[PATCH 5/6] ipc/sem.c: Replace shared sem_otime with per-semaphore value

[Manfred Spraul]

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 trashing.

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

diff --git a/include/linux/sem.h b/include/linux/sem.h
index 55e17f6..976ce3a 100644
--- 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 */
diff --git a/ipc/sem.c b/ipc/sem.c
index dcf99ef..e6d21f6 100644
--- 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. */
@@ -909,8 +910,14 @@ static void do_smart_update(struct sem_array *sma, struct sembuf *sops, int nsop
 			}
 		}
 	}
-	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();
+		}
+	}
 }
 
 
@@ -1056,6 +1063,21 @@ static unsigned long copy_semid_to_user(void __user *buf, struct semid64_ds *in,
 	}
 }
 
+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)
 {
@@ -1129,9 +1151,9 @@ static int semctl_nolock(struct ipc_namespace *ns, int semid,
 			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;
@@ -2019,6 +2041,9 @@ static int sysvipc_sem_proc_show(struct seq_file *s, void *it)
 {
 	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",
@@ -2030,7 +2055,7 @@ static int sysvipc_sem_proc_show(struct seq_file *s, void *it)
 			  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
-- 
1.8.1.4

--
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/