27 files changed, 567 insertions, 247 deletions

diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index bd2cac057928..29fe21099298 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -752,13 +752,12 @@ static bool btf_name_offset_valid(const struct btf *btf, u32 offset)
 	return offset < btf->hdr.str_len;
 }
 
-static bool __btf_name_char_ok(char c, bool first, bool dot_ok)
+static bool __btf_name_char_ok(char c, bool first)
 {
 	if ((first ? !isalpha(c) :
 		     !isalnum(c)) &&
 	    c != '_' &&
-	    ((c == '.' && !dot_ok) ||
-	      c != '.'))
+	    c != '.')
 		return false;
 	return true;
 }
@@ -775,20 +774,20 @@ static const char *btf_str_by_offset(const struct btf *btf, u32 offset)
 	return NULL;
 }
 
-static bool __btf_name_valid(const struct btf *btf, u32 offset, bool dot_ok)
+static bool __btf_name_valid(const struct btf *btf, u32 offset)
 {
 	/* offset must be valid */
 	const char *src = btf_str_by_offset(btf, offset);
 	const char *src_limit;
 
-	if (!__btf_name_char_ok(*src, true, dot_ok))
+	if (!__btf_name_char_ok(*src, true))
 		return false;
 
 	/* set a limit on identifier length */
 	src_limit = src + KSYM_NAME_LEN;
 	src++;
 	while (*src && src < src_limit) {
-		if (!__btf_name_char_ok(*src, false, dot_ok))
+		if (!__btf_name_char_ok(*src, false))
 			return false;
 		src++;
 	}
@@ -796,17 +795,14 @@ static bool __btf_name_valid(const struct btf *btf, u32 offset, bool dot_ok)
 	return !*src;
 }
 
-/* Only C-style identifier is permitted. This can be relaxed if
- * necessary.
- */
 static bool btf_name_valid_identifier(const struct btf *btf, u32 offset)
 {
-	return __btf_name_valid(btf, offset, false);
+	return __btf_name_valid(btf, offset);
 }
 
 static bool btf_name_valid_section(const struct btf *btf, u32 offset)
 {
-	return __btf_name_valid(btf, offset, true);
+	return __btf_name_valid(btf, offset);
 }
 
 static const char *__btf_name_by_offset(const struct btf *btf, u32 offset)
@@ -4430,7 +4426,7 @@ static s32 btf_var_check_meta(struct btf_verifier_env *env,
 	}
 
 	if (!t->name_off ||
-	    !__btf_name_valid(env->btf, t->name_off, true)) {
+	    !__btf_name_valid(env->btf, t->name_off)) {
 		btf_verifier_log_type(env, t, "Invalid name");
 		return -EINVAL;
 	}
diff --git a/kernel/bpf/map_in_map.c b/kernel/bpf/map_in_map.c
index 2c5c64c2a53b..cd5eafaba97e 100644
--- a/kernel/bpf/map_in_map.c
+++ b/kernel/bpf/map_in_map.c
@@ -69,9 +69,13 @@ struct bpf_map *bpf_map_meta_alloc(int inner_map_ufd)
 	/* Misc members not needed in bpf_map_meta_equal() check. */
 	inner_map_meta->ops = inner_map->ops;
 	if (inner_map->ops == &array_map_ops) {
+		struct bpf_array *inner_array_meta =
+			container_of(inner_map_meta, struct bpf_array, map);
+		struct bpf_array *inner_array = container_of(inner_map, struct bpf_array, map);
+
+		inner_array_meta->index_mask = inner_array->index_mask;
+		inner_array_meta->elem_size = inner_array->elem_size;
 		inner_map_meta->bypass_spec_v1 = inner_map->bypass_spec_v1;
-		container_of(inner_map_meta, struct bpf_array, map)->index_mask =
-		     container_of(inner_map, struct bpf_array, map)->index_mask;
 	}
 
