Merge tag 'ib-mfd-gpio-input-pwm-v6.17' of git://git.kernel.org/pub/scm/linux/kernel/git/lee/mfd into next

Merge an immutable branch between MFD, GPIO, Input and PWM to resolve
conflicts for the merge window pull request.

157 files changed, 10498 insertions, 6229 deletions

diff --git a/kernel/Kconfig.kexec b/kernel/Kconfig.kexec
index 4d111f871951..e64ce21f9a80 100644
--- a/kernel/Kconfig.kexec
+++ b/kernel/Kconfig.kexec
@@ -38,8 +38,7 @@ config KEXEC
 config KEXEC_FILE
 	bool "Enable kexec file based system call"
 	depends on ARCH_SUPPORTS_KEXEC_FILE
-	select CRYPTO
-	select CRYPTO_SHA256
+	select CRYPTO_LIB_SHA256
 	select KEXEC_CORE
 	help
 	  This is new version of kexec system call. This system call is
@@ -95,6 +94,20 @@ config KEXEC_JUMP
 	  Jump between original kernel and kexeced kernel and invoke
 	  code in physical address mode via KEXEC
 
+config KEXEC_HANDOVER
+	bool "kexec handover"
+	depends on ARCH_SUPPORTS_KEXEC_HANDOVER && ARCH_SUPPORTS_KEXEC_FILE
+	select MEMBLOCK_KHO_SCRATCH
+	select KEXEC_FILE
+	select DEBUG_FS
+	select LIBFDT
+	select CMA
+	help
+	  Allow kexec to hand over state across kernels by generating and
+	  passing additional metadata to the target kernel. This is useful
+	  to keep data or state alive across the kexec. For this to work,
+	  both source and target kernels need to have this option enabled.
+
 config CRASH_DUMP
 	bool "kernel crash dumps"
 	default ARCH_DEFAULT_CRASH_DUMP
@@ -116,6 +129,23 @@ config CRASH_DUMP
 	  For s390, this option also enables zfcpdump.
 	  See also <file:Documentation/arch/s390/zfcpdump.rst>
 
+config CRASH_DM_CRYPT
+	bool "Support saving crash dump to dm-crypt encrypted volume"
+	depends on KEXEC_FILE
+	depends on CRASH_DUMP
+	depends on DM_CRYPT
+	help
+	  With this option enabled, user space can intereact with
+	  /sys/kernel/config/crash_dm_crypt_keys to make the dm crypt keys
+	  persistent for the dump-capture kernel.
+
+config CRASH_DM_CRYPT_CONFIGS
+	def_tristate CRASH_DM_CRYPT
+	select CONFIGFS_FS
+	help
+	  CRASH_DM_CRYPT cannot directly select CONFIGFS_FS, because that
+	  is required to be built-in.
+
 config CRASH_HOTPLUG
 	bool "Update the crash elfcorehdr on system configuration changes"
 	default y
diff --git a/kernel/Makefile b/kernel/Makefile
index 434929de17ef..32e80dd626af 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -77,9 +77,11 @@ obj-$(CONFIG_VMCORE_INFO) += vmcore_info.o elfcorehdr.o
 obj-$(CONFIG_CRASH_RESERVE) += crash_reserve.o
 obj-$(CONFIG_KEXEC_CORE) += kexec_core.o
 obj-$(CONFIG_CRASH_DUMP) += crash_core.o
+obj-$(CONFIG_CRASH_DM_CRYPT) += crash_dump_dm_crypt.o
 obj-$(CONFIG_KEXEC) += kexec.o
 obj-$(CONFIG_KEXEC_FILE) += kexec_file.o
 obj-$(CONFIG_KEXEC_ELF) += kexec_elf.o
+obj-$(CONFIG_KEXEC_HANDOVER) += kexec_handover.o
 obj-$(CONFIG_BACKTRACE_SELF_TEST) += backtracetest.o
 obj-$(CONFIG_COMPAT) += compat.o
 obj-$(CONFIG_CGROUPS) += cgroup/
diff --git a/kernel/audit.c b/kernel/audit.c
index 5f5bf85bcc90..61b5744d0bb6 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -1956,8 +1956,8 @@ static inline int audit_expand(struct audit_buffer *ab, int extra)
  * will be called a second time.  Currently, we assume that a printk
  * can't format message larger than 1024 bytes, so we don't either.
  */
-static void audit_log_vformat(struct audit_buffer *ab, const char *fmt,
-			      va_list args)
+static __printf(2, 0)
+void audit_log_vformat(struct audit_buffer *ab, const char *fmt, va_list args)
 {
 	int len, avail;
 	struct sk_buff *skb;
@@ -2285,7 +2285,7 @@ void audit_log_path_denied(int type, const char *operation)
 {
 	struct audit_buffer *ab;
 
-	if (!audit_enabled || audit_dummy_context())
+	if (!audit_enabled)
 		return;
 
 	/* Generate log with subject, operation, outcome. */
diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile
index 70502f038b92..3a335c50e6e3 100644
--- a/kernel/bpf/Makefile
+++ b/kernel/bpf/Makefile
@@ -53,6 +53,9 @@ obj-$(CONFIG_BPF_SYSCALL) += relo_core.o
 obj-$(CONFIG_BPF_SYSCALL) += btf_iter.o
 obj-$(CONFIG_BPF_SYSCALL) += btf_relocate.o
 obj-$(CONFIG_BPF_SYSCALL) += kmem_cache_iter.o
+ifeq ($(CONFIG_DMA_SHARED_BUFFER),y)
+obj-$(CONFIG_BPF_SYSCALL) += dmabuf_iter.o
+endif
 
 CFLAGS_REMOVE_percpu_freelist.o = $(CC_FLAGS_FTRACE)
 CFLAGS_REMOVE_bpf_lru_list.o = $(CC_FLAGS_FTRACE)
diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c
index db13ee70d94d..96113633e391 100644
--- a/kernel/bpf/bpf_struct_ops.c
+++ b/kernel/bpf/bpf_struct_ops.c
@@ -601,7 +601,7 @@ int bpf_struct_ops_prepare_trampoline(struct bpf_tramp_links *tlinks,
 	if (model->ret_size > 0)
 		flags |= BPF_TRAMP_F_RET_FENTRY_RET;
 
-	size = arch_bpf_trampoline_size(model, flags, tlinks, NULL);
+	size = arch_bpf_trampoline_size(model, flags, tlinks, stub_func);
 	if (size <= 0)
 		return size ? : -EFAULT;
 
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 16ba36f34dfa..1d2cf898e21e 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -26,6 +26,7 @@
 #include <linux/bsearch.h>
 #include <linux/kobject.h>
 #include <linux/sysfs.h>
+#include <linux/overflow.h>
 
 #include <net/netfilter/nf_bpf_link.h>
 
@@ -3957,7 +3958,7 @@ struct btf_record *btf_parse_fields(const struct btf *btf, const struct btf_type
 	/* This needs to be kzalloc to zero out padding and unused fields, see
 	 * comment in btf_record_equal.
 	 */
-	rec = kzalloc(offsetof(struct btf_record, fields[cnt]), GFP_KERNEL | __GFP_NOWARN);
+	rec = kzalloc(struct_size(rec, fields, cnt), GFP_KERNEL | __GFP_NOWARN);
 	if (!rec)
 		return ERR_PTR(-ENOMEM);
 
@@ -5583,7 +5584,7 @@ btf_parse_struct_metas(struct bpf_verifier_log *log, struct btf *btf)
 		if (id < 0)
 			continue;
 
-		new_aof = krealloc(aof, offsetof(struct btf_id_set, ids[aof->cnt + 1]),
+		new_aof = krealloc(aof, struct_size(new_aof, ids, aof->cnt + 1),
 				   GFP_KERNEL | __GFP_NOWARN);
 		if (!new_aof) {
 			ret = -ENOMEM;
@@ -5610,7 +5611,7 @@ btf_parse_struct_metas(struct bpf_verifier_log *log, struct btf *btf)
 		if (ret != BTF_FIELD_FOUND)
 			continue;
 
-		new_aof = krealloc(aof, offsetof(struct btf_id_set, ids[aof->cnt + 1]),
+		new_aof = krealloc(aof, struct_size(new_aof, ids, aof->cnt + 1),
 				   GFP_KERNEL | __GFP_NOWARN);
 		if (!new_aof) {
 			ret = -ENOMEM;
@@ -5647,7 +5648,7 @@ btf_parse_struct_metas(struct bpf_verifier_log *log, struct btf *btf)
 		continue;
 	parse:
 		tab_cnt = tab ? tab->cnt : 0;
-		new_tab = krealloc(tab, offsetof(struct btf_struct_metas, types[tab_cnt + 1]),
+		new_tab = krealloc(tab, struct_size(new_tab, types, tab_cnt + 1),
 				   GFP_KERNEL | __GFP_NOWARN);
 		if (!new_tab) {
 			ret = -ENOMEM;
@@ -6383,16 +6384,15 @@ struct btf *bpf_prog_get_target_btf(const struct bpf_prog *prog)
 		return prog->aux->attach_btf;
 }
 
-static bool is_int_ptr(struct btf *btf, const struct btf_type *t)
+static bool is_void_or_int_ptr(struct btf *btf, const struct btf_type *t)
 {
 	/* skip modifiers */
 	t = btf_type_skip_modifiers(btf, t->type, NULL);
-
-	return btf_type_is_int(t);
+	return btf_type_is_void(t) || btf_type_is_int(t);
 }
 
-static u32 get_ctx_arg_idx(struct btf *btf, const struct btf_type *func_proto,
-			   int off)
+u32 btf_ctx_arg_idx(struct btf *btf, const struct btf_type *func_proto,
+		    int off)
 {
 	const struct btf_param *args;
 	const struct btf_type *t;
@@ -6541,6 +6541,7 @@ static const struct bpf_raw_tp_null_args raw_tp_null_args[] = {
 	{ "xprt_put_cong", 0x10 },
 	/* tcp */
 	{ "tcp_send_reset", 0x11 },
+	{ "tcp_sendmsg_locked", 0x100 },
 	/* tegra_apb_dma */
 	{ "tegra_dma_tx_status", 0x100 },
 	/* timer_migration */
@@ -6671,7 +6672,7 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type,
 			tname, off);
 		return false;
 	}
-	arg = get_ctx_arg_idx(btf, t, off);
+	arg = btf_ctx_arg_idx(btf, t, off);
 	args = (const struct btf_param *)(t + 1);
 	/* if (t == NULL) Fall back to default BPF prog with
 	 * MAX_BPF_FUNC_REG_ARGS u64 arguments.
@@ -6776,14 +6777,11 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type,
 		}
 	}
 
-	if (t->type == 0)
-		/* This is a pointer to void.
-		 * It is the same as scalar from the verifier safety pov.
-		 * No further pointer walking is allowed.
-		 */
-		return true;
-
-	if (is_int_ptr(btf, t))
+	/*
+	 * If it's a pointer to void, it's the same as scalar from the verifier
+	 * safety POV. Either way, no futher pointer walking is allowed.
+	 */
+	if (is_void_or_int_ptr(btf, t))
 		return true;
 
 	/* this is a pointer to another type */
@@ -6829,10 +6827,10 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type,
 			/* Is this a func with potential NULL args? */
 			if (strcmp(tname, raw_tp_null_args[i].func))
 				continue;
-			if (raw_tp_null_args[i].mask & (0x1 << (arg * 4)))
+			if (raw_tp_null_args[i].mask & (0x1ULL << (arg * 4)))
 				info->reg_type |= PTR_MAYBE_NULL;
 			/* Is the current arg IS_ERR? */
-			if (raw_tp_null_args[i].mask & (0x2 << (arg * 4)))
+			if (raw_tp_null_args[i].mask & (0x2ULL << (arg * 4)))
 				ptr_err_raw_tp = true;
 			break;
 		}
@@ -7662,7 +7660,7 @@ int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog)
 		return 0;
 
 	if (!prog->aux->func_info) {
-		bpf_log(log, "Verifier bug\n");
+		verifier_bug(env, "func_info undefined");
 		return -EFAULT;
 	}
 
@@ -7686,7 +7684,7 @@ int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog)
 	tname = btf_name_by_offset(btf, fn_t->name_off);
 
 	if (prog->aux->func_info_aux[subprog].unreliable) {
-		bpf_log(log, "Verifier bug in function %s()\n", tname);
+		verifier_bug(env, "unreliable BTF for function %s()", tname);
 		return -EFAULT;
 	}
 	if (prog_type == BPF_PROG_TYPE_EXT)
@@ -8563,7 +8561,7 @@ static int btf_populate_kfunc_set(struct btf *btf, enum btf_kfunc_hook hook,
 
 	/* Grow set */
 	set = krealloc(tab->sets[hook],
-		       offsetof(struct btf_id_set8, pairs[set_cnt + add_set->cnt]),
+		       struct_size(set, pairs, set_cnt + add_set->cnt),
 		       GFP_KERNEL | __GFP_NOWARN);
 	if (!set) {
 		ret = -ENOMEM;
@@ -8849,7 +8847,7 @@ int register_btf_id_dtor_kfuncs(const struct btf_id_dtor_kfunc *dtors, u32 add_c
 	}
 
 	tab = krealloc(btf->dtor_kfunc_tab,
-		       offsetof(struct btf_id_dtor_kfunc_tab, dtors[tab_cnt + add_cnt]),
+		       struct_size(tab, dtors, tab_cnt + add_cnt),
 		       GFP_KERNEL | __GFP_NOWARN);
 	if (!tab) {
 		ret = -ENOMEM;
@@ -9407,8 +9405,7 @@ btf_add_struct_ops(struct btf *btf, struct bpf_struct_ops *st_ops,
 
 	tab = btf->struct_ops_tab;
 	if (!tab) {
-		tab = kzalloc(offsetof(struct btf_struct_ops_tab, ops[4]),
-			      GFP_KERNEL);
+		tab = kzalloc(struct_size(tab, ops, 4), GFP_KERNEL);
 		if (!tab)
 			return -ENOMEM;
 		tab->capacity = 4;
@@ -9421,8 +9418,7 @@ btf_add_struct_ops(struct btf *btf, struct bpf_struct_ops *st_ops,
 
 	if (tab->cnt == tab->capacity) {
 		new_tab = krealloc(tab,
-				   offsetof(struct btf_struct_ops_tab,
-					    ops[tab->capacity * 2]),
+				   struct_size(tab, ops, tab->capacity * 2),
 				   GFP_KERNEL);
 		if (!new_tab)
 			return -ENOMEM;
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index 84f58f3d028a..9122c39870bf 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -41,6 +41,19 @@ static int __init cgroup_bpf_wq_init(void)
 }
 core_initcall(cgroup_bpf_wq_init);
 
+static int cgroup_bpf_lifetime_notify(struct notifier_block *nb,
+				      unsigned long action, void *data);
+
+static struct notifier_block cgroup_bpf_lifetime_nb = {
+	.notifier_call = cgroup_bpf_lifetime_notify,
+};
+
+void __init cgroup_bpf_lifetime_notifier_init(void)
+{
+	BUG_ON(blocking_notifier_chain_register(&cgroup_lifetime_notifier,
+						&cgroup_bpf_lifetime_nb));
+}
+
 /* __always_inline is necessary to prevent indirect call through run_prog
  * function pointer.
  */
@@ -206,7 +219,7 @@ bpf_cgroup_atype_find(enum bpf_attach_type attach_type, u32 attach_btf_id)
 }
 #endif /* CONFIG_BPF_LSM */
 
-void cgroup_bpf_offline(struct cgroup *cgrp)
+static void cgroup_bpf_offline(struct cgroup *cgrp)
 {
 	cgroup_get(cgrp);
 	percpu_ref_kill(&cgrp->bpf.refcnt);
@@ -491,7 +504,7 @@ static void activate_effective_progs(struct cgroup *cgrp,
  * cgroup_bpf_inherit() - inherit effective programs from parent
  * @cgrp: the cgroup to modify
  */
-int cgroup_bpf_inherit(struct cgroup *cgrp)
+static int cgroup_bpf_inherit(struct cgroup *cgrp)
 {
 /* has to use marco instead of const int, since compiler thinks
  * that array below is variable length
@@ -534,6 +547,27 @@ cleanup:
 	return -ENOMEM;
 }
 
+static int cgroup_bpf_lifetime_notify(struct notifier_block *nb,
+				      unsigned long action, void *data)
+{
+	struct cgroup *cgrp = data;
+	int ret = 0;
+
+	if (cgrp->root != &cgrp_dfl_root)
+		return NOTIFY_OK;
+
+	switch (action) {
+	case CGROUP_LIFETIME_ONLINE:
+		ret = cgroup_bpf_inherit(cgrp);
+		break;
+	case CGROUP_LIFETIME_OFFLINE:
+		cgroup_bpf_offline(cgrp);
+		break;
+	}
+
+	return notifier_from_errno(ret);
+}
+
 static int update_effective_progs(struct cgroup *cgrp,
 				  enum cgroup_bpf_attach_type atype)
 {
@@ -1653,10 +1687,6 @@ cgroup_dev_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	if (func_proto)
 		return func_proto;
 
-	func_proto = cgroup_current_func_proto(func_id, prog);
-	if (func_proto)
-		return func_proto;
-
 	switch (func_id) {
 	case BPF_FUNC_perf_event_output:
 		return &bpf_event_output_data_proto;
@@ -2204,10 +2234,6 @@ sysctl_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	if (func_proto)
 		return func_proto;
 
-	func_proto = cgroup_current_func_proto(func_id, prog);
-	if (func_proto)
-		return func_proto;
-
 	switch (func_id) {
 	case BPF_FUNC_sysctl_get_name:
 		return &bpf_sysctl_get_name_proto;
@@ -2351,10 +2377,6 @@ cg_sockopt_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	if (func_proto)
 		return func_proto;
 
-	func_proto = cgroup_current_func_proto(func_id, prog);
-	if (func_proto)
-		return func_proto;
-
 	switch (func_id) {
 #ifdef CONFIG_NET
 	case BPF_FUNC_get_netns_cookie:
@@ -2601,23 +2623,3 @@ cgroup_common_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return NULL;
 	}
 }
-
-/* Common helpers for cgroup hooks with valid process context. */
-const struct bpf_func_proto *
-cgroup_current_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
-{
-	switch (func_id) {
-	case BPF_FUNC_get_current_uid_gid:
-		return &bpf_get_current_uid_gid_proto;
-	case BPF_FUNC_get_current_comm:
-		return &bpf_get_current_comm_proto;
-#ifdef CONFIG_CGROUP_NET_CLASSID
-	case BPF_FUNC_get_cgroup_classid:
-		return &bpf_get_cgroup_classid_curr_proto;
-#endif
-	case BPF_FUNC_current_task_under_cgroup:
-		return &bpf_current_task_under_cgroup_proto;
-	default:
-		return NULL;
-	}
-}
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index ba6b6118cf50..c20babbf998f 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -2358,8 +2358,8 @@ static unsigned int __bpf_prog_ret0_warn(const void *ctx,
 	return 0;
 }
 
-bool bpf_prog_map_compatible(struct bpf_map *map,
-			     const struct bpf_prog *fp)
+static bool __bpf_prog_map_compatible(struct bpf_map *map,
+				      const struct bpf_prog *fp)
 {
 	enum bpf_prog_type prog_type = resolve_prog_type(fp);
 	bool ret;
@@ -2368,14 +2368,6 @@ bool bpf_prog_map_compatible(struct bpf_map *map,
 	if (fp->kprobe_override)
 		return false;
 
-	/* XDP programs inserted into maps are not guaranteed to run on
-	 * a particular netdev (and can run outside driver context entirely
-	 * in the case of devmap and cpumap). Until device checks
-	 * are implemented, prohibit adding dev-bound programs to program maps.
-	 */
-	if (bpf_prog_is_dev_bound(aux))
-		return false;
-
 	spin_lock(&map->owner.lock);
 	if (!map->owner.type) {
 		/* There's no owner yet where we could check for
@@ -2409,6 +2401,19 @@ bool bpf_prog_map_compatible(struct bpf_map *map,
 	return ret;
 }
 
+bool bpf_prog_map_compatible(struct bpf_map *map, const struct bpf_prog *fp)
+{
+	/* XDP programs inserted into maps are not guaranteed to run on
+	 * a particular netdev (and can run outside driver context entirely
+	 * in the case of devmap and cpumap). Until device checks
+	 * are implemented, prohibit adding dev-bound programs to program maps.
+	 */
+	if (bpf_prog_is_dev_bound(fp->aux))
+		return false;
+
+	return __bpf_prog_map_compatible(map, fp);
+}
+
 static int bpf_check_tail_call(const struct bpf_prog *fp)
 {
 	struct bpf_prog_aux *aux = fp->aux;
@@ -2421,7 +2426,7 @@ static int bpf_check_tail_call(const struct bpf_prog *fp)
 		if (!map_type_contains_progs(map))
 			continue;
 
-		if (!bpf_prog_map_compatible(map, fp)) {
+		if (!__bpf_prog_map_compatible(map, fp)) {
 			ret = -EINVAL;
 			goto out;
 		}
@@ -2469,7 +2474,7 @@ struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err)
 	/* In case of BPF to BPF calls, verifier did all the prep
 	 * work with regards to JITing, etc.
 	 */
-	bool jit_needed = false;
+	bool jit_needed = fp->jit_requested;
 
 	if (fp->bpf_func)
 		goto finalize;
diff --git a/kernel/bpf/dmabuf_iter.c b/kernel/bpf/dmabuf_iter.c
new file mode 100644
index 000000000000..4dd7ef7c145c
--- /dev/null
+++ b/kernel/bpf/dmabuf_iter.c
@@ -0,0 +1,150 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (c) 2025 Google LLC */
+#include <linux/bpf.h>
+#include <linux/btf_ids.h>
+#include <linux/dma-buf.h>
+#include <linux/kernel.h>
+#include <linux/seq_file.h>
+
+static void *dmabuf_iter_seq_start(struct seq_file *seq, loff_t *pos)
+{
+	if (*pos)
+		return NULL;
+
+	return dma_buf_iter_begin();
+}
+
+static void *dmabuf_iter_seq_next(struct seq_file *seq, void *v, loff_t *pos)
+{
+	struct dma_buf *dmabuf = v;
+
+	++*pos;
+
+	return dma_buf_iter_next(dmabuf);
+}
+
+struct bpf_iter__dmabuf {
+	__bpf_md_ptr(struct bpf_iter_meta *, meta);
+	__bpf_md_ptr(struct dma_buf *, dmabuf);
+};
+
+static int __dmabuf_seq_show(struct seq_file *seq, void *v, bool in_stop)
+{
+	struct bpf_iter_meta meta = {
+		.seq = seq,
+	};
+	struct bpf_iter__dmabuf ctx = {
+		.meta = &meta,
+		.dmabuf = v,
+	};
+	struct bpf_prog *prog = bpf_iter_get_info(&meta, in_stop);
+
+	if (prog)
+		return bpf_iter_run_prog(prog, &ctx);
+
+	return 0;
+}
+
+static int dmabuf_iter_seq_show(struct seq_file *seq, void *v)
+{
+	return __dmabuf_seq_show(seq, v, false);
+}
+
+static void dmabuf_iter_seq_stop(struct seq_file *seq, void *v)
+{
+	struct dma_buf *dmabuf = v;
+
+	if (dmabuf)
+		dma_buf_put(dmabuf);
+}
+
+static const struct seq_operations dmabuf_iter_seq_ops = {
+	.start	= dmabuf_iter_seq_start,
+	.next	= dmabuf_iter_seq_next,
+	.stop	= dmabuf_iter_seq_stop,
+	.show	= dmabuf_iter_seq_show,
+};
+
+static void bpf_iter_dmabuf_show_fdinfo(const struct bpf_iter_aux_info *aux,
+					struct seq_file *seq)
+{
+	seq_puts(seq, "dmabuf iter\n");
+}
+
+static const struct bpf_iter_seq_info dmabuf_iter_seq_info = {
+	.seq_ops		= &dmabuf_iter_seq_ops,
+	.init_seq_private	= NULL,
+	.fini_seq_private	= NULL,
+	.seq_priv_size		= 0,
+};
+
+static struct bpf_iter_reg bpf_dmabuf_reg_info = {
+	.target			= "dmabuf",
+	.feature                = BPF_ITER_RESCHED,
+	.show_fdinfo		= bpf_iter_dmabuf_show_fdinfo,
+	.ctx_arg_info_size	= 1,
+	.ctx_arg_info		= {
+		{ offsetof(struct bpf_iter__dmabuf, dmabuf),
+		  PTR_TO_BTF_ID_OR_NULL },
+	},
+	.seq_info		= &dmabuf_iter_seq_info,
+};
+
+DEFINE_BPF_ITER_FUNC(dmabuf, struct bpf_iter_meta *meta, struct dma_buf *dmabuf)
+BTF_ID_LIST_SINGLE(bpf_dmabuf_btf_id, struct, dma_buf)
+
+static int __init dmabuf_iter_init(void)
+{
+	bpf_dmabuf_reg_info.ctx_arg_info[0].btf_id = bpf_dmabuf_btf_id[0];
+	return bpf_iter_reg_target(&bpf_dmabuf_reg_info);
+}
+
+late_initcall(dmabuf_iter_init);
+
+struct bpf_iter_dmabuf {
+	/*
+	 * opaque iterator state; having __u64 here allows to preserve correct
+	 * alignment requirements in vmlinux.h, generated from BTF
+	 */
+	__u64 __opaque[1];
+} __aligned(8);
+
+/* Non-opaque version of bpf_iter_dmabuf */
+struct bpf_iter_dmabuf_kern {
+	struct dma_buf *dmabuf;
+} __aligned(8);
+
+__bpf_kfunc_start_defs();
+
+__bpf_kfunc int bpf_iter_dmabuf_new(struct bpf_iter_dmabuf *it)
+{
+	struct bpf_iter_dmabuf_kern *kit = (void *)it;
+
+	BUILD_BUG_ON(sizeof(*kit) > sizeof(*it));
+	BUILD_BUG_ON(__alignof__(*kit) != __alignof__(*it));
+
+	kit->dmabuf = NULL;
+	return 0;
+}
+
+__bpf_kfunc struct dma_buf *bpf_iter_dmabuf_next(struct bpf_iter_dmabuf *it)
+{
+	struct bpf_iter_dmabuf_kern *kit = (void *)it;
+
+	if (kit->dmabuf)
+		kit->dmabuf = dma_buf_iter_next(kit->dmabuf);
+	else
+		kit->dmabuf = dma_buf_iter_begin();
+
+	return kit->dmabuf;
+}
+
+__bpf_kfunc void bpf_iter_dmabuf_destroy(struct bpf_iter_dmabuf *it)
+{
+	struct bpf_iter_dmabuf_kern *kit = (void *)it;
+
+	if (kit->dmabuf)
+		dma_buf_put(kit->dmabuf);
+}
+
+__bpf_kfunc_end_defs();
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index 92b606d60020..71f9931ac64c 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -175,20 +175,30 @@ static bool htab_is_percpu(const struct bpf_htab *htab)
 		htab->map.map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH;
 }
 
+static inline bool is_fd_htab(const struct bpf_htab *htab)
+{
+	return htab->map.map_type == BPF_MAP_TYPE_HASH_OF_MAPS;
+}
+
+static inline void *htab_elem_value(struct htab_elem *l, u32 key_size)
+{
+	return l->key + round_up(key_size, 8);
+}
+
 static inline void htab_elem_set_ptr(struct htab_elem *l, u32 key_size,
 				     void __percpu *pptr)
 {
-	*(void __percpu **)(l->key + roundup(key_size, 8)) = pptr;
+	*(void __percpu **)htab_elem_value(l, key_size) = pptr;
 }
 
 static inline void __percpu *htab_elem_get_ptr(struct htab_elem *l, u32 key_size)
 {
-	return *(void __percpu **)(l->key + roundup(key_size, 8));
+	return *(void __percpu **)htab_elem_value(l, key_size);
 }
 
 static void *fd_htab_map_get_ptr(const struct bpf_map *map, struct htab_elem *l)
 {
-	return *(void **)(l->key + roundup(map->key_size, 8));
+	return *(void **)htab_elem_value(l, map->key_size);
 }
 
 static struct htab_elem *get_htab_elem(struct bpf_htab *htab, int i)
@@ -196,9 +206,13 @@ static struct htab_elem *get_htab_elem(struct bpf_htab *htab, int i)
 	return (struct htab_elem *) (htab->elems + i * (u64)htab->elem_size);
 }
 
+/* Both percpu and fd htab support in-place update, so no need for
+ * extra elem. LRU itself can remove the least used element, so
+ * there is no need for an extra elem during map_update.
+ */
 static bool htab_has_extra_elems(struct bpf_htab *htab)
 {
-	return !htab_is_percpu(htab) && !htab_is_lru(htab);
+	return !htab_is_percpu(htab) && !htab_is_lru(htab) && !is_fd_htab(htab);
 }
 
 static void htab_free_prealloced_timers_and_wq(struct bpf_htab *htab)
@@ -215,10 +229,10 @@ static void htab_free_prealloced_timers_and_wq(struct bpf_htab *htab)
 		elem = get_htab_elem(htab, i);
 		if (btf_record_has_field(htab->map.record, BPF_TIMER))
 			bpf_obj_free_timer(htab->map.record,
-					   elem->key + round_up(htab->map.key_size, 8));
+					   htab_elem_value(elem, htab->map.key_size));
 		if (btf_record_has_field(htab->map.record, BPF_WORKQUEUE))
 			bpf_obj_free_workqueue(htab->map.record,
-					       elem->key + round_up(htab->map.key_size, 8));
+					       htab_elem_value(elem, htab->map.key_size));
 		cond_resched();
 	}
 }
@@ -245,7 +259,8 @@ static void htab_free_prealloced_fields(struct bpf_htab *htab)
 				cond_resched();
 			}
 		} else {
-			bpf_obj_free_fields(htab->map.record, elem->key + round_up(htab->map.key_size, 8));
+			bpf_obj_free_fields(htab->map.record,
+					    htab_elem_value(elem, htab->map.key_size));
 			cond_resched();
 		}
 		cond_resched();
@@ -453,8 +468,6 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr)
 {
 	bool percpu = (attr->map_type == BPF_MAP_TYPE_PERCPU_HASH ||
 		       attr->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH);
-	bool lru = (attr->map_type == BPF_MAP_TYPE_LRU_HASH ||
-		    attr->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH);
 	/* percpu_lru means each cpu has its own LRU list.
 	 * it is different from BPF_MAP_TYPE_PERCPU_HASH where
 	 * the map's value itself is percpu.  percpu_lru has
@@ -549,10 +562,7 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr)
 		if (err)
 			goto free_map_locked;
 
-		if (!percpu && !lru) {
-			/* lru itself can remove the least used element, so
-			 * there is no need for an extra elem during map_update.
-			 */
+		if (htab_has_extra_elems(htab)) {
 			err = alloc_extra_elems(htab);
 			if (err)
 				goto free_prealloc;
@@ -670,7 +680,7 @@ static void *htab_map_lookup_elem(struct bpf_map *map, void *key)
 	struct htab_elem *l = __htab_map_lookup_elem(map, key);
 
 	if (l)
-		return l->key + round_up(map->key_size, 8);
+		return htab_elem_value(l, map->key_size);
 
 	return NULL;
 }
@@ -709,7 +719,7 @@ static __always_inline void *__htab_lru_map_lookup_elem(struct bpf_map *map,
 	if (l) {
 		if (mark)
 			bpf_lru_node_set_ref(&l->lru_node);
-		return l->key + round_up(map->key_size, 8);
+		return htab_elem_value(l, map->key_size);
 	}
 
 	return NULL;
@@ -763,7 +773,7 @@ static void check_and_free_fields(struct bpf_htab *htab,
 		for_each_possible_cpu(cpu)
 			bpf_obj_free_fields(htab->map.record, per_cpu_ptr(pptr, cpu));
 	} else {
-		void *map_value = elem->key + round_up(htab->map.key_size, 8);
+		void *map_value = htab_elem_value(elem, htab->map.key_size);
 
 		bpf_obj_free_fields(htab->map.record, map_value);
 	}
@@ -968,8 +978,7 @@ static void pcpu_init_value(struct bpf_htab *htab, void __percpu *pptr,
 
 static bool fd_htab_map_needs_adjust(const struct bpf_htab *htab)
 {
-	return htab->map.map_type == BPF_MAP_TYPE_HASH_OF_MAPS &&
-	       BITS_PER_LONG == 64;
+	return is_fd_htab(htab) && BITS_PER_LONG == 64;
 }
 
 static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key,
@@ -1039,11 +1048,9 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key,
 			htab_elem_set_ptr(l_new, key_size, pptr);
 	} else if (fd_htab_map_needs_adjust(htab)) {
 		size = round_up(size, 8);
-		memcpy(l_new->key + round_up(key_size, 8), value, size);
+		memcpy(htab_elem_value(l_new, key_size), value, size);
 	} else {
-		copy_map_value(&htab->map,
-			       l_new->key + round_up(key_size, 8),
-			       value);
+		copy_map_value(&htab->map, htab_elem_value(l_new, key_size), value);
 	}
 
 	l_new->hash = hash;
@@ -1072,10 +1079,9 @@ static long htab_map_update_elem(struct bpf_map *map, void *key, void *value,
 				 u64 map_flags)
 {
 	struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
-	struct htab_elem *l_new = NULL, *l_old;
+	struct htab_elem *l_new, *l_old;
 	struct hlist_nulls_head *head;
 	unsigned long flags;
-	void *old_map_ptr;
 	struct bucket *b;
 	u32 key_size, hash;
 	int ret;
@@ -1106,7 +1112,7 @@ static long htab_map_update_elem(struct bpf_map *map, void *key, void *value,
 		if (l_old) {
 			/* grab the element lock and update value in place */
 			copy_map_value_locked(map,
-					      l_old->key + round_up(key_size, 8),
+					      htab_elem_value(l_old, key_size),
 					      value, false);
 			return 0;
 		}
@@ -1134,7 +1140,7 @@ static long htab_map_update_elem(struct bpf_map *map, void *key, void *value,
 		 * and update element in place
 		 */
 		copy_map_value_locked(map,
-				      l_old->key + round_up(key_size, 8),
+				      htab_elem_value(l_old, key_size),
 				      value, false);
 		ret = 0;
 		goto err;
@@ -1156,24 +1162,14 @@ static long htab_map_update_elem(struct bpf_map *map, void *key, void *value,
 		hlist_nulls_del_rcu(&l_old->hash_node);
 
 		/* l_old has already been stashed in htab->extra_elems, free
-		 * its special fields before it is available for reuse. Also
-		 * save the old map pointer in htab of maps before unlock
-		 * and release it after unlock.
+		 * its special fields before it is available for reuse.
 		 */
-		old_map_ptr = NULL;
-		if (htab_is_prealloc(htab)) {
-			if (map->ops->map_fd_put_ptr)
-				old_map_ptr = fd_htab_map_get_ptr(map, l_old);
+		if (htab_is_prealloc(htab))
 			check_and_free_fields(htab, l_old);
-		}
 	}
 	htab_unlock_bucket(b, flags);
-	if (l_old) {
-		if (old_map_ptr)
-			map->ops->map_fd_put_ptr(map, old_map_ptr, true);
-		if (!htab_is_prealloc(htab))
-			free_htab_elem(htab, l_old);
-	}
+	if (l_old && !htab_is_prealloc(htab))
+		free_htab_elem(htab, l_old);
 	return 0;
 err:
 	htab_unlock_bucket(b, flags);
@@ -1220,8 +1216,7 @@ static long htab_lru_map_update_elem(struct bpf_map *map, void *key, void *value
 	l_new = prealloc_lru_pop(htab, key, hash);
 	if (!l_new)
 		return -ENOMEM;
-	copy_map_value(&htab->map,
-		       l_new->key + round_up(map->key_size, 8), value);
+	copy_map_value(&htab->map, htab_elem_value(l_new, map->key_size), value);
 
 	ret = htab_lock_bucket(b, &flags);
 	if (ret)
@@ -1255,13 +1250,14 @@ err_lock_bucket:
 	return ret;
 }
 
-static long __htab_percpu_map_update_elem(struct bpf_map *map, void *key,
+static long htab_map_update_elem_in_place(struct bpf_map *map, void *key,
 					  void *value, u64 map_flags,
-					  bool onallcpus)
+					  bool percpu, bool onallcpus)
 {
 	struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
-	struct htab_elem *l_new = NULL, *l_old;
+	struct htab_elem *l_new, *l_old;
 	struct hlist_nulls_head *head;
+	void *old_map_ptr = NULL;
 	unsigned long flags;
 	struct bucket *b;
 	u32 key_size, hash;
@@ -1292,21 +1288,29 @@ static long __htab_percpu_map_update_elem(struct bpf_map *map, void *key,
 		goto err;
 
 	if (l_old) {
-		/* per-cpu hash map can update value in-place */
-		pcpu_copy_value(htab, htab_elem_get_ptr(l_old, key_size),
-				value, onallcpus);
+		/* Update value in-place */
+		if (percpu) {
+			pcpu_copy_value(htab, htab_elem_get_ptr(l_old, key_size),
+					value, onallcpus);
+		} else {
+			void **inner_map_pptr = htab_elem_value(l_old, key_size);
+
+			old_map_ptr = *inner_map_pptr;
+			WRITE_ONCE(*inner_map_pptr, *(void **)value);
+		}
 	} else {
 		l_new = alloc_htab_elem(htab, key, value, key_size,
-					hash, true, onallcpus, NULL);
+					hash, percpu, onallcpus, NULL);
 		if (IS_ERR(l_new)) {
 			ret = PTR_ERR(l_new);
 			goto err;
 		}
 		hlist_nulls_add_head_rcu(&l_new->hash_node, head);
 	}
-	ret = 0;
 err:
 	htab_unlock_bucket(b, flags);
+	if (old_map_ptr)
+		map->ops->map_fd_put_ptr(map, old_map_ptr, true);
 	return ret;
 }
 
@@ -1383,7 +1387,7 @@ err_lock_bucket:
 static long htab_percpu_map_update_elem(struct bpf_map *map, void *key,
 					void *value, u64 map_flags)
 {
-	return __htab_percpu_map_update_elem(map, key, value, map_flags, false);
+	return htab_map_update_elem_in_place(map, key, value, map_flags, true, false);
 }
 
 static long htab_lru_percpu_map_update_elem(struct bpf_map *map, void *key,
@@ -1500,10 +1504,10 @@ static void htab_free_malloced_timers_and_wq(struct bpf_htab *htab)
 			/* We only free timer on uref dropping to zero */
 			if (btf_record_has_field(htab->map.record, BPF_TIMER))
 				bpf_obj_free_timer(htab->map.record,
-						   l->key + round_up(htab->map.key_size, 8));
+						   htab_elem_value(l, htab->map.key_size));
 			if (btf_record_has_field(htab->map.record, BPF_WORKQUEUE))
 				bpf_obj_free_workqueue(htab->map.record,
-						       l->key + round_up(htab->map.key_size, 8));
+						       htab_elem_value(l, htab->map.key_size));
 		}
 		cond_resched_rcu();
 	}
@@ -1615,15 +1619,12 @@ static int __htab_map_lookup_and_delete_elem(struct bpf_map *map, void *key,
 			off += roundup_value_size;
 		}
 	} else {
-		u32 roundup_key_size = round_up(map->key_size, 8);
+		void *src = htab_elem_value(l, map->key_size);
 
 		if (flags & BPF_F_LOCK)
-			copy_map_value_locked(map, value, l->key +
-					      roundup_key_size,
-					      true);
+			copy_map_value_locked(map, value, src, true);
 		else
-			copy_map_value(map, value, l->key +
-				       roundup_key_size);
+			copy_map_value(map, value, src);
 		/* Zeroing special fields in the temp buffer */
 		check_and_init_map_value(map, value);
 	}
@@ -1680,12 +1681,12 @@ __htab_map_lookup_and_delete_batch(struct bpf_map *map,
 				   bool is_percpu)
 {
 	struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
-	u32 bucket_cnt, total, key_size, value_size, roundup_key_size;
 	void *keys = NULL, *values = NULL, *value, *dst_key, *dst_val;
 	void __user *uvalues = u64_to_user_ptr(attr->batch.values);
 	void __user *ukeys = u64_to_user_ptr(attr->batch.keys);
 	void __user *ubatch = u64_to_user_ptr(attr->batch.in_batch);
 	u32 batch, max_count, size, bucket_size, map_id;
+	u32 bucket_cnt, total, key_size, value_size;
 	struct htab_elem *node_to_free = NULL;
 	u64 elem_map_flags, map_flags;
 	struct hlist_nulls_head *head;
@@ -1720,7 +1721,6 @@ __htab_map_lookup_and_delete_batch(struct bpf_map *map,
 		return -ENOENT;
 
 	key_size = htab->map.key_size;
-	roundup_key_size = round_up(htab->map.key_size, 8);
 	value_size = htab->map.value_size;
 	size = round_up(value_size, 8);
 	if (is_percpu)
@@ -1812,8 +1812,8 @@ again_nocopy:
 				off += size;
 			}
 		} else {
-			value = l->key + roundup_key_size;
-			if (map->map_type == BPF_MAP_TYPE_HASH_OF_MAPS) {
+			value = htab_elem_value(l, key_size);
+			if (is_fd_htab(htab)) {
 				struct bpf_map **inner_map = value;
 
 				 /* Actual value is the id of the inner map */
@@ -2063,11 +2063,11 @@ static void *bpf_hash_map_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 static int __bpf_hash_map_seq_show(struct seq_file *seq, struct htab_elem *elem)
 {
 	struct bpf_iter_seq_hash_map_info *info = seq->private;
-	u32 roundup_key_size, roundup_value_size;
 	struct bpf_iter__bpf_map_elem ctx = {};
 	struct bpf_map *map = info->map;
 	struct bpf_iter_meta meta;
 	int ret = 0, off = 0, cpu;
+	u32 roundup_value_size;
 	struct bpf_prog *prog;
 	void __percpu *pptr;
 
@@ -2077,10 +2077,9 @@ static int __bpf_hash_map_seq_show(struct seq_file *seq, struct htab_elem *elem)
 		ctx.meta = &meta;
 		ctx.map = info->map;
 		if (elem) {
-			roundup_key_size = round_up(map->key_size, 8);
 			ctx.key = elem->key;
 			if (!info->percpu_value_buf) {
-				ctx.value = elem->key + roundup_key_size;
+				ctx.value = htab_elem_value(elem, map->key_size);
 			} else {
 				roundup_value_size = round_up(map->value_size, 8);
 				pptr = htab_elem_get_ptr(elem, map->key_size);
@@ -2165,7 +2164,6 @@ static long bpf_for_each_hash_elem(struct bpf_map *map, bpf_callback_t callback_
 	struct hlist_nulls_head *head;
 	struct hlist_nulls_node *n;
 	struct htab_elem *elem;
-	u32 roundup_key_size;
 	int i, num_elems = 0;
 	void __percpu *pptr;
 	struct bucket *b;
@@ -2180,7 +2178,6 @@ static long bpf_for_each_hash_elem(struct bpf_map *map, bpf_callback_t callback_
 
 	is_percpu = htab_is_percpu(htab);
 
-	roundup_key_size = round_up(map->key_size, 8);
 	/* migration has been disabled, so percpu value prepared here will be
 	 * the same as the one seen by the bpf program with
 	 * bpf_map_lookup_elem().
@@ -2196,7 +2193,7 @@ static long bpf_for_each_hash_elem(struct bpf_map *map, bpf_callback_t callback_
 				pptr = htab_elem_get_ptr(elem, map->key_size);
 				val = this_cpu_ptr(pptr);
 			} else {
-				val = elem->key + roundup_key_size;
+				val = htab_elem_value(elem, map->key_size);
 			}
 			num_elems++;
 			ret = callback_fn((u64)(long)map, (u64)(long)key,
@@ -2411,8 +2408,8 @@ int bpf_percpu_hash_update(struct bpf_map *map, void *key, void *value,
 		ret = __htab_lru_percpu_map_update_elem(map, key, value,
 							map_flags, true);
 	else
-		ret = __htab_percpu_map_update_elem(map, key, value, map_flags,
-						    true);
+		ret = htab_map_update_elem_in_place(map, key, value, map_flags,
+						    true, true);
 	rcu_read_unlock();
 
 	return ret;
@@ -2536,24 +2533,23 @@ int bpf_fd_htab_map_lookup_elem(struct bpf_map *map, void *key, u32 *value)
 	return ret;
 }
 
-/* only called from syscall */
+/* Only called from syscall */
 int bpf_fd_htab_map_update_elem(struct bpf_map *map, struct file *map_file,
 				void *key, void *value, u64 map_flags)
 {
 	void *ptr;
 	int ret;
-	u32 ufd = *(u32 *)value;
 
-	ptr = map->ops->map_fd_get_ptr(map, map_file, ufd);
+	ptr = map->ops->map_fd_get_ptr(map, map_file, *(int *)value);
 	if (IS_ERR(ptr))
 		return PTR_ERR(ptr);
 
 	/* The htab bucket lock is always held during update operations in fd
 	 * htab map, and the following rcu_read_lock() is only used to avoid
-	 * the WARN_ON_ONCE in htab_map_update_elem().
+	 * the WARN_ON_ONCE in htab_map_update_elem_in_place().
 	 */
 	rcu_read_lock();
-	ret = htab_map_update_elem(map, key, &ptr, map_flags);
+	ret = htab_map_update_elem_in_place(map, key, &ptr, map_flags, false, false);
 	rcu_read_unlock();
 	if (ret)
 		map->ops->map_fd_put_ptr(map, ptr, false);
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index e3a2662f4e33..b71e428ad936 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -23,6 +23,7 @@
 #include <linux/btf_ids.h>
 #include <linux/bpf_mem_alloc.h>
 #include <linux/kasan.h>
+#include <linux/bpf_verifier.h>
 
 #include "../../lib/kstrtox.h"
 
@@ -129,7 +130,8 @@ const struct bpf_func_proto bpf_map_peek_elem_proto = {
 
 BPF_CALL_3(bpf_map_lookup_percpu_elem, struct bpf_map *, map, void *, key, u32, cpu)
 {
-	WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_bh_held());
+	WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held() &&
+		     !rcu_read_lock_bh_held());
 	return (unsigned long) map->ops->map_lookup_percpu_elem(map, key, cpu);
 }
 
@@ -1713,16 +1715,6 @@ void bpf_dynptr_set_null(struct bpf_dynptr_kern *ptr)
 	memset(ptr, 0, sizeof(*ptr));
 }
 
-static int bpf_dynptr_check_off_len(const struct bpf_dynptr_kern *ptr, u32 offset, u32 len)
-{
-	u32 size = __bpf_dynptr_size(ptr);
-
-	if (len > size || offset > size - len)
-		return -E2BIG;
-
-	return 0;
-}
-
 BPF_CALL_4(bpf_dynptr_from_mem, void *, data, u32, size, u64, flags, struct bpf_dynptr_kern *, ptr)
 {
 	int err;
@@ -1809,8 +1801,8 @@ static const struct bpf_func_proto bpf_dynptr_read_proto = {
 	.arg5_type	= ARG_ANYTHING,
 };
 
-static int __bpf_dynptr_write(const struct bpf_dynptr_kern *dst, u32 offset, void *src,
-			      u32 len, u64 flags)
+int __bpf_dynptr_write(const struct bpf_dynptr_kern *dst, u32 offset, void *src,
+		       u32 len, u64 flags)
 {
 	enum bpf_dynptr_type type;
 	int err;
@@ -1912,6 +1904,12 @@ const struct bpf_func_proto bpf_probe_read_user_str_proto __weak;
 const struct bpf_func_proto bpf_probe_read_kernel_proto __weak;
 const struct bpf_func_proto bpf_probe_read_kernel_str_proto __weak;
 const struct bpf_func_proto bpf_task_pt_regs_proto __weak;
+const struct bpf_func_proto bpf_perf_event_read_proto __weak;
+const struct bpf_func_proto bpf_send_signal_proto __weak;
+const struct bpf_func_proto bpf_send_signal_thread_proto __weak;
+const struct bpf_func_proto bpf_get_task_stack_sleepable_proto __weak;
+const struct bpf_func_proto bpf_get_task_stack_proto __weak;
+const struct bpf_func_proto bpf_get_branch_snapshot_proto __weak;
 
 const struct bpf_func_proto *
 bpf_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
@@ -1965,6 +1963,8 @@ bpf_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_get_current_pid_tgid_proto;
 	case BPF_FUNC_get_ns_current_pid_tgid:
 		return &bpf_get_ns_current_pid_tgid_proto;
+	case BPF_FUNC_get_current_uid_gid:
+		return &bpf_get_current_uid_gid_proto;
 	default:
 		break;
 	}
@@ -2022,7 +2022,21 @@ bpf_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_get_current_cgroup_id_proto;
 	case BPF_FUNC_get_current_ancestor_cgroup_id:
 		return &bpf_get_current_ancestor_cgroup_id_proto;
+	case BPF_FUNC_current_task_under_cgroup:
+		return &bpf_current_task_under_cgroup_proto;
 #endif
+#ifdef CONFIG_CGROUP_NET_CLASSID
+	case BPF_FUNC_get_cgroup_classid:
+		return &bpf_get_cgroup_classid_curr_proto;
+#endif
+	case BPF_FUNC_task_storage_get:
+		if (bpf_prog_check_recur(prog))
+			return &bpf_task_storage_get_recur_proto;
+		return &bpf_task_storage_get_proto;
+	case BPF_FUNC_task_storage_delete:
+		if (bpf_prog_check_recur(prog))
+			return &bpf_task_storage_delete_recur_proto;
+		return &bpf_task_storage_delete_proto;
 	default:
 		break;
 	}
@@ -2037,6 +2051,8 @@ bpf_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_get_current_task_proto;
 	case BPF_FUNC_get_current_task_btf:
 		return &bpf_get_current_task_btf_proto;
+	case BPF_FUNC_get_current_comm:
+		return &bpf_get_current_comm_proto;
 	case BPF_FUNC_probe_read_user:
 		return &bpf_probe_read_user_proto;
 	case BPF_FUNC_probe_read_kernel:
@@ -2047,6 +2063,10 @@ bpf_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	case BPF_FUNC_probe_read_kernel_str:
 		return security_locked_down(LOCKDOWN_BPF_READ_KERNEL) < 0 ?
 		       NULL : &bpf_probe_read_kernel_str_proto;
+	case BPF_FUNC_copy_from_user:
+		return &bpf_copy_from_user_proto;
+	case BPF_FUNC_copy_from_user_task:
+		return &bpf_copy_from_user_task_proto;
 	case BPF_FUNC_snprintf_btf:
 		return &bpf_snprintf_btf_proto;
 	case BPF_FUNC_snprintf:
@@ -2057,6 +2077,19 @@ bpf_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return bpf_get_trace_vprintk_proto();
 	case BPF_FUNC_perf_event_read_value:
 		return bpf_get_perf_event_read_value_proto();
+	case BPF_FUNC_perf_event_read:
+		return &bpf_perf_event_read_proto;
+	case BPF_FUNC_send_signal:
+		return &bpf_send_signal_proto;
+	case BPF_FUNC_send_signal_thread:
+		return &bpf_send_signal_thread_proto;
+	case BPF_FUNC_get_task_stack:
+		return prog->sleepable ? &bpf_get_task_stack_sleepable_proto
+				       : &bpf_get_task_stack_proto;
+	case BPF_FUNC_get_branch_snapshot:
+		return &bpf_get_branch_snapshot_proto;
+	case BPF_FUNC_find_vma:
+		return &bpf_find_vma_proto;
 	default:
 		return NULL;
 	}
@@ -2293,6 +2326,26 @@ __bpf_kfunc struct bpf_list_node *bpf_list_pop_back(struct bpf_list_head *head)
 	return __bpf_list_del(head, true);
 }
 
+__bpf_kfunc struct bpf_list_node *bpf_list_front(struct bpf_list_head *head)
+{
+	struct list_head *h = (struct list_head *)head;
+
+	if (list_empty(h) || unlikely(!h->next))
+		return NULL;
+
+	return (struct bpf_list_node *)h->next;
+}
+
+__bpf_kfunc struct bpf_list_node *bpf_list_back(struct bpf_list_head *head)
+{
+	struct list_head *h = (struct list_head *)head;
+
+	if (list_empty(h) || unlikely(!h->next))
+		return NULL;
+
+	return (struct bpf_list_node *)h->prev;
+}
+
 __bpf_kfunc struct bpf_rb_node *bpf_rbtree_remove(struct bpf_rb_root *root,
 						  struct bpf_rb_node *node)
 {
@@ -2366,6 +2419,33 @@ __bpf_kfunc struct bpf_rb_node *bpf_rbtree_first(struct bpf_rb_root *root)
 	return (struct bpf_rb_node *)rb_first_cached(r);
 }
 
+__bpf_kfunc struct bpf_rb_node *bpf_rbtree_root(struct bpf_rb_root *root)
+{
+	struct rb_root_cached *r = (struct rb_root_cached *)root;
+
+	return (struct bpf_rb_node *)r->rb_root.rb_node;
+}
+
+__bpf_kfunc struct bpf_rb_node *bpf_rbtree_left(struct bpf_rb_root *root, struct bpf_rb_node *node)
+{
+	struct bpf_rb_node_kern *node_internal = (struct bpf_rb_node_kern *)node;
+
+	if (READ_ONCE(node_internal->owner) != root)
+		return NULL;
+
+	return (struct bpf_rb_node *)node_internal->rb_node.rb_left;
+}
+
+__bpf_kfunc struct bpf_rb_node *bpf_rbtree_right(struct bpf_rb_root *root, struct bpf_rb_node *node)
+{
+	struct bpf_rb_node_kern *node_internal = (struct bpf_rb_node_kern *)node;
+
+	if (READ_ONCE(node_internal->owner) != root)
+		return NULL;
+
+	return (struct bpf_rb_node *)node_internal->rb_node.rb_right;
+}
+
 /**
  * bpf_task_acquire - Acquire a reference to a task. A task acquired by this
  * kfunc which is not stored in a map as a kptr, must be released by calling
@@ -2923,9 +3003,9 @@ __bpf_kfunc int bpf_wq_start(struct bpf_wq *wq, unsigned int flags)
 __bpf_kfunc int bpf_wq_set_callback_impl(struct bpf_wq *wq,
 					 int (callback_fn)(void *map, int *key, void *value),
 					 unsigned int flags,
-					 void *aux__ign)
+					 void *aux__prog)
 {
-	struct bpf_prog_aux *aux = (struct bpf_prog_aux *)aux__ign;
+	struct bpf_prog_aux *aux = (struct bpf_prog_aux *)aux__prog;
 	struct bpf_async_kern *async = (struct bpf_async_kern *)wq;
 
 	if (flags)
@@ -3194,6 +3274,10 @@ __bpf_kfunc void bpf_local_irq_restore(unsigned long *flags__irq_flag)
 	local_irq_restore(*flags__irq_flag);
 }
 
+__bpf_kfunc void __bpf_trap(void)
+{
+}
+
 __bpf_kfunc_end_defs();
 
 BTF_KFUNCS_START(generic_btf_ids)
@@ -3209,11 +3293,16 @@ BTF_ID_FLAGS(func, bpf_list_push_front_impl)
 BTF_ID_FLAGS(func, bpf_list_push_back_impl)
 BTF_ID_FLAGS(func, bpf_list_pop_front, KF_ACQUIRE | KF_RET_NULL)
 BTF_ID_FLAGS(func, bpf_list_pop_back, KF_ACQUIRE | KF_RET_NULL)
+BTF_ID_FLAGS(func, bpf_list_front, KF_RET_NULL)
+BTF_ID_FLAGS(func, bpf_list_back, KF_RET_NULL)
 BTF_ID_FLAGS(func, bpf_task_acquire, KF_ACQUIRE | KF_RCU | KF_RET_NULL)
 BTF_ID_FLAGS(func, bpf_task_release, KF_RELEASE)
 BTF_ID_FLAGS(func, bpf_rbtree_remove, KF_ACQUIRE | KF_RET_NULL)
 BTF_ID_FLAGS(func, bpf_rbtree_add_impl)
 BTF_ID_FLAGS(func, bpf_rbtree_first, KF_RET_NULL)
+BTF_ID_FLAGS(func, bpf_rbtree_root, KF_RET_NULL)
+BTF_ID_FLAGS(func, bpf_rbtree_left, KF_RET_NULL)
+BTF_ID_FLAGS(func, bpf_rbtree_right, KF_RET_NULL)
 
 #ifdef CONFIG_CGROUPS
 BTF_ID_FLAGS(func, bpf_cgroup_acquire, KF_ACQUIRE | KF_RCU | KF_RET_NULL)
@@ -3294,6 +3383,20 @@ BTF_ID_FLAGS(func, bpf_iter_kmem_cache_next, KF_ITER_NEXT | KF_RET_NULL | KF_SLE
 BTF_ID_FLAGS(func, bpf_iter_kmem_cache_destroy, KF_ITER_DESTROY | KF_SLEEPABLE)
 BTF_ID_FLAGS(func, bpf_local_irq_save)
 BTF_ID_FLAGS(func, bpf_local_irq_restore)
+BTF_ID_FLAGS(func, bpf_probe_read_user_dynptr)
+BTF_ID_FLAGS(func, bpf_probe_read_kernel_dynptr)
+BTF_ID_FLAGS(func, bpf_probe_read_user_str_dynptr)
+BTF_ID_FLAGS(func, bpf_probe_read_kernel_str_dynptr)
+BTF_ID_FLAGS(func, bpf_copy_from_user_dynptr, KF_SLEEPABLE)
+BTF_ID_FLAGS(func, bpf_copy_from_user_str_dynptr, KF_SLEEPABLE)
+BTF_ID_FLAGS(func, bpf_copy_from_user_task_dynptr, KF_SLEEPABLE | KF_TRUSTED_ARGS)
+BTF_ID_FLAGS(func, bpf_copy_from_user_task_str_dynptr, KF_SLEEPABLE | KF_TRUSTED_ARGS)
+#ifdef CONFIG_DMA_SHARED_BUFFER
+BTF_ID_FLAGS(func, bpf_iter_dmabuf_new, KF_ITER_NEW | KF_SLEEPABLE)
+BTF_ID_FLAGS(func, bpf_iter_dmabuf_next, KF_ITER_NEXT | KF_RET_NULL | KF_SLEEPABLE)
+BTF_ID_FLAGS(func, bpf_iter_dmabuf_destroy, KF_ITER_DESTROY | KF_SLEEPABLE)
+#endif
+BTF_ID_FLAGS(func, __bpf_trap)
 BTF_KFUNCS_END(common_btf_ids)
 
 static const struct btf_kfunc_id_set common_kfunc_set = {
diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c
index dc3aa91a6ba0..5c2e96b19392 100644
--- a/kernel/bpf/inode.c
+++ b/kernel/bpf/inode.c
@@ -421,7 +421,7 @@ static int bpf_iter_link_pin_kernel(struct dentry *parent,
 	int ret;
 
 	inode_lock(parent->d_inode);
-	dentry = lookup_one_len(name, parent, strlen(name));
+	dentry = lookup_noperm(&QSTR(name), parent);
 	if (IS_ERR(dentry)) {
 		inode_unlock(parent->d_inode);
 		return PTR_ERR(dentry);
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 64c3393e8270..dd5304c6ac3c 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -36,6 +36,7 @@
 #include <linux/memcontrol.h>
 #include <linux/trace_events.h>
 #include <linux/tracepoint.h>
+#include <linux/overflow.h>
 
 #include <net/netfilter/nf_bpf_link.h>
 #include <net/netkit.h>
@@ -578,7 +579,7 @@ static bool can_alloc_pages(void)
 static struct page *__bpf_alloc_page(int nid)
 {
 	if (!can_alloc_pages())
-		return try_alloc_pages(nid, 0);
+		return alloc_pages_nolock(nid, 0);
 
 	return alloc_pages_node(nid,
 				GFP_KERNEL | __GFP_ZERO | __GFP_ACCOUNT
@@ -693,7 +694,7 @@ struct btf_record *btf_record_dup(const struct btf_record *rec)
 
 	if (IS_ERR_OR_NULL(rec))
 		return NULL;
-	size = offsetof(struct btf_record, fields[rec->cnt]);
+	size = struct_size(rec, fields, rec->cnt);
 	new_rec = kmemdup(rec, size, GFP_KERNEL | __GFP_NOWARN);
 	if (!new_rec)
 		return ERR_PTR(-ENOMEM);
@@ -748,7 +749,7 @@ bool btf_record_equal(const struct btf_record *rec_a, const struct btf_record *r
 		return false;
 	if (rec_a->cnt != rec_b->cnt)
 		return false;
-	size = offsetof(struct btf_record, fields[rec_a->cnt]);
+	size = struct_size(rec_a, fields, rec_a->cnt);
 	/* btf_parse_fields uses kzalloc to allocate a btf_record, so unused
 	 * members are zeroed out. So memcmp is safe to do without worrying
 	 * about padding/unused fields.
@@ -3799,14 +3800,14 @@ static int bpf_perf_link_fill_kprobe(const struct perf_event *event,
 static int bpf_perf_link_fill_uprobe(const struct perf_event *event,
 				     struct bpf_link_info *info)
 {
+	u64 ref_ctr_offset, offset;
 	char __user *uname;
-	u64 addr, offset;
 	u32 ulen, type;
 	int err;
 
 	uname = u64_to_user_ptr(info->perf_event.uprobe.file_name);
 	ulen = info->perf_event.uprobe.name_len;
-	err = bpf_perf_link_fill_common(event, uname, &ulen, &offset, &addr,
+	err = bpf_perf_link_fill_common(event, uname, &ulen, &offset, &ref_ctr_offset,
 					&type, NULL);
 	if (err)
 		return err;
@@ -3818,6 +3819,7 @@ static int bpf_perf_link_fill_uprobe(const struct perf_event *event,
 	info->perf_event.uprobe.name_len = ulen;
 	info->perf_event.uprobe.offset = offset;
 	info->perf_event.uprobe.cookie = event->bpf_cookie;
+	info->perf_event.uprobe.ref_ctr_offset = ref_ctr_offset;
 	return 0;
 }
 #endif
diff --git a/kernel/bpf/sysfs_btf.c b/kernel/bpf/sysfs_btf.c
index 81d6cf90584a..941d0d2427e3 100644
--- a/kernel/bpf/sysfs_btf.c
+++ b/kernel/bpf/sysfs_btf.c
@@ -7,14 +7,46 @@
 #include <linux/kobject.h>
 #include <linux/init.h>
 #include <linux/sysfs.h>
+#include <linux/mm.h>
+#include <linux/io.h>
+#include <linux/btf.h>
 
 /* See scripts/link-vmlinux.sh, gen_btf() func for details */
 extern char __start_BTF[];
 extern char __stop_BTF[];
 
+static int btf_sysfs_vmlinux_mmap(struct file *filp, struct kobject *kobj,
+				  const struct bin_attribute *attr,
+				  struct vm_area_struct *vma)
+{
+	unsigned long pages = PAGE_ALIGN(attr->size) >> PAGE_SHIFT;
+	size_t vm_size = vma->vm_end - vma->vm_start;
+	phys_addr_t addr = virt_to_phys(__start_BTF);
+	unsigned long pfn = addr >> PAGE_SHIFT;
+
+	if (attr->private != __start_BTF || !PAGE_ALIGNED(addr))
+		return -EINVAL;
+
+	if (vma->vm_pgoff)
+		return -EINVAL;
+
+	if (vma->vm_flags & (VM_WRITE | VM_EXEC | VM_MAYSHARE))
+		return -EACCES;
+
+	if (pfn + pages < pfn)
+		return -EINVAL;
+
+	if ((vm_size >> PAGE_SHIFT) > pages)
+		return -EINVAL;
+
+	vm_flags_mod(vma, VM_DONTDUMP, VM_MAYEXEC | VM_MAYWRITE);
+	return remap_pfn_range(vma, vma->vm_start, pfn, vm_size, vma->vm_page_prot);
+}
+
 static struct bin_attribute bin_attr_btf_vmlinux __ro_after_init = {
 	.attr = { .name = "vmlinux", .mode = 0444, },
 	.read_new = sysfs_bin_attr_simple_read,
+	.mmap = btf_sysfs_vmlinux_mmap,
 };
 
 struct kobject *btf_kobj;
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 54c6953a8b84..a7d6e0c5928b 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -322,6 +322,7 @@ struct bpf_kfunc_call_arg_meta {
 	struct btf *arg_btf;
 	u32 arg_btf_id;
 	bool arg_owning_ref;
+	bool arg_prog;
 
 	struct {
 		struct btf_field *field;
@@ -1923,11 +1924,8 @@ static struct bpf_verifier_state *get_loop_entry(struct bpf_verifier_env *env,
 	u32 steps = 0;
 
 	while (topmost && topmost->loop_entry) {
-		if (steps++ > st->dfs_depth) {
-			WARN_ONCE(true, "verifier bug: infinite loop in get_loop_entry\n");
-			verbose(env, "verifier bug: infinite loop in get_loop_entry()\n");
+		if (verifier_bug_if(steps++ > st->dfs_depth, env, "infinite loop"))
 			return ERR_PTR(-EFAULT);
-		}
 		topmost = topmost->loop_entry;
 	}
 	return topmost;
@@ -3459,12 +3457,11 @@ static int mark_reg_read(struct bpf_verifier_env *env,
 		/* if read wasn't screened by an earlier write ... */
 		if (writes && state->live & REG_LIVE_WRITTEN)
 			break;
-		if (parent->live & REG_LIVE_DONE) {
-			verbose(env, "verifier BUG type %s var_off %lld off %d\n",
-				reg_type_str(env, parent->type),
-				parent->var_off.value, parent->off);
+		if (verifier_bug_if(parent->live & REG_LIVE_DONE, env,
+				    "type %s var_off %lld off %d",
+				    reg_type_str(env, parent->type),
+				    parent->var_off.value, parent->off))
 			return -EFAULT;
-		}
 		/* The first condition is more likely to be true than the
 		 * second, checked it first.
 		 */
@@ -3649,16 +3646,16 @@ static int insn_def_regno(const struct bpf_insn *insn)
 	case BPF_ST:
 		return -1;
 	case BPF_STX:
-		if ((BPF_MODE(insn->code) == BPF_ATOMIC ||
-		     BPF_MODE(insn->code) == BPF_PROBE_ATOMIC) &&
-		    (insn->imm & BPF_FETCH)) {
+		if (BPF_MODE(insn->code) == BPF_ATOMIC ||
+		    BPF_MODE(insn->code) == BPF_PROBE_ATOMIC) {
 			if (insn->imm == BPF_CMPXCHG)
 				return BPF_REG_0;
-			else
+			else if (insn->imm == BPF_LOAD_ACQ)
+				return insn->dst_reg;
+			else if (insn->imm & BPF_FETCH)
 				return insn->src_reg;
-		} else {
-			return -1;
 		}
+		return -1;
 	default:
 		return insn->dst_reg;
 	}
@@ -3857,14 +3854,14 @@ static int push_insn_history(struct bpf_verifier_env *env, struct bpf_verifier_s
 		/* atomic instructions push insn_flags twice, for READ and
 		 * WRITE sides, but they should agree on stack slot
 		 */
-		WARN_ONCE((env->cur_hist_ent->flags & insn_flags) &&
-			  (env->cur_hist_ent->flags & insn_flags) != insn_flags,
-			  "verifier insn history bug: insn_idx %d cur flags %x new flags %x\n",
-			  env->insn_idx, env->cur_hist_ent->flags, insn_flags);
+		verifier_bug_if((env->cur_hist_ent->flags & insn_flags) &&
+				(env->cur_hist_ent->flags & insn_flags) != insn_flags,
+				env, "insn history: insn_idx %d cur flags %x new flags %x",
+				env->insn_idx, env->cur_hist_ent->flags, insn_flags);
 		env->cur_hist_ent->flags |= insn_flags;
-		WARN_ONCE(env->cur_hist_ent->linked_regs != 0,
-			  "verifier insn history bug: insn_idx %d linked_regs != 0: %#llx\n",
-			  env->insn_idx, env->cur_hist_ent->linked_regs);
+		verifier_bug_if(env->cur_hist_ent->linked_regs != 0, env,
+				"insn history: insn_idx %d linked_regs: %#llx",
+				env->insn_idx, env->cur_hist_ent->linked_regs);
 		env->cur_hist_ent->linked_regs = linked_regs;
 		return 0;
 	}
@@ -3987,8 +3984,7 @@ static inline u32 bt_empty(struct backtrack_state *bt)
 static inline int bt_subprog_enter(struct backtrack_state *bt)
 {
 	if (bt->frame == MAX_CALL_FRAMES - 1) {
-		verbose(bt->env, "BUG subprog enter from frame %d\n", bt->frame);
-		WARN_ONCE(1, "verifier backtracking bug");
+		verifier_bug(bt->env, "subprog enter from frame %d", bt->frame);
 		return -EFAULT;
 	}
 	bt->frame++;
@@ -3998,8 +3994,7 @@ static inline int bt_subprog_enter(struct backtrack_state *bt)
 static inline int bt_subprog_exit(struct backtrack_state *bt)
 {
 	if (bt->frame == 0) {
-		verbose(bt->env, "BUG subprog exit from frame 0\n");
-		WARN_ONCE(1, "verifier backtracking bug");
+		verifier_bug(bt->env, "subprog exit from frame 0");
 		return -EFAULT;
 	}
 	bt->frame--;
@@ -4277,14 +4272,15 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, int subseq_idx,
 				 * should be literally next instruction in
 				 * caller program
 				 */
-				WARN_ONCE(idx + 1 != subseq_idx, "verifier backtracking bug");
+				verifier_bug_if(idx + 1 != subseq_idx, env,
+						"extra insn from subprog");
 				/* r1-r5 are invalidated after subprog call,
 				 * so for global func call it shouldn't be set
 				 * anymore
 				 */
 				if (bt_reg_mask(bt) & BPF_REGMASK_ARGS) {
-					verbose(env, "BUG regs %x\n", bt_reg_mask(bt));
-					WARN_ONCE(1, "verifier backtracking bug");
+					verifier_bug(env, "global subprog unexpected regs %x",
+						     bt_reg_mask(bt));
 					return -EFAULT;
 				}
 				/* global subprog always sets R0 */
@@ -4298,16 +4294,17 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, int subseq_idx,
 				 * the current frame should be zero by now
 				 */
 				if (bt_reg_mask(bt) & ~BPF_REGMASK_ARGS) {
-					verbose(env, "BUG regs %x\n", bt_reg_mask(bt));
-					WARN_ONCE(1, "verifier backtracking bug");
+					verifier_bug(env, "static subprog unexpected regs %x",
+						     bt_reg_mask(bt));
 					return -EFAULT;
 				}
 				/* we are now tracking register spills correctly,
 				 * so any instance of leftover slots is a bug
 				 */
 				if (bt_stack_mask(bt) != 0) {
-					verbose(env, "BUG stack slots %llx\n", bt_stack_mask(bt));
-					WARN_ONCE(1, "verifier backtracking bug (subprog leftover stack slots)");
+					verifier_bug(env,
+						     "static subprog leftover stack slots %llx",
+						     bt_stack_mask(bt));
 					return -EFAULT;
 				}
 				/* propagate r1-r5 to the caller */
@@ -4330,13 +4327,13 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, int subseq_idx,
 			 * not actually arguments passed directly to callback subprogs
 			 */
 			if (bt_reg_mask(bt) & ~BPF_REGMASK_ARGS) {
-				verbose(env, "BUG regs %x\n", bt_reg_mask(bt));
-				WARN_ONCE(1, "verifier backtracking bug");
+				verifier_bug(env, "callback unexpected regs %x",
+					     bt_reg_mask(bt));
 				return -EFAULT;
 			}
 			if (bt_stack_mask(bt) != 0) {
-				verbose(env, "BUG stack slots %llx\n", bt_stack_mask(bt));
-				WARN_ONCE(1, "verifier backtracking bug (callback leftover stack slots)");
+				verifier_bug(env, "callback leftover stack slots %llx",
+					     bt_stack_mask(bt));
 				return -EFAULT;
 			}
 			/* clear r1-r5 in callback subprog's mask */
@@ -4355,11 +4352,11 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, int subseq_idx,
 			/* regular helper call sets R0 */
 			bt_clear_reg(bt, BPF_REG_0);
 			if (bt_reg_mask(bt) & BPF_REGMASK_ARGS) {
-				/* if backtracing was looking for registers R1-R5
+				/* if backtracking was looking for registers R1-R5
 				 * they should have been found already.
 				 */
-				verbose(env, "BUG regs %x\n", bt_reg_mask(bt));
-				WARN_ONCE(1, "verifier backtracking bug");
+				verifier_bug(env, "backtracking call unexpected regs %x",
+					     bt_reg_mask(bt));
 				return -EFAULT;
 			}
 		} else if (opcode == BPF_EXIT) {
@@ -4377,8 +4374,8 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, int subseq_idx,
 				for (i = BPF_REG_1; i <= BPF_REG_5; i++)
 					bt_clear_reg(bt, i);
 			if (bt_reg_mask(bt) & BPF_REGMASK_ARGS) {
-				verbose(env, "BUG regs %x\n", bt_reg_mask(bt));
-				WARN_ONCE(1, "verifier backtracking bug");
+				verifier_bug(env, "backtracking exit unexpected regs %x",
+					     bt_reg_mask(bt));
 				return -EFAULT;
 			}
 
@@ -4413,8 +4410,10 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, int subseq_idx,
 			 * before it would be equally necessary to
 			 * propagate it to dreg.
 			 */
-			bt_set_reg(bt, dreg);
-			bt_set_reg(bt, sreg);
+			if (!hist || !(hist->flags & INSN_F_SRC_REG_STACK))
+				bt_set_reg(bt, sreg);
+			if (!hist || !(hist->flags & INSN_F_DST_REG_STACK))
+				bt_set_reg(bt, dreg);
 		} else if (BPF_SRC(insn->code) == BPF_K) {
 			 /* dreg <cond> K
 			  * Only dreg still needs precision before
@@ -4719,9 +4718,8 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int regno)
 				return 0;
 			}
 
-			verbose(env, "BUG backtracking func entry subprog %d reg_mask %x stack_mask %llx\n",
-				st->frame[0]->subprogno, bt_reg_mask(bt), bt_stack_mask(bt));
-			WARN_ONCE(1, "verifier backtracking bug");
+			verifier_bug(env, "backtracking func entry subprog %d reg_mask %x stack_mask %llx",
+				     st->frame[0]->subprogno, bt_reg_mask(bt), bt_stack_mask(bt));
 			return -EFAULT;
 		}
 
@@ -4757,8 +4755,7 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int regno)
 				 * It means the backtracking missed the spot where
 				 * particular register was initialized with a constant.
 				 */
-				verbose(env, "BUG backtracking idx %d\n", i);
-				WARN_ONCE(1, "verifier backtracking bug");
+				verifier_bug(env, "backtracking idx %d", i);
 				return -EFAULT;
 			}
 		}
@@ -4783,12 +4780,10 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int regno)
 
 			bitmap_from_u64(mask, bt_frame_stack_mask(bt, fr));
 			for_each_set_bit(i, mask, 64) {
-				if (i >= func->allocated_stack / BPF_REG_SIZE) {
-					verbose(env, "BUG backtracking (stack slot %d, total slots %d)\n",
-						i, func->allocated_stack / BPF_REG_SIZE);
-					WARN_ONCE(1, "verifier backtracking bug (stack slot out of bounds)");
+				if (verifier_bug_if(i >= func->allocated_stack / BPF_REG_SIZE,
+						    env, "stack slot %d, total slots %d",
+						    i, func->allocated_stack / BPF_REG_SIZE))
 					return -EFAULT;
-				}
 
 				if (!is_spilled_scalar_reg(&func->stack[i])) {
 					bt_clear_frame_slot(bt, fr, i);
@@ -6561,21 +6556,18 @@ continue_func:
 		/* find the callee */
 		next_insn = i + insn[i].imm + 1;
 		sidx = find_subprog(env, next_insn);
-		if (sidx < 0) {
-			WARN_ONCE(1, "verifier bug. No program starts at insn %d\n",
-				  next_insn);
+		if (verifier_bug_if(sidx < 0, env, "callee not found at insn %d", next_insn))
 			return -EFAULT;
-		}
 		if (subprog[sidx].is_async_cb) {
 			if (subprog[sidx].has_tail_call) {
-				verbose(env, "verifier bug. subprog has tail_call and async cb\n");
+				verifier_bug(env, "subprog has tail_call and async cb");
 				return -EFAULT;
 			}
 			/* async callbacks don't increase bpf prog stack size unless called directly */
 			if (!bpf_pseudo_call(insn + i))
 				continue;
 			if (subprog[sidx].is_exception_cb) {
-				verbose(env, "insn %d cannot call exception cb directly\n", i);
+				verbose(env, "insn %d cannot call exception cb directly", i);
 				return -EINVAL;
 			}
 		}
@@ -6675,11 +6667,8 @@ static int get_callee_stack_depth(struct bpf_verifier_env *env,
 	int start = idx + insn->imm + 1, subprog;
 
 	subprog = find_subprog(env, start);
-	if (subprog < 0) {
-		WARN_ONCE(1, "verifier bug. No program starts at insn %d\n",
-			  start);
+	if (verifier_bug_if(subprog < 0, env, "get stack depth: no program at insn %d", start))
 		return -EFAULT;
-	}
 	return env->subprog_info[subprog].stack_depth;
 }
 #endif
@@ -7984,7 +7973,7 @@ static int check_stack_range_initialized(
 		slot = -i - 1;
 		spi = slot / BPF_REG_SIZE;
 		if (state->allocated_stack <= slot) {
-			verbose(env, "verifier bug: allocated_stack too small\n");
+			verbose(env, "allocated_stack too small\n");
 			return -EFAULT;
 		}
 
@@ -8413,7 +8402,7 @@ static int process_timer_func(struct bpf_verifier_env *env, int regno,
 		return -EINVAL;
 	}
 	if (meta->map_ptr) {
-		verbose(env, "verifier bug. Two map pointers in a timer helper\n");
+		verifier_bug(env, "Two map pointers in a timer helper");
 		return -EFAULT;
 	}
 	meta->map_uid = reg->map_uid;
@@ -10285,8 +10274,7 @@ static int setup_func_entry(struct bpf_verifier_env *env, int subprog, int calls
 	}
 
 	if (state->frame[state->curframe + 1]) {
-		verbose(env, "verifier bug. Frame %d already allocated\n",
-			state->curframe + 1);
+		verifier_bug(env, "Frame %d already allocated", state->curframe + 1);
 		return -EFAULT;
 	}
 
@@ -10400,8 +10388,7 @@ static int btf_check_func_arg_match(struct bpf_verifier_env *env, int subprog,
 			if (err)
 				return err;
 		} else {
-			bpf_log(log, "verifier bug: unrecognized arg#%d type %d\n",
-				i, arg->arg_type);
+			verifier_bug(env, "unrecognized arg#%d type %d", i, arg->arg_type);
 			return -EFAULT;
 		}
 	}
@@ -10464,13 +10451,13 @@ static int push_callback_call(struct bpf_verifier_env *env, struct bpf_insn *ins
 	env->subprog_info[subprog].is_cb = true;
 	if (bpf_pseudo_kfunc_call(insn) &&
 	    !is_callback_calling_kfunc(insn->imm)) {
-		verbose(env, "verifier bug: kfunc %s#%d not marked as callback-calling\n",
-			func_id_name(insn->imm), insn->imm);
+		verifier_bug(env, "kfunc %s#%d not marked as callback-calling",
+			     func_id_name(insn->imm), insn->imm);
 		return -EFAULT;
 	} else if (!bpf_pseudo_kfunc_call(insn) &&
 		   !is_callback_calling_function(insn->imm)) { /* helper */
-		verbose(env, "verifier bug: helper %s#%d not marked as callback-calling\n",
-			func_id_name(insn->imm), insn->imm);
+		verifier_bug(env, "helper %s#%d not marked as callback-calling",
+			     func_id_name(insn->imm), insn->imm);
 		return -EFAULT;
 	}
 
@@ -10522,10 +10509,9 @@ static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
 
 	target_insn = *insn_idx + insn->imm + 1;
 	subprog = find_subprog(env, target_insn);
-	if (subprog < 0) {
-		verbose(env, "verifier bug. No program starts at insn %d\n", target_insn);
+	if (verifier_bug_if(subprog < 0, env, "target of func call at insn %d is not a program",
+			    target_insn))
 		return -EFAULT;
-	}
 
 	caller = state->frame[state->curframe];
 	err = btf_check_subprog_call(env, subprog, caller->regs);
@@ -11124,7 +11110,7 @@ static int check_bpf_snprintf_call(struct bpf_verifier_env *env,
 	err = fmt_map->ops->map_direct_value_addr(fmt_map, &fmt_addr,
 						  fmt_map_off);
 	if (err) {
-		verbose(env, "verifier bug\n");
+		verbose(env, "failed to retrieve map value address\n");
 		return -EFAULT;
 	}
 	fmt = (char *)(long)fmt_addr + fmt_map_off;
@@ -11897,6 +11883,11 @@ static bool is_kfunc_arg_irq_flag(const struct btf *btf, const struct btf_param
 	return btf_param_match_suffix(btf, arg, "__irq_flag");
 }
 
+static bool is_kfunc_arg_prog(const struct btf *btf, const struct btf_param *arg)
+{
+	return btf_param_match_suffix(btf, arg, "__prog");
+}
+
 static bool is_kfunc_arg_scalar_with_name(const struct btf *btf,
 					  const struct btf_param *arg,
 					  const char *name)
@@ -11987,6 +11978,16 @@ static bool is_kfunc_arg_res_spin_lock(const struct btf *btf, const struct btf_p
 	return __is_kfunc_ptr_arg_type(btf, arg, KF_ARG_RES_SPIN_LOCK_ID);
 }
 
+static bool is_rbtree_node_type(const struct btf_type *t)
+{
+	return t == btf_type_by_id(btf_vmlinux, kf_arg_btf_ids[KF_ARG_RB_NODE_ID]);
+}
+
+static bool is_list_node_type(const struct btf_type *t)
+{
+	return t == btf_type_by_id(btf_vmlinux, kf_arg_btf_ids[KF_ARG_LIST_NODE_ID]);
+}
+
 static bool is_kfunc_arg_callback(struct bpf_verifier_env *env, const struct btf *btf,
 				  const struct btf_param *arg)
 {
@@ -12069,6 +12070,8 @@ enum special_kfunc_type {
 	KF_bpf_list_push_back_impl,
 	KF_bpf_list_pop_front,
 	KF_bpf_list_pop_back,
+	KF_bpf_list_front,
+	KF_bpf_list_back,
 	KF_bpf_cast_to_kern_ctx,
 	KF_bpf_rdonly_cast,
 	KF_bpf_rcu_read_lock,
@@ -12076,6 +12079,9 @@ enum special_kfunc_type {
 	KF_bpf_rbtree_remove,
 	KF_bpf_rbtree_add_impl,
 	KF_bpf_rbtree_first,
+	KF_bpf_rbtree_root,
+	KF_bpf_rbtree_left,
+	KF_bpf_rbtree_right,
 	KF_bpf_dynptr_from_skb,
 	KF_bpf_dynptr_from_xdp,
 	KF_bpf_dynptr_slice,
@@ -12101,41 +12107,9 @@ enum special_kfunc_type {
 	KF_bpf_res_spin_unlock,
 	KF_bpf_res_spin_lock_irqsave,
 	KF_bpf_res_spin_unlock_irqrestore,
+	KF___bpf_trap,
 };
 
-BTF_SET_START(special_kfunc_set)
-BTF_ID(func, bpf_obj_new_impl)
-BTF_ID(func, bpf_obj_drop_impl)
-BTF_ID(func, bpf_refcount_acquire_impl)
-BTF_ID(func, bpf_list_push_front_impl)
-BTF_ID(func, bpf_list_push_back_impl)
-BTF_ID(func, bpf_list_pop_front)
-BTF_ID(func, bpf_list_pop_back)
-BTF_ID(func, bpf_cast_to_kern_ctx)
-BTF_ID(func, bpf_rdonly_cast)
-BTF_ID(func, bpf_rbtree_remove)
-BTF_ID(func, bpf_rbtree_add_impl)
-BTF_ID(func, bpf_rbtree_first)
-#ifdef CONFIG_NET
-BTF_ID(func, bpf_dynptr_from_skb)
-BTF_ID(func, bpf_dynptr_from_xdp)
-#endif
-BTF_ID(func, bpf_dynptr_slice)
-BTF_ID(func, bpf_dynptr_slice_rdwr)
-BTF_ID(func, bpf_dynptr_clone)
-BTF_ID(func, bpf_percpu_obj_new_impl)
-BTF_ID(func, bpf_percpu_obj_drop_impl)
-BTF_ID(func, bpf_throw)
-BTF_ID(func, bpf_wq_set_callback_impl)
-#ifdef CONFIG_CGROUPS
-BTF_ID(func, bpf_iter_css_task_new)
-#endif
-#ifdef CONFIG_BPF_LSM
-BTF_ID(func, bpf_set_dentry_xattr)
-BTF_ID(func, bpf_remove_dentry_xattr)
-#endif
-BTF_SET_END(special_kfunc_set)
-
 BTF_ID_LIST(special_kfunc_list)
 BTF_ID(func, bpf_obj_new_impl)
 BTF_ID(func, bpf_obj_drop_impl)
@@ -12144,6 +12118,8 @@ BTF_ID(func, bpf_list_push_front_impl)
 BTF_ID(func, bpf_list_push_back_impl)
 BTF_ID(func, bpf_list_pop_front)
 BTF_ID(func, bpf_list_pop_back)
+BTF_ID(func, bpf_list_front)
+BTF_ID(func, bpf_list_back)
 BTF_ID(func, bpf_cast_to_kern_ctx)
 BTF_ID(func, bpf_rdonly_cast)
 BTF_ID(func, bpf_rcu_read_lock)
@@ -12151,6 +12127,9 @@ BTF_ID(func, bpf_rcu_read_unlock)
 BTF_ID(func, bpf_rbtree_remove)
 BTF_ID(func, bpf_rbtree_add_impl)
 BTF_ID(func, bpf_rbtree_first)
+BTF_ID(func, bpf_rbtree_root)
+BTF_ID(func, bpf_rbtree_left)
+BTF_ID(func, bpf_rbtree_right)
 #ifdef CONFIG_NET
 BTF_ID(func, bpf_dynptr_from_skb)
 BTF_ID(func, bpf_dynptr_from_xdp)
@@ -12194,6 +12173,7 @@ BTF_ID(func, bpf_res_spin_lock)
 BTF_ID(func, bpf_res_spin_unlock)
 BTF_ID(func, bpf_res_spin_lock_irqsave)
 BTF_ID(func, bpf_res_spin_unlock_irqrestore)
+BTF_ID(func, __bpf_trap)
 
 static bool is_kfunc_ret_null(struct bpf_kfunc_call_arg_meta *meta)
 {
@@ -12579,14 +12559,19 @@ static bool is_bpf_list_api_kfunc(u32 btf_id)
 	return btf_id == special_kfunc_list[KF_bpf_list_push_front_impl] ||
 	       btf_id == special_kfunc_list[KF_bpf_list_push_back_impl] ||
 	       btf_id == special_kfunc_list[KF_bpf_list_pop_front] ||
-	       btf_id == special_kfunc_list[KF_bpf_list_pop_back];
+	       btf_id == special_kfunc_list[KF_bpf_list_pop_back] ||
+	       btf_id == special_kfunc_list[KF_bpf_list_front] ||
+	       btf_id == special_kfunc_list[KF_bpf_list_back];
 }
 
 static bool is_bpf_rbtree_api_kfunc(u32 btf_id)
 {
 	return btf_id == special_kfunc_list[KF_bpf_rbtree_add_impl] ||
 	       btf_id == special_kfunc_list[KF_bpf_rbtree_remove] ||
-	       btf_id == special_kfunc_list[KF_bpf_rbtree_first];
+	       btf_id == special_kfunc_list[KF_bpf_rbtree_first] ||
+	       btf_id == special_kfunc_list[KF_bpf_rbtree_root] ||
+	       btf_id == special_kfunc_list[KF_bpf_rbtree_left] ||
+	       btf_id == special_kfunc_list[KF_bpf_rbtree_right];
 }
 
 static bool is_bpf_iter_num_api_kfunc(u32 btf_id)
@@ -12686,7 +12671,9 @@ static bool check_kfunc_is_graph_node_api(struct bpf_verifier_env *env,
 		break;
 	case BPF_RB_NODE:
 		ret = (kfunc_btf_id == special_kfunc_list[KF_bpf_rbtree_remove] ||
-		       kfunc_btf_id == special_kfunc_list[KF_bpf_rbtree_add_impl]);
+		       kfunc_btf_id == special_kfunc_list[KF_bpf_rbtree_add_impl] ||
+		       kfunc_btf_id == special_kfunc_list[KF_bpf_rbtree_left] ||
+		       kfunc_btf_id == special_kfunc_list[KF_bpf_rbtree_right]);
 		break;
 	default:
 		verbose(env, "verifier internal error: unexpected graph node argument type %s\n",
@@ -12906,6 +12893,17 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_
 		if (is_kfunc_arg_ignore(btf, &args[i]))
 			continue;
 
+		if (is_kfunc_arg_prog(btf, &args[i])) {
+			/* Used to reject repeated use of __prog. */
+			if (meta->arg_prog) {
+				verbose(env, "Only 1 prog->aux argument supported per-kfunc\n");
+				return -EFAULT;
+			}
+			meta->arg_prog = true;
+			cur_aux(env)->arg_prog = regno;
+			continue;
+		}
+
 		if (btf_type_is_scalar(t)) {
 			if (reg->type != SCALAR_VALUE) {
 				verbose(env, "R%d is not a scalar\n", regno);
@@ -13200,22 +13198,22 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_
 				return ret;
 			break;
 		case KF_ARG_PTR_TO_RB_NODE:
-			if (meta->func_id == special_kfunc_list[KF_bpf_rbtree_remove]) {
-				if (!type_is_non_owning_ref(reg->type) || reg->ref_obj_id) {
-					verbose(env, "rbtree_remove node input must be non-owning ref\n");
+			if (meta->func_id == special_kfunc_list[KF_bpf_rbtree_add_impl]) {
+				if (reg->type != (PTR_TO_BTF_ID | MEM_ALLOC)) {
+					verbose(env, "arg#%d expected pointer to allocated object\n", i);
 					return -EINVAL;
 				}
-				if (in_rbtree_lock_required_cb(env)) {
-					verbose(env, "rbtree_remove not allowed in rbtree cb\n");
+				if (!reg->ref_obj_id) {
+					verbose(env, "allocated object must be referenced\n");
 					return -EINVAL;
 				}
 			} else {
-				if (reg->type != (PTR_TO_BTF_ID | MEM_ALLOC)) {
-					verbose(env, "arg#%d expected pointer to allocated object\n", i);
+				if (!type_is_non_owning_ref(reg->type) && !reg->ref_obj_id) {
+					verbose(env, "%s can only take non-owning or refcounted bpf_rb_node pointer\n", func_name);
 					return -EINVAL;
 				}
-				if (!reg->ref_obj_id) {
-					verbose(env, "allocated object must be referenced\n");
+				if (in_rbtree_lock_required_cb(env)) {
+					verbose(env, "%s not allowed in rbtree cb\n", func_name);
 					return -EINVAL;
 				}
 			}
@@ -13420,6 +13418,178 @@ static int fetch_kfunc_meta(struct bpf_verifier_env *env,
 	return 0;
 }
 
+/* check special kfuncs and return:
+ *  1  - not fall-through to 'else' branch, continue verification
+ *  0  - fall-through to 'else' branch
+ * < 0 - not fall-through to 'else' branch, return error
+ */
+static int check_special_kfunc(struct bpf_verifier_env *env, struct bpf_kfunc_call_arg_meta *meta,
+			       struct bpf_reg_state *regs, struct bpf_insn_aux_data *insn_aux,
+			       const struct btf_type *ptr_type, struct btf *desc_btf)
+{
+	const struct btf_type *ret_t;
+	int err = 0;
+
+	if (meta->btf != btf_vmlinux)
+		return 0;
+
+	if (meta->func_id == special_kfunc_list[KF_bpf_obj_new_impl] ||
+	    meta->func_id == special_kfunc_list[KF_bpf_percpu_obj_new_impl]) {
+		struct btf_struct_meta *struct_meta;
+		struct btf *ret_btf;
+		u32 ret_btf_id;
+
+		if (meta->func_id == special_kfunc_list[KF_bpf_obj_new_impl] && !bpf_global_ma_set)
+			return -ENOMEM;
+
+		if (((u64)(u32)meta->arg_constant.value) != meta->arg_constant.value) {
+			verbose(env, "local type ID argument must be in range [0, U32_MAX]\n");
+			return -EINVAL;
+		}
+
+		ret_btf = env->prog->aux->btf;
+		ret_btf_id = meta->arg_constant.value;
+
+		/* This may be NULL due to user not supplying a BTF */
+		if (!ret_btf) {
+			verbose(env, "bpf_obj_new/bpf_percpu_obj_new requires prog BTF\n");
+			return -EINVAL;
+		}
+
+		ret_t = btf_type_by_id(ret_btf, ret_btf_id);
+		if (!ret_t || !__btf_type_is_struct(ret_t)) {
+			verbose(env, "bpf_obj_new/bpf_percpu_obj_new type ID argument must be of a struct\n");
+			return -EINVAL;
+		}
+
+		if (meta->func_id == special_kfunc_list[KF_bpf_percpu_obj_new_impl]) {
+			if (ret_t->size > BPF_GLOBAL_PERCPU_MA_MAX_SIZE) {
+				verbose(env, "bpf_percpu_obj_new type size (%d) is greater than %d\n",
+					ret_t->size, BPF_GLOBAL_PERCPU_MA_MAX_SIZE);
+				return -EINVAL;
+			}
+
+			if (!bpf_global_percpu_ma_set) {
+				mutex_lock(&bpf_percpu_ma_lock);
+				if (!bpf_global_percpu_ma_set) {
+					/* Charge memory allocated with bpf_global_percpu_ma to
+					 * root memcg. The obj_cgroup for root memcg is NULL.
+					 */
+					err = bpf_mem_alloc_percpu_init(&bpf_global_percpu_ma, NULL);
+					if (!err)
+						bpf_global_percpu_ma_set = true;
+				}
+				mutex_unlock(&bpf_percpu_ma_lock);
+				if (err)
+					return err;
+			}
+
+			mutex_lock(&bpf_percpu_ma_lock);
+			err = bpf_mem_alloc_percpu_unit_init(&bpf_global_percpu_ma, ret_t->size);
+			mutex_unlock(&bpf_percpu_ma_lock);
+			if (err)
+				return err;
+		}
+
+		struct_meta = btf_find_struct_meta(ret_btf, ret_btf_id);
+		if (meta->func_id == special_kfunc_list[KF_bpf_percpu_obj_new_impl]) {
+			if (!__btf_type_is_scalar_struct(env, ret_btf, ret_t, 0)) {
+				verbose(env, "bpf_percpu_obj_new type ID argument must be of a struct of scalars\n");
+				return -EINVAL;
+			}
+
+			if (struct_meta) {
+				verbose(env, "bpf_percpu_obj_new type ID argument must not contain special fields\n");
+				return -EINVAL;
+			}
+		}
+
+		mark_reg_known_zero(env, regs, BPF_REG_0);
+		regs[BPF_REG_0].type = PTR_TO_BTF_ID | MEM_ALLOC;
+		regs[BPF_REG_0].btf = ret_btf;
+		regs[BPF_REG_0].btf_id = ret_btf_id;
+		if (meta->func_id == special_kfunc_list[KF_bpf_percpu_obj_new_impl])
+			regs[BPF_REG_0].type |= MEM_PERCPU;
+
+		insn_aux->obj_new_size = ret_t->size;
+		insn_aux->kptr_struct_meta = struct_meta;
+	} else if (meta->func_id == special_kfunc_list[KF_bpf_refcount_acquire_impl]) {
+		mark_reg_known_zero(env, regs, BPF_REG_0);
+		regs[BPF_REG_0].type = PTR_TO_BTF_ID | MEM_ALLOC;
+		regs[BPF_REG_0].btf = meta->arg_btf;
+		regs[BPF_REG_0].btf_id = meta->arg_btf_id;
+
+		insn_aux->kptr_struct_meta =
+			btf_find_struct_meta(meta->arg_btf,
+					     meta->arg_btf_id);
+	} else if (is_list_node_type(ptr_type)) {
+		struct btf_field *field = meta->arg_list_head.field;
+
+		mark_reg_graph_node(regs, BPF_REG_0, &field->graph_root);
+	} else if (is_rbtree_node_type(ptr_type)) {
+		struct btf_field *field = meta->arg_rbtree_root.field;
+
+		mark_reg_graph_node(regs, BPF_REG_0, &field->graph_root);
+	} else if (meta->func_id == special_kfunc_list[KF_bpf_cast_to_kern_ctx]) {
+		mark_reg_known_zero(env, regs, BPF_REG_0);
+		regs[BPF_REG_0].type = PTR_TO_BTF_ID | PTR_TRUSTED;
+		regs[BPF_REG_0].btf = desc_btf;
+		regs[BPF_REG_0].btf_id = meta->ret_btf_id;
+	} else if (meta->func_id == special_kfunc_list[KF_bpf_rdonly_cast]) {
+		ret_t = btf_type_by_id(desc_btf, meta->arg_constant.value);
+		if (!ret_t || !btf_type_is_struct(ret_t)) {
+			verbose(env,
+				"kfunc bpf_rdonly_cast type ID argument must be of a struct\n");
+			return -EINVAL;
+		}
+
+		mark_reg_known_zero(env, regs, BPF_REG_0);
+		regs[BPF_REG_0].type = PTR_TO_BTF_ID | PTR_UNTRUSTED;
+		regs[BPF_REG_0].btf = desc_btf;
+		regs[BPF_REG_0].btf_id = meta->arg_constant.value;
+	} else if (meta->func_id == special_kfunc_list[KF_bpf_dynptr_slice] ||
+		   meta->func_id == special_kfunc_list[KF_bpf_dynptr_slice_rdwr]) {
+		enum bpf_type_flag type_flag = get_dynptr_type_flag(meta->initialized_dynptr.type);
+
+		mark_reg_known_zero(env, regs, BPF_REG_0);
+
+		if (!meta->arg_constant.found) {
+			verbose(env, "verifier internal error: bpf_dynptr_slice(_rdwr) no constant size\n");
+			return -EFAULT;
+		}
+
+		regs[BPF_REG_0].mem_size = meta->arg_constant.value;
+
+		/* PTR_MAYBE_NULL will be added when is_kfunc_ret_null is checked */
+		regs[BPF_REG_0].type = PTR_TO_MEM | type_flag;
+
+		if (meta->func_id == special_kfunc_list[KF_bpf_dynptr_slice]) {
+			regs[BPF_REG_0].type |= MEM_RDONLY;
+		} else {
+			/* this will set env->seen_direct_write to true */
+			if (!may_access_direct_pkt_data(env, NULL, BPF_WRITE)) {
+				verbose(env, "the prog does not allow writes to packet data\n");
+				return -EINVAL;
+			}
+		}
+
+		if (!meta->initialized_dynptr.id) {
+			verbose(env, "verifier internal error: no dynptr id\n");
+			return -EFAULT;
+		}
+		regs[BPF_REG_0].dynptr_id = meta->initialized_dynptr.id;
+
+		/* we don't need to set BPF_REG_0's ref obj id
+		 * because packet slices are not refcounted (see
+		 * dynptr_type_refcounted)
+		 */
+	} else {
+		return 0;
+	}
+
+	return 1;
+}
+
 static int check_return_code(struct bpf_verifier_env *env, int regno, const char *reg_name);
 
 static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
@@ -13434,7 +13604,6 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
 	struct bpf_insn_aux_data *insn_aux;
 	int err, insn_idx = *insn_idx_p;
 	const struct btf_param *args;
-	const struct btf_type *ret_t;
 	struct btf *desc_btf;
 
 	/* skip for now, but return error when we find this in fixup_kfunc_call */
@@ -13476,6 +13645,9 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
 			return err;
 		}
 		__mark_btf_func_reg_size(env, regs, BPF_REG_0, sizeof(u32));
+	} else if (!insn->off && insn->imm == special_kfunc_list[KF___bpf_trap]) {
+		verbose(env, "unexpected __bpf_trap() due to uninitialized variable?\n");
+		return -EFAULT;
 	}
 
 	if (is_kfunc_destructive(&meta) && !capable(CAP_SYS_BOOT)) {
@@ -13654,165 +13826,10 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
 		mark_btf_func_reg_size(env, BPF_REG_0, t->size);
 	} else if (btf_type_is_ptr(t)) {
 		ptr_type = btf_type_skip_modifiers(desc_btf, t->type, &ptr_type_id);
-
-		if (meta.btf == btf_vmlinux && btf_id_set_contains(&special_kfunc_set, meta.func_id)) {
-			if (meta.func_id == special_kfunc_list[KF_bpf_obj_new_impl] ||
-			    meta.func_id == special_kfunc_list[KF_bpf_percpu_obj_new_impl]) {
-				struct btf_struct_meta *struct_meta;
-				struct btf *ret_btf;
-				u32 ret_btf_id;
-
-				if (meta.func_id == special_kfunc_list[KF_bpf_obj_new_impl] && !bpf_global_ma_set)
-					return -ENOMEM;
-
-				if (((u64)(u32)meta.arg_constant.value) != meta.arg_constant.value) {
-					verbose(env, "local type ID argument must be in range [0, U32_MAX]\n");
-					return -EINVAL;
-				}
-
-				ret_btf = env->prog->aux->btf;
-				ret_btf_id = meta.arg_constant.value;
-
-				/* This may be NULL due to user not supplying a BTF */
-				if (!ret_btf) {
-					verbose(env, "bpf_obj_new/bpf_percpu_obj_new requires prog BTF\n");
-					return -EINVAL;
-				}
-
-				ret_t = btf_type_by_id(ret_btf, ret_btf_id);
-				if (!ret_t || !__btf_type_is_struct(ret_t)) {
-					verbose(env, "bpf_obj_new/bpf_percpu_obj_new type ID argument must be of a struct\n");
-					return -EINVAL;
-				}
-
-				if (meta.func_id == special_kfunc_list[KF_bpf_percpu_obj_new_impl]) {
-					if (ret_t->size > BPF_GLOBAL_PERCPU_MA_MAX_SIZE) {
-						verbose(env, "bpf_percpu_obj_new type size (%d) is greater than %d\n",
-							ret_t->size, BPF_GLOBAL_PERCPU_MA_MAX_SIZE);
-						return -EINVAL;
-					}
-
-					if (!bpf_global_percpu_ma_set) {
-						mutex_lock(&bpf_percpu_ma_lock);
-						if (!bpf_global_percpu_ma_set) {
-							/* Charge memory allocated with bpf_global_percpu_ma to
-							 * root memcg. The obj_cgroup for root memcg is NULL.
-							 */
-							err = bpf_mem_alloc_percpu_init(&bpf_global_percpu_ma, NULL);
-							if (!err)
-								bpf_global_percpu_ma_set = true;
-						}
-						mutex_unlock(&bpf_percpu_ma_lock);
-						if (err)
-							return err;
-					}
-
-					mutex_lock(&bpf_percpu_ma_lock);
-					err = bpf_mem_alloc_percpu_unit_init(&bpf_global_percpu_ma, ret_t->size);
-					mutex_unlock(&bpf_percpu_ma_lock);
-					if (err)
-						return err;
-				}
-
-				struct_meta = btf_find_struct_meta(ret_btf, ret_btf_id);
-				if (meta.func_id == special_kfunc_list[KF_bpf_percpu_obj_new_impl]) {
-					if (!__btf_type_is_scalar_struct(env, ret_btf, ret_t, 0)) {
-						verbose(env, "bpf_percpu_obj_new type ID argument must be of a struct of scalars\n");
-						return -EINVAL;
-					}
-
-					if (struct_meta) {
-						verbose(env, "bpf_percpu_obj_new type ID argument must not contain special fields\n");
-						return -EINVAL;
-					}
-				}
-
-				mark_reg_known_zero(env, regs, BPF_REG_0);
-				regs[BPF_REG_0].type = PTR_TO_BTF_ID | MEM_ALLOC;
-				regs[BPF_REG_0].btf = ret_btf;
-				regs[BPF_REG_0].btf_id = ret_btf_id;
-				if (meta.func_id == special_kfunc_list[KF_bpf_percpu_obj_new_impl])
-					regs[BPF_REG_0].type |= MEM_PERCPU;
-
-				insn_aux->obj_new_size = ret_t->size;
-				insn_aux->kptr_struct_meta = struct_meta;
-			} else if (meta.func_id == special_kfunc_list[KF_bpf_refcount_acquire_impl]) {
-				mark_reg_known_zero(env, regs, BPF_REG_0);
-				regs[BPF_REG_0].type = PTR_TO_BTF_ID | MEM_ALLOC;
-				regs[BPF_REG_0].btf = meta.arg_btf;
-				regs[BPF_REG_0].btf_id = meta.arg_btf_id;
-
-				insn_aux->kptr_struct_meta =
-					btf_find_struct_meta(meta.arg_btf,
-							     meta.arg_btf_id);
-			} else if (meta.func_id == special_kfunc_list[KF_bpf_list_pop_front] ||
-				   meta.func_id == special_kfunc_list[KF_bpf_list_pop_back]) {
-				struct btf_field *field = meta.arg_list_head.field;
-
-				mark_reg_graph_node(regs, BPF_REG_0, &field->graph_root);
-			} else if (meta.func_id == special_kfunc_list[KF_bpf_rbtree_remove] ||
-				   meta.func_id == special_kfunc_list[KF_bpf_rbtree_first]) {
-				struct btf_field *field = meta.arg_rbtree_root.field;
-
-				mark_reg_graph_node(regs, BPF_REG_0, &field->graph_root);
-			} else if (meta.func_id == special_kfunc_list[KF_bpf_cast_to_kern_ctx]) {
-				mark_reg_known_zero(env, regs, BPF_REG_0);
-				regs[BPF_REG_0].type = PTR_TO_BTF_ID | PTR_TRUSTED;
-				regs[BPF_REG_0].btf = desc_btf;
-				regs[BPF_REG_0].btf_id = meta.ret_btf_id;
-			} else if (meta.func_id == special_kfunc_list[KF_bpf_rdonly_cast]) {
-				ret_t = btf_type_by_id(desc_btf, meta.arg_constant.value);
-				if (!ret_t || !btf_type_is_struct(ret_t)) {
-					verbose(env,
-						"kfunc bpf_rdonly_cast type ID argument must be of a struct\n");
-					return -EINVAL;
-				}
-
-				mark_reg_known_zero(env, regs, BPF_REG_0);
-				regs[BPF_REG_0].type = PTR_TO_BTF_ID | PTR_UNTRUSTED;
-				regs[BPF_REG_0].btf = desc_btf;
-				regs[BPF_REG_0].btf_id = meta.arg_constant.value;
-			} else if (meta.func_id == special_kfunc_list[KF_bpf_dynptr_slice] ||
-				   meta.func_id == special_kfunc_list[KF_bpf_dynptr_slice_rdwr]) {
-				enum bpf_type_flag type_flag = get_dynptr_type_flag(meta.initialized_dynptr.type);
-
-				mark_reg_known_zero(env, regs, BPF_REG_0);
-
-				if (!meta.arg_constant.found) {
-					verbose(env, "verifier internal error: bpf_dynptr_slice(_rdwr) no constant size\n");
-					return -EFAULT;
-				}
-
-				regs[BPF_REG_0].mem_size = meta.arg_constant.value;
-
-				/* PTR_MAYBE_NULL will be added when is_kfunc_ret_null is checked */
-				regs[BPF_REG_0].type = PTR_TO_MEM | type_flag;
-
-				if (meta.func_id == special_kfunc_list[KF_bpf_dynptr_slice]) {
-					regs[BPF_REG_0].type |= MEM_RDONLY;
-				} else {
-					/* this will set env->seen_direct_write to true */
-					if (!may_access_direct_pkt_data(env, NULL, BPF_WRITE)) {
-						verbose(env, "the prog does not allow writes to packet data\n");
-						return -EINVAL;
-					}
-				}
-
-				if (!meta.initialized_dynptr.id) {
-					verbose(env, "verifier internal error: no dynptr id\n");
-					return -EFAULT;
-				}
-				regs[BPF_REG_0].dynptr_id = meta.initialized_dynptr.id;
-
-				/* we don't need to set BPF_REG_0's ref obj id
-				 * because packet slices are not refcounted (see
-				 * dynptr_type_refcounted)
-				 */
-			} else {
-				verbose(env, "kernel function %s unhandled dynamic return type\n",
-					meta.func_name);
-				return -EFAULT;
-			}
+		err = check_special_kfunc(env, &meta, regs, insn_aux, ptr_type, desc_btf);
+		if (err) {
+			if (err < 0)
+				return err;
 		} else if (btf_type_is_void(ptr_type)) {
 			/* kfunc returning 'void *' is equivalent to returning scalar */
 			mark_reg_unknown(env, regs, BPF_REG_0);
@@ -13881,14 +13898,14 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
 			if (is_kfunc_ret_null(&meta))
 				regs[BPF_REG_0].id = id;
 			regs[BPF_REG_0].ref_obj_id = id;
-		} else if (meta.func_id == special_kfunc_list[KF_bpf_rbtree_first]) {
+		} else if (is_rbtree_node_type(ptr_type) || is_list_node_type(ptr_type)) {
 			ref_set_non_owning(env, &regs[BPF_REG_0]);
 		}
 
 		if (reg_may_point_to_spin_lock(&regs[BPF_REG_0]) && !regs[BPF_REG_0].id)
 			regs[BPF_REG_0].id = ++env->id_gen;
 	} else if (btf_type_is_void(t)) {
-		if (meta.btf == btf_vmlinux && btf_id_set_contains(&special_kfunc_set, meta.func_id)) {
+		if (meta.btf == btf_vmlinux) {
 			if (meta.func_id == special_kfunc_list[KF_bpf_obj_drop_impl] ||
 			    meta.func_id == special_kfunc_list[KF_bpf_percpu_obj_drop_impl]) {
 				insn_aux->kptr_struct_meta =
@@ -16377,6 +16394,7 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env,
 	struct bpf_reg_state *eq_branch_regs;
 	struct linked_regs linked_regs = {};
 	u8 opcode = BPF_OP(insn->code);
+	int insn_flags = 0;
 	bool is_jmp32;
 	int pred = -1;
 	int err;
@@ -16435,6 +16453,11 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env,
 				insn->src_reg);
 			return -EACCES;
 		}
+
+		if (src_reg->type == PTR_TO_STACK)
+			insn_flags |= INSN_F_SRC_REG_STACK;
+		if (dst_reg->type == PTR_TO_STACK)
+			insn_flags |= INSN_F_DST_REG_STACK;
 	} else {
 		if (insn->src_reg != BPF_REG_0) {
 			verbose(env, "BPF_JMP/JMP32 uses reserved fields\n");
@@ -16444,6 +16467,15 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env,
 		memset(src_reg, 0, sizeof(*src_reg));
 		src_reg->type = SCALAR_VALUE;
 		__mark_reg_known(src_reg, insn->imm);
+
+		if (dst_reg->type == PTR_TO_STACK)
+			insn_flags |= INSN_F_DST_REG_STACK;
+	}
+
+	if (insn_flags) {
+		err = push_insn_history(env, this_branch, insn_flags, 0);
+		if (err)
+			return err;
 	}
 
 	is_jmp32 = BPF_CLASS(insn->code) == BPF_JMP32;
@@ -19659,10 +19691,9 @@ process_bpf_exit:
 						return err;
 					break;
 				} else {
-					if (WARN_ON_ONCE(env->cur_state->loop_entry)) {
-						verbose(env, "verifier bug: env->cur_state->loop_entry != NULL\n");
+					if (verifier_bug_if(env->cur_state->loop_entry, env,
+							    "broken loop detection"))
 						return -EFAULT;
-					}
 					do_print_state = true;
 					continue;
 				}
@@ -20720,10 +20751,9 @@ static int opt_subreg_zext_lo32_rnd_hi32(struct bpf_verifier_env *env,
 		if (bpf_pseudo_kfunc_call(&insn))
 			continue;
 
-		if (WARN_ON(load_reg == -1)) {
-			verbose(env, "verifier bug. zext_dst is set, but no reg is defined\n");
+		if (verifier_bug_if(load_reg == -1, env,
+				    "zext_dst is set, but no reg is defined"))
 			return -EFAULT;
-		}
 
 		zext_patch[0] = insn;
 		zext_patch[1].dst_reg = load_reg;
@@ -21040,11 +21070,9 @@ static int jit_subprogs(struct bpf_verifier_env *env)
 		 * propagated in any case.
 		 */
 		subprog = find_subprog(env, i + insn->imm + 1);
-		if (subprog < 0) {
-			WARN_ONCE(1, "verifier bug. No program starts at insn %d\n",
-				  i + insn->imm + 1);
+		if (verifier_bug_if(subprog < 0, env, "No program to jit at insn %d",
+				    i + insn->imm + 1))
 			return -EFAULT;
-		}
 		/* temporarily remember subprog id inside insn instead of
 		 * aux_data, since next loop will split up all insns into funcs
 		 */
@@ -21487,13 +21515,17 @@ static int fixup_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
 		   desc->func_id == special_kfunc_list[KF_bpf_rdonly_cast]) {
 		insn_buf[0] = BPF_MOV64_REG(BPF_REG_0, BPF_REG_1);
 		*cnt = 1;
-	} else if (is_bpf_wq_set_callback_impl_kfunc(desc->func_id)) {
-		struct bpf_insn ld_addrs[2] = { BPF_LD_IMM64(BPF_REG_4, (long)env->prog->aux) };
+	}
 
-		insn_buf[0] = ld_addrs[0];
-		insn_buf[1] = ld_addrs[1];
-		insn_buf[2] = *insn;
-		*cnt = 3;
+	if (env->insn_aux_data[insn_idx].arg_prog) {
+		u32 regno = env->insn_aux_data[insn_idx].arg_prog;
+		struct bpf_insn ld_addrs[2] = { BPF_LD_IMM64(regno, (long)env->prog->aux) };
+		int idx = *cnt;
+
+		insn_buf[idx++] = ld_addrs[0];
+		insn_buf[idx++] = ld_addrs[1];
+		insn_buf[idx++] = *insn;
+		*cnt = idx;
 	}
 	return 0;
 }
@@ -22403,7 +22435,7 @@ next_insn:
 			continue;
 		/* We need two slots in case timed may_goto is supported. */
 		if (stack_slots > slots) {
-			verbose(env, "verifier bug: stack_slots supports may_goto only\n");
+			verifier_bug(env, "stack_slots supports may_goto only");
 			return -EFAULT;
 		}
 
diff --git a/kernel/cgroup/cgroup-internal.h b/kernel/cgroup/cgroup-internal.h
index 95ab39e1ec8f..b14e61c64a34 100644
--- a/kernel/cgroup/cgroup-internal.h
+++ b/kernel/cgroup/cgroup-internal.h
@@ -270,9 +270,9 @@ int cgroup_task_count(const struct cgroup *cgrp);
 /*
  * rstat.c
  */
-int cgroup_rstat_init(struct cgroup *cgrp);
-void cgroup_rstat_exit(struct cgroup *cgrp);
-void cgroup_rstat_boot(void);
+int css_rstat_init(struct cgroup_subsys_state *css);
+void css_rstat_exit(struct cgroup_subsys_state *css);
+int ss_rstat_init(struct cgroup_subsys *ss);
 void cgroup_base_stat_cputime_show(struct seq_file *seq);
 
 /*
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 63e5b90da1f3..a723b7dc6e4e 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -95,6 +95,9 @@ EXPORT_SYMBOL_GPL(cgroup_mutex);
 EXPORT_SYMBOL_GPL(css_set_lock);
 #endif
 
+struct blocking_notifier_head cgroup_lifetime_notifier =
+	BLOCKING_NOTIFIER_INIT(cgroup_lifetime_notifier);
+
 DEFINE_SPINLOCK(trace_cgroup_path_lock);
 char trace_cgroup_path[TRACE_CGROUP_PATH_LEN];
 static bool cgroup_debug __read_mostly;
@@ -161,10 +164,14 @@ static struct static_key_true *cgroup_subsys_on_dfl_key[] = {
 };
 #undef SUBSYS
 
-static DEFINE_PER_CPU(struct cgroup_rstat_cpu, cgrp_dfl_root_rstat_cpu);
+static DEFINE_PER_CPU(struct css_rstat_cpu, root_rstat_cpu);
+static DEFINE_PER_CPU(struct cgroup_rstat_base_cpu, root_rstat_base_cpu);
 
 /* the default hierarchy */
-struct cgroup_root cgrp_dfl_root = { .cgrp.rstat_cpu = &cgrp_dfl_root_rstat_cpu };
+struct cgroup_root cgrp_dfl_root = {
+	.cgrp.self.rstat_cpu = &root_rstat_cpu,
+	.cgrp.rstat_base_cpu = &root_rstat_base_cpu,
+};
 EXPORT_SYMBOL_GPL(cgrp_dfl_root);
 
 /*
@@ -1335,6 +1342,7 @@ static void cgroup_destroy_root(struct cgroup_root *root)
 {
 	struct cgroup *cgrp = &root->cgrp;
 	struct cgrp_cset_link *link, *tmp_link;
+	int ret;
 
 	trace_cgroup_destroy_root(root);
 
@@ -1343,6 +1351,10 @@ static void cgroup_destroy_root(struct cgroup_root *root)
 	BUG_ON(atomic_read(&root->nr_cgrps));
 	BUG_ON(!list_empty(&cgrp->self.children));
 
+	ret = blocking_notifier_call_chain(&cgroup_lifetime_notifier,
+					   CGROUP_LIFETIME_OFFLINE, cgrp);
+	WARN_ON_ONCE(notifier_to_errno(ret));
+
 	/* Rebind all subsystems back to the default hierarchy */
 	WARN_ON(rebind_subsystems(&cgrp_dfl_root, root->subsys_mask));
 
@@ -1371,7 +1383,6 @@ static void cgroup_destroy_root(struct cgroup_root *root)
 
 	cgroup_unlock();
 
-	cgroup_rstat_exit(cgrp);
 	kernfs_destroy_root(root->kf_root);
 	cgroup_free_root(root);
 }
@@ -1715,7 +1726,7 @@ static void css_clear_dir(struct cgroup_subsys_state *css)
 
 	css->flags &= ~CSS_VISIBLE;
 
-	if (!css->ss) {
+	if (css_is_self(css)) {
 		if (cgroup_on_dfl(cgrp)) {
 			cgroup_addrm_files(css, cgrp,
 					   cgroup_base_files, false);
@@ -1747,7 +1758,7 @@ static int css_populate_dir(struct cgroup_subsys_state *css)
 	if (css->flags & CSS_VISIBLE)
 		return 0;
 
-	if (!css->ss) {
+	if (css_is_self(css)) {
 		if (cgroup_on_dfl(cgrp)) {
 			ret = cgroup_addrm_files(css, cgrp,
 						 cgroup_base_files, true);
@@ -1876,13 +1887,6 @@ int rebind_subsystems(struct cgroup_root *dst_root, u16 ss_mask)
 		}
 		spin_unlock_irq(&css_set_lock);
 
-		if (ss->css_rstat_flush) {
-			list_del_rcu(&css->rstat_css_node);
-			synchronize_rcu();
-			list_add_rcu(&css->rstat_css_node,
-				     &dcgrp->rstat_css_list);
-		}
-
 		/* default hierarchy doesn't enable controllers by default */
 		dst_root->subsys_mask |= 1 << ssid;
 		if (dst_root == &cgrp_dfl_root) {
@@ -2065,7 +2069,6 @@ static void init_cgroup_housekeeping(struct cgroup *cgrp)
 	cgrp->dom_cgrp = cgrp;
 	cgrp->max_descendants = INT_MAX;
 	cgrp->max_depth = INT_MAX;
-	INIT_LIST_HEAD(&cgrp->rstat_css_list);
 	prev_cputime_init(&cgrp->prev_cputime);
 
 	for_each_subsys(ss, ssid)
@@ -2146,7 +2149,7 @@ int cgroup_setup_root(struct cgroup_root *root, u16 ss_mask)
 	if (ret)
 		goto destroy_root;
 
-	ret = cgroup_rstat_init(root_cgrp);
+	ret = css_rstat_init(&root_cgrp->self);
 	if (ret)
 		goto destroy_root;
 
@@ -2154,10 +2157,9 @@ int cgroup_setup_root(struct cgroup_root *root, u16 ss_mask)
 	if (ret)
 		goto exit_stats;
 
-	if (root == &cgrp_dfl_root) {
-		ret = cgroup_bpf_inherit(root_cgrp);
-		WARN_ON_ONCE(ret);
-	}
+	ret = blocking_notifier_call_chain(&cgroup_lifetime_notifier,
+					   CGROUP_LIFETIME_ONLINE, root_cgrp);
+	WARN_ON_ONCE(notifier_to_errno(ret));
 
 	trace_cgroup_setup_root(root);
 
@@ -2188,7 +2190,7 @@ int cgroup_setup_root(struct cgroup_root *root, u16 ss_mask)
 	goto out;
 
 exit_stats:
-	cgroup_rstat_exit(root_cgrp);
+	css_rstat_exit(&root_cgrp->self);
 destroy_root:
 	kernfs_destroy_root(root->kf_root);
 	root->kf_root = NULL;
@@ -5444,8 +5446,9 @@ static void css_free_rwork_fn(struct work_struct *work)
 	struct cgroup *cgrp = css->cgroup;
 
 	percpu_ref_exit(&css->refcnt);
+	css_rstat_exit(css);
 
-	if (ss) {
+	if (!css_is_self(css)) {
 		/* css free path */
 		struct cgroup_subsys_state *parent = css->parent;
 		int id = css->id;
@@ -5474,7 +5477,6 @@ static void css_free_rwork_fn(struct work_struct *work)
 			cgroup_put(cgroup_parent(cgrp));
 			kernfs_put(cgrp->kn);
 			psi_cgroup_free(cgrp);
-			cgroup_rstat_exit(cgrp);
 			kfree(cgrp);
 		} else {
 			/*
@@ -5499,14 +5501,10 @@ static void css_release_work_fn(struct work_struct *work)
 	css->flags |= CSS_RELEASED;
 	list_del_rcu(&css->sibling);
 
-	if (ss) {
+	if (!css_is_self(css)) {
 		struct cgroup *parent_cgrp;
 
-		/* css release path */
-		if (!list_empty(&css->rstat_css_node)) {
-			cgroup_rstat_flush(cgrp);
-			list_del_rcu(&css->rstat_css_node);
-		}
+		css_rstat_flush(css);
 
 		cgroup_idr_replace(&ss->css_idr, NULL, css->id);
 		if (ss->css_released)
@@ -5532,7 +5530,7 @@ static void css_release_work_fn(struct work_struct *work)
 		/* cgroup release path */
 		TRACE_CGROUP_PATH(release, cgrp);
 
-		cgroup_rstat_flush(cgrp);
+		css_rstat_flush(&cgrp->self);
 
 		spin_lock_irq(&css_set_lock);
 		for (tcgrp = cgroup_parent(cgrp); tcgrp;
@@ -5580,7 +5578,6 @@ static void init_and_link_css(struct cgroup_subsys_state *css,
 	css->id = -1;
 	INIT_LIST_HEAD(&css->sibling);
 	INIT_LIST_HEAD(&css->children);
-	INIT_LIST_HEAD(&css->rstat_css_node);
 	css->serial_nr = css_serial_nr_next++;
 	atomic_set(&css->online_cnt, 0);
 
@@ -5589,9 +5586,6 @@ static void init_and_link_css(struct cgroup_subsys_state *css,
 		css_get(css->parent);
 	}
 
-	if (ss->css_rstat_flush)
-		list_add_rcu(&css->rstat_css_node, &cgrp->rstat_css_list);
-
 	BUG_ON(cgroup_css(cgrp, ss));
 }
 
@@ -5684,6 +5678,10 @@ static struct cgroup_subsys_state *css_create(struct cgroup *cgrp,
 		goto err_free_css;
 	css->id = err;
 
+	err = css_rstat_init(css);
+	if (err)
+		goto err_free_css;
+
 	/* @css is ready to be brought online now, make it visible */
 	list_add_tail_rcu(&css->sibling, &parent_css->children);
 	cgroup_idr_replace(&ss->css_idr, css, css->id);
@@ -5697,7 +5695,6 @@ static struct cgroup_subsys_state *css_create(struct cgroup *cgrp,
 err_list_del:
 	list_del_rcu(&css->sibling);
 err_free_css:
-	list_del_rcu(&css->rstat_css_node);
 	INIT_RCU_WORK(&css->destroy_rwork, css_free_rwork_fn);
 	queue_rcu_work(cgroup_destroy_wq, &css->destroy_rwork);
 	return ERR_PTR(err);
@@ -5713,7 +5710,7 @@ static struct cgroup *cgroup_create(struct cgroup *parent, const char *name,
 	struct cgroup_root *root = parent->root;
 	struct cgroup *cgrp, *tcgrp;
 	struct kernfs_node *kn;
-	int level = parent->level + 1;
+	int i, level = parent->level + 1;
 	int ret;
 
 	/* allocate the cgroup and its ID, 0 is reserved for the root */
@@ -5725,17 +5722,13 @@ static struct cgroup *cgroup_create(struct cgroup *parent, const char *name,
 	if (ret)
 		goto out_free_cgrp;
 
-	ret = cgroup_rstat_init(cgrp);
-	if (ret)
-		goto out_cancel_ref;
-
 	/* create the directory */
 	kn = kernfs_create_dir_ns(parent->kn, name, mode,
 				  current_fsuid(), current_fsgid(),
 				  cgrp, NULL);
 	if (IS_ERR(kn)) {
 		ret = PTR_ERR(kn);
-		goto out_stat_exit;
+		goto out_cancel_ref;
 	}
 	cgrp->kn = kn;
 
@@ -5745,15 +5738,20 @@ static struct cgroup *cgroup_create(struct cgroup *parent, const char *name,
 	cgrp->root = root;
 	cgrp->level = level;
 
-	ret = psi_cgroup_alloc(cgrp);
+	/*
+	 * Now that init_cgroup_housekeeping() has been called and cgrp->self
+	 * is setup, it is safe to perform rstat initialization on it.
+	 */
+	ret = css_rstat_init(&cgrp->self);
 	if (ret)
 		goto out_kernfs_remove;
 
-	if (cgrp->root == &cgrp_dfl_root) {
-		ret = cgroup_bpf_inherit(cgrp);
-		if (ret)
-			goto out_psi_free;
-	}
+	ret = psi_cgroup_alloc(cgrp);
+	if (ret)
+		goto out_stat_exit;
+
+	for (tcgrp = cgrp; tcgrp; tcgrp = cgroup_parent(tcgrp))
+		cgrp->ancestors[tcgrp->level] = tcgrp;
 
 	/*
 	 * New cgroup inherits effective freeze counter, and
@@ -5771,24 +5769,6 @@ static struct cgroup *cgroup_create(struct cgroup *parent, const char *name,
 		set_bit(CGRP_FROZEN, &cgrp->flags);
 	}
 
-	spin_lock_irq(&css_set_lock);
-	for (tcgrp = cgrp; tcgrp; tcgrp = cgroup_parent(tcgrp)) {
-		cgrp->ancestors[tcgrp->level] = tcgrp;
-
-		if (tcgrp != cgrp) {
-			tcgrp->nr_descendants++;
-
-			/*
-			 * If the new cgroup is frozen, all ancestor cgroups
-			 * get a new frozen descendant, but their state can't
-			 * change because of this.
-			 */
-			if (cgrp->freezer.e_freeze)
-				tcgrp->freezer.nr_frozen_descendants++;
-		}
-	}
-	spin_unlock_irq(&css_set_lock);
-
 	if (notify_on_release(parent))
 		set_bit(CGRP_NOTIFY_ON_RELEASE, &cgrp->flags);
 
@@ -5797,7 +5777,29 @@ static struct cgroup *cgroup_create(struct cgroup *parent, const char *name,
 
 	cgrp->self.serial_nr = css_serial_nr_next++;
 
+	ret = blocking_notifier_call_chain_robust(&cgroup_lifetime_notifier,
+						  CGROUP_LIFETIME_ONLINE,
+						  CGROUP_LIFETIME_OFFLINE, cgrp);
+	ret = notifier_to_errno(ret);
+	if (ret)
+		goto out_psi_free;
+
 	/* allocation complete, commit to creation */
+	spin_lock_irq(&css_set_lock);
+	for (i = 0; i < level; i++) {
+		tcgrp = cgrp->ancestors[i];
+		tcgrp->nr_descendants++;
+
+		/*
+		 * If the new cgroup is frozen, all ancestor cgroups get a new
+		 * frozen descendant, but their state can't change because of
+		 * this.
+		 */
+		if (cgrp->freezer.e_freeze)
+			tcgrp->freezer.nr_frozen_descendants++;
+	}
+	spin_unlock_irq(&css_set_lock);
+
 	list_add_tail_rcu(&cgrp->self.sibling, &cgroup_parent(cgrp)->self.children);
 	atomic_inc(&root->nr_cgrps);
 	cgroup_get_live(parent);
@@ -5815,10 +5817,10 @@ static struct cgroup *cgroup_create(struct cgroup *parent, const char *name,
 
 out_psi_free:
 	psi_cgroup_free(cgrp);
+out_stat_exit:
+	css_rstat_exit(&cgrp->self);
 out_kernfs_remove:
 	kernfs_remove(cgrp->kn);
-out_stat_exit:
-	cgroup_rstat_exit(cgrp);
 out_cancel_ref:
 	percpu_ref_exit(&cgrp->self.refcnt);
 out_free_cgrp:
@@ -6015,7 +6017,7 @@ static int cgroup_destroy_locked(struct cgroup *cgrp)
 	struct cgroup *tcgrp, *parent = cgroup_parent(cgrp);
 	struct cgroup_subsys_state *css;
 	struct cgrp_cset_link *link;
-	int ssid;
+	int ssid, ret;
 
 	lockdep_assert_held(&cgroup_mutex);
 
@@ -6073,8 +6075,9 @@ static int cgroup_destroy_locked(struct cgroup *cgrp)
 
 	cgroup1_check_for_release(parent);
 
-	if (cgrp->root == &cgrp_dfl_root)
-		cgroup_bpf_offline(cgrp);
+	ret = blocking_notifier_call_chain(&cgroup_lifetime_notifier,
+					   CGROUP_LIFETIME_OFFLINE, cgrp);
+	WARN_ON_ONCE(notifier_to_errno(ret));
 
 	/* put the base reference */
 	percpu_ref_kill(&cgrp->self.refcnt);
@@ -6136,6 +6139,9 @@ static void __init cgroup_init_subsys(struct cgroup_subsys *ss, bool early)
 	} else {
 		css->id = cgroup_idr_alloc(&ss->css_idr, css, 1, 2, GFP_KERNEL);
 		BUG_ON(css->id < 0);
+
+		BUG_ON(ss_rstat_init(ss));
+		BUG_ON(css_rstat_init(css));
 	}
 
 	/* Update the init_css_set to contain a subsys
@@ -6184,6 +6190,8 @@ int __init cgroup_init_early(void)
 		     ss->id, ss->name);
 		WARN(strlen(cgroup_subsys_name[i]) > MAX_CGROUP_TYPE_NAMELEN,
 		     "cgroup_subsys_name %s too long\n", cgroup_subsys_name[i]);
+		WARN(ss->early_init && ss->css_rstat_flush,
+		     "cgroup rstat cannot be used with early init subsystem\n");
 
 		ss->id = i;
 		ss->name = cgroup_subsys_name[i];
@@ -6212,7 +6220,7 @@ int __init cgroup_init(void)
 	BUG_ON(cgroup_init_cftypes(NULL, cgroup_psi_files));
 	BUG_ON(cgroup_init_cftypes(NULL, cgroup1_base_files));
 
-	cgroup_rstat_boot();
+	BUG_ON(ss_rstat_init(NULL));
 
 	get_user_ns(init_cgroup_ns.user_ns);
 
@@ -6225,6 +6233,8 @@ int __init cgroup_init(void)
 	hash_add(css_set_table, &init_css_set.hlist,
 		 css_set_hash(init_css_set.subsys));
 
+	cgroup_bpf_lifetime_notifier_init();
+
 	BUG_ON(cgroup_setup_root(&cgrp_dfl_root, 0));
 
 	cgroup_unlock();
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index 306b60430091..3bc4301466f3 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -192,6 +192,20 @@ static inline void notify_partition_change(struct cpuset *cs, int old_prs)
 		WRITE_ONCE(cs->prs_err, PERR_NONE);
 }
 
+/*
+ * The top_cpuset is always synchronized to cpu_active_mask and we should avoid
+ * using cpu_online_mask as much as possible. An active CPU is always an online
+ * CPU, but not vice versa. cpu_active_mask and cpu_online_mask can differ
+ * during hotplug operations. A CPU is marked active at the last stage of CPU
+ * bringup (CPUHP_AP_ACTIVE). It is also the stage where cpuset hotplug code
+ * will be called to update the sched domains so that the scheduler can move
+ * a normal task to a newly active CPU or remove tasks away from a newly
+ * inactivated CPU. The online bit is set much earlier in the CPU bringup
+ * process and cleared much later in CPU teardown.
+ *
+ * If cpu_online_mask is used while a hotunplug operation is happening in
+ * parallel, we may leave an offline CPU in cpu_allowed or some other masks.
+ */
 static struct cpuset top_cpuset = {
 	.flags = BIT(CS_ONLINE) | BIT(CS_CPU_EXCLUSIVE) |
 		 BIT(CS_MEM_EXCLUSIVE) | BIT(CS_SCHED_LOAD_BALANCE),
@@ -355,18 +369,18 @@ static inline bool partition_is_populated(struct cpuset *cs,
  * appropriate cpus.
  *
  * One way or another, we guarantee to return some non-empty subset
- * of cpu_online_mask.
+ * of cpu_active_mask.
  *
  * Call with callback_lock or cpuset_mutex held.
  */
-static void guarantee_online_cpus(struct task_struct *tsk,
+static void guarantee_active_cpus(struct task_struct *tsk,
 				  struct cpumask *pmask)
 {
 	const struct cpumask *possible_mask = task_cpu_possible_mask(tsk);
 	struct cpuset *cs;
 
-	if (WARN_ON(!cpumask_and(pmask, possible_mask, cpu_online_mask)))
-		cpumask_copy(pmask, cpu_online_mask);
+	if (WARN_ON(!cpumask_and(pmask, possible_mask, cpu_active_mask)))
+		cpumask_copy(pmask, cpu_active_mask);
 
 	rcu_read_lock();
 	cs = task_cs(tsk);
@@ -1116,9 +1130,11 @@ void cpuset_update_tasks_cpumask(struct cpuset *cs, struct cpumask *new_cpus)
 
 		if (top_cs) {
 			/*
-			 * Percpu kthreads in top_cpuset are ignored
+			 * PF_NO_SETAFFINITY tasks are ignored.
+			 * All per cpu kthreads should have PF_NO_SETAFFINITY
+			 * flag set, see kthread_set_per_cpu().
 			 */
-			if (kthread_is_per_cpu(task))
+			if (task->flags & PF_NO_SETAFFINITY)
 				continue;
 			cpumask_andnot(new_cpus, possible_mask, subpartitions_cpus);
 		} else {
@@ -1388,14 +1404,12 @@ static int compute_effective_exclusive_cpumask(struct cpuset *cs,
 		if (sibling == cs)
 			continue;
 
-		if (!cpumask_empty(sibling->exclusive_cpus) &&
-		    cpumask_intersects(xcpus, sibling->exclusive_cpus)) {
+		if (cpumask_intersects(xcpus, sibling->exclusive_cpus)) {
 			cpumask_andnot(xcpus, xcpus, sibling->exclusive_cpus);
 			retval++;
 			continue;
 		}
-		if (!cpumask_empty(sibling->effective_xcpus) &&
-		    cpumask_intersects(xcpus, sibling->effective_xcpus)) {
+		if (cpumask_intersects(xcpus, sibling->effective_xcpus)) {
 			cpumask_andnot(xcpus, xcpus, sibling->effective_xcpus);
 			retval++;
 		}
@@ -1439,13 +1453,15 @@ static int remote_partition_enable(struct cpuset *cs, int new_prs,
 	 * The requested exclusive_cpus must not be allocated to other
 	 * partitions and it can't use up all the root's effective_cpus.
 	 *
-	 * Note that if there is any local partition root above it or
-	 * remote partition root underneath it, its exclusive_cpus must
-	 * have overlapped with subpartitions_cpus.
+	 * The effective_xcpus mask can contain offline CPUs, but there must
+	 * be at least one or more online CPUs present before it can be enabled.
+	 *
+	 * Note that creating a remote partition with any local partition root
+	 * above it or remote partition root underneath it is not allowed.
 	 */
 	compute_effective_exclusive_cpumask(cs, tmp->new_cpus, NULL);
-	if (cpumask_empty(tmp->new_cpus) ||
-	    cpumask_intersects(tmp->new_cpus, subpartitions_cpus) ||
+	WARN_ON_ONCE(cpumask_intersects(tmp->new_cpus, subpartitions_cpus));
+	if (!cpumask_intersects(tmp->new_cpus, cpu_active_mask) ||
 	    cpumask_subset(top_cpuset.effective_cpus, tmp->new_cpus))
 		return PERR_INVCPUS;
 
@@ -1541,6 +1557,7 @@ static void remote_cpus_update(struct cpuset *cs, struct cpumask *xcpus,
 	 * left in the top cpuset.
 	 */
 	if (adding) {
+		WARN_ON_ONCE(cpumask_intersects(tmp->addmask, subpartitions_cpus));
 		if (!capable(CAP_SYS_ADMIN))
 			cs->prs_err = PERR_ACCESS;
 		else if (cpumask_intersects(tmp->addmask, subpartitions_cpus) ||
@@ -1650,7 +1667,7 @@ static int update_parent_effective_cpumask(struct cpuset *cs, int cmd,
 	bool nocpu;
 
 	lockdep_assert_held(&cpuset_mutex);
-	WARN_ON_ONCE(is_remote_partition(cs));
+	WARN_ON_ONCE(is_remote_partition(cs));	/* For local partition only */
 
 	/*
 	 * new_prs will only be changed for the partcmd_update and
@@ -1696,7 +1713,7 @@ static int update_parent_effective_cpumask(struct cpuset *cs, int cmd,
 		 * exclusive_cpus not set. Sibling conflict should only happen
 		 * if exclusive_cpus isn't set.
 		 */
-		xcpus = tmp->new_cpus;
+		xcpus = tmp->delmask;
 		if (compute_effective_exclusive_cpumask(cs, xcpus, NULL))
 			WARN_ON_ONCE(!cpumask_empty(cs->exclusive_cpus));
 
@@ -1717,9 +1734,20 @@ static int update_parent_effective_cpumask(struct cpuset *cs, int cmd,
 		if (nocpu)
 			return PERR_NOCPUS;
 
-		deleting = cpumask_and(tmp->delmask, xcpus, parent->effective_xcpus);
-		if (deleting)
-			subparts_delta++;
+		/*
+		 * This function will only be called when all the preliminary
+		 * checks have passed. At this point, the following condition
+		 * should hold.
+		 *
+		 * (cs->effective_xcpus & cpu_active_mask) ⊆ parent->effective_cpus
+		 *
+		 * Warn if it is not the case.
+		 */
+		cpumask_and(tmp->new_cpus, xcpus, cpu_active_mask);
+		WARN_ON_ONCE(!cpumask_subset(tmp->new_cpus, parent->effective_cpus));
+
+		deleting = true;
+		subparts_delta++;
 		new_prs = (cmd == partcmd_enable) ? PRS_ROOT : PRS_ISOLATED;
 	} else if (cmd == partcmd_disable) {
 		/*
@@ -1774,6 +1802,15 @@ static int update_parent_effective_cpumask(struct cpuset *cs, int cmd,
 					       parent->effective_xcpus);
 		}
 		/*
+		 * The new CPUs to be removed from parent's effective CPUs
+		 * must be present.
+		 */
+		if (deleting) {
+			cpumask_and(tmp->new_cpus, tmp->delmask, cpu_active_mask);
+			WARN_ON_ONCE(!cpumask_subset(tmp->new_cpus, parent->effective_cpus));
+		}
+
+		/*
 		 * Make partition invalid if parent's effective_cpus could
 		 * become empty and there are tasks in the parent.
 		 */
@@ -2263,7 +2300,7 @@ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs,
 	bool force = false;
 	int old_prs = cs->partition_root_state;
 
-	/* top_cpuset.cpus_allowed tracks cpu_online_mask; it's read-only */
+	/* top_cpuset.cpus_allowed tracks cpu_active_mask; it's read-only */
 	if (cs == &top_cpuset)
 		return -EACCES;
 
@@ -3082,7 +3119,7 @@ static void cpuset_attach_task(struct cpuset *cs, struct task_struct *task)
 	lockdep_assert_held(&cpuset_mutex);
 
 	if (cs != &top_cpuset)
-		guarantee_online_cpus(task, cpus_attach);
+		guarantee_active_cpus(task, cpus_attach);
 	else
 		cpumask_andnot(cpus_attach, task_cpu_possible_mask(task),
 			       subpartitions_cpus);
@@ -3524,11 +3561,7 @@ out_unlock:
  * will call rebuild_sched_domains_locked(). That is not needed
  * in the default hierarchy where only changes in partition
  * will cause repartitioning.
- *
- * If the cpuset has the 'sched.partition' flag enabled, simulate
- * turning 'sched.partition" off.
  */
-
 static void cpuset_css_offline(struct cgroup_subsys_state *css)
 {
 	struct cpuset *cs = css_cs(css);
@@ -3546,6 +3579,11 @@ static void cpuset_css_offline(struct cgroup_subsys_state *css)
 	cpus_read_unlock();
 }
 
+/*
+ * If a dying cpuset has the 'cpus.partition' enabled, turn it off by
+ * changing it back to member to free its exclusive CPUs back to the pool to
+ * be used by other online cpusets.
+ */
 static void cpuset_css_killed(struct cgroup_subsys_state *css)
 {
 	struct cpuset *cs = css_cs(css);
@@ -4026,7 +4064,7 @@ void __init cpuset_init_smp(void)
  *
  * Description: Returns the cpumask_var_t cpus_allowed of the cpuset
  * attached to the specified @tsk.  Guaranteed to return some non-empty
- * subset of cpu_online_mask, even if this means going outside the
+ * subset of cpu_active_mask, even if this means going outside the
  * tasks cpuset, except when the task is in the top cpuset.
  **/
 
@@ -4040,7 +4078,7 @@ void cpuset_cpus_allowed(struct task_struct *tsk, struct cpumask *pmask)
 
 	cs = task_cs(tsk);
 	if (cs != &top_cpuset)
-		guarantee_online_cpus(tsk, pmask);
+		guarantee_active_cpus(tsk, pmask);
 	/*
 	 * Tasks in the top cpuset won't get update to their cpumasks
 	 * when a hotplug online/offline event happens. So we include all
@@ -4054,7 +4092,7 @@ void cpuset_cpus_allowed(struct task_struct *tsk, struct cpumask *pmask)
 		 * allowable online cpu left, we fall back to all possible cpus.
 		 */
 		cpumask_andnot(pmask, possible_mask, subpartitions_cpus);
-		if (!cpumask_intersects(pmask, cpu_online_mask))
+		if (!cpumask_intersects(pmask, cpu_active_mask))
 			cpumask_copy(pmask, possible_mask);
 	}
 
@@ -4164,7 +4202,7 @@ static struct cpuset *nearest_hardwall_ancestor(struct cpuset *cs)
 }
 
 /*
- * cpuset_node_allowed - Can we allocate on a memory node?
+ * cpuset_current_node_allowed - Can current task allocate on a memory node?
  * @node: is this an allowed node?
  * @gfp_mask: memory allocation flags
  *
@@ -4203,7 +4241,7 @@ static struct cpuset *nearest_hardwall_ancestor(struct cpuset *cs)
  *	GFP_KERNEL   - any node in enclosing hardwalled cpuset ok
  *	GFP_USER     - only nodes in current tasks mems allowed ok.
  */
-bool cpuset_node_allowed(int node, gfp_t gfp_mask)
+bool cpuset_current_node_allowed(int node, gfp_t gfp_mask)
 {
 	struct cpuset *cs;		/* current cpuset ancestors */
 	bool allowed;			/* is allocation in zone z allowed? */
@@ -4237,6 +4275,42 @@ bool cpuset_node_allowed(int node, gfp_t gfp_mask)
 	return allowed;
 }
 
+bool cpuset_node_allowed(struct cgroup *cgroup, int nid)
+{
+	struct cgroup_subsys_state *css;
+	struct cpuset *cs;
+	bool allowed;
+
+	/*
+	 * In v1, mem_cgroup and cpuset are unlikely in the same hierarchy
+	 * and mems_allowed is likely to be empty even if we could get to it,
+	 * so return true to avoid taking a global lock on the empty check.
+	 */
+	if (!cpuset_v2())
+		return true;
+
+	css = cgroup_get_e_css(cgroup, &cpuset_cgrp_subsys);
+	if (!css)
+		return true;
+
+	/*
+	 * Normally, accessing effective_mems would require the cpuset_mutex
+	 * or callback_lock - but node_isset is atomic and the reference
+	 * taken via cgroup_get_e_css is sufficient to protect css.
+	 *
+	 * Since this interface is intended for use by migration paths, we
+	 * relax locking here to avoid taking global locks - while accepting
+	 * there may be rare scenarios where the result may be innaccurate.
+	 *
+	 * Reclaim and migration are subject to these same race conditions, and
+	 * cannot make strong isolation guarantees, so this is acceptable.
+	 */
+	cs = container_of(css, struct cpuset, css);
+	allowed = node_isset(nid, cs->effective_mems);
+	css_put(css);
+	return allowed;
+}
+
 /**
  * cpuset_spread_node() - On which node to begin search for a page
  * @rotor: round robin rotor
diff --git a/kernel/cgroup/misc.c b/kernel/cgroup/misc.c
index 2fa3a4fb2aaf..6a01d91ea4cb 100644
--- a/kernel/cgroup/misc.c
+++ b/kernel/cgroup/misc.c
@@ -24,6 +24,10 @@ static const char *const misc_res_name[] = {
 	/* AMD SEV-ES ASIDs resource */
 	"sev_es",
 #endif
+#ifdef CONFIG_INTEL_TDX_HOST
+	/* Intel TDX HKIDs resource */
+	"tdx",
+#endif
 };
 
 /* Root misc cgroup */
diff --git a/kernel/cgroup/rstat.c b/kernel/cgroup/rstat.c
index b2239156b7de..cbeaa499a96a 100644
--- a/kernel/cgroup/rstat.c
+++ b/kernel/cgroup/rstat.c
@@ -9,18 +9,64 @@
 
 #include <trace/events/cgroup.h>
 
-static DEFINE_SPINLOCK(cgroup_rstat_lock);
-static DEFINE_PER_CPU(raw_spinlock_t, cgroup_rstat_cpu_lock);
+static DEFINE_SPINLOCK(rstat_base_lock);
+static DEFINE_PER_CPU(raw_spinlock_t, rstat_base_cpu_lock);
 
 static void cgroup_base_stat_flush(struct cgroup *cgrp, int cpu);
 
