Merge branch 'akpm' (incoming from Andrew)

Merge third batch of fixes from Andrew Morton:
 "Most of the rest.  I still have two large patchsets against AIO and
  IPC, but they're a bit stuck behind other trees and I'm about to
  vanish for six days.

   - random fixlets
   - inotify
   - more of the MM queue
   - show_stack() cleanups
   - DMI update
   - kthread/workqueue things
   - compat cleanups
   - epoll udpates
   - binfmt updates
   - nilfs2
   - hfs
   - hfsplus
   - ptrace
   - kmod
   - coredump
   - kexec
   - rbtree
   - pids
   - pidns
   - pps
   - semaphore tweaks
   - some w1 patches
   - relay updates
   - core Kconfig changes
   - sysrq tweaks"

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (109 commits)
  Documentation/sysrq: fix inconstistent help message of sysrq key
  ethernet/emac/sysrq: fix inconstistent help message of sysrq key
  sparc/sysrq: fix inconstistent help message of sysrq key
  powerpc/xmon/sysrq: fix inconstistent help message of sysrq key
  ARM/etm/sysrq: fix inconstistent help message of sysrq key
  power/sysrq: fix inconstistent help message of sysrq key
  kgdb/sysrq: fix inconstistent help message of sysrq key
  lib/decompress.c: fix initconst
  notifier-error-inject: fix module names in Kconfig
  kernel/sys.c: make prctl(PR_SET_MM) generally available
  UAPI: remove empty Kbuild files
  menuconfig: print more info for symbol without prompts
  init/Kconfig: re-order CONFIG_EXPERT options to fix menuconfig display
  kconfig menu: move Virtualization drivers near other virtualization options
  Kconfig: consolidate CONFIG_DEBUG_STRICT_USER_COPY_CHECKS
  relay: use macro PAGE_ALIGN instead of FIX_SIZE
  kernel/relay.c: move FIX_SIZE macro into relay.c
  kernel/relay.c: remove unused function argument actor
  drivers/w1/slaves/w1_ds2760.c: fix the error handling in w1_ds2760_add_slave()
  drivers/w1/slaves/w1_ds2781.c: fix the error handling in w1_ds2781_add_slave()
  ...

45 files changed, 652 insertions, 441 deletions

diff --git a/fs/Kconfig.binfmt b/fs/Kconfig.binfmt
index 0efd1524b97..370b24cee4d 100644
--- a/fs/Kconfig.binfmt
+++ b/fs/Kconfig.binfmt
@@ -65,6 +65,20 @@ config CORE_DUMP_DEFAULT_ELF_HEADERS
 	  This config option changes the default setting of coredump_filter
 	  seen at boot time.  If unsure, say Y.
 
+config BINFMT_SCRIPT
+	tristate "Kernel support for scripts starting with #!"
+	default y
+	help
+	  Say Y here if you want to execute interpreted scripts starting with
+	  #! followed by the path to an interpreter.
+
+	  You can build this support as a module; however, until that module
+	  gets loaded, you cannot run scripts.  Thus, if you want to load this
+	  module from an initramfs, the portion of the initramfs before loading
+	  this module must consist of compiled binaries only.
+
+	  Most systems will not boot if you say M or N here.  If unsure, say Y.
+
 config BINFMT_FLAT
 	bool "Kernel support for flat binaries"
 	depends on !MMU && (!FRV || BROKEN)
diff --git a/fs/Makefile b/fs/Makefile
index 3b2c76759ec..5e67e57b59d 100644
--- a/fs/Makefile
+++ b/fs/Makefile
@@ -34,10 +34,7 @@ obj-$(CONFIG_COMPAT)		+= compat.o compat_ioctl.o
 obj-$(CONFIG_BINFMT_AOUT)	+= binfmt_aout.o
 obj-$(CONFIG_BINFMT_EM86)	+= binfmt_em86.o
 obj-$(CONFIG_BINFMT_MISC)	+= binfmt_misc.o
-
-# binfmt_script is always there
-obj-y				+= binfmt_script.o
-
+obj-$(CONFIG_BINFMT_SCRIPT)	+= binfmt_script.o
 obj-$(CONFIG_BINFMT_ELF)	+= binfmt_elf.o
 obj-$(CONFIG_COMPAT_BINFMT_ELF)	+= compat_binfmt_elf.o
 obj-$(CONFIG_BINFMT_ELF_FDPIC)	+= binfmt_elf_fdpic.o
diff --git a/fs/binfmt_aout.c b/fs/binfmt_aout.c
index bbc8f8827ea..02fe378fc50 100644
--- a/fs/binfmt_aout.c
+++ b/fs/binfmt_aout.c
@@ -62,7 +62,6 @@ static int aout_core_dump(struct coredump_params *cprm)
 	fs = get_fs();
 	set_fs(KERNEL_DS);
 	has_dumped = 1;
-	current->flags |= PF_DUMPCORE;
        	strncpy(dump.u_comm, current->comm, sizeof(dump.u_comm));
 	dump.u_ar0 = offsetof(struct user, regs);
 	dump.signal = cprm->siginfo->si_signo;
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index 86af964c242..34a9771eaa6 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -803,7 +803,8 @@ static int load_elf_binary(struct linux_binprm *bprm)
 			 * follow the loader, and is not movable.  */
 #ifdef CONFIG_ARCH_BINFMT_ELF_RANDOMIZE_PIE
 			/* Memory randomization might have been switched off
-			 * in runtime via sysctl.
+			 * in runtime via sysctl or explicit setting of
+			 * personality flags.
 			 * If that is the case, retain the original non-zero
 			 * load_bias value in order to establish proper
 			 * non-randomized mappings.
@@ -2091,8 +2092,7 @@ static int elf_core_dump(struct coredump_params *cprm)
 		goto cleanup;
 
