22 files changed, 290 insertions, 143 deletions

diff --git a/kernel/bpf/crypto.c b/kernel/bpf/crypto.c
index 83c4d9943084..1d024fe7248a 100644
--- a/kernel/bpf/crypto.c
+++ b/kernel/bpf/crypto.c
@@ -261,6 +261,12 @@ __bpf_kfunc void bpf_crypto_ctx_release(struct bpf_crypto_ctx *ctx)
 		call_rcu(&ctx->rcu, crypto_free_cb);
 }
 
+__bpf_kfunc void bpf_crypto_ctx_release_dtor(void *ctx)
+{
+	bpf_crypto_ctx_release(ctx);
+}
+CFI_NOSEAL(bpf_crypto_ctx_release_dtor);
+
 static int bpf_crypto_crypt(const struct bpf_crypto_ctx *ctx,
 			    const struct bpf_dynptr_kern *src,
 			    const struct bpf_dynptr_kern *dst,
@@ -368,7 +374,7 @@ static const struct btf_kfunc_id_set crypt_kfunc_set = {
 
 BTF_ID_LIST(bpf_crypto_dtor_ids)
 BTF_ID(struct, bpf_crypto_ctx)
-BTF_ID(func, bpf_crypto_ctx_release)
+BTF_ID(func, bpf_crypto_ctx_release_dtor)
 
 static int __init crypto_kfunc_init(void)
 {
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index c4fa2268dbbc..dcbf21f61d2e 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -15224,21 +15224,17 @@ static void __scalar64_min_max_lsh(struct bpf_reg_state *dst_reg,
 				   u64 umin_val, u64 umax_val)
 {
 	/* Special case <<32 because it is a common compiler pattern to sign
-	 * extend subreg by doing <<32 s>>32. In this case if 32bit bounds are
-	 * positive we know this shift will also be positive so we can track
-	 * bounds correctly. Otherwise we lose all sign bit information except
-	 * what we can pick up from var_off. Perhaps we can generalize this
-	 * later to shifts of any length.
+	 * extend subreg by doing <<32 s>>32. smin/smax assignments are correct
+	 * because s32 bounds don't flip sign when shifting to the left by
+	 * 32bits.
 	 */
-	if (umin_val == 32 && umax_val == 32 && dst_reg->s32_max_value >= 0)
+	if (umin_val == 32 && umax_val == 32) {
 		dst_reg->smax_value = (s64)dst_reg->s32_max_value << 32;
-	else
-		dst_reg->smax_value = S64_MAX;
-
-	if (umin_val == 32 && umax_val == 32 && dst_reg->s32_min_value >= 0)
 		dst_reg->smin_value = (s64)dst_reg->s32_min_value << 32;
-	else
+	} else {
+		dst_reg->smax_value = S64_MAX;
 		dst_reg->smin_value = S64_MIN;
+	}
 
 	/* If we might shift our top bit out, then we know nothing */
 	if (dst_reg->umax_value > 1ULL << (63 - umax_val)) {
@@ -15422,6 +15418,35 @@ static bool is_safe_to_compute_dst_reg_range(struct bpf_insn *insn,
 	}
 }
 
+static int maybe_fork_scalars(struct bpf_verifier_env *env, struct bpf_insn *insn,
+			      struct bpf_reg_state *dst_reg)
+{
+	struct bpf_verifier_state *branch;
+	struct bpf_reg_state *regs;
+	bool alu32;
+
+	if (dst_reg->smin_value == -1 && dst_reg->smax_value == 0)
+		alu32 = false;
+	else if (dst_reg->s32_min_value == -1 && dst_reg->s32_max_value == 0)
+		alu32 = true;
+	else
+		return 0;
+
+	branch = push_stack(env, env->insn_idx + 1, env->insn_idx, false);
+	if (IS_ERR(branch))
+		return PTR_ERR(branch);
+
+	regs = branch->frame[branch->curframe]->regs;
+	if (alu32) {
+		__mark_reg32_known(&regs[insn->dst_reg], 0);
+		__mark_reg32_known(dst_reg, -1ull);
+	} else {
+		__mark_reg_known(&regs[insn->dst_reg], 0);
+		__mark_reg_known(dst_reg, -1ull);
+	}
+	return 0;
+}
+
 /* WARNING: This function does calculations on 64-bit values, but the actual
  * execution may occur on 32-bit values. Therefore, things like bitshifts
  * need extra checks in the 32-bit case.
@@ -15484,11 +15509,21 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env,
 		scalar_min_max_mul(dst_reg, &src_reg);
 		break;
 	case BPF_AND:
+		if (tnum_is_const(src_reg.var_off)) {
+			ret = maybe_fork_scalars(env, insn, dst_reg);
+			if (ret)
+				return ret;
+		}
 		dst_reg->var_off = tnum_and(dst_reg->var_off, src_reg.var_off);
 		scalar32_min_max_and(dst_reg, &src_reg);
 		scalar_min_max_and(dst_reg, &src_reg);
 		break;
 	case BPF_OR:
+		if (tnum_is_const(src_reg.var_off)) {
+			ret = maybe_fork_scalars(env, insn, dst_reg);
+			if (ret)
+				return ret;
+		}
 		dst_reg->var_off = tnum_or(dst_reg->var_off, src_reg.var_off);
 		scalar32_min_max_or(dst_reg, &src_reg);
 		scalar_min_max_or(dst_reg, &src_reg);
@@ -24257,6 +24292,12 @@ static void compute_insn_live_regs(struct bpf_verifier_env *env,
 	case BPF_JMP32:
 		switch (code) {
 		case BPF_JA:
+			def = 0;
+			if (BPF_SRC(insn->code) == BPF_X)
+				use = dst;
+			else
+				use = 0;
+			break;
 		case BPF_JCOND:
 			def = 0;
 			use = 0;
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index 1245418cc8b3..abaa54037918 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -599,33 +599,31 @@ static inline bool cpusets_are_exclusive(struct cpuset *cs1, struct cpuset *cs2)
 
