Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

11 files changed, 58 insertions, 31 deletions

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 1e516520433d..bc48ee783dd9 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1384,7 +1384,7 @@ static struct page *alloc_fresh_huge_page_node(struct hstate *h, int nid)
 
 	page = __alloc_pages_node(nid,
 		htlb_alloc_mask(h)|__GFP_COMP|__GFP_THISNODE|
-						__GFP_REPEAT|__GFP_NOWARN,
+						__GFP_RETRY_MAYFAIL|__GFP_NOWARN,
 		huge_page_order(h));
 	if (page) {
 		prep_new_huge_page(h, page, nid);
@@ -1525,7 +1525,7 @@ static struct page *__hugetlb_alloc_buddy_huge_page(struct hstate *h,
 {
 	int order = huge_page_order(h);
 
-	gfp_mask |= __GFP_COMP|__GFP_REPEAT|__GFP_NOWARN;
+	gfp_mask |= __GFP_COMP|__GFP_RETRY_MAYFAIL|__GFP_NOWARN;
 	if (nid == NUMA_NO_NODE)
 		nid = numa_mem_id();
 	return __alloc_pages_nodemask(gfp_mask, order, nid, nmask);
diff --git a/mm/internal.h b/mm/internal.h
index 0e4f558412fb..24d88f084705 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -23,7 +23,7 @@
  * hints such as HIGHMEM usage.
  */
 #define GFP_RECLAIM_MASK (__GFP_RECLAIM|__GFP_HIGH|__GFP_IO|__GFP_FS|\
-			__GFP_NOWARN|__GFP_REPEAT|__GFP_NOFAIL|\
+			__GFP_NOWARN|__GFP_RETRY_MAYFAIL|__GFP_NOFAIL|\
 			__GFP_NORETRY|__GFP_MEMALLOC|__GFP_NOMEMALLOC|\
 			__GFP_ATOMIC)
 
diff --git a/mm/memory.c b/mm/memory.c
index cbb57194687e..0e517be91a89 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3591,7 +3591,7 @@ out:
 	return 0;
 }
 
-static int create_huge_pmd(struct vm_fault *vmf)
+static inline int create_huge_pmd(struct vm_fault *vmf)
 {
 	if (vma_is_anonymous(vmf->vma))
 		return do_huge_pmd_anonymous_page(vmf);
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 7d8e56214ac0..d911fa5cb2a7 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -1078,7 +1078,8 @@ static struct page *new_page(struct page *page, unsigned long start, int **x)
 	/*
 	 * if !vma, alloc_page_vma() will use task or system default policy
 	 */
-	return alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, address);
+	return alloc_page_vma(GFP_HIGHUSER_MOVABLE | __GFP_RETRY_MAYFAIL,
+			vma, address);
 }
 #else
 
diff --git a/mm/mmap.c b/mm/mmap.c
index 7fa6759322d1..f19efcf75418 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -2231,7 +2231,7 @@ int expand_upwards(struct vm_area_struct *vma, unsigned long address)
 
 	/* Guard against exceeding limits of the address space. */
 	address &= PAGE_MASK;
-	if (address >= TASK_SIZE)
+	if (address >= (TASK_SIZE & PAGE_MASK))
 		return -ENOMEM;
 	address += PAGE_SIZE;
 
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 0b60cc7ddac2..96e93b214d31 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -601,7 +601,7 @@ static inline void __wb_writeout_inc(struct bdi_writeback *wb)
 {
 	struct wb_domain *cgdom;
 
-	__inc_wb_stat(wb, WB_WRITTEN);
+	inc_wb_stat(wb, WB_WRITTEN);
 	wb_domain_writeout_inc(&global_wb_domain, &wb->completions,
 			       wb->bdi->max_prop_frac);
 
@@ -2435,8 +2435,8 @@ void account_page_dirtied(struct page *page, struct address_space *mapping)
 		__inc_lruvec_page_state(page, NR_FILE_DIRTY);
 		__inc_zone_page_state(page, NR_ZONE_WRITE_PENDING);
 		__inc_node_page_state(page, NR_DIRTIED);
-		__inc_wb_stat(wb, WB_RECLAIMABLE);
-		__inc_wb_stat(wb, WB_DIRTIED);
+		inc_wb_stat(wb, WB_RECLAIMABLE);
+		inc_wb_stat(wb, WB_DIRTIED);
 		task_io_account_write(PAGE_SIZE);
 		current->nr_dirtied++;
 		this_cpu_inc(bdp_ratelimits);
@@ -2741,7 +2741,7 @@ int test_clear_page_writeback(struct page *page)
 			if (bdi_cap_account_writeback(bdi)) {
 				struct bdi_writeback *wb = inode_to_wb(inode);
 
