Merge tag 'v3.14-rc5' into patchwork

Linux 3.14-rc5

* tag 'v3.14-rc5': (1117 commits)
  Linux 3.14-rc5
  drm/vmwgfx: avoid null pointer dereference at failure paths
  drm/vmwgfx: Make sure backing mobs are cleared when allocated. Update driver date.
  drm/vmwgfx: Remove some unused surface formats
  MAINTAINERS: add maintainer entry for Armada DRM driver
  arm64: Fix !CONFIG_SMP kernel build
  arm64: mm: Add double logical invert to pte accessors
  dm cache: fix truncation bug when mapping I/O to >2TB fast device
  perf tools: Fix strict alias issue for find_first_bit
  powerpc/powernv: Fix indirect XSCOM unmangling
  powerpc/powernv: Fix opal_xscom_{read,write} prototype
  powerpc/powernv: Refactor PHB diag-data dump
  powerpc/powernv: Dump PHB diag-data immediately
  powerpc: Increase stack redzone for 64-bit userspace to 512 bytes
  powerpc/ftrace: bugfix for test_24bit_addr
  powerpc/crashdump : Fix page frame number check in copy_oldmem_page
  powerpc/le: Ensure that the 'stop-self' RTAS token is handled correctly
  kvm, vmx: Really fix lazy FPU on nested guest
  perf tools: fix BFD detection on opensuse
  drm/radeon: enable speaker allocation setup on dce3.2
  ...

12 files changed, 128 insertions, 68 deletions

diff --git a/mm/filemap.c b/mm/filemap.c
index d56d3c1..7a13f6a 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -2553,8 +2553,8 @@ ssize_t generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
 	if (ret > 0) {
 		ssize_t err;
 
-		err = generic_write_sync(file, pos, ret);
-		if (err < 0 && ret > 0)
+		err = generic_write_sync(file, iocb->ki_pos - ret, ret);
+		if (err < 0)
 			ret = err;
 	}
 	return ret;
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 82166bf..4df39b1 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1166,8 +1166,10 @@ alloc:
 		} else {
 			ret = do_huge_pmd_wp_page_fallback(mm, vma, address,
 					pmd, orig_pmd, page, haddr);
-			if (ret & VM_FAULT_OOM)
+			if (ret & VM_FAULT_OOM) {
 				split_huge_page(page);
+				ret |= VM_FAULT_FALLBACK;
+			}
 			put_page(page);
 		}
 		count_vm_event(THP_FAULT_FALLBACK);
@@ -1179,9 +1181,10 @@ alloc:
 		if (page) {
 			split_huge_page(page);
 			put_page(page);
-		}
+		} else
+			split_huge_page_pmd(vma, address, pmd);
+		ret |= VM_FAULT_FALLBACK;
 		count_vm_event(THP_FAULT_FALLBACK);
-		ret |= VM_FAULT_OOM;
 		goto out;
 	}
 
@@ -1545,6 +1548,7 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
 				entry = pmd_mknonnuma(entry);
 			entry = pmd_modify(entry, newprot);
 			ret = HPAGE_PMD_NR;
+			set_pmd_at(mm, addr, pmd, entry);
 			BUG_ON(pmd_write(entry));
 		} else {
 			struct page *page = pmd_page(*pmd);
@@ -1557,16 +1561,10 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
 			 */
 			if (!is_huge_zero_page(page) &&
 			    !pmd_numa(*pmd)) {
-				entry = *pmd;
-				entry = pmd_mknuma(entry);
+				pmdp_set_numa(mm, addr, pmd);
 				ret = HPAGE_PMD_NR;
 			}
 		}
-
-		/* Set PMD if cleared earlier */
-		if (ret == HPAGE_PMD_NR)
-			set_pmd_at(mm, addr, pmd, entry);
-
 		spin_unlock(ptl);
 	}
 
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 53385cd..ce7a8cc 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1687,7 +1687,7 @@ void mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p)
 	 * protects memcg_name and makes sure that parallel ooms do not
 	 * interleave
 	 */
-	static DEFINE_SPINLOCK(oom_info_lock);
+	static DEFINE_MUTEX(oom_info_lock);
 	struct cgroup *task_cgrp;
 	struct cgroup *mem_cgrp;
 	static char memcg_name[PATH_MAX];
@@ -1698,7 +1698,7 @@ void mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p)
 	if (!p)
 		return;
 
-	spin_lock(&oom_info_lock);
+	mutex_lock(&oom_info_lock);
 	rcu_read_lock();
 
 	mem_cgrp = memcg->css.cgroup;
@@ -1767,7 +1767,7 @@ done:
 
 		pr_cont("\n");
 	}
-	spin_unlock(&oom_info_lock);
+	mutex_unlock(&oom_info_lock);
 }
 