 /**
  * cpus_excl_conflict - Check if two cpusets have exclusive CPU conflicts
- * @cs1: first cpuset to check
- * @cs2: second cpuset to check
+ * @trial:	the trial cpuset to be checked
+ * @sibling:	a sibling cpuset to be checked against
+ * @xcpus_changed: set if exclusive_cpus has been set
  *
  * Returns: true if CPU exclusivity conflict exists, false otherwise
  *
  * Conflict detection rules:
  * 1. If either cpuset is CPU exclusive, they must be mutually exclusive
  * 2. exclusive_cpus masks cannot intersect between cpusets
- * 3. The allowed CPUs of one cpuset cannot be a subset of another's exclusive CPUs
+ * 3. The allowed CPUs of a sibling cpuset cannot be a subset of the new exclusive CPUs
  */
-static inline bool cpus_excl_conflict(struct cpuset *cs1, struct cpuset *cs2)
+static inline bool cpus_excl_conflict(struct cpuset *trial, struct cpuset *sibling,
+				      bool xcpus_changed)
 {
 	/* If either cpuset is exclusive, check if they are mutually exclusive */
-	if (is_cpu_exclusive(cs1) || is_cpu_exclusive(cs2))
-		return !cpusets_are_exclusive(cs1, cs2);
+	if (is_cpu_exclusive(trial) || is_cpu_exclusive(sibling))
+		return !cpusets_are_exclusive(trial, sibling);
 
 	/* Exclusive_cpus cannot intersect */
-	if (cpumask_intersects(cs1->exclusive_cpus, cs2->exclusive_cpus))
+	if (cpumask_intersects(trial->exclusive_cpus, sibling->exclusive_cpus))
 		return true;
 
-	/* The cpus_allowed of one cpuset cannot be a subset of another cpuset's exclusive_cpus */
-	if (!cpumask_empty(cs1->cpus_allowed) &&
-	    cpumask_subset(cs1->cpus_allowed, cs2->exclusive_cpus))
-		return true;
-
-	if (!cpumask_empty(cs2->cpus_allowed) &&
-	    cpumask_subset(cs2->cpus_allowed, cs1->exclusive_cpus))
+	/* The cpus_allowed of a sibling cpuset cannot be a subset of the new exclusive_cpus */
+	if (xcpus_changed && !cpumask_empty(sibling->cpus_allowed) &&
+	    cpumask_subset(sibling->cpus_allowed, trial->exclusive_cpus))
 		return true;
 
 	return false;
@@ -662,6 +660,7 @@ static int validate_change(struct cpuset *cur, struct cpuset *trial)
 {
 	struct cgroup_subsys_state *css;
 	struct cpuset *c, *par;
+	bool xcpus_changed;
 	int ret = 0;
 
 	rcu_read_lock();
@@ -718,10 +717,11 @@ static int validate_change(struct cpuset *cur, struct cpuset *trial)
 	 * overlap. exclusive_cpus cannot overlap with each other if set.
 	 */
 	ret = -EINVAL;
+	xcpus_changed = !cpumask_equal(cur->exclusive_cpus, trial->exclusive_cpus);
 	cpuset_for_each_child(c, css, par) {
 		if (c == cur)
 			continue;
-		if (cpus_excl_conflict(trial, c))
+		if (cpus_excl_conflict(trial, c, xcpus_changed))
 			goto out;
 		if (mems_excl_conflict(trial, c))
 			goto out;
@@ -4358,40 +4358,58 @@ bool cpuset_current_node_allowed(int node, gfp_t gfp_mask)
 	return allowed;
 }
 
-bool cpuset_node_allowed(struct cgroup *cgroup, int nid)
+/**
+ * cpuset_nodes_allowed - return effective_mems mask from a cgroup cpuset.
+ * @cgroup: pointer to struct cgroup.
+ * @mask: pointer to struct nodemask_t to be returned.
+ *
+ * Returns effective_mems mask from a cgroup cpuset if it is cgroup v2 and
+ * has cpuset subsys. Otherwise, returns node_states[N_MEMORY].
+ *
+ * This function intentionally avoids taking the cpuset_mutex or callback_lock
+ * when accessing effective_mems. This is because the obtained effective_mems
+ * is stale immediately after the query anyway (e.g., effective_mems is updated
+ * immediately after releasing the lock but before returning).
+ *
+ * As a result, returned @mask may be empty because cs->effective_mems can be
+ * rebound during this call. Besides, nodes in @mask are not guaranteed to be
+ * online due to hot plugins. Callers should check the mask for validity on
+ * return based on its subsequent use.
+ **/
+void cpuset_nodes_allowed(struct cgroup *cgroup, nodemask_t *mask)
 {
 	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.
+	 * so return directly to avoid taking a global lock on the empty check.
 	 */
-	if (!cpuset_v2())
-		return true;
+	if (!cgroup || !cpuset_v2()) {
+		nodes_copy(*mask, node_states[N_MEMORY]);
+		return;
+	}
 