 	has_dumped = 1;
-	current->flags |= PF_DUMPCORE;
-  
+
 	fs = get_fs();
 	set_fs(KERNEL_DS);
 
diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c
index 9c13e023e2b..c1cc06aed60 100644
--- a/fs/binfmt_elf_fdpic.c
+++ b/fs/binfmt_elf_fdpic.c
@@ -1687,8 +1687,6 @@ static int elf_fdpic_core_dump(struct coredump_params *cprm)
 	fill_elf_fdpic_header(elf, e_phnum);
 
 	has_dumped = 1;
-	current->flags |= PF_DUMPCORE;
-
 	/*
 	 * Set up the notes in similar form to SVR4 core dumps made
 	 * with info from their /proc.
diff --git a/fs/binfmt_misc.c b/fs/binfmt_misc.c
index 751df5e4f61..1c740e152f3 100644
--- a/fs/binfmt_misc.c
+++ b/fs/binfmt_misc.c
@@ -23,6 +23,7 @@
 #include <linux/binfmts.h>
 #include <linux/slab.h>
 #include <linux/ctype.h>
+#include <linux/string_helpers.h>
 #include <linux/file.h>
 #include <linux/pagemap.h>
 #include <linux/namei.h>
@@ -234,24 +235,6 @@ static char *scanarg(char *s, char del)
 	return s;
 }
 
-static int unquote(char *from)
-{
-	char c = 0, *s = from, *p = from;
-
-	while ((c = *s++) != '\0') {
-		if (c == '\\' && *s == 'x') {
-			s++;
-			c = toupper(*s++);
-			*p = (c - (isdigit(c) ? '0' : 'A' - 10)) << 4;
-			c = toupper(*s++);
-			*p++ |= c - (isdigit(c) ? '0' : 'A' - 10);
-			continue;
-		}
-		*p++ = c;
-	}
-	return p - from;
-}
-
 static char * check_special_flags (char * sfs, Node * e)
 {
 	char * p = sfs;
@@ -354,8 +337,9 @@ static Node *create_entry(const char __user *buffer, size_t count)
 		p[-1] = '\0';
 		if (!e->mask[0])
 			e->mask = NULL;
-		e->size = unquote(e->magic);
-		if (e->mask && unquote(e->mask) != e->size)
+		e->size = string_unescape_inplace(e->magic, UNESCAPE_HEX);
+		if (e->mask &&
+		    string_unescape_inplace(e->mask, UNESCAPE_HEX) != e->size)
 			goto Einval;
 		if (e->size + e->offset > BINPRM_BUF_SIZE)
 			goto Einval;
diff --git a/fs/block_dev.c b/fs/block_dev.c
index aae187a7f94..ce08de7467a 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -617,11 +617,9 @@ void bd_forget(struct inode *inode)
 	struct block_device *bdev = NULL;
 
