
+//
+// Perhaps most important, this variant of RCU does not affect the vanilla
+// flavors, rcu_preempt and rcu_sched.  The fact that RCU Tasks Trace
+// readers can operate from idle, offline, and exception entry/exit in no
+// way allows rcu_preempt and rcu_sched readers to also do so.
+
+// The lockdep state must be outside of #ifdef to be useful.
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+static struct lock_class_key rcu_lock_trace_key;
+struct lockdep_map rcu_trace_lock_map =
+	STATIC_LOCKDEP_MAP_INIT("rcu_read_lock_trace", &rcu_lock_trace_key);
+EXPORT_SYMBOL_GPL(rcu_trace_lock_map);
+#endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
+
+#ifdef CONFIG_TASKS_TRACE_RCU
+
+static atomic_t trc_n_readers_need_end;		// Number of waited-for readers.
+static DECLARE_WAIT_QUEUE_HEAD(trc_wait);	// List of holdout tasks.
+
+// Record outstanding IPIs to each CPU.  No point in sending two...
+static DEFINE_PER_CPU(bool, trc_ipi_to_cpu);
+
+// The number of detections of task quiescent state relying on
+// heavyweight readers executing explicit memory barriers.
+unsigned long n_heavy_reader_attempts;
+unsigned long n_heavy_reader_updates;
+unsigned long n_heavy_reader_ofl_updates;
+
+void call_rcu_tasks_trace(struct rcu_head *rhp, rcu_callback_t func);
+DEFINE_RCU_TASKS(rcu_tasks_trace, rcu_tasks_wait_gp, call_rcu_tasks_trace,
+		 "RCU Tasks Trace");
+
+/*
+ * This irq_work handler allows rcu_read_unlock_trace() to be invoked
+ * while the scheduler locks are held.
+ */
+static void rcu_read_unlock_iw(struct irq_work *iwp)
+{
+	wake_up(&trc_wait);
+}
+static DEFINE_IRQ_WORK(rcu_tasks_trace_iw, rcu_read_unlock_iw);
+
+/* If we are the last reader, wake up the grace-period kthread. */
+void rcu_read_unlock_trace_special(struct task_struct *t, int nesting)
+{
+	int nq = t->trc_reader_special.b.need_qs;
+
+	if (IS_ENABLED(CONFIG_TASKS_TRACE_RCU_READ_MB) &&
+	    t->trc_reader_special.b.need_mb)
+		smp_mb(); // Pairs with update-side barriers.
+	// Update .need_qs before ->trc_reader_nesting for irq/NMI handlers.
+	if (nq)
+		WRITE_ONCE(t->trc_reader_special.b.need_qs, false);
+	WRITE_ONCE(t->trc_reader_nesting, nesting);
+	if (nq && atomic_dec_and_test(&trc_n_readers_need_end))
+		irq_work_queue(&rcu_tasks_trace_iw);
+}
+EXPORT_SYMBOL_GPL(rcu_read_unlock_trace_special);
+
+/* Add a task to the holdout list, if it is not already on the list. */
+static void trc_add_holdout(struct task_struct *t, struct list_head *bhp)
+{
+	if (list_empty(&t->trc_holdout_list)) {
+		get_task_struct(t);
+		list_add(&t->trc_holdout_list, bhp);
+	}
+}
+
+/* Remove a task from the holdout list, if it is in fact present. */
+static void trc_del_holdout(struct task_struct *t)
+{
+	if (!list_empty(&t->trc_holdout_list)) {
+		list_del_init(&t->trc_holdout_list);
+		put_task_struct(t);
+	}
+}
+
+/* IPI handler to check task state. */
+static void trc_read_check_handler(void *t_in)
+{
+	struct task_struct *t = current;
+	struct task_struct *texp = t_in;
+
+	// If the task is no longer running on this CPU, leave.
+	if (unlikely(texp != t)) {
+		if (WARN_ON_ONCE(atomic_dec_and_test(&trc_n_readers_need_end)))
+			wake_up(&trc_wait);
+		goto reset_ipi; // Already on holdout list, so will check later.
+	}
+
+	// If the task is not in a read-side critical section, and
+	// if this is the last reader, awaken the grace-period kthread.
+	if (likely(!t->trc_reader_nesting)) {
+		if (WARN_ON_ONCE(atomic_dec_and_test(&trc_n_readers_need_end)))
+			wake_up(&trc_wait);
+		// Mark as checked after decrement to avoid false
+		// positives on the above WARN_ON_ONCE().
+		WRITE_ONCE(t->trc_reader_checked, true);
+		goto reset_ipi;
+	}
+	WRITE_ONCE(t->trc_reader_checked, true);
+
+	// Get here if the task is in a read-side critical section.  Set
+	// its state so that it will awaken the grace-period kthread upon
+	// exit from that critical section.
+	WARN_ON_ONCE(t->trc_reader_special.b.need_qs);
+	WRITE_ONCE(t->trc_reader_special.b.need_qs, true);
+
+reset_ipi:
+	// Allow future IPIs to be sent on CPU and for task.
+	// Also order this IPI handler against any later manipulations of
+	// the intended task.
+	smp_store_release(&per_cpu(trc_ipi_to_cpu, smp_processor_id()), false); // ^^^
+	smp_store_release(&texp->trc_ipi_to_cpu, -1); // ^^^
+}
+
+/* Callback function for scheduler to check locked-down task.  */
+static bool trc_inspect_reader(struct task_struct *t, void *arg)
+{
+	int cpu = task_cpu(t);
+	bool in_qs = false;
+	bool ofl = cpu_is_offline(cpu);
+
+	if (task_curr(t)) {
+		WARN_ON_ONCE(ofl && !is_idle_task(t));
+
+		// If no chance of heavyweight readers, do it the hard way.
+		if (!ofl && !IS_ENABLED(CONFIG_TASKS_TRACE_RCU_READ_MB))
+			return false;
+
+		// If heavyweight readers are enabled on the remote task,
+		// we can inspect its state despite its currently running.
+		// However, we cannot safely change its state.
+		n_heavy_reader_attempts++;
+		if (!ofl && // Check for "running" idle tasks on offline CPUs.
+		    !rcu_dynticks_zero_in_eqs(cpu, &t->trc_reader_nesting))
+			return false; // No quiescent state, do it the hard way.
+		n_heavy_reader_updates++;
+		if (ofl)
+			n_heavy_reader_ofl_updates++;
+		in_qs = true;
+	} else {
+		in_qs = likely(!t->trc_reader_nesting);
+	}
+
+	// Mark as checked.  Because this is called from the grace-period
+	// kthread, also remove the task from the holdout list.
+	t->trc_reader_checked = true;
+	trc_del_holdout(t);
+
+	if (in_qs)
+		return true;  // Already in quiescent state, done!!!
+
+	// The task is in a read-side critical section, so set up its
+	// state so that it will awaken the grace-period kthread upon exit
+	// from that critical section.
+	atomic_inc(&trc_n_readers_need_end); // One more to wait on.
+	WARN_ON_ONCE(t->trc_reader_special.b.need_qs);
+	WRITE_ONCE(t->trc_reader_special.b.need_qs, true);
+	return true;
+}
+
+/* Attempt to extract the state for the specified task. */
+static void trc_wait_for_one_reader(struct task_struct *t,
+				    struct list_head *bhp)
+{
+	int cpu;
+
+	// If a previous IPI is still in flight, let it complete.
+	if (smp_load_acquire(&t->trc_ipi_to_cpu) != -1) // Order IPI
+		return;
+
+	// The current task had better be in a quiescent state.
+	if (t == current) {
+		t->trc_reader_checked = true;
+		trc_del_holdout(t);
+		WARN_ON_ONCE(t->trc_reader_nesting);
+		return;
+	}
+
+	// Attempt to nail down the task for inspection.
+	get_task_struct(t);
+	if (try_invoke_on_locked_down_task(t, trc_inspect_reader, NULL)) {
+		put_task_struct(t);
+		return;
+	}
+	put_task_struct(t);
+
+	// If currently running, send an IPI, either way, add to list.
+	trc_add_holdout(t, bhp);
+	if (task_curr(t) && time_after(jiffies, rcu_tasks_trace.gp_start + rcu_task_ipi_delay)) {
+		// The task is currently running, so try IPIing it.
+		cpu = task_cpu(t);
+
+		// If there is already an IPI outstanding, let it happen.
+		if (per_cpu(trc_ipi_to_cpu, cpu) || t->trc_ipi_to_cpu >= 0)
+			return;
+
+		atomic_inc(&trc_n_readers_need_end);
+		per_cpu(trc_ipi_to_cpu, cpu) = true;
+		t->trc_ipi_to_cpu = cpu;
+		rcu_tasks_trace.n_ipis++;
+		if (smp_call_function_single(cpu,
+					     trc_read_check_handler, t, 0)) {
+			// Just in case there is some other reason for
+			// failure than the target CPU being offline.
+			rcu_tasks_trace.n_ipis_fails++;
+			per_cpu(trc_ipi_to_cpu, cpu) = false;
+			t->trc_ipi_to_cpu = cpu;
+			if (atomic_dec_and_test(&trc_n_readers_need_end)) {
+				WARN_ON_ONCE(1);
+				wake_up(&trc_wait);
+			}
+		}
+	}
+}
+
+/* Initialize for a new RCU-tasks-trace grace period. */
+static void rcu_tasks_trace_pregp_step(void)
+{
+	int cpu;
+
+	// Allow for fast-acting IPIs.
+	atomic_set(&trc_n_readers_need_end, 1);
+
+	// There shouldn't be any old IPIs, but...
+	for_each_possible_cpu(cpu)
+		WARN_ON_ONCE(per_cpu(trc_ipi_to_cpu, cpu));
+
+	// Disable CPU hotplug across the tasklist scan.
+	// This also waits for all readers in CPU-hotplug code paths.
+	cpus_read_lock();
+}
+
+/* Do first-round processing for the specified task. */
+static void rcu_tasks_trace_pertask(struct task_struct *t,
+				    struct list_head *hop)
+{
+	WRITE_ONCE(t->trc_reader_special.b.need_qs, false);
+	WRITE_ONCE(t->trc_reader_checked, false);
+	t->trc_ipi_to_cpu = -1;
+	trc_wait_for_one_reader(t, hop);
+}
+
+/*
+ * Do intermediate processing between task and holdout scans and
+ * pick up the idle tasks.
+ */
+static void rcu_tasks_trace_postscan(struct list_head *hop)
+{
+	int cpu;
+
+	for_each_possible_cpu(cpu)
+		rcu_tasks_trace_pertask(idle_task(cpu), hop);
+
+	// Re-enable CPU hotplug now that the tasklist scan has completed.
+	cpus_read_unlock();
+
+	// Wait for late-stage exiting tasks to finish exiting.
+	// These might have passed the call to exit_tasks_rcu_finish().
+	synchronize_rcu();
+	// Any tasks that exit after this point will set ->trc_reader_checked.
+}
+
+/* Show the state of a task stalling the current RCU tasks trace GP. */
+static void show_stalled_task_trace(struct task_struct *t, bool *firstreport)
+{
+	int cpu;
+
+	if (*firstreport) {
+		pr_err("INFO: rcu_tasks_trace detected stalls on tasks:\n");
+		*firstreport = false;
+	}
+	// FIXME: This should attempt to use try_invoke_on_nonrunning_task().
+	cpu = task_cpu(t);
+	pr_alert("P%d: %c%c%c nesting: %d%c cpu: %d\n",
+		 t->pid,
+		 ".I"[READ_ONCE(t->trc_ipi_to_cpu) > 0],
+		 ".i"[is_idle_task(t)],
+		 ".N"[cpu > 0 && tick_nohz_full_cpu(cpu)],
+		 t->trc_reader_nesting,
+		 " N"[!!t->trc_reader_special.b.need_qs],
+		 cpu);
+	sched_show_task(t);
+}
+
+/* List stalled IPIs for RCU tasks trace. */
+static void show_stalled_ipi_trace(void)
+{
+	int cpu;
+
+	for_each_possible_cpu(cpu)
+		if (per_cpu(trc_ipi_to_cpu, cpu))
+			pr_alert("\tIPI outstanding to CPU %d\n", cpu);
+}
+
+/* Do one scan of the holdout list. */
+static void check_all_holdout_tasks_trace(struct list_head *hop,
+					  bool needreport, bool *firstreport)
+{
+	struct task_struct *g, *t;
+
+	// Disable CPU hotplug across the holdout list scan.
+	cpus_read_lock();
+
+	list_for_each_entry_safe(t, g, hop, trc_holdout_list) {
+		// If safe and needed, try to check the current task.
+		if (READ_ONCE(t->trc_ipi_to_cpu) == -1 &&
+		    !READ_ONCE(t->trc_reader_checked))
+			trc_wait_for_one_reader(t, hop);
+
+		// If check succeeded, remove this task from the list.
+		if (READ_ONCE(t->trc_reader_checked))
+			trc_del_holdout(t);
+		else if (needreport)
+			show_stalled_task_trace(t, firstreport);
+	}
+
+	// Re-enable CPU hotplug now that the holdout list scan has completed.
+	cpus_read_unlock();
+
+	if (needreport) {
+		if (firstreport)
+			pr_err("INFO: rcu_tasks_trace detected stalls? (Late IPI?)\n");
+		show_stalled_ipi_trace();
+	}
+}
+
+/* Wait for grace period to complete and provide ordering. */
+static void rcu_tasks_trace_postgp(struct rcu_tasks *rtp)
+{
+	bool firstreport;
+	struct task_struct *g, *t;
+	LIST_HEAD(holdouts);
+	long ret;
+
+	// Remove the safety count.
+	smp_mb__before_atomic();  // Order vs. earlier atomics
+	atomic_dec(&trc_n_readers_need_end);
+	smp_mb__after_atomic();  // Order vs. later atomics
+
+	// Wait for readers.
+	set_tasks_gp_state(rtp, RTGS_WAIT_READERS);
+	for (;;) {
+		ret = wait_event_idle_exclusive_timeout(
+				trc_wait,
+				atomic_read(&trc_n_readers_need_end) == 0,
+				READ_ONCE(rcu_task_stall_timeout));
+		if (ret)
+			break;  // Count reached zero.
+		// Stall warning time, so make a list of the offenders.
+		for_each_process_thread(g, t)
+			if (READ_ONCE(t->trc_reader_special.b.need_qs))
+				trc_add_holdout(t, &holdouts);
+		firstreport = true;
+		list_for_each_entry_safe(t, g, &holdouts, trc_holdout_list)
+			if (READ_ONCE(t->trc_reader_special.b.need_qs)) {
+				show_stalled_task_trace(t, &firstreport);
+				trc_del_holdout(t);
+			}
+		if (firstreport)
+			pr_err("INFO: rcu_tasks_trace detected stalls? (Counter/taskslist mismatch?)\n");
+		show_stalled_ipi_trace();
+		pr_err("\t%d holdouts\n", atomic_read(&trc_n_readers_need_end));
+	}
+	smp_mb(); // Caller's code must be ordered after wakeup.
+		  // Pairs with pretty much every ordering primitive.
+}
+
+/* Report any needed quiescent state for this exiting task. */
+static void exit_tasks_rcu_finish_trace(struct task_struct *t)
+{
+	WRITE_ONCE(t->trc_reader_checked, true);
+	WARN_ON_ONCE(t->trc_reader_nesting);
+	WRITE_ONCE(t->trc_reader_nesting, 0);
+	if (WARN_ON_ONCE(READ_ONCE(t->trc_reader_special.b.need_qs)))
+		rcu_read_unlock_trace_special(t, 0);
+}
+
+/**
+ * call_rcu_tasks_trace() - Queue a callback trace task-based grace period
+ * @rhp: structure to be used for queueing the RCU updates.
+ * @func: actual callback function to be invoked after the grace period
+ *
+ * The callback function will be invoked some time after a full grace
+ * period elapses, in other words after all currently executing RCU
+ * read-side critical sections have completed. call_rcu_tasks_trace()
+ * assumes that the read-side critical sections end at context switch,
+ * cond_resched_rcu_qs(), or transition to usermode execution.  As such,
+ * there are no read-side primitives analogous to rcu_read_lock() and
+ * rcu_read_unlock() because this primitive is intended to determine
+ * that all tasks have passed through a safe state, not so much for
+ * data-strcuture synchronization.
+ *
+ * See the description of call_rcu() for more detailed information on
+ * memory ordering guarantees.
+ */
+void call_rcu_tasks_trace(struct rcu_head *rhp, rcu_callback_t func)
+{
+	call_rcu_tasks_generic(rhp, func, &rcu_tasks_trace);
+}
+EXPORT_SYMBOL_GPL(call_rcu_tasks_trace);
+
+/**
+ * synchronize_rcu_tasks_trace - wait for a trace rcu-tasks grace period
+ *
+ * Control will return to the caller some time after a trace rcu-tasks
+ * grace period has elapsed, in other words after all currently executing
+ * rcu-tasks read-side critical sections have elapsed.  These read-side
+ * critical sections are delimited by calls to rcu_read_lock_trace()
+ * and rcu_read_unlock_trace().
+ *
+ * This is a very specialized primitive, intended only for a few uses in
+ * tracing and other situations requiring manipulation of function preambles
+ * and profiling hooks.  The synchronize_rcu_tasks_trace() function is not
+ * (yet) intended for heavy use from multiple CPUs.
+ *
+ * See the description of synchronize_rcu() for more detailed information
+ * on memory ordering guarantees.
+ */
+void synchronize_rcu_tasks_trace(void)
+{
+	RCU_LOCKDEP_WARN(lock_is_held(&rcu_trace_lock_map), "Illegal synchronize_rcu_tasks_trace() in RCU Tasks Trace read-side critical section");
+	synchronize_rcu_tasks_generic(&rcu_tasks_trace);
+}
+EXPORT_SYMBOL_GPL(synchronize_rcu_tasks_trace);
+
+/**
+ * rcu_barrier_tasks_trace - Wait for in-flight call_rcu_tasks_trace() callbacks.
+ *
+ * Although the current implementation is guaranteed to wait, it is not
+ * obligated to, for example, if there are no pending callbacks.
+ */
+void rcu_barrier_tasks_trace(void)
+{
+	/* There is only one callback queue, so this is easy.  ;-) */
+	synchronize_rcu_tasks_trace();
+}
+EXPORT_SYMBOL_GPL(rcu_barrier_tasks_trace);
+
+static int __init rcu_spawn_tasks_trace_kthread(void)
+{
+	rcu_tasks_trace.pregp_func = rcu_tasks_trace_pregp_step;
+	rcu_tasks_trace.pertask_func = rcu_tasks_trace_pertask;
+	rcu_tasks_trace.postscan_func = rcu_tasks_trace_postscan;
+	rcu_tasks_trace.holdouts_func = check_all_holdout_tasks_trace;
+	rcu_tasks_trace.postgp_func = rcu_tasks_trace_postgp;
+	rcu_spawn_tasks_kthread_generic(&rcu_tasks_trace);
+	return 0;
+}
+core_initcall(rcu_spawn_tasks_trace_kthread);
+
+#ifndef CONFIG_TINY_RCU
+static void show_rcu_tasks_trace_gp_kthread(void)
+{
+	char buf[64];
+
+	sprintf(buf, "N%d h:%lu/%lu/%lu", atomic_read(&trc_n_readers_need_end),
+		data_race(n_heavy_reader_ofl_updates),
+		data_race(n_heavy_reader_updates),
+		data_race(n_heavy_reader_attempts));
+	show_rcu_tasks_generic_gp_kthread(&rcu_tasks_trace, buf);
+}
+#endif /* #ifndef CONFIG_TINY_RCU */
+
+#else /* #ifdef CONFIG_TASKS_TRACE_RCU */
+static void exit_tasks_rcu_finish_trace(struct task_struct *t) { }
+static inline void show_rcu_tasks_trace_gp_kthread(void) {}
+#endif /* #else #ifdef CONFIG_TASKS_TRACE_RCU */
+
+#ifndef CONFIG_TINY_RCU
+void show_rcu_tasks_gp_kthreads(void)
+{
+	show_rcu_tasks_classic_gp_kthread();
+	show_rcu_tasks_rude_gp_kthread();
+	show_rcu_tasks_trace_gp_kthread();
+}
+#endif /* #ifndef CONFIG_TINY_RCU */
+
+#else /* #ifdef CONFIG_TASKS_RCU_GENERIC */
+static inline void rcu_tasks_bootup_oddness(void) {}
+void show_rcu_tasks_gp_kthreads(void) {}
+#endif /* #else #ifdef CONFIG_TASKS_RCU_GENERIC */
diff --git a/kernel/rcu/tiny.c b/kernel/rcu/tiny.c
index dd572ce7c747..aa897c3f2e92 100644
--- a/kernel/rcu/tiny.c
+++ b/kernel/rcu/tiny.c
@@ -23,6 +23,7 @@
 #include <linux/cpu.h>
 #include <linux/prefetch.h>
 #include <linux/slab.h>
+#include <linux/mm.h>
 
 #include "rcu.h"
 
@@ -84,9 +85,9 @@ static inline bool rcu_reclaim_tiny(struct rcu_head *head)
 	unsigned long offset = (unsigned long)head->func;
 
 	rcu_lock_acquire(&rcu_callback_map);
-	if (__is_kfree_rcu_offset(offset)) {
-		trace_rcu_invoke_kfree_callback("", head, offset);
-		kfree((void *)head - offset);
+	if (__is_kvfree_rcu_offset(offset)) {
+		trace_rcu_invoke_kvfree_callback("", head, offset);
+		kvfree((void *)head - offset);
 		rcu_lock_release(&rcu_callback_map);
 		return true;
 	}
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index d91c9156fab2..8ce77d9ac716 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -1,12 +1,12 @@
 // SPDX-License-Identifier: GPL-2.0+
 /*
- * Read-Copy Update mechanism for mutual exclusion
+ * Read-Copy Update mechanism for mutual exclusion (tree-based version)
  *
  * Copyright IBM Corporation, 2008
  *
  * Authors: Dipankar Sarma <dipankar@in.ibm.com>
  *	    Manfred Spraul <manfred@colorfullife.com>
- *	    Paul E. McKenney <paulmck@linux.ibm.com> Hierarchical version
+ *	    Paul E. McKenney <paulmck@linux.ibm.com>
  *
  * Based on the original work by Paul McKenney <paulmck@linux.ibm.com>
  * and inputs from Rusty Russell, Andrea Arcangeli and Andi Kleen.
@@ -57,6 +57,9 @@
 #include <linux/slab.h>
 #include <linux/sched/isolation.h>
 #include <linux/sched/clock.h>
+#include <linux/vmalloc.h>
+#include <linux/mm.h>
+#include <linux/kasan.h>
 #include "../time/tick-internal.h"
 
 #include "tree.h"
@@ -67,6 +70,19 @@
 #endif
 #define MODULE_PARAM_PREFIX "rcutree."
 
+#ifndef data_race
+#define data_race(expr)							\
+	({								\
+		expr;							\
+	})
+#endif
+#ifndef ASSERT_EXCLUSIVE_WRITER
+#define ASSERT_EXCLUSIVE_WRITER(var) do { } while (0)
+#endif
+#ifndef ASSERT_EXCLUSIVE_ACCESS
+#define ASSERT_EXCLUSIVE_ACCESS(var) do { } while (0)
+#endif
+
 /* Data structures. */
 
 /*
@@ -75,9 +91,6 @@
  */
 #define RCU_DYNTICK_CTRL_MASK 0x1
 #define RCU_DYNTICK_CTRL_CTR  (RCU_DYNTICK_CTRL_MASK + 1)
-#ifndef rcu_eqs_special_exit
-#define rcu_eqs_special_exit() do { } while (0)
-#endif
 
 static DEFINE_PER_CPU_SHARED_ALIGNED(struct rcu_data, rcu_data) = {
 	.dynticks_nesting = 1,
@@ -100,7 +113,7 @@ static struct rcu_state rcu_state = {
 static bool dump_tree;
 module_param(dump_tree, bool, 0444);
 /* By default, use RCU_SOFTIRQ instead of rcuc kthreads. */
-static bool use_softirq = 1;
+static bool use_softirq = true;
 module_param(use_softirq, bool, 0444);
 /* Control rcu_node-tree auto-balancing at boot time. */
 static bool rcu_fanout_exact;
@@ -150,6 +163,7 @@ static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu)
 static void invoke_rcu_core(void);
 static void rcu_report_exp_rdp(struct rcu_data *rdp);
 static void sync_sched_exp_online_cleanup(int cpu);
+static void check_cb_ovld_locked(struct rcu_data *rdp, struct rcu_node *rnp);
 
 /* rcuc/rcub kthread realtime priority */
 static int kthread_prio = IS_ENABLED(CONFIG_RCU_BOOST) ? 1 : 0;
@@ -164,6 +178,15 @@ module_param(gp_init_delay, int, 0444);
 static int gp_cleanup_delay;
 module_param(gp_cleanup_delay, int, 0444);
 
+/*
+ * This rcu parameter is runtime-read-only. It reflects
+ * a minimum allowed number of objects which can be cached
+ * per-CPU. Object size is equal to one page. This value
+ * can be changed at boot time.
+ */
+static int rcu_min_cached_objs = 2;
+module_param(rcu_min_cached_objs, int, 0444);
+
 /* Retrieve RCU kthreads priority for rcutorture */
 int rcu_get_gp_kthreads_prio(void)
 {
@@ -224,9 +247,11 @@ void rcu_softirq_qs(void)
 
 /*
  * Record entry into an extended quiescent state.  This is only to be
- * called when not already in an extended quiescent state.
+ * called when not already in an extended quiescent state, that is,
+ * RCU is watching prior to the call to this function and is no longer
+ * watching upon return.
  */
-static void rcu_dynticks_eqs_enter(void)
+static noinstr void rcu_dynticks_eqs_enter(void)
 {
 	struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
 	int seq;
@@ -236,8 +261,9 @@ static void rcu_dynticks_eqs_enter(void)
 	 * critical sections, and we also must force ordering with the
 	 * next idle sojourn.
 	 */
-	seq = atomic_add_return(RCU_DYNTICK_CTRL_CTR, &rdp->dynticks);
-	/* Better be in an extended quiescent state! */
+	rcu_dynticks_task_trace_enter();  // Before ->dynticks update!
+	seq = arch_atomic_add_return(RCU_DYNTICK_CTRL_CTR, &rdp->dynticks);
+	// RCU is no longer watching.  Better be in extended quiescent state!
 	WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
 		     (seq & RCU_DYNTICK_CTRL_CTR));
 	/* Better not have special action (TLB flush) pending! */
@@ -247,9 +273,10 @@ static void rcu_dynticks_eqs_enter(void)
 
 /*
  * Record exit from an extended quiescent state.  This is only to be
- * called from an extended quiescent state.
+ * called from an extended quiescent state, that is, RCU is not watching
+ * prior to the call to this function and is watching upon return.
  */
-static void rcu_dynticks_eqs_exit(void)
+static noinstr void rcu_dynticks_eqs_exit(void)
 {
 	struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
 	int seq;
@@ -259,14 +286,14 @@ static void rcu_dynticks_eqs_exit(void)
 	 * and we also must force ordering with the next RCU read-side
 	 * critical section.
 	 */
-	seq = atomic_add_return(RCU_DYNTICK_CTRL_CTR, &rdp->dynticks);
+	seq = arch_atomic_add_return(RCU_DYNTICK_CTRL_CTR, &rdp->dynticks);
+	// RCU is now watching.  Better not be in an extended quiescent state!
+	rcu_dynticks_task_trace_exit();  // After ->dynticks update!
 	WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
 		     !(seq & RCU_DYNTICK_CTRL_CTR));
 	if (seq & RCU_DYNTICK_CTRL_MASK) {
-		atomic_andnot(RCU_DYNTICK_CTRL_MASK, &rdp->dynticks);
+		arch_atomic_andnot(RCU_DYNTICK_CTRL_MASK, &rdp->dynticks);
 		smp_mb__after_atomic(); /* _exit after clearing mask. */
-		/* Prefer duplicate flushes to losing a flush. */
-		rcu_eqs_special_exit();
 	}
 }
 
@@ -294,11 +321,11 @@ static void rcu_dynticks_eqs_online(void)
  *
  * No ordering, as we are sampling CPU-local information.
  */
-static bool rcu_dynticks_curr_cpu_in_eqs(void)
+static __always_inline bool rcu_dynticks_curr_cpu_in_eqs(void)
 {
 	struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
 
-	return !(atomic_read(&rdp->dynticks) & RCU_DYNTICK_CTRL_CTR);
+	return !(arch_atomic_read(&rdp->dynticks) & RCU_DYNTICK_CTRL_CTR);
 }
 
 /*
@@ -332,6 +359,28 @@ static bool rcu_dynticks_in_eqs_since(struct rcu_data *rdp, int snap)
 }
 
 /*
+ * Return true if the referenced integer is zero while the specified
+ * CPU remains within a single extended quiescent state.
+ */
+bool rcu_dynticks_zero_in_eqs(int cpu, int *vp)
+{
+	struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
+	int snap;
+
+	// If not quiescent, force back to earlier extended quiescent state.
+	snap = atomic_read(&rdp->dynticks) & ~(RCU_DYNTICK_CTRL_MASK |
+					       RCU_DYNTICK_CTRL_CTR);
+
+	smp_rmb(); // Order ->dynticks and *vp reads.
+	if (READ_ONCE(*vp))
+		return false;  // Non-zero, so report failure;
+	smp_rmb(); // Order *vp read and ->dynticks re-read.
+
+	// If still in the same extended quiescent state, we are good!
+	return snap == (atomic_read(&rdp->dynticks) & ~RCU_DYNTICK_CTRL_MASK);
+}
+
+/*
  * Set the special (bottom) bit of the specified CPU so that it
  * will take special action (such as flushing its TLB) on the
  * next exit from an extended quiescent state.  Returns true if
@@ -342,14 +391,17 @@ bool rcu_eqs_special_set(int cpu)
 {
 	int old;
 	int new;
+	int new_old;
 	struct rcu_data *rdp = &per_cpu(rcu_data, cpu);
 
+	new_old = atomic_read(&rdp->dynticks);
 	do {
-		old = atomic_read(&rdp->dynticks);
+		old = new_old;
 		if (old & RCU_DYNTICK_CTRL_CTR)
 			return false;
 		new = old | RCU_DYNTICK_CTRL_MASK;
-	} while (atomic_cmpxchg(&rdp->dynticks, old, new) != old);
+		new_old = atomic_cmpxchg(&rdp->dynticks, old, new);
+	} while (new_old != old);
 	return true;
 }
 
@@ -378,16 +430,23 @@ void rcu_momentary_dyntick_idle(void)
 EXPORT_SYMBOL_GPL(rcu_momentary_dyntick_idle);
 
 /**
- * rcu_is_cpu_rrupt_from_idle - see if interrupted from idle
+ * rcu_is_cpu_rrupt_from_idle - see if 'interrupted' from idle
  *
  * If the current CPU is idle and running at a first-level (not nested)
- * interrupt from idle, return true.  The caller must have at least
- * disabled preemption.
+ * interrupt, or directly, from idle, return true.
+ *
+ * The caller must have at least disabled IRQs.
  */
 static int rcu_is_cpu_rrupt_from_idle(void)
 {
-	/* Called only from within the scheduling-clock interrupt */
-	lockdep_assert_in_irq();
+	long nesting;
+
+	/*
+	 * Usually called from the tick; but also used from smp_function_call()
+	 * for expedited grace periods. This latter can result in running from
+	 * the idle task, instead of an actual IPI.
+	 */
+	lockdep_assert_irqs_disabled();
 
 	/* Check for counter underflows */
 	RCU_LOCKDEP_WARN(__this_cpu_read(rcu_data.dynticks_nesting) < 0,
@@ -396,9 +455,15 @@ static int rcu_is_cpu_rrupt_from_idle(void)
 			 "RCU dynticks_nmi_nesting counter underflow/zero!");
 
 	/* Are we at first interrupt nesting level? */
-	if (__this_cpu_read(rcu_data.dynticks_nmi_nesting) != 1)
+	nesting = __this_cpu_read(rcu_data.dynticks_nmi_nesting);
+	if (nesting > 1)
 		return false;
 
+	/*
+	 * If we're not in an interrupt, we must be in the idle task!
+	 */
+	WARN_ON_ONCE(!nesting && !is_idle_task(current));
+
 	/* Does CPU appear to be idle from an RCU standpoint? */
 	return __this_cpu_read(rcu_data.dynticks_nesting) == 0;
 }
@@ -410,10 +475,15 @@ static long blimit = DEFAULT_RCU_BLIMIT;
 static long qhimark = DEFAULT_RCU_QHIMARK;
 #define DEFAULT_RCU_QLOMARK 100   /* Once only this many pending, use blimit. */
 static long qlowmark = DEFAULT_RCU_QLOMARK;
+#define DEFAULT_RCU_QOVLD_MULT 2
+#define DEFAULT_RCU_QOVLD (DEFAULT_RCU_QOVLD_MULT * DEFAULT_RCU_QHIMARK)
+static long qovld = DEFAULT_RCU_QOVLD; /* If this many pending, hammer QS. */
+static long qovld_calc = -1;	  /* No pre-initialization lock acquisitions! */
 
 module_param(blimit, long, 0444);
 module_param(qhimark, long, 0444);
 module_param(qlowmark, long, 0444);
+module_param(qovld, long, 0444);
 
 static ulong jiffies_till_first_fqs = ULONG_MAX;
 static ulong jiffies_till_next_fqs = ULONG_MAX;
@@ -553,7 +623,7 @@ EXPORT_SYMBOL_GPL(rcutorture_get_gp_data);
  * the possibility of usermode upcalls having messed up our count
  * of interrupt nesting level during the prior busy period.
  */
-static void rcu_eqs_enter(bool user)
+static noinstr void rcu_eqs_enter(bool user)
 {
 	struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
 
@@ -562,19 +632,28 @@ static void rcu_eqs_enter(bool user)
 	WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
 		     rdp->dynticks_nesting == 0);
 	if (rdp->dynticks_nesting != 1) {
+		// RCU will still be watching, so just do accounting and leave.
 		rdp->dynticks_nesting--;
 		return;
 	}
 
 	lockdep_assert_irqs_disabled();
+	instrumentation_begin();
 	trace_rcu_dyntick(TPS("Start"), rdp->dynticks_nesting, 0, atomic_read(&rdp->dynticks));
 	WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && !user && !is_idle_task(current));
 	rdp = this_cpu_ptr(&rcu_data);
 	do_nocb_deferred_wakeup(rdp);
 	rcu_prepare_for_idle();
 	rcu_preempt_deferred_qs(current);
+
+	// instrumentation for the noinstr rcu_dynticks_eqs_enter()
+	instrument_atomic_write(&rdp->dynticks, sizeof(rdp->dynticks));
+
+	instrumentation_end();
 	WRITE_ONCE(rdp->dynticks_nesting, 0); /* Avoid irq-access tearing. */
+	// RCU is watching here ...
 	rcu_dynticks_eqs_enter();
+	// ... but is no longer watching here.
 	rcu_dynticks_task_enter();
 }
 
@@ -607,26 +686,29 @@ void rcu_idle_enter(void)
  * If you add or remove a call to rcu_user_enter(), be sure to test with
  * CONFIG_RCU_EQS_DEBUG=y.
  */
-void rcu_user_enter(void)
+noinstr void rcu_user_enter(void)
 {
 	lockdep_assert_irqs_disabled();
 	rcu_eqs_enter(true);
 }
 #endif /* CONFIG_NO_HZ_FULL */
 
-/*
+/**
+ * rcu_nmi_exit - inform RCU of exit from NMI context
+ *
  * If we are returning from the outermost NMI handler that interrupted an
  * RCU-idle period, update rdp->dynticks and rdp->dynticks_nmi_nesting
  * to let the RCU grace-period handling know that the CPU is back to
  * being RCU-idle.
  *
- * If you add or remove a call to rcu_nmi_exit_common(), be sure to test
+ * If you add or remove a call to rcu_nmi_exit(), be sure to test
  * with CONFIG_RCU_EQS_DEBUG=y.
  */
-static __always_inline void rcu_nmi_exit_common(bool irq)
+noinstr void rcu_nmi_exit(void)
 {
 	struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
 
+	instrumentation_begin();
 	/*
 	 * Check for ->dynticks_nmi_nesting underflow and bad ->dynticks.
 	 * (We are exiting an NMI handler, so RCU better be paying attention
@@ -644,6 +726,7 @@ static __always_inline void rcu_nmi_exit_common(bool irq)
 				  atomic_read(&rdp->dynticks));
 		WRITE_ONCE(rdp->dynticks_nmi_nesting, /* No store tearing. */
 			   rdp->dynticks_nmi_nesting - 2);
+		instrumentation_end();
 		return;
 	}
 
@@ -651,27 +734,22 @@ static __always_inline void rcu_nmi_exit_common(bool irq)
 	trace_rcu_dyntick(TPS("Startirq"), rdp->dynticks_nmi_nesting, 0, atomic_read(&rdp->dynticks));
 	WRITE_ONCE(rdp->dynticks_nmi_nesting, 0); /* Avoid store tearing. */
 
-	if (irq)
+	if (!in_nmi())
 		rcu_prepare_for_idle();
 
+	// instrumentation for the noinstr rcu_dynticks_eqs_enter()
+	instrument_atomic_write(&rdp->dynticks, sizeof(rdp->dynticks));
+	instrumentation_end();
+
+	// RCU is watching here ...
 	rcu_dynticks_eqs_enter();
+	// ... but is no longer watching here.
 
-	if (irq)
+	if (!in_nmi())
 		rcu_dynticks_task_enter();
 }
 
 /**
- * rcu_nmi_exit - inform RCU of exit from NMI context
- *
- * If you add or remove a call to rcu_nmi_exit(), be sure to test
- * with CONFIG_RCU_EQS_DEBUG=y.
- */
-void rcu_nmi_exit(void)
-{
-	rcu_nmi_exit_common(false);
-}
-
-/**
  * rcu_irq_exit - inform RCU that current CPU is exiting irq towards idle
  *
  * Exit from an interrupt handler, which might possibly result in entering
@@ -690,12 +768,52 @@ void rcu_nmi_exit(void)
  * If you add or remove a call to rcu_irq_exit(), be sure to test with
  * CONFIG_RCU_EQS_DEBUG=y.
  */
-void rcu_irq_exit(void)
+void noinstr rcu_irq_exit(void)
+{
+	lockdep_assert_irqs_disabled();
+	rcu_nmi_exit();
+}
+
+/**
+ * rcu_irq_exit_preempt - Inform RCU that current CPU is exiting irq
+ *			  towards in kernel preemption
+ *
+ * Same as rcu_irq_exit() but has a sanity check that scheduling is safe
+ * from RCU point of view. Invoked from return from interrupt before kernel
+ * preemption.
+ */
+void rcu_irq_exit_preempt(void)
 {
 	lockdep_assert_irqs_disabled();
-	rcu_nmi_exit_common(true);
+	rcu_nmi_exit();
+
+	RCU_LOCKDEP_WARN(__this_cpu_read(rcu_data.dynticks_nesting) <= 0,
+			 "RCU dynticks_nesting counter underflow/zero!");
+	RCU_LOCKDEP_WARN(__this_cpu_read(rcu_data.dynticks_nmi_nesting) !=
+			 DYNTICK_IRQ_NONIDLE,
+			 "Bad RCU  dynticks_nmi_nesting counter\n");
+	RCU_LOCKDEP_WARN(rcu_dynticks_curr_cpu_in_eqs(),
+			 "RCU in extended quiescent state!");
 }
 
+#ifdef CONFIG_PROVE_RCU
+/**
+ * rcu_irq_exit_check_preempt - Validate that scheduling is possible
+ */
+void rcu_irq_exit_check_preempt(void)
+{
+	lockdep_assert_irqs_disabled();
+
+	RCU_LOCKDEP_WARN(__this_cpu_read(rcu_data.dynticks_nesting) <= 0,
+			 "RCU dynticks_nesting counter underflow/zero!");
+	RCU_LOCKDEP_WARN(__this_cpu_read(rcu_data.dynticks_nmi_nesting) !=
+			 DYNTICK_IRQ_NONIDLE,
+			 "Bad RCU  dynticks_nmi_nesting counter\n");
+	RCU_LOCKDEP_WARN(rcu_dynticks_curr_cpu_in_eqs(),
+			 "RCU in extended quiescent state!");
+}
+#endif /* #ifdef CONFIG_PROVE_RCU */
+
 /*
  * Wrapper for rcu_irq_exit() where interrupts are enabled.
  *
@@ -719,7 +837,7 @@ void rcu_irq_exit_irqson(void)
  * allow for the possibility of usermode upcalls messing up our count of
  * interrupt nesting level during the busy period that is just now starting.
  */
-static void rcu_eqs_exit(bool user)
+static void noinstr rcu_eqs_exit(bool user)
 {
 	struct rcu_data *rdp;
 	long oldval;
@@ -729,17 +847,26 @@ static void rcu_eqs_exit(bool user)
 	oldval = rdp->dynticks_nesting;
 	WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && oldval < 0);
 	if (oldval) {
+		// RCU was already watching, so just do accounting and leave.
 		rdp->dynticks_nesting++;
 		return;
 	}
 	rcu_dynticks_task_exit();
+	// RCU is not watching here ...
 	rcu_dynticks_eqs_exit();
+	// ... but is watching here.
+	instrumentation_begin();
+
+	// instrumentation for the noinstr rcu_dynticks_eqs_exit()
+	instrument_atomic_write(&rdp->dynticks, sizeof(rdp->dynticks));
+
 	rcu_cleanup_after_idle();
 	trace_rcu_dyntick(TPS("End"), rdp->dynticks_nesting, 1, atomic_read(&rdp->dynticks));
 	WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && !user && !is_idle_task(current));
 	WRITE_ONCE(rdp->dynticks_nesting, 1);
 	WARN_ON_ONCE(rdp->dynticks_nmi_nesting);
 	WRITE_ONCE(rdp->dynticks_nmi_nesting, DYNTICK_IRQ_NONIDLE);
+	instrumentation_end();
 }
 
 /**
@@ -770,15 +897,75 @@ void rcu_idle_exit(void)
  * If you add or remove a call to rcu_user_exit(), be sure to test with
  * CONFIG_RCU_EQS_DEBUG=y.
  */
-void rcu_user_exit(void)
+void noinstr rcu_user_exit(void)
 {
 	rcu_eqs_exit(1);
 }
+
+/**
+ * __rcu_irq_enter_check_tick - Enable scheduler tick on CPU if RCU needs it.
+ *
+ * The scheduler tick is not normally enabled when CPUs enter the kernel
+ * from nohz_full userspace execution.  After all, nohz_full userspace
+ * execution is an RCU quiescent state and the time executing in the kernel
+ * is quite short.  Except of course when it isn't.  And it is not hard to
+ * cause a large system to spend tens of seconds or even minutes looping
+ * in the kernel, which can cause a number of problems, include RCU CPU
+ * stall warnings.
+ *
+ * Therefore, if a nohz_full CPU fails to report a quiescent state
+ * in a timely manner, the RCU grace-period kthread sets that CPU's
+ * ->rcu_urgent_qs flag with the expectation that the next interrupt or
+ * exception will invoke this function, which will turn on the scheduler
+ * tick, which will enable RCU to detect that CPU's quiescent states,
+ * for example, due to cond_resched() calls in CONFIG_PREEMPT=n kernels.
+ * The tick will be disabled once a quiescent state is reported for
+ * this CPU.
+ *
+ * Of course, in carefully tuned systems, there might never be an
+ * interrupt or exception.  In that case, the RCU grace-period kthread
+ * will eventually cause one to happen.  However, in less carefully
+ * controlled environments, this function allows RCU to get what it
+ * needs without creating otherwise useless interruptions.
+ */
+void __rcu_irq_enter_check_tick(void)
+{
+	struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
+
+	 // Enabling the tick is unsafe in NMI handlers.
+	if (WARN_ON_ONCE(in_nmi()))
+		return;
+
+	RCU_LOCKDEP_WARN(rcu_dynticks_curr_cpu_in_eqs(),
+			 "Illegal rcu_irq_enter_check_tick() from extended quiescent state");
+
+	if (!tick_nohz_full_cpu(rdp->cpu) ||
+	    !READ_ONCE(rdp->rcu_urgent_qs) ||
+	    READ_ONCE(rdp->rcu_forced_tick)) {
+		// RCU doesn't need nohz_full help from this CPU, or it is
+		// already getting that help.
+		return;
+	}
+
+	// We get here only when not in an extended quiescent state and
+	// from interrupts (as opposed to NMIs).  Therefore, (1) RCU is
+	// already watching and (2) The fact that we are in an interrupt
+	// handler and that the rcu_node lock is an irq-disabled lock
+	// prevents self-deadlock.  So we can safely recheck under the lock.
+	// Note that the nohz_full state currently cannot change.
+	raw_spin_lock_rcu_node(rdp->mynode);
+	if (rdp->rcu_urgent_qs && !rdp->rcu_forced_tick) {
+		// A nohz_full CPU is in the kernel and RCU needs a
+		// quiescent state.  Turn on the tick!
+		WRITE_ONCE(rdp->rcu_forced_tick, true);
+		tick_dep_set_cpu(rdp->cpu, TICK_DEP_BIT_RCU);
+	}
+	raw_spin_unlock_rcu_node(rdp->mynode);
+}
 #endif /* CONFIG_NO_HZ_FULL */
 
 /**
- * rcu_nmi_enter_common - inform RCU of entry to NMI context
- * @irq: Is this call from rcu_irq_enter?
+ * rcu_nmi_enter - inform RCU of entry to NMI context
  *
  * If the CPU was idle from RCU's viewpoint, update rdp->dynticks and
  * rdp->dynticks_nmi_nesting to let the RCU grace-period handling know
@@ -786,10 +973,10 @@ void rcu_user_exit(void)
  * long as the nesting level does not overflow an int.  (You will probably
  * run out of stack space first.)
  *
- * If you add or remove a call to rcu_nmi_enter_common(), be sure to test
+ * If you add or remove a call to rcu_nmi_enter(), be sure to test
  * with CONFIG_RCU_EQS_DEBUG=y.
  */
-static __always_inline void rcu_nmi_enter_common(bool irq)
+noinstr void rcu_nmi_enter(void)
 {
 	long incby = 2;
 	struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
@@ -807,44 +994,44 @@ static __always_inline void rcu_nmi_enter_common(bool irq)
 	 */
 	if (rcu_dynticks_curr_cpu_in_eqs()) {
 
-		if (irq)
+		if (!in_nmi())
 			rcu_dynticks_task_exit();
 
+		// RCU is not watching here ...
 		rcu_dynticks_eqs_exit();
+		// ... but is watching here.
 
-		if (irq)
+		if (!in_nmi()) {
+			instrumentation_begin();
 			rcu_cleanup_after_idle();
+			instrumentation_end();
+		}
+
+		instrumentation_begin();
+		// instrumentation for the noinstr rcu_dynticks_curr_cpu_in_eqs()
+		instrument_atomic_read(&rdp->dynticks, sizeof(rdp->dynticks));
+		// instrumentation for the noinstr rcu_dynticks_eqs_exit()
+		instrument_atomic_write(&rdp->dynticks, sizeof(rdp->dynticks));
 
 		incby = 1;
-	} else if (tick_nohz_full_cpu(rdp->cpu) &&
-		   rdp->dynticks_nmi_nesting == DYNTICK_IRQ_NONIDLE &&
-		   READ_ONCE(rdp->rcu_urgent_qs) && !rdp->rcu_forced_tick) {
-		raw_spin_lock_rcu_node(rdp->mynode);
-		// Recheck under lock.
-		if (rdp->rcu_urgent_qs && !rdp->rcu_forced_tick) {
-			rdp->rcu_forced_tick = true;
-			tick_dep_set_cpu(rdp->cpu, TICK_DEP_BIT_RCU);
-		}
-		raw_spin_unlock_rcu_node(rdp->mynode);
+	} else if (!in_nmi()) {
+		instrumentation_begin();
+		rcu_irq_enter_check_tick();
+		instrumentation_end();
+	} else  {
+		instrumentation_begin();
 	}
+
 	trace_rcu_dyntick(incby == 1 ? TPS("Endirq") : TPS("++="),
 			  rdp->dynticks_nmi_nesting,
 			  rdp->dynticks_nmi_nesting + incby, atomic_read(&rdp->dynticks));
+	instrumentation_end();
 	WRITE_ONCE(rdp->dynticks_nmi_nesting, /* Prevent store tearing. */
 		   rdp->dynticks_nmi_nesting + incby);
 	barrier();
 }
 
 /**
- * rcu_nmi_enter - inform RCU of entry to NMI context
- */
-void rcu_nmi_enter(void)
-{
-	rcu_nmi_enter_common(false);
-}
-NOKPROBE_SYMBOL(rcu_nmi_enter);
-
-/**
  * rcu_irq_enter - inform RCU that current CPU is entering irq away from idle
  *
  * Enter an interrupt handler, which might possibly result in exiting
@@ -866,10 +1053,10 @@ NOKPROBE_SYMBOL(rcu_nmi_enter);
  * If you add or remove a call to rcu_irq_enter(), be sure to test with
  * CONFIG_RCU_EQS_DEBUG=y.
  */
-void rcu_irq_enter(void)
+noinstr void rcu_irq_enter(void)
 {
 	lockdep_assert_irqs_disabled();
-	rcu_nmi_enter_common(true);
+	rcu_nmi_enter();
 }
 
 /*
@@ -899,10 +1086,15 @@ static void rcu_disable_urgency_upon_qs(struct rcu_data *rdp)
 	WRITE_ONCE(rdp->rcu_need_heavy_qs, false);
 	if (tick_nohz_full_cpu(rdp->cpu) && rdp->rcu_forced_tick) {
 		tick_dep_clear_cpu(rdp->cpu, TICK_DEP_BIT_RCU);
-		rdp->rcu_forced_tick = false;
+		WRITE_ONCE(rdp->rcu_forced_tick, false);
 	}
 }
 
+noinstr bool __rcu_is_watching(void)
+{
+	return !rcu_dynticks_curr_cpu_in_eqs();
+}
+
 /**
  * rcu_is_watching - see if RCU thinks that the current CPU is not idle
  *
@@ -911,7 +1103,7 @@ static void rcu_disable_urgency_upon_qs(struct rcu_data *rdp)
  * if the current CPU is not in its idle loop or is in an interrupt or
  * NMI handler, return true.
  */
-bool notrace rcu_is_watching(void)
+bool rcu_is_watching(void)
 {
 	bool ret;
 
@@ -963,12 +1155,12 @@ bool rcu_lockdep_current_cpu_online(void)
 
 	if (in_nmi() || !rcu_scheduler_fully_active)
 		return true;
-	preempt_disable();
+	preempt_disable_notrace();
 	rdp = this_cpu_ptr(&rcu_data);
 	rnp = rdp->mynode;
 	if (rdp->grpmask & rcu_rnp_online_cpus(rnp))
 		ret = true;
-	preempt_enable();
+	preempt_enable_notrace();
 	return ret;
 }
 EXPORT_SYMBOL_GPL(rcu_lockdep_current_cpu_online);
@@ -1072,7 +1264,8 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp)
 	rnhqp = &per_cpu(rcu_data.rcu_need_heavy_qs, rdp->cpu);
 	if (!READ_ONCE(*rnhqp) &&
 	    (time_after(jiffies, rcu_state.gp_start + jtsq * 2) ||
-	     time_after(jiffies, rcu_state.jiffies_resched))) {
+	     time_after(jiffies, rcu_state.jiffies_resched) ||
+	     rcu_state.cbovld)) {
 		WRITE_ONCE(*rnhqp, true);
 		/* Store rcu_need_heavy_qs before rcu_urgent_qs. */
 		smp_store_release(ruqp, true);
@@ -1089,8 +1282,8 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp)
 	 * So hit them over the head with the resched_cpu() hammer!
 	 */
 	if (tick_nohz_full_cpu(rdp->cpu) &&
-		   time_after(jiffies,
-			      READ_ONCE(rdp->last_fqs_resched) + jtsq * 3)) {
+	    (time_after(jiffies, READ_ONCE(rdp->last_fqs_resched) + jtsq * 3) ||
+	     rcu_state.cbovld)) {
 		WRITE_ONCE(*ruqp, true);
 		resched_cpu(rdp->cpu);
 		WRITE_ONCE(rdp->last_fqs_resched, jiffies);
@@ -1113,6 +1306,7 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp)
 		    !rdp->rcu_iw_pending && rdp->rcu_iw_gp_seq != rnp->gp_seq &&
 		    (rnp->ffmask & rdp->grpmask)) {
 			init_irq_work(&rdp->rcu_iw, rcu_iw_handler);
+			atomic_set(&rdp->rcu_iw.flags, IRQ_WORK_HARD_IRQ);
 			rdp->rcu_iw_pending = true;
 			rdp->rcu_iw_gp_seq = rnp->gp_seq;
 			irq_work_queue_on(&rdp->rcu_iw, rdp->cpu);
@@ -1126,8 +1320,9 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp)
 static void trace_rcu_this_gp(struct rcu_node *rnp, struct rcu_data *rdp,
 			      unsigned long gp_seq_req, const char *s)
 {
-	trace_rcu_future_grace_period(rcu_state.name, rnp->gp_seq, gp_seq_req,
-				      rnp->level, rnp->grplo, rnp->grphi, s);
+	trace_rcu_future_grace_period(rcu_state.name, READ_ONCE(rnp->gp_seq),
+				      gp_seq_req, rnp->level,
+				      rnp->grplo, rnp->grphi, s);
 }
 
 /*
@@ -1174,7 +1369,7 @@ static bool rcu_start_this_gp(struct rcu_node *rnp_start, struct rcu_data *rdp,
 					  TPS("Prestarted"));
 			goto unlock_out;
 		}
-		rnp->gp_seq_needed = gp_seq_req;
+		WRITE_ONCE(rnp->gp_seq_needed, gp_seq_req);
 		if (rcu_seq_state(rcu_seq_current(&rnp->gp_seq))) {
 			/*
 			 * We just marked the leaf or internal node, and a
@@ -1199,18 +1394,18 @@ static bool rcu_start_this_gp(struct rcu_node *rnp_start, struct rcu_data *rdp,
 	}
 	trace_rcu_this_gp(rnp, rdp, gp_seq_req, TPS("Startedroot"));
 	WRITE_ONCE(rcu_state.gp_flags, rcu_state.gp_flags | RCU_GP_FLAG_INIT);
-	rcu_state.gp_req_activity = jiffies;
-	if (!rcu_state.gp_kthread) {
+	WRITE_ONCE(rcu_state.gp_req_activity, jiffies);
+	if (!READ_ONCE(rcu_state.gp_kthread)) {
 		trace_rcu_this_gp(rnp, rdp, gp_seq_req, TPS("NoGPkthread"));
 		goto unlock_out;
 	}
-	trace_rcu_grace_period(rcu_state.name, READ_ONCE(rcu_state.gp_seq), TPS("newreq"));
+	trace_rcu_grace_period(rcu_state.name, data_race(rcu_state.gp_seq), TPS("newreq"));
 	ret = true;  /* Caller must wake GP kthread. */
 unlock_out:
 	/* Push furthest requested GP to leaf node and rcu_data structure. */
 	if (ULONG_CMP_LT(gp_seq_req, rnp->gp_seq_needed)) {
-		rnp_start->gp_seq_needed = rnp->gp_seq_needed;
-		rdp->gp_seq_needed = rnp->gp_seq_needed;
+		WRITE_ONCE(rnp_start->gp_seq_needed, rnp->gp_seq_needed);
+		WRITE_ONCE(rdp->gp_seq_needed, rnp->gp_seq_needed);
 	}
 	if (rnp != rnp_start)
 		raw_spin_unlock_rcu_node(rnp);
@@ -1235,12 +1430,13 @@ static bool rcu_future_gp_cleanup(struct rcu_node *rnp)
 }
 
 /*
- * Awaken the grace-period kthread.  Don't do a self-awaken (unless in
- * an interrupt or softirq handler), and don't bother awakening when there
- * is nothing for the grace-period kthread to do (as in several CPUs raced
- * to awaken, and we lost), and finally don't try to awaken a kthread that
- * has not yet been created.  If all those checks are passed, track some
- * debug information and awaken.
+ * Awaken the grace-period kthread.  Don't do a self-awaken (unless in an
+ * interrupt or softirq handler, in which case we just might immediately
+ * sleep upon return, resulting in a grace-period hang), and don't bother
+ * awakening when there is nothing for the grace-period kthread to do
+ * (as in several CPUs raced to awaken, we lost), and finally don't try
+ * to awaken a kthread that has not yet been created.  If all those checks
+ * are passed, track some debug information and awaken.
  *
  * So why do the self-wakeup when in an interrupt or softirq handler
  * in the grace-period kthread's context?  Because the kthread might have
@@ -1250,10 +1446,10 @@ static bool rcu_future_gp_cleanup(struct rcu_node *rnp)
  */
 static void rcu_gp_kthread_wake(void)
 {
-	if ((current == rcu_state.gp_kthread &&
-	     !in_irq() && !in_serving_softirq()) ||
-	    !READ_ONCE(rcu_state.gp_flags) ||
-	    !rcu_state.gp_kthread)
+	struct task_struct *t = READ_ONCE(rcu_state.gp_kthread);
+
+	if ((current == t && !in_irq() && !in_serving_softirq()) ||
+	    !READ_ONCE(rcu_state.gp_flags) || !t)
 		return;
 	WRITE_ONCE(rcu_state.gp_wake_time, jiffies);
 	WRITE_ONCE(rcu_state.gp_wake_seq, READ_ONCE(rcu_state.gp_seq));
@@ -1321,7 +1517,7 @@ static void rcu_accelerate_cbs_unlocked(struct rcu_node *rnp,
 
 	rcu_lockdep_assert_cblist_protected(rdp);
 	c = rcu_seq_snap(&rcu_state.gp_seq);
-	if (!rdp->gpwrap && ULONG_CMP_GE(rdp->gp_seq_needed, c)) {
+	if (!READ_ONCE(rdp->gpwrap) && ULONG_CMP_GE(rdp->gp_seq_needed, c)) {
 		/* Old request still live, so mark recent callbacks. */
 		(void)rcu_segcblist_accelerate(&rdp->cblist, c);
 		return;
@@ -1386,7 +1582,7 @@ static void __maybe_unused rcu_advance_cbs_nowake(struct rcu_node *rnp,
 static bool __note_gp_changes(struct rcu_node *rnp, struct rcu_data *rdp)
 {
 	bool ret = false;
-	bool need_gp;
+	bool need_qs;
 	const bool offloaded = IS_ENABLED(CONFIG_RCU_NOCB_CPU) &&
 			       rcu_segcblist_is_offloaded(&rdp->cblist);
 
@@ -1400,10 +1596,13 @@ static bool __note_gp_changes(struct rcu_node *rnp, struct rcu_data *rdp)
 	    unlikely(READ_ONCE(rdp->gpwrap))) {
 		if (!offloaded)
 			ret = rcu_advance_cbs(rnp, rdp); /* Advance CBs. */
+		rdp->core_needs_qs = false;
 		trace_rcu_grace_period(rcu_state.name, rdp->gp_seq, TPS("cpuend"));
 	} else {
 		if (!offloaded)
 			ret = rcu_accelerate_cbs(rnp, rdp); /* Recent CBs. */
+		if (rdp->core_needs_qs)
+			rdp->core_needs_qs = !!(rnp->qsmask & rdp->grpmask);
 	}
 
 	/* Now handle the beginnings of any new-to-this-CPU grace periods. */
@@ -1415,14 +1614,14 @@ static bool __note_gp_changes(struct rcu_node *rnp, struct rcu_data *rdp)
 		 * go looking for one.
 		 */
 		trace_rcu_grace_period(rcu_state.name, rnp->gp_seq, TPS("cpustart"));
-		need_gp = !!(rnp->qsmask & rdp->grpmask);
-		rdp->cpu_no_qs.b.norm = need_gp;
-		rdp->core_needs_qs = need_gp;
+		need_qs = !!(rnp->qsmask & rdp->grpmask);
+		rdp->cpu_no_qs.b.norm = need_qs;
+		rdp->core_needs_qs = need_qs;
 		zero_cpu_stall_ticks(rdp);
 	}
 	rdp->gp_seq = rnp->gp_seq;  /* Remember new grace-period state. */
 	if (ULONG_CMP_LT(rdp->gp_seq_needed, rnp->gp_seq_needed) || rdp->gpwrap)
-		rdp->gp_seq_needed = rnp->gp_seq_needed;
+		WRITE_ONCE(rdp->gp_seq_needed, rnp->gp_seq_needed);
 	WRITE_ONCE(rdp->gpwrap, false);
 	rcu_gpnum_ovf(rnp, rdp);
 	return ret;
@@ -1453,7 +1652,32 @@ static void rcu_gp_slow(int delay)
 	if (delay > 0 &&
 	    !(rcu_seq_ctr(rcu_state.gp_seq) %
 	      (rcu_num_nodes * PER_RCU_NODE_PERIOD * delay)))
-		schedule_timeout_uninterruptible(delay);
+		schedule_timeout_idle(delay);
+}
+
+static unsigned long sleep_duration;
+
+/* Allow rcutorture to stall the grace-period kthread. */
+void rcu_gp_set_torture_wait(int duration)
+{
+	if (IS_ENABLED(CONFIG_RCU_TORTURE_TEST) && duration > 0)
+		WRITE_ONCE(sleep_duration, duration);
+}
+EXPORT_SYMBOL_GPL(rcu_gp_set_torture_wait);
+
+/* Actually implement the aforementioned wait. */
+static void rcu_gp_torture_wait(void)
+{
+	unsigned long duration;
+
+	if (!IS_ENABLED(CONFIG_RCU_TORTURE_TEST))
+		return;
+	duration = xchg(&sleep_duration, 0UL);
+	if (duration > 0) {
+		pr_alert("%s: Waiting %lu jiffies\n", __func__, duration);
+		schedule_timeout_idle(duration);
+		pr_alert("%s: Wait complete\n", __func__);
+	}
 }
 
 /*
@@ -1489,6 +1713,7 @@ static bool rcu_gp_init(void)
 	record_gp_stall_check_time();
 	/* Record GP times before starting GP, hence rcu_seq_start(). */
 	rcu_seq_start(&rcu_state.gp_seq);
+	ASSERT_EXCLUSIVE_WRITER(rcu_state.gp_seq);
 	trace_rcu_grace_period(rcu_state.name, rcu_state.gp_seq, TPS("start"));
 	raw_spin_unlock_irq_rcu_node(rnp);
 
@@ -1594,12 +1819,16 @@ static bool rcu_gp_fqs_check_wake(int *gfp)
 {
 	struct rcu_node *rnp = rcu_get_root();
 
-	/* Someone like call_rcu() requested a force-quiescent-state scan. */
+	// If under overload conditions, force an immediate FQS scan.
+	if (*gfp & RCU_GP_FLAG_OVLD)
+		return true;
+
+	// Someone like call_rcu() requested a force-quiescent-state scan.
 	*gfp = READ_ONCE(rcu_state.gp_flags);
 	if (*gfp & RCU_GP_FLAG_FQS)
 		return true;
 
-	/* The current grace period has completed. */
+	// The current grace period has completed.
 	if (!READ_ONCE(rnp->qsmask) && !rcu_preempt_blocked_readers_cgp(rnp))
 		return true;
 
@@ -1637,13 +1866,15 @@ static void rcu_gp_fqs(bool first_time)
 static void rcu_gp_fqs_loop(void)
 {
 	bool first_gp_fqs;
-	int gf;
+	int gf = 0;
 	unsigned long j;
 	int ret;
 	struct rcu_node *rnp = rcu_get_root();
 
 	first_gp_fqs = true;
 	j = READ_ONCE(jiffies_till_first_fqs);
+	if (rcu_state.cbovld)
+		gf = RCU_GP_FLAG_OVLD;
 	ret = 0;
 	for (;;) {
 		if (!ret) {
@@ -1651,12 +1882,12 @@ static void rcu_gp_fqs_loop(void)
 			WRITE_ONCE(rcu_state.jiffies_kick_kthreads,
 				   jiffies + (j ? 3 * j : 2));
 		}
-		trace_rcu_grace_period(rcu_state.name,
-				       READ_ONCE(rcu_state.gp_seq),
+		trace_rcu_grace_period(rcu_state.name, rcu_state.gp_seq,
 				       TPS("fqswait"));
 		rcu_state.gp_state = RCU_GP_WAIT_FQS;
 		ret = swait_event_idle_timeout_exclusive(
 				rcu_state.gp_wq, rcu_gp_fqs_check_wake(&gf), j);
+		rcu_gp_torture_wait();
 		rcu_state.gp_state = RCU_GP_DOING_FQS;
 		/* Locking provides needed memory barriers. */
 		/* If grace period done, leave loop. */
@@ -1664,15 +1895,17 @@ static void rcu_gp_fqs_loop(void)
 		    !rcu_preempt_blocked_readers_cgp(rnp))
 			break;
 		/* If time for quiescent-state forcing, do it. */
-		if (ULONG_CMP_GE(jiffies, rcu_state.jiffies_force_qs) ||
+		if (!time_after(rcu_state.jiffies_force_qs, jiffies) ||
 		    (gf & RCU_GP_FLAG_FQS)) {
-			trace_rcu_grace_period(rcu_state.name,
-					       READ_ONCE(rcu_state.gp_seq),
+			trace_rcu_grace_period(rcu_state.name, rcu_state.gp_seq,
 					       TPS("fqsstart"));
 			rcu_gp_fqs(first_gp_fqs);
-			first_gp_fqs = false;
-			trace_rcu_grace_period(rcu_state.name,
-					       READ_ONCE(rcu_state.gp_seq),
+			gf = 0;
+			if (first_gp_fqs) {
+				first_gp_fqs = false;
+				gf = rcu_state.cbovld ? RCU_GP_FLAG_OVLD : 0;
+			}
+			trace_rcu_grace_period(rcu_state.name, rcu_state.gp_seq,
 					       TPS("fqsend"));
 			cond_resched_tasks_rcu_qs();
 			WRITE_ONCE(rcu_state.gp_activity, jiffies);
@@ -1683,8 +1916,7 @@ static void rcu_gp_fqs_loop(void)
 			cond_resched_tasks_rcu_qs();
 			WRITE_ONCE(rcu_state.gp_activity, jiffies);
 			WARN_ON(signal_pending(current));
-			trace_rcu_grace_period(rcu_state.name,
-					       READ_ONCE(rcu_state.gp_seq),
+			trace_rcu_grace_period(rcu_state.name, rcu_state.gp_seq,
 					       TPS("fqswaitsig"));
 			ret = 1; /* Keep old FQS timing. */
 			j = jiffies;
@@ -1692,6 +1924,7 @@ static void rcu_gp_fqs_loop(void)
 				j = 1;
 			else
 				j = rcu_state.jiffies_force_qs - j;
+			gf = 0;
 		}
 	}
 }
@@ -1701,8 +1934,9 @@ static void rcu_gp_fqs_loop(void)
  */
 static void rcu_gp_cleanup(void)
 {
-	unsigned long gp_duration;
+	int cpu;
 	bool needgp = false;
+	unsigned long gp_duration;
 	unsigned long new_gp_seq;
 	bool offloaded;
 	struct rcu_data *rdp;
@@ -1748,6 +1982,12 @@ static void rcu_gp_cleanup(void)
 			needgp = __note_gp_changes(rnp, rdp) || needgp;
 		/* smp_mb() provided by prior unlock-lock pair. */
 		needgp = rcu_future_gp_cleanup(rnp) || needgp;
+		// Reset overload indication for CPUs no longer overloaded
+		if (rcu_is_leaf_node(rnp))
+			for_each_leaf_node_cpu_mask(rnp, cpu, rnp->cbovldmask) {
+				rdp = per_cpu_ptr(&rcu_data, cpu);
+				check_cb_ovld_locked(rdp, rnp);
+			}
 		sq = rcu_nocb_gp_get(rnp);
 		raw_spin_unlock_irq_rcu_node(rnp);
 		rcu_nocb_gp_cleanup(sq);
@@ -1761,6 +2001,7 @@ static void rcu_gp_cleanup(void)
 	/* Declare grace period done, trace first to use old GP number. */
 	trace_rcu_grace_period(rcu_state.name, rcu_state.gp_seq, TPS("end"));
 	rcu_seq_end(&rcu_state.gp_seq);
+	ASSERT_EXCLUSIVE_WRITER(rcu_state.gp_seq);
 	rcu_state.gp_state = RCU_GP_IDLE;
 	/* Check for GP requests since above loop. */
 	rdp = this_cpu_ptr(&rcu_data);
@@ -1774,9 +2015,9 @@ static void rcu_gp_cleanup(void)
 		    rcu_segcblist_is_offloaded(&rdp->cblist);
 	if ((offloaded || !rcu_accelerate_cbs(rnp, rdp)) && needgp) {
 		WRITE_ONCE(rcu_state.gp_flags, RCU_GP_FLAG_INIT);
-		rcu_state.gp_req_activity = jiffies;
+		WRITE_ONCE(rcu_state.gp_req_activity, jiffies);
 		trace_rcu_grace_period(rcu_state.name,
-				       READ_ONCE(rcu_state.gp_seq),
+				       rcu_state.gp_seq,
 				       TPS("newreq"));
 	} else {
 		WRITE_ONCE(rcu_state.gp_flags,
@@ -1795,13 +2036,13 @@ static int __noreturn rcu_gp_kthread(void *unused)
 
 		/* Handle grace-period start. */
 		for (;;) {
-			trace_rcu_grace_period(rcu_state.name,
-					       READ_ONCE(rcu_state.gp_seq),
+			trace_rcu_grace_period(rcu_state.name, rcu_state.gp_seq,
 					       TPS("reqwait"));
 			rcu_state.gp_state = RCU_GP_WAIT_GPS;
 			swait_event_idle_exclusive(rcu_state.gp_wq,
 					 READ_ONCE(rcu_state.gp_flags) &
 					 RCU_GP_FLAG_INIT);
+			rcu_gp_torture_wait();
 			rcu_state.gp_state = RCU_GP_DONE_GPS;
 			/* Locking provides needed memory barrier. */
 			if (rcu_gp_init())
@@ -1809,8 +2050,7 @@ static int __noreturn rcu_gp_kthread(void *unused)
 			cond_resched_tasks_rcu_qs();
 			WRITE_ONCE(rcu_state.gp_activity, jiffies);
 			WARN_ON(signal_pending(current));
-			trace_rcu_grace_period(rcu_state.name,
-					       READ_ONCE(rcu_state.gp_seq),
+			trace_rcu_grace_period(rcu_state.name, rcu_state.gp_seq,
 					       TPS("reqwaitsig"));
 		}
 
@@ -1881,7 +2121,7 @@ static void rcu_report_qs_rnp(unsigned long mask, struct rcu_node *rnp,
 		WARN_ON_ONCE(oldmask); /* Any child must be all zeroed! */
 		WARN_ON_ONCE(!rcu_is_leaf_node(rnp) &&
 			     rcu_preempt_blocked_readers_cgp(rnp));
-		rnp->qsmask &= ~mask;
+		WRITE_ONCE(rnp->qsmask, rnp->qsmask & ~mask);
 		trace_rcu_quiescent_state_report(rcu_state.name, rnp->gp_seq,
 						 mask, rnp->qsmask, rnp->level,
 						 rnp->grplo, rnp->grphi,
@@ -1904,7 +2144,7 @@ static void rcu_report_qs_rnp(unsigned long mask, struct rcu_node *rnp,
 		rnp_c = rnp;
 		rnp = rnp->parent;
 		raw_spin_lock_irqsave_rcu_node(rnp, flags);
-		oldmask = rnp_c->qsmask;
+		oldmask = READ_ONCE(rnp_c->qsmask);
 	}
 
 	/*
@@ -1987,6 +2227,8 @@ rcu_report_qs_rdp(int cpu, struct rcu_data *rdp)
 		return;
 	}
 	mask = rdp->grpmask;
+	if (rdp->cpu == smp_processor_id())
+		rdp->core_needs_qs = false;
 	if ((rnp->qsmask & mask) == 0) {
 		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 	} else {
@@ -2052,7 +2294,7 @@ int rcutree_dying_cpu(unsigned int cpu)
 		return 0;
 
 	blkd = !!(rnp->qsmask & rdp->grpmask);
-	trace_rcu_grace_period(rcu_state.name, rnp->gp_seq,
+	trace_rcu_grace_period(rcu_state.name, READ_ONCE(rnp->gp_seq),
 			       blkd ? TPS("cpuofl") : TPS("cpuofl-bgp"));
 	return 0;
 }
@@ -2215,6 +2457,7 @@ static void rcu_do_batch(struct rcu_data *rdp)
 	local_irq_save(flags);
 	rcu_nocb_lock(rdp);
 	count = -rcl.len;
+	rdp->n_cbs_invoked += count;
 	trace_rcu_batch_end(rcu_state.name, count, !!rcl.head, need_resched(),
 			    is_idle_task(current), rcu_is_callbacks_kthread());
 
@@ -2294,10 +2537,13 @@ static void force_qs_rnp(int (*f)(struct rcu_data *rdp))
 	struct rcu_data *rdp;
 	struct rcu_node *rnp;
 
+	rcu_state.cbovld = rcu_state.cbovldnext;
+	rcu_state.cbovldnext = false;
 	rcu_for_each_leaf_node(rnp) {
 		cond_resched_tasks_rcu_qs();
 		mask = 0;
 		raw_spin_lock_irqsave_rcu_node(rnp, flags);
+		rcu_state.cbovldnext |= !!rnp->cbovldmask;
 		if (rnp->qsmask == 0) {
 			if (!IS_ENABLED(CONFIG_PREEMPT_RCU) ||
 			    rcu_preempt_blocked_readers_cgp(rnp)) {
@@ -2495,7 +2741,7 @@ static void rcu_cpu_kthread(unsigned int cpu)
 	}
 	*statusp = RCU_KTHREAD_YIELDING;
 	trace_rcu_utilization(TPS("Start CPU kthread@rcu_yield"));
-	schedule_timeout_interruptible(2);
+	schedule_timeout_idle(2);
 	trace_rcu_utilization(TPS("End CPU kthread@rcu_yield"));
 	*statusp = RCU_KTHREAD_WAITING;
 }
@@ -2579,11 +2825,48 @@ static void rcu_leak_callback(struct rcu_head *rhp)
 }
 
 /*
- * Helper function for call_rcu() and friends.  The cpu argument will
- * normally be -1, indicating "currently running CPU".  It may specify
- * a CPU only if that CPU is a no-CBs CPU.  Currently, only rcu_barrier()
- * is expected to specify a CPU.
+ * Check and if necessary update the leaf rcu_node structure's
+ * ->cbovldmask bit corresponding to the current CPU based on that CPU's
+ * number of queued RCU callbacks.  The caller must hold the leaf rcu_node
+ * structure's ->lock.
+ */
+static void check_cb_ovld_locked(struct rcu_data *rdp, struct rcu_node *rnp)
+{
+	raw_lockdep_assert_held_rcu_node(rnp);
+	if (qovld_calc <= 0)
+		return; // Early boot and wildcard value set.
+	if (rcu_segcblist_n_cbs(&rdp->cblist) >= qovld_calc)
+		WRITE_ONCE(rnp->cbovldmask, rnp->cbovldmask | rdp->grpmask);
+	else
+		WRITE_ONCE(rnp->cbovldmask, rnp->cbovldmask & ~rdp->grpmask);
+}
+
+/*
+ * Check and if necessary update the leaf rcu_node structure's
+ * ->cbovldmask bit corresponding to the current CPU based on that CPU's
+ * number of queued RCU callbacks.  No locks need be held, but the
+ * caller must have disabled interrupts.
+ *
+ * Note that this function ignores the possibility that there are a lot
+ * of callbacks all of which have already seen the end of their respective
+ * grace periods.  This omission is due to the need for no-CBs CPUs to
+ * be holding ->nocb_lock to do this check, which is too heavy for a
+ * common-case operation.
  */
+static void check_cb_ovld(struct rcu_data *rdp)
+{
+	struct rcu_node *const rnp = rdp->mynode;
+
+	if (qovld_calc <= 0 ||
+	    ((rcu_segcblist_n_cbs(&rdp->cblist) >= qovld_calc) ==
+	     !!(READ_ONCE(rnp->cbovldmask) & rdp->grpmask)))
+		return; // Early boot wildcard value or already set correctly.
+	raw_spin_lock_rcu_node(rnp);
+	check_cb_ovld_locked(rdp, rnp);
+	raw_spin_unlock_rcu_node(rnp);
+}
+
+/* Helper function for call_rcu() and friends.  */
 static void
 __call_rcu(struct rcu_head *head, rcu_callback_t func)
 {
@@ -2608,6 +2891,7 @@ __call_rcu(struct rcu_head *head, rcu_callback_t func)
 	head->func = func;
 	head->next = NULL;
 	local_irq_save(flags);
+	kasan_record_aux_stack(head);
 	rdp = this_cpu_ptr(&rcu_data);
 
 	/* Add the callback to our list. */
@@ -2621,12 +2905,13 @@ __call_rcu(struct rcu_head *head, rcu_callback_t func)
 			rcu_segcblist_init(&rdp->cblist);
 	}
 
+	check_cb_ovld(rdp);
 	if (rcu_nocb_try_bypass(rdp, head, &was_alldone, flags))
 		return; // Enqueued onto ->nocb_bypass, so just leave.
-	/* If we get here, rcu_nocb_try_bypass() acquired ->nocb_lock. */
+	// If no-CBs CPU gets here, rcu_nocb_try_bypass() acquired ->nocb_lock.
 	rcu_segcblist_enqueue(&rdp->cblist, head);
-	if (__is_kfree_rcu_offset((unsigned long)func))
-		trace_rcu_kfree_callback(rcu_state.name, head,
+	if (__is_kvfree_rcu_offset((unsigned long)func))
+		trace_rcu_kvfree_callback(rcu_state.name, head,
 					 (unsigned long)func,
 					 rcu_segcblist_n_cbs(&rdp->cblist));
 	else
@@ -2688,28 +2973,53 @@ EXPORT_SYMBOL_GPL(call_rcu);
 /* Maximum number of jiffies to wait before draining a batch. */
 #define KFREE_DRAIN_JIFFIES (HZ / 50)
 #define KFREE_N_BATCHES 2
+#define FREE_N_CHANNELS 2
+
+/**
+ * struct kvfree_rcu_bulk_data - single block to store kvfree_rcu() pointers
+ * @nr_records: Number of active pointers in the array
+ * @next: Next bulk object in the block chain
+ * @records: Array of the kvfree_rcu() pointers
+ */
+struct kvfree_rcu_bulk_data {
+	unsigned long nr_records;
+	struct kvfree_rcu_bulk_data *next;
+	void *records[];
+};
+
+/*
+ * This macro defines how many entries the "records" array
+ * will contain. It is based on the fact that the size of
+ * kvfree_rcu_bulk_data structure becomes exactly one page.
+ */
+#define KVFREE_BULK_MAX_ENTR \
+	((PAGE_SIZE - sizeof(struct kvfree_rcu_bulk_data)) / sizeof(void *))
 
 /**
  * struct kfree_rcu_cpu_work - single batch of kfree_rcu() requests
  * @rcu_work: Let queue_rcu_work() invoke workqueue handler after grace period
  * @head_free: List of kfree_rcu() objects waiting for a grace period
+ * @bkvhead_free: Bulk-List of kvfree_rcu() objects waiting for a grace period
  * @krcp: Pointer to @kfree_rcu_cpu structure
  */
 
 struct kfree_rcu_cpu_work {
 	struct rcu_work rcu_work;
 	struct rcu_head *head_free;
+	struct kvfree_rcu_bulk_data *bkvhead_free[FREE_N_CHANNELS];
 	struct kfree_rcu_cpu *krcp;
 };
 
 /**
  * struct kfree_rcu_cpu - batch up kfree_rcu() requests for RCU grace period
  * @head: List of kfree_rcu() objects not yet waiting for a grace period
+ * @bkvhead: Bulk-List of kvfree_rcu() objects not yet waiting for a grace period
  * @krw_arr: Array of batches of kfree_rcu() objects waiting for a grace period
  * @lock: Synchronize access to this structure
  * @monitor_work: Promote @head to @head_free after KFREE_DRAIN_JIFFIES
  * @monitor_todo: Tracks whether a @monitor_work delayed work is pending
- * @initialized: The @lock and @rcu_work fields have been initialized
+ * @initialized: The @rcu_work fields have been initialized
+ * @count: Number of objects for which GP not started
  *
  * This is a per-CPU structure.  The reason that it is not included in
  * the rcu_data structure is to permit this code to be extracted from
@@ -2718,48 +3028,166 @@ struct kfree_rcu_cpu_work {
  */
 struct kfree_rcu_cpu {
 	struct rcu_head *head;
+	struct kvfree_rcu_bulk_data *bkvhead[FREE_N_CHANNELS];
 	struct kfree_rcu_cpu_work krw_arr[KFREE_N_BATCHES];
-	spinlock_t lock;
+	raw_spinlock_t lock;
 	struct delayed_work monitor_work;
 	bool monitor_todo;
 	bool initialized;
+	int count;
+
+	/*
+	 * A simple cache list that contains objects for
+	 * reuse purpose. In order to save some per-cpu
+	 * space the list is singular. Even though it is
+	 * lockless an access has to be protected by the
+	 * per-cpu lock.
+	 */
+	struct llist_head bkvcache;
+	int nr_bkv_objs;
+};
+
+static DEFINE_PER_CPU(struct kfree_rcu_cpu, krc) = {
+	.lock = __RAW_SPIN_LOCK_UNLOCKED(krc.lock),
 };
 
-static DEFINE_PER_CPU(struct kfree_rcu_cpu, krc);
+static __always_inline void
+debug_rcu_bhead_unqueue(struct kvfree_rcu_bulk_data *bhead)
+{
+#ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD
+	int i;
+
+	for (i = 0; i < bhead->nr_records; i++)
+		debug_rcu_head_unqueue((struct rcu_head *)(bhead->records[i]));
+#endif
+}
+
+static inline struct kfree_rcu_cpu *
+krc_this_cpu_lock(unsigned long *flags)
+{
+	struct kfree_rcu_cpu *krcp;
+
+	local_irq_save(*flags);	// For safely calling this_cpu_ptr().
+	krcp = this_cpu_ptr(&krc);
+	raw_spin_lock(&krcp->lock);
+
+	return krcp;
+}
+
+static inline void
+krc_this_cpu_unlock(struct kfree_rcu_cpu *krcp, unsigned long flags)
+{
+	raw_spin_unlock(&krcp->lock);
+	local_irq_restore(flags);
+}
+
+static inline struct kvfree_rcu_bulk_data *
+get_cached_bnode(struct kfree_rcu_cpu *krcp)
+{
+	if (!krcp->nr_bkv_objs)
+		return NULL;
+
+	krcp->nr_bkv_objs--;
+	return (struct kvfree_rcu_bulk_data *)
+		llist_del_first(&krcp->bkvcache);
+}
+
+static inline bool
+put_cached_bnode(struct kfree_rcu_cpu *krcp,
+	struct kvfree_rcu_bulk_data *bnode)
+{
+	// Check the limit.
+	if (krcp->nr_bkv_objs >= rcu_min_cached_objs)
+		return false;
+
+	llist_add((struct llist_node *) bnode, &krcp->bkvcache);
+	krcp->nr_bkv_objs++;
+	return true;
+
+}
 
 /*
  * This function is invoked in workqueue context after a grace period.
- * It frees all the objects queued on ->head_free.
+ * It frees all the objects queued on ->bhead_free or ->head_free.
  */
 static void kfree_rcu_work(struct work_struct *work)
 {
 	unsigned long flags;
+	struct kvfree_rcu_bulk_data *bkvhead[FREE_N_CHANNELS], *bnext;
 	struct rcu_head *head, *next;
 	struct kfree_rcu_cpu *krcp;
 	struct kfree_rcu_cpu_work *krwp;
+	int i, j;
 
 	krwp = container_of(to_rcu_work(work),
 			    struct kfree_rcu_cpu_work, rcu_work);
 	krcp = krwp->krcp;
-	spin_lock_irqsave(&krcp->lock, flags);
+
+	raw_spin_lock_irqsave(&krcp->lock, flags);
+	// Channels 1 and 2.
+	for (i = 0; i < FREE_N_CHANNELS; i++) {
+		bkvhead[i] = krwp->bkvhead_free[i];
+		krwp->bkvhead_free[i] = NULL;
+	}
+
+	// Channel 3.
 	head = krwp->head_free;
 	krwp->head_free = NULL;
-	spin_unlock_irqrestore(&krcp->lock, flags);
+	raw_spin_unlock_irqrestore(&krcp->lock, flags);
+
+	// Handle two first channels.
+	for (i = 0; i < FREE_N_CHANNELS; i++) {
+		for (; bkvhead[i]; bkvhead[i] = bnext) {
+			bnext = bkvhead[i]->next;
+			debug_rcu_bhead_unqueue(bkvhead[i]);
+
+			rcu_lock_acquire(&rcu_callback_map);
+			if (i == 0) { // kmalloc() / kfree().
+				trace_rcu_invoke_kfree_bulk_callback(
+					rcu_state.name, bkvhead[i]->nr_records,
+					bkvhead[i]->records);
+
+				kfree_bulk(bkvhead[i]->nr_records,
+					bkvhead[i]->records);
+			} else { // vmalloc() / vfree().
+				for (j = 0; j < bkvhead[i]->nr_records; j++) {
+					trace_rcu_invoke_kvfree_callback(
+						rcu_state.name,
+						bkvhead[i]->records[j], 0);
+
+					vfree(bkvhead[i]->records[j]);
+				}
+			}
+			rcu_lock_release(&rcu_callback_map);
+
+			krcp = krc_this_cpu_lock(&flags);
+			if (put_cached_bnode(krcp, bkvhead[i]))
+				bkvhead[i] = NULL;
+			krc_this_cpu_unlock(krcp, flags);
 
-	// List "head" is now private, so traverse locklessly.
+			if (bkvhead[i])
+				free_page((unsigned long) bkvhead[i]);
+
+			cond_resched_tasks_rcu_qs();
+		}
+	}
+
+	/*
+	 * Emergency case only. It can happen under low memory
+	 * condition when an allocation gets failed, so the "bulk"
+	 * path can not be temporary maintained.
+	 */
 	for (; head; head = next) {
 		unsigned long offset = (unsigned long)head->func;
+		void *ptr = (void *)head - offset;
 
 		next = head->next;
-		// Potentially optimize with kfree_bulk in future.
-		debug_rcu_head_unqueue(head);
+		debug_rcu_head_unqueue((struct rcu_head *)ptr);
 		rcu_lock_acquire(&rcu_callback_map);
-		trace_rcu_invoke_kfree_callback(rcu_state.name, head, offset);
+		trace_rcu_invoke_kvfree_callback(rcu_state.name, head, offset);
 
-		if (!WARN_ON_ONCE(!__is_kfree_rcu_offset(offset))) {
-			/* Could be optimized with kfree_bulk() in future. */
-			kfree((void *)head - offset);
-		}
+		if (!WARN_ON_ONCE(!__is_kvfree_rcu_offset(offset)))
+			kvfree(ptr);
 
 		rcu_lock_release(&rcu_callback_map);
 		cond_resched_tasks_rcu_qs();
@@ -2774,26 +3202,58 @@ static void kfree_rcu_work(struct work_struct *work)
  */
 static inline bool queue_kfree_rcu_work(struct kfree_rcu_cpu *krcp)
 {
-	int i;
-	struct kfree_rcu_cpu_work *krwp = NULL;
+	struct kfree_rcu_cpu_work *krwp;
+	bool repeat = false;
+	int i, j;
 
 	lockdep_assert_held(&krcp->lock);
-	for (i = 0; i < KFREE_N_BATCHES; i++)
-		if (!krcp->krw_arr[i].head_free) {
-			krwp = &(krcp->krw_arr[i]);
-			break;
+
+	for (i = 0; i < KFREE_N_BATCHES; i++) {
+		krwp = &(krcp->krw_arr[i]);
+
+		/*
+		 * Try to detach bkvhead or head and attach it over any
+		 * available corresponding free channel. It can be that
+		 * a previous RCU batch is in progress, it means that
+		 * immediately to queue another one is not possible so
+		 * return false to tell caller to retry.
+		 */
+		if ((krcp->bkvhead[0] && !krwp->bkvhead_free[0]) ||
+			(krcp->bkvhead[1] && !krwp->bkvhead_free[1]) ||
+				(krcp->head && !krwp->head_free)) {
+			// Channel 1 corresponds to SLAB ptrs.
+			// Channel 2 corresponds to vmalloc ptrs.
+			for (j = 0; j < FREE_N_CHANNELS; j++) {
+				if (!krwp->bkvhead_free[j]) {
+					krwp->bkvhead_free[j] = krcp->bkvhead[j];
+					krcp->bkvhead[j] = NULL;
+				}
+			}
+
+			// Channel 3 corresponds to emergency path.
+			if (!krwp->head_free) {
+				krwp->head_free = krcp->head;
+				krcp->head = NULL;
+			}
+
+			WRITE_ONCE(krcp->count, 0);
+
+			/*
+			 * One work is per one batch, so there are three
+			 * "free channels", the batch can handle. It can
+			 * be that the work is in the pending state when
+			 * channels have been detached following by each
+			 * other.
+			 */
+			queue_rcu_work(system_wq, &krwp->rcu_work);
 		}
 
-	// If a previous RCU batch is in progress, we cannot immediately
-	// queue another one, so return false to tell caller to retry.
-	if (!krwp)
-		return false;
+		// Repeat if any "free" corresponding channel is still busy.
+		if (krcp->bkvhead[0] || krcp->bkvhead[1] || krcp->head)
+			repeat = true;
+	}
 
-	krwp->head_free = krcp->head;
-	krcp->head = NULL;
-	INIT_RCU_WORK(&krwp->rcu_work, kfree_rcu_work);
-	queue_rcu_work(system_wq, &krwp->rcu_work);
-	return true;
+	return !repeat;
 }
 
 static inline void kfree_rcu_drain_unlock(struct kfree_rcu_cpu *krcp,
@@ -2803,14 +3263,14 @@ static inline void kfree_rcu_drain_unlock(struct kfree_rcu_cpu *krcp,
 	krcp->monitor_todo = false;
 	if (queue_kfree_rcu_work(krcp)) {
 		// Success! Our job is done here.
-		spin_unlock_irqrestore(&krcp->lock, flags);
+		raw_spin_unlock_irqrestore(&krcp->lock, flags);
 		return;
 	}
 
 	// Previous RCU batch still in progress, try again later.
 	krcp->monitor_todo = true;
 	schedule_delayed_work(&krcp->monitor_work, KFREE_DRAIN_JIFFIES);
-	spin_unlock_irqrestore(&krcp->lock, flags);
+	raw_spin_unlock_irqrestore(&krcp->lock, flags);
 }
 
 /*
@@ -2823,47 +3283,135 @@ static void kfree_rcu_monitor(struct work_struct *work)
 	struct kfree_rcu_cpu *krcp = container_of(work, struct kfree_rcu_cpu,
 						 monitor_work.work);
 
-	spin_lock_irqsave(&krcp->lock, flags);
+	raw_spin_lock_irqsave(&krcp->lock, flags);
 	if (krcp->monitor_todo)
 		kfree_rcu_drain_unlock(krcp, flags);
 	else
-		spin_unlock_irqrestore(&krcp->lock, flags);
+		raw_spin_unlock_irqrestore(&krcp->lock, flags);
+}
+
+static inline bool
+kvfree_call_rcu_add_ptr_to_bulk(struct kfree_rcu_cpu *krcp, void *ptr)
+{
+	struct kvfree_rcu_bulk_data *bnode;
+	int idx;
+
+	if (unlikely(!krcp->initialized))
+		return false;
+
+	lockdep_assert_held(&krcp->lock);
+	idx = !!is_vmalloc_addr(ptr);
+
+	/* Check if a new block is required. */
+	if (!krcp->bkvhead[idx] ||
+			krcp->bkvhead[idx]->nr_records == KVFREE_BULK_MAX_ENTR) {
+		bnode = get_cached_bnode(krcp);
+		if (!bnode) {
+			/*
+			 * To keep this path working on raw non-preemptible
+			 * sections, prevent the optional entry into the
+			 * allocator as it uses sleeping locks. In fact, even
+			 * if the caller of kfree_rcu() is preemptible, this
+			 * path still is not, as krcp->lock is a raw spinlock.
+			 * With additional page pre-allocation in the works,
+			 * hitting this return is going to be much less likely.
+			 */
+			if (IS_ENABLED(CONFIG_PREEMPT_RT))
+				return false;
+
+			/*
+			 * NOTE: For one argument of kvfree_rcu() we can
+			 * drop the lock and get the page in sleepable
+			 * context. That would allow to maintain an array
+			 * for the CONFIG_PREEMPT_RT as well if no cached
+			 * pages are available.
+			 */
+			bnode = (struct kvfree_rcu_bulk_data *)
+				__get_free_page(GFP_NOWAIT | __GFP_NOWARN);
+		}
+
+		/* Switch to emergency path. */
+		if (unlikely(!bnode))
+			return false;
+
+		/* Initialize the new block. */
+		bnode->nr_records = 0;
+		bnode->next = krcp->bkvhead[idx];
+
+		/* Attach it to the head. */
+		krcp->bkvhead[idx] = bnode;
+	}
+
+	/* Finally insert. */
+	krcp->bkvhead[idx]->records
+		[krcp->bkvhead[idx]->nr_records++] = ptr;
+
+	return true;
 }
 
 /*
- * Queue a request for lazy invocation of kfree() after a grace period.
- *
- * Each kfree_call_rcu() request is added to a batch. The batch will be drained
- * every KFREE_DRAIN_JIFFIES number of jiffies. All the objects in the batch
- * will be kfree'd in workqueue context. This allows us to:
+ * Queue a request for lazy invocation of appropriate free routine after a
+ * grace period. Please note there are three paths are maintained, two are the
+ * main ones that use array of pointers interface and third one is emergency
+ * one, that is used only when the main path can not be maintained temporary,
+ * due to memory pressure.
  *
- * 1.	Batch requests together to reduce the number of grace periods during
- *	heavy kfree_rcu() load.
- *
- * 2.	It makes it possible to use kfree_bulk() on a large number of
- *	kfree_rcu() requests thus reducing cache misses and the per-object
- *	overhead of kfree().
+ * Each kvfree_call_rcu() request is added to a batch. The batch will be drained
+ * every KFREE_DRAIN_JIFFIES number of jiffies. All the objects in the batch will
+ * be free'd in workqueue context. This allows us to: batch requests together to
+ * reduce the number of grace periods during heavy kfree_rcu()/kvfree_rcu() load.
  */
-void kfree_call_rcu(struct rcu_head *head, rcu_callback_t func)
+void kvfree_call_rcu(struct rcu_head *head, rcu_callback_t func)
 {
 	unsigned long flags;
 	struct kfree_rcu_cpu *krcp;
+	bool success;
+	void *ptr;
 
-	local_irq_save(flags);	// For safely calling this_cpu_ptr().
-	krcp = this_cpu_ptr(&krc);
-	if (krcp->initialized)
-		spin_lock(&krcp->lock);
+	if (head) {
+		ptr = (void *) head - (unsigned long) func;
+	} else {
+		/*
+		 * Please note there is a limitation for the head-less
+		 * variant, that is why there is a clear rule for such
+		 * objects: it can be used from might_sleep() context
+		 * only. For other places please embed an rcu_head to
+		 * your data.
+		 */
+		might_sleep();
+		ptr = (unsigned long *) func;
+	}
+
+	krcp = krc_this_cpu_lock(&flags);
 
 	// Queue the object but don't yet schedule the batch.
-	if (debug_rcu_head_queue(head)) {
+	if (debug_rcu_head_queue(ptr)) {
 		// Probable double kfree_rcu(), just leak.
 		WARN_ONCE(1, "%s(): Double-freed call. rcu_head %p\n",
 			  __func__, head);
+
+		// Mark as success and leave.
+		success = true;
 		goto unlock_return;
 	}
-	head->func = func;
-	head->next = krcp->head;
-	krcp->head = head;
+
+	/*
+	 * Under high memory pressure GFP_NOWAIT can fail,
+	 * in that case the emergency path is maintained.
+	 */
+	success = kvfree_call_rcu_add_ptr_to_bulk(krcp, ptr);
+	if (!success) {
+		if (head == NULL)
+			// Inline if kvfree_rcu(one_arg) call.
+			goto unlock_return;
+
+		head->func = func;
+		head->next = krcp->head;
+		krcp->head = head;
+		success = true;
+	}
+
+	WRITE_ONCE(krcp->count, krcp->count + 1);
 
 	// Set timer to drain after KFREE_DRAIN_JIFFIES.
 	if (rcu_scheduler_active == RCU_SCHEDULER_RUNNING &&
@@ -2873,11 +3421,70 @@ void kfree_call_rcu(struct rcu_head *head, rcu_callback_t func)
 	}
 
 unlock_return:
-	if (krcp->initialized)
-		spin_unlock(&krcp->lock);
-	local_irq_restore(flags);
+	krc_this_cpu_unlock(krcp, flags);
+
+	/*
+	 * Inline kvfree() after synchronize_rcu(). We can do
+	 * it from might_sleep() context only, so the current
+	 * CPU can pass the QS state.
+	 */
+	if (!success) {
+		debug_rcu_head_unqueue((struct rcu_head *) ptr);
+		synchronize_rcu();
+		kvfree(ptr);
+	}
+}
+EXPORT_SYMBOL_GPL(kvfree_call_rcu);
+
+static unsigned long
+kfree_rcu_shrink_count(struct shrinker *shrink, struct shrink_control *sc)
+{
+	int cpu;
+	unsigned long count = 0;
+
+	/* Snapshot count of all CPUs */
+	for_each_online_cpu(cpu) {
+		struct kfree_rcu_cpu *krcp = per_cpu_ptr(&krc, cpu);
+
+		count += READ_ONCE(krcp->count);
+	}
+
+	return count;
+}
+
+static unsigned long
+kfree_rcu_shrink_scan(struct shrinker *shrink, struct shrink_control *sc)
+{
+	int cpu, freed = 0;
+	unsigned long flags;
+
+	for_each_online_cpu(cpu) {
+		int count;
+		struct kfree_rcu_cpu *krcp = per_cpu_ptr(&krc, cpu);
+
+		count = krcp->count;
+		raw_spin_lock_irqsave(&krcp->lock, flags);
+		if (krcp->monitor_todo)
+			kfree_rcu_drain_unlock(krcp, flags);
+		else
+			raw_spin_unlock_irqrestore(&krcp->lock, flags);
+
+		sc->nr_to_scan -= count;
+		freed += count;
+
+		if (sc->nr_to_scan <= 0)
+			break;
+	}
+
+	return freed == 0 ? SHRINK_STOP : freed;
 }
-EXPORT_SYMBOL_GPL(kfree_call_rcu);
+
+static struct shrinker kfree_rcu_shrinker = {
+	.count_objects = kfree_rcu_shrink_count,
+	.scan_objects = kfree_rcu_shrink_scan,
+	.batch = 0,
+	.seeks = DEFAULT_SEEKS,
+};
 
 void __init kfree_rcu_scheduler_running(void)
 {
@@ -2887,15 +3494,15 @@ void __init kfree_rcu_scheduler_running(void)
 	for_each_online_cpu(cpu) {
 		struct kfree_rcu_cpu *krcp = per_cpu_ptr(&krc, cpu);
 
-		spin_lock_irqsave(&krcp->lock, flags);
+		raw_spin_lock_irqsave(&krcp->lock, flags);
 		if (!krcp->head || krcp->monitor_todo) {
-			spin_unlock_irqrestore(&krcp->lock, flags);
+			raw_spin_unlock_irqrestore(&krcp->lock, flags);
 			continue;
 		}
 		krcp->monitor_todo = true;
 		schedule_delayed_work_on(cpu, &krcp->monitor_work,
 					 KFREE_DRAIN_JIFFIES);
-		spin_unlock_irqrestore(&krcp->lock, flags);
+		raw_spin_unlock_irqrestore(&krcp->lock, flags);
 	}
 }
 
@@ -3075,24 +3682,32 @@ static void rcu_barrier_trace(const char *s, int cpu, unsigned long done)
 /*
  * RCU callback function for rcu_barrier().  If we are last, wake
  * up the task executing rcu_barrier().
+ *
+ * Note that the value of rcu_state.barrier_sequence must be captured
+ * before the atomic_dec_and_test().  Otherwise, if this CPU is not last,
+ * other CPUs might count the value down to zero before this CPU gets
+ * around to invoking rcu_barrier_trace(), which might result in bogus
+ * data from the next instance of rcu_barrier().
  */
 static void rcu_barrier_callback(struct rcu_head *rhp)
 {
+	unsigned long __maybe_unused s = rcu_state.barrier_sequence;
+
 	if (atomic_dec_and_test(&rcu_state.barrier_cpu_count)) {
-		rcu_barrier_trace(TPS("LastCB"), -1,
-				  rcu_state.barrier_sequence);
+		rcu_barrier_trace(TPS("LastCB"), -1, s);
 		complete(&rcu_state.barrier_completion);
 	} else {
-		rcu_barrier_trace(TPS("CB"), -1, rcu_state.barrier_sequence);
+		rcu_barrier_trace(TPS("CB"), -1, s);
 	}
 }
 
 /*
  * Called with preemption disabled, and from cross-cpu IRQ context.
  */
-static void rcu_barrier_func(void *unused)
+static void rcu_barrier_func(void *cpu_in)
 {
-	struct rcu_data *rdp = raw_cpu_ptr(&rcu_data);
+	uintptr_t cpu = (uintptr_t)cpu_in;
+	struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
 
 	rcu_barrier_trace(TPS("IRQ"), -1, rcu_state.barrier_sequence);
 	rdp->barrier_head.func = rcu_barrier_callback;
@@ -3119,7 +3734,7 @@ static void rcu_barrier_func(void *unused)
  */
 void rcu_barrier(void)
 {
-	int cpu;
+	uintptr_t cpu;
 	struct rcu_data *rdp;
 	unsigned long s = rcu_seq_snap(&rcu_state.barrier_sequence);
 
@@ -3142,13 +3757,14 @@ void rcu_barrier(void)
 	rcu_barrier_trace(TPS("Inc1"), -1, rcu_state.barrier_sequence);
 
 	/*
-	 * Initialize the count to one rather than to zero in order to
-	 * avoid a too-soon return to zero in case of a short grace period
-	 * (or preemption of this task).  Exclude CPU-hotplug operations
-	 * to ensure that no offline CPU has callbacks queued.
+	 * Initialize the count to two rather than to zero in order
+	 * to avoid a too-soon return to zero in case of an immediate
+	 * invocation of the just-enqueued callback (or preemption of
+	 * this task).  Exclude CPU-hotplug operations to ensure that no
+	 * offline non-offloaded CPU has callbacks queued.
 	 */
 	init_completion(&rcu_state.barrier_completion);
-	atomic_set(&rcu_state.barrier_cpu_count, 1);
+	atomic_set(&rcu_state.barrier_cpu_count, 2);
 	get_online_cpus();
 
 	/*
@@ -3158,13 +3774,23 @@ void rcu_barrier(void)
 	 */
 	for_each_possible_cpu(cpu) {
 		rdp = per_cpu_ptr(&rcu_data, cpu);
-		if (!cpu_online(cpu) &&
+		if (cpu_is_offline(cpu) &&
 		    !rcu_segcblist_is_offloaded(&rdp->cblist))
 			continue;
-		if (rcu_segcblist_n_cbs(&rdp->cblist)) {
+		if (rcu_segcblist_n_cbs(&rdp->cblist) && cpu_online(cpu)) {
 			rcu_barrier_trace(TPS("OnlineQ"), cpu,
 					  rcu_state.barrier_sequence);
-			smp_call_function_single(cpu, rcu_barrier_func, NULL, 1);
+			smp_call_function_single(cpu, rcu_barrier_func, (void *)cpu, 1);
+		} else if (rcu_segcblist_n_cbs(&rdp->cblist) &&
+			   cpu_is_offline(cpu)) {
+			rcu_barrier_trace(TPS("OfflineNoCBQ"), cpu,
+					  rcu_state.barrier_sequence);
+			local_irq_disable();
+			rcu_barrier_func((void *)cpu);
+			local_irq_enable();
+		} else if (cpu_is_offline(cpu)) {
+			rcu_barrier_trace(TPS("OfflineNoCBNoQ"), cpu,
+					  rcu_state.barrier_sequence);
 		} else {
 			rcu_barrier_trace(TPS("OnlineNQ"), cpu,
 					  rcu_state.barrier_sequence);
@@ -3176,7 +3802,7 @@ void rcu_barrier(void)
 	 * Now that we have an rcu_barrier_callback() callback on each
 	 * CPU, and thus each counted, remove the initial count.
 	 */
-	if (atomic_dec_and_test(&rcu_state.barrier_cpu_count))
+	if (atomic_sub_and_test(2, &rcu_state.barrier_cpu_count))
 		complete(&rcu_state.barrier_completion);
 
 	/* Wait for all rcu_barrier_callback() callbacks to be invoked. */
@@ -3275,12 +3901,12 @@ int rcutree_prepare_cpu(unsigned int cpu)
 	rnp = rdp->mynode;
 	raw_spin_lock_rcu_node(rnp);		/* irqs already disabled. */
 	rdp->beenonline = true;	 /* We have now been online. */
-	rdp->gp_seq = rnp->gp_seq;
-	rdp->gp_seq_needed = rnp->gp_seq;
+	rdp->gp_seq = READ_ONCE(rnp->gp_seq);
+	rdp->gp_seq_needed = rdp->gp_seq;
 	rdp->cpu_no_qs.b.norm = true;
 	rdp->core_needs_qs = false;
 	rdp->rcu_iw_pending = false;
-	rdp->rcu_iw_gp_seq = rnp->gp_seq - 1;
+	rdp->rcu_iw_gp_seq = rdp->gp_seq - 1;
 	trace_rcu_grace_period(rcu_state.name, rdp->gp_seq, TPS("cpuonl"));
 	raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 	rcu_prepare_kthreads(cpu);
@@ -3364,10 +3990,9 @@ void rcu_cpu_starting(unsigned int cpu)
 {
 	unsigned long flags;
 	unsigned long mask;
-	int nbits;
-	unsigned long oldmask;
 	struct rcu_data *rdp;
 	struct rcu_node *rnp;
+	bool newcpu;
 
 	if (per_cpu(rcu_cpu_started, cpu))
 		return;
@@ -3378,13 +4003,12 @@ void rcu_cpu_starting(unsigned int cpu)
 	rnp = rdp->mynode;
 	mask = rdp->grpmask;
 	raw_spin_lock_irqsave_rcu_node(rnp, flags);
-	rnp->qsmaskinitnext |= mask;
-	oldmask = rnp->expmaskinitnext;
+	WRITE_ONCE(rnp->qsmaskinitnext, rnp->qsmaskinitnext | mask);
+	newcpu = !(rnp->expmaskinitnext & mask);
 	rnp->expmaskinitnext |= mask;
-	oldmask ^= rnp->expmaskinitnext;
-	nbits = bitmap_weight(&oldmask, BITS_PER_LONG);
 	/* Allow lockless access for expedited grace periods. */
-	smp_store_release(&rcu_state.ncpus, rcu_state.ncpus + nbits); /* ^^^ */
+	smp_store_release(&rcu_state.ncpus, rcu_state.ncpus + newcpu); /* ^^^ */
+	ASSERT_EXCLUSIVE_WRITER(rcu_state.ncpus);
 	rcu_gpnum_ovf(rnp, rdp); /* Offline-induced counter wrap? */
 	rdp->rcu_onl_gp_seq = READ_ONCE(rcu_state.gp_seq);
 	rdp->rcu_onl_gp_flags = READ_ONCE(rcu_state.gp_flags);
@@ -3431,7 +4055,7 @@ void rcu_report_dead(unsigned int cpu)
 		rcu_report_qs_rnp(mask, rnp, rnp->gp_seq, flags);
 		raw_spin_lock_irqsave_rcu_node(rnp, flags);
 	}
-	rnp->qsmaskinitnext &= ~mask;
+	WRITE_ONCE(rnp->qsmaskinitnext, rnp->qsmaskinitnext & ~mask);
 	raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 	raw_spin_unlock(&rcu_state.ofl_lock);
 
@@ -3545,7 +4169,10 @@ static int __init rcu_spawn_gp_kthread(void)
 	}
 	rnp = rcu_get_root();
 	raw_spin_lock_irqsave_rcu_node(rnp, flags);
-	rcu_state.gp_kthread = t;
+	WRITE_ONCE(rcu_state.gp_activity, jiffies);
+	WRITE_ONCE(rcu_state.gp_req_activity, jiffies);
+	// Reset .gp_activity and .gp_req_activity before setting .gp_kthread.
+	smp_store_release(&rcu_state.gp_kthread, t);  /* ^^^ */
 	raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 	wake_up_process(t);
 	rcu_spawn_nocb_kthreads();
@@ -3767,13 +4394,28 @@ static void __init kfree_rcu_batch_init(void)
 
 	for_each_possible_cpu(cpu) {
 		struct kfree_rcu_cpu *krcp = per_cpu_ptr(&krc, cpu);
+		struct kvfree_rcu_bulk_data *bnode;
 
-		spin_lock_init(&krcp->lock);
-		for (i = 0; i < KFREE_N_BATCHES; i++)
+		for (i = 0; i < KFREE_N_BATCHES; i++) {
+			INIT_RCU_WORK(&krcp->krw_arr[i].rcu_work, kfree_rcu_work);
 			krcp->krw_arr[i].krcp = krcp;
+		}
+
+		for (i = 0; i < rcu_min_cached_objs; i++) {
+			bnode = (struct kvfree_rcu_bulk_data *)
+				__get_free_page(GFP_NOWAIT | __GFP_NOWARN);
+
+			if (bnode)
+				put_cached_bnode(krcp, bnode);
+			else
+				pr_err("Failed to preallocate for %d CPU!\n", cpu);
+		}
+
 		INIT_DELAYED_WORK(&krcp->monitor_work, kfree_rcu_monitor);
 		krcp->initialized = true;
 	}
+	if (register_shrinker(&kfree_rcu_shrinker))
+		pr_err("Failed to register kfree_rcu() shrinker!\n");
 }
 
 void __init rcu_init(void)
@@ -3809,6 +4451,13 @@ void __init rcu_init(void)
 	rcu_par_gp_wq = alloc_workqueue("rcu_par_gp", WQ_MEM_RECLAIM, 0);
 	WARN_ON(!rcu_par_gp_wq);
 	srcu_init();
+
+	/* Fill in default value for rcutree.qovld boot parameter. */
+	/* -After- the rcu_node ->lock fields are initialized! */
+	if (qovld < 0)
+		qovld_calc = DEFAULT_RCU_QOVLD_MULT * qhimark;
+	else
+		qovld_calc = qovld;
 }
 
 #include "tree_stall.h"
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index 0c87e4c161c2..c96ae351688b 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -41,7 +41,7 @@ struct rcu_node {
 	raw_spinlock_t __private lock;	/* Root rcu_node's lock protects */
 					/*  some rcu_state fields as well as */
 					/*  following. */
-	unsigned long gp_seq;	/* Track rsp->rcu_gp_seq. */
+	unsigned long gp_seq;	/* Track rsp->gp_seq. */
 	unsigned long gp_seq_needed; /* Track furthest future GP request. */
 	unsigned long completedqs; /* All QSes done for this node. */
 	unsigned long qsmask;	/* CPUs or groups that need to switch in */
@@ -68,12 +68,14 @@ struct rcu_node {
 				/* Online CPUs for next expedited GP. */
 				/*  Any CPU that has ever been online will */
 				/*  have its bit set. */
+	unsigned long cbovldmask;
+				/* CPUs experiencing callback overload. */
 	unsigned long ffmask;	/* Fully functional CPUs. */
 	unsigned long grpmask;	/* Mask to apply to parent qsmask. */
 				/*  Only one bit will be set in this mask. */
-	int	grplo;		/* lowest-numbered CPU or group here. */
-	int	grphi;		/* highest-numbered CPU or group here. */
-	u8	grpnum;		/* CPU/group number for next level up. */
+	int	grplo;		/* lowest-numbered CPU here. */
+	int	grphi;		/* highest-numbered CPU here. */
+	u8	grpnum;		/* group number for next level up. */
 	u8	level;		/* root is at level 0. */
 	bool	wait_blkd_tasks;/* Necessary to wait for blocked tasks to */
 				/*  exit RCU read-side critical sections */
@@ -147,7 +149,7 @@ union rcu_noqs {
 /* Per-CPU data for read-copy update. */
 struct rcu_data {
 	/* 1) quiescent-state and grace-period handling : */
-	unsigned long	gp_seq;		/* Track rsp->rcu_gp_seq counter. */
+	unsigned long	gp_seq;		/* Track rsp->gp_seq counter. */
 	unsigned long	gp_seq_needed;	/* Track furthest future GP request. */
 	union rcu_noqs	cpu_no_qs;	/* No QSes yet for this CPU. */
 	bool		core_needs_qs;	/* Core waits for quiesc state. */
@@ -169,6 +171,7 @@ struct rcu_data {
 					/* different grace periods. */
 	long		qlen_last_fqs_check;
 					/* qlen at last check for QS forcing */
+	unsigned long	n_cbs_invoked;	/* # callbacks invoked since boot. */
 	unsigned long	n_force_qs_snap;
 					/* did other CPU force QS recently? */
 	long		blimit;		/* Upper limit on a processed batch */
@@ -299,6 +302,8 @@ struct rcu_state {
 	u8	boost ____cacheline_internodealigned_in_smp;
 						/* Subject to priority boost. */
 	unsigned long gp_seq;			/* Grace-period sequence #. */
+	unsigned long gp_max;			/* Maximum GP duration in */
+						/*  jiffies. */
 	struct task_struct *gp_kthread;		/* Task for grace periods. */
 	struct swait_queue_head gp_wq;		/* Where GP task waits. */
 	short gp_flags;				/* Commands for GP task. */
@@ -321,6 +326,8 @@ struct rcu_state {
 	atomic_t expedited_need_qs;		/* # CPUs left to check in. */
 	struct swait_queue_head expedited_wq;	/* Wait for check-ins. */
 	int ncpus_snap;				/* # CPUs seen last time. */
+	u8 cbovld;				/* Callback overload now? */
+	u8 cbovldnext;				/* ^        ^  next time? */
 
 	unsigned long jiffies_force_qs;		/* Time at which to invoke */
 						/*  force_quiescent_state(). */
@@ -342,8 +349,6 @@ struct rcu_state {
 						/*  a reluctant CPU. */
 	unsigned long n_force_qs_gpstart;	/* Snapshot of n_force_qs at */
 						/*  GP start. */
-	unsigned long gp_max;			/* Maximum GP duration in */
-						/*  jiffies. */
 	const char *name;			/* Name of structure. */
 	char abbr;				/* Abbreviated name. */
 
@@ -355,6 +360,7 @@ struct rcu_state {
 /* Values for rcu_state structure's gp_flags field. */
 #define RCU_GP_FLAG_INIT 0x1	/* Need grace-period initialization. */
 #define RCU_GP_FLAG_FQS  0x2	/* Need grace-period quiescent-state forcing. */
+#define RCU_GP_FLAG_OVLD 0x4	/* Experiencing callback overload. */
 
 /* Values for rcu_state structure's gp_state field. */
 #define RCU_GP_IDLE	 0	/* Initial state and no GP in progress. */
@@ -450,6 +456,8 @@ static void rcu_bind_gp_kthread(void);
 static bool rcu_nohz_full_cpu(void);
 static void rcu_dynticks_task_enter(void);
 static void rcu_dynticks_task_exit(void);
+static void rcu_dynticks_task_trace_enter(void);
+static void rcu_dynticks_task_trace_exit(void);
 
 /* Forward declarations for tree_stall.h */
 static void record_gp_stall_check_time(void);
diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h
index dcbd75791f39..1888c0eb1216 100644
--- a/kernel/rcu/tree_exp.h
+++ b/kernel/rcu/tree_exp.h
@@ -150,7 +150,7 @@ static void __maybe_unused sync_exp_reset_tree(void)
 static bool sync_rcu_exp_done(struct rcu_node *rnp)
 {
 	raw_lockdep_assert_held_rcu_node(rnp);
-	return rnp->exp_tasks == NULL &&
+	return READ_ONCE(rnp->exp_tasks) == NULL &&
 	       READ_ONCE(rnp->expmask) == 0;
 }
 
@@ -314,7 +314,7 @@ static bool exp_funnel_lock(unsigned long s)
 				   sync_exp_work_done(s));
 			return true;
 		}
-		rnp->exp_seq_rq = s; /* Followers can wait on us. */
+		WRITE_ONCE(rnp->exp_seq_rq, s); /* Followers can wait on us. */
 		spin_unlock(&rnp->exp_lock);
 		trace_rcu_exp_funnel_lock(rcu_state.name, rnp->level,
 					  rnp->grplo, rnp->grphi, TPS("nxtlvl"));
@@ -373,7 +373,7 @@ static void sync_rcu_exp_select_node_cpus(struct work_struct *wp)
 	 * until such time as the ->expmask bits are cleared.
 	 */
 	if (rcu_preempt_has_tasks(rnp))
-		rnp->exp_tasks = rnp->blkd_tasks.next;
+		WRITE_ONCE(rnp->exp_tasks, rnp->blkd_tasks.next);
 	raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 
 	/* IPI the remaining CPUs for expedited quiescent state. */
@@ -403,7 +403,7 @@ retry_ipi:
 			/* Online, so delay for a bit and try again. */
 			raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 			trace_rcu_exp_grace_period(rcu_state.name, rcu_exp_gp_seq_endval(), TPS("selectofl"));
-			schedule_timeout_uninterruptible(1);
+			schedule_timeout_idle(1);
 			goto retry_ipi;
 		}
 		/* CPU really is offline, so we must report its QS. */
@@ -485,6 +485,7 @@ static bool synchronize_rcu_expedited_wait_once(long tlimit)
 static void synchronize_rcu_expedited_wait(void)
 {
 	int cpu;
+	unsigned long j;
 	unsigned long jiffies_stall;
 	unsigned long jiffies_start;
 	unsigned long mask;
@@ -496,7 +497,7 @@ static void synchronize_rcu_expedited_wait(void)
 	trace_rcu_exp_grace_period(rcu_state.name, rcu_exp_gp_seq_endval(), TPS("startwait"));
 	jiffies_stall = rcu_jiffies_till_stall_check();
 	jiffies_start = jiffies;
-	if (IS_ENABLED(CONFIG_NO_HZ_FULL)) {
+	if (tick_nohz_full_enabled() && rcu_inkernel_boot_has_ended()) {
 		if (synchronize_rcu_expedited_wait_once(1))
 			return;
 		rcu_for_each_leaf_node(rnp) {
@@ -508,12 +509,16 @@ static void synchronize_rcu_expedited_wait(void)
 				tick_dep_set_cpu(cpu, TICK_DEP_BIT_RCU_EXP);
 			}
 		}
+		j = READ_ONCE(jiffies_till_first_fqs);
+		if (synchronize_rcu_expedited_wait_once(j + HZ))
+			return;
+		WARN_ON_ONCE(IS_ENABLED(CONFIG_PREEMPT_RT));
 	}
 
 	for (;;) {
 		if (synchronize_rcu_expedited_wait_once(jiffies_stall))
 			return;
-		if (rcu_cpu_stall_suppress)
+		if (rcu_stall_is_suppressed())
 			continue;
 		panic_on_rcu_stall();
 		pr_err("INFO: %s detected expedited stalls on CPUs/tasks: {",
@@ -537,8 +542,8 @@ static void synchronize_rcu_expedited_wait(void)
 		}
 		pr_cont(" } %lu jiffies s: %lu root: %#lx/%c\n",
 			jiffies - jiffies_start, rcu_state.expedited_sequence,
-			READ_ONCE(rnp_root->expmask),
-			".T"[!!rnp_root->exp_tasks]);
+			data_race(rnp_root->expmask),
+			".T"[!!data_race(rnp_root->exp_tasks)]);
 		if (ndetected) {
 			pr_err("blocking rcu_node structures:");
 			rcu_for_each_node_breadth_first(rnp) {
@@ -548,8 +553,8 @@ static void synchronize_rcu_expedited_wait(void)
 					continue;
 				pr_cont(" l=%u:%d-%d:%#lx/%c",
 					rnp->level, rnp->grplo, rnp->grphi,
-					READ_ONCE(rnp->expmask),
-					".T"[!!rnp->exp_tasks]);
+					data_race(rnp->expmask),
+					".T"[!!data_race(rnp->exp_tasks)]);
 			}
 			pr_cont("\n");
 		}
@@ -589,7 +594,7 @@ static void rcu_exp_wait_wake(unsigned long s)
 			spin_lock(&rnp->exp_lock);
 			/* Recheck, avoid hang in case someone just arrived. */
 			if (ULONG_CMP_LT(rnp->exp_seq_rq, s))
-				rnp->exp_seq_rq = s;
+				WRITE_ONCE(rnp->exp_seq_rq, s);
 			spin_unlock(&rnp->exp_lock);
 		}
 		smp_mb(); /* All above changes before wakeup. */
@@ -634,6 +639,7 @@ static void wait_rcu_exp_gp(struct work_struct *wp)
  */
 static void rcu_exp_handler(void *unused)
 {
+	int depth = rcu_preempt_depth();
 	unsigned long flags;
 	struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
 	struct rcu_node *rnp = rdp->mynode;
@@ -644,7 +650,7 @@ static void rcu_exp_handler(void *unused)
 	 * critical section.  If also enabled or idle, immediately
 	 * report the quiescent state, otherwise defer.
 	 */
-	if (!rcu_preempt_depth()) {
+	if (!depth) {
 		if (!(preempt_count() & (PREEMPT_MASK | SOFTIRQ_MASK)) ||
 		    rcu_dynticks_curr_cpu_in_eqs()) {
 			rcu_report_exp_rdp(rdp);
@@ -668,7 +674,7 @@ static void rcu_exp_handler(void *unused)
 	 * can have caused this quiescent state to already have been
 	 * reported, so we really do need to check ->expmask.
 	 */
-	if (rcu_preempt_depth() > 0) {
+	if (depth > 0) {
 		raw_spin_lock_irqsave_rcu_node(rnp, flags);
 		if (rnp->expmask & rdp->grpmask) {
 			rdp->exp_deferred_qs = true;
@@ -678,30 +684,8 @@ static void rcu_exp_handler(void *unused)
 		return;
 	}
 
-	/*
-	 * The final and least likely case is where the interrupted
-	 * code was just about to or just finished exiting the RCU-preempt
-	 * read-side critical section, and no, we can't tell which.
-	 * So either way, set ->deferred_qs to flag later code that
-	 * a quiescent state is required.
-	 *
-	 * If the CPU is fully enabled (or if some buggy RCU-preempt
-	 * read-side critical section is being used from idle), just
-	 * invoke rcu_preempt_deferred_qs() to immediately report the
-	 * quiescent state.  We cannot use rcu_read_unlock_special()
-	 * because we are in an interrupt handler, which will cause that
-	 * function to take an early exit without doing anything.
-	 *
-	 * Otherwise, force a context switch after the CPU enables everything.
-	 */
-	rdp->exp_deferred_qs = true;
-	if (!(preempt_count() & (PREEMPT_MASK | SOFTIRQ_MASK)) ||
-	    WARN_ON_ONCE(rcu_dynticks_curr_cpu_in_eqs())) {
-		rcu_preempt_deferred_qs(t);
-	} else {
-		set_tsk_need_resched(t);
-		set_preempt_need_resched();
-	}
+	// Finally, negative nesting depth should not happen.
+	WARN_ON_ONCE(1);
 }
 
 /* PREEMPTION=y, so no PREEMPTION=n expedited grace period to clean up after. */
@@ -716,17 +700,20 @@ static void sync_sched_exp_online_cleanup(int cpu)
  */
 static int rcu_print_task_exp_stall(struct rcu_node *rnp)
 {
-	struct task_struct *t;
+	unsigned long flags;
 	int ndetected = 0;
+	struct task_struct *t;
 
-	if (!rnp->exp_tasks)
+	if (!READ_ONCE(rnp->exp_tasks))
 		return 0;
+	raw_spin_lock_irqsave_rcu_node(rnp, flags);
 	t = list_entry(rnp->exp_tasks->prev,
 		       struct task_struct, rcu_node_entry);
 	list_for_each_entry_continue(t, &rnp->blkd_tasks, rcu_node_entry) {
 		pr_cont(" P%d", t->pid);
 		ndetected++;
 	}
+	raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 	return ndetected;
 }
 
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index c6ea81cd4189..982fc5be5269 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -56,6 +56,8 @@ static void __init rcu_bootup_announce_oddness(void)
 		pr_info("\tBoot-time adjustment of callback high-water mark to %ld.\n", qhimark);
 	if (qlowmark != DEFAULT_RCU_QLOMARK)
 		pr_info("\tBoot-time adjustment of callback low-water mark to %ld.\n", qlowmark);
+	if (qovld != DEFAULT_RCU_QOVLD)
+		pr_info("\tBoot-time adjustment of callback overload level to %ld.\n", qovld);
 	if (jiffies_till_first_fqs != ULONG_MAX)
 		pr_info("\tBoot-time adjustment of first FQS scan delay to %ld jiffies.\n", jiffies_till_first_fqs);
 	if (jiffies_till_next_fqs != ULONG_MAX)
@@ -224,7 +226,7 @@ static void rcu_preempt_ctxt_queue(struct rcu_node *rnp, struct rcu_data *rdp)
 		WARN_ON_ONCE(rnp->completedqs == rnp->gp_seq);
 	}
 	if (!rnp->exp_tasks && (blkd_state & RCU_EXP_BLKD))
-		rnp->exp_tasks = &t->rcu_node_entry;
+		WRITE_ONCE(rnp->exp_tasks, &t->rcu_node_entry);
 	WARN_ON_ONCE(!(blkd_state & RCU_GP_BLKD) !=
 		     !(rnp->qsmask & rdp->grpmask));
 	WARN_ON_ONCE(!(blkd_state & RCU_EXP_BLKD) !=
@@ -329,6 +331,7 @@ void rcu_note_context_switch(bool preempt)
 	rcu_qs();
 	if (rdp->exp_deferred_qs)
 		rcu_report_exp_rdp(rdp);
+	rcu_tasks_qs(current, preempt);
 	trace_rcu_utilization(TPS("End context switch"));
 }
 EXPORT_SYMBOL_GPL(rcu_note_context_switch);
@@ -343,9 +346,7 @@ static int rcu_preempt_blocked_readers_cgp(struct rcu_node *rnp)
 	return READ_ONCE(rnp->gp_tasks) != NULL;
 }
 
-/* Bias and limit values for ->rcu_read_lock_nesting. */
-#define RCU_NEST_BIAS INT_MAX
-#define RCU_NEST_NMAX (-INT_MAX / 2)
+/* limit value for ->rcu_read_lock_nesting. */
 #define RCU_NEST_PMAX (INT_MAX / 2)
 
 static void rcu_preempt_read_enter(void)
@@ -353,9 +354,9 @@ static void rcu_preempt_read_enter(void)
 	current->rcu_read_lock_nesting++;
 }
 
-static void rcu_preempt_read_exit(void)
+static int rcu_preempt_read_exit(void)
 {
-	current->rcu_read_lock_nesting--;
+	return --current->rcu_read_lock_nesting;
 }
 
 static void rcu_preempt_depth_set(int val)
@@ -388,21 +389,15 @@ void __rcu_read_unlock(void)
 {
 	struct task_struct *t = current;
 
-	if (rcu_preempt_depth() != 1) {
-		rcu_preempt_read_exit();
-	} else {
+	if (rcu_preempt_read_exit() == 0) {
 		barrier();  /* critical section before exit code. */
-		rcu_preempt_depth_set(-RCU_NEST_BIAS);
-		barrier();  /* assign before ->rcu_read_unlock_special load */
 		if (unlikely(READ_ONCE(t->rcu_read_unlock_special.s)))
 			rcu_read_unlock_special(t);
-		barrier();  /* ->rcu_read_unlock_special load before assign */
-		rcu_preempt_depth_set(0);
 	}
 	if (IS_ENABLED(CONFIG_PROVE_LOCKING)) {
 		int rrln = rcu_preempt_depth();
 
-		WARN_ON_ONCE(rrln < 0 && rrln > RCU_NEST_NMAX);
+		WARN_ON_ONCE(rrln < 0 || rrln > RCU_NEST_PMAX);
 	}
 }
 EXPORT_SYMBOL_GPL(__rcu_read_unlock);
@@ -498,12 +493,12 @@ rcu_preempt_deferred_qs_irqrestore(struct task_struct *t, unsigned long flags)
 		if (&t->rcu_node_entry == rnp->gp_tasks)
 			WRITE_ONCE(rnp->gp_tasks, np);
 		if (&t->rcu_node_entry == rnp->exp_tasks)
-			rnp->exp_tasks = np;
+			WRITE_ONCE(rnp->exp_tasks, np);
 		if (IS_ENABLED(CONFIG_RCU_BOOST)) {
 			/* Snapshot ->boost_mtx ownership w/rnp->lock held. */
 			drop_boost_mutex = rt_mutex_owner(&rnp->boost_mtx) == t;
 			if (&t->rcu_node_entry == rnp->boost_tasks)
-				rnp->boost_tasks = np;
+				WRITE_ONCE(rnp->boost_tasks, np);
 		}
 
 		/*
@@ -554,7 +549,7 @@ static bool rcu_preempt_need_deferred_qs(struct task_struct *t)
 {
 	return (__this_cpu_read(rcu_data.exp_deferred_qs) ||
 		READ_ONCE(t->rcu_read_unlock_special.s)) &&
-	       rcu_preempt_depth() <= 0;
+	       rcu_preempt_depth() == 0;
 }
 
 /*
@@ -567,16 +562,11 @@ static bool rcu_preempt_need_deferred_qs(struct task_struct *t)
 static void rcu_preempt_deferred_qs(struct task_struct *t)
 {
 	unsigned long flags;
-	bool couldrecurse = rcu_preempt_depth() >= 0;
 
 	if (!rcu_preempt_need_deferred_qs(t))
 		return;
-	if (couldrecurse)
-		rcu_preempt_depth_set(rcu_preempt_depth() - RCU_NEST_BIAS);
 	local_irq_save(flags);
 	rcu_preempt_deferred_qs_irqrestore(t, flags);
-	if (couldrecurse)
-		rcu_preempt_depth_set(rcu_preempt_depth() + RCU_NEST_BIAS);
 }
 
 /*
@@ -613,19 +603,18 @@ static void rcu_read_unlock_special(struct task_struct *t)
 		struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
 		struct rcu_node *rnp = rdp->mynode;
 
-		exp = (t->rcu_blocked_node && t->rcu_blocked_node->exp_tasks) ||
-		      (rdp->grpmask & READ_ONCE(rnp->expmask)) ||
-		      tick_nohz_full_cpu(rdp->cpu);
+		exp = (t->rcu_blocked_node &&
+		       READ_ONCE(t->rcu_blocked_node->exp_tasks)) ||
+		      (rdp->grpmask & READ_ONCE(rnp->expmask));
 		// Need to defer quiescent state until everything is enabled.
-		if (irqs_were_disabled && use_softirq &&
-		    (in_interrupt() ||
-		     (exp && !t->rcu_read_unlock_special.b.deferred_qs))) {
-			// Using softirq, safe to awaken, and we get
-			// no help from enabling irqs, unlike bh/preempt.
+		if (use_softirq && (in_irq() || (exp && !irqs_were_disabled))) {
+			// Using softirq, safe to awaken, and either the
+			// wakeup is free or there is an expedited GP.
 			raise_softirq_irqoff(RCU_SOFTIRQ);
 		} else {
 			// Enabling BH or preempt does reschedule, so...
-			// Also if no expediting or NO_HZ_FULL, slow is OK.
+			// Also if no expediting, slow is OK.
+			// Plus nohz_full CPUs eventually get tick enabled.
 			set_tsk_need_resched(current);
 			set_preempt_need_resched();
 			if (IS_ENABLED(CONFIG_IRQ_WORK) && irqs_were_disabled &&
@@ -638,7 +627,6 @@ static void rcu_read_unlock_special(struct task_struct *t)
 				irq_work_queue_on(&rdp->defer_qs_iw, rdp->cpu);
 			}
 		}
-		t->rcu_read_unlock_special.b.deferred_qs = true;
 		local_irq_restore(flags);
 		return;
 	}
@@ -697,7 +685,7 @@ static void rcu_flavor_sched_clock_irq(int user)
 	} else if (rcu_preempt_need_deferred_qs(t)) {
 		rcu_preempt_deferred_qs(t); /* Report deferred QS. */
 		return;
-	} else if (!rcu_preempt_depth()) {
+	} else if (!WARN_ON_ONCE(rcu_preempt_depth())) {
 		rcu_qs(); /* Report immediate QS. */
 		return;
 	}
@@ -753,13 +741,13 @@ dump_blkd_tasks(struct rcu_node *rnp, int ncheck)
 	raw_lockdep_assert_held_rcu_node(rnp);
 	pr_info("%s: grp: %d-%d level: %d ->gp_seq %ld ->completedqs %ld\n",
 		__func__, rnp->grplo, rnp->grphi, rnp->level,
-		(long)rnp->gp_seq, (long)rnp->completedqs);
+		(long)READ_ONCE(rnp->gp_seq), (long)rnp->completedqs);
 	for (rnp1 = rnp; rnp1; rnp1 = rnp1->parent)
 		pr_info("%s: %d:%d ->qsmask %#lx ->qsmaskinit %#lx ->qsmaskinitnext %#lx\n",
 			__func__, rnp1->grplo, rnp1->grphi, rnp1->qsmask, rnp1->qsmaskinit, rnp1->qsmaskinitnext);
 	pr_info("%s: ->gp_tasks %p ->boost_tasks %p ->exp_tasks %p\n",
-		__func__, READ_ONCE(rnp->gp_tasks), rnp->boost_tasks,
-		rnp->exp_tasks);
+		__func__, READ_ONCE(rnp->gp_tasks), data_race(rnp->boost_tasks),
+		READ_ONCE(rnp->exp_tasks));
 	pr_info("%s: ->blkd_tasks", __func__);
 	i = 0;
 	list_for_each(lhp, &rnp->blkd_tasks) {
@@ -852,8 +840,7 @@ void rcu_note_context_switch(bool preempt)
 	this_cpu_write(rcu_data.rcu_urgent_qs, false);
 	if (unlikely(raw_cpu_read(rcu_data.rcu_need_heavy_qs)))
 		rcu_momentary_dyntick_idle();
-	if (!preempt)
-		rcu_tasks_qs(current);
+	rcu_tasks_qs(current, preempt);
 out:
 	trace_rcu_utilization(TPS("End context switch"));
 }
@@ -1032,20 +1019,21 @@ static int rcu_boost_kthread(void *arg)
 
 	trace_rcu_utilization(TPS("Start boost kthread@init"));
 	for (;;) {
-		rnp->boost_kthread_status = RCU_KTHREAD_WAITING;
+		WRITE_ONCE(rnp->boost_kthread_status, RCU_KTHREAD_WAITING);
 		trace_rcu_utilization(TPS("End boost kthread@rcu_wait"));
-		rcu_wait(rnp->boost_tasks || rnp->exp_tasks);
+		rcu_wait(READ_ONCE(rnp->boost_tasks) ||
+			 READ_ONCE(rnp->exp_tasks));
 		trace_rcu_utilization(TPS("Start boost kthread@rcu_wait"));
-		rnp->boost_kthread_status = RCU_KTHREAD_RUNNING;
+		WRITE_ONCE(rnp->boost_kthread_status, RCU_KTHREAD_RUNNING);
 		more2boost = rcu_boost(rnp);
 		if (more2boost)
 			spincnt++;
 		else
 			spincnt = 0;
 		if (spincnt > 10) {
-			rnp->boost_kthread_status = RCU_KTHREAD_YIELDING;
+			WRITE_ONCE(rnp->boost_kthread_status, RCU_KTHREAD_YIELDING);
 			trace_rcu_utilization(TPS("End boost kthread@rcu_yield"));
-			schedule_timeout_interruptible(2);
+			schedule_timeout_idle(2);
 			trace_rcu_utilization(TPS("Start boost kthread@rcu_yield"));
 			spincnt = 0;
 		}
@@ -1077,12 +1065,12 @@ static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags)
 	    (rnp->gp_tasks != NULL &&
 	     rnp->boost_tasks == NULL &&
 	     rnp->qsmask == 0 &&
-	     ULONG_CMP_GE(jiffies, rnp->boost_time))) {
+	     (!time_after(rnp->boost_time, jiffies) || rcu_state.cbovld))) {
 		if (rnp->exp_tasks == NULL)
-			rnp->boost_tasks = rnp->gp_tasks;
+			WRITE_ONCE(rnp->boost_tasks, rnp->gp_tasks);
 		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 		rcu_wake_cond(rnp->boost_kthread_task,
-			      rnp->boost_kthread_status);
+			      READ_ONCE(rnp->boost_kthread_status));
 	} else {
 		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 	}
@@ -1486,6 +1474,7 @@ module_param(nocb_nobypass_lim_per_jiffy, int, 0);
  * flag the contention.
  */
 static void rcu_nocb_bypass_lock(struct rcu_data *rdp)
+	__acquires(&rdp->nocb_bypass_lock)
 {
 	lockdep_assert_irqs_disabled();
 	if (raw_spin_trylock(&rdp->nocb_bypass_lock))
@@ -1529,6 +1518,7 @@ static bool rcu_nocb_bypass_trylock(struct rcu_data *rdp)
  * Release the specified rcu_data structure's ->nocb_bypass_lock.
  */
 static void rcu_nocb_bypass_unlock(struct rcu_data *rdp)
+	__releases(&rdp->nocb_bypass_lock)
 {
 	lockdep_assert_irqs_disabled();
 	raw_spin_unlock(&rdp->nocb_bypass_lock);
@@ -1577,8 +1567,7 @@ static void rcu_nocb_unlock_irqrestore(struct rcu_data *rdp,
 static void rcu_lockdep_assert_cblist_protected(struct rcu_data *rdp)
 {
 	lockdep_assert_irqs_disabled();
-	if (rcu_segcblist_is_offloaded(&rdp->cblist) &&
-	    cpu_online(rdp->cpu))
+	if (rcu_segcblist_is_offloaded(&rdp->cblist))
 		lockdep_assert_held(&rdp->nocb_lock);
 }
 
@@ -1930,6 +1919,7 @@ static void nocb_gp_wait(struct rcu_data *my_rdp)
 	struct rcu_data *rdp;
 	struct rcu_node *rnp;
 	unsigned long wait_gp_seq = 0; // Suppress "use uninitialized" warning.
+	bool wasempty = false;
 
 	/*
 	 * Each pass through the following loop checks for CBs and for the
@@ -1969,10 +1959,13 @@ static void nocb_gp_wait(struct rcu_data *my_rdp)
 		     rcu_seq_done(&rnp->gp_seq, cur_gp_seq))) {
 			raw_spin_lock_rcu_node(rnp); /* irqs disabled. */
 			needwake_gp = rcu_advance_cbs(rnp, rdp);
+			wasempty = rcu_segcblist_restempty(&rdp->cblist,
+							   RCU_NEXT_READY_TAIL);
 			raw_spin_unlock_rcu_node(rnp); /* irqs disabled. */
 		}
 		// Need to wait on some grace period?
-		WARN_ON_ONCE(!rcu_segcblist_restempty(&rdp->cblist,
+		WARN_ON_ONCE(wasempty &&
+			     !rcu_segcblist_restempty(&rdp->cblist,
 						      RCU_NEXT_READY_TAIL));
 		if (rcu_segcblist_nextgp(&rdp->cblist, &cur_gp_seq)) {
 			if (!needwait_gp ||
@@ -2012,7 +2005,7 @@ static void nocb_gp_wait(struct rcu_data *my_rdp)
 		/* Polling, so trace if first poll in the series. */
 		if (gotcbs)
 			trace_rcu_nocb_wake(rcu_state.name, cpu, TPS("Poll"));
-		schedule_timeout_interruptible(1);
+		schedule_timeout_idle(1);
 	} else if (!needwait_gp) {
 		/* Wait for callbacks to appear. */
 		trace_rcu_nocb_wake(rcu_state.name, cpu, TPS("Sleep"));
@@ -2529,7 +2522,7 @@ static bool rcu_nohz_full_cpu(void)
 #ifdef CONFIG_NO_HZ_FULL
 	if (tick_nohz_full_cpu(smp_processor_id()) &&
 	    (!rcu_gp_in_progress() ||
-	     ULONG_CMP_LT(jiffies, READ_ONCE(rcu_state.gp_start) + HZ)))
+	     time_before(jiffies, READ_ONCE(rcu_state.gp_start) + HZ)))
 		return true;
 #endif /* #ifdef CONFIG_NO_HZ_FULL */
 	return false;
@@ -2546,7 +2539,7 @@ static void rcu_bind_gp_kthread(void)
 }
 
 /* Record the current task on dyntick-idle entry. */
-static void rcu_dynticks_task_enter(void)
+static void noinstr rcu_dynticks_task_enter(void)
 {
 #if defined(CONFIG_TASKS_RCU) && defined(CONFIG_NO_HZ_FULL)
 	WRITE_ONCE(current->rcu_tasks_idle_cpu, smp_processor_id());
@@ -2554,9 +2547,27 @@ static void rcu_dynticks_task_enter(void)
 }
 
 /* Record no current task on dyntick-idle exit. */
-static void rcu_dynticks_task_exit(void)
+static void noinstr rcu_dynticks_task_exit(void)
 {
 #if defined(CONFIG_TASKS_RCU) && defined(CONFIG_NO_HZ_FULL)
 	WRITE_ONCE(current->rcu_tasks_idle_cpu, -1);
 #endif /* #if defined(CONFIG_TASKS_RCU) && defined(CONFIG_NO_HZ_FULL) */
 }
+
+/* Turn on heavyweight RCU tasks trace readers on idle/user entry. */
+static void rcu_dynticks_task_trace_enter(void)
+{
+#ifdef CONFIG_TASKS_RCU_TRACE
+	if (IS_ENABLED(CONFIG_TASKS_TRACE_RCU_READ_MB))
+		current->trc_reader_special.b.need_mb = true;
+#endif /* #ifdef CONFIG_TASKS_RCU_TRACE */
+}
+
+/* Turn off heavyweight RCU tasks trace readers on idle/user exit. */
+static void rcu_dynticks_task_trace_exit(void)
+{
+#ifdef CONFIG_TASKS_RCU_TRACE
+	if (IS_ENABLED(CONFIG_TASKS_TRACE_RCU_READ_MB))
+		current->trc_reader_special.b.need_mb = false;
+#endif /* #ifdef CONFIG_TASKS_RCU_TRACE */
+}
diff --git a/kernel/rcu/tree_stall.h b/kernel/rcu/tree_stall.h
index 55f9b84790d3..b5d3b4794db4 100644
--- a/kernel/rcu/tree_stall.h
+++ b/kernel/rcu/tree_stall.h
@@ -15,10 +15,12 @@
 int sysctl_panic_on_rcu_stall __read_mostly;
 
 #ifdef CONFIG_PROVE_RCU
-#define RCU_STALL_DELAY_DELTA	       (5 * HZ)
+#define RCU_STALL_DELAY_DELTA		(5 * HZ)
 #else
-#define RCU_STALL_DELAY_DELTA	       0
+#define RCU_STALL_DELAY_DELTA		0
 #endif
+#define RCU_STALL_MIGHT_DIV		8
+#define RCU_STALL_MIGHT_MIN		(2 * HZ)
 
 /* Limit-check stall timeouts specified at boottime and runtime. */
 int rcu_jiffies_till_stall_check(void)
@@ -40,6 +42,36 @@ int rcu_jiffies_till_stall_check(void)
 }
 EXPORT_SYMBOL_GPL(rcu_jiffies_till_stall_check);
 
+/**
+ * rcu_gp_might_be_stalled - Is it likely that the grace period is stalled?
+ *
+ * Returns @true if the current grace period is sufficiently old that
+ * it is reasonable to assume that it might be stalled.  This can be
+ * useful when deciding whether to allocate memory to enable RCU-mediated
+ * freeing on the one hand or just invoking synchronize_rcu() on the other.
+ * The latter is preferable when the grace period is stalled.
+ *
+ * Note that sampling of the .gp_start and .gp_seq fields must be done
+ * carefully to avoid false positives at the beginnings and ends of
+ * grace periods.
+ */
+bool rcu_gp_might_be_stalled(void)
+{
+	unsigned long d = rcu_jiffies_till_stall_check() / RCU_STALL_MIGHT_DIV;
+	unsigned long j = jiffies;
+
+	if (d < RCU_STALL_MIGHT_MIN)
+		d = RCU_STALL_MIGHT_MIN;
+	smp_mb(); // jiffies before .gp_seq to avoid false positives.
+	if (!rcu_gp_in_progress())
+		return false;
+	// Long delays at this point avoids false positive, but a delay
+	// of ULONG_MAX/4 jiffies voids your no-false-positive warranty.
+	smp_mb(); // .gp_seq before second .gp_start
+	// And ditto here.
+	return !time_before(j, READ_ONCE(rcu_state.gp_start) + d);
+}
+
 /* Don't do RCU CPU stall warnings during long sysrq printouts. */
 void rcu_sysrq_start(void)
 {
@@ -102,10 +134,10 @@ static void record_gp_stall_check_time(void)
 	unsigned long j = jiffies;
 	unsigned long j1;
 
-	rcu_state.gp_start = j;
+	WRITE_ONCE(rcu_state.gp_start, j);
 	j1 = rcu_jiffies_till_stall_check();
-	/* Record ->gp_start before ->jiffies_stall. */
-	smp_store_release(&rcu_state.jiffies_stall, j + j1); /* ^^^ */
+	smp_mb(); // ->gp_start before ->jiffies_stall and caller's ->gp_seq.
+	WRITE_ONCE(rcu_state.jiffies_stall, j + j1);
 	rcu_state.jiffies_resched = j + j1 / 2;
 	rcu_state.n_force_qs_gpstart = READ_ONCE(rcu_state.n_force_qs);
 }
@@ -192,14 +224,38 @@ static void rcu_print_detail_task_stall_rnp(struct rcu_node *rnp)
 	raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 }
 
+// Communicate task state back to the RCU CPU stall warning request.
+struct rcu_stall_chk_rdr {
+	int nesting;
+	union rcu_special rs;
+	bool on_blkd_list;
+};
+
+/*
+ * Report out the state of a not-running task that is stalling the
+ * current RCU grace period.
+ */
+static bool check_slow_task(struct task_struct *t, void *arg)
+{
+	struct rcu_stall_chk_rdr *rscrp = arg;
+
+	if (task_curr(t))
+		return false; // It is running, so decline to inspect it.
+	rscrp->nesting = t->rcu_read_lock_nesting;
+	rscrp->rs = t->rcu_read_unlock_special;
+	rscrp->on_blkd_list = !list_empty(&t->rcu_node_entry);
+	return true;
+}
+
 /*
  * Scan the current list of tasks blocked within RCU read-side critical
  * sections, printing out the tid of each.
  */
 static int rcu_print_task_stall(struct rcu_node *rnp)
 {
-	struct task_struct *t;
 	int ndetected = 0;
+	struct rcu_stall_chk_rdr rscr;
+	struct task_struct *t;
 
 	if (!rcu_preempt_blocked_readers_cgp(rnp))
 		return 0;
@@ -208,7 +264,15 @@ static int rcu_print_task_stall(struct rcu_node *rnp)
 	t = list_entry(rnp->gp_tasks->prev,
 		       struct task_struct, rcu_node_entry);
 	list_for_each_entry_continue(t, &rnp->blkd_tasks, rcu_node_entry) {
-		pr_cont(" P%d", t->pid);
+		if (!try_invoke_on_locked_down_task(t, check_slow_task, &rscr))
+			pr_cont(" P%d", t->pid);
+		else
+			pr_cont(" P%d/%d:%c%c%c%c",
+				t->pid, rscr.nesting,
+				".b"[rscr.rs.b.blocked],
+				".q"[rscr.rs.b.need_qs],
+				".e"[rscr.rs.b.exp_hint],
+				".l"[rscr.on_blkd_list]);
 		ndetected++;
 	}
 	pr_cont("\n");
@@ -299,6 +363,16 @@ static const char *gp_state_getname(short gs)
 	return gp_state_names[gs];
 }
 
+/* Is the RCU grace-period kthread being starved of CPU time? */
+static bool rcu_is_gp_kthread_starving(unsigned long *jp)
+{
+	unsigned long j = jiffies - READ_ONCE(rcu_state.gp_activity);
+
+	if (jp)
+		*jp = j;
+	return j > 2 * HZ;
+}
+
 /*
  * Print out diagnostic information for the specified stalled CPU.
  *
@@ -313,6 +387,7 @@ static const char *gp_state_getname(short gs)
 static void print_cpu_stall_info(int cpu)
 {
 	unsigned long delta;
+	bool falsepositive;
 	char fast_no_hz[72];
 	struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
 	char *ticks_title;
@@ -333,7 +408,9 @@ static void print_cpu_stall_info(int cpu)
 	}
 	print_cpu_stall_fast_no_hz(fast_no_hz, cpu);
 	delta = rcu_seq_ctr(rdp->mynode->gp_seq - rdp->rcu_iw_gp_seq);
-	pr_err("\t%d-%c%c%c%c: (%lu %s) idle=%03x/%ld/%#lx softirq=%u/%u fqs=%ld %s\n",
+	falsepositive = rcu_is_gp_kthread_starving(NULL) &&
+			rcu_dynticks_in_eqs(rcu_dynticks_snap(rdp));
+	pr_err("\t%d-%c%c%c%c: (%lu %s) idle=%03x/%ld/%#lx softirq=%u/%u fqs=%ld %s%s\n",
 	       cpu,
 	       "O."[!!cpu_online(cpu)],
 	       "o."[!!(rdp->grpmask & rdp->mynode->qsmaskinit)],
@@ -345,8 +422,9 @@ static void print_cpu_stall_info(int cpu)
 	       rcu_dynticks_snap(rdp) & 0xfff,
 	       rdp->dynticks_nesting, rdp->dynticks_nmi_nesting,
 	       rdp->softirq_snap, kstat_softirqs_cpu(RCU_SOFTIRQ, cpu),
-	       READ_ONCE(rcu_state.n_force_qs) - rcu_state.n_force_qs_gpstart,
-	       fast_no_hz);
+	       data_race(rcu_state.n_force_qs) - rcu_state.n_force_qs_gpstart,
+	       fast_no_hz,
+	       falsepositive ? " (false positive?)" : "");
 }
 
 /* Complain about starvation of grace-period kthread.  */
@@ -355,15 +433,15 @@ static void rcu_check_gp_kthread_starvation(void)
 	struct task_struct *gpk = rcu_state.gp_kthread;
 	unsigned long j;
 
-	j = jiffies - READ_ONCE(rcu_state.gp_activity);
-	if (j > 2 * HZ) {
+	if (rcu_is_gp_kthread_starving(&j)) {
 		pr_err("%s kthread starved for %ld jiffies! g%ld f%#x %s(%d) ->state=%#lx ->cpu=%d\n",
 		       rcu_state.name, j,
 		       (long)rcu_seq_current(&rcu_state.gp_seq),
-		       READ_ONCE(rcu_state.gp_flags),
+		       data_race(rcu_state.gp_flags),
 		       gp_state_getname(rcu_state.gp_state), rcu_state.gp_state,
 		       gpk ? gpk->state : ~0, gpk ? task_cpu(gpk) : -1);
 		if (gpk) {
+			pr_err("\tUnless %s kthread gets sufficient CPU time, OOM is now expected behavior.\n", rcu_state.name);
 			pr_err("RCU grace-period kthread stack dump:\n");
 			sched_show_task(gpk);
 			wake_up_process(gpk);
@@ -371,7 +449,7 @@ static void rcu_check_gp_kthread_starvation(void)
 	}
 }
 
-static void print_other_cpu_stall(unsigned long gp_seq)
+static void print_other_cpu_stall(unsigned long gp_seq, unsigned long gps)
 {
 	int cpu;
 	unsigned long flags;
@@ -383,12 +461,12 @@ static void print_other_cpu_stall(unsigned long gp_seq)
 
 	/* Kick and suppress, if so configured. */
 	rcu_stall_kick_kthreads();
-	if (rcu_cpu_stall_suppress)
+	if (rcu_stall_is_suppressed())
 		return;
 
 	/*
 	 * OK, time to rat on our buddy...
-	 * See Documentation/RCU/stallwarn.txt for info on how to debug
+	 * See Documentation/RCU/stallwarn.rst for info on how to debug
 	 * RCU CPU stall warnings.
 	 */
 	pr_err("INFO: %s detected stalls on CPUs/tasks:\n", rcu_state.name);
@@ -408,7 +486,7 @@ static void print_other_cpu_stall(unsigned long gp_seq)
 	for_each_possible_cpu(cpu)
 		totqlen += rcu_get_n_cbs_cpu(cpu);
 	pr_cont("\t(detected by %d, t=%ld jiffies, g=%ld, q=%lu)\n",
-	       smp_processor_id(), (long)(jiffies - rcu_state.gp_start),
+	       smp_processor_id(), (long)(jiffies - gps),
 	       (long)rcu_seq_current(&rcu_state.gp_seq), totqlen);
 	if (ndetected) {
 		rcu_dump_cpu_stacks();
@@ -421,13 +499,11 @@ static void print_other_cpu_stall(unsigned long gp_seq)
 			pr_err("INFO: Stall ended before state dump start\n");
 		} else {
 			j = jiffies;
-			gpa = READ_ONCE(rcu_state.gp_activity);
+			gpa = data_race(rcu_state.gp_activity);
 			pr_err("All QSes seen, last %s kthread activity %ld (%ld-%ld), jiffies_till_next_fqs=%ld, root ->qsmask %#lx\n",
 			       rcu_state.name, j - gpa, j, gpa,
-			       READ_ONCE(jiffies_till_next_fqs),
+			       data_race(jiffies_till_next_fqs),
 			       rcu_get_root()->qsmask);
-			/* In this case, the current CPU might be at fault. */
-			sched_show_task(current);
 		}
 	}
 	/* Rewrite if needed in case of slow consoles. */
@@ -442,7 +518,7 @@ static void print_other_cpu_stall(unsigned long gp_seq)
 	rcu_force_quiescent_state();  /* Kick them all. */
 }
 
-static void print_cpu_stall(void)
+static void print_cpu_stall(unsigned long gps)
 {
 	int cpu;
 	unsigned long flags;
@@ -452,12 +528,12 @@ static void print_cpu_stall(void)
 
 	/* Kick and suppress, if so configured. */
 	rcu_stall_kick_kthreads();
-	if (rcu_cpu_stall_suppress)
+	if (rcu_stall_is_suppressed())
 		return;
 
 	/*
 	 * OK, time to rat on ourselves...
-	 * See Documentation/RCU/stallwarn.txt for info on how to debug
+	 * See Documentation/RCU/stallwarn.rst for info on how to debug
 	 * RCU CPU stall warnings.
 	 */
 	pr_err("INFO: %s self-detected stall on CPU\n", rcu_state.name);
@@ -467,7 +543,7 @@ static void print_cpu_stall(void)
 	for_each_possible_cpu(cpu)
 		totqlen += rcu_get_n_cbs_cpu(cpu);
 	pr_cont("\t(t=%lu jiffies g=%ld q=%lu)\n",
-		jiffies - rcu_state.gp_start,
+		jiffies - gps,
 		(long)rcu_seq_current(&rcu_state.gp_seq), totqlen);
 
 	rcu_check_gp_kthread_starvation();
@@ -504,7 +580,7 @@ static void check_cpu_stall(struct rcu_data *rdp)
 	unsigned long js;
 	struct rcu_node *rnp;
 
-	if ((rcu_cpu_stall_suppress && !rcu_kick_kthreads) ||
+	if ((rcu_stall_is_suppressed() && !rcu_kick_kthreads) ||
 	    !rcu_gp_in_progress())
 		return;
 	rcu_stall_kick_kthreads();
@@ -546,7 +622,7 @@ static void check_cpu_stall(struct rcu_data *rdp)
 	    cmpxchg(&rcu_state.jiffies_stall, js, jn) == js) {
 
 		/* We haven't checked in, so go dump stack. */
-		print_cpu_stall();
+		print_cpu_stall(gps);
 		if (rcu_cpu_stall_ftrace_dump)
 			rcu_ftrace_dump(DUMP_ALL);
 
@@ -555,7 +631,7 @@ static void check_cpu_stall(struct rcu_data *rdp)
 		   cmpxchg(&rcu_state.jiffies_stall, js, jn) == js) {
 
 		/* They had a few time units to dump stack, so complain. */
-		print_other_cpu_stall(gs2);
+		print_other_cpu_stall(gs2, gps);
 		if (rcu_cpu_stall_ftrace_dump)
 			rcu_ftrace_dump(DUMP_ALL);
 	}
@@ -571,6 +647,7 @@ static void check_cpu_stall(struct rcu_data *rdp)
  */
 void show_rcu_gp_kthreads(void)
 {
+	unsigned long cbs = 0;
 	int cpu;
 	unsigned long j;
 	unsigned long ja;
@@ -578,43 +655,46 @@ void show_rcu_gp_kthreads(void)
 	unsigned long jw;
 	struct rcu_data *rdp;
 	struct rcu_node *rnp;
+	struct task_struct *t = READ_ONCE(rcu_state.gp_kthread);
 
 	j = jiffies;
-	ja = j - READ_ONCE(rcu_state.gp_activity);
-	jr = j - READ_ONCE(rcu_state.gp_req_activity);
-	jw = j - READ_ONCE(rcu_state.gp_wake_time);
+	ja = j - data_race(rcu_state.gp_activity);
+	jr = j - data_race(rcu_state.gp_req_activity);
+	jw = j - data_race(rcu_state.gp_wake_time);
 	pr_info("%s: wait state: %s(%d) ->state: %#lx delta ->gp_activity %lu ->gp_req_activity %lu ->gp_wake_time %lu ->gp_wake_seq %ld ->gp_seq %ld ->gp_seq_needed %ld ->gp_flags %#x\n",
 		rcu_state.name, gp_state_getname(rcu_state.gp_state),
-		rcu_state.gp_state,
-		rcu_state.gp_kthread ? rcu_state.gp_kthread->state : 0x1ffffL,
-		ja, jr, jw, (long)READ_ONCE(rcu_state.gp_wake_seq),
-		(long)READ_ONCE(rcu_state.gp_seq),
-		(long)READ_ONCE(rcu_get_root()->gp_seq_needed),
-		READ_ONCE(rcu_state.gp_flags));
+		rcu_state.gp_state, t ? t->state : 0x1ffffL,
+		ja, jr, jw, (long)data_race(rcu_state.gp_wake_seq),
+		(long)data_race(rcu_state.gp_seq),
+		(long)data_race(rcu_get_root()->gp_seq_needed),
+		data_race(rcu_state.gp_flags));
 	rcu_for_each_node_breadth_first(rnp) {
-		if (ULONG_CMP_GE(rcu_state.gp_seq, rnp->gp_seq_needed))
+		if (ULONG_CMP_GE(READ_ONCE(rcu_state.gp_seq),
+				 READ_ONCE(rnp->gp_seq_needed)))
 			continue;
 		pr_info("\trcu_node %d:%d ->gp_seq %ld ->gp_seq_needed %ld\n",
-			rnp->grplo, rnp->grphi, (long)rnp->gp_seq,
-			(long)rnp->gp_seq_needed);
+			rnp->grplo, rnp->grphi, (long)data_race(rnp->gp_seq),
+			(long)data_race(rnp->gp_seq_needed));
 		if (!rcu_is_leaf_node(rnp))
 			continue;
 		for_each_leaf_node_possible_cpu(rnp, cpu) {
 			rdp = per_cpu_ptr(&rcu_data, cpu);
-			if (rdp->gpwrap ||
-			    ULONG_CMP_GE(rcu_state.gp_seq,
-					 rdp->gp_seq_needed))
+			if (READ_ONCE(rdp->gpwrap) ||
+			    ULONG_CMP_GE(READ_ONCE(rcu_state.gp_seq),
+					 READ_ONCE(rdp->gp_seq_needed)))
 				continue;
 			pr_info("\tcpu %d ->gp_seq_needed %ld\n",
-				cpu, (long)rdp->gp_seq_needed);
+				cpu, (long)data_race(rdp->gp_seq_needed));
 		}
 	}
 	for_each_possible_cpu(cpu) {
 		rdp = per_cpu_ptr(&rcu_data, cpu);
+		cbs += data_race(rdp->n_cbs_invoked);
 		if (rcu_segcblist_is_offloaded(&rdp->cblist))
 			show_rcu_nocb_state(rdp);
 	}
-	/* sched_show_task(rcu_state.gp_kthread); */
+	pr_info("RCU callbacks invoked since boot: %lu\n", cbs);
+	show_rcu_tasks_gp_kthreads();
 }
 EXPORT_SYMBOL_GPL(show_rcu_gp_kthreads);
 
@@ -631,7 +711,9 @@ static void rcu_check_gp_start_stall(struct rcu_node *rnp, struct rcu_data *rdp,
 	static atomic_t warned = ATOMIC_INIT(0);
 
 	if (!IS_ENABLED(CONFIG_PROVE_RCU) || rcu_gp_in_progress() ||
-	    ULONG_CMP_GE(rnp_root->gp_seq, rnp_root->gp_seq_needed))
+	    ULONG_CMP_GE(READ_ONCE(rnp_root->gp_seq),
+			 READ_ONCE(rnp_root->gp_seq_needed)) ||
+	    !smp_load_acquire(&rcu_state.gp_kthread)) // Get stable kthread.
 		return;
 	j = jiffies; /* Expensive access, and in common case don't get here. */
 	if (time_before(j, READ_ONCE(rcu_state.gp_req_activity) + gpssdelay) ||
@@ -642,7 +724,8 @@ static void rcu_check_gp_start_stall(struct rcu_node *rnp, struct rcu_data *rdp,
 	raw_spin_lock_irqsave_rcu_node(rnp, flags);
 	j = jiffies;
 	if (rcu_gp_in_progress() ||
-	    ULONG_CMP_GE(rnp_root->gp_seq, rnp_root->gp_seq_needed) ||
+	    ULONG_CMP_GE(READ_ONCE(rnp_root->gp_seq),
+			 READ_ONCE(rnp_root->gp_seq_needed)) ||
 	    time_before(j, READ_ONCE(rcu_state.gp_req_activity) + gpssdelay) ||
 	    time_before(j, READ_ONCE(rcu_state.gp_activity) + gpssdelay) ||
 	    atomic_read(&warned)) {
@@ -655,9 +738,10 @@ static void rcu_check_gp_start_stall(struct rcu_node *rnp, struct rcu_data *rdp,
 		raw_spin_lock_rcu_node(rnp_root); /* irqs already disabled. */
 	j = jiffies;
 	if (rcu_gp_in_progress() ||
-	    ULONG_CMP_GE(rnp_root->gp_seq, rnp_root->gp_seq_needed) ||
-	    time_before(j, rcu_state.gp_req_activity + gpssdelay) ||
-	    time_before(j, rcu_state.gp_activity + gpssdelay) ||
+	    ULONG_CMP_GE(READ_ONCE(rnp_root->gp_seq),
+			 READ_ONCE(rnp_root->gp_seq_needed)) ||
+	    time_before(j, READ_ONCE(rcu_state.gp_req_activity) + gpssdelay) ||
+	    time_before(j, READ_ONCE(rcu_state.gp_activity) + gpssdelay) ||
 	    atomic_xchg(&warned, 1)) {
 		if (rnp_root != rnp)
 			/* irqs remain disabled. */
@@ -724,7 +808,7 @@ static void sysrq_show_rcu(int key)
 	show_rcu_gp_kthreads();
 }
 
-static struct sysrq_key_op sysrq_rcudump_op = {
+static const struct sysrq_key_op sysrq_rcudump_op = {
 	.handler = sysrq_show_rcu,
 	.help_msg = "show-rcu(y)",
 	.action_msg = "Show RCU tree",
diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c
index 6c4b862f57d6..2de49b5d8dd2 100644
--- a/kernel/rcu/update.c
+++ b/kernel/rcu/update.c
@@ -41,6 +41,8 @@
 #include <linux/sched/isolation.h>
 #include <linux/kprobes.h>
 #include <linux/slab.h>
+#include <linux/irq_work.h>
+#include <linux/rcupdate_trace.h>
 
 #define CREATE_TRACE_POINTS
 
@@ -51,6 +53,19 @@
 #endif
 #define MODULE_PARAM_PREFIX "rcupdate."
 