 	fdput(f);
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index a75c54b6f8a3..a2aef900519c 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -2481,6 +2481,10 @@ bpf_prog_load_check_attach(enum bpf_prog_type prog_type,
 		default:
 			return -EINVAL;
 		}
+	case BPF_PROG_TYPE_NETFILTER:
+		if (expected_attach_type == BPF_NETFILTER)
+			return 0;
+		return -EINVAL;
 	case BPF_PROG_TYPE_SYSCALL:
 	case BPF_PROG_TYPE_EXT:
 		if (expected_attach_type)
@@ -3516,6 +3520,11 @@ static int bpf_prog_attach_check_attach_type(const struct bpf_prog *prog,
 		return prog->enforce_expected_attach_type &&
 			prog->expected_attach_type != attach_type ?
 			-EINVAL : 0;
+	case BPF_PROG_TYPE_KPROBE:
+		if (prog->expected_attach_type == BPF_TRACE_KPROBE_MULTI &&
+		    attach_type != BPF_TRACE_KPROBE_MULTI)
+			return -EINVAL;
+		return 0;
 	default:
 		return 0;
 	}
@@ -4670,7 +4679,12 @@ static int link_create(union bpf_attr *attr, bpfptr_t uattr)
 
 	switch (prog->type) {
 	case BPF_PROG_TYPE_EXT:
+		break;
 	case BPF_PROG_TYPE_NETFILTER:
+		if (attr->link_create.attach_type != BPF_NETFILTER) {
+			ret = -EINVAL;
+			goto out;
+		}
 		break;
 	case BPF_PROG_TYPE_PERF_EVENT:
 	case BPF_PROG_TYPE_TRACEPOINT:
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index fa43dc8e85b9..11e54dd8b6dd 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -4345,6 +4345,9 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env,
 				return err;
 		}
 		save_register_state(state, spi, reg, size);
+		/* Break the relation on a narrowing spill. */
+		if (fls64(reg->umax_value) > BITS_PER_BYTE * size)
+			state->stack[spi].spilled_ptr.id = 0;
 	} else if (!reg && !(off % BPF_REG_SIZE) && is_bpf_st_mem(insn) &&
 		   insn->imm != 0 && env->bpf_capable) {
 		struct bpf_reg_state fake_reg = {};
@@ -17791,9 +17794,10 @@ static int jit_subprogs(struct bpf_verifier_env *env)
 	}
 
 	/* finally lock prog and jit images for all functions and
-	 * populate kallsysm
+	 * populate kallsysm. Begin at the first subprogram, since
+	 * bpf_prog_load will add the kallsyms for the main program.
 	 */
-	for (i = 0; i < env->subprog_cnt; i++) {
+	for (i = 1; i < env->subprog_cnt; i++) {
 		bpf_prog_lock_ro(func[i]);
 		bpf_prog_kallsyms_add(func[i]);
 	}
@@ -17819,6 +17823,8 @@ static int jit_subprogs(struct bpf_verifier_env *env)
 	prog->jited = 1;
 	prog->bpf_func = func[0]->bpf_func;
 	prog->jited_len = func[0]->jited_len;
+	prog->aux->extable = func[0]->aux->extable;
+	prog->aux->num_exentries = func[0]->aux->num_exentries;
 	prog->aux->func = func;
 	prog->aux->func_cnt = env->subprog_cnt;
 	bpf_prog_jit_attempt_done(prog);
diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c
index aeef06c465ef..5407241dbb45 100644
--- a/kernel/cgroup/cgroup-v1.c
+++ b/kernel/cgroup/cgroup-v1.c
@@ -108,7 +108,7 @@ int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from)
 
 	cgroup_lock();
 
-	percpu_down_write(&cgroup_threadgroup_rwsem);
+	cgroup_attach_lock(true);
 
