Merge branch 'akpm' (patches from Andrew)

Merge patch-bomb from Andrew Morton:

 - inotify tweaks

 - some ocfs2 updates (many more are awaiting review)

 - various misc bits

 - kernel/watchdog.c updates

 - Some of mm.  I have a huge number of MM patches this time and quite a
   lot of it is quite difficult and much will be held over to next time.

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (162 commits)
  selftests: vm: add tests for lock on fault
  mm: mlock: add mlock flags to enable VM_LOCKONFAULT usage
  mm: introduce VM_LOCKONFAULT
  mm: mlock: add new mlock system call
  mm: mlock: refactor mlock, munlock, and munlockall code
  kasan: always taint kernel on report
  mm, slub, kasan: enable user tracking by default with KASAN=y
  kasan: use IS_ALIGNED in memory_is_poisoned_8()
  kasan: Fix a type conversion error
  lib: test_kasan: add some testcases
  kasan: update reference to kasan prototype repo
  kasan: move KASAN_SANITIZE in arch/x86/boot/Makefile
  kasan: various fixes in documentation
  kasan: update log messages
  kasan: accurately determine the type of the bad access
  kasan: update reported bug types for kernel memory accesses
  kasan: update reported bug types for not user nor kernel memory accesses
  mm/kasan: prevent deadlock in kasan reporting
  mm/kasan: don't use kasan shadow pointer in generic functions
  mm/kasan: MODULE_VADDR is not available on all archs
  ...

1 files changed, 124 insertions, 15 deletions

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 9cc773483624..74ef0c6a25dd 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1437,7 +1437,82 @@ void dissolve_free_huge_pages(unsigned long start_pfn, unsigned long end_pfn)
 		dissolve_free_huge_page(pfn_to_page(pfn));
 }
 
-static struct page *alloc_buddy_huge_page(struct hstate *h, int nid)
+/*
+ * There are 3 ways this can get called:
+ * 1. With vma+addr: we use the VMA's memory policy
+ * 2. With !vma, but nid=NUMA_NO_NODE:  We try to allocate a huge
+ *    page from any node, and let the buddy allocator itself figure
+ *    it out.
+ * 3. With !vma, but nid!=NUMA_NO_NODE.  We allocate a huge page
+ *    strictly from 'nid'
+ */
+static struct page *__hugetlb_alloc_buddy_huge_page(struct hstate *h,
+		struct vm_area_struct *vma, unsigned long addr, int nid)
+{
+	int order = huge_page_order(h);
+	gfp_t gfp = htlb_alloc_mask(h)|__GFP_COMP|__GFP_REPEAT|__GFP_NOWARN;
+	unsigned int cpuset_mems_cookie;
+
+	/*
+	 * We need a VMA to get a memory policy.  If we do not
+	 * have one, we use the 'nid' argument.
+	 *
+	 * The mempolicy stuff below has some non-inlined bits
+	 * and calls ->vm_ops.  That makes it hard to optimize at
+	 * compile-time, even when NUMA is off and it does
+	 * nothing.  This helps the compiler optimize it out.
+	 */
+	if (!IS_ENABLED(CONFIG_NUMA) || !vma) {
+		/*
+		 * If a specific node is requested, make sure to
+		 * get memory from there, but only when a node
+		 * is explicitly specified.
+		 */
+		if (nid != NUMA_NO_NODE)
+			gfp |= __GFP_THISNODE;
+		/*
+		 * Make sure to call something that can handle
+		 * nid=NUMA_NO_NODE
+		 */
+		return alloc_pages_node(nid, gfp, order);
+	}
+
+	/*
+	 * OK, so we have a VMA.  Fetch the mempolicy and try to
+	 * allocate a huge page with it.  We will only reach this
+	 * when CONFIG_NUMA=y.
+	 */
+	do {
+		struct page *page;
+		struct mempolicy *mpol;
+		struct zonelist *zl;
+		nodemask_t *nodemask;
+
+		cpuset_mems_cookie = read_mems_allowed_begin();
+		zl = huge_zonelist(vma, addr, gfp, &mpol, &nodemask);
+		mpol_cond_put(mpol);
+		page = __alloc_pages_nodemask(gfp, order, zl, nodemask);
+		if (page)
+			return page;
+	} while (read_mems_allowed_retry(cpuset_mems_cookie));
+
+	return NULL;
+}
+
+/*
+ * There are two ways to allocate a huge page:
+ * 1. When you have a VMA and an address (like a fault)
+ * 2. When you have no VMA (like when setting /proc/.../nr_hugepages)
+ *
+ * 'vma' and 'addr' are only for (1).  'nid' is always NUMA_NO_NODE in
+ * this case which signifies that the allocation should be done with
+ * respect for the VMA's memory policy.
+ *
+ * For (2), we ignore 'vma' and 'addr' and use 'nid' exclusively. This
+ * implies that memory policies will not be taken in to account.
+ */
+static struct page *__alloc_buddy_huge_page(struct hstate *h,
+		struct vm_area_struct *vma, unsigned long addr, int nid)
 {
 	struct page *page;
 	unsigned int r_nid;
@@ -1446,6 +1521,15 @@ static struct page *alloc_buddy_huge_page(struct hstate *h, int nid)
 		return NULL;
 
