Merge branch 'WIP.x86/asm' into x86/urgent, because the topic is ready

Signed-off-by: Ingo Molnar <mingo@kernel.org>

26 files changed, 312 insertions, 235 deletions

diff --git a/mm/Kconfig b/mm/Kconfig
index c782e8fb7235..d5004d82a1d6 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -278,13 +278,6 @@ config BOUNCE
 	  by default when ZONE_DMA or HIGHMEM is selected, but you
 	  may say n to override this.
 
-# On the 'tile' arch, USB OHCI needs the bounce pool since tilegx will often
-# have more than 4GB of memory, but we don't currently use the IOTLB to present
-# a 32-bit address to OHCI.  So we need to use a bounce pool instead.
-config NEED_BOUNCE_POOL
-	bool
-	default y if TILE && USB_OHCI_HCD
-
 config NR_QUICK
 	int
 	depends on QUICKLIST
@@ -627,15 +620,14 @@ config GENERIC_EARLY_IOREMAP
 config MAX_STACK_SIZE_MB
 	int "Maximum user stack size for 32-bit processes (MB)"
 	default 80
-	range 8 256 if METAG
 	range 8 2048
 	depends on STACK_GROWSUP && (!64BIT || COMPAT)
 	help
 	  This is the maximum stack size in Megabytes in the VM layout of 32-bit
 	  user processes when the stack grows upwards (currently only on parisc
-	  and metag arch). The stack will be located at the highest memory
-	  address minus the given value, unless the RLIMIT_STACK hard limit is
-	  changed to a smaller value in which case that is used.
+	  arch). The stack will be located at the highest memory address minus
+	  the given value, unless the RLIMIT_STACK hard limit is changed to a
+	  smaller value in which case that is used.
 
 	  A sane initial value is 80 MB.
 
diff --git a/mm/fadvise.c b/mm/fadvise.c
index 767887f5f3bf..afa41491d324 100644
--- a/mm/fadvise.c
+++ b/mm/fadvise.c
@@ -26,7 +26,8 @@
  * POSIX_FADV_WILLNEED could set PG_Referenced, and POSIX_FADV_NOREUSE could
  * deactivate the pages and clear PG_Referenced.
  */
-SYSCALL_DEFINE4(fadvise64_64, int, fd, loff_t, offset, loff_t, len, int, advice)
+
+int ksys_fadvise64_64(int fd, loff_t offset, loff_t len, int advice)
 {
 	struct fd f = fdget(fd);
 	struct inode *inode;
@@ -185,11 +186,16 @@ out:
 	return ret;
 }
 
+SYSCALL_DEFINE4(fadvise64_64, int, fd, loff_t, offset, loff_t, len, int, advice)
+{
+	return ksys_fadvise64_64(fd, offset, len, advice);
+}
+
 #ifdef __ARCH_WANT_SYS_FADVISE64
 
 SYSCALL_DEFINE4(fadvise64, int, fd, loff_t, offset, size_t, len, int, advice)
 {
-	return sys_fadvise64_64(fd, offset, len, advice);
+	return ksys_fadvise64_64(fd, offset, len, advice);
 }
 
 #endif
diff --git a/mm/gup.c b/mm/gup.c
index 1b46e6e74881..6afae32571ca 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -516,7 +516,7 @@ static int faultin_page(struct task_struct *tsk, struct vm_area_struct *vma,
 	}
 
 	if (ret & VM_FAULT_RETRY) {
-		if (nonblocking)
+		if (nonblocking && !(fault_flags & FAULT_FLAG_RETRY_NOWAIT))
 			*nonblocking = 0;
 		return -EBUSY;
 	}
@@ -890,7 +890,10 @@ static __always_inline long __get_user_pages_locked(struct task_struct *tsk,
 				break;
 		}
 		if (*locked) {
-			/* VM_FAULT_RETRY didn't trigger */
+			/*
+			 * VM_FAULT_RETRY didn't trigger or it was a
+			 * FOLL_NOWAIT.
+			 */
 			if (!pages_done)
 				pages_done = ret;
 			break;
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 87ab9b8f56b5..5a68730eebd6 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -555,7 +555,8 @@ static int __do_huge_pmd_anonymous_page(struct vm_fault *vmf, struct page *page,
 
 	VM_BUG_ON_PAGE(!PageCompound(page), page);
 
-	if (mem_cgroup_try_charge(page, vma->vm_mm, gfp, &memcg, true)) {
+	if (mem_cgroup_try_charge(page, vma->vm_mm, gfp | __GFP_NORETRY, &memcg,
+				  true)) {
 		put_page(page);
 		count_vm_event(THP_FAULT_FALLBACK);
 		return VM_FAULT_FALLBACK;
@@ -1316,7 +1317,7 @@ alloc:
 	}
 
 	if (unlikely(mem_cgroup_try_charge(new_page, vma->vm_mm,
-					huge_gfp, &memcg, true))) {
+				huge_gfp | __GFP_NORETRY, &memcg, true))) {
 		put_page(new_page);
 		split_huge_pmd(vma, vmf->pmd, vmf->address);
 		if (page)
@@ -2783,11 +2784,13 @@ static unsigned long deferred_split_scan(struct shrinker *shrink,
 
 	list_for_each_safe(pos, next, &list) {
 		page = list_entry((void *)pos, struct page, mapping);
-		lock_page(page);
+		if (!trylock_page(page))
+			goto next;
 		/* split_huge_page() removes page from list on success */
 		if (!split_huge_page(page))
 			split++;
 		unlock_page(page);
+next:
 		put_page(page);
 	}
 
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 7c204e3d132b..976bbc5646fe 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -18,6 +18,7 @@
 #include <linux/bootmem.h>
 #include <linux/sysfs.h>
 #include <linux/slab.h>
+#include <linux/mmdebug.h>
 #include <linux/sched/signal.h>
 #include <linux/rmap.h>
 #include <linux/string_helpers.h>
@@ -1583,7 +1584,7 @@ static struct page *alloc_surplus_huge_page(struct hstate *h, gfp_t gfp_mask,
 		page = NULL;
 	} else {
 		h->surplus_huge_pages++;
-		h->nr_huge_pages_node[page_to_nid(page)]++;
+		h->surplus_huge_pages_node[page_to_nid(page)]++;
 	}
 
 out_unlock:
@@ -4374,6 +4375,12 @@ int hugetlb_reserve_pages(struct inode *inode,
 	struct resv_map *resv_map;
 	long gbl_reserve;
 
