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
  ...

89 files changed, 900 insertions, 1364 deletions

diff --git a/Documentation/cgroups/memory.txt b/Documentation/cgroups/memory.txt
index 09027a9fece..ddf4f93967a 100644
--- a/Documentation/cgroups/memory.txt
+++ b/Documentation/cgroups/memory.txt
@@ -480,7 +480,9 @@ memory.stat file includes following statistics
 
 # per-memory cgroup local status
 cache		- # of bytes of page cache memory.
-rss		- # of bytes of anonymous and swap cache memory.
+rss		- # of bytes of anonymous and swap cache memory (includes
+		transparent hugepages).
+rss_huge	- # of bytes of anonymous transparent hugepages.
 mapped_file	- # of bytes of mapped file (includes tmpfs/shmem)
 pgpgin		- # of charging events to the memory cgroup. The charging
 		event happens each time a page is accounted as either mapped
diff --git a/arch/s390/hypfs/inode.c b/arch/s390/hypfs/inode.c
index 5f7d7ba2874..7a539f4f5e3 100644
--- a/arch/s390/hypfs/inode.c
+++ b/arch/s390/hypfs/inode.c
@@ -21,6 +21,7 @@
 #include <linux/module.h>
 #include <linux/seq_file.h>
 #include <linux/mount.h>
+#include <linux/aio.h>
 #include <asm/ebcdic.h>
 #include "hypfs.h"
 
diff --git a/arch/sparc/kernel/leon_smp.c b/arch/sparc/kernel/leon_smp.c
index 9b40c9c12a0..6cfc1b09ec2 100644
--- a/arch/sparc/kernel/leon_smp.c
+++ b/arch/sparc/kernel/leon_smp.c
@@ -253,24 +253,15 @@ void __init leon_smp_done(void)
 
 	/* Free unneeded trap tables */
 	if (!cpu_present(1)) {
-		ClearPageReserved(virt_to_page(&trapbase_cpu1));
-		init_page_count(virt_to_page(&trapbase_cpu1));
-		free_page((unsigned long)&trapbase_cpu1);
-		totalram_pages++;
+		free_reserved_page(virt_to_page(&trapbase_cpu1));
 		num_physpages++;
 	}
 	if (!cpu_present(2)) {
-		ClearPageReserved(virt_to_page(&trapbase_cpu2));
-		init_page_count(virt_to_page(&trapbase_cpu2));
-		free_page((unsigned long)&trapbase_cpu2);
-		totalram_pages++;
+		free_reserved_page(virt_to_page(&trapbase_cpu2));
 		num_physpages++;
 	}
 	if (!cpu_present(3)) {
-		ClearPageReserved(virt_to_page(&trapbase_cpu3));
-		init_page_count(virt_to_page(&trapbase_cpu3));
-		free_page((unsigned long)&trapbase_cpu3);
-		totalram_pages++;
+		free_reserved_page(virt_to_page(&trapbase_cpu3));
 		num_physpages++;
 	}
 	/* Ok, they are spinning and ready to go. */
diff --git a/arch/sparc/mm/init_32.c b/arch/sparc/mm/init_32.c
index 4490c397bb5..af472cf7c69 100644
--- a/arch/sparc/mm/init_32.c
+++ b/arch/sparc/mm/init_32.c
@@ -366,45 +366,14 @@ void __init mem_init(void)
 
 void free_initmem (void)
 {
-	unsigned long addr;
-	unsigned long freed;
-
-	addr = (unsigned long)(&__init_begin);
-	freed = (unsigned long)(&__init_end) - addr;
-	for (; addr < (unsigned long)(&__init_end); addr += PAGE_SIZE) {
-		struct page *p;
-
-		memset((void *)addr, POISON_FREE_INITMEM, PAGE_SIZE);
-		p = virt_to_page(addr);
-
-		ClearPageReserved(p);
-		init_page_count(p);
-		__free_page(p);
-		totalram_pages++;
-		num_physpages++;
-	}
-	printk(KERN_INFO "Freeing unused kernel memory: %ldk freed\n",
-		freed >> 10);
+	num_physpages += free_initmem_default(POISON_FREE_INITMEM);
 }
 
 #ifdef CONFIG_BLK_DEV_INITRD
 void free_initrd_mem(unsigned long start, unsigned long end)
 {
-	if (start < end)
-		printk(KERN_INFO "Freeing initrd memory: %ldk freed\n",
-			(end - start) >> 10);
-	for (; start < end; start += PAGE_SIZE) {
-		struct page *p;
-
-		memset((void *)start, POISON_FREE_INITMEM, PAGE_SIZE);
-		p = virt_to_page(start);
-
-		ClearPageReserved(p);
-		init_page_count(p);
-		__free_page(p);
-		totalram_pages++;
-		num_physpages++;
-	}
+	num_physpages += free_reserved_area(start, end, POISON_FREE_INITMEM,
+					    "initrd");
 }
 #endif
 
diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c
index cf72a8a5b3a..a7171997adf 100644
--- a/arch/sparc/mm/init_64.c
+++ b/arch/sparc/mm/init_64.c
@@ -2059,8 +2059,7 @@ void __init mem_init(void)
 	/* We subtract one to account for the mem_map_zero page
 	 * allocated below.
 	 */
-	totalram_pages -= 1;
-	num_physpages = totalram_pages;
+	num_physpages = totalram_pages - 1;
 
 	/*
 	 * Set up the zero page, mark it reserved, so that page count
@@ -2071,7 +2070,7 @@ void __init mem_init(void)
 		prom_printf("paging_init: Cannot alloc zero page.\n");
 		prom_halt();
 	}
-	SetPageReserved(mem_map_zero);
+	mark_page_reserved(mem_map_zero);
 
 	codepages = (((unsigned long) _etext) - ((unsigned long) _start));
 	codepages = PAGE_ALIGN(codepages) >> PAGE_SHIFT;
@@ -2111,37 +2110,22 @@ void free_initmem(void)
 	initend = (unsigned long)(__init_end) & PAGE_MASK;
 	for (; addr < initend; addr += PAGE_SIZE) {
 		unsigned long page;
-		struct page *p;
 
 		page = (addr +
 			((unsigned long) __va(kern_base)) -
 			((unsigned long) KERNBASE));
 		memset((void *)addr, POISON_FREE_INITMEM, PAGE_SIZE);
 
-		if (do_free) {
-			p = virt_to_page(page);
-
-			ClearPageReserved(p);
-			init_page_count(p);
-			__free_page(p);
-			totalram_pages++;
-		}
+		if (do_free)
+			free_reserved_page(virt_to_page(page));
 	}
 }
 
 #ifdef CONFIG_BLK_DEV_INITRD
 void free_initrd_mem(unsigned long start, unsigned long end)
 {
-	if (start < end)
-		printk ("Freeing initrd memory: %ldk freed\n", (end - start) >> 10);
-	for (; start < end; start += PAGE_SIZE) {
-		struct page *p = virt_to_page(start);
-
-		ClearPageReserved(p);
-		init_page_count(p);
-		__free_page(p);
-		totalram_pages++;
-	}
+	num_physpages += free_reserved_area(start, end, POISON_FREE_INITMEM,
+					    "initrd");
 }
 #endif
 
diff --git a/block/scsi_ioctl.c b/block/scsi_ioctl.c
index 9a87daa6f4f..a5ffcc988f0 100644
--- a/block/scsi_ioctl.c
+++ b/block/scsi_ioctl.c
@@ -27,6 +27,7 @@
 #include <linux/ratelimit.h>
 #include <linux/slab.h>
 #include <linux/times.h>
+#include <linux/uio.h>
 #include <asm/uaccess.h>
 
 #include <scsi/scsi.h>
diff --git a/drivers/char/mem.c b/drivers/char/mem.c
index 2c644afbcdd..1ccbe9482fa 100644
--- a/drivers/char/mem.c
+++ b/drivers/char/mem.c
@@ -28,6 +28,7 @@
 #include <linux/pfn.h>
 #include <linux/export.h>
 #include <linux/io.h>
+#include <linux/aio.h>
 
 #include <asm/uaccess.h>
 
@@ -627,6 +628,18 @@ static ssize_t write_null(struct file *file, const char __user *buf,
 	return count;
 }
 
+static ssize_t aio_read_null(struct kiocb *iocb, const struct iovec *iov,
+			     unsigned long nr_segs, loff_t pos)
+{
+	return 0;
+}
+
+static ssize_t aio_write_null(struct kiocb *iocb, const struct iovec *iov,
+			      unsigned long nr_segs, loff_t pos)
+{
+	return iov_length(iov, nr_segs);
+}
+
 static int pipe_to_null(struct pipe_inode_info *info, struct pipe_buffer *buf,
 			struct splice_desc *sd)
 {
@@ -670,6 +683,24 @@ static ssize_t read_zero(struct file *file, char __user *buf,
 	return written ? written : -EFAULT;
 }
 
+static ssize_t aio_read_zero(struct kiocb *iocb, const struct iovec *iov,
+			     unsigned long nr_segs, loff_t pos)
+{
+	size_t written = 0;
+	unsigned long i;
+	ssize_t ret;
+
+	for (i = 0; i < nr_segs; i++) {
+		ret = read_zero(iocb->ki_filp, iov[i].iov_base, iov[i].iov_len,
+				&pos);
+		if (ret < 0)
+			break;
+		written += ret;
+	}
+
+	return written ? written : -EFAULT;
+}
+
 static int mmap_zero(struct file *file, struct vm_area_struct *vma)
 {
 #ifndef CONFIG_MMU
@@ -738,6 +769,7 @@ static int open_port(struct inode *inode, struct file *filp)
 #define full_lseek      null_lseek
 #define write_zero	write_null
 #define read_full       read_zero
+#define aio_write_zero	aio_write_null
 #define open_mem	open_port
 #define open_kmem	open_mem
 #define open_oldmem	open_mem
@@ -766,6 +798,8 @@ static const struct file_operations null_fops = {
 	.llseek		= null_lseek,
 	.read		= read_null,
 	.write		= write_null,
+	.aio_read	= aio_read_null,
+	.aio_write	= aio_write_null,
 	.splice_write	= splice_write_null,
 };
 
@@ -782,6 +816,8 @@ static const struct file_operations zero_fops = {
 	.llseek		= zero_lseek,
 	.read		= read_zero,
 	.write		= write_zero,
+	.aio_read	= aio_read_zero,
+	.aio_write	= aio_write_zero,
 	.mmap		= mmap_zero,
 };
 
diff --git a/drivers/infiniband/hw/cxgb3/cxio_resource.c b/drivers/infiniband/hw/cxgb3/cxio_resource.c
index 31f9201b298..c40088ecf9f 100644
--- a/drivers/infiniband/hw/cxgb3/cxio_resource.c
+++ b/drivers/infiniband/hw/cxgb3/cxio_resource.c
@@ -62,13 +62,13 @@ static int __cxio_init_resource_fifo(struct kfifo *fifo,
 		kfifo_in(fifo, (unsigned char *) &entry, sizeof(u32));
 	if (random) {
 		j = 0;
-		random_bytes = random32();
+		random_bytes = prandom_u32();
 		for (i = 0; i < RANDOM_SIZE; i++)
 			rarray[i] = i + skip_low;
 		for (i = skip_low + RANDOM_SIZE; i < nr - skip_high; i++) {
 			if (j >= RANDOM_SIZE) {
 				j = 0;
-				random_bytes = random32();
+				random_bytes = prandom_u32();
 			}
 			idx = (random_bytes >> (j * 2)) & 0xF;
 			kfifo_in(fifo,
diff --git a/drivers/infiniband/hw/cxgb4/id_table.c b/drivers/infiniband/hw/cxgb4/id_table.c
index f95e5df30db..0161ae6ad62 100644
--- a/drivers/infiniband/hw/cxgb4/id_table.c
+++ b/drivers/infiniband/hw/cxgb4/id_table.c
@@ -54,7 +54,7 @@ u32 c4iw_id_alloc(struct c4iw_id_table *alloc)
 
 	if (obj < alloc->max) {
 		if (alloc->flags & C4IW_ID_TABLE_F_RANDOM)
-			alloc->last += random32() % RANDOM_SKIP;
+			alloc->last += prandom_u32() % RANDOM_SKIP;
 		else
 			alloc->last = obj + 1;
 		if (alloc->last >= alloc->max)
@@ -88,7 +88,7 @@ int c4iw_id_table_alloc(struct c4iw_id_table *alloc, u32 start, u32 num,
 	alloc->start = start;
 	alloc->flags = flags;
 	if (flags & C4IW_ID_TABLE_F_RANDOM)
-		alloc->last = random32() % RANDOM_SKIP;
+		alloc->last = prandom_u32() % RANDOM_SKIP;
 	else
 		alloc->last = 0;
 	alloc->max  = num;
diff --git a/drivers/infiniband/hw/ipath/ipath_file_ops.c b/drivers/infiniband/hw/ipath/ipath_file_ops.c
index aed8afee56d..6d7f453b4d0 100644
--- a/drivers/infiniband/hw/ipath/ipath_file_ops.c
+++ b/drivers/infiniband/hw/ipath/ipath_file_ops.c
@@ -40,6 +40,7 @@
 #include <linux/slab.h>
 #include <linux/highmem.h>
 #include <linux/io.h>
+#include <linux/aio.h>
 #include <linux/jiffies.h>
 #include <linux/cpu.h>
 #include <asm/pgtable.h>
diff --git a/drivers/infiniband/hw/mlx4/mad.c b/drivers/infiniband/hw/mlx4/mad.c
index 934792c477b..4d599cedbb0 100644
--- a/drivers/infiniband/hw/mlx4/mad.c
+++ b/drivers/infiniband/hw/mlx4/mad.c
@@ -93,7 +93,7 @@ static void __propagate_pkey_ev(struct mlx4_ib_dev *dev, int port_num,
 __be64 mlx4_ib_gen_node_guid(void)
 {
 #define NODE_GUID_HI	((u64) (((u64)IB_OPENIB_OUI) << 40))
-	return cpu_to_be64(NODE_GUID_HI | random32());
+	return cpu_to_be64(NODE_GUID_HI | prandom_u32());
 }
 
 __be64 mlx4_ib_get_new_demux_tid(struct mlx4_ib_demux_ctx *ctx)
diff --git a/drivers/infiniband/hw/qib/qib_file_ops.c b/drivers/infiniband/hw/qib/qib_file_ops.c
index 4f7aa301b3b..b56c9428f3c 100644
--- a/drivers/infiniband/hw/qib/qib_file_ops.c
+++ b/drivers/infiniband/hw/qib/qib_file_ops.c
@@ -39,7 +39,7 @@
 #include <linux/vmalloc.h>
 #include <linux/highmem.h>
 #include <linux/io.h>
-#include <linux/uio.h>
+#include <linux/aio.h>
 #include <linux/jiffies.h>
 #include <asm/pgtable.h>
 #include <linux/delay.h>
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_cm.c b/drivers/infiniband/ulp/ipoib/ipoib_cm.c
index 1ef880de3a4..3eceb61e353 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_cm.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_cm.c
@@ -460,7 +460,7 @@ static int ipoib_cm_req_handler(struct ib_cm_id *cm_id, struct ib_cm_event *even
 		goto err_qp;
 	}
 
-	psn = random32() & 0xffffff;
+	psn = prandom_u32() & 0xffffff;
 	ret = ipoib_cm_modify_rx_qp(dev, cm_id, p->qp, psn);
 	if (ret)
 		goto err_modify;
diff --git a/drivers/net/ethernet/broadcom/cnic.c b/drivers/net/ethernet/broadcom/cnic.c
index 40649a8bf39..6b0dc131b20 100644
--- a/drivers/net/ethernet/broadcom/cnic.c
+++ b/drivers/net/ethernet/broadcom/cnic.c
@@ -4085,7 +4085,7 @@ static int cnic_cm_alloc_mem(struct cnic_dev *dev)
 	if (!cp->csk_tbl)
 		return -ENOMEM;
 
-	port_id = random32();
+	port_id = prandom_u32();
 	port_id %= CNIC_LOCAL_PORT_RANGE;
 	if (cnic_init_id_tbl(&cp->csk_port_tbl, CNIC_LOCAL_PORT_RANGE,
 			     CNIC_LOCAL_PORT_MIN, port_id)) {
@@ -4145,7 +4145,7 @@ static int cnic_cm_init_bnx2_hw(struct cnic_dev *dev)
 {
 	u32 seed;
 
-	seed = random32();
+	seed = prandom_u32();
 	cnic_ctx_wr(dev, 45, 0, seed);
 	return 0;
 }
diff --git a/drivers/net/hamradio/baycom_epp.c b/drivers/net/hamradio/baycom_epp.c
index 49b8b58fc5c..484f77ec2ce 100644
--- a/drivers/net/hamradio/baycom_epp.c
+++ b/drivers/net/hamradio/baycom_epp.c
@@ -449,7 +449,7 @@ static int transmit(struct baycom_state *bc, int cnt, unsigned char stat)
 			if ((--bc->hdlctx.slotcnt) > 0)
 				return 0;
 			bc->hdlctx.slotcnt = bc->ch_params.slottime;
-			if ((random32() % 256) > bc->ch_params.ppersist)
+			if ((prandom_u32() % 256) > bc->ch_params.ppersist)
 				return 0;
 		}
 	}
diff --git a/drivers/net/hamradio/hdlcdrv.c b/drivers/net/hamradio/hdlcdrv.c
index a4a3516b6bb..3169252613f 100644
--- a/drivers/net/hamradio/hdlcdrv.c
+++ b/drivers/net/hamradio/hdlcdrv.c
@@ -389,7 +389,7 @@ void hdlcdrv_arbitrate(struct net_device *dev, struct hdlcdrv_state *s)
 	if ((--s->hdlctx.slotcnt) > 0)
 		return;
 	s->hdlctx.slotcnt = s->ch_params.slottime;
-	if ((random32() % 256) > s->ch_params.ppersist)
+	if ((prandom_u32() % 256) > s->ch_params.ppersist)
 		return;
 	start_tx(dev, s);
 }
diff --git a/drivers/net/hamradio/yam.c b/drivers/net/hamradio/yam.c
index b2d863f2ea4..0721e72f929 100644
--- a/drivers/net/hamradio/yam.c
+++ b/drivers/net/hamradio/yam.c
@@ -638,7 +638,7 @@ static void yam_arbitrate(struct net_device *dev)
 	yp->slotcnt = yp->slot / 10;
 
