Merge branch 'linus' into x86/apic, to resolve conflicts

Conflicts:
	arch/x86/include/asm/x2apic.h

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

154 files changed, 492 insertions, 240 deletions

diff --git a/kernel/Makefile b/kernel/Makefile
index ed470aac53da..172d151d429c 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 #
 # Makefile for the linux kernel.
 #
diff --git a/kernel/acct.c b/kernel/acct.c
index 5e72af29ab73..6670fbd3e466 100644
--- a/kernel/acct.c
+++ b/kernel/acct.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  *  linux/kernel/acct.c
  *
diff --git a/kernel/audit_tree.c b/kernel/audit_tree.c
index 011d46e5f73f..d4b050d9a66e 100644
--- a/kernel/audit_tree.c
+++ b/kernel/audit_tree.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include "audit.h"
 #include <linux/fsnotify_backend.h>
 #include <linux/namei.h>
diff --git a/kernel/bounds.c b/kernel/bounds.c
index e1d1d1952bfa..c373e887c066 100644
--- a/kernel/bounds.c
+++ b/kernel/bounds.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Generate definitions needed by the preprocessor.
  * This code generates raw asm output which is post-processed
diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile
index 897daa005b23..af3ab6164ff5 100644
--- a/kernel/bpf/Makefile
+++ b/kernel/bpf/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 obj-y := core.o
 
 obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index 98c0f00c3f5e..e2636737b69b 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -98,7 +98,7 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr)
 	array_size += (u64) attr->max_entries * elem_size * num_possible_cpus();
 
 	if (array_size >= U32_MAX - PAGE_SIZE ||
-	    elem_size > PCPU_MIN_UNIT_SIZE || bpf_array_alloc_percpu(array)) {
+	    bpf_array_alloc_percpu(array)) {
 		bpf_map_area_free(array);
 		return ERR_PTR(-ENOMEM);
 	}
diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c
index e093d9a2c4dd..e745d6a88224 100644
--- a/kernel/bpf/devmap.c
+++ b/kernel/bpf/devmap.c
@@ -69,7 +69,7 @@ static LIST_HEAD(dev_map_list);
 
 static u64 dev_map_bitmap_size(const union bpf_attr *attr)
 {
-	return BITS_TO_LONGS(attr->max_entries) * sizeof(unsigned long);
+	return BITS_TO_LONGS((u64) attr->max_entries) * sizeof(unsigned long);
 }
 
 static struct bpf_map *dev_map_alloc(union bpf_attr *attr)
@@ -78,6 +78,9 @@ static struct bpf_map *dev_map_alloc(union bpf_attr *attr)
 	int err = -EINVAL;
 	u64 cost;
 
+	if (!capable(CAP_NET_ADMIN))
+		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)
@@ -111,8 +114,9 @@ static struct bpf_map *dev_map_alloc(union bpf_attr *attr)
 	err = -ENOMEM;
 
 	/* A per cpu bitfield with a bit per possible net device */
-	dtab->flush_needed = __alloc_percpu(dev_map_bitmap_size(attr),
-					    __alignof__(unsigned long));
+	dtab->flush_needed = __alloc_percpu_gfp(dev_map_bitmap_size(attr),
+						__alignof__(unsigned long),
+						GFP_KERNEL | __GFP_NOWARN);
 	if (!dtab->flush_needed)
 		goto free_dtab;
 
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index 431126f31ea3..6533f08d1238 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -317,10 +317,6 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr)
 		 */
 		goto free_htab;
 
-	if (percpu && round_up(htab->map.value_size, 8) > PCPU_MIN_UNIT_SIZE)
-		/* make sure the size for pcpu_alloc() is reasonable */
-		goto free_htab;
-
 	htab->elem_size = sizeof(struct htab_elem) +
 			  round_up(htab->map.key_size, 8);
 	if (percpu)
diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c
index e833ed914358..be1dde967208 100644
--- a/kernel/bpf/inode.c
+++ b/kernel/bpf/inode.c
@@ -363,6 +363,7 @@ out:
 	putname(pname);
 	return ret;
 }
+EXPORT_SYMBOL_GPL(bpf_obj_get_user);
 
 static void bpf_evict_inode(struct inode *inode)
 {
diff --git a/kernel/bpf/sockmap.c b/kernel/bpf/sockmap.c
index 6424ce0e4969..dbd7b322a86b 100644
--- a/kernel/bpf/sockmap.c
+++ b/kernel/bpf/sockmap.c
@@ -39,6 +39,7 @@
 #include <linux/workqueue.h>
 #include <linux/list.h>
 #include <net/strparser.h>
+#include <net/tcp.h>
 
 struct bpf_stab {
 	struct bpf_map map;
@@ -92,21 +93,45 @@ static inline struct smap_psock *smap_psock_sk(const struct sock *sk)
 	return rcu_dereference_sk_user_data(sk);
 }
 
+/* compute the linear packet data range [data, data_end) for skb when
+ * sk_skb type programs are in use.
+ */
+static inline void bpf_compute_data_end_sk_skb(struct sk_buff *skb)
+{
+	TCP_SKB_CB(skb)->bpf.data_end = skb->data + skb_headlen(skb);
+}
+
+enum __sk_action {
+	__SK_DROP = 0,
+	__SK_PASS,
+	__SK_REDIRECT,
+};
+
 static int smap_verdict_func(struct smap_psock *psock, struct sk_buff *skb)
 {
 	struct bpf_prog *prog = READ_ONCE(psock->bpf_verdict);
 	int rc;
 
 	if (unlikely(!prog))
-		return SK_DROP;
+		return __SK_DROP;
 
 	skb_orphan(skb);
+	/* We need to ensure that BPF metadata for maps is also cleared
+	 * when we orphan the skb so that we don't have the possibility
+	 * to reference a stale map.
+	 */
+	TCP_SKB_CB(skb)->bpf.map = NULL;
 	skb->sk = psock->sock;
-	bpf_compute_data_end(skb);
+	bpf_compute_data_end_sk_skb(skb);
+	preempt_disable();
 	rc = (*prog->bpf_func)(skb, prog->insnsi);
+	preempt_enable();
 	skb->sk = NULL;
 
-	return rc;
+	/* Moving return codes from UAPI namespace into internal namespace */
+	return rc == SK_PASS ?
+		(TCP_SKB_CB(skb)->bpf.map ? __SK_REDIRECT : __SK_PASS) :
+		__SK_DROP;
 }
 
 static void smap_do_verdict(struct smap_psock *psock, struct sk_buff *skb)
@@ -114,17 +139,10 @@ static void smap_do_verdict(struct smap_psock *psock, struct sk_buff *skb)
 	struct sock *sk;
 	int rc;
 
-	/* Because we use per cpu values to feed input from sock redirect
-	 * in BPF program to do_sk_redirect_map() call we need to ensure we
-	 * are not preempted. RCU read lock is not sufficient in this case
-	 * with CONFIG_PREEMPT_RCU enabled so we must be explicit here.
-	 */
-	preempt_disable();
 	rc = smap_verdict_func(psock, skb);
 	switch (rc) {
-	case SK_REDIRECT:
-		sk = do_sk_redirect_map();
-		preempt_enable();
+	case __SK_REDIRECT:
+		sk = do_sk_redirect_map(skb);
 		if (likely(sk)) {
 			struct smap_psock *peer = smap_psock_sk(sk);
 
@@ -139,10 +157,8 @@ static void smap_do_verdict(struct smap_psock *psock, struct sk_buff *skb)
 			}
 		}
 	/* Fall through and free skb otherwise */
-	case SK_DROP:
+	case __SK_DROP:
 	default:
-		if (rc != SK_REDIRECT)
-			preempt_enable();
 		kfree_skb(skb);
 	}
 }
@@ -369,7 +385,7 @@ static int smap_parse_func_strparser(struct strparser *strp,
 	 * any socket yet.
 	 */
 	skb->sk = psock->sock;
-	bpf_compute_data_end(skb);
+	bpf_compute_data_end_sk_skb(skb);
 	rc = (*prog->bpf_func)(skb, prog->insnsi);
 	skb->sk = NULL;
 	rcu_read_unlock();
@@ -487,6 +503,9 @@ static struct bpf_map *sock_map_alloc(union bpf_attr *attr)
 	int err = -EINVAL;
 	u64 cost;
 
+	if (!capable(CAP_NET_ADMIN))
+		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)
@@ -840,6 +859,12 @@ static int sock_map_update_elem(struct bpf_map *map,
 		return -EINVAL;
 	}
 
+	if (skops.sk->sk_type != SOCK_STREAM ||
+	    skops.sk->sk_protocol != IPPROTO_TCP) {
+		fput(socket->file);
+		return -EOPNOTSUPP;
+	}
+
 	err = sock_map_ctx_update_elem(&skops, map, key, flags);
 	fput(socket->file);
 	return err;
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index b914fbe1383e..c48ca2a34b5e 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -653,6 +653,10 @@ static void mark_reg_read(const struct bpf_verifier_state *state, u32 regno)
 {
 	struct bpf_verifier_state *parent = state->parent;
 
+	if (regno == BPF_REG_FP)
+		/* We don't need to worry about FP liveness because it's read-only */
+		return;
+
 	while (parent) {
 		/* if read wasn't screened by an earlier write ... */
 		if (state->regs[regno].live & REG_LIVE_WRITTEN)
@@ -1112,7 +1116,12 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
 		/* ctx accesses must be at a fixed offset, so that we can
 		 * determine what type of data were returned.
 		 */
-		if (!tnum_is_const(reg->var_off)) {
+		if (reg->off) {
+			verbose("dereference of modified ctx ptr R%d off=%d+%d, ctx+const is allowed, ctx+const+const is not\n",
+				regno, reg->off, off - reg->off);
+			return -EACCES;
+		}
+		if (!tnum_is_const(reg->var_off) || reg->var_off.value) {
 			char tn_buf[48];
 
 			tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
@@ -1120,7 +1129,6 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
 				tn_buf, off, size);
 			return -EACCES;
 		}
-		off += reg->var_off.value;
 		err = check_ctx_access(env, insn_idx, off, size, t, &reg_type);
 		if (!err && t == BPF_READ && value_regno >= 0) {
 			/* ctx access returns either a scalar, or a
@@ -2345,6 +2353,7 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
 				 * copy register state to dest reg
 				 */
 				regs[insn->dst_reg] = regs[insn->src_reg];
+				regs[insn->dst_reg].live |= REG_LIVE_WRITTEN;
 			} else {
 				/* R1 = (u32) R2 */
 				if (is_pointer_value(env, insn->src_reg)) {
@@ -2421,12 +2430,15 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
 }
 
 static void find_good_pkt_pointers(struct bpf_verifier_state *state,
-				   struct bpf_reg_state *dst_reg)
+				   struct bpf_reg_state *dst_reg,
+				   bool range_right_open)
 {
 	struct bpf_reg_state *regs = state->regs, *reg;
+	u16 new_range;
 	int i;
 
-	if (dst_reg->off < 0)
+	if (dst_reg->off < 0 ||
+	    (dst_reg->off == 0 && range_right_open))
 		/* This doesn't give us any range */
 		return;
 
@@ -2437,9 +2449,13 @@ static void find_good_pkt_pointers(struct bpf_verifier_state *state,
 		 */
 		return;
 