+	/* This should never happen */
+	if (from > to) {
+		VM_WARN(1, "%s called with a negative range\n", __func__);
+		return -EINVAL;
+	}
+
 	/*
 	 * Only apply hugepage reservation if asked. At fault time, an
 	 * attempt will be made for VM_NORESERVE to allocate a page
diff --git a/mm/kasan/kasan_init.c b/mm/kasan/kasan_init.c
index 554e4c0f23a2..f436246ccc79 100644
--- a/mm/kasan/kasan_init.c
+++ b/mm/kasan/kasan_init.c
@@ -31,7 +31,7 @@
 unsigned char kasan_zero_page[PAGE_SIZE] __page_aligned_bss;
 
 #if CONFIG_PGTABLE_LEVELS > 4
-p4d_t kasan_zero_p4d[PTRS_PER_P4D] __page_aligned_bss;
+p4d_t kasan_zero_p4d[MAX_PTRS_PER_P4D] __page_aligned_bss;
 #endif
 #if CONFIG_PGTABLE_LEVELS > 3
 pud_t kasan_zero_pud[PTRS_PER_PUD] __page_aligned_bss;
diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index b7e2268dfc9a..e42568284e06 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -530,7 +530,12 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma,
 			goto out;
 		}
 
-		VM_BUG_ON_PAGE(PageCompound(page), page);
+		/* TODO: teach khugepaged to collapse THP mapped with pte */
+		if (PageCompound(page)) {
+			result = SCAN_PAGE_COMPOUND;
+			goto out;
+		}
+
 		VM_BUG_ON_PAGE(!PageAnon(page), page);
 
 		/*
@@ -960,7 +965,9 @@ static void collapse_huge_page(struct mm_struct *mm,
 		goto out_nolock;
 	}
 
-	if (unlikely(mem_cgroup_try_charge(new_page, mm, gfp, &memcg, true))) {
+	/* Do not oom kill for khugepaged charges */
+	if (unlikely(mem_cgroup_try_charge(new_page, mm, gfp | __GFP_NORETRY,
+					   &memcg, true))) {
 		result = SCAN_CGROUP_CHARGE_FAIL;
 		goto out_nolock;
 	}
@@ -1319,7 +1326,9 @@ static void collapse_shmem(struct mm_struct *mm,
 		goto out;
 	}
 
-	if (unlikely(mem_cgroup_try_charge(new_page, mm, gfp, &memcg, true))) {
+	/* Do not oom kill for khugepaged charges */
+	if (unlikely(mem_cgroup_try_charge(new_page, mm, gfp | __GFP_NORETRY,
+					   &memcg, true))) {
 		result = SCAN_CGROUP_CHARGE_FAIL;
 		goto out;
 	}
diff --git a/mm/kmemleak.c b/mm/kmemleak.c
index e83987c55a08..46c2290a08f1 100644
--- a/mm/kmemleak.c
+++ b/mm/kmemleak.c
@@ -1657,8 +1657,7 @@ static void start_scan_thread(void)
 }
 
 /*
- * Stop the automatic memory scanning thread. This function must be called
- * with the scan_mutex held.
+ * Stop the automatic memory scanning thread.
  */
 static void stop_scan_thread(void)
 {
@@ -1921,12 +1920,15 @@ static void kmemleak_do_cleanup(struct work_struct *work)
 {
 	stop_scan_thread();
 
+	mutex_lock(&scan_mutex);
 	/*
-	 * Once the scan thread has stopped, it is safe to no longer track
-	 * object freeing. Ordering of the scan thread stopping and the memory
-	 * accesses below is guaranteed by the kthread_stop() function.
+	 * Once it is made sure that kmemleak_scan has stopped, it is safe to no
+	 * longer track object freeing. Ordering of the scan thread stopping and
+	 * the memory accesses below is guaranteed by the kthread_stop()
+	 * function.
 	 */
 	kmemleak_free_enabled = 0;
+	mutex_unlock(&scan_mutex);
 
 	if (!kmemleak_found_leaks)
 		__kmemleak_do_cleanup();
diff --git a/mm/memblock.c b/mm/memblock.c
index 5a9ca2a1751b..48376bd33274 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -1101,34 +1101,6 @@ void __init_memblock __next_mem_pfn_range(int *idx, int nid,
 		*out_nid = r->nid;
 }
 
-unsigned long __init_memblock memblock_next_valid_pfn(unsigned long pfn,
-						      unsigned long max_pfn)
-{
-	struct memblock_type *type = &memblock.memory;
-	unsigned int right = type->cnt;
-	unsigned int mid, left = 0;
-	phys_addr_t addr = PFN_PHYS(pfn + 1);
-
-	do {
-		mid = (right + left) / 2;
-
-		if (addr < type->regions[mid].base)
-			right = mid;
-		else if (addr >= (type->regions[mid].base +
-				  type->regions[mid].size))
-			left = mid + 1;
-		else {
-			/* addr is within the region, so pfn + 1 is valid */
-			return min(pfn + 1, max_pfn);
-		}
-	} while (left < right);
-
-	if (right == type->cnt)
-		return max_pfn;
-	else
-		return min(PHYS_PFN(type->regions[right].base), max_pfn);
-}
-
 /**
  * memblock_set_node - set node ID on memblock regions
  * @base: base of area to set node ID for
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 670e99b68aa6..9ec024b862ac 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -714,9 +714,9 @@ static struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm)
  * invocations for reference counting, or use mem_cgroup_iter_break()
  * to cancel a hierarchy walk before the round-trip is complete.
  *
- * Reclaimers can specify a zone and a priority level in @reclaim to
+ * Reclaimers can specify a node and a priority level in @reclaim to
  * divide up the memcgs in the hierarchy among all concurrent
- * reclaimers operating on the same zone and priority.
+ * reclaimers operating on the same node and priority.
  */
 struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root,
 				   struct mem_cgroup *prev,
@@ -2299,7 +2299,7 @@ void memcg_kmem_put_cache(struct kmem_cache *cachep)
 }
 
 /**
- * memcg_kmem_charge: charge a kmem page
+ * memcg_kmem_charge_memcg: charge a kmem page
  * @page: page to charge
  * @gfp: reclaim mode
  * @order: allocation order
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index d879f1d8a44a..01cbb7078d6c 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -1336,9 +1336,9 @@ static int copy_nodes_to_user(unsigned long __user *mask, unsigned long maxnode,
 	return copy_to_user(mask, nodes_addr(*nodes), copy) ? -EFAULT : 0;
 }
 
-SYSCALL_DEFINE6(mbind, unsigned long, start, unsigned long, len,
-		unsigned long, mode, const unsigned long __user *, nmask,
-		unsigned long, maxnode, unsigned, flags)
+static long kernel_mbind(unsigned long start, unsigned long len,
+			 unsigned long mode, const unsigned long __user *nmask,
+			 unsigned long maxnode, unsigned int flags)
 {
 	nodemask_t nodes;
 	int err;
@@ -1357,9 +1357,16 @@ SYSCALL_DEFINE6(mbind, unsigned long, start, unsigned long, len,
 	return do_mbind(start, len, mode, mode_flags, &nodes, flags);
 }
 