 	/* is random > persist ? */
-	if ((random32() % 256) > yp->pers)
+	if ((prandom_u32() % 256) > yp->pers)
 		return;
 
 	yam_start_tx(dev, yp);
diff --git a/drivers/net/team/team_mode_random.c b/drivers/net/team/team_mode_random.c
index 9eabfaa22f3..5ca14d463ba 100644
--- a/drivers/net/team/team_mode_random.c
+++ b/drivers/net/team/team_mode_random.c
@@ -18,7 +18,7 @@
 
 static u32 random_N(unsigned int N)
 {
-	return reciprocal_divide(random32(), N);
+	return reciprocal_divide(prandom_u32(), N);
 }
 
 static bool rnd_transmit(struct team *team, struct sk_buff *skb)
diff --git a/drivers/net/wireless/brcm80211/brcmfmac/p2p.c b/drivers/net/wireless/brcm80211/brcmfmac/p2p.c
index 2b90da0d85f..e7a1a477099 100644
--- a/drivers/net/wireless/brcm80211/brcmfmac/p2p.c
+++ b/drivers/net/wireless/brcm80211/brcmfmac/p2p.c
@@ -1117,7 +1117,7 @@ static void brcmf_p2p_afx_handler(struct work_struct *work)
 	if (afx_hdl->is_listen && afx_hdl->my_listen_chan)
 		/* 100ms ~ 300ms */
 		err = brcmf_p2p_discover_listen(p2p, afx_hdl->my_listen_chan,
-						100 * (1 + (random32() % 3)));
+						100 * (1 + prandom_u32() % 3));
 	else
 		err = brcmf_p2p_act_frm_search(p2p, afx_hdl->peer_listen_chan);
 
diff --git a/drivers/net/wireless/mwifiex/cfg80211.c b/drivers/net/wireless/mwifiex/cfg80211.c
index a0cb0770d31..d3c8ece980d 100644
--- a/drivers/net/wireless/mwifiex/cfg80211.c
+++ b/drivers/net/wireless/mwifiex/cfg80211.c
@@ -216,7 +216,7 @@ mwifiex_cfg80211_mgmt_tx(struct wiphy *wiphy, struct wireless_dev *wdev,
 	mwifiex_form_mgmt_frame(skb, buf, len);
 	mwifiex_queue_tx_pkt(priv, skb);
 
-	*cookie = random32() | 1;
+	*cookie = prandom_u32() | 1;
 	cfg80211_mgmt_tx_status(wdev, *cookie, buf, len, true, GFP_ATOMIC);
 
 	wiphy_dbg(wiphy, "info: management frame transmitted\n");
@@ -271,7 +271,7 @@ mwifiex_cfg80211_remain_on_channel(struct wiphy *wiphy,
 					 duration);
 
 	if (!ret) {
-		*cookie = random32() | 1;
+		*cookie = prandom_u32() | 1;
 		priv->roc_cfg.cookie = *cookie;
 		priv->roc_cfg.chan = *chan;
 
diff --git a/drivers/rtc/rtc-rs5c372.c b/drivers/rtc/rtc-rs5c372.c
index 224d634322b..ccf54f06396 100644
--- a/drivers/rtc/rtc-rs5c372.c
+++ b/drivers/rtc/rtc-rs5c372.c
@@ -68,6 +68,7 @@
 enum rtc_type {
 	rtc_undef = 0,
 	rtc_r2025sd,
+	rtc_r2221tl,
 	rtc_rs5c372a,
 	rtc_rs5c372b,
 	rtc_rv5c386,
@@ -76,6 +77,7 @@ enum rtc_type {
 
 static const struct i2c_device_id rs5c372_id[] = {
 	{ "r2025sd", rtc_r2025sd },
+	{ "r2221tl", rtc_r2221tl },
 	{ "rs5c372a", rtc_rs5c372a },
 	{ "rs5c372b", rtc_rs5c372b },
 	{ "rv5c386", rtc_rv5c386 },
@@ -529,6 +531,7 @@ static int rs5c_oscillator_setup(struct rs5c372 *rs5c372)
 		rs5c372->time24 = 1;
 		break;
 	case rtc_r2025sd:
+	case rtc_r2221tl:
 	case rtc_rv5c386:
 	case rtc_rv5c387a:
 		buf[0] |= RV5C387_CTRL1_24;
@@ -609,6 +612,7 @@ static int rs5c372_probe(struct i2c_client *client,
 			rs5c372->time24 = 1;
 		break;
 	case rtc_r2025sd:
+	case rtc_r2221tl:
 	case rtc_rv5c386:
 	case rtc_rv5c387a:
 		if (rs5c372->regs[RS5C_REG_CTRL1] & RV5C387_CTRL1_24)
@@ -640,6 +644,7 @@ static int rs5c372_probe(struct i2c_client *client,
 	dev_info(&client->dev, "%s found, %s, driver version " DRV_VERSION "\n",
 			({ char *s; switch (rs5c372->type) {
 			case rtc_r2025sd:	s = "r2025sd"; break;
+			case rtc_r2221tl:	s = "r2221tl"; break;
 			case rtc_rs5c372a:	s = "rs5c372a"; break;
 			case rtc_rs5c372b:	s = "rs5c372b"; break;
 			case rtc_rv5c386:	s = "rv5c386"; break;
diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c
index 9f0c4654745..df5e961484e 100644
--- a/drivers/scsi/sg.c
+++ b/drivers/scsi/sg.c
@@ -35,6 +35,7 @@ static int sg_version_num = 30534;	/* 2 digits for each component */
 #include <linux/sched.h>
 #include <linux/string.h>
 #include <linux/mm.h>
+#include <linux/aio.h>
 #include <linux/errno.h>
 #include <linux/mtio.h>
 #include <linux/ioctl.h>
diff --git a/drivers/staging/android/logger.c b/drivers/staging/android/logger.c
index b14a5574255..b040200a5a5 100644
--- a/drivers/staging/android/logger.c
+++ b/drivers/staging/android/logger.c
@@ -28,6 +28,7 @@
 #include <linux/slab.h>
 #include <linux/time.h>
 #include <linux/vmalloc.h>
+#include <linux/aio.h>
 #include "logger.h"
 
 #include <asm/ioctls.h>
diff --git a/drivers/usb/gadget/inode.c b/drivers/usb/gadget/inode.c
index dda0dc4a556..570c005062a 100644
--- a/drivers/usb/gadget/inode.c
+++ b/drivers/usb/gadget/inode.c
@@ -24,6 +24,8 @@
 #include <linux/sched.h>
 #include <linux/slab.h>
 #include <linux/poll.h>
+#include <linux/mmu_context.h>
+#include <linux/aio.h>
 
 #include <linux/device.h>
 #include <linux/moduleparam.h>
@@ -513,6 +515,9 @@ static long ep_ioctl(struct file *fd, unsigned code, unsigned long value)
 struct kiocb_priv {
 	struct usb_request	*req;
 	struct ep_data		*epdata;
+	struct kiocb		*iocb;
+	struct mm_struct	*mm;
+	struct work_struct	work;
 	void			*buf;
 	const struct iovec	*iv;
 	unsigned long		nr_segs;
@@ -528,7 +533,6 @@ static int ep_aio_cancel(struct kiocb *iocb, struct io_event *e)
 	local_irq_disable();
 	epdata = priv->epdata;
 	// spin_lock(&epdata->dev->lock);
-	kiocbSetCancelled(iocb);
 	if (likely(epdata && epdata->ep && priv->req))
 		value = usb_ep_dequeue (epdata->ep, priv->req);
 	else
@@ -540,15 +544,12 @@ static int ep_aio_cancel(struct kiocb *iocb, struct io_event *e)
 	return value;
 }
 
-static ssize_t ep_aio_read_retry(struct kiocb *iocb)
+static ssize_t ep_copy_to_user(struct kiocb_priv *priv)
 {
-	struct kiocb_priv	*priv = iocb->private;
 	ssize_t			len, total;
 	void			*to_copy;
 	int			i;
 
-	/* we "retry" to get the right mm context for this: */
-
 	/* copy stuff into user buffers */
 	total = priv->actual;
 	len = 0;
@@ -568,9 +569,26 @@ static ssize_t ep_aio_read_retry(struct kiocb *iocb)
 		if (total == 0)
 			break;
 	}
+
+	return len;
+}
+
+static void ep_user_copy_worker(struct work_struct *work)
+{
+	struct kiocb_priv *priv = container_of(work, struct kiocb_priv, work);
+	struct mm_struct *mm = priv->mm;
+	struct kiocb *iocb = priv->iocb;
+	size_t ret;
+
+	use_mm(mm);
+	ret = ep_copy_to_user(priv);
+	unuse_mm(mm);
+
+	/* completing the iocb can drop the ctx and mm, don't touch mm after */
+	aio_complete(iocb, ret, ret);
+
 	kfree(priv->buf);
 	kfree(priv);
-	return len;
 }
 
 static void ep_aio_complete(struct usb_ep *ep, struct usb_request *req)
@@ -596,14 +614,14 @@ static void ep_aio_complete(struct usb_ep *ep, struct usb_request *req)
 		aio_complete(iocb, req->actual ? req->actual : req->status,
 				req->status);
 	} else {
-		/* retry() won't report both; so we hide some faults */
+		/* ep_copy_to_user() won't report both; we hide some faults */
 		if (unlikely(0 != req->status))
 			DBG(epdata->dev, "%s fault %d len %d\n",
 				ep->name, req->status, req->actual);
 
 		priv->buf = req->buf;
 		priv->actual = req->actual;
-		kick_iocb(iocb);
+		schedule_work(&priv->work);
 	}
 	spin_unlock(&epdata->dev->lock);
 
@@ -633,8 +651,10 @@ fail:
 		return value;
 	}
 	iocb->private = priv;
+	priv->iocb = iocb;
 	priv->iv = iv;
 	priv->nr_segs = nr_segs;
+	INIT_WORK(&priv->work, ep_user_copy_worker);
 
 	value = get_ready_ep(iocb->ki_filp->f_flags, epdata);
 	if (unlikely(value < 0)) {
@@ -642,10 +662,11 @@ fail:
 		goto fail;
 	}
 
-	iocb->ki_cancel = ep_aio_cancel;
+	kiocb_set_cancel_fn(iocb, ep_aio_cancel);
 	get_ep(epdata);
 	priv->epdata = epdata;
 	priv->actual = 0;
+	priv->mm = current->mm; /* mm teardown waits for iocbs in exit_aio() */
 
 	/* each kiocb is coupled to one usb_request, but we can't
 	 * allocate or submit those if the host disconnected.
@@ -674,7 +695,7 @@ fail:
 		kfree(priv);
 		put_ep(epdata);
 	} else
-		value = (iv ? -EIOCBRETRY : -EIOCBQUEUED);
+		value = -EIOCBQUEUED;
 	return value;
 }
 
@@ -692,7 +713,6 @@ ep_aio_read(struct kiocb *iocb, const struct iovec *iov,
 	if (unlikely(!buf))
 		return -ENOMEM;
 
-	iocb->ki_retry = ep_aio_read_retry;
 	return ep_aio_rwtail(iocb, buf, iocb->ki_left, epdata, iov, nr_segs);
 }
 
diff --git a/fs/9p/vfs_addr.c b/fs/9p/vfs_addr.c
index 0ad61c6a65a..055562c580b 100644
--- a/fs/9p/vfs_addr.c
+++ b/fs/9p/vfs_addr.c
@@ -33,6 +33,7 @@
 #include <linux/pagemap.h>
 #include <linux/idr.h>
 #include <linux/sched.h>
+#include <linux/aio.h>
 #include <net/9p/9p.h>
 #include <net/9p/client.h>
 
diff --git a/fs/afs/write.c b/fs/afs/write.c
index 7e03eadb40c..a890db4b989 100644
--- a/fs/afs/write.c
+++ b/fs/afs/write.c
@@ -14,6 +14,7 @@
 #include <linux/pagemap.h>
 #include <linux/writeback.h>
 #include <linux/pagevec.h>
+#include <linux/aio.h>
 #include "internal.h"
 
 static int afs_write_back_from_locked_page(struct afs_writeback *wb,
diff --git a/fs/aio.c b/fs/aio.c
index 351afe7ac78..c5b1a8c1041 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -8,6 +8,8 @@
  *
  *	See ../COPYING for licensing terms.
  */
+#define pr_fmt(fmt) "%s: " fmt, __func__
+
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/errno.h>
@@ -18,8 +20,6 @@
 #include <linux/backing-dev.h>
 #include <linux/uio.h>
 
-#define DEBUG 0
-
 #include <linux/sched.h>
 #include <linux/fs.h>
 #include <linux/file.h>
@@ -39,11 +39,76 @@
 #include <asm/kmap_types.h>
 #include <asm/uaccess.h>
 
-#if DEBUG > 1
-#define dprintk		printk
-#else
-#define dprintk(x...)	do { ; } while (0)
-#endif
+#define AIO_RING_MAGIC			0xa10a10a1
+#define AIO_RING_COMPAT_FEATURES	1
+#define AIO_RING_INCOMPAT_FEATURES	0
+struct aio_ring {
+	unsigned	id;	/* kernel internal index number */
+	unsigned	nr;	/* number of io_events */
+	unsigned	head;
+	unsigned	tail;
+
+	unsigned	magic;
+	unsigned	compat_features;
+	unsigned	incompat_features;
+	unsigned	header_length;	/* size of aio_ring */
+
+
+	struct io_event		io_events[0];
+}; /* 128 bytes + ring size */
+
+#define AIO_RING_PAGES	8
+
+struct kioctx {
+	atomic_t		users;
+	atomic_t		dead;
+
+	/* This needs improving */
+	unsigned long		user_id;
+	struct hlist_node	list;
+
+	/*
+	 * This is what userspace passed to io_setup(), it's not used for
+	 * anything but counting against the global max_reqs quota.
+	 *
+	 * The real limit is nr_events - 1, which will be larger (see
+	 * aio_setup_ring())
+	 */
+	unsigned		max_reqs;
+
+	/* Size of ringbuffer, in units of struct io_event */
+	unsigned		nr_events;
+
+	unsigned long		mmap_base;
+	unsigned long		mmap_size;
+
+	struct page		**ring_pages;
+	long			nr_pages;
+
+	struct rcu_head		rcu_head;
+	struct work_struct	rcu_work;
+
+	struct {
+		atomic_t	reqs_active;
+	} ____cacheline_aligned_in_smp;
+
+	struct {
+		spinlock_t	ctx_lock;
+		struct list_head active_reqs;	/* used for cancellation */
+	} ____cacheline_aligned_in_smp;
+
+	struct {
+		struct mutex	ring_lock;
+		wait_queue_head_t wait;
+	} ____cacheline_aligned_in_smp;
+
+	struct {
+		unsigned	tail;
+		spinlock_t	completion_lock;
+	} ____cacheline_aligned_in_smp;
+
+	struct page		*internal_pages[AIO_RING_PAGES];
+};
 
 /*------ sysctl variables----*/
 static DEFINE_SPINLOCK(aio_nr_lock);
@@ -54,11 +119,6 @@ unsigned long aio_max_nr = 0x10000; /* system wide maximum number of aio request
 static struct kmem_cache	*kiocb_cachep;
 static struct kmem_cache	*kioctx_cachep;
 
-static struct workqueue_struct *aio_wq;
-
-static void aio_kick_handler(struct work_struct *);
-static void aio_queue_work(struct kioctx *);
-
 /* aio_setup
  *	Creates the slab caches used by the aio routines, panic on
  *	failure as this is done early during the boot sequence.
@@ -68,10 +128,7 @@ static int __init aio_setup(void)
 	kiocb_cachep = KMEM_CACHE(kiocb, SLAB_HWCACHE_ALIGN|SLAB_PANIC);
 	kioctx_cachep = KMEM_CACHE(kioctx,SLAB_HWCACHE_ALIGN|SLAB_PANIC);
 
-	aio_wq = alloc_workqueue("aio", 0, 1);	/* used to limit concurrency */
-	BUG_ON(!aio_wq);
-
-	pr_debug("aio_setup: sizeof(struct page) = %d\n", (int)sizeof(struct page));
+	pr_debug("sizeof(struct page) = %zu\n", sizeof(struct page));
 
 	return 0;
 }
@@ -79,28 +136,23 @@ __initcall(aio_setup);
 
 static void aio_free_ring(struct kioctx *ctx)
 {
-	struct aio_ring_info *info = &ctx->ring_info;
 	long i;
 
-	for (i=0; i<info->nr_pages; i++)
-		put_page(info->ring_pages[i]);
+	for (i = 0; i < ctx->nr_pages; i++)
+		put_page(ctx->ring_pages[i]);
 
-	if (info->mmap_size) {
-		BUG_ON(ctx->mm != current->mm);
-		vm_munmap(info->mmap_base, info->mmap_size);
-	}
+	if (ctx->mmap_size)
+		vm_munmap(ctx->mmap_base, ctx->mmap_size);
 
-	if (info->ring_pages && info->ring_pages != info->internal_pages)
-		kfree(info->ring_pages);
-	info->ring_pages = NULL;
-	info->nr = 0;
+	if (ctx->ring_pages && ctx->ring_pages != ctx->internal_pages)
+		kfree(ctx->ring_pages);
 }
 
 static int aio_setup_ring(struct kioctx *ctx)
 {
 	struct aio_ring *ring;
-	struct aio_ring_info *info = &ctx->ring_info;
 	unsigned nr_events = ctx->max_reqs;
+	struct mm_struct *mm = current->mm;
 	unsigned long size, populate;
 	int nr_pages;
 
@@ -116,46 +168,44 @@ static int aio_setup_ring(struct kioctx *ctx)
 
 	nr_events = (PAGE_SIZE * nr_pages - sizeof(struct aio_ring)) / sizeof(struct io_event);
 
-	info->nr = 0;
-	info->ring_pages = info->internal_pages;
+	ctx->nr_events = 0;
+	ctx->ring_pages = ctx->internal_pages;
 	if (nr_pages > AIO_RING_PAGES) {
-		info->ring_pages = kcalloc(nr_pages, sizeof(struct page *), GFP_KERNEL);
-		if (!info->ring_pages)
+		ctx->ring_pages = kcalloc(nr_pages, sizeof(struct page *),
+					  GFP_KERNEL);
+		if (!ctx->ring_pages)
 			return -ENOMEM;
 	}
 
-	info->mmap_size = nr_pages * PAGE_SIZE;
-	dprintk("attempting mmap of %lu bytes\n", info->mmap_size);
-	down_write(&ctx->mm->mmap_sem);
-	info->mmap_base = do_mmap_pgoff(NULL, 0, info->mmap_size, 
-					PROT_READ|PROT_WRITE,
-					MAP_ANONYMOUS|MAP_PRIVATE, 0,
-					&populate);
-	if (IS_ERR((void *)info->mmap_base)) {
-		up_write(&ctx->mm->mmap_sem);
-		info->mmap_size = 0;
+	ctx->mmap_size = nr_pages * PAGE_SIZE;
+	pr_debug("attempting mmap of %lu bytes\n", ctx->mmap_size);
+	down_write(&mm->mmap_sem);
+	ctx->mmap_base = do_mmap_pgoff(NULL, 0, ctx->mmap_size,
+				       PROT_READ|PROT_WRITE,
+				       MAP_ANONYMOUS|MAP_PRIVATE, 0, &populate);
+	if (IS_ERR((void *)ctx->mmap_base)) {
+		up_write(&mm->mmap_sem);
+		ctx->mmap_size = 0;
 		aio_free_ring(ctx);
 		return -EAGAIN;
 	}
 
