Merge branch 'akpm' (patches from Andrew)

Merge fixes from Andrew Morton:
 "26 fixes"

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (26 commits)
  MAINTAINERS: add Dan Streetman to zbud maintainers
  MAINTAINERS: add Dan Streetman to zswap maintainers
  mm: do not export ioremap_page_range symbol for external module
  mn10300: fix build error of missing fpu_save()
  romfs: use different way to generate fsid for BLOCK or MTD
  frv: add missing atomic64 operations
  mm, page_alloc: fix premature OOM when racing with cpuset mems update
  mm, page_alloc: move cpuset seqcount checking to slowpath
  mm, page_alloc: fix fast-path race with cpuset update or removal
  mm, page_alloc: fix check for NULL preferred_zone
  kernel/panic.c: add missing \n
  fbdev: color map copying bounds checking
  frv: add atomic64_add_unless()
  mm/mempolicy.c: do not put mempolicy before using its nodemask
  radix-tree: fix private list warnings
  Documentation/filesystems/proc.txt: add VmPin
  mm, memcg: do not retry precharge charges
  proc: add a schedule point in proc_pid_readdir()
  mm: alloc_contig: re-allow CMA to compact FS pages
  mm/slub.c: trace free objects at KERN_INFO
  ...

Documentation/filesystems/proc.txt

@@ -212,10 +212,11 @@ asynchronous manner and the value may not be very precise. To see a precise
 snapshot of a moment, you can see /proc/<pid>/smaps file and scan page table.
 It's slow but very precise.
 
-Table 1-2: Contents of the status files (as of 4.1)
+Table 1-2: Contents of the status files (as of 4.8)
 ..............................................................................
  Field                       Content
  Name                        filename of the executable
+ Umask                       file mode creation mask
  State                       state (R is running, S is sleeping, D is sleeping
                              in an uninterruptible wait, Z is zombie,
 			     T is traced or stopped)
@@ -226,7 +227,6 @@ Table 1-2: Contents of the status files (as of 4.1)
  TracerPid                   PID of process tracing this process (0 if not)
  Uid                         Real, effective, saved set, and  file system UIDs
  Gid                         Real, effective, saved set, and  file system GIDs
- Umask                       file mode creation mask
  FDSize                      number of file descriptor slots currently allocated
  Groups                      supplementary group list
  NStgid                      descendant namespace thread group ID hierarchy
@@ -236,6 +236,7 @@ Table 1-2: Contents of the status files (as of 4.1)
  VmPeak                      peak virtual memory size
  VmSize                      total program size
  VmLck                       locked memory size
+ VmPin                       pinned memory size
  VmHWM                       peak resident set size ("high water mark")
  VmRSS                       size of memory portions. It contains the three
                              following parts (VmRSS = RssAnon + RssFile + RssShmem)

MAINTAINERS

@@ -13625,6 +13625,7 @@ F:	drivers/net/hamradio/z8530.h
 
 ZBUD COMPRESSED PAGE ALLOCATOR
 M:	Seth Jennings <sjenning@redhat.com>
+M:	Dan Streetman <ddstreet@ieee.org>
 L:	linux-mm@kvack.org
 S:	Maintained
 F:	mm/zbud.c
@@ -13680,6 +13681,7 @@ F:	Documentation/vm/zsmalloc.txt
 
 ZSWAP COMPRESSED SWAP CACHING
 M:	Seth Jennings <sjenning@redhat.com>
+M:	Dan Streetman <ddstreet@ieee.org>
 L:	linux-mm@kvack.org
 S:	Maintained
 F:	mm/zswap.c

arch/frv/include/asm/atomic.h

@@ -139,7 +139,7 @@ static inline void atomic64_dec(atomic64_t *v)
 #define atomic64_sub_and_test(i,v)	(atomic64_sub_return((i), (v)) == 0)
 #define atomic64_dec_and_test(v)	(atomic64_dec_return((v)) == 0)
 #define atomic64_inc_and_test(v)	(atomic64_inc_return((v)) == 0)
-
+#define atomic64_inc_not_zero(v)	atomic64_add_unless((v), 1, 0)
 
 #define atomic_cmpxchg(v, old, new)	(cmpxchg(&(v)->counter, old, new))
 #define atomic_xchg(v, new)		(xchg(&(v)->counter, new))
@@ -161,6 +161,39 @@ static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u)
 	return c;
 }
 
