Merge remote-tracking branch 'origin/x86/espfix' into x86/vdso

Merge x86/espfix into x86/vdso, due to changes in the vdso setup code
that otherwise cause conflicts.

Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>

15 files changed, 138 insertions, 90 deletions

diff --git a/mm/compaction.c b/mm/compaction.c
index 37f9762..627dc2e 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -671,16 +671,20 @@ static void isolate_freepages(struct zone *zone,
 				struct compact_control *cc)
 {
 	struct page *page;
-	unsigned long high_pfn, low_pfn, pfn, z_end_pfn, end_pfn;
+	unsigned long high_pfn, low_pfn, pfn, z_end_pfn;
 	int nr_freepages = cc->nr_freepages;
 	struct list_head *freelist = &cc->freepages;
 
 	/*
 	 * Initialise the free scanner. The starting point is where we last
-	 * scanned from (or the end of the zone if starting). The low point
-	 * is the end of the pageblock the migration scanner is using.
+	 * successfully isolated from, zone-cached value, or the end of the
+	 * zone when isolating for the first time. We need this aligned to
+	 * the pageblock boundary, because we do pfn -= pageblock_nr_pages
+	 * in the for loop.
+	 * The low boundary is the end of the pageblock the migration scanner
+	 * is using.
 	 */
-	pfn = cc->free_pfn;
+	pfn = cc->free_pfn & ~(pageblock_nr_pages-1);
 	low_pfn = ALIGN(cc->migrate_pfn + 1, pageblock_nr_pages);
 
 	/*
@@ -700,6 +704,7 @@ static void isolate_freepages(struct zone *zone,
 	for (; pfn >= low_pfn && cc->nr_migratepages > nr_freepages;
 					pfn -= pageblock_nr_pages) {
 		unsigned long isolated;
+		unsigned long end_pfn;
 
 		/*
 		 * This can iterate a massively long zone without finding any
@@ -734,13 +739,10 @@ static void isolate_freepages(struct zone *zone,
 		isolated = 0;
 