+SYSCALL_DEFINE6(mbind, unsigned long, start, unsigned long, len,
+		unsigned long, mode, const unsigned long __user *, nmask,
+		unsigned long, maxnode, unsigned int, flags)
+{
+	return kernel_mbind(start, len, mode, nmask, maxnode, flags);
+}
+
 /* Set the process memory policy */
-SYSCALL_DEFINE3(set_mempolicy, int, mode, const unsigned long __user *, nmask,
-		unsigned long, maxnode)
+static long kernel_set_mempolicy(int mode, const unsigned long __user *nmask,
+				 unsigned long maxnode)
 {
 	int err;
 	nodemask_t nodes;
@@ -1377,9 +1384,15 @@ SYSCALL_DEFINE3(set_mempolicy, int, mode, const unsigned long __user *, nmask,
 	return do_set_mempolicy(mode, flags, &nodes);
 }
 
-SYSCALL_DEFINE4(migrate_pages, pid_t, pid, unsigned long, maxnode,
-		const unsigned long __user *, old_nodes,
-		const unsigned long __user *, new_nodes)
+SYSCALL_DEFINE3(set_mempolicy, int, mode, const unsigned long __user *, nmask,
+		unsigned long, maxnode)
+{
+	return kernel_set_mempolicy(mode, nmask, maxnode);
+}
+
+static int kernel_migrate_pages(pid_t pid, unsigned long maxnode,
+				const unsigned long __user *old_nodes,
+				const unsigned long __user *new_nodes)
 {
 	struct mm_struct *mm = NULL;
 	struct task_struct *task;
@@ -1469,11 +1482,20 @@ out_put:
 
 }
 
+SYSCALL_DEFINE4(migrate_pages, pid_t, pid, unsigned long, maxnode,
+		const unsigned long __user *, old_nodes,
+		const unsigned long __user *, new_nodes)
+{
+	return kernel_migrate_pages(pid, maxnode, old_nodes, new_nodes);
+}
+
 
 /* Retrieve NUMA policy */
-SYSCALL_DEFINE5(get_mempolicy, int __user *, policy,
-		unsigned long __user *, nmask, unsigned long, maxnode,
-		unsigned long, addr, unsigned long, flags)
+static int kernel_get_mempolicy(int __user *policy,
+				unsigned long __user *nmask,
+				unsigned long maxnode,
+				unsigned long addr,
+				unsigned long flags)
 {
 	int err;
 	int uninitialized_var(pval);
@@ -1496,6 +1518,13 @@ SYSCALL_DEFINE5(get_mempolicy, int __user *, policy,
 	return err;
 }
 
+SYSCALL_DEFINE5(get_mempolicy, int __user *, policy,
+		unsigned long __user *, nmask, unsigned long, maxnode,
+		unsigned long, addr, unsigned long, flags)
+{
+	return kernel_get_mempolicy(policy, nmask, maxnode, addr, flags);
+}
+
 #ifdef CONFIG_COMPAT
 
 COMPAT_SYSCALL_DEFINE5(get_mempolicy, int __user *, policy,
@@ -1514,7 +1543,7 @@ COMPAT_SYSCALL_DEFINE5(get_mempolicy, int __user *, policy,
 	if (nmask)
 		nm = compat_alloc_user_space(alloc_size);
 
-	err = sys_get_mempolicy(policy, nm, nr_bits+1, addr, flags);
+	err = kernel_get_mempolicy(policy, nm, nr_bits+1, addr, flags);
 
 	if (!err && nmask) {
 		unsigned long copy_size;
@@ -1546,7 +1575,7 @@ COMPAT_SYSCALL_DEFINE3(set_mempolicy, int, mode, compat_ulong_t __user *, nmask,
 			return -EFAULT;
 	}
 
-	return sys_set_mempolicy(mode, nm, nr_bits+1);
+	return kernel_set_mempolicy(mode, nm, nr_bits+1);
 }
 
 COMPAT_SYSCALL_DEFINE6(mbind, compat_ulong_t, start, compat_ulong_t, len,
@@ -1568,10 +1597,43 @@ COMPAT_SYSCALL_DEFINE6(mbind, compat_ulong_t, start, compat_ulong_t, len,
 			return -EFAULT;
 	}
 
-	return sys_mbind(start, len, mode, nm, nr_bits+1, flags);
+	return kernel_mbind(start, len, mode, nm, nr_bits+1, flags);
 }
 
-#endif
+COMPAT_SYSCALL_DEFINE4(migrate_pages, compat_pid_t, pid,
+		       compat_ulong_t, maxnode,
+		       const compat_ulong_t __user *, old_nodes,
+		       const compat_ulong_t __user *, new_nodes)
+{
+	unsigned long __user *old = NULL;
+	unsigned long __user *new = NULL;
+	nodemask_t tmp_mask;
+	unsigned long nr_bits;
+	unsigned long size;
+
+	nr_bits = min_t(unsigned long, maxnode - 1, MAX_NUMNODES);
+	size = ALIGN(nr_bits, BITS_PER_LONG) / 8;
+	if (old_nodes) {
+		if (compat_get_bitmap(nodes_addr(tmp_mask), old_nodes, nr_bits))
+			return -EFAULT;
+		old = compat_alloc_user_space(new_nodes ? size * 2 : size);
+		if (new_nodes)
+			new = old + size / sizeof(unsigned long);
+		if (copy_to_user(old, nodes_addr(tmp_mask), size))
+			return -EFAULT;
+	}
+	if (new_nodes) {
+		if (compat_get_bitmap(nodes_addr(tmp_mask), new_nodes, nr_bits))
+			return -EFAULT;
+		if (new == NULL)
+			new = compat_alloc_user_space(size);
+		if (copy_to_user(new, nodes_addr(tmp_mask), size))
+			return -EFAULT;
+	}
+	return kernel_migrate_pages(pid, nr_bits + 1, old, new);
+}
+
+#endif /* CONFIG_COMPAT */
 