 	css = cgroup_get_e_css(cgroup, &cpuset_cgrp_subsys);
-	if (!css)
-		return true;
+	if (!css) {
+		nodes_copy(*mask, node_states[N_MEMORY]);
+		return;
+	}
 
 	/*
-	 * 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.
+	 * The reference taken via cgroup_get_e_css is sufficient to
+	 * protect css, but it does not imply safe accesses to effective_mems.
 	 *
-	 * Reclaim and migration are subject to these same race conditions, and
-	 * cannot make strong isolation guarantees, so this is acceptable.
+	 * Normally, accessing effective_mems would require the cpuset_mutex
+	 * or callback_lock - but the correctness of this information is stale
+	 * immediately after the query anyway. We do not acquire the lock
+	 * during this process to save lock contention in exchange for racing
+	 * against mems_allowed rebinds.
 	 */
 	cs = container_of(css, struct cpuset, css);
-	allowed = node_isset(nid, cs->effective_mems);
+	nodes_copy(*mask, cs->effective_mems);
 	css_put(css);
-	return allowed;
 }
 
 /**
diff --git a/kernel/configs/debug.config b/kernel/configs/debug.config
index e81327d2cd63..1d5d8b0396e9 100644
--- a/kernel/configs/debug.config
+++ b/kernel/configs/debug.config
@@ -29,7 +29,6 @@ CONFIG_SECTION_MISMATCH_WARN_ONLY=y
 # CONFIG_UBSAN_ALIGNMENT is not set
 # CONFIG_UBSAN_DIV_ZERO is not set
 # CONFIG_UBSAN_TRAP is not set
-# CONFIG_WARN_ALL_UNSEEDED_RANDOM is not set
 CONFIG_DEBUG_FS=y
 CONFIG_DEBUG_FS_ALLOW_ALL=y
 CONFIG_DEBUG_IRQFLAGS=y
diff --git a/kernel/crash_dump_dm_crypt.c b/kernel/crash_dump_dm_crypt.c
index 401423ba477d..abb307a23de3 100644
--- a/kernel/crash_dump_dm_crypt.c
+++ b/kernel/crash_dump_dm_crypt.c
@@ -143,6 +143,7 @@ static int read_key_from_user_keying(struct dm_crypt_key *dm_key)
 {
 	const struct user_key_payload *ukp;
 	struct key *key;
+	int ret = 0;
 
 	kexec_dprintk("Requesting logon key %s", dm_key->key_desc);
 	key = request_key(&key_type_logon, dm_key->key_desc, NULL);
@@ -152,20 +153,28 @@ static int read_key_from_user_keying(struct dm_crypt_key *dm_key)
 		return PTR_ERR(key);
 	}
 
+	down_read(&key->sem);
 	ukp = user_key_payload_locked(key);
-	if (!ukp)
-		return -EKEYREVOKED;
+	if (!ukp) {
+		ret = -EKEYREVOKED;
+		goto out;
+	}
 
 	if (ukp->datalen > KEY_SIZE_MAX) {
 		pr_err("Key size %u exceeds maximum (%u)\n", ukp->datalen, KEY_SIZE_MAX);
-		return -EINVAL;
+		ret = -EINVAL;
+		goto out;
 	}
 
 	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;
+
+out:
+	up_read(&key->sem);
+	key_put(key);
+	return ret;
 }
 
 struct config_key {
diff --git a/kernel/dma/direct.h b/kernel/dma/direct.h
index da2fadf45bcd..62f0d9d0ba02 100644
--- a/kernel/dma/direct.h
+++ b/kernel/dma/direct.h
@@ -88,7 +88,7 @@ static inline dma_addr_t dma_direct_map_phys(struct device *dev,
 
 	if (is_swiotlb_force_bounce(dev)) {
 		if (attrs & DMA_ATTR_MMIO)
-			goto err_overflow;
+			return DMA_MAPPING_ERROR;
 
 		return swiotlb_map(dev, phys, size, dir, attrs);
 	}
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 1d8ca8e34f5c..c34b927e5ece 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -5279,9 +5279,20 @@ attach_task_ctx_data(struct task_struct *task, struct kmem_cache *ctx_cache,
 		return -ENOMEM;
 
 	for (;;) {
-		if (try_cmpxchg((struct perf_ctx_data **)&task->perf_ctx_data, &old, cd)) {
+		if (try_cmpxchg(&task->perf_ctx_data, &old, cd)) {
 			if (old)
 				perf_free_ctx_data_rcu(old);
+			/*
+			 * Above try_cmpxchg() pairs with try_cmpxchg() from
+			 * detach_task_ctx_data() such that
+			 * if we race with perf_event_exit_task(), we must
+			 * observe PF_EXITING.
+			 */
+			if (task->flags & PF_EXITING) {
+				/* detach_task_ctx_data() may free it already */
+				if (try_cmpxchg(&task->perf_ctx_data, &cd, NULL))
+					perf_free_ctx_data_rcu(cd);
+			}
 			return 0;
 		}
 
