Merge branch 'akpm' (incoming fixes from Andrew)

Merge misc fixes from Andrew Morton:
 "The audit fixes have been floating around for a while - Al and Eric
  aren't responding to either myself or Kees so I asked Kees to
  re-review them and here they are."

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (22 commits)
  lib/rbtree.c: avoid the use of non-static __always_inline
  MAINTAINERS: Omar had moved
  mm: compaction: partially revert capture of suitable high-order page
  linux/audit.h: move ptrace.h include to kernel header
  kernel/audit.c: avoid negative sleep durations
  audit: catch possible NULL audit buffers
  audit: create explicit AUDIT_SECCOMP event type
  MAINTAINERS: fix a status pattern
  MAINTAINERS: fix arch/arm/plat-omap/include/plat/omap_hwmod.h
  mm: thp: acquire the anon_vma rwsem for write during split
  mm: mmap: annotate vm_lock_anon_vma locking properly for lockdep
  lockdep, rwsem: provide down_write_nest_lock()
  arch/mn10300/Kconfig: select CONFIG_GENERIC_ATOMIC64
  mm: bootmem: fix free_all_bootmem_core() with odd bitmap alignment
  mm: use aligned zone start for pfn_to_bitidx calculation
  fs/exec.c: work around icc miscompilation
  mm: compaction: fix echo 1 > compact_memory return error issue
  mm: memblock: fix wrong memmove size in memblock_merge_regions()
  drivers/video/ssd1307fb.c: fix bit order bug in the byte translation function
  mm: migrate: check page_count of THP before migrating
  ...

MAINTAINERS

@@ -648,7 +648,7 @@ F:	arch/arm/
 
 ARM SUB-ARCHITECTURES
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
-S:	MAINTAINED
+S:	Maintained
 F:	arch/arm/mach-*/
 F:	arch/arm/plat-*/
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/arm/arm-soc.git
@@ -5507,8 +5507,7 @@ M:	Benoît Cousson <b-cousson@ti.com>
 M:	Paul Walmsley <paul@pwsan.com>
 L:	linux-omap@vger.kernel.org
 S:	Maintained
-F:	arch/arm/mach-omap2/omap_hwmod.c
-F:	arch/arm/plat-omap/include/plat/omap_hwmod.h
+F:	arch/arm/mach-omap2/omap_hwmod.*
 
 OMAP HWMOD DATA FOR OMAP4-BASED DEVICES
 M:	Benoît Cousson <b-cousson@ti.com>
@@ -7334,7 +7333,7 @@ S:	Odd Fixes
 F:	drivers/staging/speakup/
 
 STAGING - TI DSP BRIDGE DRIVERS
-M:	Omar Ramirez Luna <omar.ramirez@ti.com>
+M:	Omar Ramirez Luna <omar.ramirez@copitl.com>
 S:	Odd Fixes
 F:	drivers/staging/tidspbridge/
 

arch/mn10300/Kconfig

@@ -6,6 +6,7 @@ config MN10300
 	select ARCH_WANT_IPC_PARSE_VERSION
 	select HAVE_ARCH_TRACEHOOK
 	select HAVE_ARCH_KGDB
+	select GENERIC_ATOMIC64
 	select HAVE_NMI_WATCHDOG if MN10300_WD_TIMER
 	select GENERIC_CLOCKEVENTS
 	select MODULES_USE_ELF_RELA

drivers/rtc/rtc-da9055.c

@@ -227,7 +227,7 @@ static const struct rtc_class_ops da9055_rtc_ops = {
 	.alarm_irq_enable = da9055_rtc_alarm_irq_enable,
 };
 
-static int __init da9055_rtc_device_init(struct da9055 *da9055,
+static int da9055_rtc_device_init(struct da9055 *da9055,
 					struct da9055_pdata *pdata)
 {
 	int ret;

drivers/video/ssd1307fb.c

@@ -145,8 +145,8 @@ static void ssd1307fb_update_display(struct ssd1307fb_par *par)
 				u32 page_length = SSD1307FB_WIDTH * i;
 				u32 index = page_length + (SSD1307FB_WIDTH * k + j) / 8;
 				u8 byte = *(vmem + index);
-				u8 bit = byte & (1 << (7 - (j % 8)));
-				bit = bit >> (7 - (j % 8));
+				u8 bit = byte & (1 << (j % 8));
+				bit = bit >> (j % 8);
 				buf |= bit << k;
 			}
 			ssd1307fb_write_data(par->client, buf);

fs/exec.c

@@ -434,8 +434,9 @@ static int count(struct user_arg_ptr argv, int max)
 			if (IS_ERR(p))
 				return -EFAULT;
 