 struct mempolicy *__get_vma_policy(struct vm_area_struct *vma,
 						unsigned long addr)
@@ -2124,6 +2186,9 @@ bool __mpol_equal(struct mempolicy *a, struct mempolicy *b)
 	case MPOL_INTERLEAVE:
 		return !!nodes_equal(a->v.nodes, b->v.nodes);
 	case MPOL_PREFERRED:
+		/* a's ->flags is the same as b's */
+		if (a->flags & MPOL_F_LOCAL)
+			return true;
 		return a->v.preferred_node == b->v.preferred_node;
 	default:
 		BUG();
diff --git a/mm/migrate.c b/mm/migrate.c
index 1e5525a25691..003886606a22 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -34,6 +34,7 @@
 #include <linux/backing-dev.h>
 #include <linux/compaction.h>
 #include <linux/syscalls.h>
+#include <linux/compat.h>
 #include <linux/hugetlb.h>
 #include <linux/hugetlb_cgroup.h>
 #include <linux/gfp.h>
@@ -1745,10 +1746,10 @@ static int do_pages_stat(struct mm_struct *mm, unsigned long nr_pages,
  * Move a list of pages in the address space of the currently executing
  * process.
  */
-SYSCALL_DEFINE6(move_pages, pid_t, pid, unsigned long, nr_pages,
-		const void __user * __user *, pages,
-		const int __user *, nodes,
-		int __user *, status, int, flags)
+static int kernel_move_pages(pid_t pid, unsigned long nr_pages,
+			     const void __user * __user *pages,
+			     const int __user *nodes,
+			     int __user *status, int flags)
 {
 	struct task_struct *task;
 	struct mm_struct *mm;
@@ -1807,6 +1808,36 @@ out:
 	return err;
 }
 
+SYSCALL_DEFINE6(move_pages, pid_t, pid, unsigned long, nr_pages,
+		const void __user * __user *, pages,
+		const int __user *, nodes,
+		int __user *, status, int, flags)
+{
+	return kernel_move_pages(pid, nr_pages, pages, nodes, status, flags);
+}
+
+#ifdef CONFIG_COMPAT
+COMPAT_SYSCALL_DEFINE6(move_pages, pid_t, pid, compat_ulong_t, nr_pages,
+		       compat_uptr_t __user *, pages32,
+		       const int __user *, nodes,
+		       int __user *, status,
+		       int, flags)
+{
+	const void __user * __user *pages;
+	int i;
+
+	pages = compat_alloc_user_space(nr_pages * sizeof(void *));
+	for (i = 0; i < nr_pages; i++) {
+		compat_uptr_t p;
+
+		if (get_user(p, pages32 + i) ||
+			put_user(compat_ptr(p), pages + i))
+			return -EFAULT;
+	}
+	return kernel_move_pages(pid, nr_pages, pages, nodes, status, flags);
+}
+#endif /* CONFIG_COMPAT */
+
 #ifdef CONFIG_NUMA_BALANCING
 /*
  * Returns true if this is a safe migration target node for misplaced NUMA
diff --git a/mm/mmap.c b/mm/mmap.c
index 9efdc021ad22..aa0dc8231c0d 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1488,9 +1488,9 @@ unsigned long do_mmap(struct file *file, unsigned long addr,
 	return addr;
 }
 
-SYSCALL_DEFINE6(mmap_pgoff, unsigned long, addr, unsigned long, len,
-		unsigned long, prot, unsigned long, flags,
-		unsigned long, fd, unsigned long, pgoff)
+unsigned long ksys_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;
@@ -1537,6 +1537,13 @@ out_fput:
 	return retval;
 }
 
+SYSCALL_DEFINE6(mmap_pgoff, unsigned long, addr, unsigned long, len,
+		unsigned long, prot, unsigned long, flags,
+		unsigned long, fd, unsigned long, pgoff)
+{
+	return ksys_mmap_pgoff(addr, len, prot, flags, fd, pgoff);
+}
+
 #ifdef __ARCH_WANT_SYS_OLD_MMAP
 struct mmap_arg_struct {
 	unsigned long addr;
@@ -1556,8 +1563,8 @@ SYSCALL_DEFINE1(old_mmap, struct mmap_arg_struct __user *, arg)
 	if (offset_in_page(a.offset))
 		return -EINVAL;
 
-	return sys_mmap_pgoff(a.addr, a.len, a.prot, a.flags, a.fd,
-			      a.offset >> PAGE_SHIFT);
+	return ksys_mmap_pgoff(a.addr, a.len, a.prot, a.flags, a.fd,
+			       a.offset >> PAGE_SHIFT);
 }
 #endif /* __ARCH_WANT_SYS_OLD_MMAP */
 
diff --git a/mm/nommu.c b/mm/nommu.c
index ebb6e618dade..4f8720243ae7 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -663,22 +663,6 @@ static void put_nommu_region(struct vm_region *region)
 }
 
 /*
- * update protection on a vma
- */
-static void protect_vma(struct vm_area_struct *vma, unsigned long flags)
-{
-#ifdef CONFIG_MPU
-	struct mm_struct *mm = vma->vm_mm;
-	long start = vma->vm_start & PAGE_MASK;
-	while (start < vma->vm_end) {
-		protect_page(mm, start, flags);
-		start += PAGE_SIZE;
-	}
-	update_protections(mm);
-#endif
-}
-
-/*
  * add a VMA into a process's mm_struct in the appropriate place in the list
  * and tree and add to the address space's page tree also if not an anonymous
  * page
@@ -695,8 +679,6 @@ static void add_vma_to_mm(struct mm_struct *mm, struct vm_area_struct *vma)
 	mm->map_count++;
 	vma->vm_mm = mm;
 
-	protect_vma(vma, vma->vm_flags);
-
 	/* add the VMA to the mapping */
 	if (vma->vm_file) {
 		mapping = vma->vm_file->f_mapping;
@@ -757,8 +739,6 @@ static void delete_vma_from_mm(struct vm_area_struct *vma)
 	struct mm_struct *mm = vma->vm_mm;
 	struct task_struct *curr = current;
 
-	protect_vma(vma, 0);
-
 	mm->map_count--;
 	for (i = 0; i < VMACACHE_SIZE; i++) {
 		/* if the vma is cached, invalidate the entire cache */
@@ -1423,9 +1403,9 @@ error_getting_region:
 	return -ENOMEM;
 }
 
-SYSCALL_DEFINE6(mmap_pgoff, unsigned long, addr, unsigned long, len,
-		unsigned long, prot, unsigned long, flags,
-		unsigned long, fd, unsigned long, pgoff)
+unsigned long ksys_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;
@@ -1447,6 +1427,13 @@ out:
 	return retval;
 }
 
+SYSCALL_DEFINE6(mmap_pgoff, unsigned long, addr, unsigned long, len,
+		unsigned long, prot, unsigned long, flags,
+		unsigned long, fd, unsigned long, pgoff)
+{
+	return ksys_mmap_pgoff(addr, len, prot, flags, fd, pgoff);
+}
+
 #ifdef __ARCH_WANT_SYS_OLD_MMAP
 struct mmap_arg_struct {
 	unsigned long addr;
@@ -1466,8 +1453,8 @@ SYSCALL_DEFINE1(old_mmap, struct mmap_arg_struct __user *, arg)
 	if (offset_in_page(a.offset))
 		return -EINVAL;
 