-	dprintk("mmap address: 0x%08lx\n", info->mmap_base);
-	info->nr_pages = get_user_pages(current, ctx->mm,
-					info->mmap_base, nr_pages, 
-					1, 0, info->ring_pages, NULL);
-	up_write(&ctx->mm->mmap_sem);
+	pr_debug("mmap address: 0x%08lx\n", ctx->mmap_base);
+	ctx->nr_pages = get_user_pages(current, mm, ctx->mmap_base, nr_pages,
+				       1, 0, ctx->ring_pages, NULL);
+	up_write(&mm->mmap_sem);
 
-	if (unlikely(info->nr_pages != nr_pages)) {
+	if (unlikely(ctx->nr_pages != nr_pages)) {
 		aio_free_ring(ctx);
 		return -EAGAIN;
 	}
 	if (populate)
-		mm_populate(info->mmap_base, populate);
+		mm_populate(ctx->mmap_base, populate);
 
-	ctx->user_id = info->mmap_base;
+	ctx->user_id = ctx->mmap_base;
+	ctx->nr_events = nr_events; /* trusted copy */
 
-	info->nr = nr_events;		/* trusted copy */
-
-	ring = kmap_atomic(info->ring_pages[0]);
+	ring = kmap_atomic(ctx->ring_pages[0]);
 	ring->nr = nr_events;	/* user copy */
 	ring->id = ctx->user_id;
 	ring->head = ring->tail = 0;
@@ -164,72 +214,133 @@ static int aio_setup_ring(struct kioctx *ctx)
 	ring->incompat_features = AIO_RING_INCOMPAT_FEATURES;
 	ring->header_length = sizeof(struct aio_ring);
 	kunmap_atomic(ring);
+	flush_dcache_page(ctx->ring_pages[0]);
 
 	return 0;
 }
 
-
-/* aio_ring_event: returns a pointer to the event at the given index from
- * kmap_atomic().  Release the pointer with put_aio_ring_event();
- */
 #define AIO_EVENTS_PER_PAGE	(PAGE_SIZE / sizeof(struct io_event))
 #define AIO_EVENTS_FIRST_PAGE	((PAGE_SIZE - sizeof(struct aio_ring)) / sizeof(struct io_event))
 #define AIO_EVENTS_OFFSET	(AIO_EVENTS_PER_PAGE - AIO_EVENTS_FIRST_PAGE)
 
-#define aio_ring_event(info, nr) ({					\
-	unsigned pos = (nr) + AIO_EVENTS_OFFSET;			\
-	struct io_event *__event;					\
-	__event = kmap_atomic(						\
-			(info)->ring_pages[pos / AIO_EVENTS_PER_PAGE]); \
-	__event += pos % AIO_EVENTS_PER_PAGE;				\
-	__event;							\
-})
-
-#define put_aio_ring_event(event) do {		\
-	struct io_event *__event = (event);	\
-	(void)__event;				\
-	kunmap_atomic((void *)((unsigned long)__event & PAGE_MASK)); \
-} while(0)
-
-static void ctx_rcu_free(struct rcu_head *head)
+void kiocb_set_cancel_fn(struct kiocb *req, kiocb_cancel_fn *cancel)
+{
+	struct kioctx *ctx = req->ki_ctx;
+	unsigned long flags;
+
+	spin_lock_irqsave(&ctx->ctx_lock, flags);
+
+	if (!req->ki_list.next)
+		list_add(&req->ki_list, &ctx->active_reqs);
+
+	req->ki_cancel = cancel;
+
+	spin_unlock_irqrestore(&ctx->ctx_lock, flags);
+}
+EXPORT_SYMBOL(kiocb_set_cancel_fn);
+
+static int kiocb_cancel(struct kioctx *ctx, struct kiocb *kiocb,
+			struct io_event *res)
+{
+	kiocb_cancel_fn *old, *cancel;
+	int ret = -EINVAL;
+
+	/*
+	 * Don't want to set kiocb->ki_cancel = KIOCB_CANCELLED unless it
+	 * actually has a cancel function, hence the cmpxchg()
+	 */
+
+	cancel = ACCESS_ONCE(kiocb->ki_cancel);
+	do {
+		if (!cancel || cancel == KIOCB_CANCELLED)
+			return ret;
+
+		old = cancel;
+		cancel = cmpxchg(&kiocb->ki_cancel, old, KIOCB_CANCELLED);
+	} while (cancel != old);
+
+	atomic_inc(&kiocb->ki_users);
+	spin_unlock_irq(&ctx->ctx_lock);
+
+	memset(res, 0, sizeof(*res));
+	res->obj = (u64)(unsigned long)kiocb->ki_obj.user;
+	res->data = kiocb->ki_user_data;
+	ret = cancel(kiocb, res);
+
+	spin_lock_irq(&ctx->ctx_lock);
+
+	return ret;
+}
+
+static void free_ioctx_rcu(struct rcu_head *head)
 {
 	struct kioctx *ctx = container_of(head, struct kioctx, rcu_head);
 	kmem_cache_free(kioctx_cachep, ctx);
 }
 
-/* __put_ioctx
- *	Called when the last user of an aio context has gone away,
- *	and the struct needs to be freed.
+/*
+ * When this function runs, the kioctx has been removed from the "hash table"
+ * and ctx->users has dropped to 0, so we know no more kiocbs can be submitted -
+ * now it's safe to cancel any that need to be.
  */
-static void __put_ioctx(struct kioctx *ctx)
+static void free_ioctx(struct kioctx *ctx)
 {
-	unsigned nr_events = ctx->max_reqs;
-	BUG_ON(ctx->reqs_active);
+	struct aio_ring *ring;
+	struct io_event res;
+	struct kiocb *req;
+	unsigned head, avail;
 
-	cancel_delayed_work_sync(&ctx->wq);
-	aio_free_ring(ctx);
-	mmdrop(ctx->mm);
-	ctx->mm = NULL;
-	if (nr_events) {
-		spin_lock(&aio_nr_lock);
-		BUG_ON(aio_nr - nr_events > aio_nr);
-		aio_nr -= nr_events;
-		spin_unlock(&aio_nr_lock);
+	spin_lock_irq(&ctx->ctx_lock);
+
+	while (!list_empty(&ctx->active_reqs)) {
+		req = list_first_entry(&ctx->active_reqs,
+				       struct kiocb, ki_list);
+
+		list_del_init(&req->ki_list);
+		kiocb_cancel(ctx, req, &res);
 	}
-	pr_debug("__put_ioctx: freeing %p\n", ctx);
-	call_rcu(&ctx->rcu_head, ctx_rcu_free);
-}
 
-static inline int try_get_ioctx(struct kioctx *kioctx)
-{
-	return atomic_inc_not_zero(&kioctx->users);
+	spin_unlock_irq(&ctx->ctx_lock);
+
+	ring = kmap_atomic(ctx->ring_pages[0]);
+	head = ring->head;
+	kunmap_atomic(ring);
+
+	while (atomic_read(&ctx->reqs_active) > 0) {
+		wait_event(ctx->wait, head != ctx->tail);
+
+		avail = (head <= ctx->tail ? ctx->tail : ctx->nr_events) - head;
+
+		atomic_sub(avail, &ctx->reqs_active);
+		head += avail;
+		head %= ctx->nr_events;
+	}
+
+	WARN_ON(atomic_read(&ctx->reqs_active) < 0);
+
+	aio_free_ring(ctx);
+
+	spin_lock(&aio_nr_lock);
+	BUG_ON(aio_nr - ctx->max_reqs > aio_nr);
+	aio_nr -= ctx->max_reqs;
+	spin_unlock(&aio_nr_lock);
+
+	pr_debug("freeing %p\n", ctx);
+
+	/*
+	 * Here the call_rcu() is between the wait_event() for reqs_active to
+	 * hit 0, and freeing the ioctx.
+	 *
+	 * aio_complete() decrements reqs_active, but it has to touch the ioctx
+	 * after to issue a wakeup so we use rcu.
+	 */
+	call_rcu(&ctx->rcu_head, free_ioctx_rcu);
 }
 
-static inline void put_ioctx(struct kioctx *kioctx)
+static void put_ioctx(struct kioctx *ctx)
 {
-	BUG_ON(atomic_read(&kioctx->users) <= 0);
-	if (unlikely(atomic_dec_and_test(&kioctx->users)))
-		__put_ioctx(kioctx);
+	if (unlikely(atomic_dec_and_test(&ctx->users)))
+		free_ioctx(ctx);
 }
 
 /* ioctx_alloc
@@ -237,7 +348,7 @@ static inline void put_ioctx(struct kioctx *kioctx)
  */
 static struct kioctx *ioctx_alloc(unsigned nr_events)
 {
-	struct mm_struct *mm;
+	struct mm_struct *mm = current->mm;
 	struct kioctx *ctx;
 	int err = -ENOMEM;
 
@@ -256,17 +367,15 @@ static struct kioctx *ioctx_alloc(unsigned nr_events)
 		return ERR_PTR(-ENOMEM);
 
 	ctx->max_reqs = nr_events;
-	mm = ctx->mm = current->mm;
-	atomic_inc(&mm->mm_count);
 
 	atomic_set(&ctx->users, 2);
+	atomic_set(&ctx->dead, 0);
 	spin_lock_init(&ctx->ctx_lock);
-	spin_lock_init(&ctx->ring_info.ring_lock);
+	spin_lock_init(&ctx->completion_lock);
+	mutex_init(&ctx->ring_lock);
 	init_waitqueue_head(&ctx->wait);
 
 	INIT_LIST_HEAD(&ctx->active_reqs);
-	INIT_LIST_HEAD(&ctx->run_list);
-	INIT_DELAYED_WORK(&ctx->wq, aio_kick_handler);
 
 	if (aio_setup_ring(ctx) < 0)
 		goto out_freectx;
@@ -286,64 +395,56 @@ static struct kioctx *ioctx_alloc(unsigned nr_events)
 	hlist_add_head_rcu(&ctx->list, &mm->ioctx_list);
 	spin_unlock(&mm->ioctx_lock);
 
-	dprintk("aio: allocated ioctx %p[%ld]: mm=%p mask=0x%x\n",
-		ctx, ctx->user_id, current->mm, ctx->ring_info.nr);
+	pr_debug("allocated ioctx %p[%ld]: mm=%p mask=0x%x\n",
+		 ctx, ctx->user_id, mm, ctx->nr_events);
 	return ctx;
 
 out_cleanup:
 	err = -EAGAIN;
 	aio_free_ring(ctx);
 out_freectx:
-	mmdrop(mm);
 	kmem_cache_free(kioctx_cachep, ctx);
-	dprintk("aio: error allocating ioctx %d\n", err);
+	pr_debug("error allocating ioctx %d\n", err);
 	return ERR_PTR(err);
 }
 
-/* kill_ctx
- *	Cancels all outstanding aio requests on an aio context.  Used 
- *	when the processes owning a context have all exited to encourage 
- *	the rapid destruction of the kioctx.
- */
-static void kill_ctx(struct kioctx *ctx)
+static void kill_ioctx_work(struct work_struct *work)
 {
-	int (*cancel)(struct kiocb *, struct io_event *);
-	struct task_struct *tsk = current;
-	DECLARE_WAITQUEUE(wait, tsk);
-	struct io_event res;
+	struct kioctx *ctx = container_of(work, struct kioctx, rcu_work);
 
-	spin_lock_irq(&ctx->ctx_lock);
-	ctx->dead = 1;
-	while (!list_empty(&ctx->active_reqs)) {
-		struct list_head *pos = ctx->active_reqs.next;
-		struct kiocb *iocb = list_kiocb(pos);
-		list_del_init(&iocb->ki_list);
-		cancel = iocb->ki_cancel;
-		kiocbSetCancelled(iocb);
-		if (cancel) {
-			iocb->ki_users++;
-			spin_unlock_irq(&ctx->ctx_lock);
-			cancel(iocb, &res);
-			spin_lock_irq(&ctx->ctx_lock);
-		}
-	}
+	wake_up_all(&ctx->wait);
+	put_ioctx(ctx);
+}
 
-	if (!ctx->reqs_active)
-		goto out;
+static void kill_ioctx_rcu(struct rcu_head *head)
+{
+	struct kioctx *ctx = container_of(head, struct kioctx, rcu_head);
 
-	add_wait_queue(&ctx->wait, &wait);
-	set_task_state(tsk, TASK_UNINTERRUPTIBLE);
-	while (ctx->reqs_active) {
-		spin_unlock_irq(&ctx->ctx_lock);
-		io_schedule();
-		set_task_state(tsk, TASK_UNINTERRUPTIBLE);
-		spin_lock_irq(&ctx->ctx_lock);
-	}
-	__set_task_state(tsk, TASK_RUNNING);
-	remove_wait_queue(&ctx->wait, &wait);
+	INIT_WORK(&ctx->rcu_work, kill_ioctx_work);
+	schedule_work(&ctx->rcu_work);
+}
 
-out:
-	spin_unlock_irq(&ctx->ctx_lock);
+/* kill_ioctx
+ *	Cancels all outstanding aio requests on an aio context.  Used
+ *	when the processes owning a context have all exited to encourage
+ *	the rapid destruction of the kioctx.
+ */
+static void kill_ioctx(struct kioctx *ctx)
+{
+	if (!atomic_xchg(&ctx->dead, 1)) {
+		hlist_del_rcu(&ctx->list);
+		/* Between hlist_del_rcu() and dropping the initial ref */
+		synchronize_rcu();
+
+		/*
+		 * We can't punt to workqueue here because put_ioctx() ->
+		 * free_ioctx() will unmap the ringbuffer, and that has to be
+		 * done in the original process's context. kill_ioctx_rcu/work()
+		 * exist for exit_aio(), as in that path free_ioctx() won't do
+		 * the unmap.
+		 */
+		kill_ioctx_work(&ctx->rcu_work);
+	}
 }
 
 /* wait_on_sync_kiocb:
@@ -351,9 +452,9 @@ out:
  */
 ssize_t wait_on_sync_kiocb(struct kiocb *iocb)
 {
-	while (iocb->ki_users) {
+	while (atomic_read(&iocb->ki_users)) {
 		set_current_state(TASK_UNINTERRUPTIBLE);
-		if (!iocb->ki_users)
+		if (!atomic_read(&iocb->ki_users))
 			break;
 		io_schedule();
 	}
@@ -362,28 +463,26 @@ ssize_t wait_on_sync_kiocb(struct kiocb *iocb)
 }
 EXPORT_SYMBOL(wait_on_sync_kiocb);
 
-/* exit_aio: called when the last user of mm goes away.  At this point, 
- * there is no way for any new requests to be submited or any of the 
- * io_* syscalls to be called on the context.  However, there may be 
- * outstanding requests which hold references to the context; as they 
- * go away, they will call put_ioctx and release any pinned memory
- * associated with the request (held via struct page * references).
+/*
+ * exit_aio: called when the last user of mm goes away.  At this point, there is
+ * no way for any new requests to be submited or any of the io_* syscalls to be
+ * called on the context.
+ *
+ * There may be outstanding kiocbs, but free_ioctx() will explicitly wait on
+ * them.
  */
 void exit_aio(struct mm_struct *mm)
 {
 	struct kioctx *ctx;
+	struct hlist_node *n;
 
-	while (!hlist_empty(&mm->ioctx_list)) {
-		ctx = hlist_entry(mm->ioctx_list.first, struct kioctx, list);
-		hlist_del_rcu(&ctx->list);
-
-		kill_ctx(ctx);
-
+	hlist_for_each_entry_safe(ctx, n, &mm->ioctx_list, list) {
 		if (1 != atomic_read(&ctx->users))
 			printk(KERN_DEBUG
 				"exit_aio:ioctx still alive: %d %d %d\n",
-				atomic_read(&ctx->users), ctx->dead,
-				ctx->reqs_active);
+				atomic_read(&ctx->users),
+				atomic_read(&ctx->dead),
+				atomic_read(&ctx->reqs_active));
 		/*
 		 * We don't need to bother with munmap() here -
 		 * exit_mmap(mm) is coming and it'll unmap everything.
@@ -391,150 +490,53 @@ void exit_aio(struct mm_struct *mm)
 		 * as indicator that it needs to unmap the area,
 		 * just set it to 0; aio_free_ring() is the only
 		 * place that uses ->mmap_size, so it's safe.
-		 * That way we get all munmap done to current->mm -
-		 * all other callers have ctx->mm == current->mm.
 		 */
-		ctx->ring_info.mmap_size = 0;
-		put_ioctx(ctx);
+		ctx->mmap_size = 0;
+
+		if (!atomic_xchg(&ctx->dead, 1)) {
+			hlist_del_rcu(&ctx->list);
+			call_rcu(&ctx->rcu_head, kill_ioctx_rcu);
+		}
 	}
 }
 
 /* aio_get_req
- *	Allocate a slot for an aio request.  Increments the users count
+ *	Allocate a slot for an aio request.  Increments the ki_users count
  * of the kioctx so that the kioctx stays around until all requests are
  * complete.  Returns NULL if no requests are free.
  *
- * Returns with kiocb->users set to 2.  The io submit code path holds
+ * Returns with kiocb->ki_users set to 2.  The io submit code path holds
  * an extra reference while submitting the i/o.
  * This prevents races between the aio code path referencing the
  * req (after submitting it) and aio_complete() freeing the req.
  */
-static struct kiocb *__aio_get_req(struct kioctx *ctx)
+static inline struct kiocb *aio_get_req(struct kioctx *ctx)
 {
-	struct kiocb *req = NULL;
+	struct kiocb *req;
 
-	req = kmem_cache_alloc(kiocb_cachep, GFP_KERNEL);
-	if (unlikely(!req))
+	if (atomic_read(&ctx->reqs_active) >= ctx->nr_events)
 		return NULL;
 
-	req->ki_flags = 0;
-	req->ki_users = 2;
-	req->ki_key = 0;
-	req->ki_ctx = ctx;
-	req->ki_cancel = NULL;
-	req->ki_retry = NULL;
-	req->ki_dtor = NULL;
-	req->private = NULL;
-	req->ki_iovec = NULL;
-	INIT_LIST_HEAD(&req->ki_run_list);
-	req->ki_eventfd = NULL;
-
-	return req;
-}
-
-/*
- * struct kiocb's are allocated in batches to reduce the number of
- * times the ctx lock is acquired and released.
- */
-#define KIOCB_BATCH_SIZE	32L
-struct kiocb_batch {
-	struct list_head head;
-	long count; /* number of requests left to allocate */
-};
-
-static void kiocb_batch_init(struct kiocb_batch *batch, long total)
-{
-	INIT_LIST_HEAD(&batch->head);
-	batch->count = total;
-}
-
-static void kiocb_batch_free(struct kioctx *ctx, struct kiocb_batch *batch)
-{
-	struct kiocb *req, *n;
-
-	if (list_empty(&batch->head))
-		return;
-
-	spin_lock_irq(&ctx->ctx_lock);
-	list_for_each_entry_safe(req, n, &batch->head, ki_batch) {
-		list_del(&req->ki_batch);
-		list_del(&req->ki_list);
-		kmem_cache_free(kiocb_cachep, req);
-		ctx->reqs_active--;
-	}
-	if (unlikely(!ctx->reqs_active && ctx->dead))
-		wake_up_all(&ctx->wait);
-	spin_unlock_irq(&ctx->ctx_lock);
-}
-
-/*
- * Allocate a batch of kiocbs.  This avoids taking and dropping the
- * context lock a lot during setup.
- */
-static int kiocb_batch_refill(struct kioctx *ctx, struct kiocb_batch *batch)
-{
-	unsigned short allocated, to_alloc;
-	long avail;
-	struct kiocb *req, *n;
-	struct aio_ring *ring;
-
-	to_alloc = min(batch->count, KIOCB_BATCH_SIZE);
-	for (allocated = 0; allocated < to_alloc; allocated++) {
-		req = __aio_get_req(ctx);
-		if (!req)
-			/* allocation failed, go with what we've got */
-			break;
-		list_add(&req->ki_batch, &batch->head);
-	}
-
-	if (allocated == 0)
-		goto out;
-
-	spin_lock_irq(&ctx->ctx_lock);
-	ring = kmap_atomic(ctx->ring_info.ring_pages[0]);
-
-	avail = aio_ring_avail(&ctx->ring_info, ring) - ctx->reqs_active;
-	BUG_ON(avail < 0);
-	if (avail < allocated) {
-		/* Trim back the number of requests. */
-		list_for_each_entry_safe(req, n, &batch->head, ki_batch) {
-			list_del(&req->ki_batch);
-			kmem_cache_free(kiocb_cachep, req);
-			if (--allocated <= avail)
-				break;
-		}
-	}
-
-	batch->count -= allocated;
-	list_for_each_entry(req, &batch->head, ki_batch) {
-		list_add(&req->ki_list, &ctx->active_reqs);
-		ctx->reqs_active++;
-	}
+	if (atomic_inc_return(&ctx->reqs_active) > ctx->nr_events - 1)
+		goto out_put;
 
