Merge tag 'v4.18-rc6' into for-4.19/block2

Pull in 4.18-rc6 to get the NVMe core AEN change to avoid a
merge conflict down the line.

Signed-of-by: Jens Axboe <axboe@kernel.dk>

8 files changed, 46 insertions, 56 deletions

diff --git a/mm/gup.c b/mm/gup.c
index b70d7ba7cc13..fc5f98069f4e 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -1238,8 +1238,6 @@ int __mm_populate(unsigned long start, unsigned long len, int ignore_errors)
 	int locked = 0;
 	long ret = 0;
 
-	VM_BUG_ON(start & ~PAGE_MASK);
-	VM_BUG_ON(len != PAGE_ALIGN(len));
 	end = start + len;
 
 	for (nstart = start; nstart < end; nstart = nend) {
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index b87d5b151db2..a9e1e093df51 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -2084,6 +2084,8 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
 		if (vma_is_dax(vma))
 			return;
 		page = pmd_page(_pmd);
+		if (!PageDirty(page) && pmd_dirty(_pmd))
+			set_page_dirty(page);
 		if (!PageReferenced(page) && pmd_young(_pmd))
 			SetPageReferenced(page);
 		page_remove_rmap(page, true);
diff --git a/mm/memblock.c b/mm/memblock.c
index 03d48d8835ba..4b5d245fafc1 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -20,6 +20,7 @@
 #include <linux/kmemleak.h>
 #include <linux/seq_file.h>
 #include <linux/memblock.h>
+#include <linux/bootmem.h>
 
 #include <asm/sections.h>
 #include <linux/io.h>
@@ -227,7 +228,8 @@ phys_addr_t __init_memblock memblock_find_in_range_node(phys_addr_t size,
 		 * so we use WARN_ONCE() here to see the stack trace if
 		 * fail happens.
 		 */
-		WARN_ONCE(1, "memblock: bottom-up allocation failed, memory hotunplug may be affected\n");
+		WARN_ONCE(IS_ENABLED(CONFIG_MEMORY_HOTREMOVE),
+			  "memblock: bottom-up allocation failed, memory hotremove may be affected\n");
 	}
 
 	return __memblock_find_range_top_down(start, end, size, align, nid,
@@ -1224,6 +1226,7 @@ phys_addr_t __init memblock_alloc_try_nid(phys_addr_t size, phys_addr_t align, i
 	return memblock_alloc_base(size, align, MEMBLOCK_ALLOC_ACCESSIBLE);
 }
 
+#if defined(CONFIG_NO_BOOTMEM)
 /**
  * memblock_virt_alloc_internal - allocate boot memory block
  * @size: size of memory block to be allocated in bytes
@@ -1431,6 +1434,7 @@ void * __init memblock_virt_alloc_try_nid(
 	      (u64)max_addr);
 	return NULL;
 }
+#endif
 
 /**
  * __memblock_free_early - free boot memory block
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 64bd28d35388..473278bed142 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -850,7 +850,7 @@ static void invalidate_reclaim_iterators(struct mem_cgroup *dead_memcg)
 	int nid;
 	int i;
 
-	while ((memcg = parent_mem_cgroup(memcg))) {
+	for (; memcg; memcg = parent_mem_cgroup(memcg)) {
 		for_each_node(nid) {
 			mz = mem_cgroup_nodeinfo(memcg, nid);
 			for (i = 0; i <= DEF_PRIORITY; i++) {
diff --git a/mm/mmap.c b/mm/mmap.c
index d1eb87ef4b1a..ff1944d8d458 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -182,12 +182,12 @@ static struct vm_area_struct *remove_vma(struct vm_area_struct *vma)
 	if (vma->vm_file)
 		fput(vma->vm_file);
 	mpol_put(vma_policy(vma));
-	kmem_cache_free(vm_area_cachep, vma);
+	vm_area_free(vma);
 	return next;
 }
 
-static int do_brk(unsigned long addr, unsigned long len, struct list_head *uf);
-
+static int do_brk_flags(unsigned long addr, unsigned long request, unsigned long flags,
+		struct list_head *uf);
 SYSCALL_DEFINE1(brk, unsigned long, brk)
 {
 	unsigned long retval;
@@ -245,7 +245,7 @@ SYSCALL_DEFINE1(brk, unsigned long, brk)
 		goto out;
 
