Merge branch 'x86/build' into locking/core, to pick up dependent patches and unify jump-label work

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

17 files changed, 180 insertions, 120 deletions

diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 2590700237c13c..138f0302692ec4 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -1844,7 +1844,7 @@ static int btf_check_all_metas(struct btf_verifier_env *env)
 
 	hdr = &btf->hdr;
 	cur = btf->nohdr_data + hdr->type_off;
-	end = btf->nohdr_data + hdr->type_len;
+	end = cur + hdr->type_len;
 
 	env->log_type_id = 1;
 	while (cur < end) {
diff --git a/kernel/bpf/sockmap.c b/kernel/bpf/sockmap.c
index 488ef9663c01f3..0a0f2ec75370d8 100644
--- a/kernel/bpf/sockmap.c
+++ b/kernel/bpf/sockmap.c
@@ -132,6 +132,7 @@ struct smap_psock {
 	struct work_struct gc_work;
 
 	struct proto *sk_proto;
+	void (*save_unhash)(struct sock *sk);
 	void (*save_close)(struct sock *sk, long timeout);
 	void (*save_data_ready)(struct sock *sk);
 	void (*save_write_space)(struct sock *sk);
@@ -143,6 +144,7 @@ static int bpf_tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 static int bpf_tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size);
 static int bpf_tcp_sendpage(struct sock *sk, struct page *page,
 			    int offset, size_t size, int flags);
+static void bpf_tcp_unhash(struct sock *sk);
 static void bpf_tcp_close(struct sock *sk, long timeout);
 
 static inline struct smap_psock *smap_psock_sk(const struct sock *sk)
@@ -184,6 +186,7 @@ static void build_protos(struct proto prot[SOCKMAP_NUM_CONFIGS],
 			 struct proto *base)
 {
 	prot[SOCKMAP_BASE]			= *base;
+	prot[SOCKMAP_BASE].unhash		= bpf_tcp_unhash;
 	prot[SOCKMAP_BASE].close		= bpf_tcp_close;
 	prot[SOCKMAP_BASE].recvmsg		= bpf_tcp_recvmsg;
 	prot[SOCKMAP_BASE].stream_memory_read	= bpf_tcp_stream_read;
@@ -217,6 +220,7 @@ static int bpf_tcp_init(struct sock *sk)
 		return -EBUSY;
 	}
 
+	psock->save_unhash = sk->sk_prot->unhash;
 	psock->save_close = sk->sk_prot->close;
 	psock->sk_proto = sk->sk_prot;
 
@@ -305,30 +309,12 @@ static struct smap_psock_map_entry *psock_map_pop(struct sock *sk,
 	return e;
 }
 
-static void bpf_tcp_close(struct sock *sk, long timeout)
+static void bpf_tcp_remove(struct sock *sk, struct smap_psock *psock)
 {
-	void (*close_fun)(struct sock *sk, long timeout);
 	struct smap_psock_map_entry *e;
 	struct sk_msg_buff *md, *mtmp;
-	struct smap_psock *psock;
 	struct sock *osk;
 
