Merge branch 'akpm' (patches from Andrew)

Merge more updates from Andrew Morton:
 "Subsystems affected by this patch series: mm/hotfixes, lz4, exec,
  mailmap, mm/thp, autofs, sysctl, mm/kmemleak, mm/misc and lib"

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (35 commits)
  virtio: pci: constify ioreadX() iomem argument (as in generic implementation)
  ntb: intel: constify ioreadX() iomem argument (as in generic implementation)
  rtl818x: constify ioreadX() iomem argument (as in generic implementation)
  iomap: constify ioreadX() iomem argument (as in generic implementation)
  sh: use generic strncpy()
  sh: clkfwk: remove r8/r16/r32
  include/asm-generic/vmlinux.lds.h: align ro_after_init
  mm: annotate a data race in page_zonenum()
  mm/swap.c: annotate data races for lru_rotate_pvecs
  mm/rmap: annotate a data race at tlb_flush_batched
  mm/mempool: fix a data race in mempool_free()
  mm/list_lru: fix a data race in list_lru_count_one
  mm/memcontrol: fix a data race in scan count
  mm/page_counter: fix various data races at memsw
  mm/swapfile: fix and annotate various data races
  mm/filemap.c: fix a data race in filemap_fault()
  mm/swap_state: mark various intentional data races
  mm/page_io: mark various intentional data races
  mm/frontswap: mark various intentional data races
  mm/kmemleak: silence KCSAN splats in checksum
  ...

11 files changed, 75 insertions, 28 deletions

diff --git a/include/linux/compat.h b/include/linux/compat.h
index c4255d8a4a8a..d38c4d7e83bd 100644
--- a/include/linux/compat.h
+++ b/include/linux/compat.h
@@ -851,7 +851,6 @@ asmlinkage long compat_sys_select(int n, compat_ulong_t __user *inp,
 asmlinkage long compat_sys_ustat(unsigned dev, struct compat_ustat __user *u32);
 asmlinkage long compat_sys_recv(int fd, void __user *buf, compat_size_t len,
 				unsigned flags);
-asmlinkage long compat_sys_sysctl(struct compat_sysctl_args __user *args);
 
 /* obsolete: fs/readdir.c */
 asmlinkage long compat_sys_old_readdir(unsigned int fd,
diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index 467302056e17..8a8bc46a2432 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -258,9 +258,36 @@ static inline spinlock_t *pud_trans_huge_lock(pud_t *pud,
 	else
 		return NULL;
 }
-static inline int hpage_nr_pages(struct page *page)
+
+/**
+ * thp_head - Head page of a transparent huge page.
+ * @page: Any page (tail, head or regular) found in the page cache.
+ */
+static inline struct page *thp_head(struct page *page)
+{
+	return compound_head(page);
+}
+
+/**
+ * thp_order - Order of a transparent huge page.
+ * @page: Head page of a transparent huge page.
+ */
+static inline unsigned int thp_order(struct page *page)
+{
+	VM_BUG_ON_PGFLAGS(PageTail(page), page);
+	if (PageHead(page))
+		return HPAGE_PMD_ORDER;
+	return 0;
+}
+
+/**
+ * thp_nr_pages - The number of regular pages in this huge page.
+ * @page: The head page of a huge page.
+ */
+static inline int thp_nr_pages(struct page *page)
 {
-	if (unlikely(PageTransHuge(page)))
+	VM_BUG_ON_PGFLAGS(PageTail(page), page);
+	if (PageHead(page))
 		return HPAGE_PMD_NR;
 	return 1;
 }
@@ -317,9 +344,21 @@ static inline struct list_head *page_deferred_list(struct page *page)
 #define HPAGE_PUD_MASK ({ BUILD_BUG(); 0; })
 #define HPAGE_PUD_SIZE ({ BUILD_BUG(); 0; })
 
-static inline int hpage_nr_pages(struct page *page)
+static inline struct page *thp_head(struct page *page)
 {
-	VM_BUG_ON_PAGE(PageTail(page), page);
+	VM_BUG_ON_PGFLAGS(PageTail(page), page);
+	return page;
+}
+
+static inline unsigned int thp_order(struct page *page)
+{
+	VM_BUG_ON_PGFLAGS(PageTail(page), page);
+	return 0;
+}
+
+static inline int thp_nr_pages(struct page *page)
+{
+	VM_BUG_ON_PGFLAGS(PageTail(page), page);
 	return 1;
 }
 
@@ -443,4 +482,15 @@ static inline bool thp_migration_supported(void)
 }
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
+/**
+ * thp_size - Size of a transparent huge page.
+ * @page: Head page of a transparent huge page.
+ *
+ * Return: Number of bytes in this page.
+ */
+static inline unsigned long thp_size(struct page *page)
+{
+	return PAGE_SIZE << thp_order(page);
+}
+
 #endif /* _LINUX_HUGE_MM_H */
diff --git a/include/linux/io-64-nonatomic-hi-lo.h b/include/linux/io-64-nonatomic-hi-lo.h
index ae21b72cce85..f32522bb3aa5 100644
--- a/include/linux/io-64-nonatomic-hi-lo.h
+++ b/include/linux/io-64-nonatomic-hi-lo.h
@@ -57,7 +57,7 @@ static inline void hi_lo_writeq_relaxed(__u64 val, volatile void __iomem *addr)
 
