Merge branch 'akpm' (patches from Andrew)

Merge more updates from Andrew Morton:
 "155 patches.

  Subsystems affected by this patch series: mm (dax, debug, thp,
  readahead, page-poison, util, memory-hotplug, zram, cleanups), misc,
  core-kernel, get_maintainer, MAINTAINERS, lib, bitops, checkpatch,
  binfmt, ramfs, autofs, nilfs, rapidio, panic, relay, kgdb, ubsan,
  romfs, and fault-injection"

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (155 commits)
  lib, uaccess: add failure injection to usercopy functions
  lib, include/linux: add usercopy failure capability
  ROMFS: support inode blocks calculation
  ubsan: introduce CONFIG_UBSAN_LOCAL_BOUNDS for Clang
  sched.h: drop in_ubsan field when UBSAN is in trap mode
  scripts/gdb/tasks: add headers and improve spacing format
  scripts/gdb/proc: add struct mount & struct super_block addr in lx-mounts command
  kernel/relay.c: drop unneeded initialization
  panic: dump registers on panic_on_warn
  rapidio: fix the missed put_device() for rio_mport_add_riodev
  rapidio: fix error handling path
  nilfs2: fix some kernel-doc warnings for nilfs2
  autofs: harden ioctl table
  ramfs: fix nommu mmap with gaps in the page cache
  mm: remove the now-unnecessary mmget_still_valid() hack
  mm/gup: take mmap_lock in get_dump_page()
  binfmt_elf, binfmt_elf_fdpic: use a VMA list snapshot
  coredump: rework elf/elf_fdpic vma_dump_size() into common helper
  coredump: refactor page range dumping into common helper
  coredump: let dump_emit() bail out on short writes
  ...

21 files changed, 118 insertions, 53 deletions

diff --git a/kernel/acct.c b/kernel/acct.c
index b0c5b3a9f5af..f175df8f6aa4 100644
--- a/kernel/acct.c
+++ b/kernel/acct.c
@@ -25,7 +25,7 @@
  *  Now we silently close acct_file on attempt to reopen. Cleaned sys_acct().
  *  XTerms and EMACS are manifestations of pure evil. 21/10/98, AV.
  *
- *  Fixed a nasty interaction with with sys_umount(). If the accointing
+ *  Fixed a nasty interaction with sys_umount(). If the accounting
  *  was suspeneded we failed to stop it on umount(). Messy.
  *  Another one: remount to readonly didn't stop accounting.
  *	Question: what should we do if we have CAP_SYS_ADMIN but not
@@ -263,12 +263,12 @@ static DEFINE_MUTEX(acct_on_mutex);
  * sys_acct - enable/disable process accounting
  * @name: file name for accounting records or NULL to shutdown accounting
  *
- * Returns 0 for success or negative errno values for failure.
- *
  * sys_acct() is the only system call needed to implement process
  * accounting. It takes the name of the file where accounting records
  * should be written. If the filename is NULL, accounting will be
  * shutdown.
+ *
+ * Returns: 0 for success or negative errno values for failure.
  */
 SYSCALL_DEFINE1(acct, const char __user *, name)
 {
@@ -586,9 +586,7 @@ static void slow_acct_process(struct pid_namespace *ns)
 }
 
 /**
- * acct_process
- *
- * handles process accounting for an exiting task
+ * acct_process - handles process accounting for an exiting task
  */
 void acct_process(void)
 {
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index 642415b8c3c9..57b5b5d0a5fd 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -390,7 +390,7 @@ static void guarantee_online_cpus(struct cpuset *cs, struct cpumask *pmask)
 			 * The top cpuset doesn't have any online cpu as a
 			 * consequence of a race between cpuset_hotplug_work
 			 * and cpu hotplug notifier.  But we know the top
-			 * cpuset's effective_cpus is on its way to to be
+			 * cpuset's effective_cpus is on its way to be
 			 * identical to cpu_online_mask.
 			 */
 			cpumask_copy(pmask, cpu_online_mask);
diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index b92d08e65999..06c111544f61 100644
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -16,7 +16,7 @@
 #include "direct.h"
 