-	lock_sock(sk);
-	rcu_read_lock();
-	psock = smap_psock_sk(sk);
-	if (unlikely(!psock)) {
-		rcu_read_unlock();
-		release_sock(sk);
-		return sk->sk_prot->close(sk, timeout);
-	}
-
-	/* The psock may be destroyed anytime after exiting the RCU critial
-	 * section so by the time we use close_fun the psock may no longer
-	 * be valid. However, bpf_tcp_close is called with the sock lock
-	 * held so the close hook and sk are still valid.
-	 */
-	close_fun = psock->save_close;
-
 	if (psock->cork) {
 		free_start_sg(psock->sock, psock->cork, true);
 		kfree(psock->cork);
@@ -379,6 +365,42 @@ static void bpf_tcp_close(struct sock *sk, long timeout)
 		kfree(e);
 		e = psock_map_pop(sk, psock);
 	}
+}
+
+static void bpf_tcp_unhash(struct sock *sk)
+{
+	void (*unhash_fun)(struct sock *sk);
+	struct smap_psock *psock;
+
+	rcu_read_lock();
+	psock = smap_psock_sk(sk);
+	if (unlikely(!psock)) {
+		rcu_read_unlock();
+		if (sk->sk_prot->unhash)
+			sk->sk_prot->unhash(sk);
+		return;
+	}
+	unhash_fun = psock->save_unhash;
+	bpf_tcp_remove(sk, psock);
+	rcu_read_unlock();
+	unhash_fun(sk);
+}
+
+static void bpf_tcp_close(struct sock *sk, long timeout)
+{
+	void (*close_fun)(struct sock *sk, long timeout);
+	struct smap_psock *psock;
+
+	lock_sock(sk);
+	rcu_read_lock();
+	psock = smap_psock_sk(sk);
+	if (unlikely(!psock)) {
+		rcu_read_unlock();
+		release_sock(sk);
+		return sk->sk_prot->close(sk, timeout);
+	}
+	close_fun = psock->save_close;
+	bpf_tcp_remove(sk, psock);
 	rcu_read_unlock();
 	release_sock(sk);
 	close_fun(sk, timeout);
@@ -2097,8 +2119,12 @@ static int sock_map_update_elem(struct bpf_map *map,
 		return -EINVAL;
 	}
 
+	/* ULPs are currently supported only for TCP sockets in ESTABLISHED
+	 * state.
+	 */
 	if (skops.sk->sk_type != SOCK_STREAM ||
-	    skops.sk->sk_protocol != IPPROTO_TCP) {
+	    skops.sk->sk_protocol != IPPROTO_TCP ||
+	    skops.sk->sk_state != TCP_ESTABLISHED) {
 		fput(socket->file);
 		return -EOPNOTSUPP;
 	}
@@ -2453,6 +2479,16 @@ static int sock_hash_update_elem(struct bpf_map *map,
 		return -EINVAL;
 	}
 
+	/* ULPs are currently supported only for TCP sockets in ESTABLISHED
+	 * state.
+	 */
+	if (skops.sk->sk_type != SOCK_STREAM ||
+	    skops.sk->sk_protocol != IPPROTO_TCP ||
+	    skops.sk->sk_state != TCP_ESTABLISHED) {
+		fput(socket->file);
+		return -EOPNOTSUPP;
+	}
+
 	lock_sock(skops.sk);
 	preempt_disable();
 	rcu_read_lock();
@@ -2543,10 +2579,22 @@ const struct bpf_map_ops sock_hash_ops = {
 	.map_check_btf = map_check_no_btf,
 };
 
+static bool bpf_is_valid_sock_op(struct bpf_sock_ops_kern *ops)
+{
+	return ops->op == BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB ||
+	       ops->op == BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB;
+}
 BPF_CALL_4(bpf_sock_map_update, struct bpf_sock_ops_kern *, bpf_sock,
 	   struct bpf_map *, map, void *, key, u64, flags)
 {
 	WARN_ON_ONCE(!rcu_read_lock_held());
+
+	/* ULPs are currently supported only for TCP sockets in ESTABLISHED
+	 * state. This checks that the sock ops triggering the update is
+	 * one indicating we are (or will be soon) in an ESTABLISHED state.
+	 */
+	if (!bpf_is_valid_sock_op(bpf_sock))
+		return -EOPNOTSUPP;
 	return sock_map_ctx_update_elem(bpf_sock, map, key, flags);
 }
 
@@ -2565,6 +2613,9 @@ BPF_CALL_4(bpf_sock_hash_update, struct bpf_sock_ops_kern *, bpf_sock,
 	   struct bpf_map *, map, void *, key, u64, flags)
 {
 	WARN_ON_ONCE(!rcu_read_lock_held());
+
+	if (!bpf_is_valid_sock_op(bpf_sock))
+		return -EOPNOTSUPP;
 	return sock_hash_ctx_update_elem(bpf_sock, map, key, flags);
 }
 