@@ -5327,6 +5338,8 @@ again:
 	/* Allocate everything */
 	scoped_guard (rcu) {
 		for_each_process_thread(g, p) {
+			if (p->flags & PF_EXITING)
+				continue;
 			cd = rcu_dereference(p->perf_ctx_data);
 			if (cd && !cd->global) {
 				cd->global = 1;
@@ -14223,8 +14236,11 @@ void perf_event_exit_task(struct task_struct *task)
 
 	/*
 	 * Detach the perf_ctx_data for the system-wide event.
+	 *
+	 * Done without holding global_ctx_data_rwsem; typically
+	 * attach_global_ctx_data() will skip over this task, but otherwise
+	 * attach_task_ctx_data() will observe PF_EXITING.
 	 */
-	guard(percpu_read)(&global_ctx_data_rwsem);
 	detach_task_ctx_data(task);
 }
 
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index f11ceb8be8c4..4f42e7af575f 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -1138,7 +1138,7 @@ static bool filter_chain(struct uprobe *uprobe, struct mm_struct *mm)
 	bool ret = false;
 
 	down_read(&uprobe->consumer_rwsem);
-	list_for_each_entry_rcu(uc, &uprobe->consumers, cons_node, rcu_read_lock_trace_held()) {
+	list_for_each_entry(uc, &uprobe->consumers, cons_node) {
 		ret = consumer_filter(uc, mm);
 		if (ret)
 			break;
diff --git a/kernel/irq/cpuhotplug.c b/kernel/irq/cpuhotplug.c
index 755346ea9819..cd5689e383b0 100644
--- a/kernel/irq/cpuhotplug.c
+++ b/kernel/irq/cpuhotplug.c
@@ -177,9 +177,11 @@ void irq_migrate_all_off_this_cpu(void)
 		bool affinity_broken;
 
 		desc = irq_to_desc(irq);
-		scoped_guard(raw_spinlock, &desc->lock)
+		scoped_guard(raw_spinlock, &desc->lock) {
 			affinity_broken = migrate_one_irq(desc);
-
+			if (affinity_broken && desc->affinity_notify)
+				irq_affinity_schedule_notify_work(desc);
+		}
 		if (affinity_broken) {
 			pr_debug_ratelimited("IRQ %u: no longer affine to CPU%u\n",
 					    irq, smp_processor_id());
diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h
index 0164ca48da59..5568ed3a8b85 100644
--- a/kernel/irq/internals.h
+++ b/kernel/irq/internals.h
@@ -135,6 +135,7 @@ extern bool irq_can_set_affinity_usr(unsigned int irq);
 
 extern int irq_do_set_affinity(struct irq_data *data,
 			       const struct cpumask *dest, bool force);
+extern void irq_affinity_schedule_notify_work(struct irq_desc *desc);
 
 #ifdef CONFIG_SMP
 extern int irq_setup_affinity(struct irq_desc *desc);
@@ -142,7 +143,6 @@ 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)
 
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 400856abf672..c09751b7a0c4 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -347,6 +347,21 @@ static bool irq_set_affinity_deactivated(struct irq_data *data,
 	return true;
 }
 
+/**
+ * irq_affinity_schedule_notify_work - Schedule work to notify about affinity change
+ * @desc:  Interrupt descriptor whose affinity changed
+ */
+void irq_affinity_schedule_notify_work(struct irq_desc *desc)
+{
+	lockdep_assert_held(&desc->lock);
+
+	kref_get(&desc->affinity_notify->kref);
+	if (!schedule_work(&desc->affinity_notify->work)) {
+		/* Work was already scheduled, drop our extra ref */
+		kref_put(&desc->affinity_notify->kref, desc->affinity_notify->release);
+	}
+}
+
 int irq_set_affinity_locked(struct irq_data *data, const struct cpumask *mask,
 			    bool force)
 {
@@ -367,14 +382,9 @@ int irq_set_affinity_locked(struct irq_data *data, const struct cpumask *mask,
 		irq_copy_pending(desc, mask);
 	}
 
-	if (desc->affinity_notify) {
-		kref_get(&desc->affinity_notify->kref);
-		if (!schedule_work(&desc->affinity_notify->work)) {
-			/* Work was already scheduled, drop our extra ref */
-			kref_put(&desc->affinity_notify->kref,
-				 desc->affinity_notify->release);
-		}
-	}
+	if (desc->affinity_notify)
+		irq_affinity_schedule_notify_work(desc);
+
 	irqd_set(data, IRQD_AFFINITY_SET);
 
 	return ret;
diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c
index eb62a9794242..2bfbb2d144e6 100644
--- a/kernel/kexec_file.c
+++ b/kernel/kexec_file.c
@@ -883,6 +883,60 @@ out_free_sha_regions:
 