+static inline int atomic64_add_unless(atomic64_t *v, long long i, long long u)
+{
+	long long c, old;
+
+	c = atomic64_read(v);
+	for (;;) {
+		if (unlikely(c == u))
+			break;
+		old = atomic64_cmpxchg(v, c, c + i);
+		if (likely(old == c))
+			break;
+		c = old;
+	}
+	return c != u;
+}
+
+static inline long long atomic64_dec_if_positive(atomic64_t *v)
+{
+	long long c, old, dec;
+
+	c = atomic64_read(v);
+	for (;;) {
+		dec = c - 1;
+		if (unlikely(dec < 0))
+			break;
+		old = atomic64_cmpxchg((v), c, dec);
+		if (likely(old == c))
+			break;
+		c = old;
+	}
+		return dec;
+}
+
 #define ATOMIC_OP(op)							\
 static inline int atomic_fetch_##op(int i, atomic_t *v)			\
 {									\

arch/mn10300/include/asm/switch_to.h

@@ -16,7 +16,7 @@
 struct task_struct;
 struct thread_struct;
 
-#if !defined(CONFIG_LAZY_SAVE_FPU)
+#if defined(CONFIG_FPU) && !defined(CONFIG_LAZY_SAVE_FPU)
 struct fpu_state_struct;
 extern asmlinkage void fpu_save(struct fpu_state_struct *);
 #define switch_fpu(prev, next)						\

drivers/base/memory.c

@@ -408,14 +408,14 @@ static ssize_t show_valid_zones(struct device *dev,
 	sprintf(buf, "%s", zone->name);
 
 	/* MMOP_ONLINE_KERNEL */
-	zone_shift = zone_can_shift(start_pfn, nr_pages, ZONE_NORMAL);
+	zone_can_shift(start_pfn, nr_pages, ZONE_NORMAL, &zone_shift);
 	if (zone_shift) {
 		strcat(buf, " ");
 		strcat(buf, (zone + zone_shift)->name);
 	}
 
 	/* MMOP_ONLINE_MOVABLE */
-	zone_shift = zone_can_shift(start_pfn, nr_pages, ZONE_MOVABLE);
+	zone_can_shift(start_pfn, nr_pages, ZONE_MOVABLE, &zone_shift);
 	if (zone_shift) {
 		strcat(buf, " ");
 		strcat(buf, (zone + zone_shift)->name);

drivers/memstick/core/memstick.c

@@ -330,7 +330,7 @@ static int h_memstick_read_dev_id(struct memstick_dev *card,
 	struct ms_id_register id_reg;
 
 	if (!(*mrq)) {
-		memstick_init_req(&card->current_mrq, MS_TPC_READ_REG, NULL,
+		memstick_init_req(&card->current_mrq, MS_TPC_READ_REG, &id_reg,
 				  sizeof(struct ms_id_register));
 		*mrq = &card->current_mrq;
 		return 0;

drivers/video/fbdev/core/fbcmap.c

@@ -163,17 +163,18 @@ void fb_dealloc_cmap(struct fb_cmap *cmap)
 
 int fb_copy_cmap(const struct fb_cmap *from, struct fb_cmap *to)
 {
-	int tooff = 0, fromoff = 0;
-	int size;
+	unsigned int tooff = 0, fromoff = 0;
+	size_t size;
 
 	if (to->start > from->start)
 		fromoff = to->start - from->start;
 	else
 		tooff = from->start - to->start;
-	size = to->len - tooff;
-	if (size > (int) (from->len - fromoff))
-		size = from->len - fromoff;
-	if (size <= 0)
+	if (fromoff >= from->len || tooff >= to->len)
+		return -EINVAL;
+
+	size = min_t(size_t, to->len - tooff, from->len - fromoff);
+	if (size == 0)
 		return -EINVAL;
 	size *= sizeof(u16);
 
@@ -187,17 +188,18 @@ int fb_copy_cmap(const struct fb_cmap *from, struct fb_cmap *to)
 
 int fb_cmap_to_user(const struct fb_cmap *from, struct fb_cmap_user *to)
 {
-	int tooff = 0, fromoff = 0;
-	int size;
+	unsigned int tooff = 0, fromoff = 0;
+	size_t size;
 
 	if (to->start > from->start)
 		fromoff = to->start - from->start;
 	else
 		tooff = from->start - to->start;
-	size = to->len - tooff;
-	if (size > (int) (from->len - fromoff))
-		size = from->len - fromoff;
-	if (size <= 0)
+	if (fromoff >= from->len || tooff >= to->len)
+		return -EINVAL;
+
+	size = min_t(size_t, to->len - tooff, from->len - fromoff);
+	if (size == 0)
 		return -EINVAL;
 	size *= sizeof(u16);
 

fs/Kconfig

@@ -38,6 +38,7 @@ config FS_DAX
 	bool "Direct Access (DAX) support"
 	depends on MMU
 	depends on !(ARM || MIPS || SPARC)
+	select FS_IOMAP
 	help
 	  Direct Access (DAX) can be used on memory-backed block devices.
 	  If the block device supports DAX and the filesystem supports DAX,

fs/dax.c

@@ -990,7 +990,6 @@ int __dax_zero_page_range(struct block_device *bdev, sector_t sector,
 }
 EXPORT_SYMBOL_GPL(__dax_zero_page_range);
 