 	/* all tasks in @from are being moved, all csets are source */
 	spin_lock_irq(&css_set_lock);
@@ -144,7 +144,7 @@ int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from)
 	} while (task && !ret);
 out_err:
 	cgroup_migrate_finish(&mgctx);
-	percpu_up_write(&cgroup_threadgroup_rwsem);
+	cgroup_attach_unlock(true);
 	cgroup_unlock();
 	return ret;
 }
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 625d7483951c..4d42f0cbc11e 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -1798,7 +1798,7 @@ int rebind_subsystems(struct cgroup_root *dst_root, u16 ss_mask)
 {
 	struct cgroup *dcgrp = &dst_root->cgrp;
 	struct cgroup_subsys *ss;
-	int ssid, i, ret;
+	int ssid, ret;
 	u16 dfl_disable_ss_mask = 0;
 
 	lockdep_assert_held(&cgroup_mutex);
@@ -1842,7 +1842,8 @@ int rebind_subsystems(struct cgroup_root *dst_root, u16 ss_mask)
 		struct cgroup_root *src_root = ss->root;
 		struct cgroup *scgrp = &src_root->cgrp;
 		struct cgroup_subsys_state *css = cgroup_css(scgrp, ss);
-		struct css_set *cset;
+		struct css_set *cset, *cset_pos;
+		struct css_task_iter *it;
 
 		WARN_ON(!css || cgroup_css(dcgrp, ss));
 
@@ -1860,9 +1861,22 @@ int rebind_subsystems(struct cgroup_root *dst_root, u16 ss_mask)
 		css->cgroup = dcgrp;
 
 		spin_lock_irq(&css_set_lock);
-		hash_for_each(css_set_table, i, cset, hlist)
+		WARN_ON(!list_empty(&dcgrp->e_csets[ss->id]));
+		list_for_each_entry_safe(cset, cset_pos, &scgrp->e_csets[ss->id],
+					 e_cset_node[ss->id]) {
 			list_move_tail(&cset->e_cset_node[ss->id],
 				       &dcgrp->e_csets[ss->id]);
+			/*
+			 * all css_sets of scgrp together in same order to dcgrp,
+			 * patch in-flight iterators to preserve correct iteration.
+			 * since the iterator is always advanced right away and
+			 * finished when it->cset_pos meets it->cset_head, so only
+			 * update it->cset_head is enough here.
+			 */
+			list_for_each_entry(it, &cset->task_iters, iters_node)
+				if (it->cset_head == &scgrp->e_csets[ss->id])
+					it->cset_head = &dcgrp->e_csets[ss->id];
+		}
 		spin_unlock_irq(&css_set_lock);
 
 		if (ss->css_rstat_flush) {
@@ -6486,19 +6500,18 @@ err:
 static void cgroup_css_set_put_fork(struct kernel_clone_args *kargs)
 	__releases(&cgroup_threadgroup_rwsem) __releases(&cgroup_mutex)
 {
+	struct cgroup *cgrp = kargs->cgrp;
+	struct css_set *cset = kargs->cset;
+
 	cgroup_threadgroup_change_end(current);
 
-	if (kargs->flags & CLONE_INTO_CGROUP) {
-		struct cgroup *cgrp = kargs->cgrp;
-		struct css_set *cset = kargs->cset;
+	if (cset) {
+		put_css_set(cset);
+		kargs->cset = NULL;
+	}
 
+	if (kargs->flags & CLONE_INTO_CGROUP) {
 		cgroup_unlock();
-
-		if (cset) {
-			put_css_set(cset);
-			kargs->cset = NULL;
-		}
-
 		if (cgrp) {
 			cgroup_put(cgrp);
 			kargs->cgrp = NULL;
diff --git a/kernel/cgroup/legacy_freezer.c b/kernel/cgroup/legacy_freezer.c
index 936473203a6b..122dacb3a443 100644
--- a/kernel/cgroup/legacy_freezer.c
+++ b/kernel/cgroup/legacy_freezer.c
@@ -108,16 +108,18 @@ static int freezer_css_online(struct cgroup_subsys_state *css)
 	struct freezer *freezer = css_freezer(css);
 	struct freezer *parent = parent_freezer(freezer);
 