 /*
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 4f08a2d..2f2f34a 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -945,8 +945,10 @@ static int hwpoison_user_mappings(struct page *p, unsigned long pfn,
 			 * to it. Similarly, page lock is shifted.
 			 */
 			if (hpage != p) {
-				put_page(hpage);
-				get_page(p);
+				if (!(flags & MF_COUNT_INCREASED)) {
+					put_page(hpage);
+					get_page(p);
+				}
 				lock_page(p);
 				unlock_page(hpage);
 				*hpagep = p;
diff --git a/mm/memory.c b/mm/memory.c
index be6a0c0..22dfa61 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3348,6 +3348,7 @@ static int __do_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 		if (ret & VM_FAULT_LOCKED)
 			unlock_page(vmf.page);
 		ret = VM_FAULT_HWPOISON;
+		page_cache_release(vmf.page);
 		goto uncharge_out;
 	}
 
@@ -3703,7 +3704,6 @@ static int __handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	if (unlikely(is_vm_hugetlb_page(vma)))
 		return hugetlb_fault(mm, vma, address, flags);
 
-retry:
 	pgd = pgd_offset(mm, address);
 	pud = pud_alloc(mm, pgd, address);
 	if (!pud)
@@ -3741,20 +3741,13 @@ retry:
 			if (dirty && !pmd_write(orig_pmd)) {
 				ret = do_huge_pmd_wp_page(mm, vma, address, pmd,
 							  orig_pmd);
-				/*
-				 * If COW results in an oom, the huge pmd will
-				 * have been split, so retry the fault on the
-				 * pte for a smaller charge.
-				 */
-				if (unlikely(ret & VM_FAULT_OOM))
-					goto retry;
-				return ret;
+				if (!(ret & VM_FAULT_FALLBACK))
+					return ret;
 			} else {
 				huge_pmd_set_accessed(mm, vma, address, pmd,
 						      orig_pmd, dirty);
+				return 0;
 			}
-
-			return 0;
 		}
 	}
 
diff --git a/mm/mprotect.c b/mm/mprotect.c
index 7332c17..769a67a 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -58,36 +58,27 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 				if (pte_numa(ptent))
 					ptent = pte_mknonnuma(ptent);
 				ptent = pte_modify(ptent, newprot);
+				/*
+				 * Avoid taking write faults for pages we
+				 * know to be dirty.
+				 */
+				if (dirty_accountable && pte_dirty(ptent))
+					ptent = pte_mkwrite(ptent);
+				ptep_modify_prot_commit(mm, addr, pte, ptent);
 				updated = true;
 			} else {
 				struct page *page;
 
-				ptent = *pte;
 				page = vm_normal_page(vma, addr, oldpte);
 				if (page && !PageKsm(page)) {
 					if (!pte_numa(oldpte)) {
-						ptent = pte_mknuma(ptent);
-						set_pte_at(mm, addr, pte, ptent);
+						ptep_set_numa(mm, addr, pte);
 						updated = true;
 					}
 				}
 			}
-
-			/*
-			 * Avoid taking write faults for pages we know to be
-			 * dirty.
-			 */
-			if (dirty_accountable && pte_dirty(ptent)) {
-				ptent = pte_mkwrite(ptent);
-				updated = true;
-			}
-
 			if (updated)
 				pages++;
-
-			/* Only !prot_numa always clears the pte */
-			if (!prot_numa)
-				ptep_modify_prot_commit(mm, addr, pte, ptent);
 		} else if (IS_ENABLED(CONFIG_MIGRATION) && !pte_file(oldpte)) {
 			swp_entry_t entry = pte_to_swp_entry(oldpte);
 
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 2d30e2c..7106cb1 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -2173,11 +2173,12 @@ int __set_page_dirty_nobuffers(struct page *page)
 	if (!TestSetPageDirty(page)) {
 		struct address_space *mapping = page_mapping(page);
 		struct address_space *mapping2;
+		unsigned long flags;
 
 		if (!mapping)
 			return 1;
 
-		spin_lock_irq(&mapping->tree_lock);
+		spin_lock_irqsave(&mapping->tree_lock, flags);
 		mapping2 = page_mapping(page);
 		if (mapping2) { /* Race with truncate? */
 			BUG_ON(mapping2 != mapping);
@@ -2186,7 +2187,7 @@ int __set_page_dirty_nobuffers(struct page *page)
 			radix_tree_tag_set(&mapping->page_tree,
 				page_index(page), PAGECACHE_TAG_DIRTY);
 		}
-		spin_unlock_irq(&mapping->tree_lock);
+		spin_unlock_irqrestore(&mapping->tree_lock, flags);
 		if (mapping->host) {
 			/* !PageAnon && !swapper_space */
 			__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
diff --git a/mm/slub.c b/mm/slub.c
index 7e3e045..25f14ad 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -1004,21 +1004,19 @@ static inline void slab_free_hook(struct kmem_cache *s, void *x)
 static void add_full(struct kmem_cache *s,
 	struct kmem_cache_node *n, struct page *page)
 {
-	lockdep_assert_held(&n->list_lock);
-
 	if (!(s->flags & SLAB_STORE_USER))
 		return;
 