-#ifdef CONFIG_FS_IOMAP
 static sector_t dax_iomap_sector(struct iomap *iomap, loff_t pos)
 {
 	return iomap->blkno + (((pos & PAGE_MASK) - iomap->offset) >> 9);
@@ -1428,4 +1427,3 @@ int dax_iomap_pmd_fault(struct vm_area_struct *vma, unsigned long address,
 }
 EXPORT_SYMBOL_GPL(dax_iomap_pmd_fault);
 #endif /* CONFIG_FS_DAX_PMD */
-#endif /* CONFIG_FS_IOMAP */

fs/ext2/Kconfig

 config EXT2_FS
 	tristate "Second extended fs support"
-	select FS_IOMAP if FS_DAX
 	help
 	  Ext2 is a standard Linux file system for hard disks.
 

fs/ext4/Kconfig

@@ -37,7 +37,6 @@ config EXT4_FS
 	select CRC16
 	select CRYPTO
 	select CRYPTO_CRC32C
-	select FS_IOMAP if FS_DAX
 	help
 	  This is the next generation of the ext3 filesystem.
 

fs/proc/base.c

@@ -3179,6 +3179,8 @@ int proc_pid_readdir(struct file *file, struct dir_context *ctx)
 	     iter.tgid += 1, iter = next_tgid(ns, iter)) {
 		char name[PROC_NUMBUF];
 		int len;
+
+		cond_resched();
 		if (!has_pid_permissions(ns, iter.task, 2))
 			continue;
 

fs/romfs/super.c

@@ -74,6 +74,7 @@
 #include <linux/highmem.h>
 #include <linux/pagemap.h>
 #include <linux/uaccess.h>
+#include <linux/major.h>
 #include "internal.h"
 
 static struct kmem_cache *romfs_inode_cachep;
@@ -416,7 +417,22 @@ static void romfs_destroy_inode(struct inode *inode)
 static int romfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 {
 	struct super_block *sb = dentry->d_sb;
-	u64 id = huge_encode_dev(sb->s_bdev->bd_dev);
+	u64 id = 0;
+
+	/* When calling huge_encode_dev(),
+	 * use sb->s_bdev->bd_dev when,
+	 *   - CONFIG_ROMFS_ON_BLOCK defined
+	 * use sb->s_dev when,
+	 *   - CONFIG_ROMFS_ON_BLOCK undefined and
+	 *   - CONFIG_ROMFS_ON_MTD defined
+	 * leave id as 0 when,
+	 *   - CONFIG_ROMFS_ON_BLOCK undefined and
+	 *   - CONFIG_ROMFS_ON_MTD undefined
+	 */
+	if (sb->s_bdev)
+		id = huge_encode_dev(sb->s_bdev->bd_dev);
+	else if (sb->s_dev)
+		id = huge_encode_dev(sb->s_dev);
 
 	buf->f_type = ROMFS_MAGIC;
 	buf->f_namelen = ROMFS_MAXFN;
@@ -489,6 +505,11 @@ static int romfs_fill_super(struct super_block *sb, void *data, int silent)
 	sb->s_flags |= MS_RDONLY | MS_NOATIME;
 	sb->s_op = &romfs_super_ops;
 
+#ifdef CONFIG_ROMFS_ON_MTD
+	/* Use same dev ID from the underlying mtdblock device */
+	if (sb->s_mtd)
+		sb->s_dev = MKDEV(MTD_BLOCK_MAJOR, sb->s_mtd->index);
+#endif
 	/* read the image superblock and check it */
 	rsb = kmalloc(512, GFP_KERNEL);
 	if (!rsb)

fs/userfaultfd.c

@@ -63,6 +63,7 @@ struct userfaultfd_wait_queue {
 	struct uffd_msg msg;
 	wait_queue_t wq;
 	struct userfaultfd_ctx *ctx;
+	bool waken;
 };
 