 		/*
-		 * As pfn may not start aligned, pfn+pageblock_nr_page
-		 * may cross a MAX_ORDER_NR_PAGES boundary and miss
-		 * a pfn_valid check. Ensure isolate_freepages_block()
-		 * only scans within a pageblock
+		 * Take care when isolating in last pageblock of a zone which
+		 * ends in the middle of a pageblock.
 		 */
-		end_pfn = ALIGN(pfn + 1, pageblock_nr_pages);
-		end_pfn = min(end_pfn, z_end_pfn);
+		end_pfn = min(pfn + pageblock_nr_pages, z_end_pfn);
 		isolated = isolate_freepages_block(cc, pfn, end_pfn,
 						   freelist, false);
 		nr_freepages += isolated;
diff --git a/mm/filemap.c b/mm/filemap.c
index 5020b28..000a220 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -906,8 +906,8 @@ EXPORT_SYMBOL(page_cache_prev_hole);
  * Looks up the page cache slot at @mapping & @offset.  If there is a
  * page cache page, it is returned with an increased refcount.
  *
- * If the slot holds a shadow entry of a previously evicted page, it
- * is returned.
+ * If the slot holds a shadow entry of a previously evicted page, or a
+ * swap entry from shmem/tmpfs, it is returned.
  *
  * Otherwise, %NULL is returned.
  */
@@ -928,9 +928,9 @@ repeat:
 			if (radix_tree_deref_retry(page))
 				goto repeat;
 			/*
-			 * Otherwise, shmem/tmpfs must be storing a swap entry
-			 * here as an exceptional entry: so return it without
-			 * attempting to raise page count.
+			 * A shadow entry of a recently evicted page,
+			 * or a swap entry from shmem/tmpfs.  Return
+			 * it without attempting to raise page count.
 			 */
 			goto out;
 		}
@@ -983,8 +983,8 @@ EXPORT_SYMBOL(find_get_page);
  * page cache page, it is returned locked and with an increased
  * refcount.
  *
- * If the slot holds a shadow entry of a previously evicted page, it
- * is returned.
+ * If the slot holds a shadow entry of a previously evicted page, or a
+ * swap entry from shmem/tmpfs, it is returned.
  *
  * Otherwise, %NULL is returned.
  *
@@ -1099,8 +1099,8 @@ EXPORT_SYMBOL(find_or_create_page);
  * with ascending indexes.  There may be holes in the indices due to
  * not-present pages.
  *
- * Any shadow entries of evicted pages are included in the returned
- * array.
+ * Any shadow entries of evicted pages, or swap entries from
+ * shmem/tmpfs, are included in the returned array.
  *
  * find_get_entries() returns the number of pages and shadow entries
  * which were found.
@@ -1128,9 +1128,9 @@ repeat:
 			if (radix_tree_deref_retry(page))
 				goto restart;
 			/*
-			 * Otherwise, we must be storing a swap entry
-			 * here as an exceptional entry: so return it
-			 * without attempting to raise page count.
+			 * A shadow entry of a recently evicted page,
+			 * or a swap entry from shmem/tmpfs.  Return
+			 * it without attempting to raise page count.
 			 */
 			goto export;
 		}
@@ -1198,9 +1198,9 @@ repeat:
 				goto restart;
 			}
 			/*
-			 * Otherwise, shmem/tmpfs must be storing a swap entry
-			 * here as an exceptional entry: so skip over it -
-			 * we only reach this from invalidate_mapping_pages().
+			 * A shadow entry of a recently evicted page,
+			 * or a swap entry from shmem/tmpfs.  Skip
+			 * over it.
 			 */
 			continue;
 		}
@@ -1265,9 +1265,9 @@ repeat:
 				goto restart;
 			}
 			/*
-			 * Otherwise, shmem/tmpfs must be storing a swap entry
-			 * here as an exceptional entry: so stop looking for
-			 * contiguous pages.
+			 * A shadow entry of a recently evicted page,
+			 * or a swap entry from shmem/tmpfs.  Stop
+			 * looking for contiguous pages.
 			 */
 			break;
 		}
@@ -1341,10 +1341,17 @@ repeat:
 				goto restart;
 			}
 			/*
-			 * This function is never used on a shmem/tmpfs
-			 * mapping, so a swap entry won't be found here.
+			 * A shadow entry of a recently evicted page.
+			 *
+			 * Those entries should never be tagged, but
+			 * this tree walk is lockless and the tags are
+			 * looked up in bulk, one radix tree node at a
+			 * time, so there is a sizable window for page
+			 * reclaim to evict a page we saw tagged.
+			 *
+			 * Skip over it.
 			 */
-			BUG();
+			continue;
 		}
 
 		if (!page_cache_get_speculative(page))
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 2461929..c82290b 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1981,11 +1981,7 @@ static int __init hugetlb_init(void)
 {
 	int i;
 
-	/* Some platform decide whether they support huge pages at boot
-	 * time. On these, such as powerpc, HPAGE_SHIFT is set to 0 when
-	 * there is no such support
-	 */
-	if (HPAGE_SHIFT == 0)
+	if (!hugepages_supported())
 		return 0;
 
 	if (!size_to_hstate(default_hstate_size)) {
@@ -2112,6 +2108,9 @@ static int hugetlb_sysctl_handler_common(bool obey_mempolicy,
 	unsigned long tmp;
 	int ret;
 
+	if (!hugepages_supported())
+		return -ENOTSUPP;
+
 	tmp = h->max_huge_pages;
 
 	if (write && h->order >= MAX_ORDER)
@@ -2165,6 +2164,9 @@ int hugetlb_overcommit_handler(struct ctl_table *table, int write,
 	unsigned long tmp;
 	int ret;
 