-static struct cgroup_rstat_cpu *cgroup_rstat_cpu(struct cgroup *cgrp, int cpu)
+/*
+ * Determines whether a given css can participate in rstat.
+ * css's that are cgroup::self use rstat for base stats.
+ * Other css's associated with a subsystem use rstat only when
+ * they define the ss->css_rstat_flush callback.
+ */
+static inline bool css_uses_rstat(struct cgroup_subsys_state *css)
+{
+	return css_is_self(css) || css->ss->css_rstat_flush != NULL;
+}
+
+static struct css_rstat_cpu *css_rstat_cpu(
+		struct cgroup_subsys_state *css, int cpu)
+{
+	return per_cpu_ptr(css->rstat_cpu, cpu);
+}
+
+static struct cgroup_rstat_base_cpu *cgroup_rstat_base_cpu(
+		struct cgroup *cgrp, int cpu)
 {
-	return per_cpu_ptr(cgrp->rstat_cpu, cpu);
+	return per_cpu_ptr(cgrp->rstat_base_cpu, cpu);
+}
+
+static spinlock_t *ss_rstat_lock(struct cgroup_subsys *ss)
+{
+	if (ss)
+		return &ss->rstat_ss_lock;
+
+	return &rstat_base_lock;
+}
+
+static raw_spinlock_t *ss_rstat_cpu_lock(struct cgroup_subsys *ss, int cpu)
+{
+	if (ss) {
+		/*
+		 * Depending on config, the subsystem per-cpu lock type may be an
+		 * empty struct. In enviromnents where this is the case, allocation
+		 * of this field is not performed in ss_rstat_init(). Avoid a
+		 * cpu-based offset relative to NULL by returning early. When the
+		 * lock type is zero in size, the corresponding lock functions are
+		 * no-ops so passing them NULL is acceptable.
+		 */
+		if (sizeof(*ss->rstat_ss_cpu_lock) == 0)
+			return NULL;
+
+		return per_cpu_ptr(ss->rstat_ss_cpu_lock, cpu);
+	}
+
+	return per_cpu_ptr(&rstat_base_cpu_lock, cpu);
 }
 
 /*
- * Helper functions for rstat per CPU lock (cgroup_rstat_cpu_lock).
+ * Helper functions for rstat per CPU locks.
  *
  * This makes it easier to diagnose locking issues and contention in
  * production environments. The parameter @fast_path determine the
@@ -28,20 +74,23 @@ static struct cgroup_rstat_cpu *cgroup_rstat_cpu(struct cgroup *cgrp, int cpu)
  * operations without handling high-frequency fast-path "update" events.
  */
 static __always_inline
-unsigned long _cgroup_rstat_cpu_lock(raw_spinlock_t *cpu_lock, int cpu,
-				     struct cgroup *cgrp, const bool fast_path)
+unsigned long _css_rstat_cpu_lock(struct cgroup_subsys_state *css, int cpu,
+		const bool fast_path)
 {
+	struct cgroup *cgrp = css->cgroup;
+	raw_spinlock_t *cpu_lock;
 	unsigned long flags;
 	bool contended;
 
 	/*
-	 * The _irqsave() is needed because cgroup_rstat_lock is
-	 * spinlock_t which is a sleeping lock on PREEMPT_RT. Acquiring
-	 * this lock with the _irq() suffix only disables interrupts on
-	 * a non-PREEMPT_RT kernel. The raw_spinlock_t below disables
-	 * interrupts on both configurations. The _irqsave() ensures
-	 * that interrupts are always disabled and later restored.
+	 * The _irqsave() is needed because the locks used for flushing are
+	 * spinlock_t which is a sleeping lock on PREEMPT_RT. Acquiring this lock
+	 * with the _irq() suffix only disables interrupts on a non-PREEMPT_RT
+	 * kernel. The raw_spinlock_t below disables interrupts on both
+	 * configurations. The _irqsave() ensures that interrupts are always
+	 * disabled and later restored.
 	 */
+	cpu_lock = ss_rstat_cpu_lock(css->ss, cpu);
 	contended = !raw_spin_trylock_irqsave(cpu_lock, flags);
 	if (contended) {
 		if (fast_path)
@@ -61,50 +110,59 @@ unsigned long _cgroup_rstat_cpu_lock(raw_spinlock_t *cpu_lock, int cpu,
 }
 
 static __always_inline
-void _cgroup_rstat_cpu_unlock(raw_spinlock_t *cpu_lock, int cpu,
-			      struct cgroup *cgrp, unsigned long flags,
-			      const bool fast_path)
+void _css_rstat_cpu_unlock(struct cgroup_subsys_state *css, int cpu,
+		unsigned long flags, const bool fast_path)
 {
+	struct cgroup *cgrp = css->cgroup;
+	raw_spinlock_t *cpu_lock;
+
 	if (fast_path)
 		trace_cgroup_rstat_cpu_unlock_fastpath(cgrp, cpu, false);
 	else
 		trace_cgroup_rstat_cpu_unlock(cgrp, cpu, false);
 
+	cpu_lock = ss_rstat_cpu_lock(css->ss, cpu);
 	raw_spin_unlock_irqrestore(cpu_lock, flags);
 }
 
 /**
- * cgroup_rstat_updated - keep track of updated rstat_cpu
- * @cgrp: target cgroup
+ * css_rstat_updated - keep track of updated rstat_cpu
+ * @css: target cgroup subsystem state
  * @cpu: cpu on which rstat_cpu was updated
  *
- * @cgrp's rstat_cpu on @cpu was updated.  Put it on the parent's matching
- * rstat_cpu->updated_children list.  See the comment on top of
- * cgroup_rstat_cpu definition for details.
+ * @css's rstat_cpu on @cpu was updated. Put it on the parent's matching
+ * rstat_cpu->updated_children list. See the comment on top of
+ * css_rstat_cpu definition for details.
  */
-__bpf_kfunc void cgroup_rstat_updated(struct cgroup *cgrp, int cpu)
+__bpf_kfunc void css_rstat_updated(struct cgroup_subsys_state *css, int cpu)
 {
-	raw_spinlock_t *cpu_lock = per_cpu_ptr(&cgroup_rstat_cpu_lock, cpu);
 	unsigned long flags;
 
 	/*
+	 * Since bpf programs can call this function, prevent access to
+	 * uninitialized rstat pointers.
+	 */
+	if (!css_uses_rstat(css))
+		return;
+
+	/*
 	 * Speculative already-on-list test. This may race leading to
 	 * temporary inaccuracies, which is fine.
 	 *
 	 * Because @parent's updated_children is terminated with @parent
-	 * instead of NULL, we can tell whether @cgrp is on the list by
+	 * instead of NULL, we can tell whether @css is on the list by
 	 * testing the next pointer for NULL.
 	 */
-	if (data_race(cgroup_rstat_cpu(cgrp, cpu)->updated_next))
+	if (data_race(css_rstat_cpu(css, cpu)->updated_next))
 		return;
 
-	flags = _cgroup_rstat_cpu_lock(cpu_lock, cpu, cgrp, true);
+	flags = _css_rstat_cpu_lock(css, cpu, true);
 
-	/* put @cgrp and all ancestors on the corresponding updated lists */
+	/* put @css and all ancestors on the corresponding updated lists */
 	while (true) {
-		struct cgroup_rstat_cpu *rstatc = cgroup_rstat_cpu(cgrp, cpu);
-		struct cgroup *parent = cgroup_parent(cgrp);
-		struct cgroup_rstat_cpu *prstatc;
+		struct css_rstat_cpu *rstatc = css_rstat_cpu(css, cpu);
+		struct cgroup_subsys_state *parent = css->parent;
+		struct css_rstat_cpu *prstatc;
 
 		/*
 		 * Both additions and removals are bottom-up.  If a cgroup
@@ -115,53 +173,78 @@ __bpf_kfunc void cgroup_rstat_updated(struct cgroup *cgrp, int cpu)
 
 		/* Root has no parent to link it to, but mark it busy */
 		if (!parent) {
-			rstatc->updated_next = cgrp;
+			rstatc->updated_next = css;
 			break;
 		}
 
-		prstatc = cgroup_rstat_cpu(parent, cpu);
+		prstatc = css_rstat_cpu(parent, cpu);
 		rstatc->updated_next = prstatc->updated_children;
-		prstatc->updated_children = cgrp;
+		prstatc->updated_children = css;
 
-		cgrp = parent;
+		css = parent;
 	}
 
-	_cgroup_rstat_cpu_unlock(cpu_lock, cpu, cgrp, flags, true);
+	_css_rstat_cpu_unlock(css, cpu, flags, true);
 }
 
 /**
- * cgroup_rstat_push_children - push children cgroups into the given list
+ * css_rstat_push_children - push children css's into the given list
  * @head: current head of the list (= subtree root)
  * @child: first child of the root
  * @cpu: target cpu
- * Return: A new singly linked list of cgroups to be flush
+ * Return: A new singly linked list of css's to be flushed
  *
- * Iteratively traverse down the cgroup_rstat_cpu updated tree level by
+ * Iteratively traverse down the css_rstat_cpu updated tree level by
  * level and push all the parents first before their next level children
- * into a singly linked list built from the tail backward like "pushing"
- * cgroups into a stack. The root is pushed by the caller.
+ * into a singly linked list via the rstat_flush_next pointer built from the
+ * tail backward like "pushing" css's into a stack. The root is pushed by
+ * the caller.
  */
-static struct cgroup *cgroup_rstat_push_children(struct cgroup *head,
-						 struct cgroup *child, int cpu)
+static struct cgroup_subsys_state *css_rstat_push_children(
+		struct cgroup_subsys_state *head,
+		struct cgroup_subsys_state *child, int cpu)
 {
-	struct cgroup *chead = child;	/* Head of child cgroup level */
-	struct cgroup *ghead = NULL;	/* Head of grandchild cgroup level */
-	struct cgroup *parent, *grandchild;
-	struct cgroup_rstat_cpu *crstatc;
+	struct cgroup_subsys_state *cnext = child;	/* Next head of child css level */
+	struct cgroup_subsys_state *ghead = NULL;	/* Head of grandchild css level */
+	struct cgroup_subsys_state *parent, *grandchild;
+	struct css_rstat_cpu *crstatc;
 
 	child->rstat_flush_next = NULL;
 
+	/*
+	 * The subsystem rstat lock must be held for the whole duration from
+	 * here as the rstat_flush_next list is being constructed to when
+	 * it is consumed later in css_rstat_flush().
+	 */
+	lockdep_assert_held(ss_rstat_lock(head->ss));
+
+	/*
+	 * Notation: -> updated_next pointer
+	 *	     => rstat_flush_next pointer
+	 *
+	 * Assuming the following sample updated_children lists:
+	 *  P: C1 -> C2 -> P
+	 *  C1: G11 -> G12 -> C1
+	 *  C2: G21 -> G22 -> C2
+	 *
+	 * After 1st iteration:
+	 *  head => C2 => C1 => NULL
+	 *  ghead => G21 => G11 => NULL
+	 *
+	 * After 2nd iteration:
+	 *  head => G12 => G11 => G22 => G21 => C2 => C1 => NULL
+	 */
 next_level:
-	while (chead) {
-		child = chead;
-		chead = child->rstat_flush_next;
-		parent = cgroup_parent(child);
+	while (cnext) {
+		child = cnext;
+		cnext = child->rstat_flush_next;
+		parent = child->parent;
 
-		/* updated_next is parent cgroup terminated */
+		/* updated_next is parent cgroup terminated if !NULL */
 		while (child != parent) {
 			child->rstat_flush_next = head;
 			head = child;
-			crstatc = cgroup_rstat_cpu(child, cpu);
+			crstatc = css_rstat_cpu(child, cpu);
 			grandchild = crstatc->updated_children;
 			if (grandchild != child) {
 				/* Push the grand child to the next level */
@@ -175,7 +258,7 @@ next_level:
 	}
 
 	if (ghead) {
-		chead = ghead;
+		cnext = ghead;
 		ghead = NULL;
 		goto next_level;
 	}
@@ -183,31 +266,31 @@ next_level:
 }
 
 /**
- * cgroup_rstat_updated_list - return a list of updated cgroups to be flushed
- * @root: root of the cgroup subtree to traverse
+ * css_rstat_updated_list - build a list of updated css's to be flushed
+ * @root: root of the css subtree to traverse
  * @cpu: target cpu
- * Return: A singly linked list of cgroups to be flushed
+ * Return: A singly linked list of css's to be flushed
  *
  * Walks the updated rstat_cpu tree on @cpu from @root.  During traversal,
- * each returned cgroup is unlinked from the updated tree.
+ * each returned css is unlinked from the updated tree.
  *
  * The only ordering guarantee is that, for a parent and a child pair
  * covered by a given traversal, the child is before its parent in
  * the list.
  *
  * Note that updated_children is self terminated and points to a list of
- * child cgroups if not empty. Whereas updated_next is like a sibling link
- * within the children list and terminated by the parent cgroup. An exception
- * here is the cgroup root whose updated_next can be self terminated.
+ * child css's if not empty. Whereas updated_next is like a sibling link
+ * within the children list and terminated by the parent css. An exception
+ * here is the css root whose updated_next can be self terminated.
  */
-static struct cgroup *cgroup_rstat_updated_list(struct cgroup *root, int cpu)
+static struct cgroup_subsys_state *css_rstat_updated_list(
+		struct cgroup_subsys_state *root, int cpu)
 {
-	raw_spinlock_t *cpu_lock = per_cpu_ptr(&cgroup_rstat_cpu_lock, cpu);
-	struct cgroup_rstat_cpu *rstatc = cgroup_rstat_cpu(root, cpu);
-	struct cgroup *head = NULL, *parent, *child;
+	struct css_rstat_cpu *rstatc = css_rstat_cpu(root, cpu);
+	struct cgroup_subsys_state *head = NULL, *parent, *child;
 	unsigned long flags;
 
-	flags = _cgroup_rstat_cpu_lock(cpu_lock, cpu, root, false);
+	flags = _css_rstat_cpu_lock(root, cpu, false);
 
 	/* Return NULL if this subtree is not on-list */
 	if (!rstatc->updated_next)
@@ -217,17 +300,17 @@ static struct cgroup *cgroup_rstat_updated_list(struct cgroup *root, int cpu)
 	 * Unlink @root from its parent. As the updated_children list is
 	 * singly linked, we have to walk it to find the removal point.
 	 */
-	parent = cgroup_parent(root);
+	parent = root->parent;
 	if (parent) {
-		struct cgroup_rstat_cpu *prstatc;
-		struct cgroup **nextp;
+		struct css_rstat_cpu *prstatc;
+		struct cgroup_subsys_state **nextp;
 
-		prstatc = cgroup_rstat_cpu(parent, cpu);
+		prstatc = css_rstat_cpu(parent, cpu);
 		nextp = &prstatc->updated_children;
 		while (*nextp != root) {
-			struct cgroup_rstat_cpu *nrstatc;
+			struct css_rstat_cpu *nrstatc;
 
-			nrstatc = cgroup_rstat_cpu(*nextp, cpu);
+			nrstatc = css_rstat_cpu(*nextp, cpu);
 			WARN_ON_ONCE(*nextp == parent);
 			nextp = &nrstatc->updated_next;
 		}
@@ -242,16 +325,16 @@ static struct cgroup *cgroup_rstat_updated_list(struct cgroup *root, int cpu)
 	child = rstatc->updated_children;
 	rstatc->updated_children = root;
 	if (child != root)
-		head = cgroup_rstat_push_children(head, child, cpu);
+		head = css_rstat_push_children(head, child, cpu);
 unlock_ret:
-	_cgroup_rstat_cpu_unlock(cpu_lock, cpu, root, flags, false);
+	_css_rstat_cpu_unlock(root, cpu, flags, false);
 	return head;
 }
 
 /*
  * A hook for bpf stat collectors to attach to and flush their stats.
- * Together with providing bpf kfuncs for cgroup_rstat_updated() and
- * cgroup_rstat_flush(), this enables a complete workflow where bpf progs that
+ * Together with providing bpf kfuncs for css_rstat_updated() and
+ * css_rstat_flush(), this enables a complete workflow where bpf progs that
  * collect cgroup stats can integrate with rstat for efficient flushing.
  *
  * A static noinline declaration here could cause the compiler to optimize away
@@ -271,7 +354,7 @@ __weak noinline void bpf_rstat_flush(struct cgroup *cgrp,
 __bpf_hook_end();
 
 /*
- * Helper functions for locking cgroup_rstat_lock.
+ * Helper functions for locking.
  *
  * This makes it easier to diagnose locking issues and contention in
  * production environments.  The parameter @cpu_in_loop indicate lock
@@ -279,115 +362,181 @@ __bpf_hook_end();
  * value -1 is used when obtaining the main lock else this is the CPU
  * number processed last.
  */
-static inline void __cgroup_rstat_lock(struct cgroup *cgrp, int cpu_in_loop)
-	__acquires(&cgroup_rstat_lock)
+static inline void __css_rstat_lock(struct cgroup_subsys_state *css,
+		int cpu_in_loop)
+	__acquires(ss_rstat_lock(css->ss))
 {
+	struct cgroup *cgrp = css->cgroup;
+	spinlock_t *lock;
 	bool contended;
 
-	contended = !spin_trylock_irq(&cgroup_rstat_lock);
+	lock = ss_rstat_lock(css->ss);
+	contended = !spin_trylock_irq(lock);
 	if (contended) {
 		trace_cgroup_rstat_lock_contended(cgrp, cpu_in_loop, contended);
-		spin_lock_irq(&cgroup_rstat_lock);
+		spin_lock_irq(lock);
 	}
 	trace_cgroup_rstat_locked(cgrp, cpu_in_loop, contended);
 }
 
-static inline void __cgroup_rstat_unlock(struct cgroup *cgrp, int cpu_in_loop)
-	__releases(&cgroup_rstat_lock)
+static inline void __css_rstat_unlock(struct cgroup_subsys_state *css,
+				      int cpu_in_loop)
+	__releases(ss_rstat_lock(css->ss))
 {
+	struct cgroup *cgrp = css->cgroup;
+	spinlock_t *lock;
+
+	lock = ss_rstat_lock(css->ss);
 	trace_cgroup_rstat_unlock(cgrp, cpu_in_loop, false);
-	spin_unlock_irq(&cgroup_rstat_lock);
+	spin_unlock_irq(lock);
 }
 
 /**
- * cgroup_rstat_flush - flush stats in @cgrp's subtree
- * @cgrp: target cgroup
+ * css_rstat_flush - flush stats in @css's rstat subtree
+ * @css: target cgroup subsystem state
  *
- * Collect all per-cpu stats in @cgrp's subtree into the global counters
- * and propagate them upwards.  After this function returns, all cgroups in
- * the subtree have up-to-date ->stat.
+ * Collect all per-cpu stats in @css's subtree into the global counters
+ * and propagate them upwards. After this function returns, all rstat
+ * nodes in the subtree have up-to-date ->stat.
  *
- * This also gets all cgroups in the subtree including @cgrp off the
+ * This also gets all rstat nodes in the subtree including @css off the
  * ->updated_children lists.
  *
  * This function may block.
  */
-__bpf_kfunc void cgroup_rstat_flush(struct cgroup *cgrp)
+__bpf_kfunc void css_rstat_flush(struct cgroup_subsys_state *css)
 {
 	int cpu;
+	bool is_self = css_is_self(css);
+
+	/*
+	 * Since bpf programs can call this function, prevent access to
+	 * uninitialized rstat pointers.
+	 */
+	if (!css_uses_rstat(css))
+		return;
 
 	might_sleep();
 	for_each_possible_cpu(cpu) {
-		struct cgroup *pos;
+		struct cgroup_subsys_state *pos;
 
 		/* Reacquire for each CPU to avoid disabling IRQs too long */
-		__cgroup_rstat_lock(cgrp, cpu);
-		pos = cgroup_rstat_updated_list(cgrp, cpu);
+		__css_rstat_lock(css, cpu);
+		pos = css_rstat_updated_list(css, cpu);
 		for (; pos; pos = pos->rstat_flush_next) {
-			struct cgroup_subsys_state *css;
-
-			cgroup_base_stat_flush(pos, cpu);
-			bpf_rstat_flush(pos, cgroup_parent(pos), cpu);
-
-			rcu_read_lock();
-			list_for_each_entry_rcu(css, &pos->rstat_css_list,
-						rstat_css_node)
-				css->ss->css_rstat_flush(css, cpu);
-			rcu_read_unlock();
+			if (is_self) {
+				cgroup_base_stat_flush(pos->cgroup, cpu);
+				bpf_rstat_flush(pos->cgroup,
+						cgroup_parent(pos->cgroup), cpu);
+			} else
+				pos->ss->css_rstat_flush(pos, cpu);
 		}
-		__cgroup_rstat_unlock(cgrp, cpu);
+		__css_rstat_unlock(css, cpu);
 		if (!cond_resched())
 			cpu_relax();
 	}
 }
 
-int cgroup_rstat_init(struct cgroup *cgrp)
+int css_rstat_init(struct cgroup_subsys_state *css)
 {
+	struct cgroup *cgrp = css->cgroup;
 	int cpu;
+	bool is_self = css_is_self(css);
+
+	if (is_self) {
+		/* the root cgrp has rstat_base_cpu preallocated */
+		if (!cgrp->rstat_base_cpu) {
+			cgrp->rstat_base_cpu = alloc_percpu(struct cgroup_rstat_base_cpu);
+			if (!cgrp->rstat_base_cpu)
+				return -ENOMEM;
+		}
+	} else if (css->ss->css_rstat_flush == NULL)
+		return 0;
+
+	/* the root cgrp's self css has rstat_cpu preallocated */
+	if (!css->rstat_cpu) {
+		css->rstat_cpu = alloc_percpu(struct css_rstat_cpu);
+		if (!css->rstat_cpu) {
+			if (is_self)
+				free_percpu(cgrp->rstat_base_cpu);
 
-	/* the root cgrp has rstat_cpu preallocated */
-	if (!cgrp->rstat_cpu) {
-		cgrp->rstat_cpu = alloc_percpu(struct cgroup_rstat_cpu);
-		if (!cgrp->rstat_cpu)
 			return -ENOMEM;
+		}
 	}
 
 	/* ->updated_children list is self terminated */
 	for_each_possible_cpu(cpu) {
-		struct cgroup_rstat_cpu *rstatc = cgroup_rstat_cpu(cgrp, cpu);
+		struct css_rstat_cpu *rstatc = css_rstat_cpu(css, cpu);
 
-		rstatc->updated_children = cgrp;
-		u64_stats_init(&rstatc->bsync);
+		rstatc->updated_children = css;
+
+		if (is_self) {
+			struct cgroup_rstat_base_cpu *rstatbc;
+
+			rstatbc = cgroup_rstat_base_cpu(cgrp, cpu);
+			u64_stats_init(&rstatbc->bsync);
+		}
 	}
 
 	return 0;
 }
 
-void cgroup_rstat_exit(struct cgroup *cgrp)
+void css_rstat_exit(struct cgroup_subsys_state *css)
 {
 	int cpu;
 
-	cgroup_rstat_flush(cgrp);
+	if (!css_uses_rstat(css))
+		return;
+
+	css_rstat_flush(css);
 
 	/* sanity check */
 	for_each_possible_cpu(cpu) {
-		struct cgroup_rstat_cpu *rstatc = cgroup_rstat_cpu(cgrp, cpu);
+		struct css_rstat_cpu *rstatc = css_rstat_cpu(css, cpu);
 
-		if (WARN_ON_ONCE(rstatc->updated_children != cgrp) ||
+		if (WARN_ON_ONCE(rstatc->updated_children != css) ||
 		    WARN_ON_ONCE(rstatc->updated_next))
 			return;
 	}
 
-	free_percpu(cgrp->rstat_cpu);
-	cgrp->rstat_cpu = NULL;
+	if (css_is_self(css)) {
+		struct cgroup *cgrp = css->cgroup;
+
+		free_percpu(cgrp->rstat_base_cpu);
+		cgrp->rstat_base_cpu = NULL;
+	}
+
+	free_percpu(css->rstat_cpu);
+	css->rstat_cpu = NULL;
 }
 
-void __init cgroup_rstat_boot(void)
+/**
+ * ss_rstat_init - subsystem-specific rstat initialization
+ * @ss: target subsystem
+ *
+ * If @ss is NULL, the static locks associated with the base stats
+ * are initialized. If @ss is non-NULL, the subsystem-specific locks
+ * are initialized.
+ */
+int __init ss_rstat_init(struct cgroup_subsys *ss)
 {
 	int cpu;
 
+	/*
+	 * Depending on config, the subsystem per-cpu lock type may be an empty
+	 * struct. Avoid allocating a size of zero in this case.
+	 */
+	if (ss && sizeof(*ss->rstat_ss_cpu_lock)) {
+		ss->rstat_ss_cpu_lock = alloc_percpu(raw_spinlock_t);
+		if (!ss->rstat_ss_cpu_lock)
+			return -ENOMEM;
+	}
+
+	spin_lock_init(ss_rstat_lock(ss));
 	for_each_possible_cpu(cpu)
-		raw_spin_lock_init(per_cpu_ptr(&cgroup_rstat_cpu_lock, cpu));
+		raw_spin_lock_init(ss_rstat_cpu_lock(ss, cpu));
+
+	return 0;
 }
 
 /*
@@ -420,9 +569,9 @@ static void cgroup_base_stat_sub(struct cgroup_base_stat *dst_bstat,
 
 static void cgroup_base_stat_flush(struct cgroup *cgrp, int cpu)
 {
-	struct cgroup_rstat_cpu *rstatc = cgroup_rstat_cpu(cgrp, cpu);
+	struct cgroup_rstat_base_cpu *rstatbc = cgroup_rstat_base_cpu(cgrp, cpu);
 	struct cgroup *parent = cgroup_parent(cgrp);
-	struct cgroup_rstat_cpu *prstatc;
+	struct cgroup_rstat_base_cpu *prstatbc;
 	struct cgroup_base_stat delta;
 	unsigned seq;
 
@@ -432,15 +581,15 @@ static void cgroup_base_stat_flush(struct cgroup *cgrp, int cpu)
 
 	/* fetch the current per-cpu values */
 	do {
-		seq = __u64_stats_fetch_begin(&rstatc->bsync);
-		delta = rstatc->bstat;
-	} while (__u64_stats_fetch_retry(&rstatc->bsync, seq));
+		seq = __u64_stats_fetch_begin(&rstatbc->bsync);
+		delta = rstatbc->bstat;
+	} while (__u64_stats_fetch_retry(&rstatbc->bsync, seq));
 
 	/* propagate per-cpu delta to cgroup and per-cpu global statistics */
-	cgroup_base_stat_sub(&delta, &rstatc->last_bstat);
+	cgroup_base_stat_sub(&delta, &rstatbc->last_bstat);
 	cgroup_base_stat_add(&cgrp->bstat, &delta);
-	cgroup_base_stat_add(&rstatc->last_bstat, &delta);
-	cgroup_base_stat_add(&rstatc->subtree_bstat, &delta);
+	cgroup_base_stat_add(&rstatbc->last_bstat, &delta);
+	cgroup_base_stat_add(&rstatbc->subtree_bstat, &delta);
 
 	/* propagate cgroup and per-cpu global delta to parent (unless that's root) */
 	if (cgroup_parent(parent)) {
@@ -449,73 +598,73 @@ static void cgroup_base_stat_flush(struct cgroup *cgrp, int cpu)
 		cgroup_base_stat_add(&parent->bstat, &delta);
 		cgroup_base_stat_add(&cgrp->last_bstat, &delta);
 
-		delta = rstatc->subtree_bstat;
-		prstatc = cgroup_rstat_cpu(parent, cpu);
-		cgroup_base_stat_sub(&delta, &rstatc->last_subtree_bstat);
-		cgroup_base_stat_add(&prstatc->subtree_bstat, &delta);
-		cgroup_base_stat_add(&rstatc->last_subtree_bstat, &delta);
+		delta = rstatbc->subtree_bstat;
+		prstatbc = cgroup_rstat_base_cpu(parent, cpu);
+		cgroup_base_stat_sub(&delta, &rstatbc->last_subtree_bstat);
+		cgroup_base_stat_add(&prstatbc->subtree_bstat, &delta);
+		cgroup_base_stat_add(&rstatbc->last_subtree_bstat, &delta);
 	}
 }
 
-static struct cgroup_rstat_cpu *
+static struct cgroup_rstat_base_cpu *
 cgroup_base_stat_cputime_account_begin(struct cgroup *cgrp, unsigned long *flags)
 {
-	struct cgroup_rstat_cpu *rstatc;
+	struct cgroup_rstat_base_cpu *rstatbc;
 
-	rstatc = get_cpu_ptr(cgrp->rstat_cpu);
-	*flags = u64_stats_update_begin_irqsave(&rstatc->bsync);
-	return rstatc;
+	rstatbc = get_cpu_ptr(cgrp->rstat_base_cpu);
+	*flags = u64_stats_update_begin_irqsave(&rstatbc->bsync);
+	return rstatbc;
 }
 
 static void cgroup_base_stat_cputime_account_end(struct cgroup *cgrp,
-						 struct cgroup_rstat_cpu *rstatc,
+						 struct cgroup_rstat_base_cpu *rstatbc,
 						 unsigned long flags)
 {
-	u64_stats_update_end_irqrestore(&rstatc->bsync, flags);
-	cgroup_rstat_updated(cgrp, smp_processor_id());
-	put_cpu_ptr(rstatc);
+	u64_stats_update_end_irqrestore(&rstatbc->bsync, flags);
+	css_rstat_updated(&cgrp->self, smp_processor_id());
+	put_cpu_ptr(rstatbc);
 }
 
 void __cgroup_account_cputime(struct cgroup *cgrp, u64 delta_exec)
 {
-	struct cgroup_rstat_cpu *rstatc;
+	struct cgroup_rstat_base_cpu *rstatbc;
 	unsigned long flags;
 
-	rstatc = cgroup_base_stat_cputime_account_begin(cgrp, &flags);
-	rstatc->bstat.cputime.sum_exec_runtime += delta_exec;
-	cgroup_base_stat_cputime_account_end(cgrp, rstatc, flags);
+	rstatbc = cgroup_base_stat_cputime_account_begin(cgrp, &flags);
+	rstatbc->bstat.cputime.sum_exec_runtime += delta_exec;
+	cgroup_base_stat_cputime_account_end(cgrp, rstatbc, flags);
 }
 
 void __cgroup_account_cputime_field(struct cgroup *cgrp,
 				    enum cpu_usage_stat index, u64 delta_exec)
 {
-	struct cgroup_rstat_cpu *rstatc;
+	struct cgroup_rstat_base_cpu *rstatbc;
 	unsigned long flags;
 
-	rstatc = cgroup_base_stat_cputime_account_begin(cgrp, &flags);
+	rstatbc = cgroup_base_stat_cputime_account_begin(cgrp, &flags);
 
 	switch (index) {
 	case CPUTIME_NICE:
-		rstatc->bstat.ntime += delta_exec;
+		rstatbc->bstat.ntime += delta_exec;
 		fallthrough;
 	case CPUTIME_USER:
-		rstatc->bstat.cputime.utime += delta_exec;
+		rstatbc->bstat.cputime.utime += delta_exec;
 		break;
 	case CPUTIME_SYSTEM:
 	case CPUTIME_IRQ:
 	case CPUTIME_SOFTIRQ:
-		rstatc->bstat.cputime.stime += delta_exec;
+		rstatbc->bstat.cputime.stime += delta_exec;
 		break;
 #ifdef CONFIG_SCHED_CORE
 	case CPUTIME_FORCEIDLE:
-		rstatc->bstat.forceidle_sum += delta_exec;
+		rstatbc->bstat.forceidle_sum += delta_exec;
 		break;
 #endif
 	default:
 		break;
 	}
 
-	cgroup_base_stat_cputime_account_end(cgrp, rstatc, flags);
+	cgroup_base_stat_cputime_account_end(cgrp, rstatbc, flags);
 }
 
 /*
@@ -574,12 +723,12 @@ void cgroup_base_stat_cputime_show(struct seq_file *seq)
 	struct cgroup_base_stat bstat;
 
 	if (cgroup_parent(cgrp)) {
-		cgroup_rstat_flush(cgrp);
-		__cgroup_rstat_lock(cgrp, -1);
+		css_rstat_flush(&cgrp->self);
+		__css_rstat_lock(&cgrp->self, -1);
 		bstat = cgrp->bstat;
 		cputime_adjust(&cgrp->bstat.cputime, &cgrp->prev_cputime,
 			       &bstat.cputime.utime, &bstat.cputime.stime);
-		__cgroup_rstat_unlock(cgrp, -1);
+		__css_rstat_unlock(&cgrp->self, -1);
 	} else {
 		root_cgroup_cputime(&bstat);
 	}
@@ -601,10 +750,10 @@ void cgroup_base_stat_cputime_show(struct seq_file *seq)
 	cgroup_force_idle_show(seq, &bstat);
 }
 
-/* Add bpf kfuncs for cgroup_rstat_updated() and cgroup_rstat_flush() */
+/* Add bpf kfuncs for css_rstat_updated() and css_rstat_flush() */
 BTF_KFUNCS_START(bpf_rstat_kfunc_ids)
-BTF_ID_FLAGS(func, cgroup_rstat_updated)
-BTF_ID_FLAGS(func, cgroup_rstat_flush, KF_SLEEPABLE)
+BTF_ID_FLAGS(func, css_rstat_updated)
+BTF_ID_FLAGS(func, css_rstat_flush, KF_SLEEPABLE)
 BTF_KFUNCS_END(bpf_rstat_kfunc_ids)
 
 static const struct btf_kfunc_id_set bpf_rstat_kfunc_set = {
diff --git a/kernel/configs/debug.config b/kernel/configs/debug.config
index 8aafd050b754..e81327d2cd63 100644
--- a/kernel/configs/debug.config
+++ b/kernel/configs/debug.config
@@ -112,3 +112,8 @@ CONFIG_BRANCH_PROFILE_NONE=y
 CONFIG_DYNAMIC_FTRACE=y
 CONFIG_FTRACE=y
 CONFIG_FUNCTION_TRACER=y
+#
+# Preemption
+#
+CONFIG_DEBUG_PREEMPT=y
+CONFIG_PREEMPT=y
diff --git a/kernel/configs/tiny.config b/kernel/configs/tiny.config
index b753695c5a8f..5dd0f0a34a73 100644
--- a/kernel/configs/tiny.config
+++ b/kernel/configs/tiny.config
@@ -2,3 +2,4 @@ CONFIG_CC_OPTIMIZE_FOR_SIZE=y
 CONFIG_KERNEL_XZ=y
 CONFIG_SLUB=y
 CONFIG_SLUB_TINY=y
+CONFIG_LD_DEAD_CODE_DATA_ELIMINATION=y
diff --git a/kernel/configs/xen.config b/kernel/configs/xen.config
index 6878b9a49be8..1875a0a5047a 100644
--- a/kernel/configs/xen.config
+++ b/kernel/configs/xen.config
@@ -13,6 +13,8 @@ CONFIG_SCSI=y
 CONFIG_FB=y
 CONFIG_INPUT_MISC=y
 CONFIG_MEMORY_HOTPLUG=y
+CONFIG_MEMORY_HOTREMOVE=y
+CONFIG_ZONE_DEVICE=y
 CONFIG_TTY=y
 # Technically not required but otherwise produces
 # pretty useless systems starting from allnoconfig
@@ -47,3 +49,4 @@ CONFIG_XEN_GNTDEV=m
 CONFIG_XEN_GRANT_DEV_ALLOC=m
 CONFIG_SWIOTLB_XEN=y
 CONFIG_XEN_PRIVCMD=m
+CONFIG_XEN_UNPOPULATED_ALLOC=y
diff --git a/kernel/cpu.c b/kernel/cpu.c
index b08bb34b1718..a59e009e0be4 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -2069,11 +2069,6 @@ static struct cpuhp_step cpuhp_hp_states[] = {
 		.teardown.single	= NULL,
 		.cant_stop		= true,
 	},
-	[CPUHP_PERF_PREPARE] = {
-		.name			= "perf:prepare",
-		.startup.single		= perf_event_init_cpu,
-		.teardown.single	= perf_event_exit_cpu,
-	},
 	[CPUHP_RANDOM_PREPARE] = {
 		.name			= "random:prepare",
 		.startup.single		= random_prepare_cpu,
diff --git a/kernel/crash_dump_dm_crypt.c b/kernel/crash_dump_dm_crypt.c
new file mode 100644
index 000000000000..401423ba477d
--- /dev/null
+++ b/kernel/crash_dump_dm_crypt.c
@@ -0,0 +1,464 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include <linux/key.h>
+#include <linux/keyctl.h>
+#include <keys/user-type.h>
+#include <linux/crash_dump.h>
+#include <linux/cc_platform.h>
+#include <linux/configfs.h>
+#include <linux/module.h>
+
+#define KEY_NUM_MAX 128	/* maximum dm crypt keys */
+#define KEY_SIZE_MAX 256	/* maximum dm crypt key size */
+#define KEY_DESC_MAX_LEN 128	/* maximum dm crypt key description size */
+
+static unsigned int key_count;
+
+struct dm_crypt_key {
+	unsigned int key_size;
+	char key_desc[KEY_DESC_MAX_LEN];
+	u8 data[KEY_SIZE_MAX];
+};
+
+static struct keys_header {
+	unsigned int total_keys;
+	struct dm_crypt_key keys[] __counted_by(total_keys);
+} *keys_header;
+
+static size_t get_keys_header_size(size_t total_keys)
+{
+	return struct_size(keys_header, keys, total_keys);
+}
+
+unsigned long long dm_crypt_keys_addr;
+EXPORT_SYMBOL_GPL(dm_crypt_keys_addr);
+
+static int __init setup_dmcryptkeys(char *arg)
+{
+	char *end;
+
+	if (!arg)
+		return -EINVAL;
+	dm_crypt_keys_addr = memparse(arg, &end);
+	if (end > arg)
+		return 0;
+
+	dm_crypt_keys_addr = 0;
+	return -EINVAL;
+}
+
+early_param("dmcryptkeys", setup_dmcryptkeys);
+
+/*
+ * Architectures may override this function to read dm crypt keys
+ */
+ssize_t __weak dm_crypt_keys_read(char *buf, size_t count, u64 *ppos)
+{
+	struct kvec kvec = { .iov_base = buf, .iov_len = count };
+	struct iov_iter iter;
+
+	iov_iter_kvec(&iter, READ, &kvec, 1, count);
+	return read_from_oldmem(&iter, count, ppos, cc_platform_has(CC_ATTR_MEM_ENCRYPT));
+}
+
+static int add_key_to_keyring(struct dm_crypt_key *dm_key,
+			      key_ref_t keyring_ref)
+{
+	key_ref_t key_ref;
+	int r;
+
+	/* create or update the requested key and add it to the target keyring */
+	key_ref = key_create_or_update(keyring_ref, "user", dm_key->key_desc,
+				       dm_key->data, dm_key->key_size,
+				       KEY_USR_ALL, KEY_ALLOC_IN_QUOTA);
+
+	if (!IS_ERR(key_ref)) {
+		r = key_ref_to_ptr(key_ref)->serial;
+		key_ref_put(key_ref);
+		kexec_dprintk("Success adding key %s", dm_key->key_desc);
+	} else {
+		r = PTR_ERR(key_ref);
+		kexec_dprintk("Error when adding key");
+	}
+
+	key_ref_put(keyring_ref);
+	return r;
+}
+
+static void get_keys_from_kdump_reserved_memory(void)
+{
+	struct keys_header *keys_header_loaded;
+
+	arch_kexec_unprotect_crashkres();
+
+	keys_header_loaded = kmap_local_page(pfn_to_page(
+		kexec_crash_image->dm_crypt_keys_addr >> PAGE_SHIFT));
+
+	memcpy(keys_header, keys_header_loaded, get_keys_header_size(key_count));
+	kunmap_local(keys_header_loaded);
+	arch_kexec_protect_crashkres();
+}
+
+static int restore_dm_crypt_keys_to_thread_keyring(void)
+{
+	struct dm_crypt_key *key;
+	size_t keys_header_size;
+	key_ref_t keyring_ref;
+	u64 addr;
+
+	/* find the target keyring (which must be writable) */
+	keyring_ref =
+		lookup_user_key(KEY_SPEC_USER_KEYRING, 0x01, KEY_NEED_WRITE);
+	if (IS_ERR(keyring_ref)) {
+		kexec_dprintk("Failed to get the user keyring\n");
+		return PTR_ERR(keyring_ref);
+	}
+
+	addr = dm_crypt_keys_addr;
+	dm_crypt_keys_read((char *)&key_count, sizeof(key_count), &addr);
+	if (key_count < 0 || key_count > KEY_NUM_MAX) {
+		kexec_dprintk("Failed to read the number of dm-crypt keys\n");
+		return -1;
+	}
+
+	kexec_dprintk("There are %u keys\n", key_count);
+	addr = dm_crypt_keys_addr;
+
+	keys_header_size = get_keys_header_size(key_count);
+	keys_header = kzalloc(keys_header_size, GFP_KERNEL);
+	if (!keys_header)
+		return -ENOMEM;
+
+	dm_crypt_keys_read((char *)keys_header, keys_header_size, &addr);
+
+	for (int i = 0; i < keys_header->total_keys; i++) {
+		key = &keys_header->keys[i];
+		kexec_dprintk("Get key (size=%u)\n", key->key_size);
+		add_key_to_keyring(key, keyring_ref);
+	}
+
+	return 0;
+}
+
+static int read_key_from_user_keying(struct dm_crypt_key *dm_key)
+{
+	const struct user_key_payload *ukp;
+	struct key *key;
+
+	kexec_dprintk("Requesting logon key %s", dm_key->key_desc);
+	key = request_key(&key_type_logon, dm_key->key_desc, NULL);
+
+	if (IS_ERR(key)) {
+		pr_warn("No such logon key %s\n", dm_key->key_desc);
+		return PTR_ERR(key);
+	}
+
+	ukp = user_key_payload_locked(key);
+	if (!ukp)
+		return -EKEYREVOKED;
+
+	if (ukp->datalen > KEY_SIZE_MAX) {
+		pr_err("Key size %u exceeds maximum (%u)\n", ukp->datalen, KEY_SIZE_MAX);
+		return -EINVAL;
+	}
+
+	memcpy(dm_key->data, ukp->data, ukp->datalen);
+	dm_key->key_size = ukp->datalen;
+	kexec_dprintk("Get dm crypt key (size=%u) %s: %8ph\n", dm_key->key_size,
+		      dm_key->key_desc, dm_key->data);
+	return 0;
+}
+
+struct config_key {
+	struct config_item item;
+	const char *description;
+};
+
+static inline struct config_key *to_config_key(struct config_item *item)
+{
+	return container_of(item, struct config_key, item);
+}
+
+static ssize_t config_key_description_show(struct config_item *item, char *page)
+{
+	return sprintf(page, "%s\n", to_config_key(item)->description);
+}
+
+static ssize_t config_key_description_store(struct config_item *item,
+					    const char *page, size_t count)
+{
+	struct config_key *config_key = to_config_key(item);
+	size_t len;
+	int ret;
+
+	ret = -EINVAL;
+	len = strcspn(page, "\n");
+
+	if (len > KEY_DESC_MAX_LEN) {
+		pr_err("The key description shouldn't exceed %u characters", KEY_DESC_MAX_LEN);
+		return ret;
+	}
+
+	if (!len)
+		return ret;
+
+	kfree(config_key->description);
+	ret = -ENOMEM;
+	config_key->description = kmemdup_nul(page, len, GFP_KERNEL);
+	if (!config_key->description)
+		return ret;
+
+	return count;
+}
+
+CONFIGFS_ATTR(config_key_, description);
+
+static struct configfs_attribute *config_key_attrs[] = {
+	&config_key_attr_description,
+	NULL,
+};
+
+static void config_key_release(struct config_item *item)
+{
+	kfree(to_config_key(item));
+	key_count--;
+}
+
+static struct configfs_item_operations config_key_item_ops = {
+	.release = config_key_release,
+};
+
+static const struct config_item_type config_key_type = {
+	.ct_item_ops = &config_key_item_ops,
+	.ct_attrs = config_key_attrs,
+	.ct_owner = THIS_MODULE,
+};
+
+static struct config_item *config_keys_make_item(struct config_group *group,
+						 const char *name)
+{
+	struct config_key *config_key;
+
+	if (key_count > KEY_NUM_MAX) {
+		pr_err("Only %u keys at maximum to be created\n", KEY_NUM_MAX);
+		return ERR_PTR(-EINVAL);
+	}
+
+	config_key = kzalloc(sizeof(struct config_key), GFP_KERNEL);
+	if (!config_key)
+		return ERR_PTR(-ENOMEM);
+
+	config_item_init_type_name(&config_key->item, name, &config_key_type);
+
+	key_count++;
+
+	return &config_key->item;
+}
+
+static ssize_t config_keys_count_show(struct config_item *item, char *page)
+{
+	return sprintf(page, "%d\n", key_count);
+}
+
+CONFIGFS_ATTR_RO(config_keys_, count);
+
+static bool is_dm_key_reused;
+
+static ssize_t config_keys_reuse_show(struct config_item *item, char *page)
+{
+	return sprintf(page, "%d\n", is_dm_key_reused);
+}
+
+static ssize_t config_keys_reuse_store(struct config_item *item,
+					   const char *page, size_t count)
+{
+	if (!kexec_crash_image || !kexec_crash_image->dm_crypt_keys_addr) {
+		kexec_dprintk(
+			"dm-crypt keys haven't be saved to crash-reserved memory\n");
+		return -EINVAL;
+	}
+
+	if (kstrtobool(page, &is_dm_key_reused))
+		return -EINVAL;
+
+	if (is_dm_key_reused)
+		get_keys_from_kdump_reserved_memory();
+
+	return count;
+}
+
+CONFIGFS_ATTR(config_keys_, reuse);
+
+static struct configfs_attribute *config_keys_attrs[] = {
+	&config_keys_attr_count,
+	&config_keys_attr_reuse,
+	NULL,
+};
+
+/*
+ * Note that, since no extra work is required on ->drop_item(),
+ * no ->drop_item() is provided.
+ */
+static struct configfs_group_operations config_keys_group_ops = {
+	.make_item = config_keys_make_item,
+};
+
+static const struct config_item_type config_keys_type = {
+	.ct_group_ops = &config_keys_group_ops,
+	.ct_attrs = config_keys_attrs,
+	.ct_owner = THIS_MODULE,
+};
+
+static bool restore;
+
+static ssize_t config_keys_restore_show(struct config_item *item, char *page)
+{
+	return sprintf(page, "%d\n", restore);
+}
+
+static ssize_t config_keys_restore_store(struct config_item *item,
+					  const char *page, size_t count)
+{
+	if (!restore)
+		restore_dm_crypt_keys_to_thread_keyring();
+
+	if (kstrtobool(page, &restore))
+		return -EINVAL;
+
+	return count;
+}
+
+CONFIGFS_ATTR(config_keys_, restore);
+
+static struct configfs_attribute *kdump_config_keys_attrs[] = {
+	&config_keys_attr_restore,
+	NULL,
+};
+
+static const struct config_item_type kdump_config_keys_type = {
+	.ct_attrs = kdump_config_keys_attrs,
+	.ct_owner = THIS_MODULE,
+};
+
+static struct configfs_subsystem config_keys_subsys = {
+	.su_group = {
+		.cg_item = {
+			.ci_namebuf = "crash_dm_crypt_keys",
+			.ci_type = &config_keys_type,
+		},
+	},
+};
+
+static int build_keys_header(void)
+{
+	struct config_item *item = NULL;
+	struct config_key *key;
+	int i, r;
+
+	if (keys_header != NULL)
+		kvfree(keys_header);
+
+	keys_header = kzalloc(get_keys_header_size(key_count), GFP_KERNEL);
+	if (!keys_header)
+		return -ENOMEM;
+
+	keys_header->total_keys = key_count;
+
+	i = 0;
+	list_for_each_entry(item, &config_keys_subsys.su_group.cg_children,
+			    ci_entry) {
+		if (item->ci_type != &config_key_type)
+			continue;
+
+		key = to_config_key(item);
+
+		if (!key->description) {
+			pr_warn("No key description for key %s\n", item->ci_name);
+			return -EINVAL;
+		}
+
+		strscpy(keys_header->keys[i].key_desc, key->description,
+			KEY_DESC_MAX_LEN);
+		r = read_key_from_user_keying(&keys_header->keys[i]);
+		if (r != 0) {
+			kexec_dprintk("Failed to read key %s\n",
+				      keys_header->keys[i].key_desc);
+			return r;
+		}
+		i++;
+		kexec_dprintk("Found key: %s\n", item->ci_name);
+	}
+
+	return 0;
+}
+
+int crash_load_dm_crypt_keys(struct kimage *image)
+{
+	struct kexec_buf kbuf = {
+		.image = image,
+		.buf_min = 0,
+		.buf_max = ULONG_MAX,
+		.top_down = false,
+		.random = true,
+	};
+	int r;
+
+
+	if (key_count <= 0) {
+		kexec_dprintk("No dm-crypt keys\n");
+		return -ENOENT;
+	}
+
+	if (!is_dm_key_reused) {
+		image->dm_crypt_keys_addr = 0;
+		r = build_keys_header();
+		if (r)
+			return r;
+	}
+
+	kbuf.buffer = keys_header;
+	kbuf.bufsz = get_keys_header_size(key_count);
+
+	kbuf.memsz = kbuf.bufsz;
+	kbuf.buf_align = ELF_CORE_HEADER_ALIGN;
+	kbuf.mem = KEXEC_BUF_MEM_UNKNOWN;
+	r = kexec_add_buffer(&kbuf);
+	if (r) {
+		kvfree((void *)kbuf.buffer);
+		return r;
+	}
+	image->dm_crypt_keys_addr = kbuf.mem;
+	image->dm_crypt_keys_sz = kbuf.bufsz;
+	kexec_dprintk(
+		"Loaded dm crypt keys to kexec_buffer bufsz=0x%lx memsz=0x%lx\n",
+		kbuf.bufsz, kbuf.memsz);
+
+	return r;
+}
+
+static int __init configfs_dmcrypt_keys_init(void)
+{
+	int ret;
+
+	if (is_kdump_kernel()) {
+		config_keys_subsys.su_group.cg_item.ci_type =
+			&kdump_config_keys_type;
+	}
+
+	config_group_init(&config_keys_subsys.su_group);
+	mutex_init(&config_keys_subsys.su_mutex);
+	ret = configfs_register_subsystem(&config_keys_subsys);
+	if (ret) {
+		pr_err("Error %d while registering subsystem %s\n", ret,
+		       config_keys_subsys.su_group.cg_item.ci_namebuf);
+		goto out_unregister;
+	}
+
+	return 0;
+
+out_unregister:
+	configfs_unregister_subsystem(&config_keys_subsys);
+
+	return ret;
+}
+
+module_init(configfs_dmcrypt_keys_init);
diff --git a/kernel/crash_reserve.c b/kernel/crash_reserve.c
index aff7c0fdbefa..acb6bf42e30d 100644
--- a/kernel/crash_reserve.c
+++ b/kernel/crash_reserve.c
@@ -131,7 +131,7 @@ static int __init parse_crashkernel_mem(char *cmdline,
 			cur++;
 			*crash_base = memparse(cur, &tmp);
 			if (cur == tmp) {
-				pr_warn("crahskernel: Memory value expected after '@'\n");
+				pr_warn("crashkernel: Memory value expected after '@'\n");
 				return -EINVAL;
 			}
 		}
diff --git a/kernel/delayacct.c b/kernel/delayacct.c
index eb63a021ac04..30e7912ebb0d 100644
--- a/kernel/delayacct.c
+++ b/kernel/delayacct.c
@@ -14,6 +14,15 @@
 #include <linux/delayacct.h>
 #include <linux/module.h>
 
+#define UPDATE_DELAY(type) \
+do { \
+	d->type##_delay_max = tsk->delays->type##_delay_max; \
+	d->type##_delay_min = tsk->delays->type##_delay_min; \
+	tmp = d->type##_delay_total + tsk->delays->type##_delay; \
+	d->type##_delay_total = (tmp < d->type##_delay_total) ? 0 : tmp; \
+	d->type##_count += tsk->delays->type##_count; \
+} while (0)
+
 DEFINE_STATIC_KEY_FALSE(delayacct_key);
 int delayacct_on __read_mostly;	/* Delay accounting turned on/off */
 struct kmem_cache *delayacct_cache;
@@ -173,41 +182,13 @@ int delayacct_add_tsk(struct taskstats *d, struct task_struct *tsk)
 
 	/* zero XXX_total, non-zero XXX_count implies XXX stat overflowed */
 	raw_spin_lock_irqsave(&tsk->delays->lock, flags);
-	d->blkio_delay_max = tsk->delays->blkio_delay_max;
-	d->blkio_delay_min = tsk->delays->blkio_delay_min;
-	tmp = d->blkio_delay_total + tsk->delays->blkio_delay;
-	d->blkio_delay_total = (tmp < d->blkio_delay_total) ? 0 : tmp;
-	d->swapin_delay_max = tsk->delays->swapin_delay_max;
-	d->swapin_delay_min = tsk->delays->swapin_delay_min;
-	tmp = d->swapin_delay_total + tsk->delays->swapin_delay;
-	d->swapin_delay_total = (tmp < d->swapin_delay_total) ? 0 : tmp;
-	d->freepages_delay_max = tsk->delays->freepages_delay_max;
-	d->freepages_delay_min = tsk->delays->freepages_delay_min;
-	tmp = d->freepages_delay_total + tsk->delays->freepages_delay;
-	d->freepages_delay_total = (tmp < d->freepages_delay_total) ? 0 : tmp;
-	d->thrashing_delay_max = tsk->delays->thrashing_delay_max;
-	d->thrashing_delay_min = tsk->delays->thrashing_delay_min;
-	tmp = d->thrashing_delay_total + tsk->delays->thrashing_delay;
-	d->thrashing_delay_total = (tmp < d->thrashing_delay_total) ? 0 : tmp;
-	d->compact_delay_max = tsk->delays->compact_delay_max;
-	d->compact_delay_min = tsk->delays->compact_delay_min;
-	tmp = d->compact_delay_total + tsk->delays->compact_delay;
-	d->compact_delay_total = (tmp < d->compact_delay_total) ? 0 : tmp;
-	d->wpcopy_delay_max = tsk->delays->wpcopy_delay_max;
-	d->wpcopy_delay_min = tsk->delays->wpcopy_delay_min;
-	tmp = d->wpcopy_delay_total + tsk->delays->wpcopy_delay;
-	d->wpcopy_delay_total = (tmp < d->wpcopy_delay_total) ? 0 : tmp;
-	d->irq_delay_max = tsk->delays->irq_delay_max;
-	d->irq_delay_min = tsk->delays->irq_delay_min;
-	tmp = d->irq_delay_total + tsk->delays->irq_delay;
-	d->irq_delay_total = (tmp < d->irq_delay_total) ? 0 : tmp;
-	d->blkio_count += tsk->delays->blkio_count;
-	d->swapin_count += tsk->delays->swapin_count;
-	d->freepages_count += tsk->delays->freepages_count;
-	d->thrashing_count += tsk->delays->thrashing_count;
-	d->compact_count += tsk->delays->compact_count;
-	d->wpcopy_count += tsk->delays->wpcopy_count;
-	d->irq_count += tsk->delays->irq_count;
+	UPDATE_DELAY(blkio);
+	UPDATE_DELAY(swapin);
+	UPDATE_DELAY(freepages);
+	UPDATE_DELAY(thrashing);
+	UPDATE_DELAY(compact);
+	UPDATE_DELAY(wpcopy);
+	UPDATE_DELAY(irq);
 	raw_spin_unlock_irqrestore(&tsk->delays->lock, flags);
 
 	return 0;
diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index b8fe0b3d0ffb..24c359d9c879 100644
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -13,6 +13,7 @@
 #include <linux/vmalloc.h>
 #include <linux/set_memory.h>
 #include <linux/slab.h>
+#include <linux/pci-p2pdma.h>
 #include "direct.h"
 
 /*
@@ -462,34 +463,33 @@ int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, int nents,
 		enum dma_data_direction dir, unsigned long attrs)
 {
 	struct pci_p2pdma_map_state p2pdma_state = {};
-	enum pci_p2pdma_map_type map;
 	struct scatterlist *sg;
 	int i, ret;
 
 	for_each_sg(sgl, sg, nents, i) {
-		if (is_pci_p2pdma_page(sg_page(sg))) {
-			map = pci_p2pdma_map_segment(&p2pdma_state, dev, sg);
-			switch (map) {
-			case PCI_P2PDMA_MAP_BUS_ADDR:
-				continue;
-			case PCI_P2PDMA_MAP_THRU_HOST_BRIDGE:
-				/*
-				 * Any P2P mapping that traverses the PCI
-				 * host bridge must be mapped with CPU physical
-				 * address and not PCI bus addresses. This is
-				 * done with dma_direct_map_page() below.
-				 */
-				break;
-			default:
-				ret = -EREMOTEIO;
+		switch (pci_p2pdma_state(&p2pdma_state, dev, sg_page(sg))) {
+		case PCI_P2PDMA_MAP_THRU_HOST_BRIDGE:
+			/*
+			 * Any P2P mapping that traverses the PCI host bridge
+			 * must be mapped with CPU physical address and not PCI
+			 * bus addresses.
+			 */
+			break;
+		case PCI_P2PDMA_MAP_NONE:
+			sg->dma_address = dma_direct_map_page(dev, sg_page(sg),
+					sg->offset, sg->length, dir, attrs);
+			if (sg->dma_address == DMA_MAPPING_ERROR) {
+				ret = -EIO;
 				goto out_unmap;
 			}
-		}
-
-		sg->dma_address = dma_direct_map_page(dev, sg_page(sg),
-				sg->offset, sg->length, dir, attrs);
-		if (sg->dma_address == DMA_MAPPING_ERROR) {
-			ret = -EIO;
+			break;
+		case PCI_P2PDMA_MAP_BUS_ADDR:
+			sg->dma_address = pci_p2pdma_bus_addr_map(&p2pdma_state,
+					sg_phys(sg));
+			sg_dma_mark_bus_address(sg);
+			continue;
+		default:
+			ret = -EREMOTEIO;
 			goto out_unmap;
 		}
 		sg_dma_len(sg) = sg->length;
diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c
index 051a32988040..107e4a4d251d 100644
--- a/kernel/dma/mapping.c
+++ b/kernel/dma/mapping.c
@@ -443,6 +443,24 @@ bool __dma_need_sync(struct device *dev, dma_addr_t dma_addr)
 }
 EXPORT_SYMBOL_GPL(__dma_need_sync);
 
+/**
+ * dma_need_unmap - does this device need dma_unmap_* operations
+ * @dev: device to check
+ *
+ * If this function returns %false, drivers can skip calling dma_unmap_* after
+ * finishing an I/O.  This function must be called after all mappings that might
+ * need to be unmapped have been performed.
+ */
+bool dma_need_unmap(struct device *dev)
+{
+	if (!dma_map_direct(dev, get_dma_ops(dev)))
+		return true;
+	if (!dev->dma_skip_sync)
+		return true;
+	return IS_ENABLED(CONFIG_DMA_API_DEBUG);
+}
+EXPORT_SYMBOL_GPL(dma_need_unmap);
+
 static void dma_setup_need_sync(struct device *dev)
 {
 	const struct dma_map_ops *ops = get_dma_ops(dev);
diff --git a/kernel/entry/common.c b/kernel/entry/common.c
index 20154572ede9..a8dd1f27417c 100644
--- a/kernel/entry/common.c
+++ b/kernel/entry/common.c
@@ -146,7 +146,7 @@ static inline bool report_single_step(unsigned long work)
 	return work & SYSCALL_WORK_SYSCALL_EXIT_TRAP;
 }
 
-static void syscall_exit_work(struct pt_regs *regs, unsigned long work)
+void syscall_exit_work(struct pt_regs *regs, unsigned long work)
 {
 	bool step;
 
@@ -173,53 +173,6 @@ static void syscall_exit_work(struct pt_regs *regs, unsigned long work)
 		ptrace_report_syscall_exit(regs, step);
 }
 
-/*
- * Syscall specific exit to user mode preparation. Runs with interrupts
- * enabled.
- */
-static void syscall_exit_to_user_mode_prepare(struct pt_regs *regs)
-{
-	unsigned long work = READ_ONCE(current_thread_info()->syscall_work);
-	unsigned long nr = syscall_get_nr(current, regs);
-
-	CT_WARN_ON(ct_state() != CT_STATE_KERNEL);
-
-	if (IS_ENABLED(CONFIG_PROVE_LOCKING)) {
-		if (WARN(irqs_disabled(), "syscall %lu left IRQs disabled", nr))
-			local_irq_enable();
-	}
-
-	rseq_syscall(regs);
-
-	/*
-	 * Do one-time syscall specific work. If these work items are
-	 * enabled, we want to run them exactly once per syscall exit with
-	 * interrupts enabled.
-	 */
-	if (unlikely(work & SYSCALL_WORK_EXIT))
-		syscall_exit_work(regs, work);
-}
-
-static __always_inline void __syscall_exit_to_user_mode_work(struct pt_regs *regs)
-{
-	syscall_exit_to_user_mode_prepare(regs);
-	local_irq_disable_exit_to_user();
-	exit_to_user_mode_prepare(regs);
-}
-
-void syscall_exit_to_user_mode_work(struct pt_regs *regs)
-{
-	__syscall_exit_to_user_mode_work(regs);
-}
-
-__visible noinstr void syscall_exit_to_user_mode(struct pt_regs *regs)
-{
-	instrumentation_begin();
-	__syscall_exit_to_user_mode_work(regs);
-	instrumentation_end();
-	exit_to_user_mode();
-}
-
 noinstr void irqentry_enter_from_user_mode(struct pt_regs *regs)
 {
 	enter_from_user_mode(regs);
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 95e703891b24..f34c99f8ce8f 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -1270,6 +1270,10 @@ static void put_ctx(struct perf_event_context *ctx)
 		if (ctx->task && ctx->task != TASK_TOMBSTONE)
 			put_task_struct(ctx->task);
 		call_rcu(&ctx->rcu_head, free_ctx);
+	} else {
+		smp_mb__after_atomic(); /* pairs with wait_var_event() */
+		if (ctx->task == TASK_TOMBSTONE)
+			wake_up_var(&ctx->refcount);
 	}
 }
 
@@ -2167,7 +2171,7 @@ static void perf_put_aux_event(struct perf_event *event)
 	 * If the event is an aux_event, tear down all links to
 	 * it from other events.
 	 */
-	for_each_sibling_event(iter, event->group_leader) {
+	for_each_sibling_event(iter, event) {
 		if (iter->aux_event != event)
 			continue;
 
@@ -2325,7 +2329,11 @@ static void perf_child_detach(struct perf_event *event)
 	if (WARN_ON_ONCE(!parent_event))
 		return;
 
+	/*
+	 * Can't check this from an IPI, the holder is likey another CPU.
+	 *
 	lockdep_assert_held(&parent_event->child_mutex);
+	 */
 
 	sync_child_event(event);
 	list_del_init(&event->child_list);
@@ -2343,6 +2351,11 @@ event_filter_match(struct perf_event *event)
 	       perf_cgroup_match(event);
 }
 
+static inline bool is_event_in_freq_mode(struct perf_event *event)
+{
+	return event->attr.freq && event->attr.sample_freq;
+}
+
 static void
 event_sched_out(struct perf_event *event, struct perf_event_context *ctx)
 {
@@ -2380,7 +2393,7 @@ event_sched_out(struct perf_event *event, struct perf_event_context *ctx)
 
 	if (!is_software_event(event))
 		cpc->active_oncpu--;
-	if (event->attr.freq && event->attr.sample_freq) {
+	if (is_event_in_freq_mode(event)) {
 		ctx->nr_freq--;
 		epc->nr_freq--;
 	}
@@ -2450,8 +2463,9 @@ ctx_time_update_event(struct perf_event_context *ctx, struct perf_event *event)
 
 #define DETACH_GROUP	0x01UL
 #define DETACH_CHILD	0x02UL
-#define DETACH_DEAD	0x04UL
-#define DETACH_EXIT	0x08UL
+#define DETACH_EXIT	0x04UL
+#define DETACH_REVOKE	0x08UL
+#define DETACH_DEAD	0x10UL
 
 /*
  * Cross CPU call to remove a performance event
@@ -2477,12 +2491,15 @@ __perf_remove_from_context(struct perf_event *event,
 	 */
 	if (flags & DETACH_EXIT)
 		state = PERF_EVENT_STATE_EXIT;
+	if (flags & DETACH_REVOKE)
+		state = PERF_EVENT_STATE_REVOKED;
 	if (flags & DETACH_DEAD) {
 		event->pending_disable = 1;
 		state = PERF_EVENT_STATE_DEAD;
 	}
 	event_sched_out(event, ctx);
 	perf_event_set_state(event, min(event->state, state));
+
 	if (flags & DETACH_GROUP)
 		perf_group_detach(event);
 	if (flags & DETACH_CHILD)
@@ -2628,6 +2645,41 @@ void perf_event_disable_inatomic(struct perf_event *event)
 static void perf_log_throttle(struct perf_event *event, int enable);
 static void perf_log_itrace_start(struct perf_event *event);
 
+static void perf_event_unthrottle(struct perf_event *event, bool start)
+{
+	event->hw.interrupts = 0;
+	if (start)
+		event->pmu->start(event, 0);
+	if (event == event->group_leader)
+		perf_log_throttle(event, 1);
+}
+
+static void perf_event_throttle(struct perf_event *event)
+{
+	event->pmu->stop(event, 0);
+	event->hw.interrupts = MAX_INTERRUPTS;
+	if (event == event->group_leader)
+		perf_log_throttle(event, 0);
+}
+
+static void perf_event_unthrottle_group(struct perf_event *event, bool skip_start_event)
+{
+	struct perf_event *sibling, *leader = event->group_leader;
+
+	perf_event_unthrottle(leader, skip_start_event ? leader != event : true);
+	for_each_sibling_event(sibling, leader)
+		perf_event_unthrottle(sibling, skip_start_event ? sibling != event : true);
+}
+
+static void perf_event_throttle_group(struct perf_event *event)
+{
+	struct perf_event *sibling, *leader = event->group_leader;
+
+	perf_event_throttle(leader);
+	for_each_sibling_event(sibling, leader)
+		perf_event_throttle(sibling);
+}
+
 static int
 event_sched_in(struct perf_event *event, struct perf_event_context *ctx)
 {
@@ -2656,10 +2708,8 @@ event_sched_in(struct perf_event *event, struct perf_event_context *ctx)
 	 * ticks already, also for a heavily scheduling task there is little
 	 * guarantee it'll get a tick in a timely manner.
 	 */
-	if (unlikely(event->hw.interrupts == MAX_INTERRUPTS)) {
-		perf_log_throttle(event, 1);
-		event->hw.interrupts = 0;
-	}
+	if (unlikely(event->hw.interrupts == MAX_INTERRUPTS))
+		perf_event_unthrottle(event, false);
 
 	perf_pmu_disable(event->pmu);
 
@@ -2674,7 +2724,7 @@ event_sched_in(struct perf_event *event, struct perf_event_context *ctx)
 
 	if (!is_software_event(event))
 		cpc->active_oncpu++;
-	if (event->attr.freq && event->attr.sample_freq) {
+	if (is_event_in_freq_mode(event)) {
 		ctx->nr_freq++;
 		epc->nr_freq++;
 	}
@@ -4237,14 +4287,10 @@ static void perf_adjust_freq_unthr_events(struct list_head *event_list)
 
 		hwc = &event->hw;
 
-		if (hwc->interrupts == MAX_INTERRUPTS) {
-			hwc->interrupts = 0;
-			perf_log_throttle(event, 1);
-			if (!event->attr.freq || !event->attr.sample_freq)
-				event->pmu->start(event, 0);
-		}
+		if (hwc->interrupts == MAX_INTERRUPTS)
+			perf_event_unthrottle_group(event, is_event_in_freq_mode(event));
 
-		if (!event->attr.freq || !event->attr.sample_freq)
+		if (!is_event_in_freq_mode(event))
 			continue;
 
 		/*
@@ -4516,7 +4562,8 @@ out:
 
 static void perf_remove_from_owner(struct perf_event *event);
 static void perf_event_exit_event(struct perf_event *event,
-				  struct perf_event_context *ctx);
+				  struct perf_event_context *ctx,
+				  bool revoke);
 
 /*
  * Removes all events from the current task that have been marked
@@ -4543,7 +4590,7 @@ static void perf_event_remove_on_exec(struct perf_event_context *ctx)
 
 		modified = true;
 
-		perf_event_exit_event(event, ctx);
+		perf_event_exit_event(event, ctx, false);
 	}
 
 	raw_spin_lock_irqsave(&ctx->lock, flags);
@@ -5125,6 +5172,7 @@ static bool is_sb_event(struct perf_event *event)
 	    attr->context_switch || attr->text_poke ||
 	    attr->bpf_event)
 		return true;
+
 	return false;
 }
 
@@ -5521,6 +5569,8 @@ static void perf_free_addr_filters(struct perf_event *event);
 /* vs perf_event_alloc() error */
 static void __free_event(struct perf_event *event)
 {
+	struct pmu *pmu = event->pmu;
+
 	if (event->attach_state & PERF_ATTACH_CALLCHAIN)
 		put_callchain_buffers();
 
@@ -5550,6 +5600,7 @@ static void __free_event(struct perf_event *event)
 		 * put_pmu_ctx() needs an event->ctx reference, because of
 		 * epc->ctx.
 		 */
+		WARN_ON_ONCE(!pmu);
 		WARN_ON_ONCE(!event->ctx);
 		WARN_ON_ONCE(event->pmu_ctx->ctx != event->ctx);
 		put_pmu_ctx(event->pmu_ctx);
@@ -5562,8 +5613,13 @@ static void __free_event(struct perf_event *event)
 	if (event->ctx)
 		put_ctx(event->ctx);
 
-	if (event->pmu)
-		module_put(event->pmu->module);
+	if (pmu) {
+		module_put(pmu->module);
+		scoped_guard (spinlock, &pmu->events_lock) {
+			list_del(&event->pmu_list);
+			wake_up_var(pmu);
+		}
+	}
 
 	call_rcu(&event->rcu_head, free_event_rcu);
 }
@@ -5600,13 +5656,13 @@ static void _free_event(struct perf_event *event)
 
 /*
  * Used to free events which have a known refcount of 1, such as in error paths
- * where the event isn't exposed yet and inherited events.
+ * of inherited events.
  */
 static void free_event(struct perf_event *event)
 {
 	if (WARN(atomic_long_cmpxchg(&event->refcount, 1, 0) != 1,
-				"unexpected event refcount: %ld; ptr=%p\n",
-				atomic_long_read(&event->refcount), event)) {
+				     "unexpected event refcount: %ld; ptr=%p\n",
+				     atomic_long_read(&event->refcount), event)) {
 		/* leak to avoid use-after-free */
 		return;
 	}
@@ -5689,7 +5745,6 @@ int perf_event_release_kernel(struct perf_event *event)
 {
 	struct perf_event_context *ctx = event->ctx;
 	struct perf_event *child, *tmp;
-	LIST_HEAD(free_list);
 
 	/*
 	 * If we got here through err_alloc: free_event(event); we will not
@@ -5718,15 +5773,17 @@ int perf_event_release_kernel(struct perf_event *event)
 	 * Thus this guarantees that we will in fact observe and kill _ALL_
 	 * child events.
 	 */
-	perf_remove_from_context(event, DETACH_GROUP|DETACH_DEAD);
+	if (event->state > PERF_EVENT_STATE_REVOKED) {
+		perf_remove_from_context(event, DETACH_GROUP|DETACH_DEAD);
+	} else {
+		event->state = PERF_EVENT_STATE_DEAD;
+	}
 
 	perf_event_ctx_unlock(event, ctx);
 
 again:
 	mutex_lock(&event->child_mutex);
 	list_for_each_entry(child, &event->child_list, child_list) {
-		void *var = NULL;
-
 		/*
 		 * Cannot change, child events are not migrated, see the
 		 * comment with perf_event_ctx_lock_nested().
@@ -5759,44 +5816,24 @@ again:
 		tmp = list_first_entry_or_null(&event->child_list,
 					       struct perf_event, child_list);
 		if (tmp == child) {
-			perf_remove_from_context(child, DETACH_GROUP);
-			list_move(&child->child_list, &free_list);
+			perf_remove_from_context(child, DETACH_GROUP | DETACH_CHILD);
 		} else {
-			var = &ctx->refcount;
+			child = NULL;
 		}
 
 		mutex_unlock(&event->child_mutex);
 		mutex_unlock(&ctx->mutex);
-		put_ctx(ctx);
 
-		if (var) {
-			/*
-			 * If perf_event_free_task() has deleted all events from the
-			 * ctx while the child_mutex got released above, make sure to
-			 * notify about the preceding put_ctx().
-			 */
-			smp_mb(); /* pairs with wait_var_event() */
-			wake_up_var(var);
+		if (child) {
+			/* Last reference unless ->pending_task work is pending */
+			put_event(child);
 		}
+		put_ctx(ctx);
+
 		goto again;
 	}
 	mutex_unlock(&event->child_mutex);
 
-	list_for_each_entry_safe(child, tmp, &free_list, child_list) {
-		void *var = &child->ctx->refcount;
-
-		list_del(&child->child_list);
-		/* Last reference unless ->pending_task work is pending */
-		put_event(child);
-
-		/*
-		 * Wake any perf_event_free_task() waiting for this event to be
-		 * freed.
-		 */
-		smp_mb(); /* pairs with wait_var_event() */
-		wake_up_var(var);
-	}
-
 no_ctx:
 	/*
 	 * Last reference unless ->pending_task work is pending on this event
@@ -6068,8 +6105,14 @@ static __poll_t perf_poll(struct file *file, poll_table *wait)
 	struct perf_buffer *rb;
 	__poll_t events = EPOLLHUP;
 
+	if (event->state <= PERF_EVENT_STATE_REVOKED)
+		return EPOLLERR;
+
 	poll_wait(file, &event->waitq, wait);
 
+	if (event->state <= PERF_EVENT_STATE_REVOKED)
+		return EPOLLERR;
+
 	if (is_event_hup(event))
 		return events;
 
@@ -6167,14 +6210,6 @@ static void __perf_event_period(struct perf_event *event,
 	active = (event->state == PERF_EVENT_STATE_ACTIVE);
 	if (active) {
 		perf_pmu_disable(event->pmu);
-		/*
-		 * We could be throttled; unthrottle now to avoid the tick
-		 * trying to unthrottle while we already re-started the event.
-		 */
-		if (event->hw.interrupts == MAX_INTERRUPTS) {
-			event->hw.interrupts = 0;
-			perf_log_throttle(event, 1);
-		}
 		event->pmu->stop(event, PERF_EF_UPDATE);
 	}
 
@@ -6182,6 +6217,14 @@ static void __perf_event_period(struct perf_event *event,
 
 	if (active) {
 		event->pmu->start(event, PERF_EF_RELOAD);
+		/*
+		 * Once the period is force-reset, the event starts immediately.
+		 * But the event/group could be throttled. Unthrottle the
+		 * event/group now to avoid the next tick trying to unthrottle
+		 * while we already re-started the event/group.
+		 */
+		if (event->hw.interrupts == MAX_INTERRUPTS)
+			perf_event_unthrottle_group(event, true);
 		perf_pmu_enable(event->pmu);
 	}
 }
@@ -6239,12 +6282,18 @@ static int perf_event_set_output(struct perf_event *event,
 static int perf_event_set_filter(struct perf_event *event, void __user *arg);
 static int perf_copy_attr(struct perf_event_attr __user *uattr,
 			  struct perf_event_attr *attr);
+static int __perf_event_set_bpf_prog(struct perf_event *event,
+				     struct bpf_prog *prog,
+				     u64 bpf_cookie);
 
 static long _perf_ioctl(struct perf_event *event, unsigned int cmd, unsigned long arg)
 {
 	void (*func)(struct perf_event *);
 	u32 flags = arg;
 
+	if (event->state <= PERF_EVENT_STATE_REVOKED)
+		return -ENODEV;
+
 	switch (cmd) {
 	case PERF_EVENT_IOC_ENABLE:
 		func = _perf_event_enable;
@@ -6301,7 +6350,7 @@ static long _perf_ioctl(struct perf_event *event, unsigned int cmd, unsigned lon
 		if (IS_ERR(prog))
 			return PTR_ERR(prog);
 
-		err = perf_event_set_bpf_prog(event, prog, 0);
+		err = __perf_event_set_bpf_prog(event, prog, 0);
 		if (err) {
 			bpf_prog_put(prog);
 			return err;
@@ -6620,9 +6669,22 @@ void ring_buffer_put(struct perf_buffer *rb)
 	call_rcu(&rb->rcu_head, rb_free_rcu);
 }
 
+typedef void (*mapped_f)(struct perf_event *event, struct mm_struct *mm);
+
+#define get_mapped(event, func)			\
+({	struct pmu *pmu;			\
+	mapped_f f = NULL;			\
+	guard(rcu)();				\
+	pmu = READ_ONCE(event->pmu);		\
+	if (pmu)				\
+		f = pmu->func;			\
+	f;					\
+})
+
 static void perf_mmap_open(struct vm_area_struct *vma)
 {
 	struct perf_event *event = vma->vm_file->private_data;
+	mapped_f mapped = get_mapped(event, event_mapped);
 
 	atomic_inc(&event->mmap_count);
 	atomic_inc(&event->rb->mmap_count);
@@ -6630,8 +6692,8 @@ static void perf_mmap_open(struct vm_area_struct *vma)
 	if (vma->vm_pgoff)
 		atomic_inc(&event->rb->aux_mmap_count);
 
-	if (event->pmu->event_mapped)
-		event->pmu->event_mapped(event, vma->vm_mm);
+	if (mapped)
+		mapped(event, vma->vm_mm);
 }
 
 static void perf_pmu_output_stop(struct perf_event *event);
@@ -6647,14 +6709,16 @@ static void perf_pmu_output_stop(struct perf_event *event);
 static void perf_mmap_close(struct vm_area_struct *vma)
 {
 	struct perf_event *event = vma->vm_file->private_data;
+	mapped_f unmapped = get_mapped(event, event_unmapped);
 	struct perf_buffer *rb = ring_buffer_get(event);
 	struct user_struct *mmap_user = rb->mmap_user;
 	int mmap_locked = rb->mmap_locked;
 	unsigned long size = perf_data_size(rb);
 	bool detach_rest = false;
 
-	if (event->pmu->event_unmapped)
-		event->pmu->event_unmapped(event, vma->vm_mm);
+	/* FIXIES vs perf_pmu_unregister() */
+	if (unmapped)
+		unmapped(event, vma->vm_mm);
 
 	/*
 	 * The AUX buffer is strictly a sub-buffer, serialize using aux_mutex
@@ -6847,6 +6911,7 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma)
 	unsigned long nr_pages;
 	long user_extra = 0, extra = 0;
 	int ret, flags = 0;
+	mapped_f mapped;
 
 	/*
 	 * Don't allow mmap() of inherited per-task counters. This would
@@ -6877,6 +6942,16 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma)
 	mutex_lock(&event->mmap_mutex);
 	ret = -EINVAL;
 
+	/*
+	 * This relies on __pmu_detach_event() taking mmap_mutex after marking
+	 * the event REVOKED. Either we observe the state, or __pmu_detach_event()
+	 * will detach the rb created here.
+	 */
+	if (event->state <= PERF_EVENT_STATE_REVOKED) {
+		ret = -ENODEV;
+		goto unlock;
+	}
+
 	if (vma->vm_pgoff == 0) {
 		nr_pages -= 1;
 
@@ -7055,8 +7130,9 @@ aux_unlock:
 	if (!ret)
 		ret = map_range(rb, vma);
 
-	if (!ret && event->pmu->event_mapped)
-		event->pmu->event_mapped(event, vma->vm_mm);
+	mapped = get_mapped(event, event_mapped);
+	if (mapped)
+		mapped(event, vma->vm_mm);
 
 	return ret;
 }
@@ -7067,6 +7143,9 @@ static int perf_fasync(int fd, struct file *filp, int on)
 	struct perf_event *event = filp->private_data;
 	int retval;
 
+	if (event->state <= PERF_EVENT_STATE_REVOKED)
+		return -ENODEV;
+
 	inode_lock(inode);
 	retval = fasync_helper(fd, filp, on, &event->fasync);
 	inode_unlock(inode);
@@ -9946,7 +10025,7 @@ void perf_event_text_poke(const void *addr, const void *old_bytes,
 
 void perf_event_itrace_started(struct perf_event *event)
 {
-	event->attach_state |= PERF_ATTACH_ITRACE;
+	WRITE_ONCE(event->attach_state, event->attach_state | PERF_ATTACH_ITRACE);
 }
 
 static void perf_log_itrace_start(struct perf_event *event)
@@ -10029,14 +10108,13 @@ __perf_event_account_interrupt(struct perf_event *event, int throttle)
 		hwc->interrupts = 1;
 	} else {
 		hwc->interrupts++;
-		if (unlikely(throttle &&
-			     hwc->interrupts > max_samples_per_tick)) {
-			__this_cpu_inc(perf_throttled_count);
-			tick_dep_set_cpu(smp_processor_id(), TICK_DEP_BIT_PERF_EVENTS);
-			hwc->interrupts = MAX_INTERRUPTS;
-			perf_log_throttle(event, 0);
-			ret = 1;
-		}
+	}
+
+	if (unlikely(throttle && hwc->interrupts >= max_samples_per_tick)) {
+		__this_cpu_inc(perf_throttled_count);
+		tick_dep_set_cpu(smp_processor_id(), TICK_DEP_BIT_PERF_EVENTS);
+		perf_event_throttle_group(event);
+		ret = 1;
 	}
 
 	if (event->attr.freq) {
@@ -11069,11 +11147,15 @@ static inline bool perf_event_is_tracing(struct perf_event *event)
 	return false;
 }
 
-int perf_event_set_bpf_prog(struct perf_event *event, struct bpf_prog *prog,
-			    u64 bpf_cookie)
+static int __perf_event_set_bpf_prog(struct perf_event *event,
+				     struct bpf_prog *prog,
+				     u64 bpf_cookie)
 {
 	bool is_kprobe, is_uprobe, is_tracepoint, is_syscall_tp;
 
+	if (event->state <= PERF_EVENT_STATE_REVOKED)
+		return -ENODEV;
+
 	if (!perf_event_is_tracing(event))
 		return perf_event_set_bpf_handler(event, prog, bpf_cookie);
 
@@ -11108,6 +11190,20 @@ int perf_event_set_bpf_prog(struct perf_event *event, struct bpf_prog *prog,
 	return perf_event_attach_bpf_prog(event, prog, bpf_cookie);
 }
 
+int perf_event_set_bpf_prog(struct perf_event *event,
+			    struct bpf_prog *prog,
+			    u64 bpf_cookie)
+{
+	struct perf_event_context *ctx;
+	int ret;
+
+	ctx = perf_event_ctx_lock(event);
+	ret = __perf_event_set_bpf_prog(event, prog, bpf_cookie);
+	perf_event_ctx_unlock(event, ctx);
+
+	return ret;
+}
+
 void perf_event_free_bpf_prog(struct perf_event *event)
 {
 	if (!event->prog)
@@ -11130,7 +11226,15 @@ static void perf_event_free_filter(struct perf_event *event)
 {
 }
 
-int perf_event_set_bpf_prog(struct perf_event *event, struct bpf_prog *prog,
+static int __perf_event_set_bpf_prog(struct perf_event *event,
+				     struct bpf_prog *prog,
+				     u64 bpf_cookie)
+{
+	return -ENOENT;
+}
+
+int perf_event_set_bpf_prog(struct perf_event *event,
+			    struct bpf_prog *prog,
 			    u64 bpf_cookie)
 {
 	return -ENOENT;
@@ -12235,6 +12339,9 @@ int perf_pmu_register(struct pmu *_pmu, const char *name, int type)
 	if (!pmu->event_idx)
 		pmu->event_idx = perf_event_idx_default;
 
+	INIT_LIST_HEAD(&pmu->events);
+	spin_lock_init(&pmu->events_lock);
+
 	/*
 	 * Now that the PMU is complete, make it visible to perf_try_init_event().
 	 */
@@ -12248,21 +12355,143 @@ int perf_pmu_register(struct pmu *_pmu, const char *name, int type)
 }
 EXPORT_SYMBOL_GPL(perf_pmu_register);
 
-void perf_pmu_unregister(struct pmu *pmu)
+static void __pmu_detach_event(struct pmu *pmu, struct perf_event *event,
+			       struct perf_event_context *ctx)
+{
+	/*
+	 * De-schedule the event and mark it REVOKED.
+	 */
+	perf_event_exit_event(event, ctx, true);
+
+	/*
+	 * All _free_event() bits that rely on event->pmu:
+	 *
+	 * Notably, perf_mmap() relies on the ordering here.
+	 */
+	scoped_guard (mutex, &event->mmap_mutex) {
+		WARN_ON_ONCE(pmu->event_unmapped);
+		/*
+		 * Mostly an empty lock sequence, such that perf_mmap(), which
+		 * relies on mmap_mutex, is sure to observe the state change.
+		 */
+	}
+
+	perf_event_free_bpf_prog(event);
+	perf_free_addr_filters(event);
+
+	if (event->destroy) {
+		event->destroy(event);
+		event->destroy = NULL;
+	}
+
+	if (event->pmu_ctx) {
+		put_pmu_ctx(event->pmu_ctx);
+		event->pmu_ctx = NULL;
+	}
+
+	exclusive_event_destroy(event);
+	module_put(pmu->module);
+
+	event->pmu = NULL; /* force fault instead of UAF */
+}
+
+static void pmu_detach_event(struct pmu *pmu, struct perf_event *event)
+{
+	struct perf_event_context *ctx;
+
+	ctx = perf_event_ctx_lock(event);
+	__pmu_detach_event(pmu, event, ctx);
+	perf_event_ctx_unlock(event, ctx);
+
+	scoped_guard (spinlock, &pmu->events_lock)
+		list_del(&event->pmu_list);
+}
+
+static struct perf_event *pmu_get_event(struct pmu *pmu)
+{
+	struct perf_event *event;
+
+	guard(spinlock)(&pmu->events_lock);
+	list_for_each_entry(event, &pmu->events, pmu_list) {
+		if (atomic_long_inc_not_zero(&event->refcount))
+			return event;
+	}
+
+	return NULL;
+}
+
+static bool pmu_empty(struct pmu *pmu)
+{
+	guard(spinlock)(&pmu->events_lock);
+	return list_empty(&pmu->events);
+}
+
+static void pmu_detach_events(struct pmu *pmu)
+{
+	struct perf_event *event;
+
+	for (;;) {
+		event = pmu_get_event(pmu);
+		if (!event)
+			break;
+
+		pmu_detach_event(pmu, event);
+		put_event(event);
+	}
+
+	/*
+	 * wait for pending _free_event()s
+	 */
+	wait_var_event(pmu, pmu_empty(pmu));
+}
+
+int perf_pmu_unregister(struct pmu *pmu)
 {
 	scoped_guard (mutex, &pmus_lock) {
+		if (!idr_cmpxchg(&pmu_idr, pmu->type, pmu, NULL))
+			return -EINVAL;
+
 		list_del_rcu(&pmu->entry);
-		idr_remove(&pmu_idr, pmu->type);
 	}
 
 	/*
 	 * We dereference the pmu list under both SRCU and regular RCU, so
 	 * synchronize against both of those.
+	 *
+	 * Notably, the entirety of event creation, from perf_init_event()
+	 * (which will now fail, because of the above) until
+	 * perf_install_in_context() should be under SRCU such that
+	 * this synchronizes against event creation. This avoids trying to
+	 * detach events that are not fully formed.
 	 */
 	synchronize_srcu(&pmus_srcu);
 	synchronize_rcu();
 
+	if (pmu->event_unmapped && !pmu_empty(pmu)) {
+		/*
+		 * Can't force remove events when pmu::event_unmapped()
+		 * is used in perf_mmap_close().
+		 */
+		guard(mutex)(&pmus_lock);
+		idr_cmpxchg(&pmu_idr, pmu->type, NULL, pmu);
+		list_add_rcu(&pmu->entry, &pmus);
+		return -EBUSY;
+	}
+
+	scoped_guard (mutex, &pmus_lock)
+		idr_remove(&pmu_idr, pmu->type);
+
+	/*
+	 * PMU is removed from the pmus list, so no new events will
+	 * be created, now take care of the existing ones.
+	 */
+	pmu_detach_events(pmu);
+
+	/*
+	 * PMU is unused, make it go away.
+	 */
 	perf_pmu_free(pmu);
+	return 0;
 }
 EXPORT_SYMBOL_GPL(perf_pmu_unregister);
 
@@ -12356,7 +12585,7 @@ static struct pmu *perf_init_event(struct perf_event *event)
 	struct pmu *pmu;
 	int type, ret;
 
-	guard(srcu)(&pmus_srcu);
+	guard(srcu)(&pmus_srcu); /* pmu idr/list access */
 
 	/*
 	 * Save original type before calling pmu->event_init() since certain
@@ -12580,6 +12809,7 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
 	INIT_LIST_HEAD(&event->active_entry);
 	INIT_LIST_HEAD(&event->addr_filters.list);
 	INIT_HLIST_NODE(&event->hlist_entry);
+	INIT_LIST_HEAD(&event->pmu_list);
 
 
 	init_waitqueue_head(&event->waitq);
@@ -12651,7 +12881,7 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
 
 	hwc = &event->hw;
 	hwc->sample_period = attr->sample_period;
-	if (attr->freq && attr->sample_freq)
+	if (is_event_in_freq_mode(event))
 		hwc->sample_period = 1;
 	hwc->last_period = hwc->sample_period;
 
@@ -12758,6 +12988,13 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
 	/* symmetric to unaccount_event() in _free_event() */
 	account_event(event);
 
+	/*
+	 * Event creation should be under SRCU, see perf_pmu_unregister().
+	 */
+	lockdep_assert_held(&pmus_srcu);
+	scoped_guard (spinlock, &pmu->events_lock)
+		list_add(&event->pmu_list, &pmu->events);
+
 	return_ptr(event);
 }
 
@@ -12957,6 +13194,9 @@ set:
 		goto unlock;
 
 	if (output_event) {
+		if (output_event->state <= PERF_EVENT_STATE_REVOKED)
+			goto unlock;
+
 		/* get the rb we want to redirect to */
 		rb = ring_buffer_get(output_event);
 		if (!rb)
@@ -13138,6 +13378,11 @@ SYSCALL_DEFINE5(perf_event_open,
 	if (event_fd < 0)
 		return event_fd;
 
+	/*
+	 * Event creation should be under SRCU, see perf_pmu_unregister().
+	 */
+	guard(srcu)(&pmus_srcu);
+
 	CLASS(fd, group)(group_fd);     // group_fd == -1 => empty
 	if (group_fd != -1) {
 		if (!is_perf_file(group)) {
@@ -13145,6 +13390,10 @@ SYSCALL_DEFINE5(perf_event_open,
 			goto err_fd;
 		}
 		group_leader = fd_file(group)->private_data;
+		if (group_leader->state <= PERF_EVENT_STATE_REVOKED) {
+			err = -ENODEV;
+			goto err_fd;
+		}
 		if (flags & PERF_FLAG_FD_OUTPUT)
 			output_event = group_leader;
 		if (flags & PERF_FLAG_FD_NO_GROUP)
@@ -13441,7 +13690,7 @@ err_cred:
 	if (task)
 		up_read(&task->signal->exec_update_lock);
 err_alloc:
-	free_event(event);
+	put_event(event);
 err_task:
 	if (task)
 		put_task_struct(task);
@@ -13478,6 +13727,11 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu,
 	if (attr->aux_output || attr->aux_action)
 		return ERR_PTR(-EINVAL);
 
+	/*
+	 * Event creation should be under SRCU, see perf_pmu_unregister().
+	 */
+	guard(srcu)(&pmus_srcu);
+
 	event = perf_event_alloc(attr, cpu, task, NULL, NULL,
 				 overflow_handler, context, -1);
 	if (IS_ERR(event)) {
@@ -13549,7 +13803,7 @@ err_unlock:
 	perf_unpin_context(ctx);
 	put_ctx(ctx);
 err_alloc:
-	free_event(event);
+	put_event(event);
 err:
 	return ERR_PTR(err);
 }
@@ -13689,10 +13943,12 @@ static void sync_child_event(struct perf_event *child_event)
 }
 
 static void
-perf_event_exit_event(struct perf_event *event, struct perf_event_context *ctx)
+perf_event_exit_event(struct perf_event *event,
+		      struct perf_event_context *ctx, bool revoke)
 {
 	struct perf_event *parent_event = event->parent;
-	unsigned long detach_flags = 0;
+	unsigned long detach_flags = DETACH_EXIT;
+	unsigned int attach_state;
 
 	if (parent_event) {
 		/*
@@ -13707,22 +13963,38 @@ perf_event_exit_event(struct perf_event *event, struct perf_event_context *ctx)
 		 * Do destroy all inherited groups, we don't care about those
 		 * and being thorough is better.
 		 */
-		detach_flags = DETACH_GROUP | DETACH_CHILD;
+		detach_flags |= DETACH_GROUP | DETACH_CHILD;
 		mutex_lock(&parent_event->child_mutex);
+		/* PERF_ATTACH_ITRACE might be set concurrently */
+		attach_state = READ_ONCE(event->attach_state);
 	}
 
-	perf_remove_from_context(event, detach_flags | DETACH_EXIT);
+	if (revoke)
+		detach_flags |= DETACH_GROUP | DETACH_REVOKE;
 
+	perf_remove_from_context(event, detach_flags);
 	/*
 	 * Child events can be freed.
 	 */
 	if (parent_event) {
 		mutex_unlock(&parent_event->child_mutex);
+
 		/*
-		 * Kick perf_poll() for is_event_hup();
+		 * Match the refcount initialization. Make sure it doesn't happen
+		 * twice if pmu_detach_event() calls it on an already exited task.
 		 */
-		perf_event_wakeup(parent_event);
-		put_event(event);
+		if (attach_state & PERF_ATTACH_CHILD) {
+			/*
+			 * Kick perf_poll() for is_event_hup();
+			 */
+			perf_event_wakeup(parent_event);
+			/*
+			 * pmu_detach_event() will have an extra refcount.
+			 * perf_pending_task() might have one too.
+			 */
+			put_event(event);
+		}
+
 		return;
 	}
 
@@ -13732,15 +14004,13 @@ perf_event_exit_event(struct perf_event *event, struct perf_event_context *ctx)
 	perf_event_wakeup(event);
 }
 
-static void perf_event_exit_task_context(struct task_struct *child)
+static void perf_event_exit_task_context(struct task_struct *task, bool exit)
 {
-	struct perf_event_context *child_ctx, *clone_ctx = NULL;
+	struct perf_event_context *ctx, *clone_ctx = NULL;
 	struct perf_event *child_event, *next;
 
-	WARN_ON_ONCE(child != current);
-
-	child_ctx = perf_pin_task_context(child);
-	if (!child_ctx)
+	ctx = perf_pin_task_context(task);
+	if (!ctx)
 		return;
 
 	/*
@@ -13753,27 +14023,28 @@ static void perf_event_exit_task_context(struct task_struct *child)
 	 * without ctx::mutex (it cannot because of the move_group double mutex
 	 * lock thing). See the comments in perf_install_in_context().
 	 */
-	mutex_lock(&child_ctx->mutex);
+	mutex_lock(&ctx->mutex);
 
 	/*
 	 * In a single ctx::lock section, de-schedule the events and detach the
 	 * context from the task such that we cannot ever get it scheduled back
 	 * in.
 	 */
-	raw_spin_lock_irq(&child_ctx->lock);
-	task_ctx_sched_out(child_ctx, NULL, EVENT_ALL);
+	raw_spin_lock_irq(&ctx->lock);
+	if (exit)
+		task_ctx_sched_out(ctx, NULL, EVENT_ALL);
 
 	/*
 	 * Now that the context is inactive, destroy the task <-> ctx relation
 	 * and mark the context dead.
 	 */
-	RCU_INIT_POINTER(child->perf_event_ctxp, NULL);
-	put_ctx(child_ctx); /* cannot be last */
-	WRITE_ONCE(child_ctx->task, TASK_TOMBSTONE);
-	put_task_struct(current); /* cannot be last */
+	RCU_INIT_POINTER(task->perf_event_ctxp, NULL);
+	put_ctx(ctx); /* cannot be last */
+	WRITE_ONCE(ctx->task, TASK_TOMBSTONE);
+	put_task_struct(task); /* cannot be last */
 
-	clone_ctx = unclone_ctx(child_ctx);
-	raw_spin_unlock_irq(&child_ctx->lock);
+	clone_ctx = unclone_ctx(ctx);
+	raw_spin_unlock_irq(&ctx->lock);
 
 	if (clone_ctx)
 		put_ctx(clone_ctx);
@@ -13783,28 +14054,48 @@ static void perf_event_exit_task_context(struct task_struct *child)
 	 * won't get any samples after PERF_RECORD_EXIT. We can however still
 	 * get a few PERF_RECORD_READ events.
 	 */
-	perf_event_task(child, child_ctx, 0);
+	if (exit)
+		perf_event_task(task, ctx, 0);
 
-	list_for_each_entry_safe(child_event, next, &child_ctx->event_list, event_entry)
-		perf_event_exit_event(child_event, child_ctx);
+	list_for_each_entry_safe(child_event, next, &ctx->event_list, event_entry)
+		perf_event_exit_event(child_event, ctx, false);
 
-	mutex_unlock(&child_ctx->mutex);
+	mutex_unlock(&ctx->mutex);
 
-	put_ctx(child_ctx);
+	if (!exit) {
+		/*
+		 * perf_event_release_kernel() could still have a reference on
+		 * this context. In that case we must wait for these events to
+		 * have been freed (in particular all their references to this
+		 * task must've been dropped).
+		 *
+		 * Without this copy_process() will unconditionally free this
+		 * task (irrespective of its reference count) and
+		 * _free_event()'s put_task_struct(event->hw.target) will be a
+		 * use-after-free.
+		 *
+		 * Wait for all events to drop their context reference.
+		 */
+		wait_var_event(&ctx->refcount,
+			       refcount_read(&ctx->refcount) == 1);
+	}
+	put_ctx(ctx);
 }
 
 /*
- * When a child task exits, feed back event values to parent events.
+ * When a task exits, feed back event values to parent events.
  *
  * Can be called with exec_update_lock held when called from
  * setup_new_exec().
  */
-void perf_event_exit_task(struct task_struct *child)
+void perf_event_exit_task(struct task_struct *task)
 {
 	struct perf_event *event, *tmp;
 
-	mutex_lock(&child->perf_event_mutex);
-	list_for_each_entry_safe(event, tmp, &child->perf_event_list,
+	WARN_ON_ONCE(task != current);
+
+	mutex_lock(&task->perf_event_mutex);
+	list_for_each_entry_safe(event, tmp, &task->perf_event_list,
 				 owner_entry) {
 		list_del_init(&event->owner_entry);
 
@@ -13815,42 +14106,23 @@ void perf_event_exit_task(struct task_struct *child)
 		 */
 		smp_store_release(&event->owner, NULL);
 	}
-	mutex_unlock(&child->perf_event_mutex);
+	mutex_unlock(&task->perf_event_mutex);
 
-	perf_event_exit_task_context(child);
+	perf_event_exit_task_context(task, true);
 
 	/*
 	 * The perf_event_exit_task_context calls perf_event_task
-	 * with child's task_ctx, which generates EXIT events for
-	 * child contexts and sets child->perf_event_ctxp[] to NULL.
+	 * with task's task_ctx, which generates EXIT events for
+	 * task contexts and sets task->perf_event_ctxp[] to NULL.
 	 * At this point we need to send EXIT events to cpu contexts.
 	 */
-	perf_event_task(child, NULL, 0);
+	perf_event_task(task, NULL, 0);
 
 	/*
 	 * Detach the perf_ctx_data for the system-wide event.
 	 */
 	guard(percpu_read)(&global_ctx_data_rwsem);
-	detach_task_ctx_data(child);
-}
-
-static void perf_free_event(struct perf_event *event,
-			    struct perf_event_context *ctx)
-{
-	struct perf_event *parent = event->parent;
-
-	if (WARN_ON_ONCE(!parent))
-		return;
-
-	mutex_lock(&parent->child_mutex);
-	list_del_init(&event->child_list);
-	mutex_unlock(&parent->child_mutex);
-
-	raw_spin_lock_irq(&ctx->lock);
-	perf_group_detach(event);
-	list_del_event(event, ctx);
-	raw_spin_unlock_irq(&ctx->lock);
-	put_event(event);
+	detach_task_ctx_data(task);
 }
 
 /*
@@ -13862,48 +14134,7 @@ static void perf_free_event(struct perf_event *event,
  */
 void perf_event_free_task(struct task_struct *task)
 {
-	struct perf_event_context *ctx;
-	struct perf_event *event, *tmp;
-
-	ctx = rcu_access_pointer(task->perf_event_ctxp);
-	if (!ctx)
-		return;
-
-	mutex_lock(&ctx->mutex);
-	raw_spin_lock_irq(&ctx->lock);
-	/*
-	 * Destroy the task <-> ctx relation and mark the context dead.
-	 *
-	 * This is important because even though the task hasn't been
-	 * exposed yet the context has been (through child_list).
-	 */
-	RCU_INIT_POINTER(task->perf_event_ctxp, NULL);
-	WRITE_ONCE(ctx->task, TASK_TOMBSTONE);
-	put_task_struct(task); /* cannot be last */
-	raw_spin_unlock_irq(&ctx->lock);
-
-
-	list_for_each_entry_safe(event, tmp, &ctx->event_list, event_entry)
-		perf_free_event(event, ctx);
-
-	mutex_unlock(&ctx->mutex);
-
-	/*
-	 * perf_event_release_kernel() could've stolen some of our
-	 * child events and still have them on its free_list. In that
-	 * case we must wait for these events to have been freed (in
-	 * particular all their references to this task must've been
-	 * dropped).
-	 *
-	 * Without this copy_process() will unconditionally free this
-	 * task (irrespective of its reference count) and
-	 * _free_event()'s put_task_struct(event->hw.target) will be a
-	 * use-after-free.
-	 *
-	 * Wait for all events to drop their context reference.
-	 */
-	wait_var_event(&ctx->refcount, refcount_read(&ctx->refcount) == 1);
-	put_ctx(ctx); /* must be last */
+	perf_event_exit_task_context(task, false);
 }
 
 void perf_event_delayed_put(struct task_struct *task)
@@ -13980,6 +14211,14 @@ inherit_event(struct perf_event *parent_event,
 	if (parent_event->parent)
 		parent_event = parent_event->parent;
 
+	if (parent_event->state <= PERF_EVENT_STATE_REVOKED)
+		return NULL;
+
+	/*
+	 * Event creation should be under SRCU, see perf_pmu_unregister().
+	 */
+	guard(srcu)(&pmus_srcu);
+
 	child_event = perf_event_alloc(&parent_event->attr,
 					   parent_event->cpu,
 					   child,
diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index 5130b119d0ae..d2aef87c7e9f 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -679,7 +679,15 @@ int rb_alloc_aux(struct perf_buffer *rb, struct perf_event *event,
 {
 	bool overwrite = !(flags & RING_BUFFER_WRITABLE);
 	int node = (event->cpu == -1) ? -1 : cpu_to_node(event->cpu);
-	int ret = -ENOMEM, max_order;
+	bool use_contiguous_pages = event->pmu->capabilities & (
+		PERF_PMU_CAP_AUX_NO_SG | PERF_PMU_CAP_AUX_PREFER_LARGE);
+	/*
+	 * Initialize max_order to 0 for page allocation. This allocates single
+	 * pages to minimize memory fragmentation. This is overridden if the
+	 * PMU needs or prefers contiguous pages (use_contiguous_pages = true).
+	 */
+	int max_order = 0;
+	int ret = -ENOMEM;
 
 	if (!has_aux(event))
 		return -EOPNOTSUPP;
@@ -689,8 +697,8 @@ int rb_alloc_aux(struct perf_buffer *rb, struct perf_event *event,
 
 	if (!overwrite) {
 		/*
-		 * Watermark defaults to half the buffer, and so does the
-		 * max_order, to aid PMU drivers in double buffering.
+		 * Watermark defaults to half the buffer, to aid PMU drivers
+		 * in double buffering.
 		 */
 		if (!watermark)
 			watermark = min_t(unsigned long,
@@ -698,16 +706,19 @@ int rb_alloc_aux(struct perf_buffer *rb, struct perf_event *event,
 					  (unsigned long)nr_pages << (PAGE_SHIFT - 1));
 
 		/*
-		 * Use aux_watermark as the basis for chunking to
-		 * help PMU drivers honor the watermark.
+		 * If using contiguous pages, use aux_watermark as the basis
+		 * for chunking to help PMU drivers honor the watermark.
 		 */
-		max_order = get_order(watermark);
+		if (use_contiguous_pages)
+			max_order = get_order(watermark);
 	} else {
 		/*
-		 * We need to start with the max_order that fits in nr_pages,
-		 * not the other way around, hence ilog2() and not get_order.
+		 * If using contiguous pages, we need to start with the
+		 * max_order that fits in nr_pages, not the other way around,
+		 * hence ilog2() and not get_order.
 		 */
-		max_order = ilog2(nr_pages);
+		if (use_contiguous_pages)
+			max_order = ilog2(nr_pages);
 		watermark = 0;
 	}
 
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index 8d783b5882b6..4c965ba77f9f 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -29,6 +29,7 @@
 #include <linux/workqueue.h>
 #include <linux/srcu.h>
 #include <linux/oom.h>          /* check_stable_address_space */
+#include <linux/pagewalk.h>
 
 #include <linux/uprobes.h>
 
@@ -152,91 +153,6 @@ static loff_t vaddr_to_offset(struct vm_area_struct *vma, unsigned long vaddr)
 }
 
 /**
- * __replace_page - replace page in vma by new page.
- * based on replace_page in mm/ksm.c
- *
- * @vma:      vma that holds the pte pointing to page
- * @addr:     address the old @page is mapped at
- * @old_page: the page we are replacing by new_page
- * @new_page: the modified page we replace page by
- *
- * If @new_page is NULL, only unmap @old_page.
- *
- * Returns 0 on success, negative error code otherwise.
- */
-static int __replace_page(struct vm_area_struct *vma, unsigned long addr,
-				struct page *old_page, struct page *new_page)
-{
-	struct folio *old_folio = page_folio(old_page);
-	struct folio *new_folio;
-	struct mm_struct *mm = vma->vm_mm;
-	DEFINE_FOLIO_VMA_WALK(pvmw, old_folio, vma, addr, 0);
-	int err;
-	struct mmu_notifier_range range;
-	pte_t pte;
-
-	mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, addr,
-				addr + PAGE_SIZE);
-
-	if (new_page) {
-		new_folio = page_folio(new_page);
-		err = mem_cgroup_charge(new_folio, vma->vm_mm, GFP_KERNEL);
-		if (err)
-			return err;
-	}
-
-	/* For folio_free_swap() below */
-	folio_lock(old_folio);
-
-	mmu_notifier_invalidate_range_start(&range);
-	err = -EAGAIN;
-	if (!page_vma_mapped_walk(&pvmw))
-		goto unlock;
-	VM_BUG_ON_PAGE(addr != pvmw.address, old_page);
-	pte = ptep_get(pvmw.pte);
-
-	/*
-	 * Handle PFN swap PTES, such as device-exclusive ones, that actually
-	 * map pages: simply trigger GUP again to fix it up.
-	 */
-	if (unlikely(!pte_present(pte))) {
-		page_vma_mapped_walk_done(&pvmw);
-		goto unlock;
-	}
-
-	if (new_page) {
-		folio_get(new_folio);
-		folio_add_new_anon_rmap(new_folio, vma, addr, RMAP_EXCLUSIVE);
-		folio_add_lru_vma(new_folio, vma);
-	} else
-		/* no new page, just dec_mm_counter for old_page */
-		dec_mm_counter(mm, MM_ANONPAGES);
-
-	if (!folio_test_anon(old_folio)) {
-		dec_mm_counter(mm, mm_counter_file(old_folio));
-		inc_mm_counter(mm, MM_ANONPAGES);
-	}
-
-	flush_cache_page(vma, addr, pte_pfn(pte));
-	ptep_clear_flush(vma, addr, pvmw.pte);
-	if (new_page)
-		set_pte_at(mm, addr, pvmw.pte,
-			   mk_pte(new_page, vma->vm_page_prot));
-
-	folio_remove_rmap_pte(old_folio, old_page, vma);
-	if (!folio_mapped(old_folio))
-		folio_free_swap(old_folio);
-	page_vma_mapped_walk_done(&pvmw);
-	folio_put(old_folio);
-
-	err = 0;
- unlock:
-	mmu_notifier_invalidate_range_end(&range);
-	folio_unlock(old_folio);
-	return err;
-}
-
-/**
  * is_swbp_insn - check if instruction is breakpoint instruction.
  * @insn: instruction to be checked.
  * Default implementation of is_swbp_insn
@@ -463,6 +379,95 @@ static int update_ref_ctr(struct uprobe *uprobe, struct mm_struct *mm,
 	return ret;
 }
 
+static bool orig_page_is_identical(struct vm_area_struct *vma,
+		unsigned long vaddr, struct page *page, bool *pmd_mappable)
+{
+	const pgoff_t index = vaddr_to_offset(vma, vaddr) >> PAGE_SHIFT;
+	struct folio *orig_folio = filemap_get_folio(vma->vm_file->f_mapping,
+						    index);
+	struct page *orig_page;
+	bool identical;
+
+	if (IS_ERR(orig_folio))
+		return false;
+	orig_page = folio_file_page(orig_folio, index);
+
+	*pmd_mappable = folio_test_pmd_mappable(orig_folio);
+	identical = folio_test_uptodate(orig_folio) &&
+		    pages_identical(page, orig_page);
+	folio_put(orig_folio);
+	return identical;
+}
+
+static int __uprobe_write_opcode(struct vm_area_struct *vma,
+		struct folio_walk *fw, struct folio *folio,
+		unsigned long opcode_vaddr, uprobe_opcode_t opcode)
+{
+	const unsigned long vaddr = opcode_vaddr & PAGE_MASK;
+	const bool is_register = !!is_swbp_insn(&opcode);
+	bool pmd_mappable;
+
+	/* For now, we'll only handle PTE-mapped folios. */
+	if (fw->level != FW_LEVEL_PTE)
+		return -EFAULT;
+
+	/*
+	 * See can_follow_write_pte(): we'd actually prefer a writable PTE here,
+	 * but the VMA might not be writable.
+	 */
+	if (!pte_write(fw->pte)) {
+		if (!PageAnonExclusive(fw->page))
+			return -EFAULT;
+		if (unlikely(userfaultfd_pte_wp(vma, fw->pte)))
+			return -EFAULT;
+		/* SOFTDIRTY is handled via pte_mkdirty() below. */
+	}
+
+	/*
+	 * We'll temporarily unmap the page and flush the TLB, such that we can
+	 * modify the page atomically.
+	 */
+	flush_cache_page(vma, vaddr, pte_pfn(fw->pte));
+	fw->pte = ptep_clear_flush(vma, vaddr, fw->ptep);
+	copy_to_page(fw->page, opcode_vaddr, &opcode, UPROBE_SWBP_INSN_SIZE);
+
+	/*
+	 * When unregistering, we may only zap a PTE if uffd is disabled and
+	 * there are no unexpected folio references ...
+	 */
+	if (is_register || userfaultfd_missing(vma) ||
+	    (folio_ref_count(folio) != folio_mapcount(folio) + 1 +
+	     folio_test_swapcache(folio) * folio_nr_pages(folio)))
+		goto remap;
+
+	/*
+	 * ... and the mapped page is identical to the original page that
+	 * would get faulted in on next access.
+	 */
+	if (!orig_page_is_identical(vma, vaddr, fw->page, &pmd_mappable))
+		goto remap;
+
+	dec_mm_counter(vma->vm_mm, MM_ANONPAGES);
+	folio_remove_rmap_pte(folio, fw->page, vma);
+	if (!folio_mapped(folio) && folio_test_swapcache(folio) &&
+	     folio_trylock(folio)) {
+		folio_free_swap(folio);
+		folio_unlock(folio);
+	}
+	folio_put(folio);
+
+	return pmd_mappable;
+remap:
+	/*
+	 * Make sure that our copy_to_page() changes become visible before the
+	 * set_pte_at() write.
+	 */
+	smp_wmb();
+	/* We modified the page. Make sure to mark the PTE dirty. */
+	set_pte_at(vma->vm_mm, vaddr, fw->ptep, pte_mkdirty(fw->pte));
+	return 0;
+}
+
 /*
  * NOTE:
  * Expect the breakpoint instruction to be the smallest size instruction for
@@ -474,146 +479,146 @@ static int update_ref_ctr(struct uprobe *uprobe, struct mm_struct *mm,
  *
  * uprobe_write_opcode - write the opcode at a given virtual address.
  * @auprobe: arch specific probepoint information.
- * @mm: the probed process address space.
- * @vaddr: the virtual address to store the opcode.
- * @opcode: opcode to be written at @vaddr.
+ * @vma: the probed virtual memory area.
+ * @opcode_vaddr: the virtual address to store the opcode.
+ * @opcode: opcode to be written at @opcode_vaddr.
  *
  * Called with mm->mmap_lock held for read or write.
  * Return 0 (success) or a negative errno.
  */
-int uprobe_write_opcode(struct arch_uprobe *auprobe, struct mm_struct *mm,
-			unsigned long vaddr, uprobe_opcode_t opcode)
+int uprobe_write_opcode(struct arch_uprobe *auprobe, struct vm_area_struct *vma,
+		const unsigned long opcode_vaddr, uprobe_opcode_t opcode)
 {
+	const unsigned long vaddr = opcode_vaddr & PAGE_MASK;
+	struct mm_struct *mm = vma->vm_mm;
 	struct uprobe *uprobe;
-	struct page *old_page, *new_page;
-	struct vm_area_struct *vma;
 	int ret, is_register, ref_ctr_updated = 0;
-	bool orig_page_huge = false;
 	unsigned int gup_flags = FOLL_FORCE;
+	struct mmu_notifier_range range;
+	struct folio_walk fw;
+	struct folio *folio;
+	struct page *page;
 
 	is_register = is_swbp_insn(&opcode);
 	uprobe = container_of(auprobe, struct uprobe, arch);
 
-retry:
+	if (WARN_ON_ONCE(!is_cow_mapping(vma->vm_flags)))
+		return -EINVAL;
+
+	/*
+	 * When registering, we have to break COW to get an exclusive anonymous
+	 * page that we can safely modify. Use FOLL_WRITE to trigger a write
+	 * fault if required. When unregistering, we might be lucky and the
+	 * anon page is already gone. So defer write faults until really
+	 * required. Use FOLL_SPLIT_PMD, because __uprobe_write_opcode()
+	 * cannot deal with PMDs yet.
+	 */
 	if (is_register)
-		gup_flags |= FOLL_SPLIT_PMD;
-	/* Read the page with vaddr into memory */
-	old_page = get_user_page_vma_remote(mm, vaddr, gup_flags, &vma);
-	if (IS_ERR(old_page))
-		return PTR_ERR(old_page);
+		gup_flags |= FOLL_WRITE | FOLL_SPLIT_PMD;
 
-	ret = verify_opcode(old_page, vaddr, &opcode);
+retry:
+	ret = get_user_pages_remote(mm, vaddr, 1, gup_flags, &page, NULL);
 	if (ret <= 0)
-		goto put_old;
-
-	if (is_zero_page(old_page)) {
-		ret = -EINVAL;
-		goto put_old;
-	}
+		goto out;
+	folio = page_folio(page);
 
-	if (WARN(!is_register && PageCompound(old_page),
-		 "uprobe unregister should never work on compound page\n")) {
-		ret = -EINVAL;
-		goto put_old;
+	ret = verify_opcode(page, opcode_vaddr, &opcode);
+	if (ret <= 0) {
+		folio_put(folio);
+		goto out;
 	}
 
 	/* We are going to replace instruction, update ref_ctr. */
 	if (!ref_ctr_updated && uprobe->ref_ctr_offset) {
 		ret = update_ref_ctr(uprobe, mm, is_register ? 1 : -1);
-		if (ret)
-			goto put_old;
+		if (ret) {
+			folio_put(folio);
+			goto out;
+		}
 
 		ref_ctr_updated = 1;
 	}
 
 	ret = 0;
-	if (!is_register && !PageAnon(old_page))
-		goto put_old;
-
-	ret = anon_vma_prepare(vma);
-	if (ret)
-		goto put_old;
-
-	ret = -ENOMEM;
-	new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, vaddr);
-	if (!new_page)
-		goto put_old;
-
-	__SetPageUptodate(new_page);
-	copy_highpage(new_page, old_page);
-	copy_to_page(new_page, vaddr, &opcode, UPROBE_SWBP_INSN_SIZE);
+	if (unlikely(!folio_test_anon(folio))) {
+		VM_WARN_ON_ONCE(is_register);
+		folio_put(folio);
+		goto out;
+	}
 
 	if (!is_register) {
-		struct page *orig_page;
-		pgoff_t index;
-
-		VM_BUG_ON_PAGE(!PageAnon(old_page), old_page);
-
-		index = vaddr_to_offset(vma, vaddr & PAGE_MASK) >> PAGE_SHIFT;
-		orig_page = find_get_page(vma->vm_file->f_inode->i_mapping,
-					  index);
-
-		if (orig_page) {
-			if (PageUptodate(orig_page) &&
-			    pages_identical(new_page, orig_page)) {
-				/* let go new_page */
-				put_page(new_page);
-				new_page = NULL;
-
-				if (PageCompound(orig_page))
-					orig_page_huge = true;
-			}
-			put_page(orig_page);
-		}
+		/*
+		 * In the common case, we'll be able to zap the page when
+		 * unregistering. So trigger MMU notifiers now, as we won't
+		 * be able to do it under PTL.
+		 */
+		mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm,
+					vaddr, vaddr + PAGE_SIZE);
+		mmu_notifier_invalidate_range_start(&range);
 	}
 
-	ret = __replace_page(vma, vaddr & PAGE_MASK, old_page, new_page);
-	if (new_page)
-		put_page(new_page);
-put_old:
-	put_page(old_page);
+	ret = -EAGAIN;
+	/* Walk the page tables again, to perform the actual update. */
+	if (folio_walk_start(&fw, vma, vaddr, 0)) {
+		if (fw.page == page)
+			ret = __uprobe_write_opcode(vma, &fw, folio, opcode_vaddr, opcode);
+		folio_walk_end(&fw, vma);
+	}
+
+	if (!is_register)
+		mmu_notifier_invalidate_range_end(&range);
 
-	if (unlikely(ret == -EAGAIN))
+	folio_put(folio);
+	switch (ret) {
+	case -EFAULT:
+		gup_flags |= FOLL_WRITE | FOLL_SPLIT_PMD;
+		fallthrough;
+	case -EAGAIN:
 		goto retry;
+	default:
+		break;
+	}
 
+out:
 	/* Revert back reference counter if instruction update failed. */
-	if (ret && is_register && ref_ctr_updated)
+	if (ret < 0 && is_register && ref_ctr_updated)
 		update_ref_ctr(uprobe, mm, -1);
 
 	/* try collapse pmd for compound page */
-	if (!ret && orig_page_huge)
+	if (ret > 0)
 		collapse_pte_mapped_thp(mm, vaddr, false);
 
-	return ret;
+	return ret < 0 ? ret : 0;
 }
 
 /**
  * set_swbp - store breakpoint at a given address.
  * @auprobe: arch specific probepoint information.
- * @mm: the probed process address space.
+ * @vma: the probed virtual memory area.
  * @vaddr: the virtual address to insert the opcode.
  *
  * For mm @mm, store the breakpoint instruction at @vaddr.
  * Return 0 (success) or a negative errno.
  */
-int __weak set_swbp(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long vaddr)
+int __weak set_swbp(struct arch_uprobe *auprobe, struct vm_area_struct *vma,
+		unsigned long vaddr)
 {
-	return uprobe_write_opcode(auprobe, mm, vaddr, UPROBE_SWBP_INSN);
+	return uprobe_write_opcode(auprobe, vma, vaddr, UPROBE_SWBP_INSN);
 }
 
 /**
  * set_orig_insn - Restore the original instruction.
- * @mm: the probed process address space.
+ * @vma: the probed virtual memory area.
  * @auprobe: arch specific probepoint information.
  * @vaddr: the virtual address to insert the opcode.
  *
  * For mm @mm, restore the original opcode (opcode) at @vaddr.
  * Return 0 (success) or a negative errno.
  */
-int __weak
-set_orig_insn(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long vaddr)
+int __weak set_orig_insn(struct arch_uprobe *auprobe,
+		struct vm_area_struct *vma, unsigned long vaddr)
 {
-	return uprobe_write_opcode(auprobe, mm, vaddr,
+	return uprobe_write_opcode(auprobe, vma, vaddr,
 			*(uprobe_opcode_t *)&auprobe->insn);
 }
 
@@ -1134,10 +1139,10 @@ static bool filter_chain(struct uprobe *uprobe, struct mm_struct *mm)
 	return ret;
 }
 
-static int
-install_breakpoint(struct uprobe *uprobe, struct mm_struct *mm,
-			struct vm_area_struct *vma, unsigned long vaddr)
+static int install_breakpoint(struct uprobe *uprobe, struct vm_area_struct *vma,
+		unsigned long vaddr)
 {
+	struct mm_struct *mm = vma->vm_mm;
 	bool first_uprobe;
 	int ret;
 
@@ -1153,7 +1158,7 @@ install_breakpoint(struct uprobe *uprobe, struct mm_struct *mm,
 	if (first_uprobe)
 		set_bit(MMF_HAS_UPROBES, &mm->flags);
 
-	ret = set_swbp(&uprobe->arch, mm, vaddr);
+	ret = set_swbp(&uprobe->arch, vma, vaddr);
 	if (!ret)
 		clear_bit(MMF_RECALC_UPROBES, &mm->flags);
 	else if (first_uprobe)
@@ -1162,11 +1167,13 @@ install_breakpoint(struct uprobe *uprobe, struct mm_struct *mm,
 	return ret;
 }
 
-static int
-remove_breakpoint(struct uprobe *uprobe, struct mm_struct *mm, unsigned long vaddr)
+static int remove_breakpoint(struct uprobe *uprobe, struct vm_area_struct *vma,
+		unsigned long vaddr)
 {
+	struct mm_struct *mm = vma->vm_mm;
+
 	set_bit(MMF_RECALC_UPROBES, &mm->flags);
-	return set_orig_insn(&uprobe->arch, mm, vaddr);
+	return set_orig_insn(&uprobe->arch, vma, vaddr);
 }
 
 struct map_info {
@@ -1296,10 +1303,10 @@ register_for_each_vma(struct uprobe *uprobe, struct uprobe_consumer *new)
 		if (is_register) {
 			/* consult only the "caller", new consumer. */
 			if (consumer_filter(new, mm))
-				err = install_breakpoint(uprobe, mm, vma, info->vaddr);
+				err = install_breakpoint(uprobe, vma, info->vaddr);
 		} else if (test_bit(MMF_HAS_UPROBES, &mm->flags)) {
 			if (!filter_chain(uprobe, mm))
-				err |= remove_breakpoint(uprobe, mm, info->vaddr);
+				err |= remove_breakpoint(uprobe, vma, info->vaddr);
 		}
 
  unlock:
@@ -1472,7 +1479,7 @@ static int unapply_uprobe(struct uprobe *uprobe, struct mm_struct *mm)
 			continue;
 
 		vaddr = offset_to_vaddr(vma, uprobe->offset);
-		err |= remove_breakpoint(uprobe, mm, vaddr);
+		err |= remove_breakpoint(uprobe, vma, vaddr);
 	}
 	mmap_read_unlock(mm);
 
@@ -1610,7 +1617,7 @@ int uprobe_mmap(struct vm_area_struct *vma)
 		if (!fatal_signal_pending(current) &&
 		    filter_chain(uprobe, vma->vm_mm)) {
 			unsigned long vaddr = offset_to_vaddr(vma, uprobe->offset);
-			install_breakpoint(uprobe, vma->vm_mm, vma, vaddr);
+			install_breakpoint(uprobe, vma, vaddr);
 		}
 		put_uprobe(uprobe);
 	}
diff --git a/kernel/exit.c b/kernel/exit.c
index 1b51dc099f1e..bd743900354c 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -133,8 +133,13 @@ struct release_task_post {
 static void __unhash_process(struct release_task_post *post, struct task_struct *p,
 			     bool group_dead)
 {
+	struct pid *pid = task_pid(p);
+
 	nr_threads--;
+
 	detach_pid(post->pids, p, PIDTYPE_PID);
+	wake_up_all(&pid->wait_pidfd);
+
 	if (group_dead) {
 		detach_pid(post->pids, p, PIDTYPE_TGID);
 		detach_pid(post->pids, p, PIDTYPE_PGID);
@@ -253,7 +258,8 @@ repeat:
 	pidfs_exit(p);
 	cgroup_release(p);
 
-	thread_pid = get_pid(p->thread_pid);
+	/* Retrieve @thread_pid before __unhash_process() may set it to NULL. */
+	thread_pid = task_pid(p);
 
 	write_lock_irq(&tasklist_lock);
 	ptrace_release_task(p);
@@ -282,8 +288,8 @@ repeat:
 	}
 
 	write_unlock_irq(&tasklist_lock);
+	/* @thread_pid can't go away until free_pids() below */
 	proc_flush_pid(thread_pid);
-	put_pid(thread_pid);
 	add_device_randomness(&p->se.sum_exec_runtime,
 			      sizeof(p->se.sum_exec_runtime));
 	free_pids(post.pids);
@@ -415,44 +421,30 @@ kill_orphaned_pgrp(struct task_struct *tsk, struct task_struct *parent)
 	}
 }
 
-static void coredump_task_exit(struct task_struct *tsk)
+static void coredump_task_exit(struct task_struct *tsk,
+			       struct core_state *core_state)
 {
-	struct core_state *core_state;
+	struct core_thread self;
 
+	self.task = tsk;
+	if (self.task->flags & PF_SIGNALED)
+		self.next = xchg(&core_state->dumper.next, &self);
+	else
+		self.task = NULL;
 	/*
-	 * Serialize with any possible pending coredump.
-	 * We must hold siglock around checking core_state
-	 * and setting PF_POSTCOREDUMP.  The core-inducing thread
-	 * will increment ->nr_threads for each thread in the
-	 * group without PF_POSTCOREDUMP set.
+	 * Implies mb(), the result of xchg() must be visible
+	 * to core_state->dumper.
 	 */
-	spin_lock_irq(&tsk->sighand->siglock);
-	tsk->flags |= PF_POSTCOREDUMP;
-	core_state = tsk->signal->core_state;
-	spin_unlock_irq(&tsk->sighand->siglock);
-	if (core_state) {
-		struct core_thread self;
-
-		self.task = current;
-		if (self.task->flags & PF_SIGNALED)
-			self.next = xchg(&core_state->dumper.next, &self);
-		else
-			self.task = NULL;
-		/*
-		 * Implies mb(), the result of xchg() must be visible
-		 * to core_state->dumper.
-		 */
-		if (atomic_dec_and_test(&core_state->nr_threads))
-			complete(&core_state->startup);
+	if (atomic_dec_and_test(&core_state->nr_threads))
+		complete(&core_state->startup);
 
-		for (;;) {
-			set_current_state(TASK_IDLE|TASK_FREEZABLE);
-			if (!self.task) /* see coredump_finish() */
-				break;
-			schedule();
-		}
-		__set_current_state(TASK_RUNNING);
+	for (;;) {
+		set_current_state(TASK_IDLE|TASK_FREEZABLE);
+		if (!self.task) /* see coredump_finish() */
+			break;
+		schedule();
 	}
+	__set_current_state(TASK_RUNNING);
 }
 
 #ifdef CONFIG_MEMCG
@@ -876,6 +868,7 @@ static void synchronize_group_exit(struct task_struct *tsk, long code)
 {
 	struct sighand_struct *sighand = tsk->sighand;
 	struct signal_struct *signal = tsk->signal;
+	struct core_state *core_state;
 
 	spin_lock_irq(&sighand->siglock);
 	signal->quick_threads--;
@@ -885,7 +878,19 @@ static void synchronize_group_exit(struct task_struct *tsk, long code)
 		signal->group_exit_code = code;
 		signal->group_stop_count = 0;
 	}
+	/*
+	 * Serialize with any possible pending coredump.
+	 * We must hold siglock around checking core_state
+	 * and setting PF_POSTCOREDUMP.  The core-inducing thread
+	 * will increment ->nr_threads for each thread in the
+	 * group without PF_POSTCOREDUMP set.
+	 */
+	tsk->flags |= PF_POSTCOREDUMP;
+	core_state = signal->core_state;
 	spin_unlock_irq(&sighand->siglock);
+
+	if (unlikely(core_state))
+		coredump_task_exit(tsk, core_state);
 }
 
 void __noreturn do_exit(long code)
@@ -894,15 +899,12 @@ void __noreturn do_exit(long code)
 	int group_dead;
 
 	WARN_ON(irqs_disabled());
-
-	synchronize_group_exit(tsk, code);
-
 	WARN_ON(tsk->plug);
 
 	kcov_task_exit(tsk);
 	kmsan_task_exit(tsk);
 
-	coredump_task_exit(tsk);
+	synchronize_group_exit(tsk, code);
 	ptrace_event(PTRACE_EVENT_EXIT, code);
 	user_events_exit(tsk);
 
@@ -936,12 +938,12 @@ void __noreturn do_exit(long code)
 
 	tsk->exit_code = code;
 	taskstats_exit(tsk, group_dead);
+	trace_sched_process_exit(tsk, group_dead);
 
 	exit_mm();
 
 	if (group_dead)
 		acct_process();
-	trace_sched_process_exit(tsk);
 
 	exit_sem(tsk);
 	exit_shm(tsk);
diff --git a/kernel/fork.c b/kernel/fork.c
index c4b26cd8998b..1ee8eb11f38b 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -112,6 +112,9 @@
 #include <asm/cacheflush.h>
 #include <asm/tlbflush.h>
 
+/* For dup_mmap(). */
+#include "../mm/internal.h"
+
 #include <trace/events/sched.h>
 
 #define CREATE_TRACE_POINTS
@@ -428,92 +431,9 @@ struct kmem_cache *files_cachep;
 /* SLAB cache for fs_struct structures (tsk->fs) */
 struct kmem_cache *fs_cachep;
 
-/* SLAB cache for vm_area_struct structures */
-static struct kmem_cache *vm_area_cachep;
-
 /* SLAB cache for mm_struct structures (tsk->mm) */
 static struct kmem_cache *mm_cachep;
 
-struct vm_area_struct *vm_area_alloc(struct mm_struct *mm)
-{
-	struct vm_area_struct *vma;
-
-	vma = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL);
-	if (!vma)
-		return NULL;
-
-	vma_init(vma, mm);
-
-	return vma;
-}
-
-static void vm_area_init_from(const struct vm_area_struct *src,
-			      struct vm_area_struct *dest)
-{
-	dest->vm_mm = src->vm_mm;
-	dest->vm_ops = src->vm_ops;
-	dest->vm_start = src->vm_start;
-	dest->vm_end = src->vm_end;
-	dest->anon_vma = src->anon_vma;
-	dest->vm_pgoff = src->vm_pgoff;
-	dest->vm_file = src->vm_file;
-	dest->vm_private_data = src->vm_private_data;
-	vm_flags_init(dest, src->vm_flags);
-	memcpy(&dest->vm_page_prot, &src->vm_page_prot,
-	       sizeof(dest->vm_page_prot));
-	/*
-	 * src->shared.rb may be modified concurrently when called from
-	 * dup_mmap(), but the clone will reinitialize it.
-	 */
-	data_race(memcpy(&dest->shared, &src->shared, sizeof(dest->shared)));
-	memcpy(&dest->vm_userfaultfd_ctx, &src->vm_userfaultfd_ctx,
-	       sizeof(dest->vm_userfaultfd_ctx));
-#ifdef CONFIG_ANON_VMA_NAME
-	dest->anon_name = src->anon_name;
-#endif
-#ifdef CONFIG_SWAP
-	memcpy(&dest->swap_readahead_info, &src->swap_readahead_info,
-	       sizeof(dest->swap_readahead_info));
-#endif
-#ifndef CONFIG_MMU
-	dest->vm_region = src->vm_region;
-#endif
-#ifdef CONFIG_NUMA
-	dest->vm_policy = src->vm_policy;
-#endif
-}
-
-struct vm_area_struct *vm_area_dup(struct vm_area_struct *orig)
-{
-	struct vm_area_struct *new = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL);
-
-	if (!new)
-		return NULL;
-
-	ASSERT_EXCLUSIVE_WRITER(orig->vm_flags);
-	ASSERT_EXCLUSIVE_WRITER(orig->vm_file);
-	vm_area_init_from(orig, new);
-	vma_lock_init(new, true);
-	INIT_LIST_HEAD(&new->anon_vma_chain);
-	vma_numab_state_init(new);
-	dup_anon_vma_name(orig, new);
-
-	/* track_pfn_copy() will later take care of copying internal state. */
-	if (unlikely(new->vm_flags & VM_PFNMAP))
-		untrack_pfn_clear(new);
-
-	return new;
-}
-
-void vm_area_free(struct vm_area_struct *vma)
-{
-	/* The vma should be detached while being destroyed. */
-	vma_assert_detached(vma);
-	vma_numab_state_free(vma);
-	free_anon_vma_name(vma);
-	kmem_cache_free(vm_area_cachep, vma);
-}
-
 static void account_kernel_stack(struct task_struct *tsk, int account)
 {
 	if (IS_ENABLED(CONFIG_VMAP_STACK)) {
@@ -593,7 +513,7 @@ void free_task(struct task_struct *tsk)
 }
 EXPORT_SYMBOL(free_task);
 
-static void dup_mm_exe_file(struct mm_struct *mm, struct mm_struct *oldmm)
+void dup_mm_exe_file(struct mm_struct *mm, struct mm_struct *oldmm)
 {
 	struct file *exe_file;
 
@@ -608,178 +528,6 @@ static void dup_mm_exe_file(struct mm_struct *mm, struct mm_struct *oldmm)
 }
 
 #ifdef CONFIG_MMU
-static __latent_entropy int dup_mmap(struct mm_struct *mm,
-					struct mm_struct *oldmm)
-{
-	struct vm_area_struct *mpnt, *tmp;
-	int retval;
-	unsigned long charge = 0;
-	LIST_HEAD(uf);
-	VMA_ITERATOR(vmi, mm, 0);
-
-	if (mmap_write_lock_killable(oldmm))
-		return -EINTR;
-	flush_cache_dup_mm(oldmm);
-	uprobe_dup_mmap(oldmm, mm);
-	/*
-	 * Not linked in yet - no deadlock potential:
-	 */
-	mmap_write_lock_nested(mm, SINGLE_DEPTH_NESTING);
-
-	/* No ordering required: file already has been exposed. */
-	dup_mm_exe_file(mm, oldmm);
-
-	mm->total_vm = oldmm->total_vm;
-	mm->data_vm = oldmm->data_vm;
-	mm->exec_vm = oldmm->exec_vm;
-	mm->stack_vm = oldmm->stack_vm;
-
-	/* Use __mt_dup() to efficiently build an identical maple tree. */
-	retval = __mt_dup(&oldmm->mm_mt, &mm->mm_mt, GFP_KERNEL);
-	if (unlikely(retval))
-		goto out;
-
-	mt_clear_in_rcu(vmi.mas.tree);
-	for_each_vma(vmi, mpnt) {
-		struct file *file;
-
-		vma_start_write(mpnt);
-		if (mpnt->vm_flags & VM_DONTCOPY) {
-			retval = vma_iter_clear_gfp(&vmi, mpnt->vm_start,
-						    mpnt->vm_end, GFP_KERNEL);
-			if (retval)
-				goto loop_out;
-
-			vm_stat_account(mm, mpnt->vm_flags, -vma_pages(mpnt));
-			continue;
-		}
-		charge = 0;
-		/*
-		 * Don't duplicate many vmas if we've been oom-killed (for
-		 * example)
-		 */
-		if (fatal_signal_pending(current)) {
-			retval = -EINTR;
-			goto loop_out;
-		}
-		if (mpnt->vm_flags & VM_ACCOUNT) {
-			unsigned long len = vma_pages(mpnt);
-
-			if (security_vm_enough_memory_mm(oldmm, len)) /* sic */
-				goto fail_nomem;
-			charge = len;
-		}
-		tmp = vm_area_dup(mpnt);
-		if (!tmp)
-			goto fail_nomem;
-		retval = vma_dup_policy(mpnt, tmp);
-		if (retval)
-			goto fail_nomem_policy;
-		tmp->vm_mm = mm;
-		retval = dup_userfaultfd(tmp, &uf);
-		if (retval)
-			goto fail_nomem_anon_vma_fork;
-		if (tmp->vm_flags & VM_WIPEONFORK) {
-			/*
-			 * VM_WIPEONFORK gets a clean slate in the child.
-			 * Don't prepare anon_vma until fault since we don't
-			 * copy page for current vma.
-			 */
-			tmp->anon_vma = NULL;
-		} else if (anon_vma_fork(tmp, mpnt))
-			goto fail_nomem_anon_vma_fork;
-		vm_flags_clear(tmp, VM_LOCKED_MASK);
-		/*
-		 * Copy/update hugetlb private vma information.
-		 */
-		if (is_vm_hugetlb_page(tmp))
-			hugetlb_dup_vma_private(tmp);
-
-		/*
-		 * Link the vma into the MT. After using __mt_dup(), memory
-		 * allocation is not necessary here, so it cannot fail.
-		 */
-		vma_iter_bulk_store(&vmi, tmp);
-
-		mm->map_count++;
-
-		if (tmp->vm_ops && tmp->vm_ops->open)
-			tmp->vm_ops->open(tmp);
-
-		file = tmp->vm_file;
-		if (file) {
-			struct address_space *mapping = file->f_mapping;
-
-			get_file(file);
-			i_mmap_lock_write(mapping);
-			if (vma_is_shared_maywrite(tmp))
-				mapping_allow_writable(mapping);
-			flush_dcache_mmap_lock(mapping);
-			/* insert tmp into the share list, just after mpnt */
-			vma_interval_tree_insert_after(tmp, mpnt,
-					&mapping->i_mmap);
-			flush_dcache_mmap_unlock(mapping);
-			i_mmap_unlock_write(mapping);
-		}
-
-		if (!(tmp->vm_flags & VM_WIPEONFORK))
-			retval = copy_page_range(tmp, mpnt);
-
-		if (retval) {
-			mpnt = vma_next(&vmi);
-			goto loop_out;
-		}
-	}
-	/* a new mm has just been created */
-	retval = arch_dup_mmap(oldmm, mm);
-loop_out:
-	vma_iter_free(&vmi);
-	if (!retval) {
-		mt_set_in_rcu(vmi.mas.tree);
-		ksm_fork(mm, oldmm);
-		khugepaged_fork(mm, oldmm);
-	} else {
-
-		/*
-		 * The entire maple tree has already been duplicated. If the
-		 * mmap duplication fails, mark the failure point with
-		 * XA_ZERO_ENTRY. In exit_mmap(), if this marker is encountered,
-		 * stop releasing VMAs that have not been duplicated after this
-		 * point.
-		 */
-		if (mpnt) {
-			mas_set_range(&vmi.mas, mpnt->vm_start, mpnt->vm_end - 1);
-			mas_store(&vmi.mas, XA_ZERO_ENTRY);
-			/* Avoid OOM iterating a broken tree */
-			set_bit(MMF_OOM_SKIP, &mm->flags);
-		}
-		/*
-		 * The mm_struct is going to exit, but the locks will be dropped
-		 * first.  Set the mm_struct as unstable is advisable as it is
-		 * not fully initialised.
-		 */
-		set_bit(MMF_UNSTABLE, &mm->flags);
-	}
-out:
-	mmap_write_unlock(mm);
-	flush_tlb_mm(oldmm);
-	mmap_write_unlock(oldmm);
-	if (!retval)
-		dup_userfaultfd_complete(&uf);
-	else
-		dup_userfaultfd_fail(&uf);
-	return retval;
-
-fail_nomem_anon_vma_fork:
-	mpol_put(vma_policy(tmp));
-fail_nomem_policy:
-	vm_area_free(tmp);
-fail_nomem:
-	retval = -ENOMEM;
-	vm_unacct_memory(charge);
-	goto loop_out;
-}
-
 static inline int mm_alloc_pgd(struct mm_struct *mm)
 {
 	mm->pgd = pgd_alloc(mm);
@@ -793,13 +541,6 @@ static inline void mm_free_pgd(struct mm_struct *mm)
 	pgd_free(mm, mm->pgd);
 }
 #else
-static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
-{
-	mmap_write_lock(oldmm);
-	dup_mm_exe_file(mm, oldmm);
-	mmap_write_unlock(oldmm);
-	return 0;
-}
 #define mm_alloc_pgd(mm)	(0)
 #define mm_free_pgd(mm)
 #endif /* CONFIG_MMU */
@@ -1305,6 +1046,7 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p,
 	RCU_INIT_POINTER(mm->exe_file, NULL);
 	mmu_notifier_subscriptions_init(mm);
 	init_tlb_flush_pending(mm);
+	futex_mm_init(mm);
 #if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !defined(CONFIG_SPLIT_PMD_PTLOCKS)
 	mm->pmd_huge_pte = NULL;
 #endif
@@ -1387,6 +1129,7 @@ static inline void __mmput(struct mm_struct *mm)
 	if (mm->binfmt)
 		module_put(mm->binfmt->module);
 	lru_gen_del_mm(mm);
+	futex_hash_free(mm);
 	mmdrop(mm);
 }
 
@@ -2036,17 +1779,16 @@ static inline void rcu_copy_process(struct task_struct *p)
 }
 
 /**
- * __pidfd_prepare - allocate a new pidfd_file and reserve a pidfd
+ * pidfd_prepare - allocate a new pidfd_file and reserve a pidfd
  * @pid:   the struct pid for which to create a pidfd
  * @flags: flags of the new @pidfd
- * @ret: Where to return the file for the pidfd.
+ * @ret_file: return the new pidfs file
  *
  * Allocate a new file that stashes @pid and reserve a new pidfd number in the
  * caller's file descriptor table. The pidfd is reserved but not installed yet.
  *
- * The helper doesn't perform checks on @pid which makes it useful for pidfds
- * created via CLONE_PIDFD where @pid has no task attached when the pidfd and
- * pidfd file are prepared.
+ * The helper verifies that @pid is still in use, without PIDFD_THREAD the
+ * task identified by @pid must be a thread-group leader.
  *
  * If this function returns successfully the caller is responsible to either
  * call fd_install() passing the returned pidfd and pidfd file as arguments in
@@ -2063,59 +1805,50 @@ static inline void rcu_copy_process(struct task_struct *p)
  *         error, a negative error code is returned from the function and the
  *         last argument remains unchanged.
  */
-static int __pidfd_prepare(struct pid *pid, unsigned int flags, struct file **ret)
+int pidfd_prepare(struct pid *pid, unsigned int flags, struct file **ret_file)
 {
-	struct file *pidfd_file;
+	struct file *pidfs_file;
+
+	/*
+	 * PIDFD_STALE is only allowed to be passed if the caller knows
+	 * that @pid is already registered in pidfs and thus
+	 * PIDFD_INFO_EXIT information is guaranteed to be available.
+	 */
+	if (!(flags & PIDFD_STALE)) {
+		/*
+		 * While holding the pidfd waitqueue lock removing the
+		 * task linkage for the thread-group leader pid
+		 * (PIDTYPE_TGID) isn't possible. Thus, if there's still
+		 * task linkage for PIDTYPE_PID not having thread-group
+		 * leader linkage for the pid means it wasn't a
+		 * thread-group leader in the first place.
+		 */
+		guard(spinlock_irq)(&pid->wait_pidfd.lock);
+
+		/* Task has already been reaped. */
+		if (!pid_has_task(pid, PIDTYPE_PID))
+			return -ESRCH;
+		/*
+		 * If this struct pid isn't used as a thread-group
+		 * leader but the caller requested to create a
+		 * thread-group leader pidfd then report ENOENT.
+		 */
+		if (!(flags & PIDFD_THREAD) && !pid_has_task(pid, PIDTYPE_TGID))
+			return -ENOENT;
+	}
 
 	CLASS(get_unused_fd, pidfd)(O_CLOEXEC);
 	if (pidfd < 0)
 		return pidfd;
 
-	pidfd_file = pidfs_alloc_file(pid, flags | O_RDWR);
-	if (IS_ERR(pidfd_file))
-		return PTR_ERR(pidfd_file);
+	pidfs_file = pidfs_alloc_file(pid, flags | O_RDWR);
+	if (IS_ERR(pidfs_file))
+		return PTR_ERR(pidfs_file);
 
-	*ret = pidfd_file;
+	*ret_file = pidfs_file;
 	return take_fd(pidfd);
 }
 
-/**
- * pidfd_prepare - allocate a new pidfd_file and reserve a pidfd
- * @pid:   the struct pid for which to create a pidfd
- * @flags: flags of the new @pidfd
- * @ret: Where to return the pidfd.
- *
- * Allocate a new file that stashes @pid and reserve a new pidfd number in the
- * caller's file descriptor table. The pidfd is reserved but not installed yet.
- *
- * The helper verifies that @pid is still in use, without PIDFD_THREAD the
- * task identified by @pid must be a thread-group leader.
- *
- * If this function returns successfully the caller is responsible to either
- * call fd_install() passing the returned pidfd and pidfd file as arguments in
- * order to install the pidfd into its file descriptor table or they must use
- * put_unused_fd() and fput() on the returned pidfd and pidfd file
- * respectively.
- *
- * This function is useful when a pidfd must already be reserved but there
- * might still be points of failure afterwards and the caller wants to ensure
- * that no pidfd is leaked into its file descriptor table.
- *
- * Return: On success, a reserved pidfd is returned from the function and a new
- *         pidfd file is returned in the last argument to the function. On
- *         error, a negative error code is returned from the function and the
- *         last argument remains unchanged.
- */
-int pidfd_prepare(struct pid *pid, unsigned int flags, struct file **ret)
-{
-	bool thread = flags & PIDFD_THREAD;
-
-	if (!pid || !pid_has_task(pid, thread ? PIDTYPE_PID : PIDTYPE_TGID))
-		return -EINVAL;
-
-	return __pidfd_prepare(pid, flags, ret);
-}
-
 static void __delayed_free_task(struct rcu_head *rhp)
 {
 	struct task_struct *tsk = container_of(rhp, struct task_struct, rcu);
@@ -2162,6 +1895,13 @@ static void rv_task_fork(struct task_struct *p)
 #define rv_task_fork(p) do {} while (0)
 #endif
 
+static bool need_futex_hash_allocate_default(u64 clone_flags)
+{
+	if ((clone_flags & (CLONE_THREAD | CLONE_VM)) != (CLONE_THREAD | CLONE_VM))
+		return false;
+	return true;
+}
+
 /*
  * This creates a new process as a copy of the old one,
  * but does not actually start it yet.
@@ -2462,7 +2202,7 @@ __latent_entropy struct task_struct *copy_process(
 		 * Note that no task has been attached to @pid yet indicate
 		 * that via CLONE_PIDFD.
 		 */
-		retval = __pidfd_prepare(pid, flags | PIDFD_CLONE, &pidfile);
+		retval = pidfd_prepare(pid, flags | PIDFD_STALE, &pidfile);
 		if (retval < 0)
 			goto bad_fork_free_pid;
 		pidfd = retval;
@@ -2543,6 +2283,21 @@ __latent_entropy struct task_struct *copy_process(
 		goto bad_fork_cancel_cgroup;
 