 struct userfaultfd_wake_range {
@@ -86,6 +87,12 @@ static int userfaultfd_wake_function(wait_queue_t *wq, unsigned mode,
 	if (len && (start > uwq->msg.arg.pagefault.address ||
 		    start + len <= uwq->msg.arg.pagefault.address))
 		goto out;
+	WRITE_ONCE(uwq->waken, true);
+	/*
+	 * The implicit smp_mb__before_spinlock in try_to_wake_up()
+	 * renders uwq->waken visible to other CPUs before the task is
+	 * waken.
+	 */
 	ret = wake_up_state(wq->private, mode);
 	if (ret)
 		/*
@@ -264,6 +271,7 @@ int handle_userfault(struct vm_fault *vmf, unsigned long reason)
 	struct userfaultfd_wait_queue uwq;
 	int ret;
 	bool must_wait, return_to_userland;
+	long blocking_state;
 
 	BUG_ON(!rwsem_is_locked(&mm->mmap_sem));
 
@@ -334,10 +342,13 @@ int handle_userfault(struct vm_fault *vmf, unsigned long reason)
 	uwq.wq.private = current;
 	uwq.msg = userfault_msg(vmf->address, vmf->flags, reason);
 	uwq.ctx = ctx;
+	uwq.waken = false;
 
 	return_to_userland =
 		(vmf->flags & (FAULT_FLAG_USER|FAULT_FLAG_KILLABLE)) ==
 		(FAULT_FLAG_USER|FAULT_FLAG_KILLABLE);
+	blocking_state = return_to_userland ? TASK_INTERRUPTIBLE :
+			 TASK_KILLABLE;
 
 	spin_lock(&ctx->fault_pending_wqh.lock);
 	/*
@@ -350,8 +361,7 @@ int handle_userfault(struct vm_fault *vmf, unsigned long reason)
 	 * following the spin_unlock to happen before the list_add in
 	 * __add_wait_queue.
 	 */
-	set_current_state(return_to_userland ? TASK_INTERRUPTIBLE :
-			  TASK_KILLABLE);
+	set_current_state(blocking_state);
 	spin_unlock(&ctx->fault_pending_wqh.lock);
 
 	must_wait = userfaultfd_must_wait(ctx, vmf->address, vmf->flags,
@@ -364,6 +374,29 @@ int handle_userfault(struct vm_fault *vmf, unsigned long reason)
 		wake_up_poll(&ctx->fd_wqh, POLLIN);
 		schedule();
 		ret |= VM_FAULT_MAJOR;
+
+		/*
+		 * False wakeups can orginate even from rwsem before
+		 * up_read() however userfaults will wait either for a
+		 * targeted wakeup on the specific uwq waitqueue from
+		 * wake_userfault() or for signals or for uffd
+		 * release.
+		 */
+		while (!READ_ONCE(uwq.waken)) {
+			/*
+			 * This needs the full smp_store_mb()
+			 * guarantee as the state write must be
+			 * visible to other CPUs before reading
+			 * uwq.waken from other CPUs.
+			 */
+			set_current_state(blocking_state);
+			if (READ_ONCE(uwq.waken) ||
+			    READ_ONCE(ctx->released) ||
+			    (return_to_userland ? signal_pending(current) :
+			     fatal_signal_pending(current)))
+				break;
+			schedule();
+		}
 	}
 
 	__set_current_state(TASK_RUNNING);

include/linux/memory_hotplug.h

@@ -284,7 +284,7 @@ extern void sparse_remove_one_section(struct zone *zone, struct mem_section *ms,
 		unsigned long map_offset);
 extern struct page *sparse_decode_mem_map(unsigned long coded_mem_map,
 					  unsigned long pnum);
-extern int zone_can_shift(unsigned long pfn, unsigned long nr_pages,
-			  enum zone_type target);
+extern bool zone_can_shift(unsigned long pfn, unsigned long nr_pages,
+			  enum zone_type target, int *zone_shift);
 