 	/*
+	 * Make sure that anyone specifying 'nid' is not also specifying a VMA.
+	 * This makes sure the caller is picking _one_ of the modes with which
+	 * we can call this function, not both.
+	 */
+	if (vma || (addr != -1)) {
+		VM_WARN_ON_ONCE(addr == -1);
+		VM_WARN_ON_ONCE(nid != NUMA_NO_NODE);
+	}
+	/*
 	 * Assume we will successfully allocate the surplus page to
 	 * prevent racing processes from causing the surplus to exceed
 	 * overcommit
@@ -1478,14 +1562,7 @@ static struct page *alloc_buddy_huge_page(struct hstate *h, int nid)
 	}
 	spin_unlock(&hugetlb_lock);
 
-	if (nid == NUMA_NO_NODE)
-		page = alloc_pages(htlb_alloc_mask(h)|__GFP_COMP|
-				   __GFP_REPEAT|__GFP_NOWARN,
-				   huge_page_order(h));
-	else
-		page = __alloc_pages_node(nid,
-			htlb_alloc_mask(h)|__GFP_COMP|__GFP_THISNODE|
-			__GFP_REPEAT|__GFP_NOWARN, huge_page_order(h));
+	page = __hugetlb_alloc_buddy_huge_page(h, vma, addr, nid);
 
 	spin_lock(&hugetlb_lock);
 	if (page) {
@@ -1510,6 +1587,29 @@ static struct page *alloc_buddy_huge_page(struct hstate *h, int nid)
 }
 
 /*
+ * Allocate a huge page from 'nid'.  Note, 'nid' may be
+ * NUMA_NO_NODE, which means that it may be allocated
+ * anywhere.
+ */
+static
+struct page *__alloc_buddy_huge_page_no_mpol(struct hstate *h, int nid)
+{
+	unsigned long addr = -1;
+
+	return __alloc_buddy_huge_page(h, NULL, addr, nid);
+}
+
+/*
+ * Use the VMA's mpolicy to allocate a huge page from the buddy.
+ */
+static
+struct page *__alloc_buddy_huge_page_with_mpol(struct hstate *h,
+		struct vm_area_struct *vma, unsigned long addr)
+{
+	return __alloc_buddy_huge_page(h, vma, addr, NUMA_NO_NODE);
+}
+
+/*
  * This allocation function is useful in the context where vma is irrelevant.
  * E.g. soft-offlining uses this function because it only cares physical
  * address of error page.
@@ -1524,7 +1624,7 @@ struct page *alloc_huge_page_node(struct hstate *h, int nid)
 	spin_unlock(&hugetlb_lock);
 
 	if (!page)
-		page = alloc_buddy_huge_page(h, nid);
+		page = __alloc_buddy_huge_page_no_mpol(h, nid);
 