 /*
- * Most architectures use ZONE_DMA for the first 16 Megabytes, but some use it
+ * Most architectures use ZONE_DMA for the first 16 Megabytes, but some use
  * it for entirely different regions. In that case the arch code needs to
  * override the variable below for dma-direct to work properly.
  */
diff --git a/kernel/fork.c b/kernel/fork.c
index 3ca8f1f83fb3..32083db7a2a2 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -556,7 +556,7 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
 
 			get_file(file);
 			if (tmp->vm_flags & VM_DENYWRITE)
-				atomic_dec(&inode->i_writecount);
+				put_write_access(inode);
 			i_mmap_lock_write(mapping);
 			if (tmp->vm_flags & VM_SHARED)
 				mapping_allow_writable(mapping);
@@ -2189,7 +2189,7 @@ static __latent_entropy struct task_struct *copy_process(
 
 	/*
 	 * Ensure that the cgroup subsystem policies allow the new process to be
-	 * forked. It should be noted the the new process's css_set can be changed
+	 * forked. It should be noted that the new process's css_set can be changed
 	 * between here and cgroup_post_fork() if an organisation operation is in
 	 * progress.
 	 */
diff --git a/kernel/futex.c b/kernel/futex.c
index a5876694a60e..680854dcf156 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -916,7 +916,7 @@ static inline void exit_pi_state_list(struct task_struct *curr) { }
  * [10] Found  | Found    | task      | !=taskTID | 0/1    | Invalid
  *
  * [1]	Indicates that the kernel can acquire the futex atomically. We
- *	came came here due to a stale FUTEX_WAITERS/FUTEX_OWNER_DIED bit.
+ *	came here due to a stale FUTEX_WAITERS/FUTEX_OWNER_DIED bit.
  *
  * [2]	Valid, if TID does not belong to a kernel thread. If no matching
  *      thread is found then it indicates that the owner TID has died.
diff --git a/kernel/irq/timings.c b/kernel/irq/timings.c
index e960d7ce7bcc..773b6105c4ae 100644
--- a/kernel/irq/timings.c
+++ b/kernel/irq/timings.c
@@ -604,7 +604,7 @@ int irq_timings_alloc(int irq)
 
 	/*
 	 * Some platforms can have the same private interrupt per cpu,
-	 * so this function may be be called several times with the
+	 * so this function may be called several times with the
 	 * same interrupt number. Just bail out in case the per cpu
 	 * stat structure is already allocated.
 	 */
diff --git a/kernel/jump_label.c b/kernel/jump_label.c
index e661c61b3d6b..015ef903ce8c 100644
--- a/kernel/jump_label.c
+++ b/kernel/jump_label.c
@@ -19,7 +19,7 @@
 #include <linux/cpu.h>
 #include <asm/sections.h>
 
-/* mutex to protect coming/going of the the jump_label table */
+/* mutex to protect coming/going of the jump_label table */
 static DEFINE_MUTEX(jump_label_mutex);
 
 void jump_label_lock(void)
diff --git a/kernel/kcsan/encoding.h b/kernel/kcsan/encoding.h
index f03562aaf2eb..1a6db2f797ac 100644
--- a/kernel/kcsan/encoding.h
+++ b/kernel/kcsan/encoding.h
@@ -32,7 +32,7 @@
  *	1. different addresses but with the same encoded address race;
  *	2. and both map onto the same watchpoint slots;
  *
- * Both these are assumed to be very unlikely. However, in case it still happens
+ * Both these are assumed to be very unlikely. However, in case it still
  * happens, the report logic will filter out the false positive (see report.c).
  */
 #define WATCHPOINT_ADDR_BITS (BITS_PER_LONG-1 - WATCHPOINT_SIZE_BITS)
diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c
index c5e5e5a11535..8798a8183974 100644
--- a/kernel/kexec_core.c
+++ b/kernel/kexec_core.c
@@ -109,7 +109,7 @@ EXPORT_SYMBOL_GPL(kexec_crash_loaded);
  * defined more restrictively in <asm/kexec.h>.
  *
  * The code for the transition from the current kernel to the
- * the new kernel is placed in the control_code_buffer, whose size
+ * new kernel is placed in the control_code_buffer, whose size
  * is given by KEXEC_CONTROL_PAGE_SIZE.  In the best case only a single
  * page of memory is necessary, but some architectures require more.
  * Because this memory must be identity mapped in the transition from
diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c
index 84f7316792a7..e21f6b9234f7 100644
--- a/kernel/kexec_file.c
+++ b/kernel/kexec_file.c
@@ -521,7 +521,7 @@ static int locate_mem_hole_callback(struct resource *res, void *arg)
 	/* Returning 0 will take to next memory range */
 