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 92246117d2b039..bb07e74b34a225 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -3163,7 +3163,7 @@ static int adjust_reg_min_max_vals(struct bpf_verifier_env *env,
 				 * an arbitrary scalar. Disallow all math except
 				 * pointer subtraction
 				 */
-				if (opcode == BPF_SUB){
+				if (opcode == BPF_SUB && env->allow_ptr_leaks) {
 					mark_reg_unknown(env, regs, insn->dst_reg);
 					return 0;
 				}
diff --git a/kernel/dma/Kconfig b/kernel/dma/Kconfig
index 9bd54304446f8b..1b1d63b3634b58 100644
--- a/kernel/dma/Kconfig
+++ b/kernel/dma/Kconfig
@@ -23,6 +23,9 @@ config ARCH_HAS_SYNC_DMA_FOR_CPU
 	bool
 	select NEED_DMA_MAP_STATE
 
+config ARCH_HAS_SYNC_DMA_FOR_CPU_ALL
+	bool
+
 config DMA_DIRECT_OPS
 	bool
 	depends on HAS_DMA
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 2a62b96600ad91..dcb093e7b37770 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -2867,16 +2867,11 @@ static int perf_event_modify_breakpoint(struct perf_event *bp,
 	_perf_event_disable(bp);
 
 	err = modify_user_hw_breakpoint_check(bp, attr, true);
-	if (err) {
-		if (!bp->attr.disabled)
-			_perf_event_enable(bp);
 
-		return err;
-	}
-
-	if (!attr->disabled)
+	if (!bp->attr.disabled)
 		_perf_event_enable(bp);
-	return 0;
+
+	return err;
 }
 
 static int perf_event_modify_attr(struct perf_event *event,
@@ -3940,6 +3935,12 @@ int perf_event_read_local(struct perf_event *event, u64 *value,
 		goto out;
 	}
 
+	/* If this is a pinned event it must be running on this CPU */
+	if (event->attr.pinned && event->oncpu != smp_processor_id()) {
+		ret = -EBUSY;
+		goto out;
+	}
+
 	/*
 	 * If the event is currently on this CPU, its either a per-task event,
 	 * or local to this CPU. Furthermore it means its ACTIVE (otherwise
@@ -5948,6 +5949,7 @@ perf_output_sample_ustack(struct perf_output_handle *handle, u64 dump_size,
 		unsigned long sp;
 		unsigned int rem;
 		u64 dyn_size;
+		mm_segment_t fs;
 
 		/*
 		 * We dump:
@@ -5965,7 +5967,10 @@ 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);
 		rem = __output_copy_user(handle, (void *) sp, dump_size);
+		set_fs(fs);
 		dyn_size = dump_size - rem;
 
 		perf_output_skip(handle, rem);
diff --git a/kernel/events/hw_breakpoint.c b/kernel/events/hw_breakpoint.c
index b3814fce5ecb6b..d6b56180827c73 100644
--- a/kernel/events/hw_breakpoint.c
+++ b/kernel/events/hw_breakpoint.c
@@ -509,6 +509,8 @@ modify_user_hw_breakpoint_check(struct perf_event *bp, struct perf_event_attr *a
  */
 int modify_user_hw_breakpoint(struct perf_event *bp, struct perf_event_attr *attr)
 {
+	int err;
+
 	/*
 	 * modify_user_hw_breakpoint can be invoked with IRQs disabled and hence it
 	 * will not be possible to raise IPIs that invoke __perf_event_disable.
@@ -520,15 +522,12 @@ int modify_user_hw_breakpoint(struct perf_event *bp, struct perf_event_attr *att
 	else
 		perf_event_disable(bp);
 
-	if (!attr->disabled) {
-		int err = modify_user_hw_breakpoint_check(bp, attr, false);
+	err = modify_user_hw_breakpoint_check(bp, attr, false);
 
