Skip to contentSkip to conversation

locking fixes

GIT PULL New Ingo Molnar 4 participants 5 messages Jan 17, 2018 – Jan 24, 2018 Locking primitives

lore
Share & tools
lore
#0 lore raw

Linus,

Please pull the latest locking-urgent-for-linus git tree from:

git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git locking-urgent-for-linus

# HEAD: fbe0e839d1e22d88810f3ee3e2f1479be4c0aa4a futex: Prevent overflow by strengthen input validation

Two futex fixes: a input parameters robustness fix, and futex race fixes.

Thanks,

Ingo

------------------>
Li Jinyue (1):
futex: Prevent overflow by strengthen input validation

Peter Zijlstra (1):
futex: Avoid violating the 10th rule of futex

 kernel/futex.c                  | 86 +++++++++++++++++++++++++++++++++--------
 kernel/locking/rtmutex.c        | 26 +++++++++----
 kernel/locking/rtmutex_common.h |  1 +
 3 files changed, 90 insertions(+), 23 deletions(-)
kernel/futex.c +70 -16
index 57d0b3657e16..8c5424dd5924 100644
@@ -1878,6 +1878,9 @@ static int futex_requeue(u32 __user *uaddr1, unsigned int flags,
 	struct futex_q *this, *next;
 	DEFINE_WAKE_Q(wake_q);
 
+	if (nr_wake < 0 || nr_requeue < 0)
+		return -EINVAL;
+
 	/*
 	 * When PI not supported: return -ENOSYS if requeue_pi is true,
 	 * consequently the compiler knows requeue_pi is always false past
@@ -2294,21 +2297,17 @@ static void unqueue_me_pi(struct futex_q *q)
 	spin_unlock(q->lock_ptr);
 }
 
-/*
- * Fixup the pi_state owner with the new owner.
- *
- * Must be called with hash bucket lock held and mm->sem held for non
- * private futexes.
- */
 static int fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q,
-				struct task_struct *newowner)
+				struct task_struct *argowner)
 {
-	u32 newtid = task_pid_vnr(newowner) | FUTEX_WAITERS;
 	struct futex_pi_state *pi_state = q->pi_state;
 	u32 uval, uninitialized_var(curval), newval;
-	struct task_struct *oldowner;
+	struct task_struct *oldowner, *newowner;
+	u32 newtid;
 	int ret;
 
+	lockdep_assert_held(q->lock_ptr);
+
 	raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock);
 
 	oldowner = pi_state->owner;
@@ -2317,11 +2316,17 @@ static int fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q,
 		newtid |= FUTEX_OWNER_DIED;
 
 	/*
-	 * We are here either because we stole the rtmutex from the
-	 * previous highest priority waiter or we are the highest priority
-	 * waiter but have failed to get the rtmutex the first time.
+	 * We are here because either:
+	 *
+	 *  - we stole the lock and pi_state->owner needs updating to reflect
+	 *    that (@argowner == current),
+	 *
+	 * or:
+	 *
+	 *  - someone stole our lock and we need to fix things to point to the
+	 *    new owner (@argowner == NULL).
 	 *
-	 * We have to replace the newowner TID in the user space variable.
+	 * Either way, we have to replace the TID in the user space variable.
 	 * This must be atomic as we have to preserve the owner died bit here.
 	 *
 	 * Note: We write the user space value _before_ changing the pi_state
@@ -2334,6 +2339,42 @@ static int fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q,
 	 * in the PID check in lookup_pi_state.
 	 */
 retry:
+	if (!argowner) {
+		if (oldowner != current) {
+			/*
+			 * We raced against a concurrent self; things are
+			 * already fixed up. Nothing to do.
+			 */
+			ret = 0;
+			goto out_unlock;
+		}
+
+		if (__rt_mutex_futex_trylock(&pi_state->pi_mutex)) {
+			/* We got the lock after all, nothing to fix. */
+			ret = 0;
+			goto out_unlock;
+		}
+
+		/*
+		 * Since we just failed the trylock; there must be an owner.
+		 */
+		newowner = rt_mutex_owner(&pi_state->pi_mutex);
+		BUG_ON(!newowner);
+	} else {
+		WARN_ON_ONCE(argowner != current);
+		if (oldowner == current) {
+			/*
+			 * We raced against a concurrent self; things are
+			 * already fixed up. Nothing to do.
+			 */
+			ret = 0;
+			goto out_unlock;
+		}
+		newowner = argowner;
+	}
+
+	newtid = task_pid_vnr(newowner) | FUTEX_WAITERS;
+
 	if (get_futex_value_locked(&uval, uaddr))
 		goto handle_fault;
 