-			if (i++ >= max)
+			if (i >= max)
 				return -E2BIG;
+			++i;
 
 			if (fatal_signal_pending(current))
 				return -ERESTARTNOHAND;

include/linux/audit.h

@@ -24,6 +24,7 @@
 #define _LINUX_AUDIT_H_
 
 #include <linux/sched.h>
+#include <linux/ptrace.h>
 #include <uapi/linux/audit.h>
 
 struct audit_sig_info {
@@ -157,7 +158,8 @@ void audit_core_dumps(long signr);
 
 static inline void audit_seccomp(unsigned long syscall, long signr, int code)
 {
-	if (unlikely(!audit_dummy_context()))
+	/* Force a record to be reported if a signal was delivered. */
+	if (signr || unlikely(!audit_dummy_context()))
 		__audit_seccomp(syscall, signr, code);
 }
 

include/linux/cpu_rmap.h

@@ -13,9 +13,11 @@
 #include <linux/cpumask.h>
 #include <linux/gfp.h>
 #include <linux/slab.h>
+#include <linux/kref.h>
 
 /**
  * struct cpu_rmap - CPU affinity reverse-map
+ * @refcount: kref for object
  * @size: Number of objects to be reverse-mapped
  * @used: Number of objects added
  * @obj: Pointer to array of object pointers
@@ -23,6 +25,7 @@
  *      based on affinity masks
  */
 struct cpu_rmap {
+	struct kref	refcount;
 	u16		size, used;
 	void		**obj;
 	struct {
@@ -33,15 +36,7 @@ struct cpu_rmap {
 #define CPU_RMAP_DIST_INF 0xffff
 
 extern struct cpu_rmap *alloc_cpu_rmap(unsigned int size, gfp_t flags);
-
-/**
- * free_cpu_rmap - free CPU affinity reverse-map
- * @rmap: Reverse-map allocated with alloc_cpu_rmap(), or %NULL
- */
-static inline void free_cpu_rmap(struct cpu_rmap *rmap)
-{
-	kfree(rmap);
-}
+extern int cpu_rmap_put(struct cpu_rmap *rmap);
 
 extern int cpu_rmap_add(struct cpu_rmap *rmap, void *obj);
 extern int cpu_rmap_update(struct cpu_rmap *rmap, u16 index,

include/linux/interrupt.h

@@ -268,11 +268,6 @@ struct irq_affinity_notify {
 extern int
 irq_set_affinity_notifier(unsigned int irq, struct irq_affinity_notify *notify);
 
-static inline void irq_run_affinity_notifiers(void)
-{
-	flush_scheduled_work();
-}
-
 #else /* CONFIG_SMP */
 
 static inline int irq_set_affinity(unsigned int irq, const struct cpumask *m)

include/linux/lockdep.h

@@ -524,14 +524,17 @@ static inline void print_irqtrace_events(struct task_struct *curr)
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 # ifdef CONFIG_PROVE_LOCKING
 #  define rwsem_acquire(l, s, t, i)		lock_acquire(l, s, t, 0, 2, NULL, i)
+#  define rwsem_acquire_nest(l, s, t, n, i)	lock_acquire(l, s, t, 0, 2, n, i)
 #  define rwsem_acquire_read(l, s, t, i)	lock_acquire(l, s, t, 1, 2, NULL, i)
 # else
 #  define rwsem_acquire(l, s, t, i)		lock_acquire(l, s, t, 0, 1, NULL, i)
+#  define rwsem_acquire_nest(l, s, t, n, i)	lock_acquire(l, s, t, 0, 1, n, i)
 #  define rwsem_acquire_read(l, s, t, i)	lock_acquire(l, s, t, 1, 1, NULL, i)
 # endif
 # define rwsem_release(l, n, i)			lock_release(l, n, i)
 #else
 # define rwsem_acquire(l, s, t, i)		do { } while (0)
+# define rwsem_acquire_nest(l, s, t, n, i)	do { } while (0)
 # define rwsem_acquire_read(l, s, t, i)		do { } while (0)
 # define rwsem_release(l, n, i)			do { } while (0)
 #endif