 #ifdef CONFIG_ARCH_SUPPORTS_KEXEC_PURGATORY
 /*
+ * kexec_purgatory_find_symbol - find a symbol in the purgatory
+ * @pi:		Purgatory to search in.
+ * @name:	Name of the symbol.
+ *
+ * Return: pointer to symbol in read-only symtab on success, NULL on error.
+ */
+static const Elf_Sym *kexec_purgatory_find_symbol(struct purgatory_info *pi,
+						  const char *name)
+{
+	const Elf_Shdr *sechdrs;
+	const Elf_Ehdr *ehdr;
+	const Elf_Sym *syms;
+	const char *strtab;
+	int i, k;
+
+	if (!pi->ehdr)
+		return NULL;
+
+	ehdr = pi->ehdr;
+	sechdrs = (void *)ehdr + ehdr->e_shoff;
+
+	for (i = 0; i < ehdr->e_shnum; i++) {
+		if (sechdrs[i].sh_type != SHT_SYMTAB)
+			continue;
+
+		if (sechdrs[i].sh_link >= ehdr->e_shnum)
+			/* Invalid strtab section number */
+			continue;
+		strtab = (void *)ehdr + sechdrs[sechdrs[i].sh_link].sh_offset;
+		syms = (void *)ehdr + sechdrs[i].sh_offset;
+
+		/* Go through symbols for a match */
+		for (k = 0; k < sechdrs[i].sh_size/sizeof(Elf_Sym); k++) {
+			if (ELF_ST_BIND(syms[k].st_info) != STB_GLOBAL)
+				continue;
+
+			if (strcmp(strtab + syms[k].st_name, name) != 0)
+				continue;
+
+			if (syms[k].st_shndx == SHN_UNDEF ||
+			    syms[k].st_shndx >= ehdr->e_shnum) {
+				pr_debug("Symbol: %s has bad section index %d.\n",
+					name, syms[k].st_shndx);
+				return NULL;
+			}
+
+			/* Found the symbol we are looking for */
+			return &syms[k];
+		}
+	}
+
+	return NULL;
+}
+/*
  * kexec_purgatory_setup_kbuf - prepare buffer to load purgatory.
  * @pi:		Purgatory to be loaded.
  * @kbuf:	Buffer to setup.
@@ -960,6 +1014,10 @@ static int kexec_purgatory_setup_sechdrs(struct purgatory_info *pi,
 	unsigned long offset;
 	size_t sechdrs_size;
 	Elf_Shdr *sechdrs;
+	const Elf_Sym *entry_sym;
+	u16 entry_shndx = 0;
+	unsigned long entry_off = 0;
+	bool start_fixed = false;
 	int i;
 
 	/*
@@ -977,6 +1035,12 @@ static int kexec_purgatory_setup_sechdrs(struct purgatory_info *pi,
 	bss_addr = kbuf->mem + kbuf->bufsz;
 	kbuf->image->start = pi->ehdr->e_entry;
 
+	entry_sym = kexec_purgatory_find_symbol(pi, "purgatory_start");
+	if (entry_sym) {
+		entry_shndx = entry_sym->st_shndx;
+		entry_off = entry_sym->st_value;
+	}
+
 	for (i = 0; i < pi->ehdr->e_shnum; i++) {
 		unsigned long align;
 		void *src, *dst;
@@ -994,6 +1058,13 @@ static int kexec_purgatory_setup_sechdrs(struct purgatory_info *pi,
 
 		offset = ALIGN(offset, align);
 
+		if (!start_fixed && entry_sym && i == entry_shndx &&
+		    (sechdrs[i].sh_flags & SHF_EXECINSTR) &&
+		    entry_off < sechdrs[i].sh_size) {
+			kbuf->image->start = kbuf->mem + offset + entry_off;
+			start_fixed = true;
+		}
+
 		/*
 		 * Check if the segment contains the entry point, if so,
 		 * calculate the value of image->start based on it.
@@ -1004,13 +1075,14 @@ static int kexec_purgatory_setup_sechdrs(struct purgatory_info *pi,
 		 * 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 &&
+		if (!start_fixed && 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) &&
-		    !WARN_ON(kbuf->image->start != pi->ehdr->e_entry)) {
+		    kbuf->image->start == pi->ehdr->e_entry) {
 			kbuf->image->start -= sechdrs[i].sh_addr;
 			kbuf->image->start += kbuf->mem + offset;
+			start_fixed = true;
 		}
 
 		src = (void *)pi->ehdr + sechdrs[i].sh_offset;
@@ -1128,61 +1200,6 @@ out_free_kbuf:
 	return ret;
 }
 
