18 files changed, 162 insertions, 77 deletions
diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c
index 72fa4bb78f0a..fee42a73d64a 100644
--- a/arch/x86/kernel/apic/vector.c
+++ b/arch/x86/kernel/apic/vector.c
@@ -799,7 +799,7 @@ int __init arch_early_irq_init(void)
 	x86_vector_domain = irq_domain_create_tree(fn, &x86_vector_domain_ops,
 						   NULL);
 	BUG_ON(x86_vector_domain == NULL);
-	irq_set_default_host(x86_vector_domain);
+	irq_set_default_domain(x86_vector_domain);
 
 	BUG_ON(!alloc_cpumask_var(&vector_searchmask, GFP_KERNEL));
 
diff --git a/arch/x86/kernel/callthunks.c b/arch/x86/kernel/callthunks.c
index 25ae54250112..d86d7d6e750c 100644
--- a/arch/x86/kernel/callthunks.c
+++ b/arch/x86/kernel/callthunks.c
@@ -98,11 +98,10 @@ static inline bool within_module_coretext(void *addr)
 #ifdef CONFIG_MODULES
 	struct module *mod;
 
-	preempt_disable();
+	guard(rcu)();
 	mod = __module_address((unsigned long)addr);
 	if (mod && within_module_core((unsigned long)addr, mod))
 		ret = true;
-	preempt_enable();
 #endif
 	return ret;
 }
diff --git a/arch/x86/kernel/cpu/bus_lock.c b/arch/x86/kernel/cpu/bus_lock.c
index 97222efb4d2a..237faf7e700c 100644
--- a/arch/x86/kernel/cpu/bus_lock.c
+++ b/arch/x86/kernel/cpu/bus_lock.c
@@ -201,6 +201,26 @@ static void __split_lock_reenable(struct work_struct *work)
 static DEFINE_PER_CPU(struct delayed_work, sl_reenable);
 
 /*
+ * Per-CPU delayed_work can't be statically initialized properly because
+ * the struct address is unknown. Thus per-CPU delayed_work structures
+ * have to be initialized during kernel initialization and after calling
+ * setup_per_cpu_areas().
+ */
+static int __init setup_split_lock_delayed_work(void)
+{
+	unsigned int cpu;
+
+	for_each_possible_cpu(cpu) {
+		struct delayed_work *work = per_cpu_ptr(&sl_reenable, cpu);
+
+		INIT_DELAYED_WORK(work, __split_lock_reenable);
+	}
+
+	return 0;
+}
+pure_initcall(setup_split_lock_delayed_work);
+
+/*
  * If a CPU goes offline with pending delayed work to re-enable split lock
  * detection then the delayed work will be executed on some other CPU. That
  * handles releasing the buslock_sem, but because it executes on a
@@ -219,15 +239,16 @@ static int splitlock_cpu_offline(unsigned int cpu)
 
 static void split_lock_warn(unsigned long ip)
 {
-	struct delayed_work *work = NULL;
+	struct delayed_work *work;
 	int cpu;
+	unsigned int saved_sld_mitigate = READ_ONCE(sysctl_sld_mitigate);
 
 	if (!current->reported_split_lock)
 		pr_warn_ratelimited("#AC: %s/%d took a split_lock trap at address: 0x%lx\n",
 				    current->comm, current->pid, ip);
 	current->reported_split_lock = 1;
 
-	if (sysctl_sld_mitigate) {
+	if (saved_sld_mitigate) {
 		/*
 		 * misery factor #1:
 		 * sleep 10ms before trying to execute split lock.
@@ -240,18 +261,10 @@ static void split_lock_warn(unsigned long ip)
 		 */
 		if (down_interruptible(&buslock_sem) == -EINTR)
 			return;
-		work = &sl_reenable_unlock;
 	}
 
 	cpu = get_cpu();
-
-	if (!work) {
-		work = this_cpu_ptr(&sl_reenable);
-		/* Deferred initialization of per-CPU struct */
-		if (!work->work.func)
-			INIT_DELAYED_WORK(work, __split_lock_reenable);
-	}
-
+	work = saved_sld_mitigate ? &sl_reenable_unlock : per_cpu_ptr(&sl_reenable, cpu);
 	schedule_delayed_work_on(cpu, work, 2);
 