include/linux/rbtree_augmented.h

@@ -123,8 +123,8 @@ __rb_change_child(struct rb_node *old, struct rb_node *new,
 extern void __rb_erase_color(struct rb_node *parent, struct rb_root *root,
 	void (*augment_rotate)(struct rb_node *old, struct rb_node *new));
 
-static __always_inline void
-rb_erase_augmented(struct rb_node *node, struct rb_root *root,
+static __always_inline struct rb_node *
+__rb_erase_augmented(struct rb_node *node, struct rb_root *root,
 		     const struct rb_augment_callbacks *augment)
 {
 	struct rb_node *child = node->rb_right, *tmp = node->rb_left;
@@ -217,6 +217,14 @@ rb_erase_augmented(struct rb_node *node, struct rb_root *root,
 	}
 
 	augment->propagate(tmp, NULL);
+	return rebalance;
+}
+
+static __always_inline void
+rb_erase_augmented(struct rb_node *node, struct rb_root *root,
+		   const struct rb_augment_callbacks *augment)
+{
+	struct rb_node *rebalance = __rb_erase_augmented(node, root, augment);
 	if (rebalance)
 		__rb_erase_color(rebalance, root, augment->rotate);
 }

include/linux/rwsem.h

@@ -125,8 +125,17 @@ extern void downgrade_write(struct rw_semaphore *sem);
  */
 extern void down_read_nested(struct rw_semaphore *sem, int subclass);
 extern void down_write_nested(struct rw_semaphore *sem, int subclass);
+extern void _down_write_nest_lock(struct rw_semaphore *sem, struct lockdep_map *nest_lock);
+
+# define down_write_nest_lock(sem, nest_lock)			\
+do {								\
+	typecheck(struct lockdep_map *, &(nest_lock)->dep_map);	\
+	_down_write_nest_lock(sem, &(nest_lock)->dep_map);	\
+} while (0);
+
 #else
 # define down_read_nested(sem, subclass)		down_read(sem)
+# define down_write_nest_lock(sem, nest_lock)	down_read(sem)
 # define down_write_nested(sem, subclass)	down_write(sem)
 #endif
 

include/uapi/linux/audit.h

@@ -26,7 +26,6 @@
 
 #include <linux/types.h>
 #include <linux/elf-em.h>
-#include <linux/ptrace.h>
 
 /* The netlink messages for the audit system is divided into blocks:
  * 1000 - 1099 are for commanding the audit system
@@ -106,6 +105,7 @@
 #define AUDIT_MMAP		1323	/* Record showing descriptor and flags in mmap */
 #define AUDIT_NETFILTER_PKT	1324	/* Packets traversing netfilter chains */
 #define AUDIT_NETFILTER_CFG	1325	/* Netfilter chain modifications */
+#define AUDIT_SECCOMP		1326	/* Secure Computing event */
 
 #define AUDIT_AVC		1400	/* SE Linux avc denial or grant */
 #define AUDIT_SELINUX_ERR	1401	/* Internal SE Linux Errors */

kernel/audit.c

@@ -272,6 +272,8 @@ static int audit_log_config_change(char *function_name, int new, int old,
 	int rc = 0;
 
 	ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_CONFIG_CHANGE);
+	if (unlikely(!ab))
+		return rc;
 	audit_log_format(ab, "%s=%d old=%d auid=%u ses=%u", function_name, new,
 			 old, from_kuid(&init_user_ns, loginuid), sessionid);
 	if (sid) {
@@ -619,6 +621,8 @@ static int audit_log_common_recv_msg(struct audit_buffer **ab, u16 msg_type,
 	}
 
