Merge branch 'master' of master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6

14 files changed, 205 insertions, 120 deletions

diff --git a/mm/Kconfig b/mm/Kconfig
index ee9f3e0..17b8947 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -253,7 +253,7 @@ config MEMORY_FAILURE
 
 config HWPOISON_INJECT
 	tristate "HWPoison pages injector"
-	depends on MEMORY_FAILURE && DEBUG_KERNEL
+	depends on MEMORY_FAILURE && DEBUG_KERNEL && PROC_FS
 	select PROC_PAGE_MONITOR
 
 config NOMMU_INITIAL_TRIM_EXCESS
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 65f38c2..e91b81b 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -402,7 +402,7 @@ static void clear_huge_page(struct page *page,
 {
 	int i;
 
-	if (unlikely(sz > MAX_ORDER_NR_PAGES)) {
+	if (unlikely(sz/PAGE_SIZE > MAX_ORDER_NR_PAGES)) {
 		clear_gigantic_page(page, addr, sz);
 		return;
 	}
diff --git a/mm/maccess.c b/mm/maccess.c
index 9073695..4e348db 100644
--- a/mm/maccess.c
+++ b/mm/maccess.c
@@ -14,7 +14,11 @@
  * Safely read from address @src to the buffer at @dst.  If a kernel fault
  * happens, handle that and return -EFAULT.
  */
-long probe_kernel_read(void *dst, void *src, size_t size)
+
+long __weak probe_kernel_read(void *dst, void *src, size_t size)
+    __attribute__((alias("__probe_kernel_read")));
+
+long __probe_kernel_read(void *dst, void *src, size_t size)
 {
 	long ret;
 	mm_segment_t old_fs = get_fs();
@@ -39,7 +43,10 @@ EXPORT_SYMBOL_GPL(probe_kernel_read);
  * Safely write to address @dst from the buffer at @src.  If a kernel fault
  * happens, handle that and return -EFAULT.
  */
-long notrace __weak probe_kernel_write(void *dst, void *src, size_t size)
+long __weak probe_kernel_write(void *dst, void *src, size_t size)
+    __attribute__((alias("__probe_kernel_write")));
+
+long __probe_kernel_write(void *dst, void *src, size_t size)
 {
 	long ret;
 	mm_segment_t old_fs = get_fs();
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 488b644..954032b 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -2586,7 +2586,7 @@ static int mem_cgroup_force_empty(struct mem_cgroup *mem, bool free_all)
 	if (free_all)
 		goto try_to_free;
 move_account:
-	while (mem->res.usage > 0) {
+	do {
 		ret = -EBUSY;
 		if (cgroup_task_count(cgrp) || !list_empty(&cgrp->children))
 			goto out;
@@ -2614,8 +2614,8 @@ move_account:
 		if (ret == -ENOMEM)
 			goto try_to_free;
 		cond_resched();
-	}
-	ret = 0;
+	/* "ret" should also be checked to ensure all lists are empty. */
+	} while (mem->res.usage > 0 || ret);
 out:
 	css_put(&mem->css);
 	return ret;
@@ -2648,10 +2648,7 @@ try_to_free:
 	}
 	lru_add_drain();
 	/* try move_account...there may be some *locked* pages. */
-	if (mem->res.usage)
-		goto move_account;
-	ret = 0;
-	goto out;
+	goto move_account;
 }
 
 int mem_cgroup_force_empty_write(struct cgroup *cont, unsigned int event)
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 6a0466e..17299fd 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -52,6 +52,8 @@ int sysctl_memory_failure_recovery __read_mostly = 1;
 
 atomic_long_t mce_bad_pages __read_mostly = ATOMIC_LONG_INIT(0);
 
+#if defined(CONFIG_HWPOISON_INJECT) || defined(CONFIG_HWPOISON_INJECT_MODULE)
+
 u32 hwpoison_filter_enable = 0;
 u32 hwpoison_filter_dev_major = ~0U;
 u32 hwpoison_filter_dev_minor = ~0U;
@@ -164,6 +166,13 @@ int hwpoison_filter(struct page *p)
 
 	return 0;
 }
+#else
+int hwpoison_filter(struct page *p)
+{
+	return 0;
+}
+#endif
+
 EXPORT_SYMBOL_GPL(hwpoison_filter);
 