@@ -2434,15 +2475,28 @@ static int fixup_owner(u32 __user *uaddr, struct futex_q *q, int locked)
 		 * Got the lock. We might not be the anticipated owner if we
 		 * did a lock-steal - fix up the PI-state in that case:
 		 *
-		 * We can safely read pi_state->owner without holding wait_lock
-		 * because we now own the rt_mutex, only the owner will attempt
-		 * to change it.
+		 * Speculative pi_state->owner read (we don't hold wait_lock);
+		 * since we own the lock pi_state->owner == current is the
+		 * stable state, anything else needs more attention.
 		 */
 		if (q->pi_state->owner != current)
 			ret = fixup_pi_state_owner(uaddr, q, current);
 		goto out;
 	}
 
+	/*
+	 * If we didn't get the lock; check if anybody stole it from us. In
+	 * that case, we need to fix up the uval to point to them instead of
+	 * us, otherwise bad things happen. [10]
+	 *
+	 * Another speculative read; pi_state->owner == current is unstable
+	 * but needs our attention.
+	 */
+	if (q->pi_state->owner == current) {
+		ret = fixup_pi_state_owner(uaddr, q, NULL);
+		goto out;
+	}
+
 	/*
 	 * Paranoia check. If we did not take the lock, then we should not be
 	 * the owner of the rt_mutex.
kernel/locking/rtmutex.c +19 -7
index 6f3dba6e4e9e..65cc0cb984e6 100644
@@ -1290,6 +1290,19 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state,
 	return ret;
 }
 
+static inline int __rt_mutex_slowtrylock(struct rt_mutex *lock)
+{
+	int ret = try_to_take_rt_mutex(lock, current, NULL);
+
+	/*
+	 * try_to_take_rt_mutex() sets the lock waiters bit
+	 * unconditionally. Clean this up.
+	 */
+	fixup_rt_mutex_waiters(lock);
+
+	return ret;
+}
+
 /*
  * Slow path try-lock function:
  */
@@ -1312,13 +1325,7 @@ static inline int rt_mutex_slowtrylock(struct rt_mutex *lock)
 	 */
 	raw_spin_lock_irqsave(&lock->wait_lock, flags);
 
-	ret = try_to_take_rt_mutex(lock, current, NULL);
-
-	/*
-	 * try_to_take_rt_mutex() sets the lock waiters bit
-	 * unconditionally. Clean this up.
-	 */
-	fixup_rt_mutex_waiters(lock);
+	ret = __rt_mutex_slowtrylock(lock);
 
 	raw_spin_unlock_irqrestore(&lock->wait_lock, flags);
 
@@ -1505,6 +1512,11 @@ int __sched rt_mutex_futex_trylock(struct rt_mutex *lock)
 	return rt_mutex_slowtrylock(lock);
 }
 
+int __sched __rt_mutex_futex_trylock(struct rt_mutex *lock)
+{
+	return __rt_mutex_slowtrylock(lock);
+}
+
 /**
  * rt_mutex_timed_lock - lock a rt_mutex interruptible
  *			the timeout structure is provided
kernel/locking/rtmutex_common.h +1 -0
index 124e98ca0b17..68686b3ec3c1 100644
@@ -148,6 +148,7 @@ extern bool rt_mutex_cleanup_proxy_lock(struct rt_mutex *lock,
 				 struct rt_mutex_waiter *waiter);
 
 extern int rt_mutex_futex_trylock(struct rt_mutex *l);
+extern int __rt_mutex_futex_trylock(struct rt_mutex *l);
 
 extern void rt_mutex_futex_unlock(struct rt_mutex *lock);
 extern bool __rt_mutex_futex_unlock(struct rt_mutex *lock,
#1 lore raw

Hi Ingo, Peter,

Quoted 24 lines · Ingo Molnar

Please pull the latest locking-urgent-for-linus git tree from:

git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git locking-urgent-for-linus

# HEAD: fbe0e839d1e22d88810f3ee3e2f1479be4c0aa4a futex: Prevent overflow by strengthen input validation

Two futex fixes: a input parameters robustness fix, and futex race fixes.