+#ifndef data_race
+#define data_race(expr)							\
+	({								\
+		expr;							\
+	})
+#endif
+#ifndef ASSERT_EXCLUSIVE_WRITER
+#define ASSERT_EXCLUSIVE_WRITER(var) do { } while (0)
+#endif
+#ifndef ASSERT_EXCLUSIVE_ACCESS
+#define ASSERT_EXCLUSIVE_ACCESS(var) do { } while (0)
+#endif
+
 #ifndef CONFIG_TINY_RCU
 module_param(rcu_expedited, int, 0);
 module_param(rcu_normal, int, 0);
@@ -63,12 +78,12 @@ module_param(rcu_normal_after_boot, int, 0);
  * rcu_read_lock_held_common() - might we be in RCU-sched read-side critical section?
  * @ret:	Best guess answer if lockdep cannot be relied on
  *
- * Returns true if lockdep must be ignored, in which case *ret contains
+ * Returns true if lockdep must be ignored, in which case ``*ret`` contains
  * the best guess described below.  Otherwise returns false, in which
- * case *ret tells the caller nothing and the caller should instead
+ * case ``*ret`` tells the caller nothing and the caller should instead
  * consult lockdep.
  *
- * If CONFIG_DEBUG_LOCK_ALLOC is selected, set *ret to nonzero iff in an
+ * If CONFIG_DEBUG_LOCK_ALLOC is selected, set ``*ret`` to nonzero iff in an
  * RCU-sched read-side critical section.  In absence of
  * CONFIG_DEBUG_LOCK_ALLOC, this assumes we are in an RCU-sched read-side
  * critical section unless it can prove otherwise.  Note that disabling
@@ -82,7 +97,7 @@ module_param(rcu_normal_after_boot, int, 0);
  *
  * Note that if the CPU is in the idle loop from an RCU point of view (ie:
  * that we are in the section between rcu_idle_enter() and rcu_idle_exit())
- * then rcu_read_lock_held() sets *ret to false even if the CPU did an
+ * then rcu_read_lock_held() sets ``*ret`` to false even if the CPU did an
  * rcu_read_lock().  The reason for this is that RCU ignores CPUs that are
  * in such a section, considering these as in extended quiescent state,
  * so such a CPU is effectively never in an RCU read-side critical section
@@ -98,15 +113,15 @@ module_param(rcu_normal_after_boot, int, 0);
 static bool rcu_read_lock_held_common(bool *ret)
 {
 	if (!debug_lockdep_rcu_enabled()) {
-		*ret = 1;
+		*ret = true;
 		return true;
 	}
 	if (!rcu_is_watching()) {
-		*ret = 0;
+		*ret = false;
 		return true;
 	}
 	if (!rcu_lockdep_current_cpu_online()) {
-		*ret = 0;
+		*ret = false;
 		return true;
 	}
 	return false;
@@ -183,6 +198,8 @@ void rcu_unexpedite_gp(void)
 }
 EXPORT_SYMBOL_GPL(rcu_unexpedite_gp);
 
+static bool rcu_boot_ended __read_mostly;
+
 /*
  * Inform RCU of the end of the in-kernel boot sequence.
  */
@@ -191,8 +208,18 @@ void rcu_end_inkernel_boot(void)
 	rcu_unexpedite_gp();
 	if (rcu_normal_after_boot)
 		WRITE_ONCE(rcu_normal, 1);
+	rcu_boot_ended = true;
 }
 
+/*
+ * Let rcutorture know when it is OK to turn it up to eleven.
+ */
+bool rcu_inkernel_boot_has_ended(void)
+{
+	return rcu_boot_ended;
+}
+EXPORT_SYMBOL_GPL(rcu_inkernel_boot_has_ended);
+
 #endif /* #ifndef CONFIG_TINY_RCU */
 
 /*
@@ -227,32 +254,44 @@ core_initcall(rcu_set_runtime_mode);
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 static struct lock_class_key rcu_lock_key;
-struct lockdep_map rcu_lock_map =
-	STATIC_LOCKDEP_MAP_INIT("rcu_read_lock", &rcu_lock_key);
+struct lockdep_map rcu_lock_map = {
+	.name = "rcu_read_lock",
+	.key = &rcu_lock_key,
+	.wait_type_outer = LD_WAIT_FREE,
+	.wait_type_inner = LD_WAIT_CONFIG, /* XXX PREEMPT_RCU ? */
+};
 EXPORT_SYMBOL_GPL(rcu_lock_map);
 
 static struct lock_class_key rcu_bh_lock_key;
-struct lockdep_map rcu_bh_lock_map =
-	STATIC_LOCKDEP_MAP_INIT("rcu_read_lock_bh", &rcu_bh_lock_key);
+struct lockdep_map rcu_bh_lock_map = {
+	.name = "rcu_read_lock_bh",
+	.key = &rcu_bh_lock_key,
+	.wait_type_outer = LD_WAIT_FREE,
+	.wait_type_inner = LD_WAIT_CONFIG, /* PREEMPT_LOCK also makes BH preemptible */
+};
 EXPORT_SYMBOL_GPL(rcu_bh_lock_map);
 
 static struct lock_class_key rcu_sched_lock_key;
-struct lockdep_map rcu_sched_lock_map =
-	STATIC_LOCKDEP_MAP_INIT("rcu_read_lock_sched", &rcu_sched_lock_key);
+struct lockdep_map rcu_sched_lock_map = {
+	.name = "rcu_read_lock_sched",
+	.key = &rcu_sched_lock_key,
+	.wait_type_outer = LD_WAIT_FREE,
+	.wait_type_inner = LD_WAIT_SPIN,
+};
 EXPORT_SYMBOL_GPL(rcu_sched_lock_map);
 
+// Tell lockdep when RCU callbacks are being invoked.
 static struct lock_class_key rcu_callback_key;
 struct lockdep_map rcu_callback_map =
 	STATIC_LOCKDEP_MAP_INIT("rcu_callback", &rcu_callback_key);
 EXPORT_SYMBOL_GPL(rcu_callback_map);
 
-int notrace debug_lockdep_rcu_enabled(void)
+noinstr int notrace debug_lockdep_rcu_enabled(void)
 {
 	return rcu_scheduler_active != RCU_SCHEDULER_INACTIVE && debug_locks &&
 	       current->lockdep_recursion == 0;
 }
 EXPORT_SYMBOL_GPL(debug_lockdep_rcu_enabled);
-NOKPROBE_SYMBOL(debug_lockdep_rcu_enabled);
 
 /**
  * rcu_read_lock_held() - might we be in RCU read-side critical section?
@@ -353,13 +392,14 @@ void __wait_rcu_gp(bool checktiny, int n, call_rcu_func_t *crcu_array,
 			might_sleep();
 			continue;
 		}
-		init_rcu_head_on_stack(&rs_array[i].head);
-		init_completion(&rs_array[i].completion);
 		for (j = 0; j < i; j++)
 			if (crcu_array[j] == crcu_array[i])
 				break;
-		if (j == i)
+		if (j == i) {
+			init_rcu_head_on_stack(&rs_array[i].head);
+			init_completion(&rs_array[i].completion);
 			(crcu_array[i])(&rs_array[i].head, wakeme_after_rcu);
+		}
 	}
 
 	/* Wait for all callbacks to be invoked. */
@@ -370,9 +410,10 @@ void __wait_rcu_gp(bool checktiny, int n, call_rcu_func_t *crcu_array,
 		for (j = 0; j < i; j++)
 			if (crcu_array[j] == crcu_array[i])
 				break;
-		if (j == i)
+		if (j == i) {
 			wait_for_completion(&rs_array[i].completion);
-		destroy_rcu_head_on_stack(&rs_array[i].head);
+			destroy_rcu_head_on_stack(&rs_array[i].head);
+		}
 	}
 }
 EXPORT_SYMBOL_GPL(__wait_rcu_gp);
@@ -464,376 +505,18 @@ EXPORT_SYMBOL_GPL(rcutorture_sched_setaffinity);
 #ifdef CONFIG_RCU_STALL_COMMON
 int rcu_cpu_stall_ftrace_dump __read_mostly;
 module_param(rcu_cpu_stall_ftrace_dump, int, 0644);
-int rcu_cpu_stall_suppress __read_mostly; /* 1 = suppress stall warnings. */
+int rcu_cpu_stall_suppress __read_mostly; // !0 = suppress stall warnings.
 EXPORT_SYMBOL_GPL(rcu_cpu_stall_suppress);
 module_param(rcu_cpu_stall_suppress, int, 0644);
 int rcu_cpu_stall_timeout __read_mostly = CONFIG_RCU_CPU_STALL_TIMEOUT;
 module_param(rcu_cpu_stall_timeout, int, 0644);
 #endif /* #ifdef CONFIG_RCU_STALL_COMMON */
 
-#ifdef CONFIG_TASKS_RCU
-
-/*
- * Simple variant of RCU whose quiescent states are voluntary context
- * switch, cond_resched_rcu_qs(), user-space execution, and idle.
- * As such, grace periods can take one good long time.  There are no
- * read-side primitives similar to rcu_read_lock() and rcu_read_unlock()
- * because this implementation is intended to get the system into a safe
- * state for some of the manipulations involved in tracing and the like.
- * Finally, this implementation does not support high call_rcu_tasks()
- * rates from multiple CPUs.  If this is required, per-CPU callback lists
- * will be needed.
- */
-
-/* Global list of callbacks and associated lock. */
-static struct rcu_head *rcu_tasks_cbs_head;
-static struct rcu_head **rcu_tasks_cbs_tail = &rcu_tasks_cbs_head;
-static DECLARE_WAIT_QUEUE_HEAD(rcu_tasks_cbs_wq);
-static DEFINE_RAW_SPINLOCK(rcu_tasks_cbs_lock);
-
-/* Track exiting tasks in order to allow them to be waited for. */
-DEFINE_STATIC_SRCU(tasks_rcu_exit_srcu);
-
-/* Control stall timeouts.  Disable with <= 0, otherwise jiffies till stall. */
-#define RCU_TASK_STALL_TIMEOUT (HZ * 60 * 10)
-static int rcu_task_stall_timeout __read_mostly = RCU_TASK_STALL_TIMEOUT;
-module_param(rcu_task_stall_timeout, int, 0644);
-
-static struct task_struct *rcu_tasks_kthread_ptr;
-
-/**
- * call_rcu_tasks() - Queue an RCU for invocation task-based grace period
- * @rhp: structure to be used for queueing the RCU updates.
- * @func: actual callback function to be invoked after the grace period
- *
- * The callback function will be invoked some time after a full grace
- * period elapses, in other words after all currently executing RCU
- * read-side critical sections have completed. call_rcu_tasks() assumes
- * that the read-side critical sections end at a voluntary context
- * switch (not a preemption!), cond_resched_rcu_qs(), entry into idle,
- * or transition to usermode execution.  As such, there are no read-side
- * primitives analogous to rcu_read_lock() and rcu_read_unlock() because
- * this primitive is intended to determine that all tasks have passed
- * through a safe state, not so much for data-strcuture synchronization.
- *
- * See the description of call_rcu() for more detailed information on
- * memory ordering guarantees.
- */
-void call_rcu_tasks(struct rcu_head *rhp, rcu_callback_t func)
-{
-	unsigned long flags;
-	bool needwake;
-
-	rhp->next = NULL;
-	rhp->func = func;
-	raw_spin_lock_irqsave(&rcu_tasks_cbs_lock, flags);
-	needwake = !rcu_tasks_cbs_head;
-	*rcu_tasks_cbs_tail = rhp;
-	rcu_tasks_cbs_tail = &rhp->next;
-	raw_spin_unlock_irqrestore(&rcu_tasks_cbs_lock, flags);
-	/* We can't create the thread unless interrupts are enabled. */
-	if (needwake && READ_ONCE(rcu_tasks_kthread_ptr))
-		wake_up(&rcu_tasks_cbs_wq);
-}
-EXPORT_SYMBOL_GPL(call_rcu_tasks);
-
-/**
- * synchronize_rcu_tasks - wait until an rcu-tasks grace period has elapsed.
- *
- * Control will return to the caller some time after a full rcu-tasks
- * grace period has elapsed, in other words after all currently
- * executing rcu-tasks read-side critical sections have elapsed.  These
- * read-side critical sections are delimited by calls to schedule(),
- * cond_resched_tasks_rcu_qs(), idle execution, userspace execution, calls
- * to synchronize_rcu_tasks(), and (in theory, anyway) cond_resched().
- *
- * This is a very specialized primitive, intended only for a few uses in
- * tracing and other situations requiring manipulation of function
- * preambles and profiling hooks.  The synchronize_rcu_tasks() function
- * is not (yet) intended for heavy use from multiple CPUs.
- *
- * Note that this guarantee implies further memory-ordering guarantees.
- * On systems with more than one CPU, when synchronize_rcu_tasks() returns,
- * each CPU is guaranteed to have executed a full memory barrier since the
- * end of its last RCU-tasks read-side critical section whose beginning
- * preceded the call to synchronize_rcu_tasks().  In addition, each CPU
- * having an RCU-tasks read-side critical section that extends beyond
- * the return from synchronize_rcu_tasks() is guaranteed to have executed
- * a full memory barrier after the beginning of synchronize_rcu_tasks()
- * and before the beginning of that RCU-tasks read-side critical section.
- * Note that these guarantees include CPUs that are offline, idle, or
- * executing in user mode, as well as CPUs that are executing in the kernel.
- *
- * Furthermore, if CPU A invoked synchronize_rcu_tasks(), which returned
- * to its caller on CPU B, then both CPU A and CPU B are guaranteed
- * to have executed a full memory barrier during the execution of
- * synchronize_rcu_tasks() -- even if CPU A and CPU B are the same CPU
- * (but again only if the system has more than one CPU).
- */
-void synchronize_rcu_tasks(void)
-{
-	/* Complain if the scheduler has not started.  */
-	RCU_LOCKDEP_WARN(rcu_scheduler_active == RCU_SCHEDULER_INACTIVE,
-			 "synchronize_rcu_tasks called too soon");
-
-	/* Wait for the grace period. */
-	wait_rcu_gp(call_rcu_tasks);
-}
-EXPORT_SYMBOL_GPL(synchronize_rcu_tasks);
-
-/**
- * rcu_barrier_tasks - Wait for in-flight call_rcu_tasks() callbacks.
- *
- * Although the current implementation is guaranteed to wait, it is not
- * obligated to, for example, if there are no pending callbacks.
- */
-void rcu_barrier_tasks(void)
-{
-	/* There is only one callback queue, so this is easy.  ;-) */
-	synchronize_rcu_tasks();
-}
-EXPORT_SYMBOL_GPL(rcu_barrier_tasks);
-
-/* See if tasks are still holding out, complain if so. */
-static void check_holdout_task(struct task_struct *t,
-			       bool needreport, bool *firstreport)
-{
-	int cpu;
-
-	if (!READ_ONCE(t->rcu_tasks_holdout) ||
-	    t->rcu_tasks_nvcsw != READ_ONCE(t->nvcsw) ||
-	    !READ_ONCE(t->on_rq) ||
-	    (IS_ENABLED(CONFIG_NO_HZ_FULL) &&
-	     !is_idle_task(t) && t->rcu_tasks_idle_cpu >= 0)) {
-		WRITE_ONCE(t->rcu_tasks_holdout, false);
-		list_del_init(&t->rcu_tasks_holdout_list);
-		put_task_struct(t);
-		return;
-	}
-	rcu_request_urgent_qs_task(t);
-	if (!needreport)
-		return;
-	if (*firstreport) {
-		pr_err("INFO: rcu_tasks detected stalls on tasks:\n");
-		*firstreport = false;
-	}
-	cpu = task_cpu(t);
-	pr_alert("%p: %c%c nvcsw: %lu/%lu holdout: %d idle_cpu: %d/%d\n",
-		 t, ".I"[is_idle_task(t)],
-		 "N."[cpu < 0 || !tick_nohz_full_cpu(cpu)],
-		 t->rcu_tasks_nvcsw, t->nvcsw, t->rcu_tasks_holdout,
-		 t->rcu_tasks_idle_cpu, cpu);
-	sched_show_task(t);
-}
-
-/* RCU-tasks kthread that detects grace periods and invokes callbacks. */
-static int __noreturn rcu_tasks_kthread(void *arg)
-{
-	unsigned long flags;
-	struct task_struct *g, *t;
-	unsigned long lastreport;
-	struct rcu_head *list;
-	struct rcu_head *next;
-	LIST_HEAD(rcu_tasks_holdouts);
-	int fract;
-
-	/* Run on housekeeping CPUs by default.  Sysadm can move if desired. */
-	housekeeping_affine(current, HK_FLAG_RCU);
-
-	/*
-	 * Each pass through the following loop makes one check for
-	 * newly arrived callbacks, and, if there are some, waits for
-	 * one RCU-tasks grace period and then invokes the callbacks.
-	 * This loop is terminated by the system going down.  ;-)
-	 */
-	for (;;) {
-
-		/* Pick up any new callbacks. */
-		raw_spin_lock_irqsave(&rcu_tasks_cbs_lock, flags);
-		list = rcu_tasks_cbs_head;
-		rcu_tasks_cbs_head = NULL;
-		rcu_tasks_cbs_tail = &rcu_tasks_cbs_head;
-		raw_spin_unlock_irqrestore(&rcu_tasks_cbs_lock, flags);
-
-		/* If there were none, wait a bit and start over. */
-		if (!list) {
-			wait_event_interruptible(rcu_tasks_cbs_wq,
-						 rcu_tasks_cbs_head);
-			if (!rcu_tasks_cbs_head) {
-				WARN_ON(signal_pending(current));
-				schedule_timeout_interruptible(HZ/10);
-			}
-			continue;
-		}
-
-		/*
-		 * Wait for all pre-existing t->on_rq and t->nvcsw
-		 * transitions to complete.  Invoking synchronize_rcu()
-		 * suffices because all these transitions occur with
-		 * interrupts disabled.  Without this synchronize_rcu(),
-		 * a read-side critical section that started before the
-		 * grace period might be incorrectly seen as having started
-		 * after the grace period.
-		 *
-		 * This synchronize_rcu() also dispenses with the
-		 * need for a memory barrier on the first store to
-		 * ->rcu_tasks_holdout, as it forces the store to happen
-		 * after the beginning of the grace period.
-		 */
-		synchronize_rcu();
-
-		/*
-		 * There were callbacks, so we need to wait for an
-		 * RCU-tasks grace period.  Start off by scanning
-		 * the task list for tasks that are not already
-		 * voluntarily blocked.  Mark these tasks and make
-		 * a list of them in rcu_tasks_holdouts.
-		 */
-		rcu_read_lock();
-		for_each_process_thread(g, t) {
-			if (t != current && READ_ONCE(t->on_rq) &&
-			    !is_idle_task(t)) {
-				get_task_struct(t);
-				t->rcu_tasks_nvcsw = READ_ONCE(t->nvcsw);
-				WRITE_ONCE(t->rcu_tasks_holdout, true);
-				list_add(&t->rcu_tasks_holdout_list,
-					 &rcu_tasks_holdouts);
-			}
-		}
-		rcu_read_unlock();
-
-		/*
-		 * Wait for tasks that are in the process of exiting.
-		 * This does only part of the job, ensuring that all
-		 * tasks that were previously exiting reach the point
-		 * where they have disabled preemption, allowing the
-		 * later synchronize_rcu() to finish the job.
-		 */
-		synchronize_srcu(&tasks_rcu_exit_srcu);
-
-		/*
-		 * Each pass through the following loop scans the list
-		 * of holdout tasks, removing any that are no longer
-		 * holdouts.  When the list is empty, we are done.
-		 */
-		lastreport = jiffies;
-
-		/* Start off with HZ/10 wait and slowly back off to 1 HZ wait*/
-		fract = 10;
-
-		for (;;) {
-			bool firstreport;
-			bool needreport;
-			int rtst;
-			struct task_struct *t1;
-
-			if (list_empty(&rcu_tasks_holdouts))
-				break;
-
-			/* Slowly back off waiting for holdouts */
-			schedule_timeout_interruptible(HZ/fract);
-
-			if (fract > 1)
-				fract--;
-
-			rtst = READ_ONCE(rcu_task_stall_timeout);
-			needreport = rtst > 0 &&
-				     time_after(jiffies, lastreport + rtst);
-			if (needreport)
-				lastreport = jiffies;
-			firstreport = true;
-			WARN_ON(signal_pending(current));
-			list_for_each_entry_safe(t, t1, &rcu_tasks_holdouts,
-						rcu_tasks_holdout_list) {
-				check_holdout_task(t, needreport, &firstreport);
-				cond_resched();
-			}
-		}
-
-		/*
-		 * Because ->on_rq and ->nvcsw are not guaranteed
-		 * to have a full memory barriers prior to them in the
-		 * schedule() path, memory reordering on other CPUs could
-		 * cause their RCU-tasks read-side critical sections to
-		 * extend past the end of the grace period.  However,
-		 * because these ->nvcsw updates are carried out with
-		 * interrupts disabled, we can use synchronize_rcu()
-		 * to force the needed ordering on all such CPUs.
-		 *
-		 * This synchronize_rcu() also confines all
-		 * ->rcu_tasks_holdout accesses to be within the grace
-		 * period, avoiding the need for memory barriers for
-		 * ->rcu_tasks_holdout accesses.
-		 *
-		 * In addition, this synchronize_rcu() waits for exiting
-		 * tasks to complete their final preempt_disable() region
-		 * of execution, cleaning up after the synchronize_srcu()
-		 * above.
-		 */
-		synchronize_rcu();
-
-		/* Invoke the callbacks. */
-		while (list) {
-			next = list->next;
-			local_bh_disable();
-			list->func(list);
-			local_bh_enable();
-			list = next;
-			cond_resched();
-		}
-		/* Paranoid sleep to keep this from entering a tight loop */
-		schedule_timeout_uninterruptible(HZ/10);
-	}
-}
-
-/* Spawn rcu_tasks_kthread() at core_initcall() time. */
-static int __init rcu_spawn_tasks_kthread(void)
-{
-	struct task_struct *t;
-
-	t = kthread_run(rcu_tasks_kthread, NULL, "rcu_tasks_kthread");
-	if (WARN_ONCE(IS_ERR(t), "%s: Could not start Tasks-RCU grace-period kthread, OOM is now expected behavior\n", __func__))
-		return 0;
-	smp_mb(); /* Ensure others see full kthread. */
-	WRITE_ONCE(rcu_tasks_kthread_ptr, t);
-	return 0;
-}
-core_initcall(rcu_spawn_tasks_kthread);
-
-/* Do the srcu_read_lock() for the above synchronize_srcu().  */
-void exit_tasks_rcu_start(void)
-{
-	preempt_disable();
-	current->rcu_tasks_idx = __srcu_read_lock(&tasks_rcu_exit_srcu);
-	preempt_enable();
-}
-
-/* Do the srcu_read_unlock() for the above synchronize_srcu().  */
-void exit_tasks_rcu_finish(void)
-{
-	preempt_disable();
-	__srcu_read_unlock(&tasks_rcu_exit_srcu, current->rcu_tasks_idx);
-	preempt_enable();
-}
-
-#endif /* #ifdef CONFIG_TASKS_RCU */
-
-#ifndef CONFIG_TINY_RCU
-
-/*
- * Print any non-default Tasks RCU settings.
- */
-static void __init rcu_tasks_bootup_oddness(void)
-{
-#ifdef CONFIG_TASKS_RCU
-	if (rcu_task_stall_timeout != RCU_TASK_STALL_TIMEOUT)
-		pr_info("\tTasks-RCU CPU stall warnings timeout set to %d (rcu_task_stall_timeout).\n", rcu_task_stall_timeout);
-	else
-		pr_info("\tTasks RCU enabled.\n");
-#endif /* #ifdef CONFIG_TASKS_RCU */
-}
-
-#endif /* #ifndef CONFIG_TINY_RCU */
+// Suppress boot-time RCU CPU stall warnings and rcutorture writer stall
+// warnings.  Also used by rcutorture even if stall warnings are excluded.
+int rcu_cpu_stall_suppress_at_boot __read_mostly; // !0 = suppress boot stalls.
+EXPORT_SYMBOL_GPL(rcu_cpu_stall_suppress_at_boot);
+module_param(rcu_cpu_stall_suppress_at_boot, int, 0444);
 
 #ifdef CONFIG_PROVE_RCU
 
@@ -905,6 +588,8 @@ late_initcall(rcu_verify_early_boot_tests);
 void rcu_early_boot_tests(void) {}
 #endif /* CONFIG_PROVE_RCU */
 
+#include "tasks.h"
+
 #ifndef CONFIG_TINY_RCU
 
 /*
diff --git a/kernel/reboot.c b/kernel/reboot.c
index c4d472b7f1b4..e7b78d5ae1ab 100644
--- a/kernel/reboot.c
+++ b/kernel/reboot.c
@@ -26,7 +26,7 @@ int C_A_D = 1;
 struct pid *cad_pid;
 EXPORT_SYMBOL(cad_pid);
 
-#if defined(CONFIG_ARM) || defined(CONFIG_UNICORE32)
+#if defined(CONFIG_ARM)
 #define DEFAULT_REBOOT_MODE		= REBOOT_HARD
 #else
 #define DEFAULT_REBOOT_MODE
@@ -250,7 +250,7 @@ void kernel_restart(char *cmd)
 		pr_emerg("Restarting system\n");
 	else
 		pr_emerg("Restarting system with command '%s'\n", cmd);
-	kmsg_dump(KMSG_DUMP_RESTART);
+	kmsg_dump(KMSG_DUMP_SHUTDOWN);
 	machine_restart(cmd);
 }
 EXPORT_SYMBOL_GPL(kernel_restart);
@@ -274,7 +274,7 @@ void kernel_halt(void)
 	migrate_to_reboot_cpu();
 	syscore_shutdown();
 	pr_emerg("System halted\n");
-	kmsg_dump(KMSG_DUMP_HALT);
+	kmsg_dump(KMSG_DUMP_SHUTDOWN);
 	machine_halt();
 }
 EXPORT_SYMBOL_GPL(kernel_halt);
@@ -292,7 +292,7 @@ void kernel_power_off(void)
 	migrate_to_reboot_cpu();
 	syscore_shutdown();
 	pr_emerg("Power down\n");
-	kmsg_dump(KMSG_DUMP_POWEROFF);
+	kmsg_dump(KMSG_DUMP_SHUTDOWN);
 	machine_power_off();
 }
 EXPORT_SYMBOL_GPL(kernel_power_off);
diff --git a/kernel/regset.c b/kernel/regset.c
new file mode 100644
index 000000000000..586823786f39
--- /dev/null
+++ b/kernel/regset.c
@@ -0,0 +1,76 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include <linux/export.h>
+#include <linux/slab.h>
+#include <linux/regset.h>
+
+static int __regset_get(struct task_struct *target,
+			const struct user_regset *regset,
+			unsigned int size,
+			void **data)
+{
+	void *p = *data, *to_free = NULL;
+	int res;
+
+	if (!regset->regset_get)
+		return -EOPNOTSUPP;
+	if (size > regset->n * regset->size)
+		size = regset->n * regset->size;
+	if (!p) {
+		to_free = p = kzalloc(size, GFP_KERNEL);
+		if (!p)
+			return -ENOMEM;
+	}
+	res = regset->regset_get(target, regset,
+			   (struct membuf){.p = p, .left = size});
+	if (res < 0) {
+		kfree(to_free);
+		return res;
+	}
+	*data = p;
+	return size - res;
+}
+
+int regset_get(struct task_struct *target,
+	       const struct user_regset *regset,
+	       unsigned int size,
+	       void *data)
+{
+	return __regset_get(target, regset, size, &data);
+}
+EXPORT_SYMBOL(regset_get);
+
+int regset_get_alloc(struct task_struct *target,
+		     const struct user_regset *regset,
+		     unsigned int size,
+		     void **data)
+{
+	*data = NULL;
+	return __regset_get(target, regset, size, data);
+}
+EXPORT_SYMBOL(regset_get_alloc);
+
+/**
+ * copy_regset_to_user - fetch a thread's user_regset data into user memory
+ * @target:	thread to be examined
+ * @view:	&struct user_regset_view describing user thread machine state
+ * @setno:	index in @view->regsets
+ * @offset:	offset into the regset data, in bytes
+ * @size:	amount of data to copy, in bytes
+ * @data:	user-mode pointer to copy into
+ */
+int copy_regset_to_user(struct task_struct *target,
+			const struct user_regset_view *view,
+			unsigned int setno,
+			unsigned int offset, unsigned int size,
+			void __user *data)
+{
+	const struct user_regset *regset = &view->regsets[setno];
+	void *buf;
+	int ret;
+
+	ret = regset_get_alloc(target, regset, size, &buf);
+	if (ret > 0)
+		ret = copy_to_user(data, buf, ret) ? -EFAULT : 0;
+	kfree(buf);
+	return ret;
+}
diff --git a/kernel/relay.c b/kernel/relay.c
index ade14fb7ce2e..fb4e0c530c08 100644
--- a/kernel/relay.c
+++ b/kernel/relay.c
@@ -1,7 +1,7 @@
 /*
  * Public API and common code for kernel->userspace relay file support.
  *
- * See Documentation/filesystems/relay.txt for an overview.
+ * See Documentation/filesystems/relay.rst for an overview.
  *
  * Copyright (C) 2002-2005 - Tom Zanussi (zanussi@us.ibm.com), IBM Corp
  * Copyright (C) 1999-2005 - Karim Yaghmour (karim@opersys.com)
@@ -91,7 +91,7 @@ static void relay_free_page_array(struct page **array)
  *
  *	Returns 0 if ok, negative on error
  *
- *	Caller should already have grabbed mmap_sem.
+ *	Caller should already have grabbed mmap_lock.
  */
 static int relay_mmap_buf(struct rchan_buf *buf, struct vm_area_struct *vma)
 {
@@ -197,6 +197,7 @@ free_buf:
 static void relay_destroy_channel(struct kref *kref)
 {
 	struct rchan *chan = container_of(kref, struct rchan, kref);
+	free_percpu(chan->buf);
 	kfree(chan);
 }
 
@@ -581,6 +582,11 @@ struct rchan *relay_open(const char *base_filename,
 		return NULL;
 
 	chan->buf = alloc_percpu(struct rchan_buf *);
+	if (!chan->buf) {
+		kfree(chan);
+		return NULL;
+	}
+
 	chan->version = RELAYFS_CHANNEL_VERSION;
 	chan->n_subbufs = n_subbufs;
 	chan->subbuf_size = subbuf_size;
@@ -991,14 +997,14 @@ static void relay_file_read_consume(struct rchan_buf *buf,
 /*
  *	relay_file_read_avail - boolean, are there unconsumed bytes available?
  */
-static int relay_file_read_avail(struct rchan_buf *buf, size_t read_pos)
+static int relay_file_read_avail(struct rchan_buf *buf)
 {
 	size_t subbuf_size = buf->chan->subbuf_size;
 	size_t n_subbufs = buf->chan->n_subbufs;
 	size_t produced = buf->subbufs_produced;
 	size_t consumed = buf->subbufs_consumed;
 
-	relay_file_read_consume(buf, read_pos, 0);
+	relay_file_read_consume(buf, 0, 0);
 
 	consumed = buf->subbufs_consumed;
 
@@ -1059,23 +1065,20 @@ static size_t relay_file_read_subbuf_avail(size_t read_pos,
 
 /**
  *	relay_file_read_start_pos - find the first available byte to read
- *	@read_pos: file read position
  *	@buf: relay channel buffer
  *
- *	If the @read_pos is in the middle of padding, return the
+ *	If the read_pos is in the middle of padding, return the
  *	position of the first actually available byte, otherwise
  *	return the original value.
  */
-static size_t relay_file_read_start_pos(size_t read_pos,
-					struct rchan_buf *buf)
+static size_t relay_file_read_start_pos(struct rchan_buf *buf)
 {
 	size_t read_subbuf, padding, padding_start, padding_end;
 	size_t subbuf_size = buf->chan->subbuf_size;
 	size_t n_subbufs = buf->chan->n_subbufs;
 	size_t consumed = buf->subbufs_consumed % n_subbufs;
+	size_t read_pos = consumed * subbuf_size + buf->bytes_consumed;
 
-	if (!read_pos)
-		read_pos = consumed * subbuf_size + buf->bytes_consumed;
 	read_subbuf = read_pos / subbuf_size;
 	padding = buf->padding[read_subbuf];
 	padding_start = (read_subbuf + 1) * subbuf_size - padding;
@@ -1131,10 +1134,10 @@ static ssize_t relay_file_read(struct file *filp,
 	do {
 		void *from;
 
-		if (!relay_file_read_avail(buf, *ppos))
+		if (!relay_file_read_avail(buf))
 			break;
 
-		read_start = relay_file_read_start_pos(*ppos, buf);
+		read_start = relay_file_read_start_pos(buf);
 		avail = relay_file_read_subbuf_avail(read_start, buf);
 		if (!avail)
 			break;
@@ -1177,10 +1180,9 @@ static void relay_pipe_buf_release(struct pipe_inode_info *pipe,
 }
 
 static const struct pipe_buf_operations relay_pipe_buf_ops = {
-	.confirm = generic_pipe_buf_confirm,
-	.release = relay_pipe_buf_release,
-	.steal = generic_pipe_buf_steal,
-	.get = generic_pipe_buf_get,
+	.release	= relay_pipe_buf_release,
+	.try_steal	= generic_pipe_buf_try_steal,
+	.get		= generic_pipe_buf_get,
 };
 
 static void relay_page_release(struct splice_pipe_desc *spd, unsigned int i)
diff --git a/kernel/resource.c b/kernel/resource.c
index 76036a41143b..841737bbda9e 100644
--- a/kernel/resource.c
+++ b/kernel/resource.c
@@ -1126,6 +1126,7 @@ struct resource * __request_region(struct resource *parent,
 {
 	DECLARE_WAITQUEUE(wait, current);
 	struct resource *res = alloc_resource(GFP_KERNEL);
+	struct resource *orig_parent = parent;
 
 	if (!res)
 		return NULL;
@@ -1176,6 +1177,10 @@ struct resource * __request_region(struct resource *parent,
 		break;
 	}
 	write_unlock(&resource_lock);
+
+	if (res && orig_parent == &iomem_resource)
+		revoke_devmem(res);
+
 	return res;
 }
 EXPORT_SYMBOL(__request_region);
diff --git a/kernel/sched/Makefile b/kernel/sched/Makefile
index 21fb5a5662b5..5fc9c9b70862 100644
--- a/kernel/sched/Makefile
+++ b/kernel/sched/Makefile
@@ -7,6 +7,12 @@ endif
 # that is not a function of syscall inputs. E.g. involuntary context switches.
 KCOV_INSTRUMENT := n
 
+# There are numerous data races here, however, most of them are due to plain accesses.
+# This would make it even harder for syzbot to find reproducers, because these
+# bugs trigger without specific input. Disable by default, but should re-enable
+# eventually.
+KCSAN_SANITIZE := n
+
 ifneq ($(CONFIG_SCHED_OMIT_FRAME_POINTER),y)
 # According to Alan Modra <alan@linuxcare.com.au>, the -fno-omit-frame-pointer is
 # needed for x86 only.  Why this used to be enabled for all architectures is beyond
diff --git a/kernel/sched/completion.c b/kernel/sched/completion.c
index a1ad5b7d5521..a778554f9dad 100644
--- a/kernel/sched/completion.c
+++ b/kernel/sched/completion.c
@@ -29,12 +29,12 @@ void complete(struct completion *x)
 {
 	unsigned long flags;
 
-	spin_lock_irqsave(&x->wait.lock, flags);
+	raw_spin_lock_irqsave(&x->wait.lock, flags);
 
 	if (x->done != UINT_MAX)
 		x->done++;
-	__wake_up_locked(&x->wait, TASK_NORMAL, 1);
-	spin_unlock_irqrestore(&x->wait.lock, flags);
+	swake_up_locked(&x->wait);
+	raw_spin_unlock_irqrestore(&x->wait.lock, flags);
 }
 EXPORT_SYMBOL(complete);
 
@@ -58,10 +58,12 @@ void complete_all(struct completion *x)
 {
 	unsigned long flags;
 
-	spin_lock_irqsave(&x->wait.lock, flags);
+	lockdep_assert_RT_in_threaded_ctx();
+
+	raw_spin_lock_irqsave(&x->wait.lock, flags);
 	x->done = UINT_MAX;
-	__wake_up_locked(&x->wait, TASK_NORMAL, 0);
-	spin_unlock_irqrestore(&x->wait.lock, flags);
+	swake_up_all_locked(&x->wait);
+	raw_spin_unlock_irqrestore(&x->wait.lock, flags);
 }
 EXPORT_SYMBOL(complete_all);
 
@@ -70,20 +72,20 @@ do_wait_for_common(struct completion *x,
 		   long (*action)(long), long timeout, int state)
 {
 	if (!x->done) {
-		DECLARE_WAITQUEUE(wait, current);
+		DECLARE_SWAITQUEUE(wait);
 
-		__add_wait_queue_entry_tail_exclusive(&x->wait, &wait);
 		do {
 			if (signal_pending_state(state, current)) {
 				timeout = -ERESTARTSYS;
 				break;
 			}
+			__prepare_to_swait(&x->wait, &wait);
 			__set_current_state(state);
-			spin_unlock_irq(&x->wait.lock);
+			raw_spin_unlock_irq(&x->wait.lock);
 			timeout = action(timeout);
-			spin_lock_irq(&x->wait.lock);
+			raw_spin_lock_irq(&x->wait.lock);
 		} while (!x->done && timeout);
-		__remove_wait_queue(&x->wait, &wait);
+		__finish_swait(&x->wait, &wait);
 		if (!x->done)
 			return timeout;
 	}
@@ -100,9 +102,9 @@ __wait_for_common(struct completion *x,
 
 	complete_acquire(x);
 
-	spin_lock_irq(&x->wait.lock);
+	raw_spin_lock_irq(&x->wait.lock);
 	timeout = do_wait_for_common(x, action, timeout, state);
-	spin_unlock_irq(&x->wait.lock);
+	raw_spin_unlock_irq(&x->wait.lock);
 
 	complete_release(x);
 
@@ -291,12 +293,12 @@ bool try_wait_for_completion(struct completion *x)
 	if (!READ_ONCE(x->done))
 		return false;
 
-	spin_lock_irqsave(&x->wait.lock, flags);
+	raw_spin_lock_irqsave(&x->wait.lock, flags);
 	if (!x->done)
 		ret = false;
 	else if (x->done != UINT_MAX)
 		x->done--;
-	spin_unlock_irqrestore(&x->wait.lock, flags);
+	raw_spin_unlock_irqrestore(&x->wait.lock, flags);
 	return ret;
 }
 EXPORT_SYMBOL(try_wait_for_completion);
@@ -322,8 +324,8 @@ bool completion_done(struct completion *x)
 	 * otherwise we can end up freeing the completion before complete()
 	 * is done referencing it.
 	 */
-	spin_lock_irqsave(&x->wait.lock, flags);
-	spin_unlock_irqrestore(&x->wait.lock, flags);
+	raw_spin_lock_irqsave(&x->wait.lock, flags);
+	raw_spin_unlock_irqrestore(&x->wait.lock, flags);
 	return true;
 }
 EXPORT_SYMBOL(completion_done);
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 1a9983da4408..2d95dc3f4644 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -6,11 +6,16 @@
  *
  *  Copyright (C) 1991-2002  Linus Torvalds
  */
+#define CREATE_TRACE_POINTS
+#include <trace/events/sched.h>
+#undef CREATE_TRACE_POINTS
+
 #include "sched.h"
 
 #include <linux/nospec.h>
 
 #include <linux/kcov.h>
+#include <linux/scs.h>
 
 #include <asm/switch_to.h>
 #include <asm/tlb.h>
@@ -20,9 +25,7 @@
 #include "../smpboot.h"
 
 #include "pelt.h"
-
-#define CREATE_TRACE_POINTS
-#include <trace/events/sched.h>
+#include "smp.h"
 
 /*
  * Export tracepoints that act as a bare tracehook (ie: have no trace event
@@ -34,6 +37,9 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_dl_tp);
 EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_irq_tp);
 EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_se_tp);
 EXPORT_TRACEPOINT_SYMBOL_GPL(sched_overutilized_tp);
+EXPORT_TRACEPOINT_SYMBOL_GPL(sched_util_est_cfs_tp);
+EXPORT_TRACEPOINT_SYMBOL_GPL(sched_util_est_se_tp);
+EXPORT_TRACEPOINT_SYMBOL_GPL(sched_update_nr_running_tp);
 
 DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
 
@@ -73,6 +79,100 @@ __read_mostly int scheduler_running;
  */
 int sysctl_sched_rt_runtime = 950000;
 
+
+/*
+ * Serialization rules:
+ *
+ * Lock order:
+ *
+ *   p->pi_lock
+ *     rq->lock
+ *       hrtimer_cpu_base->lock (hrtimer_start() for bandwidth controls)
+ *
+ *  rq1->lock
+ *    rq2->lock  where: rq1 < rq2
+ *
+ * Regular state:
+ *
+ * Normal scheduling state is serialized by rq->lock. __schedule() takes the
+ * local CPU's rq->lock, it optionally removes the task from the runqueue and
+ * always looks at the local rq data structures to find the most elegible task
+ * to run next.
+ *
+ * Task enqueue is also under rq->lock, possibly taken from another CPU.
+ * Wakeups from another LLC domain might use an IPI to transfer the enqueue to
+ * the local CPU to avoid bouncing the runqueue state around [ see
+ * ttwu_queue_wakelist() ]
+ *
+ * Task wakeup, specifically wakeups that involve migration, are horribly
+ * complicated to avoid having to take two rq->locks.
+ *
+ * Special state:
+ *
+ * System-calls and anything external will use task_rq_lock() which acquires
+ * both p->pi_lock and rq->lock. As a consequence the state they change is
+ * stable while holding either lock:
+ *
+ *  - sched_setaffinity()/
+ *    set_cpus_allowed_ptr():	p->cpus_ptr, p->nr_cpus_allowed
+ *  - set_user_nice():		p->se.load, p->*prio
+ *  - __sched_setscheduler():	p->sched_class, p->policy, p->*prio,
+ *				p->se.load, p->rt_priority,
+ *				p->dl.dl_{runtime, deadline, period, flags, bw, density}
+ *  - sched_setnuma():		p->numa_preferred_nid
+ *  - sched_move_task()/
+ *    cpu_cgroup_fork():	p->sched_task_group
+ *  - uclamp_update_active()	p->uclamp*
+ *
+ * p->state <- TASK_*:
+ *
+ *   is changed locklessly using set_current_state(), __set_current_state() or
+ *   set_special_state(), see their respective comments, or by
+ *   try_to_wake_up(). This latter uses p->pi_lock to serialize against
+ *   concurrent self.
+ *
+ * p->on_rq <- { 0, 1 = TASK_ON_RQ_QUEUED, 2 = TASK_ON_RQ_MIGRATING }:
+ *
+ *   is set by activate_task() and cleared by deactivate_task(), under
+ *   rq->lock. Non-zero indicates the task is runnable, the special
+ *   ON_RQ_MIGRATING state is used for migration without holding both
+ *   rq->locks. It indicates task_cpu() is not stable, see task_rq_lock().
+ *
+ * p->on_cpu <- { 0, 1 }:
+ *
+ *   is set by prepare_task() and cleared by finish_task() such that it will be
+ *   set before p is scheduled-in and cleared after p is scheduled-out, both
+ *   under rq->lock. Non-zero indicates the task is running on its CPU.
+ *
+ *   [ The astute reader will observe that it is possible for two tasks on one
+ *     CPU to have ->on_cpu = 1 at the same time. ]
+ *
+ * task_cpu(p): is changed by set_task_cpu(), the rules are:
+ *
+ *  - Don't call set_task_cpu() on a blocked task:
+ *
+ *    We don't care what CPU we're not running on, this simplifies hotplug,
+ *    the CPU assignment of blocked tasks isn't required to be valid.
+ *
+ *  - for try_to_wake_up(), called under p->pi_lock:
+ *
+ *    This allows try_to_wake_up() to only take one rq->lock, see its comment.
+ *
+ *  - for migration called under rq->lock:
+ *    [ see task_on_rq_migrating() in task_rq_lock() ]
+ *
+ *    o move_queued_task()
+ *    o detach_task()
+ *
+ *  - for migration called under double_rq_lock():
+ *
+ *    o __migrate_swap_task()
+ *    o push_rt_task() / pull_rt_task()
+ *    o push_dl_task() / pull_dl_task()
+ *    o dl_task_offline_migration()
+ *
+ */
+
 /*
  * __task_rq_lock - lock the rq @p resides on.
  */
@@ -219,6 +319,13 @@ void update_rq_clock(struct rq *rq)
 	update_rq_clock_task(rq, delta);
 }
 
+static inline void
+rq_csd_init(struct rq *rq, call_single_data_t *csd, smp_call_func_t func)
+{
+	csd->flags = 0;
+	csd->func = func;
+	csd->info = rq;
+}
 
 #ifdef CONFIG_SCHED_HRTICK
 /*
@@ -269,7 +376,6 @@ static void __hrtick_start(void *arg)
 
 	rq_lock(rq, &rf);
 	__hrtick_restart(rq);
-	rq->hrtick_csd_pending = 0;
 	rq_unlock(rq, &rf);
 }
 
@@ -293,12 +399,10 @@ void hrtick_start(struct rq *rq, u64 delay)
 
 	hrtimer_set_expires(timer, time);
 
-	if (rq == this_rq()) {
+	if (rq == this_rq())
 		__hrtick_restart(rq);
-	} else if (!rq->hrtick_csd_pending) {
+	else
 		smp_call_function_single_async(cpu_of(rq), &rq->hrtick_csd);
-		rq->hrtick_csd_pending = 1;
-	}
 }
 
 #else
@@ -317,18 +421,14 @@ void hrtick_start(struct rq *rq, u64 delay)
 	hrtimer_start(&rq->hrtick_timer, ns_to_ktime(delay),
 		      HRTIMER_MODE_REL_PINNED_HARD);
 }
+
 #endif /* CONFIG_SMP */
 
 static void hrtick_rq_init(struct rq *rq)
 {
 #ifdef CONFIG_SMP
-	rq->hrtick_csd_pending = 0;
-
-	rq->hrtick_csd.flags = 0;
-	rq->hrtick_csd.func = __hrtick_start;
-	rq->hrtick_csd.info = rq;
+	rq_csd_init(rq, &rq->hrtick_csd, __hrtick_start);
 #endif
-
 	hrtimer_init(&rq->hrtick_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD);
 	rq->hrtick_timer.function = hrtick;
 }
@@ -637,29 +737,23 @@ void wake_up_nohz_cpu(int cpu)
 		wake_up_idle_cpu(cpu);
 }
 
-static inline bool got_nohz_idle_kick(void)
+static void nohz_csd_func(void *info)
 {
-	int cpu = smp_processor_id();
-
-	if (!(atomic_read(nohz_flags(cpu)) & NOHZ_KICK_MASK))
-		return false;
-
-	if (idle_cpu(cpu) && !need_resched())
-		return true;
+	struct rq *rq = info;
+	int cpu = cpu_of(rq);
+	unsigned int flags;
 
 	/*
-	 * We can't run Idle Load Balance on this CPU for this time so we
-	 * cancel it and clear NOHZ_BALANCE_KICK
+	 * Release the rq::nohz_csd.
 	 */
-	atomic_andnot(NOHZ_KICK_MASK, nohz_flags(cpu));
-	return false;
-}
-
-#else /* CONFIG_NO_HZ_COMMON */
+	flags = atomic_fetch_andnot(NOHZ_KICK_MASK, nohz_flags(cpu));
+	WARN_ON(!(flags & NOHZ_KICK_MASK));
 
-static inline bool got_nohz_idle_kick(void)
-{
-	return false;
+	rq->idle_balance = idle_cpu(cpu);
+	if (rq->idle_balance && !need_resched()) {
+		rq->nohz_idle_balance = flags;
+		raise_softirq_irqoff(SCHED_SOFTIRQ);
+	}
 }
 
 #endif /* CONFIG_NO_HZ_COMMON */
@@ -761,7 +855,6 @@ static void set_load_weight(struct task_struct *p, bool update_load)
 	if (task_has_idle_policy(p)) {
 		load->weight = scale_load(WEIGHT_IDLEPRIO);
 		load->inv_weight = WMULT_IDLEPRIO;
-		p->se.runnable_weight = load->weight;
 		return;
 	}
 
@@ -774,7 +867,6 @@ static void set_load_weight(struct task_struct *p, bool update_load)
 	} else {
 		load->weight = scale_load(sched_prio_to_weight[prio]);
 		load->inv_weight = sched_prio_to_wmult[prio];
-		p->se.runnable_weight = load->weight;
 	}
 }
 
@@ -797,9 +889,46 @@ unsigned int sysctl_sched_uclamp_util_min = SCHED_CAPACITY_SCALE;
 /* Max allowed maximum utilization */
 unsigned int sysctl_sched_uclamp_util_max = SCHED_CAPACITY_SCALE;
 
+/*
+ * By default RT tasks run at the maximum performance point/capacity of the
+ * system. Uclamp enforces this by always setting UCLAMP_MIN of RT tasks to
+ * SCHED_CAPACITY_SCALE.
+ *
+ * This knob allows admins to change the default behavior when uclamp is being
+ * used. In battery powered devices, particularly, running at the maximum
+ * capacity and frequency will increase energy consumption and shorten the
+ * battery life.
+ *
+ * This knob only affects RT tasks that their uclamp_se->user_defined == false.
+ *
+ * This knob will not override the system default sched_util_clamp_min defined
+ * above.
+ */
+unsigned int sysctl_sched_uclamp_util_min_rt_default = SCHED_CAPACITY_SCALE;
+
 /* All clamps are required to be less or equal than these values */
 static struct uclamp_se uclamp_default[UCLAMP_CNT];
 
+/*
+ * This static key is used to reduce the uclamp overhead in the fast path. It
+ * primarily disables the call to uclamp_rq_{inc, dec}() in
+ * enqueue/dequeue_task().
+ *
+ * This allows users to continue to enable uclamp in their kernel config with
+ * minimum uclamp overhead in the fast path.
+ *
+ * As soon as userspace modifies any of the uclamp knobs, the static key is
+ * enabled, since we have an actual users that make use of uclamp
+ * functionality.
+ *
+ * The knobs that would enable this static key are:
+ *
+ *   * A task modifying its uclamp value with sched_setattr().
+ *   * An admin modifying the sysctl_sched_uclamp_{min, max} via procfs.
+ *   * An admin modifying the cgroup cpu.uclamp.{min, max}
+ */
+DEFINE_STATIC_KEY_FALSE(sched_uclamp_used);
+
 /* Integer rounded range for each bucket */
 #define UCLAMP_BUCKET_DELTA DIV_ROUND_CLOSEST(SCHED_CAPACITY_SCALE, UCLAMP_BUCKETS)
 
@@ -879,6 +1008,64 @@ unsigned int uclamp_rq_max_value(struct rq *rq, enum uclamp_id clamp_id,
 	return uclamp_idle_value(rq, clamp_id, clamp_value);
 }
 
+static void __uclamp_update_util_min_rt_default(struct task_struct *p)
+{
+	unsigned int default_util_min;
+	struct uclamp_se *uc_se;
+
+	lockdep_assert_held(&p->pi_lock);
+
+	uc_se = &p->uclamp_req[UCLAMP_MIN];
+
+	/* Only sync if user didn't override the default */
+	if (uc_se->user_defined)
+		return;
+
+	default_util_min = sysctl_sched_uclamp_util_min_rt_default;
+	uclamp_se_set(uc_se, default_util_min, false);
+}
+
+static void uclamp_update_util_min_rt_default(struct task_struct *p)
+{
+	struct rq_flags rf;
+	struct rq *rq;
+
+	if (!rt_task(p))
+		return;
+
+	/* Protect updates to p->uclamp_* */
+	rq = task_rq_lock(p, &rf);
+	__uclamp_update_util_min_rt_default(p);
+	task_rq_unlock(rq, p, &rf);
+}
+
+static void uclamp_sync_util_min_rt_default(void)
+{
+	struct task_struct *g, *p;
+
+	/*
+	 * copy_process()			sysctl_uclamp
+	 *					  uclamp_min_rt = X;
+	 *   write_lock(&tasklist_lock)		  read_lock(&tasklist_lock)
+	 *   // link thread			  smp_mb__after_spinlock()
+	 *   write_unlock(&tasklist_lock)	  read_unlock(&tasklist_lock);
+	 *   sched_post_fork()			  for_each_process_thread()
+	 *     __uclamp_sync_rt()		    __uclamp_sync_rt()
+	 *
+	 * Ensures that either sched_post_fork() will observe the new
+	 * uclamp_min_rt or for_each_process_thread() will observe the new
+	 * task.
+	 */
+	read_lock(&tasklist_lock);
+	smp_mb__after_spinlock();
+	read_unlock(&tasklist_lock);
+
+	rcu_read_lock();
+	for_each_process_thread(g, p)
+		uclamp_update_util_min_rt_default(p);
+	rcu_read_unlock();
+}
+
 static inline struct uclamp_se
 uclamp_tg_restrict(struct task_struct *p, enum uclamp_id clamp_id)
 {
@@ -996,10 +1183,38 @@ static inline void uclamp_rq_dec_id(struct rq *rq, struct task_struct *p,
 
 	lockdep_assert_held(&rq->lock);
 
+	/*
+	 * If sched_uclamp_used was enabled after task @p was enqueued,
+	 * we could end up with unbalanced call to uclamp_rq_dec_id().
+	 *
+	 * In this case the uc_se->active flag should be false since no uclamp
+	 * accounting was performed at enqueue time and we can just return
+	 * here.
+	 *
+	 * Need to be careful of the following enqeueue/dequeue ordering
+	 * problem too
+	 *
+	 *	enqueue(taskA)
+	 *	// sched_uclamp_used gets enabled
+	 *	enqueue(taskB)
+	 *	dequeue(taskA)
+	 *	// Must not decrement bukcet->tasks here
+	 *	dequeue(taskB)
+	 *
+	 * where we could end up with stale data in uc_se and
+	 * bucket[uc_se->bucket_id].
+	 *
+	 * The following check here eliminates the possibility of such race.
+	 */
+	if (unlikely(!uc_se->active))
+		return;
+
 	bucket = &uc_rq->bucket[uc_se->bucket_id];
+
 	SCHED_WARN_ON(!bucket->tasks);
 	if (likely(bucket->tasks))
 		bucket->tasks--;
+
 	uc_se->active = false;
 
 	/*
@@ -1027,6 +1242,15 @@ static inline void uclamp_rq_inc(struct rq *rq, struct task_struct *p)
 {
 	enum uclamp_id clamp_id;
 
+	/*
+	 * Avoid any overhead until uclamp is actually used by the userspace.
+	 *
+	 * The condition is constructed such that a NOP is generated when
+	 * sched_uclamp_used is disabled.
+	 */
+	if (!static_branch_unlikely(&sched_uclamp_used))
+		return;
+
 	if (unlikely(!p->sched_class->uclamp_enabled))
 		return;
 
@@ -1042,6 +1266,15 @@ static inline void uclamp_rq_dec(struct rq *rq, struct task_struct *p)
 {
 	enum uclamp_id clamp_id;
 
+	/*
+	 * Avoid any overhead until uclamp is actually used by the userspace.
+	 *
+	 * The condition is constructed such that a NOP is generated when
+	 * sched_uclamp_used is disabled.
+	 */
+	if (!static_branch_unlikely(&sched_uclamp_used))
+		return;
+
 	if (unlikely(!p->sched_class->uclamp_enabled))
 		return;
 
@@ -1117,16 +1350,16 @@ static void uclamp_update_root_tg(void) { }
 #endif
 
 int sysctl_sched_uclamp_handler(struct ctl_table *table, int write,
-				void __user *buffer, size_t *lenp,
-				loff_t *ppos)
+				void *buffer, size_t *lenp, loff_t *ppos)
 {
 	bool update_root_tg = false;
-	int old_min, old_max;
+	int old_min, old_max, old_min_rt;
 	int result;
 
 	mutex_lock(&uclamp_mutex);
 	old_min = sysctl_sched_uclamp_util_min;
 	old_max = sysctl_sched_uclamp_util_max;
+	old_min_rt = sysctl_sched_uclamp_util_min_rt_default;
 
 	result = proc_dointvec(table, write, buffer, lenp, ppos);
 	if (result)
@@ -1135,7 +1368,9 @@ int sysctl_sched_uclamp_handler(struct ctl_table *table, int write,
 		goto done;
 
 	if (sysctl_sched_uclamp_util_min > sysctl_sched_uclamp_util_max ||
-	    sysctl_sched_uclamp_util_max > SCHED_CAPACITY_SCALE) {
+	    sysctl_sched_uclamp_util_max > SCHED_CAPACITY_SCALE	||
+	    sysctl_sched_uclamp_util_min_rt_default > SCHED_CAPACITY_SCALE) {
+
 		result = -EINVAL;
 		goto undo;
 	}
@@ -1151,8 +1386,15 @@ int sysctl_sched_uclamp_handler(struct ctl_table *table, int write,
 		update_root_tg = true;
 	}
 
-	if (update_root_tg)
+	if (update_root_tg) {
+		static_branch_enable(&sched_uclamp_used);
 		uclamp_update_root_tg();
+	}
+
+	if (old_min_rt != sysctl_sched_uclamp_util_min_rt_default) {
+		static_branch_enable(&sched_uclamp_used);
+		uclamp_sync_util_min_rt_default();
+	}
 
 	/*
 	 * We update all RUNNABLE tasks only when task groups are in use.
@@ -1165,6 +1407,7 @@ int sysctl_sched_uclamp_handler(struct ctl_table *table, int write,
 undo:
 	sysctl_sched_uclamp_util_min = old_min;
 	sysctl_sched_uclamp_util_max = old_max;
+	sysctl_sched_uclamp_util_min_rt_default = old_min_rt;
 done:
 	mutex_unlock(&uclamp_mutex);
 
@@ -1187,6 +1430,15 @@ static int uclamp_validate(struct task_struct *p,
 	if (upper_bound > SCHED_CAPACITY_SCALE)
 		return -EINVAL;
 
+	/*
+	 * We have valid uclamp attributes; make sure uclamp is enabled.
+	 *
+	 * We need to do that here, because enabling static branches is a
+	 * blocking operation which obviously cannot be done while holding
+	 * scheduler locks.
+	 */
+	static_branch_enable(&sched_uclamp_used);
+
 	return 0;
 }
 
@@ -1201,17 +1453,20 @@ static void __setscheduler_uclamp(struct task_struct *p,
 	 */
 	for_each_clamp_id(clamp_id) {
 		struct uclamp_se *uc_se = &p->uclamp_req[clamp_id];
-		unsigned int clamp_value = uclamp_none(clamp_id);
 
 		/* Keep using defined clamps across class changes */
 		if (uc_se->user_defined)
 			continue;
 
-		/* By default, RT tasks always get 100% boost */
+		/*
+		 * RT by default have a 100% boost value that could be modified
+		 * at runtime.
+		 */
 		if (unlikely(rt_task(p) && clamp_id == UCLAMP_MIN))
-			clamp_value = uclamp_none(UCLAMP_MAX);
+			__uclamp_update_util_min_rt_default(p);
+		else
+			uclamp_se_set(uc_se, uclamp_none(clamp_id), false);
 
-		uclamp_se_set(uc_se, clamp_value, false);
 	}
 
 	if (likely(!(attr->sched_flags & SCHED_FLAG_UTIL_CLAMP)))
@@ -1232,6 +1487,10 @@ static void uclamp_fork(struct task_struct *p)
 {
 	enum uclamp_id clamp_id;
 
+	/*
+	 * We don't need to hold task_rq_lock() when updating p->uclamp_* here
+	 * as the task is still at its early fork stages.
+	 */
 	for_each_clamp_id(clamp_id)
 		p->uclamp[clamp_id].active = false;
 
@@ -1239,14 +1498,28 @@ static void uclamp_fork(struct task_struct *p)
 		return;
 
 	for_each_clamp_id(clamp_id) {
-		unsigned int clamp_value = uclamp_none(clamp_id);
+		uclamp_se_set(&p->uclamp_req[clamp_id],
+			      uclamp_none(clamp_id), false);
+	}
+}
 
-		/* By default, RT tasks always get 100% boost */
-		if (unlikely(rt_task(p) && clamp_id == UCLAMP_MIN))
-			clamp_value = uclamp_none(UCLAMP_MAX);
+static void uclamp_post_fork(struct task_struct *p)
+{
+	uclamp_update_util_min_rt_default(p);
+}
 
-		uclamp_se_set(&p->uclamp_req[clamp_id], clamp_value, false);
+static void __init init_uclamp_rq(struct rq *rq)
+{
+	enum uclamp_id clamp_id;
+	struct uclamp_rq *uc_rq = rq->uclamp;
+
+	for_each_clamp_id(clamp_id) {
+		uc_rq[clamp_id] = (struct uclamp_rq) {
+			.value = uclamp_none(clamp_id)
+		};
 	}
+
+	rq->uclamp_flags = 0;
 }
 
 static void __init init_uclamp(void)
@@ -1255,13 +1528,8 @@ static void __init init_uclamp(void)
 	enum uclamp_id clamp_id;
 	int cpu;
 
-	mutex_init(&uclamp_mutex);
-
-	for_each_possible_cpu(cpu) {
-		memset(&cpu_rq(cpu)->uclamp, 0,
-				sizeof(struct uclamp_rq)*UCLAMP_CNT);
-		cpu_rq(cpu)->uclamp_flags = 0;
-	}
+	for_each_possible_cpu(cpu)
+		init_uclamp_rq(cpu_rq(cpu));
 
 	for_each_clamp_id(clamp_id) {
 		uclamp_se_set(&init_task.uclamp_req[clamp_id],
@@ -1290,6 +1558,7 @@ static inline int uclamp_validate(struct task_struct *p,
 static void __setscheduler_uclamp(struct task_struct *p,
 				  const struct sched_attr *attr) { }
 static inline void uclamp_fork(struct task_struct *p) { }
+static inline void uclamp_post_fork(struct task_struct *p) { }
 static inline void init_uclamp(void) { }
 #endif /* CONFIG_UCLAMP_TASK */
 
@@ -1323,9 +1592,6 @@ static inline void dequeue_task(struct rq *rq, struct task_struct *p, int flags)
 
 void activate_task(struct rq *rq, struct task_struct *p, int flags)
 {
-	if (task_contributes_to_load(p))
-		rq->nr_uninterruptible--;
-
 	enqueue_task(rq, p, flags);
 
 	p->on_rq = TASK_ON_RQ_QUEUED;
@@ -1335,9 +1601,6 @@ void deactivate_task(struct rq *rq, struct task_struct *p, int flags)
 {
 	p->on_rq = (flags & DEQUEUE_SLEEP) ? 0 : TASK_ON_RQ_MIGRATING;
 
-	if (task_contributes_to_load(p))
-		rq->nr_uninterruptible++;
-
 	dequeue_task(rq, p, flags);
 }
 
@@ -1422,20 +1685,10 @@ static inline void check_class_changed(struct rq *rq, struct task_struct *p,
 
 void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags)
 {
-	const struct sched_class *class;
-
-	if (p->sched_class == rq->curr->sched_class) {
+	if (p->sched_class == rq->curr->sched_class)
 		rq->curr->sched_class->check_preempt_curr(rq, p, flags);
-	} else {
-		for_each_class(class) {
-			if (class == rq->curr->sched_class)
-				break;
-			if (class == p->sched_class) {
-				resched_curr(rq);
-				break;
-			}
-		}
-	}
+	else if (p->sched_class > rq->curr->sched_class)
+		resched_curr(rq);
 
 	/*
 	 * A queue event has occurred, and we're going to schedule.  In
@@ -1486,8 +1739,7 @@ static struct rq *move_queued_task(struct rq *rq, struct rq_flags *rf,
 {
 	lockdep_assert_held(&rq->lock);
 
-	WRITE_ONCE(p->on_rq, TASK_ON_RQ_MIGRATING);
-	dequeue_task(rq, p, DEQUEUE_NOCLOCK);
+	deactivate_task(rq, p, DEQUEUE_NOCLOCK);
 	set_task_cpu(p, new_cpu);
 	rq_unlock(rq, rf);
 
@@ -1495,8 +1747,7 @@ static struct rq *move_queued_task(struct rq *rq, struct rq_flags *rf,
 
 	rq_lock(rq, rf);
 	BUG_ON(task_cpu(p) != new_cpu);
-	enqueue_task(rq, p, 0);
-	p->on_rq = TASK_ON_RQ_QUEUED;
+	activate_task(rq, p, 0);
 	check_preempt_curr(rq, p, 0);
 
 	return rq;
@@ -1551,7 +1802,7 @@ static int migration_cpu_stop(void *data)
 	 * __migrate_task() such that we will not miss enforcing cpus_ptr
 	 * during wakeups, see set_cpus_allowed_ptr()'s TASK_WAKING test.
 	 */
-	sched_ttwu_pending();
+	flush_smp_call_function_from_idle();
 
 	raw_spin_lock(&p->pi_lock);
 	rq_lock(rq, &rf);
@@ -1649,10 +1900,15 @@ static int __set_cpus_allowed_ptr(struct task_struct *p,
 		goto out;
 	}
 
-	if (cpumask_equal(p->cpus_ptr, new_mask))
+	if (cpumask_equal(&p->cpus_mask, new_mask))
 		goto out;
 
-	dest_cpu = cpumask_any_and(cpu_valid_mask, new_mask);
+	/*
+	 * Picking a ~random cpu helps in cases where we are changing affinity
+	 * for groups of tasks (ie. cpuset), so that load balancing is not
+	 * immediately required to distribute the tasks within their new mask.
+	 */
+	dest_cpu = cpumask_any_and_distribute(cpu_valid_mask, new_mask);
 	if (dest_cpu >= nr_cpu_ids) {
 		ret = -EINVAL;
 		goto out;
@@ -2064,7 +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;
@@ -2121,12 +2377,6 @@ int select_task_rq(struct task_struct *p, int cpu, int sd_flags, int wake_flags)
 	return cpu;
 }
 
-static void update_avg(u64 *avg, u64 sample)
-{
-	s64 diff = sample - *avg;
-	*avg += diff >> 3;
-}
-
 void sched_set_stop_task(int cpu, struct task_struct *stop)
 {
 	struct sched_param param = { .sched_priority = MAX_RT_PRIO - 1 };
@@ -2249,10 +2499,10 @@ ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags,
 
 	lockdep_assert_held(&rq->lock);
 
-#ifdef CONFIG_SMP
 	if (p->sched_contributes_to_load)
 		rq->nr_uninterruptible--;
 
+#ifdef CONFIG_SMP
 	if (wake_flags & WF_MIGRATED)
 		en_flags |= ENQUEUE_MIGRATED;
 #endif
@@ -2262,12 +2512,31 @@ ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags,
 }
 
 /*
- * Called in case the task @p isn't fully descheduled from its runqueue,
- * in this case we must do a remote wakeup. Its a 'light' wakeup though,
- * since all we need to do is flip p->state to TASK_RUNNING, since
- * the task is still ->on_rq.
+ * Consider @p being inside a wait loop:
+ *
+ *   for (;;) {
+ *      set_current_state(TASK_UNINTERRUPTIBLE);
+ *
+ *      if (CONDITION)
+ *         break;
+ *
+ *      schedule();
+ *   }
+ *   __set_current_state(TASK_RUNNING);
+ *
+ * between set_current_state() and schedule(). In this case @p is still
+ * runnable, so all that needs doing is change p->state back to TASK_RUNNING in
+ * an atomic manner.
+ *
+ * By taking task_rq(p)->lock we serialize against schedule(), if @p->on_rq
+ * then schedule() must still happen and p->state can be changed to
+ * TASK_RUNNING. Otherwise we lost the race, schedule() has happened, and we
+ * need to do a full wakeup with enqueue.
+ *
+ * Returns: %true when the wakeup is done,
+ *          %false otherwise.
  */
-static int ttwu_remote(struct task_struct *p, int wake_flags)
+static int ttwu_runnable(struct task_struct *p, int wake_flags)
 {
 	struct rq_flags rf;
 	struct rq *rq;
@@ -2286,75 +2555,63 @@ static int ttwu_remote(struct task_struct *p, int wake_flags)
 }
 
 #ifdef CONFIG_SMP
-void sched_ttwu_pending(void)
+void sched_ttwu_pending(void *arg)
 {
+	struct llist_node *llist = arg;
 	struct rq *rq = this_rq();
-	struct llist_node *llist = llist_del_all(&rq->wake_list);
 	struct task_struct *p, *t;
 	struct rq_flags rf;
 
 	if (!llist)
 		return;
 
+	/*
+	 * rq::ttwu_pending racy indication of out-standing wakeups.
+	 * Races such that false-negatives are possible, since they
+	 * are shorter lived that false-positives would be.
+	 */
+	WRITE_ONCE(rq->ttwu_pending, 0);
+
 	rq_lock_irqsave(rq, &rf);
 	update_rq_clock(rq);
 
-	llist_for_each_entry_safe(p, t, llist, wake_entry)
+	llist_for_each_entry_safe(p, t, llist, wake_entry.llist) {
+		if (WARN_ON_ONCE(p->on_cpu))
+			smp_cond_load_acquire(&p->on_cpu, !VAL);
+
+		if (WARN_ON_ONCE(task_cpu(p) != cpu_of(rq)))
+			set_task_cpu(p, cpu_of(rq));
+
 		ttwu_do_activate(rq, p, p->sched_remote_wakeup ? WF_MIGRATED : 0, &rf);
+	}
 
 	rq_unlock_irqrestore(rq, &rf);
 }
 
-void scheduler_ipi(void)
+void send_call_function_single_ipi(int cpu)
 {
-	/*
-	 * Fold TIF_NEED_RESCHED into the preempt_count; anybody setting
-	 * TIF_NEED_RESCHED remotely (for the first time) will also send
-	 * this IPI.
-	 */
-	preempt_fold_need_resched();
-
-	if (llist_empty(&this_rq()->wake_list) && !got_nohz_idle_kick())
-		return;
-
-	/*
-	 * Not all reschedule IPI handlers call irq_enter/irq_exit, since
-	 * traditionally all their work was done from the interrupt return
-	 * path. Now that we actually do some work, we need to make sure
-	 * we do call them.
-	 *
-	 * Some archs already do call them, luckily irq_enter/exit nest
-	 * properly.
-	 *
-	 * Arguably we should visit all archs and update all handlers,
-	 * however a fair share of IPIs are still resched only so this would
-	 * somewhat pessimize the simple resched case.
-	 */
-	irq_enter();
-	sched_ttwu_pending();
+	struct rq *rq = cpu_rq(cpu);
 
-	/*
-	 * Check if someone kicked us for doing the nohz idle load balance.
-	 */
-	if (unlikely(got_nohz_idle_kick())) {
-		this_rq()->idle_balance = 1;
-		raise_softirq_irqoff(SCHED_SOFTIRQ);
-	}
-	irq_exit();
+	if (!set_nr_if_polling(rq->idle))
+		arch_send_call_function_single_ipi(cpu);
+	else
+		trace_sched_wake_idle_without_ipi(cpu);
 }
 
-static void ttwu_queue_remote(struct task_struct *p, int cpu, int wake_flags)
+/*
+ * Queue a task on the target CPUs wake_list and wake the CPU via IPI if
+ * necessary. The wakee CPU on receipt of the IPI will queue the task
+ * via sched_ttwu_wakeup() for activation so the wakee incurs the cost
+ * of the wakeup instead of the waker.
+ */
+static void __ttwu_queue_wakelist(struct task_struct *p, int cpu, int wake_flags)
 {
 	struct rq *rq = cpu_rq(cpu);
 
 	p->sched_remote_wakeup = !!(wake_flags & WF_MIGRATED);
 
-	if (llist_add(&p->wake_entry, &cpu_rq(cpu)->wake_list)) {
-		if (!set_nr_if_polling(rq->idle))
-			smp_send_reschedule(cpu);
-		else
-			trace_sched_wake_idle_without_ipi(cpu);
-	}
+	WRITE_ONCE(rq->ttwu_pending, 1);
+	__smp_call_single_queue(cpu, &p->wake_entry.llist);
 }
 
 void wake_up_if_idle(int cpu)
@@ -2385,6 +2642,49 @@ bool cpus_share_cache(int this_cpu, int that_cpu)
 {
 	return per_cpu(sd_llc_id, this_cpu) == per_cpu(sd_llc_id, that_cpu);
 }
+
+static inline bool ttwu_queue_cond(int cpu, int wake_flags)
+{
+	/*
+	 * If the CPU does not share cache, then queue the task on the
+	 * remote rqs wakelist to avoid accessing remote data.
+	 */
+	if (!cpus_share_cache(smp_processor_id(), cpu))
+		return true;
+
+	/*
+	 * If the task is descheduling and the only running task on the
+	 * CPU then use the wakelist to offload the task activation to
+	 * the soon-to-be-idle CPU as the current CPU is likely busy.
+	 * nr_running is checked to avoid unnecessary task stacking.
+	 */
+	if ((wake_flags & WF_ON_CPU) && cpu_rq(cpu)->nr_running <= 1)
+		return true;
+
+	return false;
+}
+
+static bool ttwu_queue_wakelist(struct task_struct *p, int cpu, int wake_flags)
+{
+	if (sched_feat(TTWU_QUEUE) && ttwu_queue_cond(cpu, wake_flags)) {
+		if (WARN_ON_ONCE(cpu == smp_processor_id()))
+			return false;
+
+		sched_clock_cpu(cpu); /* Sync clocks across CPUs */
+		__ttwu_queue_wakelist(p, cpu, wake_flags);
+		return true;
+	}
+
+	return false;
+}
+
+#else /* !CONFIG_SMP */
+
+static inline bool ttwu_queue_wakelist(struct task_struct *p, int cpu, int wake_flags)
+{
+	return false;
+}
+
 #endif /* CONFIG_SMP */
 
 static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags)
@@ -2392,13 +2692,8 @@ static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags)
 	struct rq *rq = cpu_rq(cpu);
 	struct rq_flags rf;
 
-#if defined(CONFIG_SMP)
-	if (sched_feat(TTWU_QUEUE) && !cpus_share_cache(smp_processor_id(), cpu)) {
-		sched_clock_cpu(cpu); /* Sync clocks across CPUs */
-		ttwu_queue_remote(p, cpu, wake_flags);
+	if (ttwu_queue_wakelist(p, cpu, wake_flags))
 		return;
-	}
-#endif
 
 	rq_lock(rq, &rf);
 	update_rq_clock(rq);
@@ -2454,8 +2749,8 @@ static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags)
  * migration. However the means are completely different as there is no lock
  * chain to provide order. Instead we do:
  *
- *   1) smp_store_release(X->on_cpu, 0)
- *   2) smp_cond_load_acquire(!X->on_cpu)
+ *   1) smp_store_release(X->on_cpu, 0)   -- finish_task()
+ *   2) smp_cond_load_acquire(!X->on_cpu) -- try_to_wake_up()
  *
  * Example:
  *
@@ -2495,15 +2790,33 @@ static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags)
  * @state: the mask of task states that can be woken
  * @wake_flags: wake modifier flags (WF_*)
  *
- * If (@state & @p->state) @p->state = TASK_RUNNING.
+ * Conceptually does:
+ *
+ *   If (@state & @p->state) @p->state = TASK_RUNNING.
  *
  * If the task was not queued/runnable, also place it back on a runqueue.
  *
- * Atomic against schedule() which would dequeue a task, also see
- * set_current_state().
+ * This function is atomic against schedule() which would dequeue the task.
+ *
+ * It issues a full memory barrier before accessing @p->state, see the comment
+ * with set_current_state().
+ *
+ * Uses p->pi_lock to serialize against concurrent wake-ups.
+ *
+ * Relies on p->pi_lock stabilizing:
+ *  - p->sched_class
+ *  - p->cpus_ptr
+ *  - p->sched_task_group
+ * in order to do migration, see its use of select_task_rq()/set_task_cpu().
+ *
+ * Tries really hard to only take one task_rq(p)->lock for performance.
+ * Takes rq->lock in:
+ *  - ttwu_runnable()    -- old rq, unavoidable, see comment there;
+ *  - ttwu_queue()       -- new rq, for enqueue of the task;
+ *  - psi_ttwu_dequeue() -- much sadness :-( accounting will kill us.
  *
- * This function executes a full memory barrier before accessing the task
- * state; see set_current_state().
+ * As a consequence we race really badly with just about everything. See the
+ * many memory barriers and their comments for details.
  *
  * Return: %true if @p->state changes (an actual wakeup was done),
  *	   %false otherwise.
@@ -2519,7 +2832,7 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 		/*
 		 * We're waking current, this means 'p->on_rq' and 'task_cpu(p)
 		 * == smp_processor_id()'. Together this means we can special
-		 * case the whole 'p->on_rq && ttwu_remote()' case below
+		 * case the whole 'p->on_rq && ttwu_runnable()' case below
 		 * without taking any locks.
 		 *
 		 * In particular:
@@ -2531,7 +2844,6 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 			goto out;
 
 		success = 1;
-		cpu = task_cpu(p);
 		trace_sched_waking(p);
 		p->state = TASK_RUNNING;
 		trace_sched_wakeup(p);
@@ -2541,8 +2853,8 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 	/*
 	 * If we are going to wake up a thread waiting for CONDITION we
 	 * need to ensure that CONDITION=1 done by the caller can not be
-	 * reordered with p->state check below. This pairs with mb() in
-	 * set_current_state() the waiting thread does.
+	 * reordered with p->state check below. This pairs with smp_store_mb()
+	 * in set_current_state() that the waiting thread does.
 	 */
 	raw_spin_lock_irqsave(&p->pi_lock, flags);
 	smp_mb__after_spinlock();
@@ -2553,7 +2865,6 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 
 	/* We're going to change ->state: */
 	success = 1;
-	cpu = task_cpu(p);
 
 	/*
 	 * Ensure we load p->on_rq _after_ p->state, otherwise it would
@@ -2574,11 +2885,18 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 	 *
 	 * Pairs with the LOCK+smp_mb__after_spinlock() on rq->lock in
 	 * __schedule().  See the comment for smp_mb__after_spinlock().
+	 *
+	 * A similar smb_rmb() lives in try_invoke_on_locked_down_task().
 	 */
 	smp_rmb();
-	if (p->on_rq && ttwu_remote(p, wake_flags))
+	if (READ_ONCE(p->on_rq) && ttwu_runnable(p, wake_flags))
 		goto unlock;
 
+	if (p->in_iowait) {
+		delayacct_blkio_end(p);
+		atomic_dec(&task_rq(p)->nr_iowait);
+	}
+
 #ifdef CONFIG_SMP
 	/*
 	 * Ensure we load p->on_cpu _after_ p->on_rq, otherwise it would be
@@ -2598,8 +2916,43 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 	 *
 	 * Pairs with the LOCK+smp_mb__after_spinlock() on rq->lock in
 	 * __schedule().  See the comment for smp_mb__after_spinlock().
+	 *
+	 * Form a control-dep-acquire with p->on_rq == 0 above, to ensure
+	 * schedule()'s deactivate_task() has 'happened' and p will no longer
+	 * care about it's own p->state. See the comment in __schedule().
 	 */
-	smp_rmb();
+	smp_acquire__after_ctrl_dep();
+
+	/*
+	 * We're doing the wakeup (@success == 1), they did a dequeue (p->on_rq
+	 * == 0), which means we need to do an enqueue, change p->state to
+	 * TASK_WAKING such that we can unlock p->pi_lock before doing the
+	 * enqueue, such as ttwu_queue_wakelist().
+	 */
+	p->state = TASK_WAKING;
+
+	/*
+	 * If the owning (remote) CPU is still in the middle of schedule() with
+	 * this task as prev, considering queueing p on the remote CPUs wake_list
+	 * which potentially sends an IPI instead of spinning on p->on_cpu to
+	 * let the waker make forward progress. This is safe because IRQs are
+	 * disabled and the IPI will deliver after on_cpu is cleared.
+	 *
+	 * Ensure we load task_cpu(p) after p->on_cpu:
+	 *
+	 * set_task_cpu(p, cpu);
+	 *   STORE p->cpu = @cpu
+	 * __schedule() (switch to task 'p')
+	 *   LOCK rq->lock
+	 *   smp_mb__after_spin_lock()		smp_cond_load_acquire(&p->on_cpu)
+	 *   STORE p->on_cpu = 1		LOAD p->cpu
+	 *
+	 * to ensure we observe the correct CPU on which the task is currently
+	 * scheduling.
+	 */
+	if (smp_load_acquire(&p->on_cpu) &&
+	    ttwu_queue_wakelist(p, task_cpu(p), wake_flags | WF_ON_CPU))
+		goto unlock;
 
 	/*
 	 * If the owning (remote) CPU is still in the middle of schedule() with
@@ -2612,28 +2965,14 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 	 */
 	smp_cond_load_acquire(&p->on_cpu, !VAL);
 
-	p->sched_contributes_to_load = !!task_contributes_to_load(p);
-	p->state = TASK_WAKING;
-
-	if (p->in_iowait) {
-		delayacct_blkio_end(p);
-		atomic_dec(&task_rq(p)->nr_iowait);
-	}
-
 	cpu = select_task_rq(p, p->wake_cpu, SD_BALANCE_WAKE, wake_flags);
 	if (task_cpu(p) != cpu) {
 		wake_flags |= WF_MIGRATED;
 		psi_ttwu_dequeue(p);
 		set_task_cpu(p, cpu);
 	}
-
-#else /* CONFIG_SMP */
-
-	if (p->in_iowait) {
-		delayacct_blkio_end(p);
-		atomic_dec(&task_rq(p)->nr_iowait);
-	}
-
+#else
+	cpu = task_cpu(p);
 #endif /* CONFIG_SMP */
 
 	ttwu_queue(p, cpu, wake_flags);
@@ -2641,13 +2980,59 @@ unlock:
 	raw_spin_unlock_irqrestore(&p->pi_lock, flags);
 out:
 	if (success)
-		ttwu_stat(p, cpu, wake_flags);
+		ttwu_stat(p, task_cpu(p), wake_flags);
 	preempt_enable();
 
 	return success;
 }
 
 /**
+ * try_invoke_on_locked_down_task - Invoke a function on task in fixed state
+ * @p: Process for which the function is to be invoked.
+ * @func: Function to invoke.
+ * @arg: Argument to function.
+ *
+ * If the specified task can be quickly locked into a definite state
+ * (either sleeping or on a given runqueue), arrange to keep it in that
+ * state while invoking @func(@arg).  This function can use ->on_rq and
+ * task_curr() to work out what the state is, if required.  Given that
+ * @func can be invoked with a runqueue lock held, it had better be quite
+ * lightweight.
+ *
+ * Returns:
+ *	@false if the task slipped out from under the locks.
+ *	@true if the task was locked onto a runqueue or is sleeping.
+ *		However, @func can override this by returning @false.
+ */
+bool try_invoke_on_locked_down_task(struct task_struct *p, bool (*func)(struct task_struct *t, void *arg), void *arg)
+{
+	bool ret = false;
+	struct rq_flags rf;
+	struct rq *rq;
+
+	lockdep_assert_irqs_enabled();
+	raw_spin_lock_irq(&p->pi_lock);
+	if (p->on_rq) {
+		rq = __task_rq_lock(p, &rf);
+		if (task_rq(p) == rq)
+			ret = func(p, arg);
+		rq_unlock(rq, &rf);
+	} else {
+		switch (p->state) {
+		case TASK_RUNNING:
+		case TASK_WAKING:
+			break;
+		default:
+			smp_rmb(); // See smp_rmb() comment in try_to_wake_up().
+			if (!p->on_rq)
+				ret = func(p, arg);
+		}
+	}
+	raw_spin_unlock_irq(&p->pi_lock);
+	return ret;
+}
+
+/**
  * wake_up_process - Wake up a specific process
  * @p: The process to be woken up.
  *
@@ -2715,6 +3100,9 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p)
 	p->capture_control = NULL;
 #endif
 	init_numa_balancing(clone_flags, p);
+#ifdef CONFIG_SMP
+	p->wake_entry.u_flags = CSD_TYPE_TTWU;
+#endif
 }
 
 DEFINE_STATIC_KEY_FALSE(sched_numa_balancing);
@@ -2731,7 +3119,7 @@ void set_numabalancing_state(bool enabled)
 
 #ifdef CONFIG_PROC_SYSCTL
 int sysctl_numa_balancing(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 err;
@@ -2805,8 +3193,8 @@ static void __init init_schedstats(void)
 }
 
 #ifdef CONFIG_PROC_SYSCTL
-int sysctl_schedstats(struct ctl_table *table, int write,
-			 void __user *buffer, size_t *lenp, loff_t *ppos)
+int sysctl_schedstats(struct ctl_table *table, int write, void *buffer,
+		size_t *lenp, loff_t *ppos)
 {
 	struct ctl_table t;
 	int err;
@@ -2889,6 +3277,7 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p)
 	 * Silence PROVE_RCU.
 	 */
 	raw_spin_lock_irqsave(&p->pi_lock, flags);
+	rseq_migrate(p);
 	/*
 	 * We're setting the CPU for the first time, we don't migrate,
 	 * so use __set_task_cpu().
@@ -2913,6 +3302,11 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p)
 	return 0;
 }
 
+void sched_post_fork(struct task_struct *p)
+{
+	uclamp_post_fork(p);
+}
+
 unsigned long to_ratio(u64 period, u64 runtime)
 {
 	if (runtime == RUNTIME_INF)
@@ -2953,6 +3347,7 @@ void wake_up_new_task(struct task_struct *p)
 	 * as we're not fully set-up yet.
 	 */
 	p->recent_used_cpu = task_cpu(p);
+	rseq_migrate(p);
 	__set_task_cpu(p, select_task_rq(p, task_cpu(p), SD_BALANCE_FORK, 0));
 #endif
 	rq = __task_rq_lock(p, &rf);
@@ -3069,8 +3464,10 @@ static inline void prepare_task(struct task_struct *next)
 	/*
 	 * Claim the task as running, we do this before switching to it
 	 * such that any running task will have this set.
+	 *
+	 * See the ttwu() WF_ON_CPU case and its ordering comment.
 	 */
-	next->on_cpu = 1;
+	WRITE_ONCE(next->on_cpu, 1);
 #endif
 }
 
@@ -3078,8 +3475,9 @@ static inline void finish_task(struct task_struct *prev)
 {
 #ifdef CONFIG_SMP
 	/*
-	 * After ->on_cpu is cleared, the task can be moved to a different CPU.
-	 * We must ensure this doesn't happen until the switch is completely
+	 * This must be the very last reference to @prev from this CPU. After
+	 * p->on_cpu is cleared, the task can be moved to a different CPU. We
+	 * must ensure this doesn't happen until the switch is completely
 	 * finished.
 	 *
 	 * In particular, the load of prev->state in finish_task_switch() must
@@ -3588,12 +3986,16 @@ void scheduler_tick(void)
 	struct rq *rq = cpu_rq(cpu);
 	struct task_struct *curr = rq->curr;
 	struct rq_flags rf;
+	unsigned long thermal_pressure;
 
+	arch_scale_freq_tick();
 	sched_clock_tick();
 
 	rq_lock(rq, &rf);
 
 	update_rq_clock(rq);
+	thermal_pressure = arch_scale_thermal_pressure(cpu_of(rq));
+	update_thermal_load_avg(rq_clock_thermal(rq), rq, thermal_pressure);
 	curr->sched_class->task_tick(rq, curr, 0);
 	calc_global_load_tick(rq);
 	psi_task_tick(rq);
@@ -3671,7 +4073,6 @@ static void sched_tick_remote(struct work_struct *work)
 	if (cpu_is_offline(cpu))
 		goto out_unlock;
 
-	curr = rq->curr;
 	update_rq_clock(rq);
 
 	if (!is_idle_task(curr)) {
@@ -3858,8 +4259,7 @@ static noinline void __schedule_bug(struct task_struct *prev)
 	if (IS_ENABLED(CONFIG_DEBUG_PREEMPT)
 	    && in_atomic_preempt_off()) {
 		pr_err("Preemption disabled at:");
-		print_ip_sym(preempt_disable_ip);
-		pr_cont("\n");
+		print_ip_sym(KERN_ERR, preempt_disable_ip);
 	}
 	if (panic_on_warn)
 		panic("scheduling while atomic\n");
@@ -3876,6 +4276,9 @@ static inline void schedule_debug(struct task_struct *prev, bool preempt)
 #ifdef CONFIG_SCHED_STACK_END_CHECK
 	if (task_stack_end_corrupted(prev))
 		panic("corrupted stack end detected inside scheduler\n");
+
+	if (task_scs_end_corrupted(prev))
+		panic("corrupted shadow stack detected inside scheduler\n");
 #endif
 
 #ifdef CONFIG_DEBUG_ATOMIC_SLEEP
@@ -3898,6 +4301,28 @@ static inline void schedule_debug(struct task_struct *prev, bool preempt)
 	schedstat_inc(this_rq()->sched_count);
 }
 
+static void put_prev_task_balance(struct rq *rq, struct task_struct *prev,
+				  struct rq_flags *rf)
+{
+#ifdef CONFIG_SMP
+	const struct sched_class *class;
+	/*
+	 * We must do the balancing pass before put_prev_task(), such
+	 * that when we release the rq->lock the task is in the same
+	 * state as before we took rq->lock.
+	 *
+	 * We can terminate the balance pass as soon as we know there is
+	 * a runnable task of @class priority or higher.
+	 */
+	for_class_range(class, prev->sched_class, &idle_sched_class) {
+		if (class->balance(rq, prev, rf))
+			break;
+	}
+#endif
+
+	put_prev_task(rq, prev);
+}
+
 /*
  * Pick up the highest-prio task:
  */
@@ -3913,8 +4338,7 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 	 * higher scheduling class, because otherwise those loose the
 	 * opportunity to pull in more work from other CPUs.
 	 */
-	if (likely((prev->sched_class == &idle_sched_class ||
-		    prev->sched_class == &fair_sched_class) &&
+	if (likely(prev->sched_class <= &fair_sched_class &&
 		   rq->nr_running == rq->cfs.h_nr_running)) {
 
 		p = pick_next_task_fair(rq, prev, rf);
@@ -3931,22 +4355,7 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 	}
 
 restart:
-#ifdef CONFIG_SMP
-	/*
-	 * We must do the balancing pass before put_next_task(), such
-	 * that when we release the rq->lock the task is in the same
-	 * state as before we took rq->lock.
-	 *
-	 * We can terminate the balance pass as soon as we know there is
-	 * a runnable task of @class priority or higher.
-	 */
-	for_class_range(class, prev->sched_class, &idle_sched_class) {
-		if (class->balance(rq, prev, rf))
-			break;
-	}
-#endif
-
-	put_prev_task(rq, prev);
+	put_prev_task_balance(rq, prev, rf);
 
 	for_each_class(class) {
 		p = class->pick_next_task(rq);
@@ -4001,6 +4410,7 @@ static void __sched notrace __schedule(bool preempt)
 {
 	struct task_struct *prev, *next;
 	unsigned long *switch_count;
+	unsigned long prev_state;
 	struct rq_flags rf;
 	struct rq *rq;
 	int cpu;
@@ -4020,9 +4430,16 @@ static void __sched notrace __schedule(bool preempt)
 	/*
 	 * Make sure that signal_pending_state()->signal_pending() below
 	 * can't be reordered with __set_current_state(TASK_INTERRUPTIBLE)
-	 * done by the caller to avoid the race with signal_wake_up().
+	 * done by the caller to avoid the race with signal_wake_up():
 	 *
-	 * The membarrier system call requires a full memory barrier
+	 * __set_current_state(@state)		signal_wake_up()
+	 * schedule()				  set_tsk_thread_flag(p, TIF_SIGPENDING)
+	 *					  wake_up_state(p, state)
+	 *   LOCK rq->lock			    LOCK p->pi_state
+	 *   smp_mb__after_spinlock()		    smp_mb__after_spinlock()
+	 *     if (signal_pending_state())	    if (p->state & @state)
+	 *
+	 * Also, the membarrier system call requires a full memory barrier
 	 * after coming from user-space, before storing to rq->curr.
 	 */
 	rq_lock(rq, &rf);
@@ -4033,10 +4450,38 @@ static void __sched notrace __schedule(bool preempt)
 	update_rq_clock(rq);
 
 	switch_count = &prev->nivcsw;
-	if (!preempt && prev->state) {
-		if (signal_pending_state(prev->state, prev)) {
+
+	/*
+	 * We must load prev->state once (task_struct::state is volatile), such
+	 * that:
+	 *
+	 *  - we form a control dependency vs deactivate_task() below.
+	 *  - ptrace_{,un}freeze_traced() can change ->state underneath us.
+	 */
+	prev_state = prev->state;
+	if (!preempt && prev_state) {
+		if (signal_pending_state(prev_state, prev)) {
 			prev->state = TASK_RUNNING;
 		} else {
+			prev->sched_contributes_to_load =
+				(prev_state & TASK_UNINTERRUPTIBLE) &&
+				!(prev_state & TASK_NOLOAD) &&
+				!(prev->flags & PF_FROZEN);
+
+			if (prev->sched_contributes_to_load)
+				rq->nr_uninterruptible++;
+
+			/*
+			 * __schedule()			ttwu()
+			 *   prev_state = prev->state;    if (p->on_rq && ...)
+			 *   if (prev_state)		    goto out;
+			 *     p->on_rq = 0;		  smp_acquire__after_ctrl_dep();
+			 *				  p->state = TASK_WAKING
+			 *
+			 * Where __schedule() and ttwu() have matching control dependencies.
+			 *
+			 * After this, schedule() must not care about p->state any more.
+			 */
 			deactivate_task(rq, prev, DEQUEUE_SLEEP | DEQUEUE_NOCLOCK);
 
 			if (prev->in_iowait) {
@@ -4074,6 +4519,8 @@ static void __sched notrace __schedule(bool preempt)
 		 */
 		++*switch_count;
 
+		psi_sched_switch(prev, next, !task_on_rq_queued(prev));
+
 		trace_sched_switch(preempt, prev, next);
 
 		/* Also unlocks the rq: */
@@ -4112,7 +4559,8 @@ static inline void sched_submit_work(struct task_struct *tsk)
 	 * it wants to wake up a task to maintain concurrency.
 	 * As this function is called inside the schedule() context,
 	 * we disable preemption to avoid it calling schedule() again
-	 * in the possible wakeup of a kworker.
+	 * in the possible wakeup of a kworker and because wq_worker_sleeping()
+	 * requires it.
 	 */
 	if (tsk->flags & (PF_WQ_WORKER | PF_IO_WORKER)) {
 		preempt_disable();
@@ -4345,6 +4793,7 @@ asmlinkage __visible void __sched preempt_schedule_irq(void)
 int default_wake_function(wait_queue_entry_t *curr, unsigned mode, int wake_flags,
 			  void *key)
 {
+	WARN_ON_ONCE(IS_ENABLED(CONFIG_SCHED_DEBUG) && wake_flags & ~WF_SYNC);
 	return try_to_wake_up(curr->private, mode, wake_flags);
 }
 EXPORT_SYMBOL(default_wake_function);
@@ -4457,7 +4906,8 @@ void rt_mutex_setprio(struct task_struct *p, struct task_struct *pi_task)
 	 */
 	if (dl_prio(prio)) {
 		if (!dl_prio(p->normal_prio) ||
-		    (pi_task && dl_entity_preempt(&pi_task->dl, &p->dl))) {
+		    (pi_task && dl_prio(pi_task->prio) &&
+		     dl_entity_preempt(&pi_task->dl, &p->dl))) {
 			p->dl.dl_boosted = 1;
 			queue_flag |= ENQUEUE_REPLENISH;
 		} else
@@ -4633,7 +5083,7 @@ int idle_cpu(int cpu)
 		return 0;
 
 #ifdef CONFIG_SMP
-	if (!llist_empty(&rq->wake_list))
+	if (rq->ttwu_pending)
 		return 0;
 #endif
 
@@ -5046,6 +5496,8 @@ static int _sched_setscheduler(struct task_struct *p, int policy,
  * @policy: new policy.
  * @param: structure containing the new RT priority.
  *
+ * Use sched_set_fifo(), read its comment.
+ *
  * Return: 0 on success. An error code otherwise.
  *
  * NOTE that the task may be already dead.
@@ -5055,13 +5507,11 @@ int sched_setscheduler(struct task_struct *p, int policy,
 {
 	return _sched_setscheduler(p, policy, param, true);
 }
-EXPORT_SYMBOL_GPL(sched_setscheduler);
 
 int sched_setattr(struct task_struct *p, const struct sched_attr *attr)
 {
 	return __sched_setscheduler(p, attr, true, true);
 }
-EXPORT_SYMBOL_GPL(sched_setattr);
 
 int sched_setattr_nocheck(struct task_struct *p, const struct sched_attr *attr)
 {
@@ -5086,7 +5536,51 @@ int sched_setscheduler_nocheck(struct task_struct *p, int policy,
 {
 	return _sched_setscheduler(p, policy, param, false);
 }
-EXPORT_SYMBOL_GPL(sched_setscheduler_nocheck);
+
+/*
+ * SCHED_FIFO is a broken scheduler model; that is, it is fundamentally
+ * incapable of resource management, which is the one thing an OS really should
+ * be doing.
+ *
+ * This is of course the reason it is limited to privileged users only.
+ *
+ * Worse still; it is fundamentally impossible to compose static priority
+ * workloads. You cannot take two correctly working static prio workloads
+ * and smash them together and still expect them to work.
+ *
+ * For this reason 'all' FIFO tasks the kernel creates are basically at:
+ *
+ *   MAX_RT_PRIO / 2
+ *
+ * The administrator _MUST_ configure the system, the kernel simply doesn't
+ * know enough information to make a sensible choice.
+ */
+void sched_set_fifo(struct task_struct *p)
+{
+	struct sched_param sp = { .sched_priority = MAX_RT_PRIO / 2 };
+	WARN_ON_ONCE(sched_setscheduler_nocheck(p, SCHED_FIFO, &sp) != 0);
+}
+EXPORT_SYMBOL_GPL(sched_set_fifo);
+
+/*
+ * For when you don't much care about FIFO, but want to be above SCHED_NORMAL.
+ */
+void sched_set_fifo_low(struct task_struct *p)
+{
+	struct sched_param sp = { .sched_priority = 1 };
+	WARN_ON_ONCE(sched_setscheduler_nocheck(p, SCHED_FIFO, &sp) != 0);
+}
+EXPORT_SYMBOL_GPL(sched_set_fifo_low);
+
+void sched_set_normal(struct task_struct *p, int nice)
+{
+	struct sched_attr attr = {
+		.sched_policy = SCHED_NORMAL,
+		.sched_nice = nice,
+	};
+	WARN_ON_ONCE(sched_setattr_nocheck(p, &attr) != 0);
+}
+EXPORT_SYMBOL_GPL(sched_set_normal);
 
 static int
 do_sched_setscheduler(pid_t pid, int policy, struct sched_param __user *param)
@@ -5377,6 +5871,11 @@ SYSCALL_DEFINE4(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr,
 		kattr.sched_nice = task_nice(p);
 
 #ifdef CONFIG_UCLAMP_TASK
+	/*
+	 * This could race with another potential updater, but this is fine
+	 * because it'll correctly read the old or the new value. We don't need
+	 * to guarantee who wins the race as long as it doesn't return garbage.
+	 */
 	kattr.sched_util_min = p->uclamp_req[UCLAMP_MIN].value;
 	kattr.sched_util_max = p->uclamp_req[UCLAMP_MAX].value;
 #endif
@@ -5734,7 +6233,7 @@ again:
 	if (task_running(p_rq, p) || p->state)
 		goto out_unlock;
 
-	yielded = curr->sched_class->yield_to_task(rq, p, preempt);
+	yielded = curr->sched_class->yield_to_task(rq, p);
 	if (yielded) {
 		schedstat_inc(rq->yld_count);
 		/*
@@ -5932,10 +6431,10 @@ void sched_show_task(struct task_struct *p)
 	if (!try_get_task_stack(p))
 		return;
 
-	printk(KERN_INFO "%-15.15s %c", p->comm, task_state_to_char(p));
+	pr_info("task:%-15.15s state:%c", p->comm, task_state_to_char(p));
 
 	if (p->state == TASK_RUNNING)
-		printk(KERN_CONT "  running task    ");
+		pr_cont("  running task    ");
 #ifdef CONFIG_DEBUG_STACK_USAGE
 	free = stack_not_used(p);
 #endif
@@ -5944,12 +6443,12 @@ void sched_show_task(struct task_struct *p)
 	if (pid_alive(p))
 		ppid = task_pid_nr(rcu_dereference(p->real_parent));
 	rcu_read_unlock();
-	printk(KERN_CONT "%5lu %5d %6d 0x%08lx\n", free,
-		task_pid_nr(p), ppid,
+	pr_cont(" stack:%5lu pid:%5d ppid:%6d flags:0x%08lx\n",
+		free, task_pid_nr(p), ppid,
 		(unsigned long)task_thread_info(p)->flags);
 
 	print_worker_info(KERN_INFO, p);
-	show_stack(p, NULL);
+	show_stack(p, NULL, KERN_INFO);
 	put_task_stack(p);
 }
 EXPORT_SYMBOL_GPL(sched_show_task);
@@ -5980,13 +6479,6 @@ void show_state_filter(unsigned long state_filter)
 {
 	struct task_struct *g, *p;
 
-#if BITS_PER_LONG == 32
-	printk(KERN_INFO
-		"  task                PC stack   pid father\n");
-#else
-	printk(KERN_INFO
-		"  task                        PC stack   pid father\n");
-#endif
 	rcu_read_lock();
 	for_each_process_thread(g, p) {
 		/*
@@ -6036,6 +6528,7 @@ void init_idle(struct task_struct *idle, int cpu)
 	idle->se.exec_start = sched_clock();
 	idle->flags |= PF_IDLE;
 
+	scs_task_reset(idle);
 	kasan_unpoison_task_stack(idle);
 
 #ifdef CONFIG_SMP
@@ -6186,13 +6679,14 @@ void idle_task_exit(void)
 	struct mm_struct *mm = current->active_mm;
 
 	BUG_ON(cpu_online(smp_processor_id()));
+	BUG_ON(current != this_rq()->idle);
 
 	if (mm != &init_mm) {
 		switch_mm(mm, &init_mm, current);
-		current->active_mm = &init_mm;
 		finish_arch_post_lock_switch();
 	}
-	mmdrop(mm);
+
+	/* finish_cpu(), as ran on the BP, will clean up the active_mm state */
 }
 
 /*
@@ -6482,7 +6976,6 @@ int sched_cpu_dying(unsigned int cpu)
 	struct rq_flags rf;
 
 	/* Handle pending wakeups and then migrate everything off */
-	sched_ttwu_pending();
 	sched_tick_stop(cpu);
 
 	rq_lock_irqsave(rq, &rf);
@@ -6567,6 +7060,14 @@ void __init sched_init(void)
 	unsigned long ptr = 0;
 	int i;
 
+	/* Make sure the linker didn't screw up */
+	BUG_ON(&idle_sched_class + 1 != &fair_sched_class ||
+	       &fair_sched_class + 1 != &rt_sched_class ||
+	       &rt_sched_class + 1   != &dl_sched_class);
+#ifdef CONFIG_SMP
+	BUG_ON(&dl_sched_class + 1 != &stop_sched_class);
+#endif
+
 	wait_bit_init();
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
@@ -6585,6 +7086,8 @@ void __init sched_init(void)
 		root_task_group.cfs_rq = (struct cfs_rq **)ptr;
 		ptr += nr_cpu_ids * sizeof(void **);
 
+		root_task_group.shares = ROOT_TASK_GROUP_LOAD;
+		init_cfs_bandwidth(&root_task_group.cfs_bandwidth);
 #endif /* CONFIG_FAIR_GROUP_SCHED */
 #ifdef CONFIG_RT_GROUP_SCHED
 		root_task_group.rt_se = (struct sched_rt_entity **)ptr;
@@ -6637,7 +7140,6 @@ void __init sched_init(void)
 		init_rt_rq(&rq->rt);
 		init_dl_rq(&rq->dl);
 #ifdef CONFIG_FAIR_GROUP_SCHED
-		root_task_group.shares = ROOT_TASK_GROUP_LOAD;
 		INIT_LIST_HEAD(&rq->leaf_cfs_rq_list);
 		rq->tmp_alone_branch = &rq->leaf_cfs_rq_list;
 		/*
@@ -6659,7 +7161,6 @@ void __init sched_init(void)
 		 * We achieve this by letting root_task_group's tasks sit
 		 * directly in rq->cfs (i.e root_task_group->se[] = NULL).
 		 */
-		init_cfs_bandwidth(&root_task_group.cfs_bandwidth);
 		init_tg_cfs_entry(&root_task_group, &rq->cfs, NULL, i, NULL);
 #endif /* CONFIG_FAIR_GROUP_SCHED */
 
@@ -6685,9 +7186,10 @@ void __init sched_init(void)
 
 		rq_attach_root(rq, &def_root_domain);
 #ifdef CONFIG_NO_HZ_COMMON
-		rq->last_load_update_tick = jiffies;
 		rq->last_blocked_load_update_tick = jiffies;
 		atomic_set(&rq->nohz_flags, 0);
+
+		rq_csd_init(rq, &rq->nohz_csd, nohz_csd_func);
 #endif
 #endif /* CONFIG_SMP */
 		hrtick_rq_init(rq);
@@ -6792,8 +7294,7 @@ void ___might_sleep(const char *file, int line, int preempt_offset)
 	if (IS_ENABLED(CONFIG_DEBUG_PREEMPT)
 	    && !preempt_count_equals(preempt_offset)) {
 		pr_err("Preemption disabled at:");
-		print_ip_sym(preempt_disable_ip);
-		pr_cont("\n");
+		print_ip_sym(KERN_ERR, preempt_disable_ip);
 	}
 	dump_stack();
 	add_taint(TAINT_WARN, LOCKDEP_STILL_OK);
@@ -7288,6 +7789,8 @@ static ssize_t cpu_uclamp_write(struct kernfs_open_file *of, char *buf,
 	if (req.ret)
 		return req.ret;
 
+	static_branch_enable(&sched_uclamp_used);
+
 	mutex_lock(&uclamp_mutex);
 	rcu_read_lock();
 
@@ -7382,6 +7885,8 @@ static DEFINE_MUTEX(cfs_constraints_mutex);
 
 const u64 max_cfs_quota_period = 1 * NSEC_PER_SEC; /* 1s */
 static const u64 min_cfs_quota_period = 1 * NSEC_PER_MSEC; /* 1ms */
+/* More than 203 days if BW_SHIFT equals 20. */
+static const u64 max_cfs_runtime = MAX_BW * NSEC_PER_USEC;
 
 static int __cfs_schedulable(struct task_group *tg, u64 period, u64 runtime);
 
@@ -7410,6 +7915,12 @@ static int tg_set_cfs_bandwidth(struct task_group *tg, u64 period, u64 quota)
 		return -EINVAL;
 
 	/*
+	 * Bound quota to defend quota against overflow during bandwidth shift.
+	 */
+	if (quota != RUNTIME_INF && quota > max_cfs_runtime)
+		return -EINVAL;
+
+	/*
 	 * Prevent race between setting of cfs_rq->runtime_enabled and
 	 * unthrottle_offline_cfs_rqs().
 	 */
@@ -7967,4 +8478,7 @@ const u32 sched_prio_to_wmult[40] = {
  /*  15 */ 119304647, 148102320, 186737708, 238609294, 286331153,
 };
 
-#undef CREATE_TRACE_POINTS
+void call_trace_sched_update_nr_running(struct rq *rq, int count)
+{
+        trace_sched_update_nr_running_tp(rq, count);
+}
diff --git a/kernel/sched/cpuacct.c b/kernel/sched/cpuacct.c
index 9fbb10383434..941c28cf9738 100644
--- a/kernel/sched/cpuacct.c
+++ b/kernel/sched/cpuacct.c
@@ -5,6 +5,7 @@
  * Based on the work by Paul Menage (menage@google.com) and Balbir Singh
  * (balbir@in.ibm.com).
  */
+#include <asm/irq_regs.h>
 #include "sched.h"
 
 /* Time spent by the tasks of the CPU accounting group executing in ... */
@@ -339,7 +340,7 @@ void cpuacct_charge(struct task_struct *tsk, u64 cputime)
 {
 	struct cpuacct *ca;
 	int index = CPUACCT_STAT_SYSTEM;
-	struct pt_regs *regs = task_pt_regs(tsk);
+	struct pt_regs *regs = get_irq_regs() ? : task_pt_regs(tsk);
 
 	if (regs && user_mode(regs))
 		index = CPUACCT_STAT_USER;
@@ -347,7 +348,7 @@ void cpuacct_charge(struct task_struct *tsk, u64 cputime)
 	rcu_read_lock();
 
 	for (ca = task_ca(tsk); ca; ca = parent_ca(ca))
-		this_cpu_ptr(ca->cpuusage)->usages[index] += cputime;
+		__this_cpu_add(ca->cpuusage->usages[index], cputime);
 
 	rcu_read_unlock();
 }
@@ -363,7 +364,7 @@ void cpuacct_account_field(struct task_struct *tsk, int index, u64 val)
 
 	rcu_read_lock();
 	for (ca = task_ca(tsk); ca != &root_cpuacct; ca = parent_ca(ca))
-		this_cpu_ptr(ca->cpustat)->cpustat[index] += val;
+		__this_cpu_add(ca->cpustat->cpustat[index], val);
 	rcu_read_unlock();
 }
 
diff --git a/kernel/sched/cpudeadline.c b/kernel/sched/cpudeadline.c
index 5cc4012572ec..8cb06c8c7eb1 100644
--- a/kernel/sched/cpudeadline.c
+++ b/kernel/sched/cpudeadline.c
@@ -121,6 +121,30 @@ int cpudl_find(struct cpudl *cp, struct task_struct *p,
 
 	if (later_mask &&
 	    cpumask_and(later_mask, cp->free_cpus, p->cpus_ptr)) {
+		unsigned long cap, max_cap = 0;
+		int cpu, max_cpu = -1;
+
+		if (!static_branch_unlikely(&sched_asym_cpucapacity))
+			return 1;
+
+		/* Ensure the capacity of the CPUs fits the task. */
+		for_each_cpu(cpu, later_mask) {
+			if (!dl_task_fits_capacity(p, cpu)) {
+				cpumask_clear_cpu(cpu, later_mask);
+
+				cap = capacity_orig_of(cpu);
+
+				if (cap > max_cap ||
+				    (cpu == task_cpu(p) && cap == max_cap)) {
+					max_cap = cap;
+					max_cpu = cpu;
+				}
+			}
+		}
+
+		if (cpumask_empty(later_mask))
+			cpumask_set_cpu(max_cpu, later_mask);
+
 		return 1;
 	} else {
 		int best_cpu = cpudl_maximum(cp);
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index 7fbaee24c824..e39008242cf4 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -210,7 +210,7 @@ unsigned long schedutil_cpu_util(int cpu, unsigned long util_cfs,
 	unsigned long dl_util, util, irq;
 	struct rq *rq = cpu_rq(cpu);
 
-	if (!IS_BUILTIN(CONFIG_UCLAMP_TASK) &&
+	if (!uclamp_is_used() &&
 	    type == FREQUENCY_UTIL && rt_rq_is_runnable(&rq->rt)) {
 		return max;
 	}
@@ -909,11 +909,7 @@ struct cpufreq_governor *cpufreq_default_governor(void)
 }
 #endif
 
-static int __init sugov_register(void)
-{
-	return cpufreq_register_governor(&schedutil_gov);
-}
-core_initcall(sugov_register);
+cpufreq_governor_init(schedutil_gov);
 
 #ifdef CONFIG_ENERGY_MODEL
 extern bool sched_energy_update;
diff --git a/kernel/sched/cpupri.c b/kernel/sched/cpupri.c
index 1a2719e1350a..0033731a0797 100644
--- a/kernel/sched/cpupri.c
+++ b/kernel/sched/cpupri.c
@@ -41,8 +41,67 @@ static int convert_prio(int prio)
 	return cpupri;
 }
 
+static inline int __cpupri_find(struct cpupri *cp, struct task_struct *p,
+				struct cpumask *lowest_mask, int idx)
+{
+	struct cpupri_vec *vec  = &cp->pri_to_cpu[idx];
+	int skip = 0;
+
+	if (!atomic_read(&(vec)->count))
+		skip = 1;
+	/*
+	 * When looking at the vector, we need to read the counter,
+	 * do a memory barrier, then read the mask.
+	 *
+	 * Note: This is still all racey, but we can deal with it.
+	 *  Ideally, we only want to look at masks that are set.
+	 *
+	 *  If a mask is not set, then the only thing wrong is that we
+	 *  did a little more work than necessary.
+	 *
+	 *  If we read a zero count but the mask is set, because of the
+	 *  memory barriers, that can only happen when the highest prio
+	 *  task for a run queue has left the run queue, in which case,
+	 *  it will be followed by a pull. If the task we are processing
+	 *  fails to find a proper place to go, that pull request will
+	 *  pull this task if the run queue is running at a lower
+	 *  priority.
+	 */
+	smp_rmb();
+
+	/* Need to do the rmb for every iteration */
+	if (skip)
+		return 0;
+
+	if (cpumask_any_and(p->cpus_ptr, vec->mask) >= nr_cpu_ids)
+		return 0;
+
+	if (lowest_mask) {
+		cpumask_and(lowest_mask, p->cpus_ptr, vec->mask);
+
+		/*
+		 * We have to ensure that we have at least one bit
+		 * still set in the array, since the map could have
+		 * been concurrently emptied between the first and
+		 * second reads of vec->mask.  If we hit this
+		 * condition, simply act as though we never hit this
+		 * priority level and continue on.
+		 */
+		if (cpumask_empty(lowest_mask))
+			return 0;
+	}
+
+	return 1;
+}
+
+int cpupri_find(struct cpupri *cp, struct task_struct *p,
+		struct cpumask *lowest_mask)
+{
+	return cpupri_find_fitness(cp, p, lowest_mask, NULL);
+}
+
 /**
- * cpupri_find - find the best (lowest-pri) CPU in the system
+ * cpupri_find_fitness - find the best (lowest-pri) CPU in the system
  * @cp: The cpupri context
  * @p: The task
  * @lowest_mask: A mask to fill in with selected CPUs (or NULL)
@@ -58,84 +117,59 @@ static int convert_prio(int prio)
  *
  * Return: (int)bool - CPUs were found
  */
-int cpupri_find(struct cpupri *cp, struct task_struct *p,
+int cpupri_find_fitness(struct cpupri *cp, struct task_struct *p,
 		struct cpumask *lowest_mask,
 		bool (*fitness_fn)(struct task_struct *p, int cpu))
 {
-	int idx = 0;
 	int task_pri = convert_prio(p->prio);
+	int idx, cpu;
 
 	BUG_ON(task_pri >= CPUPRI_NR_PRIORITIES);
 
 	for (idx = 0; idx < task_pri; idx++) {
-		struct cpupri_vec *vec  = &cp->pri_to_cpu[idx];
-		int skip = 0;
-
-		if (!atomic_read(&(vec)->count))
-			skip = 1;
-		/*
-		 * When looking at the vector, we need to read the counter,
-		 * do a memory barrier, then read the mask.
-		 *
-		 * Note: This is still all racey, but we can deal with it.
-		 *  Ideally, we only want to look at masks that are set.
-		 *
-		 *  If a mask is not set, then the only thing wrong is that we
-		 *  did a little more work than necessary.
-		 *
-		 *  If we read a zero count but the mask is set, because of the
-		 *  memory barriers, that can only happen when the highest prio
-		 *  task for a run queue has left the run queue, in which case,
-		 *  it will be followed by a pull. If the task we are processing
-		 *  fails to find a proper place to go, that pull request will
-		 *  pull this task if the run queue is running at a lower
-		 *  priority.
-		 */
-		smp_rmb();
 
-		/* Need to do the rmb for every iteration */
-		if (skip)
+		if (!__cpupri_find(cp, p, lowest_mask, idx))
 			continue;
 
-		if (cpumask_any_and(p->cpus_ptr, vec->mask) >= nr_cpu_ids)
-			continue;
+		if (!lowest_mask || !fitness_fn)
+			return 1;
 
-		if (lowest_mask) {
-			int cpu;
-
-			cpumask_and(lowest_mask, p->cpus_ptr, vec->mask);
-
-			/*
-			 * We have to ensure that we have at least one bit
-			 * still set in the array, since the map could have
-			 * been concurrently emptied between the first and
-			 * second reads of vec->mask.  If we hit this
-			 * condition, simply act as though we never hit this
-			 * priority level and continue on.
-			 */
-			if (cpumask_empty(lowest_mask))
-				continue;
-
-			if (!fitness_fn)
-				return 1;
-
-			/* Ensure the capacity of the CPUs fit the task */
-			for_each_cpu(cpu, lowest_mask) {
-				if (!fitness_fn(p, cpu))
-					cpumask_clear_cpu(cpu, lowest_mask);
-			}
-
-			/*
-			 * If no CPU at the current priority can fit the task
-			 * continue looking
-			 */
-			if (cpumask_empty(lowest_mask))
-				continue;
+		/* Ensure the capacity of the CPUs fit the task */
+		for_each_cpu(cpu, lowest_mask) {
+			if (!fitness_fn(p, cpu))
+				cpumask_clear_cpu(cpu, lowest_mask);
 		}
 
+		/*
+		 * If no CPU at the current priority can fit the task
+		 * continue looking
+		 */
+		if (cpumask_empty(lowest_mask))
+			continue;
+
 		return 1;
 	}
 
+	/*
+	 * If we failed to find a fitting lowest_mask, kick off a new search
+	 * but without taking into account any fitness criteria this time.
+	 *
+	 * This rule favours honouring priority over fitting the task in the
+	 * correct CPU (Capacity Awareness being the only user now).
+	 * The idea is that if a higher priority task can run, then it should
+	 * run even if this ends up being on unfitting CPU.
+	 *
+	 * The cost of this trade-off is not entirely clear and will probably
+	 * be good for some workloads and bad for others.
+	 *
+	 * The main idea here is that if some CPUs were overcommitted, we try
+	 * to spread which is what the scheduler traditionally did. Sys admins
+	 * must do proper RT planning to avoid overloading the system if they
+	 * really care.
+	 */
+	if (fitness_fn)
+		return cpupri_find(cp, p, lowest_mask);
+
 	return 0;
 }
 
diff --git a/kernel/sched/cpupri.h b/kernel/sched/cpupri.h
index 32dd520db11f..efbb492bb94c 100644
--- a/kernel/sched/cpupri.h
+++ b/kernel/sched/cpupri.h
@@ -19,8 +19,10 @@ struct cpupri {
 
 #ifdef CONFIG_SMP
 int  cpupri_find(struct cpupri *cp, struct task_struct *p,
-		 struct cpumask *lowest_mask,
-		 bool (*fitness_fn)(struct task_struct *p, int cpu));
+		 struct cpumask *lowest_mask);
+int  cpupri_find_fitness(struct cpupri *cp, struct task_struct *p,
+			 struct cpumask *lowest_mask,
+			 bool (*fitness_fn)(struct task_struct *p, int cpu));
 void cpupri_set(struct cpupri *cp, int cpu, int pri);
 int  cpupri_init(struct cpupri *cp);
 void cpupri_cleanup(struct cpupri *cp);
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index cff3e656566d..5a55d2300452 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -520,50 +520,6 @@ void account_idle_ticks(unsigned long ticks)
 }
 
 /*
- * Perform (stime * rtime) / total, but avoid multiplication overflow by
- * losing precision when the numbers are big.
- */
-static u64 scale_stime(u64 stime, u64 rtime, u64 total)
-{
-	u64 scaled;
-
-	for (;;) {
-		/* Make sure "rtime" is the bigger of stime/rtime */
-		if (stime > rtime)
-			swap(rtime, stime);
-
-		/* Make sure 'total' fits in 32 bits */
-		if (total >> 32)
-			goto drop_precision;
-
-		/* Does rtime (and thus stime) fit in 32 bits? */
-		if (!(rtime >> 32))
-			break;
-
-		/* Can we just balance rtime/stime rather than dropping bits? */
-		if (stime >> 31)
-			goto drop_precision;
-
-		/* We can grow stime and shrink rtime and try to make them both fit */
-		stime <<= 1;
-		rtime >>= 1;
-		continue;
-
-drop_precision:
-		/* We drop from rtime, it has more bits than stime */
-		rtime >>= 1;
-		total >>= 1;
-	}
-
-	/*
-	 * Make sure gcc understands that this is a 32x32->64 multiply,
-	 * followed by a 64/32->64 divide.
-	 */
-	scaled = div_u64((u64) (u32) stime * (u64) (u32) rtime, (u32)total);
-	return scaled;
-}
-
-/*
  * Adjust tick based cputime random precision against scheduler runtime
  * accounting.
  *
@@ -622,7 +578,7 @@ void cputime_adjust(struct task_cputime *curr, struct prev_cputime *prev,
 		goto update;
 	}
 
-	stime = scale_stime(stime, rtime, stime + utime);
+	stime = mul_u64_u64_div_u64(stime, rtime, stime + utime);
 
 update:
 	/*
@@ -909,8 +865,10 @@ void task_cputime(struct task_struct *t, u64 *utime, u64 *stime)
 	} while (read_seqcount_retry(&vtime->seqcount, seq));
 }
 
-static int vtime_state_check(struct vtime *vtime, int cpu)
+static int vtime_state_fetch(struct vtime *vtime, int cpu)
 {
+	int state = READ_ONCE(vtime->state);
+
 	/*
 	 * We raced against a context switch, fetch the
 	 * kcpustat task again.
@@ -927,10 +885,10 @@ static int vtime_state_check(struct vtime *vtime, int cpu)
 	 *
 	 * Case 1) is ok but 2) is not. So wait for a safe VTIME state.
 	 */
-	if (vtime->state == VTIME_INACTIVE)
+	if (state == VTIME_INACTIVE)
 		return -EAGAIN;
 
-	return 0;
+	return state;
 }
 
 static u64 kcpustat_user_vtime(struct vtime *vtime)
@@ -949,14 +907,15 @@ static int kcpustat_field_vtime(u64 *cpustat,
 {
 	struct vtime *vtime = &tsk->vtime;
 	unsigned int seq;
-	int err;
 
 	do {
+		int state;
+
 		seq = read_seqcount_begin(&vtime->seqcount);
 
-		err = vtime_state_check(vtime, cpu);
-		if (err < 0)
-			return err;
+		state = vtime_state_fetch(vtime, cpu);
+		if (state < 0)
+			return state;
 
 		*val = cpustat[usage];
 
@@ -969,7 +928,7 @@ static int kcpustat_field_vtime(u64 *cpustat,
 		 */
 		switch (usage) {
 		case CPUTIME_SYSTEM:
-			if (vtime->state == VTIME_SYS)
+			if (state == VTIME_SYS)
 				*val += vtime->stime + vtime_delta(vtime);
 			break;
 		case CPUTIME_USER:
@@ -981,11 +940,11 @@ static int kcpustat_field_vtime(u64 *cpustat,
 				*val += kcpustat_user_vtime(vtime);
 			break;
 		case CPUTIME_GUEST:
-			if (vtime->state == VTIME_GUEST && task_nice(tsk) <= 0)
+			if (state == VTIME_GUEST && task_nice(tsk) <= 0)
 				*val += vtime->gtime + vtime_delta(vtime);
 			break;
 		case CPUTIME_GUEST_NICE:
-			if (vtime->state == VTIME_GUEST && task_nice(tsk) > 0)
+			if (state == VTIME_GUEST && task_nice(tsk) > 0)
 				*val += vtime->gtime + vtime_delta(vtime);
 			break;
 		default:
@@ -1000,12 +959,12 @@ u64 kcpustat_field(struct kernel_cpustat *kcpustat,
 		   enum cpu_usage_stat usage, int cpu)
 {
 	u64 *cpustat = kcpustat->cpustat;
+	u64 val = cpustat[usage];
 	struct rq *rq;
-	u64 val;
 	int err;
 
 	if (!vtime_accounting_enabled_cpu(cpu))
-		return cpustat[usage];
+		return val;
 
 	rq = cpu_rq(cpu);
 
@@ -1036,23 +995,23 @@ static int kcpustat_cpu_fetch_vtime(struct kernel_cpustat *dst,
 {
 	struct vtime *vtime = &tsk->vtime;
 	unsigned int seq;
-	int err;
 
 	do {
 		u64 *cpustat;
 		u64 delta;
+		int state;
 
 		seq = read_seqcount_begin(&vtime->seqcount);
 
-		err = vtime_state_check(vtime, cpu);
-		if (err < 0)
-			return err;
+		state = vtime_state_fetch(vtime, cpu);
+		if (state < 0)
+			return state;
 
 		*dst = *src;
 		cpustat = dst->cpustat;
 
 		/* Task is sleeping, dead or idle, nothing to add */
-		if (vtime->state < VTIME_SYS)
+		if (state < VTIME_SYS)
 			continue;
 
 		delta = vtime_delta(vtime);
@@ -1061,15 +1020,15 @@ static int kcpustat_cpu_fetch_vtime(struct kernel_cpustat *dst,
 		 * Task runs either in user (including guest) or kernel space,
 		 * add pending nohz time to the right place.
 		 */
-		if (vtime->state == VTIME_SYS) {
+		if (state == VTIME_SYS) {
 			cpustat[CPUTIME_SYSTEM] += vtime->stime + delta;
-		} else if (vtime->state == VTIME_USER) {
+		} else if (state == VTIME_USER) {
 			if (task_nice(tsk) > 0)
 				cpustat[CPUTIME_NICE] += vtime->utime + delta;
 			else
 				cpustat[CPUTIME_USER] += vtime->utime + delta;
 		} else {
-			WARN_ON_ONCE(vtime->state != VTIME_GUEST);
+			WARN_ON_ONCE(state != VTIME_GUEST);
 			if (task_nice(tsk) > 0) {
 				cpustat[CPUTIME_GUEST_NICE] += vtime->gtime + delta;
 				cpustat[CPUTIME_NICE] += vtime->gtime + delta;
@@ -1080,7 +1039,7 @@ static int kcpustat_cpu_fetch_vtime(struct kernel_cpustat *dst,
 		}
 	} while (read_seqcount_retry(&vtime->seqcount, seq));
 
-	return err;
+	return 0;
 }
 
 void kcpustat_cpu_fetch(struct kernel_cpustat *dst, int cpu)
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 43323f875cb9..3862a28cd05d 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -54,15 +54,49 @@ static inline struct dl_bw *dl_bw_of(int i)
 static inline int dl_bw_cpus(int i)
 {
 	struct root_domain *rd = cpu_rq(i)->rd;
-	int cpus = 0;
+	int cpus;
 
 	RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held(),
 			 "sched RCU must be held");
+
+	if (cpumask_subset(rd->span, cpu_active_mask))
+		return cpumask_weight(rd->span);
+
+	cpus = 0;
+
 	for_each_cpu_and(i, rd->span, cpu_active_mask)
 		cpus++;
 
 	return cpus;
 }
+
+static inline unsigned long __dl_bw_capacity(int i)
+{
+	struct root_domain *rd = cpu_rq(i)->rd;
+	unsigned long cap = 0;
+
+	RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held(),
+			 "sched RCU must be held");
+
+	for_each_cpu_and(i, rd->span, cpu_active_mask)
+		cap += capacity_orig_of(i);
+
+	return cap;
+}
+
+/*
+ * XXX Fix: If 'rq->rd == def_root_domain' perform AC against capacity
+ * of the CPU the task is running on rather rd's \Sum CPU capacity.
+ */
+static inline unsigned long dl_bw_capacity(int i)
+{
+	if (!static_branch_unlikely(&sched_asym_cpucapacity) &&
+	    capacity_orig_of(i) == SCHED_CAPACITY_SCALE) {
+		return dl_bw_cpus(i) << SCHED_CAPACITY_SHIFT;
+	} else {
+		return __dl_bw_capacity(i);
+	}
+}
 #else
 static inline struct dl_bw *dl_bw_of(int i)
 {
@@ -73,6 +107,11 @@ static inline int dl_bw_cpus(int i)
 {
 	return 1;
 }
+
+static inline unsigned long dl_bw_capacity(int i)
+{
+	return SCHED_CAPACITY_SCALE;
+}
 #endif
 
 static inline
@@ -153,7 +192,7 @@ void sub_running_bw(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
 		__sub_running_bw(dl_se->dl_bw, dl_rq);
 }
 