-	kunmap_atomic(ring);
-	spin_unlock_irq(&ctx->ctx_lock);
-
-out:
-	return allocated;
-}
+	req = kmem_cache_alloc(kiocb_cachep, GFP_KERNEL|__GFP_ZERO);
+	if (unlikely(!req))
+		goto out_put;
 
-static inline struct kiocb *aio_get_req(struct kioctx *ctx,
-					struct kiocb_batch *batch)
-{
-	struct kiocb *req;
+	atomic_set(&req->ki_users, 2);
+	req->ki_ctx = ctx;
 
-	if (list_empty(&batch->head))
-		if (kiocb_batch_refill(ctx, batch) == 0)
-			return NULL;
-	req = list_first_entry(&batch->head, struct kiocb, ki_batch);
-	list_del(&req->ki_batch);
 	return req;
+out_put:
+	atomic_dec(&ctx->reqs_active);
+	return NULL;
 }
 
-static inline void really_put_req(struct kioctx *ctx, struct kiocb *req)
+static void kiocb_free(struct kiocb *req)
 {
-	assert_spin_locked(&ctx->ctx_lock);
-
+	if (req->ki_filp)
+		fput(req->ki_filp);
 	if (req->ki_eventfd != NULL)
 		eventfd_ctx_put(req->ki_eventfd);
 	if (req->ki_dtor)
@@ -542,48 +544,12 @@ static inline void really_put_req(struct kioctx *ctx, struct kiocb *req)
 	if (req->ki_iovec != &req->ki_inline_vec)
 		kfree(req->ki_iovec);
 	kmem_cache_free(kiocb_cachep, req);
-	ctx->reqs_active--;
-
-	if (unlikely(!ctx->reqs_active && ctx->dead))
-		wake_up_all(&ctx->wait);
 }
 
-/* __aio_put_req
- *	Returns true if this put was the last user of the request.
- */
-static int __aio_put_req(struct kioctx *ctx, struct kiocb *req)
+void aio_put_req(struct kiocb *req)
 {
-	dprintk(KERN_DEBUG "aio_put(%p): f_count=%ld\n",
-		req, atomic_long_read(&req->ki_filp->f_count));
-
-	assert_spin_locked(&ctx->ctx_lock);
-
-	req->ki_users--;
-	BUG_ON(req->ki_users < 0);
-	if (likely(req->ki_users))
-		return 0;
-	list_del(&req->ki_list);		/* remove from active_reqs */
-	req->ki_cancel = NULL;
-	req->ki_retry = NULL;
-
-	fput(req->ki_filp);
-	req->ki_filp = NULL;
-	really_put_req(ctx, req);
-	return 1;
-}
-
-/* aio_put_req
- *	Returns true if this put was the last user of the kiocb,
- *	false if the request is still in use.
- */
-int aio_put_req(struct kiocb *req)
-{
-	struct kioctx *ctx = req->ki_ctx;
-	int ret;
-	spin_lock_irq(&ctx->ctx_lock);
-	ret = __aio_put_req(ctx, req);
-	spin_unlock_irq(&ctx->ctx_lock);
-	return ret;
+	if (atomic_dec_and_test(&req->ki_users))
+		kiocb_free(req);
 }
 EXPORT_SYMBOL(aio_put_req);
 
@@ -595,13 +561,8 @@ static struct kioctx *lookup_ioctx(unsigned long ctx_id)
 	rcu_read_lock();
 
 	hlist_for_each_entry_rcu(ctx, &mm->ioctx_list, list) {
-		/*
-		 * RCU protects us against accessing freed memory but
-		 * we have to be careful not to get a reference when the
-		 * reference count already dropped to 0 (ctx->dead test
-		 * is unreliable because of races).
-		 */
-		if (ctx->user_id == ctx_id && !ctx->dead && try_get_ioctx(ctx)){
+		if (ctx->user_id == ctx_id) {
+			atomic_inc(&ctx->users);
 			ret = ctx;
 			break;
 		}
@@ -611,295 +572,16 @@ static struct kioctx *lookup_ioctx(unsigned long ctx_id)
 	return ret;
 }
 
-/*
- * Queue up a kiocb to be retried. Assumes that the kiocb
- * has already been marked as kicked, and places it on
- * the retry run list for the corresponding ioctx, if it
- * isn't already queued. Returns 1 if it actually queued
- * the kiocb (to tell the caller to activate the work
- * queue to process it), or 0, if it found that it was
- * already queued.
- */
-static inline int __queue_kicked_iocb(struct kiocb *iocb)
-{
-	struct kioctx *ctx = iocb->ki_ctx;
-
-	assert_spin_locked(&ctx->ctx_lock);
-
-	if (list_empty(&iocb->ki_run_list)) {
-		list_add_tail(&iocb->ki_run_list,
-			&ctx->run_list);
-		return 1;
-	}
-	return 0;
-}
-
-/* aio_run_iocb
- *	This is the core aio execution routine. It is
- *	invoked both for initial i/o submission and
- *	subsequent retries via the aio_kick_handler.
- *	Expects to be invoked with iocb->ki_ctx->lock
- *	already held. The lock is released and reacquired
- *	as needed during processing.
- *
- * Calls the iocb retry method (already setup for the
- * iocb on initial submission) for operation specific
- * handling, but takes care of most of common retry
- * execution details for a given iocb. The retry method
- * needs to be non-blocking as far as possible, to avoid
- * holding up other iocbs waiting to be serviced by the
- * retry kernel thread.
- *
- * The trickier parts in this code have to do with
- * ensuring that only one retry instance is in progress
- * for a given iocb at any time. Providing that guarantee
- * simplifies the coding of individual aio operations as
- * it avoids various potential races.
- */
-static ssize_t aio_run_iocb(struct kiocb *iocb)
-{
-	struct kioctx	*ctx = iocb->ki_ctx;
-	ssize_t (*retry)(struct kiocb *);
-	ssize_t ret;
-
-	if (!(retry = iocb->ki_retry)) {
-		printk("aio_run_iocb: iocb->ki_retry = NULL\n");
-		return 0;
-	}
-
-	/*
-	 * We don't want the next retry iteration for this
-	 * operation to start until this one has returned and
-	 * updated the iocb state. However, wait_queue functions
-	 * can trigger a kick_iocb from interrupt context in the
-	 * meantime, indicating that data is available for the next
-	 * iteration. We want to remember that and enable the
-	 * next retry iteration _after_ we are through with
-	 * this one.
-	 *
-	 * So, in order to be able to register a "kick", but
-	 * prevent it from being queued now, we clear the kick
-	 * flag, but make the kick code *think* that the iocb is
-	 * still on the run list until we are actually done.
-	 * When we are done with this iteration, we check if
-	 * the iocb was kicked in the meantime and if so, queue
-	 * it up afresh.
-	 */
-
-	kiocbClearKicked(iocb);
-
-	/*
-	 * This is so that aio_complete knows it doesn't need to
-	 * pull the iocb off the run list (We can't just call
-	 * INIT_LIST_HEAD because we don't want a kick_iocb to
-	 * queue this on the run list yet)
-	 */
-	iocb->ki_run_list.next = iocb->ki_run_list.prev = NULL;
-	spin_unlock_irq(&ctx->ctx_lock);
-
-	/* Quit retrying if the i/o has been cancelled */
-	if (kiocbIsCancelled(iocb)) {
-		ret = -EINTR;
-		aio_complete(iocb, ret, 0);
-		/* must not access the iocb after this */
-		goto out;
-	}
-
-	/*
-	 * Now we are all set to call the retry method in async
-	 * context.
-	 */
-	ret = retry(iocb);
-
-	if (ret != -EIOCBRETRY && ret != -EIOCBQUEUED) {
-		/*
-		 * There's no easy way to restart the syscall since other AIO's
-		 * may be already running. Just fail this IO with EINTR.
-		 */
-		if (unlikely(ret == -ERESTARTSYS || ret == -ERESTARTNOINTR ||
-			     ret == -ERESTARTNOHAND || ret == -ERESTART_RESTARTBLOCK))
-			ret = -EINTR;
-		aio_complete(iocb, ret, 0);
-	}
-out:
-	spin_lock_irq(&ctx->ctx_lock);
-
-	if (-EIOCBRETRY == ret) {
-		/*
-		 * OK, now that we are done with this iteration
-		 * and know that there is more left to go,
-		 * this is where we let go so that a subsequent
-		 * "kick" can start the next iteration
-		 */
-
-		/* will make __queue_kicked_iocb succeed from here on */
-		INIT_LIST_HEAD(&iocb->ki_run_list);
-		/* we must queue the next iteration ourselves, if it
-		 * has already been kicked */
-		if (kiocbIsKicked(iocb)) {
-			__queue_kicked_iocb(iocb);
-
-			/*
-			 * __queue_kicked_iocb will always return 1 here, because
-			 * iocb->ki_run_list is empty at this point so it should
-			 * be safe to unconditionally queue the context into the
-			 * work queue.
-			 */
-			aio_queue_work(ctx);
-		}
-	}
-	return ret;
-}
-
-/*
- * __aio_run_iocbs:
- * 	Process all pending retries queued on the ioctx
- * 	run list.
- * Assumes it is operating within the aio issuer's mm
- * context.
- */
-static int __aio_run_iocbs(struct kioctx *ctx)
-{
-	struct kiocb *iocb;
-	struct list_head run_list;
-
-	assert_spin_locked(&ctx->ctx_lock);
-
-	list_replace_init(&ctx->run_list, &run_list);
-	while (!list_empty(&run_list)) {
-		iocb = list_entry(run_list.next, struct kiocb,
-			ki_run_list);
-		list_del(&iocb->ki_run_list);
-		/*
-		 * Hold an extra reference while retrying i/o.
-		 */
-		iocb->ki_users++;       /* grab extra reference */
-		aio_run_iocb(iocb);
-		__aio_put_req(ctx, iocb);
- 	}
-	if (!list_empty(&ctx->run_list))
-		return 1;
-	return 0;
-}
-
-static void aio_queue_work(struct kioctx * ctx)
-{
-	unsigned long timeout;
-	/*
-	 * if someone is waiting, get the work started right
-	 * away, otherwise, use a longer delay
-	 */
-	smp_mb();
-	if (waitqueue_active(&ctx->wait))
-		timeout = 1;
-	else
-		timeout = HZ/10;
-	queue_delayed_work(aio_wq, &ctx->wq, timeout);
-}
-
-/*
- * aio_run_all_iocbs:
- *	Process all pending retries queued on the ioctx
- *	run list, and keep running them until the list
- *	stays empty.
- * Assumes it is operating within the aio issuer's mm context.
- */
-static inline void aio_run_all_iocbs(struct kioctx *ctx)
-{
-	spin_lock_irq(&ctx->ctx_lock);
-	while (__aio_run_iocbs(ctx))
-		;
-	spin_unlock_irq(&ctx->ctx_lock);
-}
-
-/*
- * aio_kick_handler:
- * 	Work queue handler triggered to process pending
- * 	retries on an ioctx. Takes on the aio issuer's
- *	mm context before running the iocbs, so that
- *	copy_xxx_user operates on the issuer's address
- *      space.
- * Run on aiod's context.
- */
-static void aio_kick_handler(struct work_struct *work)
-{
-	struct kioctx *ctx = container_of(work, struct kioctx, wq.work);
-	mm_segment_t oldfs = get_fs();
-	struct mm_struct *mm;
-	int requeue;
-
-	set_fs(USER_DS);
-	use_mm(ctx->mm);
-	spin_lock_irq(&ctx->ctx_lock);
-	requeue =__aio_run_iocbs(ctx);
-	mm = ctx->mm;
-	spin_unlock_irq(&ctx->ctx_lock);
- 	unuse_mm(mm);
-	set_fs(oldfs);
-	/*
-	 * we're in a worker thread already; no point using non-zero delay
-	 */
-	if (requeue)
-		queue_delayed_work(aio_wq, &ctx->wq, 0);
-}
-
-
-/*
- * Called by kick_iocb to queue the kiocb for retry
- * and if required activate the aio work queue to process
- * it
- */
-static void try_queue_kicked_iocb(struct kiocb *iocb)
-{
- 	struct kioctx	*ctx = iocb->ki_ctx;
-	unsigned long flags;
-	int run = 0;
-
-	spin_lock_irqsave(&ctx->ctx_lock, flags);
-	/* set this inside the lock so that we can't race with aio_run_iocb()
-	 * testing it and putting the iocb on the run list under the lock */
-	if (!kiocbTryKick(iocb))
-		run = __queue_kicked_iocb(iocb);
-	spin_unlock_irqrestore(&ctx->ctx_lock, flags);
-	if (run)
-		aio_queue_work(ctx);
-}
-
-/*
- * kick_iocb:
- *      Called typically from a wait queue callback context
- *      to trigger a retry of the iocb.
- *      The retry is usually executed by aio workqueue
- *      threads (See aio_kick_handler).
- */
-void kick_iocb(struct kiocb *iocb)
-{
-	/* sync iocbs are easy: they can only ever be executing from a 
-	 * single context. */
-	if (is_sync_kiocb(iocb)) {
-		kiocbSetKicked(iocb);
-	        wake_up_process(iocb->ki_obj.tsk);
-		return;
-	}
-
-	try_queue_kicked_iocb(iocb);
-}
-EXPORT_SYMBOL(kick_iocb);
-
 /* aio_complete
  *	Called when the io request on the given iocb is complete.
- *	Returns true if this is the last user of the request.  The 
- *	only other user of the request can be the cancellation code.
  */
-int aio_complete(struct kiocb *iocb, long res, long res2)
+void aio_complete(struct kiocb *iocb, long res, long res2)
 {
 	struct kioctx	*ctx = iocb->ki_ctx;
-	struct aio_ring_info	*info;
 	struct aio_ring	*ring;
-	struct io_event	*event;
+	struct io_event	*ev_page, *event;
 	unsigned long	flags;
-	unsigned long	tail;
-	int		ret;
+	unsigned tail, pos;
 
 	/*
 	 * Special case handling for sync iocbs:
@@ -909,61 +591,81 @@ int aio_complete(struct kiocb *iocb, long res, long res2)
 	 *  - the sync task helpfully left a reference to itself in the iocb
 	 */
 	if (is_sync_kiocb(iocb)) {
-		BUG_ON(iocb->ki_users != 1);
+		BUG_ON(atomic_read(&iocb->ki_users) != 1);
 		iocb->ki_user_data = res;
-		iocb->ki_users = 0;
+		atomic_set(&iocb->ki_users, 0);
 		wake_up_process(iocb->ki_obj.tsk);
-		return 1;
+		return;
 	}
 
-	info = &ctx->ring_info;
-
-	/* add a completion event to the ring buffer.
-	 * must be done holding ctx->ctx_lock to prevent
-	 * other code from messing with the tail
-	 * pointer since we might be called from irq
-	 * context.
+	/*
+	 * Take rcu_read_lock() in case the kioctx is being destroyed, as we
+	 * need to issue a wakeup after decrementing reqs_active.
 	 */
-	spin_lock_irqsave(&ctx->ctx_lock, flags);
+	rcu_read_lock();
 
-	if (iocb->ki_run_list.prev && !list_empty(&iocb->ki_run_list))
-		list_del_init(&iocb->ki_run_list);
+	if (iocb->ki_list.next) {
+		unsigned long flags;
+
+		spin_lock_irqsave(&ctx->ctx_lock, flags);
+		list_del(&iocb->ki_list);
+		spin_unlock_irqrestore(&ctx->ctx_lock, flags);
+	}
 
 	/*
 	 * cancelled requests don't get events, userland was given one
 	 * when the event got cancelled.
 	 */
-	if (kiocbIsCancelled(iocb))
+	if (unlikely(xchg(&iocb->ki_cancel,
+			  KIOCB_CANCELLED) == KIOCB_CANCELLED)) {
+		atomic_dec(&ctx->reqs_active);
+		/* Still need the wake_up in case free_ioctx is waiting */
 		goto put_rq;
+	}
 
-	ring = kmap_atomic(info->ring_pages[0]);
+	/*
+	 * Add a completion event to the ring buffer. Must be done holding
+	 * ctx->ctx_lock to prevent other code from messing with the tail
+	 * pointer since we might be called from irq context.
+	 */
+	spin_lock_irqsave(&ctx->completion_lock, flags);
 
-	tail = info->tail;
-	event = aio_ring_event(info, tail);
-	if (++tail >= info->nr)
+	tail = ctx->tail;
+	pos = tail + AIO_EVENTS_OFFSET;
+
+	if (++tail >= ctx->nr_events)
 		tail = 0;
 
+	ev_page = kmap_atomic(ctx->ring_pages[pos / AIO_EVENTS_PER_PAGE]);
+	event = ev_page + pos % AIO_EVENTS_PER_PAGE;
+
 	event->obj = (u64)(unsigned long)iocb->ki_obj.user;
 	event->data = iocb->ki_user_data;
 	event->res = res;
 	event->res2 = res2;
 
-	dprintk("aio_complete: %p[%lu]: %p: %p %Lx %lx %lx\n",
-		ctx, tail, iocb, iocb->ki_obj.user, iocb->ki_user_data,
-		res, res2);
+	kunmap_atomic(ev_page);
+	flush_dcache_page(ctx->ring_pages[pos / AIO_EVENTS_PER_PAGE]);
+
+	pr_debug("%p[%u]: %p: %p %Lx %lx %lx\n",
+		 ctx, tail, iocb, iocb->ki_obj.user, iocb->ki_user_data,
+		 res, res2);
 
 	/* after flagging the request as done, we
 	 * must never even look at it again
 	 */
 	smp_wmb();	/* make event visible before updating tail */
 