-	return sys_mmap_pgoff(a.addr, a.len, a.prot, a.flags, a.fd,
-			      a.offset >> PAGE_SHIFT);
+	return ksys_mmap_pgoff(a.addr, a.len, a.prot, a.flags, a.fd,
+			       a.offset >> PAGE_SHIFT);
 }
 #endif /* __ARCH_WANT_SYS_OLD_MMAP */
 
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index cb416723538f..4ea018263210 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1910,7 +1910,9 @@ static int move_freepages(struct zone *zone,
 	 * Remove at a later date when no bug reports exist related to
 	 * grouping pages by mobility
 	 */
-	VM_BUG_ON(page_zone(start_page) != page_zone(end_page));
+	VM_BUG_ON(pfn_valid(page_to_pfn(start_page)) &&
+	          pfn_valid(page_to_pfn(end_page)) &&
+	          page_zone(start_page) != page_zone(end_page));
 #endif
 
 	if (num_movable)
@@ -3594,7 +3596,7 @@ static bool __need_fs_reclaim(gfp_t gfp_mask)
 		return false;
 
 	/* this guy won't enter reclaim */
-	if ((current->flags & PF_MEMALLOC) && !(gfp_mask & __GFP_NOMEMALLOC))
+	if (current->flags & PF_MEMALLOC)
 		return false;
 
 	/* We're only interested __GFP_FS allocations for now */
@@ -5354,17 +5356,8 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone,
 		if (context != MEMMAP_EARLY)
 			goto not_early;
 
-		if (!early_pfn_valid(pfn)) {
-#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
-			/*
-			 * Skip to the pfn preceding the next valid one (or
-			 * end_pfn), such that we hit a valid pfn (or end_pfn)
-			 * on our next iteration of the loop.
-			 */
-			pfn = memblock_next_valid_pfn(pfn, end_pfn) - 1;
-#endif
+		if (!early_pfn_valid(pfn))
 			continue;
-		}
 		if (!early_pfn_in_nid(pfn, nid))
 			continue;
 		if (!update_defer_init(pgdat, pfn, end_pfn, &nr_initialised))
@@ -6199,10 +6192,7 @@ static void __ref alloc_node_mem_map(struct pglist_data *pgdat)
 		end = pgdat_end_pfn(pgdat);
 		end = ALIGN(end, MAX_ORDER_NR_PAGES);
 		size =  (end - start) * sizeof(struct page);
-		map = alloc_remap(pgdat->node_id, size);
-		if (!map)
-			map = memblock_virt_alloc_node_nopanic(size,
-							       pgdat->node_id);
+		map = memblock_virt_alloc_node_nopanic(size, pgdat->node_id);
 		pgdat->node_mem_map = map + offset;
 	}
 	pr_debug("%s: node %d, pgdat %08lx, node_mem_map %08lx\n",
diff --git a/mm/page_owner.c b/mm/page_owner.c
index 9886c6073828..7172e0a80e13 100644
--- a/mm/page_owner.c
+++ b/mm/page_owner.c
@@ -123,13 +123,13 @@ void __reset_page_owner(struct page *page, unsigned int order)
 static inline bool check_recursive_alloc(struct stack_trace *trace,
 					unsigned long ip)
 {
-	int i, count;
+	int i;
 
 	if (!trace->nr_entries)
 		return false;
 
-	for (i = 0, count = 0; i < trace->nr_entries; i++) {
-		if (trace->entries[i] == ip && ++count == 2)
+	for (i = 0; i < trace->nr_entries; i++) {
+		if (trace->entries[i] == ip)
 			return true;
 	}
 
diff --git a/mm/percpu-km.c b/mm/percpu-km.c
index d2a76642c4ae..38de70ab1a0d 100644
--- a/mm/percpu-km.c
+++ b/mm/percpu-km.c
@@ -34,7 +34,7 @@
 #include <linux/log2.h>
 
 static int pcpu_populate_chunk(struct pcpu_chunk *chunk,
-			       int page_start, int page_end)
+			       int page_start, int page_end, gfp_t gfp)
 {
 	return 0;
 }
@@ -45,18 +45,18 @@ static void pcpu_depopulate_chunk(struct pcpu_chunk *chunk,
 	/* nada */
 }
 
-static struct pcpu_chunk *pcpu_create_chunk(void)
+static struct pcpu_chunk *pcpu_create_chunk(gfp_t gfp)
 {
 	const int nr_pages = pcpu_group_sizes[0] >> PAGE_SHIFT;
 	struct pcpu_chunk *chunk;
 	struct page *pages;
 	int i;
 
-	chunk = pcpu_alloc_chunk();
+	chunk = pcpu_alloc_chunk(gfp);
 	if (!chunk)
 		return NULL;
 
-	pages = alloc_pages(GFP_KERNEL, order_base_2(nr_pages));
+	pages = alloc_pages(gfp, order_base_2(nr_pages));
 	if (!pages) {
 		pcpu_free_chunk(chunk);
 		return NULL;
diff --git a/mm/percpu-vm.c b/mm/percpu-vm.c
index 9158e5a81391..d8078de912de 100644
--- a/mm/percpu-vm.c
+++ b/mm/percpu-vm.c
@@ -37,7 +37,7 @@ static struct page **pcpu_get_pages(void)
 	lockdep_assert_held(&pcpu_alloc_mutex);
 
 	if (!pages)
-		pages = pcpu_mem_zalloc(pages_size);
+		pages = pcpu_mem_zalloc(pages_size, GFP_KERNEL);
 	return pages;
 }
 
@@ -73,18 +73,21 @@ static void pcpu_free_pages(struct pcpu_chunk *chunk,
  * @pages: array to put the allocated pages into, indexed by pcpu_page_idx()
  * @page_start: page index of the first page to be allocated
  * @page_end: page index of the last page to be allocated + 1
+ * @gfp: allocation flags passed to the underlying allocator
  *
  * Allocate pages [@page_start,@page_end) into @pages for all units.
  * The allocation is for @chunk.  Percpu core doesn't care about the
  * content of @pages and will pass it verbatim to pcpu_map_pages().
  */
 static int pcpu_alloc_pages(struct pcpu_chunk *chunk,
-			    struct page **pages, int page_start, int page_end)
+			    struct page **pages, int page_start, int page_end,
+			    gfp_t gfp)
 {
-	const gfp_t gfp = GFP_KERNEL | __GFP_HIGHMEM;
 	unsigned int cpu, tcpu;
 	int i;
 
