Message-ID: <20130703181706.GB3049@kroah.com>
Date:	Wed, 3 Jul 2013 11:17:06 -0700
From:	Greg KH <gregkh@...uxfoundation.org>
To:	linux-kernel@...r.kernel.org,
	Andrew Morton <akpm@...ux-foundation.org>,
	torvalds@...ux-foundation.org, stable@...r.kernel.org
Cc:	lwn@....net, Jiri Slaby <jslaby@...e.cz>
Subject: Re: Linux 3.4.52

diff --git a/Makefile b/Makefile
index 5adfadf..810572b 100644
--- a/Makefile
+++ b/Makefile
@@ -1,6 +1,6 @@
 VERSION = 3
 PATCHLEVEL = 4
-SUBLEVEL = 51
+SUBLEVEL = 52
 EXTRAVERSION =
 NAME = Saber-toothed Squirrel
 
diff --git a/arch/arm/include/asm/cacheflush.h b/arch/arm/include/asm/cacheflush.h
index 42dec04..0a5e8a5 100644
--- a/arch/arm/include/asm/cacheflush.h
+++ b/arch/arm/include/asm/cacheflush.h
@@ -305,9 +305,7 @@ static inline void flush_anon_page(struct vm_area_struct *vma,
 }
 
 #define ARCH_HAS_FLUSH_KERNEL_DCACHE_PAGE
-static inline void flush_kernel_dcache_page(struct page *page)
-{
-}
+extern void flush_kernel_dcache_page(struct page *);
 
 #define flush_dcache_mmap_lock(mapping) \
 	spin_lock_irq(&(mapping)->tree_lock)
diff --git a/arch/arm/mm/flush.c b/arch/arm/mm/flush.c
index 40ca11e..8f0d285 100644
--- a/arch/arm/mm/flush.c
+++ b/arch/arm/mm/flush.c
@@ -299,6 +299,39 @@ void flush_dcache_page(struct page *page)
 EXPORT_SYMBOL(flush_dcache_page);
 
 /*
+ * Ensure cache coherency for the kernel mapping of this page. We can
+ * assume that the page is pinned via kmap.
+ *
+ * If the page only exists in the page cache and there are no user
+ * space mappings, this is a no-op since the page was already marked
+ * dirty at creation.  Otherwise, we need to flush the dirty kernel
+ * cache lines directly.
+ */
+void flush_kernel_dcache_page(struct page *page)
+{
+	if (cache_is_vivt() || cache_is_vipt_aliasing()) {
+		struct address_space *mapping;
+
+		mapping = page_mapping(page);
+
+		if (!mapping || mapping_mapped(mapping)) {
+			void *addr;
+
+			addr = page_address(page);
+			/*
+			 * kmap_atomic() doesn't set the page virtual
+			 * address for highmem pages, and
+			 * kunmap_atomic() takes care of cache
+			 * flushing already.
+			 */
+			if (!IS_ENABLED(CONFIG_HIGHMEM) || addr)
+				__cpuc_flush_dcache_area(addr, PAGE_SIZE);
+		}
+	}
+}
+EXPORT_SYMBOL(flush_kernel_dcache_page);
+
+/*
  * Flush an anonymous page so that users of get_user_pages()
  * can safely access the data.  The expected sequence is:
  *
diff --git a/arch/arm/mm/nommu.c b/arch/arm/mm/nommu.c
index d51225f..eb5293a 100644
--- a/arch/arm/mm/nommu.c
+++ b/arch/arm/mm/nommu.c
@@ -57,6 +57,12 @@ void flush_dcache_page(struct page *page)
 }
 EXPORT_SYMBOL(flush_dcache_page);
 
+void flush_kernel_dcache_page(struct page *page)
+{
+	__cpuc_flush_dcache_area(page_address(page), PAGE_SIZE);
+}
+EXPORT_SYMBOL(flush_kernel_dcache_page);
+
 void copy_to_user_page(struct vm_area_struct *vma, struct page *page,
 		       unsigned long uaddr, void *dst, const void *src,
 		       unsigned long len)
diff --git a/drivers/net/wan/dlci.c b/drivers/net/wan/dlci.c
index 147614e..6a8a382 100644
--- a/drivers/net/wan/dlci.c
+++ b/drivers/net/wan/dlci.c
@@ -384,21 +384,37 @@ static int dlci_del(struct dlci_add *dlci)
 	struct frad_local	*flp;
 	struct net_device	*master, *slave;
 	int			err;
+	bool			found = false;
+
+	rtnl_lock();
 
