Merge tag 'v4.18-rc5' into x86/mm, to pick up fixes

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

8 files changed, 43 insertions, 27 deletions

diff --git a/mm/debug.c b/mm/debug.c
index 56e2d9125ea5..38c926520c97 100644
--- a/mm/debug.c
+++ b/mm/debug.c
@@ -43,12 +43,25 @@ const struct trace_print_flags vmaflag_names[] = {
 
 void __dump_page(struct page *page, const char *reason)
 {
+	bool page_poisoned = PagePoisoned(page);
+	int mapcount;
+
+	/*
+	 * If struct page is poisoned don't access Page*() functions as that
+	 * leads to recursive loop. Page*() check for poisoned pages, and calls
+	 * dump_page() when detected.
+	 */
+	if (page_poisoned) {
+		pr_emerg("page:%px is uninitialized and poisoned", page);
+		goto hex_only;
+	}
+
 	/*
 	 * Avoid VM_BUG_ON() in page_mapcount().
 	 * page->_mapcount space in struct page is used by sl[aou]b pages to
 	 * encode own info.
 	 */
-	int mapcount = PageSlab(page) ? 0 : page_mapcount(page);
+	mapcount = PageSlab(page) ? 0 : page_mapcount(page);
 
 	pr_emerg("page:%px count:%d mapcount:%d mapping:%px index:%#lx",
 		  page, page_ref_count(page), mapcount,
@@ -60,6 +73,7 @@ void __dump_page(struct page *page, const char *reason)
 
 	pr_emerg("flags: %#lx(%pGp)\n", page->flags, &page->flags);
 
+hex_only:
 	print_hex_dump(KERN_ALERT, "raw: ", DUMP_PREFIX_NONE, 32,
 			sizeof(unsigned long), page,
 			sizeof(struct page), false);
@@ -68,7 +82,7 @@ void __dump_page(struct page *page, const char *reason)
 		pr_alert("page dumped because: %s\n", reason);
 
 #ifdef CONFIG_MEMCG
-	if (page->mem_cgroup)
+	if (!page_poisoned && page->mem_cgroup)
 		pr_alert("page->mem_cgroup:%px\n", page->mem_cgroup);
 #endif
 }
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/hugetlb.c b/mm/hugetlb.c
index 3612fbb32e9d..039ddbc574e9 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -2163,6 +2163,7 @@ static void __init gather_bootmem_prealloc(void)
 		 */
 		if (hstate_is_gigantic(h))
 			adjust_managed_page_count(page, 1 << h->order);
+		cond_resched();
 	}
 }
 
diff --git a/mm/kasan/kasan.c b/mm/kasan/kasan.c
index f185455b3406..c3bd5209da38 100644
--- a/mm/kasan/kasan.c
+++ b/mm/kasan/kasan.c
@@ -619,12 +619,13 @@ void kasan_kfree_large(void *ptr, unsigned long ip)
 int kasan_module_alloc(void *addr, size_t size)
 {
 	void *ret;
+	size_t scaled_size;
 	size_t shadow_size;
 	unsigned long shadow_start;
 
 	shadow_start = (unsigned long)kasan_mem_to_shadow(addr);
-	shadow_size = round_up(size >> KASAN_SHADOW_SCALE_SHIFT,
-			PAGE_SIZE);
+	scaled_size = (size + KASAN_SHADOW_MASK) >> KASAN_SHADOW_SCALE_SHIFT;
+	shadow_size = round_up(scaled_size, PAGE_SIZE);
 
 	if (WARN_ON(!PAGE_ALIGNED(shadow_start)))
 		return -EINVAL;
diff --git a/mm/memblock.c b/mm/memblock.c
index 03d48d8835ba..11e46f83e1ad 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -227,7 +227,8 @@ 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,
diff --git a/mm/mmap.c b/mm/mmap.c
index d1eb87ef4b1a..5801b5f0a634 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -186,8 +186,8 @@ static struct vm_area_struct *remove_vma(struct vm_area_struct *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:
@@ -2929,21 +2929,14 @@ 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;
@@ -3015,18 +3008,20 @@ 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;
 
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 1521100f1e63..5d800d61ddb7 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -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 */