Peter Zijlstra (1):
futex: Avoid violating the 10th rule of futex

kernel/futex.c +0 -6
@@ -2294,21 +2297,17 @@ static void unqueue_me_pi(struct futex_q *q)
        spin_unlock(q->lock_ptr);
 }
 
-/*
- * Fixup the pi_state owner with the new owner.
- *
- * Must be called with hash bucket lock held and mm->sem held for non
- * private futexes.
- */

kernel/futex.c static void unqueue_me_pi(struct futex_q *q) · line 2306

Quoted 10 lines
kernel/futex.c +3 -3
 static int fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q,
-                               struct task_struct *newowner)
+                               struct task_struct *argowner)
 {
-       u32 newtid = task_pid_vnr(newowner) | FUTEX_WAITERS;
        struct futex_pi_state *pi_state = q->pi_state;
        u32 uval, uninitialized_var(curval), newval;
-       struct task_struct *oldowner;
+       struct task_struct *oldowner, *newowner;
+       u32 newtid;

new tid is no longer initialized...

kernel/futex.c static int fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q, · line 2316

Quoted 9 lines
kernel/futex.c +2 -0
        int ret;
 
+       lockdep_assert_held(q->lock_ptr);
+
        raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock);
 
        oldowner = pi_state->owner;
@@ -2317,11 +2316,17 @@ static int fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q,
                newtid |= FUTEX_OWNER_DIED;

... leading to a compiler warning with gcc 4.1.2:

warning: ‘newtid’ is used uninitialized in this function

I guess newer compilers don't give the warning, as the result of the assignment above is not used at all, and thus may be optimized away...

Quoted 49 lines
kernel/futex.c +35 -4
        /*
-        * We are here either because we stole the rtmutex from the
-        * previous highest priority waiter or we are the highest priority
-        * waiter but have failed to get the rtmutex the first time.
+        * We are here because either:
+        *
+        *  - we stole the lock and pi_state->owner needs updating to reflect
+        *    that (@argowner == current),
+        *
+        * or:
+        *
+        *  - someone stole our lock and we need to fix things to point to the
+        *    new owner (@argowner == NULL).
         *
-        * We have to replace the newowner TID in the user space variable.
+        * Either way, we have to replace the TID in the user space variable.
         * This must be atomic as we have to preserve the owner died bit here.
         *
         * Note: We write the user space value _before_ changing the pi_state
@@ -2334,6 +2339,42 @@ static int fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q,
         * in the PID check in lookup_pi_state.
         */
 retry:
+       if (!argowner) {
+               if (oldowner != current) {
+                       /*
+                        * We raced against a concurrent self; things are
+                        * already fixed up. Nothing to do.
+                        */
+                       ret = 0;
+                       goto out_unlock;
+               }
+
+               if (__rt_mutex_futex_trylock(&pi_state->pi_mutex)) {
+                       /* We got the lock after all, nothing to fix. */
+                       ret = 0;
+                       goto out_unlock;
+               }
+
+               /*
+                * Since we just failed the trylock; there must be an owner.
+                */
+               newowner = rt_mutex_owner(&pi_state->pi_mutex);
+               BUG_ON(!newowner);
+       } else {
+               WARN_ON_ONCE(argowner != current);
+               if (oldowner == current) {
+                       /*

kernel/futex.c static int fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q, · line 2376

Quoted 10 lines
kernel/futex.c +10 -0
+                        * We raced against a concurrent self; things are
+                        * already fixed up. Nothing to do.
+                        */
+                       ret = 0;
+                       goto out_unlock;
+               }
+               newowner = argowner;
+       }
+
+       newtid = task_pid_vnr(newowner) | FUTEX_WAITERS;

... since it is always overwritten here.

Is that intentional?

