Merge tag 'mm-nonmm-stable-2022-10-11' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull non-MM updates from Andrew Morton:

 - hfs and hfsplus kmap API modernization (Fabio Francesco)

 - make crash-kexec work properly when invoked from an NMI-time panic
   (Valentin Schneider)

 - ntfs bugfixes (Hawkins Jiawei)

 - improve IPC msg scalability by replacing atomic_t's with percpu
   counters (Jiebin Sun)

 - nilfs2 cleanups (Minghao Chi)

 - lots of other single patches all over the tree!

* tag 'mm-nonmm-stable-2022-10-11' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (71 commits)
  include/linux/entry-common.h: remove has_signal comment of arch_do_signal_or_restart() prototype
  proc: test how it holds up with mapping'less process
  mailmap: update Frank Rowand email address
  ia64: mca: use strscpy() is more robust and safer
  init/Kconfig: fix unmet direct dependencies
  ia64: update config files
  nilfs2: replace WARN_ONs by nilfs_error for checkpoint acquisition failure
  fork: remove duplicate included header files
  init/main.c: remove unnecessary (void*) conversions
  proc: mark more files as permanent
  nilfs2: remove the unneeded result variable
  nilfs2: delete unnecessary checks before brelse()
  checkpatch: warn for non-standard fixes tag style
  usr/gen_init_cpio.c: remove unnecessary -1 values from int file
  ipc/msg: mitigate the lock contention with percpu counter
  percpu: add percpu_counter_add_local and percpu_counter_sub_local
  fs/ocfs2: fix repeated words in comments
  relay: use kvcalloc to alloc page array in relay_alloc_page_array
  proc: make config PROC_CHILDREN depend on PROC_FS
  fs: uninline inode_maybe_inc_iversion()
  ...

14 files changed, 101 insertions, 82 deletions

diff --git a/kernel/exit.c b/kernel/exit.c
index 98c859ffa728..35e0a31a0315 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -184,6 +184,10 @@ void put_task_struct_rcu_user(struct task_struct *task)
 		call_rcu(&task->rcu, delayed_put_task_struct);
 }
 
+void __weak release_thread(struct task_struct *dead_task)
+{
+}
+
 void release_task(struct task_struct *p)
 {
 	struct task_struct *leader;
diff --git a/kernel/fail_function.c b/kernel/fail_function.c
index 60dc825ecc2b..a7ccd2930c5f 100644
--- a/kernel/fail_function.c
+++ b/kernel/fail_function.c
@@ -247,15 +247,11 @@ static ssize_t fei_write(struct file *file, const char __user *buffer,
 	/* cut off if it is too long */
 	if (count > KSYM_NAME_LEN)
 		count = KSYM_NAME_LEN;
-	buf = kmalloc(count + 1, GFP_KERNEL);
-	if (!buf)
-		return -ENOMEM;
 
-	if (copy_from_user(buf, buffer, count)) {
-		ret = -EFAULT;
-		goto out_free;
-	}
-	buf[count] = '\0';
+	buf = memdup_user_nul(buffer, count);
+	if (IS_ERR(buf))
+		return PTR_ERR(buf);
+
 	sym = strstrip(buf);
 
 	mutex_lock(&fei_lock);
@@ -298,17 +294,15 @@ static ssize_t fei_write(struct file *file, const char __user *buffer,
 	}
 
 	ret = register_kprobe(&attr->kp);
-	if (!ret)
-		fei_debugfs_add_attr(attr);
-	if (ret < 0)
-		fei_attr_remove(attr);
-	else {
-		list_add_tail(&attr->list, &fei_attr_list);
-		ret = count;
+	if (ret) {
+		fei_attr_free(attr);
+		goto out;
 	}
+	fei_debugfs_add_attr(attr);
+	list_add_tail(&attr->list, &fei_attr_list);
+	ret = count;
 out:
 	mutex_unlock(&fei_lock);
-out_free:
 	kfree(buf);
 	return ret;
 }
diff --git a/kernel/fork.c b/kernel/fork.c
index 5f986a32d0e6..08969f5aa38d 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -97,7 +97,6 @@
 #include <linux/scs.h>
 #include <linux/io_uring.h>
 #include <linux/bpf.h>
-#include <linux/sched/mm.h>
 
 #include <asm/pgalloc.h>
 #include <linux/uaccess.h>
diff --git a/kernel/kexec.c b/kernel/kexec.c
index b5e40f069768..cb8e6e6f983c 100644
--- a/kernel/kexec.c
+++ b/kernel/kexec.c
@@ -93,13 +93,10 @@ static int do_kexec_load(unsigned long entry, unsigned long nr_segments,
 