 	/* Ok, looks good - let it rip. */
-	if (do_brk(oldbrk, newbrk-oldbrk, &uf) < 0)
+	if (do_brk_flags(oldbrk, newbrk-oldbrk, 0, &uf) < 0)
 		goto out;
 
 set_brk:
@@ -911,7 +911,7 @@ again:
 			anon_vma_merge(vma, next);
 		mm->map_count--;
 		mpol_put(vma_policy(next));
-		kmem_cache_free(vm_area_cachep, next);
+		vm_area_free(next);
 		/*
 		 * In mprotect's case 6 (see comments on vma_merge),
 		 * we must remove another next too. It would clutter
@@ -1729,19 +1729,17 @@ unsigned long mmap_region(struct file *file, unsigned long addr,
 	 * specific mapper. the address has already been validated, but
 	 * not unmapped, but the maps are removed from the list.
 	 */
-	vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL);
+	vma = vm_area_alloc(mm);
 	if (!vma) {
 		error = -ENOMEM;
 		goto unacct_error;
 	}
 
-	vma->vm_mm = mm;
 	vma->vm_start = addr;
 	vma->vm_end = addr + len;
 	vma->vm_flags = vm_flags;
 	vma->vm_page_prot = vm_get_page_prot(vm_flags);
 	vma->vm_pgoff = pgoff;
-	INIT_LIST_HEAD(&vma->anon_vma_chain);
 
 	if (file) {
 		if (vm_flags & VM_DENYWRITE) {
@@ -1832,7 +1830,7 @@ allow_write_and_free_vma:
 	if (vm_flags & VM_DENYWRITE)
 		allow_write_access(file);
 free_vma:
-	kmem_cache_free(vm_area_cachep, vma);
+	vm_area_free(vma);
 unacct_error:
 	if (charged)
 		vm_unacct_memory(charged);
@@ -2620,15 +2618,10 @@ int __split_vma(struct mm_struct *mm, struct vm_area_struct *vma,
 			return err;
 	}
 
-	new = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL);
+	new = vm_area_dup(vma);
 	if (!new)
 		return -ENOMEM;
 
-	/* most fields are the same, copy all, and then fixup */
-	*new = *vma;
-
-	INIT_LIST_HEAD(&new->anon_vma_chain);
-
 	if (new_below)
 		new->vm_end = addr;
 	else {
@@ -2669,7 +2662,7 @@ int __split_vma(struct mm_struct *mm, struct vm_area_struct *vma,
  out_free_mpol:
 	mpol_put(vma_policy(new));
  out_free_vma:
-	kmem_cache_free(vm_area_cachep, new);
+	vm_area_free(new);
 	return err;
 }
 
@@ -2929,21 +2922,14 @@ static inline void verify_mm_writelocked(struct mm_struct *mm)
  *  anonymous maps.  eventually we may be able to do some
  *  brk-specific accounting here.
  */
-static int do_brk_flags(unsigned long addr, unsigned long request, unsigned long flags, struct list_head *uf)
+static int do_brk_flags(unsigned long addr, unsigned long len, unsigned long flags, struct list_head *uf)
 {
 	struct mm_struct *mm = current->mm;
 	struct vm_area_struct *vma, *prev;
-	unsigned long len;
 	struct rb_node **rb_link, *rb_parent;
 	pgoff_t pgoff = addr >> PAGE_SHIFT;
 	int error;
 
-	len = PAGE_ALIGN(request);
-	if (len < request)
-		return -ENOMEM;
-	if (!len)
-		return 0;
-
 	/* Until we need other flags, refuse anything except VM_EXEC. */
 	if ((flags & (~VM_EXEC)) != 0)
 		return -EINVAL;
@@ -2991,14 +2977,12 @@ static int do_brk_flags(unsigned long addr, unsigned long request, unsigned long
 	/*
 	 * create a vma struct for an anonymous mapping
 	 */
-	vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL);
+	vma = vm_area_alloc(mm);
 	if (!vma) {
 		vm_unacct_memory(len >> PAGE_SHIFT);
 		return -ENOMEM;
 	}
 