Gr{oetje,eeting}s,

Geert

--
Geert Uytterhoeven -- There's lots of Linux beyond ia32 -- [email protected]

In personal conversations with technical people, I call myself a hacker. But when I'm talking to journalists I just say "programmer" or something like that.
-- Linus Torvalds

maintainer
#2 lore raw
Quoted 85 lines · Geert Uytterhoeven

Review

Quoted 7 lines

static int fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q,

(quoted diff) +3 -0
+                               struct task_struct *argowner)
 {
        struct futex_pi_state *pi_state = q->pi_state;
        u32 uval, uninitialized_var(curval), newval;
+       struct task_struct *oldowner, *newowner;
+       u32 newtid;

new tid is no longer initialized...

Review static int fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q, · line 2316

Quoted 9 lines
        int ret;
(quoted diff) +2 -0
+       lockdep_assert_held(q->lock_ptr);
+
        raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock);
 
        oldowner = pi_state->owner;
@@ -2317,11 +2316,17 @@ static int fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q,
                newtid |= FUTEX_OWNER_DIED;

... leading to a compiler warning with gcc 4.1.2:

warning: ‘newtid’ is used uninitialized in this function

I guess newer compilers don't give the warning, as the result of the assignment above is not used at all, and thus may be optimized away...

Quoted 45 lines
(quoted diff) +35 -0
        /*
+        * We are here because either:
+        *
+        *  - we stole the lock and pi_state->owner needs updating to reflect
+        *    that (@argowner == current),
+        *
+        * or:
+        *
+        *  - someone stole our lock and we need to fix things to point to the
+        *    new owner (@argowner == NULL).
         *
+        * Either way, we have to replace the TID in the user space variable.
         * This must be atomic as we have to preserve the owner died bit here.
         *
         * Note: We write the user space value _before_ changing the pi_state
@@ -2334,6 +2339,42 @@ static int fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q,
         * in the PID check in lookup_pi_state.
         */
 retry:
+       if (!argowner) {
+               if (oldowner != current) {
+                       /*
+                        * We raced against a concurrent self; things are
+                        * already fixed up. Nothing to do.
+                        */
+                       ret = 0;
+                       goto out_unlock;
+               }
+
+               if (__rt_mutex_futex_trylock(&pi_state->pi_mutex)) {
+                       /* We got the lock after all, nothing to fix. */
+                       ret = 0;
+                       goto out_unlock;
+               }
+
+               /*
+                * Since we just failed the trylock; there must be an owner.
+                */
+               newowner = rt_mutex_owner(&pi_state->pi_mutex);
+               BUG_ON(!newowner);
+       } else {
+               WARN_ON_ONCE(argowner != current);
+               if (oldowner == current) {
+                       /*

Review static int fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q, · line 2376

Quoted 10 lines
(quoted diff) +10 -0
+                        * We raced against a concurrent self; things are
+                        * already fixed up. Nothing to do.
+                        */
+                       ret = 0;
+                       goto out_unlock;
+               }
+               newowner = argowner;
+       }
+
+       newtid = task_pid_vnr(newowner) | FUTEX_WAITERS;

... since it is always overwritten here.

Quoted 1 line

Is that intentional?

No, I think you actually spotted a bug there. We now can't set OWNER_DIED anymore, which is bad.

I think the below fixes things, but let me go trawl through the various futex test things, because I think I've seen a unit test for this _somewhere_.

---
 kernel/futex.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)
kernel/futex.c +3 -3
index 8c5424dd5924..7f719d110908 100644
@@ -2311,9 +2311,6 @@ static int fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q,
 	raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock);
 
 	oldowner = pi_state->owner;
-	/* Owner died? */
-	if (!pi_state->owner)
-		newtid |= FUTEX_OWNER_DIED;
 
 	/*
 	 * We are here because either:
@@ -2374,6 +2371,9 @@ static int fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q,
 	}
 
 	newtid = task_pid_vnr(newowner) | FUTEX_WAITERS;
+	/* Owner died? */
+	if (!pi_state->owner)
+		newtid |= FUTEX_OWNER_DIED;
 
 	if (get_futex_value_locked(&uval, uaddr))
 		goto handle_fault;
maintainer
#3 lore raw

PATCH 1/1 futex: Fix OWNER_DEAD fixup

Quoted 6 lines · Peter Zijlstra

No, I think you actually spotted a bug there. We now can't set OWNER_DIED anymore, which is bad.