 /*
diff --git a/mm/mmap.c b/mm/mmap.c
index d9c77b2..ee22989 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1043,6 +1043,46 @@ unsigned long do_mmap_pgoff(struct file *file, unsigned long addr,
 }
 EXPORT_SYMBOL(do_mmap_pgoff);
 
+SYSCALL_DEFINE6(mmap_pgoff, unsigned long, addr, unsigned long, len,
+		unsigned long, prot, unsigned long, flags,
+		unsigned long, fd, unsigned long, pgoff)
+{
+	struct file *file = NULL;
+	unsigned long retval = -EBADF;
+
+	if (!(flags & MAP_ANONYMOUS)) {
+		if (unlikely(flags & MAP_HUGETLB))
+			return -EINVAL;
+		file = fget(fd);
+		if (!file)
+			goto out;
+	} else if (flags & MAP_HUGETLB) {
+		struct user_struct *user = NULL;
+		/*
+		 * VM_NORESERVE is used because the reservations will be
+		 * taken when vm_ops->mmap() is called
+		 * A dummy user value is used because we are not locking
+		 * memory so no accounting is necessary
+		 */
+		len = ALIGN(len, huge_page_size(&default_hstate));
+		file = hugetlb_file_setup(HUGETLB_ANON_FILE, len, VM_NORESERVE,
+						&user, HUGETLB_ANONHUGE_INODE);
+		if (IS_ERR(file))
+			return PTR_ERR(file);
+	}
+
+	flags &= ~(MAP_EXECUTABLE | MAP_DENYWRITE);
+
+	down_write(&current->mm->mmap_sem);
+	retval = do_mmap_pgoff(file, addr, len, prot, flags, pgoff);
+	up_write(&current->mm->mmap_sem);
+
+	if (file)
+		fput(file);
+out:
+	return retval;
+}
+
 /*
  * Some shared mappigns will want the pages marked read-only
  * to track write events. If so, we'll downgrade vm_page_prot
diff --git a/mm/nommu.c b/mm/nommu.c
index 8687973..48a2ecf 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -432,6 +432,7 @@ SYSCALL_DEFINE1(brk, unsigned long, brk)
 	/*
 	 * Ok, looks good - let it rip.
 	 */
+	flush_icache_range(mm->brk, brk);
 	return mm->brk = brk;
 }
 
@@ -551,11 +552,11 @@ static void free_page_series(unsigned long from, unsigned long to)
 static void __put_nommu_region(struct vm_region *region)
 	__releases(nommu_region_sem)
 {
-	kenter("%p{%d}", region, atomic_read(&region->vm_usage));
+	kenter("%p{%d}", region, region->vm_usage);
 
 	BUG_ON(!nommu_region_tree.rb_node);
 
-	if (atomic_dec_and_test(&region->vm_usage)) {
+	if (--region->vm_usage == 0) {
 		if (region->vm_top > region->vm_start)
 			delete_nommu_region(region);
 		up_write(&nommu_region_sem);
@@ -1204,7 +1205,7 @@ unsigned long do_mmap_pgoff(struct file *file,
 	if (!vma)
 		goto error_getting_vma;
 
-	atomic_set(&region->vm_usage, 1);
+	region->vm_usage = 1;
 	region->vm_flags = vm_flags;
 	region->vm_pgoff = pgoff;
 
@@ -1271,7 +1272,7 @@ unsigned long do_mmap_pgoff(struct file *file,
 			}
 
 			/* we've found a region we can share */
-			atomic_inc(&pregion->vm_usage);
+			pregion->vm_usage++;
 			vma->vm_region = pregion;
 			start = pregion->vm_start;
 			start += (pgoff - pregion->vm_pgoff) << PAGE_SHIFT;
@@ -1288,7 +1289,7 @@ unsigned long do_mmap_pgoff(struct file *file,
 					vma->vm_region = NULL;
 					vma->vm_start = 0;
 					vma->vm_end = 0;
-					atomic_dec(&pregion->vm_usage);
+					pregion->vm_usage--;
 					pregion = NULL;
 					goto error_just_free;
 				}
@@ -1353,10 +1354,14 @@ unsigned long do_mmap_pgoff(struct file *file,
 share:
 	add_vma_to_mm(current->mm, vma);
 