-void dl_change_utilization(struct task_struct *p, u64 new_bw)
+static void dl_change_utilization(struct task_struct *p, u64 new_bw)
 {
 	struct rq *rq;
 
@@ -334,6 +373,8 @@ static inline int is_leftmost(struct task_struct *p, struct dl_rq *dl_rq)
 	return dl_rq->root.rb_leftmost == &dl_se->rb_node;
 }
 
+static void init_dl_rq_bw_ratio(struct dl_rq *dl_rq);
+
 void init_dl_bandwidth(struct dl_bandwidth *dl_b, u64 period, u64 runtime)
 {
 	raw_spin_lock_init(&dl_b->dl_runtime_lock);
@@ -1096,7 +1137,7 @@ void init_dl_task_timer(struct sched_dl_entity *dl_se)
  * cannot use the runtime, and so it replenishes the task. This rule
  * works fine for implicit deadline tasks (deadline == period), and the
  * CBS was designed for implicit deadline tasks. However, a task with
- * constrained deadline (deadine < period) might be awakened after the
+ * constrained deadline (deadline < period) might be awakened after the
  * deadline, but before the next period. In this case, replenishing the
  * task would allow it to run for runtime / deadline. As in this case
  * deadline < period, CBS enables a task to run for more than the
@@ -1602,6 +1643,7 @@ static int
 select_task_rq_dl(struct task_struct *p, int cpu, int sd_flag, int flags)
 {
 	struct task_struct *curr;
+	bool select_rq;
 	struct rq *rq;
 
 	if (sd_flag != SD_BALANCE_WAKE)
@@ -1621,10 +1663,19 @@ select_task_rq_dl(struct task_struct *p, int cpu, int sd_flag, int flags)
 	 * other hand, if it has a shorter deadline, we
 	 * try to make it stay here, it might be important.
 	 */
-	if (unlikely(dl_task(curr)) &&
-	    (curr->nr_cpus_allowed < 2 ||
-	     !dl_entity_preempt(&p->dl, &curr->dl)) &&
-	    (p->nr_cpus_allowed > 1)) {
+	select_rq = unlikely(dl_task(curr)) &&
+		    (curr->nr_cpus_allowed < 2 ||
+		     !dl_entity_preempt(&p->dl, &curr->dl)) &&
+		    p->nr_cpus_allowed > 1;
+
+	/*
+	 * Take the capacity of the CPU into account to
+	 * ensure it fits the requirement of the task.
+	 */
+	if (static_branch_unlikely(&sched_asym_cpucapacity))
+		select_rq |= !dl_task_fits_capacity(p, cpu);
+
+	if (select_rq) {
 		int target = find_later_rq(p);
 
 		if (target != -1 &&
@@ -2428,8 +2479,8 @@ static void prio_changed_dl(struct rq *rq, struct task_struct *p,
 	}
 }
 
-const struct sched_class dl_sched_class = {
-	.next			= &rt_sched_class,
+const struct sched_class dl_sched_class
+	__attribute__((section("__dl_sched_class"))) = {
 	.enqueue_task		= enqueue_task_dl,
 	.dequeue_task		= dequeue_task_dl,
 	.yield_task		= yield_task_dl,
@@ -2496,7 +2547,7 @@ int sched_dl_global_validate(void)
 	return ret;
 }
 
-void init_dl_rq_bw_ratio(struct dl_rq *dl_rq)
+static void init_dl_rq_bw_ratio(struct dl_rq *dl_rq)
 {
 	if (global_rt_runtime() == RUNTIME_INF) {
 		dl_rq->bw_ratio = 1 << RATIO_SHIFT;
@@ -2549,11 +2600,12 @@ void sched_dl_do_global(void)
 int sched_dl_overflow(struct task_struct *p, int policy,
 		      const struct sched_attr *attr)
 {
-	struct dl_bw *dl_b = dl_bw_of(task_cpu(p));
 	u64 period = attr->sched_period ?: attr->sched_deadline;
 	u64 runtime = attr->sched_runtime;
 	u64 new_bw = dl_policy(policy) ? to_ratio(period, runtime) : 0;
-	int cpus, err = -1;
+	int cpus, err = -1, cpu = task_cpu(p);
+	struct dl_bw *dl_b = dl_bw_of(cpu);
+	unsigned long cap;
 
 	if (attr->sched_flags & SCHED_FLAG_SUGOV)
 		return 0;
@@ -2568,15 +2620,17 @@ int sched_dl_overflow(struct task_struct *p, int policy,
 	 * allocated bandwidth of the container.
 	 */
 	raw_spin_lock(&dl_b->lock);
-	cpus = dl_bw_cpus(task_cpu(p));
+	cpus = dl_bw_cpus(cpu);
+	cap = dl_bw_capacity(cpu);
+
 	if (dl_policy(policy) && !task_has_dl_policy(p) &&
-	    !__dl_overflow(dl_b, cpus, 0, new_bw)) {
+	    !__dl_overflow(dl_b, cap, 0, new_bw)) {
 		if (hrtimer_active(&p->dl.inactive_timer))
 			__dl_sub(dl_b, p->dl.dl_bw, cpus);
 		__dl_add(dl_b, new_bw, cpus);
 		err = 0;
 	} else if (dl_policy(policy) && task_has_dl_policy(p) &&
-		   !__dl_overflow(dl_b, cpus, p->dl.dl_bw, new_bw)) {
+		   !__dl_overflow(dl_b, cap, p->dl.dl_bw, new_bw)) {
 		/*
 		 * XXX this is slightly incorrect: when the task
 		 * utilization decreases, we should delay the total
@@ -2633,6 +2687,14 @@ void __getparam_dl(struct task_struct *p, struct sched_attr *attr)
 }
 
 /*
+ * Default limits for DL period; on the top end we guard against small util
+ * tasks still getting rediculous long effective runtimes, on the bottom end we
+ * guard against timer DoS.
+ */
+unsigned int sysctl_sched_dl_period_max = 1 << 22; /* ~4 seconds */
+unsigned int sysctl_sched_dl_period_min = 100;     /* 100 us */
+
+/*
  * This function validates the new parameters of a -deadline task.
  * We ask for the deadline not being zero, and greater or equal
  * than the runtime, as well as the period of being zero or
@@ -2644,6 +2706,8 @@ void __getparam_dl(struct task_struct *p, struct sched_attr *attr)
  */
 bool __checkparam_dl(const struct sched_attr *attr)
 {
+	u64 period, max, min;
+
 	/* special dl tasks don't actually use any parameter */
 	if (attr->sched_flags & SCHED_FLAG_SUGOV)
 		return true;
@@ -2667,12 +2731,21 @@ bool __checkparam_dl(const struct sched_attr *attr)
 	    attr->sched_period & (1ULL << 63))
 		return false;
 
+	period = attr->sched_period;
+	if (!period)
+		period = attr->sched_deadline;
+
 	/* runtime <= deadline <= period (if period != 0) */
-	if ((attr->sched_period != 0 &&
-	     attr->sched_period < attr->sched_deadline) ||
+	if (period < attr->sched_deadline ||
 	    attr->sched_deadline < attr->sched_runtime)
 		return false;
 
+	max = (u64)READ_ONCE(sysctl_sched_dl_period_max) * NSEC_PER_USEC;
+	min = (u64)READ_ONCE(sysctl_sched_dl_period_min) * NSEC_PER_USEC;
+
+	if (period < min || period > max)
+		return false;
+
 	return true;
 }
 
@@ -2690,6 +2763,7 @@ void __dl_clear_params(struct task_struct *p)
 	dl_se->dl_bw			= 0;
 	dl_se->dl_density		= 0;
 
+	dl_se->dl_boosted		= 0;
 	dl_se->dl_throttled		= 0;
 	dl_se->dl_yielded		= 0;
 	dl_se->dl_non_contending	= 0;
@@ -2712,19 +2786,19 @@ bool dl_param_changed(struct task_struct *p, const struct sched_attr *attr)
 #ifdef CONFIG_SMP
 int dl_task_can_attach(struct task_struct *p, const struct cpumask *cs_cpus_allowed)
 {
+	unsigned long flags, cap;
 	unsigned int dest_cpu;
 	struct dl_bw *dl_b;
 	bool overflow;
-	int cpus, ret;
-	unsigned long flags;
+	int ret;
 
 	dest_cpu = cpumask_any_and(cpu_active_mask, cs_cpus_allowed);
 
 	rcu_read_lock_sched();
 	dl_b = dl_bw_of(dest_cpu);
 	raw_spin_lock_irqsave(&dl_b->lock, flags);
-	cpus = dl_bw_cpus(dest_cpu);
-	overflow = __dl_overflow(dl_b, cpus, 0, p->dl.dl_bw);
+	cap = dl_bw_capacity(dest_cpu);
+	overflow = __dl_overflow(dl_b, cap, 0, p->dl.dl_bw);
 	if (overflow) {
 		ret = -EBUSY;
 	} else {
@@ -2734,6 +2808,8 @@ int dl_task_can_attach(struct task_struct *p, const struct cpumask *cs_cpus_allo
 		 * We will free resources in the source root_domain
 		 * later on (see set_cpus_allowed_dl()).
 		 */
+		int cpus = dl_bw_cpus(dest_cpu);
+
 		__dl_add(dl_b, p->dl.dl_bw, cpus);
 		ret = 0;
 	}
@@ -2766,16 +2842,15 @@ int dl_cpuset_cpumask_can_shrink(const struct cpumask *cur,
 
 bool dl_cpu_busy(unsigned int cpu)
 {
-	unsigned long flags;
+	unsigned long flags, cap;
 	struct dl_bw *dl_b;
 	bool overflow;
-	int cpus;
 
 	rcu_read_lock_sched();
 	dl_b = dl_bw_of(cpu);
 	raw_spin_lock_irqsave(&dl_b->lock, flags);
-	cpus = dl_bw_cpus(cpu);
-	overflow = __dl_overflow(dl_b, cpus, 0, 0);
+	cap = dl_bw_capacity(cpu);
+	overflow = __dl_overflow(dl_b, cap, 0, 0);
 	raw_spin_unlock_irqrestore(&dl_b->lock, flags);
 	rcu_read_unlock_sched();
 
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 879d3ccf3806..36c54265bb2b 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -258,7 +258,7 @@ sd_alloc_ctl_domain_table(struct sched_domain *sd)
 	set_table_entry(&table[2], "busy_factor",	  &sd->busy_factor,	    sizeof(int),  0644, proc_dointvec_minmax);
 	set_table_entry(&table[3], "imbalance_pct",	  &sd->imbalance_pct,	    sizeof(int),  0644, proc_dointvec_minmax);
 	set_table_entry(&table[4], "cache_nice_tries",	  &sd->cache_nice_tries,    sizeof(int),  0644, proc_dointvec_minmax);
-	set_table_entry(&table[5], "flags",		  &sd->flags,		    sizeof(int),  0644, proc_dointvec_minmax);
+	set_table_entry(&table[5], "flags",		  &sd->flags,		    sizeof(int),  0444, proc_dointvec_minmax);
 	set_table_entry(&table[6], "max_newidle_lb_cost", &sd->max_newidle_lb_cost, sizeof(long), 0644, proc_doulongvec_minmax);
 	set_table_entry(&table[7], "name",		  sd->name,	       CORENAME_MAX_SIZE, 0444, proc_dostring);
 	/* &table[8] is terminator */
@@ -402,11 +402,10 @@ static void print_cfs_group_stats(struct seq_file *m, int cpu, struct task_group
 	}
 
 	P(se->load.weight);
-	P(se->runnable_weight);
 #ifdef CONFIG_SMP
 	P(se->avg.load_avg);
 	P(se->avg.util_avg);
-	P(se->avg.runnable_load_avg);
+	P(se->avg.runnable_avg);
 #endif
 
 #undef PN_SCHEDSTAT
@@ -438,7 +437,7 @@ print_task(struct seq_file *m, struct rq *rq, struct task_struct *p)
 	else
 		SEQ_printf(m, " %c", task_state_to_char(p));
 
-	SEQ_printf(m, "%15s %5d %9Ld.%06ld %9Ld %5d ",
+	SEQ_printf(m, " %15s %5d %9Ld.%06ld %9Ld %5d ",
 		p->comm, task_pid_nr(p),
 		SPLIT_NS(p->se.vruntime),
 		(long long)(p->nvcsw + p->nivcsw),
@@ -465,10 +464,10 @@ static void print_rq(struct seq_file *m, struct rq *rq, int rq_cpu)
 
 	SEQ_printf(m, "\n");
 	SEQ_printf(m, "runnable tasks:\n");
-	SEQ_printf(m, " S           task   PID         tree-key  switches  prio"
+	SEQ_printf(m, " S            task   PID         tree-key  switches  prio"
 		   "     wait-time             sum-exec        sum-sleep\n");
 	SEQ_printf(m, "-------------------------------------------------------"
-		   "----------------------------------------------------\n");
+		   "------------------------------------------------------\n");
 
 	rcu_read_lock();
 	for_each_process_thread(g, p) {
@@ -524,11 +523,10 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
 	SEQ_printf(m, "  .%-30s: %d\n", "nr_running", cfs_rq->nr_running);
 	SEQ_printf(m, "  .%-30s: %ld\n", "load", cfs_rq->load.weight);
 #ifdef CONFIG_SMP
-	SEQ_printf(m, "  .%-30s: %ld\n", "runnable_weight", cfs_rq->runnable_weight);
 	SEQ_printf(m, "  .%-30s: %lu\n", "load_avg",
 			cfs_rq->avg.load_avg);
-	SEQ_printf(m, "  .%-30s: %lu\n", "runnable_load_avg",
-			cfs_rq->avg.runnable_load_avg);
+	SEQ_printf(m, "  .%-30s: %lu\n", "runnable_avg",
+			cfs_rq->avg.runnable_avg);
 	SEQ_printf(m, "  .%-30s: %lu\n", "util_avg",
 			cfs_rq->avg.util_avg);
 	SEQ_printf(m, "  .%-30s: %u\n", "util_est_enqueued",
@@ -537,8 +535,8 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
 			cfs_rq->removed.load_avg);
 	SEQ_printf(m, "  .%-30s: %ld\n", "removed.util_avg",
 			cfs_rq->removed.util_avg);
-	SEQ_printf(m, "  .%-30s: %ld\n", "removed.runnable_sum",
-			cfs_rq->removed.runnable_sum);
+	SEQ_printf(m, "  .%-30s: %ld\n", "removed.runnable_avg",
+			cfs_rq->removed.runnable_avg);
 #ifdef CONFIG_FAIR_GROUP_SCHED
 	SEQ_printf(m, "  .%-30s: %lu\n", "tg_load_avg_contrib",
 			cfs_rq->tg_load_avg_contrib);
@@ -640,7 +638,6 @@ do {									\
 
 	P(nr_running);
 	P(nr_switches);
-	P(nr_load_updates);
 	P(nr_uninterruptible);
 	PN(next_balance);
 	SEQ_printf(m, "  .%-30s: %ld\n", "curr->pid", (long)(task_pid_nr(rq->curr)));
@@ -818,10 +815,12 @@ static int __init init_sched_debug_procfs(void)
 
 __initcall(init_sched_debug_procfs);
 
-#define __P(F)	SEQ_printf(m, "%-45s:%21Ld\n",	     #F, (long long)F)
-#define   P(F)	SEQ_printf(m, "%-45s:%21Ld\n",	     #F, (long long)p->F)
-#define __PN(F)	SEQ_printf(m, "%-45s:%14Ld.%06ld\n", #F, SPLIT_NS((long long)F))
-#define   PN(F)	SEQ_printf(m, "%-45s:%14Ld.%06ld\n", #F, SPLIT_NS((long long)p->F))
+#define __PS(S, F) SEQ_printf(m, "%-45s:%21Ld\n", S, (long long)(F))
+#define __P(F) __PS(#F, F)
+#define   P(F) __PS(#F, p->F)
+#define __PSN(S, F) SEQ_printf(m, "%-45s:%14Ld.%06ld\n", S, SPLIT_NS((long long)(F)))
+#define __PN(F) __PSN(#F, F)
+#define   PN(F) __PSN(#F, p->F)
 
 
 #ifdef CONFIG_NUMA_BALANCING
@@ -870,18 +869,9 @@ void proc_sched_show_task(struct task_struct *p, struct pid_namespace *ns,
 	SEQ_printf(m,
 		"---------------------------------------------------------"
 		"----------\n");
-#define __P(F) \
-	SEQ_printf(m, "%-45s:%21Ld\n", #F, (long long)F)
-#define P(F) \
-	SEQ_printf(m, "%-45s:%21Ld\n", #F, (long long)p->F)
-#define P_SCHEDSTAT(F) \
-	SEQ_printf(m, "%-45s:%21Ld\n", #F, (long long)schedstat_val(p->F))
-#define __PN(F) \
-	SEQ_printf(m, "%-45s:%14Ld.%06ld\n", #F, SPLIT_NS((long long)F))
-#define PN(F) \
-	SEQ_printf(m, "%-45s:%14Ld.%06ld\n", #F, SPLIT_NS((long long)p->F))
-#define PN_SCHEDSTAT(F) \
-	SEQ_printf(m, "%-45s:%14Ld.%06ld\n", #F, SPLIT_NS((long long)schedstat_val(p->F)))
+
+#define P_SCHEDSTAT(F)  __PS(#F, schedstat_val(p->F))
+#define PN_SCHEDSTAT(F) __PSN(#F, schedstat_val(p->F))
 
 	PN(se.exec_start);
 	PN(se.vruntime);
@@ -941,24 +931,27 @@ void proc_sched_show_task(struct task_struct *p, struct pid_namespace *ns,
 	}
 
 	__P(nr_switches);
-	SEQ_printf(m, "%-45s:%21Ld\n",
-		   "nr_voluntary_switches", (long long)p->nvcsw);
-	SEQ_printf(m, "%-45s:%21Ld\n",
-		   "nr_involuntary_switches", (long long)p->nivcsw);
+	__PS("nr_voluntary_switches", p->nvcsw);
+	__PS("nr_involuntary_switches", p->nivcsw);
 
 	P(se.load.weight);
-	P(se.runnable_weight);
 #ifdef CONFIG_SMP
 	P(se.avg.load_sum);
-	P(se.avg.runnable_load_sum);
+	P(se.avg.runnable_sum);
 	P(se.avg.util_sum);
 	P(se.avg.load_avg);
-	P(se.avg.runnable_load_avg);
+	P(se.avg.runnable_avg);
 	P(se.avg.util_avg);
 	P(se.avg.last_update_time);
 	P(se.avg.util_est.ewma);
 	P(se.avg.util_est.enqueued);
 #endif
+#ifdef CONFIG_UCLAMP_TASK
+	__PS("uclamp.min", p->uclamp_req[UCLAMP_MIN].value);
+	__PS("uclamp.max", p->uclamp_req[UCLAMP_MAX].value);
+	__PS("effective uclamp.min", uclamp_eff_value(p, UCLAMP_MIN));
+	__PS("effective uclamp.max", uclamp_eff_value(p, UCLAMP_MAX));
+#endif
 	P(policy);
 	P(prio);
 	if (task_has_dl_policy(p)) {
@@ -966,11 +959,7 @@ void proc_sched_show_task(struct task_struct *p, struct pid_namespace *ns,
 		P(dl.deadline);
 	}
 #undef PN_SCHEDSTAT
-#undef PN
-#undef __PN
 #undef P_SCHEDSTAT
-#undef P
-#undef __P
 
 	{
 		unsigned int this_cpu = raw_smp_processor_id();
@@ -978,8 +967,7 @@ void proc_sched_show_task(struct task_struct *p, struct pid_namespace *ns,
 
 		t0 = cpu_clock(this_cpu);
 		t1 = cpu_clock(this_cpu);
-		SEQ_printf(m, "%-45s:%21Ld\n",
-			   "clock-delta", (long long)(t1-t0));
+		__PS("clock-delta", t1-t0);
 	}
 
 	sched_show_numa(p, m);
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index c1217bfe5e81..1a68a0536add 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -22,8 +22,6 @@
  */
 #include "sched.h"
 
-#include <trace/events/sched.h>
-
 /*
  * Targeted preemption latency for CPU-bound tasks:
  *
@@ -86,6 +84,19 @@ static unsigned int normalized_sysctl_sched_wakeup_granularity	= 1000000UL;
 
 const_debug unsigned int sysctl_sched_migration_cost	= 500000UL;
 
+int sched_thermal_decay_shift;
+static int __init setup_sched_thermal_decay_shift(char *str)
+{
+	int _shift = 0;
+
+	if (kstrtoint(str, 0, &_shift))
+		pr_warn("Unable to set scheduler thermal pressure decay shift parameter\n");
+
+	sched_thermal_decay_shift = clamp(_shift, 0, 10);
+	return 1;
+}
+__setup("sched_thermal_decay_shift=", setup_sched_thermal_decay_shift);
+
 #ifdef CONFIG_SMP
 /*
  * For asym packing, by default the lower numbered CPU has higher priority.
@@ -178,7 +189,7 @@ static void update_sysctl(void)
 #undef SET_SYSCTL
 }
 
-void sched_init_granularity(void)
+void __init sched_init_granularity(void)
 {
 	update_sysctl();
 }
@@ -632,8 +643,7 @@ struct sched_entity *__pick_last_entity(struct cfs_rq *cfs_rq)
  */
 
 int sched_proc_update_handler(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 = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
 	unsigned int factor = get_update_sysctl_factor();
@@ -741,9 +751,7 @@ void init_entity_runnable_average(struct sched_entity *se)
 	 * nothing has been attached to the task group yet.
 	 */
 	if (entity_is_task(se))
-		sa->runnable_load_avg = sa->load_avg = scale_load_down(se->load.weight);
-
-	se->runnable_weight = se->load.weight;
+		sa->load_avg = scale_load_down(se->load.weight);
 
 	/* when this task enqueue'ed, it will contribute to its cfs_rq's load_avg */
 }
@@ -796,6 +804,8 @@ void post_init_entity_util_avg(struct task_struct *p)
 		}
 	}
 
+	sa->runnable_avg = sa->util_avg;
+
 	if (p->sched_class != &fair_sched_class) {
 		/*
 		 * For !fair tasks do:
@@ -1081,7 +1091,7 @@ struct numa_group {
 	 * more by CPU use than by memory faults.
 	 */
 	unsigned long *faults_cpu;
-	unsigned long faults[0];
+	unsigned long faults[];
 };
 
 /*
@@ -1473,36 +1483,51 @@ bool should_numa_migrate_memory(struct task_struct *p, struct page * page,
 	       group_faults_cpu(ng, src_nid) * group_faults(p, dst_nid) * 4;
 }
 
-static inline unsigned long cfs_rq_runnable_load_avg(struct cfs_rq *cfs_rq);
-
-static unsigned long cpu_runnable_load(struct rq *rq)
-{
-	return cfs_rq_runnable_load_avg(&rq->cfs);
-}
+/*
+ * 'numa_type' describes the node at the moment of load balancing.
+ */
+enum numa_type {
+	/* The node has spare capacity that can be used to run more tasks.  */
+	node_has_spare = 0,
+	/*
+	 * The node is fully used and the tasks don't compete for more CPU
+	 * cycles. Nevertheless, some tasks might wait before running.
+	 */
+	node_fully_busy,
+	/*
+	 * The node is overloaded and can't provide expected CPU cycles to all
+	 * tasks.
+	 */
+	node_overloaded
+};
 
 /* Cached statistics for all CPUs within a node */
 struct numa_stats {
 	unsigned long load;
-
+	unsigned long util;
 	/* Total compute capacity of CPUs on a node */
 	unsigned long compute_capacity;
+	unsigned int nr_running;
+	unsigned int weight;
+	enum numa_type node_type;
+	int idle_cpu;
 };
 
-/*
- * XXX borrowed from update_sg_lb_stats
- */
-static void update_numa_stats(struct numa_stats *ns, int nid)
+static inline bool is_core_idle(int cpu)
 {
-	int cpu;
+#ifdef CONFIG_SCHED_SMT
+	int sibling;
 
-	memset(ns, 0, sizeof(*ns));
-	for_each_cpu(cpu, cpumask_of_node(nid)) {
-		struct rq *rq = cpu_rq(cpu);
+	for_each_cpu(sibling, cpu_smt_mask(cpu)) {
+		if (cpu == sibling)
+			continue;
 
-		ns->load += cpu_runnable_load(rq);
-		ns->compute_capacity += capacity_of(cpu);
+		if (!idle_cpu(cpu))
+			return false;
 	}
+#endif
 
+	return true;
 }
 
 struct task_numa_env {
@@ -1521,20 +1546,128 @@ struct task_numa_env {
 	int best_cpu;
 };
 
+static unsigned long cpu_load(struct rq *rq);
+static unsigned long cpu_util(int cpu);
+static inline long adjust_numa_imbalance(int imbalance, int src_nr_running);
+
+static inline enum
+numa_type numa_classify(unsigned int imbalance_pct,
+			 struct numa_stats *ns)
+{
+	if ((ns->nr_running > ns->weight) &&
+	    ((ns->compute_capacity * 100) < (ns->util * imbalance_pct)))
+		return node_overloaded;
+
+	if ((ns->nr_running < ns->weight) ||
+	    ((ns->compute_capacity * 100) > (ns->util * imbalance_pct)))
+		return node_has_spare;
+
+	return node_fully_busy;
+}
+
+#ifdef CONFIG_SCHED_SMT
+/* Forward declarations of select_idle_sibling helpers */
+static inline bool test_idle_cores(int cpu, bool def);
+static inline int numa_idle_core(int idle_core, int cpu)
+{
+	if (!static_branch_likely(&sched_smt_present) ||
+	    idle_core >= 0 || !test_idle_cores(cpu, false))
+		return idle_core;
+
+	/*
+	 * Prefer cores instead of packing HT siblings
+	 * and triggering future load balancing.
+	 */
+	if (is_core_idle(cpu))
+		idle_core = cpu;
+
+	return idle_core;
+}
+#else
+static inline int numa_idle_core(int idle_core, int cpu)
+{
+	return idle_core;
+}
+#endif
+
+/*
+ * Gather all necessary information to make NUMA balancing placement
+ * decisions that are compatible with standard load balancer. This
+ * borrows code and logic from update_sg_lb_stats but sharing a
+ * common implementation is impractical.
+ */
+static void update_numa_stats(struct task_numa_env *env,
+			      struct numa_stats *ns, int nid,
+			      bool find_idle)
+{
+	int cpu, idle_core = -1;
+
+	memset(ns, 0, sizeof(*ns));
+	ns->idle_cpu = -1;
+
+	rcu_read_lock();
+	for_each_cpu(cpu, cpumask_of_node(nid)) {
+		struct rq *rq = cpu_rq(cpu);
+
+		ns->load += cpu_load(rq);
+		ns->util += cpu_util(cpu);
+		ns->nr_running += rq->cfs.h_nr_running;
+		ns->compute_capacity += capacity_of(cpu);
+
+		if (find_idle && !rq->nr_running && idle_cpu(cpu)) {
+			if (READ_ONCE(rq->numa_migrate_on) ||
+			    !cpumask_test_cpu(cpu, env->p->cpus_ptr))
+				continue;
+
+			if (ns->idle_cpu == -1)
+				ns->idle_cpu = cpu;
+
+			idle_core = numa_idle_core(idle_core, cpu);
+		}
+	}
+	rcu_read_unlock();
+
+	ns->weight = cpumask_weight(cpumask_of_node(nid));
+
+	ns->node_type = numa_classify(env->imbalance_pct, ns);
+
+	if (idle_core >= 0)
+		ns->idle_cpu = idle_core;
+}
+
 static void task_numa_assign(struct task_numa_env *env,
 			     struct task_struct *p, long imp)
 {
 	struct rq *rq = cpu_rq(env->dst_cpu);
 
-	/* Bail out if run-queue part of active NUMA balance. */
-	if (xchg(&rq->numa_migrate_on, 1))
+	/* Check if run-queue part of active NUMA balance. */
+	if (env->best_cpu != env->dst_cpu && xchg(&rq->numa_migrate_on, 1)) {
+		int cpu;
+		int start = env->dst_cpu;
+
+		/* Find alternative idle CPU. */
+		for_each_cpu_wrap(cpu, cpumask_of_node(env->dst_nid), start) {
+			if (cpu == env->best_cpu || !idle_cpu(cpu) ||
+			    !cpumask_test_cpu(cpu, env->p->cpus_ptr)) {
+				continue;
+			}
+
+			env->dst_cpu = cpu;
+			rq = cpu_rq(env->dst_cpu);
+			if (!xchg(&rq->numa_migrate_on, 1))
+				goto assign;
+		}
+
+		/* Failed to find an alternative idle CPU */
 		return;
+	}
 
+assign:
 	/*
 	 * Clear previous best_cpu/rq numa-migrate flag, since task now
 	 * found a better CPU to move/swap.
 	 */
-	if (env->best_cpu != -1) {
+	if (env->best_cpu != -1 && env->best_cpu != env->dst_cpu) {
 		rq = cpu_rq(env->best_cpu);
 		WRITE_ONCE(rq->numa_migrate_on, 0);
 	}
@@ -1590,7 +1723,7 @@ static bool load_too_imbalanced(long src_load, long dst_load,
  * into account that it might be best if task running on the dst_cpu should
  * be exchanged with the source task
  */
-static void task_numa_compare(struct task_numa_env *env,
+static bool task_numa_compare(struct task_numa_env *env,
 			      long taskimp, long groupimp, bool maymove)
 {
 	struct numa_group *cur_ng, *p_ng = deref_curr_numa_group(env->p);
@@ -1601,9 +1734,10 @@ static void task_numa_compare(struct task_numa_env *env,
 	int dist = env->dist;
 	long moveimp = imp;
 	long load;
+	bool stopsearch = false;
 
 	if (READ_ONCE(dst_rq->numa_migrate_on))
-		return;
+		return false;
 
 	rcu_read_lock();
 	cur = rcu_dereference(dst_rq->curr);
@@ -1614,8 +1748,10 @@ static void task_numa_compare(struct task_numa_env *env,
 	 * Because we have preemption enabled we can get migrated around and
 	 * end try selecting ourselves (current == env->p) as a swap candidate.
 	 */
-	if (cur == env->p)
+	if (cur == env->p) {
+		stopsearch = true;
 		goto unlock;
+	}
 
 	if (!cur) {
 		if (maymove && moveimp >= env->best_imp)
@@ -1624,18 +1760,27 @@ static void task_numa_compare(struct task_numa_env *env,
 			goto unlock;
 	}
 
+	/* Skip this swap candidate if cannot move to the source cpu. */
+	if (!cpumask_test_cpu(env->src_cpu, cur->cpus_ptr))
+		goto unlock;
+
+	/*
+	 * Skip this swap candidate if it is not moving to its preferred
+	 * node and the best task is.
+	 */
+	if (env->best_task &&
+	    env->best_task->numa_preferred_nid == env->src_nid &&
+	    cur->numa_preferred_nid != env->src_nid) {
+		goto unlock;
+	}
+
 	/*
 	 * "imp" is the fault differential for the source task between the
 	 * source and destination node. Calculate the total differential for
 	 * the source task and potential destination task. The more negative
 	 * the value is, the more remote accesses that would be expected to
 	 * be incurred if the tasks were swapped.
-	 */
-	/* Skip this swap candidate if cannot move to the source cpu */
-	if (!cpumask_test_cpu(env->src_cpu, cur->cpus_ptr))
-		goto unlock;
-
-	/*
+	 *
 	 * If dst and source tasks are in the same NUMA group, or not
 	 * in any group then look only at task weights.
 	 */
@@ -1662,6 +1807,19 @@ static void task_numa_compare(struct task_numa_env *env,
 			       task_weight(cur, env->dst_nid, dist);
 	}
 
+	/* Discourage picking a task already on its preferred node */
+	if (cur->numa_preferred_nid == env->dst_nid)
+		imp -= imp / 16;
+
+	/*
+	 * Encourage picking a task that moves to its preferred node.
+	 * This potentially makes imp larger than it's maximum of
+	 * 1998 (see SMALLIMP and task_weight for why) but in this
+	 * case, it does not matter.
+	 */
+	if (cur->numa_preferred_nid == env->src_nid)
+		imp += imp / 8;
+
 	if (maymove && moveimp > imp && moveimp > env->best_imp) {
 		imp = moveimp;
 		cur = NULL;
@@ -1669,6 +1827,15 @@ static void task_numa_compare(struct task_numa_env *env,
 	}
 
 	/*
+	 * Prefer swapping with a task moving to its preferred node over a
+	 * task that is not.
+	 */
+	if (env->best_task && cur->numa_preferred_nid == env->src_nid &&
+	    env->best_task->numa_preferred_nid != env->src_nid) {
+		goto assign;
+	}
+
+	/*
 	 * If the NUMA importance is less than SMALLIMP,
 	 * task migration might only result in ping pong
 	 * of tasks and also hurt performance due to cache
@@ -1691,42 +1858,95 @@ static void task_numa_compare(struct task_numa_env *env,
 		goto unlock;
 
 assign:
-	/*
-	 * One idle CPU per node is evaluated for a task numa move.
-	 * Call select_idle_sibling to maybe find a better one.
-	 */
+	/* Evaluate an idle CPU for a task numa move. */
 	if (!cur) {
+		int cpu = env->dst_stats.idle_cpu;
+
+		/* Nothing cached so current CPU went idle since the search. */
+		if (cpu < 0)
+			cpu = env->dst_cpu;
+
 		/*
-		 * select_idle_siblings() uses an per-CPU cpumask that
-		 * can be used from IRQ context.
+		 * If the CPU is no longer truly idle and the previous best CPU
+		 * is, keep using it.
 		 */
-		local_irq_disable();
-		env->dst_cpu = select_idle_sibling(env->p, env->src_cpu,
-						   env->dst_cpu);
-		local_irq_enable();
+		if (!idle_cpu(cpu) && env->best_cpu >= 0 &&
+		    idle_cpu(env->best_cpu)) {
+			cpu = env->best_cpu;
+		}
+
+		env->dst_cpu = cpu;
 	}
 
 	task_numa_assign(env, cur, imp);
+
+	/*
+	 * If a move to idle is allowed because there is capacity or load
+	 * balance improves then stop the search. While a better swap
+	 * candidate may exist, a search is not free.
+	 */
+	if (maymove && !cur && env->best_cpu >= 0 && idle_cpu(env->best_cpu))
+		stopsearch = true;
+
+	/*
+	 * If a swap candidate must be identified and the current best task
+	 * moves its preferred node then stop the search.
+	 */
+	if (!maymove && env->best_task &&
+	    env->best_task->numa_preferred_nid == env->src_nid) {
+		stopsearch = true;
+	}
 unlock:
 	rcu_read_unlock();
+
+	return stopsearch;
 }
 
 static void task_numa_find_cpu(struct task_numa_env *env,
 				long taskimp, long groupimp)
 {
-	long src_load, dst_load, load;
 	bool maymove = false;
 	int cpu;
 
-	load = task_h_load(env->p);
-	dst_load = env->dst_stats.load + load;
-	src_load = env->src_stats.load - load;
-
 	/*
-	 * If the improvement from just moving env->p direction is better
-	 * than swapping tasks around, check if a move is possible.
+	 * If dst node has spare capacity, then check if there is an
+	 * imbalance that would be overruled by the load balancer.
 	 */
-	maymove = !load_too_imbalanced(src_load, dst_load, env);
+	if (env->dst_stats.node_type == node_has_spare) {
+		unsigned int imbalance;
+		int src_running, dst_running;
+
+		/*
+		 * Would movement cause an imbalance? Note that if src has
+		 * more running tasks that the imbalance is ignored as the
+		 * move improves the imbalance from the perspective of the
+		 * CPU load balancer.
+		 * */
+		src_running = env->src_stats.nr_running - 1;
+		dst_running = env->dst_stats.nr_running + 1;
+		imbalance = max(0, dst_running - src_running);
+		imbalance = adjust_numa_imbalance(imbalance, src_running);
+
+		/* Use idle CPU if there is no imbalance */
+		if (!imbalance) {
+			maymove = true;
+			if (env->dst_stats.idle_cpu >= 0) {
+				env->dst_cpu = env->dst_stats.idle_cpu;
+				task_numa_assign(env, NULL, 0);
+				return;
+			}
+		}
+	} else {
+		long src_load, dst_load, load;
+		/*
+		 * If the improvement from just moving env->p direction is better
+		 * than swapping tasks around, check if a move is possible.
+		 */
+		load = task_h_load(env->p);
+		dst_load = env->dst_stats.load + load;
+		src_load = env->src_stats.load - load;
+		maymove = !load_too_imbalanced(src_load, dst_load, env);
+	}
 
 	for_each_cpu(cpu, cpumask_of_node(env->dst_nid)) {
 		/* Skip this CPU if the source task cannot migrate */
@@ -1734,7 +1954,8 @@ static void task_numa_find_cpu(struct task_numa_env *env,
 			continue;
 
 		env->dst_cpu = cpu;
-		task_numa_compare(env, taskimp, groupimp, maymove);
+		if (task_numa_compare(env, taskimp, groupimp, maymove))
+			break;
 	}
 }
 
@@ -1788,10 +2009,10 @@ static int task_numa_migrate(struct task_struct *p)
 	dist = env.dist = node_distance(env.src_nid, env.dst_nid);
 	taskweight = task_weight(p, env.src_nid, dist);
 	groupweight = group_weight(p, env.src_nid, dist);
-	update_numa_stats(&env.src_stats, env.src_nid);
+	update_numa_stats(&env, &env.src_stats, env.src_nid, false);
 	taskimp = task_weight(p, env.dst_nid, dist) - taskweight;
 	groupimp = group_weight(p, env.dst_nid, dist) - groupweight;
-	update_numa_stats(&env.dst_stats, env.dst_nid);
+	update_numa_stats(&env, &env.dst_stats, env.dst_nid, true);
 
 	/* Try to find a spot on the preferred nid. */
 	task_numa_find_cpu(&env, taskimp, groupimp);
@@ -1824,7 +2045,7 @@ static int task_numa_migrate(struct task_struct *p)
 
 			env.dist = dist;
 			env.dst_nid = nid;
-			update_numa_stats(&env.dst_stats, env.dst_nid);
+			update_numa_stats(&env, &env.dst_stats, env.dst_nid, true);
 			task_numa_find_cpu(&env, taskimp, groupimp);
 		}
 	}
@@ -1848,15 +2069,17 @@ static int task_numa_migrate(struct task_struct *p)
 	}
 
 	/* No better CPU than the current one was found. */
-	if (env.best_cpu == -1)
+	if (env.best_cpu == -1) {
+		trace_sched_stick_numa(p, env.src_cpu, NULL, -1);
 		return -EAGAIN;
+	}
 
 	best_rq = cpu_rq(env.best_cpu);
 	if (env.best_task == NULL) {
 		ret = migrate_task_to(p, env.best_cpu);
 		WRITE_ONCE(best_rq->numa_migrate_on, 0);
 		if (ret != 0)
-			trace_sched_stick_numa(p, env.src_cpu, env.best_cpu);
+			trace_sched_stick_numa(p, env.src_cpu, NULL, env.best_cpu);
 		return ret;
 	}
 
@@ -1864,7 +2087,7 @@ static int task_numa_migrate(struct task_struct *p)
 	WRITE_ONCE(best_rq->numa_migrate_on, 0);
 
 	if (ret != 0)
-		trace_sched_stick_numa(p, env.src_cpu, task_cpu(env.best_task));
+		trace_sched_stick_numa(p, env.src_cpu, env.best_task, env.best_cpu);
 	put_task_struct(env.best_task);
 	return ret;
 }
@@ -2545,7 +2768,7 @@ static void task_numa_work(struct callback_head *work)
 		return;
 
 
-	if (!down_read_trylock(&mm->mmap_sem))
+	if (!mmap_read_trylock(mm))
 		return;
 	vma = find_vma(mm, start);
 	if (!vma) {
@@ -2573,7 +2796,7 @@ static void task_numa_work(struct callback_head *work)
 		 * Skip inaccessible VMAs to avoid any confusion between
 		 * PROT_NONE and NUMA hinting ptes
 		 */
-		if (!(vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE)))
+		if (!vma_is_accessible(vma))
 			continue;
 
 		do {
@@ -2613,7 +2836,7 @@ out:
 		mm->numa_scan_offset = start;
 	else
 		reset_ptenuma_scan(p);
-	up_read(&mm->mmap_sem);
+	mmap_read_unlock(mm);
 
 	/*
 	 * Make sure tasks use at least 32x as much time to run other code
@@ -2682,7 +2905,7 @@ static void task_tick_numa(struct rq *rq, struct task_struct *curr)
 	/*
 	 * We don't care about NUMA placement if we don't have memory.
 	 */
-	if (!curr->mm || (curr->flags & PF_EXITING) || work->next != work)
+	if ((curr->flags & (PF_EXITING | PF_KTHREAD)) || work->next != work)
 		return;
 
 	/*
@@ -2835,25 +3058,6 @@ account_entity_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se)
 
 #ifdef CONFIG_SMP
 static inline void
-enqueue_runnable_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
-{
-	cfs_rq->runnable_weight += se->runnable_weight;
-
-	cfs_rq->avg.runnable_load_avg += se->avg.runnable_load_avg;
-	cfs_rq->avg.runnable_load_sum += se_runnable(se) * se->avg.runnable_load_sum;
-}
-
-static inline void
-dequeue_runnable_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
-{
-	cfs_rq->runnable_weight -= se->runnable_weight;
-
-	sub_positive(&cfs_rq->avg.runnable_load_avg, se->avg.runnable_load_avg);
-	sub_positive(&cfs_rq->avg.runnable_load_sum,
-		     se_runnable(se) * se->avg.runnable_load_sum);
-}
-
-static inline void
 enqueue_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
 	cfs_rq->avg.load_avg += se->avg.load_avg;
@@ -2868,45 +3072,36 @@ dequeue_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
 }
 #else
 static inline void
-enqueue_runnable_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) { }
-static inline void
-dequeue_runnable_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) { }
-static inline void
 enqueue_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) { }
 static inline void
 dequeue_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) { }
 #endif
 
 static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se,
-			    unsigned long weight, unsigned long runnable)
+			    unsigned long weight)
 {
 	if (se->on_rq) {
 		/* commit outstanding execution time */
 		if (cfs_rq->curr == se)
 			update_curr(cfs_rq);
 		account_entity_dequeue(cfs_rq, se);
-		dequeue_runnable_load_avg(cfs_rq, se);
 	}
 	dequeue_load_avg(cfs_rq, se);
 
-	se->runnable_weight = runnable;
 	update_load_set(&se->load, weight);
 
 #ifdef CONFIG_SMP
 	do {
-		u32 divider = LOAD_AVG_MAX - 1024 + se->avg.period_contrib;
+		u32 divider = get_pelt_divider(&se->avg);
 
 		se->avg.load_avg = div_u64(se_weight(se) * se->avg.load_sum, divider);
-		se->avg.runnable_load_avg =
-			div_u64(se_runnable(se) * se->avg.runnable_load_sum, divider);
 	} while (0);
 #endif
 
 	enqueue_load_avg(cfs_rq, se);
-	if (se->on_rq) {
+	if (se->on_rq)
 		account_entity_enqueue(cfs_rq, se);
-		enqueue_runnable_load_avg(cfs_rq, se);
-	}
+
 }
 
 void reweight_task(struct task_struct *p, int prio)
@@ -2916,7 +3111,7 @@ void reweight_task(struct task_struct *p, int prio)
 	struct load_weight *load = &se->load;
 	unsigned long weight = scale_load(sched_prio_to_weight[prio]);
 
-	reweight_entity(cfs_rq, se, weight, weight);
+	reweight_entity(cfs_rq, se, weight);
 	load->inv_weight = sched_prio_to_wmult[prio];
 }
 
@@ -3028,50 +3223,6 @@ static long calc_group_shares(struct cfs_rq *cfs_rq)
 	 */
 	return clamp_t(long, shares, MIN_SHARES, tg_shares);
 }
-
-/*
- * This calculates the effective runnable weight for a group entity based on
- * the group entity weight calculated above.
- *
- * Because of the above approximation (2), our group entity weight is
- * an load_avg based ratio (3). This means that it includes blocked load and
- * does not represent the runnable weight.
- *
- * Approximate the group entity's runnable weight per ratio from the group
- * runqueue:
- *
- *					     grq->avg.runnable_load_avg
- *   ge->runnable_weight = ge->load.weight * -------------------------- (7)
- *						 grq->avg.load_avg
- *
- * However, analogous to above, since the avg numbers are slow, this leads to
- * transients in the from-idle case. Instead we use:
- *
- *   ge->runnable_weight = ge->load.weight *
- *
- *		max(grq->avg.runnable_load_avg, grq->runnable_weight)
- *		-----------------------------------------------------	(8)
- *		      max(grq->avg.load_avg, grq->load.weight)
- *
- * Where these max() serve both to use the 'instant' values to fix the slow
- * from-idle and avoid the /0 on to-idle, similar to (6).
- */
-static long calc_group_runnable(struct cfs_rq *cfs_rq, long shares)
-{
-	long runnable, load_avg;
-
-	load_avg = max(cfs_rq->avg.load_avg,
-		       scale_load_down(cfs_rq->load.weight));
-
-	runnable = max(cfs_rq->avg.runnable_load_avg,
-		       scale_load_down(cfs_rq->runnable_weight));
-
-	runnable *= shares;
-	if (load_avg)
-		runnable /= load_avg;
-
-	return clamp_t(long, runnable, MIN_SHARES, shares);
-}
 #endif /* CONFIG_SMP */
 
 static inline int throttled_hierarchy(struct cfs_rq *cfs_rq);
@@ -3083,7 +3234,7 @@ static inline int throttled_hierarchy(struct cfs_rq *cfs_rq);
 static void update_cfs_group(struct sched_entity *se)
 {
 	struct cfs_rq *gcfs_rq = group_cfs_rq(se);
-	long shares, runnable;
+	long shares;
 
 	if (!gcfs_rq)
 		return;
@@ -3092,16 +3243,15 @@ static void update_cfs_group(struct sched_entity *se)
 		return;
 
 #ifndef CONFIG_SMP
-	runnable = shares = READ_ONCE(gcfs_rq->tg->shares);
+	shares = READ_ONCE(gcfs_rq->tg->shares);
 
 	if (likely(se->load.weight == shares))
 		return;
 #else
 	shares   = calc_group_shares(gcfs_rq);
-	runnable = calc_group_runnable(gcfs_rq, shares);
 #endif
 
-	reweight_entity(cfs_rq_of(se), se, shares, runnable);
+	reweight_entity(cfs_rq_of(se), se, shares);
 }
 
 #else /* CONFIG_FAIR_GROUP_SCHED */
@@ -3226,11 +3376,11 @@ void set_task_rq_fair(struct sched_entity *se,
  * _IFF_ we look at the pure running and runnable sums. Because they
  * represent the very same entity, just at different points in the hierarchy.
  *
- * Per the above update_tg_cfs_util() is trivial and simply copies the running
- * sum over (but still wrong, because the group entity and group rq do not have
- * their PELT windows aligned).
+ * Per the above update_tg_cfs_util() and update_tg_cfs_runnable() are trivial
+ * and simply copies the running/runnable sum over (but still wrong, because
+ * the group entity and group rq do not have their PELT windows aligned).
  *
- * However, update_tg_cfs_runnable() is more complex. So we have:
+ * However, update_tg_cfs_load() is more complex. So we have:
  *
  *   ge->avg.load_avg = ge->load.weight * ge->avg.runnable_avg		(2)
  *
@@ -3288,48 +3438,79 @@ static inline void
 update_tg_cfs_util(struct cfs_rq *cfs_rq, struct sched_entity *se, struct cfs_rq *gcfs_rq)
 {
 	long delta = gcfs_rq->avg.util_avg - se->avg.util_avg;
+	u32 divider;
 
 	/* Nothing to update */
 	if (!delta)
 		return;
 
 	/*
-	 * The relation between sum and avg is:
-	 *
-	 *   LOAD_AVG_MAX - 1024 + sa->period_contrib
-	 *
-	 * however, the PELT windows are not aligned between grq and gse.
+	 * cfs_rq->avg.period_contrib can be used for both cfs_rq and se.
+	 * See ___update_load_avg() for details.
 	 */
+	divider = get_pelt_divider(&cfs_rq->avg);
 
 	/* Set new sched_entity's utilization */
 	se->avg.util_avg = gcfs_rq->avg.util_avg;
-	se->avg.util_sum = se->avg.util_avg * LOAD_AVG_MAX;
+	se->avg.util_sum = se->avg.util_avg * divider;
 
 	/* Update parent cfs_rq utilization */
 	add_positive(&cfs_rq->avg.util_avg, delta);
-	cfs_rq->avg.util_sum = cfs_rq->avg.util_avg * LOAD_AVG_MAX;
+	cfs_rq->avg.util_sum = cfs_rq->avg.util_avg * divider;
 }
 
 static inline void
 update_tg_cfs_runnable(struct cfs_rq *cfs_rq, struct sched_entity *se, struct cfs_rq *gcfs_rq)
 {
+	long delta = gcfs_rq->avg.runnable_avg - se->avg.runnable_avg;
+	u32 divider;
+
+	/* Nothing to update */
+	if (!delta)
+		return;
+
+	/*
+	 * cfs_rq->avg.period_contrib can be used for both cfs_rq and se.
+	 * See ___update_load_avg() for details.
+	 */
+	divider = get_pelt_divider(&cfs_rq->avg);
+
+	/* Set new sched_entity's runnable */
+	se->avg.runnable_avg = gcfs_rq->avg.runnable_avg;
+	se->avg.runnable_sum = se->avg.runnable_avg * divider;
+
+	/* Update parent cfs_rq runnable */
+	add_positive(&cfs_rq->avg.runnable_avg, delta);
+	cfs_rq->avg.runnable_sum = cfs_rq->avg.runnable_avg * divider;
+}
+
+static inline void
+update_tg_cfs_load(struct cfs_rq *cfs_rq, struct sched_entity *se, struct cfs_rq *gcfs_rq)
+{
 	long delta_avg, running_sum, runnable_sum = gcfs_rq->prop_runnable_sum;
-	unsigned long runnable_load_avg, load_avg;
-	u64 runnable_load_sum, load_sum = 0;
+	unsigned long load_avg;
+	u64 load_sum = 0;
 	s64 delta_sum;
+	u32 divider;
 
 	if (!runnable_sum)
 		return;
 
 	gcfs_rq->prop_runnable_sum = 0;
 
+	/*
+	 * cfs_rq->avg.period_contrib can be used for both cfs_rq and se.
+	 * See ___update_load_avg() for details.
+	 */
+	divider = get_pelt_divider(&cfs_rq->avg);
+
 	if (runnable_sum >= 0) {
 		/*
 		 * Add runnable; clip at LOAD_AVG_MAX. Reflects that until
 		 * the CPU is saturated running == runnable.
 		 */
 		runnable_sum += se->avg.load_sum;
-		runnable_sum = min(runnable_sum, (long)LOAD_AVG_MAX);
+		runnable_sum = min_t(long, runnable_sum, divider);
 	} else {
 		/*
 		 * Estimate the new unweighted runnable_sum of the gcfs_rq by
@@ -3354,7 +3535,7 @@ update_tg_cfs_runnable(struct cfs_rq *cfs_rq, struct sched_entity *se, struct cf
 	runnable_sum = max(runnable_sum, running_sum);
 
 	load_sum = (s64)se_weight(se) * runnable_sum;
-	load_avg = div_s64(load_sum, LOAD_AVG_MAX);
+	load_avg = div_s64(load_sum, divider);
 
 	delta_sum = load_sum - (s64)se_weight(se) * se->avg.load_sum;
 	delta_avg = load_avg - se->avg.load_avg;
@@ -3363,20 +3544,6 @@ update_tg_cfs_runnable(struct cfs_rq *cfs_rq, struct sched_entity *se, struct cf
 	se->avg.load_avg = load_avg;
 	add_positive(&cfs_rq->avg.load_avg, delta_avg);
 	add_positive(&cfs_rq->avg.load_sum, delta_sum);
-
-	runnable_load_sum = (s64)se_runnable(se) * runnable_sum;
-	runnable_load_avg = div_s64(runnable_load_sum, LOAD_AVG_MAX);
-
-	if (se->on_rq) {
-		delta_sum = runnable_load_sum -
-				se_weight(se) * se->avg.runnable_load_sum;
-		delta_avg = runnable_load_avg - se->avg.runnable_load_avg;
-		add_positive(&cfs_rq->avg.runnable_load_avg, delta_avg);
-		add_positive(&cfs_rq->avg.runnable_load_sum, delta_sum);
-	}
-
-	se->avg.runnable_load_sum = runnable_sum;
-	se->avg.runnable_load_avg = runnable_load_avg;
 }
 
 static inline void add_tg_cfs_propagate(struct cfs_rq *cfs_rq, long runnable_sum)
@@ -3405,6 +3572,7 @@ static inline int propagate_entity_load_avg(struct sched_entity *se)
 
 	update_tg_cfs_util(cfs_rq, se, gcfs_rq);
 	update_tg_cfs_runnable(cfs_rq, se, gcfs_rq);
+	update_tg_cfs_load(cfs_rq, se, gcfs_rq);
 
 	trace_pelt_cfs_tp(cfs_rq);
 	trace_pelt_se_tp(se);
@@ -3474,18 +3642,18 @@ static inline void add_tg_cfs_propagate(struct cfs_rq *cfs_rq, long runnable_sum
 static inline int
 update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq)
 {
-	unsigned long removed_load = 0, removed_util = 0, removed_runnable_sum = 0;
+	unsigned long removed_load = 0, removed_util = 0, removed_runnable = 0;
 	struct sched_avg *sa = &cfs_rq->avg;
 	int decayed = 0;
 
 	if (cfs_rq->removed.nr) {
 		unsigned long r;
-		u32 divider = LOAD_AVG_MAX - 1024 + sa->period_contrib;
+		u32 divider = get_pelt_divider(&cfs_rq->avg);
 
 		raw_spin_lock(&cfs_rq->removed.lock);
 		swap(cfs_rq->removed.util_avg, removed_util);
 		swap(cfs_rq->removed.load_avg, removed_load);
-		swap(cfs_rq->removed.runnable_sum, removed_runnable_sum);
+		swap(cfs_rq->removed.runnable_avg, removed_runnable);
 		cfs_rq->removed.nr = 0;
 		raw_spin_unlock(&cfs_rq->removed.lock);
 
@@ -3497,7 +3665,16 @@ update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq)
 		sub_positive(&sa->util_avg, r);
 		sub_positive(&sa->util_sum, r * divider);
 
-		add_tg_cfs_propagate(cfs_rq, -(long)removed_runnable_sum);
+		r = removed_runnable;
+		sub_positive(&sa->runnable_avg, r);
+		sub_positive(&sa->runnable_sum, r * divider);
+
+		/*
+		 * removed_runnable is the unweighted version of removed_load so we
+		 * can use it to estimate removed_load_sum.
+		 */
+		add_tg_cfs_propagate(cfs_rq,
+			-(long)(removed_runnable * divider) >> SCHED_CAPACITY_SHIFT);
 
 		decayed = 1;
 	}
@@ -3522,7 +3699,11 @@ update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq)
  */
 static void attach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
-	u32 divider = LOAD_AVG_MAX - 1024 + cfs_rq->avg.period_contrib;
+	/*
+	 * cfs_rq->avg.period_contrib can be used for both cfs_rq and se.
+	 * See ___update_load_avg() for details.
+	 */
+	u32 divider = get_pelt_divider(&cfs_rq->avg);
 
 	/*
 	 * When we attach the @se to the @cfs_rq, we must align the decay
@@ -3542,17 +3723,19 @@ static void attach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *s
 	 */
 	se->avg.util_sum = se->avg.util_avg * divider;
 
+	se->avg.runnable_sum = se->avg.runnable_avg * divider;
+
 	se->avg.load_sum = divider;
 	if (se_weight(se)) {
 		se->avg.load_sum =
 			div_u64(se->avg.load_avg * se->avg.load_sum, se_weight(se));
 	}
 
-	se->avg.runnable_load_sum = se->avg.load_sum;
-
 	enqueue_load_avg(cfs_rq, se);
 	cfs_rq->avg.util_avg += se->avg.util_avg;
 	cfs_rq->avg.util_sum += se->avg.util_sum;
+	cfs_rq->avg.runnable_avg += se->avg.runnable_avg;
+	cfs_rq->avg.runnable_sum += se->avg.runnable_sum;
 
 	add_tg_cfs_propagate(cfs_rq, se->avg.load_sum);
 
@@ -3574,6 +3757,8 @@ static void detach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *s
 	dequeue_load_avg(cfs_rq, se);
 	sub_positive(&cfs_rq->avg.util_avg, se->avg.util_avg);
 	sub_positive(&cfs_rq->avg.util_sum, se->avg.util_sum);
+	sub_positive(&cfs_rq->avg.runnable_avg, se->avg.runnable_avg);
+	sub_positive(&cfs_rq->avg.runnable_sum, se->avg.runnable_sum);
 
 	add_tg_cfs_propagate(cfs_rq, -se->avg.load_sum);
 
@@ -3680,13 +3865,13 @@ static void remove_entity_load_avg(struct sched_entity *se)
 	++cfs_rq->removed.nr;
 	cfs_rq->removed.util_avg	+= se->avg.util_avg;
 	cfs_rq->removed.load_avg	+= se->avg.load_avg;
-	cfs_rq->removed.runnable_sum	+= se->avg.load_sum; /* == runnable_sum */
+	cfs_rq->removed.runnable_avg	+= se->avg.runnable_avg;
 	raw_spin_unlock_irqrestore(&cfs_rq->removed.lock, flags);
 }
 
-static inline unsigned long cfs_rq_runnable_load_avg(struct cfs_rq *cfs_rq)
+static inline unsigned long cfs_rq_runnable_avg(struct cfs_rq *cfs_rq)
 {
-	return cfs_rq->avg.runnable_load_avg;
+	return cfs_rq->avg.runnable_avg;
 }
 
 static inline unsigned long cfs_rq_load_avg(struct cfs_rq *cfs_rq)
@@ -3694,6 +3879,8 @@ static inline unsigned long cfs_rq_load_avg(struct cfs_rq *cfs_rq)
 	return cfs_rq->avg.load_avg;
 }
 
+static int newidle_balance(struct rq *this_rq, struct rq_flags *rf);
+
 static inline unsigned long task_util(struct task_struct *p)
 {
 	return READ_ONCE(p->se.avg.util_avg);
@@ -3737,6 +3924,8 @@ static inline void util_est_enqueue(struct cfs_rq *cfs_rq,
 	enqueued  = cfs_rq->avg.util_est.enqueued;
 	enqueued += _task_util_est(p);
 	WRITE_ONCE(cfs_rq->avg.util_est.enqueued, enqueued);
+
+	trace_sched_util_est_cfs_tp(cfs_rq);
 }
 
 /*
@@ -3767,6 +3956,8 @@ util_est_dequeue(struct cfs_rq *cfs_rq, struct task_struct *p, bool task_sleep)
 	ue.enqueued -= min_t(unsigned int, ue.enqueued, _task_util_est(p));
 	WRITE_ONCE(cfs_rq->avg.util_est.enqueued, ue.enqueued);
 
+	trace_sched_util_est_cfs_tp(cfs_rq);
+
 	/*
 	 * Skip update of task's estimated utilization when the task has not
 	 * yet completed an activation, e.g. being migrated.
@@ -3832,6 +4023,8 @@ util_est_dequeue(struct cfs_rq *cfs_rq, struct task_struct *p, bool task_sleep)
 	ue.ewma >>= UTIL_EST_WEIGHT_SHIFT;
 done:
 	WRITE_ONCE(p->se.avg.util_est, ue);
+
+	trace_sched_util_est_se_tp(&p->se);
 }
 
 static inline int task_fits_capacity(struct task_struct *p, long capacity)
@@ -3854,7 +4047,11 @@ static inline void update_misfit_status(struct task_struct *p, struct rq *rq)
 		return;
 	}
 
-	rq->misfit_task_load = task_h_load(p);
+	/*
+	 * Make sure that misfit_task_load will not be null even if
+	 * task_h_load() returns 0.
+	 */
+	rq->misfit_task_load = max_t(unsigned long, task_h_load(p), 1);
 }
 
 #else /* CONFIG_SMP */
@@ -3875,7 +4072,7 @@ attach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) {}
 static inline void
 detach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) {}
 
-static inline int idle_balance(struct rq *rq, struct rq_flags *rf)
+static inline int newidle_balance(struct rq *rq, struct rq_flags *rf)
 {
 	return 0;
 }
@@ -3957,6 +4154,7 @@ static inline void check_schedstat_required(void)
 #endif
 }
 
+static inline bool cfs_bandwidth_used(void);
 
 /*
  * MIGRATION
@@ -4021,8 +4219,8 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 	 *   - Add its new weight to cfs_rq->load.weight
 	 */
 	update_load_avg(cfs_rq, se, UPDATE_TG | DO_ATTACH);
+	se_update_runnable(se);
 	update_cfs_group(se);
-	enqueue_runnable_load_avg(cfs_rq, se);
 	account_entity_enqueue(cfs_rq, se);
 
 	if (flags & ENQUEUE_WAKEUP)
@@ -4035,10 +4233,16 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 		__enqueue_entity(cfs_rq, se);
 	se->on_rq = 1;
 
-	if (cfs_rq->nr_running == 1) {
+	/*
+	 * When bandwidth control is enabled, cfs might have been removed
+	 * because of a parent been throttled but cfs->nr_running > 1. Try to
+	 * add it unconditionnally.
+	 */
+	if (cfs_rq->nr_running == 1 || cfs_bandwidth_used())
 		list_add_leaf_cfs_rq(cfs_rq);
+
+	if (cfs_rq->nr_running == 1)
 		check_enqueue_throttle(cfs_rq);
-	}
 }
 
 static void __clear_buddies_last(struct sched_entity *se)
@@ -4105,7 +4309,7 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 	 *     of its group cfs_rq.
 	 */
 	update_load_avg(cfs_rq, se, UPDATE_TG);
-	dequeue_runnable_load_avg(cfs_rq, se);
+	se_update_runnable(se);
 
 	update_stats_dequeue(cfs_rq, se, flags);
 
@@ -4402,16 +4606,16 @@ static inline struct cfs_bandwidth *tg_cfs_bandwidth(struct task_group *tg)
 }
 
 /* returns 0 on failure to allocate runtime */
-static int assign_cfs_rq_runtime(struct cfs_rq *cfs_rq)
+static int __assign_cfs_rq_runtime(struct cfs_bandwidth *cfs_b,
+				   struct cfs_rq *cfs_rq, u64 target_runtime)
 {
-	struct task_group *tg = cfs_rq->tg;
-	struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(tg);
-	u64 amount = 0, min_amount;
+	u64 min_amount, amount = 0;
+
+	lockdep_assert_held(&cfs_b->lock);
 
 	/* note: this is a positive sum as runtime_remaining <= 0 */
-	min_amount = sched_cfs_bandwidth_slice() - cfs_rq->runtime_remaining;
+	min_amount = target_runtime - cfs_rq->runtime_remaining;
 
-	raw_spin_lock(&cfs_b->lock);
 	if (cfs_b->quota == RUNTIME_INF)
 		amount = min_amount;
 	else {
@@ -4423,13 +4627,25 @@ static int assign_cfs_rq_runtime(struct cfs_rq *cfs_rq)
 			cfs_b->idle = 0;
 		}
 	}
-	raw_spin_unlock(&cfs_b->lock);
 
 	cfs_rq->runtime_remaining += amount;
 
 	return cfs_rq->runtime_remaining > 0;
 }
 
+/* returns 0 on failure to allocate runtime */
+static int assign_cfs_rq_runtime(struct cfs_rq *cfs_rq)
+{
+	struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg);
+	int ret;
+
+	raw_spin_lock(&cfs_b->lock);
+	ret = __assign_cfs_rq_runtime(cfs_b, cfs_rq, sched_cfs_bandwidth_slice());
+	raw_spin_unlock(&cfs_b->lock);
+
+	return ret;
+}
+
 static void __account_cfs_rq_runtime(struct cfs_rq *cfs_rq, u64 delta_exec)
 {
 	/* dock delta_exec before expiring quota (as it could span periods) */
@@ -4518,13 +4734,33 @@ static int tg_throttle_down(struct task_group *tg, void *data)
 	return 0;
 }
 
-static void throttle_cfs_rq(struct cfs_rq *cfs_rq)
+static bool throttle_cfs_rq(struct cfs_rq *cfs_rq)
 {
 	struct rq *rq = rq_of(cfs_rq);
 	struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg);
 	struct sched_entity *se;
 	long task_delta, idle_task_delta, dequeue = 1;
-	bool empty;
+
+	raw_spin_lock(&cfs_b->lock);
+	/* This will start the period timer if necessary */
+	if (__assign_cfs_rq_runtime(cfs_b, cfs_rq, 1)) {
+		/*
+		 * We have raced with bandwidth becoming available, and if we
+		 * actually throttled the timer might not unthrottle us for an
+		 * entire period. We additionally needed to make sure that any
+		 * subsequent check_cfs_rq_runtime calls agree not to throttle
+		 * us, as we may commit to do cfs put_prev+pick_next, so we ask
+		 * for 1ns of runtime rather than just check cfs_b.
+		 */
+		dequeue = 0;
+	} else {
+		list_add_tail_rcu(&cfs_rq->throttled_list,
+				  &cfs_b->throttled_cfs_rq);
+	}
+	raw_spin_unlock(&cfs_b->lock);
+
+	if (!dequeue)
+		return false;  /* Throttle no longer required. */
 
 	se = cfs_rq->tg->se[cpu_of(rq_of(cfs_rq))];
 
@@ -4541,8 +4777,13 @@ static void throttle_cfs_rq(struct cfs_rq *cfs_rq)
 		if (!se->on_rq)
 			break;
 
-		if (dequeue)
+		if (dequeue) {
 			dequeue_entity(qcfs_rq, se, DEQUEUE_SLEEP);
+		} else {
+			update_load_avg(qcfs_rq, se, 0);
+			se_update_runnable(se);
+		}
+
 		qcfs_rq->h_nr_running -= task_delta;
 		qcfs_rq->idle_h_nr_running -= idle_task_delta;
 
@@ -4553,29 +4794,13 @@ static void throttle_cfs_rq(struct cfs_rq *cfs_rq)
 	if (!se)
 		sub_nr_running(rq, task_delta);
 
-	cfs_rq->throttled = 1;
-	cfs_rq->throttled_clock = rq_clock(rq);
-	raw_spin_lock(&cfs_b->lock);
-	empty = list_empty(&cfs_b->throttled_cfs_rq);
-
 	/*
-	 * Add to the _head_ of the list, so that an already-started
-	 * distribute_cfs_runtime will not see us. If disribute_cfs_runtime is
-	 * not running add to the tail so that later runqueues don't get starved.
+	 * Note: distribution will already see us throttled via the
+	 * throttled-list.  rq->lock protects completion.
 	 */
-	if (cfs_b->distribute_running)
-		list_add_rcu(&cfs_rq->throttled_list, &cfs_b->throttled_cfs_rq);
-	else
-		list_add_tail_rcu(&cfs_rq->throttled_list, &cfs_b->throttled_cfs_rq);
-
-	/*
-	 * If we're the first throttled task, make sure the bandwidth
-	 * timer is running.
-	 */
-	if (empty)
-		start_cfs_bandwidth(cfs_b);
-
-	raw_spin_unlock(&cfs_b->lock);
+	cfs_rq->throttled = 1;
+	cfs_rq->throttled_clock = rq_clock(rq);
+	return true;
 }
 
 void unthrottle_cfs_rq(struct cfs_rq *cfs_rq)
@@ -4583,7 +4808,6 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq)
 	struct rq *rq = rq_of(cfs_rq);
 	struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg);
 	struct sched_entity *se;
-	int enqueue = 1;
 	long task_delta, idle_task_delta;
 
 	se = cfs_rq->tg->se[cpu_of(rq)];
@@ -4607,33 +4831,67 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq)
 	idle_task_delta = cfs_rq->idle_h_nr_running;
 	for_each_sched_entity(se) {
 		if (se->on_rq)
-			enqueue = 0;
+			break;
+		cfs_rq = cfs_rq_of(se);
+		enqueue_entity(cfs_rq, se, ENQUEUE_WAKEUP);
 
+		cfs_rq->h_nr_running += task_delta;
+		cfs_rq->idle_h_nr_running += idle_task_delta;
+
+		/* end evaluation on encountering a throttled cfs_rq */
+		if (cfs_rq_throttled(cfs_rq))
+			goto unthrottle_throttle;
+	}
+
+	for_each_sched_entity(se) {
 		cfs_rq = cfs_rq_of(se);
-		if (enqueue)
-			enqueue_entity(cfs_rq, se, ENQUEUE_WAKEUP);
+
+		update_load_avg(cfs_rq, se, UPDATE_TG);
+		se_update_runnable(se);
+
 		cfs_rq->h_nr_running += task_delta;
 		cfs_rq->idle_h_nr_running += idle_task_delta;
 
+
+		/* end evaluation on encountering a throttled cfs_rq */
 		if (cfs_rq_throttled(cfs_rq))
+			goto unthrottle_throttle;
+
+		/*
+		 * One parent has been throttled and cfs_rq removed from the
+		 * list. Add it back to not break the leaf list.
+		 */
+		if (throttled_hierarchy(cfs_rq))
+			list_add_leaf_cfs_rq(cfs_rq);
+	}
+
+	/* At this point se is NULL and we are at root level*/
+	add_nr_running(rq, task_delta);
+
+unthrottle_throttle:
+	/*
+	 * The cfs_rq_throttled() breaks in the above iteration can result in
+	 * incomplete leaf list maintenance, resulting in triggering the
+	 * assertion below.
+	 */
+	for_each_sched_entity(se) {
+		cfs_rq = cfs_rq_of(se);
+
+		if (list_add_leaf_cfs_rq(cfs_rq))
 			break;
 	}
 
 	assert_list_leaf_cfs_rq(rq);
 
-	if (!se)
-		add_nr_running(rq, task_delta);
-
 	/* Determine whether we need to wake up potentially idle CPU: */
 	if (rq->curr == rq->idle && rq->cfs.nr_running)
 		resched_curr(rq);
 }
 
-static u64 distribute_cfs_runtime(struct cfs_bandwidth *cfs_b, u64 remaining)
+static void distribute_cfs_runtime(struct cfs_bandwidth *cfs_b)
 {
 	struct cfs_rq *cfs_rq;
-	u64 runtime;
-	u64 starting_runtime = remaining;
+	u64 runtime, remaining = 1;
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(cfs_rq, &cfs_b->throttled_cfs_rq,
@@ -4648,10 +4906,13 @@ static u64 distribute_cfs_runtime(struct cfs_bandwidth *cfs_b, u64 remaining)
 		/* By the above check, this should never be true */
 		SCHED_WARN_ON(cfs_rq->runtime_remaining > 0);
 
+		raw_spin_lock(&cfs_b->lock);
 		runtime = -cfs_rq->runtime_remaining + 1;
-		if (runtime > remaining)
-			runtime = remaining;
-		remaining -= runtime;
+		if (runtime > cfs_b->runtime)
+			runtime = cfs_b->runtime;
+		cfs_b->runtime -= runtime;
+		remaining = cfs_b->runtime;
+		raw_spin_unlock(&cfs_b->lock);
 
 		cfs_rq->runtime_remaining += runtime;
 
@@ -4666,8 +4927,6 @@ next:
 			break;
 	}
 	rcu_read_unlock();
-
-	return starting_runtime - remaining;
 }
 
 /*
@@ -4678,7 +4937,6 @@ next:
  */
 static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun, unsigned long flags)
 {
-	u64 runtime;
 	int throttled;
 
 	/* no need to continue the timer with no bandwidth constraint */
@@ -4707,24 +4965,15 @@ static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun, u
 	cfs_b->nr_throttled += overrun;
 
 	/*
-	 * This check is repeated as we are holding onto the new bandwidth while
-	 * we unthrottle. This can potentially race with an unthrottled group
-	 * trying to acquire new bandwidth from the global pool. This can result
-	 * in us over-using our runtime if it is all used during this loop, but
-	 * only by limited amounts in that extreme case.
+	 * This check is repeated as we release cfs_b->lock while we unthrottle.
 	 */
-	while (throttled && cfs_b->runtime > 0 && !cfs_b->distribute_running) {
-		runtime = cfs_b->runtime;
-		cfs_b->distribute_running = 1;
+	while (throttled && cfs_b->runtime > 0) {
 		raw_spin_unlock_irqrestore(&cfs_b->lock, flags);
 		/* we can't nest cfs_b->lock while distributing bandwidth */
-		runtime = distribute_cfs_runtime(cfs_b, runtime);
+		distribute_cfs_runtime(cfs_b);
 		raw_spin_lock_irqsave(&cfs_b->lock, flags);
 
-		cfs_b->distribute_running = 0;
 		throttled = !list_empty(&cfs_b->throttled_cfs_rq);
-
-		lsub_positive(&cfs_b->runtime, runtime);
 	}
 
 	/*
@@ -4837,10 +5086,6 @@ static void do_sched_cfs_slack_timer(struct cfs_bandwidth *cfs_b)
 	/* confirm we're still not at a refresh boundary */
 	raw_spin_lock_irqsave(&cfs_b->lock, flags);
 	cfs_b->slack_started = false;
-	if (cfs_b->distribute_running) {
-		raw_spin_unlock_irqrestore(&cfs_b->lock, flags);
-		return;
-	}
 
 	if (runtime_refresh_within(cfs_b, min_bandwidth_expiration)) {
 		raw_spin_unlock_irqrestore(&cfs_b->lock, flags);
@@ -4850,19 +5095,14 @@ static void do_sched_cfs_slack_timer(struct cfs_bandwidth *cfs_b)
 	if (cfs_b->quota != RUNTIME_INF && cfs_b->runtime > slice)
 		runtime = cfs_b->runtime;
 
-	if (runtime)
-		cfs_b->distribute_running = 1;
-
 	raw_spin_unlock_irqrestore(&cfs_b->lock, flags);
 
 	if (!runtime)
 		return;
 
-	runtime = distribute_cfs_runtime(cfs_b, runtime);
+	distribute_cfs_runtime(cfs_b);
 
 	raw_spin_lock_irqsave(&cfs_b->lock, flags);
-	lsub_positive(&cfs_b->runtime, runtime);
-	cfs_b->distribute_running = 0;
 	raw_spin_unlock_irqrestore(&cfs_b->lock, flags);
 }
 
@@ -4923,8 +5163,7 @@ static bool check_cfs_rq_runtime(struct cfs_rq *cfs_rq)
 	if (cfs_rq_throttled(cfs_rq))
 		return true;
 
-	throttle_cfs_rq(cfs_rq);
-	return true;
+	return throttle_cfs_rq(cfs_rq);
 }
 
 static enum hrtimer_restart sched_cfs_slack_timer(struct hrtimer *timer)
@@ -4954,6 +5193,8 @@ static enum hrtimer_restart sched_cfs_period_timer(struct hrtimer *timer)
 		if (!overrun)
 			break;
 
+		idle = do_sched_cfs_period_timer(cfs_b, overrun, flags);
+
 		if (++count > 3) {
 			u64 new, old = ktime_to_ns(cfs_b->period);
 
@@ -4983,8 +5224,6 @@ static enum hrtimer_restart sched_cfs_period_timer(struct hrtimer *timer)
 			/* reset count so we don't come right back in here */
 			count = 0;
 		}
-
-		idle = do_sched_cfs_period_timer(cfs_b, overrun, flags);
 	}
 	if (idle)
 		cfs_b->period_active = 0;
@@ -5005,7 +5244,6 @@ void init_cfs_bandwidth(struct cfs_bandwidth *cfs_b)
 	cfs_b->period_timer.function = sched_cfs_period_timer;
 	hrtimer_init(&cfs_b->slack_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	cfs_b->slack_timer.function = sched_cfs_slack_timer;
-	cfs_b->distribute_running = 0;
 	cfs_b->slack_started = false;
 }
 
@@ -5258,53 +5496,59 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 		cfs_rq = cfs_rq_of(se);
 		enqueue_entity(cfs_rq, se, flags);
 
-		/*
-		 * end evaluation on encountering a throttled cfs_rq
-		 *
-		 * note: in the case of encountering a throttled cfs_rq we will
-		 * post the final h_nr_running increment below.
-		 */
-		if (cfs_rq_throttled(cfs_rq))
-			break;
 		cfs_rq->h_nr_running++;
 		cfs_rq->idle_h_nr_running += idle_h_nr_running;
 
+		/* end evaluation on encountering a throttled cfs_rq */
+		if (cfs_rq_throttled(cfs_rq))
+			goto enqueue_throttle;
+
 		flags = ENQUEUE_WAKEUP;
 	}
 
 	for_each_sched_entity(se) {
 		cfs_rq = cfs_rq_of(se);
+
+		update_load_avg(cfs_rq, se, UPDATE_TG);
+		se_update_runnable(se);
+		update_cfs_group(se);
+
 		cfs_rq->h_nr_running++;
 		cfs_rq->idle_h_nr_running += idle_h_nr_running;
 
+		/* end evaluation on encountering a throttled cfs_rq */
 		if (cfs_rq_throttled(cfs_rq))
-			break;
+			goto enqueue_throttle;
 
-		update_load_avg(cfs_rq, se, UPDATE_TG);
-		update_cfs_group(se);
+               /*
+                * One parent has been throttled and cfs_rq removed from the
+                * list. Add it back to not break the leaf list.
+                */
+               if (throttled_hierarchy(cfs_rq))
+                       list_add_leaf_cfs_rq(cfs_rq);
 	}
 
-	if (!se) {
-		add_nr_running(rq, 1);
-		/*
-		 * Since new tasks are assigned an initial util_avg equal to
-		 * half of the spare capacity of their CPU, tiny tasks have the
-		 * ability to cross the overutilized threshold, which will
-		 * result in the load balancer ruining all the task placement
-		 * done by EAS. As a way to mitigate that effect, do not account
-		 * for the first enqueue operation of new tasks during the
-		 * overutilized flag detection.
-		 *
-		 * A better way of solving this problem would be to wait for
-		 * the PELT signals of tasks to converge before taking them
-		 * into account, but that is not straightforward to implement,
-		 * and the following generally works well enough in practice.
-		 */
-		if (flags & ENQUEUE_WAKEUP)
-			update_overutilized_status(rq);
+	/* At this point se is NULL and we are at root level*/
+	add_nr_running(rq, 1);
 
-	}
+	/*
+	 * Since new tasks are assigned an initial util_avg equal to
+	 * half of the spare capacity of their CPU, tiny tasks have the
+	 * ability to cross the overutilized threshold, which will
+	 * result in the load balancer ruining all the task placement
+	 * done by EAS. As a way to mitigate that effect, do not account
+	 * for the first enqueue operation of new tasks during the
+	 * overutilized flag detection.
+	 *
+	 * A better way of solving this problem would be to wait for
+	 * the PELT signals of tasks to converge before taking them
+	 * into account, but that is not straightforward to implement,
+	 * and the following generally works well enough in practice.
+	 */
+	if (flags & ENQUEUE_WAKEUP)
+		update_overutilized_status(rq);
 
+enqueue_throttle:
 	if (cfs_bandwidth_used()) {
 		/*
 		 * When bandwidth control is enabled; the cfs_rq_throttled()
@@ -5344,17 +5588,13 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 		cfs_rq = cfs_rq_of(se);
 		dequeue_entity(cfs_rq, se, flags);
 
-		/*
-		 * end evaluation on encountering a throttled cfs_rq
-		 *
-		 * note: in the case of encountering a throttled cfs_rq we will
-		 * post the final h_nr_running decrement below.
-		*/
-		if (cfs_rq_throttled(cfs_rq))
-			break;
 		cfs_rq->h_nr_running--;
 		cfs_rq->idle_h_nr_running -= idle_h_nr_running;
 
+		/* end evaluation on encountering a throttled cfs_rq */
+		if (cfs_rq_throttled(cfs_rq))
+			goto dequeue_throttle;
+
 		/* Don't dequeue parent if it has other entities besides us */
 		if (cfs_rq->load.weight) {
 			/* Avoid re-evaluating load for this entity: */
@@ -5372,23 +5612,28 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 
 	for_each_sched_entity(se) {
 		cfs_rq = cfs_rq_of(se);
+
+		update_load_avg(cfs_rq, se, UPDATE_TG);
+		se_update_runnable(se);
+		update_cfs_group(se);
+
 		cfs_rq->h_nr_running--;
 		cfs_rq->idle_h_nr_running -= idle_h_nr_running;
 
+		/* end evaluation on encountering a throttled cfs_rq */
 		if (cfs_rq_throttled(cfs_rq))
-			break;
+			goto dequeue_throttle;
 
-		update_load_avg(cfs_rq, se, UPDATE_TG);
-		update_cfs_group(se);
 	}
 
-	if (!se)
-		sub_nr_running(rq, 1);
+	/* At this point se is NULL and we are at root level*/
+	sub_nr_running(rq, 1);
 
 	/* balance early to pull high priority tasks */
 	if (unlikely(!was_sched_idle && sched_idle_rq(rq)))
 		rq->next_balance = jiffies;
 
+dequeue_throttle:
 	util_est_dequeue(&rq->cfs, p, task_sleep);
 	hrtick_update(rq);
 }
@@ -5447,6 +5692,29 @@ static unsigned long cpu_load_without(struct rq *rq, struct task_struct *p)
 	return load;
 }
 
+static unsigned long cpu_runnable(struct rq *rq)
+{
+	return cfs_rq_runnable_avg(&rq->cfs);
+}
+
+static unsigned long cpu_runnable_without(struct rq *rq, struct task_struct *p)
+{
+	struct cfs_rq *cfs_rq;
+	unsigned int runnable;
+
+	/* Task has no contribution or is new */
+	if (cpu_of(rq) != task_cpu(p) || !READ_ONCE(p->se.avg.last_update_time))
+		return cpu_runnable(rq);
+
+	cfs_rq = &rq->cfs;
+	runnable = READ_ONCE(cfs_rq->avg.runnable_avg);
+
+	/* Discount task's runnable from CPU's runnable */
+	lsub_positive(&runnable, p->se.avg.runnable_avg);
+
+	return runnable;
+}
+
 static unsigned long capacity_of(int cpu)
 {
 	return cpu_rq(cpu)->cpu_capacity;
@@ -5490,7 +5758,7 @@ static int wake_wide(struct task_struct *p)
 {
 	unsigned int master = current->wakee_flips;
 	unsigned int slave = p->wakee_flips;
-	int factor = this_cpu_read(sd_llc_size);
+	int factor = __this_cpu_read(sd_llc_size);
 
 	if (master < slave)
 		swap(master, slave);
@@ -5599,8 +5867,7 @@ static int wake_affine(struct sched_domain *sd, struct task_struct *p,
 }
 
 static struct sched_group *
-find_idlest_group(struct sched_domain *sd, struct task_struct *p,
-		  int this_cpu, int sd_flag);
+find_idlest_group(struct sched_domain *sd, struct task_struct *p, int this_cpu);
 
 /*
  * find_idlest_group_cpu - find the idlest CPU among the CPUs in the group.
@@ -5683,7 +5950,7 @@ static inline int find_idlest_cpu(struct sched_domain *sd, struct task_struct *p
 			continue;
 		}
 
-		group = find_idlest_group(sd, p, cpu, sd_flag);
+		group = find_idlest_group(sd, p, cpu);
 		if (!group) {
 			sd = sd->child;
 			continue;
@@ -5786,10 +6053,12 @@ static int select_idle_core(struct task_struct *p, struct sched_domain *sd, int
 		bool idle = true;
 
 		for_each_cpu(cpu, cpu_smt_mask(core)) {
-			__cpumask_clear_cpu(cpu, cpus);
-			if (!available_idle_cpu(cpu))
+			if (!available_idle_cpu(cpu)) {
 				idle = false;
+				break;
+			}
 		}
+		cpumask_andnot(cpus, cpus, cpu_smt_mask(core));
 
 		if (idle)
 			return core;
@@ -5847,8 +6116,7 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, int t
 	struct cpumask *cpus = this_cpu_cpumask_var_ptr(select_idle_mask);
 	struct sched_domain *this_sd;
 	u64 avg_cost, avg_idle;
-	u64 time, cost;
-	s64 delta;
+	u64 time;
 	int this = smp_processor_id();
 	int cpu, nr = INT_MAX;
 
@@ -5886,14 +6154,46 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, int t
 	}
 
 	time = cpu_clock(this) - time;
-	cost = this_sd->avg_scan_cost;
-	delta = (s64)(time - cost) / 8;
-	this_sd->avg_scan_cost += delta;
+	update_avg(&this_sd->avg_scan_cost, time);
 
 	return cpu;
 }
 
 /*
+ * Scan the asym_capacity domain for idle CPUs; pick the first idle one on which
+ * the task fits. If no CPU is big enough, but there are idle ones, try to
+ * maximize capacity.
+ */
+static int
+select_idle_capacity(struct task_struct *p, struct sched_domain *sd, int target)
+{
+	unsigned long best_cap = 0;
+	int cpu, best_cpu = -1;
+	struct cpumask *cpus;
+
+	sync_entity_load_avg(&p->se);
+
+	cpus = this_cpu_cpumask_var_ptr(select_idle_mask);
+	cpumask_and(cpus, sched_domain_span(sd), p->cpus_ptr);
+
+	for_each_cpu_wrap(cpu, cpus, target) {
+		unsigned long cpu_cap = capacity_of(cpu);
+
+		if (!available_idle_cpu(cpu) && !sched_idle_cpu(cpu))
+			continue;
+		if (task_fits_capacity(p, cpu_cap))
+			return cpu;
+
+		if (cpu_cap > best_cap) {
+			best_cap = cpu_cap;
+			best_cpu = cpu;
+		}
+	}
+
+	return best_cpu;
+}
+
+/*
  * Try and locate an idle core/thread in the LLC cache domain.
  */
 static int select_idle_sibling(struct task_struct *p, int prev, int target)
@@ -5901,6 +6201,28 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target)
 	struct sched_domain *sd;
 	int i, recent_used_cpu;
 
+	/*
+	 * For asymmetric CPU capacity systems, our domain of interest is
+	 * sd_asym_cpucapacity rather than sd_llc.
+	 */
+	if (static_branch_unlikely(&sched_asym_cpucapacity)) {
+		sd = rcu_dereference(per_cpu(sd_asym_cpucapacity, target));
+		/*
+		 * On an asymmetric CPU capacity system where an exclusive
+		 * cpuset defines a symmetric island (i.e. one unique
+		 * capacity_orig value through the cpuset), the key will be set
+		 * but the CPUs within that cpuset will not have a domain with
+		 * SD_ASYM_CPUCAPACITY. These should follow the usual symmetric
+		 * capacity path.
+		 */
+		if (!sd)
+			goto symmetric;
+
+		i = select_idle_capacity(p, sd, target);
+		return ((unsigned)i < nr_cpumask_bits) ? i : target;
+	}
+
+symmetric:
 	if (available_idle_cpu(target) || sched_idle_cpu(target))
 		return target;
 
@@ -6101,33 +6423,6 @@ static unsigned long cpu_util_without(int cpu, struct task_struct *p)
 }
 
 /*
- * Disable WAKE_AFFINE in the case where task @p doesn't fit in the
- * capacity of either the waking CPU @cpu or the previous CPU @prev_cpu.
- *
- * In that case WAKE_AFFINE doesn't make sense and we'll let
- * BALANCE_WAKE sort things out.
- */
-static int wake_cap(struct task_struct *p, int cpu, int prev_cpu)
-{
-	long min_cap, max_cap;
-
-	if (!static_branch_unlikely(&sched_asym_cpucapacity))
-		return 0;
-
-	min_cap = min(capacity_orig_of(prev_cpu), capacity_orig_of(cpu));
-	max_cap = cpu_rq(cpu)->rd->max_cpu_capacity;
-
-	/* Minimum capacity is close to max, no need to abort wake_affine */
-	if (max_cap - min_cap < max_cap >> 3)
-		return 0;
-
-	/* Bring task utilization in sync with prev_cpu */
-	sync_entity_load_avg(&p->se);
-
-	return !task_fits_capacity(p, min_cap);
-}
-
-/*
  * Predicts what cpu_util(@cpu) would return if @p was migrated (and enqueued)
  * to @dst_cpu.
  */
@@ -6214,7 +6509,7 @@ compute_energy(struct task_struct *p, int dst_cpu, struct perf_domain *pd)
 		max_util = max(max_util, cpu_util);
 	}
 
-	return em_pd_energy(pd->em_pd, max_util, sum_util);
+	return em_cpu_energy(pd->em_pd, max_util, sum_util);
 }
 
 /*
@@ -6391,15 +6686,11 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_f
 			new_cpu = prev_cpu;
 		}
 
-		want_affine = !wake_wide(p) && !wake_cap(p, cpu, prev_cpu) &&
-			      cpumask_test_cpu(cpu, p->cpus_ptr);
+		want_affine = !wake_wide(p) && cpumask_test_cpu(cpu, p->cpus_ptr);
 	}
 
 	rcu_read_lock();
 	for_each_domain(cpu, tmp) {
-		if (!(tmp->flags & SD_LOAD_BALANCE))
-			break;
-
 		/*
 		 * If both 'cpu' and 'prev_cpu' are part of this domain,
 		 * cpu is a valid SD_WAKE_AFFINE target.
@@ -6878,7 +7169,7 @@ static void yield_task_fair(struct rq *rq)
 	set_skip_buddy(se);
 }
 
-static bool yield_to_task_fair(struct rq *rq, struct task_struct *p, bool preempt)
+static bool yield_to_task_fair(struct rq *rq, struct task_struct *p)
 {
 	struct sched_entity *se = &p->se;
 
@@ -7359,7 +7650,14 @@ static int detach_tasks(struct lb_env *env)
 
 		switch (env->migration_type) {
 		case migrate_load:
-			load = task_h_load(p);
+			/*
+			 * Depending of the number of CPUs and tasks and the
+			 * cgroup hierarchy, task_h_load() can return a null
+			 * value. Make sure that env->imbalance decreases
+			 * otherwise detach_tasks() will stop only after
+			 * detaching up to loop_max tasks.
+			 */
+			load = max_t(unsigned long, task_h_load(p), 1);
 
 			if (sched_feat(LB_MIN) &&
 			    load < 16 && !env->sd->nr_balance_failed)
@@ -7506,6 +7804,9 @@ static inline bool others_have_blocked(struct rq *rq)
 	if (READ_ONCE(rq->avg_dl.util_avg))
 		return true;
 
+	if (thermal_load_avg(rq))
+		return true;
+
 #ifdef CONFIG_HAVE_SCHED_AVG_IRQ
 	if (READ_ONCE(rq->avg_irq.util_avg))
 		return true;
@@ -7531,6 +7832,7 @@ static bool __update_blocked_others(struct rq *rq, bool *done)
 {
 	const struct sched_class *curr_class;
 	u64 now = rq_clock_pelt(rq);
+	unsigned long thermal_pressure;
 	bool decayed;
 
 	/*
@@ -7539,8 +7841,11 @@ static bool __update_blocked_others(struct rq *rq, bool *done)
 	 */
 	curr_class = rq->curr->sched_class;
 
+	thermal_pressure = arch_scale_thermal_pressure(cpu_of(rq));
+
 	decayed = update_rt_rq_load_avg(now, rq, curr_class == &rt_sched_class) |
 		  update_dl_rq_load_avg(now, rq, curr_class == &dl_sched_class) |
+		  update_thermal_load_avg(rq_clock_thermal(rq), rq, thermal_pressure) |
 		  update_irq_load_avg(rq, 0);
 
 	if (others_have_blocked(rq))
@@ -7562,7 +7867,7 @@ static inline bool cfs_rq_is_decayed(struct cfs_rq *cfs_rq)
 	if (cfs_rq->avg.util_sum)
 		return false;
 
-	if (cfs_rq->avg.runnable_load_sum)
+	if (cfs_rq->avg.runnable_sum)
 		return false;
 
 	return true;
@@ -7700,7 +8005,8 @@ struct sg_lb_stats {
 	unsigned long avg_load; /*Avg load across the CPUs of the group */
 	unsigned long group_load; /* Total load over the CPUs of the group */
 	unsigned long group_capacity;
-	unsigned long group_util; /* Total utilization of the group */
+	unsigned long group_util; /* Total utilization over the CPUs of the group */
+	unsigned long group_runnable; /* Total runnable time over the CPUs of the group */
 	unsigned int sum_nr_running; /* Nr of tasks running in the group */
 	unsigned int sum_h_nr_running; /* Nr of CFS tasks running in the group */
 	unsigned int idle_cpus;
@@ -7751,7 +8057,7 @@ static inline void init_sd_lb_stats(struct sd_lb_stats *sds)
 	};
 }
 
-static unsigned long scale_rt_capacity(struct sched_domain *sd, int cpu)
+static unsigned long scale_rt_capacity(int cpu)
 {
 	struct rq *rq = cpu_rq(cpu);
 	unsigned long max = arch_scale_cpu_capacity(cpu);
@@ -7763,8 +8069,15 @@ static unsigned long scale_rt_capacity(struct sched_domain *sd, int cpu)
 	if (unlikely(irq >= max))
 		return 1;
 
+	/*
+	 * avg_rt.util_avg and avg_dl.util_avg track binary signals
+	 * (running and not running) with weights 0 and 1024 respectively.
+	 * avg_thermal.load_avg tracks thermal pressure and the weighted
+	 * average uses the actual delta max capacity(load).
+	 */
 	used = READ_ONCE(rq->avg_rt.util_avg);
 	used += READ_ONCE(rq->avg_dl.util_avg);
+	used += thermal_load_avg(rq);
 
 	if (unlikely(used >= max))
 		return 1;
@@ -7776,7 +8089,7 @@ static unsigned long scale_rt_capacity(struct sched_domain *sd, int cpu)
 
 static void update_cpu_capacity(struct sched_domain *sd, int cpu)
 {
-	unsigned long capacity = scale_rt_capacity(sd, cpu);
+	unsigned long capacity = scale_rt_capacity(cpu);
 	struct sched_group *sdg = sd->groups;
 
 	cpu_rq(cpu)->cpu_capacity_orig = arch_scale_cpu_capacity(cpu);
@@ -7921,6 +8234,10 @@ group_has_capacity(unsigned int imbalance_pct, struct sg_lb_stats *sgs)
 	if (sgs->sum_nr_running < sgs->group_weight)
 		return true;
 
+	if ((sgs->group_capacity * imbalance_pct) <
+			(sgs->group_runnable * 100))
+		return false;
+
 	if ((sgs->group_capacity * 100) >
 			(sgs->group_util * imbalance_pct))
 		return true;
@@ -7946,6 +8263,10 @@ group_is_overloaded(unsigned int imbalance_pct, struct sg_lb_stats *sgs)
 			(sgs->group_util * imbalance_pct))
 		return true;
 
+	if ((sgs->group_capacity * imbalance_pct) <
+			(sgs->group_runnable * 100))
+		return true;
+
 	return false;
 }
 
@@ -8040,6 +8361,7 @@ static inline void update_sg_lb_stats(struct lb_env *env,
 
 		sgs->group_load += cpu_load(rq);
 		sgs->group_util += cpu_util(i);
+		sgs->group_runnable += cpu_runnable(rq);
 		sgs->sum_h_nr_running += rq->cfs.h_nr_running;
 
 		nr_running = rq->nr_running;
@@ -8286,7 +8608,7 @@ static int idle_cpu_without(int cpu, struct task_struct *p)
 	 */
 
 #ifdef CONFIG_SMP
-	if (!llist_empty(&rq->wake_list))
+	if (rq->ttwu_pending)
 		return 0;
 #endif
 
@@ -8315,6 +8637,7 @@ static inline void update_sg_wakeup_stats(struct sched_domain *sd,
 
 		sgs->group_load += cpu_load_without(rq, p);
 		sgs->group_util += cpu_util_without(i, p);
+		sgs->group_runnable += cpu_runnable_without(rq, p);
 		local = task_running_on_cpu(i, p);
 		sgs->sum_h_nr_running += rq->cfs.h_nr_running - local;
 
@@ -8345,7 +8668,8 @@ static inline void update_sg_wakeup_stats(struct sched_domain *sd,
 	 * Computing avg_load makes sense only when group is fully busy or
 	 * overloaded
 	 */
-	if (sgs->group_type < group_fully_busy)
+	if (sgs->group_type == group_fully_busy ||
+		sgs->group_type == group_overloaded)
 		sgs->avg_load = (sgs->group_load * SCHED_CAPACITY_SCALE) /
 				sgs->group_capacity;
 }
@@ -8387,8 +8711,14 @@ static bool update_pick_idlest(struct sched_group *idlest,
 
 	case group_has_spare:
 		/* Select group with most idle CPUs */
-		if (idlest_sgs->idle_cpus >= sgs->idle_cpus)
+		if (idlest_sgs->idle_cpus > sgs->idle_cpus)
 			return false;
+
+		/* Select group with lowest group_util */
+		if (idlest_sgs->idle_cpus == sgs->idle_cpus &&
+			idlest_sgs->group_util <= sgs->group_util)
+			return false;
+
 		break;
 	}
 
@@ -8402,8 +8732,7 @@ static bool update_pick_idlest(struct sched_group *idlest,
  * Assumes p is allowed on at least one CPU in sd.
  */
 static struct sched_group *
-find_idlest_group(struct sched_domain *sd, struct task_struct *p,
-		  int this_cpu, int sd_flag)
+find_idlest_group(struct sched_domain *sd, struct task_struct *p, int this_cpu)
 {
 	struct sched_group *idlest = NULL, *local = NULL, *group = sd->groups;
 	struct sg_lb_stats local_sgs, tmp_sgs;
@@ -8628,6 +8957,21 @@ next_group:
 	}
 }
 
+static inline long adjust_numa_imbalance(int imbalance, int src_nr_running)
+{
+	unsigned int imbalance_min;
+
+	/*
+	 * Allow a small imbalance based on a simple pair of communicating
+	 * tasks that remain local when the source domain is almost idle.
+	 */
+	imbalance_min = 2;
+	if (src_nr_running <= imbalance_min)
+		return 0;
+
+	return imbalance;
+}
+
 /**
  * calculate_imbalance - Calculate the amount of imbalance present within the
  *			 groups of a given sched_domain during load balance.
@@ -8724,24 +9068,9 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s
 		}
 
 		/* Consider allowing a small imbalance between NUMA groups */
-		if (env->sd->flags & SD_NUMA) {
-			unsigned int imbalance_min;
-
-			/*
-			 * Compute an allowed imbalance based on a simple
-			 * pair of communicating tasks that should remain
-			 * local and ignore them.
-			 *
-			 * NOTE: Generally this would have been based on
-			 * the domain size and this was evaluated. However,
-			 * the benefit is similar across a range of workloads
-			 * and machines but scaling by the domain size adds
-			 * the risk that lower domains have to be rebalanced.
-			 */
-			imbalance_min = 2;
-			if (busiest->sum_nr_running <= imbalance_min)
-				env->imbalance = 0;
-		}
+		if (env->sd->flags & SD_NUMA)
+			env->imbalance = adjust_numa_imbalance(env->imbalance,
+						busiest->sum_nr_running);
 
 		return;
 	}
@@ -8761,6 +9090,14 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s
 
 		sds->avg_load = (sds->total_load * SCHED_CAPACITY_SCALE) /
 				sds->total_capacity;
+		/*
+		 * If the local group is more loaded than the selected
+		 * busiest group don't try to pull any tasks.
+		 */
+		if (local->avg_load >= busiest->avg_load) {
+			env->imbalance = 0;
+			return;
+		}
 	}
 
 	/*
@@ -9027,6 +9364,14 @@ static struct rq *find_busiest_queue(struct lb_env *env,
 		case migrate_util:
 			util = cpu_util(cpu_of(rq));
 
+			/*
+			 * Don't try to pull utilization from a CPU with one
+			 * running task. Whatever its utilization, we will fail
+			 * detach the task.
+			 */
+			if (nr_running <= 1)
+				continue;
+
 			if (busiest_util < util) {
 				busiest_util = util;
 				busiest = rq;
@@ -9118,7 +9463,7 @@ static int active_load_balance_cpu_stop(void *data);
 static int should_we_balance(struct lb_env *env)
 {
 	struct sched_group *sg = env->sd->groups;
-	int cpu, balance_cpu = -1;
+	int cpu;
 
 	/*
 	 * Ensure the balancing environment is consistent; can happen
@@ -9139,18 +9484,12 @@ static int should_we_balance(struct lb_env *env)
 		if (!idle_cpu(cpu))
 			continue;
 
-		balance_cpu = cpu;
-		break;
+		/* Are we the first idle CPU? */
+		return cpu == env->dst_cpu;
 	}
 
-	if (balance_cpu == -1)
-		balance_cpu = group_balance_cpu(sg);
-
-	/*
-	 * First idle CPU or the first CPU(busiest) in this sched group
-	 * is eligible for doing load balancing at this and above domains.
-	 */
-	return balance_cpu == env->dst_cpu;
+	/* Are we the first CPU of this group ? */
+	return group_balance_cpu(sg) == env->dst_cpu;
 }
 
 /*
@@ -9503,9 +9842,8 @@ static int active_load_balance_cpu_stop(void *data)
 	/* Search for an sd spanning us and the target CPU. */
 	rcu_read_lock();
 	for_each_domain(target_cpu, sd) {
-		if ((sd->flags & SD_LOAD_BALANCE) &&
-		    cpumask_test_cpu(busiest_cpu, sched_domain_span(sd)))
-				break;
+		if (cpumask_test_cpu(busiest_cpu, sched_domain_span(sd)))
+			break;
 	}
 
 	if (likely(sd)) {
@@ -9594,9 +9932,6 @@ static void rebalance_domains(struct rq *rq, enum cpu_idle_type idle)
 		}
 		max_cost += sd->max_newidle_lb_cost;
 
-		if (!(sd->flags & SD_LOAD_BALANCE))
-			continue;
-
 		/*
 		 * Stop the load balance at this level. There is another
 		 * CPU in our sched group which is doing load balancing more
@@ -9706,24 +10041,32 @@ static void kick_ilb(unsigned int flags)
 {
 	int ilb_cpu;
 
-	nohz.next_balance++;
+	/*
+	 * Increase nohz.next_balance only when if full ilb is triggered but
+	 * not if we only update stats.
+	 */
+	if (flags & NOHZ_BALANCE_KICK)
+		nohz.next_balance = jiffies+1;
 
 	ilb_cpu = find_new_ilb();
 
 	if (ilb_cpu >= nr_cpu_ids)
 		return;
 
+	/*
+	 * Access to rq::nohz_csd is serialized by NOHZ_KICK_MASK; he who sets
+	 * the first flag owns it; cleared by nohz_csd_func().
+	 */
 	flags = atomic_fetch_or(flags, nohz_flags(ilb_cpu));
 	if (flags & NOHZ_KICK_MASK)
 		return;
 
 	/*
-	 * Use smp_send_reschedule() instead of resched_cpu().
-	 * This way we generate a sched IPI on the target CPU which
+	 * This way we generate an IPI on the target CPU which
 	 * is idle. And the softirq performing nohz idle load balance
 	 * will be run before returning from the IPI.
 	 */
-	smp_send_reschedule(ilb_cpu);
+	smp_call_function_single_async(ilb_cpu, &cpu_rq(ilb_cpu)->nohz_csd);
 }
 
 /*
@@ -10024,6 +10367,14 @@ static bool _nohz_idle_balance(struct rq *this_rq, unsigned int flags,
 		}
 	}
 
+	/*
+	 * next_balance will be updated only when there is a need.
+	 * When the CPU is attached to null domain for ex, it will not be
+	 * updated.
+	 */
+	if (likely(update_next_balance))
+		nohz.next_balance = next_balance;
+
 	/* Newly idle CPU doesn't need an update */
 	if (idle != CPU_NEWLY_IDLE) {
 		update_blocked_averages(this_cpu);
@@ -10044,14 +10395,6 @@ abort:
 	if (has_blocked_load)
 		WRITE_ONCE(nohz.has_blocked, 1);
 
-	/*
-	 * next_balance will be updated only when there is a need.
-	 * When the CPU is attached to null domain for ex, it will not be
-	 * updated.
-	 */
-	if (likely(update_next_balance))
-		nohz.next_balance = next_balance;
-
 	return ret;
 }
 
@@ -10061,20 +10404,14 @@ abort:
  */
 static bool nohz_idle_balance(struct rq *this_rq, enum cpu_idle_type idle)
 {
-	int this_cpu = this_rq->cpu;
-	unsigned int flags;
+	unsigned int flags = this_rq->nohz_idle_balance;
 
-	if (!(atomic_read(nohz_flags(this_cpu)) & NOHZ_KICK_MASK))
+	if (!flags)
 		return false;
 
-	if (idle != CPU_IDLE) {
-		atomic_andnot(NOHZ_KICK_MASK, nohz_flags(this_cpu));
-		return false;
-	}
+	this_rq->nohz_idle_balance = 0;
 
-	/* could be _relaxed() */
-	flags = atomic_fetch_andnot(NOHZ_KICK_MASK, nohz_flags(this_cpu));
-	if (!(flags & NOHZ_KICK_MASK))
+	if (idle != CPU_IDLE)
 		return false;
 
 	_nohz_idle_balance(this_rq, flags, idle);
@@ -10134,7 +10471,7 @@ static inline void nohz_newidle_balance(struct rq *this_rq) { }
  *     0 - failed, no new tasks
  *   > 0 - success, new (fair) tasks present
  */
-int newidle_balance(struct rq *this_rq, struct rq_flags *rf)
+static int newidle_balance(struct rq *this_rq, struct rq_flags *rf)
 {
 	unsigned long next_balance = jiffies + HZ;
 	int this_cpu = this_rq->cpu;
@@ -10185,9 +10522,6 @@ int newidle_balance(struct rq *this_rq, struct rq_flags *rf)
 		int continue_balancing = 1;
 		u64 t0, domain_cost;
 
-		if (!(sd->flags & SD_LOAD_BALANCE))
-			continue;
-
 		if (this_rq->avg_idle < curr_cost + sd->max_newidle_lb_cost) {
 			update_next_balance(sd, &next_balance);
 			break;
@@ -10803,8 +11137,8 @@ static unsigned int get_rr_interval_fair(struct rq *rq, struct task_struct *task
 /*
  * All the scheduling class methods:
  */
-const struct sched_class fair_sched_class = {
-	.next			= &idle_sched_class,
+const struct sched_class fair_sched_class
+	__attribute__((section("__fair_sched_class"))) = {
 	.enqueue_task		= enqueue_task_fair,
 	.dequeue_task		= dequeue_task_fair,
 	.yield_task		= yield_task_fair,
@@ -10977,3 +11311,9 @@ const struct cpumask *sched_trace_rd_span(struct root_domain *rd)
 #endif
 }
 EXPORT_SYMBOL_GPL(sched_trace_rd_span);
+
+int sched_trace_rq_nr_running(struct rq *rq)
+{
+        return rq ? rq->nr_running : -1;
+}
+EXPORT_SYMBOL_GPL(sched_trace_rq_nr_running);
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index b743bf38f08f..f324dc36fc43 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -54,17 +54,18 @@ __setup("hlt", cpu_idle_nopoll_setup);
 
 static noinline int __cpuidle cpu_idle_poll(void)
 {
+	trace_cpu_idle(0, smp_processor_id());
+	stop_critical_timings();
 	rcu_idle_enter();
-	trace_cpu_idle_rcuidle(0, smp_processor_id());
 	local_irq_enable();
-	stop_critical_timings();
 
 	while (!tif_need_resched() &&
-		(cpu_idle_force_poll || tick_check_broadcast_expired()))
+	       (cpu_idle_force_poll || tick_check_broadcast_expired()))
 		cpu_relax();
-	start_critical_timings();
-	trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id());
+
 	rcu_idle_exit();
+	start_critical_timings();
+	trace_cpu_idle(PWR_EVENT_EXIT, smp_processor_id());
 
 	return 1;
 }
@@ -90,12 +91,26 @@ void __cpuidle default_idle_call(void)
 	if (current_clr_polling_and_test()) {
 		local_irq_enable();
 	} else {
+
+		trace_cpu_idle(1, smp_processor_id());
 		stop_critical_timings();
+		rcu_idle_enter();
 		arch_cpu_idle();
+		rcu_idle_exit();
 		start_critical_timings();
+		trace_cpu_idle(PWR_EVENT_EXIT, smp_processor_id());
 	}
 }
 
+static int call_cpuidle_s2idle(struct cpuidle_driver *drv,
+			       struct cpuidle_device *dev)
+{
+	if (current_clr_polling_and_test())
+		return -EBUSY;
+
+	return cpuidle_enter_s2idle(drv, dev);
+}
+
 static int call_cpuidle(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 		      int next_state)
 {
@@ -149,7 +164,6 @@ static void cpuidle_idle_call(void)
 
 	if (cpuidle_not_available(drv, dev)) {
 		tick_nohz_idle_stop_tick();
-		rcu_idle_enter();
 
 		default_idle_call();
 		goto exit_idle;
@@ -169,15 +183,10 @@ static void cpuidle_idle_call(void)
 		u64 max_latency_ns;
 
 		if (idle_should_enter_s2idle()) {
-			rcu_idle_enter();
 
-			entered_state = cpuidle_enter_s2idle(drv, dev);
-			if (entered_state > 0) {
-				local_irq_enable();
+			entered_state = call_cpuidle_s2idle(drv, dev);
+			if (entered_state > 0)
 				goto exit_idle;
-			}
-
-			rcu_idle_exit();
 
 			max_latency_ns = U64_MAX;
 		} else {
@@ -185,7 +194,6 @@ static void cpuidle_idle_call(void)
 		}
 
 		tick_nohz_idle_stop_tick();
-		rcu_idle_enter();
 
 		next_state = cpuidle_find_deepest_state(drv, dev, max_latency_ns);
 		call_cpuidle(drv, dev, next_state);
@@ -202,8 +210,6 @@ static void cpuidle_idle_call(void)
 		else
 			tick_nohz_idle_retain_tick();
 
-		rcu_idle_enter();
-
 		entered_state = call_cpuidle(drv, dev, next_state);
 		/*
 		 * Give the governor an opportunity to reflect on the outcome
@@ -219,8 +225,6 @@ exit_idle:
 	 */
 	if (WARN_ON_ONCE(irqs_disabled()))
 		local_irq_enable();
-
-	rcu_idle_exit();
 }
 
 /*
@@ -289,7 +293,11 @@ static void do_idle(void)
 	 */
 	smp_mb__after_atomic();
 
-	sched_ttwu_pending();
+	/*
+	 * RCU relies on this call to be done outside of an RCU read-side
+	 * critical section.
+	 */
+	flush_smp_call_function_from_idle();
 	schedule_idle();
 
 	if (unlikely(klp_patch_pending(current)))
@@ -442,11 +450,6 @@ prio_changed_idle(struct rq *rq, struct task_struct *p, int oldprio)
 	BUG();
 }
 
-static unsigned int get_rr_interval_idle(struct rq *rq, struct task_struct *task)
-{
-	return 0;
-}
-
 static void update_curr_idle(struct rq *rq)
 {
 }
@@ -454,8 +457,8 @@ static void update_curr_idle(struct rq *rq)
 /*
  * Simple, special scheduling class for the per-CPU idle tasks:
  */
-const struct sched_class idle_sched_class = {
-	/* .next is NULL */
+const struct sched_class idle_sched_class
+	__attribute__((section("__idle_sched_class"))) = {
 	/* no enqueue/yield_task for idle tasks */
 
 	/* dequeue is not valid, we print a debug message there: */
@@ -475,8 +478,6 @@ const struct sched_class idle_sched_class = {
 
 	.task_tick		= task_tick_idle,
 
-	.get_rr_interval	= get_rr_interval_idle,
-
 	.prio_changed		= prio_changed_idle,
 	.switched_to		= switched_to_idle,
 	.update_curr		= update_curr_idle,
diff --git a/kernel/sched/isolation.c b/kernel/sched/isolation.c
index 008d6ac2342b..5a6ea03f9882 100644
--- a/kernel/sched/isolation.c
+++ b/kernel/sched/isolation.c
@@ -140,7 +140,8 @@ static int __init housekeeping_nohz_full_setup(char *str)
 {
 	unsigned int flags;
 
-	flags = HK_FLAG_TICK | HK_FLAG_WQ | HK_FLAG_TIMER | HK_FLAG_RCU | HK_FLAG_MISC;
+	flags = HK_FLAG_TICK | HK_FLAG_WQ | HK_FLAG_TIMER | HK_FLAG_RCU |
+		HK_FLAG_MISC | HK_FLAG_KTHREAD;
 
 	return housekeeping_setup(str, flags);
 }
@@ -149,6 +150,9 @@ __setup("nohz_full=", housekeeping_nohz_full_setup);
 static int __init housekeeping_isolcpus_setup(char *str)
 {
 	unsigned int flags = 0;
+	bool illegal = false;
+	char *par;
+	int len;
 
 	while (isalpha(*str)) {
 		if (!strncmp(str, "nohz,", 5)) {
@@ -169,8 +173,22 @@ static int __init housekeeping_isolcpus_setup(char *str)
 			continue;
 		}
 
-		pr_warn("isolcpus: Error, unknown flag\n");
-		return 0;
+		/*
+		 * Skip unknown sub-parameter and validate that it is not
+		 * containing an invalid character.
+		 */
+		for (par = str, len = 0; *str && *str != ','; str++, len++) {
+			if (!isalpha(*str) && *str != '_')
+				illegal = true;
+		}
+
+		if (illegal) {
+			pr_warn("isolcpus: Invalid flag %.*s\n", len, par);
+			return 0;
+		}
+
+		pr_info("isolcpus: Skipped unknown flag %.*s\n", len, par);
+		str++;
 	}
 
 	/* Default behaviour for isolcpus without flags */
diff --git a/kernel/sched/loadavg.c b/kernel/sched/loadavg.c
index de22da666ac7..d2a655643a02 100644
--- a/kernel/sched/loadavg.c
+++ b/kernel/sched/loadavg.c
@@ -347,7 +347,7 @@ static inline void calc_global_nohz(void) { }
  *
  * Called from the global timer code.
  */
-void calc_global_load(unsigned long ticks)
+void calc_global_load(void)
 {
 	unsigned long sample_window;
 	long active, delta;
diff --git a/kernel/sched/pelt.c b/kernel/sched/pelt.c
index bd006b79b360..2c613e1cff3a 100644
--- a/kernel/sched/pelt.c
+++ b/kernel/sched/pelt.c
@@ -28,8 +28,6 @@
 #include "sched.h"
 #include "pelt.h"
 
-#include <trace/events/sched.h>
-
 /*
  * Approximate:
  *   val * y^n,    where y^32 ~= 0.5 (~1 scheduling period)
@@ -83,8 +81,6 @@ static u32 __accumulate_pelt_segments(u64 periods, u32 d1, u32 d3)
 	return c1 + c2 + c3;
 }
 
-#define cap_scale(v, s) ((v)*(s) >> SCHED_CAPACITY_SHIFT)
-
 /*
  * Accumulate the three separate parts of the sum; d1 the remainder
  * of the last (incomplete) period, d2 the span of full periods and d3
@@ -121,8 +117,8 @@ accumulate_sum(u64 delta, struct sched_avg *sa,
 	 */
 	if (periods) {
 		sa->load_sum = decay_load(sa->load_sum, periods);
-		sa->runnable_load_sum =
-			decay_load(sa->runnable_load_sum, periods);
+		sa->runnable_sum =
+			decay_load(sa->runnable_sum, periods);
 		sa->util_sum = decay_load((u64)(sa->util_sum), periods);
 
 		/*
@@ -149,7 +145,7 @@ accumulate_sum(u64 delta, struct sched_avg *sa,
 	if (load)
 		sa->load_sum += load * contrib;
 	if (runnable)
-		sa->runnable_load_sum += runnable * contrib;
+		sa->runnable_sum += runnable * contrib << SCHED_CAPACITY_SHIFT;
 	if (running)
 		sa->util_sum += contrib << SCHED_CAPACITY_SHIFT;
 
@@ -237,16 +233,40 @@ ___update_load_sum(u64 now, struct sched_avg *sa,
 	return 1;
 }
 
+/*
+ * When syncing *_avg with *_sum, we must take into account the current
+ * position in the PELT segment otherwise the remaining part of the segment
+ * will be considered as idle time whereas it's not yet elapsed and this will
+ * generate unwanted oscillation in the range [1002..1024[.
+ *
+ * The max value of *_sum varies with the position in the time segment and is
+ * equals to :
+ *
+ *   LOAD_AVG_MAX*y + sa->period_contrib
+ *
+ * which can be simplified into:
+ *
+ *   LOAD_AVG_MAX - 1024 + sa->period_contrib
+ *
+ * because LOAD_AVG_MAX*y == LOAD_AVG_MAX-1024
+ *
+ * The same care must be taken when a sched entity is added, updated or
+ * removed from a cfs_rq and we need to update sched_avg. Scheduler entities
+ * and the cfs rq, to which they are attached, have the same position in the
+ * time segment because they use the same clock. This means that we can use
+ * the period_contrib of cfs_rq when updating the sched_avg of a sched_entity
+ * if it's more convenient.
+ */
 static __always_inline void
-___update_load_avg(struct sched_avg *sa, unsigned long load, unsigned long runnable)
+___update_load_avg(struct sched_avg *sa, unsigned long load)
 {
-	u32 divider = LOAD_AVG_MAX - 1024 + sa->period_contrib;
+	u32 divider = get_pelt_divider(sa);
 
 	/*
 	 * Step 2: update *_avg.
 	 */
 	sa->load_avg = div_u64(load * sa->load_sum, divider);
-	sa->runnable_load_avg =	div_u64(runnable * sa->runnable_load_sum, divider);
+	sa->runnable_avg = div_u64(sa->runnable_sum, divider);
 	WRITE_ONCE(sa->util_avg, sa->util_sum / divider);
 }
 
@@ -254,33 +274,32 @@ ___update_load_avg(struct sched_avg *sa, unsigned long load, unsigned long runna
  * sched_entity:
  *
  *   task:
- *     se_runnable() == se_weight()
+ *     se_weight()   = se->load.weight
+ *     se_runnable() = !!on_rq
  *
  *   group: [ see update_cfs_group() ]
  *     se_weight()   = tg->weight * grq->load_avg / tg->load_avg
- *     se_runnable() = se_weight(se) * grq->runnable_load_avg / grq->load_avg
+ *     se_runnable() = grq->h_nr_running
  *
- *   load_sum := runnable_sum
- *   load_avg = se_weight(se) * runnable_avg
+ *   runnable_sum = se_runnable() * runnable = grq->runnable_sum
+ *   runnable_avg = runnable_sum
  *
- *   runnable_load_sum := runnable_sum
- *   runnable_load_avg = se_runnable(se) * runnable_avg
- *
- * XXX collapse load_sum and runnable_load_sum
+ *   load_sum := runnable
+ *   load_avg = se_weight(se) * load_sum
  *
  * cfq_rq:
  *
+ *   runnable_sum = \Sum se->avg.runnable_sum
+ *   runnable_avg = \Sum se->avg.runnable_avg
+ *
  *   load_sum = \Sum se_weight(se) * se->avg.load_sum
  *   load_avg = \Sum se->avg.load_avg
- *
- *   runnable_load_sum = \Sum se_runnable(se) * se->avg.runnable_load_sum
- *   runnable_load_avg = \Sum se->avg.runable_load_avg
  */
 
 int __update_load_avg_blocked_se(u64 now, struct sched_entity *se)
 {
 	if (___update_load_sum(now, &se->avg, 0, 0, 0)) {
-		___update_load_avg(&se->avg, se_weight(se), se_runnable(se));
+		___update_load_avg(&se->avg, se_weight(se));
 		trace_pelt_se_tp(se);
 		return 1;
 	}
@@ -290,10 +309,10 @@ int __update_load_avg_blocked_se(u64 now, struct sched_entity *se)
 
 int __update_load_avg_se(u64 now, struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
-	if (___update_load_sum(now, &se->avg, !!se->on_rq, !!se->on_rq,
+	if (___update_load_sum(now, &se->avg, !!se->on_rq, se_runnable(se),
 				cfs_rq->curr == se)) {
 
-		___update_load_avg(&se->avg, se_weight(se), se_runnable(se));
+		___update_load_avg(&se->avg, se_weight(se));
 		cfs_se_util_change(&se->avg);
 		trace_pelt_se_tp(se);
 		return 1;
@@ -306,10 +325,10 @@ int __update_load_avg_cfs_rq(u64 now, struct cfs_rq *cfs_rq)
 {
 	if (___update_load_sum(now, &cfs_rq->avg,
 				scale_load_down(cfs_rq->load.weight),
-				scale_load_down(cfs_rq->runnable_weight),
+				cfs_rq->h_nr_running,
 				cfs_rq->curr != NULL)) {
 
-		___update_load_avg(&cfs_rq->avg, 1, 1);
+		___update_load_avg(&cfs_rq->avg, 1);
 		trace_pelt_cfs_tp(cfs_rq);
 		return 1;
 	}
@@ -322,9 +341,9 @@ int __update_load_avg_cfs_rq(u64 now, struct cfs_rq *cfs_rq)
  *
  *   util_sum = \Sum se->avg.util_sum but se->avg.util_sum is not tracked
  *   util_sum = cpu_scale * load_sum
- *   runnable_load_sum = load_sum
+ *   runnable_sum = util_sum
  *
- *   load_avg and runnable_load_avg are not supported and meaningless.
+ *   load_avg and runnable_avg are not supported and meaningless.
  *
  */
 
@@ -335,7 +354,7 @@ int update_rt_rq_load_avg(u64 now, struct rq *rq, int running)
 				running,
 				running)) {
 
-		___update_load_avg(&rq->avg_rt, 1, 1);
+		___update_load_avg(&rq->avg_rt, 1);
 		trace_pelt_rt_tp(rq);
 		return 1;
 	}
@@ -348,7 +367,9 @@ int update_rt_rq_load_avg(u64 now, struct rq *rq, int running)
  *
  *   util_sum = \Sum se->avg.util_sum but se->avg.util_sum is not tracked
  *   util_sum = cpu_scale * load_sum
- *   runnable_load_sum = load_sum
+ *   runnable_sum = util_sum
+ *
+ *   load_avg and runnable_avg are not supported and meaningless.
  *
  */
 
@@ -359,7 +380,7 @@ int update_dl_rq_load_avg(u64 now, struct rq *rq, int running)
 				running,
 				running)) {
 
-		___update_load_avg(&rq->avg_dl, 1, 1);
+		___update_load_avg(&rq->avg_dl, 1);
 		trace_pelt_dl_tp(rq);
 		return 1;
 	}
@@ -367,13 +388,46 @@ int update_dl_rq_load_avg(u64 now, struct rq *rq, int running)
 	return 0;
 }
 
+#ifdef CONFIG_SCHED_THERMAL_PRESSURE
+/*
+ * thermal:
+ *
+ *   load_sum = \Sum se->avg.load_sum but se->avg.load_sum is not tracked
+ *
+ *   util_avg and runnable_load_avg are not supported and meaningless.
+ *
+ * Unlike rt/dl utilization tracking that track time spent by a cpu
+ * running a rt/dl task through util_avg, the average thermal pressure is
+ * tracked through load_avg. This is because thermal pressure signal is
+ * time weighted "delta" capacity unlike util_avg which is binary.
+ * "delta capacity" =  actual capacity  -
+ *			capped capacity a cpu due to a thermal event.
+ */
+
+int update_thermal_load_avg(u64 now, struct rq *rq, u64 capacity)
+{
+	if (___update_load_sum(now, &rq->avg_thermal,
+			       capacity,
+			       capacity,
+			       capacity)) {
+		___update_load_avg(&rq->avg_thermal, 1);
+		trace_pelt_thermal_tp(rq);
+		return 1;
+	}
+
+	return 0;
+}
+#endif
+
 #ifdef CONFIG_HAVE_SCHED_AVG_IRQ
 /*
  * irq:
  *
  *   util_sum = \Sum se->avg.util_sum but se->avg.util_sum is not tracked
  *   util_sum = cpu_scale * load_sum
- *   runnable_load_sum = load_sum
+ *   runnable_sum = util_sum
+ *
+ *   load_avg and runnable_avg are not supported and meaningless.
  *
  */
 
@@ -410,7 +464,7 @@ int update_irq_load_avg(struct rq *rq, u64 running)
 				1);
 
 	if (ret) {
-		___update_load_avg(&rq->avg_irq, 1, 1);
+		___update_load_avg(&rq->avg_irq, 1);
 		trace_pelt_irq_tp(rq);
 	}
 
diff --git a/kernel/sched/pelt.h b/kernel/sched/pelt.h
index afff644da065..795e43e02afc 100644
--- a/kernel/sched/pelt.h
+++ b/kernel/sched/pelt.h
@@ -7,6 +7,26 @@ int __update_load_avg_cfs_rq(u64 now, struct cfs_rq *cfs_rq);
 int update_rt_rq_load_avg(u64 now, struct rq *rq, int running);
 int update_dl_rq_load_avg(u64 now, struct rq *rq, int running);
 
+#ifdef CONFIG_SCHED_THERMAL_PRESSURE
+int update_thermal_load_avg(u64 now, struct rq *rq, u64 capacity);
+
+static inline u64 thermal_load_avg(struct rq *rq)
+{
+	return READ_ONCE(rq->avg_thermal.load_avg);
+}
+#else
+static inline int
+update_thermal_load_avg(u64 now, struct rq *rq, u64 capacity)
+{
+	return 0;
+}
+
+static inline u64 thermal_load_avg(struct rq *rq)
+{
+	return 0;
+}
+#endif
+
 #ifdef CONFIG_HAVE_SCHED_AVG_IRQ
 int update_irq_load_avg(struct rq *rq, u64 running);
 #else
@@ -17,6 +37,11 @@ update_irq_load_avg(struct rq *rq, u64 running)
 }
 #endif
 
+static inline u32 get_pelt_divider(struct sched_avg *avg)
+{
+	return LOAD_AVG_MAX - 1024 + avg->period_contrib;
+}
+
 /*
  * When a task is dequeued, its estimated utilization should not be update if
  * its util_avg has not been updated at least once.
@@ -159,6 +184,17 @@ update_dl_rq_load_avg(u64 now, struct rq *rq, int running)
 }
 
 static inline int
+update_thermal_load_avg(u64 now, struct rq *rq, u64 capacity)
+{
+	return 0;
+}
+
+static inline u64 thermal_load_avg(struct rq *rq)
+{
+	return 0;
+}
+
+static inline int
 update_irq_load_avg(struct rq *rq, u64 running)
 {
 	return 0;
diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c
index 028520702717..967732c0766c 100644
--- a/kernel/sched/psi.c
+++ b/kernel/sched/psi.c
@@ -190,7 +190,6 @@ static void group_init(struct psi_group *group)
 	INIT_DELAYED_WORK(&group->avgs_work, psi_avgs_work);
 	mutex_init(&group->avgs_lock);
 	/* Init trigger-related members */
-	atomic_set(&group->poll_scheduled, 0);
 	mutex_init(&group->trigger_lock);
 	INIT_LIST_HEAD(&group->triggers);
 	memset(group->nr_triggers, 0, sizeof(group->nr_triggers));
@@ -199,7 +198,7 @@ static void group_init(struct psi_group *group)
 	memset(group->polling_total, 0, sizeof(group->polling_total));
 	group->polling_next_update = ULLONG_MAX;
 	group->polling_until = 0;
-	rcu_assign_pointer(group->poll_kworker, NULL);
+	rcu_assign_pointer(group->poll_task, NULL);
 }
 
 void __init psi_init(void)
@@ -225,7 +224,7 @@ static bool test_state(unsigned int *tasks, enum psi_states state)
 	case PSI_MEM_FULL:
 		return tasks[NR_MEMSTALL] && !tasks[NR_RUNNING];
 	case PSI_CPU_SOME:
-		return tasks[NR_RUNNING] > 1;
+		return tasks[NR_RUNNING] > tasks[NR_ONCPU];
 	case PSI_NONIDLE:
 		return tasks[NR_IOWAIT] || tasks[NR_MEMSTALL] ||
 			tasks[NR_RUNNING];
@@ -547,47 +546,38 @@ static u64 update_triggers(struct psi_group *group, u64 now)
 	return now + group->poll_min_period;
 }
 
-/*
- * Schedule polling if it's not already scheduled. It's safe to call even from
- * hotpath because even though kthread_queue_delayed_work takes worker->lock
- * spinlock that spinlock is never contended due to poll_scheduled atomic
- * preventing such competition.
- */
+/* Schedule polling if it's not already scheduled. */
 static void psi_schedule_poll_work(struct psi_group *group, unsigned long delay)
 {
-	struct kthread_worker *kworker;
+	struct task_struct *task;
 
-	/* Do not reschedule if already scheduled */
-	if (atomic_cmpxchg(&group->poll_scheduled, 0, 1) != 0)
+	/*
+	 * Do not reschedule if already scheduled.
+	 * Possible race with a timer scheduled after this check but before
+	 * mod_timer below can be tolerated because group->polling_next_update
+	 * will keep updates on schedule.
+	 */
+	if (timer_pending(&group->poll_timer))
 		return;
 
 	rcu_read_lock();
 
-	kworker = rcu_dereference(group->poll_kworker);
+	task = rcu_dereference(group->poll_task);
 	/*
 	 * kworker might be NULL in case psi_trigger_destroy races with
 	 * psi_task_change (hotpath) which can't use locks
 	 */
-	if (likely(kworker))
-		kthread_queue_delayed_work(kworker, &group->poll_work, delay);
-	else
-		atomic_set(&group->poll_scheduled, 0);
+	if (likely(task))
+		mod_timer(&group->poll_timer, jiffies + delay);
 
 	rcu_read_unlock();
 }
 
-static void psi_poll_work(struct kthread_work *work)
+static void psi_poll_work(struct psi_group *group)
 {
-	struct kthread_delayed_work *dwork;
-	struct psi_group *group;
 	u32 changed_states;
 	u64 now;
 
-	dwork = container_of(work, struct kthread_delayed_work, work);
-	group = container_of(dwork, struct psi_group, poll_work);
-
-	atomic_set(&group->poll_scheduled, 0);
-
 	mutex_lock(&group->trigger_lock);
 
 	now = sched_clock();
@@ -623,6 +613,32 @@ out:
 	mutex_unlock(&group->trigger_lock);
 }
 
+static int psi_poll_worker(void *data)
+{
+	struct psi_group *group = (struct psi_group *)data;
+
+	sched_set_fifo_low(current);
+
+	while (true) {
+		wait_event_interruptible(group->poll_wait,
+				atomic_cmpxchg(&group->poll_wakeup, 1, 0) ||
+				kthread_should_stop());
+		if (kthread_should_stop())
+			break;
+
+		psi_poll_work(group);
+	}
+	return 0;
+}
+
+static void poll_timer_fn(struct timer_list *t)
+{
+	struct psi_group *group = from_timer(group, t, poll_timer);
+
+	atomic_set(&group->poll_wakeup, 1);
+	wake_up_interruptible(&group->poll_wait);
+}
+
 static void record_times(struct psi_group_cpu *groupc, int cpu,
 			 bool memstall_tick)
 {
@@ -669,13 +685,14 @@ static void record_times(struct psi_group_cpu *groupc, int cpu,
 		groupc->times[PSI_NONIDLE] += delta;
 }
 
-static u32 psi_group_change(struct psi_group *group, int cpu,
-			    unsigned int clear, unsigned int set)
+static void psi_group_change(struct psi_group *group, int cpu,
+			     unsigned int clear, unsigned int set,
+			     bool wake_clock)
 {
 	struct psi_group_cpu *groupc;
+	u32 state_mask = 0;
 	unsigned int t, m;
 	enum psi_states s;
-	u32 state_mask = 0;
 
 	groupc = per_cpu_ptr(group->pcpu, cpu);
 
@@ -695,10 +712,10 @@ static u32 psi_group_change(struct psi_group *group, int cpu,
 		if (!(m & (1 << t)))
 			continue;
 		if (groupc->tasks[t] == 0 && !psi_bug) {
-			printk_deferred(KERN_ERR "psi: task underflow! cpu=%d t=%d tasks=[%u %u %u] clear=%x set=%x\n",
+			printk_deferred(KERN_ERR "psi: task underflow! cpu=%d t=%d tasks=[%u %u %u %u] clear=%x set=%x\n",
 					cpu, t, groupc->tasks[0],
 					groupc->tasks[1], groupc->tasks[2],
-					clear, set);
+					groupc->tasks[3], clear, set);
 			psi_bug = 1;
 		}
 		groupc->tasks[t]--;
@@ -717,7 +734,11 @@ static u32 psi_group_change(struct psi_group *group, int cpu,
 
 	write_seqcount_end(&groupc->seq);
 
-	return state_mask;
+	if (state_mask & group->poll_states)
+		psi_schedule_poll_work(group, 1);
+
+	if (wake_clock && !delayed_work_pending(&group->avgs_work))
+		schedule_delayed_work(&group->avgs_work, PSI_FREQ);
 }
 
 static struct psi_group *iterate_groups(struct task_struct *task, void **iter)
@@ -744,27 +765,32 @@ static struct psi_group *iterate_groups(struct task_struct *task, void **iter)
 	return &psi_system;
 }
 
-void psi_task_change(struct task_struct *task, int clear, int set)
+static void psi_flags_change(struct task_struct *task, int clear, int set)
 {
-	int cpu = task_cpu(task);
-	struct psi_group *group;
-	bool wake_clock = true;
-	void *iter = NULL;
-
-	if (!task->pid)
-		return;
-
 	if (((task->psi_flags & set) ||
 	     (task->psi_flags & clear) != clear) &&
 	    !psi_bug) {
 		printk_deferred(KERN_ERR "psi: inconsistent task state! task=%d:%s cpu=%d psi_flags=%x clear=%x set=%x\n",
-				task->pid, task->comm, cpu,
+				task->pid, task->comm, task_cpu(task),
 				task->psi_flags, clear, set);
 		psi_bug = 1;
 	}
 
 	task->psi_flags &= ~clear;
 	task->psi_flags |= set;
+}
+
+void psi_task_change(struct task_struct *task, int clear, int set)
+{
+	int cpu = task_cpu(task);
+	struct psi_group *group;
+	bool wake_clock = true;
+	void *iter = NULL;
+
+	if (!task->pid)
+		return;
+
+	psi_flags_change(task, clear, set);
 
 	/*
 	 * Periodic aggregation shuts off if there is a period of no
@@ -777,14 +803,51 @@ void psi_task_change(struct task_struct *task, int clear, int set)
 		     wq_worker_last_func(task) == psi_avgs_work))
 		wake_clock = false;
 
-	while ((group = iterate_groups(task, &iter))) {
-		u32 state_mask = psi_group_change(group, cpu, clear, set);
+	while ((group = iterate_groups(task, &iter)))
+		psi_group_change(group, cpu, clear, set, wake_clock);
+}
+
+void psi_task_switch(struct task_struct *prev, struct task_struct *next,
+		     bool sleep)
+{
+	struct psi_group *group, *common = NULL;
+	int cpu = task_cpu(prev);
+	void *iter;
+
+	if (next->pid) {
+		psi_flags_change(next, 0, TSK_ONCPU);
+		/*
+		 * When moving state between tasks, the group that
+		 * contains them both does not change: we can stop
+		 * updating the tree once we reach the first common
+		 * ancestor. Iterate @next's ancestors until we
+		 * encounter @prev's state.
+		 */
+		iter = NULL;
+		while ((group = iterate_groups(next, &iter))) {
+			if (per_cpu_ptr(group->pcpu, cpu)->tasks[NR_ONCPU]) {
+				common = group;
+				break;
+			}
+
+			psi_group_change(group, cpu, 0, TSK_ONCPU, true);
+		}
+	}
 
-		if (state_mask & group->poll_states)
-			psi_schedule_poll_work(group, 1);
+	/*
+	 * If this is a voluntary sleep, dequeue will have taken care
+	 * of the outgoing TSK_ONCPU alongside TSK_RUNNING already. We
+	 * only need to deal with it during preemption.
+	 */
+	if (sleep)
+		return;
+
+	if (prev->pid) {
+		psi_flags_change(prev, TSK_ONCPU, 0);
 
-		if (wake_clock && !delayed_work_pending(&group->avgs_work))
-			schedule_delayed_work(&group->avgs_work, PSI_FREQ);
+		iter = NULL;
+		while ((group = iterate_groups(prev, &iter)) && group != common)
+			psi_group_change(group, cpu, TSK_ONCPU, 0, true);
 	}
 }
 
@@ -818,17 +881,17 @@ void psi_memstall_enter(unsigned long *flags)
 	if (static_branch_likely(&psi_disabled))
 		return;
 
-	*flags = current->flags & PF_MEMSTALL;
+	*flags = current->in_memstall;
 	if (*flags)
 		return;
 	/*
-	 * PF_MEMSTALL setting & accounting needs to be atomic wrt
+	 * in_memstall setting & accounting needs to be atomic wrt
 	 * changes to the task's scheduling state, otherwise we can
 	 * race with CPU migration.
 	 */
 	rq = this_rq_lock_irq(&rf);
 
-	current->flags |= PF_MEMSTALL;
+	current->in_memstall = 1;
 	psi_task_change(current, 0, TSK_MEMSTALL);
 
 	rq_unlock_irq(rq, &rf);
@@ -851,13 +914,13 @@ void psi_memstall_leave(unsigned long *flags)
 	if (*flags)
 		return;
 	/*
-	 * PF_MEMSTALL clearing & accounting needs to be atomic wrt
+	 * in_memstall clearing & accounting needs to be atomic wrt
 	 * changes to the task's scheduling state, otherwise we could
 	 * race with CPU migration.
 	 */
 	rq = this_rq_lock_irq(&rf);
 
-	current->flags &= ~PF_MEMSTALL;
+	current->in_memstall = 0;
 	psi_task_change(current, TSK_MEMSTALL, 0);
 
 	rq_unlock_irq(rq, &rf);
@@ -916,12 +979,14 @@ void cgroup_move_task(struct task_struct *task, struct css_set *to)
 
 	rq = task_rq_lock(task, &rf);
 
-	if (task_on_rq_queued(task))
+	if (task_on_rq_queued(task)) {
 		task_flags = TSK_RUNNING;
-	else if (task->in_iowait)
+		if (task_current(rq, task))
+			task_flags |= TSK_ONCPU;
+	} else if (task->in_iowait)
 		task_flags = TSK_IOWAIT;
 
-	if (task->flags & PF_MEMSTALL)
+	if (task->in_memstall)
 		task_flags |= TSK_MEMSTALL;
 
 	if (task_flags)
@@ -1050,22 +1115,20 @@ struct psi_trigger *psi_trigger_create(struct psi_group *group,
 
 	mutex_lock(&group->trigger_lock);
 
-	if (!rcu_access_pointer(group->poll_kworker)) {
-		struct sched_param param = {
-			.sched_priority = 1,
-		};
-		struct kthread_worker *kworker;
+	if (!rcu_access_pointer(group->poll_task)) {
+		struct task_struct *task;
 
-		kworker = kthread_create_worker(0, "psimon");
-		if (IS_ERR(kworker)) {
+		task = kthread_create(psi_poll_worker, group, "psimon");
+		if (IS_ERR(task)) {
 			kfree(t);
 			mutex_unlock(&group->trigger_lock);
-			return ERR_CAST(kworker);
+			return ERR_CAST(task);
 		}
-		sched_setscheduler_nocheck(kworker->task, SCHED_FIFO, &param);
-		kthread_init_delayed_work(&group->poll_work,
-				psi_poll_work);
-		rcu_assign_pointer(group->poll_kworker, kworker);
+		atomic_set(&group->poll_wakeup, 0);
+		init_waitqueue_head(&group->poll_wait);
+		wake_up_process(task);
+		timer_setup(&group->poll_timer, poll_timer_fn, 0);
+		rcu_assign_pointer(group->poll_task, task);
 	}
 
 	list_add(&t->node, &group->triggers);
@@ -1083,7 +1146,7 @@ static void psi_trigger_destroy(struct kref *ref)
 {
 	struct psi_trigger *t = container_of(ref, struct psi_trigger, refcount);
 	struct psi_group *group = t->group;
-	struct kthread_worker *kworker_to_destroy = NULL;
+	struct task_struct *task_to_destroy = NULL;
 
 	if (static_branch_likely(&psi_disabled))
 		return;
@@ -1109,13 +1172,13 @@ static void psi_trigger_destroy(struct kref *ref)
 			period = min(period, div_u64(tmp->win.size,
 					UPDATES_PER_WINDOW));
 		group->poll_min_period = period;
-		/* Destroy poll_kworker when the last trigger is destroyed */
+		/* Destroy poll_task when the last trigger is destroyed */
 		if (group->poll_states == 0) {
 			group->polling_until = 0;
-			kworker_to_destroy = rcu_dereference_protected(
-					group->poll_kworker,
+			task_to_destroy = rcu_dereference_protected(
+					group->poll_task,
 					lockdep_is_held(&group->trigger_lock));
-			rcu_assign_pointer(group->poll_kworker, NULL);
+			rcu_assign_pointer(group->poll_task, NULL);
 		}
 	}
 
@@ -1123,25 +1186,23 @@ static void psi_trigger_destroy(struct kref *ref)
 
 	/*
 	 * Wait for both *trigger_ptr from psi_trigger_replace and
-	 * poll_kworker RCUs to complete their read-side critical sections
-	 * before destroying the trigger and optionally the poll_kworker
+	 * poll_task RCUs to complete their read-side critical sections
+	 * before destroying the trigger and optionally the poll_task
 	 */
 	synchronize_rcu();
 	/*
 	 * Destroy the kworker after releasing trigger_lock to prevent a
 	 * deadlock while waiting for psi_poll_work to acquire trigger_lock
 	 */
-	if (kworker_to_destroy) {
+	if (task_to_destroy) {
 		/*
 		 * After the RCU grace period has expired, the worker
-		 * can no longer be found through group->poll_kworker.
+		 * can no longer be found through group->poll_task.
 		 * But it might have been already scheduled before
 		 * that - deschedule it cleanly before destroying it.
 		 */
-		kthread_cancel_delayed_work_sync(&group->poll_work);
-		atomic_set(&group->poll_scheduled, 0);
-
-		kthread_destroy_worker(kworker_to_destroy);
+		del_timer_sync(&group->poll_timer);
+		kthread_stop(task_to_destroy);
 	}
 	kfree(t);
 }
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 4043abe45459..f215eea6a966 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -9,6 +9,8 @@
 
 int sched_rr_timeslice = RR_TIMESLICE;
 int sysctl_sched_rr_timeslice = (MSEC_PER_SEC / HZ) * RR_TIMESLICE;
+/* More than 4 hours if BW_SHIFT equals 20. */
+static const u64 max_rt_runtime = MAX_BW;
 
 static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun);
 
@@ -1475,6 +1477,13 @@ select_task_rq_rt(struct task_struct *p, int cpu, int sd_flag, int flags)
 		int target = find_lowest_rq(p);
 
 		/*
+		 * Bail out if we were forcing a migration to find a better
+		 * fitting CPU but our search failed.
+		 */
+		if (!test && target != -1 && !rt_task_fits_capacity(p, target))
+			goto out_unlock;
+
+		/*
 		 * Don't bother moving it if the destination CPU is
 		 * not running a lower priority task.
 		 */
@@ -1482,6 +1491,8 @@ select_task_rq_rt(struct task_struct *p, int cpu, int sd_flag, int flags)
 		    p->prio < cpu_rq(target)->rt.highest_prio.curr)
 			cpu = target;
 	}
+
+out_unlock:
 	rcu_read_unlock();
 
 out:
@@ -1495,7 +1506,7 @@ static void check_preempt_equal_prio(struct rq *rq, struct task_struct *p)
 	 * let's hope p can move out.
 	 */
 	if (rq->curr->nr_cpus_allowed == 1 ||
-	    !cpupri_find(&rq->rd->cpupri, rq->curr, NULL, NULL))
+	    !cpupri_find(&rq->rd->cpupri, rq->curr, NULL))
 		return;
 
 	/*
@@ -1503,7 +1514,7 @@ static void check_preempt_equal_prio(struct rq *rq, struct task_struct *p)
 	 * see if it is pushed or pulled somewhere else.
 	 */
 	if (p->nr_cpus_allowed != 1 &&
-	    cpupri_find(&rq->rd->cpupri, p, NULL, NULL))
+	    cpupri_find(&rq->rd->cpupri, p, NULL))
 		return;
 
 	/*
@@ -1647,8 +1658,7 @@ static void put_prev_task_rt(struct rq *rq, struct task_struct *p)
 static int pick_rt_task(struct rq *rq, struct task_struct *p, int cpu)
 {
 	if (!task_running(rq, p) &&
-	    cpumask_test_cpu(cpu, p->cpus_ptr) &&
-	    rt_task_fits_capacity(p, cpu))
+	    cpumask_test_cpu(cpu, p->cpus_ptr))
 		return 1;
 
 	return 0;
@@ -1682,6 +1692,7 @@ static int find_lowest_rq(struct task_struct *task)
 	struct cpumask *lowest_mask = this_cpu_cpumask_var_ptr(local_cpu_mask);
 	int this_cpu = smp_processor_id();
 	int cpu      = task_cpu(task);
+	int ret;
 
 	/* Make sure the mask is initialized first */
 	if (unlikely(!lowest_mask))
@@ -1690,8 +1701,22 @@ static int find_lowest_rq(struct task_struct *task)
 	if (task->nr_cpus_allowed == 1)
 		return -1; /* No other targets possible */
 
-	if (!cpupri_find(&task_rq(task)->rd->cpupri, task, lowest_mask,
-			 rt_task_fits_capacity))
+	/*
+	 * If we're on asym system ensure we consider the different capacities
+	 * of the CPUs when searching for the lowest_mask.
+	 */
+	if (static_branch_unlikely(&sched_asym_cpucapacity)) {
+
+		ret = cpupri_find_fitness(&task_rq(task)->rd->cpupri,
+					  task, lowest_mask,
+					  rt_task_fits_capacity);
+	} else {
+
+		ret = cpupri_find(&task_rq(task)->rd->cpupri,
+				  task, lowest_mask);
+	}
+
+	if (!ret)
 		return -1; /* No targets found */
 