+	lockdep_assert_held(&n->list_lock);
 	list_add(&page->lru, &n->full);
 }
 
 static void remove_full(struct kmem_cache *s, struct kmem_cache_node *n, struct page *page)
 {
-	lockdep_assert_held(&n->list_lock);
-
 	if (!(s->flags & SLAB_STORE_USER))
 		return;
 
+	lockdep_assert_held(&n->list_lock);
 	list_del(&page->lru);
 }
 
@@ -1520,11 +1518,9 @@ static void discard_slab(struct kmem_cache *s, struct page *page)
 /*
  * Management of partially allocated slabs.
  */
-static inline void add_partial(struct kmem_cache_node *n,
-				struct page *page, int tail)
+static inline void
+__add_partial(struct kmem_cache_node *n, struct page *page, int tail)
 {
-	lockdep_assert_held(&n->list_lock);
-
 	n->nr_partial++;
 	if (tail == DEACTIVATE_TO_TAIL)
 		list_add_tail(&page->lru, &n->partial);
@@ -1532,15 +1528,27 @@ static inline void add_partial(struct kmem_cache_node *n,
 		list_add(&page->lru, &n->partial);
 }
 
-static inline void remove_partial(struct kmem_cache_node *n,
-					struct page *page)
+static inline void add_partial(struct kmem_cache_node *n,
+				struct page *page, int tail)
 {
 	lockdep_assert_held(&n->list_lock);
+	__add_partial(n, page, tail);
+}
 
+static inline void
+__remove_partial(struct kmem_cache_node *n, struct page *page)
+{
 	list_del(&page->lru);
 	n->nr_partial--;
 }
 
+static inline void remove_partial(struct kmem_cache_node *n,
+					struct page *page)
+{
+	lockdep_assert_held(&n->list_lock);
+	__remove_partial(n, page);
+}
+
 /*
  * Remove slab from the partial list, freeze it and
  * return the pointer to the freelist.
@@ -2906,12 +2914,10 @@ static void early_kmem_cache_node_alloc(int node)
 	inc_slabs_node(kmem_cache_node, node, page->objects);
 
 	/*
-	 * the lock is for lockdep's sake, not for any actual
-	 * race protection
+	 * No locks need to be taken here as it has just been
+	 * initialized and there is no concurrent access.
 	 */
-	spin_lock(&n->list_lock);
-	add_partial(n, page, DEACTIVATE_TO_HEAD);
-	spin_unlock(&n->list_lock);
+	__add_partial(n, page, DEACTIVATE_TO_HEAD);
 }
 
 static void free_kmem_cache_nodes(struct kmem_cache *s)
@@ -3197,7 +3203,7 @@ static void free_partial(struct kmem_cache *s, struct kmem_cache_node *n)
 
 	list_for_each_entry_safe(page, h, &n->partial, lru) {
 		if (!page->inuse) {
-			remove_partial(n, page);
+			__remove_partial(n, page);
 			discard_slab(s, page);
 		} else {
 			list_slab_objects(s, page,
diff --git a/mm/swap_state.c b/mm/swap_state.c
index 98e85e9..e76ace3 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -63,6 +63,8 @@ unsigned long total_swapcache_pages(void)
 	return ret;
 }
 
+static atomic_t swapin_readahead_hits = ATOMIC_INIT(4);
+
 void show_swap_cache_info(void)
 {
 	printk("%lu pages in swap cache\n", total_swapcache_pages());
@@ -286,8 +288,11 @@ struct page * lookup_swap_cache(swp_entry_t entry)
 
 	page = find_get_page(swap_address_space(entry), entry.val);
 
-	if (page)
+	if (page) {
 		INC_CACHE_INFO(find_success);
+		if (TestClearPageReadahead(page))
+			atomic_inc(&swapin_readahead_hits);
+	}
 
 	INC_CACHE_INFO(find_total);
 	return page;
@@ -389,6 +394,50 @@ struct page *read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
 	return found_page;
 }
 