 	*ab = audit_log_start(NULL, GFP_KERNEL, msg_type);
+	if (unlikely(!*ab))
+		return rc;
 	audit_log_format(*ab, "pid=%d uid=%u auid=%u ses=%u",
 			 task_tgid_vnr(current),
 			 from_kuid(&init_user_ns, current_uid()),
@@ -1097,6 +1101,23 @@ static inline void audit_get_stamp(struct audit_context *ctx,
 	}
 }
 
+/*
+ * Wait for auditd to drain the queue a little
+ */
+static void wait_for_auditd(unsigned long sleep_time)
+{
+	DECLARE_WAITQUEUE(wait, current);
+	set_current_state(TASK_INTERRUPTIBLE);
+	add_wait_queue(&audit_backlog_wait, &wait);
+
+	if (audit_backlog_limit &&
+	    skb_queue_len(&audit_skb_queue) > audit_backlog_limit)
+		schedule_timeout(sleep_time);
+
+	__set_current_state(TASK_RUNNING);
+	remove_wait_queue(&audit_backlog_wait, &wait);
+}
+
 /* Obtain an audit buffer.  This routine does locking to obtain the
  * audit buffer, but then no locking is required for calls to
  * audit_log_*format.  If the tsk is a task that is currently in a
@@ -1142,20 +1163,13 @@ struct audit_buffer *audit_log_start(struct audit_context *ctx, gfp_t gfp_mask,
 
 	while (audit_backlog_limit
 	       && skb_queue_len(&audit_skb_queue) > audit_backlog_limit + reserve) {
-		if (gfp_mask & __GFP_WAIT && audit_backlog_wait_time
-		    && time_before(jiffies, timeout_start + audit_backlog_wait_time)) {
-
-			/* Wait for auditd to drain the queue a little */
-			DECLARE_WAITQUEUE(wait, current);
-			set_current_state(TASK_INTERRUPTIBLE);
-			add_wait_queue(&audit_backlog_wait, &wait);
-
-			if (audit_backlog_limit &&
-			    skb_queue_len(&audit_skb_queue) > audit_backlog_limit)
-				schedule_timeout(timeout_start + audit_backlog_wait_time - jiffies);
+		if (gfp_mask & __GFP_WAIT && audit_backlog_wait_time) {
+			unsigned long sleep_time;
 
-			__set_current_state(TASK_RUNNING);
-			remove_wait_queue(&audit_backlog_wait, &wait);
+			sleep_time = timeout_start + audit_backlog_wait_time -
+					jiffies;
+			if ((long)sleep_time > 0)
+				wait_for_auditd(sleep_time);
 			continue;
 		}
 		if (audit_rate_check() && printk_ratelimit())

kernel/audit_tree.c

@@ -449,19 +449,13 @@ static int tag_chunk(struct inode *inode, struct audit_tree *tree)
 	return 0;
 }
 
-static void kill_rules(struct audit_tree *tree)
+static void audit_log_remove_rule(struct audit_krule *rule)
 {
-	struct audit_krule *rule, *next;
-	struct audit_entry *entry;
 	struct audit_buffer *ab;
 
-	list_for_each_entry_safe(rule, next, &tree->rules, rlist) {
-		entry = container_of(rule, struct audit_entry, rule);
-
-		list_del_init(&rule->rlist);
-		if (rule->tree) {
-			/* not a half-baked one */
 	ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_CONFIG_CHANGE);
+	if (unlikely(!ab))
+		return;
 	audit_log_format(ab, "op=");
 	audit_log_string(ab, "remove rule");
 	audit_log_format(ab, " dir=");
@@ -469,6 +463,20 @@ static void kill_rules(struct audit_tree *tree)
 	audit_log_key(ab, rule->filterkey);
 	audit_log_format(ab, " list=%d res=1", rule->listnr);
 	audit_log_end(ab);
+}
+
+static void kill_rules(struct audit_tree *tree)
+{
+	struct audit_krule *rule, *next;
+	struct audit_entry *entry;
+
+	list_for_each_entry_safe(rule, next, &tree->rules, rlist) {
+		entry = container_of(rule, struct audit_entry, rule);
+
+		list_del_init(&rule->rlist);
+		if (rule->tree) {
+			/* not a half-baked one */
+			audit_log_remove_rule(rule);
 			rule->tree = NULL;
 			list_del_rcu(&entry->list);
 			list_del(&entry->rule.list);

