Merge tag 'v4.12-rc5' into for-4.13/block

We've already got a few conflicts and upcoming work depends on some of the
changes that have gone into mainline as regression fixes for this series.

Pull in 4.12-rc5 to resolve these conflicts and make it easier on down stream
trees to continue working on 4.13 changes.

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

10 files changed, 106 insertions, 48 deletions

diff --git a/mm/gup.c b/mm/gup.c
index d9e6fddcc51f..b3c7214d710d 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -407,12 +407,10 @@ static int faultin_page(struct task_struct *tsk, struct vm_area_struct *vma,
 
 	ret = handle_mm_fault(vma, address, fault_flags);
 	if (ret & VM_FAULT_ERROR) {
-		if (ret & VM_FAULT_OOM)
-			return -ENOMEM;
-		if (ret & (VM_FAULT_HWPOISON | VM_FAULT_HWPOISON_LARGE))
-			return *flags & FOLL_HWPOISON ? -EHWPOISON : -EFAULT;
-		if (ret & (VM_FAULT_SIGBUS | VM_FAULT_SIGSEGV))
-			return -EFAULT;
+		int err = vm_fault_to_errno(ret, *flags);
+
+		if (err)
+			return err;
 		BUG();
 	}
 
@@ -723,12 +721,10 @@ retry:
 	ret = handle_mm_fault(vma, address, fault_flags);
 	major |= ret & VM_FAULT_MAJOR;
 	if (ret & VM_FAULT_ERROR) {
-		if (ret & VM_FAULT_OOM)
-			return -ENOMEM;
-		if (ret & (VM_FAULT_HWPOISON | VM_FAULT_HWPOISON_LARGE))
-			return -EHWPOISON;
-		if (ret & (VM_FAULT_SIGBUS | VM_FAULT_SIGSEGV))
-			return -EFAULT;
+		int err = vm_fault_to_errno(ret, 0);
+
+		if (err)
+			return err;
 		BUG();
 	}
 
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index e5828875f7bb..3eedb187e549 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -4170,6 +4170,11 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
 			}
 			ret = hugetlb_fault(mm, vma, vaddr, fault_flags);
 			if (ret & VM_FAULT_ERROR) {
+				int err = vm_fault_to_errno(ret, flags);
+
+				if (err)
+					return err;
+
 				remainder = 0;
 				break;
 			}
diff --git a/mm/ksm.c b/mm/ksm.c
index d9fc0e456128..216184af0e19 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -1028,8 +1028,7 @@ static int try_to_merge_one_page(struct vm_area_struct *vma,
 		goto out;
 
 	if (PageTransCompound(page)) {
-		err = split_huge_page(page);
-		if (err)
+		if (split_huge_page(page))
 			goto out_unlock;
 	}
 
diff --git a/mm/memblock.c b/mm/memblock.c
index b049c9b2dba8..7b8a5db76a2f 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -1739,6 +1739,29 @@ static void __init_memblock memblock_dump(struct memblock_type *type)
 	}
 }
 
+extern unsigned long __init_memblock
+memblock_reserved_memory_within(phys_addr_t start_addr, phys_addr_t end_addr)
+{
+	struct memblock_region *rgn;
+	unsigned long size = 0;
+	int idx;
+
+	for_each_memblock_type((&memblock.reserved), rgn) {
+		phys_addr_t start, end;
+
+		if (rgn->base + rgn->size < start_addr)
+			continue;
+		if (rgn->base > end_addr)
+			continue;
+
+		start = rgn->base;
+		end = start + rgn->size;
+		size += end - start;
+	}
+
+	return size;
+}
+
 void __init_memblock __memblock_dump_all(void)
 {
 	pr_info("MEMBLOCK configuration:\n");
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 2527dfeddb00..342fac9ba89b 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -1595,12 +1595,8 @@ static int soft_offline_huge_page(struct page *page, int flags)
 	if (ret) {
 		pr_info("soft offline: %#lx: migration failed %d, type %lx (%pGp)\n",
 			pfn, ret, page->flags, &page->flags);
-		/*
-		 * We know that soft_offline_huge_page() tries to migrate
-		 * only one hugepage pointed to by hpage, so we need not
-		 * run through the pagelist here.
-		 */
-		putback_active_hugepage(hpage);
+		if (!list_empty(&pagelist))
+			putback_movable_pages(&pagelist);
 		if (ret > 0)
 			ret = -EIO;
 	} else {
diff --git a/mm/memory.c b/mm/memory.c
index 6ff5d729ded0..2e65df1831d9 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3029,6 +3029,17 @@ static int __do_fault(struct vm_fault *vmf)
 	return ret;
 }
 