-	/* LLVM can generate four kind of checks:
+	new_range = dst_reg->off;
+	if (range_right_open)
+		new_range--;
+
+	/* Examples for register markings:
 	 *
-	 * Type 1/2:
+	 * pkt_data in dst register:
 	 *
 	 *   r2 = r3;
 	 *   r2 += 8;
@@ -2456,7 +2472,7 @@ static void find_good_pkt_pointers(struct bpf_verifier_state *state,
 	 *     r2=pkt(id=n,off=8,r=0)
 	 *     r3=pkt(id=n,off=0,r=0)
 	 *
-	 * Type 3/4:
+	 * pkt_data in src register:
 	 *
 	 *   r2 = r3;
 	 *   r2 += 8;
@@ -2474,7 +2490,9 @@ static void find_good_pkt_pointers(struct bpf_verifier_state *state,
 	 *     r3=pkt(id=n,off=0,r=0)
 	 *
 	 * Find register r3 and mark its range as r3=pkt(id=n,off=0,r=8)
-	 * so that range of bytes [r3, r3 + 8) is safe to access.
+	 * or r3=pkt(id=n,off=0,r=8-1), so that range of bytes [r3, r3 + 8)
+	 * and [r3, r3 + 8-1) respectively is safe to access depending on
+	 * the check.
 	 */
 
 	/* If our ids match, then we must have the same max_value.  And we
@@ -2485,14 +2503,14 @@ static void find_good_pkt_pointers(struct bpf_verifier_state *state,
 	for (i = 0; i < MAX_BPF_REG; i++)
 		if (regs[i].type == PTR_TO_PACKET && regs[i].id == dst_reg->id)
 			/* keep the maximum range already checked */
-			regs[i].range = max_t(u16, regs[i].range, dst_reg->off);
+			regs[i].range = max(regs[i].range, new_range);
 
 	for (i = 0; i < MAX_BPF_STACK; i += BPF_REG_SIZE) {
 		if (state->stack_slot_type[i] != STACK_SPILL)
 			continue;
 		reg = &state->spilled_regs[i / BPF_REG_SIZE];
 		if (reg->type == PTR_TO_PACKET && reg->id == dst_reg->id)
-			reg->range = max_t(u16, reg->range, dst_reg->off);
+			reg->range = max(reg->range, new_range);
 	}
 }
 
@@ -2856,19 +2874,43 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env,
 	} else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JGT &&
 		   dst_reg->type == PTR_TO_PACKET &&
 		   regs[insn->src_reg].type == PTR_TO_PACKET_END) {
-		find_good_pkt_pointers(this_branch, dst_reg);
+		/* pkt_data' > pkt_end */
+		find_good_pkt_pointers(this_branch, dst_reg, false);
+	} else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JGT &&
+		   dst_reg->type == PTR_TO_PACKET_END &&
+		   regs[insn->src_reg].type == PTR_TO_PACKET) {
+		/* pkt_end > pkt_data' */
+		find_good_pkt_pointers(other_branch, &regs[insn->src_reg], true);
 	} else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JLT &&
 		   dst_reg->type == PTR_TO_PACKET &&
 		   regs[insn->src_reg].type == PTR_TO_PACKET_END) {
-		find_good_pkt_pointers(other_branch, dst_reg);
+		/* pkt_data' < pkt_end */
+		find_good_pkt_pointers(other_branch, dst_reg, true);
+	} else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JLT &&
+		   dst_reg->type == PTR_TO_PACKET_END &&
+		   regs[insn->src_reg].type == PTR_TO_PACKET) {
+		/* pkt_end < pkt_data' */
+		find_good_pkt_pointers(this_branch, &regs[insn->src_reg], false);
+	} else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JGE &&
+		   dst_reg->type == PTR_TO_PACKET &&
+		   regs[insn->src_reg].type == PTR_TO_PACKET_END) {
+		/* pkt_data' >= pkt_end */
+		find_good_pkt_pointers(this_branch, dst_reg, true);
 	} else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JGE &&
 		   dst_reg->type == PTR_TO_PACKET_END &&
 		   regs[insn->src_reg].type == PTR_TO_PACKET) {
-		find_good_pkt_pointers(other_branch, &regs[insn->src_reg]);
+		/* pkt_end >= pkt_data' */
+		find_good_pkt_pointers(other_branch, &regs[insn->src_reg], false);
+	} else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JLE &&
+		   dst_reg->type == PTR_TO_PACKET &&
+		   regs[insn->src_reg].type == PTR_TO_PACKET_END) {
+		/* pkt_data' <= pkt_end */
+		find_good_pkt_pointers(other_branch, dst_reg, false);
 	} else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JLE &&
 		   dst_reg->type == PTR_TO_PACKET_END &&
 		   regs[insn->src_reg].type == PTR_TO_PACKET) {
-		find_good_pkt_pointers(this_branch, &regs[insn->src_reg]);
+		/* pkt_end <= pkt_data' */
+		find_good_pkt_pointers(this_branch, &regs[insn->src_reg], true);
 	} else if (is_pointer_value(env, insn->dst_reg)) {
 		verbose("R%d pointer comparison prohibited\n", insn->dst_reg);
 		return -EACCES;
diff --git a/kernel/capability.c b/kernel/capability.c
index f97fe77ceb88..1e1c0236f55b 100644
--- a/kernel/capability.c
+++ b/kernel/capability.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * linux/kernel/capability.c
  *
diff --git a/kernel/cgroup/Makefile b/kernel/cgroup/Makefile
index ce693ccb8c58..ae448f7632cc 100644
--- a/kernel/cgroup/Makefile
+++ b/kernel/cgroup/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 obj-y := cgroup.o namespace.o cgroup-v1.o
 
 obj-$(CONFIG_CGROUP_FREEZER) += freezer.o
diff --git a/kernel/cgroup/cgroup-internal.h b/kernel/cgroup/cgroup-internal.h
index 5151ff256c29..bf54ade001be 100644
--- a/kernel/cgroup/cgroup-internal.h
+++ b/kernel/cgroup/cgroup-internal.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __CGROUP_INTERNAL_H
 #define __CGROUP_INTERNAL_H
 
diff --git a/kernel/cgroup/debug.c b/kernel/cgroup/debug.c
index f661b4cc5efd..5f780d8f6a9d 100644
--- a/kernel/cgroup/debug.c
+++ b/kernel/cgroup/debug.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Debug controller
  *
diff --git a/kernel/cgroup/namespace.c b/kernel/cgroup/namespace.c
index 66129eb4371d..b05f1dd58a62 100644
--- a/kernel/cgroup/namespace.c
+++ b/kernel/cgroup/namespace.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include "cgroup-internal.h"
 
 #include <linux/sched/task.h>
diff --git a/kernel/cpu.c b/kernel/cpu.c
index d851df22f5c5..04892a82f6ac 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -632,6 +632,11 @@ cpuhp_invoke_ap_callback(int cpu, enum cpuhp_state state, bool bringup,
 		__cpuhp_kick_ap(st);
 	}
 
+	/*
+	 * Clean up the leftovers so the next hotplug operation wont use stale
+	 * data.
+	 */
+	st->node = st->last = NULL;
 	return ret;
 }
 
diff --git a/kernel/dma.c b/kernel/dma.c
index 6c6262f86c17..3506fc34a712 100644
--- a/kernel/dma.c
+++ b/kernel/dma.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * linux/kernel/dma.c: A DMA channel allocator. Inspired by linux/kernel/irq.c.
  *
diff --git a/kernel/elfcore.c b/kernel/elfcore.c
index e556751d15d9..fc482c8e0bd8 100644
--- a/kernel/elfcore.c
+++ b/kernel/elfcore.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <linux/elf.h>
 #include <linux/fs.h>
 #include <linux/mm.h>
diff --git a/kernel/events/Makefile b/kernel/events/Makefile
index 2925188f50ea..3c022e33c109 100644
--- a/kernel/events/Makefile
+++ b/kernel/events/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 ifdef CONFIG_FUNCTION_TRACER
 CFLAGS_REMOVE_core.o = $(CC_FLAGS_FTRACE)
 endif
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 6bc21e202ae4..10cdb9c26b5d 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -662,7 +662,7 @@ static inline void update_cgrp_time_from_event(struct perf_event *event)
 	/*
 	 * Do not update time when cgroup is not active
 	 */
-	if (cgrp == event->cgrp)
+       if (cgroup_is_descendant(cgrp->css.cgroup, event->cgrp->css.cgroup))
 		__update_cgrp_time(event->cgrp);
 }
 
@@ -901,9 +901,11 @@ list_update_cgroup_event(struct perf_event *event,
 	cpuctx_entry = &cpuctx->cgrp_cpuctx_entry;
 	/* cpuctx->cgrp is NULL unless a cgroup event is active in this CPU .*/
 	if (add) {
+		struct perf_cgroup *cgrp = perf_cgroup_from_task(current, ctx);
+
 		list_add(cpuctx_entry, this_cpu_ptr(&cgrp_cpuctx_list));
-		if (perf_cgroup_from_task(current, ctx) == event->cgrp)
-			cpuctx->cgrp = event->cgrp;
+		if (cgroup_is_descendant(cgrp->css.cgroup, event->cgrp->css.cgroup))
+			cpuctx->cgrp = cgrp;
 	} else {
 		list_del(cpuctx_entry);
 		cpuctx->cgrp = NULL;
@@ -8955,6 +8957,14 @@ static struct perf_cpu_context __percpu *find_pmu_context(int ctxn)
 
 static void free_pmu_context(struct pmu *pmu)
 {
+	/*
+	 * Static contexts such as perf_sw_context have a global lifetime
+	 * and may be shared between different PMUs. Avoid freeing them
+	 * when a single PMU is going away.
+	 */
+	if (pmu->task_ctx_nr > perf_invalid_context)
+		return;
+
 	mutex_lock(&pmus_lock);
 	free_percpu(pmu->pmu_cpu_context);
 	mutex_unlock(&pmus_lock);
diff --git a/kernel/events/internal.h b/kernel/events/internal.h
index 843e97047335..09b1537ae06c 100644
--- a/kernel/events/internal.h
+++ b/kernel/events/internal.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _KERNEL_EVENTS_INTERNAL_H
 #define _KERNEL_EVENTS_INTERNAL_H
 
diff --git a/kernel/exec_domain.c b/kernel/exec_domain.c
index 6873bb3e6b7e..0975b0268545 100644
--- a/kernel/exec_domain.c
+++ b/kernel/exec_domain.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Handling of different ABIs (personalities).
  *
diff --git a/kernel/exit.c b/kernel/exit.c
index f2cd53e92147..f6cad39f35df 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -1610,6 +1610,9 @@ SYSCALL_DEFINE5(waitid, int, which, pid_t, upid, struct siginfo __user *,
 	if (!infop)
 		return err;
 
+	if (!access_ok(VERIFY_WRITE, infop, sizeof(*infop)))
+		return -EFAULT;
+
 	user_access_begin();
 	unsafe_put_user(signo, &infop->si_signo, Efault);
 	unsafe_put_user(0, &infop->si_errno, Efault);
@@ -1735,6 +1738,9 @@ COMPAT_SYSCALL_DEFINE5(waitid,
 	if (!infop)
 		return err;
 
