[14/19] futex: Fix regression with read only mappings

[Greg KH <gregkh@suse.de>]

2.6.32-longterm review patch.  If anyone has any objections, please let us know.

------------------

From: Shawn Bohrer <sbohrer@rgmadvisors.com>

commit 9ea71503a8ed9184d2d0b8ccc4d269d05f7940ae upstream.

commit 7485d0d3758e8e6491a5c9468114e74dc050785d (futexes: Remove rw
parameter from get_futex_key()) in 2.6.33 fixed two problems:  First, It
prevented a loop when encountering a ZERO_PAGE. Second, it fixed RW
MAP_PRIVATE futex operations by forcing the COW to occur by
unconditionally performing a write access get_user_pages_fast() to get
the page.  The commit also introduced a user-mode regression in that it
broke futex operations on read-only memory maps.  For example, this
breaks workloads that have one or more reader processes doing a
FUTEX_WAIT on a futex within a read only shared file mapping, and a
writer processes that has a writable mapping issuing the FUTEX_WAKE.

This fixes the regression for valid futex operations on RO mappings by
trying a RO get_user_pages_fast() when the RW get_user_pages_fast()
fails. This change makes it necessary to also check for invalid use
cases, such as anonymous RO mappings (which can never change) and the
ZERO_PAGE which the commit referenced above was written to address.

This patch does restore the original behavior with RO MAP_PRIVATE
mappings, which have inherent user-mode usage problems and don't really
make sense.  With this patch performing a FUTEX_WAIT within a RO
MAP_PRIVATE mapping will be successfully woken provided another process
updates the region of the underlying mapped file.  However, the mmap()
man page states that for a MAP_PRIVATE mapping:

  It is unspecified whether changes made to the file after
  the mmap() call are visible in the mapped region.

So user-mode users attempting to use futex operations on RO MAP_PRIVATE
mappings are depending on unspecified behavior.  Additionally a
RO MAP_PRIVATE mapping could fail to wake up in the following case.

  Thread-A: call futex(FUTEX_WAIT, memory-region-A).
            get_futex_key() return inode based key.
            sleep on the key
  Thread-B: call mprotect(PROT_READ|PROT_WRITE, memory-region-A)
  Thread-B: write memory-region-A.
            COW happen. This process's memory-region-A become related
            to new COWed private (ie PageAnon=1) page.
  Thread-B: call futex(FUETX_WAKE, memory-region-A).
            get_futex_key() return mm based key.
            IOW, we fail to wake up Thread-A.

Once again doing something like this is just silly and users who do
something like this get what they deserve.

While RO MAP_PRIVATE mappings are nonsensical, checking for a private
mapping requires walking the vmas and was deemed too costly to avoid a
userspace hang.

This Patch is based on Peter Zijlstra's initial patch with modifications to
only allow RO mappings for futex operations that need VERIFY_READ access.

Reported-by: David Oliver <david@rgmadvisors.com>
Signed-off-by: Shawn Bohrer <sbohrer@rgmadvisors.com>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Darren Hart <dvhart@linux.intel.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: peterz@infradead.org
Cc: eric.dumazet@gmail.com
Cc: zvonler@rgmadvisors.com
Cc: hughd@google.com
Link: http://lkml.kernel.org/r/1309450892-30676-1-git-send-email-sbohrer@rgmadvisors.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>


---
 kernel/futex.c |   54 ++++++++++++++++++++++++++++++++++++++++++------------
 1 file changed, 42 insertions(+), 12 deletions(-)

--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -203,6 +203,8 @@ static void drop_futex_key_refs(union fu
  * @uaddr:	virtual address of the futex
  * @fshared:	0 for a PROCESS_PRIVATE futex, 1 for PROCESS_SHARED
  * @key:	address where result is stored.
+ * @rw:		mapping needs to be read/write (values: VERIFY_READ,
+ *              VERIFY_WRITE)
  *
  * Returns a negative error code or 0
  * The key words are stored in *key on success.
@@ -214,12 +216,12 @@ static void drop_futex_key_refs(union fu
  * lock_page() might sleep, the caller should not hold a spinlock.
  */
 static int
-get_futex_key(u32 __user *uaddr, int fshared, union futex_key *key)
+get_futex_key(u32 __user *uaddr, int fshared, union futex_key *key, int rw)
 {
 	unsigned long address = (unsigned long)uaddr;
 	struct mm_struct *mm = current->mm;
 	struct page *page;
-	int err;
+	int err, ro = 0;
 
