[ 45/69] ipc/sem.c: replace shared sem_otime with per-semaphore value

[Greg Kroah-Hartman]

3.10-stable review patch.  If anyone has any objections, please let me know.

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

From: Manfred Spraul <manfred@xxxxxxxxxxxxxxxx>

commit d12e1e50e47e0900dbbf52237b7e171f4f15ea1e upstream.

sem_otime contains the time of the last semaphore operation that
completed successfully.  Every operation updates this value, thus access
from multiple cpus can cause thrashing.

Therefore the patch replaces the variable with a per-semaphore variable.
The per-array sem_otime is only calculated when required.

No performance improvement on a single-socket i3 - only important for
larger systems.

Signed-off-by: Manfred Spraul <manfred@xxxxxxxxxxxxxxxx>
Cc: Rik van Riel <riel@xxxxxxxxxx>
Cc: Davidlohr Bueso <davidlohr.bueso@xxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Signed-off-by: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Cc: Mike Galbraith <efault@xxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>

---
 include/linux/sem.h |    1 -
 ipc/sem.c           |   37 +++++++++++++++++++++++++++++++------
 2 files changed, 31 insertions(+), 7 deletions(-)

--- a/include/linux/sem.h
+++ b/include/linux/sem.h
@@ -12,7 +12,6 @@ struct task_struct;
 struct sem_array {
 	struct kern_ipc_perm	____cacheline_aligned_in_smp
 				sem_perm;	/* permissions .. see ipc.h */
-	time_t			sem_otime;	/* last semop time */
 	time_t			sem_ctime;	/* last change time */
 	struct sem		*sem_base;	/* ptr to first semaphore in array */
 	struct list_head	pending_alter;	/* pending operations */
--- a/ipc/sem.c
+++ b/ipc/sem.c
@@ -99,6 +99,7 @@ struct sem {
 					/* that alter the semaphore */
 	struct list_head pending_const; /* pending single-sop operations */
 					/* that do not alter the semaphore*/
+	time_t	sem_otime;	/* candidate for sem_otime */
 } ____cacheline_aligned_in_smp;
 
 /* One queue for each sleeping process in the system. */
@@ -911,8 +912,14 @@ static void do_smart_update(struct sem_a
 			}
 		}
 	}
-	if (otime)
-		sma->sem_otime = get_seconds();
+	if (otime) {
+		if (sops == NULL) {
+			sma->sem_base[0].sem_otime = get_seconds();
+		} else {
+			sma->sem_base[sops[0].sem_num].sem_otime =
+								get_seconds();
+		}
+	}
 }
 
 
@@ -1058,6 +1065,21 @@ static unsigned long copy_semid_to_user(
 	}
 }
 
+static time_t get_semotime(struct sem_array *sma)
+{
+	int i;
+	time_t res;
+
+	res = sma->sem_base[0].sem_otime;
+	for (i = 1; i < sma->sem_nsems; i++) {
+		time_t to = sma->sem_base[i].sem_otime;
+
+		if (to > res)
+			res = to;
+	}
+	return res;
+}
+
 static int semctl_nolock(struct ipc_namespace *ns, int semid,
 			 int cmd, int version, void __user *p)
 {
@@ -1131,9 +1153,9 @@ static int semctl_nolock(struct ipc_name
 			goto out_unlock;
 
 		kernel_to_ipc64_perm(&sma->sem_perm, &tbuf.sem_perm);
-		tbuf.sem_otime  = sma->sem_otime;
-		tbuf.sem_ctime  = sma->sem_ctime;
-		tbuf.sem_nsems  = sma->sem_nsems;
+		tbuf.sem_otime = get_semotime(sma);
+		tbuf.sem_ctime = sma->sem_ctime;
+		tbuf.sem_nsems = sma->sem_nsems;
 		rcu_read_unlock();
 		if (copy_semid_to_user(p, &tbuf, version))
 			return -EFAULT;
@@ -2025,6 +2047,9 @@ static int sysvipc_sem_proc_show(struct
 {
 	struct user_namespace *user_ns = seq_user_ns(s);
 	struct sem_array *sma = it;
+	time_t sem_otime;
+
+	sem_otime = get_semotime(sma);
 
 	return seq_printf(s,
 			  "%10d %10d  %4o %10u %5u %5u %5u %5u %10lu %10lu\n",
@@ -2036,7 +2061,7 @@ static int sysvipc_sem_proc_show(struct
 			  from_kgid_munged(user_ns, sma->sem_perm.gid),
 			  from_kuid_munged(user_ns, sma->sem_perm.cuid),
 			  from_kgid_munged(user_ns, sma->sem_perm.cgid),
-			  sma->sem_otime,
+			  sem_otime,
 			  sma->sem_ctime);
 }
 #endif


--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/