-	up_write(&nommu_region_sem);
+	/* we flush the region from the icache only when the first executable
+	 * mapping of it is made  */
+	if (vma->vm_flags & VM_EXEC && !region->vm_icache_flushed) {
+		flush_icache_range(region->vm_start, region->vm_end);
+		region->vm_icache_flushed = true;
+	}
 
-	if (prot & PROT_EXEC)
-		flush_icache_range(result, result + len);
+	up_write(&nommu_region_sem);
 
 	kleave(" = %lx", result);
 	return result;
@@ -1398,6 +1403,31 @@ error_getting_region:
 }
 EXPORT_SYMBOL(do_mmap_pgoff);
 
+SYSCALL_DEFINE6(mmap_pgoff, unsigned long, addr, unsigned long, len,
+		unsigned long, prot, unsigned long, flags,
+		unsigned long, fd, unsigned long, pgoff)
+{
+	struct file *file = NULL;
+	unsigned long retval = -EBADF;
+
+	if (!(flags & MAP_ANONYMOUS)) {
+		file = fget(fd);
+		if (!file)
+			goto out;
+	}
+
+	flags &= ~(MAP_EXECUTABLE | MAP_DENYWRITE);
+
+	down_write(&current->mm->mmap_sem);
+	retval = do_mmap_pgoff(file, addr, len, prot, flags, pgoff);
+	up_write(&current->mm->mmap_sem);
+
+	if (file)
+		fput(file);
+out:
+	return retval;
+}
+
 /*
  * split a vma into two pieces at address 'addr', a new vma is allocated either
  * for the first part or the tail.
@@ -1411,10 +1441,9 @@ int split_vma(struct mm_struct *mm, struct vm_area_struct *vma,
 
 	kenter("");
 
-	/* we're only permitted to split anonymous regions that have a single
-	 * owner */
-	if (vma->vm_file ||
-	    atomic_read(&vma->vm_region->vm_usage) != 1)
+	/* we're only permitted to split anonymous regions (these should have
+	 * only a single usage on the region) */
+	if (vma->vm_file)
 		return -ENOMEM;
 
 	if (mm->map_count >= sysctl_max_map_count)
@@ -1488,7 +1517,7 @@ static int shrink_vma(struct mm_struct *mm,
 
 	/* cut the backing region down to size */
 	region = vma->vm_region;
-	BUG_ON(atomic_read(&region->vm_usage) != 1);
+	BUG_ON(region->vm_usage != 1);
 
 	down_write(&nommu_region_sem);
 	delete_nommu_region(region);
@@ -1732,27 +1761,6 @@ void unmap_mapping_range(struct address_space *mapping,
 EXPORT_SYMBOL(unmap_mapping_range);
 
 /*
- * ask for an unmapped area at which to create a mapping on a file
- */
-unsigned long get_unmapped_area(struct file *file, unsigned long addr,
-				unsigned long len, unsigned long pgoff,
-				unsigned long flags)
-{
-	unsigned long (*get_area)(struct file *, unsigned long, unsigned long,
-				  unsigned long, unsigned long);
-
-	get_area = current->mm->get_unmapped_area;
-	if (file && file->f_op && file->f_op->get_unmapped_area)
-		get_area = file->f_op->get_unmapped_area;
-
-	if (!get_area)
-		return -ENOSYS;
-
-	return get_area(file, addr, len, pgoff, flags);
-}
-EXPORT_SYMBOL(get_unmapped_area);
-
-/*
  * Check that a process has enough memory to allocate a new virtual
  * mapping. 0 means there is enough memory for the allocation to
  * succeed and -ENOMEM implies there is not.
@@ -1891,9 +1899,11 @@ int access_process_vm(struct task_struct *tsk, unsigned long addr, void *buf, in
 