 	/*
 	 * Because we write directly to the reserved memory region when loading
-	 * crash kernels we need a mutex here to prevent multiple crash kernels
-	 * from attempting to load simultaneously, and to prevent a crash kernel
-	 * from loading over the top of a in use crash kernel.
-	 *
-	 * KISS: always take the mutex.
+	 * crash kernels we need a serialization here to prevent multiple crash
+	 * kernels from attempting to load simultaneously.
 	 */
-	if (!mutex_trylock(&kexec_mutex))
+	if (!kexec_trylock())
 		return -EBUSY;
 
 	if (flags & KEXEC_ON_CRASH) {
@@ -165,7 +162,7 @@ out:
 
 	kimage_free(image);
 out_unlock:
-	mutex_unlock(&kexec_mutex);
+	kexec_unlock();
 	return ret;
 }
 
diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c
index acd029b307e4..ca2743f9c634 100644
--- a/kernel/kexec_core.c
+++ b/kernel/kexec_core.c
@@ -46,7 +46,7 @@
 #include <crypto/hash.h>
 #include "kexec_internal.h"
 
-DEFINE_MUTEX(kexec_mutex);
+atomic_t __kexec_lock = ATOMIC_INIT(0);
 
 /* Per cpu memory for storing cpu states in case of system crash. */
 note_buf_t __percpu *crash_notes;
@@ -809,7 +809,7 @@ static int kimage_load_normal_segment(struct kimage *image,
 		if (result < 0)
 			goto out;
 
-		ptr = kmap(page);
+		ptr = kmap_local_page(page);
 		/* Start with a clear page */
 		clear_page(ptr);
 		ptr += maddr & ~PAGE_MASK;
@@ -822,7 +822,7 @@ static int kimage_load_normal_segment(struct kimage *image,
 			memcpy(ptr, kbuf, uchunk);
 		else
 			result = copy_from_user(ptr, buf, uchunk);
-		kunmap(page);
+		kunmap_local(ptr);
 		if (result) {
 			result = -EFAULT;
 			goto out;
@@ -873,7 +873,7 @@ static int kimage_load_crash_segment(struct kimage *image,
 			goto out;
 		}
 		arch_kexec_post_alloc_pages(page_address(page), 1, 0);
-		ptr = kmap(page);
+		ptr = kmap_local_page(page);
 		ptr += maddr & ~PAGE_MASK;
 		mchunk = min_t(size_t, mbytes,
 				PAGE_SIZE - (maddr & ~PAGE_MASK));
@@ -889,7 +889,7 @@ static int kimage_load_crash_segment(struct kimage *image,
 		else
 			result = copy_from_user(ptr, buf, uchunk);
 		kexec_flush_icache_page(page);
-		kunmap(page);
+		kunmap_local(ptr);
 		arch_kexec_pre_free_pages(page_address(page), 1);
 		if (result) {
 			result = -EFAULT;
@@ -959,7 +959,7 @@ late_initcall(kexec_core_sysctl_init);
  */
 void __noclone __crash_kexec(struct pt_regs *regs)
 {
-	/* Take the kexec_mutex here to prevent sys_kexec_load
+	/* Take the kexec_lock here to prevent sys_kexec_load
 	 * running on one cpu from replacing the crash kernel
 	 * we are using after a panic on a different cpu.
 	 *
@@ -967,7 +967,7 @@ void __noclone __crash_kexec(struct pt_regs *regs)
 	 * of memory the xchg(&kexec_crash_image) would be
 	 * sufficient.  But since I reuse the memory...
 	 */
-	if (mutex_trylock(&kexec_mutex)) {
+	if (kexec_trylock()) {
 		if (kexec_crash_image) {
 			struct pt_regs fixed_regs;
 
@@ -976,7 +976,7 @@ void __noclone __crash_kexec(struct pt_regs *regs)
 			machine_crash_shutdown(&fixed_regs);
 			machine_kexec(kexec_crash_image);
 		}
-		mutex_unlock(&kexec_mutex);
+		kexec_unlock();
 	}
 }
 STACK_FRAME_NON_STANDARD(__crash_kexec);
@@ -1004,14 +1004,17 @@ void crash_kexec(struct pt_regs *regs)
 	}
 }
 
-size_t crash_get_memory_size(void)
+ssize_t crash_get_memory_size(void)
 {
-	size_t size = 0;
+	ssize_t size = 0;
+
+	if (!kexec_trylock())
+		return -EBUSY;
 
-	mutex_lock(&kexec_mutex);
 	if (crashk_res.end != crashk_res.start)
 		size = resource_size(&crashk_res);
-	mutex_unlock(&kexec_mutex);
+
+	kexec_unlock();
 	return size;
 }
 