 	/* Disable split lock detection on this CPU to make progress */
diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index 1f14c3308b6b..f6fd71b64b66 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -1786,13 +1786,13 @@ void mce_timer_kick(bool storm)
 		__this_cpu_write(mce_next_interval, check_interval * HZ);
 }
 
-/* Must not be called in IRQ context where del_timer_sync() can deadlock */
+/* Must not be called in IRQ context where timer_delete_sync() can deadlock */
 static void mce_timer_delete_all(void)
 {
 	int cpu;
 
 	for_each_online_cpu(cpu)
-		del_timer_sync(&per_cpu(mce_timer, cpu));
+		timer_delete_sync(&per_cpu(mce_timer, cpu));
 }
 
 static void __mcheck_cpu_mce_banks_init(void)
@@ -2820,7 +2820,7 @@ static int mce_cpu_pre_down(unsigned int cpu)
 	struct timer_list *t = this_cpu_ptr(&mce_timer);
 
 	mce_disable_cpu();
-	del_timer_sync(t);
+	timer_delete_sync(t);
 	mce_threshold_remove_device(cpu);
 	mce_device_remove(cpu);
 	return 0;
diff --git a/arch/x86/kernel/cpu/mce/severity.c b/arch/x86/kernel/cpu/mce/severity.c
index dac4d64dfb2a..2235a7477436 100644
--- a/arch/x86/kernel/cpu/mce/severity.c
+++ b/arch/x86/kernel/cpu/mce/severity.c
@@ -300,13 +300,12 @@ static noinstr int error_context(struct mce *m, struct pt_regs *regs)
 	copy_user  = is_copy_from_user(regs);
 	instrumentation_end();
 
-	switch (fixup_type) {
-	case EX_TYPE_UACCESS:
-		if (!copy_user)
-			return IN_KERNEL;
-		m->kflags |= MCE_IN_KERNEL_COPYIN;
-		fallthrough;
+	if (copy_user) {
+		m->kflags |= MCE_IN_KERNEL_COPYIN | MCE_IN_KERNEL_RECOV;
+		return IN_KERNEL_RECOV;
+	}
 
+	switch (fixup_type) {
 	case EX_TYPE_FAULT_MCE_SAFE:
 	case EX_TYPE_DEFAULT_MCE_SAFE:
 		m->kflags |= MCE_IN_KERNEL_RECOV;
diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c
index 138689b8e1d8..b61028cf5c8a 100644
--- a/arch/x86/kernel/cpu/microcode/amd.c
+++ b/arch/x86/kernel/cpu/microcode/amd.c
@@ -600,7 +600,7 @@ static bool __apply_microcode_amd(struct microcode_amd *mc, u32 *cur_rev,
 	unsigned long p_addr = (unsigned long)&mc->hdr.data_code;
 
 	if (!verify_sha256_digest(mc->hdr.patch_id, *cur_rev, (const u8 *)p_addr, psize))
-		return -1;
+		return false;
 
 	native_wrmsrl(MSR_AMD64_PATCH_LOADER, p_addr);
 
diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h
index c44c5b496355..eaae99602b61 100644
--- a/arch/x86/kernel/cpu/resctrl/internal.h
+++ b/arch/x86/kernel/cpu/resctrl/internal.h
@@ -403,6 +403,11 @@ static inline struct rdt_hw_resource *resctrl_to_arch_res(struct rdt_resource *r
 
 extern struct mutex rdtgroup_mutex;
 
+static inline const char *rdt_kn_name(const struct kernfs_node *kn)
+{
+	return rcu_dereference_check(kn->name, lockdep_is_held(&rdtgroup_mutex));
+}
+
 extern struct rdt_hw_resource rdt_resources_all[];
 extern struct rdtgroup rdtgroup_default;
 extern struct dentry *debugfs_resctrl;
diff --git a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c
index 01fa7890b43f..92ea1472bde9 100644
--- a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c
+++ b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c
@@ -52,7 +52,8 @@ static char *pseudo_lock_devnode(const struct device *dev, umode_t *mode)
 	rdtgrp = dev_get_drvdata(dev);
 	if (mode)
 		*mode = 0600;
-	return kasprintf(GFP_KERNEL, "pseudo_lock/%s", rdtgrp->kn->name);
+	guard(mutex)(&rdtgroup_mutex);
+	return kasprintf(GFP_KERNEL, "pseudo_lock/%s", rdt_kn_name(rdtgrp->kn));
 }
 