 	/* Don't use memory that will be detected and handled by a driver. */
-	if (res->flags & IORESOURCE_MEM_DRIVER_MANAGED)
+	if (res->flags & IORESOURCE_SYSRAM_DRIVER_MANAGED)
 		return 0;
 
 	if (sz < kbuf->memsz)
diff --git a/kernel/kthread.c b/kernel/kthread.c
index 3edaa380dc7b..e29773c82b70 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -775,7 +775,7 @@ EXPORT_SYMBOL(kthread_create_worker);
 
 /**
  * kthread_create_worker_on_cpu - create a kthread worker and bind it
- *	it to a given CPU and the associated NUMA node.
+ *	to a given CPU and the associated NUMA node.
  * @cpu: CPU number
  * @flags: flags modifying the default behavior of the worker
  * @namefmt: printf-style name for the kthread worker (task).
diff --git a/kernel/livepatch/state.c b/kernel/livepatch/state.c
index 7ee19476de9d..2565d039ade0 100644
--- a/kernel/livepatch/state.c
+++ b/kernel/livepatch/state.c
@@ -55,7 +55,7 @@ EXPORT_SYMBOL_GPL(klp_get_state);
  *
  * The function can be called only during transition when a new
  * livepatch is being enabled or when such a transition is reverted.
- * It is typically called only from from pre/post (un)patch
+ * It is typically called only from pre/post (un)patch
  * callbacks.
  *
  * Return: pointer to the latest struct klp_state from already
diff --git a/kernel/panic.c b/kernel/panic.c
index aef8872ba843..396142ee43fd 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -589,6 +589,11 @@ void __warn(const char *file, int line, void *caller, unsigned taint,
 	if (args)
 		vprintk(args->fmt, args->args);
 
+	print_modules();
+
+	if (regs)
+		show_regs(regs);
+
 	if (panic_on_warn) {
 		/*
 		 * This thread may hit another WARN() in the panic path.
@@ -600,12 +605,7 @@ void __warn(const char *file, int line, void *caller, unsigned taint,
 		panic("panic_on_warn set ...\n");
 	}
 
-	print_modules();
-
-	if (regs)
-		show_regs(regs);
-	else
-		dump_stack();
+	dump_stack();
 
 	print_irqtrace_events(current);
 
diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c
index ac135bd600eb..9de21803a8ae 100644
--- a/kernel/pid_namespace.c
+++ b/kernel/pid_namespace.c
@@ -233,7 +233,7 @@ void zap_pid_ns_processes(struct pid_namespace *pid_ns)
 	 * to pid_ns->child_reaper.  Thus pidns->child_reaper needs to
 	 * stay valid until they all go away.
 	 *
-	 * The code relies on the the pid_ns->child_reaper ignoring
+	 * The code relies on the pid_ns->child_reaper ignoring
 	 * SIGCHILD to cause those EXIT_ZOMBIE processes to be
 	 * autoreaped if reparented.
 	 *
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index d25749bce7cf..46b1804c1ddf 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -735,7 +735,7 @@ zone_found:
 	 */
 
 	/*
-	 * If the zone we wish to scan is the the current zone and the
+	 * If the zone we wish to scan is the current zone and the
 	 * pfn falls into the current node then we do not need to walk
 	 * the tree.
 	 */
diff --git a/kernel/range.c b/kernel/range.c
index d84de6766472..56435f96da73 100644
--- a/kernel/range.c
+++ b/kernel/range.c
@@ -2,8 +2,9 @@
 /*
  * Range add and subtract
  */
-#include <linux/kernel.h>
 #include <linux/init.h>
+#include <linux/minmax.h>
+#include <linux/printk.h>
 #include <linux/sort.h>
 #include <linux/string.h>
 #include <linux/range.h>
diff --git a/kernel/relay.c b/kernel/relay.c
index fb4e0c530c08..b08d936d5fa7 100644
--- a/kernel/relay.c
+++ b/kernel/relay.c
@@ -1002,7 +1002,7 @@ static int relay_file_read_avail(struct rchan_buf *buf)
 	size_t subbuf_size = buf->chan->subbuf_size;
 	size_t n_subbufs = buf->chan->n_subbufs;
 	size_t produced = buf->subbufs_produced;
-	size_t consumed = buf->subbufs_consumed;
+	size_t consumed;
 