+	if (!hugepages_supported())
+		return -ENOTSUPP;
+
 	tmp = h->nr_overcommit_huge_pages;
 
 	if (write && h->order >= MAX_ORDER)
@@ -2190,6 +2192,8 @@ out:
 void hugetlb_report_meminfo(struct seq_file *m)
 {
 	struct hstate *h = &default_hstate;
+	if (!hugepages_supported())
+		return;
 	seq_printf(m,
 			"HugePages_Total:   %5lu\n"
 			"HugePages_Free:    %5lu\n"
@@ -2206,6 +2210,8 @@ void hugetlb_report_meminfo(struct seq_file *m)
 int hugetlb_report_node_meminfo(int nid, char *buf)
 {
 	struct hstate *h = &default_hstate;
+	if (!hugepages_supported())
+		return 0;
 	return sprintf(buf,
 		"Node %d HugePages_Total: %5u\n"
 		"Node %d HugePages_Free:  %5u\n"
@@ -2220,6 +2226,9 @@ void hugetlb_show_meminfo(void)
 	struct hstate *h;
 	int nid;
 
+	if (!hugepages_supported())
+		return;
+
 	for_each_node_state(nid, N_MEMORY)
 		for_each_hstate(h)
 			pr_info("Node %d hugepages_total=%u hugepages_free=%u hugepages_surp=%u hugepages_size=%lukB\n",
diff --git a/mm/kmemleak.c b/mm/kmemleak.c
index 91d67ea..8d2fcdf 100644
--- a/mm/kmemleak.c
+++ b/mm/kmemleak.c
@@ -1775,10 +1775,9 @@ void __init kmemleak_init(void)
 	int i;
 	unsigned long flags;
 
-	kmemleak_early_log = 0;
-
 #ifdef CONFIG_DEBUG_KMEMLEAK_DEFAULT_OFF
 	if (!kmemleak_skip_disable) {
+		kmemleak_early_log = 0;
 		kmemleak_disable();
 		return;
 	}
@@ -1796,6 +1795,7 @@ void __init kmemleak_init(void)
 
 	/* the kernel is still in UP mode, so disabling the IRQs is enough */
 	local_irq_save(flags);
+	kmemleak_early_log = 0;
 	if (kmemleak_error) {
 		local_irq_restore(flags);
 		return;
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 29501f0..c47dffd 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -6686,16 +6686,20 @@ static struct page *mc_handle_file_pte(struct vm_area_struct *vma,
 		pgoff = pte_to_pgoff(ptent);
 
 	/* page is moved even if it's not RSS of this task(page-faulted). */
-	page = find_get_page(mapping, pgoff);
-
 #ifdef CONFIG_SWAP
 	/* shmem/tmpfs may report page out on swap: account for that too. */
-	if (radix_tree_exceptional_entry(page)) {
-		swp_entry_t swap = radix_to_swp_entry(page);
-		if (do_swap_account)
-			*entry = swap;
-		page = find_get_page(swap_address_space(swap), swap.val);
-	}
+	if (shmem_mapping(mapping)) {
+		page = find_get_entry(mapping, pgoff);
+		if (radix_tree_exceptional_entry(page)) {
+			swp_entry_t swp = radix_to_swp_entry(page);
+			if (do_swap_account)
+				*entry = swp;
+			page = find_get_page(swap_address_space(swp), swp.val);
+		}
+	} else
+		page = find_get_page(mapping, pgoff);
+#else
+	page = find_get_page(mapping, pgoff);
 #endif
 	return page;
 }
diff --git a/mm/mremap.c b/mm/mremap.c
index 0843feb..05f1180 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -194,10 +194,17 @@ unsigned long move_page_tables(struct vm_area_struct *vma,
 			break;
 		if (pmd_trans_huge(*old_pmd)) {
 			int err = 0;
-			if (extent == HPAGE_PMD_SIZE)
+			if (extent == HPAGE_PMD_SIZE) {
+				VM_BUG_ON(vma->vm_file || !vma->anon_vma);
+				/* See comment in move_ptes() */
+				if (need_rmap_locks)
+					anon_vma_lock_write(vma->anon_vma);
 				err = move_huge_pmd(vma, new_vma, old_addr,
 						    new_addr, old_end,
 						    old_pmd, new_pmd);
+				if (need_rmap_locks)
+					anon_vma_unlock_write(vma->anon_vma);
+			}
 			if (err > 0) {
 				need_flush = true;
 				continue;
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index ef41349..a4317da 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -593,14 +593,14 @@ unsigned long bdi_dirty_limit(struct backing_dev_info *bdi, unsigned long dirty)
  * (5) the closer to setpoint, the smaller |df/dx| (and the reverse)
  *     => fast response on large errors; small oscillation near setpoint
  */
-static inline long long pos_ratio_polynom(unsigned long setpoint,
+static long long pos_ratio_polynom(unsigned long setpoint,
 					  unsigned long dirty,
 					  unsigned long limit)
 {
 	long long pos_ratio;
 	long x;
 