 	/*
 	 * The futex address must be "naturally" aligned.
@@ -247,14 +249,31 @@ get_futex_key(u32 __user *uaddr, int fsh
 
 again:
 	err = get_user_pages_fast(address, 1, 1, &page);
+	/*
+	 * If write access is not required (eg. FUTEX_WAIT), try
+	 * and get read-only access.
+	 */
+	if (err == -EFAULT && rw == VERIFY_READ) {
+		err = get_user_pages_fast(address, 1, 0, &page);
+		ro = 1;
+	}
 	if (err < 0)
 		return err;
+	else
+		err = 0;
 
 	page = compound_head(page);
 	lock_page(page);
 	if (!page->mapping) {
 		unlock_page(page);
 		put_page(page);
+		/*
+		* ZERO_PAGE pages don't have a mapping. Avoid a busy loop
+		* trying to find one. RW mapping would have COW'd (and thus
+		* have a mapping) so this page is RO and won't ever change.
+		*/
+		if ((page == ZERO_PAGE(address)))
+			return -EFAULT;
 		goto again;
 	}
 
@@ -266,6 +285,15 @@ again:
 	 * the object not the particular process.
 	 */
 	if (PageAnon(page)) {
+		/*
+		 * A RO anonymous page will never change and thus doesn't make
+		 * sense for futex operations.
+		 */
+		if (ro) {
+			err = -EFAULT;
+			goto out;
+		}
+
 		key->both.offset |= FUT_OFF_MMSHARED; /* ref taken on mm */
 		key->private.mm = mm;
 		key->private.address = address;
@@ -277,9 +305,10 @@ again:
 
 	get_futex_key_refs(key);
 
+out:
 	unlock_page(page);
 	put_page(page);
-	return 0;
+	return err;
 }
 
 static inline
@@ -880,7 +909,7 @@ static int futex_wake(u32 __user *uaddr,
 	if (!bitset)
 		return -EINVAL;
 
-	ret = get_futex_key(uaddr, fshared, &key);
+	ret = get_futex_key(uaddr, fshared, &key, VERIFY_READ);
 	if (unlikely(ret != 0))
 		goto out;
 
@@ -926,10 +955,10 @@ futex_wake_op(u32 __user *uaddr1, int fs
 	int ret, op_ret;
 
 retry:
-	ret = get_futex_key(uaddr1, fshared, &key1);
+	ret = get_futex_key(uaddr1, fshared, &key1, VERIFY_READ);
 	if (unlikely(ret != 0))
 		goto out;
-	ret = get_futex_key(uaddr2, fshared, &key2);
+	ret = get_futex_key(uaddr2, fshared, &key2, VERIFY_WRITE);
 	if (unlikely(ret != 0))
 		goto out_put_key1;
 
@@ -1188,10 +1217,11 @@ retry:
 		pi_state = NULL;
 	}
 
-	ret = get_futex_key(uaddr1, fshared, &key1);
+	ret = get_futex_key(uaddr1, fshared, &key1, VERIFY_READ);
 	if (unlikely(ret != 0))
 		goto out;
-	ret = get_futex_key(uaddr2, fshared, &key2);
+	ret = get_futex_key(uaddr2, fshared, &key2,
+			    requeue_pi ? VERIFY_WRITE : VERIFY_READ);
 	if (unlikely(ret != 0))
 		goto out_put_key1;
 
@@ -1746,7 +1776,7 @@ static int futex_wait_setup(u32 __user *
 	 */
 retry:
 	q->key = FUTEX_KEY_INIT;
-	ret = get_futex_key(uaddr, fshared, &q->key);
+	ret = get_futex_key(uaddr, fshared, &q->key, VERIFY_READ);
 	if (unlikely(ret != 0))
 		return ret;
 
@@ -1912,7 +1942,7 @@ static int futex_lock_pi(u32 __user *uad
 	q.requeue_pi_key = NULL;
 retry:
 	q.key = FUTEX_KEY_INIT;
-	ret = get_futex_key(uaddr, fshared, &q.key);
+	ret = get_futex_key(uaddr, fshared, &q.key, VERIFY_WRITE);
 	if (unlikely(ret != 0))
 		goto out;
 
@@ -2031,7 +2061,7 @@ retry:
 	if ((uval & FUTEX_TID_MASK) != task_pid_vnr(current))
 		return -EPERM;
 
-	ret = get_futex_key(uaddr, fshared, &key);
+	ret = get_futex_key(uaddr, fshared, &key, VERIFY_WRITE);
 	if (unlikely(ret != 0))
 		goto out;
 
@@ -2223,7 +2253,7 @@ static int futex_wait_requeue_pi(u32 __u
 	rt_waiter.task = NULL;
 
 	key2 = FUTEX_KEY_INIT;
-	ret = get_futex_key(uaddr2, fshared, &key2);
+	ret = get_futex_key(uaddr2, fshared, &key2, VERIFY_WRITE);
 	if (unlikely(ret != 0))
 		goto out;