+	cpus_read_lock();
 	mutex_lock(&freezer_mutex);
 
 	freezer->state |= CGROUP_FREEZER_ONLINE;
 
 	if (parent && (parent->state & CGROUP_FREEZING)) {
 		freezer->state |= CGROUP_FREEZING_PARENT | CGROUP_FROZEN;
-		static_branch_inc(&freezer_active);
+		static_branch_inc_cpuslocked(&freezer_active);
 	}
 
 	mutex_unlock(&freezer_mutex);
+	cpus_read_unlock();
 	return 0;
 }
 
@@ -132,14 +134,16 @@ static void freezer_css_offline(struct cgroup_subsys_state *css)
 {
 	struct freezer *freezer = css_freezer(css);
 
+	cpus_read_lock();
 	mutex_lock(&freezer_mutex);
 
 	if (freezer->state & CGROUP_FREEZING)
-		static_branch_dec(&freezer_active);
+		static_branch_dec_cpuslocked(&freezer_active);
 
 	freezer->state = 0;
 
 	mutex_unlock(&freezer_mutex);
+	cpus_read_unlock();
 }
 
 static void freezer_css_free(struct cgroup_subsys_state *css)
diff --git a/kernel/exit.c b/kernel/exit.c
index 34b90e2e7cf7..edb50b4c9972 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -411,7 +411,10 @@ static void coredump_task_exit(struct task_struct *tsk)
 	tsk->flags |= PF_POSTCOREDUMP;
 	core_state = tsk->signal->core_state;
 	spin_unlock_irq(&tsk->sighand->siglock);
-	if (core_state) {
+
+	/* The vhost_worker does not particpate in coredumps */
+	if (core_state &&
+	    ((tsk->flags & (PF_IO_WORKER | PF_USER_WORKER)) != PF_USER_WORKER)) {
 		struct core_thread self;
 
 		self.task = current;
diff --git a/kernel/fork.c b/kernel/fork.c
index ed4e01daccaa..41c964104b58 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -627,6 +627,7 @@ void free_task(struct task_struct *tsk)
 	arch_release_task_struct(tsk);
 	if (tsk->flags & PF_KTHREAD)
 		free_kthread_struct(tsk);
+	bpf_task_storage_free(tsk);
 	free_task_struct(tsk);
 }
 EXPORT_SYMBOL(free_task);
@@ -979,7 +980,6 @@ void __put_task_struct(struct task_struct *tsk)
 	cgroup_free(tsk);
 	task_numa_free(tsk, true);
 	security_task_free(tsk);
-	bpf_task_storage_free(tsk);
 	exit_creds(tsk);
 	delayacct_tsk_free(tsk);
 	put_signal_struct(tsk->signal);
@@ -2336,16 +2336,16 @@ __latent_entropy struct task_struct *copy_process(
 	p->flags &= ~PF_KTHREAD;
 	if (args->kthread)
 		p->flags |= PF_KTHREAD;
-	if (args->user_worker)
-		p->flags |= PF_USER_WORKER;
-	if (args->io_thread) {
+	if (args->user_worker) {
 		/*
-		 * Mark us an IO worker, and block any signal that isn't
+		 * Mark us a user worker, and block any signal that isn't
 		 * fatal or STOP
 		 */
-		p->flags |= PF_IO_WORKER;
+		p->flags |= PF_USER_WORKER;
 		siginitsetinv(&p->blocked, sigmask(SIGKILL)|sigmask(SIGSTOP));
 	}
+	if (args->io_thread)
+		p->flags |= PF_IO_WORKER;
 
 	if (args->name)
 		strscpy_pad(p->comm, args->name, sizeof(p->comm));
@@ -2517,9 +2517,6 @@ __latent_entropy struct task_struct *copy_process(
 	if (retval)
 		goto bad_fork_cleanup_io;
 
-	if (args->ignore_signals)
-		ignore_signals(p);
-
 	stackleak_task_init(p);
 
 	if (pid != &init_struct_pid) {
diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c
index 7a97bcb086bf..b4c31a5c1147 100644
--- a/kernel/irq/msi.c
+++ b/kernel/irq/msi.c
@@ -542,7 +542,7 @@ fail:
 	return ret;
 }
 