 	/* validate slave device */
 	master = __dev_get_by_name(&init_net, dlci->devname);
-	if (!master)
-		return -ENODEV;
+	if (!master) {
+		err = -ENODEV;
+		goto out;
+	}
+
+	list_for_each_entry(dlp, &dlci_devs, list) {
+		if (dlp->master == master) {
+			found = true;
+			break;
+		}
+	}
+	if (!found) {
+		err = -ENODEV;
+		goto out;
+	}
 
 	if (netif_running(master)) {
-		return -EBUSY;
+		err = -EBUSY;
+		goto out;
 	}
 
 	dlp = netdev_priv(master);
 	slave = dlp->slave;
 	flp = netdev_priv(slave);
 
-	rtnl_lock();
 	err = (*flp->deassoc)(slave, master);
 	if (!err) {
 		list_del(&dlp->list);
@@ -407,8 +423,8 @@ static int dlci_del(struct dlci_add *dlci)
 
 		dev_put(slave);
 	}
+out:
 	rtnl_unlock();
-
 	return err;
 }
 
diff --git a/drivers/tty/serial/pch_uart.c b/drivers/tty/serial/pch_uart.c
index 7d47514..2e99f79 100644
--- a/drivers/tty/serial/pch_uart.c
+++ b/drivers/tty/serial/pch_uart.c
@@ -1034,22 +1034,37 @@ static unsigned int dma_handle_tx(struct eg20t_port *priv)
 static void pch_uart_err_ir(struct eg20t_port *priv, unsigned int lsr)
 {
 	u8 fcr = ioread8(priv->membase + UART_FCR);
+	struct uart_port *port = &priv->port;
+	struct tty_struct *tty = tty_port_tty_get(&port->state->port);
+	char   *error_msg[5] = {};
+	int    i = 0;
 
 	/* Reset FIFO */
 	fcr |= UART_FCR_CLEAR_RCVR;
 	iowrite8(fcr, priv->membase + UART_FCR);
 
 	if (lsr & PCH_UART_LSR_ERR)
-		dev_err(&priv->pdev->dev, "Error data in FIFO\n");
+		error_msg[i++] = "Error data in FIFO\n";
 
-	if (lsr & UART_LSR_FE)
-		dev_err(&priv->pdev->dev, "Framing Error\n");
+	if (lsr & UART_LSR_FE) {
+		port->icount.frame++;
+		error_msg[i++] = "  Framing Error\n";
+	}
 
-	if (lsr & UART_LSR_PE)
-		dev_err(&priv->pdev->dev, "Parity Error\n");
+	if (lsr & UART_LSR_PE) {
+		port->icount.parity++;
+		error_msg[i++] = "  Parity Error\n";
+	}
 
-	if (lsr & UART_LSR_OE)
-		dev_err(&priv->pdev->dev, "Overrun Error\n");
+	if (lsr & UART_LSR_OE) {
+		port->icount.overrun++;
+		error_msg[i++] = "  Overrun Error\n";
+	}
+
+	if (tty == NULL) {
+		for (i = 0; error_msg[i] != NULL; i++)
+			dev_err(&priv->pdev->dev, error_msg[i]);
+	}
 }
 
 static irqreturn_t pch_uart_interrupt(int irq, void *dev_id)
diff --git a/fs/exec.c b/fs/exec.c
index 2b7f5ff..0ea0b4c 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -1163,13 +1163,6 @@ void setup_new_exec(struct linux_binprm * bprm)
 			set_dumpable(current->mm, suid_dumpable);
 	}
 
-	/*
-	 * Flush performance counters when crossing a
-	 * security domain:
-	 */
-	if (!get_dumpable(current->mm))
-		perf_event_exit_task(current);
-
 	/* An exec changes our domain. We are no longer part of the thread
 	   group */
 