 static const struct class pseudo_lock_class = {
@@ -1298,6 +1299,7 @@ int rdtgroup_pseudo_lock_create(struct rdtgroup *rdtgrp)
 	struct task_struct *thread;
 	unsigned int new_minor;
 	struct device *dev;
+	char *kn_name __free(kfree) = NULL;
 	int ret;
 
 	ret = pseudo_lock_region_alloc(plr);
@@ -1309,6 +1311,11 @@ int rdtgroup_pseudo_lock_create(struct rdtgroup *rdtgrp)
 		ret = -EINVAL;
 		goto out_region;
 	}
+	kn_name = kstrdup(rdt_kn_name(rdtgrp->kn), GFP_KERNEL);
+	if (!kn_name) {
+		ret = -ENOMEM;
+		goto out_cstates;
+	}
 
 	plr->thread_done = 0;
 
@@ -1353,8 +1360,7 @@ int rdtgroup_pseudo_lock_create(struct rdtgroup *rdtgrp)
 	mutex_unlock(&rdtgroup_mutex);
 
 	if (!IS_ERR_OR_NULL(debugfs_resctrl)) {
-		plr->debugfs_dir = debugfs_create_dir(rdtgrp->kn->name,
-						      debugfs_resctrl);
+		plr->debugfs_dir = debugfs_create_dir(kn_name, debugfs_resctrl);
 		if (!IS_ERR_OR_NULL(plr->debugfs_dir))
 			debugfs_create_file("pseudo_lock_measure", 0200,
 					    plr->debugfs_dir, rdtgrp,
@@ -1363,7 +1369,7 @@ int rdtgroup_pseudo_lock_create(struct rdtgroup *rdtgrp)
 
 	dev = device_create(&pseudo_lock_class, NULL,
 			    MKDEV(pseudo_lock_major, new_minor),
-			    rdtgrp, "%s", rdtgrp->kn->name);
+			    rdtgrp, "%s", kn_name);
 
 	mutex_lock(&rdtgroup_mutex);
 
diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index c6274d40b217..93ec829015f1 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -944,14 +944,14 @@ int proc_resctrl_show(struct seq_file *s, struct pid_namespace *ns,
 			continue;
 
 		seq_printf(s, "res:%s%s\n", (rdtg == &rdtgroup_default) ? "/" : "",
-			   rdtg->kn->name);
+			   rdt_kn_name(rdtg->kn));
 		seq_puts(s, "mon:");
 		list_for_each_entry(crg, &rdtg->mon.crdtgrp_list,
 				    mon.crdtgrp_list) {
 			if (!resctrl_arch_match_rmid(tsk, crg->mon.parent->closid,
 						     crg->mon.rmid))
 				continue;
-			seq_printf(s, "%s", crg->kn->name);
+			seq_printf(s, "%s", rdt_kn_name(crg->kn));
 			break;
 		}
 		seq_putc(s, '\n');
@@ -984,10 +984,20 @@ static int rdt_last_cmd_status_show(struct kernfs_open_file *of,
 	return 0;
 }
 
+static void *rdt_kn_parent_priv(struct kernfs_node *kn)
+{
+	/*
+	 * The parent pointer is only valid within RCU section since it can be
+	 * replaced.
+	 */
+	guard(rcu)();
+	return rcu_dereference(kn->__parent)->priv;
+}
+
 static int rdt_num_closids_show(struct kernfs_open_file *of,
 				struct seq_file *seq, void *v)
 {
-	struct resctrl_schema *s = of->kn->parent->priv;
+	struct resctrl_schema *s = rdt_kn_parent_priv(of->kn);
 
 	seq_printf(seq, "%u\n", s->num_closid);
 	return 0;
@@ -996,7 +1006,7 @@ static int rdt_num_closids_show(struct kernfs_open_file *of,
 static int rdt_default_ctrl_show(struct kernfs_open_file *of,
 			     struct seq_file *seq, void *v)
 {
-	struct resctrl_schema *s = of->kn->parent->priv;
+	struct resctrl_schema *s = rdt_kn_parent_priv(of->kn);
 	struct rdt_resource *r = s->res;
 
