The patch titled
Subject: ipc/sem.c: increase SEMMSL, SEMMNI, SEMOPM
has been added to the -mm tree. Its filename is
ipc-semc-increase-semmsl-semmni-semopm.patch
This patch should soon appear at
http://ozlabs.org/~akpm/mmots/broken-out/ipc-semc-increase-semmsl-semmni-semopm.patch
and later at
http://ozlabs.org/~akpm/mmotm/broken-out/ipc-semc-increase-semmsl-semmni-semopm.patch
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/SubmitChecklist when testing your code ***
The -mm tree is included into linux-next and is updated
there every 3-4 working days
------------------------------------------------------
From: Manfred Spraul <manfred@xxxxxxxxxxxxxxxx>
Subject: ipc/sem.c: increase SEMMSL, SEMMNI, SEMOPM
a)
SysV can be abused to allocate locked kernel memory. For most systems, a
small limit doesn't make sense, see the discussion with regards to SHMMAX.
Therefore: Increase the sysv sem limits so that all known applications
will work with these defaults.
b)
With regards to the maximum supported:
Some of the specified hard limits are not correct anymore, therefore the
patch updates the documentation.
- SEMMNI must stay below IPCMNI, which is 32768.
As for SHMMAX: Stay a bit below this limit.
- SEMMSL was limited to 8k, to ensure that the kmalloc for the kernel array
was limited to 16 kB (order=2)
This doesn't apply anymore:
- the allocation size isn't sizeof(short)*nsems anymore.
- ipc_alloc falls back to vmalloc
- SEMOPM should stay below 1000, to limit the kmalloc in semtimedop() to an
order=1 allocation.
Therefore: Leave it at 500 (order=0 allocation).
Note:
If an administrator must limit the memory allocations, then he can set the
values as necessary.
Or he can disable sysv entirely (as e.g. done by Android).
Signed-off-by: Manfred Spraul <manfred@xxxxxxxxxxxxxxxx>
Cc: Davidlohr Bueso <dave@xxxxxxxxxxxx>
Acked-by: Rafael Aquini <aquini@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
include/uapi/linux/sem.h | 18 +++++++++++++++---
1 file changed, 15 insertions(+), 3 deletions(-)
diff -puN include/uapi/linux/sem.h~ipc-semc-increase-semmsl-semmni-semopm include/uapi/linux/sem.h
--- a/include/uapi/linux/sem.h~ipc-semc-increase-semmsl-semmni-semopm
+++ a/include/uapi/linux/sem.h
@@ -63,10 +63,22 @@ struct seminfo {
int semaem;
};
-#define SEMMNI 128 /* <= IPCMNI max # of semaphore identifiers */
-#define SEMMSL 250 /* <= 8 000 max num of semaphores per id */
+/*
+ * SEMMNI, SEMMSL and SEMMNS are default values which can be
+ * modified by sysctl.
+ * The values has been chosen to be larger than necessary for any
+ * known configuration.
+ *
+ * SEMOPM should not be increased beyond 1000, otherwise there is the
+ * risk that semop()/semtimedop() fails due to kernel memory fragmentation when
+ * allocating the sop array.
+ */
+
+
+#define SEMMNI 32000 /* <= IPCMNI max # of semaphore identifiers */
+#define SEMMSL 32000 /* <= INT_MAX max num of semaphores per id */
#define SEMMNS (SEMMNI*SEMMSL) /* <= INT_MAX max # of semaphores in system */
-#define SEMOPM 32 /* <= 1 000 max num of ops per semop call */
+#define SEMOPM 500 /* <= 1 000 max num of ops per semop call */
#define SEMVMX 32767 /* <= 32767 semaphore maximum value */
#define SEMAEM SEMVMX /* adjust on exit max value */
_
Patches currently in -mm which might be from manfred@xxxxxxxxxxxxxxxx are
origin.patch
ipc-semc-chance-memory-barrier-in-sem_lock-to-smp_rmb.patch
ipc-semc-chance-memory-barrier-in-sem_lock-to-smp_rmb-fix.patch
ipc-semc-increase-semmsl-semmni-semopm.patch
ipc-msg-increase-msgmni-remove-scaling.patch
slab-leaks3-default-y.patch
--
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