 	spin_lock(&bdev_lock);
-	if (inode->i_bdev) {
-		if (!sb_is_blkdev_sb(inode->i_sb))
-			bdev = inode->i_bdev;
-		__bd_forget(inode);
-	}
+	if (!sb_is_blkdev_sb(inode->i_sb))
+		bdev = inode->i_bdev;
+	__bd_forget(inode);
 	spin_unlock(&bdev_lock);
 
 	if (bdev)
diff --git a/fs/coredump.c b/fs/coredump.c
index c6479658d48..ec306cc9a28 100644
--- a/fs/coredump.c
+++ b/fs/coredump.c
@@ -263,7 +263,6 @@ static int zap_process(struct task_struct *start, int exit_code)
 	struct task_struct *t;
 	int nr = 0;
 
-	start->signal->flags = SIGNAL_GROUP_EXIT;
 	start->signal->group_exit_code = exit_code;
 	start->signal->group_stop_count = 0;
 
@@ -280,8 +279,8 @@ static int zap_process(struct task_struct *start, int exit_code)
 	return nr;
 }
 
-static inline int zap_threads(struct task_struct *tsk, struct mm_struct *mm,
-				struct core_state *core_state, int exit_code)
+static int zap_threads(struct task_struct *tsk, struct mm_struct *mm,
+			struct core_state *core_state, int exit_code)
 {
 	struct task_struct *g, *p;
 	unsigned long flags;
@@ -291,11 +290,16 @@ static inline int zap_threads(struct task_struct *tsk, struct mm_struct *mm,
 	if (!signal_group_exit(tsk->signal)) {
 		mm->core_state = core_state;
 		nr = zap_process(tsk, exit_code);
+		tsk->signal->group_exit_task = tsk;
+		/* ignore all signals except SIGKILL, see prepare_signal() */
+		tsk->signal->flags = SIGNAL_GROUP_COREDUMP;
+		clear_tsk_thread_flag(tsk, TIF_SIGPENDING);
 	}
 	spin_unlock_irq(&tsk->sighand->siglock);
 	if (unlikely(nr < 0))
 		return nr;
 
+	tsk->flags = PF_DUMPCORE;
 	if (atomic_read(&mm->mm_users) == nr + 1)
 		goto done;
 	/*
@@ -340,6 +344,7 @@ static inline int zap_threads(struct task_struct *tsk, struct mm_struct *mm,
 				if (unlikely(p->mm == mm)) {
 					lock_task_sighand(p, &flags);
 					nr += zap_process(p, exit_code);
+					p->signal->flags = SIGNAL_GROUP_EXIT;
 					unlock_task_sighand(p, &flags);
 				}
 				break;
@@ -386,11 +391,18 @@ static int coredump_wait(int exit_code, struct core_state *core_state)
 	return core_waiters;
 }
 
-static void coredump_finish(struct mm_struct *mm)
+static void coredump_finish(struct mm_struct *mm, bool core_dumped)
 {
 	struct core_thread *curr, *next;
 	struct task_struct *task;
 
+	spin_lock_irq(&current->sighand->siglock);
+	if (core_dumped && !__fatal_signal_pending(current))
+		current->signal->group_exit_code |= 0x80;
+	current->signal->group_exit_task = NULL;
+	current->signal->flags = SIGNAL_GROUP_EXIT;
+	spin_unlock_irq(&current->sighand->siglock);
+
 	next = mm->core_state->dumper.next;
 	while ((curr = next) != NULL) {
 		next = curr->next;
@@ -407,6 +419,17 @@ static void coredump_finish(struct mm_struct *mm)
 	mm->core_state = NULL;
 }
 
+static bool dump_interrupted(void)
+{
+	/*
+	 * SIGKILL or freezing() interrupt the coredumping. Perhaps we
+	 * can do try_to_freeze() and check __fatal_signal_pending(),
+	 * but then we need to teach dump_write() to restart and clear
+	 * TIF_SIGPENDING.
+	 */
+	return signal_pending(current);
+}
+
 static void wait_for_dump_helpers(struct file *file)
 {
 	struct pipe_inode_info *pipe;
@@ -416,17 +439,20 @@ static void wait_for_dump_helpers(struct file *file)
 	pipe_lock(pipe);
 	pipe->readers++;
 	pipe->writers--;
+	wake_up_interruptible_sync(&pipe->wait);
+	kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN);
+	pipe_unlock(pipe);
 