 	seq_printf(seq, "%x\n", resctrl_get_default_ctrl(r));
@@ -1006,7 +1016,7 @@ static int rdt_default_ctrl_show(struct kernfs_open_file *of,
 static int rdt_min_cbm_bits_show(struct kernfs_open_file *of,
 			     struct seq_file *seq, void *v)
 {
-	struct resctrl_schema *s = of->kn->parent->priv;
+	struct resctrl_schema *s = rdt_kn_parent_priv(of->kn);
 	struct rdt_resource *r = s->res;
 
 	seq_printf(seq, "%u\n", r->cache.min_cbm_bits);
@@ -1016,7 +1026,7 @@ static int rdt_min_cbm_bits_show(struct kernfs_open_file *of,
 static int rdt_shareable_bits_show(struct kernfs_open_file *of,
 				   struct seq_file *seq, void *v)
 {
-	struct resctrl_schema *s = of->kn->parent->priv;
+	struct resctrl_schema *s = rdt_kn_parent_priv(of->kn);
 	struct rdt_resource *r = s->res;
 
 	seq_printf(seq, "%x\n", r->cache.shareable_bits);
@@ -1040,7 +1050,7 @@ static int rdt_shareable_bits_show(struct kernfs_open_file *of,
 static int rdt_bit_usage_show(struct kernfs_open_file *of,
 			      struct seq_file *seq, void *v)
 {
-	struct resctrl_schema *s = of->kn->parent->priv;
+	struct resctrl_schema *s = rdt_kn_parent_priv(of->kn);
 	/*
 	 * Use unsigned long even though only 32 bits are used to ensure
 	 * test_bit() is used safely.
@@ -1122,7 +1132,7 @@ static int rdt_bit_usage_show(struct kernfs_open_file *of,
 static int rdt_min_bw_show(struct kernfs_open_file *of,
 			     struct seq_file *seq, void *v)
 {
-	struct resctrl_schema *s = of->kn->parent->priv;
+	struct resctrl_schema *s = rdt_kn_parent_priv(of->kn);
 	struct rdt_resource *r = s->res;
 
 	seq_printf(seq, "%u\n", r->membw.min_bw);
@@ -1132,7 +1142,7 @@ static int rdt_min_bw_show(struct kernfs_open_file *of,
 static int rdt_num_rmids_show(struct kernfs_open_file *of,
 			      struct seq_file *seq, void *v)
 {
-	struct rdt_resource *r = of->kn->parent->priv;
+	struct rdt_resource *r = rdt_kn_parent_priv(of->kn);
 
 	seq_printf(seq, "%d\n", r->num_rmid);
 
@@ -1142,7 +1152,7 @@ static int rdt_num_rmids_show(struct kernfs_open_file *of,
 static int rdt_mon_features_show(struct kernfs_open_file *of,
 				 struct seq_file *seq, void *v)
 {
-	struct rdt_resource *r = of->kn->parent->priv;
+	struct rdt_resource *r = rdt_kn_parent_priv(of->kn);
 	struct mon_evt *mevt;
 
 	list_for_each_entry(mevt, &r->evt_list, list) {
@@ -1157,7 +1167,7 @@ static int rdt_mon_features_show(struct kernfs_open_file *of,
 static int rdt_bw_gran_show(struct kernfs_open_file *of,
 			     struct seq_file *seq, void *v)
 {
-	struct resctrl_schema *s = of->kn->parent->priv;
+	struct resctrl_schema *s = rdt_kn_parent_priv(of->kn);
 	struct rdt_resource *r = s->res;
 
 	seq_printf(seq, "%u\n", r->membw.bw_gran);
@@ -1167,7 +1177,7 @@ static int rdt_bw_gran_show(struct kernfs_open_file *of,
 static int rdt_delay_linear_show(struct kernfs_open_file *of,
 			     struct seq_file *seq, void *v)
 {
-	struct resctrl_schema *s = of->kn->parent->priv;
+	struct resctrl_schema *s = rdt_kn_parent_priv(of->kn);
 	struct rdt_resource *r = s->res;
 