@@ -1233,6 +1226,15 @@ void install_exec_creds(struct linux_binprm *bprm)
 
 	commit_creds(bprm->cred);
 	bprm->cred = NULL;
+
+	/*
+	 * Disable monitoring for regular users
+	 * when executing setuid binaries. Must
+	 * wait until new credentials are committed
+	 * by commit_creds() above
+	 */
+	if (get_dumpable(current->mm) != SUID_DUMP_USER)
+		perf_event_exit_task(current);
 	/*
 	 * cred_guard_mutex must be held at least to this point to prevent
 	 * ptrace_attach() from altering our determination of the task's
diff --git a/fs/ubifs/dir.c b/fs/ubifs/dir.c
index 8640a12..25c472b 100644
--- a/fs/ubifs/dir.c
+++ b/fs/ubifs/dir.c
@@ -357,31 +357,50 @@ static unsigned int vfs_dent_type(uint8_t type)
 static int ubifs_readdir(struct file *file, void *dirent, filldir_t filldir)
 {
 	int err, over = 0;
+	loff_t pos = file->f_pos;
 	struct qstr nm;
 	union ubifs_key key;
 	struct ubifs_dent_node *dent;
 	struct inode *dir = file->f_path.dentry->d_inode;
 	struct ubifs_info *c = dir->i_sb->s_fs_info;
 
-	dbg_gen("dir ino %lu, f_pos %#llx", dir->i_ino, file->f_pos);
+	dbg_gen("dir ino %lu, f_pos %#llx", dir->i_ino, pos);
 
-	if (file->f_pos > UBIFS_S_KEY_HASH_MASK || file->f_pos == 2)
+	if (pos > UBIFS_S_KEY_HASH_MASK || pos == 2)
 		/*
 		 * The directory was seek'ed to a senseless position or there
 		 * are no more entries.
 		 */
 		return 0;
 
+	if (file->f_version == 0) {
+		/*
+		 * The file was seek'ed, which means that @file->private_data
+		 * is now invalid. This may also be just the first
+		 * 'ubifs_readdir()' invocation, in which case
+		 * @file->private_data is NULL, and the below code is
+		 * basically a no-op.
+		 */
+		kfree(file->private_data);
+		file->private_data = NULL;
+	}
+
+	/*
+	 * 'generic_file_llseek()' unconditionally sets @file->f_version to
+	 * zero, and we use this for detecting whether the file was seek'ed.
+	 */
+	file->f_version = 1;
+
 	/* File positions 0 and 1 correspond to "." and ".." */
-	if (file->f_pos == 0) {
+	if (pos == 0) {
 		ubifs_assert(!file->private_data);
 		over = filldir(dirent, ".", 1, 0, dir->i_ino, DT_DIR);
 		if (over)
 			return 0;
-		file->f_pos = 1;
+		file->f_pos = pos = 1;
 	}
 
-	if (file->f_pos == 1) {
+	if (pos == 1) {
 		ubifs_assert(!file->private_data);
 		over = filldir(dirent, "..", 2, 1,
 			       parent_ino(file->f_path.dentry), DT_DIR);
@@ -397,7 +416,7 @@ static int ubifs_readdir(struct file *file, void *dirent, filldir_t filldir)
 			goto out;
 		}
 
-		file->f_pos = key_hash_flash(c, &dent->key);
+		file->f_pos = pos = key_hash_flash(c, &dent->key);
 		file->private_data = dent;
 	}
 
@@ -405,17 +424,16 @@ static int ubifs_readdir(struct file *file, void *dirent, filldir_t filldir)
 	if (!dent) {
 		/*
 		 * The directory was seek'ed to and is now readdir'ed.
-		 * Find the entry corresponding to @file->f_pos or the
-		 * closest one.
+		 * Find the entry corresponding to @pos or the closest one.
 		 */
-		dent_key_init_hash(c, &key, dir->i_ino, file->f_pos);
+		dent_key_init_hash(c, &key, dir->i_ino, pos);
 		nm.name = NULL;
 		dent = ubifs_tnc_next_ent(c, &key, &nm);
 		if (IS_ERR(dent)) {
 			err = PTR_ERR(dent);
 			goto out;
 		}
-		file->f_pos = key_hash_flash(c, &dent->key);
+		file->f_pos = pos = key_hash_flash(c, &dent->key);
 		file->private_data = dent;
 	}
 
