futex: Add bitset conditional wait/wakeup functionality

To allow the implementation of optimized rw-locks in user space, glibc
needs a possibility to select waiters for wakeup depending on a bitset
mask.

This requires two new futex OPs: FUTEX_WAIT_BITS and FUTEX_WAKE_BITS
These OPs are basically the same as FUTEX_WAIT and FUTEX_WAKE plus an
additional argument - a bitset. Further the FUTEX_WAIT_BITS OP is
expecting an absolute timeout value instead of the relative one, which
is used for the FUTEX_WAIT OP.

FUTEX_WAIT_BITS calls into the kernel with a bitset. The bitset is
stored in the futex_q structure, which is used to enqueue the waiter
into the hashed futex waitqueue.

FUTEX_WAKE_BITS also calls into the kernel with a bitset. The wakeup
function logically ANDs the bitset with the bitset stored in each
waiters futex_q structure. If the result is zero (i.e. none of the set
bits in the bitsets is matching), then the waiter is not woken up. If
the result is not zero (i.e. one of the set bits in the bitsets is
matching), then the waiter is woken.

The bitset provided by the caller must be non zero. In case the
provided bitset is zero the kernel returns EINVAL.

Internaly the new OPs are only extensions to the existing FUTEX_WAIT
and FUTEX_WAKE functions. The existing OPs hand a bitset with all bits
set into the futex_wait() and futex_wake() functions.

Signed-off-by: Thomas Gleixner <tgxl@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

1 files changed, 30 insertions, 7 deletions

diff --git a/kernel/futex.c b/kernel/futex.c
index 0006d64c448e..a6baaec44b8f 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -109,6 +109,9 @@ struct futex_q {
         /* Optional priority inheritance state: */
         struct futex_pi_state *pi_state;
         struct task_struct *task;
+
+        /* Bitset for the optional bitmasked wakeup */
+        u32 bitset;
 };
 
 /*
@@ -722,7 +725,7 @@ double_lock_hb(struct futex_hash_bucket *hb1, struct futex_hash_bucket *hb2)
  * to this virtual address:
  */
 static int futex_wake(u32 __user *uaddr, struct rw_semaphore *fshared,
-                      int nr_wake)
+                      int nr_wake, u32 bitset)
 {
         struct futex_hash_bucket *hb;
         struct futex_q *this, *next;
@@ -730,6 +733,9 @@ static int futex_wake(u32 __user *uaddr, struct rw_semaphore *fshared,
         union futex_key key;
         int ret;
 
+        if (!bitset)
+                return -EINVAL;
+
         futex_lock_mm(fshared);
 
         ret = get_futex_key(uaddr, fshared, &key);
@@ -746,6 +752,11 @@ static int futex_wake(u32 __user *uaddr, struct rw_semaphore *fshared,
                                 ret = -EINVAL;
                                 break;
                         }
+
+                        /* Check if one of the bits is set in both bitsets */
+                        if (!(this->bitset & bitset))
+                                continue;
+
                         wake_futex(this);
                         if (++ret >= nr_wake)
                                 break;
@@ -1156,7 +1167,7 @@ static int fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q,
 static long futex_wait_restart(struct restart_block *restart);
 
 static int futex_wait(u32 __user *uaddr, struct rw_semaphore *fshared,
-                      u32 val, ktime_t *abs_time)
+                      u32 val, ktime_t *abs_time, u32 bitset)
 {
         struct task_struct *curr = current;
         DECLARE_WAITQUEUE(wait, curr);
@@ -1167,7 +1178,11 @@ static int futex_wait(u32 __user *uaddr, struct rw_semaphore *fshared,
         struct hrtimer_sleeper t;
         int rem = 0;
 
+        if (!bitset)
+                return -EINVAL;
+
         q.pi_state = NULL;
+        q.bitset = bitset;
  retry:
         futex_lock_mm(fshared);
 
@@ -1295,6 +1310,7 @@ static int futex_wait(u32 __user *uaddr, struct rw_semaphore *fshared,
                 restart->futex.uaddr = (u32 *)uaddr;
                 restart->futex.val = val;
                 restart->futex.time = abs_time->tv64;
+                restart->futex.bitset = bitset;
                 restart->futex.flags = 0;
 
                 if (fshared)
@@ -1321,7 +1337,8 @@ static long futex_wait_restart(struct restart_block *restart)
         restart->fn = do_no_restart_syscall;
         if (restart->futex.flags & FLAGS_SHARED)
                 fshared = &current->mm->mmap_sem;
-        return (long)futex_wait(uaddr, fshared, restart->futex.val, &t);
+        return (long)futex_wait(uaddr, fshared, restart->futex.val, &t,
+                                restart->futex.bitset);
 }
 
 
@@ -1942,7 +1959,8 @@ retry:
                  * PI futexes happens in exit_pi_state():
                  */
                 if (!pi && (uval & FUTEX_WAITERS))
-                                futex_wake(uaddr, &curr->mm->mmap_sem, 1);
+                        futex_wake(uaddr, &curr->mm->mmap_sem, 1,
+                                   FUTEX_BITSET_MATCH_ANY);
         }
         return 0;
 }
@@ -2042,10 +2060,14 @@ long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout,
 
         switch (cmd) {
         case FUTEX_WAIT:
-                ret = futex_wait(uaddr, fshared, val, timeout);
+                val3 = FUTEX_BITSET_MATCH_ANY;
+        case FUTEX_WAIT_BITSET:
+                ret = futex_wait(uaddr, fshared, val, timeout, val3);
                 break;
         case FUTEX_WAKE:
-                ret = futex_wake(uaddr, fshared, val);
+                val3 = FUTEX_BITSET_MATCH_ANY;
+        case FUTEX_WAKE_BITSET:
+                ret = futex_wake(uaddr, fshared, val, val3);
                 break;
         case FUTEX_FD:
                 /* non-zero val means F_SETOWN(getpid()) & F_SETSIG(val) */
@@ -2085,7 +2107,8 @@ asmlinkage long sys_futex(u32 __user *uaddr, int op, u32 val,
         u32 val2 = 0;
         int cmd = op & FUTEX_CMD_MASK;
 
-        if (utime && (cmd == FUTEX_WAIT || cmd == FUTEX_LOCK_PI)) {
+        if (utime && (cmd == FUTEX_WAIT || cmd == FUTEX_LOCK_PI ||
+                      cmd == FUTEX_WAIT_BITSET)) {
                 if (copy_from_user(&ts, utime, sizeof(ts)) != 0)
                         return -EFAULT;
                 if (!timespec_valid(&ts))