 #ifndef ioread64_hi_lo
 #define ioread64_hi_lo ioread64_hi_lo
-static inline u64 ioread64_hi_lo(void __iomem *addr)
+static inline u64 ioread64_hi_lo(const void __iomem *addr)
 {
 	u32 low, high;
 
@@ -79,7 +79,7 @@ static inline void iowrite64_hi_lo(u64 val, void __iomem *addr)
 
 #ifndef ioread64be_hi_lo
 #define ioread64be_hi_lo ioread64be_hi_lo
-static inline u64 ioread64be_hi_lo(void __iomem *addr)
+static inline u64 ioread64be_hi_lo(const void __iomem *addr)
 {
 	u32 low, high;
 
diff --git a/include/linux/io-64-nonatomic-lo-hi.h b/include/linux/io-64-nonatomic-lo-hi.h
index faaa842dbdb9..448a21435dba 100644
--- a/include/linux/io-64-nonatomic-lo-hi.h
+++ b/include/linux/io-64-nonatomic-lo-hi.h
@@ -57,7 +57,7 @@ static inline void lo_hi_writeq_relaxed(__u64 val, volatile void __iomem *addr)
 
 #ifndef ioread64_lo_hi
 #define ioread64_lo_hi ioread64_lo_hi
-static inline u64 ioread64_lo_hi(void __iomem *addr)
+static inline u64 ioread64_lo_hi(const void __iomem *addr)
 {
 	u32 low, high;
 
@@ -79,7 +79,7 @@ static inline void iowrite64_lo_hi(u64 val, void __iomem *addr)
 
 #ifndef ioread64be_lo_hi
 #define ioread64be_lo_hi ioread64be_lo_hi
-static inline u64 ioread64be_lo_hi(void __iomem *addr)
+static inline u64 ioread64be_lo_hi(const void __iomem *addr)
 {
 	u32 low, high;
 
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 385237e4cb44..d0b036123c6a 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -630,7 +630,7 @@ unsigned long mem_cgroup_get_zone_lru_size(struct lruvec *lruvec,
 	struct mem_cgroup_per_node *mz;
 
 	mz = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
-	return mz->lru_zone_size[zone_idx][lru];
+	return READ_ONCE(mz->lru_zone_size[zone_idx][lru]);
 }
 
 void mem_cgroup_handle_over_high(void);
diff --git a/include/linux/mm.h b/include/linux/mm.h
index e7602a3bcef1..1983e08f5906 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -24,6 +24,7 @@
 #include <linux/resource.h>
 #include <linux/page_ext.h>
 #include <linux/err.h>
+#include <linux/page-flags.h>
 #include <linux/page_ref.h>
 #include <linux/memremap.h>
 #include <linux/overflow.h>
@@ -668,11 +669,6 @@ int vma_is_stack_for_current(struct vm_area_struct *vma);
 struct mmu_gather;
 struct inode;
 
-/*
- * FIXME: take this include out, include page-flags.h in
- * files which need it (119 of them)
- */
-#include <linux/page-flags.h>
 #include <linux/huge_mm.h>
 
 /*
@@ -922,12 +918,15 @@ static inline int compound_pincount(struct page *page)
 static inline void set_compound_order(struct page *page, unsigned int order)
 {
 	page[1].compound_order = order;
+	page[1].compound_nr = 1U << order;
 }
 
 /* Returns the number of pages in this potentially compound page. */
 static inline unsigned long compound_nr(struct page *page)
 {
-	return 1UL << compound_order(page);
+	if (!PageHead(page))
+		return 1;
+	return page[1].compound_nr;
 }
 
 /* Returns the number of bytes in this potentially compound page. */
@@ -1068,6 +1067,7 @@ vm_fault_t finish_mkwrite_fault(struct vm_fault *vmf);
 
 static inline enum zone_type page_zonenum(const struct page *page)
 {
+	ASSERT_EXCLUSIVE_BITS(page->flags, ZONES_MASK << ZONES_PGSHIFT);
 	return (page->flags >> ZONES_PGSHIFT) & ZONES_MASK;
 }
 
@@ -1595,6 +1595,7 @@ static inline void clear_page_pfmemalloc(struct page *page)
 extern void pagefault_out_of_memory(void);
 
 #define offset_in_page(p)	((unsigned long)(p) & ~PAGE_MASK)
+#define offset_in_thp(page, p)	((unsigned long)(p) & (thp_size(page) - 1))
 