I think the below fixes things, but let me go trawl through the various futex test things, because I think I've seen a unit test for this _somewhere_.

glibc has robustpi tests, but nothing there triggered this case.

---
Subject: futex: Fix OWNER_DEAD fixup
From: Peter Zijlstra <[email protected]>
Date: Mon, 22 Jan 2018 11:39:47 +0100

Both Geert and DaveJ reported that the recent futex commit:

c1e2f0eaf015 ("futex: Avoid violating the 10th rule of futex")

introduced a problem with setting OWNER_DEAD. We set the bit on an uninitialized variable and then entirely optimize it away as a dead-store.

Move the setting of the bit to where it is more useful.

Cc Ingo Molnar <[email protected]>
Cc Andrew Morton <[email protected]>
Cc Linus Torvalds <[email protected]>
Cc Thomas Gleixner <[email protected]>
Cc "Paul E. McKenney" <[email protected]>
Fixes c1e2f0eaf015 ("futex: Avoid violating the 10th rule of futex")
---
 kernel/futex.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)
kernel/futex.c +3 -3
index 8c5424dd5924..7f719d110908 100644
@@ -2311,9 +2311,6 @@ static int fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q,
 	raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock);
 
 	oldowner = pi_state->owner;
-	/* Owner died? */
-	if (!pi_state->owner)
-		newtid |= FUTEX_OWNER_DIED;
 
 	/*
 	 * We are here because either:
@@ -2374,6 +2371,9 @@ static int fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q,
 	}
 
 	newtid = task_pid_vnr(newowner) | FUTEX_WAITERS;
+	/* Owner died? */
+	if (!pi_state->owner)
+		newtid |= FUTEX_OWNER_DIED;
 
 	if (get_futex_value_locked(&uval, uaddr))
 		goto handle_fault;
#4 lore raw

[tip:locking/urgent] futex: Fix OWNER_DEAD fixup

In reply to Peter Zijlstra
futex: Fix OWNER_DEAD fixup
Commit-ID:  a97cb0e7b3f4c6297fd857055ae8e895f402f501
Gitweb:     https://git.kernel.org/tip/a97cb0e7b3f4c6297fd857055ae8e895f402f501
Author:     Peter Zijlstra <[email protected]>
AuthorDate: Mon, 22 Jan 2018 11:39:47 +0100
Committer:  Ingo Molnar <[email protected]>
CommitDate: Wed, 24 Jan 2018 09:58:18 +0100

futex: Fix OWNER_DEAD fixup

Both Geert and DaveJ reported that the recent futex commit:

c1e2f0eaf015 ("futex: Avoid violating the 10th rule of futex")

introduced a problem with setting OWNER_DEAD. We set the bit on an uninitialized variable and then entirely optimize it away as a dead-store.

Move the setting of the bit to where it is more useful.

Cc Andrew Morton <[email protected]>
Cc Linus Torvalds <[email protected]>
Cc Paul E. McKenney <[email protected]>
Cc Peter Zijlstra <[email protected]>
Cc Thomas Gleixner <[email protected]>
Fixes c1e2f0eaf015 ("futex: Avoid violating the 10th rule of futex")
---
 kernel/futex.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)
kernel/futex.c +3 -3
index 8c5424d..7f719d1 100644
@@ -2311,9 +2311,6 @@ static int fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q,
 	raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock);
 
 	oldowner = pi_state->owner;
-	/* Owner died? */
-	if (!pi_state->owner)
-		newtid |= FUTEX_OWNER_DIED;
 
 	/*
 	 * We are here because either:
@@ -2374,6 +2371,9 @@ retry:
 	}
 
 	newtid = task_pid_vnr(newowner) | FUTEX_WAITERS;
+	/* Owner died? */
+	if (!pi_state->owner)
+		newtid |= FUTEX_OWNER_DIED;
 
 	if (get_futex_value_locked(&uval, uaddr))
 		goto handle_fault;