 #endif /* __LINUX_MEMORY_HOTPLUG_H */

include/linux/mmzone.h

@@ -972,12 +972,16 @@ static __always_inline struct zoneref *next_zones_zonelist(struct zoneref *z,
  * @zonelist - The zonelist to search for a suitable zone
  * @highest_zoneidx - The zone index of the highest zone to return
  * @nodes - An optional nodemask to filter the zonelist with
- * @zone - The first suitable zone found is returned via this parameter
+ * @return - Zoneref pointer for the first suitable zone found (see below)
  *
  * This function returns the first zone at or below a given zone index that is
  * within the allowed nodemask. The zoneref returned is a cursor that can be
  * used to iterate the zonelist with next_zones_zonelist by advancing it by
  * one before calling.
+ *
+ * When no eligible zone is found, zoneref->zone is NULL (zoneref itself is
+ * never NULL). This may happen either genuinely, or due to concurrent nodemask
+ * update due to cpuset modification.
  */
 static inline struct zoneref *first_zones_zonelist(struct zonelist *zonelist,
 					enum zone_type highest_zoneidx,

include/linux/nmi.h

@@ -110,6 +110,7 @@ extern int watchdog_user_enabled;
 extern int watchdog_thresh;
 extern unsigned long watchdog_enabled;
 extern unsigned long *watchdog_cpumask_bits;
+extern atomic_t watchdog_park_in_progress;
 #ifdef CONFIG_SMP
 extern int sysctl_softlockup_all_cpu_backtrace;
 extern int sysctl_hardlockup_all_cpu_backtrace;

kernel/panic.c

@@ -249,7 +249,7 @@ void panic(const char *fmt, ...)
 		 * Delay timeout seconds before rebooting the machine.
 		 * We can't use the "normal" timers since we just panicked.
 		 */
-		pr_emerg("Rebooting in %d seconds..", panic_timeout);
+		pr_emerg("Rebooting in %d seconds..\n", panic_timeout);
 
 		for (i = 0; i < panic_timeout * 1000; i += PANIC_TIMER_STEP) {
 			touch_nmi_watchdog();

kernel/watchdog.c

@@ -49,6 +49,8 @@ unsigned long *watchdog_cpumask_bits = cpumask_bits(&watchdog_cpumask);
 #define for_each_watchdog_cpu(cpu) \
 	for_each_cpu_and((cpu), cpu_online_mask, &watchdog_cpumask)
 
+atomic_t watchdog_park_in_progress = ATOMIC_INIT(0);
+
 /*
  * The 'watchdog_running' variable is set to 1 when the watchdog threads
  * are registered/started and is set to 0 when the watchdog threads are
@@ -260,6 +262,9 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
 	int duration;
 	int softlockup_all_cpu_backtrace = sysctl_softlockup_all_cpu_backtrace;
 
+	if (atomic_read(&watchdog_park_in_progress) != 0)
+		return HRTIMER_NORESTART;
+
 	/* kick the hardlockup detector */
 	watchdog_interrupt_count();
 
@@ -467,12 +472,16 @@ static int watchdog_park_threads(void)
 {
 	int cpu, ret = 0;
 
+	atomic_set(&watchdog_park_in_progress, 1);
+
 	for_each_watchdog_cpu(cpu) {
 		ret = kthread_park(per_cpu(softlockup_watchdog, cpu));
 		if (ret)
 			break;
 	}
 
+	atomic_set(&watchdog_park_in_progress, 0);
+
 	return ret;
 }
 

kernel/watchdog_hld.c

@@ -84,6 +84,9 @@ static void watchdog_overflow_callback(struct perf_event *event,
 	/* Ensure the watchdog never gets throttled */
 	event->hw.interrupts = 0;
 
+	if (atomic_read(&watchdog_park_in_progress) != 0)
+		return;
+
 	if (__this_cpu_read(watchdog_nmi_touch) == true) {
 		__this_cpu_write(watchdog_nmi_touch, false);
 		return;

lib/ioremap.c

@@ -144,4 +144,3 @@ int ioremap_page_range(unsigned long addr,
 
 	return err;
 }
-EXPORT_SYMBOL_GPL(ioremap_page_range);

lib/radix-tree.c

@@ -769,7 +769,7 @@ static void radix_tree_free_nodes(struct radix_tree_node *node)
 			struct radix_tree_node *old = child;
 			offset = child->offset + 1;
 			child = child->parent;
-			WARN_ON_ONCE(!list_empty(&node->private_list));
+			WARN_ON_ONCE(!list_empty(&old->private_list));
 			radix_tree_node_free(old);
 			if (old == entry_to_node(node))
 				return;

mm/huge_memory.c

@@ -783,6 +783,12 @@ struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr,
 
 	assert_spin_locked(pmd_lockptr(mm, pmd));
 
+	/*
+	 * When we COW a devmap PMD entry, we split it into PTEs, so we should
+	 * not be in this function with `flags & FOLL_COW` set.
+	 */
+	WARN_ONCE(flags & FOLL_COW, "mm: In follow_devmap_pmd with FOLL_COW set");
+
 	if (flags & FOLL_WRITE && !pmd_write(*pmd))
 		return NULL;
 