@@ -427,7 +445,7 @@ static int ubifs_readdir(struct file *file, void *dirent, filldir_t filldir)
 			     ubifs_inode(dir)->creat_sqnum);
 
 		nm.len = le16_to_cpu(dent->nlen);
-		over = filldir(dirent, dent->name, nm.len, file->f_pos,
+		over = filldir(dirent, dent->name, nm.len, pos,
 			       le64_to_cpu(dent->inum),
 			       vfs_dent_type(dent->type));
 		if (over)
@@ -443,9 +461,17 @@ static int ubifs_readdir(struct file *file, void *dirent, filldir_t filldir)
 		}
 
 		kfree(file->private_data);
-		file->f_pos = key_hash_flash(c, &dent->key);
+		file->f_pos = pos = key_hash_flash(c, &dent->key);
 		file->private_data = dent;
 		cond_resched();
+
+		if (file->f_version == 0)
+			/*
+			 * The file was seek'ed meanwhile, lets return and start
+			 * reading direntries from the new position on the next
+			 * invocation.
+			 */
+			return 0;
 	}
 
 out:
@@ -456,15 +482,13 @@ out:
 
 	kfree(file->private_data);
 	file->private_data = NULL;
+	/* 2 is a special value indicating that there are no more direntries */
 	file->f_pos = 2;
 	return 0;
 }
 
-/* If a directory is seeked, we have to free saved readdir() state */
 static loff_t ubifs_dir_llseek(struct file *file, loff_t offset, int origin)
 {
-	kfree(file->private_data);
-	file->private_data = NULL;
 	return generic_file_llseek(file, offset, origin);
 }
 
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 8e9a069..89fb74e 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -950,8 +950,7 @@ struct perf_event {
 	/* mmap bits */
 	struct mutex			mmap_mutex;
 	atomic_t			mmap_count;
-	int				mmap_locked;
-	struct user_struct		*mmap_user;
+
 	struct ring_buffer		*rb;
 	struct list_head		rb_entry;
 
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 839a24f..7ceb270 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -193,9 +193,6 @@ static void cpu_ctx_sched_in(struct perf_cpu_context *cpuctx,
 static void update_context_time(struct perf_event_context *ctx);
 static u64 perf_event_time(struct perf_event *event);
 
-static void ring_buffer_attach(struct perf_event *event,
-			       struct ring_buffer *rb);
-
 void __weak perf_event_print_debug(void)	{ }
 
 extern __weak const char *perf_pmu_name(void)
@@ -2849,6 +2846,7 @@ static void free_event_rcu(struct rcu_head *head)
 }
 
 static void ring_buffer_put(struct ring_buffer *rb);
+static void ring_buffer_detach(struct perf_event *event, struct ring_buffer *rb);
 
 static void free_event(struct perf_event *event)
 {
@@ -2873,15 +2871,30 @@ static void free_event(struct perf_event *event)
 		if (has_branch_stack(event)) {
 			static_key_slow_dec_deferred(&perf_sched_events);
 			/* is system-wide event */
-			if (!(event->attach_state & PERF_ATTACH_TASK))
+			if (!(event->attach_state & PERF_ATTACH_TASK)) {
 				atomic_dec(&per_cpu(perf_branch_stack_events,
 						    event->cpu));
+			}
 		}
 	}
 
 	if (event->rb) {
-		ring_buffer_put(event->rb);
-		event->rb = NULL;
+		struct ring_buffer *rb;
+
+		/*
+		 * Can happen when we close an event with re-directed output.
+		 *
+		 * Since we have a 0 refcount, perf_mmap_close() will skip
+		 * over us; possibly making our ring_buffer_put() the last.
+		 */
+		mutex_lock(&event->mmap_mutex);
+		rb = event->rb;
+		if (rb) {
+			rcu_assign_pointer(event->rb, NULL);
+			ring_buffer_detach(event, rb);
+			ring_buffer_put(rb); /* could be last */
+		}
+		mutex_unlock(&event->mmap_mutex);
 	}
 
 	if (is_cgroup_event(event))
@@ -3119,30 +3132,13 @@ static unsigned int perf_poll(struct file *file, poll_table *wait)
 	unsigned int events = POLL_HUP;
 