-		if (err)
-			return err;
+	if (!bp->attr.disabled)
 		perf_event_enable(bp);
-		bp->attr.disabled = 0;
-	}
-	return 0;
+
+	return err;
 }
 EXPORT_SYMBOL_GPL(modify_user_hw_breakpoint);
 
diff --git a/kernel/jump_label.c b/kernel/jump_label.c
index 966a9e9c0f04a9..b28028b08d443a 100644
--- a/kernel/jump_label.c
+++ b/kernel/jump_label.c
@@ -38,23 +38,43 @@ static int jump_label_cmp(const void *a, const void *b)
 	const struct jump_entry *jea = a;
 	const struct jump_entry *jeb = b;
 
-	if (jea->key < jeb->key)
+	if (jump_entry_key(jea) < jump_entry_key(jeb))
 		return -1;
 
-	if (jea->key > jeb->key)
+	if (jump_entry_key(jea) > jump_entry_key(jeb))
 		return 1;
 
 	return 0;
 }
 
+static void jump_label_swap(void *a, void *b, int size)
+{
+	long delta = (unsigned long)a - (unsigned long)b;
+	struct jump_entry *jea = a;
+	struct jump_entry *jeb = b;
+	struct jump_entry tmp = *jea;
+
+	jea->code	= jeb->code - delta;
+	jea->target	= jeb->target - delta;
+	jea->key	= jeb->key - delta;
+
+	jeb->code	= tmp.code + delta;
+	jeb->target	= tmp.target + delta;
+	jeb->key	= tmp.key + delta;
+}
+
 static void
 jump_label_sort_entries(struct jump_entry *start, struct jump_entry *stop)
 {
 	unsigned long size;
+	void *swapfn = NULL;
+
+	if (IS_ENABLED(CONFIG_HAVE_ARCH_JUMP_LABEL_RELATIVE))
+		swapfn = jump_label_swap;
 
 	size = (((unsigned long)stop - (unsigned long)start)
 					/ sizeof(struct jump_entry));
-	sort(start, size, sizeof(struct jump_entry), jump_label_cmp, NULL);
+	sort(start, size, sizeof(struct jump_entry), jump_label_cmp, swapfn);
 }
 
 static void jump_label_update(struct static_key *key);
@@ -266,8 +286,8 @@ EXPORT_SYMBOL_GPL(jump_label_rate_limit);
 
 static int addr_conflict(struct jump_entry *entry, void *start, void *end)
 {
-	if (entry->code <= (unsigned long)end &&
-		entry->code + JUMP_LABEL_NOP_SIZE > (unsigned long)start)
+	if (jump_entry_code(entry) <= (unsigned long)end &&
+	    jump_entry_code(entry) + JUMP_LABEL_NOP_SIZE > (unsigned long)start)
 		return 1;
 
 	return 0;
@@ -326,16 +346,6 @@ static inline void static_key_set_linked(struct static_key *key)
 	key->type |= JUMP_TYPE_LINKED;
 }
 
-static inline struct static_key *jump_entry_key(struct jump_entry *entry)
-{
-	return (struct static_key *)((unsigned long)entry->key & ~1UL);
-}
-
-static bool jump_entry_branch(struct jump_entry *entry)
-{
-	return (unsigned long)entry->key & 1UL;
-}
-
 /***
  * A 'struct static_key' uses a union such that it either points directly
  * to a table of 'struct jump_entry' or to a linked list of modules which in
@@ -360,7 +370,7 @@ static enum jump_label_type jump_label_type(struct jump_entry *entry)
 {
 	struct static_key *key = jump_entry_key(entry);
 	bool enabled = static_key_enabled(key);
-	bool branch = jump_entry_branch(entry);
+	bool branch = jump_entry_is_branch(entry);
 
