Merge branch 'akpm' (incoming from Andrew)

Merge more incoming from Andrew Morton:

 - Various fixes which were stalled or which I picked up recently

 - A large rotorooting of the AIO code.  Allegedly to improve
   performance but I don't really have good performance numbers (I might
   have lost the email) and I can't raise Kent today.  I held this out
   of 3.9 and we could give it another cycle if it's all too late/scary.

I ended up taking only the first two thirds of the AIO rotorooting.  I
left the percpu parts and the batch completion for later.  - Linus

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (33 commits)
  aio: don't include aio.h in sched.h
  aio: kill ki_retry
  aio: kill ki_key
  aio: give shared kioctx fields their own cachelines
  aio: kill struct aio_ring_info
  aio: kill batch allocation
  aio: change reqs_active to include unreaped completions
  aio: use cancellation list lazily
  aio: use flush_dcache_page()
  aio: make aio_read_evt() more efficient, convert to hrtimers
  wait: add wait_event_hrtimeout()
  aio: refcounting cleanup
  aio: make aio_put_req() lockless
  aio: do fget() after aio_get_req()
  aio: dprintk() -> pr_debug()
  aio: move private stuff out of aio.h
  aio: add kiocb_cancel()
  aio: kill return value of aio_complete()
  char: add aio_{read,write} to /dev/{null,zero}
  aio: remove retry-based AIO
  ...

7 files changed, 37 insertions, 14 deletions

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 0f1d92163f30..cb1c9dedf9b6 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -92,16 +92,18 @@ enum mem_cgroup_stat_index {
 	/*
 	 * For MEM_CONTAINER_TYPE_ALL, usage = pagecache + rss.
 	 */
-	MEM_CGROUP_STAT_CACHE, 	   /* # of pages charged as cache */
-	MEM_CGROUP_STAT_RSS,	   /* # of pages charged as anon rss */
-	MEM_CGROUP_STAT_FILE_MAPPED,  /* # of pages charged as file rss */
-	MEM_CGROUP_STAT_SWAP, /* # of pages, swapped out */
+	MEM_CGROUP_STAT_CACHE,		/* # of pages charged as cache */
+	MEM_CGROUP_STAT_RSS,		/* # of pages charged as anon rss */
+	MEM_CGROUP_STAT_RSS_HUGE,	/* # of pages charged as anon huge */
+	MEM_CGROUP_STAT_FILE_MAPPED,	/* # of pages charged as file rss */
+	MEM_CGROUP_STAT_SWAP,		/* # of pages, swapped out */
 	MEM_CGROUP_STAT_NSTATS,
 };
 
 static const char * const mem_cgroup_stat_names[] = {
 	"cache",
 	"rss",
+	"rss_huge",
 	"mapped_file",
 	"swap",
 };
@@ -917,6 +919,7 @@ static unsigned long mem_cgroup_read_events(struct mem_cgroup *memcg,
 }
 
 static void mem_cgroup_charge_statistics(struct mem_cgroup *memcg,
+					 struct page *page,
 					 bool anon, int nr_pages)
 {
 	preempt_disable();
@@ -932,6 +935,10 @@ static void mem_cgroup_charge_statistics(struct mem_cgroup *memcg,
 		__this_cpu_add(memcg->stat->count[MEM_CGROUP_STAT_CACHE],
 				nr_pages);
 
+	if (PageTransHuge(page))
+		__this_cpu_add(memcg->stat->count[MEM_CGROUP_STAT_RSS_HUGE],
+				nr_pages);
+
 	/* pagein of a big page is an event. So, ignore page size */
 	if (nr_pages > 0)
 		__this_cpu_inc(memcg->stat->events[MEM_CGROUP_EVENTS_PGPGIN]);
@@ -2914,7 +2921,7 @@ static void __mem_cgroup_commit_charge(struct mem_cgroup *memcg,
 	else
 		anon = false;
 
-	mem_cgroup_charge_statistics(memcg, anon, nr_pages);
+	mem_cgroup_charge_statistics(memcg, page, anon, nr_pages);
 	unlock_page_cgroup(pc);
 
 	/*
@@ -3708,16 +3715,21 @@ void mem_cgroup_split_huge_fixup(struct page *head)
 {
 	struct page_cgroup *head_pc = lookup_page_cgroup(head);
 	struct page_cgroup *pc;
+	struct mem_cgroup *memcg;
 	int i;
 
 	if (mem_cgroup_disabled())
 		return;
+
+	memcg = head_pc->mem_cgroup;
 	for (i = 1; i < HPAGE_PMD_NR; i++) {
 		pc = head_pc + i;
-		pc->mem_cgroup = head_pc->mem_cgroup;
+		pc->mem_cgroup = memcg;
 		smp_wmb();/* see __commit_charge() */
 		pc->flags = head_pc->flags & ~PCGF_NOCOPY_AT_SPLIT;
 	}
+	__this_cpu_sub(memcg->stat->count[MEM_CGROUP_STAT_RSS_HUGE],
+		       HPAGE_PMD_NR);
 }
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
@@ -3773,11 +3785,11 @@ static int mem_cgroup_move_account(struct page *page,
 		__this_cpu_inc(to->stat->count[MEM_CGROUP_STAT_FILE_MAPPED]);
 		preempt_enable();
 	}
-	mem_cgroup_charge_statistics(from, anon, -nr_pages);
+	mem_cgroup_charge_statistics(from, page, anon, -nr_pages);
 