-	INIT_LIST_HEAD(&vma->anon_vma_chain);
-	vma->vm_mm = mm;
 	vma->vm_start = addr;
 	vma->vm_end = addr + len;
 	vma->vm_pgoff = pgoff;
@@ -3015,18 +2999,20 @@ out:
 	return 0;
 }
 
-static int do_brk(unsigned long addr, unsigned long len, struct list_head *uf)
-{
-	return do_brk_flags(addr, len, 0, uf);
-}
-
-int vm_brk_flags(unsigned long addr, unsigned long len, unsigned long flags)
+int vm_brk_flags(unsigned long addr, unsigned long request, unsigned long flags)
 {
 	struct mm_struct *mm = current->mm;
+	unsigned long len;
 	int ret;
 	bool populate;
 	LIST_HEAD(uf);
 
+	len = PAGE_ALIGN(request);
+	if (len < request)
+		return -ENOMEM;
+	if (!len)
+		return 0;
+
 	if (down_write_killable(&mm->mmap_sem))
 		return -EINTR;
 
@@ -3207,16 +3193,14 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap,
 		}
 		*need_rmap_locks = (new_vma->vm_pgoff <= vma->vm_pgoff);
 	} else {
-		new_vma = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL);
+		new_vma = vm_area_dup(vma);
 		if (!new_vma)
 			goto out;
-		*new_vma = *vma;
 		new_vma->vm_start = addr;
 		new_vma->vm_end = addr + len;
 		new_vma->vm_pgoff = pgoff;
 		if (vma_dup_policy(vma, new_vma))
 			goto out_free_vma;
-		INIT_LIST_HEAD(&new_vma->anon_vma_chain);
 		if (anon_vma_clone(new_vma, vma))
 			goto out_free_mempol;
 		if (new_vma->vm_file)
@@ -3231,7 +3215,7 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap,
 out_free_mempol:
 	mpol_put(vma_policy(new_vma));
 out_free_vma:
-	kmem_cache_free(vm_area_cachep, new_vma);
+	vm_area_free(new_vma);
 out:
 	return NULL;
 }
@@ -3355,12 +3339,10 @@ static struct vm_area_struct *__install_special_mapping(
 	int ret;
 	struct vm_area_struct *vma;
 
-	vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL);
+	vma = vm_area_alloc(mm);
 	if (unlikely(vma == NULL))
 		return ERR_PTR(-ENOMEM);
 
-	INIT_LIST_HEAD(&vma->anon_vma_chain);
-	vma->vm_mm = mm;
 	vma->vm_start = addr;
 	vma->vm_end = addr + len;
 
@@ -3381,7 +3363,7 @@ static struct vm_area_struct *__install_special_mapping(
 	return vma;
 
 out:
-	kmem_cache_free(vm_area_cachep, vma);
+	vm_area_free(vma);
 	return ERR_PTR(ret);
 }
 
diff --git a/mm/nommu.c b/mm/nommu.c
index 4452d8bd9ae4..1d22fdbf7d7c 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -769,7 +769,7 @@ static void delete_vma(struct mm_struct *mm, struct vm_area_struct *vma)
 	if (vma->vm_file)
 		fput(vma->vm_file);
 	put_nommu_region(vma->vm_region);
-	kmem_cache_free(vm_area_cachep, vma);
+	vm_area_free(vma);
 }
 
 /*
@@ -1204,7 +1204,7 @@ unsigned long do_mmap(struct file *file,
 	if (!region)
 		goto error_getting_region;
 
-	vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL);
+	vma = vm_area_alloc(current->mm);
 	if (!vma)
 		goto error_getting_vma;
 
@@ -1212,7 +1212,6 @@ unsigned long do_mmap(struct file *file,
 	region->vm_flags = vm_flags;
 	region->vm_pgoff = pgoff;
 
-	INIT_LIST_HEAD(&vma->anon_vma_chain);
 	vma->vm_flags = vm_flags;
 	vma->vm_pgoff = pgoff;
 
