Merge branch 'userns-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace

Pull namespace updates from Eric Biederman:
 "There was a lot of work this cycle fixing bugs that were discovered
  after the merge window and getting everything ready where we can
  reasonably support fully unprivileged fuse. The bug fixes you already
  have and much of the unprivileged fuse work is coming in via other
  trees.

  Still left for fully unprivileged fuse is figuring out how to cleanly
  handle .set_acl and .get_acl in the legacy case, and properly handling
  of evm xattrs on unprivileged mounts.

  Included in the tree is a cleanup from Alexely that replaced a linked
  list with a statically allocated fix sized array for the pid caches,
  which simplifies and speeds things up.

  Then there is are some cleanups and fixes for the ipc namespace. The
  motivation was that in reviewing other code it was discovered that
  access ipc objects from different pid namespaces recorded pids in such
  a way that when asked the wrong pids were returned. In the worst case
  there has been a measured 30% performance impact for sysvipc
  semaphores. Other test cases showed no measurable performance impact.
  Manfred Spraul and Davidlohr Bueso who tend to work on sysvipc
  performance both gave the nod that this is good enough.

  Casey Schaufler and James Morris have given their approval to the LSM
  side of the changes.

  I simplified the types and the code dealing with sysvipc to pass just
  kern_ipc_perm for all three types of ipc. Which reduced the header
  dependencies throughout the kernel and simplified the lsm code.

  Which let me work on the pid fixes without having to worry about
  trivial changes causing complete kernel recompiles"

* 'userns-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace:
  ipc/shm: Fix pid freeing.
  ipc/shm: fix up for struct file no longer being available in shm.h
  ipc/smack: Tidy up from the change in type of the ipc security hooks
  ipc: Directly call the security hook in ipc_ops.associate
  ipc/sem: Fix semctl(..., GETPID, ...) between pid namespaces
  ipc/msg: Fix msgctl(..., IPC_STAT, ...) between pid namespaces
  ipc/shm: Fix shmctl(..., IPC_STAT, ...) between pid namespaces.
  ipc/util: Helpers for making the sysvipc operations pid namespace aware
  ipc: Move IPCMNI from include/ipc.h into ipc/util.h
  msg: Move struct msg_queue into ipc/msg.c
  shm: Move struct shmid_kernel into ipc/shm.c
  sem: Move struct sem and struct sem_array into ipc/sem.c
  msg/security: Pass kern_ipc_perm not msg_queue into the msg_queue security hooks
  shm/security: Pass kern_ipc_perm not shmid_kernel into the shm security hooks
  sem/security: Pass kern_ipc_perm not sem_array into the sem security hooks
  pidns: simpler allocation of pid_* caches

1 files changed, 24 insertions, 43 deletions

diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c
index 93b57f026688..2a2ac53d8b8b 100644
--- a/kernel/pid_namespace.c
+++ b/kernel/pid_namespace.c
@@ -23,55 +23,39 @@
 #include <linux/sched/signal.h>
 #include <linux/idr.h>
 
-struct pid_cache {
-        int nr_ids;
-        char name[16];
-        struct kmem_cache *cachep;
-        struct list_head list;
-};
-
-static LIST_HEAD(pid_caches_lh);
 static DEFINE_MUTEX(pid_caches_mutex);
 static struct kmem_cache *pid_ns_cachep;
+/* MAX_PID_NS_LEVEL is needed for limiting size of 'struct pid' */
+#define MAX_PID_NS_LEVEL 32
+/* Write once array, filled from the beginning. */
+static struct kmem_cache *pid_cache[MAX_PID_NS_LEVEL];
 
 /*
  * creates the kmem cache to allocate pids from.
- * @nr_ids: the number of numerical ids this pid will have to carry
+ * @level: pid namespace level
  */
 
-static struct kmem_cache *create_pid_cachep(int nr_ids)
+static struct kmem_cache *create_pid_cachep(unsigned int level)
 {
-        struct pid_cache *pcache;
-        struct kmem_cache *cachep;
-
+        /* Level 0 is init_pid_ns.pid_cachep */
+        struct kmem_cache **pkc = &pid_cache[level - 1];
+        struct kmem_cache *kc;
+        char name[4 + 10 + 1];
+        unsigned int len;
+
+        kc = READ_ONCE(*pkc);
+        if (kc)
+                return kc;
+
+        snprintf(name, sizeof(name), "pid_%u", level + 1);
+        len = sizeof(struct pid) + level * sizeof(struct upid);
         mutex_lock(&pid_caches_mutex);
-        list_for_each_entry(pcache, &pid_caches_lh, list)
-                if (pcache->nr_ids == nr_ids)
-                        goto out;
-
-        pcache = kmalloc(sizeof(struct pid_cache), GFP_KERNEL);
-        if (pcache == NULL)
-                goto err_alloc;
-
-        snprintf(pcache->name, sizeof(pcache->name), "pid_%d", nr_ids);
-        cachep = kmem_cache_create(pcache->name,
-                        sizeof(struct pid) + (nr_ids - 1) * sizeof(struct upid),
-                        0, SLAB_HWCACHE_ALIGN, NULL);
-        if (cachep == NULL)
-                goto err_cachep;
-
-        pcache->nr_ids = nr_ids;
-        pcache->cachep = cachep;
-        list_add(&pcache->list, &pid_caches_lh);
-out:
+        /* Name collision forces to do allocation under mutex. */
+        if (!*pkc)
+                *pkc = kmem_cache_create(name, len, 0, SLAB_HWCACHE_ALIGN, 0);
         mutex_unlock(&pid_caches_mutex);
-        return pcache->cachep;
-
-err_cachep:
-        kfree(pcache);
-err_alloc:
-        mutex_unlock(&pid_caches_mutex);
-        return NULL;
+        /* current can fail, but someone else can succeed. */
+        return READ_ONCE(*pkc);
 }
 
 static void proc_cleanup_work(struct work_struct *work)
@@ -80,9 +64,6 @@ static void proc_cleanup_work(struct work_struct *work)
         pid_ns_release_proc(ns);
 }
 
-/* MAX_PID_NS_LEVEL is needed for limiting size of 'struct pid' */
-#define MAX_PID_NS_LEVEL 32
-
 static struct ucounts *inc_pid_namespaces(struct user_namespace *ns)
 {
         return inc_ucount(ns, current_euid(), UCOUNT_PID_NAMESPACES);
@@ -119,7 +100,7 @@ static struct pid_namespace *create_pid_namespace(struct user_namespace *user_ns
 
         idr_init(&ns->idr);
 
-        ns->pid_cachep = create_pid_cachep(level + 1);
+        ns->pid_cachep = create_pid_cachep(level);
         if (ns->pid_cachep == NULL)
                 goto out_free_idr;