 /*
  * Flags passed to show_mem() and show_free_areas() to suppress output in
diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h
index 219bef41d87c..8fc71e9d7bb0 100644
--- a/include/linux/mm_inline.h
+++ b/include/linux/mm_inline.h
@@ -48,14 +48,14 @@ static __always_inline void update_lru_size(struct lruvec *lruvec,
 static __always_inline void add_page_to_lru_list(struct page *page,
 				struct lruvec *lruvec, enum lru_list lru)
 {
-	update_lru_size(lruvec, lru, page_zonenum(page), hpage_nr_pages(page));
+	update_lru_size(lruvec, lru, page_zonenum(page), thp_nr_pages(page));
 	list_add(&page->lru, &lruvec->lists[lru]);
 }
 
 static __always_inline void add_page_to_lru_list_tail(struct page *page,
 				struct lruvec *lruvec, enum lru_list lru)
 {
-	update_lru_size(lruvec, lru, page_zonenum(page), hpage_nr_pages(page));
+	update_lru_size(lruvec, lru, page_zonenum(page), thp_nr_pages(page));
 	list_add_tail(&page->lru, &lruvec->lists[lru]);
 }
 
@@ -63,7 +63,7 @@ static __always_inline void del_page_from_lru_list(struct page *page,
 				struct lruvec *lruvec, enum lru_list lru)
 {
 	list_del(&page->lru);
-	update_lru_size(lruvec, lru, page_zonenum(page), -hpage_nr_pages(page));
+	update_lru_size(lruvec, lru, page_zonenum(page), -thp_nr_pages(page));
 }
 
 /**
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 0277fbab7c93..496c3ff97cce 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -134,6 +134,7 @@ struct page {
 			unsigned char compound_dtor;
 			unsigned char compound_order;
 			atomic_t compound_mapcount;
+			unsigned int compound_nr; /* 1 << compound_order */
 		};
 		struct {	/* Second tail page of compound page */
 			unsigned long _compound_pad_1;	/* compound_head */
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index d1f4eff605ad..7de11dcd534d 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -381,7 +381,7 @@ static inline struct page *find_subpage(struct page *head, pgoff_t index)
 	if (PageHuge(head))
 		return head;
 
-	return head + (index & (hpage_nr_pages(head) - 1));
+	return head + (index & (thp_nr_pages(head) - 1));
 }
 
 struct page *find_get_entry(struct address_space *mapping, pgoff_t offset);
@@ -773,7 +773,7 @@ static inline struct page *readahead_page(struct readahead_control *rac)
 
 	page = xa_load(&rac->mapping->i_pages, rac->_index);
 	VM_BUG_ON_PAGE(!PageLocked(page), page);
-	rac->_batch_count = hpage_nr_pages(page);
+	rac->_batch_count = thp_nr_pages(page);
 
 	return page;
 }
@@ -796,7 +796,7 @@ static inline unsigned int __readahead_batch(struct readahead_control *rac,
 		VM_BUG_ON_PAGE(!PageLocked(page), page);
 		VM_BUG_ON_PAGE(PageTail(page), page);
 		array[i++] = page;
-		rac->_batch_count += hpage_nr_pages(page);
+		rac->_batch_count += thp_nr_pages(page);
 
 		/*
 		 * The page cache isn't using multi-index entries yet,
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index dc2b827c81e5..75ac7f8ae93c 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -47,7 +47,6 @@ struct stat64;
 struct statfs;
 struct statfs64;
 struct statx;
-struct __sysctl_args;
 struct sysinfo;
 struct timespec;
 struct __kernel_old_timeval;
@@ -1117,7 +1116,6 @@ asmlinkage long sys_send(int, void __user *, size_t, unsigned);
 asmlinkage long sys_bdflush(int func, long data);
 asmlinkage long sys_oldumount(char __user *name);
 asmlinkage long sys_uselib(const char __user *library);
-asmlinkage long sys_sysctl(struct __sysctl_args __user *args);
 asmlinkage long sys_sysfs(int option,
 				unsigned long arg1, unsigned long arg2);
 asmlinkage long sys_fork(void);
diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h
index 50bb7f383a1b..51298a4f4623 100644
--- a/include/linux/sysctl.h
+++ b/include/linux/sysctl.h
@@ -74,15 +74,13 @@ int proc_do_static_key(struct ctl_table *table, int write, void *buffer,
  * sysctl names can be mirrored automatically under /proc/sys.  The
  * procname supplied controls /proc naming.
  *
- * The table's mode will be honoured both for sys_sysctl(2) and
- * proc-fs access.
+ * The table's mode will be honoured for proc-fs access.
  *
  * Leaf nodes in the sysctl tree will be represented by a single file
  * under /proc; non-leaf nodes will be represented by directories.  A
  * null procname disables /proc mirroring at this node.
  *
- * sysctl(2) can automatically manage read and write requests through
- * the sysctl table.  The data and maxlen fields of the ctl_table
+ * The data and maxlen fields of the ctl_table
  * struct enable minimal validation of the values being written to be
  * performed, and the mode field allows minimal authentication.
  *