-				__dec_wb_stat(wb, WB_WRITEBACK);
+				dec_wb_stat(wb, WB_WRITEBACK);
 				__wb_writeout_inc(wb);
 			}
 		}
@@ -2786,7 +2786,7 @@ int __test_set_page_writeback(struct page *page, bool keep_write)
 						page_index(page),
 						PAGECACHE_TAG_WRITEBACK);
 			if (bdi_cap_account_writeback(bdi))
-				__inc_wb_stat(inode_to_wb(inode), WB_WRITEBACK);
+				inc_wb_stat(inode_to_wb(inode), WB_WRITEBACK);
 
 			/*
 			 * We can come through here when swapping anonymous
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 64b7d82a9b1a..6d30e914afb6 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -3284,6 +3284,14 @@ __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order,
 	/* The OOM killer will not help higher order allocs */
 	if (order > PAGE_ALLOC_COSTLY_ORDER)
 		goto out;
+	/*
+	 * We have already exhausted all our reclaim opportunities without any
+	 * success so it is time to admit defeat. We will skip the OOM killer
+	 * because it is very likely that the caller has a more reasonable
+	 * fallback than shooting a random task.
+	 */
+	if (gfp_mask & __GFP_RETRY_MAYFAIL)
+		goto out;
 	/* The OOM killer does not needlessly kill tasks for lowmem */
 	if (ac->high_zoneidx < ZONE_NORMAL)
 		goto out;
@@ -3413,7 +3421,7 @@ should_compact_retry(struct alloc_context *ac, int order, int alloc_flags,
 	}
 
 	/*
-	 * !costly requests are much more important than __GFP_REPEAT
+	 * !costly requests are much more important than __GFP_RETRY_MAYFAIL
 	 * costly ones because they are de facto nofail and invoke OOM
 	 * killer to move on while costly can fail and users are ready
 	 * to cope with that. 1/4 retries is rather arbitrary but we
@@ -3920,9 +3928,9 @@ retry:
 
 	/*
 	 * Do not retry costly high order allocations unless they are
-	 * __GFP_REPEAT
+	 * __GFP_RETRY_MAYFAIL
 	 */
-	if (costly_order && !(gfp_mask & __GFP_REPEAT))
+	if (costly_order && !(gfp_mask & __GFP_RETRY_MAYFAIL))
 		goto nopage;
 
 	if (should_reclaim_retry(gfp_mask, order, ac, alloc_flags,
diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c
index a56c3989f773..c50b1a14d55e 100644
--- a/mm/sparse-vmemmap.c
+++ b/mm/sparse-vmemmap.c
@@ -56,11 +56,11 @@ void * __meminit vmemmap_alloc_block(unsigned long size, int node)
 
 		if (node_state(node, N_HIGH_MEMORY))
 			page = alloc_pages_node(
-				node, GFP_KERNEL | __GFP_ZERO | __GFP_REPEAT,
+				node, GFP_KERNEL | __GFP_ZERO | __GFP_RETRY_MAYFAIL,
 				get_order(size));
 		else
 			page = alloc_pages(
-				GFP_KERNEL | __GFP_ZERO | __GFP_REPEAT,
+				GFP_KERNEL | __GFP_ZERO | __GFP_RETRY_MAYFAIL,
 				get_order(size));
 		if (page)
 			return page_address(page);
diff --git a/mm/util.c b/mm/util.c
index 26be6407abd7..7b07ec852e01 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -83,6 +83,8 @@ EXPORT_SYMBOL(kstrdup_const);
  * @s: the string to duplicate
  * @max: read at most @max chars from @s
  * @gfp: the GFP mask used in the kmalloc() call when allocating memory
+ *
+ * Note: Use kmemdup_nul() instead if the size is known exactly.
  */
 char *kstrndup(const char *s, size_t max, gfp_t gfp)
 {
@@ -121,6 +123,28 @@ void *kmemdup(const void *src, size_t len, gfp_t gfp)
 EXPORT_SYMBOL(kmemdup);
 