-/*
- * kexec_purgatory_find_symbol - find a symbol in the purgatory
- * @pi:		Purgatory to search in.
- * @name:	Name of the symbol.
- *
- * Return: pointer to symbol in read-only symtab on success, NULL on error.
- */
-static const Elf_Sym *kexec_purgatory_find_symbol(struct purgatory_info *pi,
-						  const char *name)
-{
-	const Elf_Shdr *sechdrs;
-	const Elf_Ehdr *ehdr;
-	const Elf_Sym *syms;
-	const char *strtab;
-	int i, k;
-
-	if (!pi->ehdr)
-		return NULL;
-
-	ehdr = pi->ehdr;
-	sechdrs = (void *)ehdr + ehdr->e_shoff;
-
-	for (i = 0; i < ehdr->e_shnum; i++) {
-		if (sechdrs[i].sh_type != SHT_SYMTAB)
-			continue;
-
-		if (sechdrs[i].sh_link >= ehdr->e_shnum)
-			/* Invalid strtab section number */
-			continue;
-		strtab = (void *)ehdr + sechdrs[sechdrs[i].sh_link].sh_offset;
-		syms = (void *)ehdr + sechdrs[i].sh_offset;
-
-		/* Go through symbols for a match */
-		for (k = 0; k < sechdrs[i].sh_size/sizeof(Elf_Sym); k++) {
-			if (ELF_ST_BIND(syms[k].st_info) != STB_GLOBAL)
-				continue;
-
-			if (strcmp(strtab + syms[k].st_name, name) != 0)
-				continue;
-
-			if (syms[k].st_shndx == SHN_UNDEF ||
-			    syms[k].st_shndx >= ehdr->e_shnum) {
-				pr_debug("Symbol: %s has bad section index %d.\n",
-						name, syms[k].st_shndx);
-				return NULL;
-			}
-
-			/* Found the symbol we are looking for */
-			return &syms[k];
-		}
-	}
-
-	return NULL;
-}
-
 void *kexec_purgatory_get_symbol_addr(struct kimage *image, const char *name)
 {
 	struct purgatory_info *pi = &image->purgatory_info;
diff --git a/kernel/kexec_handover.c b/kernel/kexec_handover.c
index 03d12e27189f..2da4bd994322 100644
--- a/kernel/kexec_handover.c
+++ b/kernel/kexec_handover.c
@@ -619,7 +619,7 @@ static void __init kho_reserve_scratch(void)
 	scratch_size_update();
 
 	/* FIXME: deal with node hot-plug/remove */
-	kho_scratch_cnt = num_online_nodes() + 2;
+	kho_scratch_cnt = nodes_weight(node_states[N_MEMORY]) + 2;
 	size = kho_scratch_cnt * sizeof(*kho_scratch);
 	kho_scratch = memblock_alloc(size, PAGE_SIZE);
 	if (!kho_scratch)
@@ -649,7 +649,11 @@ static void __init kho_reserve_scratch(void)
 	kho_scratch[i].size = size;
 	i++;
 
-	for_each_online_node(nid) {
+	/*
+	 * Loop over nodes that have both memory and are online. Skip
+	 * memoryless nodes, as we can not allocate scratch areas there.
+	 */
+	for_each_node_state(nid, N_MEMORY) {
 		size = scratch_size_node(nid);
 		addr = memblock_alloc_range_nid(size, CMA_MIN_ALIGNMENT_BYTES,
 						0, MEMBLOCK_ALLOC_ACCESSIBLE,
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 41caa22e0680..93f009e1076d 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -345,8 +345,8 @@ static ssize_t sched_fair_server_write(struct file *filp, const char __user *ubu
 	long cpu = (long) ((struct seq_file *) filp->private_data)->private;
 	struct rq *rq = cpu_rq(cpu);
 	u64 runtime, period;
+	int retval = 0;
 	size_t err;
-	int retval;
 	u64 value;
 
 	err = kstrtoull_from_user(ubuf, cnt, 10, &value);
@@ -380,8 +380,6 @@ static ssize_t sched_fair_server_write(struct file *filp, const char __user *ubu
 		dl_server_stop(&rq->fair_server);
 
 		retval = dl_server_apply_params(&rq->fair_server, runtime, period, 0);
-		if (retval)
-			cnt = retval;
 
 		if (!runtime)
 			printk_deferred("Fair server disabled in CPU %d, system may crash due to starvation.\n",
@@ -389,6 +387,9 @@ static ssize_t sched_fair_server_write(struct file *filp, const char __user *ubu
 
 		if (rq->cfs.h_nr_queued)
 			dl_server_start(&rq->fair_server);
+
+		if (retval < 0)
+			return retval;
 	}
 
 	*ppos += cnt;
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index e7f1fe44352a..ae64b261de8e 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -2564,6 +2564,7 @@ kprobe_multi_link_prog_run(struct bpf_kprobe_multi_link *link,
 	old_run_ctx = bpf_set_run_ctx(&run_ctx.session_ctx.run_ctx);
 	err = bpf_prog_run(link->link.prog, regs);
 	bpf_reset_run_ctx(old_run_ctx);
+	ftrace_partial_regs_update(fregs, bpf_kprobe_multi_pt_regs_ptr());
 	rcu_read_unlock();
 
  out:
diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c
index 599f2939cd94..234fd9d45b56 100644
--- a/kernel/trace/fgraph.c
+++ b/kernel/trace/fgraph.c
@@ -542,7 +542,11 @@ static struct fgraph_ops fgraph_stub = {
 static struct fgraph_ops *fgraph_direct_gops = &fgraph_stub;
 DEFINE_STATIC_CALL(fgraph_func, ftrace_graph_entry_stub);
 DEFINE_STATIC_CALL(fgraph_retfunc, ftrace_graph_ret_stub);
+#if FGRAPH_NO_DIRECT
+static DEFINE_STATIC_KEY_FALSE(fgraph_do_direct);
+#else
 static DEFINE_STATIC_KEY_TRUE(fgraph_do_direct);
+#endif
 