@@ -1368,7 +1367,7 @@ error:
 	kmem_cache_free(vm_region_jar, region);
 	if (vma->vm_file)
 		fput(vma->vm_file);
-	kmem_cache_free(vm_area_cachep, vma);
+	vm_area_free(vma);
 	return ret;
 
 sharing_violation:
@@ -1469,14 +1468,13 @@ int split_vma(struct mm_struct *mm, struct vm_area_struct *vma,
 	if (!region)
 		return -ENOMEM;
 
-	new = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL);
+	new = vm_area_dup(vma);
 	if (!new) {
 		kmem_cache_free(vm_region_jar, region);
 		return -ENOMEM;
 	}
 
 	/* most fields are the same, copy all, and then fixup */
-	*new = *vma;
 	*region = *vma->vm_region;
 	new->vm_region = region;
 
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 1521100f1e63..a790ef4be74e 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -6383,7 +6383,7 @@ void __paginginit free_area_init_node(int nid, unsigned long *zones_size,
 	free_area_init_core(pgdat);
 }
 
-#ifdef CONFIG_HAVE_MEMBLOCK
+#if defined(CONFIG_HAVE_MEMBLOCK) && !defined(CONFIG_FLAT_NODE_MEM_MAP)
 /*
  * Only struct pages that are backed by physical memory are zeroed and
  * initialized by going through __init_single_page(). But, there are some
@@ -6421,7 +6421,7 @@ void __paginginit zero_resv_unavail(void)
 	if (pgcnt)
 		pr_info("Reserved but unavailable: %lld pages", pgcnt);
 }
-#endif /* CONFIG_HAVE_MEMBLOCK */
+#endif /* CONFIG_HAVE_MEMBLOCK && !CONFIG_FLAT_NODE_MEM_MAP */
 
 #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
 
@@ -6847,6 +6847,7 @@ void __init free_area_init_nodes(unsigned long *max_zone_pfn)
 	/* Initialise every node */
 	mminit_verify_pageflags_layout();
 	setup_nr_node_ids();
+	zero_resv_unavail();
 	for_each_online_node(nid) {
 		pg_data_t *pgdat = NODE_DATA(nid);
 		free_area_init_node(nid, NULL,
@@ -6857,7 +6858,6 @@ void __init free_area_init_nodes(unsigned long *max_zone_pfn)
 			node_set_state(nid, N_MEMORY);
 		check_for_memory(pgdat, nid);
 	}
-	zero_resv_unavail();
 }
 
 static int __init cmdline_parse_core(char *p, unsigned long *core,
@@ -7033,9 +7033,9 @@ void __init set_dma_reserve(unsigned long new_dma_reserve)
 
 void __init free_area_init(unsigned long *zones_size)
 {
+	zero_resv_unavail();
 	free_area_init_node(0, zones_size,
 			__pa(PAGE_OFFSET) >> PAGE_SHIFT, NULL);
-	zero_resv_unavail();
 }
 
 static int page_alloc_cpu_dead(unsigned int cpu)
diff --git a/mm/rmap.c b/mm/rmap.c
index 6db729dc4c50..eb477809a5c0 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -64,6 +64,7 @@
 #include <linux/backing-dev.h>
 #include <linux/page_idle.h>
 #include <linux/memremap.h>
+#include <linux/userfaultfd_k.h>
 
 #include <asm/tlbflush.h>
 
@@ -1481,11 +1482,16 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
 				set_pte_at(mm, address, pvmw.pte, pteval);
 			}
 
-		} else if (pte_unused(pteval)) {
+		} else if (pte_unused(pteval) && !userfaultfd_armed(vma)) {
 			/*
 			 * The guest indicated that the page content is of no
 			 * interest anymore. Simply discard the pte, vmscan
 			 * will take care of the rest.
+			 * A future reference will then fault in a new zero
+			 * page. When userfaultfd is active, we must not drop
+			 * this page though, as its main user (postcopy
+			 * migration) will not expect userfaults on already
+			 * copied pages.
 			 */
 			dec_mm_counter(mm, mm_counter(page));
 			/* We have to invalidate as we cleared the pte */