-	while ((pipe->readers > 1) && (!signal_pending(current))) {
-		wake_up_interruptible_sync(&pipe->wait);
-		kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN);
-		pipe_wait(pipe);
-	}
+	/*
+	 * We actually want wait_event_freezable() but then we need
+	 * to clear TIF_SIGPENDING and improve dump_interrupted().
+	 */
+	wait_event_interruptible(pipe->wait, pipe->readers == 1);
 
+	pipe_lock(pipe);
 	pipe->readers--;
 	pipe->writers++;
 	pipe_unlock(pipe);
-
 }
 
 /*
@@ -471,6 +497,7 @@ void do_coredump(siginfo_t *siginfo)
 	int ispipe;
 	struct files_struct *displaced;
 	bool need_nonrelative = false;
+	bool core_dumped = false;
 	static atomic_t core_dump_count = ATOMIC_INIT(0);
 	struct coredump_params cprm = {
 		.siginfo = siginfo,
@@ -514,17 +541,12 @@ void do_coredump(siginfo_t *siginfo)
 
 	old_cred = override_creds(cred);
 
-	/*
-	 * Clear any false indication of pending signals that might
-	 * be seen by the filesystem code called to write the core file.
-	 */
-	clear_thread_flag(TIF_SIGPENDING);
-
 	ispipe = format_corename(&cn, &cprm);
 
- 	if (ispipe) {
+	if (ispipe) {
 		int dump_count;
 		char **helper_argv;
+		struct subprocess_info *sub_info;
 
 		if (ispipe < 0) {
 			printk(KERN_WARNING "format_corename failed\n");
@@ -571,15 +593,20 @@ void do_coredump(siginfo_t *siginfo)
 			goto fail_dropcount;
 		}
 
-		retval = call_usermodehelper_fns(helper_argv[0], helper_argv,
-					NULL, UMH_WAIT_EXEC, umh_pipe_setup,
-					NULL, &cprm);
+		retval = -ENOMEM;
+		sub_info = call_usermodehelper_setup(helper_argv[0],
+						helper_argv, NULL, GFP_KERNEL,
+						umh_pipe_setup, NULL, &cprm);
+		if (sub_info)
+			retval = call_usermodehelper_exec(sub_info,
+							  UMH_WAIT_EXEC);
+
 		argv_free(helper_argv);
 		if (retval) {
- 			printk(KERN_INFO "Core dump to %s pipe failed\n",
+			printk(KERN_INFO "Core dump to %s pipe failed\n",
 			       cn.corename);
 			goto close_fail;
- 		}
+		}
 	} else {
 		struct inode *inode;
 
@@ -629,9 +656,7 @@ void do_coredump(siginfo_t *siginfo)
 		goto close_fail;
 	if (displaced)
 		put_files_struct(displaced);
-	retval = binfmt->core_dump(&cprm);
-	if (retval)
-		current->signal->group_exit_code |= 0x80;
+	core_dumped = !dump_interrupted() && binfmt->core_dump(&cprm);
 
 	if (ispipe && core_pipe_limit)
 		wait_for_dump_helpers(cprm.file);
@@ -644,7 +669,7 @@ fail_dropcount:
 fail_unlock:
 	kfree(cn.corename);
 fail_corename:
-	coredump_finish(mm);
+	coredump_finish(mm, core_dumped);
 	revert_creds(old_cred);
 fail_creds:
 	put_cred(cred);
@@ -659,7 +684,9 @@ fail:
  */
 int dump_write(struct file *file, const void *addr, int nr)
 {
-	return access_ok(VERIFY_READ, addr, nr) && file->f_op->write(file, addr, nr, &file->f_pos) == nr;
+	return !dump_interrupted() &&
+		access_ok(VERIFY_READ, addr, nr) &&
+		file->f_op->write(file, addr, nr, &file->f_pos) == nr;
 }
 EXPORT_SYMBOL(dump_write);
 
@@ -668,7 +695,8 @@ int dump_seek(struct file *file, loff_t off)
 	int ret = 1;
 
 	if (file->f_op->llseek && file->f_op->llseek != no_llseek) {
-		if (file->f_op->llseek(file, off, SEEK_CUR) < 0)
+		if (dump_interrupted() ||
+		    file->f_op->llseek(file, off, SEEK_CUR) < 0)
 			return 0;
 	} else {
 		char *buf = (char *)get_zeroed_page(GFP_KERNEL);
diff --git a/fs/dcache.c b/fs/dcache.c
index e8bc3420d63..e689268046c 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -1230,8 +1230,10 @@ void shrink_dcache_parent(struct dentry * parent)
 	LIST_HEAD(dispose);
 	int found;
 