+/*
+ * The ordering of these checks is important for pmds with _PAGE_DEVMAP set.
+ * If we check pmd_trans_unstable() first we will trip the bad_pmd() check
+ * inside of pmd_none_or_trans_huge_or_clear_bad(). This will end up correctly
+ * returning 1 but not before it spams dmesg with the pmd_clear_bad() output.
+ */
+static int pmd_devmap_trans_unstable(pmd_t *pmd)
+{
+	return pmd_devmap(*pmd) || pmd_trans_unstable(pmd);
+}
+
 static int pte_alloc_one_map(struct vm_fault *vmf)
 {
 	struct vm_area_struct *vma = vmf->vma;
@@ -3052,18 +3063,27 @@ static int pte_alloc_one_map(struct vm_fault *vmf)
 map_pte:
 	/*
 	 * If a huge pmd materialized under us just retry later.  Use
-	 * pmd_trans_unstable() instead of pmd_trans_huge() to ensure the pmd
-	 * didn't become pmd_trans_huge under us and then back to pmd_none, as
-	 * a result of MADV_DONTNEED running immediately after a huge pmd fault
-	 * in a different thread of this mm, in turn leading to a misleading
-	 * pmd_trans_huge() retval.  All we have to ensure is that it is a
-	 * regular pmd that we can walk with pte_offset_map() and we can do that
-	 * through an atomic read in C, which is what pmd_trans_unstable()
-	 * provides.
+	 * pmd_trans_unstable() via pmd_devmap_trans_unstable() instead of
+	 * pmd_trans_huge() to ensure the pmd didn't become pmd_trans_huge
+	 * under us and then back to pmd_none, as a result of MADV_DONTNEED
+	 * running immediately after a huge pmd fault in a different thread of
+	 * this mm, in turn leading to a misleading pmd_trans_huge() retval.
+	 * All we have to ensure is that it is a regular pmd that we can walk
+	 * with pte_offset_map() and we can do that through an atomic read in
+	 * C, which is what pmd_trans_unstable() provides.
 	 */
-	if (pmd_trans_unstable(vmf->pmd) || pmd_devmap(*vmf->pmd))
+	if (pmd_devmap_trans_unstable(vmf->pmd))
 		return VM_FAULT_NOPAGE;
 
+	/*
+	 * At this point we know that our vmf->pmd points to a page of ptes
+	 * and it cannot become pmd_none(), pmd_devmap() or pmd_trans_huge()
+	 * for the duration of the fault.  If a racing MADV_DONTNEED runs and
+	 * we zap the ptes pointed to by our vmf->pmd, the vmf->ptl will still
+	 * be valid and we will re-check to make sure the vmf->pte isn't
+	 * pte_none() under vmf->ptl protection when we return to
+	 * alloc_set_pte().
+	 */
 	vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address,
 			&vmf->ptl);
 	return 0;
@@ -3690,7 +3710,7 @@ static int handle_pte_fault(struct vm_fault *vmf)
 		vmf->pte = NULL;
 	} else {
 		/* See comment in pte_alloc_one_map() */
-		if (pmd_trans_unstable(vmf->pmd) || pmd_devmap(*vmf->pmd))
+		if (pmd_devmap_trans_unstable(vmf->pmd))
 			return 0;
 		/*
 		 * A regular pmd is established and it can't morph into a huge
diff --git a/mm/mlock.c b/mm/mlock.c
index c483c5c20b4b..b562b5523a65 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -284,7 +284,7 @@ static void __munlock_pagevec(struct pagevec *pvec, struct zone *zone)
 {
 	int i;
 	int nr = pagevec_count(pvec);
-	int delta_munlocked;
+	int delta_munlocked = -nr;
 	struct pagevec pvec_putback;
 	int pgrescued = 0;
 
@@ -304,6 +304,8 @@ static void __munlock_pagevec(struct pagevec *pvec, struct zone *zone)
 				continue;
 			else
 				__munlock_isolation_failed(page);
+		} else {
+			delta_munlocked++;
 		}
 
 		/*
@@ -315,7 +317,6 @@ static void __munlock_pagevec(struct pagevec *pvec, struct zone *zone)
 		pagevec_add(&pvec_putback, pvec->pages[i]);
 		pvec->pages[i] = NULL;
 	}
-	delta_munlocked = -nr + pagevec_count(&pvec_putback);
 	__mod_zone_page_state(zone, NR_MLOCK, delta_munlocked);
 	spin_unlock_irq(zone_lru_lock(zone));
 