 	seq_printf(seq, "%u\n", r->membw.delay_linear);
@@ -1185,7 +1195,7 @@ static int max_threshold_occ_show(struct kernfs_open_file *of,
 static int rdt_thread_throttle_mode_show(struct kernfs_open_file *of,
 					 struct seq_file *seq, void *v)
 {
-	struct resctrl_schema *s = of->kn->parent->priv;
+	struct resctrl_schema *s = rdt_kn_parent_priv(of->kn);
 	struct rdt_resource *r = s->res;
 
 	switch (r->membw.throttle_mode) {
@@ -1259,7 +1269,7 @@ static enum resctrl_conf_type resctrl_peer_type(enum resctrl_conf_type my_type)
 static int rdt_has_sparse_bitmasks_show(struct kernfs_open_file *of,
 					struct seq_file *seq, void *v)
 {
-	struct resctrl_schema *s = of->kn->parent->priv;
+	struct resctrl_schema *s = rdt_kn_parent_priv(of->kn);
 	struct rdt_resource *r = s->res;
 
 	seq_printf(seq, "%u\n", r->cache.arch_has_sparse_bitmasks);
@@ -1670,7 +1680,7 @@ static int mbm_config_show(struct seq_file *s, struct rdt_resource *r, u32 evtid
 static int mbm_total_bytes_config_show(struct kernfs_open_file *of,
 				       struct seq_file *seq, void *v)
 {
-	struct rdt_resource *r = of->kn->parent->priv;
+	struct rdt_resource *r = rdt_kn_parent_priv(of->kn);
 
 	mbm_config_show(seq, r, QOS_L3_MBM_TOTAL_EVENT_ID);
 
@@ -1680,7 +1690,7 @@ static int mbm_total_bytes_config_show(struct kernfs_open_file *of,
 static int mbm_local_bytes_config_show(struct kernfs_open_file *of,
 				       struct seq_file *seq, void *v)
 {
-	struct rdt_resource *r = of->kn->parent->priv;
+	struct rdt_resource *r = rdt_kn_parent_priv(of->kn);
 
 	mbm_config_show(seq, r, QOS_L3_MBM_LOCAL_EVENT_ID);
 
@@ -1787,7 +1797,7 @@ static ssize_t mbm_total_bytes_config_write(struct kernfs_open_file *of,
 					    char *buf, size_t nbytes,
 					    loff_t off)
 {
-	struct rdt_resource *r = of->kn->parent->priv;
+	struct rdt_resource *r = rdt_kn_parent_priv(of->kn);
 	int ret;
 
 	/* Valid input requires a trailing newline */
@@ -1813,7 +1823,7 @@ static ssize_t mbm_local_bytes_config_write(struct kernfs_open_file *of,
 					    char *buf, size_t nbytes,
 					    loff_t off)
 {
-	struct rdt_resource *r = of->kn->parent->priv;
+	struct rdt_resource *r = rdt_kn_parent_priv(of->kn);
 	int ret;
 
 	/* Valid input requires a trailing newline */
@@ -2513,12 +2523,13 @@ static struct rdtgroup *kernfs_to_rdtgroup(struct kernfs_node *kn)
 		 * resource. "info" and its subdirectories don't
 		 * have rdtgroup structures, so return NULL here.
 		 */
-		if (kn == kn_info || kn->parent == kn_info)
+		if (kn == kn_info ||
+		    rcu_access_pointer(kn->__parent) == kn_info)
 			return NULL;
 		else
 			return kn->priv;
 	} else {
-		return kn->parent->priv;
+		return rdt_kn_parent_priv(kn);
 	}
 }
 
@@ -3752,7 +3763,7 @@ out_unlock:
  */
 static bool is_mon_groups(struct kernfs_node *kn, const char *name)
 {
-	return (!strcmp(kn->name, "mon_groups") &&
+	return (!strcmp(rdt_kn_name(kn), "mon_groups") &&
 		strcmp(name, "mon_groups"));
 }
 
@@ -3867,9 +3878,18 @@ static int rdtgroup_rmdir_ctrl(struct rdtgroup *rdtgrp, cpumask_var_t tmpmask)
 	return 0;
 }
 