-	while ((found = select_parent(parent, &dispose)) != 0)
+	while ((found = select_parent(parent, &dispose)) != 0) {
 		shrink_dentry_list(&dispose);
+		cond_resched();
+	}
 }
 EXPORT_SYMBOL(shrink_dcache_parent);
 
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 9fec1836057..277cc38aeda 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -104,7 +104,7 @@
 struct epoll_filefd {
 	struct file *file;
 	int fd;
-};
+} __packed;
 
 /*
  * Structure used to track possible nested calls, for too deep recursions
@@ -128,6 +128,8 @@ struct nested_calls {
 /*
  * Each file descriptor added to the eventpoll interface will
  * have an entry of this type linked to the "rbr" RB tree.
+ * Avoid increasing the size of this struct, there can be many thousands
+ * of these on a server and we do not want this to take another cache line.
  */
 struct epitem {
 	/* RB tree node used to link this structure to the eventpoll RB tree */
@@ -158,7 +160,7 @@ struct epitem {
 	struct list_head fllink;
 
 	/* wakeup_source used when EPOLLWAKEUP is set */
-	struct wakeup_source *ws;
+	struct wakeup_source __rcu *ws;
 
 	/* The structure that describe the interested events and the source fd */
 	struct epoll_event event;
@@ -536,6 +538,38 @@ static void ep_unregister_pollwait(struct eventpoll *ep, struct epitem *epi)
 	}
 }
 
+/* call only when ep->mtx is held */
+static inline struct wakeup_source *ep_wakeup_source(struct epitem *epi)
+{
+	return rcu_dereference_check(epi->ws, lockdep_is_held(&epi->ep->mtx));
+}
+
+/* call only when ep->mtx is held */
+static inline void ep_pm_stay_awake(struct epitem *epi)
+{
+	struct wakeup_source *ws = ep_wakeup_source(epi);
+
+	if (ws)
+		__pm_stay_awake(ws);
+}
+
+static inline bool ep_has_wakeup_source(struct epitem *epi)
+{
+	return rcu_access_pointer(epi->ws) ? true : false;
+}
+
+/* call when ep->mtx cannot be held (ep_poll_callback) */
+static inline void ep_pm_stay_awake_rcu(struct epitem *epi)
+{
+	struct wakeup_source *ws;
+
+	rcu_read_lock();
+	ws = rcu_dereference(epi->ws);
+	if (ws)
+		__pm_stay_awake(ws);
+	rcu_read_unlock();
+}
+
 /**
  * ep_scan_ready_list - Scans the ready list in a way that makes possible for
  *                      the scan code, to call f_op->poll(). Also allows for
@@ -599,7 +633,7 @@ static int ep_scan_ready_list(struct eventpoll *ep,
 		 */
 		if (!ep_is_linked(&epi->rdllink)) {
 			list_add_tail(&epi->rdllink, &ep->rdllist);
-			__pm_stay_awake(epi->ws);
+			ep_pm_stay_awake(epi);
 		}
 	}
 	/*
@@ -668,7 +702,7 @@ static int ep_remove(struct eventpoll *ep, struct epitem *epi)
 		list_del_init(&epi->rdllink);
 	spin_unlock_irqrestore(&ep->lock, flags);
 
-	wakeup_source_unregister(epi->ws);
+	wakeup_source_unregister(ep_wakeup_source(epi));
 
 	/* At this point it is safe to free the eventpoll item */
 	kmem_cache_free(epi_cache, epi);
@@ -711,11 +745,15 @@ static void ep_free(struct eventpoll *ep)
 	 * point we are sure no poll callbacks will be lingering around, and also by
 	 * holding "epmutex" we can be sure that no file cleanup code will hit
 	 * us during this operation. So we can avoid the lock on "ep->lock".
+	 * We do not need to lock ep->mtx, either, we only do it to prevent
+	 * a lockdep warning.
 	 */
+	mutex_lock(&ep->mtx);
 	while ((rbp = rb_first(&ep->rbr)) != NULL) {
 		epi = rb_entry(rbp, struct epitem, rbn);
 		ep_remove(ep, epi);
 	}
+	mutex_unlock(&ep->mtx);
 
 	mutex_unlock(&epmutex);
 	mutex_destroy(&ep->mtx);
@@ -734,6 +772,13 @@ static int ep_eventpoll_release(struct inode *inode, struct file *file)
 	return 0;
 }
 