+	if (!access_ok(VERIFY_WRITE, infop, sizeof(*infop)))
+		return -EFAULT;
+
 	user_access_begin();
 	unsafe_put_user(signo, &infop->si_signo, Efault);
 	unsafe_put_user(0, &infop->si_errno, Efault);
diff --git a/kernel/fork.c b/kernel/fork.c
index e702cb9ffbd8..07cc743698d3 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -215,6 +215,10 @@ static unsigned long *alloc_thread_stack_node(struct task_struct *tsk, int node)
 		if (!s)
 			continue;
 
+#ifdef CONFIG_DEBUG_KMEMLEAK
+		/* Clear stale pointers from reused stack. */
+		memset(s->addr, 0, THREAD_SIZE);
+#endif
 		tsk->stack_vm_area = s;
 		return s->addr;
 	}
diff --git a/kernel/futex.c b/kernel/futex.c
index 0518a0bfc746..76ed5921117a 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -903,11 +903,27 @@ void exit_pi_state_list(struct task_struct *curr)
 	 */
 	raw_spin_lock_irq(&curr->pi_lock);
 	while (!list_empty(head)) {
-
 		next = head->next;
 		pi_state = list_entry(next, struct futex_pi_state, list);
 		key = pi_state->key;
 		hb = hash_futex(&key);
+
+		/*
+		 * We can race against put_pi_state() removing itself from the
+		 * list (a waiter going away). put_pi_state() will first
+		 * decrement the reference count and then modify the list, so
+		 * its possible to see the list entry but fail this reference
+		 * acquire.
+		 *
+		 * In that case; drop the locks to let put_pi_state() make
+		 * progress and retry the loop.
+		 */
+		if (!atomic_inc_not_zero(&pi_state->refcount)) {
+			raw_spin_unlock_irq(&curr->pi_lock);
+			cpu_relax();
+			raw_spin_lock_irq(&curr->pi_lock);
+			continue;
+		}
 		raw_spin_unlock_irq(&curr->pi_lock);
 
 		spin_lock(&hb->lock);
@@ -918,8 +934,10 @@ void exit_pi_state_list(struct task_struct *curr)
 		 * task still owns the PI-state:
 		 */
 		if (head->next != next) {
+			/* retain curr->pi_lock for the loop invariant */
 			raw_spin_unlock(&pi_state->pi_mutex.wait_lock);
 			spin_unlock(&hb->lock);
+			put_pi_state(pi_state);
 			continue;
 		}
 
@@ -927,9 +945,8 @@ void exit_pi_state_list(struct task_struct *curr)
 		WARN_ON(list_empty(&pi_state->list));
 		list_del_init(&pi_state->list);
 		pi_state->owner = NULL;
-		raw_spin_unlock(&curr->pi_lock);
 
-		get_pi_state(pi_state);
+		raw_spin_unlock(&curr->pi_lock);
 		raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);
 		spin_unlock(&hb->lock);
 
@@ -1570,8 +1587,16 @@ static int futex_atomic_op_inuser(unsigned int encoded_op, u32 __user *uaddr)
 	int oldval, ret;
 
 	if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28)) {
-		if (oparg < 0 || oparg > 31)
-			return -EINVAL;
+		if (oparg < 0 || oparg > 31) {
+			char comm[sizeof(current->comm)];
+			/*
+			 * kill this print and return -EINVAL when userspace
+			 * is sane again
+			 */
+			pr_info_ratelimited("futex_wake_op: %s tries to shift op by %d; fix this program\n",
+					get_task_comm(comm, current), oparg);
+			oparg &= 31;
+		}
 		oparg = 1 << oparg;
 	}
 
diff --git a/kernel/futex_compat.c b/kernel/futex_compat.c
index 3f409968e466..83f830acbb5f 100644
--- a/kernel/futex_compat.c
+++ b/kernel/futex_compat.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * linux/kernel/futex_compat.c
  *
diff --git a/kernel/gcov/Makefile b/kernel/gcov/Makefile
index 752d6486b67e..c6c50e5c680e 100644
--- a/kernel/gcov/Makefile
+++ b/kernel/gcov/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 ccflags-y := -DSRCTREE='"$(srctree)"' -DOBJTREE='"$(objtree)"'
 
 obj-y := base.o fs.o
diff --git a/kernel/gcov/base.c b/kernel/gcov/base.c
index c51a49c9be70..9c7c8d5c18f2 100644
--- a/kernel/gcov/base.c
+++ b/kernel/gcov/base.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  *  This code maintains a list of active profiling data structures.
  *
diff --git a/kernel/gcov/fs.c b/kernel/gcov/fs.c
index edf67c493a8e..6e40ff6be083 100644
--- a/kernel/gcov/fs.c
+++ b/kernel/gcov/fs.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  *  This code exports profiling data as debugfs files to userspace.
  *
diff --git a/kernel/gcov/gcc_3_4.c b/kernel/gcov/gcc_3_4.c
index 27bc88a35013..1e32e66c9563 100644
--- a/kernel/gcov/gcc_3_4.c
+++ b/kernel/gcov/gcc_3_4.c
@@ -1,3 +1,4 @@
+// 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
diff --git a/kernel/gcov/gcc_4_7.c b/kernel/gcov/gcc_4_7.c
index 46a18e72bce6..ca5e5c0ef853 100644
--- a/kernel/gcov/gcc_4_7.c
+++ b/kernel/gcov/gcc_4_7.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  *  This code provides functions to handle gcc's profiling data format
  *  introduced with gcc 4.7.
diff --git a/kernel/gcov/gcov.h b/kernel/gcov/gcov.h
index 92c8e22a29ed..de118ad4a024 100644
--- a/kernel/gcov/gcov.h
+++ b/kernel/gcov/gcov.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  *  Profiling infrastructure declarations.
  *
diff --git a/kernel/groups.c b/kernel/groups.c
index 434f6665f187..e357bc800111 100644
--- a/kernel/groups.c
+++ b/kernel/groups.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Supplementary group IDs
  */
diff --git a/kernel/irq/Makefile b/kernel/irq/Makefile
index 329c9193b4bf..ff6e352e3a6c 100644
--- a/kernel/irq/Makefile
+++ b/kernel/irq/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 
 obj-y := irqdesc.o handle.o manage.o spurious.o resend.o chip.o dummychip.o devres.o
 obj-$(CONFIG_IRQ_TIMINGS) += timings.o
diff --git a/kernel/irq/affinity.c b/kernel/irq/affinity.c
index d69bd77252a7..e12d35108225 100644
--- a/kernel/irq/affinity.c
+++ b/kernel/irq/affinity.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Copyright (C) 2016 Thomas Gleixner.
  * Copyright (C) 2016-2017 Christoph Hellwig.
diff --git a/kernel/irq/autoprobe.c b/kernel/irq/autoprobe.c
index 6608d03efb23..4e8089b319ae 100644
--- a/kernel/irq/autoprobe.c
+++ b/kernel/irq/autoprobe.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * linux/kernel/irq/autoprobe.c
  *
diff --git a/kernel/irq/debug.h b/kernel/irq/debug.h
index e75e29e4434a..17f05ef8f575 100644
--- a/kernel/irq/debug.h
+++ b/kernel/irq/debug.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Debugging printout:
  */
diff --git a/kernel/irq/generic-chip.c b/kernel/irq/generic-chip.c
index 5270a54b9fa4..c26c5bb6b491 100644
--- a/kernel/irq/generic-chip.c
+++ b/kernel/irq/generic-chip.c
@@ -135,17 +135,26 @@ void irq_gc_ack_clr_bit(struct irq_data *d)
 }
 
 /**
- * irq_gc_mask_disable_reg_and_ack - Mask and ack pending interrupt
+ * irq_gc_mask_disable_and_ack_set - Mask and ack pending interrupt
  * @d: irq_data
+ *
+ * This generic implementation of the irq_mask_ack method is for chips
+ * with separate enable/disable registers instead of a single mask
+ * register and where a pending interrupt is acknowledged by setting a
+ * bit.
+ *
+ * Note: This is the only permutation currently used.  Similar generic
+ * functions should be added here if other permutations are required.
  */
-void irq_gc_mask_disable_reg_and_ack(struct irq_data *d)
+void irq_gc_mask_disable_and_ack_set(struct irq_data *d)
 {
 	struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d);
 	struct irq_chip_type *ct = irq_data_get_chip_type(d);
 	u32 mask = d->mask;
 
 	irq_gc_lock(gc);
-	irq_reg_writel(gc, mask, ct->regs.mask);
+	irq_reg_writel(gc, mask, ct->regs.disable);
+	*ct->mask_cache &= ~mask;
 	irq_reg_writel(gc, mask, ct->regs.ack);
 	irq_gc_unlock(gc);
 }
diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h
index a0327136e469..07d08ca701ec 100644
--- a/kernel/irq/internals.h
+++ b/kernel/irq/internals.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * IRQ subsystem internal functions and variables:
  *
diff --git a/kernel/irq/migration.c b/kernel/irq/migration.c
index 6ca054a3f91d..86ae0eb80b53 100644
--- a/kernel/irq/migration.c
+++ b/kernel/irq/migration.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 
 #include <linux/irq.h>
 #include <linux/interrupt.h>
diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c
index 6376b4a598d3..c010cc0daf79 100644
--- a/kernel/irq/proc.c
+++ b/kernel/irq/proc.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * linux/kernel/irq/proc.c
  *
diff --git a/kernel/irq/resend.c b/kernel/irq/resend.c
index b86886beee4f..1d08f45135c2 100644
--- a/kernel/irq/resend.c
+++ b/kernel/irq/resend.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * linux/kernel/irq/resend.c
  *
diff --git a/kernel/irq/settings.h b/kernel/irq/settings.h
index 320579d89091..e43795cd2ccf 100644
--- a/kernel/irq/settings.h
+++ b/kernel/irq/settings.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Internal header to deal with irq_desc->status which will be renamed
  * to irq_desc->settings.
diff --git a/kernel/irq/spurious.c b/kernel/irq/spurious.c
index 061ba7eed4ed..987d7bca4864 100644
--- a/kernel/irq/spurious.c
+++ b/kernel/irq/spurious.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * linux/kernel/irq/spurious.c
  *
diff --git a/kernel/kcmp.c b/kernel/kcmp.c
index 055bb2962a0b..a0e3d7a0e8b8 100644
--- a/kernel/kcmp.c
+++ b/kernel/kcmp.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <linux/kernel.h>
 #include <linux/syscalls.h>
 #include <linux/fdtable.h>
diff --git a/kernel/kcov.c b/kernel/kcov.c
index 3f693a0f6f3e..fc6af9e1308b 100644
--- a/kernel/kcov.c
+++ b/kernel/kcov.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #define pr_fmt(fmt) "kcov: " fmt
 
 #define DISABLE_BRANCH_PROFILING
diff --git a/kernel/kexec_internal.h b/kernel/kexec_internal.h
index 50dfcb039a41..48aaf2ac0d0d 100644
--- a/kernel/kexec_internal.h
+++ b/kernel/kexec_internal.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef LINUX_KEXEC_INTERNAL_H
 #define LINUX_KEXEC_INTERNAL_H
 
diff --git a/kernel/livepatch/core.c b/kernel/livepatch/core.c
index b9628e43c78f..bf8c8fd72589 100644
--- a/kernel/livepatch/core.c
+++ b/kernel/livepatch/core.c
@@ -830,6 +830,41 @@ int klp_register_patch(struct klp_patch *patch)
 }
 EXPORT_SYMBOL_GPL(klp_register_patch);
 