 		/* only read or write mappings where it is permitted */
 		if (write && vma->vm_flags & VM_MAYWRITE)
-			len -= copy_to_user((void *) addr, buf, len);
+			copy_to_user_page(vma, NULL, addr,
+					 (void *) addr, buf, len);
 		else if (!write && vma->vm_flags & VM_MAYREAD)
-			len -= copy_from_user(buf, (void *) addr, len);
+			copy_from_user_page(vma, NULL, addr,
+					    buf, (void *) addr, len);
 		else
 			len = 0;
 	} else {
@@ -1904,3 +1914,65 @@ int access_process_vm(struct task_struct *tsk, unsigned long addr, void *buf, in
 	mmput(mm);
 	return len;
 }
+
+/**
+ * nommu_shrink_inode_mappings - Shrink the shared mappings on an inode
+ * @inode: The inode to check
+ * @size: The current filesize of the inode
+ * @newsize: The proposed filesize of the inode
+ *
+ * Check the shared mappings on an inode on behalf of a shrinking truncate to
+ * make sure that that any outstanding VMAs aren't broken and then shrink the
+ * vm_regions that extend that beyond so that do_mmap_pgoff() doesn't
+ * automatically grant mappings that are too large.
+ */
+int nommu_shrink_inode_mappings(struct inode *inode, size_t size,
+				size_t newsize)
+{
+	struct vm_area_struct *vma;
+	struct prio_tree_iter iter;
+	struct vm_region *region;
+	pgoff_t low, high;
+	size_t r_size, r_top;
+
+	low = newsize >> PAGE_SHIFT;
+	high = (size + PAGE_SIZE - 1) >> PAGE_SHIFT;
+
+	down_write(&nommu_region_sem);
+
+	/* search for VMAs that fall within the dead zone */
+	vma_prio_tree_foreach(vma, &iter, &inode->i_mapping->i_mmap,
+			      low, high) {
+		/* found one - only interested if it's shared out of the page
+		 * cache */
+		if (vma->vm_flags & VM_SHARED) {
+			up_write(&nommu_region_sem);
+			return -ETXTBSY; /* not quite true, but near enough */
+		}
+	}
+
+	/* reduce any regions that overlap the dead zone - if in existence,
+	 * these will be pointed to by VMAs that don't overlap the dead zone
+	 *
+	 * we don't check for any regions that start beyond the EOF as there
+	 * shouldn't be any
+	 */
+	vma_prio_tree_foreach(vma, &iter, &inode->i_mapping->i_mmap,
+			      0, ULONG_MAX) {
+		if (!(vma->vm_flags & VM_SHARED))
+			continue;
+
+		region = vma->vm_region;
+		r_size = region->vm_top - region->vm_start;
+		r_top = (region->vm_pgoff << PAGE_SHIFT) + r_size;
+
+		if (r_top > newsize) {
+			region->vm_top -= r_top - newsize;
+			if (region->vm_end > region->vm_top)
+				region->vm_end = region->vm_top;
+		}
+	}
+
+	up_write(&nommu_region_sem);
+	return 0;
+}
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index d79b925..d2a8889 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1222,10 +1222,10 @@ again:
 		}
 		spin_lock_irqsave(&zone->lock, flags);
 		page = __rmqueue(zone, order, migratetype);
-		__mod_zone_page_state(zone, NR_FREE_PAGES, -(1 << order));
 		spin_unlock(&zone->lock);
 		if (!page)
 			goto failed;
+		__mod_zone_page_state(zone, NR_FREE_PAGES, -(1 << order));
 	}
 
 	__count_zone_vm_events(PGALLOC, zone, 1 << order);
@@ -2402,13 +2402,14 @@ int numa_zonelist_order_handler(ctl_table *table, int write,
 {
 	char saved_string[NUMA_ZONELIST_ORDER_LEN];
 	int ret;
+	static DEFINE_MUTEX(zl_order_mutex);
 