@@ -1022,7 +1025,8 @@ int crash_shrink_memory(unsigned long new_size)
 	unsigned long old_size;
 	struct resource *ram_res;
 
-	mutex_lock(&kexec_mutex);
+	if (!kexec_trylock())
+		return -EBUSY;
 
 	if (kexec_crash_image) {
 		ret = -ENOENT;
@@ -1060,7 +1064,7 @@ int crash_shrink_memory(unsigned long new_size)
 	insert_resource(&iomem_resource, ram_res);
 
 unlock:
-	mutex_unlock(&kexec_mutex);
+	kexec_unlock();
 	return ret;
 }
 
@@ -1132,7 +1136,7 @@ int kernel_kexec(void)
 {
 	int error = 0;
 
-	if (!mutex_trylock(&kexec_mutex))
+	if (!kexec_trylock())
 		return -EBUSY;
 	if (!kexec_image) {
 		error = -EINVAL;
@@ -1208,6 +1212,6 @@ int kernel_kexec(void)
 #endif
 
  Unlock:
-	mutex_unlock(&kexec_mutex);
+	kexec_unlock();
 	return error;
 }
diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c
index 1d546dc97c50..45637511e0de 100644
--- a/kernel/kexec_file.c
+++ b/kernel/kexec_file.c
@@ -339,7 +339,7 @@ SYSCALL_DEFINE5(kexec_file_load, int, kernel_fd, int, initrd_fd,
 
 	image = NULL;
 
-	if (!mutex_trylock(&kexec_mutex))
+	if (!kexec_trylock())
 		return -EBUSY;
 
 	dest_image = &kexec_image;
@@ -411,7 +411,7 @@ out:
 	if ((flags & KEXEC_FILE_ON_CRASH) && kexec_crash_image)
 		arch_kexec_protect_crashkres();
 
-	mutex_unlock(&kexec_mutex);
+	kexec_unlock();
 	kimage_free(image);
 	return ret;
 }
diff --git a/kernel/kexec_internal.h b/kernel/kexec_internal.h
index 48aaf2ac0d0d..74da1409cd14 100644
--- a/kernel/kexec_internal.h
+++ b/kernel/kexec_internal.h
@@ -13,7 +13,20 @@ void kimage_terminate(struct kimage *image);
 int kimage_is_destination_range(struct kimage *image,
 				unsigned long start, unsigned long end);
 
-extern struct mutex kexec_mutex;
+/*
+ * Whatever is used to serialize accesses to the kexec_crash_image needs to be
+ * NMI safe, as __crash_kexec() can happen during nmi_panic(), so here we use a
+ * "simple" atomic variable that is acquired with a cmpxchg().
+ */
+extern atomic_t __kexec_lock;
+static inline bool kexec_trylock(void)
+{
+	return atomic_cmpxchg_acquire(&__kexec_lock, 0, 1) == 0;
+}
+static inline void kexec_unlock(void)
+{
+	atomic_set_release(&__kexec_lock, 0);
+}
 
 #ifdef CONFIG_KEXEC_FILE
 #include <linux/purgatory.h>
diff --git a/kernel/ksysfs.c b/kernel/ksysfs.c
index b1292a57c2a5..65dba9076f31 100644
--- a/kernel/ksysfs.c
+++ b/kernel/ksysfs.c
@@ -105,7 +105,12 @@ KERNEL_ATTR_RO(kexec_crash_loaded);
 static ssize_t kexec_crash_size_show(struct kobject *kobj,
 				       struct kobj_attribute *attr, char *buf)
 {
-	return sprintf(buf, "%zu\n", crash_get_memory_size());
+	ssize_t size = crash_get_memory_size();
+
+	if (size < 0)
+		return size;
+
+	return sprintf(buf, "%zd\n", size);
 }
 static ssize_t kexec_crash_size_store(struct kobject *kobj,
 				   struct kobj_attribute *attr,
diff --git a/kernel/latencytop.c b/kernel/latencytop.c
index 76166df011a4..781249098cb6 100644
--- a/kernel/latencytop.c
+++ b/kernel/latencytop.c
@@ -112,7 +112,7 @@ static void __sched
 account_global_scheduler_latency(struct task_struct *tsk,
 				 struct latency_record *lat)
 {
-	int firstnonnull = MAXLR + 1;
+	int firstnonnull = MAXLR;
 	int i;
 