 	/*
+	 * Allocate a default futex hash for the user process once the first
+	 * thread spawns.
+	 */
+	if (need_futex_hash_allocate_default(clone_flags)) {
+		retval = futex_hash_allocate_default();
+		if (retval)
+			goto bad_fork_core_free;
+		/*
+		 * If we fail beyond this point we don't free the allocated
+		 * futex hash map. We assume that another thread will be created
+		 * and makes use of it. The hash map will be freed once the main
+		 * thread terminates.
+		 */
+	}
+	/*
 	 * From this point on we must avoid any synchronous user-space
 	 * communication until we take the tasklist-lock. In particular, we do
 	 * not want user-space to be able to predict the process start-time by
@@ -3213,11 +2968,6 @@ void __init mm_cache_init(void)
 
 void __init proc_caches_init(void)
 {
-	struct kmem_cache_args args = {
-		.use_freeptr_offset = true,
-		.freeptr_offset = offsetof(struct vm_area_struct, vm_freeptr),
-	};
-
 	sighand_cachep = kmem_cache_create("sighand_cache",
 			sizeof(struct sighand_struct), 0,
 			SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_TYPESAFE_BY_RCU|
@@ -3234,10 +2984,6 @@ void __init proc_caches_init(void)
 			sizeof(struct fs_struct), 0,
 			SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT,
 			NULL);
-	vm_area_cachep = kmem_cache_create("vm_area_struct",
-			sizeof(struct vm_area_struct), &args,
-			SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_TYPESAFE_BY_RCU|
-			SLAB_ACCOUNT);
 	mmap_init();
 	nsproxy_cache_init();
 }
diff --git a/kernel/futex/core.c b/kernel/futex/core.c
index cca15859a50b..565f9717c6ca 100644
--- a/kernel/futex/core.c
+++ b/kernel/futex/core.c
@@ -36,9 +36,15 @@
 #include <linux/pagemap.h>
 #include <linux/debugfs.h>
 #include <linux/plist.h>
+#include <linux/gfp.h>
+#include <linux/vmalloc.h>
 #include <linux/memblock.h>
 #include <linux/fault-inject.h>
 #include <linux/slab.h>
+#include <linux/prctl.h>
+#include <linux/rcuref.h>
+#include <linux/mempolicy.h>
+#include <linux/mmap_lock.h>
 
 #include "futex.h"
 #include "../locking/rtmutex_common.h"
@@ -49,12 +55,24 @@
  * reside in the same cacheline.
  */
 static struct {
-	struct futex_hash_bucket *queues;
 	unsigned long            hashmask;
+	unsigned int		 hashshift;
+	struct futex_hash_bucket *queues[MAX_NUMNODES];
 } __futex_data __read_mostly __aligned(2*sizeof(long));
-#define futex_queues   (__futex_data.queues)
-#define futex_hashmask (__futex_data.hashmask)
 
+#define futex_hashmask	(__futex_data.hashmask)
+#define futex_hashshift	(__futex_data.hashshift)
+#define futex_queues	(__futex_data.queues)
+
+struct futex_private_hash {
+	rcuref_t	users;
+	unsigned int	hash_mask;
+	struct rcu_head	rcu;
+	void		*mm;
+	bool		custom;
+	bool		immutable;
+	struct futex_hash_bucket queues[];
+};
 
 /*
  * Fault injections for futexes.
@@ -107,21 +125,328 @@ late_initcall(fail_futex_debugfs);
 
 #endif /* CONFIG_FAIL_FUTEX */
 
+static struct futex_hash_bucket *
+__futex_hash(union futex_key *key, struct futex_private_hash *fph);
+
+#ifdef CONFIG_FUTEX_PRIVATE_HASH
+static inline bool futex_key_is_private(union futex_key *key)
+{
+	/*
+	 * Relies on get_futex_key() to set either bit for shared
+	 * futexes -- see comment with union futex_key.
+	 */
+	return !(key->both.offset & (FUT_OFF_INODE | FUT_OFF_MMSHARED));
+}
+
+bool futex_private_hash_get(struct futex_private_hash *fph)
+{
+	if (fph->immutable)
+		return true;
+	return rcuref_get(&fph->users);
+}
+
+void futex_private_hash_put(struct futex_private_hash *fph)
+{
+	/* Ignore return value, last put is verified via rcuref_is_dead() */
+	if (fph->immutable)
+		return;
+	if (rcuref_put(&fph->users))
+		wake_up_var(fph->mm);
+}
+
 /**
- * futex_hash - Return the hash bucket in the global hash
- * @key:	Pointer to the futex key for which the hash is calculated
+ * futex_hash_get - Get an additional reference for the local hash.
+ * @hb:                    ptr to the private local hash.
  *
- * We hash on the keys returned from get_futex_key (see below) and return the
- * corresponding hash bucket in the global hash.
+ * Obtain an additional reference for the already obtained hash bucket. The
+ * caller must already own an reference.
  */
+void futex_hash_get(struct futex_hash_bucket *hb)
+{
+	struct futex_private_hash *fph = hb->priv;
+
+	if (!fph)
+		return;
+	WARN_ON_ONCE(!futex_private_hash_get(fph));
+}
+
+void futex_hash_put(struct futex_hash_bucket *hb)
+{
+	struct futex_private_hash *fph = hb->priv;
+
+	if (!fph)
+		return;
+	futex_private_hash_put(fph);
+}
+
+static struct futex_hash_bucket *
+__futex_hash_private(union futex_key *key, struct futex_private_hash *fph)
+{
+	u32 hash;
+
+	if (!futex_key_is_private(key))
+		return NULL;
+
+	if (!fph)
+		fph = rcu_dereference(key->private.mm->futex_phash);
+	if (!fph || !fph->hash_mask)
+		return NULL;
+
+	hash = jhash2((void *)&key->private.address,
+		      sizeof(key->private.address) / 4,
+		      key->both.offset);
+	return &fph->queues[hash & fph->hash_mask];
+}
+
+static void futex_rehash_private(struct futex_private_hash *old,
+				 struct futex_private_hash *new)
+{
+	struct futex_hash_bucket *hb_old, *hb_new;
+	unsigned int slots = old->hash_mask + 1;
+	unsigned int i;
+
+	for (i = 0; i < slots; i++) {
+		struct futex_q *this, *tmp;
+
+		hb_old = &old->queues[i];
+
+		spin_lock(&hb_old->lock);
+		plist_for_each_entry_safe(this, tmp, &hb_old->chain, list) {
+
+			plist_del(&this->list, &hb_old->chain);
+			futex_hb_waiters_dec(hb_old);
+
+			WARN_ON_ONCE(this->lock_ptr != &hb_old->lock);
+
+			hb_new = __futex_hash(&this->key, new);
+			futex_hb_waiters_inc(hb_new);
+			/*
+			 * The new pointer isn't published yet but an already
+			 * moved user can be unqueued due to timeout or signal.
+			 */
+			spin_lock_nested(&hb_new->lock, SINGLE_DEPTH_NESTING);
+			plist_add(&this->list, &hb_new->chain);
+			this->lock_ptr = &hb_new->lock;
+			spin_unlock(&hb_new->lock);
+		}
+		spin_unlock(&hb_old->lock);
+	}
+}
+
+static bool __futex_pivot_hash(struct mm_struct *mm,
+			       struct futex_private_hash *new)
+{
+	struct futex_private_hash *fph;
+
+	WARN_ON_ONCE(mm->futex_phash_new);
+
+	fph = rcu_dereference_protected(mm->futex_phash,
+					lockdep_is_held(&mm->futex_hash_lock));
+	if (fph) {
+		if (!rcuref_is_dead(&fph->users)) {
+			mm->futex_phash_new = new;
+			return false;
+		}
+
+		futex_rehash_private(fph, new);
+	}
+	rcu_assign_pointer(mm->futex_phash, new);
+	kvfree_rcu(fph, rcu);
+	return true;
+}
+
+static void futex_pivot_hash(struct mm_struct *mm)
+{
+	scoped_guard(mutex, &mm->futex_hash_lock) {
+		struct futex_private_hash *fph;
+
+		fph = mm->futex_phash_new;
+		if (fph) {
+			mm->futex_phash_new = NULL;
+			__futex_pivot_hash(mm, fph);
+		}
+	}
+}
+
+struct futex_private_hash *futex_private_hash(void)
+{
+	struct mm_struct *mm = current->mm;
+	/*
+	 * Ideally we don't loop. If there is a replacement in progress
+	 * then a new private hash is already prepared and a reference can't be
+	 * obtained once the last user dropped it's.
+	 * In that case we block on mm_struct::futex_hash_lock and either have
+	 * to perform the replacement or wait while someone else is doing the
+	 * job. Eitherway, on the second iteration we acquire a reference on the
+	 * new private hash or loop again because a new replacement has been
+	 * requested.
+	 */
+again:
+	scoped_guard(rcu) {
+		struct futex_private_hash *fph;
+
+		fph = rcu_dereference(mm->futex_phash);
+		if (!fph)
+			return NULL;
+
+		if (fph->immutable)
+			return fph;
+		if (rcuref_get(&fph->users))
+			return fph;
+	}
+	futex_pivot_hash(mm);
+	goto again;
+}
+
 struct futex_hash_bucket *futex_hash(union futex_key *key)
 {
-	u32 hash = jhash2((u32 *)key, offsetof(typeof(*key), both.offset) / 4,
-			  key->both.offset);
+	struct futex_private_hash *fph;
+	struct futex_hash_bucket *hb;
+
+again:
+	scoped_guard(rcu) {
+		hb = __futex_hash(key, NULL);
+		fph = hb->priv;
+
+		if (!fph || futex_private_hash_get(fph))
+			return hb;
+	}
+	futex_pivot_hash(key->private.mm);
+	goto again;
+}
+
+#else /* !CONFIG_FUTEX_PRIVATE_HASH */
+
+static struct futex_hash_bucket *
+__futex_hash_private(union futex_key *key, struct futex_private_hash *fph)
+{
+	return NULL;
+}
+
+struct futex_hash_bucket *futex_hash(union futex_key *key)
+{
+	return __futex_hash(key, NULL);
+}
+
+#endif /* CONFIG_FUTEX_PRIVATE_HASH */
+
+#ifdef CONFIG_FUTEX_MPOL
+
+static int __futex_key_to_node(struct mm_struct *mm, unsigned long addr)
+{
+	struct vm_area_struct *vma = vma_lookup(mm, addr);
+	struct mempolicy *mpol;
+	int node = FUTEX_NO_NODE;
+
+	if (!vma)
+		return FUTEX_NO_NODE;
+
+	mpol = vma_policy(vma);
+	if (!mpol)
+		return FUTEX_NO_NODE;
+
+	switch (mpol->mode) {
+	case MPOL_PREFERRED:
+		node = first_node(mpol->nodes);
+		break;
+	case MPOL_PREFERRED_MANY:
+	case MPOL_BIND:
+		if (mpol->home_node != NUMA_NO_NODE)
+			node = mpol->home_node;
+		break;
+	default:
+		break;
+	}
+
+	return node;
+}
+
+static int futex_key_to_node_opt(struct mm_struct *mm, unsigned long addr)
+{
+	int seq, node;
+
+	guard(rcu)();
+
+	if (!mmap_lock_speculate_try_begin(mm, &seq))
+		return -EBUSY;
+
+	node = __futex_key_to_node(mm, addr);
+
+	if (mmap_lock_speculate_retry(mm, seq))
+		return -EAGAIN;
+
+	return node;
+}
+
+static int futex_mpol(struct mm_struct *mm, unsigned long addr)
+{
+	int node;
+
+	node = futex_key_to_node_opt(mm, addr);
+	if (node >= FUTEX_NO_NODE)
+		return node;
 
-	return &futex_queues[hash & futex_hashmask];
+	guard(mmap_read_lock)(mm);
+	return __futex_key_to_node(mm, addr);
 }
 
+#else /* !CONFIG_FUTEX_MPOL */
+
+static int futex_mpol(struct mm_struct *mm, unsigned long addr)
+{
+	return FUTEX_NO_NODE;
+}
+
+#endif /* CONFIG_FUTEX_MPOL */
+
+/**
+ * __futex_hash - Return the hash bucket
+ * @key:	Pointer to the futex key for which the hash is calculated
+ * @fph:	Pointer to private hash if known
+ *
+ * We hash on the keys returned from get_futex_key (see below) and return the
+ * corresponding hash bucket.
+ * If the FUTEX is PROCESS_PRIVATE then a per-process hash bucket (from the
+ * private hash) is returned if existing. Otherwise a hash bucket from the
+ * global hash is returned.
+ */
+static struct futex_hash_bucket *
+__futex_hash(union futex_key *key, struct futex_private_hash *fph)
+{
+	int node = key->both.node;
+	u32 hash;
+
+	if (node == FUTEX_NO_NODE) {
+		struct futex_hash_bucket *hb;
+
+		hb = __futex_hash_private(key, fph);
+		if (hb)
+			return hb;
+	}
+
+	hash = jhash2((u32 *)key,
+		      offsetof(typeof(*key), both.offset) / sizeof(u32),
+		      key->both.offset);
+
+	if (node == FUTEX_NO_NODE) {
+		/*
+		 * In case of !FLAGS_NUMA, use some unused hash bits to pick a
+		 * node -- this ensures regular futexes are interleaved across
+		 * the nodes and avoids having to allocate multiple
+		 * hash-tables.
+		 *
+		 * NOTE: this isn't perfectly uniform, but it is fast and
+		 * handles sparse node masks.
+		 */
+		node = (hash >> futex_hashshift) % nr_node_ids;
+		if (!node_possible(node)) {
+			node = find_next_bit_wrap(node_possible_map.bits,
+						  nr_node_ids, node);
+		}
+	}
+
+	return &futex_queues[node][hash & futex_hashmask];
+}
 
 /**
  * futex_setup_timer - set up the sleeping hrtimer.
@@ -206,7 +531,7 @@ static u64 get_inode_sequence_number(struct inode *inode)
  *
  * For shared mappings (when @fshared), the key is:
  *
- *   ( inode->i_sequence, page->index, offset_within_page )
+ *   ( inode->i_sequence, page offset within mapping, offset_within_page )
  *
  * [ also see get_inode_sequence_number() ]
  *
@@ -227,25 +552,60 @@ int get_futex_key(u32 __user *uaddr, unsigned int flags, union futex_key *key,
 	struct page *page;
 	struct folio *folio;
 	struct address_space *mapping;
-	int err, ro = 0;
+	int node, err, size, ro = 0;
+	bool node_updated = false;
 	bool fshared;
 
 	fshared = flags & FLAGS_SHARED;
+	size = futex_size(flags);
+	if (flags & FLAGS_NUMA)
+		size *= 2;
 
 	/*
 	 * The futex address must be "naturally" aligned.
 	 */
 	key->both.offset = address % PAGE_SIZE;
-	if (unlikely((address % sizeof(u32)) != 0))
+	if (unlikely((address % size) != 0))
 		return -EINVAL;
 	address -= key->both.offset;
 
-	if (unlikely(!access_ok(uaddr, sizeof(u32))))
+	if (unlikely(!access_ok(uaddr, size)))
 		return -EFAULT;
 
 	if (unlikely(should_fail_futex(fshared)))
 		return -EFAULT;
 
+	node = FUTEX_NO_NODE;
+
+	if (flags & FLAGS_NUMA) {
+		u32 __user *naddr = (void *)uaddr + size / 2;
+
+		if (futex_get_value(&node, naddr))
+			return -EFAULT;
+
+		if (node != FUTEX_NO_NODE &&
+		    (node >= MAX_NUMNODES || !node_possible(node)))
+			return -EINVAL;
+	}
+
+	if (node == FUTEX_NO_NODE && (flags & FLAGS_MPOL)) {
+		node = futex_mpol(mm, address);
+		node_updated = true;
+	}
+
+	if (flags & FLAGS_NUMA) {
+		u32 __user *naddr = (void *)uaddr + size / 2;
+
+		if (node == FUTEX_NO_NODE) {
+			node = numa_node_id();
+			node_updated = true;
+		}
+		if (node_updated && futex_put_value(node, naddr))
+			return -EFAULT;
+	}
+
+	key->both.node = node;
+
 	/*
 	 * PROCESS_PRIVATE futexes are fast.
 	 * As the mm cannot disappear under us and the 'key' only needs
@@ -502,13 +862,9 @@ void __futex_unqueue(struct futex_q *q)
 }
 
 /* The key must be already stored in q->key. */
-struct futex_hash_bucket *futex_q_lock(struct futex_q *q)
+void futex_q_lock(struct futex_q *q, struct futex_hash_bucket *hb)
 	__acquires(&hb->lock)
 {
-	struct futex_hash_bucket *hb;
-
-	hb = futex_hash(&q->key);
-
 	/*
 	 * Increment the counter before taking the lock so that
 	 * a potential waker won't miss a to-be-slept task that is
@@ -522,14 +878,13 @@ struct futex_hash_bucket *futex_q_lock(struct futex_q *q)
 	q->lock_ptr = &hb->lock;
 
 	spin_lock(&hb->lock);
-	return hb;
 }
 
 void futex_q_unlock(struct futex_hash_bucket *hb)
 	__releases(&hb->lock)
 {
-	spin_unlock(&hb->lock);
 	futex_hb_waiters_dec(hb);
+	spin_unlock(&hb->lock);
 }
 
 void __futex_queue(struct futex_q *q, struct futex_hash_bucket *hb,
@@ -568,6 +923,8 @@ int futex_unqueue(struct futex_q *q)
 	spinlock_t *lock_ptr;
 	int ret = 0;
 
+	/* RCU so lock_ptr is not going away during locking. */
+	guard(rcu)();
 	/* In the common case we don't take the spinlock, which is nice. */
 retry:
 	/*
@@ -606,6 +963,24 @@ retry:
 	return ret;
 }
 
+void futex_q_lockptr_lock(struct futex_q *q)
+{
+	spinlock_t *lock_ptr;
+
+	/*
+	 * See futex_unqueue() why lock_ptr can change.
+	 */
+	guard(rcu)();
+retry:
+	lock_ptr = READ_ONCE(q->lock_ptr);
+	spin_lock(lock_ptr);
+
+	if (unlikely(lock_ptr != q->lock_ptr)) {
+		spin_unlock(lock_ptr);
+		goto retry;
+	}
+}
+
 /*
  * PI futexes can not be requeued and must remove themselves from the hash
  * bucket. The hash bucket lock (i.e. lock_ptr) is held.
@@ -949,10 +1324,20 @@ static void exit_pi_state_list(struct task_struct *curr)
 {
 	struct list_head *next, *head = &curr->pi_state_list;
 	struct futex_pi_state *pi_state;
-	struct futex_hash_bucket *hb;
 	union futex_key key = FUTEX_KEY_INIT;
 
 	/*
+	 * The mutex mm_struct::futex_hash_lock might be acquired.
+	 */
+	might_sleep();
+	/*
+	 * Ensure the hash remains stable (no resize) during the while loop
+	 * below. The hb pointer is acquired under the pi_lock so we can't block
+	 * on the mutex.
+	 */
+	WARN_ON(curr != current);
+	guard(private_hash)();
+	/*
 	 * We are a ZOMBIE and nobody can enqueue itself on
 	 * pi_state_list anymore, but we have to be careful
 	 * versus waiters unqueueing themselves:
@@ -962,50 +1347,52 @@ static void exit_pi_state_list(struct task_struct *curr)
 		next = head->next;
 		pi_state = list_entry(next, struct futex_pi_state, list);
 		key = pi_state->key;
-		hb = futex_hash(&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 (!refcount_inc_not_zero(&pi_state->refcount)) {
+		if (1) {
+			CLASS(hb, hb)(&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 (!refcount_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);
-			cpu_relax();
-			raw_spin_lock_irq(&curr->pi_lock);
-			continue;
-		}
-		raw_spin_unlock_irq(&curr->pi_lock);
 
-		spin_lock(&hb->lock);
-		raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock);
-		raw_spin_lock(&curr->pi_lock);
-		/*
-		 * We dropped the pi-lock, so re-check whether this
-		 * 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_lock(&hb->lock);
+			raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock);
+			raw_spin_lock(&curr->pi_lock);
+			/*
+			 * We dropped the pi-lock, so re-check whether this
+			 * 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;
+			}
+
+			WARN_ON(pi_state->owner != curr);
+			WARN_ON(list_empty(&pi_state->list));
+			list_del_init(&pi_state->list);
+			pi_state->owner = NULL;
+
+			raw_spin_unlock(&curr->pi_lock);
+			raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);
 			spin_unlock(&hb->lock);
-			put_pi_state(pi_state);
-			continue;
 		}
 
-		WARN_ON(pi_state->owner != curr);
-		WARN_ON(list_empty(&pi_state->list));
-		list_del_init(&pi_state->list);
-		pi_state->owner = NULL;
-
-		raw_spin_unlock(&curr->pi_lock);
-		raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);
-		spin_unlock(&hb->lock);
-
 		rt_mutex_futex_unlock(&pi_state->pi_mutex);
 		put_pi_state(pi_state);
 
@@ -1125,30 +1512,304 @@ void futex_exit_release(struct task_struct *tsk)
 	futex_cleanup_end(tsk, FUTEX_STATE_DEAD);
 }
 
+static void futex_hash_bucket_init(struct futex_hash_bucket *fhb,
+				   struct futex_private_hash *fph)
+{
+#ifdef CONFIG_FUTEX_PRIVATE_HASH
+	fhb->priv = fph;
+#endif
+	atomic_set(&fhb->waiters, 0);
+	plist_head_init(&fhb->chain);
+	spin_lock_init(&fhb->lock);
+}
+
+#define FH_CUSTOM	0x01
+#define FH_IMMUTABLE	0x02
+
+#ifdef CONFIG_FUTEX_PRIVATE_HASH
+void futex_hash_free(struct mm_struct *mm)
+{
+	struct futex_private_hash *fph;
+
+	kvfree(mm->futex_phash_new);
+	fph = rcu_dereference_raw(mm->futex_phash);
+	if (fph) {
+		WARN_ON_ONCE(rcuref_read(&fph->users) > 1);
+		kvfree(fph);
+	}
+}
+
+static bool futex_pivot_pending(struct mm_struct *mm)
+{
+	struct futex_private_hash *fph;
+
+	guard(rcu)();
+
+	if (!mm->futex_phash_new)
+		return true;
+
+	fph = rcu_dereference(mm->futex_phash);
+	return rcuref_is_dead(&fph->users);
+}
+
+static bool futex_hash_less(struct futex_private_hash *a,
+			    struct futex_private_hash *b)
+{
+	/* user provided always wins */
+	if (!a->custom && b->custom)
+		return true;
+	if (a->custom && !b->custom)
+		return false;
+
+	/* zero-sized hash wins */
+	if (!b->hash_mask)
+		return true;
+	if (!a->hash_mask)
+		return false;
+
+	/* keep the biggest */
+	if (a->hash_mask < b->hash_mask)
+		return true;
+	if (a->hash_mask > b->hash_mask)
+		return false;
+
+	return false; /* equal */
+}
+
+static int futex_hash_allocate(unsigned int hash_slots, unsigned int flags)
+{
+	struct mm_struct *mm = current->mm;
+	struct futex_private_hash *fph;
+	bool custom = flags & FH_CUSTOM;
+	int i;
+
+	if (hash_slots && (hash_slots == 1 || !is_power_of_2(hash_slots)))
+		return -EINVAL;
+
+	/*
+	 * Once we've disabled the global hash there is no way back.
+	 */
+	scoped_guard(rcu) {
+		fph = rcu_dereference(mm->futex_phash);
+		if (fph && (!fph->hash_mask || fph->immutable)) {
+			if (custom)
+				return -EBUSY;
+			return 0;
+		}
+	}
+
+	fph = kvzalloc(struct_size(fph, queues, hash_slots), GFP_KERNEL_ACCOUNT | __GFP_NOWARN);
+	if (!fph)
+		return -ENOMEM;
+
+	rcuref_init(&fph->users, 1);
+	fph->hash_mask = hash_slots ? hash_slots - 1 : 0;
+	fph->custom = custom;
+	fph->immutable = !!(flags & FH_IMMUTABLE);
+	fph->mm = mm;
+
+	for (i = 0; i < hash_slots; i++)
+		futex_hash_bucket_init(&fph->queues[i], fph);
+
+	if (custom) {
+		/*
+		 * Only let prctl() wait / retry; don't unduly delay clone().
+		 */
+again:
+		wait_var_event(mm, futex_pivot_pending(mm));
+	}
+
+	scoped_guard(mutex, &mm->futex_hash_lock) {
+		struct futex_private_hash *free __free(kvfree) = NULL;
+		struct futex_private_hash *cur, *new;
+
+		cur = rcu_dereference_protected(mm->futex_phash,
+						lockdep_is_held(&mm->futex_hash_lock));
+		new = mm->futex_phash_new;
+		mm->futex_phash_new = NULL;
+
+		if (fph) {
+			if (cur && !new) {
+				/*
+				 * If we have an existing hash, but do not yet have
+				 * allocated a replacement hash, drop the initial
+				 * reference on the existing hash.
+				 */
+				futex_private_hash_put(cur);
+			}
+
+			if (new) {
+				/*
+				 * Two updates raced; throw out the lesser one.
+				 */
+				if (futex_hash_less(new, fph)) {
+					free = new;
+					new = fph;
+				} else {
+					free = fph;
+				}
+			} else {
+				new = fph;
+			}
+			fph = NULL;
+		}
+
+		if (new) {
+			/*
+			 * Will set mm->futex_phash_new on failure;
+			 * futex_private_hash_get() will try again.
+			 */
+			if (!__futex_pivot_hash(mm, new) && custom)
+				goto again;
+		}
+	}
+	return 0;
+}
+
+int futex_hash_allocate_default(void)
+{
+	unsigned int threads, buckets, current_buckets = 0;
+	struct futex_private_hash *fph;
+
+	if (!current->mm)
+		return 0;
+
+	scoped_guard(rcu) {
+		threads = min_t(unsigned int,
+				get_nr_threads(current),
+				num_online_cpus());
+
+		fph = rcu_dereference(current->mm->futex_phash);
+		if (fph) {
+			if (fph->custom)
+				return 0;
+
+			current_buckets = fph->hash_mask + 1;
+		}
+	}
+
+	/*
+	 * The default allocation will remain within
+	 *   16 <= threads * 4 <= global hash size
+	 */
+	buckets = roundup_pow_of_two(4 * threads);
+	buckets = clamp(buckets, 16, futex_hashmask + 1);
+
+	if (current_buckets >= buckets)
+		return 0;
+
+	return futex_hash_allocate(buckets, 0);
+}
+
+static int futex_hash_get_slots(void)
+{
+	struct futex_private_hash *fph;
+
+	guard(rcu)();
+	fph = rcu_dereference(current->mm->futex_phash);
+	if (fph && fph->hash_mask)
+		return fph->hash_mask + 1;
+	return 0;
+}
+
+static int futex_hash_get_immutable(void)
+{
+	struct futex_private_hash *fph;
+
+	guard(rcu)();
+	fph = rcu_dereference(current->mm->futex_phash);
+	if (fph && fph->immutable)
+		return 1;
+	if (fph && !fph->hash_mask)
+		return 1;
+	return 0;
+}
+
+#else
+
+static int futex_hash_allocate(unsigned int hash_slots, unsigned int flags)
+{
+	return -EINVAL;
+}
+
+static int futex_hash_get_slots(void)
+{
+	return 0;
+}
+
+static int futex_hash_get_immutable(void)
+{
+	return 0;
+}
+#endif
+
+int futex_hash_prctl(unsigned long arg2, unsigned long arg3, unsigned long arg4)
+{
+	unsigned int flags = FH_CUSTOM;
+	int ret;
+
+	switch (arg2) {
+	case PR_FUTEX_HASH_SET_SLOTS:
+		if (arg4 & ~FH_FLAG_IMMUTABLE)
+			return -EINVAL;
+		if (arg4 & FH_FLAG_IMMUTABLE)
+			flags |= FH_IMMUTABLE;
+		ret = futex_hash_allocate(arg3, flags);
+		break;
+
+	case PR_FUTEX_HASH_GET_SLOTS:
+		ret = futex_hash_get_slots();
+		break;
+
+	case PR_FUTEX_HASH_GET_IMMUTABLE:
+		ret = futex_hash_get_immutable();
+		break;
+
+	default:
+		ret = -EINVAL;
+		break;
+	}
+	return ret;
+}
+
 static int __init futex_init(void)
 {
 	unsigned long hashsize, i;
-	unsigned int futex_shift;
+	unsigned int order, n;
+	unsigned long size;
 
 #ifdef CONFIG_BASE_SMALL
 	hashsize = 16;
 #else
-	hashsize = roundup_pow_of_two(256 * num_possible_cpus());
+	hashsize = 256 * num_possible_cpus();
+	hashsize /= num_possible_nodes();
+	hashsize = max(4, hashsize);
+	hashsize = roundup_pow_of_two(hashsize);
 #endif
+	futex_hashshift = ilog2(hashsize);
+	size = sizeof(struct futex_hash_bucket) * hashsize;
+	order = get_order(size);
+
+	for_each_node(n) {
+		struct futex_hash_bucket *table;
+
+		if (order > MAX_PAGE_ORDER)
+			table = vmalloc_huge_node(size, GFP_KERNEL, n);
+		else
+			table = alloc_pages_exact_nid(n, size, GFP_KERNEL);
+
+		BUG_ON(!table);
 
-	futex_queues = alloc_large_system_hash("futex", sizeof(*futex_queues),
-					       hashsize, 0, 0,
-					       &futex_shift, NULL,
-					       hashsize, hashsize);
-	hashsize = 1UL << futex_shift;
+		for (i = 0; i < hashsize; i++)
+			futex_hash_bucket_init(&table[i], NULL);
 
-	for (i = 0; i < hashsize; i++) {
-		atomic_set(&futex_queues[i].waiters, 0);
-		plist_head_init(&futex_queues[i].chain);
-		spin_lock_init(&futex_queues[i].lock);
+		futex_queues[n] = table;
 	}
 
 	futex_hashmask = hashsize - 1;
+	pr_info("futex hash table entries: %lu (%lu bytes on %d NUMA nodes, total %lu KiB, %s).\n",
+		hashsize, size, num_possible_nodes(), size * num_possible_nodes() / 1024,
+		order > MAX_PAGE_ORDER ? "vmalloc" : "linear");
 	return 0;
 }
 core_initcall(futex_init);
diff --git a/kernel/futex/futex.h b/kernel/futex/futex.h
index 6b2f4c7eb720..fcd1617212ee 100644
--- a/kernel/futex/futex.h
+++ b/kernel/futex/futex.h
@@ -7,6 +7,7 @@
 #include <linux/sched/wake_q.h>
 #include <linux/compat.h>
 #include <linux/uaccess.h>
+#include <linux/cleanup.h>
 
 #ifdef CONFIG_PREEMPT_RT
 #include <linux/rcuwait.h>
@@ -38,6 +39,7 @@
 #define FLAGS_HAS_TIMEOUT	0x0040
 #define FLAGS_NUMA		0x0080
 #define FLAGS_STRICT		0x0100
+#define FLAGS_MPOL		0x0200
 
 /* FUTEX_ to FLAGS_ */
 static inline unsigned int futex_to_flags(unsigned int op)
@@ -53,7 +55,7 @@ static inline unsigned int futex_to_flags(unsigned int op)
 	return flags;
 }
 
-#define FUTEX2_VALID_MASK (FUTEX2_SIZE_MASK | FUTEX2_PRIVATE)
+#define FUTEX2_VALID_MASK (FUTEX2_SIZE_MASK | FUTEX2_NUMA | FUTEX2_MPOL | FUTEX2_PRIVATE)
 
 /* FUTEX2_ to FLAGS_ */
 static inline unsigned int futex2_to_flags(unsigned int flags2)
@@ -66,6 +68,9 @@ static inline unsigned int futex2_to_flags(unsigned int flags2)
 	if (flags2 & FUTEX2_NUMA)
 		flags |= FLAGS_NUMA;
 
+	if (flags2 & FUTEX2_MPOL)
+		flags |= FLAGS_MPOL;
+
 	return flags;
 }
 
@@ -86,6 +91,19 @@ static inline bool futex_flags_valid(unsigned int flags)
 	if ((flags & FLAGS_SIZE_MASK) != FLAGS_SIZE_32)
 		return false;
 
+	/*
+	 * Must be able to represent both FUTEX_NO_NODE and every valid nodeid
+	 * in a futex word.
+	 */
+	if (flags & FLAGS_NUMA) {
+		int bits = 8 * futex_size(flags);
+		u64 max = ~0ULL;
+
+		max >>= 64 - bits;
+		if (nr_node_ids >= max)
+			return false;
+	}
+
 	return true;
 }
 
@@ -117,6 +135,7 @@ struct futex_hash_bucket {
 	atomic_t waiters;
 	spinlock_t lock;
 	struct plist_head chain;
+	struct futex_private_hash *priv;
 } ____cacheline_aligned_in_smp;
 
 /*
@@ -156,6 +175,7 @@ typedef void (futex_wake_fn)(struct wake_q_head *wake_q, struct futex_q *q);
  * @requeue_pi_key:	the requeue_pi target futex key
  * @bitset:		bitset for the optional bitmasked wakeup
  * @requeue_state:	State field for futex_requeue_pi()
+ * @drop_hb_ref:	Waiter should drop the extra hash bucket reference if true
  * @requeue_wait:	RCU wait for futex_requeue_pi() (RT only)
  *
  * We use this hashed waitqueue, instead of a normal wait_queue_entry_t, so
@@ -182,6 +202,7 @@ struct futex_q {
 	union futex_key *requeue_pi_key;
 	u32 bitset;
 	atomic_t requeue_state;
+	bool drop_hb_ref;
 #ifdef CONFIG_PREEMPT_RT
 	struct rcuwait requeue_wait;
 #endif
@@ -196,12 +217,35 @@ enum futex_access {
 
 extern int get_futex_key(u32 __user *uaddr, unsigned int flags, union futex_key *key,
 			 enum futex_access rw);
-
+extern void futex_q_lockptr_lock(struct futex_q *q);
 extern struct hrtimer_sleeper *
 futex_setup_timer(ktime_t *time, struct hrtimer_sleeper *timeout,
 		  int flags, u64 range_ns);
 
 extern struct futex_hash_bucket *futex_hash(union futex_key *key);
+#ifdef CONFIG_FUTEX_PRIVATE_HASH
+extern void futex_hash_get(struct futex_hash_bucket *hb);
+extern void futex_hash_put(struct futex_hash_bucket *hb);
+
+extern struct futex_private_hash *futex_private_hash(void);
+extern bool futex_private_hash_get(struct futex_private_hash *fph);
+extern void futex_private_hash_put(struct futex_private_hash *fph);
+
+#else /* !CONFIG_FUTEX_PRIVATE_HASH */
+static inline void futex_hash_get(struct futex_hash_bucket *hb) { }
+static inline void futex_hash_put(struct futex_hash_bucket *hb) { }
+static inline struct futex_private_hash *futex_private_hash(void) { return NULL; }
+static inline bool futex_private_hash_get(void) { return false; }
+static inline void futex_private_hash_put(struct futex_private_hash *fph) { }
+#endif
+
+DEFINE_CLASS(hb, struct futex_hash_bucket *,
+	     if (_T) futex_hash_put(_T),
+	     futex_hash(key), union futex_key *key);
+
+DEFINE_CLASS(private_hash, struct futex_private_hash *,
+	     if (_T) futex_private_hash_put(_T),
+	     futex_private_hash(), void);
 
 /**
  * futex_match - Check whether two futex keys are equal
@@ -219,9 +263,9 @@ static inline int futex_match(union futex_key *key1, union futex_key *key2)
 }
 
 extern int futex_wait_setup(u32 __user *uaddr, u32 val, unsigned int flags,
-			    struct futex_q *q, struct futex_hash_bucket **hb);
-extern void futex_wait_queue(struct futex_hash_bucket *hb, struct futex_q *q,
-				   struct hrtimer_sleeper *timeout);
+			    struct futex_q *q, union futex_key *key2,
+			    struct task_struct *task);
+extern void futex_do_wait(struct futex_q *q, struct hrtimer_sleeper *timeout);
 extern bool __futex_wake_mark(struct futex_q *q);
 extern void futex_wake_mark(struct wake_q_head *wake_q, struct futex_q *q);
 
@@ -256,7 +300,7 @@ static inline int futex_cmpxchg_value_locked(u32 *curval, u32 __user *uaddr, u32
  * This looks a bit overkill, but generally just results in a couple
  * of instructions.
  */
-static __always_inline int futex_read_inatomic(u32 *dest, u32 __user *from)
+static __always_inline int futex_get_value(u32 *dest, u32 __user *from)
 {
 	u32 val;
 
@@ -273,12 +317,26 @@ Efault:
 	return -EFAULT;
 }
 
+static __always_inline int futex_put_value(u32 val, u32 __user *to)
+{
+	if (can_do_masked_user_access())
+		to = masked_user_access_begin(to);
+	else if (!user_read_access_begin(to, sizeof(*to)))
+		return -EFAULT;
+	unsafe_put_user(val, to, Efault);
+	user_read_access_end();
+	return 0;
+Efault:
+	user_read_access_end();
+	return -EFAULT;
+}
+
 static inline int futex_get_value_locked(u32 *dest, u32 __user *from)
 {
 	int ret;
 
 	pagefault_disable();
-	ret = futex_read_inatomic(dest, from);
+	ret = futex_get_value(dest, from);
 	pagefault_enable();
 
 	return ret;
@@ -354,7 +412,7 @@ static inline int futex_hb_waiters_pending(struct futex_hash_bucket *hb)
 #endif
 }
 
-extern struct futex_hash_bucket *futex_q_lock(struct futex_q *q);
+extern void futex_q_lock(struct futex_q *q, struct futex_hash_bucket *hb);
 extern void futex_q_unlock(struct futex_hash_bucket *hb);
 
 
diff --git a/kernel/futex/pi.c b/kernel/futex/pi.c
index 7a941845f7ee..dacb2330f1fb 100644
--- a/kernel/futex/pi.c
+++ b/kernel/futex/pi.c
@@ -806,7 +806,7 @@ handle_err:
 		break;
 	}
 
-	spin_lock(q->lock_ptr);
+	futex_q_lockptr_lock(q);
 	raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock);
 
 	/*
@@ -920,7 +920,6 @@ int futex_lock_pi(u32 __user *uaddr, unsigned int flags, ktime_t *time, int tryl
 	struct hrtimer_sleeper timeout, *to;
 	struct task_struct *exiting = NULL;
 	struct rt_mutex_waiter rt_waiter;
-	struct futex_hash_bucket *hb;
 	struct futex_q q = futex_q_init;
 	DEFINE_WAKE_Q(wake_q);
 	int res, ret;
@@ -939,151 +938,183 @@ retry:
 		goto out;
 
 retry_private:
-	hb = futex_q_lock(&q);
+	if (1) {
+		CLASS(hb, hb)(&q.key);
 
-	ret = futex_lock_pi_atomic(uaddr, hb, &q.key, &q.pi_state, current,
-				   &exiting, 0);
-	if (unlikely(ret)) {
-		/*
-		 * Atomic work succeeded and we got the lock,
-		 * or failed. Either way, we do _not_ block.
-		 */
-		switch (ret) {
-		case 1:
-			/* We got the lock. */
-			ret = 0;
-			goto out_unlock_put_key;
-		case -EFAULT:
-			goto uaddr_faulted;
-		case -EBUSY:
-		case -EAGAIN:
-			/*
-			 * Two reasons for this:
-			 * - EBUSY: Task is exiting and we just wait for the
-			 *   exit to complete.
-			 * - EAGAIN: The user space value changed.
-			 */
-			futex_q_unlock(hb);
+		futex_q_lock(&q, hb);
+
+		ret = futex_lock_pi_atomic(uaddr, hb, &q.key, &q.pi_state, current,
+					   &exiting, 0);
+		if (unlikely(ret)) {
 			/*
-			 * Handle the case where the owner is in the middle of
-			 * exiting. Wait for the exit to complete otherwise
-			 * this task might loop forever, aka. live lock.
+			 * Atomic work succeeded and we got the lock,
+			 * or failed. Either way, we do _not_ block.
 			 */
-			wait_for_owner_exiting(ret, exiting);
-			cond_resched();
-			goto retry;
-		default:
-			goto out_unlock_put_key;
+			switch (ret) {
+			case 1:
+				/* We got the lock. */
+				ret = 0;
+				goto out_unlock_put_key;
+			case -EFAULT:
+				goto uaddr_faulted;
+			case -EBUSY:
+			case -EAGAIN:
+				/*
+				 * Two reasons for this:
+				 * - EBUSY: Task is exiting and we just wait for the
+				 *   exit to complete.
+				 * - EAGAIN: The user space value changed.
+				 */
+				futex_q_unlock(hb);
+				/*
+				 * Handle the case where the owner is in the middle of
+				 * exiting. Wait for the exit to complete otherwise
+				 * this task might loop forever, aka. live lock.
+				 */
+				wait_for_owner_exiting(ret, exiting);
+				cond_resched();
+				goto retry;
+			default:
+				goto out_unlock_put_key;
+			}
 		}
-	}
 
-	WARN_ON(!q.pi_state);
+		WARN_ON(!q.pi_state);
 
-	/*
-	 * Only actually queue now that the atomic ops are done:
-	 */
-	__futex_queue(&q, hb, current);
+		/*
+		 * Only actually queue now that the atomic ops are done:
+		 */
+		__futex_queue(&q, hb, current);
 
-	if (trylock) {
-		ret = rt_mutex_futex_trylock(&q.pi_state->pi_mutex);
-		/* Fixup the trylock return value: */
-		ret = ret ? 0 : -EWOULDBLOCK;
-		goto no_block;
-	}
+		if (trylock) {
+			ret = rt_mutex_futex_trylock(&q.pi_state->pi_mutex);
+			/* Fixup the trylock return value: */
+			ret = ret ? 0 : -EWOULDBLOCK;
+			goto no_block;
+		}
 
-	/*
-	 * Must be done before we enqueue the waiter, here is unfortunately
-	 * under the hb lock, but that *should* work because it does nothing.
-	 */
-	rt_mutex_pre_schedule();
+		/*
+		 * Caution; releasing @hb in-scope. The hb->lock is still locked
+		 * while the reference is dropped. The reference can not be dropped
+		 * after the unlock because if a user initiated resize is in progress
+		 * then we might need to wake him. This can not be done after the
+		 * rt_mutex_pre_schedule() invocation. The hb will remain valid because
+		 * the thread, performing resize, will block on hb->lock during
+		 * the requeue.
+		 */
+		futex_hash_put(no_free_ptr(hb));
+		/*
+		 * Must be done before we enqueue the waiter, here is unfortunately
+		 * under the hb lock, but that *should* work because it does nothing.
+		 */
+		rt_mutex_pre_schedule();
 
-	rt_mutex_init_waiter(&rt_waiter);
+		rt_mutex_init_waiter(&rt_waiter);
 
-	/*
-	 * On PREEMPT_RT, when hb->lock becomes an rt_mutex, we must not
-	 * hold it while doing rt_mutex_start_proxy(), because then it will
-	 * include hb->lock in the blocking chain, even through we'll not in
-	 * fact hold it while blocking. This will lead it to report -EDEADLK
-	 * and BUG when futex_unlock_pi() interleaves with this.
-	 *
-	 * Therefore acquire wait_lock while holding hb->lock, but drop the
-	 * latter before calling __rt_mutex_start_proxy_lock(). This
-	 * interleaves with futex_unlock_pi() -- which does a similar lock
-	 * handoff -- such that the latter can observe the futex_q::pi_state
-	 * before __rt_mutex_start_proxy_lock() is done.
-	 */
-	raw_spin_lock_irq(&q.pi_state->pi_mutex.wait_lock);
-	spin_unlock(q.lock_ptr);
-	/*
-	 * __rt_mutex_start_proxy_lock() unconditionally enqueues the @rt_waiter
-	 * such that futex_unlock_pi() is guaranteed to observe the waiter when
-	 * it sees the futex_q::pi_state.
-	 */
-	ret = __rt_mutex_start_proxy_lock(&q.pi_state->pi_mutex, &rt_waiter, current, &wake_q);
-	raw_spin_unlock_irq_wake(&q.pi_state->pi_mutex.wait_lock, &wake_q);
+		/*
+		 * On PREEMPT_RT, when hb->lock becomes an rt_mutex, we must not
+		 * hold it while doing rt_mutex_start_proxy(), because then it will
+		 * include hb->lock in the blocking chain, even through we'll not in
+		 * fact hold it while blocking. This will lead it to report -EDEADLK
+		 * and BUG when futex_unlock_pi() interleaves with this.
+		 *
+		 * Therefore acquire wait_lock while holding hb->lock, but drop the
+		 * latter before calling __rt_mutex_start_proxy_lock(). This
+		 * interleaves with futex_unlock_pi() -- which does a similar lock
+		 * handoff -- such that the latter can observe the futex_q::pi_state
+		 * before __rt_mutex_start_proxy_lock() is done.
+		 */
+		raw_spin_lock_irq(&q.pi_state->pi_mutex.wait_lock);
+		spin_unlock(q.lock_ptr);
+		/*
+		 * __rt_mutex_start_proxy_lock() unconditionally enqueues the @rt_waiter
+		 * such that futex_unlock_pi() is guaranteed to observe the waiter when
+		 * it sees the futex_q::pi_state.
+		 */
+		ret = __rt_mutex_start_proxy_lock(&q.pi_state->pi_mutex, &rt_waiter, current, &wake_q);
+		raw_spin_unlock_irq_wake(&q.pi_state->pi_mutex.wait_lock, &wake_q);
 
-	if (ret) {
-		if (ret == 1)
-			ret = 0;
-		goto cleanup;
-	}
+		if (ret) {
+			if (ret == 1)
+				ret = 0;
+			goto cleanup;
+		}
 
-	if (unlikely(to))
-		hrtimer_sleeper_start_expires(to, HRTIMER_MODE_ABS);
+		if (unlikely(to))
+			hrtimer_sleeper_start_expires(to, HRTIMER_MODE_ABS);
 
-	ret = rt_mutex_wait_proxy_lock(&q.pi_state->pi_mutex, to, &rt_waiter);
+		ret = rt_mutex_wait_proxy_lock(&q.pi_state->pi_mutex, to, &rt_waiter);
 
 cleanup:
-	/*
-	 * If we failed to acquire the lock (deadlock/signal/timeout), we must
-	 * must unwind the above, however we canont lock hb->lock because
-	 * rt_mutex already has a waiter enqueued and hb->lock can itself try
-	 * and enqueue an rt_waiter through rtlock.
-	 *
-	 * Doing the cleanup without holding hb->lock can cause inconsistent
-	 * state between hb and pi_state, but only in the direction of not
-	 * seeing a waiter that is leaving.
-	 *
-	 * See futex_unlock_pi(), it deals with this inconsistency.
-	 *
-	 * There be dragons here, since we must deal with the inconsistency on
-	 * the way out (here), it is impossible to detect/warn about the race
-	 * the other way around (missing an incoming waiter).
-	 *
-	 * What could possibly go wrong...
-	 */
-	if (ret && !rt_mutex_cleanup_proxy_lock(&q.pi_state->pi_mutex, &rt_waiter))
-		ret = 0;
+		/*
+		 * If we failed to acquire the lock (deadlock/signal/timeout), we must
+		 * unwind the above, however we canont lock hb->lock because
+		 * rt_mutex already has a waiter enqueued and hb->lock can itself try
+		 * and enqueue an rt_waiter through rtlock.
+		 *
+		 * Doing the cleanup without holding hb->lock can cause inconsistent
+		 * state between hb and pi_state, but only in the direction of not
+		 * seeing a waiter that is leaving.
+		 *
+		 * See futex_unlock_pi(), it deals with this inconsistency.
+		 *
+		 * There be dragons here, since we must deal with the inconsistency on
+		 * the way out (here), it is impossible to detect/warn about the race
+		 * the other way around (missing an incoming waiter).
+		 *
+		 * What could possibly go wrong...
+		 */
+		if (ret && !rt_mutex_cleanup_proxy_lock(&q.pi_state->pi_mutex, &rt_waiter))
+			ret = 0;
 
-	/*
-	 * Now that the rt_waiter has been dequeued, it is safe to use
-	 * spinlock/rtlock (which might enqueue its own rt_waiter) and fix up
-	 * the
-	 */
-	spin_lock(q.lock_ptr);
-	/*
-	 * Waiter is unqueued.
-	 */
-	rt_mutex_post_schedule();
+		/*
+		 * Now that the rt_waiter has been dequeued, it is safe to use
+		 * spinlock/rtlock (which might enqueue its own rt_waiter) and fix up
+		 * the
+		 */
+		futex_q_lockptr_lock(&q);
+		/*
+		 * Waiter is unqueued.
+		 */
+		rt_mutex_post_schedule();
 no_block:
-	/*
-	 * Fixup the pi_state owner and possibly acquire the lock if we
-	 * haven't already.
-	 */
-	res = fixup_pi_owner(uaddr, &q, !ret);
-	/*
-	 * If fixup_pi_owner() returned an error, propagate that.  If it acquired
-	 * the lock, clear our -ETIMEDOUT or -EINTR.
-	 */
-	if (res)
-		ret = (res < 0) ? res : 0;
-
-	futex_unqueue_pi(&q);
-	spin_unlock(q.lock_ptr);
-	goto out;
+		/*
+		 * Fixup the pi_state owner and possibly acquire the lock if we
+		 * haven't already.
+		 */
+		res = fixup_pi_owner(uaddr, &q, !ret);
+		/*
+		 * If fixup_pi_owner() returned an error, propagate that.  If it acquired
+		 * the lock, clear our -ETIMEDOUT or -EINTR.
+		 */
+		if (res)
+			ret = (res < 0) ? res : 0;
+
+		futex_unqueue_pi(&q);
+		spin_unlock(q.lock_ptr);
+		if (q.drop_hb_ref) {
+			CLASS(hb, hb)(&q.key);
+			/* Additional reference from futex_unlock_pi() */
+			futex_hash_put(hb);
+		}
+		goto out;
 
 out_unlock_put_key:
-	futex_q_unlock(hb);
+		futex_q_unlock(hb);
+		goto out;
+
+uaddr_faulted:
+		futex_q_unlock(hb);
+
+		ret = fault_in_user_writeable(uaddr);
+		if (ret)
+			goto out;
+
+		if (!(flags & FLAGS_SHARED))
+			goto retry_private;
+
+		goto retry;
+	}
 
 out:
 	if (to) {
@@ -1091,18 +1122,6 @@ out:
 		destroy_hrtimer_on_stack(&to->timer);
 	}
 	return ret != -EINTR ? ret : -ERESTARTNOINTR;
-
-uaddr_faulted:
-	futex_q_unlock(hb);
-
-	ret = fault_in_user_writeable(uaddr);
-	if (ret)
-		goto out;
-
-	if (!(flags & FLAGS_SHARED))
-		goto retry_private;
-
-	goto retry;
 }
 
 /*
@@ -1114,7 +1133,6 @@ int futex_unlock_pi(u32 __user *uaddr, unsigned int flags)
 {
 	u32 curval, uval, vpid = task_pid_vnr(current);
 	union futex_key key = FUTEX_KEY_INIT;
-	struct futex_hash_bucket *hb;
 	struct futex_q *top_waiter;
 	int ret;
 
@@ -1134,7 +1152,7 @@ retry:
 	if (ret)
 		return ret;
 
-	hb = futex_hash(&key);
+	CLASS(hb, hb)(&key);
 	spin_lock(&hb->lock);
 retry_hb:
 
@@ -1187,6 +1205,12 @@ retry_hb:
 		 */
 		rt_waiter = rt_mutex_top_waiter(&pi_state->pi_mutex);
 		if (!rt_waiter) {
+			/*
+			 * Acquire a reference for the leaving waiter to ensure
+			 * valid futex_q::lock_ptr.
+			 */
+			futex_hash_get(hb);
+			top_waiter->drop_hb_ref = true;
 			__futex_unqueue(top_waiter);
 			raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);
 			goto retry_hb;
diff --git a/kernel/futex/requeue.c b/kernel/futex/requeue.c
index b47bb764b352..c716a66f8692 100644
--- a/kernel/futex/requeue.c
+++ b/kernel/futex/requeue.c
@@ -87,6 +87,11 @@ void requeue_futex(struct futex_q *q, struct futex_hash_bucket *hb1,
 		futex_hb_waiters_inc(hb2);
 		plist_add(&q->list, &hb2->chain);
 		q->lock_ptr = &hb2->lock;
+		/*
+		 * hb1 and hb2 belong to the same futex_hash_bucket_private
+		 * because if we managed get a reference on hb1 then it can't be
+		 * replaced. Therefore we avoid put(hb1)+get(hb2) here.
+		 */
 	}
 	q->key = *key2;
 }
@@ -231,7 +236,12 @@ void requeue_pi_wake_futex(struct futex_q *q, union futex_key *key,
 
 	WARN_ON(!q->rt_waiter);
 	q->rt_waiter = NULL;
-
+	/*
+	 * Acquire a reference for the waiter to ensure valid
+	 * futex_q::lock_ptr.
+	 */
+	futex_hash_get(hb);
+	q->drop_hb_ref = true;
 	q->lock_ptr = &hb->lock;
 
 	/* Signal locked state to the waiter */
@@ -371,7 +381,6 @@ int futex_requeue(u32 __user *uaddr1, unsigned int flags1,
 	union futex_key key1 = FUTEX_KEY_INIT, key2 = FUTEX_KEY_INIT;
 	int task_count = 0, ret;
 	struct futex_pi_state *pi_state = NULL;
-	struct futex_hash_bucket *hb1, *hb2;
 	struct futex_q *this, *next;
 	DEFINE_WAKE_Q(wake_q);
 
@@ -443,240 +452,242 @@ retry:
 	if (requeue_pi && futex_match(&key1, &key2))
 		return -EINVAL;
 
-	hb1 = futex_hash(&key1);
-	hb2 = futex_hash(&key2);
-
 retry_private:
-	futex_hb_waiters_inc(hb2);
-	double_lock_hb(hb1, hb2);
+	if (1) {
+		CLASS(hb, hb1)(&key1);
+		CLASS(hb, hb2)(&key2);
 
-	if (likely(cmpval != NULL)) {
-		u32 curval;
+		futex_hb_waiters_inc(hb2);
+		double_lock_hb(hb1, hb2);
 
-		ret = futex_get_value_locked(&curval, uaddr1);
+		if (likely(cmpval != NULL)) {
+			u32 curval;
 
-		if (unlikely(ret)) {
-			double_unlock_hb(hb1, hb2);
-			futex_hb_waiters_dec(hb2);
+			ret = futex_get_value_locked(&curval, uaddr1);
 
-			ret = get_user(curval, uaddr1);
-			if (ret)
-				return ret;
+			if (unlikely(ret)) {
+				futex_hb_waiters_dec(hb2);
+				double_unlock_hb(hb1, hb2);
 
-			if (!(flags1 & FLAGS_SHARED))
-				goto retry_private;
+				ret = get_user(curval, uaddr1);
+				if (ret)
+					return ret;
 
-			goto retry;
-		}
-		if (curval != *cmpval) {
-			ret = -EAGAIN;
-			goto out_unlock;
-		}
-	}
+				if (!(flags1 & FLAGS_SHARED))
+					goto retry_private;
 
-	if (requeue_pi) {
-		struct task_struct *exiting = NULL;
+				goto retry;
+			}
+			if (curval != *cmpval) {
+				ret = -EAGAIN;
+				goto out_unlock;
+			}
+		}
 
-		/*
-		 * Attempt to acquire uaddr2 and wake the top waiter. If we
-		 * intend to requeue waiters, force setting the FUTEX_WAITERS
-		 * bit.  We force this here where we are able to easily handle
-		 * faults rather in the requeue loop below.
-		 *
-		 * Updates topwaiter::requeue_state if a top waiter exists.
-		 */
-		ret = futex_proxy_trylock_atomic(uaddr2, hb1, hb2, &key1,
-						 &key2, &pi_state,
-						 &exiting, nr_requeue);
+		if (requeue_pi) {
+			struct task_struct *exiting = NULL;
 
-		/*
-		 * At this point the top_waiter has either taken uaddr2 or
-		 * is waiting on it. In both cases pi_state has been
-		 * established and an initial refcount on it. In case of an
-		 * error there's nothing.
-		 *
-		 * The top waiter's requeue_state is up to date:
-		 *
-		 *  - If the lock was acquired atomically (ret == 1), then
-		 *    the state is Q_REQUEUE_PI_LOCKED.
-		 *
-		 *    The top waiter has been dequeued and woken up and can
-		 *    return to user space immediately. The kernel/user
-		 *    space state is consistent. In case that there must be
-		 *    more waiters requeued the WAITERS bit in the user
-		 *    space futex is set so the top waiter task has to go
-		 *    into the syscall slowpath to unlock the futex. This
-		 *    will block until this requeue operation has been
-		 *    completed and the hash bucket locks have been
-		 *    dropped.
-		 *
-		 *  - If the trylock failed with an error (ret < 0) then
-		 *    the state is either Q_REQUEUE_PI_NONE, i.e. "nothing
-		 *    happened", or Q_REQUEUE_PI_IGNORE when there was an
-		 *    interleaved early wakeup.
-		 *
-		 *  - If the trylock did not succeed (ret == 0) then the
-		 *    state is either Q_REQUEUE_PI_IN_PROGRESS or
-		 *    Q_REQUEUE_PI_WAIT if an early wakeup interleaved.
-		 *    This will be cleaned up in the loop below, which
-		 *    cannot fail because futex_proxy_trylock_atomic() did
-		 *    the same sanity checks for requeue_pi as the loop
-		 *    below does.
-		 */
-		switch (ret) {
-		case 0:
-			/* We hold a reference on the pi state. */
-			break;
-
-		case 1:
 			/*
-			 * futex_proxy_trylock_atomic() acquired the user space
-			 * futex. Adjust task_count.
+			 * Attempt to acquire uaddr2 and wake the top waiter. If we
+			 * intend to requeue waiters, force setting the FUTEX_WAITERS
+			 * bit.  We force this here where we are able to easily handle
+			 * faults rather in the requeue loop below.
+			 *
+			 * Updates topwaiter::requeue_state if a top waiter exists.
 			 */
-			task_count++;
-			ret = 0;
-			break;
+			ret = futex_proxy_trylock_atomic(uaddr2, hb1, hb2, &key1,
+							 &key2, &pi_state,
+							 &exiting, nr_requeue);
 
-		/*
-		 * If the above failed, then pi_state is NULL and
-		 * waiter::requeue_state is correct.
-		 */
-		case -EFAULT:
-			double_unlock_hb(hb1, hb2);
-			futex_hb_waiters_dec(hb2);
-			ret = fault_in_user_writeable(uaddr2);
-			if (!ret)
-				goto retry;
-			return ret;
-		case -EBUSY:
-		case -EAGAIN:
-			/*
-			 * Two reasons for this:
-			 * - EBUSY: Owner is exiting and we just wait for the
-			 *   exit to complete.
-			 * - EAGAIN: The user space value changed.
-			 */
-			double_unlock_hb(hb1, hb2);
-			futex_hb_waiters_dec(hb2);
 			/*
-			 * Handle the case where the owner is in the middle of
-			 * exiting. Wait for the exit to complete otherwise
-			 * this task might loop forever, aka. live lock.
+			 * At this point the top_waiter has either taken uaddr2 or
+			 * is waiting on it. In both cases pi_state has been
+			 * established and an initial refcount on it. In case of an
+			 * error there's nothing.
+			 *
+			 * The top waiter's requeue_state is up to date:
+			 *
+			 *  - If the lock was acquired atomically (ret == 1), then
+			 *    the state is Q_REQUEUE_PI_LOCKED.
+			 *
+			 *    The top waiter has been dequeued and woken up and can
+			 *    return to user space immediately. The kernel/user
+			 *    space state is consistent. In case that there must be
+			 *    more waiters requeued the WAITERS bit in the user
+			 *    space futex is set so the top waiter task has to go
+			 *    into the syscall slowpath to unlock the futex. This
+			 *    will block until this requeue operation has been
+			 *    completed and the hash bucket locks have been
+			 *    dropped.
+			 *
+			 *  - If the trylock failed with an error (ret < 0) then
+			 *    the state is either Q_REQUEUE_PI_NONE, i.e. "nothing
+			 *    happened", or Q_REQUEUE_PI_IGNORE when there was an
+			 *    interleaved early wakeup.
+			 *
+			 *  - If the trylock did not succeed (ret == 0) then the
+			 *    state is either Q_REQUEUE_PI_IN_PROGRESS or
+			 *    Q_REQUEUE_PI_WAIT if an early wakeup interleaved.
+			 *    This will be cleaned up in the loop below, which
+			 *    cannot fail because futex_proxy_trylock_atomic() did
+			 *    the same sanity checks for requeue_pi as the loop
+			 *    below does.
 			 */
-			wait_for_owner_exiting(ret, exiting);
-			cond_resched();
-			goto retry;
-		default:
-			goto out_unlock;
-		}
-	}
-
-	plist_for_each_entry_safe(this, next, &hb1->chain, list) {
-		if (task_count - nr_wake >= nr_requeue)
-			break;
-
-		if (!futex_match(&this->key, &key1))
-			continue;
-
-		/*
-		 * FUTEX_WAIT_REQUEUE_PI and FUTEX_CMP_REQUEUE_PI should always
-		 * be paired with each other and no other futex ops.
-		 *
-		 * We should never be requeueing a futex_q with a pi_state,
-		 * which is awaiting a futex_unlock_pi().
-		 */
-		if ((requeue_pi && !this->rt_waiter) ||
-		    (!requeue_pi && this->rt_waiter) ||
-		    this->pi_state) {
-			ret = -EINVAL;
-			break;
+			switch (ret) {
+			case 0:
+				/* We hold a reference on the pi state. */
+				break;
+
+			case 1:
+				/*
+				 * futex_proxy_trylock_atomic() acquired the user space
+				 * futex. Adjust task_count.
+				 */
+				task_count++;
+				ret = 0;
+				break;
+
+				/*
+				 * If the above failed, then pi_state is NULL and
+				 * waiter::requeue_state is correct.
+				 */
+			case -EFAULT:
+				futex_hb_waiters_dec(hb2);
+				double_unlock_hb(hb1, hb2);
+				ret = fault_in_user_writeable(uaddr2);
+				if (!ret)
+					goto retry;
+				return ret;
+			case -EBUSY:
+			case -EAGAIN:
+				/*
+				 * Two reasons for this:
+				 * - EBUSY: Owner is exiting and we just wait for the
+				 *   exit to complete.
+				 * - EAGAIN: The user space value changed.
+				 */
+				futex_hb_waiters_dec(hb2);
+				double_unlock_hb(hb1, hb2);
+				/*
+				 * Handle the case where the owner is in the middle of
+				 * exiting. Wait for the exit to complete otherwise
+				 * this task might loop forever, aka. live lock.
+				 */
+				wait_for_owner_exiting(ret, exiting);
+				cond_resched();
+				goto retry;
+			default:
+				goto out_unlock;
+			}
 		}
 
-		/* Plain futexes just wake or requeue and are done */
-		if (!requeue_pi) {
-			if (++task_count <= nr_wake)
-				this->wake(&wake_q, this);
-			else
-				requeue_futex(this, hb1, hb2, &key2);
-			continue;
-		}
+		plist_for_each_entry_safe(this, next, &hb1->chain, list) {
+			if (task_count - nr_wake >= nr_requeue)
+				break;
 
-		/* Ensure we requeue to the expected futex for requeue_pi. */
-		if (!futex_match(this->requeue_pi_key, &key2)) {
-			ret = -EINVAL;
-			break;
-		}
+			if (!futex_match(&this->key, &key1))
+				continue;
 
-		/*
-		 * Requeue nr_requeue waiters and possibly one more in the case
-		 * of requeue_pi if we couldn't acquire the lock atomically.
-		 *
-		 * Prepare the waiter to take the rt_mutex. Take a refcount
-		 * on the pi_state and store the pointer in the futex_q
-		 * object of the waiter.
-		 */
-		get_pi_state(pi_state);
-
-		/* Don't requeue when the waiter is already on the way out. */
-		if (!futex_requeue_pi_prepare(this, pi_state)) {
 			/*
-			 * Early woken waiter signaled that it is on the
-			 * way out. Drop the pi_state reference and try the
-			 * next waiter. @this->pi_state is still NULL.
+			 * FUTEX_WAIT_REQUEUE_PI and FUTEX_CMP_REQUEUE_PI should always
+			 * be paired with each other and no other futex ops.
+			 *
+			 * We should never be requeueing a futex_q with a pi_state,
+			 * which is awaiting a futex_unlock_pi().
 			 */
-			put_pi_state(pi_state);
-			continue;
-		}
+			if ((requeue_pi && !this->rt_waiter) ||
+			    (!requeue_pi && this->rt_waiter) ||
+			    this->pi_state) {
+				ret = -EINVAL;
+				break;
+			}
+
+			/* Plain futexes just wake or requeue and are done */
+			if (!requeue_pi) {
+				if (++task_count <= nr_wake)
+					this->wake(&wake_q, this);
+				else
+					requeue_futex(this, hb1, hb2, &key2);
+				continue;
+			}
+
+			/* Ensure we requeue to the expected futex for requeue_pi. */
+			if (!futex_match(this->requeue_pi_key, &key2)) {
+				ret = -EINVAL;
+				break;
+			}
 
-		ret = rt_mutex_start_proxy_lock(&pi_state->pi_mutex,
-						this->rt_waiter,
-						this->task);
-
-		if (ret == 1) {
-			/*
-			 * We got the lock. We do neither drop the refcount
-			 * on pi_state nor clear this->pi_state because the
-			 * waiter needs the pi_state for cleaning up the
-			 * user space value. It will drop the refcount
-			 * after doing so. this::requeue_state is updated
-			 * in the wakeup as well.
-			 */
-			requeue_pi_wake_futex(this, &key2, hb2);
-			task_count++;
-		} else if (!ret) {
-			/* Waiter is queued, move it to hb2 */
-			requeue_futex(this, hb1, hb2, &key2);
-			futex_requeue_pi_complete(this, 0);
-			task_count++;
-		} else {
 			/*
-			 * rt_mutex_start_proxy_lock() detected a potential
-			 * deadlock when we tried to queue that waiter.
-			 * Drop the pi_state reference which we took above
-			 * and remove the pointer to the state from the
-			 * waiters futex_q object.
+			 * Requeue nr_requeue waiters and possibly one more in the case
+			 * of requeue_pi if we couldn't acquire the lock atomically.
+			 *
+			 * Prepare the waiter to take the rt_mutex. Take a refcount
+			 * on the pi_state and store the pointer in the futex_q
+			 * object of the waiter.
 			 */
-			this->pi_state = NULL;
-			put_pi_state(pi_state);
-			futex_requeue_pi_complete(this, ret);
-			/*
-			 * We stop queueing more waiters and let user space
-			 * deal with the mess.
-			 */
-			break;
+			get_pi_state(pi_state);
+
+			/* Don't requeue when the waiter is already on the way out. */
+			if (!futex_requeue_pi_prepare(this, pi_state)) {
+				/*
+				 * Early woken waiter signaled that it is on the
+				 * way out. Drop the pi_state reference and try the
+				 * next waiter. @this->pi_state is still NULL.
+				 */
+				put_pi_state(pi_state);
+				continue;
+			}
+
+			ret = rt_mutex_start_proxy_lock(&pi_state->pi_mutex,
+							this->rt_waiter,
+							this->task);
+
+			if (ret == 1) {
+				/*
+				 * We got the lock. We do neither drop the refcount
+				 * on pi_state nor clear this->pi_state because the
+				 * waiter needs the pi_state for cleaning up the
+				 * user space value. It will drop the refcount
+				 * after doing so. this::requeue_state is updated
+				 * in the wakeup as well.
+				 */
+				requeue_pi_wake_futex(this, &key2, hb2);
+				task_count++;
+			} else if (!ret) {
+				/* Waiter is queued, move it to hb2 */
+				requeue_futex(this, hb1, hb2, &key2);
+				futex_requeue_pi_complete(this, 0);
+				task_count++;
+			} else {
+				/*
+				 * rt_mutex_start_proxy_lock() detected a potential
+				 * deadlock when we tried to queue that waiter.
+				 * Drop the pi_state reference which we took above
+				 * and remove the pointer to the state from the
+				 * waiters futex_q object.
+				 */
+				this->pi_state = NULL;
+				put_pi_state(pi_state);
+				futex_requeue_pi_complete(this, ret);
+				/*
+				 * We stop queueing more waiters and let user space
+				 * deal with the mess.
+				 */
+				break;
+			}
 		}
-	}
 
-	/*
-	 * We took an extra initial reference to the pi_state in
-	 * futex_proxy_trylock_atomic(). We need to drop it here again.
-	 */
-	put_pi_state(pi_state);
+		/*
+		 * We took an extra initial reference to the pi_state in
+		 * futex_proxy_trylock_atomic(). We need to drop it here again.
+		 */
+		put_pi_state(pi_state);
 
 out_unlock:
-	double_unlock_hb(hb1, hb2);
+		futex_hb_waiters_dec(hb2);
+		double_unlock_hb(hb1, hb2);
+	}
 	wake_up_q(&wake_q);
-	futex_hb_waiters_dec(hb2);
 	return ret ? ret : task_count;
 }
 
@@ -769,7 +780,6 @@ int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
 {
 	struct hrtimer_sleeper timeout, *to;
 	struct rt_mutex_waiter rt_waiter;
-	struct futex_hash_bucket *hb;
 	union futex_key key2 = FUTEX_KEY_INIT;
 	struct futex_q q = futex_q_init;
 	struct rt_mutex_base *pi_mutex;
@@ -805,35 +815,28 @@ int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
 	 * Prepare to wait on uaddr. On success, it holds hb->lock and q
 	 * is initialized.
 	 */
-	ret = futex_wait_setup(uaddr, val, flags, &q, &hb);
+	ret = futex_wait_setup(uaddr, val, flags, &q, &key2, current);
 	if (ret)
 		goto out;
 
-	/*
-	 * The check above which compares uaddrs is not sufficient for
-	 * shared futexes. We need to compare the keys:
-	 */
-	if (futex_match(&q.key, &key2)) {
-		futex_q_unlock(hb);
-		ret = -EINVAL;
-		goto out;
-	}
-
 	/* Queue the futex_q, drop the hb lock, wait for wakeup. */
-	futex_wait_queue(hb, &q, to);
+	futex_do_wait(&q, to);
 
 	switch (futex_requeue_pi_wakeup_sync(&q)) {
 	case Q_REQUEUE_PI_IGNORE:
-		/* The waiter is still on uaddr1 */
-		spin_lock(&hb->lock);
-		ret = handle_early_requeue_pi_wakeup(hb, &q, to);
-		spin_unlock(&hb->lock);
+		{
+			CLASS(hb, hb)(&q.key);
+			/* The waiter is still on uaddr1 */
+			spin_lock(&hb->lock);
+			ret = handle_early_requeue_pi_wakeup(hb, &q, to);
+			spin_unlock(&hb->lock);
+		}
 		break;
 
 	case Q_REQUEUE_PI_LOCKED:
 		/* The requeue acquired the lock */
 		if (q.pi_state && (q.pi_state->owner != current)) {
-			spin_lock(q.lock_ptr);
+			futex_q_lockptr_lock(&q);
 			ret = fixup_pi_owner(uaddr2, &q, true);
 			/*
 			 * Drop the reference to the pi state which the
@@ -860,7 +863,7 @@ int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
 		if (ret && !rt_mutex_cleanup_proxy_lock(pi_mutex, &rt_waiter))
 			ret = 0;
 
-		spin_lock(q.lock_ptr);
+		futex_q_lockptr_lock(&q);
 		debug_rt_mutex_free_waiter(&rt_waiter);
 		/*
 		 * Fixup the pi_state owner and possibly acquire the lock if we
@@ -892,6 +895,11 @@ int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
 	default:
 		BUG();
 	}
+	if (q.drop_hb_ref) {
+		CLASS(hb, hb)(&q.key);
+		/* Additional reference from requeue_pi_wake_futex() */
+		futex_hash_put(hb);
+	}
 
 out:
 	if (to) {
diff --git a/kernel/futex/waitwake.c b/kernel/futex/waitwake.c
index 25877d4f2f8f..e2bbe5509ec2 100644
--- a/kernel/futex/waitwake.c
+++ b/kernel/futex/waitwake.c
@@ -154,7 +154,6 @@ void futex_wake_mark(struct wake_q_head *wake_q, struct futex_q *q)
  */
 int futex_wake(u32 __user *uaddr, unsigned int flags, int nr_wake, u32 bitset)
 {
-	struct futex_hash_bucket *hb;
 	struct futex_q *this, *next;
 	union futex_key key = FUTEX_KEY_INIT;
 	DEFINE_WAKE_Q(wake_q);
@@ -170,7 +169,7 @@ int futex_wake(u32 __user *uaddr, unsigned int flags, int nr_wake, u32 bitset)
 	if ((flags & FLAGS_STRICT) && !nr_wake)
 		return 0;
 
-	hb = futex_hash(&key);
+	CLASS(hb, hb)(&key);
 
 	/* Make sure we really have tasks to wakeup */
 	if (!futex_hb_waiters_pending(hb))
@@ -253,7 +252,6 @@ int futex_wake_op(u32 __user *uaddr1, unsigned int flags, u32 __user *uaddr2,
 		  int nr_wake, int nr_wake2, int op)
 {
 	union futex_key key1 = FUTEX_KEY_INIT, key2 = FUTEX_KEY_INIT;
-	struct futex_hash_bucket *hb1, *hb2;
 	struct futex_q *this, *next;
 	int ret, op_ret;
 	DEFINE_WAKE_Q(wake_q);
@@ -266,67 +264,69 @@ retry:
 	if (unlikely(ret != 0))
 		return ret;
 
-	hb1 = futex_hash(&key1);
-	hb2 = futex_hash(&key2);
-
 retry_private:
-	double_lock_hb(hb1, hb2);
-	op_ret = futex_atomic_op_inuser(op, uaddr2);
-	if (unlikely(op_ret < 0)) {
-		double_unlock_hb(hb1, hb2);
-
-		if (!IS_ENABLED(CONFIG_MMU) ||
-		    unlikely(op_ret != -EFAULT && op_ret != -EAGAIN)) {
-			/*
-			 * we don't get EFAULT from MMU faults if we don't have
-			 * an MMU, but we might get them from range checking
-			 */
-			ret = op_ret;
-			return ret;
-		}
-
-		if (op_ret == -EFAULT) {
-			ret = fault_in_user_writeable(uaddr2);
-			if (ret)
+	if (1) {
+		CLASS(hb, hb1)(&key1);
+		CLASS(hb, hb2)(&key2);
+
+		double_lock_hb(hb1, hb2);
+		op_ret = futex_atomic_op_inuser(op, uaddr2);
+		if (unlikely(op_ret < 0)) {
+			double_unlock_hb(hb1, hb2);
+
+			if (!IS_ENABLED(CONFIG_MMU) ||
+			    unlikely(op_ret != -EFAULT && op_ret != -EAGAIN)) {
+				/*
+				 * we don't get EFAULT from MMU faults if we don't have
+				 * an MMU, but we might get them from range checking
+				 */
+				ret = op_ret;
 				return ret;
-		}
-
-		cond_resched();
-		if (!(flags & FLAGS_SHARED))
-			goto retry_private;
-		goto retry;
-	}
+			}
 
-	plist_for_each_entry_safe(this, next, &hb1->chain, list) {
-		if (futex_match (&this->key, &key1)) {
-			if (this->pi_state || this->rt_waiter) {
-				ret = -EINVAL;
-				goto out_unlock;
+			if (op_ret == -EFAULT) {
+				ret = fault_in_user_writeable(uaddr2);
+				if (ret)
+					return ret;
 			}
-			this->wake(&wake_q, this);
-			if (++ret >= nr_wake)
-				break;
+
+			cond_resched();
+			if (!(flags & FLAGS_SHARED))
+				goto retry_private;
+			goto retry;
 		}
-	}
 
-	if (op_ret > 0) {
-		op_ret = 0;
-		plist_for_each_entry_safe(this, next, &hb2->chain, list) {
-			if (futex_match (&this->key, &key2)) {
+		plist_for_each_entry_safe(this, next, &hb1->chain, list) {
+			if (futex_match(&this->key, &key1)) {
 				if (this->pi_state || this->rt_waiter) {
 					ret = -EINVAL;
 					goto out_unlock;
 				}
 				this->wake(&wake_q, this);
-				if (++op_ret >= nr_wake2)
+				if (++ret >= nr_wake)
 					break;
 			}
 		}
-		ret += op_ret;
-	}
+
+		if (op_ret > 0) {
+			op_ret = 0;
+			plist_for_each_entry_safe(this, next, &hb2->chain, list) {
+				if (futex_match(&this->key, &key2)) {
+					if (this->pi_state || this->rt_waiter) {
+						ret = -EINVAL;
+						goto out_unlock;
+					}
+					this->wake(&wake_q, this);
+					if (++op_ret >= nr_wake2)
+						break;
+				}
+			}
+			ret += op_ret;
+		}
 
 out_unlock:
-	double_unlock_hb(hb1, hb2);
+		double_unlock_hb(hb1, hb2);
+	}
 	wake_up_q(&wake_q);
 	return ret;
 }
@@ -334,23 +334,12 @@ out_unlock:
 static long futex_wait_restart(struct restart_block *restart);
 
 /**
- * futex_wait_queue() - futex_queue() and wait for wakeup, timeout, or signal
- * @hb:		the futex hash bucket, must be locked by the caller
+ * futex_do_wait() - wait for wakeup, timeout, or signal
  * @q:		the futex_q to queue up on
  * @timeout:	the prepared hrtimer_sleeper, or null for no timeout
  */
-void futex_wait_queue(struct futex_hash_bucket *hb, struct futex_q *q,
-			    struct hrtimer_sleeper *timeout)
+void futex_do_wait(struct futex_q *q, struct hrtimer_sleeper *timeout)
 {
-	/*
-	 * The task state is guaranteed to be set before another task can
-	 * wake it. set_current_state() is implemented using smp_store_mb() and
-	 * futex_queue() calls spin_unlock() upon completion, both serializing
-	 * access to the hash list and forcing another memory barrier.
-	 */
-	set_current_state(TASK_INTERRUPTIBLE|TASK_FREEZABLE);
-	futex_queue(q, hb, current);
-
 	/* Arm the timer */
 	if (timeout)
 		hrtimer_sleeper_start_expires(timeout, HRTIMER_MODE_ABS);
@@ -412,12 +401,17 @@ int futex_unqueue_multiple(struct futex_vector *v, int count)
  */
 int futex_wait_multiple_setup(struct futex_vector *vs, int count, int *woken)
 {
-	struct futex_hash_bucket *hb;
 	bool retry = false;
 	int ret, i;
 	u32 uval;
 
 	/*
+	 * Make sure to have a reference on the private_hash such that we
+	 * don't block on rehash after changing the task state below.
+	 */
+	guard(private_hash)();
+
+	/*
 	 * Enqueuing multiple futexes is tricky, because we need to enqueue
 	 * each futex on the list before dealing with the next one to avoid
 	 * deadlocking on the hash bucket. But, before enqueuing, we need to
@@ -451,20 +445,24 @@ retry:
 		struct futex_q *q = &vs[i].q;
 		u32 val = vs[i].w.val;
 
-		hb = futex_q_lock(q);
-		ret = futex_get_value_locked(&uval, uaddr);
+		if (1) {
+			CLASS(hb, hb)(&q->key);
 
-		if (!ret && uval == val) {
-			/*
-			 * The bucket lock can't be held while dealing with the
-			 * next futex. Queue each futex at this moment so hb can
-			 * be unlocked.
-			 */
-			futex_queue(q, hb, current);
-			continue;
-		}
+			futex_q_lock(q, hb);
+			ret = futex_get_value_locked(&uval, uaddr);
+
+			if (!ret && uval == val) {
+				/*
+				 * The bucket lock can't be held while dealing with the
+				 * next futex. Queue each futex at this moment so hb can
+				 * be unlocked.
+				 */
+				futex_queue(q, hb, current);
+				continue;
+			}
 
-		futex_q_unlock(hb);
+			futex_q_unlock(hb);
+		}
 		__set_current_state(TASK_RUNNING);
 
 		/*
@@ -578,7 +576,8 @@ int futex_wait_multiple(struct futex_vector *vs, unsigned int count,
  * @val:	the expected value
  * @flags:	futex flags (FLAGS_SHARED, etc.)
  * @q:		the associated futex_q
- * @hb:		storage for hash_bucket pointer to be returned to caller
+ * @key2:	the second futex_key if used for requeue PI
+ * @task:	Task queueing this futex
  *
  * Setup the futex_q and locate the hash_bucket.  Get the futex value and
  * compare it with the expected value.  Handle atomic faults internally.
@@ -586,10 +585,12 @@ int futex_wait_multiple(struct futex_vector *vs, unsigned int count,
  *
  * Return:
  *  -  0 - uaddr contains val and hb has been locked;
- *  - <1 - -EFAULT or -EWOULDBLOCK (uaddr does not contain val) and hb is unlocked
+ *  - <0 - On error and the hb is unlocked. A possible reason: the uaddr can not
+ *	   be read, does not contain the expected value or is not properly aligned.
  */
 int futex_wait_setup(u32 __user *uaddr, u32 val, unsigned int flags,
-		     struct futex_q *q, struct futex_hash_bucket **hb)
+		     struct futex_q *q, union futex_key *key2,
+		     struct task_struct *task)
 {
 	u32 uval;
 	int ret;
@@ -618,26 +619,45 @@ retry:
 		return ret;
 
 retry_private:
-	*hb = futex_q_lock(q);
+	if (1) {
+		CLASS(hb, hb)(&q->key);
 
-	ret = futex_get_value_locked(&uval, uaddr);
+		futex_q_lock(q, hb);
 
-	if (ret) {
-		futex_q_unlock(*hb);
+		ret = futex_get_value_locked(&uval, uaddr);
 
-		ret = get_user(uval, uaddr);
-		if (ret)
-			return ret;
+		if (ret) {
+			futex_q_unlock(hb);
 
-		if (!(flags & FLAGS_SHARED))
-			goto retry_private;
+			ret = get_user(uval, uaddr);
+			if (ret)
+				return ret;
 
-		goto retry;
-	}
+			if (!(flags & FLAGS_SHARED))
+				goto retry_private;
+
+			goto retry;
+		}
 
-	if (uval != val) {
-		futex_q_unlock(*hb);
-		ret = -EWOULDBLOCK;
+		if (uval != val) {
+			futex_q_unlock(hb);
+			return -EWOULDBLOCK;
+		}
+
+		if (key2 && futex_match(&q->key, key2)) {
+			futex_q_unlock(hb);
+			return -EINVAL;
+		}
+
+		/*
+		 * The task state is guaranteed to be set before another task can
+		 * wake it. set_current_state() is implemented using smp_store_mb() and
+		 * futex_queue() calls spin_unlock() upon completion, both serializing
+		 * access to the hash list and forcing another memory barrier.
+		 */
+		if (task == current)
+			set_current_state(TASK_INTERRUPTIBLE|TASK_FREEZABLE);
+		futex_queue(q, hb, task);
 	}
 
 	return ret;
@@ -647,7 +667,6 @@ int __futex_wait(u32 __user *uaddr, unsigned int flags, u32 val,
 		 struct hrtimer_sleeper *to, u32 bitset)
 {
 	struct futex_q q = futex_q_init;
-	struct futex_hash_bucket *hb;
 	int ret;
 
 	if (!bitset)
@@ -660,12 +679,12 @@ retry:
 	 * Prepare to wait on uaddr. On success, it holds hb->lock and q
 	 * is initialized.
 	 */
-	ret = futex_wait_setup(uaddr, val, flags, &q, &hb);
+	ret = futex_wait_setup(uaddr, val, flags, &q, NULL, current);
 	if (ret)
 		return ret;
 
 	/* futex_queue and wait for wakeup, timeout, or a signal. */
-	futex_wait_queue(hb, &q, to);
+	futex_do_wait(&q, to);
 
 	/* If we were woken (and unqueued), we succeeded, whatever. */
 	if (!futex_unqueue(&q))
diff --git a/kernel/gcov/gcc_4_7.c b/kernel/gcov/gcc_4_7.c
index fd75b4a484d7..a08cc076f332 100644
--- a/kernel/gcov/gcc_4_7.c
+++ b/kernel/gcov/gcc_4_7.c
@@ -22,10 +22,6 @@
 #define GCOV_COUNTERS			9
 #elif (__GNUC__ >= 10)
 #define GCOV_COUNTERS			8
-#elif (__GNUC__ >= 7)
-#define GCOV_COUNTERS			9
-#elif (__GNUC__ > 5) || (__GNUC__ == 5 && __GNUC_MINOR__ >= 1)
-#define GCOV_COUNTERS			10
 #else
 #define GCOV_COUNTERS			9
 #endif
diff --git a/kernel/hung_task.c b/kernel/hung_task.c
index dc898ec93463..d2432df2b905 100644
--- a/kernel/hung_task.c
+++ b/kernel/hung_task.c
@@ -22,6 +22,7 @@
 #include <linux/sched/signal.h>
 #include <linux/sched/debug.h>
 #include <linux/sched/sysctl.h>
+#include <linux/hung_task.h>
 
 #include <trace/events/sched.h>
 
@@ -98,30 +99,62 @@ static struct notifier_block panic_block = {
 static void debug_show_blocker(struct task_struct *task)
 {
 	struct task_struct *g, *t;
-	unsigned long owner;
-	struct mutex *lock;
+	unsigned long owner, blocker, blocker_type;
 
 	RCU_LOCKDEP_WARN(!rcu_read_lock_held(), "No rcu lock held");
 
-	lock = READ_ONCE(task->blocker_mutex);
-	if (!lock)
+	blocker = READ_ONCE(task->blocker);
+	if (!blocker)
 		return;
 
-	owner = mutex_get_owner(lock);
+	blocker_type = hung_task_get_blocker_type(blocker);
+
+	switch (blocker_type) {
+	case BLOCKER_TYPE_MUTEX:
+		owner = mutex_get_owner(
+			(struct mutex *)hung_task_blocker_to_lock(blocker));
+		break;
+	case BLOCKER_TYPE_SEM:
+		owner = sem_last_holder(
+			(struct semaphore *)hung_task_blocker_to_lock(blocker));
+		break;
+	default:
+		WARN_ON_ONCE(1);
+		return;
+	}
+
+
 	if (unlikely(!owner)) {
-		pr_err("INFO: task %s:%d is blocked on a mutex, but the owner is not found.\n",
-			task->comm, task->pid);
+		switch (blocker_type) {
+		case BLOCKER_TYPE_MUTEX:
+			pr_err("INFO: task %s:%d is blocked on a mutex, but the owner is not found.\n",
+			       task->comm, task->pid);
+			break;
+		case BLOCKER_TYPE_SEM:
+			pr_err("INFO: task %s:%d is blocked on a semaphore, but the last holder is not found.\n",
+			       task->comm, task->pid);
+			break;
+		}
 		return;
 	}
 
 	/* Ensure the owner information is correct. */
 	for_each_process_thread(g, t) {
-		if ((unsigned long)t == owner) {
+		if ((unsigned long)t != owner)
+			continue;
+
+		switch (blocker_type) {
+		case BLOCKER_TYPE_MUTEX:
 			pr_err("INFO: task %s:%d is blocked on a mutex likely owned by task %s:%d.\n",
-				task->comm, task->pid, t->comm, t->pid);
-			sched_show_task(t);
-			return;
+			       task->comm, task->pid, t->comm, t->pid);
+			break;
+		case BLOCKER_TYPE_SEM:
+			pr_err("INFO: task %s:%d blocked on a semaphore likely last held by task %s:%d\n",
+			       task->comm, task->pid, t->comm, t->pid);
+			break;
 		}
+		sched_show_task(t);
+		return;
 	}
 }
 #else
diff --git a/kernel/irq/autoprobe.c b/kernel/irq/autoprobe.c
index ae60cae24e9a..d0af8a8b3ae6 100644
--- a/kernel/irq/autoprobe.c
+++ b/kernel/irq/autoprobe.c
@@ -43,18 +43,16 @@ unsigned long probe_irq_on(void)
 	 * flush such a longstanding irq before considering it as spurious.
 	 */
 	for_each_irq_desc_reverse(i, desc) {
-		raw_spin_lock_irq(&desc->lock);
+		guard(raw_spinlock_irq)(&desc->lock);
 		if (!desc->action && irq_settings_can_probe(desc)) {
 			/*
 			 * Some chips need to know about probing in
 			 * progress:
 			 */
 			if (desc->irq_data.chip->irq_set_type)
-				desc->irq_data.chip->irq_set_type(&desc->irq_data,
-							 IRQ_TYPE_PROBE);
+				desc->irq_data.chip->irq_set_type(&desc->irq_data, IRQ_TYPE_PROBE);
 			irq_activate_and_startup(desc, IRQ_NORESEND);
 		}
-		raw_spin_unlock_irq(&desc->lock);
 	}
 
 	/* Wait for longstanding interrupts to trigger. */
@@ -66,13 +64,12 @@ unsigned long probe_irq_on(void)
 	 * happened in the previous stage, it may have masked itself)
 	 */
 	for_each_irq_desc_reverse(i, desc) {
-		raw_spin_lock_irq(&desc->lock);
+		guard(raw_spinlock_irq)(&desc->lock);
 		if (!desc->action && irq_settings_can_probe(desc)) {
 			desc->istate |= IRQS_AUTODETECT | IRQS_WAITING;
 			if (irq_activate_and_startup(desc, IRQ_NORESEND))
 				desc->istate |= IRQS_PENDING;
 		}
-		raw_spin_unlock_irq(&desc->lock);
 	}
 
 	/*
@@ -84,18 +81,16 @@ unsigned long probe_irq_on(void)
 	 * Now filter out any obviously spurious interrupts
 	 */
 	for_each_irq_desc(i, desc) {
-		raw_spin_lock_irq(&desc->lock);
-
+		guard(raw_spinlock_irq)(&desc->lock);
 		if (desc->istate & IRQS_AUTODETECT) {
 			/* It triggered already - consider it spurious. */
 			if (!(desc->istate & IRQS_WAITING)) {
 				desc->istate &= ~IRQS_AUTODETECT;
 				irq_shutdown_and_deactivate(desc);
-			} else
-				if (i < 32)
-					mask |= 1 << i;
+			} else if (i < 32) {
+				mask |= 1 << i;
+			}
 		}
-		raw_spin_unlock_irq(&desc->lock);
 	}
 
 	return mask;
@@ -121,7 +116,7 @@ unsigned int probe_irq_mask(unsigned long val)
 	int i;
 
 	for_each_irq_desc(i, desc) {
-		raw_spin_lock_irq(&desc->lock);
+		guard(raw_spinlock_irq)(&desc->lock);
 		if (desc->istate & IRQS_AUTODETECT) {
 			if (i < 16 && !(desc->istate & IRQS_WAITING))
 				mask |= 1 << i;
@@ -129,7 +124,6 @@ unsigned int probe_irq_mask(unsigned long val)
 			desc->istate &= ~IRQS_AUTODETECT;
 			irq_shutdown_and_deactivate(desc);
 		}
-		raw_spin_unlock_irq(&desc->lock);
 	}
 	mutex_unlock(&probing_active);
 
@@ -160,8 +154,7 @@ int probe_irq_off(unsigned long val)
 	struct irq_desc *desc;
 
 	for_each_irq_desc(i, desc) {
-		raw_spin_lock_irq(&desc->lock);
-
+		guard(raw_spinlock_irq)(&desc->lock);
 		if (desc->istate & IRQS_AUTODETECT) {
 			if (!(desc->istate & IRQS_WAITING)) {
 				if (!nr_of_irqs)
@@ -171,7 +164,6 @@ int probe_irq_off(unsigned long val)
 			desc->istate &= ~IRQS_AUTODETECT;
 			irq_shutdown_and_deactivate(desc);
 		}
-		raw_spin_unlock_irq(&desc->lock);
 	}
 	mutex_unlock(&probing_active);
 
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index 36cf1b09cc84..b0e0a7332993 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -34,98 +34,80 @@ struct irqaction chained_action = {
 };
 
 /**
- *	irq_set_chip - set the irq chip for an irq
- *	@irq:	irq number
- *	@chip:	pointer to irq chip description structure
+ * irq_set_chip - set the irq chip for an irq
+ * @irq:	irq number
+ * @chip:	pointer to irq chip description structure
  */
 int irq_set_chip(unsigned int irq, const struct irq_chip *chip)
 {
-	unsigned long flags;
-	struct irq_desc *desc = irq_get_desc_lock(irq, &flags, 0);
+	int ret = -EINVAL;
 
-	if (!desc)
-		return -EINVAL;
-
-	desc->irq_data.chip = (struct irq_chip *)(chip ?: &no_irq_chip);
-	irq_put_desc_unlock(desc, flags);
-	/*
-	 * For !CONFIG_SPARSE_IRQ make the irq show up in
-	 * allocated_irqs.
-	 */
-	irq_mark_irq(irq);
-	return 0;
+	scoped_irqdesc_get_and_lock(irq, 0) {
+		scoped_irqdesc->irq_data.chip = (struct irq_chip *)(chip ?: &no_irq_chip);
+		ret = 0;
+	}
+	/* For !CONFIG_SPARSE_IRQ make the irq show up in allocated_irqs. */
+	if (!ret)
+		irq_mark_irq(irq);
+	return ret;
 }
 EXPORT_SYMBOL(irq_set_chip);
 
 /**
- *	irq_set_irq_type - set the irq trigger type for an irq
- *	@irq:	irq number
- *	@type:	IRQ_TYPE_{LEVEL,EDGE}_* value - see include/linux/irq.h
+ * irq_set_irq_type - set the irq trigger type for an irq
+ * @irq:	irq number
+ * @type:	IRQ_TYPE_{LEVEL,EDGE}_* value - see include/linux/irq.h
  */
 int irq_set_irq_type(unsigned int irq, unsigned int type)
 {
-	unsigned long flags;
-	struct irq_desc *desc = irq_get_desc_buslock(irq, &flags, IRQ_GET_DESC_CHECK_GLOBAL);
-	int ret = 0;
-
-	if (!desc)
-		return -EINVAL;
-
-	ret = __irq_set_trigger(desc, type);
-	irq_put_desc_busunlock(desc, flags);
-	return ret;
+	scoped_irqdesc_get_and_buslock(irq, IRQ_GET_DESC_CHECK_GLOBAL)
+		return __irq_set_trigger(scoped_irqdesc, type);
+	return -EINVAL;
 }
 EXPORT_SYMBOL(irq_set_irq_type);
 
 /**
- *	irq_set_handler_data - set irq handler data for an irq
- *	@irq:	Interrupt number
- *	@data:	Pointer to interrupt specific data
+ * irq_set_handler_data - set irq handler data for an irq
+ * @irq:	Interrupt number
+ * @data:	Pointer to interrupt specific data
  *
- *	Set the hardware irq controller data for an irq
+ * Set the hardware irq controller data for an irq
  */
 int irq_set_handler_data(unsigned int irq, void *data)
 {
-	unsigned long flags;
-	struct irq_desc *desc = irq_get_desc_lock(irq, &flags, 0);
-
-	if (!desc)
-		return -EINVAL;
-	desc->irq_common_data.handler_data = data;
-	irq_put_desc_unlock(desc, flags);
-	return 0;
+	scoped_irqdesc_get_and_lock(irq, 0) {
+		scoped_irqdesc->irq_common_data.handler_data = data;
+		return 0;
+	}
+	return -EINVAL;
 }
 EXPORT_SYMBOL(irq_set_handler_data);
 
 /**
- *	irq_set_msi_desc_off - set MSI descriptor data for an irq at offset
- *	@irq_base:	Interrupt number base
- *	@irq_offset:	Interrupt number offset
- *	@entry:		Pointer to MSI descriptor data
+ * irq_set_msi_desc_off - set MSI descriptor data for an irq at offset
+ * @irq_base:	Interrupt number base
+ * @irq_offset:	Interrupt number offset
+ * @entry:		Pointer to MSI descriptor data
  *
- *	Set the MSI descriptor entry for an irq at offset
+ * Set the MSI descriptor entry for an irq at offset
  */
-int irq_set_msi_desc_off(unsigned int irq_base, unsigned int irq_offset,
-			 struct msi_desc *entry)
-{
-	unsigned long flags;
-	struct irq_desc *desc = irq_get_desc_lock(irq_base + irq_offset, &flags, IRQ_GET_DESC_CHECK_GLOBAL);
-
-	if (!desc)
-		return -EINVAL;
-	desc->irq_common_data.msi_desc = entry;
-	if (entry && !irq_offset)
-		entry->irq = irq_base;
-	irq_put_desc_unlock(desc, flags);
-	return 0;
+int irq_set_msi_desc_off(unsigned int irq_base, unsigned int irq_offset, struct msi_desc *entry)
+{
+	scoped_irqdesc_get_and_lock(irq_base + irq_offset, IRQ_GET_DESC_CHECK_GLOBAL) {
+		scoped_irqdesc->irq_common_data.msi_desc = entry;
+		if (entry && !irq_offset)
+			entry->irq = irq_base;
+		return 0;
+	}
+	return -EINVAL;
 }
 
 /**
- *	irq_set_msi_desc - set MSI descriptor data for an irq
- *	@irq:	Interrupt number
- *	@entry:	Pointer to MSI descriptor data
+ * irq_set_msi_desc - set MSI descriptor data for an irq
+ * @irq:	Interrupt number
+ * @entry:	Pointer to MSI descriptor data
  *
- *	Set the MSI descriptor entry for an irq
+ * Set the MSI descriptor entry for an irq
  */
 int irq_set_msi_desc(unsigned int irq, struct msi_desc *entry)
 {
@@ -133,22 +115,19 @@ int irq_set_msi_desc(unsigned int irq, struct msi_desc *entry)
 }
 
 /**
- *	irq_set_chip_data - set irq chip data for an irq
- *	@irq:	Interrupt number
- *	@data:	Pointer to chip specific data
+ * irq_set_chip_data - set irq chip data for an irq
+ * @irq:	Interrupt number
+ * @data:	Pointer to chip specific data
  *
- *	Set the hardware irq chip data for an irq
+ * Set the hardware irq chip data for an irq
  */
 int irq_set_chip_data(unsigned int irq, void *data)
 {
-	unsigned long flags;
-	struct irq_desc *desc = irq_get_desc_lock(irq, &flags, 0);
-
-	if (!desc)
-		return -EINVAL;
-	desc->irq_data.chip_data = data;
-	irq_put_desc_unlock(desc, flags);
-	return 0;
+	scoped_irqdesc_get_and_lock(irq, 0) {
+		scoped_irqdesc->irq_data.chip_data = data;
+		return 0;
+	}
+	return -EINVAL;
 }
 EXPORT_SYMBOL(irq_set_chip_data);
 
@@ -223,6 +202,19 @@ __irq_startup_managed(struct irq_desc *desc, const struct cpumask *aff,
 		return IRQ_STARTUP_ABORT;
 	return IRQ_STARTUP_MANAGED;
 }
+
+void irq_startup_managed(struct irq_desc *desc)
+{
+	/*
+	 * Only start it up when the disable depth is 1, so that a disable,
+	 * hotunplug, hotplug sequence does not end up enabling it during
+	 * hotplug unconditionally.
+	 */
+	desc->depth--;
+	if (!desc->depth)
+		irq_startup(desc, IRQ_RESEND, IRQ_START_COND);
+}
+
 #else
 static __always_inline int
 __irq_startup_managed(struct irq_desc *desc, const struct cpumask *aff,
@@ -290,6 +282,7 @@ int irq_startup(struct irq_desc *desc, bool resend, bool force)
 			ret = __irq_startup(desc);
 			break;
 		case IRQ_STARTUP_ABORT:
+			desc->depth = 1;
 			irqd_set_managed_shutdown(d);
 			return 0;
 		}
@@ -322,7 +315,13 @@ void irq_shutdown(struct irq_desc *desc)
 {
 	if (irqd_is_started(&desc->irq_data)) {
 		clear_irq_resend(desc);
-		desc->depth = 1;
+		/*
+		 * Increment disable depth, so that a managed shutdown on
+		 * CPU hotunplug preserves the actual disabled state when the
+		 * CPU comes back online. See irq_startup_managed().
+		 */
+		desc->depth++;
+
 		if (desc->irq_data.chip->irq_shutdown) {
 			desc->irq_data.chip->irq_shutdown(&desc->irq_data);
 			irq_state_set_disabled(desc);
@@ -450,48 +449,6 @@ void unmask_threaded_irq(struct irq_desc *desc)
 	unmask_irq(desc);
 }
 
-/*
- *	handle_nested_irq - Handle a nested irq from a irq thread
- *	@irq:	the interrupt number
- *
- *	Handle interrupts which are nested into a threaded interrupt
- *	handler. The handler function is called inside the calling
- *	threads context.
- */
-void handle_nested_irq(unsigned int irq)
-{
-	struct irq_desc *desc = irq_to_desc(irq);
-	struct irqaction *action;
-	irqreturn_t action_ret;
-
-	might_sleep();
-
-	raw_spin_lock_irq(&desc->lock);
-
-	desc->istate &= ~(IRQS_REPLAY | IRQS_WAITING);
-
-	action = desc->action;
-	if (unlikely(!action || irqd_irq_disabled(&desc->irq_data))) {
-		desc->istate |= IRQS_PENDING;
-		raw_spin_unlock_irq(&desc->lock);
-		return;
-	}
-
-	kstat_incr_irqs_this_cpu(desc);
-	atomic_inc(&desc->threads_active);
-	raw_spin_unlock_irq(&desc->lock);
-
-	action_ret = IRQ_NONE;
-	for_each_action_of_desc(desc, action)
-		action_ret |= action->thread_fn(action->irq, action->dev_id);
-
-	if (!irq_settings_no_debug(desc))
-		note_interrupt(desc, action_ret);
-
-	wake_threads_waitq(desc);
-}
-EXPORT_SYMBOL_GPL(handle_nested_irq);
-
 static bool irq_check_poll(struct irq_desc *desc)
 {
 	if (!(desc->istate & IRQS_POLL_INPROGRESS))
@@ -499,7 +456,7 @@ static bool irq_check_poll(struct irq_desc *desc)
 	return irq_wait_for_poll(desc);
 }
 
-static bool irq_may_run(struct irq_desc *desc)
+static bool irq_can_handle_pm(struct irq_desc *desc)
 {
 	unsigned int mask = IRQD_IRQ_INPROGRESS | IRQD_WAKEUP_ARMED;
 
@@ -524,77 +481,111 @@ static bool irq_may_run(struct irq_desc *desc)
 	return irq_check_poll(desc);
 }
 
+static inline bool irq_can_handle_actions(struct irq_desc *desc)
+{
+	desc->istate &= ~(IRQS_REPLAY | IRQS_WAITING);
+
+	if (unlikely(!desc->action || irqd_irq_disabled(&desc->irq_data))) {
+		desc->istate |= IRQS_PENDING;
+		return false;
+	}
+	return true;
+}
+
+static inline bool irq_can_handle(struct irq_desc *desc)
+{
+	if (!irq_can_handle_pm(desc))
+		return false;
+
+	return irq_can_handle_actions(desc);
+}
+
 /**
- *	handle_simple_irq - Simple and software-decoded IRQs.
- *	@desc:	the interrupt description structure for this irq
- *
- *	Simple interrupts are either sent from a demultiplexing interrupt
- *	handler or come from hardware, where no interrupt hardware control
- *	is necessary.
+ * handle_nested_irq - Handle a nested irq from a irq thread
+ * @irq:	the interrupt number
  *
- *	Note: The caller is expected to handle the ack, clear, mask and
- *	unmask issues if necessary.
+ * Handle interrupts which are nested into a threaded interrupt
+ * handler. The handler function is called inside the calling threads
+ * context.
  */
-void handle_simple_irq(struct irq_desc *desc)
+void handle_nested_irq(unsigned int irq)
 {
-	raw_spin_lock(&desc->lock);
+	struct irq_desc *desc = irq_to_desc(irq);
+	struct irqaction *action;
+	irqreturn_t action_ret;
 
-	if (!irq_may_run(desc))
-		goto out_unlock;
+	might_sleep();
 
-	desc->istate &= ~(IRQS_REPLAY | IRQS_WAITING);
+	scoped_guard(raw_spinlock_irq, &desc->lock) {
+		if (!irq_can_handle_actions(desc))
+			return;
 
-	if (unlikely(!desc->action || irqd_irq_disabled(&desc->irq_data))) {
-		desc->istate |= IRQS_PENDING;
-		goto out_unlock;
+		action = desc->action;
+		kstat_incr_irqs_this_cpu(desc);
+		atomic_inc(&desc->threads_active);
 	}
 
+	action_ret = IRQ_NONE;
+	for_each_action_of_desc(desc, action)
+		action_ret |= action->thread_fn(action->irq, action->dev_id);
+
+	if (!irq_settings_no_debug(desc))
+		note_interrupt(desc, action_ret);
+
+	wake_threads_waitq(desc);
+}
+EXPORT_SYMBOL_GPL(handle_nested_irq);
+
+/**
+ * handle_simple_irq - Simple and software-decoded IRQs.
+ * @desc:	the interrupt description structure for this irq
+ *
+ * Simple interrupts are either sent from a demultiplexing interrupt
+ * handler or come from hardware, where no interrupt hardware control is
+ * necessary.
+ *
+ * Note: The caller is expected to handle the ack, clear, mask and unmask
+ * issues if necessary.
+ */
+void handle_simple_irq(struct irq_desc *desc)
+{
+	guard(raw_spinlock)(&desc->lock);
+
+	if (!irq_can_handle(desc))
+		return;
+
 	kstat_incr_irqs_this_cpu(desc);
 	handle_irq_event(desc);
-
-out_unlock:
-	raw_spin_unlock(&desc->lock);
 }
 EXPORT_SYMBOL_GPL(handle_simple_irq);
 
 /**
- *	handle_untracked_irq - Simple and software-decoded IRQs.
- *	@desc:	the interrupt description structure for this irq
+ * handle_untracked_irq - Simple and software-decoded IRQs.
+ * @desc:	the interrupt description structure for this irq
  *
- *	Untracked interrupts are sent from a demultiplexing interrupt
- *	handler when the demultiplexer does not know which device it its
- *	multiplexed irq domain generated the interrupt. IRQ's handled
- *	through here are not subjected to stats tracking, randomness, or
- *	spurious interrupt detection.
+ * Untracked interrupts are sent from a demultiplexing interrupt handler
+ * when the demultiplexer does not know which device it its multiplexed irq
+ * domain generated the interrupt. IRQ's handled through here are not
+ * subjected to stats tracking, randomness, or spurious interrupt
+ * detection.
  *
- *	Note: Like handle_simple_irq, the caller is expected to handle
- *	the ack, clear, mask and unmask issues if necessary.
+ * Note: Like handle_simple_irq, the caller is expected to handle the ack,
+ * clear, mask and unmask issues if necessary.
  */
 void handle_untracked_irq(struct irq_desc *desc)
 {
-	raw_spin_lock(&desc->lock);
-
-	if (!irq_may_run(desc))
-		goto out_unlock;
-
-	desc->istate &= ~(IRQS_REPLAY | IRQS_WAITING);
+	scoped_guard(raw_spinlock, &desc->lock) {
+		if (!irq_can_handle(desc))
+			return;
 
-	if (unlikely(!desc->action || irqd_irq_disabled(&desc->irq_data))) {
-		desc->istate |= IRQS_PENDING;
-		goto out_unlock;
+		desc->istate &= ~IRQS_PENDING;
+		irqd_set(&desc->irq_data, IRQD_IRQ_INPROGRESS);
 	}
 
-	desc->istate &= ~IRQS_PENDING;
-	irqd_set(&desc->irq_data, IRQD_IRQ_INPROGRESS);
-	raw_spin_unlock(&desc->lock);
-
 	__handle_irq_event_percpu(desc);
 
-	raw_spin_lock(&desc->lock);
-	irqd_clear(&desc->irq_data, IRQD_IRQ_INPROGRESS);
-
-out_unlock:
-	raw_spin_unlock(&desc->lock);
+	scoped_guard(raw_spinlock, &desc->lock)
+		irqd_clear(&desc->irq_data, IRQD_IRQ_INPROGRESS);
 }
 EXPORT_SYMBOL_GPL(handle_untracked_irq);
 
@@ -617,40 +608,26 @@ static void cond_unmask_irq(struct irq_desc *desc)
 }
 
 /**
- *	handle_level_irq - Level type irq handler
- *	@desc:	the interrupt description structure for this irq
+ * handle_level_irq - Level type irq handler
+ * @desc:	the interrupt description structure for this irq
  *
- *	Level type interrupts are active as long as the hardware line has
- *	the active level. This may require to mask the interrupt and unmask
- *	it after the associated handler has acknowledged the device, so the
- *	interrupt line is back to inactive.
+ * Level type interrupts are active as long as the hardware line has the
+ * active level. This may require to mask the interrupt and unmask it after
+ * the associated handler has acknowledged the device, so the interrupt
+ * line is back to inactive.
  */
 void handle_level_irq(struct irq_desc *desc)
 {
-	raw_spin_lock(&desc->lock);
+	guard(raw_spinlock)(&desc->lock);
 	mask_ack_irq(desc);
 
-	if (!irq_may_run(desc))
-		goto out_unlock;
-
-	desc->istate &= ~(IRQS_REPLAY | IRQS_WAITING);
-
-	/*
-	 * If its disabled or no action available
-	 * keep it masked and get out of here
-	 */
-	if (unlikely(!desc->action || irqd_irq_disabled(&desc->irq_data))) {
-		desc->istate |= IRQS_PENDING;
-		goto out_unlock;
-	}
+	if (!irq_can_handle(desc))
+		return;
 
 	kstat_incr_irqs_this_cpu(desc);
 	handle_irq_event(desc);
 
 	cond_unmask_irq(desc);
-
-out_unlock:
-	raw_spin_unlock(&desc->lock);
 }
 EXPORT_SYMBOL_GPL(handle_level_irq);
 
@@ -675,42 +652,43 @@ static void cond_unmask_eoi_irq(struct irq_desc *desc, struct irq_chip *chip)
 	}
 }
 
+static inline void cond_eoi_irq(struct irq_chip *chip, struct irq_data *data)
+{
+	if (!(chip->flags & IRQCHIP_EOI_IF_HANDLED))
+		chip->irq_eoi(data);
+}
+
 /**
- *	handle_fasteoi_irq - irq handler for transparent controllers
- *	@desc:	the interrupt description structure for this irq
+ * handle_fasteoi_irq - irq handler for transparent controllers
+ * @desc:	the interrupt description structure for this irq
  *
- *	Only a single callback will be issued to the chip: an ->eoi()
- *	call when the interrupt has been serviced. This enables support
- *	for modern forms of interrupt handlers, which handle the flow
- *	details in hardware, transparently.
+ * Only a single callback will be issued to the chip: an ->eoi() call when
+ * the interrupt has been serviced. This enables support for modern forms
+ * of interrupt handlers, which handle the flow details in hardware,
+ * transparently.
  */
 void handle_fasteoi_irq(struct irq_desc *desc)
 {
 	struct irq_chip *chip = desc->irq_data.chip;
 
-	raw_spin_lock(&desc->lock);
+	guard(raw_spinlock)(&desc->lock);
 
 	/*
 	 * When an affinity change races with IRQ handling, the next interrupt
 	 * can arrive on the new CPU before the original CPU has completed
 	 * handling the previous one - it may need to be resent.
 	 */
-	if (!irq_may_run(desc)) {
+	if (!irq_can_handle_pm(desc)) {
 		if (irqd_needs_resend_when_in_progress(&desc->irq_data))
 			desc->istate |= IRQS_PENDING;
-		goto out;
+		cond_eoi_irq(chip, &desc->irq_data);
+		return;
 	}
 
-	desc->istate &= ~(IRQS_REPLAY | IRQS_WAITING);
-
-	/*
-	 * If its disabled or no action available
-	 * then mask it and get out of here:
-	 */
-	if (unlikely(!desc->action || irqd_irq_disabled(&desc->irq_data))) {
-		desc->istate |= IRQS_PENDING;
+	if (!irq_can_handle_actions(desc)) {
 		mask_irq(desc);
-		goto out;
+		cond_eoi_irq(chip, &desc->irq_data);
+		return;
 	}
 
 	kstat_incr_irqs_this_cpu(desc);
@@ -726,13 +704,6 @@ void handle_fasteoi_irq(struct irq_desc *desc)
 	 */
 	if (unlikely(desc->istate & IRQS_PENDING))
 		check_irq_resend(desc, false);
-
-	raw_spin_unlock(&desc->lock);
-	return;
-out:
-	if (!(chip->flags & IRQCHIP_EOI_IF_HANDLED))
-		chip->irq_eoi(&desc->irq_data);
-	raw_spin_unlock(&desc->lock);
 }
 EXPORT_SYMBOL_GPL(handle_fasteoi_irq);
 
@@ -770,40 +741,27 @@ void handle_fasteoi_nmi(struct irq_desc *desc)
 EXPORT_SYMBOL_GPL(handle_fasteoi_nmi);
 
 /**
- *	handle_edge_irq - edge type IRQ handler
- *	@desc:	the interrupt description structure for this irq
+ * handle_edge_irq - edge type IRQ handler
+ * @desc:	the interrupt description structure for this irq
  *
- *	Interrupt occurs on the falling and/or rising edge of a hardware
- *	signal. The occurrence is latched into the irq controller hardware
- *	and must be acked in order to be reenabled. After the ack another
- *	interrupt can happen on the same source even before the first one
- *	is handled by the associated event handler. If this happens it
- *	might be necessary to disable (mask) the interrupt depending on the
- *	controller hardware. This requires to reenable the interrupt inside
- *	of the loop which handles the interrupts which have arrived while
- *	the handler was running. If all pending interrupts are handled, the
- *	loop is left.
+ * Interrupt occurs on the falling and/or rising edge of a hardware
+ * signal. The occurrence is latched into the irq controller hardware and
+ * must be acked in order to be reenabled. After the ack another interrupt
+ * can happen on the same source even before the first one is handled by
+ * the associated event handler. If this happens it might be necessary to
+ * disable (mask) the interrupt depending on the controller hardware. This
+ * requires to reenable the interrupt inside of the loop which handles the
+ * interrupts which have arrived while the handler was running. If all
+ * pending interrupts are handled, the loop is left.
  */
 void handle_edge_irq(struct irq_desc *desc)
 {
-	raw_spin_lock(&desc->lock);
-
-	desc->istate &= ~(IRQS_REPLAY | IRQS_WAITING);
-
-	if (!irq_may_run(desc)) {
-		desc->istate |= IRQS_PENDING;
-		mask_ack_irq(desc);
-		goto out_unlock;
-	}
+	guard(raw_spinlock)(&desc->lock);
 
-	/*
-	 * If its disabled or no action available then mask it and get
-	 * out of here.
-	 */
-	if (irqd_irq_disabled(&desc->irq_data) || !desc->action) {
+	if (!irq_can_handle(desc)) {
 		desc->istate |= IRQS_PENDING;
 		mask_ack_irq(desc);
-		goto out_unlock;
+		return;
 	}
 
 	kstat_incr_irqs_this_cpu(desc);
@@ -814,7 +772,7 @@ void handle_edge_irq(struct irq_desc *desc)
 	do {
 		if (unlikely(!desc->action)) {
 			mask_irq(desc);
-			goto out_unlock;
+			return;
 		}
 
 		/*
@@ -830,11 +788,7 @@ void handle_edge_irq(struct irq_desc *desc)
 
 		handle_irq_event(desc);
 
-	} while ((desc->istate & IRQS_PENDING) &&
-		 !irqd_irq_disabled(&desc->irq_data));
-
-out_unlock:
-	raw_spin_unlock(&desc->lock);
+	} while ((desc->istate & IRQS_PENDING) && !irqd_irq_disabled(&desc->irq_data));
 }
 EXPORT_SYMBOL(handle_edge_irq);
 
@@ -1007,35 +961,23 @@ __irq_do_set_handler(struct irq_desc *desc, irq_flow_handler_t handle,
 	}
 }
 
-void
-__irq_set_handler(unsigned int irq, irq_flow_handler_t handle, int is_chained,
-		  const char *name)
+void __irq_set_handler(unsigned int irq, irq_flow_handler_t handle, int is_chained,
+		       const char *name)
 {
-	unsigned long flags;
-	struct irq_desc *desc = irq_get_desc_buslock(irq, &flags, 0);
-
-	if (!desc)
-		return;
-
-	__irq_do_set_handler(desc, handle, is_chained, name);
-	irq_put_desc_busunlock(desc, flags);
+	scoped_irqdesc_get_and_lock(irq, 0)
+		__irq_do_set_handler(scoped_irqdesc, handle, is_chained, name);
 }
 EXPORT_SYMBOL_GPL(__irq_set_handler);
 
-void
-irq_set_chained_handler_and_data(unsigned int irq, irq_flow_handler_t handle,
-				 void *data)
+void irq_set_chained_handler_and_data(unsigned int irq, irq_flow_handler_t handle,
+				      void *data)
 {
-	unsigned long flags;
-	struct irq_desc *desc = irq_get_desc_buslock(irq, &flags, 0);
-
-	if (!desc)
-		return;
-
-	desc->irq_common_data.handler_data = data;
-	__irq_do_set_handler(desc, handle, 1, NULL);
+	scoped_irqdesc_get_and_buslock(irq, 0) {
+		struct irq_desc *desc = scoped_irqdesc;
 
-	irq_put_desc_busunlock(desc, flags);
+		desc->irq_common_data.handler_data = data;
+		__irq_do_set_handler(desc, handle, 1, NULL);
+	}
 }
 EXPORT_SYMBOL_GPL(irq_set_chained_handler_and_data);
 
@@ -1050,38 +992,34 @@ EXPORT_SYMBOL_GPL(irq_set_chip_and_handler_name);
 
 void irq_modify_status(unsigned int irq, unsigned long clr, unsigned long set)
 {
-	unsigned long flags, trigger, tmp;
-	struct irq_desc *desc = irq_get_desc_lock(irq, &flags, 0);
-
-	if (!desc)
-		return;
-
-	/*
-	 * Warn when a driver sets the no autoenable flag on an already
-	 * active interrupt.
-	 */
-	WARN_ON_ONCE(!desc->depth && (set & _IRQ_NOAUTOEN));
-
-	irq_settings_clr_and_set(desc, clr, set);
+	scoped_irqdesc_get_and_lock(irq, 0) {
+		struct irq_desc *desc = scoped_irqdesc;
+		unsigned long trigger, tmp;
+		/*
+		 * Warn when a driver sets the no autoenable flag on an already
+		 * active interrupt.
+		 */
+		WARN_ON_ONCE(!desc->depth && (set & _IRQ_NOAUTOEN));
 
-	trigger = irqd_get_trigger_type(&desc->irq_data);
+		irq_settings_clr_and_set(desc, clr, set);
 
-	irqd_clear(&desc->irq_data, IRQD_NO_BALANCING | IRQD_PER_CPU |
-		   IRQD_TRIGGER_MASK | IRQD_LEVEL);
-	if (irq_settings_has_no_balance_set(desc))
-		irqd_set(&desc->irq_data, IRQD_NO_BALANCING);
-	if (irq_settings_is_per_cpu(desc))
-		irqd_set(&desc->irq_data, IRQD_PER_CPU);
-	if (irq_settings_is_level(desc))
-		irqd_set(&desc->irq_data, IRQD_LEVEL);
+		trigger = irqd_get_trigger_type(&desc->irq_data);
 
-	tmp = irq_settings_get_trigger_mask(desc);
-	if (tmp != IRQ_TYPE_NONE)
-		trigger = tmp;
+		irqd_clear(&desc->irq_data, IRQD_NO_BALANCING | IRQD_PER_CPU |
+			   IRQD_TRIGGER_MASK | IRQD_LEVEL);
+		if (irq_settings_has_no_balance_set(desc))
+			irqd_set(&desc->irq_data, IRQD_NO_BALANCING);
+		if (irq_settings_is_per_cpu(desc))
+			irqd_set(&desc->irq_data, IRQD_PER_CPU);
+		if (irq_settings_is_level(desc))
+			irqd_set(&desc->irq_data, IRQD_LEVEL);
 
-	irqd_set(&desc->irq_data, trigger);
+		tmp = irq_settings_get_trigger_mask(desc);
+		if (tmp != IRQ_TYPE_NONE)
+			trigger = tmp;
 
-	irq_put_desc_unlock(desc, flags);
+		irqd_set(&desc->irq_data, trigger);
+	}
 }
 EXPORT_SYMBOL_GPL(irq_modify_status);
 
@@ -1094,25 +1032,21 @@ EXPORT_SYMBOL_GPL(irq_modify_status);
  */
 void irq_cpu_online(void)
 {
-	struct irq_desc *desc;
-	struct irq_chip *chip;
-	unsigned long flags;
 	unsigned int irq;
 
 	for_each_active_irq(irq) {
-		desc = irq_to_desc(irq);
+		struct irq_desc *desc = irq_to_desc(irq);
+		struct irq_chip *chip;
+
 		if (!desc)
 			continue;
 
-		raw_spin_lock_irqsave(&desc->lock, flags);
-
+		guard(raw_spinlock_irqsave)(&desc->lock);
 		chip = irq_data_get_irq_chip(&desc->irq_data);
 		if (chip && chip->irq_cpu_online &&
 		    (!(chip->flags & IRQCHIP_ONOFFLINE_ENABLED) ||
 		     !irqd_irq_disabled(&desc->irq_data)))
 			chip->irq_cpu_online(&desc->irq_data);
-
-		raw_spin_unlock_irqrestore(&desc->lock, flags);
 	}
 }
 
@@ -1124,25 +1058,21 @@ void irq_cpu_online(void)
  */
 void irq_cpu_offline(void)
 {
-	struct irq_desc *desc;
-	struct irq_chip *chip;
-	unsigned long flags;
 	unsigned int irq;
 
 	for_each_active_irq(irq) {
-		desc = irq_to_desc(irq);
+		struct irq_desc *desc = irq_to_desc(irq);
+		struct irq_chip *chip;
+
 		if (!desc)
 			continue;
 
-		raw_spin_lock_irqsave(&desc->lock, flags);
-
+		guard(raw_spinlock_irqsave)(&desc->lock);
 		chip = irq_data_get_irq_chip(&desc->irq_data);
 		if (chip && chip->irq_cpu_offline &&
 		    (!(chip->flags & IRQCHIP_ONOFFLINE_ENABLED) ||
 		     !irqd_irq_disabled(&desc->irq_data)))
 			chip->irq_cpu_offline(&desc->irq_data);
-
-		raw_spin_unlock_irqrestore(&desc->lock, flags);
 	}
 }
 #endif
@@ -1151,102 +1081,69 @@ void irq_cpu_offline(void)
 
 #ifdef CONFIG_IRQ_FASTEOI_HIERARCHY_HANDLERS
 /**
- *	handle_fasteoi_ack_irq - irq handler for edge hierarchy
- *	stacked on transparent controllers
+ * handle_fasteoi_ack_irq - irq handler for edge hierarchy stacked on
+ *			    transparent controllers
  *
- *	@desc:	the interrupt description structure for this irq
+ * @desc:	the interrupt description structure for this irq
  *
- *	Like handle_fasteoi_irq(), but for use with hierarchy where
- *	the irq_chip also needs to have its ->irq_ack() function
- *	called.
+ * Like handle_fasteoi_irq(), but for use with hierarchy where the irq_chip
+ * also needs to have its ->irq_ack() function called.
  */
 void handle_fasteoi_ack_irq(struct irq_desc *desc)
 {
 	struct irq_chip *chip = desc->irq_data.chip;
 
-	raw_spin_lock(&desc->lock);
-
-	if (!irq_may_run(desc))
-		goto out;
+	guard(raw_spinlock)(&desc->lock);
 
-	desc->istate &= ~(IRQS_REPLAY | IRQS_WAITING);
+	if (!irq_can_handle_pm(desc)) {
+		cond_eoi_irq(chip, &desc->irq_data);
+		return;
+	}
 
-	/*
-	 * If its disabled or no action available
-	 * then mask it and get out of here:
-	 */
-	if (unlikely(!desc->action || irqd_irq_disabled(&desc->irq_data))) {
-		desc->istate |= IRQS_PENDING;
+	if (unlikely(!irq_can_handle_actions(desc))) {
 		mask_irq(desc);
-		goto out;
+		cond_eoi_irq(chip, &desc->irq_data);
+		return;
 	}
 
 	kstat_incr_irqs_this_cpu(desc);
 	if (desc->istate & IRQS_ONESHOT)
 		mask_irq(desc);
 
-	/* Start handling the irq */
 	desc->irq_data.chip->irq_ack(&desc->irq_data);
 
 	handle_irq_event(desc);
 
 	cond_unmask_eoi_irq(desc, chip);
-
-	raw_spin_unlock(&desc->lock);
-	return;
-out:
-	if (!(chip->flags & IRQCHIP_EOI_IF_HANDLED))
-		chip->irq_eoi(&desc->irq_data);
-	raw_spin_unlock(&desc->lock);
 }
 EXPORT_SYMBOL_GPL(handle_fasteoi_ack_irq);
 
 /**
- *	handle_fasteoi_mask_irq - irq handler for level hierarchy
- *	stacked on transparent controllers
+ * handle_fasteoi_mask_irq - irq handler for level hierarchy stacked on
+ *			     transparent controllers
  *
- *	@desc:	the interrupt description structure for this irq
+ * @desc:	the interrupt description structure for this irq
  *
- *	Like handle_fasteoi_irq(), but for use with hierarchy where
- *	the irq_chip also needs to have its ->irq_mask_ack() function
- *	called.
+ * Like handle_fasteoi_irq(), but for use with hierarchy where the irq_chip
+ * also needs to have its ->irq_mask_ack() function called.
  */
 void handle_fasteoi_mask_irq(struct irq_desc *desc)
 {
 	struct irq_chip *chip = desc->irq_data.chip;
 
-	raw_spin_lock(&desc->lock);
+	guard(raw_spinlock)(&desc->lock);
 	mask_ack_irq(desc);
 
-	if (!irq_may_run(desc))
-		goto out;
-
-	desc->istate &= ~(IRQS_REPLAY | IRQS_WAITING);
-
-	/*
-	 * If its disabled or no action available
-	 * then mask it and get out of here:
-	 */
-	if (unlikely(!desc->action || irqd_irq_disabled(&desc->irq_data))) {
-		desc->istate |= IRQS_PENDING;
-		mask_irq(desc);
-		goto out;
+	if (!irq_can_handle(desc)) {
+		cond_eoi_irq(chip, &desc->irq_data);
+		return;
 	}
 
 	kstat_incr_irqs_this_cpu(desc);
-	if (desc->istate & IRQS_ONESHOT)
-		mask_irq(desc);
 
 	handle_irq_event(desc);
 
 	cond_unmask_eoi_irq(desc, chip);
-
-	raw_spin_unlock(&desc->lock);
-	return;
-out:
-	if (!(chip->flags & IRQCHIP_EOI_IF_HANDLED))
-		chip->irq_eoi(&desc->irq_data);
-	raw_spin_unlock(&desc->lock);
 }
 EXPORT_SYMBOL_GPL(handle_fasteoi_mask_irq);
 
diff --git a/kernel/irq/cpuhotplug.c b/kernel/irq/cpuhotplug.c
index 15a7654eff68..f07529ae4895 100644
--- a/kernel/irq/cpuhotplug.c
+++ b/kernel/irq/cpuhotplug.c
@@ -177,9 +177,8 @@ void irq_migrate_all_off_this_cpu(void)
 		bool affinity_broken;
 
 		desc = irq_to_desc(irq);
-		raw_spin_lock(&desc->lock);
-		affinity_broken = migrate_one_irq(desc);
-		raw_spin_unlock(&desc->lock);
+		scoped_guard(raw_spinlock, &desc->lock)
+			affinity_broken = migrate_one_irq(desc);
 
 		if (affinity_broken) {
 			pr_debug_ratelimited("IRQ %u: no longer affine to CPU%u\n",
@@ -219,7 +218,7 @@ static void irq_restore_affinity_of_irq(struct irq_desc *desc, unsigned int cpu)
 		return;
 
 	if (irqd_is_managed_and_shutdown(data))
-		irq_startup(desc, IRQ_RESEND, IRQ_START_COND);
+		irq_startup_managed(desc);
 
 	/*
 	 * If the interrupt can only be directed to a single target
@@ -244,9 +243,8 @@ int irq_affinity_online_cpu(unsigned int cpu)
 	irq_lock_sparse();
 	for_each_active_irq(irq) {
 		desc = irq_to_desc(irq);
-		raw_spin_lock_irq(&desc->lock);
-		irq_restore_affinity_of_irq(desc, cpu);
-		raw_spin_unlock_irq(&desc->lock);
+		scoped_guard(raw_spinlock_irq, &desc->lock)
+			irq_restore_affinity_of_irq(desc, cpu);
 	}
 	irq_unlock_sparse();
 
diff --git a/kernel/irq/debugfs.c b/kernel/irq/debugfs.c
index ca142b9a4db3..3527defd2890 100644
--- a/kernel/irq/debugfs.c
+++ b/kernel/irq/debugfs.c
@@ -160,7 +160,7 @@ static int irq_debug_show(struct seq_file *m, void *p)
 	struct irq_desc *desc = m->private;
 	struct irq_data *data;
 
-	raw_spin_lock_irq(&desc->lock);
+	guard(raw_spinlock_irq)(&desc->lock);
 	data = irq_desc_get_irq_data(desc);
 	seq_printf(m, "handler:  %ps\n", desc->handle_irq);
 	seq_printf(m, "device:   %s\n", desc->dev_name);
@@ -178,7 +178,6 @@ static int irq_debug_show(struct seq_file *m, void *p)
 	seq_printf(m, "node:     %d\n", irq_data_get_node(data));
 	irq_debug_show_masks(m, desc);
 	irq_debug_show_data(m, data, 0);
-	raw_spin_unlock_irq(&desc->lock);
 	return 0;
 }
 
@@ -226,12 +225,12 @@ void irq_debugfs_copy_devname(int irq, struct device *dev)
 
 void irq_add_debugfs_entry(unsigned int irq, struct irq_desc *desc)
 {
-	char name [10];
+	char name [12];
 
 	if (!irq_dir || !desc || desc->debugfs_file)
 		return;
 
-	sprintf(name, "%d", irq);
+	sprintf(name, "%u", irq);
 	desc->debugfs_file = debugfs_create_file(name, 0644, irq_dir, desc,
 						 &dfs_irq_ops);
 }
diff --git a/kernel/irq/generic-chip.c b/kernel/irq/generic-chip.c
index c4a8bca5f2b0..bf59e37d650a 100644
--- a/kernel/irq/generic-chip.c
+++ b/kernel/irq/generic-chip.c
@@ -40,10 +40,9 @@ void irq_gc_mask_disable_reg(struct irq_data *d)
 	struct irq_chip_type *ct = irq_data_get_chip_type(d);
 	u32 mask = d->mask;
 
-	irq_gc_lock(gc);
+	guard(raw_spinlock)(&gc->lock);
 	irq_reg_writel(gc, mask, ct->regs.disable);
 	*ct->mask_cache &= ~mask;
-	irq_gc_unlock(gc);
 }
 EXPORT_SYMBOL_GPL(irq_gc_mask_disable_reg);
 
@@ -60,10 +59,9 @@ void irq_gc_mask_set_bit(struct irq_data *d)
 	struct irq_chip_type *ct = irq_data_get_chip_type(d);
 	u32 mask = d->mask;
 
-	irq_gc_lock(gc);
+	guard(raw_spinlock)(&gc->lock);
 	*ct->mask_cache |= mask;
 	irq_reg_writel(gc, *ct->mask_cache, ct->regs.mask);
-	irq_gc_unlock(gc);
 }
 EXPORT_SYMBOL_GPL(irq_gc_mask_set_bit);
 
@@ -80,10 +78,9 @@ void irq_gc_mask_clr_bit(struct irq_data *d)
 	struct irq_chip_type *ct = irq_data_get_chip_type(d);
 	u32 mask = d->mask;
 
-	irq_gc_lock(gc);
+	guard(raw_spinlock)(&gc->lock);
 	*ct->mask_cache &= ~mask;
 	irq_reg_writel(gc, *ct->mask_cache, ct->regs.mask);
-	irq_gc_unlock(gc);
 }
 EXPORT_SYMBOL_GPL(irq_gc_mask_clr_bit);
 
@@ -100,10 +97,9 @@ void irq_gc_unmask_enable_reg(struct irq_data *d)
 	struct irq_chip_type *ct = irq_data_get_chip_type(d);
 	u32 mask = d->mask;
 
-	irq_gc_lock(gc);
+	guard(raw_spinlock)(&gc->lock);
 	irq_reg_writel(gc, mask, ct->regs.enable);
 	*ct->mask_cache |= mask;
-	irq_gc_unlock(gc);
 }
 EXPORT_SYMBOL_GPL(irq_gc_unmask_enable_reg);
 
@@ -117,9 +113,8 @@ void irq_gc_ack_set_bit(struct irq_data *d)
 	struct irq_chip_type *ct = irq_data_get_chip_type(d);
 	u32 mask = d->mask;
 
-	irq_gc_lock(gc);
+	guard(raw_spinlock)(&gc->lock);
 	irq_reg_writel(gc, mask, ct->regs.ack);
-	irq_gc_unlock(gc);
 }
 EXPORT_SYMBOL_GPL(irq_gc_ack_set_bit);
 
@@ -133,9 +128,8 @@ void irq_gc_ack_clr_bit(struct irq_data *d)
 	struct irq_chip_type *ct = irq_data_get_chip_type(d);
 	u32 mask = ~d->mask;
 
-	irq_gc_lock(gc);
+	guard(raw_spinlock)(&gc->lock);
 	irq_reg_writel(gc, mask, ct->regs.ack);
-	irq_gc_unlock(gc);
 }
 
 /**
@@ -156,11 +150,10 @@ void irq_gc_mask_disable_and_ack_set(struct irq_data *d)
 	struct irq_chip_type *ct = irq_data_get_chip_type(d);
 	u32 mask = d->mask;
 
-	irq_gc_lock(gc);
+	guard(raw_spinlock)(&gc->lock);
 	irq_reg_writel(gc, mask, ct->regs.disable);
 	*ct->mask_cache &= ~mask;
 	irq_reg_writel(gc, mask, ct->regs.ack);
-	irq_gc_unlock(gc);
 }
 EXPORT_SYMBOL_GPL(irq_gc_mask_disable_and_ack_set);
 
@@ -174,9 +167,8 @@ void irq_gc_eoi(struct irq_data *d)
 	struct irq_chip_type *ct = irq_data_get_chip_type(d);
 	u32 mask = d->mask;
 
-	irq_gc_lock(gc);
+	guard(raw_spinlock)(&gc->lock);
 	irq_reg_writel(gc, mask, ct->regs.eoi);
-	irq_gc_unlock(gc);
 }
 
 /**
@@ -196,12 +188,11 @@ int irq_gc_set_wake(struct irq_data *d, unsigned int on)
 	if (!(mask & gc->wake_enabled))
 		return -EINVAL;
 
-	irq_gc_lock(gc);
+	guard(raw_spinlock)(&gc->lock);
 	if (on)
 		gc->wake_active |= mask;
 	else
 		gc->wake_active &= ~mask;
-	irq_gc_unlock(gc);
 	return 0;
 }
 EXPORT_SYMBOL_GPL(irq_gc_set_wake);
@@ -288,7 +279,6 @@ int irq_domain_alloc_generic_chips(struct irq_domain *d,
 {
 	struct irq_domain_chip_generic *dgc;
 	struct irq_chip_generic *gc;
-	unsigned long flags;
 	int numchips, i;
 	size_t dgc_sz;
 	size_t gc_sz;
@@ -340,9 +330,8 @@ int irq_domain_alloc_generic_chips(struct irq_domain *d,
 				goto err;
 		}
 
-		raw_spin_lock_irqsave(&gc_lock, flags);
-		list_add_tail(&gc->list, &gc_list);
-		raw_spin_unlock_irqrestore(&gc_lock, flags);
+		scoped_guard (raw_spinlock_irqsave, &gc_lock)
+			list_add_tail(&gc->list, &gc_list);
 		/* Calc pointer to the next generic chip */
 		tmp += gc_sz;
 	}
@@ -459,7 +448,6 @@ int irq_map_generic_chip(struct irq_domain *d, unsigned int virq,
 	struct irq_chip_generic *gc;
 	struct irq_chip_type *ct;
 	struct irq_chip *chip;
-	unsigned long flags;
 	int idx;
 
 	gc = __irq_get_domain_generic_chip(d, hw_irq);
@@ -479,9 +467,8 @@ int irq_map_generic_chip(struct irq_domain *d, unsigned int virq,
 
 	/* We only init the cache for the first mapping of a generic chip */
 	if (!gc->installed) {
-		raw_spin_lock_irqsave(&gc->lock, flags);
+		guard(raw_spinlock_irqsave)(&gc->lock);
 		irq_gc_init_mask_cache(gc, dgc->gc_flags);
-		raw_spin_unlock_irqrestore(&gc->lock, flags);
 	}
 
 	/* Mark the interrupt as installed */
@@ -548,9 +535,8 @@ void irq_setup_generic_chip(struct irq_chip_generic *gc, u32 msk,
 	struct irq_chip *chip = &ct->chip;
 	unsigned int i;
 
-	raw_spin_lock(&gc_lock);
-	list_add_tail(&gc->list, &gc_list);
-	raw_spin_unlock(&gc_lock);
+	scoped_guard (raw_spinlock, &gc_lock)
+		list_add_tail(&gc->list, &gc_list);
 
 	irq_gc_init_mask_cache(gc, flags);
 
@@ -616,9 +602,8 @@ void irq_remove_generic_chip(struct irq_chip_generic *gc, u32 msk,
 {
 	unsigned int i, virq;
 
-	raw_spin_lock(&gc_lock);
-	list_del(&gc->list);
-	raw_spin_unlock(&gc_lock);
+	scoped_guard (raw_spinlock, &gc_lock)
+		list_del(&gc->list);
 
 	for (i = 0; msk; msk >>= 1, i++) {
 		if (!(msk & 0x01))
diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h
index b0290849c395..aebfe225c9a6 100644
--- a/kernel/irq/internals.h
+++ b/kernel/irq/internals.h
@@ -87,6 +87,7 @@ extern void __enable_irq(struct irq_desc *desc);
 extern int irq_activate(struct irq_desc *desc);
 extern int irq_activate_and_startup(struct irq_desc *desc, bool resend);
 extern int irq_startup(struct irq_desc *desc, bool resend, bool force);
+extern void irq_startup_managed(struct irq_desc *desc);
 
 extern void irq_shutdown(struct irq_desc *desc);
 extern void irq_shutdown_and_deactivate(struct irq_desc *desc);
@@ -141,6 +142,10 @@ extern int irq_setup_affinity(struct irq_desc *desc);
 static inline int irq_setup_affinity(struct irq_desc *desc) { return 0; }
 #endif
 
+
+#define for_each_action_of_desc(desc, act)			\
+	for (act = desc->action; act; act = act->next)
+
 /* Inline functions for support of irq chips on slow busses */
 static inline void chip_bus_lock(struct irq_desc *desc)
 {
@@ -160,38 +165,33 @@ static inline void chip_bus_sync_unlock(struct irq_desc *desc)
 #define IRQ_GET_DESC_CHECK_GLOBAL	(_IRQ_DESC_CHECK)
 #define IRQ_GET_DESC_CHECK_PERCPU	(_IRQ_DESC_CHECK | _IRQ_DESC_PERCPU)
 
-#define for_each_action_of_desc(desc, act)			\
-	for (act = desc->action; act; act = act->next)
-
-struct irq_desc *
-__irq_get_desc_lock(unsigned int irq, unsigned long *flags, bool bus,
-		    unsigned int check);
+struct irq_desc *__irq_get_desc_lock(unsigned int irq, unsigned long *flags, bool bus,
+				     unsigned int check);
 void __irq_put_desc_unlock(struct irq_desc *desc, unsigned long flags, bool bus);
 
-static inline struct irq_desc *
-irq_get_desc_buslock(unsigned int irq, unsigned long *flags, unsigned int check)
-{
-	return __irq_get_desc_lock(irq, flags, true, check);
-}
+__DEFINE_CLASS_IS_CONDITIONAL(irqdesc_lock, true);
+__DEFINE_UNLOCK_GUARD(irqdesc_lock, struct irq_desc,
+		      __irq_put_desc_unlock(_T->lock, _T->flags, _T->bus),
+		      unsigned long flags; bool bus);
 
-static inline void
-irq_put_desc_busunlock(struct irq_desc *desc, unsigned long flags)
+static inline class_irqdesc_lock_t class_irqdesc_lock_constructor(unsigned int irq, bool bus,
+								  unsigned int check)
 {
-	__irq_put_desc_unlock(desc, flags, true);
-}
+	class_irqdesc_lock_t _t = { .bus = bus, };
 
-static inline struct irq_desc *
-irq_get_desc_lock(unsigned int irq, unsigned long *flags, unsigned int check)
-{
-	return __irq_get_desc_lock(irq, flags, false, check);
-}
+	_t.lock = __irq_get_desc_lock(irq, &_t.flags, bus, check);
 
-static inline void
-irq_put_desc_unlock(struct irq_desc *desc, unsigned long flags)
-{
-	__irq_put_desc_unlock(desc, flags, false);
+	return _t;
 }
 
+#define scoped_irqdesc_get_and_lock(_irq, _check)		\
+	scoped_guard(irqdesc_lock, _irq, false, _check)
+
+#define scoped_irqdesc_get_and_buslock(_irq, _check)		\
+	scoped_guard(irqdesc_lock, _irq, true, _check)
+
+#define scoped_irqdesc		((struct irq_desc *)(__guard_ptr(irqdesc_lock)(&scope)))
+
 #define __irqd_to_state(d) ACCESS_PRIVATE((d)->common, state_use_accessors)
 
 static inline unsigned int irqd_get(struct irq_data *d)
diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c
index 4258cd6bd3b4..b64c57b44c20 100644
--- a/kernel/irq/irqdesc.c
+++ b/kernel/irq/irqdesc.c
@@ -246,8 +246,7 @@ static struct kobject *irq_kobj_base;
 #define IRQ_ATTR_RO(_name) \
 static struct kobj_attribute _name##_attr = __ATTR_RO(_name)
 
-static ssize_t per_cpu_count_show(struct kobject *kobj,
-				  struct kobj_attribute *attr, char *buf)
+static ssize_t per_cpu_count_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf)
 {
 	struct irq_desc *desc = container_of(kobj, struct irq_desc, kobj);
 	ssize_t ret = 0;
@@ -257,112 +256,83 @@ static ssize_t per_cpu_count_show(struct kobject *kobj,
 	for_each_possible_cpu(cpu) {
 		unsigned int c = irq_desc_kstat_cpu(desc, cpu);
 
-		ret += scnprintf(buf + ret, PAGE_SIZE - ret, "%s%u", p, c);
+		ret += sysfs_emit_at(buf, ret, "%s%u", p, c);
 		p = ",";
 	}
 
-	ret += scnprintf(buf + ret, PAGE_SIZE - ret, "\n");
+	ret += sysfs_emit_at(buf, ret, "\n");
 	return ret;
 }
 IRQ_ATTR_RO(per_cpu_count);
 
-static ssize_t chip_name_show(struct kobject *kobj,
-			      struct kobj_attribute *attr, char *buf)
+static ssize_t chip_name_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf)
 {
 	struct irq_desc *desc = container_of(kobj, struct irq_desc, kobj);
-	ssize_t ret = 0;
-
-	raw_spin_lock_irq(&desc->lock);
-	if (desc->irq_data.chip && desc->irq_data.chip->name) {
-		ret = scnprintf(buf, PAGE_SIZE, "%s\n",
-				desc->irq_data.chip->name);
-	}
-	raw_spin_unlock_irq(&desc->lock);
 
-	return ret;
+	guard(raw_spinlock_irq)(&desc->lock);
+	if (desc->irq_data.chip && desc->irq_data.chip->name)
+		return sysfs_emit(buf, "%s\n", desc->irq_data.chip->name);
+	return 0;
 }
 IRQ_ATTR_RO(chip_name);
 
-static ssize_t hwirq_show(struct kobject *kobj,
-			  struct kobj_attribute *attr, char *buf)
+static ssize_t hwirq_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf)
 {
 	struct irq_desc *desc = container_of(kobj, struct irq_desc, kobj);
-	ssize_t ret = 0;
 
-	raw_spin_lock_irq(&desc->lock);
+	guard(raw_spinlock_irq)(&desc->lock);
 	if (desc->irq_data.domain)
-		ret = sprintf(buf, "%lu\n", desc->irq_data.hwirq);
-	raw_spin_unlock_irq(&desc->lock);
-
-	return ret;
+		return sysfs_emit(buf, "%lu\n", desc->irq_data.hwirq);
+	return 0;
 }
 IRQ_ATTR_RO(hwirq);
 
-static ssize_t type_show(struct kobject *kobj,
-			 struct kobj_attribute *attr, char *buf)
+static ssize_t type_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf)
 {
 	struct irq_desc *desc = container_of(kobj, struct irq_desc, kobj);
-	ssize_t ret = 0;
 
-	raw_spin_lock_irq(&desc->lock);
-	ret = sprintf(buf, "%s\n",
-		      irqd_is_level_type(&desc->irq_data) ? "level" : "edge");
-	raw_spin_unlock_irq(&desc->lock);
-
-	return ret;
+	guard(raw_spinlock_irq)(&desc->lock);
+	return sysfs_emit(buf, "%s\n", irqd_is_level_type(&desc->irq_data) ? "level" : "edge");
 
 }
 IRQ_ATTR_RO(type);
 
-static ssize_t wakeup_show(struct kobject *kobj,
-			   struct kobj_attribute *attr, char *buf)
+static ssize_t wakeup_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf)
 {
 	struct irq_desc *desc = container_of(kobj, struct irq_desc, kobj);
-	ssize_t ret = 0;
-
-	raw_spin_lock_irq(&desc->lock);
-	ret = sprintf(buf, "%s\n", str_enabled_disabled(irqd_is_wakeup_set(&desc->irq_data)));
-	raw_spin_unlock_irq(&desc->lock);
-
-	return ret;
 
+	guard(raw_spinlock_irq)(&desc->lock);
+	return sysfs_emit(buf, "%s\n", str_enabled_disabled(irqd_is_wakeup_set(&desc->irq_data)));
 }
 IRQ_ATTR_RO(wakeup);
 
-static ssize_t name_show(struct kobject *kobj,
-			 struct kobj_attribute *attr, char *buf)
+static ssize_t name_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf)
 {
 	struct irq_desc *desc = container_of(kobj, struct irq_desc, kobj);
-	ssize_t ret = 0;
 