-	info->tail = tail;
-	ring->tail = tail;
+	ctx->tail = tail;
 
-	put_aio_ring_event(event);
+	ring = kmap_atomic(ctx->ring_pages[0]);
+	ring->tail = tail;
 	kunmap_atomic(ring);
+	flush_dcache_page(ctx->ring_pages[0]);
+
+	spin_unlock_irqrestore(&ctx->completion_lock, flags);
 
-	pr_debug("added to ring %p at [%lu]\n", iocb, tail);
+	pr_debug("added to ring %p at [%u]\n", iocb, tail);
 
 	/*
 	 * Check if the user asked us to deliver the result through an
@@ -975,7 +677,7 @@ int aio_complete(struct kiocb *iocb, long res, long res2)
 
 put_rq:
 	/* everything turned out well, dispose of the aiocb. */
-	ret = __aio_put_req(ctx, iocb);
+	aio_put_req(iocb);
 
 	/*
 	 * We have to order our ring_info tail store above and test
@@ -988,233 +690,133 @@ put_rq:
 	if (waitqueue_active(&ctx->wait))
 		wake_up(&ctx->wait);
 
-	spin_unlock_irqrestore(&ctx->ctx_lock, flags);
-	return ret;
+	rcu_read_unlock();
 }
 EXPORT_SYMBOL(aio_complete);
 
-/* aio_read_evt
- *	Pull an event off of the ioctx's event ring.  Returns the number of 
- *	events fetched (0 or 1 ;-)
- *	FIXME: make this use cmpxchg.
- *	TODO: make the ringbuffer user mmap()able (requires FIXME).
+/* aio_read_events
+ *	Pull an event off of the ioctx's event ring.  Returns the number of
+ *	events fetched
  */
-static int aio_read_evt(struct kioctx *ioctx, struct io_event *ent)
+static long aio_read_events_ring(struct kioctx *ctx,
+				 struct io_event __user *event, long nr)
 {
-	struct aio_ring_info *info = &ioctx->ring_info;
 	struct aio_ring *ring;
-	unsigned long head;
-	int ret = 0;
-
-	ring = kmap_atomic(info->ring_pages[0]);
-	dprintk("in aio_read_evt h%lu t%lu m%lu\n",
-		 (unsigned long)ring->head, (unsigned long)ring->tail,
-		 (unsigned long)ring->nr);
-
-	if (ring->head == ring->tail)
-		goto out;
+	unsigned head, pos;
+	long ret = 0;
+	int copy_ret;
 
-	spin_lock(&info->ring_lock);
-
-	head = ring->head % info->nr;
-	if (head != ring->tail) {
-		struct io_event *evp = aio_ring_event(info, head);
-		*ent = *evp;
-		head = (head + 1) % info->nr;
-		smp_mb(); /* finish reading the event before updatng the head */
-		ring->head = head;
-		ret = 1;
-		put_aio_ring_event(evp);
-	}
-	spin_unlock(&info->ring_lock);
+	mutex_lock(&ctx->ring_lock);
 
-out:
-	dprintk("leaving aio_read_evt: %d  h%lu t%lu\n", ret,
-		 (unsigned long)ring->head, (unsigned long)ring->tail);
+	ring = kmap_atomic(ctx->ring_pages[0]);
+	head = ring->head;
 	kunmap_atomic(ring);
-	return ret;
-}
 
-struct aio_timeout {
-	struct timer_list	timer;
-	int			timed_out;
-	struct task_struct	*p;
-};
+	pr_debug("h%u t%u m%u\n", head, ctx->tail, ctx->nr_events);
 
-static void timeout_func(unsigned long data)
-{
-	struct aio_timeout *to = (struct aio_timeout *)data;
+	if (head == ctx->tail)
+		goto out;
 
-	to->timed_out = 1;
-	wake_up_process(to->p);
-}
+	while (ret < nr) {
+		long avail;
+		struct io_event *ev;
+		struct page *page;
 
-static inline void init_timeout(struct aio_timeout *to)
-{
-	setup_timer_on_stack(&to->timer, timeout_func, (unsigned long) to);
-	to->timed_out = 0;
-	to->p = current;
-}
+		avail = (head <= ctx->tail ? ctx->tail : ctx->nr_events) - head;
+		if (head == ctx->tail)
+			break;
 
-static inline void set_timeout(long start_jiffies, struct aio_timeout *to,
-			       const struct timespec *ts)
-{
-	to->timer.expires = start_jiffies + timespec_to_jiffies(ts);
-	if (time_after(to->timer.expires, jiffies))
-		add_timer(&to->timer);
-	else
-		to->timed_out = 1;
-}
+		avail = min(avail, nr - ret);
+		avail = min_t(long, avail, AIO_EVENTS_PER_PAGE -
+			    ((head + AIO_EVENTS_OFFSET) % AIO_EVENTS_PER_PAGE));
 
-static inline void clear_timeout(struct aio_timeout *to)
-{
-	del_singleshot_timer_sync(&to->timer);
-}
+		pos = head + AIO_EVENTS_OFFSET;
+		page = ctx->ring_pages[pos / AIO_EVENTS_PER_PAGE];
+		pos %= AIO_EVENTS_PER_PAGE;
 
-static int read_events(struct kioctx *ctx,
-			long min_nr, long nr,
-			struct io_event __user *event,
-			struct timespec __user *timeout)
-{
-	long			start_jiffies = jiffies;
-	struct task_struct	*tsk = current;
-	DECLARE_WAITQUEUE(wait, tsk);
-	int			ret;
-	int			i = 0;
-	struct io_event		ent;
-	struct aio_timeout	to;
-	int			retry = 0;
-
-	/* needed to zero any padding within an entry (there shouldn't be 
-	 * any, but C is fun!
-	 */
-	memset(&ent, 0, sizeof(ent));
-retry:
-	ret = 0;
-	while (likely(i < nr)) {
-		ret = aio_read_evt(ctx, &ent);
-		if (unlikely(ret <= 0))
-			break;
-
-		dprintk("read event: %Lx %Lx %Lx %Lx\n",
-			ent.data, ent.obj, ent.res, ent.res2);
+		ev = kmap(page);
+		copy_ret = copy_to_user(event + ret, ev + pos,
+					sizeof(*ev) * avail);
+		kunmap(page);
 
-		/* Could we split the check in two? */
-		ret = -EFAULT;
-		if (unlikely(copy_to_user(event, &ent, sizeof(ent)))) {
-			dprintk("aio: lost an event due to EFAULT.\n");
-			break;
+		if (unlikely(copy_ret)) {
+			ret = -EFAULT;
+			goto out;
 		}
-		ret = 0;
 
-		/* Good, event copied to userland, update counts. */
-		event ++;
-		i ++;
+		ret += avail;
+		head += avail;
+		head %= ctx->nr_events;
 	}
 
-	if (min_nr <= i)
-		return i;
-	if (ret)
-		return ret;
+	ring = kmap_atomic(ctx->ring_pages[0]);
+	ring->head = head;
+	kunmap_atomic(ring);
+	flush_dcache_page(ctx->ring_pages[0]);
 
-	/* End fast path */
+	pr_debug("%li  h%u t%u\n", ret, head, ctx->tail);
 
-	/* racey check, but it gets redone */
-	if (!retry && unlikely(!list_empty(&ctx->run_list))) {
-		retry = 1;
-		aio_run_all_iocbs(ctx);
-		goto retry;
-	}
+	atomic_sub(ret, &ctx->reqs_active);
+out:
+	mutex_unlock(&ctx->ring_lock);
 
-	init_timeout(&to);
-	if (timeout) {
-		struct timespec	ts;
-		ret = -EFAULT;
-		if (unlikely(copy_from_user(&ts, timeout, sizeof(ts))))
-			goto out;
+	return ret;
+}
 
-		set_timeout(start_jiffies, &to, &ts);
-	}
+static bool aio_read_events(struct kioctx *ctx, long min_nr, long nr,
+			    struct io_event __user *event, long *i)
+{
+	long ret = aio_read_events_ring(ctx, event + *i, nr - *i);
 
-	while (likely(i < nr)) {
-		add_wait_queue_exclusive(&ctx->wait, &wait);
-		do {
-			set_task_state(tsk, TASK_INTERRUPTIBLE);
-			ret = aio_read_evt(ctx, &ent);
-			if (ret)
-				break;
-			if (min_nr <= i)
-				break;
-			if (unlikely(ctx->dead)) {
-				ret = -EINVAL;
-				break;
-			}
-			if (to.timed_out)	/* Only check after read evt */
-				break;
-			/* Try to only show up in io wait if there are ops
-			 *  in flight */
-			if (ctx->reqs_active)
-				io_schedule();
-			else
-				schedule();
-			if (signal_pending(tsk)) {
-				ret = -EINTR;
-				break;
-			}
-			/*ret = aio_read_evt(ctx, &ent);*/
-		} while (1) ;
-
-		set_task_state(tsk, TASK_RUNNING);
-		remove_wait_queue(&ctx->wait, &wait);
-
-		if (unlikely(ret <= 0))
-			break;
+	if (ret > 0)
+		*i += ret;
 
-		ret = -EFAULT;
-		if (unlikely(copy_to_user(event, &ent, sizeof(ent)))) {
-			dprintk("aio: lost an event due to EFAULT.\n");
-			break;
-		}
+	if (unlikely(atomic_read(&ctx->dead)))
+		ret = -EINVAL;
 
-		/* Good, event copied to userland, update counts. */
-		event ++;
-		i ++;
-	}
+	if (!*i)
+		*i = ret;
 
-	if (timeout)
-		clear_timeout(&to);
-out:
-	destroy_timer_on_stack(&to.timer);
-	return i ? i : ret;
+	return ret < 0 || *i >= min_nr;
 }
 
-/* Take an ioctx and remove it from the list of ioctx's.  Protects 
- * against races with itself via ->dead.
- */
-static void io_destroy(struct kioctx *ioctx)
+static long read_events(struct kioctx *ctx, long min_nr, long nr,
+			struct io_event __user *event,
+			struct timespec __user *timeout)
 {
-	struct mm_struct *mm = current->mm;
-	int was_dead;
+	ktime_t until = { .tv64 = KTIME_MAX };
+	long ret = 0;
 
-	/* delete the entry from the list is someone else hasn't already */
-	spin_lock(&mm->ioctx_lock);
-	was_dead = ioctx->dead;
-	ioctx->dead = 1;
-	hlist_del_rcu(&ioctx->list);
-	spin_unlock(&mm->ioctx_lock);
+	if (timeout) {
+		struct timespec	ts;
 
-	dprintk("aio_release(%p)\n", ioctx);
-	if (likely(!was_dead))
-		put_ioctx(ioctx);	/* twice for the list */
+		if (unlikely(copy_from_user(&ts, timeout, sizeof(ts))))
+			return -EFAULT;
 
-	kill_ctx(ioctx);
+		until = timespec_to_ktime(ts);
+	}
 
 	/*
-	 * Wake up any waiters.  The setting of ctx->dead must be seen
-	 * by other CPUs at this point.  Right now, we rely on the
-	 * locking done by the above calls to ensure this consistency.
+	 * Note that aio_read_events() is being called as the conditional - i.e.
+	 * we're calling it after prepare_to_wait() has set task state to
+	 * TASK_INTERRUPTIBLE.
+	 *
+	 * But aio_read_events() can block, and if it blocks it's going to flip
+	 * the task state back to TASK_RUNNING.
+	 *
+	 * This should be ok, provided it doesn't flip the state back to
+	 * TASK_RUNNING and return 0 too much - that causes us to spin. That
+	 * will only happen if the mutex_lock() call blocks, and we then find
+	 * the ringbuffer empty. So in practice we should be ok, but it's
+	 * something to be aware of when touching this code.
 	 */
-	wake_up_all(&ioctx->wait);
+	wait_event_interruptible_hrtimeout(ctx->wait,
+			aio_read_events(ctx, min_nr, nr, event, &ret), until);
+
+	if (!ret && signal_pending(current))
+		ret = -EINTR;
+
+	return ret;
 }
 
 /* sys_io_setup:
@@ -1252,7 +854,7 @@ SYSCALL_DEFINE2(io_setup, unsigned, nr_events, aio_context_t __user *, ctxp)
 	if (!IS_ERR(ioctx)) {
 		ret = put_user(ioctx->user_id, ctxp);
 		if (ret)
-			io_destroy(ioctx);
+			kill_ioctx(ioctx);
 		put_ioctx(ioctx);
 	}
 
@@ -1270,7 +872,7 @@ SYSCALL_DEFINE1(io_destroy, aio_context_t, ctx)
 {
 	struct kioctx *ioctx = lookup_ioctx(ctx);
 	if (likely(NULL != ioctx)) {
-		io_destroy(ioctx);
+		kill_ioctx(ioctx);
 		put_ioctx(ioctx);
 		return 0;
 	}
@@ -1301,30 +903,21 @@ static void aio_advance_iovec(struct kiocb *iocb, ssize_t ret)
 	BUG_ON(ret > 0 && iocb->ki_left == 0);
 }
 
-static ssize_t aio_rw_vect_retry(struct kiocb *iocb)
+typedef ssize_t (aio_rw_op)(struct kiocb *, const struct iovec *,
+			    unsigned long, loff_t);
+
+static ssize_t aio_rw_vect_retry(struct kiocb *iocb, int rw, aio_rw_op *rw_op)
 {
 	struct file *file = iocb->ki_filp;
 	struct address_space *mapping = file->f_mapping;
 	struct inode *inode = mapping->host;
-	ssize_t (*rw_op)(struct kiocb *, const struct iovec *,
-			 unsigned long, loff_t);
 	ssize_t ret = 0;
-	unsigned short opcode;
-
-	if ((iocb->ki_opcode == IOCB_CMD_PREADV) ||
-		(iocb->ki_opcode == IOCB_CMD_PREAD)) {
-		rw_op = file->f_op->aio_read;
-		opcode = IOCB_CMD_PREADV;
-	} else {
-		rw_op = file->f_op->aio_write;
-		opcode = IOCB_CMD_PWRITEV;
-	}
 
 	/* This matches the pread()/pwrite() logic */
 	if (iocb->ki_pos < 0)
 		return -EINVAL;
 
-	if (opcode == IOCB_CMD_PWRITEV)
+	if (rw == WRITE)
 		file_start_write(file);
 	do {
 		ret = rw_op(iocb, &iocb->ki_iovec[iocb->ki_cur_seg],
@@ -1336,9 +929,9 @@ static ssize_t aio_rw_vect_retry(struct kiocb *iocb)
 	/* retry all partial writes.  retry partial reads as long as its a
 	 * regular file. */
 	} while (ret > 0 && iocb->ki_left > 0 &&
-		 (opcode == IOCB_CMD_PWRITEV ||
+		 (rw == WRITE ||
 		  (!S_ISFIFO(inode->i_mode) && !S_ISSOCK(inode->i_mode))));
-	if (opcode == IOCB_CMD_PWRITEV)
+	if (rw == WRITE)
 		file_end_write(file);
 
 	/* This means we must have transferred all that we could */
@@ -1348,81 +941,49 @@ static ssize_t aio_rw_vect_retry(struct kiocb *iocb)
 
 	/* If we managed to write some out we return that, rather than
 	 * the eventual error. */
-	if (opcode == IOCB_CMD_PWRITEV
-	    && ret < 0 && ret != -EIOCBQUEUED && ret != -EIOCBRETRY
+	if (rw == WRITE
+	    && ret < 0 && ret != -EIOCBQUEUED
 	    && iocb->ki_nbytes - iocb->ki_left)
 		ret = iocb->ki_nbytes - iocb->ki_left;
 
 	return ret;
 }
 
-static ssize_t aio_fdsync(struct kiocb *iocb)
-{
-	struct file *file = iocb->ki_filp;
-	ssize_t ret = -EINVAL;
-
-	if (file->f_op->aio_fsync)
-		ret = file->f_op->aio_fsync(iocb, 1);
-	return ret;
-}
-
-static ssize_t aio_fsync(struct kiocb *iocb)
-{
-	struct file *file = iocb->ki_filp;
-	ssize_t ret = -EINVAL;
-
-	if (file->f_op->aio_fsync)
-		ret = file->f_op->aio_fsync(iocb, 0);
-	return ret;
-}
-
-static ssize_t aio_setup_vectored_rw(int type, struct kiocb *kiocb, bool compat)
+static ssize_t aio_setup_vectored_rw(int rw, struct kiocb *kiocb, bool compat)
 {
 	ssize_t ret;
 
+	kiocb->ki_nr_segs = kiocb->ki_nbytes;
+
 #ifdef CONFIG_COMPAT
 	if (compat)
-		ret = compat_rw_copy_check_uvector(type,
+		ret = compat_rw_copy_check_uvector(rw,
 				(struct compat_iovec __user *)kiocb->ki_buf,
-				kiocb->ki_nbytes, 1, &kiocb->ki_inline_vec,
+				kiocb->ki_nr_segs, 1, &kiocb->ki_inline_vec,
 				&kiocb->ki_iovec);
 	else
 #endif
-		ret = rw_copy_check_uvector(type,
+		ret = rw_copy_check_uvector(rw,
 				(struct iovec __user *)kiocb->ki_buf,
-				kiocb->ki_nbytes, 1, &kiocb->ki_inline_vec,
+				kiocb->ki_nr_segs, 1, &kiocb->ki_inline_vec,
 				&kiocb->ki_iovec);
 	if (ret < 0)
-		goto out;
-
-	ret = rw_verify_area(type, kiocb->ki_filp, &kiocb->ki_pos, ret);
-	if (ret < 0)
-		goto out;
+		return ret;
 
-	kiocb->ki_nr_segs = kiocb->ki_nbytes;
-	kiocb->ki_cur_seg = 0;
-	/* ki_nbytes/left now reflect bytes instead of segs */
+	/* ki_nbytes now reflect bytes instead of segs */
 	kiocb->ki_nbytes = ret;
-	kiocb->ki_left = ret;
-
-	ret = 0;
-out:
-	return ret;
+	return 0;
 }
 
-static ssize_t aio_setup_single_vector(int type, struct file * file, struct kiocb *kiocb)
+static ssize_t aio_setup_single_vector(int rw, struct kiocb *kiocb)
 {
-	int bytes;
-
-	bytes = rw_verify_area(type, file, &kiocb->ki_pos, kiocb->ki_left);
-	if (bytes < 0)
-		return bytes;
+	if (unlikely(!access_ok(!rw, kiocb->ki_buf, kiocb->ki_nbytes)))
+		return -EFAULT;
 
 	kiocb->ki_iovec = &kiocb->ki_inline_vec;
 	kiocb->ki_iovec->iov_base = kiocb->ki_buf;
-	kiocb->ki_iovec->iov_len = bytes;
+	kiocb->ki_iovec->iov_len = kiocb->ki_nbytes;
 	kiocb->ki_nr_segs = 1;
-	kiocb->ki_cur_seg = 0;
 	return 0;
 }
 