+static struct kernfs_node *rdt_kn_parent(struct kernfs_node *kn)
+{
+	/*
+	 * Valid within the RCU section it was obtained or while rdtgroup_mutex
+	 * is held.
+	 */
+	return rcu_dereference_check(kn->__parent, lockdep_is_held(&rdtgroup_mutex));
+}
+
 static int rdtgroup_rmdir(struct kernfs_node *kn)
 {
-	struct kernfs_node *parent_kn = kn->parent;
+	struct kernfs_node *parent_kn;
 	struct rdtgroup *rdtgrp;
 	cpumask_var_t tmpmask;
 	int ret = 0;
@@ -3882,6 +3902,7 @@ static int rdtgroup_rmdir(struct kernfs_node *kn)
 		ret = -EPERM;
 		goto out;
 	}
+	parent_kn = rdt_kn_parent(kn);
 
 	/*
 	 * If the rdtgroup is a ctrl_mon group and parent directory
@@ -3899,7 +3920,7 @@ static int rdtgroup_rmdir(struct kernfs_node *kn)
 			ret = rdtgroup_rmdir_ctrl(rdtgrp, tmpmask);
 		}
 	} else if (rdtgrp->type == RDTMON_GROUP &&
-		 is_mon_groups(parent_kn, kn->name)) {
+		 is_mon_groups(parent_kn, rdt_kn_name(kn))) {
 		ret = rdtgroup_rmdir_mon(rdtgrp, tmpmask);
 	} else {
 		ret = -EPERM;
@@ -3950,6 +3971,7 @@ static void mongrp_reparent(struct rdtgroup *rdtgrp,
 static int rdtgroup_rename(struct kernfs_node *kn,
 			   struct kernfs_node *new_parent, const char *new_name)
 {
+	struct kernfs_node *kn_parent;
 	struct rdtgroup *new_prdtgrp;
 	struct rdtgroup *rdtgrp;
 	cpumask_var_t tmpmask;
@@ -3984,8 +4006,9 @@ static int rdtgroup_rename(struct kernfs_node *kn,
 		goto out;
 	}
 
-	if (rdtgrp->type != RDTMON_GROUP || !kn->parent ||
-	    !is_mon_groups(kn->parent, kn->name)) {
+	kn_parent = rdt_kn_parent(kn);
+	if (rdtgrp->type != RDTMON_GROUP || !kn_parent ||
+	    !is_mon_groups(kn_parent, rdt_kn_name(kn))) {
 		rdt_last_cmd_puts("Source must be a MON group\n");
 		ret = -EPERM;
 		goto out;
diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c
index 91639d1e4ec2..c6fefd4585f8 100644
--- a/arch/x86/kernel/dumpstack.c
+++ b/arch/x86/kernel/dumpstack.c
@@ -195,6 +195,7 @@ static void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
 	printk("%sCall Trace:\n", log_lvl);
 
 	unwind_start(&state, task, regs, stack);
+	stack = stack ?: get_stack_pointer(task, regs);
 	regs = unwind_get_entry_regs(&state, &partial);
 
 	/*
@@ -213,9 +214,7 @@ static void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
 	 * - hardirq stack
 	 * - entry stack
 	 */
-	for (stack = stack ?: get_stack_pointer(task, regs);
-	     stack;
-	     stack = stack_info.next_sp) {
+	for (; stack; stack = stack_info.next_sp) {
 		const char *stack_name;
 
 		stack = PTR_ALIGN(stack, sizeof(long));
diff --git a/arch/x86/kernel/early_printk.c b/arch/x86/kernel/early_printk.c
index fc1714bad045..611f27e3890c 100644
--- a/arch/x86/kernel/early_printk.c
+++ b/arch/x86/kernel/early_printk.c
@@ -190,7 +190,6 @@ static __init void early_serial_init(char *s)
 	early_serial_hw_init(divisor);
 }
 
-#ifdef CONFIG_PCI
 static __noendbr void mem32_serial_out(unsigned long addr, int offset, int value)
 {
 	u32 __iomem *vaddr = (u32 __iomem *)addr;
@@ -208,6 +207,45 @@ static __noendbr unsigned int mem32_serial_in(unsigned long addr, int offset)
 ANNOTATE_NOENDBR_SYM(mem32_serial_in);
 