 	/* skip kernel threads for now */
@@ -150,7 +150,7 @@ account_global_scheduler_latency(struct task_struct *tsk,
 	}
 
 	i = firstnonnull;
-	if (i >= MAXLR - 1)
+	if (i >= MAXLR)
 		return;
 
 	/* Allocted a new one: */
diff --git a/kernel/profile.c b/kernel/profile.c
index 7ea01ba30e75..8a77769bc4b4 100644
--- a/kernel/profile.c
+++ b/kernel/profile.c
@@ -59,43 +59,39 @@ int profile_setup(char *str)
 	static const char schedstr[] = "schedule";
 	static const char sleepstr[] = "sleep";
 	static const char kvmstr[] = "kvm";
+	const char *select = NULL;
 	int par;
 
 	if (!strncmp(str, sleepstr, strlen(sleepstr))) {
 #ifdef CONFIG_SCHEDSTATS
 		force_schedstat_enabled();
 		prof_on = SLEEP_PROFILING;
-		if (str[strlen(sleepstr)] == ',')
-			str += strlen(sleepstr) + 1;
-		if (get_option(&str, &par))
-			prof_shift = clamp(par, 0, BITS_PER_LONG - 1);
-		pr_info("kernel sleep profiling enabled (shift: %u)\n",
-			prof_shift);
+		select = sleepstr;
 #else
 		pr_warn("kernel sleep profiling requires CONFIG_SCHEDSTATS\n");
 #endif /* CONFIG_SCHEDSTATS */
 	} else if (!strncmp(str, schedstr, strlen(schedstr))) {
 		prof_on = SCHED_PROFILING;
-		if (str[strlen(schedstr)] == ',')
-			str += strlen(schedstr) + 1;
-		if (get_option(&str, &par))
-			prof_shift = clamp(par, 0, BITS_PER_LONG - 1);
-		pr_info("kernel schedule profiling enabled (shift: %u)\n",
-			prof_shift);
+		select = schedstr;
 	} else if (!strncmp(str, kvmstr, strlen(kvmstr))) {
 		prof_on = KVM_PROFILING;
-		if (str[strlen(kvmstr)] == ',')
-			str += strlen(kvmstr) + 1;
-		if (get_option(&str, &par))
-			prof_shift = clamp(par, 0, BITS_PER_LONG - 1);
-		pr_info("kernel KVM profiling enabled (shift: %u)\n",
-			prof_shift);
+		select = kvmstr;
 	} else if (get_option(&str, &par)) {
 		prof_shift = clamp(par, 0, BITS_PER_LONG - 1);
 		prof_on = CPU_PROFILING;
 		pr_info("kernel profiling enabled (shift: %u)\n",
 			prof_shift);
 	}
+
+	if (select) {
+		if (str[strlen(select)] == ',')
+			str += strlen(select) + 1;
+		if (get_option(&str, &par))
+			prof_shift = clamp(par, 0, BITS_PER_LONG - 1);
+		pr_info("kernel %s profiling enabled (shift: %u)\n",
+			select, prof_shift);
+	}
+
 	return 1;
 }
 __setup("profile=", profile_setup);
diff --git a/kernel/relay.c b/kernel/relay.c
index 6a611e779e95..d7edc934c56d 100644
--- a/kernel/relay.c
+++ b/kernel/relay.c
@@ -60,10 +60,7 @@ static const struct vm_operations_struct relay_file_mmap_ops = {
  */
 static struct page **relay_alloc_page_array(unsigned int n_pages)
 {
-	const size_t pa_size = n_pages * sizeof(struct page *);
-	if (pa_size > PAGE_SIZE)
-		return vzalloc(pa_size);
-	return kzalloc(pa_size, GFP_KERNEL);
+	return kvcalloc(n_pages, sizeof(struct page *), GFP_KERNEL);
 }
 
 /*
diff --git a/kernel/smpboot.c b/kernel/smpboot.c
index b9f54544e749..2c7396da470c 100644
--- a/kernel/smpboot.c
+++ b/kernel/smpboot.c
@@ -433,7 +433,7 @@ bool cpu_wait_death(unsigned int cpu, int seconds)
 
 	/* The outgoing CPU will normally get done quite quickly. */
 	if (atomic_read(&per_cpu(cpu_hotplug_state, cpu)) == CPU_DEAD)
-		goto update_state;
+		goto update_state_early;
 	udelay(5);
 