+/*
+ * Remove parts of patches that touch a given kernel module. The list of
+ * patches processed might be limited. When limit is NULL, all patches
+ * will be handled.
+ */
+static void klp_cleanup_module_patches_limited(struct module *mod,
+					       struct klp_patch *limit)
+{
+	struct klp_patch *patch;
+	struct klp_object *obj;
+
+	list_for_each_entry(patch, &klp_patches, list) {
+		if (patch == limit)
+			break;
+
+		klp_for_each_object(patch, obj) {
+			if (!klp_is_module(obj) || strcmp(obj->name, mod->name))
+				continue;
+
+			/*
+			 * Only unpatch the module if the patch is enabled or
+			 * is in transition.
+			 */
+			if (patch->enabled || patch == klp_transition_patch) {
+				pr_notice("reverting patch '%s' on unloading module '%s'\n",
+					  patch->mod->name, obj->mod->name);
+				klp_unpatch_object(obj);
+			}
+
+			klp_free_object_loaded(obj);
+			break;
+		}
+	}
+}
+
 int klp_module_coming(struct module *mod)
 {
 	int ret;
@@ -894,7 +929,7 @@ err:
 	pr_warn("patch '%s' failed for module '%s', refusing to load module '%s'\n",
 		patch->mod->name, obj->mod->name, obj->mod->name);
 	mod->klp_alive = false;
-	klp_free_object_loaded(obj);
+	klp_cleanup_module_patches_limited(mod, patch);
 	mutex_unlock(&klp_mutex);
 
 	return ret;
@@ -902,9 +937,6 @@ err:
 
 void klp_module_going(struct module *mod)
 {
-	struct klp_patch *patch;
-	struct klp_object *obj;
-
 	if (WARN_ON(mod->state != MODULE_STATE_GOING &&
 		    mod->state != MODULE_STATE_COMING))
 		return;
@@ -917,25 +949,7 @@ void klp_module_going(struct module *mod)
 	 */
 	mod->klp_alive = false;
 
-	list_for_each_entry(patch, &klp_patches, list) {
-		klp_for_each_object(patch, obj) {
-			if (!klp_is_module(obj) || strcmp(obj->name, mod->name))
-				continue;
-
-			/*
-			 * Only unpatch the module if the patch is enabled or
-			 * is in transition.
-			 */
-			if (patch->enabled || patch == klp_transition_patch) {
-				pr_notice("reverting patch '%s' on unloading module '%s'\n",
-					  patch->mod->name, obj->mod->name);
-				klp_unpatch_object(obj);
-			}
-
-			klp_free_object_loaded(obj);
-			break;
-		}
-	}
+	klp_cleanup_module_patches_limited(mod, NULL);
 
 	mutex_unlock(&klp_mutex);
 }
diff --git a/kernel/livepatch/core.h b/kernel/livepatch/core.h
index c74f24c47837..a351601d7f76 100644
--- a/kernel/livepatch/core.h
+++ b/kernel/livepatch/core.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _LIVEPATCH_CORE_H
 #define _LIVEPATCH_CORE_H
 
diff --git a/kernel/livepatch/patch.h b/kernel/livepatch/patch.h
index 0db227170c36..e72d8250d04b 100644
--- a/kernel/livepatch/patch.h
+++ b/kernel/livepatch/patch.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _LIVEPATCH_PATCH_H
 #define _LIVEPATCH_PATCH_H
 
diff --git a/kernel/livepatch/transition.h b/kernel/livepatch/transition.h
index ce09b326546c..0f6e27c481f9 100644
--- a/kernel/livepatch/transition.h
+++ b/kernel/livepatch/transition.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _LIVEPATCH_TRANSITION_H
 #define _LIVEPATCH_TRANSITION_H
 
diff --git a/kernel/locking/Makefile b/kernel/locking/Makefile
index 760158d9d98d..392c7f23af76 100644
--- a/kernel/locking/Makefile
+++ b/kernel/locking/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 # Any varying coverage in these files is non-deterministic
 # and is generally not a function of system call inputs.
 KCOV_INSTRUMENT		:= n
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index 44c8d0d17170..e36e652d996f 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -1873,10 +1873,10 @@ check_prev_add(struct task_struct *curr, struct held_lock *prev,
 	       struct held_lock *next, int distance, struct stack_trace *trace,
 	       int (*save)(struct stack_trace *trace))
 {
+	struct lock_list *uninitialized_var(target_entry);
 	struct lock_list *entry;
-	int ret;
 	struct lock_list this;
-	struct lock_list *uninitialized_var(target_entry);
+	int ret;
 
 	/*
 	 * Prove that the new <prev> -> <next> dependency would not
@@ -1890,8 +1890,17 @@ check_prev_add(struct task_struct *curr, struct held_lock *prev,
 	this.class = hlock_class(next);
 	this.parent = NULL;
 	ret = check_noncircular(&this, hlock_class(prev), &target_entry);
-	if (unlikely(!ret))
+	if (unlikely(!ret)) {
+		if (!trace->entries) {
+			/*
+			 * If @save fails here, the printing might trigger
+			 * a WARN but because of the !nr_entries it should
+			 * not do bad things.
+			 */
+			save(trace);
+		}
 		return print_circular_bug(&this, target_entry, next, prev, trace);
+	}
 	else if (unlikely(ret < 0))
 		return print_bfs_bug(ret);
 
@@ -1938,7 +1947,7 @@ check_prev_add(struct task_struct *curr, struct held_lock *prev,
 		return print_bfs_bug(ret);
 
 
-	if (save && !save(trace))
+	if (!trace->entries && !save(trace))
 		return 0;
 
 	/*
@@ -1958,20 +1967,6 @@ check_prev_add(struct task_struct *curr, struct held_lock *prev,
 	if (!ret)
 		return 0;
 
-	/*
-	 * Debugging printouts:
-	 */
-	if (verbose(hlock_class(prev)) || verbose(hlock_class(next))) {
-		graph_unlock();
-		printk("\n new dependency: ");
-		print_lock_name(hlock_class(prev));
-		printk(KERN_CONT " => ");
-		print_lock_name(hlock_class(next));
-		printk(KERN_CONT "\n");
-		dump_stack();
-		if (!graph_lock())
-			return 0;
-	}
 	return 2;
 }
 
@@ -1986,8 +1981,12 @@ check_prevs_add(struct task_struct *curr, struct held_lock *next)
 {
 	int depth = curr->lockdep_depth;
 	struct held_lock *hlock;
-	struct stack_trace trace;
-	int (*save)(struct stack_trace *trace) = save_trace;
+	struct stack_trace trace = {
+		.nr_entries = 0,
+		.max_entries = 0,
+		.entries = NULL,
+		.skip = 0,
+	};
 
 	/*
 	 * Debugging checks.
@@ -2018,18 +2017,11 @@ check_prevs_add(struct task_struct *curr, struct held_lock *next)
 			 */
 			if (hlock->read != 2 && hlock->check) {
 				int ret = check_prev_add(curr, hlock, next,
-							 distance, &trace, save);
+							 distance, &trace, save_trace);
 				if (!ret)
 					return 0;
 
 				/*
-				 * Stop saving stack_trace if save_trace() was
-				 * called at least once:
-				 */
-				if (save && ret == 2)
-					save = NULL;
-
-				/*
 				 * Stop after the first non-trylock entry,
 				 * as non-trylock entries have added their
 				 * own direct dependencies already, so this
diff --git a/kernel/locking/lockdep_internals.h b/kernel/locking/lockdep_internals.h
index 1da4669d57a7..d459d624ba2a 100644
--- a/kernel/locking/lockdep_internals.h
+++ b/kernel/locking/lockdep_internals.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * kernel/lockdep_internals.h
  *
diff --git a/kernel/locking/lockdep_proc.c b/kernel/locking/lockdep_proc.c
index 68d9e267ccd4..ad69bbc9bd28 100644
--- a/kernel/locking/lockdep_proc.c
+++ b/kernel/locking/lockdep_proc.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * kernel/lockdep_proc.c
  *
diff --git a/kernel/locking/mcs_spinlock.h b/kernel/locking/mcs_spinlock.h
index 6a385aabcce7..f046b7ce9dd6 100644
--- a/kernel/locking/mcs_spinlock.h
+++ b/kernel/locking/mcs_spinlock.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * MCS lock defines
  *
diff --git a/kernel/locking/mutex-debug.h b/kernel/locking/mutex-debug.h
index 4174417d5309..1edd3f45a4ec 100644
--- a/kernel/locking/mutex-debug.h
+++ b/kernel/locking/mutex-debug.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Mutexes: blocking mutual exclusion locks
  *
diff --git a/kernel/locking/mutex.h b/kernel/locking/mutex.h
index 6ebc1902f779..1c2287d3fa71 100644
--- a/kernel/locking/mutex.h
+++ b/kernel/locking/mutex.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Mutexes: blocking mutual exclusion locks
  *
diff --git a/kernel/locking/osq_lock.c b/kernel/locking/osq_lock.c
index a74ee6abd039..6ef600aa0f47 100644
--- a/kernel/locking/osq_lock.c
+++ b/kernel/locking/osq_lock.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <linux/percpu.h>
 #include <linux/sched.h>
 #include <linux/osq_lock.h>
diff --git a/kernel/locking/qspinlock_paravirt.h b/kernel/locking/qspinlock_paravirt.h
index 43555681c40b..15b6a39366c6 100644
--- a/kernel/locking/qspinlock_paravirt.h
+++ b/kernel/locking/qspinlock_paravirt.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _GEN_PV_LOCK_SLOWPATH
 #error "do not include this file"
 #endif
diff --git a/kernel/locking/rtmutex-debug.c b/kernel/locking/rtmutex-debug.c
index f4a74e78d467..fd4fe1f5b458 100644
--- a/kernel/locking/rtmutex-debug.c
+++ b/kernel/locking/rtmutex-debug.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * RT-Mutexes: blocking mutual exclusion locks with PI support
  *
diff --git a/kernel/locking/rtmutex-debug.h b/kernel/locking/rtmutex-debug.h
index 5078c6ddf4a5..fc549713bba3 100644
--- a/kernel/locking/rtmutex-debug.h
+++ b/kernel/locking/rtmutex-debug.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * RT-Mutexes: blocking mutual exclusion locks with PI support
  *
diff --git a/kernel/locking/rtmutex.h b/kernel/locking/rtmutex.h
index 5c253caffe91..732f96abf462 100644
--- a/kernel/locking/rtmutex.h
+++ b/kernel/locking/rtmutex.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * RT-Mutexes: blocking mutual exclusion locks with PI support
  *
diff --git a/kernel/locking/rtmutex_common.h b/kernel/locking/rtmutex_common.h
index 7453be0485a5..124e98ca0b17 100644
--- a/kernel/locking/rtmutex_common.h
+++ b/kernel/locking/rtmutex_common.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * RT Mutexes: blocking mutual exclusion locks with PI support
  *
diff --git a/kernel/locking/rwsem-spinlock.c b/kernel/locking/rwsem-spinlock.c
index 0848634c5512..a7ffb2a96ede 100644
--- a/kernel/locking/rwsem-spinlock.c
+++ b/kernel/locking/rwsem-spinlock.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /* rwsem-spinlock.c: R/W semaphores: contention handling functions for
  * generic spinlock implementation
  *
diff --git a/kernel/locking/rwsem-xadd.c b/kernel/locking/rwsem-xadd.c
index 1fefe6dcafd7..e795908f3607 100644
--- a/kernel/locking/rwsem-xadd.c
+++ b/kernel/locking/rwsem-xadd.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /* rwsem.c: R/W semaphores: contention handling functions
  *
  * Written by David Howells (dhowells@redhat.com).
diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c
index 4d48b1c4870d..a6c76a4832b4 100644
--- a/kernel/locking/rwsem.c
+++ b/kernel/locking/rwsem.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /* kernel/rwsem.c: R/W semaphores, public implementation
  *
  * Written by David Howells (dhowells@redhat.com).
diff --git a/kernel/locking/rwsem.h b/kernel/locking/rwsem.h
index a699f4048ba1..a883b8f1fdc6 100644
--- a/kernel/locking/rwsem.h
+++ b/kernel/locking/rwsem.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * The owner field of the rw_semaphore structure will be set to
  * RWSEM_READ_OWNED when a reader grabs the lock. A writer will clear
diff --git a/kernel/locking/spinlock.c b/kernel/locking/spinlock.c
index 4b082b5cac9e..6e40fdfba326 100644
--- a/kernel/locking/spinlock.c
+++ b/kernel/locking/spinlock.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Copyright (2004) Linus Torvalds
  *
diff --git a/kernel/power/Makefile b/kernel/power/Makefile
index eb4f717705ba..a3f79f0eef36 100644
--- a/kernel/power/Makefile
+++ b/kernel/power/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 
 ccflags-$(CONFIG_PM_DEBUG)	:= -DDEBUG
 