 /*
+ * early_mmio_serial_init() - Initialize MMIO-based early serial console.
+ * @s: MMIO-based serial specification.
+ */
+static __init void early_mmio_serial_init(char *s)
+{
+	unsigned long baudrate;
+	unsigned long membase;
+	char *e;
+
+	if (*s == ',')
+		s++;
+
+	if (!strncmp(s, "0x", 2)) {
+		/* NB: only 32-bit addresses are supported. */
+		membase = simple_strtoul(s, &e, 16);
+		early_serial_base = (unsigned long)early_ioremap(membase, PAGE_SIZE);
+
+		static_call_update(serial_in, mem32_serial_in);
+		static_call_update(serial_out, mem32_serial_out);
+
+		s += strcspn(s, ",");
+		if (*s == ',')
+			s++;
+	}
+
+	if (!strncmp(s, "nocfg", 5)) {
+		baudrate = 0;
+	} else {
+		baudrate = simple_strtoul(s, &e, 0);
+		if (baudrate == 0 || s == e)
+			baudrate = DEFAULT_BAUD;
+	}
+
+	if (baudrate)
+		early_serial_hw_init(115200 / baudrate);
+}
+
+#ifdef CONFIG_PCI
+/*
  * early_pci_serial_init()
  *
  * This function is invoked when the early_printk param starts with "pciserial"
@@ -351,6 +389,11 @@ static int __init setup_early_printk(char *buf)
 	keep = (strstr(buf, "keep") != NULL);
 
 	while (*buf != '\0') {
+		if (!strncmp(buf, "mmio", 4)) {
+			early_mmio_serial_init(buf + 4);
+			early_console_register(&early_serial_console, keep);
+			buf += 4;
+		}
 		if (!strncmp(buf, "serial", 6)) {
 			buf += 6;
 			early_serial_init(buf);
diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c
index 1b734a9ff088..91d6341f281f 100644
--- a/arch/x86/kernel/fpu/core.c
+++ b/arch/x86/kernel/fpu/core.c
@@ -508,7 +508,7 @@ static inline void fpstate_init_fstate(struct fpstate *fpstate)
 /*
  * Used in two places:
  * 1) Early boot to setup init_fpstate for non XSAVE systems
- * 2) fpu_init_fpstate_user() which is invoked from KVM
+ * 2) fpu_alloc_guest_fpstate() which is invoked from KVM
  */
 void fpstate_init_user(struct fpstate *fpstate)
 {
diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c
index 9c9faa1634fb..102641fd2172 100644
--- a/arch/x86/kernel/kgdb.c
+++ b/arch/x86/kernel/kgdb.c
@@ -655,7 +655,7 @@ void kgdb_arch_late(void)
 		if (breakinfo[i].pev)
 			continue;
 		breakinfo[i].pev = register_wide_hw_breakpoint(&attr, NULL, NULL);
-		if (IS_ERR((void * __force)breakinfo[i].pev)) {
+		if (IS_ERR_PCPU(breakinfo[i].pev)) {
 			printk(KERN_ERR "kgdb: Could not allocate hw"
 			       "breakpoints\nDisabling the kernel debugger\n");
 			breakinfo[i].pev = NULL;
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index 97925632c28e..1ccd05d8999f 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -75,6 +75,11 @@ void paravirt_set_sched_clock(u64 (*func)(void))
 	static_call_update(pv_sched_clock, func);
 }
 
+static noinstr void pv_native_safe_halt(void)
+{
+	native_safe_halt();
+}
+
 #ifdef CONFIG_PARAVIRT_XXL
 static noinstr void pv_native_write_cr2(unsigned long val)
 {
@@ -100,11 +105,6 @@ static noinstr void pv_native_set_debugreg(int regno, unsigned long val)
 {
 	native_set_debugreg(regno, val);
 }
-
-static noinstr void pv_native_safe_halt(void)
-{
-	native_safe_halt();
-}
 #endif
 
 struct pv_info pv_info = {
@@ -161,9 +161,11 @@ struct paravirt_patch_template pv_ops = {
 	.irq.save_fl		= __PV_IS_CALLEE_SAVE(pv_native_save_fl),
 	.irq.irq_disable	= __PV_IS_CALLEE_SAVE(pv_native_irq_disable),
 	.irq.irq_enable		= __PV_IS_CALLEE_SAVE(pv_native_irq_enable),
+#endif /* CONFIG_PARAVIRT_XXL */
+
+	/* Irq HLT ops. */
 	.irq.safe_halt		= pv_native_safe_halt,
 	.irq.halt		= native_halt,
-#endif /* CONFIG_PARAVIRT_XXL */
 