@@ -1431,96 +992,95 @@ static ssize_t aio_setup_single_vector(int type, struct file * file, struct kioc
  *	Performs the initial checks and aio retry method
  *	setup for the kiocb at the time of io submission.
  */
-static ssize_t aio_setup_iocb(struct kiocb *kiocb, bool compat)
+static ssize_t aio_run_iocb(struct kiocb *req, bool compat)
 {
-	struct file *file = kiocb->ki_filp;
-	ssize_t ret = 0;
+	struct file *file = req->ki_filp;
+	ssize_t ret;
+	int rw;
+	fmode_t mode;
+	aio_rw_op *rw_op;
 
-	switch (kiocb->ki_opcode) {
+	switch (req->ki_opcode) {
 	case IOCB_CMD_PREAD:
-		ret = -EBADF;
-		if (unlikely(!(file->f_mode & FMODE_READ)))
-			break;
-		ret = -EFAULT;
-		if (unlikely(!access_ok(VERIFY_WRITE, kiocb->ki_buf,
-			kiocb->ki_left)))
-			break;
-		ret = aio_setup_single_vector(READ, file, kiocb);
-		if (ret)
-			break;
-		ret = -EINVAL;
-		if (file->f_op->aio_read)
-			kiocb->ki_retry = aio_rw_vect_retry;
-		break;
-	case IOCB_CMD_PWRITE:
-		ret = -EBADF;
-		if (unlikely(!(file->f_mode & FMODE_WRITE)))
-			break;
-		ret = -EFAULT;
-		if (unlikely(!access_ok(VERIFY_READ, kiocb->ki_buf,
-			kiocb->ki_left)))
-			break;
-		ret = aio_setup_single_vector(WRITE, file, kiocb);
-		if (ret)
-			break;
-		ret = -EINVAL;
-		if (file->f_op->aio_write)
-			kiocb->ki_retry = aio_rw_vect_retry;
-		break;
 	case IOCB_CMD_PREADV:
-		ret = -EBADF;
-		if (unlikely(!(file->f_mode & FMODE_READ)))
-			break;
-		ret = aio_setup_vectored_rw(READ, kiocb, compat);
-		if (ret)
-			break;
-		ret = -EINVAL;
-		if (file->f_op->aio_read)
-			kiocb->ki_retry = aio_rw_vect_retry;
-		break;
+		mode	= FMODE_READ;
+		rw	= READ;
+		rw_op	= file->f_op->aio_read;
+		goto rw_common;
+
+	case IOCB_CMD_PWRITE:
 	case IOCB_CMD_PWRITEV:
-		ret = -EBADF;
-		if (unlikely(!(file->f_mode & FMODE_WRITE)))
-			break;
-		ret = aio_setup_vectored_rw(WRITE, kiocb, compat);
+		mode	= FMODE_WRITE;
+		rw	= WRITE;
+		rw_op	= file->f_op->aio_write;
+		goto rw_common;
+rw_common:
+		if (unlikely(!(file->f_mode & mode)))
+			return -EBADF;
+
+		if (!rw_op)
+			return -EINVAL;
+
+		ret = (req->ki_opcode == IOCB_CMD_PREADV ||
+		       req->ki_opcode == IOCB_CMD_PWRITEV)
+			? aio_setup_vectored_rw(rw, req, compat)
+			: aio_setup_single_vector(rw, req);
 		if (ret)
-			break;
-		ret = -EINVAL;
-		if (file->f_op->aio_write)
-			kiocb->ki_retry = aio_rw_vect_retry;
+			return ret;
+
+		ret = rw_verify_area(rw, file, &req->ki_pos, req->ki_nbytes);
+		if (ret < 0)
+			return ret;
+
+		req->ki_nbytes = ret;
+		req->ki_left = ret;
+
+		ret = aio_rw_vect_retry(req, rw, rw_op);
 		break;
+
 	case IOCB_CMD_FDSYNC:
-		ret = -EINVAL;
-		if (file->f_op->aio_fsync)
-			kiocb->ki_retry = aio_fdsync;
+		if (!file->f_op->aio_fsync)
+			return -EINVAL;
+
+		ret = file->f_op->aio_fsync(req, 1);
 		break;
+
 	case IOCB_CMD_FSYNC:
-		ret = -EINVAL;
-		if (file->f_op->aio_fsync)
-			kiocb->ki_retry = aio_fsync;
+		if (!file->f_op->aio_fsync)
+			return -EINVAL;
+
+		ret = file->f_op->aio_fsync(req, 0);
 		break;
+
 	default:
-		dprintk("EINVAL: io_submit: no operation provided\n");
-		ret = -EINVAL;
+		pr_debug("EINVAL: no operation provided\n");
+		return -EINVAL;
 	}
 
-	if (!kiocb->ki_retry)
-		return ret;
+	if (ret != -EIOCBQUEUED) {
+		/*
+		 * There's no easy way to restart the syscall since other AIO's
+		 * may be already running. Just fail this IO with EINTR.
+		 */
+		if (unlikely(ret == -ERESTARTSYS || ret == -ERESTARTNOINTR ||
+			     ret == -ERESTARTNOHAND ||
+			     ret == -ERESTART_RESTARTBLOCK))
+			ret = -EINTR;
+		aio_complete(req, ret, 0);
+	}
 
 	return 0;
 }
 
 static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
-			 struct iocb *iocb, struct kiocb_batch *batch,
-			 bool compat)
+			 struct iocb *iocb, bool compat)
 {
 	struct kiocb *req;
-	struct file *file;
 	ssize_t ret;
 
 	/* enforce forwards compatibility on users */
 	if (unlikely(iocb->aio_reserved1 || iocb->aio_reserved2)) {
-		pr_debug("EINVAL: io_submit: reserve field set\n");
+		pr_debug("EINVAL: reserve field set\n");
 		return -EINVAL;
 	}
 
@@ -1534,16 +1094,16 @@ static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
 		return -EINVAL;
 	}
 
-	file = fget(iocb->aio_fildes);
-	if (unlikely(!file))
-		return -EBADF;
-
-	req = aio_get_req(ctx, batch);  /* returns with 2 references to req */
-	if (unlikely(!req)) {
-		fput(file);
+	req = aio_get_req(ctx);
+	if (unlikely(!req))
 		return -EAGAIN;
+
+	req->ki_filp = fget(iocb->aio_fildes);
+	if (unlikely(!req->ki_filp)) {
+		ret = -EBADF;
+		goto out_put_req;
 	}
-	req->ki_filp = file;
+
 	if (iocb->aio_flags & IOCB_FLAG_RESFD) {
 		/*
 		 * If the IOCB_FLAG_RESFD flag of aio_flags is set, get an
@@ -1559,9 +1119,9 @@ static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
 		}
 	}
 
-	ret = put_user(req->ki_key, &user_iocb->aio_key);
+	ret = put_user(KIOCB_KEY, &user_iocb->aio_key);
 	if (unlikely(ret)) {
-		dprintk("EFAULT: aio_key\n");
+		pr_debug("EFAULT: aio_key\n");
 		goto out_put_req;
 	}
 
@@ -1573,41 +1133,14 @@ static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
 	req->ki_left = req->ki_nbytes = iocb->aio_nbytes;
 	req->ki_opcode = iocb->aio_lio_opcode;
 
-	ret = aio_setup_iocb(req, compat);
-
+	ret = aio_run_iocb(req, compat);
 	if (ret)
 		goto out_put_req;
 
-	spin_lock_irq(&ctx->ctx_lock);
-	/*
-	 * We could have raced with io_destroy() and are currently holding a
-	 * reference to ctx which should be destroyed. We cannot submit IO
-	 * since ctx gets freed as soon as io_submit() puts its reference.  The
-	 * check here is reliable: io_destroy() sets ctx->dead before waiting
-	 * for outstanding IO and the barrier between these two is realized by
-	 * unlock of mm->ioctx_lock and lock of ctx->ctx_lock.  Analogously we
-	 * increment ctx->reqs_active before checking for ctx->dead and the
-	 * barrier is realized by unlock and lock of ctx->ctx_lock. Thus if we
-	 * don't see ctx->dead set here, io_destroy() waits for our IO to
-	 * finish.
-	 */
-	if (ctx->dead) {
-		spin_unlock_irq(&ctx->ctx_lock);
-		ret = -EINVAL;
-		goto out_put_req;
-	}
-	aio_run_iocb(req);
-	if (!list_empty(&ctx->run_list)) {
-		/* drain the run list */
-		while (__aio_run_iocbs(ctx))
-			;
-	}
-	spin_unlock_irq(&ctx->ctx_lock);
-
 	aio_put_req(req);	/* drop extra ref to req */
 	return 0;
-
 out_put_req:
+	atomic_dec(&ctx->reqs_active);
 	aio_put_req(req);	/* drop extra ref to req */
 	aio_put_req(req);	/* drop i/o ref to req */
 	return ret;
@@ -1620,7 +1153,6 @@ long do_io_submit(aio_context_t ctx_id, long nr,
 	long ret = 0;
 	int i = 0;
 	struct blk_plug plug;
-	struct kiocb_batch batch;
 
 	if (unlikely(nr < 0))
 		return -EINVAL;
@@ -1633,12 +1165,10 @@ long do_io_submit(aio_context_t ctx_id, long nr,
 
 	ctx = lookup_ioctx(ctx_id);
 	if (unlikely(!ctx)) {
-		pr_debug("EINVAL: io_submit: invalid context id\n");
+		pr_debug("EINVAL: invalid context id\n");
 		return -EINVAL;
 	}
 
-	kiocb_batch_init(&batch, nr);
-
 	blk_start_plug(&plug);
 
 	/*
@@ -1659,13 +1189,12 @@ long do_io_submit(aio_context_t ctx_id, long nr,
 			break;
 		}
 
-		ret = io_submit_one(ctx, user_iocb, &tmp, &batch, compat);
+		ret = io_submit_one(ctx, user_iocb, &tmp, compat);
 		if (ret)
 			break;
 	}
 	blk_finish_plug(&plug);
 
-	kiocb_batch_free(ctx, &batch);
 	put_ioctx(ctx);
 	return i ? i : ret;
 }
@@ -1698,10 +1227,13 @@ static struct kiocb *lookup_kiocb(struct kioctx *ctx, struct iocb __user *iocb,
 
 	assert_spin_locked(&ctx->ctx_lock);
 
+	if (key != KIOCB_KEY)
+		return NULL;
+
 	/* TODO: use a hash or array, this sucks. */
 	list_for_each(pos, &ctx->active_reqs) {
 		struct kiocb *kiocb = list_kiocb(pos);
-		if (kiocb->ki_obj.user == iocb && kiocb->ki_key == key)
+		if (kiocb->ki_obj.user == iocb)
 			return kiocb;
 	}
 	return NULL;
@@ -1720,7 +1252,7 @@ static struct kiocb *lookup_kiocb(struct kioctx *ctx, struct iocb __user *iocb,
 SYSCALL_DEFINE3(io_cancel, aio_context_t, ctx_id, struct iocb __user *, iocb,
 		struct io_event __user *, result)
 {
-	int (*cancel)(struct kiocb *iocb, struct io_event *res);
+	struct io_event res;
 	struct kioctx *ctx;
 	struct kiocb *kiocb;
 	u32 key;
@@ -1735,32 +1267,22 @@ SYSCALL_DEFINE3(io_cancel, aio_context_t, ctx_id, struct iocb __user *, iocb,
 		return -EINVAL;
 
 	spin_lock_irq(&ctx->ctx_lock);
-	ret = -EAGAIN;
+
 	kiocb = lookup_kiocb(ctx, iocb, key);
-	if (kiocb && kiocb->ki_cancel) {
-		cancel = kiocb->ki_cancel;
-		kiocb->ki_users ++;
-		kiocbSetCancelled(kiocb);
-	} else
-		cancel = NULL;
+	if (kiocb)
+		ret = kiocb_cancel(ctx, kiocb, &res);
+	else
+		ret = -EINVAL;
+
 	spin_unlock_irq(&ctx->ctx_lock);
 
-	if (NULL != cancel) {
-		struct io_event tmp;
-		pr_debug("calling cancel\n");
-		memset(&tmp, 0, sizeof(tmp));
-		tmp.obj = (u64)(unsigned long)kiocb->ki_obj.user;
-		tmp.data = kiocb->ki_user_data;
-		ret = cancel(kiocb, &tmp);
-		if (!ret) {
-			/* Cancellation succeeded -- copy the result
-			 * into the user's buffer.
-			 */
-			if (copy_to_user(result, &tmp, sizeof(tmp)))
-				ret = -EFAULT;
-		}
-	} else
-		ret = -EINVAL;
+	if (!ret) {
+		/* Cancellation succeeded -- copy the result
+		 * into the user's buffer.
+		 */
+		if (copy_to_user(result, &res, sizeof(res)))
+			ret = -EFAULT;
+	}
 
 	put_ioctx(ctx);
 
diff --git a/fs/bio.c b/fs/bio.c
index b96fc6ce485..954d73124b4 100644
--- a/fs/bio.c
+++ b/fs/bio.c
@@ -19,6 +19,7 @@
 #include <linux/swap.h>
 #include <linux/bio.h>
 #include <linux/blkdev.h>
+#include <linux/uio.h>
 #include <linux/iocontext.h>
 #include <linux/slab.h>
 #include <linux/init.h>
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 3823d3ffb76..d9871c1f089 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -27,6 +27,7 @@
 #include <linux/namei.h>
 #include <linux/log2.h>
 #include <linux/cleancache.h>
+#include <linux/aio.h>
 #include <asm/uaccess.h>
 #include "internal.h"
 
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index bb8b7a0e28a..bc4d54c465a 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -24,6 +24,7 @@
 #include <linux/string.h>
 #include <linux/backing-dev.h>
 #include <linux/mpage.h>
+#include <linux/aio.h>
 #include <linux/falloc.h>
 #include <linux/swap.h>
 #include <linux/writeback.h>
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 09c58a35b42..898da0a01e0 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -32,6 +32,7 @@
 #include <linux/writeback.h>
 #include <linux/statfs.h>
 #include <linux/compat.h>
+#include <linux/aio.h>
 #include <linux/bit_spinlock.h>
 #include <linux/xattr.h>
 #include <linux/posix_acl.h>
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index d70830c6683..656e1690743 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -7,6 +7,7 @@
 #include <linux/mount.h>
 #include <linux/namei.h>
 #include <linux/writeback.h>
+#include <linux/aio.h>
 
 #include "super.h"
 #include "mds_client.h"
diff --git a/fs/compat.c b/fs/compat.c
index 93f7d021b71..fc3b55dce18 100644
--- a/fs/compat.c
+++ b/fs/compat.c
@@ -47,6 +47,7 @@
 #include <linux/fs_struct.h>
 #include <linux/slab.h>
 #include <linux/pagemap.h>
+#include <linux/aio.h>
 
 #include <asm/uaccess.h>
 #include <asm/mmu_context.h>
diff --git a/fs/direct-io.c b/fs/direct-io.c
index cfb816dc6d9..51d16e067d6 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -37,6 +37,7 @@
 #include <linux/uio.h>
 #include <linux/atomic.h>
 #include <linux/prefetch.h>
+#include <linux/aio.h>
 
 /*
  * How many user pages to map in one call to get_user_pages().  This determines
diff --git a/fs/ecryptfs/file.c b/fs/ecryptfs/file.c
index 63b1f54b6a1..201f0a0d6b0 100644
--- a/fs/ecryptfs/file.c
+++ b/fs/ecryptfs/file.c
@@ -31,6 +31,7 @@
 #include <linux/security.h>
 #include <linux/compat.h>
 #include <linux/fs_stack.h>
+#include <linux/aio.h>
 #include "ecryptfs_kernel.h"
 
 /**
diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c
index fe60cc1117d..0a87bb10998 100644
--- a/fs/ext2/inode.c
+++ b/fs/ext2/inode.c
@@ -31,6 +31,7 @@
 #include <linux/mpage.h>
 #include <linux/fiemap.h>
 #include <linux/namei.h>
+#include <linux/aio.h>
 #include "ext2.h"
 #include "acl.h"
 #include "xip.h"
diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c
index d706dbfa622..23c71282564 100644
--- a/fs/ext3/inode.c
+++ b/fs/ext3/inode.c
@@ -27,6 +27,7 @@
 #include <linux/writeback.h>
 #include <linux/mpage.h>
 #include <linux/namei.h>
+#include <linux/aio.h>
 #include "ext3.h"
 #include "xattr.h"
 #include "acl.h"
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 64848b595b2..4959e29573b 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -23,6 +23,7 @@
 #include <linux/jbd2.h>
 #include <linux/mount.h>
 #include <linux/path.h>
+#include <linux/aio.h>
 #include <linux/quotaops.h>
 #include <linux/pagevec.h>
 #include "ext4.h"
diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c
index 98be6f69746..b8d5d351e24 100644
--- a/fs/ext4/indirect.c
+++ b/fs/ext4/indirect.c
@@ -20,6 +20,7 @@
  *	(sct@redhat.com), 1993, 1998
  */
 
+#include <linux/aio.h>
 #include "ext4_jbd2.h"
 #include "truncate.h"
 #include "ext4_extents.h"	/* Needed for EXT_MAX_BLOCKS */
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 793d44b84d7..0723774bdfb 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -37,6 +37,7 @@
 #include <linux/printk.h>
 #include <linux/slab.h>
 #include <linux/ratelimit.h>
+#include <linux/aio.h>
 
 #include "ext4_jbd2.h"
 #include "xattr.h"
diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c
index 5929cd0baa2..19599bded62 100644
--- a/fs/ext4/page-io.c
+++ b/fs/ext4/page-io.c
@@ -18,6 +18,7 @@
 #include <linux/pagevec.h>
 #include <linux/mpage.h>
 #include <linux/namei.h>
+#include <linux/aio.h>
 #include <linux/uio.h>
 #include <linux/bio.h>
 #include <linux/workqueue.h>
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 7bd22a20112..d0ed4ba4b61 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -12,6 +12,7 @@
 #include <linux/f2fs_fs.h>
 #include <linux/buffer_head.h>
 #include <linux/mpage.h>
+#include <linux/aio.h>
 #include <linux/writeback.h>
 #include <linux/backing-dev.h>
 #include <linux/blkdev.h>
diff --git a/fs/fat/inode.c b/fs/fat/inode.c
index 4ff901632b2..dfce656ddb3 100644
--- a/fs/fat/inode.c
+++ b/fs/fat/inode.c
@@ -19,6 +19,7 @@
 #include <linux/mpage.h>
 #include <linux/buffer_head.h>
 #include <linux/mount.h>
+#include <linux/aio.h>
 #include <linux/vfs.h>
 #include <linux/parser.h>
 #include <linux/uio.h>
diff --git a/fs/fuse/cuse.c b/fs/fuse/cuse.c
index b3aaf7b3578..aef34b1e635 100644
--- a/fs/fuse/cuse.c
+++ b/fs/fuse/cuse.c
@@ -38,6 +38,7 @@
 #include <linux/device.h>
 #include <linux/file.h>
 #include <linux/fs.h>
+#include <linux/aio.h>
 #include <linux/kdev_t.h>
 #include <linux/kthread.h>
 #include <linux/list.h>
diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index a6c1664e330..1d55f946540 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -19,6 +19,7 @@
 #include <linux/pipe_fs_i.h>
 #include <linux/swap.h>
 #include <linux/splice.h>
+#include <linux/aio.h>
 