@@ -1128,6 +1134,16 @@ int do_huge_pmd_wp_page(struct vm_fault *vmf, pmd_t orig_pmd)
 	return ret;
 }
 
+/*
+ * FOLL_FORCE can write to even unwritable pmd's, but only
+ * after we've gone through a COW cycle and they are dirty.
+ */
+static inline bool can_follow_write_pmd(pmd_t pmd, unsigned int flags)
+{
+	return pmd_write(pmd) ||
+	       ((flags & FOLL_FORCE) && (flags & FOLL_COW) && pmd_dirty(pmd));
+}
+
 struct page *follow_trans_huge_pmd(struct vm_area_struct *vma,
 				   unsigned long addr,
 				   pmd_t *pmd,
@@ -1138,7 +1154,7 @@ struct page *follow_trans_huge_pmd(struct vm_area_struct *vma,
 
 	assert_spin_locked(pmd_lockptr(mm, pmd));
 
-	if (flags & FOLL_WRITE && !pmd_write(*pmd))
+	if (flags & FOLL_WRITE && !can_follow_write_pmd(*pmd, flags))
 		goto out;
 
 	/* Avoid dumping huge zero page */

mm/memcontrol.c

@@ -4353,9 +4353,9 @@ static int mem_cgroup_do_precharge(unsigned long count)
 		return ret;
 	}
 
-	/* Try charges one by one with reclaim */
+	/* Try charges one by one with reclaim, but do not retry */
 	while (count--) {
-		ret = try_charge(mc.to, GFP_KERNEL & ~__GFP_NORETRY, 1);
+		ret = try_charge(mc.to, GFP_KERNEL | __GFP_NORETRY, 1);
 		if (ret)
 			return ret;
 		mc.precharge++;

mm/memory_hotplug.c

@@ -1033,36 +1033,39 @@ static void node_states_set_node(int node, struct memory_notify *arg)
 	node_set_state(node, N_MEMORY);
 }
 
-int zone_can_shift(unsigned long pfn, unsigned long nr_pages,
-		   enum zone_type target)
+bool zone_can_shift(unsigned long pfn, unsigned long nr_pages,
+		   enum zone_type target, int *zone_shift)
 {
 	struct zone *zone = page_zone(pfn_to_page(pfn));
 	enum zone_type idx = zone_idx(zone);
 	int i;
 
+	*zone_shift = 0;
+
 	if (idx < target) {
 		/* pages must be at end of current zone */
 		if (pfn + nr_pages != zone_end_pfn(zone))
-			return 0;
+			return false;
 
 		/* no zones in use between current zone and target */
 		for (i = idx + 1; i < target; i++)
 			if (zone_is_initialized(zone - idx + i))
-				return 0;
+				return false;
 	}
 
 	if (target < idx) {
 		/* pages must be at beginning of current zone */
 		if (pfn != zone->zone_start_pfn)
-			return 0;
+			return false;
 
 		/* no zones in use between current zone and target */
 		for (i = target + 1; i < idx; i++)
 			if (zone_is_initialized(zone - idx + i))
-				return 0;
+				return false;
 	}
 
-	return target - idx;
+	*zone_shift = target - idx;
+	return true;
 }
 
 /* Must be protected by mem_hotplug_begin() */
@@ -1089,10 +1092,13 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, int online_typ
 	    !can_online_high_movable(zone))
 		return -EINVAL;
 
-	if (online_type == MMOP_ONLINE_KERNEL)
-		zone_shift = zone_can_shift(pfn, nr_pages, ZONE_NORMAL);
-	else if (online_type == MMOP_ONLINE_MOVABLE)
-		zone_shift = zone_can_shift(pfn, nr_pages, ZONE_MOVABLE);
+	if (online_type == MMOP_ONLINE_KERNEL) {
+		if (!zone_can_shift(pfn, nr_pages, ZONE_NORMAL, &zone_shift))
+			return -EINVAL;
+	} else if (online_type == MMOP_ONLINE_MOVABLE) {
+		if (!zone_can_shift(pfn, nr_pages, ZONE_MOVABLE, &zone_shift))
+			return -EINVAL;
+	}
 
 	zone = move_pfn_range(zone_shift, pfn, pfn + nr_pages);
 	if (!zone)

mm/mempolicy.c

@@ -2017,8 +2017,8 @@ alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma,
 
 	nmask = policy_nodemask(gfp, pol);
 	zl = policy_zonelist(gfp, pol, node);
-	mpol_cond_put(pol);
 	page = __alloc_pages_nodemask(gfp, order, zl, nmask);
+	mpol_cond_put(pol);
 out:
 	if (unlikely(!page && read_mems_allowed_retry(cpuset_mems_cookie)))
 		goto retry_cpuset;