 	/* Mmu ops. */
 	.mmu.flush_tlb_user	= native_flush_tlb_local,
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 91f6ff618852..962c3ce39323 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -939,7 +939,7 @@ void __init select_idle_routine(void)
 		static_call_update(x86_idle, mwait_idle);
 	} else if (cpu_feature_enabled(X86_FEATURE_TDX_GUEST)) {
 		pr_info("using TDX aware idle routine\n");
-		static_call_update(x86_idle, tdx_safe_halt);
+		static_call_update(x86_idle, tdx_halt);
 	} else {
 		static_call_update(x86_idle, default_idle);
 	}
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index c7164a8de983..9d2a13b37833 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -578,14 +578,13 @@ static void __init memblock_x86_reserve_range_setup_data(void)
 static void __init arch_reserve_crashkernel(void)
 {
 	unsigned long long crash_base, crash_size, low_size = 0;
-	char *cmdline = boot_command_line;
 	bool high = false;
 	int ret;
 
 	if (!IS_ENABLED(CONFIG_CRASH_RESERVE))
 		return;
 
-	ret = parse_crashkernel(cmdline, memblock_phys_mem_size(),
+	ret = parse_crashkernel(boot_command_line, memblock_phys_mem_size(),
 				&crash_size, &crash_base,
 				&low_size, &high);
 	if (ret)
@@ -596,8 +595,7 @@ static void __init arch_reserve_crashkernel(void)
 		return;
 	}
 
-	reserve_crashkernel_generic(cmdline, crash_size, crash_base,
-				    low_size, high);
+	reserve_crashkernel_generic(crash_size, crash_base, low_size, high);
 }
 
 static struct resource standard_io_resources[] = {
@@ -1031,8 +1029,6 @@ void __init setup_arch(char **cmdline_p)
 		max_low_pfn = e820__end_of_low_ram_pfn();
 	else
 		max_low_pfn = max_pfn;
-
-	high_memory = (void *)__va(max_pfn * PAGE_SIZE - 1) + 1;
 #endif
 
 	/* Find and reserve MPTABLE area */
@@ -1166,8 +1162,10 @@ void __init setup_arch(char **cmdline_p)
 	initmem_init();
 	dma_contiguous_reserve(max_pfn_mapped << PAGE_SHIFT);
 
-	if (boot_cpu_has(X86_FEATURE_GBPAGES))
+	if (boot_cpu_has(X86_FEATURE_GBPAGES)) {
 		hugetlb_cma_reserve(PUD_SHIFT - PAGE_SHIFT);
+		hugetlb_bootmem_alloc();
+	}
 
 	/*
 	 * Reserve memory for crash kernel after SRAT is parsed so that it
diff --git a/arch/x86/kernel/static_call.c b/arch/x86/kernel/static_call.c
index 9e51242ed125..a59c72e77645 100644
--- a/arch/x86/kernel/static_call.c
+++ b/arch/x86/kernel/static_call.c
@@ -158,7 +158,7 @@ void arch_static_call_transform(void *site, void *tramp, void *func, bool tail)
 {
 	mutex_lock(&text_mutex);
 
-	if (tramp) {
+	if (tramp && !site) {
 		__static_call_validate(tramp, true, true);
 		__static_call_transform(tramp, __sc_insn(!func, true), func, false);
 	}
diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c
index d4705a348a80..977ee75e047c 100644
--- a/arch/x86/kernel/unwind_orc.c
+++ b/arch/x86/kernel/unwind_orc.c
@@ -476,7 +476,7 @@ bool unwind_next_frame(struct unwind_state *state)
 		return false;
 
 	/* Don't let modules unload while we're reading their ORC data. */
-	preempt_disable();
+	guard(rcu)();
 
 	/* End-of-stack check for user tasks: */
 	if (state->regs && user_mode(state->regs))
@@ -669,14 +669,12 @@ bool unwind_next_frame(struct unwind_state *state)
 		goto err;
 	}
 
-	preempt_enable();
 	return true;
 
 err:
 	state->error = true;
 
 the_end:
-	preempt_enable();
 	state->stack_info.type = STACK_TYPE_UNKNOWN;
 	return false;
 }