 MODULE_ALIAS_MISCDEV(FUSE_MINOR);
 MODULE_ALIAS("devname:fuse");
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 4655e59d545..d1c9b85b3f5 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -15,6 +15,7 @@
 #include <linux/module.h>
 #include <linux/compat.h>
 #include <linux/swap.h>
+#include <linux/aio.h>
 
 static const struct file_operations fuse_direct_io_file_operations;
 
diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c
index 9883694f1e7..0bad69ed633 100644
--- a/fs/gfs2/aops.c
+++ b/fs/gfs2/aops.c
@@ -20,6 +20,7 @@
 #include <linux/swap.h>
 #include <linux/gfs2_ondisk.h>
 #include <linux/backing-dev.h>
+#include <linux/aio.h>
 
 #include "gfs2.h"
 #include "incore.h"
diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c
index d79c2dadc53..acd16764b13 100644
--- a/fs/gfs2/file.c
+++ b/fs/gfs2/file.c
@@ -25,6 +25,7 @@
 #include <asm/uaccess.h>
 #include <linux/dlm.h>
 #include <linux/dlm_plock.h>
+#include <linux/aio.h>
 
 #include "gfs2.h"
 #include "incore.h"
diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c
index 716e1aafb2e..f9299d8a64e 100644
--- a/fs/hfs/inode.c
+++ b/fs/hfs/inode.c
@@ -14,6 +14,7 @@
 #include <linux/pagemap.h>
 #include <linux/mpage.h>
 #include <linux/sched.h>
+#include <linux/aio.h>
 
 #include "hfs_fs.h"
 #include "btree.h"
diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c
index 7faaa964968..f833d35630a 100644
--- a/fs/hfsplus/inode.c
+++ b/fs/hfsplus/inode.c
@@ -14,6 +14,7 @@
 #include <linux/pagemap.h>
 #include <linux/mpage.h>
 #include <linux/sched.h>
+#include <linux/aio.h>
 
 #include "hfsplus_fs.h"
 #include "hfsplus_raw.h"
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index 523464e6284..a3f868ae3fd 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -909,11 +909,8 @@ static int can_do_hugetlb_shm(void)
 
 static int get_hstate_idx(int page_size_log)
 {
-	struct hstate *h;
+	struct hstate *h = hstate_sizelog(page_size_log);
 
-	if (!page_size_log)
-		return default_hstate_idx;
-	h = size_to_hstate(1 << page_size_log);
 	if (!h)
 		return -1;
 	return h - hstates;
@@ -929,9 +926,12 @@ static struct dentry_operations anon_ops = {
 	.d_dname = hugetlb_dname
 };
 
-struct file *hugetlb_file_setup(const char *name, unsigned long addr,
-				size_t size, vm_flags_t acctflag,
-				struct user_struct **user,
+/*
+ * Note that size should be aligned to proper hugepage size in caller side,
+ * otherwise hugetlb_reserve_pages reserves one less hugepages than intended.
+ */
+struct file *hugetlb_file_setup(const char *name, size_t size,
+				vm_flags_t acctflag, struct user_struct **user,
 				int creat_flags, int page_size_log)
 {
 	struct file *file = ERR_PTR(-ENOMEM);
@@ -939,8 +939,6 @@ struct file *hugetlb_file_setup(const char *name, unsigned long addr,
 	struct path path;
 	struct super_block *sb;
 	struct qstr quick_string;
-	struct hstate *hstate;
-	unsigned long num_pages;
 	int hstate_idx;
 
 	hstate_idx = get_hstate_idx(page_size_log);
@@ -980,12 +978,10 @@ struct file *hugetlb_file_setup(const char *name, unsigned long addr,
 	if (!inode)
 		goto out_dentry;
 
-	hstate = hstate_inode(inode);
-	size += addr & ~huge_page_mask(hstate);
-	num_pages = ALIGN(size, huge_page_size(hstate)) >>
-			huge_page_shift(hstate);
 	file = ERR_PTR(-ENOMEM);
-	if (hugetlb_reserve_pages(inode, 0, num_pages, NULL, acctflag))
+	if (hugetlb_reserve_pages(inode, 0,
+			size >> huge_page_shift(hstate_inode(inode)), NULL,
+			acctflag))
 		goto out_inode;
 
 	d_instantiate(path.dentry, inode);
diff --git a/fs/jfs/inode.c b/fs/jfs/inode.c
index 77554b61d12..730f24e282a 100644
--- a/fs/jfs/inode.c
+++ b/fs/jfs/inode.c
@@ -23,6 +23,7 @@
 #include <linux/pagemap.h>
 #include <linux/quotaops.h>
 #include <linux/writeback.h>
+#include <linux/aio.h>
 #include "jfs_incore.h"
 #include "jfs_inode.h"
 #include "jfs_filsys.h"
diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c
index cf02f553071..689fb608648 100644
--- a/fs/nilfs2/inode.c
+++ b/fs/nilfs2/inode.c
@@ -25,7 +25,7 @@
 #include <linux/gfp.h>
 #include <linux/mpage.h>
 #include <linux/writeback.h>
-#include <linux/uio.h>
+#include <linux/aio.h>
 #include "nilfs.h"
 #include "btnode.h"
 #include "segment.h"
diff --git a/fs/ntfs/file.c b/fs/ntfs/file.c
index 1da4b81e6f7..c5670b8d198 100644
--- a/fs/ntfs/file.c
+++ b/fs/ntfs/file.c
@@ -27,6 +27,7 @@
 #include <linux/swap.h>
 #include <linux/uio.h>
 #include <linux/writeback.h>
+#include <linux/aio.h>
 
 #include <asm/page.h>
 #include <asm/uaccess.h>
diff --git a/fs/ntfs/inode.c b/fs/ntfs/inode.c
index d3e118cc6ff..2778b0255dc 100644
--- a/fs/ntfs/inode.c
+++ b/fs/ntfs/inode.c
@@ -28,6 +28,7 @@
 #include <linux/quotaops.h>
 #include <linux/slab.h>
 #include <linux/log2.h>
+#include <linux/aio.h>
 
 #include "aops.h"
 #include "attrib.h"
diff --git a/fs/ocfs2/aops.h b/fs/ocfs2/aops.h
index ffb2da370a9..f671e49beb3 100644
--- a/fs/ocfs2/aops.h
+++ b/fs/ocfs2/aops.h
@@ -22,6 +22,8 @@
 #ifndef OCFS2_AOPS_H
 #define OCFS2_AOPS_H
 
+#include <linux/aio.h>
+
 handle_t *ocfs2_start_walk_page_trans(struct inode *inode,
 							 struct page *page,
 							 unsigned from,
diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c
index 12ae194ac94..3a44a648dae 100644
--- a/fs/ocfs2/dlmglue.c
+++ b/fs/ocfs2/dlmglue.c
@@ -2322,7 +2322,7 @@ int ocfs2_inode_lock_full_nested(struct inode *inode,
 	status = __ocfs2_cluster_lock(osb, lockres, level, dlm_flags,
 				      arg_flags, subclass, _RET_IP_);
 	if (status < 0) {
-		if (status != -EAGAIN && status != -EIOCBRETRY)
+		if (status != -EAGAIN)
 			mlog_errno(status);
 		goto bail;
 	}
diff --git a/fs/ocfs2/inode.h b/fs/ocfs2/inode.h
index 88924a3133f..621fc73bf23 100644
--- a/fs/ocfs2/inode.h
+++ b/fs/ocfs2/inode.h
@@ -147,8 +147,6 @@ void ocfs2_refresh_inode(struct inode *inode,
 int ocfs2_mark_inode_dirty(handle_t *handle,
 			   struct inode *inode,
 			   struct buffer_head *bh);
-int ocfs2_aio_read(struct file *file, struct kiocb *req, struct iocb *iocb);
-int ocfs2_aio_write(struct file *file, struct kiocb *req, struct iocb *iocb);
 struct buffer_head *ocfs2_bread(struct inode *inode,
 				int block, int *err, int reada);
 
diff --git a/fs/pipe.c b/fs/pipe.c
index a029a14bacf..d2c45e14e6d 100644
--- a/fs/pipe.c
+++ b/fs/pipe.c
@@ -21,6 +21,7 @@
 #include <linux/audit.h>
 #include <linux/syscalls.h>
 #include <linux/fcntl.h>
+#include <linux/aio.h>
 
 #include <asm/uaccess.h>
 #include <asm/ioctls.h>
diff --git a/fs/read_write.c b/fs/read_write.c
index 90ba3b350e5..03430008704 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -9,6 +9,7 @@
 #include <linux/fcntl.h>
 #include <linux/file.h>
 #include <linux/uio.h>
+#include <linux/aio.h>
 #include <linux/fsnotify.h>
 #include <linux/security.h>
 #include <linux/export.h>
@@ -329,16 +330,6 @@ int rw_verify_area(int read_write, struct file *file, loff_t *ppos, size_t count
 	return count > MAX_RW_COUNT ? MAX_RW_COUNT : count;
 }
 
-static void wait_on_retry_sync_kiocb(struct kiocb *iocb)
-{
-	set_current_state(TASK_UNINTERRUPTIBLE);
-	if (!kiocbIsKicked(iocb))
-		schedule();
-	else
-		kiocbClearKicked(iocb);
-	__set_current_state(TASK_RUNNING);
-}
-
 ssize_t do_sync_read(struct file *filp, char __user *buf, size_t len, loff_t *ppos)
 {
 	struct iovec iov = { .iov_base = buf, .iov_len = len };
@@ -350,13 +341,7 @@ ssize_t do_sync_read(struct file *filp, char __user *buf, size_t len, loff_t *pp
 	kiocb.ki_left = len;
 	kiocb.ki_nbytes = len;
 
-	for (;;) {
-		ret = filp->f_op->aio_read(&kiocb, &iov, 1, kiocb.ki_pos);
-		if (ret != -EIOCBRETRY)
-			break;
-		wait_on_retry_sync_kiocb(&kiocb);
-	}
-
+	ret = filp->f_op->aio_read(&kiocb, &iov, 1, kiocb.ki_pos);
 	if (-EIOCBQUEUED == ret)
 		ret = wait_on_sync_kiocb(&kiocb);
 	*ppos = kiocb.ki_pos;
@@ -406,13 +391,7 @@ ssize_t do_sync_write(struct file *filp, const char __user *buf, size_t len, lof
 	kiocb.ki_left = len;
 	kiocb.ki_nbytes = len;
 
-	for (;;) {
-		ret = filp->f_op->aio_write(&kiocb, &iov, 1, kiocb.ki_pos);
-		if (ret != -EIOCBRETRY)
-			break;
-		wait_on_retry_sync_kiocb(&kiocb);
-	}
-
+	ret = filp->f_op->aio_write(&kiocb, &iov, 1, kiocb.ki_pos);
 	if (-EIOCBQUEUED == ret)
 		ret = wait_on_sync_kiocb(&kiocb);
 	*ppos = kiocb.ki_pos;
@@ -592,13 +571,7 @@ static ssize_t do_sync_readv_writev(struct file *filp, const struct iovec *iov,
 	kiocb.ki_left = len;
 	kiocb.ki_nbytes = len;
 
-	for (;;) {
-		ret = fn(&kiocb, iov, nr_segs, kiocb.ki_pos);
-		if (ret != -EIOCBRETRY)
-			break;
-		wait_on_retry_sync_kiocb(&kiocb);
-	}
-
+	ret = fn(&kiocb, iov, nr_segs, kiocb.ki_pos);
 	if (ret == -EIOCBQUEUED)
 		ret = wait_on_sync_kiocb(&kiocb);
 	*ppos = kiocb.ki_pos;
diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c
index ea5061fd4f3..77d6d47abc8 100644
--- a/fs/reiserfs/inode.c
+++ b/fs/reiserfs/inode.c
@@ -18,6 +18,7 @@
 #include <linux/writeback.h>
 #include <linux/quotaops.h>
 #include <linux/swap.h>
+#include <linux/aio.h>
 
 int reiserfs_commit_write(struct file *f, struct page *page,
 			  unsigned from, unsigned to);
diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c
index f12189d2db1..14374530784 100644
--- a/fs/ubifs/file.c
+++ b/fs/ubifs/file.c
@@ -50,6 +50,7 @@
  */
 
 #include "ubifs.h"
+#include <linux/aio.h>
 #include <linux/mount.h>
 #include <linux/namei.h>
 #include <linux/slab.h>
diff --git a/fs/udf/inode.c b/fs/udf/inode.c
index 7a12e48ad81..b6d15d34981 100644
--- a/fs/udf/inode.c
+++ b/fs/udf/inode.c
@@ -38,6 +38,7 @@
 #include <linux/slab.h>
 #include <linux/crc-itu-t.h>
 #include <linux/mpage.h>
+#include <linux/aio.h>
 
 #include "udf_i.h"
 #include "udf_sb.h"
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 3244c988d37..2b2691b7342 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -31,6 +31,7 @@
 #include "xfs_vnodeops.h"
 #include "xfs_trace.h"
 #include "xfs_bmap.h"
+#include <linux/aio.h>
 #include <linux/gfp.h>
 #include <linux/mpage.h>
 #include <linux/pagevec.h>
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 054d60c0ac5..a5f2042aec8 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -36,6 +36,7 @@
 #include "xfs_ioctl.h"
 #include "xfs_trace.h"
 
+#include <linux/aio.h>
 #include <linux/dcache.h>
 #include <linux/falloc.h>
 #include <linux/pagevec.h>
diff --git a/include/linux/aio.h b/include/linux/aio.h
index 31ff6dba487..1bdf965339f 100644
--- a/include/linux/aio.h
+++ b/include/linux/aio.h
@@ -9,91 +9,32 @@
 
 #include <linux/atomic.h>
 
-#define AIO_MAXSEGS		4
-#define AIO_KIOGRP_NR_ATOMIC	8
-
 struct kioctx;
+struct kiocb;
 
-/* Notes on cancelling a kiocb:
- *	If a kiocb is cancelled, aio_complete may return 0 to indicate 
- *	that cancel has not yet disposed of the kiocb.  All cancel 
- *	operations *must* call aio_put_req to dispose of the kiocb 
- *	to guard against races with the completion code.
- */
-#define KIOCB_C_CANCELLED	0x01
-#define KIOCB_C_COMPLETE	0x02
-
-#define KIOCB_SYNC_KEY		(~0U)
+#define KIOCB_KEY		0
 
-/* ki_flags bits */
 /*
- * This may be used for cancel/retry serialization in the future, but
- * for now it's unused and we probably don't want modules to even
- * think they can use it.
+ * We use ki_cancel == KIOCB_CANCELLED to indicate that a kiocb has been either
+ * cancelled or completed (this makes a certain amount of sense because
+ * successful cancellation - io_cancel() - does deliver the completion to
+ * userspace).
+ *
+ * And since most things don't implement kiocb cancellation and we'd really like
+ * kiocb completion to be lockless when possible, we use ki_cancel to
+ * synchronize cancellation and completion - we only set it to KIOCB_CANCELLED
+ * with xchg() or cmpxchg(), see batch_complete_aio() and kiocb_cancel().
  */
-/* #define KIF_LOCKED		0 */
-#define KIF_KICKED		1
-#define KIF_CANCELLED		2
-
-#define kiocbTryLock(iocb)	test_and_set_bit(KIF_LOCKED, &(iocb)->ki_flags)
-#define kiocbTryKick(iocb)	test_and_set_bit(KIF_KICKED, &(iocb)->ki_flags)
+#define KIOCB_CANCELLED		((void *) (~0ULL))
 
-#define kiocbSetLocked(iocb)	set_bit(KIF_LOCKED, &(iocb)->ki_flags)
-#define kiocbSetKicked(iocb)	set_bit(KIF_KICKED, &(iocb)->ki_flags)
-#define kiocbSetCancelled(iocb)	set_bit(KIF_CANCELLED, &(iocb)->ki_flags)
+typedef int (kiocb_cancel_fn)(struct kiocb *, struct io_event *);
 
-#define kiocbClearLocked(iocb)	clear_bit(KIF_LOCKED, &(iocb)->ki_flags)
-#define kiocbClearKicked(iocb)	clear_bit(KIF_KICKED, &(iocb)->ki_flags)
-#define kiocbClearCancelled(iocb)	clear_bit(KIF_CANCELLED, &(iocb)->ki_flags)
-
-#define kiocbIsLocked(iocb)	test_bit(KIF_LOCKED, &(iocb)->ki_flags)
-#define kiocbIsKicked(iocb)	test_bit(KIF_KICKED, &(iocb)->ki_flags)
-#define kiocbIsCancelled(iocb)	test_bit(KIF_CANCELLED, &(iocb)->ki_flags)
-
-/* is there a better place to document function pointer methods? */
-/**
- * ki_retry	-	iocb forward progress callback
- * @kiocb:	The kiocb struct to advance by performing an operation.
- *
- * This callback is called when the AIO core wants a given AIO operation
- * to make forward progress.  The kiocb argument describes the operation
- * that is to be performed.  As the operation proceeds, perhaps partially,
- * ki_retry is expected to update the kiocb with progress made.  Typically
- * ki_retry is set in the AIO core and it itself calls file_operations
- * helpers.
- *
- * ki_retry's return value determines when the AIO operation is completed
- * and an event is generated in the AIO event ring.  Except the special
- * return values described below, the value that is returned from ki_retry
- * is transferred directly into the completion ring as the operation's
- * resulting status.  Once this has happened ki_retry *MUST NOT* reference
- * the kiocb pointer again.
- *
- * If ki_retry returns -EIOCBQUEUED it has made a promise that aio_complete()
- * will be called on the kiocb pointer in the future.  The AIO core will
- * not ask the method again -- ki_retry must ensure forward progress.
- * aio_complete() must be called once and only once in the future, multiple
- * calls may result in undefined behaviour.
- *
- * If ki_retry returns -EIOCBRETRY it has made a promise that kick_iocb()
- * will be called on the kiocb pointer in the future.  This may happen
- * through generic helpers that associate kiocb->ki_wait with a wait
- * queue head that ki_retry uses via current->io_wait.  It can also happen
- * with custom tracking and manual calls to kick_iocb(), though that is
- * discouraged.  In either case, kick_iocb() must be called once and only
- * once.  ki_retry must ensure forward progress, the AIO core will wait
- * indefinitely for kick_iocb() to be called.
- */
 struct kiocb {
-	struct list_head	ki_run_list;
-	unsigned long		ki_flags;
-	int			ki_users;
-	unsigned		ki_key;		/* id of this request */
+	atomic_t		ki_users;
 
 	struct file		*ki_filp;
-	struct kioctx		*ki_ctx;	/* may be NULL for sync ops */
-	int			(*ki_cancel)(struct kiocb *, struct io_event *);
-	ssize_t			(*ki_retry)(struct kiocb *);
+	struct kioctx		*ki_ctx;	/* NULL for sync ops */
+	kiocb_cancel_fn		*ki_cancel;
 	void			(*ki_dtor)(struct kiocb *);
 
 	union {
@@ -117,7 +58,6 @@ struct kiocb {
 
 	struct list_head	ki_list;	/* the aio core uses this
 						 * for cancellation */
-	struct list_head	ki_batch;	/* batch allocation */
 