diff --git a/kernel/power/autosleep.c b/kernel/power/autosleep.c
index 9012ecf7b814..41e83a779e19 100644
--- a/kernel/power/autosleep.c
+++ b/kernel/power/autosleep.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * kernel/power/autosleep.c
  *
diff --git a/kernel/power/console.c b/kernel/power/console.c
index 0e781798b0b3..fcdf0e14a47d 100644
--- a/kernel/power/console.c
+++ b/kernel/power/console.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Functions for saving/restoring console.
  *
diff --git a/kernel/power/power.h b/kernel/power/power.h
index 1d2d761e3c25..f29cd178df90 100644
--- a/kernel/power/power.h
+++ b/kernel/power/power.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #include <linux/suspend.h>
 #include <linux/suspend_ioctls.h>
 #include <linux/utsname.h>
diff --git a/kernel/power/process.c b/kernel/power/process.c
index 50f25cb370c6..7381d49a44db 100644
--- a/kernel/power/process.c
+++ b/kernel/power/process.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * drivers/power/process.c - Functions for starting/stopping processes on 
  *                           suspend transitions.
diff --git a/kernel/power/wakelock.c b/kernel/power/wakelock.c
index 1896386e16bb..dfba59be190b 100644
--- a/kernel/power/wakelock.c
+++ b/kernel/power/wakelock.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * kernel/power/wakelock.c
  *
diff --git a/kernel/printk/braille.c b/kernel/printk/braille.c
index 61d41ca41844..1d21ebacfdb8 100644
--- a/kernel/printk/braille.c
+++ b/kernel/printk/braille.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
 #include <linux/kernel.h>
diff --git a/kernel/printk/braille.h b/kernel/printk/braille.h
index 749a6756843a..123154f86304 100644
--- a/kernel/printk/braille.h
+++ b/kernel/printk/braille.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _PRINTK_BRAILLE_H
 #define _PRINTK_BRAILLE_H
 
diff --git a/kernel/printk/console_cmdline.h b/kernel/printk/console_cmdline.h
index 2ca4a8b5fe57..11f19c466af5 100644
--- a/kernel/printk/console_cmdline.h
+++ b/kernel/printk/console_cmdline.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _CONSOLE_CMDLINE_H
 #define _CONSOLE_CMDLINE_H
 
diff --git a/kernel/range.c b/kernel/range.c
index 82cfc285b046..d84de6766472 100644
--- a/kernel/range.c
+++ b/kernel/range.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Range add and subtract
  */
diff --git a/kernel/rcu/Makefile b/kernel/rcu/Makefile
index 13c0fc852767..020e8b6a644b 100644
--- a/kernel/rcu/Makefile
+++ b/kernel/rcu/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 # Any varying coverage in these files is non-deterministic
 # and is generally not a function of system call inputs.
 KCOV_INSTRUMENT := n
diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c
index 729a8706751d..6d5880089ff6 100644
--- a/kernel/rcu/srcutree.c
+++ b/kernel/rcu/srcutree.c
@@ -854,7 +854,7 @@ void __call_srcu(struct srcu_struct *sp, struct rcu_head *rhp,
 /**
  * call_srcu() - Queue a callback for invocation after an SRCU grace period
  * @sp: srcu_struct in queue the callback
- * @head: structure to be used for queueing the SRCU callback.
+ * @rhp: structure to be used for queueing the SRCU callback.
  * @func: function to be invoked after the SRCU grace period
  *
  * The callback function will be invoked some time after a full SRCU
diff --git a/kernel/rcu/sync.c b/kernel/rcu/sync.c
index 50d1861f7759..3f943efcf61c 100644
--- a/kernel/rcu/sync.c
+++ b/kernel/rcu/sync.c
@@ -85,6 +85,9 @@ void rcu_sync_init(struct rcu_sync *rsp, enum rcu_sync_type type)
 }
 
 /**
+ * rcu_sync_enter_start - Force readers onto slow path for multiple updates
+ * @rsp: Pointer to rcu_sync structure to use for synchronization
+ *
  * Must be called after rcu_sync_init() and before first use.
  *
  * Ensures rcu_sync_is_idle() returns false and rcu_sync_{enter,exit}()
@@ -142,7 +145,7 @@ void rcu_sync_enter(struct rcu_sync *rsp)
 
 /**
  * rcu_sync_func() - Callback function managing reader access to fastpath
- * @rsp: Pointer to rcu_sync structure to use for synchronization
+ * @rhp: Pointer to rcu_head in rcu_sync structure to use for synchronization
  *
  * This function is passed to one of the call_rcu() functions by
  * rcu_sync_exit(), so that it is invoked after a grace period following the
@@ -158,9 +161,9 @@ void rcu_sync_enter(struct rcu_sync *rsp)
  * rcu_sync_exit().  Otherwise, set all state back to idle so that readers
  * can again use their fastpaths.
  */
-static void rcu_sync_func(struct rcu_head *rcu)
+static void rcu_sync_func(struct rcu_head *rhp)
 {
-	struct rcu_sync *rsp = container_of(rcu, struct rcu_sync, cb_head);
+	struct rcu_sync *rsp = container_of(rhp, struct rcu_sync, cb_head);
 	unsigned long flags;
 
 	BUG_ON(rsp->gp_state != GP_PASSED);
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index b0ad62b0e7b8..3e3650e94ae6 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -3097,9 +3097,10 @@ __call_rcu(struct rcu_head *head, rcu_callback_t func,
  * read-side critical sections have completed. call_rcu_sched() assumes
  * that the read-side critical sections end on enabling of preemption
  * or on voluntary preemption.
- * RCU read-side critical sections are delimited by :
- *  - rcu_read_lock_sched() and rcu_read_unlock_sched(), OR
- *  - anything that disables preemption.
+ * RCU read-side critical sections are delimited by:
+ *
+ * - rcu_read_lock_sched() and rcu_read_unlock_sched(), OR
+ * - anything that disables preemption.
  *
  *  These may be nested.
  *
@@ -3124,11 +3125,12 @@ EXPORT_SYMBOL_GPL(call_rcu_sched);
  * handler. This means that read-side critical sections in process
  * context must not be interrupted by softirqs. This interface is to be
  * used when most of the read-side critical sections are in softirq context.
- * RCU read-side critical sections are delimited by :
- *  - rcu_read_lock() and  rcu_read_unlock(), if in interrupt context.
- *  OR
- *  - rcu_read_lock_bh() and rcu_read_unlock_bh(), if in process context.
- *  These may be nested.
+ * RCU read-side critical sections are delimited by:
+ *
+ * - rcu_read_lock() and  rcu_read_unlock(), if in interrupt context, OR
+ * - rcu_read_lock_bh() and rcu_read_unlock_bh(), if in process context.
+ *
+ * These may be nested.
  *
  * See the description of call_rcu() for more detailed information on
  * memory ordering guarantees.
diff --git a/kernel/sched/Makefile b/kernel/sched/Makefile
index 78f54932ea1d..a9ee16bbc693 100644
--- a/kernel/sched/Makefile
+++ b/kernel/sched/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 ifdef CONFIG_FUNCTION_TRACER
 CFLAGS_REMOVE_clock.o = $(CC_FLAGS_FTRACE)
 endif
diff --git a/kernel/sched/autogroup.c b/kernel/sched/autogroup.c
index de6d7f4dfcb5..a43df5193538 100644
--- a/kernel/sched/autogroup.c
+++ b/kernel/sched/autogroup.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include "sched.h"
 
 #include <linux/proc_fs.h>
diff --git a/kernel/sched/autogroup.h b/kernel/sched/autogroup.h
index ce40c810cd5c..27cd22b89824 100644
--- a/kernel/sched/autogroup.h
+++ b/kernel/sched/autogroup.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifdef CONFIG_SCHED_AUTOGROUP
 
 #include <linux/kref.h>
diff --git a/kernel/sched/completion.c b/kernel/sched/completion.c
index cc873075c3bd..2ddaec40956f 100644
--- a/kernel/sched/completion.c
+++ b/kernel/sched/completion.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Generic wait-for-completion handler;
  *
diff --git a/kernel/sched/cpuacct.c b/kernel/sched/cpuacct.c
index f95ab29a45d0..44ab32a4fab6 100644
--- a/kernel/sched/cpuacct.c
+++ b/kernel/sched/cpuacct.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <linux/cgroup.h>
 #include <linux/slab.h>
 #include <linux/percpu.h>
diff --git a/kernel/sched/cpuacct.h b/kernel/sched/cpuacct.h
index ba72807c73d4..a8358a57a316 100644
--- a/kernel/sched/cpuacct.h
+++ b/kernel/sched/cpuacct.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifdef CONFIG_CGROUP_CPUACCT
 
 extern void cpuacct_charge(struct task_struct *tsk, u64 cputime);
diff --git a/kernel/sched/cpudeadline.h b/kernel/sched/cpudeadline.h
index f7da8c55bba0..b010d26e108e 100644
--- a/kernel/sched/cpudeadline.h
+++ b/kernel/sched/cpudeadline.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _LINUX_CPUDL_H
 #define _LINUX_CPUDL_H
 
diff --git a/kernel/sched/cpupri.h b/kernel/sched/cpupri.h
index 63cbb9ca0496..bab050019071 100644
--- a/kernel/sched/cpupri.h
+++ b/kernel/sched/cpupri.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _LINUX_CPUPRI_H
 #define _LINUX_CPUPRI_H
 
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 0191ec7667c3..4ae5c1ea90e2 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Deadline Scheduling Class (SCHED_DEADLINE)
  *
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 70ba32e08a23..5c09ddf8c832 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Completely Fair Scheduling (CFS) Class (SCHED_NORMAL/SCHED_BATCH)
  *
@@ -5356,91 +5357,62 @@ static int wake_wide(struct task_struct *p)
 	return 1;
 }
 