 	/*
@@ -2202,7 +2227,7 @@ static void task_woken_rt(struct rq *rq, struct task_struct *p)
 			    (rq->curr->nr_cpus_allowed < 2 ||
 			     rq->curr->prio <= p->prio);
 
-	if (need_to_push || !rt_task_fits_capacity(p, cpu_of(rq)))
+	if (need_to_push)
 		push_rt_tasks(rq);
 }
 
@@ -2274,10 +2299,7 @@ static void switched_to_rt(struct rq *rq, struct task_struct *p)
 	 */
 	if (task_on_rq_queued(p) && rq->curr != p) {
 #ifdef CONFIG_SMP
-		bool need_to_push = rq->rt.overloaded ||
-				    !rt_task_fits_capacity(p, cpu_of(rq));
-
-		if (p->nr_cpus_allowed > 1 && need_to_push)
+		if (p->nr_cpus_allowed > 1 && rq->rt.overloaded)
 			rt_queue_push_tasks(rq);
 #endif /* CONFIG_SMP */
 		if (p->prio < rq->curr->prio && cpu_online(cpu_of(rq)))
@@ -2407,8 +2429,8 @@ static unsigned int get_rr_interval_rt(struct rq *rq, struct task_struct *task)
 		return 0;
 }
 
-const struct sched_class rt_sched_class = {
-	.next			= &fair_sched_class,
+const struct sched_class rt_sched_class
+	__attribute__((section("__rt_sched_class"))) = {
 	.enqueue_task		= enqueue_task_rt,
 	.dequeue_task		= dequeue_task_rt,
 	.yield_task		= yield_task_rt,
@@ -2449,10 +2471,11 @@ const struct sched_class rt_sched_class = {
  */
 static DEFINE_MUTEX(rt_constraints_mutex);
 
-/* Must be called with tasklist_lock held */
 static inline int tg_has_rt_tasks(struct task_group *tg)
 {
-	struct task_struct *g, *p;
+	struct task_struct *task;
+	struct css_task_iter it;
+	int ret = 0;
 
 	/*
 	 * Autogroups do not have RT tasks; see autogroup_create().
@@ -2460,12 +2483,12 @@ static inline int tg_has_rt_tasks(struct task_group *tg)
 	if (task_group_is_autogroup(tg))
 		return 0;
 
-	for_each_process_thread(g, p) {
-		if (rt_task(p) && task_group(p) == tg)
-			return 1;
-	}
+	css_task_iter_start(&tg->css, 0, &it);
+	while (!ret && (task = css_task_iter_next(&it)))
+		ret |= rt_task(task);
+	css_task_iter_end(&it);
 
-	return 0;
+	return ret;
 }
 
 struct rt_schedulable_data {
@@ -2496,9 +2519,10 @@ static int tg_rt_schedulable(struct task_group *tg, void *data)
 		return -EINVAL;
 
 	/*
-	 * Ensure we don't starve existing RT tasks.
+	 * Ensure we don't starve existing RT tasks if runtime turns zero.
 	 */
-	if (rt_bandwidth_enabled() && !runtime && tg_has_rt_tasks(tg))
+	if (rt_bandwidth_enabled() && !runtime &&
+	    tg->rt_bandwidth.rt_runtime && tg_has_rt_tasks(tg))
 		return -EBUSY;
 
 	total = to_ratio(period, runtime);
@@ -2563,8 +2587,13 @@ static int tg_set_rt_bandwidth(struct task_group *tg,
 	if (rt_period == 0)
 		return -EINVAL;
 
+	/*
+	 * Bound quota to defend quota against overflow during bandwidth shift.
+	 */
+	if (rt_runtime != RUNTIME_INF && rt_runtime > max_rt_runtime)
+		return -EINVAL;
+
 	mutex_lock(&rt_constraints_mutex);
-	read_lock(&tasklist_lock);
 	err = __rt_schedulable(tg, rt_period, rt_runtime);
 	if (err)
 		goto unlock;
@@ -2582,7 +2611,6 @@ static int tg_set_rt_bandwidth(struct task_group *tg,
 	}
 	raw_spin_unlock_irq(&tg->rt_bandwidth.rt_runtime_lock);
 unlock:
-	read_unlock(&tasklist_lock);
 	mutex_unlock(&rt_constraints_mutex);
 
 	return err;
@@ -2641,9 +2669,7 @@ static int sched_rt_global_constraints(void)
 	int ret = 0;
 
 	mutex_lock(&rt_constraints_mutex);
-	read_lock(&tasklist_lock);
 	ret = __rt_schedulable(NULL, 0, 0);
-	read_unlock(&tasklist_lock);
 	mutex_unlock(&rt_constraints_mutex);
 
 	return ret;
@@ -2684,7 +2710,9 @@ static int sched_rt_global_validate(void)
 		return -EINVAL;
 
 	if ((sysctl_sched_rt_runtime != RUNTIME_INF) &&
-		(sysctl_sched_rt_runtime > sysctl_sched_rt_period))
+		((sysctl_sched_rt_runtime > sysctl_sched_rt_period) ||
+		 ((u64)sysctl_sched_rt_runtime *
+			NSEC_PER_USEC > max_rt_runtime)))
 		return -EINVAL;
 
 	return 0;
@@ -2696,9 +2724,8 @@ static void sched_rt_do_global(void)
 	def_rt_bandwidth.rt_period = ns_to_ktime(global_rt_period());
 }
 
-int sched_rt_handler(struct ctl_table *table, int write,
-		void __user *buffer, size_t *lenp,
-		loff_t *ppos)
+int sched_rt_handler(struct ctl_table *table, int write, void *buffer,
+		size_t *lenp, loff_t *ppos)
 {
 	int old_period, old_runtime;
 	static DEFINE_MUTEX(mutex);
@@ -2736,9 +2763,8 @@ undo:
 	return ret;
 }
 
-int sched_rr_handler(struct ctl_table *table, int write,
-		void __user *buffer, size_t *lenp,
-		loff_t *ppos)
+int sched_rr_handler(struct ctl_table *table, int write, void *buffer,
+		size_t *lenp, loff_t *ppos)
 {
 	int ret;
 	static DEFINE_MUTEX(mutex);
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 9ea647835fd6..28709f6b0975 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -67,6 +67,7 @@
 #include <linux/tsacct_kern.h>
 
 #include <asm/tlb.h>
+#include <asm-generic/vmlinux.lds.h>
 
 #ifdef CONFIG_PARAVIRT
 # include <asm/paravirt.h>
@@ -75,6 +76,8 @@
 #include "cpupri.h"
 #include "cpudeadline.h"
 
+#include <trace/events/sched.h>
+
 #ifdef CONFIG_SCHED_DEBUG
 # define SCHED_WARN_ON(x)	WARN_ONCE(x, #x)
 #else
@@ -96,6 +99,7 @@ extern atomic_long_t calc_load_tasks;
 extern void calc_global_load_tick(struct rq *this_rq);
 extern long calc_load_fold_active(struct rq *this_rq, long adjust);
 
+extern void call_trace_sched_update_nr_running(struct rq *rq, int count);
 /*
  * Helpers for converting nanosecond timing to jiffy resolution
  */
@@ -118,7 +122,13 @@ extern long calc_load_fold_active(struct rq *this_rq, long adjust);
 #ifdef CONFIG_64BIT
 # define NICE_0_LOAD_SHIFT	(SCHED_FIXEDPOINT_SHIFT + SCHED_FIXEDPOINT_SHIFT)
 # define scale_load(w)		((w) << SCHED_FIXEDPOINT_SHIFT)
-# define scale_load_down(w)	((w) >> SCHED_FIXEDPOINT_SHIFT)
+# define scale_load_down(w) \
+({ \
+	unsigned long __w = (w); \
+	if (__w) \
+		__w = max(2UL, __w >> SCHED_FIXEDPOINT_SHIFT); \
+	__w; \
+})
 #else
 # define NICE_0_LOAD_SHIFT	(SCHED_FIXEDPOINT_SHIFT)
 # define scale_load(w)		(w)
@@ -189,6 +199,12 @@ static inline int task_has_dl_policy(struct task_struct *p)
 
 #define cap_scale(v, s) ((v)*(s) >> SCHED_CAPACITY_SHIFT)
 
+static inline void update_avg(u64 *avg, u64 sample)
+{
+	s64 diff = sample - *avg;
+	*avg += diff / 8;
+}
+
 /*
  * !! For sched_setattr_nocheck() (kernel) only !!
  *
@@ -298,14 +314,28 @@ void __dl_add(struct dl_bw *dl_b, u64 tsk_bw, int cpus)
 	__dl_update(dl_b, -((s32)tsk_bw / cpus));
 }
 
-static inline
-bool __dl_overflow(struct dl_bw *dl_b, int cpus, u64 old_bw, u64 new_bw)
+static inline bool __dl_overflow(struct dl_bw *dl_b, unsigned long cap,
+				 u64 old_bw, u64 new_bw)
 {
 	return dl_b->bw != -1 &&
-	       dl_b->bw * cpus < dl_b->total_bw - old_bw + new_bw;
+	       cap_scale(dl_b->bw, cap) < dl_b->total_bw - old_bw + new_bw;
+}
+
+/*
+ * Verify the fitness of task @p to run on @cpu taking into account the
+ * CPU original capacity and the runtime/deadline ratio of the task.
+ *
+ * The function will return true if the CPU original capacity of the
+ * @cpu scaled by SCHED_CAPACITY_SCALE >= runtime/deadline ratio of the
+ * task and false otherwise.
+ */
+static inline bool dl_task_fits_capacity(struct task_struct *p, int cpu)
+{
+	unsigned long cap = arch_scale_cpu_capacity(cpu);
+
+	return cap_scale(p->dl.dl_deadline, cap) >= p->dl.dl_runtime;
 }
 
-extern void dl_change_utilization(struct task_struct *p, u64 new_bw);
 extern void init_dl_bw(struct dl_bw *dl_b);
 extern int  sched_dl_global_validate(void);
 extern void sched_dl_do_global(void);
@@ -338,7 +368,6 @@ struct cfs_bandwidth {
 
 	u8			idle;
 	u8			period_active;
-	u8			distribute_running;
 	u8			slack_started;
 	struct hrtimer		period_timer;
 	struct hrtimer		slack_timer;
@@ -489,7 +518,6 @@ struct cfs_bandwidth { };
 /* CFS-related fields in a runqueue */
 struct cfs_rq {
 	struct load_weight	load;
-	unsigned long		runnable_weight;
 	unsigned int		nr_running;
 	unsigned int		h_nr_running;      /* SCHED_{NORMAL,BATCH,IDLE} */
 	unsigned int		idle_h_nr_running; /* SCHED_IDLE */
@@ -528,7 +556,7 @@ struct cfs_rq {
 		int		nr;
 		unsigned long	load_avg;
 		unsigned long	util_avg;
-		unsigned long	runnable_sum;
+		unsigned long	runnable_avg;
 	} removed;
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
@@ -688,8 +716,30 @@ struct dl_rq {
 #ifdef CONFIG_FAIR_GROUP_SCHED
 /* An entity is a task if it doesn't "own" a runqueue */
 #define entity_is_task(se)	(!se->my_q)
+
+static inline void se_update_runnable(struct sched_entity *se)
+{
+	if (!entity_is_task(se))
+		se->runnable_weight = se->my_q->h_nr_running;
+}
+
+static inline long se_runnable(struct sched_entity *se)
+{
+	if (entity_is_task(se))
+		return !!se->on_rq;
+	else
+		return se->runnable_weight;
+}
+
 #else
 #define entity_is_task(se)	1
+
+static inline void se_update_runnable(struct sched_entity *se) {}
+
+static inline long se_runnable(struct sched_entity *se)
+{
+	return !!se->on_rq;
+}
 #endif
 
 #ifdef CONFIG_SMP
@@ -701,10 +751,6 @@ static inline long se_weight(struct sched_entity *se)
 	return scale_load_down(se->load.weight);
 }
 
-static inline long se_runnable(struct sched_entity *se)
-{
-	return scale_load_down(se->runnable_weight);
-}
 
 static inline bool sched_asym_prefer(int a, int b)
 {
@@ -835,6 +881,8 @@ struct uclamp_rq {
 	unsigned int value;
 	struct uclamp_bucket bucket[UCLAMP_BUCKETS];
 };
+
+DECLARE_STATIC_KEY_FALSE(sched_uclamp_used);
 #endif /* CONFIG_UCLAMP_TASK */
 
 /*
@@ -860,15 +908,17 @@ struct rq {
 #endif
 #ifdef CONFIG_NO_HZ_COMMON
 #ifdef CONFIG_SMP
-	unsigned long		last_load_update_tick;
 	unsigned long		last_blocked_load_update_tick;
 	unsigned int		has_blocked_load;
+	call_single_data_t	nohz_csd;
 #endif /* CONFIG_SMP */
 	unsigned int		nohz_tick_stopped;
-	atomic_t nohz_flags;
+	atomic_t		nohz_flags;
 #endif /* CONFIG_NO_HZ_COMMON */
 
-	unsigned long		nr_load_updates;
+#ifdef CONFIG_SMP
+	unsigned int		ttwu_pending;
+#endif
 	u64			nr_switches;
 
 #ifdef CONFIG_UCLAMP_TASK
@@ -924,6 +974,7 @@ struct rq {
 
 	struct callback_head	*balance_callback;
 
+	unsigned char		nohz_idle_balance;
 	unsigned char		idle_balance;
 
 	unsigned long		misfit_task_load;
@@ -944,12 +995,15 @@ struct rq {
 #ifdef CONFIG_HAVE_SCHED_AVG_IRQ
 	struct sched_avg	avg_irq;
 #endif
+#ifdef CONFIG_SCHED_THERMAL_PRESSURE
+	struct sched_avg	avg_thermal;
+#endif
 	u64			idle_stamp;
 	u64			avg_idle;
 
 	/* This is used to determine avg_idle's max value */
 	u64			max_idle_balance_cost;
-#endif
+#endif /* CONFIG_SMP */
 
 #ifdef CONFIG_IRQ_TIME_ACCOUNTING
 	u64			prev_irq_time;
@@ -967,7 +1021,6 @@ struct rq {
 
 #ifdef CONFIG_SCHED_HRTICK
 #ifdef CONFIG_SMP
-	int			hrtick_csd_pending;
 	call_single_data_t	hrtick_csd;
 #endif
 	struct hrtimer		hrtick_timer;
@@ -991,10 +1044,6 @@ struct rq {
 	unsigned int		ttwu_local;
 #endif
 
-#ifdef CONFIG_SMP
-	struct llist_head	wake_list;
-#endif
-
 #ifdef CONFIG_CPU_IDLE
 	/* Must be inspected within a rcu lock section */
 	struct cpuidle_state	*idle_state;
@@ -1107,6 +1156,24 @@ static inline u64 rq_clock_task(struct rq *rq)
 	return rq->clock_task;
 }
 
+/**
+ * By default the decay is the default pelt decay period.
+ * The decay shift can change the decay period in
+ * multiples of 32.
+ *  Decay shift		Decay period(ms)
+ *	0			32
+ *	1			64
+ *	2			128
+ *	3			256
+ *	4			512
+ */
+extern int sched_thermal_decay_shift;
+
+static inline u64 rq_clock_thermal(struct rq *rq)
+{
+	return rq_clock_task(rq) >> sched_thermal_decay_shift;
+}
+
 static inline void rq_clock_skip_update(struct rq *rq)
 {
 	lockdep_assert_held(&rq->lock);
@@ -1136,6 +1203,16 @@ struct rq_flags {
 #endif
 };
 
+/*
+ * Lockdep annotation that avoids accidental unlocks; it's like a
+ * sticky/continuous lockdep_assert_held().
+ *
+ * This avoids code that has access to 'struct rq *rq' (basically everything in
+ * the scheduler) from accidentally unlocking the rq if they do not also have a
+ * copy of the (on-stack) 'struct rq_flags rf'.
+ *
+ * Also see Documentation/locking/lockdep-design.rst.
+ */
 static inline void rq_pin_lock(struct rq *rq, struct rq_flags *rf)
 {
 	rf->cookie = lockdep_pin_lock(&rq->lock);
@@ -1320,8 +1397,6 @@ queue_balance_callback(struct rq *rq,
 	rq->balance_callback = head;
 }
 
-extern void sched_ttwu_pending(void);
-
 #define rcu_dereference_check_sched_domain(p) \
 	rcu_dereference_check((p), \
 			      lockdep_is_held(&sched_domains_mutex))
@@ -1337,8 +1412,6 @@ extern void sched_ttwu_pending(void);
 	for (__sd = rcu_dereference_check_sched_domain(cpu_rq(cpu)->sd); \
 			__sd; __sd = __sd->parent)
 
-#define for_each_lower_domain(sd) for (; sd; sd = sd->child)
-
 /**
  * highest_flag_domain - Return highest sched_domain containing flag.
  * @cpu:	The CPU whose highest level of sched domain is to
@@ -1416,7 +1489,7 @@ struct sched_group {
 	 * by attaching extra space to the end of the structure,
 	 * depending on how many CPUs the kernel has booted up with)
 	 */
-	unsigned long		cpumask[0];
+	unsigned long		cpumask[];
 };
 
 static inline struct cpumask *sched_group_span(struct sched_group *sg)
@@ -1459,15 +1532,11 @@ static inline void unregister_sched_domain_sysctl(void)
 }
 #endif
 
-extern int newidle_balance(struct rq *this_rq, struct rq_flags *rf);
-
-#else
-
-static inline void sched_ttwu_pending(void) { }
+extern void flush_smp_call_function_from_idle(void);
 
-static inline int newidle_balance(struct rq *this_rq, struct rq_flags *rf) { return 0; }
-
-#endif /* CONFIG_SMP */
+#else /* !CONFIG_SMP: */
+static inline void flush_smp_call_function_from_idle(void) { }
+#endif
 
 #include "stats.h"
 #include "autogroup.h"
@@ -1643,7 +1712,8 @@ static inline int task_on_rq_migrating(struct task_struct *p)
  */
 #define WF_SYNC			0x01		/* Waker goes to sleep after wakeup */
 #define WF_FORK			0x02		/* Child wakeup after fork */
-#define WF_MIGRATED		0x4		/* Internal use, task got migrated */
+#define WF_MIGRATED		0x04		/* Internal use, task got migrated */
+#define WF_ON_CPU		0x08		/* Wakee is on_cpu */
 
 /*
  * To aid in avoiding the subversion of "niceness" due to uneven distribution
@@ -1700,7 +1770,6 @@ extern const u32		sched_prio_to_wmult[40];
 #define RETRY_TASK		((void *)-1UL)
 
 struct sched_class {
-	const struct sched_class *next;
 
 #ifdef CONFIG_UCLAMP_TASK
 	int uclamp_enabled;
@@ -1709,7 +1778,7 @@ struct sched_class {
 	void (*enqueue_task) (struct rq *rq, struct task_struct *p, int flags);
 	void (*dequeue_task) (struct rq *rq, struct task_struct *p, int flags);
 	void (*yield_task)   (struct rq *rq);
-	bool (*yield_to_task)(struct rq *rq, struct task_struct *p, bool preempt);
+	bool (*yield_to_task)(struct rq *rq, struct task_struct *p);
 
 	void (*check_preempt_curr)(struct rq *rq, struct task_struct *p, int flags);
 
@@ -1757,7 +1826,7 @@ struct sched_class {
 #ifdef CONFIG_FAIR_GROUP_SCHED
 	void (*task_change_group)(struct task_struct *p, int type);
 #endif
-};
+} __aligned(STRUCT_ALIGNMENT); /* STRUCT_ALIGN(), vmlinux.lds.h */
 
 static inline void put_prev_task(struct rq *rq, struct task_struct *prev)
 {
@@ -1771,17 +1840,18 @@ static inline void set_next_task(struct rq *rq, struct task_struct *next)
 	next->sched_class->set_next_task(rq, next, false);
 }
 
-#ifdef CONFIG_SMP
-#define sched_class_highest (&stop_sched_class)
-#else
-#define sched_class_highest (&dl_sched_class)
-#endif
+/* Defined in include/asm-generic/vmlinux.lds.h */
+extern struct sched_class __begin_sched_classes[];
+extern struct sched_class __end_sched_classes[];
+
+#define sched_class_highest (__end_sched_classes - 1)
+#define sched_class_lowest  (__begin_sched_classes - 1)
 
 #define for_class_range(class, _from, _to) \
-	for (class = (_from); class != (_to); class = class->next)
+	for (class = (_from); class != (_to); class--)
 
 #define for_each_class(class) \
-	for_class_range(class, sched_class_highest, NULL)
+	for_class_range(class, sched_class_highest, sched_class_lowest)
 
 extern const struct sched_class stop_sched_class;
 extern const struct sched_class dl_sched_class;
@@ -1869,11 +1939,12 @@ extern struct dl_bandwidth def_dl_bandwidth;
 extern void init_dl_bandwidth(struct dl_bandwidth *dl_b, u64 period, u64 runtime);
 extern void init_dl_task_timer(struct sched_dl_entity *dl_se);
 extern void init_dl_inactive_task_timer(struct sched_dl_entity *dl_se);
-extern void init_dl_rq_bw_ratio(struct dl_rq *dl_rq);
 
 #define BW_SHIFT		20
 #define BW_UNIT			(1 << BW_SHIFT)
 #define RATIO_SHIFT		8
+#define MAX_BW_BITS		(64 - BW_SHIFT)
+#define MAX_BW			((1ULL << MAX_BW_BITS) - 1)
 unsigned long to_ratio(u64 period, u64 runtime);
 
 extern void init_entity_runnable_average(struct sched_entity *se);
@@ -1890,12 +1961,7 @@ extern int __init sched_tick_offload_init(void);
  */
 static inline void sched_update_tick_dependency(struct rq *rq)
 {
-	int cpu;
-
-	if (!tick_nohz_full_enabled())
-		return;
-
-	cpu = cpu_of(rq);
+	int cpu = cpu_of(rq);
 
 	if (!tick_nohz_full_cpu(cpu))
 		return;
@@ -1915,6 +1981,9 @@ static inline void add_nr_running(struct rq *rq, unsigned count)
 	unsigned prev_nr = rq->nr_running;
 
 	rq->nr_running = prev_nr + count;
+	if (trace_sched_update_nr_running_tp_enabled()) {
+		call_trace_sched_update_nr_running(rq, count);
+	}
 
 #ifdef CONFIG_SMP
 	if (prev_nr < 2 && rq->nr_running >= 2) {
@@ -1929,6 +1998,10 @@ static inline void add_nr_running(struct rq *rq, unsigned count)
 static inline void sub_nr_running(struct rq *rq, unsigned count)
 {
 	rq->nr_running -= count;
+	if (trace_sched_update_nr_running_tp_enabled()) {
+		call_trace_sched_update_nr_running(rq, -count);
+	}
+
 	/* Check if we still need preemption */
 	sched_update_tick_dependency(rq);
 }
@@ -1968,7 +2041,24 @@ static inline int hrtick_enabled(struct rq *rq)
 
 #endif /* CONFIG_SCHED_HRTICK */
 
+#ifndef arch_scale_freq_tick
+static __always_inline
+void arch_scale_freq_tick(void)
+{
+}
+#endif
+
 #ifndef arch_scale_freq_capacity
+/**
+ * arch_scale_freq_capacity - get the frequency scale factor of a given CPU.
+ * @cpu: the CPU in question.
+ *
+ * Return: the frequency scale factor normalized against SCHED_CAPACITY_SCALE, i.e.
+ *
+ *     f_curr
+ *     ------ * SCHED_CAPACITY_SCALE
+ *     f_max
+ */
 static __always_inline
 unsigned long arch_scale_freq_capacity(int cpu)
 {
@@ -2302,12 +2392,35 @@ static inline void cpufreq_update_util(struct rq *rq, unsigned int flags) {}
 #ifdef CONFIG_UCLAMP_TASK
 unsigned long uclamp_eff_value(struct task_struct *p, enum uclamp_id clamp_id);
 
+/**
+ * uclamp_rq_util_with - clamp @util with @rq and @p effective uclamp values.
+ * @rq:		The rq to clamp against. Must not be NULL.
+ * @util:	The util value to clamp.
+ * @p:		The task to clamp against. Can be NULL if you want to clamp
+ *		against @rq only.
+ *
+ * Clamps the passed @util to the max(@rq, @p) effective uclamp values.
+ *
+ * If sched_uclamp_used static key is disabled, then just return the util
+ * without any clamping since uclamp aggregation at the rq level in the fast
+ * path is disabled, rendering this operation a NOP.
+ *
+ * Use uclamp_eff_value() if you don't care about uclamp values at rq level. It
+ * will return the correct effective uclamp value of the task even if the
+ * static key is disabled.
+ */
 static __always_inline
 unsigned long uclamp_rq_util_with(struct rq *rq, unsigned long util,
 				  struct task_struct *p)
 {
-	unsigned long min_util = READ_ONCE(rq->uclamp[UCLAMP_MIN].value);
-	unsigned long max_util = READ_ONCE(rq->uclamp[UCLAMP_MAX].value);
+	unsigned long min_util;
+	unsigned long max_util;
+
+	if (!static_branch_likely(&sched_uclamp_used))
+		return util;
+
+	min_util = READ_ONCE(rq->uclamp[UCLAMP_MIN].value);
+	max_util = READ_ONCE(rq->uclamp[UCLAMP_MAX].value);
 
 	if (p) {
 		min_util = max(min_util, uclamp_eff_value(p, UCLAMP_MIN));
@@ -2324,6 +2437,19 @@ unsigned long uclamp_rq_util_with(struct rq *rq, unsigned long util,
 
 	return clamp(util, min_util, max_util);
 }
+
+/*
+ * When uclamp is compiled in, the aggregation at rq level is 'turned off'
+ * by default in the fast path and only gets turned on once userspace performs
+ * an operation that requires it.
+ *
+ * Returns true if userspace opted-in to use uclamp and aggregation at rq level
+ * hence is active.
+ */
+static inline bool uclamp_is_used(void)
+{
+	return static_branch_likely(&sched_uclamp_used);
+}
 #else /* CONFIG_UCLAMP_TASK */
 static inline
 unsigned long uclamp_rq_util_with(struct rq *rq, unsigned long util,
@@ -2331,6 +2457,11 @@ unsigned long uclamp_rq_util_with(struct rq *rq, unsigned long util,
 {
 	return util;
 }
+
+static inline bool uclamp_is_used(void)
+{
+	return false;
+}
 #endif /* CONFIG_UCLAMP_TASK */
 
 #ifdef arch_scale_freq_capacity
@@ -2492,3 +2623,6 @@ static inline bool is_per_cpu_kthread(struct task_struct *p)
 	return true;
 }
 #endif
+
+void swake_up_all_locked(struct swait_queue_head *q);
+void __prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait);
diff --git a/kernel/sched/smp.h b/kernel/sched/smp.h
new file mode 100644
index 000000000000..9620e323162c
--- /dev/null
+++ b/kernel/sched/smp.h
@@ -0,0 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Scheduler internal SMP callback types and methods between the scheduler
+ * and other internal parts of the core kernel:
+ */
+
+extern void sched_ttwu_pending(void *arg);
+
+extern void send_call_function_single_ipi(int cpu);
diff --git a/kernel/sched/stats.h b/kernel/sched/stats.h
index ba683fe81a6e..33d0daf83842 100644
--- a/kernel/sched/stats.h
+++ b/kernel/sched/stats.h
@@ -70,7 +70,7 @@ static inline void psi_enqueue(struct task_struct *p, bool wakeup)
 		return;
 
 	if (!wakeup || p->sched_psi_wake_requeue) {
-		if (p->flags & PF_MEMSTALL)
+		if (p->in_memstall)
 			set |= TSK_MEMSTALL;
 		if (p->sched_psi_wake_requeue)
 			p->sched_psi_wake_requeue = 0;
@@ -90,9 +90,17 @@ static inline void psi_dequeue(struct task_struct *p, bool sleep)
 		return;
 
 	if (!sleep) {
-		if (p->flags & PF_MEMSTALL)
+		if (p->in_memstall)
 			clear |= TSK_MEMSTALL;
 	} else {
+		/*
+		 * When a task sleeps, schedule() dequeues it before
+		 * switching to the next one. Merge the clearing of
+		 * TSK_RUNNING and TSK_ONCPU to save an unnecessary
+		 * psi_task_change() call in psi_sched_switch().
+		 */
+		clear |= TSK_ONCPU;
+
 		if (p->in_iowait)
 			set |= TSK_IOWAIT;
 	}
@@ -109,14 +117,14 @@ static inline void psi_ttwu_dequeue(struct task_struct *p)
 	 * deregister its sleep-persistent psi states from the old
 	 * queue, and let psi_enqueue() know it has to requeue.
 	 */
-	if (unlikely(p->in_iowait || (p->flags & PF_MEMSTALL))) {
+	if (unlikely(p->in_iowait || p->in_memstall)) {
 		struct rq_flags rf;
 		struct rq *rq;
 		int clear = 0;
 
 		if (p->in_iowait)
 			clear |= TSK_IOWAIT;
-		if (p->flags & PF_MEMSTALL)
+		if (p->in_memstall)
 			clear |= TSK_MEMSTALL;
 
 		rq = __task_rq_lock(p, &rf);
@@ -126,18 +134,31 @@ static inline void psi_ttwu_dequeue(struct task_struct *p)
 	}
 }
 
+static inline void psi_sched_switch(struct task_struct *prev,
+				    struct task_struct *next,
+				    bool sleep)
+{
+	if (static_branch_likely(&psi_disabled))
+		return;
+
+	psi_task_switch(prev, next, sleep);
+}
+
 static inline void psi_task_tick(struct rq *rq)
 {
 	if (static_branch_likely(&psi_disabled))
 		return;
 
-	if (unlikely(rq->curr->flags & PF_MEMSTALL))
+	if (unlikely(rq->curr->in_memstall))
 		psi_memstall_tick(rq->curr, cpu_of(rq));
 }
 #else /* CONFIG_PSI */
 static inline void psi_enqueue(struct task_struct *p, bool wakeup) {}
 static inline void psi_dequeue(struct task_struct *p, bool sleep) {}
 static inline void psi_ttwu_dequeue(struct task_struct *p) {}
+static inline void psi_sched_switch(struct task_struct *prev,
+				    struct task_struct *next,
+				    bool sleep) {}
 static inline void psi_task_tick(struct rq *rq) {}
 #endif /* CONFIG_PSI */
 
diff --git a/kernel/sched/stop_task.c b/kernel/sched/stop_task.c
index 4c9e9975684f..394bc8126a1e 100644
--- a/kernel/sched/stop_task.c
+++ b/kernel/sched/stop_task.c
@@ -102,12 +102,6 @@ prio_changed_stop(struct rq *rq, struct task_struct *p, int oldprio)
 	BUG(); /* how!?, what priority? */
 }
 
-static unsigned int
-get_rr_interval_stop(struct rq *rq, struct task_struct *task)
-{
-	return 0;
-}
-
 static void update_curr_stop(struct rq *rq)
 {
 }
@@ -115,8 +109,8 @@ static void update_curr_stop(struct rq *rq)
 /*
  * Simple, special scheduling class for the per-CPU stop tasks:
  */
-const struct sched_class stop_sched_class = {
-	.next			= &dl_sched_class,
+const struct sched_class stop_sched_class
+	__attribute__((section("__stop_sched_class"))) = {
 
 	.enqueue_task		= enqueue_task_stop,
 	.dequeue_task		= dequeue_task_stop,
@@ -136,8 +130,6 @@ const struct sched_class stop_sched_class = {
 
 	.task_tick		= task_tick_stop,
 
-	.get_rr_interval	= get_rr_interval_stop,
-
 	.prio_changed		= prio_changed_stop,
 	.switched_to		= switched_to_stop,
 	.update_curr		= update_curr_stop,
diff --git a/kernel/sched/swait.c b/kernel/sched/swait.c
index e83a3f8449f6..e1c655f928c7 100644
--- a/kernel/sched/swait.c
+++ b/kernel/sched/swait.c
@@ -32,6 +32,19 @@ void swake_up_locked(struct swait_queue_head *q)
 }
 EXPORT_SYMBOL(swake_up_locked);
 
+/*
+ * Wake up all waiters. This is an interface which is solely exposed for
+ * completions and not for general usage.
+ *
+ * It is intentionally different from swake_up_all() to allow usage from
+ * hard interrupt context and interrupt disabled regions.
+ */
+void swake_up_all_locked(struct swait_queue_head *q)
+{
+	while (!list_empty(&q->task_list))
+		swake_up_locked(q);
+}
+
 void swake_up_one(struct swait_queue_head *q)
 {
 	unsigned long flags;
@@ -69,7 +82,7 @@ void swake_up_all(struct swait_queue_head *q)
 }
 EXPORT_SYMBOL(swake_up_all);
 
-static void __prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait)
+void __prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait)
 {
 	wait->task = current;
 	if (list_empty(&wait->task_list))
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index dfb64c08a407..1bd7e3af904f 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -33,14 +33,6 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level,
 	cpumask_clear(groupmask);
 
 	printk(KERN_DEBUG "%*s domain-%d: ", level, "", level);
-
-	if (!(sd->flags & SD_LOAD_BALANCE)) {
-		printk("does not load-balance\n");
-		if (sd->parent)
-			printk(KERN_ERR "ERROR: !SD_LOAD_BALANCE domain has parent");
-		return -1;
-	}
-
 	printk(KERN_CONT "span=%*pbl level=%s\n",
 	       cpumask_pr_args(sched_domain_span(sd)), sd->name);
 
@@ -151,8 +143,7 @@ static int sd_degenerate(struct sched_domain *sd)
 		return 1;
 
 	/* Following flags need at least 2 groups */
-	if (sd->flags & (SD_LOAD_BALANCE |
-			 SD_BALANCE_NEWIDLE |
+	if (sd->flags & (SD_BALANCE_NEWIDLE |
 			 SD_BALANCE_FORK |
 			 SD_BALANCE_EXEC |
 			 SD_SHARE_CPUCAPACITY |
@@ -183,15 +174,14 @@ sd_parent_degenerate(struct sched_domain *sd, struct sched_domain *parent)
 
 	/* Flags needing groups don't count if only 1 group in parent */
 	if (parent->groups == parent->groups->next) {
-		pflags &= ~(SD_LOAD_BALANCE |
-				SD_BALANCE_NEWIDLE |
-				SD_BALANCE_FORK |
-				SD_BALANCE_EXEC |
-				SD_ASYM_CPUCAPACITY |
-				SD_SHARE_CPUCAPACITY |
-				SD_SHARE_PKG_RESOURCES |
-				SD_PREFER_SIBLING |
-				SD_SHARE_POWERDOMAIN);
+		pflags &= ~(SD_BALANCE_NEWIDLE |
+			    SD_BALANCE_FORK |
+			    SD_BALANCE_EXEC |
+			    SD_ASYM_CPUCAPACITY |
+			    SD_SHARE_CPUCAPACITY |
+			    SD_SHARE_PKG_RESOURCES |
+			    SD_PREFER_SIBLING |
+			    SD_SHARE_POWERDOMAIN);
 		if (nr_node_ids == 1)
 			pflags &= ~SD_SERIALIZE;
 	}
@@ -209,7 +199,7 @@ bool sched_energy_update;
 
 #ifdef CONFIG_PROC_SYSCTL
 int sched_energy_aware_handler(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, state;
 
@@ -282,10 +272,10 @@ static void perf_domain_debug(const struct cpumask *cpu_map,
 	printk(KERN_DEBUG "root_domain %*pbl:", cpumask_pr_args(cpu_map));
 
 	while (pd) {
-		printk(KERN_CONT " pd%d:{ cpus=%*pbl nr_cstate=%d }",
+		printk(KERN_CONT " pd%d:{ cpus=%*pbl nr_pstate=%d }",
 				cpumask_first(perf_domain_span(pd)),
 				cpumask_pr_args(perf_domain_span(pd)),
-				em_pd_nr_cap_states(pd->em_pd));
+				em_pd_nr_perf_states(pd->em_pd));
 		pd = pd->next;
 	}
 
@@ -317,31 +307,32 @@ static void sched_energy_set(bool has_eas)
  * EAS can be used on a root domain if it meets all the following conditions:
  *    1. an Energy Model (EM) is available;
  *    2. the SD_ASYM_CPUCAPACITY flag is set in the sched_domain hierarchy.
- *    3. the EM complexity is low enough to keep scheduling overheads low;
- *    4. schedutil is driving the frequency of all CPUs of the rd;
+ *    3. no SMT is detected.
+ *    4. the EM complexity is low enough to keep scheduling overheads low;
+ *    5. schedutil is driving the frequency of all CPUs of the rd;
  *
  * The complexity of the Energy Model is defined as:
  *
- *              C = nr_pd * (nr_cpus + nr_cs)
+ *              C = nr_pd * (nr_cpus + nr_ps)
  *
  * with parameters defined as:
  *  - nr_pd:    the number of performance domains
  *  - nr_cpus:  the number of CPUs
- *  - nr_cs:    the sum of the number of capacity states of all performance
+ *  - nr_ps:    the sum of the number of performance states of all performance
  *              domains (for example, on a system with 2 performance domains,
- *              with 10 capacity states each, nr_cs = 2 * 10 = 20).
+ *              with 10 performance states each, nr_ps = 2 * 10 = 20).
  *
  * It is generally not a good idea to use such a model in the wake-up path on
  * very complex platforms because of the associated scheduling overheads. The
  * arbitrary constraint below prevents that. It makes EAS usable up to 16 CPUs
- * with per-CPU DVFS and less than 8 capacity states each, for example.
+ * with per-CPU DVFS and less than 8 performance states each, for example.
  */
 #define EM_MAX_COMPLEXITY 2048
 
 extern struct cpufreq_governor schedutil_gov;
 static bool build_perf_domains(const struct cpumask *cpu_map)
 {
-	int i, nr_pd = 0, nr_cs = 0, nr_cpus = cpumask_weight(cpu_map);
+	int i, nr_pd = 0, nr_ps = 0, nr_cpus = cpumask_weight(cpu_map);
 	struct perf_domain *pd = NULL, *tmp;
 	int cpu = cpumask_first(cpu_map);
 	struct root_domain *rd = cpu_rq(cpu)->rd;
@@ -360,6 +351,13 @@ static bool build_perf_domains(const struct cpumask *cpu_map)
 		goto free;
 	}
 
+	/* EAS definitely does *not* handle SMT */
+	if (sched_smt_active()) {
+		pr_warn("rd %*pbl: Disabling EAS, SMT is not supported\n",
+			cpumask_pr_args(cpu_map));
+		goto free;
+	}
+
 	for_each_cpu(i, cpu_map) {
 		/* Skip already covered CPUs. */
 		if (find_pd(pd, i))
@@ -386,15 +384,15 @@ static bool build_perf_domains(const struct cpumask *cpu_map)
 		pd = tmp;
 
 		/*
-		 * Count performance domains and capacity states for the
+		 * Count performance domains and performance states for the
 		 * complexity check.
 		 */
 		nr_pd++;
-		nr_cs += em_pd_nr_cap_states(pd->em_pd);
+		nr_ps += em_pd_nr_perf_states(pd->em_pd);
 	}
 
 	/* Bail out if the Energy Model complexity is too high. */
-	if (nr_pd * (nr_cs + nr_cpus) > EM_MAX_COMPLEXITY) {
+	if (nr_pd * (nr_ps + nr_cpus) > EM_MAX_COMPLEXITY) {
 		WARN(1, "rd %*pbl: Failed to start EAS, EM complexity is too high\n",
 						cpumask_pr_args(cpu_map));
 		goto free;
@@ -1221,13 +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;
 	}
@@ -1330,7 +1328,7 @@ sd_init(struct sched_domain_topology_level *tl,
 		sd_flags = (*tl->sd_flags)();
 	if (WARN_ONCE(sd_flags & ~TOPOLOGY_SD_FLAGS,
 			"wrong sd_flags in topology description\n"))
-		sd_flags &= ~TOPOLOGY_SD_FLAGS;
+		sd_flags &= TOPOLOGY_SD_FLAGS;
 
 	/* Apply detected topology flags */
 	sd_flags |= dflags;
@@ -1343,8 +1341,7 @@ sd_init(struct sched_domain_topology_level *tl,
 
 		.cache_nice_tries	= 0,
 
-		.flags			= 1*SD_LOAD_BALANCE
-					| 1*SD_BALANCE_NEWIDLE
+		.flags			= 1*SD_BALANCE_NEWIDLE
 					| 1*SD_BALANCE_EXEC
 					| 1*SD_BALANCE_FORK
 					| 0*SD_BALANCE_WAKE
@@ -1374,18 +1371,9 @@ sd_init(struct sched_domain_topology_level *tl,
 	 * Convert topological properties into behaviour.
 	 */
 
-	if (sd->flags & SD_ASYM_CPUCAPACITY) {
-		struct sched_domain *t = sd;
-
-		/*
-		 * Don't attempt to spread across CPUs of different capacities.
-		 */
-		if (sd->child)
-			sd->child->flags &= ~SD_PREFER_SIBLING;
-
-		for_each_lower_domain(t)
-			t->flags |= SD_BALANCE_WAKE;
-	}
+	/* Don't attempt to spread across CPUs of different capacities. */
+	if ((sd->flags & SD_ASYM_CPUCAPACITY) && sd->child)
+		sd->child->flags &= ~SD_PREFER_SIBLING;
 
 	if (sd->flags & SD_SHARE_CPUCAPACITY) {
 		sd->imbalance_pct = 110;
diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c
index ba059fbfc53a..01f5d3020589 100644
--- a/kernel/sched/wait.c
+++ b/kernel/sched/wait.c
@@ -389,7 +389,7 @@ int autoremove_wake_function(struct wait_queue_entry *wq_entry, unsigned mode, i
 	int ret = default_wake_function(wq_entry, mode, sync, key);
 
 	if (ret)
-		list_del_init(&wq_entry->entry);
+		list_del_init_careful(&wq_entry->entry);
 
 	return ret;
 }
diff --git a/kernel/scs.c b/kernel/scs.c
new file mode 100644
index 000000000000..4ff4a7ba0094
--- /dev/null
+++ b/kernel/scs.c
@@ -0,0 +1,104 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Shadow Call Stack support.
+ *
+ * Copyright (C) 2019 Google LLC
+ */
+
+#include <linux/kasan.h>
+#include <linux/mm.h>
+#include <linux/scs.h>
+#include <linux/slab.h>
+#include <linux/vmstat.h>
+
+static struct kmem_cache *scs_cache;
+
+static void __scs_account(void *s, int account)
+{
+	struct page *scs_page = virt_to_page(s);
+
+	mod_node_page_state(page_pgdat(scs_page), NR_KERNEL_SCS_KB,
+			    account * (SCS_SIZE / SZ_1K));
+}
+
+static void *scs_alloc(int node)
+{
+	void *s = kmem_cache_alloc_node(scs_cache, GFP_SCS, node);
+
+	if (!s)
+		return NULL;
+
+	*__scs_magic(s) = SCS_END_MAGIC;
+
+	/*
+	 * Poison the allocation to catch unintentional accesses to
+	 * the shadow stack when KASAN is enabled.
+	 */
+	kasan_poison_object_data(scs_cache, s);
+	__scs_account(s, 1);
+	return s;
+}
+
+static void scs_free(void *s)
+{
+	__scs_account(s, -1);
+	kasan_unpoison_object_data(scs_cache, s);
+	kmem_cache_free(scs_cache, s);
+}
+
+void __init scs_init(void)
+{
+	scs_cache = kmem_cache_create("scs_cache", SCS_SIZE, 0, 0, NULL);
+}
+
+int scs_prepare(struct task_struct *tsk, int node)
+{
+	void *s = scs_alloc(node);
+
+	if (!s)
+		return -ENOMEM;
+
+	task_scs(tsk) = task_scs_sp(tsk) = s;
+	return 0;
+}
+
+static void scs_check_usage(struct task_struct *tsk)
+{
+	static unsigned long highest;
+
+	unsigned long *p, prev, curr = highest, used = 0;
+
+	if (!IS_ENABLED(CONFIG_DEBUG_STACK_USAGE))
+		return;
+
+	for (p = task_scs(tsk); p < __scs_magic(tsk); ++p) {
+		if (!READ_ONCE_NOCHECK(*p))
+			break;
+		used += sizeof(*p);
+	}
+
+	while (used > curr) {
+		prev = cmpxchg_relaxed(&highest, curr, used);
+
+		if (prev == curr) {
+			pr_info("%s (%d): highest shadow stack usage: %lu bytes\n",
+				tsk->comm, task_pid_nr(tsk), used);
+			break;
+		}
+
+		curr = prev;
+	}
+}
+
+void scs_release(struct task_struct *tsk)
+{
+	void *s = task_scs(tsk);
+
+	if (!s)
+		return;
+
+	WARN(task_scs_end_corrupted(tsk),
+	     "corrupted shadow stack detected when freeing task\n");
+	scs_check_usage(tsk);
+	scs_free(s);
+}
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index b6ea3dcb57bf..3ee59ce0a323 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -13,6 +13,7 @@
  * Mode 2 allows user-defined system call filters in the form
  *        of Berkeley Packet Filters/Linux Socket Filters.
  */
+#define pr_fmt(fmt) "seccomp: " fmt
 
 #include <linux/refcount.h>
 #include <linux/audit.h>
@@ -41,6 +42,15 @@
 #include <linux/tracehook.h>
 #include <linux/uaccess.h>
 #include <linux/anon_inodes.h>
+#include <linux/lockdep.h>
+
+/*
+ * When SECCOMP_IOCTL_NOTIF_ID_VALID was first introduced, it had the
+ * wrong direction flag in the ioctl number. This is the broken one,
+ * which the kernel needs to keep supporting until all userspaces stop
+ * using the wrong command number.
+ */
+#define SECCOMP_IOCTL_NOTIF_ID_VALID_WRONG_DIR	SECCOMP_IOR(2, __u64)
 
 enum notify_state {
 	SECCOMP_NOTIFY_INIT,
@@ -77,10 +87,42 @@ struct seccomp_knotif {
 	long val;
 	u32 flags;
 
-	/* Signals when this has entered SECCOMP_NOTIFY_REPLIED */
+	/*
+	 * Signals when this has changed states, such as the listener
+	 * dying, a new seccomp addfd message, or changing to REPLIED
+	 */
 	struct completion ready;
 
 	struct list_head list;
+
+	/* outstanding addfd requests */
+	struct list_head addfd;
+};
+
+/**
+ * struct seccomp_kaddfd - container for seccomp_addfd ioctl messages
+ *
+ * @file: A reference to the file to install in the other task
+ * @fd: The fd number to install it at. If the fd number is -1, it means the
+ *      installing process should allocate the fd as normal.
+ * @flags: The flags for the new file descriptor. At the moment, only O_CLOEXEC
+ *         is allowed.
+ * @ret: The return value of the installing process. It is set to the fd num
+ *       upon success (>= 0).
+ * @completion: Indicates that the installing process has completed fd
+ *              installation, or gone away (either due to successful
+ *              reply, or signal)
+ *
+ */
+struct seccomp_kaddfd {
+	struct file *file;
+	int fd;
+	unsigned int flags;
+
+	/* To only be set on reply */
+	int ret;
+	struct completion completion;
+	struct list_head list;
 };
 
 /**
@@ -94,27 +136,35 @@ struct seccomp_knotif {
  *           filter->notify_lock.
  * @next_id: The id of the next request.
  * @notifications: A list of struct seccomp_knotif elements.
- * @wqh: A wait queue for poll.
  */
 struct notification {
 	struct semaphore request;
 	u64 next_id;
 	struct list_head notifications;
-	wait_queue_head_t wqh;
 };
 
 /**
  * struct seccomp_filter - container for seccomp BPF programs
  *
- * @usage: reference count to manage the object lifetime.
- *         get/put helpers should be used when accessing an instance
- *         outside of a lifetime-guarded section.  In general, this
- *         is only needed for handling filters shared across tasks.
+ * @refs: Reference count to manage the object lifetime.
+ *	  A filter's reference count is incremented for each directly
+ *	  attached task, once for the dependent filter, and if
+ *	  requested for the user notifier. When @refs reaches zero,
+ *	  the filter can be freed.
+ * @users: A filter's @users count is incremented for each directly
+ *         attached task (filter installation, fork(), thread_sync),
+ *	   and once for the dependent filter (tracked in filter->prev).
+ *	   When it reaches zero it indicates that no direct or indirect
+ *	   users of that filter exist. No new tasks can get associated with
+ *	   this filter after reaching 0. The @users count is always smaller
+ *	   or equal to @refs. Hence, reaching 0 for @users does not mean
+ *	   the filter can be freed.
  * @log: true if all actions except for SECCOMP_RET_ALLOW should be logged
  * @prev: points to a previously installed, or inherited, filter
  * @prog: the BPF program to evaluate
  * @notif: the struct that holds all notification related information
  * @notify_lock: A lock for all notification-related accesses.
+ * @wqh: A wait queue for poll if a notifier is in use.
  *
  * seccomp_filter objects are organized in a tree linked via the @prev
  * pointer.  For any task, it appears to be a singly-linked list starting
@@ -124,15 +174,17 @@ struct notification {
  * how namespaces work.
  *
  * seccomp_filter objects should never be modified after being attached
- * to a task_struct (other than @usage).
+ * to a task_struct (other than @refs).
  */
 struct seccomp_filter {
-	refcount_t usage;
+	refcount_t refs;
+	refcount_t users;
 	bool log;
 	struct seccomp_filter *prev;
 	struct bpf_prog *prog;
 	struct notification *notif;
 	struct mutex notify_lock;
+	wait_queue_head_t wqh;
 };
 
 /* Limit any path through the tree to 256KB worth of instructions. */
@@ -268,16 +320,14 @@ static u32 seccomp_run_filters(const struct seccomp_data *sd,
 	 * All filters in the list are evaluated and the lowest BPF return
 	 * value always takes priority (ignoring the DATA).
 	 */
-	preempt_disable();
 	for (; f; f = f->prev) {
-		u32 cur_ret = BPF_PROG_RUN(f->prog, sd);
+		u32 cur_ret = bpf_prog_run_pin_on_cpu(f->prog, sd);
 
 		if (ACTION_ONLY(cur_ret) < ACTION_ONLY(ret)) {
 			ret = cur_ret;
 			*match = f;
 		}
 	}
-	preempt_enable();
 	return ret;
 }
 #endif /* CONFIG_SECCOMP_FILTER */
@@ -368,6 +418,59 @@ static inline pid_t seccomp_can_sync_threads(void)
 	return 0;
 }
 
+static inline void seccomp_filter_free(struct seccomp_filter *filter)
+{
+	if (filter) {
+		bpf_prog_destroy(filter->prog);
+		kfree(filter);
+	}
+}
+
+static void __seccomp_filter_orphan(struct seccomp_filter *orig)
+{
+	while (orig && refcount_dec_and_test(&orig->users)) {
+		if (waitqueue_active(&orig->wqh))
+			wake_up_poll(&orig->wqh, EPOLLHUP);
+		orig = orig->prev;
+	}
+}
+
+static void __put_seccomp_filter(struct seccomp_filter *orig)
+{
+	/* Clean up single-reference branches iteratively. */
+	while (orig && refcount_dec_and_test(&orig->refs)) {
+		struct seccomp_filter *freeme = orig;
+		orig = orig->prev;
+		seccomp_filter_free(freeme);
+	}
+}
+
+static void __seccomp_filter_release(struct seccomp_filter *orig)
+{
+	/* Notify about any unused filters in the task's former filter tree. */
+	__seccomp_filter_orphan(orig);
+	/* Finally drop all references to the task's former tree. */
+	__put_seccomp_filter(orig);
+}
+
+/**
+ * seccomp_filter_release - Detach the task from its filter tree,
+ *			    drop its reference count, and notify
+ *			    about unused filters
+ *
+ * This function should only be called when the task is exiting as
+ * it detaches it from its filter tree. As such, READ_ONCE() and
+ * barriers are not needed here, as would normally be needed.
+ */
+void seccomp_filter_release(struct task_struct *tsk)
+{
+	struct seccomp_filter *orig = tsk->seccomp.filter;
+
+	/* Detach task from its filter tree. */
+	tsk->seccomp.filter = NULL;
+	__seccomp_filter_release(orig);
+}
+
 /**
  * seccomp_sync_threads: sets all threads to use current's filter
  *
@@ -392,14 +495,19 @@ static inline void seccomp_sync_threads(unsigned long flags)
 
 		/* Get a task reference for the new leaf node. */
 		get_seccomp_filter(caller);
+
 		/*
 		 * Drop the task reference to the shared ancestor since
 		 * current's path will hold a reference.  (This also
 		 * allows a put before the assignment.)
 		 */
-		put_seccomp_filter(thread);
+		__seccomp_filter_release(thread->seccomp.filter);
+
+		/* Make our new filter tree visible. */
 		smp_store_release(&thread->seccomp.filter,
 				  caller->seccomp.filter);
+		atomic_set(&thread->seccomp.filter_count,
+			   atomic_read(&thread->seccomp.filter_count));
 
 		/*
 		 * Don't let an unprivileged task work around
@@ -463,7 +571,9 @@ static struct seccomp_filter *seccomp_prepare_filter(struct sock_fprog *fprog)
 		return ERR_PTR(ret);
 	}
 
-	refcount_set(&sfilter->usage, 1);
+	refcount_set(&sfilter->refs, 1);
+	refcount_set(&sfilter->users, 1);
+	init_waitqueue_head(&sfilter->wqh);
 
 	return sfilter;
 }
@@ -528,8 +638,12 @@ static long seccomp_attach_filter(unsigned int flags,
 		int ret;
 
 		ret = seccomp_can_sync_threads();
-		if (ret)
-			return ret;
+		if (ret) {
+			if (flags & SECCOMP_FILTER_FLAG_TSYNC_ESRCH)
+				return -ESRCH;
+			else
+				return ret;
+		}
 	}
 
 	/* Set log flag, if present. */
@@ -542,6 +656,7 @@ static long seccomp_attach_filter(unsigned int flags,
 	 */
 	filter->prev = current->seccomp.filter;
 	current->seccomp.filter = filter;
+	atomic_inc(&current->seccomp.filter_count);
 
 	/* Now that the new filter is in place, synchronize to all threads. */
 	if (flags & SECCOMP_FILTER_FLAG_TSYNC)
@@ -552,7 +667,7 @@ static long seccomp_attach_filter(unsigned int flags,
 
 static void __get_seccomp_filter(struct seccomp_filter *filter)
 {
-	refcount_inc(&filter->usage);
+	refcount_inc(&filter->refs);
 }
 
 /* get_seccomp_filter - increments the reference count of the filter on @tsk */
@@ -562,30 +677,7 @@ void get_seccomp_filter(struct task_struct *tsk)
 	if (!orig)
 		return;
 	__get_seccomp_filter(orig);
-}
-
-static inline void seccomp_filter_free(struct seccomp_filter *filter)
-{
-	if (filter) {
-		bpf_prog_destroy(filter->prog);
-		kfree(filter);
-	}
-}
-
-static void __put_seccomp_filter(struct seccomp_filter *orig)
-{
-	/* Clean up single-reference branches iteratively. */
-	while (orig && refcount_dec_and_test(&orig->usage)) {
-		struct seccomp_filter *freeme = orig;
-		orig = orig->prev;
-		seccomp_filter_free(freeme);
-	}
-}
-
-/* put_seccomp_filter - decrements the ref count of tsk->seccomp.filter */
-void put_seccomp_filter(struct task_struct *tsk)
-{
-	__put_seccomp_filter(tsk->seccomp.filter);
+	refcount_inc(&orig->users);
 }
 
 static void seccomp_init_siginfo(kernel_siginfo_t *info, int syscall, int reason)
@@ -682,20 +774,20 @@ static inline void seccomp_log(unsigned long syscall, long signr, u32 action,
  */
 static const int mode1_syscalls[] = {
 	__NR_seccomp_read, __NR_seccomp_write, __NR_seccomp_exit, __NR_seccomp_sigreturn,
-	0, /* null terminated */
+	-1, /* negative terminated */
 };
 
 static void __secure_computing_strict(int this_syscall)
 {
-	const int *syscall_whitelist = mode1_syscalls;
+	const int *allowed_syscalls = mode1_syscalls;
 #ifdef CONFIG_COMPAT
 	if (in_compat_syscall())
-		syscall_whitelist = get_compat_mode1_syscalls();
+		allowed_syscalls = get_compat_mode1_syscalls();
 #endif
 	do {
-		if (*syscall_whitelist == this_syscall)
+		if (*allowed_syscalls == this_syscall)
 			return;
-	} while (*++syscall_whitelist);
+	} while (*++allowed_syscalls != -1);
 
 #ifdef SECCOMP_DEBUG
 	dump_stack();
@@ -733,6 +825,17 @@ static u64 seccomp_next_notify_id(struct seccomp_filter *filter)
 	return filter->notif->next_id++;
 }
 
+static void seccomp_handle_addfd(struct seccomp_kaddfd *addfd)
+{
+	/*
+	 * Remove the notification, and reset the list pointers, indicating
+	 * that it has been handled.
+	 */
+	list_del_init(&addfd->list);
+	addfd->ret = receive_fd_replace(addfd->fd, addfd->file, addfd->flags);
+	complete(&addfd->completion);
+}
+
 static int seccomp_do_user_notification(int this_syscall,
 					struct seccomp_filter *match,
 					const struct seccomp_data *sd)
@@ -741,6 +844,7 @@ static int seccomp_do_user_notification(int this_syscall,
 	u32 flags = 0;
 	long ret = 0;
 	struct seccomp_knotif n = {};
+	struct seccomp_kaddfd *addfd, *tmp;
 
 	mutex_lock(&match->notify_lock);
 	err = -ENOSYS;
@@ -753,25 +857,43 @@ static int seccomp_do_user_notification(int this_syscall,
 	n.id = seccomp_next_notify_id(match);
 	init_completion(&n.ready);
 	list_add(&n.list, &match->notif->notifications);
+	INIT_LIST_HEAD(&n.addfd);
 
 	up(&match->notif->request);
-	wake_up_poll(&match->notif->wqh, EPOLLIN | EPOLLRDNORM);
+	wake_up_poll(&match->wqh, EPOLLIN | EPOLLRDNORM);
 	mutex_unlock(&match->notify_lock);
 
 	/*
 	 * This is where we wait for a reply from userspace.
 	 */
+wait:
 	err = wait_for_completion_interruptible(&n.ready);
 	mutex_lock(&match->notify_lock);
 	if (err == 0) {
+		/* Check if we were woken up by a addfd message */
+		addfd = list_first_entry_or_null(&n.addfd,
+						 struct seccomp_kaddfd, list);
+		if (addfd && n.state != SECCOMP_NOTIFY_REPLIED) {
+			seccomp_handle_addfd(addfd);
+			mutex_unlock(&match->notify_lock);
+			goto wait;
+		}
 		ret = n.val;
 		err = n.error;
 		flags = n.flags;
 	}
 
+	/* If there were any pending addfd calls, clear them out */
+	list_for_each_entry_safe(addfd, tmp, &n.addfd, list) {
+		/* The process went away before we got a chance to handle it */
+		addfd->ret = -ESRCH;
+		list_del_init(&addfd->list);
+		complete(&addfd->completion);
+	}
+
 	/*
 	 * Note that it's possible the listener died in between the time when
-	 * we were notified of a respons (or a signal) and when we were able to
+	 * we were notified of a response (or a signal) and when we were able to
 	 * re-acquire the lock, so only delete from the list if the
 	 * notification actually exists.
 	 *
@@ -1009,6 +1131,11 @@ static int seccomp_notify_release(struct inode *inode, struct file *file)
 		knotif->error = -ENOSYS;
 		knotif->val = 0;
 
+		/*
+		 * We do not need to wake up any pending addfd messages, as
+		 * the notifier will do that for us, as this just looks
+		 * like a standard reply.
+		 */
 		complete(&knotif->ready);
 	}
 
@@ -1019,6 +1146,23 @@ static int seccomp_notify_release(struct inode *inode, struct file *file)
 	return 0;
 }
 
+/* must be called with notif_lock held */
+static inline struct seccomp_knotif *
+find_notification(struct seccomp_filter *filter, u64 id)
+{
+	struct seccomp_knotif *cur;
+
+	lockdep_assert_held(&filter->notify_lock);
+
+	list_for_each_entry(cur, &filter->notif->notifications, list) {
+		if (cur->id == id)
+			return cur;
+	}
+
+	return NULL;
+}
+
+
 static long seccomp_notify_recv(struct seccomp_filter *filter,
 				void __user *buf)
 {
@@ -1062,7 +1206,7 @@ static long seccomp_notify_recv(struct seccomp_filter *filter,
 	unotif.data = *(knotif->data);
 
 	knotif->state = SECCOMP_NOTIFY_SENT;
-	wake_up_poll(&filter->notif->wqh, EPOLLOUT | EPOLLWRNORM);
+	wake_up_poll(&filter->wqh, EPOLLOUT | EPOLLWRNORM);
 	ret = 0;
 out:
 	mutex_unlock(&filter->notify_lock);
@@ -1076,15 +1220,8 @@ out:
 		 * may have died when we released the lock, so we need to make
 		 * sure it's still around.
 		 */
-		knotif = NULL;
 		mutex_lock(&filter->notify_lock);
-		list_for_each_entry(cur, &filter->notif->notifications, list) {
-			if (cur->id == unotif.id) {
-				knotif = cur;
-				break;
-			}
-		}
-
+		knotif = find_notification(filter, unotif.id);
 		if (knotif) {
 			knotif->state = SECCOMP_NOTIFY_INIT;
 			up(&filter->notif->request);
@@ -1099,7 +1236,7 @@ static long seccomp_notify_send(struct seccomp_filter *filter,
 				void __user *buf)
 {
 	struct seccomp_notif_resp resp = {};
-	struct seccomp_knotif *knotif = NULL, *cur;
+	struct seccomp_knotif *knotif;
 	long ret;
 
 	if (copy_from_user(&resp, buf, sizeof(resp)))
@@ -1116,13 +1253,7 @@ static long seccomp_notify_send(struct seccomp_filter *filter,
 	if (ret < 0)
 		return ret;
 
-	list_for_each_entry(cur, &filter->notif->notifications, list) {
-		if (cur->id == resp.id) {
-			knotif = cur;
-			break;
-		}
-	}
-
+	knotif = find_notification(filter, resp.id);
 	if (!knotif) {
 		ret = -ENOENT;
 		goto out;
@@ -1148,7 +1279,7 @@ out:
 static long seccomp_notify_id_valid(struct seccomp_filter *filter,
 				    void __user *buf)
 {
-	struct seccomp_knotif *knotif = NULL;
+	struct seccomp_knotif *knotif;
 	u64 id;
 	long ret;
 
@@ -1159,17 +1290,109 @@ static long seccomp_notify_id_valid(struct seccomp_filter *filter,
 	if (ret < 0)
 		return ret;
 
-	ret = -ENOENT;
-	list_for_each_entry(knotif, &filter->notif->notifications, list) {
-		if (knotif->id == id) {
-			if (knotif->state == SECCOMP_NOTIFY_SENT)
-				ret = 0;
-			goto out;
-		}
+	knotif = find_notification(filter, id);
+	if (knotif && knotif->state == SECCOMP_NOTIFY_SENT)
+		ret = 0;
+	else
+		ret = -ENOENT;
+
+	mutex_unlock(&filter->notify_lock);
+	return ret;
+}
+
+static long seccomp_notify_addfd(struct seccomp_filter *filter,
+				 struct seccomp_notif_addfd __user *uaddfd,
+				 unsigned int size)
+{
+	struct seccomp_notif_addfd addfd;
+	struct seccomp_knotif *knotif;
+	struct seccomp_kaddfd kaddfd;
+	int ret;
+
+	BUILD_BUG_ON(sizeof(addfd) < SECCOMP_NOTIFY_ADDFD_SIZE_VER0);
+	BUILD_BUG_ON(sizeof(addfd) != SECCOMP_NOTIFY_ADDFD_SIZE_LATEST);
+
+	if (size < SECCOMP_NOTIFY_ADDFD_SIZE_VER0 || size >= PAGE_SIZE)
+		return -EINVAL;
+
+	ret = copy_struct_from_user(&addfd, sizeof(addfd), uaddfd, size);
+	if (ret)
+		return ret;
+
+	if (addfd.newfd_flags & ~O_CLOEXEC)
+		return -EINVAL;
+
+	if (addfd.flags & ~SECCOMP_ADDFD_FLAG_SETFD)
+		return -EINVAL;
+
+	if (addfd.newfd && !(addfd.flags & SECCOMP_ADDFD_FLAG_SETFD))
+		return -EINVAL;
+
+	kaddfd.file = fget(addfd.srcfd);
+	if (!kaddfd.file)
+		return -EBADF;
+
+	kaddfd.flags = addfd.newfd_flags;
+	kaddfd.fd = (addfd.flags & SECCOMP_ADDFD_FLAG_SETFD) ?
+		    addfd.newfd : -1;
+	init_completion(&kaddfd.completion);
+
+	ret = mutex_lock_interruptible(&filter->notify_lock);
+	if (ret < 0)
+		goto out;
+
+	knotif = find_notification(filter, addfd.id);
+	if (!knotif) {
+		ret = -ENOENT;
+		goto out_unlock;
 	}
 
-out:
+	/*
+	 * We do not want to allow for FD injection to occur before the
+	 * notification has been picked up by a userspace handler, or after
+	 * the notification has been replied to.
+	 */
+	if (knotif->state != SECCOMP_NOTIFY_SENT) {
+		ret = -EINPROGRESS;
+		goto out_unlock;
+	}
+
+	list_add(&kaddfd.list, &knotif->addfd);
+	complete(&knotif->ready);
+	mutex_unlock(&filter->notify_lock);
+
+	/* Now we wait for it to be processed or be interrupted */
+	ret = wait_for_completion_interruptible(&kaddfd.completion);
+	if (ret == 0) {
+		/*
+		 * We had a successful completion. The other side has already
+		 * removed us from the addfd queue, and
+		 * wait_for_completion_interruptible has a memory barrier upon
+		 * success that lets us read this value directly without
+		 * locking.
+		 */
+		ret = kaddfd.ret;
+		goto out;
+	}
+
+	mutex_lock(&filter->notify_lock);
+	/*
+	 * Even though we were woken up by a signal and not a successful
+	 * completion, a completion may have happened in the mean time.
+	 *
+	 * We need to check again if the addfd request has been handled,
+	 * and if not, we will remove it from the queue.
+	 */
+	if (list_empty(&kaddfd.list))
+		ret = kaddfd.ret;
+	else
+		list_del(&kaddfd.list);
+
+out_unlock:
 	mutex_unlock(&filter->notify_lock);
+out:
+	fput(kaddfd.file);
+
 	return ret;
 }
 
@@ -1179,13 +1402,22 @@ static long seccomp_notify_ioctl(struct file *file, unsigned int cmd,
 	struct seccomp_filter *filter = file->private_data;
 	void __user *buf = (void __user *)arg;
 
+	/* Fixed-size ioctls */
 	switch (cmd) {
 	case SECCOMP_IOCTL_NOTIF_RECV:
 		return seccomp_notify_recv(filter, buf);
 	case SECCOMP_IOCTL_NOTIF_SEND:
 		return seccomp_notify_send(filter, buf);
+	case SECCOMP_IOCTL_NOTIF_ID_VALID_WRONG_DIR:
 	case SECCOMP_IOCTL_NOTIF_ID_VALID:
 		return seccomp_notify_id_valid(filter, buf);
+	}
+
+	/* Extensible Argument ioctls */
+#define EA_IOCTL(cmd)	((cmd) & ~(IOC_INOUT | IOCSIZE_MASK))
+	switch (EA_IOCTL(cmd)) {
+	case EA_IOCTL(SECCOMP_IOCTL_NOTIF_ADDFD):
+		return seccomp_notify_addfd(filter, buf, _IOC_SIZE(cmd));
 	default:
 		return -EINVAL;
 	}
@@ -1198,7 +1430,7 @@ static __poll_t seccomp_notify_poll(struct file *file,
 	__poll_t ret = 0;
 	struct seccomp_knotif *cur;
 
-	poll_wait(file, &filter->notif->wqh, poll_tab);
+	poll_wait(file, &filter->wqh, poll_tab);
 
 	if (mutex_lock_interruptible(&filter->notify_lock) < 0)
 		return EPOLLERR;
@@ -1214,6 +1446,9 @@ static __poll_t seccomp_notify_poll(struct file *file,
 
 	mutex_unlock(&filter->notify_lock);
 
+	if (refcount_read(&filter->users) == 0)
+		ret |= EPOLLHUP;
+
 	return ret;
 }
 
@@ -1221,6 +1456,7 @@ static const struct file_operations seccomp_notify_ops = {
 	.poll = seccomp_notify_poll,
 	.release = seccomp_notify_release,
 	.unlocked_ioctl = seccomp_notify_ioctl,
+	.compat_ioctl = seccomp_notify_ioctl,
 };
 
 static struct file *init_listener(struct seccomp_filter *filter)
@@ -1241,7 +1477,6 @@ static struct file *init_listener(struct seccomp_filter *filter)
 	sema_init(&filter->notif->request, 0);
 	filter->notif->next_id = get_random_u64();
 	INIT_LIST_HEAD(&filter->notif->notifications);
-	init_waitqueue_head(&filter->notif->wqh);
 
 	ret = anon_inode_getfile("seccomp notify", &seccomp_notify_ops,
 				 filter, O_RDWR);
@@ -1288,10 +1523,12 @@ static long seccomp_set_mode_filter(unsigned int flags,
 	 * In the successful case, NEW_LISTENER returns the new listener fd.
 	 * But in the failure case, TSYNC returns the thread that died. If you
 	 * combine these two flags, there's no way to tell whether something
-	 * succeeded or failed. So, let's disallow this combination.
+	 * succeeded or failed. So, let's disallow this combination if the user
+	 * has not explicitly requested no errors from TSYNC.
 	 */
 	if ((flags & SECCOMP_FILTER_FLAG_TSYNC) &&
-	    (flags & SECCOMP_FILTER_FLAG_NEW_LISTENER))
+	    (flags & SECCOMP_FILTER_FLAG_NEW_LISTENER) &&
+	    ((flags & SECCOMP_FILTER_FLAG_TSYNC_ESRCH) == 0))
 		return -EINVAL;
 
 	/* Prepare the new filter before holding any locks. */
@@ -1771,7 +2008,7 @@ static void audit_actions_logged(u32 actions_logged, u32 old_actions_logged,
 }
 
 static int seccomp_actions_logged_handler(struct ctl_table *ro_table, int write,
-					  void __user *buffer, size_t *lenp,
+					  void *buffer, size_t *lenp,
 					  loff_t *ppos)
 {
 	int ret;
@@ -1817,7 +2054,7 @@ static int __init seccomp_sysctl_init(void)
 
 	hdr = register_sysctl_paths(seccomp_sysctl_path, seccomp_sysctl_table);
 	if (!hdr)
-		pr_warn("seccomp: sysctl registration failed\n");
+		pr_warn("sysctl registration failed\n");
 	else
 		kmemleak_not_leak(hdr);
 
diff --git a/kernel/signal.c b/kernel/signal.c
index 5b2396350dd1..a38b3edc6851 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -719,7 +719,7 @@ static int dequeue_synchronous_signal(kernel_siginfo_t *info)
 	 * Return the first synchronous signal in the queue.
 	 */
 	list_for_each_entry(q, &pending->list, list) {
-		/* Synchronous signals have a postive si_code */
+		/* Synchronous signals have a positive si_code */
 		if ((q->info.si_code > SI_USER) &&
 		    (sigmask(q->info.si_signo) & SYNCHRONOUS_MASK)) {
 			sync = q;
@@ -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;
 		}
@@ -1510,15 +1510,15 @@ int kill_pid_usb_asyncio(int sig, int errno, sigval_t addr,
 	unsigned long flags;
 	int ret = -EINVAL;
 
+	if (!valid_signal(sig))
+		return ret;
+
 	clear_siginfo(&info);
 	info.si_signo = sig;
 	info.si_errno = errno;
 	info.si_code = SI_ASYNCIO;
 	*((sigval_t *)&info.si_pid) = addr;
 
-	if (!valid_signal(sig))
-		return ret;
-
 	rcu_read_lock();
 	p = pid_task(pid, PIDTYPE_PID);
 	if (!p) {
@@ -1557,12 +1557,8 @@ static int kill_something_info(int sig, struct kernel_siginfo *info, pid_t pid)
 {
 	int ret;
 
-	if (pid > 0) {
-		rcu_read_lock();
-		ret = kill_pid_info(sig, info, find_vpid(pid));
-		rcu_read_unlock();
-		return ret;
-	}
+	if (pid > 0)
+		return kill_proc_info(sig, info, pid);
 
 	/* -INT_MIN is undefined.  Exclude this case to avoid a UBSAN warning */
 	if (pid == INT_MIN)
@@ -1931,7 +1927,7 @@ bool do_notify_parent(struct task_struct *tsk, int sig)
 		 * This is only possible if parent == real_parent.
 		 * Check if it has changed security domain.
 		 */
-		if (tsk->parent_exec_id != tsk->parent->self_exec_id)
+		if (tsk->parent_exec_id != READ_ONCE(tsk->parent->self_exec_id))
 			sig = SIGCHLD;
 	}
 
@@ -1993,8 +1989,12 @@ bool do_notify_parent(struct task_struct *tsk, int sig)
 		if (psig->action[SIGCHLD-1].sa.sa_handler == SIG_IGN)
 			sig = 0;
 	}
+	/*
+	 * Send with __send_signal as si_pid and si_uid are in the
+	 * parent's namespaces.
+	 */
 	if (valid_signal(sig) && sig)
-		__group_send_sig_info(sig, &info, tsk->parent);
+		__send_signal(sig, &info, tsk->parent, PIDTYPE_TGID, false);
 	__wake_up_parent(tsk, tsk->parent);
 	spin_unlock_irqrestore(&psig->siglock, flags);
 
@@ -2529,9 +2529,6 @@ bool get_signal(struct ksignal *ksig)
 	struct signal_struct *signal = current->signal;
 	int signr;
 
-	if (unlikely(current->task_works))
-		task_work_run();
-
 	if (unlikely(uprobe_deny_signal()))
 		return false;
 
@@ -2545,6 +2542,27 @@ bool get_signal(struct ksignal *ksig)
 relock:
 	spin_lock_irq(&sighand->siglock);
 	/*
+	 * Make sure we can safely read ->jobctl() in task_work add. As Oleg
+	 * states:
+	 *
+	 * It pairs with mb (implied by cmpxchg) before READ_ONCE. So we
+	 * roughly have
+	 *
+	 *	task_work_add:				get_signal:
+	 *	STORE(task->task_works, new_work);	STORE(task->jobctl);
+	 *	mb();					mb();
+	 *	LOAD(task->jobctl);			LOAD(task->task_works);
+	 *
+	 * and we can rely on STORE-MB-LOAD [ in task_work_add].
+	 */
+	smp_store_mb(current->jobctl, current->jobctl & ~JOBCTL_TASK_WORK);
+	if (unlikely(current->task_works)) {
+		spin_unlock_irq(&sighand->siglock);
+		task_work_run();
+		goto relock;
+	}
+
+	/*
 	 * Every stopped thread goes here after wakeup. Check to see if
 	 * we should notify the parent, prepare_signal(SIGCONT) encodes
 	 * the CLD_ si_code into SIGNAL_CLD_MASK bits.
@@ -3235,94 +3253,94 @@ int copy_siginfo_from_user(kernel_siginfo_t *to, const siginfo_t __user *from)
 }
 
 #ifdef CONFIG_COMPAT
-int copy_siginfo_to_user32(struct compat_siginfo __user *to,
-			   const struct kernel_siginfo *from)
-#if defined(CONFIG_X86_X32_ABI) || defined(CONFIG_IA32_EMULATION)
-{
-	return __copy_siginfo_to_user32(to, from, in_x32_syscall());
-}
-int __copy_siginfo_to_user32(struct compat_siginfo __user *to,
-			     const struct kernel_siginfo *from, bool x32_ABI)
-#endif
+/**
+ * copy_siginfo_to_external32 - copy a kernel siginfo into a compat user siginfo
+ * @to: compat siginfo destination
+ * @from: kernel siginfo source
+ *
+ * Note: This function does not work properly for the SIGCHLD on x32, but
+ * fortunately it doesn't have to.  The only valid callers for this function are
+ * copy_siginfo_to_user32, which is overriden for x32 and the coredump code.
+ * The latter does not care because SIGCHLD will never cause a coredump.
+ */
+void copy_siginfo_to_external32(struct compat_siginfo *to,
+		const struct kernel_siginfo *from)
 {
-	struct compat_siginfo new;
-	memset(&new, 0, sizeof(new));
+	memset(to, 0, sizeof(*to));
 
-	new.si_signo = from->si_signo;
-	new.si_errno = from->si_errno;
-	new.si_code  = from->si_code;
+	to->si_signo = from->si_signo;
+	to->si_errno = from->si_errno;
+	to->si_code  = from->si_code;
 	switch(siginfo_layout(from->si_signo, from->si_code)) {
 	case SIL_KILL:
-		new.si_pid = from->si_pid;
-		new.si_uid = from->si_uid;
+		to->si_pid = from->si_pid;
+		to->si_uid = from->si_uid;
 		break;
 	case SIL_TIMER:
-		new.si_tid     = from->si_tid;
-		new.si_overrun = from->si_overrun;
-		new.si_int     = from->si_int;
+		to->si_tid     = from->si_tid;
+		to->si_overrun = from->si_overrun;
+		to->si_int     = from->si_int;
 		break;
 	case SIL_POLL:
-		new.si_band = from->si_band;
-		new.si_fd   = from->si_fd;
+		to->si_band = from->si_band;
+		to->si_fd   = from->si_fd;
 		break;
 	case SIL_FAULT:
-		new.si_addr = ptr_to_compat(from->si_addr);
+		to->si_addr = ptr_to_compat(from->si_addr);
 #ifdef __ARCH_SI_TRAPNO
-		new.si_trapno = from->si_trapno;
+		to->si_trapno = from->si_trapno;
 #endif
 		break;
 	case SIL_FAULT_MCEERR:
-		new.si_addr = ptr_to_compat(from->si_addr);
+		to->si_addr = ptr_to_compat(from->si_addr);
 #ifdef __ARCH_SI_TRAPNO
-		new.si_trapno = from->si_trapno;
+		to->si_trapno = from->si_trapno;
 #endif
-		new.si_addr_lsb = from->si_addr_lsb;
+		to->si_addr_lsb = from->si_addr_lsb;
 		break;
 	case SIL_FAULT_BNDERR:
-		new.si_addr = ptr_to_compat(from->si_addr);
+		to->si_addr = ptr_to_compat(from->si_addr);
 #ifdef __ARCH_SI_TRAPNO
-		new.si_trapno = from->si_trapno;
+		to->si_trapno = from->si_trapno;
 #endif
-		new.si_lower = ptr_to_compat(from->si_lower);
-		new.si_upper = ptr_to_compat(from->si_upper);
+		to->si_lower = ptr_to_compat(from->si_lower);
+		to->si_upper = ptr_to_compat(from->si_upper);
 		break;
 	case SIL_FAULT_PKUERR:
-		new.si_addr = ptr_to_compat(from->si_addr);
+		to->si_addr = ptr_to_compat(from->si_addr);
 #ifdef __ARCH_SI_TRAPNO
-		new.si_trapno = from->si_trapno;
+		to->si_trapno = from->si_trapno;
 #endif
-		new.si_pkey = from->si_pkey;
+		to->si_pkey = from->si_pkey;
 		break;
 	case SIL_CHLD:
-		new.si_pid    = from->si_pid;
-		new.si_uid    = from->si_uid;
-		new.si_status = from->si_status;
-#ifdef CONFIG_X86_X32_ABI
-		if (x32_ABI) {
-			new._sifields._sigchld_x32._utime = from->si_utime;
-			new._sifields._sigchld_x32._stime = from->si_stime;
-		} else
-#endif
-		{
-			new.si_utime = from->si_utime;
-			new.si_stime = from->si_stime;
-		}
+		to->si_pid = from->si_pid;
+		to->si_uid = from->si_uid;
+		to->si_status = from->si_status;
+		to->si_utime = from->si_utime;
+		to->si_stime = from->si_stime;
 		break;
 	case SIL_RT:
-		new.si_pid = from->si_pid;
-		new.si_uid = from->si_uid;
-		new.si_int = from->si_int;
+		to->si_pid = from->si_pid;
+		to->si_uid = from->si_uid;
+		to->si_int = from->si_int;
 		break;
 	case SIL_SYS:
-		new.si_call_addr = ptr_to_compat(from->si_call_addr);
-		new.si_syscall   = from->si_syscall;
-		new.si_arch      = from->si_arch;
+		to->si_call_addr = ptr_to_compat(from->si_call_addr);
+		to->si_syscall   = from->si_syscall;
+		to->si_arch      = from->si_arch;
 		break;
 	}
+}
+
+int __copy_siginfo_to_user32(struct compat_siginfo __user *to,
+			   const struct kernel_siginfo *from)
+{
+	struct compat_siginfo new;
 
+	copy_siginfo_to_external32(&new, from);
 	if (copy_to_user(to, &new, sizeof(struct compat_siginfo)))
 		return -EFAULT;
-
 	return 0;
 }
 
diff --git a/kernel/smp.c b/kernel/smp.c
index d0ada39eb4d4..d0ae8eb6bf8b 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -22,11 +22,9 @@
 #include <linux/hypervisor.h>
 
 #include "smpboot.h"
+#include "sched/smp.h"
 
-enum {
-	CSD_FLAG_LOCK		= 0x01,
-	CSD_FLAG_SYNCHRONOUS	= 0x02,
-};
+#define CSD_TYPE(_csd)	((_csd)->flags & CSD_FLAG_TYPE_MASK)
 
 struct call_function_data {
 	call_single_data_t	__percpu *csd;
@@ -84,6 +82,7 @@ int smpcfd_dying_cpu(unsigned int cpu)
 	 * still pending.
 	 */
 	flush_smp_call_function_queue(false);
+	irq_work_run();
 	return 0;
 }
 
@@ -134,15 +133,33 @@ static __always_inline void csd_unlock(call_single_data_t *csd)
 
 static DEFINE_PER_CPU_SHARED_ALIGNED(call_single_data_t, csd_data);
 
+void __smp_call_single_queue(int cpu, struct llist_node *node)
+{
+	/*
+	 * The list addition should be visible before sending the IPI
+	 * handler locks the list to pull the entry off it because of
+	 * normal cache coherency rules implied by spinlocks.
+	 *
+	 * If IPIs can go out of order to the cache coherency protocol
+	 * in an architecture, sufficient synchronisation should be added
+	 * to arch code to make it appear to obey cache coherency WRT
+	 * locking and barrier primitives. Generic code isn't really
+	 * equipped to do the right thing...
+	 */
+	if (llist_add(node, &per_cpu(call_single_queue, cpu)))
+		send_call_function_single_ipi(cpu);
+}
+
 /*
  * Insert a previously allocated call_single_data_t element
  * for execution on the given CPU. data must already have
  * ->func, ->info, and ->flags set.
  */
-static int generic_exec_single(int cpu, call_single_data_t *csd,
-			       smp_call_func_t func, void *info)
+static int generic_exec_single(int cpu, call_single_data_t *csd)
 {
 	if (cpu == smp_processor_id()) {
+		smp_call_func_t func = csd->func;
+		void *info = csd->info;
 		unsigned long flags;
 
 		/*
@@ -156,28 +173,12 @@ static int generic_exec_single(int cpu, call_single_data_t *csd,
 		return 0;
 	}
 
-
 	if ((unsigned)cpu >= nr_cpu_ids || !cpu_online(cpu)) {
 		csd_unlock(csd);
 		return -ENXIO;
 	}
 
-	csd->func = func;
-	csd->info = info;
-
-	/*
-	 * The list addition should be visible before sending the IPI
-	 * handler locks the list to pull the entry off it because of
-	 * normal cache coherency rules implied by spinlocks.
-	 *
-	 * If IPIs can go out of order to the cache coherency protocol
-	 * in an architecture, sufficient synchronisation should be added
-	 * to arch code to make it appear to obey cache coherency WRT
-	 * locking and barrier primitives. Generic code isn't really
-	 * equipped to do the right thing...
-	 */
-	if (llist_add(&csd->llist, &per_cpu(call_single_queue, cpu)))
-		arch_send_call_function_single_ipi(cpu);
+	__smp_call_single_queue(cpu, &csd->llist);
 
 	return 0;
 }
@@ -209,9 +210,9 @@ void generic_smp_call_function_single_interrupt(void)
  */
 static void flush_smp_call_function_queue(bool warn_cpu_offline)
 {
-	struct llist_head *head;
-	struct llist_node *entry;
 	call_single_data_t *csd, *csd_next;
+	struct llist_node *entry, *prev;
+	struct llist_head *head;
 	static bool warned;
 
 	lockdep_assert_irqs_disabled();
@@ -230,32 +231,99 @@ static void flush_smp_call_function_queue(bool warn_cpu_offline)
 		 * We don't have to use the _safe() variant here
 		 * because we are not invoking the IPI handlers yet.
 		 */
-		llist_for_each_entry(csd, entry, llist)
-			pr_warn("IPI callback %pS sent to offline CPU\n",
-				csd->func);
+		llist_for_each_entry(csd, entry, llist) {
+			switch (CSD_TYPE(csd)) {
+			case CSD_TYPE_ASYNC:
+			case CSD_TYPE_SYNC:
+			case CSD_TYPE_IRQ_WORK:
+				pr_warn("IPI callback %pS sent to offline CPU\n",
+					csd->func);
+				break;
+
+			case CSD_TYPE_TTWU:
+				pr_warn("IPI task-wakeup sent to offline CPU\n");
+				break;
+
+			default:
+				pr_warn("IPI callback, unknown type %d, sent to offline CPU\n",
+					CSD_TYPE(csd));
+				break;
+			}
+		}
 	}
 
+	/*
+	 * First; run all SYNC callbacks, people are waiting for us.
+	 */
+	prev = NULL;
 	llist_for_each_entry_safe(csd, csd_next, entry, llist) {
-		smp_call_func_t func = csd->func;
-		void *info = csd->info;
-
 		/* Do we wait until *after* callback? */
-		if (csd->flags & CSD_FLAG_SYNCHRONOUS) {
+		if (CSD_TYPE(csd) == CSD_TYPE_SYNC) {
+			smp_call_func_t func = csd->func;
+			void *info = csd->info;
+
+			if (prev) {
+				prev->next = &csd_next->llist;
+			} else {
+				entry = &csd_next->llist;
+			}
+
 			func(info);
 			csd_unlock(csd);
 		} else {
-			csd_unlock(csd);
-			func(info);
+			prev = &csd->llist;
 		}
 	}
 
+	if (!entry)
+		return;
+
 	/*
-	 * Handle irq works queued remotely by irq_work_queue_on().
-	 * Smp functions above are typically synchronous so they
-	 * better run first since some other CPUs may be busy waiting
-	 * for them.
+	 * Second; run all !SYNC callbacks.
 	 */
-	irq_work_run();
+	prev = NULL;
+	llist_for_each_entry_safe(csd, csd_next, entry, llist) {
+		int type = CSD_TYPE(csd);
+
+		if (type != CSD_TYPE_TTWU) {
+			if (prev) {
+				prev->next = &csd_next->llist;
+			} else {
+				entry = &csd_next->llist;
+			}
+
+			if (type == CSD_TYPE_ASYNC) {
+				smp_call_func_t func = csd->func;
+				void *info = csd->info;
+
+				csd_unlock(csd);
+				func(info);
+			} else if (type == CSD_TYPE_IRQ_WORK) {
+				irq_work_single(csd);
+			}
+
+		} else {
+			prev = &csd->llist;
+		}
+	}
+
+	/*
+	 * Third; only CSD_TYPE_TTWU is left, issue those.
+	 */
+	if (entry)
+		sched_ttwu_pending(entry);
+}
+
+void flush_smp_call_function_from_idle(void)
+{
+	unsigned long flags;
+
+	if (llist_empty(this_cpu_ptr(&call_single_queue)))
+		return;
+
+	local_irq_save(flags);
+	flush_smp_call_function_queue(true);
+	local_irq_restore(flags);
 }
 
 /*
@@ -271,7 +339,7 @@ int smp_call_function_single(int cpu, smp_call_func_t func, void *info,
 {
 	call_single_data_t *csd;
 	call_single_data_t csd_stack = {
-		.flags = CSD_FLAG_LOCK | CSD_FLAG_SYNCHRONOUS,
+		.flags = CSD_FLAG_LOCK | CSD_TYPE_SYNC,
 	};
 	int this_cpu;
 	int err;
@@ -305,7 +373,10 @@ int smp_call_function_single(int cpu, smp_call_func_t func, void *info,
 		csd_lock(csd);
 	}
 
-	err = generic_exec_single(cpu, csd, func, info);
+	csd->func = func;
+	csd->info = info;
+
+	err = generic_exec_single(cpu, csd);
 
 	if (wait)
 		csd_lock_wait(csd);
@@ -329,6 +400,11 @@ EXPORT_SYMBOL(smp_call_function_single);
  * (ie: embedded in an object) and is responsible for synchronizing it
  * such that the IPIs performed on the @csd are strictly serialized.
  *
+ * If the function is called with one csd which has not yet been
+ * processed by previous call to smp_call_function_single_async(), the
+ * function will return immediately with -EBUSY showing that the csd
+ * object is still in progress.
+ *
  * NOTE: Be careful, there is unfortunately no current debugging facility to
  * validate the correctness of this serialization.
  */
@@ -338,14 +414,17 @@ int smp_call_function_single_async(int cpu, call_single_data_t *csd)
 
 	preempt_disable();
 
-	/* We could deadlock if we have to wait here with interrupts disabled! */
-	if (WARN_ON_ONCE(csd->flags & CSD_FLAG_LOCK))
-		csd_lock_wait(csd);
+	if (csd->flags & CSD_FLAG_LOCK) {
+		err = -EBUSY;
+		goto out;
+	}
 
 	csd->flags = CSD_FLAG_LOCK;
 	smp_wmb();
 
-	err = generic_exec_single(cpu, csd, csd->func, csd->info);
+	err = generic_exec_single(cpu, csd);
+
+out:
 	preempt_enable();
 
 	return err;
@@ -458,7 +537,7 @@ static void smp_call_function_many_cond(const struct cpumask *mask,
 
 		csd_lock(csd);
 		if (wait)
-			csd->flags |= CSD_FLAG_SYNCHRONOUS;
+			csd->flags |= CSD_TYPE_SYNC;
 		csd->func = func;
 		csd->info = info;
 		if (llist_add(&csd->llist, &per_cpu(call_single_queue, cpu)))
@@ -555,8 +634,7 @@ static int __init nrcpus(char *str)
 {
 	int nr_cpus;
 
-	get_option(&str, &nr_cpus);
-	if (nr_cpus > 0 && nr_cpus < nr_cpu_ids)
+	if (get_option(&str, &nr_cpus) && nr_cpus > 0 && nr_cpus < nr_cpu_ids)
 		nr_cpu_ids = nr_cpus;
 
 	return 0;
@@ -589,20 +667,13 @@ void __init setup_nr_cpu_ids(void)
 void __init smp_init(void)
 {
 	int num_nodes, num_cpus;
-	unsigned int cpu;
 
 	idle_threads_init();
 	cpuhp_threads_init();
 
 	pr_info("Bringing up secondary CPUs ...\n");
 
-	/* FIXME: This should be done in userspace --RR */
-	for_each_present_cpu(cpu) {
-		if (num_online_cpus() >= setup_max_cpus)
-			break;
-		if (!cpu_online(cpu))
-			cpu_up(cpu);
-	}
+	bringup_nonboot_cpus(setup_max_cpus);
 
 	num_nodes = num_online_nodes();
 	num_cpus  = num_online_cpus();
@@ -619,7 +690,7 @@ void __init smp_init(void)
  * early_boot_irqs_disabled is set.  Use local_irq_save/restore() instead
  * of local_irq_disable/enable().
  */
-void on_each_cpu(void (*func) (void *info), void *info, int wait)
+void on_each_cpu(smp_call_func_t func, void *info, int wait)
 {
 	unsigned long flags;
 
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 0427a86743a4..bf88d7f62433 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -107,6 +107,12 @@ static bool ksoftirqd_running(unsigned long pending)
  * where hardirqs are disabled legitimately:
  */
 #ifdef CONFIG_TRACE_IRQFLAGS
+
+DEFINE_PER_CPU(int, hardirqs_enabled);
+DEFINE_PER_CPU(int, hardirq_context);
+EXPORT_PER_CPU_SYMBOL_GPL(hardirqs_enabled);
+EXPORT_PER_CPU_SYMBOL_GPL(hardirq_context);
+
 void __local_bh_disable_ip(unsigned long ip, unsigned int cnt)
 {
 	unsigned long flags;
@@ -126,7 +132,7 @@ void __local_bh_disable_ip(unsigned long ip, unsigned int cnt)
 	 * Were softirqs turned off above:
 	 */
 	if (softirq_count() == (cnt & SOFTIRQ_MASK))
-		trace_softirqs_off(ip);
+		lockdep_softirqs_off(ip);
 	raw_local_irq_restore(flags);
 
 	if (preempt_count() == cnt) {
@@ -147,7 +153,7 @@ static void __local_bh_enable(unsigned int cnt)
 		trace_preempt_on(CALLER_ADDR0, get_lock_parent_ip());
 
 	if (softirq_count() == (cnt & SOFTIRQ_MASK))
-		trace_softirqs_on(_RET_IP_);
+		lockdep_softirqs_on(_RET_IP_);
 
 	__preempt_count_sub(cnt);
 }
@@ -174,7 +180,7 @@ void __local_bh_enable_ip(unsigned long ip, unsigned int cnt)
 	 * Are softirqs going to be turned on now:
 	 */
 	if (softirq_count() == SOFTIRQ_DISABLE_OFFSET)
-		trace_softirqs_on(ip);
+		lockdep_softirqs_on(ip);
 	/*
 	 * Keep preemption disabled until we are done with
 	 * softirq processing:
@@ -224,9 +230,9 @@ static inline bool lockdep_softirq_start(void)
 {
 	bool in_hardirq = false;
 
-	if (trace_hardirq_context(current)) {
+	if (lockdep_hardirq_context()) {
 		in_hardirq = true;
-		trace_hardirq_exit();
+		lockdep_hardirq_exit();
 	}
 
 	lockdep_softirq_enter();
@@ -239,7 +245,7 @@ static inline void lockdep_softirq_end(bool in_hardirq)
 	lockdep_softirq_exit();
 
 	if (in_hardirq)
-		trace_hardirq_enter();
+		lockdep_hardirq_enter();
 }
 #else
 static inline bool lockdep_softirq_start(void) { return false; }
@@ -339,12 +345,11 @@ asmlinkage __visible void do_softirq(void)
 	local_irq_restore(flags);
 }
 
-/*
- * Enter an interrupt context.
+/**
+ * irq_enter_rcu - Enter an interrupt context with RCU watching
  */
-void irq_enter(void)
+void irq_enter_rcu(void)
 {
-	rcu_irq_enter();
 	if (is_idle_task(current) && !in_interrupt()) {
 		/*
 		 * Prevent raise_softirq from needlessly waking up ksoftirqd
@@ -354,10 +359,18 @@ void irq_enter(void)
 		tick_irq_enter();
 		_local_bh_enable();
 	}
-
 	__irq_enter();
 }
 
+/**
+ * irq_enter - Enter an interrupt context including RCU update
+ */
+void irq_enter(void)
+{
+	rcu_irq_enter();
+	irq_enter_rcu();
+}
+
 static inline void invoke_softirq(void)
 {
 	if (ksoftirqd_running(local_softirq_pending()))
@@ -397,10 +410,7 @@ static inline void tick_irq_exit(void)
 #endif
 }
 
-/*
- * Exit an interrupt context. Process softirqs if needed and possible:
- */
-void irq_exit(void)
+static inline void __irq_exit_rcu(void)
 {
 #ifndef __ARCH_IRQ_EXIT_IRQS_DISABLED
 	local_irq_disable();
@@ -413,8 +423,31 @@ void irq_exit(void)
 		invoke_softirq();
 
 	tick_irq_exit();
+}
+
+/**
+ * irq_exit_rcu() - Exit an interrupt context without updating RCU
+ *
+ * Also processes softirqs if needed and possible.
+ */
+void irq_exit_rcu(void)
+{
+	__irq_exit_rcu();
+	 /* must be last! */
+	lockdep_hardirq_exit();
+}
+
+/**
+ * irq_exit - Exit an interrupt context, update RCU and lockdep
+ *
+ * Also processes softirqs if needed and possible.
+ */
+void irq_exit(void)
+{
+	__irq_exit_rcu();
 	rcu_irq_exit();
-	trace_hardirq_exit(); /* must be last! */
+	 /* must be last! */
+	lockdep_hardirq_exit();
 }
 
 /*
@@ -520,7 +553,10 @@ static void tasklet_action_common(struct softirq_action *a,
 				if (!test_and_clear_bit(TASKLET_STATE_SCHED,
 							&t->state))
 					BUG();
-				t->func(t->data);
+				if (t->use_callback)
+					t->callback(t);
+				else
+					t->func(t->data);
 				tasklet_unlock(t);
 				continue;
 			}
@@ -546,6 +582,18 @@ static __latent_entropy void tasklet_hi_action(struct softirq_action *a)
 	tasklet_action_common(a, this_cpu_ptr(&tasklet_hi_vec), HI_SOFTIRQ);
 }
 
+void tasklet_setup(struct tasklet_struct *t,
+		   void (*callback)(struct tasklet_struct *))
+{
+	t->next = NULL;
+	t->state = 0;
+	atomic_set(&t->count, 0);
+	t->callback = callback;
+	t->use_callback = true;
+	t->data = 0;
+}
+EXPORT_SYMBOL(tasklet_setup);
+
 void tasklet_init(struct tasklet_struct *t,
 		  void (*func)(unsigned long), unsigned long data)
 {
@@ -553,6 +601,7 @@ void tasklet_init(struct tasklet_struct *t,
 	t->state = 0;
 	atomic_set(&t->count, 0);
 	t->func = func;
+	t->use_callback = false;
 	t->data = data;
 }
 EXPORT_SYMBOL(tasklet_init);
diff --git a/kernel/stackleak.c b/kernel/stackleak.c
index b193a59fc05b..a8fc9ae1d03d 100644
--- a/kernel/stackleak.c
+++ b/kernel/stackleak.c
@@ -104,19 +104,9 @@ asmlinkage void notrace stackleak_erase(void)
 }
 NOKPROBE_SYMBOL(stackleak_erase);
 
-void __used notrace stackleak_track_stack(void)
+void __used __no_caller_saved_registers notrace stackleak_track_stack(void)
 {
-	/*
-	 * N.B. stackleak_erase() fills the kernel stack with the poison value,
-	 * which has the register width. That code assumes that the value
-	 * of 'lowest_stack' is aligned on the register width boundary.
-	 *
-	 * That is true for x86 and x86_64 because of the kernel stack
-	 * alignment on these platforms (for details, see 'cc_stack_align' in
-	 * arch/x86/Makefile). Take care of that when you port STACKLEAK to
-	 * new platforms.
-	 */
-	unsigned long sp = (unsigned long)&sp;
+	unsigned long sp = current_stack_pointer;
 
 	/*
 	 * Having CONFIG_STACKLEAK_TRACK_MIN_SIZE larger than
@@ -125,6 +115,8 @@ void __used notrace stackleak_track_stack(void)
 	 */
 	BUILD_BUG_ON(CONFIG_STACKLEAK_TRACK_MIN_SIZE > STACKLEAK_SEARCH_DEPTH);
 
+	/* 'lowest_stack' should be aligned on the register width boundary */
+	sp = ALIGN(sp, sizeof(unsigned long));
 	if (sp < current->lowest_stack &&
 	    sp >= (unsigned long)task_stack_page(current) +
 						sizeof(unsigned long)) {
diff --git a/kernel/stacktrace.c b/kernel/stacktrace.c
index 2af66e449aa6..946f44a9e86a 100644
--- a/kernel/stacktrace.c
+++ b/kernel/stacktrace.c
@@ -233,10 +233,9 @@ unsigned int stack_trace_save_user(unsigned long *store, unsigned int size)
 	if (current->flags & PF_KTHREAD)
 		return 0;
 
-	fs = get_fs();
-	set_fs(USER_DS);
+	fs = force_uaccess_begin();
 	arch_stack_walk_user(consume_entry, &c, task_pt_regs(current));
-	set_fs(fs);
+	force_uaccess_end(fs);
 
 	return c.len;
 }
diff --git a/kernel/sys.c b/kernel/sys.c
index d325f3ab624a..ab6c409b1159 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -393,6 +393,10 @@ long __sys_setregid(gid_t rgid, gid_t egid)
 		new->sgid = new->egid;
 	new->fsgid = new->egid;
 
+	retval = security_task_fix_setgid(new, old, LSM_SETID_RE);
+	if (retval < 0)
+		goto error;
+
 	return commit_creds(new);
 
 error:
@@ -435,6 +439,10 @@ long __sys_setgid(gid_t gid)
 	else
 		goto error;
 
+	retval = security_task_fix_setgid(new, old, LSM_SETID_ID);
+	if (retval < 0)
+		goto error;
+
 	return commit_creds(new);
 
 error:
@@ -756,6 +764,10 @@ long __sys_setresgid(gid_t rgid, gid_t egid, gid_t sgid)
 		new->sgid = ksgid;
 	new->fsgid = new->egid;
 
+	retval = security_task_fix_setgid(new, old, LSM_SETID_RES);
+	if (retval < 0)
+		goto error;
+
 	return commit_creds(new);
 
 error:
@@ -862,7 +874,8 @@ long __sys_setfsgid(gid_t gid)
 	    ns_capable(old->user_ns, CAP_SETGID)) {
 		if (!gid_eq(kgid, old->fsgid)) {
 			new->fsgid = kgid;
-			goto change_okay;
+			if (security_task_fix_setgid(new,old,LSM_SETID_FS) == 0)
+				goto change_okay;
 		}
 	}
 
@@ -1740,7 +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);
@@ -1846,7 +1859,7 @@ static int prctl_set_mm_exe_file(struct mm_struct *mm, unsigned int fd)
 	if (exe_file) {
 		struct vm_area_struct *vma;
 
-		down_read(&mm->mmap_sem);
+		mmap_read_lock(mm);
 		for (vma = mm->mmap; vma; vma = vma->vm_next) {
 			if (!vma->vm_file)
 				continue;
@@ -1855,7 +1868,7 @@ static int prctl_set_mm_exe_file(struct mm_struct *mm, unsigned int fd)
 				goto exit_err;
 		}
 
-		up_read(&mm->mmap_sem);
+		mmap_read_unlock(mm);
 		fput(exe_file);
 	}
 
@@ -1869,7 +1882,7 @@ exit:
 	fdput(exe);
 	return err;
 exit_err:
-	up_read(&mm->mmap_sem);
+	mmap_read_unlock(mm);
 	fput(exe_file);
 	goto exit;
 }
@@ -1994,12 +2007,15 @@ static int prctl_set_mm_map(int opt, const void __user *addr, unsigned long data
 
 	if (prctl_map.exe_fd != (u32)-1) {
 		/*
-		 * Make sure the caller has the rights to
-		 * change /proc/pid/exe link: only local sys admin should
-		 * be allowed to.
+		 * Check if the current user is checkpoint/restore capable.
+		 * At the time of this writing, it checks for CAP_SYS_ADMIN
+		 * or CAP_CHECKPOINT_RESTORE.
+		 * Note that a user with access to ptrace can masquerade an
+		 * arbitrary program as any executable, even setuid ones.
+		 * This may have implications in the tomoyo subsystem.
 		 */
-		if (!ns_capable(current_user_ns(), CAP_SYS_ADMIN))
-			return -EINVAL;
+		if (!checkpoint_restore_ns_capable(current_user_ns()))
+			return -EPERM;
 
 		error = prctl_set_mm_exe_file(mm, prctl_map.exe_fd);
 		if (error)
@@ -2007,10 +2023,10 @@ static int prctl_set_mm_map(int opt, const void __user *addr, unsigned long data
 	}
 
 	/*
-	 * arg_lock protects concurent updates but we still need mmap_sem for
+	 * arg_lock protects concurent updates but we still need mmap_lock for
 	 * read to exclude races with sys_brk.
 	 */
-	down_read(&mm->mmap_sem);
+	mmap_read_lock(mm);
 
 	/*
 	 * We don't validate if these members are pointing to
@@ -2049,7 +2065,7 @@ static int prctl_set_mm_map(int opt, const void __user *addr, unsigned long data
 	if (prctl_map.auxv_size)
 		memcpy(mm->saved_auxv, user_auxv, sizeof(user_auxv));
 
-	up_read(&mm->mmap_sem);
+	mmap_read_unlock(mm);
 	return 0;
 }
 #endif /* CONFIG_CHECKPOINT_RESTORE */
@@ -2122,10 +2138,10 @@ static int prctl_set_mm(int opt, unsigned long addr,
 
 	/*
 	 * arg_lock protects concurent updates of arg boundaries, we need
-	 * mmap_sem for a) concurrent sys_brk, b) finding VMA for addr
+	 * mmap_lock for a) concurrent sys_brk, b) finding VMA for addr
 	 * validation.
 	 */
-	down_read(&mm->mmap_sem);
+	mmap_read_lock(mm);
 	vma = find_vma(mm, addr);
 
 	spin_lock(&mm->arg_lock);
@@ -2217,7 +2233,7 @@ static int prctl_set_mm(int opt, unsigned long addr,
 	error = 0;
 out:
 	spin_unlock(&mm->arg_lock);
-	up_read(&mm->mmap_sem);
+	mmap_read_unlock(mm);
 	return error;
 }
 
@@ -2262,7 +2278,7 @@ int __weak arch_prctl_spec_ctrl_set(struct task_struct *t, unsigned long which,
 	return -EINVAL;
 }
 
-#define PR_IO_FLUSHER (PF_MEMALLOC_NOIO | PF_LESS_THROTTLE)
+#define PR_IO_FLUSHER (PF_MEMALLOC_NOIO | PF_LOCAL_THROTTLE)
 
 SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
 		unsigned long, arg4, unsigned long, arg5)
@@ -2442,13 +2458,13 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
 	case PR_SET_THP_DISABLE:
 		if (arg3 || arg4 || arg5)
 			return -EINVAL;
-		if (down_write_killable(&me->mm->mmap_sem))
+		if (mmap_write_lock_killable(me->mm))
 			return -EINTR;
 		if (arg2)
 			set_bit(MMF_DISABLE_THP, &me->mm->flags);
 		else
 			clear_bit(MMF_DISABLE_THP, &me->mm->flags);
-		up_write(&me->mm->mmap_sem);
+		mmap_write_unlock(me->mm);
 		break;
 	case PR_MPX_ENABLE_MANAGEMENT:
 	case PR_MPX_DISABLE_MANAGEMENT:
@@ -2634,6 +2650,7 @@ struct compat_sysinfo {
 COMPAT_SYSCALL_DEFINE1(sysinfo, struct compat_sysinfo __user *, info)
 {
 	struct sysinfo s;
+	struct compat_sysinfo s_32;
 
 	do_sysinfo(&s);
 
@@ -2658,23 +2675,23 @@ COMPAT_SYSCALL_DEFINE1(sysinfo, struct compat_sysinfo __user *, info)
 		s.freehigh >>= bitcount;
 	}
 
-	if (!access_ok(info, sizeof(struct compat_sysinfo)) ||
-	    __put_user(s.uptime, &info->uptime) ||
-	    __put_user(s.loads[0], &info->loads[0]) ||
-	    __put_user(s.loads[1], &info->loads[1]) ||
-	    __put_user(s.loads[2], &info->loads[2]) ||
-	    __put_user(s.totalram, &info->totalram) ||
-	    __put_user(s.freeram, &info->freeram) ||
-	    __put_user(s.sharedram, &info->sharedram) ||
-	    __put_user(s.bufferram, &info->bufferram) ||
-	    __put_user(s.totalswap, &info->totalswap) ||
-	    __put_user(s.freeswap, &info->freeswap) ||
-	    __put_user(s.procs, &info->procs) ||
-	    __put_user(s.totalhigh, &info->totalhigh) ||
-	    __put_user(s.freehigh, &info->freehigh) ||
-	    __put_user(s.mem_unit, &info->mem_unit))
+	memset(&s_32, 0, sizeof(s_32));
+	s_32.uptime = s.uptime;
+	s_32.loads[0] = s.loads[0];
+	s_32.loads[1] = s.loads[1];
+	s_32.loads[2] = s.loads[2];
+	s_32.totalram = s.totalram;
+	s_32.freeram = s.freeram;
+	s_32.sharedram = s.sharedram;
+	s_32.bufferram = s.bufferram;
+	s_32.totalswap = s.totalswap;
+	s_32.freeswap = s.freeswap;
+	s_32.procs = s.procs;
+	s_32.totalhigh = s.totalhigh;
+	s_32.freehigh = s.freehigh;
+	s_32.mem_unit = s.mem_unit;
+	if (copy_to_user(info, &s_32, sizeof(s_32)))
 		return -EFAULT;
-
 	return 0;
 }
 #endif /* CONFIG_COMPAT */
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index 3b69a560a7ac..4d59775ea79c 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -364,7 +364,6 @@ COND_SYSCALL(socketcall);
 COND_SYSCALL_COMPAT(socketcall);
 
 /* compat syscalls for arm64, x86, ... */
-COND_SYSCALL_COMPAT(sysctl);
 COND_SYSCALL_COMPAT(fanotify_mark);
 
 /* x86 */
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index ad5b88a53c5a..287862f91717 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -68,6 +68,9 @@
 #include <linux/bpf.h>
 #include <linux/mount.h>
 #include <linux/userfaultfd_k.h>
+#include <linux/coredump.h>
+#include <linux/latencytop.h>
+#include <linux/pid.h>
 
 #include "../lib/kstrtox.h"
 
@@ -103,22 +106,6 @@
 
 #if defined(CONFIG_SYSCTL)
 
-/* External variables not in a header file. */
-extern int suid_dumpable;
-#ifdef CONFIG_COREDUMP
-extern int core_uses_pid;
-extern char core_pattern[];
-extern unsigned int core_pipe_limit;
-#endif
-extern int pid_max;
-extern int pid_max_min, pid_max_max;
-extern int percpu_pagelist_fraction;
-extern int latencytop_enabled;
-extern unsigned int sysctl_nr_open_min, sysctl_nr_open_max;
-#ifndef CONFIG_MMU
-extern int sysctl_nr_trim_pages;
-#endif
-
 /* Constants used for minimum and  maximum */
 #ifdef CONFIG_LOCKUP_DETECTOR
 static int sixty = 60;
@@ -131,6 +118,7 @@ static unsigned long zero_ul;
 static unsigned long one_ul = 1;
 static unsigned long long_max = LONG_MAX;
 static int one_hundred = 100;
+static int two_hundred = 200;
 static int one_thousand = 1000;
 #ifdef CONFIG_PRINTK
 static int ten_thousand = 10000;
@@ -160,24 +148,6 @@ static unsigned long hung_task_timeout_max = (LONG_MAX/HZ);
 #ifdef CONFIG_INOTIFY_USER
 #include <linux/inotify.h>
 #endif
-#ifdef CONFIG_SPARC
-#endif
-
-#ifdef CONFIG_PARISC
-extern int pwrsw_enabled;
-#endif
-
-#ifdef CONFIG_SYSCTL_ARCH_UNALIGN_ALLOW
-extern int unaligned_enabled;
-#endif
-
-#ifdef CONFIG_IA64
-extern int unaligned_dump_stack;
-#endif
-
-#ifdef CONFIG_SYSCTL_ARCH_UNALIGN_NO_WARN
-extern int no_unaligned_warning;
-#endif
 
 #ifdef CONFIG_PROC_SYSCTL
 
@@ -207,114 +177,1480 @@ enum sysctl_writes_mode {
 };
 
 static enum sysctl_writes_mode sysctl_writes_strict = SYSCTL_WRITES_STRICT;
+#endif /* CONFIG_PROC_SYSCTL */
 
-static int proc_do_cad_pid(struct ctl_table *table, int write,
-		  void __user *buffer, size_t *lenp, loff_t *ppos);
-static int proc_taint(struct ctl_table *table, int write,
-			       void __user *buffer, size_t *lenp, loff_t *ppos);
+#if defined(HAVE_ARCH_PICK_MMAP_LAYOUT) || \
+    defined(CONFIG_ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT)
+int sysctl_legacy_va_layout;
+#endif
+
+#ifdef CONFIG_SCHED_DEBUG
+static int min_sched_granularity_ns = 100000;		/* 100 usecs */
+static int max_sched_granularity_ns = NSEC_PER_SEC;	/* 1 second */
+static int min_wakeup_granularity_ns;			/* 0 usecs */
+static int max_wakeup_granularity_ns = NSEC_PER_SEC;	/* 1 second */
+#ifdef CONFIG_SMP
+static int min_sched_tunable_scaling = SCHED_TUNABLESCALING_NONE;
+static int max_sched_tunable_scaling = SCHED_TUNABLESCALING_END-1;
+#endif /* CONFIG_SMP */
+#endif /* CONFIG_SCHED_DEBUG */
+
+#ifdef CONFIG_COMPACTION
+static int min_extfrag_threshold;
+static int max_extfrag_threshold = 1000;
+#endif
+
+#endif /* CONFIG_SYSCTL */
+
+#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)
+{
+	struct static_key *key = (struct static_key *)table->data;
+	static int saved_val;
+	int val, ret;
+	struct ctl_table tmp = {
+		.data   = &val,
+		.maxlen = sizeof(val),
+		.mode   = table->mode,
+		.extra1 = SYSCTL_ZERO,
+		.extra2 = SYSCTL_ONE,
+	};
+
+	if (write && !capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	mutex_lock(&bpf_stats_enabled_mutex);
+	val = saved_val;
+	ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos);
+	if (write && !ret && val != saved_val) {
+		if (val)
+			static_key_slow_inc(key);
+		else
+			static_key_slow_dec(key);
+		saved_val = val;
+	}
+	mutex_unlock(&bpf_stats_enabled_mutex);
+	return ret;
+}
 #endif
 
+/*
+ * /proc/sys support
+ */
+
+#ifdef CONFIG_PROC_SYSCTL
+
+static int _proc_do_string(char *data, int maxlen, int write,
+		char *buffer, size_t *lenp, loff_t *ppos)
+{
+	size_t len;
+	char c, *p;
+
+	if (!data || !maxlen || !*lenp) {
+		*lenp = 0;
+		return 0;
+	}
+
+	if (write) {
+		if (sysctl_writes_strict == SYSCTL_WRITES_STRICT) {
+			/* Only continue writes not past the end of buffer. */
+			len = strlen(data);
+			if (len > maxlen - 1)
+				len = maxlen - 1;
+
+			if (*ppos > len)
+				return 0;
+			len = *ppos;
+		} else {
+			/* Start writing from beginning of buffer. */
+			len = 0;
+		}
+
+		*ppos += *lenp;
+		p = buffer;
+		while ((p - buffer) < *lenp && len < maxlen - 1) {
+			c = *(p++);
+			if (c == 0 || c == '\n')
+				break;
+			data[len++] = c;
+		}
+		data[len] = 0;
+	} else {
+		len = strlen(data);
+		if (len > maxlen)
+			len = maxlen;
+
+		if (*ppos > len) {
+			*lenp = 0;
+			return 0;
+		}
+
+		data += *ppos;
+		len  -= *ppos;
+
+		if (len > *lenp)
+			len = *lenp;
+		if (len)
+			memcpy(buffer, data, len);
+		if (len < *lenp) {
+			buffer[len] = '\n';
+			len++;
+		}
+		*lenp = len;
+		*ppos += len;
+	}
+	return 0;
+}
+
+static void warn_sysctl_write(struct ctl_table *table)
+{
+	pr_warn_once("%s wrote to %s when file position was not 0!\n"
+		"This will not be supported in the future. To silence this\n"
+		"warning, set kernel.sysctl_writes_strict = -1\n",
+		current->comm, table->procname);
+}
+
+/**
+ * proc_first_pos_non_zero_ignore - check if first position is allowed
+ * @ppos: file position
+ * @table: the sysctl table
+ *
+ * Returns true if the first position is non-zero and the sysctl_writes_strict
+ * mode indicates this is not allowed for numeric input types. String proc
+ * handlers can ignore the return value.
+ */
+static bool proc_first_pos_non_zero_ignore(loff_t *ppos,
+					   struct ctl_table *table)
+{
+	if (!*ppos)
+		return false;
+
+	switch (sysctl_writes_strict) {
+	case SYSCTL_WRITES_STRICT:
+		return true;
+	case SYSCTL_WRITES_WARN:
+		warn_sysctl_write(table);
+		return false;
+	default:
+		return false;
+	}
+}
+
+/**
+ * proc_dostring - read a string sysctl
+ * @table: the sysctl table
+ * @write: %TRUE if this is a write to the sysctl file
+ * @buffer: the user buffer
+ * @lenp: the size of the user buffer
+ * @ppos: file position
+ *
+ * Reads/writes a string from/to the user buffer. If the kernel
+ * buffer provided is not large enough to hold the string, the
+ * string is truncated. The copied string is %NULL-terminated.
+ * If the string is being read by the user process, it is copied
+ * and a newline '\n' is added. It is truncated if the buffer is
+ * not large enough.
+ *
+ * Returns 0 on success.
+ */
+int proc_dostring(struct ctl_table *table, int write,
+		  void *buffer, size_t *lenp, loff_t *ppos)
+{
+	if (write)
+		proc_first_pos_non_zero_ignore(ppos, table);
+
+	return _proc_do_string(table->data, table->maxlen, write, buffer, lenp,
+			ppos);
+}
+
+static size_t proc_skip_spaces(char **buf)
+{
+	size_t ret;
+	char *tmp = skip_spaces(*buf);
+	ret = tmp - *buf;
+	*buf = tmp;
+	return ret;
+}
+
+static void proc_skip_char(char **buf, size_t *size, const char v)
+{
+	while (*size) {
+		if (**buf != v)
+			break;
+		(*size)--;
+		(*buf)++;
+	}
+}
+
+/**
+ * strtoul_lenient - parse an ASCII formatted integer from a buffer and only
+ *                   fail on overflow
+ *
+ * @cp: kernel buffer containing the string to parse
+ * @endp: pointer to store the trailing characters
+ * @base: the base to use
+ * @res: where the parsed integer will be stored
+ *
+ * In case of success 0 is returned and @res will contain the parsed integer,
+ * @endp will hold any trailing characters.
+ * This function will fail the parse on overflow. If there wasn't an overflow
+ * the function will defer the decision what characters count as invalid to the
+ * caller.
+ */
+static int strtoul_lenient(const char *cp, char **endp, unsigned int base,
+			   unsigned long *res)
+{
+	unsigned long long result;
+	unsigned int rv;
+
+	cp = _parse_integer_fixup_radix(cp, &base);
+	rv = _parse_integer(cp, base, &result);
+	if ((rv & KSTRTOX_OVERFLOW) || (result != (unsigned long)result))
+		return -ERANGE;
+
+	cp += rv;
+
+	if (endp)
+		*endp = (char *)cp;
+
+	*res = (unsigned long)result;
+	return 0;
+}
+
+#define TMPBUFLEN 22
+/**
+ * proc_get_long - reads an ASCII formatted integer from a user buffer
+ *
+ * @buf: a kernel buffer
+ * @size: size of the kernel buffer
+ * @val: this is where the number will be stored
+ * @neg: set to %TRUE if number is negative
+ * @perm_tr: a vector which contains the allowed trailers
+ * @perm_tr_len: size of the perm_tr vector
+ * @tr: pointer to store the trailer character
+ *
+ * In case of success %0 is returned and @buf and @size are updated with
+ * the amount of bytes read. If @tr is non-NULL and a trailing
+ * character exists (size is non-zero after returning from this
+ * function), @tr is updated with the trailing character.
+ */
+static int proc_get_long(char **buf, size_t *size,
+			  unsigned long *val, bool *neg,
+			  const char *perm_tr, unsigned perm_tr_len, char *tr)
+{
+	int len;
+	char *p, tmp[TMPBUFLEN];
+
+	if (!*size)
+		return -EINVAL;
+
+	len = *size;
+	if (len > TMPBUFLEN - 1)
+		len = TMPBUFLEN - 1;
+
+	memcpy(tmp, *buf, len);
+
+	tmp[len] = 0;
+	p = tmp;
+	if (*p == '-' && *size > 1) {
+		*neg = true;
+		p++;
+	} else
+		*neg = false;
+	if (!isdigit(*p))
+		return -EINVAL;
+
+	if (strtoul_lenient(p, &p, 0, val))
+		return -EINVAL;
+
+	len = p - tmp;
+
+	/* We don't know if the next char is whitespace thus we may accept
+	 * invalid integers (e.g. 1234...a) or two integers instead of one
+	 * (e.g. 123...1). So lets not allow such large numbers. */
+	if (len == TMPBUFLEN - 1)
+		return -EINVAL;
+
+	if (len < *size && perm_tr_len && !memchr(perm_tr, *p, perm_tr_len))
+		return -EINVAL;
+
+	if (tr && (len < *size))
+		*tr = *p;
+
+	*buf += len;
+	*size -= len;
+
+	return 0;
+}
+
+/**
+ * proc_put_long - converts an integer to a decimal ASCII formatted string
+ *
+ * @buf: the user buffer
+ * @size: the size of the user buffer
+ * @val: the integer to be converted
+ * @neg: sign of the number, %TRUE for negative
+ *
+ * In case of success @buf and @size are updated with the amount of bytes
+ * written.
+ */
+static void proc_put_long(void **buf, size_t *size, unsigned long val, bool neg)
+{
+	int len;
+	char tmp[TMPBUFLEN], *p = tmp;
+
+	sprintf(p, "%s%lu", neg ? "-" : "", val);
+	len = strlen(tmp);
+	if (len > *size)
+		len = *size;
+	memcpy(*buf, tmp, len);
+	*size -= len;
+	*buf += len;
+}
+#undef TMPBUFLEN
+
+static void proc_put_char(void **buf, size_t *size, char c)
+{
+	if (*size) {
+		char **buffer = (char **)buf;
+		**buffer = c;
+
+		(*size)--;
+		(*buffer)++;
+		*buf = *buffer;
+	}
+}
+
+static int do_proc_dointvec_conv(bool *negp, unsigned long *lvalp,
+				 int *valp,
+				 int write, void *data)
+{
+	if (write) {
+		if (*negp) {
+			if (*lvalp > (unsigned long) INT_MAX + 1)
+				return -EINVAL;
+			*valp = -*lvalp;
+		} else {
+			if (*lvalp > (unsigned long) INT_MAX)
+				return -EINVAL;
+			*valp = *lvalp;
+		}
+	} else {
+		int val = *valp;
+		if (val < 0) {
+			*negp = true;
+			*lvalp = -(unsigned long)val;
+		} else {
+			*negp = false;
+			*lvalp = (unsigned long)val;
+		}
+	}
+	return 0;
+}
+
+static int do_proc_douintvec_conv(unsigned long *lvalp,
+				  unsigned int *valp,
+				  int write, void *data)
+{
+	if (write) {
+		if (*lvalp > UINT_MAX)
+			return -EINVAL;
+		*valp = *lvalp;
+	} else {
+		unsigned int val = *valp;
+		*lvalp = (unsigned long)val;
+	}
+	return 0;
+}
+
+static const char proc_wspace_sep[] = { ' ', '\t', '\n' };
+
+static int __do_proc_dointvec(void *tbl_data, struct ctl_table *table,
+		  int write, void *buffer,
+		  size_t *lenp, loff_t *ppos,
+		  int (*conv)(bool *negp, unsigned long *lvalp, int *valp,
+			      int write, void *data),
+		  void *data)
+{
+	int *i, vleft, first = 1, err = 0;
+	size_t left;
+	char *p;
+	
+	if (!tbl_data || !table->maxlen || !*lenp || (*ppos && !write)) {
+		*lenp = 0;
+		return 0;
+	}
+	
+	i = (int *) tbl_data;
+	vleft = table->maxlen / sizeof(*i);
+	left = *lenp;
+
+	if (!conv)
+		conv = do_proc_dointvec_conv;
+
+	if (write) {
+		if (proc_first_pos_non_zero_ignore(ppos, table))
+			goto out;
+
+		if (left > PAGE_SIZE - 1)
+			left = PAGE_SIZE - 1;
+		p = buffer;
+	}
+
+	for (; left && vleft--; i++, first=0) {
+		unsigned long lval;
+		bool neg;
+
+		if (write) {
+			left -= proc_skip_spaces(&p);
+
+			if (!left)
+				break;
+			err = proc_get_long(&p, &left, &lval, &neg,
+					     proc_wspace_sep,
+					     sizeof(proc_wspace_sep), NULL);
+			if (err)
+				break;
+			if (conv(&neg, &lval, i, 1, data)) {
+				err = -EINVAL;
+				break;
+			}
+		} else {
+			if (conv(&neg, &lval, i, 0, data)) {
+				err = -EINVAL;
+				break;
+			}
+			if (!first)
+				proc_put_char(&buffer, &left, '\t');
+			proc_put_long(&buffer, &left, lval, neg);
+		}
+	}
+
+	if (!write && !first && left && !err)
+		proc_put_char(&buffer, &left, '\n');
+	if (write && !err && left)
+		left -= proc_skip_spaces(&p);
+	if (write && first)
+		return err ? : -EINVAL;
+	*lenp -= left;
+out:
+	*ppos += *lenp;
+	return err;
+}
+
+static int do_proc_dointvec(struct ctl_table *table, int write,
+		  void *buffer, size_t *lenp, loff_t *ppos,
+		  int (*conv)(bool *negp, unsigned long *lvalp, int *valp,
+			      int write, void *data),
+		  void *data)
+{
+	return __do_proc_dointvec(table->data, table, write,
+			buffer, lenp, ppos, conv, data);
+}
+
+static int do_proc_douintvec_w(unsigned int *tbl_data,
+			       struct ctl_table *table,
+			       void *buffer,
+			       size_t *lenp, loff_t *ppos,
+			       int (*conv)(unsigned long *lvalp,
+					   unsigned int *valp,
+					   int write, void *data),
+			       void *data)
+{
+	unsigned long lval;
+	int err = 0;
+	size_t left;
+	bool neg;
+	char *p = buffer;
+
+	left = *lenp;
+
+	if (proc_first_pos_non_zero_ignore(ppos, table))
+		goto bail_early;
+
+	if (left > PAGE_SIZE - 1)
+		left = PAGE_SIZE - 1;
+
+	left -= proc_skip_spaces(&p);
+	if (!left) {
+		err = -EINVAL;
+		goto out_free;
+	}
+
+	err = proc_get_long(&p, &left, &lval, &neg,
+			     proc_wspace_sep,
+			     sizeof(proc_wspace_sep), NULL);
+	if (err || neg) {
+		err = -EINVAL;
+		goto out_free;
+	}
+
+	if (conv(&lval, tbl_data, 1, data)) {
+		err = -EINVAL;
+		goto out_free;
+	}
+
+	if (!err && left)
+		left -= proc_skip_spaces(&p);
+
+out_free:
+	if (err)
+		return -EINVAL;
+
+	return 0;
+
+	/* This is in keeping with old __do_proc_dointvec() */
+bail_early:
+	*ppos += *lenp;
+	return err;
+}
+
+static int do_proc_douintvec_r(unsigned int *tbl_data, void *buffer,
+			       size_t *lenp, loff_t *ppos,
+			       int (*conv)(unsigned long *lvalp,
+					   unsigned int *valp,
+					   int write, void *data),
+			       void *data)
+{
+	unsigned long lval;
+	int err = 0;
+	size_t left;
+
+	left = *lenp;
+
+	if (conv(&lval, tbl_data, 0, data)) {
+		err = -EINVAL;
+		goto out;
+	}
+
+	proc_put_long(&buffer, &left, lval, false);
+	if (!left)
+		goto out;
+
+	proc_put_char(&buffer, &left, '\n');
+
+out:
+	*lenp -= left;
+	*ppos += *lenp;
+
+	return err;
+}
+
+static int __do_proc_douintvec(void *tbl_data, struct ctl_table *table,
+			       int write, void *buffer,
+			       size_t *lenp, loff_t *ppos,
+			       int (*conv)(unsigned long *lvalp,
+					   unsigned int *valp,
+					   int write, void *data),
+			       void *data)
+{
+	unsigned int *i, vleft;
+
+	if (!tbl_data || !table->maxlen || !*lenp || (*ppos && !write)) {
+		*lenp = 0;
+		return 0;
+	}
+
+	i = (unsigned int *) tbl_data;
+	vleft = table->maxlen / sizeof(*i);
+
+	/*
+	 * Arrays are not supported, keep this simple. *Do not* add
+	 * support for them.
+	 */
+	if (vleft != 1) {
+		*lenp = 0;
+		return -EINVAL;
+	}
+
+	if (!conv)
+		conv = do_proc_douintvec_conv;
+
+	if (write)
+		return do_proc_douintvec_w(i, table, buffer, lenp, ppos,
+					   conv, data);
+	return do_proc_douintvec_r(i, buffer, lenp, ppos, conv, data);
+}
+
+static int do_proc_douintvec(struct ctl_table *table, int write,
+			     void *buffer, size_t *lenp, loff_t *ppos,
+			     int (*conv)(unsigned long *lvalp,
+					 unsigned int *valp,
+					 int write, void *data),
+			     void *data)
+{
+	return __do_proc_douintvec(table->data, table, write,
+				   buffer, lenp, ppos, conv, data);
+}
+
+/**
+ * proc_dointvec - read a vector of integers
+ * @table: the sysctl table
+ * @write: %TRUE if this is a write to the sysctl file
+ * @buffer: the user buffer
+ * @lenp: the size of the user buffer
+ * @ppos: file position
+ *
+ * Reads/writes up to table->maxlen/sizeof(unsigned int) integer
+ * values from/to the user buffer, treated as an ASCII string. 
+ *
+ * Returns 0 on success.
+ */
+int proc_dointvec(struct ctl_table *table, int write, void *buffer,
+		  size_t *lenp, loff_t *ppos)
+{
+	return do_proc_dointvec(table, write, buffer, lenp, ppos, NULL, NULL);
+}
+
+#ifdef CONFIG_COMPACTION
+static int proc_dointvec_minmax_warn_RT_change(struct ctl_table *table,
+		int write, void *buffer, size_t *lenp, loff_t *ppos)
+{
+	int ret, old;
+
+	if (!IS_ENABLED(CONFIG_PREEMPT_RT) || !write)
+		return proc_dointvec_minmax(table, write, buffer, lenp, ppos);
+
+	old = *(int *)table->data;
+	ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
+	if (ret)
+		return ret;
+	if (old != *(int *)table->data)
+		pr_warn_once("sysctl attribute %s changed by %s[%d]\n",
+			     table->procname, current->comm,
+			     task_pid_nr(current));
+	return ret;
+}
+#endif
+
+/**
+ * proc_douintvec - read a vector of unsigned integers
+ * @table: the sysctl table
+ * @write: %TRUE if this is a write to the sysctl file
+ * @buffer: the user buffer
+ * @lenp: the size of the user buffer
+ * @ppos: file position
+ *
+ * Reads/writes up to table->maxlen/sizeof(unsigned int) unsigned integer
+ * values from/to the user buffer, treated as an ASCII string.
+ *
+ * Returns 0 on success.
+ */
+int proc_douintvec(struct ctl_table *table, int write, void *buffer,
+		size_t *lenp, loff_t *ppos)
+{
+	return do_proc_douintvec(table, write, buffer, lenp, ppos,
+				 do_proc_douintvec_conv, NULL);
+}
+
+/*
+ * Taint values can only be increased
+ * This means we can safely use a temporary.
+ */
+static int proc_taint(struct ctl_table *table, int write,
+			       void *buffer, size_t *lenp, loff_t *ppos)
+{
+	struct ctl_table t;
+	unsigned long tmptaint = get_taint();
+	int err;
+
+	if (write && !capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	t = *table;
+	t.data = &tmptaint;
+	err = proc_doulongvec_minmax(&t, write, buffer, lenp, ppos);
+	if (err < 0)
+		return err;
+
+	if (write) {
+		int i;
+
+		/*
+		 * If we are relying on panic_on_taint not producing
+		 * false positives due to userspace input, bail out
+		 * before setting the requested taint flags.
+		 */
+		if (panic_on_taint_nousertaint && (tmptaint & panic_on_taint))
+			return -EINVAL;
+
+		/*
+		 * Poor man's atomic or. Not worth adding a primitive
+		 * to everyone's atomic.h for this
+		 */
+		for (i = 0; i < TAINT_FLAGS_COUNT; i++)
+			if ((1UL << i) & tmptaint)
+				add_taint(i, LOCKDEP_STILL_OK);
+	}
+
+	return err;
+}
+
 #ifdef CONFIG_PRINTK
 static int proc_dointvec_minmax_sysadmin(struct ctl_table *table, int write,
-				void __user *buffer, size_t *lenp, loff_t *ppos);
+				void *buffer, size_t *lenp, loff_t *ppos)
+{
+	if (write && !capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	return proc_dointvec_minmax(table, write, buffer, lenp, ppos);
+}
+#endif
+
+/**
+ * struct do_proc_dointvec_minmax_conv_param - proc_dointvec_minmax() range checking structure
+ * @min: pointer to minimum allowable value
+ * @max: pointer to maximum allowable value
+ *
+ * The do_proc_dointvec_minmax_conv_param structure provides the
+ * minimum and maximum values for doing range checking for those sysctl
+ * parameters that use the proc_dointvec_minmax() handler.
+ */
+struct do_proc_dointvec_minmax_conv_param {
+	int *min;
+	int *max;
+};
+
+static int do_proc_dointvec_minmax_conv(bool *negp, unsigned long *lvalp,
+					int *valp,
+					int write, void *data)
+{
+	int tmp, ret;
+	struct do_proc_dointvec_minmax_conv_param *param = data;
+	/*
+	 * If writing, first do so via a temporary local int so we can
+	 * bounds-check it before touching *valp.
+	 */
+	int *ip = write ? &tmp : valp;
+
+	ret = do_proc_dointvec_conv(negp, lvalp, ip, write, data);
+	if (ret)
+		return ret;
+
+	if (write) {
+		if ((param->min && *param->min > tmp) ||
+		    (param->max && *param->max < tmp))
+			return -EINVAL;
+		*valp = tmp;
+	}
+
+	return 0;
+}
+
+/**
+ * proc_dointvec_minmax - read a vector of integers with min/max values
+ * @table: the sysctl table
+ * @write: %TRUE if this is a write to the sysctl file
+ * @buffer: the user buffer
+ * @lenp: the size of the user buffer
+ * @ppos: file position
+ *
+ * Reads/writes up to table->maxlen/sizeof(unsigned int) integer
+ * values from/to the user buffer, treated as an ASCII string.
+ *
+ * This routine will ensure the values are within the range specified by
+ * table->extra1 (min) and table->extra2 (max).
+ *
+ * Returns 0 on success or -EINVAL on write when the range check fails.
+ */
+int proc_dointvec_minmax(struct ctl_table *table, int write,
+		  void *buffer, size_t *lenp, loff_t *ppos)
+{
+	struct do_proc_dointvec_minmax_conv_param param = {
+		.min = (int *) table->extra1,
+		.max = (int *) table->extra2,
+	};
+	return do_proc_dointvec(table, write, buffer, lenp, ppos,
+				do_proc_dointvec_minmax_conv, &param);
+}
+
+/**
+ * struct do_proc_douintvec_minmax_conv_param - proc_douintvec_minmax() range checking structure
+ * @min: pointer to minimum allowable value
+ * @max: pointer to maximum allowable value
+ *
+ * The do_proc_douintvec_minmax_conv_param structure provides the
+ * minimum and maximum values for doing range checking for those sysctl
+ * parameters that use the proc_douintvec_minmax() handler.
+ */
+struct do_proc_douintvec_minmax_conv_param {
+	unsigned int *min;
+	unsigned int *max;
+};
+
+static int do_proc_douintvec_minmax_conv(unsigned long *lvalp,
+					 unsigned int *valp,
+					 int write, void *data)
+{
+	int ret;
+	unsigned int tmp;
+	struct do_proc_douintvec_minmax_conv_param *param = data;
+	/* write via temporary local uint for bounds-checking */
+	unsigned int *up = write ? &tmp : valp;
+
+	ret = do_proc_douintvec_conv(lvalp, up, write, data);
+	if (ret)
+		return ret;
+
+	if (write) {
+		if ((param->min && *param->min > tmp) ||
+		    (param->max && *param->max < tmp))
+			return -ERANGE;
+
+		*valp = tmp;
+	}
+
+	return 0;
+}
+
+/**
+ * proc_douintvec_minmax - read a vector of unsigned ints with min/max values
+ * @table: the sysctl table
+ * @write: %TRUE if this is a write to the sysctl file
+ * @buffer: the user buffer
+ * @lenp: the size of the user buffer
+ * @ppos: file position
+ *
+ * Reads/writes up to table->maxlen/sizeof(unsigned int) unsigned integer
+ * values from/to the user buffer, treated as an ASCII string. Negative
+ * strings are not allowed.
+ *
+ * This routine will ensure the values are within the range specified by
+ * table->extra1 (min) and table->extra2 (max). There is a final sanity
+ * check for UINT_MAX to avoid having to support wrap around uses from
+ * userspace.
+ *
+ * Returns 0 on success or -ERANGE on write when the range check fails.
+ */
+int proc_douintvec_minmax(struct ctl_table *table, int write,
+			  void *buffer, size_t *lenp, loff_t *ppos)
+{
+	struct do_proc_douintvec_minmax_conv_param param = {
+		.min = (unsigned int *) table->extra1,
+		.max = (unsigned int *) table->extra2,
+	};
+	return do_proc_douintvec(table, write, buffer, lenp, ppos,
+				 do_proc_douintvec_minmax_conv, &param);
+}
+
+static int do_proc_dopipe_max_size_conv(unsigned long *lvalp,
+					unsigned int *valp,
+					int write, void *data)
+{
+	if (write) {
+		unsigned int val;
+
+		val = round_pipe_size(*lvalp);
+		if (val == 0)
+			return -EINVAL;
+
+		*valp = val;
+	} else {
+		unsigned int val = *valp;
+		*lvalp = (unsigned long) val;
+	}
+
+	return 0;
+}
+
+static int proc_dopipe_max_size(struct ctl_table *table, int write,
+				void *buffer, size_t *lenp, loff_t *ppos)
+{
+	return do_proc_douintvec(table, write, buffer, lenp, ppos,
+				 do_proc_dopipe_max_size_conv, NULL);
+}
+
+static void validate_coredump_safety(void)
+{
+#ifdef CONFIG_COREDUMP
+	if (suid_dumpable == SUID_DUMP_ROOT &&
+	    core_pattern[0] != '/' && core_pattern[0] != '|') {
+		printk(KERN_WARNING
+"Unsafe core_pattern used with fs.suid_dumpable=2.\n"
+"Pipe handler or fully qualified core dump path required.\n"
+"Set kernel.core_pattern before fs.suid_dumpable.\n"
+		);
+	}
 #endif
+}
 
 static int proc_dointvec_minmax_coredump(struct ctl_table *table, int write,
-		void __user *buffer, size_t *lenp, loff_t *ppos);
+		void *buffer, size_t *lenp, loff_t *ppos)
+{
+	int error = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
+	if (!error)
+		validate_coredump_safety();
+	return error;
+}
+
 #ifdef CONFIG_COREDUMP
 static int proc_dostring_coredump(struct ctl_table *table, int write,
-		void __user *buffer, size_t *lenp, loff_t *ppos);
+		  void *buffer, size_t *lenp, loff_t *ppos)
+{
+	int error = proc_dostring(table, write, buffer, lenp, ppos);
+	if (!error)
+		validate_coredump_safety();
+	return error;
+}
 #endif
-static int proc_dopipe_max_size(struct ctl_table *table, int write,
-		void __user *buffer, size_t *lenp, loff_t *ppos);
 
 #ifdef CONFIG_MAGIC_SYSRQ
-/* Note: sysrq code uses its own private copy */
-static int __sysrq_enabled = CONFIG_MAGIC_SYSRQ_DEFAULT_ENABLE;
-
 static int sysrq_sysctl_handler(struct ctl_table *table, int write,
-				void __user *buffer, size_t *lenp,
-				loff_t *ppos)
+				void *buffer, size_t *lenp, loff_t *ppos)
 {
-	int error;
+	int tmp, ret;
+
+	tmp = sysrq_mask();
 
-	error = proc_dointvec(table, write, buffer, lenp, ppos);
-	if (error)
-		return error;
+	ret = __do_proc_dointvec(&tmp, table, write, buffer,
+			       lenp, ppos, NULL, NULL);
+	if (ret || !write)
+		return ret;
 
 	if (write)
-		sysrq_toggle_support(__sysrq_enabled);
+		sysrq_toggle_support(tmp);
 
 	return 0;
 }
-
 #endif
 
-static struct ctl_table kern_table[];
-static struct ctl_table vm_table[];
-static struct ctl_table fs_table[];
-static struct ctl_table debug_table[];
-static struct ctl_table dev_table[];
-extern struct ctl_table random_table[];
-#ifdef CONFIG_EPOLL
-extern struct ctl_table epoll_table[];
-#endif
+static int __do_proc_doulongvec_minmax(void *data, struct ctl_table *table,
+		int write, void *buffer, size_t *lenp, loff_t *ppos,
+		unsigned long convmul, unsigned long convdiv)
+{
+	unsigned long *i, *min, *max;
+	int vleft, first = 1, err = 0;
+	size_t left;
+	char *p;
 
-#ifdef CONFIG_FW_LOADER_USER_HELPER
-extern struct ctl_table firmware_config_table[];
-#endif
+	if (!data || !table->maxlen || !*lenp || (*ppos && !write)) {
+		*lenp = 0;
+		return 0;
+	}
 
-#if defined(HAVE_ARCH_PICK_MMAP_LAYOUT) || \
-    defined(CONFIG_ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT)
-int sysctl_legacy_va_layout;
-#endif
+	i = (unsigned long *) data;
+	min = (unsigned long *) table->extra1;
+	max = (unsigned long *) table->extra2;
+	vleft = table->maxlen / sizeof(unsigned long);
+	left = *lenp;
 
-/* The default sysctl tables: */
+	if (write) {
+		if (proc_first_pos_non_zero_ignore(ppos, table))
+			goto out;
 
-static struct ctl_table sysctl_base_table[] = {
-	{
-		.procname	= "kernel",
-		.mode		= 0555,
-		.child		= kern_table,
-	},
-	{
-		.procname	= "vm",
-		.mode		= 0555,
-		.child		= vm_table,
-	},
-	{
-		.procname	= "fs",
-		.mode		= 0555,
-		.child		= fs_table,
-	},
-	{
-		.procname	= "debug",
-		.mode		= 0555,
-		.child		= debug_table,
-	},
-	{
-		.procname	= "dev",
-		.mode		= 0555,
-		.child		= dev_table,
-	},
-	{ }
-};
+		if (left > PAGE_SIZE - 1)
+			left = PAGE_SIZE - 1;
+		p = buffer;
+	}
 
-#ifdef CONFIG_SCHED_DEBUG
-static int min_sched_granularity_ns = 100000;		/* 100 usecs */
-static int max_sched_granularity_ns = NSEC_PER_SEC;	/* 1 second */
-static int min_wakeup_granularity_ns;			/* 0 usecs */
-static int max_wakeup_granularity_ns = NSEC_PER_SEC;	/* 1 second */
-#ifdef CONFIG_SMP
-static int min_sched_tunable_scaling = SCHED_TUNABLESCALING_NONE;
-static int max_sched_tunable_scaling = SCHED_TUNABLESCALING_END-1;
-#endif /* CONFIG_SMP */
-#endif /* CONFIG_SCHED_DEBUG */
+	for (; left && vleft--; i++, first = 0) {
+		unsigned long val;
 