 	/* See the comment in linux/jump_label.h */
 	return enabled ^ branch;
@@ -368,19 +378,20 @@ static enum jump_label_type jump_label_type(struct jump_entry *entry)
 
 static void __jump_label_update(struct static_key *key,
 				struct jump_entry *entry,
-				struct jump_entry *stop)
+				struct jump_entry *stop,
+				bool init)
 {
 	for (; (entry < stop) && (jump_entry_key(entry) == key); entry++) {
 		/*
 		 * An entry->code of 0 indicates an entry which has been
 		 * disabled because it was in an init text area.
 		 */
-		if (entry->code) {
-			if (kernel_text_address(entry->code))
+		if (init || !jump_entry_is_init(entry)) {
+			if (kernel_text_address(jump_entry_code(entry)))
 				arch_jump_label_transform(entry, jump_label_type(entry));
 			else
 				WARN_ONCE(1, "can't patch jump_label at %pS",
-					  (void *)(unsigned long)entry->code);
+					  (void *)jump_entry_code(entry));
 		}
 	}
 }
@@ -415,6 +426,9 @@ void __init jump_label_init(void)
 		if (jump_label_type(iter) == JUMP_LABEL_NOP)
 			arch_jump_label_transform_static(iter, JUMP_LABEL_NOP);
 
+		if (init_section_contains((void *)jump_entry_code(iter), 1))
+			jump_entry_set_init(iter);
+
 		iterk = jump_entry_key(iter);
 		if (iterk == key)
 			continue;
@@ -427,26 +441,13 @@ void __init jump_label_init(void)
 	cpus_read_unlock();
 }
 
-/* Disable any jump label entries in __init/__exit code */
-void __init jump_label_invalidate_initmem(void)
-{
-	struct jump_entry *iter_start = __start___jump_table;
-	struct jump_entry *iter_stop = __stop___jump_table;
-	struct jump_entry *iter;
-
-	for (iter = iter_start; iter < iter_stop; iter++) {
-		if (init_section_contains((void *)(unsigned long)iter->code, 1))
-			iter->code = 0;
-	}
-}
-
 #ifdef CONFIG_MODULES
 
 static enum jump_label_type jump_label_init_type(struct jump_entry *entry)
 {
 	struct static_key *key = jump_entry_key(entry);
 	bool type = static_key_type(key);
-	bool branch = jump_entry_branch(entry);
+	bool branch = jump_entry_is_branch(entry);
 
 	/* See the comment in linux/jump_label.h */
 	return type ^ branch;
@@ -519,7 +520,8 @@ static void __jump_label_mod_update(struct static_key *key)
 			stop = __stop___jump_table;
 		else
 			stop = m->jump_entries + m->num_jump_entries;
-		__jump_label_update(key, mod->entries, stop);
+		__jump_label_update(key, mod->entries, stop,
+				    m && m->state == MODULE_STATE_COMING);
 	}
 }
 
@@ -565,12 +567,15 @@ static int jump_label_add_module(struct module *mod)
 	for (iter = iter_start; iter < iter_stop; iter++) {
 		struct static_key *iterk;
 
+		if (within_module_init(jump_entry_code(iter), mod))
+			jump_entry_set_init(iter);
+
 		iterk = jump_entry_key(iter);
 		if (iterk == key)
 			continue;
 
 		key = iterk;
-		if (within_module(iter->key, mod)) {
+		if (within_module((unsigned long)key, mod)) {
 			static_key_set_entries(key, iter);
 			continue;
 		}
@@ -600,7 +605,7 @@ static int jump_label_add_module(struct module *mod)
 
 		/* Only update if we've changed from our initial state */
 		if (jump_label_type(iter) != jump_label_init_type(iter))
-			__jump_label_update(key, iter, iter_stop);
+			__jump_label_update(key, iter, iter_stop, true);
 	}
 
 	return 0;
@@ -620,7 +625,7 @@ static void jump_label_del_module(struct module *mod)
 
 		key = jump_entry_key(iter);
 
-		if (within_module(iter->key, mod))
+		if (within_module((unsigned long)key, mod))
 			continue;
 
 		/* No memory during module load */
@@ -656,19 +661,6 @@ static void jump_label_del_module(struct module *mod)
 	}
 }
 