+static inline unsigned int ep_item_poll(struct epitem *epi, poll_table *pt)
+{
+	pt->_key = epi->event.events;
+
+	return epi->ffd.file->f_op->poll(epi->ffd.file, pt) & epi->event.events;
+}
+
 static int ep_read_events_proc(struct eventpoll *ep, struct list_head *head,
 			       void *priv)
 {
@@ -741,10 +786,9 @@ static int ep_read_events_proc(struct eventpoll *ep, struct list_head *head,
 	poll_table pt;
 
 	init_poll_funcptr(&pt, NULL);
+
 	list_for_each_entry_safe(epi, tmp, head, rdllink) {
-		pt._key = epi->event.events;
-		if (epi->ffd.file->f_op->poll(epi->ffd.file, &pt) &
-		    epi->event.events)
+		if (ep_item_poll(epi, &pt))
 			return POLLIN | POLLRDNORM;
 		else {
 			/*
@@ -752,7 +796,7 @@ static int ep_read_events_proc(struct eventpoll *ep, struct list_head *head,
 			 * callback, but it's not actually ready, as far as
 			 * caller requested events goes. We can remove it here.
 			 */
-			__pm_relax(epi->ws);
+			__pm_relax(ep_wakeup_source(epi));
 			list_del_init(&epi->rdllink);
 		}
 	}
@@ -984,7 +1028,7 @@ static int ep_poll_callback(wait_queue_t *wait, unsigned mode, int sync, void *k
 	/* If this file is already in the ready list we exit soon */
 	if (!ep_is_linked(&epi->rdllink)) {
 		list_add_tail(&epi->rdllink, &ep->rdllist);
-		__pm_stay_awake(epi->ws);
+		ep_pm_stay_awake_rcu(epi);
 	}
 
 	/*
@@ -1146,6 +1190,7 @@ static int reverse_path_check(void)
 static int ep_create_wakeup_source(struct epitem *epi)
 {
 	const char *name;
+	struct wakeup_source *ws;
 
 	if (!epi->ep->ws) {
 		epi->ep->ws = wakeup_source_register("eventpoll");
@@ -1154,17 +1199,29 @@ static int ep_create_wakeup_source(struct epitem *epi)
 	}
 
 	name = epi->ffd.file->f_path.dentry->d_name.name;
-	epi->ws = wakeup_source_register(name);
-	if (!epi->ws)
+	ws = wakeup_source_register(name);
+
+	if (!ws)
 		return -ENOMEM;
+	rcu_assign_pointer(epi->ws, ws);
 
 	return 0;
 }
 
-static void ep_destroy_wakeup_source(struct epitem *epi)
+/* rare code path, only used when EPOLL_CTL_MOD removes a wakeup source */
+static noinline void ep_destroy_wakeup_source(struct epitem *epi)
 {
-	wakeup_source_unregister(epi->ws);
-	epi->ws = NULL;
+	struct wakeup_source *ws = ep_wakeup_source(epi);
+
+	RCU_INIT_POINTER(epi->ws, NULL);
+
+	/*
+	 * wait for ep_pm_stay_awake_rcu to finish, synchronize_rcu is
+	 * used internally by wakeup_source_remove, too (called by
+	 * wakeup_source_unregister), so we cannot use call_rcu
+	 */
+	synchronize_rcu();
+	wakeup_source_unregister(ws);
 }
 
 /*
@@ -1199,13 +1256,12 @@ static int ep_insert(struct eventpoll *ep, struct epoll_event *event,
 		if (error)
 			goto error_create_wakeup_source;
 	} else {
-		epi->ws = NULL;
+		RCU_INIT_POINTER(epi->ws, NULL);
 	}
 
 	/* Initialize the poll table using the queue callback */
 	epq.epi = epi;
 	init_poll_funcptr(&epq.pt, ep_ptable_queue_proc);
-	epq.pt._key = event->events;
 