 	relay_file_read_consume(buf, 0, 0);
 
diff --git a/kernel/resource.c b/kernel/resource.c
index f1175ce93a1d..3ae2f56cc79d 100644
--- a/kernel/resource.c
+++ b/kernel/resource.c
@@ -1240,7 +1240,6 @@ EXPORT_SYMBOL(__release_region);
 #ifdef CONFIG_MEMORY_HOTREMOVE
 /**
  * release_mem_region_adjustable - release a previously reserved memory region
- * @parent: parent resource descriptor
  * @start: resource start address
  * @size: resource region size
  *
@@ -1258,21 +1257,28 @@ EXPORT_SYMBOL(__release_region);
  *   assumes that all children remain in the lower address entry for
  *   simplicity.  Enhance this logic when necessary.
  */
-int release_mem_region_adjustable(struct resource *parent,
-				  resource_size_t start, resource_size_t size)
+void release_mem_region_adjustable(resource_size_t start, resource_size_t size)
 {
+	struct resource *parent = &iomem_resource;
+	struct resource *new_res = NULL;
+	bool alloc_nofail = false;
 	struct resource **p;
 	struct resource *res;
-	struct resource *new_res;
 	resource_size_t end;
-	int ret = -EINVAL;
 
 	end = start + size - 1;
-	if ((start < parent->start) || (end > parent->end))
-		return ret;
+	if (WARN_ON_ONCE((start < parent->start) || (end > parent->end)))
+		return;
 
-	/* The alloc_resource() result gets checked later */
-	new_res = alloc_resource(GFP_KERNEL);
+	/*
+	 * We free up quite a lot of memory on memory hotunplug (esp., memap),
+	 * just before releasing the region. This is highly unlikely to
+	 * fail - let's play save and make it never fail as the caller cannot
+	 * perform any error handling (e.g., trying to re-add memory will fail
+	 * similarly).
+	 */
+retry:
+	new_res = alloc_resource(GFP_KERNEL | (alloc_nofail ? __GFP_NOFAIL : 0));
 
 	p = &parent->child;
 	write_lock(&resource_lock);
@@ -1298,7 +1304,6 @@ int release_mem_region_adjustable(struct resource *parent,
 		 * so if we are dealing with them, let us just back off here.
 		 */
 		if (!(res->flags & IORESOURCE_SYSRAM)) {
-			ret = 0;
 			break;
 		}
 
@@ -1315,20 +1320,23 @@ int release_mem_region_adjustable(struct resource *parent,
 			/* free the whole entry */
 			*p = res->sibling;
 			free_resource(res);
-			ret = 0;
 		} else if (res->start == start && res->end != end) {
 			/* adjust the start */
-			ret = __adjust_resource(res, end + 1,
-						res->end - end);
+			WARN_ON_ONCE(__adjust_resource(res, end + 1,
+						       res->end - end));
 		} else if (res->start != start && res->end == end) {
 			/* adjust the end */
-			ret = __adjust_resource(res, res->start,
-						start - res->start);
+			WARN_ON_ONCE(__adjust_resource(res, res->start,
+						       start - res->start));
 		} else {
-			/* split into two entries */
+			/* split into two entries - we need a new resource */
 			if (!new_res) {
-				ret = -ENOMEM;
-				break;
+				new_res = alloc_resource(GFP_ATOMIC);
+				if (!new_res) {
+					alloc_nofail = true;
+					write_unlock(&resource_lock);
+					goto retry;
+				}
 			}
 			new_res->name = res->name;
 			new_res->start = end + 1;
@@ -1339,9 +1347,8 @@ int release_mem_region_adjustable(struct resource *parent,
 			new_res->sibling = res->sibling;
 			new_res->child = NULL;
 
-			ret = __adjust_resource(res, res->start,
-						start - res->start);
-			if (ret)
+			if (WARN_ON_ONCE(__adjust_resource(res, res->start,
+							   start - res->start)))
 				break;
 			res->sibling = new_res;
 			new_res = NULL;
@@ -1352,10 +1359,69 @@ int release_mem_region_adjustable(struct resource *parent,
 
 	write_unlock(&resource_lock);
 	free_resource(new_res);
-	return ret;
 }
 #endif	/* CONFIG_MEMORY_HOTREMOVE */
 