+	mutex_lock(&zl_order_mutex);
 	if (write)
-		strncpy(saved_string, (char*)table->data,
-			NUMA_ZONELIST_ORDER_LEN);
+		strcpy(saved_string, (char*)table->data);
 	ret = proc_dostring(table, write, buffer, length, ppos);
 	if (ret)
-		return ret;
+		goto out;
 	if (write) {
 		int oldval = user_zonelist_order;
 		if (__parse_numa_zonelist_order((char*)table->data)) {
@@ -2421,7 +2422,9 @@ int numa_zonelist_order_handler(ctl_table *table, int write,
 		} else if (oldval != user_zonelist_order)
 			build_all_zonelists();
 	}
-	return 0;
+out:
+	mutex_unlock(&zl_order_mutex);
+	return ret;
 }
 
 
@@ -3995,7 +3998,7 @@ void __init add_active_range(unsigned int nid, unsigned long start_pfn,
 		}
 
 		/* Merge backward if suitable */
-		if (start_pfn < early_node_map[i].end_pfn &&
+		if (start_pfn < early_node_map[i].start_pfn &&
 				end_pfn >= early_node_map[i].start_pfn) {
 			early_node_map[i].start_pfn = start_pfn;
 			return;
diff --git a/mm/percpu.c b/mm/percpu.c
index 442010c..083e7c9 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -1271,7 +1271,7 @@ static void pcpu_reclaim(struct work_struct *work)
  */
 void free_percpu(void *ptr)
 {
-	void *addr = __pcpu_ptr_to_addr(ptr);
+	void *addr;
 	struct pcpu_chunk *chunk;
 	unsigned long flags;
 	int off;
@@ -1279,6 +1279,8 @@ void free_percpu(void *ptr)
 	if (!ptr)
 		return;
 
+	addr = __pcpu_ptr_to_addr(ptr);
+
 	spin_lock_irqsave(&pcpu_lock, flags);
 
 	chunk = pcpu_chunk_addr_search(addr);
diff --git a/mm/slab.c b/mm/slab.c
index 7d41f15..7451bda 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -654,7 +654,7 @@ static void init_node_lock_keys(int q)
 
 		l3 = s->cs_cachep->nodelists[q];
 		if (!l3 || OFF_SLAB(s->cs_cachep))
-			return;
+			continue;
 		lockdep_set_class(&l3->list_lock, &on_slab_l3_key);
 		alc = l3->alien;
 		/*
@@ -665,7 +665,7 @@ static void init_node_lock_keys(int q)
 		 * for alloc_alien_cache,
 		 */
 		if (!alc || (unsigned long)alc == BAD_ALIEN_MAGIC)
-			return;
+			continue;
 		for_each_node(r) {
 			if (alc[r])
 				lockdep_set_class(&alc[r]->lock,
diff --git a/mm/truncate.c b/mm/truncate.c
index 342deee..e87e372 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -522,22 +522,20 @@ EXPORT_SYMBOL_GPL(invalidate_inode_pages2);
  */
 void truncate_pagecache(struct inode *inode, loff_t old, loff_t new)
 {
-	if (new < old) {
-		struct address_space *mapping = inode->i_mapping;
-
-		/*
-		 * unmap_mapping_range is called twice, first simply for
-		 * efficiency so that truncate_inode_pages does fewer
-		 * single-page unmaps.  However after this first call, and
-		 * before truncate_inode_pages finishes, it is possible for
-		 * private pages to be COWed, which remain after
-		 * truncate_inode_pages finishes, hence the second
-		 * unmap_mapping_range call must be made for correctness.
-		 */
-		unmap_mapping_range(mapping, new + PAGE_SIZE - 1, 0, 1);
-		truncate_inode_pages(mapping, new);
-		unmap_mapping_range(mapping, new + PAGE_SIZE - 1, 0, 1);
-	}
+	struct address_space *mapping = inode->i_mapping;
+
+	/*
+	 * unmap_mapping_range is called twice, first simply for
+	 * efficiency so that truncate_inode_pages does fewer
+	 * single-page unmaps.  However after this first call, and
+	 * before truncate_inode_pages finishes, it is possible for
+	 * private pages to be COWed, which remain after
+	 * truncate_inode_pages finishes, hence the second
+	 * unmap_mapping_range call must be made for correctness.
+	 */
+	unmap_mapping_range(mapping, new + PAGE_SIZE - 1, 0, 1);
+	truncate_inode_pages(mapping, new);
+	unmap_mapping_range(mapping, new + PAGE_SIZE - 1, 0, 1);
 }
 EXPORT_SYMBOL(truncate_pagecache);
 