kernel/audit_watch.c

@@ -240,6 +240,8 @@ static void audit_watch_log_rule_change(struct audit_krule *r, struct audit_watc
 	if (audit_enabled) {
 		struct audit_buffer *ab;
 		ab = audit_log_start(NULL, GFP_NOFS, AUDIT_CONFIG_CHANGE);
+		if (unlikely(!ab))
+			return;
 		audit_log_format(ab, "auid=%u ses=%u op=",
 				 from_kuid(&init_user_ns, audit_get_loginuid(current)),
 				 audit_get_sessionid(current));

kernel/auditsc.c

@@ -1464,14 +1464,14 @@ static void show_special(struct audit_context *context, int *call_panic)
 			audit_log_end(ab);
 			ab = audit_log_start(context, GFP_KERNEL,
 					     AUDIT_IPC_SET_PERM);
+			if (unlikely(!ab))
+				return;
 			audit_log_format(ab,
 				"qbytes=%lx ouid=%u ogid=%u mode=%#ho",
 				context->ipc.qbytes,
 				context->ipc.perm_uid,
 				context->ipc.perm_gid,
 				context->ipc.perm_mode);
-			if (!ab)
-				return;
 		}
 		break; }
 	case AUDIT_MQ_OPEN: {
@@ -2675,7 +2675,7 @@ void __audit_mmap_fd(int fd, int flags)
 	context->type = AUDIT_MMAP;
 }
 
-static void audit_log_abend(struct audit_buffer *ab, char *reason, long signr)
+static void audit_log_task(struct audit_buffer *ab)
 {
 	kuid_t auid, uid;
 	kgid_t gid;
@@ -2693,6 +2693,11 @@ static void audit_log_abend(struct audit_buffer *ab, char *reason, long signr)
 	audit_log_task_context(ab);
 	audit_log_format(ab, " pid=%d comm=", current->pid);
 	audit_log_untrustedstring(ab, current->comm);
+}
+
+static void audit_log_abend(struct audit_buffer *ab, char *reason, long signr)
+{
+	audit_log_task(ab);
 	audit_log_format(ab, " reason=");
 	audit_log_string(ab, reason);
 	audit_log_format(ab, " sig=%ld", signr);
@@ -2715,6 +2720,8 @@ void audit_core_dumps(long signr)
 		return;
 
 	ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_ANOM_ABEND);
+	if (unlikely(!ab))
+		return;
 	audit_log_abend(ab, "memory violation", signr);
 	audit_log_end(ab);
 }
@@ -2723,8 +2730,11 @@ void __audit_seccomp(unsigned long syscall, long signr, int code)
 {
 	struct audit_buffer *ab;
 
-	ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_ANOM_ABEND);
-	audit_log_abend(ab, "seccomp", signr);
+	ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_SECCOMP);
+	if (unlikely(!ab))
+		return;
+	audit_log_task(ab);
+	audit_log_format(ab, " sig=%ld", signr);
 	audit_log_format(ab, " syscall=%ld", syscall);
 	audit_log_format(ab, " compat=%d", is_compat_task());
 	audit_log_format(ab, " ip=0x%lx", KSTK_EIP(current));

kernel/rwsem.c

@@ -116,6 +116,16 @@ void down_read_nested(struct rw_semaphore *sem, int subclass)
 
 EXPORT_SYMBOL(down_read_nested);
 
+void _down_write_nest_lock(struct rw_semaphore *sem, struct lockdep_map *nest)
+{
+	might_sleep();
+	rwsem_acquire_nest(&sem->dep_map, 0, 0, nest, _RET_IP_);
+
+	LOCK_CONTENDED(sem, __down_write_trylock, __down_write);
+}
+
+EXPORT_SYMBOL(_down_write_nest_lock);
+
 void down_write_nested(struct rw_semaphore *sem, int subclass)
 {
 	might_sleep();

lib/cpu_rmap.c

@@ -45,6 +45,7 @@ struct cpu_rmap *alloc_cpu_rmap(unsigned int size, gfp_t flags)
 	if (!rmap)
 		return NULL;
 