+	gfp |= __GFP_HIGHMEM;
+
 	for_each_possible_cpu(cpu) {
 		for (i = page_start; i < page_end; i++) {
 			struct page **pagep = &pages[pcpu_page_idx(cpu, i)];
@@ -262,6 +265,7 @@ static void pcpu_post_map_flush(struct pcpu_chunk *chunk,
  * @chunk: chunk of interest
  * @page_start: the start page
  * @page_end: the end page
+ * @gfp: allocation flags passed to the underlying memory allocator
  *
  * For each cpu, populate and map pages [@page_start,@page_end) into
  * @chunk.
@@ -270,7 +274,7 @@ static void pcpu_post_map_flush(struct pcpu_chunk *chunk,
  * pcpu_alloc_mutex, does GFP_KERNEL allocation.
  */
 static int pcpu_populate_chunk(struct pcpu_chunk *chunk,
-			       int page_start, int page_end)
+			       int page_start, int page_end, gfp_t gfp)
 {
 	struct page **pages;
 
@@ -278,7 +282,7 @@ static int pcpu_populate_chunk(struct pcpu_chunk *chunk,
 	if (!pages)
 		return -ENOMEM;
 
-	if (pcpu_alloc_pages(chunk, pages, page_start, page_end))
+	if (pcpu_alloc_pages(chunk, pages, page_start, page_end, gfp))
 		return -ENOMEM;
 
 	if (pcpu_map_pages(chunk, pages, page_start, page_end)) {
@@ -325,12 +329,12 @@ static void pcpu_depopulate_chunk(struct pcpu_chunk *chunk,
 	pcpu_free_pages(chunk, pages, page_start, page_end);
 }
 
-static struct pcpu_chunk *pcpu_create_chunk(void)
+static struct pcpu_chunk *pcpu_create_chunk(gfp_t gfp)
 {
 	struct pcpu_chunk *chunk;
 	struct vm_struct **vms;
 
-	chunk = pcpu_alloc_chunk();
+	chunk = pcpu_alloc_chunk(gfp);
 	if (!chunk)
 		return NULL;
 
diff --git a/mm/percpu.c b/mm/percpu.c
index 50e7fdf84055..0b6480979ac7 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -80,6 +80,7 @@
 #include <linux/vmalloc.h>
 #include <linux/workqueue.h>
 #include <linux/kmemleak.h>
+#include <linux/sched.h>
 
 #include <asm/cacheflush.h>
 #include <asm/sections.h>
@@ -447,26 +448,25 @@ static void pcpu_next_fit_region(struct pcpu_chunk *chunk, int alloc_bits,
 /**
  * pcpu_mem_zalloc - allocate memory
  * @size: bytes to allocate
+ * @gfp: allocation flags
  *
  * Allocate @size bytes.  If @size is smaller than PAGE_SIZE,
- * kzalloc() is used; otherwise, vzalloc() is used.  The returned
- * memory is always zeroed.
- *
- * CONTEXT:
- * Does GFP_KERNEL allocation.
+ * kzalloc() is used; otherwise, the equivalent of vzalloc() is used.
+ * This is to facilitate passing through whitelisted flags.  The
+ * returned memory is always zeroed.
  *
  * RETURNS:
  * Pointer to the allocated area on success, NULL on failure.
  */
-static void *pcpu_mem_zalloc(size_t size)
+static void *pcpu_mem_zalloc(size_t size, gfp_t gfp)
 {
 	if (WARN_ON_ONCE(!slab_is_available()))
 		return NULL;
 
 	if (size <= PAGE_SIZE)
-		return kzalloc(size, GFP_KERNEL);
+		return kzalloc(size, gfp);
 	else
-		return vzalloc(size);
+		return __vmalloc(size, gfp | __GFP_ZERO, PAGE_KERNEL);
 }
 
 /**
@@ -1154,12 +1154,12 @@ static struct pcpu_chunk * __init pcpu_alloc_first_chunk(unsigned long tmp_addr,
 	return chunk;
 }
 
-static struct pcpu_chunk *pcpu_alloc_chunk(void)
+static struct pcpu_chunk *pcpu_alloc_chunk(gfp_t gfp)
 {
 	struct pcpu_chunk *chunk;
 	int region_bits;
 
-	chunk = pcpu_mem_zalloc(pcpu_chunk_struct_size);
+	chunk = pcpu_mem_zalloc(pcpu_chunk_struct_size, gfp);
 	if (!chunk)
 		return NULL;
 
@@ -1168,17 +1168,17 @@ static struct pcpu_chunk *pcpu_alloc_chunk(void)
 	region_bits = pcpu_chunk_map_bits(chunk);
 
 	chunk->alloc_map = pcpu_mem_zalloc(BITS_TO_LONGS(region_bits) *
-					   sizeof(chunk->alloc_map[0]));
+					   sizeof(chunk->alloc_map[0]), gfp);
 	if (!chunk->alloc_map)
 		goto alloc_map_fail;
 
 	chunk->bound_map = pcpu_mem_zalloc(BITS_TO_LONGS(region_bits + 1) *
-					   sizeof(chunk->bound_map[0]));
+					   sizeof(chunk->bound_map[0]), gfp);
 	if (!chunk->bound_map)
 		goto bound_map_fail;
 
 	chunk->md_blocks = pcpu_mem_zalloc(pcpu_chunk_nr_blocks(chunk) *
-					   sizeof(chunk->md_blocks[0]));
+					   sizeof(chunk->md_blocks[0]), gfp);
 	if (!chunk->md_blocks)
 		goto md_blocks_fail;
 
@@ -1277,9 +1277,11 @@ static void pcpu_chunk_depopulated(struct pcpu_chunk *chunk,
  * pcpu_addr_to_page		- translate address to physical address
  * pcpu_verify_alloc_info	- check alloc_info is acceptable during init
  */
-static int pcpu_populate_chunk(struct pcpu_chunk *chunk, int off, int size);
-static void pcpu_depopulate_chunk(struct pcpu_chunk *chunk, int off, int size);
-static struct pcpu_chunk *pcpu_create_chunk(void);
+static int pcpu_populate_chunk(struct pcpu_chunk *chunk,
+			       int page_start, int page_end, gfp_t gfp);
+static void pcpu_depopulate_chunk(struct pcpu_chunk *chunk,
+				  int page_start, int page_end);
+static struct pcpu_chunk *pcpu_create_chunk(gfp_t gfp);
 static void pcpu_destroy_chunk(struct pcpu_chunk *chunk);
 static struct page *pcpu_addr_to_page(void *addr);
 static int __init pcpu_verify_alloc_info(const struct pcpu_alloc_info *ai);
@@ -1339,6 +1341,8 @@ static struct pcpu_chunk *pcpu_chunk_addr_search(void *addr)
 static void __percpu *pcpu_alloc(size_t size, size_t align, bool reserved,
 				 gfp_t gfp)
 {
+	/* whitelisted flags that can be passed to the backing allocators */
+	gfp_t pcpu_gfp = gfp & (GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN);
 	bool is_atomic = (gfp & GFP_KERNEL) != GFP_KERNEL;
 	bool do_warn = !(gfp & __GFP_NOWARN);
 	static int warn_limit = 10;
@@ -1369,8 +1373,17 @@ static void __percpu *pcpu_alloc(size_t size, size_t align, bool reserved,
 		return NULL;
 	}
 