+#ifdef CONFIG_MEMORY_HOTPLUG
+static bool system_ram_resources_mergeable(struct resource *r1,
+					   struct resource *r2)
+{
+	/* We assume either r1 or r2 is IORESOURCE_SYSRAM_MERGEABLE. */
+	return r1->flags == r2->flags && r1->end + 1 == r2->start &&
+	       r1->name == r2->name && r1->desc == r2->desc &&
+	       !r1->child && !r2->child;
+}
+
+/*
+ * merge_system_ram_resource - mark the System RAM resource mergeable and try to
+ * merge it with adjacent, mergeable resources
+ * @res: resource descriptor
+ *
+ * This interface is intended for memory hotplug, whereby lots of contiguous
+ * system ram resources are added (e.g., via add_memory*()) by a driver, and
+ * the actual resource boundaries are not of interest (e.g., it might be
+ * relevant for DIMMs). Only resources that are marked mergeable, that have the
+ * same parent, and that don't have any children are considered. All mergeable
+ * resources must be immutable during the request.
+ *
+ * Note:
+ * - The caller has to make sure that no pointers to resources that are
+ *   marked mergeable are used anymore after this call - the resource might
+ *   be freed and the pointer might be stale!
+ * - release_mem_region_adjustable() will split on demand on memory hotunplug
+ */
+void merge_system_ram_resource(struct resource *res)
+{
+	const unsigned long flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
+	struct resource *cur;
+
+	if (WARN_ON_ONCE((res->flags & flags) != flags))
+		return;
+
+	write_lock(&resource_lock);
+	res->flags |= IORESOURCE_SYSRAM_MERGEABLE;
+
+	/* Try to merge with next item in the list. */
+	cur = res->sibling;
+	if (cur && system_ram_resources_mergeable(res, cur)) {
+		res->end = cur->end;
+		res->sibling = cur->sibling;
+		free_resource(cur);
+	}
+
+	/* Try to merge with previous item in the list. */
+	cur = res->parent->child;
+	while (cur && cur->sibling != res)
+		cur = cur->sibling;
+	if (cur && system_ram_resources_mergeable(cur, res)) {
+		cur->end = res->end;
+		cur->sibling = res->sibling;
+		free_resource(res);
+	}
+	write_unlock(&resource_lock);
+}
+#endif	/* CONFIG_MEMORY_HOTPLUG */
+
 /*
  * Managed region resource
  */
diff --git a/kernel/smp.c b/kernel/smp.c
index d0ae8eb6bf8b..d9832a171046 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -741,7 +741,7 @@ EXPORT_SYMBOL(on_each_cpu_mask);
  * for all the required CPUs to finish. This may include the local
  * processor.
  * @cond_func:	A callback function that is passed a cpu id and
- *		the the info parameter. The function is called
+ *		the info parameter. The function is called
  *		with preemption disabled. The function should
  *		return a blooean value indicating whether to IPI
  *		the specified CPU.
diff --git a/kernel/sys.c b/kernel/sys.c
index ab6c409b1159..6401880dff74 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -2034,7 +2034,7 @@ static int prctl_set_mm_map(int opt, const void __user *addr, unsigned long data
 	 * VMAs already unmapped and kernel uses these members for statistics
 	 * output in procfs mostly, except
 	 *
-	 *  - @start_brk/@brk which are used in do_brk but kernel lookups
+	 *  - @start_brk/@brk which are used in do_brk_flags but kernel lookups
 	 *    for VMAs when updating these memvers so anything wrong written
 	 *    here cause kernel to swear at userspace program but won't lead
 	 *    to any problem in kernel itself
diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c
index 87804e0371fe..e703d5d9cbe8 100644
--- a/kernel/user_namespace.c
+++ b/kernel/user_namespace.c
@@ -515,7 +515,7 @@ EXPORT_SYMBOL(from_kgid_munged);
  *
  *	When there is no mapping defined for the user-namespace projid
  *	pair INVALID_PROJID is returned.  Callers are expected to test
- *	for and handle handle INVALID_PROJID being returned.  INVALID_PROJID
+ *	for and handle INVALID_PROJID being returned.  INVALID_PROJID
  *	may be tested for using projid_valid().
  */
 kprojid_t make_kprojid(struct user_namespace *ns, projid_t projid)