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index f9e450c6b6e4..2302f250d6b1 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -292,6 +292,26 @@ int page_group_by_mobility_disabled __read_mostly;
 #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
 static inline void reset_deferred_meminit(pg_data_t *pgdat)
 {
+	unsigned long max_initialise;
+	unsigned long reserved_lowmem;
+
+	/*
+	 * Initialise at least 2G of a node but also take into account that
+	 * two large system hashes that can take up 1GB for 0.25TB/node.
+	 */
+	max_initialise = max(2UL << (30 - PAGE_SHIFT),
+		(pgdat->node_spanned_pages >> 8));
+
+	/*
+	 * Compensate the all the memblock reservations (e.g. crash kernel)
+	 * from the initial estimation to make sure we will initialize enough
+	 * memory to boot.
+	 */
+	reserved_lowmem = memblock_reserved_memory_within(pgdat->node_start_pfn,
+			pgdat->node_start_pfn + max_initialise);
+	max_initialise += reserved_lowmem;
+
+	pgdat->static_init_size = min(max_initialise, pgdat->node_spanned_pages);
 	pgdat->first_deferred_pfn = ULONG_MAX;
 }
 
@@ -314,20 +334,11 @@ static inline bool update_defer_init(pg_data_t *pgdat,
 				unsigned long pfn, unsigned long zone_end,
 				unsigned long *nr_initialised)
 {
-	unsigned long max_initialise;
-
 	/* Always populate low zones for address-contrained allocations */
 	if (zone_end < pgdat_end_pfn(pgdat))
 		return true;
-	/*
-	 * Initialise at least 2G of a node but also take into account that
-	 * two large system hashes that can take up 1GB for 0.25TB/node.
-	 */
-	max_initialise = max(2UL << (30 - PAGE_SHIFT),
-		(pgdat->node_spanned_pages >> 8));
-
 	(*nr_initialised)++;
-	if ((*nr_initialised > max_initialise) &&
+	if ((*nr_initialised > pgdat->static_init_size) &&
 	    (pfn & (PAGES_PER_SECTION - 1)) == 0) {
 		pgdat->first_deferred_pfn = pfn;
 		return false;
@@ -3870,7 +3881,9 @@ retry:
 		goto got_pg;
 
 	/* Avoid allocations with no watermarks from looping endlessly */
-	if (test_thread_flag(TIF_MEMDIE))
+	if (test_thread_flag(TIF_MEMDIE) &&
+	    (alloc_flags == ALLOC_NO_WATERMARKS ||
+	     (gfp_mask & __GFP_NOMEMALLOC)))
 		goto nopage;
 
 	/* Retry as long as the OOM killer is making progress */
@@ -6136,7 +6149,6 @@ void __paginginit free_area_init_node(int nid, unsigned long *zones_size,
 	/* pg_data_t should be reset to zero when it's allocated */
 	WARN_ON(pgdat->nr_zones || pgdat->kswapd_classzone_idx);
 
-	reset_deferred_meminit(pgdat);
 	pgdat->node_id = nid;
 	pgdat->node_start_pfn = node_start_pfn;
 	pgdat->per_cpu_nodestats = NULL;
@@ -6158,6 +6170,7 @@ void __paginginit free_area_init_node(int nid, unsigned long *zones_size,
 		(unsigned long)pgdat->node_mem_map);
 #endif
 
+	reset_deferred_meminit(pgdat);
 	free_area_init_core(pgdat);
 }
 
diff --git a/mm/slub.c b/mm/slub.c
index 57e5156f02be..7449593fca72 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -5512,6 +5512,7 @@ static void memcg_propagate_slab_attrs(struct kmem_cache *s)
 		char mbuf[64];
 		char *buf;
 		struct slab_attribute *attr = to_slab_attr(slab_attrs[i]);
+		ssize_t len;
 
 		if (!attr || !attr->store || !attr->show)
 			continue;
@@ -5536,8 +5537,9 @@ static void memcg_propagate_slab_attrs(struct kmem_cache *s)
 			buf = buffer;
 		}
 
-		attr->show(root_cache, buf);
-		attr->store(s, buf, strlen(buf));
+		len = attr->show(root_cache, buf);
+		if (len > 0)
+			attr->store(s, buf, len);
 	}
 
 	if (buffer)
diff --git a/mm/util.c b/mm/util.c
index 464df3489903..26be6407abd7 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -357,8 +357,11 @@ void *kvmalloc_node(size_t size, gfp_t flags, int node)
 	WARN_ON_ONCE((flags & GFP_KERNEL) != GFP_KERNEL);
 
 	/*
-	 * Make sure that larger requests are not too disruptive - no OOM
-	 * killer and no allocation failure warnings as we have a fallback
+	 * We want to attempt a large physically contiguous block first because
+	 * it is less likely to fragment multiple larger blocks and therefore
+	 * contribute to a long term fragmentation less than vmalloc fallback.
+	 * However make sure that larger requests are not too disruptive - no
+	 * OOM killer and no allocation failure warnings as we have a fallback.
 	 */
 	if (size > PAGE_SIZE) {
 		kmalloc_flags |= __GFP_NOWARN;