-	raw_spin_lock_irq(&desc->lock);
+	guard(raw_spinlock_irq)(&desc->lock);
 	if (desc->name)
-		ret = scnprintf(buf, PAGE_SIZE, "%s\n", desc->name);
-	raw_spin_unlock_irq(&desc->lock);
-
-	return ret;
+		return sysfs_emit(buf, "%s\n", desc->name);
+	return 0;
 }
 IRQ_ATTR_RO(name);
 
-static ssize_t actions_show(struct kobject *kobj,
-			    struct kobj_attribute *attr, char *buf)
+static ssize_t actions_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf)
 {
 	struct irq_desc *desc = container_of(kobj, struct irq_desc, kobj);
 	struct irqaction *action;
 	ssize_t ret = 0;
 	char *p = "";
 
-	raw_spin_lock_irq(&desc->lock);
-	for_each_action_of_desc(desc, action) {
-		ret += scnprintf(buf + ret, PAGE_SIZE - ret, "%s%s",
-				 p, action->name);
-		p = ",";
+	scoped_guard(raw_spinlock_irq, &desc->lock) {
+		for_each_action_of_desc(desc, action) {
+			ret += sysfs_emit_at(buf, ret, "%s%s", p, action->name);
+			p = ",";
+		}
 	}
-	raw_spin_unlock_irq(&desc->lock);
 
 	if (ret)
-		ret += scnprintf(buf + ret, PAGE_SIZE - ret, "\n");
-
+		ret += sysfs_emit_at(buf, ret, "\n");
 	return ret;
 }
 IRQ_ATTR_RO(actions);
@@ -418,19 +388,14 @@ static int __init irq_sysfs_init(void)
 	int irq;
 
 	/* Prevent concurrent irq alloc/free */
-	irq_lock_sparse();
-
+	guard(mutex)(&sparse_irq_lock);
 	irq_kobj_base = kobject_create_and_add("irq", kernel_kobj);
-	if (!irq_kobj_base) {
-		irq_unlock_sparse();
+	if (!irq_kobj_base)
 		return -ENOMEM;
-	}
 
 	/* Add the already allocated interrupts */
 	for_each_irq_desc(irq, desc)
 		irq_sysfs_add(irq, desc);
-	irq_unlock_sparse();
-
 	return 0;
 }
 postcore_initcall(irq_sysfs_init);
@@ -573,12 +538,12 @@ err:
 	return -ENOMEM;
 }
 
-static int irq_expand_nr_irqs(unsigned int nr)
+static bool irq_expand_nr_irqs(unsigned int nr)
 {
 	if (nr > MAX_SPARSE_IRQS)
-		return -ENOMEM;
+		return false;
 	nr_irqs = nr;
-	return 0;
+	return true;
 }
 
 int __init early_irq_init(void)
@@ -656,11 +621,9 @@ EXPORT_SYMBOL(irq_to_desc);
 static void free_desc(unsigned int irq)
 {
 	struct irq_desc *desc = irq_to_desc(irq);
-	unsigned long flags;
 
-	raw_spin_lock_irqsave(&desc->lock, flags);
-	desc_set_defaults(irq, desc, irq_desc_get_node(desc), NULL, NULL);
-	raw_spin_unlock_irqrestore(&desc->lock, flags);
+	scoped_guard(raw_spinlock_irqsave, &desc->lock)
+		desc_set_defaults(irq, desc, irq_desc_get_node(desc), NULL, NULL);
 	delete_irq_desc(irq);
 }
 
@@ -679,16 +642,15 @@ static inline int alloc_descs(unsigned int start, unsigned int cnt, int node,
 	return start;
 }
 
-static int irq_expand_nr_irqs(unsigned int nr)
+static inline bool irq_expand_nr_irqs(unsigned int nr)
 {
-	return -ENOMEM;
+	return false;
 }
 
 void irq_mark_irq(unsigned int irq)
 {
-	mutex_lock(&sparse_irq_lock);
+	guard(mutex)(&sparse_irq_lock);
 	irq_insert_desc(irq, irq_desc + irq);
-	mutex_unlock(&sparse_irq_lock);
 }
 
 #ifdef CONFIG_GENERIC_IRQ_LEGACY
@@ -827,11 +789,9 @@ void irq_free_descs(unsigned int from, unsigned int cnt)
 	if (from >= nr_irqs || (from + cnt) > nr_irqs)
 		return;
 
-	mutex_lock(&sparse_irq_lock);
+	guard(mutex)(&sparse_irq_lock);
 	for (i = 0; i < cnt; i++)
 		free_desc(from + i);
-
-	mutex_unlock(&sparse_irq_lock);
 }
 EXPORT_SYMBOL_GPL(irq_free_descs);
 
@@ -848,11 +808,10 @@ EXPORT_SYMBOL_GPL(irq_free_descs);
  *
  * Returns the first irq number or error code
  */
-int __ref
-__irq_alloc_descs(int irq, unsigned int from, unsigned int cnt, int node,
-		  struct module *owner, const struct irq_affinity_desc *affinity)
+int __ref __irq_alloc_descs(int irq, unsigned int from, unsigned int cnt, int node,
+			    struct module *owner, const struct irq_affinity_desc *affinity)
 {
-	int start, ret;
+	int start;
 
 	if (!cnt)
 		return -EINVAL;
@@ -870,22 +829,17 @@ __irq_alloc_descs(int irq, unsigned int from, unsigned int cnt, int node,
 		from = arch_dynirq_lower_bound(from);
 	}
 
-	mutex_lock(&sparse_irq_lock);
+	guard(mutex)(&sparse_irq_lock);
 
 	start = irq_find_free_area(from, cnt);
-	ret = -EEXIST;
 	if (irq >=0 && start != irq)
-		goto unlock;
+		return -EEXIST;
 
 	if (start + cnt > nr_irqs) {
-		ret = irq_expand_nr_irqs(start + cnt);
-		if (ret)
-			goto unlock;
+		if (!irq_expand_nr_irqs(start + cnt))
+			return -ENOMEM;
 	}
-	ret = alloc_descs(start, cnt, node, affinity, owner);
-unlock:
-	mutex_unlock(&sparse_irq_lock);
-	return ret;
+	return alloc_descs(start, cnt, node, affinity, owner);
 }
 EXPORT_SYMBOL_GPL(__irq_alloc_descs);
 
@@ -900,27 +854,27 @@ unsigned int irq_get_next_irq(unsigned int offset)
 	return irq_find_at_or_after(offset);
 }
 
-struct irq_desc *
-__irq_get_desc_lock(unsigned int irq, unsigned long *flags, bool bus,
-		    unsigned int check)
+struct irq_desc *__irq_get_desc_lock(unsigned int irq, unsigned long *flags, bool bus,
+				     unsigned int check)
 {
-	struct irq_desc *desc = irq_to_desc(irq);
+	struct irq_desc *desc;
 
-	if (desc) {
-		if (check & _IRQ_DESC_CHECK) {
-			if ((check & _IRQ_DESC_PERCPU) &&
-			    !irq_settings_is_per_cpu_devid(desc))
-				return NULL;
-
-			if (!(check & _IRQ_DESC_PERCPU) &&
-			    irq_settings_is_per_cpu_devid(desc))
-				return NULL;
-		}
+	desc = irq_to_desc(irq);
+	if (!desc)
+		return NULL;
+
+	if (check & _IRQ_DESC_CHECK) {
+		if ((check & _IRQ_DESC_PERCPU) && !irq_settings_is_per_cpu_devid(desc))
+			return NULL;
 
-		if (bus)
-			chip_bus_lock(desc);
-		raw_spin_lock_irqsave(&desc->lock, *flags);
+		if (!(check & _IRQ_DESC_PERCPU) && irq_settings_is_per_cpu_devid(desc))
+			return NULL;
 	}
+
+	if (bus)
+		chip_bus_lock(desc);
+	raw_spin_lock_irqsave(&desc->lock, *flags);
+
 	return desc;
 }
 
diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c
index 9d5c8651492d..c8b6de09047b 100644
--- a/kernel/irq/irqdomain.c
+++ b/kernel/irq/irqdomain.c
@@ -480,33 +480,6 @@ struct irq_domain *irq_domain_create_simple(struct fwnode_handle *fwnode,
 }
 EXPORT_SYMBOL_GPL(irq_domain_create_simple);
 
-/**
- * irq_domain_add_legacy() - Allocate and register a legacy revmap irq_domain.
- * @of_node: pointer to interrupt controller's device tree node.
- * @size: total number of irqs in legacy mapping
- * @first_irq: first number of irq block assigned to the domain
- * @first_hwirq: first hwirq number to use for the translation. Should normally
- *               be '0', but a positive integer can be used if the effective
- *               hwirqs numbering does not begin at zero.
- * @ops: map/unmap domain callbacks
- * @host_data: Controller private data pointer
- *
- * Note: the map() callback will be called before this function returns
- * for all legacy interrupts except 0 (which is always the invalid irq for
- * a legacy controller).
- */
-struct irq_domain *irq_domain_add_legacy(struct device_node *of_node,
-					 unsigned int size,
-					 unsigned int first_irq,
-					 irq_hw_number_t first_hwirq,
-					 const struct irq_domain_ops *ops,
-					 void *host_data)
-{
-	return irq_domain_create_legacy(of_node_to_fwnode(of_node), size,
-					first_irq, first_hwirq, ops, host_data);
-}
-EXPORT_SYMBOL_GPL(irq_domain_add_legacy);
-
 struct irq_domain *irq_domain_create_legacy(struct fwnode_handle *fwnode,
 					 unsigned int size,
 					 unsigned int first_irq,
@@ -885,7 +858,7 @@ void of_phandle_args_to_fwspec(struct device_node *np, const u32 *args,
 {
 	int i;
 
-	fwspec->fwnode = of_node_to_fwnode(np);
+	fwspec->fwnode = of_fwnode_handle(np);
 	fwspec->param_count = count;
 
 	for (i = 0; i < count; i++)
@@ -1133,6 +1106,31 @@ int irq_domain_xlate_twocell(struct irq_domain *d, struct device_node *ctrlr,
 EXPORT_SYMBOL_GPL(irq_domain_xlate_twocell);
 
 /**
+ * irq_domain_xlate_twothreecell() - Generic xlate for direct two or three cell bindings
+ * @d:		Interrupt domain involved in the translation
+ * @ctrlr:	The device tree node for the device whose interrupt is translated
+ * @intspec:	The interrupt specifier data from the device tree
+ * @intsize:	The number of entries in @intspec
+ * @out_hwirq:	Pointer to storage for the hardware interrupt number
+ * @out_type:	Pointer to storage for the interrupt type
+ *
+ * Device Tree interrupt specifier translation function for two or three
+ * cell bindings, where the cell values map directly to the hardware
+ * interrupt number and the type specifier.
+ */
+int irq_domain_xlate_twothreecell(struct irq_domain *d, struct device_node *ctrlr,
+				  const u32 *intspec, unsigned int intsize,
+				  irq_hw_number_t *out_hwirq, unsigned int *out_type)
+{
+	struct irq_fwspec fwspec;
+
+	of_phandle_args_to_fwspec(ctrlr, intspec, intsize, &fwspec);
+
+	return irq_domain_translate_twothreecell(d, &fwspec, out_hwirq, out_type);
+}
+EXPORT_SYMBOL_GPL(irq_domain_xlate_twothreecell);
+
+/**
  * irq_domain_xlate_onetwocell() - Generic xlate for one or two cell bindings
  * @d:		Interrupt domain involved in the translation
  * @ctrlr:	The device tree node for the device whose interrupt is translated
@@ -1216,6 +1214,37 @@ int irq_domain_translate_twocell(struct irq_domain *d,
 }
 EXPORT_SYMBOL_GPL(irq_domain_translate_twocell);
 
+/**
+ * irq_domain_translate_twothreecell() - Generic translate for direct two or three cell
+ * bindings
+ * @d:		Interrupt domain involved in the translation
+ * @fwspec:	The firmware interrupt specifier to translate
+ * @out_hwirq:	Pointer to storage for the hardware interrupt number
+ * @out_type:	Pointer to storage for the interrupt type
+ *
+ * Firmware interrupt specifier translation function for two or three cell
+ * specifications, where the parameter values map directly to the hardware
+ * interrupt number and the type specifier.
+ */
+int irq_domain_translate_twothreecell(struct irq_domain *d, struct irq_fwspec *fwspec,
+				      unsigned long *out_hwirq, unsigned int *out_type)
+{
+	if (fwspec->param_count == 2) {
+		*out_hwirq = fwspec->param[0];
+		*out_type = fwspec->param[1] & IRQ_TYPE_SENSE_MASK;
+		return 0;
+	}
+
+	if (fwspec->param_count == 3) {
+		*out_hwirq = fwspec->param[1];
+		*out_type = fwspec->param[2] & IRQ_TYPE_SENSE_MASK;
+		return 0;
+	}
+
+	return -EINVAL;
+}
+EXPORT_SYMBOL_GPL(irq_domain_translate_twothreecell);
+
 int irq_domain_alloc_descs(int virq, unsigned int cnt, irq_hw_number_t hwirq,
 			   int node, const struct irq_affinity_desc *affinity)
 {
@@ -1252,47 +1281,6 @@ void irq_domain_reset_irq_data(struct irq_data *irq_data)
 EXPORT_SYMBOL_GPL(irq_domain_reset_irq_data);
 
 #ifdef	CONFIG_IRQ_DOMAIN_HIERARCHY
-/**
- * irq_domain_create_hierarchy - Add a irqdomain into the hierarchy
- * @parent:	Parent irq domain to associate with the new domain
- * @flags:	Irq domain flags associated to the domain
- * @size:	Size of the domain. See below
- * @fwnode:	Optional fwnode of the interrupt controller
- * @ops:	Pointer to the interrupt domain callbacks
- * @host_data:	Controller private data pointer
- *
- * If @size is 0 a tree domain is created, otherwise a linear domain.
- *
- * If successful the parent is associated to the new domain and the
- * domain flags are set.
- * Returns pointer to IRQ domain, or NULL on failure.
- */
-struct irq_domain *irq_domain_create_hierarchy(struct irq_domain *parent,
-					    unsigned int flags,
-					    unsigned int size,
-					    struct fwnode_handle *fwnode,
-					    const struct irq_domain_ops *ops,
-					    void *host_data)
-{
-	struct irq_domain_info info = {
-		.fwnode		= fwnode,
-		.size		= size,
-		.hwirq_max	= size,
-		.ops		= ops,
-		.host_data	= host_data,
-		.domain_flags	= flags,
-		.parent		= parent,
-	};
-	struct irq_domain *d;
-
-	if (!info.size)
-		info.hwirq_max = ~0U;
-
-	d = irq_domain_instantiate(&info);
-	return IS_ERR(d) ? NULL : d;
-}
-EXPORT_SYMBOL_GPL(irq_domain_create_hierarchy);
-
 static void irq_domain_insert_irq(int virq)
 {
 	struct irq_data *data;
@@ -2008,7 +1996,7 @@ static void irq_domain_check_hierarchy(struct irq_domain *domain)
 		domain->flags |= IRQ_DOMAIN_FLAG_HIERARCHY;
 }
 #else	/* CONFIG_IRQ_DOMAIN_HIERARCHY */
-/**
+/*
  * irq_domain_get_irq_data - Get irq_data associated with @virq and @domain
  * @domain:	domain to match
  * @virq:	IRQ number to get irq_data
@@ -2022,7 +2010,7 @@ struct irq_data *irq_domain_get_irq_data(struct irq_domain *domain,
 }
 EXPORT_SYMBOL_GPL(irq_domain_get_irq_data);
 
-/**
+/*
  * irq_domain_set_info - Set the complete data for a @virq in @domain
  * @domain:		Interrupt domain to match
  * @virq:		IRQ number
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 753eef8e041c..c94837382037 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -43,8 +43,6 @@ static void __synchronize_hardirq(struct irq_desc *desc, bool sync_chip)
 	bool inprogress;
 
 	do {
-		unsigned long flags;
-
 		/*
 		 * Wait until we're out of the critical section.  This might
 		 * give the wrong answer due to the lack of memory barriers.
@@ -53,7 +51,7 @@ static void __synchronize_hardirq(struct irq_desc *desc, bool sync_chip)
 			cpu_relax();
 
 		/* Ok, that indicated we're done: double-check carefully. */
-		raw_spin_lock_irqsave(&desc->lock, flags);
+		guard(raw_spinlock_irqsave)(&desc->lock);
 		inprogress = irqd_irq_inprogress(&desc->irq_data);
 
 		/*
@@ -69,33 +67,30 @@ static void __synchronize_hardirq(struct irq_desc *desc, bool sync_chip)
 			__irq_get_irqchip_state(irqd, IRQCHIP_STATE_ACTIVE,
 						&inprogress);
 		}
-		raw_spin_unlock_irqrestore(&desc->lock, flags);
-
 		/* Oops, that failed? */
 	} while (inprogress);
 }
 
 /**
- *	synchronize_hardirq - wait for pending hard IRQ handlers (on other CPUs)
- *	@irq: interrupt number to wait for
+ * synchronize_hardirq - wait for pending hard IRQ handlers (on other CPUs)
+ * @irq: interrupt number to wait for
  *
- *	This function waits for any pending hard IRQ handlers for this
- *	interrupt to complete before returning. If you use this
- *	function while holding a resource the IRQ handler may need you
- *	will deadlock. It does not take associated threaded handlers
- *	into account.
+ * This function waits for any pending hard IRQ handlers for this interrupt
+ * to complete before returning. If you use this function while holding a
+ * resource the IRQ handler may need you will deadlock. It does not take
+ * associated threaded handlers into account.
  *
- *	Do not use this for shutdown scenarios where you must be sure
- *	that all parts (hardirq and threaded handler) have completed.
+ * Do not use this for shutdown scenarios where you must be sure that all
+ * parts (hardirq and threaded handler) have completed.
  *
- *	Returns: false if a threaded handler is active.
+ * Returns: false if a threaded handler is active.
  *
- *	This function may be called - with care - from IRQ context.
+ * This function may be called - with care - from IRQ context.
  *
- *	It does not check whether there is an interrupt in flight at the
- *	hardware level, but not serviced yet, as this might deadlock when
- *	called with interrupts disabled and the target CPU of the interrupt
- *	is the current CPU.
+ * It does not check whether there is an interrupt in flight at the
+ * hardware level, but not serviced yet, as this might deadlock when called
+ * with interrupts disabled and the target CPU of the interrupt is the
+ * current CPU.
  */
 bool synchronize_hardirq(unsigned int irq)
 {
@@ -121,19 +116,19 @@ static void __synchronize_irq(struct irq_desc *desc)
 }
 
 /**
- *	synchronize_irq - wait for pending IRQ handlers (on other CPUs)
- *	@irq: interrupt number to wait for
+ * synchronize_irq - wait for pending IRQ handlers (on other CPUs)
+ * @irq: interrupt number to wait for
  *
- *	This function waits for any pending IRQ handlers for this interrupt
- *	to complete before returning. If you use this function while
- *	holding a resource the IRQ handler may need you will deadlock.
+ * This function waits for any pending IRQ handlers for this interrupt to
+ * complete before returning. If you use this function while holding a
+ * resource the IRQ handler may need you will deadlock.
  *
- *	Can only be called from preemptible code as it might sleep when
- *	an interrupt thread is associated to @irq.
+ * Can only be called from preemptible code as it might sleep when
+ * an interrupt thread is associated to @irq.
  *
- *	It optionally makes sure (when the irq chip supports that method)
- *	that the interrupt is not pending in any CPU and waiting for
- *	service.
+ * It optionally makes sure (when the irq chip supports that method)
+ * that the interrupt is not pending in any CPU and waiting for
+ * service.
  */
 void synchronize_irq(unsigned int irq)
 {
@@ -156,8 +151,8 @@ static bool __irq_can_set_affinity(struct irq_desc *desc)
 }
 
 /**
- *	irq_can_set_affinity - Check if the affinity of a given irq can be set
- *	@irq:		Interrupt to check
+ * irq_can_set_affinity - Check if the affinity of a given irq can be set
+ * @irq:	Interrupt to check
  *
  */
 int irq_can_set_affinity(unsigned int irq)
@@ -181,13 +176,13 @@ bool irq_can_set_affinity_usr(unsigned int irq)
 }
 
 /**
- *	irq_set_thread_affinity - Notify irq threads to adjust affinity
- *	@desc:		irq descriptor which has affinity changed
+ * irq_set_thread_affinity - Notify irq threads to adjust affinity
+ * @desc:	irq descriptor which has affinity changed
  *
- *	We just set IRQTF_AFFINITY and delegate the affinity setting
- *	to the interrupt thread itself. We can not call
- *	set_cpus_allowed_ptr() here as we hold desc->lock and this
- *	code can be called from hard interrupt context.
+ * Just set IRQTF_AFFINITY and delegate the affinity setting to the
+ * interrupt thread itself. We can not call set_cpus_allowed_ptr() here as
+ * we hold desc->lock and this code can be called from hard interrupt
+ * context.
  */
 static void irq_set_thread_affinity(struct irq_desc *desc)
 {
@@ -400,14 +395,8 @@ int irq_set_affinity_locked(struct irq_data *data, const struct cpumask *mask,
  * an interrupt which is already started or which has already been configured
  * as managed will also fail, as these mean invalid init state or double init.
  */
-int irq_update_affinity_desc(unsigned int irq,
-			     struct irq_affinity_desc *affinity)
+int irq_update_affinity_desc(unsigned int irq, struct irq_affinity_desc *affinity)
 {
-	struct irq_desc *desc;
-	unsigned long flags;
-	bool activated;
-	int ret = 0;
-
 	/*
 	 * Supporting this with the reservation scheme used by x86 needs
 	 * some more thought. Fail it for now.
@@ -415,60 +404,50 @@ int irq_update_affinity_desc(unsigned int irq,
 	if (IS_ENABLED(CONFIG_GENERIC_IRQ_RESERVATION_MODE))
 		return -EOPNOTSUPP;
 
-	desc = irq_get_desc_buslock(irq, &flags, 0);
-	if (!desc)
-		return -EINVAL;
-
-	/* Requires the interrupt to be shut down */
-	if (irqd_is_started(&desc->irq_data)) {
-		ret = -EBUSY;
-		goto out_unlock;
-	}
+	scoped_irqdesc_get_and_buslock(irq, 0) {
+		struct irq_desc *desc = scoped_irqdesc;
+		bool activated;
 
-	/* Interrupts which are already managed cannot be modified */
-	if (irqd_affinity_is_managed(&desc->irq_data)) {
-		ret = -EBUSY;
-		goto out_unlock;
-	}
-
-	/*
-	 * Deactivate the interrupt. That's required to undo
-	 * anything an earlier activation has established.
-	 */
-	activated = irqd_is_activated(&desc->irq_data);
-	if (activated)
-		irq_domain_deactivate_irq(&desc->irq_data);
+		/* Requires the interrupt to be shut down */
+		if (irqd_is_started(&desc->irq_data))
+			return -EBUSY;
 
-	if (affinity->is_managed) {
-		irqd_set(&desc->irq_data, IRQD_AFFINITY_MANAGED);
-		irqd_set(&desc->irq_data, IRQD_MANAGED_SHUTDOWN);
-	}
+		/* Interrupts which are already managed cannot be modified */
+		if (irqd_affinity_is_managed(&desc->irq_data))
+			return -EBUSY;
+		/*
+		 * Deactivate the interrupt. That's required to undo
+		 * anything an earlier activation has established.
+		 */
+		activated = irqd_is_activated(&desc->irq_data);
+		if (activated)
+			irq_domain_deactivate_irq(&desc->irq_data);
 
-	cpumask_copy(desc->irq_common_data.affinity, &affinity->mask);
+		if (affinity->is_managed) {
+			irqd_set(&desc->irq_data, IRQD_AFFINITY_MANAGED);
+			irqd_set(&desc->irq_data, IRQD_MANAGED_SHUTDOWN);
+		}
 
-	/* Restore the activation state */
-	if (activated)
-		irq_domain_activate_irq(&desc->irq_data, false);
+		cpumask_copy(desc->irq_common_data.affinity, &affinity->mask);
 
-out_unlock:
-	irq_put_desc_busunlock(desc, flags);
-	return ret;
+		/* Restore the activation state */
+		if (activated)
+			irq_domain_activate_irq(&desc->irq_data, false);
+		return 0;
+	}
+	return -EINVAL;
 }
 
 static int __irq_set_affinity(unsigned int irq, const struct cpumask *mask,
 			      bool force)
 {
 	struct irq_desc *desc = irq_to_desc(irq);
-	unsigned long flags;
-	int ret;
 
 	if (!desc)
 		return -EINVAL;
 
-	raw_spin_lock_irqsave(&desc->lock, flags);
-	ret = irq_set_affinity_locked(irq_desc_get_irq_data(desc), mask, force);
-	raw_spin_unlock_irqrestore(&desc->lock, flags);
-	return ret;
+	guard(raw_spinlock_irqsave)(&desc->lock);
+	return irq_set_affinity_locked(irq_desc_get_irq_data(desc), mask, force);
 }
 
 /**
@@ -501,39 +480,36 @@ int irq_force_affinity(unsigned int irq, const struct cpumask *cpumask)
 }
 EXPORT_SYMBOL_GPL(irq_force_affinity);
 
-int __irq_apply_affinity_hint(unsigned int irq, const struct cpumask *m,
-			      bool setaffinity)
+int __irq_apply_affinity_hint(unsigned int irq, const struct cpumask *m, bool setaffinity)
 {
-	unsigned long flags;
-	struct irq_desc *desc = irq_get_desc_lock(irq, &flags, IRQ_GET_DESC_CHECK_GLOBAL);
+	int ret = -EINVAL;
 
-	if (!desc)
-		return -EINVAL;
-	desc->affinity_hint = m;
-	irq_put_desc_unlock(desc, flags);
-	if (m && setaffinity)
+	scoped_irqdesc_get_and_lock(irq, IRQ_GET_DESC_CHECK_GLOBAL) {
+		scoped_irqdesc->affinity_hint = m;
+		ret = 0;
+	}
+
+	if (!ret && m && setaffinity)
 		__irq_set_affinity(irq, m, false);
-	return 0;
+	return ret;
 }
 EXPORT_SYMBOL_GPL(__irq_apply_affinity_hint);
 
 static void irq_affinity_notify(struct work_struct *work)
 {
-	struct irq_affinity_notify *notify =
-		container_of(work, struct irq_affinity_notify, work);
+	struct irq_affinity_notify *notify = container_of(work, struct irq_affinity_notify, work);
 	struct irq_desc *desc = irq_to_desc(notify->irq);
 	cpumask_var_t cpumask;
-	unsigned long flags;
 
 	if (!desc || !alloc_cpumask_var(&cpumask, GFP_KERNEL))
 		goto out;
 
-	raw_spin_lock_irqsave(&desc->lock, flags);
-	if (irq_move_pending(&desc->irq_data))
-		irq_get_pending(cpumask, desc);
-	else
-		cpumask_copy(cpumask, desc->irq_common_data.affinity);
-	raw_spin_unlock_irqrestore(&desc->lock, flags);
+	scoped_guard(raw_spinlock_irqsave, &desc->lock) {
+		if (irq_move_pending(&desc->irq_data))
+			irq_get_pending(cpumask, desc);
+		else
+			cpumask_copy(cpumask, desc->irq_common_data.affinity);
+	}
 
 	notify->notify(notify, cpumask);
 
@@ -543,22 +519,20 @@ out:
 }
 
 /**
- *	irq_set_affinity_notifier - control notification of IRQ affinity changes
- *	@irq:		Interrupt for which to enable/disable notification
- *	@notify:	Context for notification, or %NULL to disable
- *			notification.  Function pointers must be initialised;
- *			the other fields will be initialised by this function.
- *
- *	Must be called in process context.  Notification may only be enabled
- *	after the IRQ is allocated and must be disabled before the IRQ is
- *	freed using free_irq().
+ * irq_set_affinity_notifier - control notification of IRQ affinity changes
+ * @irq:	Interrupt for which to enable/disable notification
+ * @notify:	Context for notification, or %NULL to disable
+ *		notification.  Function pointers must be initialised;
+ *		the other fields will be initialised by this function.
+ *
+ * Must be called in process context.  Notification may only be enabled
+ * after the IRQ is allocated and must be disabled before the IRQ is freed
+ * using free_irq().
  */
-int
-irq_set_affinity_notifier(unsigned int irq, struct irq_affinity_notify *notify)
+int irq_set_affinity_notifier(unsigned int irq, struct irq_affinity_notify *notify)
 {
 	struct irq_desc *desc = irq_to_desc(irq);
 	struct irq_affinity_notify *old_notify;
-	unsigned long flags;
 
 	/* The release function is promised process context */
 	might_sleep();
@@ -573,10 +547,10 @@ irq_set_affinity_notifier(unsigned int irq, struct irq_affinity_notify *notify)
 		INIT_WORK(&notify->work, irq_affinity_notify);
 	}
 
-	raw_spin_lock_irqsave(&desc->lock, flags);
-	old_notify = desc->affinity_notify;
-	desc->affinity_notify = notify;
-	raw_spin_unlock_irqrestore(&desc->lock, flags);
+	scoped_guard(raw_spinlock_irqsave, &desc->lock) {
+		old_notify = desc->affinity_notify;
+		desc->affinity_notify = notify;
+	}
 
 	if (old_notify) {
 		if (cancel_work_sync(&old_notify->work)) {
@@ -597,7 +571,8 @@ EXPORT_SYMBOL_GPL(irq_set_affinity_notifier);
 int irq_setup_affinity(struct irq_desc *desc)
 {
 	struct cpumask *set = irq_default_affinity;
-	int ret, node = irq_desc_get_node(desc);
+	int node = irq_desc_get_node(desc);
+
 	static DEFINE_RAW_SPINLOCK(mask_lock);
 	static struct cpumask mask;
 
@@ -605,7 +580,7 @@ int irq_setup_affinity(struct irq_desc *desc)
 	if (!__irq_can_set_affinity(desc))
 		return 0;
 
-	raw_spin_lock(&mask_lock);
+	guard(raw_spinlock)(&mask_lock);
 	/*
 	 * Preserve the managed affinity setting and a userspace affinity
 	 * setup, but make sure that one of the targets is online.
@@ -630,9 +605,7 @@ int irq_setup_affinity(struct irq_desc *desc)
 		if (cpumask_intersects(&mask, nodemask))
 			cpumask_and(&mask, &mask, nodemask);
 	}
-	ret = irq_do_set_affinity(&desc->irq_data, &mask, false);
-	raw_spin_unlock(&mask_lock);
-	return ret;
+	return irq_do_set_affinity(&desc->irq_data, &mask, false);
 }
 #else
 /* Wrapper for ALPHA specific affinity selector magic */
@@ -645,44 +618,36 @@ int irq_setup_affinity(struct irq_desc *desc)
 
 
 /**
- *	irq_set_vcpu_affinity - Set vcpu affinity for the interrupt
- *	@irq: interrupt number to set affinity
- *	@vcpu_info: vCPU specific data or pointer to a percpu array of vCPU
- *	            specific data for percpu_devid interrupts
- *
- *	This function uses the vCPU specific data to set the vCPU
- *	affinity for an irq. The vCPU specific data is passed from
- *	outside, such as KVM. One example code path is as below:
- *	KVM -> IOMMU -> irq_set_vcpu_affinity().
+ * irq_set_vcpu_affinity - Set vcpu affinity for the interrupt
+ * @irq:	interrupt number to set affinity
+ * @vcpu_info:	vCPU specific data or pointer to a percpu array of vCPU
+ *		specific data for percpu_devid interrupts
+ *
+ * This function uses the vCPU specific data to set the vCPU affinity for
+ * an irq. The vCPU specific data is passed from outside, such as KVM. One
+ * example code path is as below: KVM -> IOMMU -> irq_set_vcpu_affinity().
  */
 int irq_set_vcpu_affinity(unsigned int irq, void *vcpu_info)
 {
-	unsigned long flags;
-	struct irq_desc *desc = irq_get_desc_lock(irq, &flags, 0);
-	struct irq_data *data;
-	struct irq_chip *chip;
-	int ret = -ENOSYS;
+	scoped_irqdesc_get_and_lock(irq, 0) {
+		struct irq_desc *desc = scoped_irqdesc;
+		struct irq_data *data;
+		struct irq_chip *chip;
 
-	if (!desc)
-		return -EINVAL;
-
-	data = irq_desc_get_irq_data(desc);
-	do {
-		chip = irq_data_get_irq_chip(data);
-		if (chip && chip->irq_set_vcpu_affinity)
-			break;
-#ifdef CONFIG_IRQ_DOMAIN_HIERARCHY
-		data = data->parent_data;
-#else
-		data = NULL;
-#endif
-	} while (data);
+		data = irq_desc_get_irq_data(desc);
+		do {
+			chip = irq_data_get_irq_chip(data);
+			if (chip && chip->irq_set_vcpu_affinity)
+				break;
 
-	if (data)
-		ret = chip->irq_set_vcpu_affinity(data, vcpu_info);
-	irq_put_desc_unlock(desc, flags);
+			data = irqd_get_parent_data(data);
+		} while (data);
 
-	return ret;
+		if (!data)
+			return -ENOSYS;
+		return chip->irq_set_vcpu_affinity(data, vcpu_info);
+	}
+	return -EINVAL;
 }
 EXPORT_SYMBOL_GPL(irq_set_vcpu_affinity);
 
@@ -694,26 +659,23 @@ void __disable_irq(struct irq_desc *desc)
 
 static int __disable_irq_nosync(unsigned int irq)
 {
-	unsigned long flags;
-	struct irq_desc *desc = irq_get_desc_buslock(irq, &flags, IRQ_GET_DESC_CHECK_GLOBAL);
-
-	if (!desc)
-		return -EINVAL;
-	__disable_irq(desc);
-	irq_put_desc_busunlock(desc, flags);
-	return 0;
+	scoped_irqdesc_get_and_lock(irq, IRQ_GET_DESC_CHECK_GLOBAL) {
+		__disable_irq(scoped_irqdesc);
+		return 0;
+	}
+	return -EINVAL;
 }
 
 /**
- *	disable_irq_nosync - disable an irq without waiting
- *	@irq: Interrupt to disable
+ * disable_irq_nosync - disable an irq without waiting
+ * @irq: Interrupt to disable
  *
- *	Disable the selected interrupt line.  Disables and Enables are
- *	nested.
- *	Unlike disable_irq(), this function does not ensure existing
- *	instances of the IRQ handler have completed before returning.
+ * Disable the selected interrupt line.  Disables and Enables are
+ * nested.
+ * Unlike disable_irq(), this function does not ensure existing
+ * instances of the IRQ handler have completed before returning.
  *
- *	This function may be called from IRQ context.
+ * This function may be called from IRQ context.
  */
 void disable_irq_nosync(unsigned int irq)
 {
@@ -722,17 +684,17 @@ void disable_irq_nosync(unsigned int irq)
 EXPORT_SYMBOL(disable_irq_nosync);
 
 /**
- *	disable_irq - disable an irq and wait for completion
- *	@irq: Interrupt to disable
+ * disable_irq - disable an irq and wait for completion
+ * @irq: Interrupt to disable
+ *
+ * Disable the selected interrupt line.  Enables and Disables are nested.
  *
- *	Disable the selected interrupt line.  Enables and Disables are
- *	nested.
- *	This function waits for any pending IRQ handlers for this interrupt
- *	to complete before returning. If you use this function while
- *	holding a resource the IRQ handler may need you will deadlock.
+ * This function waits for any pending IRQ handlers for this interrupt to
+ * complete before returning. If you use this function while holding a
+ * resource the IRQ handler may need you will deadlock.
  *
- *	Can only be called from preemptible code as it might sleep when
- *	an interrupt thread is associated to @irq.
+ * Can only be called from preemptible code as it might sleep when an
+ * interrupt thread is associated to @irq.
  *
  */
 void disable_irq(unsigned int irq)
@@ -744,40 +706,39 @@ void disable_irq(unsigned int irq)
 EXPORT_SYMBOL(disable_irq);
 
 /**
- *	disable_hardirq - disables an irq and waits for hardirq completion
- *	@irq: Interrupt to disable
+ * disable_hardirq - disables an irq and waits for hardirq completion
+ * @irq: Interrupt to disable
  *
- *	Disable the selected interrupt line.  Enables and Disables are
- *	nested.
- *	This function waits for any pending hard IRQ handlers for this
- *	interrupt to complete before returning. If you use this function while
- *	holding a resource the hard IRQ handler may need you will deadlock.
+ * Disable the selected interrupt line.  Enables and Disables are nested.
  *
- *	When used to optimistically disable an interrupt from atomic context
- *	the return value must be checked.
+ * This function waits for any pending hard IRQ handlers for this interrupt
+ * to complete before returning. If you use this function while holding a
+ * resource the hard IRQ handler may need you will deadlock.
  *
- *	Returns: false if a threaded handler is active.
+ * When used to optimistically disable an interrupt from atomic context the
+ * return value must be checked.
  *
- *	This function may be called - with care - from IRQ context.
+ * Returns: false if a threaded handler is active.
+ *
+ * This function may be called - with care - from IRQ context.
  */
 bool disable_hardirq(unsigned int irq)
 {
 	if (!__disable_irq_nosync(irq))
 		return synchronize_hardirq(irq);
-
 	return false;
 }
 EXPORT_SYMBOL_GPL(disable_hardirq);
 
 /**
- *	disable_nmi_nosync - disable an nmi without waiting
- *	@irq: Interrupt to disable
- *
- *	Disable the selected interrupt line. Disables and enables are
- *	nested.
- *	The interrupt to disable must have been requested through request_nmi.
- *	Unlike disable_nmi(), this function does not ensure existing
- *	instances of the IRQ handler have completed before returning.
+ * disable_nmi_nosync - disable an nmi without waiting
+ * @irq: Interrupt to disable
+ *
+ * Disable the selected interrupt line. Disables and enables are nested.
+ *
+ * The interrupt to disable must have been requested through request_nmi.
+ * Unlike disable_nmi(), this function does not ensure existing
+ * instances of the IRQ handler have completed before returning.
  */
 void disable_nmi_nosync(unsigned int irq)
 {
@@ -817,41 +778,34 @@ void __enable_irq(struct irq_desc *desc)
 }
 
 /**
- *	enable_irq - enable handling of an irq
- *	@irq: Interrupt to enable
+ * enable_irq - enable handling of an irq
+ * @irq: Interrupt to enable
  *
- *	Undoes the effect of one call to disable_irq().  If this
- *	matches the last disable, processing of interrupts on this
- *	IRQ line is re-enabled.
+ * Undoes the effect of one call to disable_irq().  If this matches the
+ * last disable, processing of interrupts on this IRQ line is re-enabled.
  *
- *	This function may be called from IRQ context only when
- *	desc->irq_data.chip->bus_lock and desc->chip->bus_sync_unlock are NULL !
+ * This function may be called from IRQ context only when
+ * desc->irq_data.chip->bus_lock and desc->chip->bus_sync_unlock are NULL !
  */
 void enable_irq(unsigned int irq)
 {
-	unsigned long flags;
-	struct irq_desc *desc = irq_get_desc_buslock(irq, &flags, IRQ_GET_DESC_CHECK_GLOBAL);
+	scoped_irqdesc_get_and_lock(irq, IRQ_GET_DESC_CHECK_GLOBAL) {
+		struct irq_desc *desc = scoped_irqdesc;
 
-	if (!desc)
-		return;
-	if (WARN(!desc->irq_data.chip,
-		 KERN_ERR "enable_irq before setup/request_irq: irq %u\n", irq))
-		goto out;
-
-	__enable_irq(desc);
-out:
-	irq_put_desc_busunlock(desc, flags);
+		if (WARN(!desc->irq_data.chip, "enable_irq before setup/request_irq: irq %u\n", irq))
+			return;
+		__enable_irq(desc);
+	}
 }
 EXPORT_SYMBOL(enable_irq);
 
 /**
- *	enable_nmi - enable handling of an nmi
- *	@irq: Interrupt to enable
+ * enable_nmi - enable handling of an nmi
+ * @irq: Interrupt to enable
  *
- *	The interrupt to enable must have been requested through request_nmi.
- *	Undoes the effect of one call to disable_nmi(). If this
- *	matches the last disable, processing of interrupts on this
- *	IRQ line is re-enabled.
+ * The interrupt to enable must have been requested through request_nmi.
+ * Undoes the effect of one call to disable_nmi(). If this matches the last
+ * disable, processing of interrupts on this IRQ line is re-enabled.
  */
 void enable_nmi(unsigned int irq)
 {
@@ -873,65 +827,59 @@ static int set_irq_wake_real(unsigned int irq, unsigned int on)
 }
 
 /**
- *	irq_set_irq_wake - control irq power management wakeup
- *	@irq:	interrupt to control
- *	@on:	enable/disable power management wakeup
- *
- *	Enable/disable power management wakeup mode, which is
- *	disabled by default.  Enables and disables must match,
- *	just as they match for non-wakeup mode support.
- *
- *	Wakeup mode lets this IRQ wake the system from sleep
- *	states like "suspend to RAM".
- *
- *	Note: irq enable/disable state is completely orthogonal
- *	to the enable/disable state of irq wake. An irq can be
- *	disabled with disable_irq() and still wake the system as
- *	long as the irq has wake enabled. If this does not hold,
- *	then the underlying irq chip and the related driver need
- *	to be investigated.
+ * irq_set_irq_wake - control irq power management wakeup
+ * @irq:	interrupt to control
+ * @on:	enable/disable power management wakeup
+ *
+ * Enable/disable power management wakeup mode, which is disabled by
+ * default.  Enables and disables must match, just as they match for
+ * non-wakeup mode support.
+ *
+ * Wakeup mode lets this IRQ wake the system from sleep states like
+ * "suspend to RAM".
+ *
+ * Note: irq enable/disable state is completely orthogonal to the
+ * enable/disable state of irq wake. An irq can be disabled with
+ * disable_irq() and still wake the system as long as the irq has wake
+ * enabled. If this does not hold, then the underlying irq chip and the
+ * related driver need to be investigated.
  */
 int irq_set_irq_wake(unsigned int irq, unsigned int on)
 {
-	unsigned long flags;
-	struct irq_desc *desc = irq_get_desc_buslock(irq, &flags, IRQ_GET_DESC_CHECK_GLOBAL);
-	int ret = 0;
+	scoped_irqdesc_get_and_buslock(irq, IRQ_GET_DESC_CHECK_GLOBAL) {
+		struct irq_desc *desc = scoped_irqdesc;
+		int ret = 0;
 
-	if (!desc)
-		return -EINVAL;
-
-	/* Don't use NMIs as wake up interrupts please */
-	if (irq_is_nmi(desc)) {
-		ret = -EINVAL;
-		goto out_unlock;
-	}
+		/* Don't use NMIs as wake up interrupts please */
+		if (irq_is_nmi(desc))
+			return -EINVAL;
 
-	/* wakeup-capable irqs can be shared between drivers that
-	 * don't need to have the same sleep mode behaviors.
-	 */
-	if (on) {
-		if (desc->wake_depth++ == 0) {
-			ret = set_irq_wake_real(irq, on);
-			if (ret)
-				desc->wake_depth = 0;
-			else
-				irqd_set(&desc->irq_data, IRQD_WAKEUP_STATE);
-		}
-	} else {
-		if (desc->wake_depth == 0) {
-			WARN(1, "Unbalanced IRQ %d wake disable\n", irq);
-		} else if (--desc->wake_depth == 0) {
-			ret = set_irq_wake_real(irq, on);
-			if (ret)
-				desc->wake_depth = 1;
-			else
-				irqd_clear(&desc->irq_data, IRQD_WAKEUP_STATE);
+		/*
+		 * wakeup-capable irqs can be shared between drivers that
+		 * don't need to have the same sleep mode behaviors.
+		 */
+		if (on) {
+			if (desc->wake_depth++ == 0) {
+				ret = set_irq_wake_real(irq, on);
+				if (ret)
+					desc->wake_depth = 0;
+				else
+					irqd_set(&desc->irq_data, IRQD_WAKEUP_STATE);
+			}
+		} else {
+			if (desc->wake_depth == 0) {
+				WARN(1, "Unbalanced IRQ %d wake disable\n", irq);
+			} else if (--desc->wake_depth == 0) {
+				ret = set_irq_wake_real(irq, on);
+				if (ret)
+					desc->wake_depth = 1;
+				else
+					irqd_clear(&desc->irq_data, IRQD_WAKEUP_STATE);
+			}
 		}
+		return ret;
 	}
-
-out_unlock:
-	irq_put_desc_busunlock(desc, flags);
-	return ret;
+	return -EINVAL;
 }
 EXPORT_SYMBOL(irq_set_irq_wake);
 
@@ -940,22 +888,17 @@ EXPORT_SYMBOL(irq_set_irq_wake);
  * particular irq has been exclusively allocated or is available
  * for driver use.
  */
-int can_request_irq(unsigned int irq, unsigned long irqflags)
+bool can_request_irq(unsigned int irq, unsigned long irqflags)
 {
-	unsigned long flags;
-	struct irq_desc *desc = irq_get_desc_lock(irq, &flags, 0);
-	int canrequest = 0;
+	scoped_irqdesc_get_and_lock(irq, IRQ_GET_DESC_CHECK_GLOBAL) {
+		struct irq_desc *desc = scoped_irqdesc;
 
-	if (!desc)
-		return 0;
-
-	if (irq_settings_can_request(desc)) {
-		if (!desc->action ||
-		    irqflags & desc->action->flags & IRQF_SHARED)
-			canrequest = 1;
+		if (irq_settings_can_request(desc)) {
+			if (!desc->action || irqflags & desc->action->flags & IRQF_SHARED)
+				return true;
+		}
 	}
-	irq_put_desc_unlock(desc, flags);
-	return canrequest;
+	return false;
 }
 
 int __irq_set_trigger(struct irq_desc *desc, unsigned long flags)
@@ -1016,16 +959,11 @@ int __irq_set_trigger(struct irq_desc *desc, unsigned long flags)
 #ifdef CONFIG_HARDIRQS_SW_RESEND
 int irq_set_parent(int irq, int parent_irq)
 {
-	unsigned long flags;
-	struct irq_desc *desc = irq_get_desc_lock(irq, &flags, 0);
-
-	if (!desc)
-		return -EINVAL;
-
-	desc->parent_irq = parent_irq;
-
-	irq_put_desc_unlock(desc, flags);
-	return 0;
+	scoped_irqdesc_get_and_lock(irq, 0) {
+		scoped_irqdesc->parent_irq = parent_irq;
+		return 0;
+	}
+	return -EINVAL;
 }
 EXPORT_SYMBOL_GPL(irq_set_parent);
 #endif
@@ -1079,19 +1017,19 @@ static void irq_thread_check_affinity(struct irq_desc *desc, struct irqaction *a
 		return;
 	}
 
-	raw_spin_lock_irq(&desc->lock);
-	/*
-	 * This code is triggered unconditionally. Check the affinity
-	 * mask pointer. For CPU_MASK_OFFSTACK=n this is optimized out.
-	 */
-	if (cpumask_available(desc->irq_common_data.affinity)) {
-		const struct cpumask *m;
+	scoped_guard(raw_spinlock_irq, &desc->lock) {
+		/*
+		 * This code is triggered unconditionally. Check the affinity
+		 * mask pointer. For CPU_MASK_OFFSTACK=n this is optimized out.
+		 */
+		if (cpumask_available(desc->irq_common_data.affinity)) {
+			const struct cpumask *m;
 
-		m = irq_data_get_effective_affinity_mask(&desc->irq_data);
-		cpumask_copy(mask, m);
-		valid = true;
+			m = irq_data_get_effective_affinity_mask(&desc->irq_data);
+			cpumask_copy(mask, m);
+			valid = true;
+		}
 	}
-	raw_spin_unlock_irq(&desc->lock);
 
 	if (valid)
 		set_cpus_allowed_ptr(current, mask);
@@ -1259,9 +1197,8 @@ static void irq_wake_secondary(struct irq_desc *desc, struct irqaction *action)
 	if (WARN_ON_ONCE(!secondary))
 		return;
 
-	raw_spin_lock_irq(&desc->lock);
+	guard(raw_spinlock_irq)(&desc->lock);
 	__irq_wake_thread(desc, secondary);
-	raw_spin_unlock_irq(&desc->lock);
 }
 
 /*
@@ -1334,21 +1271,19 @@ static int irq_thread(void *data)
 }
 
 /**
- *	irq_wake_thread - wake the irq thread for the action identified by dev_id
- *	@irq:		Interrupt line
- *	@dev_id:	Device identity for which the thread should be woken
- *
+ * irq_wake_thread - wake the irq thread for the action identified by dev_id
+ * @irq:	Interrupt line
+ * @dev_id:	Device identity for which the thread should be woken
  */
 void irq_wake_thread(unsigned int irq, void *dev_id)
 {
 	struct irq_desc *desc = irq_to_desc(irq);
 	struct irqaction *action;
-	unsigned long flags;
 
 	if (!desc || WARN_ON(irq_settings_is_per_cpu_devid(desc)))
 		return;
 
-	raw_spin_lock_irqsave(&desc->lock, flags);
+	guard(raw_spinlock_irqsave)(&desc->lock);
 	for_each_action_of_desc(desc, action) {
 		if (action->dev_id == dev_id) {
 			if (action->thread)
@@ -1356,7 +1291,6 @@ void irq_wake_thread(unsigned int irq, void *dev_id)
 			break;
 		}
 	}
-	raw_spin_unlock_irqrestore(&desc->lock, flags);
 }
 EXPORT_SYMBOL_GPL(irq_wake_thread);
 
@@ -1987,9 +1921,8 @@ static struct irqaction *__free_irq(struct irq_desc *desc, void *dev_id)
 		 * There is no interrupt on the fly anymore. Deactivate it
 		 * completely.
 		 */
-		raw_spin_lock_irqsave(&desc->lock, flags);
-		irq_domain_deactivate_irq(&desc->irq_data);
-		raw_spin_unlock_irqrestore(&desc->lock, flags);
+		scoped_guard(raw_spinlock_irqsave, &desc->lock)
+			irq_domain_deactivate_irq(&desc->irq_data);
 
 		irq_release_resources(desc);
 		chip_bus_sync_unlock(desc);
@@ -2005,20 +1938,19 @@ static struct irqaction *__free_irq(struct irq_desc *desc, void *dev_id)
 }
 
 /**
- *	free_irq - free an interrupt allocated with request_irq
- *	@irq: Interrupt line to free
- *	@dev_id: Device identity to free
+ * free_irq - free an interrupt allocated with request_irq
+ * @irq:	Interrupt line to free
+ * @dev_id:	Device identity to free
  *
- *	Remove an interrupt handler. The handler is removed and if the
- *	interrupt line is no longer in use by any driver it is disabled.
- *	On a shared IRQ the caller must ensure the interrupt is disabled
- *	on the card it drives before calling this function. The function
- *	does not return until any executing interrupts for this IRQ
- *	have completed.
+ * Remove an interrupt handler. The handler is removed and if the interrupt
+ * line is no longer in use by any driver it is disabled.  On a shared IRQ
+ * the caller must ensure the interrupt is disabled on the card it drives
+ * before calling this function. The function does not return until any
+ * executing interrupts for this IRQ have completed.
  *
- *	This function must not be called from interrupt context.
+ * This function must not be called from interrupt context.
  *
- *	Returns the devname argument passed to request_irq.
+ * Returns the devname argument passed to request_irq.
  */
 const void *free_irq(unsigned int irq, void *dev_id)
 {
@@ -2075,8 +2007,6 @@ static const void *__cleanup_nmi(unsigned int irq, struct irq_desc *desc)
 const void *free_nmi(unsigned int irq, void *dev_id)
 {
 	struct irq_desc *desc = irq_to_desc(irq);
-	unsigned long flags;
-	const void *devname;
 
 	if (!desc || WARN_ON(!irq_is_nmi(desc)))
 		return NULL;
@@ -2088,53 +2018,46 @@ const void *free_nmi(unsigned int irq, void *dev_id)
 	if (WARN_ON(desc->depth == 0))
 		disable_nmi_nosync(irq);
 
-	raw_spin_lock_irqsave(&desc->lock, flags);
-
+	guard(raw_spinlock_irqsave)(&desc->lock);
 	irq_nmi_teardown(desc);
-	devname = __cleanup_nmi(irq, desc);
-
-	raw_spin_unlock_irqrestore(&desc->lock, flags);
-
-	return devname;
+	return __cleanup_nmi(irq, desc);
 }
 
 /**
- *	request_threaded_irq - allocate an interrupt line
- *	@irq: Interrupt line to allocate
- *	@handler: Function to be called when the IRQ occurs.
- *		  Primary handler for threaded interrupts.
- *		  If handler is NULL and thread_fn != NULL
- *		  the default primary handler is installed.
- *	@thread_fn: Function called from the irq handler thread
- *		    If NULL, no irq thread is created
- *	@irqflags: Interrupt type flags
- *	@devname: An ascii name for the claiming device
- *	@dev_id: A cookie passed back to the handler function
- *
- *	This call allocates interrupt resources and enables the
- *	interrupt line and IRQ handling. From the point this
- *	call is made your handler function may be invoked. Since
- *	your handler function must clear any interrupt the board
- *	raises, you must take care both to initialise your hardware
- *	and to set up the interrupt handler in the right order.
- *
- *	If you want to set up a threaded irq handler for your device
- *	then you need to supply @handler and @thread_fn. @handler is
- *	still called in hard interrupt context and has to check
- *	whether the interrupt originates from the device. If yes it
- *	needs to disable the interrupt on the device and return
- *	IRQ_WAKE_THREAD which will wake up the handler thread and run
- *	@thread_fn. This split handler design is necessary to support
- *	shared interrupts.
- *
- *	Dev_id must be globally unique. Normally the address of the
- *	device data structure is used as the cookie. Since the handler
- *	receives this value it makes sense to use it.
- *
- *	If your interrupt is shared you must pass a non NULL dev_id
- *	as this is required when freeing the interrupt.
- *
- *	Flags:
+ * request_threaded_irq - allocate an interrupt line
+ * @irq:	Interrupt line to allocate
+ * @handler:	Function to be called when the IRQ occurs.
+ *		Primary handler for threaded interrupts.
+ *		If handler is NULL and thread_fn != NULL
+ *		the default primary handler is installed.
+ * @thread_fn:	Function called from the irq handler thread
+ *		If NULL, no irq thread is created
+ * @irqflags:	Interrupt type flags
+ * @devname:	An ascii name for the claiming device
+ * @dev_id:	A cookie passed back to the handler function
+ *
+ * This call allocates interrupt resources and enables the interrupt line
+ * and IRQ handling. From the point this call is made your handler function
+ * may be invoked. Since your handler function must clear any interrupt the
+ * board raises, you must take care both to initialise your hardware and to
+ * set up the interrupt handler in the right order.
+ *
+ * If you want to set up a threaded irq handler for your device then you
+ * need to supply @handler and @thread_fn. @handler is still called in hard
+ * interrupt context and has to check whether the interrupt originates from
+ * the device. If yes it needs to disable the interrupt on the device and
+ * return IRQ_WAKE_THREAD which will wake up the handler thread and run
+ * @thread_fn. This split handler design is necessary to support shared
+ * interrupts.
+ *
+ * @dev_id must be globally unique. Normally the address of the device data
+ * structure is used as the cookie. Since the handler receives this value
+ * it makes sense to use it.
+ *
+ * If your interrupt is shared you must pass a non NULL dev_id as this is
+ * required when freeing the interrupt.
+ *
+ * Flags:
  *
  *	IRQF_SHARED		Interrupt is shared
  *	IRQF_TRIGGER_*		Specify active edge(s) or level
@@ -2232,21 +2155,20 @@ int request_threaded_irq(unsigned int irq, irq_handler_t handler,
 EXPORT_SYMBOL(request_threaded_irq);
 
 /**
- *	request_any_context_irq - allocate an interrupt line
- *	@irq: Interrupt line to allocate
- *	@handler: Function to be called when the IRQ occurs.
- *		  Threaded handler for threaded interrupts.
- *	@flags: Interrupt type flags
- *	@name: An ascii name for the claiming device
- *	@dev_id: A cookie passed back to the handler function
- *
- *	This call allocates interrupt resources and enables the
- *	interrupt line and IRQ handling. It selects either a
- *	hardirq or threaded handling method depending on the
- *	context.
- *
- *	On failure, it returns a negative value. On success,
- *	it returns either IRQC_IS_HARDIRQ or IRQC_IS_NESTED.
+ * request_any_context_irq - allocate an interrupt line
+ * @irq:	Interrupt line to allocate
+ * @handler:	Function to be called when the IRQ occurs.
+ *		Threaded handler for threaded interrupts.
+ * @flags:	Interrupt type flags
+ * @name:	An ascii name for the claiming device
+ * @dev_id:	A cookie passed back to the handler function
+ *
+ * This call allocates interrupt resources and enables the interrupt line
+ * and IRQ handling. It selects either a hardirq or threaded handling
+ * method depending on the context.
+ *
+ * Returns: On failure, it returns a negative value. On success, it returns either
+ * IRQC_IS_HARDIRQ or IRQC_IS_NESTED.
  */
 int request_any_context_irq(unsigned int irq, irq_handler_t handler,
 			    unsigned long flags, const char *name, void *dev_id)
@@ -2273,37 +2195,35 @@ int request_any_context_irq(unsigned int irq, irq_handler_t handler,
 EXPORT_SYMBOL_GPL(request_any_context_irq);
 
 /**
- *	request_nmi - allocate an interrupt line for NMI delivery
- *	@irq: Interrupt line to allocate
- *	@handler: Function to be called when the IRQ occurs.
- *		  Threaded handler for threaded interrupts.
- *	@irqflags: Interrupt type flags
- *	@name: An ascii name for the claiming device
- *	@dev_id: A cookie passed back to the handler function
- *
- *	This call allocates interrupt resources and enables the
- *	interrupt line and IRQ handling. It sets up the IRQ line
- *	to be handled as an NMI.
- *
- *	An interrupt line delivering NMIs cannot be shared and IRQ handling
- *	cannot be threaded.
- *
- *	Interrupt lines requested for NMI delivering must produce per cpu
- *	interrupts and have auto enabling setting disabled.
- *
- *	Dev_id must be globally unique. Normally the address of the
- *	device data structure is used as the cookie. Since the handler
- *	receives this value it makes sense to use it.
- *
- *	If the interrupt line cannot be used to deliver NMIs, function
- *	will fail and return a negative value.
+ * request_nmi - allocate an interrupt line for NMI delivery
+ * @irq:	Interrupt line to allocate
+ * @handler:	Function to be called when the IRQ occurs.
+ *		Threaded handler for threaded interrupts.
+ * @irqflags:	Interrupt type flags
+ * @name:	An ascii name for the claiming device
+ * @dev_id:	A cookie passed back to the handler function
+ *
+ * This call allocates interrupt resources and enables the interrupt line
+ * and IRQ handling. It sets up the IRQ line to be handled as an NMI.
+ *
+ * An interrupt line delivering NMIs cannot be shared and IRQ handling
+ * cannot be threaded.
+ *
+ * Interrupt lines requested for NMI delivering must produce per cpu
+ * interrupts and have auto enabling setting disabled.
+ *
+ * @dev_id must be globally unique. Normally the address of the device data
+ * structure is used as the cookie. Since the handler receives this value
+ * it makes sense to use it.
+ *
+ * If the interrupt line cannot be used to deliver NMIs, function will fail
+ * and return a negative value.
  */
 int request_nmi(unsigned int irq, irq_handler_t handler,
 		unsigned long irqflags, const char *name, void *dev_id)
 {
 	struct irqaction *action;
 	struct irq_desc *desc;
-	unsigned long flags;
 	int retval;
 
 	if (irq == IRQ_NOTCONNECTED)
@@ -2345,21 +2265,17 @@ int request_nmi(unsigned int irq, irq_handler_t handler,
 	if (retval)
 		goto err_irq_setup;
 
-	raw_spin_lock_irqsave(&desc->lock, flags);
-
-	/* Setup NMI state */
-	desc->istate |= IRQS_NMI;
-	retval = irq_nmi_setup(desc);
-	if (retval) {
-		__cleanup_nmi(irq, desc);
-		raw_spin_unlock_irqrestore(&desc->lock, flags);
-		return -EINVAL;
+	scoped_guard(raw_spinlock_irqsave, &desc->lock) {
+		/* Setup NMI state */
+		desc->istate |= IRQS_NMI;
+		retval = irq_nmi_setup(desc);
+		if (retval) {
+			__cleanup_nmi(irq, desc);
+			return -EINVAL;
+		}
+		return 0;
 	}
 
-	raw_spin_unlock_irqrestore(&desc->lock, flags);
-
-	return 0;
-
 err_irq_setup:
 	irq_chip_pm_put(&desc->irq_data);
 err_out:
@@ -2370,35 +2286,25 @@ err_out:
 
 void enable_percpu_irq(unsigned int irq, unsigned int type)
 {
-	unsigned int cpu = smp_processor_id();
-	unsigned long flags;
-	struct irq_desc *desc = irq_get_desc_lock(irq, &flags, IRQ_GET_DESC_CHECK_PERCPU);
+	scoped_irqdesc_get_and_lock(irq, IRQ_GET_DESC_CHECK_PERCPU) {
+		struct irq_desc *desc = scoped_irqdesc;
 
-	if (!desc)
-		return;
-
-	/*
-	 * If the trigger type is not specified by the caller, then
-	 * use the default for this interrupt.
-	 */
-	type &= IRQ_TYPE_SENSE_MASK;
-	if (type == IRQ_TYPE_NONE)
-		type = irqd_get_trigger_type(&desc->irq_data);
-
-	if (type != IRQ_TYPE_NONE) {
-		int ret;
-
-		ret = __irq_set_trigger(desc, type);
-
-		if (ret) {
-			WARN(1, "failed to set type for IRQ%d\n", irq);
-			goto out;
+		/*
+		 * If the trigger type is not specified by the caller, then
+		 * use the default for this interrupt.
+		 */
+		type &= IRQ_TYPE_SENSE_MASK;
+		if (type == IRQ_TYPE_NONE)
+			type = irqd_get_trigger_type(&desc->irq_data);
+
+		if (type != IRQ_TYPE_NONE) {
+			if (__irq_set_trigger(desc, type)) {
+				WARN(1, "failed to set type for IRQ%d\n", irq);
+				return;
+			}
 		}
+		irq_percpu_enable(desc, smp_processor_id());
 	}
-
-	irq_percpu_enable(desc, cpu);
-out:
-	irq_put_desc_unlock(desc, flags);
 }
 EXPORT_SYMBOL_GPL(enable_percpu_irq);
 
@@ -2416,33 +2322,16 @@ void enable_percpu_nmi(unsigned int irq, unsigned int type)
  */
 bool irq_percpu_is_enabled(unsigned int irq)
 {
-	unsigned int cpu = smp_processor_id();
-	struct irq_desc *desc;
-	unsigned long flags;
-	bool is_enabled;
-
-	desc = irq_get_desc_lock(irq, &flags, IRQ_GET_DESC_CHECK_PERCPU);
-	if (!desc)
-		return false;
-
-	is_enabled = cpumask_test_cpu(cpu, desc->percpu_enabled);
-	irq_put_desc_unlock(desc, flags);
-
-	return is_enabled;
+	scoped_irqdesc_get_and_lock(irq, IRQ_GET_DESC_CHECK_PERCPU)
+		return cpumask_test_cpu(smp_processor_id(), scoped_irqdesc->percpu_enabled);
+	return false;
 }
 EXPORT_SYMBOL_GPL(irq_percpu_is_enabled);
 
 void disable_percpu_irq(unsigned int irq)
 {
-	unsigned int cpu = smp_processor_id();
-	unsigned long flags;
-	struct irq_desc *desc = irq_get_desc_lock(irq, &flags, IRQ_GET_DESC_CHECK_PERCPU);
-
-	if (!desc)
-		return;
-
-	irq_percpu_disable(desc, cpu);
-	irq_put_desc_unlock(desc, flags);
+	scoped_irqdesc_get_and_lock(irq, IRQ_GET_DESC_CHECK_PERCPU)
+		irq_percpu_disable(scoped_irqdesc, smp_processor_id());
 }
 EXPORT_SYMBOL_GPL(disable_percpu_irq);
 
@@ -2458,71 +2347,47 @@ static struct irqaction *__free_percpu_irq(unsigned int irq, void __percpu *dev_
 {
 	struct irq_desc *desc = irq_to_desc(irq);
 	struct irqaction *action;
-	unsigned long flags;
 
 	WARN(in_interrupt(), "Trying to free IRQ %d from IRQ context!\n", irq);
 
 	if (!desc)
 		return NULL;
 
-	raw_spin_lock_irqsave(&desc->lock, flags);
+	scoped_guard(raw_spinlock_irqsave, &desc->lock) {
+		action = desc->action;
+		if (!action || action->percpu_dev_id != dev_id) {
+			WARN(1, "Trying to free already-free IRQ %d\n", irq);
+			return NULL;
+		}
 
-	action = desc->action;
-	if (!action || action->percpu_dev_id != dev_id) {
-		WARN(1, "Trying to free already-free IRQ %d\n", irq);
-		goto bad;
-	}
+		if (!cpumask_empty(desc->percpu_enabled)) {
+			WARN(1, "percpu IRQ %d still enabled on CPU%d!\n",
+			     irq, cpumask_first(desc->percpu_enabled));
+			return NULL;
+		}
 
-	if (!cpumask_empty(desc->percpu_enabled)) {
-		WARN(1, "percpu IRQ %d still enabled on CPU%d!\n",
-		     irq, cpumask_first(desc->percpu_enabled));
-		goto bad;
+		/* Found it - now remove it from the list of entries: */
+		desc->action = NULL;
+		desc->istate &= ~IRQS_NMI;
 	}
 
-	/* Found it - now remove it from the list of entries: */
-	desc->action = NULL;
-
-	desc->istate &= ~IRQS_NMI;
-
-	raw_spin_unlock_irqrestore(&desc->lock, flags);
-
 	unregister_handler_proc(irq, action);
-
 	irq_chip_pm_put(&desc->irq_data);
 	module_put(desc->owner);
 	return action;
-
-bad:
-	raw_spin_unlock_irqrestore(&desc->lock, flags);
-	return NULL;
 }
 
 /**
- *	remove_percpu_irq - free a per-cpu interrupt
- *	@irq: Interrupt line to free
- *	@act: irqaction for the interrupt
+ * free_percpu_irq - free an interrupt allocated with request_percpu_irq
+ * @irq:	Interrupt line to free
+ * @dev_id:	Device identity to free
  *
- * Used to remove interrupts statically setup by the early boot process.
- */
-void remove_percpu_irq(unsigned int irq, struct irqaction *act)
-{
-	struct irq_desc *desc = irq_to_desc(irq);
-
-	if (desc && irq_settings_is_per_cpu_devid(desc))
-	    __free_percpu_irq(irq, act->percpu_dev_id);
-}
-
-/**
- *	free_percpu_irq - free an interrupt allocated with request_percpu_irq
- *	@irq: Interrupt line to free
- *	@dev_id: Device identity to free
+ * Remove a percpu interrupt handler. The handler is removed, but the
+ * interrupt line is not disabled. This must be done on each CPU before
+ * calling this function. The function does not return until any executing
+ * interrupts for this IRQ have completed.
  *
- *	Remove a percpu interrupt handler. The handler is removed, but
- *	the interrupt line is not disabled. This must be done on each
- *	CPU before calling this function. The function does not return
- *	until any executing interrupts for this IRQ have completed.
- *
- *	This function must not be called from interrupt context.
+ * This function must not be called from interrupt context.
  */
 void free_percpu_irq(unsigned int irq, void __percpu *dev_id)
 {
@@ -2551,9 +2416,9 @@ void free_percpu_nmi(unsigned int irq, void __percpu *dev_id)
 }
 
 /**
- *	setup_percpu_irq - setup a per-cpu interrupt
- *	@irq: Interrupt line to setup
- *	@act: irqaction for the interrupt
+ * setup_percpu_irq - setup a per-cpu interrupt
+ * @irq:	Interrupt line to setup
+ * @act:	irqaction for the interrupt
  *
  * Used to statically setup per-cpu interrupts in the early boot process.
  */
@@ -2578,21 +2443,20 @@ int setup_percpu_irq(unsigned int irq, struct irqaction *act)
 }
 
 /**
- *	__request_percpu_irq - allocate a percpu interrupt line
- *	@irq: Interrupt line to allocate
- *	@handler: Function to be called when the IRQ occurs.
- *	@flags: Interrupt type flags (IRQF_TIMER only)
- *	@devname: An ascii name for the claiming device
- *	@dev_id: A percpu cookie passed back to the handler function
- *
- *	This call allocates interrupt resources and enables the
- *	interrupt on the local CPU. If the interrupt is supposed to be
- *	enabled on other CPUs, it has to be done on each CPU using
- *	enable_percpu_irq().
- *
- *	Dev_id must be globally unique. It is a per-cpu variable, and
- *	the handler gets called with the interrupted CPU's instance of
- *	that variable.
+ * __request_percpu_irq - allocate a percpu interrupt line
+ * @irq:	Interrupt line to allocate
+ * @handler:	Function to be called when the IRQ occurs.
+ * @flags:	Interrupt type flags (IRQF_TIMER only)
+ * @devname:	An ascii name for the claiming device
+ * @dev_id:	A percpu cookie passed back to the handler function
+ *
+ * This call allocates interrupt resources and enables the interrupt on the
+ * local CPU. If the interrupt is supposed to be enabled on other CPUs, it
+ * has to be done on each CPU using enable_percpu_irq().
+ *
+ * @dev_id must be globally unique. It is a per-cpu variable, and
+ * the handler gets called with the interrupted CPU's instance of
+ * that variable.
  */
 int __request_percpu_irq(unsigned int irq, irq_handler_t handler,
 			 unsigned long flags, const char *devname,
@@ -2640,32 +2504,31 @@ int __request_percpu_irq(unsigned int irq, irq_handler_t handler,
 EXPORT_SYMBOL_GPL(__request_percpu_irq);
 
 /**
- *	request_percpu_nmi - allocate a percpu interrupt line for NMI delivery
- *	@irq: Interrupt line to allocate
- *	@handler: Function to be called when the IRQ occurs.
- *	@name: An ascii name for the claiming device
- *	@dev_id: A percpu cookie passed back to the handler function
+ * request_percpu_nmi - allocate a percpu interrupt line for NMI delivery
+ * @irq:	Interrupt line to allocate
+ * @handler:	Function to be called when the IRQ occurs.
+ * @name:	An ascii name for the claiming device
+ * @dev_id:	A percpu cookie passed back to the handler function
  *
- *	This call allocates interrupt resources for a per CPU NMI. Per CPU NMIs
- *	have to be setup on each CPU by calling prepare_percpu_nmi() before
- *	being enabled on the same CPU by using enable_percpu_nmi().
+ * This call allocates interrupt resources for a per CPU NMI. Per CPU NMIs
+ * have to be setup on each CPU by calling prepare_percpu_nmi() before
+ * being enabled on the same CPU by using enable_percpu_nmi().
  *
- *	Dev_id must be globally unique. It is a per-cpu variable, and
- *	the handler gets called with the interrupted CPU's instance of
- *	that variable.
+ * @dev_id must be globally unique. It is a per-cpu variable, and the
+ * handler gets called with the interrupted CPU's instance of that
+ * variable.
  *
- *	Interrupt lines requested for NMI delivering should have auto enabling
- *	setting disabled.
+ * Interrupt lines requested for NMI delivering should have auto enabling
+ * setting disabled.
  *
- *	If the interrupt line cannot be used to deliver NMIs, function
- *	will fail returning a negative value.
+ * If the interrupt line cannot be used to deliver NMIs, function
+ * will fail returning a negative value.
  */
 int request_percpu_nmi(unsigned int irq, irq_handler_t handler,
 		       const char *name, void __percpu *dev_id)
 {
 	struct irqaction *action;
 	struct irq_desc *desc;
-	unsigned long flags;
 	int retval;
 
 	if (!handler)
@@ -2701,10 +2564,8 @@ int request_percpu_nmi(unsigned int irq, irq_handler_t handler,
 	if (retval)
 		goto err_irq_setup;
 
-	raw_spin_lock_irqsave(&desc->lock, flags);
-	desc->istate |= IRQS_NMI;
-	raw_spin_unlock_irqrestore(&desc->lock, flags);
-
+	scoped_guard(raw_spinlock_irqsave, &desc->lock)
+		desc->istate |= IRQS_NMI;
 	return 0;
 
 err_irq_setup:
@@ -2716,79 +2577,55 @@ err_out:
 }
 
 /**
- *	prepare_percpu_nmi - performs CPU local setup for NMI delivery
- *	@irq: Interrupt line to prepare for NMI delivery
+ * prepare_percpu_nmi - performs CPU local setup for NMI delivery
+ * @irq: Interrupt line to prepare for NMI delivery
  *
- *	This call prepares an interrupt line to deliver NMI on the current CPU,
- *	before that interrupt line gets enabled with enable_percpu_nmi().
+ * This call prepares an interrupt line to deliver NMI on the current CPU,
+ * before that interrupt line gets enabled with enable_percpu_nmi().
  *
- *	As a CPU local operation, this should be called from non-preemptible
- *	context.
+ * As a CPU local operation, this should be called from non-preemptible
+ * context.
  *
- *	If the interrupt line cannot be used to deliver NMIs, function
- *	will fail returning a negative value.
+ * If the interrupt line cannot be used to deliver NMIs, function will fail
+ * returning a negative value.
  */
 int prepare_percpu_nmi(unsigned int irq)
 {
-	unsigned long flags;
-	struct irq_desc *desc;
-	int ret = 0;
+	int ret = -EINVAL;
 
 	WARN_ON(preemptible());
 
-	desc = irq_get_desc_lock(irq, &flags,
-				 IRQ_GET_DESC_CHECK_PERCPU);
-	if (!desc)
-		return -EINVAL;
-
-	if (WARN(!irq_is_nmi(desc),
-		 KERN_ERR "prepare_percpu_nmi called for a non-NMI interrupt: irq %u\n",
-		 irq)) {
-		ret = -EINVAL;
-		goto out;
-	}
+	scoped_irqdesc_get_and_lock(irq, IRQ_GET_DESC_CHECK_PERCPU) {
+		if (WARN(!irq_is_nmi(scoped_irqdesc),
+			 "prepare_percpu_nmi called for a non-NMI interrupt: irq %u\n", irq))
+			return -EINVAL;
 
-	ret = irq_nmi_setup(desc);
-	if (ret) {
-		pr_err("Failed to setup NMI delivery: irq %u\n", irq);
-		goto out;
+		ret = irq_nmi_setup(scoped_irqdesc);
+		if (ret)
+			pr_err("Failed to setup NMI delivery: irq %u\n", irq);
 	}
-
-out:
-	irq_put_desc_unlock(desc, flags);
 	return ret;
 }
 
 /**
- *	teardown_percpu_nmi - undoes NMI setup of IRQ line
- *	@irq: Interrupt line from which CPU local NMI configuration should be
- *	      removed
- *
- *	This call undoes the setup done by prepare_percpu_nmi().
+ * teardown_percpu_nmi - undoes NMI setup of IRQ line
+ * @irq: Interrupt line from which CPU local NMI configuration should be removed
  *
- *	IRQ line should not be enabled for the current CPU.
+ * This call undoes the setup done by prepare_percpu_nmi().
  *
- *	As a CPU local operation, this should be called from non-preemptible
- *	context.
+ * IRQ line should not be enabled for the current CPU.
+ * As a CPU local operation, this should be called from non-preemptible
+ * context.
  */
 void teardown_percpu_nmi(unsigned int irq)
 {
-	unsigned long flags;
-	struct irq_desc *desc;
-
 	WARN_ON(preemptible());
 
-	desc = irq_get_desc_lock(irq, &flags,
-				 IRQ_GET_DESC_CHECK_PERCPU);
-	if (!desc)
-		return;
-
-	if (WARN_ON(!irq_is_nmi(desc)))
-		goto out;
-
-	irq_nmi_teardown(desc);
-out:
-	irq_put_desc_unlock(desc, flags);
+	scoped_irqdesc_get_and_lock(irq, IRQ_GET_DESC_CHECK_PERCPU) {
+		if (WARN_ON(!irq_is_nmi(scoped_irqdesc)))
+			return;
+		irq_nmi_teardown(scoped_irqdesc);
+	}
 }
 
 static int __irq_get_irqchip_state(struct irq_data *data, enum irqchip_irq_state which, bool *state)
@@ -2815,87 +2652,62 @@ static int __irq_get_irqchip_state(struct irq_data *data, enum irqchip_irq_state
 }
 
 /**
- *	irq_get_irqchip_state - returns the irqchip state of a interrupt.
- *	@irq: Interrupt line that is forwarded to a VM
- *	@which: One of IRQCHIP_STATE_* the caller wants to know about
- *	@state: a pointer to a boolean where the state is to be stored
+ * irq_get_irqchip_state - returns the irqchip state of a interrupt.
+ * @irq:	Interrupt line that is forwarded to a VM
+ * @which:	One of IRQCHIP_STATE_* the caller wants to know about
+ * @state:	a pointer to a boolean where the state is to be stored
  *
- *	This call snapshots the internal irqchip state of an
- *	interrupt, returning into @state the bit corresponding to
- *	stage @which
+ * This call snapshots the internal irqchip state of an interrupt,
+ * returning into @state the bit corresponding to stage @which
  *
- *	This function should be called with preemption disabled if the
- *	interrupt controller has per-cpu registers.
+ * This function should be called with preemption disabled if the interrupt
+ * controller has per-cpu registers.
  */
-int irq_get_irqchip_state(unsigned int irq, enum irqchip_irq_state which,
-			  bool *state)
+int irq_get_irqchip_state(unsigned int irq, enum irqchip_irq_state which, bool *state)
 {
-	struct irq_desc *desc;
-	struct irq_data *data;
-	unsigned long flags;
-	int err = -EINVAL;
-
-	desc = irq_get_desc_buslock(irq, &flags, 0);
-	if (!desc)
-		return err;
+	scoped_irqdesc_get_and_buslock(irq, 0) {
+		struct irq_data *data = irq_desc_get_irq_data(scoped_irqdesc);
 
-	data = irq_desc_get_irq_data(desc);
-
-	err = __irq_get_irqchip_state(data, which, state);
-
-	irq_put_desc_busunlock(desc, flags);
-	return err;
+		return __irq_get_irqchip_state(data, which, state);
+	}
+	return -EINVAL;
 }
 EXPORT_SYMBOL_GPL(irq_get_irqchip_state);
 
 /**
- *	irq_set_irqchip_state - set the state of a forwarded interrupt.
- *	@irq: Interrupt line that is forwarded to a VM
- *	@which: State to be restored (one of IRQCHIP_STATE_*)
- *	@val: Value corresponding to @which
+ * irq_set_irqchip_state - set the state of a forwarded interrupt.
+ * @irq:	Interrupt line that is forwarded to a VM
+ * @which:	State to be restored (one of IRQCHIP_STATE_*)
+ * @val:	Value corresponding to @which
  *
- *	This call sets the internal irqchip state of an interrupt,
- *	depending on the value of @which.
+ * This call sets the internal irqchip state of an interrupt, depending on
+ * the value of @which.
  *
- *	This function should be called with migration disabled if the
- *	interrupt controller has per-cpu registers.
+ * This function should be called with migration disabled if the interrupt
+ * controller has per-cpu registers.
  */
-int irq_set_irqchip_state(unsigned int irq, enum irqchip_irq_state which,
-			  bool val)
+int irq_set_irqchip_state(unsigned int irq, enum irqchip_irq_state which, bool val)
 {
-	struct irq_desc *desc;
-	struct irq_data *data;
-	struct irq_chip *chip;
-	unsigned long flags;
-	int err = -EINVAL;
+	scoped_irqdesc_get_and_buslock(irq, 0) {
+		struct irq_data *data = irq_desc_get_irq_data(scoped_irqdesc);
+		struct irq_chip *chip;
 
-	desc = irq_get_desc_buslock(irq, &flags, 0);
-	if (!desc)
-		return err;
+		do {
+			chip = irq_data_get_irq_chip(data);
 
-	data = irq_desc_get_irq_data(desc);
+			if (WARN_ON_ONCE(!chip))
+				return -ENODEV;
 
-	do {
-		chip = irq_data_get_irq_chip(data);
-		if (WARN_ON_ONCE(!chip)) {
-			err = -ENODEV;
-			goto out_unlock;
-		}
-		if (chip->irq_set_irqchip_state)
-			break;
-#ifdef CONFIG_IRQ_DOMAIN_HIERARCHY
-		data = data->parent_data;
-#else
-		data = NULL;
-#endif
-	} while (data);
+			if (chip->irq_set_irqchip_state)
+				break;
 
-	if (data)
-		err = chip->irq_set_irqchip_state(data, which, val);
+			data = irqd_get_parent_data(data);
+		} while (data);
 
-out_unlock:
-	irq_put_desc_busunlock(desc, flags);
-	return err;
+		if (data)
+			return chip->irq_set_irqchip_state(data, which, val);
+	}
+	return -EINVAL;
 }
 EXPORT_SYMBOL_GPL(irq_set_irqchip_state);
 
diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c
index c05ba7ca00fa..9febe797a5f6 100644
--- a/kernel/irq/msi.c
+++ b/kernel/irq/msi.c
@@ -59,7 +59,8 @@ struct msi_ctrl {
 static void msi_domain_free_locked(struct device *dev, struct msi_ctrl *ctrl);
 static unsigned int msi_domain_get_hwsize(struct device *dev, unsigned int domid);
 static inline int msi_sysfs_create_group(struct device *dev);
-
+static int msi_domain_prepare_irqs(struct irq_domain *domain, struct device *dev,
+				   int nvec, msi_alloc_info_t *arg);
 
 /**
  * msi_alloc_desc - Allocate an initialized msi_desc
@@ -343,26 +344,30 @@ int msi_setup_device_data(struct device *dev)
 }
 
 /**
- * msi_lock_descs - Lock the MSI descriptor storage of a device
+ * __msi_lock_descs - Lock the MSI descriptor storage of a device
  * @dev:	Device to operate on
+ *
+ * Internal function for guard(msi_descs_lock). Don't use in code.
  */
-void msi_lock_descs(struct device *dev)
+void __msi_lock_descs(struct device *dev)
 {
 	mutex_lock(&dev->msi.data->mutex);
 }
-EXPORT_SYMBOL_GPL(msi_lock_descs);
+EXPORT_SYMBOL_GPL(__msi_lock_descs);
 
 /**
- * msi_unlock_descs - Unlock the MSI descriptor storage of a device
+ * __msi_unlock_descs - Unlock the MSI descriptor storage of a device
  * @dev:	Device to operate on
+ *
+ * Internal function for guard(msi_descs_lock). Don't use in code.
  */
-void msi_unlock_descs(struct device *dev)
+void __msi_unlock_descs(struct device *dev)
 {
 	/* Invalidate the index which was cached by the iterator */
 	dev->msi.data->__iter_idx = MSI_XA_MAX_INDEX;
 	mutex_unlock(&dev->msi.data->mutex);
 }
-EXPORT_SYMBOL_GPL(msi_unlock_descs);
+EXPORT_SYMBOL_GPL(__msi_unlock_descs);
 
 static struct msi_desc *msi_find_desc(struct msi_device_data *md, unsigned int domid,
 				      enum msi_desc_filter filter)
@@ -448,7 +453,6 @@ EXPORT_SYMBOL_GPL(msi_next_desc);
 unsigned int msi_domain_get_virq(struct device *dev, unsigned int domid, unsigned int index)
 {
 	struct msi_desc *desc;
-	unsigned int ret = 0;
 	bool pcimsi = false;
 	struct xarray *xa;
 
@@ -462,7 +466,7 @@ unsigned int msi_domain_get_virq(struct device *dev, unsigned int domid, unsigne
 	if (dev_is_pci(dev) && domid == MSI_DEFAULT_DOMAIN)
 		pcimsi = to_pci_dev(dev)->msi_enabled;
 
-	msi_lock_descs(dev);
+	guard(msi_descs_lock)(dev);
 	xa = &dev->msi.data->__domains[domid].store;
 	desc = xa_load(xa, pcimsi ? 0 : index);
 	if (desc && desc->irq) {
@@ -471,16 +475,12 @@ unsigned int msi_domain_get_virq(struct device *dev, unsigned int domid, unsigne
 		 * PCI-MSIX and platform MSI use a descriptor per
 		 * interrupt.
 		 */
-		if (pcimsi) {
-			if (index < desc->nvec_used)
-				ret = desc->irq + index;
-		} else {
-			ret = desc->irq;
-		}
+		if (!pcimsi)
+			return desc->irq;
+		if (index < desc->nvec_used)
+			return desc->irq + index;
 	}
-
-	msi_unlock_descs(dev);
-	return ret;
+	return 0;
 }
 EXPORT_SYMBOL_GPL(msi_domain_get_virq);
 
@@ -796,6 +796,10 @@ static int msi_domain_ops_prepare(struct irq_domain *domain, struct device *dev,
 	return 0;
 }
 
+static void msi_domain_ops_teardown(struct irq_domain *domain, msi_alloc_info_t *arg)
+{
+}
+
 static void msi_domain_ops_set_desc(msi_alloc_info_t *arg,
 				    struct msi_desc *desc)
 {
@@ -821,6 +825,7 @@ static struct msi_domain_ops msi_domain_ops_default = {
 	.get_hwirq		= msi_domain_ops_get_hwirq,
 	.msi_init		= msi_domain_ops_init,
 	.msi_prepare		= msi_domain_ops_prepare,
+	.msi_teardown		= msi_domain_ops_teardown,
 	.set_desc		= msi_domain_ops_set_desc,
 };
 
@@ -842,6 +847,8 @@ static void msi_domain_update_dom_ops(struct msi_domain_info *info)
 		ops->msi_init = msi_domain_ops_default.msi_init;
 	if (ops->msi_prepare == NULL)
 		ops->msi_prepare = msi_domain_ops_default.msi_prepare;
+	if (ops->msi_teardown == NULL)
+		ops->msi_teardown = msi_domain_ops_default.msi_teardown;
 	if (ops->set_desc == NULL)
 		ops->set_desc = msi_domain_ops_default.set_desc;
 }
@@ -905,6 +912,32 @@ struct irq_domain *msi_create_irq_domain(struct fwnode_handle *fwnode,
 }
 
 /**
+ * msi_create_parent_irq_domain - Create an MSI-parent interrupt domain
+ * @info:		MSI irqdomain creation info
+ * @msi_parent_ops:	MSI parent callbacks and configuration
+ *
+ * Return: pointer to the created &struct irq_domain or %NULL on failure
+ */
+struct irq_domain *msi_create_parent_irq_domain(struct irq_domain_info *info,
+						const struct msi_parent_ops *msi_parent_ops)
+{
+	struct irq_domain *d;
+
+	info->hwirq_max		= max(info->hwirq_max, info->size);
+	info->size		= info->hwirq_max;
+	info->domain_flags	|= IRQ_DOMAIN_FLAG_MSI_PARENT;
+	info->bus_token		= msi_parent_ops->bus_select_token;
+
+	d = irq_domain_instantiate(info);
+	if (IS_ERR(d))
+		return NULL;
+
+	d->msi_parent_ops = msi_parent_ops;
+	return d;
+}
+EXPORT_SYMBOL_GPL(msi_create_parent_irq_domain);
+
+/**
  * msi_parent_init_dev_msi_info - Delegate initialization of device MSI info down
  *				  in the domain hierarchy
  * @dev:		The device for which the domain should be created
@@ -998,9 +1031,8 @@ bool msi_create_device_irq_domain(struct device *dev, unsigned int domid,
 				  void *chip_data)
 {
 	struct irq_domain *domain, *parent = dev->msi.domain;
-	struct fwnode_handle *fwnode, *fwnalloced = NULL;
-	struct msi_domain_template *bundle;
 	const struct msi_parent_ops *pops;
+	struct fwnode_handle *fwnode;
 
 	if (!irq_domain_is_msi_parent(parent))
 		return false;
@@ -1008,7 +1040,8 @@ bool msi_create_device_irq_domain(struct device *dev, unsigned int domid,
 	if (domid >= MSI_MAX_DEVICE_IRQDOMAINS)
 		return false;
 
-	bundle = kmemdup(template, sizeof(*bundle), GFP_KERNEL);
+	struct msi_domain_template *bundle __free(kfree) =
+		kmemdup(template, sizeof(*bundle), GFP_KERNEL);
 	if (!bundle)
 		return false;
 
@@ -1017,6 +1050,7 @@ bool msi_create_device_irq_domain(struct device *dev, unsigned int domid,
 	bundle->info.ops = &bundle->ops;
 	bundle->info.data = domain_data;
 	bundle->info.chip_data = chip_data;
+	bundle->info.alloc_data = &bundle->alloc_info;
 
 	pops = parent->msi_parent_ops;
 	snprintf(bundle->name, sizeof(bundle->name), "%s%s-%s",
@@ -1031,41 +1065,43 @@ bool msi_create_device_irq_domain(struct device *dev, unsigned int domid,
 	 * node as they are not guaranteed to have a fwnode. They are never
 	 * looked up and always handled in the context of the device.
 	 */
-	if (bundle->info.flags & MSI_FLAG_USE_DEV_FWNODE)
-		fwnode = dev->fwnode;
+	struct fwnode_handle *fwnode_alloced __free(irq_domain_free_fwnode) = NULL;
+
+	if (!(bundle->info.flags & MSI_FLAG_USE_DEV_FWNODE))
+		fwnode = fwnode_alloced = irq_domain_alloc_named_fwnode(bundle->name);
 	else
-		fwnode = fwnalloced = irq_domain_alloc_named_fwnode(bundle->name);
+		fwnode = dev->fwnode;
 
 	if (!fwnode)
-		goto free_bundle;
+		return false;
 
 	if (msi_setup_device_data(dev))
-		goto free_fwnode;
-
-	msi_lock_descs(dev);
+		return false;
 
+	guard(msi_descs_lock)(dev);
 	if (WARN_ON_ONCE(msi_get_device_domain(dev, domid)))
-		goto fail;
+		return false;
 
 	if (!pops->init_dev_msi_info(dev, parent, parent, &bundle->info))
-		goto fail;
+		return false;
 
 	domain = __msi_create_irq_domain(fwnode, &bundle->info, IRQ_DOMAIN_FLAG_MSI_DEVICE, parent);
 	if (!domain)
-		goto fail;
+		return false;
 
 	domain->dev = dev;
 	dev->msi.data->__domains[domid].domain = domain;
-	msi_unlock_descs(dev);
-	return true;
 
-fail:
-	msi_unlock_descs(dev);
-free_fwnode:
-	irq_domain_free_fwnode(fwnalloced);
-free_bundle:
-	kfree(bundle);
-	return false;
+	if (msi_domain_prepare_irqs(domain, dev, hwsize, &bundle->alloc_info)) {
+		dev->msi.data->__domains[domid].domain = NULL;
+		irq_domain_remove(domain);
+		return false;
+	}
+
+	/* @bundle and @fwnode_alloced are now in use. Prevent cleanup */
+	retain_and_null_ptr(bundle);
+	retain_and_null_ptr(fwnode_alloced);
+	return true;
 }
 
 /**
@@ -1079,23 +1115,21 @@ void msi_remove_device_irq_domain(struct device *dev, unsigned int domid)
 	struct msi_domain_info *info;
 	struct irq_domain *domain;
 
-	msi_lock_descs(dev);
-
+	guard(msi_descs_lock)(dev);
 	domain = msi_get_device_domain(dev, domid);
-
 	if (!domain || !irq_domain_is_msi_device(domain))
-		goto unlock;
+		return;
 
 	dev->msi.data->__domains[domid].domain = NULL;
 	info = domain->host_data;
+
+	info->ops->msi_teardown(domain, info->alloc_data);
+
 	if (irq_domain_is_msi_device(domain))
 		fwnode = domain->fwnode;
 	irq_domain_remove(domain);
 	irq_domain_free_fwnode(fwnode);
 	kfree(container_of(info, struct msi_domain_template, info));
-
-unlock:
-	msi_unlock_descs(dev);
 }
 
 /**
@@ -1111,16 +1145,14 @@ bool msi_match_device_irq_domain(struct device *dev, unsigned int domid,
 {
 	struct msi_domain_info *info;
 	struct irq_domain *domain;
-	bool ret = false;
 
-	msi_lock_descs(dev);
+	guard(msi_descs_lock)(dev);
 	domain = msi_get_device_domain(dev, domid);
 	if (domain && irq_domain_is_msi_device(domain)) {
 		info = domain->host_data;
-		ret = info->bus_token == bus_token;
+		return info->bus_token == bus_token;
 	}
-	msi_unlock_descs(dev);
-	return ret;
+	return false;
 }
 
 static int msi_domain_prepare_irqs(struct irq_domain *domain, struct device *dev,
@@ -1238,6 +1270,24 @@ static int msi_init_virq(struct irq_domain *domain, int virq, unsigned int vflag
 	return 0;
 }
 
+static int populate_alloc_info(struct irq_domain *domain, struct device *dev,
+			       unsigned int nirqs, msi_alloc_info_t *arg)
+{
+	struct msi_domain_info *info = domain->host_data;
+
+	/*
+	 * If the caller has provided a template alloc info, use that. Once
+	 * all users of msi_create_irq_domain() have been eliminated, this
+	 * should be the only source of allocation information, and the
+	 * prepare call below should be finally removed.
+	 */
+	if (!info->alloc_data)
+		return msi_domain_prepare_irqs(domain, dev, nirqs, arg);
+
+	*arg = *info->alloc_data;
+	return 0;
+}
+
 static int __msi_domain_alloc_irqs(struct device *dev, struct irq_domain *domain,
 				   struct msi_ctrl *ctrl)
 {
@@ -1250,7 +1300,7 @@ static int __msi_domain_alloc_irqs(struct device *dev, struct irq_domain *domain
 	unsigned long idx;
 	int i, ret, virq;
 
-	ret = msi_domain_prepare_irqs(domain, dev, ctrl->nirqs, &arg);
+	ret = populate_alloc_info(domain, dev, ctrl->nirqs, &arg);
 	if (ret)
 		return ret;
 
@@ -1391,12 +1441,9 @@ int msi_domain_alloc_irqs_range_locked(struct device *dev, unsigned int domid,
 int msi_domain_alloc_irqs_range(struct device *dev, unsigned int domid,
 				unsigned int first, unsigned int last)
 {
-	int ret;
 
-	msi_lock_descs(dev);
-	ret = msi_domain_alloc_irqs_range_locked(dev, domid, first, last);
-	msi_unlock_descs(dev);
-	return ret;
+	guard(msi_descs_lock)(dev);
+	return msi_domain_alloc_irqs_range_locked(dev, domid, first, last);
 }
 EXPORT_SYMBOL_GPL(msi_domain_alloc_irqs_range);
 
@@ -1500,12 +1547,8 @@ struct msi_map msi_domain_alloc_irq_at(struct device *dev, unsigned int domid, u
 				       const struct irq_affinity_desc *affdesc,
 				       union msi_instance_cookie *icookie)
 {
-	struct msi_map map;
-
-	msi_lock_descs(dev);
-	map = __msi_domain_alloc_irq_at(dev, domid, index, affdesc, icookie);
-	msi_unlock_descs(dev);
-	return map;
+	guard(msi_descs_lock)(dev);
+	return __msi_domain_alloc_irq_at(dev, domid, index, affdesc, icookie);
 }
 
 /**
@@ -1542,13 +1585,11 @@ int msi_device_domain_alloc_wired(struct irq_domain *domain, unsigned int hwirq,
 
 	icookie.value = ((u64)type << 32) | hwirq;
 
-	msi_lock_descs(dev);
+	guard(msi_descs_lock)(dev);
 	if (WARN_ON_ONCE(msi_get_device_domain(dev, domid) != domain))
 		map.index = -EINVAL;
 	else
 		map = __msi_domain_alloc_irq_at(dev, domid, MSI_ANY_INDEX, NULL, &icookie);
-	msi_unlock_descs(dev);
-
 	return map.index >= 0 ? map.virq : map.index;
 }
 
@@ -1641,9 +1682,8 @@ void msi_domain_free_irqs_range_locked(struct device *dev, unsigned int domid,
 void msi_domain_free_irqs_range(struct device *dev, unsigned int domid,
 				unsigned int first, unsigned int last)
 {
-	msi_lock_descs(dev);
+	guard(msi_descs_lock)(dev);
 	msi_domain_free_irqs_range_locked(dev, domid, first, last);
-	msi_unlock_descs(dev);
 }
 EXPORT_SYMBOL_GPL(msi_domain_free_irqs_all);
 
@@ -1673,9 +1713,8 @@ void msi_domain_free_irqs_all_locked(struct device *dev, unsigned int domid)
  */
 void msi_domain_free_irqs_all(struct device *dev, unsigned int domid)
 {
-	msi_lock_descs(dev);
+	guard(msi_descs_lock)(dev);
 	msi_domain_free_irqs_all_locked(dev, domid);
-	msi_unlock_descs(dev);
 }
 
 /**
@@ -1694,12 +1733,11 @@ void msi_device_domain_free_wired(struct irq_domain *domain, unsigned int virq)
 	if (WARN_ON_ONCE(!dev || !desc || domain->bus_token != DOMAIN_BUS_WIRED_TO_MSI))
 		return;
 
-	msi_lock_descs(dev);
-	if (!WARN_ON_ONCE(msi_get_device_domain(dev, MSI_DEFAULT_DOMAIN) != domain)) {
-		msi_domain_free_irqs_range_locked(dev, MSI_DEFAULT_DOMAIN, desc->msi_index,
-						  desc->msi_index);
-	}
-	msi_unlock_descs(dev);
+	guard(msi_descs_lock)(dev);
+	if (WARN_ON_ONCE(msi_get_device_domain(dev, MSI_DEFAULT_DOMAIN) != domain))
+		return;
+	msi_domain_free_irqs_range_locked(dev, MSI_DEFAULT_DOMAIN, desc->msi_index,
+					  desc->msi_index);
 }
 
 /**
diff --git a/kernel/irq/pm.c b/kernel/irq/pm.c
index c556bc49d213..445912d51033 100644
--- a/kernel/irq/pm.c
+++ b/kernel/irq/pm.c
@@ -46,8 +46,7 @@ void irq_pm_install_action(struct irq_desc *desc, struct irqaction *action)
 		desc->cond_suspend_depth++;
 
 	WARN_ON_ONCE(desc->no_suspend_depth &&
-		     (desc->no_suspend_depth +
-			desc->cond_suspend_depth) != desc->nr_actions);
+		     (desc->no_suspend_depth + desc->cond_suspend_depth) != desc->nr_actions);
 }
 
 /*
@@ -134,14 +133,12 @@ void suspend_device_irqs(void)
 	int irq;
 
 	for_each_irq_desc(irq, desc) {
-		unsigned long flags;
 		bool sync;
 
 		if (irq_settings_is_nested_thread(desc))
 			continue;
-		raw_spin_lock_irqsave(&desc->lock, flags);
-		sync = suspend_device_irq(desc);
-		raw_spin_unlock_irqrestore(&desc->lock, flags);
+		scoped_guard(raw_spinlock_irqsave, &desc->lock)
+			sync = suspend_device_irq(desc);
 
 		if (sync)
 			synchronize_irq(irq);
@@ -186,18 +183,15 @@ static void resume_irqs(bool want_early)
 	int irq;
 
 	for_each_irq_desc(irq, desc) {
-		unsigned long flags;
-		bool is_early = desc->action &&
-			desc->action->flags & IRQF_EARLY_RESUME;
+		bool is_early = desc->action &&	desc->action->flags & IRQF_EARLY_RESUME;
 
 		if (!is_early && want_early)
 			continue;
 		if (irq_settings_is_nested_thread(desc))
 			continue;
 
-		raw_spin_lock_irqsave(&desc->lock, flags);
+		guard(raw_spinlock_irqsave)(&desc->lock);
 		resume_irq(desc);
-		raw_spin_unlock_irqrestore(&desc->lock, flags);
 	}
 }
 
@@ -207,22 +201,16 @@ static void resume_irqs(bool want_early)
  */
 void rearm_wake_irq(unsigned int irq)
 {
-	unsigned long flags;
-	struct irq_desc *desc = irq_get_desc_buslock(irq, &flags, IRQ_GET_DESC_CHECK_GLOBAL);
+	scoped_irqdesc_get_and_buslock(irq, IRQ_GET_DESC_CHECK_GLOBAL) {
+		struct irq_desc *desc = scoped_irqdesc;
 
-	if (!desc)
-		return;
-
-	if (!(desc->istate & IRQS_SUSPENDED) ||
-	    !irqd_is_wakeup_set(&desc->irq_data))
-		goto unlock;
-
-	desc->istate &= ~IRQS_SUSPENDED;
-	irqd_set(&desc->irq_data, IRQD_WAKEUP_ARMED);
-	__enable_irq(desc);
+		if (!(desc->istate & IRQS_SUSPENDED) || !irqd_is_wakeup_set(&desc->irq_data))
+			return;
 
-unlock:
-	irq_put_desc_busunlock(desc, flags);
+		desc->istate &= ~IRQS_SUSPENDED;
+		irqd_set(&desc->irq_data, IRQD_WAKEUP_ARMED);
+		__enable_irq(desc);
+	}
 }
 
 /**
diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c
index 8e29809de38d..29c2404e743b 100644
--- a/kernel/irq/proc.c
+++ b/kernel/irq/proc.c
@@ -81,20 +81,18 @@ static int show_irq_affinity(int type, struct seq_file *m)
 static int irq_affinity_hint_proc_show(struct seq_file *m, void *v)
 {
 	struct irq_desc *desc = irq_to_desc((long)m->private);
-	unsigned long flags;
 	cpumask_var_t mask;
 
 	if (!zalloc_cpumask_var(&mask, GFP_KERNEL))
 		return -ENOMEM;
 
-	raw_spin_lock_irqsave(&desc->lock, flags);
-	if (desc->affinity_hint)
-		cpumask_copy(mask, desc->affinity_hint);
-	raw_spin_unlock_irqrestore(&desc->lock, flags);
+	scoped_guard(raw_spinlock_irq, &desc->lock) {
+		if (desc->affinity_hint)
+			cpumask_copy(mask, desc->affinity_hint);
+	}
 
 	seq_printf(m, "%*pb\n", cpumask_pr_args(mask));
 	free_cpumask_var(mask);
-
 	return 0;
 }
 
@@ -295,32 +293,26 @@ static int irq_spurious_proc_show(struct seq_file *m, void *v)
 
 #define MAX_NAMELEN 128
 
-static int name_unique(unsigned int irq, struct irqaction *new_action)
+static bool name_unique(unsigned int irq, struct irqaction *new_action)
 {
 	struct irq_desc *desc = irq_to_desc(irq);
 	struct irqaction *action;
-	unsigned long flags;
-	int ret = 1;
 
-	raw_spin_lock_irqsave(&desc->lock, flags);
+	guard(raw_spinlock_irq)(&desc->lock);
 	for_each_action_of_desc(desc, action) {
 		if ((action != new_action) && action->name &&
-				!strcmp(new_action->name, action->name)) {
-			ret = 0;
-			break;
-		}
+		    !strcmp(new_action->name, action->name))
+			return false;
 	}
-	raw_spin_unlock_irqrestore(&desc->lock, flags);
-	return ret;
+	return true;
 }
 
 void register_handler_proc(unsigned int irq, struct irqaction *action)
 {
-	char name [MAX_NAMELEN];
+	char name[MAX_NAMELEN];
 	struct irq_desc *desc = irq_to_desc(irq);
 
-	if (!desc->dir || action->dir || !action->name ||
-					!name_unique(irq, action))
+	if (!desc->dir || action->dir || !action->name || !name_unique(irq, action))
 		return;
 
 	snprintf(name, MAX_NAMELEN, "%s", action->name);
@@ -347,17 +339,16 @@ void register_irq_proc(unsigned int irq, struct irq_desc *desc)
 	 * added, not when the descriptor is created, so multiple
 	 * tasks might try to register at the same time.
 	 */
-	mutex_lock(&register_lock);
+	guard(mutex)(&register_lock);
 
 	if (desc->dir)
-		goto out_unlock;
-
-	sprintf(name, "%d", irq);
+		return;
 
 	/* create /proc/irq/1234 */
+	sprintf(name, "%u", irq);
 	desc->dir = proc_mkdir(name, root_irq_dir);
 	if (!desc->dir)
-		goto out_unlock;
+		return;
 
 #ifdef CONFIG_SMP
 	umode_t umode = S_IRUGO;
@@ -366,31 +357,27 @@ void register_irq_proc(unsigned int irq, struct irq_desc *desc)
 		umode |= S_IWUSR;
 
 	/* create /proc/irq/<irq>/smp_affinity */
-	proc_create_data("smp_affinity", umode, desc->dir,
-			 &irq_affinity_proc_ops, irqp);
+	proc_create_data("smp_affinity", umode, desc->dir, &irq_affinity_proc_ops, irqp);
 
 	/* create /proc/irq/<irq>/affinity_hint */
 	proc_create_single_data("affinity_hint", 0444, desc->dir,
-			irq_affinity_hint_proc_show, irqp);
+				irq_affinity_hint_proc_show, irqp);
 
 	/* create /proc/irq/<irq>/smp_affinity_list */
 	proc_create_data("smp_affinity_list", umode, desc->dir,
 			 &irq_affinity_list_proc_ops, irqp);
 
-	proc_create_single_data("node", 0444, desc->dir, irq_node_proc_show,
-			irqp);
+	proc_create_single_data("node", 0444, desc->dir, irq_node_proc_show, irqp);
 # ifdef CONFIG_GENERIC_IRQ_EFFECTIVE_AFF_MASK
 	proc_create_single_data("effective_affinity", 0444, desc->dir,
-			irq_effective_aff_proc_show, irqp);
+				irq_effective_aff_proc_show, irqp);
 	proc_create_single_data("effective_affinity_list", 0444, desc->dir,
-			irq_effective_aff_list_proc_show, irqp);
+				irq_effective_aff_list_proc_show, irqp);
 # endif
 #endif
 	proc_create_single_data("spurious", 0444, desc->dir,
-			irq_spurious_proc_show, (void *)(long)irq);
+				irq_spurious_proc_show, (void *)(long)irq);
 
-out_unlock:
-	mutex_unlock(&register_lock);
 }
 
 void unregister_irq_proc(unsigned int irq, struct irq_desc *desc)
@@ -468,7 +455,6 @@ int show_interrupts(struct seq_file *p, void *v)
 	int i = *(loff_t *) v, j;
 	struct irqaction *action;
 	struct irq_desc *desc;
-	unsigned long flags;
 
 	if (i > ACTUAL_NR_IRQS)
 		return 0;
@@ -487,13 +473,13 @@ int show_interrupts(struct seq_file *p, void *v)
 		seq_putc(p, '\n');
 	}
 
-	rcu_read_lock();
+	guard(rcu)();
 	desc = irq_to_desc(i);
 	if (!desc || irq_settings_is_hidden(desc))
-		goto outsparse;
+		return 0;
 
 	if (!desc->action || irq_desc_is_chained(desc) || !desc->kstat_irqs)
-		goto outsparse;
+		return 0;
 
 	seq_printf(p, "%*d:", prec, i);
 	for_each_online_cpu(j) {
@@ -503,7 +489,7 @@ int show_interrupts(struct seq_file *p, void *v)
 	}
 	seq_putc(p, ' ');
 
-	raw_spin_lock_irqsave(&desc->lock, flags);
+	guard(raw_spinlock_irq)(&desc->lock);
 	if (desc->irq_data.chip) {
 		if (desc->irq_data.chip->irq_print_chip)
 			desc->irq_data.chip->irq_print_chip(&desc->irq_data, p);
@@ -532,9 +518,6 @@ int show_interrupts(struct seq_file *p, void *v)
 	}
 
 	seq_putc(p, '\n');
-	raw_spin_unlock_irqrestore(&desc->lock, flags);
-outsparse:
-	rcu_read_unlock();
 	return 0;
 }
 #endif
diff --git a/kernel/irq/resend.c b/kernel/irq/resend.c
index 1b7fa72968bd..ca9cc1b806a9 100644
--- a/kernel/irq/resend.c
+++ b/kernel/irq/resend.c
@@ -30,18 +30,17 @@ static DEFINE_RAW_SPINLOCK(irq_resend_lock);
  */
 static void resend_irqs(struct tasklet_struct *unused)
 {
-	struct irq_desc *desc;
-
-	raw_spin_lock_irq(&irq_resend_lock);
+	guard(raw_spinlock_irq)(&irq_resend_lock);
 	while (!hlist_empty(&irq_resend_list)) {
-		desc = hlist_entry(irq_resend_list.first, struct irq_desc,
-				   resend_node);
+		struct irq_desc *desc;
+
+		desc = hlist_entry(irq_resend_list.first, struct irq_desc,  resend_node);
 		hlist_del_init(&desc->resend_node);
+
 		raw_spin_unlock(&irq_resend_lock);
 		desc->handle_irq(desc);
 		raw_spin_lock(&irq_resend_lock);
 	}
-	raw_spin_unlock_irq(&irq_resend_lock);
 }
 
 /* Tasklet to handle resend: */
@@ -75,19 +74,18 @@ static int irq_sw_resend(struct irq_desc *desc)
 	}
 
 	/* Add to resend_list and activate the softirq: */
-	raw_spin_lock(&irq_resend_lock);
-	if (hlist_unhashed(&desc->resend_node))
-		hlist_add_head(&desc->resend_node, &irq_resend_list);
-	raw_spin_unlock(&irq_resend_lock);
+	scoped_guard(raw_spinlock, &irq_resend_lock) {
+		if (hlist_unhashed(&desc->resend_node))
+			hlist_add_head(&desc->resend_node, &irq_resend_list);
+	}
 	tasklet_schedule(&resend_tasklet);
 	return 0;
 }
 
 void clear_irq_resend(struct irq_desc *desc)
 {
-	raw_spin_lock(&irq_resend_lock);
+	guard(raw_spinlock)(&irq_resend_lock);
 	hlist_del_init(&desc->resend_node);
-	raw_spin_unlock(&irq_resend_lock);
 }
 
 void irq_resend_init(struct irq_desc *desc)
@@ -172,30 +170,24 @@ int check_irq_resend(struct irq_desc *desc, bool inject)
  */
 int irq_inject_interrupt(unsigned int irq)
 {
-	struct irq_desc *desc;
-	unsigned long flags;
-	int err;
+	int err = -EINVAL;
 
 	/* Try the state injection hardware interface first */
 	if (!irq_set_irqchip_state(irq, IRQCHIP_STATE_PENDING, true))
 		return 0;
 
 	/* That failed, try via the resend mechanism */
-	desc = irq_get_desc_buslock(irq, &flags, 0);
-	if (!desc)
-		return -EINVAL;
+	scoped_irqdesc_get_and_buslock(irq, 0) {
+		struct irq_desc *desc = scoped_irqdesc;
 
-	/*
-	 * Only try to inject when the interrupt is:
-	 *  - not NMI type
-	 *  - activated
-	 */
-	if (irq_is_nmi(desc) || !irqd_is_activated(&desc->irq_data))
-		err = -EINVAL;
-	else
-		err = check_irq_resend(desc, true);
-
-	irq_put_desc_busunlock(desc, flags);
+		/*
+		 * Only try to inject when the interrupt is:
+		 *  - not NMI type
+		 *  - activated
+		 */
+		if (!irq_is_nmi(desc) && irqd_is_activated(&desc->irq_data))
+			err = check_irq_resend(desc, true);
+	}
 	return err;
 }
 EXPORT_SYMBOL_GPL(irq_inject_interrupt);
diff --git a/kernel/irq/spurious.c b/kernel/irq/spurious.c
index 02b2daf07441..8f26982e7300 100644
--- a/kernel/irq/spurious.c
+++ b/kernel/irq/spurious.c
@@ -34,8 +34,9 @@ static atomic_t irq_poll_active;
  * true and let the handler run.
  */
 bool irq_wait_for_poll(struct irq_desc *desc)
-	__must_hold(&desc->lock)
 {
+	lockdep_assert_held(&desc->lock);
+
 	if (WARN_ONCE(irq_poll_cpu == smp_processor_id(),
 		      "irq poll in progress on cpu %d for irq %d\n",
 		      smp_processor_id(), desc->irq_data.irq))
@@ -59,37 +60,35 @@ bool irq_wait_for_poll(struct irq_desc *desc)
 /*
  * Recovery handler for misrouted interrupts.
  */
-static int try_one_irq(struct irq_desc *desc, bool force)
+static bool try_one_irq(struct irq_desc *desc, bool force)
 {
-	irqreturn_t ret = IRQ_NONE;
 	struct irqaction *action;
+	bool ret = false;
 
-	raw_spin_lock(&desc->lock);
+	guard(raw_spinlock)(&desc->lock);
 
 	/*
 	 * PER_CPU, nested thread interrupts and interrupts explicitly
 	 * marked polled are excluded from polling.
 	 */
-	if (irq_settings_is_per_cpu(desc) ||
-	    irq_settings_is_nested_thread(desc) ||
+	if (irq_settings_is_per_cpu(desc) || irq_settings_is_nested_thread(desc) ||
 	    irq_settings_is_polled(desc))
-		goto out;
+		return false;
 
 	/*
 	 * Do not poll disabled interrupts unless the spurious
 	 * disabled poller asks explicitly.
 	 */
 	if (irqd_irq_disabled(&desc->irq_data) && !force)
-		goto out;
+		return false;
 
 	/*
 	 * All handlers must agree on IRQF_SHARED, so we test just the
 	 * first.
 	 */
 	action = desc->action;
-	if (!action || !(action->flags & IRQF_SHARED) ||
-	    (action->flags & __IRQF_TIMER))
-		goto out;
+	if (!action || !(action->flags & IRQF_SHARED) || (action->flags & __IRQF_TIMER))
+		return false;
 
 	/* Already running on another processor */
 	if (irqd_irq_inprogress(&desc->irq_data)) {
@@ -98,21 +97,19 @@ static int try_one_irq(struct irq_desc *desc, bool force)
 		 * CPU to go looking for our mystery interrupt too
 		 */
 		desc->istate |= IRQS_PENDING;
-		goto out;
+		return false;
 	}
 
 	/* Mark it poll in progress */
 	desc->istate |= IRQS_POLL_INPROGRESS;
 	do {
 		if (handle_irq_event(desc) == IRQ_HANDLED)
-			ret = IRQ_HANDLED;
+			ret = true;
 		/* Make sure that there is still a valid action */
 		action = desc->action;
 	} while ((desc->istate & IRQS_PENDING) && action);
 	desc->istate &= ~IRQS_POLL_INPROGRESS;
-out:
-	raw_spin_unlock(&desc->lock);
-	return ret == IRQ_HANDLED;
+	return ret;
 }
 
 static int misrouted_irq(int irq)
@@ -157,8 +154,7 @@ static void poll_spurious_irqs(struct timer_list *unused)
 			 continue;
 
 		/* Racy but it doesn't matter */
-		state = desc->istate;
-		barrier();
+		state = READ_ONCE(desc->istate);
 		if (!(state & IRQS_SPURIOUS_DISABLED))
 			continue;
 
@@ -168,8 +164,7 @@ static void poll_spurious_irqs(struct timer_list *unused)
 	}
 out:
 	atomic_dec(&irq_poll_active);
-	mod_timer(&poll_spurious_irq_timer,
-		  jiffies + POLL_SPURIOUS_IRQ_INTERVAL);
+	mod_timer(&poll_spurious_irq_timer, jiffies + POLL_SPURIOUS_IRQ_INTERVAL);
 }
 
 static inline int bad_action_ret(irqreturn_t action_ret)
@@ -193,17 +188,13 @@ static void __report_bad_irq(struct irq_desc *desc, irqreturn_t action_ret)
 {
 	unsigned int irq = irq_desc_get_irq(desc);
 	struct irqaction *action;
-	unsigned long flags;
 
-	if (bad_action_ret(action_ret)) {
-		printk(KERN_ERR "irq event %d: bogus return value %x\n",
-				irq, action_ret);
-	} else {
-		printk(KERN_ERR "irq %d: nobody cared (try booting with "
-				"the \"irqpoll\" option)\n", irq);
-	}
+	if (bad_action_ret(action_ret))
+		pr_err("irq event %d: bogus return value %x\n", irq, action_ret);
+	else
+		pr_err("irq %d: nobody cared (try booting with the \"irqpoll\" option)\n", irq);
 	dump_stack();
-	printk(KERN_ERR "handlers:\n");
+	pr_err("handlers:\n");
 
 	/*
 	 * We need to take desc->lock here. note_interrupt() is called
@@ -211,15 +202,13 @@ static void __report_bad_irq(struct irq_desc *desc, irqreturn_t action_ret)
 	 * with something else removing an action. It's ok to take
 	 * desc->lock here. See synchronize_irq().
 	 */
-	raw_spin_lock_irqsave(&desc->lock, flags);
+	guard(raw_spinlock_irqsave)(&desc->lock);
 	for_each_action_of_desc(desc, action) {
-		printk(KERN_ERR "[<%p>] %ps", action->handler, action->handler);
+		pr_err("[<%p>] %ps", action->handler, action->handler);
 		if (action->thread_fn)
-			printk(KERN_CONT " threaded [<%p>] %ps",
-					action->thread_fn, action->thread_fn);
-		printk(KERN_CONT "\n");
+			pr_cont(" threaded [<%p>] %ps", action->thread_fn, action->thread_fn);
+		pr_cont("\n");
 	}
-	raw_spin_unlock_irqrestore(&desc->lock, flags);
 }
 
 static void report_bad_irq(struct irq_desc *desc, irqreturn_t action_ret)
@@ -232,18 +221,17 @@ static void report_bad_irq(struct irq_desc *desc, irqreturn_t action_ret)
 	}
 }
 
-static inline int
-try_misrouted_irq(unsigned int irq, struct irq_desc *desc,
-		  irqreturn_t action_ret)
+static inline bool try_misrouted_irq(unsigned int irq, struct irq_desc *desc,
+				     irqreturn_t action_ret)
 {
 	struct irqaction *action;
 
 	if (!irqfixup)
-		return 0;
+		return false;
 
 	/* We didn't actually handle the IRQ - see if it was misrouted? */
 	if (action_ret == IRQ_NONE)
-		return 1;
+		return true;
 
 	/*
 	 * But for 'irqfixup == 2' we also do it for handled interrupts if
@@ -251,19 +239,16 @@ try_misrouted_irq(unsigned int irq, struct irq_desc *desc,
 	 * traditional PC timer interrupt.. Legacy)
 	 */
 	if (irqfixup < 2)
-		return 0;
+		return false;
 
 	if (!irq)
-		return 1;
+		return true;
 
 	/*
 	 * Since we don't get the descriptor lock, "action" can
-	 * change under us.  We don't really care, but we don't
-	 * want to follow a NULL pointer. So tell the compiler to
-	 * just load it once by using a barrier.
+	 * change under us.
 	 */
-	action = desc->action;
-	barrier();
+	action = READ_ONCE(desc->action);
 	return action && (action->flags & IRQF_IRQPOLL);
 }
 
@@ -273,8 +258,7 @@ void note_interrupt(struct irq_desc *desc, irqreturn_t action_ret)
 {
 	unsigned int irq;
 
-	if (desc->istate & IRQS_POLL_INPROGRESS ||
-	    irq_settings_is_polled(desc))
+	if (desc->istate & IRQS_POLL_INPROGRESS || irq_settings_is_polled(desc))
 		return;
 
 	if (bad_action_ret(action_ret)) {
@@ -420,13 +404,12 @@ void note_interrupt(struct irq_desc *desc, irqreturn_t action_ret)
 		/*
 		 * Now kill the IRQ
 		 */
-		printk(KERN_EMERG "Disabling IRQ #%d\n", irq);
+		pr_emerg("Disabling IRQ #%d\n", irq);
 		desc->istate |= IRQS_SPURIOUS_DISABLED;
 		desc->depth++;
 		irq_disable(desc);
 
-		mod_timer(&poll_spurious_irq_timer,
-			  jiffies + POLL_SPURIOUS_IRQ_INTERVAL);
+		mod_timer(&poll_spurious_irq_timer, jiffies + POLL_SPURIOUS_IRQ_INTERVAL);
 	}
 	desc->irqs_unhandled = 0;
 }
@@ -436,11 +419,9 @@ bool noirqdebug __read_mostly;
 int noirqdebug_setup(char *str)
 {
 	noirqdebug = 1;
-	printk(KERN_INFO "IRQ lockup detection disabled\n");
-
+	pr_info("IRQ lockup detection disabled\n");
 	return 1;
 }
-
 __setup("noirqdebug", noirqdebug_setup);
 module_param(noirqdebug, bool, 0644);
 MODULE_PARM_DESC(noirqdebug, "Disable irq lockup detection when true");
@@ -452,12 +433,10 @@ static int __init irqfixup_setup(char *str)
 		return 1;
 	}
 	irqfixup = 1;
-	printk(KERN_WARNING "Misrouted IRQ fixup support enabled.\n");
-	printk(KERN_WARNING "This may impact system performance.\n");
-
+	pr_warn("Misrouted IRQ fixup support enabled.\n");
+	pr_warn("This may impact system performance.\n");
 	return 1;
 }
-
 __setup("irqfixup", irqfixup_setup);
 module_param(irqfixup, int, 0644);
 
@@ -468,11 +447,8 @@ static int __init irqpoll_setup(char *str)
 		return 1;
 	}
 	irqfixup = 2;
-	printk(KERN_WARNING "Misrouted IRQ fixup and polling support "
-				"enabled\n");
-	printk(KERN_WARNING "This may significantly impact system "
-				"performance\n");
+	pr_warn("Misrouted IRQ fixup and polling support enabled\n");
+	pr_warn("This may significantly impact system performance\n");
 	return 1;
 }
-
 __setup("irqpoll", irqpoll_setup);
diff --git a/kernel/kcsan/kcsan_test.c b/kernel/kcsan/kcsan_test.c
index 6ce73cceaf53..c2871180edcc 100644
--- a/kernel/kcsan/kcsan_test.c
+++ b/kernel/kcsan/kcsan_test.c
@@ -1501,7 +1501,7 @@ static int access_thread(void *arg)
 		}
 	} while (!torture_must_stop());
 	timer_delete_sync(&timer);
-	destroy_timer_on_stack(&timer);
+	timer_destroy_on_stack(&timer);
 
 	torture_kthread_stopping("access_thread");
 	return 0;
diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c
index 3e62b944c883..9c59fa480b0b 100644
--- a/kernel/kexec_core.c
+++ b/kernel/kexec_core.c
@@ -877,6 +877,60 @@ int kimage_load_segment(struct kimage *image,
 	return result;
 }
 
+void *kimage_map_segment(struct kimage *image,
+			 unsigned long addr, unsigned long size)
+{
+	unsigned long src_page_addr, dest_page_addr = 0;
+	unsigned long eaddr = addr + size;
+	kimage_entry_t *ptr, entry;
+	struct page **src_pages;
+	unsigned int npages;
+	void *vaddr = NULL;
+	int i;
+
+	/*
+	 * Collect the source pages and map them in a contiguous VA range.
+	 */
+	npages = PFN_UP(eaddr) - PFN_DOWN(addr);
+	src_pages = kmalloc_array(npages, sizeof(*src_pages), GFP_KERNEL);
+	if (!src_pages) {
+		pr_err("Could not allocate ima pages array.\n");
+		return NULL;
+	}
+
+	i = 0;
+	for_each_kimage_entry(image, ptr, entry) {
+		if (entry & IND_DESTINATION) {
+			dest_page_addr = entry & PAGE_MASK;
+		} else if (entry & IND_SOURCE) {
+			if (dest_page_addr >= addr && dest_page_addr < eaddr) {
+				src_page_addr = entry & PAGE_MASK;
+				src_pages[i++] =
+					virt_to_page(__va(src_page_addr));
+				if (i == npages)
+					break;
+				dest_page_addr += PAGE_SIZE;
+			}
+		}
+	}
+
+	/* Sanity check. */
+	WARN_ON(i < npages);
+
+	vaddr = vmap(src_pages, npages, VM_MAP, PAGE_KERNEL);
+	kfree(src_pages);
+
+	if (!vaddr)
+		pr_err("Could not map ima buffer.\n");
+
+	return vaddr;
+}
+
+void kimage_unmap_segment(void *segment_buffer)
+{
+	vunmap(segment_buffer);
+}
+
 struct kexec_load_limit {
 	/* Mutex protects the limit count. */
 	struct mutex mutex;
diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c
index fba686487e3b..69fe76fd9233 100644
--- a/kernel/kexec_file.c
+++ b/kernel/kexec_file.c
@@ -19,7 +19,6 @@
 #include <linux/list.h>
 #include <linux/fs.h>
 #include <linux/ima.h>
-#include <crypto/hash.h>
 #include <crypto/sha2.h>
 #include <linux/elf.h>
 #include <linux/elfcore.h>
@@ -38,6 +37,21 @@ void set_kexec_sig_enforced(void)
 }
 #endif
 
+#ifdef CONFIG_IMA_KEXEC
+static bool check_ima_segment_index(struct kimage *image, int i)
+{
+	if (image->is_ima_segment_index_set && i == image->ima_segment_index)
+		return true;
+	else
+		return false;
+}
+#else
+static bool check_ima_segment_index(struct kimage *image, int i)
+{
+	return false;
+}
+#endif
+
 static int kexec_calculate_store_digests(struct kimage *image);
 
 /* Maximum size in bytes for kernel/initrd files. */
@@ -186,6 +200,15 @@ kimage_validate_signature(struct kimage *image)
 }
 #endif
 
+static int kexec_post_load(struct kimage *image, unsigned long flags)
+{
+#ifdef CONFIG_IMA_KEXEC
+	if (!(flags & KEXEC_FILE_ON_CRASH))
+		ima_kexec_post_load(image);
+#endif
+	return machine_kexec_post_load(image);
+}
+
 /*
  * In file mode list of segments is prepared by kernel. Copy relevant
  * data from user space, do error checking, prepare segment list
@@ -253,6 +276,11 @@ kimage_file_prepare_segments(struct kimage *image, int kernel_fd, int initrd_fd,
 	/* IMA needs to pass the measurement list to the next kernel. */
 	ima_add_kexec_buffer(image);
 
+	/* If KHO is active, add its images to the list */
+	ret = kho_fill_kimage(image);
+	if (ret)
+		goto out;
+
 	/* Call image load handler */
 	ldata = kexec_image_load_default(image);
 
@@ -413,7 +441,7 @@ SYSCALL_DEFINE5(kexec_file_load, int, kernel_fd, int, initrd_fd,
 
 	kimage_terminate(image);
 
-	ret = machine_kexec_post_load(image);
+	ret = kexec_post_load(image, flags);
 	if (ret)
 		goto out;
 
@@ -445,6 +473,7 @@ static int locate_mem_hole_top_down(unsigned long start, unsigned long end,
 
 	temp_end = min(end, kbuf->buf_max);
 	temp_start = temp_end - kbuf->memsz + 1;
+	kexec_random_range_start(temp_start, temp_end, kbuf, &temp_start);
 
 	do {
 		/* align down start */
@@ -489,6 +518,8 @@ static int locate_mem_hole_bottom_up(unsigned long start, unsigned long end,
 
 	temp_start = max(start, kbuf->buf_min);
 
+	kexec_random_range_start(temp_start, end, kbuf, &temp_start);
+
 	do {
 		temp_start = ALIGN(temp_start, kbuf->buf_align);
 		temp_end = temp_start + kbuf->memsz - 1;
@@ -648,6 +679,14 @@ int kexec_locate_mem_hole(struct kexec_buf *kbuf)
 	if (kbuf->mem != KEXEC_BUF_MEM_UNKNOWN)
 		return 0;
 
+	/*
+	 * If KHO is active, only use KHO scratch memory. All other memory
+	 * could potentially be handed over.
+	 */
+	ret = kho_locate_mem_hole(kbuf, locate_mem_hole_callback);
+	if (ret <= 0)
+		return ret;
+
 	if (!IS_ENABLED(CONFIG_ARCH_KEEP_MEMBLOCK))
 		ret = kexec_walk_resources(kbuf, locate_mem_hole_callback);
 	else
@@ -712,11 +751,10 @@ int kexec_add_buffer(struct kexec_buf *kbuf)
 /* Calculate and store the digest of segments */
 static int kexec_calculate_store_digests(struct kimage *image)
 {
-	struct crypto_shash *tfm;
-	struct shash_desc *desc;
+	struct sha256_state state;
 	int ret = 0, i, j, zero_buf_sz, sha_region_sz;
-	size_t desc_size, nullsz;
-	char *digest;
+	size_t nullsz;
+	u8 digest[SHA256_DIGEST_SIZE];
 	void *zero_buf;
 	struct kexec_sha_region *sha_regions;
 	struct purgatory_info *pi = &image->purgatory_info;
@@ -727,37 +765,12 @@ static int kexec_calculate_store_digests(struct kimage *image)
 	zero_buf = __va(page_to_pfn(ZERO_PAGE(0)) << PAGE_SHIFT);
 	zero_buf_sz = PAGE_SIZE;
 
-	tfm = crypto_alloc_shash("sha256", 0, 0);
-	if (IS_ERR(tfm)) {
-		ret = PTR_ERR(tfm);
-		goto out;
-	}
-
-	desc_size = crypto_shash_descsize(tfm) + sizeof(*desc);
-	desc = kzalloc(desc_size, GFP_KERNEL);
-	if (!desc) {
-		ret = -ENOMEM;
-		goto out_free_tfm;
-	}
-
 	sha_region_sz = KEXEC_SEGMENT_MAX * sizeof(struct kexec_sha_region);
 	sha_regions = vzalloc(sha_region_sz);
-	if (!sha_regions) {
-		ret = -ENOMEM;
-		goto out_free_desc;
-	}
+	if (!sha_regions)
+		return -ENOMEM;
 
-	desc->tfm   = tfm;
-
-	ret = crypto_shash_init(desc);
-	if (ret < 0)
-		goto out_free_sha_regions;
-
-	digest = kzalloc(SHA256_DIGEST_SIZE, GFP_KERNEL);
-	if (!digest) {
-		ret = -ENOMEM;
-		goto out_free_sha_regions;
-	}
+	sha256_init(&state);
 
 	for (j = i = 0; i < image->nr_segments; i++) {
 		struct kexec_segment *ksegment;
@@ -776,10 +789,14 @@ static int kexec_calculate_store_digests(struct kimage *image)
 		if (ksegment->kbuf == pi->purgatory_buf)
 			continue;
 
-		ret = crypto_shash_update(desc, ksegment->kbuf,
-					  ksegment->bufsz);
-		if (ret)
-			break;
+		/*
+		 * Skip the segment if ima_segment_index is set and matches
+		 * the current index
+		 */
+		if (check_ima_segment_index(image, i))
+			continue;
+
+		sha256_update(&state, ksegment->kbuf, ksegment->bufsz);
 
 		/*
 		 * Assume rest of the buffer is filled with zero and
@@ -791,44 +808,26 @@ static int kexec_calculate_store_digests(struct kimage *image)
 
 			if (bytes > zero_buf_sz)
 				bytes = zero_buf_sz;
-			ret = crypto_shash_update(desc, zero_buf, bytes);
-			if (ret)
-				break;
+			sha256_update(&state, zero_buf, bytes);
 			nullsz -= bytes;
 		}
 
-		if (ret)
-			break;
-
 		sha_regions[j].start = ksegment->mem;
 		sha_regions[j].len = ksegment->memsz;
 		j++;
 	}
 
-	if (!ret) {
-		ret = crypto_shash_final(desc, digest);
-		if (ret)
-			goto out_free_digest;
-		ret = kexec_purgatory_get_set_symbol(image, "purgatory_sha_regions",
-						     sha_regions, sha_region_sz, 0);
-		if (ret)
-			goto out_free_digest;
+	sha256_final(&state, digest);
 
-		ret = kexec_purgatory_get_set_symbol(image, "purgatory_sha256_digest",
-						     digest, SHA256_DIGEST_SIZE, 0);
-		if (ret)
-			goto out_free_digest;
-	}
+	ret = kexec_purgatory_get_set_symbol(image, "purgatory_sha_regions",
+					     sha_regions, sha_region_sz, 0);
+	if (ret)
+		goto out_free_sha_regions;
 
