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
  ...

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

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"
 

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. */

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
 

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
 

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>

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,
 };
 

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,

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;

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>

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)

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>

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;

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;
 }

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;
 		}
 	}

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);
 }

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);

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)

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);
 

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;
 

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;

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>

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>

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);
 }
 

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>
 

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,

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>

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"
 

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>

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>

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"

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>

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

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"
 
 /**

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"

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"

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"

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 */

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"

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>

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>

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>

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>

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");

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;
 

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"

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"

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"

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"

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);

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"

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"

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>

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"

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,

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;
 	}

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);
 

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>

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;

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);

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>

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"

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>

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>

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)

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);

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

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 */

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;
 };

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>

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);
 

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

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);						\

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);

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 {

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>

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>

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>

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);
 

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);

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)
  */

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,

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;
 

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"
 

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)

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__)

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"
 

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>