-#ifdef CONFIG_COMPACTION
-static int min_extfrag_threshold;
-static int max_extfrag_threshold = 1000;
-#endif
+		if (write) {
+			bool neg;
+
+			left -= proc_skip_spaces(&p);
+			if (!left)
+				break;
+
+			err = proc_get_long(&p, &left, &val, &neg,
+					     proc_wspace_sep,
+					     sizeof(proc_wspace_sep), NULL);
+			if (err)
+				break;
+			if (neg)
+				continue;
+			val = convmul * val / convdiv;
+			if ((min && val < *min) || (max && val > *max)) {
+				err = -EINVAL;
+				break;
+			}
+			*i = val;
+		} else {
+			val = convdiv * (*i) / convmul;
+			if (!first)
+				proc_put_char(&buffer, &left, '\t');
+			proc_put_long(&buffer, &left, val, false);
+		}
+	}
+
+	if (!write && !first && left && !err)
+		proc_put_char(&buffer, &left, '\n');
+	if (write && !err)
+		left -= proc_skip_spaces(&p);
+	if (write && first)
+		return err ? : -EINVAL;
+	*lenp -= left;
+out:
+	*ppos += *lenp;
+	return err;
+}
+
+static int do_proc_doulongvec_minmax(struct ctl_table *table, int write,
+		void *buffer, size_t *lenp, loff_t *ppos, unsigned long convmul,
+		unsigned long convdiv)
+{
+	return __do_proc_doulongvec_minmax(table->data, table, write,
+			buffer, lenp, ppos, convmul, convdiv);
+}
+
+/**
+ * proc_doulongvec_minmax - read a vector of long integers with min/max values
+ * @table: the sysctl table
+ * @write: %TRUE if this is a write to the sysctl file
+ * @buffer: the user buffer
+ * @lenp: the size of the user buffer
+ * @ppos: file position
+ *
+ * Reads/writes up to table->maxlen/sizeof(unsigned long) unsigned long
+ * values from/to the user buffer, treated as an ASCII string.
+ *
+ * This routine will ensure the values are within the range specified by
+ * table->extra1 (min) and table->extra2 (max).
+ *
+ * Returns 0 on success.
+ */
+int proc_doulongvec_minmax(struct ctl_table *table, int write,
+			   void *buffer, size_t *lenp, loff_t *ppos)
+{
+    return do_proc_doulongvec_minmax(table, write, buffer, lenp, ppos, 1l, 1l);
+}
+
+/**
+ * proc_doulongvec_ms_jiffies_minmax - read a vector of millisecond values with min/max values
+ * @table: the sysctl table
+ * @write: %TRUE if this is a write to the sysctl file
+ * @buffer: the user buffer
+ * @lenp: the size of the user buffer
+ * @ppos: file position
+ *
+ * Reads/writes up to table->maxlen/sizeof(unsigned long) unsigned long
+ * values from/to the user buffer, treated as an ASCII string. The values
+ * are treated as milliseconds, and converted to jiffies when they are stored.
+ *
+ * This routine will ensure the values are within the range specified by
+ * table->extra1 (min) and table->extra2 (max).
+ *
+ * Returns 0 on success.
+ */
+int proc_doulongvec_ms_jiffies_minmax(struct ctl_table *table, int write,
+				      void *buffer, size_t *lenp, loff_t *ppos)
+{
+    return do_proc_doulongvec_minmax(table, write, buffer,
+				     lenp, ppos, HZ, 1000l);
+}
+
+
+static int do_proc_dointvec_jiffies_conv(bool *negp, unsigned long *lvalp,
+					 int *valp,
+					 int write, void *data)
+{
+	if (write) {
+		if (*lvalp > INT_MAX / HZ)
+			return 1;
+		*valp = *negp ? -(*lvalp*HZ) : (*lvalp*HZ);
+	} else {
+		int val = *valp;
+		unsigned long lval;
+		if (val < 0) {
+			*negp = true;
+			lval = -(unsigned long)val;
+		} else {
+			*negp = false;
+			lval = (unsigned long)val;
+		}
+		*lvalp = lval / HZ;
+	}
+	return 0;
+}
+
+static int do_proc_dointvec_userhz_jiffies_conv(bool *negp, unsigned long *lvalp,
+						int *valp,
+						int write, void *data)
+{
+	if (write) {
+		if (USER_HZ < HZ && *lvalp > (LONG_MAX / HZ) * USER_HZ)
+			return 1;
+		*valp = clock_t_to_jiffies(*negp ? -*lvalp : *lvalp);
+	} else {
+		int val = *valp;
+		unsigned long lval;
+		if (val < 0) {
+			*negp = true;
+			lval = -(unsigned long)val;
+		} else {
+			*negp = false;
+			lval = (unsigned long)val;
+		}
+		*lvalp = jiffies_to_clock_t(lval);
+	}
+	return 0;
+}
+
+static int do_proc_dointvec_ms_jiffies_conv(bool *negp, unsigned long *lvalp,
+					    int *valp,
+					    int write, void *data)
+{
+	if (write) {
+		unsigned long jif = msecs_to_jiffies(*negp ? -*lvalp : *lvalp);
+
+		if (jif > INT_MAX)
+			return 1;
+		*valp = (int)jif;
+	} else {
+		int val = *valp;
+		unsigned long lval;
+		if (val < 0) {
+			*negp = true;
+			lval = -(unsigned long)val;
+		} else {
+			*negp = false;
+			lval = (unsigned long)val;
+		}
+		*lvalp = jiffies_to_msecs(lval);
+	}
+	return 0;
+}
+
+/**
+ * proc_dointvec_jiffies - read a vector of integers as seconds
+ * @table: the sysctl table
+ * @write: %TRUE if this is a write to the sysctl file
+ * @buffer: the user buffer
+ * @lenp: the size of the user buffer
+ * @ppos: file position
+ *
+ * Reads/writes up to table->maxlen/sizeof(unsigned int) integer
+ * values from/to the user buffer, treated as an ASCII string. 
+ * The values read are assumed to be in seconds, and are converted into
+ * jiffies.
+ *
+ * Returns 0 on success.
+ */
+int proc_dointvec_jiffies(struct ctl_table *table, int write,
+			  void *buffer, size_t *lenp, loff_t *ppos)
+{
+    return do_proc_dointvec(table,write,buffer,lenp,ppos,
+		    	    do_proc_dointvec_jiffies_conv,NULL);
+}
+
+/**
+ * proc_dointvec_userhz_jiffies - read a vector of integers as 1/USER_HZ seconds
+ * @table: the sysctl table
+ * @write: %TRUE if this is a write to the sysctl file
+ * @buffer: the user buffer
+ * @lenp: the size of the user buffer
+ * @ppos: pointer to the file position
+ *
+ * Reads/writes up to table->maxlen/sizeof(unsigned int) integer
+ * values from/to the user buffer, treated as an ASCII string. 
+ * The values read are assumed to be in 1/USER_HZ seconds, and 
+ * are converted into jiffies.
+ *
+ * Returns 0 on success.
+ */
+int proc_dointvec_userhz_jiffies(struct ctl_table *table, int write,
+				 void *buffer, size_t *lenp, loff_t *ppos)
+{
+    return do_proc_dointvec(table,write,buffer,lenp,ppos,
+		    	    do_proc_dointvec_userhz_jiffies_conv,NULL);
+}
+
+/**
+ * proc_dointvec_ms_jiffies - read a vector of integers as 1 milliseconds
+ * @table: the sysctl table
+ * @write: %TRUE if this is a write to the sysctl file
+ * @buffer: the user buffer
+ * @lenp: the size of the user buffer
+ * @ppos: file position
+ * @ppos: the current position in the file
+ *
+ * Reads/writes up to table->maxlen/sizeof(unsigned int) integer
+ * values from/to the user buffer, treated as an ASCII string. 
+ * The values read are assumed to be in 1/1000 seconds, and 
+ * are converted into jiffies.
+ *
+ * Returns 0 on success.
+ */
+int proc_dointvec_ms_jiffies(struct ctl_table *table, int write, void *buffer,
+		size_t *lenp, loff_t *ppos)
+{
+	return do_proc_dointvec(table, write, buffer, lenp, ppos,
+				do_proc_dointvec_ms_jiffies_conv, NULL);
+}
+
+static int proc_do_cad_pid(struct ctl_table *table, int write, void *buffer,
+		size_t *lenp, loff_t *ppos)
+{
+	struct pid *new_pid;
+	pid_t tmp;
+	int r;
+
+	tmp = pid_vnr(cad_pid);
+
+	r = __do_proc_dointvec(&tmp, table, write, buffer,
+			       lenp, ppos, NULL, NULL);
+	if (r || !write)
+		return r;
+
+	new_pid = find_get_pid(tmp);
+	if (!new_pid)
+		return -ESRCH;
+
+	put_pid(xchg(&cad_pid, new_pid));
+	return 0;
+}
+
+/**
+ * proc_do_large_bitmap - read/write from/to a large bitmap
+ * @table: the sysctl table
+ * @write: %TRUE if this is a write to the sysctl file
+ * @buffer: the user buffer
+ * @lenp: the size of the user buffer
+ * @ppos: file position
+ *
+ * The bitmap is stored at table->data and the bitmap length (in bits)
+ * in table->maxlen.
+ *
+ * We use a range comma separated format (e.g. 1,3-4,10-10) so that
+ * large bitmaps may be represented in a compact manner. Writing into
+ * the file will clear the bitmap then update it with the given input.
+ *
+ * Returns 0 on success.
+ */
+int proc_do_large_bitmap(struct ctl_table *table, int write,
+			 void *buffer, size_t *lenp, loff_t *ppos)
+{
+	int err = 0;
+	bool first = 1;
+	size_t left = *lenp;
+	unsigned long bitmap_len = table->maxlen;
+	unsigned long *bitmap = *(unsigned long **) table->data;
+	unsigned long *tmp_bitmap = NULL;
+	char tr_a[] = { '-', ',', '\n' }, tr_b[] = { ',', '\n', 0 }, c;
+
+	if (!bitmap || !bitmap_len || !left || (*ppos && !write)) {
+		*lenp = 0;
+		return 0;
+	}
+
+	if (write) {
+		char *p = buffer;
+		size_t skipped = 0;
+
+		if (left > PAGE_SIZE - 1) {
+			left = PAGE_SIZE - 1;
+			/* How much of the buffer we'll skip this pass */
+			skipped = *lenp - left;
+		}
+
+		tmp_bitmap = bitmap_zalloc(bitmap_len, GFP_KERNEL);
+		if (!tmp_bitmap)
+			return -ENOMEM;
+		proc_skip_char(&p, &left, '\n');
+		while (!err && left) {
+			unsigned long val_a, val_b;
+			bool neg;
+			size_t saved_left;
+
+			/* In case we stop parsing mid-number, we can reset */
+			saved_left = left;
+			err = proc_get_long(&p, &left, &val_a, &neg, tr_a,
+					     sizeof(tr_a), &c);
+			/*
+			 * If we consumed the entirety of a truncated buffer or
+			 * only one char is left (may be a "-"), then stop here,
+			 * reset, & come back for more.
+			 */
+			if ((left <= 1) && skipped) {
+				left = saved_left;
+				break;
+			}
+
+			if (err)
+				break;
+			if (val_a >= bitmap_len || neg) {
+				err = -EINVAL;
+				break;
+			}
+
+			val_b = val_a;
+			if (left) {
+				p++;
+				left--;
+			}
+
+			if (c == '-') {
+				err = proc_get_long(&p, &left, &val_b,
+						     &neg, tr_b, sizeof(tr_b),
+						     &c);
+				/*
+				 * If we consumed all of a truncated buffer or
+				 * then stop here, reset, & come back for more.
+				 */
+				if (!left && skipped) {
+					left = saved_left;
+					break;
+				}
+
+				if (err)
+					break;
+				if (val_b >= bitmap_len || neg ||
+				    val_a > val_b) {
+					err = -EINVAL;
+					break;
+				}
+				if (left) {
+					p++;
+					left--;
+				}
+			}
+
+			bitmap_set(tmp_bitmap, val_a, val_b - val_a + 1);
+			first = 0;
+			proc_skip_char(&p, &left, '\n');
+		}
+		left += skipped;
+	} else {
+		unsigned long bit_a, bit_b = 0;
+
+		while (left) {
+			bit_a = find_next_bit(bitmap, bitmap_len, bit_b);
+			if (bit_a >= bitmap_len)
+				break;
+			bit_b = find_next_zero_bit(bitmap, bitmap_len,
+						   bit_a + 1) - 1;
+
+			if (!first)
+				proc_put_char(&buffer, &left, ',');
+			proc_put_long(&buffer, &left, bit_a, false);
+			if (bit_a != bit_b) {
+				proc_put_char(&buffer, &left, '-');
+				proc_put_long(&buffer, &left, bit_b, false);
+			}
+
+			first = 0; bit_b++;
+		}
+		proc_put_char(&buffer, &left, '\n');
+	}
+
+	if (!err) {
+		if (write) {
+			if (*ppos)
+				bitmap_or(bitmap, bitmap, tmp_bitmap, bitmap_len);
+			else
+				bitmap_copy(bitmap, tmp_bitmap, bitmap_len);
+		}
+		*lenp -= left;
+		*ppos += *lenp;
+	}
+
+	bitmap_free(tmp_bitmap);
+	return err;
+}
+
+#else /* CONFIG_PROC_SYSCTL */
+
+int proc_dostring(struct ctl_table *table, int write,
+		  void *buffer, size_t *lenp, loff_t *ppos)
+{
+	return -ENOSYS;
+}
+
+int proc_dointvec(struct ctl_table *table, int write,
+		  void *buffer, size_t *lenp, loff_t *ppos)
+{
+	return -ENOSYS;
+}
+
+int proc_douintvec(struct ctl_table *table, int write,
+		  void *buffer, size_t *lenp, loff_t *ppos)
+{
+	return -ENOSYS;
+}
+
+int proc_dointvec_minmax(struct ctl_table *table, int write,
+		    void *buffer, size_t *lenp, loff_t *ppos)
+{
+	return -ENOSYS;
+}
+
+int proc_douintvec_minmax(struct ctl_table *table, int write,
+			  void *buffer, size_t *lenp, loff_t *ppos)
+{
+	return -ENOSYS;
+}
+
+int proc_dointvec_jiffies(struct ctl_table *table, int write,
+		    void *buffer, size_t *lenp, loff_t *ppos)
+{
+	return -ENOSYS;
+}
+
+int proc_dointvec_userhz_jiffies(struct ctl_table *table, int write,
+		    void *buffer, size_t *lenp, loff_t *ppos)
+{
+	return -ENOSYS;
+}
+
+int proc_dointvec_ms_jiffies(struct ctl_table *table, int write,
+			     void *buffer, size_t *lenp, loff_t *ppos)
+{
+	return -ENOSYS;
+}
+
+int proc_doulongvec_minmax(struct ctl_table *table, int write,
+		    void *buffer, size_t *lenp, loff_t *ppos)
+{
+	return -ENOSYS;
+}
+
+int proc_doulongvec_ms_jiffies_minmax(struct ctl_table *table, int write,
+				      void *buffer, size_t *lenp, loff_t *ppos)
+{
+	return -ENOSYS;
+}
+
+int proc_do_large_bitmap(struct ctl_table *table, int write,
+			 void *buffer, size_t *lenp, loff_t *ppos)
+{
+	return -ENOSYS;
+}
+
+#endif /* CONFIG_PROC_SYSCTL */
+
+#if defined(CONFIG_SYSCTL)
+int proc_do_static_key(struct ctl_table *table, int write,
+		       void *buffer, size_t *lenp, loff_t *ppos)
+{
+	struct static_key *key = (struct static_key *)table->data;
+	static DEFINE_MUTEX(static_key_mutex);
+	int val, ret;
+	struct ctl_table tmp = {
+		.data   = &val,
+		.maxlen = sizeof(val),
+		.mode   = table->mode,
+		.extra1 = SYSCTL_ZERO,
+		.extra2 = SYSCTL_ONE,
+	};
+
+	if (write && !capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	mutex_lock(&static_key_mutex);
+	val = static_key_enabled(key);
+	ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos);
+	if (write && !ret) {
+		if (val)
+			static_key_enable(key);
+		else
+			static_key_disable(key);
+	}
+	mutex_unlock(&static_key_mutex);
+	return ret;
+}
 
 static struct ctl_table kern_table[] = {
 	{
@@ -444,6 +1780,20 @@ static struct ctl_table kern_table[] = {
 		.proc_handler	= sched_rt_handler,
 	},
 	{
+		.procname	= "sched_deadline_period_max_us",
+		.data		= &sysctl_sched_dl_period_max,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+	{
+		.procname	= "sched_deadline_period_min_us",
+		.data		= &sysctl_sched_dl_period_min,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+	{
 		.procname	= "sched_rr_timeslice_ms",
 		.data		= &sysctl_sched_rr_timeslice,
 		.maxlen		= sizeof(int),
@@ -465,6 +1815,13 @@ static struct ctl_table kern_table[] = {
 		.mode		= 0644,
 		.proc_handler	= sysctl_sched_uclamp_handler,
 	},
+	{
+		.procname	= "sched_util_clamp_min_rt_default",
+		.data		= &sysctl_sched_uclamp_util_min_rt_default,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= sysctl_sched_uclamp_handler,
+	},
 #endif
 #ifdef CONFIG_SCHED_AUTOGROUP
 	{
@@ -625,7 +1982,7 @@ static struct ctl_table kern_table[] = {
 		.procname	= "soft-power",
 		.data		= &pwrsw_enabled,
 		.maxlen		= sizeof (int),
-	 	.mode		= 0644,
+		.mode		= 0644,
 		.proc_handler	= proc_dointvec,
 	},
 #endif
@@ -747,7 +2104,7 @@ static struct ctl_table kern_table[] = {
 #ifdef CONFIG_MAGIC_SYSRQ
 	{
 		.procname	= "sysrq",
-		.data		= &__sysrq_enabled,
+		.data		= NULL,
 		.maxlen		= sizeof (int),
 		.mode		= 0644,
 		.proc_handler	= sysrq_sysctl_handler,
@@ -813,6 +2170,17 @@ static struct ctl_table kern_table[] = {
 		.proc_handler	= proc_dointvec,
 	},
 #endif
+#ifdef CONFIG_SMP
+	{
+		.procname	= "oops_all_cpu_backtrace",
+		.data		= &sysctl_oops_all_cpu_backtrace,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= SYSCTL_ONE,
+	},
+#endif /* CONFIG_SMP */
 	{
 		.procname	= "pid_max",
 		.data		= &pid_max,
@@ -1006,30 +2374,32 @@ static struct ctl_table kern_table[] = {
 		.proc_handler   = proc_dointvec,
 	},
 #endif
-#if defined(CONFIG_X86)
+
+#if (defined(CONFIG_X86_32) || defined(CONFIG_PARISC)) && \
+	defined(CONFIG_DEBUG_STACKOVERFLOW)
 	{
-		.procname	= "panic_on_unrecovered_nmi",
-		.data		= &panic_on_unrecovered_nmi,
+		.procname	= "panic_on_stackoverflow",
+		.data		= &sysctl_panic_on_stackoverflow,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec,
 	},
+#endif
+#if defined(CONFIG_X86)
 	{
-		.procname	= "panic_on_io_nmi",
-		.data		= &panic_on_io_nmi,
+		.procname	= "panic_on_unrecovered_nmi",
+		.data		= &panic_on_unrecovered_nmi,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec,
 	},
-#ifdef CONFIG_DEBUG_STACKOVERFLOW
 	{
-		.procname	= "panic_on_stackoverflow",
-		.data		= &sysctl_panic_on_stackoverflow,
+		.procname	= "panic_on_io_nmi",
+		.data		= &panic_on_io_nmi,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec,
 	},
-#endif
 	{
 		.procname	= "bootloader_type",
 		.data		= &bootloader_type,
@@ -1084,7 +2454,7 @@ static struct ctl_table kern_table[] = {
 		.procname	= "ignore-unaligned-usertrap",
 		.data		= &no_unaligned_warning,
 		.maxlen		= sizeof (int),
-	 	.mode		= 0644,
+		.mode		= 0644,
 		.proc_handler	= proc_dointvec,
 	},
 #endif
@@ -1098,6 +2468,17 @@ static struct ctl_table kern_table[] = {
 	},
 #endif
 #ifdef CONFIG_DETECT_HUNG_TASK
+#ifdef CONFIG_SMP
+	{
+		.procname	= "hung_task_all_cpu_backtrace",
+		.data		= &sysctl_hung_task_all_cpu_backtrace,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= SYSCTL_ONE,
+	},
+#endif /* CONFIG_SMP */
 	{
 		.procname	= "hung_task_panic",
 		.data		= &sysctl_hung_task_panic,
@@ -1256,7 +2637,7 @@ static struct ctl_table kern_table[] = {
 		.data		= &bpf_stats_enabled_key.key,
 		.maxlen		= sizeof(bpf_stats_enabled_key),
 		.mode		= 0644,
-		.proc_handler	= proc_do_static_key,
+		.proc_handler	= bpf_stats_handler,
 	},
 #endif
 #if defined(CONFIG_TREE_RCU)
@@ -1290,7 +2671,7 @@ static struct ctl_table vm_table[] = {
 		.data		= &sysctl_overcommit_memory,
 		.maxlen		= sizeof(sysctl_overcommit_memory),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec_minmax,
+		.proc_handler	= overcommit_policy_handler,
 		.extra1		= SYSCTL_ZERO,
 		.extra2		= &two,
 	},
@@ -1332,7 +2713,7 @@ static struct ctl_table vm_table[] = {
 		.proc_handler	= overcommit_kbytes_handler,
 	},
 	{
-		.procname	= "page-cluster", 
+		.procname	= "page-cluster",
 		.data		= &page_cluster,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
@@ -1403,7 +2784,7 @@ static struct ctl_table vm_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
 		.extra1		= SYSCTL_ZERO,
-		.extra2		= &one_hundred,
+		.extra2		= &two_hundred,
 	},
 #ifdef CONFIG_HUGETLB_PAGE
 	{
@@ -1471,6 +2852,15 @@ static struct ctl_table vm_table[] = {
 		.proc_handler	= sysctl_compaction_handler,
 	},
 	{
+		.procname	= "compaction_proactiveness",
+		.data		= &sysctl_compaction_proactiveness,
+		.maxlen		= sizeof(sysctl_compaction_proactiveness),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= &one_hundred,
+	},
+	{
 		.procname	= "extfrag_threshold",
 		.data		= &sysctl_extfrag_threshold,
 		.maxlen		= sizeof(int),
@@ -1484,7 +2874,7 @@ static struct ctl_table vm_table[] = {
 		.data		= &sysctl_compact_unevictable_allowed,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
+		.proc_handler	= proc_dointvec_minmax_warn_RT_change,
 		.extra1		= SYSCTL_ZERO,
 		.extra2		= SYSCTL_ONE,
 	},
@@ -1503,7 +2893,7 @@ static struct ctl_table vm_table[] = {
 		.data		= &watermark_boost_factor,
 		.maxlen		= sizeof(watermark_boost_factor),
 		.mode		= 0644,
-		.proc_handler	= watermark_boost_factor_sysctl_handler,
+		.proc_handler	= proc_dointvec_minmax,
 		.extra1		= SYSCTL_ZERO,
 	},
 	{
@@ -1971,6 +3361,35 @@ static struct ctl_table dev_table[] = {
 	{ }
 };
 
+static struct ctl_table sysctl_base_table[] = {
+	{
+		.procname	= "kernel",
+		.mode		= 0555,
+		.child		= kern_table,
+	},
+	{
+		.procname	= "vm",
+		.mode		= 0555,
+		.child		= vm_table,
+	},
+	{
+		.procname	= "fs",
+		.mode		= 0555,
+		.child		= fs_table,
+	},
+	{
+		.procname	= "debug",
+		.mode		= 0555,
+		.child		= debug_table,
+	},
+	{
+		.procname	= "dev",
+		.mode		= 0555,
+		.child		= dev_table,
+	},
+	{ }
+};
+
 int __init sysctl_init(void)
 {
 	struct ctl_table_header *hdr;
@@ -1979,1432 +3398,7 @@ int __init sysctl_init(void)
 	kmemleak_not_leak(hdr);
 	return 0;
 }
-
 #endif /* CONFIG_SYSCTL */
-
-/*
- * /proc/sys support
- */
-
-#ifdef CONFIG_PROC_SYSCTL
-
-static int _proc_do_string(char *data, int maxlen, int write,
-			   char __user *buffer,
-			   size_t *lenp, loff_t *ppos)
-{
-	size_t len;
-	char __user *p;
-	char c;
-
-	if (!data || !maxlen || !*lenp) {
-		*lenp = 0;
-		return 0;
-	}
-
-	if (write) {
-		if (sysctl_writes_strict == SYSCTL_WRITES_STRICT) {
-			/* Only continue writes not past the end of buffer. */
-			len = strlen(data);
-			if (len > maxlen - 1)
-				len = maxlen - 1;
-
-			if (*ppos > len)
-				return 0;
-			len = *ppos;
-		} else {
-			/* Start writing from beginning of buffer. */
-			len = 0;
-		}
-
-		*ppos += *lenp;
-		p = buffer;
-		while ((p - buffer) < *lenp && len < maxlen - 1) {
-			if (get_user(c, p++))
-				return -EFAULT;
-			if (c == 0 || c == '\n')
-				break;
-			data[len++] = c;
-		}
-		data[len] = 0;
-	} else {
-		len = strlen(data);
-		if (len > maxlen)
-			len = maxlen;
-
-		if (*ppos > len) {
-			*lenp = 0;
-			return 0;
-		}
-
-		data += *ppos;
-		len  -= *ppos;
-
-		if (len > *lenp)
-			len = *lenp;
-		if (len)
-			if (copy_to_user(buffer, data, len))
-				return -EFAULT;
-		if (len < *lenp) {
-			if (put_user('\n', buffer + len))
-				return -EFAULT;
-			len++;
-		}
-		*lenp = len;
-		*ppos += len;
-	}
-	return 0;
-}
-
-static void warn_sysctl_write(struct ctl_table *table)
-{
-	pr_warn_once("%s wrote to %s when file position was not 0!\n"
-		"This will not be supported in the future. To silence this\n"
-		"warning, set kernel.sysctl_writes_strict = -1\n",
-		current->comm, table->procname);
-}
-
-/**
- * proc_first_pos_non_zero_ignore - check if first position is allowed
- * @ppos: file position
- * @table: the sysctl table
- *
- * Returns true if the first position is non-zero and the sysctl_writes_strict
- * mode indicates this is not allowed for numeric input types. String proc
- * handlers can ignore the return value.
- */
-static bool proc_first_pos_non_zero_ignore(loff_t *ppos,
-					   struct ctl_table *table)
-{
-	if (!*ppos)
-		return false;
-
-	switch (sysctl_writes_strict) {
-	case SYSCTL_WRITES_STRICT:
-		return true;
-	case SYSCTL_WRITES_WARN:
-		warn_sysctl_write(table);
-		return false;
-	default:
-		return false;
-	}
-}
-
-/**
- * proc_dostring - read a string sysctl
- * @table: the sysctl table
- * @write: %TRUE if this is a write to the sysctl file
- * @buffer: the user buffer
- * @lenp: the size of the user buffer
- * @ppos: file position
- *
- * Reads/writes a string from/to the user buffer. If the kernel
- * buffer provided is not large enough to hold the string, the
- * string is truncated. The copied string is %NULL-terminated.
- * If the string is being read by the user process, it is copied
- * and a newline '\n' is added. It is truncated if the buffer is
- * not large enough.
- *
- * Returns 0 on success.
- */
-int proc_dostring(struct ctl_table *table, int write,
-		  void __user *buffer, size_t *lenp, loff_t *ppos)
-{
-	if (write)
-		proc_first_pos_non_zero_ignore(ppos, table);
-
-	return _proc_do_string((char *)(table->data), table->maxlen, write,
-			       (char __user *)buffer, lenp, ppos);
-}
-
-static size_t proc_skip_spaces(char **buf)
-{
-	size_t ret;
-	char *tmp = skip_spaces(*buf);
-	ret = tmp - *buf;
-	*buf = tmp;
-	return ret;
-}
-
-static void proc_skip_char(char **buf, size_t *size, const char v)
-{
-	while (*size) {
-		if (**buf != v)
-			break;
-		(*size)--;
-		(*buf)++;
-	}
-}
-
-/**
- * strtoul_lenient - parse an ASCII formatted integer from a buffer and only
- *                   fail on overflow
- *
- * @cp: kernel buffer containing the string to parse
- * @endp: pointer to store the trailing characters
- * @base: the base to use
- * @res: where the parsed integer will be stored
- *
- * In case of success 0 is returned and @res will contain the parsed integer,
- * @endp will hold any trailing characters.
- * This function will fail the parse on overflow. If there wasn't an overflow
- * the function will defer the decision what characters count as invalid to the
- * caller.
- */
-static int strtoul_lenient(const char *cp, char **endp, unsigned int base,
-			   unsigned long *res)
-{
-	unsigned long long result;
-	unsigned int rv;
-
-	cp = _parse_integer_fixup_radix(cp, &base);
-	rv = _parse_integer(cp, base, &result);
-	if ((rv & KSTRTOX_OVERFLOW) || (result != (unsigned long)result))
-		return -ERANGE;
-
-	cp += rv;
-
-	if (endp)
-		*endp = (char *)cp;
-
-	*res = (unsigned long)result;
-	return 0;
-}
-
-#define TMPBUFLEN 22
-/**
- * proc_get_long - reads an ASCII formatted integer from a user buffer
- *
- * @buf: a kernel buffer
- * @size: size of the kernel buffer
- * @val: this is where the number will be stored
- * @neg: set to %TRUE if number is negative
- * @perm_tr: a vector which contains the allowed trailers
- * @perm_tr_len: size of the perm_tr vector
- * @tr: pointer to store the trailer character
- *
- * In case of success %0 is returned and @buf and @size are updated with
- * the amount of bytes read. If @tr is non-NULL and a trailing
- * character exists (size is non-zero after returning from this
- * function), @tr is updated with the trailing character.
- */
-static int proc_get_long(char **buf, size_t *size,
-			  unsigned long *val, bool *neg,
-			  const char *perm_tr, unsigned perm_tr_len, char *tr)
-{
-	int len;
-	char *p, tmp[TMPBUFLEN];
-
-	if (!*size)
-		return -EINVAL;
-
-	len = *size;
-	if (len > TMPBUFLEN - 1)
-		len = TMPBUFLEN - 1;
-
-	memcpy(tmp, *buf, len);
-
-	tmp[len] = 0;
-	p = tmp;
-	if (*p == '-' && *size > 1) {
-		*neg = true;
-		p++;
-	} else
-		*neg = false;
-	if (!isdigit(*p))
-		return -EINVAL;
-
-	if (strtoul_lenient(p, &p, 0, val))
-		return -EINVAL;
-
-	len = p - tmp;
-
-	/* We don't know if the next char is whitespace thus we may accept
-	 * invalid integers (e.g. 1234...a) or two integers instead of one
-	 * (e.g. 123...1). So lets not allow such large numbers. */
-	if (len == TMPBUFLEN - 1)
-		return -EINVAL;
-
-	if (len < *size && perm_tr_len && !memchr(perm_tr, *p, perm_tr_len))
-		return -EINVAL;
-
-	if (tr && (len < *size))
-		*tr = *p;
-
-	*buf += len;
-	*size -= len;
-
-	return 0;
-}
-
-/**
- * proc_put_long - converts an integer to a decimal ASCII formatted string
- *
- * @buf: the user buffer
- * @size: the size of the user buffer
- * @val: the integer to be converted
- * @neg: sign of the number, %TRUE for negative
- *
- * In case of success %0 is returned and @buf and @size are updated with
- * the amount of bytes written.
- */
-static int proc_put_long(void __user **buf, size_t *size, unsigned long val,
-			  bool neg)
-{
-	int len;
-	char tmp[TMPBUFLEN], *p = tmp;
-
-	sprintf(p, "%s%lu", neg ? "-" : "", val);
-	len = strlen(tmp);
-	if (len > *size)
-		len = *size;
-	if (copy_to_user(*buf, tmp, len))
-		return -EFAULT;
-	*size -= len;
-	*buf += len;
-	return 0;
-}
-#undef TMPBUFLEN
-
-static int proc_put_char(void __user **buf, size_t *size, char c)
-{
-	if (*size) {
-		char __user **buffer = (char __user **)buf;
-		if (put_user(c, *buffer))
-			return -EFAULT;
-		(*size)--, (*buffer)++;
-		*buf = *buffer;
-	}
-	return 0;
-}
-
-static int do_proc_dointvec_conv(bool *negp, unsigned long *lvalp,
-				 int *valp,
-				 int write, void *data)
-{
-	if (write) {
-		if (*negp) {
-			if (*lvalp > (unsigned long) INT_MAX + 1)
-				return -EINVAL;
-			*valp = -*lvalp;
-		} else {
-			if (*lvalp > (unsigned long) INT_MAX)
-				return -EINVAL;
-			*valp = *lvalp;
-		}
-	} else {
-		int val = *valp;
-		if (val < 0) {
-			*negp = true;
-			*lvalp = -(unsigned long)val;
-		} else {
-			*negp = false;
-			*lvalp = (unsigned long)val;
-		}
-	}
-	return 0;
-}
-
-static int do_proc_douintvec_conv(unsigned long *lvalp,
-				  unsigned int *valp,
-				  int write, void *data)
-{
-	if (write) {
-		if (*lvalp > UINT_MAX)
-			return -EINVAL;
-		*valp = *lvalp;
-	} else {
-		unsigned int val = *valp;
-		*lvalp = (unsigned long)val;
-	}
-	return 0;
-}
-
-static const char proc_wspace_sep[] = { ' ', '\t', '\n' };
-
-static int __do_proc_dointvec(void *tbl_data, struct ctl_table *table,
-		  int write, void __user *buffer,
-		  size_t *lenp, loff_t *ppos,
-		  int (*conv)(bool *negp, unsigned long *lvalp, int *valp,
-			      int write, void *data),
-		  void *data)
-{
-	int *i, vleft, first = 1, err = 0;
-	size_t left;
-	char *kbuf = NULL, *p;
-	
-	if (!tbl_data || !table->maxlen || !*lenp || (*ppos && !write)) {
-		*lenp = 0;
-		return 0;
-	}
-	
-	i = (int *) tbl_data;
-	vleft = table->maxlen / sizeof(*i);
-	left = *lenp;
-
-	if (!conv)
-		conv = do_proc_dointvec_conv;
-
-	if (write) {
-		if (proc_first_pos_non_zero_ignore(ppos, table))
-			goto out;
-
-		if (left > PAGE_SIZE - 1)
-			left = PAGE_SIZE - 1;
-		p = kbuf = memdup_user_nul(buffer, left);
-		if (IS_ERR(kbuf))
-			return PTR_ERR(kbuf);
-	}
-
-	for (; left && vleft--; i++, first=0) {
-		unsigned long lval;
-		bool neg;
-
-		if (write) {
-			left -= proc_skip_spaces(&p);
-
-			if (!left)
-				break;
-			err = proc_get_long(&p, &left, &lval, &neg,
-					     proc_wspace_sep,
-					     sizeof(proc_wspace_sep), NULL);
-			if (err)
-				break;
-			if (conv(&neg, &lval, i, 1, data)) {
-				err = -EINVAL;
-				break;
-			}
-		} else {
-			if (conv(&neg, &lval, i, 0, data)) {
-				err = -EINVAL;
-				break;
-			}
-			if (!first)
-				err = proc_put_char(&buffer, &left, '\t');
-			if (err)
-				break;
-			err = proc_put_long(&buffer, &left, lval, neg);
-			if (err)
-				break;
-		}
-	}
-
-	if (!write && !first && left && !err)
-		err = proc_put_char(&buffer, &left, '\n');
-	if (write && !err && left)
-		left -= proc_skip_spaces(&p);
-	if (write) {
-		kfree(kbuf);
-		if (first)
-			return err ? : -EINVAL;
-	}
-	*lenp -= left;
-out:
-	*ppos += *lenp;
-	return err;
-}
-
-static int do_proc_dointvec(struct ctl_table *table, int write,
-		  void __user *buffer, size_t *lenp, loff_t *ppos,
-		  int (*conv)(bool *negp, unsigned long *lvalp, int *valp,
-			      int write, void *data),
-		  void *data)
-{
-	return __do_proc_dointvec(table->data, table, write,
-			buffer, lenp, ppos, conv, data);
-}
-
-static int do_proc_douintvec_w(unsigned int *tbl_data,
-			       struct ctl_table *table,
-			       void __user *buffer,
-			       size_t *lenp, loff_t *ppos,
-			       int (*conv)(unsigned long *lvalp,
-					   unsigned int *valp,
-					   int write, void *data),
-			       void *data)
-{
-	unsigned long lval;
-	int err = 0;
-	size_t left;
-	bool neg;
-	char *kbuf = NULL, *p;
-
-	left = *lenp;
-
-	if (proc_first_pos_non_zero_ignore(ppos, table))
-		goto bail_early;
-
-	if (left > PAGE_SIZE - 1)
-		left = PAGE_SIZE - 1;
-
-	p = kbuf = memdup_user_nul(buffer, left);
-	if (IS_ERR(kbuf))
-		return -EINVAL;
-
-	left -= proc_skip_spaces(&p);
-	if (!left) {
-		err = -EINVAL;
-		goto out_free;
-	}
-
-	err = proc_get_long(&p, &left, &lval, &neg,
-			     proc_wspace_sep,
-			     sizeof(proc_wspace_sep), NULL);
-	if (err || neg) {
-		err = -EINVAL;
-		goto out_free;
-	}
-
-	if (conv(&lval, tbl_data, 1, data)) {
-		err = -EINVAL;
-		goto out_free;
-	}
-
-	if (!err && left)
-		left -= proc_skip_spaces(&p);
-
-out_free:
-	kfree(kbuf);
-	if (err)
-		return -EINVAL;
-
-	return 0;
-
-	/* This is in keeping with old __do_proc_dointvec() */
-bail_early:
-	*ppos += *lenp;
-	return err;
-}
-
-static int do_proc_douintvec_r(unsigned int *tbl_data, void __user *buffer,
-			       size_t *lenp, loff_t *ppos,
-			       int (*conv)(unsigned long *lvalp,
-					   unsigned int *valp,
-					   int write, void *data),
-			       void *data)
-{
-	unsigned long lval;
-	int err = 0;
-	size_t left;
-
-	left = *lenp;
-
-	if (conv(&lval, tbl_data, 0, data)) {
-		err = -EINVAL;
-		goto out;
-	}
-
-	err = proc_put_long(&buffer, &left, lval, false);
-	if (err || !left)
-		goto out;
-
-	err = proc_put_char(&buffer, &left, '\n');
-
-out:
-	*lenp -= left;
-	*ppos += *lenp;
-
-	return err;
-}
-
-static int __do_proc_douintvec(void *tbl_data, struct ctl_table *table,
-			       int write, void __user *buffer,
-			       size_t *lenp, loff_t *ppos,
-			       int (*conv)(unsigned long *lvalp,
-					   unsigned int *valp,
-					   int write, void *data),
-			       void *data)
-{
-	unsigned int *i, vleft;
-
-	if (!tbl_data || !table->maxlen || !*lenp || (*ppos && !write)) {
-		*lenp = 0;
-		return 0;
-	}
-
-	i = (unsigned int *) tbl_data;
-	vleft = table->maxlen / sizeof(*i);
-
-	/*
-	 * Arrays are not supported, keep this simple. *Do not* add
-	 * support for them.
-	 */
-	if (vleft != 1) {
-		*lenp = 0;
-		return -EINVAL;
-	}
-
-	if (!conv)
-		conv = do_proc_douintvec_conv;
-
-	if (write)
-		return do_proc_douintvec_w(i, table, buffer, lenp, ppos,
-					   conv, data);
-	return do_proc_douintvec_r(i, buffer, lenp, ppos, conv, data);
-}
-
-static int do_proc_douintvec(struct ctl_table *table, int write,
-			     void __user *buffer, size_t *lenp, loff_t *ppos,
-			     int (*conv)(unsigned long *lvalp,
-					 unsigned int *valp,
-					 int write, void *data),
-			     void *data)
-{
-	return __do_proc_douintvec(table->data, table, write,
-				   buffer, lenp, ppos, conv, data);
-}
-
-/**
- * proc_dointvec - read a vector of integers
- * @table: the sysctl table
- * @write: %TRUE if this is a write to the sysctl file
- * @buffer: the user buffer
- * @lenp: the size of the user buffer
- * @ppos: file position
- *
- * Reads/writes up to table->maxlen/sizeof(unsigned int) integer
- * values from/to the user buffer, treated as an ASCII string. 
- *
- * Returns 0 on success.
- */
-int proc_dointvec(struct ctl_table *table, int write,
-		     void __user *buffer, size_t *lenp, loff_t *ppos)
-{
-	return do_proc_dointvec(table, write, buffer, lenp, ppos, NULL, NULL);
-}
-
-/**
- * proc_douintvec - read a vector of unsigned integers
- * @table: the sysctl table
- * @write: %TRUE if this is a write to the sysctl file
- * @buffer: the user buffer
- * @lenp: the size of the user buffer
- * @ppos: file position
- *
- * Reads/writes up to table->maxlen/sizeof(unsigned int) unsigned integer
- * values from/to the user buffer, treated as an ASCII string.
- *
- * Returns 0 on success.
- */
-int proc_douintvec(struct ctl_table *table, int write,
-		     void __user *buffer, size_t *lenp, loff_t *ppos)
-{
-	return do_proc_douintvec(table, write, buffer, lenp, ppos,
-				 do_proc_douintvec_conv, NULL);
-}
-
-/*
- * Taint values can only be increased
- * This means we can safely use a temporary.
- */
-static int proc_taint(struct ctl_table *table, int write,
-			       void __user *buffer, size_t *lenp, loff_t *ppos)
-{
-	struct ctl_table t;
-	unsigned long tmptaint = get_taint();
-	int err;
-
-	if (write && !capable(CAP_SYS_ADMIN))
-		return -EPERM;
-
-	t = *table;
-	t.data = &tmptaint;
-	err = proc_doulongvec_minmax(&t, write, buffer, lenp, ppos);
-	if (err < 0)
-		return err;
-
-	if (write) {
-		/*
-		 * Poor man's atomic or. Not worth adding a primitive
-		 * to everyone's atomic.h for this
-		 */
-		int i;
-		for (i = 0; i < BITS_PER_LONG && tmptaint >> i; i++) {
-			if ((tmptaint >> i) & 1)
-				add_taint(i, LOCKDEP_STILL_OK);
-		}
-	}
-
-	return err;
-}
-
-#ifdef CONFIG_PRINTK
-static int proc_dointvec_minmax_sysadmin(struct ctl_table *table, int write,
-				void __user *buffer, size_t *lenp, loff_t *ppos)
-{
-	if (write && !capable(CAP_SYS_ADMIN))
-		return -EPERM;
-
-	return proc_dointvec_minmax(table, write, buffer, lenp, ppos);
-}
-#endif
-
-/**
- * struct do_proc_dointvec_minmax_conv_param - proc_dointvec_minmax() range checking structure
- * @min: pointer to minimum allowable value
- * @max: pointer to maximum allowable value
- *
- * The do_proc_dointvec_minmax_conv_param structure provides the
- * minimum and maximum values for doing range checking for those sysctl
- * parameters that use the proc_dointvec_minmax() handler.
- */
-struct do_proc_dointvec_minmax_conv_param {
-	int *min;
-	int *max;
-};
-
-static int do_proc_dointvec_minmax_conv(bool *negp, unsigned long *lvalp,
-					int *valp,
-					int write, void *data)
-{
-	int tmp, ret;
-	struct do_proc_dointvec_minmax_conv_param *param = data;
-	/*
-	 * If writing, first do so via a temporary local int so we can
-	 * bounds-check it before touching *valp.
-	 */
-	int *ip = write ? &tmp : valp;
-
-	ret = do_proc_dointvec_conv(negp, lvalp, ip, write, data);
-	if (ret)
-		return ret;
-
-	if (write) {
-		if ((param->min && *param->min > tmp) ||
-		    (param->max && *param->max < tmp))
-			return -EINVAL;
-		*valp = tmp;
-	}
-
-	return 0;
-}
-
-/**
- * proc_dointvec_minmax - read a vector of integers with min/max values
- * @table: the sysctl table
- * @write: %TRUE if this is a write to the sysctl file
- * @buffer: the user buffer
- * @lenp: the size of the user buffer
- * @ppos: file position
- *
- * Reads/writes up to table->maxlen/sizeof(unsigned int) integer
- * values from/to the user buffer, treated as an ASCII string.
- *
- * This routine will ensure the values are within the range specified by
- * table->extra1 (min) and table->extra2 (max).
- *
- * Returns 0 on success or -EINVAL on write when the range check fails.
- */
-int proc_dointvec_minmax(struct ctl_table *table, int write,
-		  void __user *buffer, size_t *lenp, loff_t *ppos)
-{
-	struct do_proc_dointvec_minmax_conv_param param = {
-		.min = (int *) table->extra1,
-		.max = (int *) table->extra2,
-	};
-	return do_proc_dointvec(table, write, buffer, lenp, ppos,
-				do_proc_dointvec_minmax_conv, &param);
-}
-
-/**
- * struct do_proc_douintvec_minmax_conv_param - proc_douintvec_minmax() range checking structure
- * @min: pointer to minimum allowable value
- * @max: pointer to maximum allowable value
- *
- * The do_proc_douintvec_minmax_conv_param structure provides the
- * minimum and maximum values for doing range checking for those sysctl
- * parameters that use the proc_douintvec_minmax() handler.
- */
-struct do_proc_douintvec_minmax_conv_param {
-	unsigned int *min;
-	unsigned int *max;
-};
-
-static int do_proc_douintvec_minmax_conv(unsigned long *lvalp,
-					 unsigned int *valp,
-					 int write, void *data)
-{
-	int ret;
-	unsigned int tmp;
-	struct do_proc_douintvec_minmax_conv_param *param = data;
-	/* write via temporary local uint for bounds-checking */
-	unsigned int *up = write ? &tmp : valp;
-
-	ret = do_proc_douintvec_conv(lvalp, up, write, data);
-	if (ret)
-		return ret;
-
-	if (write) {
-		if ((param->min && *param->min > tmp) ||
-		    (param->max && *param->max < tmp))
-			return -ERANGE;
-
-		*valp = tmp;
-	}
-
-	return 0;
-}
-
-/**
- * proc_douintvec_minmax - read a vector of unsigned ints with min/max values
- * @table: the sysctl table
- * @write: %TRUE if this is a write to the sysctl file
- * @buffer: the user buffer
- * @lenp: the size of the user buffer
- * @ppos: file position
- *
- * Reads/writes up to table->maxlen/sizeof(unsigned int) unsigned integer
- * values from/to the user buffer, treated as an ASCII string. Negative
- * strings are not allowed.
- *
- * This routine will ensure the values are within the range specified by
- * table->extra1 (min) and table->extra2 (max). There is a final sanity
- * check for UINT_MAX to avoid having to support wrap around uses from
- * userspace.
- *
- * Returns 0 on success or -ERANGE on write when the range check fails.
- */
-int proc_douintvec_minmax(struct ctl_table *table, int write,
-			  void __user *buffer, size_t *lenp, loff_t *ppos)
-{
-	struct do_proc_douintvec_minmax_conv_param param = {
-		.min = (unsigned int *) table->extra1,
-		.max = (unsigned int *) table->extra2,
-	};
-	return do_proc_douintvec(table, write, buffer, lenp, ppos,
-				 do_proc_douintvec_minmax_conv, &param);
-}
-
-static int do_proc_dopipe_max_size_conv(unsigned long *lvalp,
-					unsigned int *valp,
-					int write, void *data)
-{
-	if (write) {
-		unsigned int val;
-
-		val = round_pipe_size(*lvalp);
-		if (val == 0)
-			return -EINVAL;
-
-		*valp = val;
-	} else {
-		unsigned int val = *valp;
-		*lvalp = (unsigned long) val;
-	}
-
-	return 0;
-}
-
-static int proc_dopipe_max_size(struct ctl_table *table, int write,
-				void __user *buffer, size_t *lenp, loff_t *ppos)
-{
-	return do_proc_douintvec(table, write, buffer, lenp, ppos,
-				 do_proc_dopipe_max_size_conv, NULL);
-}
-
-static void validate_coredump_safety(void)
-{
-#ifdef CONFIG_COREDUMP
-	if (suid_dumpable == SUID_DUMP_ROOT &&
-	    core_pattern[0] != '/' && core_pattern[0] != '|') {
-		printk(KERN_WARNING
-"Unsafe core_pattern used with fs.suid_dumpable=2.\n"
-"Pipe handler or fully qualified core dump path required.\n"
-"Set kernel.core_pattern before fs.suid_dumpable.\n"
-		);
-	}
-#endif
-}
-
-static int proc_dointvec_minmax_coredump(struct ctl_table *table, int write,
-		void __user *buffer, size_t *lenp, loff_t *ppos)
-{
-	int error = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
-	if (!error)
-		validate_coredump_safety();
-	return error;
-}
-
-#ifdef CONFIG_COREDUMP
-static int proc_dostring_coredump(struct ctl_table *table, int write,
-		  void __user *buffer, size_t *lenp, loff_t *ppos)
-{
-	int error = proc_dostring(table, write, buffer, lenp, ppos);
-	if (!error)
-		validate_coredump_safety();
-	return error;
-}
-#endif
-
-static int __do_proc_doulongvec_minmax(void *data, struct ctl_table *table, int write,
-				     void __user *buffer,
-				     size_t *lenp, loff_t *ppos,
-				     unsigned long convmul,
-				     unsigned long convdiv)
-{
-	unsigned long *i, *min, *max;
-	int vleft, first = 1, err = 0;
-	size_t left;
-	char *kbuf = NULL, *p;
-
-	if (!data || !table->maxlen || !*lenp || (*ppos && !write)) {
-		*lenp = 0;
-		return 0;
-	}
-
-	i = (unsigned long *) data;
-	min = (unsigned long *) table->extra1;
-	max = (unsigned long *) table->extra2;
-	vleft = table->maxlen / sizeof(unsigned long);
-	left = *lenp;
-
-	if (write) {
-		if (proc_first_pos_non_zero_ignore(ppos, table))
-			goto out;
-
-		if (left > PAGE_SIZE - 1)
-			left = PAGE_SIZE - 1;
-		p = kbuf = memdup_user_nul(buffer, left);
-		if (IS_ERR(kbuf))
-			return PTR_ERR(kbuf);
-	}
-
-	for (; left && vleft--; i++, first = 0) {
-		unsigned long val;
-
-		if (write) {
-			bool neg;
-
-			left -= proc_skip_spaces(&p);
-			if (!left)
-				break;
-
-			err = proc_get_long(&p, &left, &val, &neg,
-					     proc_wspace_sep,
-					     sizeof(proc_wspace_sep), NULL);
-			if (err)
-				break;
-			if (neg)
-				continue;
-			val = convmul * val / convdiv;
-			if ((min && val < *min) || (max && val > *max)) {
-				err = -EINVAL;
-				break;
-			}
-			*i = val;
-		} else {
-			val = convdiv * (*i) / convmul;
-			if (!first) {
-				err = proc_put_char(&buffer, &left, '\t');
-				if (err)
-					break;
-			}
-			err = proc_put_long(&buffer, &left, val, false);
-			if (err)
-				break;
-		}
-	}
-
-	if (!write && !first && left && !err)
-		err = proc_put_char(&buffer, &left, '\n');
-	if (write && !err)
-		left -= proc_skip_spaces(&p);
-	if (write) {
-		kfree(kbuf);
-		if (first)
-			return err ? : -EINVAL;
-	}
-	*lenp -= left;
-out:
-	*ppos += *lenp;
-	return err;
-}
-
-static int do_proc_doulongvec_minmax(struct ctl_table *table, int write,
-				     void __user *buffer,
-				     size_t *lenp, loff_t *ppos,
-				     unsigned long convmul,
-				     unsigned long convdiv)
-{
-	return __do_proc_doulongvec_minmax(table->data, table, write,
-			buffer, lenp, ppos, convmul, convdiv);
-}
-
-/**
- * proc_doulongvec_minmax - read a vector of long integers with min/max values
- * @table: the sysctl table
- * @write: %TRUE if this is a write to the sysctl file
- * @buffer: the user buffer
- * @lenp: the size of the user buffer
- * @ppos: file position
- *
- * Reads/writes up to table->maxlen/sizeof(unsigned long) unsigned long
- * values from/to the user buffer, treated as an ASCII string.
- *
- * This routine will ensure the values are within the range specified by
- * table->extra1 (min) and table->extra2 (max).
- *
- * Returns 0 on success.
- */
-int proc_doulongvec_minmax(struct ctl_table *table, int write,
-			   void __user *buffer, size_t *lenp, loff_t *ppos)
-{
-    return do_proc_doulongvec_minmax(table, write, buffer, lenp, ppos, 1l, 1l);
-}
-
-/**
- * proc_doulongvec_ms_jiffies_minmax - read a vector of millisecond values with min/max values
- * @table: the sysctl table
- * @write: %TRUE if this is a write to the sysctl file
- * @buffer: the user buffer
- * @lenp: the size of the user buffer
- * @ppos: file position
- *
- * Reads/writes up to table->maxlen/sizeof(unsigned long) unsigned long
- * values from/to the user buffer, treated as an ASCII string. The values
- * are treated as milliseconds, and converted to jiffies when they are stored.
- *
- * This routine will ensure the values are within the range specified by
- * table->extra1 (min) and table->extra2 (max).
- *
- * Returns 0 on success.
- */
-int proc_doulongvec_ms_jiffies_minmax(struct ctl_table *table, int write,
-				      void __user *buffer,
-				      size_t *lenp, loff_t *ppos)
-{
-    return do_proc_doulongvec_minmax(table, write, buffer,
-				     lenp, ppos, HZ, 1000l);
-}
-
-
-static int do_proc_dointvec_jiffies_conv(bool *negp, unsigned long *lvalp,
-					 int *valp,
-					 int write, void *data)
-{
-	if (write) {
-		if (*lvalp > INT_MAX / HZ)
-			return 1;
-		*valp = *negp ? -(*lvalp*HZ) : (*lvalp*HZ);
-	} else {
-		int val = *valp;
-		unsigned long lval;
-		if (val < 0) {
-			*negp = true;
-			lval = -(unsigned long)val;
-		} else {
-			*negp = false;
-			lval = (unsigned long)val;
-		}
-		*lvalp = lval / HZ;
-	}
-	return 0;
-}
-
-static int do_proc_dointvec_userhz_jiffies_conv(bool *negp, unsigned long *lvalp,
-						int *valp,
-						int write, void *data)
-{
-	if (write) {
-		if (USER_HZ < HZ && *lvalp > (LONG_MAX / HZ) * USER_HZ)
-			return 1;
-		*valp = clock_t_to_jiffies(*negp ? -*lvalp : *lvalp);
-	} else {
-		int val = *valp;
-		unsigned long lval;
-		if (val < 0) {
-			*negp = true;
-			lval = -(unsigned long)val;
-		} else {
-			*negp = false;
-			lval = (unsigned long)val;
-		}
-		*lvalp = jiffies_to_clock_t(lval);
-	}
-	return 0;
-}
-
-static int do_proc_dointvec_ms_jiffies_conv(bool *negp, unsigned long *lvalp,
-					    int *valp,
-					    int write, void *data)
-{
-	if (write) {
-		unsigned long jif = msecs_to_jiffies(*negp ? -*lvalp : *lvalp);
-
-		if (jif > INT_MAX)
-			return 1;
-		*valp = (int)jif;
-	} else {
-		int val = *valp;
-		unsigned long lval;
-		if (val < 0) {
-			*negp = true;
-			lval = -(unsigned long)val;
-		} else {
-			*negp = false;
-			lval = (unsigned long)val;
-		}
-		*lvalp = jiffies_to_msecs(lval);
-	}
-	return 0;
-}
-
-/**
- * proc_dointvec_jiffies - read a vector of integers as seconds
- * @table: the sysctl table
- * @write: %TRUE if this is a write to the sysctl file
- * @buffer: the user buffer
- * @lenp: the size of the user buffer
- * @ppos: file position
- *
- * Reads/writes up to table->maxlen/sizeof(unsigned int) integer
- * values from/to the user buffer, treated as an ASCII string. 
- * The values read are assumed to be in seconds, and are converted into
- * jiffies.
- *
- * Returns 0 on success.
- */
-int proc_dointvec_jiffies(struct ctl_table *table, int write,
-			  void __user *buffer, size_t *lenp, loff_t *ppos)
-{
-    return do_proc_dointvec(table,write,buffer,lenp,ppos,
-		    	    do_proc_dointvec_jiffies_conv,NULL);
-}
-
-/**
- * proc_dointvec_userhz_jiffies - read a vector of integers as 1/USER_HZ seconds
- * @table: the sysctl table
- * @write: %TRUE if this is a write to the sysctl file
- * @buffer: the user buffer
- * @lenp: the size of the user buffer
- * @ppos: pointer to the file position
- *
- * Reads/writes up to table->maxlen/sizeof(unsigned int) integer
- * values from/to the user buffer, treated as an ASCII string. 
- * The values read are assumed to be in 1/USER_HZ seconds, and 
- * are converted into jiffies.
- *
- * Returns 0 on success.
- */
-int proc_dointvec_userhz_jiffies(struct ctl_table *table, int write,
-				 void __user *buffer, size_t *lenp, loff_t *ppos)
-{
-    return do_proc_dointvec(table,write,buffer,lenp,ppos,
-		    	    do_proc_dointvec_userhz_jiffies_conv,NULL);
-}
-
-/**
- * proc_dointvec_ms_jiffies - read a vector of integers as 1 milliseconds
- * @table: the sysctl table
- * @write: %TRUE if this is a write to the sysctl file
- * @buffer: the user buffer
- * @lenp: the size of the user buffer
- * @ppos: file position
- * @ppos: the current position in the file
- *
- * Reads/writes up to table->maxlen/sizeof(unsigned int) integer
- * values from/to the user buffer, treated as an ASCII string. 
- * The values read are assumed to be in 1/1000 seconds, and 
- * are converted into jiffies.
- *
- * Returns 0 on success.
- */
-int proc_dointvec_ms_jiffies(struct ctl_table *table, int write,
-			     void __user *buffer, size_t *lenp, loff_t *ppos)
-{
-	return do_proc_dointvec(table, write, buffer, lenp, ppos,
-				do_proc_dointvec_ms_jiffies_conv, NULL);
-}
-
-static int proc_do_cad_pid(struct ctl_table *table, int write,
-			   void __user *buffer, size_t *lenp, loff_t *ppos)
-{
-	struct pid *new_pid;
-	pid_t tmp;
-	int r;
-
-	tmp = pid_vnr(cad_pid);
-
-	r = __do_proc_dointvec(&tmp, table, write, buffer,
-			       lenp, ppos, NULL, NULL);
-	if (r || !write)
-		return r;
-
-	new_pid = find_get_pid(tmp);
-	if (!new_pid)
-		return -ESRCH;
-
-	put_pid(xchg(&cad_pid, new_pid));
-	return 0;
-}
-
-/**
- * proc_do_large_bitmap - read/write from/to a large bitmap
- * @table: the sysctl table
- * @write: %TRUE if this is a write to the sysctl file
- * @buffer: the user buffer
- * @lenp: the size of the user buffer
- * @ppos: file position
- *
- * The bitmap is stored at table->data and the bitmap length (in bits)
- * in table->maxlen.
- *
- * We use a range comma separated format (e.g. 1,3-4,10-10) so that
- * large bitmaps may be represented in a compact manner. Writing into
- * the file will clear the bitmap then update it with the given input.
- *
- * Returns 0 on success.
- */
-int proc_do_large_bitmap(struct ctl_table *table, int write,
-			 void __user *buffer, size_t *lenp, loff_t *ppos)
-{
-	int err = 0;
-	bool first = 1;
-	size_t left = *lenp;
-	unsigned long bitmap_len = table->maxlen;
-	unsigned long *bitmap = *(unsigned long **) table->data;
-	unsigned long *tmp_bitmap = NULL;
-	char tr_a[] = { '-', ',', '\n' }, tr_b[] = { ',', '\n', 0 }, c;
-
-	if (!bitmap || !bitmap_len || !left || (*ppos && !write)) {
-		*lenp = 0;
-		return 0;
-	}
-
-	if (write) {
-		char *kbuf, *p;
-		size_t skipped = 0;
-
-		if (left > PAGE_SIZE - 1) {
-			left = PAGE_SIZE - 1;
-			/* How much of the buffer we'll skip this pass */
-			skipped = *lenp - left;
-		}
-
-		p = kbuf = memdup_user_nul(buffer, left);
-		if (IS_ERR(kbuf))
-			return PTR_ERR(kbuf);
-
-		tmp_bitmap = bitmap_zalloc(bitmap_len, GFP_KERNEL);
-		if (!tmp_bitmap) {
-			kfree(kbuf);
-			return -ENOMEM;
-		}
-		proc_skip_char(&p, &left, '\n');
-		while (!err && left) {
-			unsigned long val_a, val_b;
-			bool neg;
-			size_t saved_left;
-
-			/* In case we stop parsing mid-number, we can reset */
-			saved_left = left;
-			err = proc_get_long(&p, &left, &val_a, &neg, tr_a,
-					     sizeof(tr_a), &c);
-			/*
-			 * If we consumed the entirety of a truncated buffer or
-			 * only one char is left (may be a "-"), then stop here,
-			 * reset, & come back for more.
-			 */
-			if ((left <= 1) && skipped) {
-				left = saved_left;
-				break;
-			}
-
-			if (err)
-				break;
-			if (val_a >= bitmap_len || neg) {
-				err = -EINVAL;
-				break;
-			}
-
-			val_b = val_a;
-			if (left) {
-				p++;
-				left--;
-			}
-
-			if (c == '-') {
-				err = proc_get_long(&p, &left, &val_b,
-						     &neg, tr_b, sizeof(tr_b),
-						     &c);
-				/*
-				 * If we consumed all of a truncated buffer or
-				 * then stop here, reset, & come back for more.
-				 */
-				if (!left && skipped) {
-					left = saved_left;
-					break;
-				}
-
-				if (err)
-					break;
-				if (val_b >= bitmap_len || neg ||
-				    val_a > val_b) {
-					err = -EINVAL;
-					break;
-				}
-				if (left) {
-					p++;
-					left--;
-				}
-			}
-
-			bitmap_set(tmp_bitmap, val_a, val_b - val_a + 1);
-			first = 0;
-			proc_skip_char(&p, &left, '\n');
-		}
-		kfree(kbuf);
-		left += skipped;
-	} else {
-		unsigned long bit_a, bit_b = 0;
-
-		while (left) {
-			bit_a = find_next_bit(bitmap, bitmap_len, bit_b);
-			if (bit_a >= bitmap_len)
-				break;
-			bit_b = find_next_zero_bit(bitmap, bitmap_len,
-						   bit_a + 1) - 1;
-
-			if (!first) {
-				err = proc_put_char(&buffer, &left, ',');
-				if (err)
-					break;
-			}
-			err = proc_put_long(&buffer, &left, bit_a, false);
-			if (err)
-				break;
-			if (bit_a != bit_b) {
-				err = proc_put_char(&buffer, &left, '-');
-				if (err)
-					break;
-				err = proc_put_long(&buffer, &left, bit_b, false);
-				if (err)
-					break;
-			}
-
-			first = 0; bit_b++;
-		}
-		if (!err)
-			err = proc_put_char(&buffer, &left, '\n');
-	}
-
-	if (!err) {
-		if (write) {
-			if (*ppos)
-				bitmap_or(bitmap, bitmap, tmp_bitmap, bitmap_len);
-			else
-				bitmap_copy(bitmap, tmp_bitmap, bitmap_len);
-		}
-		*lenp -= left;
-		*ppos += *lenp;
-	}
-
-	bitmap_free(tmp_bitmap);
-	return err;
-}
-
-#else /* CONFIG_PROC_SYSCTL */
-
-int proc_dostring(struct ctl_table *table, int write,
-		  void __user *buffer, size_t *lenp, loff_t *ppos)
-{
-	return -ENOSYS;
-}
-
-int proc_dointvec(struct ctl_table *table, int write,
-		  void __user *buffer, size_t *lenp, loff_t *ppos)
-{
-	return -ENOSYS;
-}
-
-int proc_douintvec(struct ctl_table *table, int write,
-		  void __user *buffer, size_t *lenp, loff_t *ppos)
-{
-	return -ENOSYS;
-}
-
-int proc_dointvec_minmax(struct ctl_table *table, int write,
-		    void __user *buffer, size_t *lenp, loff_t *ppos)
-{
-	return -ENOSYS;
-}
-
-int proc_douintvec_minmax(struct ctl_table *table, int write,
-			  void __user *buffer, size_t *lenp, loff_t *ppos)
-{
-	return -ENOSYS;
-}
-
-int proc_dointvec_jiffies(struct ctl_table *table, int write,
-		    void __user *buffer, size_t *lenp, loff_t *ppos)
-{
-	return -ENOSYS;
-}
-
-int proc_dointvec_userhz_jiffies(struct ctl_table *table, int write,
-		    void __user *buffer, size_t *lenp, loff_t *ppos)
-{
-	return -ENOSYS;
-}
-
-int proc_dointvec_ms_jiffies(struct ctl_table *table, int write,
-			     void __user *buffer, size_t *lenp, loff_t *ppos)
-{
-	return -ENOSYS;
-}
-
-int proc_doulongvec_minmax(struct ctl_table *table, int write,
-		    void __user *buffer, size_t *lenp, loff_t *ppos)
-{
-	return -ENOSYS;
-}
-
-int proc_doulongvec_ms_jiffies_minmax(struct ctl_table *table, int write,
-				      void __user *buffer,
-				      size_t *lenp, loff_t *ppos)
-{
-    return -ENOSYS;
-}
-
-int proc_do_large_bitmap(struct ctl_table *table, int write,
-			 void __user *buffer, size_t *lenp, loff_t *ppos)
-{
-	return -ENOSYS;
-}
-
-#endif /* CONFIG_PROC_SYSCTL */
-
-#if defined(CONFIG_SYSCTL)
-int proc_do_static_key(struct ctl_table *table, int write,
-		       void __user *buffer, size_t *lenp,
-		       loff_t *ppos)
-{
-	struct static_key *key = (struct static_key *)table->data;
-	static DEFINE_MUTEX(static_key_mutex);
-	int val, ret;
-	struct ctl_table tmp = {
-		.data   = &val,
-		.maxlen = sizeof(val),
-		.mode   = table->mode,
-		.extra1 = SYSCTL_ZERO,
-		.extra2 = SYSCTL_ONE,
-	};
-
-	if (write && !capable(CAP_SYS_ADMIN))
-		return -EPERM;
-
-	mutex_lock(&static_key_mutex);
-	val = static_key_enabled(key);
-	ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos);
-	if (write && !ret) {
-		if (val)
-			static_key_enable(key);
-		else
-			static_key_disable(key);
-	}
-	mutex_unlock(&static_key_mutex);
-	return ret;
-}
-#endif
 /*
  * No sense putting this after each symbol definition, twice,
  * exception granted :-)
diff --git a/kernel/sysctl_binary.c b/kernel/sysctl_binary.c
deleted file mode 100644
index 7d550cc76a3b..000000000000
--- a/kernel/sysctl_binary.c
+++ /dev/null
@@ -1,171 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-#include <linux/stat.h>
-#include <linux/sysctl.h>
-#include "../fs/xfs/xfs_sysctl.h"
-#include <linux/sunrpc/debug.h>
-#include <linux/string.h>
-#include <linux/syscalls.h>
-#include <linux/namei.h>
-#include <linux/mount.h>
-#include <linux/fs.h>
-#include <linux/nsproxy.h>
-#include <linux/pid_namespace.h>
-#include <linux/file.h>
-#include <linux/ctype.h>
-#include <linux/netdevice.h>
-#include <linux/kernel.h>
-#include <linux/uuid.h>
-#include <linux/slab.h>
-#include <linux/compat.h>
-
-static ssize_t binary_sysctl(const int *name, int nlen,
-	void __user *oldval, size_t oldlen, void __user *newval, size_t newlen)
-{
-	return -ENOSYS;
-}
-
-static void deprecated_sysctl_warning(const int *name, int nlen)
-{
-	int i;
-
-	/*
-	 * CTL_KERN/KERN_VERSION is used by older glibc and cannot
-	 * ever go away.
-	 */
-	if (nlen >= 2 && name[0] == CTL_KERN && name[1] == KERN_VERSION)
-		return;
-
-	if (printk_ratelimit()) {
-		printk(KERN_INFO
-			"warning: process `%s' used the deprecated sysctl "
-			"system call with ", current->comm);
-		for (i = 0; i < nlen; i++)
-			printk(KERN_CONT "%d.", name[i]);
-		printk(KERN_CONT "\n");
-	}
-	return;
-}
-
-#define WARN_ONCE_HASH_BITS 8
-#define WARN_ONCE_HASH_SIZE (1<<WARN_ONCE_HASH_BITS)
-
-static DECLARE_BITMAP(warn_once_bitmap, WARN_ONCE_HASH_SIZE);
-
-#define FNV32_OFFSET 2166136261U
-#define FNV32_PRIME 0x01000193
-
-/*
- * Print each legacy sysctl (approximately) only once.
- * To avoid making the tables non-const use a external
- * hash-table instead.
- * Worst case hash collision: 6, but very rarely.
- * NOTE! We don't use the SMP-safe bit tests. We simply
- * don't care enough.
- */
-static void warn_on_bintable(const int *name, int nlen)
-{
-	int i;
-	u32 hash = FNV32_OFFSET;
-
-	for (i = 0; i < nlen; i++)
-		hash = (hash ^ name[i]) * FNV32_PRIME;
-	hash %= WARN_ONCE_HASH_SIZE;
-	if (__test_and_set_bit(hash, warn_once_bitmap))
-		return;
-	deprecated_sysctl_warning(name, nlen);
-}
-
-static ssize_t do_sysctl(int __user *args_name, int nlen,
-	void __user *oldval, size_t oldlen, void __user *newval, size_t newlen)
-{
-	int name[CTL_MAXNAME];
-	int i;
-
-	/* Check args->nlen. */
-	if (nlen < 0 || nlen > CTL_MAXNAME)
-		return -ENOTDIR;
-	/* Read in the sysctl name for simplicity */
-	for (i = 0; i < nlen; i++)
-		if (get_user(name[i], args_name + i))
-			return -EFAULT;
-
-	warn_on_bintable(name, nlen);
-
-	return binary_sysctl(name, nlen, oldval, oldlen, newval, newlen);
-}
-
-SYSCALL_DEFINE1(sysctl, struct __sysctl_args __user *, args)
-{
-	struct __sysctl_args tmp;
-	size_t oldlen = 0;
-	ssize_t result;
-
-	if (copy_from_user(&tmp, args, sizeof(tmp)))
-		return -EFAULT;
-
-	if (tmp.oldval && !tmp.oldlenp)
-		return -EFAULT;
-
-	if (tmp.oldlenp && get_user(oldlen, tmp.oldlenp))
-		return -EFAULT;
-
-	result = do_sysctl(tmp.name, tmp.nlen, tmp.oldval, oldlen,
-			   tmp.newval, tmp.newlen);
-
-	if (result >= 0) {
-		oldlen = result;
-		result = 0;
-	}
-
-	if (tmp.oldlenp && put_user(oldlen, tmp.oldlenp))
-		return -EFAULT;
-
-	return result;
-}
-
-
-#ifdef CONFIG_COMPAT
-
-struct compat_sysctl_args {
-	compat_uptr_t	name;
-	int		nlen;
-	compat_uptr_t	oldval;
-	compat_uptr_t	oldlenp;
-	compat_uptr_t	newval;
-	compat_size_t	newlen;
-	compat_ulong_t	__unused[4];
-};
-
-COMPAT_SYSCALL_DEFINE1(sysctl, struct compat_sysctl_args __user *, args)
-{
-	struct compat_sysctl_args tmp;
-	compat_size_t __user *compat_oldlenp;
-	size_t oldlen = 0;
-	ssize_t result;
-
-	if (copy_from_user(&tmp, args, sizeof(tmp)))
-		return -EFAULT;
-
-	if (tmp.oldval && !tmp.oldlenp)
-		return -EFAULT;
-
-	compat_oldlenp = compat_ptr(tmp.oldlenp);
-	if (compat_oldlenp && get_user(oldlen, compat_oldlenp))
-		return -EFAULT;
-
-	result = do_sysctl(compat_ptr(tmp.name), tmp.nlen,
-			   compat_ptr(tmp.oldval), oldlen,
-			   compat_ptr(tmp.newval), tmp.newlen);
-
-	if (result >= 0) {
-		oldlen = result;
-		result = 0;
-	}
-
-	if (compat_oldlenp && put_user(oldlen, compat_oldlenp))
-		return -EFAULT;
-
-	return result;
-}
-
-#endif /* CONFIG_COMPAT */
diff --git a/kernel/task_work.c b/kernel/task_work.c
index 0fef395662a6..613b2d634af8 100644
--- a/kernel/task_work.c
+++ b/kernel/task_work.c
@@ -25,9 +25,10 @@ static struct callback_head work_exited; /* all we need is ->next == NULL */
  * 0 if succeeds or -ESRCH.
  */
 int
-task_work_add(struct task_struct *task, struct callback_head *work, bool notify)
+task_work_add(struct task_struct *task, struct callback_head *work, int notify)
 {
 	struct callback_head *head;
+	unsigned long flags;
 
 	do {
 		head = READ_ONCE(task->task_works);
@@ -36,8 +37,25 @@ task_work_add(struct task_struct *task, struct callback_head *work, bool notify)
 		work->next = head;
 	} while (cmpxchg(&task->task_works, head, work) != head);
 
-	if (notify)
+	switch (notify) {
+	case TWA_RESUME:
 		set_notify_resume(task);
+		break;
+	case TWA_SIGNAL:
+		/*
+		 * Only grab the sighand lock if we don't already have some
+		 * task_work pending. This pairs with the smp_store_mb()
+		 * in get_signal(), see comment there.
+		 */
+		if (!(READ_ONCE(task->jobctl) & JOBCTL_TASK_WORK) &&
+		    lock_task_sighand(task, &flags)) {
+			task->jobctl |= JOBCTL_TASK_WORK;
+			signal_wake_up(task, 0);
+			unlock_task_sighand(task, &flags);
+		}
+		break;
+	}
+
 	return 0;
 }
 
@@ -97,16 +115,26 @@ void task_work_run(void)
 		 * work->func() can do task_work_add(), do not set
 		 * work_exited unless the list is empty.
 		 */
-		raw_spin_lock_irq(&task->pi_lock);
 		do {
+			head = NULL;
 			work = READ_ONCE(task->task_works);
-			head = !work && (task->flags & PF_EXITING) ?
-				&work_exited : NULL;
+			if (!work) {
+				if (task->flags & PF_EXITING)
+					head = &work_exited;
+				else
+					break;
+			}
 		} while (cmpxchg(&task->task_works, work, head) != work);
-		raw_spin_unlock_irq(&task->pi_lock);
 
 		if (!work)
 			break;
+		/*
+		 * Synchronize with task_work_cancel(). It can not remove
+		 * the first entry == work, cmpxchg(task_works) must fail.
+		 * But it can remove another entry from the ->next list.
+		 */
+		raw_spin_lock_irq(&task->pi_lock);
+		raw_spin_unlock_irq(&task->pi_lock);
 
 		do {
 			next = work->next;
diff --git a/kernel/time/Kconfig b/kernel/time/Kconfig
index fcc42353f125..a09b1d61df6a 100644
--- a/kernel/time/Kconfig
+++ b/kernel/time/Kconfig
@@ -52,6 +52,15 @@ config GENERIC_CLOCKEVENTS_MIN_ADJUST
 config GENERIC_CMOS_UPDATE
 	bool
 
+# Select to handle posix CPU timers from task_work
+# and not from the timer interrupt context
+config HAVE_POSIX_CPU_TIMERS_TASK_WORK
+	bool
+
+config POSIX_CPU_TIMERS_TASK_WORK
+	bool
+	default y if POSIX_TIMERS && HAVE_POSIX_CPU_TIMERS_TASK_WORK
+
 if GENERIC_CLOCKEVENTS
 menu "Timers subsystem"
 
diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c
index 2ffb466af77e..ca223a89530a 100644
--- a/kernel/time/alarmtimer.c
+++ b/kernel/time/alarmtimer.c
@@ -192,7 +192,7 @@ static void alarmtimer_dequeue(struct alarm_base *base, struct alarm *alarm)
  * When a alarm timer fires, this runs through the timerqueue to
  * see which alarms expired, and runs those. If there are more alarm
  * timers queued for the future, we set the hrtimer to fire when
- * when the next future alarm timer expires.
+ * the next future alarm timer expires.
  */
 static enum hrtimer_restart alarmtimer_fired(struct hrtimer *timer)
 {
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index 428beb69426a..02441ead3c3b 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -928,6 +928,13 @@ int __clocksource_register_scale(struct clocksource *cs, u32 scale, u32 freq)
 
 	clocksource_arch_init(cs);
 
+	if (cs->vdso_clock_mode < 0 ||
+	    cs->vdso_clock_mode >= VDSO_CLOCKMODE_MAX) {
+		pr_warn("clocksource %s registered with invalid VDSO mode %d. Disabling VDSO support.\n",
+			cs->name, cs->vdso_clock_mode);
+		cs->vdso_clock_mode = VDSO_CLOCKMODE_NONE;
+	}
+
 	/* Initialize mult/shift and max_idle_ns */
 	__clocksource_update_freq_scale(cs, scale, freq);
 
diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index 3a609e7344f3..95b6a708b040 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -135,7 +135,11 @@ static const int hrtimer_clock_to_base_table[MAX_CLOCKS] = {
  * timer->base->cpu_base
  */
 static struct hrtimer_cpu_base migration_cpu_base = {
-	.clock_base = { { .cpu_base = &migration_cpu_base, }, },
+	.clock_base = { {
+		.cpu_base = &migration_cpu_base,
+		.seq      = SEQCNT_RAW_SPINLOCK_ZERO(migration_cpu_base.seq,
+						     &migration_cpu_base.lock),
+	}, },
 };
 
 #define migration_base	migration_cpu_base.clock_base[0]
@@ -311,7 +315,7 @@ s64 __ktime_divns(const ktime_t kt, s64 div)
 		div >>= 1;
 	}
 	tmp >>= sft;
-	do_div(tmp, (unsigned long) div);
+	do_div(tmp, (u32) div);
 	return dclc < 0 ? -tmp : tmp;
 }
 EXPORT_SYMBOL_GPL(__ktime_divns);
@@ -373,7 +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;
 	}
@@ -1404,7 +1408,7 @@ static void __hrtimer_init(struct hrtimer *timer, clockid_t clock_id,
 	base = softtimer ? HRTIMER_MAX_CLOCK_BASES / 2 : 0;
 	base += hrtimer_clockid_to_base(clock_id);
 	timer->is_soft = softtimer;
-	timer->is_hard = !softtimer;
+	timer->is_hard = !!(mode & HRTIMER_MODE_HARD);
 	timer->base = &cpu_base->clock_base[base];
 	timerqueue_init(&timer->node);
 }
@@ -1480,6 +1484,7 @@ static void __run_hrtimer(struct hrtimer_cpu_base *cpu_base,
 			  unsigned long flags) __must_hold(&cpu_base->lock)
 {
 	enum hrtimer_restart (*fn)(struct hrtimer *);
+	bool expires_in_hardirq;
 	int restart;
 
 	lockdep_assert_held(&cpu_base->lock);
@@ -1514,7 +1519,11 @@ static void __run_hrtimer(struct hrtimer_cpu_base *cpu_base,
 	 */
 	raw_spin_unlock_irqrestore(&cpu_base->lock, flags);
 	trace_hrtimer_expire_entry(timer, now);
+	expires_in_hardirq = lockdep_hrtimer_enter(timer);
+
 	restart = fn(timer);
+
+	lockdep_hrtimer_exit(expires_in_hardirq);
 	trace_hrtimer_expire_exit(timer);
 	raw_spin_lock_irq(&cpu_base->lock);
 
@@ -1993,8 +2002,11 @@ int hrtimers_prepare_cpu(unsigned int cpu)
 	int i;
 
 	for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) {
-		cpu_base->clock_base[i].cpu_base = cpu_base;
-		timerqueue_init_head(&cpu_base->clock_base[i].active);
+		struct hrtimer_clock_base *clock_b = &cpu_base->clock_base[i];
+
+		clock_b->cpu_base = cpu_base;
+		seqcount_raw_spinlock_init(&clock_b->seq, &cpu_base->lock);
+		timerqueue_init_head(&clock_b->active);
 	}
 
 	cpu_base->cpu = cpu;
diff --git a/kernel/time/jiffies.c b/kernel/time/jiffies.c
index d23b434c2ca7..eddcf4970444 100644
--- a/kernel/time/jiffies.c
+++ b/kernel/time/jiffies.c
@@ -58,7 +58,8 @@ static struct clocksource clocksource_jiffies = {
 	.max_cycles	= 10,
 };
 
-__cacheline_aligned_in_smp DEFINE_SEQLOCK(jiffies_lock);
+__cacheline_aligned_in_smp DEFINE_RAW_SPINLOCK(jiffies_lock);
+__cacheline_aligned_in_smp seqcount_t jiffies_seq;
 
 #if (BITS_PER_LONG < 64)
 u64 get_jiffies_64(void)
@@ -67,9 +68,9 @@ u64 get_jiffies_64(void)
 	u64 ret;
 
 	do {
-		seq = read_seqbegin(&jiffies_lock);
+		seq = read_seqcount_begin(&jiffies_seq);
 		ret = jiffies_64;
-	} while (read_seqretry(&jiffies_lock, seq));
+	} while (read_seqcount_retry(&jiffies_seq, seq));
 	return ret;
 }
 EXPORT_SYMBOL(get_jiffies_64);
diff --git a/kernel/time/namespace.c b/kernel/time/namespace.c
index 12858507d75a..afc65e6be33e 100644
--- a/kernel/time/namespace.c
+++ b/kernel/time/namespace.c
@@ -8,6 +8,7 @@
 #include <linux/user_namespace.h>
 #include <linux/sched/signal.h>
 #include <linux/sched/task.h>
+#include <linux/clocksource.h>
 #include <linux/seq_file.h>
 #include <linux/proc_ns.h>
 #include <linux/export.h>
@@ -172,8 +173,8 @@ static struct timens_offset offset_from_ts(struct timespec64 off)
  * for vdso_data->clock_mode is a non-issue. The task is spin waiting for the
  * update to finish and for 'seq' to become even anyway.
  *
- * Timens page has vdso_data->clock_mode set to VCLOCK_TIMENS which enforces
- * the time namespace handling path.
+ * Timens page has vdso_data->clock_mode set to VDSO_CLOCKMODE_TIMENS which
+ * enforces the time namespace handling path.
  */
 static void timens_setup_vdso_data(struct vdso_data *vdata,
 				   struct time_namespace *ns)
@@ -183,7 +184,7 @@ static void timens_setup_vdso_data(struct vdso_data *vdata,
 	struct timens_offset boottime = offset_from_ts(ns->offsets.boottime);
 
 	vdata->seq			= 1;
-	vdata->clock_mode		= VCLOCK_TIMENS;
+	vdata->clock_mode		= VDSO_CLOCKMODE_TIMENS;
 	offset[CLOCK_MONOTONIC]		= monotonic;
 	offset[CLOCK_MONOTONIC_RAW]	= monotonic;
 	offset[CLOCK_MONOTONIC_COARSE]	= monotonic;
@@ -279,24 +280,24 @@ static void timens_put(struct ns_common *ns)
 	put_time_ns(to_time_ns(ns));
 }
 
-static int timens_install(struct nsproxy *nsproxy, struct ns_common *new)
+void timens_commit(struct task_struct *tsk, struct time_namespace *ns)
 {
+	timens_set_vvar_page(tsk, ns);
+	vdso_join_timens(tsk, ns);
+}
+
+static int timens_install(struct nsset *nsset, struct ns_common *new)
+{
+	struct nsproxy *nsproxy = nsset->nsproxy;
 	struct time_namespace *ns = to_time_ns(new);
-	int err;
 
 	if (!current_is_single_threaded())
 		return -EUSERS;
 
 	if (!ns_capable(ns->user_ns, CAP_SYS_ADMIN) ||
-	    !ns_capable(current_user_ns(), CAP_SYS_ADMIN))
+	    !ns_capable(nsset->cred->user_ns, CAP_SYS_ADMIN))
 		return -EPERM;
 
-	timens_set_vvar_page(current, ns);
-
-	err = vdso_join_timens(current, ns);
-	if (err)
-		return err;
-
 	get_time_ns(ns);
 	put_time_ns(nsproxy->time_ns);
 	nsproxy->time_ns = ns;
@@ -311,22 +312,17 @@ int timens_on_fork(struct nsproxy *nsproxy, struct task_struct *tsk)
 {
 	struct ns_common *nsc = &nsproxy->time_ns_for_children->ns;
 	struct time_namespace *ns = to_time_ns(nsc);
-	int err;
 
 	/* create_new_namespaces() already incremented the ref counter */
 	if (nsproxy->time_ns == nsproxy->time_ns_for_children)
 		return 0;
 
-	timens_set_vvar_page(tsk, ns);
-
-	err = vdso_join_timens(tsk, ns);
-	if (err)
-		return err;
-
 	get_time_ns(ns);
 	put_time_ns(nsproxy->time_ns);
 	nsproxy->time_ns = ns;
 
+	timens_commit(tsk, ns);
+
 	return 0;
 }
 
@@ -337,7 +333,20 @@ static struct user_namespace *timens_owner(struct ns_common *ns)
 
 static void show_offset(struct seq_file *m, int clockid, struct timespec64 *ts)
 {
-	seq_printf(m, "%d %lld %ld\n", clockid, ts->tv_sec, ts->tv_nsec);
+	char *clock;
+
+	switch (clockid) {
+	case CLOCK_BOOTTIME:
+		clock = "boottime";
+		break;
+	case CLOCK_MONOTONIC:
+		clock = "monotonic";
+		break;
+	default:
+		clock = "unknown";
+		break;
+	}
+	seq_printf(m, "%-10s %10lld %9ld\n", clock, ts->tv_sec, ts->tv_nsec);
 }
 
 void proc_timens_show_offsets(struct task_struct *p, struct seq_file *m)
@@ -446,6 +455,7 @@ const struct proc_ns_operations timens_operations = {
 
 const struct proc_ns_operations timens_for_children_operations = {
 	.name		= "time_for_children",
+	.real_ns_name	= "time",
 	.type		= CLONE_NEWTIME,
 	.get		= timens_for_children_get,
 	.put		= timens_put,
diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c
index 8ff6da77a01f..a71758e34e45 100644
--- a/kernel/time/posix-cpu-timers.c
+++ b/kernel/time/posix-cpu-timers.c
@@ -47,75 +47,65 @@ void update_rlimit_cpu(struct task_struct *task, unsigned long rlim_new)
 /*
  * Functions for validating access to tasks.
  */
-static struct task_struct *lookup_task(const pid_t pid, bool thread,
-				       bool gettime)
+static struct pid *pid_for_clock(const clockid_t clock, bool gettime)
 {
-	struct task_struct *p;
+	const bool thread = !!CPUCLOCK_PERTHREAD(clock);
+	const pid_t upid = CPUCLOCK_PID(clock);
+	struct pid *pid;
+
+	if (CPUCLOCK_WHICH(clock) >= CPUCLOCK_MAX)
+		return NULL;
 
 	/*
 	 * If the encoded PID is 0, then the timer is targeted at current
 	 * or the process to which current belongs.
 	 */
-	if (!pid)
-		return thread ? current : current->group_leader;
+	if (upid == 0)
+		return thread ? task_pid(current) : task_tgid(current);
 
-	p = find_task_by_vpid(pid);
-	if (!p)
-		return p;
-
-	if (thread)
-		return same_thread_group(p, current) ? p : NULL;
+	pid = find_vpid(upid);
+	if (!pid)
+		return NULL;
 
-	if (gettime) {
-		/*
-		 * For clock_gettime(PROCESS) the task does not need to be
-		 * the actual group leader. tsk->sighand gives
-		 * access to the group's clock.
-		 *
-		 * Timers need the group leader because they take a
-		 * reference on it and store the task pointer until the
-		 * timer is destroyed.
-		 */
-		return (p == current || thread_group_leader(p)) ? p : NULL;
+	if (thread) {
+		struct task_struct *tsk = pid_task(pid, PIDTYPE_PID);
+		return (tsk && same_thread_group(tsk, current)) ? pid : NULL;
 	}
 
 	/*
-	 * For processes require that p is group leader.
+	 * For clock_gettime(PROCESS) allow finding the process by
+	 * with the pid of the current task.  The code needs the tgid
+	 * of the process so that pid_task(pid, PIDTYPE_TGID) can be
+	 * used to find the process.
+	 */
+	if (gettime && (pid == task_pid(current)))
+		return task_tgid(current);
+
+	/*
+	 * For processes require that pid identifies a process.
 	 */
-	return has_group_leader_pid(p) ? p : NULL;
+	return pid_has_task(pid, PIDTYPE_TGID) ? pid : NULL;
 }
 
-static struct task_struct *__get_task_for_clock(const clockid_t clock,
-						bool getref, bool gettime)
+static inline int validate_clock_permissions(const clockid_t clock)
 {
-	const bool thread = !!CPUCLOCK_PERTHREAD(clock);
-	const pid_t pid = CPUCLOCK_PID(clock);
-	struct task_struct *p;
-
-	if (CPUCLOCK_WHICH(clock) >= CPUCLOCK_MAX)
-		return NULL;
+	int ret;
 
 	rcu_read_lock();
-	p = lookup_task(pid, thread, gettime);
-	if (p && getref)
-		get_task_struct(p);
+	ret = pid_for_clock(clock, false) ? 0 : -EINVAL;
 	rcu_read_unlock();
-	return p;
-}
 
-static inline struct task_struct *get_task_for_clock(const clockid_t clock)
-{
-	return __get_task_for_clock(clock, true, false);
+	return ret;
 }
 
-static inline struct task_struct *get_task_for_clock_get(const clockid_t clock)
+static inline enum pid_type clock_pid_type(const clockid_t clock)
 {
-	return __get_task_for_clock(clock, true, true);
+	return CPUCLOCK_PERTHREAD(clock) ? PIDTYPE_PID : PIDTYPE_TGID;
 }
 
-static inline int validate_clock_permissions(const clockid_t clock)
+static inline struct task_struct *cpu_timer_task_rcu(struct k_itimer *timer)
 {
-	return __get_task_for_clock(clock, false, false) ? 0 : -EINVAL;
+	return pid_task(timer->it.cpu.pid, clock_pid_type(timer->it_clock));
 }
 
 /*
@@ -336,9 +326,7 @@ static void __thread_group_cputime(struct task_struct *tsk, u64 *samples)
 /*
  * Sample a process (thread group) clock for the given task clkid. If the
  * group's cputime accounting is already enabled, read the atomic
- * store. Otherwise a full update is required.  Task's sighand lock must be
- * held to protect the task traversal on a full update. clkid is already
- * validated.
+ * store. Otherwise a full update is required.  clkid is already validated.
  */
 static u64 cpu_clock_sample_group(const clockid_t clkid, struct task_struct *p,
 				  bool start)
@@ -365,15 +353,18 @@ static int posix_cpu_clock_get(const clockid_t clock, struct timespec64 *tp)
 	struct task_struct *tsk;
 	u64 t;
 
-	tsk = get_task_for_clock_get(clock);
-	if (!tsk)
+	rcu_read_lock();
+	tsk = pid_task(pid_for_clock(clock, true), clock_pid_type(clock));
+	if (!tsk) {
+		rcu_read_unlock();
 		return -EINVAL;
+	}
 
 	if (CPUCLOCK_PERTHREAD(clock))
 		t = cpu_clock_sample(clkid, tsk);
 	else
 		t = cpu_clock_sample_group(clkid, tsk, false);
-	put_task_struct(tsk);
+	rcu_read_unlock();
 
 	*tp = ns_to_timespec64(t);
 	return 0;
@@ -386,14 +377,31 @@ static int posix_cpu_clock_get(const clockid_t clock, struct timespec64 *tp)
  */
 static int posix_cpu_timer_create(struct k_itimer *new_timer)
 {
-	struct task_struct *p = get_task_for_clock(new_timer->it_clock);
+	static struct lock_class_key posix_cpu_timers_key;
+	struct pid *pid;
 
-	if (!p)
+	rcu_read_lock();
+	pid = pid_for_clock(new_timer->it_clock, false);
+	if (!pid) {
+		rcu_read_unlock();
 		return -EINVAL;
+	}
+
+	/*
+	 * If posix timer expiry is handled in task work context then
+	 * timer::it_lock can be taken without disabling interrupts as all
+	 * other locking happens in task context. This requires a seperate
+	 * lock class key otherwise regular posix timer expiry would record
+	 * the lock class being taken in interrupt context and generate a
+	 * false positive warning.
+	 */
+	if (IS_ENABLED(CONFIG_POSIX_CPU_TIMERS_TASK_WORK))
+		lockdep_set_class(&new_timer->it_lock, &posix_cpu_timers_key);
 
 	new_timer->kclock = &clock_posix_cpu;
 	timerqueue_init(&new_timer->it.cpu.node);
-	new_timer->it.cpu.task = p;
+	new_timer->it.cpu.pid = get_pid(pid);
+	rcu_read_unlock();
 	return 0;
 }
 
@@ -406,13 +414,15 @@ static int posix_cpu_timer_create(struct k_itimer *new_timer)
 static int posix_cpu_timer_del(struct k_itimer *timer)
 {
 	struct cpu_timer *ctmr = &timer->it.cpu;
-	struct task_struct *p = ctmr->task;
 	struct sighand_struct *sighand;
+	struct task_struct *p;
 	unsigned long flags;
 	int ret = 0;
 
-	if (WARN_ON_ONCE(!p))
-		return -EINVAL;
+	rcu_read_lock();
+	p = cpu_timer_task_rcu(timer);
+	if (!p)
+		goto out;
 
 	/*
 	 * Protect against sighand release/switch in exit/exec and process/
@@ -434,8 +444,10 @@ static int posix_cpu_timer_del(struct k_itimer *timer)
 		unlock_task_sighand(p, &flags);
 	}
 
+out:
+	rcu_read_unlock();
 	if (!ret)
-		put_task_struct(p);
+		put_pid(ctmr->pid);
 
 	return ret;
 }
@@ -484,12 +496,11 @@ void posix_cpu_timers_exit_group(struct task_struct *tsk)
  * Insert the timer on the appropriate list before any timers that
  * expire later.  This must be called with the sighand lock held.
  */
-static void arm_timer(struct k_itimer *timer)
+static void arm_timer(struct k_itimer *timer, struct task_struct *p)
 {
 	int clkidx = CPUCLOCK_WHICH(timer->it_clock);
 	struct cpu_timer *ctmr = &timer->it.cpu;
 	u64 newexp = cpu_timer_getexpires(ctmr);
-	struct task_struct *p = ctmr->task;
 	struct posix_cputimer_base *base;
 
 	if (CPUCLOCK_PERTHREAD(timer->it_clock))
@@ -564,13 +575,21 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int timer_flags,
 	clockid_t clkid = CPUCLOCK_WHICH(timer->it_clock);
 	u64 old_expires, new_expires, old_incr, val;
 	struct cpu_timer *ctmr = &timer->it.cpu;
-	struct task_struct *p = ctmr->task;
 	struct sighand_struct *sighand;
+	struct task_struct *p;
 	unsigned long flags;
 	int ret = 0;
 
-	if (WARN_ON_ONCE(!p))
-		return -EINVAL;
+	rcu_read_lock();
+	p = cpu_timer_task_rcu(timer);
+	if (!p) {
+		/*
+		 * If p has just been reaped, we can no
+		 * longer get any information about it at all.
+		 */
+		rcu_read_unlock();
+		return -ESRCH;
+	}
 
 	/*
 	 * Use the to_ktime conversion because that clamps the maximum
@@ -587,8 +606,10 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int timer_flags,
 	 * If p has just been reaped, we can no
 	 * longer get any information about it at all.
 	 */
-	if (unlikely(sighand == NULL))
+	if (unlikely(sighand == NULL)) {
+		rcu_read_unlock();
 		return -ESRCH;
+	}
 
 	/*
 	 * Disarm any old timer after extracting its expiry time.
@@ -662,7 +683,7 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int timer_flags,
 	 */
 	cpu_timer_setexpires(ctmr, new_expires);
 	if (new_expires != 0 && val < new_expires) {
-		arm_timer(timer);
+		arm_timer(timer, p);
 	}
 
 	unlock_task_sighand(p, &flags);
@@ -693,6 +714,7 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int timer_flags,
 
 	ret = 0;
  out:
+	rcu_read_unlock();
 	if (old)
 		old->it_interval = ns_to_timespec64(old_incr);
 
@@ -704,10 +726,12 @@ static void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec64 *itp
 	clockid_t clkid = CPUCLOCK_WHICH(timer->it_clock);
 	struct cpu_timer *ctmr = &timer->it.cpu;
 	u64 now, expires = cpu_timer_getexpires(ctmr);
-	struct task_struct *p = ctmr->task;
+	struct task_struct *p;
 
-	if (WARN_ON_ONCE(!p))
-		return;
+	rcu_read_lock();
+	p = cpu_timer_task_rcu(timer);
+	if (!p)
+		goto out;
 
 	/*
 	 * Easy part: convert the reload time.
@@ -715,36 +739,15 @@ static void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec64 *itp
 	itp->it_interval = ktime_to_timespec64(timer->it_interval);
 
 	if (!expires)
-		return;
+		goto out;
 
 	/*
 	 * Sample the clock to take the difference with the expiry time.
 	 */
-	if (CPUCLOCK_PERTHREAD(timer->it_clock)) {
+	if (CPUCLOCK_PERTHREAD(timer->it_clock))
 		now = cpu_clock_sample(clkid, p);
-	} else {
-		struct sighand_struct *sighand;
-		unsigned long flags;
-
-		/*
-		 * Protect against sighand release/switch in exit/exec and
-		 * also make timer sampling safe if it ends up calling
-		 * thread_group_cputime().
-		 */
-		sighand = lock_task_sighand(p, &flags);
-		if (unlikely(sighand == NULL)) {
-			/*
-			 * The process has been reaped.
-			 * We can't even collect a sample any more.
-			 * Disarm the timer, nothing else to do.
-			 */
-			cpu_timer_setexpires(ctmr, 0);
-			return;
-		} else {
-			now = cpu_clock_sample_group(clkid, p, false);
-			unlock_task_sighand(p, &flags);
-		}
-	}
+	else
+		now = cpu_clock_sample_group(clkid, p, false);
 
 	if (now < expires) {
 		itp->it_value = ns_to_timespec64(expires - now);
@@ -756,6 +759,8 @@ static void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec64 *itp
 		itp->it_value.tv_nsec = 1;
 		itp->it_value.tv_sec = 0;
 	}
+out:
+	rcu_read_unlock();
 }
 
 #define MAX_COLLECTED	20
@@ -976,56 +981,38 @@ static void check_process_timers(struct task_struct *tsk,
 static void posix_cpu_timer_rearm(struct k_itimer *timer)
 {
 	clockid_t clkid = CPUCLOCK_WHICH(timer->it_clock);
-	struct cpu_timer *ctmr = &timer->it.cpu;
-	struct task_struct *p = ctmr->task;
+	struct task_struct *p;
 	struct sighand_struct *sighand;
 	unsigned long flags;
 	u64 now;
 
-	if (WARN_ON_ONCE(!p))
-		return;
+	rcu_read_lock();
+	p = cpu_timer_task_rcu(timer);
+	if (!p)
+		goto out;
 
 	/*
 	 * Fetch the current sample and update the timer's expiry time.
 	 */
-	if (CPUCLOCK_PERTHREAD(timer->it_clock)) {
+	if (CPUCLOCK_PERTHREAD(timer->it_clock))
 		now = cpu_clock_sample(clkid, p);
-		bump_cpu_timer(timer, now);
-		if (unlikely(p->exit_state))
-			return;
-
-		/* Protect timer list r/w in arm_timer() */
-		sighand = lock_task_sighand(p, &flags);
-		if (!sighand)
-			return;
-	} else {
-		/*
-		 * Protect arm_timer() and timer sampling in case of call to
-		 * thread_group_cputime().
-		 */
-		sighand = lock_task_sighand(p, &flags);
-		if (unlikely(sighand == NULL)) {
-			/*
-			 * The process has been reaped.
-			 * We can't even collect a sample any more.
-			 */
-			cpu_timer_setexpires(ctmr, 0);
-			return;
-		} else if (unlikely(p->exit_state) && thread_group_empty(p)) {
-			/* If the process is dying, no need to rearm */
-			goto unlock;
-		}
+	else
 		now = cpu_clock_sample_group(clkid, p, true);
-		bump_cpu_timer(timer, now);
-		/* Leave the sighand locked for the call below.  */
-	}
+
+	bump_cpu_timer(timer, now);
+
+	/* Protect timer list r/w in arm_timer() */
+	sighand = lock_task_sighand(p, &flags);
+	if (unlikely(sighand == NULL))
+		goto out;
 
 	/*
 	 * Now re-arm for the new expiry time.
 	 */
-	arm_timer(timer);
-unlock:
+	arm_timer(timer, p);
 	unlock_task_sighand(p, &flags);
+out:
+	rcu_read_unlock();
 }
 
 /**
@@ -1105,40 +1092,163 @@ static inline bool fastpath_timer_check(struct task_struct *tsk)
 	return false;
 }
 
+static void handle_posix_cpu_timers(struct task_struct *tsk);
+
+#ifdef CONFIG_POSIX_CPU_TIMERS_TASK_WORK
+static void posix_cpu_timers_work(struct callback_head *work)
+{
+	handle_posix_cpu_timers(current);
+}
+
 /*
- * This is called from the timer interrupt handler.  The irq handler has
- * already updated our counts.  We need to check if any timers fire now.
- * Interrupts are disabled.
+ * Initialize posix CPU timers task work in init task. Out of line to
+ * keep the callback static and to avoid header recursion hell.
  */
-void run_posix_cpu_timers(void)
+void __init posix_cputimers_init_work(void)
 {
-	struct task_struct *tsk = current;
-	struct k_itimer *timer, *next;
-	unsigned long flags;
-	LIST_HEAD(firing);
+	init_task_work(&current->posix_cputimers_work.work,
+		       posix_cpu_timers_work);
+}
 
-	lockdep_assert_irqs_disabled();
+/*
+ * Note: All operations on tsk->posix_cputimer_work.scheduled happen either
+ * in hard interrupt context or in task context with interrupts
+ * disabled. Aside of that the writer/reader interaction is always in the
+ * context of the current task, which means they are strict per CPU.
+ */
+static inline bool posix_cpu_timers_work_scheduled(struct task_struct *tsk)
+{
+	return tsk->posix_cputimers_work.scheduled;
+}
+
+static inline void __run_posix_cpu_timers(struct task_struct *tsk)
+{
+	if (WARN_ON_ONCE(tsk->posix_cputimers_work.scheduled))
+		return;
+
+	/* Schedule task work to actually expire the timers */
+	tsk->posix_cputimers_work.scheduled = true;
+	task_work_add(tsk, &tsk->posix_cputimers_work.work, TWA_RESUME);
+}
+
+static inline bool posix_cpu_timers_enable_work(struct task_struct *tsk,
+						unsigned long start)
+{
+	bool ret = true;
 
 	/*
-	 * The fast path checks that there are no expired thread or thread
-	 * group timers.  If that's so, just return.
+	 * On !RT kernels interrupts are disabled while collecting expired
+	 * timers, so no tick can happen and the fast path check can be
+	 * reenabled without further checks.
 	 */
-	if (!fastpath_timer_check(tsk))
-		return;
+	if (!IS_ENABLED(CONFIG_PREEMPT_RT)) {
+		tsk->posix_cputimers_work.scheduled = false;
+		return true;
+	}
 
-	if (!lock_task_sighand(tsk, &flags))
-		return;
 	/*
-	 * Here we take off tsk->signal->cpu_timers[N] and
-	 * tsk->cpu_timers[N] all the timers that are firing, and
-	 * put them on the firing list.
+	 * On RT enabled kernels ticks can happen while the expired timers
+	 * are collected under sighand lock. But any tick which observes
+	 * the CPUTIMERS_WORK_SCHEDULED bit set, does not run the fastpath
+	 * checks. So reenabling the tick work has do be done carefully:
+	 *
+	 * Disable interrupts and run the fast path check if jiffies have
+	 * advanced since the collecting of expired timers started. If
+	 * jiffies have not advanced or the fast path check did not find
+	 * newly expired timers, reenable the fast path check in the timer
+	 * interrupt. If there are newly expired timers, return false and
+	 * let the collection loop repeat.
 	 */
-	check_thread_timers(tsk, &firing);
+	local_irq_disable();
+	if (start != jiffies && fastpath_timer_check(tsk))
+		ret = false;
+	else
+		tsk->posix_cputimers_work.scheduled = false;
+	local_irq_enable();
+
+	return ret;
+}
+#else /* CONFIG_POSIX_CPU_TIMERS_TASK_WORK */
+static inline void __run_posix_cpu_timers(struct task_struct *tsk)
+{
+	lockdep_posixtimer_enter();
+	handle_posix_cpu_timers(tsk);
+	lockdep_posixtimer_exit();
+}
+
+static inline bool posix_cpu_timers_work_scheduled(struct task_struct *tsk)
+{
+	return false;
+}
+
+static inline bool posix_cpu_timers_enable_work(struct task_struct *tsk,
+						unsigned long start)
+{
+	return true;
+}
+#endif /* CONFIG_POSIX_CPU_TIMERS_TASK_WORK */
+
+static void handle_posix_cpu_timers(struct task_struct *tsk)
+{
+	struct k_itimer *timer, *next;
+	unsigned long flags, start;
+	LIST_HEAD(firing);
+
+	if (!lock_task_sighand(tsk, &flags))
+		return;
+
+	do {
+		/*
+		 * On RT locking sighand lock does not disable interrupts,
+		 * so this needs to be careful vs. ticks. Store the current
+		 * jiffies value.
+		 */
+		start = READ_ONCE(jiffies);
+		barrier();
 
-	check_process_timers(tsk, &firing);
+		/*
+		 * Here we take off tsk->signal->cpu_timers[N] and
+		 * tsk->cpu_timers[N] all the timers that are firing, and
+		 * put them on the firing list.
+		 */
+		check_thread_timers(tsk, &firing);
+
+		check_process_timers(tsk, &firing);
+
+		/*
+		 * The above timer checks have updated the exipry cache and
+		 * because nothing can have queued or modified timers after
+		 * sighand lock was taken above it is guaranteed to be
+		 * consistent. So the next timer interrupt fastpath check
+		 * will find valid data.
+		 *
+		 * If timer expiry runs in the timer interrupt context then
+		 * the loop is not relevant as timers will be directly
+		 * expired in interrupt context. The stub function below
+		 * returns always true which allows the compiler to
+		 * optimize the loop out.
+		 *
+		 * If timer expiry is deferred to task work context then
+		 * the following rules apply:
+		 *
+		 * - On !RT kernels no tick can have happened on this CPU
+		 *   after sighand lock was acquired because interrupts are
+		 *   disabled. So reenabling task work before dropping
+		 *   sighand lock and reenabling interrupts is race free.
+		 *
+		 * - On RT kernels ticks might have happened but the tick
+		 *   work ignored posix CPU timer handling because the
+		 *   CPUTIMERS_WORK_SCHEDULED bit is set. Reenabling work
+		 *   must be done very carefully including a check whether
+		 *   ticks have happened since the start of the timer
+		 *   expiry checks. posix_cpu_timers_enable_work() takes
+		 *   care of that and eventually lets the expiry checks
+		 *   run again.
+		 */
+	} while (!posix_cpu_timers_enable_work(tsk, start));
 
 	/*
-	 * We must release these locks before taking any timer's lock.
+	 * We must release sighand lock before taking any timer's lock.
 	 * There is a potential race with timer deletion here, as the
 	 * siglock now protects our private firing list.  We have set
 	 * the firing flag in each timer, so that a deletion attempt
@@ -1156,6 +1266,13 @@ void run_posix_cpu_timers(void)
 	list_for_each_entry_safe(timer, next, &firing, it.cpu.elist) {
 		int cpu_firing;
 
+		/*
+		 * spin_lock() is sufficient here even independent of the
+		 * expiry context. If expiry happens in hard interrupt
+		 * context it's obvious. For task work context it's safe
+		 * because all other operations on timer::it_lock happen in
+		 * task context (syscall or exit).
+		 */
 		spin_lock(&timer->it_lock);
 		list_del_init(&timer->it.cpu.elist);
 		cpu_firing = timer->it.cpu.firing;
@@ -1172,6 +1289,34 @@ void run_posix_cpu_timers(void)
 }
 
 /*
+ * This is called from the timer interrupt handler.  The irq handler has
+ * already updated our counts.  We need to check if any timers fire now.
+ * Interrupts are disabled.
+ */
+void run_posix_cpu_timers(void)
+{
+	struct task_struct *tsk = current;
+
+	lockdep_assert_irqs_disabled();
+
+	/*
+	 * If the actual expiry is deferred to task work context and the
+	 * work is already scheduled there is no point to do anything here.
+	 */
+	if (posix_cpu_timers_work_scheduled(tsk))
+		return;
+
+	/*
+	 * The fast path checks that there are no expired thread or thread
+	 * group timers.  If that's so, just return.
+	 */
+	if (!fastpath_timer_check(tsk))
+		return;
+
+	__run_posix_cpu_timers(tsk);
+}
+
+/*
  * Set one of the process-wide special case CPU timers or RLIMIT_CPU.
  * The tsk->sighand->siglock must be held by the caller.
  */
diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c
index ff0eb30de346..bf540f5a4115 100644
--- a/kernel/time/posix-timers.c
+++ b/kernel/time/posix-timers.c
@@ -121,7 +121,8 @@ static struct k_itimer *__posix_timers_find(struct hlist_head *head,
 {
 	struct k_itimer *timer;
 
-	hlist_for_each_entry_rcu(timer, head, t_hash) {
+	hlist_for_each_entry_rcu(timer, head, t_hash,
+				 lockdep_is_held(&hash_lock)) {
 		if ((timer->it_signal == sig) && (timer->it_id == id))
 			return timer;
 	}
@@ -438,12 +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/sched_clock.c b/kernel/time/sched_clock.c
index e4332e3e2d56..1c03eec6ca9b 100644
--- a/kernel/time/sched_clock.c
+++ b/kernel/time/sched_clock.c
@@ -20,31 +20,6 @@
 #include "timekeeping.h"
 
 /**
- * struct clock_read_data - data required to read from sched_clock()
- *
- * @epoch_ns:		sched_clock() value at last update
- * @epoch_cyc:		Clock cycle value at last update.
- * @sched_clock_mask:   Bitmask for two's complement subtraction of non 64bit
- *			clocks.
- * @read_sched_clock:	Current clock source (or dummy source when suspended).
- * @mult:		Multipler for scaled math conversion.
- * @shift:		Shift value for scaled math conversion.
- *
- * Care must be taken when updating this structure; it is read by
- * some very hot code paths. It occupies <=40 bytes and, when combined
- * with the seqcount used to synchronize access, comfortably fits into
- * a 64 byte cache line.
- */
-struct clock_read_data {
-	u64 epoch_ns;
-	u64 epoch_cyc;
-	u64 sched_clock_mask;
-	u64 (*read_sched_clock)(void);
-	u32 mult;
-	u32 shift;
-};
-
-/**
  * struct clock_data - all data needed for sched_clock() (including
  *                     registration of a new clock source)
  *
@@ -93,6 +68,17 @@ static inline u64 notrace cyc_to_ns(u64 cyc, u32 mult, u32 shift)
 	return (cyc * mult) >> shift;
 }
 
+struct clock_read_data *sched_clock_read_begin(unsigned int *seq)
+{
+	*seq = raw_read_seqcount_latch(&cd.seq);
+	return cd.read_data + (*seq & 1);
+}
+
+int sched_clock_read_retry(unsigned int seq)
+{
+	return read_seqcount_retry(&cd.seq, seq);
+}
+
 unsigned long long notrace sched_clock(void)
 {
 	u64 cyc, res;
@@ -100,13 +86,12 @@ unsigned long long notrace sched_clock(void)
 	struct clock_read_data *rd;
 
 	do {
-		seq = raw_read_seqcount(&cd.seq);
-		rd = cd.read_data + (seq & 1);
+		rd = sched_clock_read_begin(&seq);
 
 		cyc = (rd->read_sched_clock() - rd->epoch_cyc) &
 		      rd->sched_clock_mask;
 		res = rd->epoch_ns + cyc_to_ns(cyc, rd->mult, rd->shift);
-	} while (read_seqcount_retry(&cd.seq, seq));
+	} while (sched_clock_read_retry(seq));
 
 	return res;
 }
@@ -208,7 +193,8 @@ sched_clock_register(u64 (*read)(void), int bits, unsigned long rate)
 
 	if (sched_clock_timer.function != NULL) {
 		/* update timeout for clock wrap */
-		hrtimer_start(&sched_clock_timer, cd.wrap_kt, HRTIMER_MODE_REL);
+		hrtimer_start(&sched_clock_timer, cd.wrap_kt,
+			      HRTIMER_MODE_REL_HARD);
 	}
 
 	r = rate;
@@ -243,7 +229,7 @@ void __init generic_sched_clock_init(void)
 {
 	/*
 	 * If no sched_clock() function has been provided at that point,
-	 * make it the final one one.
+	 * make it the final one.
 	 */
 	if (cd.actual_read_sched_clock == jiffy_sched_clock_read)
 		sched_clock_register(jiffy_sched_clock_read, BITS_PER_LONG, HZ);
@@ -254,9 +240,9 @@ void __init generic_sched_clock_init(void)
 	 * Start the timer to keep sched_clock() properly updated and
 	 * sets the initial epoch.
 	 */
-	hrtimer_init(&sched_clock_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+	hrtimer_init(&sched_clock_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD);
 	sched_clock_timer.function = sched_clock_poll;
-	hrtimer_start(&sched_clock_timer, cd.wrap_kt, HRTIMER_MODE_REL);
+	hrtimer_start(&sched_clock_timer, cd.wrap_kt, HRTIMER_MODE_REL_HARD);
 }
 
 /*
@@ -293,7 +279,7 @@ void sched_clock_resume(void)
 	struct clock_read_data *rd = &cd.read_data[0];
 
 	rd->epoch_cyc = cd.actual_read_sched_clock();
-	hrtimer_start(&sched_clock_timer, cd.wrap_kt, HRTIMER_MODE_REL);
+	hrtimer_start(&sched_clock_timer, cd.wrap_kt, HRTIMER_MODE_REL_HARD);
 	rd->read_sched_clock = cd.actual_read_sched_clock;
 }
 
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/tick-common.c b/kernel/time/tick-common.c
index 7e5d3524e924..6c9c342dd0e5 100644
--- a/kernel/time/tick-common.c
+++ b/kernel/time/tick-common.c
@@ -84,13 +84,15 @@ int tick_is_oneshot_available(void)
 static void tick_periodic(int cpu)
 {
 	if (tick_do_timer_cpu == cpu) {
-		write_seqlock(&jiffies_lock);
+		raw_spin_lock(&jiffies_lock);
+		write_seqcount_begin(&jiffies_seq);
 
 		/* Keep track of the next tick event */
 		tick_next_period = ktime_add(tick_next_period, tick_period);
 
 		do_timer(1);
-		write_sequnlock(&jiffies_lock);
+		write_seqcount_end(&jiffies_seq);
+		raw_spin_unlock(&jiffies_lock);
 		update_wall_time();
 	}
 
@@ -162,9 +164,9 @@ void tick_setup_periodic(struct clock_event_device *dev, int broadcast)
 		ktime_t next;
 
 		do {
-			seq = read_seqbegin(&jiffies_lock);
+			seq = read_seqcount_begin(&jiffies_seq);
 			next = tick_next_period;
-		} while (read_seqretry(&jiffies_lock, seq));
+		} while (read_seqcount_retry(&jiffies_seq, seq));
 
 		clockevents_switch_state(dev, CLOCK_EVT_STATE_ONESHOT);
 
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index a792d21cac64..f0199a4ba1ad 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -65,7 +65,8 @@ static void tick_do_update_jiffies64(ktime_t now)
 		return;
 
 	/* Reevaluate with jiffies_lock held */
-	write_seqlock(&jiffies_lock);
+	raw_spin_lock(&jiffies_lock);
+	write_seqcount_begin(&jiffies_seq);
 
 	delta = ktime_sub(now, last_jiffies_update);
 	if (delta >= tick_period) {
@@ -91,10 +92,12 @@ static void tick_do_update_jiffies64(ktime_t now)
 		/* Keep the tick_next_period variable up to date */
 		tick_next_period = ktime_add(last_jiffies_update, tick_period);
 	} else {
-		write_sequnlock(&jiffies_lock);
+		write_seqcount_end(&jiffies_seq);
+		raw_spin_unlock(&jiffies_lock);
 		return;
 	}
-	write_sequnlock(&jiffies_lock);
+	write_seqcount_end(&jiffies_seq);
+	raw_spin_unlock(&jiffies_lock);
 	update_wall_time();
 }
 
@@ -105,12 +108,14 @@ static ktime_t tick_init_jiffy_update(void)
 {
 	ktime_t period;
 
-	write_seqlock(&jiffies_lock);
+	raw_spin_lock(&jiffies_lock);
+	write_seqcount_begin(&jiffies_seq);
 	/* Did we start the jiffies update yet ? */
 	if (last_jiffies_update == 0)
 		last_jiffies_update = tick_next_period;
 	period = last_jiffies_update;
-	write_sequnlock(&jiffies_lock);
+	write_seqcount_end(&jiffies_seq);
+	raw_spin_unlock(&jiffies_lock);
 	return period;
 }
 
@@ -240,6 +245,7 @@ static void nohz_full_kick_func(struct irq_work *work)
 
 static DEFINE_PER_CPU(struct irq_work, nohz_full_kick_work) = {
 	.func = nohz_full_kick_func,
+	.flags = ATOMIC_INIT(IRQ_WORK_HARD_IRQ),
 };
 
 /*
@@ -345,16 +351,24 @@ void tick_nohz_dep_clear_cpu(int cpu, enum tick_dep_bits bit)
 EXPORT_SYMBOL_GPL(tick_nohz_dep_clear_cpu);
 
 /*
- * Set a per-task tick dependency. Posix CPU timers need this in order to elapse
- * per task timers.
+ * Set a per-task tick dependency. RCU need this. Also posix CPU timers
+ * in order to elapse per task timers.
  */
 void tick_nohz_dep_set_task(struct task_struct *tsk, enum tick_dep_bits bit)
 {
-	/*
-	 * We could optimize this with just kicking the target running the task
-	 * if that noise matters for nohz full users.
-	 */
-	tick_nohz_dep_set_all(&tsk->tick_dep_mask, bit);
+	if (!atomic_fetch_or(BIT(bit), &tsk->tick_dep_mask)) {
+		if (tsk == current) {
+			preempt_disable();
+			tick_nohz_full_kick();
+			preempt_enable();
+		} else {
+			/*
+			 * Some future tick_nohz_full_kick_task()
+			 * should optimize this.
+			 */
+			tick_nohz_full_kick_all();
+		}
+	}
 }
 EXPORT_SYMBOL_GPL(tick_nohz_dep_set_task);
 
@@ -676,10 +690,10 @@ static ktime_t tick_nohz_next_event(struct tick_sched *ts, int cpu)
 
 	/* Read jiffies and the time when jiffies were updated last */
 	do {
-		seq = read_seqbegin(&jiffies_lock);
+		seq = read_seqcount_begin(&jiffies_seq);
 		basemono = last_jiffies_update;
 		basejiff = jiffies;
-	} while (read_seqretry(&jiffies_lock, seq));
+	} while (read_seqcount_retry(&jiffies_seq, seq));
 	ts->last_jiffies = basejiff;
 	ts->timer_expires_base = basemono;
 
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index ca69290bee2a..4c47f388a83f 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -39,18 +39,19 @@ enum timekeeping_adv_mode {
 	TK_ADV_FREQ
 };
 
+DEFINE_RAW_SPINLOCK(timekeeper_lock);
+
 /*
  * The most important data for readout fits into a single 64 byte
  * cache line.
  */
 static struct {
-	seqcount_t		seq;
+	seqcount_raw_spinlock_t	seq;
 	struct timekeeper	timekeeper;
 } tk_core ____cacheline_aligned = {
-	.seq = SEQCNT_ZERO(tk_core.seq),
+	.seq = SEQCNT_RAW_SPINLOCK_ZERO(tk_core.seq, &timekeeper_lock),
 };
 
-static DEFINE_RAW_SPINLOCK(timekeeper_lock);
 static struct timekeeper shadow_timekeeper;
 
 /**
@@ -63,7 +64,7 @@ static struct timekeeper shadow_timekeeper;
  * See @update_fast_timekeeper() below.
  */
 struct tk_fast {
-	seqcount_t		seq;
+	seqcount_raw_spinlock_t	seq;
 	struct tk_read_base	base[2];
 };
 
@@ -80,11 +81,13 @@ static struct clocksource dummy_clock = {
 };
 
 static struct tk_fast tk_fast_mono ____cacheline_aligned = {
+	.seq     = SEQCNT_RAW_SPINLOCK_ZERO(tk_fast_mono.seq, &timekeeper_lock),
 	.base[0] = { .clock = &dummy_clock, },
 	.base[1] = { .clock = &dummy_clock, },
 };
 
 static struct tk_fast tk_fast_raw  ____cacheline_aligned = {
+	.seq     = SEQCNT_RAW_SPINLOCK_ZERO(tk_fast_raw.seq, &timekeeper_lock),
 	.base[0] = { .clock = &dummy_clock, },
 	.base[1] = { .clock = &dummy_clock, },
 };
@@ -157,7 +160,7 @@ static inline void tk_update_sleep_time(struct timekeeper *tk, ktime_t delta)
  * tk_clock_read - atomic clocksource read() helper
  *
  * This helper is necessary to use in the read paths because, while the
- * seqlock ensures we don't return a bad value while structures are updated,
+ * seqcount ensures we don't return a bad value while structures are updated,
  * it doesn't protect from potential crashes. There is the possibility that
  * the tkr's clocksource may change between the read reference, and the
  * clock reference passed to the read function.  This can cause crashes if
@@ -222,10 +225,10 @@ static inline u64 timekeeping_get_delta(const struct tk_read_base *tkr)
 	unsigned int seq;
 
 	/*
-	 * Since we're called holding a seqlock, the data may shift
+	 * Since we're called holding a seqcount, the data may shift
 	 * under us while we're doing the calculation. This can cause
 	 * false positives, since we'd note a problem but throw the
-	 * results away. So nest another seqlock here to atomically
+	 * results away. So nest another seqcount here to atomically
 	 * grab the points we are checking with.
 	 */
 	do {
@@ -486,7 +489,7 @@ EXPORT_SYMBOL_GPL(ktime_get_raw_fast_ns);
  *
  * To keep it NMI safe since we're accessing from tracing, we're not using a
  * separate timekeeper with updates to monotonic clock and boot offset
- * protected with seqlocks. This has the following minor side effects:
+ * protected with seqcounts. This has the following minor side effects:
  *
  * (1) Its possible that a timestamp be taken after the boot offset is updated
  * but before the timekeeper is updated. If this happens, the new boot offset
@@ -953,7 +956,7 @@ EXPORT_SYMBOL_GPL(ktime_get_real_seconds);
  * but without the sequence counter protect. This internal function
  * is called just when timekeeping lock is already held.
  */
-time64_t __ktime_get_real_seconds(void)
+noinstr time64_t __ktime_get_real_seconds(void)
 {
 	struct timekeeper *tk = &tk_core.timekeeper;
 
@@ -1005,9 +1008,8 @@ static int scale64_check_overflow(u64 mult, u64 div, u64 *base)
 	    ((int)sizeof(u64)*8 - fls64(mult) < fls64(rem)))
 		return -EOVERFLOW;
 	tmp *= mult;
-	rem *= mult;
 
-	do_div(rem, div);
+	rem = div64_u64(rem * mult, div);
 	*base = tmp + rem;
 	return 0;
 }
@@ -2002,7 +2004,7 @@ static inline unsigned int accumulate_nsecs_to_secs(struct timekeeper *tk)
  * logarithmic_accumulation - shifted accumulation of cycles
  *
  * This functions accumulates a shifted interval of cycles into
- * into a shifted interval nanoseconds. Allows for O(log) accumulation
+ * a shifted interval nanoseconds. Allows for O(log) accumulation
  * loop.
  *
  * Returns the unconsumed cycles.
@@ -2194,7 +2196,7 @@ EXPORT_SYMBOL(ktime_get_coarse_ts64);
 void do_timer(unsigned long ticks)
 {
 	jiffies_64 += ticks;
-	calc_global_load(ticks);
+	calc_global_load();
 }
 
 /**
@@ -2397,8 +2399,10 @@ EXPORT_SYMBOL(hardpps);
  */
 void xtime_update(unsigned long ticks)
 {
-	write_seqlock(&jiffies_lock);
+	raw_spin_lock(&jiffies_lock);
+	write_seqcount_begin(&jiffies_seq);
 	do_timer(ticks);
-	write_sequnlock(&jiffies_lock);
+	write_seqcount_end(&jiffies_seq);
+	raw_spin_unlock(&jiffies_lock);
 	update_wall_time();
 }
diff --git a/kernel/time/timekeeping.h b/kernel/time/timekeeping.h
index 141ab3ab0354..099737f6f10c 100644
--- a/kernel/time/timekeeping.h
+++ b/kernel/time/timekeeping.h
@@ -25,7 +25,8 @@ static inline void sched_clock_resume(void) { }
 extern void do_timer(unsigned long ticks);
 extern void update_wall_time(void);
 
-extern seqlock_t jiffies_lock;
+extern raw_spinlock_t jiffies_lock;
+extern seqcount_t jiffies_seq;
 
 #define CS_NAME_LEN	32
 
diff --git a/kernel/time/timekeeping_internal.h b/kernel/time/timekeeping_internal.h
index bcbb52db2256..4ca2787d1642 100644
--- a/kernel/time/timekeeping_internal.h
+++ b/kernel/time/timekeeping_internal.h
@@ -1,12 +1,14 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _TIMEKEEPING_INTERNAL_H
 #define _TIMEKEEPING_INTERNAL_H
-/*
- * timekeeping debug functions
- */
+
 #include <linux/clocksource.h>
+#include <linux/spinlock.h>
 #include <linux/time.h>
 
+/*
+ * timekeeping debug functions
+ */
 #ifdef CONFIG_DEBUG_FS
 extern void tk_debug_account_sleep_time(const struct timespec64 *t);
 #else
@@ -31,4 +33,7 @@ static inline u64 clocksource_delta(u64 now, u64 last, u64 mask)
 }
 #endif
 
+/* Semi public for serialization of non timekeeper VDSO updates. */
+extern raw_spinlock_t timekeeper_lock;
+
 #endif /* _TIMEKEEPING_INTERNAL_H */
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index 4820823515e9..a50364df1054 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -43,6 +43,7 @@
 #include <linux/sched/debug.h>
 #include <linux/slab.h>
 #include <linux/compat.h>
+#include <linux/random.h>
 
 #include <linux/uaccess.h>
 #include <asm/unistd.h>
@@ -156,7 +157,8 @@ EXPORT_SYMBOL(jiffies_64);
 
 /*
  * The time start value for each level to select the bucket at enqueue
- * time.
+ * time. We start from the last possible delta of the previous level
+ * so that we can later add an extra LVL_GRAN(n) to n (see calc_index()).
  */
 #define LVL_START(n)	((LVL_SIZE - 1) << (((n) - 1) * LVL_CLK_SHIFT))
 
@@ -203,8 +205,8 @@ struct timer_base {
 	unsigned long		clk;
 	unsigned long		next_expiry;
 	unsigned int		cpu;
+	bool			next_expiry_recalc;
 	bool			is_idle;
-	bool			must_forward_clk;
 	DECLARE_BITMAP(pending_map, WHEEL_SIZE);
 	struct hlist_head	vectors[WHEEL_SIZE];
 } ____cacheline_aligned;
@@ -249,8 +251,7 @@ void timers_update_nohz(void)
 }
 
 int timer_migration_handler(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;
 
@@ -488,71 +489,61 @@ static inline void timer_set_idx(struct timer_list *timer, unsigned int idx)
  * Helper function to calculate the array index for a given expiry
  * time.
  */
-static inline unsigned calc_index(unsigned expires, unsigned lvl)
+static inline unsigned calc_index(unsigned long expires, unsigned lvl,
+				  unsigned long *bucket_expiry)
 {
+
+	/*
+	 * The timer wheel has to guarantee that a timer does not fire
+	 * early. Early expiry can happen due to:
+	 * - Timer is armed at the edge of a tick
+	 * - Truncation of the expiry time in the outer wheel levels
+	 *
+	 * Round up with level granularity to prevent this.
+	 */
 	expires = (expires + LVL_GRAN(lvl)) >> LVL_SHIFT(lvl);
+	*bucket_expiry = expires << LVL_SHIFT(lvl);
 	return LVL_OFFS(lvl) + (expires & LVL_MASK);
 }
 
-static int calc_wheel_index(unsigned long expires, unsigned long clk)
+static int calc_wheel_index(unsigned long expires, unsigned long clk,
+			    unsigned long *bucket_expiry)
 {
 	unsigned long delta = expires - clk;
 	unsigned int idx;
 
 	if (delta < LVL_START(1)) {
-		idx = calc_index(expires, 0);
+		idx = calc_index(expires, 0, bucket_expiry);
 	} else if (delta < LVL_START(2)) {
-		idx = calc_index(expires, 1);
+		idx = calc_index(expires, 1, bucket_expiry);
 	} else if (delta < LVL_START(3)) {
-		idx = calc_index(expires, 2);
+		idx = calc_index(expires, 2, bucket_expiry);
 	} else if (delta < LVL_START(4)) {
-		idx = calc_index(expires, 3);
+		idx = calc_index(expires, 3, bucket_expiry);
 	} else if (delta < LVL_START(5)) {
-		idx = calc_index(expires, 4);
+		idx = calc_index(expires, 4, bucket_expiry);
 	} else if (delta < LVL_START(6)) {
-		idx = calc_index(expires, 5);
+		idx = calc_index(expires, 5, bucket_expiry);
 	} else if (delta < LVL_START(7)) {
-		idx = calc_index(expires, 6);
+		idx = calc_index(expires, 6, bucket_expiry);
 	} else if (LVL_DEPTH > 8 && delta < LVL_START(8)) {
-		idx = calc_index(expires, 7);
+		idx = calc_index(expires, 7, bucket_expiry);
 	} else if ((long) delta < 0) {
 		idx = clk & LVL_MASK;
+		*bucket_expiry = clk;
 	} else {
 		/*
 		 * Force expire obscene large timeouts to expire at the
 		 * capacity limit of the wheel.
 		 */
-		if (expires >= WHEEL_TIMEOUT_CUTOFF)
-			expires = WHEEL_TIMEOUT_MAX;
+		if (delta >= WHEEL_TIMEOUT_CUTOFF)
+			expires = clk + WHEEL_TIMEOUT_MAX;
 
-		idx = calc_index(expires, LVL_DEPTH - 1);
+		idx = calc_index(expires, LVL_DEPTH - 1, bucket_expiry);
 	}
 	return idx;
 }
 
-/*
- * Enqueue the timer into the hash bucket, mark it pending in
- * the bitmap and store the index in the timer flags.
- */
-static void enqueue_timer(struct timer_base *base, struct timer_list *timer,
-			  unsigned int idx)
-{
-	hlist_add_head(&timer->entry, base->vectors + idx);
-	__set_bit(idx, base->pending_map);
-	timer_set_idx(timer, idx);
-
-	trace_timer_start(timer, timer->expires, timer->flags);
-}
-
-static void
-__internal_add_timer(struct timer_base *base, struct timer_list *timer)
-{
-	unsigned int idx;
-
-	idx = calc_wheel_index(timer->expires, base->clk);
-	enqueue_timer(base, timer, idx);
-}
-
 static void
 trigger_dyntick_cpu(struct timer_base *base, struct timer_list *timer)
 {
@@ -574,26 +565,48 @@ trigger_dyntick_cpu(struct timer_base *base, struct timer_list *timer)
 	 * timer is not deferrable. If the other CPU is on the way to idle
 	 * then it can't set base->is_idle as we hold the base lock:
 	 */
-	if (!base->is_idle)
-		return;
+	if (base->is_idle)
+		wake_up_nohz_cpu(base->cpu);
+}
 
-	/* Check whether this is the new first expiring timer: */
-	if (time_after_eq(timer->expires, base->next_expiry))
-		return;
+/*
+ * Enqueue the timer into the hash bucket, mark it pending in
+ * the bitmap, store the index in the timer flags then wake up
+ * the target CPU if needed.
+ */
+static void enqueue_timer(struct timer_base *base, struct timer_list *timer,
+			  unsigned int idx, unsigned long bucket_expiry)
+{
+
+	hlist_add_head(&timer->entry, base->vectors + idx);
+	__set_bit(idx, base->pending_map);
+	timer_set_idx(timer, idx);
+
+	trace_timer_start(timer, timer->expires, timer->flags);
 
 	/*
-	 * Set the next expiry time and kick the CPU so it can reevaluate the
-	 * wheel:
+	 * Check whether this is the new first expiring timer. The
+	 * effective expiry time of the timer is required here
+	 * (bucket_expiry) instead of timer->expires.
 	 */
-	base->next_expiry = timer->expires;
-	wake_up_nohz_cpu(base->cpu);
+	if (time_before(bucket_expiry, base->next_expiry)) {
+		/*
+		 * Set the next expiry time and kick the CPU so it
+		 * can reevaluate the wheel:
+		 */
+		base->next_expiry = bucket_expiry;
+		base->next_expiry_recalc = false;
+		trigger_dyntick_cpu(base, timer);
+	}
 }
 
-static void
-internal_add_timer(struct timer_base *base, struct timer_list *timer)
+static void internal_add_timer(struct timer_base *base, struct timer_list *timer)
 {
-	__internal_add_timer(base, timer);
-	trigger_dyntick_cpu(base, timer);
+	unsigned long bucket_expiry;
+	unsigned int idx;
+
+	idx = calc_wheel_index(timer->expires, base->clk, &bucket_expiry);
+	enqueue_timer(base, timer, idx, bucket_expiry);
 }
 
 #ifdef CONFIG_DEBUG_OBJECTS_TIMERS
@@ -653,7 +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;
 	}
@@ -826,8 +839,10 @@ static int detach_if_pending(struct timer_list *timer, struct timer_base *base,
 	if (!timer_pending(timer))
 		return 0;
 
-	if (hlist_is_singular_node(&timer->entry, base->vectors + idx))
+	if (hlist_is_singular_node(&timer->entry, base->vectors + idx)) {
 		__clear_bit(idx, base->pending_map);
+		base->next_expiry_recalc = true;
+	}
 
 	detach_timer(timer, clear_pending);
 	return 1;
@@ -877,31 +892,27 @@ get_target_base(struct timer_base *base, unsigned tflags)
 
 static inline void forward_timer_base(struct timer_base *base)
 {
-#ifdef CONFIG_NO_HZ_COMMON
-	unsigned long jnow;
+	unsigned long jnow = READ_ONCE(jiffies);
 
 	/*
-	 * We only forward the base when we are idle or have just come out of
-	 * idle (must_forward_clk logic), and have a delta between base clock
-	 * and jiffies. In the common case, run_timers will take care of it.
+	 * No need to forward if we are close enough below jiffies.
+	 * Also while executing timers, base->clk is 1 offset ahead
+	 * of jiffies to avoid endless requeuing to current jffies.
 	 */
-	if (likely(!base->must_forward_clk))
-		return;
-
-	jnow = READ_ONCE(jiffies);
-	base->must_forward_clk = base->is_idle;
-	if ((long)(jnow - base->clk) < 2)
+	if ((long)(jnow - base->clk) < 1)
 		return;
 
 	/*
 	 * If the next expiry value is > jiffies, then we fast forward to
 	 * jiffies otherwise we forward to the next expiry value.
 	 */
-	if (time_after(base->next_expiry, jnow))
+	if (time_after(base->next_expiry, jnow)) {
 		base->clk = jnow;
-	else
+	} else {
+		if (WARN_ON_ONCE(time_before(base->next_expiry, base->clk)))
+			return;
 		base->clk = base->next_expiry;
-#endif
+	}
 }
 
 
@@ -944,13 +955,14 @@ static struct timer_base *lock_timer_base(struct timer_list *timer,
 
 #define MOD_TIMER_PENDING_ONLY		0x01
 #define MOD_TIMER_REDUCE		0x02
+#define MOD_TIMER_NOTPENDING		0x04
 
 static inline int
 __mod_timer(struct timer_list *timer, unsigned long expires, unsigned int options)
 {
+	unsigned long clk = 0, flags, bucket_expiry;
 	struct timer_base *base, *new_base;
 	unsigned int idx = UINT_MAX;
-	unsigned long clk = 0, flags;
 	int ret = 0;
 
 	BUG_ON(!timer->function);
@@ -960,7 +972,7 @@ __mod_timer(struct timer_list *timer, unsigned long expires, unsigned int option
 	 * the timer is re-modified to have the same timeout or ends up in the
 	 * same array bucket then just return:
 	 */
-	if (timer_pending(timer)) {
+	if (!(options & MOD_TIMER_NOTPENDING) && timer_pending(timer)) {
 		/*
 		 * The downside of this optimization is that it can result in
 		 * larger granularity than you would get from adding a new
@@ -989,7 +1001,7 @@ __mod_timer(struct timer_list *timer, unsigned long expires, unsigned int option
 		}
 
 		clk = base->clk;
-		idx = calc_wheel_index(expires, clk);
+		idx = calc_wheel_index(expires, clk, &bucket_expiry);
 
 		/*
 		 * Retrieve and compare the array index of the pending
@@ -1042,16 +1054,13 @@ __mod_timer(struct timer_list *timer, unsigned long expires, unsigned int option
 	/*
 	 * If 'idx' was calculated above and the base time did not advance
 	 * between calculating 'idx' and possibly switching the base, only
-	 * enqueue_timer() and trigger_dyntick_cpu() is required. Otherwise
-	 * we need to (re)calculate the wheel index via
-	 * internal_add_timer().
+	 * enqueue_timer() is required. Otherwise we need to (re)calculate
+	 * the wheel index via internal_add_timer().
 	 */
-	if (idx != UINT_MAX && clk == base->clk) {
-		enqueue_timer(base, timer, idx);
-		trigger_dyntick_cpu(base, timer);
-	} else {
+	if (idx != UINT_MAX && clk == base->clk)
+		enqueue_timer(base, timer, idx, bucket_expiry);
+	else
 		internal_add_timer(base, timer);
-	}
 
 out_unlock:
 	raw_spin_unlock_irqrestore(&base->lock, flags);
@@ -1133,7 +1142,7 @@ EXPORT_SYMBOL(timer_reduce);
 void add_timer(struct timer_list *timer)
 {
 	BUG_ON(timer_pending(timer));
-	mod_timer(timer, timer->expires);
+	__mod_timer(timer, timer->expires, MOD_TIMER_NOTPENDING);
 }
 EXPORT_SYMBOL(add_timer);
 
@@ -1454,10 +1463,10 @@ static void expire_timers(struct timer_base *base, struct hlist_head *head)
 	}
 }
 
-static int __collect_expired_timers(struct timer_base *base,
-				    struct hlist_head *heads)
+static int collect_expired_timers(struct timer_base *base,
+				  struct hlist_head *heads)
 {
-	unsigned long clk = base->clk;
+	unsigned long clk = base->clk = base->next_expiry;
 	struct hlist_head *vec;
 	int i, levels = 0;
 	unsigned int idx;
@@ -1479,7 +1488,6 @@ static int __collect_expired_timers(struct timer_base *base,
 	return levels;
 }
 
-#ifdef CONFIG_NO_HZ_COMMON
 /*
  * Find the next pending bucket of a level. Search from level start (@offset)
  * + @clk upwards and if nothing there, search from start of the level
@@ -1512,6 +1520,7 @@ static unsigned long __next_timer_interrupt(struct timer_base *base)
 	clk = base->clk;
 	for (lvl = 0; lvl < LVL_DEPTH; lvl++, offset += LVL_SIZE) {
 		int pos = next_pending_bucket(base, offset, clk & LVL_MASK);
+		unsigned long lvl_clk = clk & LVL_CLK_MASK;
 
 		if (pos >= 0) {
 			unsigned long tmp = clk + (unsigned long) pos;
@@ -1519,6 +1528,13 @@ static unsigned long __next_timer_interrupt(struct timer_base *base)
 			tmp <<= LVL_SHIFT(lvl);
 			if (time_before(tmp, next))
 				next = tmp;
+
+			/*
+			 * If the next expiration happens before we reach
+			 * the next level, no need to check further.
+			 */
+			if (pos <= ((LVL_CLK_DIV - lvl_clk) & LVL_CLK_MASK))
+				break;
 		}
 		/*
 		 * Clock for the next level. If the current level clock lower
@@ -1556,13 +1572,17 @@ static unsigned long __next_timer_interrupt(struct timer_base *base)
 		 * So the simple check whether the lower bits of the current
 		 * level are 0 or not is sufficient for all cases.
 		 */
-		adj = clk & LVL_CLK_MASK ? 1 : 0;
+		adj = lvl_clk ? 1 : 0;
 		clk >>= LVL_CLK_SHIFT;
 		clk += adj;
 	}
+
+	base->next_expiry_recalc = false;
+
 	return next;
 }
 
+#ifdef CONFIG_NO_HZ_COMMON
 /*
  * Check, if the next hrtimer event is before the next timer wheel
  * event:
@@ -1619,9 +1639,11 @@ u64 get_next_timer_interrupt(unsigned long basej, u64 basem)
 		return expires;
 
 	raw_spin_lock(&base->lock);
-	nextevt = __next_timer_interrupt(base);
+	if (base->next_expiry_recalc)
+		base->next_expiry = __next_timer_interrupt(base);
+	nextevt = base->next_expiry;
 	is_max_delta = (nextevt == base->clk + NEXT_TIMER_MAX_DELTA);
-	base->next_expiry = nextevt;
+
 	/*
 	 * We have a fresh next event. Check whether we can forward the
 	 * base. We can only do that when @basej is past base->clk
@@ -1647,10 +1669,8 @@ u64 get_next_timer_interrupt(unsigned long basej, u64 basem)
 		 * logic is only maintained for the BASE_STD base, deferrable
 		 * timers may still see large granularity skew (by design).
 		 */
-		if ((expires - basem) > TICK_NSEC) {
-			base->must_forward_clk = true;
+		if ((expires - basem) > TICK_NSEC)
 			base->is_idle = true;
-		}
 	}
 	raw_spin_unlock(&base->lock);
 
@@ -1674,42 +1694,6 @@ void timer_clear_idle(void)
 	 */
 	base->is_idle = false;
 }
-
-static int collect_expired_timers(struct timer_base *base,
-				  struct hlist_head *heads)
-{
-	unsigned long now = READ_ONCE(jiffies);
-
-	/*
-	 * NOHZ optimization. After a long idle sleep we need to forward the
-	 * base to current jiffies. Avoid a loop by searching the bitfield for
-	 * the next expiring timer.
-	 */
-	if ((long)(now - base->clk) > 2) {
-		unsigned long next = __next_timer_interrupt(base);
-
-		/*
-		 * If the next timer is ahead of time forward to current
-		 * jiffies, otherwise forward to the next expiry time:
-		 */
-		if (time_after(next, now)) {
-			/*
-			 * The call site will increment base->clk and then
-			 * terminate the expiry loop immediately.
-			 */
-			base->clk = now;
-			return 0;
-		}
-		base->clk = next;
-	}
-	return __collect_expired_timers(base, heads);
-}
-#else
-static inline int collect_expired_timers(struct timer_base *base,
-					 struct hlist_head *heads)
-{
-	return __collect_expired_timers(base, heads);
-}
 #endif
 
 /*
@@ -1731,6 +1715,13 @@ void update_process_times(int user_tick)
 	scheduler_tick();
 	if (IS_ENABLED(CONFIG_POSIX_TIMERS))
 		run_posix_cpu_timers();
+
+	/* The current CPU might make use of net randoms without receiving IRQs
+	 * to renew them often enough. Let's update the net_rand_state from a
+	 * non-constant value that's not affine to the number of calls to make
+	 * sure it's updated when there's some activity (we don't care in idle).
+	 */
+	this_cpu_add(net_rand_state.s1, rol32(jiffies, 24) + user_tick);
 }
 
 /**
@@ -1742,32 +1733,23 @@ static inline void __run_timers(struct timer_base *base)
 	struct hlist_head heads[LVL_DEPTH];
 	int levels;
 
-	if (!time_after_eq(jiffies, base->clk))
+	if (time_before(jiffies, base->next_expiry))
 		return;
 
 	timer_base_lock_expiry(base);
 	raw_spin_lock_irq(&base->lock);
 
-	/*
-	 * timer_base::must_forward_clk must be cleared before running
-	 * timers so that any timer functions that call mod_timer() will
-	 * not try to forward the base. Idle tracking / clock forwarding
-	 * logic is only used with BASE_STD timers.
-	 *
-	 * The must_forward_clk flag is cleared unconditionally also for
-	 * the deferrable base. The deferrable base is not affected by idle
-	 * tracking and never forwarded, so clearing the flag is a NOOP.
-	 *
-	 * The fact that the deferrable base is never forwarded can cause
-	 * large variations in granularity for deferrable timers, but they
-	 * can be deferred for long periods due to idle anyway.
-	 */
-	base->must_forward_clk = false;
-
-	while (time_after_eq(jiffies, base->clk)) {
-
+	while (time_after_eq(jiffies, base->clk) &&
+	       time_after_eq(jiffies, base->next_expiry)) {
 		levels = collect_expired_timers(base, heads);
+		/*
+		 * The only possible reason for not finding any expired
+		 * timer at this clk is that all matching timers have been
+		 * dequeued.
+		 */
+		WARN_ON_ONCE(!levels && !base->next_expiry_recalc);
 		base->clk++;
+		base->next_expiry = __next_timer_interrupt(base);
 
 		while (levels--)
 			expire_timers(base, heads + levels);
@@ -1797,12 +1779,12 @@ void run_local_timers(void)
 
 	hrtimer_run_queues();
 	/* Raise the softirq only if required. */
-	if (time_before(jiffies, base->clk)) {
+	if (time_before(jiffies, base->next_expiry)) {
 		if (!IS_ENABLED(CONFIG_NO_HZ_COMMON))
 			return;
 		/* CPU is awake, so check the deferrable base. */
 		base++;
-		if (time_before(jiffies, base->clk))
+		if (time_before(jiffies, base->next_expiry))
 			return;
 	}
 	raise_softirq(TIMER_SOFTIRQ);
@@ -1828,21 +1810,23 @@ static void process_timeout(struct timer_list *t)
  * schedule_timeout - sleep until timeout
  * @timeout: timeout value in jiffies
  *
- * Make the current task sleep until @timeout jiffies have
- * elapsed. The routine will return immediately unless
- * the current task state has been set (see set_current_state()).
+ * Make the current task sleep until @timeout jiffies have elapsed.
+ * The function behavior depends on the current task state
+ * (see also set_current_state() description):
  *
- * You can set the task state as follows -
+ * %TASK_RUNNING - the scheduler is called, but the task does not sleep
+ * at all. That happens because sched_submit_work() does nothing for
+ * tasks in %TASK_RUNNING state.
  *
  * %TASK_UNINTERRUPTIBLE - at least @timeout jiffies are guaranteed to
  * pass before the routine returns unless the current task is explicitly
- * woken up, (e.g. by wake_up_process())".
+ * woken up, (e.g. by wake_up_process()).
  *
  * %TASK_INTERRUPTIBLE - the routine may return early if a signal is
  * delivered to the current task or the current task is explicitly woken
  * up.
  *
- * The current task state is guaranteed to be TASK_RUNNING when this
+ * The current task state is guaranteed to be %TASK_RUNNING when this
  * routine returns.
  *
  * Specifying a @timeout value of %MAX_SCHEDULE_TIMEOUT will schedule
@@ -1850,7 +1834,7 @@ static void process_timeout(struct timer_list *t)
  * value will be %MAX_SCHEDULE_TIMEOUT.
  *
  * Returns 0 when the timer has expired otherwise the remaining time in
- * jiffies will be returned.  In all cases the return value is guaranteed
+ * jiffies will be returned. In all cases the return value is guaranteed
  * to be non-negative.
  */
 signed long __sched schedule_timeout(signed long timeout)
@@ -1891,7 +1875,7 @@ signed long __sched schedule_timeout(signed long timeout)
 
 	timer.task = current;
 	timer_setup_on_stack(&timer.timer, process_timeout, 0);
-	__mod_timer(&timer.timer, expire, 0);
+	__mod_timer(&timer.timer, expire, MOD_TIMER_NOTPENDING);
 	schedule();
 	del_singleshot_timer_sync(&timer.timer);
 
@@ -1965,7 +1949,6 @@ int timers_prepare_cpu(unsigned int cpu)
 		base->clk = jiffies;
 		base->next_expiry = base->clk + NEXT_TIMER_MAX_DELTA;
 		base->is_idle = false;
-		base->must_forward_clk = true;
 	}
 	return 0;
 }
@@ -2018,6 +2001,7 @@ static void __init init_timer_cpu(int cpu)
 		base->cpu = cpu;
 		raw_spin_lock_init(&base->lock);
 		base->clk = jiffies;
+		base->next_expiry = base->clk + NEXT_TIMER_MAX_DELTA;
 		timer_base_init_expiry_lock(base);
 	}
 }
@@ -2033,6 +2017,7 @@ static void __init init_timer_cpus(void)
 void __init init_timers(void)
 {
 	init_timer_cpus();
+	posix_cputimers_init_work();
 	open_softirq(TIMER_SOFTIRQ, run_timer_softirq);
 }
 
diff --git a/kernel/time/vsyscall.c b/kernel/time/vsyscall.c
index 9577c89179cd..88e6b8ed6ca5 100644
--- a/kernel/time/vsyscall.c
+++ b/kernel/time/vsyscall.c
@@ -13,6 +13,8 @@
 #include <vdso/helpers.h>
 #include <vdso/vsyscall.h>
 
+#include "timekeeping_internal.h"
+
 static inline void update_vdso_data(struct vdso_data *vdata,
 				    struct timekeeper *tk)
 {
@@ -71,13 +73,15 @@ void update_vsyscall(struct timekeeper *tk)
 {
 	struct vdso_data *vdata = __arch_get_k_vdso_data();
 	struct vdso_timestamp *vdso_ts;
+	s32 clock_mode;
 	u64 nsec;
 
 	/* copy vsyscall data */
 	vdso_write_begin(vdata);
 
-	vdata[CS_HRES_COARSE].clock_mode	= __arch_get_clock_mode(tk);
-	vdata[CS_RAW].clock_mode		= __arch_get_clock_mode(tk);
+	clock_mode = tk->tkr_mono.clock->vdso_clock_mode;
+	vdata[CS_HRES_COARSE].clock_mode	= clock_mode;
+	vdata[CS_RAW].clock_mode		= clock_mode;
 
 	/* CLOCK_REALTIME also required for time() */
 	vdso_ts		= &vdata[CS_HRES_COARSE].basetime[CLOCK_REALTIME];
@@ -103,10 +107,10 @@ void update_vsyscall(struct timekeeper *tk)
 	WRITE_ONCE(vdata[CS_HRES_COARSE].hrtimer_res, hrtimer_resolution);
 
 	/*
-	 * Architectures can opt out of updating the high resolution part
-	 * of the VDSO.
+	 * If the current clocksource is not VDSO capable, then spare the
+	 * update of the high reolution parts.
 	 */
-	if (__arch_update_vdso_data())
+	if (clock_mode != VDSO_CLOCKMODE_NONE)
 		update_vdso_data(vdata, tk);
 
 	__arch_update_vsyscall(vdata, tk);
@@ -125,3 +129,42 @@ void update_vsyscall_tz(void)
 
 	__arch_sync_vdso_data(vdata);
 }
+
+/**
+ * vdso_update_begin - Start of a VDSO update section
+ *
+ * Allows architecture code to safely update the architecture specific VDSO
+ * data. Disables interrupts, acquires timekeeper lock to serialize against
+ * concurrent updates from timekeeping and invalidates the VDSO data
+ * sequence counter to prevent concurrent readers from accessing
+ * inconsistent data.
+ *
+ * Returns: Saved interrupt flags which need to be handed in to
+ * vdso_update_end().
+ */
+unsigned long vdso_update_begin(void)
+{
+	struct vdso_data *vdata = __arch_get_k_vdso_data();
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&timekeeper_lock, flags);
+	vdso_write_begin(vdata);
+	return flags;
+}
+
+/**
+ * vdso_update_end - End of a VDSO update section
+ * @flags:	Interrupt flags as returned from vdso_update_begin()
+ *
+ * Pairs with vdso_update_begin(). Marks vdso data consistent, invokes data
+ * synchronization if the architecture requires it, drops timekeeper lock
+ * and restores interrupt flags.
+ */
+void vdso_update_end(unsigned long flags)
+{
+	struct vdso_data *vdata = __arch_get_k_vdso_data();
+
+	vdso_write_end(vdata);
+	__arch_sync_vdso_data(vdata);
+	raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
+}
diff --git a/kernel/torture.c b/kernel/torture.c
index 7c13f5558b71..1061492f14bd 100644
--- a/kernel/torture.c
+++ b/kernel/torture.c
@@ -42,6 +42,12 @@
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Paul E. McKenney <paulmck@linux.ibm.com>");
 
+static bool disable_onoff_at_boot;
+module_param(disable_onoff_at_boot, bool, 0444);
+
+static bool ftrace_dump_at_shutdown;
+module_param(ftrace_dump_at_shutdown, bool, 0444);
+
 static char *torture_type;
 static int verbose;
 
@@ -84,6 +90,7 @@ bool torture_offline(int cpu, long *n_offl_attempts, long *n_offl_successes,
 {
 	unsigned long delta;
 	int ret;
+	char *s;
 	unsigned long starttime;
 
 	if (!cpu_online(cpu) || !cpu_is_hotpluggable(cpu))
@@ -97,12 +104,18 @@ bool torture_offline(int cpu, long *n_offl_attempts, long *n_offl_successes,
 			 torture_type, cpu);
 	starttime = jiffies;
 	(*n_offl_attempts)++;
-	ret = cpu_down(cpu);
+	ret = remove_cpu(cpu);
 	if (ret) {
+		s = "";
+		if (!rcu_inkernel_boot_has_ended() && ret == -EBUSY) {
+			// PCI probe frequently disables hotplug during boot.
+			(*n_offl_attempts)--;
+			s = " (-EBUSY forgiven during boot)";
+		}
 		if (verbose)
 			pr_alert("%s" TORTURE_FLAG
-				 "torture_onoff task: offline %d failed: errno %d\n",
-				 torture_type, cpu, ret);
+				 "torture_onoff task: offline %d failed%s: errno %d\n",
+				 torture_type, cpu, s, ret);
 	} else {
 		if (verbose > 1)
 			pr_alert("%s" TORTURE_FLAG
@@ -137,6 +150,7 @@ bool torture_online(int cpu, long *n_onl_attempts, long *n_onl_successes,
 {
 	unsigned long delta;
 	int ret;
+	char *s;
 	unsigned long starttime;
 
 	if (cpu_online(cpu) || !cpu_is_hotpluggable(cpu))
@@ -148,12 +162,18 @@ bool torture_online(int cpu, long *n_onl_attempts, long *n_onl_successes,
 			 torture_type, cpu);
 	starttime = jiffies;
 	(*n_onl_attempts)++;
-	ret = cpu_up(cpu);
+	ret = add_cpu(cpu);
 	if (ret) {
+		s = "";
+		if (!rcu_inkernel_boot_has_ended() && ret == -EBUSY) {
+			// PCI probe frequently disables hotplug during boot.
+			(*n_onl_attempts)--;
+			s = " (-EBUSY forgiven during boot)";
+		}
 		if (verbose)
 			pr_alert("%s" TORTURE_FLAG
-				 "torture_onoff task: online %d failed: errno %d\n",
-				 torture_type, cpu, ret);
+				 "torture_onoff task: online %d failed%s: errno %d\n",
+				 torture_type, cpu, s, ret);
 	} else {
 		if (verbose > 1)
 			pr_alert("%s" TORTURE_FLAG
@@ -192,17 +212,18 @@ torture_onoff(void *arg)
 	for_each_online_cpu(cpu)
 		maxcpu = cpu;
 	WARN_ON(maxcpu < 0);
-	if (!IS_MODULE(CONFIG_TORTURE_TEST))
+	if (!IS_MODULE(CONFIG_TORTURE_TEST)) {
 		for_each_possible_cpu(cpu) {
 			if (cpu_online(cpu))
 				continue;
-			ret = cpu_up(cpu);
+			ret = add_cpu(cpu);
 			if (ret && verbose) {
 				pr_alert("%s" TORTURE_FLAG
 					 "%s: Initial online %d: errno %d\n",
 					 __func__, torture_type, cpu, ret);
 			}
 		}
+	}
 
 	if (maxcpu == 0) {
 		VERBOSE_TOROUT_STRING("Only one CPU, so CPU-hotplug testing is disabled");
@@ -215,6 +236,10 @@ torture_onoff(void *arg)
 		VERBOSE_TOROUT_STRING("torture_onoff end holdoff");
 	}
 	while (!torture_must_stop()) {
+		if (disable_onoff_at_boot && !rcu_inkernel_boot_has_ended()) {
+			schedule_timeout_interruptible(HZ / 10);
+			continue;
+		}
 		cpu = (torture_random(&rand) >> 4) % (maxcpu + 1);
 		if (!torture_offline(cpu,
 				     &n_offline_attempts, &n_offline_successes,
@@ -505,7 +530,8 @@ static int torture_shutdown(void *arg)
 		torture_shutdown_hook();
 	else
 		VERBOSE_TOROUT_STRING("No torture_shutdown_hook(), skipping.");
-	rcu_ftrace_dump(DUMP_ALL);
+	if (ftrace_dump_at_shutdown)
+		rcu_ftrace_dump(DUMP_ALL);
 	kernel_power_off();	/* Shut down the system. */
 	return 0;
 }
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 402eef84c859..a4020c0b4508 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -10,11 +10,6 @@ config USER_STACKTRACE_SUPPORT
 config NOP_TRACER
 	bool
 
-config HAVE_FTRACE_NMI_ENTER
-	bool
-	help
-	  See Documentation/trace/ftrace-design.rst
-
 config HAVE_FUNCTION_TRACER
 	bool
 	help
@@ -72,11 +67,6 @@ config RING_BUFFER
 	select TRACE_CLOCK
 	select IRQ_WORK
 
-config FTRACE_NMI_ENTER
-       bool
-       depends on HAVE_FTRACE_NMI_ENTER
-       default y
-
 config EVENT_TRACING
 	select CONTEXT_SWITCH_TRACER
 	select GLOB
@@ -158,6 +148,7 @@ config FUNCTION_TRACER
 	select CONTEXT_SWITCH_TRACER
 	select GLOB
 	select TASKS_RCU if PREEMPTION
+	select TASKS_RUDE_RCU
 	help
 	  Enable the kernel to trace every kernel function. This is done
 	  by using a compiler feature to insert a small, 5-byte No-Operation
@@ -258,15 +249,6 @@ config TRACE_PREEMPT_TOGGLE
 	  Enables hooks which will be called when preemption is first disabled,
 	  and last enabled.
 