-out_free_digest:
-	kfree(digest);
+	ret = kexec_purgatory_get_set_symbol(image, "purgatory_sha256_digest",
+					     digest, SHA256_DIGEST_SIZE, 0);
 out_free_sha_regions:
 	vfree(sha_regions);
-out_free_desc:
-	kfree(desc);
-out_free_tfm:
-	kfree(tfm);
-out:
 	return ret;
 }
 
diff --git a/kernel/kexec_handover.c b/kernel/kexec_handover.c
new file mode 100644
index 000000000000..69b953551677
--- /dev/null
+++ b/kernel/kexec_handover.c
@@ -0,0 +1,1266 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * kexec_handover.c - kexec handover metadata processing
+ * Copyright (C) 2023 Alexander Graf <graf@amazon.com>
+ * Copyright (C) 2025 Microsoft Corporation, Mike Rapoport <rppt@kernel.org>
+ * Copyright (C) 2025 Google LLC, Changyuan Lyu <changyuanl@google.com>
+ */
+
+#define pr_fmt(fmt) "KHO: " fmt
+
+#include <linux/cma.h>
+#include <linux/count_zeros.h>
+#include <linux/debugfs.h>
+#include <linux/kexec.h>
+#include <linux/kexec_handover.h>
+#include <linux/libfdt.h>
+#include <linux/list.h>
+#include <linux/memblock.h>
+#include <linux/notifier.h>
+#include <linux/page-isolation.h>
+
+#include <asm/early_ioremap.h>
+
+/*
+ * KHO is tightly coupled with mm init and needs access to some of mm
+ * internal APIs.
+ */
+#include "../mm/internal.h"
+#include "kexec_internal.h"
+
+#define KHO_FDT_COMPATIBLE "kho-v1"
+#define PROP_PRESERVED_MEMORY_MAP "preserved-memory-map"
+#define PROP_SUB_FDT "fdt"
+
+static bool kho_enable __ro_after_init;
+
+bool kho_is_enabled(void)
+{
+	return kho_enable;
+}
+EXPORT_SYMBOL_GPL(kho_is_enabled);
+
+static int __init kho_parse_enable(char *p)
+{
+	return kstrtobool(p, &kho_enable);
+}
+early_param("kho", kho_parse_enable);
+
+/*
+ * Keep track of memory that is to be preserved across KHO.
+ *
+ * The serializing side uses two levels of xarrays to manage chunks of per-order
+ * 512 byte bitmaps. For instance if PAGE_SIZE = 4096, the entire 1G order of a
+ * 1TB system would fit inside a single 512 byte bitmap. For order 0 allocations
+ * each bitmap will cover 16M of address space. Thus, for 16G of memory at most
+ * 512K of bitmap memory will be needed for order 0.
+ *
+ * This approach is fully incremental, as the serialization progresses folios
+ * can continue be aggregated to the tracker. The final step, immediately prior
+ * to kexec would serialize the xarray information into a linked list for the
+ * successor kernel to parse.
+ */
+
+#define PRESERVE_BITS (512 * 8)
+
+struct kho_mem_phys_bits {
+	DECLARE_BITMAP(preserve, PRESERVE_BITS);
+};
+
+struct kho_mem_phys {
+	/*
+	 * Points to kho_mem_phys_bits, a sparse bitmap array. Each bit is sized
+	 * to order.
+	 */
+	struct xarray phys_bits;
+};
+
+struct kho_mem_track {
+	/* Points to kho_mem_phys, each order gets its own bitmap tree */
+	struct xarray orders;
+};
+
+struct khoser_mem_chunk;
+
+struct kho_serialization {
+	struct page *fdt;
+	struct list_head fdt_list;
+	struct dentry *sub_fdt_dir;
+	struct kho_mem_track track;
+	/* First chunk of serialized preserved memory map */
+	struct khoser_mem_chunk *preserved_mem_map;
+};
+
+static void *xa_load_or_alloc(struct xarray *xa, unsigned long index, size_t sz)
+{
+	void *elm, *res;
+
+	elm = xa_load(xa, index);
+	if (elm)
+		return elm;
+
+	elm = kzalloc(sz, GFP_KERNEL);
+	if (!elm)
+		return ERR_PTR(-ENOMEM);
+
+	res = xa_cmpxchg(xa, index, NULL, elm, GFP_KERNEL);
+	if (xa_is_err(res))
+		res = ERR_PTR(xa_err(res));
+
+	if (res) {
+		kfree(elm);
+		return res;
+	}
+
+	return elm;
+}
+
+static void __kho_unpreserve(struct kho_mem_track *track, unsigned long pfn,
+			     unsigned long end_pfn)
+{
+	struct kho_mem_phys_bits *bits;
+	struct kho_mem_phys *physxa;
+
+	while (pfn < end_pfn) {
+		const unsigned int order =
+			min(count_trailing_zeros(pfn), ilog2(end_pfn - pfn));
+		const unsigned long pfn_high = pfn >> order;
+
+		physxa = xa_load(&track->orders, order);
+		if (!physxa)
+			continue;
+
+		bits = xa_load(&physxa->phys_bits, pfn_high / PRESERVE_BITS);
+		if (!bits)
+			continue;
+
+		clear_bit(pfn_high % PRESERVE_BITS, bits->preserve);
+
+		pfn += 1 << order;
+	}
+}
+
+static int __kho_preserve_order(struct kho_mem_track *track, unsigned long pfn,
+				unsigned int order)
+{
+	struct kho_mem_phys_bits *bits;
+	struct kho_mem_phys *physxa;
+	const unsigned long pfn_high = pfn >> order;
+
+	might_sleep();
+
+	physxa = xa_load_or_alloc(&track->orders, order, sizeof(*physxa));
+	if (IS_ERR(physxa))
+		return PTR_ERR(physxa);
+
+	bits = xa_load_or_alloc(&physxa->phys_bits, pfn_high / PRESERVE_BITS,
+				sizeof(*bits));
+	if (IS_ERR(bits))
+		return PTR_ERR(bits);
+
+	set_bit(pfn_high % PRESERVE_BITS, bits->preserve);
+
+	return 0;
+}
+
+/* almost as free_reserved_page(), just don't free the page */
+static void kho_restore_page(struct page *page)
+{
+	ClearPageReserved(page);
+	init_page_count(page);
+	adjust_managed_page_count(page, 1);
+}
+
+/**
+ * kho_restore_folio - recreates the folio from the preserved memory.
+ * @phys: physical address of the folio.
+ *
+ * Return: pointer to the struct folio on success, NULL on failure.
+ */
+struct folio *kho_restore_folio(phys_addr_t phys)
+{
+	struct page *page = pfn_to_online_page(PHYS_PFN(phys));
+	unsigned long order;
+
+	if (!page)
+		return NULL;
+
+	order = page->private;
+	if (order) {
+		if (order > MAX_PAGE_ORDER)
+			return NULL;
+
+		prep_compound_page(page, order);
+	} else {
+		kho_restore_page(page);
+	}
+
+	return page_folio(page);
+}
+EXPORT_SYMBOL_GPL(kho_restore_folio);
+
+/* Serialize and deserialize struct kho_mem_phys across kexec
+ *
+ * Record all the bitmaps in a linked list of pages for the next kernel to
+ * process. Each chunk holds bitmaps of the same order and each block of bitmaps
+ * starts at a given physical address. This allows the bitmaps to be sparse. The
+ * xarray is used to store them in a tree while building up the data structure,
+ * but the KHO successor kernel only needs to process them once in order.
+ *
+ * All of this memory is normal kmalloc() memory and is not marked for
+ * preservation. The successor kernel will remain isolated to the scratch space
+ * until it completes processing this list. Once processed all the memory
+ * storing these ranges will be marked as free.
+ */
+
+struct khoser_mem_bitmap_ptr {
+	phys_addr_t phys_start;
+	DECLARE_KHOSER_PTR(bitmap, struct kho_mem_phys_bits *);
+};
+
+struct khoser_mem_chunk_hdr {
+	DECLARE_KHOSER_PTR(next, struct khoser_mem_chunk *);
+	unsigned int order;
+	unsigned int num_elms;
+};
+
+#define KHOSER_BITMAP_SIZE                                   \
+	((PAGE_SIZE - sizeof(struct khoser_mem_chunk_hdr)) / \
+	 sizeof(struct khoser_mem_bitmap_ptr))
+
+struct khoser_mem_chunk {
+	struct khoser_mem_chunk_hdr hdr;
+	struct khoser_mem_bitmap_ptr bitmaps[KHOSER_BITMAP_SIZE];
+};
+
+static_assert(sizeof(struct khoser_mem_chunk) == PAGE_SIZE);
+
+static struct khoser_mem_chunk *new_chunk(struct khoser_mem_chunk *cur_chunk,
+					  unsigned long order)
+{
+	struct khoser_mem_chunk *chunk;
+
+	chunk = kzalloc(PAGE_SIZE, GFP_KERNEL);
+	if (!chunk)
+		return NULL;
+	chunk->hdr.order = order;
+	if (cur_chunk)
+		KHOSER_STORE_PTR(cur_chunk->hdr.next, chunk);
+	return chunk;
+}
+
+static void kho_mem_ser_free(struct khoser_mem_chunk *first_chunk)
+{
+	struct khoser_mem_chunk *chunk = first_chunk;
+
+	while (chunk) {
+		struct khoser_mem_chunk *tmp = chunk;
+
+		chunk = KHOSER_LOAD_PTR(chunk->hdr.next);
+		kfree(tmp);
+	}
+}
+
+static int kho_mem_serialize(struct kho_serialization *ser)
+{
+	struct khoser_mem_chunk *first_chunk = NULL;
+	struct khoser_mem_chunk *chunk = NULL;
+	struct kho_mem_phys *physxa;
+	unsigned long order;
+
+	xa_for_each(&ser->track.orders, order, physxa) {
+		struct kho_mem_phys_bits *bits;
+		unsigned long phys;
+
+		chunk = new_chunk(chunk, order);
+		if (!chunk)
+			goto err_free;
+
+		if (!first_chunk)
+			first_chunk = chunk;
+
+		xa_for_each(&physxa->phys_bits, phys, bits) {
+			struct khoser_mem_bitmap_ptr *elm;
+
+			if (chunk->hdr.num_elms == ARRAY_SIZE(chunk->bitmaps)) {
+				chunk = new_chunk(chunk, order);
+				if (!chunk)
+					goto err_free;
+			}
+
+			elm = &chunk->bitmaps[chunk->hdr.num_elms];
+			chunk->hdr.num_elms++;
+			elm->phys_start = (phys * PRESERVE_BITS)
+					  << (order + PAGE_SHIFT);
+			KHOSER_STORE_PTR(elm->bitmap, bits);
+		}
+	}
+
+	ser->preserved_mem_map = first_chunk;
+
+	return 0;
+
+err_free:
+	kho_mem_ser_free(first_chunk);
+	return -ENOMEM;
+}
+
+static void deserialize_bitmap(unsigned int order,
+			       struct khoser_mem_bitmap_ptr *elm)
+{
+	struct kho_mem_phys_bits *bitmap = KHOSER_LOAD_PTR(elm->bitmap);
+	unsigned long bit;
+
+	for_each_set_bit(bit, bitmap->preserve, PRESERVE_BITS) {
+		int sz = 1 << (order + PAGE_SHIFT);
+		phys_addr_t phys =
+			elm->phys_start + (bit << (order + PAGE_SHIFT));
+		struct page *page = phys_to_page(phys);
+
+		memblock_reserve(phys, sz);
+		memblock_reserved_mark_noinit(phys, sz);
+		page->private = order;
+	}
+}
+
+static void __init kho_mem_deserialize(const void *fdt)
+{
+	struct khoser_mem_chunk *chunk;
+	const phys_addr_t *mem;
+	int len;
+
+	mem = fdt_getprop(fdt, 0, PROP_PRESERVED_MEMORY_MAP, &len);
+
+	if (!mem || len != sizeof(*mem)) {
+		pr_err("failed to get preserved memory bitmaps\n");
+		return;
+	}
+
+	chunk = *mem ? phys_to_virt(*mem) : NULL;
+	while (chunk) {
+		unsigned int i;
+
+		for (i = 0; i != chunk->hdr.num_elms; i++)
+			deserialize_bitmap(chunk->hdr.order,
+					   &chunk->bitmaps[i]);
+		chunk = KHOSER_LOAD_PTR(chunk->hdr.next);
+	}
+}
+
+/*
+ * With KHO enabled, memory can become fragmented because KHO regions may
+ * be anywhere in physical address space. The scratch regions give us a
+ * safe zones that we will never see KHO allocations from. This is where we
+ * can later safely load our new kexec images into and then use the scratch
+ * area for early allocations that happen before page allocator is
+ * initialized.
+ */
+static struct kho_scratch *kho_scratch;
+static unsigned int kho_scratch_cnt;
+
+/*
+ * The scratch areas are scaled by default as percent of memory allocated from
+ * memblock. A user can override the scale with command line parameter:
+ *
+ * kho_scratch=N%
+ *
+ * It is also possible to explicitly define size for a lowmem, a global and
+ * per-node scratch areas:
+ *
+ * kho_scratch=l[KMG],n[KMG],m[KMG]
+ *
+ * The explicit size definition takes precedence over scale definition.
+ */
+static unsigned int scratch_scale __initdata = 200;
+static phys_addr_t scratch_size_global __initdata;
+static phys_addr_t scratch_size_pernode __initdata;
+static phys_addr_t scratch_size_lowmem __initdata;
+
+static int __init kho_parse_scratch_size(char *p)
+{
+	size_t len;
+	unsigned long sizes[3];
+	int i;
+
+	if (!p)
+		return -EINVAL;
+
+	len = strlen(p);
+	if (!len)
+		return -EINVAL;
+
+	/* parse nn% */
+	if (p[len - 1] == '%') {
+		/* unsigned int max is 4,294,967,295, 10 chars */
+		char s_scale[11] = {};
+		int ret = 0;
+
+		if (len > ARRAY_SIZE(s_scale))
+			return -EINVAL;
+
+		memcpy(s_scale, p, len - 1);
+		ret = kstrtouint(s_scale, 10, &scratch_scale);
+		if (!ret)
+			pr_notice("scratch scale is %d%%\n", scratch_scale);
+		return ret;
+	}
+
+	/* parse ll[KMG],mm[KMG],nn[KMG] */
+	for (i = 0; i < ARRAY_SIZE(sizes); i++) {
+		char *endp = p;
+
+		if (i > 0) {
+			if (*p != ',')
+				return -EINVAL;
+			p += 1;
+		}
+
+		sizes[i] = memparse(p, &endp);
+		if (!sizes[i] || endp == p)
+			return -EINVAL;
+		p = endp;
+	}
+
+	scratch_size_lowmem = sizes[0];
+	scratch_size_global = sizes[1];
+	scratch_size_pernode = sizes[2];
+	scratch_scale = 0;
+
+	pr_notice("scratch areas: lowmem: %lluMiB global: %lluMiB pernode: %lldMiB\n",
+		  (u64)(scratch_size_lowmem >> 20),
+		  (u64)(scratch_size_global >> 20),
+		  (u64)(scratch_size_pernode >> 20));
+
+	return 0;
+}
+early_param("kho_scratch", kho_parse_scratch_size);
+
+static void __init scratch_size_update(void)
+{
+	phys_addr_t size;
+
+	if (!scratch_scale)
+		return;
+
+	size = memblock_reserved_kern_size(ARCH_LOW_ADDRESS_LIMIT,
+					   NUMA_NO_NODE);
+	size = size * scratch_scale / 100;
+	scratch_size_lowmem = round_up(size, CMA_MIN_ALIGNMENT_BYTES);
+
+	size = memblock_reserved_kern_size(MEMBLOCK_ALLOC_ANYWHERE,
+					   NUMA_NO_NODE);
+	size = size * scratch_scale / 100 - scratch_size_lowmem;
+	scratch_size_global = round_up(size, CMA_MIN_ALIGNMENT_BYTES);
+}
+
+static phys_addr_t __init scratch_size_node(int nid)
+{
+	phys_addr_t size;
+
+	if (scratch_scale) {
+		size = memblock_reserved_kern_size(MEMBLOCK_ALLOC_ANYWHERE,
+						   nid);
+		size = size * scratch_scale / 100;
+	} else {
+		size = scratch_size_pernode;
+	}
+
+	return round_up(size, CMA_MIN_ALIGNMENT_BYTES);
+}
+
+/**
+ * kho_reserve_scratch - Reserve a contiguous chunk of memory for kexec
+ *
+ * With KHO we can preserve arbitrary pages in the system. To ensure we still
+ * have a large contiguous region of memory when we search the physical address
+ * space for target memory, let's make sure we always have a large CMA region
+ * active. This CMA region will only be used for movable pages which are not a
+ * problem for us during KHO because we can just move them somewhere else.
+ */
+static void __init kho_reserve_scratch(void)
+{
+	phys_addr_t addr, size;
+	int nid, i = 0;
+
+	if (!kho_enable)
+		return;
+
+	scratch_size_update();
+
+	/* FIXME: deal with node hot-plug/remove */
+	kho_scratch_cnt = num_online_nodes() + 2;
+	size = kho_scratch_cnt * sizeof(*kho_scratch);
+	kho_scratch = memblock_alloc(size, PAGE_SIZE);
+	if (!kho_scratch)
+		goto err_disable_kho;
+
+	/*
+	 * reserve scratch area in low memory for lowmem allocations in the
+	 * next kernel
+	 */
+	size = scratch_size_lowmem;
+	addr = memblock_phys_alloc_range(size, CMA_MIN_ALIGNMENT_BYTES, 0,
+					 ARCH_LOW_ADDRESS_LIMIT);
+	if (!addr)
+		goto err_free_scratch_desc;
+
+	kho_scratch[i].addr = addr;
+	kho_scratch[i].size = size;
+	i++;
+
+	/* reserve large contiguous area for allocations without nid */
+	size = scratch_size_global;
+	addr = memblock_phys_alloc(size, CMA_MIN_ALIGNMENT_BYTES);
+	if (!addr)
+		goto err_free_scratch_areas;
+
+	kho_scratch[i].addr = addr;
+	kho_scratch[i].size = size;
+	i++;
+
+	for_each_online_node(nid) {
+		size = scratch_size_node(nid);
+		addr = memblock_alloc_range_nid(size, CMA_MIN_ALIGNMENT_BYTES,
+						0, MEMBLOCK_ALLOC_ACCESSIBLE,
+						nid, true);
+		if (!addr)
+			goto err_free_scratch_areas;
+
+		kho_scratch[i].addr = addr;
+		kho_scratch[i].size = size;
+		i++;
+	}
+
+	return;
+
+err_free_scratch_areas:
+	for (i--; i >= 0; i--)
+		memblock_phys_free(kho_scratch[i].addr, kho_scratch[i].size);
+err_free_scratch_desc:
+	memblock_free(kho_scratch, kho_scratch_cnt * sizeof(*kho_scratch));
+err_disable_kho:
+	kho_enable = false;
+}
+
+struct fdt_debugfs {
+	struct list_head list;
+	struct debugfs_blob_wrapper wrapper;
+	struct dentry *file;
+};
+
+static int kho_debugfs_fdt_add(struct list_head *list, struct dentry *dir,
+			       const char *name, const void *fdt)
+{
+	struct fdt_debugfs *f;
+	struct dentry *file;
+
+	f = kmalloc(sizeof(*f), GFP_KERNEL);
+	if (!f)
+		return -ENOMEM;
+
+	f->wrapper.data = (void *)fdt;
+	f->wrapper.size = fdt_totalsize(fdt);
+
+	file = debugfs_create_blob(name, 0400, dir, &f->wrapper);
+	if (IS_ERR(file)) {
+		kfree(f);
+		return PTR_ERR(file);
+	}
+
+	f->file = file;
+	list_add(&f->list, list);
+
+	return 0;
+}
+
+/**
+ * kho_add_subtree - record the physical address of a sub FDT in KHO root tree.
+ * @ser: serialization control object passed by KHO notifiers.
+ * @name: name of the sub tree.
+ * @fdt: the sub tree blob.
+ *
+ * Creates a new child node named @name in KHO root FDT and records
+ * the physical address of @fdt. The pages of @fdt must also be preserved
+ * by KHO for the new kernel to retrieve it after kexec.
+ *
+ * A debugfs blob entry is also created at
+ * ``/sys/kernel/debug/kho/out/sub_fdts/@name``.
+ *
+ * Return: 0 on success, error code on failure
+ */
+int kho_add_subtree(struct kho_serialization *ser, const char *name, void *fdt)
+{
+	int err = 0;
+	u64 phys = (u64)virt_to_phys(fdt);
+	void *root = page_to_virt(ser->fdt);
+
+	err |= fdt_begin_node(root, name);
+	err |= fdt_property(root, PROP_SUB_FDT, &phys, sizeof(phys));
+	err |= fdt_end_node(root);
+
+	if (err)
+		return err;
+
+	return kho_debugfs_fdt_add(&ser->fdt_list, ser->sub_fdt_dir, name, fdt);
+}
+EXPORT_SYMBOL_GPL(kho_add_subtree);
+
+struct kho_out {
+	struct blocking_notifier_head chain_head;
+
+	struct dentry *dir;
+
+	struct mutex lock; /* protects KHO FDT finalization */
+
+	struct kho_serialization ser;
+	bool finalized;
+};
+
+static struct kho_out kho_out = {
+	.chain_head = BLOCKING_NOTIFIER_INIT(kho_out.chain_head),
+	.lock = __MUTEX_INITIALIZER(kho_out.lock),
+	.ser = {
+		.fdt_list = LIST_HEAD_INIT(kho_out.ser.fdt_list),
+		.track = {
+			.orders = XARRAY_INIT(kho_out.ser.track.orders, 0),
+		},
+	},
+	.finalized = false,
+};
+
+int register_kho_notifier(struct notifier_block *nb)
+{
+	return blocking_notifier_chain_register(&kho_out.chain_head, nb);
+}
+EXPORT_SYMBOL_GPL(register_kho_notifier);
+
+int unregister_kho_notifier(struct notifier_block *nb)
+{
+	return blocking_notifier_chain_unregister(&kho_out.chain_head, nb);
+}
+EXPORT_SYMBOL_GPL(unregister_kho_notifier);
+
+/**
+ * kho_preserve_folio - preserve a folio across kexec.
+ * @folio: folio to preserve.
+ *
+ * Instructs KHO to preserve the whole folio across kexec. The order
+ * will be preserved as well.
+ *
+ * Return: 0 on success, error code on failure
+ */
+int kho_preserve_folio(struct folio *folio)
+{
+	const unsigned long pfn = folio_pfn(folio);
+	const unsigned int order = folio_order(folio);
+	struct kho_mem_track *track = &kho_out.ser.track;
+
+	if (kho_out.finalized)
+		return -EBUSY;
+
+	return __kho_preserve_order(track, pfn, order);
+}
+EXPORT_SYMBOL_GPL(kho_preserve_folio);
+
+/**
+ * kho_preserve_phys - preserve a physically contiguous range across kexec.
+ * @phys: physical address of the range.
+ * @size: size of the range.
+ *
+ * Instructs KHO to preserve the memory range from @phys to @phys + @size
+ * across kexec.
+ *
+ * Return: 0 on success, error code on failure
+ */
+int kho_preserve_phys(phys_addr_t phys, size_t size)
+{
+	unsigned long pfn = PHYS_PFN(phys);
+	unsigned long failed_pfn = 0;
+	const unsigned long start_pfn = pfn;
+	const unsigned long end_pfn = PHYS_PFN(phys + size);
+	int err = 0;
+	struct kho_mem_track *track = &kho_out.ser.track;
+
+	if (kho_out.finalized)
+		return -EBUSY;
+
+	if (!PAGE_ALIGNED(phys) || !PAGE_ALIGNED(size))
+		return -EINVAL;
+
+	while (pfn < end_pfn) {
+		const unsigned int order =
+			min(count_trailing_zeros(pfn), ilog2(end_pfn - pfn));
+
+		err = __kho_preserve_order(track, pfn, order);
+		if (err) {
+			failed_pfn = pfn;
+			break;
+		}
+
+		pfn += 1 << order;
+	}
+
+	if (err)
+		__kho_unpreserve(track, start_pfn, failed_pfn);
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(kho_preserve_phys);
+
+/* Handling for debug/kho/out */
+
+static struct dentry *debugfs_root;
+
+static int kho_out_update_debugfs_fdt(void)
+{
+	int err = 0;
+	struct fdt_debugfs *ff, *tmp;
+
+	if (kho_out.finalized) {
+		err = kho_debugfs_fdt_add(&kho_out.ser.fdt_list, kho_out.dir,
+					  "fdt", page_to_virt(kho_out.ser.fdt));
+	} else {
+		list_for_each_entry_safe(ff, tmp, &kho_out.ser.fdt_list, list) {
+			debugfs_remove(ff->file);
+			list_del(&ff->list);
+			kfree(ff);
+		}
+	}
+
+	return err;
+}
+
+static int kho_abort(void)
+{
+	int err;
+	unsigned long order;
+	struct kho_mem_phys *physxa;
+
+	xa_for_each(&kho_out.ser.track.orders, order, physxa) {
+		struct kho_mem_phys_bits *bits;
+		unsigned long phys;
+
+		xa_for_each(&physxa->phys_bits, phys, bits)
+			kfree(bits);
+
+		xa_destroy(&physxa->phys_bits);
+		kfree(physxa);
+	}
+	xa_destroy(&kho_out.ser.track.orders);
+
+	if (kho_out.ser.preserved_mem_map) {
+		kho_mem_ser_free(kho_out.ser.preserved_mem_map);
+		kho_out.ser.preserved_mem_map = NULL;
+	}
+
+	err = blocking_notifier_call_chain(&kho_out.chain_head, KEXEC_KHO_ABORT,
+					   NULL);
+	err = notifier_to_errno(err);
+
+	if (err)
+		pr_err("Failed to abort KHO finalization: %d\n", err);
+
+	return err;
+}
+
+static int kho_finalize(void)
+{
+	int err = 0;
+	u64 *preserved_mem_map;
+	void *fdt = page_to_virt(kho_out.ser.fdt);
+
+	err |= fdt_create(fdt, PAGE_SIZE);
+	err |= fdt_finish_reservemap(fdt);
+	err |= fdt_begin_node(fdt, "");
+	err |= fdt_property_string(fdt, "compatible", KHO_FDT_COMPATIBLE);
+	/**
+	 * Reserve the preserved-memory-map property in the root FDT, so
+	 * that all property definitions will precede subnodes created by
+	 * KHO callers.
+	 */
+	err |= fdt_property_placeholder(fdt, PROP_PRESERVED_MEMORY_MAP,
+					sizeof(*preserved_mem_map),
+					(void **)&preserved_mem_map);
+	if (err)
+		goto abort;
+
+	err = kho_preserve_folio(page_folio(kho_out.ser.fdt));
+	if (err)
+		goto abort;
+
+	err = blocking_notifier_call_chain(&kho_out.chain_head,
+					   KEXEC_KHO_FINALIZE, &kho_out.ser);
+	err = notifier_to_errno(err);
+	if (err)
+		goto abort;
+
+	err = kho_mem_serialize(&kho_out.ser);
+	if (err)
+		goto abort;
+
+	*preserved_mem_map = (u64)virt_to_phys(kho_out.ser.preserved_mem_map);
+
+	err |= fdt_end_node(fdt);
+	err |= fdt_finish(fdt);
+
+abort:
+	if (err) {
+		pr_err("Failed to convert KHO state tree: %d\n", err);
+		kho_abort();
+	}
+
+	return err;
+}
+
+static int kho_out_finalize_get(void *data, u64 *val)
+{
+	mutex_lock(&kho_out.lock);
+	*val = kho_out.finalized;
+	mutex_unlock(&kho_out.lock);
+
+	return 0;
+}
+
+static int kho_out_finalize_set(void *data, u64 _val)
+{
+	int ret = 0;
+	bool val = !!_val;
+
+	mutex_lock(&kho_out.lock);
+
+	if (val == kho_out.finalized) {
+		if (kho_out.finalized)
+			ret = -EEXIST;
+		else
+			ret = -ENOENT;
+		goto unlock;
+	}
+
+	if (val)
+		ret = kho_finalize();
+	else
+		ret = kho_abort();
+
+	if (ret)
+		goto unlock;
+
+	kho_out.finalized = val;
+	ret = kho_out_update_debugfs_fdt();
+
+unlock:
+	mutex_unlock(&kho_out.lock);
+	return ret;
+}
+
+DEFINE_DEBUGFS_ATTRIBUTE(fops_kho_out_finalize, kho_out_finalize_get,
+			 kho_out_finalize_set, "%llu\n");
+
+static int scratch_phys_show(struct seq_file *m, void *v)
+{
+	for (int i = 0; i < kho_scratch_cnt; i++)
+		seq_printf(m, "0x%llx\n", kho_scratch[i].addr);
+
+	return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(scratch_phys);
+
+static int scratch_len_show(struct seq_file *m, void *v)
+{
+	for (int i = 0; i < kho_scratch_cnt; i++)
+		seq_printf(m, "0x%llx\n", kho_scratch[i].size);
+
+	return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(scratch_len);
+
+static __init int kho_out_debugfs_init(void)
+{
+	struct dentry *dir, *f, *sub_fdt_dir;
+
+	dir = debugfs_create_dir("out", debugfs_root);
+	if (IS_ERR(dir))
+		return -ENOMEM;
+
+	sub_fdt_dir = debugfs_create_dir("sub_fdts", dir);
+	if (IS_ERR(sub_fdt_dir))
+		goto err_rmdir;
+
+	f = debugfs_create_file("scratch_phys", 0400, dir, NULL,
+				&scratch_phys_fops);
+	if (IS_ERR(f))
+		goto err_rmdir;
+
+	f = debugfs_create_file("scratch_len", 0400, dir, NULL,
+				&scratch_len_fops);
+	if (IS_ERR(f))
+		goto err_rmdir;
+
+	f = debugfs_create_file("finalize", 0600, dir, NULL,
+				&fops_kho_out_finalize);
+	if (IS_ERR(f))
+		goto err_rmdir;
+
+	kho_out.dir = dir;
+	kho_out.ser.sub_fdt_dir = sub_fdt_dir;
+	return 0;
+
+err_rmdir:
+	debugfs_remove_recursive(dir);
+	return -ENOENT;
+}
+
+struct kho_in {
+	struct dentry *dir;
+	phys_addr_t fdt_phys;
+	phys_addr_t scratch_phys;
+	struct list_head fdt_list;
+};
+
+static struct kho_in kho_in = {
+	.fdt_list = LIST_HEAD_INIT(kho_in.fdt_list),
+};
+
+static const void *kho_get_fdt(void)
+{
+	return kho_in.fdt_phys ? phys_to_virt(kho_in.fdt_phys) : NULL;
+}
+
+/**
+ * kho_retrieve_subtree - retrieve a preserved sub FDT by its name.
+ * @name: the name of the sub FDT passed to kho_add_subtree().
+ * @phys: if found, the physical address of the sub FDT is stored in @phys.
+ *
+ * Retrieve a preserved sub FDT named @name and store its physical
+ * address in @phys.
+ *
+ * Return: 0 on success, error code on failure
+ */
+int kho_retrieve_subtree(const char *name, phys_addr_t *phys)
+{
+	const void *fdt = kho_get_fdt();
+	const u64 *val;
+	int offset, len;
+
+	if (!fdt)
+		return -ENOENT;
+
+	if (!phys)
+		return -EINVAL;
+
+	offset = fdt_subnode_offset(fdt, 0, name);
+	if (offset < 0)
+		return -ENOENT;
+
+	val = fdt_getprop(fdt, offset, PROP_SUB_FDT, &len);
+	if (!val || len != sizeof(*val))
+		return -EINVAL;
+
+	*phys = (phys_addr_t)*val;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(kho_retrieve_subtree);
+
+/* Handling for debugfs/kho/in */
+
+static __init int kho_in_debugfs_init(const void *fdt)
+{
+	struct dentry *sub_fdt_dir;
+	int err, child;
+
+	kho_in.dir = debugfs_create_dir("in", debugfs_root);
+	if (IS_ERR(kho_in.dir))
+		return PTR_ERR(kho_in.dir);
+
+	sub_fdt_dir = debugfs_create_dir("sub_fdts", kho_in.dir);
+	if (IS_ERR(sub_fdt_dir)) {
+		err = PTR_ERR(sub_fdt_dir);
+		goto err_rmdir;
+	}
+
+	err = kho_debugfs_fdt_add(&kho_in.fdt_list, kho_in.dir, "fdt", fdt);
+	if (err)
+		goto err_rmdir;
+
+	fdt_for_each_subnode(child, fdt, 0) {
+		int len = 0;
+		const char *name = fdt_get_name(fdt, child, NULL);
+		const u64 *fdt_phys;
+
+		fdt_phys = fdt_getprop(fdt, child, "fdt", &len);
+		if (!fdt_phys)
+			continue;
+		if (len != sizeof(*fdt_phys)) {
+			pr_warn("node `%s`'s prop `fdt` has invalid length: %d\n",
+				name, len);
+			continue;
+		}
+		err = kho_debugfs_fdt_add(&kho_in.fdt_list, sub_fdt_dir, name,
+					  phys_to_virt(*fdt_phys));
+		if (err) {
+			pr_warn("failed to add fdt `%s` to debugfs: %d\n", name,
+				err);
+			continue;
+		}
+	}
+
+	return 0;
+
+err_rmdir:
+	debugfs_remove_recursive(kho_in.dir);
+	return err;
+}
+
+static __init int kho_init(void)
+{
+	int err = 0;
+	const void *fdt = kho_get_fdt();
+
+	if (!kho_enable)
+		return 0;
+
+	kho_out.ser.fdt = alloc_page(GFP_KERNEL);
+	if (!kho_out.ser.fdt) {
+		err = -ENOMEM;
+		goto err_free_scratch;
+	}
+
+	debugfs_root = debugfs_create_dir("kho", NULL);
+	if (IS_ERR(debugfs_root)) {
+		err = -ENOENT;
+		goto err_free_fdt;
+	}
+
+	err = kho_out_debugfs_init();
+	if (err)
+		goto err_free_fdt;
+
+	if (fdt) {
+		err = kho_in_debugfs_init(fdt);
+		/*
+		 * Failure to create /sys/kernel/debug/kho/in does not prevent
+		 * reviving state from KHO and setting up KHO for the next
+		 * kexec.
+		 */
+		if (err)
+			pr_err("failed exposing handover FDT in debugfs: %d\n",
+			       err);
+
+		return 0;
+	}
+
+	for (int i = 0; i < kho_scratch_cnt; i++) {
+		unsigned long base_pfn = PHYS_PFN(kho_scratch[i].addr);
+		unsigned long count = kho_scratch[i].size >> PAGE_SHIFT;
+		unsigned long pfn;
+
+		for (pfn = base_pfn; pfn < base_pfn + count;
+		     pfn += pageblock_nr_pages)
+			init_cma_reserved_pageblock(pfn_to_page(pfn));
+	}
+
+	return 0;
+
+err_free_fdt:
+	put_page(kho_out.ser.fdt);
+	kho_out.ser.fdt = NULL;
+err_free_scratch:
+	for (int i = 0; i < kho_scratch_cnt; i++) {
+		void *start = __va(kho_scratch[i].addr);
+		void *end = start + kho_scratch[i].size;
+
+		free_reserved_area(start, end, -1, "");
+	}
+	kho_enable = false;
+	return err;
+}
+late_initcall(kho_init);
+
+static void __init kho_release_scratch(void)
+{
+	phys_addr_t start, end;
+	u64 i;
+
+	memmap_init_kho_scratch_pages();
+
+	/*
+	 * Mark scratch mem as CMA before we return it. That way we
+	 * ensure that no kernel allocations happen on it. That means
+	 * we can reuse it as scratch memory again later.
+	 */
+	__for_each_mem_range(i, &memblock.memory, NULL, NUMA_NO_NODE,
+			     MEMBLOCK_KHO_SCRATCH, &start, &end, NULL) {
+		ulong start_pfn = pageblock_start_pfn(PFN_DOWN(start));
+		ulong end_pfn = pageblock_align(PFN_UP(end));
+		ulong pfn;
+
+		for (pfn = start_pfn; pfn < end_pfn; pfn += pageblock_nr_pages)
+			set_pageblock_migratetype(pfn_to_page(pfn),
+						  MIGRATE_CMA);
+	}
+}
+
+void __init kho_memory_init(void)
+{
+	struct folio *folio;
+
+	if (kho_in.scratch_phys) {
+		kho_scratch = phys_to_virt(kho_in.scratch_phys);
+		kho_release_scratch();
+
+		kho_mem_deserialize(kho_get_fdt());
+		folio = kho_restore_folio(kho_in.fdt_phys);
+		if (!folio)
+			pr_warn("failed to restore folio for KHO fdt\n");
+	} else {
+		kho_reserve_scratch();
+	}
+}
+
+void __init kho_populate(phys_addr_t fdt_phys, u64 fdt_len,
+			 phys_addr_t scratch_phys, u64 scratch_len)
+{
+	void *fdt = NULL;
+	struct kho_scratch *scratch = NULL;
+	int err = 0;
+	unsigned int scratch_cnt = scratch_len / sizeof(*kho_scratch);
+
+	/* Validate the input FDT */
+	fdt = early_memremap(fdt_phys, fdt_len);
+	if (!fdt) {
+		pr_warn("setup: failed to memremap FDT (0x%llx)\n", fdt_phys);
+		err = -EFAULT;
+		goto out;
+	}
+	err = fdt_check_header(fdt);
+	if (err) {
+		pr_warn("setup: handover FDT (0x%llx) is invalid: %d\n",
+			fdt_phys, err);
+		err = -EINVAL;
+		goto out;
+	}
+	err = fdt_node_check_compatible(fdt, 0, KHO_FDT_COMPATIBLE);
+	if (err) {
+		pr_warn("setup: handover FDT (0x%llx) is incompatible with '%s': %d\n",
+			fdt_phys, KHO_FDT_COMPATIBLE, err);
+		err = -EINVAL;
+		goto out;
+	}
+
+	scratch = early_memremap(scratch_phys, scratch_len);
+	if (!scratch) {
+		pr_warn("setup: failed to memremap scratch (phys=0x%llx, len=%lld)\n",
+			scratch_phys, scratch_len);
+		err = -EFAULT;
+		goto out;
+	}
+
+	/*
+	 * We pass a safe contiguous blocks of memory to use for early boot
+	 * purporses from the previous kernel so that we can resize the
+	 * memblock array as needed.
+	 */
+	for (int i = 0; i < scratch_cnt; i++) {
+		struct kho_scratch *area = &scratch[i];
+		u64 size = area->size;
+
+		memblock_add(area->addr, size);
+		err = memblock_mark_kho_scratch(area->addr, size);
+		if (WARN_ON(err)) {
+			pr_warn("failed to mark the scratch region 0x%pa+0x%pa: %d",
+				&area->addr, &size, err);
+			goto out;
+		}
+		pr_debug("Marked 0x%pa+0x%pa as scratch", &area->addr, &size);
+	}
+
+	memblock_reserve(scratch_phys, scratch_len);
+
+	/*
+	 * Now that we have a viable region of scratch memory, let's tell
+	 * the memblocks allocator to only use that for any allocations.
+	 * That way we ensure that nothing scribbles over in use data while
+	 * we initialize the page tables which we will need to ingest all
+	 * memory reservations from the previous kernel.
+	 */
+	memblock_set_kho_scratch_only();
+
+	kho_in.fdt_phys = fdt_phys;
+	kho_in.scratch_phys = scratch_phys;
+	kho_scratch_cnt = scratch_cnt;
+	pr_info("found kexec handover data. Will skip init for some devices\n");
+
+out:
+	if (fdt)
+		early_memunmap(fdt, fdt_len);
+	if (scratch)
+		early_memunmap(scratch, scratch_len);
+	if (err)
+		pr_warn("disabling KHO revival: %d\n", err);
+}
+
+/* Helper functions for kexec_file_load */
+
+int kho_fill_kimage(struct kimage *image)
+{
+	ssize_t scratch_size;
+	int err = 0;
+	struct kexec_buf scratch;
+
+	if (!kho_enable)
+		return 0;
+
+	image->kho.fdt = page_to_phys(kho_out.ser.fdt);
+
+	scratch_size = sizeof(*kho_scratch) * kho_scratch_cnt;
+	scratch = (struct kexec_buf){
+		.image = image,
+		.buffer = kho_scratch,
+		.bufsz = scratch_size,
+		.mem = KEXEC_BUF_MEM_UNKNOWN,
+		.memsz = scratch_size,
+		.buf_align = SZ_64K, /* Makes it easier to map */
+		.buf_max = ULONG_MAX,
+		.top_down = true,
+	};
+	err = kexec_add_buffer(&scratch);
+	if (err)
+		return err;
+	image->kho.scratch = &image->segment[image->nr_segments - 1];
+
+	return 0;
+}
+
+static int kho_walk_scratch(struct kexec_buf *kbuf,
+			    int (*func)(struct resource *, void *))
+{
+	int ret = 0;
+	int i;
+
+	for (i = 0; i < kho_scratch_cnt; i++) {
+		struct resource res = {
+			.start = kho_scratch[i].addr,
+			.end = kho_scratch[i].addr + kho_scratch[i].size - 1,
+		};
+
+		/* Try to fit the kimage into our KHO scratch region */
+		ret = func(&res, kbuf);
+		if (ret)
+			break;
+	}
+
+	return ret;
+}
+
+int kho_locate_mem_hole(struct kexec_buf *kbuf,
+			int (*func)(struct resource *, void *))
+{
+	int ret;
+
+	if (!kho_enable || kbuf->image->type == KEXEC_TYPE_CRASH)
+		return 1;
+
+	ret = kho_walk_scratch(kbuf, func);
+
+	return ret == 1 ? 0 : -EADDRNOTAVAIL;
+}
diff --git a/kernel/kexec_internal.h b/kernel/kexec_internal.h
index d35d9792402d..30a733a55a67 100644
--- a/kernel/kexec_internal.h
+++ b/kernel/kexec_internal.h
@@ -39,4 +39,20 @@ extern size_t kexec_purgatory_size;
 #else /* CONFIG_KEXEC_FILE */
 static inline void kimage_file_post_load_cleanup(struct kimage *image) { }
 #endif /* CONFIG_KEXEC_FILE */
+
+struct kexec_buf;
+
+#ifdef CONFIG_KEXEC_HANDOVER
+int kho_locate_mem_hole(struct kexec_buf *kbuf,
+			int (*func)(struct resource *, void *));
+int kho_fill_kimage(struct kimage *image);
+#else
+static inline int kho_locate_mem_hole(struct kexec_buf *kbuf,
+				      int (*func)(struct resource *, void *))
+{
+	return 1;
+}
+
+static inline int kho_fill_kimage(struct kimage *image) { return 0; }
+#endif /* CONFIG_KEXEC_HANDOVER */
 #endif /* LINUX_KEXEC_INTERNAL_H */
diff --git a/kernel/kthread.c b/kernel/kthread.c
index 77c44924cf54..85fc068f0083 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -1207,7 +1207,8 @@ EXPORT_SYMBOL_GPL(kthread_queue_work);
  */
 void kthread_delayed_work_timer_fn(struct timer_list *t)
 {
-	struct kthread_delayed_work *dwork = from_timer(dwork, t, timer);
+	struct kthread_delayed_work *dwork = timer_container_of(dwork, t,
+								timer);
 	struct kthread_work *work = &dwork->work;
 	struct kthread_worker *worker = work->worker;
 	unsigned long flags;
diff --git a/kernel/livepatch/transition.c b/kernel/livepatch/transition.c
index ba069459c101..2351a19ac2a9 100644
--- a/kernel/livepatch/transition.c
+++ b/kernel/livepatch/transition.c
@@ -29,22 +29,13 @@ static unsigned int klp_signals_cnt;
 
 /*
  * When a livepatch is in progress, enable klp stack checking in
- * cond_resched().  This helps CPU-bound kthreads get patched.
+ * schedule().  This helps CPU-bound kthreads get patched.
  */
-#if defined(CONFIG_PREEMPT_DYNAMIC) && defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL)
-
-#define klp_cond_resched_enable() sched_dynamic_klp_enable()
-#define klp_cond_resched_disable() sched_dynamic_klp_disable()
-
-#else /* !CONFIG_PREEMPT_DYNAMIC || !CONFIG_HAVE_PREEMPT_DYNAMIC_CALL */
 
 DEFINE_STATIC_KEY_FALSE(klp_sched_try_switch_key);
-EXPORT_SYMBOL(klp_sched_try_switch_key);
 
-#define klp_cond_resched_enable() static_branch_enable(&klp_sched_try_switch_key)
-#define klp_cond_resched_disable() static_branch_disable(&klp_sched_try_switch_key)
-
-#endif /* CONFIG_PREEMPT_DYNAMIC && CONFIG_HAVE_PREEMPT_DYNAMIC_CALL */
+#define klp_resched_enable() static_branch_enable(&klp_sched_try_switch_key)
+#define klp_resched_disable() static_branch_disable(&klp_sched_try_switch_key)
 
 /*
  * This work can be performed periodically to finish patching or unpatching any
@@ -365,26 +356,18 @@ static bool klp_try_switch_task(struct task_struct *task)
 
 void __klp_sched_try_switch(void)
 {
-	if (likely(!klp_patch_pending(current)))
-		return;
-
 	/*
-	 * This function is called from cond_resched() which is called in many
-	 * places throughout the kernel.  Using the klp_mutex here might
-	 * deadlock.
-	 *
-	 * Instead, disable preemption to prevent racing with other callers of
-	 * klp_try_switch_task().  Thanks to task_call_func() they won't be
-	 * able to switch this task while it's running.
+	 * This function is called from __schedule() while a context switch is
+	 * about to happen. Preemption is already disabled and klp_mutex
+	 * can't be acquired.
+	 * Disabled preemption is used to prevent racing with other callers of
+	 * klp_try_switch_task(). Thanks to task_call_func() they won't be
+	 * able to switch to this task while it's running.
 	 */
-	preempt_disable();
+	lockdep_assert_preemption_disabled();
 
-	/*
-	 * Make sure current didn't get patched between the above check and
-	 * preempt_disable().
-	 */
-	if (unlikely(!klp_patch_pending(current)))
-		goto out;
+	if (likely(!klp_patch_pending(current)))
+		return;
 
 	/*
 	 * Enforce the order of the TIF_PATCH_PENDING read above and the
@@ -395,11 +378,7 @@ void __klp_sched_try_switch(void)
 	smp_rmb();
 
 	klp_try_switch_task(current);
-
-out:
-	preempt_enable();
 }
-EXPORT_SYMBOL(__klp_sched_try_switch);
 
 /*
  * Sends a fake signal to all non-kthread tasks with TIF_PATCH_PENDING set.
@@ -508,7 +487,7 @@ void klp_try_complete_transition(void)
 	}
 
 	/* Done!  Now cleanup the data structures. */
-	klp_cond_resched_disable();
+	klp_resched_disable();
 	patch = klp_transition_patch;
 	klp_complete_transition();
 
@@ -560,7 +539,7 @@ void klp_start_transition(void)
 			set_tsk_thread_flag(task, TIF_PATCH_PENDING);
 	}
 
-	klp_cond_resched_enable();
+	klp_resched_enable();
 
 	klp_signals_cnt = 0;
 }
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index 58d78a33ac65..dd2bbf73718b 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -219,6 +219,7 @@ static DECLARE_BITMAP(list_entries_in_use, MAX_LOCKDEP_ENTRIES);
 static struct hlist_head lock_keys_hash[KEYHASH_SIZE];
 unsigned long nr_lock_classes;
 unsigned long nr_zapped_classes;
+unsigned long nr_dynamic_keys;
 unsigned long max_lock_class_idx;
 struct lock_class lock_classes[MAX_LOCKDEP_KEYS];
 DECLARE_BITMAP(lock_classes_in_use, MAX_LOCKDEP_KEYS);
@@ -1238,6 +1239,7 @@ void lockdep_register_key(struct lock_class_key *key)
 			goto out_unlock;
 	}
 	hlist_add_head_rcu(&key->hash_entry, hash_head);
+	nr_dynamic_keys++;
 out_unlock:
 	graph_unlock();
 restore_irqs:
@@ -1977,41 +1979,6 @@ print_circular_bug_header(struct lock_list *entry, unsigned int depth,
 }
 
 /*
- * We are about to add A -> B into the dependency graph, and in __bfs() a
- * strong dependency path A -> .. -> B is found: hlock_class equals
- * entry->class.
- *
- * If A -> .. -> B can replace A -> B in any __bfs() search (means the former
- * is _stronger_ than or equal to the latter), we consider A -> B as redundant.
- * For example if A -> .. -> B is -(EN)-> (i.e. A -(E*)-> .. -(*N)-> B), and A
- * -> B is -(ER)-> or -(EN)->, then we don't need to add A -> B into the
- * dependency graph, as any strong path ..-> A -> B ->.. we can get with
- * having dependency A -> B, we could already get a equivalent path ..-> A ->
- * .. -> B -> .. with A -> .. -> B. Therefore A -> B is redundant.
- *
- * We need to make sure both the start and the end of A -> .. -> B is not
- * weaker than A -> B. For the start part, please see the comment in
- * check_redundant(). For the end part, we need:
- *
- * Either
- *
- *     a) A -> B is -(*R)-> (everything is not weaker than that)
- *
- * or
- *
- *     b) A -> .. -> B is -(*N)-> (nothing is stronger than this)
- *
- */
-static inline bool hlock_equal(struct lock_list *entry, void *data)
-{
-	struct held_lock *hlock = (struct held_lock *)data;
-
-	return hlock_class(hlock) == entry->class && /* Found A -> .. -> B */
-	       (hlock->read == 2 ||  /* A -> B is -(*R)-> */
-		!entry->only_xr); /* A -> .. -> B is -(*N)-> */
-}
-
-/*
  * We are about to add B -> A into the dependency graph, and in __bfs() a
  * strong dependency path A -> .. -> B is found: hlock_class equals
  * entry->class.
@@ -2916,6 +2883,41 @@ static inline bool usage_skip(struct lock_list *entry, void *mask)
 
 #ifdef CONFIG_LOCKDEP_SMALL
 /*
+ * We are about to add A -> B into the dependency graph, and in __bfs() a
+ * strong dependency path A -> .. -> B is found: hlock_class equals
+ * entry->class.
+ *
+ * If A -> .. -> B can replace A -> B in any __bfs() search (means the former
+ * is _stronger_ than or equal to the latter), we consider A -> B as redundant.
+ * For example if A -> .. -> B is -(EN)-> (i.e. A -(E*)-> .. -(*N)-> B), and A
+ * -> B is -(ER)-> or -(EN)->, then we don't need to add A -> B into the
+ * dependency graph, as any strong path ..-> A -> B ->.. we can get with
+ * having dependency A -> B, we could already get a equivalent path ..-> A ->
+ * .. -> B -> .. with A -> .. -> B. Therefore A -> B is redundant.
+ *
+ * We need to make sure both the start and the end of A -> .. -> B is not
+ * weaker than A -> B. For the start part, please see the comment in
+ * check_redundant(). For the end part, we need:
+ *
+ * Either
+ *
+ *     a) A -> B is -(*R)-> (everything is not weaker than that)
+ *
+ * or
+ *
+ *     b) A -> .. -> B is -(*N)-> (nothing is stronger than this)
+ *
+ */
+static inline bool hlock_equal(struct lock_list *entry, void *data)
+{
+	struct held_lock *hlock = (struct held_lock *)data;
+
+	return hlock_class(hlock) == entry->class && /* Found A -> .. -> B */
+	       (hlock->read == 2 ||  /* A -> B is -(*R)-> */
+		!entry->only_xr); /* A -> .. -> B is -(*N)-> */
+}
+
+/*
  * Check that the dependency graph starting at <src> can lead to
  * <target> or not. If it can, <src> -> <target> dependency is already
  * in the graph.
@@ -5101,6 +5103,9 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass,
 		lockevent_inc(lockdep_nocheck);
 	}
 
+	if (DEBUG_LOCKS_WARN_ON(subclass >= MAX_LOCKDEP_SUBCLASSES))
+		return 0;
+
 	if (subclass < NR_LOCKDEP_CACHING_CLASSES)
 		class = lock->class_cache[subclass];
 	/*
@@ -6606,6 +6611,7 @@ void lockdep_unregister_key(struct lock_class_key *key)
 		pf = get_pending_free();
 		__lockdep_free_key_range(pf, key, 1);
 		need_callback = prepare_call_rcu_zapped(pf);
+		nr_dynamic_keys--;
 	}
 	lockdep_unlock();
 	raw_local_irq_restore(flags);
diff --git a/kernel/locking/lockdep_internals.h b/kernel/locking/lockdep_internals.h
index 20f9ef58d3d0..82156caf77d1 100644
--- a/kernel/locking/lockdep_internals.h
+++ b/kernel/locking/lockdep_internals.h
@@ -138,6 +138,7 @@ extern unsigned long nr_lock_classes;
 extern unsigned long nr_zapped_classes;
 extern unsigned long nr_zapped_lock_chains;
 extern unsigned long nr_list_entries;
+extern unsigned long nr_dynamic_keys;
 long lockdep_next_lockchain(long i);
 unsigned long lock_chain_count(void);
 extern unsigned long nr_stack_trace_entries;
diff --git a/kernel/locking/lockdep_proc.c b/kernel/locking/lockdep_proc.c
index 6db0f43fc4df..b52c07c4707c 100644
--- a/kernel/locking/lockdep_proc.c
+++ b/kernel/locking/lockdep_proc.c
@@ -286,6 +286,8 @@ static int lockdep_stats_show(struct seq_file *m, void *v)
 #endif
 	seq_printf(m, " lock-classes:                  %11lu [max: %lu]\n",
 			nr_lock_classes, MAX_LOCKDEP_KEYS);
+	seq_printf(m, " dynamic-keys:                  %11lu\n",
+			nr_dynamic_keys);
 	seq_printf(m, " direct dependencies:           %11lu [max: %lu]\n",
 			nr_list_entries, MAX_LOCKDEP_ENTRIES);
 	seq_printf(m, " indirect dependencies:         %11lu\n",
diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c
index 555e2b3a665a..a39ecccbd106 100644
--- a/kernel/locking/mutex.c
+++ b/kernel/locking/mutex.c
@@ -29,6 +29,7 @@
 #include <linux/interrupt.h>
 #include <linux/debug_locks.h>
 #include <linux/osq_lock.h>
+#include <linux/hung_task.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/lock.h>
@@ -191,7 +192,7 @@ __mutex_add_waiter(struct mutex *lock, struct mutex_waiter *waiter,
 		   struct list_head *list)
 {
 #ifdef CONFIG_DETECT_HUNG_TASK_BLOCKER
-	WRITE_ONCE(current->blocker_mutex, lock);
+	hung_task_set_blocker(lock, BLOCKER_TYPE_MUTEX);
 #endif
 	debug_mutex_add_waiter(lock, waiter, current);
 
@@ -209,7 +210,7 @@ __mutex_remove_waiter(struct mutex *lock, struct mutex_waiter *waiter)
 
 	debug_mutex_remove_waiter(lock, waiter, current);
 #ifdef CONFIG_DETECT_HUNG_TASK_BLOCKER
-	WRITE_ONCE(current->blocker_mutex, NULL);
+	hung_task_clear_blocker();
 #endif
 }
 
@@ -808,11 +809,12 @@ _mutex_lock_nest_lock(struct mutex *lock, struct lockdep_map *nest)
 EXPORT_SYMBOL_GPL(_mutex_lock_nest_lock);
 
 int __sched
-mutex_lock_killable_nested(struct mutex *lock, unsigned int subclass)
+_mutex_lock_killable(struct mutex *lock, unsigned int subclass,
+				      struct lockdep_map *nest)
 {
-	return __mutex_lock(lock, TASK_KILLABLE, subclass, NULL, _RET_IP_);
+	return __mutex_lock(lock, TASK_KILLABLE, subclass, nest, _RET_IP_);
 }
-EXPORT_SYMBOL_GPL(mutex_lock_killable_nested);
+EXPORT_SYMBOL_GPL(_mutex_lock_killable);
 
 int __sched
 mutex_lock_interruptible_nested(struct mutex *lock, unsigned int subclass)
@@ -1062,6 +1064,7 @@ __ww_mutex_lock_interruptible_slowpath(struct ww_mutex *lock,
 
 #endif
 
+#ifndef CONFIG_DEBUG_LOCK_ALLOC
 /**
  * mutex_trylock - try to acquire the mutex, without waiting
  * @lock: the mutex to be acquired
@@ -1078,17 +1081,24 @@ __ww_mutex_lock_interruptible_slowpath(struct ww_mutex *lock,
  */
 int __sched mutex_trylock(struct mutex *lock)
 {
+	MUTEX_WARN_ON(lock->magic != lock);
+	return __mutex_trylock(lock);
+}
+EXPORT_SYMBOL(mutex_trylock);
+#else
+int __sched _mutex_trylock_nest_lock(struct mutex *lock, struct lockdep_map *nest_lock)
+{
 	bool locked;
 
 	MUTEX_WARN_ON(lock->magic != lock);
-
 	locked = __mutex_trylock(lock);
 	if (locked)
-		mutex_acquire(&lock->dep_map, 0, 1, _RET_IP_);
+		mutex_acquire_nest(&lock->dep_map, 0, 1, nest_lock, _RET_IP_);
 
 	return locked;
 }
-EXPORT_SYMBOL(mutex_trylock);
+EXPORT_SYMBOL(_mutex_trylock_nest_lock);
+#endif
 
 #ifndef CONFIG_DEBUG_LOCK_ALLOC
 int __sched
diff --git a/kernel/locking/percpu-rwsem.c b/kernel/locking/percpu-rwsem.c
index d6964fc29f51..ef234469baac 100644
--- a/kernel/locking/percpu-rwsem.c
+++ b/kernel/locking/percpu-rwsem.c
@@ -138,7 +138,8 @@ static int percpu_rwsem_wake_function(struct wait_queue_entry *wq_entry,
 	return !reader; /* wake (readers until) 1 writer */
 }
 
-static void percpu_rwsem_wait(struct percpu_rw_semaphore *sem, bool reader)
+static void percpu_rwsem_wait(struct percpu_rw_semaphore *sem, bool reader,
+			      bool freeze)
 {
 	DEFINE_WAIT_FUNC(wq_entry, percpu_rwsem_wake_function);
 	bool wait;
@@ -156,7 +157,8 @@ static void percpu_rwsem_wait(struct percpu_rw_semaphore *sem, bool reader)
 	spin_unlock_irq(&sem->waiters.lock);
 
 	while (wait) {
-		set_current_state(TASK_UNINTERRUPTIBLE);
+		set_current_state(TASK_UNINTERRUPTIBLE |
+				  (freeze ? TASK_FREEZABLE : 0));
 		if (!smp_load_acquire(&wq_entry.private))
 			break;
 		schedule();
@@ -164,7 +166,8 @@ static void percpu_rwsem_wait(struct percpu_rw_semaphore *sem, bool reader)
 	__set_current_state(TASK_RUNNING);
 }
 
-bool __sched __percpu_down_read(struct percpu_rw_semaphore *sem, bool try)
+bool __sched __percpu_down_read(struct percpu_rw_semaphore *sem, bool try,
+				bool freeze)
 {
 	if (__percpu_down_read_trylock(sem))
 		return true;
@@ -174,7 +177,7 @@ bool __sched __percpu_down_read(struct percpu_rw_semaphore *sem, bool try)
 
 	trace_contention_begin(sem, LCB_F_PERCPU | LCB_F_READ);
 	preempt_enable();
-	percpu_rwsem_wait(sem, /* .reader = */ true);
+	percpu_rwsem_wait(sem, /* .reader = */ true, freeze);
 	preempt_disable();
 	trace_contention_end(sem, 0);
 
@@ -237,7 +240,7 @@ void __sched percpu_down_write(struct percpu_rw_semaphore *sem)
 	 */
 	if (!__percpu_down_write_trylock(sem)) {
 		trace_contention_begin(sem, LCB_F_PERCPU | LCB_F_WRITE);
-		percpu_rwsem_wait(sem, /* .reader = */ false);
+		percpu_rwsem_wait(sem, /* .reader = */ false, false);
 		contended = true;
 	}
 
diff --git a/kernel/locking/rtmutex_api.c b/kernel/locking/rtmutex_api.c
index 191e4720e546..2d933528a0fa 100644
--- a/kernel/locking/rtmutex_api.c
+++ b/kernel/locking/rtmutex_api.c
@@ -544,12 +544,12 @@ int __sched mutex_lock_interruptible_nested(struct mutex *lock,
 }
 EXPORT_SYMBOL_GPL(mutex_lock_interruptible_nested);
 
-int __sched mutex_lock_killable_nested(struct mutex *lock,
-					    unsigned int subclass)
+int __sched _mutex_lock_killable(struct mutex *lock, unsigned int subclass,
+				 struct lockdep_map *nest_lock)
 {
-	return __mutex_lock_common(lock, TASK_KILLABLE, subclass, NULL, _RET_IP_);
+	return __mutex_lock_common(lock, TASK_KILLABLE, subclass, nest_lock, _RET_IP_);
 }
-EXPORT_SYMBOL_GPL(mutex_lock_killable_nested);
+EXPORT_SYMBOL_GPL(_mutex_lock_killable);
 
 void __sched mutex_lock_io_nested(struct mutex *lock, unsigned int subclass)
 {
@@ -563,6 +563,21 @@ void __sched mutex_lock_io_nested(struct mutex *lock, unsigned int subclass)
 }
 EXPORT_SYMBOL_GPL(mutex_lock_io_nested);
 
+int __sched _mutex_trylock_nest_lock(struct mutex *lock,
+				     struct lockdep_map *nest_lock)
+{
+	int ret;
+
+	if (IS_ENABLED(CONFIG_DEBUG_RT_MUTEXES) && WARN_ON_ONCE(!in_task()))
+		return 0;
+
+	ret = __rt_mutex_trylock(&lock->rtmutex);
+	if (ret)
+		mutex_acquire_nest(&lock->dep_map, 0, 1, nest_lock, _RET_IP_);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(_mutex_trylock_nest_lock);
 #else /* CONFIG_DEBUG_LOCK_ALLOC */
 
 void __sched mutex_lock(struct mutex *lock)
@@ -591,22 +606,16 @@ void __sched mutex_lock_io(struct mutex *lock)
 	io_schedule_finish(token);
 }
 EXPORT_SYMBOL(mutex_lock_io);
-#endif /* !CONFIG_DEBUG_LOCK_ALLOC */
 
 int __sched mutex_trylock(struct mutex *lock)
 {
-	int ret;
-
 	if (IS_ENABLED(CONFIG_DEBUG_RT_MUTEXES) && WARN_ON_ONCE(!in_task()))
 		return 0;
 
-	ret = __rt_mutex_trylock(&lock->rtmutex);
-	if (ret)
-		mutex_acquire(&lock->dep_map, 0, 1, _RET_IP_);
-
-	return ret;
+	return __rt_mutex_trylock(&lock->rtmutex);
 }
 EXPORT_SYMBOL(mutex_trylock);
+#endif /* !CONFIG_DEBUG_LOCK_ALLOC */
 
 void __sched mutex_unlock(struct mutex *lock)
 {
diff --git a/kernel/locking/semaphore.c b/kernel/locking/semaphore.c
index de9117c0e671..3ef032e22f7e 100644
--- a/kernel/locking/semaphore.c
+++ b/kernel/locking/semaphore.c
@@ -34,6 +34,7 @@
 #include <linux/spinlock.h>
 #include <linux/ftrace.h>
 #include <trace/events/lock.h>
+#include <linux/hung_task.h>
 
 static noinline void __down(struct semaphore *sem);
 static noinline int __down_interruptible(struct semaphore *sem);
@@ -41,6 +42,41 @@ static noinline int __down_killable(struct semaphore *sem);
 static noinline int __down_timeout(struct semaphore *sem, long timeout);
 static noinline void __up(struct semaphore *sem, struct wake_q_head *wake_q);
 
+#ifdef CONFIG_DETECT_HUNG_TASK_BLOCKER
+static inline void hung_task_sem_set_holder(struct semaphore *sem)
+{
+	WRITE_ONCE((sem)->last_holder, (unsigned long)current);
+}
+
+static inline void hung_task_sem_clear_if_holder(struct semaphore *sem)
+{
+	if (READ_ONCE((sem)->last_holder) == (unsigned long)current)
+		WRITE_ONCE((sem)->last_holder, 0UL);
+}
+
+unsigned long sem_last_holder(struct semaphore *sem)
+{
+	return READ_ONCE(sem->last_holder);
+}
+#else
+static inline void hung_task_sem_set_holder(struct semaphore *sem)
+{
+}
+static inline void hung_task_sem_clear_if_holder(struct semaphore *sem)
+{
+}
+unsigned long sem_last_holder(struct semaphore *sem)
+{
+	return 0UL;
+}
+#endif
+
+static inline void __sem_acquire(struct semaphore *sem)
+{
+	sem->count--;
+	hung_task_sem_set_holder(sem);
+}
+
 /**
  * down - acquire the semaphore
  * @sem: the semaphore to be acquired
@@ -59,7 +95,7 @@ void __sched down(struct semaphore *sem)
 	might_sleep();
 	raw_spin_lock_irqsave(&sem->lock, flags);
 	if (likely(sem->count > 0))
-		sem->count--;
+		__sem_acquire(sem);
 	else
 		__down(sem);
 	raw_spin_unlock_irqrestore(&sem->lock, flags);
@@ -83,7 +119,7 @@ int __sched down_interruptible(struct semaphore *sem)
 	might_sleep();
 	raw_spin_lock_irqsave(&sem->lock, flags);
 	if (likely(sem->count > 0))
-		sem->count--;
+		__sem_acquire(sem);
 	else
 		result = __down_interruptible(sem);
 	raw_spin_unlock_irqrestore(&sem->lock, flags);
@@ -110,7 +146,7 @@ int __sched down_killable(struct semaphore *sem)
 	might_sleep();
 	raw_spin_lock_irqsave(&sem->lock, flags);
 	if (likely(sem->count > 0))
-		sem->count--;
+		__sem_acquire(sem);
 	else
 		result = __down_killable(sem);
 	raw_spin_unlock_irqrestore(&sem->lock, flags);
@@ -140,7 +176,7 @@ int __sched down_trylock(struct semaphore *sem)
 	raw_spin_lock_irqsave(&sem->lock, flags);
 	count = sem->count - 1;
 	if (likely(count >= 0))
-		sem->count = count;
+		__sem_acquire(sem);
 	raw_spin_unlock_irqrestore(&sem->lock, flags);
 
 	return (count < 0);
@@ -165,7 +201,7 @@ int __sched down_timeout(struct semaphore *sem, long timeout)
 	might_sleep();
 	raw_spin_lock_irqsave(&sem->lock, flags);
 	if (likely(sem->count > 0))
-		sem->count--;
+		__sem_acquire(sem);
 	else
 		result = __down_timeout(sem, timeout);
 	raw_spin_unlock_irqrestore(&sem->lock, flags);
@@ -187,6 +223,9 @@ void __sched up(struct semaphore *sem)
 	DEFINE_WAKE_Q(wake_q);
 
 	raw_spin_lock_irqsave(&sem->lock, flags);
+
+	hung_task_sem_clear_if_holder(sem);
+
 	if (likely(list_empty(&sem->wait_list)))
 		sem->count++;
 	else
@@ -228,8 +267,10 @@ static inline int __sched ___down_common(struct semaphore *sem, long state,
 		raw_spin_unlock_irq(&sem->lock);
 		timeout = schedule_timeout(timeout);
 		raw_spin_lock_irq(&sem->lock);
-		if (waiter.up)
+		if (waiter.up) {
+			hung_task_sem_set_holder(sem);
 			return 0;
+		}
 	}
 
  timed_out:
@@ -246,10 +287,14 @@ static inline int __sched __down_common(struct semaphore *sem, long state,
 {
 	int ret;
 
+	hung_task_set_blocker(sem, BLOCKER_TYPE_SEM);
+
 	trace_contention_begin(sem, 0);
 	ret = ___down_common(sem, state, timeout);
 	trace_contention_end(sem, ret);
 
+	hung_task_clear_blocker();
+
 	return ret;
 }
 
diff --git a/kernel/module/Kconfig b/kernel/module/Kconfig
index d7762ef5949a..39278737bb68 100644
--- a/kernel/module/Kconfig
+++ b/kernel/module/Kconfig
@@ -192,6 +192,11 @@ config GENDWARFKSYMS
 	depends on !DEBUG_INFO_REDUCED && !DEBUG_INFO_SPLIT
 	# Requires ELF object files.
 	depends on !LTO
+	# To avoid conflicts with the discarded __gendwarfksyms_ptr symbols on
+	# X86, requires pahole before commit 47dcb534e253 ("btf_encoder: Stop
+	# indexing symbols for VARs") or after commit 9810758003ce ("btf_encoder:
+	# Verify 0 address DWARF variables are in ELF section").
+	depends on !X86 || !DEBUG_INFO_BTF || PAHOLE_VERSION < 128 || PAHOLE_VERSION > 129
 	help
 	  Calculate symbol versions from DWARF debugging information using
 	  gendwarfksyms. Requires DEBUG_INFO to be enabled.
diff --git a/kernel/module/internal.h b/kernel/module/internal.h
index 626cf8668a7e..8d74b0a21c82 100644
--- a/kernel/module/internal.h
+++ b/kernel/module/internal.h
@@ -322,8 +322,11 @@ int module_enable_rodata_ro(const struct module *mod);
 int module_enable_rodata_ro_after_init(const struct module *mod);
 int module_enable_data_nx(const struct module *mod);
 int module_enable_text_rox(const struct module *mod);
-int module_enforce_rwx_sections(Elf_Ehdr *hdr, Elf_Shdr *sechdrs,
-				char *secstrings, struct module *mod);
+int module_enforce_rwx_sections(const Elf_Ehdr *hdr, const Elf_Shdr *sechdrs,
+				const char *secstrings,
+				const struct module *mod);
+void module_mark_ro_after_init(const Elf_Ehdr *hdr, Elf_Shdr *sechdrs,
+			       const char *secstrings);
 
 #ifdef CONFIG_MODULE_SIG
 int module_sig_check(struct load_info *info, int flags);
diff --git a/kernel/module/main.c b/kernel/module/main.c
index a2859dc3eea6..413ac6ea3702 100644
--- a/kernel/module/main.c
+++ b/kernel/module/main.c
@@ -170,6 +170,30 @@ static inline void add_taint_module(struct module *mod, unsigned flag,
 }
 
 /*
+ * Like strncmp(), except s/-/_/g as per scripts/Makefile.lib:name-fix-token rule.
+ */
+static int mod_strncmp(const char *str_a, const char *str_b, size_t n)
+{
+	for (int i = 0; i < n; i++) {
+		char a = str_a[i];
+		char b = str_b[i];
+		int d;
+
+		if (a == '-') a = '_';
+		if (b == '-') b = '_';
+
+		d = a - b;
+		if (d)
+			return d;
+
+		if (!a)
+			break;
+	}
+
+	return 0;
+}
+
+/*
  * A thread that wants to hold a reference to a module only while it
  * is running can call this to safely exit.
  */
@@ -1083,6 +1107,46 @@ static char *get_modinfo(const struct load_info *info, const char *tag)
 	return get_next_modinfo(info, tag, NULL);
 }
 
+/**
+ * verify_module_namespace() - does @modname have access to this symbol's @namespace
+ * @namespace: export symbol namespace
+ * @modname: module name
+ *
+ * If @namespace is prefixed with "module:" to indicate it is a module namespace
+ * then test if @modname matches any of the comma separated patterns.
+ *
+ * The patterns only support tail-glob.
+ */
+static bool verify_module_namespace(const char *namespace, const char *modname)
+{
+	size_t len, modlen = strlen(modname);
+	const char *prefix = "module:";
+	const char *sep;
+	bool glob;
+
+	if (!strstarts(namespace, prefix))
+		return false;
+
+	for (namespace += strlen(prefix); *namespace; namespace = sep) {
+		sep = strchrnul(namespace, ',');
+		len = sep - namespace;
+
+		glob = false;
+		if (sep[-1] == '*') {
+			len--;
+			glob = true;
+		}
+
+		if (*sep)
+			sep++;
+
+		if (mod_strncmp(namespace, modname, len) == 0 && (glob || len == modlen))
+			return true;
+	}
+
+	return false;
+}
+
 static int verify_namespace_is_imported(const struct load_info *info,
 					const struct kernel_symbol *sym,
 					struct module *mod)
@@ -1092,6 +1156,10 @@ static int verify_namespace_is_imported(const struct load_info *info,
 
 	namespace = kernel_symbol_namespace(sym);
 	if (namespace && namespace[0]) {
+
+		if (verify_module_namespace(namespace, mod->name))
+			return 0;
+
 		for_each_modinfo_entry(imported_namespace, info, "import_ns") {
 			if (strcmp(namespace, imported_namespace) == 0)
 				return 0;
@@ -1562,12 +1630,11 @@ static void __layout_sections(struct module *mod, struct load_info *info, bool i
 {
 	unsigned int m, i;
 
+	/*
+	 * { Mask of required section header flags,
+	 *   Mask of excluded section header flags }
+	 */
 	static const unsigned long masks[][2] = {
-		/*
-		 * NOTE: all executable code must be the first section
-		 * in this array; otherwise modify the text_size
-		 * finder in the two loops below
-		 */
 		{ SHF_EXECINSTR | SHF_ALLOC, ARCH_SHF_SMALL },
 		{ SHF_ALLOC, SHF_WRITE | ARCH_SHF_SMALL },
 		{ SHF_RO_AFTER_INIT | SHF_ALLOC, ARCH_SHF_SMALL },
@@ -1659,15 +1726,30 @@ static void module_license_taint_check(struct module *mod, const char *license)
 	}
 }
 
-static void setup_modinfo(struct module *mod, struct load_info *info)
+static int setup_modinfo(struct module *mod, struct load_info *info)
 {
 	const struct module_attribute *attr;
+	char *imported_namespace;
 	int i;
 
 	for (i = 0; (attr = modinfo_attrs[i]); i++) {
 		if (attr->setup)
 			attr->setup(mod, get_modinfo(info, attr->attr.name));
 	}
+
+	for_each_modinfo_entry(imported_namespace, info, "import_ns") {
+		/*
+		 * 'module:' prefixed namespaces are implicit, disallow
+		 * explicit imports.
+		 */
+		if (strstarts(imported_namespace, "module:")) {
+			pr_err("%s: module tries to import module namespace: %s\n",
+			       mod->name, imported_namespace);
+			return -EPERM;
+		}
+	}
+
+	return 0;
 }
 
 static void free_modinfo(struct module *mod)
@@ -2768,7 +2850,6 @@ core_param(module_blacklist, module_blacklist, charp, 0400);
 static struct module *layout_and_allocate(struct load_info *info, int flags)
 {
 	struct module *mod;
-	unsigned int ndx;
 	int err;
 
 	/* Allow arches to frob section contents and sizes.  */
@@ -2786,22 +2867,11 @@ static struct module *layout_and_allocate(struct load_info *info, int flags)
 	info->sechdrs[info->index.pcpu].sh_flags &= ~(unsigned long)SHF_ALLOC;
 
 	/*
-	 * Mark ro_after_init section with SHF_RO_AFTER_INIT so that
-	 * layout_sections() can put it in the right place.
+	 * Mark relevant sections as SHF_RO_AFTER_INIT so layout_sections() can
+	 * put them in the right place.
 	 * Note: ro_after_init sections also have SHF_{WRITE,ALLOC} set.
 	 */
-	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;
+	module_mark_ro_after_init(info->hdr, info->sechdrs, info->secstrings);
 
 	/*
 	 * Determine total sizes, and put offsets in sh_entsize.  For now
@@ -2829,6 +2899,7 @@ static void module_deallocate(struct module *mod, struct load_info *info)
 {
 	percpu_modfree(mod);
 	module_arch_freeing_init(mod);
+	codetag_free_module_sections(mod);
 
 	free_mod_mem(mod);
 }
@@ -3335,7 +3406,9 @@ static int load_module(struct load_info *info, const char __user *uargs,
 		goto free_unload;
 
 	/* Set up MODINFO_ATTR fields */
-	setup_modinfo(mod, info);
+	err = setup_modinfo(mod, info);
+	if (err)
+		goto free_modinfo;
 
 	/* Fix up syms, so that st_value is a pointer to location. */
 	err = simplify_symbols(mod, info);
@@ -3398,11 +3471,12 @@ static int load_module(struct load_info *info, const char __user *uargs,
 			goto sysfs_cleanup;
 	}
 
+	if (codetag_load_module(mod))
+		goto sysfs_cleanup;
+
 	/* Get rid of temporary copy. */
 	free_copy(info, flags);
 
-	codetag_load_module(mod);
-
 	/* Done! */
 	trace_module_load(mod);
 
diff --git a/kernel/module/strict_rwx.c b/kernel/module/strict_rwx.c
index 03f4142cfbf4..8fd438529fbc 100644
--- a/kernel/module/strict_rwx.c
+++ b/kernel/module/strict_rwx.c
@@ -87,8 +87,9 @@ int module_enable_data_nx(const struct module *mod)
 	return 0;
 }
 
-int module_enforce_rwx_sections(Elf_Ehdr *hdr, Elf_Shdr *sechdrs,
-				char *secstrings, struct module *mod)
+int module_enforce_rwx_sections(const Elf_Ehdr *hdr, const Elf_Shdr *sechdrs,
+				const char *secstrings,
+				const struct module *mod)
 {
 	const unsigned long shf_wx = SHF_WRITE | SHF_EXECINSTR;
 	int i;
@@ -106,3 +107,45 @@ int module_enforce_rwx_sections(Elf_Ehdr *hdr, Elf_Shdr *sechdrs,
 
 	return 0;
 }
+
+static const char *const ro_after_init[] = {
+	/*
+	 * Section .data..ro_after_init holds data explicitly annotated by
+	 * __ro_after_init.
+	 */
+	".data..ro_after_init",
+
+	/*
+	 * Section __jump_table holds data structures that are never modified,
+	 * with the exception of entries that refer to code in the __init
+	 * section, which are marked as such at module load time.
+	 */
+	"__jump_table",
+
+#ifdef CONFIG_HAVE_STATIC_CALL_INLINE
+	/*
+	 * Section .static_call_sites holds data structures that need to be
+	 * sorted and processed at module load time but are never modified
+	 * afterwards.
+	 */
+	".static_call_sites",
+#endif
+};
+
+void module_mark_ro_after_init(const Elf_Ehdr *hdr, Elf_Shdr *sechdrs,
+			       const char *secstrings)
+{
+	int i, j;
+
+	for (i = 1; i < hdr->e_shnum; i++) {
+		Elf_Shdr *shdr = &sechdrs[i];
+
+		for (j = 0; j < ARRAY_SIZE(ro_after_init); j++) {
+			if (strcmp(secstrings + shdr->sh_name,
+				   ro_after_init[j]) == 0) {
+				shdr->sh_flags |= SHF_RO_AFTER_INIT;
+				break;
+			}
+		}
+	}
+}
diff --git a/kernel/nsproxy.c b/kernel/nsproxy.c
index c9d97ed20122..5f31fdff8a38 100644
--- a/kernel/nsproxy.c
+++ b/kernel/nsproxy.c
@@ -128,17 +128,13 @@ out_time:
 out_net:
 	put_cgroup_ns(new_nsp->cgroup_ns);
 out_cgroup:
-	if (new_nsp->pid_ns_for_children)
-		put_pid_ns(new_nsp->pid_ns_for_children);
+	put_pid_ns(new_nsp->pid_ns_for_children);
 out_pid:
-	if (new_nsp->ipc_ns)
-		put_ipc_ns(new_nsp->ipc_ns);
+	put_ipc_ns(new_nsp->ipc_ns);
 out_ipc:
-	if (new_nsp->uts_ns)
-		put_uts_ns(new_nsp->uts_ns);
+	put_uts_ns(new_nsp->uts_ns);
 out_uts:
-	if (new_nsp->mnt_ns)
-		put_mnt_ns(new_nsp->mnt_ns);
+	put_mnt_ns(new_nsp->mnt_ns);
 out_ns:
 	kmem_cache_free(nsproxy_cachep, new_nsp);
 	return ERR_PTR(err);
@@ -189,18 +185,12 @@ int copy_namespaces(unsigned long flags, struct task_struct *tsk)
 
 void free_nsproxy(struct nsproxy *ns)
 {
-	if (ns->mnt_ns)
-		put_mnt_ns(ns->mnt_ns);
-	if (ns->uts_ns)
-		put_uts_ns(ns->uts_ns);
-	if (ns->ipc_ns)
-		put_ipc_ns(ns->ipc_ns);
-	if (ns->pid_ns_for_children)
-		put_pid_ns(ns->pid_ns_for_children);
-	if (ns->time_ns)
-		put_time_ns(ns->time_ns);
-	if (ns->time_ns_for_children)
-		put_time_ns(ns->time_ns_for_children);
+	put_mnt_ns(ns->mnt_ns);
+	put_uts_ns(ns->uts_ns);
+	put_ipc_ns(ns->ipc_ns);
+	put_pid_ns(ns->pid_ns_for_children);
+	put_time_ns(ns->time_ns);
+	put_time_ns(ns->time_ns_for_children);
 	put_cgroup_ns(ns->cgroup_ns);
 	put_net(ns->net_ns);
 	kmem_cache_free(nsproxy_cachep, ns);
diff --git a/kernel/padata.c b/kernel/padata.c
index b3d4eacc4f5d..7eee94166357 100644
--- a/kernel/padata.c
+++ b/kernel/padata.c
@@ -358,7 +358,8 @@ static void padata_reorder(struct parallel_data *pd)
 		 * To avoid UAF issue, add pd ref here, and put pd ref after reorder_work finish.
 		 */
 		padata_get_pd(pd);
-		queue_work(pinst->serial_wq, &pd->reorder_work);
+		if (!queue_work(pinst->serial_wq, &pd->reorder_work))
+			padata_put_pd(pd);
 	}
 }
 
diff --git a/kernel/panic.c b/kernel/panic.c
index a3889f38153d..b0b9a8bf4560 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -97,6 +97,36 @@ static const struct ctl_table kern_panic_table[] = {
 	},
 #endif
 	{
+		.procname	= "panic",
+		.data		= &panic_timeout,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+	{
+		.procname	= "panic_on_oops",
+		.data		= &panic_on_oops,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+	{
+		.procname	= "panic_print",
+		.data		= &panic_print,
+		.maxlen		= sizeof(unsigned long),
+		.mode		= 0644,
+		.proc_handler	= proc_doulongvec_minmax,
+	},
+	{
+		.procname	= "panic_on_warn",
+		.data		= &panic_on_warn,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= SYSCTL_ONE,
+	},
+	{
 		.procname       = "warn_limit",
 		.data           = &warn_limit,
 		.maxlen         = sizeof(warn_limit),
@@ -277,12 +307,10 @@ static void panic_other_cpus_shutdown(bool crash_kexec)
 }
 
 /**
- *	panic - halt the system
- *	@fmt: The text string to print
- *
- *	Display a message, then perform cleanups.
+ * panic - halt the system
+ * @fmt: The text string to print
  *
- *	This function never returns.
+ * Display a message, then perform cleanups. This function never returns.
  */
 void panic(const char *fmt, ...)
 {
diff --git a/kernel/pid.c b/kernel/pid.c
index 4ac2ce46817f..8317bcbc7cf7 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -100,6 +100,7 @@ void put_pid(struct pid *pid)
 
 	ns = pid->numbers[pid->level].ns;
 	if (refcount_dec_and_test(&pid->count)) {
+		WARN_ON_ONCE(pid->stashed);
 		kmem_cache_free(ns->pid_cachep, pid);
 		put_pid_ns(ns);
 	}
@@ -359,11 +360,6 @@ static void __change_pid(struct pid **pids, struct task_struct *task,
 	hlist_del_rcu(&task->pid_links[type]);
 	*pid_ptr = new;
 
-	if (type == PIDTYPE_PID) {
-		WARN_ON_ONCE(pid_has_task(pid, PIDTYPE_PID));
-		wake_up_all(&pid->wait_pidfd);
-	}
-
 	for (tmp = PIDTYPE_MAX; --tmp >= 0; )
 		if (pid_has_task(pid, tmp))
 			return;
diff --git a/kernel/power/energy_model.c b/kernel/power/energy_model.c
index d9b7e2b38c7a..ea7995a25780 100644
--- a/kernel/power/energy_model.c
+++ b/kernel/power/energy_model.c
@@ -233,6 +233,10 @@ static int em_compute_costs(struct device *dev, struct em_perf_state *table,
 	unsigned long prev_cost = ULONG_MAX;
 	int i, ret;
 
+	/* This is needed only for CPUs and EAS skip other devices */
+	if (!_is_cpu_device(dev))
+		return 0;
+
 	/* Compute the cost of each performance state. */
 	for (i = nr_states - 1; i >= 0; i--) {
 		unsigned long power_res, cost;
@@ -698,10 +702,12 @@ static int em_recalc_and_update(struct device *dev, struct em_perf_domain *pd,
 {
 	int ret;
 
-	ret = em_compute_costs(dev, em_table->state, NULL, pd->nr_perf_states,
-			       pd->flags);
-	if (ret)
-		goto free_em_table;
+	if (!em_is_artificial(pd)) {
+		ret = em_compute_costs(dev, em_table->state, NULL,
+				       pd->nr_perf_states, pd->flags);
+		if (ret)
+			goto free_em_table;
+	}
 
 	ret = em_dev_update_perf_domain(dev, em_table);
 	if (ret)
@@ -721,10 +727,24 @@ free_em_table:
  * Adjustment of CPU performance values after boot, when all CPUs capacites
  * are correctly calculated.
  */
-static void em_adjust_new_capacity(struct device *dev,
+static void em_adjust_new_capacity(unsigned int cpu, struct device *dev,
 				   struct em_perf_domain *pd)
 {
+	unsigned long cpu_capacity = arch_scale_cpu_capacity(cpu);
 	struct em_perf_table *em_table;
+	struct em_perf_state *table;
+	unsigned long em_max_perf;
+
+	rcu_read_lock();
+	table = em_perf_state_from_pd(pd);
+	em_max_perf = table[pd->nr_perf_states - 1].performance;
+	rcu_read_unlock();
+
+	if (em_max_perf == cpu_capacity)
+		return;
+
+	pr_debug("updating cpu%d cpu_cap=%lu old capacity=%lu\n", cpu,
+		 cpu_capacity, em_max_perf);
 
 	em_table = em_table_dup(pd);
 	if (!em_table) {
@@ -737,12 +757,27 @@ static void em_adjust_new_capacity(struct device *dev,
 	em_recalc_and_update(dev, pd, em_table);
 }
 
+/**
+ * em_adjust_cpu_capacity() - Adjust the EM for a CPU after a capacity update.
+ * @cpu: Target CPU.
+ *
+ * Adjust the existing EM for @cpu after a capacity update under the assumption
+ * that the capacity has been updated in the same way for all of the CPUs in
+ * the same perf domain.
+ */
+void em_adjust_cpu_capacity(unsigned int cpu)
+{
+	struct device *dev = get_cpu_device(cpu);
+	struct em_perf_domain *pd;
+
+	pd = em_pd_get(dev);
+	if (pd)
+		em_adjust_new_capacity(cpu, dev, pd);
+}
+
 static void em_check_capacity_update(void)
 {
 	cpumask_var_t cpu_done_mask;
-	struct em_perf_state *table;
-	struct em_perf_domain *pd;
-	unsigned long cpu_capacity;
 	int cpu;
 
 	if (!zalloc_cpumask_var(&cpu_done_mask, GFP_KERNEL)) {
@@ -753,7 +788,7 @@ static void em_check_capacity_update(void)
 	/* Check if CPUs capacity has changed than update EM */
 	for_each_possible_cpu(cpu) {
 		struct cpufreq_policy *policy;
-		unsigned long em_max_perf;
+		struct em_perf_domain *pd;
 		struct device *dev;
 
 		if (cpumask_test_cpu(cpu, cpu_done_mask))
@@ -776,24 +811,7 @@ static void em_check_capacity_update(void)
 		cpumask_or(cpu_done_mask, cpu_done_mask,
 			   em_span_cpus(pd));
 
-		cpu_capacity = arch_scale_cpu_capacity(cpu);
-
-		rcu_read_lock();
-		table = em_perf_state_from_pd(pd);
-		em_max_perf = table[pd->nr_perf_states - 1].performance;
-		rcu_read_unlock();
-
-		/*
-		 * Check if the CPU capacity has been adjusted during boot
-		 * and trigger the update for new performance values.
-		 */
-		if (em_max_perf == cpu_capacity)
-			continue;
-
-		pr_debug("updating cpu%d cpu_cap=%lu old capacity=%lu\n",
-			 cpu, cpu_capacity, em_max_perf);
-
-		em_adjust_new_capacity(dev, pd);
+		em_adjust_new_capacity(cpu, dev, pd);
 	}
 
 	free_cpumask_var(cpu_done_mask);
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index 23c0f4e6cb2f..519fb09de5e0 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -90,6 +90,11 @@ void hibernate_release(void)
 	atomic_inc(&hibernate_atomic);
 }
 
+bool hibernation_in_progress(void)
+{
+	return !atomic_read(&hibernate_atomic);
+}
+
 bool hibernation_available(void)
 {
 	return nohibernate == 0 &&
@@ -133,10 +138,15 @@ bool system_entering_hibernation(void)
 EXPORT_SYMBOL(system_entering_hibernation);
 
 #ifdef CONFIG_PM_DEBUG
+static unsigned int pm_test_delay = 5;
+module_param(pm_test_delay, uint, 0644);
+MODULE_PARM_DESC(pm_test_delay,
+		 "Number of seconds to wait before resuming from hibernation test");
 static void hibernation_debug_sleep(void)
 {
-	pr_info("debug: Waiting for 5 seconds.\n");
-	mdelay(5000);
+	pr_info("hibernation debug: Waiting for %d second(s).\n",
+		pm_test_delay);
+	mdelay(pm_test_delay * 1000);
 }
 
 static int hibernation_test(int level)
@@ -757,7 +767,7 @@ int hibernate(void)
 	 * Query for the compression algorithm support if compression is enabled.
 	 */
 	if (!nocompress) {
-		strscpy(hib_comp_algo, hibernate_compressor, sizeof(hib_comp_algo));
+		strscpy(hib_comp_algo, hibernate_compressor);
 		if (!crypto_has_acomp(hib_comp_algo, 0, CRYPTO_ALG_ASYNC)) {
 			pr_err("%s compression is not available\n", hib_comp_algo);
 			return -EOPNOTSUPP;
@@ -778,6 +788,8 @@ int hibernate(void)
 		goto Restore;
 
 	ksys_sync_helper();
+	if (filesystem_freeze_enabled)
+		filesystems_freeze();
 
 	error = freeze_processes();
 	if (error)
@@ -846,6 +858,7 @@ int hibernate(void)
 	/* Don't bother checking whether freezer_test_done is true */
 	freezer_test_done = false;
  Exit:
+	filesystems_thaw();
 	pm_notifier_call_chain(PM_POST_HIBERNATION);
  Restore:
 	pm_restore_console();
@@ -882,6 +895,9 @@ int hibernate_quiet_exec(int (*func)(void *data), void *data)
 	if (error)
 		goto restore;
 
+	if (filesystem_freeze_enabled)
+		filesystems_freeze();
+
 	error = freeze_processes();
 	if (error)
 		goto exit;
@@ -941,6 +957,7 @@ thaw:
 	thaw_processes();
 
 exit:
+	filesystems_thaw();
 	pm_notifier_call_chain(PM_POST_HIBERNATION);
 
 restore:
@@ -1006,9 +1023,9 @@ static int software_resume(void)
 	 */
 	if (!(swsusp_header_flags & SF_NOCOMPRESS_MODE)) {
 		if (swsusp_header_flags & SF_COMPRESSION_ALG_LZ4)
-			strscpy(hib_comp_algo, COMPRESSION_ALGO_LZ4, sizeof(hib_comp_algo));
+			strscpy(hib_comp_algo, COMPRESSION_ALGO_LZ4);
 		else
-			strscpy(hib_comp_algo, COMPRESSION_ALGO_LZO, sizeof(hib_comp_algo));
+			strscpy(hib_comp_algo, COMPRESSION_ALGO_LZO);
 		if (!crypto_has_acomp(hib_comp_algo, 0, CRYPTO_ALG_ASYNC)) {
 			pr_err("%s compression is not available\n", hib_comp_algo);
 			error = -EOPNOTSUPP;
@@ -1029,19 +1046,26 @@ static int software_resume(void)
 	if (error)
 		goto Restore;
 
+	if (filesystem_freeze_enabled)
+		filesystems_freeze();
+
 	pm_pr_dbg("Preparing processes for hibernation restore.\n");
 	error = freeze_processes();
-	if (error)
+	if (error) {
+		filesystems_thaw();
 		goto Close_Finish;
+	}
 
 	error = freeze_kernel_threads();
 	if (error) {
 		thaw_processes();
+		filesystems_thaw();
 		goto Close_Finish;
 	}
 
 	error = load_image_and_restore();
 	thaw_processes();
+	filesystems_thaw();
  Finish:
 	pm_notifier_call_chain(PM_POST_RESTORE);
  Restore:
@@ -1456,8 +1480,7 @@ static int hibernate_compressor_param_set(const char *compressor,
 	if (index >= 0) {
 		ret = param_set_copystring(comp_alg_enabled[index], kp);
 		if (!ret)
-			strscpy(hib_comp_algo, comp_alg_enabled[index],
-				sizeof(hib_comp_algo));
+			strscpy(hib_comp_algo, comp_alg_enabled[index]);
 	} else {
 		ret = index;
 	}
diff --git a/kernel/power/main.c b/kernel/power/main.c
index 6254814d4817..3d484630505a 100644
--- a/kernel/power/main.c
+++ b/kernel/power/main.c
@@ -557,6 +557,10 @@ static int __init pm_debugfs_init(void)
 late_initcall(pm_debugfs_init);
 #endif /* CONFIG_DEBUG_FS */
 
+bool pm_sleep_transition_in_progress(void)
+{
+	return pm_suspend_in_progress() || hibernation_in_progress();
+}
 #endif /* CONFIG_PM_SLEEP */
 
 #ifdef CONFIG_PM_SLEEP_DEBUG
@@ -594,7 +598,7 @@ power_attr(pm_print_times);
 
 static inline void pm_print_times_init(void)
 {
-	pm_print_times_enabled = !!initcall_debug;
+	pm_print_times_enabled = initcall_debug;
 }
 
 static ssize_t pm_wakeup_irq_show(struct kobject *kobj,
@@ -613,7 +617,7 @@ bool pm_debug_messages_on __read_mostly;
 
 bool pm_debug_messages_should_print(void)
 {
-	return pm_debug_messages_on && pm_suspend_target_state != PM_SUSPEND_ON;
+	return pm_debug_messages_on && pm_sleep_transition_in_progress();
 }
 EXPORT_SYMBOL_GPL(pm_debug_messages_should_print);
 
@@ -962,6 +966,34 @@ power_attr(pm_freeze_timeout);
 
 #endif	/* CONFIG_FREEZER*/
 
+#if defined(CONFIG_SUSPEND) || defined(CONFIG_HIBERNATION)
+bool filesystem_freeze_enabled = false;
+
+static ssize_t freeze_filesystems_show(struct kobject *kobj,
+				       struct kobj_attribute *attr, char *buf)
+{
+	return sysfs_emit(buf, "%d\n", filesystem_freeze_enabled);
+}
+
+static ssize_t freeze_filesystems_store(struct kobject *kobj,
+					struct kobj_attribute *attr,
+					const char *buf, size_t n)
+{
+	unsigned long val;
+
+	if (kstrtoul(buf, 10, &val))
+		return -EINVAL;
+
+	if (val > 1)
+		return -EINVAL;
+
+	filesystem_freeze_enabled = !!val;
+	return n;
+}
+
+power_attr(freeze_filesystems);
+#endif /* CONFIG_SUSPEND || CONFIG_HIBERNATION */
+
 static struct attribute * g[] = {
 	&state_attr.attr,
 #ifdef CONFIG_PM_TRACE
@@ -992,6 +1024,9 @@ static struct attribute * g[] = {
 #ifdef CONFIG_FREEZER
 	&pm_freeze_timeout_attr.attr,
 #endif
+#if defined(CONFIG_SUSPEND) || defined(CONFIG_HIBERNATION)
+	&freeze_filesystems_attr.attr,
+#endif
 	NULL,
 };
 
diff --git a/kernel/power/power.h b/kernel/power/power.h
index c352dea2f67b..cb1d71562002 100644
--- a/kernel/power/power.h
+++ b/kernel/power/power.h
@@ -18,6 +18,10 @@ struct swsusp_info {
 	unsigned long		size;
 } __aligned(PAGE_SIZE);
 
+#if defined(CONFIG_SUSPEND) || defined(CONFIG_HIBERNATION)
+extern bool filesystem_freeze_enabled;
+#endif
+
 #ifdef CONFIG_HIBERNATION
 /* kernel/power/snapshot.c */
 extern void __init hibernate_reserved_size_init(void);
@@ -71,10 +75,14 @@ extern void enable_restore_image_protection(void);
 static inline void enable_restore_image_protection(void) {}
 #endif /* CONFIG_STRICT_KERNEL_RWX */
 
+extern bool hibernation_in_progress(void);
+
 #else /* !CONFIG_HIBERNATION */
 
 static inline void hibernate_reserved_size_init(void) {}
 static inline void hibernate_image_size_init(void) {}
+
+static inline bool hibernation_in_progress(void) { return false; }
 #endif /* !CONFIG_HIBERNATION */
 
 #define power_attr(_name) \
diff --git a/kernel/power/process.c b/kernel/power/process.c
index 66ac067d9ae6..dc0dfc349f22 100644
--- a/kernel/power/process.c
+++ b/kernel/power/process.c
@@ -189,7 +189,7 @@ void thaw_processes(void)
 
 	oom_killer_enable();
 
-	pr_info("Restarting tasks ... ");
+	pr_info("Restarting tasks: Starting\n");
 
 	__usermodehelper_set_disable_depth(UMH_FREEZING);
 	thaw_workqueues();
@@ -208,7 +208,7 @@ void thaw_processes(void)
 	usermodehelper_enable();
 
 	schedule();
-	pr_cont("done.\n");
+	pr_info("Restarting tasks: Done\n");
 	trace_suspend_resume(TPS("thaw_processes"), 0, false);
 }
 
@@ -217,7 +217,7 @@ void thaw_kernel_threads(void)
 	struct task_struct *g, *p;
 
 	pm_nosig_freezing = false;
-	pr_info("Restarting kernel threads ... ");
+	pr_info("Restarting kernel threads ...\n");
 
 	thaw_workqueues();
 
@@ -229,5 +229,5 @@ void thaw_kernel_threads(void)
 	read_unlock(&tasklist_lock);
 
 	schedule();
-	pr_cont("done.\n");
+	pr_info("Done restarting kernel threads.\n");
 }
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index 4e6e24e8b854..2af36cfe35cd 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -1094,16 +1094,15 @@ static void mark_nosave_pages(struct memory_bitmap *bm)
 			 ((unsigned long long) region->end_pfn << PAGE_SHIFT)
 				- 1);
 
-		for (pfn = region->start_pfn; pfn < region->end_pfn; pfn++)
-			if (pfn_valid(pfn)) {
-				/*
-				 * It is safe to ignore the result of
-				 * mem_bm_set_bit_check() here, since we won't
-				 * touch the PFNs for which the error is
-				 * returned anyway.
-				 */
-				mem_bm_set_bit_check(bm, pfn);
-			}
+		for_each_valid_pfn(pfn, region->start_pfn, region->end_pfn) {
+			/*
+			 * It is safe to ignore the result of
+			 * mem_bm_set_bit_check() here, since we won't
+			 * touch the PFNs for which the error is
+			 * returned anyway.
+			 */
+			mem_bm_set_bit_check(bm, pfn);
+		}
 	}
 }
 
@@ -1255,21 +1254,20 @@ static void mark_free_pages(struct zone *zone)
 	spin_lock_irqsave(&zone->lock, flags);
 
 	max_zone_pfn = zone_end_pfn(zone);
-	for (pfn = zone->zone_start_pfn; pfn < max_zone_pfn; pfn++)
-		if (pfn_valid(pfn)) {
-			page = pfn_to_page(pfn);
+	for_each_valid_pfn(pfn, zone->zone_start_pfn, max_zone_pfn) {
+		page = pfn_to_page(pfn);
 
-			if (!--page_count) {
-				touch_nmi_watchdog();
-				page_count = WD_PAGE_COUNT;
-			}
+		if (!--page_count) {
+			touch_nmi_watchdog();
+			page_count = WD_PAGE_COUNT;
+		}
 
-			if (page_zone(page) != zone)
-				continue;
+		if (page_zone(page) != zone)
+			continue;
 
-			if (!swsusp_page_is_forbidden(page))
-				swsusp_unset_page_free(page);
-		}
+		if (!swsusp_page_is_forbidden(page))
+			swsusp_unset_page_free(page);
+	}
 
 	for_each_migratetype_order(order, t) {
 		list_for_each_entry(page,
diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
index 8eaec4ab121d..76b141b9aac0 100644
--- a/kernel/power/suspend.c
+++ b/kernel/power/suspend.c
@@ -30,6 +30,7 @@
 #include <trace/events/power.h>
 #include <linux/compiler.h>
 #include <linux/moduleparam.h>
+#include <linux/fs.h>
 
 #include "power.h"
 
@@ -374,6 +375,8 @@ static int suspend_prepare(suspend_state_t state)
 	if (error)
 		goto Restore;
 
+	if (filesystem_freeze_enabled)
+		filesystems_freeze();
 	trace_suspend_resume(TPS("freeze_processes"), 0, true);
 	error = suspend_freeze_processes();
 	trace_suspend_resume(TPS("freeze_processes"), 0, false);
@@ -550,6 +553,7 @@ int suspend_devices_and_enter(suspend_state_t state)
 static void suspend_finish(void)
 {
 	suspend_thaw_processes();
+	filesystems_thaw();
 	pm_notifier_call_chain(PM_POST_SUSPEND);
 	pm_restore_console();
 }
@@ -588,6 +592,8 @@ static int enter_state(suspend_state_t state)
 		ksys_sync_helper();
 		trace_suspend_resume(TPS("sync_filesystems"), 0, false);
 	}
+	if (filesystem_freeze_enabled)
+		filesystems_freeze();
 
 	pm_pr_dbg("Preparing system for sleep (%s)\n", mem_sleep_labels[state]);
 	pm_suspend_clear_flags();
@@ -609,6 +615,7 @@ static int enter_state(suspend_state_t state)
 	pm_pr_dbg("Finishing wakeup.\n");
 	suspend_finish();
  Unlock:
+	filesystems_thaw();
 	mutex_unlock(&system_transition_mutex);
 	return error;
 }
diff --git a/kernel/power/swap.c b/kernel/power/swap.c
index 80ff5f933a62..ad13c461b657 100644
--- a/kernel/power/swap.c
+++ b/kernel/power/swap.c
@@ -268,35 +268,26 @@ static void hib_end_io(struct bio *bio)
 	bio_put(bio);
 }
 
-static int hib_submit_io(blk_opf_t opf, pgoff_t page_off, void *addr,
+static int hib_submit_io_sync(blk_opf_t opf, pgoff_t page_off, void *addr)
+{
+	return bdev_rw_virt(file_bdev(hib_resume_bdev_file),
+			page_off * (PAGE_SIZE >> 9), addr, PAGE_SIZE, opf);
+}
+
+static int hib_submit_io_async(blk_opf_t opf, pgoff_t page_off, void *addr,
 			 struct hib_bio_batch *hb)
 {
-	struct page *page = virt_to_page(addr);
 	struct bio *bio;
-	int error = 0;
 
 	bio = bio_alloc(file_bdev(hib_resume_bdev_file), 1, opf,
 			GFP_NOIO | __GFP_HIGH);
 	bio->bi_iter.bi_sector = page_off * (PAGE_SIZE >> 9);
-
-	if (bio_add_page(bio, page, PAGE_SIZE, 0) < PAGE_SIZE) {
-		pr_err("Adding page to bio failed at %llu\n",
-		       (unsigned long long)bio->bi_iter.bi_sector);
-		bio_put(bio);
-		return -EFAULT;
-	}
-
-	if (hb) {
-		bio->bi_end_io = hib_end_io;
-		bio->bi_private = hb;
-		atomic_inc(&hb->count);
-		submit_bio(bio);
-	} else {
-		error = submit_bio_wait(bio);
-		bio_put(bio);
-	}
-
-	return error;
+	bio_add_virt_nofail(bio, addr, PAGE_SIZE);
+	bio->bi_end_io = hib_end_io;
+	bio->bi_private = hb;
+	atomic_inc(&hb->count);
+	submit_bio(bio);
+	return 0;
 }
 
 static int hib_wait_io(struct hib_bio_batch *hb)
@@ -316,7 +307,7 @@ static int mark_swapfiles(struct swap_map_handle *handle, unsigned int flags)
 {
 	int error;
 
-	hib_submit_io(REQ_OP_READ, swsusp_resume_block, swsusp_header, NULL);
+	hib_submit_io_sync(REQ_OP_READ, swsusp_resume_block, swsusp_header);
 	if (!memcmp("SWAP-SPACE",swsusp_header->sig, 10) ||
 	    !memcmp("SWAPSPACE2",swsusp_header->sig, 10)) {
 		memcpy(swsusp_header->orig_sig,swsusp_header->sig, 10);
@@ -329,8 +320,8 @@ static int mark_swapfiles(struct swap_map_handle *handle, unsigned int flags)
 		swsusp_header->flags = flags;
 		if (flags & SF_CRC32_MODE)
 			swsusp_header->crc32 = handle->crc32;
-		error = hib_submit_io(REQ_OP_WRITE | REQ_SYNC,
-				      swsusp_resume_block, swsusp_header, NULL);
+		error = hib_submit_io_sync(REQ_OP_WRITE | REQ_SYNC,
+				      swsusp_resume_block, swsusp_header);
 	} else {
 		pr_err("Swap header not found!\n");
 		error = -ENODEV;
@@ -380,36 +371,30 @@ static int swsusp_swap_check(void)
 
 static int write_page(void *buf, sector_t offset, struct hib_bio_batch *hb)
 {
+	gfp_t gfp = GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY;
 	void *src;
 	int ret;
 
 	if (!offset)
 		return -ENOSPC;
 
-	if (hb) {
-		src = (void *)__get_free_page(GFP_NOIO | __GFP_NOWARN |
-		                              __GFP_NORETRY);
-		if (src) {
-			copy_page(src, buf);
-		} else {
-			ret = hib_wait_io(hb); /* Free pages */
-			if (ret)
-				return ret;
-			src = (void *)__get_free_page(GFP_NOIO |
-			                              __GFP_NOWARN |
-			                              __GFP_NORETRY);
-			if (src) {
-				copy_page(src, buf);
-			} else {
-				WARN_ON_ONCE(1);
-				hb = NULL;	/* Go synchronous */
-				src = buf;
-			}
-		}
-	} else {
-		src = buf;
+	if (!hb)
+		goto sync_io;
+
+	src = (void *)__get_free_page(gfp);
+	if (!src) {
+		ret = hib_wait_io(hb); /* Free pages */
+		if (ret)
+			return ret;
+		src = (void *)__get_free_page(gfp);
+		if (WARN_ON_ONCE(!src))
+			goto sync_io;
 	}
-	return hib_submit_io(REQ_OP_WRITE | REQ_SYNC, offset, src, hb);
+
+	copy_page(src, buf);
+	return hib_submit_io_async(REQ_OP_WRITE | REQ_SYNC, offset, src, hb);
+sync_io:
+	return hib_submit_io_sync(REQ_OP_WRITE | REQ_SYNC, offset, buf);
 }
 
 static void release_swap_writer(struct swap_map_handle *handle)
@@ -1041,7 +1026,7 @@ static int get_swap_reader(struct swap_map_handle *handle,
 			return -ENOMEM;
 		}
 
-		error = hib_submit_io(REQ_OP_READ, offset, tmp->map, NULL);
+		error = hib_submit_io_sync(REQ_OP_READ, offset, tmp->map);
 		if (error) {
 			release_swap_reader(handle);
 			return error;
@@ -1065,7 +1050,10 @@ static int swap_read_page(struct swap_map_handle *handle, void *buf,
 	offset = handle->cur->entries[handle->k];
 	if (!offset)
 		return -EFAULT;
-	error = hib_submit_io(REQ_OP_READ, offset, buf, hb);
+	if (hb)
+		error = hib_submit_io_async(REQ_OP_READ, offset, buf, hb);
+	else
+		error = hib_submit_io_sync(REQ_OP_READ, offset, buf);
 	if (error)
 		return error;
 	if (++handle->k >= MAP_PAGE_ENTRIES) {
@@ -1590,8 +1578,8 @@ int swsusp_check(bool exclusive)
 				BLK_OPEN_READ, holder, NULL);
 	if (!IS_ERR(hib_resume_bdev_file)) {
 		clear_page(swsusp_header);
-		error = hib_submit_io(REQ_OP_READ, swsusp_resume_block,
-					swsusp_header, NULL);
+		error = hib_submit_io_sync(REQ_OP_READ, swsusp_resume_block,
+					swsusp_header);
 		if (error)
 			goto put;
 
@@ -1599,9 +1587,9 @@ int swsusp_check(bool exclusive)
 			memcpy(swsusp_header->sig, swsusp_header->orig_sig, 10);
 			swsusp_header_flags = swsusp_header->flags;
 			/* Reset swap signature now */
-			error = hib_submit_io(REQ_OP_WRITE | REQ_SYNC,
+			error = hib_submit_io_sync(REQ_OP_WRITE | REQ_SYNC,
 						swsusp_resume_block,
-						swsusp_header, NULL);
+						swsusp_header);
 		} else {
 			error = -EINVAL;
 		}
@@ -1650,13 +1638,12 @@ int swsusp_unmark(void)
 {
 	int error;
 
-	hib_submit_io(REQ_OP_READ, swsusp_resume_block,
-			swsusp_header, NULL);
+	hib_submit_io_sync(REQ_OP_READ, swsusp_resume_block, swsusp_header);
 	if (!memcmp(HIBERNATE_SIG,swsusp_header->sig, 10)) {
 		memcpy(swsusp_header->sig,swsusp_header->orig_sig, 10);
-		error = hib_submit_io(REQ_OP_WRITE | REQ_SYNC,
+		error = hib_submit_io_sync(REQ_OP_WRITE | REQ_SYNC,
 					swsusp_resume_block,
-					swsusp_header, NULL);
+					swsusp_header);
 	} else {
 		pr_err("Cannot find swsusp signature!\n");
 		error = -ENODEV;
diff --git a/kernel/power/wakelock.c b/kernel/power/wakelock.c
index 52571dcad768..4e941999a53b 100644
--- a/kernel/power/wakelock.c
+++ b/kernel/power/wakelock.c
@@ -49,6 +49,9 @@ ssize_t pm_show_wakelocks(char *buf, bool show_active)
 			len += sysfs_emit_at(buf, len, "%s ", wl->name);
 	}
 
+	if (len > 0)
+		--len;
+
 	len += sysfs_emit_at(buf, len, "\n");
 
 	mutex_unlock(&wakelocks_lock);
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index d5f89f9ef29f..75a84efad40f 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -921,7 +921,6 @@ ptrace_get_syscall_info_entry(struct task_struct *child, struct pt_regs *regs,
 	unsigned long args[ARRAY_SIZE(info->entry.args)];
 	int i;
 
-	info->op = PTRACE_SYSCALL_INFO_ENTRY;
 	info->entry.nr = syscall_get_nr(child, regs);
 	syscall_get_arguments(child, regs, args);
 	for (i = 0; i < ARRAY_SIZE(args); i++)
@@ -943,10 +942,12 @@ ptrace_get_syscall_info_seccomp(struct task_struct *child, struct pt_regs *regs,
 	 * diverge significantly enough.
 	 */
 	ptrace_get_syscall_info_entry(child, regs, info);
-	info->op = PTRACE_SYSCALL_INFO_SECCOMP;
 	info->seccomp.ret_data = child->ptrace_message;
 
-	/* ret_data is the last field in struct ptrace_syscall_info.seccomp */
+	/*
+	 * ret_data is the last non-reserved field
+	 * in struct ptrace_syscall_info.seccomp
+	 */
 	return offsetofend(struct ptrace_syscall_info, seccomp.ret_data);
 }
 
@@ -954,7 +955,6 @@ static unsigned long
 ptrace_get_syscall_info_exit(struct task_struct *child, struct pt_regs *regs,
 			     struct ptrace_syscall_info *info)
 {
-	info->op = PTRACE_SYSCALL_INFO_EXIT;
 	info->exit.rval = syscall_get_error(child, regs);
 	info->exit.is_error = !!info->exit.rval;
 	if (!info->exit.is_error)
@@ -965,19 +965,8 @@ ptrace_get_syscall_info_exit(struct task_struct *child, struct pt_regs *regs,
 }
 
 static int
-ptrace_get_syscall_info(struct task_struct *child, unsigned long user_size,
-			void __user *datavp)
+ptrace_get_syscall_info_op(struct task_struct *child)
 {
-	struct pt_regs *regs = task_pt_regs(child);
-	struct ptrace_syscall_info info = {
-		.op = PTRACE_SYSCALL_INFO_NONE,
-		.arch = syscall_get_arch(child),
-		.instruction_pointer = instruction_pointer(regs),
-		.stack_pointer = user_stack_pointer(regs),
-	};
-	unsigned long actual_size = offsetof(struct ptrace_syscall_info, entry);
-	unsigned long write_size;
-
 	/*
 	 * This does not need lock_task_sighand() to access
 	 * child->last_siginfo because ptrace_freeze_traced()
@@ -988,24 +977,160 @@ ptrace_get_syscall_info(struct task_struct *child, unsigned long user_size,
 	case SIGTRAP | 0x80:
 		switch (child->ptrace_message) {
 		case PTRACE_EVENTMSG_SYSCALL_ENTRY:
-			actual_size = ptrace_get_syscall_info_entry(child, regs,
-								    &info);
-			break;
+			return PTRACE_SYSCALL_INFO_ENTRY;
 		case PTRACE_EVENTMSG_SYSCALL_EXIT:
-			actual_size = ptrace_get_syscall_info_exit(child, regs,
-								   &info);
-			break;
+			return PTRACE_SYSCALL_INFO_EXIT;
+		default:
+			return PTRACE_SYSCALL_INFO_NONE;
 		}
-		break;
 	case SIGTRAP | (PTRACE_EVENT_SECCOMP << 8):
-		actual_size = ptrace_get_syscall_info_seccomp(child, regs,
-							      &info);
+		return PTRACE_SYSCALL_INFO_SECCOMP;
+	default:
+		return PTRACE_SYSCALL_INFO_NONE;
+	}
+}
+
+static int
+ptrace_get_syscall_info(struct task_struct *child, unsigned long user_size,
+			void __user *datavp)
+{
+	struct pt_regs *regs = task_pt_regs(child);
+	struct ptrace_syscall_info info = {
+		.op = ptrace_get_syscall_info_op(child),
+		.arch = syscall_get_arch(child),
+		.instruction_pointer = instruction_pointer(regs),
+		.stack_pointer = user_stack_pointer(regs),
+	};
+	unsigned long actual_size = offsetof(struct ptrace_syscall_info, entry);
+	unsigned long write_size;
+
+	switch (info.op) {
+	case PTRACE_SYSCALL_INFO_ENTRY:
+		actual_size = ptrace_get_syscall_info_entry(child, regs, &info);
+		break;
+	case PTRACE_SYSCALL_INFO_EXIT:
+		actual_size = ptrace_get_syscall_info_exit(child, regs, &info);
+		break;
+	case PTRACE_SYSCALL_INFO_SECCOMP:
+		actual_size = ptrace_get_syscall_info_seccomp(child, regs, &info);
 		break;
 	}
 
 	write_size = min(actual_size, user_size);
 	return copy_to_user(datavp, &info, write_size) ? -EFAULT : actual_size;
 }
+
+static int
+ptrace_set_syscall_info_entry(struct task_struct *child, struct pt_regs *regs,
+			      struct ptrace_syscall_info *info)
+{
+	unsigned long args[ARRAY_SIZE(info->entry.args)];
+	int nr = info->entry.nr;
+	int i;
+
+	/*
+	 * Check that the syscall number specified in info->entry.nr
+	 * is either a value of type "int" or a sign-extended value
+	 * of type "int".
+	 */
+	if (nr != info->entry.nr)
+		return -ERANGE;
+
+	for (i = 0; i < ARRAY_SIZE(args); i++) {
+		args[i] = info->entry.args[i];
+		/*
+		 * Check that the syscall argument specified in
+		 * info->entry.args[i] is either a value of type
+		 * "unsigned long" or a sign-extended value of type "long".
+		 */
+		if (args[i] != info->entry.args[i])
+			return -ERANGE;
+	}
+
+	syscall_set_nr(child, regs, nr);
+	/*
+	 * If the syscall number is set to -1, setting syscall arguments is not
+	 * just pointless, it would also clobber the syscall return value on
+	 * those architectures that share the same register both for the first
+	 * argument of syscall and its return value.
+	 */
+	if (nr != -1)
+		syscall_set_arguments(child, regs, args);
+
+	return 0;
+}
+
+static int
+ptrace_set_syscall_info_seccomp(struct task_struct *child, struct pt_regs *regs,
+				struct ptrace_syscall_info *info)
+{
+	/*
+	 * info->entry is currently a subset of info->seccomp,
+	 * info->seccomp.ret_data is currently ignored.
+	 */
+	return ptrace_set_syscall_info_entry(child, regs, info);
+}
+
+static int
+ptrace_set_syscall_info_exit(struct task_struct *child, struct pt_regs *regs,
+			     struct ptrace_syscall_info *info)
+{
+	long rval = info->exit.rval;
+
+	/*
+	 * Check that the return value specified in info->exit.rval
+	 * is either a value of type "long" or a sign-extended value
+	 * of type "long".
+	 */
+	if (rval != info->exit.rval)
+		return -ERANGE;
+
+	if (info->exit.is_error)
+		syscall_set_return_value(child, regs, rval, 0);
+	else
+		syscall_set_return_value(child, regs, 0, rval);
+
+	return 0;
+}
+
+static int
+ptrace_set_syscall_info(struct task_struct *child, unsigned long user_size,
+			const void __user *datavp)
+{
+	struct pt_regs *regs = task_pt_regs(child);
+	struct ptrace_syscall_info info;
+
+	if (user_size < sizeof(info))
+		return -EINVAL;
+
+	/*
+	 * The compatibility is tracked by info.op and info.flags: if user-space
+	 * does not instruct us to use unknown extra bits from future versions
+	 * of ptrace_syscall_info, we are not going to read them either.
+	 */
+	if (copy_from_user(&info, datavp, sizeof(info)))
+		return -EFAULT;
+
+	/* Reserved for future use. */
+	if (info.flags || info.reserved)
+		return -EINVAL;
+
+	/* Changing the type of the system call stop is not supported yet. */
+	if (ptrace_get_syscall_info_op(child) != info.op)
+		return -EINVAL;
+
+	switch (info.op) {
+	case PTRACE_SYSCALL_INFO_ENTRY:
+		return ptrace_set_syscall_info_entry(child, regs, &info);
+	case PTRACE_SYSCALL_INFO_EXIT:
+		return ptrace_set_syscall_info_exit(child, regs, &info);
+	case PTRACE_SYSCALL_INFO_SECCOMP:
+		return ptrace_set_syscall_info_seccomp(child, regs, &info);
+	default:
+		/* Other types of system call stops are not supported yet. */
+		return -EINVAL;
+	}
+}
 #endif /* CONFIG_HAVE_ARCH_TRACEHOOK */
 
 int ptrace_request(struct task_struct *child, long request,
@@ -1224,6 +1349,10 @@ int ptrace_request(struct task_struct *child, long request,
 	case PTRACE_GET_SYSCALL_INFO:
 		ret = ptrace_get_syscall_info(child, addr, datavp);
 		break;
+
+	case PTRACE_SET_SYSCALL_INFO:
+		ret = ptrace_set_syscall_info(child, addr, datavp);
+		break;
 #endif
 
 	case PTRACE_SECCOMP_GET_FILTER:
diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h
index eed2951a4962..9cf01832a6c3 100644
--- a/kernel/rcu/rcu.h
+++ b/kernel/rcu/rcu.h
@@ -57,6 +57,9 @@
 /* Low-order bit definition for polled grace-period APIs. */
 #define RCU_GET_STATE_COMPLETED	0x1
 
+/* A complete grace period count */
+#define RCU_SEQ_GP (RCU_SEQ_STATE_MASK + 1)
+
 extern int sysctl_sched_rt_runtime;
 
 /*
@@ -157,12 +160,21 @@ static inline bool rcu_seq_done(unsigned long *sp, unsigned long s)
  * Given a snapshot from rcu_seq_snap(), determine whether or not a
  * full update-side operation has occurred, but do not allow the
  * (ULONG_MAX / 2) safety-factor/guard-band.
+ *
+ * The token returned by get_state_synchronize_rcu_full() is based on
+ * rcu_state.gp_seq but it is tested in poll_state_synchronize_rcu_full()
+ * against the root rnp->gp_seq. Since rcu_seq_start() is first called
+ * on rcu_state.gp_seq and only later reflected on the root rnp->gp_seq,
+ * it is possible that rcu_seq_snap(rcu_state.gp_seq) returns 2 full grace
+ * periods ahead of the root rnp->gp_seq. To prevent false-positives with the
+ * full polling API that a wrap around instantly completed the GP, when nothing
+ * like that happened, adjust for the 2 GPs in the ULONG_CMP_LT().
  */
 static inline bool rcu_seq_done_exact(unsigned long *sp, unsigned long s)
 {
 	unsigned long cur_s = READ_ONCE(*sp);
 
-	return ULONG_CMP_GE(cur_s, s) || ULONG_CMP_LT(cur_s, s - (3 * RCU_SEQ_STATE_MASK + 1));
+	return ULONG_CMP_GE(cur_s, s) || ULONG_CMP_LT(cur_s, s - (2 * RCU_SEQ_GP));
 }
 
 /*
@@ -572,6 +584,8 @@ void do_trace_rcu_torture_read(const char *rcutorturename,
 			       unsigned long c_old,
 			       unsigned long c);
 void rcu_gp_set_torture_wait(int duration);
+void rcu_set_gpwrap_lag(unsigned long lag);
+int rcu_get_gpwrap_count(int cpu);
 #else
 static inline void rcutorture_get_gp_data(int *flags, unsigned long *gp_seq)
 {
@@ -589,6 +603,8 @@ void do_trace_rcu_torture_read(const char *rcutorturename,
 	do { } while (0)
 #endif
 static inline void rcu_gp_set_torture_wait(int duration) { }
+static inline void rcu_set_gpwrap_lag(unsigned long lag) { }
+static inline int rcu_get_gpwrap_count(int cpu) { return 0; }
 #endif
 unsigned long long rcutorture_gather_gp_seqs(void);
 void rcutorture_format_gp_seqs(unsigned long long seqs, char *cp, size_t len);
diff --git a/kernel/rcu/rcuscale.c b/kernel/rcu/rcuscale.c
index 0f3059b1b80d..b521d0455992 100644
--- a/kernel/rcu/rcuscale.c
+++ b/kernel/rcu/rcuscale.c
@@ -762,7 +762,7 @@ kfree_scale_thread(void *arg)
 		}
 
 		for (i = 0; i < kfree_alloc_num; i++) {
-			alloc_ptr = kmalloc(kfree_mult * sizeof(struct kfree_obj), GFP_KERNEL);
+			alloc_ptr = kcalloc(kfree_mult, sizeof(struct kfree_obj), GFP_KERNEL);
 			if (!alloc_ptr)
 				return -ENOMEM;
 
diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index 4fa7772be183..70ec0f21abc3 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -115,6 +115,10 @@ torture_param(int, nreaders, -1, "Number of RCU reader threads");
 torture_param(int, object_debug, 0, "Enable debug-object double call_rcu() testing");
 torture_param(int, onoff_holdoff, 0, "Time after boot before CPU hotplugs (s)");
 torture_param(int, onoff_interval, 0, "Time between CPU hotplugs (jiffies), 0=disable");
+torture_param(bool, gpwrap_lag, true, "Enable grace-period wrap lag testing");
+torture_param(int, gpwrap_lag_gps, 8, "Value to set for set_gpwrap_lag during an active testing period.");
+torture_param(int, gpwrap_lag_cycle_mins, 30, "Total cycle duration for gpwrap lag testing (in minutes)");
+torture_param(int, gpwrap_lag_active_mins, 5, "Duration for which gpwrap lag is active within each cycle (in minutes)");
 torture_param(int, nocbs_nthreads, 0, "Number of NOCB toggle threads, 0 to disable");
 torture_param(int, nocbs_toggle, 1000, "Time between toggling nocb state (ms)");
 torture_param(int, preempt_duration, 0, "Preemption duration (ms), zero to disable");
@@ -413,6 +417,8 @@ struct rcu_torture_ops {
 	bool (*reader_blocked)(void);
 	unsigned long long (*gather_gp_seqs)(void);
 	void (*format_gp_seqs)(unsigned long long seqs, char *cp, size_t len);
+	void (*set_gpwrap_lag)(unsigned long lag);
+	int (*get_gpwrap_count)(int cpu);
 	long cbflood_max;
 	int irq_capable;
 	int can_boost;
@@ -619,6 +625,8 @@ static struct rcu_torture_ops rcu_ops = {
 				  : NULL,
 	.gather_gp_seqs		= rcutorture_gather_gp_seqs,
 	.format_gp_seqs		= rcutorture_format_gp_seqs,
+	.set_gpwrap_lag		= rcu_set_gpwrap_lag,
+	.get_gpwrap_count	= rcu_get_gpwrap_count,
 	.irq_capable		= 1,
 	.can_boost		= IS_ENABLED(CONFIG_RCU_BOOST),
 	.extendables		= RCUTORTURE_MAX_EXTEND,
@@ -2164,53 +2172,70 @@ rcutorture_loop_extend(int *readstate, bool insoftirq, struct torture_random_sta
 	return &rtrsp[j];
 }
 
-/*
- * Do one read-side critical section, returning false if there was
- * no data to read.  Can be invoked both from process context and
- * from a timer handler.
- */
-static bool rcu_torture_one_read(struct torture_random_state *trsp, long myid)
-{
-	bool checkpolling = !(torture_random(trsp) & 0xfff);
+struct rcu_torture_one_read_state {
+	bool checkpolling;
 	unsigned long cookie;
 	struct rcu_gp_oldstate cookie_full;
-	int i;
 	unsigned long started;
-	unsigned long completed;
-	int newstate;
 	struct rcu_torture *p;
-	int pipe_count;
-	bool preempted = false;
-	int readstate = 0;
-	struct rt_read_seg rtseg[RCUTORTURE_RDR_MAX_SEGS] = { { 0 } };
-	struct rt_read_seg *rtrsp = &rtseg[0];
-	struct rt_read_seg *rtrsp1;
+	int readstate;
+	struct rt_read_seg rtseg[RCUTORTURE_RDR_MAX_SEGS];
+	struct rt_read_seg *rtrsp;
 	unsigned long long ts;
+};
 
-	WARN_ON_ONCE(!rcu_is_watching());
-	newstate = rcutorture_extend_mask(readstate, trsp);
-	rcutorture_one_extend(&readstate, newstate, myid < 0, trsp, rtrsp++);
-	if (checkpolling) {
+static void init_rcu_torture_one_read_state(struct rcu_torture_one_read_state *rtorsp,
+					    struct torture_random_state *trsp)
+{
+	memset(rtorsp, 0, sizeof(*rtorsp));
+	rtorsp->checkpolling = !(torture_random(trsp) & 0xfff);
+	rtorsp->rtrsp = &rtorsp->rtseg[0];
+}
+
+/*
+ * Set up the first segment of a series of overlapping read-side
+ * critical sections.  The caller must have actually initiated the
+ * outermost read-side critical section.
+ */
+static bool rcu_torture_one_read_start(struct rcu_torture_one_read_state *rtorsp,
+				       struct torture_random_state *trsp, long myid)
+{
+	if (rtorsp->checkpolling) {
 		if (cur_ops->get_gp_state && cur_ops->poll_gp_state)
-			cookie = cur_ops->get_gp_state();
+			rtorsp->cookie = cur_ops->get_gp_state();
 		if (cur_ops->get_gp_state_full && cur_ops->poll_gp_state_full)
-			cur_ops->get_gp_state_full(&cookie_full);
+			cur_ops->get_gp_state_full(&rtorsp->cookie_full);
 	}
-	started = cur_ops->get_gp_seq();
-	ts = rcu_trace_clock_local();
-	p = rcu_dereference_check(rcu_torture_current,
+	rtorsp->started = cur_ops->get_gp_seq();
+	rtorsp->ts = rcu_trace_clock_local();
+	rtorsp->p = rcu_dereference_check(rcu_torture_current,
 				  !cur_ops->readlock_held || cur_ops->readlock_held());
-	if (p == NULL) {
+	if (rtorsp->p == NULL) {
 		/* Wait for rcu_torture_writer to get underway */
-		rcutorture_one_extend(&readstate, 0, myid < 0, trsp, rtrsp);
+		rcutorture_one_extend(&rtorsp->readstate, 0, myid < 0, trsp, rtorsp->rtrsp);
 		return false;
 	}
-	if (p->rtort_mbtest == 0)
+	if (rtorsp->p->rtort_mbtest == 0)
 		atomic_inc(&n_rcu_torture_mberror);
-	rcu_torture_reader_do_mbchk(myid, p, trsp);
-	rtrsp = rcutorture_loop_extend(&readstate, myid < 0, trsp, rtrsp);
+	rcu_torture_reader_do_mbchk(myid, rtorsp->p, trsp);
+	return true;
+}
+
+/*
+ * Complete the last segment of a series of overlapping read-side
+ * critical sections and check for errors.
+ */
+static void rcu_torture_one_read_end(struct rcu_torture_one_read_state *rtorsp,
+				     struct torture_random_state *trsp, long myid)
+{
+	int i;
+	unsigned long completed;
+	int pipe_count;
+	bool preempted = false;
+	struct rt_read_seg *rtrsp1;
+
 	preempt_disable();
-	pipe_count = READ_ONCE(p->rtort_pipe_count);
+	pipe_count = READ_ONCE(rtorsp->p->rtort_pipe_count);
 	if (pipe_count > RCU_TORTURE_PIPE_LEN) {
 		// Should not happen in a correct RCU implementation,
 		// happens quite often for torture_type=busted.
@@ -2218,28 +2243,28 @@ static bool rcu_torture_one_read(struct torture_random_state *trsp, long myid)
 	}
 	completed = cur_ops->get_gp_seq();
 	if (pipe_count > 1) {
-		do_trace_rcu_torture_read(cur_ops->name, &p->rtort_rcu,
-					  ts, started, completed);
+		do_trace_rcu_torture_read(cur_ops->name, &rtorsp->p->rtort_rcu,
+					  rtorsp->ts, rtorsp->started, completed);
 		rcu_ftrace_dump(DUMP_ALL);
 	}
 	__this_cpu_inc(rcu_torture_count[pipe_count]);
-	completed = rcutorture_seq_diff(completed, started);
+	completed = rcutorture_seq_diff(completed, rtorsp->started);
 	if (completed > RCU_TORTURE_PIPE_LEN) {
 		/* Should not happen, but... */
 		completed = RCU_TORTURE_PIPE_LEN;
 	}
 	__this_cpu_inc(rcu_torture_batch[completed]);
 	preempt_enable();
-	if (checkpolling) {
+	if (rtorsp->checkpolling) {
 		if (cur_ops->get_gp_state && cur_ops->poll_gp_state)
-			WARN_ONCE(cur_ops->poll_gp_state(cookie),
+			WARN_ONCE(cur_ops->poll_gp_state(rtorsp->cookie),
 				  "%s: Cookie check 2 failed %s(%d) %lu->%lu\n",
 				  __func__,
 				  rcu_torture_writer_state_getname(),
 				  rcu_torture_writer_state,
-				  cookie, cur_ops->get_gp_state());
+				  rtorsp->cookie, cur_ops->get_gp_state());
 		if (cur_ops->get_gp_state_full && cur_ops->poll_gp_state_full)
-			WARN_ONCE(cur_ops->poll_gp_state_full(&cookie_full),
+			WARN_ONCE(cur_ops->poll_gp_state_full(&rtorsp->cookie_full),
 				  "%s: Cookie check 6 failed %s(%d) online %*pbl\n",
 				  __func__,
 				  rcu_torture_writer_state_getname(),
@@ -2248,21 +2273,42 @@ static bool rcu_torture_one_read(struct torture_random_state *trsp, long myid)
 	}
 	if (cur_ops->reader_blocked)
 		preempted = cur_ops->reader_blocked();
-	rcutorture_one_extend(&readstate, 0, myid < 0, trsp, rtrsp);
-	WARN_ON_ONCE(readstate);
+	rcutorture_one_extend(&rtorsp->readstate, 0, myid < 0, trsp, rtorsp->rtrsp);
+	WARN_ON_ONCE(rtorsp->readstate);
 	// This next splat is expected behavior if leakpointer, especially
 	// for CONFIG_RCU_STRICT_GRACE_PERIOD=y kernels.
-	WARN_ON_ONCE(leakpointer && READ_ONCE(p->rtort_pipe_count) > 1);
+	WARN_ON_ONCE(leakpointer && READ_ONCE(rtorsp->p->rtort_pipe_count) > 1);
 
 	/* If error or close call, record the sequence of reader protections. */
 	if ((pipe_count > 1 || completed > 1) && !xchg(&err_segs_recorded, 1)) {
 		i = 0;
-		for (rtrsp1 = &rtseg[0]; rtrsp1 < rtrsp; rtrsp1++)
+		for (rtrsp1 = &rtorsp->rtseg[0]; rtrsp1 < rtorsp->rtrsp; rtrsp1++)
 			err_segs[i++] = *rtrsp1;
 		rt_read_nsegs = i;
 		rt_read_preempted = preempted;
 	}
+}
 
+/*
+ * Do one read-side critical section, returning false if there was
+ * no data to read.  Can be invoked both from process context and
+ * from a timer handler.
+ */
+static bool rcu_torture_one_read(struct torture_random_state *trsp, long myid)
+{
+	int newstate;
+	struct rcu_torture_one_read_state rtors;
+
+	WARN_ON_ONCE(!rcu_is_watching());
+	init_rcu_torture_one_read_state(&rtors, trsp);
+	newstate = rcutorture_extend_mask(rtors.readstate, trsp);
+	rcutorture_one_extend(&rtors.readstate, newstate, myid < 0, trsp, rtors.rtrsp++);
+	if (!rcu_torture_one_read_start(&rtors, trsp, myid)) {
+		rcutorture_one_extend(&rtors.readstate, 0, myid < 0, trsp, rtors.rtrsp);
+		return false;
+	}
+	rtors.rtrsp = rcutorture_loop_extend(&rtors.readstate, myid < 0, trsp, rtors.rtrsp);
+	rcu_torture_one_read_end(&rtors, trsp, myid);
 	return true;
 }
 
@@ -2307,7 +2353,7 @@ rcu_torture_reader(void *arg)
 	set_user_nice(current, MAX_NICE);
 	if (irqreader && cur_ops->irq_capable)
 		timer_setup_on_stack(&t, rcu_torture_timer, 0);
-	tick_dep_set_task(current, TICK_DEP_BIT_RCU);
+	tick_dep_set_task(current, TICK_DEP_BIT_RCU);  // CPU bound, so need tick.
 	do {
 		if (irqreader && cur_ops->irq_capable) {
 			if (!timer_pending(&t))
@@ -2325,7 +2371,7 @@ rcu_torture_reader(void *arg)
 	} while (!torture_must_stop());
 	if (irqreader && cur_ops->irq_capable) {
 		timer_delete_sync(&t);
-		destroy_timer_on_stack(&t);
+		timer_destroy_on_stack(&t);
 	}
 	tick_dep_clear_task(current, TICK_DEP_BIT_RCU);
 	torture_kthread_stopping("rcu_torture_reader");
@@ -2394,6 +2440,7 @@ rcu_torture_stats_print(void)
 	int i;
 	long pipesummary[RCU_TORTURE_PIPE_LEN + 1] = { 0 };
 	long batchsummary[RCU_TORTURE_PIPE_LEN + 1] = { 0 };
+	long n_gpwraps = 0;
 	struct rcu_torture *rtcp;
 	static unsigned long rtcv_snap = ULONG_MAX;
 	static bool splatted;
@@ -2404,6 +2451,8 @@ rcu_torture_stats_print(void)
 			pipesummary[i] += READ_ONCE(per_cpu(rcu_torture_count, cpu)[i]);
 			batchsummary[i] += READ_ONCE(per_cpu(rcu_torture_batch, cpu)[i]);
 		}
+		if (cur_ops->get_gpwrap_count)
+			n_gpwraps += cur_ops->get_gpwrap_count(cpu);
 	}
 	for (i = RCU_TORTURE_PIPE_LEN; i >= 0; i--) {
 		if (pipesummary[i] != 0)
@@ -2435,8 +2484,9 @@ rcu_torture_stats_print(void)
 		data_race(n_barrier_attempts),
 		data_race(n_rcu_torture_barrier_error));
 	pr_cont("read-exits: %ld ", data_race(n_read_exits)); // Statistic.
-	pr_cont("nocb-toggles: %ld:%ld\n",
+	pr_cont("nocb-toggles: %ld:%ld ",
 		atomic_long_read(&n_nocb_offload), atomic_long_read(&n_nocb_deoffload));
+	pr_cont("gpwraps: %ld\n", n_gpwraps);
 
 	pr_alert("%s%s ", torture_type, TORTURE_FLAG);
 	if (atomic_read(&n_rcu_torture_mberror) ||
@@ -3036,7 +3086,7 @@ static void rcu_torture_fwd_prog_cr(struct rcu_fwd *rfp)
 	cver = READ_ONCE(rcu_torture_current_version);
 	gps = cur_ops->get_gp_seq();
 	rfp->rcu_launder_gp_seq_start = gps;
-	tick_dep_set_task(current, TICK_DEP_BIT_RCU);
+	tick_dep_set_task(current, TICK_DEP_BIT_RCU);  // CPU bound, so need tick.
 	while (time_before(jiffies, stopat) &&
 	       !shutdown_time_arrived() &&
 	       !READ_ONCE(rcu_fwd_emergency_stop) && !torture_must_stop()) {
@@ -3607,6 +3657,57 @@ static int rcu_torture_preempt(void *unused)
 
 static enum cpuhp_state rcutor_hp;
 
+static struct hrtimer gpwrap_lag_timer;
+static bool gpwrap_lag_active;
+
+/* Timer handler for toggling RCU grace-period sequence overflow test lag value */
+static enum hrtimer_restart rcu_gpwrap_lag_timer(struct hrtimer *timer)
+{
+	ktime_t next_delay;
+
+	if (gpwrap_lag_active) {
+		pr_alert("rcu-torture: Disabling gpwrap lag (value=0)\n");
+		cur_ops->set_gpwrap_lag(0);
+		gpwrap_lag_active = false;
+		next_delay = ktime_set((gpwrap_lag_cycle_mins - gpwrap_lag_active_mins) * 60, 0);
+	} else {
+		pr_alert("rcu-torture: Enabling gpwrap lag (value=%d)\n", gpwrap_lag_gps);
+		cur_ops->set_gpwrap_lag(gpwrap_lag_gps);
+		gpwrap_lag_active = true;
+		next_delay = ktime_set(gpwrap_lag_active_mins * 60, 0);
+	}
+
+	if (torture_must_stop_irq())
+		return HRTIMER_NORESTART;
+
+	hrtimer_forward_now(timer, next_delay);
+	return HRTIMER_RESTART;
+}
+
+static int rcu_gpwrap_lag_init(void)
+{
+	if (!gpwrap_lag)
+		return 0;
+
+	if (gpwrap_lag_cycle_mins <= 0 || gpwrap_lag_active_mins <= 0) {
+		pr_alert("rcu-torture: lag timing parameters must be positive\n");
+		return -EINVAL;
+	}
+
+	hrtimer_setup(&gpwrap_lag_timer, rcu_gpwrap_lag_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+	gpwrap_lag_active = false;
+	hrtimer_start(&gpwrap_lag_timer,
+		      ktime_set((gpwrap_lag_cycle_mins - gpwrap_lag_active_mins) * 60, 0), HRTIMER_MODE_REL);
+
+	return 0;
+}
+
+static void rcu_gpwrap_lag_cleanup(void)
+{
+	hrtimer_cancel(&gpwrap_lag_timer);
+	cur_ops->set_gpwrap_lag(0);
+	gpwrap_lag_active = false;
+}
 static void
 rcu_torture_cleanup(void)
 {
@@ -3776,6 +3877,9 @@ rcu_torture_cleanup(void)
 	torture_cleanup_end();
 	if (cur_ops->gp_slow_unregister)
 		cur_ops->gp_slow_unregister(NULL);
+
+	if (gpwrap_lag && cur_ops->set_gpwrap_lag)
+		rcu_gpwrap_lag_cleanup();
 }
 
 static void rcu_torture_leak_cb(struct rcu_head *rhp)
@@ -4272,9 +4376,17 @@ rcu_torture_init(void)
 	}
 	if (object_debug)
 		rcu_test_debug_objects();
-	torture_init_end();
+
 	if (cur_ops->gp_slow_register && !WARN_ON_ONCE(!cur_ops->gp_slow_unregister))
 		cur_ops->gp_slow_register(&rcu_fwd_cb_nodelay);
+
+	if (gpwrap_lag && cur_ops->set_gpwrap_lag) {
+		firsterr = rcu_gpwrap_lag_init();
+		if (torture_init_error(firsterr))
+			goto unwind;
+	}
+
+	torture_init_end();
 	return 0;
 
 unwind:
diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c
index 9a59b071501b..48047260697e 100644
--- a/kernel/rcu/srcutree.c
+++ b/kernel/rcu/srcutree.c
@@ -1589,7 +1589,7 @@ EXPORT_SYMBOL_GPL(start_poll_synchronize_srcu);
 bool poll_state_synchronize_srcu(struct srcu_struct *ssp, unsigned long cookie)
 {
 	if (cookie != SRCU_GET_STATE_COMPLETED &&
-	    !rcu_seq_done(&ssp->srcu_sup->srcu_gp_seq, cookie))
+	    !rcu_seq_done_exact(&ssp->srcu_sup->srcu_gp_seq, cookie))
 		return false;
 	// Ensure that the end of the SRCU grace period happens before
 	// any subsequent code that the caller might execute.
diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h
index c0cc7ae41106..f92443561d36 100644
--- a/kernel/rcu/tasks.h
+++ b/kernel/rcu/tasks.h
@@ -316,7 +316,8 @@ static void call_rcu_tasks_generic_timer(struct timer_list *tlp)
 	unsigned long flags;
 	bool needwake = false;
 	struct rcu_tasks *rtp;
-	struct rcu_tasks_percpu *rtpcp = from_timer(rtpcp, tlp, lazy_timer);
+	struct rcu_tasks_percpu *rtpcp = timer_container_of(rtpcp, tlp,
+						            lazy_timer);
 
 	rtp = rtpcp->rtpp;
 	raw_spin_lock_irqsave_rcu_node(rtpcp, flags);
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 659f83e71048..e8a4b720d7d2 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -80,6 +80,15 @@ static void rcu_sr_normal_gp_cleanup_work(struct work_struct *);
 static DEFINE_PER_CPU_SHARED_ALIGNED(struct rcu_data, rcu_data) = {
 	.gpwrap = true,
 };
+
+int rcu_get_gpwrap_count(int cpu)
+{
+	struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
+
+	return READ_ONCE(rdp->gpwrap_count);
+}
+EXPORT_SYMBOL_GPL(rcu_get_gpwrap_count);
+
 static struct rcu_state rcu_state = {
 	.level = { &rcu_state.node[0] },
 	.gp_state = RCU_GP_IDLE,
@@ -757,6 +766,25 @@ void rcu_request_urgent_qs_task(struct task_struct *t)
 	smp_store_release(per_cpu_ptr(&rcu_data.rcu_urgent_qs, cpu), true);
 }
 
+static unsigned long seq_gpwrap_lag = ULONG_MAX / 4;
+
+/**
+ * rcu_set_gpwrap_lag - Set RCU GP sequence overflow lag value.
+ * @lag_gps: Set overflow lag to this many grace period worth of counters
+ * which is used by rcutorture to quickly force a gpwrap situation.
+ * @lag_gps = 0 means we reset it back to the boot-time value.
+ */
+void rcu_set_gpwrap_lag(unsigned long lag_gps)
+{
+	unsigned long lag_seq_count;
+
+	lag_seq_count = (lag_gps == 0)
+			? ULONG_MAX / 4
+			: lag_gps << RCU_SEQ_CTR_SHIFT;
+	WRITE_ONCE(seq_gpwrap_lag, lag_seq_count);
+}
+EXPORT_SYMBOL_GPL(rcu_set_gpwrap_lag);
+
 /*
  * When trying to report a quiescent state on behalf of some other CPU,
  * it is our responsibility to check for and handle potential overflow
@@ -767,9 +795,11 @@ void rcu_request_urgent_qs_task(struct task_struct *t)
 static void rcu_gpnum_ovf(struct rcu_node *rnp, struct rcu_data *rdp)
 {
 	raw_lockdep_assert_held_rcu_node(rnp);
-	if (ULONG_CMP_LT(rcu_seq_current(&rdp->gp_seq) + ULONG_MAX / 4,
-			 rnp->gp_seq))
+	if (ULONG_CMP_LT(rcu_seq_current(&rdp->gp_seq) + seq_gpwrap_lag,
+			 rnp->gp_seq)) {
 		WRITE_ONCE(rdp->gpwrap, true);
+		WRITE_ONCE(rdp->gpwrap_count, READ_ONCE(rdp->gpwrap_count) + 1);
+	}
 	if (ULONG_CMP_LT(rdp->rcu_iw_gp_seq + ULONG_MAX / 4, rnp->gp_seq))
 		rdp->rcu_iw_gp_seq = rnp->gp_seq + ULONG_MAX / 4;
 }
@@ -801,6 +831,10 @@ static int rcu_watching_snap_save(struct rcu_data *rdp)
 	return 0;
 }
 
+#ifndef arch_irq_stat_cpu
+#define arch_irq_stat_cpu(cpu) 0
+#endif
+
 /*
  * Returns positive if the specified CPU has passed through a quiescent state
  * by virtue of being in or having passed through an dynticks idle state since
@@ -936,9 +970,9 @@ static int rcu_watching_snap_recheck(struct rcu_data *rdp)
 			rsrp->cputime_irq     = kcpustat_field(kcsp, CPUTIME_IRQ, cpu);
 			rsrp->cputime_softirq = kcpustat_field(kcsp, CPUTIME_SOFTIRQ, cpu);
 			rsrp->cputime_system  = kcpustat_field(kcsp, CPUTIME_SYSTEM, cpu);
-			rsrp->nr_hardirqs = kstat_cpu_irqs_sum(rdp->cpu);
-			rsrp->nr_softirqs = kstat_cpu_softirqs_sum(rdp->cpu);
-			rsrp->nr_csw = nr_context_switches_cpu(rdp->cpu);
+			rsrp->nr_hardirqs = kstat_cpu_irqs_sum(cpu) + arch_irq_stat_cpu(cpu);
+			rsrp->nr_softirqs = kstat_cpu_softirqs_sum(cpu);
+			rsrp->nr_csw = nr_context_switches_cpu(cpu);
 			rsrp->jiffies = jiffies;
 			rsrp->gp_seq = rdp->gp_seq;
 		}
@@ -1060,38 +1094,6 @@ static bool rcu_future_gp_cleanup(struct rcu_node *rnp)
 	return needmore;
 }
 
-static void swake_up_one_online_ipi(void *arg)
-{
-	struct swait_queue_head *wqh = arg;
-
-	swake_up_one(wqh);
-}
-
-static void swake_up_one_online(struct swait_queue_head *wqh)
-{
-	int cpu = get_cpu();
-
-	/*
-	 * If called from rcutree_report_cpu_starting(), wake up
-	 * is dangerous that late in the CPU-down hotplug process. The
-	 * scheduler might queue an ignored hrtimer. Defer the wake up
-	 * to an online CPU instead.
-	 */
-	if (unlikely(cpu_is_offline(cpu))) {
-		int target;
-
-		target = cpumask_any_and(housekeeping_cpumask(HK_TYPE_RCU),
-					 cpu_online_mask);
-
-		smp_call_function_single(target, swake_up_one_online_ipi,
-					 wqh, 0);
-		put_cpu();
-	} else {
-		put_cpu();
-		swake_up_one(wqh);
-	}
-}
-
 /*
  * Awaken the grace-period kthread.  Don't do a self-awaken (unless in an
  * interrupt or softirq handler, in which case we just might immediately
@@ -1116,7 +1118,7 @@ static void rcu_gp_kthread_wake(void)
 		return;
 	WRITE_ONCE(rcu_state.gp_wake_time, jiffies);
 	WRITE_ONCE(rcu_state.gp_wake_seq, READ_ONCE(rcu_state.gp_seq));
-	swake_up_one_online(&rcu_state.gp_wq);
+	swake_up_one(&rcu_state.gp_wq);
 }
 
 /*
@@ -1798,6 +1800,7 @@ static noinline_for_stack bool rcu_gp_init(void)
 	struct rcu_data *rdp;
 	struct rcu_node *rnp = rcu_get_root();
 	bool start_new_poll;
+	unsigned long old_gp_seq;
 
 	WRITE_ONCE(rcu_state.gp_activity, jiffies);
 	raw_spin_lock_irq_rcu_node(rnp);
@@ -1825,7 +1828,12 @@ static noinline_for_stack bool rcu_gp_init(void)
 	 */
 	start_new_poll = rcu_sr_normal_gp_init();
 	/* Record GP times before starting GP, hence rcu_seq_start(). */
+	old_gp_seq = rcu_state.gp_seq;
 	rcu_seq_start(&rcu_state.gp_seq);
+	/* Ensure that rcu_seq_done_exact() guardband doesn't give false positives. */
+	WARN_ON_ONCE(IS_ENABLED(CONFIG_PROVE_RCU) &&
+		     rcu_seq_done_exact(&old_gp_seq, rcu_seq_snap(&rcu_state.gp_seq)));
+
 	ASSERT_EXCLUSIVE_WRITER(rcu_state.gp_seq);
 	trace_rcu_grace_period(rcu_state.name, rcu_state.gp_seq, TPS("start"));
 	rcu_poll_gp_seq_start(&rcu_state.gp_seq_polled_snap);
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index a9a811d9d7a3..3830c19cf2f6 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -168,7 +168,7 @@ struct rcu_snap_record {
 	u64		cputime_irq;	/* Accumulated cputime of hard irqs */
 	u64		cputime_softirq;/* Accumulated cputime of soft irqs */
 	u64		cputime_system; /* Accumulated cputime of kernel tasks */
-	unsigned long	nr_hardirqs;	/* Accumulated number of hard irqs */
+	u64		nr_hardirqs;	/* Accumulated number of hard irqs */
 	unsigned int	nr_softirqs;	/* Accumulated number of soft irqs */
 	unsigned long long nr_csw;	/* Accumulated number of task switches */
 	unsigned long   jiffies;	/* Track jiffies value */
@@ -183,6 +183,7 @@ struct rcu_data {
 	bool		core_needs_qs;	/* Core waits for quiescent state. */
 	bool		beenonline;	/* CPU online at least once. */
 	bool		gpwrap;		/* Possible ->gp_seq wrap. */
+	unsigned int	gpwrap_count;	/* Count of GP sequence wrap. */
 	bool		cpu_started;	/* RCU watching this onlining CPU. */
 	struct rcu_node *mynode;	/* This CPU's leaf of hierarchy */
 	unsigned long grpmask;		/* Mask to apply to leaf qsmask. */
diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h
index 8d4895c854c5..c36c7d5575ca 100644
--- a/kernel/rcu/tree_exp.h
+++ b/kernel/rcu/tree_exp.h
@@ -200,7 +200,7 @@ static void __rcu_report_exp_rnp(struct rcu_node *rnp,
 		if (rnp->parent == NULL) {
 			raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 			if (wake)
-				swake_up_one_online(&rcu_state.expedited_wq);
+				swake_up_one(&rcu_state.expedited_wq);
 
 			break;
 		}
diff --git a/kernel/rcu/tree_nocb.h b/kernel/rcu/tree_nocb.h
index fa269d34167a..b473ff056f49 100644
--- a/kernel/rcu/tree_nocb.h
+++ b/kernel/rcu/tree_nocb.h
@@ -216,7 +216,7 @@ static bool __wake_nocb_gp(struct rcu_data *rdp_gp,
 	raw_spin_unlock_irqrestore(&rdp_gp->nocb_gp_lock, flags);
 	if (needwake) {
 		trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, TPS("DoWake"));
-		swake_up_one_online(&rdp_gp->nocb_gp_wq);
+		swake_up_one(&rdp_gp->nocb_gp_wq);
 	}
 
 	return needwake;
@@ -554,19 +554,13 @@ static void __call_rcu_nocb_wake(struct rcu_data *rdp, bool was_alldone,
 			rcu_nocb_unlock(rdp);
 			wake_nocb_gp_defer(rdp, RCU_NOCB_WAKE_LAZY,
 					   TPS("WakeLazy"));
-		} else if (!irqs_disabled_flags(flags) && cpu_online(rdp->cpu)) {
+		} else if (!irqs_disabled_flags(flags)) {
 			/* ... if queue was empty ... */
 			rcu_nocb_unlock(rdp);
 			wake_nocb_gp(rdp, false);
 			trace_rcu_nocb_wake(rcu_state.name, rdp->cpu,
 					    TPS("WakeEmpty"));
 		} else {
-			/*
-			 * Don't do the wake-up upfront on fragile paths.
-			 * Also offline CPUs can't call swake_up_one_online() from
-			 * (soft-)IRQs. Rely on the final deferred wake-up from
-			 * rcutree_report_cpu_dead()
-			 */
 			rcu_nocb_unlock(rdp);
 			wake_nocb_gp_defer(rdp, RCU_NOCB_WAKE,
 					   TPS("WakeEmptyIsDeferred"));
@@ -991,7 +985,7 @@ static bool do_nocb_deferred_wakeup_common(struct rcu_data *rdp_gp,
 static void do_nocb_deferred_wakeup_timer(struct timer_list *t)
 {
 	unsigned long flags;
-	struct rcu_data *rdp = from_timer(rdp, t, nocb_timer);
+	struct rcu_data *rdp = timer_container_of(rdp, t, nocb_timer);
 
 	WARN_ON_ONCE(rdp->nocb_gp_rdp != rdp);
 	trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, TPS("Timer"));
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 3c0bbbbb686f..0b0f56f6abc8 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -29,7 +29,7 @@ static bool rcu_rdp_is_offloaded(struct rcu_data *rdp)
 		  (IS_ENABLED(CONFIG_HOTPLUG_CPU) && lockdep_is_cpus_held()) ||
 		  lockdep_is_held(&rdp->nocb_lock) ||
 		  lockdep_is_held(&rcu_state.nocb_mutex) ||
-		  (!(IS_ENABLED(CONFIG_PREEMPT_COUNT) && preemptible()) &&
+		  ((!(IS_ENABLED(CONFIG_PREEMPT_COUNT) && preemptible()) || softirq_count()) &&
 		   rdp == this_cpu_ptr(&rcu_data)) ||
 		  rcu_current_is_nocb_kthread(rdp)),
 		"Unsafe read of RCU_NOCB offloaded state"
diff --git a/kernel/rcu/tree_stall.h b/kernel/rcu/tree_stall.h
index 925fcdad5dea..486c00536207 100644
--- a/kernel/rcu/tree_stall.h
+++ b/kernel/rcu/tree_stall.h
@@ -20,6 +20,28 @@
 int sysctl_panic_on_rcu_stall __read_mostly;
 int sysctl_max_rcu_stall_to_panic __read_mostly;
 
+#ifdef CONFIG_SYSFS
+
+static unsigned int rcu_stall_count;
+
+static ssize_t rcu_stall_count_show(struct kobject *kobj, struct kobj_attribute *attr,
+				    char *page)
+{
+	return sysfs_emit(page, "%u\n", rcu_stall_count);
+}
+
+static struct kobj_attribute rcu_stall_count_attr = __ATTR_RO(rcu_stall_count);
+
+static __init int kernel_rcu_stall_sysfs_init(void)
+{
+	sysfs_add_file_to_group(kernel_kobj, &rcu_stall_count_attr.attr, NULL);
+	return 0;
+}
+
+late_initcall(kernel_rcu_stall_sysfs_init);
+
+#endif // CONFIG_SYSFS
+
 #ifdef CONFIG_PROVE_RCU
 #define RCU_STALL_DELAY_DELTA		(5 * HZ)
 #else
@@ -435,8 +457,8 @@ static void print_cpu_stat_info(int cpu)
 	rsr.cputime_system  = kcpustat_field(kcsp, CPUTIME_SYSTEM, cpu);
 
 	pr_err("\t         hardirqs   softirqs   csw/system\n");
-	pr_err("\t number: %8ld %10d %12lld\n",
-		kstat_cpu_irqs_sum(cpu) - rsrp->nr_hardirqs,
+	pr_err("\t number: %8lld %10d %12lld\n",
+		kstat_cpu_irqs_sum(cpu) + arch_irq_stat_cpu(cpu) - rsrp->nr_hardirqs,
 		kstat_cpu_softirqs_sum(cpu) - rsrp->nr_softirqs,
 		nr_context_switches_cpu(cpu) - rsrp->nr_csw);
 	pr_err("\tcputime: %8lld %10lld %12lld   ==> %d(ms)\n",
@@ -784,6 +806,10 @@ static void check_cpu_stall(struct rcu_data *rdp)
 		if (kvm_check_and_clear_guest_paused())
 			return;
 
+#ifdef CONFIG_SYSFS
+		++rcu_stall_count;
+#endif
+
 		rcu_stall_notifier_call_chain(RCU_STALL_NOTIFY_NORM, (void *)j - gps);
 		if (READ_ONCE(csd_lock_suppress_rcu_stall) && csd_lock_is_stuck()) {
 			pr_err("INFO: %s detected stall, but suppressed full report due to a stuck CSD-lock.\n", rcu_state.name);
diff --git a/kernel/relay.c b/kernel/relay.c
index 5ac7e711e4b6..c0c93a04d4ce 100644
--- a/kernel/relay.c
+++ b/kernel/relay.c
@@ -452,7 +452,7 @@ int relay_prepare_cpu(unsigned int cpu)
 
 /**
  *	relay_open - create a new relay channel
- *	@base_filename: base name of files to create, %NULL for buffering only
+ *	@base_filename: base name of files to create
  *	@parent: dentry of parent directory, %NULL for root directory or buffer
  *	@subbuf_size: size of sub-buffers
  *	@n_subbufs: number of sub-buffers
@@ -465,10 +465,6 @@ int relay_prepare_cpu(unsigned int cpu)
  *	attributes specified.  The created channel buffer files
  *	will be named base_filename0...base_filenameN-1.  File
  *	permissions will be %S_IRUSR.
- *
- *	If opening a buffer (@parent = NULL) that you later wish to register
- *	in a filesystem, call relay_late_setup_files() once the @parent dentry
- *	is available.
  */
 struct rchan *relay_open(const char *base_filename,
 			 struct dentry *parent,
@@ -540,111 +536,6 @@ struct rchan_percpu_buf_dispatcher {
 	struct dentry *dentry;
 };
 
-/* Called in atomic context. */
-static void __relay_set_buf_dentry(void *info)
-{
-	struct rchan_percpu_buf_dispatcher *p = info;
-
-	relay_set_buf_dentry(p->buf, p->dentry);
-}
-
-/**
- *	relay_late_setup_files - triggers file creation
- *	@chan: channel to operate on
- *	@base_filename: base name of files to create
- *	@parent: dentry of parent directory, %NULL for root directory
- *
- *	Returns 0 if successful, non-zero otherwise.
- *
- *	Use to setup files for a previously buffer-only channel created
- *	by relay_open() with a NULL parent dentry.
- *
- *	For example, this is useful for perfomring early tracing in kernel,
- *	before VFS is up and then exposing the early results once the dentry
- *	is available.
- */
-int relay_late_setup_files(struct rchan *chan,
-			   const char *base_filename,
-			   struct dentry *parent)
-{
-	int err = 0;
-	unsigned int i, curr_cpu;
-	unsigned long flags;
-	struct dentry *dentry;
-	struct rchan_buf *buf;
-	struct rchan_percpu_buf_dispatcher disp;
-
-	if (!chan || !base_filename)
-		return -EINVAL;
-
-	strscpy(chan->base_filename, base_filename, NAME_MAX);
-
-	mutex_lock(&relay_channels_mutex);
-	/* Is chan already set up? */
-	if (unlikely(chan->has_base_filename)) {
-		mutex_unlock(&relay_channels_mutex);
-		return -EEXIST;
-	}
-	chan->has_base_filename = 1;
-	chan->parent = parent;
-
-	if (chan->is_global) {
-		err = -EINVAL;
-		buf = *per_cpu_ptr(chan->buf, 0);
-		if (!WARN_ON_ONCE(!buf)) {
-			dentry = relay_create_buf_file(chan, buf, 0);
-			if (dentry && !WARN_ON_ONCE(!chan->is_global)) {
-				relay_set_buf_dentry(buf, dentry);
-				err = 0;
-			}
-		}
-		mutex_unlock(&relay_channels_mutex);
-		return err;
-	}
-
-	curr_cpu = get_cpu();
-	/*
-	 * The CPU hotplug notifier ran before us and created buffers with
-	 * no files associated. So it's safe to call relay_setup_buf_file()
-	 * on all currently online CPUs.
-	 */
-	for_each_online_cpu(i) {
-		buf = *per_cpu_ptr(chan->buf, i);
-		if (unlikely(!buf)) {
-			WARN_ONCE(1, KERN_ERR "CPU has no buffer!\n");
-			err = -EINVAL;
-			break;
-		}
-
-		dentry = relay_create_buf_file(chan, buf, i);
-		if (unlikely(!dentry)) {
-			err = -EINVAL;
-			break;
-		}
-
-		if (curr_cpu == i) {
-			local_irq_save(flags);
-			relay_set_buf_dentry(buf, dentry);
-			local_irq_restore(flags);
-		} else {
-			disp.buf = buf;
-			disp.dentry = dentry;
-			smp_mb();
-			/* relay_channels_mutex must be held, so wait. */
-			err = smp_call_function_single(i,
-						       __relay_set_buf_dentry,
-						       &disp, 1);
-		}
-		if (unlikely(err))
-			break;
-	}
-	put_cpu();
-	mutex_unlock(&relay_channels_mutex);
-
-	return err;
-}
-EXPORT_SYMBOL_GPL(relay_late_setup_files);
-
 /**
  *	relay_switch_subbuf - switch to a new sub-buffer
  *	@buf: channel buffer
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index c81cf642dba0..dce50fa57471 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -66,6 +66,7 @@
 #include <linux/vtime.h>
 #include <linux/wait_api.h>
 #include <linux/workqueue_api.h>
+#include <linux/livepatch_sched.h>
 