 	/* But if the outgoing CPU dawdles, wait increasingly long times. */
@@ -444,16 +444,17 @@ bool cpu_wait_death(unsigned int cpu, int seconds)
 			break;
 		sleep_jf = DIV_ROUND_UP(sleep_jf * 11, 10);
 	}
-update_state:
+update_state_early:
 	oldstate = atomic_read(&per_cpu(cpu_hotplug_state, cpu));
+update_state:
 	if (oldstate == CPU_DEAD) {
 		/* Outgoing CPU died normally, update state. */
 		smp_mb(); /* atomic_read() before update. */
 		atomic_set(&per_cpu(cpu_hotplug_state, cpu), CPU_POST_DEAD);
 	} else {
 		/* Outgoing CPU still hasn't died, set state accordingly. */
-		if (atomic_cmpxchg(&per_cpu(cpu_hotplug_state, cpu),
-				   oldstate, CPU_BROKEN) != oldstate)
+		if (!atomic_try_cmpxchg(&per_cpu(cpu_hotplug_state, cpu),
+					&oldstate, CPU_BROKEN))
 			goto update_state;
 		ret = false;
 	}
@@ -475,14 +476,14 @@ bool cpu_report_death(void)
 	int newstate;
 	int cpu = smp_processor_id();
 
+	oldstate = atomic_read(&per_cpu(cpu_hotplug_state, cpu));
 	do {
-		oldstate = atomic_read(&per_cpu(cpu_hotplug_state, cpu));
 		if (oldstate != CPU_BROKEN)
 			newstate = CPU_DEAD;
 		else
 			newstate = CPU_DEAD_FROZEN;
-	} while (atomic_cmpxchg(&per_cpu(cpu_hotplug_state, cpu),
-				oldstate, newstate) != oldstate);
+	} while (!atomic_try_cmpxchg(&per_cpu(cpu_hotplug_state, cpu),
+				     &oldstate, newstate));
 	return newstate == CPU_DEAD;
 }
 
diff --git a/kernel/task_work.c b/kernel/task_work.c
index dff75bcde151..065e1ef8fc8d 100644
--- a/kernel/task_work.c
+++ b/kernel/task_work.c
@@ -47,12 +47,12 @@ int task_work_add(struct task_struct *task, struct callback_head *work,
 	/* record the work call stack in order to print it in KASAN reports */
 	kasan_record_aux_stack(work);
 
+	head = READ_ONCE(task->task_works);
 	do {
-		head = READ_ONCE(task->task_works);
 		if (unlikely(head == &work_exited))
 			return -ESRCH;
 		work->next = head;
-	} while (cmpxchg(&task->task_works, head, work) != head);
+	} while (!try_cmpxchg(&task->task_works, &head, work));
 
 	switch (notify) {
 	case TWA_NONE:
@@ -100,10 +100,12 @@ task_work_cancel_match(struct task_struct *task,
 	 * we raced with task_work_run(), *pprev == NULL/exited.
 	 */
 	raw_spin_lock_irqsave(&task->pi_lock, flags);
-	while ((work = READ_ONCE(*pprev))) {
-		if (!match(work, data))
+	work = READ_ONCE(*pprev);
+	while (work) {
+		if (!match(work, data)) {
 			pprev = &work->next;
-		else if (cmpxchg(pprev, work, work->next) == work)
+			work = READ_ONCE(*pprev);
+		} else if (try_cmpxchg(pprev, &work, work->next))
 			break;
 	}
 	raw_spin_unlock_irqrestore(&task->pi_lock, flags);
@@ -151,16 +153,16 @@ void task_work_run(void)
 		 * work->func() can do task_work_add(), do not set
 		 * work_exited unless the list is empty.
 		 */
+		work = READ_ONCE(task->task_works);
 		do {
 			head = NULL;
-			work = READ_ONCE(task->task_works);
 			if (!work) {
 				if (task->flags & PF_EXITING)
 					head = &work_exited;
 				else
 					break;
 			}
-		} while (cmpxchg(&task->task_works, work, head) != work);
+		} while (!try_cmpxchg(&task->task_works, &work, head));
 
 		if (!work)
 			break;
diff --git a/kernel/utsname_sysctl.c b/kernel/utsname_sysctl.c
index de16bcf14b03..064072c16e3d 100644
--- a/kernel/utsname_sysctl.c
+++ b/kernel/utsname_sysctl.c
@@ -76,6 +76,13 @@ static DEFINE_CTL_TABLE_POLL(domainname_poll);
 
 static struct ctl_table uts_kern_table[] = {
 	{
+		.procname	= "arch",
+		.data		= init_uts_ns.name.machine,
+		.maxlen		= sizeof(init_uts_ns.name.machine),
+		.mode		= 0444,
+		.proc_handler	= proc_do_uts_string,
+	},
+	{
 		.procname	= "ostype",
 		.data		= init_uts_ns.name.sysname,
 		.maxlen		= sizeof(init_uts_ns.name.sysname),