-	if (!is_atomic)
-		mutex_lock(&pcpu_alloc_mutex);
+	if (!is_atomic) {
+		/*
+		 * pcpu_balance_workfn() allocates memory under this mutex,
+		 * and it may wait for memory reclaim. Allow current task
+		 * to become OOM victim, in case of memory pressure.
+		 */
+		if (gfp & __GFP_NOFAIL)
+			mutex_lock(&pcpu_alloc_mutex);
+		else if (mutex_lock_killable(&pcpu_alloc_mutex))
+			return NULL;
+	}
 
 	spin_lock_irqsave(&pcpu_lock, flags);
 
@@ -1421,7 +1434,7 @@ restart:
 	}
 
 	if (list_empty(&pcpu_slot[pcpu_nr_slots - 1])) {
-		chunk = pcpu_create_chunk();
+		chunk = pcpu_create_chunk(pcpu_gfp);
 		if (!chunk) {
 			err = "failed to allocate new chunk";
 			goto fail;
@@ -1450,7 +1463,7 @@ area_found:
 					   page_start, page_end) {
 			WARN_ON(chunk->immutable);
 
-			ret = pcpu_populate_chunk(chunk, rs, re);
+			ret = pcpu_populate_chunk(chunk, rs, re, pcpu_gfp);
 
 			spin_lock_irqsave(&pcpu_lock, flags);
 			if (ret) {
@@ -1561,10 +1574,17 @@ void __percpu *__alloc_reserved_percpu(size_t size, size_t align)
  * pcpu_balance_workfn - manage the amount of free chunks and populated pages
  * @work: unused
  *
- * Reclaim all fully free chunks except for the first one.
+ * Reclaim all fully free chunks except for the first one.  This is also
+ * responsible for maintaining the pool of empty populated pages.  However,
+ * it is possible that this is called when physical memory is scarce causing
+ * OOM killer to be triggered.  We should avoid doing so until an actual
+ * allocation causes the failure as it is possible that requests can be
+ * serviced from already backed regions.
  */
 static void pcpu_balance_workfn(struct work_struct *work)
 {
+	/* gfp flags passed to underlying allocators */
+	const gfp_t gfp = GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN;
 	LIST_HEAD(to_free);
 	struct list_head *free_head = &pcpu_slot[pcpu_nr_slots - 1];
 	struct pcpu_chunk *chunk, *next;
@@ -1600,6 +1620,7 @@ static void pcpu_balance_workfn(struct work_struct *work)
 			spin_unlock_irq(&pcpu_lock);
 		}
 		pcpu_destroy_chunk(chunk);
+		cond_resched();
 	}
 
 	/*
@@ -1645,7 +1666,7 @@ retry_pop:
 					   chunk->nr_pages) {
 			int nr = min(re - rs, nr_to_pop);
 
-			ret = pcpu_populate_chunk(chunk, rs, rs + nr);
+			ret = pcpu_populate_chunk(chunk, rs, rs + nr, gfp);
 			if (!ret) {
 				nr_to_pop -= nr;
 				spin_lock_irq(&pcpu_lock);
@@ -1662,7 +1683,7 @@ retry_pop:
 
 	if (nr_to_pop) {
 		/* ran out of chunks to populate, create a new one and retry */
-		chunk = pcpu_create_chunk();
+		chunk = pcpu_create_chunk(gfp);
 		if (chunk) {
 			spin_lock_irq(&pcpu_lock);
 			pcpu_chunk_relocate(chunk, -1);
@@ -2719,11 +2740,7 @@ void __init setup_per_cpu_areas(void)
 
 	if (pcpu_setup_first_chunk(ai, fc) < 0)
 		panic("Failed to initialize percpu areas.");
-#ifdef CONFIG_CRIS
-#warning "the CRIS architecture has physical and virtual addresses confused"
-#else
 	pcpu_free_alloc_info(ai);
-#endif
 }
 
 #endif	/* CONFIG_SMP */
diff --git a/mm/readahead.c b/mm/readahead.c
index c4ca70239233..4d57b4644f98 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -573,7 +573,7 @@ do_readahead(struct address_space *mapping, struct file *filp,
 	return force_page_cache_readahead(mapping, filp, index, nr);
 }
 
-SYSCALL_DEFINE3(readahead, int, fd, loff_t, offset, size_t, count)
+ssize_t ksys_readahead(int fd, loff_t offset, size_t count)
 {
 	ssize_t ret;
 	struct fd f;
@@ -592,3 +592,8 @@ SYSCALL_DEFINE3(readahead, int, fd, loff_t, offset, size_t, count)
 	}
 	return ret;
 }
+
+SYSCALL_DEFINE3(readahead, int, fd, loff_t, offset, size_t, count)
+{
+	return ksys_readahead(fd, offset, count);
+}
diff --git a/mm/shmem.c b/mm/shmem.c
index 1907688b75ee..b85919243399 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -493,36 +493,45 @@ next:
 		info = list_entry(pos, struct shmem_inode_info, shrinklist);
 		inode = &info->vfs_inode;
 
-		if (nr_to_split && split >= nr_to_split) {
-			iput(inode);
-			continue;
-		}
+		if (nr_to_split && split >= nr_to_split)
+			goto leave;
 
-		page = find_lock_page(inode->i_mapping,
+		page = find_get_page(inode->i_mapping,
 				(inode->i_size & HPAGE_PMD_MASK) >> PAGE_SHIFT);
 		if (!page)
 			goto drop;
 
+		/* No huge page at the end of the file: nothing to split */
 		if (!PageTransHuge(page)) {
-			unlock_page(page);
 			put_page(page);
 			goto drop;
 		}
 
+		/*
+		 * Leave the inode on the list if we failed to lock
+		 * the page at this time.
+		 *
+		 * Waiting for the lock may lead to deadlock in the
+		 * reclaim path.
+		 */
+		if (!trylock_page(page)) {
+			put_page(page);
+			goto leave;
+		}
+
 		ret = split_huge_page(page);
 		unlock_page(page);
 		put_page(page);
 
-		if (ret) {
-			/* split failed: leave it on the list */
-			iput(inode);
-			continue;
-		}
+		/* If split failed leave the inode on the list */
+		if (ret)
+			goto leave;
 
 		split++;
 drop:
 		list_del_init(&info->shrinklist);
 		removed++;
+leave:
 		iput(inode);
 	}
 
diff --git a/mm/slab.c b/mm/slab.c
index 324446621b3e..9095c3945425 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -1283,6 +1283,7 @@ void __init kmem_cache_init(void)
 				  nr_node_ids * sizeof(struct kmem_cache_node *),
 				  SLAB_HWCACHE_ALIGN, 0, 0);
 	list_add(&kmem_cache->list, &slab_caches);
+	memcg_link_cache(kmem_cache);
 	slab_state = PARTIAL;
 