-/* Disable any jump label entries in module init code */
-static void jump_label_invalidate_module_init(struct module *mod)
-{
-	struct jump_entry *iter_start = mod->jump_entries;
-	struct jump_entry *iter_stop = iter_start + mod->num_jump_entries;
-	struct jump_entry *iter;
-
-	for (iter = iter_start; iter < iter_stop; iter++) {
-		if (within_module_init(iter->code, mod))
-			iter->code = 0;
-	}
-}
-
 static int
 jump_label_module_notify(struct notifier_block *self, unsigned long val,
 			 void *data)
@@ -690,9 +682,6 @@ jump_label_module_notify(struct notifier_block *self, unsigned long val,
 	case MODULE_STATE_GOING:
 		jump_label_del_module(mod);
 		break;
-	case MODULE_STATE_LIVE:
-		jump_label_invalidate_module_init(mod);
-		break;
 	}
 
 	jump_label_unlock();
@@ -762,7 +751,8 @@ static void jump_label_update(struct static_key *key)
 	entry = static_key_entries(key);
 	/* if there are no users, entry can be NULL */
 	if (entry)
-		__jump_label_update(key, entry, stop);
+		__jump_label_update(key, entry, stop,
+				    system_state < SYSTEM_RUNNING);
 }
 
 #ifdef CONFIG_STATIC_KEYS_SELFTEST
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index 8a732c8566242a..be76f476c63fbe 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -55,7 +55,6 @@
 
 #include "lockdep_internals.h"
 
-#include <trace/events/preemptirq.h>
 #define CREATE_TRACE_POINTS
 #include <trace/events/lock.h>
 
diff --git a/kernel/locking/test-ww_mutex.c b/kernel/locking/test-ww_mutex.c
index 5b915b370d5a83..0be047dbd8971d 100644
--- a/kernel/locking/test-ww_mutex.c
+++ b/kernel/locking/test-ww_mutex.c
@@ -324,7 +324,7 @@ static int __test_cycle(unsigned int nthreads)
 		if (!cycle->result)
 			continue;
 
-		pr_err("cylic deadlock not resolved, ret[%d/%d] = %d\n",
+		pr_err("cyclic deadlock not resolved, ret[%d/%d] = %d\n",
 		       n, nthreads, cycle->result);
 		ret = -EINVAL;
 		break;
diff --git a/kernel/module.c b/kernel/module.c
index 6746c85511fefe..49a4058915870c 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -3317,6 +3317,15 @@ static struct module *layout_and_allocate(struct load_info *info, int flags)
 	ndx = find_sec(info, ".data..ro_after_init");
 	if (ndx)
 		info->sechdrs[ndx].sh_flags |= SHF_RO_AFTER_INIT;
+	/*
+	 * Mark the __jump_table section as ro_after_init as well: these data
+	 * structures are never modified, with the exception of entries that
+	 * refer to code in the __init section, which are annotated as such
+	 * at module load time.
+	 */
+	ndx = find_sec(info, "__jump_table");
+	if (ndx)
+		info->sechdrs[ndx].sh_flags |= SHF_RO_AFTER_INIT;
 
 	/* Determine total sizes, and put offsets in sh_entsize.  For now
 	   this is done generically; there doesn't appear to be any
diff --git a/kernel/pid.c b/kernel/pid.c
index de1cfc4f75a2eb..cdf63e53a01425 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -195,7 +195,7 @@ struct pid *alloc_pid(struct pid_namespace *ns)
 		idr_preload_end();
 
 		if (nr < 0) {
-			retval = nr;
+			retval = (nr == -ENOSPC) ? -EAGAIN : nr;
 			goto out_free;
 		}
 
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index fd6f8ed28e010a..9bf5404397e0b2 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -351,7 +351,6 @@ static int console_msg_format = MSG_FORMAT_DEFAULT;
  */
 
 enum log_flags {
-	LOG_NOCONS	= 1,	/* suppress print, do not print to console */
 	LOG_NEWLINE	= 2,	/* text ended with a newline */
 	LOG_PREFIX	= 4,	/* text started with a prefix */
 	LOG_CONT	= 8,	/* text is a fragment of a continuation line */
@@ -1881,9 +1880,6 @@ int vprintk_store(int facility, int level,
 	if (dict)
 		lflags |= LOG_PREFIX|LOG_NEWLINE;
 