-config PREEMPTIRQ_EVENTS
-	bool "Enable trace events for preempt and irq disable/enable"
-	select TRACE_IRQFLAGS
-	select TRACE_PREEMPT_TOGGLE if PREEMPTION
-	select GENERIC_TRACER
-	default n
-	help
-	  Enable tracing of disable and enable events for preemption and irqs.
-
 config IRQSOFF_TRACER
 	bool "Interrupts-off Latency Tracer"
 	default n
@@ -466,7 +448,6 @@ config PROFILE_ANNOTATED_BRANCHES
 config PROFILE_ALL_BRANCHES
 	bool "Profile all if conditionals" if !FORTIFY_SOURCE
 	select TRACE_BRANCH_PROFILING
-	imply CC_DISABLE_WARN_MAYBE_UNINITIALIZED  # avoid false positives
 	help
 	  This tracer profiles all branch conditions. Every if ()
 	  taken in the kernel is recorded whether it hit or miss.
@@ -624,12 +605,30 @@ config TRACING_MAP
 	  generally used outside of that context, and is normally
 	  selected by tracers that use it.
 
+config SYNTH_EVENTS
+	bool "Synthetic trace events"
+	select TRACING
+	select DYNAMIC_EVENTS
+	default n
+	help
+	  Synthetic events are user-defined trace events that can be
+	  used to combine data from other trace events or in fact any
+	  data source.  Synthetic events can be generated indirectly
+	  via the trace() action of histogram triggers or directly
+	  by way of an in-kernel API.
+
+	  See Documentation/trace/events.rst or
+	  Documentation/trace/histogram.rst for details and examples.
+
+	  If in doubt, say N.
+
 config HIST_TRIGGERS
 	bool "Histogram triggers"
 	depends on ARCH_HAVE_NMI_SAFE_CMPXCHG
 	select TRACING_MAP
 	select TRACING
 	select DYNAMIC_EVENTS
+	select SYNTH_EVENTS
 	default n
 	help
 	  Hist triggers allow one or more arbitrary trace event fields
@@ -825,7 +824,7 @@ config PREEMPTIRQ_DELAY_TEST
 
 config SYNTH_EVENT_GEN_TEST
 	tristate "Test module for in-kernel synthetic event generation"
-	depends on HIST_TRIGGERS
+	depends on SYNTH_EVENTS
 	help
           This option creates a test module to check the base
           functionality of in-kernel synthetic event definition and
@@ -848,6 +847,29 @@ config KPROBE_EVENT_GEN_TEST
 
 	  If unsure, say N.
 
+config HIST_TRIGGERS_DEBUG
+	bool "Hist trigger debug support"
+	depends on HIST_TRIGGERS
+	help
+          Add "hist_debug" file for each event, which when read will
+          dump out a bunch of internal details about the hist triggers
+          defined on that event.
+
+          The hist_debug file serves a couple of purposes:
+
+            - Helps developers verify that nothing is broken.
+
+            - Provides educational information to support the details
+              of the hist trigger internals as described by
+              Documentation/trace/histogram-design.rst.
+
+          The hist_debug output only covers the data structures
+          related to the histogram definitions themselves and doesn't
+          display the internals of map buckets or variable values of
+          running histograms.
+
+          If unsure, say N.
+
 endif # FTRACE
 
 endif # TRACING_SUPPORT
diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile
index f9dcd19165fa..e153be351548 100644
--- a/kernel/trace/Makefile
+++ b/kernel/trace/Makefile
@@ -2,9 +2,12 @@
 
 # Do not instrument the tracer itself:
 
+ccflags-remove-$(CONFIG_FUNCTION_TRACER) += $(CC_FLAGS_FTRACE)
+
 ifdef CONFIG_FUNCTION_TRACER
-ORIG_CFLAGS := $(KBUILD_CFLAGS)
-KBUILD_CFLAGS = $(subst $(CC_FLAGS_FTRACE),,$(ORIG_CFLAGS))
+
+# Avoid recursion due to instrumentation.
+KCSAN_SANITIZE := n
 
 ifdef CONFIG_FTRACE_SELFTEST
 # selftest needs instrumentation
@@ -28,6 +31,8 @@ ifdef CONFIG_GCOV_PROFILE_FTRACE
 GCOV_PROFILE := y
 endif
 
+CFLAGS_bpf_trace.o := -I$(src)
+
 CFLAGS_trace_benchmark.o := -I$(src)
 CFLAGS_trace_events_filter.o := -I$(src)
 
@@ -72,6 +77,7 @@ endif
 obj-$(CONFIG_EVENT_TRACING) += trace_events_filter.o
 obj-$(CONFIG_EVENT_TRACING) += trace_events_trigger.o
 obj-$(CONFIG_TRACE_EVENT_INJECT) += trace_events_inject.o
+obj-$(CONFIG_SYNTH_EVENTS) += trace_events_synth.o
 obj-$(CONFIG_HIST_TRIGGERS) += trace_events_hist.o
 obj-$(CONFIG_BPF_EVENTS) += bpf_trace.o
 obj-$(CONFIG_KPROBE_EVENTS) += trace_kprobe.o
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index ca39dc3230cb..4b3a42fc3b24 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -3,6 +3,9 @@
  * Copyright (C) 2006 Jens Axboe <axboe@kernel.dk>
  *
  */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/kernel.h>
 #include <linux/blkdev.h>
 #include <linux/blktrace_api.h>
@@ -170,10 +173,10 @@ void __trace_note_message(struct blk_trace *bt, struct blkcg *blkcg,
 	if (!(blk_tracer_flags.val & TRACE_BLK_OPT_CGROUP))
 		blkcg = NULL;
 #ifdef CONFIG_BLK_CGROUP
-	trace_note(bt, 0, BLK_TN_MESSAGE, buf, n,
+	trace_note(bt, current->pid, BLK_TN_MESSAGE, buf, n,
 		   blkcg ? cgroup_id(blkcg->css.cgroup) : 1);
 #else
-	trace_note(bt, 0, BLK_TN_MESSAGE, buf, n, 0);
+	trace_note(bt, current->pid, BLK_TN_MESSAGE, buf, n, 0);
 #endif
 	local_irq_restore(flags);
 }
@@ -344,7 +347,8 @@ static int __blk_trace_remove(struct request_queue *q)
 {
 	struct blk_trace *bt;
 
-	bt = xchg(&q->blk_trace, NULL);
+	bt = rcu_replace_pointer(q->blk_trace, NULL,
+				 lockdep_is_held(&q->debugfs_mutex));
 	if (!bt)
 		return -EINVAL;
 
@@ -358,9 +362,9 @@ int blk_trace_remove(struct request_queue *q)
 {
 	int ret;
 
-	mutex_lock(&q->blk_trace_mutex);
+	mutex_lock(&q->debugfs_mutex);
 	ret = __blk_trace_remove(q);
-	mutex_unlock(&q->blk_trace_mutex);
+	mutex_unlock(&q->debugfs_mutex);
 
 	return ret;
 }
@@ -479,12 +483,11 @@ static int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
 	struct dentry *dir = NULL;
 	int ret;
 
+	lockdep_assert_held(&q->debugfs_mutex);
+
 	if (!buts->buf_size || !buts->buf_nr)
 		return -EINVAL;
 
-	if (!blk_debugfs_root)
-		return -ENOENT;
-
 	strncpy(buts->name, name, BLKTRACE_BDEV_SIZE);
 	buts->name[BLKTRACE_BDEV_SIZE - 1] = '\0';
 
@@ -494,6 +497,17 @@ static int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
 	 */
 	strreplace(buts->name, '/', '_');
 
+	/*
+	 * bdev can be NULL, as with scsi-generic, this is a helpful as
+	 * we can be.
+	 */
+	if (rcu_dereference_protected(q->blk_trace,
+				      lockdep_is_held(&q->debugfs_mutex))) {
+		pr_warn("Concurrent blktraces are not allowed on %s\n",
+			buts->name);
+		return -EBUSY;
+	}
+
 	bt = kzalloc(sizeof(*bt), GFP_KERNEL);
 	if (!bt)
 		return -ENOMEM;
@@ -507,12 +521,29 @@ static int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
 	if (!bt->msg_data)
 		goto err;
 
-	ret = -ENOENT;
-
-	dir = debugfs_lookup(buts->name, blk_debugfs_root);
-	if (!dir)
+	/*
+	 * When tracing the whole disk reuse the existing debugfs directory
+	 * created by the block layer on init. For partitions block devices,
+	 * and scsi-generic block devices we create a temporary new debugfs
+	 * directory that will be removed once the trace ends.
+	 */
+	if (bdev && bdev == bdev->bd_contains)
+		dir = q->debugfs_dir;
+	else
 		bt->dir = dir = debugfs_create_dir(buts->name, blk_debugfs_root);
 
+	/*
+	 * As blktrace relies on debugfs for its interface the debugfs directory
+	 * is required, contrary to the usual mantra of not checking for debugfs
+	 * files or directories.
+	 */
+	if (IS_ERR_OR_NULL(dir)) {
+		pr_warn("debugfs_dir not present for %s so skipping\n",
+			buts->name);
+		ret = -ENOENT;
+		goto err;
+	}
+
 	bt->dev = dev;
 	atomic_set(&bt->dropped, 0);
 	INIT_LIST_HEAD(&bt->running_list);
@@ -543,16 +574,11 @@ static int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
 	bt->pid = buts->pid;
 	bt->trace_state = Blktrace_setup;
 
-	ret = -EBUSY;
-	if (cmpxchg(&q->blk_trace, NULL, bt))
-		goto err;
-
+	rcu_assign_pointer(q->blk_trace, bt);
 	get_probe_ref();
 
 	ret = 0;
 err:
-	if (dir && !bt->dir)
-		dput(dir);
 	if (ret)
 		blk_trace_free(bt);
 	return ret;
@@ -585,9 +611,9 @@ int blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
 {
 	int ret;
 
-	mutex_lock(&q->blk_trace_mutex);
+	mutex_lock(&q->debugfs_mutex);
 	ret = __blk_trace_setup(q, name, dev, bdev, arg);
-	mutex_unlock(&q->blk_trace_mutex);
+	mutex_unlock(&q->debugfs_mutex);
 
 	return ret;
 }
@@ -633,7 +659,7 @@ static int __blk_trace_startstop(struct request_queue *q, int start)
 	struct blk_trace *bt;
 
 	bt = rcu_dereference_protected(q->blk_trace,
-				       lockdep_is_held(&q->blk_trace_mutex));
+				       lockdep_is_held(&q->debugfs_mutex));
 	if (bt == NULL)
 		return -EINVAL;
 
@@ -673,9 +699,9 @@ int blk_trace_startstop(struct request_queue *q, int start)
 {
 	int ret;
 
-	mutex_lock(&q->blk_trace_mutex);
+	mutex_lock(&q->debugfs_mutex);
 	ret = __blk_trace_startstop(q, start);
-	mutex_unlock(&q->blk_trace_mutex);
+	mutex_unlock(&q->debugfs_mutex);
 
 	return ret;
 }
@@ -704,7 +730,7 @@ int blk_trace_ioctl(struct block_device *bdev, unsigned cmd, char __user *arg)
 	if (!q)
 		return -ENXIO;
 
-	mutex_lock(&q->blk_trace_mutex);
+	mutex_lock(&q->debugfs_mutex);
 
 	switch (cmd) {
 	case BLKTRACESETUP:
@@ -719,7 +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;
@@ -731,7 +757,7 @@ int blk_trace_ioctl(struct block_device *bdev, unsigned cmd, char __user *arg)
 		break;
 	}
 
-	mutex_unlock(&q->blk_trace_mutex);
+	mutex_unlock(&q->debugfs_mutex);
 	return ret;
 }
 
@@ -742,14 +768,14 @@ int blk_trace_ioctl(struct block_device *bdev, unsigned cmd, char __user *arg)
  **/
 void blk_trace_shutdown(struct request_queue *q)
 {
-	mutex_lock(&q->blk_trace_mutex);
+	mutex_lock(&q->debugfs_mutex);
 	if (rcu_dereference_protected(q->blk_trace,
-				      lockdep_is_held(&q->blk_trace_mutex))) {
+				      lockdep_is_held(&q->debugfs_mutex))) {
 		__blk_trace_startstop(q, 0);
 		__blk_trace_remove(q);
 	}
 
-	mutex_unlock(&q->blk_trace_mutex);
+	mutex_unlock(&q->debugfs_mutex);
 }
 
 #ifdef CONFIG_BLK_CGROUP
@@ -834,6 +860,13 @@ static void blk_add_trace_rq_issue(void *ignore,
 			 blk_trace_request_get_cgid(q, rq));
 }
 
+static void blk_add_trace_rq_merge(void *ignore,
+				   struct request_queue *q, struct request *rq)
+{
+	blk_add_trace_rq(rq, 0, blk_rq_bytes(rq), BLK_TA_BACKMERGE,
+			 blk_trace_request_get_cgid(q, rq));
+}
+
 static void blk_add_trace_rq_requeue(void *ignore,
 				     struct request_queue *q,
 				     struct request *rq)
@@ -885,10 +918,10 @@ static void blk_add_trace_bio_bounce(void *ignore,
 }
 
 static void blk_add_trace_bio_complete(void *ignore,
-				       struct request_queue *q, struct bio *bio,
-				       int error)
+				       struct request_queue *q, struct bio *bio)
 {
-	blk_add_trace_bio(q, bio, BLK_TA_COMPLETE, error);
+	blk_add_trace_bio(q, bio, BLK_TA_COMPLETE,
+			  blk_status_to_errno(bio->bi_status));
 }
 
 static void blk_add_trace_bio_backmerge(void *ignore,
@@ -995,8 +1028,10 @@ static void blk_add_trace_split(void *ignore,
 
 		__blk_add_trace(bt, bio->bi_iter.bi_sector,
 				bio->bi_iter.bi_size, bio_op(bio), bio->bi_opf,
-				BLK_TA_SPLIT, bio->bi_status, sizeof(rpdu),
-				&rpdu, blk_trace_bio_get_cgid(q, bio));
+				BLK_TA_SPLIT,
+				blk_status_to_errno(bio->bi_status),
+				sizeof(rpdu), &rpdu,
+				blk_trace_bio_get_cgid(q, bio));
 	}
 	rcu_read_unlock();
 }
@@ -1033,7 +1068,8 @@ static void blk_add_trace_bio_remap(void *ignore,
 	r.sector_from = cpu_to_be64(from);
 
 	__blk_add_trace(bt, bio->bi_iter.bi_sector, bio->bi_iter.bi_size,
-			bio_op(bio), bio->bi_opf, BLK_TA_REMAP, bio->bi_status,
+			bio_op(bio), bio->bi_opf, BLK_TA_REMAP,
+			blk_status_to_errno(bio->bi_status),
 			sizeof(r), &r, blk_trace_bio_get_cgid(q, bio));
 	rcu_read_unlock();
 }
@@ -1115,6 +1151,8 @@ static void blk_register_tracepoints(void)
 	WARN_ON(ret);
 	ret = register_trace_block_rq_issue(blk_add_trace_rq_issue, NULL);
 	WARN_ON(ret);
+	ret = register_trace_block_rq_merge(blk_add_trace_rq_merge, NULL);
+	WARN_ON(ret);
 	ret = register_trace_block_rq_requeue(blk_add_trace_rq_requeue, NULL);
 	WARN_ON(ret);
 	ret = register_trace_block_rq_complete(blk_add_trace_rq_complete, NULL);
@@ -1161,6 +1199,7 @@ static void blk_unregister_tracepoints(void)
 	unregister_trace_block_bio_bounce(blk_add_trace_bio_bounce, NULL);
 	unregister_trace_block_rq_complete(blk_add_trace_rq_complete, NULL);
 	unregister_trace_block_rq_requeue(blk_add_trace_rq_requeue, NULL);
+	unregister_trace_block_rq_merge(blk_add_trace_rq_merge, NULL);
 	unregister_trace_block_rq_issue(blk_add_trace_rq_issue, NULL);
 	unregister_trace_block_rq_insert(blk_add_trace_rq_insert, NULL);
 
@@ -1253,21 +1292,10 @@ static inline __u16 t_error(const struct trace_entry *ent)
 
 static __u64 get_pdu_int(const struct trace_entry *ent, bool has_cg)
 {
-	const __u64 *val = pdu_start(ent, has_cg);
+	const __be64 *val = pdu_start(ent, has_cg);
 	return be64_to_cpu(*val);
 }
 
-static void get_pdu_remap(const struct trace_entry *ent,
-			  struct blk_io_trace_remap *r, bool has_cg)
-{
-	const struct blk_io_trace_remap *__r = pdu_start(ent, has_cg);
-	__u64 sector_from = __r->sector_from;
-
-	r->device_from = be32_to_cpu(__r->device_from);
-	r->device_to   = be32_to_cpu(__r->device_to);
-	r->sector_from = be64_to_cpu(sector_from);
-}
-
 typedef void (blk_log_action_t) (struct trace_iterator *iter, const char *act,
 	bool has_cg);
 
@@ -1407,13 +1435,13 @@ static void blk_log_with_error(struct trace_seq *s,
 
 static void blk_log_remap(struct trace_seq *s, const struct trace_entry *ent, bool has_cg)
 {
-	struct blk_io_trace_remap r = { .device_from = 0, };
+	const struct blk_io_trace_remap *__r = pdu_start(ent, has_cg);
 
-	get_pdu_remap(ent, &r, has_cg);
 	trace_seq_printf(s, "%llu + %u <- (%d,%d) %llu\n",
 			 t_sector(ent), t_sec(ent),
-			 MAJOR(r.device_from), MINOR(r.device_from),
-			 (unsigned long long)r.sector_from);
+			 MAJOR(be32_to_cpu(__r->device_from)),
+			 MINOR(be32_to_cpu(__r->device_from)),
+			 be64_to_cpu(__r->sector_from));
 }
 
 static void blk_log_plug(struct trace_seq *s, const struct trace_entry *ent, bool has_cg)
@@ -1637,7 +1665,8 @@ static int blk_trace_remove_queue(struct request_queue *q)
 {
 	struct blk_trace *bt;
 
-	bt = xchg(&q->blk_trace, NULL);
+	bt = rcu_replace_pointer(q->blk_trace, NULL,
+				 lockdep_is_held(&q->debugfs_mutex));
 	if (bt == NULL)
 		return -EINVAL;
 
@@ -1669,10 +1698,7 @@ static int blk_trace_setup_queue(struct request_queue *q,
 
 	blk_trace_setup_lba(bt, bdev);
 
-	ret = -EBUSY;
-	if (cmpxchg(&q->blk_trace, NULL, bt))
-		goto free_bt;
-
+	rcu_assign_pointer(q->blk_trace, bt);
 	get_probe_ref();
 	return 0;
 
@@ -1815,10 +1841,10 @@ static ssize_t sysfs_blk_trace_attr_show(struct device *dev,
 	if (q == NULL)
 		goto out_bdput;
 
-	mutex_lock(&q->blk_trace_mutex);
+	mutex_lock(&q->debugfs_mutex);
 
 	bt = rcu_dereference_protected(q->blk_trace,
-				       lockdep_is_held(&q->blk_trace_mutex));
+				       lockdep_is_held(&q->debugfs_mutex));
 	if (attr == &dev_attr_enable) {
 		ret = sprintf(buf, "%u\n", !!bt);
 		goto out_unlock_bdev;
@@ -1836,7 +1862,7 @@ static ssize_t sysfs_blk_trace_attr_show(struct device *dev,
 		ret = sprintf(buf, "%llu\n", bt->end_lba);
 
 out_unlock_bdev:
-	mutex_unlock(&q->blk_trace_mutex);
+	mutex_unlock(&q->debugfs_mutex);
 out_bdput:
 	bdput(bdev);
 out:
@@ -1879,10 +1905,10 @@ static ssize_t sysfs_blk_trace_attr_store(struct device *dev,
 	if (q == NULL)
 		goto out_bdput;
 
-	mutex_lock(&q->blk_trace_mutex);
+	mutex_lock(&q->debugfs_mutex);
 
 	bt = rcu_dereference_protected(q->blk_trace,
-				       lockdep_is_held(&q->blk_trace_mutex));
+				       lockdep_is_held(&q->debugfs_mutex));
 	if (attr == &dev_attr_enable) {
 		if (!!value == !!bt) {
 			ret = 0;
@@ -1899,7 +1925,7 @@ static ssize_t sysfs_blk_trace_attr_store(struct device *dev,
 	if (bt == NULL) {
 		ret = blk_trace_setup_queue(q, bdev);
 		bt = rcu_dereference_protected(q->blk_trace,
-				lockdep_is_held(&q->blk_trace_mutex));
+				lockdep_is_held(&q->debugfs_mutex));
 	}
 
 	if (ret == 0) {
@@ -1914,7 +1940,7 @@ static ssize_t sysfs_blk_trace_attr_store(struct device *dev,
 	}
 
 out_unlock_bdev:
-	mutex_unlock(&q->blk_trace_mutex);
+	mutex_unlock(&q->debugfs_mutex);
 out_bdput:
 	bdput(bdev);
 out:
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 19e793aa441a..a8d4f253ed77 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -11,14 +11,19 @@
 #include <linux/uaccess.h>
 #include <linux/ctype.h>
 #include <linux/kprobes.h>
+#include <linux/spinlock.h>
 #include <linux/syscalls.h>
 #include <linux/error-injection.h>
+#include <linux/btf_ids.h>
 
 #include <asm/tlb.h>
 
 #include "trace_probe.h"
 #include "trace.h"
 
+#define CREATE_TRACE_POINTS
+#include "bpf_trace.h"
+
 #define bpf_event_rcu_dereference(p)					\
 	rcu_dereference_protected(p, lockdep_is_held(&bpf_event_mutex))
 
@@ -83,7 +88,7 @@ unsigned int trace_call_bpf(struct trace_event_call *call, void *ctx)
 	if (in_nmi()) /* not supported yet */
 		return 1;
 
-	preempt_disable();
+	cant_sleep();
 
 	if (unlikely(__this_cpu_inc_return(bpf_prog_active) != 1)) {
 		/*
@@ -115,11 +120,9 @@ unsigned int trace_call_bpf(struct trace_event_call *call, void *ctx)
 
  out:
 	__this_cpu_dec(bpf_prog_active);
-	preempt_enable();
 
 	return ret;
 }
-EXPORT_SYMBOL_GPL(trace_call_bpf);
 
 #ifdef CONFIG_BPF_KPROBE_OVERRIDE
 BPF_CALL_2(bpf_override_return, struct pt_regs *, regs, unsigned long, rc)
@@ -138,18 +141,24 @@ static const struct bpf_func_proto bpf_override_return_proto = {
 };
 #endif
 
-BPF_CALL_3(bpf_probe_read_user, void *, dst, u32, size,
-	   const void __user *, unsafe_ptr)
+static __always_inline int
+bpf_probe_read_user_common(void *dst, u32 size, const void __user *unsafe_ptr)
 {
-	int ret = probe_user_read(dst, unsafe_ptr, size);
+	int ret;
 
+	ret = copy_from_user_nofault(dst, unsafe_ptr, size);
 	if (unlikely(ret < 0))
 		memset(dst, 0, size);
-
 	return ret;
 }
 
-static const struct bpf_func_proto bpf_probe_read_user_proto = {
+BPF_CALL_3(bpf_probe_read_user, void *, dst, u32, size,
+	   const void __user *, unsafe_ptr)
+{
+	return bpf_probe_read_user_common(dst, size, unsafe_ptr);
+}
+
+const struct bpf_func_proto bpf_probe_read_user_proto = {
 	.func		= bpf_probe_read_user,
 	.gpl_only	= true,
 	.ret_type	= RET_INTEGER,
@@ -158,18 +167,25 @@ static const struct bpf_func_proto bpf_probe_read_user_proto = {
 	.arg3_type	= ARG_ANYTHING,
 };
 
-BPF_CALL_3(bpf_probe_read_user_str, void *, dst, u32, size,
-	   const void __user *, unsafe_ptr)
+static __always_inline int
+bpf_probe_read_user_str_common(void *dst, u32 size,
+			       const void __user *unsafe_ptr)
 {
-	int ret = strncpy_from_unsafe_user(dst, unsafe_ptr, size);
+	int ret;
 
+	ret = strncpy_from_user_nofault(dst, unsafe_ptr, size);
 	if (unlikely(ret < 0))
 		memset(dst, 0, size);
-
 	return ret;
 }
 
-static const struct bpf_func_proto bpf_probe_read_user_str_proto = {
+BPF_CALL_3(bpf_probe_read_user_str, void *, dst, u32, size,
+	   const void __user *, unsafe_ptr)
+{
+	return bpf_probe_read_user_str_common(dst, size, unsafe_ptr);
+}
+
+const struct bpf_func_proto bpf_probe_read_user_str_proto = {
 	.func		= bpf_probe_read_user_str,
 	.gpl_only	= true,
 	.ret_type	= RET_INTEGER,
@@ -179,28 +195,28 @@ static const struct bpf_func_proto bpf_probe_read_user_str_proto = {
 };
 
 static __always_inline int
-bpf_probe_read_kernel_common(void *dst, u32 size, const void *unsafe_ptr,
-			     const bool compat)
+bpf_probe_read_kernel_common(void *dst, u32 size, const void *unsafe_ptr)
 {
 	int ret = security_locked_down(LOCKDOWN_BPF_READ);
 
 	if (unlikely(ret < 0))
-		goto out;
-	ret = compat ? probe_kernel_read(dst, unsafe_ptr, size) :
-	      probe_kernel_read_strict(dst, unsafe_ptr, size);
+		goto fail;
+	ret = copy_from_kernel_nofault(dst, unsafe_ptr, size);
 	if (unlikely(ret < 0))
-out:
-		memset(dst, 0, size);
+		goto fail;
+	return ret;
+fail:
+	memset(dst, 0, size);
 	return ret;
 }
 
 BPF_CALL_3(bpf_probe_read_kernel, void *, dst, u32, size,
 	   const void *, unsafe_ptr)
 {
-	return bpf_probe_read_kernel_common(dst, size, unsafe_ptr, false);
+	return bpf_probe_read_kernel_common(dst, size, unsafe_ptr);
 }
 
-static const struct bpf_func_proto bpf_probe_read_kernel_proto = {
+const struct bpf_func_proto bpf_probe_read_kernel_proto = {
 	.func		= bpf_probe_read_kernel,
 	.gpl_only	= true,
 	.ret_type	= RET_INTEGER,
@@ -209,53 +225,40 @@ static const struct bpf_func_proto bpf_probe_read_kernel_proto = {
 	.arg3_type	= ARG_ANYTHING,
 };
 
-BPF_CALL_3(bpf_probe_read_compat, void *, dst, u32, size,
-	   const void *, unsafe_ptr)
-{
-	return bpf_probe_read_kernel_common(dst, size, unsafe_ptr, true);
-}
-
-static const struct bpf_func_proto bpf_probe_read_compat_proto = {
-	.func		= bpf_probe_read_compat,
-	.gpl_only	= true,
-	.ret_type	= RET_INTEGER,
-	.arg1_type	= ARG_PTR_TO_UNINIT_MEM,
-	.arg2_type	= ARG_CONST_SIZE_OR_ZERO,
-	.arg3_type	= ARG_ANYTHING,
-};
-
 static __always_inline int
-bpf_probe_read_kernel_str_common(void *dst, u32 size, const void *unsafe_ptr,
-				 const bool compat)
+bpf_probe_read_kernel_str_common(void *dst, u32 size, const void *unsafe_ptr)
 {
 	int ret = security_locked_down(LOCKDOWN_BPF_READ);
 
 	if (unlikely(ret < 0))
-		goto out;
+		goto fail;
+
 	/*
-	 * The strncpy_from_unsafe_*() call will likely not fill the entire
-	 * buffer, but that's okay in this circumstance as we're probing
+	 * The strncpy_from_kernel_nofault() call will likely not fill the
+	 * entire buffer, but that's okay in this circumstance as we're probing
 	 * arbitrary memory anyway similar to bpf_probe_read_*() and might
 	 * as well probe the stack. Thus, memory is explicitly cleared
 	 * only in error case, so that improper users ignoring return
 	 * code altogether don't copy garbage; otherwise length of string
 	 * is returned that can be used for bpf_perf_event_output() et al.
 	 */
-	ret = compat ? strncpy_from_unsafe(dst, unsafe_ptr, size) :
-	      strncpy_from_unsafe_strict(dst, unsafe_ptr, size);
+	ret = strncpy_from_kernel_nofault(dst, unsafe_ptr, size);
 	if (unlikely(ret < 0))
-out:
-		memset(dst, 0, size);
+		goto fail;
+
+	return ret;
+fail:
+	memset(dst, 0, size);
 	return ret;
 }
 
 BPF_CALL_3(bpf_probe_read_kernel_str, void *, dst, u32, size,
 	   const void *, unsafe_ptr)
 {
-	return bpf_probe_read_kernel_str_common(dst, size, unsafe_ptr, false);
+	return bpf_probe_read_kernel_str_common(dst, size, unsafe_ptr);
 }
 
-static const struct bpf_func_proto bpf_probe_read_kernel_str_proto = {
+const struct bpf_func_proto bpf_probe_read_kernel_str_proto = {
 	.func		= bpf_probe_read_kernel_str,
 	.gpl_only	= true,
 	.ret_type	= RET_INTEGER,
@@ -264,10 +267,34 @@ static const struct bpf_func_proto bpf_probe_read_kernel_str_proto = {
 	.arg3_type	= ARG_ANYTHING,
 };
 
+#ifdef CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE
+BPF_CALL_3(bpf_probe_read_compat, void *, dst, u32, size,
+	   const void *, unsafe_ptr)
+{
+	if ((unsigned long)unsafe_ptr < TASK_SIZE) {
+		return bpf_probe_read_user_common(dst, size,
+				(__force void __user *)unsafe_ptr);
+	}
+	return bpf_probe_read_kernel_common(dst, size, unsafe_ptr);
+}
+
+static const struct bpf_func_proto bpf_probe_read_compat_proto = {
+	.func		= bpf_probe_read_compat,
+	.gpl_only	= true,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_UNINIT_MEM,
+	.arg2_type	= ARG_CONST_SIZE_OR_ZERO,
+	.arg3_type	= ARG_ANYTHING,
+};
+
 BPF_CALL_3(bpf_probe_read_compat_str, void *, dst, u32, size,
 	   const void *, unsafe_ptr)
 {
-	return bpf_probe_read_kernel_str_common(dst, size, unsafe_ptr, true);
+	if ((unsigned long)unsafe_ptr < TASK_SIZE) {
+		return bpf_probe_read_user_str_common(dst, size,
+				(__force void __user *)unsafe_ptr);
+	}
+	return bpf_probe_read_kernel_str_common(dst, size, unsafe_ptr);
 }
 
 static const struct bpf_func_proto bpf_probe_read_compat_str_proto = {
@@ -278,6 +305,7 @@ static const struct bpf_func_proto bpf_probe_read_compat_str_proto = {
 	.arg2_type	= ARG_CONST_SIZE_OR_ZERO,
 	.arg3_type	= ARG_ANYTHING,
 };
+#endif /* CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE */
 
 BPF_CALL_3(bpf_probe_write_user, void __user *, unsafe_ptr, const void *, src,
 	   u32, size)
@@ -303,7 +331,7 @@ BPF_CALL_3(bpf_probe_write_user, void __user *, unsafe_ptr, const void *, src,
 	if (unlikely(!nmi_uaccess_okay()))
 		return -EPERM;
 
-	return probe_user_write(unsafe_ptr, src, size);
+	return copy_to_user_nofault(unsafe_ptr, src, size);
 }
 
 static const struct bpf_func_proto bpf_probe_write_user_proto = {
@@ -317,25 +345,75 @@ static const struct bpf_func_proto bpf_probe_write_user_proto = {
 
 static const struct bpf_func_proto *bpf_get_probe_write_proto(void)
 {
+	if (!capable(CAP_SYS_ADMIN))
+		return NULL;
+
 	pr_warn_ratelimited("%s[%d] is installing a program with bpf_probe_write_user helper that may corrupt user memory!",
 			    current->comm, task_pid_nr(current));
 
 	return &bpf_probe_write_user_proto;
 }
 
+static void bpf_trace_copy_string(char *buf, void *unsafe_ptr, char fmt_ptype,
+		size_t bufsz)
+{
+	void __user *user_ptr = (__force void __user *)unsafe_ptr;
+
+	buf[0] = 0;
+
+	switch (fmt_ptype) {
+	case 's':
+#ifdef CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE
+		if ((unsigned long)unsafe_ptr < TASK_SIZE) {
+			strncpy_from_user_nofault(buf, user_ptr, bufsz);
+			break;
+		}
+		fallthrough;
+#endif
+	case 'k':
+		strncpy_from_kernel_nofault(buf, unsafe_ptr, bufsz);
+		break;
+	case 'u':
+		strncpy_from_user_nofault(buf, user_ptr, bufsz);
+		break;
+	}
+}
+
+static DEFINE_RAW_SPINLOCK(trace_printk_lock);
+
+#define BPF_TRACE_PRINTK_SIZE   1024
+
+static __printf(1, 0) int bpf_do_trace_printk(const char *fmt, ...)
+{
+	static char buf[BPF_TRACE_PRINTK_SIZE];
+	unsigned long flags;
+	va_list ap;
+	int ret;
+
+	raw_spin_lock_irqsave(&trace_printk_lock, flags);
+	va_start(ap, fmt);
+	ret = vsnprintf(buf, sizeof(buf), fmt, ap);
+	va_end(ap);
+	/* vsnprintf() will not append null for zero-length strings */
+	if (ret == 0)
+		buf[0] = '\0';
+	trace_bpf_trace_printk(buf);
+	raw_spin_unlock_irqrestore(&trace_printk_lock, flags);
+
+	return ret;
+}
+
 /*
  * Only limited trace_printk() conversion specifiers allowed:
- * %d %i %u %x %ld %li %lu %lx %lld %lli %llu %llx %p %s
+ * %d %i %u %x %ld %li %lu %lx %lld %lli %llu %llx %p %pB %pks %pus %s
  */
 BPF_CALL_5(bpf_trace_printk, char *, fmt, u32, fmt_size, u64, arg1,
 	   u64, arg2, u64, arg3)
 {
+	int i, mod[3] = {}, fmt_cnt = 0;
+	char buf[64], fmt_ptype;
+	void *unsafe_ptr = NULL;
 	bool str_seen = false;
-	int mod[3] = {};
-	int fmt_cnt = 0;
-	u64 unsafe_addr;
-	char buf[64];
-	int i;
 
 	/*
 	 * bpf_check()->check_func_arg()->check_stack_boundary()
@@ -361,40 +439,60 @@ BPF_CALL_5(bpf_trace_printk, char *, fmt, u32, fmt_size, u64, arg1,
 		if (fmt[i] == 'l') {
 			mod[fmt_cnt]++;
 			i++;
-		} else if (fmt[i] == 'p' || fmt[i] == 's') {
+		} else if (fmt[i] == 'p') {
 			mod[fmt_cnt]++;
+			if ((fmt[i + 1] == 'k' ||
+			     fmt[i + 1] == 'u') &&
+			    fmt[i + 2] == 's') {
+				fmt_ptype = fmt[i + 1];
+				i += 2;
+				goto fmt_str;
+			}
+
+			if (fmt[i + 1] == 'B') {
+				i++;
+				goto fmt_next;
+			}
+
 			/* disallow any further format extensions */
 			if (fmt[i + 1] != 0 &&
 			    !isspace(fmt[i + 1]) &&
 			    !ispunct(fmt[i + 1]))
 				return -EINVAL;
-			fmt_cnt++;
-			if (fmt[i] == 's') {
-				if (str_seen)
-					/* allow only one '%s' per fmt string */
-					return -EINVAL;
-				str_seen = true;
-
-				switch (fmt_cnt) {
-				case 1:
-					unsafe_addr = arg1;
-					arg1 = (long) buf;
-					break;
-				case 2:
-					unsafe_addr = arg2;
-					arg2 = (long) buf;
-					break;
-				case 3:
-					unsafe_addr = arg3;
-					arg3 = (long) buf;
-					break;
-				}
-				buf[0] = 0;
-				strncpy_from_unsafe(buf,
-						    (void *) (long) unsafe_addr,
-						    sizeof(buf));
+
+			goto fmt_next;
+		} else if (fmt[i] == 's') {
+			mod[fmt_cnt]++;
+			fmt_ptype = fmt[i];
+fmt_str:
+			if (str_seen)
+				/* allow only one '%s' per fmt string */
+				return -EINVAL;
+			str_seen = true;
+
+			if (fmt[i + 1] != 0 &&
+			    !isspace(fmt[i + 1]) &&
+			    !ispunct(fmt[i + 1]))
+				return -EINVAL;
+
+			switch (fmt_cnt) {
+			case 0:
+				unsafe_ptr = (void *)(long)arg1;
+				arg1 = (long)buf;
+				break;
+			case 1:
+				unsafe_ptr = (void *)(long)arg2;
+				arg2 = (long)buf;
+				break;
+			case 2:
+				unsafe_ptr = (void *)(long)arg3;
+				arg3 = (long)buf;
+				break;
 			}
-			continue;
+
+			bpf_trace_copy_string(buf, unsafe_ptr, fmt_ptype,
+					sizeof(buf));
+			goto fmt_next;
 		}
 
 		if (fmt[i] == 'l') {
@@ -405,6 +503,7 @@ BPF_CALL_5(bpf_trace_printk, char *, fmt, u32, fmt_size, u64, arg1,
 		if (fmt[i] != 'i' && fmt[i] != 'd' &&
 		    fmt[i] != 'u' && fmt[i] != 'x')
 			return -EINVAL;
+fmt_next:
 		fmt_cnt++;
 	}
 
@@ -413,8 +512,7 @@ BPF_CALL_5(bpf_trace_printk, char *, fmt, u32, fmt_size, u64, arg1,
  */
 #define __BPF_TP_EMIT()	__BPF_ARG3_TP()
 #define __BPF_TP(...)							\
-	__trace_printk(0 /* Fake ip */,					\
-		       fmt, ##__VA_ARGS__)
+	bpf_do_trace_printk(fmt, ##__VA_ARGS__)
 
 #define __BPF_ARG1_TP(...)						\
 	((mod[0] == 2 || (mod[0] == 1 && __BITS_PER_LONG == 64))	\
@@ -451,14 +549,233 @@ static const struct bpf_func_proto bpf_trace_printk_proto = {
 const struct bpf_func_proto *bpf_get_trace_printk_proto(void)
 {
 	/*
-	 * this program might be calling bpf_trace_printk,
-	 * so allocate per-cpu printk buffers
+	 * This program might be calling bpf_trace_printk,
+	 * so enable the associated bpf_trace/bpf_trace_printk event.
+	 * Repeat this each time as it is possible a user has
+	 * disabled bpf_trace_printk events.  By loading a program
+	 * calling bpf_trace_printk() however the user has expressed
+	 * the intent to see such events.
 	 */
-	trace_printk_init_buffers();
+	if (trace_set_clr_event("bpf_trace", "bpf_trace_printk", 1))
+		pr_warn_ratelimited("could not enable bpf_trace_printk events");
 
 	return &bpf_trace_printk_proto;
 }
 
+#define MAX_SEQ_PRINTF_VARARGS		12
+#define MAX_SEQ_PRINTF_MAX_MEMCPY	6
+#define MAX_SEQ_PRINTF_STR_LEN		128
+
+struct bpf_seq_printf_buf {
+	char buf[MAX_SEQ_PRINTF_MAX_MEMCPY][MAX_SEQ_PRINTF_STR_LEN];
+};
+static DEFINE_PER_CPU(struct bpf_seq_printf_buf, bpf_seq_printf_buf);
+static DEFINE_PER_CPU(int, bpf_seq_printf_buf_used);
+
+BPF_CALL_5(bpf_seq_printf, struct seq_file *, m, char *, fmt, u32, fmt_size,
+	   const void *, data, u32, data_len)
+{
+	int err = -EINVAL, fmt_cnt = 0, memcpy_cnt = 0;
+	int i, buf_used, copy_size, num_args;
+	u64 params[MAX_SEQ_PRINTF_VARARGS];
+	struct bpf_seq_printf_buf *bufs;
+	const u64 *args = data;
+
+	buf_used = this_cpu_inc_return(bpf_seq_printf_buf_used);
+	if (WARN_ON_ONCE(buf_used > 1)) {
+		err = -EBUSY;
+		goto out;
+	}
+
+	bufs = this_cpu_ptr(&bpf_seq_printf_buf);
+
+	/*
+	 * bpf_check()->check_func_arg()->check_stack_boundary()
+	 * guarantees that fmt points to bpf program stack,
+	 * fmt_size bytes of it were initialized and fmt_size > 0
+	 */
+	if (fmt[--fmt_size] != 0)
+		goto out;
+
+	if (data_len & 7)
+		goto out;
+
+	for (i = 0; i < fmt_size; i++) {
+		if (fmt[i] == '%') {
+			if (fmt[i + 1] == '%')
+				i++;
+			else if (!data || !data_len)
+				goto out;
+		}
+	}
+
+	num_args = data_len / 8;
+
+	/* check format string for allowed specifiers */
+	for (i = 0; i < fmt_size; i++) {
+		/* only printable ascii for now. */
+		if ((!isprint(fmt[i]) && !isspace(fmt[i])) || !isascii(fmt[i])) {
+			err = -EINVAL;
+			goto out;
+		}
+
+		if (fmt[i] != '%')
+			continue;
+
+		if (fmt[i + 1] == '%') {
+			i++;
+			continue;
+		}
+
+		if (fmt_cnt >= MAX_SEQ_PRINTF_VARARGS) {
+			err = -E2BIG;
+			goto out;
+		}
+
+		if (fmt_cnt >= num_args) {
+			err = -EINVAL;
+			goto out;
+		}
+
+		/* fmt[i] != 0 && fmt[last] == 0, so we can access fmt[i + 1] */
+		i++;
+
+		/* skip optional "[0 +-][num]" width formating field */
+		while (fmt[i] == '0' || fmt[i] == '+'  || fmt[i] == '-' ||
+		       fmt[i] == ' ')
+			i++;
+		if (fmt[i] >= '1' && fmt[i] <= '9') {
+			i++;
+			while (fmt[i] >= '0' && fmt[i] <= '9')
+				i++;
+		}
+
+		if (fmt[i] == 's') {
+			void *unsafe_ptr;
+
+			/* try our best to copy */
+			if (memcpy_cnt >= MAX_SEQ_PRINTF_MAX_MEMCPY) {
+				err = -E2BIG;
+				goto out;
+			}
+
+			unsafe_ptr = (void *)(long)args[fmt_cnt];
+			err = strncpy_from_kernel_nofault(bufs->buf[memcpy_cnt],
+					unsafe_ptr, MAX_SEQ_PRINTF_STR_LEN);
+			if (err < 0)
+				bufs->buf[memcpy_cnt][0] = '\0';
+			params[fmt_cnt] = (u64)(long)bufs->buf[memcpy_cnt];
+
+			fmt_cnt++;
+			memcpy_cnt++;
+			continue;
+		}
+
+		if (fmt[i] == 'p') {
+			if (fmt[i + 1] == 0 ||
+			    fmt[i + 1] == 'K' ||
+			    fmt[i + 1] == 'x' ||
+			    fmt[i + 1] == 'B') {
+				/* just kernel pointers */
+				params[fmt_cnt] = args[fmt_cnt];
+				fmt_cnt++;
+				continue;
+			}
+
+			/* only support "%pI4", "%pi4", "%pI6" and "%pi6". */
+			if (fmt[i + 1] != 'i' && fmt[i + 1] != 'I') {
+				err = -EINVAL;
+				goto out;
+			}
+			if (fmt[i + 2] != '4' && fmt[i + 2] != '6') {
+				err = -EINVAL;
+				goto out;
+			}
+
+			if (memcpy_cnt >= MAX_SEQ_PRINTF_MAX_MEMCPY) {
+				err = -E2BIG;
+				goto out;
+			}
+
+
+			copy_size = (fmt[i + 2] == '4') ? 4 : 16;
+
+			err = copy_from_kernel_nofault(bufs->buf[memcpy_cnt],
+						(void *) (long) args[fmt_cnt],
+						copy_size);
+			if (err < 0)
+				memset(bufs->buf[memcpy_cnt], 0, copy_size);
+			params[fmt_cnt] = (u64)(long)bufs->buf[memcpy_cnt];
+
+			i += 2;
+			fmt_cnt++;
+			memcpy_cnt++;
+			continue;
+		}
+
+		if (fmt[i] == 'l') {
+			i++;
+			if (fmt[i] == 'l')
+				i++;
+		}
+
+		if (fmt[i] != 'i' && fmt[i] != 'd' &&
+		    fmt[i] != 'u' && fmt[i] != 'x' &&
+		    fmt[i] != 'X') {
+			err = -EINVAL;
+			goto out;
+		}
+
+		params[fmt_cnt] = args[fmt_cnt];
+		fmt_cnt++;
+	}
+
+	/* Maximumly we can have MAX_SEQ_PRINTF_VARARGS parameter, just give
+	 * all of them to seq_printf().
+	 */
+	seq_printf(m, fmt, params[0], params[1], params[2], params[3],
+		   params[4], params[5], params[6], params[7], params[8],
+		   params[9], params[10], params[11]);
+
+	err = seq_has_overflowed(m) ? -EOVERFLOW : 0;
+out:
+	this_cpu_dec(bpf_seq_printf_buf_used);
+	return err;
+}
+
+BTF_ID_LIST(bpf_seq_printf_btf_ids)
+BTF_ID(struct, seq_file)
+
+static const struct bpf_func_proto bpf_seq_printf_proto = {
+	.func		= bpf_seq_printf,
+	.gpl_only	= true,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_BTF_ID,
+	.arg2_type	= ARG_PTR_TO_MEM,
+	.arg3_type	= ARG_CONST_SIZE,
+	.arg4_type      = ARG_PTR_TO_MEM_OR_NULL,
+	.arg5_type      = ARG_CONST_SIZE_OR_ZERO,
+	.btf_id		= bpf_seq_printf_btf_ids,
+};
+
+BPF_CALL_3(bpf_seq_write, struct seq_file *, m, const void *, data, u32, len)
+{
+	return seq_write(m, data, len) ? -EOVERFLOW : 0;
+}
+
+BTF_ID_LIST(bpf_seq_write_btf_ids)
+BTF_ID(struct, seq_file)
+
+static const struct bpf_func_proto bpf_seq_write_proto = {
+	.func		= bpf_seq_write,
+	.gpl_only	= true,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_BTF_ID,
+	.arg2_type	= ARG_PTR_TO_MEM,
+	.arg3_type	= ARG_CONST_SIZE_OR_ZERO,
+	.btf_id		= bpf_seq_write_btf_ids,
+};
+
 static __always_inline int
 get_map_perf_counter(struct bpf_map *map, u64 flags,
 		     u64 *value, u64 *enabled, u64 *running)
@@ -670,7 +987,7 @@ BPF_CALL_0(bpf_get_current_task)
 	return (long) current;
 }
 
-static const struct bpf_func_proto bpf_get_current_task_proto = {
+const struct bpf_func_proto bpf_get_current_task_proto = {
 	.func		= bpf_get_current_task,
 	.gpl_only	= true,
 	.ret_type	= RET_INTEGER,
@@ -732,7 +1049,7 @@ static int bpf_send_signal_common(u32 sig, enum pid_type type)
 	if (unlikely(!nmi_uaccess_okay()))
 		return -EPERM;
 
-	if (in_nmi()) {
+	if (irqs_disabled()) {
 		/* Do an early check on signal validity. Otherwise,
 		 * the error is lost in deferred irq_work.
 		 */
@@ -781,8 +1098,8 @@ static const struct bpf_func_proto bpf_send_signal_thread_proto = {
 	.arg1_type	= ARG_ANYTHING,
 };
 
-static const struct bpf_func_proto *
-tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
+const struct bpf_func_proto *
+bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 {
 	switch (func_id) {
 	case BPF_FUNC_map_lookup_elem:
@@ -799,6 +1116,8 @@ tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_map_peek_elem_proto;
 	case BPF_FUNC_ktime_get_ns:
 		return &bpf_ktime_get_ns_proto;
+	case BPF_FUNC_ktime_get_boot_ns:
+		return &bpf_ktime_get_boot_ns_proto;
 	case BPF_FUNC_tail_call:
 		return &bpf_tail_call_proto;
 	case BPF_FUNC_get_current_pid_tgid:
@@ -827,14 +1146,16 @@ tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_probe_read_user_proto;
 	case BPF_FUNC_probe_read_kernel:
 		return &bpf_probe_read_kernel_proto;
-	case BPF_FUNC_probe_read:
-		return &bpf_probe_read_compat_proto;
 	case BPF_FUNC_probe_read_user_str:
 		return &bpf_probe_read_user_str_proto;
 	case BPF_FUNC_probe_read_kernel_str:
 		return &bpf_probe_read_kernel_str_proto;
+#ifdef CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE
+	case BPF_FUNC_probe_read:
+		return &bpf_probe_read_compat_proto;
 	case BPF_FUNC_probe_read_str:
 		return &bpf_probe_read_compat_str_proto;
+#endif
 #ifdef CONFIG_CGROUPS
 	case BPF_FUNC_get_current_cgroup_id:
 		return &bpf_get_current_cgroup_id_proto;
@@ -843,6 +1164,24 @@ tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_send_signal_proto;
 	case BPF_FUNC_send_signal_thread:
 		return &bpf_send_signal_thread_proto;
+	case BPF_FUNC_perf_event_read_value:
+		return &bpf_perf_event_read_value_proto;
+	case BPF_FUNC_get_ns_current_pid_tgid:
+		return &bpf_get_ns_current_pid_tgid_proto;
+	case BPF_FUNC_ringbuf_output:
+		return &bpf_ringbuf_output_proto;
+	case BPF_FUNC_ringbuf_reserve:
+		return &bpf_ringbuf_reserve_proto;
+	case BPF_FUNC_ringbuf_submit:
+		return &bpf_ringbuf_submit_proto;
+	case BPF_FUNC_ringbuf_discard:
+		return &bpf_ringbuf_discard_proto;
+	case BPF_FUNC_ringbuf_query:
+		return &bpf_ringbuf_query_proto;
+	case BPF_FUNC_jiffies64:
+		return &bpf_jiffies64_proto;
+	case BPF_FUNC_get_task_stack:
+		return &bpf_get_task_stack_proto;
 	default:
 		return NULL;
 	}
@@ -858,14 +1197,12 @@ kprobe_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_get_stackid_proto;
 	case BPF_FUNC_get_stack:
 		return &bpf_get_stack_proto;
-	case BPF_FUNC_perf_event_read_value:
-		return &bpf_perf_event_read_value_proto;
 #ifdef CONFIG_BPF_KPROBE_OVERRIDE
 	case BPF_FUNC_override_return:
 		return &bpf_override_return_proto;
 #endif
 	default:
-		return tracing_func_proto(func_id, prog);
+		return bpf_tracing_func_proto(func_id, prog);
 	}
 }
 
@@ -975,7 +1312,7 @@ tp_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	case BPF_FUNC_get_stack:
 		return &bpf_get_stack_proto_tp;
 	default:
-		return tracing_func_proto(func_id, prog);
+		return bpf_tracing_func_proto(func_id, prog);
 	}
 }
 
@@ -1028,6 +1365,45 @@ static const struct bpf_func_proto bpf_perf_prog_read_value_proto = {
          .arg3_type      = ARG_CONST_SIZE,
 };
 
+BPF_CALL_4(bpf_read_branch_records, struct bpf_perf_event_data_kern *, ctx,
+	   void *, buf, u32, size, u64, flags)
+{
+#ifndef CONFIG_X86
+	return -ENOENT;
+#else
+	static const u32 br_entry_size = sizeof(struct perf_branch_entry);
+	struct perf_branch_stack *br_stack = ctx->data->br_stack;
+	u32 to_copy;
+
+	if (unlikely(flags & ~BPF_F_GET_BRANCH_RECORDS_SIZE))
+		return -EINVAL;
+
+	if (unlikely(!br_stack))
+		return -EINVAL;
+
+	if (flags & BPF_F_GET_BRANCH_RECORDS_SIZE)
+		return br_stack->nr * br_entry_size;
+
+	if (!buf || (size % br_entry_size != 0))
+		return -EINVAL;
+
+	to_copy = min_t(u32, br_stack->nr * br_entry_size, size);
+	memcpy(buf, br_stack->entries, to_copy);
+
+	return to_copy;
+#endif
+}
+
+static const struct bpf_func_proto bpf_read_branch_records_proto = {
+	.func           = bpf_read_branch_records,
+	.gpl_only       = true,
+	.ret_type       = RET_INTEGER,
+	.arg1_type      = ARG_PTR_TO_CTX,
+	.arg2_type      = ARG_PTR_TO_MEM_OR_NULL,
+	.arg3_type      = ARG_CONST_SIZE_OR_ZERO,
+	.arg4_type      = ARG_ANYTHING,
+};
+
 static const struct bpf_func_proto *
 pe_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 {
@@ -1035,13 +1411,15 @@ pe_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	case BPF_FUNC_perf_event_output:
 		return &bpf_perf_event_output_proto_tp;
 	case BPF_FUNC_get_stackid:
-		return &bpf_get_stackid_proto_tp;
+		return &bpf_get_stackid_proto_pe;
 	case BPF_FUNC_get_stack:
-		return &bpf_get_stack_proto_tp;
+		return &bpf_get_stack_proto_pe;
 	case BPF_FUNC_perf_prog_read_value:
 		return &bpf_perf_prog_read_value_proto;
+	case BPF_FUNC_read_branch_records:
+		return &bpf_read_branch_records_proto;
 	default:
-		return tracing_func_proto(func_id, prog);
+		return bpf_tracing_func_proto(func_id, prog);
 	}
 }
 
@@ -1104,6 +1482,7 @@ static const struct bpf_func_proto bpf_perf_event_output_proto_raw_tp = {
 };
 
 extern const struct bpf_func_proto bpf_skb_output_proto;
+extern const struct bpf_func_proto bpf_xdp_output_proto;
 
 BPF_CALL_3(bpf_get_stackid_raw_tp, struct bpf_raw_tracepoint_args *, args,
 	   struct bpf_map *, map, u64, flags)
@@ -1168,18 +1547,38 @@ raw_tp_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	case BPF_FUNC_get_stack:
 		return &bpf_get_stack_proto_raw_tp;
 	default:
-		return tracing_func_proto(func_id, prog);
+		return bpf_tracing_func_proto(func_id, prog);
 	}
 }
 
-static const struct bpf_func_proto *
+const struct bpf_func_proto *
 tracing_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 {
 	switch (func_id) {
 #ifdef CONFIG_NET
 	case BPF_FUNC_skb_output:
 		return &bpf_skb_output_proto;
+	case BPF_FUNC_xdp_output:
+		return &bpf_xdp_output_proto;
+	case BPF_FUNC_skc_to_tcp6_sock:
+		return &bpf_skc_to_tcp6_sock_proto;
+	case BPF_FUNC_skc_to_tcp_sock:
+		return &bpf_skc_to_tcp_sock_proto;
+	case BPF_FUNC_skc_to_tcp_timewait_sock:
+		return &bpf_skc_to_tcp_timewait_sock_proto;
+	case BPF_FUNC_skc_to_tcp_request_sock:
+		return &bpf_skc_to_tcp_request_sock_proto;
+	case BPF_FUNC_skc_to_udp6_sock:
+		return &bpf_skc_to_udp6_sock_proto;
 #endif
+	case BPF_FUNC_seq_printf:
+		return prog->expected_attach_type == BPF_TRACE_ITER ?
+		       &bpf_seq_printf_proto :
+		       NULL;
+	case BPF_FUNC_seq_write:
+		return prog->expected_attach_type == BPF_TRACE_ITER ?
+		       &bpf_seq_write_proto :
+		       NULL;
 	default:
 		return raw_tp_prog_func_proto(func_id, prog);
 	}
@@ -1213,6 +1612,13 @@ static bool tracing_prog_is_valid_access(int off, int size,
 	return btf_ctx_access(off, size, type, prog, info);
 }
 
+int __weak bpf_prog_test_run_tracing(struct bpf_prog *prog,
+				     const union bpf_attr *kattr,
+				     union bpf_attr __user *uattr)
+{
+	return -ENOTSUPP;
+}
+
 const struct bpf_verifier_ops raw_tracepoint_verifier_ops = {
 	.get_func_proto  = raw_tp_prog_func_proto,
 	.is_valid_access = raw_tp_prog_is_valid_access,
@@ -1227,6 +1633,7 @@ const struct bpf_verifier_ops tracing_verifier_ops = {
 };
 
 const struct bpf_prog_ops tracing_prog_ops = {
+	.test_run = bpf_prog_test_run_tracing,
 };
 
 static bool raw_tp_writable_prog_is_valid_access(int off, int size,
@@ -1416,7 +1823,7 @@ int perf_event_query_prog_array(struct perf_event *event, void __user *info)
 	u32 *ids, prog_cnt, ids_len;
 	int ret;
 
-	if (!capable(CAP_SYS_ADMIN))
+	if (!perfmon_capable())
 		return -EPERM;
 	if (event->attr.type != PERF_TYPE_TRACEPOINT)
 		return -EINVAL;
@@ -1475,10 +1882,9 @@ void bpf_put_raw_tracepoint(struct bpf_raw_event_map *btp)
 static __always_inline
 void __bpf_trace_run(struct bpf_prog *prog, u64 *args)
 {
+	cant_sleep();
 	rcu_read_lock();
-	preempt_disable();
 	(void) BPF_PROG_RUN(prog, args);
-	preempt_enable();
 	rcu_read_unlock();
 }
 
diff --git a/kernel/trace/bpf_trace.h b/kernel/trace/bpf_trace.h
new file mode 100644
index 000000000000..9acbc11ac7bb
--- /dev/null
+++ b/kernel/trace/bpf_trace.h
@@ -0,0 +1,34 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM bpf_trace
+
+#if !defined(_TRACE_BPF_TRACE_H) || defined(TRACE_HEADER_MULTI_READ)
+
+#define _TRACE_BPF_TRACE_H
+
+#include <linux/tracepoint.h>
+
+TRACE_EVENT(bpf_trace_printk,
+
+	TP_PROTO(const char *bpf_string),
+
+	TP_ARGS(bpf_string),
+
+	TP_STRUCT__entry(
+		__string(bpf_string, bpf_string)
+	),
+
+	TP_fast_assign(
+		__assign_str(bpf_string, bpf_string);
+	),
+
+	TP_printk("%s", __get_str(bpf_string))
+);
+
+#endif /* _TRACE_BPF_TRACE_H */
+
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH .
+#define TRACE_INCLUDE_FILE bpf_trace
+
+#include <trace/define_trace.h>
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index fd81c7de77a7..275441254bb5 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -102,7 +102,7 @@ static bool ftrace_pids_enabled(struct ftrace_ops *ops)
 
 	tr = ops->private;
 
-	return tr->function_pids != NULL;
+	return tr->function_pids != NULL || tr->function_no_pids != NULL;
 }
 
 static void ftrace_update_trampoline(struct ftrace_ops *ops);
@@ -143,24 +143,20 @@ static void ftrace_pid_func(unsigned long ip, unsigned long parent_ip,
 			    struct ftrace_ops *op, struct pt_regs *regs)
 {
 	struct trace_array *tr = op->private;
+	int pid;
 
-	if (tr && this_cpu_read(tr->array_buffer.data->ftrace_ignore_pid))
-		return;
+	if (tr) {
+		pid = this_cpu_read(tr->array_buffer.data->ftrace_ignore_pid);
+		if (pid == FTRACE_PID_IGNORE)
+			return;
+		if (pid != FTRACE_PID_TRACE &&
+		    pid != current->pid)
+			return;
+	}
 
 	op->saved_func(ip, parent_ip, op, regs);
 }
 
-static void ftrace_sync(struct work_struct *work)
-{
-	/*
-	 * This function is just a stub to implement a hard force
-	 * of synchronize_rcu(). This requires synchronizing
-	 * tasks even in userspace and idle.
-	 *
-	 * Yes, function tracing is rude.
-	 */
-}
-
 static void ftrace_sync_ipi(void *data)
 {
 	/* Probably not needed, but do it anyway */
@@ -246,7 +242,7 @@ static void update_ftrace_function(void)
 	 * Make sure all CPUs see this. Yes this is slow, but static
 	 * tracing is slow and nasty to have enabled.
 	 */
-	schedule_on_each_cpu(ftrace_sync);
+	synchronize_rcu_tasks_rude();
 	/* Now all cpus are using the list ops. */
 	function_trace_op = set_function_trace_op;
 	/* Make sure the function_trace_op is visible on all CPUs */
@@ -2017,16 +2013,16 @@ void ftrace_bug(int failed, struct dyn_ftrace *rec)
 {
 	unsigned long ip = rec ? rec->ip : 0;
 
+	pr_info("------------[ ftrace bug ]------------\n");
+
 	switch (failed) {
 	case -EFAULT:
-		FTRACE_WARN_ON_ONCE(1);
 		pr_info("ftrace faulted on modifying ");
-		print_ip_sym(ip);
+		print_ip_sym(KERN_INFO, ip);
 		break;
 	case -EINVAL:
-		FTRACE_WARN_ON_ONCE(1);
 		pr_info("ftrace failed to modify ");
-		print_ip_sym(ip);
+		print_ip_sym(KERN_INFO, ip);
 		print_ip_ins(" actual:   ", (unsigned char *)ip);
 		pr_cont("\n");
 		if (ftrace_expected) {
@@ -2035,14 +2031,12 @@ void ftrace_bug(int failed, struct dyn_ftrace *rec)
 		}
 		break;
 	case -EPERM:
-		FTRACE_WARN_ON_ONCE(1);
 		pr_info("ftrace faulted on writing ");
-		print_ip_sym(ip);
+		print_ip_sym(KERN_INFO, ip);
 		break;
 	default:
-		FTRACE_WARN_ON_ONCE(1);
 		pr_info("ftrace faulted on unknown error ");
-		print_ip_sym(ip);
+		print_ip_sym(KERN_INFO, ip);
 	}
 	print_bug_type();
 	if (rec) {
@@ -2067,6 +2061,8 @@ void ftrace_bug(int failed, struct dyn_ftrace *rec)
 		ip = ftrace_get_addr_curr(rec);
 		pr_cont("\n expected tramp: %lx\n", ip);
 	}
+
+	FTRACE_WARN_ON_ONCE(1);
 }
 
 static int ftrace_check_record(struct dyn_ftrace *rec, bool enable, bool update)
@@ -2261,7 +2257,7 @@ ftrace_find_tramp_ops_next(struct dyn_ftrace *rec,
 
 		if (hash_contains_ip(ip, op->func_hash))
 			return op;
-	} 
+	}
 
 	return NULL;
 }
@@ -2389,6 +2385,14 @@ struct ftrace_ops direct_ops = {
 	.flags		= FTRACE_OPS_FL_IPMODIFY | FTRACE_OPS_FL_RECURSION_SAFE
 			  | FTRACE_OPS_FL_DIRECT | FTRACE_OPS_FL_SAVE_REGS
 			  | FTRACE_OPS_FL_PERMANENT,
+	/*
+	 * By declaring the main trampoline as this trampoline
+	 * it will never have one allocated for it. Allocated
+	 * trampolines should not call direct functions.
+	 * The direct_ops should only be called by the builtin
+	 * ftrace_regs_caller trampoline.
+	 */
+	.trampoline	= FTRACE_REGS_ADDR,
 };
 #endif /* CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS */
 
@@ -2765,6 +2769,50 @@ void __weak arch_ftrace_trampoline_free(struct ftrace_ops *ops)
 {
 }
 
+/* List of trace_ops that have allocated trampolines */
+static LIST_HEAD(ftrace_ops_trampoline_list);
+
+static void ftrace_add_trampoline_to_kallsyms(struct ftrace_ops *ops)
+{
+	lockdep_assert_held(&ftrace_lock);
+	list_add_rcu(&ops->list, &ftrace_ops_trampoline_list);
+}
+
+static void ftrace_remove_trampoline_from_kallsyms(struct ftrace_ops *ops)
+{
+	lockdep_assert_held(&ftrace_lock);
+	list_del_rcu(&ops->list);
+}
+
+/*
+ * "__builtin__ftrace" is used as a module name in /proc/kallsyms for symbols
+ * for pages allocated for ftrace purposes, even though "__builtin__ftrace" is
+ * not a module.
+ */
+#define FTRACE_TRAMPOLINE_MOD "__builtin__ftrace"
+#define FTRACE_TRAMPOLINE_SYM "ftrace_trampoline"
+
+static void ftrace_trampoline_free(struct ftrace_ops *ops)
+{
+	if (ops && (ops->flags & FTRACE_OPS_FL_ALLOC_TRAMP) &&
+	    ops->trampoline) {
+		/*
+		 * Record the text poke event before the ksymbol unregister
+		 * event.
+		 */
+		perf_event_text_poke((void *)ops->trampoline,
+				     (void *)ops->trampoline,
+				     ops->trampoline_size, NULL, 0);
+		perf_event_ksymbol(PERF_RECORD_KSYMBOL_TYPE_OOL,
+				   ops->trampoline, ops->trampoline_size,
+				   true, FTRACE_TRAMPOLINE_SYM);
+		/* Remove from kallsyms after the perf events */
+		ftrace_remove_trampoline_from_kallsyms(ops);
+	}
+
+	arch_ftrace_trampoline_free(ops);
+}
+
 static void ftrace_startup_enable(int command)
 {
 	if (saved_ftrace_func != ftrace_trace_function) {
@@ -2922,7 +2970,7 @@ int ftrace_shutdown(struct ftrace_ops *ops, int command)
 		 * infrastructure to do the synchronization, thus we must do it
 		 * ourselves.
 		 */
-		schedule_on_each_cpu(ftrace_sync);
+		synchronize_rcu_tasks_rude();
 
 		/*
 		 * When the kernel is preeptive, tasks can be preempted
@@ -2935,7 +2983,7 @@ int ftrace_shutdown(struct ftrace_ops *ops, int command)
 			synchronize_rcu_tasks();
 
  free_ops:
-		arch_ftrace_trampoline_free(ops);
+		ftrace_trampoline_free(ops);
 	}
 
 	return 0;
@@ -3600,7 +3648,7 @@ static int t_show(struct seq_file *m, void *v)
 			if (direct)
 				seq_printf(m, "\n\tdirect-->%pS", (void *)direct);
 		}
-	}	
+	}
 
 	seq_putc(m, '\n');
 
@@ -5155,6 +5203,7 @@ int unregister_ftrace_direct(unsigned long ip, unsigned long addr)
 			list_del_rcu(&direct->next);
 			synchronize_rcu_tasks();
 			kfree(direct);
+			kfree(entry);
 			ftrace_direct_func_count--;
 		}
 	}
@@ -5877,7 +5926,7 @@ ftrace_graph_release(struct inode *inode, struct file *file)
 		 * infrastructure to do the synchronization, thus we must do it
 		 * ourselves.
 		 */
-		schedule_on_each_cpu(ftrace_sync);
+		synchronize_rcu_tasks_rude();
 
 		free_ftrace_hash(old_hash);
 	}
@@ -6178,6 +6227,27 @@ struct ftrace_mod_map {
 	unsigned int		num_funcs;
 };
 
+static int ftrace_get_trampoline_kallsym(unsigned int symnum,
+					 unsigned long *value, char *type,
+					 char *name, char *module_name,
+					 int *exported)
+{
+	struct ftrace_ops *op;
+
+	list_for_each_entry_rcu(op, &ftrace_ops_trampoline_list, list) {
+		if (!op->trampoline || symnum--)
+			continue;
+		*value = op->trampoline;
+		*type = 't';
+		strlcpy(name, FTRACE_TRAMPOLINE_SYM, KSYM_NAME_LEN);
+		strlcpy(module_name, FTRACE_TRAMPOLINE_MOD, MODULE_NAME_LEN);
+		*exported = 0;
+		return 0;
+	}
+
+	return -ERANGE;
+}
+
 #ifdef CONFIG_MODULES
 
 #define next_to_ftrace_page(p) container_of(p, struct ftrace_page, next)
@@ -6190,8 +6260,19 @@ static int referenced_filters(struct dyn_ftrace *rec)
 	int cnt = 0;
 
 	for (ops = ftrace_ops_list; ops != &ftrace_list_end; ops = ops->next) {
-		if (ops_references_rec(ops, rec))
-		    cnt++;
+		if (ops_references_rec(ops, rec)) {
+			if (WARN_ON_ONCE(ops->flags & FTRACE_OPS_FL_DIRECT))
+				continue;
+			if (WARN_ON_ONCE(ops->flags & FTRACE_OPS_FL_IPMODIFY))
+				continue;
+			cnt++;
+			if (ops->flags & FTRACE_OPS_FL_SAVE_REGS)
+				rec->flags |= FTRACE_FL_REGS;
+			if (cnt == 1 && ops->trampoline)
+				rec->flags |= FTRACE_FL_TRAMP;
+			else
+				rec->flags &= ~FTRACE_FL_TRAMP;
+		}
 	}
 
 	return cnt;
@@ -6370,8 +6451,8 @@ void ftrace_module_enable(struct module *mod)
 		if (ftrace_start_up)
 			cnt += referenced_filters(rec);
 
-		/* This clears FTRACE_FL_DISABLED */
-		rec->flags = cnt;
+		rec->flags &= ~FTRACE_FL_DISABLED;
+		rec->flags += cnt;
 
 		if (ftrace_start_up && cnt) {
 			int failed = __ftrace_replace_code(rec, 1);
@@ -6514,6 +6595,7 @@ int ftrace_mod_get_kallsym(unsigned int symnum, unsigned long *value,
 {
 	struct ftrace_mod_map *mod_map;
 	struct ftrace_mod_func *mod_func;
+	int ret;
 
 	preempt_disable();
 	list_for_each_entry_rcu(mod_map, &ftrace_mod_maps, list) {
@@ -6540,8 +6622,10 @@ int ftrace_mod_get_kallsym(unsigned int symnum, unsigned long *value,
 		WARN_ON(1);
 		break;
 	}
+	ret = ftrace_get_trampoline_kallsym(symnum, value, type, name,
+					    module_name, exported);
 	preempt_enable();
-	return -ERANGE;
+	return ret;
 }
 
 #else
@@ -6553,6 +6637,18 @@ allocate_ftrace_mod_map(struct module *mod,
 {
 	return NULL;
 }
+int ftrace_mod_get_kallsym(unsigned int symnum, unsigned long *value,
+			   char *type, char *name, char *module_name,
+			   int *exported)
+{
+	int ret;
+
+	preempt_disable();
+	ret = ftrace_get_trampoline_kallsym(symnum, value, type, name,
+					    module_name, exported);
+	preempt_enable();
+	return ret;
+}
 #endif /* CONFIG_MODULES */
 
 struct ftrace_init_func {
@@ -6733,7 +6829,24 @@ void __weak arch_ftrace_update_trampoline(struct ftrace_ops *ops)
 
 static void ftrace_update_trampoline(struct ftrace_ops *ops)
 {
+	unsigned long trampoline = ops->trampoline;
+
 	arch_ftrace_update_trampoline(ops);
+	if (ops->trampoline && ops->trampoline != trampoline &&
+	    (ops->flags & FTRACE_OPS_FL_ALLOC_TRAMP)) {
+		/* Add to kallsyms before the perf events */
+		ftrace_add_trampoline_to_kallsyms(ops);
+		perf_event_ksymbol(PERF_RECORD_KSYMBOL_TYPE_OOL,
+				   ops->trampoline, ops->trampoline_size, false,
+				   FTRACE_TRAMPOLINE_SYM);
+		/*
+		 * Record the perf text poke event after the ksymbol register
+		 * event.
+		 */
+		perf_event_text_poke((void *)ops->trampoline, NULL, 0,
+				     (void *)ops->trampoline,
+				     ops->trampoline_size);
+	}
 }
 
 void ftrace_init_trace_array(struct trace_array *tr)
@@ -6923,11 +7036,17 @@ ftrace_filter_pid_sched_switch_probe(void *data, bool preempt,
 {
 	struct trace_array *tr = data;
 	struct trace_pid_list *pid_list;
+	struct trace_pid_list *no_pid_list;
 
 	pid_list = rcu_dereference_sched(tr->function_pids);
+	no_pid_list = rcu_dereference_sched(tr->function_no_pids);
 
-	this_cpu_write(tr->array_buffer.data->ftrace_ignore_pid,
-		       trace_ignore_this_task(pid_list, next));
+	if (trace_ignore_this_task(pid_list, no_pid_list, next))
+		this_cpu_write(tr->array_buffer.data->ftrace_ignore_pid,
+			       FTRACE_PID_IGNORE);
+	else
+		this_cpu_write(tr->array_buffer.data->ftrace_ignore_pid,
+			       next->pid);
 }
 
 static void
@@ -6940,6 +7059,9 @@ ftrace_pid_follow_sched_process_fork(void *data,
 
 	pid_list = rcu_dereference_sched(tr->function_pids);
 	trace_filter_add_remove_task(pid_list, self, task);
+
+	pid_list = rcu_dereference_sched(tr->function_no_pids);
+	trace_filter_add_remove_task(pid_list, self, task);
 }
 
 static void
@@ -6950,6 +7072,9 @@ ftrace_pid_follow_sched_process_exit(void *data, struct task_struct *task)
 
 	pid_list = rcu_dereference_sched(tr->function_pids);
 	trace_filter_add_remove_task(pid_list, NULL, task);
+
+	pid_list = rcu_dereference_sched(tr->function_no_pids);
+	trace_filter_add_remove_task(pid_list, NULL, task);
 }
 
 void ftrace_pid_follow_fork(struct trace_array *tr, bool enable)
@@ -6957,52 +7082,67 @@ void ftrace_pid_follow_fork(struct trace_array *tr, bool enable)
 	if (enable) {
 		register_trace_sched_process_fork(ftrace_pid_follow_sched_process_fork,
 						  tr);
-		register_trace_sched_process_exit(ftrace_pid_follow_sched_process_exit,
+		register_trace_sched_process_free(ftrace_pid_follow_sched_process_exit,
 						  tr);
 	} else {
 		unregister_trace_sched_process_fork(ftrace_pid_follow_sched_process_fork,
 						    tr);
-		unregister_trace_sched_process_exit(ftrace_pid_follow_sched_process_exit,
+		unregister_trace_sched_process_free(ftrace_pid_follow_sched_process_exit,
 						    tr);
 	}
 }
 
-static void clear_ftrace_pids(struct trace_array *tr)
+static void clear_ftrace_pids(struct trace_array *tr, int type)
 {
 	struct trace_pid_list *pid_list;
+	struct trace_pid_list *no_pid_list;
 	int cpu;
 
 	pid_list = rcu_dereference_protected(tr->function_pids,
 					     lockdep_is_held(&ftrace_lock));
-	if (!pid_list)
+	no_pid_list = rcu_dereference_protected(tr->function_no_pids,
+						lockdep_is_held(&ftrace_lock));
+
+	/* Make sure there's something to do */
+	if (!pid_type_enabled(type, pid_list, no_pid_list))
 		return;
 
-	unregister_trace_sched_switch(ftrace_filter_pid_sched_switch_probe, tr);
+	/* See if the pids still need to be checked after this */
+	if (!still_need_pid_events(type, pid_list, no_pid_list)) {
+		unregister_trace_sched_switch(ftrace_filter_pid_sched_switch_probe, tr);
+		for_each_possible_cpu(cpu)
+			per_cpu_ptr(tr->array_buffer.data, cpu)->ftrace_ignore_pid = FTRACE_PID_TRACE;
+	}
 
-	for_each_possible_cpu(cpu)
-		per_cpu_ptr(tr->array_buffer.data, cpu)->ftrace_ignore_pid = false;
+	if (type & TRACE_PIDS)
+		rcu_assign_pointer(tr->function_pids, NULL);
 
-	rcu_assign_pointer(tr->function_pids, NULL);
+	if (type & TRACE_NO_PIDS)
+		rcu_assign_pointer(tr->function_no_pids, NULL);
 
 	/* Wait till all users are no longer using pid filtering */
 	synchronize_rcu();
 
-	trace_free_pid_list(pid_list);
+	if ((type & TRACE_PIDS) && pid_list)
+		trace_free_pid_list(pid_list);
+
+	if ((type & TRACE_NO_PIDS) && no_pid_list)
+		trace_free_pid_list(no_pid_list);
 }
 
 void ftrace_clear_pids(struct trace_array *tr)
 {
 	mutex_lock(&ftrace_lock);
 
-	clear_ftrace_pids(tr);
+	clear_ftrace_pids(tr, TRACE_PIDS | TRACE_NO_PIDS);
 
 	mutex_unlock(&ftrace_lock);
 }
 
-static void ftrace_pid_reset(struct trace_array *tr)
+static void ftrace_pid_reset(struct trace_array *tr, int type)
 {
 	mutex_lock(&ftrace_lock);
-	clear_ftrace_pids(tr);
+	clear_ftrace_pids(tr, type);
 
 	ftrace_update_pid_func();
 	ftrace_startup_all(0);
@@ -7066,9 +7206,45 @@ static const struct seq_operations ftrace_pid_sops = {
 	.show = fpid_show,
 };
 
-static int
-ftrace_pid_open(struct inode *inode, struct file *file)
+static void *fnpid_start(struct seq_file *m, loff_t *pos)
+	__acquires(RCU)
+{
+	struct trace_pid_list *pid_list;
+	struct trace_array *tr = m->private;
+
+	mutex_lock(&ftrace_lock);
+	rcu_read_lock_sched();
+
+	pid_list = rcu_dereference_sched(tr->function_no_pids);
+
+	if (!pid_list)
+		return !(*pos) ? FTRACE_NO_PIDS : NULL;
+
+	return trace_pid_start(pid_list, pos);
+}
+
+static void *fnpid_next(struct seq_file *m, void *v, loff_t *pos)
 {
+	struct trace_array *tr = m->private;
+	struct trace_pid_list *pid_list = rcu_dereference_sched(tr->function_no_pids);
+
+	if (v == FTRACE_NO_PIDS) {
+		(*pos)++;
+		return NULL;
+	}
+	return trace_pid_next(pid_list, v, pos);
+}
+
+static const struct seq_operations ftrace_no_pid_sops = {
+	.start = fnpid_start,
+	.next = fnpid_next,
+	.stop = fpid_stop,
+	.show = fpid_show,
+};
+
+static int pid_open(struct inode *inode, struct file *file, int type)
+{
+	const struct seq_operations *seq_ops;
 	struct trace_array *tr = inode->i_private;
 	struct seq_file *m;
 	int ret = 0;
@@ -7079,9 +7255,22 @@ ftrace_pid_open(struct inode *inode, struct file *file)
 
 	if ((file->f_mode & FMODE_WRITE) &&
 	    (file->f_flags & O_TRUNC))
-		ftrace_pid_reset(tr);
+		ftrace_pid_reset(tr, type);
 
-	ret = seq_open(file, &ftrace_pid_sops);
+	switch (type) {
+	case TRACE_PIDS:
+		seq_ops = &ftrace_pid_sops;
+		break;
+	case TRACE_NO_PIDS:
+		seq_ops = &ftrace_no_pid_sops;
+		break;
+	default:
+		trace_array_put(tr);
+		WARN_ON_ONCE(1);
+		return -EINVAL;
+	}
+
+	ret = seq_open(file, seq_ops);
 	if (ret < 0) {
 		trace_array_put(tr);
 	} else {
@@ -7093,10 +7282,23 @@ ftrace_pid_open(struct inode *inode, struct file *file)
 	return ret;
 }
 
+static int
+ftrace_pid_open(struct inode *inode, struct file *file)
+{
+	return pid_open(inode, file, TRACE_PIDS);
+}
+
+static int
+ftrace_no_pid_open(struct inode *inode, struct file *file)
+{
+	return pid_open(inode, file, TRACE_NO_PIDS);
+}
+
 static void ignore_task_cpu(void *data)
 {
 	struct trace_array *tr = data;
 	struct trace_pid_list *pid_list;
+	struct trace_pid_list *no_pid_list;
 
 	/*
 	 * This function is called by on_each_cpu() while the
@@ -7104,18 +7306,25 @@ static void ignore_task_cpu(void *data)
 	 */
 	pid_list = rcu_dereference_protected(tr->function_pids,
 					     mutex_is_locked(&ftrace_lock));
+	no_pid_list = rcu_dereference_protected(tr->function_no_pids,
+						mutex_is_locked(&ftrace_lock));
 
-	this_cpu_write(tr->array_buffer.data->ftrace_ignore_pid,
-		       trace_ignore_this_task(pid_list, current));
+	if (trace_ignore_this_task(pid_list, no_pid_list, current))
+		this_cpu_write(tr->array_buffer.data->ftrace_ignore_pid,
+			       FTRACE_PID_IGNORE);
+	else
+		this_cpu_write(tr->array_buffer.data->ftrace_ignore_pid,
+			       current->pid);
 }
 
 static ssize_t
-ftrace_pid_write(struct file *filp, const char __user *ubuf,
-		   size_t cnt, loff_t *ppos)
+pid_write(struct file *filp, const char __user *ubuf,
+	  size_t cnt, loff_t *ppos, int type)
 {
 	struct seq_file *m = filp->private_data;
 	struct trace_array *tr = m->private;
-	struct trace_pid_list *filtered_pids = NULL;
+	struct trace_pid_list *filtered_pids;
+	struct trace_pid_list *other_pids;
 	struct trace_pid_list *pid_list;
 	ssize_t ret;
 
@@ -7124,19 +7333,43 @@ ftrace_pid_write(struct file *filp, const char __user *ubuf,
 
 	mutex_lock(&ftrace_lock);
 
-	filtered_pids = rcu_dereference_protected(tr->function_pids,
+	switch (type) {
+	case TRACE_PIDS:
+		filtered_pids = rcu_dereference_protected(tr->function_pids,
 					     lockdep_is_held(&ftrace_lock));
+		other_pids = rcu_dereference_protected(tr->function_no_pids,
+					     lockdep_is_held(&ftrace_lock));
+		break;
+	case TRACE_NO_PIDS:
+		filtered_pids = rcu_dereference_protected(tr->function_no_pids,
+					     lockdep_is_held(&ftrace_lock));
+		other_pids = rcu_dereference_protected(tr->function_pids,
+					     lockdep_is_held(&ftrace_lock));
+		break;
+	default:
+		ret = -EINVAL;
+		WARN_ON_ONCE(1);
+		goto out;
+	}
 
 	ret = trace_pid_write(filtered_pids, &pid_list, ubuf, cnt);
 	if (ret < 0)
 		goto out;
 
-	rcu_assign_pointer(tr->function_pids, pid_list);
+	switch (type) {
+	case TRACE_PIDS:
+		rcu_assign_pointer(tr->function_pids, pid_list);
+		break;
+	case TRACE_NO_PIDS:
+		rcu_assign_pointer(tr->function_no_pids, pid_list);
+		break;
+	}
+
 
 	if (filtered_pids) {
 		synchronize_rcu();
 		trace_free_pid_list(filtered_pids);
-	} else if (pid_list) {
+	} else if (pid_list && !other_pids) {
 		/* Register a probe to set whether to ignore the tracing of a task */
 		register_trace_sched_switch(ftrace_filter_pid_sched_switch_probe, tr);
 	}
@@ -7159,6 +7392,20 @@ ftrace_pid_write(struct file *filp, const char __user *ubuf,
 	return ret;
 }
 
+static ssize_t
+ftrace_pid_write(struct file *filp, const char __user *ubuf,
+		 size_t cnt, loff_t *ppos)
+{
+	return pid_write(filp, ubuf, cnt, ppos, TRACE_PIDS);
+}
+
+static ssize_t
+ftrace_no_pid_write(struct file *filp, const char __user *ubuf,
+		    size_t cnt, loff_t *ppos)
+{
+	return pid_write(filp, ubuf, cnt, ppos, TRACE_NO_PIDS);
+}
+
 static int
 ftrace_pid_release(struct inode *inode, struct file *file)
 {
@@ -7177,10 +7424,20 @@ static const struct file_operations ftrace_pid_fops = {
 	.release	= ftrace_pid_release,
 };
 
+static const struct file_operations ftrace_no_pid_fops = {
+	.open		= ftrace_no_pid_open,
+	.write		= ftrace_no_pid_write,
+	.read		= seq_read,
+	.llseek		= tracing_lseek,
+	.release	= ftrace_pid_release,
+};
+
 void ftrace_init_tracefs(struct trace_array *tr, struct dentry *d_tracer)
 {
 	trace_create_file("set_ftrace_pid", 0644, d_tracer,
 			    tr, &ftrace_pid_fops);
+	trace_create_file("set_ftrace_notrace_pid", 0644, d_tracer,
+			    tr, &ftrace_no_pid_fops);
 }
 
 void __init ftrace_init_tracefs_toplevel(struct trace_array *tr,
diff --git a/kernel/trace/ftrace_internal.h b/kernel/trace/ftrace_internal.h
index 0456e0a3dab1..382775edf690 100644
--- a/kernel/trace/ftrace_internal.h
+++ b/kernel/trace/ftrace_internal.h
@@ -4,28 +4,6 @@
 
 #ifdef CONFIG_FUNCTION_TRACER
 
-/*
- * Traverse the ftrace_global_list, invoking all entries.  The reason that we
- * can use rcu_dereference_raw_check() is that elements removed from this list
- * are simply leaked, so there is no need to interact with a grace-period
- * mechanism.  The rcu_dereference_raw_check() calls are needed to handle
- * concurrent insertions into the ftrace_global_list.
- *
- * Silly Alpha and silly pointer-speculation compiler optimizations!
- */
-#define do_for_each_ftrace_op(op, list)			\
-	op = rcu_dereference_raw_check(list);			\
-	do
-
-/*
- * Optimized for just a single item in the list (as that is the normal case).
- */
-#define while_for_each_ftrace_op(op)				\
-	while (likely(op = rcu_dereference_raw_check((op)->next)) &&	\
-	       unlikely((op) != &ftrace_list_end))
-
-extern struct ftrace_ops __rcu *ftrace_ops_list;
-extern struct ftrace_ops ftrace_list_end;
 extern struct mutex ftrace_lock;
 extern struct ftrace_ops global_ops;
 
diff --git a/kernel/trace/preemptirq_delay_test.c b/kernel/trace/preemptirq_delay_test.c
index 31c0fad4cb9e..312d1a0ca3b6 100644
--- a/kernel/trace/preemptirq_delay_test.c
+++ b/kernel/trace/preemptirq_delay_test.c
@@ -16,6 +16,7 @@
 #include <linux/printk.h>
 #include <linux/string.h>
 #include <linux/sysfs.h>
+#include <linux/completion.h>
 
 static ulong delay = 100;
 static char test_mode[12] = "irq";
@@ -28,6 +29,8 @@ MODULE_PARM_DESC(delay, "Period in microseconds (100 us default)");
 MODULE_PARM_DESC(test_mode, "Mode of the test such as preempt, irq, or alternate (default irq)");
 MODULE_PARM_DESC(burst_size, "The size of a burst (default 1)");
 
+static struct completion done;
+
 #define MIN(x, y) ((x) < (y) ? (x) : (y))
 
 static void busy_wait(ulong time)
@@ -113,22 +116,47 @@ static int preemptirq_delay_run(void *data)
 
 	for (i = 0; i < s; i++)
 		(testfuncs[i])(i);
+
+	complete(&done);
+
+	set_current_state(TASK_INTERRUPTIBLE);
+	while (!kthread_should_stop()) {
+		schedule();
+		set_current_state(TASK_INTERRUPTIBLE);
+	}
+
+	__set_current_state(TASK_RUNNING);
+
 	return 0;
 }
 
-static struct task_struct *preemptirq_start_test(void)
+static int preemptirq_run_test(void)
 {
+	struct task_struct *task;
 	char task_name[50];
 
+	init_completion(&done);
+
 	snprintf(task_name, sizeof(task_name), "%s_test", test_mode);
-	return kthread_run(preemptirq_delay_run, NULL, task_name);
+	task =  kthread_run(preemptirq_delay_run, NULL, task_name);
+	if (IS_ERR(task))
+		return PTR_ERR(task);
+	if (task) {
+		wait_for_completion(&done);
+		kthread_stop(task);
+	}
+	return 0;
 }
 
 
 static ssize_t trigger_store(struct kobject *kobj, struct kobj_attribute *attr,
 			 const char *buf, size_t count)
 {
-	preemptirq_start_test();
+	ssize_t ret;
+
+	ret = preemptirq_run_test();
+	if (ret)
+		return ret;
 	return count;
 }
 
@@ -148,11 +176,9 @@ static struct kobject *preemptirq_delay_kobj;
 
 static int __init preemptirq_delay_init(void)
 {
-	struct task_struct *test_task;
 	int retval;
 
-	test_task = preemptirq_start_test();
-	retval = PTR_ERR_OR_ZERO(test_task);
+	retval = preemptirq_run_test();
 	if (retval != 0)
 		return retval;
 
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 61f0e92ace99..93ef0ab6ea20 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -193,7 +193,7 @@ rb_event_length(struct ring_buffer_event *event)
 	case RINGBUF_TYPE_DATA:
 		return rb_event_data_length(event);
 	default:
-		BUG();
+		WARN_ON_ONCE(1);
 	}
 	/* not hit */
 	return 0;
@@ -249,7 +249,7 @@ rb_event_data(struct ring_buffer_event *event)
 {
 	if (extended_time(event))
 		event = skip_time_extend(event);
-	BUG_ON(event->type_len > RINGBUF_TYPE_DATA_TYPE_LEN_MAX);
+	WARN_ON_ONCE(event->type_len > RINGBUF_TYPE_DATA_TYPE_LEN_MAX);
 	/* If length is in len field, then array[0] has the data */
 	if (event->type_len)
 		return (void *)&event->array[0];
@@ -270,6 +270,9 @@ EXPORT_SYMBOL_GPL(ring_buffer_event_data);
 #define for_each_buffer_cpu(buffer, cpu)		\
 	for_each_cpu(cpu, buffer->cpumask)
 
+#define for_each_online_buffer_cpu(buffer, cpu)		\
+	for_each_cpu_and(cpu, buffer->cpumask, cpu_online_mask)
+
 #define TS_SHIFT	27
 #define TS_MASK		((1ULL << TS_SHIFT) - 1)
 #define TS_DELTA_TEST	(~TS_MASK)
@@ -413,12 +416,27 @@ struct rb_irq_work {
 struct rb_event_info {
 	u64			ts;
 	u64			delta;
+	u64			before;
+	u64			after;
 	unsigned long		length;
 	struct buffer_page	*tail_page;
 	int			add_timestamp;
 };
 
 /*
+ * Used for the add_timestamp
+ *  NONE
+ *  EXTEND - wants a time extend
+ *  ABSOLUTE - the buffer requests all events to have absolute time stamps
+ *  FORCE - force a full time stamp.
+ */
+enum {
+	RB_ADD_STAMP_NONE		= 0,
+	RB_ADD_STAMP_EXTEND		= BIT(1),
+	RB_ADD_STAMP_ABSOLUTE		= BIT(2),
+	RB_ADD_STAMP_FORCE		= BIT(3)
+};
+/*
  * Used for which event context the event is in.
  *  NMI     = 0
  *  IRQ     = 1
@@ -435,12 +453,35 @@ enum {
 	RB_CTX_MAX
 };
 
+#if BITS_PER_LONG == 32
+#define RB_TIME_32
+#endif
+
+/* To test on 64 bit machines */
+//#define RB_TIME_32
+
+#ifdef RB_TIME_32
+
+struct rb_time_struct {
+	local_t		cnt;
+	local_t		top;
+	local_t		bottom;
+};
+#else
+#include <asm/local64.h>
+struct rb_time_struct {
+	local64_t	time;
+};
+#endif
+typedef struct rb_time_struct rb_time_t;
+
 /*
  * head_page == tail_page && head == tail then buffer is empty.
  */
 struct ring_buffer_per_cpu {
 	int				cpu;
 	atomic_t			record_disabled;
+	atomic_t			resize_disabled;
 	struct trace_buffer	*buffer;
 	raw_spinlock_t			reader_lock;	/* serialize readers */
 	arch_spinlock_t			lock;
@@ -469,7 +510,8 @@ struct ring_buffer_per_cpu {
 	size_t				shortest_full;
 	unsigned long			read;
 	unsigned long			read_bytes;
-	u64				write_stamp;
+	rb_time_t			write_stamp;
+	rb_time_t			before_stamp;
 	u64				read_stamp;
 	/* ring buffer pages to update, > 0 to add, < 0 to remove */
 	long				nr_pages_to_update;
@@ -484,7 +526,6 @@ struct trace_buffer {
 	unsigned			flags;
 	int				cpus;
 	atomic_t			record_disabled;
-	atomic_t			resize_disabled;
 	cpumask_var_t			cpumask;
 
 	struct lock_class_key		*reader_lock_key;
@@ -503,12 +544,199 @@ struct trace_buffer {
 struct ring_buffer_iter {
 	struct ring_buffer_per_cpu	*cpu_buffer;
 	unsigned long			head;
+	unsigned long			next_event;
 	struct buffer_page		*head_page;
 	struct buffer_page		*cache_reader_page;
 	unsigned long			cache_read;
 	u64				read_stamp;
+	u64				page_stamp;
+	struct ring_buffer_event	*event;
+	int				missed_events;
 };
 
+#ifdef RB_TIME_32
+
+/*
+ * On 32 bit machines, local64_t is very expensive. As the ring
+ * buffer doesn't need all the features of a true 64 bit atomic,
+ * on 32 bit, it uses these functions (64 still uses local64_t).
+ *
+ * For the ring buffer, 64 bit required operations for the time is
+ * the following:
+ *
+ *  - Only need 59 bits (uses 60 to make it even).
+ *  - Reads may fail if it interrupted a modification of the time stamp.
+ *      It will succeed if it did not interrupt another write even if
+ *      the read itself is interrupted by a write.
+ *      It returns whether it was successful or not.
+ *
+ *  - Writes always succeed and will overwrite other writes and writes
+ *      that were done by events interrupting the current write.
+ *
+ *  - A write followed by a read of the same time stamp will always succeed,
+ *      but may not contain the same value.
+ *
+ *  - A cmpxchg will fail if it interrupted another write or cmpxchg.
+ *      Other than that, it acts like a normal cmpxchg.
+ *
+ * The 60 bit time stamp is broken up by 30 bits in a top and bottom half
+ *  (bottom being the least significant 30 bits of the 60 bit time stamp).
+ *
+ * The two most significant bits of each half holds a 2 bit counter (0-3).
+ * Each update will increment this counter by one.
+ * When reading the top and bottom, if the two counter bits match then the
+ *  top and bottom together make a valid 60 bit number.
+ */
+#define RB_TIME_SHIFT	30
+#define RB_TIME_VAL_MASK ((1 << RB_TIME_SHIFT) - 1)
+
+static inline int rb_time_cnt(unsigned long val)
+{
+	return (val >> RB_TIME_SHIFT) & 3;
+}
+
+static inline u64 rb_time_val(unsigned long top, unsigned long bottom)
+{
+	u64 val;
+
+	val = top & RB_TIME_VAL_MASK;
+	val <<= RB_TIME_SHIFT;
+	val |= bottom & RB_TIME_VAL_MASK;
+
+	return val;
+}
+
+static inline bool __rb_time_read(rb_time_t *t, u64 *ret, unsigned long *cnt)
+{
+	unsigned long top, bottom;
+	unsigned long c;
+
+	/*
+	 * If the read is interrupted by a write, then the cnt will
+	 * be different. Loop until both top and bottom have been read
+	 * without interruption.
+	 */
+	do {
+		c = local_read(&t->cnt);
+		top = local_read(&t->top);
+		bottom = local_read(&t->bottom);
+	} while (c != local_read(&t->cnt));
+
+	*cnt = rb_time_cnt(top);
+
+	/* If top and bottom counts don't match, this interrupted a write */
+	if (*cnt != rb_time_cnt(bottom))
+		return false;
+
+	*ret = rb_time_val(top, bottom);
+	return true;
+}
+
+static bool rb_time_read(rb_time_t *t, u64 *ret)
+{
+	unsigned long cnt;
+
+	return __rb_time_read(t, ret, &cnt);
+}
+
+static inline unsigned long rb_time_val_cnt(unsigned long val, unsigned long cnt)
+{
+	return (val & RB_TIME_VAL_MASK) | ((cnt & 3) << RB_TIME_SHIFT);
+}
+
+static inline void rb_time_split(u64 val, unsigned long *top, unsigned long *bottom)
+{
+	*top = (unsigned long)((val >> RB_TIME_SHIFT) & RB_TIME_VAL_MASK);
+	*bottom = (unsigned long)(val & RB_TIME_VAL_MASK);
+}
+
+static inline void rb_time_val_set(local_t *t, unsigned long val, unsigned long cnt)
+{
+	val = rb_time_val_cnt(val, cnt);
+	local_set(t, val);
+}
+
+static void rb_time_set(rb_time_t *t, u64 val)
+{
+	unsigned long cnt, top, bottom;
+
+	rb_time_split(val, &top, &bottom);
+
+	/* Writes always succeed with a valid number even if it gets interrupted. */
+	do {
+		cnt = local_inc_return(&t->cnt);
+		rb_time_val_set(&t->top, top, cnt);
+		rb_time_val_set(&t->bottom, bottom, cnt);
+	} while (cnt != local_read(&t->cnt));
+}
+
+static inline bool
+rb_time_read_cmpxchg(local_t *l, unsigned long expect, unsigned long set)
+{
+	unsigned long ret;
+
+	ret = local_cmpxchg(l, expect, set);
+	return ret == expect;
+}
+
+static int rb_time_cmpxchg(rb_time_t *t, u64 expect, u64 set)
+{
+	unsigned long cnt, top, bottom;
+	unsigned long cnt2, top2, bottom2;
+	u64 val;
+
+	/* The cmpxchg always fails if it interrupted an update */
+	 if (!__rb_time_read(t, &val, &cnt2))
+		 return false;
+
+	 if (val != expect)
+		 return false;
+
+	 cnt = local_read(&t->cnt);
+	 if ((cnt & 3) != cnt2)
+		 return false;
+
+	 cnt2 = cnt + 1;
+
+	 rb_time_split(val, &top, &bottom);
+	 top = rb_time_val_cnt(top, cnt);
+	 bottom = rb_time_val_cnt(bottom, cnt);
+
+	 rb_time_split(set, &top2, &bottom2);
+	 top2 = rb_time_val_cnt(top2, cnt2);
+	 bottom2 = rb_time_val_cnt(bottom2, cnt2);
+
+	if (!rb_time_read_cmpxchg(&t->cnt, cnt, cnt2))
+		return false;
+	if (!rb_time_read_cmpxchg(&t->top, top, top2))
+		return false;
+	if (!rb_time_read_cmpxchg(&t->bottom, bottom, bottom2))
+		return false;
+	return true;
+}
+
+#else /* 64 bits */
+
+/* local64_t always succeeds */
+
+static inline bool rb_time_read(rb_time_t *t, u64 *ret)
+{
+	*ret = local64_read(&t->time);
+	return true;
+}
+static void rb_time_set(rb_time_t *t, u64 val)
+{
+	local64_set(&t->time, val);
+}
+
+static bool rb_time_cmpxchg(rb_time_t *t, u64 expect, u64 set)
+{
+	u64 val;
+	val = local64_cmpxchg(&t->time, expect, set);
+	return val == expect;
+}
+#endif
+
 /**
  * ring_buffer_nr_pages - get the number of buffer pages in the ring buffer
  * @buffer: The ring_buffer to get the number of pages from
@@ -573,7 +801,7 @@ static void rb_wake_up_waiters(struct irq_work *work)
  */
 int ring_buffer_wait(struct trace_buffer *buffer, int cpu, int full)
 {
-	struct ring_buffer_per_cpu *uninitialized_var(cpu_buffer);
+	struct ring_buffer_per_cpu *cpu_buffer;
 	DEFINE_WAIT(wait);
 	struct rb_irq_work *work;
 	int ret = 0;
@@ -742,8 +970,16 @@ __poll_t ring_buffer_poll_wait(struct trace_buffer *buffer, int cpu,
 
 static inline u64 rb_time_stamp(struct trace_buffer *buffer)
 {
+	u64 ts;
+
+	/* Skip retpolines :-( */
+	if (IS_ENABLED(CONFIG_RETPOLINE) && likely(buffer->clock == trace_clock_local))
+		ts = trace_clock_local();
+	else
+		ts = buffer->clock();
+
 	/* shift to debug/test normalization and TIME_EXTENTS */
-	return buffer->clock() << DEBUG_SHIFT;
+	return ts << DEBUG_SHIFT;
 }
 
 u64 ring_buffer_time_stamp(struct trace_buffer *buffer, int cpu)
@@ -1737,18 +1973,24 @@ int ring_buffer_resize(struct trace_buffer *buffer, unsigned long size,
 
 	size = nr_pages * BUF_PAGE_SIZE;
 
-	/*
-	 * Don't succeed if resizing is disabled, as a reader might be
-	 * manipulating the ring buffer and is expecting a sane state while
-	 * this is true.
-	 */
-	if (atomic_read(&buffer->resize_disabled))
-		return -EBUSY;
-
 	/* prevent another thread from changing buffer sizes */
 	mutex_lock(&buffer->mutex);
 
+
 	if (cpu_id == RING_BUFFER_ALL_CPUS) {
+		/*
+		 * Don't succeed if resizing is disabled, as a reader might be
+		 * manipulating the ring buffer and is expecting a sane state while
+		 * this is true.
+		 */
+		for_each_buffer_cpu(buffer, cpu) {
+			cpu_buffer = buffer->buffers[cpu];
+			if (atomic_read(&cpu_buffer->resize_disabled)) {
+				err = -EBUSY;
+				goto out_err_unlock;
+			}
+		}
+
 		/* calculate the pages to update */
 		for_each_buffer_cpu(buffer, cpu) {
 			cpu_buffer = buffer->buffers[cpu];
@@ -1816,6 +2058,16 @@ int ring_buffer_resize(struct trace_buffer *buffer, unsigned long size,
 		if (nr_pages == cpu_buffer->nr_pages)
 			goto out;
 
+		/*
+		 * Don't succeed if resizing is disabled, as a reader might be
+		 * manipulating the ring buffer and is expecting a sane state while
+		 * this is true.
+		 */
+		if (atomic_read(&cpu_buffer->resize_disabled)) {
+			err = -EBUSY;
+			goto out_err_unlock;
+		}
+
 		cpu_buffer->nr_pages_to_update = nr_pages -
 						cpu_buffer->nr_pages;
 
@@ -1885,6 +2137,7 @@ int ring_buffer_resize(struct trace_buffer *buffer, unsigned long size,
 			free_buffer_page(bpage);
 		}
 	}
+ out_err_unlock:
 	mutex_unlock(&buffer->mutex);
 	return err;
 }
@@ -1913,15 +2166,63 @@ rb_reader_event(struct ring_buffer_per_cpu *cpu_buffer)
 			       cpu_buffer->reader_page->read);
 }
 
-static __always_inline struct ring_buffer_event *
-rb_iter_head_event(struct ring_buffer_iter *iter)
+static __always_inline unsigned rb_page_commit(struct buffer_page *bpage)
 {
-	return __rb_page_index(iter->head_page, iter->head);
+	return local_read(&bpage->page->commit);
 }
 
-static __always_inline unsigned rb_page_commit(struct buffer_page *bpage)
+static struct ring_buffer_event *
+rb_iter_head_event(struct ring_buffer_iter *iter)
 {
-	return local_read(&bpage->page->commit);
+	struct ring_buffer_event *event;
+	struct buffer_page *iter_head_page = iter->head_page;
+	unsigned long commit;
+	unsigned length;
+
+	if (iter->head != iter->next_event)
+		return iter->event;
+
+	/*
+	 * When the writer goes across pages, it issues a cmpxchg which
+	 * is a mb(), which will synchronize with the rmb here.
+	 * (see rb_tail_page_update() and __rb_reserve_next())
+	 */
+	commit = rb_page_commit(iter_head_page);
+	smp_rmb();
+	event = __rb_page_index(iter_head_page, iter->head);
+	length = rb_event_length(event);
+
+	/*
+	 * READ_ONCE() doesn't work on functions and we don't want the
+	 * compiler doing any crazy optimizations with length.
+	 */
+	barrier();
+
+	if ((iter->head + length) > commit || length > BUF_MAX_DATA_SIZE)
+		/* Writer corrupted the read? */
+		goto reset;
+
+	memcpy(iter->event, event, length);
+	/*
+	 * If the page stamp is still the same after this rmb() then the
+	 * event was safely copied without the writer entering the page.
+	 */
+	smp_rmb();
+
+	/* Make sure the page didn't change since we read this */
+	if (iter->page_stamp != iter_head_page->page->time_stamp ||
+	    commit > rb_page_commit(iter_head_page))
+		goto reset;
+
+	iter->next_event = iter->head + length;
+	return iter->event;
+ reset:
+	/* Reset to the beginning */
+	iter->page_stamp = iter->read_stamp = iter->head_page->page->time_stamp;
+	iter->head = 0;
+	iter->next_event = 0;
+	iter->missed_events = 1;
+	return NULL;
 }
 
 /* Size is determined by what has been committed */
@@ -1959,8 +2260,9 @@ static void rb_inc_iter(struct ring_buffer_iter *iter)
 	else
 		rb_inc_page(cpu_buffer, &iter->head_page);
 
-	iter->read_stamp = iter->head_page->page->time_stamp;
+	iter->page_stamp = iter->read_stamp = iter->head_page->page->time_stamp;
 	iter->head = 0;
+	iter->next_event = 0;
 }
 
 /*
@@ -2302,8 +2604,8 @@ rb_move_tail(struct ring_buffer_per_cpu *cpu_buffer,
 	return NULL;
 }
 
-/* Slow path, do not inline */
-static noinline struct ring_buffer_event *
+/* Slow path */
+static struct ring_buffer_event *
 rb_add_time_stamp(struct ring_buffer_event *event, u64 delta, bool abs)
 {
 	if (abs)
@@ -2327,6 +2629,66 @@ rb_add_time_stamp(struct ring_buffer_event *event, u64 delta, bool abs)
 static inline bool rb_event_is_commit(struct ring_buffer_per_cpu *cpu_buffer,
 				     struct ring_buffer_event *event);
 
+#ifndef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK
+static inline bool sched_clock_stable(void)
+{
+	return true;
+}
+#endif
+
+static void
+rb_check_timestamp(struct ring_buffer_per_cpu *cpu_buffer,
+		   struct rb_event_info *info)
+{
+	u64 write_stamp;
+
+	WARN_ONCE(1, "Delta way too big! %llu ts=%llu before=%llu after=%llu write stamp=%llu\n%s",
+		  (unsigned long long)info->delta,
+		  (unsigned long long)info->ts,
+		  (unsigned long long)info->before,
+		  (unsigned long long)info->after,
+		  (unsigned long long)(rb_time_read(&cpu_buffer->write_stamp, &write_stamp) ? write_stamp : 0),
+		  sched_clock_stable() ? "" :
+		  "If you just came from a suspend/resume,\n"
+		  "please switch to the trace global clock:\n"
+		  "  echo global > /sys/kernel/debug/tracing/trace_clock\n"
+		  "or add trace_clock=global to the kernel command line\n");
+}
+
+static void rb_add_timestamp(struct ring_buffer_per_cpu *cpu_buffer,
+				      struct ring_buffer_event **event,
+				      struct rb_event_info *info,
+				      u64 *delta,
+				      unsigned int *length)
+{
+	bool abs = info->add_timestamp &
+		(RB_ADD_STAMP_FORCE | RB_ADD_STAMP_ABSOLUTE);
+
+	if (unlikely(info->delta > (1ULL << 59))) {
+		/* did the clock go backwards */
+		if (info->before == info->after && info->before > info->ts) {
+			/* not interrupted */
+			static int once;
+
+			/*
+			 * This is possible with a recalibrating of the TSC.
+			 * Do not produce a call stack, but just report it.
+			 */
+			if (!once) {
+				once++;
+				pr_warn("Ring buffer clock went backwards: %llu -> %llu\n",
+					info->before, info->ts);
+			}
+		} else
+			rb_check_timestamp(cpu_buffer, info);
+		if (!abs)
+			info->delta = 0;
+	}
+	*event = rb_add_time_stamp(*event, info->delta, abs);
+	*length -= RB_LEN_TIME_EXTEND;
+	*delta = 0;
+}
+
 /**
  * rb_update_event - update event type and data
  * @cpu_buffer: The per cpu buffer of the @event
@@ -2346,21 +2708,12 @@ rb_update_event(struct ring_buffer_per_cpu *cpu_buffer,
 	unsigned length = info->length;
 	u64 delta = info->delta;
 
-	/* Only a commit updates the timestamp */
-	if (unlikely(!rb_event_is_commit(cpu_buffer, event)))
-		delta = 0;
-
 	/*
 	 * If we need to add a timestamp, then we
 	 * add it to the start of the reserved space.
 	 */
-	if (unlikely(info->add_timestamp)) {
-		bool abs = ring_buffer_time_stamp_abs(cpu_buffer->buffer);
-
-		event = rb_add_time_stamp(event, info->delta, abs);
-		length -= RB_LEN_TIME_EXTEND;
-		delta = 0;
-	}
+	if (unlikely(info->add_timestamp))
+		rb_add_timestamp(cpu_buffer, &event, info, &delta, &length);
 
 	event->time_delta = delta;
 	length -= RB_EVNT_HDR_SIZE;
@@ -2403,12 +2756,38 @@ static unsigned rb_calculate_event_length(unsigned length)
 	return length;
 }
 
-#ifndef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK
-static inline bool sched_clock_stable(void)
+static __always_inline bool
+rb_event_is_commit(struct ring_buffer_per_cpu *cpu_buffer,
+		   struct ring_buffer_event *event)
 {
-	return true;
+	unsigned long addr = (unsigned long)event;
+	unsigned long index;
+
+	index = rb_event_index(event);
+	addr &= PAGE_MASK;
+
+	return cpu_buffer->commit_page->page == (void *)addr &&
+		rb_commit_index(cpu_buffer) == index;
+}
+
+static u64 rb_time_delta(struct ring_buffer_event *event)
+{
+	switch (event->type_len) {
+	case RINGBUF_TYPE_PADDING:
+		return 0;
+
+	case RINGBUF_TYPE_TIME_EXTEND:
+		return ring_buffer_event_time_stamp(event);
+
+	case RINGBUF_TYPE_TIME_STAMP:
+		return 0;
+
+	case RINGBUF_TYPE_DATA:
+		return event->time_delta;
+	default:
+		return 0;
+	}
 }
-#endif
 
 static inline int
 rb_try_to_discard(struct ring_buffer_per_cpu *cpu_buffer,
@@ -2418,6 +2797,8 @@ rb_try_to_discard(struct ring_buffer_per_cpu *cpu_buffer,
 	struct buffer_page *bpage;
 	unsigned long index;
 	unsigned long addr;
+	u64 write_stamp;
+	u64 delta;
 
 	new_index = rb_event_index(event);
 	old_index = new_index + rb_event_ts_length(event);
@@ -2426,10 +2807,32 @@ rb_try_to_discard(struct ring_buffer_per_cpu *cpu_buffer,
 
 	bpage = READ_ONCE(cpu_buffer->tail_page);
 
+	delta = rb_time_delta(event);
+
+	if (!rb_time_read(&cpu_buffer->write_stamp, &write_stamp))
+		return 0;
+
+	/* Make sure the write stamp is read before testing the location */
+	barrier();
+
 	if (bpage->page == (void *)addr && rb_page_write(bpage) == old_index) {
 		unsigned long write_mask =
 			local_read(&bpage->write) & ~RB_WRITE_MASK;
 		unsigned long event_length = rb_event_length(event);
+
+		/* Something came in, can't discard */
+		if (!rb_time_cmpxchg(&cpu_buffer->write_stamp,
+				       write_stamp, write_stamp - delta))
+			return 0;
+
+		/*
+		 * If an event were to come in now, it would see that the
+		 * write_stamp and the before_stamp are different, and assume
+		 * that this event just added itself before updating
+		 * the write stamp. The interrupting event will fix the
+		 * write stamp for us, and use the before stamp as its delta.
+		 */
+
 		/*
 		 * This is on the tail page. It is possible that
 		 * a write could come in and move the tail page
@@ -2481,10 +2884,6 @@ rb_set_commit_to_write(struct ring_buffer_per_cpu *cpu_buffer)
 		local_set(&cpu_buffer->commit_page->page->commit,
 			  rb_page_write(cpu_buffer->commit_page));
 		rb_inc_page(cpu_buffer, &cpu_buffer->commit_page);
-		/* Only update the write stamp if the page has an event */
-		if (rb_page_write(cpu_buffer->commit_page))
-			cpu_buffer->write_stamp =
-				cpu_buffer->commit_page->page->time_stamp;
 		/* add barrier to keep gcc from optimizing too much */
 		barrier();
 	}
@@ -2556,54 +2955,10 @@ static inline void rb_event_discard(struct ring_buffer_event *event)
 		event->time_delta = 1;
 }
 
-static __always_inline bool
-rb_event_is_commit(struct ring_buffer_per_cpu *cpu_buffer,
-		   struct ring_buffer_event *event)
-{
-	unsigned long addr = (unsigned long)event;
-	unsigned long index;
-
-	index = rb_event_index(event);
-	addr &= PAGE_MASK;
-
-	return cpu_buffer->commit_page->page == (void *)addr &&
-		rb_commit_index(cpu_buffer) == index;
-}
-
-static __always_inline void
-rb_update_write_stamp(struct ring_buffer_per_cpu *cpu_buffer,
-		      struct ring_buffer_event *event)
-{
-	u64 delta;
-
-	/*
-	 * The event first in the commit queue updates the
-	 * time stamp.
-	 */
-	if (rb_event_is_commit(cpu_buffer, event)) {
-		/*
-		 * A commit event that is first on a page
-		 * updates the write timestamp with the page stamp
-		 */
-		if (!rb_event_index(event))
-			cpu_buffer->write_stamp =
-				cpu_buffer->commit_page->page->time_stamp;
-		else if (event->type_len == RINGBUF_TYPE_TIME_EXTEND) {
-			delta = ring_buffer_event_time_stamp(event);
-			cpu_buffer->write_stamp += delta;
-		} else if (event->type_len == RINGBUF_TYPE_TIME_STAMP) {
-			delta = ring_buffer_event_time_stamp(event);
-			cpu_buffer->write_stamp = delta;
-		} else
-			cpu_buffer->write_stamp += event->time_delta;
-	}
-}
-
 static void rb_commit(struct ring_buffer_per_cpu *cpu_buffer,
 		      struct ring_buffer_event *event)
 {
 	local_inc(&cpu_buffer->entries);
-	rb_update_write_stamp(cpu_buffer, event);
 	rb_end_commit(cpu_buffer);
 }
 
@@ -2794,58 +3149,138 @@ int ring_buffer_unlock_commit(struct trace_buffer *buffer,
 }
 EXPORT_SYMBOL_GPL(ring_buffer_unlock_commit);
 
-static noinline void
-rb_handle_timestamp(struct ring_buffer_per_cpu *cpu_buffer,
-		    struct rb_event_info *info)
-{
-	WARN_ONCE(info->delta > (1ULL << 59),
-		  KERN_WARNING "Delta way too big! %llu ts=%llu write stamp = %llu\n%s",
-		  (unsigned long long)info->delta,
-		  (unsigned long long)info->ts,
-		  (unsigned long long)cpu_buffer->write_stamp,
-		  sched_clock_stable() ? "" :
-		  "If you just came from a suspend/resume,\n"
-		  "please switch to the trace global clock:\n"
-		  "  echo global > /sys/kernel/debug/tracing/trace_clock\n"
-		  "or add trace_clock=global to the kernel command line\n");
-	info->add_timestamp = 1;
-}
-
 static struct ring_buffer_event *
 __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
 		  struct rb_event_info *info)
 {
 	struct ring_buffer_event *event;
 	struct buffer_page *tail_page;
-	unsigned long tail, write;
-
-	/*
-	 * If the time delta since the last event is too big to
-	 * hold in the time field of the event, then we append a
-	 * TIME EXTEND event ahead of the data event.
-	 */
-	if (unlikely(info->add_timestamp))
-		info->length += RB_LEN_TIME_EXTEND;
+	unsigned long tail, write, w;
+	bool a_ok;
+	bool b_ok;
 
 	/* Don't let the compiler play games with cpu_buffer->tail_page */
 	tail_page = info->tail_page = READ_ONCE(cpu_buffer->tail_page);
-	write = local_add_return(info->length, &tail_page->write);
+
+ /*A*/	w = local_read(&tail_page->write) & RB_WRITE_MASK;
+	barrier();
+	b_ok = rb_time_read(&cpu_buffer->before_stamp, &info->before);
+	a_ok = rb_time_read(&cpu_buffer->write_stamp, &info->after);
+	barrier();
+	info->ts = rb_time_stamp(cpu_buffer->buffer);
+
+	if ((info->add_timestamp & RB_ADD_STAMP_ABSOLUTE)) {
+		info->delta = info->ts;
+	} else {
+		/*
+		 * If interrupting an event time update, we may need an
+		 * absolute timestamp.
+		 * Don't bother if this is the start of a new page (w == 0).
+		 */
+		if (unlikely(!a_ok || !b_ok || (info->before != info->after && w))) {
+			info->add_timestamp |= RB_ADD_STAMP_FORCE | RB_ADD_STAMP_EXTEND;
+			info->length += RB_LEN_TIME_EXTEND;
+		} else {
+			info->delta = info->ts - info->after;
+			if (unlikely(test_time_stamp(info->delta))) {
+				info->add_timestamp |= RB_ADD_STAMP_EXTEND;
+				info->length += RB_LEN_TIME_EXTEND;
+			}
+		}
+	}
+
+ /*B*/	rb_time_set(&cpu_buffer->before_stamp, info->ts);
+
+ /*C*/	write = local_add_return(info->length, &tail_page->write);
 
 	/* set write to only the index of the write */
 	write &= RB_WRITE_MASK;
+
 	tail = write - info->length;
 
+	/* See if we shot pass the end of this buffer page */
+	if (unlikely(write > BUF_PAGE_SIZE)) {
+		if (tail != w) {
+			/* before and after may now different, fix it up*/
+			b_ok = rb_time_read(&cpu_buffer->before_stamp, &info->before);
+			a_ok = rb_time_read(&cpu_buffer->write_stamp, &info->after);
+			if (a_ok && b_ok && info->before != info->after)
+				(void)rb_time_cmpxchg(&cpu_buffer->before_stamp,
+						      info->before, info->after);
+		}
+		return rb_move_tail(cpu_buffer, tail, info);
+	}
+
+	if (likely(tail == w)) {
+		u64 save_before;
+		bool s_ok;
+
+		/* Nothing interrupted us between A and C */
+ /*D*/		rb_time_set(&cpu_buffer->write_stamp, info->ts);
+		barrier();
+ /*E*/		s_ok = rb_time_read(&cpu_buffer->before_stamp, &save_before);
+		RB_WARN_ON(cpu_buffer, !s_ok);
+		if (likely(!(info->add_timestamp &
+			     (RB_ADD_STAMP_FORCE | RB_ADD_STAMP_ABSOLUTE))))
+			/* This did not interrupt any time update */
+			info->delta = info->ts - info->after;
+		else
+			/* Just use full timestamp for inerrupting event */
+			info->delta = info->ts;
+		barrier();
+		if (unlikely(info->ts != save_before)) {
+			/* SLOW PATH - Interrupted between C and E */
+
+			a_ok = rb_time_read(&cpu_buffer->write_stamp, &info->after);
+			RB_WARN_ON(cpu_buffer, !a_ok);
+
+			/* Write stamp must only go forward */
+			if (save_before > info->after) {
+				/*
+				 * We do not care about the result, only that
+				 * it gets updated atomically.
+				 */
+				(void)rb_time_cmpxchg(&cpu_buffer->write_stamp,
+						      info->after, save_before);
+			}
+		}
+	} else {
+		u64 ts;
+		/* SLOW PATH - Interrupted between A and C */
+		a_ok = rb_time_read(&cpu_buffer->write_stamp, &info->after);
+		/* Was interrupted before here, write_stamp must be valid */
+		RB_WARN_ON(cpu_buffer, !a_ok);
+		ts = rb_time_stamp(cpu_buffer->buffer);
+		barrier();
+ /*E*/		if (write == (local_read(&tail_page->write) & RB_WRITE_MASK) &&
+		    info->after < ts) {
+			/* Nothing came after this event between C and E */
+			info->delta = ts - info->after;
+			(void)rb_time_cmpxchg(&cpu_buffer->write_stamp,
+					      info->after, info->ts);
+			info->ts = ts;
+		} else {
+			/*
+			 * Interrupted beween C and E:
+			 * Lost the previous events time stamp. Just set the
+			 * delta to zero, and this will be the same time as
+			 * the event this event interrupted. And the events that
+			 * came after this will still be correct (as they would
+			 * have built their delta on the previous event.
+			 */
+			info->delta = 0;
+		}
+		info->add_timestamp &= ~RB_ADD_STAMP_FORCE;
+	}
+
 	/*
 	 * If this is the first commit on the page, then it has the same
 	 * timestamp as the page itself.
 	 */
-	if (!tail && !ring_buffer_time_stamp_abs(cpu_buffer->buffer))
+	if (unlikely(!tail && !(info->add_timestamp &
+				(RB_ADD_STAMP_FORCE | RB_ADD_STAMP_ABSOLUTE))))
 		info->delta = 0;
 
-	/* See if we shot pass the end of this buffer page */
-	if (unlikely(write > BUF_PAGE_SIZE))
-		return rb_move_tail(cpu_buffer, tail, info);
-
 	/* We reserved something on the buffer */
 
 	event = __rb_page_index(tail_page, tail);
@@ -2857,7 +3292,7 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
 	 * If this is the first commit on the page, then update
 	 * its timestamp.
 	 */
-	if (!tail)
+	if (unlikely(!tail))
 		tail_page->page->time_stamp = info->ts;
 
 	/* account for these added bytes */
@@ -2874,9 +3309,10 @@ rb_reserve_next_event(struct trace_buffer *buffer,
 	struct ring_buffer_event *event;
 	struct rb_event_info info;
 	int nr_loops = 0;
-	u64 diff;
+	int add_ts_default;
 
 	rb_start_commit(cpu_buffer);
+	/* The commit page can not change after this */
 
 #ifdef CONFIG_RING_BUFFER_ALLOW_SWAP
 	/*
@@ -2894,8 +3330,16 @@ rb_reserve_next_event(struct trace_buffer *buffer,
 #endif
 
 	info.length = rb_calculate_event_length(length);
+
+	if (ring_buffer_time_stamp_abs(cpu_buffer->buffer)) {
+		add_ts_default = RB_ADD_STAMP_ABSOLUTE;
+		info.length += RB_LEN_TIME_EXTEND;
+	} else {
+		add_ts_default = RB_ADD_STAMP_NONE;
+	}
+
  again:
-	info.add_timestamp = 0;
+	info.add_timestamp = add_ts_default;
 	info.delta = 0;
 
 	/*
@@ -2910,35 +3354,16 @@ rb_reserve_next_event(struct trace_buffer *buffer,
 	if (RB_WARN_ON(cpu_buffer, ++nr_loops > 1000))
 		goto out_fail;
 
-	info.ts = rb_time_stamp(cpu_buffer->buffer);
-	diff = info.ts - cpu_buffer->write_stamp;
-
-	/* make sure this diff is calculated here */
-	barrier();
-
-	if (ring_buffer_time_stamp_abs(buffer)) {
-		info.delta = info.ts;
-		rb_handle_timestamp(cpu_buffer, &info);
-	} else /* Did the write stamp get updated already? */
-		if (likely(info.ts >= cpu_buffer->write_stamp)) {
-		info.delta = diff;
-		if (unlikely(test_time_stamp(info.delta)))
-			rb_handle_timestamp(cpu_buffer, &info);
-	}
-
 	event = __rb_reserve_next(cpu_buffer, &info);
 
 	if (unlikely(PTR_ERR(event) == -EAGAIN)) {
-		if (info.add_timestamp)
+		if (info.add_timestamp & (RB_ADD_STAMP_FORCE | RB_ADD_STAMP_EXTEND))
 			info.length -= RB_LEN_TIME_EXTEND;
 		goto again;
 	}
 
-	if (!event)
-		goto out_fail;
-
-	return event;
-
+	if (likely(event))
+		return event;
  out_fail:
 	rb_end_commit(cpu_buffer);
 	return NULL;
@@ -3084,11 +3509,6 @@ void ring_buffer_discard_commit(struct trace_buffer *buffer,
 	if (rb_try_to_discard(cpu_buffer, event))
 		goto out;
 
-	/*
-	 * The commit is still visible by the reader, so we
-	 * must still update the timestamp.
-	 */
-	rb_update_write_stamp(cpu_buffer, event);
  out:
 	rb_end_commit(cpu_buffer);
 
@@ -3547,14 +3967,18 @@ static void rb_iter_reset(struct ring_buffer_iter *iter)
 	/* Iterator usage is expected to have record disabled */
 	iter->head_page = cpu_buffer->reader_page;
 	iter->head = cpu_buffer->reader_page->read;
+	iter->next_event = iter->head;
 
 	iter->cache_reader_page = iter->head_page;
 	iter->cache_read = cpu_buffer->read;
 
-	if (iter->head)
+	if (iter->head) {
 		iter->read_stamp = cpu_buffer->read_stamp;
-	else
+		iter->page_stamp = cpu_buffer->reader_page->page->time_stamp;
+	} else {
 		iter->read_stamp = iter->head_page->page->time_stamp;
+		iter->page_stamp = iter->read_stamp;
+	}
 }
 
 /**
@@ -3590,17 +4014,38 @@ int ring_buffer_iter_empty(struct ring_buffer_iter *iter)
 	struct buffer_page *reader;
 	struct buffer_page *head_page;
 	struct buffer_page *commit_page;
+	struct buffer_page *curr_commit_page;
 	unsigned commit;
+	u64 curr_commit_ts;
+	u64 commit_ts;
 
 	cpu_buffer = iter->cpu_buffer;
-
-	/* Remember, trace recording is off when iterator is in use */
 	reader = cpu_buffer->reader_page;
 	head_page = cpu_buffer->head_page;
 	commit_page = cpu_buffer->commit_page;
+	commit_ts = commit_page->page->time_stamp;
+
+	/*
+	 * When the writer goes across pages, it issues a cmpxchg which
+	 * is a mb(), which will synchronize with the rmb here.
+	 * (see rb_tail_page_update())
+	 */
+	smp_rmb();
 	commit = rb_page_commit(commit_page);
+	/* We want to make sure that the commit page doesn't change */
+	smp_rmb();
 
-	return ((iter->head_page == commit_page && iter->head == commit) ||
+	/* Make sure commit page didn't change */
+	curr_commit_page = READ_ONCE(cpu_buffer->commit_page);
+	curr_commit_ts = READ_ONCE(curr_commit_page->page->time_stamp);
+
+	/* If the commit page changed, then there's more data */
+	if (curr_commit_page != commit_page ||
+	    curr_commit_ts != commit_ts)
+		return 0;
+
+	/* Still racy, as it may return a false positive, but that's OK */
+	return ((iter->head_page == commit_page && iter->head >= commit) ||
 		(iter->head_page == reader && commit_page == head_page &&
 		 head_page->read == commit &&
 		 iter->head == rb_page_commit(cpu_buffer->reader_page)));
@@ -3632,7 +4077,7 @@ rb_update_read_stamp(struct ring_buffer_per_cpu *cpu_buffer,
 		return;
 
 	default:
-		BUG();
+		RB_WARN_ON(cpu_buffer, 1);
 	}
 	return;
 }
@@ -3662,7 +4107,7 @@ rb_update_iter_read_stamp(struct ring_buffer_iter *iter,
 		return;
 
 	default:
-		BUG();
+		RB_WARN_ON(iter->cpu_buffer, 1);
 	}
 	return;
 }
@@ -3828,15 +4273,22 @@ static void rb_advance_reader(struct ring_buffer_per_cpu *cpu_buffer)
 static void rb_advance_iter(struct ring_buffer_iter *iter)
 {
 	struct ring_buffer_per_cpu *cpu_buffer;
-	struct ring_buffer_event *event;
-	unsigned length;
 
 	cpu_buffer = iter->cpu_buffer;
 
+	/* If head == next_event then we need to jump to the next event */
+	if (iter->head == iter->next_event) {
+		/* If the event gets overwritten again, there's nothing to do */
+		if (rb_iter_head_event(iter) == NULL)
+			return;
+	}
+
+	iter->head = iter->next_event;
+
 	/*
 	 * Check if we are at the end of the buffer.
 	 */
-	if (iter->head >= rb_page_size(iter->head_page)) {
+	if (iter->next_event >= rb_page_size(iter->head_page)) {
 		/* discarded commits can make the page empty */
 		if (iter->head_page == cpu_buffer->commit_page)
 			return;
@@ -3844,27 +4296,7 @@ static void rb_advance_iter(struct ring_buffer_iter *iter)
 		return;
 	}
 
-	event = rb_iter_head_event(iter);
-
-	length = rb_event_length(event);
-
-	/*
-	 * This should not be called to advance the header if we are
-	 * at the tail of the buffer.
-	 */
-	if (RB_WARN_ON(cpu_buffer,
-		       (iter->head_page == cpu_buffer->commit_page) &&
-		       (iter->head + length > rb_commit_index(cpu_buffer))))
-		return;
-
-	rb_update_iter_read_stamp(iter, event);
-
-	iter->head += length;
-
-	/* check for end of page padding */
-	if ((iter->head >= rb_page_size(iter->head_page)) &&
-	    (iter->head_page != cpu_buffer->commit_page))
-		rb_inc_iter(iter);
+	rb_update_iter_read_stamp(iter, iter->event);
 }
 
 static int rb_lost_events(struct ring_buffer_per_cpu *cpu_buffer)
@@ -3938,7 +4370,7 @@ rb_buffer_peek(struct ring_buffer_per_cpu *cpu_buffer, u64 *ts,
 		return event;
 
 	default:
-		BUG();
+		RB_WARN_ON(cpu_buffer, 1);
 	}
 
 	return NULL;
@@ -3973,14 +4405,13 @@ rb_iter_peek(struct ring_buffer_iter *iter, u64 *ts)
 		return NULL;
 
 	/*
-	 * We repeat when a time extend is encountered or we hit
-	 * the end of the page. Since the time extend is always attached
-	 * to a data event, we should never loop more than three times.
-	 * Once for going to next page, once on time extend, and
-	 * finally once to get the event.
-	 * (We never hit the following condition more than thrice).
+	 * As the writer can mess with what the iterator is trying
+	 * to read, just give up if we fail to get an event after
+	 * three tries. The iterator is not as reliable when reading
+	 * the ring buffer with an active write as the consumer is.
+	 * Do not warn if the three failures is reached.
 	 */
-	if (RB_WARN_ON(cpu_buffer, ++nr_loops > 3))
+	if (++nr_loops > 3)
 		return NULL;
 
 	if (rb_per_cpu_empty(cpu_buffer))
@@ -3992,6 +4423,8 @@ rb_iter_peek(struct ring_buffer_iter *iter, u64 *ts)
 	}
 
 	event = rb_iter_head_event(iter);
+	if (!event)
+		goto again;
 
 	switch (event->type_len) {
 	case RINGBUF_TYPE_PADDING:
@@ -4026,7 +4459,7 @@ rb_iter_peek(struct ring_buffer_iter *iter, u64 *ts)
 		return event;
 
 	default:
-		BUG();
+		RB_WARN_ON(cpu_buffer, 1);
 	}
 
 	return NULL;
@@ -4102,6 +4535,20 @@ ring_buffer_peek(struct trace_buffer *buffer, int cpu, u64 *ts,
 	return event;
 }
 
+/** ring_buffer_iter_dropped - report if there are dropped events
+ * @iter: The ring buffer iterator
+ *
+ * Returns true if there was dropped events since the last peek.
+ */
+bool ring_buffer_iter_dropped(struct ring_buffer_iter *iter)
+{
+	bool ret = iter->missed_events != 0;
+
+	iter->missed_events = 0;
+	return ret;
+}
+EXPORT_SYMBOL_GPL(ring_buffer_iter_dropped);
+
 /**
  * ring_buffer_iter_peek - peek at the next event to be read
  * @iter: The ring buffer iterator
@@ -4208,16 +4655,21 @@ ring_buffer_read_prepare(struct trace_buffer *buffer, int cpu, gfp_t flags)
 	if (!cpumask_test_cpu(cpu, buffer->cpumask))
 		return NULL;
 
-	iter = kmalloc(sizeof(*iter), flags);
+	iter = kzalloc(sizeof(*iter), flags);
 	if (!iter)
 		return NULL;
 
+	iter->event = kmalloc(BUF_MAX_DATA_SIZE, flags);
+	if (!iter->event) {
+		kfree(iter);
+		return NULL;
+	}
+
 	cpu_buffer = buffer->buffers[cpu];
 
 	iter->cpu_buffer = cpu_buffer;
 
-	atomic_inc(&buffer->resize_disabled);
-	atomic_inc(&cpu_buffer->record_disabled);
+	atomic_inc(&cpu_buffer->resize_disabled);
 
 	return iter;
 }
@@ -4290,42 +4742,31 @@ ring_buffer_read_finish(struct ring_buffer_iter *iter)
 	rb_check_pages(cpu_buffer);
 	raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
 
-	atomic_dec(&cpu_buffer->record_disabled);
-	atomic_dec(&cpu_buffer->buffer->resize_disabled);
+	atomic_dec(&cpu_buffer->resize_disabled);
+	kfree(iter->event);
 	kfree(iter);
 }
 EXPORT_SYMBOL_GPL(ring_buffer_read_finish);
 
 /**
- * ring_buffer_read - read the next item in the ring buffer by the iterator
+ * ring_buffer_iter_advance - advance the iterator to the next location
  * @iter: The ring buffer iterator
- * @ts: The time stamp of the event read.
  *
- * This reads the next event in the ring buffer and increments the iterator.
+ * Move the location of the iterator such that the next read will
+ * be the next location of the iterator.
  */
-struct ring_buffer_event *
-ring_buffer_read(struct ring_buffer_iter *iter, u64 *ts)
+void ring_buffer_iter_advance(struct ring_buffer_iter *iter)
 {
-	struct ring_buffer_event *event;
 	struct ring_buffer_per_cpu *cpu_buffer = iter->cpu_buffer;
 	unsigned long flags;
 
 	raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
- again:
-	event = rb_iter_peek(iter, ts);
-	if (!event)
-		goto out;
-
-	if (event->type_len == RINGBUF_TYPE_PADDING)
-		goto again;
 
 	rb_advance_iter(iter);
- out:
-	raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
 
-	return event;
+	raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
 }
-EXPORT_SYMBOL_GPL(ring_buffer_read);
+EXPORT_SYMBOL_GPL(ring_buffer_iter_advance);
 
 /**
  * ring_buffer_size - return the size of the ring buffer (in bytes)
@@ -4384,8 +4825,8 @@ rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer)
 	cpu_buffer->read = 0;
 	cpu_buffer->read_bytes = 0;
 