 	/* caller should have done css_get */
 	pc->mem_cgroup = to;
-	mem_cgroup_charge_statistics(to, anon, nr_pages);
+	mem_cgroup_charge_statistics(to, page, anon, nr_pages);
 	move_unlock_mem_cgroup(from, &flags);
 	ret = 0;
 unlock:
@@ -4152,7 +4164,7 @@ __mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype,
 		break;
 	}
 
-	mem_cgroup_charge_statistics(memcg, anon, -nr_pages);
+	mem_cgroup_charge_statistics(memcg, page, anon, -nr_pages);
 
 	ClearPageCgroupUsed(pc);
 	/*
@@ -4502,7 +4514,7 @@ void mem_cgroup_replace_page_cache(struct page *oldpage,
 	lock_page_cgroup(pc);
 	if (PageCgroupUsed(pc)) {
 		memcg = pc->mem_cgroup;
-		mem_cgroup_charge_statistics(memcg, false, -1);
+		mem_cgroup_charge_statistics(memcg, oldpage, false, -1);
 		ClearPageCgroupUsed(pc);
 	}
 	unlock_page_cgroup(pc);
@@ -5030,6 +5042,10 @@ static inline u64 mem_cgroup_usage(struct mem_cgroup *memcg, bool swap)
 			return res_counter_read_u64(&memcg->memsw, RES_USAGE);
 	}
 
+	/*
+	 * Transparent hugepages are still accounted for in MEM_CGROUP_STAT_RSS
+	 * as well as in MEM_CGROUP_STAT_RSS_HUGE.
+	 */
 	val = mem_cgroup_recursive_stat(memcg, MEM_CGROUP_STAT_CACHE);
 	val += mem_cgroup_recursive_stat(memcg, MEM_CGROUP_STAT_RSS);
 
diff --git a/mm/mmap.c b/mm/mmap.c
index da3e9c04bf37..1ae21d645c68 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1363,15 +1363,20 @@ SYSCALL_DEFINE6(mmap_pgoff, unsigned long, addr, unsigned long, len,
 		file = fget(fd);
 		if (!file)
 			goto out;
+		if (is_file_hugepages(file))
+			len = ALIGN(len, huge_page_size(hstate_file(file)));
 	} else if (flags & MAP_HUGETLB) {
 		struct user_struct *user = NULL;
+
+		len = ALIGN(len, huge_page_size(hstate_sizelog(
+			(flags >> MAP_HUGE_SHIFT) & MAP_HUGE_MASK)));
 		/*
 		 * VM_NORESERVE is used because the reservations will be
 		 * taken when vm_ops->mmap() is called
 		 * A dummy user value is used because we are not locking
 		 * memory so no accounting is necessary
 		 */
-		file = hugetlb_file_setup(HUGETLB_ANON_FILE, addr, len,
+		file = hugetlb_file_setup(HUGETLB_ANON_FILE, len,
 				VM_NORESERVE,
 				&user, HUGETLB_ANONHUGE_INODE,
 				(flags >> MAP_HUGE_SHIFT) & MAP_HUGE_MASK);
diff --git a/mm/mmu_context.c b/mm/mmu_context.c
index 3dcfaf4ed355..8a8cd0265e52 100644
--- a/mm/mmu_context.c
+++ b/mm/mmu_context.c
@@ -14,9 +14,6 @@
  * use_mm
  *	Makes the calling kernel thread take on the specified
  *	mm context.
- *	Called by the retry thread execute retries within the
- *	iocb issuer's mm context, so that copy_from/to_user
- *	operations work seamlessly for aio.
  *	(Note: this routine is intended to be called only
  *	from a kernel thread context)
  */
diff --git a/mm/page_io.c b/mm/page_io.c
index bb5d75274686..06a8842a6ec6 100644
--- a/mm/page_io.c
+++ b/mm/page_io.c
@@ -20,6 +20,7 @@
 #include <linux/buffer_head.h>
 #include <linux/writeback.h>
 #include <linux/frontswap.h>
+#include <linux/aio.h>
 #include <asm/pgtable.h>
 
 static struct bio *get_swap_bio(gfp_t gfp_flags,
diff --git a/mm/shmem.c b/mm/shmem.c
index 39b2a0b86fe8..5e6a8422658b 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -31,6 +31,7 @@
 #include <linux/mm.h>
 #include <linux/export.h>
 #include <linux/swap.h>
+#include <linux/aio.h>
 
 static struct vfsmount *shm_mnt;
 
diff --git a/mm/swap.c b/mm/swap.c
index acd40bfffa82..dfd7d71d6841 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -30,6 +30,7 @@
 #include <linux/backing-dev.h>
 #include <linux/memcontrol.h>
 #include <linux/gfp.h>
+#include <linux/uio.h>
 
 #include "internal.h"
 
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index b12fd8612604..d365724feb05 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -1522,6 +1522,8 @@ static void __vunmap(const void *addr, int deallocate_pages)
  *	Must not be called in NMI context (strictly speaking, only if we don't
  *	have CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG, but making the calling
  *	conventions for vfree() arch-depenedent would be a really bad idea)
+ *
+ *	NOTE: assumes that the object at *addr has a size >= sizeof(llist_node)
  *	
  */
 void vfree(const void *addr)