 	return page;
 }
@@ -1554,7 +1654,7 @@ static int gather_surplus_pages(struct hstate *h, int delta)
 retry:
 	spin_unlock(&hugetlb_lock);
 	for (i = 0; i < needed; i++) {
-		page = alloc_buddy_huge_page(h, NUMA_NO_NODE);
+		page = __alloc_buddy_huge_page_no_mpol(h, NUMA_NO_NODE);
 		if (!page) {
 			alloc_ok = false;
 			break;
@@ -1787,7 +1887,7 @@ struct page *alloc_huge_page(struct vm_area_struct *vma,
 	page = dequeue_huge_page_vma(h, vma, addr, avoid_reserve, gbl_chg);
 	if (!page) {
 		spin_unlock(&hugetlb_lock);
-		page = alloc_buddy_huge_page(h, NUMA_NO_NODE);
+		page = __alloc_buddy_huge_page_with_mpol(h, vma, addr);
 		if (!page)
 			goto out_uncharge_cgroup;
 
@@ -2376,7 +2476,7 @@ struct node_hstate {
 	struct kobject		*hugepages_kobj;
 	struct kobject		*hstate_kobjs[HUGE_MAX_HSTATE];
 };
-struct node_hstate node_hstates[MAX_NUMNODES];
+static struct node_hstate node_hstates[MAX_NUMNODES];
 
 /*
  * A subset of global hstate attributes for node devices
@@ -2790,6 +2890,12 @@ void hugetlb_show_meminfo(void)
 				1UL << (huge_page_order(h) + PAGE_SHIFT - 10));
 }
 
+void hugetlb_report_usage(struct seq_file *m, struct mm_struct *mm)
+{
+	seq_printf(m, "HugetlbPages:\t%8lu kB\n",
+		   atomic_long_read(&mm->hugetlb_usage) << (PAGE_SHIFT - 10));
+}
+
 /* Return the number pages of memory we physically have, in PAGE_SIZE units. */
 unsigned long hugetlb_total_pages(void)
 {
@@ -3025,6 +3131,7 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
 			get_page(ptepage);
 			page_dup_rmap(ptepage);
 			set_huge_pte_at(dst, addr, dst_pte, entry);
+			hugetlb_count_add(pages_per_huge_page(h), dst);
 		}
 		spin_unlock(src_ptl);
 		spin_unlock(dst_ptl);
@@ -3105,6 +3212,7 @@ again:
 		if (huge_pte_dirty(pte))
 			set_page_dirty(page);
 
+		hugetlb_count_sub(pages_per_huge_page(h), mm);
 		page_remove_rmap(page);
 		force_flush = !__tlb_remove_page(tlb, page);
 		if (force_flush) {
@@ -3509,6 +3617,7 @@ retry:
 				&& (vma->vm_flags & VM_SHARED)));
 	set_huge_pte_at(mm, address, ptep, new_pte);
 
+	hugetlb_count_add(pages_per_huge_page(h), mm);
 	if ((flags & FAULT_FLAG_WRITE) && !(vma->vm_flags & VM_SHARED)) {
 		/* Optimization, do the COW without a second fault */
 		ret = hugetlb_cow(mm, vma, address, ptep, new_pte, page, ptl);
@@ -4028,8 +4137,8 @@ static unsigned long page_table_shareable(struct vm_area_struct *svma,
 	unsigned long s_end = sbase + PUD_SIZE;
 
 	/* Allow segments to share if only one is marked locked */
-	unsigned long vm_flags = vma->vm_flags & ~VM_LOCKED;
-	unsigned long svm_flags = svma->vm_flags & ~VM_LOCKED;
+	unsigned long vm_flags = vma->vm_flags & VM_LOCKED_CLEAR_MASK;
+	unsigned long svm_flags = svma->vm_flags & VM_LOCKED_CLEAR_MASK;
 
 	/*
 	 * match the virtual addresses, permission and the alignment of the