 	/*
-	 * Race between perf_event_set_output() and perf_poll(): perf_poll()
-	 * grabs the rb reference but perf_event_set_output() overrides it.
-	 * Here is the timeline for two threads T1, T2:
-	 * t0: T1, rb = rcu_dereference(event->rb)
-	 * t1: T2, old_rb = event->rb
-	 * t2: T2, event->rb = new rb
-	 * t3: T2, ring_buffer_detach(old_rb)
-	 * t4: T1, ring_buffer_attach(rb1)
-	 * t5: T1, poll_wait(event->waitq)
-	 *
-	 * To avoid this problem, we grab mmap_mutex in perf_poll()
-	 * thereby ensuring that the assignment of the new ring buffer
-	 * and the detachment of the old buffer appear atomic to perf_poll()
+	 * Pin the event->rb by taking event->mmap_mutex; otherwise
+	 * perf_event_set_output() can swizzle our rb and make us miss wakeups.
 	 */
 	mutex_lock(&event->mmap_mutex);
-
-	rcu_read_lock();
-	rb = rcu_dereference(event->rb);
-	if (rb) {
-		ring_buffer_attach(event, rb);
+	rb = event->rb;
+	if (rb)
 		events = atomic_xchg(&rb->poll, 0);
-	}
-	rcu_read_unlock();
-
 	mutex_unlock(&event->mmap_mutex);
 
 	poll_wait(file, &event->waitq, wait);
@@ -3459,16 +3455,12 @@ static void ring_buffer_attach(struct perf_event *event,
 		return;
 
 	spin_lock_irqsave(&rb->event_lock, flags);
-	if (!list_empty(&event->rb_entry))
-		goto unlock;
-
-	list_add(&event->rb_entry, &rb->event_list);
-unlock:
+	if (list_empty(&event->rb_entry))
+		list_add(&event->rb_entry, &rb->event_list);
 	spin_unlock_irqrestore(&rb->event_lock, flags);
 }
 
-static void ring_buffer_detach(struct perf_event *event,
-			       struct ring_buffer *rb)
+static void ring_buffer_detach(struct perf_event *event, struct ring_buffer *rb)
 {
 	unsigned long flags;
 
@@ -3487,13 +3479,10 @@ static void ring_buffer_wakeup(struct perf_event *event)
 
 	rcu_read_lock();
 	rb = rcu_dereference(event->rb);
-	if (!rb)
-		goto unlock;
-
-	list_for_each_entry_rcu(event, &rb->event_list, rb_entry)
-		wake_up_all(&event->waitq);
-
-unlock:
+	if (rb) {
+		list_for_each_entry_rcu(event, &rb->event_list, rb_entry)
+			wake_up_all(&event->waitq);
+	}
 	rcu_read_unlock();
 }
 
@@ -3522,18 +3511,10 @@ static struct ring_buffer *ring_buffer_get(struct perf_event *event)
 
 static void ring_buffer_put(struct ring_buffer *rb)
 {
-	struct perf_event *event, *n;
-	unsigned long flags;
-
 	if (!atomic_dec_and_test(&rb->refcount))
 		return;
 
-	spin_lock_irqsave(&rb->event_lock, flags);
-	list_for_each_entry_safe(event, n, &rb->event_list, rb_entry) {
-		list_del_init(&event->rb_entry);
-		wake_up_all(&event->waitq);
-	}
-	spin_unlock_irqrestore(&rb->event_lock, flags);
+	WARN_ON_ONCE(!list_empty(&rb->event_list));
 
 	call_rcu(&rb->rcu_head, rb_free_rcu);
 }
@@ -3543,26 +3524,100 @@ static void perf_mmap_open(struct vm_area_struct *vma)
 	struct perf_event *event = vma->vm_file->private_data;
 
 	atomic_inc(&event->mmap_count);
+	atomic_inc(&event->rb->mmap_count);
 }
 
+/*
+ * A buffer can be mmap()ed multiple times; either directly through the same
+ * event, or through other events by use of perf_event_set_output().
+ *
+ * In order to undo the VM accounting done by perf_mmap() we need to destroy
+ * the buffer here, where we still have a VM context. This means we need
+ * to detach all events redirecting to us.
+ */
 static void perf_mmap_close(struct vm_area_struct *vma)
 {
 	struct perf_event *event = vma->vm_file->private_data;
 