mm/page_alloc.c

@@ -3523,12 +3523,13 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
 	struct page *page = NULL;
 	unsigned int alloc_flags;
 	unsigned long did_some_progress;
-	enum compact_priority compact_priority = DEF_COMPACT_PRIORITY;
+	enum compact_priority compact_priority;
 	enum compact_result compact_result;
-	int compaction_retries = 0;
-	int no_progress_loops = 0;
+	int compaction_retries;
+	int no_progress_loops;
 	unsigned long alloc_start = jiffies;
 	unsigned int stall_timeout = 10 * HZ;
+	unsigned int cpuset_mems_cookie;
 
 	/*
 	 * In the slowpath, we sanity check order to avoid ever trying to
@@ -3549,6 +3550,23 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
 				(__GFP_ATOMIC|__GFP_DIRECT_RECLAIM)))
 		gfp_mask &= ~__GFP_ATOMIC;
 
+retry_cpuset:
+	compaction_retries = 0;
+	no_progress_loops = 0;
+	compact_priority = DEF_COMPACT_PRIORITY;
+	cpuset_mems_cookie = read_mems_allowed_begin();
+	/*
+	 * We need to recalculate the starting point for the zonelist iterator
+	 * because we might have used different nodemask in the fast path, or
+	 * there was a cpuset modification and we are retrying - otherwise we
+	 * could end up iterating over non-eligible zones endlessly.
+	 */
+	ac->preferred_zoneref = first_zones_zonelist(ac->zonelist,
+					ac->high_zoneidx, ac->nodemask);
+	if (!ac->preferred_zoneref->zone)
+		goto nopage;
+
+
 	/*
 	 * The fast path uses conservative alloc_flags to succeed only until
 	 * kswapd needs to be woken up, and to avoid the cost of setting up
@@ -3708,6 +3726,13 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
 				&compaction_retries))
 		goto retry;
 
+	/*
+	 * It's possible we raced with cpuset update so the OOM would be
+	 * premature (see below the nopage: label for full explanation).
+	 */
+	if (read_mems_allowed_retry(cpuset_mems_cookie))
+		goto retry_cpuset;
+
 	/* Reclaim has failed us, start killing things */
 	page = __alloc_pages_may_oom(gfp_mask, order, ac, &did_some_progress);
 	if (page)
@@ -3720,6 +3745,16 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
 	}
 
 nopage:
+	/*
+	 * When updating a task's mems_allowed or mempolicy nodemask, it is
+	 * possible to race with parallel threads in such a way that our
+	 * allocation can fail while the mask is being updated. If we are about
+	 * to fail, check if the cpuset changed during allocation and if so,
+	 * retry.
+	 */
+	if (read_mems_allowed_retry(cpuset_mems_cookie))
+		goto retry_cpuset;
+
 	warn_alloc(gfp_mask,
 			"page allocation failure: order:%u", order);
 got_pg:
@@ -3734,7 +3769,6 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order,
 			struct zonelist *zonelist, nodemask_t *nodemask)
 {
 	struct page *page;
-	unsigned int cpuset_mems_cookie;
 	unsigned int alloc_flags = ALLOC_WMARK_LOW;
 	gfp_t alloc_mask = gfp_mask; /* The gfp_t that was actually used for allocation */
 	struct alloc_context ac = {
@@ -3771,9 +3805,6 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order,
 	if (IS_ENABLED(CONFIG_CMA) && ac.migratetype == MIGRATE_MOVABLE)
 		alloc_flags |= ALLOC_CMA;
 
-retry_cpuset:
-	cpuset_mems_cookie = read_mems_allowed_begin();
-
 	/* Dirty zone balancing only done in the fast path */
 	ac.spread_dirty_pages = (gfp_mask & __GFP_WRITE);
 
@@ -3784,8 +3815,13 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order,
 	 */
 	ac.preferred_zoneref = first_zones_zonelist(ac.zonelist,
 					ac.high_zoneidx, ac.nodemask);
-	if (!ac.preferred_zoneref) {
+	if (!ac.preferred_zoneref->zone) {
 		page = NULL;
+		/*
+		 * This might be due to race with cpuset_current_mems_allowed
+		 * update, so make sure we retry with original nodemask in the
+		 * slow path.
+		 */
 		goto no_zone;
 	}
 
@@ -3794,6 +3830,7 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order,
 	if (likely(page))
 		goto out;
 