-	if (suppress_message_printing(level))
-		lflags |= LOG_NOCONS;
-
 	return log_output(facility, level, lflags,
 			  dict, dictlen, text, text_len);
 }
@@ -2032,6 +2028,7 @@ static void call_console_drivers(const char *ext_text, size_t ext_len,
 				 const char *text, size_t len) {}
 static size_t msg_print_text(const struct printk_log *msg,
 			     bool syslog, char *buf, size_t size) { return 0; }
+static bool suppress_message_printing(int level) { return false; }
 
 #endif /* CONFIG_PRINTK */
 
@@ -2368,10 +2365,11 @@ skip:
 			break;
 
 		msg = log_from_idx(console_idx);
-		if (msg->flags & LOG_NOCONS) {
+		if (suppress_message_printing(msg->level)) {
 			/*
-			 * Skip record if !ignore_loglevel, and
-			 * record has level above the console loglevel.
+			 * Skip record we have buffered and already printed
+			 * directly to the console when we received it, and
+			 * record that has level above the console loglevel.
 			 */
 			console_idx = log_next(console_idx);
 			console_seq++;
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 60caf1fb94e057..6383aa6a60ca02 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -89,12 +89,12 @@ struct static_key sched_feat_keys[__SCHED_FEAT_NR] = {
 
 static void sched_feat_disable(int i)
 {
-	static_key_disable(&sched_feat_keys[i]);
+	static_key_disable_cpuslocked(&sched_feat_keys[i]);
 }
 
 static void sched_feat_enable(int i)
 {
-	static_key_enable(&sched_feat_keys[i]);
+	static_key_enable_cpuslocked(&sched_feat_keys[i]);
 }
 #else
 static void sched_feat_disable(int i) { };
@@ -146,9 +146,11 @@ sched_feat_write(struct file *filp, const char __user *ubuf,
 
 	/* Ensure the static_key remains in a consistent state */
 	inode = file_inode(filp);
+	cpus_read_lock();
 	inode_lock(inode);
 	ret = sched_feat_set(cmp);
 	inode_unlock(inode);
+	cpus_read_unlock();
 	if (ret < 0)
 		return ret;
 
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index b39fb596f6c1e8..f808ddf2a868e7 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -3362,6 +3362,7 @@ update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq)
  * attach_entity_load_avg - attach this entity to its cfs_rq load avg
  * @cfs_rq: cfs_rq to attach to
  * @se: sched_entity to attach
+ * @flags: migration hints
  *
  * Must call update_cfs_rq_load_avg() before this, since we rely on
  * cfs_rq->avg.last_update_time being current.
@@ -7263,6 +7264,7 @@ static void update_blocked_averages(int cpu)
 {
 	struct rq *rq = cpu_rq(cpu);
 	struct cfs_rq *cfs_rq, *pos;
+	const struct sched_class *curr_class;
 	struct rq_flags rf;
 	bool done = true;
 
@@ -7299,8 +7301,10 @@ static void update_blocked_averages(int cpu)
 		if (cfs_rq_has_blocked(cfs_rq))
 			done = false;
 	}
-	update_rt_rq_load_avg(rq_clock_task(rq), rq, 0);
-	update_dl_rq_load_avg(rq_clock_task(rq), rq, 0);
+
+	curr_class = rq->curr->sched_class;
+	update_rt_rq_load_avg(rq_clock_task(rq), rq, curr_class == &rt_sched_class);
+	update_dl_rq_load_avg(rq_clock_task(rq), rq, curr_class == &dl_sched_class);
 	update_irq_load_avg(rq, 0);
 	/* Don't need periodic decay once load/util_avg are null */
 	if (others_have_blocked(rq))
@@ -7365,13 +7369,16 @@ static inline void update_blocked_averages(int cpu)
 {
 	struct rq *rq = cpu_rq(cpu);
 	struct cfs_rq *cfs_rq = &rq->cfs;
+	const struct sched_class *curr_class;
 	struct rq_flags rf;
 