-struct llc_stats {
-	unsigned long	nr_running;
-	unsigned long	load;
-	unsigned long	capacity;
-	int		has_capacity;
-};
+/*
+ * The purpose of wake_affine() is to quickly determine on which CPU we can run
+ * soonest. For the purpose of speed we only consider the waking and previous
+ * CPU.
+ *
+ * wake_affine_idle() - only considers 'now', it check if the waking CPU is (or
+ *			will be) idle.
+ *
+ * wake_affine_weight() - considers the weight to reflect the average
+ *			  scheduling latency of the CPUs. This seems to work
+ *			  for the overloaded case.
+ */
 
-static bool get_llc_stats(struct llc_stats *stats, int cpu)
+static bool
+wake_affine_idle(struct sched_domain *sd, struct task_struct *p,
+		 int this_cpu, int prev_cpu, int sync)
 {
-	struct sched_domain_shared *sds = rcu_dereference(per_cpu(sd_llc_shared, cpu));
-
-	if (!sds)
-		return false;
+	if (idle_cpu(this_cpu))
+		return true;
 
-	stats->nr_running	= READ_ONCE(sds->nr_running);
-	stats->load		= READ_ONCE(sds->load);
-	stats->capacity		= READ_ONCE(sds->capacity);
-	stats->has_capacity	= stats->nr_running < per_cpu(sd_llc_size, cpu);
+	if (sync && cpu_rq(this_cpu)->nr_running == 1)
+		return true;
 
-	return true;
+	return false;
 }
 
-/*
- * Can a task be moved from prev_cpu to this_cpu without causing a load
- * imbalance that would trigger the load balancer?
- *
- * Since we're running on 'stale' values, we might in fact create an imbalance
- * but recomputing these values is expensive, as that'd mean iteration 2 cache
- * domains worth of CPUs.
- */
 static bool
-wake_affine_llc(struct sched_domain *sd, struct task_struct *p,
-		int this_cpu, int prev_cpu, int sync)
+wake_affine_weight(struct sched_domain *sd, struct task_struct *p,
+		   int this_cpu, int prev_cpu, int sync)
 {
-	struct llc_stats prev_stats, this_stats;
 	s64 this_eff_load, prev_eff_load;
 	unsigned long task_load;
 
-	if (!get_llc_stats(&prev_stats, prev_cpu) ||
-	    !get_llc_stats(&this_stats, this_cpu))
-		return false;
+	this_eff_load = target_load(this_cpu, sd->wake_idx);
+	prev_eff_load = source_load(prev_cpu, sd->wake_idx);
 
-	/*
-	 * If sync wakeup then subtract the (maximum possible)
-	 * effect of the currently running task from the load
-	 * of the current LLC.
-	 */
 	if (sync) {
 		unsigned long current_load = task_h_load(current);
 
-		/* in this case load hits 0 and this LLC is considered 'idle' */
-		if (current_load > this_stats.load)
+		if (current_load > this_eff_load)
 			return true;
 
-		this_stats.load -= current_load;
+		this_eff_load -= current_load;
 	}
 
-	/*
-	 * The has_capacity stuff is not SMT aware, but by trying to balance
-	 * the nr_running on both ends we try and fill the domain at equal
-	 * rates, thereby first consuming cores before siblings.
-	 */
-
-	/* if the old cache has capacity, stay there */
-	if (prev_stats.has_capacity && prev_stats.nr_running < this_stats.nr_running+1)
-		return false;
-
-	/* if this cache has capacity, come here */
-	if (this_stats.has_capacity && this_stats.nr_running+1 < prev_stats.nr_running)
-		return true;
-
-	/*
-	 * Check to see if we can move the load without causing too much
-	 * imbalance.
-	 */
 	task_load = task_h_load(p);
 
-	this_eff_load = 100;
-	this_eff_load *= prev_stats.capacity;
-
-	prev_eff_load = 100 + (sd->imbalance_pct - 100) / 2;
-	prev_eff_load *= this_stats.capacity;
+	this_eff_load += task_load;
+	if (sched_feat(WA_BIAS))
+		this_eff_load *= 100;
+	this_eff_load *= capacity_of(prev_cpu);
 
-	this_eff_load *= this_stats.load + task_load;
-	prev_eff_load *= prev_stats.load - task_load;
+	prev_eff_load -= task_load;
+	if (sched_feat(WA_BIAS))
+		prev_eff_load *= 100 + (sd->imbalance_pct - 100) / 2;
+	prev_eff_load *= capacity_of(this_cpu);
 
 	return this_eff_load <= prev_eff_load;
 }
@@ -5449,22 +5421,13 @@ static int wake_affine(struct sched_domain *sd, struct task_struct *p,
 		       int prev_cpu, int sync)
 {
 	int this_cpu = smp_processor_id();
-	bool affine;
+	bool affine = false;
 
-	/*
-	 * Default to no affine wakeups; wake_affine() should not effect a task
-	 * placement the load-balancer feels inclined to undo. The conservative
-	 * option is therefore to not move tasks when they wake up.
-	 */
-	affine = false;
+	if (sched_feat(WA_IDLE) && !affine)
+		affine = wake_affine_idle(sd, p, this_cpu, prev_cpu, sync);
 
-	/*
-	 * If the wakeup is across cache domains, try to evaluate if movement
-	 * makes sense, otherwise rely on select_idle_siblings() to do
-	 * placement inside the cache domain.
-	 */
-	if (!cpus_share_cache(prev_cpu, this_cpu))
-		affine = wake_affine_llc(sd, p, this_cpu, prev_cpu, sync);
+	if (sched_feat(WA_WEIGHT) && !affine)
+		affine = wake_affine_weight(sd, p, this_cpu, prev_cpu, sync);
 
 	schedstat_inc(p->se.statistics.nr_wakeups_affine_attempts);
 	if (affine) {
@@ -7600,7 +7563,6 @@ static inline enum fbq_type fbq_classify_rq(struct rq *rq)
  */
 static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sds)
 {
-	struct sched_domain_shared *shared = env->sd->shared;
 	struct sched_domain *child = env->sd->child;
 	struct sched_group *sg = env->sd->groups;
 	struct sg_lb_stats *local = &sds->local_stat;
@@ -7672,22 +7634,6 @@ next_group:
 		if (env->dst_rq->rd->overload != overload)
 			env->dst_rq->rd->overload = overload;
 	}
-
-	if (!shared)
-		return;
-
-	/*
-	 * Since these are sums over groups they can contain some CPUs
-	 * multiple times for the NUMA domains.
-	 *
-	 * Currently only wake_affine_llc() and find_busiest_group()
-	 * uses these numbers, only the last is affected by this problem.
-	 *
-	 * XXX fix that.
-	 */
-	WRITE_ONCE(shared->nr_running,	sds->total_running);
-	WRITE_ONCE(shared->load,	sds->total_load);
-	WRITE_ONCE(shared->capacity,	sds->total_capacity);
 }
 
 /**
@@ -8098,6 +8044,13 @@ static int should_we_balance(struct lb_env *env)
 	int cpu, balance_cpu = -1;
 
 	/*
+	 * Ensure the balancing environment is consistent; can happen
+	 * when the softirq triggers 'during' hotplug.
+	 */
+	if (!cpumask_test_cpu(env->dst_cpu, env->cpus))
+		return 0;
+
+	/*
 	 * In the newly idle case, we will allow all the cpu's
 	 * to do the newly idle load balance.
 	 */
diff --git a/kernel/sched/features.h b/kernel/sched/features.h
index d3fb15555291..9552fd5854bf 100644
--- a/kernel/sched/features.h
+++ b/kernel/sched/features.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Only give sleepers 50% of their service deficit. This allows
  * them to run sooner, but does not allow tons of sleepers to
@@ -81,3 +82,6 @@ SCHED_FEAT(RT_RUNTIME_SHARE, true)
 SCHED_FEAT(LB_MIN, false)
 SCHED_FEAT(ATTACH_AGE_LOAD, true)
 
+SCHED_FEAT(WA_IDLE, true)
+SCHED_FEAT(WA_WEIGHT, true)
+SCHED_FEAT(WA_BIAS, true)
diff --git a/kernel/sched/idle_task.c b/kernel/sched/idle_task.c
index 0c00172db63e..d518664cce4f 100644
--- a/kernel/sched/idle_task.c
+++ b/kernel/sched/idle_task.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include "sched.h"
 
 /*
diff --git a/kernel/sched/loadavg.c b/kernel/sched/loadavg.c
index f14716a3522f..89a989e4d758 100644
--- a/kernel/sched/loadavg.c
+++ b/kernel/sched/loadavg.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * kernel/sched/loadavg.c
  *
diff --git a/kernel/sched/membarrier.c b/kernel/sched/membarrier.c
index a92fddc22747..dd7908743dab 100644
--- a/kernel/sched/membarrier.c
+++ b/kernel/sched/membarrier.c
@@ -18,6 +18,7 @@
 #include <linux/membarrier.h>
 #include <linux/tick.h>
 #include <linux/cpumask.h>
+#include <linux/atomic.h>
 
 #include "sched.h"	/* for cpu_rq(). */
 
@@ -26,21 +27,26 @@
  * except MEMBARRIER_CMD_QUERY.
  */
 #define MEMBARRIER_CMD_BITMASK	\
-	(MEMBARRIER_CMD_SHARED | MEMBARRIER_CMD_PRIVATE_EXPEDITED)
+	(MEMBARRIER_CMD_SHARED | MEMBARRIER_CMD_PRIVATE_EXPEDITED	\
+	| MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED)
 
 static void ipi_mb(void *info)
 {
 	smp_mb();	/* IPIs should be serializing but paranoid. */
 }
 
-static void membarrier_private_expedited(void)
+static int membarrier_private_expedited(void)
 {
 	int cpu;
 	bool fallback = false;
 	cpumask_var_t tmpmask;
 
+	if (!(atomic_read(&current->mm->membarrier_state)
+			& MEMBARRIER_STATE_PRIVATE_EXPEDITED_READY))
+		return -EPERM;
+
 	if (num_online_cpus() == 1)
-		return;
+		return 0;
 
 	/*
 	 * Matches memory barriers around rq->curr modification in
@@ -94,6 +100,24 @@ static void membarrier_private_expedited(void)
 	 * rq->curr modification in scheduler.
 	 */
 	smp_mb();	/* exit from system call is not a mb */
+	return 0;
+}
+
+static void membarrier_register_private_expedited(void)
+{
+	struct task_struct *p = current;
+	struct mm_struct *mm = p->mm;
+
+	/*
+	 * We need to consider threads belonging to different thread
+	 * groups, which use the same mm. (CLONE_VM but not
+	 * CLONE_THREAD).
+	 */
+	if (atomic_read(&mm->membarrier_state)
+			& MEMBARRIER_STATE_PRIVATE_EXPEDITED_READY)
+		return;
+	atomic_or(MEMBARRIER_STATE_PRIVATE_EXPEDITED_READY,
+			&mm->membarrier_state);
 }
 