-	x = div_s64(((s64)setpoint - (s64)dirty) << RATELIMIT_CALC_SHIFT,
+	x = div64_s64(((s64)setpoint - (s64)dirty) << RATELIMIT_CALC_SHIFT,
 		    limit - setpoint + 1);
 	pos_ratio = x;
 	pos_ratio = pos_ratio * x >> RATELIMIT_CALC_SHIFT;
@@ -842,7 +842,7 @@ static unsigned long bdi_position_ratio(struct backing_dev_info *bdi,
 	x_intercept = bdi_setpoint + span;
 
 	if (bdi_dirty < x_intercept - span / 4) {
-		pos_ratio = div_u64(pos_ratio * (x_intercept - bdi_dirty),
+		pos_ratio = div64_u64(pos_ratio * (x_intercept - bdi_dirty),
 				    x_intercept - bdi_setpoint + 1);
 	} else
 		pos_ratio /= 4;
diff --git a/mm/percpu.c b/mm/percpu.c
index 63e24fb..2ddf9a9 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -610,7 +610,7 @@ static struct pcpu_chunk *pcpu_alloc_chunk(void)
 	chunk->map = pcpu_mem_zalloc(PCPU_DFL_MAP_ALLOC *
 						sizeof(chunk->map[0]));
 	if (!chunk->map) {
-		kfree(chunk);
+		pcpu_mem_free(chunk, pcpu_chunk_struct_size);
 		return NULL;
 	}
 
diff --git a/mm/slab.c b/mm/slab.c
index 388cb1a..19d9218 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -166,7 +166,7 @@ typedef unsigned char freelist_idx_t;
 typedef unsigned short freelist_idx_t;
 #endif
 
-#define SLAB_OBJ_MAX_NUM (1 << sizeof(freelist_idx_t) * BITS_PER_BYTE)
+#define SLAB_OBJ_MAX_NUM ((1 << sizeof(freelist_idx_t) * BITS_PER_BYTE) - 1)
 
 /*
  * true if a page was allocated from pfmemalloc reserves for network-based
@@ -2572,13 +2572,13 @@ static void *alloc_slabmgmt(struct kmem_cache *cachep,
 	return freelist;
 }
 
-static inline freelist_idx_t get_free_obj(struct page *page, unsigned char idx)
+static inline freelist_idx_t get_free_obj(struct page *page, unsigned int idx)
 {
 	return ((freelist_idx_t *)page->freelist)[idx];
 }
 
 static inline void set_free_obj(struct page *page,
-					unsigned char idx, freelist_idx_t val)
+					unsigned int idx, freelist_idx_t val)
 {
 	((freelist_idx_t *)(page->freelist))[idx] = val;
 }
diff --git a/mm/slab.h b/mm/slab.h
index 3045316b..6bd4c35 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -91,6 +91,7 @@ __kmem_cache_alias(const char *name, size_t size, size_t align,
 #define CACHE_CREATE_MASK (SLAB_CORE_FLAGS | SLAB_DEBUG_FLAGS | SLAB_CACHE_FLAGS)
 
 int __kmem_cache_shutdown(struct kmem_cache *);
+void slab_kmem_cache_release(struct kmem_cache *);
 
 struct seq_file;
 struct file;
diff --git a/mm/slab_common.c b/mm/slab_common.c
index f3cfccf..102cc6f 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -323,6 +323,12 @@ static int kmem_cache_destroy_memcg_children(struct kmem_cache *s)
 }
 #endif /* CONFIG_MEMCG_KMEM */
 