-#ifdef CONFIG_PCI_MSI_ARCH_FALLBACKS
+#if defined(CONFIG_PCI_MSI_ARCH_FALLBACKS) || defined(CONFIG_PCI_XEN)
 /**
  * msi_device_populate_sysfs - Populate msi_irqs sysfs entries for a device
  * @dev:	The device (PCI, platform etc) which will get sysfs entries
@@ -574,7 +574,7 @@ void msi_device_destroy_sysfs(struct device *dev)
 	msi_for_each_desc(desc, dev, MSI_DESC_ALL)
 		msi_sysfs_remove_desc(dev, desc);
 }
-#endif /* CONFIG_PCI_MSI_ARCH_FALLBACK */
+#endif /* CONFIG_PCI_MSI_ARCH_FALLBACK || CONFIG_PCI_XEN */
 #else /* CONFIG_SYSFS */
 static inline int msi_sysfs_create_group(struct device *dev) { return 0; }
 static inline int msi_sysfs_populate_desc(struct device *dev, struct msi_desc *desc) { return 0; }
diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c
index f989f5f1933b..69ee4a29136f 100644
--- a/kernel/kexec_file.c
+++ b/kernel/kexec_file.c
@@ -901,10 +901,22 @@ static int kexec_purgatory_setup_sechdrs(struct purgatory_info *pi,
 		}
 
 		offset = ALIGN(offset, align);
+
+		/*
+		 * Check if the segment contains the entry point, if so,
+		 * calculate the value of image->start based on it.
+		 * If the compiler has produced more than one .text section
+		 * (Eg: .text.hot), they are generally after the main .text
+		 * section, and they shall not be used to calculate
+		 * image->start. So do not re-calculate image->start if it
+		 * is not set to the initial value, and warn the user so they
+		 * have a chance to fix their purgatory's linker script.
+		 */
 		if (sechdrs[i].sh_flags & SHF_EXECINSTR &&
 		    pi->ehdr->e_entry >= sechdrs[i].sh_addr &&
 		    pi->ehdr->e_entry < (sechdrs[i].sh_addr
-					 + sechdrs[i].sh_size)) {
+					 + sechdrs[i].sh_size) &&
+		    !WARN_ON(kbuf->image->start != pi->ehdr->e_entry)) {
 			kbuf->image->start -= sechdrs[i].sh_addr;
 			kbuf->image->start += kbuf->mem + offset;
 		}
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index dcd1d5bfc1e0..4dfd2f3e09b2 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -2263,6 +2263,9 @@ static inline bool usage_match(struct lock_list *entry, void *mask)
 
 static inline bool usage_skip(struct lock_list *entry, void *mask)
 {
+	if (entry->class->lock_type == LD_LOCK_NORMAL)
+		return false;
+
 	/*
 	 * Skip local_lock() for irq inversion detection.
 	 *
@@ -2289,14 +2292,16 @@ static inline bool usage_skip(struct lock_list *entry, void *mask)
 	 * As a result, we will skip local_lock(), when we search for irq
 	 * inversion bugs.
 	 */
-	if (entry->class->lock_type == LD_LOCK_PERCPU) {
-		if (DEBUG_LOCKS_WARN_ON(entry->class->wait_type_inner < LD_WAIT_CONFIG))
-			return false;
+	if (entry->class->lock_type == LD_LOCK_PERCPU &&
+	    DEBUG_LOCKS_WARN_ON(entry->class->wait_type_inner < LD_WAIT_CONFIG))
+		return false;
 
-		return true;
-	}
+	/*
+	 * Skip WAIT_OVERRIDE for irq inversion detection -- it's not actually
+	 * a lock and only used to override the wait_type.
+	 */
 