 /**
+ * kmemdup_nul - Create a NUL-terminated string from unterminated data
+ * @s: The data to stringify
+ * @len: The size of the data
+ * @gfp: the GFP mask used in the kmalloc() call when allocating memory
+ */
+char *kmemdup_nul(const char *s, size_t len, gfp_t gfp)
+{
+	char *buf;
+
+	if (!s)
+		return NULL;
+
+	buf = kmalloc_track_caller(len + 1, gfp);
+	if (buf) {
+		memcpy(buf, s, len);
+		buf[len] = '\0';
+	}
+	return buf;
+}
+EXPORT_SYMBOL(kmemdup_nul);
+
+/**
  * memdup_user - duplicate memory region from user space
  *
  * @src: source address in user space
@@ -339,9 +363,9 @@ EXPORT_SYMBOL(vm_mmap);
  * Uses kmalloc to get the memory but if the allocation fails then falls back
  * to the vmalloc allocator. Use kvfree for freeing the memory.
  *
- * Reclaim modifiers - __GFP_NORETRY and __GFP_NOFAIL are not supported. __GFP_REPEAT
- * is supported only for large (>32kB) allocations, and it should be used only if
- * kmalloc is preferable to the vmalloc fallback, due to visible performance drawbacks.
+ * Reclaim modifiers - __GFP_NORETRY and __GFP_NOFAIL are not supported.
+ * __GFP_RETRY_MAYFAIL is supported, and it should be used only if kmalloc is
+ * preferable to the vmalloc fallback, due to visible performance drawbacks.
  *
  * Any use of gfp flags outside of GFP_KERNEL should be consulted with mm people.
  */
@@ -366,13 +390,7 @@ void *kvmalloc_node(size_t size, gfp_t flags, int node)
 	if (size > PAGE_SIZE) {
 		kmalloc_flags |= __GFP_NOWARN;
 
-		/*
-		 * We have to override __GFP_REPEAT by __GFP_NORETRY for !costly
-		 * requests because there is no other way to tell the allocator
-		 * that we want to fail rather than retry endlessly.
-		 */
-		if (!(kmalloc_flags & __GFP_REPEAT) ||
-				(size <= PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER))
+		if (!(kmalloc_flags & __GFP_RETRY_MAYFAIL))
 			kmalloc_flags |= __GFP_NORETRY;
 	}
 
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 6016ab079e2b..8698c1c86c4d 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -1795,7 +1795,7 @@ fail:
  *	allocator with @gfp_mask flags.  Map them into contiguous
  *	kernel virtual space, using a pagetable protection of @prot.
  *
- *	Reclaim modifiers in @gfp_mask - __GFP_NORETRY, __GFP_REPEAT
+ *	Reclaim modifiers in @gfp_mask - __GFP_NORETRY, __GFP_RETRY_MAYFAIL
  *	and __GFP_NOFAIL are not supported
  *
  *	Any use of gfp flags outside of GFP_KERNEL should be consulted
diff --git a/mm/vmscan.c b/mm/vmscan.c
index e9210f825219..a1af041930a6 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2506,18 +2506,18 @@ static inline bool should_continue_reclaim(struct pglist_data *pgdat,
 		return false;
 
 	/* Consider stopping depending on scan and reclaim activity */
-	if (sc->gfp_mask & __GFP_REPEAT) {
+	if (sc->gfp_mask & __GFP_RETRY_MAYFAIL) {
 		/*
-		 * For __GFP_REPEAT allocations, stop reclaiming if the
+		 * For __GFP_RETRY_MAYFAIL allocations, stop reclaiming if the
 		 * full LRU list has been scanned and we are still failing
 		 * to reclaim pages. This full LRU scan is potentially
-		 * expensive but a __GFP_REPEAT caller really wants to succeed
+		 * expensive but a __GFP_RETRY_MAYFAIL caller really wants to succeed
 		 */
 		if (!nr_reclaimed && !nr_scanned)
 			return false;
 	} else {
 		/*
-		 * For non-__GFP_REPEAT allocations which can presumably
+		 * For non-__GFP_RETRY_MAYFAIL allocations which can presumably
 		 * fail without consequence, stop if we failed to reclaim
 		 * any pages from the last SWAP_CLUSTER_MAX number of
 		 * pages that were scanned. This will return to the