-	cpu_buffer->write_stamp = 0;
-	cpu_buffer->read_stamp = 0;
+	rb_time_set(&cpu_buffer->write_stamp, 0);
+	rb_time_set(&cpu_buffer->before_stamp, 0);
 
 	cpu_buffer->lost_events = 0;
 	cpu_buffer->last_overrun = 0;
@@ -4393,6 +4834,26 @@ rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer)
 	rb_head_page_activate(cpu_buffer);
 }
 
+/* Must have disabled the cpu buffer then done a synchronize_rcu */
+static void reset_disabled_cpu_buffer(struct ring_buffer_per_cpu *cpu_buffer)
+{
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
+
+	if (RB_WARN_ON(cpu_buffer, local_read(&cpu_buffer->committing)))
+		goto out;
+
+	arch_spin_lock(&cpu_buffer->lock);
+
+	rb_reset_cpu(cpu_buffer);
+
+	arch_spin_unlock(&cpu_buffer->lock);
+
+ out:
+	raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
+}
+
 /**
  * ring_buffer_reset_cpu - reset a ring buffer per CPU buffer
  * @buffer: The ring buffer to reset a per cpu buffer of
@@ -4401,35 +4862,52 @@ rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer)
 void ring_buffer_reset_cpu(struct trace_buffer *buffer, int cpu)
 {
 	struct ring_buffer_per_cpu *cpu_buffer = buffer->buffers[cpu];
-	unsigned long flags;
 
 	if (!cpumask_test_cpu(cpu, buffer->cpumask))
 		return;
 
-	atomic_inc(&buffer->resize_disabled);
+	atomic_inc(&cpu_buffer->resize_disabled);
 	atomic_inc(&cpu_buffer->record_disabled);
 
 	/* Make sure all commits have finished */
 	synchronize_rcu();
 
-	raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
+	reset_disabled_cpu_buffer(cpu_buffer);
 
-	if (RB_WARN_ON(cpu_buffer, local_read(&cpu_buffer->committing)))
-		goto out;
+	atomic_dec(&cpu_buffer->record_disabled);
+	atomic_dec(&cpu_buffer->resize_disabled);
+}
+EXPORT_SYMBOL_GPL(ring_buffer_reset_cpu);
 
-	arch_spin_lock(&cpu_buffer->lock);
+/**
+ * ring_buffer_reset_cpu - reset a ring buffer per CPU buffer
+ * @buffer: The ring buffer to reset a per cpu buffer of
+ * @cpu: The CPU buffer to be reset
+ */
+void ring_buffer_reset_online_cpus(struct trace_buffer *buffer)
+{
+	struct ring_buffer_per_cpu *cpu_buffer;
+	int cpu;
 
-	rb_reset_cpu(cpu_buffer);
+	for_each_online_buffer_cpu(buffer, cpu) {
+		cpu_buffer = buffer->buffers[cpu];
 
-	arch_spin_unlock(&cpu_buffer->lock);
+		atomic_inc(&cpu_buffer->resize_disabled);
+		atomic_inc(&cpu_buffer->record_disabled);
+	}
 
- out:
-	raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
+	/* Make sure all commits have finished */
+	synchronize_rcu();
 
-	atomic_dec(&cpu_buffer->record_disabled);
-	atomic_dec(&buffer->resize_disabled);
+	for_each_online_buffer_cpu(buffer, cpu) {
+		cpu_buffer = buffer->buffers[cpu];
+
+		reset_disabled_cpu_buffer(cpu_buffer);
+
+		atomic_dec(&cpu_buffer->record_disabled);
+		atomic_dec(&cpu_buffer->resize_disabled);
+	}
 }
-EXPORT_SYMBOL_GPL(ring_buffer_reset_cpu);
 
 /**
  * ring_buffer_reset - reset a ring buffer
@@ -4437,10 +4915,27 @@ EXPORT_SYMBOL_GPL(ring_buffer_reset_cpu);
  */
 void ring_buffer_reset(struct trace_buffer *buffer)
 {
+	struct ring_buffer_per_cpu *cpu_buffer;
 	int cpu;
 
-	for_each_buffer_cpu(buffer, cpu)
-		ring_buffer_reset_cpu(buffer, cpu);
+	for_each_buffer_cpu(buffer, cpu) {
+		cpu_buffer = buffer->buffers[cpu];
+
+		atomic_inc(&cpu_buffer->resize_disabled);
+		atomic_inc(&cpu_buffer->record_disabled);
+	}
+
+	/* Make sure all commits have finished */
+	synchronize_rcu();
+
+	for_each_buffer_cpu(buffer, cpu) {
+		cpu_buffer = buffer->buffers[cpu];
+
+		reset_disabled_cpu_buffer(cpu_buffer);
+
+		atomic_dec(&cpu_buffer->record_disabled);
+		atomic_dec(&cpu_buffer->resize_disabled);
+	}
 }
 EXPORT_SYMBOL_GPL(ring_buffer_reset);
 
diff --git a/kernel/trace/ring_buffer_benchmark.c b/kernel/trace/ring_buffer_benchmark.c
index 8df0aa810950..78e576575b79 100644
--- a/kernel/trace/ring_buffer_benchmark.c
+++ b/kernel/trace/ring_buffer_benchmark.c
@@ -45,8 +45,8 @@ MODULE_PARM_DESC(write_iteration, "# of writes between timestamp readings");
 static int producer_nice = MAX_NICE;
 static int consumer_nice = MAX_NICE;
 
-static int producer_fifo = -1;
-static int consumer_fifo = -1;
+static int producer_fifo;
+static int consumer_fifo;
 
 module_param(producer_nice, int, 0644);
 MODULE_PARM_DESC(producer_nice, "nice prio for producer");
@@ -55,10 +55,10 @@ module_param(consumer_nice, int, 0644);
 MODULE_PARM_DESC(consumer_nice, "nice prio for consumer");
 
 module_param(producer_fifo, int, 0644);
-MODULE_PARM_DESC(producer_fifo, "fifo prio for producer");
+MODULE_PARM_DESC(producer_fifo, "use fifo for producer: 0 - disabled, 1 - low prio, 2 - fifo");
 
 module_param(consumer_fifo, int, 0644);
-MODULE_PARM_DESC(consumer_fifo, "fifo prio for consumer");
+MODULE_PARM_DESC(consumer_fifo, "use fifo for consumer: 0 - disabled, 1 - low prio, 2 - fifo");
 
 static int read_events;
 
@@ -303,22 +303,22 @@ static void ring_buffer_producer(void)
 		trace_printk("ERROR!\n");
 
 	if (!disable_reader) {
-		if (consumer_fifo < 0)
+		if (consumer_fifo)
+			trace_printk("Running Consumer at SCHED_FIFO %s\n",
+				     consumer_fifo == 1 ? "low" : "high");
+		else
 			trace_printk("Running Consumer at nice: %d\n",
 				     consumer_nice);
-		else
-			trace_printk("Running Consumer at SCHED_FIFO %d\n",
-				     consumer_fifo);
 	}
-	if (producer_fifo < 0)
+	if (producer_fifo)
+		trace_printk("Running Producer at SCHED_FIFO %s\n",
+			     producer_fifo == 1 ? "low" : "high");
+	else
 		trace_printk("Running Producer at nice: %d\n",
 			     producer_nice);
-	else
-		trace_printk("Running Producer at SCHED_FIFO %d\n",
-			     producer_fifo);
 
 	/* Let the user know that the test is running at low priority */
-	if (producer_fifo < 0 && consumer_fifo < 0 &&
+	if (!producer_fifo && !consumer_fifo &&
 	    producer_nice == MAX_NICE && consumer_nice == MAX_NICE)
 		trace_printk("WARNING!!! This test is running at lowest priority.\n");
 
@@ -455,21 +455,19 @@ static int __init ring_buffer_benchmark_init(void)
 	 * Run them as low-prio background tasks by default:
 	 */
 	if (!disable_reader) {
-		if (consumer_fifo >= 0) {
-			struct sched_param param = {
-				.sched_priority = consumer_fifo
-			};
-			sched_setscheduler(consumer, SCHED_FIFO, &param);
-		} else
+		if (consumer_fifo >= 2)
+			sched_set_fifo(consumer);
+		else if (consumer_fifo == 1)
+			sched_set_fifo_low(consumer);
+		else
 			set_user_nice(consumer, consumer_nice);
 	}
 
-	if (producer_fifo >= 0) {
-		struct sched_param param = {
-			.sched_priority = producer_fifo
-		};
-		sched_setscheduler(producer, SCHED_FIFO, &param);
-	} else
+	if (producer_fifo >= 2)
+		sched_set_fifo(producer);
+	else if (producer_fifo == 1)
+		sched_set_fifo_low(producer);
+	else
 		set_user_nice(producer, producer_nice);
 
 	return 0;
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 6b11e4e2150c..f40d850ebabc 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -386,16 +386,22 @@ trace_find_filtered_pid(struct trace_pid_list *filtered_pids, pid_t search_pid)
  * Returns false if @task should be traced.
  */
 bool
-trace_ignore_this_task(struct trace_pid_list *filtered_pids, struct task_struct *task)
+trace_ignore_this_task(struct trace_pid_list *filtered_pids,
+		       struct trace_pid_list *filtered_no_pids,
+		       struct task_struct *task)
 {
 	/*
-	 * Return false, because if filtered_pids does not exist,
-	 * all pids are good to trace.
+	 * If filterd_no_pids is not empty, and the task's pid is listed
+	 * in filtered_no_pids, then return true.
+	 * Otherwise, if filtered_pids is empty, that means we can
+	 * trace all tasks. If it has content, then only trace pids
+	 * within filtered_pids.
 	 */
-	if (!filtered_pids)
-		return false;
 
-	return !trace_find_filtered_pid(filtered_pids, task->pid);
+	return (filtered_pids &&
+		!trace_find_filtered_pid(filtered_pids, task->pid)) ||
+		(filtered_no_pids &&
+		 trace_find_filtered_pid(filtered_no_pids, task->pid));
 }
 
 /**
@@ -941,7 +947,8 @@ int __trace_bputs(unsigned long ip, const char *str)
 EXPORT_SYMBOL_GPL(__trace_bputs);
 
 #ifdef CONFIG_TRACER_SNAPSHOT
-void tracing_snapshot_instance_cond(struct trace_array *tr, void *cond_data)
+static void tracing_snapshot_instance_cond(struct trace_array *tr,
+					   void *cond_data)
 {
 	struct tracer *tracer = tr->current_trace;
 	unsigned long flags;
@@ -1292,8 +1299,11 @@ EXPORT_SYMBOL_GPL(tracing_off);
 
 void disable_trace_on_warning(void)
 {
-	if (__disable_trace_on_warning)
+	if (__disable_trace_on_warning) {
+		trace_array_printk_buf(global_trace.array_buffer.buffer, _THIS_IP_,
+			"Disabling tracing due to warning\n");
 		tracing_off();
+	}
 }
 
 /**
@@ -1533,8 +1543,7 @@ static void latency_fsnotify_workfn(struct work_struct *work)
 {
 	struct trace_array *tr = container_of(work, struct trace_array,
 					      fsnotify_work);
-	fsnotify(tr->d_max_latency->d_inode, FS_MODIFY,
-		 tr->d_max_latency->d_inode, FSNOTIFY_EVENT_INODE, NULL, 0);
+	fsnotify_inode(tr->d_max_latency->d_inode, FS_MODIFY);
 }
 
 static void latency_fsnotify_workfn_irq(struct irq_work *iwork)
@@ -1993,7 +2002,6 @@ static void tracing_reset_cpu(struct array_buffer *buf, int cpu)
 void tracing_reset_online_cpus(struct array_buffer *buf)
 {
 	struct trace_buffer *buffer = buf->buffer;
-	int cpu;
 
 	if (!buffer)
 		return;
@@ -2005,8 +2013,7 @@ void tracing_reset_online_cpus(struct array_buffer *buf)
 
 	buf->time_start = buffer_ftrace_now(buf, buf->cpu);
 
-	for_each_online_cpu(cpu)
-		ring_buffer_reset_cpu(buffer, cpu);
+	ring_buffer_reset_online_cpus(buffer);
 
 	ring_buffer_record_enable(buffer);
 }
@@ -2655,7 +2662,7 @@ static void output_printk(struct trace_event_buffer *fbuffer)
 }
 
 int tracepoint_printk_sysctl(struct ctl_table *table, int write,
-			     void __user *buffer, size_t *lenp,
+			     void *buffer, size_t *lenp,
 			     loff_t *ppos)
 {
 	int save_tracepoint_printk;
@@ -2922,12 +2929,6 @@ static void __ftrace_trace_stack(struct trace_buffer *buffer,
 		skip++;
 #endif
 
-	/*
-	 * Since events can happen in NMIs there's no safe way to
-	 * use the per cpu ftrace_stacks. We reserve it and if an interrupt
-	 * or NMI comes in, it will just have to use the default
-	 * FTRACE_STACK_SIZE.
-	 */
 	preempt_disable_notrace();
 
 	stackidx = __this_cpu_inc_return(ftrace_stack_reserve) - 1;
@@ -3127,6 +3128,9 @@ static int alloc_percpu_trace_buffer(void)
 {
 	struct trace_buffer_struct *buffers;
 
+	if (trace_percpu_buffer)
+		return 0;
+
 	buffers = alloc_percpu(struct trace_buffer_struct);
 	if (MEM_FAIL(!buffers, "Could not allocate percpu trace_printk buffer"))
 		return -ENOMEM;
@@ -3329,6 +3333,26 @@ int trace_array_vprintk(struct trace_array *tr,
 	return __trace_array_vprintk(tr->array_buffer.buffer, ip, fmt, args);
 }
 
+/**
+ * trace_array_printk - Print a message to a specific instance
+ * @tr: The instance trace_array descriptor
+ * @ip: The instruction pointer that this is called from.
+ * @fmt: The format to print (printf format)
+ *
+ * If a subsystem sets up its own instance, they have the right to
+ * printk strings into their tracing instance buffer using this
+ * function. Note, this function will not write into the top level
+ * buffer (use trace_printk() for that), as writing into the top level
+ * buffer should only have events that can be individually disabled.
+ * trace_printk() is only used for debugging a kernel, and should not
+ * be ever encorporated in normal use.
+ *
+ * trace_array_printk() can be used, as it will not add noise to the
+ * top level tracing buffer.
+ *
+ * Note, trace_array_init_printk() must be called on @tr before this
+ * can be used.
+ */
 __printf(3, 0)
 int trace_array_printk(struct trace_array *tr,
 		       unsigned long ip, const char *fmt, ...)
@@ -3336,12 +3360,16 @@ int trace_array_printk(struct trace_array *tr,
 	int ret;
 	va_list ap;
 
-	if (!(global_trace.trace_flags & TRACE_ITER_PRINTK))
-		return 0;
-
 	if (!tr)
 		return -ENOENT;
 
+	/* This is only allowed for created instances */
+	if (tr == &global_trace)
+		return 0;
+
+	if (!(tr->trace_flags & TRACE_ITER_PRINTK))
+		return 0;
+
 	va_start(ap, fmt);
 	ret = trace_array_vprintk(tr, ip, fmt, ap);
 	va_end(ap);
@@ -3349,6 +3377,27 @@ int trace_array_printk(struct trace_array *tr,
 }
 EXPORT_SYMBOL_GPL(trace_array_printk);
 
+/**
+ * trace_array_init_printk - Initialize buffers for trace_array_printk()
+ * @tr: The trace array to initialize the buffers for
+ *
+ * As trace_array_printk() only writes into instances, they are OK to
+ * have in the kernel (unlike trace_printk()). This needs to be called
+ * before trace_array_printk() can be used on a trace_array.
+ */
+int trace_array_init_printk(struct trace_array *tr)
+{
+	if (!tr)
+		return -ENOENT;
+
+	/* This is only allowed for created instances */
+	if (tr == &global_trace)
+		return -EINVAL;
+
+	return alloc_percpu_trace_buffer();
+}
+EXPORT_SYMBOL_GPL(trace_array_init_printk);
+
 __printf(3, 4)
 int trace_array_printk_buf(struct trace_buffer *buffer,
 			   unsigned long ip, const char *fmt, ...)
@@ -3378,7 +3427,7 @@ static void trace_iterator_increment(struct trace_iterator *iter)
 
 	iter->idx++;
 	if (buf_iter)
-		ring_buffer_read(buf_iter, NULL);
+		ring_buffer_iter_advance(buf_iter);
 }
 
 static struct trace_entry *
@@ -3388,11 +3437,15 @@ peek_next_entry(struct trace_iterator *iter, int cpu, u64 *ts,
 	struct ring_buffer_event *event;
 	struct ring_buffer_iter *buf_iter = trace_buffer_iter(iter, cpu);
 
-	if (buf_iter)
+	if (buf_iter) {
 		event = ring_buffer_iter_peek(buf_iter, ts);
-	else
+		if (lost_events)
+			*lost_events = ring_buffer_iter_dropped(buf_iter) ?
+				(unsigned long)-1 : 0;
+	} else {
 		event = ring_buffer_peek(iter->array_buffer->buffer, cpu, ts,
 					 lost_events);
+	}
 
 	if (event) {
 		iter->ent_size = ring_buffer_event_length(event);
@@ -3462,11 +3515,51 @@ __find_next_entry(struct trace_iterator *iter, int *ent_cpu,
 	return next;
 }
 
+#define STATIC_TEMP_BUF_SIZE	128
+static char static_temp_buf[STATIC_TEMP_BUF_SIZE];
+
 /* Find the next real entry, without updating the iterator itself */
 struct trace_entry *trace_find_next_entry(struct trace_iterator *iter,
 					  int *ent_cpu, u64 *ent_ts)
 {
-	return __find_next_entry(iter, ent_cpu, NULL, ent_ts);
+	/* __find_next_entry will reset ent_size */
+	int ent_size = iter->ent_size;
+	struct trace_entry *entry;
+
+	/*
+	 * If called from ftrace_dump(), then the iter->temp buffer
+	 * will be the static_temp_buf and not created from kmalloc.
+	 * If the entry size is greater than the buffer, we can
+	 * not save it. Just return NULL in that case. This is only
+	 * used to add markers when two consecutive events' time
+	 * stamps have a large delta. See trace_print_lat_context()
+	 */
+	if (iter->temp == static_temp_buf &&
+	    STATIC_TEMP_BUF_SIZE < ent_size)
+		return NULL;
+
+	/*
+	 * The __find_next_entry() may call peek_next_entry(), which may
+	 * call ring_buffer_peek() that may make the contents of iter->ent
+	 * undefined. Need to copy iter->ent now.
+	 */
+	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)
+				return NULL;
+		}
+		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);
+	/* Put back the original ent_size */
+	iter->ent_size = ent_size;
+
+	return entry;
 }
 
 /* Find the next real entry, and increment the iterator to the next entry */
@@ -3516,7 +3609,6 @@ static void *s_next(struct seq_file *m, void *v, loff_t *pos)
 
 void tracing_iter_reset(struct trace_iterator *iter, int cpu)
 {
-	struct ring_buffer_event *event;
 	struct ring_buffer_iter *buf_iter;
 	unsigned long entries = 0;
 	u64 ts;
@@ -3534,11 +3626,11 @@ void tracing_iter_reset(struct trace_iterator *iter, int cpu)
 	 * that a reset never took place on a cpu. This is evident
 	 * by the timestamp being before the start of the buffer.
 	 */
-	while ((event = ring_buffer_iter_peek(buf_iter, &ts))) {
+	while (ring_buffer_iter_peek(buf_iter, &ts)) {
 		if (ts >= iter->array_buffer->time_start)
 			break;
 		entries++;
-		ring_buffer_read(buf_iter, NULL);
+		ring_buffer_iter_advance(buf_iter);
 	}
 
 	per_cpu_ptr(iter->array_buffer->data, cpu)->skipped_entries = entries;
@@ -3981,8 +4073,12 @@ enum print_line_t print_trace_line(struct trace_iterator *iter)
 	enum print_line_t ret;
 
 	if (iter->lost_events) {
-		trace_seq_printf(&iter->seq, "CPU:%d [LOST %lu EVENTS]\n",
-				 iter->cpu, iter->lost_events);
+		if (iter->lost_events == (unsigned long)-1)
+			trace_seq_printf(&iter->seq, "CPU:%d [LOST EVENTS]\n",
+					 iter->cpu);
+		else
+			trace_seq_printf(&iter->seq, "CPU:%d [LOST %lu EVENTS]\n",
+					 iter->cpu, iter->lost_events);
 		if (trace_seq_has_overflowed(&iter->seq))
 			return TRACE_TYPE_PARTIAL_LINE;
 	}
@@ -4198,6 +4294,18 @@ __tracing_open(struct inode *inode, struct file *file, bool snapshot)
 		goto release;
 
 	/*
+	 * trace_find_next_entry() may need to save off iter->ent.
+	 * It will place it into the iter->temp buffer. As most
+	 * events are less than 128, allocate a buffer of that size.
+	 * If one is greater, then trace_find_next_entry() will
+	 * allocate a new buffer to adjust for the bigger iter->ent.
+	 * It's not critical if it fails to get allocated here.
+	 */
+	iter->temp = kmalloc(128, GFP_KERNEL);
+	if (iter->temp)
+		iter->temp_size = 128;
+
+	/*
 	 * We make a copy of the current tracer to avoid concurrent
 	 * changes on it while we are reading.
 	 */
@@ -4237,8 +4345,11 @@ __tracing_open(struct inode *inode, struct file *file, bool snapshot)
 	if (trace_clocks[tr->clock_id].in_ns)
 		iter->iter_flags |= TRACE_FILE_TIME_IN_NS;
 
-	/* stop the trace while dumping if we are not opening "snapshot" */
-	if (!iter->snapshot)
+	/*
+	 * If pause-on-trace is enabled, then stop the trace while
+	 * dumping, unless this is the "snapshot" file
+	 */
+	if (!iter->snapshot && (tr->trace_flags & TRACE_ITER_PAUSE_ON_TRACE))
 		tracing_stop_tr(tr);
 
 	if (iter->cpu_file == RING_BUFFER_ALL_CPUS) {
@@ -4269,6 +4380,7 @@ __tracing_open(struct inode *inode, struct file *file, bool snapshot)
  fail:
 	mutex_unlock(&trace_types_lock);
 	kfree(iter->trace);
+	kfree(iter->temp);
 	kfree(iter->buffer_iter);
 release:
 	seq_release_private(inode, file);
@@ -4334,7 +4446,7 @@ static int tracing_release(struct inode *inode, struct file *file)
 	if (iter->trace && iter->trace->close)
 		iter->trace->close(iter);
 
-	if (!iter->snapshot)
+	if (!iter->snapshot && tr->stop_count)
 		/* reenable tracing if it was previously enabled */
 		tracing_start_tr(tr);
 
@@ -4344,6 +4456,7 @@ static int tracing_release(struct inode *inode, struct file *file)
 
 	mutex_destroy(&iter->mutex);
 	free_cpumask_var(iter->started);
+	kfree(iter->temp);
 	kfree(iter->trace);
 	kfree(iter->buffer_iter);
 	seq_release_private(inode, file);
@@ -4964,6 +5077,8 @@ static const char readme_msg[] =
 #ifdef CONFIG_FUNCTION_TRACER
 	"  set_ftrace_pid\t- Write pid(s) to only function trace those pids\n"
 	"\t\t    (function)\n"
+	"  set_ftrace_notrace_pid\t- Write pid(s) to not function trace those pids\n"
+	"\t\t    (function)\n"
 #endif
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 	"  set_graph_function\t- Trace the nested calls of a function (function_graph)\n"
@@ -5811,7 +5926,7 @@ int tracing_set_tracer(struct trace_array *tr, const char *buf)
 	}
 
 	/* If trace pipe files are being read, we can't change the tracer */
-	if (tr->current_trace->ref) {
+	if (tr->trace_ref) {
 		ret = -EBUSY;
 		goto out;
 	}
@@ -6027,7 +6142,7 @@ static int tracing_open_pipe(struct inode *inode, struct file *filp)
 
 	nonseekable_open(inode, filp);
 
-	tr->current_trace->ref++;
+	tr->trace_ref++;
 out:
 	mutex_unlock(&trace_types_lock);
 	return ret;
@@ -6046,7 +6161,7 @@ static int tracing_release_pipe(struct inode *inode, struct file *file)
 
 	mutex_lock(&trace_types_lock);
 
-	tr->current_trace->ref--;
+	tr->trace_ref--;
 
 	if (iter->trace->pipe_close)
 		iter->trace->pipe_close(iter);
@@ -6231,13 +6346,6 @@ static void tracing_spd_release_pipe(struct splice_pipe_desc *spd,
 	__free_page(spd->pages[idx]);
 }
 
-static const struct pipe_buf_operations tracing_pipe_buf_ops = {
-	.confirm		= generic_pipe_buf_confirm,
-	.release		= generic_pipe_buf_release,
-	.steal			= generic_pipe_buf_steal,
-	.get			= generic_pipe_buf_get,
-};
-
 static size_t
 tracing_fill_pipe_page(size_t rem, struct trace_iterator *iter)
 {
@@ -6299,7 +6407,7 @@ static ssize_t tracing_splice_read_pipe(struct file *filp,
 		.partial	= partial_def,
 		.nr_pages	= 0, /* This gets updated below. */
 		.nr_pages_max	= PIPE_DEF_BUFFERS,
-		.ops		= &tracing_pipe_buf_ops,
+		.ops		= &default_pipe_buf_ops,
 		.spd_release	= tracing_spd_release_pipe,
 	};
 	ssize_t ret;
@@ -7337,7 +7445,7 @@ static int tracing_buffers_open(struct inode *inode, struct file *filp)
 	if (ret)
 		return ret;
 
-	info = kzalloc(sizeof(*info), GFP_KERNEL);
+	info = kvzalloc(sizeof(*info), GFP_KERNEL);
 	if (!info) {
 		trace_array_put(tr);
 		return -ENOMEM;
@@ -7355,7 +7463,7 @@ static int tracing_buffers_open(struct inode *inode, struct file *filp)
 
 	filp->private_data = info;
 
-	tr->current_trace->ref++;
+	tr->trace_ref++;
 
 	mutex_unlock(&trace_types_lock);
 
@@ -7456,14 +7564,14 @@ static int tracing_buffers_release(struct inode *inode, struct file *file)
 
 	mutex_lock(&trace_types_lock);
 
-	iter->tr->current_trace->ref--;
+	iter->tr->trace_ref--;
 
 	__trace_array_put(iter->tr);
 
 	if (info->spare)
 		ring_buffer_free_read_page(iter->array_buffer->buffer,
 					   info->spare_cpu, info->spare);
-	kfree(info);
+	kvfree(info);
 
 	mutex_unlock(&trace_types_lock);
 
@@ -7508,9 +7616,7 @@ static bool buffer_pipe_buf_get(struct pipe_inode_info *pipe,
 
 /* Pipe buffer operations for a buffer. */
 static const struct pipe_buf_operations buffer_pipe_buf_ops = {
-	.confirm		= generic_pipe_buf_confirm,
 	.release		= buffer_pipe_buf_release,
-	.steal			= generic_pipe_buf_nosteal,
 	.get			= buffer_pipe_buf_get,
 };
 
@@ -8452,6 +8558,7 @@ static int allocate_trace_buffers(struct trace_array *tr, int size)
 	 */
 	allocate_snapshot = false;
 #endif
+
 	return 0;
 }
 
@@ -8665,7 +8772,7 @@ static int __remove_instance(struct trace_array *tr)
 	int i;
 
 	/* Reference counter for a newly created trace array = 1. */
-	if (tr->ref > 1 || (tr->current_trace && tr->current_trace->ref))
+	if (tr->ref > 1 || (tr->current_trace && tr->trace_ref))
 		return -EBUSY;
 
 	list_del(&tr->list);
@@ -8877,9 +8984,7 @@ struct dentry *tracing_init_dentry(void)
 	if (tr->dir)
 		return NULL;
 
-	if (WARN_ON(!tracefs_initialized()) ||
-		(IS_ENABLED(CONFIG_DEBUG_FS) &&
-		 WARN_ON(!debugfs_initialized())))
+	if (WARN_ON(!tracefs_initialized()))
 		return ERR_PTR(-ENODEV);
 
 	/*
@@ -9146,6 +9251,9 @@ void ftrace_dump(enum ftrace_dump_mode oops_dump_mode)
 
 	/* Simulate the iterator */
 	trace_init_global_iter(&iter);
+	/* Can not use kmalloc for iter.temp */
+	iter.temp = static_temp_buf;
+	iter.temp_size = STATIC_TEMP_BUF_SIZE;
 
 	for_each_tracing_cpu(cpu) {
 		atomic_inc(&per_cpu_ptr(iter.array_buffer->data, cpu)->disabled);
@@ -9334,7 +9442,7 @@ __init static int tracer_alloc_buffers(void)
 		goto out_free_buffer_mask;
 
 	/* Only allocate trace_printk buffers if a trace_printk exists */
-	if (__stop___trace_bprintk_fmt != __start___trace_bprintk_fmt)
+	if (&__stop___trace_bprintk_fmt != &__start___trace_bprintk_fmt)
 		/* Must be called before global_trace.buffer is allocated */
 		trace_printk_init_buffers();
 
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 99372dd7d168..610d21355526 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -61,6 +61,9 @@ enum trace_type {
 #undef __field_desc
 #define __field_desc(type, container, item)
 
+#undef __field_packed
+#define __field_packed(type, container, item)
+
 #undef __array
 #define __array(type, item, size)	type	item[size];
 
@@ -178,10 +181,10 @@ struct trace_array_cpu {
 	kuid_t			uid;
 	char			comm[TASK_COMM_LEN];
 
-	bool			ignore_pid;
 #ifdef CONFIG_FUNCTION_TRACER
-	bool			ftrace_ignore_pid;
+	int			ftrace_ignore_pid;
 #endif
+	bool			ignore_pid;
 };
 
 struct tracer;
@@ -207,6 +210,30 @@ struct trace_pid_list {
 	unsigned long			*pids;
 };
 
+enum {
+	TRACE_PIDS		= BIT(0),
+	TRACE_NO_PIDS		= BIT(1),
+};
+
+static inline bool pid_type_enabled(int type, struct trace_pid_list *pid_list,
+				    struct trace_pid_list *no_pid_list)
+{
+	/* Return true if the pid list in type has pids */
+	return ((type & TRACE_PIDS) && pid_list) ||
+		((type & TRACE_NO_PIDS) && no_pid_list);
+}
+
+static inline bool still_need_pid_events(int type, struct trace_pid_list *pid_list,
+					 struct trace_pid_list *no_pid_list)
+{
+	/*
+	 * Turning off what is in @type, return true if the "other"
+	 * pid list, still has pids in it.
+	 */
+	return (!(type & TRACE_PIDS) && pid_list) ||
+		(!(type & TRACE_NO_PIDS) && no_pid_list);
+}
+
 typedef bool (*cond_update_fn_t)(struct trace_array *tr, void *cond_data);
 
 /**
@@ -285,6 +312,7 @@ struct trace_array {
 #endif
 #endif
 	struct trace_pid_list	__rcu *filtered_pids;
+	struct trace_pid_list	__rcu *filtered_no_pids;
 	/*
 	 * max_lock is used to protect the swapping of buffers
 	 * when taking a max snapshot. The buffers themselves are
@@ -328,9 +356,11 @@ struct trace_array {
 	struct trace_event_file *trace_marker_file;
 	cpumask_var_t		tracing_cpumask; /* only trace on set CPUs */
 	int			ref;
+	int			trace_ref;
 #ifdef CONFIG_FUNCTION_TRACER
 	struct ftrace_ops	*ops;
 	struct trace_pid_list	__rcu *function_pids;
+	struct trace_pid_list	__rcu *function_no_pids;
 #ifdef CONFIG_DYNAMIC_FTRACE
 	/* All of these are protected by the ftrace_lock */
 	struct list_head	func_probes;
@@ -518,7 +548,6 @@ struct tracer {
 	struct tracer		*next;
 	struct tracer_flags	*flags;
 	int			enabled;
-	int			ref;
 	bool			print_max;
 	bool			allow_instances;
 #ifdef CONFIG_TRACER_MAX_TRACE
@@ -557,12 +586,7 @@ struct tracer {
  * caller, and we can skip the current check.
  */
 enum {
-	TRACE_BUFFER_BIT,
-	TRACE_BUFFER_NMI_BIT,
-	TRACE_BUFFER_IRQ_BIT,
-	TRACE_BUFFER_SIRQ_BIT,
-
-	/* Start of function recursion bits */
+	/* Function recursion bits */
 	TRACE_FTRACE_BIT,
 	TRACE_FTRACE_NMI_BIT,
 	TRACE_FTRACE_IRQ_BIT,
@@ -787,6 +811,7 @@ extern int pid_max;
 bool trace_find_filtered_pid(struct trace_pid_list *filtered_pids,
 			     pid_t search_pid);
 bool trace_ignore_this_task(struct trace_pid_list *filtered_pids,
+			    struct trace_pid_list *filtered_no_pids,
 			    struct task_struct *task);
 void trace_filter_add_remove_task(struct trace_pid_list *pid_list,
 				  struct task_struct *self,
@@ -1078,6 +1103,10 @@ print_graph_function_flags(struct trace_iterator *iter, u32 flags)
 extern struct list_head ftrace_pids;
 
 #ifdef CONFIG_FUNCTION_TRACER
+
+#define FTRACE_PID_IGNORE	-1
+#define FTRACE_PID_TRACE	-2
+
 struct ftrace_func_command {
 	struct list_head	list;
 	char			*name;
@@ -1089,7 +1118,8 @@ struct ftrace_func_command {
 extern bool ftrace_filter_param __initdata;
 static inline int ftrace_trace_task(struct trace_array *tr)
 {
-	return !this_cpu_read(tr->array_buffer.data->ftrace_ignore_pid);
+	return this_cpu_read(tr->array_buffer.data->ftrace_ignore_pid) !=
+		FTRACE_PID_IGNORE;
 }
 extern int ftrace_is_dead(void);
 int ftrace_create_function_files(struct trace_array *tr,
@@ -1307,6 +1337,7 @@ extern int trace_get_user(struct trace_parser *parser, const char __user *ubuf,
 		C(IRQ_INFO,		"irq-info"),		\
 		C(MARKERS,		"markers"),		\
 		C(EVENT_FORK,		"event-fork"),		\
+		C(PAUSE_ON_TRACE,	"pause-on-trace"),	\
 		FUNCTION_FLAGS					\
 		FGRAPH_FLAGS					\
 		STACK_FLAGS					\
@@ -1638,6 +1669,7 @@ extern struct list_head ftrace_events;
 
 extern const struct file_operations event_trigger_fops;
 extern const struct file_operations event_hist_fops;
+extern const struct file_operations event_hist_debug_fops;
 extern const struct file_operations event_inject_fops;
 
 #ifdef CONFIG_HIST_TRIGGERS
diff --git a/kernel/trace/trace_boot.c b/kernel/trace/trace_boot.c
index 06d7feb5255f..fa0fc08c6ef8 100644
--- a/kernel/trace/trace_boot.c
+++ b/kernel/trace/trace_boot.c
@@ -95,24 +95,24 @@ trace_boot_add_kprobe_event(struct xbc_node *node, const char *event)
 	struct xbc_node *anode;
 	char buf[MAX_BUF_LEN];
 	const char *val;
-	int ret;
+	int ret = 0;
 
-	kprobe_event_cmd_init(&cmd, buf, MAX_BUF_LEN);
+	xbc_node_for_each_array_value(node, "probes", anode, val) {
+		kprobe_event_cmd_init(&cmd, buf, MAX_BUF_LEN);
 
-	ret = kprobe_event_gen_cmd_start(&cmd, event, NULL);
-	if (ret)
-		return ret;
+		ret = kprobe_event_gen_cmd_start(&cmd, event, val);
+		if (ret) {
+			pr_err("Failed to generate probe: %s\n", buf);
+			break;
+		}
 
-	xbc_node_for_each_array_value(node, "probes", anode, val) {
-		ret = kprobe_event_add_field(&cmd, val);
-		if (ret)
-			return ret;
+		ret = kprobe_event_gen_cmd_end(&cmd);
+		if (ret) {
+			pr_err("Failed to add probe: %s\n", buf);
+			break;
+		}
 	}
 
-	ret = kprobe_event_gen_cmd_end(&cmd);
-	if (ret)
-		pr_err("Failed to add probe: %s\n", buf);
-
 	return ret;
 }
 #else
@@ -124,7 +124,7 @@ trace_boot_add_kprobe_event(struct xbc_node *node, const char *event)
 }
 #endif
 
-#ifdef CONFIG_HIST_TRIGGERS
+#ifdef CONFIG_SYNTH_EVENTS
 static int __init
 trace_boot_add_synth_event(struct xbc_node *node, const char *event)
 {
diff --git a/kernel/trace/trace_entries.h b/kernel/trace/trace_entries.h
index f22746f3c132..18c4a58aff79 100644
--- a/kernel/trace/trace_entries.h
+++ b/kernel/trace/trace_entries.h
@@ -78,8 +78,8 @@ FTRACE_ENTRY_PACKED(funcgraph_entry, ftrace_graph_ent_entry,
 
 	F_STRUCT(
 		__field_struct(	struct ftrace_graph_ent,	graph_ent	)
-		__field_desc(	unsigned long,	graph_ent,	func		)
-		__field_desc(	int,		graph_ent,	depth		)
+		__field_packed(	unsigned long,	graph_ent,	func		)
+		__field_packed(	int,		graph_ent,	depth		)
 	),
 
 	F_printk("--> %ps (%d)", (void *)__entry->func, __entry->depth)
@@ -92,11 +92,11 @@ FTRACE_ENTRY_PACKED(funcgraph_exit, ftrace_graph_ret_entry,
 
 	F_STRUCT(
 		__field_struct(	struct ftrace_graph_ret,	ret	)
-		__field_desc(	unsigned long,	ret,		func	)
-		__field_desc(	unsigned long,	ret,		overrun	)
-		__field_desc(	unsigned long long, ret,	calltime)
-		__field_desc(	unsigned long long, ret,	rettime	)
-		__field_desc(	int,		ret,		depth	)
+		__field_packed(	unsigned long,	ret,		func	)
+		__field_packed(	unsigned long,	ret,		overrun	)
+		__field_packed(	unsigned long long, ret,	calltime)
+		__field_packed(	unsigned long long, ret,	rettime	)
+		__field_packed(	int,		ret,		depth	)
 	),
 
 	F_printk("<-- %ps (%d) (start: %llx  end: %llx) over: %d",
@@ -325,14 +325,16 @@ FTRACE_ENTRY(hwlat, hwlat_entry,
 		__field_desc(	long,	timestamp,	tv_nsec		)
 		__field(	unsigned int,		nmi_count	)
 		__field(	unsigned int,		seqnum		)
+		__field(	unsigned int,		count		)
 	),
 
-	F_printk("cnt:%u\tts:%010llu.%010lu\tinner:%llu\touter:%llu\tnmi-ts:%llu\tnmi-count:%u\n",
+	F_printk("cnt:%u\tts:%010llu.%010lu\tinner:%llu\touter:%llu\tcount:%d\tnmi-ts:%llu\tnmi-count:%u\n",
 		 __entry->seqnum,
 		 __entry->tv_sec,
 		 __entry->tv_nsec,
 		 __entry->duration,
 		 __entry->outer_duration,
+		 __entry->count,
 		 __entry->nmi_total_ts,
 		 __entry->nmi_count)
 );
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index f38234ecea18..a85effb2373b 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -232,10 +232,13 @@ bool trace_event_ignore_this_pid(struct trace_event_file *trace_file)
 {
 	struct trace_array *tr = trace_file->tr;
 	struct trace_array_cpu *data;
+	struct trace_pid_list *no_pid_list;
 	struct trace_pid_list *pid_list;
 
 	pid_list = rcu_dereference_raw(tr->filtered_pids);
-	if (!pid_list)
+	no_pid_list = rcu_dereference_raw(tr->filtered_no_pids);
+
+	if (!pid_list && !no_pid_list)
 		return false;
 
 	data = this_cpu_ptr(tr->array_buffer.data);
@@ -510,6 +513,9 @@ event_filter_pid_sched_process_exit(void *data, struct task_struct *task)
 
 	pid_list = rcu_dereference_raw(tr->filtered_pids);
 	trace_filter_add_remove_task(pid_list, NULL, task);
+
+	pid_list = rcu_dereference_raw(tr->filtered_no_pids);
+	trace_filter_add_remove_task(pid_list, NULL, task);
 }
 
 static void
@@ -522,6 +528,9 @@ event_filter_pid_sched_process_fork(void *data,
 
 	pid_list = rcu_dereference_sched(tr->filtered_pids);
 	trace_filter_add_remove_task(pid_list, self, task);
+
+	pid_list = rcu_dereference_sched(tr->filtered_no_pids);
+	trace_filter_add_remove_task(pid_list, self, task);
 }
 
 void trace_event_follow_fork(struct trace_array *tr, bool enable)
@@ -529,12 +538,12 @@ void trace_event_follow_fork(struct trace_array *tr, bool enable)
 	if (enable) {
 		register_trace_prio_sched_process_fork(event_filter_pid_sched_process_fork,
 						       tr, INT_MIN);
-		register_trace_prio_sched_process_exit(event_filter_pid_sched_process_exit,
+		register_trace_prio_sched_process_free(event_filter_pid_sched_process_exit,
 						       tr, INT_MAX);
 	} else {
 		unregister_trace_sched_process_fork(event_filter_pid_sched_process_fork,
 						    tr);
-		unregister_trace_sched_process_exit(event_filter_pid_sched_process_exit,
+		unregister_trace_sched_process_free(event_filter_pid_sched_process_exit,
 						    tr);
 	}
 }
@@ -544,13 +553,23 @@ event_filter_pid_sched_switch_probe_pre(void *data, bool preempt,
 		    struct task_struct *prev, struct task_struct *next)
 {
 	struct trace_array *tr = data;
+	struct trace_pid_list *no_pid_list;
 	struct trace_pid_list *pid_list;
+	bool ret;
 
 	pid_list = rcu_dereference_sched(tr->filtered_pids);
+	no_pid_list = rcu_dereference_sched(tr->filtered_no_pids);
 
-	this_cpu_write(tr->array_buffer.data->ignore_pid,
-		       trace_ignore_this_task(pid_list, prev) &&
-		       trace_ignore_this_task(pid_list, next));
+	/*
+	 * Sched switch is funny, as we only want to ignore it
+	 * in the notrace case if both prev and next should be ignored.
+	 */
+	ret = trace_ignore_this_task(NULL, no_pid_list, prev) &&
+		trace_ignore_this_task(NULL, no_pid_list, next);
+
+	this_cpu_write(tr->array_buffer.data->ignore_pid, ret ||
+		       (trace_ignore_this_task(pid_list, NULL, prev) &&
+			trace_ignore_this_task(pid_list, NULL, next)));
 }
 
 static void
@@ -558,18 +577,21 @@ event_filter_pid_sched_switch_probe_post(void *data, bool preempt,
 		    struct task_struct *prev, struct task_struct *next)
 {
 	struct trace_array *tr = data;
+	struct trace_pid_list *no_pid_list;
 	struct trace_pid_list *pid_list;
 
 	pid_list = rcu_dereference_sched(tr->filtered_pids);
+	no_pid_list = rcu_dereference_sched(tr->filtered_no_pids);
 
 	this_cpu_write(tr->array_buffer.data->ignore_pid,
-		       trace_ignore_this_task(pid_list, next));
+		       trace_ignore_this_task(pid_list, no_pid_list, next));
 }
 
 static void
 event_filter_pid_sched_wakeup_probe_pre(void *data, struct task_struct *task)
 {
 	struct trace_array *tr = data;
+	struct trace_pid_list *no_pid_list;
 	struct trace_pid_list *pid_list;
 
 	/* Nothing to do if we are already tracing */
@@ -577,15 +599,17 @@ event_filter_pid_sched_wakeup_probe_pre(void *data, struct task_struct *task)
 		return;
 
 	pid_list = rcu_dereference_sched(tr->filtered_pids);
+	no_pid_list = rcu_dereference_sched(tr->filtered_no_pids);
 
 	this_cpu_write(tr->array_buffer.data->ignore_pid,
-		       trace_ignore_this_task(pid_list, task));
+		       trace_ignore_this_task(pid_list, no_pid_list, task));
 }
 
 static void
 event_filter_pid_sched_wakeup_probe_post(void *data, struct task_struct *task)
 {
 	struct trace_array *tr = data;
+	struct trace_pid_list *no_pid_list;
 	struct trace_pid_list *pid_list;
 
 	/* Nothing to do if we are not tracing */
@@ -593,23 +617,15 @@ event_filter_pid_sched_wakeup_probe_post(void *data, struct task_struct *task)
 		return;
 
 	pid_list = rcu_dereference_sched(tr->filtered_pids);
+	no_pid_list = rcu_dereference_sched(tr->filtered_no_pids);
 
 	/* Set tracing if current is enabled */
 	this_cpu_write(tr->array_buffer.data->ignore_pid,
-		       trace_ignore_this_task(pid_list, current));
+		       trace_ignore_this_task(pid_list, no_pid_list, current));
 }
 
-static void __ftrace_clear_event_pids(struct trace_array *tr)
+static void unregister_pid_events(struct trace_array *tr)
 {
-	struct trace_pid_list *pid_list;
-	struct trace_event_file *file;
-	int cpu;
-
-	pid_list = rcu_dereference_protected(tr->filtered_pids,
-					     lockdep_is_held(&event_mutex));
-	if (!pid_list)
-		return;
-
 	unregister_trace_sched_switch(event_filter_pid_sched_switch_probe_pre, tr);
 	unregister_trace_sched_switch(event_filter_pid_sched_switch_probe_post, tr);
 
@@ -621,26 +637,55 @@ static void __ftrace_clear_event_pids(struct trace_array *tr)
 
 	unregister_trace_sched_waking(event_filter_pid_sched_wakeup_probe_pre, tr);
 	unregister_trace_sched_waking(event_filter_pid_sched_wakeup_probe_post, tr);
+}
 
-	list_for_each_entry(file, &tr->events, list) {
-		clear_bit(EVENT_FILE_FL_PID_FILTER_BIT, &file->flags);
+static void __ftrace_clear_event_pids(struct trace_array *tr, int type)
+{
+	struct trace_pid_list *pid_list;
+	struct trace_pid_list *no_pid_list;
+	struct trace_event_file *file;
+	int cpu;
+
+	pid_list = rcu_dereference_protected(tr->filtered_pids,
+					     lockdep_is_held(&event_mutex));
+	no_pid_list = rcu_dereference_protected(tr->filtered_no_pids,
+					     lockdep_is_held(&event_mutex));
+
+	/* Make sure there's something to do */
+	if (!pid_type_enabled(type, pid_list, no_pid_list))
+		return;
+
+	if (!still_need_pid_events(type, pid_list, no_pid_list)) {
+		unregister_pid_events(tr);
+
+		list_for_each_entry(file, &tr->events, list) {
+			clear_bit(EVENT_FILE_FL_PID_FILTER_BIT, &file->flags);
+		}
+
+		for_each_possible_cpu(cpu)
+			per_cpu_ptr(tr->array_buffer.data, cpu)->ignore_pid = false;
 	}
 
-	for_each_possible_cpu(cpu)
-		per_cpu_ptr(tr->array_buffer.data, cpu)->ignore_pid = false;
+	if (type & TRACE_PIDS)
+		rcu_assign_pointer(tr->filtered_pids, NULL);
 
-	rcu_assign_pointer(tr->filtered_pids, NULL);
+	if (type & TRACE_NO_PIDS)
+		rcu_assign_pointer(tr->filtered_no_pids, NULL);
 
 	/* Wait till all users are no longer using pid filtering */
 	tracepoint_synchronize_unregister();
 
-	trace_free_pid_list(pid_list);
+	if ((type & TRACE_PIDS) && pid_list)
+		trace_free_pid_list(pid_list);
+
+	if ((type & TRACE_NO_PIDS) && no_pid_list)
+		trace_free_pid_list(no_pid_list);
 }
 
-static void ftrace_clear_event_pids(struct trace_array *tr)
+static void ftrace_clear_event_pids(struct trace_array *tr, int type)
 {
 	mutex_lock(&event_mutex);
-	__ftrace_clear_event_pids(tr);
+	__ftrace_clear_event_pids(tr, type);
 	mutex_unlock(&event_mutex);
 }
 
@@ -1013,15 +1058,32 @@ static void t_stop(struct seq_file *m, void *p)
 }
 
 static void *
-p_next(struct seq_file *m, void *v, loff_t *pos)
+__next(struct seq_file *m, void *v, loff_t *pos, int type)
 {
 	struct trace_array *tr = m->private;
-	struct trace_pid_list *pid_list = rcu_dereference_sched(tr->filtered_pids);
+	struct trace_pid_list *pid_list;
+
+	if (type == TRACE_PIDS)
+		pid_list = rcu_dereference_sched(tr->filtered_pids);
+	else
+		pid_list = rcu_dereference_sched(tr->filtered_no_pids);
 
 	return trace_pid_next(pid_list, v, pos);
 }
 
-static void *p_start(struct seq_file *m, loff_t *pos)
+static void *
+p_next(struct seq_file *m, void *v, loff_t *pos)
+{
+	return __next(m, v, pos, TRACE_PIDS);
+}
+
+static void *
+np_next(struct seq_file *m, void *v, loff_t *pos)
+{
+	return __next(m, v, pos, TRACE_NO_PIDS);
+}
+
+static void *__start(struct seq_file *m, loff_t *pos, int type)
 	__acquires(RCU)
 {
 	struct trace_pid_list *pid_list;
@@ -1036,7 +1098,10 @@ static void *p_start(struct seq_file *m, loff_t *pos)
 	mutex_lock(&event_mutex);
 	rcu_read_lock_sched();
 
-	pid_list = rcu_dereference_sched(tr->filtered_pids);
+	if (type == TRACE_PIDS)
+		pid_list = rcu_dereference_sched(tr->filtered_pids);
+	else
+		pid_list = rcu_dereference_sched(tr->filtered_no_pids);
 
 	if (!pid_list)
 		return NULL;
@@ -1044,6 +1109,18 @@ static void *p_start(struct seq_file *m, loff_t *pos)
 	return trace_pid_start(pid_list, pos);
 }
 
+static void *p_start(struct seq_file *m, loff_t *pos)
+	__acquires(RCU)
+{
+	return __start(m, pos, TRACE_PIDS);
+}
+
+static void *np_start(struct seq_file *m, loff_t *pos)
+	__acquires(RCU)
+{
+	return __start(m, pos, TRACE_NO_PIDS);
+}
+
 static void p_stop(struct seq_file *m, void *p)
 	__releases(RCU)
 {
@@ -1588,6 +1665,7 @@ static void ignore_task_cpu(void *data)
 {
 	struct trace_array *tr = data;
 	struct trace_pid_list *pid_list;
+	struct trace_pid_list *no_pid_list;
 
 	/*
 	 * This function is called by on_each_cpu() while the
@@ -1595,18 +1673,50 @@ static void ignore_task_cpu(void *data)
 	 */
 	pid_list = rcu_dereference_protected(tr->filtered_pids,
 					     mutex_is_locked(&event_mutex));
+	no_pid_list = rcu_dereference_protected(tr->filtered_no_pids,
+					     mutex_is_locked(&event_mutex));
 
 	this_cpu_write(tr->array_buffer.data->ignore_pid,
-		       trace_ignore_this_task(pid_list, current));
+		       trace_ignore_this_task(pid_list, no_pid_list, current));
+}
+
+static void register_pid_events(struct trace_array *tr)
+{
+	/*
+	 * Register a probe that is called before all other probes
+	 * to set ignore_pid if next or prev do not match.
+	 * Register a probe this is called after all other probes
+	 * to only keep ignore_pid set if next pid matches.
+	 */
+	register_trace_prio_sched_switch(event_filter_pid_sched_switch_probe_pre,
+					 tr, INT_MAX);
+	register_trace_prio_sched_switch(event_filter_pid_sched_switch_probe_post,
+					 tr, 0);
+
+	register_trace_prio_sched_wakeup(event_filter_pid_sched_wakeup_probe_pre,
+					 tr, INT_MAX);
+	register_trace_prio_sched_wakeup(event_filter_pid_sched_wakeup_probe_post,
+					 tr, 0);
+
+	register_trace_prio_sched_wakeup_new(event_filter_pid_sched_wakeup_probe_pre,
+					     tr, INT_MAX);
+	register_trace_prio_sched_wakeup_new(event_filter_pid_sched_wakeup_probe_post,
+					     tr, 0);
+
+	register_trace_prio_sched_waking(event_filter_pid_sched_wakeup_probe_pre,
+					 tr, INT_MAX);
+	register_trace_prio_sched_waking(event_filter_pid_sched_wakeup_probe_post,
+					 tr, 0);
 }
 
 static ssize_t
-ftrace_event_pid_write(struct file *filp, const char __user *ubuf,
-		       size_t cnt, loff_t *ppos)
+event_pid_write(struct file *filp, const char __user *ubuf,
+		size_t cnt, loff_t *ppos, int type)
 {
 	struct seq_file *m = filp->private_data;
 	struct trace_array *tr = m->private;
 	struct trace_pid_list *filtered_pids = NULL;
+	struct trace_pid_list *other_pids = NULL;
 	struct trace_pid_list *pid_list;
 	struct trace_event_file *file;
 	ssize_t ret;
@@ -1620,14 +1730,26 @@ ftrace_event_pid_write(struct file *filp, const char __user *ubuf,
 
 	mutex_lock(&event_mutex);
 
-	filtered_pids = rcu_dereference_protected(tr->filtered_pids,
-					     lockdep_is_held(&event_mutex));
+	if (type == TRACE_PIDS) {
+		filtered_pids = rcu_dereference_protected(tr->filtered_pids,
+							  lockdep_is_held(&event_mutex));
+		other_pids = rcu_dereference_protected(tr->filtered_no_pids,
+							  lockdep_is_held(&event_mutex));
+	} else {
+		filtered_pids = rcu_dereference_protected(tr->filtered_no_pids,
+							  lockdep_is_held(&event_mutex));
+		other_pids = rcu_dereference_protected(tr->filtered_pids,
+							  lockdep_is_held(&event_mutex));
+	}
 
 	ret = trace_pid_write(filtered_pids, &pid_list, ubuf, cnt);
 	if (ret < 0)
 		goto out;
 
-	rcu_assign_pointer(tr->filtered_pids, pid_list);
+	if (type == TRACE_PIDS)
+		rcu_assign_pointer(tr->filtered_pids, pid_list);
+	else
+		rcu_assign_pointer(tr->filtered_no_pids, pid_list);
 
 	list_for_each_entry(file, &tr->events, list) {
 		set_bit(EVENT_FILE_FL_PID_FILTER_BIT, &file->flags);
@@ -1636,32 +1758,8 @@ ftrace_event_pid_write(struct file *filp, const char __user *ubuf,
 	if (filtered_pids) {
 		tracepoint_synchronize_unregister();
 		trace_free_pid_list(filtered_pids);
-	} else if (pid_list) {
-		/*
-		 * Register a probe that is called before all other probes
-		 * to set ignore_pid if next or prev do not match.
-		 * Register a probe this is called after all other probes
-		 * to only keep ignore_pid set if next pid matches.
-		 */
-		register_trace_prio_sched_switch(event_filter_pid_sched_switch_probe_pre,
-						 tr, INT_MAX);
-		register_trace_prio_sched_switch(event_filter_pid_sched_switch_probe_post,
-						 tr, 0);
-
-		register_trace_prio_sched_wakeup(event_filter_pid_sched_wakeup_probe_pre,
-						 tr, INT_MAX);
-		register_trace_prio_sched_wakeup(event_filter_pid_sched_wakeup_probe_post,
-						 tr, 0);
-
-		register_trace_prio_sched_wakeup_new(event_filter_pid_sched_wakeup_probe_pre,
-						     tr, INT_MAX);
-		register_trace_prio_sched_wakeup_new(event_filter_pid_sched_wakeup_probe_post,
-						     tr, 0);
-
-		register_trace_prio_sched_waking(event_filter_pid_sched_wakeup_probe_pre,
-						 tr, INT_MAX);
-		register_trace_prio_sched_waking(event_filter_pid_sched_wakeup_probe_post,
-						 tr, 0);
+	} else if (pid_list && !other_pids) {
+		register_pid_events(tr);
 	}
 
 	/*
@@ -1680,9 +1778,24 @@ ftrace_event_pid_write(struct file *filp, const char __user *ubuf,
 	return ret;
 }
 
+static ssize_t
+ftrace_event_pid_write(struct file *filp, const char __user *ubuf,
+		       size_t cnt, loff_t *ppos)
+{
+	return event_pid_write(filp, ubuf, cnt, ppos, TRACE_PIDS);
+}
+
+static ssize_t
+ftrace_event_npid_write(struct file *filp, const char __user *ubuf,
+			size_t cnt, loff_t *ppos)
+{
+	return event_pid_write(filp, ubuf, cnt, ppos, TRACE_NO_PIDS);
+}
+
 static int ftrace_event_avail_open(struct inode *inode, struct file *file);
 static int ftrace_event_set_open(struct inode *inode, struct file *file);
 static int ftrace_event_set_pid_open(struct inode *inode, struct file *file);
+static int ftrace_event_set_npid_open(struct inode *inode, struct file *file);
 static int ftrace_event_release(struct inode *inode, struct file *file);
 
 static const struct seq_operations show_event_seq_ops = {
@@ -1706,6 +1819,13 @@ static const struct seq_operations show_set_pid_seq_ops = {
 	.stop = p_stop,
 };
 
+static const struct seq_operations show_set_no_pid_seq_ops = {
+	.start = np_start,
+	.next = np_next,
+	.show = trace_pid_show,
+	.stop = p_stop,
+};
+
 static const struct file_operations ftrace_avail_fops = {
 	.open = ftrace_event_avail_open,
 	.read = seq_read,
@@ -1729,6 +1849,14 @@ static const struct file_operations ftrace_set_event_pid_fops = {
 	.release = ftrace_event_release,
 };
 
+static const struct file_operations ftrace_set_event_notrace_pid_fops = {
+	.open = ftrace_event_set_npid_open,
+	.read = seq_read,
+	.write = ftrace_event_npid_write,
+	.llseek = seq_lseek,
+	.release = ftrace_event_release,
+};
+
 static const struct file_operations ftrace_enable_fops = {
 	.open = tracing_open_generic,
 	.read = event_enable_read,
@@ -1858,7 +1986,28 @@ ftrace_event_set_pid_open(struct inode *inode, struct file *file)
 
 	if ((file->f_mode & FMODE_WRITE) &&
 	    (file->f_flags & O_TRUNC))
-		ftrace_clear_event_pids(tr);
+		ftrace_clear_event_pids(tr, TRACE_PIDS);
+
+	ret = ftrace_event_open(inode, file, seq_ops);
+	if (ret < 0)
+		trace_array_put(tr);
+	return ret;
+}
+
+static int
+ftrace_event_set_npid_open(struct inode *inode, struct file *file)
+{
+	const struct seq_operations *seq_ops = &show_set_no_pid_seq_ops;
+	struct trace_array *tr = inode->i_private;
+	int ret;
+
+	ret = tracing_check_open_get_tr(tr);
+	if (ret)
+		return ret;
+
+	if ((file->f_mode & FMODE_WRITE) &&
+	    (file->f_flags & O_TRUNC))
+		ftrace_clear_event_pids(tr, TRACE_NO_PIDS);
 
 	ret = ftrace_event_open(inode, file, seq_ops);
 	if (ret < 0)
@@ -2060,6 +2209,10 @@ event_create_dir(struct dentry *parent, struct trace_event_file *file)
 	trace_create_file("hist", 0444, file->dir, file,
 			  &event_hist_fops);
 #endif
+#ifdef CONFIG_HIST_TRIGGERS_DEBUG
+	trace_create_file("hist_debug", 0444, file->dir, file,
+			  &event_hist_debug_fops);
+#endif
 	trace_create_file("format", 0444, file->dir, call,
 			  &ftrace_event_format_fops);
 
@@ -3075,6 +3228,11 @@ create_event_toplevel_files(struct dentry *parent, struct trace_array *tr)
 	if (!entry)
 		pr_warn("Could not create tracefs 'set_event_pid' entry\n");
 
+	entry = tracefs_create_file("set_event_notrace_pid", 0644, parent,
+				    tr, &ftrace_set_event_notrace_pid_fops);
+	if (!entry)
+		pr_warn("Could not create tracefs 'set_event_notrace_pid' entry\n");
+
 	/* ring buffer internal formats */
 	entry = trace_create_file("header_page", 0444, d_events,
 				  ring_buffer_print_page_header,
@@ -3158,7 +3316,7 @@ int event_trace_del_tracer(struct trace_array *tr)
 	clear_event_triggers(tr);
 
 	/* Clear the pid list */
-	__ftrace_clear_event_pids(tr);
+	__ftrace_clear_event_pids(tr, TRACE_PIDS | TRACE_NO_PIDS);
 
 	/* Disable any running events */
 	__ftrace_set_clr_event_nolock(tr, NULL, NULL, NULL, 0);
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 5f6834a2bf41..0b933546142e 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -19,13 +19,7 @@
 #include <trace/events/mmflags.h>
 
 #include "tracing_map.h"
-#include "trace.h"
-#include "trace_dynevent.h"
-
-#define SYNTH_SYSTEM		"synthetic"
-#define SYNTH_FIELDS_MAX	32
-
-#define STR_VAR_LEN_MAX		32 /* must be multiple of sizeof(u64) */
+#include "trace_synth.h"
 
 #define ERRORS								\
 	C(NONE,			"No error"),				\
@@ -380,69 +374,6 @@ struct hist_trigger_data {
 	unsigned int			n_save_var_str;
 };
 
-static int create_synth_event(int argc, const char **argv);
-static int synth_event_show(struct seq_file *m, struct dyn_event *ev);
-static int synth_event_release(struct dyn_event *ev);
-static bool synth_event_is_busy(struct dyn_event *ev);
-static bool synth_event_match(const char *system, const char *event,
-			int argc, const char **argv, struct dyn_event *ev);
-
-static struct dyn_event_operations synth_event_ops = {
-	.create = create_synth_event,
-	.show = synth_event_show,
-	.is_busy = synth_event_is_busy,
-	.free = synth_event_release,
-	.match = synth_event_match,
-};
-
-struct synth_field {
-	char *type;
-	char *name;
-	size_t size;
-	unsigned int offset;
-	bool is_signed;
-	bool is_string;
-};
-
-struct synth_event {
-	struct dyn_event			devent;
-	int					ref;
-	char					*name;
-	struct synth_field			**fields;
-	unsigned int				n_fields;
-	unsigned int				n_u64;
-	struct trace_event_class		class;
-	struct trace_event_call			call;
-	struct tracepoint			*tp;
-	struct module				*mod;
-};
-
-static bool is_synth_event(struct dyn_event *ev)
-{
-	return ev->ops == &synth_event_ops;
-}
-
-static struct synth_event *to_synth_event(struct dyn_event *ev)
-{
-	return container_of(ev, struct synth_event, devent);
-}
-
-static bool synth_event_is_busy(struct dyn_event *ev)
-{
-	struct synth_event *event = to_synth_event(ev);
-
-	return event->ref != 0;
-}
-
-static bool synth_event_match(const char *system, const char *event,
-			int argc, const char **argv, struct dyn_event *ev)
-{
-	struct synth_event *sev = to_synth_event(ev);
-
-	return strcmp(sev->name, event) == 0 &&
-		(!system || strcmp(system, SYNTH_SYSTEM) == 0);
-}
-
 struct action_data;
 
 typedef void (*action_fn_t) (struct hist_trigger_data *hist_data,
@@ -589,6 +520,7 @@ static struct track_data *track_data_alloc(unsigned int key_len,
 		track_data_free(data);
 		return ERR_PTR(-ENOMEM);
 	}
+
 	data->elt.private_data = elt_data;
 
 	elt_data->comm = kzalloc(TASK_COMM_LEN, GFP_KERNEL);
@@ -621,7 +553,6 @@ static void last_cmd_set(struct trace_event_file *file, char *str)
 
 	if (file) {
 		call = file->event_call;
-
 		system = call->class->system;
 		if (system) {
 			name = trace_event_name(call);
@@ -646,510 +577,6 @@ static void hist_err_clear(void)
 	last_cmd_loc[0] = '\0';
 }
 
-struct synth_trace_event {
-	struct trace_entry	ent;
-	u64			fields[];
-};
-
-static int synth_event_define_fields(struct trace_event_call *call)
-{
-	struct synth_trace_event trace;
-	int offset = offsetof(typeof(trace), fields);
-	struct synth_event *event = call->data;
-	unsigned int i, size, n_u64;
-	char *name, *type;
-	bool is_signed;
-	int ret = 0;
-
-	for (i = 0, n_u64 = 0; i < event->n_fields; i++) {
-		size = event->fields[i]->size;
-		is_signed = event->fields[i]->is_signed;
-		type = event->fields[i]->type;
-		name = event->fields[i]->name;
-		ret = trace_define_field(call, type, name, offset, size,
-					 is_signed, FILTER_OTHER);
-		if (ret)
-			break;
-
-		event->fields[i]->offset = n_u64;
-
-		if (event->fields[i]->is_string) {
-			offset += STR_VAR_LEN_MAX;
-			n_u64 += STR_VAR_LEN_MAX / sizeof(u64);
-		} else {
-			offset += sizeof(u64);
-			n_u64++;
-		}
-	}
-
-	event->n_u64 = n_u64;
-
-	return ret;
-}
-
-static bool synth_field_signed(char *type)
-{
-	if (str_has_prefix(type, "u"))
-		return false;
-	if (strcmp(type, "gfp_t") == 0)
-		return false;
-
-	return true;
-}
-
-static int synth_field_is_string(char *type)
-{
-	if (strstr(type, "char[") != NULL)
-		return true;
-
-	return false;
-}
-
-static int synth_field_string_size(char *type)
-{
-	char buf[4], *end, *start;
-	unsigned int len;
-	int size, err;
-
-	start = strstr(type, "char[");
-	if (start == NULL)
-		return -EINVAL;
-	start += sizeof("char[") - 1;
-
-	end = strchr(type, ']');
-	if (!end || end < start)
-		return -EINVAL;
-
-	len = end - start;
-	if (len > 3)
-		return -EINVAL;
-
-	strncpy(buf, start, len);
-	buf[len] = '\0';
-
-	err = kstrtouint(buf, 0, &size);
-	if (err)
-		return err;
-
-	if (size > STR_VAR_LEN_MAX)
-		return -EINVAL;
-
-	return size;
-}
-
-static int synth_field_size(char *type)
-{
-	int size = 0;
-
-	if (strcmp(type, "s64") == 0)
-		size = sizeof(s64);
-	else if (strcmp(type, "u64") == 0)
-		size = sizeof(u64);
-	else if (strcmp(type, "s32") == 0)
-		size = sizeof(s32);
-	else if (strcmp(type, "u32") == 0)
-		size = sizeof(u32);
-	else if (strcmp(type, "s16") == 0)
-		size = sizeof(s16);
-	else if (strcmp(type, "u16") == 0)
-		size = sizeof(u16);
-	else if (strcmp(type, "s8") == 0)
-		size = sizeof(s8);
-	else if (strcmp(type, "u8") == 0)
-		size = sizeof(u8);
-	else if (strcmp(type, "char") == 0)
-		size = sizeof(char);
-	else if (strcmp(type, "unsigned char") == 0)
-		size = sizeof(unsigned char);
-	else if (strcmp(type, "int") == 0)
-		size = sizeof(int);
-	else if (strcmp(type, "unsigned int") == 0)
-		size = sizeof(unsigned int);
-	else if (strcmp(type, "long") == 0)
-		size = sizeof(long);
-	else if (strcmp(type, "unsigned long") == 0)
-		size = sizeof(unsigned long);
-	else if (strcmp(type, "pid_t") == 0)
-		size = sizeof(pid_t);
-	else if (strcmp(type, "gfp_t") == 0)
-		size = sizeof(gfp_t);
-	else if (synth_field_is_string(type))
-		size = synth_field_string_size(type);
-
-	return size;
-}
-
-static const char *synth_field_fmt(char *type)
-{
-	const char *fmt = "%llu";
-
-	if (strcmp(type, "s64") == 0)
-		fmt = "%lld";
-	else if (strcmp(type, "u64") == 0)
-		fmt = "%llu";
-	else if (strcmp(type, "s32") == 0)
-		fmt = "%d";
-	else if (strcmp(type, "u32") == 0)
-		fmt = "%u";
-	else if (strcmp(type, "s16") == 0)
-		fmt = "%d";
-	else if (strcmp(type, "u16") == 0)
-		fmt = "%u";
-	else if (strcmp(type, "s8") == 0)
-		fmt = "%d";
-	else if (strcmp(type, "u8") == 0)
-		fmt = "%u";
-	else if (strcmp(type, "char") == 0)
-		fmt = "%d";
-	else if (strcmp(type, "unsigned char") == 0)
-		fmt = "%u";
-	else if (strcmp(type, "int") == 0)
-		fmt = "%d";
-	else if (strcmp(type, "unsigned int") == 0)
-		fmt = "%u";
-	else if (strcmp(type, "long") == 0)
-		fmt = "%ld";
-	else if (strcmp(type, "unsigned long") == 0)
-		fmt = "%lu";
-	else if (strcmp(type, "pid_t") == 0)
-		fmt = "%d";
-	else if (strcmp(type, "gfp_t") == 0)
-		fmt = "%x";
-	else if (synth_field_is_string(type))
-		fmt = "%s";
-
-	return fmt;
-}
-
-static void print_synth_event_num_val(struct trace_seq *s,
-				      char *print_fmt, char *name,
-				      int size, u64 val, char *space)
-{
-	switch (size) {
-	case 1:
-		trace_seq_printf(s, print_fmt, name, (u8)val, space);
-		break;
-
-	case 2:
-		trace_seq_printf(s, print_fmt, name, (u16)val, space);
-		break;
-
-	case 4:
-		trace_seq_printf(s, print_fmt, name, (u32)val, space);
-		break;
-
-	default:
-		trace_seq_printf(s, print_fmt, name, val, space);
-		break;
-	}
-}
-
-static enum print_line_t print_synth_event(struct trace_iterator *iter,
-					   int flags,
-					   struct trace_event *event)
-{
-	struct trace_array *tr = iter->tr;
-	struct trace_seq *s = &iter->seq;
-	struct synth_trace_event *entry;
-	struct synth_event *se;
-	unsigned int i, n_u64;
-	char print_fmt[32];
-	const char *fmt;
-
-	entry = (struct synth_trace_event *)iter->ent;
-	se = container_of(event, struct synth_event, call.event);
-
-	trace_seq_printf(s, "%s: ", se->name);
-
-	for (i = 0, n_u64 = 0; i < se->n_fields; i++) {
-		if (trace_seq_has_overflowed(s))
-			goto end;
-
-		fmt = synth_field_fmt(se->fields[i]->type);
-
-		/* parameter types */
-		if (tr && tr->trace_flags & TRACE_ITER_VERBOSE)
-			trace_seq_printf(s, "%s ", fmt);
-
-		snprintf(print_fmt, sizeof(print_fmt), "%%s=%s%%s", fmt);
-
-		/* parameter values */
-		if (se->fields[i]->is_string) {
-			trace_seq_printf(s, print_fmt, se->fields[i]->name,
-					 (char *)&entry->fields[n_u64],
-					 i == se->n_fields - 1 ? "" : " ");
-			n_u64 += STR_VAR_LEN_MAX / sizeof(u64);
-		} else {
-			struct trace_print_flags __flags[] = {
-			    __def_gfpflag_names, {-1, NULL} };
-			char *space = (i == se->n_fields - 1 ? "" : " ");
-
-			print_synth_event_num_val(s, print_fmt,
-						  se->fields[i]->name,
-						  se->fields[i]->size,
-						  entry->fields[n_u64],
-						  space);
-
-			if (strcmp(se->fields[i]->type, "gfp_t") == 0) {
-				trace_seq_puts(s, " (");
-				trace_print_flags_seq(s, "|",
-						      entry->fields[n_u64],
-						      __flags);
-				trace_seq_putc(s, ')');
-			}
-			n_u64++;
-		}
-	}
-end:
-	trace_seq_putc(s, '\n');
-
-	return trace_handle_return(s);
-}
-
-static struct trace_event_functions synth_event_funcs = {
-	.trace		= print_synth_event
-};
-
-static notrace void trace_event_raw_event_synth(void *__data,
-						u64 *var_ref_vals,
-						unsigned int *var_ref_idx)
-{
-	struct trace_event_file *trace_file = __data;
-	struct synth_trace_event *entry;
-	struct trace_event_buffer fbuffer;
-	struct trace_buffer *buffer;
-	struct synth_event *event;
-	unsigned int i, n_u64, val_idx;
-	int fields_size = 0;
-
-	event = trace_file->event_call->data;
-
-	if (trace_trigger_soft_disabled(trace_file))
-		return;
-
-	fields_size = event->n_u64 * sizeof(u64);
-
-	/*
-	 * Avoid ring buffer recursion detection, as this event
-	 * is being performed within another event.
-	 */
-	buffer = trace_file->tr->array_buffer.buffer;
-	ring_buffer_nest_start(buffer);
-
-	entry = trace_event_buffer_reserve(&fbuffer, trace_file,
-					   sizeof(*entry) + fields_size);
-	if (!entry)
-		goto out;
-
-	for (i = 0, n_u64 = 0; i < event->n_fields; i++) {
-		val_idx = var_ref_idx[i];
-		if (event->fields[i]->is_string) {
-			char *str_val = (char *)(long)var_ref_vals[val_idx];
-			char *str_field = (char *)&entry->fields[n_u64];
-
-			strscpy(str_field, str_val, STR_VAR_LEN_MAX);
-			n_u64 += STR_VAR_LEN_MAX / sizeof(u64);
-		} else {
-			struct synth_field *field = event->fields[i];
-			u64 val = var_ref_vals[val_idx];
-
-			switch (field->size) {
-			case 1:
-				*(u8 *)&entry->fields[n_u64] = (u8)val;
-				break;
-
-			case 2:
-				*(u16 *)&entry->fields[n_u64] = (u16)val;
-				break;
-
-			case 4:
-				*(u32 *)&entry->fields[n_u64] = (u32)val;
-				break;
-
-			default:
-				entry->fields[n_u64] = val;
-				break;
-			}
-			n_u64++;
-		}
-	}
-
-	trace_event_buffer_commit(&fbuffer);
-out:
-	ring_buffer_nest_end(buffer);
-}
-
-static void free_synth_event_print_fmt(struct trace_event_call *call)
-{
-	if (call) {
-		kfree(call->print_fmt);
-		call->print_fmt = NULL;
-	}
-}
-
-static int __set_synth_event_print_fmt(struct synth_event *event,
-				       char *buf, int len)
-{
-	const char *fmt;
-	int pos = 0;
-	int i;
-
-	/* When len=0, we just calculate the needed length */
-#define LEN_OR_ZERO (len ? len - pos : 0)
-
-	pos += snprintf(buf + pos, LEN_OR_ZERO, "\"");
-	for (i = 0; i < event->n_fields; i++) {
-		fmt = synth_field_fmt(event->fields[i]->type);
-		pos += snprintf(buf + pos, LEN_OR_ZERO, "%s=%s%s",
-				event->fields[i]->name, fmt,
-				i == event->n_fields - 1 ? "" : ", ");
-	}
-	pos += snprintf(buf + pos, LEN_OR_ZERO, "\"");
-
-	for (i = 0; i < event->n_fields; i++) {
-		pos += snprintf(buf + pos, LEN_OR_ZERO,
-				", REC->%s", event->fields[i]->name);
-	}
-
-#undef LEN_OR_ZERO
-
-	/* return the length of print_fmt */
-	return pos;
-}
-
-static int set_synth_event_print_fmt(struct trace_event_call *call)
-{
-	struct synth_event *event = call->data;
-	char *print_fmt;
-	int len;
-
-	/* First: called with 0 length to calculate the needed length */
-	len = __set_synth_event_print_fmt(event, NULL, 0);
-
-	print_fmt = kmalloc(len + 1, GFP_KERNEL);
-	if (!print_fmt)
-		return -ENOMEM;
-
-	/* Second: actually write the @print_fmt */
-	__set_synth_event_print_fmt(event, print_fmt, len + 1);
-	call->print_fmt = print_fmt;
-
-	return 0;
-}
-
-static void free_synth_field(struct synth_field *field)
-{
-	kfree(field->type);
-	kfree(field->name);
-	kfree(field);
-}
-
-static struct synth_field *parse_synth_field(int argc, const char **argv,
-					     int *consumed)
-{
-	struct synth_field *field;
-	const char *prefix = NULL, *field_type = argv[0], *field_name, *array;
-	int len, ret = 0;
-
-	if (field_type[0] == ';')
-		field_type++;
-
-	if (!strcmp(field_type, "unsigned")) {
-		if (argc < 3)
-			return ERR_PTR(-EINVAL);
-		prefix = "unsigned ";
-		field_type = argv[1];
-		field_name = argv[2];
-		*consumed = 3;
-	} else {
-		field_name = argv[1];
-		*consumed = 2;
-	}
-
-	field = kzalloc(sizeof(*field), GFP_KERNEL);
-	if (!field)
-		return ERR_PTR(-ENOMEM);
-
-	len = strlen(field_name);
-	array = strchr(field_name, '[');
-	if (array)
-		len -= strlen(array);
-	else if (field_name[len - 1] == ';')
-		len--;
-
-	field->name = kmemdup_nul(field_name, len, GFP_KERNEL);
-	if (!field->name) {
-		ret = -ENOMEM;
-		goto free;
-	}
-
-	if (field_type[0] == ';')
-		field_type++;
-	len = strlen(field_type) + 1;
-	if (array)
-		len += strlen(array);
-	if (prefix)
-		len += strlen(prefix);
-
-	field->type = kzalloc(len, GFP_KERNEL);
-	if (!field->type) {
-		ret = -ENOMEM;
-		goto free;
-	}
-	if (prefix)
-		strcat(field->type, prefix);
-	strcat(field->type, field_type);
-	if (array) {
-		strcat(field->type, array);
-		if (field->type[len - 1] == ';')
-			field->type[len - 1] = '\0';
-	}
-
-	field->size = synth_field_size(field->type);
-	if (!field->size) {
-		ret = -EINVAL;
-		goto free;
-	}
-
-	if (synth_field_is_string(field->type))
-		field->is_string = true;
-
-	field->is_signed = synth_field_signed(field->type);
-
- out:
-	return field;
- free:
-	free_synth_field(field);
-	field = ERR_PTR(ret);
-	goto out;
-}
-
-static void free_synth_tracepoint(struct tracepoint *tp)
-{
-	if (!tp)
-		return;
-
-	kfree(tp->name);
-	kfree(tp);
-}
-
-static struct tracepoint *alloc_synth_tracepoint(char *name)
-{
-	struct tracepoint *tp;
-
-	tp = kzalloc(sizeof(*tp), GFP_KERNEL);
-	if (!tp)
-		return ERR_PTR(-ENOMEM);
-
-	tp->name = kstrdup(name, GFP_KERNEL);
-	if (!tp->name) {
-		kfree(tp);
-		return ERR_PTR(-ENOMEM);
-	}
-
-	return tp;
-}
-
 typedef void (*synth_probe_func_t) (void *__data, u64 *var_ref_vals,
 				    unsigned int *var_ref_idx);
 
@@ -1177,145 +604,6 @@ static inline void trace_synth(struct synth_event *event, u64 *var_ref_vals,
 	}
 }
 
-static struct synth_event *find_synth_event(const char *name)
-{
-	struct dyn_event *pos;
-	struct synth_event *event;
-
-	for_each_dyn_event(pos) {
-		if (!is_synth_event(pos))
-			continue;
-		event = to_synth_event(pos);
-		if (strcmp(event->name, name) == 0)
-			return event;
-	}
-
-	return NULL;
-}
-
-static struct trace_event_fields synth_event_fields_array[] = {
-	{ .type = TRACE_FUNCTION_TYPE,
-	  .define_fields = synth_event_define_fields },
-	{}
-};
-
-static int register_synth_event(struct synth_event *event)
-{
-	struct trace_event_call *call = &event->call;
-	int ret = 0;
-
-	event->call.class = &event->class;
-	event->class.system = kstrdup(SYNTH_SYSTEM, GFP_KERNEL);
-	if (!event->class.system) {
-		ret = -ENOMEM;
-		goto out;
-	}
-
-	event->tp = alloc_synth_tracepoint(event->name);
-	if (IS_ERR(event->tp)) {
-		ret = PTR_ERR(event->tp);
-		event->tp = NULL;
-		goto out;
-	}
-
-	INIT_LIST_HEAD(&call->class->fields);
-	call->event.funcs = &synth_event_funcs;
-	call->class->fields_array = synth_event_fields_array;
-
-	ret = register_trace_event(&call->event);
-	if (!ret) {
-		ret = -ENODEV;
-		goto out;
-	}
-	call->flags = TRACE_EVENT_FL_TRACEPOINT;
-	call->class->reg = trace_event_reg;
-	call->class->probe = trace_event_raw_event_synth;
-	call->data = event;
-	call->tp = event->tp;
-
-	ret = trace_add_event_call(call);
-	if (ret) {
-		pr_warn("Failed to register synthetic event: %s\n",
-			trace_event_name(call));
-		goto err;
-	}
-
-	ret = set_synth_event_print_fmt(call);
-	if (ret < 0) {
-		trace_remove_event_call(call);
-		goto err;
-	}
- out:
-	return ret;
- err:
-	unregister_trace_event(&call->event);
-	goto out;
-}
-
-static int unregister_synth_event(struct synth_event *event)
-{
-	struct trace_event_call *call = &event->call;
-	int ret;
-
-	ret = trace_remove_event_call(call);
-
-	return ret;
-}
-
-static void free_synth_event(struct synth_event *event)
-{
-	unsigned int i;
-
-	if (!event)
-		return;
-
-	for (i = 0; i < event->n_fields; i++)
-		free_synth_field(event->fields[i]);
-
-	kfree(event->fields);
-	kfree(event->name);
-	kfree(event->class.system);
-	free_synth_tracepoint(event->tp);
-	free_synth_event_print_fmt(&event->call);
-	kfree(event);
-}
-
-static struct synth_event *alloc_synth_event(const char *name, int n_fields,
-					     struct synth_field **fields)
-{
-	struct synth_event *event;
-	unsigned int i;
-
-	event = kzalloc(sizeof(*event), GFP_KERNEL);
-	if (!event) {
-		event = ERR_PTR(-ENOMEM);
-		goto out;
-	}
-
-	event->name = kstrdup(name, GFP_KERNEL);
-	if (!event->name) {
-		kfree(event);
-		event = ERR_PTR(-ENOMEM);
-		goto out;
-	}
-
-	event->fields = kcalloc(n_fields, sizeof(*event->fields), GFP_KERNEL);
-	if (!event->fields) {
-		free_synth_event(event);
-		event = ERR_PTR(-ENOMEM);
-		goto out;
-	}
-
-	dyn_event_init(&event->devent, &synth_event_ops);
-
-	for (i = 0; i < n_fields; i++)
-		event->fields[i] = fields[i];
-
-	event->n_fields = n_fields;
- out:
-	return event;
-}
-
 static void action_trace(struct hist_trigger_data *hist_data,
 			 struct tracing_map_elt *elt, void *rec,
 			 struct ring_buffer_event *rbe, void *key,
@@ -1331,1056 +619,6 @@ struct hist_var_data {
 	struct hist_trigger_data *hist_data;
 };
 
-static int synth_event_check_arg_fn(void *data)
-{
-	struct dynevent_arg_pair *arg_pair = data;
-	int size;
-
-	size = synth_field_size((char *)arg_pair->lhs);
-
-	return size ? 0 : -EINVAL;
-}
-
-/**
- * synth_event_add_field - Add a new field to a synthetic event cmd
- * @cmd: A pointer to the dynevent_cmd struct representing the new event
- * @type: The type of the new field to add
- * @name: The name of the new field to add
- *
- * Add a new field to a synthetic event cmd object.  Field ordering is in
- * the same order the fields are added.
- *
- * See synth_field_size() for available types. If field_name contains
- * [n] the field is considered to be an array.
- *
- * Return: 0 if successful, error otherwise.
- */
-int synth_event_add_field(struct dynevent_cmd *cmd, const char *type,
-			  const char *name)
-{
-	struct dynevent_arg_pair arg_pair;
-	int ret;
-
-	if (cmd->type != DYNEVENT_TYPE_SYNTH)
-		return -EINVAL;
-
-	if (!type || !name)
-		return -EINVAL;
-
-	dynevent_arg_pair_init(&arg_pair, 0, ';');
-
-	arg_pair.lhs = type;
-	arg_pair.rhs = name;
-
-	ret = dynevent_arg_pair_add(cmd, &arg_pair, synth_event_check_arg_fn);
-	if (ret)
-		return ret;
-
-	if (++cmd->n_fields > SYNTH_FIELDS_MAX)
-		ret = -EINVAL;
-
-	return ret;
-}
-EXPORT_SYMBOL_GPL(synth_event_add_field);
-
-/**
- * synth_event_add_field_str - Add a new field to a synthetic event cmd
- * @cmd: A pointer to the dynevent_cmd struct representing the new event
- * @type_name: The type and name of the new field to add, as a single string
- *
- * Add a new field to a synthetic event cmd object, as a single
- * string.  The @type_name string is expected to be of the form 'type
- * name', which will be appended by ';'.  No sanity checking is done -
- * what's passed in is assumed to already be well-formed.  Field
- * ordering is in the same order the fields are added.
- *
- * See synth_field_size() for available types. If field_name contains
- * [n] the field is considered to be an array.
- *
- * Return: 0 if successful, error otherwise.
- */
-int synth_event_add_field_str(struct dynevent_cmd *cmd, const char *type_name)
-{
-	struct dynevent_arg arg;
-	int ret;
-
-	if (cmd->type != DYNEVENT_TYPE_SYNTH)
-		return -EINVAL;
-
-	if (!type_name)
-		return -EINVAL;
-
-	dynevent_arg_init(&arg, ';');
-
-	arg.str = type_name;
-
-	ret = dynevent_arg_add(cmd, &arg, NULL);
-	if (ret)
-		return ret;
-
-	if (++cmd->n_fields > SYNTH_FIELDS_MAX)
-		ret = -EINVAL;
-
-	return ret;
-}
-EXPORT_SYMBOL_GPL(synth_event_add_field_str);
-
-/**
- * synth_event_add_fields - Add multiple fields to a synthetic event cmd
- * @cmd: A pointer to the dynevent_cmd struct representing the new event
- * @fields: An array of type/name field descriptions
- * @n_fields: The number of field descriptions contained in the fields array
- *
- * Add a new set of fields to a synthetic event cmd object.  The event
- * fields that will be defined for the event should be passed in as an
- * array of struct synth_field_desc, and the number of elements in the
- * array passed in as n_fields.  Field ordering will retain the
- * ordering given in the fields array.
- *
- * See synth_field_size() for available types. If field_name contains
- * [n] the field is considered to be an array.
- *
- * Return: 0 if successful, error otherwise.
- */
-int synth_event_add_fields(struct dynevent_cmd *cmd,
-			   struct synth_field_desc *fields,
-			   unsigned int n_fields)
-{
-	unsigned int i;
-	int ret = 0;
-
-	for (i = 0; i < n_fields; i++) {
-		if (fields[i].type == NULL || fields[i].name == NULL) {
-			ret = -EINVAL;
-			break;
-		}
-
-		ret = synth_event_add_field(cmd, fields[i].type, fields[i].name);
-		if (ret)
-			break;
-	}
-
-	return ret;
-}
-EXPORT_SYMBOL_GPL(synth_event_add_fields);
-
-/**
- * __synth_event_gen_cmd_start - Start a synthetic event command from arg list
- * @cmd: A pointer to the dynevent_cmd struct representing the new event
- * @name: The name of the synthetic event
- * @mod: The module creating the event, NULL if not created from a module
- * @args: Variable number of arg (pairs), one pair for each field
- *
- * NOTE: Users normally won't want to call this function directly, but
- * rather use the synth_event_gen_cmd_start() wrapper, which
- * automatically adds a NULL to the end of the arg list.  If this
- * function is used directly, make sure the last arg in the variable
- * arg list is NULL.
- *
- * Generate a synthetic event command to be executed by
- * synth_event_gen_cmd_end().  This function can be used to generate
- * the complete command or only the first part of it; in the latter
- * case, synth_event_add_field(), synth_event_add_field_str(), or
- * synth_event_add_fields() can be used to add more fields following
- * this.
- *
- * There should be an even number variable args, each pair consisting
- * of a type followed by a field name.
- *
- * See synth_field_size() for available types. If field_name contains
- * [n] the field is considered to be an array.
- *
- * Return: 0 if successful, error otherwise.
- */
-int __synth_event_gen_cmd_start(struct dynevent_cmd *cmd, const char *name,
-				struct module *mod, ...)
-{
-	struct dynevent_arg arg;
-	va_list args;
-	int ret;
-
-	cmd->event_name = name;
-	cmd->private_data = mod;
-
-	if (cmd->type != DYNEVENT_TYPE_SYNTH)
-		return -EINVAL;
-
-	dynevent_arg_init(&arg, 0);
-	arg.str = name;
-	ret = dynevent_arg_add(cmd, &arg, NULL);
-	if (ret)
-		return ret;
-
-	va_start(args, mod);
-	for (;;) {
-		const char *type, *name;
-
-		type = va_arg(args, const char *);
-		if (!type)
-			break;
-		name = va_arg(args, const char *);
-		if (!name)
-			break;
-
-		if (++cmd->n_fields > SYNTH_FIELDS_MAX) {
-			ret = -EINVAL;
-			break;
-		}
-
-		ret = synth_event_add_field(cmd, type, name);
-		if (ret)
-			break;
-	}
-	va_end(args);
-
-	return ret;
-}
-EXPORT_SYMBOL_GPL(__synth_event_gen_cmd_start);
-
-/**
- * synth_event_gen_cmd_array_start - Start synthetic event command from an array
- * @cmd: A pointer to the dynevent_cmd struct representing the new event
- * @name: The name of the synthetic event
- * @fields: An array of type/name field descriptions
- * @n_fields: The number of field descriptions contained in the fields array
- *
- * Generate a synthetic event command to be executed by
- * synth_event_gen_cmd_end().  This function can be used to generate
- * the complete command or only the first part of it; in the latter
- * case, synth_event_add_field(), synth_event_add_field_str(), or
- * synth_event_add_fields() can be used to add more fields following
- * this.
- *
- * The event fields that will be defined for the event should be
- * passed in as an array of struct synth_field_desc, and the number of
- * elements in the array passed in as n_fields.  Field ordering will
- * retain the ordering given in the fields array.
- *
- * See synth_field_size() for available types. If field_name contains
- * [n] the field is considered to be an array.
- *
- * Return: 0 if successful, error otherwise.
- */
-int synth_event_gen_cmd_array_start(struct dynevent_cmd *cmd, const char *name,
-				    struct module *mod,
-				    struct synth_field_desc *fields,
-				    unsigned int n_fields)
-{
-	struct dynevent_arg arg;
-	unsigned int i;
-	int ret = 0;
-
-	cmd->event_name = name;
-	cmd->private_data = mod;
-
-	if (cmd->type != DYNEVENT_TYPE_SYNTH)
-		return -EINVAL;
-
-	if (n_fields > SYNTH_FIELDS_MAX)
-		return -EINVAL;
-
-	dynevent_arg_init(&arg, 0);
-	arg.str = name;
-	ret = dynevent_arg_add(cmd, &arg, NULL);
-	if (ret)
-		return ret;
-
-	for (i = 0; i < n_fields; i++) {
-		if (fields[i].type == NULL || fields[i].name == NULL)
-			return -EINVAL;
-
-		ret = synth_event_add_field(cmd, fields[i].type, fields[i].name);
-		if (ret)
-			break;
-	}
-
-	return ret;
-}
-EXPORT_SYMBOL_GPL(synth_event_gen_cmd_array_start);
-
-static int __create_synth_event(int argc, const char *name, const char **argv)
-{
-	struct synth_field *field, *fields[SYNTH_FIELDS_MAX];
-	struct synth_event *event = NULL;
-	int i, consumed = 0, n_fields = 0, ret = 0;
-
-	/*
-	 * Argument syntax:
-	 *  - Add synthetic event: <event_name> field[;field] ...
-	 *  - Remove synthetic event: !<event_name> field[;field] ...
-	 *      where 'field' = type field_name
-	 */
-
-	if (name[0] == '\0' || argc < 1)
-		return -EINVAL;
-
-	mutex_lock(&event_mutex);
-
-	event = find_synth_event(name);
-	if (event) {
-		ret = -EEXIST;
-		goto out;
-	}
-
-	for (i = 0; i < argc - 1; i++) {
-		if (strcmp(argv[i], ";") == 0)
-			continue;
-		if (n_fields == SYNTH_FIELDS_MAX) {
-			ret = -EINVAL;
-			goto err;
-		}
-
-		field = parse_synth_field(argc - i, &argv[i], &consumed);
-		if (IS_ERR(field)) {
-			ret = PTR_ERR(field);
-			goto err;
-		}
-		fields[n_fields++] = field;
-		i += consumed - 1;
-	}
-
-	if (i < argc && strcmp(argv[i], ";") != 0) {
-		ret = -EINVAL;
-		goto err;
-	}
-
-	event = alloc_synth_event(name, n_fields, fields);
-	if (IS_ERR(event)) {
-		ret = PTR_ERR(event);
-		event = NULL;
-		goto err;
-	}
-	ret = register_synth_event(event);
-	if (!ret)
-		dyn_event_add(&event->devent);
-	else
-		free_synth_event(event);
- out:
-	mutex_unlock(&event_mutex);
-
-	return ret;
- err:
-	for (i = 0; i < n_fields; i++)
-		free_synth_field(fields[i]);
-
-	goto out;
-}
-
-/**
- * synth_event_create - Create a new synthetic event
- * @name: The name of the new sythetic event
- * @fields: An array of type/name field descriptions
- * @n_fields: The number of field descriptions contained in the fields array
- * @mod: The module creating the event, NULL if not created from a module
- *
- * Create a new synthetic event with the given name under the
- * trace/events/synthetic/ directory.  The event fields that will be
- * defined for the event should be passed in as an array of struct
- * synth_field_desc, and the number elements in the array passed in as
- * n_fields. Field ordering will retain the ordering given in the
- * fields array.
- *
- * If the new synthetic event is being created from a module, the mod
- * param must be non-NULL.  This will ensure that the trace buffer
- * won't contain unreadable events.
- *
- * The new synth event should be deleted using synth_event_delete()
- * function.  The new synthetic event can be generated from modules or
- * other kernel code using trace_synth_event() and related functions.
- *
- * Return: 0 if successful, error otherwise.
- */
-int synth_event_create(const char *name, struct synth_field_desc *fields,
-		       unsigned int n_fields, struct module *mod)
-{
-	struct dynevent_cmd cmd;
-	char *buf;
-	int ret;
-
-	buf = kzalloc(MAX_DYNEVENT_CMD_LEN, GFP_KERNEL);
-	if (!buf)
-		return -ENOMEM;
-
-	synth_event_cmd_init(&cmd, buf, MAX_DYNEVENT_CMD_LEN);
-
-	ret = synth_event_gen_cmd_array_start(&cmd, name, mod,
-					      fields, n_fields);
-	if (ret)
-		goto out;
-
-	ret = synth_event_gen_cmd_end(&cmd);
- out:
-	kfree(buf);
-
-	return ret;
-}
-EXPORT_SYMBOL_GPL(synth_event_create);
-
-static int destroy_synth_event(struct synth_event *se)
-{
-	int ret;
-
-	if (se->ref)
-		ret = -EBUSY;
-	else {
-		ret = unregister_synth_event(se);
-		if (!ret) {
-			dyn_event_remove(&se->devent);
-			free_synth_event(se);
-		}
-	}
-
-	return ret;
-}
-
-/**
- * synth_event_delete - Delete a synthetic event
- * @event_name: The name of the new sythetic event
- *
- * Delete a synthetic event that was created with synth_event_create().
- *
- * Return: 0 if successful, error otherwise.
- */
-int synth_event_delete(const char *event_name)
-{
-	struct synth_event *se = NULL;
-	struct module *mod = NULL;
-	int ret = -ENOENT;
-
-	mutex_lock(&event_mutex);
-	se = find_synth_event(event_name);
-	if (se) {
-		mod = se->mod;
-		ret = destroy_synth_event(se);
-	}
-	mutex_unlock(&event_mutex);
-
-	if (mod) {
-		mutex_lock(&trace_types_lock);
-		/*
-		 * It is safest to reset the ring buffer if the module
-		 * being unloaded registered any events that were
-		 * used. The only worry is if a new module gets
-		 * loaded, and takes on the same id as the events of
-		 * this module. When printing out the buffer, traced
-		 * events left over from this module may be passed to
-		 * the new module events and unexpected results may
-		 * occur.
-		 */
-		tracing_reset_all_online_cpus();
-		mutex_unlock(&trace_types_lock);
-	}
-
-	return ret;
-}
-EXPORT_SYMBOL_GPL(synth_event_delete);
-
-static int create_or_delete_synth_event(int argc, char **argv)
-{
-	const char *name = argv[0];
-	int ret;
-
-	/* trace_run_command() ensures argc != 0 */
-	if (name[0] == '!') {
-		ret = synth_event_delete(name + 1);
-		return ret;
-	}
-
-	ret = __create_synth_event(argc - 1, name, (const char **)argv + 1);
-	return ret == -ECANCELED ? -EINVAL : ret;
-}
-
-static int synth_event_run_command(struct dynevent_cmd *cmd)
-{
-	struct synth_event *se;
-	int ret;
-
-	ret = trace_run_command(cmd->seq.buffer, create_or_delete_synth_event);
-	if (ret)
-		return ret;
-
-	se = find_synth_event(cmd->event_name);
-	if (WARN_ON(!se))
-		return -ENOENT;
-
-	se->mod = cmd->private_data;
-
-	return ret;
-}
-
-/**
- * synth_event_cmd_init - Initialize a synthetic event command object
- * @cmd: A pointer to the dynevent_cmd struct representing the new event
- * @buf: A pointer to the buffer used to build the command
- * @maxlen: The length of the buffer passed in @buf
- *
- * Initialize a synthetic event command object.  Use this before
- * calling any of the other dyenvent_cmd functions.
- */
-void synth_event_cmd_init(struct dynevent_cmd *cmd, char *buf, int maxlen)
-{
-	dynevent_cmd_init(cmd, buf, maxlen, DYNEVENT_TYPE_SYNTH,
-			  synth_event_run_command);
-}
-EXPORT_SYMBOL_GPL(synth_event_cmd_init);
-
-static inline int
-__synth_event_trace_start(struct trace_event_file *file,
-			  struct synth_event_trace_state *trace_state)
-{
-	int entry_size, fields_size = 0;
-	int ret = 0;
-
-	memset(trace_state, '\0', sizeof(*trace_state));
-
-	/*
-	 * Normal event tracing doesn't get called at all unless the
-	 * ENABLED bit is set (which attaches the probe thus allowing
-	 * this code to be called, etc).  Because this is called
-	 * directly by the user, we don't have that but we still need
-	 * to honor not logging when disabled.  For the the iterated
-	 * trace case, we save the enabed state upon start and just
-	 * ignore the following data calls.
-	 */
-	if (!(file->flags & EVENT_FILE_FL_ENABLED) ||
-	    trace_trigger_soft_disabled(file)) {
-		trace_state->disabled = true;
-		ret = -ENOENT;
-		goto out;
-	}
-
-	trace_state->event = file->event_call->data;
-
-	fields_size = trace_state->event->n_u64 * sizeof(u64);
-
-	/*
-	 * Avoid ring buffer recursion detection, as this event
-	 * is being performed within another event.
-	 */
-	trace_state->buffer = file->tr->array_buffer.buffer;
-	ring_buffer_nest_start(trace_state->buffer);
-
-	entry_size = sizeof(*trace_state->entry) + fields_size;
-	trace_state->entry = trace_event_buffer_reserve(&trace_state->fbuffer,
-							file,
-							entry_size);
-	if (!trace_state->entry) {
-		ring_buffer_nest_end(trace_state->buffer);
-		ret = -EINVAL;
-	}
-out:
-	return ret;
-}
-
-static inline void
-__synth_event_trace_end(struct synth_event_trace_state *trace_state)
-{
-	trace_event_buffer_commit(&trace_state->fbuffer);
-
-	ring_buffer_nest_end(trace_state->buffer);
-}
-
-/**
- * synth_event_trace - Trace a synthetic event
- * @file: The trace_event_file representing the synthetic event
- * @n_vals: The number of values in vals
- * @args: Variable number of args containing the event values
- *
- * Trace a synthetic event using the values passed in the variable
- * argument list.
- *
- * The argument list should be a list 'n_vals' u64 values.  The number
- * of vals must match the number of field in the synthetic event, and
- * must be in the same order as the synthetic event fields.
- *
- * All vals should be cast to u64, and string vals are just pointers
- * to strings, cast to u64.  Strings will be copied into space
- * reserved in the event for the string, using these pointers.
- *
- * Return: 0 on success, err otherwise.
- */
-int synth_event_trace(struct trace_event_file *file, unsigned int n_vals, ...)
-{
-	struct synth_event_trace_state state;
-	unsigned int i, n_u64;
-	va_list args;
-	int ret;
-
-	ret = __synth_event_trace_start(file, &state);
-	if (ret) {
-		if (ret == -ENOENT)
-			ret = 0; /* just disabled, not really an error */
-		return ret;
-	}
-
-	if (n_vals != state.event->n_fields) {
-		ret = -EINVAL;
-		goto out;
-	}
-
-	va_start(args, n_vals);
-	for (i = 0, n_u64 = 0; i < state.event->n_fields; i++) {
-		u64 val;
-
-		val = va_arg(args, u64);
-
-		if (state.event->fields[i]->is_string) {
-			char *str_val = (char *)(long)val;
-			char *str_field = (char *)&state.entry->fields[n_u64];
-
-			strscpy(str_field, str_val, STR_VAR_LEN_MAX);
-			n_u64 += STR_VAR_LEN_MAX / sizeof(u64);
-		} else {
-			struct synth_field *field = state.event->fields[i];
-
-			switch (field->size) {
-			case 1:
-				*(u8 *)&state.entry->fields[n_u64] = (u8)val;
-				break;
-
-			case 2:
-				*(u16 *)&state.entry->fields[n_u64] = (u16)val;
-				break;
-
-			case 4:
-				*(u32 *)&state.entry->fields[n_u64] = (u32)val;
-				break;
-
-			default:
-				state.entry->fields[n_u64] = val;
-				break;
-			}
-			n_u64++;
-		}
-	}
-	va_end(args);
-out:
-	__synth_event_trace_end(&state);
-
-	return ret;
-}
-EXPORT_SYMBOL_GPL(synth_event_trace);
-
-/**
- * synth_event_trace_array - Trace a synthetic event from an array
- * @file: The trace_event_file representing the synthetic event
- * @vals: Array of values
- * @n_vals: The number of values in vals
- *
- * Trace a synthetic event using the values passed in as 'vals'.
- *
- * The 'vals' array is just an array of 'n_vals' u64.  The number of
- * vals must match the number of field in the synthetic event, and
- * must be in the same order as the synthetic event fields.
- *
- * All vals should be cast to u64, and string vals are just pointers
- * to strings, cast to u64.  Strings will be copied into space
- * reserved in the event for the string, using these pointers.
- *
- * Return: 0 on success, err otherwise.
- */
-int synth_event_trace_array(struct trace_event_file *file, u64 *vals,
-			    unsigned int n_vals)
-{
-	struct synth_event_trace_state state;
-	unsigned int i, n_u64;
-	int ret;
-
-	ret = __synth_event_trace_start(file, &state);
-	if (ret) {
-		if (ret == -ENOENT)
-			ret = 0; /* just disabled, not really an error */
-		return ret;
-	}
-
-	if (n_vals != state.event->n_fields) {
-		ret = -EINVAL;
-		goto out;
-	}
-
-	for (i = 0, n_u64 = 0; i < state.event->n_fields; i++) {
-		if (state.event->fields[i]->is_string) {
-			char *str_val = (char *)(long)vals[i];
-			char *str_field = (char *)&state.entry->fields[n_u64];
-
-			strscpy(str_field, str_val, STR_VAR_LEN_MAX);
-			n_u64 += STR_VAR_LEN_MAX / sizeof(u64);
-		} else {
-			struct synth_field *field = state.event->fields[i];
-			u64 val = vals[i];
-
-			switch (field->size) {
-			case 1:
-				*(u8 *)&state.entry->fields[n_u64] = (u8)val;
-				break;
-
-			case 2:
-				*(u16 *)&state.entry->fields[n_u64] = (u16)val;
-				break;
-
-			case 4:
-				*(u32 *)&state.entry->fields[n_u64] = (u32)val;
-				break;
-
-			default:
-				state.entry->fields[n_u64] = val;
-				break;
-			}
-			n_u64++;
-		}
-	}
-out:
-	__synth_event_trace_end(&state);
-
-	return ret;
-}
-EXPORT_SYMBOL_GPL(synth_event_trace_array);
-
-/**
- * synth_event_trace_start - Start piecewise synthetic event trace
- * @file: The trace_event_file representing the synthetic event
- * @trace_state: A pointer to object tracking the piecewise trace state
- *
- * Start the trace of a synthetic event field-by-field rather than all
- * at once.
- *
- * This function 'opens' an event trace, which means space is reserved
- * for the event in the trace buffer, after which the event's
- * individual field values can be set through either
- * synth_event_add_next_val() or synth_event_add_val().
- *
- * A pointer to a trace_state object is passed in, which will keep
- * track of the current event trace state until the event trace is
- * closed (and the event finally traced) using
- * synth_event_trace_end().
- *
- * Note that synth_event_trace_end() must be called after all values
- * have been added for each event trace, regardless of whether adding
- * all field values succeeded or not.
- *
- * Note also that for a given event trace, all fields must be added
- * using either synth_event_add_next_val() or synth_event_add_val()
- * but not both together or interleaved.
- *
- * Return: 0 on success, err otherwise.
- */
-int synth_event_trace_start(struct trace_event_file *file,
-			    struct synth_event_trace_state *trace_state)
-{
-	int ret;
-
-	if (!trace_state)
-		return -EINVAL;
-
-	ret = __synth_event_trace_start(file, trace_state);
-	if (ret == -ENOENT)
-		ret = 0; /* just disabled, not really an error */
-
-	return ret;
-}
-EXPORT_SYMBOL_GPL(synth_event_trace_start);
-
-static int __synth_event_add_val(const char *field_name, u64 val,
-				 struct synth_event_trace_state *trace_state)
-{
-	struct synth_field *field = NULL;
-	struct synth_trace_event *entry;
-	struct synth_event *event;
-	int i, ret = 0;
-
-	if (!trace_state) {
-		ret = -EINVAL;
-		goto out;
-	}
-
-	/* can't mix add_next_synth_val() with add_synth_val() */
-	if (field_name) {
-		if (trace_state->add_next) {
-			ret = -EINVAL;
-			goto out;
-		}
-		trace_state->add_name = true;
-	} else {
-		if (trace_state->add_name) {
-			ret = -EINVAL;
-			goto out;
-		}
-		trace_state->add_next = true;
-	}
-
-	if (trace_state->disabled)
-		goto out;
-
-	event = trace_state->event;
-	if (trace_state->add_name) {
-		for (i = 0; i < event->n_fields; i++) {
-			field = event->fields[i];
-			if (strcmp(field->name, field_name) == 0)
-				break;
-		}
-		if (!field) {
-			ret = -EINVAL;
-			goto out;
-		}
-	} else {
-		if (trace_state->cur_field >= event->n_fields) {
-			ret = -EINVAL;
-			goto out;
-		}
-		field = event->fields[trace_state->cur_field++];
-	}
-
-	entry = trace_state->entry;
-	if (field->is_string) {
-		char *str_val = (char *)(long)val;
-		char *str_field;
-
-		if (!str_val) {
-			ret = -EINVAL;
-			goto out;
-		}
-
-		str_field = (char *)&entry->fields[field->offset];
-		strscpy(str_field, str_val, STR_VAR_LEN_MAX);
-	} else {
-		switch (field->size) {
-		case 1:
-			*(u8 *)&trace_state->entry->fields[field->offset] = (u8)val;
-			break;
-
-		case 2:
-			*(u16 *)&trace_state->entry->fields[field->offset] = (u16)val;
-			break;
-
-		case 4:
-			*(u32 *)&trace_state->entry->fields[field->offset] = (u32)val;
-			break;
-
-		default:
-			trace_state->entry->fields[field->offset] = val;
-			break;
-		}
-	}
- out:
-	return ret;
-}
-
-/**
- * synth_event_add_next_val - Add the next field's value to an open synth trace
- * @val: The value to set the next field to
- * @trace_state: A pointer to object tracking the piecewise trace state
- *
- * Set the value of the next field in an event that's been opened by
- * synth_event_trace_start().
- *
- * The val param should be the value cast to u64.  If the value points
- * to a string, the val param should be a char * cast to u64.
- *
- * This function assumes all the fields in an event are to be set one
- * after another - successive calls to this function are made, one for
- * each field, in the order of the fields in the event, until all
- * fields have been set.  If you'd rather set each field individually
- * without regard to ordering, synth_event_add_val() can be used
- * instead.
- *
- * Note however that synth_event_add_next_val() and
- * synth_event_add_val() can't be intermixed for a given event trace -
- * one or the other but not both can be used at the same time.
- *
- * Note also that synth_event_trace_end() must be called after all
- * values have been added for each event trace, regardless of whether
- * adding all field values succeeded or not.
- *
- * Return: 0 on success, err otherwise.
- */
-int synth_event_add_next_val(u64 val,
-			     struct synth_event_trace_state *trace_state)
-{
-	return __synth_event_add_val(NULL, val, trace_state);
-}
-EXPORT_SYMBOL_GPL(synth_event_add_next_val);
-
-/**
- * synth_event_add_val - Add a named field's value to an open synth trace
- * @field_name: The name of the synthetic event field value to set
- * @val: The value to set the next field to
- * @trace_state: A pointer to object tracking the piecewise trace state
- *
- * Set the value of the named field in an event that's been opened by
- * synth_event_trace_start().
- *
- * The val param should be the value cast to u64.  If the value points
- * to a string, the val param should be a char * cast to u64.
- *
- * This function looks up the field name, and if found, sets the field
- * to the specified value.  This lookup makes this function more
- * expensive than synth_event_add_next_val(), so use that or the
- * none-piecewise synth_event_trace() instead if efficiency is more
- * important.
- *
- * Note however that synth_event_add_next_val() and
- * synth_event_add_val() can't be intermixed for a given event trace -
- * one or the other but not both can be used at the same time.
- *
- * Note also that synth_event_trace_end() must be called after all
- * values have been added for each event trace, regardless of whether
- * adding all field values succeeded or not.
- *
- * Return: 0 on success, err otherwise.
- */
-int synth_event_add_val(const char *field_name, u64 val,
-			struct synth_event_trace_state *trace_state)
-{
-	return __synth_event_add_val(field_name, val, trace_state);
-}
-EXPORT_SYMBOL_GPL(synth_event_add_val);
-
-/**
- * synth_event_trace_end - End piecewise synthetic event trace
- * @trace_state: A pointer to object tracking the piecewise trace state
- *
- * End the trace of a synthetic event opened by
- * synth_event_trace__start().
- *
- * This function 'closes' an event trace, which basically means that
- * it commits the reserved event and cleans up other loose ends.
- *
- * A pointer to a trace_state object is passed in, which will keep
- * track of the current event trace state opened with
- * synth_event_trace_start().
- *
- * Note that this function must be called after all values have been
- * added for each event trace, regardless of whether adding all field
- * values succeeded or not.
- *
- * Return: 0 on success, err otherwise.
- */
-int synth_event_trace_end(struct synth_event_trace_state *trace_state)
-{
-	if (!trace_state)
-		return -EINVAL;
-
-	__synth_event_trace_end(trace_state);
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(synth_event_trace_end);
-
-static int create_synth_event(int argc, const char **argv)
-{
-	const char *name = argv[0];
-	int len;
-
-	if (name[0] != 's' || name[1] != ':')
-		return -ECANCELED;
-	name += 2;
-
-	/* This interface accepts group name prefix */
-	if (strchr(name, '/')) {
-		len = str_has_prefix(name, SYNTH_SYSTEM "/");
-		if (len == 0)
-			return -EINVAL;
-		name += len;
-	}
-	return __create_synth_event(argc - 1, name, argv + 1);
-}
-
-static int synth_event_release(struct dyn_event *ev)
-{
-	struct synth_event *event = to_synth_event(ev);
-	int ret;
-
-	if (event->ref)
-		return -EBUSY;
-
-	ret = unregister_synth_event(event);
-	if (ret)
-		return ret;
-
-	dyn_event_remove(ev);
-	free_synth_event(event);
-	return 0;
-}
-
-static int __synth_event_show(struct seq_file *m, struct synth_event *event)
-{
-	struct synth_field *field;
-	unsigned int i;
-
-	seq_printf(m, "%s\t", event->name);
-
-	for (i = 0; i < event->n_fields; i++) {
-		field = event->fields[i];
-
-		/* parameter values */
-		seq_printf(m, "%s %s%s", field->type, field->name,
-			   i == event->n_fields - 1 ? "" : "; ");
-	}
-
-	seq_putc(m, '\n');
-
-	return 0;
-}
-
-static int synth_event_show(struct seq_file *m, struct dyn_event *ev)
-{
-	struct synth_event *event = to_synth_event(ev);
-
-	seq_printf(m, "s:%s/", event->class.system);
-
-	return __synth_event_show(m, event);
-}
-
-static int synth_events_seq_show(struct seq_file *m, void *v)
-{
-	struct dyn_event *ev = v;
-
-	if (!is_synth_event(ev))
-		return 0;
-
-	return __synth_event_show(m, to_synth_event(ev));
-}
-
-static const struct seq_operations synth_events_seq_op = {
-	.start	= dyn_event_seq_start,
-	.next	= dyn_event_seq_next,
-	.stop	= dyn_event_seq_stop,
-	.show	= synth_events_seq_show,
-};
-
-static int synth_events_open(struct inode *inode, struct file *file)
-{
-	int ret;
-
-	ret = security_locked_down(LOCKDOWN_TRACEFS);
-	if (ret)
-		return ret;
-
-	if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) {
-		ret = dyn_events_release_all(&synth_event_ops);
-		if (ret < 0)
-			return ret;
-	}
-
-	return seq_open(file, &synth_events_seq_op);
-}
-
-static ssize_t synth_events_write(struct file *file,
-				  const char __user *buffer,
-				  size_t count, loff_t *ppos)
-{
-	return trace_parse_run_command(file, buffer, count, ppos,
-				       create_or_delete_synth_event);
-}
-
-static const struct file_operations synth_events_fops = {
-	.open           = synth_events_open,
-	.write		= synth_events_write,
-	.read           = seq_read,
-	.llseek         = seq_lseek,
-	.release        = seq_release,
-};
-
 static u64 hist_field_timestamp(struct hist_field *hist_field,
 				struct tracing_map_elt *elt,
 				struct ring_buffer_event *rbe,
@@ -3320,6 +1558,9 @@ static void __destroy_hist_field(struct hist_field *hist_field)
 	kfree(hist_field->name);
 	kfree(hist_field->type);
 
+	kfree(hist_field->system);
+	kfree(hist_field->event_name);
+
 	kfree(hist_field);
 }
 
@@ -4382,6 +2623,7 @@ static struct hist_field *create_var(struct hist_trigger_data *hist_data,
 		goto out;
 	}
 
+	var->ref = 1;
 	var->flags = HIST_FIELD_FL_VAR;
 	var->var.idx = idx;
 	var->var.hist_data = var->hist_data = hist_data;
@@ -5011,6 +3253,9 @@ static void destroy_field_vars(struct hist_trigger_data *hist_data)
 
 	for (i = 0; i < hist_data->n_field_vars; i++)
 		destroy_field_var(hist_data->field_vars[i]);
+
+	for (i = 0; i < hist_data->n_save_vars; i++)
+		destroy_field_var(hist_data->save_vars[i]);
 }
 
 static void save_field_var(struct hist_trigger_data *hist_data,
@@ -6484,6 +4729,279 @@ const struct file_operations event_hist_fops = {
 	.release = single_release,
 };
 
+#ifdef CONFIG_HIST_TRIGGERS_DEBUG
+static void hist_field_debug_show_flags(struct seq_file *m,
+					unsigned long flags)
+{
+	seq_puts(m, "      flags:\n");
+
+	if (flags & HIST_FIELD_FL_KEY)
+		seq_puts(m, "        HIST_FIELD_FL_KEY\n");
+	else if (flags & HIST_FIELD_FL_HITCOUNT)
+		seq_puts(m, "        VAL: HIST_FIELD_FL_HITCOUNT\n");
+	else if (flags & HIST_FIELD_FL_VAR)
+		seq_puts(m, "        HIST_FIELD_FL_VAR\n");
+	else if (flags & HIST_FIELD_FL_VAR_REF)
+		seq_puts(m, "        HIST_FIELD_FL_VAR_REF\n");
+	else
+		seq_puts(m, "        VAL: normal u64 value\n");
+
+	if (flags & HIST_FIELD_FL_ALIAS)
+		seq_puts(m, "        HIST_FIELD_FL_ALIAS\n");
+}
+
+static int hist_field_debug_show(struct seq_file *m,
+				 struct hist_field *field, unsigned long flags)
+{
+	if ((field->flags & flags) != flags) {
+		seq_printf(m, "ERROR: bad flags - %lx\n", flags);
+		return -EINVAL;
+	}
+
+	hist_field_debug_show_flags(m, field->flags);
+	if (field->field)
+		seq_printf(m, "      ftrace_event_field name: %s\n",
+			   field->field->name);
+
+	if (field->flags & HIST_FIELD_FL_VAR) {
+		seq_printf(m, "      var.name: %s\n", field->var.name);
+		seq_printf(m, "      var.idx (into tracing_map_elt.vars[]): %u\n",
+			   field->var.idx);
+	}
+
+	if (field->flags & HIST_FIELD_FL_ALIAS)
+		seq_printf(m, "      var_ref_idx (into hist_data->var_refs[]): %u\n",
+			   field->var_ref_idx);
+
+	if (field->flags & HIST_FIELD_FL_VAR_REF) {
+		seq_printf(m, "      name: %s\n", field->name);
+		seq_printf(m, "      var.idx (into tracing_map_elt.vars[]): %u\n",
+			   field->var.idx);
+		seq_printf(m, "      var.hist_data: %p\n", field->var.hist_data);
+		seq_printf(m, "      var_ref_idx (into hist_data->var_refs[]): %u\n",
+			   field->var_ref_idx);
+		if (field->system)
+			seq_printf(m, "      system: %s\n", field->system);
+		if (field->event_name)
+			seq_printf(m, "      event_name: %s\n", field->event_name);
+	}
+
+	seq_printf(m, "      type: %s\n", field->type);
+	seq_printf(m, "      size: %u\n", field->size);
+	seq_printf(m, "      is_signed: %u\n", field->is_signed);
+
+	return 0;
+}
+
+static int field_var_debug_show(struct seq_file *m,
+				struct field_var *field_var, unsigned int i,
+				bool save_vars)
+{
+	const char *vars_name = save_vars ? "save_vars" : "field_vars";
+	struct hist_field *field;
+	int ret = 0;
+
+	seq_printf(m, "\n    hist_data->%s[%d]:\n", vars_name, i);
+
+	field = field_var->var;
+
+	seq_printf(m, "\n      %s[%d].var:\n", vars_name, i);
+
+	hist_field_debug_show_flags(m, field->flags);
+	seq_printf(m, "      var.name: %s\n", field->var.name);
+	seq_printf(m, "      var.idx (into tracing_map_elt.vars[]): %u\n",
+		   field->var.idx);
+
+	field = field_var->val;
+
+	seq_printf(m, "\n      %s[%d].val:\n", vars_name, i);
+	if (field->field)
+		seq_printf(m, "      ftrace_event_field name: %s\n",
+			   field->field->name);
+	else {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	seq_printf(m, "      type: %s\n", field->type);
+	seq_printf(m, "      size: %u\n", field->size);
+	seq_printf(m, "      is_signed: %u\n", field->is_signed);
+out:
+	return ret;
+}
+
+static int hist_action_debug_show(struct seq_file *m,
+				  struct action_data *data, int i)
+{
+	int ret = 0;
+
+	if (data->handler == HANDLER_ONMAX ||
+	    data->handler == HANDLER_ONCHANGE) {
+		seq_printf(m, "\n    hist_data->actions[%d].track_data.var_ref:\n", i);
+		ret = hist_field_debug_show(m, data->track_data.var_ref,
+					    HIST_FIELD_FL_VAR_REF);
+		if (ret)
+			goto out;
+
+		seq_printf(m, "\n    hist_data->actions[%d].track_data.track_var:\n", i);
+		ret = hist_field_debug_show(m, data->track_data.track_var,
+					    HIST_FIELD_FL_VAR);
+		if (ret)
+			goto out;
+	}
+
+	if (data->handler == HANDLER_ONMATCH) {
+		seq_printf(m, "\n    hist_data->actions[%d].match_data.event_system: %s\n",
+			   i, data->match_data.event_system);
+		seq_printf(m, "    hist_data->actions[%d].match_data.event: %s\n",
+			   i, data->match_data.event);
+	}
+out:
+	return ret;
+}
+
+static int hist_actions_debug_show(struct seq_file *m,
+				   struct hist_trigger_data *hist_data)
+{
+	int i, ret = 0;
+
+	if (hist_data->n_actions)
+		seq_puts(m, "\n  action tracking variables (for onmax()/onchange()/onmatch()):\n");
+
+	for (i = 0; i < hist_data->n_actions; i++) {
+		struct action_data *action = hist_data->actions[i];
+
+		ret = hist_action_debug_show(m, action, i);
+		if (ret)
+			goto out;
+	}
+
+	if (hist_data->n_save_vars)
+		seq_puts(m, "\n  save action variables (save() params):\n");
+
+	for (i = 0; i < hist_data->n_save_vars; i++) {
+		ret = field_var_debug_show(m, hist_data->save_vars[i], i, true);
+		if (ret)
+			goto out;
+	}
+out:
+	return ret;
+}
+
+static void hist_trigger_debug_show(struct seq_file *m,
+				    struct event_trigger_data *data, int n)
+{
+	struct hist_trigger_data *hist_data;
+	int i, ret;
+
+	if (n > 0)
+		seq_puts(m, "\n\n");
+
+	seq_puts(m, "# event histogram\n#\n# trigger info: ");
+	data->ops->print(m, data->ops, data);
+	seq_puts(m, "#\n\n");
+
+	hist_data = data->private_data;
+
+	seq_printf(m, "hist_data: %p\n\n", hist_data);
+	seq_printf(m, "  n_vals: %u\n", hist_data->n_vals);
+	seq_printf(m, "  n_keys: %u\n", hist_data->n_keys);
+	seq_printf(m, "  n_fields: %u\n", hist_data->n_fields);
+
+	seq_puts(m, "\n  val fields:\n\n");
+
+	seq_puts(m, "    hist_data->fields[0]:\n");
+	ret = hist_field_debug_show(m, hist_data->fields[0],
+				    HIST_FIELD_FL_HITCOUNT);
+	if (ret)
+		return;
+
+	for (i = 1; i < hist_data->n_vals; i++) {
+		seq_printf(m, "\n    hist_data->fields[%d]:\n", i);
+		ret = hist_field_debug_show(m, hist_data->fields[i], 0);
+		if (ret)
+			return;
+	}
+
+	seq_puts(m, "\n  key fields:\n");
+
+	for (i = hist_data->n_vals; i < hist_data->n_fields; i++) {
+		seq_printf(m, "\n    hist_data->fields[%d]:\n", i);
+		ret = hist_field_debug_show(m, hist_data->fields[i],
+					    HIST_FIELD_FL_KEY);
+		if (ret)
+			return;
+	}
+
+	if (hist_data->n_var_refs)
+		seq_puts(m, "\n  variable reference fields:\n");
+
+	for (i = 0; i < hist_data->n_var_refs; i++) {
+		seq_printf(m, "\n    hist_data->var_refs[%d]:\n", i);
+		ret = hist_field_debug_show(m, hist_data->var_refs[i],
+					    HIST_FIELD_FL_VAR_REF);
+		if (ret)
+			return;
+	}
+
+	if (hist_data->n_field_vars)
+		seq_puts(m, "\n  field variables:\n");
+
+	for (i = 0; i < hist_data->n_field_vars; i++) {
+		ret = field_var_debug_show(m, hist_data->field_vars[i], i, false);
+		if (ret)
+			return;
+	}
+
+	ret = hist_actions_debug_show(m, hist_data);
+	if (ret)
+		return;
+}
+
+static int hist_debug_show(struct seq_file *m, void *v)
+{
+	struct event_trigger_data *data;
+	struct trace_event_file *event_file;
+	int n = 0, ret = 0;
+
+	mutex_lock(&event_mutex);
+
+	event_file = event_file_data(m->private);
+	if (unlikely(!event_file)) {
+		ret = -ENODEV;
+		goto out_unlock;
+	}
+
+	list_for_each_entry(data, &event_file->triggers, list) {
+		if (data->cmd_ops->trigger_type == ETT_EVENT_HIST)
+			hist_trigger_debug_show(m, data, n++);
+	}
+
+ out_unlock:
+	mutex_unlock(&event_mutex);
+
+	return ret;
+}
+
+static int event_hist_debug_open(struct inode *inode, struct file *file)
+{
+	int ret;
+
+	ret = security_locked_down(LOCKDOWN_TRACEFS);
+	if (ret)
+		return ret;
+
+	return single_open(file, hist_debug_show, file);
+}
+
+const struct file_operations event_hist_debug_fops = {
+	.open = event_hist_debug_open,
+	.read = seq_read,
+	.llseek = seq_lseek,
+	.release = single_release,
+};
+#endif
+
 static void hist_field_print(struct seq_file *m, struct hist_field *hist_field)
 {
 	const char *field_name = hist_field_name(hist_field, 0);
@@ -7386,37 +5904,3 @@ __init int register_trigger_hist_enable_disable_cmds(void)
 