 /**
  * ftrace_graph_stop - set to permanently disable function graph tracing
@@ -846,7 +850,7 @@ __ftrace_return_to_handler(struct ftrace_regs *fregs, unsigned long frame_pointe
 	bitmap = get_bitmap_bits(current, offset);
 
 #ifdef CONFIG_HAVE_STATIC_CALL
-	if (static_branch_likely(&fgraph_do_direct)) {
+	if (!FGRAPH_NO_DIRECT && static_branch_likely(&fgraph_do_direct)) {
 		if (test_bit(fgraph_direct_gops->idx, &bitmap))
 			static_call(fgraph_retfunc)(&trace, fgraph_direct_gops, fregs);
 	} else
@@ -1293,6 +1297,9 @@ static void ftrace_graph_enable_direct(bool enable_branch, struct fgraph_ops *go
 	trace_func_graph_ret_t retfunc = NULL;
 	int i;
 
+	if (FGRAPH_NO_DIRECT)
+		return;
+
 	if (gops) {
 		func = gops->entryfunc;
 		retfunc = gops->retfunc;
@@ -1311,11 +1318,14 @@ static void ftrace_graph_enable_direct(bool enable_branch, struct fgraph_ops *go
 	static_call_update(fgraph_func, func);
 	static_call_update(fgraph_retfunc, retfunc);
 	if (enable_branch)
-		static_branch_disable(&fgraph_do_direct);
+		static_branch_enable(&fgraph_do_direct);
 }
 
 static void ftrace_graph_disable_direct(bool disable_branch)
 {
+	if (FGRAPH_NO_DIRECT)
+		return;
+
 	if (disable_branch)
 		static_branch_disable(&fgraph_do_direct);
 	static_call_update(fgraph_func, ftrace_graph_entry_stub);
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 3ba08fc1b7d0..54d70bd0a3cb 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -1813,6 +1813,7 @@ static int rb_read_data_buffer(struct buffer_data_page *dpage, int tail, int cpu
 	struct ring_buffer_event *event;
 	u64 ts, delta;
 	int events = 0;
+	int len;
 	int e;
 
 	*delta_ptr = 0;
@@ -1820,9 +1821,12 @@ static int rb_read_data_buffer(struct buffer_data_page *dpage, int tail, int cpu
 
 	ts = dpage->time_stamp;
 
-	for (e = 0; e < tail; e += rb_event_length(event)) {
+	for (e = 0; e < tail; e += len) {
 
 		event = (struct ring_buffer_event *)(dpage->data + e);
+		len = rb_event_length(event);
+		if (len <= 0 || len > tail - e)
+			return -1;
 
 		switch (event->type_len) {
 
@@ -1883,6 +1887,8 @@ static void rb_meta_validate_events(struct ring_buffer_per_cpu *cpu_buffer)
 	if (!meta || !meta->head_buffer)
 		return;
 
+	orig_head = head_page = cpu_buffer->head_page;
+
 	/* Do the reader page first */
 	ret = rb_validate_buffer(cpu_buffer->reader_page->page, cpu_buffer->cpu);
 	if (ret < 0) {
@@ -1893,7 +1899,6 @@ static void rb_meta_validate_events(struct ring_buffer_per_cpu *cpu_buffer)
 	entry_bytes += local_read(&cpu_buffer->reader_page->page->commit);
 	local_set(&cpu_buffer->reader_page->entries, ret);
 
-	orig_head = head_page = cpu_buffer->head_page;
 	ts = head_page->page->time_stamp;
 
 	/*
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 907923d5f8bb..d2eabc162205 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -4852,6 +4852,8 @@ static int tracing_single_release_tr(struct inode *inode, struct file *file)
 	return single_release(inode, file);
 }
 
+static bool update_last_data_if_empty(struct trace_array *tr);
+
 static int tracing_open(struct inode *inode, struct file *file)
 {
 	struct trace_array *tr = inode->i_private;
@@ -4876,6 +4878,8 @@ static int tracing_open(struct inode *inode, struct file *file)
 			tracing_reset_online_cpus(trace_buf);
 		else
 			tracing_reset_cpu(trace_buf, cpu);
+
+		update_last_data_if_empty(tr);
 	}
 
 	if (file->f_mode & FMODE_READ) {
@@ -5917,6 +5921,7 @@ tracing_set_trace_read(struct file *filp, char __user *ubuf,
 int tracer_init(struct tracer *t, struct trace_array *tr)
 {
 	tracing_reset_online_cpus(&tr->array_buffer);
+	update_last_data_if_empty(tr);
 	return t->init(tr);
 }
 