diff --git a/mm/util.c b/mm/util.c
index b377ce4..834db7b 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -4,10 +4,6 @@
 #include <linux/module.h>
 #include <linux/err.h>
 #include <linux/sched.h>
-#include <linux/hugetlb.h>
-#include <linux/syscalls.h>
-#include <linux/mman.h>
-#include <linux/file.h>
 #include <asm/uaccess.h>
 
 #define CREATE_TRACE_POINTS
@@ -224,7 +220,7 @@ char *strndup_user(const char __user *s, long n)
 }
 EXPORT_SYMBOL(strndup_user);
 
-#ifndef HAVE_ARCH_PICK_MMAP_LAYOUT
+#if defined(CONFIG_MMU) && !defined(HAVE_ARCH_PICK_MMAP_LAYOUT)
 void arch_pick_mmap_layout(struct mm_struct *mm)
 {
 	mm->mmap_base = TASK_UNMAPPED_BASE;
@@ -272,46 +268,6 @@ int __attribute__((weak)) get_user_pages_fast(unsigned long start,
 }
 EXPORT_SYMBOL_GPL(get_user_pages_fast);
 
-SYSCALL_DEFINE6(mmap_pgoff, unsigned long, addr, unsigned long, len,
-		unsigned long, prot, unsigned long, flags,
-		unsigned long, fd, unsigned long, pgoff)
-{
-	struct file * file = NULL;
-	unsigned long retval = -EBADF;
-
-	if (!(flags & MAP_ANONYMOUS)) {
-		if (unlikely(flags & MAP_HUGETLB))
-			return -EINVAL;
-		file = fget(fd);
-		if (!file)
-			goto out;
-	} else if (flags & MAP_HUGETLB) {
-		struct user_struct *user = NULL;
-		/*
-		 * VM_NORESERVE is used because the reservations will be
-		 * taken when vm_ops->mmap() is called
-		 * A dummy user value is used because we are not locking
-		 * memory so no accounting is necessary
-		 */
-		len = ALIGN(len, huge_page_size(&default_hstate));
-		file = hugetlb_file_setup(HUGETLB_ANON_FILE, len, VM_NORESERVE,
-						&user, HUGETLB_ANONHUGE_INODE);
-		if (IS_ERR(file))
-			return PTR_ERR(file);
-	}
-
-	flags &= ~(MAP_EXECUTABLE | MAP_DENYWRITE);
-
-	down_write(&current->mm->mmap_sem);
-	retval = do_mmap_pgoff(file, addr, len, prot, flags, pgoff);
-	up_write(&current->mm->mmap_sem);
-
-	if (file)
-		fput(file);
-out:
-	return retval;
-}
-
 /* Tracepoints definitions. */
 EXPORT_TRACEPOINT_SYMBOL(kmalloc);
 EXPORT_TRACEPOINT_SYMBOL(kmem_cache_alloc);
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 37e6929..d55d905 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -555,10 +555,8 @@ static void __purge_vmap_area_lazy(unsigned long *start, unsigned long *end,
 	}
 	rcu_read_unlock();
 
-	if (nr) {
-		BUG_ON(nr > atomic_read(&vmap_lazy_nr));
+	if (nr)
 		atomic_sub(nr, &vmap_lazy_nr);
-	}
 
 	if (nr || force_flush)
 		flush_tlb_kernel_range(*start, *end);
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 885207a..c26986c 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1922,6 +1922,9 @@ static int sleeping_prematurely(pg_data_t *pgdat, int order, long remaining)
 		if (!populated_zone(zone))
 			continue;
 
+		if (zone_is_all_unreclaimable(zone))
+			continue;
+
 		if (!zone_watermark_ok(zone, order, high_wmark_pages(zone),
 								0, 0))
 			return 1;