kernel/pid.c: convert struct pid count to refcount_t

struct pid's count is an atomic_t field used as a refcount.  Use
refcount_t for it which is basically atomic_t but does additional
checking to prevent use-after-free bugs.

For memory ordering, the only change is with the following:

 -	if ((atomic_read(&pid->count) == 1) ||
 -	     atomic_dec_and_test(&pid->count)) {
 +	if (refcount_dec_and_test(&pid->count)) {
 		kmem_cache_free(ns->pid_cachep, pid);

Here the change is from: Fully ordered --> RELEASE + ACQUIRE (as per
refcount-vs-atomic.rst) This ACQUIRE should take care of making sure the
free happens after the refcount_dec_and_test().

The above hunk also removes atomic_read() since it is not needed for the
code to work and it is unclear how beneficial it is.  The removal lets
refcount_dec_and_test() check for cases where get_pid() happened before
the object was freed.

Link: http://lkml.kernel.org/r/20190701183826.191936-1-joel@joelfernandes.org
Signed-off-by: Joel Fernandes (Google) <joel@joelfernandes.org>
Reviewed-by: Andrea Parri <andrea.parri@amarulasolutions.com>
Reviewed-by: Kees Cook <keescook@chromium.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Elena Reshetova <elena.reshetova@intel.com>
Cc: Jann Horn <jannh@google.com>
Cc: Eric W. Biederman <ebiederm@xmission.com>
Cc: KJ Tsanaktsidis <ktsanaktsidis@zendesk.com>
Cc: Michal Hocko <mhocko@suse.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/include/linux/pid.h b/include/linux/pid.h
index 1484db6ca8d17a960b8dc18e0ae3bb732ea0d216..2a83e434db9d080667bd8f3465552c797e814c10 100644 (file)
--- a/include/linux/pid.h
+++ b/include/linux/pid.h
@@ -4,6 +4,7 @@
 
 #include <linux/rculist.h>
 #include <linux/wait.h>
+#include <linux/refcount.h>
 
 enum pid_type
 {
@@ -57,7 +58,7 @@ struct upid {
 
 struct pid
 {
-       atomic_t count;
+       refcount_t count;
        unsigned int level;
        /* lists of tasks that use this pid */
        struct hlist_head tasks[PIDTYPE_MAX];
@@ -74,7 +75,7 @@ extern const struct file_operations pidfd_fops;
 static inline struct pid *get_pid(struct pid *pid)
 {
        if (pid)
-               atomic_inc(&pid->count);
+               refcount_inc(&pid->count);
        return pid;
 }
 

diff --git a/kernel/pid.c b/kernel/pid.c
index 16263b5265604dd7931d4431920d51b633429050..0a9f2e437217655daf18aaba0e57b30096595371 100644 (file)
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -37,14 +37,14 @@
 #include <linux/init_task.h>
 #include <linux/syscalls.h>
 #include <linux/proc_ns.h>
-#include <linux/proc_fs.h>
+#include <linux/refcount.h>
 #include <linux/anon_inodes.h>
 #include <linux/sched/signal.h>
 #include <linux/sched/task.h>
 #include <linux/idr.h>
 
 struct pid init_struct_pid = {
-       .count          = ATOMIC_INIT(1),
+       .count          = REFCOUNT_INIT(1),
        .tasks          = {
                { .first = NULL },
                { .first = NULL },
@@ -108,8 +108,7 @@ void put_pid(struct pid *pid)
                return;
 
        ns = pid->numbers[pid->level].ns;
-       if ((atomic_read(&pid->count) == 1) ||
-            atomic_dec_and_test(&pid->count)) {
+       if (refcount_dec_and_test(&pid->count)) {
                kmem_cache_free(ns->pid_cachep, pid);
                put_pid_ns(ns);
        }
@@ -212,7 +211,7 @@ struct pid *alloc_pid(struct pid_namespace *ns)
        }
 
        get_pid_ns(ns);
-       atomic_set(&pid->count, 1);
+       refcount_set(&pid->count, 1);
        for (type = 0; type < PIDTYPE_MAX; ++type)
                INIT_HLIST_HEAD(&pid->tasks[type]);