 /**
@@ -144,7 +168,9 @@ SYSCALL_DEFINE2(membarrier, int, cmd, int, flags)
 			synchronize_sched();
 		return 0;
 	case MEMBARRIER_CMD_PRIVATE_EXPEDITED:
-		membarrier_private_expedited();
+		return membarrier_private_expedited();
+	case MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED:
+		membarrier_register_private_expedited();
 		return 0;
 	default:
 		return -EINVAL;
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 0af5ca9e3e3f..3c96c80e0992 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Real-Time Scheduling Class (mapped to the SCHED_FIFO and SCHED_RR
  * policies)
diff --git a/kernel/sched/sched-pelt.h b/kernel/sched/sched-pelt.h
index cd200d16529e..a26473674fb7 100644
--- a/kernel/sched/sched-pelt.h
+++ b/kernel/sched/sched-pelt.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /* Generated by Documentation/scheduler/sched-pelt; do not modify. */
 
 static const u32 runnable_avg_yN_inv[] = {
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 14db76cd496f..3b448ba82225 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 
 #include <linux/sched.h>
 #include <linux/sched/autogroup.h>
diff --git a/kernel/sched/stats.c b/kernel/sched/stats.c
index 87e2c9f0c33e..940b1fa1d2ce 100644
--- a/kernel/sched/stats.c
+++ b/kernel/sched/stats.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 
 #include <linux/slab.h>
 #include <linux/fs.h>
diff --git a/kernel/sched/stats.h b/kernel/sched/stats.h
index d5710651043b..baf500d12b7c 100644
--- a/kernel/sched/stats.h
+++ b/kernel/sched/stats.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 
 #ifdef CONFIG_SCHEDSTATS
 
diff --git a/kernel/sched/stop_task.c b/kernel/sched/stop_task.c
index 9f69fb630853..45caf90b24cd 100644
--- a/kernel/sched/stop_task.c
+++ b/kernel/sched/stop_task.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include "sched.h"
 
 /*
diff --git a/kernel/sched/swait.c b/kernel/sched/swait.c
index 2227e183e202..9ff1555341ed 100644
--- a/kernel/sched/swait.c
+++ b/kernel/sched/swait.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <linux/sched/signal.h>
 #include <linux/swait.h>
 
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index f1cf4f306a82..6798276d29af 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Scheduler topology setup/handling methods
  */
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index bb3a38005b9c..418a1c045933 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * linux/kernel/seccomp.c
  *
@@ -473,7 +474,7 @@ static long seccomp_attach_filter(unsigned int flags,
 	return 0;
 }
 
-void __get_seccomp_filter(struct seccomp_filter *filter)
+static void __get_seccomp_filter(struct seccomp_filter *filter)
 {
 	/* Reference count is bounded by the number of total processes. */
 	refcount_inc(&filter->usage);
diff --git a/kernel/signal.c b/kernel/signal.c
index 800a18f77732..8dcd8825b2de 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -2698,7 +2698,7 @@ enum siginfo_layout siginfo_layout(int sig, int si_code)
 			[SIGSEGV] = { NSIGSEGV, SIL_FAULT },
 			[SIGBUS]  = { NSIGBUS,  SIL_FAULT },
 			[SIGTRAP] = { NSIGTRAP, SIL_FAULT },
-#if defined(SIGMET) && defined(NSIGEMT)
+#if defined(SIGEMT) && defined(NSIGEMT)
 			[SIGEMT]  = { NSIGEMT,  SIL_FAULT },
 #endif
 			[SIGCHLD] = { NSIGCHLD, SIL_CHLD },
diff --git a/kernel/smpboot.h b/kernel/smpboot.h
index 485b81cfab34..34dd3d7ba40b 100644
--- a/kernel/smpboot.h
+++ b/kernel/smpboot.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef SMPBOOT_H
 #define SMPBOOT_H
 
diff --git a/kernel/sys.c b/kernel/sys.c
index 9aebc2935013..524a4cb9bbe2 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  *  linux/kernel/sys.c
  *
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index 8acef8576ce9..b5189762d275 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 
 #include <linux/linkage.h>
 #include <linux/errno.h>
diff --git a/kernel/sysctl_binary.c b/kernel/sysctl_binary.c
index 58ea8c03662e..e8c0dab4fd65 100644
--- a/kernel/sysctl_binary.c
+++ b/kernel/sysctl_binary.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <linux/stat.h>
 #include <linux/sysctl.h>
 #include "../fs/xfs/xfs_sysctl.h"
diff --git a/kernel/task_work.c b/kernel/task_work.c
index 836a72a66fba..5718b3ea202a 100644
--- a/kernel/task_work.c
+++ b/kernel/task_work.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <linux/spinlock.h>
 #include <linux/task_work.h>
 #include <linux/tracehook.h>
diff --git a/kernel/time/Makefile b/kernel/time/Makefile
index 938dbf33ef49..f1e46f338a9c 100644
--- a/kernel/time/Makefile
+++ b/kernel/time/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 obj-y += time.o timer.o hrtimer.o
 obj-y += timekeeping.o ntp.o clocksource.o jiffies.o timer_list.o
 obj-y += timeconv.o timecounter.o alarmtimer.o
diff --git a/kernel/time/itimer.c b/kernel/time/itimer.c
index 2ef98a02376a..f26acef5d7b4 100644
--- a/kernel/time/itimer.c
+++ b/kernel/time/itimer.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * linux/kernel/itimer.c
  *
diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c
index edf19cc53140..99e03bec68e4 100644
--- a/kernel/time/ntp.c
+++ b/kernel/time/ntp.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * NTP state machine interfaces and logic.
  *
diff --git a/kernel/time/ntp_internal.h b/kernel/time/ntp_internal.h
index d8a7c11fa71a..0a53e6ea47b1 100644
--- a/kernel/time/ntp_internal.h
+++ b/kernel/time/ntp_internal.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _LINUX_NTP_INTERNAL_H
 #define _LINUX_NTP_INTERNAL_H
 
diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c
index 8585ad6e472a..5b117110b55b 100644
--- a/kernel/time/posix-cpu-timers.c
+++ b/kernel/time/posix-cpu-timers.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Implement CPU time clocks for the POSIX clock interface.
  */
diff --git a/kernel/time/posix-timers.h b/kernel/time/posix-timers.h
index fb303c3be4d3..151e28f5bf30 100644
--- a/kernel/time/posix-timers.h
+++ b/kernel/time/posix-timers.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #define TIMER_RETRY 1
 
 struct k_clock {
diff --git a/kernel/time/tick-broadcast-hrtimer.c b/kernel/time/tick-broadcast-hrtimer.c
index a7bb8f33ae07..58045eb976c3 100644
--- a/kernel/time/tick-broadcast-hrtimer.c
+++ b/kernel/time/tick-broadcast-hrtimer.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * linux/kernel/time/tick-broadcast-hrtimer.c
  * This file emulates a local clock event device
diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h
index be0ac01f2e12..f8e1845aa464 100644
--- a/kernel/time/tick-internal.h
+++ b/kernel/time/tick-internal.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * tick internal variable and functions used by low/high res code
  */
diff --git a/kernel/time/tick-sched.h b/kernel/time/tick-sched.h
index 075444e3d48e..954b43dbf21c 100644
--- a/kernel/time/tick-sched.h
+++ b/kernel/time/tick-sched.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _TICK_SCHED_H
 #define _TICK_SCHED_H
 
diff --git a/kernel/time/timekeeping.h b/kernel/time/timekeeping.h
index d0914676d4c5..c9f9af339914 100644
--- a/kernel/time/timekeeping.h
+++ b/kernel/time/timekeeping.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _KERNEL_TIME_TIMEKEEPING_H
 #define _KERNEL_TIME_TIMEKEEPING_H
 /*
diff --git a/kernel/time/timekeeping_internal.h b/kernel/time/timekeeping_internal.h
index 9a18f121f399..fdbeeb02dde9 100644
--- a/kernel/time/timekeeping_internal.h
+++ b/kernel/time/timekeeping_internal.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _TIMEKEEPING_INTERNAL_H
 #define _TIMEKEEPING_INTERNAL_H
 /*
diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile
index 90f2701d92a7..19a15b2f1190 100644
--- a/kernel/trace/Makefile
+++ b/kernel/trace/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 
 # Do not instrument the tracer itself:
 
diff --git a/kernel/trace/power-traces.c b/kernel/trace/power-traces.c
index 0c7dee221dca..21bb161c2316 100644
--- a/kernel/trace/power-traces.c
+++ b/kernel/trace/power-traces.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Power trace points
  *
diff --git a/kernel/trace/rpm-traces.c b/kernel/trace/rpm-traces.c
index 4b3b5eaf94d1..25dec0b00280 100644
--- a/kernel/trace/rpm-traces.c
+++ b/kernel/trace/rpm-traces.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Power trace points
  *
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 652c682707cd..401b0639116f 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 
 #ifndef _LINUX_KERNEL_TRACE_H
 #define _LINUX_KERNEL_TRACE_H
diff --git a/kernel/trace/trace_benchmark.c b/kernel/trace/trace_benchmark.c
index 16a8cf02eee9..79f838a75077 100644
--- a/kernel/trace/trace_benchmark.c
+++ b/kernel/trace/trace_benchmark.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <linux/delay.h>
 #include <linux/module.h>
 #include <linux/kthread.h>
diff --git a/kernel/trace/trace_benchmark.h b/kernel/trace/trace_benchmark.h
index ebdbfc2f2a64..be1d86ff753d 100644
--- a/kernel/trace/trace_benchmark.h
+++ b/kernel/trace/trace_benchmark.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #undef TRACE_SYSTEM
 #define TRACE_SYSTEM benchmark
 
diff --git a/kernel/trace/trace_branch.c b/kernel/trace/trace_branch.c
index 4d8fdf3184dc..4ad967453b6f 100644
--- a/kernel/trace/trace_branch.c
+++ b/kernel/trace/trace_branch.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * unlikely profiler
  *
diff --git a/kernel/trace/trace_entries.h b/kernel/trace/trace_entries.h
index adcdbbeae010..e954ae3d82c0 100644
--- a/kernel/trace/trace_entries.h
+++ b/kernel/trace/trace_entries.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * This file defines the trace event structures that go into the ring
  * buffer directly. They are created via macros so that changes for them
diff --git a/kernel/trace/trace_events_filter_test.h b/kernel/trace/trace_events_filter_test.h
index bfd4dba0d603..39d7ef4f57cb 100644
--- a/kernel/trace/trace_events_filter_test.h
+++ b/kernel/trace/trace_events_filter_test.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #undef TRACE_SYSTEM
 #define TRACE_SYSTEM test
 
diff --git a/kernel/trace/trace_export.c b/kernel/trace/trace_export.c
index 39aa7aa66468..548e62eb5c46 100644
--- a/kernel/trace/trace_export.c
+++ b/kernel/trace/trace_export.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * trace_export.c - export basic ftrace utilities to user space
  *
diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c
index a0910c0cdf2e..27f7ad12c4b1 100644
--- a/kernel/trace/trace_functions.c
+++ b/kernel/trace/trace_functions.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * ring buffer based function tracer
  *
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index b8f1f54731af..23c0b0cb5fb9 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  *
  * Function graph tracer.
diff --git a/kernel/trace/trace_kdb.c b/kernel/trace/trace_kdb.c
index 57149bce6aad..d953c163a079 100644
--- a/kernel/trace/trace_kdb.c
+++ b/kernel/trace/trace_kdb.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * kdb helper for dumping the ftrace buffer
  *
diff --git a/kernel/trace/trace_mmiotrace.c b/kernel/trace/trace_mmiotrace.c
index dca78fc48439..b0388016b687 100644
--- a/kernel/trace/trace_mmiotrace.c
+++ b/kernel/trace/trace_mmiotrace.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Memory mapped I/O tracing
  *
diff --git a/kernel/trace/trace_nop.c b/kernel/trace/trace_nop.c
index 49f61fe96a6b..50523f953a5d 100644
--- a/kernel/trace/trace_nop.c
+++ b/kernel/trace/trace_nop.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * nop tracer
  *
diff --git a/kernel/trace/trace_output.h b/kernel/trace/trace_output.h
index fabc49bcd493..dbba03ed96de 100644
--- a/kernel/trace/trace_output.h
+++ b/kernel/trace/trace_output.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __TRACE_EVENTS_H
 #define __TRACE_EVENTS_H
 
diff --git a/kernel/trace/trace_sched_switch.c b/kernel/trace/trace_sched_switch.c
index b341c02730be..e288168661e1 100644
--- a/kernel/trace/trace_sched_switch.c
+++ b/kernel/trace/trace_sched_switch.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * trace context switch
  *
diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c
index 0c331978b1a6..7d461dcd4831 100644
--- a/kernel/trace/trace_sched_wakeup.c
+++ b/kernel/trace/trace_sched_wakeup.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * trace task wakeup timings
  *
diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c
index b17ec642793b..cd70eb5df38e 100644
--- a/kernel/trace/trace_selftest.c
+++ b/kernel/trace/trace_selftest.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /* Include in trace.c */
 