 #ifdef CONFIG_PREEMPT_DYNAMIC
 # ifdef CONFIG_GENERIC_ENTRY
@@ -1752,7 +1753,7 @@ static inline void uclamp_rq_dec_id(struct rq *rq, struct task_struct *p,
 	}
 }
 
-static inline void uclamp_rq_inc(struct rq *rq, struct task_struct *p)
+static inline void uclamp_rq_inc(struct rq *rq, struct task_struct *p, int flags)
 {
 	enum uclamp_id clamp_id;
 
@@ -1768,7 +1769,8 @@ static inline void uclamp_rq_inc(struct rq *rq, struct task_struct *p)
 	if (unlikely(!p->sched_class->uclamp_enabled))
 		return;
 
-	if (p->se.sched_delayed)
+	/* Only inc the delayed task which being woken up. */
+	if (p->se.sched_delayed && !(flags & ENQUEUE_DELAYED))
 		return;
 
 	for_each_clamp_id(clamp_id)
@@ -2036,7 +2038,7 @@ static void __init init_uclamp(void)
 }
 
 #else /* !CONFIG_UCLAMP_TASK */
-static inline void uclamp_rq_inc(struct rq *rq, struct task_struct *p) { }
+static inline void uclamp_rq_inc(struct rq *rq, struct task_struct *p, int flags) { }
 static inline void uclamp_rq_dec(struct rq *rq, struct task_struct *p) { }
 static inline void uclamp_fork(struct task_struct *p) { }
 static inline void uclamp_post_fork(struct task_struct *p) { }
@@ -2072,12 +2074,14 @@ void enqueue_task(struct rq *rq, struct task_struct *p, int flags)
 	if (!(flags & ENQUEUE_NOCLOCK))
 		update_rq_clock(rq);
 
-	p->sched_class->enqueue_task(rq, p, flags);
 	/*
-	 * Must be after ->enqueue_task() because ENQUEUE_DELAYED can clear
-	 * ->sched_delayed.
+	 * Can be before ->enqueue_task() because uclamp considers the
+	 * ENQUEUE_DELAYED task before its ->sched_delayed gets cleared
+	 * in ->enqueue_task().
 	 */
-	uclamp_rq_inc(rq, p);
+	uclamp_rq_inc(rq, p, flags);
+
+	p->sched_class->enqueue_task(rq, p, flags);
 
 	psi_enqueue(p, flags);
 
@@ -2283,6 +2287,12 @@ unsigned long wait_task_inactive(struct task_struct *p, unsigned int match_state
 		 * just go back and repeat.
 		 */
 		rq = task_rq_lock(p, &rf);
+		/*
+		 * If task is sched_delayed, force dequeue it, to avoid always
+		 * hitting the tick timeout in the queued case
+		 */
+		if (p->se.sched_delayed)
+			dequeue_task(rq, p, DEQUEUE_SLEEP | DEQUEUE_DELAYED);
 		trace_sched_wait_task(p);
 		running = task_on_cpu(rq, p);
 		queued = task_on_rq_queued(p);
@@ -3352,6 +3362,10 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
 #ifdef CONFIG_NUMA_BALANCING
 static void __migrate_swap_task(struct task_struct *p, int cpu)
 {
+	__schedstat_inc(p->stats.numa_task_swapped);
+	count_vm_numa_event(NUMA_TASK_SWAP);
+	count_memcg_event_mm(p->mm, NUMA_TASK_SWAP);
+
 	if (task_on_rq_queued(p)) {
 		struct rq *src_rq, *dst_rq;
 		struct rq_flags srf, drf;
@@ -6571,12 +6585,14 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
  * Otherwise marks the task's __state as RUNNING
  */
 static bool try_to_block_task(struct rq *rq, struct task_struct *p,
-			      unsigned long task_state)
+			      unsigned long *task_state_p)
 {
+	unsigned long task_state = *task_state_p;
 	int flags = DEQUEUE_NOCLOCK;
 
 	if (signal_pending_state(task_state, p)) {
 		WRITE_ONCE(p->__state, TASK_RUNNING);
+		*task_state_p = TASK_RUNNING;
 		return false;
 	}
 
@@ -6668,6 +6684,8 @@ static void __sched notrace __schedule(int sched_mode)
 	if (sched_feat(HRTICK) || sched_feat(HRTICK_DL))
 		hrtick_clear(rq);
 
+	klp_sched_try_switch(prev);
+
 	local_irq_disable();
 	rcu_note_context_switch(preempt);
 
@@ -6713,7 +6731,7 @@ static void __sched notrace __schedule(int sched_mode)
 			goto picked;
 		}
 	} else if (!preempt && prev_state) {
-		try_to_block_task(rq, prev, prev_state);
+		try_to_block_task(rq, prev, &prev_state);
 		switch_count = &prev->nvcsw;
 	}
 
@@ -7328,7 +7346,6 @@ EXPORT_STATIC_CALL_TRAMP(might_resched);
 static DEFINE_STATIC_KEY_FALSE(sk_dynamic_cond_resched);
 int __sched dynamic_cond_resched(void)
 {
-	klp_sched_try_switch();
 	if (!static_branch_unlikely(&sk_dynamic_cond_resched))
 		return 0;
 	return __cond_resched();
@@ -7500,7 +7517,6 @@ int sched_dynamic_mode(const char *str)
 #endif
 
 static DEFINE_MUTEX(sched_dynamic_mutex);
-static bool klp_override;
 
 static void __sched_dynamic_update(int mode)
 {
@@ -7508,8 +7524,7 @@ static void __sched_dynamic_update(int mode)
 	 * Avoid {NONE,VOLUNTARY} -> FULL transitions from ever ending up in
 	 * the ZERO state, which is invalid.
 	 */
-	if (!klp_override)
-		preempt_dynamic_enable(cond_resched);
+	preempt_dynamic_enable(cond_resched);
 	preempt_dynamic_enable(might_resched);
 	preempt_dynamic_enable(preempt_schedule);
 	preempt_dynamic_enable(preempt_schedule_notrace);
@@ -7518,8 +7533,7 @@ static void __sched_dynamic_update(int mode)
 
 	switch (mode) {
 	case preempt_dynamic_none:
-		if (!klp_override)
-			preempt_dynamic_enable(cond_resched);
+		preempt_dynamic_enable(cond_resched);
 		preempt_dynamic_disable(might_resched);
 		preempt_dynamic_disable(preempt_schedule);
 		preempt_dynamic_disable(preempt_schedule_notrace);
@@ -7530,8 +7544,7 @@ static void __sched_dynamic_update(int mode)
 		break;
 
 	case preempt_dynamic_voluntary:
-		if (!klp_override)
-			preempt_dynamic_enable(cond_resched);
+		preempt_dynamic_enable(cond_resched);
 		preempt_dynamic_enable(might_resched);
 		preempt_dynamic_disable(preempt_schedule);
 		preempt_dynamic_disable(preempt_schedule_notrace);
@@ -7542,8 +7555,7 @@ static void __sched_dynamic_update(int mode)
 		break;
 
 	case preempt_dynamic_full:
-		if (!klp_override)
-			preempt_dynamic_disable(cond_resched);
+		preempt_dynamic_disable(cond_resched);
 		preempt_dynamic_disable(might_resched);
 		preempt_dynamic_enable(preempt_schedule);
 		preempt_dynamic_enable(preempt_schedule_notrace);
@@ -7554,8 +7566,7 @@ static void __sched_dynamic_update(int mode)
 		break;
 
 	case preempt_dynamic_lazy:
-		if (!klp_override)
-			preempt_dynamic_disable(cond_resched);
+		preempt_dynamic_disable(cond_resched);
 		preempt_dynamic_disable(might_resched);
 		preempt_dynamic_enable(preempt_schedule);
 		preempt_dynamic_enable(preempt_schedule_notrace);
@@ -7576,36 +7587,6 @@ void sched_dynamic_update(int mode)
 	mutex_unlock(&sched_dynamic_mutex);
 }
 
-#ifdef CONFIG_HAVE_PREEMPT_DYNAMIC_CALL
-
-static int klp_cond_resched(void)
-{
-	__klp_sched_try_switch();
-	return __cond_resched();
-}
-
-void sched_dynamic_klp_enable(void)
-{
-	mutex_lock(&sched_dynamic_mutex);
-
-	klp_override = true;
-	static_call_update(cond_resched, klp_cond_resched);
-
-	mutex_unlock(&sched_dynamic_mutex);
-}
-
-void sched_dynamic_klp_disable(void)
-{
-	mutex_lock(&sched_dynamic_mutex);
-
-	klp_override = false;
-	__sched_dynamic_update(preempt_dynamic_mode);
-
-	mutex_unlock(&sched_dynamic_mutex);
-}
-
-#endif /* CONFIG_HAVE_PREEMPT_DYNAMIC_CALL */
-
 static int __init setup_preempt_mode(char *str)
 {
 	int mode = sched_dynamic_mode(str);
@@ -7953,8 +7934,9 @@ int migrate_task_to(struct task_struct *p, int target_cpu)
 	if (!cpumask_test_cpu(target_cpu, p->cpus_ptr))
 		return -EINVAL;
 
-	/* TODO: This is not properly updating schedstats */
-
+	__schedstat_inc(p->stats.numa_task_migrated);
+	count_vm_numa_event(NUMA_TASK_MIGRATE);
+	count_memcg_event_mm(p->mm, NUMA_TASK_MIGRATE);
 	trace_sched_move_numa(p, curr_cpu, target_cpu);
 	return stop_one_cpu(curr_cpu, migration_cpu_stop, &arg);
 }
@@ -9018,7 +9000,7 @@ void sched_online_group(struct task_group *tg, struct task_group *parent)
 	unsigned long flags;
 
 	spin_lock_irqsave(&task_group_lock, flags);
-	list_add_rcu(&tg->list, &task_groups);
+	list_add_tail_rcu(&tg->list, &task_groups);
 
 	/* Root should already exist: */
 	WARN_ON(!parent);
@@ -9204,11 +9186,15 @@ static int cpu_cgroup_can_attach(struct cgroup_taskset *tset)
 	struct task_struct *task;
 	struct cgroup_subsys_state *css;
 
+	if (!rt_group_sched_enabled())
+		goto scx_check;
+
 	cgroup_taskset_for_each(task, css, tset) {
 		if (!sched_rt_can_attach(css_tg(css), task))
 			return -EINVAL;
 	}
-#endif
+scx_check:
+#endif /* CONFIG_RT_GROUP_SCHED */
 	return scx_cgroup_can_attach(tset);
 }
 
@@ -9861,18 +9847,6 @@ static struct cftype cpu_legacy_files[] = {
 		.seq_show = cpu_cfs_local_stat_show,
 	},
 #endif
-#ifdef CONFIG_RT_GROUP_SCHED
-	{
-		.name = "rt_runtime_us",
-		.read_s64 = cpu_rt_runtime_read,
-		.write_s64 = cpu_rt_runtime_write,
-	},
-	{
-		.name = "rt_period_us",
-		.read_u64 = cpu_rt_period_read_uint,
-		.write_u64 = cpu_rt_period_write_uint,
-	},
-#endif
 #ifdef CONFIG_UCLAMP_TASK_GROUP
 	{
 		.name = "uclamp.min",
@@ -9890,6 +9864,55 @@ static struct cftype cpu_legacy_files[] = {
 	{ }	/* Terminate */
 };
 
+#ifdef CONFIG_RT_GROUP_SCHED
+static struct cftype rt_group_files[] = {
+	{
+		.name = "rt_runtime_us",
+		.read_s64 = cpu_rt_runtime_read,
+		.write_s64 = cpu_rt_runtime_write,
+	},
+	{
+		.name = "rt_period_us",
+		.read_u64 = cpu_rt_period_read_uint,
+		.write_u64 = cpu_rt_period_write_uint,
+	},
+	{ }	/* Terminate */
+};
+
+# ifdef CONFIG_RT_GROUP_SCHED_DEFAULT_DISABLED
+DEFINE_STATIC_KEY_FALSE(rt_group_sched);
+# else
+DEFINE_STATIC_KEY_TRUE(rt_group_sched);
+# endif
+
+static int __init setup_rt_group_sched(char *str)
+{
+	long val;
+
+	if (kstrtol(str, 0, &val) || val < 0 || val > 1) {
+		pr_warn("Unable to set rt_group_sched\n");
+		return 1;
+	}
+	if (val)
+		static_branch_enable(&rt_group_sched);
+	else
+		static_branch_disable(&rt_group_sched);
+
+	return 1;
+}
+__setup("rt_group_sched=", setup_rt_group_sched);
+
+static int __init cpu_rt_group_init(void)
+{
+	if (!rt_group_sched_enabled())
+		return 0;
+
+	WARN_ON(cgroup_add_legacy_cftypes(&cpu_cgrp_subsys, rt_group_files));
+	return 0;
+}
+subsys_initcall(cpu_rt_group_init);
+#endif /* CONFIG_RT_GROUP_SCHED */
+
 static int cpu_extra_stat_show(struct seq_file *sf,
 			       struct cgroup_subsys_state *css)
 {
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index 816f07f9d30f..461242ec958a 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -630,7 +630,7 @@ static const struct kobj_type sugov_tunables_ktype = {
 
 /********************** cpufreq governor interface *********************/
 
-struct cpufreq_governor schedutil_gov;
+static struct cpufreq_governor schedutil_gov;
 
 static struct sugov_policy *sugov_policy_alloc(struct cpufreq_policy *policy)
 {
@@ -909,7 +909,7 @@ static void sugov_limits(struct cpufreq_policy *policy)
 	WRITE_ONCE(sg_policy->limits_changed, true);
 }
 
-struct cpufreq_governor schedutil_gov = {
+static struct cpufreq_governor schedutil_gov = {
 	.name			= "schedutil",
 	.owner			= THIS_MODULE,
 	.flags			= CPUFREQ_GOV_DYNAMIC_SWITCHING,
@@ -927,4 +927,9 @@ struct cpufreq_governor *cpufreq_default_governor(void)
 }
 #endif
 
+bool sugov_is_governor(struct cpufreq_policy *policy)
+{
+	return policy->governor == &schedutil_gov;
+}
+
 cpufreq_governor_init(schedutil_gov);
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 56ae54e0ce6a..9d71baf08075 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -588,6 +588,10 @@ static void register_sd(struct sched_domain *sd, struct dentry *parent)
 	debugfs_create_file("flags", 0444, parent, &sd->flags, &sd_flags_fops);
 	debugfs_create_file("groups_flags", 0444, parent, &sd->groups->flags, &sd_flags_fops);
 	debugfs_create_u32("level", 0444, parent, (u32 *)&sd->level);
+
+	if (sd->flags & SD_ASYM_PACKING)
+		debugfs_create_u32("group_asym_prefer_cpu", 0444, parent,
+				   (u32 *)&sd->groups->asym_prefer_cpu);
 }
 
 void update_sched_domain_debugfs(void)
@@ -1206,6 +1210,10 @@ void proc_sched_show_task(struct task_struct *p, struct pid_namespace *ns,
 		P_SCHEDSTAT(nr_failed_migrations_running);
 		P_SCHEDSTAT(nr_failed_migrations_hot);
 		P_SCHEDSTAT(nr_forced_migrations);
+#ifdef CONFIG_NUMA_BALANCING
+		P_SCHEDSTAT(numa_task_migrated);
+		P_SCHEDSTAT(numa_task_swapped);
+#endif
 		P_SCHEDSTAT(nr_wakeups);
 		P_SCHEDSTAT(nr_wakeups_sync);
 		P_SCHEDSTAT(nr_wakeups_migrate);
diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index fdbf249d1c68..2c41c78be61e 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -26,7 +26,7 @@ enum scx_consts {
 	 * Iterating all tasks may take a while. Periodically drop
 	 * scx_tasks_lock to avoid causing e.g. CSD and RCU stalls.
 	 */
-	SCX_OPS_TASK_ITER_BATCH		= 32,
+	SCX_TASK_ITER_BATCH		= 32,
 };
 
 enum scx_exit_kind {
@@ -44,9 +44,9 @@ enum scx_exit_kind {
 };
 
 /*
- * An exit code can be specified when exiting with scx_bpf_exit() or
- * scx_ops_exit(), corresponding to exit_kind UNREG_BPF and UNREG_KERN
- * respectively. The codes are 64bit of the format:
+ * An exit code can be specified when exiting with scx_bpf_exit() or scx_exit(),
+ * corresponding to exit_kind UNREG_BPF and UNREG_KERN respectively. The codes
+ * are 64bit of the format:
  *
  *   Bits: [63  ..  48 47   ..  32 31 .. 0]
  *         [ SYS ACT ] [ SYS RSN ] [ USR  ]
@@ -163,16 +163,21 @@ enum scx_ops_flags {
 	/*
 	 * CPU cgroup support flags
 	 */
-	SCX_OPS_HAS_CGROUP_WEIGHT = 1LLU << 16,	/* DEPRECATED, will be removed on 6.18 */
+	SCX_OPS_HAS_CGROUP_WEIGHT	= 1LLU << 16,	/* DEPRECATED, will be removed on 6.18 */
 
-	SCX_OPS_ALL_FLAGS	= SCX_OPS_KEEP_BUILTIN_IDLE |
-				  SCX_OPS_ENQ_LAST |
-				  SCX_OPS_ENQ_EXITING |
-				  SCX_OPS_ENQ_MIGRATION_DISABLED |
-				  SCX_OPS_ALLOW_QUEUED_WAKEUP |
-				  SCX_OPS_SWITCH_PARTIAL |
-				  SCX_OPS_BUILTIN_IDLE_PER_NODE |
-				  SCX_OPS_HAS_CGROUP_WEIGHT,
+	SCX_OPS_ALL_FLAGS		= SCX_OPS_KEEP_BUILTIN_IDLE |
+					  SCX_OPS_ENQ_LAST |
+					  SCX_OPS_ENQ_EXITING |
+					  SCX_OPS_ENQ_MIGRATION_DISABLED |
+					  SCX_OPS_ALLOW_QUEUED_WAKEUP |
+					  SCX_OPS_SWITCH_PARTIAL |
+					  SCX_OPS_BUILTIN_IDLE_PER_NODE |
+					  SCX_OPS_HAS_CGROUP_WEIGHT,
+
+	/* high 8 bits are internal, don't include in SCX_OPS_ALL_FLAGS */
+	__SCX_OPS_INTERNAL_MASK		= 0xffLLU << 56,
+
+	SCX_OPS_HAS_CPU_PREEMPT		= 1LLU << 56,
 };
 
 /* argument container for ops.init_task() */
@@ -368,6 +373,15 @@ struct sched_ext_ops {
 	 * @running: A task is starting to run on its associated CPU
 	 * @p: task starting to run
 	 *
+	 * Note that this callback may be called from a CPU other than the
+	 * one the task is going to run on. This can happen when a task
+	 * property is changed (i.e., affinity), since scx_next_task_scx(),
+	 * which triggers this callback, may run on a CPU different from
+	 * the task's assigned CPU.
+	 *
+	 * Therefore, always use scx_bpf_task_cpu(@p) to determine the
+	 * target CPU the task is going to use.
+	 *
 	 * See ->runnable() for explanation on the task state notifiers.
 	 */
 	void (*running)(struct task_struct *p);
@@ -377,6 +391,15 @@ struct sched_ext_ops {
 	 * @p: task stopping to run
 	 * @runnable: is task @p still runnable?
 	 *
+	 * Note that this callback may be called from a CPU other than the
+	 * one the task was running on. This can happen when a task
+	 * property is changed (i.e., affinity), since dequeue_task_scx(),
+	 * which triggers this callback, may run on a CPU different from
+	 * the task's assigned CPU.
+	 *
+	 * Therefore, always use scx_bpf_task_cpu(@p) to retrieve the CPU
+	 * the task was running on.
+	 *
 	 * See ->runnable() for explanation on the task state notifiers. If
 	 * !@runnable, ->quiescent() will be invoked after this operation
 	 * returns.
@@ -465,6 +488,7 @@ struct sched_ext_ops {
 	 * idle CPU tracking and the following helpers become unavailable:
 	 *
 	 * - scx_bpf_select_cpu_dfl()
+	 * - scx_bpf_select_cpu_and()
 	 * - scx_bpf_test_and_clear_cpu_idle()
 	 * - scx_bpf_pick_idle_cpu()
 	 *
@@ -728,6 +752,9 @@ struct sched_ext_ops {
 	 * BPF scheduler is enabled.
 	 */
 	char name[SCX_OPS_NAME_LEN];
+
+	/* internal use only, must be NULL */
+	void *priv;
 };
 
 enum scx_opi {
@@ -739,6 +766,98 @@ enum scx_opi {
 	SCX_OPI_END			= SCX_OP_IDX(init),
 };
 
+/*
+ * Collection of event counters. Event types are placed in descending order.
+ */
+struct scx_event_stats {
+	/*
+	 * If ops.select_cpu() returns a CPU which can't be used by the task,
+	 * the core scheduler code silently picks a fallback CPU.
+	 */
+	s64		SCX_EV_SELECT_CPU_FALLBACK;
+
+	/*
+	 * When dispatching to a local DSQ, the CPU may have gone offline in
+	 * the meantime. In this case, the task is bounced to the global DSQ.
+	 */
+	s64		SCX_EV_DISPATCH_LOCAL_DSQ_OFFLINE;
+
+	/*
+	 * If SCX_OPS_ENQ_LAST is not set, the number of times that a task
+	 * continued to run because there were no other tasks on the CPU.
+	 */
+	s64		SCX_EV_DISPATCH_KEEP_LAST;
+
+	/*
+	 * If SCX_OPS_ENQ_EXITING is not set, the number of times that a task
+	 * is dispatched to a local DSQ when exiting.
+	 */
+	s64		SCX_EV_ENQ_SKIP_EXITING;
+
+	/*
+	 * If SCX_OPS_ENQ_MIGRATION_DISABLED is not set, the number of times a
+	 * migration disabled task skips ops.enqueue() and is dispatched to its
+	 * local DSQ.
+	 */
+	s64		SCX_EV_ENQ_SKIP_MIGRATION_DISABLED;
+
+	/*
+	 * Total number of times a task's time slice was refilled with the
+	 * default value (SCX_SLICE_DFL).
+	 */
+	s64		SCX_EV_REFILL_SLICE_DFL;
+
+	/*
+	 * The total duration of bypass modes in nanoseconds.
+	 */
+	s64		SCX_EV_BYPASS_DURATION;
+
+	/*
+	 * The number of tasks dispatched in the bypassing mode.
+	 */
+	s64		SCX_EV_BYPASS_DISPATCH;
+
+	/*
+	 * The number of times the bypassing mode has been activated.
+	 */
+	s64		SCX_EV_BYPASS_ACTIVATE;
+};
+
+struct scx_sched {
+	struct sched_ext_ops	ops;
+	DECLARE_BITMAP(has_op, SCX_OPI_END);
+
+	/*
+	 * Dispatch queues.
+	 *
+	 * The global DSQ (%SCX_DSQ_GLOBAL) is split per-node for scalability.
+	 * This is to avoid live-locking in bypass mode where all tasks are
+	 * dispatched to %SCX_DSQ_GLOBAL and all CPUs consume from it. If
+	 * per-node split isn't sufficient, it can be further split.
+	 */
+	struct rhashtable	dsq_hash;
+	struct scx_dispatch_q	**global_dsqs;
+
+	/*
+	 * The event counters are in a per-CPU variable to minimize the
+	 * accounting overhead. A system-wide view on the event counter is
+	 * constructed when requested by scx_bpf_events().
+	 */
+	struct scx_event_stats __percpu *event_stats_cpu;
+
+	bool			warned_zero_slice;
+
+	atomic_t		exit_kind;
+	struct scx_exit_info	*exit_info;
+
+	struct kobject		kobj;
+
+	struct kthread_worker	*helper;
+	struct irq_work		error_irq_work;
+	struct kthread_work	disable_work;
+	struct rcu_work		rcu_work;
+};
+
 enum scx_wake_flags {
 	/* expose select WF_* flags as enums */
 	SCX_WAKE_FORK		= WF_FORK,
@@ -838,18 +957,18 @@ enum scx_tg_flags {
 	SCX_TG_INITED		= 1U << 1,
 };
 
-enum scx_ops_enable_state {
-	SCX_OPS_ENABLING,
-	SCX_OPS_ENABLED,
-	SCX_OPS_DISABLING,
-	SCX_OPS_DISABLED,
+enum scx_enable_state {
+	SCX_ENABLING,
+	SCX_ENABLED,
+	SCX_DISABLING,
+	SCX_DISABLED,
 };
 
-static const char *scx_ops_enable_state_str[] = {
-	[SCX_OPS_ENABLING]	= "enabling",
-	[SCX_OPS_ENABLED]	= "enabled",
-	[SCX_OPS_DISABLING]	= "disabling",
-	[SCX_OPS_DISABLED]	= "disabled",
+static const char *scx_enable_state_str[] = {
+	[SCX_ENABLING]		= "enabling",
+	[SCX_ENABLED]		= "enabled",
+	[SCX_DISABLING]		= "disabling",
+	[SCX_DISABLED]		= "disabled",
 };
 
 /*
@@ -898,6 +1017,16 @@ enum scx_ops_state {
 #define SCX_OPSS_QSEQ_MASK	(~SCX_OPSS_STATE_MASK)
 
 /*
+ * NOTE: sched_ext is in the process of growing multiple scheduler support and
+ * scx_root usage is in a transitional state. Naked dereferences are safe if the
+ * caller is one of the tasks attached to SCX and explicit RCU dereference is
+ * necessary otherwise. Naked scx_root dereferences trigger sparse warnings but
+ * are used as temporary markers to indicate that the dereferences need to be
+ * updated to point to the associated scheduler instances rather than scx_root.
+ */
+static struct scx_sched __rcu *scx_root;
+
+/*
  * During exit, a task may schedule after losing its PIDs. When disabling the
  * BPF scheduler, we need to be able to iterate tasks in every state to
  * guarantee system safety. Maintain a dedicated task list which contains every
@@ -907,33 +1036,17 @@ static DEFINE_SPINLOCK(scx_tasks_lock);
 static LIST_HEAD(scx_tasks);
 
 /* ops enable/disable */
-static struct kthread_worker *scx_ops_helper;
-static DEFINE_MUTEX(scx_ops_enable_mutex);
-DEFINE_STATIC_KEY_FALSE(__scx_ops_enabled);
+static DEFINE_MUTEX(scx_enable_mutex);
+DEFINE_STATIC_KEY_FALSE(__scx_enabled);
 DEFINE_STATIC_PERCPU_RWSEM(scx_fork_rwsem);
-static atomic_t scx_ops_enable_state_var = ATOMIC_INIT(SCX_OPS_DISABLED);
+static atomic_t scx_enable_state_var = ATOMIC_INIT(SCX_DISABLED);
 static unsigned long scx_in_softlockup;
-static atomic_t scx_ops_breather_depth = ATOMIC_INIT(0);
-static int scx_ops_bypass_depth;
-static bool scx_ops_init_task_enabled;
+static atomic_t scx_breather_depth = ATOMIC_INIT(0);
+static int scx_bypass_depth;
+static bool scx_init_task_enabled;
 static bool scx_switching_all;
 DEFINE_STATIC_KEY_FALSE(__scx_switched_all);
 
-static struct sched_ext_ops scx_ops;
-static bool scx_warned_zero_slice;
-
-DEFINE_STATIC_KEY_FALSE(scx_ops_allow_queued_wakeup);
-static DEFINE_STATIC_KEY_FALSE(scx_ops_enq_last);
-static DEFINE_STATIC_KEY_FALSE(scx_ops_enq_exiting);
-static DEFINE_STATIC_KEY_FALSE(scx_ops_enq_migration_disabled);
-static DEFINE_STATIC_KEY_FALSE(scx_ops_cpu_preempt);
-
-static struct static_key_false scx_has_op[SCX_OPI_END] =
-	{ [0 ... SCX_OPI_END-1] = STATIC_KEY_FALSE_INIT };
-
-static atomic_t scx_exit_kind = ATOMIC_INIT(SCX_EXIT_DONE);
-static struct scx_exit_info *scx_exit_info;
-
 static atomic_long_t scx_nr_rejected = ATOMIC_LONG_INIT(0);
 static atomic_long_t scx_hotplug_seq = ATOMIC_LONG_INIT(0);
 
@@ -947,7 +1060,7 @@ static atomic_long_t scx_enable_seq = ATOMIC_LONG_INIT(0);
 /*
  * The maximum amount of time in jiffies that a task may be runnable without
  * being scheduled on a CPU. If this timeout is exceeded, it will trigger
- * scx_ops_error().
+ * scx_error().
  */
 static unsigned long scx_watchdog_timeout;
 
@@ -973,23 +1086,12 @@ static unsigned long __percpu *scx_kick_cpus_pnt_seqs;
  */
 static DEFINE_PER_CPU(struct task_struct *, direct_dispatch_task);
 
-/*
- * Dispatch queues.
- *
- * The global DSQ (%SCX_DSQ_GLOBAL) is split per-node for scalability. This is
- * to avoid live-locking in bypass mode where all tasks are dispatched to
- * %SCX_DSQ_GLOBAL and all CPUs consume from it. If per-node split isn't
- * sufficient, it can be further split.
- */
-static struct scx_dispatch_q **global_dsqs;
-
 static const struct rhashtable_params dsq_hash_params = {
 	.key_len		= sizeof_field(struct scx_dispatch_q, id),
 	.key_offset		= offsetof(struct scx_dispatch_q, id),
 	.head_offset		= offsetof(struct scx_dispatch_q, hash_node),
 };
 
-static struct rhashtable dsq_hash;
 static LLIST_HEAD(dsqs_to_free);
 
 /* dispatch buf */
@@ -1036,27 +1138,46 @@ static struct scx_dump_data scx_dump_data = {
 
 /* /sys/kernel/sched_ext interface */
 static struct kset *scx_kset;
-static struct kobject *scx_root_kobj;
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/sched_ext.h>
 
 static void process_ddsp_deferred_locals(struct rq *rq);
 static void scx_bpf_kick_cpu(s32 cpu, u64 flags);
-static __printf(3, 4) void scx_ops_exit_kind(enum scx_exit_kind kind,
-					     s64 exit_code,
-					     const char *fmt, ...);
+static void scx_vexit(struct scx_sched *sch, enum scx_exit_kind kind,
+		      s64 exit_code, const char *fmt, va_list args);
 
-#define scx_ops_error_kind(err, fmt, args...)					\
-	scx_ops_exit_kind((err), 0, fmt, ##args)
+static __printf(4, 5) void scx_exit(struct scx_sched *sch,
+				    enum scx_exit_kind kind, s64 exit_code,
+				    const char *fmt, ...)
+{
+	va_list args;
 
-#define scx_ops_exit(code, fmt, args...)					\
-	scx_ops_exit_kind(SCX_EXIT_UNREG_KERN, (code), fmt, ##args)
+	va_start(args, fmt);
+	scx_vexit(sch, kind, exit_code, fmt, args);
+	va_end(args);
+}
 
-#define scx_ops_error(fmt, args...)						\
-	scx_ops_error_kind(SCX_EXIT_ERROR, fmt, ##args)
+static __printf(3, 4) void scx_kf_exit(enum scx_exit_kind kind, s64 exit_code,
+				       const char *fmt, ...)
+{
+	struct scx_sched *sch;
+	va_list args;
 
-#define SCX_HAS_OP(op)	static_branch_likely(&scx_has_op[SCX_OP_IDX(op)])
+	rcu_read_lock();
+	sch = rcu_dereference(scx_root);
+	if (sch) {
+		va_start(args, fmt);
+		scx_vexit(sch, kind, exit_code, fmt, args);
+		va_end(args);
+	}
+	rcu_read_unlock();
+}
+
+#define scx_error(sch, fmt, args...)	scx_exit((sch), SCX_EXIT_ERROR, 0, fmt, ##args)
+#define scx_kf_error(fmt, args...)	scx_kf_exit(SCX_EXIT_ERROR, 0, fmt, ##args)
+
+#define SCX_HAS_OP(sch, op)	test_bit(SCX_OP_IDX(op), (sch)->has_op)
 
 static long jiffies_delta_msecs(unsigned long at, unsigned long now)
 {
@@ -1086,12 +1207,14 @@ static bool u32_before(u32 a, u32 b)
 
 static struct scx_dispatch_q *find_global_dsq(struct task_struct *p)
 {
-	return global_dsqs[cpu_to_node(task_cpu(p))];
+	struct scx_sched *sch = scx_root;
+
+	return sch->global_dsqs[cpu_to_node(task_cpu(p))];
 }
 
-static struct scx_dispatch_q *find_user_dsq(u64 dsq_id)
+static struct scx_dispatch_q *find_user_dsq(struct scx_sched *sch, u64 dsq_id)
 {
-	return rhashtable_lookup_fast(&dsq_hash, &dsq_id, dsq_hash_params);
+	return rhashtable_lookup_fast(&sch->dsq_hash, &dsq_id, dsq_hash_params);
 }
 
 /*
@@ -1118,27 +1241,61 @@ static void scx_kf_disallow(u32 mask)
 	current->scx.kf_mask &= ~mask;
 }
 
-#define SCX_CALL_OP(mask, op, args...)						\
+/*
+ * Track the rq currently locked.
+ *
+ * This allows kfuncs to safely operate on rq from any scx ops callback,
+ * knowing which rq is already locked.
+ */
+static DEFINE_PER_CPU(struct rq *, locked_rq);
+
+static inline void update_locked_rq(struct rq *rq)
+{
+	/*
+	 * Check whether @rq is actually locked. This can help expose bugs
+	 * or incorrect assumptions about the context in which a kfunc or
+	 * callback is executed.
+	 */
+	if (rq)
+		lockdep_assert_rq_held(rq);
+	__this_cpu_write(locked_rq, rq);
+}
+
+/*
+ * Return the rq currently locked from an scx callback, or NULL if no rq is
+ * locked.
+ */
+static inline struct rq *scx_locked_rq(void)
+{
+	return __this_cpu_read(locked_rq);
+}
+
+#define SCX_CALL_OP(sch, mask, op, rq, args...)					\
 do {										\
+	update_locked_rq(rq);							\
 	if (mask) {								\
 		scx_kf_allow(mask);						\
-		scx_ops.op(args);						\
+		(sch)->ops.op(args);						\
 		scx_kf_disallow(mask);						\
 	} else {								\
-		scx_ops.op(args);						\
+		(sch)->ops.op(args);						\
 	}									\
+	update_locked_rq(NULL);							\
 } while (0)
 
-#define SCX_CALL_OP_RET(mask, op, args...)					\
+#define SCX_CALL_OP_RET(sch, mask, op, rq, args...)				\
 ({										\
-	__typeof__(scx_ops.op(args)) __ret;					\
+	__typeof__((sch)->ops.op(args)) __ret;					\
+										\
+	update_locked_rq(rq);							\
 	if (mask) {								\
 		scx_kf_allow(mask);						\
-		__ret = scx_ops.op(args);					\
+		__ret = (sch)->ops.op(args);					\
 		scx_kf_disallow(mask);						\
 	} else {								\
-		__ret = scx_ops.op(args);					\
+		__ret = (sch)->ops.op(args);					\
 	}									\
+	update_locked_rq(NULL);							\
 	__ret;									\
 })
 
@@ -1153,31 +1310,31 @@ do {										\
  * scx_kf_allowed_on_arg_tasks() to test whether the invocation is allowed on
  * the specific task.
  */
-#define SCX_CALL_OP_TASK(mask, op, task, args...)				\
+#define SCX_CALL_OP_TASK(sch, mask, op, rq, task, args...)			\
 do {										\
 	BUILD_BUG_ON((mask) & ~__SCX_KF_TERMINAL);				\
 	current->scx.kf_tasks[0] = task;					\
-	SCX_CALL_OP(mask, op, task, ##args);					\
+	SCX_CALL_OP((sch), mask, op, rq, task, ##args);				\
 	current->scx.kf_tasks[0] = NULL;					\
 } while (0)
 
-#define SCX_CALL_OP_TASK_RET(mask, op, task, args...)				\
+#define SCX_CALL_OP_TASK_RET(sch, mask, op, rq, task, args...)			\
 ({										\
-	__typeof__(scx_ops.op(task, ##args)) __ret;				\
+	__typeof__((sch)->ops.op(task, ##args)) __ret;				\
 	BUILD_BUG_ON((mask) & ~__SCX_KF_TERMINAL);				\
 	current->scx.kf_tasks[0] = task;					\
-	__ret = SCX_CALL_OP_RET(mask, op, task, ##args);			\
+	__ret = SCX_CALL_OP_RET((sch), mask, op, rq, task, ##args);		\
 	current->scx.kf_tasks[0] = NULL;					\
 	__ret;									\
 })
 
-#define SCX_CALL_OP_2TASKS_RET(mask, op, task0, task1, args...)			\
+#define SCX_CALL_OP_2TASKS_RET(sch, mask, op, rq, task0, task1, args...)	\
 ({										\
-	__typeof__(scx_ops.op(task0, task1, ##args)) __ret;			\
+	__typeof__((sch)->ops.op(task0, task1, ##args)) __ret;			\
 	BUILD_BUG_ON((mask) & ~__SCX_KF_TERMINAL);				\
 	current->scx.kf_tasks[0] = task0;					\
 	current->scx.kf_tasks[1] = task1;					\
-	__ret = SCX_CALL_OP_RET(mask, op, task0, task1, ##args);		\
+	__ret = SCX_CALL_OP_RET((sch), mask, op, rq, task0, task1, ##args);	\
 	current->scx.kf_tasks[0] = NULL;					\
 	current->scx.kf_tasks[1] = NULL;					\
 	__ret;									\
@@ -1187,8 +1344,8 @@ do {										\
 static __always_inline bool scx_kf_allowed(u32 mask)
 {
 	if (unlikely(!(current->scx.kf_mask & mask))) {
-		scx_ops_error("kfunc with mask 0x%x called from an operation only allowing 0x%x",
-			      mask, current->scx.kf_mask);
+		scx_kf_error("kfunc with mask 0x%x called from an operation only allowing 0x%x",
+			     mask, current->scx.kf_mask);
 		return false;
 	}
 
@@ -1201,13 +1358,13 @@ static __always_inline bool scx_kf_allowed(u32 mask)
 	 */
 	if (unlikely(highest_bit(mask) == SCX_KF_CPU_RELEASE &&
 		     (current->scx.kf_mask & higher_bits(SCX_KF_CPU_RELEASE)))) {
-		scx_ops_error("cpu_release kfunc called from a nested operation");
+		scx_kf_error("cpu_release kfunc called from a nested operation");
 		return false;
 	}
 
 	if (unlikely(highest_bit(mask) == SCX_KF_DISPATCH &&
 		     (current->scx.kf_mask & higher_bits(SCX_KF_DISPATCH)))) {
-		scx_ops_error("dispatch kfunc called from a nested operation");
+		scx_kf_error("dispatch kfunc called from a nested operation");
 		return false;
 	}
 
@@ -1223,18 +1380,13 @@ static __always_inline bool scx_kf_allowed_on_arg_tasks(u32 mask,
 
 	if (unlikely((p != current->scx.kf_tasks[0] &&
 		      p != current->scx.kf_tasks[1]))) {
-		scx_ops_error("called on a task not being operated on");
+		scx_kf_error("called on a task not being operated on");
 		return false;
 	}
 
 	return true;
 }
 
-static bool scx_kf_allowed_if_unlocked(void)
-{
-	return !current->scx.kf_mask;
-}
-
 /**
  * nldsq_next_task - Iterate to the next task in a non-local DSQ
  * @dsq: user dsq being iterated
@@ -1402,15 +1554,15 @@ static void scx_task_iter_stop(struct scx_task_iter *iter)
  * @iter: iterator to walk
  *
  * Visit the next task. See scx_task_iter_start() for details. Locks are dropped
- * and re-acquired every %SCX_OPS_TASK_ITER_BATCH iterations to avoid causing
- * stalls by holding scx_tasks_lock for too long.
+ * and re-acquired every %SCX_TASK_ITER_BATCH iterations to avoid causing stalls
+ * by holding scx_tasks_lock for too long.
  */
 static struct task_struct *scx_task_iter_next(struct scx_task_iter *iter)
 {
 	struct list_head *cursor = &iter->cursor.tasks_node;
 	struct sched_ext_entity *pos;
 
-	if (!(++iter->cnt % SCX_OPS_TASK_ITER_BATCH)) {
+	if (!(++iter->cnt % SCX_TASK_ITER_BATCH)) {
 		scx_task_iter_unlock(iter);
 		cond_resched();
 		scx_task_iter_relock(iter);
@@ -1481,91 +1633,29 @@ static struct task_struct *scx_task_iter_next_locked(struct scx_task_iter *iter)
 	return p;
 }
 
-/*
- * Collection of event counters. Event types are placed in descending order.
- */
-struct scx_event_stats {
-	/*
-	 * If ops.select_cpu() returns a CPU which can't be used by the task,
-	 * the core scheduler code silently picks a fallback CPU.
-	 */
-	s64		SCX_EV_SELECT_CPU_FALLBACK;
-
-	/*
-	 * When dispatching to a local DSQ, the CPU may have gone offline in
-	 * the meantime. In this case, the task is bounced to the global DSQ.
-	 */
-	s64		SCX_EV_DISPATCH_LOCAL_DSQ_OFFLINE;
-
-	/*
-	 * If SCX_OPS_ENQ_LAST is not set, the number of times that a task
-	 * continued to run because there were no other tasks on the CPU.
-	 */
-	s64		SCX_EV_DISPATCH_KEEP_LAST;
-
-	/*
-	 * If SCX_OPS_ENQ_EXITING is not set, the number of times that a task
-	 * is dispatched to a local DSQ when exiting.
-	 */
-	s64		SCX_EV_ENQ_SKIP_EXITING;
-
-	/*
-	 * If SCX_OPS_ENQ_MIGRATION_DISABLED is not set, the number of times a
-	 * migration disabled task skips ops.enqueue() and is dispatched to its
-	 * local DSQ.
-	 */
-	s64		SCX_EV_ENQ_SKIP_MIGRATION_DISABLED;
-
-	/*
-	 * The total number of tasks enqueued (or pick_task-ed) with a
-	 * default time slice (SCX_SLICE_DFL).
-	 */
-	s64		SCX_EV_ENQ_SLICE_DFL;
-
-	/*
-	 * The total duration of bypass modes in nanoseconds.
-	 */
-	s64		SCX_EV_BYPASS_DURATION;
-
-	/*
-	 * The number of tasks dispatched in the bypassing mode.
-	 */
-	s64		SCX_EV_BYPASS_DISPATCH;
-
-	/*
-	 * The number of times the bypassing mode has been activated.
-	 */
-	s64		SCX_EV_BYPASS_ACTIVATE;
-};
-
-/*
- * The event counter is organized by a per-CPU variable to minimize the
- * accounting overhead without synchronization. A system-wide view on the
- * event counter is constructed when requested by scx_bpf_get_event_stat().
- */
-static DEFINE_PER_CPU(struct scx_event_stats, event_stats_cpu);
-
 /**
  * scx_add_event - Increase an event counter for 'name' by 'cnt'
+ * @sch: scx_sched to account events for
  * @name: an event name defined in struct scx_event_stats
  * @cnt: the number of the event occured
  *
  * This can be used when preemption is not disabled.
  */
-#define scx_add_event(name, cnt) do {						\
-	this_cpu_add(event_stats_cpu.name, cnt);				\
-	trace_sched_ext_event(#name, cnt);					\
+#define scx_add_event(sch, name, cnt) do {					\
+	this_cpu_add((sch)->event_stats_cpu->name, (cnt));			\
+	trace_sched_ext_event(#name, (cnt));					\
 } while(0)
 
 /**
  * __scx_add_event - Increase an event counter for 'name' by 'cnt'
+ * @sch: scx_sched to account events for
  * @name: an event name defined in struct scx_event_stats
  * @cnt: the number of the event occured
  *
  * This should be used only when preemption is disabled.
  */
-#define __scx_add_event(name, cnt) do {						\
-	__this_cpu_add(event_stats_cpu.name, cnt);				\
+#define __scx_add_event(sch, name, cnt) do {					\
+	__this_cpu_add((sch)->event_stats_cpu->name, (cnt));			\
 	trace_sched_ext_event(#name, cnt);					\
 } while(0)
 
@@ -1590,25 +1680,25 @@ static DEFINE_PER_CPU(struct scx_event_stats, event_stats_cpu);
 } while (0)
 
 
-static void scx_bpf_events(struct scx_event_stats *events, size_t events__sz);
+static void scx_read_events(struct scx_sched *sch,
+			    struct scx_event_stats *events);
 
-static enum scx_ops_enable_state scx_ops_enable_state(void)
+static enum scx_enable_state scx_enable_state(void)
 {
-	return atomic_read(&scx_ops_enable_state_var);
+	return atomic_read(&scx_enable_state_var);
 }
 
-static enum scx_ops_enable_state
-scx_ops_set_enable_state(enum scx_ops_enable_state to)
+static enum scx_enable_state scx_set_enable_state(enum scx_enable_state to)
 {
-	return atomic_xchg(&scx_ops_enable_state_var, to);
+	return atomic_xchg(&scx_enable_state_var, to);
 }
 
-static bool scx_ops_tryset_enable_state(enum scx_ops_enable_state to,
-					enum scx_ops_enable_state from)
+static bool scx_tryset_enable_state(enum scx_enable_state to,
+				    enum scx_enable_state from)
 {
 	int from_v = from;
 
-	return atomic_try_cmpxchg(&scx_ops_enable_state_var, &from_v, to);
+	return atomic_try_cmpxchg(&scx_enable_state_var, &from_v, to);
 }
 
 static bool scx_rq_bypassing(struct rq *rq)
@@ -1633,8 +1723,14 @@ static void wait_ops_state(struct task_struct *p, unsigned long opss)
 	} while (atomic_long_read_acquire(&p->scx.ops_state) == opss);
 }
 
+static inline bool __cpu_valid(s32 cpu)
+{
+	return likely(cpu >= 0 && cpu < nr_cpu_ids && cpu_possible(cpu));
+}
+
 /**
- * ops_cpu_valid - Verify a cpu number
+ * ops_cpu_valid - Verify a cpu number, to be used on ops input args
+ * @sch: scx_sched to abort on error
  * @cpu: cpu number which came from a BPF ops
  * @where: extra information reported on error
  *
@@ -1642,35 +1738,52 @@ static void wait_ops_state(struct task_struct *p, unsigned long opss)
  * Verify that it is in range and one of the possible cpus. If invalid, trigger
  * an ops error.
  */
-static bool ops_cpu_valid(s32 cpu, const char *where)
+static bool ops_cpu_valid(struct scx_sched *sch, s32 cpu, const char *where)
+{
+	if (__cpu_valid(cpu)) {
+		return true;
+	} else {
+		scx_error(sch, "invalid CPU %d%s%s", cpu, where ? " " : "", where ?: "");
+		return false;
+	}
+}
+
+/**
+ * kf_cpu_valid - Verify a CPU number, to be used on kfunc input args
+ * @cpu: cpu number which came from a BPF ops
+ * @where: extra information reported on error
+ *
+ * The same as ops_cpu_valid() but @sch is implicit.
+ */
+static bool kf_cpu_valid(u32 cpu, const char *where)
 {
-	if (likely(cpu >= 0 && cpu < nr_cpu_ids && cpu_possible(cpu))) {
+	if (__cpu_valid(cpu)) {
 		return true;
 	} else {
-		scx_ops_error("invalid CPU %d%s%s", cpu,
-			      where ? " " : "", where ?: "");
+		scx_kf_error("invalid CPU %d%s%s", cpu, where ? " " : "", where ?: "");
 		return false;
 	}
 }
 
 /**
  * ops_sanitize_err - Sanitize a -errno value
+ * @sch: scx_sched to error out on error
  * @ops_name: operation to blame on failure
  * @err: -errno value to sanitize
  *
- * Verify @err is a valid -errno. If not, trigger scx_ops_error() and return
+ * Verify @err is a valid -errno. If not, trigger scx_error() and return
  * -%EPROTO. This is necessary because returning a rogue -errno up the chain can
  * cause misbehaviors. For an example, a large negative return from
  * ops.init_task() triggers an oops when passed up the call chain because the
  * value fails IS_ERR() test after being encoded with ERR_PTR() and then is
  * handled as a pointer.
  */
-static int ops_sanitize_err(const char *ops_name, s32 err)
+static int ops_sanitize_err(struct scx_sched *sch, const char *ops_name, s32 err)
 {
 	if (err < 0 && err >= -MAX_ERRNO)
 		return err;
 
-	scx_ops_error("ops.%s() returned an invalid errno %d", ops_name, err);
+	scx_error(sch, "ops.%s() returned an invalid errno %d", ops_name, err);
 	return -EPROTO;
 }
 
@@ -1777,7 +1890,7 @@ static void touch_core_sched_dispatch(struct rq *rq, struct task_struct *p)
 	lockdep_assert_rq_held(rq);
 
 #ifdef CONFIG_SCHED_CORE
-	if (SCX_HAS_OP(core_sched_before))
+	if (unlikely(SCX_HAS_OP(scx_root, core_sched_before)))
 		touch_core_sched(rq, p);
 #endif
 }
@@ -1815,8 +1928,14 @@ static void dsq_mod_nr(struct scx_dispatch_q *dsq, s32 delta)
 	WRITE_ONCE(dsq->nr, dsq->nr + delta);
 }
 
-static void dispatch_enqueue(struct scx_dispatch_q *dsq, struct task_struct *p,
-			     u64 enq_flags)
+static void refill_task_slice_dfl(struct task_struct *p)
+{
+	p->scx.slice = SCX_SLICE_DFL;
+	__scx_add_event(scx_root, SCX_EV_REFILL_SLICE_DFL, 1);
+}
+
+static void dispatch_enqueue(struct scx_sched *sch, struct scx_dispatch_q *dsq,
+			     struct task_struct *p, u64 enq_flags)
 {
 	bool is_local = dsq->id == SCX_DSQ_LOCAL;
 
@@ -1827,7 +1946,7 @@ static void dispatch_enqueue(struct scx_dispatch_q *dsq, struct task_struct *p,
 	if (!is_local) {
 		raw_spin_lock(&dsq->lock);
 		if (unlikely(dsq->id == SCX_DSQ_INVALID)) {
-			scx_ops_error("attempting to dispatch to a destroyed dsq");
+			scx_error(sch, "attempting to dispatch to a destroyed dsq");
 			/* fall back to the global dsq */
 			raw_spin_unlock(&dsq->lock);
 			dsq = find_global_dsq(p);
@@ -1844,7 +1963,7 @@ static void dispatch_enqueue(struct scx_dispatch_q *dsq, struct task_struct *p,
 		 * disallow any internal DSQ from doing vtime ordering of
 		 * tasks.
 		 */
-		scx_ops_error("cannot use vtime ordering for built-in DSQs");
+		scx_error(sch, "cannot use vtime ordering for built-in DSQs");
 		enq_flags &= ~SCX_ENQ_DSQ_PRIQ;
 	}
 
@@ -1858,8 +1977,8 @@ static void dispatch_enqueue(struct scx_dispatch_q *dsq, struct task_struct *p,
 		 */
 		if (unlikely(RB_EMPTY_ROOT(&dsq->priq) &&
 			     nldsq_next_task(dsq, NULL, false)))
-			scx_ops_error("DSQ ID 0x%016llx already had FIFO-enqueued tasks",
-				      dsq->id);
+			scx_error(sch, "DSQ ID 0x%016llx already had FIFO-enqueued tasks",
+				  dsq->id);
 
 		p->scx.dsq_flags |= SCX_TASK_DSQ_ON_PRIQ;
 		rb_add(&p->scx.dsq_priq, &dsq->priq, scx_dsq_priq_less);
@@ -1880,8 +1999,8 @@ static void dispatch_enqueue(struct scx_dispatch_q *dsq, struct task_struct *p,
 	} else {
 		/* a FIFO DSQ shouldn't be using PRIQ enqueuing */
 		if (unlikely(!RB_EMPTY_ROOT(&dsq->priq)))
-			scx_ops_error("DSQ ID 0x%016llx already had PRIQ-enqueued tasks",
-				      dsq->id);
+			scx_error(sch, "DSQ ID 0x%016llx already had PRIQ-enqueued tasks",
+				  dsq->id);
 
 		if (enq_flags & (SCX_ENQ_HEAD | SCX_ENQ_PREEMPT))
 			list_add(&p->scx.dsq_list.node, &dsq->list);
@@ -1996,7 +2115,8 @@ static void dispatch_dequeue(struct rq *rq, struct task_struct *p)
 		raw_spin_unlock(&dsq->lock);
 }
 
-static struct scx_dispatch_q *find_dsq_for_dispatch(struct rq *rq, u64 dsq_id,
+static struct scx_dispatch_q *find_dsq_for_dispatch(struct scx_sched *sch,
+						    struct rq *rq, u64 dsq_id,
 						    struct task_struct *p)
 {
 	struct scx_dispatch_q *dsq;
@@ -2007,7 +2127,7 @@ static struct scx_dispatch_q *find_dsq_for_dispatch(struct rq *rq, u64 dsq_id,
 	if ((dsq_id & SCX_DSQ_LOCAL_ON) == SCX_DSQ_LOCAL_ON) {
 		s32 cpu = dsq_id & SCX_DSQ_LOCAL_CPU_MASK;
 
-		if (!ops_cpu_valid(cpu, "in SCX_DSQ_LOCAL_ON dispatch verdict"))
+		if (!ops_cpu_valid(sch, cpu, "in SCX_DSQ_LOCAL_ON dispatch verdict"))
 			return find_global_dsq(p);
 
 		return &cpu_rq(cpu)->scx.local_dsq;
@@ -2016,11 +2136,11 @@ static struct scx_dispatch_q *find_dsq_for_dispatch(struct rq *rq, u64 dsq_id,
 	if (dsq_id == SCX_DSQ_GLOBAL)
 		dsq = find_global_dsq(p);
 	else
-		dsq = find_user_dsq(dsq_id);
+		dsq = find_user_dsq(sch, dsq_id);
 
 	if (unlikely(!dsq)) {
-		scx_ops_error("non-existent DSQ 0x%llx for %s[%d]",
-			      dsq_id, p->comm, p->pid);
+		scx_error(sch, "non-existent DSQ 0x%llx for %s[%d]",
+			  dsq_id, p->comm, p->pid);
 		return find_global_dsq(p);
 	}
 
@@ -2041,12 +2161,12 @@ static void mark_direct_dispatch(struct task_struct *ddsp_task,
 	/* @p must match the task on the enqueue path */
 	if (unlikely(p != ddsp_task)) {
 		if (IS_ERR(ddsp_task))
-			scx_ops_error("%s[%d] already direct-dispatched",
-				      p->comm, p->pid);
+			scx_kf_error("%s[%d] already direct-dispatched",
+				  p->comm, p->pid);
 		else
-			scx_ops_error("scheduling for %s[%d] but trying to direct-dispatch %s[%d]",
-				      ddsp_task->comm, ddsp_task->pid,
-				      p->comm, p->pid);
+			scx_kf_error("scheduling for %s[%d] but trying to direct-dispatch %s[%d]",
+				  ddsp_task->comm, ddsp_task->pid,
+				  p->comm, p->pid);
 		return;
 	}
 
@@ -2057,11 +2177,12 @@ static void mark_direct_dispatch(struct task_struct *ddsp_task,
 	p->scx.ddsp_enq_flags = enq_flags;
 }
 
-static void direct_dispatch(struct task_struct *p, u64 enq_flags)
+static void direct_dispatch(struct scx_sched *sch, struct task_struct *p,
+			    u64 enq_flags)
 {
 	struct rq *rq = task_rq(p);
 	struct scx_dispatch_q *dsq =
-		find_dsq_for_dispatch(rq, p->scx.ddsp_dsq_id, p);
+		find_dsq_for_dispatch(sch, rq, p->scx.ddsp_dsq_id, p);
 
 	touch_core_sched_dispatch(rq, p);
 
@@ -2102,7 +2223,8 @@ static void direct_dispatch(struct task_struct *p, u64 enq_flags)
 		return;
 	}
 
-	dispatch_enqueue(dsq, p, p->scx.ddsp_enq_flags | SCX_ENQ_CLEAR_OPSS);
+	dispatch_enqueue(sch, dsq, p,
+			 p->scx.ddsp_enq_flags | SCX_ENQ_CLEAR_OPSS);
 }
 
 static bool scx_rq_online(struct rq *rq)
@@ -2120,6 +2242,7 @@ static bool scx_rq_online(struct rq *rq)
 static void do_enqueue_task(struct rq *rq, struct task_struct *p, u64 enq_flags,
 			    int sticky_cpu)
 {
+	struct scx_sched *sch = scx_root;
 	struct task_struct **ddsp_taskp;
 	unsigned long qseq;
 
@@ -2138,7 +2261,7 @@ static void do_enqueue_task(struct rq *rq, struct task_struct *p, u64 enq_flags,
 		goto local;
 
 	if (scx_rq_bypassing(rq)) {
-		__scx_add_event(SCX_EV_BYPASS_DISPATCH, 1);
+		__scx_add_event(sch, SCX_EV_BYPASS_DISPATCH, 1);
 		goto global;
 	}
 
@@ -2146,20 +2269,20 @@ static void do_enqueue_task(struct rq *rq, struct task_struct *p, u64 enq_flags,
 		goto direct;
 
 	/* see %SCX_OPS_ENQ_EXITING */
-	if (!static_branch_unlikely(&scx_ops_enq_exiting) &&
+	if (!(sch->ops.flags & SCX_OPS_ENQ_EXITING) &&
 	    unlikely(p->flags & PF_EXITING)) {
-		__scx_add_event(SCX_EV_ENQ_SKIP_EXITING, 1);
+		__scx_add_event(sch, SCX_EV_ENQ_SKIP_EXITING, 1);
 		goto local;
 	}
 
 	/* see %SCX_OPS_ENQ_MIGRATION_DISABLED */
-	if (!static_branch_unlikely(&scx_ops_enq_migration_disabled) &&
+	if (!(sch->ops.flags & SCX_OPS_ENQ_MIGRATION_DISABLED) &&
 	    is_migration_disabled(p)) {
-		__scx_add_event(SCX_EV_ENQ_SKIP_MIGRATION_DISABLED, 1);
+		__scx_add_event(sch, SCX_EV_ENQ_SKIP_MIGRATION_DISABLED, 1);
 		goto local;
 	}
 
-	if (!SCX_HAS_OP(enqueue))
+	if (unlikely(!SCX_HAS_OP(sch, enqueue)))
 		goto global;
 
 	/* DSQ bypass didn't trigger, enqueue on the BPF scheduler */
@@ -2172,7 +2295,7 @@ static void do_enqueue_task(struct rq *rq, struct task_struct *p, u64 enq_flags,
 	WARN_ON_ONCE(*ddsp_taskp);
 	*ddsp_taskp = p;
 
-	SCX_CALL_OP_TASK(SCX_KF_ENQUEUE, enqueue, p, enq_flags);
+	SCX_CALL_OP_TASK(sch, SCX_KF_ENQUEUE, enqueue, rq, p, enq_flags);
 
 	*ddsp_taskp = NULL;
 	if (p->scx.ddsp_dsq_id != SCX_DSQ_INVALID)
@@ -2186,7 +2309,7 @@ static void do_enqueue_task(struct rq *rq, struct task_struct *p, u64 enq_flags,
 	return;
 
 direct:
-	direct_dispatch(p, enq_flags);
+	direct_dispatch(sch, p, enq_flags);
 	return;
 
 local:
@@ -2196,17 +2319,15 @@ local:
 	 * higher priority it becomes from scx_prio_less()'s POV.
 	 */
 	touch_core_sched(rq, p);
-	p->scx.slice = SCX_SLICE_DFL;
-	__scx_add_event(SCX_EV_ENQ_SLICE_DFL, 1);
+	refill_task_slice_dfl(p);
 local_norefill:
-	dispatch_enqueue(&rq->scx.local_dsq, p, enq_flags);
+	dispatch_enqueue(sch, &rq->scx.local_dsq, p, enq_flags);
 	return;
 
 global:
 	touch_core_sched(rq, p);	/* see the comment in local: */
-	p->scx.slice = SCX_SLICE_DFL;
-	__scx_add_event(SCX_EV_ENQ_SLICE_DFL, 1);
-	dispatch_enqueue(find_global_dsq(p), p, enq_flags);
+	refill_task_slice_dfl(p);
+	dispatch_enqueue(sch, find_global_dsq(p), p, enq_flags);
 }
 
 static bool task_runnable(const struct task_struct *p)
@@ -2224,7 +2345,7 @@ static void set_task_runnable(struct rq *rq, struct task_struct *p)
 	}
 
 	/*
-	 * list_add_tail() must be used. scx_ops_bypass() depends on tasks being
+	 * list_add_tail() must be used. scx_bypass() depends on tasks being
 	 * appended to the runnable_list.
 	 */
 	list_add_tail(&p->scx.runnable_node, &rq->scx.runnable_list);
@@ -2239,6 +2360,7 @@ static void clr_task_runnable(struct task_struct *p, bool reset_runnable_at)
 
 static void enqueue_task_scx(struct rq *rq, struct task_struct *p, int enq_flags)
 {
+	struct scx_sched *sch = scx_root;
 	int sticky_cpu = p->scx.sticky_cpu;
 
 	if (enq_flags & ENQUEUE_WAKEUP)
@@ -2268,8 +2390,8 @@ static void enqueue_task_scx(struct rq *rq, struct task_struct *p, int enq_flags
 	rq->scx.nr_running++;
 	add_nr_running(rq, 1);
 
-	if (SCX_HAS_OP(runnable) && !task_on_rq_migrating(p))
-		SCX_CALL_OP_TASK(SCX_KF_REST, runnable, p, enq_flags);
+	if (SCX_HAS_OP(sch, runnable) && !task_on_rq_migrating(p))
+		SCX_CALL_OP_TASK(sch, SCX_KF_REST, runnable, rq, p, enq_flags);
 
 	if (enq_flags & SCX_ENQ_WAKEUP)
 		touch_core_sched(rq, p);
@@ -2280,11 +2402,12 @@ out:
 
 	if ((enq_flags & SCX_ENQ_CPU_SELECTED) &&
 	    unlikely(cpu_of(rq) != p->scx.selected_cpu))
-		__scx_add_event(SCX_EV_SELECT_CPU_FALLBACK, 1);
+		__scx_add_event(sch, SCX_EV_SELECT_CPU_FALLBACK, 1);
 }
 
-static void ops_dequeue(struct task_struct *p, u64 deq_flags)
+static void ops_dequeue(struct rq *rq, struct task_struct *p, u64 deq_flags)
 {
+	struct scx_sched *sch = scx_root;
 	unsigned long opss;
 
 	/* dequeue is always temporary, don't reset runnable_at */
@@ -2303,8 +2426,9 @@ static void ops_dequeue(struct task_struct *p, u64 deq_flags)
 		 */
 		BUG();
 	case SCX_OPSS_QUEUED:
-		if (SCX_HAS_OP(dequeue))
-			SCX_CALL_OP_TASK(SCX_KF_REST, dequeue, p, deq_flags);
+		if (SCX_HAS_OP(sch, dequeue))
+			SCX_CALL_OP_TASK(sch, SCX_KF_REST, dequeue, rq,
+					 p, deq_flags);
 
 		if (atomic_long_try_cmpxchg(&p->scx.ops_state, &opss,
 					    SCX_OPSS_NONE))
@@ -2332,12 +2456,14 @@ static void ops_dequeue(struct task_struct *p, u64 deq_flags)
 
 static bool dequeue_task_scx(struct rq *rq, struct task_struct *p, int deq_flags)
 {
+	struct scx_sched *sch = scx_root;
+
 	if (!(p->scx.flags & SCX_TASK_QUEUED)) {
 		WARN_ON_ONCE(task_runnable(p));
 		return true;
 	}
 
-	ops_dequeue(p, deq_flags);
+	ops_dequeue(rq, p, deq_flags);
 
 	/*
 	 * A currently running task which is going off @rq first gets dequeued
@@ -2351,13 +2477,13 @@ static bool dequeue_task_scx(struct rq *rq, struct task_struct *p, int deq_flags
 	 * information meaningful to the BPF scheduler and can be suppressed by
 	 * skipping the callbacks if the task is !QUEUED.
 	 */
-	if (SCX_HAS_OP(stopping) && task_current(rq, p)) {
+	if (SCX_HAS_OP(sch, stopping) && task_current(rq, p)) {
 		update_curr_scx(rq);
-		SCX_CALL_OP_TASK(SCX_KF_REST, stopping, p, false);
+		SCX_CALL_OP_TASK(sch, SCX_KF_REST, stopping, rq, p, false);
 	}
 
-	if (SCX_HAS_OP(quiescent) && !task_on_rq_migrating(p))
-		SCX_CALL_OP_TASK(SCX_KF_REST, quiescent, p, deq_flags);
+	if (SCX_HAS_OP(sch, quiescent) && !task_on_rq_migrating(p))
+		SCX_CALL_OP_TASK(sch, SCX_KF_REST, quiescent, rq, p, deq_flags);
 
 	if (deq_flags & SCX_DEQ_SLEEP)
 		p->scx.flags |= SCX_TASK_DEQD_FOR_SLEEP;
@@ -2374,20 +2500,23 @@ static bool dequeue_task_scx(struct rq *rq, struct task_struct *p, int deq_flags
 
 static void yield_task_scx(struct rq *rq)
 {
+	struct scx_sched *sch = scx_root;
 	struct task_struct *p = rq->curr;
 
-	if (SCX_HAS_OP(yield))
-		SCX_CALL_OP_2TASKS_RET(SCX_KF_REST, yield, p, NULL);
+	if (SCX_HAS_OP(sch, yield))
+		SCX_CALL_OP_2TASKS_RET(sch, SCX_KF_REST, yield, rq, p, NULL);
 	else
 		p->scx.slice = 0;
 }
 
 static bool yield_to_task_scx(struct rq *rq, struct task_struct *to)
 {
+	struct scx_sched *sch = scx_root;
 	struct task_struct *from = rq->curr;
 
-	if (SCX_HAS_OP(yield))
-		return SCX_CALL_OP_2TASKS_RET(SCX_KF_REST, yield, from, to);
+	if (SCX_HAS_OP(sch, yield))
+		return SCX_CALL_OP_2TASKS_RET(sch, SCX_KF_REST, yield, rq,
+					      from, to);
 	else
 		return false;
 }
@@ -2467,7 +2596,8 @@ static void move_remote_task_to_local_dsq(struct task_struct *p, u64 enq_flags,
  *
  * The caller must ensure that @p and @rq are on different CPUs.
  */
-static bool task_can_run_on_remote_rq(struct task_struct *p, struct rq *rq,
+static bool task_can_run_on_remote_rq(struct scx_sched *sch,
+				      struct task_struct *p, struct rq *rq,
 				      bool enforce)
 {
 	int cpu = cpu_of(rq);
@@ -2488,8 +2618,8 @@ static bool task_can_run_on_remote_rq(struct task_struct *p, struct rq *rq,
 	 */
 	if (unlikely(is_migration_disabled(p))) {
 		if (enforce)
-			scx_ops_error("SCX_DSQ_LOCAL[_ON] cannot move migration disabled %s[%d] from CPU %d to %d",
-				      p->comm, p->pid, task_cpu(p), cpu);
+			scx_error(sch, "SCX_DSQ_LOCAL[_ON] cannot move migration disabled %s[%d] from CPU %d to %d",
+				  p->comm, p->pid, task_cpu(p), cpu);
 		return false;
 	}
 
@@ -2501,14 +2631,15 @@ static bool task_can_run_on_remote_rq(struct task_struct *p, struct rq *rq,
 	 */
 	if (!task_allowed_on_cpu(p, cpu)) {
 		if (enforce)
-			scx_ops_error("SCX_DSQ_LOCAL[_ON] target CPU %d not allowed for %s[%d]",
-				      cpu, p->comm, p->pid);
+			scx_error(sch, "SCX_DSQ_LOCAL[_ON] target CPU %d not allowed for %s[%d]",
+				  cpu, p->comm, p->pid);
 		return false;
 	}
 
 	if (!scx_rq_online(rq)) {
 		if (enforce)
-			__scx_add_event(SCX_EV_DISPATCH_LOCAL_DSQ_OFFLINE, 1);
+			__scx_add_event(scx_root,
+					SCX_EV_DISPATCH_LOCAL_DSQ_OFFLINE, 1);
 		return false;
 	}
 
@@ -2580,12 +2711,13 @@ static bool consume_remote_task(struct rq *this_rq, struct task_struct *p,
 }
 #else	/* CONFIG_SMP */
 static inline void move_remote_task_to_local_dsq(struct task_struct *p, u64 enq_flags, struct rq *src_rq, struct rq *dst_rq) { WARN_ON_ONCE(1); }
-static inline bool task_can_run_on_remote_rq(struct task_struct *p, struct rq *rq, bool enforce) { return false; }
+static inline bool task_can_run_on_remote_rq(struct scx_sched *sch, struct task_struct *p, struct rq *rq, bool enforce) { return false; }
 static inline bool consume_remote_task(struct rq *this_rq, struct task_struct *p, struct scx_dispatch_q *dsq, struct rq *task_rq) { return false; }
 #endif	/* CONFIG_SMP */
 
 /**
  * move_task_between_dsqs() - Move a task from one DSQ to another
+ * @sch: scx_sched being operated on
  * @p: target task
  * @enq_flags: %SCX_ENQ_*
  * @src_dsq: DSQ @p is currently on, must not be a local DSQ
@@ -2599,7 +2731,8 @@ static inline bool consume_remote_task(struct rq *this_rq, struct task_struct *p
  * On return, @src_dsq is unlocked and only @p's new task_rq, which is the
  * return value, is locked.
  */
-static struct rq *move_task_between_dsqs(struct task_struct *p, u64 enq_flags,
+static struct rq *move_task_between_dsqs(struct scx_sched *sch,
+					 struct task_struct *p, u64 enq_flags,
 					 struct scx_dispatch_q *src_dsq,
 					 struct scx_dispatch_q *dst_dsq)
 {
@@ -2612,7 +2745,7 @@ static struct rq *move_task_between_dsqs(struct task_struct *p, u64 enq_flags,
 	if (dst_dsq->id == SCX_DSQ_LOCAL) {
 		dst_rq = container_of(dst_dsq, struct rq, scx.local_dsq);
 		if (src_rq != dst_rq &&
-		    unlikely(!task_can_run_on_remote_rq(p, dst_rq, true))) {
+		    unlikely(!task_can_run_on_remote_rq(sch, p, dst_rq, true))) {
 			dst_dsq = find_global_dsq(p);
 			dst_rq = src_rq;
 		}
@@ -2646,7 +2779,7 @@ static struct rq *move_task_between_dsqs(struct task_struct *p, u64 enq_flags,
 		p->scx.dsq = NULL;
 		raw_spin_unlock(&src_dsq->lock);
 
-		dispatch_enqueue(dst_dsq, p, enq_flags);
+		dispatch_enqueue(sch, dst_dsq, p, enq_flags);
 	}
 
 	return dst_rq;
@@ -2658,13 +2791,13 @@ static struct rq *move_task_between_dsqs(struct task_struct *p, u64 enq_flags,
  * to the bypass mode can take a long time. Inject artificial delays while the
  * bypass mode is switching to guarantee timely completion.
  */
-static void scx_ops_breather(struct rq *rq)
+static void scx_breather(struct rq *rq)
 {
 	u64 until;
 
 	lockdep_assert_rq_held(rq);
 
-	if (likely(!atomic_read(&scx_ops_breather_depth)))
+	if (likely(!atomic_read(&scx_breather_depth)))
 		return;
 
 	raw_spin_rq_unlock(rq);
@@ -2673,25 +2806,26 @@ static void scx_ops_breather(struct rq *rq)
 
 	do {
 		int cnt = 1024;
-		while (atomic_read(&scx_ops_breather_depth) && --cnt)
+		while (atomic_read(&scx_breather_depth) && --cnt)
 			cpu_relax();
-	} while (atomic_read(&scx_ops_breather_depth) &&
+	} while (atomic_read(&scx_breather_depth) &&
 		 time_before64(ktime_get_ns(), until));
 
 	raw_spin_rq_lock(rq);
 }
 
-static bool consume_dispatch_q(struct rq *rq, struct scx_dispatch_q *dsq)
+static bool consume_dispatch_q(struct scx_sched *sch, struct rq *rq,
+			       struct scx_dispatch_q *dsq)
 {
 	struct task_struct *p;
 retry:
 	/*
-	 * This retry loop can repeatedly race against scx_ops_bypass()
-	 * dequeueing tasks from @dsq trying to put the system into the bypass
-	 * mode. On some multi-socket machines (e.g. 2x Intel 8480c), this can
-	 * live-lock the machine into soft lockups. Give a breather.
+	 * This retry loop can repeatedly race against scx_bypass() dequeueing
+	 * tasks from @dsq trying to put the system into the bypass mode. On
+	 * some multi-socket machines (e.g. 2x Intel 8480c), this can live-lock
+	 * the machine into soft lockups. Give a breather.
 	 */
-	scx_ops_breather(rq);
+	scx_breather(rq);
 
 	/*
 	 * The caller can't expect to successfully consume a task if the task's
@@ -2713,7 +2847,7 @@ retry:
 			return true;
 		}
 
-		if (task_can_run_on_remote_rq(p, rq, false)) {
+		if (task_can_run_on_remote_rq(sch, p, rq, false)) {
 			if (likely(consume_remote_task(rq, p, dsq, task_rq)))
 				return true;
 			goto retry;
@@ -2724,15 +2858,16 @@ retry:
 	return false;
 }
 
-static bool consume_global_dsq(struct rq *rq)
+static bool consume_global_dsq(struct scx_sched *sch, struct rq *rq)
 {
 	int node = cpu_to_node(cpu_of(rq));
 
-	return consume_dispatch_q(rq, global_dsqs[node]);
+	return consume_dispatch_q(sch, rq, sch->global_dsqs[node]);
 }
 
 /**
  * dispatch_to_local_dsq - Dispatch a task to a local dsq
+ * @sch: scx_sched being operated on
  * @rq: current rq which is locked
  * @dst_dsq: destination DSQ
  * @p: task to dispatch
@@ -2745,7 +2880,8 @@ static bool consume_global_dsq(struct rq *rq)
  * The caller must have exclusive ownership of @p (e.g. through
  * %SCX_OPSS_DISPATCHING).
  */
-static void dispatch_to_local_dsq(struct rq *rq, struct scx_dispatch_q *dst_dsq,
+static void dispatch_to_local_dsq(struct scx_sched *sch, struct rq *rq,
+				  struct scx_dispatch_q *dst_dsq,
 				  struct task_struct *p, u64 enq_flags)
 {
 	struct rq *src_rq = task_rq(p);
@@ -2761,14 +2897,15 @@ static void dispatch_to_local_dsq(struct rq *rq, struct scx_dispatch_q *dst_dsq,
 	 * If dispatching to @rq that @p is already on, no lock dancing needed.
 	 */
 	if (rq == src_rq && rq == dst_rq) {
-		dispatch_enqueue(dst_dsq, p, enq_flags | SCX_ENQ_CLEAR_OPSS);
+		dispatch_enqueue(sch, dst_dsq, p,
+				 enq_flags | SCX_ENQ_CLEAR_OPSS);
 		return;
 	}
 
 #ifdef CONFIG_SMP
 	if (src_rq != dst_rq &&
-	    unlikely(!task_can_run_on_remote_rq(p, dst_rq, true))) {
-		dispatch_enqueue(find_global_dsq(p), p,
+	    unlikely(!task_can_run_on_remote_rq(sch, p, dst_rq, true))) {
+		dispatch_enqueue(sch, find_global_dsq(p), p,
 				 enq_flags | SCX_ENQ_CLEAR_OPSS);
 		return;
 	}
@@ -2806,7 +2943,8 @@ static void dispatch_to_local_dsq(struct rq *rq, struct scx_dispatch_q *dst_dsq,
 		 */
 		if (src_rq == dst_rq) {
 			p->scx.holding_cpu = -1;
-			dispatch_enqueue(&dst_rq->scx.local_dsq, p, enq_flags);
+			dispatch_enqueue(sch, &dst_rq->scx.local_dsq, p,
+					 enq_flags);
 		} else {
 			move_remote_task_to_local_dsq(p, enq_flags,
 						      src_rq, dst_rq);
@@ -2848,7 +2986,8 @@ static void dispatch_to_local_dsq(struct rq *rq, struct scx_dispatch_q *dst_dsq,
  * was valid in the first place. Make sure that the task is still owned by the
  * BPF scheduler and claim the ownership before dispatching.
  */
-static void finish_dispatch(struct rq *rq, struct task_struct *p,
+static void finish_dispatch(struct scx_sched *sch, struct rq *rq,
+			    struct task_struct *p,
 			    unsigned long qseq_at_dispatch,
 			    u64 dsq_id, u64 enq_flags)
 {
@@ -2901,15 +3040,15 @@ retry:
 
 	BUG_ON(!(p->scx.flags & SCX_TASK_QUEUED));
 
-	dsq = find_dsq_for_dispatch(this_rq(), dsq_id, p);
+	dsq = find_dsq_for_dispatch(sch, this_rq(), dsq_id, p);
 
 	if (dsq->id == SCX_DSQ_LOCAL)
-		dispatch_to_local_dsq(rq, dsq, p, enq_flags);
+		dispatch_to_local_dsq(sch, rq, dsq, p, enq_flags);
 	else
-		dispatch_enqueue(dsq, p, enq_flags | SCX_ENQ_CLEAR_OPSS);
+		dispatch_enqueue(sch, dsq, p, enq_flags | SCX_ENQ_CLEAR_OPSS);
 }
 
-static void flush_dispatch_buf(struct rq *rq)
+static void flush_dispatch_buf(struct scx_sched *sch, struct rq *rq)
 {
 	struct scx_dsp_ctx *dspc = this_cpu_ptr(scx_dsp_ctx);
 	u32 u;
@@ -2917,7 +3056,7 @@ static void flush_dispatch_buf(struct rq *rq)
 	for (u = 0; u < dspc->cursor; u++) {
 		struct scx_dsp_buf_ent *ent = &dspc->buf[u];
 
-		finish_dispatch(rq, ent->task, ent->qseq, ent->dsq_id,
+		finish_dispatch(sch, rq, ent->task, ent->qseq, ent->dsq_id,
 				ent->enq_flags);
 	}
 
@@ -2927,6 +3066,7 @@ static void flush_dispatch_buf(struct rq *rq)
 
 static int balance_one(struct rq *rq, struct task_struct *prev)
 {
+	struct scx_sched *sch = scx_root;
 	struct scx_dsp_ctx *dspc = this_cpu_ptr(scx_dsp_ctx);
 	bool prev_on_scx = prev->sched_class == &ext_sched_class;
 	bool prev_on_rq = prev->scx.flags & SCX_TASK_QUEUED;
@@ -2936,7 +3076,7 @@ static int balance_one(struct rq *rq, struct task_struct *prev)
 	rq->scx.flags |= SCX_RQ_IN_BALANCE;
 	rq->scx.flags &= ~(SCX_RQ_BAL_PENDING | SCX_RQ_BAL_KEEP);
 
-	if (static_branch_unlikely(&scx_ops_cpu_preempt) &&
+	if ((sch->ops.flags & SCX_OPS_HAS_CPU_PREEMPT) &&
 	    unlikely(rq->scx.cpu_released)) {
 		/*
 		 * If the previous sched_class for the current CPU was not SCX,
@@ -2944,8 +3084,9 @@ static int balance_one(struct rq *rq, struct task_struct *prev)
 		 * core. This callback complements ->cpu_release(), which is
 		 * emitted in switch_class().
 		 */
-		if (SCX_HAS_OP(cpu_acquire))
-			SCX_CALL_OP(SCX_KF_REST, cpu_acquire, cpu_of(rq), NULL);
+		if (SCX_HAS_OP(sch, cpu_acquire))
+			SCX_CALL_OP(sch, SCX_KF_REST, cpu_acquire, rq,
+				    cpu_of(rq), NULL);
 		rq->scx.cpu_released = false;
 	}
 
@@ -2959,8 +3100,8 @@ static int balance_one(struct rq *rq, struct task_struct *prev)
 		 * scheduler wants to handle this explicitly, it should
 		 * implement ->cpu_release().
 		 *
-		 * See scx_ops_disable_workfn() for the explanation on the
-		 * bypassing test.
+		 * See scx_disable_workfn() for the explanation on the bypassing
+		 * test.
 		 */
 		if (prev_on_rq && prev->scx.slice && !scx_rq_bypassing(rq)) {
 			rq->scx.flags |= SCX_RQ_BAL_KEEP;
@@ -2972,10 +3113,11 @@ static int balance_one(struct rq *rq, struct task_struct *prev)
 	if (rq->scx.local_dsq.nr)
 		goto has_tasks;
 
-	if (consume_global_dsq(rq))
+	if (consume_global_dsq(sch, rq))
 		goto has_tasks;
 
-	if (!SCX_HAS_OP(dispatch) || scx_rq_bypassing(rq) || !scx_rq_online(rq))
+	if (unlikely(!SCX_HAS_OP(sch, dispatch)) ||
+	    scx_rq_bypassing(rq) || !scx_rq_online(rq))
 		goto no_tasks;
 
 	dspc->rq = rq;
@@ -2990,10 +3132,10 @@ static int balance_one(struct rq *rq, struct task_struct *prev)
 	do {
 		dspc->nr_tasks = 0;
 
-		SCX_CALL_OP(SCX_KF_DISPATCH, dispatch, cpu_of(rq),
-			    prev_on_scx ? prev : NULL);
+		SCX_CALL_OP(sch, SCX_KF_DISPATCH, dispatch, rq,
+			    cpu_of(rq), prev_on_scx ? prev : NULL);
 
-		flush_dispatch_buf(rq);
+		flush_dispatch_buf(sch, rq);
 
 		if (prev_on_rq && prev->scx.slice) {
 			rq->scx.flags |= SCX_RQ_BAL_KEEP;
@@ -3001,7 +3143,7 @@ static int balance_one(struct rq *rq, struct task_struct *prev)
 		}
 		if (rq->scx.local_dsq.nr)
 			goto has_tasks;
-		if (consume_global_dsq(rq))
+		if (consume_global_dsq(sch, rq))
 			goto has_tasks;
 
 		/*
@@ -3024,10 +3166,10 @@ no_tasks:
 	 * Didn't find another task to run. Keep running @prev unless
 	 * %SCX_OPS_ENQ_LAST is in effect.
 	 */
-	if (prev_on_rq && (!static_branch_unlikely(&scx_ops_enq_last) ||
-	     scx_rq_bypassing(rq))) {
+	if (prev_on_rq &&
+	    (!(sch->ops.flags & SCX_OPS_ENQ_LAST) || scx_rq_bypassing(rq))) {
 		rq->scx.flags |= SCX_RQ_BAL_KEEP;
-		__scx_add_event(SCX_EV_DISPATCH_KEEP_LAST, 1);
+		__scx_add_event(sch, SCX_EV_DISPATCH_KEEP_LAST, 1);
 		goto has_tasks;
 	}
 	rq->scx.flags &= ~SCX_RQ_IN_BALANCE;
@@ -3087,32 +3229,36 @@ static void process_ddsp_deferred_locals(struct rq *rq)
 	 */
 	while ((p = list_first_entry_or_null(&rq->scx.ddsp_deferred_locals,
 				struct task_struct, scx.dsq_list.node))) {
+		struct scx_sched *sch = scx_root;
 		struct scx_dispatch_q *dsq;
 
 		list_del_init(&p->scx.dsq_list.node);
 
-		dsq = find_dsq_for_dispatch(rq, p->scx.ddsp_dsq_id, p);
+		dsq = find_dsq_for_dispatch(sch, rq, p->scx.ddsp_dsq_id, p);
 		if (!WARN_ON_ONCE(dsq->id != SCX_DSQ_LOCAL))
-			dispatch_to_local_dsq(rq, dsq, p, p->scx.ddsp_enq_flags);
+			dispatch_to_local_dsq(sch, rq, dsq, p,
+					      p->scx.ddsp_enq_flags);
 	}
 }
 
 static void set_next_task_scx(struct rq *rq, struct task_struct *p, bool first)
 {
+	struct scx_sched *sch = scx_root;
+
 	if (p->scx.flags & SCX_TASK_QUEUED) {
 		/*
 		 * Core-sched might decide to execute @p before it is
 		 * dispatched. Call ops_dequeue() to notify the BPF scheduler.
 		 */
-		ops_dequeue(p, SCX_DEQ_CORE_SCHED_EXEC);
+		ops_dequeue(rq, p, SCX_DEQ_CORE_SCHED_EXEC);
 		dispatch_dequeue(rq, p);
 	}
 
 	p->se.exec_start = rq_clock_task(rq);
 
 	/* see dequeue_task_scx() on why we skip when !QUEUED */
-	if (SCX_HAS_OP(running) && (p->scx.flags & SCX_TASK_QUEUED))
-		SCX_CALL_OP_TASK(SCX_KF_REST, running, p);
+	if (SCX_HAS_OP(sch, running) && (p->scx.flags & SCX_TASK_QUEUED))
+		SCX_CALL_OP_TASK(sch, SCX_KF_REST, running, rq, p);
 
 	clr_task_runnable(p, true);
 
@@ -3155,6 +3301,7 @@ preempt_reason_from_class(const struct sched_class *class)
 
 static void switch_class(struct rq *rq, struct task_struct *next)
 {
+	struct scx_sched *sch = scx_root;
 	const struct sched_class *next_class = next->sched_class;
 
 #ifdef CONFIG_SMP
@@ -3165,7 +3312,7 @@ static void switch_class(struct rq *rq, struct task_struct *next)
 	 */
 	smp_store_release(&rq->scx.pnt_seq, rq->scx.pnt_seq + 1);
 #endif
-	if (!static_branch_unlikely(&scx_ops_cpu_preempt))
+	if (!(sch->ops.flags & SCX_OPS_HAS_CPU_PREEMPT))
 		return;
 
 	/*
@@ -3187,14 +3334,14 @@ static void switch_class(struct rq *rq, struct task_struct *next)
 	 *  next time that balance_scx() is invoked.
 	 */
 	if (!rq->scx.cpu_released) {
-		if (SCX_HAS_OP(cpu_release)) {
+		if (SCX_HAS_OP(sch, cpu_release)) {
 			struct scx_cpu_release_args args = {
 				.reason = preempt_reason_from_class(next_class),
 				.task = next,
 			};
 
-			SCX_CALL_OP(SCX_KF_CPU_RELEASE,
-				    cpu_release, cpu_of(rq), &args);
+			SCX_CALL_OP(sch, SCX_KF_CPU_RELEASE, cpu_release, rq,
+				    cpu_of(rq), &args);
 		}
 		rq->scx.cpu_released = true;
 	}
@@ -3203,11 +3350,12 @@ static void switch_class(struct rq *rq, struct task_struct *next)
 static void put_prev_task_scx(struct rq *rq, struct task_struct *p,
 			      struct task_struct *next)
 {
+	struct scx_sched *sch = scx_root;
 	update_curr_scx(rq);
 
 	/* see dequeue_task_scx() on why we skip when !QUEUED */
-	if (SCX_HAS_OP(stopping) && (p->scx.flags & SCX_TASK_QUEUED))
-		SCX_CALL_OP_TASK(SCX_KF_REST, stopping, p, true);
+	if (SCX_HAS_OP(sch, stopping) && (p->scx.flags & SCX_TASK_QUEUED))
+		SCX_CALL_OP_TASK(sch, SCX_KF_REST, stopping, rq, p, true);
 
 	if (p->scx.flags & SCX_TASK_QUEUED) {
 		set_task_runnable(rq, p);
@@ -3219,7 +3367,8 @@ static void put_prev_task_scx(struct rq *rq, struct task_struct *p,
 		 * DSQ.
 		 */
 		if (p->scx.slice && !scx_rq_bypassing(rq)) {
-			dispatch_enqueue(&rq->scx.local_dsq, p, SCX_ENQ_HEAD);
+			dispatch_enqueue(sch, &rq->scx.local_dsq, p,
+					 SCX_ENQ_HEAD);
 			goto switch_class;
 		}
 
@@ -3230,7 +3379,7 @@ static void put_prev_task_scx(struct rq *rq, struct task_struct *p,
 		 * which should trigger an explicit follow-up scheduling event.
 		 */
 		if (sched_class_above(&ext_sched_class, next->sched_class)) {
-			WARN_ON_ONCE(!static_branch_unlikely(&scx_ops_enq_last));
+			WARN_ON_ONCE(!(sch->ops.flags & SCX_OPS_ENQ_LAST));
 			do_enqueue_task(rq, p, SCX_ENQ_LAST, -1);
 		} else {
 			do_enqueue_task(rq, p, 0, -1);
@@ -3283,7 +3432,7 @@ static struct task_struct *pick_task_scx(struct rq *rq)
 		 * Can happen while enabling as SCX_RQ_BAL_PENDING assertion is
 		 * conditional on scx_enabled() and may have been skipped.
 		 */
-		WARN_ON_ONCE(scx_ops_enable_state() == SCX_OPS_ENABLED);
+		WARN_ON_ONCE(scx_enable_state() == SCX_ENABLED);
 		keep_prev = false;
 	}
 
@@ -3294,10 +3443,8 @@ static struct task_struct *pick_task_scx(struct rq *rq)
 	 */
 	if (keep_prev) {
 		p = prev;
-		if (!p->scx.slice) {
-			p->scx.slice = SCX_SLICE_DFL;
-			__scx_add_event(SCX_EV_ENQ_SLICE_DFL, 1);
-		}
+		if (!p->scx.slice)
+			refill_task_slice_dfl(p);
 	} else {
 		p = first_local_task(rq);
 		if (!p) {
@@ -3307,13 +3454,14 @@ static struct task_struct *pick_task_scx(struct rq *rq)
 		}
 
 		if (unlikely(!p->scx.slice)) {
-			if (!scx_rq_bypassing(rq) && !scx_warned_zero_slice) {
+			struct scx_sched *sch = scx_root;
+
+			if (!scx_rq_bypassing(rq) && !sch->warned_zero_slice) {
 				printk_deferred(KERN_WARNING "sched_ext: %s[%d] has zero slice in %s()\n",
 						p->comm, p->pid, __func__);
-				scx_warned_zero_slice = true;
+				sch->warned_zero_slice = true;
 			}
-			p->scx.slice = SCX_SLICE_DFL;
-			__scx_add_event(SCX_EV_ENQ_SLICE_DFL, 1);
+			refill_task_slice_dfl(p);
 		}
 	}
 
@@ -3342,13 +3490,17 @@ static struct task_struct *pick_task_scx(struct rq *rq)
 bool scx_prio_less(const struct task_struct *a, const struct task_struct *b,
 		   bool in_fi)
 {
+	struct scx_sched *sch = scx_root;
+
 	/*
 	 * The const qualifiers are dropped from task_struct pointers when
 	 * calling ops.core_sched_before(). Accesses are controlled by the
 	 * verifier.
 	 */
-	if (SCX_HAS_OP(core_sched_before) && !scx_rq_bypassing(task_rq(a)))
-		return SCX_CALL_OP_2TASKS_RET(SCX_KF_REST, core_sched_before,
+	if (SCX_HAS_OP(sch, core_sched_before) &&
+	    !scx_rq_bypassing(task_rq(a)))
+		return SCX_CALL_OP_2TASKS_RET(sch, SCX_KF_REST, core_sched_before,
+					      NULL,
 					      (struct task_struct *)a,
 					      (struct task_struct *)b);
 	else
@@ -3360,6 +3512,7 @@ bool scx_prio_less(const struct task_struct *a, const struct task_struct *b,
 
 static int select_task_rq_scx(struct task_struct *p, int prev_cpu, int wake_flags)
 {
+	struct scx_sched *sch = scx_root;
 	bool rq_bypass;
 
 	/*
@@ -3376,7 +3529,7 @@ static int select_task_rq_scx(struct task_struct *p, int prev_cpu, int wake_flag
 		return prev_cpu;
 
 	rq_bypass = scx_rq_bypassing(task_rq(p));
-	if (SCX_HAS_OP(select_cpu) && !rq_bypass) {
+	if (likely(SCX_HAS_OP(sch, select_cpu)) && !rq_bypass) {
 		s32 cpu;
 		struct task_struct **ddsp_taskp;
 
@@ -3384,29 +3537,30 @@ static int select_task_rq_scx(struct task_struct *p, int prev_cpu, int wake_flag
 		WARN_ON_ONCE(*ddsp_taskp);
 		*ddsp_taskp = p;
 
-		cpu = SCX_CALL_OP_TASK_RET(SCX_KF_ENQUEUE | SCX_KF_SELECT_CPU,
-					   select_cpu, p, prev_cpu, wake_flags);
+		cpu = SCX_CALL_OP_TASK_RET(sch,
+					   SCX_KF_ENQUEUE | SCX_KF_SELECT_CPU,
+					   select_cpu, NULL, p, prev_cpu,
+					   wake_flags);
 		p->scx.selected_cpu = cpu;
 		*ddsp_taskp = NULL;
-		if (ops_cpu_valid(cpu, "from ops.select_cpu()"))
+		if (ops_cpu_valid(sch, cpu, "from ops.select_cpu()"))
 			return cpu;
 		else
 			return prev_cpu;
 	} else {
 		s32 cpu;
 
-		cpu = scx_select_cpu_dfl(p, prev_cpu, wake_flags, 0);
+		cpu = scx_select_cpu_dfl(p, prev_cpu, wake_flags, NULL, 0);
 		if (cpu >= 0) {
-			p->scx.slice = SCX_SLICE_DFL;
+			refill_task_slice_dfl(p);
 			p->scx.ddsp_dsq_id = SCX_DSQ_LOCAL;
-			__scx_add_event(SCX_EV_ENQ_SLICE_DFL, 1);
 		} else {
 			cpu = prev_cpu;
 		}
 		p->scx.selected_cpu = cpu;
 
 		if (rq_bypass)
-			__scx_add_event(SCX_EV_BYPASS_DISPATCH, 1);
+			__scx_add_event(sch, SCX_EV_BYPASS_DISPATCH, 1);
 		return cpu;
 	}
 }
@@ -3419,6 +3573,8 @@ static void task_woken_scx(struct rq *rq, struct task_struct *p)
 static void set_cpus_allowed_scx(struct task_struct *p,
 				 struct affinity_context *ac)
 {
+	struct scx_sched *sch = scx_root;
+
 	set_cpus_allowed_common(p, ac);
 
 	/*
@@ -3429,28 +3585,38 @@ static void set_cpus_allowed_scx(struct task_struct *p,
 	 * Fine-grained memory write control is enforced by BPF making the const
 	 * designation pointless. Cast it away when calling the operation.
 	 */
-	if (SCX_HAS_OP(set_cpumask))
-		SCX_CALL_OP_TASK(SCX_KF_REST, set_cpumask, p,
-				 (struct cpumask *)p->cpus_ptr);
+	if (SCX_HAS_OP(sch, set_cpumask))
+		SCX_CALL_OP_TASK(sch, SCX_KF_REST, set_cpumask, NULL,
+				 p, (struct cpumask *)p->cpus_ptr);
 }
 
 static void handle_hotplug(struct rq *rq, bool online)
 {
+	struct scx_sched *sch = scx_root;
 	int cpu = cpu_of(rq);
 
 	atomic_long_inc(&scx_hotplug_seq);
 
+	/*
+	 * scx_root updates are protected by cpus_read_lock() and will stay
+	 * stable here. Note that we can't depend on scx_enabled() test as the
+	 * hotplug ops need to be enabled before __scx_enabled is set.
+	 */
+	if (unlikely(!sch))
+		return;
+
 	if (scx_enabled())
-		scx_idle_update_selcpu_topology(&scx_ops);
+		scx_idle_update_selcpu_topology(&sch->ops);
 
-	if (online && SCX_HAS_OP(cpu_online))
-		SCX_CALL_OP(SCX_KF_UNLOCKED, cpu_online, cpu);
-	else if (!online && SCX_HAS_OP(cpu_offline))
-		SCX_CALL_OP(SCX_KF_UNLOCKED, cpu_offline, cpu);
+	if (online && SCX_HAS_OP(sch, cpu_online))
+		SCX_CALL_OP(sch, SCX_KF_UNLOCKED, cpu_online, NULL, cpu);
+	else if (!online && SCX_HAS_OP(sch, cpu_offline))
+		SCX_CALL_OP(sch, SCX_KF_UNLOCKED, cpu_offline, NULL, cpu);
 	else
-		scx_ops_exit(SCX_ECODE_ACT_RESTART | SCX_ECODE_RSN_HOTPLUG,
-			     "cpu %d going %s, exiting scheduler", cpu,
-			     online ? "online" : "offline");
+		scx_exit(sch, SCX_EXIT_UNREG_KERN,
+			 SCX_ECODE_ACT_RESTART | SCX_ECODE_RSN_HOTPLUG,
+			 "cpu %d going %s, exiting scheduler", cpu,
+			 online ? "online" : "offline");
 }
 
 void scx_rq_activate(struct rq *rq)
@@ -3477,11 +3643,16 @@ static void rq_offline_scx(struct rq *rq)
 
 static bool check_rq_for_timeouts(struct rq *rq)
 {
+	struct scx_sched *sch;
 	struct task_struct *p;
 	struct rq_flags rf;
 	bool timed_out = false;
 
 	rq_lock_irqsave(rq, &rf);
+	sch = rcu_dereference_bh(scx_root);
+	if (unlikely(!sch))
+		goto out_unlock;
+
 	list_for_each_entry(p, &rq->scx.runnable_list, scx.runnable_node) {
 		unsigned long last_runnable = p->scx.runnable_at;
 
@@ -3489,16 +3660,15 @@ static bool check_rq_for_timeouts(struct rq *rq)
 					last_runnable + scx_watchdog_timeout))) {
 			u32 dur_ms = jiffies_to_msecs(jiffies - last_runnable);
 
-			scx_ops_error_kind(SCX_EXIT_ERROR_STALL,
-					   "%s[%d] failed to run for %u.%03us",
-					   p->comm, p->pid,
-					   dur_ms / 1000, dur_ms % 1000);
+			scx_exit(sch, SCX_EXIT_ERROR_STALL, 0,
+				 "%s[%d] failed to run for %u.%03us",
+				 p->comm, p->pid, dur_ms / 1000, dur_ms % 1000);
 			timed_out = true;
 			break;
 		}
 	}
+out_unlock:
 	rq_unlock_irqrestore(rq, &rf);
-
 	return timed_out;
 }
 
@@ -3520,19 +3690,24 @@ static void scx_watchdog_workfn(struct work_struct *work)
 
 void scx_tick(struct rq *rq)
 {
+	struct scx_sched *sch;
 	unsigned long last_check;
 
 	if (!scx_enabled())
 		return;
 
+	sch = rcu_dereference_bh(scx_root);
+	if (unlikely(!sch))
+		return;
+
 	last_check = READ_ONCE(scx_watchdog_timestamp);
 	if (unlikely(time_after(jiffies,
 				last_check + READ_ONCE(scx_watchdog_timeout)))) {
 		u32 dur_ms = jiffies_to_msecs(jiffies - last_check);
 
-		scx_ops_error_kind(SCX_EXIT_ERROR_STALL,
-				   "watchdog failed to check in for %u.%03us",
-				   dur_ms / 1000, dur_ms % 1000);
+		scx_exit(sch, SCX_EXIT_ERROR_STALL, 0,
+			 "watchdog failed to check in for %u.%03us",
+			 dur_ms / 1000, dur_ms % 1000);
 	}
 
 	update_other_load_avgs(rq);
@@ -3540,6 +3715,8 @@ void scx_tick(struct rq *rq)
 
 static void task_tick_scx(struct rq *rq, struct task_struct *curr, int queued)
 {
+	struct scx_sched *sch = scx_root;
+
 	update_curr_scx(rq);
 
 	/*
@@ -3549,8 +3726,8 @@ static void task_tick_scx(struct rq *rq, struct task_struct *curr, int queued)
 	if (scx_rq_bypassing(rq)) {
 		curr->scx.slice = 0;
 		touch_core_sched(rq, curr);
-	} else if (SCX_HAS_OP(tick)) {
-		SCX_CALL_OP_TASK(SCX_KF_REST, tick, curr);
+	} else if (SCX_HAS_OP(sch, tick)) {
+		SCX_CALL_OP_TASK(sch, SCX_KF_REST, tick, rq, curr);
 	}
 
 	if (!curr->scx.slice)
@@ -3615,21 +3792,23 @@ static void scx_set_task_state(struct task_struct *p, enum scx_task_state state)
 	p->scx.flags |= state << SCX_TASK_STATE_SHIFT;
 }
 
-static int scx_ops_init_task(struct task_struct *p, struct task_group *tg, bool fork)
+static int scx_init_task(struct task_struct *p, struct task_group *tg, bool fork)
 {
+	struct scx_sched *sch = scx_root;
 	int ret;
 
 	p->scx.disallow = false;
 
-	if (SCX_HAS_OP(init_task)) {
+	if (SCX_HAS_OP(sch, init_task)) {
 		struct scx_init_task_args args = {
 			SCX_INIT_TASK_ARGS_CGROUP(tg)
 			.fork = fork,
 		};
 
-		ret = SCX_CALL_OP_RET(SCX_KF_UNLOCKED, init_task, p, &args);
+		ret = SCX_CALL_OP_RET(sch, SCX_KF_UNLOCKED, init_task, NULL,
+				      p, &args);
 		if (unlikely(ret)) {
-			ret = ops_sanitize_err("init_task", ret);
+			ret = ops_sanitize_err(sch, "init_task", ret);
 			return ret;
 		}
 	}
@@ -3657,8 +3836,8 @@ static int scx_ops_init_task(struct task_struct *p, struct task_group *tg, bool
 
 			task_rq_unlock(rq, p, &rf);
 		} else if (p->policy == SCHED_EXT) {
-			scx_ops_error("ops.init_task() set task->scx.disallow for %s[%d] during fork",
-				      p->comm, p->pid);
+			scx_error(sch, "ops.init_task() set task->scx.disallow for %s[%d] during fork",
+				  p->comm, p->pid);
 		}
 	}
 
@@ -3666,11 +3845,13 @@ static int scx_ops_init_task(struct task_struct *p, struct task_group *tg, bool
 	return 0;
 }
 
-static void scx_ops_enable_task(struct task_struct *p)
+static void scx_enable_task(struct task_struct *p)
 {
+	struct scx_sched *sch = scx_root;
+	struct rq *rq = task_rq(p);
 	u32 weight;
 
-	lockdep_assert_rq_held(task_rq(p));
+	lockdep_assert_rq_held(rq);
 
 	/*
 	 * Set the weight before calling ops.enable() so that the scheduler
@@ -3683,26 +3864,31 @@ static void scx_ops_enable_task(struct task_struct *p)
 
 	p->scx.weight = sched_weight_to_cgroup(weight);
 
-	if (SCX_HAS_OP(enable))
-		SCX_CALL_OP_TASK(SCX_KF_REST, enable, p);
+	if (SCX_HAS_OP(sch, enable))
+		SCX_CALL_OP_TASK(sch, SCX_KF_REST, enable, rq, p);
 	scx_set_task_state(p, SCX_TASK_ENABLED);
 
-	if (SCX_HAS_OP(set_weight))
-		SCX_CALL_OP_TASK(SCX_KF_REST, set_weight, p, p->scx.weight);
+	if (SCX_HAS_OP(sch, set_weight))
+		SCX_CALL_OP_TASK(sch, SCX_KF_REST, set_weight, rq,
+				 p, p->scx.weight);
 }
 
-static void scx_ops_disable_task(struct task_struct *p)
+static void scx_disable_task(struct task_struct *p)
 {
-	lockdep_assert_rq_held(task_rq(p));
+	struct scx_sched *sch = scx_root;
+	struct rq *rq = task_rq(p);
+
+	lockdep_assert_rq_held(rq);
 	WARN_ON_ONCE(scx_get_task_state(p) != SCX_TASK_ENABLED);
 
-	if (SCX_HAS_OP(disable))
-		SCX_CALL_OP_TASK(SCX_KF_REST, disable, p);
+	if (SCX_HAS_OP(sch, disable))
+		SCX_CALL_OP_TASK(sch, SCX_KF_REST, disable, rq, p);
 	scx_set_task_state(p, SCX_TASK_READY);
 }
 
-static void scx_ops_exit_task(struct task_struct *p)
+static void scx_exit_task(struct task_struct *p)
 {
+	struct scx_sched *sch = scx_root;
 	struct scx_exit_task_args args = {
 		.cancelled = false,
 	};
@@ -3718,15 +3904,16 @@ static void scx_ops_exit_task(struct task_struct *p)
 	case SCX_TASK_READY:
 		break;
 	case SCX_TASK_ENABLED:
-		scx_ops_disable_task(p);
+		scx_disable_task(p);
 		break;
 	default:
 		WARN_ON_ONCE(true);
 		return;
 	}
 
-	if (SCX_HAS_OP(exit_task))
-		SCX_CALL_OP_TASK(SCX_KF_REST, exit_task, p, &args);
+	if (SCX_HAS_OP(sch, exit_task))
+		SCX_CALL_OP_TASK(sch, SCX_KF_REST, exit_task, task_rq(p),
+				 p, &args);
 	scx_set_task_state(p, SCX_TASK_NONE);
 }
 
@@ -3758,15 +3945,15 @@ int scx_fork(struct task_struct *p)
 {
 	percpu_rwsem_assert_held(&scx_fork_rwsem);
 
-	if (scx_ops_init_task_enabled)
-		return scx_ops_init_task(p, task_group(p), true);
+	if (scx_init_task_enabled)
+		return scx_init_task(p, task_group(p), true);
 	else
 		return 0;
 }
 
 void scx_post_fork(struct task_struct *p)
 {
-	if (scx_ops_init_task_enabled) {
+	if (scx_init_task_enabled) {
 		scx_set_task_state(p, SCX_TASK_READY);
 
 		/*
@@ -3779,7 +3966,7 @@ void scx_post_fork(struct task_struct *p)
 			struct rq *rq;
 
 			rq = task_rq_lock(p, &rf);
-			scx_ops_enable_task(p);
+			scx_enable_task(p);
 			task_rq_unlock(rq, p, &rf);
 		}
 	}
@@ -3799,7 +3986,7 @@ void scx_cancel_fork(struct task_struct *p)
 
 		rq = task_rq_lock(p, &rf);
 		WARN_ON_ONCE(scx_get_task_state(p) >= SCX_TASK_READY);
-		scx_ops_exit_task(p);
+		scx_exit_task(p);
 		task_rq_unlock(rq, p, &rf);
 	}
 
@@ -3815,15 +4002,15 @@ void sched_ext_free(struct task_struct *p)
 	spin_unlock_irqrestore(&scx_tasks_lock, flags);
 
 	/*
-	 * @p is off scx_tasks and wholly ours. scx_ops_enable()'s READY ->
-	 * ENABLED transitions can't race us. Disable ops for @p.
+	 * @p is off scx_tasks and wholly ours. scx_enable()'s READY -> ENABLED
+	 * transitions can't race us. Disable ops for @p.
 	 */
 	if (scx_get_task_state(p) != SCX_TASK_NONE) {
 		struct rq_flags rf;
 		struct rq *rq;
 
 		rq = task_rq_lock(p, &rf);
-		scx_ops_exit_task(p);
+		scx_exit_task(p);
 		task_rq_unlock(rq, p, &rf);
 	}
 }
@@ -3831,11 +4018,14 @@ void sched_ext_free(struct task_struct *p)
 static void reweight_task_scx(struct rq *rq, struct task_struct *p,
 			      const struct load_weight *lw)
 {
+	struct scx_sched *sch = scx_root;
+
 	lockdep_assert_rq_held(task_rq(p));
 
 	p->scx.weight = sched_weight_to_cgroup(scale_load_down(lw->weight));
-	if (SCX_HAS_OP(set_weight))
-		SCX_CALL_OP_TASK(SCX_KF_REST, set_weight, p, p->scx.weight);
+	if (SCX_HAS_OP(sch, set_weight))
+		SCX_CALL_OP_TASK(sch, SCX_KF_REST, set_weight, rq,
+				 p, p->scx.weight);
 }
 
 static void prio_changed_scx(struct rq *rq, struct task_struct *p, int oldprio)
@@ -3844,20 +4034,22 @@ static void prio_changed_scx(struct rq *rq, struct task_struct *p, int oldprio)
 
 static void switching_to_scx(struct rq *rq, struct task_struct *p)
 {
-	scx_ops_enable_task(p);
+	struct scx_sched *sch = scx_root;
+
+	scx_enable_task(p);
 
 	/*
 	 * set_cpus_allowed_scx() is not called while @p is associated with a
 	 * different scheduler class. Keep the BPF scheduler up-to-date.
 	 */
-	if (SCX_HAS_OP(set_cpumask))
-		SCX_CALL_OP_TASK(SCX_KF_REST, set_cpumask, p,
-				 (struct cpumask *)p->cpus_ptr);
+	if (SCX_HAS_OP(sch, set_cpumask))
+		SCX_CALL_OP_TASK(sch, SCX_KF_REST, set_cpumask, rq,
+				 p, (struct cpumask *)p->cpus_ptr);
 }
 
 static void switched_from_scx(struct rq *rq, struct task_struct *p)
 {
-	scx_ops_disable_task(p);
+	scx_disable_task(p);
 }
 
 static void wakeup_preempt_scx(struct rq *rq, struct task_struct *p,int wake_flags) {}
@@ -3902,6 +4094,7 @@ static bool scx_cgroup_enabled;
 
 int scx_tg_online(struct task_group *tg)
 {
+	struct scx_sched *sch = scx_root;
 	int ret = 0;
 
 	WARN_ON_ONCE(tg->scx_flags & (SCX_TG_ONLINE | SCX_TG_INITED));
@@ -3909,14 +4102,14 @@ int scx_tg_online(struct task_group *tg)
 	percpu_down_read(&scx_cgroup_rwsem);
 
 	if (scx_cgroup_enabled) {
-		if (SCX_HAS_OP(cgroup_init)) {
+		if (SCX_HAS_OP(sch, cgroup_init)) {
 			struct scx_cgroup_init_args args =
 				{ .weight = tg->scx_weight };
 
-			ret = SCX_CALL_OP_RET(SCX_KF_UNLOCKED, cgroup_init,
-					      tg->css.cgroup, &args);
+			ret = SCX_CALL_OP_RET(sch, SCX_KF_UNLOCKED, cgroup_init,
+					      NULL, tg->css.cgroup, &args);
 			if (ret)
-				ret = ops_sanitize_err("cgroup_init", ret);
+				ret = ops_sanitize_err(sch, "cgroup_init", ret);
 		}
 		if (ret == 0)
 			tg->scx_flags |= SCX_TG_ONLINE | SCX_TG_INITED;
@@ -3930,12 +4123,16 @@ int scx_tg_online(struct task_group *tg)
 
 void scx_tg_offline(struct task_group *tg)
 {
+	struct scx_sched *sch = scx_root;
+
 	WARN_ON_ONCE(!(tg->scx_flags & SCX_TG_ONLINE));
 
 	percpu_down_read(&scx_cgroup_rwsem);
 
-	if (SCX_HAS_OP(cgroup_exit) && (tg->scx_flags & SCX_TG_INITED))
-		SCX_CALL_OP(SCX_KF_UNLOCKED, cgroup_exit, tg->css.cgroup);
+	if (scx_cgroup_enabled && SCX_HAS_OP(sch, cgroup_exit) &&
+	    (tg->scx_flags & SCX_TG_INITED))
+		SCX_CALL_OP(sch, SCX_KF_UNLOCKED, cgroup_exit, NULL,
+			    tg->css.cgroup);
 	tg->scx_flags &= ~(SCX_TG_ONLINE | SCX_TG_INITED);
 
 	percpu_up_read(&scx_cgroup_rwsem);
@@ -3943,6 +4140,7 @@ void scx_tg_offline(struct task_group *tg)
 
 int scx_cgroup_can_attach(struct cgroup_taskset *tset)
 {
+	struct scx_sched *sch = scx_root;
 	struct cgroup_subsys_state *css;
 	struct task_struct *p;
 	int ret;
@@ -3967,8 +4165,9 @@ int scx_cgroup_can_attach(struct cgroup_taskset *tset)
 		if (from == to)
 			continue;
 
-		if (SCX_HAS_OP(cgroup_prep_move)) {
-			ret = SCX_CALL_OP_RET(SCX_KF_UNLOCKED, cgroup_prep_move,
+		if (SCX_HAS_OP(sch, cgroup_prep_move)) {
+			ret = SCX_CALL_OP_RET(sch, SCX_KF_UNLOCKED,
+					      cgroup_prep_move, NULL,
 					      p, from, css->cgroup);
 			if (ret)
 				goto err;
@@ -3981,18 +4180,21 @@ int scx_cgroup_can_attach(struct cgroup_taskset *tset)
 
 err:
 	cgroup_taskset_for_each(p, css, tset) {
-		if (SCX_HAS_OP(cgroup_cancel_move) && p->scx.cgrp_moving_from)
-			SCX_CALL_OP(SCX_KF_UNLOCKED, cgroup_cancel_move, p,
-				    p->scx.cgrp_moving_from, css->cgroup);
+		if (SCX_HAS_OP(sch, cgroup_cancel_move) &&
+		    p->scx.cgrp_moving_from)
+			SCX_CALL_OP(sch, SCX_KF_UNLOCKED, cgroup_cancel_move, NULL,
+				    p, p->scx.cgrp_moving_from, css->cgroup);
 		p->scx.cgrp_moving_from = NULL;
 	}
 
 	percpu_up_read(&scx_cgroup_rwsem);
-	return ops_sanitize_err("cgroup_prep_move", ret);
+	return ops_sanitize_err(sch, "cgroup_prep_move", ret);
 }
 
 void scx_cgroup_move_task(struct task_struct *p)
 {
+	struct scx_sched *sch = scx_root;
+
 	if (!scx_cgroup_enabled)
 		return;
 
@@ -4000,9 +4202,11 @@ void scx_cgroup_move_task(struct task_struct *p)
 	 * @p must have ops.cgroup_prep_move() called on it and thus
 	 * cgrp_moving_from set.
 	 */
-	if (SCX_HAS_OP(cgroup_move) && !WARN_ON_ONCE(!p->scx.cgrp_moving_from))
-		SCX_CALL_OP_TASK(SCX_KF_UNLOCKED, cgroup_move, p,
-			p->scx.cgrp_moving_from, tg_cgrp(task_group(p)));
+	if (SCX_HAS_OP(sch, cgroup_move) &&
+	    !WARN_ON_ONCE(!p->scx.cgrp_moving_from))
+		SCX_CALL_OP_TASK(sch, SCX_KF_UNLOCKED, cgroup_move, NULL,
+				 p, p->scx.cgrp_moving_from,
+				 tg_cgrp(task_group(p)));
 	p->scx.cgrp_moving_from = NULL;
 }
 
@@ -4013,6 +4217,7 @@ void scx_cgroup_finish_attach(void)
 
 void scx_cgroup_cancel_attach(struct cgroup_taskset *tset)
 {
+	struct scx_sched *sch = scx_root;
 	struct cgroup_subsys_state *css;
 	struct task_struct *p;
 
@@ -4020,9 +4225,10 @@ void scx_cgroup_cancel_attach(struct cgroup_taskset *tset)
 		goto out_unlock;
 
 	cgroup_taskset_for_each(p, css, tset) {
-		if (SCX_HAS_OP(cgroup_cancel_move) && p->scx.cgrp_moving_from)
-			SCX_CALL_OP(SCX_KF_UNLOCKED, cgroup_cancel_move, p,
-				    p->scx.cgrp_moving_from, css->cgroup);
+		if (SCX_HAS_OP(sch, cgroup_cancel_move) &&
+		    p->scx.cgrp_moving_from)
+			SCX_CALL_OP(sch, SCX_KF_UNLOCKED, cgroup_cancel_move, NULL,
+				    p, p->scx.cgrp_moving_from, css->cgroup);
 		p->scx.cgrp_moving_from = NULL;
 	}
 out_unlock:
@@ -4031,11 +4237,13 @@ out_unlock:
 
 void scx_group_set_weight(struct task_group *tg, unsigned long weight)
 {
+	struct scx_sched *sch = scx_root;
+
 	percpu_down_read(&scx_cgroup_rwsem);
 
 	if (scx_cgroup_enabled && tg->scx_weight != weight) {
-		if (SCX_HAS_OP(cgroup_set_weight))
-			SCX_CALL_OP(SCX_KF_UNLOCKED, cgroup_set_weight,
+		if (SCX_HAS_OP(sch, cgroup_set_weight))
+			SCX_CALL_OP(sch, SCX_KF_UNLOCKED, cgroup_set_weight, NULL,
 				    tg_cgrp(tg), weight);
 		tg->scx_weight = weight;
 	}
@@ -4124,29 +4332,6 @@ static void init_dsq(struct scx_dispatch_q *dsq, u64 dsq_id)
 	dsq->id = dsq_id;
 }
 
-static struct scx_dispatch_q *create_dsq(u64 dsq_id, int node)
-{
-	struct scx_dispatch_q *dsq;
-	int ret;
-
-	if (dsq_id & SCX_DSQ_FLAG_BUILTIN)
-		return ERR_PTR(-EINVAL);
-
-	dsq = kmalloc_node(sizeof(*dsq), GFP_KERNEL, node);
-	if (!dsq)
-		return ERR_PTR(-ENOMEM);
-
-	init_dsq(dsq, dsq_id);
-
-	ret = rhashtable_lookup_insert_fast(&dsq_hash, &dsq->hash_node,
-					    dsq_hash_params);
-	if (ret) {
-		kfree(dsq);
-		return ERR_PTR(ret);
-	}
-	return dsq;
-}
-
 static void free_dsq_irq_workfn(struct irq_work *irq_work)
 {
 	struct llist_node *to_free = llist_del_all(&dsqs_to_free);
@@ -4158,26 +4343,27 @@ static void free_dsq_irq_workfn(struct irq_work *irq_work)
 
 static DEFINE_IRQ_WORK(free_dsq_irq_work, free_dsq_irq_workfn);
 
-static void destroy_dsq(u64 dsq_id)
+static void destroy_dsq(struct scx_sched *sch, u64 dsq_id)
 {
 	struct scx_dispatch_q *dsq;
 	unsigned long flags;
 
 	rcu_read_lock();
 
-	dsq = find_user_dsq(dsq_id);
+	dsq = find_user_dsq(sch, dsq_id);
 	if (!dsq)
 		goto out_unlock_rcu;
 
 	raw_spin_lock_irqsave(&dsq->lock, flags);
 
 	if (dsq->nr) {
-		scx_ops_error("attempting to destroy in-use dsq 0x%016llx (nr=%u)",
-			      dsq->id, dsq->nr);
+		scx_error(sch, "attempting to destroy in-use dsq 0x%016llx (nr=%u)",
+			  dsq->id, dsq->nr);
 		goto out_unlock_dsq;
 	}
 
-	if (rhashtable_remove_fast(&dsq_hash, &dsq->hash_node, dsq_hash_params))
+	if (rhashtable_remove_fast(&sch->dsq_hash, &dsq->hash_node,
+				   dsq_hash_params))
 		goto out_unlock_dsq;
 
 	/*
@@ -4197,7 +4383,7 @@ out_unlock_rcu:
 }
 
 #ifdef CONFIG_EXT_GROUP_SCHED
-static void scx_cgroup_exit(void)
+static void scx_cgroup_exit(struct scx_sched *sch)
 {
 	struct cgroup_subsys_state *css;
 
@@ -4217,14 +4403,15 @@ static void scx_cgroup_exit(void)
 			continue;
 		tg->scx_flags &= ~SCX_TG_INITED;
 
-		if (!scx_ops.cgroup_exit)
+		if (!sch->ops.cgroup_exit)
 			continue;
 
 		if (WARN_ON_ONCE(!css_tryget(css)))
 			continue;
 		rcu_read_unlock();
 
-		SCX_CALL_OP(SCX_KF_UNLOCKED, cgroup_exit, css->cgroup);
+		SCX_CALL_OP(sch, SCX_KF_UNLOCKED, cgroup_exit, NULL,
+			    css->cgroup);
 
 		rcu_read_lock();
 		css_put(css);
@@ -4232,7 +4419,7 @@ static void scx_cgroup_exit(void)
 	rcu_read_unlock();
 }
 
-static int scx_cgroup_init(void)
+static int scx_cgroup_init(struct scx_sched *sch)
 {
 	struct cgroup_subsys_state *css;
 	int ret;
@@ -4252,7 +4439,7 @@ static int scx_cgroup_init(void)
 		     (SCX_TG_ONLINE | SCX_TG_INITED)) != SCX_TG_ONLINE)
 			continue;
 
-		if (!scx_ops.cgroup_init) {
+		if (!sch->ops.cgroup_init) {
 			tg->scx_flags |= SCX_TG_INITED;
 			continue;
 		}
@@ -4261,11 +4448,11 @@ static int scx_cgroup_init(void)
 			continue;
 		rcu_read_unlock();
 
-		ret = SCX_CALL_OP_RET(SCX_KF_UNLOCKED, cgroup_init,
+		ret = SCX_CALL_OP_RET(sch, SCX_KF_UNLOCKED, cgroup_init, NULL,
 				      css->cgroup, &args);
 		if (ret) {
 			css_put(css);
-			scx_ops_error("ops.cgroup_init() failed (%d)", ret);
+			scx_error(sch, "ops.cgroup_init() failed (%d)", ret);
 			return ret;
 		}
 		tg->scx_flags |= SCX_TG_INITED;
@@ -4282,8 +4469,8 @@ static int scx_cgroup_init(void)
 }
 
 #else
-static void scx_cgroup_exit(void) {}
-static int scx_cgroup_init(void) { return 0; }
+static void scx_cgroup_exit(struct scx_sched *sch) {}
+static int scx_cgroup_init(struct scx_sched *sch) { return 0; }
 #endif
 
 
@@ -4300,8 +4487,7 @@ static int scx_cgroup_init(void) { return 0; }
 static ssize_t scx_attr_state_show(struct kobject *kobj,
 				   struct kobj_attribute *ka, char *buf)
 {
-	return sysfs_emit(buf, "%s\n",
-			  scx_ops_enable_state_str[scx_ops_enable_state()]);
+	return sysfs_emit(buf, "%s\n", scx_enable_state_str[scx_enable_state()]);
 }
 SCX_ATTR(state);
 
@@ -4346,15 +4532,51 @@ static const struct attribute_group scx_global_attr_group = {
 	.attrs = scx_global_attrs,
 };
 
+static void free_exit_info(struct scx_exit_info *ei);
+
+static void scx_sched_free_rcu_work(struct work_struct *work)
+{
+	struct rcu_work *rcu_work = to_rcu_work(work);
+	struct scx_sched *sch = container_of(rcu_work, struct scx_sched, rcu_work);
+	struct rhashtable_iter rht_iter;
+	struct scx_dispatch_q *dsq;
+	int node;
+
+	kthread_stop(sch->helper->task);
+	free_percpu(sch->event_stats_cpu);
+
+	for_each_node_state(node, N_POSSIBLE)
+		kfree(sch->global_dsqs[node]);
+	kfree(sch->global_dsqs);
+
+	rhashtable_walk_enter(&sch->dsq_hash, &rht_iter);
+	do {
+		rhashtable_walk_start(&rht_iter);
+
+		while ((dsq = rhashtable_walk_next(&rht_iter)) && !IS_ERR(dsq))
+			destroy_dsq(sch, dsq->id);
+
+		rhashtable_walk_stop(&rht_iter);
+	} while (dsq == ERR_PTR(-EAGAIN));
+	rhashtable_walk_exit(&rht_iter);
+
+	rhashtable_free_and_destroy(&sch->dsq_hash, NULL, NULL);
+	free_exit_info(sch->exit_info);
+	kfree(sch);
+}
+
 static void scx_kobj_release(struct kobject *kobj)
 {
-	kfree(kobj);
+	struct scx_sched *sch = container_of(kobj, struct scx_sched, kobj);
+
+	INIT_RCU_WORK(&sch->rcu_work, scx_sched_free_rcu_work);
+	queue_rcu_work(system_unbound_wq, &sch->rcu_work);
 }
 
 static ssize_t scx_attr_ops_show(struct kobject *kobj,
 				 struct kobj_attribute *ka, char *buf)
 {
-	return sysfs_emit(buf, "%s\n", scx_ops.name);
+	return sysfs_emit(buf, "%s\n", scx_root->ops.name);
 }
 SCX_ATTR(ops);
 
@@ -4365,16 +4587,17 @@ SCX_ATTR(ops);
 static ssize_t scx_attr_events_show(struct kobject *kobj,
 				    struct kobj_attribute *ka, char *buf)
 {
+	struct scx_sched *sch = container_of(kobj, struct scx_sched, kobj);
 	struct scx_event_stats events;
 	int at = 0;
 
-	scx_bpf_events(&events, sizeof(events));
+	scx_read_events(sch, &events);
 	at += scx_attr_event_show(buf, at, &events, SCX_EV_SELECT_CPU_FALLBACK);
 	at += scx_attr_event_show(buf, at, &events, SCX_EV_DISPATCH_LOCAL_DSQ_OFFLINE);
 	at += scx_attr_event_show(buf, at, &events, SCX_EV_DISPATCH_KEEP_LAST);
 	at += scx_attr_event_show(buf, at, &events, SCX_EV_ENQ_SKIP_EXITING);
 	at += scx_attr_event_show(buf, at, &events, SCX_EV_ENQ_SKIP_MIGRATION_DISABLED);
-	at += scx_attr_event_show(buf, at, &events, SCX_EV_ENQ_SLICE_DFL);
+	at += scx_attr_event_show(buf, at, &events, SCX_EV_REFILL_SLICE_DFL);
 	at += scx_attr_event_show(buf, at, &events, SCX_EV_BYPASS_DURATION);
 	at += scx_attr_event_show(buf, at, &events, SCX_EV_BYPASS_DISPATCH);
 	at += scx_attr_event_show(buf, at, &events, SCX_EV_BYPASS_ACTIVATE);
@@ -4397,7 +4620,7 @@ static const struct kobj_type scx_ktype = {
 
 static int scx_uevent(const struct kobject *kobj, struct kobj_uevent_env *env)
 {
-	return add_uevent_var(env, "SCXOPS=%s", scx_ops.name);
+	return add_uevent_var(env, "SCXOPS=%s", scx_root->ops.name);
 }
 
 static const struct kset_uevent_ops scx_uevent_ops = {
@@ -4410,14 +4633,20 @@ static const struct kset_uevent_ops scx_uevent_ops = {
  */
 bool task_should_scx(int policy)
 {
-	if (!scx_enabled() ||
-	    unlikely(scx_ops_enable_state() == SCX_OPS_DISABLING))
+	if (!scx_enabled() || unlikely(scx_enable_state() == SCX_DISABLING))
 		return false;
 	if (READ_ONCE(scx_switching_all))
 		return true;
 	return policy == SCHED_EXT;
 }
 
+bool scx_allow_ttwu_queue(const struct task_struct *p)
+{
+	return !scx_enabled() ||
+		(scx_root->ops.flags & SCX_OPS_ALLOW_QUEUED_WAKEUP) ||
+		p->sched_class != &ext_sched_class;
+}
+
 /**
  * scx_softlockup - sched_ext softlockup handler
  * @dur_s: number of seconds of CPU stuck due to soft lockup
@@ -4430,40 +4659,48 @@ bool task_should_scx(int policy)
  */
 void scx_softlockup(u32 dur_s)
 {
-	switch (scx_ops_enable_state()) {
-	case SCX_OPS_ENABLING:
-	case SCX_OPS_ENABLED:
+	struct scx_sched *sch;
+
+	rcu_read_lock();
+
+	sch = rcu_dereference(scx_root);
+	if (unlikely(!sch))
+		goto out_unlock;
+
+	switch (scx_enable_state()) {
+	case SCX_ENABLING:
+	case SCX_ENABLED:
 		break;
 	default:
-		return;
+		goto out_unlock;
 	}
 
-	/* allow only one instance, cleared at the end of scx_ops_bypass() */
+	/* allow only one instance, cleared at the end of scx_bypass() */
 	if (test_and_set_bit(0, &scx_in_softlockup))
-		return;
+		goto out_unlock;
 
 	printk_deferred(KERN_ERR "sched_ext: Soft lockup - CPU%d stuck for %us, disabling \"%s\"\n",
-			smp_processor_id(), dur_s, scx_ops.name);
+			smp_processor_id(), dur_s, scx_root->ops.name);
 
 	/*
 	 * Some CPUs may be trapped in the dispatch paths. Enable breather
-	 * immediately; otherwise, we might even be able to get to
-	 * scx_ops_bypass().
+	 * immediately; otherwise, we might even be able to get to scx_bypass().
 	 */
-	atomic_inc(&scx_ops_breather_depth);
+	atomic_inc(&scx_breather_depth);
 
-	scx_ops_error("soft lockup - CPU#%d stuck for %us",
-		      smp_processor_id(), dur_s);
+	scx_error(sch, "soft lockup - CPU#%d stuck for %us", smp_processor_id(), dur_s);
+out_unlock:
+	rcu_read_unlock();
 }
 
 static void scx_clear_softlockup(void)
 {
 	if (test_and_clear_bit(0, &scx_in_softlockup))
-		atomic_dec(&scx_ops_breather_depth);
+		atomic_dec(&scx_breather_depth);
 }
 
 /**
- * scx_ops_bypass - [Un]bypass scx_ops and guarantee forward progress
+ * scx_bypass - [Un]bypass scx_ops and guarantee forward progress
  * @bypass: true for bypass, false for unbypass
  *
  * Bypassing guarantees that all runnable tasks make forward progress without
@@ -4493,32 +4730,36 @@ static void scx_clear_softlockup(void)
  *
  * - scx_prio_less() reverts to the default core_sched_at order.
  */
-static void scx_ops_bypass(bool bypass)
+static void scx_bypass(bool bypass)
 {
 	static DEFINE_RAW_SPINLOCK(bypass_lock);
 	static unsigned long bypass_timestamp;
-
-	int cpu;
+	struct scx_sched *sch;
 	unsigned long flags;
+	int cpu;
 
 	raw_spin_lock_irqsave(&bypass_lock, flags);
+	sch = rcu_dereference_bh(scx_root);
+
 	if (bypass) {
-		scx_ops_bypass_depth++;
-		WARN_ON_ONCE(scx_ops_bypass_depth <= 0);
-		if (scx_ops_bypass_depth != 1)
+		scx_bypass_depth++;
+		WARN_ON_ONCE(scx_bypass_depth <= 0);
+		if (scx_bypass_depth != 1)
 			goto unlock;
 		bypass_timestamp = ktime_get_ns();
-		scx_add_event(SCX_EV_BYPASS_ACTIVATE, 1);
+		if (sch)
+			scx_add_event(sch, SCX_EV_BYPASS_ACTIVATE, 1);
 	} else {
-		scx_ops_bypass_depth--;
-		WARN_ON_ONCE(scx_ops_bypass_depth < 0);
-		if (scx_ops_bypass_depth != 0)
+		scx_bypass_depth--;
+		WARN_ON_ONCE(scx_bypass_depth < 0);
+		if (scx_bypass_depth != 0)
 			goto unlock;
-		scx_add_event(SCX_EV_BYPASS_DURATION,
-			      ktime_get_ns() - bypass_timestamp);
+		if (sch)
+			scx_add_event(sch, SCX_EV_BYPASS_DURATION,
+				      ktime_get_ns() - bypass_timestamp);
 	}
 
-	atomic_inc(&scx_ops_breather_depth);
+	atomic_inc(&scx_breather_depth);
 
 	/*
 	 * No task property is changing. We just need to make sure all currently
@@ -4576,7 +4817,7 @@ static void scx_ops_bypass(bool bypass)
 		raw_spin_rq_unlock(rq);
 	}
 
-	atomic_dec(&scx_ops_breather_depth);
+	atomic_dec(&scx_breather_depth);
 unlock:
 	raw_spin_unlock_irqrestore(&bypass_lock, flags);
 	scx_clear_softlockup();
@@ -4632,42 +4873,36 @@ static const char *scx_exit_reason(enum scx_exit_kind kind)
 	}
 }
 
-static void scx_ops_disable_workfn(struct kthread_work *work)
+static void scx_disable_workfn(struct kthread_work *work)
 {
-	struct scx_exit_info *ei = scx_exit_info;
+	struct scx_sched *sch = container_of(work, struct scx_sched, disable_work);
+	struct scx_exit_info *ei = sch->exit_info;
 	struct scx_task_iter sti;
 	struct task_struct *p;
-	struct rhashtable_iter rht_iter;
-	struct scx_dispatch_q *dsq;
-	int i, kind, cpu;
+	int kind, cpu;
 
-	kind = atomic_read(&scx_exit_kind);
+	kind = atomic_read(&sch->exit_kind);
 	while (true) {
-		/*
-		 * NONE indicates that a new scx_ops has been registered since
-		 * disable was scheduled - don't kill the new ops. DONE
-		 * indicates that the ops has already been disabled.
-		 */
-		if (kind == SCX_EXIT_NONE || kind == SCX_EXIT_DONE)
+		if (kind == SCX_EXIT_DONE)	/* already disabled? */
 			return;
-		if (atomic_try_cmpxchg(&scx_exit_kind, &kind, SCX_EXIT_DONE))
+		WARN_ON_ONCE(kind == SCX_EXIT_NONE);
+		if (atomic_try_cmpxchg(&sch->exit_kind, &kind, SCX_EXIT_DONE))
 			break;
 	}
 	ei->kind = kind;
 	ei->reason = scx_exit_reason(ei->kind);
 
 	/* guarantee forward progress by bypassing scx_ops */
-	scx_ops_bypass(true);
+	scx_bypass(true);
 
-	switch (scx_ops_set_enable_state(SCX_OPS_DISABLING)) {
-	case SCX_OPS_DISABLING:
+	switch (scx_set_enable_state(SCX_DISABLING)) {
+	case SCX_DISABLING:
 		WARN_ONCE(true, "sched_ext: duplicate disabling instance?");
 		break;
-	case SCX_OPS_DISABLED:
+	case SCX_DISABLED:
 		pr_warn("sched_ext: ops error detected without ops (%s)\n",
-			scx_exit_info->msg);
-		WARN_ON_ONCE(scx_ops_set_enable_state(SCX_OPS_DISABLED) !=
-			     SCX_OPS_DISABLING);
+			sch->exit_info->msg);
+		WARN_ON_ONCE(scx_set_enable_state(SCX_DISABLED) != SCX_DISABLING);
 		goto done;
 	default:
 		break;
@@ -4678,17 +4913,17 @@ static void scx_ops_disable_workfn(struct kthread_work *work)
 	 * we can safely use blocking synchronization constructs. Actually
 	 * disable ops.
 	 */
-	mutex_lock(&scx_ops_enable_mutex);
+	mutex_lock(&scx_enable_mutex);
 
 	static_branch_disable(&__scx_switched_all);
 	WRITE_ONCE(scx_switching_all, false);
 
 	/*
 	 * Shut down cgroup support before tasks so that the cgroup attach path
-	 * doesn't race against scx_ops_exit_task().
+	 * doesn't race against scx_exit_task().
 	 */
 	scx_cgroup_lock();
-	scx_cgroup_exit();
+	scx_cgroup_exit(sch);
 	scx_cgroup_unlock();
 
 	/*
@@ -4697,7 +4932,7 @@ static void scx_ops_disable_workfn(struct kthread_work *work)
 	 */
 	percpu_down_write(&scx_fork_rwsem);
 
-	scx_ops_init_task_enabled = false;
+	scx_init_task_enabled = false;
 
 	scx_task_iter_start(&sti);
 	while ((p = scx_task_iter_next_locked(&sti))) {
@@ -4717,7 +4952,7 @@ static void scx_ops_disable_workfn(struct kthread_work *work)
 		sched_enq_and_set_task(&ctx);
 
 		check_class_changed(task_rq(p), p, old_class, p->prio);
-		scx_ops_exit_task(p);
+		scx_exit_task(p);
 	}
 	scx_task_iter_stop(&sti);
 	percpu_up_write(&scx_fork_rwsem);
@@ -4732,98 +4967,71 @@ static void scx_ops_disable_workfn(struct kthread_work *work)
 	}
 
 	/* no task is on scx, turn off all the switches and flush in-progress calls */
-	static_branch_disable(&__scx_ops_enabled);
-	for (i = SCX_OPI_BEGIN; i < SCX_OPI_END; i++)
-		static_branch_disable(&scx_has_op[i]);
-	static_branch_disable(&scx_ops_allow_queued_wakeup);
-	static_branch_disable(&scx_ops_enq_last);
-	static_branch_disable(&scx_ops_enq_exiting);
-	static_branch_disable(&scx_ops_enq_migration_disabled);
-	static_branch_disable(&scx_ops_cpu_preempt);
+	static_branch_disable(&__scx_enabled);
+	bitmap_zero(sch->has_op, SCX_OPI_END);
 	scx_idle_disable();
 	synchronize_rcu();
 
 	if (ei->kind >= SCX_EXIT_ERROR) {
 		pr_err("sched_ext: BPF scheduler \"%s\" disabled (%s)\n",
-		       scx_ops.name, ei->reason);
+		       sch->ops.name, ei->reason);
 
 		if (ei->msg[0] != '\0')
-			pr_err("sched_ext: %s: %s\n", scx_ops.name, ei->msg);
+			pr_err("sched_ext: %s: %s\n", sch->ops.name, ei->msg);
 #ifdef CONFIG_STACKTRACE
 		stack_trace_print(ei->bt, ei->bt_len, 2);
 #endif
 	} else {
 		pr_info("sched_ext: BPF scheduler \"%s\" disabled (%s)\n",
-			scx_ops.name, ei->reason);
+			sch->ops.name, ei->reason);
 	}
 
-	if (scx_ops.exit)
-		SCX_CALL_OP(SCX_KF_UNLOCKED, exit, ei);
+	if (sch->ops.exit)
+		SCX_CALL_OP(sch, SCX_KF_UNLOCKED, exit, NULL, ei);
 
 	cancel_delayed_work_sync(&scx_watchdog_work);
 
 	/*
-	 * Delete the kobject from the hierarchy eagerly in addition to just
-	 * dropping a reference. Otherwise, if the object is deleted
-	 * asynchronously, sysfs could observe an object of the same name still
-	 * in the hierarchy when another scheduler is loaded.
+	 * scx_root clearing must be inside cpus_read_lock(). See
+	 * handle_hotplug().
 	 */
-	kobject_del(scx_root_kobj);
-	kobject_put(scx_root_kobj);
-	scx_root_kobj = NULL;
-
-	memset(&scx_ops, 0, sizeof(scx_ops));
-
-	rhashtable_walk_enter(&dsq_hash, &rht_iter);
-	do {
-		rhashtable_walk_start(&rht_iter);
-
-		while ((dsq = rhashtable_walk_next(&rht_iter)) && !IS_ERR(dsq))
-			destroy_dsq(dsq->id);
+	cpus_read_lock();
+	RCU_INIT_POINTER(scx_root, NULL);
+	cpus_read_unlock();
 
-		rhashtable_walk_stop(&rht_iter);
-	} while (dsq == ERR_PTR(-EAGAIN));
-	rhashtable_walk_exit(&rht_iter);
+	/*
+	 * Delete the kobject from the hierarchy synchronously. Otherwise, sysfs
+	 * could observe an object of the same name still in the hierarchy when
+	 * the next scheduler is loaded.
+	 */
+	kobject_del(&sch->kobj);
 
 	free_percpu(scx_dsp_ctx);
 	scx_dsp_ctx = NULL;
 	scx_dsp_max_batch = 0;
 
-	free_exit_info(scx_exit_info);
-	scx_exit_info = NULL;
-
-	mutex_unlock(&scx_ops_enable_mutex);
+	mutex_unlock(&scx_enable_mutex);
 
-	WARN_ON_ONCE(scx_ops_set_enable_state(SCX_OPS_DISABLED) !=
-		     SCX_OPS_DISABLING);
+	WARN_ON_ONCE(scx_set_enable_state(SCX_DISABLED) != SCX_DISABLING);
 done:
-	scx_ops_bypass(false);
-}
-
-static DEFINE_KTHREAD_WORK(scx_ops_disable_work, scx_ops_disable_workfn);
-
-static void schedule_scx_ops_disable_work(void)
-{
-	struct kthread_worker *helper = READ_ONCE(scx_ops_helper);
-
-	/*
-	 * We may be called spuriously before the first bpf_sched_ext_reg(). If
-	 * scx_ops_helper isn't set up yet, there's nothing to do.
-	 */
-	if (helper)
-		kthread_queue_work(helper, &scx_ops_disable_work);
+	scx_bypass(false);
 }
 
-static void scx_ops_disable(enum scx_exit_kind kind)
+static void scx_disable(enum scx_exit_kind kind)
 {
 	int none = SCX_EXIT_NONE;
+	struct scx_sched *sch;
 
 	if (WARN_ON_ONCE(kind == SCX_EXIT_NONE || kind == SCX_EXIT_DONE))
 		kind = SCX_EXIT_ERROR;
 
-	atomic_try_cmpxchg(&scx_exit_kind, &none, kind);
-
-	schedule_scx_ops_disable_work();
+	rcu_read_lock();
+	sch = rcu_dereference(scx_root);
+	if (sch) {
+		atomic_try_cmpxchg(&sch->exit_kind, &none, kind);
+		kthread_queue_work(sch->helper, &sch->disable_work);
+	}
+	rcu_read_unlock();
 }
 
 static void dump_newline(struct seq_buf *s)
@@ -4941,6 +5149,7 @@ static void scx_dump_task(struct seq_buf *s, struct scx_dump_ctx *dctx,
 			  struct task_struct *p, char marker)
 {
 	static unsigned long bt[SCX_EXIT_BT_LEN];
+	struct scx_sched *sch = scx_root;
 	char dsq_id_buf[19] = "(n/a)";
 	unsigned long ops_state = atomic_long_read(&p->scx.ops_state);
 	unsigned int bt_len = 0;
@@ -4963,9 +5172,9 @@ static void scx_dump_task(struct seq_buf *s, struct scx_dump_ctx *dctx,
 		  p->scx.dsq_vtime, p->scx.slice, p->scx.weight);
 	dump_line(s, "      cpus=%*pb", cpumask_pr_args(p->cpus_ptr));
 
-	if (SCX_HAS_OP(dump_task)) {
+	if (SCX_HAS_OP(sch, dump_task)) {
 		ops_dump_init(s, "    ");
-		SCX_CALL_OP(SCX_KF_REST, dump_task, dctx, p);
+		SCX_CALL_OP(sch, SCX_KF_REST, dump_task, NULL, dctx, p);
 		ops_dump_exit();
 	}
 
@@ -4982,6 +5191,7 @@ static void scx_dump_state(struct scx_exit_info *ei, size_t dump_len)
 {
 	static DEFINE_SPINLOCK(dump_lock);
 	static const char trunc_marker[] = "\n\n~~~~ TRUNCATED ~~~~\n";
+	struct scx_sched *sch = scx_root;
 	struct scx_dump_ctx dctx = {
 		.kind = ei->kind,
 		.exit_code = ei->exit_code,
@@ -5010,9 +5220,9 @@ static void scx_dump_state(struct scx_exit_info *ei, size_t dump_len)
 		dump_stack_trace(&s, "  ", ei->bt, ei->bt_len);
 	}
 
-	if (SCX_HAS_OP(dump)) {
+	if (SCX_HAS_OP(sch, dump)) {
 		ops_dump_init(&s, "");
-		SCX_CALL_OP(SCX_KF_UNLOCKED, dump, &dctx);
+		SCX_CALL_OP(sch, SCX_KF_UNLOCKED, dump, NULL, &dctx);
 		ops_dump_exit();
 	}
 
@@ -5033,7 +5243,7 @@ static void scx_dump_state(struct scx_exit_info *ei, size_t dump_len)
 		idle = list_empty(&rq->scx.runnable_list) &&
 			rq->curr->sched_class == &idle_sched_class;
 
-		if (idle && !SCX_HAS_OP(dump_cpu))
+		if (idle && !SCX_HAS_OP(sch, dump_cpu))
 			goto next;
 
 		/*
@@ -5067,9 +5277,10 @@ static void scx_dump_state(struct scx_exit_info *ei, size_t dump_len)
 				  cpumask_pr_args(rq->scx.cpus_to_wait));
 
 		used = seq_buf_used(&ns);
-		if (SCX_HAS_OP(dump_cpu)) {
+		if (SCX_HAS_OP(sch, dump_cpu)) {
 			ops_dump_init(&ns, "  ");
-			SCX_CALL_OP(SCX_KF_REST, dump_cpu, &dctx, cpu, idle);
+			SCX_CALL_OP(sch, SCX_KF_REST, dump_cpu, NULL,
+				    &dctx, cpu, idle);
 			ops_dump_exit();
 		}
 
@@ -5103,13 +5314,13 @@ static void scx_dump_state(struct scx_exit_info *ei, size_t dump_len)
 	dump_line(&s, "Event counters");
 	dump_line(&s, "--------------");
 
-	scx_bpf_events(&events, sizeof(events));
+	scx_read_events(sch, &events);
 	scx_dump_event(s, &events, SCX_EV_SELECT_CPU_FALLBACK);
 	scx_dump_event(s, &events, SCX_EV_DISPATCH_LOCAL_DSQ_OFFLINE);
 	scx_dump_event(s, &events, SCX_EV_DISPATCH_KEEP_LAST);
 	scx_dump_event(s, &events, SCX_EV_ENQ_SKIP_EXITING);
 	scx_dump_event(s, &events, SCX_EV_ENQ_SKIP_MIGRATION_DISABLED);
-	scx_dump_event(s, &events, SCX_EV_ENQ_SLICE_DFL);
+	scx_dump_event(s, &events, SCX_EV_REFILL_SLICE_DFL);
 	scx_dump_event(s, &events, SCX_EV_BYPASS_DURATION);
 	scx_dump_event(s, &events, SCX_EV_BYPASS_DISPATCH);
 	scx_dump_event(s, &events, SCX_EV_BYPASS_ACTIVATE);
@@ -5121,27 +5332,25 @@ static void scx_dump_state(struct scx_exit_info *ei, size_t dump_len)
 	spin_unlock_irqrestore(&dump_lock, flags);
 }
 
-static void scx_ops_error_irq_workfn(struct irq_work *irq_work)
+static void scx_error_irq_workfn(struct irq_work *irq_work)
 {
-	struct scx_exit_info *ei = scx_exit_info;
+	struct scx_sched *sch = container_of(irq_work, struct scx_sched, error_irq_work);
+	struct scx_exit_info *ei = sch->exit_info;
 
 	if (ei->kind >= SCX_EXIT_ERROR)
-		scx_dump_state(ei, scx_ops.exit_dump_len);
+		scx_dump_state(ei, sch->ops.exit_dump_len);
 