+static unsigned long swapin_nr_pages(unsigned long offset)
+{
+	static unsigned long prev_offset;
+	unsigned int pages, max_pages, last_ra;
+	static atomic_t last_readahead_pages;
+
+	max_pages = 1 << ACCESS_ONCE(page_cluster);
+	if (max_pages <= 1)
+		return 1;
+
+	/*
+	 * This heuristic has been found to work well on both sequential and
+	 * random loads, swapping to hard disk or to SSD: please don't ask
+	 * what the "+ 2" means, it just happens to work well, that's all.
+	 */
+	pages = atomic_xchg(&swapin_readahead_hits, 0) + 2;
+	if (pages == 2) {
+		/*
+		 * We can have no readahead hits to judge by: but must not get
+		 * stuck here forever, so check for an adjacent offset instead
+		 * (and don't even bother to check whether swap type is same).
+		 */
+		if (offset != prev_offset + 1 && offset != prev_offset - 1)
+			pages = 1;
+		prev_offset = offset;
+	} else {
+		unsigned int roundup = 4;
+		while (roundup < pages)
+			roundup <<= 1;
+		pages = roundup;
+	}
+
+	if (pages > max_pages)
+		pages = max_pages;
+
+	/* Don't shrink readahead too fast */
+	last_ra = atomic_read(&last_readahead_pages) / 2;
+	if (pages < last_ra)
+		pages = last_ra;
+	atomic_set(&last_readahead_pages, pages);
+
+	return pages;
+}
+
 /**
  * swapin_readahead - swap in pages in hope we need them soon
  * @entry: swap entry of this memory
@@ -412,11 +461,16 @@ struct page *swapin_readahead(swp_entry_t entry, gfp_t gfp_mask,
 			struct vm_area_struct *vma, unsigned long addr)
 {
 	struct page *page;
-	unsigned long offset = swp_offset(entry);
+	unsigned long entry_offset = swp_offset(entry);
+	unsigned long offset = entry_offset;
 	unsigned long start_offset, end_offset;
-	unsigned long mask = (1UL << page_cluster) - 1;
+	unsigned long mask;
 	struct blk_plug plug;
 
+	mask = swapin_nr_pages(offset) - 1;
+	if (!mask)
+		goto skip;
+
 	/* Read a page_cluster sized and aligned cluster around offset. */
 	start_offset = offset & ~mask;
 	end_offset = offset | mask;
@@ -430,10 +484,13 @@ struct page *swapin_readahead(swp_entry_t entry, gfp_t gfp_mask,
 						gfp_mask, vma, addr);
 		if (!page)
 			continue;
+		if (offset != entry_offset)
+			SetPageReadahead(page);
 		page_cache_release(page);
 	}
 	blk_finish_plug(&plug);
 
 	lru_add_drain();	/* Push any new pages onto the LRU now */
+skip:
 	return read_swap_cache_async(entry, gfp_mask, vma, addr);
 }
diff --git a/mm/swapfile.c b/mm/swapfile.c
index c6c13b05..4a7f7e6 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -1923,7 +1923,6 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
 	p->swap_map = NULL;
 	cluster_info = p->cluster_info;
 	p->cluster_info = NULL;
-	p->flags = 0;
 	frontswap_map = frontswap_map_get(p);
 	spin_unlock(&p->lock);
 	spin_unlock(&swap_lock);
@@ -1949,6 +1948,16 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
 		mutex_unlock(&inode->i_mutex);
 	}
 	filp_close(swap_file, NULL);
+
+	/*
+	 * Clear the SWP_USED flag after all resources are freed so that swapon
+	 * can reuse this swap_info in alloc_swap_info() safely.  It is ok to
+	 * not hold p->lock after we cleared its SWP_WRITEOK.
+	 */
+	spin_lock(&swap_lock);
+	p->flags = 0;
+	spin_unlock(&swap_lock);
+
 	err = 0;
 	atomic_inc(&proc_poll_event);
 	wake_up_interruptible(&proc_poll_wait);
diff --git a/mm/vmpressure.c b/mm/vmpressure.c
index 196970a..d4042e7 100644
--- a/mm/vmpressure.c
+++ b/mm/vmpressure.c
@@ -19,6 +19,7 @@
 #include <linux/mm.h>
 #include <linux/vmstat.h>
 #include <linux/eventfd.h>
+#include <linux/slab.h>
 #include <linux/swap.h>
 #include <linux/printk.h>
 #include <linux/vmpressure.h>
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 7249614..def5dd2 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -851,12 +851,14 @@ const char * const vmstat_text[] = {
 	"thp_zero_page_alloc",
 	"thp_zero_page_alloc_failed",
 #endif
+#ifdef CONFIG_DEBUG_TLBFLUSH
 #ifdef CONFIG_SMP
 	"nr_tlb_remote_flush",
 	"nr_tlb_remote_flush_received",
-#endif
+#endif /* CONFIG_SMP */
 	"nr_tlb_local_flush_all",
 	"nr_tlb_local_flush_one",
+#endif /* CONFIG_DEBUG_TLBFLUSH */
 
 #endif /* CONFIG_VM_EVENTS_COUNTERS */
 };