-	if (atomic_dec_and_mutex_lock(&event->mmap_count, &event->mmap_mutex)) {
-		unsigned long size = perf_data_size(event->rb);
-		struct user_struct *user = event->mmap_user;
-		struct ring_buffer *rb = event->rb;
+	struct ring_buffer *rb = event->rb;
+	struct user_struct *mmap_user = rb->mmap_user;
+	int mmap_locked = rb->mmap_locked;
+	unsigned long size = perf_data_size(rb);
+
+	atomic_dec(&rb->mmap_count);
+
+	if (!atomic_dec_and_mutex_lock(&event->mmap_count, &event->mmap_mutex))
+		return;
+
+	/* Detach current event from the buffer. */
+	rcu_assign_pointer(event->rb, NULL);
+	ring_buffer_detach(event, rb);
+	mutex_unlock(&event->mmap_mutex);
+
+	/* If there's still other mmap()s of this buffer, we're done. */
+	if (atomic_read(&rb->mmap_count)) {
+		ring_buffer_put(rb); /* can't be last */
+		return;
+	}
+
+	/*
+	 * No other mmap()s, detach from all other events that might redirect
+	 * into the now unreachable buffer. Somewhat complicated by the
+	 * fact that rb::event_lock otherwise nests inside mmap_mutex.
+	 */
+again:
+	rcu_read_lock();
+	list_for_each_entry_rcu(event, &rb->event_list, rb_entry) {
+		if (!atomic_long_inc_not_zero(&event->refcount)) {
+			/*
+			 * This event is en-route to free_event() which will
+			 * detach it and remove it from the list.
+			 */
+			continue;
+		}
+		rcu_read_unlock();
 
-		atomic_long_sub((size >> PAGE_SHIFT) + 1, &user->locked_vm);
-		vma->vm_mm->pinned_vm -= event->mmap_locked;
-		rcu_assign_pointer(event->rb, NULL);
-		ring_buffer_detach(event, rb);
+		mutex_lock(&event->mmap_mutex);
+		/*
+		 * Check we didn't race with perf_event_set_output() which can
+		 * swizzle the rb from under us while we were waiting to
+		 * acquire mmap_mutex.
+		 *
+		 * If we find a different rb; ignore this event, a next
+		 * iteration will no longer find it on the list. We have to
+		 * still restart the iteration to make sure we're not now
+		 * iterating the wrong list.
+		 */
+		if (event->rb == rb) {
+			rcu_assign_pointer(event->rb, NULL);
+			ring_buffer_detach(event, rb);
+			ring_buffer_put(rb); /* can't be last, we still have one */
+		}
 		mutex_unlock(&event->mmap_mutex);
+		put_event(event);
 
-		ring_buffer_put(rb);
-		free_uid(user);
+		/*
+		 * Restart the iteration; either we're on the wrong list or
+		 * destroyed its integrity by doing a deletion.
+		 */
+		goto again;
 	}
+	rcu_read_unlock();
+
+	/*
+	 * It could be there's still a few 0-ref events on the list; they'll
+	 * get cleaned up by free_event() -- they'll also still have their
+	 * ref on the rb and will free it whenever they are done with it.
+	 *
+	 * Aside from that, this buffer is 'fully' detached and unmapped,
+	 * undo the VM accounting.
+	 */
+
+	atomic_long_sub((size >> PAGE_SHIFT) + 1, &mmap_user->locked_vm);
+	vma->vm_mm->pinned_vm -= mmap_locked;
+	free_uid(mmap_user);
+
+	ring_buffer_put(rb); /* could be last */
 }
 
 static const struct vm_operations_struct perf_mmap_vmops = {
@@ -3612,12 +3667,24 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma)
 		return -EINVAL;
 
 	WARN_ON_ONCE(event->ctx->parent_ctx);
+again:
 	mutex_lock(&event->mmap_mutex);
 	if (event->rb) {
-		if (event->rb->nr_pages == nr_pages)
-			atomic_inc(&event->rb->refcount);
-		else
+		if (event->rb->nr_pages != nr_pages) {
 			ret = -EINVAL;
+			goto unlock;
+		}
+
+		if (!atomic_inc_not_zero(&event->rb->mmap_count)) {
+			/*
+			 * Raced against perf_mmap_close() through
+			 * perf_event_set_output(). Try again, hope for better
+			 * luck.
+			 */
+			mutex_unlock(&event->mmap_mutex);
+			goto again;
+		}
+
 		goto unlock;
 	}
 