-	schedule_scx_ops_disable_work();
+	kthread_queue_work(sch->helper, &sch->disable_work);
 }
 
-static DEFINE_IRQ_WORK(scx_ops_error_irq_work, scx_ops_error_irq_workfn);
-
-static __printf(3, 4) void scx_ops_exit_kind(enum scx_exit_kind kind,
-					     s64 exit_code,
-					     const char *fmt, ...)
+static void scx_vexit(struct scx_sched *sch,
+		      enum scx_exit_kind kind, s64 exit_code,
+		      const char *fmt, va_list args)
 {
-	struct scx_exit_info *ei = scx_exit_info;
+	struct scx_exit_info *ei = sch->exit_info;
 	int none = SCX_EXIT_NONE;
-	va_list args;
 
-	if (!atomic_try_cmpxchg(&scx_exit_kind, &none, kind))
+	if (!atomic_try_cmpxchg(&sch->exit_kind, &none, kind))
 		return;
 
 	ei->exit_code = exit_code;
@@ -5149,31 +5358,98 @@ static __printf(3, 4) void scx_ops_exit_kind(enum scx_exit_kind kind,
 	if (kind >= SCX_EXIT_ERROR)
 		ei->bt_len = stack_trace_save(ei->bt, SCX_EXIT_BT_LEN, 1);
 #endif
-	va_start(args, fmt);
 	vscnprintf(ei->msg, SCX_EXIT_MSG_LEN, fmt, args);
-	va_end(args);
 
 	/*
 	 * Set ei->kind and ->reason for scx_dump_state(). They'll be set again
-	 * in scx_ops_disable_workfn().
+	 * in scx_disable_workfn().
 	 */
 	ei->kind = kind;
 	ei->reason = scx_exit_reason(ei->kind);
 
-	irq_work_queue(&scx_ops_error_irq_work);
+	irq_work_queue(&sch->error_irq_work);
 }
 
-static struct kthread_worker *scx_create_rt_helper(const char *name)
+static struct scx_sched *scx_alloc_and_add_sched(struct sched_ext_ops *ops)
 {
-	struct kthread_worker *helper;
+	struct scx_sched *sch;
+	int node, ret;
 
-	helper = kthread_run_worker(0, name);
-	if (helper)
-		sched_set_fifo(helper->task);
-	return helper;
-}
+	sch = kzalloc(sizeof(*sch), GFP_KERNEL);
+	if (!sch)
+		return ERR_PTR(-ENOMEM);
+
+	sch->exit_info = alloc_exit_info(ops->exit_dump_len);
+	if (!sch->exit_info) {
+		ret = -ENOMEM;
+		goto err_free_sch;
+	}
+
+	ret = rhashtable_init(&sch->dsq_hash, &dsq_hash_params);
+	if (ret < 0)
+		goto err_free_ei;
+
+	sch->global_dsqs = kcalloc(nr_node_ids, sizeof(sch->global_dsqs[0]),
+				   GFP_KERNEL);
+	if (!sch->global_dsqs) {
+		ret = -ENOMEM;
+		goto err_free_hash;
+	}
 
-static void check_hotplug_seq(const struct sched_ext_ops *ops)
+	for_each_node_state(node, N_POSSIBLE) {
+		struct scx_dispatch_q *dsq;
+
+		dsq = kzalloc_node(sizeof(*dsq), GFP_KERNEL, node);
+		if (!dsq) {
+			ret = -ENOMEM;
+			goto err_free_gdsqs;
+		}
+
+		init_dsq(dsq, SCX_DSQ_GLOBAL);
+		sch->global_dsqs[node] = dsq;
+	}
+
+	sch->event_stats_cpu = alloc_percpu(struct scx_event_stats);
+	if (!sch->event_stats_cpu)
+		goto err_free_gdsqs;
+
+	sch->helper = kthread_run_worker(0, "sched_ext_helper");
+	if (!sch->helper)
+		goto err_free_event_stats;
+	sched_set_fifo(sch->helper->task);
+
+	atomic_set(&sch->exit_kind, SCX_EXIT_NONE);
+	init_irq_work(&sch->error_irq_work, scx_error_irq_workfn);
+	kthread_init_work(&sch->disable_work, scx_disable_workfn);
+	sch->ops = *ops;
+	ops->priv = sch;
+
+	sch->kobj.kset = scx_kset;
+	ret = kobject_init_and_add(&sch->kobj, &scx_ktype, NULL, "root");
+	if (ret < 0)
+		goto err_stop_helper;
+
+	return sch;
+
+err_stop_helper:
+	kthread_stop(sch->helper->task);
+err_free_event_stats:
+	free_percpu(sch->event_stats_cpu);
+err_free_gdsqs:
+	for_each_node_state(node, N_POSSIBLE)
+		kfree(sch->global_dsqs[node]);
+	kfree(sch->global_dsqs);
+err_free_hash:
+	rhashtable_free_and_destroy(&sch->dsq_hash, NULL, NULL);
+err_free_ei:
+	free_exit_info(sch->exit_info);
+err_free_sch:
+	kfree(sch);
+	return ERR_PTR(ret);
+}
+
+static void check_hotplug_seq(struct scx_sched *sch,
+			      const struct sched_ext_ops *ops)
 {
 	unsigned long long global_hotplug_seq;
 
@@ -5185,21 +5461,22 @@ static void check_hotplug_seq(const struct sched_ext_ops *ops)
 	if (ops->hotplug_seq) {
 		global_hotplug_seq = atomic_long_read(&scx_hotplug_seq);
 		if (ops->hotplug_seq != global_hotplug_seq) {
-			scx_ops_exit(SCX_ECODE_ACT_RESTART | SCX_ECODE_RSN_HOTPLUG,
-				     "expected hotplug seq %llu did not match actual %llu",
-				     ops->hotplug_seq, global_hotplug_seq);
+			scx_exit(sch, SCX_EXIT_UNREG_KERN,
+				 SCX_ECODE_ACT_RESTART | SCX_ECODE_RSN_HOTPLUG,
+				 "expected hotplug seq %llu did not match actual %llu",
+				 ops->hotplug_seq, global_hotplug_seq);
 		}
 	}
 }
 
-static int validate_ops(const struct sched_ext_ops *ops)
+static int validate_ops(struct scx_sched *sch, const struct sched_ext_ops *ops)
 {
 	/*
 	 * It doesn't make sense to specify the SCX_OPS_ENQ_LAST flag if the
 	 * ops.enqueue() callback isn't implemented.
 	 */
 	if ((ops->flags & SCX_OPS_ENQ_LAST) && !ops->enqueue) {
-		scx_ops_error("SCX_OPS_ENQ_LAST requires ops.enqueue() to be implemented");
+		scx_error(sch, "SCX_OPS_ENQ_LAST requires ops.enqueue() to be implemented");
 		return -EINVAL;
 	}
 
@@ -5209,7 +5486,7 @@ static int validate_ops(const struct sched_ext_ops *ops)
 	 */
 	if ((ops->flags & SCX_OPS_BUILTIN_IDLE_PER_NODE) &&
 	    (ops->update_idle && !(ops->flags & SCX_OPS_KEEP_BUILTIN_IDLE))) {
-		scx_ops_error("SCX_OPS_BUILTIN_IDLE_PER_NODE requires CPU idle selection enabled");
+		scx_error(sch, "SCX_OPS_BUILTIN_IDLE_PER_NODE requires CPU idle selection enabled");
 		return -EINVAL;
 	}
 
@@ -5219,12 +5496,13 @@ static int validate_ops(const struct sched_ext_ops *ops)
 	return 0;
 }
 
-static int scx_ops_enable(struct sched_ext_ops *ops, struct bpf_link *link)
+static int scx_enable(struct sched_ext_ops *ops, struct bpf_link *link)
 {
+	struct scx_sched *sch;
 	struct scx_task_iter sti;
 	struct task_struct *p;
 	unsigned long timeout;
-	int i, cpu, node, ret;
+	int i, cpu, ret;
 
 	if (!cpumask_equal(housekeeping_cpumask(HK_TYPE_DOMAIN),
 			   cpu_possible_mask)) {
@@ -5232,87 +5510,25 @@ static int scx_ops_enable(struct sched_ext_ops *ops, struct bpf_link *link)
 		return -EINVAL;
 	}
 
-	mutex_lock(&scx_ops_enable_mutex);
-
-	/*
-	 * Clear event counters so a new scx scheduler gets
-	 * fresh event counter values.
-	 */
-	for_each_possible_cpu(cpu) {
-		struct scx_event_stats *e = per_cpu_ptr(&event_stats_cpu, cpu);
-		memset(e, 0, sizeof(*e));
-	}
-
-	if (!scx_ops_helper) {
-		WRITE_ONCE(scx_ops_helper,
-			   scx_create_rt_helper("sched_ext_ops_helper"));
-		if (!scx_ops_helper) {
-			ret = -ENOMEM;
-			goto err_unlock;
-		}
-	}
-
-	if (!global_dsqs) {
-		struct scx_dispatch_q **dsqs;
-
-		dsqs = kcalloc(nr_node_ids, sizeof(dsqs[0]), GFP_KERNEL);
-		if (!dsqs) {
-			ret = -ENOMEM;
-			goto err_unlock;
-		}
-
-		for_each_node_state(node, N_POSSIBLE) {
-			struct scx_dispatch_q *dsq;
-
-			dsq = kzalloc_node(sizeof(*dsq), GFP_KERNEL, node);
-			if (!dsq) {
-				for_each_node_state(node, N_POSSIBLE)
-					kfree(dsqs[node]);
-				kfree(dsqs);
-				ret = -ENOMEM;
-				goto err_unlock;
-			}
-
-			init_dsq(dsq, SCX_DSQ_GLOBAL);
-			dsqs[node] = dsq;
-		}
-
-		global_dsqs = dsqs;
-	}
+	mutex_lock(&scx_enable_mutex);
 
-	if (scx_ops_enable_state() != SCX_OPS_DISABLED) {
+	if (scx_enable_state() != SCX_DISABLED) {
 		ret = -EBUSY;
 		goto err_unlock;
 	}
 
-	scx_root_kobj = kzalloc(sizeof(*scx_root_kobj), GFP_KERNEL);
-	if (!scx_root_kobj) {
-		ret = -ENOMEM;
+	sch = scx_alloc_and_add_sched(ops);
+	if (IS_ERR(sch)) {
+		ret = PTR_ERR(sch);
 		goto err_unlock;
 	}
 
-	scx_root_kobj->kset = scx_kset;
-	ret = kobject_init_and_add(scx_root_kobj, &scx_ktype, NULL, "root");
-	if (ret < 0)
-		goto err;
-
-	scx_exit_info = alloc_exit_info(ops->exit_dump_len);
-	if (!scx_exit_info) {
-		ret = -ENOMEM;
-		goto err_del;
-	}
-
 	/*
-	 * Set scx_ops, transition to ENABLING and clear exit info to arm the
-	 * disable path. Failure triggers full disabling from here on.
+	 * Transition to ENABLING and clear exit info to arm the disable path.
+	 * Failure triggers full disabling from here on.
 	 */
-	scx_ops = *ops;
-
-	WARN_ON_ONCE(scx_ops_set_enable_state(SCX_OPS_ENABLING) !=
-		     SCX_OPS_DISABLED);
-
-	atomic_set(&scx_exit_kind, SCX_EXIT_NONE);
-	scx_warned_zero_slice = false;
+	WARN_ON_ONCE(scx_set_enable_state(SCX_ENABLING) != SCX_DISABLED);
+	WARN_ON_ONCE(scx_root);
 
 	atomic_long_set(&scx_nr_rejected, 0);
 
@@ -5325,28 +5541,34 @@ static int scx_ops_enable(struct sched_ext_ops *ops, struct bpf_link *link)
 	 */
 	cpus_read_lock();
 
+	/*
+	 * Make the scheduler instance visible. Must be inside cpus_read_lock().
+	 * See handle_hotplug().
+	 */
+	rcu_assign_pointer(scx_root, sch);
+
 	scx_idle_enable(ops);
 
-	if (scx_ops.init) {
-		ret = SCX_CALL_OP_RET(SCX_KF_UNLOCKED, init);
+	if (sch->ops.init) {
+		ret = SCX_CALL_OP_RET(sch, SCX_KF_UNLOCKED, init, NULL);
 		if (ret) {
-			ret = ops_sanitize_err("init", ret);
+			ret = ops_sanitize_err(sch, "init", ret);
 			cpus_read_unlock();
-			scx_ops_error("ops.init() failed (%d)", ret);
+			scx_error(sch, "ops.init() failed (%d)", ret);
 			goto err_disable;
 		}
 	}
 
 	for (i = SCX_OPI_CPU_HOTPLUG_BEGIN; i < SCX_OPI_CPU_HOTPLUG_END; i++)
 		if (((void (**)(void))ops)[i])
-			static_branch_enable_cpuslocked(&scx_has_op[i]);
+			set_bit(i, sch->has_op);
 
-	check_hotplug_seq(ops);
+	check_hotplug_seq(sch, ops);
 	scx_idle_update_selcpu_topology(ops);
 
 	cpus_read_unlock();
 
-	ret = validate_ops(ops);
+	ret = validate_ops(sch, ops);
 	if (ret)
 		goto err_disable;
 
@@ -5371,27 +5593,19 @@ static int scx_ops_enable(struct sched_ext_ops *ops, struct bpf_link *link)
 			   scx_watchdog_timeout / 2);
 
 	/*
-	 * Once __scx_ops_enabled is set, %current can be switched to SCX
-	 * anytime. This can lead to stalls as some BPF schedulers (e.g.
-	 * userspace scheduling) may not function correctly before all tasks are
-	 * switched. Init in bypass mode to guarantee forward progress.
+	 * Once __scx_enabled is set, %current can be switched to SCX anytime.
+	 * This can lead to stalls as some BPF schedulers (e.g. userspace
+	 * scheduling) may not function correctly before all tasks are switched.
+	 * Init in bypass mode to guarantee forward progress.
 	 */
-	scx_ops_bypass(true);
+	scx_bypass(true);
 
 	for (i = SCX_OPI_NORMAL_BEGIN; i < SCX_OPI_NORMAL_END; i++)
 		if (((void (**)(void))ops)[i])
-			static_branch_enable(&scx_has_op[i]);
-
-	if (ops->flags & SCX_OPS_ALLOW_QUEUED_WAKEUP)
-		static_branch_enable(&scx_ops_allow_queued_wakeup);
-	if (ops->flags & SCX_OPS_ENQ_LAST)
-		static_branch_enable(&scx_ops_enq_last);
-	if (ops->flags & SCX_OPS_ENQ_EXITING)
-		static_branch_enable(&scx_ops_enq_exiting);
-	if (ops->flags & SCX_OPS_ENQ_MIGRATION_DISABLED)
-		static_branch_enable(&scx_ops_enq_migration_disabled);
-	if (scx_ops.cpu_acquire || scx_ops.cpu_release)
-		static_branch_enable(&scx_ops_cpu_preempt);
+			set_bit(i, sch->has_op);
+
+	if (sch->ops.cpu_acquire || sch->ops.cpu_release)
+		sch->ops.flags |= SCX_OPS_HAS_CPU_PREEMPT;
 
 	/*
 	 * Lock out forks, cgroup on/offlining and moves before opening the
@@ -5399,8 +5613,8 @@ static int scx_ops_enable(struct sched_ext_ops *ops, struct bpf_link *link)
 	 */
 	percpu_down_write(&scx_fork_rwsem);
 
-	WARN_ON_ONCE(scx_ops_init_task_enabled);
-	scx_ops_init_task_enabled = true;
+	WARN_ON_ONCE(scx_init_task_enabled);
+	scx_init_task_enabled = true;
 
 	/*
 	 * Enable ops for every task. Fork is excluded by scx_fork_rwsem
@@ -5409,14 +5623,14 @@ static int scx_ops_enable(struct sched_ext_ops *ops, struct bpf_link *link)
 	 * tasks. Prep all tasks first and then enable them with preemption
 	 * disabled.
 	 *
-	 * All cgroups should be initialized before scx_ops_init_task() so that
-	 * the BPF scheduler can reliably track each task's cgroup membership
-	 * from scx_ops_init_task(). Lock out cgroup on/offlining and task
-	 * migrations while tasks are being initialized so that
-	 * scx_cgroup_can_attach() never sees uninitialized tasks.
+	 * All cgroups should be initialized before scx_init_task() so that the
+	 * BPF scheduler can reliably track each task's cgroup membership from
+	 * scx_init_task(). Lock out cgroup on/offlining and task migrations
+	 * while tasks are being initialized so that scx_cgroup_can_attach()
+	 * never sees uninitialized tasks.
 	 */
 	scx_cgroup_lock();
-	ret = scx_cgroup_init();
+	ret = scx_cgroup_init(sch);
 	if (ret)
 		goto err_disable_unlock_all;
 
@@ -5432,13 +5646,13 @@ static int scx_ops_enable(struct sched_ext_ops *ops, struct bpf_link *link)
 
 		scx_task_iter_unlock(&sti);
 
-		ret = scx_ops_init_task(p, task_group(p), false);
+		ret = scx_init_task(p, task_group(p), false);
 		if (ret) {
 			put_task_struct(p);
 			scx_task_iter_relock(&sti);
 			scx_task_iter_stop(&sti);
-			scx_ops_error("ops.init_task() failed (%d) for %s[%d]",
-				      ret, p->comm, p->pid);
+			scx_error(sch, "ops.init_task() failed (%d) for %s[%d]",
+				  ret, p->comm, p->pid);
 			goto err_disable_unlock_all;
 		}
 
@@ -5456,7 +5670,7 @@ static int scx_ops_enable(struct sched_ext_ops *ops, struct bpf_link *link)
 	 * all eligible tasks.
 	 */
 	WRITE_ONCE(scx_switching_all, !(ops->flags & SCX_OPS_SWITCH_PARTIAL));
-	static_branch_enable(&__scx_ops_enabled);
+	static_branch_enable(&__scx_enabled);
 
 	/*
 	 * We're fully committed and can't fail. The task READY -> ENABLED
@@ -5487,10 +5701,10 @@ static int scx_ops_enable(struct sched_ext_ops *ops, struct bpf_link *link)
 	scx_task_iter_stop(&sti);
 	percpu_up_write(&scx_fork_rwsem);
 
-	scx_ops_bypass(false);
+	scx_bypass(false);
 
-	if (!scx_ops_tryset_enable_state(SCX_OPS_ENABLED, SCX_OPS_ENABLING)) {
-		WARN_ON_ONCE(atomic_read(&scx_exit_kind) == SCX_EXIT_NONE);
+	if (!scx_tryset_enable_state(SCX_ENABLED, SCX_ENABLING)) {
+		WARN_ON_ONCE(atomic_read(&sch->exit_kind) == SCX_EXIT_NONE);
 		goto err_disable;
 	}
 
@@ -5498,44 +5712,35 @@ static int scx_ops_enable(struct sched_ext_ops *ops, struct bpf_link *link)
 		static_branch_enable(&__scx_switched_all);
 
 	pr_info("sched_ext: BPF scheduler \"%s\" enabled%s\n",
-		scx_ops.name, scx_switched_all() ? "" : " (partial)");
-	kobject_uevent(scx_root_kobj, KOBJ_ADD);
-	mutex_unlock(&scx_ops_enable_mutex);
+		sch->ops.name, scx_switched_all() ? "" : " (partial)");
+	kobject_uevent(&sch->kobj, KOBJ_ADD);
+	mutex_unlock(&scx_enable_mutex);
 
 	atomic_long_inc(&scx_enable_seq);
 
 	return 0;
 
-err_del:
-	kobject_del(scx_root_kobj);
-err:
-	kobject_put(scx_root_kobj);
-	scx_root_kobj = NULL;
-	if (scx_exit_info) {
-		free_exit_info(scx_exit_info);
-		scx_exit_info = NULL;
-	}
 err_unlock:
-	mutex_unlock(&scx_ops_enable_mutex);
+	mutex_unlock(&scx_enable_mutex);
 	return ret;
 
 err_disable_unlock_all:
 	scx_cgroup_unlock();
 	percpu_up_write(&scx_fork_rwsem);
-	scx_ops_bypass(false);
+	scx_bypass(false);
 err_disable:
-	mutex_unlock(&scx_ops_enable_mutex);
+	mutex_unlock(&scx_enable_mutex);
 	/*
 	 * Returning an error code here would not pass all the error information
-	 * to userspace. Record errno using scx_ops_error() for cases
-	 * scx_ops_error() wasn't already invoked and exit indicating success so
-	 * that the error is notified through ops.exit() with all the details.
+	 * to userspace. Record errno using scx_error() for cases scx_error()
+	 * wasn't already invoked and exit indicating success so that the error
+	 * is notified through ops.exit() with all the details.
 	 *
-	 * Flush scx_ops_disable_work to ensure that error is reported before
-	 * init completion.
+	 * Flush scx_disable_work to ensure that error is reported before init
+	 * completion. sch's base reference will be put by bpf_scx_unreg().
 	 */
-	scx_ops_error("scx_ops_enable() failed (%d)", ret);
-	kthread_flush_work(&scx_ops_disable_work);
+	scx_error(sch, "scx_enable() failed (%d)", ret);
+	kthread_flush_work(&sch->disable_work);
 	return 0;
 }
 
@@ -5586,21 +5791,8 @@ static int bpf_scx_btf_struct_access(struct bpf_verifier_log *log,
 	return -EACCES;
 }
 
-static const struct bpf_func_proto *
-bpf_scx_get_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
-{
-	switch (func_id) {
-	case BPF_FUNC_task_storage_get:
-		return &bpf_task_storage_get_proto;
-	case BPF_FUNC_task_storage_delete:
-		return &bpf_task_storage_delete_proto;
-	default:
-		return bpf_base_func_proto(func_id, prog);
-	}
-}
-
 static const struct bpf_verifier_ops bpf_scx_verifier_ops = {
-	.get_func_proto = bpf_scx_get_func_proto,
+	.get_func_proto = bpf_base_func_proto,
 	.is_valid_access = bpf_scx_is_valid_access,
 	.btf_struct_access = bpf_scx_btf_struct_access,
 };
@@ -5679,13 +5871,17 @@ static int bpf_scx_check_member(const struct btf_type *t,
 
 static int bpf_scx_reg(void *kdata, struct bpf_link *link)
 {
-	return scx_ops_enable(kdata, link);
+	return scx_enable(kdata, link);
 }
 
 static void bpf_scx_unreg(void *kdata, struct bpf_link *link)
 {
-	scx_ops_disable(SCX_EXIT_UNREG);
-	kthread_flush_work(&scx_ops_disable_work);
+	struct sched_ext_ops *ops = kdata;
+	struct scx_sched *sch = ops->priv;
+
+	scx_disable(SCX_EXIT_UNREG);
+	kthread_flush_work(&sch->disable_work);
+	kobject_put(&sch->kobj);
 }
 
 static int bpf_scx_init(struct btf *btf)
@@ -5807,10 +6003,7 @@ static struct bpf_struct_ops bpf_sched_ext_ops = {
 
 static void sysrq_handle_sched_ext_reset(u8 key)
 {
-	if (scx_ops_helper)
-		scx_ops_disable(SCX_EXIT_SYSRQ);
-	else
-		pr_info("sched_ext: BPF scheduler not yet used\n");
+	scx_disable(SCX_EXIT_SYSRQ);
 }
 
 static const struct sysrq_key_op sysrq_sched_ext_reset_op = {
@@ -5958,13 +6151,14 @@ static void kick_cpus_irq_workfn(struct irq_work *irq_work)
  */
 void print_scx_info(const char *log_lvl, struct task_struct *p)
 {
-	enum scx_ops_enable_state state = scx_ops_enable_state();
+	struct scx_sched *sch = scx_root;
+	enum scx_enable_state state = scx_enable_state();
 	const char *all = READ_ONCE(scx_switching_all) ? "+all" : "";
 	char runnable_at_buf[22] = "?";
 	struct sched_class *class;
 	unsigned long runnable_at;
 
-	if (state == SCX_OPS_DISABLED)
+	if (state == SCX_DISABLED)
 		return;
 
 	/*
@@ -5973,8 +6167,8 @@ void print_scx_info(const char *log_lvl, struct task_struct *p)
 	 */
 	if (copy_from_kernel_nofault(&class, &p->sched_class, sizeof(class)) ||
 	    class != &ext_sched_class) {
-		printk("%sSched_ext: %s (%s%s)", log_lvl, scx_ops.name,
-		       scx_ops_enable_state_str[state], all);
+		printk("%sSched_ext: %s (%s%s)", log_lvl, sch->ops.name,
+		       scx_enable_state_str[state], all);
 		return;
 	}
 
@@ -5985,7 +6179,7 @@ void print_scx_info(const char *log_lvl, struct task_struct *p)
 
 	/* print everything onto one line to conserve console space */
 	printk("%sSched_ext: %s (%s%s), task: runnable_at=%s",
-	       log_lvl, scx_ops.name, scx_ops_enable_state_str[state], all,
+	       log_lvl, sch->ops.name, scx_enable_state_str[state], all,
 	       runnable_at_buf);
 }
 
@@ -6001,12 +6195,12 @@ static int scx_pm_handler(struct notifier_block *nb, unsigned long event, void *
 	case PM_HIBERNATION_PREPARE:
 	case PM_SUSPEND_PREPARE:
 	case PM_RESTORE_PREPARE:
-		scx_ops_bypass(true);
+		scx_bypass(true);
 		break;
 	case PM_POST_HIBERNATION:
 	case PM_POST_SUSPEND:
 	case PM_POST_RESTORE:
-		scx_ops_bypass(false);
+		scx_bypass(false);
 		break;
 	}
 
@@ -6029,7 +6223,6 @@ void __init init_sched_ext_class(void)
 	WRITE_ONCE(v, SCX_ENQ_WAKEUP | SCX_DEQ_SLEEP | SCX_KICK_PREEMPT |
 		   SCX_TG_ONLINE);
 
-	BUG_ON(rhashtable_init(&dsq_hash, &dsq_hash_params));
 	scx_idle_init_masks();
 
 	scx_kick_cpus_pnt_seqs =
@@ -6073,12 +6266,12 @@ static bool scx_dsq_insert_preamble(struct task_struct *p, u64 enq_flags)
 	lockdep_assert_irqs_disabled();
 
 	if (unlikely(!p)) {
-		scx_ops_error("called with NULL task");
+		scx_kf_error("called with NULL task");
 		return false;
 	}
 
 	if (unlikely(enq_flags & __SCX_ENQ_INTERNAL_MASK)) {
-		scx_ops_error("invalid enq_flags 0x%llx", enq_flags);
+		scx_kf_error("invalid enq_flags 0x%llx", enq_flags);
 		return false;
 	}
 
@@ -6098,7 +6291,7 @@ static void scx_dsq_insert_commit(struct task_struct *p, u64 dsq_id,
 	}
 
 	if (unlikely(dspc->cursor >= scx_dsp_max_batch)) {
-		scx_ops_error("dispatch buffer overflow");
+		scx_kf_error("dispatch buffer overflow");
 		return;
 	}
 
@@ -6230,6 +6423,7 @@ static const struct btf_kfunc_id_set scx_kfunc_set_enqueue_dispatch = {
 static bool scx_dsq_move(struct bpf_iter_scx_dsq_kern *kit,
 			 struct task_struct *p, u64 dsq_id, u64 enq_flags)
 {
+	struct scx_sched *sch = scx_root;
 	struct scx_dispatch_q *src_dsq = kit->dsq, *dst_dsq;
 	struct rq *this_rq, *src_rq, *locked_rq;
 	bool dispatched = false;
@@ -6264,7 +6458,7 @@ static bool scx_dsq_move(struct bpf_iter_scx_dsq_kern *kit,
 	 * cause similar live-lock conditions as consume_dispatch_q(). Insert a
 	 * breather if necessary.
 	 */
-	scx_ops_breather(src_rq);
+	scx_breather(src_rq);
 
 	locked_rq = src_rq;
 	raw_spin_lock(&src_dsq->lock);
@@ -6282,7 +6476,7 @@ static bool scx_dsq_move(struct bpf_iter_scx_dsq_kern *kit,
 	}
 
 	/* @p is still on $src_dsq and stable, determine the destination */
-	dst_dsq = find_dsq_for_dispatch(this_rq, dsq_id, p);
+	dst_dsq = find_dsq_for_dispatch(sch, this_rq, dsq_id, p);
 
 	/*
 	 * Apply vtime and slice updates before moving so that the new time is
@@ -6295,7 +6489,7 @@ static bool scx_dsq_move(struct bpf_iter_scx_dsq_kern *kit,
 		p->scx.slice = kit->slice;
 
 	/* execute move */
-	locked_rq = move_task_between_dsqs(p, enq_flags, src_dsq, dst_dsq);
+	locked_rq = move_task_between_dsqs(sch, p, enq_flags, src_dsq, dst_dsq);
 	dispatched = true;
 out:
 	if (in_balance) {
@@ -6343,7 +6537,7 @@ __bpf_kfunc void scx_bpf_dispatch_cancel(void)
 	if (dspc->cursor > 0)
 		dspc->cursor--;
 	else
-		scx_ops_error("dispatch buffer underflow");
+		scx_kf_error("dispatch buffer underflow");
 }
 
 /**
@@ -6362,21 +6556,22 @@ __bpf_kfunc void scx_bpf_dispatch_cancel(void)
  */
 __bpf_kfunc bool scx_bpf_dsq_move_to_local(u64 dsq_id)
 {
+	struct scx_sched *sch = scx_root;
 	struct scx_dsp_ctx *dspc = this_cpu_ptr(scx_dsp_ctx);
 	struct scx_dispatch_q *dsq;
 
 	if (!scx_kf_allowed(SCX_KF_DISPATCH))
 		return false;
 
-	flush_dispatch_buf(dspc->rq);
+	flush_dispatch_buf(sch, dspc->rq);
 
-	dsq = find_user_dsq(dsq_id);
+	dsq = find_user_dsq(sch, dsq_id);
 	if (unlikely(!dsq)) {
-		scx_ops_error("invalid DSQ ID 0x%016llx", dsq_id);
+		scx_error(sch, "invalid DSQ ID 0x%016llx", dsq_id);
 		return false;
 	}
 
-	if (consume_dispatch_q(dspc->rq, dsq)) {
+	if (consume_dispatch_q(sch, dspc->rq, dsq)) {
 		/*
 		 * A successfully consumed task can be dequeued before it starts
 		 * running while the CPU is trying to migrate other dispatched
@@ -6630,10 +6825,36 @@ __bpf_kfunc_start_defs();
  */
 __bpf_kfunc s32 scx_bpf_create_dsq(u64 dsq_id, s32 node)
 {
+	struct scx_dispatch_q *dsq;
+	struct scx_sched *sch;
+	s32 ret;
+
 	if (unlikely(node >= (int)nr_node_ids ||
 		     (node < 0 && node != NUMA_NO_NODE)))
 		return -EINVAL;
-	return PTR_ERR_OR_ZERO(create_dsq(dsq_id, node));
+
+	if (unlikely(dsq_id & SCX_DSQ_FLAG_BUILTIN))
+		return -EINVAL;
+
+	dsq = kmalloc_node(sizeof(*dsq), GFP_KERNEL, node);
+	if (!dsq)
+		return -ENOMEM;
+
+	init_dsq(dsq, dsq_id);
+
+	rcu_read_lock();
+
+	sch = rcu_dereference(scx_root);
+	if (sch)
+		ret = rhashtable_lookup_insert_fast(&sch->dsq_hash, &dsq->hash_node,
+						    dsq_hash_params);
+	else
+		ret = -ENODEV;
+
+	rcu_read_unlock();
+	if (ret)
+		kfree(dsq);
+	return ret;
 }
 
 __bpf_kfunc_end_defs();
@@ -6672,7 +6893,7 @@ __bpf_kfunc void scx_bpf_kick_cpu(s32 cpu, u64 flags)
 	struct rq *this_rq;
 	unsigned long irq_flags;
 
-	if (!ops_cpu_valid(cpu, NULL))
+	if (!kf_cpu_valid(cpu, NULL))
 		return;
 
 	local_irq_save(irq_flags);
@@ -6696,7 +6917,7 @@ __bpf_kfunc void scx_bpf_kick_cpu(s32 cpu, u64 flags)
 		struct rq *target_rq = cpu_rq(cpu);
 
 		if (unlikely(flags & (SCX_KICK_PREEMPT | SCX_KICK_WAIT)))
-			scx_ops_error("PREEMPT/WAIT cannot be used with SCX_KICK_IDLE");
+			scx_kf_error("PREEMPT/WAIT cannot be used with SCX_KICK_IDLE");
 
 		if (raw_spin_rq_trylock(target_rq)) {
 			if (can_skip_idle_kick(target_rq)) {
@@ -6729,23 +6950,30 @@ out:
  */
 __bpf_kfunc s32 scx_bpf_dsq_nr_queued(u64 dsq_id)
 {
+	struct scx_sched *sch;
 	struct scx_dispatch_q *dsq;
 	s32 ret;
 
 	preempt_disable();
 
+	sch = rcu_dereference_sched(scx_root);
+	if (unlikely(!sch)) {
+		ret = -ENODEV;
+		goto out;
+	}
+
 	if (dsq_id == SCX_DSQ_LOCAL) {
 		ret = READ_ONCE(this_rq()->scx.local_dsq.nr);
 		goto out;
 	} else if ((dsq_id & SCX_DSQ_LOCAL_ON) == SCX_DSQ_LOCAL_ON) {
 		s32 cpu = dsq_id & SCX_DSQ_LOCAL_CPU_MASK;
 
-		if (ops_cpu_valid(cpu, NULL)) {
+		if (ops_cpu_valid(sch, cpu, NULL)) {
 			ret = READ_ONCE(cpu_rq(cpu)->scx.local_dsq.nr);
 			goto out;
 		}
 	} else {
-		dsq = find_user_dsq(dsq_id);
+		dsq = find_user_dsq(sch, dsq_id);
 		if (dsq) {
 			ret = READ_ONCE(dsq->nr);
 			goto out;
@@ -6768,7 +6996,13 @@ out:
  */
 __bpf_kfunc void scx_bpf_destroy_dsq(u64 dsq_id)
 {
-	destroy_dsq(dsq_id);
+	struct scx_sched *sch;
+
+	rcu_read_lock();
+	sch = rcu_dereference(scx_root);
+	if (sch)
+		destroy_dsq(sch, dsq_id);
+	rcu_read_unlock();
 }
 
 /**
@@ -6785,16 +7019,27 @@ __bpf_kfunc int bpf_iter_scx_dsq_new(struct bpf_iter_scx_dsq *it, u64 dsq_id,
 				     u64 flags)
 {
 	struct bpf_iter_scx_dsq_kern *kit = (void *)it;
+	struct scx_sched *sch;
 
 	BUILD_BUG_ON(sizeof(struct bpf_iter_scx_dsq_kern) >
 		     sizeof(struct bpf_iter_scx_dsq));
 	BUILD_BUG_ON(__alignof__(struct bpf_iter_scx_dsq_kern) !=
 		     __alignof__(struct bpf_iter_scx_dsq));
 
+	/*
+	 * next() and destroy() will be called regardless of the return value.
+	 * Always clear $kit->dsq.
+	 */
+	kit->dsq = NULL;
+
+	sch = rcu_dereference_check(scx_root, rcu_read_lock_bh_held());
+	if (unlikely(!sch))
+		return -ENODEV;
+
 	if (flags & ~__SCX_DSQ_ITER_USER_FLAGS)
 		return -EINVAL;
 
-	kit->dsq = find_user_dsq(dsq_id);
+	kit->dsq = find_user_dsq(sch, dsq_id);
 	if (!kit->dsq)
 		return -ENOENT;
 
@@ -6884,21 +7129,20 @@ static s32 __bstr_format(u64 *data_buf, char *line_buf, size_t line_size,
 
 	if (data__sz % 8 || data__sz > MAX_BPRINTF_VARARGS * 8 ||
 	    (data__sz && !data)) {
-		scx_ops_error("invalid data=%p and data__sz=%u",
-			      (void *)data, data__sz);
+		scx_kf_error("invalid data=%p and data__sz=%u", (void *)data, data__sz);
 		return -EINVAL;
 	}
 
 	ret = copy_from_kernel_nofault(data_buf, data, data__sz);
 	if (ret < 0) {
-		scx_ops_error("failed to read data fields (%d)", ret);
+		scx_kf_error("failed to read data fields (%d)", ret);
 		return ret;
 	}
 
 	ret = bpf_bprintf_prepare(fmt, UINT_MAX, data_buf, data__sz / 8,
 				  &bprintf_data);
 	if (ret < 0) {
-		scx_ops_error("format preparation failed (%d)", ret);
+		scx_kf_error("format preparation failed (%d)", ret);
 		return ret;
 	}
 
@@ -6906,8 +7150,7 @@ static s32 __bstr_format(u64 *data_buf, char *line_buf, size_t line_size,
 			  bprintf_data.bin_args);
 	bpf_bprintf_cleanup(&bprintf_data);
 	if (ret < 0) {
-		scx_ops_error("(\"%s\", %p, %u) failed to format",
-			      fmt, data, data__sz);
+		scx_kf_error("(\"%s\", %p, %u) failed to format", fmt, data, data__sz);
 		return ret;
 	}
 
@@ -6940,8 +7183,7 @@ __bpf_kfunc void scx_bpf_exit_bstr(s64 exit_code, char *fmt,
 
 	raw_spin_lock_irqsave(&scx_exit_bstr_buf_lock, flags);
 	if (bstr_format(&scx_exit_bstr_buf, fmt, data, data__sz) >= 0)
-		scx_ops_exit_kind(SCX_EXIT_UNREG_BPF, exit_code, "%s",
-				  scx_exit_bstr_buf.line);
+		scx_kf_exit(SCX_EXIT_UNREG_BPF, exit_code, "%s", scx_exit_bstr_buf.line);
 	raw_spin_unlock_irqrestore(&scx_exit_bstr_buf_lock, flags);
 }
 
@@ -6961,8 +7203,7 @@ __bpf_kfunc void scx_bpf_error_bstr(char *fmt, unsigned long long *data,
 
 	raw_spin_lock_irqsave(&scx_exit_bstr_buf_lock, flags);
 	if (bstr_format(&scx_exit_bstr_buf, fmt, data, data__sz) >= 0)
-		scx_ops_exit_kind(SCX_EXIT_ERROR_BPF, 0, "%s",
-				  scx_exit_bstr_buf.line);
+		scx_kf_exit(SCX_EXIT_ERROR_BPF, 0, "%s", scx_exit_bstr_buf.line);
 	raw_spin_unlock_irqrestore(&scx_exit_bstr_buf_lock, flags);
 }
 
@@ -6986,7 +7227,7 @@ __bpf_kfunc void scx_bpf_dump_bstr(char *fmt, unsigned long long *data,
 	s32 ret;
 
 	if (raw_smp_processor_id() != dd->cpu) {
-		scx_ops_error("scx_bpf_dump() must only be called from ops.dump() and friends");
+		scx_kf_error("scx_bpf_dump() must only be called from ops.dump() and friends");
 		return;
 	}
 
@@ -7027,7 +7268,7 @@ __bpf_kfunc void scx_bpf_dump_bstr(char *fmt, unsigned long long *data,
  */
 __bpf_kfunc u32 scx_bpf_cpuperf_cap(s32 cpu)
 {
-	if (ops_cpu_valid(cpu, NULL))
+	if (kf_cpu_valid(cpu, NULL))
 		return arch_scale_cpu_capacity(cpu);
 	else
 		return SCX_CPUPERF_ONE;
@@ -7049,7 +7290,7 @@ __bpf_kfunc u32 scx_bpf_cpuperf_cap(s32 cpu)
  */
 __bpf_kfunc u32 scx_bpf_cpuperf_cur(s32 cpu)
 {
-	if (ops_cpu_valid(cpu, NULL))
+	if (kf_cpu_valid(cpu, NULL))
 		return arch_scale_freq_capacity(cpu);
 	else
 		return SCX_CPUPERF_ONE;
@@ -7072,18 +7313,37 @@ __bpf_kfunc u32 scx_bpf_cpuperf_cur(s32 cpu)
 __bpf_kfunc void scx_bpf_cpuperf_set(s32 cpu, u32 perf)
 {
 	if (unlikely(perf > SCX_CPUPERF_ONE)) {
-		scx_ops_error("Invalid cpuperf target %u for CPU %d", perf, cpu);
+		scx_kf_error("Invalid cpuperf target %u for CPU %d", perf, cpu);
 		return;
 	}
 
-	if (ops_cpu_valid(cpu, NULL)) {
-		struct rq *rq = cpu_rq(cpu);
+	if (kf_cpu_valid(cpu, NULL)) {
+		struct rq *rq = cpu_rq(cpu), *locked_rq = scx_locked_rq();
+		struct rq_flags rf;
+
+		/*
+		 * When called with an rq lock held, restrict the operation
+		 * to the corresponding CPU to prevent ABBA deadlocks.
+		 */
+		if (locked_rq && rq != locked_rq) {
+			scx_kf_error("Invalid target CPU %d", cpu);
+			return;
+		}
+
+		/*
+		 * If no rq lock is held, allow to operate on any CPU by
+		 * acquiring the corresponding rq lock.
+		 */
+		if (!locked_rq) {
+			rq_lock_irqsave(rq, &rf);
+			update_rq_clock(rq);
+		}
 
 		rq->scx.cpuperf_target = perf;
+		cpufreq_update_util(rq, 0);
 
-		rcu_read_lock_sched_notrace();
-		cpufreq_update_util(cpu_rq(cpu), 0);
-		rcu_read_unlock_sched_notrace();
+		if (!locked_rq)
+			rq_unlock_irqrestore(rq, &rf);
 	}
 }
 
@@ -7161,7 +7421,7 @@ __bpf_kfunc s32 scx_bpf_task_cpu(const struct task_struct *p)
  */
 __bpf_kfunc struct rq *scx_bpf_cpu_rq(s32 cpu)
 {
-	if (!ops_cpu_valid(cpu, NULL))
+	if (!kf_cpu_valid(cpu, NULL))
 		return NULL;
 
 	return cpu_rq(cpu);
@@ -7257,6 +7517,27 @@ __bpf_kfunc u64 scx_bpf_now(void)
 	return clock;
 }
 
+static void scx_read_events(struct scx_sched *sch, struct scx_event_stats *events)
+{
+	struct scx_event_stats *e_cpu;
+	int cpu;
+
+	/* Aggregate per-CPU event counters into @events. */
+	memset(events, 0, sizeof(*events));
+	for_each_possible_cpu(cpu) {
+		e_cpu = per_cpu_ptr(sch->event_stats_cpu, cpu);
+		scx_agg_event(events, e_cpu, SCX_EV_SELECT_CPU_FALLBACK);
+		scx_agg_event(events, e_cpu, SCX_EV_DISPATCH_LOCAL_DSQ_OFFLINE);
+		scx_agg_event(events, e_cpu, SCX_EV_DISPATCH_KEEP_LAST);
+		scx_agg_event(events, e_cpu, SCX_EV_ENQ_SKIP_EXITING);
+		scx_agg_event(events, e_cpu, SCX_EV_ENQ_SKIP_MIGRATION_DISABLED);
+		scx_agg_event(events, e_cpu, SCX_EV_REFILL_SLICE_DFL);
+		scx_agg_event(events, e_cpu, SCX_EV_BYPASS_DURATION);
+		scx_agg_event(events, e_cpu, SCX_EV_BYPASS_DISPATCH);
+		scx_agg_event(events, e_cpu, SCX_EV_BYPASS_ACTIVATE);
+	}
+}
+
 /*
  * scx_bpf_events - Get a system-wide event counter to
  * @events: output buffer from a BPF program
@@ -7265,23 +7546,16 @@ __bpf_kfunc u64 scx_bpf_now(void)
 __bpf_kfunc void scx_bpf_events(struct scx_event_stats *events,
 				size_t events__sz)
 {
-	struct scx_event_stats e_sys, *e_cpu;
-	int cpu;
+	struct scx_sched *sch;
+	struct scx_event_stats e_sys;
 
-	/* Aggregate per-CPU event counters into the system-wide counters. */
-	memset(&e_sys, 0, sizeof(e_sys));
-	for_each_possible_cpu(cpu) {
-		e_cpu = per_cpu_ptr(&event_stats_cpu, cpu);
-		scx_agg_event(&e_sys, e_cpu, SCX_EV_SELECT_CPU_FALLBACK);
-		scx_agg_event(&e_sys, e_cpu, SCX_EV_DISPATCH_LOCAL_DSQ_OFFLINE);
-		scx_agg_event(&e_sys, e_cpu, SCX_EV_DISPATCH_KEEP_LAST);
-		scx_agg_event(&e_sys, e_cpu, SCX_EV_ENQ_SKIP_EXITING);
-		scx_agg_event(&e_sys, e_cpu, SCX_EV_ENQ_SKIP_MIGRATION_DISABLED);
-		scx_agg_event(&e_sys, e_cpu, SCX_EV_ENQ_SLICE_DFL);
-		scx_agg_event(&e_sys, e_cpu, SCX_EV_BYPASS_DURATION);
-		scx_agg_event(&e_sys, e_cpu, SCX_EV_BYPASS_DISPATCH);
-		scx_agg_event(&e_sys, e_cpu, SCX_EV_BYPASS_ACTIVATE);
-	}
+	rcu_read_lock();
+	sch = rcu_dereference(scx_root);
+	if (sch)
+		scx_read_events(sch, &e_sys);
+	else
+		memset(&e_sys, 0, sizeof(e_sys));
+	rcu_read_unlock();
 
 	/*
 	 * We cannot entirely trust a BPF-provided size since a BPF program
@@ -7314,12 +7588,6 @@ BTF_ID_FLAGS(func, scx_bpf_nr_cpu_ids)
 BTF_ID_FLAGS(func, scx_bpf_get_possible_cpumask, KF_ACQUIRE)
 BTF_ID_FLAGS(func, scx_bpf_get_online_cpumask, KF_ACQUIRE)
 BTF_ID_FLAGS(func, scx_bpf_put_cpumask, KF_RELEASE)
-BTF_ID_FLAGS(func, scx_bpf_get_idle_cpumask, KF_ACQUIRE)
-BTF_ID_FLAGS(func, scx_bpf_get_idle_smtmask, KF_ACQUIRE)
-BTF_ID_FLAGS(func, scx_bpf_put_idle_cpumask, KF_RELEASE)
-BTF_ID_FLAGS(func, scx_bpf_test_and_clear_cpu_idle)
-BTF_ID_FLAGS(func, scx_bpf_pick_idle_cpu, KF_RCU)
-BTF_ID_FLAGS(func, scx_bpf_pick_any_cpu, KF_RCU)
 BTF_ID_FLAGS(func, scx_bpf_task_running, KF_RCU)
 BTF_ID_FLAGS(func, scx_bpf_task_cpu, KF_RCU)
 BTF_ID_FLAGS(func, scx_bpf_cpu_rq)
diff --git a/kernel/sched/ext.h b/kernel/sched/ext.h
index 1bda96b19a1b..6e5072f57771 100644
--- a/kernel/sched/ext.h
+++ b/kernel/sched/ext.h
@@ -8,6 +8,11 @@
  */
 #ifdef CONFIG_SCHED_CLASS_EXT
 
+static inline bool scx_kf_allowed_if_unlocked(void)
+{
+	return !current->scx.kf_mask;
+}
+
 DECLARE_STATIC_KEY_FALSE(scx_ops_allow_queued_wakeup);
 
 void scx_tick(struct rq *rq);
@@ -21,6 +26,7 @@ void scx_rq_activate(struct rq *rq);
 void scx_rq_deactivate(struct rq *rq);
 int scx_check_setscheduler(struct task_struct *p, int policy);
 bool task_should_scx(int policy);
+bool scx_allow_ttwu_queue(const struct task_struct *p);
 void init_sched_ext_class(void);
 
 static inline u32 scx_cpuperf_target(s32 cpu)
@@ -36,13 +42,6 @@ static inline bool task_on_scx(const struct task_struct *p)
 	return scx_enabled() && p->sched_class == &ext_sched_class;
 }
 
-static inline bool scx_allow_ttwu_queue(const struct task_struct *p)
-{
-	return !scx_enabled() ||
-		static_branch_likely(&scx_ops_allow_queued_wakeup) ||
-		p->sched_class != &ext_sched_class;
-}
-
 #ifdef CONFIG_SCHED_CORE
 bool scx_prio_less(const struct task_struct *a, const struct task_struct *b,
 		   bool in_fi);
diff --git a/kernel/sched/ext_idle.c b/kernel/sched/ext_idle.c
index cb343ca889e0..6d29d3cbc670 100644
--- a/kernel/sched/ext_idle.c
+++ b/kernel/sched/ext_idle.c
@@ -47,6 +47,13 @@ static struct scx_idle_cpus scx_idle_global_masks;
 static struct scx_idle_cpus **scx_idle_node_masks;
 
 /*
+ * Local per-CPU cpumasks (used to generate temporary idle cpumasks).
+ */
+static DEFINE_PER_CPU(cpumask_var_t, local_idle_cpumask);
+static DEFINE_PER_CPU(cpumask_var_t, local_llc_idle_cpumask);
+static DEFINE_PER_CPU(cpumask_var_t, local_numa_idle_cpumask);
+
+/*
  * Return the idle masks associated to a target @node.
  *
  * NUMA_NO_NODE identifies the global idle cpumask.
@@ -131,6 +138,7 @@ found:
 		goto retry;
 }
 
+#ifdef CONFIG_NUMA
 /*
  * Tracks nodes that have not yet been visited when searching for an idle
  * CPU across all available nodes.
@@ -179,6 +187,13 @@ static s32 pick_idle_cpu_from_online_nodes(const struct cpumask *cpus_allowed, i
 
 	return cpu;
 }
+#else
+static inline s32
+pick_idle_cpu_from_online_nodes(const struct cpumask *cpus_allowed, int node, u64 flags)
+{
+	return -EBUSY;
+}
+#endif
 
 /*
  * Find an idle CPU in the system, starting from @node.
@@ -392,6 +407,14 @@ void scx_idle_update_selcpu_topology(struct sched_ext_ops *ops)
 }
 
 /*
+ * Return true if @p can run on all possible CPUs, false otherwise.
+ */
+static inline bool task_affinity_all(const struct task_struct *p)
+{
+	return p->nr_cpus_allowed >= num_possible_cpus();
+}
+
+/*
  * Built-in CPU idle selection policy:
  *
  * 1. Prioritize full-idle cores:
@@ -403,13 +426,15 @@ void scx_idle_update_selcpu_topology(struct sched_ext_ops *ops)
  *     branch prediction optimizations.
  *
  * 3. Pick a CPU within the same LLC (Last-Level Cache):
- *   - if the above conditions aren't met, pick a CPU that shares the same LLC
- *     to maintain cache locality.
+ *   - if the above conditions aren't met, pick a CPU that shares the same
+ *     LLC, if the LLC domain is a subset of @cpus_allowed, to maintain
+ *     cache locality.
  *
  * 4. Pick a CPU within the same NUMA node, if enabled:
- *   - choose a CPU from the same NUMA node to reduce memory access latency.
+ *   - choose a CPU from the same NUMA node, if the node cpumask is a
+ *     subset of @cpus_allowed, to reduce memory access latency.
  *
- * 5. Pick any idle CPU usable by the task.
+ * 5. Pick any idle CPU within the @cpus_allowed domain.
  *
  * Step 3 and 4 are performed only if the system has, respectively,
  * multiple LLCs / multiple NUMA nodes (see scx_selcpu_topo_llc and
@@ -424,35 +449,69 @@ void scx_idle_update_selcpu_topology(struct sched_ext_ops *ops)
  * NOTE: tasks that can only run on 1 CPU are excluded by this logic, because
  * we never call ops.select_cpu() for them, see select_task_rq().
  */
-s32 scx_select_cpu_dfl(struct task_struct *p, s32 prev_cpu, u64 wake_flags, u64 flags)
+s32 scx_select_cpu_dfl(struct task_struct *p, s32 prev_cpu, u64 wake_flags,
+		       const struct cpumask *cpus_allowed, u64 flags)
 {
-	const struct cpumask *llc_cpus = NULL;
-	const struct cpumask *numa_cpus = NULL;
+	const struct cpumask *llc_cpus = NULL, *numa_cpus = NULL;
+	const struct cpumask *allowed = cpus_allowed ?: p->cpus_ptr;
 	int node = scx_cpu_node_if_enabled(prev_cpu);
+	bool is_prev_allowed;
 	s32 cpu;
 
+	preempt_disable();
+
+	/*
+	 * Check whether @prev_cpu is still within the allowed set. If not,
+	 * we can still try selecting a nearby CPU.
+	 */
+	is_prev_allowed = cpumask_test_cpu(prev_cpu, allowed);
+
+	/*
+	 * Determine the subset of CPUs usable by @p within @cpus_allowed.
+	 */
+	if (allowed != p->cpus_ptr) {
+		struct cpumask *local_cpus = this_cpu_cpumask_var_ptr(local_idle_cpumask);
+
+		if (task_affinity_all(p)) {
+			allowed = cpus_allowed;
+		} else if (cpumask_and(local_cpus, cpus_allowed, p->cpus_ptr)) {
+			allowed = local_cpus;
+		} else {
+			cpu = -EBUSY;
+			goto out_enable;
+		}
+	}
+
 	/*
 	 * This is necessary to protect llc_cpus.
 	 */
 	rcu_read_lock();
 
 	/*
-	 * Determine the scheduling domain only if the task is allowed to run
-	 * on all CPUs.
+	 * Determine the subset of CPUs that the task can use in its
+	 * current LLC and node.
 	 *
-	 * This is done primarily for efficiency, as it avoids the overhead of
-	 * updating a cpumask every time we need to select an idle CPU (which
-	 * can be costly in large SMP systems), but it also aligns logically:
-	 * if a task's scheduling domain is restricted by user-space (through
-	 * CPU affinity), the task will simply use the flat scheduling domain
-	 * defined by user-space.
+	 * If the task can run on all CPUs, use the node and LLC cpumasks
+	 * directly.
 	 */
-	if (p->nr_cpus_allowed >= num_possible_cpus()) {
-		if (static_branch_maybe(CONFIG_NUMA, &scx_selcpu_topo_numa))
-			numa_cpus = numa_span(prev_cpu);
+	if (static_branch_maybe(CONFIG_NUMA, &scx_selcpu_topo_numa)) {
+		struct cpumask *local_cpus = this_cpu_cpumask_var_ptr(local_numa_idle_cpumask);
+		const struct cpumask *cpus = numa_span(prev_cpu);
+
+		if (allowed == p->cpus_ptr && task_affinity_all(p))
+			numa_cpus = cpus;
+		else if (cpus && cpumask_and(local_cpus, allowed, cpus))
+			numa_cpus = local_cpus;
+	}
 
-		if (static_branch_maybe(CONFIG_SCHED_MC, &scx_selcpu_topo_llc))
-			llc_cpus = llc_span(prev_cpu);
+	if (static_branch_maybe(CONFIG_SCHED_MC, &scx_selcpu_topo_llc)) {
+		struct cpumask *local_cpus = this_cpu_cpumask_var_ptr(local_llc_idle_cpumask);
+		const struct cpumask *cpus = llc_span(prev_cpu);
+
+		if (allowed == p->cpus_ptr && task_affinity_all(p))
+			llc_cpus = cpus;
+		else if (cpus && cpumask_and(local_cpus, allowed, cpus))
+			llc_cpus = local_cpus;
 	}
 
 	/*
@@ -466,7 +525,7 @@ s32 scx_select_cpu_dfl(struct task_struct *p, s32 prev_cpu, u64 wake_flags, u64
 		 * then avoid a migration.
 		 */
 		cpu = smp_processor_id();
-		if (cpus_share_cache(cpu, prev_cpu) &&
+		if (is_prev_allowed && cpus_share_cache(cpu, prev_cpu) &&
 		    scx_idle_test_and_clear_cpu(prev_cpu)) {
 			cpu = prev_cpu;
 			goto out_unlock;
@@ -490,7 +549,7 @@ s32 scx_select_cpu_dfl(struct task_struct *p, s32 prev_cpu, u64 wake_flags, u64
 		    cpu_rq(cpu)->scx.local_dsq.nr == 0 &&
 		    (!(flags & SCX_PICK_IDLE_IN_NODE) || (waker_node == node)) &&
 		    !cpumask_empty(idle_cpumask(waker_node)->cpu)) {
-			if (cpumask_test_cpu(cpu, p->cpus_ptr))
+			if (cpumask_test_cpu(cpu, allowed))
 				goto out_unlock;
 		}
 	}
@@ -503,7 +562,8 @@ s32 scx_select_cpu_dfl(struct task_struct *p, s32 prev_cpu, u64 wake_flags, u64
 		/*
 		 * Keep using @prev_cpu if it's part of a fully idle core.
 		 */
-		if (cpumask_test_cpu(prev_cpu, idle_cpumask(node)->smt) &&
+		if (is_prev_allowed &&
+		    cpumask_test_cpu(prev_cpu, idle_cpumask(node)->smt) &&
 		    scx_idle_test_and_clear_cpu(prev_cpu)) {
 			cpu = prev_cpu;
 			goto out_unlock;
@@ -535,7 +595,7 @@ s32 scx_select_cpu_dfl(struct task_struct *p, s32 prev_cpu, u64 wake_flags, u64
 		 * begin in prev_cpu's node and proceed to other nodes in
 		 * order of increasing distance.
 		 */
-		cpu = scx_pick_idle_cpu(p->cpus_ptr, node, flags | SCX_PICK_IDLE_CORE);
+		cpu = scx_pick_idle_cpu(allowed, node, flags | SCX_PICK_IDLE_CORE);
 		if (cpu >= 0)
 			goto out_unlock;
 
@@ -552,7 +612,7 @@ s32 scx_select_cpu_dfl(struct task_struct *p, s32 prev_cpu, u64 wake_flags, u64
 	/*
 	 * Use @prev_cpu if it's idle.
 	 */
-	if (scx_idle_test_and_clear_cpu(prev_cpu)) {
+	if (is_prev_allowed && scx_idle_test_and_clear_cpu(prev_cpu)) {
 		cpu = prev_cpu;
 		goto out_unlock;
 	}
@@ -583,10 +643,12 @@ s32 scx_select_cpu_dfl(struct task_struct *p, s32 prev_cpu, u64 wake_flags, u64
 	 * in prev_cpu's node and proceed to other nodes in order of
 	 * increasing distance.
 	 */
-	cpu = scx_pick_idle_cpu(p->cpus_ptr, node, flags);
+	cpu = scx_pick_idle_cpu(allowed, node, flags);
 
 out_unlock:
 	rcu_read_unlock();
+out_enable:
+	preempt_enable();
 
 	return cpu;
 }
@@ -596,7 +658,7 @@ out_unlock:
  */
 void scx_idle_init_masks(void)
 {
-	int node;
+	int i;
 
 	/* Allocate global idle cpumasks */
 	BUG_ON(!alloc_cpumask_var(&scx_idle_global_masks.cpu, GFP_KERNEL));
@@ -607,13 +669,23 @@ void scx_idle_init_masks(void)
 				      sizeof(*scx_idle_node_masks), GFP_KERNEL);
 	BUG_ON(!scx_idle_node_masks);
 
-	for_each_node(node) {
-		scx_idle_node_masks[node] = kzalloc_node(sizeof(**scx_idle_node_masks),
-							 GFP_KERNEL, node);
-		BUG_ON(!scx_idle_node_masks[node]);
+	for_each_node(i) {
+		scx_idle_node_masks[i] = kzalloc_node(sizeof(**scx_idle_node_masks),
+							 GFP_KERNEL, i);
+		BUG_ON(!scx_idle_node_masks[i]);
 
-		BUG_ON(!alloc_cpumask_var_node(&scx_idle_node_masks[node]->cpu, GFP_KERNEL, node));
-		BUG_ON(!alloc_cpumask_var_node(&scx_idle_node_masks[node]->smt, GFP_KERNEL, node));
+		BUG_ON(!alloc_cpumask_var_node(&scx_idle_node_masks[i]->cpu, GFP_KERNEL, i));
+		BUG_ON(!alloc_cpumask_var_node(&scx_idle_node_masks[i]->smt, GFP_KERNEL, i));
+	}
+
+	/* Allocate local per-cpu idle cpumasks */
+	for_each_possible_cpu(i) {
+		BUG_ON(!alloc_cpumask_var_node(&per_cpu(local_idle_cpumask, i),
+					       GFP_KERNEL, cpu_to_node(i)));
+		BUG_ON(!alloc_cpumask_var_node(&per_cpu(local_llc_idle_cpumask, i),
+					       GFP_KERNEL, cpu_to_node(i)));
+		BUG_ON(!alloc_cpumask_var_node(&per_cpu(local_numa_idle_cpumask, i),
+					       GFP_KERNEL, cpu_to_node(i)));
 	}
 }
 
@@ -662,21 +734,12 @@ static void update_builtin_idle(int cpu, bool idle)
  */
 void __scx_update_idle(struct rq *rq, bool idle, bool do_notify)
 {
+	struct scx_sched *sch = scx_root;
 	int cpu = cpu_of(rq);
 
 	lockdep_assert_rq_held(rq);
 
 	/*
-	 * Trigger ops.update_idle() only when transitioning from a task to
-	 * the idle thread and vice versa.
-	 *
-	 * Idle transitions are indicated by do_notify being set to true,
-	 * managed by put_prev_task_idle()/set_next_task_idle().
-	 */
-	if (SCX_HAS_OP(update_idle) && do_notify && !scx_rq_bypassing(rq))
-		SCX_CALL_OP(SCX_KF_REST, update_idle, cpu_of(rq), idle);
-
-	/*
 	 * Update the idle masks:
 	 * - for real idle transitions (do_notify == true)
 	 * - for idle-to-idle transitions (indicated by the previous task
@@ -693,6 +756,21 @@ void __scx_update_idle(struct rq *rq, bool idle, bool do_notify)
 	if (static_branch_likely(&scx_builtin_idle_enabled))
 		if (do_notify || is_idle_task(rq->curr))
 			update_builtin_idle(cpu, idle);
+
+	/*
+	 * Trigger ops.update_idle() only when transitioning from a task to
+	 * the idle thread and vice versa.
+	 *
+	 * Idle transitions are indicated by do_notify being set to true,
+	 * managed by put_prev_task_idle()/set_next_task_idle().
+	 *
+	 * This must come after builtin idle update so that BPF schedulers can
+	 * create interlocking between ops.update_idle() and ops.enqueue() -
+	 * either enqueue() sees the idle bit or update_idle() sees the task
+	 * that enqueue() queued.
+	 */
+	if (SCX_HAS_OP(sch, update_idle) && do_notify && !scx_rq_bypassing(rq))
+		SCX_CALL_OP(sch, SCX_KF_REST, update_idle, rq, cpu_of(rq), idle);
 }
 
 static void reset_idle_masks(struct sched_ext_ops *ops)
@@ -748,7 +826,7 @@ void scx_idle_disable(void)
 static int validate_node(int node)
 {
 	if (!static_branch_likely(&scx_builtin_idle_per_node)) {
-		scx_ops_error("per-node idle tracking is disabled");
+		scx_kf_error("per-node idle tracking is disabled");
 		return -EOPNOTSUPP;
 	}
 
@@ -758,13 +836,13 @@ static int validate_node(int node)
 
 	/* Make sure node is in a valid range */
 	if (node < 0 || node >= nr_node_ids) {
-		scx_ops_error("invalid node %d", node);
+		scx_kf_error("invalid node %d", node);
 		return -EINVAL;
 	}
 
 	/* Make sure the node is part of the set of possible nodes */
 	if (!node_possible(node)) {
-		scx_ops_error("unavailable node %d", node);
+		scx_kf_error("unavailable node %d", node);
 		return -EINVAL;
 	}
 
@@ -778,10 +856,72 @@ static bool check_builtin_idle_enabled(void)
 	if (static_branch_likely(&scx_builtin_idle_enabled))
 		return true;
 
-	scx_ops_error("built-in idle tracking is disabled");
+	scx_kf_error("built-in idle tracking is disabled");
 	return false;
 }
 
+s32 select_cpu_from_kfunc(struct task_struct *p, s32 prev_cpu, u64 wake_flags,
+			  const struct cpumask *allowed, u64 flags)
+{
+	struct rq *rq;
+	struct rq_flags rf;
+	s32 cpu;
+
+	if (!kf_cpu_valid(prev_cpu, NULL))
+		return -EINVAL;
+
+	if (!check_builtin_idle_enabled())
+		return -EBUSY;
+
+	/*
+	 * If called from an unlocked context, acquire the task's rq lock,
+	 * so that we can safely access p->cpus_ptr and p->nr_cpus_allowed.
+	 *
+	 * Otherwise, allow to use this kfunc only from ops.select_cpu()
+	 * and ops.select_enqueue().
+	 */
+	if (scx_kf_allowed_if_unlocked()) {
+		rq = task_rq_lock(p, &rf);
+	} else {
+		if (!scx_kf_allowed(SCX_KF_SELECT_CPU | SCX_KF_ENQUEUE))
+			return -EPERM;
+		rq = scx_locked_rq();
+	}
+
+	/*
+	 * Validate locking correctness to access p->cpus_ptr and
+	 * p->nr_cpus_allowed: if we're holding an rq lock, we're safe;
+	 * otherwise, assert that p->pi_lock is held.
+	 */
+	if (!rq)
+		lockdep_assert_held(&p->pi_lock);
+
+#ifdef CONFIG_SMP
+	/*
+	 * This may also be called from ops.enqueue(), so we need to handle
+	 * per-CPU tasks as well. For these tasks, we can skip all idle CPU
+	 * selection optimizations and simply check whether the previously
+	 * used CPU is idle and within the allowed cpumask.
+	 */
+	if (p->nr_cpus_allowed == 1) {
+		if (cpumask_test_cpu(prev_cpu, allowed ?: p->cpus_ptr) &&
+		    scx_idle_test_and_clear_cpu(prev_cpu))
+			cpu = prev_cpu;
+		else
+			cpu = -EBUSY;
+	} else {
+		cpu = scx_select_cpu_dfl(p, prev_cpu, wake_flags,
+					 allowed ?: p->cpus_ptr, flags);
+	}
+#else
+	cpu = -EBUSY;
+#endif
+	if (scx_kf_allowed_if_unlocked())
+		task_rq_unlock(rq, p, &rf);
+
+	return cpu;
+}
+
 /**
  * scx_bpf_cpu_node - Return the NUMA node the given @cpu belongs to, or
  *		      trigger an error if @cpu is invalid
@@ -790,7 +930,7 @@ static bool check_builtin_idle_enabled(void)
 __bpf_kfunc int scx_bpf_cpu_node(s32 cpu)
 {
 #ifdef CONFIG_NUMA
-	if (!ops_cpu_valid(cpu, NULL))
+	if (!kf_cpu_valid(cpu, NULL))
 		return NUMA_NO_NODE;
 
 	return cpu_to_node(cpu);
@@ -806,9 +946,10 @@ __bpf_kfunc int scx_bpf_cpu_node(s32 cpu)
  * @wake_flags: %SCX_WAKE_* flags
  * @is_idle: out parameter indicating whether the returned CPU is idle
  *
- * Can only be called from ops.select_cpu() if the built-in CPU selection is
- * enabled - ops.update_idle() is missing or %SCX_OPS_KEEP_BUILTIN_IDLE is set.
- * @p, @prev_cpu and @wake_flags match ops.select_cpu().
+ * Can be called from ops.select_cpu(), ops.enqueue(), or from an unlocked
+ * context such as a BPF test_run() call, as long as built-in CPU selection
+ * is enabled: ops.update_idle() is missing or %SCX_OPS_KEEP_BUILTIN_IDLE
+ * is set.
  *
  * Returns the picked CPU with *@is_idle indicating whether the picked CPU is
  * currently idle and thus a good candidate for direct dispatching.
@@ -816,39 +957,52 @@ __bpf_kfunc int scx_bpf_cpu_node(s32 cpu)
 __bpf_kfunc s32 scx_bpf_select_cpu_dfl(struct task_struct *p, s32 prev_cpu,
 				       u64 wake_flags, bool *is_idle)
 {
-#ifdef CONFIG_SMP
 	s32 cpu;
-#endif
-	if (!ops_cpu_valid(prev_cpu, NULL))
-		goto prev_cpu;
-
-	if (!check_builtin_idle_enabled())
-		goto prev_cpu;
-
-	if (!scx_kf_allowed(SCX_KF_SELECT_CPU))
-		goto prev_cpu;
 
-#ifdef CONFIG_SMP
-	cpu = scx_select_cpu_dfl(p, prev_cpu, wake_flags, 0);
+	cpu = select_cpu_from_kfunc(p, prev_cpu, wake_flags, NULL, 0);
 	if (cpu >= 0) {
 		*is_idle = true;
 		return cpu;
 	}
-#endif
-
-prev_cpu:
 	*is_idle = false;
+
 	return prev_cpu;
 }
 
 /**
+ * scx_bpf_select_cpu_and - Pick an idle CPU usable by task @p,
+ *			    prioritizing those in @cpus_allowed
+ * @p: task_struct to select a CPU for
+ * @prev_cpu: CPU @p was on previously
+ * @wake_flags: %SCX_WAKE_* flags
+ * @cpus_allowed: cpumask of allowed CPUs
+ * @flags: %SCX_PICK_IDLE* flags
+ *
+ * Can be called from ops.select_cpu(), ops.enqueue(), or from an unlocked
+ * context such as a BPF test_run() call, as long as built-in CPU selection
+ * is enabled: ops.update_idle() is missing or %SCX_OPS_KEEP_BUILTIN_IDLE
+ * is set.
+ *
+ * @p, @prev_cpu and @wake_flags match ops.select_cpu().
+ *
+ * Returns the selected idle CPU, which will be automatically awakened upon
+ * returning from ops.select_cpu() and can be used for direct dispatch, or
+ * a negative value if no idle CPU is available.
+ */
+__bpf_kfunc s32 scx_bpf_select_cpu_and(struct task_struct *p, s32 prev_cpu, u64 wake_flags,
+				       const struct cpumask *cpus_allowed, u64 flags)
+{
+	return select_cpu_from_kfunc(p, prev_cpu, wake_flags, cpus_allowed, flags);
+}
+
+/**
  * scx_bpf_get_idle_cpumask_node - Get a referenced kptr to the
  * idle-tracking per-CPU cpumask of a target NUMA node.
  * @node: target NUMA node
  *
  * Returns an empty cpumask if idle tracking is not enabled, if @node is
  * not valid, or running on a UP kernel. In this case the actual error will
- * be reported to the BPF scheduler via scx_ops_error().
+ * be reported to the BPF scheduler via scx_error().
  */
 __bpf_kfunc const struct cpumask *scx_bpf_get_idle_cpumask_node(int node)
 {
@@ -873,7 +1027,7 @@ __bpf_kfunc const struct cpumask *scx_bpf_get_idle_cpumask_node(int node)
 __bpf_kfunc const struct cpumask *scx_bpf_get_idle_cpumask(void)
 {
 	if (static_branch_unlikely(&scx_builtin_idle_per_node)) {
-		scx_ops_error("SCX_OPS_BUILTIN_IDLE_PER_NODE enabled");
+		scx_kf_error("SCX_OPS_BUILTIN_IDLE_PER_NODE enabled");
 		return cpu_none_mask;
 	}
 
@@ -895,7 +1049,7 @@ __bpf_kfunc const struct cpumask *scx_bpf_get_idle_cpumask(void)
  *
  * Returns an empty cpumask if idle tracking is not enabled, if @node is
  * not valid, or running on a UP kernel. In this case the actual error will
- * be reported to the BPF scheduler via scx_ops_error().
+ * be reported to the BPF scheduler via scx_error().
  */
 __bpf_kfunc const struct cpumask *scx_bpf_get_idle_smtmask_node(int node)
 {
@@ -924,7 +1078,7 @@ __bpf_kfunc const struct cpumask *scx_bpf_get_idle_smtmask_node(int node)
 __bpf_kfunc const struct cpumask *scx_bpf_get_idle_smtmask(void)
 {
 	if (static_branch_unlikely(&scx_builtin_idle_per_node)) {
-		scx_ops_error("SCX_OPS_BUILTIN_IDLE_PER_NODE enabled");
+		scx_kf_error("SCX_OPS_BUILTIN_IDLE_PER_NODE enabled");
 		return cpu_none_mask;
 	}
 
@@ -971,7 +1125,7 @@ __bpf_kfunc bool scx_bpf_test_and_clear_cpu_idle(s32 cpu)
 	if (!check_builtin_idle_enabled())
 		return false;
 
-	if (ops_cpu_valid(cpu, NULL))
+	if (kf_cpu_valid(cpu, NULL))
 		return scx_idle_test_and_clear_cpu(cpu);
 	else
 		return false;
@@ -1032,7 +1186,7 @@ __bpf_kfunc s32 scx_bpf_pick_idle_cpu(const struct cpumask *cpus_allowed,
 				      u64 flags)
 {
 	if (static_branch_maybe(CONFIG_NUMA, &scx_builtin_idle_per_node)) {
-		scx_ops_error("per-node idle tracking is enabled");
+		scx_kf_error("per-node idle tracking is enabled");
 		return -EBUSY;
 	}
 
@@ -1109,7 +1263,7 @@ __bpf_kfunc s32 scx_bpf_pick_any_cpu(const struct cpumask *cpus_allowed,
 	s32 cpu;
 
 	if (static_branch_maybe(CONFIG_NUMA, &scx_builtin_idle_per_node)) {
-		scx_ops_error("per-node idle tracking is enabled");
+		scx_kf_error("per-node idle tracking is enabled");
 		return -EBUSY;
 	}
 
@@ -1140,6 +1294,8 @@ BTF_ID_FLAGS(func, scx_bpf_pick_idle_cpu_node, KF_RCU)
 BTF_ID_FLAGS(func, scx_bpf_pick_idle_cpu, KF_RCU)
 BTF_ID_FLAGS(func, scx_bpf_pick_any_cpu_node, KF_RCU)
 BTF_ID_FLAGS(func, scx_bpf_pick_any_cpu, KF_RCU)
+BTF_ID_FLAGS(func, scx_bpf_select_cpu_and, KF_RCU)
+BTF_ID_FLAGS(func, scx_bpf_select_cpu_dfl, KF_RCU)
 BTF_KFUNCS_END(scx_kfunc_ids_idle)
 
 static const struct btf_kfunc_id_set scx_kfunc_set_idle = {
@@ -1147,21 +1303,11 @@ static const struct btf_kfunc_id_set scx_kfunc_set_idle = {
 	.set			= &scx_kfunc_ids_idle,
 };
 
-BTF_KFUNCS_START(scx_kfunc_ids_select_cpu)
-BTF_ID_FLAGS(func, scx_bpf_select_cpu_dfl, KF_RCU)
-BTF_KFUNCS_END(scx_kfunc_ids_select_cpu)
-
-static const struct btf_kfunc_id_set scx_kfunc_set_select_cpu = {
-	.owner			= THIS_MODULE,
-	.set			= &scx_kfunc_ids_select_cpu,
-};
-
 int scx_idle_init(void)
 {
 	int ret;
 
-	ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS, &scx_kfunc_set_select_cpu) ||
-	      register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS, &scx_kfunc_set_idle) ||
+	ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS, &scx_kfunc_set_idle) ||
 	      register_btf_kfunc_id_set(BPF_PROG_TYPE_TRACING, &scx_kfunc_set_idle) ||
 	      register_btf_kfunc_id_set(BPF_PROG_TYPE_SYSCALL, &scx_kfunc_set_idle);
 
diff --git a/kernel/sched/ext_idle.h b/kernel/sched/ext_idle.h
index 511cc2221f7a..37be78a7502b 100644
--- a/kernel/sched/ext_idle.h
+++ b/kernel/sched/ext_idle.h
@@ -27,7 +27,8 @@ static inline s32 scx_pick_idle_cpu(const struct cpumask *cpus_allowed, int node
 }
 #endif /* CONFIG_SMP */
 
-s32 scx_select_cpu_dfl(struct task_struct *p, s32 prev_cpu, u64 wake_flags, u64 flags);
+s32 scx_select_cpu_dfl(struct task_struct *p, s32 prev_cpu, u64 wake_flags,
+		       const struct cpumask *cpus_allowed, u64 flags);
 void scx_idle_enable(struct sched_ext_ops *ops);
 void scx_idle_disable(void);
 int scx_idle_init(void);
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 0fb9bf995a47..7a14da5396fb 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -2273,7 +2273,8 @@ static bool task_numa_compare(struct task_numa_env *env,
 
 	rcu_read_lock();
 	cur = rcu_dereference(dst_rq->curr);
-	if (cur && ((cur->flags & PF_EXITING) || is_idle_task(cur)))
+	if (cur && ((cur->flags & (PF_EXITING | PF_KTHREAD)) ||
+		    !cur->mm))
 		cur = NULL;
 
 	/*
@@ -3329,6 +3330,15 @@ static void task_numa_work(struct callback_head *work)
 	if (p->flags & PF_EXITING)
 		return;
 
+	/*
+	 * Memory is pinned to only one NUMA node via cpuset.mems, naturally
+	 * no page can be migrated.
+	 */
+	if (cpusets_enabled() && nodes_weight(cpuset_current_mems_allowed) == 1) {
+		trace_sched_skip_cpuset_numa(current, &cpuset_current_mems_allowed);
+		return;
+	}
+
 	if (!mm->numa_next_scan) {
 		mm->numa_next_scan = now +
 			msecs_to_jiffies(sysctl_numa_balancing_scan_delay);
@@ -3795,6 +3805,7 @@ static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se,
 		update_entity_lag(cfs_rq, se);
 		se->deadline -= se->vruntime;
 		se->rel_deadline = 1;
+		cfs_rq->nr_queued--;
 		if (!curr)
 			__dequeue_entity(cfs_rq, se);
 		update_load_sub(&cfs_rq->load, se->load.weight);
@@ -3821,10 +3832,11 @@ static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se,
 
 	enqueue_load_avg(cfs_rq, se);
 	if (se->on_rq) {
-		update_load_add(&cfs_rq->load, se->load.weight);
 		place_entity(cfs_rq, se, 0);
+		update_load_add(&cfs_rq->load, se->load.weight);
 		if (!curr)
 			__enqueue_entity(cfs_rq, se);
+		cfs_rq->nr_queued++;
 
 		/*
 		 * The entity's vruntime has been adjusted, so let's check
@@ -4933,13 +4945,6 @@ static inline void util_est_update(struct cfs_rq *cfs_rq,
 		goto done;
 
 	/*
-	 * To avoid overestimation of actual task utilization, skip updates if
-	 * we cannot grant there is idle time in this CPU.
-	 */
-	if (dequeued > arch_scale_cpu_capacity(cpu_of(rq_of(cfs_rq))))
-		return;
-
-	/*
 	 * To avoid underestimate of task utilization, skip updates of EWMA if
 	 * we cannot grant that thread got all CPU time it wanted.
 	 */
@@ -6941,7 +6946,7 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 	 * Let's add the task's estimated utilization to the cfs_rq's
 	 * estimated utilization, before we update schedutil.
 	 */
-	if (!(p->se.sched_delayed && (task_on_rq_migrating(p) || (flags & ENQUEUE_RESTORE))))
+	if (!p->se.sched_delayed || (flags & ENQUEUE_DELAYED))
 		util_est_enqueue(&rq->cfs, p);
 
 	if (flags & ENQUEUE_DELAYED) {
@@ -7181,7 +7186,7 @@ static int dequeue_entities(struct rq *rq, struct sched_entity *se, int flags)
  */
 static bool dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 {
-	if (!(p->se.sched_delayed && (task_on_rq_migrating(p) || (flags & DEQUEUE_SAVE))))
+	if (!p->se.sched_delayed)
 		util_est_dequeue(&rq->cfs, p);
 
 	util_est_update(&rq->cfs, p, flags & DEQUEUE_SLEEP);
@@ -7196,6 +7201,11 @@ static bool dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 	return true;
 }
 
+static inline unsigned int cfs_h_nr_delayed(struct rq *rq)
+{
+	return (rq->cfs.h_nr_queued - rq->cfs.h_nr_runnable);
+}
+
 #ifdef CONFIG_SMP
 
 /* Working cpumask for: sched_balance_rq(), sched_balance_newidle(). */
@@ -7357,8 +7367,12 @@ wake_affine_idle(int this_cpu, int prev_cpu, int sync)
 	if (available_idle_cpu(this_cpu) && cpus_share_cache(this_cpu, prev_cpu))
 		return available_idle_cpu(prev_cpu) ? prev_cpu : this_cpu;
 
-	if (sync && cpu_rq(this_cpu)->nr_running == 1)
-		return this_cpu;
+	if (sync) {
+		struct rq *rq = cpu_rq(this_cpu);
+
+		if ((rq->nr_running - cfs_h_nr_delayed(rq)) == 1)
+			return this_cpu;
+	}
 
 	if (available_idle_cpu(prev_cpu))
 		return prev_cpu;
@@ -10256,7 +10270,7 @@ sched_group_asym(struct lb_env *env, struct sg_lb_stats *sgs, struct sched_group
 	    (sgs->group_weight - sgs->idle_cpus != 1))
 		return false;
 
-	return sched_asym(env->sd, env->dst_cpu, group->asym_prefer_cpu);
+	return sched_asym(env->sd, env->dst_cpu, READ_ONCE(group->asym_prefer_cpu));
 }
 
 /* One group has more than one SMT CPU while the other group does not */
@@ -10493,7 +10507,8 @@ static bool update_sd_pick_busiest(struct lb_env *env,
 
 	case group_asym_packing:
 		/* Prefer to move from lowest priority CPU's work */
-		return sched_asym_prefer(sds->busiest->asym_prefer_cpu, sg->asym_prefer_cpu);
+		return sched_asym_prefer(READ_ONCE(sds->busiest->asym_prefer_cpu),
+					 READ_ONCE(sg->asym_prefer_cpu));
 
 	case group_misfit_task:
 		/*
diff --git a/kernel/sched/isolation.c b/kernel/sched/isolation.c
index 81bc8b329ef1..93b038d48900 100644
--- a/kernel/sched/isolation.c
+++ b/kernel/sched/isolation.c
@@ -40,7 +40,7 @@ int housekeeping_any_cpu(enum hk_type type)
 			if (cpu < nr_cpu_ids)
 				return cpu;
 
-			cpu = cpumask_any_and(housekeeping.cpumasks[type], cpu_online_mask);
+			cpu = cpumask_any_and_distribute(housekeeping.cpumasks[type], cpu_online_mask);
 			if (likely(cpu < nr_cpu_ids))
 				return cpu;
 			/*
diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c
index 1396674fa722..ad04a5c3162a 100644
--- a/kernel/sched/psi.c
+++ b/kernel/sched/psi.c
@@ -733,7 +733,7 @@ static int psi_rtpoll_worker(void *data)
 
 static void poll_timer_fn(struct timer_list *t)
 {
-	struct psi_group *group = from_timer(group, t, rtpoll_timer);
+	struct psi_group *group = timer_container_of(group, t, rtpoll_timer);
 
 	atomic_set(&group->rtpoll_wakeup, 1);
 	wake_up_interruptible(&group->rtpoll_wait);
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index fa03ec3ed56a..e40422c37033 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -89,6 +89,7 @@ void init_rt_rq(struct rt_rq *rt_rq)
 	rt_rq->rt_throttled = 0;
 	rt_rq->rt_runtime = 0;
 	raw_spin_lock_init(&rt_rq->rt_runtime_lock);
+	rt_rq->tg = &root_task_group;
 #endif
 }
 
@@ -175,11 +176,14 @@ static inline struct task_struct *rt_task_of(struct sched_rt_entity *rt_se)
 
 static inline struct rq *rq_of_rt_rq(struct rt_rq *rt_rq)
 {
+	/* Cannot fold with non-CONFIG_RT_GROUP_SCHED version, layout */
+	WARN_ON(!rt_group_sched_enabled() && rt_rq->tg != &root_task_group);
 	return rt_rq->rq;
 }
 
 static inline struct rt_rq *rt_rq_of_se(struct sched_rt_entity *rt_se)
 {
+	WARN_ON(!rt_group_sched_enabled() && rt_se->rt_rq->tg != &root_task_group);
 	return rt_se->rt_rq;
 }
 
@@ -187,11 +191,15 @@ static inline struct rq *rq_of_rt_se(struct sched_rt_entity *rt_se)
 {
 	struct rt_rq *rt_rq = rt_se->rt_rq;
 
+	WARN_ON(!rt_group_sched_enabled() && rt_rq->tg != &root_task_group);
 	return rt_rq->rq;
 }
 
 void unregister_rt_sched_group(struct task_group *tg)
 {
+	if (!rt_group_sched_enabled())
+		return;
+
 	if (tg->rt_se)
 		destroy_rt_bandwidth(&tg->rt_bandwidth);
 }
@@ -200,6 +208,9 @@ void free_rt_sched_group(struct task_group *tg)
 {
 	int i;
 
+	if (!rt_group_sched_enabled())
+		return;
+
 	for_each_possible_cpu(i) {
 		if (tg->rt_rq)
 			kfree(tg->rt_rq[i]);
@@ -244,6 +255,9 @@ int alloc_rt_sched_group(struct task_group *tg, struct task_group *parent)
 	struct sched_rt_entity *rt_se;
 	int i;
 
+	if (!rt_group_sched_enabled())
+		return 1;
+
 	tg->rt_rq = kcalloc(nr_cpu_ids, sizeof(rt_rq), GFP_KERNEL);
 	if (!tg->rt_rq)
 		goto err;
@@ -482,9 +496,6 @@ static inline bool rt_task_fits_capacity(struct task_struct *p, int cpu)
 
 static inline u64 sched_rt_runtime(struct rt_rq *rt_rq)
 {
-	if (!rt_rq->tg)
-		return RUNTIME_INF;
-
 	return rt_rq->rt_runtime;
 }
 
@@ -497,6 +508,11 @@ typedef struct task_group *rt_rq_iter_t;
 
 static inline struct task_group *next_task_group(struct task_group *tg)
 {
+	if (!rt_group_sched_enabled()) {
+		WARN_ON(tg != &root_task_group);
+		return NULL;
+	}
+
 	do {
 		tg = list_entry_rcu(tg->list.next,
 			typeof(struct task_group), list);
@@ -509,9 +525,9 @@ static inline struct task_group *next_task_group(struct task_group *tg)
 }
 
 #define for_each_rt_rq(rt_rq, iter, rq)					\
-	for (iter = container_of(&task_groups, typeof(*iter), list);	\
-		(iter = next_task_group(iter)) &&			\
-		(rt_rq = iter->rt_rq[cpu_of(rq)]);)
+	for (iter = &root_task_group;					\
+		iter && (rt_rq = iter->rt_rq[cpu_of(rq)]);		\
+		iter = next_task_group(iter))
 
 #define for_each_sched_rt_entity(rt_se) \
 	for (; rt_se; rt_se = rt_se->parent)
@@ -1066,13 +1082,12 @@ inc_rt_prio_smp(struct rt_rq *rt_rq, int prio, int prev_prio)
 {
 	struct rq *rq = rq_of_rt_rq(rt_rq);
 
-#ifdef CONFIG_RT_GROUP_SCHED
 	/*
 	 * Change rq's cpupri only if rt_rq is the top queue.
 	 */
-	if (&rq->rt != rt_rq)
+	if (IS_ENABLED(CONFIG_RT_GROUP_SCHED) && &rq->rt != rt_rq)
 		return;
-#endif
+
 	if (rq->online && prio < prev_prio)
 		cpupri_set(&rq->rd->cpupri, rq->cpu, prio);
 }
@@ -1082,13 +1097,12 @@ dec_rt_prio_smp(struct rt_rq *rt_rq, int prio, int prev_prio)
 {
 	struct rq *rq = rq_of_rt_rq(rt_rq);
 
-#ifdef CONFIG_RT_GROUP_SCHED
 	/*
 	 * Change rq's cpupri only if rt_rq is the top queue.
 	 */
-	if (&rq->rt != rt_rq)
+	if (IS_ENABLED(CONFIG_RT_GROUP_SCHED) && &rq->rt != rt_rq)
 		return;
-#endif
+
 	if (rq->online && rt_rq->highest_prio.curr != prev_prio)
 		cpupri_set(&rq->rd->cpupri, rq->cpu, rt_rq->highest_prio.curr);
 }
@@ -1156,8 +1170,7 @@ inc_rt_group(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
 	if (rt_se_boosted(rt_se))
 		rt_rq->rt_nr_boosted++;
 
-	if (rt_rq->tg)
-		start_rt_bandwidth(&rt_rq->tg->rt_bandwidth);
+	start_rt_bandwidth(&rt_rq->tg->rt_bandwidth);
 }
 
 static void
@@ -1257,11 +1270,9 @@ static void __delist_rt_entity(struct sched_rt_entity *rt_se, struct rt_prio_arr
 static inline struct sched_statistics *
 __schedstats_from_rt_se(struct sched_rt_entity *rt_se)
 {
-#ifdef CONFIG_RT_GROUP_SCHED
 	/* schedstats is not supported for rt group. */
 	if (!rt_entity_is_task(rt_se))
 		return NULL;
-#endif
 
 	return &rt_task_of(rt_se)->stats;
 }
@@ -1883,6 +1894,27 @@ static int find_lowest_rq(struct task_struct *task)
 	return -1;
 }
 
+static struct task_struct *pick_next_pushable_task(struct rq *rq)
+{
+	struct task_struct *p;
+
+	if (!has_pushable_tasks(rq))
+		return NULL;
+
+	p = plist_first_entry(&rq->rt.pushable_tasks,
+			      struct task_struct, pushable_tasks);
+
+	BUG_ON(rq->cpu != task_cpu(p));
+	BUG_ON(task_current(rq, p));
+	BUG_ON(task_current_donor(rq, p));
+	BUG_ON(p->nr_cpus_allowed <= 1);
+
+	BUG_ON(!task_on_rq_queued(p));
+	BUG_ON(!rt_task(p));
+
+	return p;
+}
+
 /* Will lock the rq it finds */
 static struct rq *find_lock_lowest_rq(struct task_struct *task, struct rq *rq)
 {
@@ -1913,18 +1945,16 @@ static struct rq *find_lock_lowest_rq(struct task_struct *task, struct rq *rq)
 			/*
 			 * We had to unlock the run queue. In
 			 * the mean time, task could have
-			 * migrated already or had its affinity changed.
-			 * Also make sure that it wasn't scheduled on its rq.
+			 * migrated already or had its affinity changed,
+			 * therefore check if the task is still at the
+			 * head of the pushable tasks list.
 			 * It is possible the task was scheduled, set
 			 * "migrate_disabled" and then got preempted, so we must
 			 * check the task migration disable flag here too.
 			 */
-			if (unlikely(task_rq(task) != rq ||
+			if (unlikely(is_migration_disabled(task) ||
 				     !cpumask_test_cpu(lowest_rq->cpu, &task->cpus_mask) ||
-				     task_on_cpu(rq, task) ||
-				     !rt_task(task) ||
-				     is_migration_disabled(task) ||
-				     !task_on_rq_queued(task))) {
+				     task != pick_next_pushable_task(rq))) {
 
 				double_unlock_balance(rq, lowest_rq);
 				lowest_rq = NULL;
@@ -1944,27 +1974,6 @@ static struct rq *find_lock_lowest_rq(struct task_struct *task, struct rq *rq)
 	return lowest_rq;
 }
 
-static struct task_struct *pick_next_pushable_task(struct rq *rq)
-{
-	struct task_struct *p;
-
-	if (!has_pushable_tasks(rq))
-		return NULL;
-
-	p = plist_first_entry(&rq->rt.pushable_tasks,
-			      struct task_struct, pushable_tasks);
-
-	BUG_ON(rq->cpu != task_cpu(p));
-	BUG_ON(task_current(rq, p));
-	BUG_ON(task_current_donor(rq, p));
-	BUG_ON(p->nr_cpus_allowed <= 1);
-
-	BUG_ON(!task_on_rq_queued(p));
-	BUG_ON(!rt_task(p));
-
-	return p;
-}
-
 /*
  * If the current CPU has more than one RT task, see if the non
  * running task can migrate over to a CPU that is running a task
@@ -2602,8 +2611,9 @@ static int task_is_throttled_rt(struct task_struct *p, int cpu)
 {
 	struct rt_rq *rt_rq;
 
-#ifdef CONFIG_RT_GROUP_SCHED
+#ifdef CONFIG_RT_GROUP_SCHED // XXX maybe add task_rt_rq(), see also sched_rt_period_rt_rq
 	rt_rq = task_group(p)->rt_rq[cpu];
+	WARN_ON(!rt_group_sched_enabled() && rt_rq->tg != &root_task_group);
 #else
 	rt_rq = &cpu_rq(cpu)->rt;
 #endif
@@ -2713,6 +2723,9 @@ static int tg_rt_schedulable(struct task_group *tg, void *data)
 	    tg->rt_bandwidth.rt_runtime && tg_has_rt_tasks(tg))
 		return -EBUSY;
 
+	if (WARN_ON(!rt_group_sched_enabled() && tg != &root_task_group))
+		return -EBUSY;
+
 	total = to_ratio(period, runtime);
 
 	/*
@@ -2868,7 +2881,7 @@ static int sched_rt_global_constraints(void)
 int sched_rt_can_attach(struct task_group *tg, struct task_struct *tsk)
 {
 	/* Don't accept real-time tasks when there is no way for them to run */
-	if (rt_task(tsk) && tg->rt_bandwidth.rt_runtime == 0)
+	if (rt_group_sched_enabled() && rt_task(tsk) && tg->rt_bandwidth.rt_runtime == 0)
 		return 0;
 
 	return 1;
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 47972f34ea70..475bb5998295 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -813,15 +813,17 @@ struct rt_rq {
 
 #ifdef CONFIG_RT_GROUP_SCHED
 	int			rt_throttled;
-	u64			rt_time;
-	u64			rt_runtime;
+	u64			rt_time; /* consumed RT time, goes up in update_curr_rt */
+	u64			rt_runtime; /* allotted RT time, "slice" from rt_bandwidth, RT sharing/balancing */
 	/* Nests inside the rq lock: */
 	raw_spinlock_t		rt_runtime_lock;
 
 	unsigned int		rt_nr_boosted;
 
-	struct rq		*rq;
-	struct task_group	*tg;
+	struct rq		*rq; /* this is always top-level rq, cache? */
+#endif
+#ifdef CONFIG_CGROUP_SCHED
+	struct task_group	*tg; /* this tg has "this" rt_rq on given CPU for runnable entities */
 #endif
 };
 
@@ -1498,6 +1500,23 @@ static inline bool sched_group_cookie_match(struct rq *rq,
 }
 
 #endif /* !CONFIG_SCHED_CORE */
+#ifdef CONFIG_RT_GROUP_SCHED
+# ifdef CONFIG_RT_GROUP_SCHED_DEFAULT_DISABLED
+DECLARE_STATIC_KEY_FALSE(rt_group_sched);
+static inline bool rt_group_sched_enabled(void)
+{
+	return static_branch_unlikely(&rt_group_sched);
+}
+# else
+DECLARE_STATIC_KEY_TRUE(rt_group_sched);
+static inline bool rt_group_sched_enabled(void)
+{
+	return static_branch_likely(&rt_group_sched);
+}
+# endif /* CONFIG_RT_GROUP_SCHED_DEFAULT_DISABLED */
+#else
+# define rt_group_sched_enabled()	false
+#endif /* CONFIG_RT_GROUP_SCHED */
 
 static inline void lockdep_assert_rq_held(struct rq *rq)
 {
@@ -1717,10 +1736,10 @@ extern struct balance_callback balance_push_callback;
 #ifdef CONFIG_SCHED_CLASS_EXT
 extern const struct sched_class ext_sched_class;
 
-DECLARE_STATIC_KEY_FALSE(__scx_ops_enabled);	/* SCX BPF scheduler loaded */
+DECLARE_STATIC_KEY_FALSE(__scx_enabled);	/* SCX BPF scheduler loaded */
 DECLARE_STATIC_KEY_FALSE(__scx_switched_all);	/* all fair class tasks on SCX */
 
-#define scx_enabled()		static_branch_unlikely(&__scx_ops_enabled)
+#define scx_enabled()		static_branch_unlikely(&__scx_enabled)
 #define scx_switched_all()	static_branch_unlikely(&__scx_switched_all)
 
 static inline void scx_rq_clock_update(struct rq *rq, u64 clock)
@@ -2146,6 +2165,13 @@ static inline void set_task_rq(struct task_struct *p, unsigned int cpu)
 #endif
 
 #ifdef CONFIG_RT_GROUP_SCHED
+	/*
+	 * p->rt.rt_rq is NULL initially and it is easier to assign
+	 * root_task_group's rt_rq than switching in rt_rq_of_se()
+	 * Clobbers tg(!)
+	 */
+	if (!rt_group_sched_enabled())
+		tg = &root_task_group;
 	p->rt.rt_rq  = tg->rt_rq[cpu];
 	p->rt.parent = tg->rt_se[cpu];
 #endif
@@ -3509,8 +3535,6 @@ static inline bool sched_energy_enabled(void)
 	return static_branch_unlikely(&sched_energy_present);
 }
 
-extern struct cpufreq_governor schedutil_gov;
-
 #else /* ! (CONFIG_ENERGY_MODEL && CONFIG_CPU_FREQ_GOV_SCHEDUTIL) */
 
 #define perf_domain_span(pd) NULL
diff --git a/kernel/sched/syscalls.c b/kernel/sched/syscalls.c
index c326de1344fb..547c1f05b667 100644
--- a/kernel/sched/syscalls.c
+++ b/kernel/sched/syscalls.c
@@ -634,13 +634,14 @@ change:
 		 * Do not allow real-time tasks into groups that have no runtime
 		 * assigned.
 		 */
-		if (rt_bandwidth_enabled() && rt_policy(policy) &&
+		if (rt_group_sched_enabled() &&
+				rt_bandwidth_enabled() && rt_policy(policy) &&
 				task_group(p)->rt_bandwidth.rt_runtime == 0 &&
 				!task_group_is_autogroup(task_group(p))) {
 			retval = -EPERM;
 			goto unlock;
 		}
-#endif
+#endif /* CONFIG_RT_GROUP_SCHED */
 #ifdef CONFIG_SMP
 		if (dl_bandwidth_enabled() && dl_policy(policy) &&
 				!(attr->sched_flags & SCHED_FLAG_SUGOV)) {
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index f1ebc60d967f..b958fe48e020 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -212,8 +212,6 @@ static bool sched_energy_update;
 static bool sched_is_eas_possible(const struct cpumask *cpu_mask)
 {
 	bool any_asym_capacity = false;
-	struct cpufreq_policy *policy;
-	struct cpufreq_governor *gov;
 	int i;
 
 	/* EAS is enabled for asymmetric CPU capacity topologies. */
@@ -248,25 +246,12 @@ static bool sched_is_eas_possible(const struct cpumask *cpu_mask)
 		return false;
 	}
 
-	/* Do not attempt EAS if schedutil is not being used. */
-	for_each_cpu(i, cpu_mask) {
-		policy = cpufreq_cpu_get(i);
-		if (!policy) {
-			if (sched_debug()) {
-				pr_info("rd %*pbl: Checking EAS, cpufreq policy not set for CPU: %d",
-					cpumask_pr_args(cpu_mask), i);
-			}
-			return false;
-		}
-		gov = policy->governor;
-		cpufreq_cpu_put(policy);
-		if (gov != &schedutil_gov) {
-			if (sched_debug()) {
-				pr_info("rd %*pbl: Checking EAS, schedutil is mandatory\n",
-					cpumask_pr_args(cpu_mask));
-			}
-			return false;
+	if (!cpufreq_ready_for_eas(cpu_mask)) {
+		if (sched_debug()) {
+			pr_info("rd %*pbl: Checking EAS: cpufreq is not ready\n",
+				cpumask_pr_args(cpu_mask));
 		}
+		return false;
 	}
 
 	return true;
@@ -1333,6 +1318,64 @@ next:
 	update_group_capacity(sd, cpu);
 }
 
+#ifdef CONFIG_SMP
+
+/* Update the "asym_prefer_cpu" when arch_asym_cpu_priority() changes. */
+void sched_update_asym_prefer_cpu(int cpu, int old_prio, int new_prio)
+{
+	int asym_prefer_cpu = cpu;
+	struct sched_domain *sd;
+
+	guard(rcu)();
+
+	for_each_domain(cpu, sd) {
+		struct sched_group *sg;
+		int group_cpu;
+
+		if (!(sd->flags & SD_ASYM_PACKING))
+			continue;
+
+		/*
+		 * Groups of overlapping domain are replicated per NUMA
+		 * node and will require updating "asym_prefer_cpu" on
+		 * each local copy.
+		 *
+		 * If you are hitting this warning, consider moving
+		 * "sg->asym_prefer_cpu" to "sg->sgc->asym_prefer_cpu"
+		 * which is shared by all the overlapping groups.
+		 */
+		WARN_ON_ONCE(sd->flags & SD_OVERLAP);
+
+		sg = sd->groups;
+		if (cpu != sg->asym_prefer_cpu) {
+			/*
+			 * Since the parent is a superset of the current group,
+			 * if the cpu is not the "asym_prefer_cpu" at the
+			 * current level, it cannot be the preferred CPU at a
+			 * higher levels either.
+			 */
+			if (!sched_asym_prefer(cpu, sg->asym_prefer_cpu))
+				return;
+
+			WRITE_ONCE(sg->asym_prefer_cpu, cpu);
+			continue;
+		}
+
+		/* Ranking has improved; CPU is still the preferred one. */
+		if (new_prio >= old_prio)
+			continue;
+
+		for_each_cpu(group_cpu, sched_group_span(sg)) {
+			if (sched_asym_prefer(group_cpu, asym_prefer_cpu))
+				asym_prefer_cpu = group_cpu;
+		}
+
+		WRITE_ONCE(sg->asym_prefer_cpu, asym_prefer_cpu);
+	}
+}
+
+#endif /* CONFIG_SMP */
+
 /*
  * Set of available CPUs grouped by their corresponding capacities
  * Each list entry contains a CPU mask reflecting CPUs that share the same
@@ -2098,7 +2141,7 @@ int sched_numa_find_closest(const struct cpumask *cpus, int cpu)
 	for (i = 0; i < sched_domains_numa_levels; i++) {
 		if (!masks[i][j])
 			break;
-		cpu = cpumask_any_and(cpus, masks[i][j]);
+		cpu = cpumask_any_and_distribute(cpus, masks[i][j]);
 		if (cpu < nr_cpu_ids) {
 			found = cpu;
 			break;
@@ -2347,35 +2390,54 @@ static struct sched_domain *build_sched_domain(struct sched_domain_topology_leve
 
 /*
  * Ensure topology masks are sane, i.e. there are no conflicts (overlaps) for
- * any two given CPUs at this (non-NUMA) topology level.
+ * any two given CPUs on non-NUMA topology levels.
  */
-static bool topology_span_sane(struct sched_domain_topology_level *tl,
-			      const struct cpumask *cpu_map, int cpu)
+static bool topology_span_sane(const struct cpumask *cpu_map)
 {
-	int i = cpu + 1;
+	struct sched_domain_topology_level *tl;
+	struct cpumask *covered, *id_seen;
+	int cpu;
 
-	/* NUMA levels are allowed to overlap */
-	if (tl->flags & SDTL_OVERLAP)
-		return true;
+	lockdep_assert_held(&sched_domains_mutex);
+	covered = sched_domains_tmpmask;
+	id_seen = sched_domains_tmpmask2;
+
+	for_each_sd_topology(tl) {
+
+		/* NUMA levels are allowed to overlap */
+		if (tl->flags & SDTL_OVERLAP)
+			continue;
+
+		cpumask_clear(covered);
+		cpumask_clear(id_seen);
 
-	/*
-	 * Non-NUMA levels cannot partially overlap - they must be either
-	 * completely equal or completely disjoint. Otherwise we can end up
-	 * breaking the sched_group lists - i.e. a later get_group() pass
-	 * breaks the linking done for an earlier span.
-	 */
-	for_each_cpu_from(i, cpu_map) {
 		/*
-		 * We should 'and' all those masks with 'cpu_map' to exactly
-		 * match the topology we're about to build, but that can only
-		 * remove CPUs, which only lessens our ability to detect
-		 * overlaps
+		 * Non-NUMA levels cannot partially overlap - they must be either
+		 * completely equal or completely disjoint. Otherwise we can end up
+		 * breaking the sched_group lists - i.e. a later get_group() pass
+		 * breaks the linking done for an earlier span.
 		 */
-		if (!cpumask_equal(tl->mask(cpu), tl->mask(i)) &&
-		    cpumask_intersects(tl->mask(cpu), tl->mask(i)))
-			return false;
-	}
+		for_each_cpu(cpu, cpu_map) {
+			const struct cpumask *tl_cpu_mask = tl->mask(cpu);
+			int id;
+
+			/* lowest bit set in this mask is used as a unique id */
+			id = cpumask_first(tl_cpu_mask);
+
+			if (cpumask_test_cpu(id, id_seen)) {
+				/* First CPU has already been seen, ensure identical spans */
+				if (!cpumask_equal(tl->mask(id), tl_cpu_mask))
+					return false;
+			} else {
+				/* First CPU hasn't been seen before, ensure it's a completely new span */
+				if (cpumask_intersects(tl_cpu_mask, covered))
+					return false;
 
+				cpumask_or(covered, covered, tl_cpu_mask);
+				cpumask_set_cpu(id, id_seen);
+			}
+		}
+	}
 	return true;
 }
 
@@ -2408,9 +2470,6 @@ build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *att
 		sd = NULL;
 		for_each_sd_topology(tl) {
 
-			if (WARN_ON(!topology_span_sane(tl, cpu_map, i)))
-				goto error;
-
 			sd = build_sched_domain(tl, cpu_map, attr, sd, i);
 
 			has_asym |= sd->flags & SD_ASYM_CPUCAPACITY;
@@ -2424,6 +2483,9 @@ build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *att
 		}
 	}
 
+	if (WARN_ON(!topology_span_sane(cpu_map)))
+		goto error;
+
 	/* Build the groups for the domains */
 	for_each_cpu(i, cpu_map) {
 		for (sd = *per_cpu_ptr(d.sd, i); sd; sd = sd->parent) {
diff --git a/kernel/signal.c b/kernel/signal.c
index f8859faa26c5..148082db9a55 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -4981,9 +4981,20 @@ static const struct ctl_table signal_debug_table[] = {
 #endif
 };
 
+static const struct ctl_table signal_table[] = {
+	{
+		.procname	= "print-fatal-signals",
+		.data		= &print_fatal_signals,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+};
+
 static int __init init_signal_sysctls(void)
 {
 	register_sysctl_init("debug", signal_debug_table);
+	register_sysctl_init("kernel", signal_table);
 	return 0;
 }
 early_initcall(init_signal_sysctls);
diff --git a/kernel/sys.c b/kernel/sys.c
index c434968e9f5d..adc0de0aa364 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -52,6 +52,7 @@
 #include <linux/user_namespace.h>
 #include <linux/time_namespace.h>
 #include <linux/binfmts.h>
+#include <linux/futex.h>
 
 #include <linux/sched.h>
 #include <linux/sched/autogroup.h>
@@ -2820,6 +2821,9 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
 			return -EINVAL;
 		error = posixtimer_create_prctl(arg2);
 		break;
+	case PR_FUTEX_HASH:
+		error = futex_hash_prctl(arg2, arg3, arg4);
+		break;
 	default:
 		trace_task_prctl_unknown(option, arg2, arg3, arg4, arg5);
 		error = -EINVAL;
diff --git a/kernel/sysctl-test.c b/kernel/sysctl-test.c
index eb2842bd0557..92f94ea28957 100644
--- a/kernel/sysctl-test.c
+++ b/kernel/sysctl-test.c
@@ -367,54 +367,6 @@ static void sysctl_test_api_dointvec_write_single_greater_int_max(
 	KUNIT_EXPECT_EQ(test, 0, *((int *)table.data));
 }
 
-/*
- * Test that registering an invalid extra value is not allowed.
- */
-static void sysctl_test_register_sysctl_sz_invalid_extra_value(
-		struct kunit *test)
-{
-	unsigned char data = 0;
-	const struct ctl_table table_foo[] = {
-		{
-			.procname	= "foo",
-			.data		= &data,
-			.maxlen		= sizeof(u8),
-			.mode		= 0644,
-			.proc_handler	= proc_dou8vec_minmax,
-			.extra1		= SYSCTL_FOUR,
-			.extra2		= SYSCTL_ONE_THOUSAND,
-		},
-	};
-
-	const struct ctl_table table_bar[] = {
-		{
-			.procname	= "bar",
-			.data		= &data,
-			.maxlen		= sizeof(u8),
-			.mode		= 0644,
-			.proc_handler	= proc_dou8vec_minmax,
-			.extra1		= SYSCTL_NEG_ONE,
-			.extra2		= SYSCTL_ONE_HUNDRED,
-		},
-	};
-
-	const struct ctl_table table_qux[] = {
-		{
-			.procname	= "qux",
-			.data		= &data,
-			.maxlen		= sizeof(u8),
-			.mode		= 0644,
-			.proc_handler	= proc_dou8vec_minmax,
-			.extra1		= SYSCTL_ZERO,
-			.extra2		= SYSCTL_TWO_HUNDRED,
-		},
-	};
-
-	KUNIT_EXPECT_NULL(test, register_sysctl("foo", table_foo));
-	KUNIT_EXPECT_NULL(test, register_sysctl("foo", table_bar));
-	KUNIT_EXPECT_NOT_NULL(test, register_sysctl("foo", table_qux));
-}
-
 static struct kunit_case sysctl_test_cases[] = {
 	KUNIT_CASE(sysctl_test_api_dointvec_null_tbl_data),
 	KUNIT_CASE(sysctl_test_api_dointvec_table_maxlen_unset),
@@ -426,7 +378,6 @@ static struct kunit_case sysctl_test_cases[] = {
 	KUNIT_CASE(sysctl_test_dointvec_write_happy_single_negative),
 	KUNIT_CASE(sysctl_test_api_dointvec_write_single_less_int_min),
 	KUNIT_CASE(sysctl_test_api_dointvec_write_single_greater_int_max),
-	KUNIT_CASE(sysctl_test_register_sysctl_sz_invalid_extra_value),
 	{}
 };
 
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 3b7a7308e35b..9b4f0cff76ea 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -22,8 +22,6 @@
 #include <linux/module.h>
 #include <linux/sysctl.h>
 #include <linux/bitmap.h>
-#include <linux/signal.h>
-#include <linux/panic.h>
 #include <linux/printk.h>
 #include <linux/proc_fs.h>
 #include <linux/security.h>
@@ -46,7 +44,6 @@
 #include <linux/nfs_fs.h>
 #include <linux/acpi.h>
 #include <linux/reboot.h>
-#include <linux/ftrace.h>
 #include <linux/kmod.h>
 #include <linux/capability.h>
 #include <linux/binfmts.h>
@@ -61,12 +58,8 @@
 
 #ifdef CONFIG_X86
 #include <asm/nmi.h>
-#include <asm/stacktrace.h>
 #include <asm/io.h>
 #endif
-#ifdef CONFIG_SPARC
-#include <asm/setup.h>
-#endif
 #ifdef CONFIG_RT_MUTEXES
 #include <linux/rtmutex.h>
 #endif
@@ -1588,13 +1581,6 @@ int proc_do_static_key(const struct ctl_table *table, int write,
 }
 
 static const struct ctl_table kern_table[] = {
-	{
-		.procname	= "panic",
-		.data		= &panic_timeout,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
-	},
 #ifdef CONFIG_PROC_SYSCTL
 	{
 		.procname	= "tainted",
@@ -1612,45 +1598,6 @@ static const struct ctl_table kern_table[] = {
 		.extra2		= SYSCTL_ONE,
 	},
 #endif
-	{
-		.procname	= "print-fatal-signals",
-		.data		= &print_fatal_signals,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
-	},
-#ifdef CONFIG_SPARC
-	{
-		.procname	= "reboot-cmd",
-		.data		= reboot_command,
-		.maxlen		= 256,
-		.mode		= 0644,
-		.proc_handler	= proc_dostring,
-	},
-	{
-		.procname	= "stop-a",
-		.data		= &stop_a_enabled,
-		.maxlen		= sizeof (int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
-	},
-	{
-		.procname	= "scons-poweroff",
-		.data		= &scons_pwroff,
-		.maxlen		= sizeof (int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
-	},
-#endif
-#ifdef CONFIG_SPARC64
-	{
-		.procname	= "tsb-ratio",
-		.data		= &sysctl_tsb_ratio,
-		.maxlen		= sizeof (int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
-	},
-#endif
 #ifdef CONFIG_PARISC
 	{
 		.procname	= "soft-power",
@@ -1669,38 +1616,6 @@ static const struct ctl_table kern_table[] = {
 		.proc_handler	= proc_dointvec,
 	},
 #endif
-#ifdef CONFIG_STACK_TRACER
-	{
-		.procname	= "stack_tracer_enabled",
-		.data		= &stack_tracer_enabled,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= stack_trace_sysctl,
-	},
-#endif
-#ifdef CONFIG_TRACING
-	{
-		.procname	= "ftrace_dump_on_oops",
-		.data		= &ftrace_dump_on_oops,
-		.maxlen		= MAX_TRACER_SIZE,
-		.mode		= 0644,
-		.proc_handler	= proc_dostring,
-	},
-	{
-		.procname	= "traceoff_on_warning",
-		.data		= &__disable_trace_on_warning,
-		.maxlen		= sizeof(__disable_trace_on_warning),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
-	},
-	{
-		.procname	= "tracepoint_printk",
-		.data		= &tracepoint_printk,
-		.maxlen		= sizeof(tracepoint_printk),
-		.mode		= 0644,
-		.proc_handler	= tracepoint_printk_sysctl,
-	},
-#endif
 #ifdef CONFIG_MODULES
 	{
 		.procname	= "modprobe",
@@ -1773,20 +1688,6 @@ static const struct ctl_table kern_table[] = {
 		.extra2		= SYSCTL_MAXOLDUID,
 	},
 	{
-		.procname	= "panic_on_oops",
-		.data		= &panic_on_oops,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
-	},
-	{
-		.procname	= "panic_print",
-		.data		= &panic_print,
-		.maxlen		= sizeof(unsigned long),
-		.mode		= 0644,
-		.proc_handler	= proc_doulongvec_minmax,
-	},
-	{
 		.procname	= "ngroups_max",
 		.data		= (void *)&ngroups_max,
 		.maxlen		= sizeof (int),
@@ -1837,15 +1738,6 @@ static const struct ctl_table kern_table[] = {
 		.proc_handler	= proc_dointvec,
 	},
 #endif
-	{
-		.procname	= "panic_on_warn",
-		.data		= &panic_on_warn,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= SYSCTL_ZERO,
-		.extra2		= SYSCTL_ONE,
-	},
 #ifdef CONFIG_TREE_RCU
 	{
 		.procname	= "panic_on_rcu_stall",
diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c
index 0ddccdff119a..577f0e6842d4 100644
--- a/kernel/time/alarmtimer.c
+++ b/kernel/time/alarmtimer.c
@@ -70,12 +70,10 @@ static DEFINE_SPINLOCK(rtcdev_lock);
  */
 struct rtc_device *alarmtimer_get_rtcdev(void)
 {
-	unsigned long flags;
 	struct rtc_device *ret;
 
-	spin_lock_irqsave(&rtcdev_lock, flags);
+	guard(spinlock_irqsave)(&rtcdev_lock);
 	ret = rtcdev;
-	spin_unlock_irqrestore(&rtcdev_lock, flags);
 
 	return ret;
 }
@@ -83,7 +81,6 @@ EXPORT_SYMBOL_GPL(alarmtimer_get_rtcdev);
 
 static int alarmtimer_rtc_add_device(struct device *dev)
 {
-	unsigned long flags;
 	struct rtc_device *rtc = to_rtc_device(dev);
 	struct platform_device *pdev;
 	int ret = 0;
@@ -101,25 +98,18 @@ static int alarmtimer_rtc_add_device(struct device *dev)
 	if (!IS_ERR(pdev))
 		device_init_wakeup(&pdev->dev, true);
 
-	spin_lock_irqsave(&rtcdev_lock, flags);
-	if (!IS_ERR(pdev) && !rtcdev) {
-		if (!try_module_get(rtc->owner)) {
+	scoped_guard(spinlock_irqsave, &rtcdev_lock) {
+		if (!IS_ERR(pdev) && !rtcdev && try_module_get(rtc->owner)) {
+			rtcdev = rtc;
+			/* hold a reference so it doesn't go away */
+			get_device(dev);
+			pdev = NULL;
+		} else {
 			ret = -1;
-			goto unlock;
 		}
-
-		rtcdev = rtc;
-		/* hold a reference so it doesn't go away */
-		get_device(dev);
-		pdev = NULL;
-	} else {
-		ret = -1;
 	}
-unlock:
-	spin_unlock_irqrestore(&rtcdev_lock, flags);
 
 	platform_device_unregister(pdev);
-
 	return ret;
 }
 
@@ -198,7 +188,7 @@ static enum hrtimer_restart alarmtimer_fired(struct hrtimer *timer)
 	struct alarm *alarm = container_of(timer, struct alarm, timer);
 	struct alarm_base *base = &alarm_bases[alarm->type];
 
-	scoped_guard (spinlock_irqsave, &base->lock)
+	scoped_guard(spinlock_irqsave, &base->lock)
 		alarmtimer_dequeue(base, alarm);
 
 	if (alarm->function)
@@ -228,17 +218,16 @@ EXPORT_SYMBOL_GPL(alarm_expires_remaining);
 static int alarmtimer_suspend(struct device *dev)
 {
 	ktime_t min, now, expires;
-	int i, ret, type;
 	struct rtc_device *rtc;
-	unsigned long flags;
 	struct rtc_time tm;
+	int i, ret, type;
 
-	spin_lock_irqsave(&freezer_delta_lock, flags);
-	min = freezer_delta;
-	expires = freezer_expires;
-	type = freezer_alarmtype;
-	freezer_delta = 0;
-	spin_unlock_irqrestore(&freezer_delta_lock, flags);
+	scoped_guard(spinlock_irqsave, &freezer_delta_lock) {
+		min = freezer_delta;
+		expires = freezer_expires;
+		type = freezer_alarmtype;
+		freezer_delta = 0;
+	}
 
 	rtc = alarmtimer_get_rtcdev();
 	/* If we have no rtcdev, just return */
@@ -251,9 +240,8 @@ static int alarmtimer_suspend(struct device *dev)
 		struct timerqueue_node *next;
 		ktime_t delta;
 
-		spin_lock_irqsave(&base->lock, flags);
-		next = timerqueue_getnext(&base->timerqueue);
-		spin_unlock_irqrestore(&base->lock, flags);
+		scoped_guard(spinlock_irqsave, &base->lock)
+			next = timerqueue_getnext(&base->timerqueue);
 		if (!next)
 			continue;
 		delta = ktime_sub(next->expires, base->get_ktime());
@@ -352,13 +340,12 @@ EXPORT_SYMBOL_GPL(alarm_init);
 void alarm_start(struct alarm *alarm, ktime_t start)
 {
 	struct alarm_base *base = &alarm_bases[alarm->type];
-	unsigned long flags;
 
-	spin_lock_irqsave(&base->lock, flags);
-	alarm->node.expires = start;
-	alarmtimer_enqueue(base, alarm);
-	hrtimer_start(&alarm->timer, alarm->node.expires, HRTIMER_MODE_ABS);
-	spin_unlock_irqrestore(&base->lock, flags);
+	scoped_guard(spinlock_irqsave, &base->lock) {
+		alarm->node.expires = start;
+		alarmtimer_enqueue(base, alarm);
+		hrtimer_start(&alarm->timer, alarm->node.expires, HRTIMER_MODE_ABS);
+	}
 
 	trace_alarmtimer_start(alarm, base->get_ktime());
 }
@@ -381,13 +368,11 @@ EXPORT_SYMBOL_GPL(alarm_start_relative);
 void alarm_restart(struct alarm *alarm)
 {
 	struct alarm_base *base = &alarm_bases[alarm->type];
-	unsigned long flags;
 
-	spin_lock_irqsave(&base->lock, flags);
+	guard(spinlock_irqsave)(&base->lock);
 	hrtimer_set_expires(&alarm->timer, alarm->node.expires);
 	hrtimer_restart(&alarm->timer);
 	alarmtimer_enqueue(base, alarm);
-	spin_unlock_irqrestore(&base->lock, flags);
 }
 EXPORT_SYMBOL_GPL(alarm_restart);
 
@@ -401,14 +386,13 @@ EXPORT_SYMBOL_GPL(alarm_restart);
 int alarm_try_to_cancel(struct alarm *alarm)
 {
 	struct alarm_base *base = &alarm_bases[alarm->type];
-	unsigned long flags;
 	int ret;
 
-	spin_lock_irqsave(&base->lock, flags);
-	ret = hrtimer_try_to_cancel(&alarm->timer);
-	if (ret >= 0)
-		alarmtimer_dequeue(base, alarm);
-	spin_unlock_irqrestore(&base->lock, flags);
+	scoped_guard(spinlock_irqsave, &base->lock) {
+		ret = hrtimer_try_to_cancel(&alarm->timer);
+		if (ret >= 0)
+			alarmtimer_dequeue(base, alarm);
+	}
 
 	trace_alarmtimer_cancel(alarm, base->get_ktime());
 	return ret;
@@ -479,7 +463,6 @@ EXPORT_SYMBOL_GPL(alarm_forward_now);
 static void alarmtimer_freezerset(ktime_t absexp, enum alarmtimer_type type)
 {
 	struct alarm_base *base;
-	unsigned long flags;
 	ktime_t delta;
 
 	switch(type) {
@@ -498,13 +481,12 @@ static void alarmtimer_freezerset(ktime_t absexp, enum alarmtimer_type type)
 
 	delta = ktime_sub(absexp, base->get_ktime());
 
-	spin_lock_irqsave(&freezer_delta_lock, flags);
+	guard(spinlock_irqsave)(&freezer_delta_lock);
 	if (!freezer_delta || (delta < freezer_delta)) {
 		freezer_delta = delta;
 		freezer_expires = absexp;
 		freezer_alarmtype = type;
 	}
-	spin_unlock_irqrestore(&freezer_delta_lock, flags);
 }
 
 /**
@@ -515,9 +497,9 @@ static enum alarmtimer_type clock2alarm(clockid_t clockid)
 {
 	if (clockid == CLOCK_REALTIME_ALARM)
 		return ALARM_REALTIME;
-	if (clockid == CLOCK_BOOTTIME_ALARM)
-		return ALARM_BOOTTIME;
-	return -1;
+
+	WARN_ON_ONCE(clockid != CLOCK_BOOTTIME_ALARM);
+	return ALARM_BOOTTIME;
 }
 
 /**
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index bb48498ebb5a..6a8bc7da9062 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -310,7 +310,7 @@ static void clocksource_verify_choose_cpus(void)
 {
 	int cpu, i, n = verify_n_cpus;
 
-	if (n < 0) {
+	if (n < 0 || n >= num_online_cpus()) {
 		/* Check all of the CPUs. */
 		cpumask_copy(&cpus_chosen, cpu_online_mask);
 		cpumask_clear_cpu(smp_processor_id(), &cpus_chosen);
diff --git a/kernel/time/jiffies.c b/kernel/time/jiffies.c
index bc4db9e5ab70..34eeacac2253 100644
--- a/kernel/time/jiffies.c
+++ b/kernel/time/jiffies.c
@@ -75,13 +75,11 @@ struct clocksource * __init __weak clocksource_default_clock(void)
 
 static struct clocksource refined_jiffies;
 
-int register_refined_jiffies(long cycles_per_second)
+void __init register_refined_jiffies(long cycles_per_second)
 {
 	u64 nsec_per_tick, shift_hz;
 	long cycles_per_tick;
 
-
-
 	refined_jiffies = clocksource_jiffies;
 	refined_jiffies.name = "refined-jiffies";
 	refined_jiffies.rating++;
@@ -100,5 +98,4 @@ int register_refined_jiffies(long cycles_per_second)
 	refined_jiffies.mult = ((u32)nsec_per_tick) << JIFFIES_SHIFT;
 
 	__clocksource_register(&refined_jiffies);
-	return 0;
 }
diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c
index 6222112533a7..2053b1a4c9e4 100644
--- a/kernel/time/posix-timers.c
+++ b/kernel/time/posix-timers.c
@@ -30,8 +30,6 @@
 #include "timekeeping.h"
 #include "posix-timers.h"
 
-static struct kmem_cache *posix_timers_cache;
-
 /*
  * Timers are managed in a hash table for lockless lookup. The hash key is
  * constructed from current::signal and the timer ID and the timer is
@@ -49,10 +47,12 @@ struct timer_hash_bucket {
 static struct {
 	struct timer_hash_bucket	*buckets;
 	unsigned long			mask;
-} __timer_data __ro_after_init __aligned(2*sizeof(long));
+	struct kmem_cache		*cache;
+} __timer_data __ro_after_init __aligned(4*sizeof(long));
 
-#define timer_buckets	(__timer_data.buckets)
-#define timer_hashmask	(__timer_data.mask)
+#define timer_buckets		(__timer_data.buckets)
+#define timer_hashmask		(__timer_data.mask)
+#define posix_timers_cache	(__timer_data.cache)
 
 static const struct k_clock * const posix_clocks[];
 static const struct k_clock *clockid_to_kclock(const clockid_t id);
@@ -283,14 +283,6 @@ static int posix_get_hrtimer_res(clockid_t which_clock, struct timespec64 *tp)
 	return 0;
 }
 
-static __init int init_posix_timers(void)
-{
-	posix_timers_cache = kmem_cache_create("posix_timers_cache", sizeof(struct k_itimer),
-					       __alignof__(struct k_itimer), SLAB_ACCOUNT, NULL);
-	return 0;
-}
-__initcall(init_posix_timers);
-
 /*
  * The siginfo si_overrun field and the return value of timer_getoverrun(2)
  * are of type int. Clamp the overrun value to INT_MAX
@@ -1556,6 +1548,11 @@ static int __init posixtimer_init(void)
 	unsigned long i, size;
 	unsigned int shift;
 
+	posix_timers_cache = kmem_cache_create("posix_timers_cache",
+					       sizeof(struct k_itimer),
+					       __alignof__(struct k_itimer),
+					       SLAB_ACCOUNT, NULL);
+
 	if (IS_ENABLED(CONFIG_BASE_SMALL))
 		size = 512;
 	else
diff --git a/kernel/time/sleep_timeout.c b/kernel/time/sleep_timeout.c
index c0e960a5de39..3c90574bd904 100644
--- a/kernel/time/sleep_timeout.c
+++ b/kernel/time/sleep_timeout.c
@@ -22,7 +22,7 @@ struct process_timer {
 
 static void process_timeout(struct timer_list *t)
 {
-	struct process_timer *timeout = from_timer(timeout, t, timer);
+	struct process_timer *timeout = timer_container_of(timeout, t, timer);
 
 	wake_up_process(timeout->task);
 }
@@ -100,7 +100,7 @@ signed long __sched schedule_timeout(signed long timeout)
 	timer_delete_sync(&timer.timer);
 
 	/* Remove the timer from the object tracker */
-	destroy_timer_on_stack(&timer.timer);
+	timer_destroy_on_stack(&timer.timer);
 
 	timeout = expire - jiffies;
 
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index 4d915c0a263c..553fa469d7cc 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -386,32 +386,6 @@ static unsigned long round_jiffies_common(unsigned long j, int cpu,
 }
 
 /**
- * __round_jiffies - function to round jiffies to a full second
- * @j: the time in (absolute) jiffies that should be rounded
- * @cpu: the processor number on which the timeout will happen
- *
- * __round_jiffies() rounds an absolute time in the future (in jiffies)
- * up or down to (approximately) full seconds. This is useful for timers
- * for which the exact time they fire does not matter too much, as long as
- * they fire approximately every X seconds.
- *
- * By rounding these timers to whole seconds, all such timers will fire
- * at the same time, rather than at various times spread out. The goal
- * of this is to have the CPU wake up less, which saves power.
- *
- * The exact rounding is skewed for each processor to avoid all
- * processors firing at the exact same time, which could lead
- * to lock contention or spurious cache line bouncing.
- *
- * The return value is the rounded version of the @j parameter.
- */
-unsigned long __round_jiffies(unsigned long j, int cpu)
-{
-	return round_jiffies_common(j, cpu, false);
-}
-EXPORT_SYMBOL_GPL(__round_jiffies);
-
-/**
  * __round_jiffies_relative - function to round jiffies to a full second
  * @j: the time in (relative) jiffies that should be rounded
  * @cpu: the processor number on which the timeout will happen
@@ -483,22 +457,6 @@ unsigned long round_jiffies_relative(unsigned long j)
 EXPORT_SYMBOL_GPL(round_jiffies_relative);
 
 /**
- * __round_jiffies_up - function to round jiffies up to a full second
- * @j: the time in (absolute) jiffies that should be rounded
- * @cpu: the processor number on which the timeout will happen
- *
- * This is the same as __round_jiffies() except that it will never
- * round down.  This is useful for timeouts for which the exact time
- * of firing does not matter too much, as long as they don't fire too
- * early.
- */
-unsigned long __round_jiffies_up(unsigned long j, int cpu)
-{
-	return round_jiffies_common(j, cpu, true);
-}
-EXPORT_SYMBOL_GPL(__round_jiffies_up);
-
-/**
  * __round_jiffies_up_relative - function to round jiffies up to a full second
  * @j: the time in (relative) jiffies that should be rounded
  * @cpu: the processor number on which the timeout will happen
@@ -850,7 +808,7 @@ static void do_init_timer(struct timer_list *timer,
 			  unsigned int flags,
 			  const char *name, struct lock_class_key *key);
 
-void init_timer_on_stack_key(struct timer_list *timer,
+void timer_init_key_on_stack(struct timer_list *timer,
 			     void (*func)(struct timer_list *),
 			     unsigned int flags,
 			     const char *name, struct lock_class_key *key)
@@ -858,13 +816,13 @@ void init_timer_on_stack_key(struct timer_list *timer,
 	debug_object_init_on_stack(timer, &timer_debug_descr);
 	do_init_timer(timer, func, flags, name, key);
 }
-EXPORT_SYMBOL_GPL(init_timer_on_stack_key);
+EXPORT_SYMBOL_GPL(timer_init_key_on_stack);
 
-void destroy_timer_on_stack(struct timer_list *timer)
+void timer_destroy_on_stack(struct timer_list *timer)
 {
 	debug_object_free(timer, &timer_debug_descr);
 }
-EXPORT_SYMBOL_GPL(destroy_timer_on_stack);
+EXPORT_SYMBOL_GPL(timer_destroy_on_stack);
 
 #else
 static inline void debug_timer_init(struct timer_list *timer) { }
@@ -904,7 +862,7 @@ static void do_init_timer(struct timer_list *timer,
 }
 
 /**
- * init_timer_key - initialize a timer
+ * timer_init_key - initialize a timer
  * @timer: the timer to be initialized
  * @func: timer callback function
  * @flags: timer flags
@@ -912,17 +870,17 @@ static void do_init_timer(struct timer_list *timer,
  * @key: lockdep class key of the fake lock used for tracking timer
  *       sync lock dependencies
  *
- * init_timer_key() must be done to a timer prior to calling *any* of the
+ * timer_init_key() must be done to a timer prior to calling *any* of the
  * other timer functions.
  */
-void init_timer_key(struct timer_list *timer,
+void timer_init_key(struct timer_list *timer,
 		    void (*func)(struct timer_list *), unsigned int flags,
 		    const char *name, struct lock_class_key *key)
 {
 	debug_init(timer);
 	do_init_timer(timer, func, flags, name, key);
 }
-EXPORT_SYMBOL(init_timer_key);
+EXPORT_SYMBOL(timer_init_key);
 
 static inline void detach_timer(struct timer_list *timer, bool clear_pending)
 {
@@ -1511,7 +1469,7 @@ static int __try_to_del_timer_sync(struct timer_list *timer, bool shutdown)
 }
 
 /**
- * try_to_del_timer_sync - Try to deactivate a timer
+ * timer_delete_sync_try - Try to deactivate a timer
  * @timer:	Timer to deactivate
  *
  * This function tries to deactivate a timer. On success the timer is not
@@ -1526,11 +1484,11 @@ static int __try_to_del_timer_sync(struct timer_list *timer, bool shutdown)
  * * %1  - The timer was pending and deactivated
  * * %-1 - The timer callback function is running on a different CPU
  */
-int try_to_del_timer_sync(struct timer_list *timer)
+int timer_delete_sync_try(struct timer_list *timer)
 {
 	return __try_to_del_timer_sync(timer, false);
 }
-EXPORT_SYMBOL(try_to_del_timer_sync);
+EXPORT_SYMBOL(timer_delete_sync_try);
 
 #ifdef CONFIG_PREEMPT_RT
 static __init void timer_base_init_expiry_lock(struct timer_base *base)
@@ -1900,7 +1858,7 @@ static void timer_recalc_next_expiry(struct timer_base *base)
 	unsigned long clk, next, adj;
 	unsigned lvl, offset = 0;
 
-	next = base->clk + NEXT_TIMER_MAX_DELTA;
+	next = base->clk + TIMER_NEXT_MAX_DELTA;
 	clk = base->clk;
 	for (lvl = 0; lvl < LVL_DEPTH; lvl++, offset += LVL_SIZE) {
 		int pos = next_pending_bucket(base, offset, clk & LVL_MASK);
@@ -1963,7 +1921,7 @@ static void timer_recalc_next_expiry(struct timer_base *base)
 
 	WRITE_ONCE(base->next_expiry, next);
 	base->next_expiry_recalc = false;
-	base->timers_pending = !(next == base->clk + NEXT_TIMER_MAX_DELTA);
+	base->timers_pending = !(next == base->clk + TIMER_NEXT_MAX_DELTA);
 }
 
 #ifdef CONFIG_NO_HZ_COMMON
@@ -2015,7 +1973,7 @@ static unsigned long next_timer_interrupt(struct timer_base *base,
 	 * easy comparable to find out which base holds the first pending timer.
 	 */
 	if (!base->timers_pending)
-		WRITE_ONCE(base->next_expiry, basej + NEXT_TIMER_MAX_DELTA);
+		WRITE_ONCE(base->next_expiry, basej + TIMER_NEXT_MAX_DELTA);
 
 	return base->next_expiry;
 }
@@ -2399,7 +2357,7 @@ static inline void __run_timers(struct timer_base *base)
 		 * timer at this clk are that all matching timers have been
 		 * dequeued or no timer has been queued since
 		 * base::next_expiry was set to base::clk +
-		 * NEXT_TIMER_MAX_DELTA.
+		 * TIMER_NEXT_MAX_DELTA.
 		 */
 		WARN_ON_ONCE(!levels && !base->next_expiry_recalc
 			     && base->timers_pending);
@@ -2544,7 +2502,7 @@ int timers_prepare_cpu(unsigned int cpu)
 	for (b = 0; b < NR_BASES; b++) {
 		base = per_cpu_ptr(&timer_bases[b], cpu);
 		base->clk = jiffies;
-		base->next_expiry = base->clk + NEXT_TIMER_MAX_DELTA;
+		base->next_expiry = base->clk + TIMER_NEXT_MAX_DELTA;
 		base->next_expiry_recalc = false;
 		base->timers_pending = false;
 		base->is_idle = false;
@@ -2599,7 +2557,7 @@ static void __init init_timer_cpu(int cpu)
 		base->cpu = cpu;
 		raw_spin_lock_init(&base->lock);
 		base->clk = jiffies;
-		base->next_expiry = base->clk + NEXT_TIMER_MAX_DELTA;
+		base->next_expiry = base->clk + TIMER_NEXT_MAX_DELTA;
 		timer_base_init_expiry_lock(base);
 	}
 }
@@ -2612,7 +2570,7 @@ static void __init init_timer_cpus(void)
 		init_timer_cpu(cpu);
 }
 
-void __init init_timers(void)
+void __init timers_init(void)
 {
 	init_timer_cpus();
 	posix_cputimers_init_work();
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index 3679a6d18934..3f6a7bdc6edf 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -893,11 +893,6 @@ static void blk_add_trace_bio(struct request_queue *q, struct bio *bio,
 	rcu_read_unlock();
 }
 
-static void blk_add_trace_bio_bounce(void *ignore, struct bio *bio)
-{
-	blk_add_trace_bio(bio->bi_bdev->bd_disk->queue, bio, BLK_TA_BOUNCE, 0);
-}
-
 static void blk_add_trace_bio_complete(void *ignore,
 				       struct request_queue *q, struct bio *bio)
 {
@@ -1089,8 +1084,6 @@ static void blk_register_tracepoints(void)
 	WARN_ON(ret);
 	ret = register_trace_block_rq_complete(blk_add_trace_rq_complete, NULL);
 	WARN_ON(ret);
-	ret = register_trace_block_bio_bounce(blk_add_trace_bio_bounce, NULL);
-	WARN_ON(ret);
 	ret = register_trace_block_bio_complete(blk_add_trace_bio_complete, NULL);
 	WARN_ON(ret);
 	ret = register_trace_block_bio_backmerge(blk_add_trace_bio_backmerge, NULL);
@@ -1125,7 +1118,6 @@ static void blk_unregister_tracepoints(void)
 	unregister_trace_block_bio_frontmerge(blk_add_trace_bio_frontmerge, NULL);
 	unregister_trace_block_bio_backmerge(blk_add_trace_bio_backmerge, NULL);
 	unregister_trace_block_bio_complete(blk_add_trace_bio_complete, NULL);
-	unregister_trace_block_bio_bounce(blk_add_trace_bio_bounce, NULL);
 	unregister_trace_block_rq_complete(blk_add_trace_rq_complete, NULL);
 	unregister_trace_block_rq_requeue(blk_add_trace_rq_requeue, NULL);
 	unregister_trace_block_rq_merge(blk_add_trace_rq_merge, NULL);
@@ -1462,7 +1454,6 @@ static const struct {
 	[__BLK_TA_UNPLUG_TIMER]	= {{ "UT", "unplug_timer" }, blk_log_unplug },
 	[__BLK_TA_INSERT]	= {{  "I", "insert" },	   blk_log_generic },
 	[__BLK_TA_SPLIT]	= {{  "X", "split" },	   blk_log_split },
-	[__BLK_TA_BOUNCE]	= {{  "B", "bounce" },	   blk_log_generic },
 	[__BLK_TA_REMAP]	= {{  "A", "remap" },	   blk_log_remap },
 };
 
@@ -1896,6 +1887,8 @@ void blk_fill_rwbs(char *rwbs, blk_opf_t opf)
 		rwbs[i++] = 'S';
 	if (opf & REQ_META)
 		rwbs[i++] = 'M';
+	if (opf & REQ_ATOMIC)
+		rwbs[i++] = 'U';
 
 	rwbs[i] = '\0';
 }
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 187dc37d61d4..132c8be6f635 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -572,7 +572,7 @@ BPF_CALL_2(bpf_perf_event_read, struct bpf_map *, map, u64, flags)
 	return value;
 }
 
-static const struct bpf_func_proto bpf_perf_event_read_proto = {
+const struct bpf_func_proto bpf_perf_event_read_proto = {
 	.func		= bpf_perf_event_read,
 	.gpl_only	= true,
 	.ret_type	= RET_INTEGER,
@@ -882,7 +882,7 @@ BPF_CALL_1(bpf_send_signal, u32, sig)
 	return bpf_send_signal_common(sig, PIDTYPE_TGID, NULL, 0);
 }
 
-static const struct bpf_func_proto bpf_send_signal_proto = {
+const struct bpf_func_proto bpf_send_signal_proto = {
 	.func		= bpf_send_signal,
 	.gpl_only	= false,
 	.ret_type	= RET_INTEGER,
@@ -894,7 +894,7 @@ BPF_CALL_1(bpf_send_signal_thread, u32, sig)
 	return bpf_send_signal_common(sig, PIDTYPE_PID, NULL, 0);
 }
 
-static const struct bpf_func_proto bpf_send_signal_thread_proto = {
+const struct bpf_func_proto bpf_send_signal_thread_proto = {
 	.func		= bpf_send_signal_thread,
 	.gpl_only	= false,
 	.ret_type	= RET_INTEGER,
@@ -1185,7 +1185,7 @@ BPF_CALL_3(bpf_get_branch_snapshot, void *, buf, u32, size, u64, flags)
 	return entry_cnt * br_entry_size;
 }
 
-static const struct bpf_func_proto bpf_get_branch_snapshot_proto = {
+const struct bpf_func_proto bpf_get_branch_snapshot_proto = {
 	.func		= bpf_get_branch_snapshot,
 	.gpl_only	= true,
 	.ret_type	= RET_INTEGER,
@@ -1430,56 +1430,8 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	const struct bpf_func_proto *func_proto;
 
 	switch (func_id) {
-	case BPF_FUNC_map_lookup_elem:
-		return &bpf_map_lookup_elem_proto;
-	case BPF_FUNC_map_update_elem:
-		return &bpf_map_update_elem_proto;
-	case BPF_FUNC_map_delete_elem:
-		return &bpf_map_delete_elem_proto;
-	case BPF_FUNC_map_push_elem:
-		return &bpf_map_push_elem_proto;
-	case BPF_FUNC_map_pop_elem:
-		return &bpf_map_pop_elem_proto;
-	case BPF_FUNC_map_peek_elem:
-		return &bpf_map_peek_elem_proto;
-	case BPF_FUNC_map_lookup_percpu_elem:
-		return &bpf_map_lookup_percpu_elem_proto;
-	case BPF_FUNC_ktime_get_ns:
-		return &bpf_ktime_get_ns_proto;
-	case BPF_FUNC_ktime_get_boot_ns:
-		return &bpf_ktime_get_boot_ns_proto;
-	case BPF_FUNC_tail_call:
-		return &bpf_tail_call_proto;
-	case BPF_FUNC_get_current_task:
-		return &bpf_get_current_task_proto;
-	case BPF_FUNC_get_current_task_btf:
-		return &bpf_get_current_task_btf_proto;
-	case BPF_FUNC_task_pt_regs:
-		return &bpf_task_pt_regs_proto;
-	case BPF_FUNC_get_current_uid_gid:
-		return &bpf_get_current_uid_gid_proto;
-	case BPF_FUNC_get_current_comm:
-		return &bpf_get_current_comm_proto;
-	case BPF_FUNC_trace_printk:
-		return bpf_get_trace_printk_proto();
 	case BPF_FUNC_get_smp_processor_id:
 		return &bpf_get_smp_processor_id_proto;
-	case BPF_FUNC_get_numa_node_id:
-		return &bpf_get_numa_node_id_proto;
-	case BPF_FUNC_perf_event_read:
-		return &bpf_perf_event_read_proto;
-	case BPF_FUNC_get_prandom_u32:
-		return &bpf_get_prandom_u32_proto;
-	case BPF_FUNC_probe_read_user:
-		return &bpf_probe_read_user_proto;
-	case BPF_FUNC_probe_read_kernel:
-		return security_locked_down(LOCKDOWN_BPF_READ_KERNEL) < 0 ?
-		       NULL : &bpf_probe_read_kernel_proto;
-	case BPF_FUNC_probe_read_user_str:
-		return &bpf_probe_read_user_str_proto;
-	case BPF_FUNC_probe_read_kernel_str:
-		return security_locked_down(LOCKDOWN_BPF_READ_KERNEL) < 0 ?
-		       NULL : &bpf_probe_read_kernel_str_proto;
 #ifdef CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE
 	case BPF_FUNC_probe_read:
 		return security_locked_down(LOCKDOWN_BPF_READ_KERNEL) < 0 ?
@@ -1488,65 +1440,8 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return security_locked_down(LOCKDOWN_BPF_READ_KERNEL) < 0 ?
 		       NULL : &bpf_probe_read_compat_str_proto;
 #endif
-#ifdef CONFIG_CGROUPS
-	case BPF_FUNC_cgrp_storage_get:
-		return &bpf_cgrp_storage_get_proto;
-	case BPF_FUNC_cgrp_storage_delete:
-		return &bpf_cgrp_storage_delete_proto;
-	case BPF_FUNC_current_task_under_cgroup:
-		return &bpf_current_task_under_cgroup_proto;
-#endif
-	case BPF_FUNC_send_signal:
-		return &bpf_send_signal_proto;
-	case BPF_FUNC_send_signal_thread:
-		return &bpf_send_signal_thread_proto;
-	case BPF_FUNC_perf_event_read_value:
-		return &bpf_perf_event_read_value_proto;
-	case BPF_FUNC_ringbuf_output:
-		return &bpf_ringbuf_output_proto;
-	case BPF_FUNC_ringbuf_reserve:
-		return &bpf_ringbuf_reserve_proto;
-	case BPF_FUNC_ringbuf_submit:
-		return &bpf_ringbuf_submit_proto;
-	case BPF_FUNC_ringbuf_discard:
-		return &bpf_ringbuf_discard_proto;
-	case BPF_FUNC_ringbuf_query:
-		return &bpf_ringbuf_query_proto;
-	case BPF_FUNC_jiffies64:
-		return &bpf_jiffies64_proto;
-	case BPF_FUNC_get_task_stack:
-		return prog->sleepable ? &bpf_get_task_stack_sleepable_proto
-				       : &bpf_get_task_stack_proto;
-	case BPF_FUNC_copy_from_user:
-		return &bpf_copy_from_user_proto;
-	case BPF_FUNC_copy_from_user_task:
-		return &bpf_copy_from_user_task_proto;
-	case BPF_FUNC_snprintf_btf:
-		return &bpf_snprintf_btf_proto;
-	case BPF_FUNC_per_cpu_ptr:
-		return &bpf_per_cpu_ptr_proto;
-	case BPF_FUNC_this_cpu_ptr:
-		return &bpf_this_cpu_ptr_proto;
-	case BPF_FUNC_task_storage_get:
-		if (bpf_prog_check_recur(prog))
-			return &bpf_task_storage_get_recur_proto;
-		return &bpf_task_storage_get_proto;
-	case BPF_FUNC_task_storage_delete:
-		if (bpf_prog_check_recur(prog))
-			return &bpf_task_storage_delete_recur_proto;
-		return &bpf_task_storage_delete_proto;
-	case BPF_FUNC_for_each_map_elem:
-		return &bpf_for_each_map_elem_proto;
-	case BPF_FUNC_snprintf:
-		return &bpf_snprintf_proto;
 	case BPF_FUNC_get_func_ip:
 		return &bpf_get_func_ip_proto_tracing;
-	case BPF_FUNC_get_branch_snapshot:
-		return &bpf_get_branch_snapshot_proto;
-	case BPF_FUNC_find_vma:
-		return &bpf_find_vma_proto;
-	case BPF_FUNC_trace_vprintk:
-		return bpf_get_trace_vprintk_proto();
 	default:
 		break;
 	}
@@ -1858,7 +1753,7 @@ static struct pt_regs *get_bpf_raw_tp_regs(void)
 	struct bpf_raw_tp_regs *tp_regs = this_cpu_ptr(&bpf_raw_tp_regs);
 	int nest_level = this_cpu_inc_return(bpf_raw_tp_nest_level);
 