 	/*
diff --git a/mm/sparse.c b/mm/sparse.c
index 7af5e7a92528..58cab483e81b 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -236,28 +236,6 @@ void __init memory_present(int nid, unsigned long start, unsigned long end)
 }
 
 /*
- * Only used by the i386 NUMA architecures, but relatively
- * generic code.
- */
-unsigned long __init node_memmap_size_bytes(int nid, unsigned long start_pfn,
-						     unsigned long end_pfn)
-{
-	unsigned long pfn;
-	unsigned long nr_pages = 0;
-
-	mminit_validate_memmodel_limits(&start_pfn, &end_pfn);
-	for (pfn = start_pfn; pfn < end_pfn; pfn += PAGES_PER_SECTION) {
-		if (nid != early_pfn_to_nid(pfn))
-			continue;
-
-		if (pfn_present(pfn))
-			nr_pages += PAGES_PER_SECTION;
-	}
-
-	return nr_pages * sizeof(struct page);
-}
-
-/*
  * Subtle, we encode the real pfn into the mem_map such that
  * the identity pfn - section_mem_map will return the actual
  * physical page frame number.
@@ -427,10 +405,6 @@ struct page __init *sparse_mem_map_populate(unsigned long pnum, int nid,
 	struct page *map;
 	unsigned long size;
 
-	map = alloc_remap(nid, sizeof(struct page) * PAGES_PER_SECTION);
-	if (map)
-		return map;
-
 	size = PAGE_ALIGN(sizeof(struct page) * PAGES_PER_SECTION);
 	map = memblock_virt_alloc_try_nid(size,
 					  PAGE_SIZE, __pa(MAX_DMA_ADDRESS),
@@ -446,17 +420,6 @@ void __init sparse_mem_maps_populate_node(struct page **map_map,
 	unsigned long pnum;
 	unsigned long size = sizeof(struct page) * PAGES_PER_SECTION;
 
-	map = alloc_remap(nodeid, size * map_count);
-	if (map) {
-		for (pnum = pnum_begin; pnum < pnum_end; pnum++) {
-			if (!present_section_nr(pnum))
-				continue;
-			map_map[pnum] = map;
-			map += size;
-		}
-		return;
-	}
-
 	size = PAGE_ALIGN(size);
 	map = memblock_virt_alloc_try_nid_raw(size * map_count,
 					      PAGE_SIZE, __pa(MAX_DMA_ADDRESS),
diff --git a/mm/vmscan.c b/mm/vmscan.c
index bee53495a829..cd5dc3faaa57 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1780,6 +1780,20 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec,
 		set_bit(PGDAT_WRITEBACK, &pgdat->flags);
 
 	/*
+	 * If dirty pages are scanned that are not queued for IO, it
+	 * implies that flushers are not doing their job. This can
+	 * happen when memory pressure pushes dirty pages to the end of
+	 * the LRU before the dirty limits are breached and the dirty
+	 * data has expired. It can also happen when the proportion of
+	 * dirty pages grows not through writes but through memory
+	 * pressure reclaiming all the clean cache. And in some cases,
+	 * the flushers simply cannot keep up with the allocation
+	 * rate. Nudge the flusher threads in case they are asleep.
+	 */
+	if (stat.nr_unqueued_dirty == nr_taken)
+		wakeup_flusher_threads(WB_REASON_VMSCAN);
+
+	/*
 	 * Legacy memcg will stall in page writeback so avoid forcibly
 	 * stalling here.
 	 */
@@ -1791,22 +1805,9 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec,
 		if (stat.nr_dirty && stat.nr_dirty == stat.nr_congested)
 			set_bit(PGDAT_CONGESTED, &pgdat->flags);
 
-		/*
-		 * If dirty pages are scanned that are not queued for IO, it
-		 * implies that flushers are not doing their job. This can
-		 * happen when memory pressure pushes dirty pages to the end of
-		 * the LRU before the dirty limits are breached and the dirty
-		 * data has expired. It can also happen when the proportion of
-		 * dirty pages grows not through writes but through memory
-		 * pressure reclaiming all the clean cache. And in some cases,
-		 * the flushers simply cannot keep up with the allocation
-		 * rate. Nudge the flusher threads in case they are asleep, but
-		 * also allow kswapd to start writing pages during reclaim.
-		 */
-		if (stat.nr_unqueued_dirty == nr_taken) {
-			wakeup_flusher_threads(WB_REASON_VMSCAN);
+		/* Allow kswapd to start writing pages during reclaim. */
+		if (stat.nr_unqueued_dirty == nr_taken)
 			set_bit(PGDAT_DIRTY, &pgdat->flags);
-		}
 
 		/*
 		 * If kswapd scans pages marked marked for immediate
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 40b2db6db6b1..33581be705f0 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1839,9 +1839,11 @@ static void vmstat_update(struct work_struct *w)
 		 * to occur in the future. Keep on running the
 		 * update worker thread.
 		 */
+		preempt_disable();
 		queue_delayed_work_on(smp_processor_id(), mm_percpu_wq,
 				this_cpu_ptr(&vmstat_work),
 				round_jiffies_relative(sysctl_stat_interval));
+		preempt_enable();
 	}
 }
 
diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c
index c3013505c305..b7f61cd1c709 100644
--- a/mm/zsmalloc.c
+++ b/mm/zsmalloc.c
@@ -84,18 +84,19 @@
  * This is made more complicated by various memory models and PAE.
  */
 
-#ifndef MAX_PHYSMEM_BITS
-#ifdef CONFIG_HIGHMEM64G
-#define MAX_PHYSMEM_BITS 36
-#else /* !CONFIG_HIGHMEM64G */
+#ifndef MAX_POSSIBLE_PHYSMEM_BITS
+#ifdef MAX_PHYSMEM_BITS
+#define MAX_POSSIBLE_PHYSMEM_BITS MAX_PHYSMEM_BITS
+#else
 /*
  * If this definition of MAX_PHYSMEM_BITS is used, OBJ_INDEX_BITS will just
  * be PAGE_SHIFT
  */
-#define MAX_PHYSMEM_BITS BITS_PER_LONG
+#define MAX_POSSIBLE_PHYSMEM_BITS BITS_PER_LONG
 #endif
 #endif
-#define _PFN_BITS		(MAX_PHYSMEM_BITS - PAGE_SHIFT)
+
+#define _PFN_BITS		(MAX_POSSIBLE_PHYSMEM_BITS - PAGE_SHIFT)
 
 /*
  * Memory for allocating for handle keeps object position by