@@ -3658,12 +3725,16 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma)
 		ret = -ENOMEM;
 		goto unlock;
 	}
-	rcu_assign_pointer(event->rb, rb);
+
+	atomic_set(&rb->mmap_count, 1);
+	rb->mmap_locked = extra;
+	rb->mmap_user = get_current_user();
 
 	atomic_long_add(user_extra, &user->locked_vm);
-	event->mmap_locked = extra;
-	event->mmap_user = get_current_user();
-	vma->vm_mm->pinned_vm += event->mmap_locked;
+	vma->vm_mm->pinned_vm += extra;
+
+	ring_buffer_attach(event, rb);
+	rcu_assign_pointer(event->rb, rb);
 
 	perf_event_update_userpage(event);
 
@@ -3672,7 +3743,11 @@ unlock:
 		atomic_inc(&event->mmap_count);
 	mutex_unlock(&event->mmap_mutex);
 
-	vma->vm_flags |= VM_RESERVED;
+	/*
+	 * Since pinned accounting is per vm we cannot allow fork() to copy our
+	 * vma.
+	 */
+	vma->vm_flags |= VM_DONTCOPY | VM_RESERVED;
 	vma->vm_ops = &perf_mmap_vmops;
 
 	return ret;
@@ -6161,6 +6236,8 @@ set:
 	if (atomic_read(&event->mmap_count))
 		goto unlock;
 
+	old_rb = event->rb;
+
 	if (output_event) {
 		/* get the rb we want to redirect to */
 		rb = ring_buffer_get(output_event);
@@ -6168,16 +6245,28 @@ set:
 			goto unlock;
 	}
 
-	old_rb = event->rb;
-	rcu_assign_pointer(event->rb, rb);
 	if (old_rb)
 		ring_buffer_detach(event, old_rb);
+
+	if (rb)
+		ring_buffer_attach(event, rb);
+
+	rcu_assign_pointer(event->rb, rb);
+
+	if (old_rb) {
+		ring_buffer_put(old_rb);
+		/*
+		 * Since we detached before setting the new rb, so that we
+		 * could attach the new rb, we could have missed a wakeup.
+		 * Provide it now.
+		 */
+		wake_up_all(&event->waitq);
+	}
+
 	ret = 0;
 unlock:
 	mutex_unlock(&event->mmap_mutex);
 
-	if (old_rb)
-		ring_buffer_put(old_rb);
 out:
 	return ret;
 }
diff --git a/kernel/events/hw_breakpoint.c b/kernel/events/hw_breakpoint.c
index bb38c4d..fc8bfcf 100644
--- a/kernel/events/hw_breakpoint.c
+++ b/kernel/events/hw_breakpoint.c
@@ -147,7 +147,7 @@ fetch_bp_busy_slots(struct bp_busy_slots *slots, struct perf_event *bp,
 		return;
 	}
 
-	for_each_online_cpu(cpu) {
+	for_each_possible_cpu(cpu) {
 		unsigned int nr;
 
 		nr = per_cpu(nr_cpu_bp_pinned[type], cpu);
@@ -233,7 +233,7 @@ toggle_bp_slot(struct perf_event *bp, bool enable, enum bp_type_idx type,
 	if (cpu >= 0) {
 		toggle_bp_task_slot(bp, cpu, enable, type, weight);
 	} else {
-		for_each_online_cpu(cpu)
+		for_each_possible_cpu(cpu)
 			toggle_bp_task_slot(bp, cpu, enable, type, weight);
 	}
 
diff --git a/kernel/events/internal.h b/kernel/events/internal.h
index b0b107f..b400e64 100644
--- a/kernel/events/internal.h
+++ b/kernel/events/internal.h
@@ -30,6 +30,10 @@ struct ring_buffer {
 	spinlock_t			event_lock;
 	struct list_head		event_list;
 
+	atomic_t			mmap_count;
+	unsigned long			mmap_locked;
+	struct user_struct		*mmap_user;
+
 	struct perf_event_mmap_page	*user_page;
 	void				*data_pages[0];
 };
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index fa07aed..932420d 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -1880,6 +1880,9 @@ static struct sk_buff *l2cap_build_cmd(struct l2cap_conn *conn,
 	BT_DBG("conn %p, code 0x%2.2x, ident 0x%2.2x, len %d",
 			conn, code, ident, dlen);
 
+	if (conn->mtu < L2CAP_HDR_SIZE + L2CAP_CMD_HDR_SIZE)
+		return NULL;
+
 	len = L2CAP_HDR_SIZE + L2CAP_CMD_HDR_SIZE + dlen;
 	count = min_t(unsigned int, conn->mtu, len);
 
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

Powered by blists - more mailing lists