+	kref_init(&rmap->refcount);
 	rmap->obj = (void **)((char *)rmap + obj_offset);
 
 	/* Initially assign CPUs to objects on a rota, since we have
@@ -63,6 +64,35 @@ struct cpu_rmap *alloc_cpu_rmap(unsigned int size, gfp_t flags)
 }
 EXPORT_SYMBOL(alloc_cpu_rmap);
 
+/**
+ * cpu_rmap_release - internal reclaiming helper called from kref_put
+ * @ref: kref to struct cpu_rmap
+ */
+static void cpu_rmap_release(struct kref *ref)
+{
+	struct cpu_rmap *rmap = container_of(ref, struct cpu_rmap, refcount);
+	kfree(rmap);
+}
+
+/**
+ * cpu_rmap_get - internal helper to get new ref on a cpu_rmap
+ * @rmap: reverse-map allocated with alloc_cpu_rmap()
+ */
+static inline void cpu_rmap_get(struct cpu_rmap *rmap)
+{
+	kref_get(&rmap->refcount);
+}
+
+/**
+ * cpu_rmap_put - release ref on a cpu_rmap
+ * @rmap: reverse-map allocated with alloc_cpu_rmap()
+ */
+int cpu_rmap_put(struct cpu_rmap *rmap)
+{
+	return kref_put(&rmap->refcount, cpu_rmap_release);
+}
+EXPORT_SYMBOL(cpu_rmap_put);
+
 /* Reevaluate nearest object for given CPU, comparing with the given
  * neighbours at the given distance.
  */
@@ -197,8 +227,7 @@ struct irq_glue {
  * free_irq_cpu_rmap - free a CPU affinity reverse-map used for IRQs
  * @rmap: Reverse-map allocated with alloc_irq_cpu_map(), or %NULL
  *
- * Must be called in process context, before freeing the IRQs, and
- * without holding any locks required by global workqueue items.
+ * Must be called in process context, before freeing the IRQs.
  */
 void free_irq_cpu_rmap(struct cpu_rmap *rmap)
 {
@@ -212,12 +241,18 @@ void free_irq_cpu_rmap(struct cpu_rmap *rmap)
 		glue = rmap->obj[index];
 		irq_set_affinity_notifier(glue->notify.irq, NULL);
 	}
-	irq_run_affinity_notifiers();
 
-	kfree(rmap);
+	cpu_rmap_put(rmap);
 }
 EXPORT_SYMBOL(free_irq_cpu_rmap);
 
+/**
+ * irq_cpu_rmap_notify - callback for IRQ subsystem when IRQ affinity updated
+ * @notify: struct irq_affinity_notify passed by irq/manage.c
+ * @mask: cpu mask for new SMP affinity
+ *
+ * This is executed in workqueue context.
+ */
 static void
 irq_cpu_rmap_notify(struct irq_affinity_notify *notify, const cpumask_t *mask)
 {
@@ -230,10 +265,16 @@ irq_cpu_rmap_notify(struct irq_affinity_notify *notify, const cpumask_t *mask)
 		pr_warning("irq_cpu_rmap_notify: update failed: %d\n", rc);
 }
 
+/**
+ * irq_cpu_rmap_release - reclaiming callback for IRQ subsystem
+ * @ref: kref to struct irq_affinity_notify passed by irq/manage.c
+ */
 static void irq_cpu_rmap_release(struct kref *ref)
 {
 	struct irq_glue *glue =
 		container_of(ref, struct irq_glue, notify.kref);
+
+	cpu_rmap_put(glue->rmap);
 	kfree(glue);
 }
 