 	return ret;
 }
-
-static __init int trace_events_hist_init(void)
-{
-	struct dentry *entry = NULL;
-	struct dentry *d_tracer;
-	int err = 0;
-
-	err = dyn_event_register(&synth_event_ops);
-	if (err) {
-		pr_warn("Could not register synth_event_ops\n");
-		return err;
-	}
-
-	d_tracer = tracing_init_dentry();
-	if (IS_ERR(d_tracer)) {
-		err = PTR_ERR(d_tracer);
-		goto err;
-	}
-
-	entry = tracefs_create_file("synthetic_events", 0644, d_tracer,
-				    NULL, &synth_events_fops);
-	if (!entry) {
-		err = -ENODEV;
-		goto err;
-	}
-
-	return err;
- err:
-	pr_warn("Could not create tracefs 'synthetic_events' entry\n");
-
-	return err;
-}
-
-fs_initcall(trace_events_hist_init);
diff --git a/kernel/trace/trace_events_synth.c b/kernel/trace/trace_events_synth.c
new file mode 100644
index 000000000000..c6cca0d1d584
--- /dev/null
+++ b/kernel/trace/trace_events_synth.c
@@ -0,0 +1,1789 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * trace_events_synth - synthetic trace events
+ *
+ * Copyright (C) 2015, 2020 Tom Zanussi <tom.zanussi@linux.intel.com>
+ */
+
+#include <linux/module.h>
+#include <linux/kallsyms.h>
+#include <linux/security.h>
+#include <linux/mutex.h>
+#include <linux/slab.h>
+#include <linux/stacktrace.h>
+#include <linux/rculist.h>
+#include <linux/tracefs.h>
+
+/* for gfp flag names */
+#include <linux/trace_events.h>
+#include <trace/events/mmflags.h>
+
+#include "trace_synth.h"
+
+static int create_synth_event(int argc, const char **argv);
+static int synth_event_show(struct seq_file *m, struct dyn_event *ev);
+static int synth_event_release(struct dyn_event *ev);
+static bool synth_event_is_busy(struct dyn_event *ev);
+static bool synth_event_match(const char *system, const char *event,
+			int argc, const char **argv, struct dyn_event *ev);
+
+static struct dyn_event_operations synth_event_ops = {
+	.create = create_synth_event,
+	.show = synth_event_show,
+	.is_busy = synth_event_is_busy,
+	.free = synth_event_release,
+	.match = synth_event_match,
+};
+
+static bool is_synth_event(struct dyn_event *ev)
+{
+	return ev->ops == &synth_event_ops;
+}
+
+static struct synth_event *to_synth_event(struct dyn_event *ev)
+{
+	return container_of(ev, struct synth_event, devent);
+}
+
+static bool synth_event_is_busy(struct dyn_event *ev)
+{
+	struct synth_event *event = to_synth_event(ev);
+
+	return event->ref != 0;
+}
+
+static bool synth_event_match(const char *system, const char *event,
+			int argc, const char **argv, struct dyn_event *ev)
+{
+	struct synth_event *sev = to_synth_event(ev);
+
+	return strcmp(sev->name, event) == 0 &&
+		(!system || strcmp(system, SYNTH_SYSTEM) == 0);
+}
+
+struct synth_trace_event {
+	struct trace_entry	ent;
+	u64			fields[];
+};
+
+static int synth_event_define_fields(struct trace_event_call *call)
+{
+	struct synth_trace_event trace;
+	int offset = offsetof(typeof(trace), fields);
+	struct synth_event *event = call->data;
+	unsigned int i, size, n_u64;
+	char *name, *type;
+	bool is_signed;
+	int ret = 0;
+
+	for (i = 0, n_u64 = 0; i < event->n_fields; i++) {
+		size = event->fields[i]->size;
+		is_signed = event->fields[i]->is_signed;
+		type = event->fields[i]->type;
+		name = event->fields[i]->name;
+		ret = trace_define_field(call, type, name, offset, size,
+					 is_signed, FILTER_OTHER);
+		if (ret)
+			break;
+
+		event->fields[i]->offset = n_u64;
+
+		if (event->fields[i]->is_string) {
+			offset += STR_VAR_LEN_MAX;
+			n_u64 += STR_VAR_LEN_MAX / sizeof(u64);
+		} else {
+			offset += sizeof(u64);
+			n_u64++;
+		}
+	}
+
+	event->n_u64 = n_u64;
+
+	return ret;
+}
+
+static bool synth_field_signed(char *type)
+{
+	if (str_has_prefix(type, "u"))
+		return false;
+	if (strcmp(type, "gfp_t") == 0)
+		return false;
+
+	return true;
+}
+
+static int synth_field_is_string(char *type)
+{
+	if (strstr(type, "char[") != NULL)
+		return true;
+
+	return false;
+}
+
+static int synth_field_string_size(char *type)
+{
+	char buf[4], *end, *start;
+	unsigned int len;
+	int size, err;
+
+	start = strstr(type, "char[");
+	if (start == NULL)
+		return -EINVAL;
+	start += sizeof("char[") - 1;
+
+	end = strchr(type, ']');
+	if (!end || end < start)
+		return -EINVAL;
+
+	len = end - start;
+	if (len > 3)
+		return -EINVAL;
+
+	strncpy(buf, start, len);
+	buf[len] = '\0';
+
+	err = kstrtouint(buf, 0, &size);
+	if (err)
+		return err;
+
+	if (size > STR_VAR_LEN_MAX)
+		return -EINVAL;
+
+	return size;
+}
+
+static int synth_field_size(char *type)
+{
+	int size = 0;
+
+	if (strcmp(type, "s64") == 0)
+		size = sizeof(s64);
+	else if (strcmp(type, "u64") == 0)
+		size = sizeof(u64);
+	else if (strcmp(type, "s32") == 0)
+		size = sizeof(s32);
+	else if (strcmp(type, "u32") == 0)
+		size = sizeof(u32);
+	else if (strcmp(type, "s16") == 0)
+		size = sizeof(s16);
+	else if (strcmp(type, "u16") == 0)
+		size = sizeof(u16);
+	else if (strcmp(type, "s8") == 0)
+		size = sizeof(s8);
+	else if (strcmp(type, "u8") == 0)
+		size = sizeof(u8);
+	else if (strcmp(type, "char") == 0)
+		size = sizeof(char);
+	else if (strcmp(type, "unsigned char") == 0)
+		size = sizeof(unsigned char);
+	else if (strcmp(type, "int") == 0)
+		size = sizeof(int);
+	else if (strcmp(type, "unsigned int") == 0)
+		size = sizeof(unsigned int);
+	else if (strcmp(type, "long") == 0)
+		size = sizeof(long);
+	else if (strcmp(type, "unsigned long") == 0)
+		size = sizeof(unsigned long);
+	else if (strcmp(type, "pid_t") == 0)
+		size = sizeof(pid_t);
+	else if (strcmp(type, "gfp_t") == 0)
+		size = sizeof(gfp_t);
+	else if (synth_field_is_string(type))
+		size = synth_field_string_size(type);
+
+	return size;
+}
+
+static const char *synth_field_fmt(char *type)
+{
+	const char *fmt = "%llu";
+
+	if (strcmp(type, "s64") == 0)
+		fmt = "%lld";
+	else if (strcmp(type, "u64") == 0)
+		fmt = "%llu";
+	else if (strcmp(type, "s32") == 0)
+		fmt = "%d";
+	else if (strcmp(type, "u32") == 0)
+		fmt = "%u";
+	else if (strcmp(type, "s16") == 0)
+		fmt = "%d";
+	else if (strcmp(type, "u16") == 0)
+		fmt = "%u";
+	else if (strcmp(type, "s8") == 0)
+		fmt = "%d";
+	else if (strcmp(type, "u8") == 0)
+		fmt = "%u";
+	else if (strcmp(type, "char") == 0)
+		fmt = "%d";
+	else if (strcmp(type, "unsigned char") == 0)
+		fmt = "%u";
+	else if (strcmp(type, "int") == 0)
+		fmt = "%d";
+	else if (strcmp(type, "unsigned int") == 0)
+		fmt = "%u";
+	else if (strcmp(type, "long") == 0)
+		fmt = "%ld";
+	else if (strcmp(type, "unsigned long") == 0)
+		fmt = "%lu";
+	else if (strcmp(type, "pid_t") == 0)
+		fmt = "%d";
+	else if (strcmp(type, "gfp_t") == 0)
+		fmt = "%x";
+	else if (synth_field_is_string(type))
+		fmt = "%s";
+
+	return fmt;
+}
+
+static void print_synth_event_num_val(struct trace_seq *s,
+				      char *print_fmt, char *name,
+				      int size, u64 val, char *space)
+{
+	switch (size) {
+	case 1:
+		trace_seq_printf(s, print_fmt, name, (u8)val, space);
+		break;
+
+	case 2:
+		trace_seq_printf(s, print_fmt, name, (u16)val, space);
+		break;
+
+	case 4:
+		trace_seq_printf(s, print_fmt, name, (u32)val, space);
+		break;
+
+	default:
+		trace_seq_printf(s, print_fmt, name, val, space);
+		break;
+	}
+}
+
+static enum print_line_t print_synth_event(struct trace_iterator *iter,
+					   int flags,
+					   struct trace_event *event)
+{
+	struct trace_array *tr = iter->tr;
+	struct trace_seq *s = &iter->seq;
+	struct synth_trace_event *entry;
+	struct synth_event *se;
+	unsigned int i, n_u64;
+	char print_fmt[32];
+	const char *fmt;
+
+	entry = (struct synth_trace_event *)iter->ent;
+	se = container_of(event, struct synth_event, call.event);
+
+	trace_seq_printf(s, "%s: ", se->name);
+
+	for (i = 0, n_u64 = 0; i < se->n_fields; i++) {
+		if (trace_seq_has_overflowed(s))
+			goto end;
+
+		fmt = synth_field_fmt(se->fields[i]->type);
+
+		/* parameter types */
+		if (tr && tr->trace_flags & TRACE_ITER_VERBOSE)
+			trace_seq_printf(s, "%s ", fmt);
+
+		snprintf(print_fmt, sizeof(print_fmt), "%%s=%s%%s", fmt);
+
+		/* parameter values */
+		if (se->fields[i]->is_string) {
+			trace_seq_printf(s, print_fmt, se->fields[i]->name,
+					 (char *)&entry->fields[n_u64],
+					 i == se->n_fields - 1 ? "" : " ");
+			n_u64 += STR_VAR_LEN_MAX / sizeof(u64);
+		} else {
+			struct trace_print_flags __flags[] = {
+			    __def_gfpflag_names, {-1, NULL} };
+			char *space = (i == se->n_fields - 1 ? "" : " ");
+
+			print_synth_event_num_val(s, print_fmt,
+						  se->fields[i]->name,
+						  se->fields[i]->size,
+						  entry->fields[n_u64],
+						  space);
+
+			if (strcmp(se->fields[i]->type, "gfp_t") == 0) {
+				trace_seq_puts(s, " (");
+				trace_print_flags_seq(s, "|",
+						      entry->fields[n_u64],
+						      __flags);
+				trace_seq_putc(s, ')');
+			}
+			n_u64++;
+		}
+	}
+end:
+	trace_seq_putc(s, '\n');
+
+	return trace_handle_return(s);
+}
+
+static struct trace_event_functions synth_event_funcs = {
+	.trace		= print_synth_event
+};
+
+static notrace void trace_event_raw_event_synth(void *__data,
+						u64 *var_ref_vals,
+						unsigned int *var_ref_idx)
+{
+	struct trace_event_file *trace_file = __data;
+	struct synth_trace_event *entry;
+	struct trace_event_buffer fbuffer;
+	struct trace_buffer *buffer;
+	struct synth_event *event;
+	unsigned int i, n_u64, val_idx;
+	int fields_size = 0;
+
+	event = trace_file->event_call->data;
+
+	if (trace_trigger_soft_disabled(trace_file))
+		return;
+
+	fields_size = event->n_u64 * sizeof(u64);
+
+	/*
+	 * Avoid ring buffer recursion detection, as this event
+	 * is being performed within another event.
+	 */
+	buffer = trace_file->tr->array_buffer.buffer;
+	ring_buffer_nest_start(buffer);
+
+	entry = trace_event_buffer_reserve(&fbuffer, trace_file,
+					   sizeof(*entry) + fields_size);
+	if (!entry)
+		goto out;
+
+	for (i = 0, n_u64 = 0; i < event->n_fields; i++) {
+		val_idx = var_ref_idx[i];
+		if (event->fields[i]->is_string) {
+			char *str_val = (char *)(long)var_ref_vals[val_idx];
+			char *str_field = (char *)&entry->fields[n_u64];
+
+			strscpy(str_field, str_val, STR_VAR_LEN_MAX);
+			n_u64 += STR_VAR_LEN_MAX / sizeof(u64);
+		} else {
+			struct synth_field *field = event->fields[i];
+			u64 val = var_ref_vals[val_idx];
+
+			switch (field->size) {
+			case 1:
+				*(u8 *)&entry->fields[n_u64] = (u8)val;
+				break;
+
+			case 2:
+				*(u16 *)&entry->fields[n_u64] = (u16)val;
+				break;
+
+			case 4:
+				*(u32 *)&entry->fields[n_u64] = (u32)val;
+				break;
+
+			default:
+				entry->fields[n_u64] = val;
+				break;
+			}
+			n_u64++;
+		}
+	}
+
+	trace_event_buffer_commit(&fbuffer);
+out:
+	ring_buffer_nest_end(buffer);
+}
+
+static void free_synth_event_print_fmt(struct trace_event_call *call)
+{
+	if (call) {
+		kfree(call->print_fmt);
+		call->print_fmt = NULL;
+	}
+}
+
+static int __set_synth_event_print_fmt(struct synth_event *event,
+				       char *buf, int len)
+{
+	const char *fmt;
+	int pos = 0;
+	int i;
+
+	/* When len=0, we just calculate the needed length */
+#define LEN_OR_ZERO (len ? len - pos : 0)
+
+	pos += snprintf(buf + pos, LEN_OR_ZERO, "\"");
+	for (i = 0; i < event->n_fields; i++) {
+		fmt = synth_field_fmt(event->fields[i]->type);
+		pos += snprintf(buf + pos, LEN_OR_ZERO, "%s=%s%s",
+				event->fields[i]->name, fmt,
+				i == event->n_fields - 1 ? "" : ", ");
+	}
+	pos += snprintf(buf + pos, LEN_OR_ZERO, "\"");
+
+	for (i = 0; i < event->n_fields; i++) {
+		pos += snprintf(buf + pos, LEN_OR_ZERO,
+				", REC->%s", event->fields[i]->name);
+	}
+
+#undef LEN_OR_ZERO
+
+	/* return the length of print_fmt */
+	return pos;
+}
+
+static int set_synth_event_print_fmt(struct trace_event_call *call)
+{
+	struct synth_event *event = call->data;
+	char *print_fmt;
+	int len;
+
+	/* First: called with 0 length to calculate the needed length */
+	len = __set_synth_event_print_fmt(event, NULL, 0);
+
+	print_fmt = kmalloc(len + 1, GFP_KERNEL);
+	if (!print_fmt)
+		return -ENOMEM;
+
+	/* Second: actually write the @print_fmt */
+	__set_synth_event_print_fmt(event, print_fmt, len + 1);
+	call->print_fmt = print_fmt;
+
+	return 0;
+}
+
+static void free_synth_field(struct synth_field *field)
+{
+	kfree(field->type);
+	kfree(field->name);
+	kfree(field);
+}
+
+static struct synth_field *parse_synth_field(int argc, const char **argv,
+					     int *consumed)
+{
+	struct synth_field *field;
+	const char *prefix = NULL, *field_type = argv[0], *field_name, *array;
+	int len, ret = 0;
+
+	if (field_type[0] == ';')
+		field_type++;
+
+	if (!strcmp(field_type, "unsigned")) {
+		if (argc < 3)
+			return ERR_PTR(-EINVAL);
+		prefix = "unsigned ";
+		field_type = argv[1];
+		field_name = argv[2];
+		*consumed = 3;
+	} else {
+		field_name = argv[1];
+		*consumed = 2;
+	}
+
+	field = kzalloc(sizeof(*field), GFP_KERNEL);
+	if (!field)
+		return ERR_PTR(-ENOMEM);
+
+	len = strlen(field_name);
+	array = strchr(field_name, '[');
+	if (array)
+		len -= strlen(array);
+	else if (field_name[len - 1] == ';')
+		len--;
+
+	field->name = kmemdup_nul(field_name, len, GFP_KERNEL);
+	if (!field->name) {
+		ret = -ENOMEM;
+		goto free;
+	}
+
+	if (field_type[0] == ';')
+		field_type++;
+	len = strlen(field_type) + 1;
+	if (array)
+		len += strlen(array);
+	if (prefix)
+		len += strlen(prefix);
+
+	field->type = kzalloc(len, GFP_KERNEL);
+	if (!field->type) {
+		ret = -ENOMEM;
+		goto free;
+	}
+	if (prefix)
+		strcat(field->type, prefix);
+	strcat(field->type, field_type);
+	if (array) {
+		strcat(field->type, array);
+		if (field->type[len - 1] == ';')
+			field->type[len - 1] = '\0';
+	}
+
+	field->size = synth_field_size(field->type);
+	if (!field->size) {
+		ret = -EINVAL;
+		goto free;
+	}
+
+	if (synth_field_is_string(field->type))
+		field->is_string = true;
+
+	field->is_signed = synth_field_signed(field->type);
+
+ out:
+	return field;
+ free:
+	free_synth_field(field);
+	field = ERR_PTR(ret);
+	goto out;
+}
+
+static void free_synth_tracepoint(struct tracepoint *tp)
+{
+	if (!tp)
+		return;
+
+	kfree(tp->name);
+	kfree(tp);
+}
+
+static struct tracepoint *alloc_synth_tracepoint(char *name)
+{
+	struct tracepoint *tp;
+
+	tp = kzalloc(sizeof(*tp), GFP_KERNEL);
+	if (!tp)
+		return ERR_PTR(-ENOMEM);
+
+	tp->name = kstrdup(name, GFP_KERNEL);
+	if (!tp->name) {
+		kfree(tp);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	return tp;
+}
+
+struct synth_event *find_synth_event(const char *name)
+{
+	struct dyn_event *pos;
+	struct synth_event *event;
+
+	for_each_dyn_event(pos) {
+		if (!is_synth_event(pos))
+			continue;
+		event = to_synth_event(pos);
+		if (strcmp(event->name, name) == 0)
+			return event;
+	}
+
+	return NULL;
+}
+
+static struct trace_event_fields synth_event_fields_array[] = {
+	{ .type = TRACE_FUNCTION_TYPE,
+	  .define_fields = synth_event_define_fields },
+	{}
+};
+
+static int register_synth_event(struct synth_event *event)
+{
+	struct trace_event_call *call = &event->call;
+	int ret = 0;
+
+	event->call.class = &event->class;
+	event->class.system = kstrdup(SYNTH_SYSTEM, GFP_KERNEL);
+	if (!event->class.system) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	event->tp = alloc_synth_tracepoint(event->name);
+	if (IS_ERR(event->tp)) {
+		ret = PTR_ERR(event->tp);
+		event->tp = NULL;
+		goto out;
+	}
+
+	INIT_LIST_HEAD(&call->class->fields);
+	call->event.funcs = &synth_event_funcs;
+	call->class->fields_array = synth_event_fields_array;
+
+	ret = register_trace_event(&call->event);
+	if (!ret) {
+		ret = -ENODEV;
+		goto out;
+	}
+	call->flags = TRACE_EVENT_FL_TRACEPOINT;
+	call->class->reg = trace_event_reg;
+	call->class->probe = trace_event_raw_event_synth;
+	call->data = event;
+	call->tp = event->tp;
+
+	ret = trace_add_event_call(call);
+	if (ret) {
+		pr_warn("Failed to register synthetic event: %s\n",
+			trace_event_name(call));
+		goto err;
+	}
+
+	ret = set_synth_event_print_fmt(call);
+	if (ret < 0) {
+		trace_remove_event_call(call);
+		goto err;
+	}
+ out:
+	return ret;
+ err:
+	unregister_trace_event(&call->event);
+	goto out;
+}
+
+static int unregister_synth_event(struct synth_event *event)
+{
+	struct trace_event_call *call = &event->call;
+	int ret;
+
+	ret = trace_remove_event_call(call);
+
+	return ret;
+}
+
+static void free_synth_event(struct synth_event *event)
+{
+	unsigned int i;
+
+	if (!event)
+		return;
+
+	for (i = 0; i < event->n_fields; i++)
+		free_synth_field(event->fields[i]);
+
+	kfree(event->fields);
+	kfree(event->name);
+	kfree(event->class.system);
+	free_synth_tracepoint(event->tp);
+	free_synth_event_print_fmt(&event->call);
+	kfree(event);
+}
+
+static struct synth_event *alloc_synth_event(const char *name, int n_fields,
+					     struct synth_field **fields)
+{
+	struct synth_event *event;
+	unsigned int i;
+
+	event = kzalloc(sizeof(*event), GFP_KERNEL);
+	if (!event) {
+		event = ERR_PTR(-ENOMEM);
+		goto out;
+	}
+
+	event->name = kstrdup(name, GFP_KERNEL);
+	if (!event->name) {
+		kfree(event);
+		event = ERR_PTR(-ENOMEM);
+		goto out;
+	}
+
+	event->fields = kcalloc(n_fields, sizeof(*event->fields), GFP_KERNEL);
+	if (!event->fields) {
+		free_synth_event(event);
+		event = ERR_PTR(-ENOMEM);
+		goto out;
+	}
+
+	dyn_event_init(&event->devent, &synth_event_ops);
+
+	for (i = 0; i < n_fields; i++)
+		event->fields[i] = fields[i];
+
+	event->n_fields = n_fields;
+ out:
+	return event;
+}
+
+static int synth_event_check_arg_fn(void *data)
+{
+	struct dynevent_arg_pair *arg_pair = data;
+	int size;
+
+	size = synth_field_size((char *)arg_pair->lhs);
+
+	return size ? 0 : -EINVAL;
+}
+
+/**
+ * synth_event_add_field - Add a new field to a synthetic event cmd
+ * @cmd: A pointer to the dynevent_cmd struct representing the new event
+ * @type: The type of the new field to add
+ * @name: The name of the new field to add
+ *
+ * Add a new field to a synthetic event cmd object.  Field ordering is in
+ * the same order the fields are added.
+ *
+ * See synth_field_size() for available types. If field_name contains
+ * [n] the field is considered to be an array.
+ *
+ * Return: 0 if successful, error otherwise.
+ */
+int synth_event_add_field(struct dynevent_cmd *cmd, const char *type,
+			  const char *name)
+{
+	struct dynevent_arg_pair arg_pair;
+	int ret;
+
+	if (cmd->type != DYNEVENT_TYPE_SYNTH)
+		return -EINVAL;
+
+	if (!type || !name)
+		return -EINVAL;
+
+	dynevent_arg_pair_init(&arg_pair, 0, ';');
+
+	arg_pair.lhs = type;
+	arg_pair.rhs = name;
+
+	ret = dynevent_arg_pair_add(cmd, &arg_pair, synth_event_check_arg_fn);
+	if (ret)
+		return ret;
+
+	if (++cmd->n_fields > SYNTH_FIELDS_MAX)
+		ret = -EINVAL;
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(synth_event_add_field);
+
+/**
+ * synth_event_add_field_str - Add a new field to a synthetic event cmd
+ * @cmd: A pointer to the dynevent_cmd struct representing the new event
+ * @type_name: The type and name of the new field to add, as a single string
+ *
+ * Add a new field to a synthetic event cmd object, as a single
+ * string.  The @type_name string is expected to be of the form 'type
+ * name', which will be appended by ';'.  No sanity checking is done -
+ * what's passed in is assumed to already be well-formed.  Field
+ * ordering is in the same order the fields are added.
+ *
+ * See synth_field_size() for available types. If field_name contains
+ * [n] the field is considered to be an array.
+ *
+ * Return: 0 if successful, error otherwise.
+ */
+int synth_event_add_field_str(struct dynevent_cmd *cmd, const char *type_name)
+{
+	struct dynevent_arg arg;
+	int ret;
+
+	if (cmd->type != DYNEVENT_TYPE_SYNTH)
+		return -EINVAL;
+
+	if (!type_name)
+		return -EINVAL;
+
+	dynevent_arg_init(&arg, ';');
+
+	arg.str = type_name;
+
+	ret = dynevent_arg_add(cmd, &arg, NULL);
+	if (ret)
+		return ret;
+
+	if (++cmd->n_fields > SYNTH_FIELDS_MAX)
+		ret = -EINVAL;
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(synth_event_add_field_str);
+
+/**
+ * synth_event_add_fields - Add multiple fields to a synthetic event cmd
+ * @cmd: A pointer to the dynevent_cmd struct representing the new event
+ * @fields: An array of type/name field descriptions
+ * @n_fields: The number of field descriptions contained in the fields array
+ *
+ * Add a new set of fields to a synthetic event cmd object.  The event
+ * fields that will be defined for the event should be passed in as an
+ * array of struct synth_field_desc, and the number of elements in the
+ * array passed in as n_fields.  Field ordering will retain the
+ * ordering given in the fields array.
+ *
+ * See synth_field_size() for available types. If field_name contains
+ * [n] the field is considered to be an array.
+ *
+ * Return: 0 if successful, error otherwise.
+ */
+int synth_event_add_fields(struct dynevent_cmd *cmd,
+			   struct synth_field_desc *fields,
+			   unsigned int n_fields)
+{
+	unsigned int i;
+	int ret = 0;
+
+	for (i = 0; i < n_fields; i++) {
+		if (fields[i].type == NULL || fields[i].name == NULL) {
+			ret = -EINVAL;
+			break;
+		}
+
+		ret = synth_event_add_field(cmd, fields[i].type, fields[i].name);
+		if (ret)
+			break;
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(synth_event_add_fields);
+
+/**
+ * __synth_event_gen_cmd_start - Start a synthetic event command from arg list
+ * @cmd: A pointer to the dynevent_cmd struct representing the new event
+ * @name: The name of the synthetic event
+ * @mod: The module creating the event, NULL if not created from a module
+ * @args: Variable number of arg (pairs), one pair for each field
+ *
+ * NOTE: Users normally won't want to call this function directly, but
+ * rather use the synth_event_gen_cmd_start() wrapper, which
+ * automatically adds a NULL to the end of the arg list.  If this
+ * function is used directly, make sure the last arg in the variable
+ * arg list is NULL.
+ *
+ * Generate a synthetic event command to be executed by
+ * synth_event_gen_cmd_end().  This function can be used to generate
+ * the complete command or only the first part of it; in the latter
+ * case, synth_event_add_field(), synth_event_add_field_str(), or
+ * synth_event_add_fields() can be used to add more fields following
+ * this.
+ *
+ * There should be an even number variable args, each pair consisting
+ * of a type followed by a field name.
+ *
+ * See synth_field_size() for available types. If field_name contains
+ * [n] the field is considered to be an array.
+ *
+ * Return: 0 if successful, error otherwise.
+ */
+int __synth_event_gen_cmd_start(struct dynevent_cmd *cmd, const char *name,
+				struct module *mod, ...)
+{
+	struct dynevent_arg arg;
+	va_list args;
+	int ret;
+
+	cmd->event_name = name;
+	cmd->private_data = mod;
+
+	if (cmd->type != DYNEVENT_TYPE_SYNTH)
+		return -EINVAL;
+
+	dynevent_arg_init(&arg, 0);
+	arg.str = name;
+	ret = dynevent_arg_add(cmd, &arg, NULL);
+	if (ret)
+		return ret;
+
+	va_start(args, mod);
+	for (;;) {
+		const char *type, *name;
+
+		type = va_arg(args, const char *);
+		if (!type)
+			break;
+		name = va_arg(args, const char *);
+		if (!name)
+			break;
+
+		if (++cmd->n_fields > SYNTH_FIELDS_MAX) {
+			ret = -EINVAL;
+			break;
+		}
+
+		ret = synth_event_add_field(cmd, type, name);
+		if (ret)
+			break;
+	}
+	va_end(args);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(__synth_event_gen_cmd_start);
+
+/**
+ * synth_event_gen_cmd_array_start - Start synthetic event command from an array
+ * @cmd: A pointer to the dynevent_cmd struct representing the new event
+ * @name: The name of the synthetic event
+ * @fields: An array of type/name field descriptions
+ * @n_fields: The number of field descriptions contained in the fields array
+ *
+ * Generate a synthetic event command to be executed by
+ * synth_event_gen_cmd_end().  This function can be used to generate
+ * the complete command or only the first part of it; in the latter
+ * case, synth_event_add_field(), synth_event_add_field_str(), or
+ * synth_event_add_fields() can be used to add more fields following
+ * this.
+ *
+ * The event fields that will be defined for the event should be
+ * passed in as an array of struct synth_field_desc, and the number of
+ * elements in the array passed in as n_fields.  Field ordering will
+ * retain the ordering given in the fields array.
+ *
+ * See synth_field_size() for available types. If field_name contains
+ * [n] the field is considered to be an array.
+ *
+ * Return: 0 if successful, error otherwise.
+ */
+int synth_event_gen_cmd_array_start(struct dynevent_cmd *cmd, const char *name,
+				    struct module *mod,
+				    struct synth_field_desc *fields,
+				    unsigned int n_fields)
+{
+	struct dynevent_arg arg;
+	unsigned int i;
+	int ret = 0;
+
+	cmd->event_name = name;
+	cmd->private_data = mod;
+
+	if (cmd->type != DYNEVENT_TYPE_SYNTH)
+		return -EINVAL;
+
+	if (n_fields > SYNTH_FIELDS_MAX)
+		return -EINVAL;
+
+	dynevent_arg_init(&arg, 0);
+	arg.str = name;
+	ret = dynevent_arg_add(cmd, &arg, NULL);
+	if (ret)
+		return ret;
+
+	for (i = 0; i < n_fields; i++) {
+		if (fields[i].type == NULL || fields[i].name == NULL)
+			return -EINVAL;
+
+		ret = synth_event_add_field(cmd, fields[i].type, fields[i].name);
+		if (ret)
+			break;
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(synth_event_gen_cmd_array_start);
+
+static int __create_synth_event(int argc, const char *name, const char **argv)
+{
+	struct synth_field *field, *fields[SYNTH_FIELDS_MAX];
+	struct synth_event *event = NULL;
+	int i, consumed = 0, n_fields = 0, ret = 0;
+
+	/*
+	 * Argument syntax:
+	 *  - Add synthetic event: <event_name> field[;field] ...
+	 *  - Remove synthetic event: !<event_name> field[;field] ...
+	 *      where 'field' = type field_name
+	 */
+
+	if (name[0] == '\0' || argc < 1)
+		return -EINVAL;
+
+	mutex_lock(&event_mutex);
+
+	event = find_synth_event(name);
+	if (event) {
+		ret = -EEXIST;
+		goto out;
+	}
+
+	for (i = 0; i < argc - 1; i++) {
+		if (strcmp(argv[i], ";") == 0)
+			continue;
+		if (n_fields == SYNTH_FIELDS_MAX) {
+			ret = -EINVAL;
+			goto err;
+		}
+
+		field = parse_synth_field(argc - i, &argv[i], &consumed);
+		if (IS_ERR(field)) {
+			ret = PTR_ERR(field);
+			goto err;
+		}
+		fields[n_fields++] = field;
+		i += consumed - 1;
+	}
+
+	if (i < argc && strcmp(argv[i], ";") != 0) {
+		ret = -EINVAL;
+		goto err;
+	}
+
+	event = alloc_synth_event(name, n_fields, fields);
+	if (IS_ERR(event)) {
+		ret = PTR_ERR(event);
+		event = NULL;
+		goto err;
+	}
+	ret = register_synth_event(event);
+	if (!ret)
+		dyn_event_add(&event->devent);
+	else
+		free_synth_event(event);
+ out:
+	mutex_unlock(&event_mutex);
+
+	return ret;
+ err:
+	for (i = 0; i < n_fields; i++)
+		free_synth_field(fields[i]);
+
+	goto out;
+}
+
+/**
+ * synth_event_create - Create a new synthetic event
+ * @name: The name of the new sythetic event
+ * @fields: An array of type/name field descriptions
+ * @n_fields: The number of field descriptions contained in the fields array
+ * @mod: The module creating the event, NULL if not created from a module
+ *
+ * Create a new synthetic event with the given name under the
+ * trace/events/synthetic/ directory.  The event fields that will be
+ * defined for the event should be passed in as an array of struct
+ * synth_field_desc, and the number elements in the array passed in as
+ * n_fields. Field ordering will retain the ordering given in the
+ * fields array.
+ *
+ * If the new synthetic event is being created from a module, the mod
+ * param must be non-NULL.  This will ensure that the trace buffer
+ * won't contain unreadable events.
+ *
+ * The new synth event should be deleted using synth_event_delete()
+ * function.  The new synthetic event can be generated from modules or
+ * other kernel code using trace_synth_event() and related functions.
+ *
+ * Return: 0 if successful, error otherwise.
+ */
+int synth_event_create(const char *name, struct synth_field_desc *fields,
+		       unsigned int n_fields, struct module *mod)
+{
+	struct dynevent_cmd cmd;
+	char *buf;
+	int ret;
+
+	buf = kzalloc(MAX_DYNEVENT_CMD_LEN, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	synth_event_cmd_init(&cmd, buf, MAX_DYNEVENT_CMD_LEN);
+
+	ret = synth_event_gen_cmd_array_start(&cmd, name, mod,
+					      fields, n_fields);
+	if (ret)
+		goto out;
+
+	ret = synth_event_gen_cmd_end(&cmd);
+ out:
+	kfree(buf);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(synth_event_create);
+
+static int destroy_synth_event(struct synth_event *se)
+{
+	int ret;
+
+	if (se->ref)
+		ret = -EBUSY;
+	else {
+		ret = unregister_synth_event(se);
+		if (!ret) {
+			dyn_event_remove(&se->devent);
+			free_synth_event(se);
+		}
+	}
+
+	return ret;
+}
+
+/**
+ * synth_event_delete - Delete a synthetic event
+ * @event_name: The name of the new sythetic event
+ *
+ * Delete a synthetic event that was created with synth_event_create().
+ *
+ * Return: 0 if successful, error otherwise.
+ */
+int synth_event_delete(const char *event_name)
+{
+	struct synth_event *se = NULL;
+	struct module *mod = NULL;
+	int ret = -ENOENT;
+
+	mutex_lock(&event_mutex);
+	se = find_synth_event(event_name);
+	if (se) {
+		mod = se->mod;
+		ret = destroy_synth_event(se);
+	}
+	mutex_unlock(&event_mutex);
+
+	if (mod) {
+		mutex_lock(&trace_types_lock);
+		/*
+		 * It is safest to reset the ring buffer if the module
+		 * being unloaded registered any events that were
+		 * used. The only worry is if a new module gets
+		 * loaded, and takes on the same id as the events of
+		 * this module. When printing out the buffer, traced
+		 * events left over from this module may be passed to
+		 * the new module events and unexpected results may
+		 * occur.
+		 */
+		tracing_reset_all_online_cpus();
+		mutex_unlock(&trace_types_lock);
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(synth_event_delete);
+
+static int create_or_delete_synth_event(int argc, char **argv)
+{
+	const char *name = argv[0];
+	int ret;
+
+	/* trace_run_command() ensures argc != 0 */
+	if (name[0] == '!') {
+		ret = synth_event_delete(name + 1);
+		return ret;
+	}
+
+	ret = __create_synth_event(argc - 1, name, (const char **)argv + 1);
+	return ret == -ECANCELED ? -EINVAL : ret;
+}
+
+static int synth_event_run_command(struct dynevent_cmd *cmd)
+{
+	struct synth_event *se;
+	int ret;
+
+	ret = trace_run_command(cmd->seq.buffer, create_or_delete_synth_event);
+	if (ret)
+		return ret;
+
+	se = find_synth_event(cmd->event_name);
+	if (WARN_ON(!se))
+		return -ENOENT;
+
+	se->mod = cmd->private_data;
+
+	return ret;
+}
+
+/**
+ * synth_event_cmd_init - Initialize a synthetic event command object
+ * @cmd: A pointer to the dynevent_cmd struct representing the new event
+ * @buf: A pointer to the buffer used to build the command
+ * @maxlen: The length of the buffer passed in @buf
+ *
+ * Initialize a synthetic event command object.  Use this before
+ * calling any of the other dyenvent_cmd functions.
+ */
+void synth_event_cmd_init(struct dynevent_cmd *cmd, char *buf, int maxlen)
+{
+	dynevent_cmd_init(cmd, buf, maxlen, DYNEVENT_TYPE_SYNTH,
+			  synth_event_run_command);
+}
+EXPORT_SYMBOL_GPL(synth_event_cmd_init);
+
+static inline int
+__synth_event_trace_start(struct trace_event_file *file,
+			  struct synth_event_trace_state *trace_state)
+{
+	int entry_size, fields_size = 0;
+	int ret = 0;
+
+	memset(trace_state, '\0', sizeof(*trace_state));
+
+	/*
+	 * Normal event tracing doesn't get called at all unless the
+	 * ENABLED bit is set (which attaches the probe thus allowing
+	 * this code to be called, etc).  Because this is called
+	 * directly by the user, we don't have that but we still need
+	 * to honor not logging when disabled.  For the the iterated
+	 * trace case, we save the enabed state upon start and just
+	 * ignore the following data calls.
+	 */
+	if (!(file->flags & EVENT_FILE_FL_ENABLED) ||
+	    trace_trigger_soft_disabled(file)) {
+		trace_state->disabled = true;
+		ret = -ENOENT;
+		goto out;
+	}
+
+	trace_state->event = file->event_call->data;
+
+	fields_size = trace_state->event->n_u64 * sizeof(u64);
+
+	/*
+	 * Avoid ring buffer recursion detection, as this event
+	 * is being performed within another event.
+	 */
+	trace_state->buffer = file->tr->array_buffer.buffer;
+	ring_buffer_nest_start(trace_state->buffer);
+
+	entry_size = sizeof(*trace_state->entry) + fields_size;
+	trace_state->entry = trace_event_buffer_reserve(&trace_state->fbuffer,
+							file,
+							entry_size);
+	if (!trace_state->entry) {
+		ring_buffer_nest_end(trace_state->buffer);
+		ret = -EINVAL;
+	}
+out:
+	return ret;
+}
+
+static inline void
+__synth_event_trace_end(struct synth_event_trace_state *trace_state)
+{
+	trace_event_buffer_commit(&trace_state->fbuffer);
+
+	ring_buffer_nest_end(trace_state->buffer);
+}
+
+/**
+ * synth_event_trace - Trace a synthetic event
+ * @file: The trace_event_file representing the synthetic event
+ * @n_vals: The number of values in vals
+ * @args: Variable number of args containing the event values
+ *
+ * Trace a synthetic event using the values passed in the variable
+ * argument list.
+ *
+ * The argument list should be a list 'n_vals' u64 values.  The number
+ * of vals must match the number of field in the synthetic event, and
+ * must be in the same order as the synthetic event fields.
+ *
+ * All vals should be cast to u64, and string vals are just pointers
+ * to strings, cast to u64.  Strings will be copied into space
+ * reserved in the event for the string, using these pointers.
+ *
+ * Return: 0 on success, err otherwise.
+ */
+int synth_event_trace(struct trace_event_file *file, unsigned int n_vals, ...)
+{
+	struct synth_event_trace_state state;
+	unsigned int i, n_u64;
+	va_list args;
+	int ret;
+
+	ret = __synth_event_trace_start(file, &state);
+	if (ret) {
+		if (ret == -ENOENT)
+			ret = 0; /* just disabled, not really an error */
+		return ret;
+	}
+
+	if (n_vals != state.event->n_fields) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	va_start(args, n_vals);
+	for (i = 0, n_u64 = 0; i < state.event->n_fields; i++) {
+		u64 val;
+
+		val = va_arg(args, u64);
+
+		if (state.event->fields[i]->is_string) {
+			char *str_val = (char *)(long)val;
+			char *str_field = (char *)&state.entry->fields[n_u64];
+
+			strscpy(str_field, str_val, STR_VAR_LEN_MAX);
+			n_u64 += STR_VAR_LEN_MAX / sizeof(u64);
+		} else {
+			struct synth_field *field = state.event->fields[i];
+
+			switch (field->size) {
+			case 1:
+				*(u8 *)&state.entry->fields[n_u64] = (u8)val;
+				break;
+
+			case 2:
+				*(u16 *)&state.entry->fields[n_u64] = (u16)val;
+				break;
+
+			case 4:
+				*(u32 *)&state.entry->fields[n_u64] = (u32)val;
+				break;
+
+			default:
+				state.entry->fields[n_u64] = val;
+				break;
+			}
+			n_u64++;
+		}
+	}
+	va_end(args);
+out:
+	__synth_event_trace_end(&state);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(synth_event_trace);
+
+/**
+ * synth_event_trace_array - Trace a synthetic event from an array
+ * @file: The trace_event_file representing the synthetic event
+ * @vals: Array of values
+ * @n_vals: The number of values in vals
+ *
+ * Trace a synthetic event using the values passed in as 'vals'.
+ *
+ * The 'vals' array is just an array of 'n_vals' u64.  The number of
+ * vals must match the number of field in the synthetic event, and
+ * must be in the same order as the synthetic event fields.
+ *
+ * All vals should be cast to u64, and string vals are just pointers
+ * to strings, cast to u64.  Strings will be copied into space
+ * reserved in the event for the string, using these pointers.
+ *
+ * Return: 0 on success, err otherwise.
+ */
+int synth_event_trace_array(struct trace_event_file *file, u64 *vals,
+			    unsigned int n_vals)
+{
+	struct synth_event_trace_state state;
+	unsigned int i, n_u64;
+	int ret;
+
+	ret = __synth_event_trace_start(file, &state);
+	if (ret) {
+		if (ret == -ENOENT)
+			ret = 0; /* just disabled, not really an error */
+		return ret;
+	}
+
+	if (n_vals != state.event->n_fields) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	for (i = 0, n_u64 = 0; i < state.event->n_fields; i++) {
+		if (state.event->fields[i]->is_string) {
+			char *str_val = (char *)(long)vals[i];
+			char *str_field = (char *)&state.entry->fields[n_u64];
+
+			strscpy(str_field, str_val, STR_VAR_LEN_MAX);
+			n_u64 += STR_VAR_LEN_MAX / sizeof(u64);
+		} else {
+			struct synth_field *field = state.event->fields[i];
+			u64 val = vals[i];
+
+			switch (field->size) {
+			case 1:
+				*(u8 *)&state.entry->fields[n_u64] = (u8)val;
+				break;
+
+			case 2:
+				*(u16 *)&state.entry->fields[n_u64] = (u16)val;
+				break;
+
+			case 4:
+				*(u32 *)&state.entry->fields[n_u64] = (u32)val;
+				break;
+
+			default:
+				state.entry->fields[n_u64] = val;
+				break;
+			}
+			n_u64++;
+		}
+	}
+out:
+	__synth_event_trace_end(&state);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(synth_event_trace_array);
+
+/**
+ * synth_event_trace_start - Start piecewise synthetic event trace
+ * @file: The trace_event_file representing the synthetic event
+ * @trace_state: A pointer to object tracking the piecewise trace state
+ *
+ * Start the trace of a synthetic event field-by-field rather than all
+ * at once.
+ *
+ * This function 'opens' an event trace, which means space is reserved
+ * for the event in the trace buffer, after which the event's
+ * individual field values can be set through either
+ * synth_event_add_next_val() or synth_event_add_val().
+ *
+ * A pointer to a trace_state object is passed in, which will keep
+ * track of the current event trace state until the event trace is
+ * closed (and the event finally traced) using
+ * synth_event_trace_end().
+ *
+ * Note that synth_event_trace_end() must be called after all values
+ * have been added for each event trace, regardless of whether adding
+ * all field values succeeded or not.
+ *
+ * Note also that for a given event trace, all fields must be added
+ * using either synth_event_add_next_val() or synth_event_add_val()
+ * but not both together or interleaved.
+ *
+ * Return: 0 on success, err otherwise.
+ */
+int synth_event_trace_start(struct trace_event_file *file,
+			    struct synth_event_trace_state *trace_state)
+{
+	int ret;
+
+	if (!trace_state)
+		return -EINVAL;
+
+	ret = __synth_event_trace_start(file, trace_state);
+	if (ret == -ENOENT)
+		ret = 0; /* just disabled, not really an error */
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(synth_event_trace_start);
+
+static int __synth_event_add_val(const char *field_name, u64 val,
+				 struct synth_event_trace_state *trace_state)
+{
+	struct synth_field *field = NULL;
+	struct synth_trace_event *entry;
+	struct synth_event *event;
+	int i, ret = 0;
+
+	if (!trace_state) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	/* can't mix add_next_synth_val() with add_synth_val() */
+	if (field_name) {
+		if (trace_state->add_next) {
+			ret = -EINVAL;
+			goto out;
+		}
+		trace_state->add_name = true;
+	} else {
+		if (trace_state->add_name) {
+			ret = -EINVAL;
+			goto out;
+		}
+		trace_state->add_next = true;
+	}
+
+	if (trace_state->disabled)
+		goto out;
+
+	event = trace_state->event;
+	if (trace_state->add_name) {
+		for (i = 0; i < event->n_fields; i++) {
+			field = event->fields[i];
+			if (strcmp(field->name, field_name) == 0)
+				break;
+		}
+		if (!field) {
+			ret = -EINVAL;
+			goto out;
+		}
+	} else {
+		if (trace_state->cur_field >= event->n_fields) {
+			ret = -EINVAL;
+			goto out;
+		}
+		field = event->fields[trace_state->cur_field++];
+	}
+
+	entry = trace_state->entry;
+	if (field->is_string) {
+		char *str_val = (char *)(long)val;
+		char *str_field;
+
+		if (!str_val) {
+			ret = -EINVAL;
+			goto out;
+		}
+
+		str_field = (char *)&entry->fields[field->offset];
+		strscpy(str_field, str_val, STR_VAR_LEN_MAX);
+	} else {
+		switch (field->size) {
+		case 1:
+			*(u8 *)&trace_state->entry->fields[field->offset] = (u8)val;
+			break;
+
+		case 2:
+			*(u16 *)&trace_state->entry->fields[field->offset] = (u16)val;
+			break;
+
+		case 4:
+			*(u32 *)&trace_state->entry->fields[field->offset] = (u32)val;
+			break;
+
+		default:
+			trace_state->entry->fields[field->offset] = val;
+			break;
+		}
+	}
+ out:
+	return ret;
+}
+
+/**
+ * synth_event_add_next_val - Add the next field's value to an open synth trace
+ * @val: The value to set the next field to
+ * @trace_state: A pointer to object tracking the piecewise trace state
+ *
+ * Set the value of the next field in an event that's been opened by
+ * synth_event_trace_start().
+ *
+ * The val param should be the value cast to u64.  If the value points
+ * to a string, the val param should be a char * cast to u64.
+ *
+ * This function assumes all the fields in an event are to be set one
+ * after another - successive calls to this function are made, one for
+ * each field, in the order of the fields in the event, until all
+ * fields have been set.  If you'd rather set each field individually
+ * without regard to ordering, synth_event_add_val() can be used
+ * instead.
+ *
+ * Note however that synth_event_add_next_val() and
+ * synth_event_add_val() can't be intermixed for a given event trace -
+ * one or the other but not both can be used at the same time.
+ *
+ * Note also that synth_event_trace_end() must be called after all
+ * values have been added for each event trace, regardless of whether
+ * adding all field values succeeded or not.
+ *
+ * Return: 0 on success, err otherwise.
+ */
+int synth_event_add_next_val(u64 val,
+			     struct synth_event_trace_state *trace_state)
+{
+	return __synth_event_add_val(NULL, val, trace_state);
+}
+EXPORT_SYMBOL_GPL(synth_event_add_next_val);
+
+/**
+ * synth_event_add_val - Add a named field's value to an open synth trace
+ * @field_name: The name of the synthetic event field value to set
+ * @val: The value to set the next field to
+ * @trace_state: A pointer to object tracking the piecewise trace state
+ *
+ * Set the value of the named field in an event that's been opened by
+ * synth_event_trace_start().
+ *
+ * The val param should be the value cast to u64.  If the value points
+ * to a string, the val param should be a char * cast to u64.
+ *
+ * This function looks up the field name, and if found, sets the field
+ * to the specified value.  This lookup makes this function more
+ * expensive than synth_event_add_next_val(), so use that or the
+ * none-piecewise synth_event_trace() instead if efficiency is more
+ * important.
+ *
+ * Note however that synth_event_add_next_val() and
+ * synth_event_add_val() can't be intermixed for a given event trace -
+ * one or the other but not both can be used at the same time.
+ *
+ * Note also that synth_event_trace_end() must be called after all
+ * values have been added for each event trace, regardless of whether
+ * adding all field values succeeded or not.
+ *
+ * Return: 0 on success, err otherwise.
+ */
+int synth_event_add_val(const char *field_name, u64 val,
+			struct synth_event_trace_state *trace_state)
+{
+	return __synth_event_add_val(field_name, val, trace_state);
+}
+EXPORT_SYMBOL_GPL(synth_event_add_val);
+
+/**
+ * synth_event_trace_end - End piecewise synthetic event trace
+ * @trace_state: A pointer to object tracking the piecewise trace state
+ *
+ * End the trace of a synthetic event opened by
+ * synth_event_trace__start().
+ *
+ * This function 'closes' an event trace, which basically means that
+ * it commits the reserved event and cleans up other loose ends.
+ *
+ * A pointer to a trace_state object is passed in, which will keep
+ * track of the current event trace state opened with
+ * synth_event_trace_start().
+ *
+ * Note that this function must be called after all values have been
+ * added for each event trace, regardless of whether adding all field
+ * values succeeded or not.
+ *
+ * Return: 0 on success, err otherwise.
+ */
+int synth_event_trace_end(struct synth_event_trace_state *trace_state)
+{
+	if (!trace_state)
+		return -EINVAL;
+
+	__synth_event_trace_end(trace_state);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(synth_event_trace_end);
+
+static int create_synth_event(int argc, const char **argv)
+{
+	const char *name = argv[0];
+	int len;
+
+	if (name[0] != 's' || name[1] != ':')
+		return -ECANCELED;
+	name += 2;
+
+	/* This interface accepts group name prefix */
+	if (strchr(name, '/')) {
+		len = str_has_prefix(name, SYNTH_SYSTEM "/");
+		if (len == 0)
+			return -EINVAL;
+		name += len;
+	}
+	return __create_synth_event(argc - 1, name, argv + 1);
+}
+
+static int synth_event_release(struct dyn_event *ev)
+{
+	struct synth_event *event = to_synth_event(ev);
+	int ret;
+
+	if (event->ref)
+		return -EBUSY;
+
+	ret = unregister_synth_event(event);
+	if (ret)
+		return ret;
+
+	dyn_event_remove(ev);
+	free_synth_event(event);
+	return 0;
+}
+
+static int __synth_event_show(struct seq_file *m, struct synth_event *event)
+{
+	struct synth_field *field;
+	unsigned int i;
+
+	seq_printf(m, "%s\t", event->name);
+
+	for (i = 0; i < event->n_fields; i++) {
+		field = event->fields[i];
+
+		/* parameter values */
+		seq_printf(m, "%s %s%s", field->type, field->name,
+			   i == event->n_fields - 1 ? "" : "; ");
+	}
+
+	seq_putc(m, '\n');
+
+	return 0;
+}
+
+static int synth_event_show(struct seq_file *m, struct dyn_event *ev)
+{
+	struct synth_event *event = to_synth_event(ev);
+
+	seq_printf(m, "s:%s/", event->class.system);
+
+	return __synth_event_show(m, event);
+}
+
+static int synth_events_seq_show(struct seq_file *m, void *v)
+{
+	struct dyn_event *ev = v;
+
+	if (!is_synth_event(ev))
+		return 0;
+
+	return __synth_event_show(m, to_synth_event(ev));
+}
+
+static const struct seq_operations synth_events_seq_op = {
+	.start	= dyn_event_seq_start,
+	.next	= dyn_event_seq_next,
+	.stop	= dyn_event_seq_stop,
+	.show	= synth_events_seq_show,
+};
+
+static int synth_events_open(struct inode *inode, struct file *file)
+{
+	int ret;
+
+	ret = security_locked_down(LOCKDOWN_TRACEFS);
+	if (ret)
+		return ret;
+
+	if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) {
+		ret = dyn_events_release_all(&synth_event_ops);
+		if (ret < 0)
+			return ret;
+	}
+
+	return seq_open(file, &synth_events_seq_op);
+}
+
+static ssize_t synth_events_write(struct file *file,
+				  const char __user *buffer,
+				  size_t count, loff_t *ppos)
+{
+	return trace_parse_run_command(file, buffer, count, ppos,
+				       create_or_delete_synth_event);
+}
+
+static const struct file_operations synth_events_fops = {
+	.open           = synth_events_open,
+	.write		= synth_events_write,
+	.read           = seq_read,
+	.llseek         = seq_lseek,
+	.release        = seq_release,
+};
+
+static __init int trace_events_synth_init(void)
+{
+	struct dentry *entry = NULL;
+	struct dentry *d_tracer;
+	int err = 0;
+
+	err = dyn_event_register(&synth_event_ops);
+	if (err) {
+		pr_warn("Could not register synth_event_ops\n");
+		return err;
+	}
+
+	d_tracer = tracing_init_dentry();
+	if (IS_ERR(d_tracer)) {
+		err = PTR_ERR(d_tracer);
+		goto err;
+	}
+
+	entry = tracefs_create_file("synthetic_events", 0644, d_tracer,
+				    NULL, &synth_events_fops);
+	if (!entry) {
+		err = -ENODEV;
+		goto err;
+	}
+
+	return err;
+ err:
+	pr_warn("Could not create tracefs 'synthetic_events' entry\n");
+
+	return err;
+}
+
+fs_initcall(trace_events_synth_init);
diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c
index dd34a1b46a86..f725802160c0 100644
--- a/kernel/trace/trace_events_trigger.c
+++ b/kernel/trace/trace_events_trigger.c
@@ -216,11 +216,17 @@ static int event_trigger_regex_open(struct inode *inode, struct file *file)
 
 int trigger_process_regex(struct trace_event_file *file, char *buff)
 {
-	char *command, *next = buff;
+	char *command, *next;
 	struct event_command *p;
 	int ret = -EINVAL;
 
+	next = buff = skip_spaces(buff);
 	command = strsep(&next, ": \t");
+	if (next) {
+		next = skip_spaces(next);
+		if (!*next)
+			next = NULL;
+	}
 	command = (command[0] != '!') ? command : command + 1;
 
 	mutex_lock(&trigger_cmd_mutex);
@@ -630,8 +636,14 @@ event_trigger_callback(struct event_command *cmd_ops,
 	int ret;
 
 	/* separate the trigger from the filter (t:n [if filter]) */
-	if (param && isdigit(param[0]))
+	if (param && isdigit(param[0])) {
 		trigger = strsep(&param, " \t");
+		if (param) {
+			param = skip_spaces(param);
+			if (!*param)
+				param = NULL;
+		}
+	}
 
 	trigger_ops = cmd_ops->get_trigger_ops(cmd, trigger);
 
@@ -1088,14 +1100,10 @@ register_snapshot_trigger(char *glob, struct event_trigger_ops *ops,
 			  struct event_trigger_data *data,
 			  struct trace_event_file *file)
 {
-	int ret = register_trigger(glob, ops, data, file);
-
-	if (ret > 0 && tracing_alloc_snapshot_instance(file->tr) != 0) {
-		unregister_trigger(glob, ops, data, file);
-		ret = 0;
-	}
+	if (tracing_alloc_snapshot_instance(file->tr) != 0)
+		return 0;
 
-	return ret;
+	return register_trigger(glob, ops, data, file);
 }
 
 static int
@@ -1372,6 +1380,11 @@ int event_enable_trigger_func(struct event_command *cmd_ops,
 	trigger = strsep(&param, " \t");
 	if (!trigger)
 		return -EINVAL;
+	if (param) {
+		param = skip_spaces(param);
+		if (!*param)
+			param = NULL;
+	}
 
 	system = strsep(&trigger, ":");
 	if (!trigger)
diff --git a/kernel/trace/trace_export.c b/kernel/trace/trace_export.c
index 77ce5a3b6773..70d3d0a09053 100644
--- a/kernel/trace/trace_export.c
+++ b/kernel/trace/trace_export.c
@@ -45,6 +45,9 @@ static int ftrace_event_register(struct trace_event_call *call,
 #undef __field_desc
 #define __field_desc(type, container, item)		type item;
 
+#undef __field_packed
+#define __field_packed(type, container, item)		type item;
+
 #undef __array
 #define __array(type, item, size)			type item[size];
 
@@ -85,6 +88,13 @@ static void __always_unused ____ftrace_check_##name(void)		\
 	.size = sizeof(_type), .align = __alignof__(_type),		\
 	is_signed_type(_type), .filter_type = _filter_type },
 
+
+#undef __field_ext_packed
+#define __field_ext_packed(_type, _item, _filter_type) {	\
+	.type = #_type, .name = #_item,				\
+	.size = sizeof(_type), .align = 1,			\
+	is_signed_type(_type), .filter_type = _filter_type },
+
 #undef __field
 #define __field(_type, _item) __field_ext(_type, _item, FILTER_OTHER)
 
@@ -94,6 +104,9 @@ static void __always_unused ____ftrace_check_##name(void)		\
 #undef __field_desc
 #define __field_desc(_type, _container, _item) __field_ext(_type, _item, FILTER_OTHER)
 
+#undef __field_packed
+#define __field_packed(_type, _container, _item) __field_ext_packed(_type, _item, FILTER_OTHER)
+
 #undef __array
 #define __array(_type, _item, _len) {					\
 	.type = #_type"["__stringify(_len)"]", .name = #_item,		\
@@ -129,6 +142,9 @@ static struct trace_event_fields ftrace_event_fields_##name[] = {	\
 #undef __field_desc
 #define __field_desc(type, container, item)
 
+#undef __field_packed
+#define __field_packed(type, container, item)
+
 #undef __array
 #define __array(type, item, len)
 
diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c
index 8a4c8d5c2c98..dd4dff71d89a 100644
--- a/kernel/trace/trace_functions.c
+++ b/kernel/trace/trace_functions.c
@@ -42,7 +42,7 @@ static int allocate_ftrace_ops(struct trace_array *tr)
 	if (!ops)
 		return -ENOMEM;
 
-	/* Currently only the non stack verision is supported */
+	/* Currently only the non stack version is supported */
 	ops->func = function_trace_call;
 	ops->flags = FTRACE_OPS_FL_RECURSION_SAFE | FTRACE_OPS_FL_PID;
 
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index 7d71546ba00a..4a9c49c08ec9 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -482,7 +482,7 @@ get_return_for_leaf(struct trace_iterator *iter,
 
 	/* this is a leaf, now advance the iterator */
 	if (ring_iter)
-		ring_buffer_read(ring_iter, NULL);
+		ring_buffer_iter_advance(ring_iter);
 
 	return next;
 }
diff --git a/kernel/trace/trace_hwlat.c b/kernel/trace/trace_hwlat.c
index a48808c43249..17873e5d0353 100644
--- a/kernel/trace/trace_hwlat.c
+++ b/kernel/trace/trace_hwlat.c
@@ -83,6 +83,7 @@ struct hwlat_sample {
 	u64			nmi_total_ts;	/* Total time spent in NMIs */
 	struct timespec64	timestamp;	/* wall time */
 	int			nmi_count;	/* # NMIs during this sample */
+	int			count;		/* # of iteratons over threash */
 };
 
 /* keep the global state somewhere. */
@@ -124,6 +125,7 @@ static void trace_hwlat_sample(struct hwlat_sample *sample)
 	entry->timestamp		= sample->timestamp;
 	entry->nmi_total_ts		= sample->nmi_total_ts;
 	entry->nmi_count		= sample->nmi_count;
+	entry->count			= sample->count;
 
 	if (!call_filter_check_discard(call, entry, buffer, event))
 		trace_buffer_unlock_commit_nostack(buffer, event);
@@ -167,12 +169,14 @@ void trace_hwlat_callback(bool enter)
 static int get_sample(void)
 {
 	struct trace_array *tr = hwlat_trace;
+	struct hwlat_sample s;
 	time_type start, t1, t2, last_t2;
-	s64 diff, total, last_total = 0;
+	s64 diff, outer_diff, total, last_total = 0;
 	u64 sample = 0;
 	u64 thresh = tracing_thresh;
 	u64 outer_sample = 0;
 	int ret = -1;
+	unsigned int count = 0;
 
 	do_div(thresh, NSEC_PER_USEC); /* modifies interval value */
 
@@ -186,6 +190,7 @@ static int get_sample(void)
 
 	init_time(last_t2, 0);
 	start = time_get(); /* start timestamp */
+	outer_diff = 0;
 
 	do {
 
@@ -194,14 +199,14 @@ static int get_sample(void)
 
 		if (time_u64(last_t2)) {
 			/* Check the delta from outer loop (t2 to next t1) */
-			diff = time_to_us(time_sub(t1, last_t2));
+			outer_diff = time_to_us(time_sub(t1, last_t2));
 			/* This shouldn't happen */
-			if (diff < 0) {
+			if (outer_diff < 0) {
 				pr_err(BANNER "time running backwards\n");
 				goto out;
 			}
-			if (diff > outer_sample)
-				outer_sample = diff;
+			if (outer_diff > outer_sample)
+				outer_sample = outer_diff;
 		}
 		last_t2 = t2;
 
@@ -217,6 +222,12 @@ static int get_sample(void)
 		/* This checks the inner loop (t1 to t2) */
 		diff = time_to_us(time_sub(t2, t1));     /* current diff */
 
+		if (diff > thresh || outer_diff > thresh) {
+			if (!count)
+				ktime_get_real_ts64(&s.timestamp);
+			count++;
+		}
+
 		/* This shouldn't happen */
 		if (diff < 0) {
 			pr_err(BANNER "time running backwards\n");
@@ -236,7 +247,6 @@ static int get_sample(void)
 
 	/* If we exceed the threshold value, we have found a hardware latency */
 	if (sample > thresh || outer_sample > thresh) {
-		struct hwlat_sample s;
 		u64 latency;
 
 		ret = 1;
@@ -249,9 +259,9 @@ static int get_sample(void)
 		s.seqnum = hwlat_data.count;
 		s.duration = sample;
 		s.outer_duration = outer_sample;
-		ktime_get_real_ts64(&s.timestamp);
 		s.nmi_total_ts = nmi_total_ts;
 		s.nmi_count = nmi_count;
+		s.count = count;
 		trace_hwlat_sample(&s);
 
 		latency = max(sample, outer_sample);
@@ -273,6 +283,7 @@ static bool disable_migrate;
 static void move_to_next_cpu(void)
 {
 	struct cpumask *current_mask = &save_cpumask;
+	struct trace_array *tr = hwlat_trace;
 	int next_cpu;
 
 	if (disable_migrate)
@@ -286,7 +297,7 @@ static void move_to_next_cpu(void)
 		goto disable;
 
 	get_online_cpus();
-	cpumask_and(current_mask, cpu_online_mask, tracing_buffer_mask);
+	cpumask_and(current_mask, cpu_online_mask, tr->tracing_cpumask);
 	next_cpu = cpumask_next(smp_processor_id(), current_mask);
 	put_online_cpus();
 
@@ -361,9 +372,8 @@ static int start_kthread(struct trace_array *tr)
 		return 0;
 
 	/* Just pick the first CPU on first iteration */
-	current_mask = &save_cpumask;
 	get_online_cpus();
-	cpumask_and(current_mask, cpu_online_mask, tracing_buffer_mask);
+	cpumask_and(current_mask, cpu_online_mask, tr->tracing_cpumask);
 	put_online_cpus();
 	next_cpu = cpumask_first(current_mask);
 
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 362cca52f5de..aefb6065b508 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -453,7 +453,7 @@ static bool __within_notrace_func(unsigned long addr)
 
 static bool within_notrace_func(struct trace_kprobe *tk)
 {
-	unsigned long addr = addr = trace_kprobe_address(tk);
+	unsigned long addr = trace_kprobe_address(tk);
 	char symname[KSYM_NAME_LEN], *p;
 
 	if (!__within_notrace_func(addr))
@@ -940,6 +940,9 @@ EXPORT_SYMBOL_GPL(kprobe_event_cmd_init);
  * complete command or only the first part of it; in the latter case,
  * kprobe_event_add_fields() can be used to add more fields following this.
  *
+ * Unlikely the synth_event_gen_cmd_start(), @loc must be specified. This
+ * returns -EINVAL if @loc == NULL.
+ *
  * Return: 0 if successful, error otherwise.
  */
 int __kprobe_event_gen_cmd_start(struct dynevent_cmd *cmd, bool kretprobe,
@@ -953,6 +956,9 @@ int __kprobe_event_gen_cmd_start(struct dynevent_cmd *cmd, bool kretprobe,
 	if (cmd->type != DYNEVENT_TYPE_KPROBE)
 		return -EINVAL;
 
+	if (!loc)
+		return -EINVAL;
+
 	if (kretprobe)
 		snprintf(buf, MAX_EVENT_NAME_LEN, "r:kprobes/%s", name);
 	else
@@ -1078,6 +1084,8 @@ static int trace_kprobe_show(struct seq_file *m, struct dyn_event *ev)
 	int i;
 
 	seq_putc(m, trace_kprobe_is_return(tk) ? 'r' : 'p');
+	if (trace_kprobe_is_return(tk) && tk->rp.maxactive)
+		seq_printf(m, "%d", tk->rp.maxactive);
 	seq_printf(m, ":%s/%s", trace_probe_group_name(&tk->tp),
 				trace_probe_name(&tk->tp));
 
@@ -1194,35 +1202,41 @@ static const struct file_operations kprobe_profile_ops = {
 
 /* Return the length of string -- including null terminal byte */
 static nokprobe_inline int
+fetch_store_strlen_user(unsigned long addr)
+{
+	const void __user *uaddr =  (__force const void __user *)addr;
+
+	return strnlen_user_nofault(uaddr, MAX_STRING_SIZE);
+}
+
+/* Return the length of string -- including null terminal byte */
+static nokprobe_inline int
 fetch_store_strlen(unsigned long addr)
 {
 	int ret, len = 0;
 	u8 c;
 
+#ifdef CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE
+	if (addr < TASK_SIZE)
+		return fetch_store_strlen_user(addr);
+#endif
+
 	do {
-		ret = probe_kernel_read(&c, (u8 *)addr + len, 1);
+		ret = copy_from_kernel_nofault(&c, (u8 *)addr + len, 1);
 		len++;
 	} while (c && ret == 0 && len < MAX_STRING_SIZE);
 
 	return (ret < 0) ? ret : len;
 }
 
-/* Return the length of string -- including null terminal byte */
-static nokprobe_inline int
-fetch_store_strlen_user(unsigned long addr)
-{
-	const void __user *uaddr =  (__force const void __user *)addr;
-
-	return strnlen_unsafe_user(uaddr, MAX_STRING_SIZE);
-}
-
 /*
- * Fetch a null-terminated string. Caller MUST set *(u32 *)buf with max
- * length and relative data location.
+ * Fetch a null-terminated string from user. Caller MUST set *(u32 *)buf
+ * with max length and relative data location.
  */
 static nokprobe_inline int
-fetch_store_string(unsigned long addr, void *dest, void *base)
+fetch_store_string_user(unsigned long addr, void *dest, void *base)
 {
+	const void __user *uaddr =  (__force const void __user *)addr;
 	int maxlen = get_loc_len(*(u32 *)dest);
 	void *__dest;
 	long ret;
@@ -1232,11 +1246,7 @@ fetch_store_string(unsigned long addr, void *dest, void *base)
 
 	__dest = get_loc_data(dest, base);
 
-	/*
-	 * Try to get string again, since the string can be changed while
-	 * probing.
-	 */
-	ret = strncpy_from_unsafe(__dest, (void *)addr, maxlen);
+	ret = strncpy_from_user_nofault(__dest, uaddr, maxlen);
 	if (ret >= 0)
 		*(u32 *)dest = make_data_loc(ret, __dest - base);
 
@@ -1244,23 +1254,31 @@ fetch_store_string(unsigned long addr, void *dest, void *base)
 }
 
 /*
- * Fetch a null-terminated string from user. Caller MUST set *(u32 *)buf
- * with max length and relative data location.
+ * Fetch a null-terminated string. Caller MUST set *(u32 *)buf with max
+ * length and relative data location.
  */
 static nokprobe_inline int
-fetch_store_string_user(unsigned long addr, void *dest, void *base)
+fetch_store_string(unsigned long addr, void *dest, void *base)
 {
-	const void __user *uaddr =  (__force const void __user *)addr;
 	int maxlen = get_loc_len(*(u32 *)dest);
 	void *__dest;
 	long ret;
 
+#ifdef CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE
+	if ((unsigned long)addr < TASK_SIZE)
+		return fetch_store_string_user(addr, dest, base);
+#endif
+
 	if (unlikely(!maxlen))
 		return -ENOMEM;
 
 	__dest = get_loc_data(dest, base);
 
-	ret = strncpy_from_unsafe_user(__dest, uaddr, maxlen);
+	/*
+	 * Try to get string again, since the string can be changed while
+	 * probing.
+	 */
+	ret = strncpy_from_kernel_nofault(__dest, (void *)addr, maxlen);
 	if (ret >= 0)
 		*(u32 *)dest = make_data_loc(ret, __dest - base);
 
@@ -1268,17 +1286,21 @@ fetch_store_string_user(unsigned long addr, void *dest, void *base)
 }
 
 static nokprobe_inline int
-probe_mem_read(void *dest, void *src, size_t size)
+probe_mem_read_user(void *dest, void *src, size_t size)
 {
-	return probe_kernel_read(dest, src, size);
+	const void __user *uaddr =  (__force const void __user *)src;
+
+	return copy_from_user_nofault(dest, uaddr, size);
 }
 
 static nokprobe_inline int
-probe_mem_read_user(void *dest, void *src, size_t size)
+probe_mem_read(void *dest, void *src, size_t size)
 {
-	const void __user *uaddr =  (__force const void __user *)src;
-
-	return probe_user_read(dest, uaddr, size);
+#ifdef CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE
+	if ((unsigned long)src < TASK_SIZE)
+		return probe_mem_read_user(dest, src, size);
+#endif
+	return copy_from_kernel_nofault(dest, src, size);
 }
 
 /* Note that we don't verify it, since the code does not come from user space */
@@ -1621,7 +1643,7 @@ int bpf_get_kprobe_info(const struct perf_event *event, u32 *fd_type,
 	if (perf_type_tracepoint)
 		tk = find_trace_kprobe(pevent, group);
 	else
-		tk = event->tp_event->data;
+		tk = trace_kprobe_primary_from_call(event->tp_event);
 	if (!tk)
 		return -EINVAL;
 
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index b4909082f6a4..4d1893564912 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -20,7 +20,7 @@ DECLARE_RWSEM(trace_event_sem);
 
 static struct hlist_head event_hash[EVENT_HASHSIZE] __read_mostly;
 
-static int next_event_type = __TRACE_LAST_TYPE + 1;
+static int next_event_type = __TRACE_LAST_TYPE;
 
 enum print_line_t trace_print_bputs_msg_only(struct trace_iterator *iter)
 {
@@ -393,7 +393,7 @@ static int seq_print_user_ip(struct trace_seq *s, struct mm_struct *mm,
 	if (mm) {
 		const struct vm_area_struct *vma;
 
-		down_read(&mm->mmap_sem);
+		mmap_read_lock(mm);
 		vma = find_vma(mm, ip);
 		if (vma) {
 			file = vma->vm_file;
@@ -405,7 +405,7 @@ static int seq_print_user_ip(struct trace_seq *s, struct mm_struct *mm,
 				trace_seq_printf(s, "[+0x%lx]",
 						 ip - vmstart);
 		}
-		up_read(&mm->mmap_sem);
+		mmap_read_unlock(mm);
 	}
 	if (ret && ((sym_flags & TRACE_ITER_SYM_ADDR) || !file))
 		trace_seq_printf(s, " <" IP_FMT ">", ip);
@@ -617,22 +617,19 @@ int trace_print_context(struct trace_iterator *iter)
 
 int trace_print_lat_context(struct trace_iterator *iter)
 {
+	struct trace_entry *entry, *next_entry;
 	struct trace_array *tr = iter->tr;
-	/* trace_find_next_entry will reset ent_size */
-	int ent_size = iter->ent_size;
 	struct trace_seq *s = &iter->seq;
-	u64 next_ts;
-	struct trace_entry *entry = iter->ent,
-			   *next_entry = trace_find_next_entry(iter, NULL,
-							       &next_ts);
 	unsigned long verbose = (tr->trace_flags & TRACE_ITER_VERBOSE);
+	u64 next_ts;
 
-	/* Restore the original ent_size */
-	iter->ent_size = ent_size;
-
+	next_entry = trace_find_next_entry(iter, NULL, &next_ts);
 	if (!next_entry)
 		next_ts = iter->ts;
 
+	/* trace_find_next_entry() may change iter->ent */
+	entry = iter->ent;
+
 	if (verbose) {
 		char comm[TASK_COMM_LEN];
 
@@ -678,11 +675,11 @@ static LIST_HEAD(ftrace_event_list);
 static int trace_search_list(struct list_head **list)
 {
 	struct trace_event *e;
-	int last = __TRACE_LAST_TYPE;
+	int next = __TRACE_LAST_TYPE;
 
 	if (list_empty(&ftrace_event_list)) {
 		*list = &ftrace_event_list;
-		return last + 1;
+		return next;
 	}
 
 	/*
@@ -690,17 +687,17 @@ static int trace_search_list(struct list_head **list)
 	 * lets see if somebody freed one.
 	 */
 	list_for_each_entry(e, &ftrace_event_list, list) {
-		if (e->type != last + 1)
+		if (e->type != next)
 			break;
-		last++;
+		next++;
 	}
 
 	/* Did we used up all 65 thousand events??? */
-	if ((last + 1) > TRACE_EVENT_TYPE_MAX)
+	if (next > TRACE_EVENT_TYPE_MAX)
 		return 0;
 
 	*list = &e->list;
-	return last + 1;
+	return next;
 }
 
 void trace_event_read_lock(void)
@@ -1158,12 +1155,12 @@ trace_hwlat_print(struct trace_iterator *iter, int flags,
 
 	trace_assign_type(field, entry);
 
-	trace_seq_printf(s, "#%-5u inner/outer(us): %4llu/%-5llu ts:%lld.%09ld",
+	trace_seq_printf(s, "#%-5u inner/outer(us): %4llu/%-5llu ts:%lld.%09ld count:%d",
 			 field->seqnum,
 			 field->duration,
 			 field->outer_duration,
 			 (long long)field->timestamp.tv_sec,
-			 field->timestamp.tv_nsec);
+			 field->timestamp.tv_nsec, field->count);
 
 	if (field->nmi_count) {
 		/*
diff --git a/kernel/trace/trace_preemptirq.c b/kernel/trace/trace_preemptirq.c
index 4d8e99fdbbbe..f10073e62603 100644
--- a/kernel/trace/trace_preemptirq.c
+++ b/kernel/trace/trace_preemptirq.c
@@ -19,6 +19,24 @@
 /* Per-cpu variable to prevent redundant calls when IRQs already off */
 static DEFINE_PER_CPU(int, tracing_irq_cpu);
 
+/*
+ * Like trace_hardirqs_on() but without the lockdep invocation. This is
+ * used in the low level entry code where the ordering vs. RCU is important
+ * and lockdep uses a staged approach which splits the lockdep hardirq
+ * tracking into a RCU on and a RCU off section.
+ */
+void trace_hardirqs_on_prepare(void)
+{
+	if (this_cpu_read(tracing_irq_cpu)) {
+		if (!in_nmi())
+			trace_irq_enable(CALLER_ADDR0, CALLER_ADDR1);
+		tracer_hardirqs_on(CALLER_ADDR0, CALLER_ADDR1);
+		this_cpu_write(tracing_irq_cpu, 0);
+	}
+}
+EXPORT_SYMBOL(trace_hardirqs_on_prepare);
+NOKPROBE_SYMBOL(trace_hardirqs_on_prepare);
+
 void trace_hardirqs_on(void)
 {
 	if (this_cpu_read(tracing_irq_cpu)) {
@@ -28,21 +46,41 @@ void trace_hardirqs_on(void)
 		this_cpu_write(tracing_irq_cpu, 0);
 	}
 
+	lockdep_hardirqs_on_prepare(CALLER_ADDR0);
 	lockdep_hardirqs_on(CALLER_ADDR0);
 }
 EXPORT_SYMBOL(trace_hardirqs_on);
 NOKPROBE_SYMBOL(trace_hardirqs_on);
 
-void trace_hardirqs_off(void)
+/*
+ * Like trace_hardirqs_off() but without the lockdep invocation. This is
+ * used in the low level entry code where the ordering vs. RCU is important
+ * and lockdep uses a staged approach which splits the lockdep hardirq
+ * tracking into a RCU on and a RCU off section.
+ */
+void trace_hardirqs_off_finish(void)
 {
 	if (!this_cpu_read(tracing_irq_cpu)) {
 		this_cpu_write(tracing_irq_cpu, 1);
 		tracer_hardirqs_off(CALLER_ADDR0, CALLER_ADDR1);
 		if (!in_nmi())
-			trace_irq_disable_rcuidle(CALLER_ADDR0, CALLER_ADDR1);
+			trace_irq_disable(CALLER_ADDR0, CALLER_ADDR1);
 	}
 
+}
+EXPORT_SYMBOL(trace_hardirqs_off_finish);
+NOKPROBE_SYMBOL(trace_hardirqs_off_finish);
+
+void trace_hardirqs_off(void)
+{
 	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_ADDR1);
+		if (!in_nmi())
+			trace_irq_disable_rcuidle(CALLER_ADDR0, CALLER_ADDR1);
+	}
 }
 EXPORT_SYMBOL(trace_hardirqs_off);
 NOKPROBE_SYMBOL(trace_hardirqs_off);
@@ -56,6 +94,7 @@ __visible void trace_hardirqs_on_caller(unsigned long caller_addr)
 		this_cpu_write(tracing_irq_cpu, 0);
 	}
 
+	lockdep_hardirqs_on_prepare(CALLER_ADDR0);
 	lockdep_hardirqs_on(CALLER_ADDR0);
 }
 EXPORT_SYMBOL(trace_hardirqs_on_caller);
diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c
index ab8b6436d53f..d2867ccc6aca 100644
--- a/kernel/trace/trace_probe.c
+++ b/kernel/trace/trace_probe.c
@@ -639,8 +639,8 @@ static int traceprobe_parse_probe_arg_body(char *arg, ssize_t *size,
 			ret = -EINVAL;
 			goto fail;
 		}
-		if ((code->op == FETCH_OP_IMM || code->op == FETCH_OP_COMM) ||
-		     parg->count) {
+		if ((code->op == FETCH_OP_IMM || code->op == FETCH_OP_COMM ||
+		     code->op == FETCH_OP_DATA) || parg->count) {
 			/*
 			 * IMM, DATA and COMM is pointing actual address, those
 			 * must be kept, and if parg->count != 0, this is an
@@ -1006,7 +1006,7 @@ int trace_probe_init(struct trace_probe *tp, const char *event,
 	INIT_LIST_HEAD(&tp->event->class.fields);
 	INIT_LIST_HEAD(&tp->event->probes);
 	INIT_LIST_HEAD(&tp->list);
-	list_add(&tp->event->probes, &tp->list);
+	list_add(&tp->list, &tp->event->probes);
 
 	call = trace_probe_event_call(tp);
 	call->class = &tp->event->class;
diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h
index a0ff9e200ef6..a22b62813f8c 100644
--- a/kernel/trace/trace_probe.h
+++ b/kernel/trace/trace_probe.h
@@ -236,7 +236,7 @@ struct trace_probe_event {
 	struct trace_event_call		call;
 	struct list_head 		files;
 	struct list_head		probes;
-	struct trace_uprobe_filter	filter[0];
+	struct trace_uprobe_filter	filter[];
 };
 
 struct trace_probe {
diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
index c557f42a9397..98bba4764c52 100644
--- a/kernel/trace/trace_stack.c
+++ b/kernel/trace/trace_stack.c
@@ -515,9 +515,8 @@ static const struct file_operations stack_trace_filter_fops = {
 #endif /* CONFIG_DYNAMIC_FTRACE */
 
 int
-stack_trace_sysctl(struct ctl_table *table, int write,
-		   void __user *buffer, size_t *lenp,
-		   loff_t *ppos)
+stack_trace_sysctl(struct ctl_table *table, int write, void *buffer,
+		   size_t *lenp, loff_t *ppos)
 {
 	int was_enabled;
 	int ret;
diff --git a/kernel/trace/trace_synth.h b/kernel/trace/trace_synth.h
new file mode 100644
index 000000000000..ac35c45207c4
--- /dev/null
+++ b/kernel/trace/trace_synth.h
@@ -0,0 +1,36 @@
+// SPDX-License-Identifier: GPL-2.0
+#ifndef __TRACE_SYNTH_H
+#define __TRACE_SYNTH_H
+
+#include "trace_dynevent.h"
+
+#define SYNTH_SYSTEM		"synthetic"
+#define SYNTH_FIELDS_MAX	32
+
+#define STR_VAR_LEN_MAX		32 /* must be multiple of sizeof(u64) */
+
+struct synth_field {
+	char *type;
+	char *name;
+	size_t size;
+	unsigned int offset;
+	bool is_signed;
+	bool is_string;
+};
+
+struct synth_event {
+	struct dyn_event			devent;
+	int					ref;
+	char					*name;
+	struct synth_field			**fields;
+	unsigned int				n_fields;
+	unsigned int				n_u64;
+	struct trace_event_class		class;
+	struct trace_event_call			call;
+	struct tracepoint			*tp;
+	struct module				*mod;
+};
+
+extern struct synth_event *find_synth_event(const char *name);
+
+#endif /* __TRACE_SYNTH_H */
diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index 18d16f3ef980..f4286c9bdeb4 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -1333,8 +1333,15 @@ static void __uprobe_perf_func(struct trace_uprobe *tu,
 	int size, esize;
 	int rctx;
 
-	if (bpf_prog_array_valid(call) && !trace_call_bpf(call, regs))
-		return;
+	if (bpf_prog_array_valid(call)) {
+		u32 ret;
+
+		preempt_disable();
+		ret = trace_call_bpf(call, regs);
+		preempt_enable();
+		if (!ret)
+			return;
+	}
 
 	esize = SIZEOF_TRACE_ENTRY(is_ret_probe(tu));
 
@@ -1405,7 +1412,7 @@ int bpf_get_uprobe_info(const struct perf_event *event, u32 *fd_type,
 	if (perf_type_tracepoint)
 		tu = find_probe_event(pevent, group);
 	else
-		tu = event->tp_event->data;
+		tu = trace_uprobe_primary_from_call(event->tp_event);
 	if (!tu)
 		return -EINVAL;
 
@@ -1449,7 +1456,6 @@ trace_uprobe_register(struct trace_event_call *event, enum trace_reg type,
 	default:
 		return 0;
 	}
-	return 0;
 }
 
 static int uprobe_dispatcher(struct uprobe_consumer *con, struct pt_regs *regs)
diff --git a/kernel/trace/tracing_map.c b/kernel/trace/tracing_map.c
index 9e31bfc818ff..74738c9856f1 100644
--- a/kernel/trace/tracing_map.c
+++ b/kernel/trace/tracing_map.c
@@ -283,7 +283,7 @@ int tracing_map_add_key_field(struct tracing_map *map,
 	return idx;
 }
 
-void tracing_map_array_clear(struct tracing_map_array *a)
+static void tracing_map_array_clear(struct tracing_map_array *a)
 {
 	unsigned int i;
 
@@ -294,7 +294,7 @@ void tracing_map_array_clear(struct tracing_map_array *a)
 		memset(a->pages[i], 0, PAGE_SIZE);
 }
 
-void tracing_map_array_free(struct tracing_map_array *a)
+static void tracing_map_array_free(struct tracing_map_array *a)
 {
 	unsigned int i;
 
@@ -316,7 +316,7 @@ void tracing_map_array_free(struct tracing_map_array *a)
 	kfree(a);
 }
 
-struct tracing_map_array *tracing_map_array_alloc(unsigned int n_elts,
+static struct tracing_map_array *tracing_map_array_alloc(unsigned int n_elts,
 						  unsigned int entry_size)
 {
 	struct tracing_map_array *a;
diff --git a/kernel/ucount.c b/kernel/ucount.c
index a53cc2b4179c..11b1596e2542 100644
--- a/kernel/ucount.c
+++ b/kernel/ucount.c
@@ -69,6 +69,7 @@ static struct ctl_table user_table[] = {
 	UCOUNT_ENTRY("max_net_namespaces"),
 	UCOUNT_ENTRY("max_mnt_namespaces"),
 	UCOUNT_ENTRY("max_cgroup_namespaces"),
+	UCOUNT_ENTRY("max_time_namespaces"),
 #ifdef CONFIG_INOTIFY_USER
 	UCOUNT_ENTRY("max_inotify_instances"),
 	UCOUNT_ENTRY("max_inotify_watches"),
@@ -81,6 +82,8 @@ bool setup_userns_sysctls(struct user_namespace *ns)
 {
 #ifdef CONFIG_SYSCTL
 	struct ctl_table *tbl;
+
+	BUILD_BUG_ON(ARRAY_SIZE(user_table) != UCOUNT_COUNTS + 1);
 	setup_sysctl_set(&ns->set, &set_root, set_is_seen);
 	tbl = kmemdup(user_table, sizeof(user_table), GFP_KERNEL);
 	if (tbl) {
diff --git a/kernel/umh.c b/kernel/umh.c
index 7f255b5a8845..fcf3ee803630 100644
--- a/kernel/umh.c
+++ b/kernel/umh.c
@@ -26,8 +26,6 @@
 #include <linux/ptrace.h>
 #include <linux/async.h>
 #include <linux/uaccess.h>
-#include <linux/shmem_fs.h>
-#include <linux/pipe_fs_i.h>
 
 #include <trace/events/module.h>
 
@@ -38,8 +36,6 @@ static kernel_cap_t usermodehelper_bset = CAP_FULL_SET;
 static kernel_cap_t usermodehelper_inheritable = CAP_FULL_SET;
 static DEFINE_SPINLOCK(umh_sysctl_lock);
 static DECLARE_RWSEM(umhelper_sem);
-static LIST_HEAD(umh_list);
-static DEFINE_MUTEX(umh_list_lock);
 
 static void call_usermodehelper_freeinfo(struct subprocess_info *info)
 {
@@ -102,16 +98,9 @@ static int call_usermodehelper_exec_async(void *data)
 
 	commit_creds(new);
 
-	sub_info->pid = task_pid_nr(current);
-	if (sub_info->file) {
-		retval = do_execve_file(sub_info->file,
-					sub_info->argv, sub_info->envp);
-		if (!retval)
-			current->flags |= PF_UMH;
-	} else
-		retval = do_execve(getname_kernel(sub_info->path),
-				   (const char __user *const __user *)sub_info->argv,
-				   (const char __user *const __user *)sub_info->envp);
+	retval = kernel_execve(sub_info->path,
+			       (const char *const *)sub_info->argv,
+			       (const char *const *)sub_info->envp);
 out:
 	sub_info->retval = retval;
 	/*
@@ -130,37 +119,16 @@ static void call_usermodehelper_exec_sync(struct subprocess_info *sub_info)
 {
 	pid_t pid;
 
-	/* If SIGCLD is ignored kernel_wait4 won't populate the status. */
+	/* If SIGCLD is ignored do_wait won't populate the status. */
 	kernel_sigaction(SIGCHLD, SIG_DFL);
 	pid = kernel_thread(call_usermodehelper_exec_async, sub_info, SIGCHLD);
-	if (pid < 0) {
+	if (pid < 0)
 		sub_info->retval = pid;
-	} else {
-		int ret = -ECHILD;
-		/*
-		 * Normally it is bogus to call wait4() from in-kernel because
-		 * wait4() wants to write the exit code to a userspace address.
-		 * But call_usermodehelper_exec_sync() always runs as kernel
-		 * thread (workqueue) and put_user() to a kernel address works
-		 * OK for kernel threads, due to their having an mm_segment_t
-		 * which spans the entire address space.
-		 *
-		 * Thus the __user pointer cast is valid here.
-		 */
-		kernel_wait4(pid, (int __user *)&ret, 0, NULL);
-
-		/*
-		 * If ret is 0, either call_usermodehelper_exec_async failed and
-		 * the real error code is already in sub_info->retval or
-		 * sub_info->retval is 0 anyway, so don't mess with it then.
-		 */
-		if (ret)
-			sub_info->retval = ret;
-	}
+	else
+		kernel_wait(pid, &sub_info->retval);
 
 	/* Restore default kernel sig handler */
 	kernel_sigaction(SIGCHLD, SIG_IGN);
-
 	umh_complete(sub_info);
 }
 
@@ -405,134 +373,6 @@ struct subprocess_info *call_usermodehelper_setup(const char *path, char **argv,
 }
 EXPORT_SYMBOL(call_usermodehelper_setup);
 
-struct subprocess_info *call_usermodehelper_setup_file(struct file *file,
-		int (*init)(struct subprocess_info *info, struct cred *new),
-		void (*cleanup)(struct subprocess_info *info), void *data)
-{
-	struct subprocess_info *sub_info;
-	struct umh_info *info = data;
-	const char *cmdline = (info->cmdline) ? info->cmdline : "usermodehelper";
-
-	sub_info = kzalloc(sizeof(struct subprocess_info), GFP_KERNEL);
-	if (!sub_info)
-		return NULL;
-
-	sub_info->argv = argv_split(GFP_KERNEL, cmdline, NULL);
-	if (!sub_info->argv) {
-		kfree(sub_info);
-		return NULL;
-	}
-
-	INIT_WORK(&sub_info->work, call_usermodehelper_exec_work);
-	sub_info->path = "none";
-	sub_info->file = file;
-	sub_info->init = init;
-	sub_info->cleanup = cleanup;
-	sub_info->data = data;
-	return sub_info;
-}
-
-static int umh_pipe_setup(struct subprocess_info *info, struct cred *new)
-{
-	struct umh_info *umh_info = info->data;
-	struct file *from_umh[2];
-	struct file *to_umh[2];
-	int err;
-
-	/* create pipe to send data to umh */
-	err = create_pipe_files(to_umh, 0);
-	if (err)
-		return err;
-	err = replace_fd(0, to_umh[0], 0);
-	fput(to_umh[0]);
-	if (err < 0) {
-		fput(to_umh[1]);
-		return err;
-	}
-
-	/* create pipe to receive data from umh */
-	err = create_pipe_files(from_umh, 0);
-	if (err) {
-		fput(to_umh[1]);
-		replace_fd(0, NULL, 0);
-		return err;
-	}
-	err = replace_fd(1, from_umh[1], 0);
-	fput(from_umh[1]);
-	if (err < 0) {
-		fput(to_umh[1]);
-		replace_fd(0, NULL, 0);
-		fput(from_umh[0]);
-		return err;
-	}
-
-	umh_info->pipe_to_umh = to_umh[1];
-	umh_info->pipe_from_umh = from_umh[0];
-	return 0;
-}
-
-static void umh_clean_and_save_pid(struct subprocess_info *info)
-{
-	struct umh_info *umh_info = info->data;
-
-	argv_free(info->argv);
-	umh_info->pid = info->pid;
-}
-
-/**
- * fork_usermode_blob - fork a blob of bytes as a usermode process
- * @data: a blob of bytes that can be do_execv-ed as a file
- * @len: length of the blob
- * @info: information about usermode process (shouldn't be NULL)
- *
- * If info->cmdline is set it will be used as command line for the
- * user process, else "usermodehelper" is used.
- *
- * Returns either negative error or zero which indicates success
- * in executing a blob of bytes as a usermode process. In such
- * case 'struct umh_info *info' is populated with two pipes
- * and a pid of the process. The caller is responsible for health
- * check of the user process, killing it via pid, and closing the
- * pipes when user process is no longer needed.
- */
-int fork_usermode_blob(void *data, size_t len, struct umh_info *info)
-{
-	struct subprocess_info *sub_info;
-	struct file *file;
-	ssize_t written;
-	loff_t pos = 0;
-	int err;
-
-	file = shmem_kernel_file_setup("", len, 0);
-	if (IS_ERR(file))
-		return PTR_ERR(file);
-
-	written = kernel_write(file, data, len, &pos);
-	if (written != len) {
-		err = written;
-		if (err >= 0)
-			err = -ENOMEM;
-		goto out;
-	}
-
-	err = -ENOMEM;
-	sub_info = call_usermodehelper_setup_file(file, umh_pipe_setup,
-						  umh_clean_and_save_pid, info);
-	if (!sub_info)
-		goto out;
-
-	err = call_usermodehelper_exec(sub_info, UMH_WAIT_EXEC);
-	if (!err) {
-		mutex_lock(&umh_list_lock);
-		list_add(&info->list, &umh_list);
-		mutex_unlock(&umh_list_lock);
-	}
-out:
-	fput(file);
-	return err;
-}
-EXPORT_SYMBOL_GPL(fork_usermode_blob);
-
 /**
  * call_usermodehelper_exec - start a usermode application
  * @sub_info: information about the subprocessa
@@ -544,6 +384,11 @@ EXPORT_SYMBOL_GPL(fork_usermode_blob);
  * Runs a user-space application.  The application is started
  * asynchronously if wait is not set, and runs as a child of system workqueues.
  * (ie. it runs with full root capabilities and optimized affinity).
+ *
+ * Note: successful return value does not guarantee the helper was called at
+ * all. You can't rely on sub_info->{init,cleanup} being called even for
+ * UMH_WAIT_* wait modes as STATIC_USERMODEHELPER_PATH="" turns all helpers
+ * into a successful no-op.
  */
 int call_usermodehelper_exec(struct subprocess_info *sub_info, int wait)
 {
@@ -630,7 +475,7 @@ int call_usermodehelper(const char *path, char **argv, char **envp, int wait)
 EXPORT_SYMBOL(call_usermodehelper);
 
 static int proc_cap_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 ctl_table t;
 	unsigned long cap_array[_KERNEL_CAPABILITY_U32S];
@@ -689,26 +534,6 @@ static int proc_cap_handler(struct ctl_table *table, int write,
 	return 0;
 }
 
-void __exit_umh(struct task_struct *tsk)
-{
-	struct umh_info *info;
-	pid_t pid = tsk->pid;
-
-	mutex_lock(&umh_list_lock);
-	list_for_each_entry(info, &umh_list, list) {
-		if (info->pid == pid) {
-			list_del(&info->list);
-			mutex_unlock(&umh_list_lock);
-			goto out;
-		}
-	}
-	mutex_unlock(&umh_list_lock);
-	return;
-out:
-	if (info->cleanup)
-		info->cleanup(info);
-}
-
 struct ctl_table usermodehelper_table[] = {
 	{
 		.procname	= "bset",
diff --git a/kernel/user.c b/kernel/user.c
index 5235d7f49982..b1635d94a1f2 100644
--- a/kernel/user.c
+++ b/kernel/user.c
@@ -82,7 +82,7 @@ EXPORT_SYMBOL_GPL(init_user_ns);
 #define uidhashentry(uid)	(uidhash_table + __uidhashfn((__kuid_val(uid))))
 
 static struct kmem_cache *uid_cachep;
-struct hlist_head uidhash_table[UIDHASH_SZ];
+static struct hlist_head uidhash_table[UIDHASH_SZ];
 
 /*
  * The uidhash_lock is mostly taken from process context, but it is
diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c
index 8eadadc478f9..87804e0371fe 100644
--- a/kernel/user_namespace.c
+++ b/kernel/user_namespace.c
@@ -1253,7 +1253,7 @@ static void userns_put(struct ns_common *ns)
 	put_user_ns(to_user_ns(ns));
 }
 
-static int userns_install(struct nsproxy *nsproxy, struct ns_common *ns)
+static int userns_install(struct nsset *nsset, struct ns_common *ns)
 {
 	struct user_namespace *user_ns = to_user_ns(ns);
 	struct cred *cred;
@@ -1274,14 +1274,14 @@ static int userns_install(struct nsproxy *nsproxy, struct ns_common *ns)
 	if (!ns_capable(user_ns, CAP_SYS_ADMIN))
 		return -EPERM;
 
-	cred = prepare_creds();
+	cred = nsset_cred(nsset);
 	if (!cred)
-		return -ENOMEM;
+		return -EINVAL;
 
 	put_user_ns(cred->user_ns);
 	set_cred_user_ns(cred, get_user_ns(user_ns));
 
-	return commit_creds(cred);
+	return 0;
 }
 
 struct ns_common *ns_get_owner(struct ns_common *ns)
diff --git a/kernel/usermode_driver.c b/kernel/usermode_driver.c
new file mode 100644
index 000000000000..0b35212ffc3d
--- /dev/null
+++ b/kernel/usermode_driver.c
@@ -0,0 +1,182 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * umd - User mode driver support
+ */
+#include <linux/shmem_fs.h>
+#include <linux/pipe_fs_i.h>
+#include <linux/mount.h>
+#include <linux/fs_struct.h>
+#include <linux/task_work.h>
+#include <linux/usermode_driver.h>
+
+static struct vfsmount *blob_to_mnt(const void *data, size_t len, const char *name)
+{
+	struct file_system_type *type;
+	struct vfsmount *mnt;
+	struct file *file;
+	ssize_t written;
+	loff_t pos = 0;
+
+	type = get_fs_type("tmpfs");
+	if (!type)
+		return ERR_PTR(-ENODEV);
+
+	mnt = kern_mount(type);
+	put_filesystem(type);
+	if (IS_ERR(mnt))
+		return mnt;
+
+	file = file_open_root(mnt->mnt_root, mnt, name, O_CREAT | O_WRONLY, 0700);
+	if (IS_ERR(file)) {
+		mntput(mnt);
+		return ERR_CAST(file);
+	}
+
+	written = kernel_write(file, data, len, &pos);
+	if (written != len) {
+		int err = written;
+		if (err >= 0)
+			err = -ENOMEM;
+		filp_close(file, NULL);
+		mntput(mnt);
+		return ERR_PTR(err);
+	}
+
+	fput(file);
+
+	/* Flush delayed fput so exec can open the file read-only */
+	flush_delayed_fput();
+	task_work_run();
+	return mnt;
+}
+
+/**
+ * umd_load_blob - Remember a blob of bytes for fork_usermode_driver
+ * @info: information about usermode driver
+ * @data: a blob of bytes that can be executed as a file
+ * @len:  The lentgh of the blob
+ *
+ */
+int umd_load_blob(struct umd_info *info, const void *data, size_t len)
+{
+	struct vfsmount *mnt;
+
+	if (WARN_ON_ONCE(info->wd.dentry || info->wd.mnt))
+		return -EBUSY;
+
+	mnt = blob_to_mnt(data, len, info->driver_name);
+	if (IS_ERR(mnt))
+		return PTR_ERR(mnt);
+
+	info->wd.mnt = mnt;
+	info->wd.dentry = mnt->mnt_root;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(umd_load_blob);
+
+/**
+ * umd_unload_blob - Disassociate @info from a previously loaded blob
+ * @info: information about usermode driver
+ *
+ */
+int umd_unload_blob(struct umd_info *info)
+{
+	if (WARN_ON_ONCE(!info->wd.mnt ||
+			 !info->wd.dentry ||
+			 info->wd.mnt->mnt_root != info->wd.dentry))
+		return -EINVAL;
+
+	kern_unmount(info->wd.mnt);
+	info->wd.mnt = NULL;
+	info->wd.dentry = NULL;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(umd_unload_blob);
+
+static int umd_setup(struct subprocess_info *info, struct cred *new)
+{
+	struct umd_info *umd_info = info->data;
+	struct file *from_umh[2];
+	struct file *to_umh[2];
+	int err;
+
+	/* create pipe to send data to umh */
+	err = create_pipe_files(to_umh, 0);
+	if (err)
+		return err;
+	err = replace_fd(0, to_umh[0], 0);
+	fput(to_umh[0]);
+	if (err < 0) {
+		fput(to_umh[1]);
+		return err;
+	}
+
+	/* create pipe to receive data from umh */
+	err = create_pipe_files(from_umh, 0);
+	if (err) {
+		fput(to_umh[1]);
+		replace_fd(0, NULL, 0);
+		return err;
+	}
+	err = replace_fd(1, from_umh[1], 0);
+	fput(from_umh[1]);
+	if (err < 0) {
+		fput(to_umh[1]);
+		replace_fd(0, NULL, 0);
+		fput(from_umh[0]);
+		return err;
+	}
+
+	set_fs_pwd(current->fs, &umd_info->wd);
+	umd_info->pipe_to_umh = to_umh[1];
+	umd_info->pipe_from_umh = from_umh[0];
+	umd_info->tgid = get_pid(task_tgid(current));
+	return 0;
+}
+
+static void umd_cleanup(struct subprocess_info *info)
+{
+	struct umd_info *umd_info = info->data;
+
+	/* cleanup if umh_setup() was successful but exec failed */
+	if (info->retval) {
+		fput(umd_info->pipe_to_umh);
+		fput(umd_info->pipe_from_umh);
+		put_pid(umd_info->tgid);
+		umd_info->tgid = NULL;
+	}
+}
+
+/**
+ * fork_usermode_driver - fork a usermode driver
+ * @info: information about usermode driver (shouldn't be NULL)
+ *
+ * Returns either negative error or zero which indicates success in
+ * executing a usermode driver. In such case 'struct umd_info *info'
+ * is populated with two pipes and a tgid of the process. The caller is
+ * responsible for health check of the user process, killing it via
+ * tgid, and closing the pipes when user process is no longer needed.
+ */
+int fork_usermode_driver(struct umd_info *info)
+{
+	struct subprocess_info *sub_info;
+	const char *argv[] = { info->driver_name, NULL };
+	int err;
+
+	if (WARN_ON_ONCE(info->tgid))
+		return -EBUSY;
+
+	err = -ENOMEM;
+	sub_info = call_usermodehelper_setup(info->driver_name,
+					     (char **)argv, NULL, GFP_KERNEL,
+					     umd_setup, umd_cleanup, info);
+	if (!sub_info)
+		goto out;
+
+	err = call_usermodehelper_exec(sub_info, UMH_WAIT_EXEC);
+out:
+	return err;
+}
+EXPORT_SYMBOL_GPL(fork_usermode_driver);
+
+
diff --git a/kernel/utsname.c b/kernel/utsname.c
index f0e491193009..e488d0e2ab45 100644
--- a/kernel/utsname.c
+++ b/kernel/utsname.c
@@ -140,12 +140,13 @@ static void utsns_put(struct ns_common *ns)
 	put_uts_ns(to_uts_ns(ns));
 }
 
-static int utsns_install(struct nsproxy *nsproxy, struct ns_common *new)
+static int utsns_install(struct nsset *nsset, struct ns_common *new)
 {
+	struct nsproxy *nsproxy = nsset->nsproxy;
 	struct uts_namespace *ns = to_uts_ns(new);
 
 	if (!ns_capable(ns->user_ns, CAP_SYS_ADMIN) ||
-	    !ns_capable(current_user_ns(), CAP_SYS_ADMIN))
+	    !ns_capable(nsset->cred->user_ns, CAP_SYS_ADMIN))
 		return -EPERM;
 
 	get_uts_ns(ns);
diff --git a/kernel/utsname_sysctl.c b/kernel/utsname_sysctl.c
index 3732c888a949..4ca61d49885b 100644
--- a/kernel/utsname_sysctl.c
+++ b/kernel/utsname_sysctl.c
@@ -30,7 +30,7 @@ static void *get_uts(struct ctl_table *table)
  *	to observe. Should this be in kernel/sys.c ????
  */
 static int proc_do_uts_string(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 uts_table;
 	int r;
diff --git a/kernel/watch_queue.c b/kernel/watch_queue.c
new file mode 100644
index 000000000000..0ef8f65bd2d7
--- /dev/null
+++ b/kernel/watch_queue.c
@@ -0,0 +1,663 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Watch queue and general notification mechanism, built on pipes
+ *
+ * Copyright (C) 2020 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * See Documentation/watch_queue.rst
+ */
+
+#define pr_fmt(fmt) "watchq: " fmt
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/printk.h>
+#include <linux/miscdevice.h>
+#include <linux/fs.h>
+#include <linux/mm.h>
+#include <linux/pagemap.h>
+#include <linux/poll.h>
+#include <linux/uaccess.h>
+#include <linux/vmalloc.h>
+#include <linux/file.h>
+#include <linux/security.h>
+#include <linux/cred.h>
+#include <linux/sched/signal.h>
+#include <linux/watch_queue.h>
+#include <linux/pipe_fs_i.h>
+
+MODULE_DESCRIPTION("Watch queue");
+MODULE_AUTHOR("Red Hat, Inc.");
+MODULE_LICENSE("GPL");
+
+#define WATCH_QUEUE_NOTE_SIZE 128
+#define WATCH_QUEUE_NOTES_PER_PAGE (PAGE_SIZE / WATCH_QUEUE_NOTE_SIZE)
+
+static void watch_queue_pipe_buf_release(struct pipe_inode_info *pipe,
+					 struct pipe_buffer *buf)
+{
+	struct watch_queue *wqueue = (struct watch_queue *)buf->private;
+	struct page *page;
+	unsigned int bit;
+
+	/* We need to work out which note within the page this refers to, but
+	 * the note might have been maximum size, so merely ANDing the offset
+	 * off doesn't work.  OTOH, the note must've been more than zero size.
+	 */
+	bit = buf->offset + buf->len;
+	if ((bit & (WATCH_QUEUE_NOTE_SIZE - 1)) == 0)
+		bit -= WATCH_QUEUE_NOTE_SIZE;
+	bit /= WATCH_QUEUE_NOTE_SIZE;
+
+	page = buf->page;
+	bit += page->index;
+
+	set_bit(bit, wqueue->notes_bitmap);
+}
+
+// No try_steal function => no stealing
+#define watch_queue_pipe_buf_try_steal NULL
+
+/* New data written to a pipe may be appended to a buffer with this type. */
+static const struct pipe_buf_operations watch_queue_pipe_buf_ops = {
+	.release	= watch_queue_pipe_buf_release,
+	.try_steal	= watch_queue_pipe_buf_try_steal,
+	.get		= generic_pipe_buf_get,
+};
+
+/*
+ * Post a notification to a watch queue.
+ */
+static bool post_one_notification(struct watch_queue *wqueue,
+				  struct watch_notification *n)
+{
+	void *p;
+	struct pipe_inode_info *pipe = wqueue->pipe;
+	struct pipe_buffer *buf;
+	struct page *page;
+	unsigned int head, tail, mask, note, offset, len;
+	bool done = false;
+
+	if (!pipe)
+		return false;
+
+	spin_lock_irq(&pipe->rd_wait.lock);
+
+	if (wqueue->defunct)
+		goto out;
+
+	mask = pipe->ring_size - 1;
+	head = pipe->head;
+	tail = pipe->tail;
+	if (pipe_full(head, tail, pipe->ring_size))
+		goto lost;
+
+	note = find_first_bit(wqueue->notes_bitmap, wqueue->nr_notes);
+	if (note >= wqueue->nr_notes)
+		goto lost;
+
+	page = wqueue->notes[note / WATCH_QUEUE_NOTES_PER_PAGE];
+	offset = note % WATCH_QUEUE_NOTES_PER_PAGE * WATCH_QUEUE_NOTE_SIZE;
+	get_page(page);
+	len = n->info & WATCH_INFO_LENGTH;
+	p = kmap_atomic(page);
+	memcpy(p + offset, n, len);
+	kunmap_atomic(p);
+
+	buf = &pipe->bufs[head & mask];
+	buf->page = page;
+	buf->private = (unsigned long)wqueue;
+	buf->ops = &watch_queue_pipe_buf_ops;
+	buf->offset = offset;
+	buf->len = len;
+	buf->flags = PIPE_BUF_FLAG_WHOLE;
+	pipe->head = head + 1;
+
+	if (!test_and_clear_bit(note, wqueue->notes_bitmap)) {
+		spin_unlock_irq(&pipe->rd_wait.lock);
+		BUG();
+	}
+	wake_up_interruptible_sync_poll_locked(&pipe->rd_wait, EPOLLIN | EPOLLRDNORM);
+	done = true;
+
+out:
+	spin_unlock_irq(&pipe->rd_wait.lock);
+	if (done)
+		kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN);
+	return done;
+
+lost:
+	buf = &pipe->bufs[(head - 1) & mask];
+	buf->flags |= PIPE_BUF_FLAG_LOSS;
+	goto out;
+}
+
+/*
+ * Apply filter rules to a notification.
+ */
+static bool filter_watch_notification(const struct watch_filter *wf,
+				      const struct watch_notification *n)
+{
+	const struct watch_type_filter *wt;
+	unsigned int st_bits = sizeof(wt->subtype_filter[0]) * 8;
+	unsigned int st_index = n->subtype / st_bits;
+	unsigned int st_bit = 1U << (n->subtype % st_bits);
+	int i;
+
+	if (!test_bit(n->type, wf->type_filter))
+		return false;
+
+	for (i = 0; i < wf->nr_filters; i++) {
+		wt = &wf->filters[i];
+		if (n->type == wt->type &&
+		    (wt->subtype_filter[st_index] & st_bit) &&
+		    (n->info & wt->info_mask) == wt->info_filter)
+			return true;
+	}
+
+	return false; /* If there is a filter, the default is to reject. */
+}
+
+/**
+ * __post_watch_notification - Post an event notification
+ * @wlist: The watch list to post the event to.
+ * @n: The notification record to post.
+ * @cred: The creds of the process that triggered the notification.
+ * @id: The ID to match on the watch.
+ *
+ * Post a notification of an event into a set of watch queues and let the users
+ * know.
+ *
+ * The size of the notification should be set in n->info & WATCH_INFO_LENGTH and
+ * should be in units of sizeof(*n).
+ */
+void __post_watch_notification(struct watch_list *wlist,
+			       struct watch_notification *n,
+			       const struct cred *cred,
+			       u64 id)
+{
+	const struct watch_filter *wf;
+	struct watch_queue *wqueue;
+	struct watch *watch;
+
+	if (((n->info & WATCH_INFO_LENGTH) >> WATCH_INFO_LENGTH__SHIFT) == 0) {
+		WARN_ON(1);
+		return;
+	}
+
+	rcu_read_lock();
+
+	hlist_for_each_entry_rcu(watch, &wlist->watchers, list_node) {
+		if (watch->id != id)
+			continue;
+		n->info &= ~WATCH_INFO_ID;
+		n->info |= watch->info_id;
+
+		wqueue = rcu_dereference(watch->queue);
+		wf = rcu_dereference(wqueue->filter);
+		if (wf && !filter_watch_notification(wf, n))
+			continue;
+
+		if (security_post_notification(watch->cred, cred, n) < 0)
+			continue;
+
+		post_one_notification(wqueue, n);
+	}
+
+	rcu_read_unlock();
+}
+EXPORT_SYMBOL(__post_watch_notification);
+
+/*
+ * Allocate sufficient pages to preallocation for the requested number of
+ * notifications.
+ */
+long watch_queue_set_size(struct pipe_inode_info *pipe, unsigned int nr_notes)
+{
+	struct watch_queue *wqueue = pipe->watch_queue;
+	struct page **pages;
+	unsigned long *bitmap;
+	unsigned long user_bufs;
+	unsigned int bmsize;
+	int ret, i, nr_pages;
+
+	if (!wqueue)
+		return -ENODEV;
+	if (wqueue->notes)
+		return -EBUSY;
+
+	if (nr_notes < 1 ||
+	    nr_notes > 512) /* TODO: choose a better hard limit */
+		return -EINVAL;
+
+	nr_pages = (nr_notes + WATCH_QUEUE_NOTES_PER_PAGE - 1);
+	nr_pages /= WATCH_QUEUE_NOTES_PER_PAGE;
+	user_bufs = account_pipe_buffers(pipe->user, pipe->nr_accounted, nr_pages);
+
+	if (nr_pages > pipe->max_usage &&
+	    (too_many_pipe_buffers_hard(user_bufs) ||
+	     too_many_pipe_buffers_soft(user_bufs)) &&
+	    pipe_is_unprivileged_user()) {
+		ret = -EPERM;
+		goto error;
+	}
+
+	ret = pipe_resize_ring(pipe, nr_notes);
+	if (ret < 0)
+		goto error;
+
+	pages = kcalloc(sizeof(struct page *), nr_pages, GFP_KERNEL);
+	if (!pages)
+		goto error;
+
+	for (i = 0; i < nr_pages; i++) {
+		pages[i] = alloc_page(GFP_KERNEL);
+		if (!pages[i])
+			goto error_p;
+		pages[i]->index = i * WATCH_QUEUE_NOTES_PER_PAGE;
+	}
+
+	bmsize = (nr_notes + BITS_PER_LONG - 1) / BITS_PER_LONG;
+	bmsize *= sizeof(unsigned long);
+	bitmap = kmalloc(bmsize, GFP_KERNEL);
+	if (!bitmap)
+		goto error_p;
+
+	memset(bitmap, 0xff, bmsize);
+	wqueue->notes = pages;
+	wqueue->notes_bitmap = bitmap;
+	wqueue->nr_pages = nr_pages;
+	wqueue->nr_notes = nr_pages * WATCH_QUEUE_NOTES_PER_PAGE;
+	return 0;
+
+error_p:
+	for (i = 0; i < nr_pages; i++)
+		__free_page(pages[i]);
+	kfree(pages);
+error:
+	(void) account_pipe_buffers(pipe->user, nr_pages, pipe->nr_accounted);
+	return ret;
+}
+
+/*
+ * Set the filter on a watch queue.
+ */
+long watch_queue_set_filter(struct pipe_inode_info *pipe,
+			    struct watch_notification_filter __user *_filter)
+{
+	struct watch_notification_type_filter *tf;
+	struct watch_notification_filter filter;
+	struct watch_type_filter *q;
+	struct watch_filter *wfilter;
+	struct watch_queue *wqueue = pipe->watch_queue;
+	int ret, nr_filter = 0, i;
+
+	if (!wqueue)
+		return -ENODEV;
+
+	if (!_filter) {
+		/* Remove the old filter */
+		wfilter = NULL;
+		goto set;
+	}
+
+	/* Grab the user's filter specification */
+	if (copy_from_user(&filter, _filter, sizeof(filter)) != 0)
+		return -EFAULT;
+	if (filter.nr_filters == 0 ||
+	    filter.nr_filters > 16 ||
+	    filter.__reserved != 0)
+		return -EINVAL;
+
+	tf = memdup_user(_filter->filters, filter.nr_filters * sizeof(*tf));
+	if (IS_ERR(tf))
+		return PTR_ERR(tf);
+
+	ret = -EINVAL;
+	for (i = 0; i < filter.nr_filters; i++) {
+		if ((tf[i].info_filter & ~tf[i].info_mask) ||
+		    tf[i].info_mask & WATCH_INFO_LENGTH)
+			goto err_filter;
+		/* Ignore any unknown types */
+		if (tf[i].type >= sizeof(wfilter->type_filter) * 8)
+			continue;
+		nr_filter++;
+	}
+
+	/* Now we need to build the internal filter from only the relevant
+	 * user-specified filters.
+	 */
+	ret = -ENOMEM;
+	wfilter = kzalloc(struct_size(wfilter, filters, nr_filter), GFP_KERNEL);
+	if (!wfilter)
+		goto err_filter;
+	wfilter->nr_filters = nr_filter;
+
+	q = wfilter->filters;
+	for (i = 0; i < filter.nr_filters; i++) {
+		if (tf[i].type >= sizeof(wfilter->type_filter) * BITS_PER_LONG)
+			continue;
+
+		q->type			= tf[i].type;
+		q->info_filter		= tf[i].info_filter;
+		q->info_mask		= tf[i].info_mask;
+		q->subtype_filter[0]	= tf[i].subtype_filter[0];
+		__set_bit(q->type, wfilter->type_filter);
+		q++;
+	}
+
+	kfree(tf);
+set:
+	pipe_lock(pipe);
+	wfilter = rcu_replace_pointer(wqueue->filter, wfilter,
+				      lockdep_is_held(&pipe->mutex));
+	pipe_unlock(pipe);
+	if (wfilter)
+		kfree_rcu(wfilter, rcu);
+	return 0;
+
+err_filter:
+	kfree(tf);
+	return ret;
+}
+
+static void __put_watch_queue(struct kref *kref)
+{
+	struct watch_queue *wqueue =
+		container_of(kref, struct watch_queue, usage);
+	struct watch_filter *wfilter;
+	int i;
+
+	for (i = 0; i < wqueue->nr_pages; i++)
+		__free_page(wqueue->notes[i]);
+
+	wfilter = rcu_access_pointer(wqueue->filter);
+	if (wfilter)
+		kfree_rcu(wfilter, rcu);
+	kfree_rcu(wqueue, rcu);
+}
+
+/**
+ * put_watch_queue - Dispose of a ref on a watchqueue.
+ * @wqueue: The watch queue to unref.
+ */
+void put_watch_queue(struct watch_queue *wqueue)
+{
+	kref_put(&wqueue->usage, __put_watch_queue);
+}
+EXPORT_SYMBOL(put_watch_queue);
+
+static void free_watch(struct rcu_head *rcu)
+{
+	struct watch *watch = container_of(rcu, struct watch, rcu);
+
+	put_watch_queue(rcu_access_pointer(watch->queue));
+	atomic_dec(&watch->cred->user->nr_watches);
+	put_cred(watch->cred);
+}
+
+static void __put_watch(struct kref *kref)
+{
+	struct watch *watch = container_of(kref, struct watch, usage);
+
+	call_rcu(&watch->rcu, free_watch);
+}
+
+/*
+ * Discard a watch.
+ */
+static void put_watch(struct watch *watch)
+{
+	kref_put(&watch->usage, __put_watch);
+}
+
+/**
+ * init_watch_queue - Initialise a watch
+ * @watch: The watch to initialise.
+ * @wqueue: The queue to assign.
+ *
+ * Initialise a watch and set the watch queue.
+ */
+void init_watch(struct watch *watch, struct watch_queue *wqueue)
+{
+	kref_init(&watch->usage);
+	INIT_HLIST_NODE(&watch->list_node);
+	INIT_HLIST_NODE(&watch->queue_node);
+	rcu_assign_pointer(watch->queue, wqueue);
+}
+
+/**
+ * add_watch_to_object - Add a watch on an object to a watch list
+ * @watch: The watch to add
+ * @wlist: The watch list to add to
+ *
+ * @watch->queue must have been set to point to the queue to post notifications
+ * to and the watch list of the object to be watched.  @watch->cred must also
+ * have been set to the appropriate credentials and a ref taken on them.
+ *
+ * The caller must pin the queue and the list both and must hold the list
+ * locked against racing watch additions/removals.
+ */
+int add_watch_to_object(struct watch *watch, struct watch_list *wlist)
+{
+	struct watch_queue *wqueue = rcu_access_pointer(watch->queue);
+	struct watch *w;
+
+	hlist_for_each_entry(w, &wlist->watchers, list_node) {
+		struct watch_queue *wq = rcu_access_pointer(w->queue);
+		if (wqueue == wq && watch->id == w->id)
+			return -EBUSY;
+	}
+
+	watch->cred = get_current_cred();
+	rcu_assign_pointer(watch->watch_list, wlist);
+
+	if (atomic_inc_return(&watch->cred->user->nr_watches) >
+	    task_rlimit(current, RLIMIT_NOFILE)) {
+		atomic_dec(&watch->cred->user->nr_watches);
+		put_cred(watch->cred);
+		return -EAGAIN;
+	}
+
+	spin_lock_bh(&wqueue->lock);
+	kref_get(&wqueue->usage);
+	kref_get(&watch->usage);
+	hlist_add_head(&watch->queue_node, &wqueue->watches);
+	spin_unlock_bh(&wqueue->lock);
+
+	hlist_add_head(&watch->list_node, &wlist->watchers);
+	return 0;
+}
+EXPORT_SYMBOL(add_watch_to_object);
+
+/**
+ * remove_watch_from_object - Remove a watch or all watches from an object.
+ * @wlist: The watch list to remove from
+ * @wq: The watch queue of interest (ignored if @all is true)
+ * @id: The ID of the watch to remove (ignored if @all is true)
+ * @all: True to remove all objects
+ *
+ * Remove a specific watch or all watches from an object.  A notification is
+ * sent to the watcher to tell them that this happened.
+ */
+int remove_watch_from_object(struct watch_list *wlist, struct watch_queue *wq,
+			     u64 id, bool all)
+{
+	struct watch_notification_removal n;
+	struct watch_queue *wqueue;
+	struct watch *watch;
+	int ret = -EBADSLT;
+
+	rcu_read_lock();
+
+again:
+	spin_lock(&wlist->lock);
+	hlist_for_each_entry(watch, &wlist->watchers, list_node) {
+		if (all ||
+		    (watch->id == id && rcu_access_pointer(watch->queue) == wq))
+			goto found;
+	}
+	spin_unlock(&wlist->lock);
+	goto out;
+
+found:
+	ret = 0;
+	hlist_del_init_rcu(&watch->list_node);
+	rcu_assign_pointer(watch->watch_list, NULL);
+	spin_unlock(&wlist->lock);
+
+	/* We now own the reference on watch that used to belong to wlist. */
+
+	n.watch.type = WATCH_TYPE_META;
+	n.watch.subtype = WATCH_META_REMOVAL_NOTIFICATION;
+	n.watch.info = watch->info_id | watch_sizeof(n.watch);
+	n.id = id;
+	if (id != 0)
+		n.watch.info = watch->info_id | watch_sizeof(n);
+
+	wqueue = rcu_dereference(watch->queue);
+
+	/* We don't need the watch list lock for the next bit as RCU is
+	 * protecting *wqueue from deallocation.
+	 */
+	if (wqueue) {
+		post_one_notification(wqueue, &n.watch);
+
+		spin_lock_bh(&wqueue->lock);
+
+		if (!hlist_unhashed(&watch->queue_node)) {
+			hlist_del_init_rcu(&watch->queue_node);
+			put_watch(watch);
+		}
+
+		spin_unlock_bh(&wqueue->lock);
+	}
+
+	if (wlist->release_watch) {
+		void (*release_watch)(struct watch *);
+
+		release_watch = wlist->release_watch;
+		rcu_read_unlock();
+		(*release_watch)(watch);
+		rcu_read_lock();
+	}
+	put_watch(watch);
+
+	if (all && !hlist_empty(&wlist->watchers))
+		goto again;
+out:
+	rcu_read_unlock();
+	return ret;
+}
+EXPORT_SYMBOL(remove_watch_from_object);
+
+/*
+ * Remove all the watches that are contributory to a queue.  This has the
+ * potential to race with removal of the watches by the destruction of the
+ * objects being watched or with the distribution of notifications.
+ */
+void watch_queue_clear(struct watch_queue *wqueue)
+{
+	struct watch_list *wlist;
+	struct watch *watch;
+	bool release;
+
+	rcu_read_lock();
+	spin_lock_bh(&wqueue->lock);
+
+	/* Prevent new additions and prevent notifications from happening */
+	wqueue->defunct = true;
+
+	while (!hlist_empty(&wqueue->watches)) {
+		watch = hlist_entry(wqueue->watches.first, struct watch, queue_node);
+		hlist_del_init_rcu(&watch->queue_node);
+		/* We now own a ref on the watch. */
+		spin_unlock_bh(&wqueue->lock);
+
+		/* We can't do the next bit under the queue lock as we need to
+		 * get the list lock - which would cause a deadlock if someone
+		 * was removing from the opposite direction at the same time or
+		 * posting a notification.
+		 */
+		wlist = rcu_dereference(watch->watch_list);
+		if (wlist) {
+			void (*release_watch)(struct watch *);
+
+			spin_lock(&wlist->lock);
+
+			release = !hlist_unhashed(&watch->list_node);
+			if (release) {
+				hlist_del_init_rcu(&watch->list_node);
+				rcu_assign_pointer(watch->watch_list, NULL);
+
+				/* We now own a second ref on the watch. */
+			}
+
+			release_watch = wlist->release_watch;
+			spin_unlock(&wlist->lock);
+
+			if (release) {
+				if (release_watch) {
+					rcu_read_unlock();
+					/* This might need to call dput(), so
+					 * we have to drop all the locks.
+					 */
+					(*release_watch)(watch);
+					rcu_read_lock();
+				}
+				put_watch(watch);
+			}
+		}
+
+		put_watch(watch);
+		spin_lock_bh(&wqueue->lock);
+	}
+
+	spin_unlock_bh(&wqueue->lock);
+	rcu_read_unlock();
+}
+
+/**
+ * get_watch_queue - Get a watch queue from its file descriptor.
+ * @fd: The fd to query.
+ */
+struct watch_queue *get_watch_queue(int fd)
+{
+	struct pipe_inode_info *pipe;
+	struct watch_queue *wqueue = ERR_PTR(-EINVAL);
+	struct fd f;
+
+	f = fdget(fd);
+	if (f.file) {
+		pipe = get_pipe_info(f.file, false);
+		if (pipe && pipe->watch_queue) {
+			wqueue = pipe->watch_queue;
+			kref_get(&wqueue->usage);
+		}
+		fdput(f);
+	}
+
+	return wqueue;
+}
+EXPORT_SYMBOL(get_watch_queue);
+
+/*
+ * Initialise a watch queue
+ */
+int watch_queue_init(struct pipe_inode_info *pipe)
+{
+	struct watch_queue *wqueue;
+
+	wqueue = kzalloc(sizeof(*wqueue), GFP_KERNEL);
+	if (!wqueue)
+		return -ENOMEM;
+
+	wqueue->pipe = pipe;
+	kref_init(&wqueue->usage);
+	spin_lock_init(&wqueue->lock);
+	INIT_HLIST_HEAD(&wqueue->watches);
+
+	pipe->watch_queue = wqueue;
+	return 0;
+}
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index b6b1f54a7837..5abb5b22ad13 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -50,6 +50,11 @@ struct cpumask watchdog_cpumask __read_mostly;
 unsigned long *watchdog_cpumask_bits = cpumask_bits(&watchdog_cpumask);
 
 #ifdef CONFIG_HARDLOCKUP_DETECTOR
+
+# ifdef CONFIG_SMP
+int __read_mostly sysctl_hardlockup_all_cpu_backtrace;
+# endif /* CONFIG_SMP */
+
 /*
  * Should we panic when a soft-lockup or hard-lockup occurs:
  */
@@ -82,16 +87,6 @@ static int __init hardlockup_panic_setup(char *str)
 }
 __setup("nmi_watchdog=", hardlockup_panic_setup);
 
-# ifdef CONFIG_SMP
-int __read_mostly sysctl_hardlockup_all_cpu_backtrace;
-
-static int __init hardlockup_all_cpu_backtrace_setup(char *str)
-{
-	sysctl_hardlockup_all_cpu_backtrace = !!simple_strtol(str, NULL, 0);
-	return 1;
-}
-__setup("hardlockup_all_cpu_backtrace=", hardlockup_all_cpu_backtrace_setup);
-# endif /* CONFIG_SMP */
 #endif /* CONFIG_HARDLOCKUP_DETECTOR */
 
 /*
@@ -163,6 +158,10 @@ static void lockup_detector_update_enable(void)
 
 #define SOFTLOCKUP_RESET	ULONG_MAX
 
+#ifdef CONFIG_SMP
+int __read_mostly sysctl_softlockup_all_cpu_backtrace;
+#endif
+
 /* Global variables, exported for sysctl */
 unsigned int __read_mostly softlockup_panic =
 			CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC_VALUE;
@@ -178,13 +177,6 @@ static DEFINE_PER_CPU(unsigned long, hrtimer_interrupts);
 static DEFINE_PER_CPU(unsigned long, hrtimer_interrupts_saved);
 static unsigned long soft_lockup_nmi_warn;
 
-static int __init softlockup_panic_setup(char *str)
-{
-	softlockup_panic = simple_strtoul(str, NULL, 0);
-	return 1;
-}
-__setup("softlockup_panic=", softlockup_panic_setup);
-
 static int __init nowatchdog_setup(char *str)
 {
 	watchdog_user_enabled = 0;
@@ -206,17 +198,6 @@ static int __init watchdog_thresh_setup(char *str)
 }
 __setup("watchdog_thresh=", watchdog_thresh_setup);
 
-#ifdef CONFIG_SMP
-int __read_mostly sysctl_softlockup_all_cpu_backtrace;
-
-static int __init softlockup_all_cpu_backtrace_setup(char *str)
-{
-	sysctl_softlockup_all_cpu_backtrace = !!simple_strtol(str, NULL, 0);
-	return 1;
-}
-__setup("softlockup_all_cpu_backtrace=", softlockup_all_cpu_backtrace_setup);
-#endif
-
 static void __lockup_detector_cleanup(void);
 
 /*
@@ -661,7 +642,7 @@ static void proc_watchdog_update(void)
  * proc_soft_watchdog | soft_watchdog_user_enabled | SOFT_WATCHDOG_ENABLED
  */
 static int proc_watchdog_common(int which, struct ctl_table *table, int write,
-				void __user *buffer, size_t *lenp, loff_t *ppos)
+				void *buffer, size_t *lenp, loff_t *ppos)
 {
 	int err, old, *param = table->data;
 
@@ -688,7 +669,7 @@ static int proc_watchdog_common(int which, struct ctl_table *table, int write,
  * /proc/sys/kernel/watchdog
  */
 int proc_watchdog(struct ctl_table *table, int write,
-		  void __user *buffer, size_t *lenp, loff_t *ppos)
+		  void *buffer, size_t *lenp, loff_t *ppos)
 {
 	return proc_watchdog_common(NMI_WATCHDOG_ENABLED|SOFT_WATCHDOG_ENABLED,
 				    table, write, buffer, lenp, ppos);
@@ -698,7 +679,7 @@ int proc_watchdog(struct ctl_table *table, int write,
  * /proc/sys/kernel/nmi_watchdog
  */
 int proc_nmi_watchdog(struct ctl_table *table, int write,
-		      void __user *buffer, size_t *lenp, loff_t *ppos)
+		      void *buffer, size_t *lenp, loff_t *ppos)
 {
 	if (!nmi_watchdog_available && write)
 		return -ENOTSUPP;
@@ -710,7 +691,7 @@ int proc_nmi_watchdog(struct ctl_table *table, int write,
  * /proc/sys/kernel/soft_watchdog
  */
 int proc_soft_watchdog(struct ctl_table *table, int write,
-			void __user *buffer, size_t *lenp, loff_t *ppos)
+			void *buffer, size_t *lenp, loff_t *ppos)
 {
 	return proc_watchdog_common(SOFT_WATCHDOG_ENABLED,
 				    table, write, buffer, lenp, ppos);
@@ -720,7 +701,7 @@ int proc_soft_watchdog(struct ctl_table *table, int write,
  * /proc/sys/kernel/watchdog_thresh
  */
 int proc_watchdog_thresh(struct ctl_table *table, int write,
-			 void __user *buffer, size_t *lenp, loff_t *ppos)
+			 void *buffer, size_t *lenp, loff_t *ppos)
 {
 	int err, old;
 
@@ -743,7 +724,7 @@ int proc_watchdog_thresh(struct ctl_table *table, int write,
  * been brought online, if desired.
  */
 int proc_watchdog_cpumask(struct ctl_table *table, int write,
-			  void __user *buffer, size_t *lenp, loff_t *ppos)
+			  void *buffer, size_t *lenp, loff_t *ppos)
 {
 	int err;
 
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 4e01c448b4b4..c41c3c17b86a 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -145,7 +145,7 @@ enum {
 /* struct worker is defined in workqueue_internal.h */
 
 struct worker_pool {
-	spinlock_t		lock;		/* the pool lock */
+	raw_spinlock_t		lock;		/* the pool lock */
 	int			cpu;		/* I: the associated cpu */
 	int			node;		/* I: the associated node ID */
 	int			id;		/* I: pool ID */
@@ -300,8 +300,9 @@ static struct workqueue_attrs *wq_update_unbound_numa_attrs_buf;
 
 static DEFINE_MUTEX(wq_pool_mutex);	/* protects pools and workqueues list */
 static DEFINE_MUTEX(wq_pool_attach_mutex); /* protects worker attach/detach */
-static DEFINE_SPINLOCK(wq_mayday_lock);	/* protects wq->maydays list */
-static DECLARE_WAIT_QUEUE_HEAD(wq_manager_wait); /* wait for manager to go away */
+static DEFINE_RAW_SPINLOCK(wq_mayday_lock);	/* protects wq->maydays list */
+/* wait for manager to go away */
+static struct rcuwait manager_wait = __RCUWAIT_INITIALIZER(manager_wait);
 
 static LIST_HEAD(workqueues);		/* PR: list of all workqueues */
 static bool workqueue_freezing;		/* PL: have wqs started freezing? */
@@ -826,7 +827,7 @@ static struct worker *first_idle_worker(struct worker_pool *pool)
  * Wake up the first idle worker of @pool.
  *
  * CONTEXT:
- * spin_lock_irq(pool->lock).
+ * raw_spin_lock_irq(pool->lock).
  */
 static void wake_up_worker(struct worker_pool *pool)
 {
@@ -858,7 +859,8 @@ void wq_worker_running(struct task_struct *task)
  * @task: task going to sleep
  *
  * This function is called from schedule() when a busy worker is
- * going to sleep.
+ * going to sleep. Preemption needs to be disabled to protect ->sleeping
+ * assignment.
  */
 void wq_worker_sleeping(struct task_struct *task)
 {
@@ -875,11 +877,12 @@ void wq_worker_sleeping(struct task_struct *task)
 
 	pool = worker->pool;
 
-	if (WARN_ON_ONCE(worker->sleeping))
+	/* Return if preempted before wq_worker_running() was reached */
+	if (worker->sleeping)
 		return;
 
 	worker->sleeping = 1;
-	spin_lock_irq(&pool->lock);
+	raw_spin_lock_irq(&pool->lock);
 
 	/*
 	 * The counterpart of the following dec_and_test, implied mb,
@@ -898,7 +901,7 @@ void wq_worker_sleeping(struct task_struct *task)
 		if (next)
 			wake_up_process(next->task);
 	}
-	spin_unlock_irq(&pool->lock);
+	raw_spin_unlock_irq(&pool->lock);
 }
 
 /**
@@ -909,7 +912,7 @@ void wq_worker_sleeping(struct task_struct *task)
  * the scheduler to get a worker's last known identity.
  *
  * CONTEXT:
- * spin_lock_irq(rq->lock)
+ * raw_spin_lock_irq(rq->lock)
  *
  * This function is called during schedule() when a kworker is going
  * to sleep. It's used by psi to identify aggregation workers during
@@ -940,7 +943,7 @@ work_func_t wq_worker_last_func(struct task_struct *task)
  * Set @flags in @worker->flags and adjust nr_running accordingly.
  *
  * CONTEXT:
- * spin_lock_irq(pool->lock)
+ * raw_spin_lock_irq(pool->lock)
  */
 static inline void worker_set_flags(struct worker *worker, unsigned int flags)
 {
@@ -965,7 +968,7 @@ static inline void worker_set_flags(struct worker *worker, unsigned int flags)
  * Clear @flags in @worker->flags and adjust nr_running accordingly.
  *
  * CONTEXT:
- * spin_lock_irq(pool->lock)
+ * raw_spin_lock_irq(pool->lock)
  */
 static inline void worker_clr_flags(struct worker *worker, unsigned int flags)
 {
@@ -1013,7 +1016,7 @@ static inline void worker_clr_flags(struct worker *worker, unsigned int flags)
  * actually occurs, it should be easy to locate the culprit work function.
  *
  * CONTEXT:
- * spin_lock_irq(pool->lock).
+ * raw_spin_lock_irq(pool->lock).
  *
  * Return:
  * Pointer to worker which is executing @work if found, %NULL
@@ -1048,7 +1051,7 @@ static struct worker *find_worker_executing_work(struct worker_pool *pool,
  * nested inside outer list_for_each_entry_safe().
  *
  * CONTEXT:
- * spin_lock_irq(pool->lock).
+ * raw_spin_lock_irq(pool->lock).
  */
 static void move_linked_works(struct work_struct *work, struct list_head *head,
 			      struct work_struct **nextp)
@@ -1126,9 +1129,9 @@ static void put_pwq_unlocked(struct pool_workqueue *pwq)
 		 * As both pwqs and pools are RCU protected, the
 		 * following lock operations are safe.
 		 */
-		spin_lock_irq(&pwq->pool->lock);
+		raw_spin_lock_irq(&pwq->pool->lock);
 		put_pwq(pwq);
-		spin_unlock_irq(&pwq->pool->lock);
+		raw_spin_unlock_irq(&pwq->pool->lock);
 	}
 }
 
@@ -1161,7 +1164,7 @@ static void pwq_activate_first_delayed(struct pool_workqueue *pwq)
  * decrement nr_in_flight of its pwq and handle workqueue flushing.
  *
  * CONTEXT:
- * spin_lock_irq(pool->lock).
+ * raw_spin_lock_irq(pool->lock).
  */
 static void pwq_dec_nr_in_flight(struct pool_workqueue *pwq, int color)
 {
@@ -1260,7 +1263,7 @@ static int try_to_grab_pending(struct work_struct *work, bool is_dwork,
 	if (!pool)
 		goto fail;
 
-	spin_lock(&pool->lock);
+	raw_spin_lock(&pool->lock);
 	/*
 	 * work->data is guaranteed to point to pwq only while the work
 	 * item is queued on pwq->wq, and both updating work->data to point
@@ -1289,11 +1292,11 @@ static int try_to_grab_pending(struct work_struct *work, bool is_dwork,
 		/* work->data points to pwq iff queued, point to pool */
 		set_work_pool_and_keep_pending(work, pool->id);
 
-		spin_unlock(&pool->lock);
+		raw_spin_unlock(&pool->lock);
 		rcu_read_unlock();
 		return 1;
 	}
-	spin_unlock(&pool->lock);
+	raw_spin_unlock(&pool->lock);
 fail:
 	rcu_read_unlock();
 	local_irq_restore(*flags);
@@ -1314,7 +1317,7 @@ fail:
  * work_struct flags.
  *
  * CONTEXT:
- * spin_lock_irq(pool->lock).
+ * raw_spin_lock_irq(pool->lock).
  */
 static void insert_work(struct pool_workqueue *pwq, struct work_struct *work,
 			struct list_head *head, unsigned int extra_flags)
@@ -1431,7 +1434,7 @@ retry:
 	if (last_pool && last_pool != pwq->pool) {
 		struct worker *worker;
 
-		spin_lock(&last_pool->lock);
+		raw_spin_lock(&last_pool->lock);
 
 		worker = find_worker_executing_work(last_pool, work);
 
@@ -1439,11 +1442,11 @@ retry:
 			pwq = worker->current_pwq;
 		} else {
 			/* meh... not running there, queue here */
-			spin_unlock(&last_pool->lock);
-			spin_lock(&pwq->pool->lock);
+			raw_spin_unlock(&last_pool->lock);
+			raw_spin_lock(&pwq->pool->lock);
 		}
 	} else {
-		spin_lock(&pwq->pool->lock);
+		raw_spin_lock(&pwq->pool->lock);
 	}
 
 	/*
@@ -1456,7 +1459,7 @@ retry:
 	 */
 	if (unlikely(!pwq->refcnt)) {
 		if (wq->flags & WQ_UNBOUND) {
-			spin_unlock(&pwq->pool->lock);
+			raw_spin_unlock(&pwq->pool->lock);
 			cpu_relax();
 			goto retry;
 		}
@@ -1488,7 +1491,7 @@ retry:
 	insert_work(pwq, work, worklist, work_flags);
 
 out:
-	spin_unlock(&pwq->pool->lock);
+	raw_spin_unlock(&pwq->pool->lock);
 	rcu_read_unlock();
 }
 
@@ -1757,7 +1760,7 @@ EXPORT_SYMBOL(queue_rcu_work);
  * necessary.
  *
  * LOCKING:
- * spin_lock_irq(pool->lock).
+ * raw_spin_lock_irq(pool->lock).
  */
 static void worker_enter_idle(struct worker *worker)
 {
@@ -1797,7 +1800,7 @@ static void worker_enter_idle(struct worker *worker)
  * @worker is leaving idle state.  Update stats.
  *
  * LOCKING:
- * spin_lock_irq(pool->lock).
+ * raw_spin_lock_irq(pool->lock).
  */
 static void worker_leave_idle(struct worker *worker)
 {
@@ -1935,11 +1938,11 @@ static struct worker *create_worker(struct worker_pool *pool)
 	worker_attach_to_pool(worker, pool);
 
 	/* start the newly created worker */
-	spin_lock_irq(&pool->lock);
+	raw_spin_lock_irq(&pool->lock);
 	worker->pool->nr_workers++;
 	worker_enter_idle(worker);
 	wake_up_process(worker->task);
-	spin_unlock_irq(&pool->lock);
+	raw_spin_unlock_irq(&pool->lock);
 
 	return worker;
 
@@ -1958,7 +1961,7 @@ fail:
  * be idle.
  *
  * CONTEXT:
- * spin_lock_irq(pool->lock).
+ * raw_spin_lock_irq(pool->lock).
  */
 static void destroy_worker(struct worker *worker)
 {
@@ -1984,7 +1987,7 @@ static void idle_worker_timeout(struct timer_list *t)
 {
 	struct worker_pool *pool = from_timer(pool, t, idle_timer);
 
-	spin_lock_irq(&pool->lock);
+	raw_spin_lock_irq(&pool->lock);
 
 	while (too_many_workers(pool)) {
 		struct worker *worker;
@@ -2002,7 +2005,7 @@ static void idle_worker_timeout(struct timer_list *t)
 		destroy_worker(worker);
 	}
 
-	spin_unlock_irq(&pool->lock);
+	raw_spin_unlock_irq(&pool->lock);
 }
 
 static void send_mayday(struct work_struct *work)
@@ -2033,8 +2036,8 @@ static void pool_mayday_timeout(struct timer_list *t)
 	struct worker_pool *pool = from_timer(pool, t, mayday_timer);
 	struct work_struct *work;
 
-	spin_lock_irq(&pool->lock);
-	spin_lock(&wq_mayday_lock);		/* for wq->maydays */
+	raw_spin_lock_irq(&pool->lock);
+	raw_spin_lock(&wq_mayday_lock);		/* for wq->maydays */
 
 	if (need_to_create_worker(pool)) {
 		/*
@@ -2047,8 +2050,8 @@ static void pool_mayday_timeout(struct timer_list *t)
 			send_mayday(work);
 	}
 
-	spin_unlock(&wq_mayday_lock);
-	spin_unlock_irq(&pool->lock);
+	raw_spin_unlock(&wq_mayday_lock);
+	raw_spin_unlock_irq(&pool->lock);
 
 	mod_timer(&pool->mayday_timer, jiffies + MAYDAY_INTERVAL);
 }
@@ -2067,7 +2070,7 @@ static void pool_mayday_timeout(struct timer_list *t)
  * may_start_working() %true.
  *
  * LOCKING:
- * spin_lock_irq(pool->lock) which may be released and regrabbed
+ * raw_spin_lock_irq(pool->lock) which may be released and regrabbed
  * multiple times.  Does GFP_KERNEL allocations.  Called only from
  * manager.
  */
@@ -2076,7 +2079,7 @@ __releases(&pool->lock)
 __acquires(&pool->lock)
 {
 restart:
-	spin_unlock_irq(&pool->lock);
+	raw_spin_unlock_irq(&pool->lock);
 
 	/* if we don't make progress in MAYDAY_INITIAL_TIMEOUT, call for help */
 	mod_timer(&pool->mayday_timer, jiffies + MAYDAY_INITIAL_TIMEOUT);
@@ -2092,7 +2095,7 @@ restart:
 	}
 
 	del_timer_sync(&pool->mayday_timer);
-	spin_lock_irq(&pool->lock);
+	raw_spin_lock_irq(&pool->lock);
 	/*
 	 * This is necessary even after a new worker was just successfully
 	 * created as @pool->lock was dropped and the new worker might have
@@ -2115,7 +2118,7 @@ restart:
  * and may_start_working() is true.
  *
  * CONTEXT:
- * spin_lock_irq(pool->lock) which may be released and regrabbed
+ * raw_spin_lock_irq(pool->lock) which may be released and regrabbed
  * multiple times.  Does GFP_KERNEL allocations.
  *
  * Return:
@@ -2138,7 +2141,7 @@ static bool manage_workers(struct worker *worker)
 
 	pool->manager = NULL;
 	pool->flags &= ~POOL_MANAGER_ACTIVE;
-	wake_up(&wq_manager_wait);
+	rcuwait_wake_up(&manager_wait);
 	return true;
 }
 
@@ -2154,7 +2157,7 @@ static bool manage_workers(struct worker *worker)
  * call this function to process a work.
  *
  * CONTEXT:
- * spin_lock_irq(pool->lock) which is released and regrabbed.
+ * raw_spin_lock_irq(pool->lock) which is released and regrabbed.
  */
 static void process_one_work(struct worker *worker, struct work_struct *work)
 __releases(&pool->lock)
@@ -2236,7 +2239,7 @@ __acquires(&pool->lock)
 	 */
 	set_work_pool_and_clear_pending(work, pool->id);
 
-	spin_unlock_irq(&pool->lock);
+	raw_spin_unlock_irq(&pool->lock);
 
 	lock_map_acquire(&pwq->wq->lockdep_map);
 	lock_map_acquire(&lockdep_map);
@@ -2291,7 +2294,7 @@ __acquires(&pool->lock)
 	 */
 	cond_resched();
 
-	spin_lock_irq(&pool->lock);
+	raw_spin_lock_irq(&pool->lock);
 
 	/* clear cpu intensive status */
 	if (unlikely(cpu_intensive))
@@ -2317,7 +2320,7 @@ __acquires(&pool->lock)
  * fetches a work from the top and executes it.
  *
  * CONTEXT:
- * spin_lock_irq(pool->lock) which may be released and regrabbed
+ * raw_spin_lock_irq(pool->lock) which may be released and regrabbed
  * multiple times.
  */
 static void process_scheduled_works(struct worker *worker)
@@ -2359,11 +2362,11 @@ static int worker_thread(void *__worker)
 	/* tell the scheduler that this is a workqueue worker */
 	set_pf_worker(true);
 woke_up:
-	spin_lock_irq(&pool->lock);
+	raw_spin_lock_irq(&pool->lock);
 
 	/* am I supposed to die? */
 	if (unlikely(worker->flags & WORKER_DIE)) {
-		spin_unlock_irq(&pool->lock);
+		raw_spin_unlock_irq(&pool->lock);
 		WARN_ON_ONCE(!list_empty(&worker->entry));
 		set_pf_worker(false);
 
@@ -2429,7 +2432,7 @@ sleep:
 	 */
 	worker_enter_idle(worker);
 	__set_current_state(TASK_IDLE);
-	spin_unlock_irq(&pool->lock);
+	raw_spin_unlock_irq(&pool->lock);
 	schedule();
 	goto woke_up;
 }
@@ -2483,7 +2486,7 @@ repeat:
 	should_stop = kthread_should_stop();
 
 	/* see whether any pwq is asking for help */
-	spin_lock_irq(&wq_mayday_lock);
+	raw_spin_lock_irq(&wq_mayday_lock);
 
 	while (!list_empty(&wq->maydays)) {
 		struct pool_workqueue *pwq = list_first_entry(&wq->maydays,
@@ -2495,11 +2498,11 @@ repeat:
 		__set_current_state(TASK_RUNNING);
 		list_del_init(&pwq->mayday_node);
 
-		spin_unlock_irq(&wq_mayday_lock);
+		raw_spin_unlock_irq(&wq_mayday_lock);
 
 		worker_attach_to_pool(rescuer, pool);
 
-		spin_lock_irq(&pool->lock);
+		raw_spin_lock_irq(&pool->lock);
 
 		/*
 		 * Slurp in all works issued via this workqueue and
@@ -2527,8 +2530,8 @@ repeat:
 			 * being used to relieve memory pressure, don't
 			 * incur MAYDAY_INTERVAL delay inbetween.
 			 */
-			if (need_to_create_worker(pool)) {
-				spin_lock(&wq_mayday_lock);
+			if (pwq->nr_active && need_to_create_worker(pool)) {
+				raw_spin_lock(&wq_mayday_lock);
 				/*
 				 * Queue iff we aren't racing destruction
 				 * and somebody else hasn't queued it already.
@@ -2537,7 +2540,7 @@ repeat:
 					get_pwq(pwq);
 					list_add_tail(&pwq->mayday_node, &wq->maydays);
 				}
-				spin_unlock(&wq_mayday_lock);
+				raw_spin_unlock(&wq_mayday_lock);
 			}
 		}
 
@@ -2555,14 +2558,14 @@ repeat:
 		if (need_more_worker(pool))
 			wake_up_worker(pool);
 
-		spin_unlock_irq(&pool->lock);
+		raw_spin_unlock_irq(&pool->lock);
 
 		worker_detach_from_pool(rescuer);
 
-		spin_lock_irq(&wq_mayday_lock);
+		raw_spin_lock_irq(&wq_mayday_lock);
 	}
 
-	spin_unlock_irq(&wq_mayday_lock);
+	raw_spin_unlock_irq(&wq_mayday_lock);
 
 	if (should_stop) {
 		__set_current_state(TASK_RUNNING);
@@ -2642,7 +2645,7 @@ static void wq_barrier_func(struct work_struct *work)
  * underneath us, so we can't reliably determine pwq from @target.
  *
  * CONTEXT:
- * spin_lock_irq(pool->lock).
+ * raw_spin_lock_irq(pool->lock).
  */
 static void insert_wq_barrier(struct pool_workqueue *pwq,
 			      struct wq_barrier *barr,
@@ -2729,7 +2732,7 @@ static bool flush_workqueue_prep_pwqs(struct workqueue_struct *wq,
 	for_each_pwq(pwq, wq) {
 		struct worker_pool *pool = pwq->pool;
 
-		spin_lock_irq(&pool->lock);
+		raw_spin_lock_irq(&pool->lock);
 
 		if (flush_color >= 0) {
 			WARN_ON_ONCE(pwq->flush_color != -1);
@@ -2746,7 +2749,7 @@ static bool flush_workqueue_prep_pwqs(struct workqueue_struct *wq,
 			pwq->work_color = work_color;
 		}
 
-		spin_unlock_irq(&pool->lock);
+		raw_spin_unlock_irq(&pool->lock);
 	}
 
 	if (flush_color >= 0 && atomic_dec_and_test(&wq->nr_pwqs_to_flush))
@@ -2834,7 +2837,7 @@ void flush_workqueue(struct workqueue_struct *wq)
 	 * First flushers are responsible for cascading flushes and
 	 * handling overflow.  Non-first flushers can simply return.
 	 */
-	if (wq->first_flusher != &this_flusher)
+	if (READ_ONCE(wq->first_flusher) != &this_flusher)
 		return;
 
 	mutex_lock(&wq->mutex);
@@ -2843,7 +2846,7 @@ void flush_workqueue(struct workqueue_struct *wq)
 	if (wq->first_flusher != &this_flusher)
 		goto out_unlock;
 
-	wq->first_flusher = NULL;
+	WRITE_ONCE(wq->first_flusher, NULL);
 
 	WARN_ON_ONCE(!list_empty(&this_flusher.list));
 	WARN_ON_ONCE(wq->flush_color != this_flusher.flush_color);
@@ -2946,9 +2949,9 @@ reflush:
 	for_each_pwq(pwq, wq) {
 		bool drained;
 
-		spin_lock_irq(&pwq->pool->lock);
+		raw_spin_lock_irq(&pwq->pool->lock);
 		drained = !pwq->nr_active && list_empty(&pwq->delayed_works);
-		spin_unlock_irq(&pwq->pool->lock);
+		raw_spin_unlock_irq(&pwq->pool->lock);
 
 		if (drained)
 			continue;
@@ -2984,7 +2987,7 @@ static bool start_flush_work(struct work_struct *work, struct wq_barrier *barr,
 		return false;
 	}
 
-	spin_lock_irq(&pool->lock);
+	raw_spin_lock_irq(&pool->lock);
 	/* see the comment in try_to_grab_pending() with the same code */
 	pwq = get_work_pwq(work);
 	if (pwq) {
@@ -3000,7 +3003,7 @@ static bool start_flush_work(struct work_struct *work, struct wq_barrier *barr,
 	check_flush_dependency(pwq->wq, work);
 
 	insert_wq_barrier(pwq, barr, work, worker);
-	spin_unlock_irq(&pool->lock);
+	raw_spin_unlock_irq(&pool->lock);
 
 	/*
 	 * Force a lock recursion deadlock when using flush_work() inside a
@@ -3019,7 +3022,7 @@ static bool start_flush_work(struct work_struct *work, struct wq_barrier *barr,
 	rcu_read_unlock();
 	return true;
 already_gone:
-	spin_unlock_irq(&pool->lock);
+	raw_spin_unlock_irq(&pool->lock);
 	rcu_read_unlock();
 	return false;
 }
@@ -3412,7 +3415,7 @@ static bool wqattrs_equal(const struct workqueue_attrs *a,
  */
 static int init_worker_pool(struct worker_pool *pool)
 {
-	spin_lock_init(&pool->lock);
+	raw_spin_lock_init(&pool->lock);
 	pool->id = -1;
 	pool->cpu = -1;
 	pool->node = NUMA_NO_NODE;
@@ -3489,7 +3492,6 @@ static void rcu_free_wq(struct rcu_head *rcu)
 	else
 		free_workqueue_attrs(wq->unbound_attrs);
 
-	kfree(wq->rescuer);
 	kfree(wq);
 }
 
@@ -3502,6 +3504,18 @@ static void rcu_free_pool(struct rcu_head *rcu)
 	kfree(pool);
 }
 
+/* This returns with the lock held on success (pool manager is inactive). */
+static bool wq_manager_inactive(struct worker_pool *pool)
+{
+	raw_spin_lock_irq(&pool->lock);
+
+	if (pool->flags & POOL_MANAGER_ACTIVE) {
+		raw_spin_unlock_irq(&pool->lock);
+		return false;
+	}
+	return true;
+}
+
 /**
  * put_unbound_pool - put a worker_pool
  * @pool: worker_pool to put
@@ -3537,16 +3551,17 @@ static void put_unbound_pool(struct worker_pool *pool)
 	 * Become the manager and destroy all workers.  This prevents
 	 * @pool's workers from blocking on attach_mutex.  We're the last
 	 * manager and @pool gets freed with the flag set.
+	 * Because of how wq_manager_inactive() works, we will hold the
+	 * spinlock after a successful wait.
 	 */
-	spin_lock_irq(&pool->lock);
-	wait_event_lock_irq(wq_manager_wait,
-			    !(pool->flags & POOL_MANAGER_ACTIVE), pool->lock);
+	rcuwait_wait_event(&manager_wait, wq_manager_inactive(pool),
+			   TASK_UNINTERRUPTIBLE);
 	pool->flags |= POOL_MANAGER_ACTIVE;
 
 	while ((worker = first_idle_worker(pool)))
 		destroy_worker(worker);
 	WARN_ON(pool->nr_workers || pool->nr_idle);
-	spin_unlock_irq(&pool->lock);
+	raw_spin_unlock_irq(&pool->lock);
 
 	mutex_lock(&wq_pool_attach_mutex);
 	if (!list_empty(&pool->workers))
@@ -3702,7 +3717,7 @@ static void pwq_adjust_max_active(struct pool_workqueue *pwq)
 		return;
 
 	/* this function can be called during early boot w/ irq disabled */
-	spin_lock_irqsave(&pwq->pool->lock, flags);
+	raw_spin_lock_irqsave(&pwq->pool->lock, flags);
 
 	/*
 	 * During [un]freezing, the caller is responsible for ensuring that
@@ -3725,7 +3740,7 @@ static void pwq_adjust_max_active(struct pool_workqueue *pwq)
 		pwq->max_active = 0;
 	}
 
-	spin_unlock_irqrestore(&pwq->pool->lock, flags);
+	raw_spin_unlock_irqrestore(&pwq->pool->lock, flags);
 }
 
 /* initialize newly alloced @pwq which is associated with @wq and @pool */
@@ -4127,9 +4142,9 @@ static void wq_update_unbound_numa(struct workqueue_struct *wq, int cpu,
 
 use_dfl_pwq:
 	mutex_lock(&wq->mutex);
-	spin_lock_irq(&wq->dfl_pwq->pool->lock);
+	raw_spin_lock_irq(&wq->dfl_pwq->pool->lock);
 	get_pwq(wq->dfl_pwq);
-	spin_unlock_irq(&wq->dfl_pwq->pool->lock);
+	raw_spin_unlock_irq(&wq->dfl_pwq->pool->lock);
 	old_pwq = numa_pwq_tbl_install(wq, node, wq->dfl_pwq);
 out_unlock:
 	mutex_unlock(&wq->mutex);
@@ -4206,8 +4221,8 @@ static int init_rescuer(struct workqueue_struct *wq)
 
 	rescuer->rescue_wq = wq;
 	rescuer->task = kthread_create(rescuer_thread, rescuer, "%s", wq->name);
-	ret = PTR_ERR_OR_ZERO(rescuer->task);
-	if (ret) {
+	if (IS_ERR(rescuer->task)) {
+		ret = PTR_ERR(rescuer->task);
 		kfree(rescuer);
 		return ret;
 	}
@@ -4358,9 +4373,9 @@ void destroy_workqueue(struct workqueue_struct *wq)
 		struct worker *rescuer = wq->rescuer;
 
 		/* this prevents new queueing */
-		spin_lock_irq(&wq_mayday_lock);
+		raw_spin_lock_irq(&wq_mayday_lock);
 		wq->rescuer = NULL;
-		spin_unlock_irq(&wq_mayday_lock);
+		raw_spin_unlock_irq(&wq_mayday_lock);
 
 		/* rescuer will empty maydays list before exiting */
 		kthread_stop(rescuer->task);
@@ -4374,27 +4389,25 @@ void destroy_workqueue(struct workqueue_struct *wq)
 	mutex_lock(&wq_pool_mutex);
 	mutex_lock(&wq->mutex);
 	for_each_pwq(pwq, wq) {
-		spin_lock_irq(&pwq->pool->lock);
+		raw_spin_lock_irq(&pwq->pool->lock);
 		if (WARN_ON(pwq_busy(pwq))) {
 			pr_warn("%s: %s has the following busy pwq\n",
 				__func__, wq->name);
 			show_pwq(pwq);
-			spin_unlock_irq(&pwq->pool->lock);
+			raw_spin_unlock_irq(&pwq->pool->lock);
 			mutex_unlock(&wq->mutex);
 			mutex_unlock(&wq_pool_mutex);
 			show_workqueue_state();
 			return;
 		}
-		spin_unlock_irq(&pwq->pool->lock);
+		raw_spin_unlock_irq(&pwq->pool->lock);
 	}
 	mutex_unlock(&wq->mutex);
-	mutex_unlock(&wq_pool_mutex);
 
 	/*
 	 * wq list is used to freeze wq, remove from list after
 	 * flushing is complete in case freeze races us.
 	 */
-	mutex_lock(&wq_pool_mutex);
 	list_del_rcu(&wq->list);
 	mutex_unlock(&wq_pool_mutex);
 
@@ -4556,10 +4569,10 @@ unsigned int work_busy(struct work_struct *work)
 	rcu_read_lock();
 	pool = get_work_pool(work);
 	if (pool) {
-		spin_lock_irqsave(&pool->lock, flags);
+		raw_spin_lock_irqsave(&pool->lock, flags);
 		if (find_worker_executing_work(pool, work))
 			ret |= WORK_BUSY_RUNNING;
-		spin_unlock_irqrestore(&pool->lock, flags);
+		raw_spin_unlock_irqrestore(&pool->lock, flags);
 	}
 	rcu_read_unlock();
 
@@ -4625,11 +4638,11 @@ void print_worker_info(const char *log_lvl, struct task_struct *task)
 	 * Carefully copy the associated workqueue's workfn, name and desc.
 	 * Keep the original last '\0' in case the original is garbage.
 	 */
-	probe_kernel_read(&fn, &worker->current_func, sizeof(fn));
-	probe_kernel_read(&pwq, &worker->current_pwq, sizeof(pwq));
-	probe_kernel_read(&wq, &pwq->wq, sizeof(wq));
-	probe_kernel_read(name, wq->name, sizeof(name) - 1);
-	probe_kernel_read(desc, worker->desc, sizeof(desc) - 1);
+	copy_from_kernel_nofault(&fn, &worker->current_func, sizeof(fn));
+	copy_from_kernel_nofault(&pwq, &worker->current_pwq, sizeof(pwq));
+	copy_from_kernel_nofault(&wq, &pwq->wq, sizeof(wq));
+	copy_from_kernel_nofault(name, wq->name, sizeof(name) - 1);
+	copy_from_kernel_nofault(desc, worker->desc, sizeof(desc) - 1);
 
 	if (fn || name[0] || desc[0]) {
 		printk("%sWorkqueue: %s %ps", log_lvl, name, fn);
@@ -4766,10 +4779,10 @@ void show_workqueue_state(void)
 		pr_info("workqueue %s: flags=0x%x\n", wq->name, wq->flags);
 
 		for_each_pwq(pwq, wq) {
-			spin_lock_irqsave(&pwq->pool->lock, flags);
+			raw_spin_lock_irqsave(&pwq->pool->lock, flags);
 			if (pwq->nr_active || !list_empty(&pwq->delayed_works))
 				show_pwq(pwq);
-			spin_unlock_irqrestore(&pwq->pool->lock, flags);
+			raw_spin_unlock_irqrestore(&pwq->pool->lock, flags);
 			/*
 			 * We could be printing a lot from atomic context, e.g.
 			 * sysrq-t -> show_workqueue_state(). Avoid triggering
@@ -4783,7 +4796,7 @@ void show_workqueue_state(void)
 		struct worker *worker;
 		bool first = true;
 
-		spin_lock_irqsave(&pool->lock, flags);
+		raw_spin_lock_irqsave(&pool->lock, flags);
 		if (pool->nr_workers == pool->nr_idle)
 			goto next_pool;
 
@@ -4802,7 +4815,7 @@ void show_workqueue_state(void)
 		}
 		pr_cont("\n");
 	next_pool:
-		spin_unlock_irqrestore(&pool->lock, flags);
+		raw_spin_unlock_irqrestore(&pool->lock, flags);
 		/*
 		 * We could be printing a lot from atomic context, e.g.
 		 * sysrq-t -> show_workqueue_state(). Avoid triggering
@@ -4832,7 +4845,7 @@ void wq_worker_comm(char *buf, size_t size, struct task_struct *task)
 		struct worker_pool *pool = worker->pool;
 
 		if (pool) {
-			spin_lock_irq(&pool->lock);
+			raw_spin_lock_irq(&pool->lock);
 			/*
 			 * ->desc tracks information (wq name or
 			 * set_worker_desc()) for the latest execution.  If
@@ -4846,7 +4859,7 @@ void wq_worker_comm(char *buf, size_t size, struct task_struct *task)
 					scnprintf(buf + off, size - off, "-%s",
 						  worker->desc);
 			}
-			spin_unlock_irq(&pool->lock);
+			raw_spin_unlock_irq(&pool->lock);
 		}
 	}
 
@@ -4877,7 +4890,7 @@ static void unbind_workers(int cpu)
 
 	for_each_cpu_worker_pool(pool, cpu) {
 		mutex_lock(&wq_pool_attach_mutex);
-		spin_lock_irq(&pool->lock);
+		raw_spin_lock_irq(&pool->lock);
 
 		/*
 		 * We've blocked all attach/detach operations. Make all workers
@@ -4891,7 +4904,7 @@ static void unbind_workers(int cpu)
 
 		pool->flags |= POOL_DISASSOCIATED;
 
-		spin_unlock_irq(&pool->lock);
+		raw_spin_unlock_irq(&pool->lock);
 		mutex_unlock(&wq_pool_attach_mutex);
 
 		/*
@@ -4917,9 +4930,9 @@ static void unbind_workers(int cpu)
 		 * worker blocking could lead to lengthy stalls.  Kick off
 		 * unbound chain execution of currently pending work items.
 		 */
-		spin_lock_irq(&pool->lock);
+		raw_spin_lock_irq(&pool->lock);
 		wake_up_worker(pool);
-		spin_unlock_irq(&pool->lock);
+		raw_spin_unlock_irq(&pool->lock);
 	}
 }
 
@@ -4946,7 +4959,7 @@ static void rebind_workers(struct worker_pool *pool)
 		WARN_ON_ONCE(set_cpus_allowed_ptr(worker->task,
 						  pool->attrs->cpumask) < 0);
 
-	spin_lock_irq(&pool->lock);
+	raw_spin_lock_irq(&pool->lock);
 
 	pool->flags &= ~POOL_DISASSOCIATED;
 
@@ -4985,7 +4998,7 @@ static void rebind_workers(struct worker_pool *pool)
 		WRITE_ONCE(worker->flags, worker_flags);
 	}
 
-	spin_unlock_irq(&pool->lock);
+	raw_spin_unlock_irq(&pool->lock);
 }
 
 /**
@@ -5898,13 +5911,13 @@ static void __init wq_numa_init(void)
  * items.  Actual work item execution starts only after kthreads can be
  * created and scheduled right before early initcalls.
  */
-int __init workqueue_init_early(void)
+void __init workqueue_init_early(void)
 {
 	int std_nice[NR_STD_WORKER_POOLS] = { 0, HIGHPRI_NICE_LEVEL };
 	int hk_flags = HK_FLAG_DOMAIN | HK_FLAG_WQ;
 	int i, cpu;
 
-	WARN_ON(__alignof__(struct pool_workqueue) < __alignof__(long long));
+	BUILD_BUG_ON(__alignof__(struct pool_workqueue) < __alignof__(long long));
 
 	BUG_ON(!alloc_cpumask_var(&wq_unbound_cpumask, GFP_KERNEL));
 	cpumask_copy(wq_unbound_cpumask, housekeeping_cpumask(hk_flags));
@@ -5965,8 +5978,6 @@ int __init workqueue_init_early(void)
 	       !system_unbound_wq || !system_freezable_wq ||
 	       !system_power_efficient_wq ||
 	       !system_freezable_power_efficient_wq);
-
-	return 0;
 }
 
 /**
@@ -5978,7 +5989,7 @@ int __init workqueue_init_early(void)
  * are no kworkers executing the work items yet.  Populate the worker pools
  * with the initial workers and enable future kworker creations.
  */
-int __init workqueue_init(void)
+void __init workqueue_init(void)
 {
 	struct workqueue_struct *wq;
 	struct worker_pool *pool;
@@ -6025,6 +6036,4 @@ int __init workqueue_init(void)
 
 	wq_online = true;
 	wq_watchdog_init();
-
-	return 0;
 }