 	/*
 	 * If the aio_resfd field of the userspace iocb is not zero,
@@ -128,106 +68,40 @@ struct kiocb {
 
 static inline bool is_sync_kiocb(struct kiocb *kiocb)
 {
-	return kiocb->ki_key == KIOCB_SYNC_KEY;
+	return kiocb->ki_ctx == NULL;
 }
 
 static inline void init_sync_kiocb(struct kiocb *kiocb, struct file *filp)
 {
 	*kiocb = (struct kiocb) {
-			.ki_users = 1,
-			.ki_key = KIOCB_SYNC_KEY,
+			.ki_users = ATOMIC_INIT(1),
+			.ki_ctx = NULL,
 			.ki_filp = filp,
 			.ki_obj.tsk = current,
 		};
 }
 
-#define AIO_RING_MAGIC			0xa10a10a1
-#define AIO_RING_COMPAT_FEATURES	1
-#define AIO_RING_INCOMPAT_FEATURES	0
-struct aio_ring {
-	unsigned	id;	/* kernel internal index number */
-	unsigned	nr;	/* number of io_events */
-	unsigned	head;
-	unsigned	tail;
-
-	unsigned	magic;
-	unsigned	compat_features;
-	unsigned	incompat_features;
-	unsigned	header_length;	/* size of aio_ring */
-
-
-	struct io_event		io_events[0];
-}; /* 128 bytes + ring size */
-
-#define AIO_RING_PAGES	8
-struct aio_ring_info {
-	unsigned long		mmap_base;
-	unsigned long		mmap_size;
-
-	struct page		**ring_pages;
-	spinlock_t		ring_lock;
-	long			nr_pages;
-
-	unsigned		nr, tail;
-
-	struct page		*internal_pages[AIO_RING_PAGES];
-};
-
-static inline unsigned aio_ring_avail(struct aio_ring_info *info,
-					struct aio_ring *ring)
-{
-	return (ring->head + info->nr - 1 - ring->tail) % info->nr;
-}
-
-struct kioctx {
-	atomic_t		users;
-	int			dead;
-	struct mm_struct	*mm;
-
-	/* This needs improving */
-	unsigned long		user_id;
-	struct hlist_node	list;
-
-	wait_queue_head_t	wait;
-
-	spinlock_t		ctx_lock;
-
-	int			reqs_active;
-	struct list_head	active_reqs;	/* used for cancellation */
-	struct list_head	run_list;	/* used for kicked reqs */
-
-	/* sys_io_setup currently limits this to an unsigned int */
-	unsigned		max_reqs;
-
-	struct aio_ring_info	ring_info;
-
-	struct delayed_work	wq;
-
-	struct rcu_head		rcu_head;
-};
-
 /* prototypes */
-extern unsigned aio_max_size;
-
 #ifdef CONFIG_AIO
 extern ssize_t wait_on_sync_kiocb(struct kiocb *iocb);
-extern int aio_put_req(struct kiocb *iocb);
-extern void kick_iocb(struct kiocb *iocb);
-extern int aio_complete(struct kiocb *iocb, long res, long res2);
+extern void aio_put_req(struct kiocb *iocb);
+extern void aio_complete(struct kiocb *iocb, long res, long res2);
 struct mm_struct;
 extern void exit_aio(struct mm_struct *mm);
 extern long do_io_submit(aio_context_t ctx_id, long nr,
 			 struct iocb __user *__user *iocbpp, bool compat);
+void kiocb_set_cancel_fn(struct kiocb *req, kiocb_cancel_fn *cancel);
 #else
 static inline ssize_t wait_on_sync_kiocb(struct kiocb *iocb) { return 0; }
-static inline int aio_put_req(struct kiocb *iocb) { return 0; }
-static inline void kick_iocb(struct kiocb *iocb) { }
-static inline int aio_complete(struct kiocb *iocb, long res, long res2) { return 0; }
+static inline void aio_put_req(struct kiocb *iocb) { }
+static inline void aio_complete(struct kiocb *iocb, long res, long res2) { }
 struct mm_struct;
 static inline void exit_aio(struct mm_struct *mm) { }
 static inline long do_io_submit(aio_context_t ctx_id, long nr,
 				struct iocb __user * __user *iocbpp,
 				bool compat) { return 0; }
+static inline void kiocb_set_cancel_fn(struct kiocb *req,
+				       kiocb_cancel_fn *cancel) { }
 #endif /* CONFIG_AIO */
 
 static inline struct kiocb *list_kiocb(struct list_head *h)
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 3bff9ce09cf..5047355b9a0 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -28,6 +28,7 @@ struct cgroup_subsys;
 struct inode;
 struct cgroup;
 struct css_id;
+struct eventfd_ctx;
 
 extern int cgroup_init_early(void);
 extern int cgroup_init(void);
diff --git a/include/linux/errno.h b/include/linux/errno.h
index f6bf082d4d4..89627b9187f 100644
--- a/include/linux/errno.h
+++ b/include/linux/errno.h
@@ -28,6 +28,5 @@
 #define EBADTYPE	527	/* Type not supported by server */
 #define EJUKEBOX	528	/* Request initiated, but will not complete before timeout */
 #define EIOCBQUEUED	529	/* iocb queued, will get completion event */
-#define EIOCBRETRY	530	/* iocb queued, will trigger a retry */
 
 #endif
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 3a62df310f2..6b4890fa57e 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -189,8 +189,7 @@ static inline struct hugetlbfs_sb_info *HUGETLBFS_SB(struct super_block *sb)
 
 extern const struct file_operations hugetlbfs_file_operations;
 extern const struct vm_operations_struct hugetlb_vm_ops;
-struct file *hugetlb_file_setup(const char *name, unsigned long addr,
-				size_t size, vm_flags_t acct,
+struct file *hugetlb_file_setup(const char *name, size_t size, vm_flags_t acct,
 				struct user_struct **user, int creat_flags,
 				int page_size_log);
 
@@ -209,8 +208,8 @@ static inline int is_file_hugepages(struct file *file)
 
 #define is_file_hugepages(file)			0
 static inline struct file *
-hugetlb_file_setup(const char *name, unsigned long addr, size_t size,
-		vm_flags_t acctflag, struct user_struct **user, int creat_flags,
+hugetlb_file_setup(const char *name, size_t size, vm_flags_t acctflag,
+		struct user_struct **user, int creat_flags,
 		int page_size_log)
 {
 	return ERR_PTR(-ENOSYS);
@@ -288,6 +287,13 @@ static inline struct hstate *hstate_file(struct file *f)
 	return hstate_inode(file_inode(f));
 }
 
+static inline struct hstate *hstate_sizelog(int page_size_log)
+{
+	if (!page_size_log)
+		return &default_hstate;
+	return size_to_hstate(1 << page_size_log);
+}
+
 static inline struct hstate *hstate_vma(struct vm_area_struct *vma)
 {
 	return hstate_file(vma->vm_file);
@@ -352,11 +358,12 @@ static inline int hstate_index(struct hstate *h)
 	return h - hstates;
 }
 
-#else
+#else	/* CONFIG_HUGETLB_PAGE */
 struct hstate {};
 #define alloc_huge_page_node(h, nid) NULL
 #define alloc_bootmem_huge_page(h) NULL
 #define hstate_file(f) NULL
+#define hstate_sizelog(s) NULL
 #define hstate_vma(v) NULL
 #define hstate_inode(i) NULL
 #define huge_page_size(h) PAGE_SIZE
@@ -371,6 +378,6 @@ static inline unsigned int pages_per_huge_page(struct hstate *h)
 }
 #define hstate_index_to_shift(index) 0
 #define hstate_index(h) 0
-#endif
+#endif	/* CONFIG_HUGETLB_PAGE */
 
 #endif /* _LINUX_HUGETLB_H */
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 1a7f19e7f1a..e0c8528a41a 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -951,13 +951,19 @@ void unmap_vmas(struct mmu_gather *tlb, struct vm_area_struct *start_vma,
  * (see walk_page_range for more details)
  */
 struct mm_walk {
-	int (*pgd_entry)(pgd_t *, unsigned long, unsigned long, struct mm_walk *);
-	int (*pud_entry)(pud_t *, unsigned long, unsigned long, struct mm_walk *);
-	int (*pmd_entry)(pmd_t *, unsigned long, unsigned long, struct mm_walk *);
-	int (*pte_entry)(pte_t *, unsigned long, unsigned long, struct mm_walk *);
-	int (*pte_hole)(unsigned long, unsigned long, struct mm_walk *);
-	int (*hugetlb_entry)(pte_t *, unsigned long,
-			     unsigned long, unsigned long, struct mm_walk *);
+	int (*pgd_entry)(pgd_t *pgd, unsigned long addr,
+			 unsigned long next, struct mm_walk *walk);
+	int (*pud_entry)(pud_t *pud, unsigned long addr,
+	                 unsigned long next, struct mm_walk *walk);
+	int (*pmd_entry)(pmd_t *pmd, unsigned long addr,
+			 unsigned long next, struct mm_walk *walk);
+	int (*pte_entry)(pte_t *pte, unsigned long addr,
+			 unsigned long next, struct mm_walk *walk);
+	int (*pte_hole)(unsigned long addr, unsigned long next,
+			struct mm_walk *walk);
+	int (*hugetlb_entry)(pte_t *pte, unsigned long hmask,
+			     unsigned long addr, unsigned long next,
+			     struct mm_walk *walk);
 	struct mm_struct *mm;
 	void *private;
 };
diff --git a/include/linux/pid_namespace.h b/include/linux/pid_namespace.h
index 731e4ecee3b..e2772666f00 100644
--- a/include/linux/pid_namespace.h
+++ b/include/linux/pid_namespace.h
@@ -4,6 +4,7 @@
 #include <linux/sched.h>
 #include <linux/bug.h>
 #include <linux/mm.h>
+#include <linux/workqueue.h>
 #include <linux/threads.h>
 #include <linux/nsproxy.h>
 #include <linux/kref.h>
diff --git a/include/linux/random.h b/include/linux/random.h
index 347ce553a30..3b9377d6b7a 100644
--- a/include/linux/random.h
+++ b/include/linux/random.h
@@ -29,13 +29,6 @@ u32 prandom_u32(void);
 void prandom_bytes(void *buf, int nbytes);
 void prandom_seed(u32 seed);
 
-/*
- * These macros are preserved for backward compatibility and should be
- * removed as soon as a transition is finished.
- */
-#define random32() prandom_u32()
-#define srandom32(seed) prandom_seed(seed)
-
 u32 prandom_u32_state(struct rnd_state *);
 void prandom_bytes_state(struct rnd_state *state, void *buf, int nbytes);
 
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 4800e9d1864..022c085ac3c 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -313,8 +313,6 @@ extern void schedule_preempt_disabled(void);
 struct nsproxy;
 struct user_namespace;
 
-#include <linux/aio.h>
-
 #ifdef CONFIG_MMU
 extern void arch_pick_mmap_layout(struct mm_struct *mm);
 extern unsigned long
diff --git a/include/linux/wait.h b/include/linux/wait.h
index 7cb64d4b499..ac38be2692d 100644
--- a/include/linux/wait.h
+++ b/include/linux/wait.h
@@ -330,6 +330,92 @@ do {									\
 	__ret;								\
 })
 
+#define __wait_event_hrtimeout(wq, condition, timeout, state)		\
+({									\
+	int __ret = 0;							\
+	DEFINE_WAIT(__wait);						\
+	struct hrtimer_sleeper __t;					\
+									\
+	hrtimer_init_on_stack(&__t.timer, CLOCK_MONOTONIC,		\
+			      HRTIMER_MODE_REL);			\
+	hrtimer_init_sleeper(&__t, current);				\
+	if ((timeout).tv64 != KTIME_MAX)				\
+		hrtimer_start_range_ns(&__t.timer, timeout,		\
+				       current->timer_slack_ns,		\
+				       HRTIMER_MODE_REL);		\
+									\
+	for (;;) {							\
+		prepare_to_wait(&wq, &__wait, state);			\
+		if (condition)						\
+			break;						\
+		if (state == TASK_INTERRUPTIBLE &&			\
+		    signal_pending(current)) {				\
+			__ret = -ERESTARTSYS;				\
+			break;						\
+		}							\
+		if (!__t.task) {					\
+			__ret = -ETIME;					\
+			break;						\
+		}							\
+		schedule();						\
+	}								\
+									\
+	hrtimer_cancel(&__t.timer);					\
+	destroy_hrtimer_on_stack(&__t.timer);				\
+	finish_wait(&wq, &__wait);					\
+	__ret;								\
+})
+
+/**
+ * wait_event_hrtimeout - sleep until a condition gets true or a timeout elapses
+ * @wq: the waitqueue to wait on
+ * @condition: a C expression for the event to wait for
+ * @timeout: timeout, as a ktime_t
+ *
+ * The process is put to sleep (TASK_UNINTERRUPTIBLE) until the
+ * @condition evaluates to true or a signal is received.
+ * The @condition is checked each time the waitqueue @wq is woken up.
+ *
+ * wake_up() has to be called after changing any variable that could
+ * change the result of the wait condition.
+ *
+ * The function returns 0 if @condition became true, or -ETIME if the timeout
+ * elapsed.
+ */
+#define wait_event_hrtimeout(wq, condition, timeout)			\
+({									\
+	int __ret = 0;							\
+	if (!(condition))						\
+		__ret = __wait_event_hrtimeout(wq, condition, timeout,	\
+					       TASK_UNINTERRUPTIBLE);	\
+	__ret;								\
+})
+
+/**
+ * wait_event_interruptible_hrtimeout - sleep until a condition gets true or a timeout elapses
+ * @wq: the waitqueue to wait on
+ * @condition: a C expression for the event to wait for
+ * @timeout: timeout, as a ktime_t
+ *
+ * The process is put to sleep (TASK_INTERRUPTIBLE) until the
+ * @condition evaluates to true or a signal is received.
+ * The @condition is checked each time the waitqueue @wq is woken up.
+ *
+ * wake_up() has to be called after changing any variable that could
+ * change the result of the wait condition.
+ *
+ * The function returns 0 if @condition became true, -ERESTARTSYS if it was
+ * interrupted by a signal, or -ETIME if the timeout elapsed.
+ */
+#define wait_event_interruptible_hrtimeout(wq, condition, timeout)	\
+({									\
+	long __ret = 0;							\
+	if (!(condition))						\
+		__ret = __wait_event_hrtimeout(wq, condition, timeout,	\
+					       TASK_INTERRUPTIBLE);	\
+	__ret;								\
+})
+
 #define __wait_event_interruptible_exclusive(wq, condition, ret)	\
 do {									\
 	DEFINE_WAIT(__wait);						\
diff --git a/include/linux/writeback.h b/include/linux/writeback.h
index 9a9367c0c07..579a5007c69 100644
--- a/include/linux/writeback.h
+++ b/include/linux/writeback.h
@@ -5,6 +5,7 @@
 #define WRITEBACK_H
 
 #include <linux/sched.h>
+#include <linux/workqueue.h>
 #include <linux/fs.h>
 
 DECLARE_PER_CPU(int, dirty_throttle_leaks);
diff --git a/ipc/shm.c b/ipc/shm.c
index 8247c49ec07..34af1fe3470 100644
--- a/ipc/shm.c
+++ b/ipc/shm.c
@@ -491,10 +491,14 @@ static int newseg(struct ipc_namespace *ns, struct ipc_params *params)
 
 	sprintf (name, "SYSV%08x", key);
 	if (shmflg & SHM_HUGETLB) {
+		struct hstate *hs = hstate_sizelog((shmflg >> SHM_HUGE_SHIFT)
+						& SHM_HUGE_MASK);
+		size_t hugesize = ALIGN(size, huge_page_size(hs));
+
 		/* hugetlb_file_setup applies strict accounting */
 		if (shmflg & SHM_NORESERVE)
 			acctflag = VM_NORESERVE;
-		file = hugetlb_file_setup(name, 0, size, acctflag,
+		file = hugetlb_file_setup(name, hugesize, acctflag,
 				  &shp->mlock_user, HUGETLB_SHMFS_INODE,
 				(shmflg >> SHM_HUGE_SHIFT) & SHM_HUGE_MASK);
 	} else {
diff --git a/kernel/fork.c b/kernel/fork.c
index 7d40687b143..c509cc4a0d5 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -70,6 +70,7 @@
 #include <linux/khugepaged.h>
 #include <linux/signalfd.h>
 #include <linux/uprobes.h>
+#include <linux/aio.h>
 
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
diff --git a/kernel/printk.c b/kernel/printk.c
index 96dcfcd9a2d..fa36e149442 100644
--- a/kernel/printk.c
+++ b/kernel/printk.c
@@ -32,6 +32,7 @@
 #include <linux/security.h>
 #include <linux/bootmem.h>
 #include <linux/memblock.h>
+#include <linux/aio.h>
 #include <linux/syscalls.h>
 #include <linux/kexec.h>
 #include <linux/kdb.h>
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 17ae54da0ec..aed981a3f69 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -17,6 +17,7 @@
 #include <linux/ptrace.h>
 #include <linux/security.h>
 #include <linux/signal.h>
+#include <linux/uio.h>
 #include <linux/audit.h>
 #include <linux/pid_namespace.h>
 #include <linux/syscalls.h>
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 0f1d92163f3..cb1c9dedf9b 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 da3e9c04bf3..1ae21d645c6 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 3dcfaf4ed35..8a8cd0265e5 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 bb5d7527468..06a8842a6ec 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 39b2a0b86fe..5e6a8422658 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 acd40bfffa8..dfd7d71d684 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 b12fd861260..d365724feb0 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)
diff --git a/security/keys/internal.h b/security/keys/internal.h
index 8bbefc3b55d..d4f1468b9b5 100644
--- a/security/keys/internal.h
+++ b/security/keys/internal.h
@@ -16,6 +16,8 @@
 #include <linux/key-type.h>
 #include <linux/task_work.h>
 
+struct iovec;
+
 #ifdef __KDEBUG
 #define kenter(FMT, ...) \
 	printk(KERN_DEBUG "==> %s("FMT")\n", __func__, ##__VA_ARGS__)
diff --git a/security/keys/keyctl.c b/security/keys/keyctl.c
index 4b5c948eb41..33cfd27b4de 100644
--- a/security/keys/keyctl.c
+++ b/security/keys/keyctl.c
@@ -22,6 +22,7 @@
 #include <linux/err.h>
 #include <linux/vmalloc.h>
 #include <linux/security.h>
+#include <linux/uio.h>
 #include <asm/uaccess.h>
 #include "internal.h"
 
diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c
index 23e3c46cd0a..ccfa383f1fd 100644
--- a/sound/core/pcm_native.c
+++ b/sound/core/pcm_native.c
@@ -25,7 +25,7 @@
 #include <linux/slab.h>
 #include <linux/time.h>
 #include <linux/pm_qos.h>
-#include <linux/uio.h>
+#include <linux/aio.h>
 #include <linux/dma-mapping.h>
 #include <sound/core.h>
 #include <sound/control.h>