+void slab_kmem_cache_release(struct kmem_cache *s)
+{
+	kfree(s->name);
+	kmem_cache_free(kmem_cache, s);
+}
+
 void kmem_cache_destroy(struct kmem_cache *s)
 {
 	get_online_cpus();
@@ -352,8 +358,11 @@ void kmem_cache_destroy(struct kmem_cache *s)
 		rcu_barrier();
 
 	memcg_free_cache_params(s);
-	kfree(s->name);
-	kmem_cache_free(kmem_cache, s);
+#ifdef SLAB_SUPPORTS_SYSFS
+	sysfs_slab_remove(s);
+#else
+	slab_kmem_cache_release(s);
+#endif
 	goto out_put_cpus;
 
 out_unlock:
diff --git a/mm/slub.c b/mm/slub.c
index 5e234f1..2b1ce69 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -210,14 +210,11 @@ enum track_item { TRACK_ALLOC, TRACK_FREE };
 #ifdef CONFIG_SYSFS
 static int sysfs_slab_add(struct kmem_cache *);
 static int sysfs_slab_alias(struct kmem_cache *, const char *);
-static void sysfs_slab_remove(struct kmem_cache *);
 static void memcg_propagate_slab_attrs(struct kmem_cache *s);
 #else
 static inline int sysfs_slab_add(struct kmem_cache *s) { return 0; }
 static inline int sysfs_slab_alias(struct kmem_cache *s, const char *p)
 							{ return 0; }
-static inline void sysfs_slab_remove(struct kmem_cache *s) { }
-
 static inline void memcg_propagate_slab_attrs(struct kmem_cache *s) { }
 #endif
 
@@ -3238,24 +3235,7 @@ static inline int kmem_cache_close(struct kmem_cache *s)
 
 int __kmem_cache_shutdown(struct kmem_cache *s)
 {
-	int rc = kmem_cache_close(s);
-
-	if (!rc) {
-		/*
-		 * Since slab_attr_store may take the slab_mutex, we should
-		 * release the lock while removing the sysfs entry in order to
-		 * avoid a deadlock. Because this is pretty much the last
-		 * operation we do and the lock will be released shortly after
-		 * that in slab_common.c, we could just move sysfs_slab_remove
-		 * to a later point in common code. We should do that when we
-		 * have a common sysfs framework for all allocators.
-		 */
-		mutex_unlock(&slab_mutex);
-		sysfs_slab_remove(s);
-		mutex_lock(&slab_mutex);
-	}
-
-	return rc;
+	return kmem_cache_close(s);
 }
 
 /********************************************************************
@@ -5071,15 +5051,18 @@ static void memcg_propagate_slab_attrs(struct kmem_cache *s)
 #ifdef CONFIG_MEMCG_KMEM
 	int i;
 	char *buffer = NULL;
+	struct kmem_cache *root_cache;
 
-	if (!is_root_cache(s))
+	if (is_root_cache(s))
 		return;
 
+	root_cache = s->memcg_params->root_cache;
+
 	/*
 	 * This mean this cache had no attribute written. Therefore, no point
 	 * in copying default values around
 	 */
-	if (!s->max_attr_size)
+	if (!root_cache->max_attr_size)
 		return;
 
 	for (i = 0; i < ARRAY_SIZE(slab_attrs); i++) {
@@ -5101,7 +5084,7 @@ static void memcg_propagate_slab_attrs(struct kmem_cache *s)
 		 */
 		if (buffer)
 			buf = buffer;
-		else if (s->max_attr_size < ARRAY_SIZE(mbuf))
+		else if (root_cache->max_attr_size < ARRAY_SIZE(mbuf))
 			buf = mbuf;
 		else {
 			buffer = (char *) get_zeroed_page(GFP_KERNEL);
@@ -5110,7 +5093,7 @@ static void memcg_propagate_slab_attrs(struct kmem_cache *s)
 			buf = buffer;
 		}
 