@@ -7582,6 +7587,7 @@ int tracing_set_clock(struct trace_array *tr, const char *clockstr)
 		ring_buffer_set_clock(tr->max_buffer.buffer, trace_clocks[i].func);
 	tracing_reset_online_cpus(&tr->max_buffer);
 #endif
+	update_last_data_if_empty(tr);
 
 	if (tr->scratch && !(tr->flags & TRACE_ARRAY_FL_LAST_BOOT)) {
 		struct trace_scratch *tscratch = tr->scratch;
@@ -9183,7 +9189,7 @@ tracing_init_tracefs_percpu(struct trace_array *tr, long cpu)
 	trace_create_cpu_file("stats", TRACE_MODE_READ, d_cpu,
 				tr, cpu, &tracing_stats_fops);
 
-	trace_create_cpu_file("buffer_size_kb", TRACE_MODE_READ, d_cpu,
+	trace_create_cpu_file("buffer_size_kb", TRACE_MODE_WRITE, d_cpu,
 				tr, cpu, &tracing_entries_fops);
 
 	if (tr->range_addr_start)
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 5cf55a9c6fad..e4ce7f856f63 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -1296,6 +1296,9 @@ static void remove_event_file_dir(struct trace_event_file *file)
 	free_event_filter(file->filter);
 	file->flags |= EVENT_FILE_FL_FREED;
 	event_file_put(file);
+
+	/* Wake up hist poll waiters to notice the EVENT_FILE_FL_FREED flag. */
+	hist_poll_wakeup();
 }
 
 /*
diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
index 45727c4cf954..2a0726e1bc97 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -5778,7 +5778,7 @@ static __poll_t event_hist_poll(struct file *file, struct poll_table_struct *wai
 
 	guard(mutex)(&event_mutex);
 
-	event_file = event_file_data(file);
+	event_file = event_file_file(file);
 	if (!event_file)
 		return EPOLLERR;
 
@@ -5816,7 +5816,7 @@ static int event_hist_open(struct inode *inode, struct file *file)
 
 	guard(mutex)(&event_mutex);
 
-	event_file = event_file_data(file);
+	event_file = event_file_file(file);
 	if (!event_file) {
 		ret = -ENODEV;
 		goto err;
diff --git a/kernel/trace/trace_hwlat.c b/kernel/trace/trace_hwlat.c
index 2f7b94e98317..3fe274b84f1c 100644
--- a/kernel/trace/trace_hwlat.c
+++ b/kernel/trace/trace_hwlat.c
@@ -102,9 +102,9 @@ struct hwlat_sample {
 /* keep the global state somewhere. */
 static struct hwlat_data {
 
-	struct mutex lock;		/* protect changes */
+	struct mutex	lock;		/* protect changes */
 
-	u64	count;			/* total since reset */
+	atomic64_t	count;		/* total since reset */
 
 	u64	sample_window;		/* total sampling window (on+off) */
 	u64	sample_width;		/* active sampling portion of window */
@@ -193,8 +193,7 @@ void trace_hwlat_callback(bool enter)
  * get_sample - sample the CPU TSC and look for likely hardware latencies
  *
  * Used to repeatedly capture the CPU TSC (or similar), looking for potential
- * hardware-induced latency. Called with interrupts disabled and with
- * hwlat_data.lock held.
+ * hardware-induced latency. Called with interrupts disabled.
  */
 static int get_sample(void)
 {
@@ -204,6 +203,7 @@ static int get_sample(void)
 	time_type start, t1, t2, last_t2;
 	s64 diff, outer_diff, total, last_total = 0;
 	u64 sample = 0;
+	u64 sample_width = READ_ONCE(hwlat_data.sample_width);
 	u64 thresh = tracing_thresh;
 	u64 outer_sample = 0;
 	int ret = -1;
@@ -267,7 +267,7 @@ static int get_sample(void)
 		if (diff > sample)
 			sample = diff; /* only want highest value */
 
-	} while (total <= hwlat_data.sample_width);
+	} while (total <= sample_width);
 
 	barrier(); /* finish the above in the view for NMIs */
 	trace_hwlat_callback_enabled = false;
@@ -285,8 +285,7 @@ static int get_sample(void)
 		if (kdata->nmi_total_ts)
 			do_div(kdata->nmi_total_ts, NSEC_PER_USEC);
 
-		hwlat_data.count++;
-		s.seqnum = hwlat_data.count;
+		s.seqnum = atomic64_inc_return(&hwlat_data.count);
 		s.duration = sample;
 		s.outer_duration = outer_sample;
 		s.nmi_total_ts = kdata->nmi_total_ts;
@@ -832,7 +831,7 @@ static int hwlat_tracer_init(struct trace_array *tr)
 
 	hwlat_trace = tr;
 
-	hwlat_data.count = 0;
+	atomic64_set(&hwlat_data.count, 0);
 	tr->max_latency = 0;
 	save_tracing_thresh = tracing_thresh;
 
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index 5b62d1002783..25d134306e14 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -521,7 +521,7 @@ static bool need_counting_irqs(void)
 	u8 util;
 	int tail = __this_cpu_read(cpustat_tail);
 
-	tail = (tail + NUM_HARDIRQ_REPORT - 1) % NUM_HARDIRQ_REPORT;
+	tail = (tail + NUM_SAMPLE_PERIODS - 1) % NUM_SAMPLE_PERIODS;
 	util = __this_cpu_read(cpustat_util[tail][STATS_HARDIRQ]);
 	return util > HARDIRQ_PERCENT_THRESH;
 }