 	rq_lock_irqsave(rq, &rf);
 	update_rq_clock(rq);
 	update_cfs_rq_load_avg(cfs_rq_clock_task(cfs_rq), cfs_rq);
-	update_rt_rq_load_avg(rq_clock_task(rq), rq, 0);
-	update_dl_rq_load_avg(rq_clock_task(rq), rq, 0);
+
+	curr_class = rq->curr->sched_class;
+	update_rt_rq_load_avg(rq_clock_task(rq), rq, curr_class == &rt_sched_class);
+	update_dl_rq_load_avg(rq_clock_task(rq), rq, curr_class == &dl_sched_class);
 	update_irq_load_avg(rq, 0);
 #ifdef CONFIG_NO_HZ_COMMON
 	rq->last_blocked_load_update_tick = jiffies;
@@ -7482,10 +7489,10 @@ static inline int get_sd_load_idx(struct sched_domain *sd,
 	return load_idx;
 }
 
-static unsigned long scale_rt_capacity(int cpu)
+static unsigned long scale_rt_capacity(struct sched_domain *sd, int cpu)
 {
 	struct rq *rq = cpu_rq(cpu);
-	unsigned long max = arch_scale_cpu_capacity(NULL, cpu);
+	unsigned long max = arch_scale_cpu_capacity(sd, cpu);
 	unsigned long used, free;
 	unsigned long irq;
 
@@ -7507,7 +7514,7 @@ static unsigned long scale_rt_capacity(int cpu)
 
 static void update_cpu_capacity(struct sched_domain *sd, int cpu)
 {
-	unsigned long capacity = scale_rt_capacity(cpu);
+	unsigned long capacity = scale_rt_capacity(sd, cpu);
 	struct sched_group *sdg = sd->groups;
 
 	cpu_rq(cpu)->cpu_capacity_orig = arch_scale_cpu_capacity(sd, cpu);
@@ -8269,7 +8276,7 @@ static struct sched_group *find_busiest_group(struct lb_env *env)
 force_balance:
 	/* Looks like there is an imbalance. Compute it */
 	calculate_imbalance(env, &sds);
-	return sds.busiest;
+	return env->imbalance ? sds.busiest : NULL;
 
 out_balanced:
 	env->imbalance = 0;
@@ -9638,7 +9645,8 @@ static inline bool vruntime_normalized(struct task_struct *p)
 	 * - A task which has been woken up by try_to_wake_up() and
 	 *   waiting for actually being woken up by sched_ttwu_pending().
 	 */
-	if (!se->sum_exec_runtime || p->state == TASK_WAKING)
+	if (!se->sum_exec_runtime ||
+	    (p->state == TASK_WAKING && p->sched_remote_wakeup))
 		return true;
 
 	return false;
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index 56a0fed30c0a87..505a41c42b9610 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -1295,7 +1295,7 @@ static void init_numa_topology_type(void)
 
 	n = sched_max_numa_distance;
 
-	if (sched_domains_numa_levels <= 1) {
+	if (sched_domains_numa_levels <= 2) {
 		sched_numa_topology_type = NUMA_DIRECT;
 		return;
 	}
@@ -1380,9 +1380,6 @@ void sched_init_numa(void)
 			break;
 	}
 
-	if (!level)
-		return;
-
 	/*
 	 * 'level' contains the number of unique distances
 	 *
diff --git a/kernel/sys.c b/kernel/sys.c
index cf5c67533ff1e1..123bd73046ec6b 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -71,9 +71,6 @@
 #include <asm/io.h>
 #include <asm/unistd.h>
 
-/* Hardening for Spectre-v1 */
-#include <linux/nospec.h>
-
 #include "uid16.h"
 
 #ifndef SET_UNALIGN_CTL
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 1d92d4a982fd46..65bd4616220db7 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -1546,6 +1546,8 @@ rb_remove_pages(struct ring_buffer_per_cpu *cpu_buffer, unsigned long nr_pages)
 	tmp_iter_page = first_page;
 
 	do {
+		cond_resched();
+
 		to_remove_page = tmp_iter_page;
 		rb_inc_page(cpu_buffer, &tmp_iter_page);