@@ -258,10 +299,13 @@ int irq_cpu_rmap_add(struct cpu_rmap *rmap, int irq)
 	glue->notify.notify = irq_cpu_rmap_notify;
 	glue->notify.release = irq_cpu_rmap_release;
 	glue->rmap = rmap;
+	cpu_rmap_get(rmap);
 	glue->index = cpu_rmap_add(rmap, glue);
 	rc = irq_set_affinity_notifier(irq, &glue->notify);
-	if (rc)
+	if (rc) {
+		cpu_rmap_put(glue->rmap);
 		kfree(glue);
+	}
 	return rc;
 }
 EXPORT_SYMBOL(irq_cpu_rmap_add);

lib/rbtree.c

@@ -194,8 +194,12 @@ __rb_insert(struct rb_node *node, struct rb_root *root,
 	}
 }
 
-__always_inline void
-__rb_erase_color(struct rb_node *parent, struct rb_root *root,
+/*
+ * Inline version for rb_erase() use - we want to be able to inline
+ * and eliminate the dummy_rotate callback there
+ */
+static __always_inline void
+____rb_erase_color(struct rb_node *parent, struct rb_root *root,
 	void (*augment_rotate)(struct rb_node *old, struct rb_node *new))
 {
 	struct rb_node *node = NULL, *sibling, *tmp1, *tmp2;
@@ -355,6 +359,13 @@ __rb_erase_color(struct rb_node *parent, struct rb_root *root,
 		}
 	}
 }
+
+/* Non-inline version for rb_erase_augmented() use */
+void __rb_erase_color(struct rb_node *parent, struct rb_root *root,
+	void (*augment_rotate)(struct rb_node *old, struct rb_node *new))
+{
+	____rb_erase_color(parent, root, augment_rotate);
+}
 EXPORT_SYMBOL(__rb_erase_color);
 
 /*
@@ -380,7 +391,10 @@ EXPORT_SYMBOL(rb_insert_color);
 
 void rb_erase(struct rb_node *node, struct rb_root *root)
 {
-	rb_erase_augmented(node, root, &dummy_callbacks);
+	struct rb_node *rebalance;
+	rebalance = __rb_erase_augmented(node, root, &dummy_callbacks);
+	if (rebalance)
+		____rb_erase_color(rebalance, root, dummy_rotate);
 }
 EXPORT_SYMBOL(rb_erase);
 

mm/bootmem.c

@@ -185,10 +185,23 @@ static unsigned long __init free_all_bootmem_core(bootmem_data_t *bdata)
 
 	while (start < end) {
 		unsigned long *map, idx, vec;
+		unsigned shift;
 
 		map = bdata->node_bootmem_map;
 		idx = start - bdata->node_min_pfn;
+		shift = idx & (BITS_PER_LONG - 1);
+		/*
+		 * vec holds at most BITS_PER_LONG map bits,
+		 * bit 0 corresponds to start.
+		 */
 		vec = ~map[idx / BITS_PER_LONG];
+
+		if (shift) {
+			vec >>= shift;
+			if (end - start >= BITS_PER_LONG)
+				vec |= ~map[idx / BITS_PER_LONG + 1] <<
+					(BITS_PER_LONG - shift);
+		}
 		/*
 		 * If we have a properly aligned and fully unreserved
 		 * BITS_PER_LONG block of pages in front of us, free
@@ -201,19 +214,18 @@ static unsigned long __init free_all_bootmem_core(bootmem_data_t *bdata)
 			count += BITS_PER_LONG;
 			start += BITS_PER_LONG;
 		} else {
-			unsigned long off = 0;
+			unsigned long cur = start;
 
-			vec >>= start & (BITS_PER_LONG - 1);
-			while (vec) {
+			start = ALIGN(start + 1, BITS_PER_LONG);
+			while (vec && cur != start) {
 				if (vec & 1) {
-					page = pfn_to_page(start + off);
+					page = pfn_to_page(cur);
 					__free_pages_bootmem(page, 0);
 					count++;
 				}
 				vec >>= 1;
-				off++;
+				++cur;
 			}
-			start = ALIGN(start + 1, BITS_PER_LONG);
 		}
 	}
 

mm/compaction.c

@@ -1144,7 +1144,7 @@ static int compact_node(int nid)
 }
 
 /* Compact all nodes in the system */
-static int compact_nodes(void)
+static void compact_nodes(void)
 {
 	int nid;
 