 #include <uapi/linux/sched/types.h>
diff --git a/kernel/trace/trace_selftest_dynamic.c b/kernel/trace/trace_selftest_dynamic.c
index b4c475a0a48b..8cda06a10d66 100644
--- a/kernel/trace/trace_selftest_dynamic.c
+++ b/kernel/trace/trace_selftest_dynamic.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include "trace.h"
 
 int DYN_FTRACE_TEST_NAME(void)
diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
index 49cb41412eec..719a52a4064a 100644
--- a/kernel/trace/trace_stack.c
+++ b/kernel/trace/trace_stack.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Copyright (C) 2008 Steven Rostedt <srostedt@redhat.com>
  *
diff --git a/kernel/trace/trace_stat.c b/kernel/trace/trace_stat.c
index 413ff108fbd0..75bf1bcb4a8a 100644
--- a/kernel/trace/trace_stat.c
+++ b/kernel/trace/trace_stat.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Infrastructure for statistic tracing (histogram output).
  *
diff --git a/kernel/trace/trace_stat.h b/kernel/trace/trace_stat.h
index 8f03914b9a6a..76d30b4ebe83 100644
--- a/kernel/trace/trace_stat.h
+++ b/kernel/trace/trace_stat.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __TRACE_STAT_H
 #define __TRACE_STAT_H
 
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index 696afe72d3b1..a2a642f2c64f 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <trace/syscall.h>
 #include <trace/events/syscalls.h>
 #include <linux/syscalls.h>
diff --git a/kernel/trace/tracing_map.h b/kernel/trace/tracing_map.h
index 618838f5f30a..ab0ca77331d0 100644
--- a/kernel/trace/tracing_map.h
+++ b/kernel/trace/tracing_map.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __TRACING_MAP_H
 #define __TRACING_MAP_H
 
diff --git a/kernel/uid16.c b/kernel/uid16.c
index 5c2dc5b2bf4f..ce74a4901d2b 100644
--- a/kernel/uid16.c
+++ b/kernel/uid16.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  *	Wrapper functions for 16bit uid back compatibility. All nicely tied
  *	together in the faint hope we can take the out in five years time.
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index 6bcb854909c0..c8e06703e44c 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Detect hard and soft lockups on a system
  *
diff --git a/kernel/watchdog_hld.c b/kernel/watchdog_hld.c
index 71a62ceacdc8..e449a23e9d59 100644
--- a/kernel/watchdog_hld.c
+++ b/kernel/watchdog_hld.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Detect hard lockups on a system
  *
@@ -12,6 +13,7 @@
 #define pr_fmt(fmt) "NMI watchdog: " fmt
 
 #include <linux/nmi.h>
+#include <linux/atomic.h>
 #include <linux/module.h>
 #include <linux/sched/debug.h>
 
@@ -21,10 +23,11 @@
 static DEFINE_PER_CPU(bool, hard_watchdog_warn);
 static DEFINE_PER_CPU(bool, watchdog_nmi_touch);
 static DEFINE_PER_CPU(struct perf_event *, watchdog_ev);
+static DEFINE_PER_CPU(struct perf_event *, dead_event);
 static struct cpumask dead_events_mask;
 
 static unsigned long hardlockup_allcpu_dumped;
-static unsigned int watchdog_cpus;
+static atomic_t watchdog_cpus = ATOMIC_INIT(0);
 
 void arch_touch_nmi_watchdog(void)
 {
@@ -188,7 +191,8 @@ void hardlockup_detector_perf_enable(void)
 	if (hardlockup_detector_event_create())
 		return;
 
-	if (!watchdog_cpus++)
+	/* use original value for check */
+	if (!atomic_fetch_inc(&watchdog_cpus))
 		pr_info("Enabled. Permanently consumes one hw-PMU counter.\n");
 
 	perf_event_enable(this_cpu_read(watchdog_ev));
@@ -203,8 +207,10 @@ void hardlockup_detector_perf_disable(void)
 
 	if (event) {
 		perf_event_disable(event);
+		this_cpu_write(watchdog_ev, NULL);
+		this_cpu_write(dead_event, event);
 		cpumask_set_cpu(smp_processor_id(), &dead_events_mask);
-		watchdog_cpus--;
+		atomic_dec(&watchdog_cpus);
 	}
 }
 
@@ -218,7 +224,7 @@ void hardlockup_detector_perf_cleanup(void)
 	int cpu;
 
 	for_each_cpu(cpu, &dead_events_mask) {
-		struct perf_event *event = per_cpu(watchdog_ev, cpu);
+		struct perf_event *event = per_cpu(dead_event, cpu);
 
 		/*
 		 * Required because for_each_cpu() reports  unconditionally
@@ -226,7 +232,7 @@ void hardlockup_detector_perf_cleanup(void)
 		 */
 		if (event)
 			perf_event_release_kernel(event);
-		per_cpu(watchdog_ev, cpu) = NULL;
+		per_cpu(dead_event, cpu) = NULL;
 	}
 	cpumask_clear(&dead_events_mask);
 }
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 64d0edf428f8..a2dccfe1acec 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -68,6 +68,7 @@ enum {
 	 * attach_mutex to avoid changing binding state while
 	 * worker_attach_to_pool() is in progress.
 	 */
+	POOL_MANAGER_ACTIVE	= 1 << 0,	/* being managed */
 	POOL_DISASSOCIATED	= 1 << 2,	/* cpu can't serve workers */
 
 	/* worker flags */
@@ -165,7 +166,6 @@ struct worker_pool {
 						/* L: hash of busy workers */
 
 	/* see manage_workers() for details on the two manager mutexes */
-	struct mutex		manager_arb;	/* manager arbitration */
 	struct worker		*manager;	/* L: purely informational */
 	struct mutex		attach_mutex;	/* attach/detach exclusion */
 	struct list_head	workers;	/* A: attached workers */
@@ -299,6 +299,7 @@ static struct workqueue_attrs *wq_update_unbound_numa_attrs_buf;
 
 static DEFINE_MUTEX(wq_pool_mutex);	/* protects pools and workqueues list */
 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 LIST_HEAD(workqueues);		/* PR: list of all workqueues */
 static bool workqueue_freezing;		/* PL: have wqs started freezing? */
@@ -801,7 +802,7 @@ static bool need_to_create_worker(struct worker_pool *pool)
 /* Do we have too many workers and should some go away? */
 static bool too_many_workers(struct worker_pool *pool)
 {
-	bool managing = mutex_is_locked(&pool->manager_arb);
+	bool managing = pool->flags & POOL_MANAGER_ACTIVE;
 	int nr_idle = pool->nr_idle + managing; /* manager is considered idle */
 	int nr_busy = pool->nr_workers - nr_idle;
 
@@ -1980,24 +1981,17 @@ static bool manage_workers(struct worker *worker)
 {
 	struct worker_pool *pool = worker->pool;
 
-	/*
-	 * Anyone who successfully grabs manager_arb wins the arbitration
-	 * and becomes the manager.  mutex_trylock() on pool->manager_arb
-	 * failure while holding pool->lock reliably indicates that someone
-	 * else is managing the pool and the worker which failed trylock
-	 * can proceed to executing work items.  This means that anyone
-	 * grabbing manager_arb is responsible for actually performing
-	 * manager duties.  If manager_arb is grabbed and released without
-	 * actual management, the pool may stall indefinitely.
-	 */
-	if (!mutex_trylock(&pool->manager_arb))
+	if (pool->flags & POOL_MANAGER_ACTIVE)
 		return false;
+
+	pool->flags |= POOL_MANAGER_ACTIVE;
 	pool->manager = worker;
 
 	maybe_create_worker(pool);
 
 	pool->manager = NULL;
-	mutex_unlock(&pool->manager_arb);
+	pool->flags &= ~POOL_MANAGER_ACTIVE;
+	wake_up(&wq_manager_wait);
 	return true;
 }
 
@@ -3248,7 +3242,6 @@ static int init_worker_pool(struct worker_pool *pool)
 	setup_timer(&pool->mayday_timer, pool_mayday_timeout,
 		    (unsigned long)pool);
 
-	mutex_init(&pool->manager_arb);
 	mutex_init(&pool->attach_mutex);
 	INIT_LIST_HEAD(&pool->workers);
 
@@ -3318,13 +3311,15 @@ static void put_unbound_pool(struct worker_pool *pool)
 	hash_del(&pool->hash_node);
 
 	/*
-	 * Become the manager and destroy all workers.  Grabbing
-	 * manager_arb prevents @pool's workers from blocking on
-	 * attach_mutex.
+	 * 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.
 	 */
-	mutex_lock(&pool->manager_arb);
-
 	spin_lock_irq(&pool->lock);
+	wait_event_lock_irq(wq_manager_wait,
+			    !(pool->flags & POOL_MANAGER_ACTIVE), pool->lock);
+	pool->flags |= POOL_MANAGER_ACTIVE;
+
 	while ((worker = first_idle_worker(pool)))
 		destroy_worker(worker);
 	WARN_ON(pool->nr_workers || pool->nr_idle);
@@ -3338,8 +3333,6 @@ static void put_unbound_pool(struct worker_pool *pool)
 	if (pool->detach_completion)
 		wait_for_completion(pool->detach_completion);
 
-	mutex_unlock(&pool->manager_arb);
-
 	/* shut down the timers */
 	del_timer_sync(&pool->idle_timer);
 	del_timer_sync(&pool->mayday_timer);
diff --git a/kernel/workqueue_internal.h b/kernel/workqueue_internal.h
index 8635417c587b..d390d1be3748 100644
--- a/kernel/workqueue_internal.h
+++ b/kernel/workqueue_internal.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * kernel/workqueue_internal.h
  *
@@ -9,6 +10,7 @@
 
 #include <linux/workqueue.h>
 #include <linux/kthread.h>
+#include <linux/preempt.h>
 
 struct worker_pool;
 
@@ -59,7 +61,7 @@ struct worker {
  */
 static inline struct worker *current_wq_worker(void)
 {
-	if (current->flags & PF_WQ_WORKER)
+	if (in_task() && (current->flags & PF_WQ_WORKER))
 		return kthread_data(current);
 	return NULL;
 }