+no_zone:
 	/*
 	 * Runtime PM, block IO and its error handling path can deadlock
 	 * because I/O on the device might not complete.
@@ -3805,21 +3842,10 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order,
 	 * Restore the original nodemask if it was potentially replaced with
 	 * &cpuset_current_mems_allowed to optimize the fast-path attempt.
 	 */
-	if (cpusets_enabled())
+	if (unlikely(ac.nodemask != nodemask))
 		ac.nodemask = nodemask;
-	page = __alloc_pages_slowpath(alloc_mask, order, &ac);
 
-no_zone:
-	/*
-	 * When updating a task's mems_allowed, it is possible to race with
-	 * parallel threads in such a way that an allocation can fail while
-	 * the mask is being updated. If a page allocation is about to fail,
-	 * check if the cpuset changed during allocation and if so, retry.
-	 */
-	if (unlikely(!page && read_mems_allowed_retry(cpuset_mems_cookie))) {
-		alloc_mask = gfp_mask;
-		goto retry_cpuset;
-	}
+	page = __alloc_pages_slowpath(alloc_mask, order, &ac);
 
 out:
 	if (memcg_kmem_enabled() && (gfp_mask & __GFP_ACCOUNT) && page &&
@@ -7248,6 +7274,7 @@ int alloc_contig_range(unsigned long start, unsigned long end,
 		.zone = page_zone(pfn_to_page(start)),
 		.mode = MIGRATE_SYNC,
 		.ignore_skip_hint = true,
+		.gfp_mask = GFP_KERNEL,
 	};
 	INIT_LIST_HEAD(&cc.migratepages);
 

mm/slub.c

@@ -496,10 +496,11 @@ static inline int check_valid_pointer(struct kmem_cache *s,
 	return 1;
 }
 
-static void print_section(char *text, u8 *addr, unsigned int length)
+static void print_section(char *level, char *text, u8 *addr,
+			  unsigned int length)
 {
 	metadata_access_enable();
-	print_hex_dump(KERN_ERR, text, DUMP_PREFIX_ADDRESS, 16, 1, addr,
+	print_hex_dump(level, text, DUMP_PREFIX_ADDRESS, 16, 1, addr,
 			length, 1);
 	metadata_access_disable();
 }
@@ -636,14 +637,15 @@ static void print_trailer(struct kmem_cache *s, struct page *page, u8 *p)
 	       p, p - addr, get_freepointer(s, p));
 
 	if (s->flags & SLAB_RED_ZONE)
-		print_section("Redzone ", p - s->red_left_pad, s->red_left_pad);
+		print_section(KERN_ERR, "Redzone ", p - s->red_left_pad,
+			      s->red_left_pad);
 	else if (p > addr + 16)
-		print_section("Bytes b4 ", p - 16, 16);
+		print_section(KERN_ERR, "Bytes b4 ", p - 16, 16);
 
-	print_section("Object ", p, min_t(unsigned long, s->object_size,
-				PAGE_SIZE));
+	print_section(KERN_ERR, "Object ", p,
+		      min_t(unsigned long, s->object_size, PAGE_SIZE));
 	if (s->flags & SLAB_RED_ZONE)
-		print_section("Redzone ", p + s->object_size,
+		print_section(KERN_ERR, "Redzone ", p + s->object_size,
 			s->inuse - s->object_size);
 
 	if (s->offset)
@@ -658,7 +660,8 @@ static void print_trailer(struct kmem_cache *s, struct page *page, u8 *p)
 
 	if (off != size_from_object(s))
 		/* Beginning of the filler is the free pointer */
-		print_section("Padding ", p + off, size_from_object(s) - off);
+		print_section(KERN_ERR, "Padding ", p + off,
+			      size_from_object(s) - off);
 
 	dump_stack();
 }
@@ -820,7 +823,7 @@ static int slab_pad_check(struct kmem_cache *s, struct page *page)
 		end--;
 
 	slab_err(s, page, "Padding overwritten. 0x%p-0x%p", fault, end - 1);
-	print_section("Padding ", end - remainder, remainder);
+	print_section(KERN_ERR, "Padding ", end - remainder, remainder);
 
 	restore_bytes(s, "slab padding", POISON_INUSE, end - remainder, end);
 	return 0;
@@ -973,7 +976,7 @@ static void trace(struct kmem_cache *s, struct page *page, void *object,
 			page->freelist);
 
 		if (!alloc)
-			print_section("Object ", (void *)object,
+			print_section(KERN_INFO, "Object ", (void *)object,
 					s->object_size);
 
 		dump_stack();