-	if (WARN_ON_ONCE(nest_level > ARRAY_SIZE(tp_regs->regs))) {
+	if (nest_level > ARRAY_SIZE(tp_regs->regs)) {
 		this_cpu_dec(bpf_raw_tp_nest_level);
 		return ERR_PTR(-EBUSY);
 	}
@@ -2987,6 +2882,9 @@ int bpf_kprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr
 	if (sizeof(u64) != sizeof(void *))
 		return -EOPNOTSUPP;
 
+	if (attr->link_create.flags)
+		return -EINVAL;
+
 	if (!is_kprobe_multi(prog))
 		return -EINVAL;
 
@@ -3376,6 +3274,9 @@ int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr
 	if (sizeof(u64) != sizeof(void *))
 		return -EOPNOTSUPP;
 
+	if (attr->link_create.flags)
+		return -EINVAL;
+
 	if (!is_uprobe_multi(prog))
 		return -EINVAL;
 
@@ -3417,7 +3318,9 @@ int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr
 	}
 
 	if (pid) {
+		rcu_read_lock();
 		task = get_pid_task(find_vpid(pid), PIDTYPE_TGID);
+		rcu_read_unlock();
 		if (!task) {
 			err = -ESRCH;
 			goto error_path_put;
@@ -3565,6 +3468,146 @@ static int __init bpf_kprobe_multi_kfuncs_init(void)
 
 late_initcall(bpf_kprobe_multi_kfuncs_init);
 
+typedef int (*copy_fn_t)(void *dst, const void *src, u32 size, struct task_struct *tsk);
+
+/*
+ * The __always_inline is to make sure the compiler doesn't
+ * generate indirect calls into callbacks, which is expensive,
+ * on some kernel configurations. This allows compiler to put
+ * direct calls into all the specific callback implementations
+ * (copy_user_data_sleepable, copy_user_data_nofault, and so on)
+ */
+static __always_inline int __bpf_dynptr_copy_str(struct bpf_dynptr *dptr, u32 doff, u32 size,
+						 const void *unsafe_src,
+						 copy_fn_t str_copy_fn,
+						 struct task_struct *tsk)
+{
+	struct bpf_dynptr_kern *dst;
+	u32 chunk_sz, off;
+	void *dst_slice;
+	int cnt, err;
+	char buf[256];
+
+	dst_slice = bpf_dynptr_slice_rdwr(dptr, doff, NULL, size);
+	if (likely(dst_slice))
+		return str_copy_fn(dst_slice, unsafe_src, size, tsk);
+
+	dst = (struct bpf_dynptr_kern *)dptr;
+	if (bpf_dynptr_check_off_len(dst, doff, size))
+		return -E2BIG;
+
+	for (off = 0; off < size; off += chunk_sz - 1) {
+		chunk_sz = min_t(u32, sizeof(buf), size - off);
+		/* Expect str_copy_fn to return count of copied bytes, including
+		 * zero terminator. Next iteration increment off by chunk_sz - 1 to
+		 * overwrite NUL.
+		 */
+		cnt = str_copy_fn(buf, unsafe_src + off, chunk_sz, tsk);
+		if (cnt < 0)
+			return cnt;
+		err = __bpf_dynptr_write(dst, doff + off, buf, cnt, 0);
+		if (err)
+			return err;
+		if (cnt < chunk_sz || chunk_sz == 1) /* we are done */
+			return off + cnt;
+	}
+	return off;
+}
+
+static __always_inline int __bpf_dynptr_copy(const struct bpf_dynptr *dptr, u32 doff,
+					     u32 size, const void *unsafe_src,
+					     copy_fn_t copy_fn, struct task_struct *tsk)
+{
+	struct bpf_dynptr_kern *dst;
+	void *dst_slice;
+	char buf[256];
+	u32 off, chunk_sz;
+	int err;
+
+	dst_slice = bpf_dynptr_slice_rdwr(dptr, doff, NULL, size);
+	if (likely(dst_slice))
+		return copy_fn(dst_slice, unsafe_src, size, tsk);
+
+	dst = (struct bpf_dynptr_kern *)dptr;
+	if (bpf_dynptr_check_off_len(dst, doff, size))
+		return -E2BIG;
+
+	for (off = 0; off < size; off += chunk_sz) {
+		chunk_sz = min_t(u32, sizeof(buf), size - off);
+		err = copy_fn(buf, unsafe_src + off, chunk_sz, tsk);
+		if (err)
+			return err;
+		err = __bpf_dynptr_write(dst, doff + off, buf, chunk_sz, 0);
+		if (err)
+			return err;
+	}
+	return 0;
+}
+
+static __always_inline int copy_user_data_nofault(void *dst, const void *unsafe_src,
+						  u32 size, struct task_struct *tsk)
+{
+	return copy_from_user_nofault(dst, (const void __user *)unsafe_src, size);
+}
+
+static __always_inline int copy_user_data_sleepable(void *dst, const void *unsafe_src,
+						    u32 size, struct task_struct *tsk)
+{
+	int ret;
+
+	if (!tsk) { /* Read from the current task */
+		ret = copy_from_user(dst, (const void __user *)unsafe_src, size);
+		if (ret)
+			return -EFAULT;
+		return 0;
+	}
+
+	ret = access_process_vm(tsk, (unsigned long)unsafe_src, dst, size, 0);
+	if (ret != size)
+		return -EFAULT;
+	return 0;
+}
+
+static __always_inline int copy_kernel_data_nofault(void *dst, const void *unsafe_src,
+						    u32 size, struct task_struct *tsk)
+{
+	return copy_from_kernel_nofault(dst, unsafe_src, size);
+}
+
+static __always_inline int copy_user_str_nofault(void *dst, const void *unsafe_src,
+						 u32 size, struct task_struct *tsk)
+{
+	return strncpy_from_user_nofault(dst, (const void __user *)unsafe_src, size);
+}
+
+static __always_inline int copy_user_str_sleepable(void *dst, const void *unsafe_src,
+						   u32 size, struct task_struct *tsk)
+{
+	int ret;
+
+	if (unlikely(size == 0))
+		return 0;
+
+	if (tsk) {
+		ret = copy_remote_vm_str(tsk, (unsigned long)unsafe_src, dst, size, 0);
+	} else {
+		ret = strncpy_from_user(dst, (const void __user *)unsafe_src, size - 1);
+		/* strncpy_from_user does not guarantee NUL termination */
+		if (ret >= 0)
+			((char *)dst)[ret] = '\0';
+	}
+
+	if (ret < 0)
+		return ret;
+	return ret + 1;
+}
+
+static __always_inline int copy_kernel_str_nofault(void *dst, const void *unsafe_src,
+						   u32 size, struct task_struct *tsk)
+{
+	return strncpy_from_kernel_nofault(dst, unsafe_src, size);
+}
+
 __bpf_kfunc_start_defs();
 
 __bpf_kfunc int bpf_send_signal_task(struct task_struct *task, int sig, enum pid_type type,
@@ -3576,4 +3619,62 @@ __bpf_kfunc int bpf_send_signal_task(struct task_struct *task, int sig, enum pid
 	return bpf_send_signal_common(sig, type, task, value);
 }
 
+__bpf_kfunc int bpf_probe_read_user_dynptr(struct bpf_dynptr *dptr, u32 off,
+					   u32 size, const void __user *unsafe_ptr__ign)
+{
+	return __bpf_dynptr_copy(dptr, off, size, (const void *)unsafe_ptr__ign,
+				 copy_user_data_nofault, NULL);
+}
+
+__bpf_kfunc int bpf_probe_read_kernel_dynptr(struct bpf_dynptr *dptr, u32 off,
+					     u32 size, const void *unsafe_ptr__ign)
+{
+	return __bpf_dynptr_copy(dptr, off, size, unsafe_ptr__ign,
+				 copy_kernel_data_nofault, NULL);
+}
+
+__bpf_kfunc int bpf_probe_read_user_str_dynptr(struct bpf_dynptr *dptr, u32 off,
+					       u32 size, const void __user *unsafe_ptr__ign)
+{
+	return __bpf_dynptr_copy_str(dptr, off, size, (const void *)unsafe_ptr__ign,
+				     copy_user_str_nofault, NULL);
+}
+
+__bpf_kfunc int bpf_probe_read_kernel_str_dynptr(struct bpf_dynptr *dptr, u32 off,
+						 u32 size, const void *unsafe_ptr__ign)
+{
+	return __bpf_dynptr_copy_str(dptr, off, size, unsafe_ptr__ign,
+				     copy_kernel_str_nofault, NULL);
+}
+
+__bpf_kfunc int bpf_copy_from_user_dynptr(struct bpf_dynptr *dptr, u32 off,
+					  u32 size, const void __user *unsafe_ptr__ign)
+{
+	return __bpf_dynptr_copy(dptr, off, size, (const void *)unsafe_ptr__ign,
+				 copy_user_data_sleepable, NULL);
+}
+
+__bpf_kfunc int bpf_copy_from_user_str_dynptr(struct bpf_dynptr *dptr, u32 off,
+					      u32 size, const void __user *unsafe_ptr__ign)
+{
+	return __bpf_dynptr_copy_str(dptr, off, size, (const void *)unsafe_ptr__ign,
+				     copy_user_str_sleepable, NULL);
+}
+
+__bpf_kfunc int bpf_copy_from_user_task_dynptr(struct bpf_dynptr *dptr, u32 off,
+					       u32 size, const void __user *unsafe_ptr__ign,
+					       struct task_struct *tsk)
+{
+	return __bpf_dynptr_copy(dptr, off, size, (const void *)unsafe_ptr__ign,
+				 copy_user_data_sleepable, tsk);
+}
+
+__bpf_kfunc int bpf_copy_from_user_task_str_dynptr(struct bpf_dynptr *dptr, u32 off,
+						   u32 size, const void __user *unsafe_ptr__ign,
+						   struct task_struct *tsk)
+{
+	return __bpf_dynptr_copy_str(dptr, off, size, (const void *)unsafe_ptr__ign,
+				     copy_user_str_sleepable, tsk);
+}
+
 __bpf_kfunc_end_defs();
diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c
index 8d925cbdce3a..c5b207992fb4 100644
--- a/kernel/trace/fgraph.c
+++ b/kernel/trace/fgraph.c
@@ -1382,6 +1382,8 @@ int register_ftrace_graph(struct fgraph_ops *gops)
 	/* Always save the function, and reset at unregistering */
 	gops->saved_func = gops->entryfunc;
 
+	gops->ops.flags |= FTRACE_OPS_FL_GRAPH;
+
 	ret = ftrace_startup_subops(&graph_ops, &gops->ops, command);
 	if (!ret)
 		fgraph_array[i] = gops;
diff --git a/kernel/trace/fprobe.c b/kernel/trace/fprobe.c
index 95c6e3473a76..ba7ff14f5339 100644
--- a/kernel/trace/fprobe.c
+++ b/kernel/trace/fprobe.c
@@ -454,7 +454,8 @@ static void fprobe_remove_node_in_module(struct module *mod, struct hlist_head *
 	struct fprobe_hlist_node *node;
 	int ret = 0;
 
-	hlist_for_each_entry_rcu(node, head, hlist) {
+	hlist_for_each_entry_rcu(node, head, hlist,
+				 lockdep_is_held(&fprobe_mutex)) {
 		if (!within_module(node->addr, mod))
 			continue;
 		if (delete_fprobe_node(node))
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 6981830c3128..4203fad56b6c 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -188,7 +188,7 @@ static void ftrace_pid_func(unsigned long ip, unsigned long parent_ip,
 	op->saved_func(ip, parent_ip, op, fregs);
 }
 
-static void ftrace_sync_ipi(void *data)
+void ftrace_sync_ipi(void *data)
 {
 	/* Probably not needed, but do it anyway */
 	smp_rmb();
@@ -4373,6 +4373,42 @@ static inline int print_rec(struct seq_file *m, unsigned long ip)
 }
 #endif
 
+static void print_subops(struct seq_file *m, struct ftrace_ops *ops, struct dyn_ftrace *rec)
+{
+	struct ftrace_ops *subops;
+	bool first = true;
+
+	list_for_each_entry(subops, &ops->subop_list, list) {
+		if (!((subops->flags & FTRACE_OPS_FL_ENABLED) &&
+		      hash_contains_ip(rec->ip, subops->func_hash)))
+			continue;
+		if (first) {
+			seq_printf(m, "\tsubops:");
+			first = false;
+		}
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+		if (subops->flags & FTRACE_OPS_FL_GRAPH) {
+			struct fgraph_ops *gops;
+
+			gops = container_of(subops, struct fgraph_ops, ops);
+			seq_printf(m, " {ent:%pS ret:%pS}",
+				   (void *)gops->entryfunc,
+				   (void *)gops->retfunc);
+			continue;
+		}
+#endif
+		if (subops->trampoline) {
+			seq_printf(m, " {%pS (%pS)}",
+				   (void *)subops->trampoline,
+				   (void *)subops->func);
+			add_trampoline_func(m, subops, rec);
+		} else {
+			seq_printf(m, " {%pS}",
+				   (void *)subops->func);
+		}
+	}
+}
+
 static int t_show(struct seq_file *m, void *v)
 {
 	struct ftrace_iterator *iter = m->private;
@@ -4425,6 +4461,7 @@ static int t_show(struct seq_file *m, void *v)
 						   (void *)ops->trampoline,
 						   (void *)ops->func);
 					add_trampoline_func(m, ops, rec);
+					print_subops(m, ops, rec);
 					ops = ftrace_find_tramp_ops_next(rec, ops);
 				} while (ops);
 			} else
@@ -4437,6 +4474,7 @@ static int t_show(struct seq_file *m, void *v)
 			if (ops) {
 				seq_printf(m, "\tops: %pS (%pS)",
 					   ops, ops->func);
+				print_subops(m, ops, rec);
 			} else {
 				seq_puts(m, "\tops: ERROR!");
 			}
@@ -5170,8 +5208,12 @@ struct ftrace_func_map {
 	void				*data;
 };
 
+/*
+ * Note, ftrace_func_mapper is freed by free_ftrace_hash(&mapper->hash).
+ * The hash field must be the first field.
+ */
 struct ftrace_func_mapper {
-	struct ftrace_hash		hash;
+	struct ftrace_hash		hash;	/* Must be first! */
 };
 
 /**
@@ -5306,6 +5348,7 @@ void free_ftrace_func_mapper(struct ftrace_func_mapper *mapper,
 			}
 		}
 	}
+	/* This also frees the mapper itself */
 	free_ftrace_hash(&mapper->hash);
 }
 
@@ -7395,9 +7438,10 @@ void ftrace_release_mod(struct module *mod)
 
 	mutex_lock(&ftrace_lock);
 
-	if (ftrace_disabled)
-		goto out_unlock;
-
+	/*
+	 * To avoid the UAF problem after the module is unloaded, the
+	 * 'mod_map' resource needs to be released unconditionally.
+	 */
 	list_for_each_entry_safe(mod_map, n, &ftrace_mod_maps, list) {
 		if (mod_map->mod == mod) {
 			list_del_rcu(&mod_map->list);
@@ -7406,6 +7450,9 @@ void ftrace_release_mod(struct module *mod)
 		}
 	}
 
+	if (ftrace_disabled)
+		goto out_unlock;
+
 	/*
 	 * Each module has its own ftrace_pages, remove
 	 * them from the list.
@@ -7584,6 +7631,9 @@ allocate_ftrace_mod_map(struct module *mod,
 {
 	struct ftrace_mod_map *mod_map;
 
+	if (ftrace_disabled)
+		return NULL;
+
 	mod_map = kmalloc(sizeof(*mod_map), GFP_KERNEL);
 	if (!mod_map)
 		return NULL;
diff --git a/kernel/trace/pid_list.c b/kernel/trace/pid_list.c
index c62b9b3cfb3d..090bb5ea4a19 100644
--- a/kernel/trace/pid_list.c
+++ b/kernel/trace/pid_list.c
@@ -81,13 +81,9 @@ static inline bool upper_empty(union upper_chunk *chunk)
 {
 	/*
 	 * If chunk->data has no lower chunks, it will be the same
-	 * as a zeroed bitmask. Use find_first_bit() to test it
-	 * and if it doesn't find any bits set, then the array
-	 * is empty.
+	 * as a zeroed bitmask.
 	 */
-	int bit = find_first_bit((unsigned long *)chunk->data,
-				 sizeof(chunk->data) * 8);
-	return bit >= sizeof(chunk->data) * 8;
+	return bitmap_empty((unsigned long *)chunk->data, BITS_PER_TYPE(chunk->data));
 }
 
 static inline int pid_split(unsigned int pid, unsigned int *upper1,
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index c0f877d39a24..00fc38d70e86 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -1887,10 +1887,12 @@ static void rb_meta_validate_events(struct ring_buffer_per_cpu *cpu_buffer)
 
 	head_page = cpu_buffer->head_page;
 
-	/* If both the head and commit are on the reader_page then we are done. */
-	if (head_page == cpu_buffer->reader_page &&
-	    head_page == cpu_buffer->commit_page)
+	/* If the commit_buffer is the reader page, update the commit page */
+	if (meta->commit_buffer == (unsigned long)cpu_buffer->reader_page->page) {
+		cpu_buffer->commit_page = cpu_buffer->reader_page;
+		/* Nothing more to do, the only page is the reader page */
 		goto done;
+	}
 
 	/* Iterate until finding the commit page */
 	for (i = 0; i < meta->nr_subbufs + 1; i++, rb_inc_page(&head_page)) {
@@ -2224,7 +2226,7 @@ static int rb_allocate_pages(struct ring_buffer_per_cpu *cpu_buffer,
 static struct ring_buffer_per_cpu *
 rb_allocate_cpu_buffer(struct trace_buffer *buffer, long nr_pages, int cpu)
 {
-	struct ring_buffer_per_cpu *cpu_buffer;
+	struct ring_buffer_per_cpu *cpu_buffer __free(kfree) = NULL;
 	struct ring_buffer_cpu_meta *meta;
 	struct buffer_page *bpage;
 	struct page *page;
@@ -2250,7 +2252,7 @@ rb_allocate_cpu_buffer(struct trace_buffer *buffer, long nr_pages, int cpu)
 	bpage = kzalloc_node(ALIGN(sizeof(*bpage), cache_line_size()),
 			    GFP_KERNEL, cpu_to_node(cpu));
 	if (!bpage)
-		goto fail_free_buffer;
+		return NULL;
 
 	rb_check_bpage(cpu_buffer, bpage);
 
@@ -2316,13 +2318,11 @@ rb_allocate_cpu_buffer(struct trace_buffer *buffer, long nr_pages, int cpu)
 		rb_head_page_activate(cpu_buffer);
 	}
 
-	return cpu_buffer;
+	return_ptr(cpu_buffer);
 
  fail_free_reader:
 	free_buffer_page(cpu_buffer->reader_page);
 
- fail_free_buffer:
-	kfree(cpu_buffer);
 	return NULL;
 }
 
@@ -2357,7 +2357,7 @@ static struct trace_buffer *alloc_buffer(unsigned long size, unsigned flags,
 					 unsigned long scratch_size,
 					 struct lock_class_key *key)
 {
-	struct trace_buffer *buffer;
+	struct trace_buffer *buffer __free(kfree) = NULL;
 	long nr_pages;
 	int subbuf_size;
 	int bsize;
@@ -2371,7 +2371,7 @@ static struct trace_buffer *alloc_buffer(unsigned long size, unsigned flags,
 		return NULL;
 
 	if (!zalloc_cpumask_var(&buffer->cpumask, GFP_KERNEL))
-		goto fail_free_buffer;
+		return NULL;
 
 	buffer->subbuf_order = order;
 	subbuf_size = (PAGE_SIZE << order);
@@ -2470,7 +2470,7 @@ static struct trace_buffer *alloc_buffer(unsigned long size, unsigned flags,
 
 	mutex_init(&buffer->mutex);
 
-	return buffer;
+	return_ptr(buffer);
 
  fail_free_buffers:
 	for_each_buffer_cpu(buffer, cpu) {
@@ -2482,8 +2482,6 @@ static struct trace_buffer *alloc_buffer(unsigned long size, unsigned flags,
  fail_free_cpumask:
 	free_cpumask_var(buffer->cpumask);
 
- fail_free_buffer:
-	kfree(buffer);
 	return NULL;
 }
 
@@ -2847,6 +2845,12 @@ int ring_buffer_resize(struct trace_buffer *buffer, unsigned long size,
 	if (nr_pages < 2)
 		nr_pages = 2;
 
+	/*
+	 * Keep CPUs from coming online while resizing to synchronize
+	 * with new per CPU buffers being created.
+	 */
+	guard(cpus_read_lock)();
+
 	/* prevent another thread from changing buffer sizes */
 	mutex_lock(&buffer->mutex);
 	atomic_inc(&buffer->resizing);
@@ -2891,7 +2895,6 @@ int ring_buffer_resize(struct trace_buffer *buffer, unsigned long size,
 			cond_resched();
 		}
 
-		cpus_read_lock();
 		/*
 		 * Fire off all the required work handlers
 		 * We can't schedule on offline CPUs, but it's not necessary
@@ -2931,7 +2934,6 @@ int ring_buffer_resize(struct trace_buffer *buffer, unsigned long size,
 			cpu_buffer->nr_pages_to_update = 0;
 		}
 
-		cpus_read_unlock();
 	} else {
 		cpu_buffer = buffer->buffers[cpu_id];
 
@@ -2959,8 +2961,6 @@ int ring_buffer_resize(struct trace_buffer *buffer, unsigned long size,
 			goto out_err;
 		}
 
-		cpus_read_lock();
-
 		/* Can't run something on an offline CPU. */
 		if (!cpu_online(cpu_id))
 			rb_update_pages(cpu_buffer);
@@ -2979,7 +2979,6 @@ int ring_buffer_resize(struct trace_buffer *buffer, unsigned long size,
 		}
 
 		cpu_buffer->nr_pages_to_update = 0;
-		cpus_read_unlock();
 	}
 
  out:
@@ -4682,10 +4681,7 @@ void ring_buffer_discard_commit(struct trace_buffer *buffer,
 	RB_WARN_ON(buffer, !local_read(&cpu_buffer->committing));
 
 	rb_decrement_entry(cpu_buffer, event);
-	if (rb_try_to_discard(cpu_buffer, event))
-		goto out;
-
- out:
+	rb_try_to_discard(cpu_buffer, event);
 	rb_end_commit(cpu_buffer);
 
 	trace_recursive_unlock(cpu_buffer);
@@ -4883,6 +4879,24 @@ bool ring_buffer_record_is_set_on(struct trace_buffer *buffer)
 }
 
 /**
+ * ring_buffer_record_is_on_cpu - return true if the ring buffer can write
+ * @buffer: The ring buffer to see if write is enabled
+ * @cpu: The CPU to test if the ring buffer can write too
+ *
+ * Returns true if the ring buffer is in a state that it accepts writes
+ *   for a particular CPU.
+ */
+bool ring_buffer_record_is_on_cpu(struct trace_buffer *buffer, int cpu)
+{
+	struct ring_buffer_per_cpu *cpu_buffer;
+
+	cpu_buffer = buffer->buffers[cpu];
+
+	return ring_buffer_record_is_set_on(buffer) &&
+		!atomic_read(&cpu_buffer->record_disabled);
+}
+
+/**
  * ring_buffer_record_disable_cpu - stop all writes into the cpu_buffer
  * @buffer: The ring buffer to stop writes to.
  * @cpu: The CPU buffer to stop
@@ -6000,6 +6014,39 @@ static void rb_clear_buffer_page(struct buffer_page *page)
 	page->read = 0;
 }
 
+/*
+ * When the buffer is memory mapped to user space, each sub buffer
+ * has a unique id that is used by the meta data to tell the user
+ * where the current reader page is.
+ *
+ * For a normal allocated ring buffer, the id is saved in the buffer page
+ * id field, and updated via this function.
+ *
+ * But for a fixed memory mapped buffer, the id is already assigned for
+ * fixed memory ording in the memory layout and can not be used. Instead
+ * the index of where the page lies in the memory layout is used.
+ *
+ * For the normal pages, set the buffer page id with the passed in @id
+ * value and return that.
+ *
+ * For fixed memory mapped pages, get the page index in the memory layout
+ * and return that as the id.
+ */
+static int rb_page_id(struct ring_buffer_per_cpu *cpu_buffer,
+		      struct buffer_page *bpage, int id)
+{
+	/*
+	 * For boot buffers, the id is the index,
+	 * otherwise, set the buffer page with this id
+	 */
+	if (cpu_buffer->ring_meta)
+		id = rb_meta_subbuf_idx(cpu_buffer->ring_meta, bpage->page);
+	else
+		bpage->id = id;
+
+	return id;
+}
+
 static void rb_update_meta_page(struct ring_buffer_per_cpu *cpu_buffer)
 {
 	struct trace_buffer_meta *meta = cpu_buffer->meta_page;
@@ -6008,7 +6055,9 @@ static void rb_update_meta_page(struct ring_buffer_per_cpu *cpu_buffer)
 		return;
 
 	meta->reader.read = cpu_buffer->reader_page->read;
-	meta->reader.id = cpu_buffer->reader_page->id;
+	meta->reader.id = rb_page_id(cpu_buffer, cpu_buffer->reader_page,
+				     cpu_buffer->reader_page->id);
+
 	meta->reader.lost_events = cpu_buffer->lost_events;
 
 	meta->entries = local_read(&cpu_buffer->entries);
@@ -6078,21 +6127,16 @@ rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer)
 /* Must have disabled the cpu buffer then done a synchronize_rcu */
 static void reset_disabled_cpu_buffer(struct ring_buffer_per_cpu *cpu_buffer)
 {
-	unsigned long flags;
-
-	raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
+	guard(raw_spinlock_irqsave)(&cpu_buffer->reader_lock);
 
 	if (RB_WARN_ON(cpu_buffer, local_read(&cpu_buffer->committing)))
-		goto out;
+		return;
 
 	arch_spin_lock(&cpu_buffer->lock);
 
 	rb_reset_cpu(cpu_buffer);
 
 	arch_spin_unlock(&cpu_buffer->lock);
-
- out:
-	raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
 }
 
 /**
@@ -6280,37 +6324,33 @@ int ring_buffer_swap_cpu(struct trace_buffer *buffer_a,
 
 	if (!cpumask_test_cpu(cpu, buffer_a->cpumask) ||
 	    !cpumask_test_cpu(cpu, buffer_b->cpumask))
-		goto out;
+		return -EINVAL;
 
 	cpu_buffer_a = buffer_a->buffers[cpu];
 	cpu_buffer_b = buffer_b->buffers[cpu];
 
 	/* It's up to the callers to not try to swap mapped buffers */
-	if (WARN_ON_ONCE(cpu_buffer_a->mapped || cpu_buffer_b->mapped)) {
-		ret = -EBUSY;
-		goto out;
-	}
+	if (WARN_ON_ONCE(cpu_buffer_a->mapped || cpu_buffer_b->mapped))
+		return -EBUSY;
 
 	/* At least make sure the two buffers are somewhat the same */
 	if (cpu_buffer_a->nr_pages != cpu_buffer_b->nr_pages)
-		goto out;
+		return -EINVAL;
 
 	if (buffer_a->subbuf_order != buffer_b->subbuf_order)
-		goto out;
-
-	ret = -EAGAIN;
+		return -EINVAL;
 
 	if (atomic_read(&buffer_a->record_disabled))
-		goto out;
+		return -EAGAIN;
 
 	if (atomic_read(&buffer_b->record_disabled))
-		goto out;
+		return -EAGAIN;
 
 	if (atomic_read(&cpu_buffer_a->record_disabled))
-		goto out;
+		return -EAGAIN;
 
 	if (atomic_read(&cpu_buffer_b->record_disabled))
-		goto out;
+		return -EAGAIN;
 
 	/*
 	 * We can't do a synchronize_rcu here because this
@@ -6347,7 +6387,6 @@ int ring_buffer_swap_cpu(struct trace_buffer *buffer_a,
 out_dec:
 	atomic_dec(&cpu_buffer_a->record_disabled);
 	atomic_dec(&cpu_buffer_b->record_disabled);
-out:
 	return ret;
 }
 EXPORT_SYMBOL_GPL(ring_buffer_swap_cpu);
@@ -6506,38 +6545,37 @@ int ring_buffer_read_page(struct trace_buffer *buffer,
 	struct buffer_data_page *bpage;
 	struct buffer_page *reader;
 	unsigned long missed_events;
-	unsigned long flags;
 	unsigned int commit;
 	unsigned int read;
 	u64 save_timestamp;
-	int ret = -1;
 
 	if (!cpumask_test_cpu(cpu, buffer->cpumask))
-		goto out;
+		return -1;
 
 	/*
 	 * If len is not big enough to hold the page header, then
 	 * we can not copy anything.
 	 */
 	if (len <= BUF_PAGE_HDR_SIZE)
-		goto out;
+		return -1;
 
 	len -= BUF_PAGE_HDR_SIZE;
 
 	if (!data_page || !data_page->data)
-		goto out;
+		return -1;
+
 	if (data_page->order != buffer->subbuf_order)
-		goto out;
+		return -1;
 
 	bpage = data_page->data;
 	if (!bpage)
-		goto out;
+		return -1;
 
-	raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
+	guard(raw_spinlock_irqsave)(&cpu_buffer->reader_lock);
 
 	reader = rb_get_reader_page(cpu_buffer);
 	if (!reader)
-		goto out_unlock;
+		return -1;
 
 	event = rb_reader_event(cpu_buffer);
 
@@ -6571,7 +6609,7 @@ int ring_buffer_read_page(struct trace_buffer *buffer,
 		if (full &&
 		    (!read || (len < (commit - read)) ||
 		     cpu_buffer->reader_page == cpu_buffer->commit_page))
-			goto out_unlock;
+			return -1;
 
 		if (len > (commit - read))
 			len = (commit - read);
@@ -6580,7 +6618,7 @@ int ring_buffer_read_page(struct trace_buffer *buffer,
 		size = rb_event_ts_length(event);
 
 		if (len < size)
-			goto out_unlock;
+			return -1;
 
 		/* save the current timestamp, since the user will need it */
 		save_timestamp = cpu_buffer->read_stamp;
@@ -6638,7 +6676,6 @@ int ring_buffer_read_page(struct trace_buffer *buffer,
 		if (reader->real_end)
 			local_set(&bpage->commit, reader->real_end);
 	}
-	ret = read;
 
 	cpu_buffer->lost_events = 0;
 
@@ -6665,11 +6702,7 @@ int ring_buffer_read_page(struct trace_buffer *buffer,
 	if (commit < buffer->subbuf_size)
 		memset(&bpage->data[commit], 0, buffer->subbuf_size - commit);
 
- out_unlock:
-	raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
-
- out:
-	return ret;
+	return read;
 }
 EXPORT_SYMBOL_GPL(ring_buffer_read_page);
 
@@ -6762,7 +6795,7 @@ int ring_buffer_subbuf_order_set(struct trace_buffer *buffer, int order)
 	old_size = buffer->subbuf_size;
 
 	/* prevent another thread from changing buffer sizes */
-	mutex_lock(&buffer->mutex);
+	guard(mutex)(&buffer->mutex);
 	atomic_inc(&buffer->record_disabled);
 
 	/* Make sure all commits have finished */
@@ -6867,7 +6900,6 @@ int ring_buffer_subbuf_order_set(struct trace_buffer *buffer, int order)
 	}
 
 	atomic_dec(&buffer->record_disabled);
-	mutex_unlock(&buffer->mutex);
 
 	return 0;
 
@@ -6876,7 +6908,6 @@ error:
 	buffer->subbuf_size = old_size;
 
 	atomic_dec(&buffer->record_disabled);
-	mutex_unlock(&buffer->mutex);
 
 	for_each_buffer_cpu(buffer, cpu) {
 		cpu_buffer = buffer->buffers[cpu];
@@ -6924,23 +6955,29 @@ static void rb_setup_ids_meta_page(struct ring_buffer_per_cpu *cpu_buffer,
 	struct trace_buffer_meta *meta = cpu_buffer->meta_page;
 	unsigned int nr_subbufs = cpu_buffer->nr_pages + 1;
 	struct buffer_page *first_subbuf, *subbuf;
+	int cnt = 0;
 	int id = 0;
 
-	subbuf_ids[id] = (unsigned long)cpu_buffer->reader_page->page;
-	cpu_buffer->reader_page->id = id++;
+	id = rb_page_id(cpu_buffer, cpu_buffer->reader_page, id);
+	subbuf_ids[id++] = (unsigned long)cpu_buffer->reader_page->page;
+	cnt++;
 
 	first_subbuf = subbuf = rb_set_head_page(cpu_buffer);
 	do {
+		id = rb_page_id(cpu_buffer, subbuf, id);
+
 		if (WARN_ON(id >= nr_subbufs))
 			break;
 
 		subbuf_ids[id] = (unsigned long)subbuf->page;
-		subbuf->id = id;
 
 		rb_inc_page(&subbuf);
 		id++;
+		cnt++;
 	} while (subbuf != first_subbuf);
 
+	WARN_ON(cnt != nr_subbufs);
+
 	/* install subbuf ID to kern VA translation */
 	cpu_buffer->subbuf_ids = subbuf_ids;
 
@@ -7032,7 +7069,7 @@ static int __rb_map_vma(struct ring_buffer_per_cpu *cpu_buffer,
 {
 	unsigned long nr_subbufs, nr_pages, nr_vma_pages, pgoff = vma->vm_pgoff;
 	unsigned int subbuf_pages, subbuf_order;
-	struct page **pages;
+	struct page **pages __free(kfree) = NULL;
 	int p = 0, s = 0;
 	int err;
 
@@ -7100,10 +7137,8 @@ static int __rb_map_vma(struct ring_buffer_per_cpu *cpu_buffer,
 		struct page *page;
 		int off = 0;
 
-		if (WARN_ON_ONCE(s >= nr_subbufs)) {
-			err = -EINVAL;
-			goto out;
-		}
+		if (WARN_ON_ONCE(s >= nr_subbufs))
+			return -EINVAL;
 
 		page = virt_to_page((void *)cpu_buffer->subbuf_ids[s]);
 
@@ -7118,9 +7153,6 @@ static int __rb_map_vma(struct ring_buffer_per_cpu *cpu_buffer,
 
 	err = vm_insert_pages(vma, vma->vm_start, pages, &nr_pages);
 
-out:
-	kfree(pages);
-
 	return err;
 }
 #else
@@ -7136,36 +7168,34 @@ int ring_buffer_map(struct trace_buffer *buffer, int cpu,
 {
 	struct ring_buffer_per_cpu *cpu_buffer;
 	unsigned long flags, *subbuf_ids;
-	int err = 0;
+	int err;
 
 	if (!cpumask_test_cpu(cpu, buffer->cpumask))
 		return -EINVAL;
 
 	cpu_buffer = buffer->buffers[cpu];
 
-	mutex_lock(&cpu_buffer->mapping_lock);
+	guard(mutex)(&cpu_buffer->mapping_lock);
 
 	if (cpu_buffer->user_mapped) {
 		err = __rb_map_vma(cpu_buffer, vma);
 		if (!err)
 			err = __rb_inc_dec_mapped(cpu_buffer, true);
-		mutex_unlock(&cpu_buffer->mapping_lock);
 		return err;
 	}
 
 	/* prevent another thread from changing buffer/sub-buffer sizes */
-	mutex_lock(&buffer->mutex);
+	guard(mutex)(&buffer->mutex);
 
 	err = rb_alloc_meta_page(cpu_buffer);
 	if (err)
-		goto unlock;
+		return err;
 
 	/* subbuf_ids include the reader while nr_pages does not */
 	subbuf_ids = kcalloc(cpu_buffer->nr_pages + 1, sizeof(*subbuf_ids), GFP_KERNEL);
 	if (!subbuf_ids) {
 		rb_free_meta_page(cpu_buffer);
-		err = -ENOMEM;
-		goto unlock;
+		return -ENOMEM;
 	}
 
 	atomic_inc(&cpu_buffer->resize_disabled);
@@ -7193,35 +7223,29 @@ int ring_buffer_map(struct trace_buffer *buffer, int cpu,
 		atomic_dec(&cpu_buffer->resize_disabled);
 	}
 
-unlock:
-	mutex_unlock(&buffer->mutex);
-	mutex_unlock(&cpu_buffer->mapping_lock);
-
-	return err;
+	return 0;
 }
 
 int ring_buffer_unmap(struct trace_buffer *buffer, int cpu)
 {
 	struct ring_buffer_per_cpu *cpu_buffer;
 	unsigned long flags;
-	int err = 0;
 
 	if (!cpumask_test_cpu(cpu, buffer->cpumask))
 		return -EINVAL;
 
 	cpu_buffer = buffer->buffers[cpu];
 
-	mutex_lock(&cpu_buffer->mapping_lock);
+	guard(mutex)(&cpu_buffer->mapping_lock);
 
 	if (!cpu_buffer->user_mapped) {
-		err = -ENODEV;
-		goto out;
+		return -ENODEV;
 	} else if (cpu_buffer->user_mapped > 1) {
 		__rb_inc_dec_mapped(cpu_buffer, false);
-		goto out;
+		return 0;
 	}
 
-	mutex_lock(&buffer->mutex);
+	guard(mutex)(&buffer->mutex);
 	raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
 
 	/* This is the last user space mapping */
@@ -7236,12 +7260,7 @@ int ring_buffer_unmap(struct trace_buffer *buffer, int cpu)
 	rb_free_meta_page(cpu_buffer);
 	atomic_dec(&cpu_buffer->resize_disabled);
 
-	mutex_unlock(&buffer->mutex);
-
-out:
-	mutex_unlock(&cpu_buffer->mapping_lock);
-
-	return err;
+	return 0;
 }
 
 int ring_buffer_map_get_reader(struct trace_buffer *buffer, int cpu)
@@ -7282,8 +7301,8 @@ consume:
 	/* Check if any events were dropped */
 	missed_events = cpu_buffer->lost_events;
 
-	if (cpu_buffer->reader_page != cpu_buffer->commit_page) {
-		if (missed_events) {
+	if (missed_events) {
+		if (cpu_buffer->reader_page != cpu_buffer->commit_page) {
 			struct buffer_data_page *bpage = reader->page;
 			unsigned int commit;
 			/*
@@ -7304,13 +7323,23 @@ consume:
 				local_add(RB_MISSED_STORED, &bpage->commit);
 			}
 			local_add(RB_MISSED_EVENTS, &bpage->commit);
+		} else if (!WARN_ONCE(cpu_buffer->reader_page == cpu_buffer->tail_page,
+				      "Reader on commit with %ld missed events",
+				      missed_events)) {
+			/*
+			 * There shouldn't be any missed events if the tail_page
+			 * is on the reader page. But if the tail page is not on the
+			 * reader page and the commit_page is, that would mean that
+			 * there's a commit_overrun (an interrupt preempted an
+			 * addition of an event and then filled the buffer
+			 * with new events). In this case it's not an
+			 * error, but it should still be reported.
+			 *
+			 * TODO: Add missed events to the page for user space to know.
+			 */
+			pr_info("Ring buffer [%d] commit overrun lost %ld events at timestamp:%lld\n",
+				cpu, missed_events, cpu_buffer->reader_page->page->time_stamp);
 		}
-	} else {
-		/*
-		 * There really shouldn't be any missed events if the commit
-		 * is on the reader page.
-		 */
-		WARN_ON_ONCE(missed_events);
 	}
 
 	cpu_buffer->lost_events = 0;
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 5b8db27fb6ef..95ae7c4e5835 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -51,6 +51,7 @@
 #include <linux/workqueue.h>
 #include <linux/sort.h>
 #include <linux/io.h> /* vmap_page_range() */
+#include <linux/fs_context.h>
 
 #include <asm/setup.h> /* COMMAND_LINE_SIZE */
 
@@ -120,6 +121,7 @@ static int tracing_disabled = 1;
 
 cpumask_var_t __read_mostly	tracing_buffer_mask;
 
+#define MAX_TRACER_SIZE		100
 /*
  * ftrace_dump_on_oops - variable to dump ftrace buffer on oops
  *
@@ -142,7 +144,40 @@ cpumask_var_t __read_mostly	tracing_buffer_mask;
 char ftrace_dump_on_oops[MAX_TRACER_SIZE] = "0";
 
 /* When set, tracing will stop when a WARN*() is hit */
-int __disable_trace_on_warning;
+static int __disable_trace_on_warning;
+
+int tracepoint_printk_sysctl(const struct ctl_table *table, int write,
+			     void *buffer, size_t *lenp, loff_t *ppos);
+static const struct ctl_table trace_sysctl_table[] = {
+	{
+		.procname	= "ftrace_dump_on_oops",
+		.data		= &ftrace_dump_on_oops,
+		.maxlen		= MAX_TRACER_SIZE,
+		.mode		= 0644,
+		.proc_handler	= proc_dostring,
+	},
+	{
+		.procname	= "traceoff_on_warning",
+		.data		= &__disable_trace_on_warning,
+		.maxlen		= sizeof(__disable_trace_on_warning),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+	{
+		.procname	= "tracepoint_printk",
+		.data		= &tracepoint_printk,
+		.maxlen		= sizeof(tracepoint_printk),
+		.mode		= 0644,
+		.proc_handler	= tracepoint_printk_sysctl,
+	},
+};
+
+static int __init init_trace_sysctls(void)
+{
+	register_sysctl_init("kernel", trace_sysctl_table);
+	return 0;
+}
+subsys_initcall(init_trace_sysctls);
 
 #ifdef CONFIG_TRACE_EVAL_MAP_FILE
 /* Map of enums to their values, for "eval_map" file */
@@ -493,7 +528,8 @@ EXPORT_SYMBOL_GPL(unregister_ftrace_export);
 	 TRACE_ITER_ANNOTATE | TRACE_ITER_CONTEXT_INFO |		\
 	 TRACE_ITER_RECORD_CMD | TRACE_ITER_OVERWRITE |			\
 	 TRACE_ITER_IRQ_INFO | TRACE_ITER_MARKERS |			\
-	 TRACE_ITER_HASH_PTR | TRACE_ITER_TRACE_PRINTK)
+	 TRACE_ITER_HASH_PTR | TRACE_ITER_TRACE_PRINTK |		\
+	 TRACE_ITER_COPY_MARKER)
 
 /* trace_options that are only supported by global_trace */
 #define TOP_LEVEL_TRACE_FLAGS (TRACE_ITER_PRINTK |			\
@@ -501,7 +537,8 @@ EXPORT_SYMBOL_GPL(unregister_ftrace_export);
 
 /* trace_flags that are default zero for instances */
 #define ZEROED_TRACE_FLAGS \
-	(TRACE_ITER_EVENT_FORK | TRACE_ITER_FUNC_FORK | TRACE_ITER_TRACE_PRINTK)
+	(TRACE_ITER_EVENT_FORK | TRACE_ITER_FUNC_FORK | TRACE_ITER_TRACE_PRINTK | \
+	 TRACE_ITER_COPY_MARKER)
 
 /*
  * The global_trace is the descriptor that holds the top-level tracing
@@ -513,6 +550,9 @@ static struct trace_array global_trace = {
 
 static struct trace_array *printk_trace = &global_trace;
 
+/* List of trace_arrays interested in the top level trace_marker */
+static LIST_HEAD(marker_copies);
+
 static __always_inline bool printk_binsafe(struct trace_array *tr)
 {
 	/*
@@ -534,6 +574,28 @@ static void update_printk_trace(struct trace_array *tr)
 	tr->trace_flags |= TRACE_ITER_TRACE_PRINTK;
 }
 
+/* Returns true if the status of tr changed */
+static bool update_marker_trace(struct trace_array *tr, int enabled)
+{
+	lockdep_assert_held(&event_mutex);
+
+	if (enabled) {
+		if (!list_empty(&tr->marker_list))
+			return false;
+
+		list_add_rcu(&tr->marker_list, &marker_copies);
+		tr->trace_flags |= TRACE_ITER_COPY_MARKER;
+		return true;
+	}
+
+	if (list_empty(&tr->marker_list))
+		return false;
+
+	list_del_init(&tr->marker_list);
+	tr->trace_flags &= ~TRACE_ITER_COPY_MARKER;
+	return true;
+}
+
 void trace_set_ring_buffer_expanded(struct trace_array *tr)
 {
 	if (!tr)
@@ -1583,6 +1645,39 @@ void tracer_tracing_off(struct trace_array *tr)
 }
 
 /**
+ * tracer_tracing_disable() - temporary disable the buffer from write
+ * @tr: The trace array to disable its buffer for
+ *
+ * Expects trace_tracing_enable() to re-enable tracing.
+ * The difference between this and tracer_tracing_off() is that this
+ * is a counter and can nest, whereas, tracer_tracing_off() can
+ * be called multiple times and a single trace_tracing_on() will
+ * enable it.
+ */
+void tracer_tracing_disable(struct trace_array *tr)
+{
+	if (WARN_ON_ONCE(!tr->array_buffer.buffer))
+		return;
+
+	ring_buffer_record_disable(tr->array_buffer.buffer);
+}
+
+/**
+ * tracer_tracing_enable() - counter part of tracer_tracing_disable()
+ * @tr: The trace array that had tracer_tracincg_disable() called on it
+ *
+ * This is called after tracer_tracing_disable() has been called on @tr,
+ * when it's safe to re-enable tracing.
+ */
+void tracer_tracing_enable(struct trace_array *tr)
+{
+	if (WARN_ON_ONCE(!tr->array_buffer.buffer))
+		return;
+
+	ring_buffer_record_enable(tr->array_buffer.buffer);
+}
+
+/**
  * tracing_off - turn off tracing buffers
  *
  * This function stops the tracing buffers from recording data.
@@ -5048,7 +5143,6 @@ int tracing_set_cpumask(struct trace_array *tr,
 		 */
 		if (cpumask_test_cpu(cpu, tr->tracing_cpumask) &&
 				!cpumask_test_cpu(cpu, tracing_cpumask_new)) {
-			atomic_inc(&per_cpu_ptr(tr->array_buffer.data, cpu)->disabled);
 			ring_buffer_record_disable_cpu(tr->array_buffer.buffer, cpu);
 #ifdef CONFIG_TRACER_MAX_TRACE
 			ring_buffer_record_disable_cpu(tr->max_buffer.buffer, cpu);
@@ -5056,7 +5150,6 @@ int tracing_set_cpumask(struct trace_array *tr,
 		}
 		if (!cpumask_test_cpu(cpu, tr->tracing_cpumask) &&
 				cpumask_test_cpu(cpu, tracing_cpumask_new)) {
-			atomic_dec(&per_cpu_ptr(tr->array_buffer.data, cpu)->disabled);
 			ring_buffer_record_enable_cpu(tr->array_buffer.buffer, cpu);
 #ifdef CONFIG_TRACER_MAX_TRACE
 			ring_buffer_record_enable_cpu(tr->max_buffer.buffer, cpu);
@@ -5189,7 +5282,8 @@ int set_tracer_flag(struct trace_array *tr, unsigned int mask, int enabled)
 {
 	if ((mask == TRACE_ITER_RECORD_TGID) ||
 	    (mask == TRACE_ITER_RECORD_CMD) ||
-	    (mask == TRACE_ITER_TRACE_PRINTK))
+	    (mask == TRACE_ITER_TRACE_PRINTK) ||
+	    (mask == TRACE_ITER_COPY_MARKER))
 		lockdep_assert_held(&event_mutex);
 
 	/* do nothing if flag is already set */
@@ -5220,6 +5314,9 @@ int set_tracer_flag(struct trace_array *tr, unsigned int mask, int enabled)
 		}
 	}
 
+	if (mask == TRACE_ITER_COPY_MARKER)
+		update_marker_trace(tr, enabled);
+
 	if (enabled)
 		tr->trace_flags |= mask;
 	else
@@ -6004,6 +6101,7 @@ struct trace_mod_entry {
 };
 
 struct trace_scratch {
+	unsigned int		clock_id;
 	unsigned long		text_addr;
 	unsigned long		nr_entries;
 	struct trace_mod_entry	entries[];
@@ -6032,6 +6130,7 @@ unsigned long trace_adjust_address(struct trace_array *tr, unsigned long addr)
 	struct trace_module_delta *module_delta;
 	struct trace_scratch *tscratch;
 	struct trace_mod_entry *entry;
+	unsigned long raddr;
 	int idx = 0, nr_entries;
 
 	/* If we don't have last boot delta, return the address */
@@ -6045,7 +6144,9 @@ unsigned long trace_adjust_address(struct trace_array *tr, unsigned long addr)
 	module_delta = READ_ONCE(tr->module_delta);
 	if (!module_delta || !tscratch->nr_entries ||
 	    tscratch->entries[0].mod_addr > addr) {
-		return addr + tr->text_delta;
+		raddr = addr + tr->text_delta;
+		return __is_kernel(raddr) || is_kernel_core_data(raddr) ||
+			is_kernel_rodata(raddr) ? raddr : addr;
 	}
 
 	/* Note that entries must be sorted. */
@@ -6116,6 +6217,7 @@ static void update_last_data(struct trace_array *tr)
 	if (tr->scratch) {
 		struct trace_scratch *tscratch = tr->scratch;
 
+		tscratch->clock_id = tr->clock_id;
 		memset(tscratch->entries, 0,
 		       flex_array_size(tscratch, entries, tscratch->nr_entries));
 		tscratch->nr_entries = 0;
@@ -6610,6 +6712,22 @@ static int tracing_wait_pipe(struct file *filp)
 	return 1;
 }
 
+static bool update_last_data_if_empty(struct trace_array *tr)
+{
+	if (!(tr->flags & TRACE_ARRAY_FL_LAST_BOOT))
+		return false;
+
+	if (!ring_buffer_empty(tr->array_buffer.buffer))
+		return false;
+
+	/*
+	 * If the buffer contains the last boot data and all per-cpu
+	 * buffers are empty, reset it from the kernel side.
+	 */
+	update_last_data(tr);
+	return true;
+}
+
 /*
  * Consumer reader.
  */
@@ -6641,6 +6759,9 @@ tracing_read_pipe(struct file *filp, char __user *ubuf,
 	}
 
 waitagain:
+	if (update_last_data_if_empty(iter->tr))
+		return 0;
+
 	sret = tracing_wait_pipe(filp);
 	if (sret <= 0)
 		return sret;
@@ -6824,7 +6945,7 @@ static ssize_t tracing_splice_read_pipe(struct file *filp,
 		ret = trace_seq_to_buffer(&iter->seq,
 					  page_address(spd.pages[i]),
 					  min((size_t)trace_seq_used(&iter->seq),
-						  PAGE_SIZE));
+						  (size_t)PAGE_SIZE));
 		if (ret < 0) {
 			__free_page(spd.pages[i]);
 			break;
@@ -7100,11 +7221,9 @@ tracing_free_buffer_release(struct inode *inode, struct file *filp)
 
 #define TRACE_MARKER_MAX_SIZE		4096
 
-static ssize_t
-tracing_mark_write(struct file *filp, const char __user *ubuf,
-					size_t cnt, loff_t *fpos)
+static ssize_t write_marker_to_buffer(struct trace_array *tr, const char __user *ubuf,
+				      size_t cnt, unsigned long ip)
 {
-	struct trace_array *tr = filp->private_data;
 	struct ring_buffer_event *event;
 	enum event_trigger_type tt = ETT_NONE;
 	struct trace_buffer *buffer;
@@ -7118,18 +7237,6 @@ tracing_mark_write(struct file *filp, const char __user *ubuf,
 #define FAULTED_STR "<faulted>"
 #define FAULTED_SIZE (sizeof(FAULTED_STR) - 1) /* '\0' is already accounted for */
 
-	if (tracing_disabled)
-		return -EINVAL;
-
-	if (!(tr->trace_flags & TRACE_ITER_MARKERS))
-		return -EINVAL;
-
-	if ((ssize_t)cnt < 0)
-		return -EINVAL;
-
-	if (cnt > TRACE_MARKER_MAX_SIZE)
-		cnt = TRACE_MARKER_MAX_SIZE;
-
 	meta_size = sizeof(*entry) + 2;  /* add '\0' and possible '\n' */
  again:
 	size = cnt + meta_size;
@@ -7162,7 +7269,7 @@ tracing_mark_write(struct file *filp, const char __user *ubuf,
 	}
 
 	entry = ring_buffer_event_data(event);
-	entry->ip = _THIS_IP_;
+	entry->ip = ip;
 
 	len = __copy_from_user_inatomic(&entry->buf, ubuf, cnt);
 	if (len) {
@@ -7195,18 +7302,12 @@ tracing_mark_write(struct file *filp, const char __user *ubuf,
 }
 
 static ssize_t
-tracing_mark_raw_write(struct file *filp, const char __user *ubuf,
+tracing_mark_write(struct file *filp, const char __user *ubuf,
 					size_t cnt, loff_t *fpos)
 {
 	struct trace_array *tr = filp->private_data;
-	struct ring_buffer_event *event;
-	struct trace_buffer *buffer;
-	struct raw_data_entry *entry;
-	ssize_t written;
-	int size;
-	int len;
-
-#define FAULT_SIZE_ID (FAULTED_SIZE + sizeof(int))
+	ssize_t written = -ENODEV;
+	unsigned long ip;
 
 	if (tracing_disabled)
 		return -EINVAL;
@@ -7214,10 +7315,42 @@ tracing_mark_raw_write(struct file *filp, const char __user *ubuf,
 	if (!(tr->trace_flags & TRACE_ITER_MARKERS))
 		return -EINVAL;
 
-	/* The marker must at least have a tag id */
-	if (cnt < sizeof(unsigned int))
+	if ((ssize_t)cnt < 0)
 		return -EINVAL;
 
+	if (cnt > TRACE_MARKER_MAX_SIZE)
+		cnt = TRACE_MARKER_MAX_SIZE;
+
+	/* The selftests expect this function to be the IP address */
+	ip = _THIS_IP_;
+
+	/* The global trace_marker can go to multiple instances */
+	if (tr == &global_trace) {
+		guard(rcu)();
+		list_for_each_entry_rcu(tr, &marker_copies, marker_list) {
+			written = write_marker_to_buffer(tr, ubuf, cnt, ip);
+			if (written < 0)
+				break;
+		}
+	} else {
+		written = write_marker_to_buffer(tr, ubuf, cnt, ip);
+	}
+
+	return written;
+}
+
+static ssize_t write_raw_marker_to_buffer(struct trace_array *tr,
+					  const char __user *ubuf, size_t cnt)
+{
+	struct ring_buffer_event *event;
+	struct trace_buffer *buffer;
+	struct raw_data_entry *entry;
+	ssize_t written;
+	int size;
+	int len;
+
+#define FAULT_SIZE_ID (FAULTED_SIZE + sizeof(int))
+
 	size = sizeof(*entry) + cnt;
 	if (cnt < FAULT_SIZE_ID)
 		size += FAULT_SIZE_ID - cnt;
@@ -7248,6 +7381,40 @@ tracing_mark_raw_write(struct file *filp, const char __user *ubuf,
 	return written;
 }
 
+static ssize_t
+tracing_mark_raw_write(struct file *filp, const char __user *ubuf,
+					size_t cnt, loff_t *fpos)
+{
+	struct trace_array *tr = filp->private_data;
+	ssize_t written = -ENODEV;
+
+#define FAULT_SIZE_ID (FAULTED_SIZE + sizeof(int))
+
+	if (tracing_disabled)
+		return -EINVAL;
+
+	if (!(tr->trace_flags & TRACE_ITER_MARKERS))
+		return -EINVAL;
+
+	/* The marker must at least have a tag id */
+	if (cnt < sizeof(unsigned int))
+		return -EINVAL;
+
+	/* The global trace_marker_raw can go to multiple instances */
+	if (tr == &global_trace) {
+		guard(rcu)();
+		list_for_each_entry_rcu(tr, &marker_copies, marker_list) {
+			written = write_raw_marker_to_buffer(tr, ubuf, cnt);
+			if (written < 0)
+				break;
+		}
+	} else {
+		written = write_raw_marker_to_buffer(tr, ubuf, cnt);
+	}
+
+	return written;
+}
+
 static int tracing_clock_show(struct seq_file *m, void *v)
 {
 	struct trace_array *tr = m->private;
@@ -7292,6 +7459,12 @@ int tracing_set_clock(struct trace_array *tr, const char *clockstr)
 	tracing_reset_online_cpus(&tr->max_buffer);
 #endif
 
+	if (tr->scratch && !(tr->flags & TRACE_ARRAY_FL_LAST_BOOT)) {
+		struct trace_scratch *tscratch = tr->scratch;
+
+		tscratch->clock_id = i;
+	}
+
 	mutex_unlock(&trace_types_lock);
 
 	return 0;
@@ -8167,6 +8340,9 @@ tracing_buffers_read(struct file *filp, char __user *ubuf,
 
 	if (ret < 0) {
 		if (trace_empty(iter) && !iter->closed) {
+			if (update_last_data_if_empty(iter->tr))
+				return 0;
+
 			if ((filp->f_flags & O_NONBLOCK))
 				return -EAGAIN;
 
@@ -8508,10 +8684,6 @@ static int tracing_buffers_mmap(struct file *filp, struct vm_area_struct *vma)
 	if (iter->tr->flags & TRACE_ARRAY_FL_MEMMAP)
 		return -ENODEV;
 
-	/* Currently the boot mapped buffer is not supported for mmap */
-	if (iter->tr->flags & TRACE_ARRAY_FL_BOOT)
-		return -ENODEV;
-
 	ret = get_snapshot_map(iter->tr);
 	if (ret)
 		return ret;
@@ -9517,6 +9689,15 @@ static void setup_trace_scratch(struct trace_array *tr,
 
 	/* Scan modules to make text delta for modules. */
 	module_for_each_mod(make_mod_delta, tr);
+
+	/* Set trace_clock as the same of the previous boot. */
+	if (tscratch->clock_id != tr->clock_id) {
+		if (tscratch->clock_id >= ARRAY_SIZE(trace_clocks) ||
+		    tracing_set_clock(tr, trace_clocks[tscratch->clock_id].name) < 0) {
+			pr_info("the previous trace_clock info is not valid.");
+			goto reset;
+		}
+	}
 	return;
  reset:
 	/* Invalid trace modules */
@@ -9741,6 +9922,7 @@ trace_array_create_systems(const char *name, const char *systems,
 	INIT_LIST_HEAD(&tr->events);
 	INIT_LIST_HEAD(&tr->hist_vars);
 	INIT_LIST_HEAD(&tr->err_log);
+	INIT_LIST_HEAD(&tr->marker_list);
 
 #ifdef CONFIG_MODULES
 	INIT_LIST_HEAD(&tr->mod_events);
@@ -9900,6 +10082,9 @@ static int __remove_instance(struct trace_array *tr)
 	if (printk_trace == tr)
 		update_printk_trace(&global_trace);
 
+	if (update_marker_trace(tr, 0))
+		synchronize_rcu();
+
 	tracing_set_nop(tr);
 	clear_ftrace_function_probes(tr);
 	event_trace_del_tracer(tr);
@@ -10075,6 +10260,8 @@ static struct vfsmount *trace_automount(struct dentry *mntpt, void *ingore)
 {
 	struct vfsmount *mnt;
 	struct file_system_type *type;
+	struct fs_context *fc;
+	int ret;
 
 	/*
 	 * To maintain backward compatibility for tools that mount
@@ -10084,12 +10271,20 @@ static struct vfsmount *trace_automount(struct dentry *mntpt, void *ingore)
 	type = get_fs_type("tracefs");
 	if (!type)
 		return NULL;
-	mnt = vfs_submount(mntpt, type, "tracefs", NULL);
+
+	fc = fs_context_for_submount(type, mntpt);
 	put_filesystem(type);
-	if (IS_ERR(mnt))
-		return NULL;
-	mntget(mnt);
+	if (IS_ERR(fc))
+		return ERR_CAST(fc);
+
+	ret = vfs_parse_fs_string(fc, "source",
+				  "tracefs", strlen("tracefs"));
+	if (!ret)
+		mnt = fc_mount(fc);
+	else
+		mnt = ERR_PTR(ret);
 
+	put_fs_context(fc);
 	return mnt;
 }
 
@@ -10448,7 +10643,7 @@ static void ftrace_dump_one(struct trace_array *tr, enum ftrace_dump_mode dump_m
 	static struct trace_iterator iter;
 	unsigned int old_userobj;
 	unsigned long flags;
-	int cnt = 0, cpu;
+	int cnt = 0;
 
 	/*
 	 * Always turn off tracing when we dump.
@@ -10465,9 +10660,8 @@ static void ftrace_dump_one(struct trace_array *tr, enum ftrace_dump_mode dump_m
 	/* Simulate the iterator */
 	trace_init_iter(&iter, tr);
 
-	for_each_tracing_cpu(cpu) {
-		atomic_inc(&per_cpu_ptr(iter.array_buffer->data, cpu)->disabled);
-	}
+	/* While dumping, do not allow the buffer to be enable */
+	tracer_tracing_disable(tr);
 
 	old_userobj = tr->trace_flags & TRACE_ITER_SYM_USEROBJ;
 
@@ -10526,9 +10720,7 @@ static void ftrace_dump_one(struct trace_array *tr, enum ftrace_dump_mode dump_m
 
 	tr->trace_flags |= old_userobj;
 
-	for_each_tracing_cpu(cpu) {
-		atomic_dec(&per_cpu_ptr(iter.array_buffer->data, cpu)->disabled);
-	}
+	tracer_tracing_enable(tr);
 	local_irq_restore(flags);
 }
 
@@ -10968,6 +11160,7 @@ __init static int tracer_alloc_buffers(void)
 	INIT_LIST_HEAD(&global_trace.events);
 	INIT_LIST_HEAD(&global_trace.hist_vars);
 	INIT_LIST_HEAD(&global_trace.err_log);
+	list_add(&global_trace.marker_list, &marker_copies);
 	list_add(&global_trace.list, &ftrace_trace_arrays);
 
 	apply_trace_boot_options();
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 79be1995db44..bd084953a98b 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -183,8 +183,7 @@ struct trace_array;
  * the trace, etc.)
  */
 struct trace_array_cpu {
-	atomic_t		disabled;
-	void			*buffer_page;	/* ring buffer spare */
+	local_t			disabled;
 
 	unsigned long		entries;
 	unsigned long		saved_latency;
@@ -404,6 +403,7 @@ struct trace_array {
 	struct trace_options	*topts;
 	struct list_head	systems;
 	struct list_head	events;
+	struct list_head	marker_list;
 	struct trace_event_file *trace_marker_file;
 	cpumask_var_t		tracing_cpumask; /* only trace on set CPUs */
 	/* one per_cpu trace_pipe can be opened by only one user */
@@ -665,12 +665,29 @@ bool tracing_is_disabled(void);
 bool tracer_tracing_is_on(struct trace_array *tr);
 void tracer_tracing_on(struct trace_array *tr);
 void tracer_tracing_off(struct trace_array *tr);
+void tracer_tracing_disable(struct trace_array *tr);
+void tracer_tracing_enable(struct trace_array *tr);
 struct dentry *trace_create_file(const char *name,
 				 umode_t mode,
 				 struct dentry *parent,
 				 void *data,
 				 const struct file_operations *fops);
 
+
+/**
+ * tracer_tracing_is_on_cpu - show real state of ring buffer enabled on for a cpu
+ * @tr : the trace array to know if ring buffer is enabled
+ * @cpu: The cpu buffer to check if enabled
+ *
+ * Shows real state of the per CPU buffer if it is enabled or not.
+ */
+static inline bool tracer_tracing_is_on_cpu(struct trace_array *tr, int cpu)
+{
+	if (tr->array_buffer.buffer)
+		return ring_buffer_record_is_on_cpu(tr->array_buffer.buffer, cpu);
+	return false;
+}
+
 int tracing_init_dentry(void);
 
 struct ring_buffer_event;
@@ -1368,6 +1385,7 @@ extern int trace_get_user(struct trace_parser *parser, const char __user *ubuf,
 		C(MARKERS,		"markers"),		\
 		C(EVENT_FORK,		"event-fork"),		\
 		C(TRACE_PRINTK,		"trace_printk_dest"),	\
+		C(COPY_MARKER,		"copy_trace_marker"),\
 		C(PAUSE_ON_TRACE,	"pause-on-trace"),	\
 		C(HASH_PTR,		"hash-ptr"),	/* Print hashed pointer */ \
 		FUNCTION_FLAGS					\
@@ -1772,6 +1790,9 @@ extern int event_enable_register_trigger(char *glob,
 extern void event_enable_unregister_trigger(char *glob,
 					    struct event_trigger_data *test,
 					    struct trace_event_file *file);
+extern struct event_trigger_data *
+trigger_data_alloc(struct event_command *cmd_ops, char *cmd, char *param,
+		   void *private_data);
 extern void trigger_data_free(struct event_trigger_data *data);
 extern int event_trigger_init(struct event_trigger_data *data);
 extern int trace_event_trigger_enable_disable(struct trace_event_file *file,
@@ -1798,11 +1819,6 @@ extern bool event_trigger_check_remove(const char *glob);
 extern bool event_trigger_empty_param(const char *param);
 extern int event_trigger_separate_filter(char *param_and_filter, char **param,
 					 char **filter, bool param_required);
-extern struct event_trigger_data *
-event_trigger_alloc(struct event_command *cmd_ops,
-		    char *cmd,
-		    char *param,
-		    void *private_data);
 extern int event_trigger_parse_num(char *trigger,
 				   struct event_trigger_data *trigger_data);
 extern int event_trigger_set_filter(struct event_command *cmd_ops,
diff --git a/kernel/trace/trace_branch.c b/kernel/trace/trace_branch.c
index 6d08a5523ce0..6809b370e991 100644
--- a/kernel/trace/trace_branch.c
+++ b/kernel/trace/trace_branch.c
@@ -32,7 +32,6 @@ probe_likely_condition(struct ftrace_likely_data *f, int val, int expect)
 {
 	struct trace_array *tr = branch_tracer;
 	struct trace_buffer *buffer;
-	struct trace_array_cpu *data;
 	struct ring_buffer_event *event;
 	struct trace_branch *entry;
 	unsigned long flags;
@@ -54,8 +53,7 @@ probe_likely_condition(struct ftrace_likely_data *f, int val, int expect)
 
 	raw_local_irq_save(flags);
 	current->trace_recursion |= TRACE_BRANCH_BIT;
-	data = this_cpu_ptr(tr->array_buffer.data);
-	if (atomic_read(&data->disabled))
+	if (!tracer_tracing_is_on_cpu(tr, raw_smp_processor_id()))
 		goto out;
 
 	trace_ctx = tracing_gen_ctx_flags(flags);
diff --git a/kernel/trace/trace_dynevent.c b/kernel/trace/trace_dynevent.c
index a322e4f249a5..5d64a18cacac 100644
--- a/kernel/trace/trace_dynevent.c
+++ b/kernel/trace/trace_dynevent.c
@@ -16,7 +16,7 @@
 #include "trace_output.h"	/* for trace_event_sem */
 #include "trace_dynevent.h"
 
-static DEFINE_MUTEX(dyn_event_ops_mutex);
+DEFINE_MUTEX(dyn_event_ops_mutex);
 static LIST_HEAD(dyn_event_ops_list);
 
 bool trace_event_dyn_try_get_ref(struct trace_event_call *dyn_call)
@@ -116,6 +116,20 @@ int dyn_event_release(const char *raw_command, struct dyn_event_operations *type
 	return ret;
 }
 
+/*
+ * Locked version of event creation. The event creation must be protected by
+ * dyn_event_ops_mutex because of protecting trace_probe_log.
+ */
+int dyn_event_create(const char *raw_command, struct dyn_event_operations *type)
+{
+	int ret;
+
+	mutex_lock(&dyn_event_ops_mutex);
+	ret = type->create(raw_command);
+	mutex_unlock(&dyn_event_ops_mutex);
+	return ret;
+}
+
 static int create_dyn_event(const char *raw_command)
 {
 	struct dyn_event_operations *ops;
diff --git a/kernel/trace/trace_dynevent.h b/kernel/trace/trace_dynevent.h
index 936477a111d3..beee3f8d7544 100644
--- a/kernel/trace/trace_dynevent.h
+++ b/kernel/trace/trace_dynevent.h
@@ -100,6 +100,7 @@ void *dyn_event_seq_next(struct seq_file *m, void *v, loff_t *pos);
 void dyn_event_seq_stop(struct seq_file *m, void *v);
 int dyn_events_release_all(struct dyn_event_operations *type);
 int dyn_event_release(const char *raw_command, struct dyn_event_operations *type);
+int dyn_event_create(const char *raw_command, struct dyn_event_operations *type);
 
 /*
  * for_each_dyn_event	-	iterate over the dyn_event list
diff --git a/kernel/trace/trace_entries.h b/kernel/trace/trace_entries.h
index 4ef4df6623a8..de294ae2c5c5 100644
--- a/kernel/trace/trace_entries.h
+++ b/kernel/trace/trace_entries.h
@@ -97,11 +97,11 @@ FTRACE_ENTRY_PACKED(fgraph_retaddr_entry, fgraph_retaddr_ent_entry,
 	F_STRUCT(
 		__field_struct(	struct fgraph_retaddr_ent,	graph_ent	)
 		__field_packed(	unsigned long,	graph_ent,	func		)
-		__field_packed(	int,		graph_ent,	depth		)
+		__field_packed(	unsigned int,	graph_ent,	depth		)
 		__field_packed(	unsigned long,	graph_ent,	retaddr		)
 	),
 
-	F_printk("--> %ps (%d) <- %ps", (void *)__entry->func, __entry->depth,
+	F_printk("--> %ps (%u) <- %ps", (void *)__entry->func, __entry->depth,
 		(void *)__entry->retaddr)
 );
 
@@ -124,13 +124,13 @@ FTRACE_ENTRY_PACKED(funcgraph_exit, ftrace_graph_ret_entry,
 		__field_struct(	struct ftrace_graph_ret,	ret	)
 		__field_packed(	unsigned long,	ret,		func	)
 		__field_packed(	unsigned long,	ret,		retval	)
-		__field_packed(	int,		ret,		depth	)
+		__field_packed(	unsigned int,	ret,		depth	)
 		__field_packed(	unsigned int,	ret,		overrun	)
 		__field(unsigned long long,	calltime		)
 		__field(unsigned long long,	rettime			)
 	),
 
-	F_printk("<-- %ps (%d) (start: %llx  end: %llx) over: %d retval: %lx",
+	F_printk("<-- %ps (%u) (start: %llx  end: %llx) over: %u retval: %lx",
 		 (void *)__entry->func, __entry->depth,
 		 __entry->calltime, __entry->rettime,
 		 __entry->depth, __entry->retval)
@@ -146,13 +146,13 @@ FTRACE_ENTRY_PACKED(funcgraph_exit, ftrace_graph_ret_entry,
 	F_STRUCT(
 		__field_struct(	struct ftrace_graph_ret,	ret	)
 		__field_packed(	unsigned long,	ret,		func	)
-		__field_packed(	int,		ret,		depth	)
+		__field_packed(	unsigned int,	ret,		depth	)
 		__field_packed(	unsigned int,	ret,		overrun	)
 		__field(unsigned long long,	calltime		)
 		__field(unsigned long long,	rettime			)
 	),
 
-	F_printk("<-- %ps (%d) (start: %llx  end: %llx) over: %d",
+	F_printk("<-- %ps (%u) (start: %llx  end: %llx) over: %u",
 		 (void *)__entry->func, __entry->depth,
 		 __entry->calltime, __entry->rettime,
 		 __entry->depth)
diff --git a/kernel/trace/trace_eprobe.c b/kernel/trace/trace_eprobe.c
index c08355c3ef32..916555f0de81 100644
--- a/kernel/trace/trace_eprobe.c
+++ b/kernel/trace/trace_eprobe.c
@@ -969,10 +969,13 @@ static int __trace_eprobe_create(int argc, const char *argv[])
 			goto error;
 		}
 	}
+	trace_probe_log_clear();
 	return ret;
+
 parse_error:
 	ret = -EINVAL;
 error:
+	trace_probe_log_clear();
 	trace_event_probe_cleanup(ep);
 	return ret;
 }
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 069e92856bda..120531268abf 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -400,6 +400,20 @@ static bool process_string(const char *fmt, int len, struct trace_event_call *ca
 	return true;
 }
 
+static void handle_dereference_arg(const char *arg_str, u64 string_flags, int len,
+				   u64 *dereference_flags, int arg,
+				   struct trace_event_call *call)
+{
+	if (string_flags & (1ULL << arg)) {
+		if (process_string(arg_str, len, call))
+			*dereference_flags &= ~(1ULL << arg);
+	} else if (process_pointer(arg_str, len, call))
+		*dereference_flags &= ~(1ULL << arg);
+	else
+		pr_warn("TRACE EVENT ERROR: Bad dereference argument: '%.*s'\n",
+			len, arg_str);
+}
+
 /*
  * Examine the print fmt of the event looking for unsafe dereference
  * pointers using %p* that could be recorded in the trace event and
@@ -563,11 +577,9 @@ static void test_event_printk(struct trace_event_call *call)
 			}
 
 			if (dereference_flags & (1ULL << arg)) {
-				if (string_flags & (1ULL << arg)) {
-					if (process_string(fmt + start_arg, e - start_arg, call))
-						dereference_flags &= ~(1ULL << arg);
-				} else if (process_pointer(fmt + start_arg, e - start_arg, call))
-					dereference_flags &= ~(1ULL << arg);
+				handle_dereference_arg(fmt + start_arg, string_flags,
+						       e - start_arg,
+						       &dereference_flags, arg, call);
 			}
 
 			start_arg = i;
@@ -578,11 +590,9 @@ static void test_event_printk(struct trace_event_call *call)
 	}
 
 	if (dereference_flags & (1ULL << arg)) {
-		if (string_flags & (1ULL << arg)) {
-			if (process_string(fmt + start_arg, i - start_arg, call))
-				dereference_flags &= ~(1ULL << arg);
-		} else if (process_pointer(fmt + start_arg, i - start_arg, call))
-			dereference_flags &= ~(1ULL << arg);
+		handle_dereference_arg(fmt + start_arg, string_flags,
+				       i - start_arg,
+				       &dereference_flags, arg, call);
 	}
 
 	/*
@@ -622,7 +632,6 @@ EXPORT_SYMBOL_GPL(trace_event_raw_init);
 bool trace_event_ignore_this_pid(struct trace_event_file *trace_file)
 {
 	struct trace_array *tr = trace_file->tr;
-	struct trace_array_cpu *data;
 	struct trace_pid_list *no_pid_list;
 	struct trace_pid_list *pid_list;
 
@@ -632,9 +641,11 @@ bool trace_event_ignore_this_pid(struct trace_event_file *trace_file)
 	if (!pid_list && !no_pid_list)
 		return false;
 
-	data = this_cpu_ptr(tr->array_buffer.data);
-
-	return data->ignore_pid;
+	/*
+	 * This is recorded at every sched_switch for this task.
+	 * Thus, even if the task migrates the ignore value will be the same.
+	 */
+	return this_cpu_read(tr->array_buffer.data->ignore_pid) != 0;
 }
 EXPORT_SYMBOL_GPL(trace_event_ignore_this_pid);
 
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index 2048560264bb..ea8b364b6818 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -1250,7 +1250,9 @@ static void append_filter_err(struct trace_array *tr,
 
 static inline struct event_filter *event_filter(struct trace_event_file *file)
 {
-	return file->filter;
+	return rcu_dereference_protected(file->filter,
+					 lockdep_is_held(&event_mutex));
+
 }
 
 /* caller must hold event_mutex */
@@ -1320,7 +1322,7 @@ void free_event_filter(struct event_filter *filter)
 static inline void __remove_filter(struct trace_event_file *file)
 {
 	filter_disable(file);
-	remove_filter_string(file->filter);
+	remove_filter_string(event_filter(file));
 }
 
 static void filter_free_subsystem_preds(struct trace_subsystem_dir *dir,
@@ -1335,22 +1337,139 @@ static void filter_free_subsystem_preds(struct trace_subsystem_dir *dir,
 	}
 }
 
+struct filter_list {
+	struct list_head	list;
+	struct event_filter	*filter;
+};
+
+struct filter_head {
+	struct list_head	list;
+	struct rcu_head		rcu;
+};
+
+
+static void free_filter_list(struct rcu_head *rhp)
+{
+	struct filter_head *filter_list = container_of(rhp, struct filter_head, rcu);
+	struct filter_list *filter_item, *tmp;
+
+	list_for_each_entry_safe(filter_item, tmp, &filter_list->list, list) {
+		__free_filter(filter_item->filter);
+		list_del(&filter_item->list);
+		kfree(filter_item);
+	}
+	kfree(filter_list);
+}
+
+static void free_filter_list_tasks(struct rcu_head *rhp)
+{
+	call_rcu(rhp, free_filter_list);
+}
+
+/*
+ * The tracepoint_synchronize_unregister() is a double rcu call.
+ * It calls synchronize_rcu_tasks_trace() followed by synchronize_rcu().
+ * Instead of waiting for it, simply call these via the call_rcu*()
+ * variants.
+ */
+static void delay_free_filter(struct filter_head *head)
+{
+	call_rcu_tasks_trace(&head->rcu, free_filter_list_tasks);
+}
+
+static void try_delay_free_filter(struct event_filter *filter)
+{
+	struct filter_head *head;
+	struct filter_list *item;
+
+	head = kmalloc(sizeof(*head), GFP_KERNEL);
+	if (!head)
+		goto free_now;
+
+	INIT_LIST_HEAD(&head->list);
+
+	item = kmalloc(sizeof(*item), GFP_KERNEL);
+	if (!item) {
+		kfree(head);
+		goto free_now;
+	}
+
+	item->filter = filter;
+	list_add_tail(&item->list, &head->list);
+	delay_free_filter(head);
+	return;
+
+ free_now:
+	/* Make sure the filter is not being used */
+	tracepoint_synchronize_unregister();
+	__free_filter(filter);
+}
+
 static inline void __free_subsystem_filter(struct trace_event_file *file)
 {
-	__free_filter(file->filter);
+	__free_filter(event_filter(file));
 	file->filter = NULL;
 }
 
+static inline void event_set_filter(struct trace_event_file *file,
+				    struct event_filter *filter)
+{
+	rcu_assign_pointer(file->filter, filter);
+}
+
+static inline void event_clear_filter(struct trace_event_file *file)
+{
+	RCU_INIT_POINTER(file->filter, NULL);
+}
+
 static void filter_free_subsystem_filters(struct trace_subsystem_dir *dir,
-					  struct trace_array *tr)
+					  struct trace_array *tr,
+					  struct event_filter *filter)
 {
 	struct trace_event_file *file;
+	struct filter_head *head;
+	struct filter_list *item;
+
+	head = kmalloc(sizeof(*head), GFP_KERNEL);
+	if (!head)
+		goto free_now;
+
+	INIT_LIST_HEAD(&head->list);
+
+	item = kmalloc(sizeof(*item), GFP_KERNEL);
+	if (!item) {
+		kfree(head);
+		goto free_now;
+	}
+
+	item->filter = filter;
+	list_add_tail(&item->list, &head->list);
 
 	list_for_each_entry(file, &tr->events, list) {
 		if (file->system != dir)
 			continue;
+		item = kmalloc(sizeof(*item), GFP_KERNEL);
+		if (!item)
+			goto free_now;
+		item->filter = event_filter(file);
+		list_add_tail(&item->list, &head->list);
+		event_clear_filter(file);
+	}
+
+	delay_free_filter(head);
+	return;
+ free_now:
+	tracepoint_synchronize_unregister();
+
+	if (head)
+		free_filter_list(&head->rcu);
+
+	list_for_each_entry(file, &tr->events, list) {
+		if (file->system != dir || !file->filter)
+			continue;
 		__free_subsystem_filter(file);
 	}
+	__free_filter(filter);
 }
 
 int filter_assign_type(const char *type)
@@ -2120,22 +2239,6 @@ static inline void event_set_filtered_flag(struct trace_event_file *file)
 		trace_buffered_event_enable();
 }
 
-static inline void event_set_filter(struct trace_event_file *file,
-				    struct event_filter *filter)
-{
-	rcu_assign_pointer(file->filter, filter);
-}
-
-static inline void event_clear_filter(struct trace_event_file *file)
-{
-	RCU_INIT_POINTER(file->filter, NULL);
-}
-
-struct filter_list {
-	struct list_head	list;
-	struct event_filter	*filter;
-};
-
 static int process_system_preds(struct trace_subsystem_dir *dir,
 				struct trace_array *tr,
 				struct filter_parse_error *pe,
@@ -2144,11 +2247,16 @@ static int process_system_preds(struct trace_subsystem_dir *dir,
 	struct trace_event_file *file;
 	struct filter_list *filter_item;
 	struct event_filter *filter = NULL;
-	struct filter_list *tmp;
-	LIST_HEAD(filter_list);
+	struct filter_head *filter_list;
 	bool fail = true;
 	int err;
 
+	filter_list = kmalloc(sizeof(*filter_list), GFP_KERNEL);
+	if (!filter_list)
+		return -ENOMEM;
+
+	INIT_LIST_HEAD(&filter_list->list);
+
 	list_for_each_entry(file, &tr->events, list) {
 
 		if (file->system != dir)
@@ -2175,7 +2283,7 @@ static int process_system_preds(struct trace_subsystem_dir *dir,
 		if (!filter_item)
 			goto fail_mem;
 
-		list_add_tail(&filter_item->list, &filter_list);
+		list_add_tail(&filter_item->list, &filter_list->list);
 		/*
 		 * Regardless of if this returned an error, we still
 		 * replace the filter for the call.
@@ -2195,31 +2303,22 @@ static int process_system_preds(struct trace_subsystem_dir *dir,
 	 * Do a synchronize_rcu() and to ensure all calls are
 	 * done with them before we free them.
 	 */
-	tracepoint_synchronize_unregister();
-	list_for_each_entry_safe(filter_item, tmp, &filter_list, list) {
-		__free_filter(filter_item->filter);
-		list_del(&filter_item->list);
-		kfree(filter_item);
-	}
+	delay_free_filter(filter_list);
 	return 0;
  fail:
 	/* No call succeeded */
-	list_for_each_entry_safe(filter_item, tmp, &filter_list, list) {
-		list_del(&filter_item->list);
-		kfree(filter_item);
-	}
+	free_filter_list(&filter_list->rcu);
 	parse_error(pe, FILT_ERR_BAD_SUBSYS_FILTER, 0);
 	return -EINVAL;
  fail_mem:
 	__free_filter(filter);
+
 	/* If any call succeeded, we still need to sync */
 	if (!fail)
-		tracepoint_synchronize_unregister();
-	list_for_each_entry_safe(filter_item, tmp, &filter_list, list) {
-		__free_filter(filter_item->filter);
-		list_del(&filter_item->list);
-		kfree(filter_item);
-	}
+		delay_free_filter(filter_list);
+	else
+		free_filter_list(&filter_list->rcu);
+
 	return -ENOMEM;
 }
 
@@ -2361,9 +2460,7 @@ int apply_event_filter(struct trace_event_file *file, char *filter_string)
 
 		event_clear_filter(file);
 
-		/* Make sure the filter is not being used */
-		tracepoint_synchronize_unregister();
-		__free_filter(filter);
+		try_delay_free_filter(filter);
 
 		return 0;
 	}
@@ -2387,11 +2484,8 @@ int apply_event_filter(struct trace_event_file *file, char *filter_string)
 
 		event_set_filter(file, filter);
 
-		if (tmp) {
-			/* Make sure the call is done with the filter */
-			tracepoint_synchronize_unregister();
-			__free_filter(tmp);
-		}
+		if (tmp)
+			try_delay_free_filter(tmp);
 	}
 
 	return err;
@@ -2417,9 +2511,7 @@ int apply_subsystem_event_filter(struct trace_subsystem_dir *dir,
 		filter = system->filter;
 		system->filter = NULL;
 		/* Ensure all filters are no longer used */
-		tracepoint_synchronize_unregister();
-		filter_free_subsystem_filters(dir, tr);
-		__free_filter(filter);
+		filter_free_subsystem_filters(dir, tr, filter);
 		return 0;
 	}
 
diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
index 1260c23cfa5f..1d536219b624 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -114,6 +114,7 @@ enum hist_field_fn {
 	HIST_FIELD_FN_BUCKET,
 	HIST_FIELD_FN_TIMESTAMP,
 	HIST_FIELD_FN_CPU,
+	HIST_FIELD_FN_COMM,
 	HIST_FIELD_FN_STRING,
 	HIST_FIELD_FN_DYNSTRING,
 	HIST_FIELD_FN_RELDYNSTRING,
@@ -506,6 +507,7 @@ enum hist_field_flags {
 	HIST_FIELD_FL_CONST		= 1 << 18,
 	HIST_FIELD_FL_PERCENT		= 1 << 19,
 	HIST_FIELD_FL_GRAPH		= 1 << 20,
+	HIST_FIELD_FL_COMM		= 1 << 21,
 };
 
 struct var_defs {
@@ -885,6 +887,15 @@ static u64 hist_field_cpu(struct hist_field *hist_field,
 	return cpu;
 }
 
+static u64 hist_field_comm(struct hist_field *hist_field,
+			  struct tracing_map_elt *elt,
+			  struct trace_buffer *buffer,
+			  struct ring_buffer_event *rbe,
+			  void *event)
+{
+	return (u64)(unsigned long)current->comm;
+}
+
 /**
  * check_field_for_var_ref - Check if a VAR_REF field references a variable
  * @hist_field: The VAR_REF field to check
@@ -1338,6 +1349,8 @@ static const char *hist_field_name(struct hist_field *field,
 		field_name = hist_field_name(field->operands[0], ++level);
 	else if (field->flags & HIST_FIELD_FL_CPU)
 		field_name = "common_cpu";
+	else if (field->flags & HIST_FIELD_FL_COMM)
+		field_name = "common_comm";
 	else if (field->flags & HIST_FIELD_FL_EXPR ||
 		 field->flags & HIST_FIELD_FL_VAR_REF) {
 		if (field->system) {
@@ -2015,6 +2028,13 @@ static struct hist_field *create_hist_field(struct hist_trigger_data *hist_data,
 		goto out;
 	}
 
+	if (flags & HIST_FIELD_FL_COMM) {
+		hist_field->fn_num = HIST_FIELD_FN_COMM;
+		hist_field->size = MAX_FILTER_STR_VAL;
+		hist_field->type = "char[]";
+		goto out;
+	}
+
 	if (WARN_ON_ONCE(!field))
 		goto out;
 
@@ -2359,9 +2379,11 @@ parse_field(struct hist_trigger_data *hist_data, struct trace_event_file *file,
 			hist_data->attrs->ts_in_usecs = true;
 	} else if (strcmp(field_name, "common_stacktrace") == 0) {
 		*flags |= HIST_FIELD_FL_STACKTRACE;
-	} else if (strcmp(field_name, "common_cpu") == 0)
+	} else if (strcmp(field_name, "common_cpu") == 0) {
 		*flags |= HIST_FIELD_FL_CPU;
-	else if (strcmp(field_name, "hitcount") == 0)
+	} else if (strcmp(field_name, "common_comm") == 0) {
+		*flags |= HIST_FIELD_FL_COMM | HIST_FIELD_FL_STRING;
+	} else if (strcmp(field_name, "hitcount") == 0)
 		*flags |= HIST_FIELD_FL_HITCOUNT;
 	else {
 		field = trace_find_event_field(file->event_call, field_name);
@@ -2377,6 +2399,8 @@ parse_field(struct hist_trigger_data *hist_data, struct trace_event_file *file,
 				*flags |= HIST_FIELD_FL_CPU;
 			} else if (field && field->filter_type == FILTER_STACKTRACE) {
 				*flags |= HIST_FIELD_FL_STACKTRACE;
+			} else if (field && field->filter_type == FILTER_COMM) {
+				*flags |= HIST_FIELD_FL_COMM | HIST_FIELD_FL_STRING;
 			} else {
 				hist_err(tr, HIST_ERR_FIELD_NOT_FOUND,
 					 errpos(field_name));
@@ -4327,6 +4351,8 @@ static u64 hist_fn_call(struct hist_field *hist_field,
 		return hist_field_timestamp(hist_field, elt, buffer, rbe, event);
 	case HIST_FIELD_FN_CPU:
 		return hist_field_cpu(hist_field, elt, buffer, rbe, event);
+	case HIST_FIELD_FN_COMM:
+		return hist_field_comm(hist_field, elt, buffer, rbe, event);
 	case HIST_FIELD_FN_STRING:
 		return hist_field_string(hist_field, elt, buffer, rbe, event);
 	case HIST_FIELD_FN_DYNSTRING:
@@ -5212,22 +5238,25 @@ static inline void add_to_key(char *compound_key, void *key,
 	size_t size = key_field->size;
 
 	if (key_field->flags & HIST_FIELD_FL_STRING) {
-		struct ftrace_event_field *field;
 
-		field = key_field->field;
-		if (field->filter_type == FILTER_DYN_STRING ||
-		    field->filter_type == FILTER_RDYN_STRING)
-			size = *(u32 *)(rec + field->offset) >> 16;
-		else if (field->filter_type == FILTER_STATIC_STRING)
-			size = field->size;
+		if (key_field->flags & HIST_FIELD_FL_COMM) {
+			size = strlen((char *)key);
+		} else {
+			struct ftrace_event_field *field;
+
+			field = key_field->field;
+			if (field->filter_type == FILTER_DYN_STRING ||
+			    field->filter_type == FILTER_RDYN_STRING)
+				size = *(u32 *)(rec + field->offset) >> 16;
+			else if (field->filter_type == FILTER_STATIC_STRING)
+				size = field->size;
+		}
 
 		/* ensure NULL-termination */
 		if (size > key_field->size - 1)
 			size = key_field->size - 1;
-
-		strncpy(compound_key + key_field->offset, (char *)key, size);
-	} else
-		memcpy(compound_key + key_field->offset, key, size);
+	}
+	memcpy(compound_key + key_field->offset, key, size);
 }
 
 static void
@@ -5246,17 +5275,94 @@ hist_trigger_actions(struct hist_trigger_data *hist_data,
 	}
 }
 
+/*
+ * The hist_pad structure is used to save information to create
+ * a histogram from the histogram trigger. It's too big to store
+ * on the stack, so when the histogram trigger is initialized
+ * a percpu array of 4 hist_pad structures is allocated.
+ * This will cover every context from normal, softirq, irq and NMI
+ * in the very unlikely event that a tigger happens at each of
+ * these contexts and interrupts a currently active trigger.
+ */
+struct hist_pad {
+	unsigned long		entries[HIST_STACKTRACE_DEPTH];
+	u64			var_ref_vals[TRACING_MAP_VARS_MAX];
+	char			compound_key[HIST_KEY_SIZE_MAX];
+};
+
+static struct hist_pad __percpu *hist_pads;
+static DEFINE_PER_CPU(int, hist_pad_cnt);
+static refcount_t hist_pad_ref;
+
+/* One hist_pad for every context (normal, softirq, irq, NMI) */
+#define MAX_HIST_CNT 4
+
+static int alloc_hist_pad(void)
+{
+	lockdep_assert_held(&event_mutex);
+
+	if (refcount_read(&hist_pad_ref)) {
+		refcount_inc(&hist_pad_ref);
+		return 0;
+	}
+
+	hist_pads = __alloc_percpu(sizeof(struct hist_pad) * MAX_HIST_CNT,
+				   __alignof__(struct hist_pad));
+	if (!hist_pads)
+		return -ENOMEM;
+
+	refcount_set(&hist_pad_ref, 1);
+	return 0;
+}
+
+static void free_hist_pad(void)
+{
+	lockdep_assert_held(&event_mutex);
+
+	if (!refcount_dec_and_test(&hist_pad_ref))
+		return;
+
+	free_percpu(hist_pads);
+	hist_pads = NULL;
+}
+
+static struct hist_pad *get_hist_pad(void)
+{
+	struct hist_pad *hist_pad;
+	int cnt;
+
+	if (WARN_ON_ONCE(!hist_pads))
+		return NULL;
+
+	preempt_disable();
+
+	hist_pad = per_cpu_ptr(hist_pads, smp_processor_id());
+
+	if (this_cpu_read(hist_pad_cnt) == MAX_HIST_CNT) {
+		preempt_enable();
+		return NULL;
+	}
+
+	cnt = this_cpu_inc_return(hist_pad_cnt) - 1;
+
+	return &hist_pad[cnt];
+}
+
+static void put_hist_pad(void)
+{
+	this_cpu_dec(hist_pad_cnt);
+	preempt_enable();
+}
+
 static void event_hist_trigger(struct event_trigger_data *data,
 			       struct trace_buffer *buffer, void *rec,
 			       struct ring_buffer_event *rbe)
 {
 	struct hist_trigger_data *hist_data = data->private_data;
 	bool use_compound_key = (hist_data->n_keys > 1);
-	unsigned long entries[HIST_STACKTRACE_DEPTH];
-	u64 var_ref_vals[TRACING_MAP_VARS_MAX];
-	char compound_key[HIST_KEY_SIZE_MAX];
 	struct tracing_map_elt *elt = NULL;
 	struct hist_field *key_field;
+	struct hist_pad *hist_pad;
 	u64 field_contents;
 	void *key = NULL;
 	unsigned int i;
@@ -5264,12 +5370,18 @@ static void event_hist_trigger(struct event_trigger_data *data,
 	if (unlikely(!rbe))
 		return;
 
-	memset(compound_key, 0, hist_data->key_size);
+	hist_pad = get_hist_pad();
+	if (!hist_pad)
+		return;
+
+	memset(hist_pad->compound_key, 0, hist_data->key_size);
 
 	for_each_hist_key_field(i, hist_data) {
 		key_field = hist_data->fields[i];
 
 		if (key_field->flags & HIST_FIELD_FL_STACKTRACE) {
+			unsigned long *entries = hist_pad->entries;
+
 			memset(entries, 0, HIST_STACKTRACE_SIZE);
 			if (key_field->field) {
 				unsigned long *stack, n_entries;
@@ -5293,26 +5405,31 @@ static void event_hist_trigger(struct event_trigger_data *data,
 		}
 
 		if (use_compound_key)
-			add_to_key(compound_key, key, key_field, rec);
+			add_to_key(hist_pad->compound_key, key, key_field, rec);
 	}
 
 	if (use_compound_key)
-		key = compound_key;
+		key = hist_pad->compound_key;
 
 	if (hist_data->n_var_refs &&
-	    !resolve_var_refs(hist_data, key, var_ref_vals, false))
-		return;
+	    !resolve_var_refs(hist_data, key, hist_pad->var_ref_vals, false))
+		goto out;
 
 	elt = tracing_map_insert(hist_data->map, key);
 	if (!elt)
-		return;
+		goto out;
 
-	hist_trigger_elt_update(hist_data, elt, buffer, rec, rbe, var_ref_vals);
+	hist_trigger_elt_update(hist_data, elt, buffer, rec, rbe, hist_pad->var_ref_vals);
 
-	if (resolve_var_refs(hist_data, key, var_ref_vals, true))
-		hist_trigger_actions(hist_data, elt, buffer, rec, rbe, key, var_ref_vals);
+	if (resolve_var_refs(hist_data, key, hist_pad->var_ref_vals, true)) {
+		hist_trigger_actions(hist_data, elt, buffer, rec, rbe,
+				     key, hist_pad->var_ref_vals);
+	}
 
 	hist_poll_wakeup();
+
+ out:
+	put_hist_pad();
 }
 
 static void hist_trigger_stacktrace_print(struct seq_file *m,
@@ -6011,6 +6128,8 @@ static void hist_field_print(struct seq_file *m, struct hist_field *hist_field)
 
 	if (hist_field->flags & HIST_FIELD_FL_CPU)
 		seq_puts(m, "common_cpu");
+	if (hist_field->flags & HIST_FIELD_FL_COMM)
+		seq_puts(m, "common_comm");
 	else if (hist_field->flags & HIST_FIELD_FL_CONST)
 		seq_printf(m, "%llu", hist_field->constant);
 	else if (field_name) {
@@ -6157,6 +6276,9 @@ static int event_hist_trigger_init(struct event_trigger_data *data)
 {
 	struct hist_trigger_data *hist_data = data->private_data;
 
+	if (alloc_hist_pad() < 0)
+		return -ENOMEM;
+
 	if (!data->ref && hist_data->attrs->name)
 		save_named_trigger(hist_data->attrs->name, data);
 
@@ -6201,6 +6323,7 @@ static void event_hist_trigger_free(struct event_trigger_data *data)
 
 		destroy_hist_data(hist_data);
 	}
+	free_hist_pad();
 }
 
 static const struct event_trigger_ops event_hist_trigger_ops = {
@@ -6216,9 +6339,7 @@ static int event_hist_trigger_named_init(struct event_trigger_data *data)
 
 	save_named_trigger(data->named_data->name, data);
 
-	event_hist_trigger_init(data->named_data);
-
-	return 0;
+	return event_hist_trigger_init(data->named_data);
 }
 
 static void event_hist_trigger_named_free(struct event_trigger_data *data)
@@ -6705,7 +6826,7 @@ static int event_hist_trigger_parse(struct event_command *cmd_ops,
 		return PTR_ERR(hist_data);
 	}
 
-	trigger_data = event_trigger_alloc(cmd_ops, cmd, param, hist_data);
+	trigger_data = trigger_data_alloc(cmd_ops, cmd, param, hist_data);
 	if (!trigger_data) {
 		ret = -ENOMEM;
 		goto out_free;
diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c
index b66b6d235d91..cbfc306c0159 100644
--- a/kernel/trace/trace_events_trigger.c
+++ b/kernel/trace/trace_events_trigger.c
@@ -552,16 +552,14 @@ static int register_trigger(char *glob,
 	lockdep_assert_held(&event_mutex);
 
 	list_for_each_entry(test, &file->triggers, list) {
-		if (test->cmd_ops->trigger_type == data->cmd_ops->trigger_type) {
-			ret = -EEXIST;
-			goto out;
-		}
+		if (test->cmd_ops->trigger_type == data->cmd_ops->trigger_type)
+			return -EEXIST;
 	}
 
 	if (data->ops->init) {
 		ret = data->ops->init(data);
 		if (ret < 0)
-			goto out;
+			return ret;
 	}
 
 	list_add_rcu(&data->list, &file->triggers);
@@ -572,7 +570,6 @@ static int register_trigger(char *glob,
 		list_del_rcu(&data->list);
 		update_cond_flag(file);
 	}
-out:
 	return ret;
 }
 
@@ -770,7 +767,7 @@ int event_trigger_separate_filter(char *param_and_filter, char **param,
 	if (!param_and_filter) {
 		if (param_required)
 			ret = -EINVAL;
-		goto out;
+		return ret;
 	}
 
 	/*
@@ -781,7 +778,7 @@ int event_trigger_separate_filter(char *param_and_filter, char **param,
 	 */
 	if (!param_required && param_and_filter && !isdigit(param_and_filter[0])) {
 		*filter = param_and_filter;
-		goto out;
+		return ret;
 	}
 
 	/*
@@ -799,12 +796,11 @@ int event_trigger_separate_filter(char *param_and_filter, char **param,
 		if (!**filter)
 			*filter = NULL;
 	}
-out:
 	return ret;
 }
 
 /**
- * event_trigger_alloc - allocate and init event_trigger_data for a trigger
+ * trigger_data_alloc - allocate and init event_trigger_data for a trigger
  * @cmd_ops: The event_command operations for the trigger
  * @cmd: The cmd string
  * @param: The param string
@@ -815,14 +811,14 @@ out:
  * trigger_ops to assign to the event_trigger_data.  @private_data can
  * also be passed in and associated with the event_trigger_data.
  *
- * Use event_trigger_free() to free an event_trigger_data object.
+ * Use trigger_data_free() to free an event_trigger_data object.
  *
  * Return: The trigger_data object success, NULL otherwise
  */
-struct event_trigger_data *event_trigger_alloc(struct event_command *cmd_ops,
-					       char *cmd,
-					       char *param,
-					       void *private_data)
+struct event_trigger_data *trigger_data_alloc(struct event_command *cmd_ops,
+					      char *cmd,
+					      char *param,
+					      void *private_data)
 {
 	struct event_trigger_data *trigger_data;
 	const struct event_trigger_ops *trigger_ops;
@@ -989,15 +985,14 @@ event_trigger_parse(struct event_command *cmd_ops,
 		return ret;
 
 	ret = -ENOMEM;
-	trigger_data = event_trigger_alloc(cmd_ops, cmd, param, file);
+	trigger_data = trigger_data_alloc(cmd_ops, cmd, param, file);
 	if (!trigger_data)
-		goto out;
+		return ret;
 
 	if (remove) {
 		event_trigger_unregister(cmd_ops, file, glob+1, trigger_data);
-		kfree(trigger_data);
-		ret = 0;
-		goto out;
+		trigger_data_free(trigger_data);
+		return 0;
 	}
 
 	ret = event_trigger_parse_num(param, trigger_data);
@@ -1017,13 +1012,12 @@ event_trigger_parse(struct event_command *cmd_ops,
 
 	/* Down the counter of trigger_data or free it if not used anymore */
 	event_trigger_free(trigger_data);
- out:
 	return ret;
 
  out_free:
 	event_trigger_reset_filter(cmd_ops, trigger_data);
-	kfree(trigger_data);
-	goto out;
+	trigger_data_free(trigger_data);
+	return ret;
 }
 
 /**
@@ -1057,10 +1051,10 @@ int set_trigger_filter(char *filter_str,
 	s = strsep(&filter_str, " \t");
 
 	if (!strlen(s) || strcmp(s, "if") != 0)
-		goto out;
+		return ret;
 
 	if (!filter_str)
-		goto out;
+		return ret;
 
 	/* The filter is for the 'trigger' event, not the triggered event */
 	ret = create_event_filter(file->tr, file->event_call,
@@ -1104,7 +1098,6 @@ int set_trigger_filter(char *filter_str,
 			ret = -ENOMEM;
 		}
 	}
- out:
 	return ret;
 }
 
@@ -1560,7 +1553,7 @@ stacktrace_trigger(struct event_trigger_data *data,
 	struct trace_event_file *file = data->private_data;
 
 	if (file)
-		__trace_stack(file->tr, tracing_gen_ctx(), STACK_SKIP);
+		__trace_stack(file->tr, tracing_gen_ctx_dec(), STACK_SKIP);
 	else
 		trace_dump_stack(STACK_SKIP);
 }
@@ -1772,7 +1765,7 @@ int event_enable_trigger_parse(struct event_command *cmd_ops,
 	ret = -EINVAL;
 	event_enable_file = find_event_file(tr, system, event);
 	if (!event_enable_file)
-		goto out;
+		return ret;
 
 #ifdef CONFIG_HIST_TRIGGERS
 	hist = ((strcmp(cmd, ENABLE_HIST_STR) == 0) ||
@@ -1787,16 +1780,16 @@ int event_enable_trigger_parse(struct event_command *cmd_ops,
 
 	enable_data = kzalloc(sizeof(*enable_data), GFP_KERNEL);
 	if (!enable_data)
-		goto out;
+		return ret;
 
 	enable_data->hist = hist;
 	enable_data->enable = enable;
 	enable_data->file = event_enable_file;
 
-	trigger_data = event_trigger_alloc(cmd_ops, cmd, param, enable_data);
+	trigger_data = trigger_data_alloc(cmd_ops, cmd, param, enable_data);
 	if (!trigger_data) {
 		kfree(enable_data);
-		goto out;
+		return ret;
 	}
 
 	if (remove) {
@@ -1804,7 +1797,7 @@ int event_enable_trigger_parse(struct event_command *cmd_ops,
 		kfree(trigger_data);
 		kfree(enable_data);
 		ret = 0;
-		goto out;
+		return ret;
 	}
 
 	/* Up the trigger_data count to make sure nothing frees it on failure */
@@ -1834,7 +1827,6 @@ int event_enable_trigger_parse(struct event_command *cmd_ops,
 		goto out_disable;
 
 	event_trigger_free(trigger_data);
- out:
 	return ret;
  out_disable:
 	trace_event_enable_disable(event_enable_file, 0, 1);
@@ -1845,7 +1837,7 @@ int event_enable_trigger_parse(struct event_command *cmd_ops,
 	event_trigger_free(trigger_data);
 	kfree(enable_data);
 
-	goto out;
+	return ret;
 }
 
 int event_enable_register_trigger(char *glob,
@@ -1865,15 +1857,14 @@ int event_enable_register_trigger(char *glob,
 		    (test->cmd_ops->trigger_type ==
 		     data->cmd_ops->trigger_type) &&
 		    (test_enable_data->file == enable_data->file)) {
-			ret = -EEXIST;
-			goto out;
+			return -EEXIST;
 		}
 	}
 
 	if (data->ops->init) {
 		ret = data->ops->init(data);
 		if (ret < 0)
-			goto out;
+			return ret;
 	}
 
 	list_add_rcu(&data->list, &file->triggers);
@@ -1884,7 +1875,6 @@ int event_enable_register_trigger(char *glob,
 		list_del_rcu(&data->list);
 		update_cond_flag(file);
 	}
-out:
 	return ret;
 }
 
diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c
index 98ccf3f00c51..d17c18934445 100644
--- a/kernel/trace/trace_functions.c
+++ b/kernel/trace/trace_functions.c
@@ -209,7 +209,6 @@ function_trace_call(unsigned long ip, unsigned long parent_ip,
 		    struct ftrace_ops *op, struct ftrace_regs *fregs)
 {
 	struct trace_array *tr = op->private;
-	struct trace_array_cpu *data;
 	unsigned int trace_ctx;
 	int bit;
 
@@ -224,9 +223,7 @@ function_trace_call(unsigned long ip, unsigned long parent_ip,
 
 	trace_ctx = tracing_gen_ctx_dec();
 
-	data = this_cpu_ptr(tr->array_buffer.data);
-	if (!atomic_read(&data->disabled))
-		trace_function(tr, ip, parent_ip, trace_ctx, NULL);
+	trace_function(tr, ip, parent_ip, trace_ctx, NULL);
 
 	ftrace_test_recursion_unlock(bit);
 }
@@ -236,10 +233,8 @@ function_args_trace_call(unsigned long ip, unsigned long parent_ip,
 			 struct ftrace_ops *op, struct ftrace_regs *fregs)
 {
 	struct trace_array *tr = op->private;
-	struct trace_array_cpu *data;
 	unsigned int trace_ctx;
 	int bit;
-	int cpu;
 
 	if (unlikely(!tr->function_enabled))
 		return;
@@ -250,10 +245,7 @@ function_args_trace_call(unsigned long ip, unsigned long parent_ip,
 
 	trace_ctx = tracing_gen_ctx();
 
-	cpu = smp_processor_id();
-	data = per_cpu_ptr(tr->array_buffer.data, cpu);
-	if (!atomic_read(&data->disabled))
-		trace_function(tr, ip, parent_ip, trace_ctx, fregs);
+	trace_function(tr, ip, parent_ip, trace_ctx, fregs);
 
 	ftrace_test_recursion_unlock(bit);
 }
@@ -299,7 +291,7 @@ function_stack_trace_call(unsigned long ip, unsigned long parent_ip,
 	parent_ip = function_get_true_parent_ip(parent_ip, fregs);
 	cpu = raw_smp_processor_id();
 	data = per_cpu_ptr(tr->array_buffer.data, cpu);
-	disabled = atomic_inc_return(&data->disabled);
+	disabled = local_inc_return(&data->disabled);
 
 	if (likely(disabled == 1)) {
 		trace_ctx = tracing_gen_ctx_flags(flags);
@@ -311,7 +303,7 @@ function_stack_trace_call(unsigned long ip, unsigned long parent_ip,
 		__trace_stack(tr, trace_ctx, skip);
 	}
 
-	atomic_dec(&data->disabled);
+	local_dec(&data->disabled);
 	local_irq_restore(flags);
 }
 
@@ -352,7 +344,6 @@ function_no_repeats_trace_call(unsigned long ip, unsigned long parent_ip,
 {
 	struct trace_func_repeats *last_info;
 	struct trace_array *tr = op->private;
-	struct trace_array_cpu *data;
 	unsigned int trace_ctx;
 	int bit;
 
@@ -364,8 +355,7 @@ function_no_repeats_trace_call(unsigned long ip, unsigned long parent_ip,
 		return;
 
 	parent_ip = function_get_true_parent_ip(parent_ip, fregs);
-	data = this_cpu_ptr(tr->array_buffer.data);
-	if (atomic_read(&data->disabled))
+	if (!tracer_tracing_is_on(tr))
 		goto out;
 
 	/*
@@ -412,7 +402,7 @@ function_stack_no_repeats_trace_call(unsigned long ip, unsigned long parent_ip,
 	parent_ip = function_get_true_parent_ip(parent_ip, fregs);
 	cpu = raw_smp_processor_id();
 	data = per_cpu_ptr(tr->array_buffer.data, cpu);
-	disabled = atomic_inc_return(&data->disabled);
+	disabled = local_inc_return(&data->disabled);
 
 	if (likely(disabled == 1)) {
 		last_info = per_cpu_ptr(tr->last_func_repeats, cpu);
@@ -427,7 +417,7 @@ function_stack_no_repeats_trace_call(unsigned long ip, unsigned long parent_ip,
 	}
 
  out:
-	atomic_dec(&data->disabled);
+	local_dec(&data->disabled);
 	local_irq_restore(flags);
 }
 
@@ -633,11 +623,7 @@ ftrace_traceoff(unsigned long ip, unsigned long parent_ip,
 
 static __always_inline void trace_stack(struct trace_array *tr)
 {
-	unsigned int trace_ctx;
-
-	trace_ctx = tracing_gen_ctx();
-
-	__trace_stack(tr, trace_ctx, FTRACE_STACK_SKIP);
+	__trace_stack(tr, tracing_gen_ctx_dec(), FTRACE_STACK_SKIP);
 }
 
 static void
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index 0c357a89c58e..9234e2c39abf 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -202,12 +202,9 @@ static int graph_entry(struct ftrace_graph_ent *trace,
 {
 	unsigned long *task_var = fgraph_get_task_var(gops);
 	struct trace_array *tr = gops->private;
-	struct trace_array_cpu *data;
 	struct fgraph_times *ftimes;
 	unsigned int trace_ctx;
-	long disabled;
 	int ret = 0;
-	int cpu;
 
 	if (*task_var & TRACE_GRAPH_NOTRACE)
 		return 0;
@@ -257,21 +254,14 @@ static int graph_entry(struct ftrace_graph_ent *trace,
 	if (tracing_thresh)
 		return 1;
 
-	preempt_disable_notrace();
-	cpu = raw_smp_processor_id();
-	data = per_cpu_ptr(tr->array_buffer.data, cpu);
-	disabled = atomic_read(&data->disabled);
-	if (likely(!disabled)) {
-		trace_ctx = tracing_gen_ctx();
-		if (IS_ENABLED(CONFIG_FUNCTION_GRAPH_RETADDR) &&
-		    tracer_flags_is_set(TRACE_GRAPH_PRINT_RETADDR)) {
-			unsigned long retaddr = ftrace_graph_top_ret_addr(current);
-			ret = __trace_graph_retaddr_entry(tr, trace, trace_ctx, retaddr);
-		} else {
-			ret = __graph_entry(tr, trace, trace_ctx, fregs);
-		}
+	trace_ctx = tracing_gen_ctx();
+	if (IS_ENABLED(CONFIG_FUNCTION_GRAPH_RETADDR) &&
+	    tracer_flags_is_set(TRACE_GRAPH_PRINT_RETADDR)) {
+		unsigned long retaddr = ftrace_graph_top_ret_addr(current);
+		ret = __trace_graph_retaddr_entry(tr, trace, trace_ctx, retaddr);
+	} else {
+		ret = __graph_entry(tr, trace, trace_ctx, fregs);
 	}
-	preempt_enable_notrace();
 
 	return ret;
 }
@@ -351,13 +341,10 @@ void trace_graph_return(struct ftrace_graph_ret *trace,
 {
 	unsigned long *task_var = fgraph_get_task_var(gops);
 	struct trace_array *tr = gops->private;
-	struct trace_array_cpu *data;
 	struct fgraph_times *ftimes;
 	unsigned int trace_ctx;
 	u64 calltime, rettime;
-	long disabled;
 	int size;
-	int cpu;
 
 	rettime = trace_clock_local();
 
@@ -376,15 +363,8 @@ void trace_graph_return(struct ftrace_graph_ret *trace,
 
 	calltime = ftimes->calltime;
 
-	preempt_disable_notrace();
-	cpu = raw_smp_processor_id();
-	data = per_cpu_ptr(tr->array_buffer.data, cpu);
-	disabled = atomic_read(&data->disabled);
-	if (likely(!disabled)) {
-		trace_ctx = tracing_gen_ctx();
-		__trace_graph_return(tr, trace, trace_ctx, calltime, rettime);
-	}
-	preempt_enable_notrace();
+	trace_ctx = tracing_gen_ctx();
+	__trace_graph_return(tr, trace, trace_ctx, calltime, rettime);
 }
 
 static void trace_graph_thresh_return(struct ftrace_graph_ret *trace,
diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c
index 40c39e946940..5496758b6c76 100644
--- a/kernel/trace/trace_irqsoff.c
+++ b/kernel/trace/trace_irqsoff.c
@@ -123,12 +123,12 @@ static int func_prolog_dec(struct trace_array *tr,
 		return 0;
 
 	*data = per_cpu_ptr(tr->array_buffer.data, cpu);
-	disabled = atomic_inc_return(&(*data)->disabled);
+	disabled = local_inc_return(&(*data)->disabled);
 
 	if (likely(disabled == 1))
 		return 1;
 
-	atomic_dec(&(*data)->disabled);
+	local_dec(&(*data)->disabled);
 
 	return 0;
 }
@@ -152,7 +152,7 @@ irqsoff_tracer_call(unsigned long ip, unsigned long parent_ip,
 
 	trace_function(tr, ip, parent_ip, trace_ctx, fregs);
 
-	atomic_dec(&data->disabled);
+	local_dec(&data->disabled);
 }
 #endif /* CONFIG_FUNCTION_TRACER */
 
@@ -209,7 +209,7 @@ static int irqsoff_graph_entry(struct ftrace_graph_ent *trace,
 
 	trace_ctx = tracing_gen_ctx_flags(flags);
 	ret = __trace_graph_entry(tr, trace, trace_ctx);
-	atomic_dec(&data->disabled);
+	local_dec(&data->disabled);
 
 	return ret;
 }
@@ -238,7 +238,7 @@ static void irqsoff_graph_return(struct ftrace_graph_ret *trace,
 
 	trace_ctx = tracing_gen_ctx_flags(flags);
 	__trace_graph_return(tr, trace, trace_ctx, *calltime, rettime);
-	atomic_dec(&data->disabled);
+	local_dec(&data->disabled);
 }
 
 static struct fgraph_ops fgraph_ops = {
@@ -397,6 +397,7 @@ start_critical_timing(unsigned long ip, unsigned long parent_ip)
 	int cpu;
 	struct trace_array *tr = irqsoff_trace;
 	struct trace_array_cpu *data;
+	long disabled;
 
 	if (!tracer_enabled || !tracing_is_enabled())
 		return;
@@ -408,20 +409,22 @@ start_critical_timing(unsigned long ip, unsigned long parent_ip)
 
 	data = per_cpu_ptr(tr->array_buffer.data, cpu);
 
-	if (unlikely(!data) || atomic_read(&data->disabled))
+	if (unlikely(!data) || local_read(&data->disabled))
 		return;
 
-	atomic_inc(&data->disabled);
+	disabled = local_inc_return(&data->disabled);
 
-	data->critical_sequence = max_sequence;
-	data->preempt_timestamp = ftrace_now(cpu);
-	data->critical_start = parent_ip ? : ip;
+	if (disabled == 1) {
+		data->critical_sequence = max_sequence;
+		data->preempt_timestamp = ftrace_now(cpu);
+		data->critical_start = parent_ip ? : ip;
 
-	__trace_function(tr, ip, parent_ip, tracing_gen_ctx());
+		__trace_function(tr, ip, parent_ip, tracing_gen_ctx());
 
-	per_cpu(tracing_cpu, cpu) = 1;
+		per_cpu(tracing_cpu, cpu) = 1;
+	}
 
-	atomic_dec(&data->disabled);
+	local_dec(&data->disabled);
 }
 
 static nokprobe_inline void
@@ -431,6 +434,7 @@ stop_critical_timing(unsigned long ip, unsigned long parent_ip)
 	struct trace_array *tr = irqsoff_trace;
 	struct trace_array_cpu *data;
 	unsigned int trace_ctx;
+	long disabled;
 
 	cpu = raw_smp_processor_id();
 	/* Always clear the tracing cpu on stopping the trace */
@@ -445,16 +449,19 @@ stop_critical_timing(unsigned long ip, unsigned long parent_ip)
 	data = per_cpu_ptr(tr->array_buffer.data, cpu);
 
 	if (unlikely(!data) ||
-	    !data->critical_start || atomic_read(&data->disabled))
+	    !data->critical_start || local_read(&data->disabled))
 		return;
 
-	atomic_inc(&data->disabled);
+	disabled = local_inc_return(&data->disabled);
 
-	trace_ctx = tracing_gen_ctx();
-	__trace_function(tr, ip, parent_ip, trace_ctx);
-	check_critical_timing(tr, data, parent_ip ? : ip, cpu);
-	data->critical_start = 0;
-	atomic_dec(&data->disabled);
+	if (disabled == 1) {
+		trace_ctx = tracing_gen_ctx();
+		__trace_function(tr, ip, parent_ip, trace_ctx);
+		check_critical_timing(tr, data, parent_ip ? : ip, cpu);
+		data->critical_start = 0;
+	}
+
+	local_dec(&data->disabled);
 }
 
 /* start and stop critical timings used to for stoppage (in idle) */
diff --git a/kernel/trace/trace_kdb.c b/kernel/trace/trace_kdb.c
index 1e72d20b3c2f..d7b135de958a 100644
--- a/kernel/trace/trace_kdb.c
+++ b/kernel/trace/trace_kdb.c
@@ -98,7 +98,6 @@ static int kdb_ftdump(int argc, const char **argv)
 	long cpu_file;
 	int err;
 	int cnt;
-	int cpu;
 
 	if (argc > 2)
 		return KDB_ARGCOUNT;
@@ -120,9 +119,7 @@ static int kdb_ftdump(int argc, const char **argv)
 	trace_init_global_iter(&iter);
 	iter.buffer_iter = buffer_iter;
 
-	for_each_tracing_cpu(cpu) {
-		atomic_inc(&per_cpu_ptr(iter.array_buffer->data, cpu)->disabled);
-	}
+	tracer_tracing_disable(iter.tr);
 
 	/* A negative skip_entries means skip all but the last entries */
 	if (skip_entries < 0) {
@@ -135,9 +132,7 @@ static int kdb_ftdump(int argc, const char **argv)
 
 	ftrace_dump_buf(skip_entries, cpu_file);
 
-	for_each_tracing_cpu(cpu) {
-		atomic_dec(&per_cpu_ptr(iter.array_buffer->data, cpu)->disabled);
-	}
+	tracer_tracing_enable(iter.tr);
 
 	kdb_trap_printk--;
 
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 2703b96d8990..3e5c47b6d7b2 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -1089,7 +1089,7 @@ static int create_or_delete_trace_kprobe(const char *raw_command)
 	if (raw_command[0] == '-')
 		return dyn_event_release(raw_command, &trace_kprobe_ops);
 
-	ret = trace_kprobe_create(raw_command);
+	ret = dyn_event_create(raw_command, &trace_kprobe_ops);
 	return ret == -ECANCELED ? -EINVAL : ret;
 }
 
diff --git a/kernel/trace/trace_mmiotrace.c b/kernel/trace/trace_mmiotrace.c
index ba5858866b2f..c706544be60c 100644
--- a/kernel/trace/trace_mmiotrace.c
+++ b/kernel/trace/trace_mmiotrace.c
@@ -291,7 +291,6 @@ __init static int init_mmio_trace(void)
 device_initcall(init_mmio_trace);
 
 static void __trace_mmiotrace_rw(struct trace_array *tr,
-				struct trace_array_cpu *data,
 				struct mmiotrace_rw *rw)
 {
 	struct trace_buffer *buffer = tr->array_buffer.buffer;
@@ -315,12 +314,10 @@ static void __trace_mmiotrace_rw(struct trace_array *tr,
 void mmio_trace_rw(struct mmiotrace_rw *rw)
 {
 	struct trace_array *tr = mmio_trace_array;
-	struct trace_array_cpu *data = per_cpu_ptr(tr->array_buffer.data, smp_processor_id());
-	__trace_mmiotrace_rw(tr, data, rw);
+	__trace_mmiotrace_rw(tr, rw);
 }
 
 static void __trace_mmiotrace_map(struct trace_array *tr,
-				struct trace_array_cpu *data,
 				struct mmiotrace_map *map)
 {
 	struct trace_buffer *buffer = tr->array_buffer.buffer;
@@ -344,12 +341,7 @@ static void __trace_mmiotrace_map(struct trace_array *tr,
 void mmio_trace_mapping(struct mmiotrace_map *map)
 {
 	struct trace_array *tr = mmio_trace_array;
-	struct trace_array_cpu *data;
-
-	preempt_disable();
-	data = per_cpu_ptr(tr->array_buffer.data, smp_processor_id());
-	__trace_mmiotrace_map(tr, data, map);
-	preempt_enable();
+	__trace_mmiotrace_map(tr, map);
 }
 
 int mmio_trace_printk(const char *fmt, va_list args)
diff --git a/kernel/trace/trace_osnoise.c b/kernel/trace/trace_osnoise.c
index e732c9e37e14..6819b93309ce 100644
--- a/kernel/trace/trace_osnoise.c
+++ b/kernel/trace/trace_osnoise.c
@@ -2302,7 +2302,7 @@ osnoise_cpus_read(struct file *filp, char __user *ubuf, size_t count,
  * osnoise_cpus_write - Write function for "cpus" entry
  * @filp: The active open file structure
  * @ubuf: The user buffer that contains the value to write
- * @cnt: The maximum number of bytes to write to "file"
+ * @count: The maximum number of bytes to write to "file"
  * @ppos: The current position in @file
  *
  * This function provides a write implementation for the "cpus"
@@ -2320,10 +2320,11 @@ osnoise_cpus_write(struct file *filp, const char __user *ubuf, size_t count,
 {
 	cpumask_var_t osnoise_cpumask_new;
 	int running, err;
-	char buf[256];
+	char *buf __free(kfree) = NULL;
 
-	if (count >= 256)
-		return -EINVAL;
+	buf = kmalloc(count, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
 
 	if (copy_from_user(buf, ubuf, count))
 		return -EFAULT;
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index b9ab06c99543..0b3db02030a7 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -938,6 +938,9 @@ static void print_fields(struct trace_iterator *iter, struct trace_event_call *c
 			 struct list_head *head)
 {
 	struct ftrace_event_field *field;
+	struct trace_array *tr = iter->tr;
+	unsigned long long laddr;
+	unsigned long addr;
 	int offset;
 	int len;
 	int ret;
@@ -974,8 +977,8 @@ static void print_fields(struct trace_iterator *iter, struct trace_event_call *c
 		case FILTER_PTR_STRING:
 			if (!iter->fmt_size)
 				trace_iter_expand_format(iter);
-			pos = *(void **)pos;
-			ret = strncpy_from_kernel_nofault(iter->fmt, pos,
+			addr = trace_adjust_address(tr, *(unsigned long *)pos);
+			ret = strncpy_from_kernel_nofault(iter->fmt, (void *)addr,
 							  iter->fmt_size);
 			if (ret < 0)
 				trace_seq_printf(&iter->seq, "(0x%px)", pos);
@@ -984,8 +987,8 @@ static void print_fields(struct trace_iterator *iter, struct trace_event_call *c
 						 pos, iter->fmt);
 			break;
 		case FILTER_TRACE_FN:
-			pos = *(void **)pos;
-			trace_seq_printf(&iter->seq, "%pS", pos);
+			addr = trace_adjust_address(tr, *(unsigned long *)pos);
+			trace_seq_printf(&iter->seq, "%pS", (void *)addr);
 			break;
 		case FILTER_CPU:
 		case FILTER_OTHER:
@@ -1015,14 +1018,36 @@ static void print_fields(struct trace_iterator *iter, struct trace_event_call *c
 					break;
 				}
 
-				trace_seq_printf(&iter->seq, "0x%x (%d)",
-						 *(unsigned int *)pos,
-						 *(unsigned int *)pos);
+				addr = *(unsigned int *)pos;
+
+				/* Some fields reference offset from _stext. */
+				if (!strcmp(field->name, "caller_offs") ||
+				    !strcmp(field->name, "parent_offs")) {
+					unsigned long ip;
+
+					ip = addr + (unsigned long)_stext;
+					ip = trace_adjust_address(tr, ip);
+					trace_seq_printf(&iter->seq, "%pS ", (void *)ip);
+				}
+
+				if (sizeof(long) == 4) {
+					addr = trace_adjust_address(tr, addr);
+					trace_seq_printf(&iter->seq, "%pS (%d)",
+							 (void *)addr, (int)addr);
+				} else {
+					trace_seq_printf(&iter->seq, "0x%x (%d)",
+							 (unsigned int)addr, (int)addr);
+				}
 				break;
 			case 8:
-				trace_seq_printf(&iter->seq, "0x%llx (%lld)",
-						 *(unsigned long long *)pos,
-						 *(unsigned long long *)pos);
+				laddr = *(unsigned long long *)pos;
+				if (sizeof(long) == 8) {
+					laddr = trace_adjust_address(tr, (unsigned long)laddr);
+					trace_seq_printf(&iter->seq, "%pS (%lld)",
+							 (void *)(long)laddr, laddr);
+				} else {
+					trace_seq_printf(&iter->seq, "0x%llx (%lld)", laddr, laddr);
+				}
 				break;
 			default:
 				trace_seq_puts(&iter->seq, "<INVALID-SIZE>");
@@ -1086,11 +1111,11 @@ enum print_line_t trace_nop_print(struct trace_iterator *iter, int flags,
 }
 
 static void print_fn_trace(struct trace_seq *s, unsigned long ip,
-			   unsigned long parent_ip, long delta,
-			   unsigned long *args, int flags)
+			   unsigned long parent_ip, unsigned long *args,
+			   struct trace_array *tr, int flags)
 {
-	ip += delta;
-	parent_ip += delta;
+	ip = trace_adjust_address(tr, ip);
+	parent_ip = trace_adjust_address(tr, parent_ip);
 
 	seq_print_ip_sym(s, ip, flags);
 	if (args)
@@ -1119,8 +1144,7 @@ static enum print_line_t trace_fn_trace(struct trace_iterator *iter, int flags,
 	else
 		args = NULL;
 
-	print_fn_trace(s, field->ip, field->parent_ip, iter->tr->text_delta,
-		       args, flags);
+	print_fn_trace(s, field->ip, field->parent_ip, args, iter->tr, flags);
 	trace_seq_putc(s, '\n');
 
 	return trace_handle_return(s);
@@ -1706,7 +1730,7 @@ static enum print_line_t trace_print_print(struct trace_iterator *iter,
 
 	trace_assign_type(field, iter->ent);
 
-	ip = field->ip + iter->tr->text_delta;
+	ip = trace_adjust_address(iter->tr, field->ip);
 
 	seq_print_ip_sym(s, ip, flags);
 	trace_seq_printf(s, ": %s", field->buf);
@@ -1792,7 +1816,7 @@ trace_func_repeats_print(struct trace_iterator *iter, int flags,
 
 	trace_assign_type(field, iter->ent);
 
-	print_fn_trace(s, field->ip, field->parent_ip, iter->tr->text_delta, NULL, flags);
+	print_fn_trace(s, field->ip, field->parent_ip, NULL, iter->tr, flags);
 	trace_seq_printf(s, " (repeats: %u, last_ts:", field->count);
 	trace_print_time(s, iter,
 			 iter->ts - FUNC_REPEATS_GET_DELTA_TS(field));
diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c
index 2eeecb6c95ee..424751cdf31f 100644
--- a/kernel/trace/trace_probe.c
+++ b/kernel/trace/trace_probe.c
@@ -154,9 +154,12 @@ fail:
 }
 
 static struct trace_probe_log trace_probe_log;
+extern struct mutex dyn_event_ops_mutex;
 
 void trace_probe_log_init(const char *subsystem, int argc, const char **argv)
 {
+	lockdep_assert_held(&dyn_event_ops_mutex);
+
 	trace_probe_log.subsystem = subsystem;
 	trace_probe_log.argc = argc;
 	trace_probe_log.argv = argv;
@@ -165,11 +168,15 @@ void trace_probe_log_init(const char *subsystem, int argc, const char **argv)
 
 void trace_probe_log_clear(void)
 {
+	lockdep_assert_held(&dyn_event_ops_mutex);
+
 	memset(&trace_probe_log, 0, sizeof(trace_probe_log));
 }
 
 void trace_probe_log_set_index(int index)
 {
+	lockdep_assert_held(&dyn_event_ops_mutex);
+
 	trace_probe_log.index = index;
 }
 
@@ -178,6 +185,8 @@ void __trace_probe_log_err(int offset, int err_type)
 	char *command, *p;
 	int i, len = 0, pos = 0;
 
+	lockdep_assert_held(&dyn_event_ops_mutex);
+
 	if (!trace_probe_log.argv)
 		return;
 
diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c
index a0db3404f7f7..bf1cb80742ae 100644
--- a/kernel/trace/trace_sched_wakeup.c
+++ b/kernel/trace/trace_sched_wakeup.c
@@ -83,14 +83,14 @@ func_prolog_preempt_disable(struct trace_array *tr,
 		goto out_enable;
 
 	*data = per_cpu_ptr(tr->array_buffer.data, cpu);
-	disabled = atomic_inc_return(&(*data)->disabled);
+	disabled = local_inc_return(&(*data)->disabled);
 	if (unlikely(disabled != 1))
 		goto out;
 
 	return 1;
 
 out:
-	atomic_dec(&(*data)->disabled);
+	local_dec(&(*data)->disabled);
 
 out_enable:
 	preempt_enable_notrace();
@@ -144,7 +144,7 @@ static int wakeup_graph_entry(struct ftrace_graph_ent *trace,
 	*calltime = trace_clock_local();
 
 	ret = __trace_graph_entry(tr, trace, trace_ctx);
-	atomic_dec(&data->disabled);
+	local_dec(&data->disabled);
 	preempt_enable_notrace();
 
 	return ret;
@@ -173,7 +173,7 @@ static void wakeup_graph_return(struct ftrace_graph_ret *trace,
 		return;
 
 	__trace_graph_return(tr, trace, trace_ctx, *calltime, rettime);
-	atomic_dec(&data->disabled);
+	local_dec(&data->disabled);
 
 	preempt_enable_notrace();
 	return;
@@ -243,7 +243,7 @@ wakeup_tracer_call(unsigned long ip, unsigned long parent_ip,
 	trace_function(tr, ip, parent_ip, trace_ctx, fregs);
 	local_irq_restore(flags);
 
-	atomic_dec(&data->disabled);
+	local_dec(&data->disabled);
 	preempt_enable_notrace();
 }
 
@@ -471,7 +471,7 @@ probe_wakeup_sched_switch(void *ignore, bool preempt,
 
 	/* disable local data, not wakeup_cpu data */
 	cpu = raw_smp_processor_id();
-	disabled = atomic_inc_return(&per_cpu_ptr(wakeup_trace->array_buffer.data, cpu)->disabled);
+	disabled = local_inc_return(&per_cpu_ptr(wakeup_trace->array_buffer.data, cpu)->disabled);
 	if (likely(disabled != 1))
 		goto out;
 
@@ -508,7 +508,7 @@ out_unlock:
 	arch_spin_unlock(&wakeup_lock);
 	local_irq_restore(flags);
 out:
-	atomic_dec(&per_cpu_ptr(wakeup_trace->array_buffer.data, cpu)->disabled);
+	local_dec(&per_cpu_ptr(wakeup_trace->array_buffer.data, cpu)->disabled);
 }
 
 static void __wakeup_reset(struct trace_array *tr)
@@ -563,7 +563,7 @@ probe_wakeup(void *ignore, struct task_struct *p)
 	    (!dl_task(p) && (p->prio >= wakeup_prio || p->prio >= current->prio)))
 		return;
 
-	disabled = atomic_inc_return(&per_cpu_ptr(wakeup_trace->array_buffer.data, cpu)->disabled);
+	disabled = local_inc_return(&per_cpu_ptr(wakeup_trace->array_buffer.data, cpu)->disabled);
 	if (unlikely(disabled != 1))
 		goto out;
 
@@ -610,7 +610,7 @@ probe_wakeup(void *ignore, struct task_struct *p)
 out_locked:
 	arch_spin_unlock(&wakeup_lock);
 out:
-	atomic_dec(&per_cpu_ptr(wakeup_trace->array_buffer.data, cpu)->disabled);
+	local_dec(&per_cpu_ptr(wakeup_trace->array_buffer.data, cpu)->disabled);
 }
 
 static void start_wakeup_tracer(struct trace_array *tr)
diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
index 14c6f272c4d8..0aa2514a6593 100644
--- a/kernel/trace/trace_stack.c
+++ b/kernel/trace/trace_stack.c
@@ -32,7 +32,7 @@ static arch_spinlock_t stack_trace_max_lock =
 DEFINE_PER_CPU(int, disable_stack_tracer);
 static DEFINE_MUTEX(stack_sysctl_mutex);
 
-int stack_tracer_enabled;
+static int stack_tracer_enabled;
 
 static void print_max_stack(void)
 {
@@ -542,7 +542,7 @@ static __init int enable_stacktrace(char *str)
 	int len;
 
 	if ((len = str_has_prefix(str, "_filter=")))
-		strncpy(stack_trace_filter_buf, str + len, COMMAND_LINE_SIZE);
+		strscpy(stack_trace_filter_buf, str + len);
 
 	stack_tracer_enabled = 1;
 	return 1;
@@ -578,3 +578,23 @@ static __init int stack_trace_init(void)
 }
 
 device_initcall(stack_trace_init);
+
+
+static const struct ctl_table trace_stack_sysctl_table[] = {
+	{
+		.procname	= "stack_tracer_enabled",
+		.data		= &stack_tracer_enabled,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= stack_trace_sysctl,
+	},
+};
+
+static int __init init_trace_stack_sysctls(void)
+{
+	register_sysctl_init("kernel", trace_stack_sysctl_table);
+	return 0;
+}
+subsys_initcall(init_trace_stack_sysctls);
+
+
diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index 3386439ec9f6..f95a2c3d5b1b 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -741,7 +741,7 @@ static int create_or_delete_trace_uprobe(const char *raw_command)
 	if (raw_command[0] == '-')
 		return dyn_event_release(raw_command, &trace_uprobe_ops);
 
-	ret = trace_uprobe_create(raw_command);
+	ret = dyn_event_create(raw_command, &trace_uprobe_ops);
 	return ret == -ECANCELED ? -EINVAL : ret;
 }
 
@@ -1489,7 +1489,7 @@ int bpf_get_uprobe_info(const struct perf_event *event, u32 *fd_type,
 				    : BPF_FD_TYPE_UPROBE;
 	*filename = tu->filename;
 	*probe_offset = tu->offset;
-	*probe_addr = 0;
+	*probe_addr = tu->ref_ctr_offset;
 	return 0;
 }
 #endif	/* CONFIG_PERF_EVENTS */
diff --git a/kernel/vmcore_info.c b/kernel/vmcore_info.c
index 1fec61603ef3..e066d31d08f8 100644
--- a/kernel/vmcore_info.c
+++ b/kernel/vmcore_info.c
@@ -210,6 +210,10 @@ static int __init crash_save_vmcoreinfo_init(void)
 	VMCOREINFO_NUMBER(PAGE_HUGETLB_MAPCOUNT_VALUE);
 #define PAGE_OFFLINE_MAPCOUNT_VALUE	(PGTY_offline << 24)
 	VMCOREINFO_NUMBER(PAGE_OFFLINE_MAPCOUNT_VALUE);
+#ifdef CONFIG_UNACCEPTED_MEMORY
+#define PAGE_UNACCEPTED_MAPCOUNT_VALUE	(PGTY_unaccepted << 24)
+	VMCOREINFO_NUMBER(PAGE_UNACCEPTED_MAPCOUNT_VALUE);
+#endif
 
 #ifdef CONFIG_KALLSYMS
 	VMCOREINFO_SYMBOL(kallsyms_names);
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index 9fa2af9dbf2c..80b56c002c7f 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -47,6 +47,7 @@ int __read_mostly watchdog_user_enabled = 1;
 static int __read_mostly watchdog_hardlockup_user_enabled = WATCHDOG_HARDLOCKUP_DEFAULT;
 static int __read_mostly watchdog_softlockup_user_enabled = 1;
 int __read_mostly watchdog_thresh = 10;
+static int __read_mostly watchdog_thresh_next;
 static int __read_mostly watchdog_hardlockup_available;
 
 struct cpumask watchdog_cpumask __read_mostly;
@@ -63,6 +64,29 @@ int __read_mostly sysctl_hardlockup_all_cpu_backtrace;
  */
 unsigned int __read_mostly hardlockup_panic =
 			IS_ENABLED(CONFIG_BOOTPARAM_HARDLOCKUP_PANIC);
+
+#ifdef CONFIG_SYSFS
+
+static unsigned int hardlockup_count;
+
+static ssize_t hardlockup_count_show(struct kobject *kobj, struct kobj_attribute *attr,
+				     char *page)
+{
+	return sysfs_emit(page, "%u\n", hardlockup_count);
+}
+
+static struct kobj_attribute hardlockup_count_attr = __ATTR_RO(hardlockup_count);
+
+static __init int kernel_hardlockup_sysfs_init(void)
+{
+	sysfs_add_file_to_group(kernel_kobj, &hardlockup_count_attr.attr, NULL);
+	return 0;
+}
+
+late_initcall(kernel_hardlockup_sysfs_init);
+
+#endif // CONFIG_SYSFS
+
 /*
  * We may not want to enable hard lockup detection by default in all cases,
  * for example when running the kernel as a guest on a hypervisor. In these
@@ -169,6 +193,10 @@ void watchdog_hardlockup_check(unsigned int cpu, struct pt_regs *regs)
 		unsigned int this_cpu = smp_processor_id();
 		unsigned long flags;
 
+#ifdef CONFIG_SYSFS
+		++hardlockup_count;
+#endif
+
 		/* Only print hardlockups once. */
 		if (per_cpu(watchdog_hardlockup_warned, cpu))
 			return;
@@ -311,6 +339,28 @@ unsigned int __read_mostly softlockup_panic =
 static bool softlockup_initialized __read_mostly;
 static u64 __read_mostly sample_period;
 
+#ifdef CONFIG_SYSFS
+
+static unsigned int softlockup_count;
+
+static ssize_t softlockup_count_show(struct kobject *kobj, struct kobj_attribute *attr,
+				     char *page)
+{
+	return sysfs_emit(page, "%u\n", softlockup_count);
+}
+
+static struct kobj_attribute softlockup_count_attr = __ATTR_RO(softlockup_count);
+
+static __init int kernel_softlockup_sysfs_init(void)
+{
+	sysfs_add_file_to_group(kernel_kobj, &softlockup_count_attr.attr, NULL);
+	return 0;
+}
+
+late_initcall(kernel_softlockup_sysfs_init);
+
+#endif // CONFIG_SYSFS
+
 /* Timestamp taken after the last successful reschedule. */
 static DEFINE_PER_CPU(unsigned long, watchdog_touch_ts);
 /* Timestamp of the last softlockup report. */
@@ -742,6 +792,10 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
 	touch_ts = __this_cpu_read(watchdog_touch_ts);
 	duration = is_softlockup(touch_ts, period_ts, now);
 	if (unlikely(duration)) {
+#ifdef CONFIG_SYSFS
+		++softlockup_count;
+#endif
+
 		/*
 		 * Prevent multiple soft-lockup reports if one cpu is already
 		 * engaged in dumping all cpu back traces.
@@ -870,12 +924,20 @@ int lockup_detector_offline_cpu(unsigned int cpu)
 	return 0;
 }
 
-static void __lockup_detector_reconfigure(void)
+static void __lockup_detector_reconfigure(bool thresh_changed)
 {
 	cpus_read_lock();
 	watchdog_hardlockup_stop();
 
 	softlockup_stop_all();
+	/*
+	 * To prevent watchdog_timer_fn from using the old interval and
+	 * the new watchdog_thresh at the same time, which could lead to
+	 * false softlockup reports, it is necessary to update the
+	 * watchdog_thresh after the softlockup is completed.
+	 */
+	if (thresh_changed)
+		watchdog_thresh = READ_ONCE(watchdog_thresh_next);
 	set_sample_period();
 	lockup_detector_update_enable();
 	if (watchdog_enabled && watchdog_thresh)
@@ -888,7 +950,7 @@ static void __lockup_detector_reconfigure(void)
 void lockup_detector_reconfigure(void)
 {
 	mutex_lock(&watchdog_mutex);
-	__lockup_detector_reconfigure();
+	__lockup_detector_reconfigure(false);
 	mutex_unlock(&watchdog_mutex);
 }
 
@@ -908,27 +970,29 @@ static __init void lockup_detector_setup(void)
 		return;
 
 	mutex_lock(&watchdog_mutex);
-	__lockup_detector_reconfigure();
+	__lockup_detector_reconfigure(false);
 	softlockup_initialized = true;
 	mutex_unlock(&watchdog_mutex);
 }
 
 #else /* CONFIG_SOFTLOCKUP_DETECTOR */
-static void __lockup_detector_reconfigure(void)
+static void __lockup_detector_reconfigure(bool thresh_changed)
 {
 	cpus_read_lock();
 	watchdog_hardlockup_stop();
+	if (thresh_changed)
+		watchdog_thresh = READ_ONCE(watchdog_thresh_next);
 	lockup_detector_update_enable();
 	watchdog_hardlockup_start();
 	cpus_read_unlock();
 }
 void lockup_detector_reconfigure(void)
 {
-	__lockup_detector_reconfigure();
+	__lockup_detector_reconfigure(false);
 }
 static inline void lockup_detector_setup(void)
 {
-	__lockup_detector_reconfigure();
+	__lockup_detector_reconfigure(false);
 }
 #endif /* !CONFIG_SOFTLOCKUP_DETECTOR */
 
@@ -946,11 +1010,11 @@ void lockup_detector_soft_poweroff(void)
 #ifdef CONFIG_SYSCTL
 
 /* Propagate any changes to the watchdog infrastructure */
-static void proc_watchdog_update(void)
+static void proc_watchdog_update(bool thresh_changed)
 {
 	/* Remove impossible cpus to keep sysctl output clean. */
 	cpumask_and(&watchdog_cpumask, &watchdog_cpumask, cpu_possible_mask);
-	__lockup_detector_reconfigure();
+	__lockup_detector_reconfigure(thresh_changed);
 }
 
 /*
@@ -984,7 +1048,7 @@ static int proc_watchdog_common(int which, const struct ctl_table *table, int wr
 	} else {
 		err = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
 		if (!err && old != READ_ONCE(*param))
-			proc_watchdog_update();
+			proc_watchdog_update(false);
 	}
 	mutex_unlock(&watchdog_mutex);
 	return err;
@@ -1035,11 +1099,13 @@ static int proc_watchdog_thresh(const struct ctl_table *table, int write,
 
 	mutex_lock(&watchdog_mutex);
 
-	old = READ_ONCE(watchdog_thresh);
+	watchdog_thresh_next = READ_ONCE(watchdog_thresh);
+
+	old = watchdog_thresh_next;
 	err = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
 
-	if (!err && write && old != READ_ONCE(watchdog_thresh))
-		proc_watchdog_update();
+	if (!err && write && old != READ_ONCE(watchdog_thresh_next))
+		proc_watchdog_update(true);
 
 	mutex_unlock(&watchdog_mutex);
 	return err;
@@ -1060,7 +1126,7 @@ static int proc_watchdog_cpumask(const struct ctl_table *table, int write,
 
 	err = proc_do_large_bitmap(table, write, buffer, lenp, ppos);
 	if (!err && write)
-		proc_watchdog_update();
+		proc_watchdog_update(false);
 
 	mutex_unlock(&watchdog_mutex);
 	return err;
@@ -1080,7 +1146,7 @@ static const struct ctl_table watchdog_sysctls[] = {
 	},
 	{
 		.procname	= "watchdog_thresh",
-		.data		= &watchdog_thresh,
+		.data		= &watchdog_thresh_next,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= proc_watchdog_thresh,
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index cf6203282737..97f37b5bae66 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -686,7 +686,7 @@ EXPORT_SYMBOL_GPL(destroy_work_on_stack);
 
 void destroy_delayed_work_on_stack(struct delayed_work *work)
 {
-	destroy_timer_on_stack(&work->timer);
+	timer_destroy_on_stack(&work->timer);
 	debug_object_free(&work->work, &work_debug_descr);
 }
 EXPORT_SYMBOL_GPL(destroy_delayed_work_on_stack);
@@ -2481,7 +2481,7 @@ EXPORT_SYMBOL_GPL(queue_work_node);
 
 void delayed_work_timer_fn(struct timer_list *t)
 {
-	struct delayed_work *dwork = from_timer(dwork, t, timer);
+	struct delayed_work *dwork = timer_container_of(dwork, t, timer);
 
 	/* should have been called from irqsafe timer with irq already off */
 	__queue_work(dwork->cpu, dwork->wq, &dwork->work);
@@ -2909,7 +2909,7 @@ static void set_worker_dying(struct worker *worker, struct list_head *list)
  */
 static void idle_worker_timeout(struct timer_list *t)
 {
-	struct worker_pool *pool = from_timer(pool, t, idle_timer);
+	struct worker_pool *pool = timer_container_of(pool, t, idle_timer);
 	bool do_cull = false;
 
 	if (work_pending(&pool->idle_cull_work))
@@ -3008,7 +3008,7 @@ static void send_mayday(struct work_struct *work)
 
 static void pool_mayday_timeout(struct timer_list *t)
 {
-	struct worker_pool *pool = from_timer(pool, t, mayday_timer);
+	struct worker_pool *pool = timer_container_of(pool, t, mayday_timer);
 	struct work_struct *work;
 
 	raw_spin_lock_irq(&pool->lock);
@@ -3241,7 +3241,7 @@ __acquires(&pool->lock)
 	 * point will only record its address.
 	 */
 	trace_workqueue_execute_end(work, worker->current_func);
-	pwq->stats[PWQ_STAT_COMPLETED]++;
+
 	lock_map_release(&lockdep_map);
 	if (!bh_draining)
 		lock_map_release(pwq->wq->lockdep_map);
@@ -3272,6 +3272,8 @@ __acquires(&pool->lock)
 
 	raw_spin_lock_irq(&pool->lock);
 
+	pwq->stats[PWQ_STAT_COMPLETED]++;
+
 	/*
 	 * In addition to %WQ_CPU_INTENSIVE, @worker may also have been marked
 	 * CPU intensive by wq_worker_tick() if @work hogged CPU longer than
@@ -5837,6 +5839,17 @@ static bool pwq_busy(struct pool_workqueue *pwq)
  * @wq: target workqueue
  *
  * Safely destroy a workqueue. All work currently pending will be done first.
+ *
+ * This function does NOT guarantee that non-pending work that has been
+ * submitted with queue_delayed_work() and similar functions will be done
+ * before destroying the workqueue. The fundamental problem is that, currently,
+ * the workqueue has no way of accessing non-pending delayed_work. delayed_work
+ * is only linked on the timer-side. All delayed_work must, therefore, be
+ * canceled before calling this function.
+ *
+ * TODO: It would be better if the problem described above wouldn't exist and
+ * destroy_workqueue() would cleanly cancel all pending and non-pending
+ * delayed_work.
  */
 void destroy_workqueue(struct workqueue_struct *wq)
 {