-		attr->show(s->memcg_params->root_cache, buf);
+		attr->show(root_cache, buf);
 		attr->store(s, buf, strlen(buf));
 	}
 
@@ -5119,6 +5102,11 @@ static void memcg_propagate_slab_attrs(struct kmem_cache *s)
 #endif
 }
 
+static void kmem_cache_release(struct kobject *k)
+{
+	slab_kmem_cache_release(to_slab(k));
+}
+
 static const struct sysfs_ops slab_sysfs_ops = {
 	.show = slab_attr_show,
 	.store = slab_attr_store,
@@ -5126,6 +5114,7 @@ static const struct sysfs_ops slab_sysfs_ops = {
 
 static struct kobj_type slab_ktype = {
 	.sysfs_ops = &slab_sysfs_ops,
+	.release = kmem_cache_release,
 };
 
 static int uevent_filter(struct kset *kset, struct kobject *kobj)
@@ -5252,7 +5241,7 @@ out_put_kobj:
 	goto out;
 }
 
-static void sysfs_slab_remove(struct kmem_cache *s)
+void sysfs_slab_remove(struct kmem_cache *s)
 {
 	if (slab_state < FULL)
 		/*
diff --git a/mm/truncate.c b/mm/truncate.c
index e5cc39a..6a78c81 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -484,14 +484,6 @@ unsigned long invalidate_mapping_pages(struct address_space *mapping,
 	unsigned long count = 0;
 	int i;
 
-	/*
-	 * Note: this function may get called on a shmem/tmpfs mapping:
-	 * pagevec_lookup() might then return 0 prematurely (because it
-	 * got a gangful of swap entries); but it's hardly worth worrying
-	 * about - it can rarely have anything to free from such a mapping
-	 * (most pages are dirty), and already skips over any difficulties.
-	 */
-
 	pagevec_init(&pvec, 0);
 	while (index <= end && pagevec_lookup_entries(&pvec, mapping, index,
 			min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1,
diff --git a/mm/util.c b/mm/util.c
index f380af7..d5ea733 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -10,6 +10,7 @@
 #include <linux/swapops.h>
 #include <linux/mman.h>
 #include <linux/hugetlb.h>
+#include <linux/vmalloc.h>
 
 #include <asm/uaccess.h>
 
@@ -387,6 +388,15 @@ unsigned long vm_mmap(struct file *file, unsigned long addr,
 }
 EXPORT_SYMBOL(vm_mmap);
 
+void kvfree(const void *addr)
+{
+	if (is_vmalloc_addr(addr))
+		vfree(addr);
+	else
+		kfree(addr);
+}
+EXPORT_SYMBOL(kvfree);
+
 struct address_space *page_mapping(struct page *page)
 {
 	struct address_space *mapping = page->mapping;
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 3f56c8d..32c661d 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1916,6 +1916,24 @@ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc,
 		get_lru_size(lruvec, LRU_INACTIVE_FILE);
 
 	/*
+	 * Prevent the reclaimer from falling into the cache trap: as
+	 * cache pages start out inactive, every cache fault will tip
+	 * the scan balance towards the file LRU.  And as the file LRU
+	 * shrinks, so does the window for rotation from references.
+	 * This means we have a runaway feedback loop where a tiny
+	 * thrashing file LRU becomes infinitely more attractive than
+	 * anon pages.  Try to detect this based on file LRU size.
+	 */
+	if (global_reclaim(sc)) {
+		unsigned long free = zone_page_state(zone, NR_FREE_PAGES);
+
+		if (unlikely(file + free <= high_wmark_pages(zone))) {
+			scan_balance = SCAN_ANON;
+			goto out;
+		}
+	}
+
+	/*
 	 * There is enough inactive page cache, do not reclaim
 	 * anything from the anonymous working set right now.
 	 */