-	return false;
+	return true;
 }
 
 /*
@@ -4768,7 +4773,8 @@ static int check_wait_context(struct task_struct *curr, struct held_lock *next)
 
 	for (; depth < curr->lockdep_depth; depth++) {
 		struct held_lock *prev = curr->held_locks + depth;
-		u8 prev_inner = hlock_class(prev)->wait_type_inner;
+		struct lock_class *class = hlock_class(prev);
+		u8 prev_inner = class->wait_type_inner;
 
 		if (prev_inner) {
 			/*
@@ -4778,6 +4784,14 @@ static int check_wait_context(struct task_struct *curr, struct held_lock *next)
 			 * Also due to trylocks.
 			 */
 			curr_inner = min(curr_inner, prev_inner);
+
+			/*
+			 * Allow override for annotations -- this is typically
+			 * only valid/needed for code that only exists when
+			 * CONFIG_PREEMPT_RT=n.
+			 */
+			if (unlikely(class->lock_type == LD_LOCK_WAIT_OVERRIDE))
+				curr_inner = prev_inner;
 		}
 	}
 
diff --git a/kernel/module/decompress.c b/kernel/module/decompress.c
index e97232b125eb..8a5d6d63b06c 100644
--- a/kernel/module/decompress.c
+++ b/kernel/module/decompress.c
@@ -257,7 +257,7 @@ static ssize_t module_zstd_decompress(struct load_info *info,
 	do {
 		struct page *page = module_get_next_page(info);
 
-		if (!IS_ERR(page)) {
+		if (IS_ERR(page)) {
 			retval = PTR_ERR(page);
 			goto out;
 		}
diff --git a/kernel/module/main.c b/kernel/module/main.c
index 044aa2c9e3cb..4e2cf784cf8c 100644
--- a/kernel/module/main.c
+++ b/kernel/module/main.c
@@ -1521,14 +1521,14 @@ static void __layout_sections(struct module *mod, struct load_info *info, bool i
 		MOD_RODATA,
 		MOD_RO_AFTER_INIT,
 		MOD_DATA,
-		MOD_INVALID,	/* This is needed to match the masks array */
+		MOD_DATA,
 	};
 	static const int init_m_to_mem_type[] = {
 		MOD_INIT_TEXT,
 		MOD_INIT_RODATA,
 		MOD_INVALID,
 		MOD_INIT_DATA,
-		MOD_INVALID,	/* This is needed to match the masks array */
+		MOD_INIT_DATA,
 	};
 
 	for (m = 0; m < ARRAY_SIZE(masks); ++m) {
diff --git a/kernel/signal.c b/kernel/signal.c
index 8f6330f0e9ca..2547fa73bde5 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -1368,7 +1368,9 @@ int zap_other_threads(struct task_struct *p)
 
 	while_each_thread(p, t) {
 		task_clear_jobctl_pending(t, JOBCTL_PENDING_MASK);
-		count++;
+		/* Don't require de_thread to wait for the vhost_worker */
+		if ((t->flags & (PF_IO_WORKER | PF_USER_WORKER)) != PF_USER_WORKER)
+			count++;
 
 		/* Don't bother with already dead threads */
 		if (t->exit_state)
@@ -2861,11 +2863,11 @@ relock:
 		}
 
 		/*
-		 * PF_IO_WORKER threads will catch and exit on fatal signals
+		 * PF_USER_WORKER threads will catch and exit on fatal signals
 		 * themselves. They have cleanup that must be performed, so
 		 * we cannot call do_exit() on their behalf.
 		 */
-		if (current->flags & PF_IO_WORKER)
+		if (current->flags & PF_USER_WORKER)
 			goto out;
 