@@ -1153,8 +1153,6 @@ static int compact_nodes(void)
 
 	for_each_online_node(nid)
 		compact_node(nid);
-
-	return COMPACT_COMPLETE;
 }
 
 /* The written value is actually unused, all memory is compacted */
@@ -1165,7 +1163,7 @@ int sysctl_compaction_handler(struct ctl_table *table, int write,
 			void __user *buffer, size_t *length, loff_t *ppos)
 {
 	if (write)
-		return compact_nodes();
+		compact_nodes();
 
 	return 0;
 }

mm/huge_memory.c

@@ -1819,9 +1819,19 @@ int split_huge_page(struct page *page)
 
 	BUG_ON(is_huge_zero_pfn(page_to_pfn(page)));
 	BUG_ON(!PageAnon(page));
-	anon_vma = page_lock_anon_vma_read(page);
+
+	/*
+	 * The caller does not necessarily hold an mmap_sem that would prevent
+	 * the anon_vma disappearing so we first we take a reference to it
+	 * and then lock the anon_vma for write. This is similar to
+	 * page_lock_anon_vma_read except the write lock is taken to serialise
+	 * against parallel split or collapse operations.
+	 */
+	anon_vma = page_get_anon_vma(page);
 	if (!anon_vma)
 		goto out;
+	anon_vma_lock_write(anon_vma);
+
 	ret = 0;
 	if (!PageCompound(page))
 		goto out_unlock;
@@ -1832,7 +1842,8 @@ int split_huge_page(struct page *page)
 
 	BUG_ON(PageCompound(page));
 out_unlock:
-	page_unlock_anon_vma_read(anon_vma);
+	anon_vma_unlock(anon_vma);
+	put_anon_vma(anon_vma);
 out:
 	return ret;
 }

mm/memblock.c

@@ -314,7 +314,8 @@ static void __init_memblock memblock_merge_regions(struct memblock_type *type)
 		}
 
 		this->size += next->size;
-		memmove(next, next + 1, (type->cnt - (i + 1)) * sizeof(*next));
+		/* move forward from next + 1, index of which is i + 2 */
+		memmove(next, next + 1, (type->cnt - (i + 2)) * sizeof(*next));
 		type->cnt--;
 	}
 }

mm/migrate.c

@@ -1679,9 +1679,21 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm,
 	page_xchg_last_nid(new_page, page_last_nid(page));
 
 	isolated = numamigrate_isolate_page(pgdat, page);
-	if (!isolated) {
+
+	/*
+	 * Failing to isolate or a GUP pin prevents migration. The expected
+	 * page count is 2. 1 for anonymous pages without a mapping and 1
+	 * for the callers pin. If the page was isolated, the page will
+	 * need to be put back on the LRU.
+	 */
+	if (!isolated || page_count(page) != 2) {
 		count_vm_events(PGMIGRATE_FAIL, HPAGE_PMD_NR);
 		put_page(new_page);
+		if (isolated) {
+			putback_lru_page(page);
+			isolated = 0;
+			goto out;
+		}
 		goto out_keep_locked;
 	}
 

mm/mmap.c

@@ -2886,7 +2886,7 @@ static void vm_lock_anon_vma(struct mm_struct *mm, struct anon_vma *anon_vma)
 		 * The LSB of head.next can't change from under us
 		 * because we hold the mm_all_locks_mutex.
 		 */
-		down_write(&anon_vma->root->rwsem);
+		down_write_nest_lock(&anon_vma->root->rwsem, &mm->mmap_sem);
 		/*
 		 * We can safely modify head.next after taking the
 		 * anon_vma->root->rwsem. If some other vma in this mm shares

mm/page_alloc.c

@@ -5585,7 +5585,7 @@ static inline int pfn_to_bitidx(struct zone *zone, unsigned long pfn)
 	pfn &= (PAGES_PER_SECTION-1);
 	return (pfn >> pageblock_order) * NR_PAGEBLOCK_BITS;
 #else
-	pfn = pfn - zone->zone_start_pfn;
+	pfn = pfn - round_down(zone->zone_start_pfn, pageblock_nr_pages);
 	return (pfn >> pageblock_order) * NR_PAGEBLOCK_BITS;
 #endif /* CONFIG_SPARSEMEM */
 }