 	/*
 	 * Attach the item to the poll hooks and get current event bits.
@@ -1214,7 +1270,7 @@ static int ep_insert(struct eventpoll *ep, struct epoll_event *event,
 	 * this operation completes, the poll callback can start hitting
 	 * the new item.
 	 */
-	revents = tfile->f_op->poll(tfile, &epq.pt);
+	revents = ep_item_poll(epi, &epq.pt);
 
 	/*
 	 * We have to check if something went wrong during the poll wait queue
@@ -1247,7 +1303,7 @@ static int ep_insert(struct eventpoll *ep, struct epoll_event *event,
 	/* If the file is already "ready" we drop it inside the ready list */
 	if ((revents & event->events) && !ep_is_linked(&epi->rdllink)) {
 		list_add_tail(&epi->rdllink, &ep->rdllist);
-		__pm_stay_awake(epi->ws);
+		ep_pm_stay_awake(epi);
 
 		/* Notify waiting tasks that events are available */
 		if (waitqueue_active(&ep->wq))
@@ -1288,7 +1344,7 @@ error_unregister:
 		list_del_init(&epi->rdllink);
 	spin_unlock_irqrestore(&ep->lock, flags);
 
-	wakeup_source_unregister(epi->ws);
+	wakeup_source_unregister(ep_wakeup_source(epi));
 
 error_create_wakeup_source:
 	kmem_cache_free(epi_cache, epi);
@@ -1314,12 +1370,11 @@ static int ep_modify(struct eventpoll *ep, struct epitem *epi, struct epoll_even
 	 * f_op->poll() call and the new event set registering.
 	 */
 	epi->event.events = event->events; /* need barrier below */
-	pt._key = event->events;
 	epi->event.data = event->data; /* protected by mtx */
 	if (epi->event.events & EPOLLWAKEUP) {
-		if (!epi->ws)
+		if (!ep_has_wakeup_source(epi))
 			ep_create_wakeup_source(epi);
-	} else if (epi->ws) {
+	} else if (ep_has_wakeup_source(epi)) {
 		ep_destroy_wakeup_source(epi);
 	}
 
@@ -1347,7 +1402,7 @@ static int ep_modify(struct eventpoll *ep, struct epitem *epi, struct epoll_even
 	 * Get current event bits. We can safely use the file* here because
 	 * its usage count has been increased by the caller of this function.
 	 */
-	revents = epi->ffd.file->f_op->poll(epi->ffd.file, &pt);
+	revents = ep_item_poll(epi, &pt);
 
 	/*
 	 * If the item is "hot" and it is not registered inside the ready
@@ -1357,7 +1412,7 @@ static int ep_modify(struct eventpoll *ep, struct epitem *epi, struct epoll_even
 		spin_lock_irq(&ep->lock);
 		if (!ep_is_linked(&epi->rdllink)) {
 			list_add_tail(&epi->rdllink, &ep->rdllist);
-			__pm_stay_awake(epi->ws);
+			ep_pm_stay_awake(epi);
 
 			/* Notify waiting tasks that events are available */
 			if (waitqueue_active(&ep->wq))
@@ -1383,6 +1438,7 @@ static int ep_send_events_proc(struct eventpoll *ep, struct list_head *head,
 	unsigned int revents;
 	struct epitem *epi;
 	struct epoll_event __user *uevent;
+	struct wakeup_source *ws;
 	poll_table pt;
 
 	init_poll_funcptr(&pt, NULL);
@@ -1405,14 +1461,16 @@ static int ep_send_events_proc(struct eventpoll *ep, struct list_head *head,
 		 * instead, but then epi->ws would temporarily be out of sync
 		 * with ep_is_linked().
 		 */
-		if (epi->ws && epi->ws->active)
-			__pm_stay_awake(ep->ws);
-		__pm_relax(epi->ws);
+		ws = ep_wakeup_source(epi);
+		if (ws) {
+			if (ws->active)
+				__pm_stay_awake(ep->ws);
+			__pm_relax(ws);
+		}
+
 		list_del_init(&epi->rdllink);
 
-		pt._key = epi->event.events;
-		revents = epi->ffd.file->f_op->poll(epi->ffd.file, &pt) &
-			epi->event.events;
+		revents = ep_item_poll(epi, &pt);
 
 		/*
 		 * If the event mask intersect the caller-requested one,
@@ -1424,7 +1482,7 @@ static int ep_send_events_proc(struct ev