ipc/mqueue: update maximums for the mqueue subsystem

Commit b231cca4381e ("message queues: increase range limits") changed the
maximum size of a message in a message queue from INT_MAX to 8192*128.
Unfortunately, we had customers that relied on a size much larger than
8192*128 on their production systems.  After reviewing POSIX, we found
that it is silent on the maximum message size.  We did find a couple other
areas in which it was not silent.  Fix up the mqueue maximums so that the
customer's system can continue to work, and document both the POSIX and
real world requirements in ipc_namespace.h so that we don't have this
issue crop back up.

Also, commit 9cf18e1dd74cd0 ("ipc: HARD_MSGMAX should be higher not lower
on 64bit") fiddled with HARD_MSGMAX without realizing that the number was
intentionally in place to limit the msg queue depth to one that was small
enough to kmalloc an array of pointers (hence why we divided 128k by
sizeof(long)).  If we wish to meet POSIX requirements, we have no choice
but to change our allocation to a vmalloc instead (at least for the large
queue size case).  With that, it's possible to increase our allowed
maximum to the POSIX requirements (or more if we choose).

[sfr@canb.auug.org.au: using vmalloc requires including vmalloc.h]
Signed-off-by: Doug Ledford <dledford@redhat.com>
Cc: Serge E. Hallyn <serue@us.ibm.com>
Cc: Amerigo Wang <amwang@redhat.com>
Cc: Joe Korty <joe.korty@ccur.com>
Cc: Jiri Slaby <jslaby@suse.cz>
Acked-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Manfred Spraul <manfred@colorfullife.com>
Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

2 files changed, 44 insertions, 14 deletions

diff --git a/include/linux/ipc_namespace.h b/include/linux/ipc_namespace.h
index bde094ee7b0e..6e1dd08194fd 100644
--- a/include/linux/ipc_namespace.h
+++ b/include/linux/ipc_namespace.h
@@ -90,18 +90,41 @@ static inline void shm_destroy_orphaned(struct ipc_namespace *ns) {}
 
 #ifdef CONFIG_POSIX_MQUEUE
 extern int mq_init_ns(struct ipc_namespace *ns);
-/* default values */
-#define MIN_QUEUESMAX  1
-#define DFLT_QUEUESMAX 256     /* max number of message queues */
-#define HARD_QUEUESMAX 1024
-#define MIN_MSGMAX     1
-#define DFLT_MSG       10U
-#define DFLT_MSGMAX    10      /* max number of messages in each queue */
-#define HARD_MSGMAX    (32768*sizeof(void *)/4)
-#define MIN_MSGSIZEMAX  128
-#define DFLT_MSGSIZE    8192U
-#define DFLT_MSGSIZEMAX 8192   /* max message size */
-#define HARD_MSGSIZEMAX (8192*128)
+/*
+ * POSIX Message Queue default values:
+ *
+ * MIN_*: Lowest value an admin can set the maximum unprivileged limit to
+ * DFLT_*MAX: Default values for the maximum unprivileged limits
+ * DFLT_{MSG,MSGSIZE}: Default values used when the user doesn't supply
+ *   an attribute to the open call and the queue must be created
+ * HARD_*: Highest value the maximums can be set to.  These are enforced
+ *   on CAP_SYS_RESOURCE apps as well making them inviolate (so make them
+ *   suitably high)
+ *
+ * POSIX Requirements:
+ *   Per app minimum openable message queues - 8.  This does not map well
+ *     to the fact that we limit the number of queues on a per namespace
+ *     basis instead of a per app basis.  So, make the default high enough
+ *     that no given app should have a hard time opening 8 queues.
+ *   Minimum maximum for HARD_MSGMAX - 32767.  I bumped this to 65536.
+ *   Minimum maximum for HARD_MSGSIZEMAX - POSIX is silent on this.  However,
+ *     we have run into a situation where running applications in the wild
+ *     require this to be at least 5MB, and preferably 10MB, so I set the
+ *     value to 16MB in hopes that this user is the worst of the bunch and
+ *     the new maximum will handle anyone else.  I may have to revisit this
+ *     in the future.
+ */
+#define MIN_QUEUESMAX                   1
+#define DFLT_QUEUESMAX                256
+#define HARD_QUEUESMAX               1024
+#define MIN_MSGMAX                      1
+#define DFLT_MSG                       64U
+#define DFLT_MSGMAX                  1024
+#define HARD_MSGMAX                 65536
+#define MIN_MSGSIZEMAX                128
+#define DFLT_MSGSIZE                 8192U
+#define DFLT_MSGSIZEMAX        (1024*1024)
+#define HARD_MSGSIZEMAX     (16*1024*1024)
 #else
 static inline int mq_init_ns(struct ipc_namespace *ns) { return 0; }
 #endif
diff --git a/ipc/mqueue.c b/ipc/mqueue.c
index 6e10a55a78c5..f8eba5e46c5a 100644
--- a/ipc/mqueue.c
+++ b/ipc/mqueue.c
@@ -24,6 +24,7 @@
 #include <linux/mqueue.h>
 #include <linux/msg.h>
 #include <linux/skbuff.h>
+#include <linux/vmalloc.h>
 #include <linux/netlink.h>
 #include <linux/syscalls.h>
 #include <linux/audit.h>
@@ -152,7 +153,10 @@ static struct inode *mqueue_get_inode(struct super_block *sb,
                         info->attr.mq_msgsize = attr->mq_msgsize;
                 }
                 mq_msg_tblsz = info->attr.mq_maxmsg * sizeof(struct msg_msg *);
-                info->messages = kmalloc(mq_msg_tblsz, GFP_KERNEL);
+                if (mq_msg_tblsz > KMALLOC_MAX_SIZE)
+                        info->messages = vmalloc(mq_msg_tblsz);
+                else
+                        info->messages = kmalloc(mq_msg_tblsz, GFP_KERNEL);
                 if (!info->messages)
                         goto out_inode;
 
@@ -262,7 +266,10 @@ static void mqueue_evict_inode(struct inode *inode)
         spin_lock(&info->lock);
         for (i = 0; i < info->attr.mq_curmsgs; i++)
                 free_msg(info->messages[i]);
-        kfree(info->messages);
+        if (info->attr.mq_maxmsg * sizeof(struct msg_msg *) > KMALLOC_MAX_SIZE)
+                vfree(info->messages);
+        else
+                kfree(info->messages);
         spin_unlock(&info->lock);
 
         /* Total amount of bytes accounted for the mqueue */