 		/*
diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c
index 65b8658da829..e9138cd7a0f5 100644
--- a/kernel/time/tick-common.c
+++ b/kernel/time/tick-common.c
@@ -218,19 +218,8 @@ static void tick_setup_device(struct tick_device *td,
 		 * this cpu:
 		 */
 		if (tick_do_timer_cpu == TICK_DO_TIMER_BOOT) {
-			ktime_t next_p;
-			u32 rem;
-
 			tick_do_timer_cpu = cpu;
-
-			next_p = ktime_get();
-			div_u64_rem(next_p, TICK_NSEC, &rem);
-			if (rem) {
-				next_p -= rem;
-				next_p += TICK_NSEC;
-			}
-
-			tick_next_period = next_p;
+			tick_next_period = ktime_get();
 #ifdef CONFIG_NO_HZ_FULL
 			/*
 			 * The boot CPU may be nohz_full, in which case set
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 52254679ec48..42c0be3080bd 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -161,8 +161,19 @@ static ktime_t tick_init_jiffy_update(void)
 	raw_spin_lock(&jiffies_lock);
 	write_seqcount_begin(&jiffies_seq);
 	/* Did we start the jiffies update yet ? */
-	if (last_jiffies_update == 0)
+	if (last_jiffies_update == 0) {
+		u32 rem;
+
+		/*
+		 * Ensure that the tick is aligned to a multiple of
+		 * TICK_NSEC.
+		 */
+		div_u64_rem(tick_next_period, TICK_NSEC, &rem);
+		if (rem)
+			tick_next_period += TICK_NSEC - rem;
+
 		last_jiffies_update = tick_next_period;
+	}
 	period = last_jiffies_update;
 	write_seqcount_end(&jiffies_seq);
 	raw_spin_unlock(&jiffies_lock);
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 2bc41e6ac9fe..03b7f6b8e4f0 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -900,13 +900,23 @@ static const struct bpf_func_proto bpf_send_signal_thread_proto = {
 
 BPF_CALL_3(bpf_d_path, struct path *, path, char *, buf, u32, sz)
 {
+	struct path copy;
 	long len;
 	char *p;
 
 	if (!sz)
 		return 0;
 
-	p = d_path(path, buf, sz);
+	/*
+	 * The path pointer is verified as trusted and safe to use,
+	 * but let's double check it's valid anyway to workaround
+	 * potentially broken verifier.
+	 */
+	len = copy_from_kernel_nofault(&copy, path, sizeof(*path));
+	if (len < 0)
+		return len;
+
+	p = d_path(&copy, buf, sz);
 	if (IS_ERR(p)) {
 		len = PTR_ERR(p);
 	} else {
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index ebc59781456a..64a4dde073ef 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -60,6 +60,7 @@
  */
 bool ring_buffer_expanded;
 
+#ifdef CONFIG_FTRACE_STARTUP_TEST
 /*
  * We need to change this state when a selftest is running.
  * A selftest will lurk into the ring-buffer to count the
@@ -75,7 +76,6 @@ static bool __read_mostly tracing_selftest_running;
  */
 bool __read_mostly tracing_selftest_disabled;
 
-#ifdef CONFIG_FTRACE_STARTUP_TEST
 void __init disable_tracing_selftest(const char *reason)
 {
 	if (!tracing_selftest_disabled) {
@@ -83,6 +83,9 @@ void __init disable_tracing_selftest(const char *reason)
 		pr_info("Ftrace startup test is disabled due to %s\n", reason);
 	}
 }
+#else
+#define tracing_selftest_running	0
+#define tracing_selftest_disabled	0
 #endif
 
 /* Pipe tracepoints to printk */
@@ -1051,7 +1054,10 @@ int __trace_array_puts(struct trace_array *tr, unsigned long ip,
 	if (!(tr->trace_flags & TRACE_ITER_PRINTK))
 		return 0;
 
-	if (unlikely(tracing_selftest_running || tracing_disabled))
+	if (unlikely(tracing_selftest_running && tr == &global_trace))
+		return 0;
+
+	if (unlikely(tracing_disabled))
 		return 0;
 
 	alloc = sizeof(*entry) + size + 2; /* possible \n added */
@@ -2041,6 +2047,24 @@ static int run_tracer_selftest(struct tracer *type)
 	return 0;
 }
 
+static int do_run_tracer_selftest(struct tracer *type)
+{
+	int ret;
+
+	/*
+	 * Tests can take a long time, especially if they are run one after the
+	 * other, as does happen during bootup when all the tracers are
+	 * registered. This could cause the soft lockup watchdog to trigger.
+	 */
+	cond_resched();
+
+	tracing_selftest_running = true;
+	ret = run_tracer_selftest(type);
+	tracing_selftest_running = false;
+
+	return ret;
+}
+
 static __init int init_trace_selftests(void)
 {
 	struct trace_selftests *p, *n;
@@ -2092,6 +2116,10 @@ static inline int run_tracer_selftest(struct tracer *type)
 {
 	return 0;
 }
+static inline int do_run_tracer_selftest(struct tracer *type)
+{
+	return 0;
+}
 #endif /* CONFIG_FTRACE_STARTUP_TEST */
 
 static void add_tracer_options(struct trace_array *tr, struct tracer *t);
@@ -2127,8 +2155,6 @@ int __init register_tracer(struct tracer *type)
 
 	mutex_lock(&trace_types_lock);
 
-	tracing_selftest_running = true;
-
 	for (t = trace_types; t; t = t->next) {
 		if (strcmp(type->name, t->name) == 0) {
 			/* already found */
@@ -2157,7 +2183,7 @@ int __init register_tracer(struct tracer *type)
 	/* store the tracer for __set_tracer_option */
 	type->flags->trace = type;
 
-	ret = run_tracer_selftest(type);
+	ret = do_run_tracer_selftest(type);
 	if (ret < 0)
 		goto out;
 
@@ -2166,7 +2192,6 @@ int __init register_tracer(struct tracer *type)
 	add_tracer_options(&global_trace, type);
 
  out:
-	tracing_selftest_running = false;
 	mutex_unlock(&trace_types_lock);
 
 	if (ret || !default_bootup_tracer)
@@ -3490,7 +3515,7 @@ __trace_array_vprintk(struct trace_buffer *buffer,
 	unsigned int trace_ctx;
 	char *tbuffer;
 
-	if (tracing_disabled || tracing_selftest_running)
+	if (tracing_disabled)
 		return 0;
 
 	/* Don't pollute graph traces with trace_vprintk internals */
@@ -3538,6 +3563,9 @@ __printf(3, 0)
 int trace_array_vprintk(struct trace_array *tr,
 			unsigned long ip, const char *fmt, va_list args)
 {
+	if (tracing_selftest_running && tr == &global_trace)
+		return 0;
+
 	return __trace_array_vprintk(tr->array_buffer.buffer, ip, fmt, args);
 }
 
@@ -5752,7 +5780,7 @@ static const char readme_msg[] =
 	"\t    table using the key(s) and value(s) named, and the value of a\n"
 	"\t    sum called 'hitcount' is incremented.  Keys and values\n"
 	"\t    correspond to fields in the event's format description.  Keys\n"
-	"\t    can be any field, or the special string 'stacktrace'.\n"
+	"\t    can be any field, or the special string 'common_stacktrace'.\n"
 	"\t    Compound keys consisting of up to two fields can be specified\n"
 	"\t    by the 'keys' keyword.  Values must correspond to numeric\n"
 	"\t    fields.  Sort keys consisting of up to two fields can be\n"
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 654ffa40457a..57e539d47989 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -194,6 +194,8 @@ static int trace_define_generic_fields(void)
 	__generic_field(int, common_cpu, FILTER_CPU);
 	__generic_field(char *, COMM, FILTER_COMM);
 	__generic_field(char *, comm, FILTER_COMM);
+	__generic_field(char *, stacktrace, FILTER_STACKTRACE);
+	__generic_field(char *, STACKTRACE, FILTER_STACKTRACE);
 
 	return ret;
 }
diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
index 486cca3c2b75..b97d3ad832f1 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -1364,7 +1364,7 @@ static const char *hist_field_name(struct hist_field *field,
 		if (field->field)
 			field_name = field->field->name;
 		else
-			field_name = "stacktrace";
+			field_name = "common_stacktrace";
 	} else if (field->flags & HIST_FIELD_FL_HITCOUNT)
 		field_name = "hitcount";
 
@@ -2367,7 +2367,7 @@ parse_field(struct hist_trigger_data *hist_data, struct trace_event_file *file,
 		hist_data->enable_timestamps = true;
 		if (*flags & HIST_FIELD_FL_TIMESTAMP_USECS)
 			hist_data->attrs->ts_in_usecs = true;