ptrace: Prepare to fix racy accesses on task breakpoints

commit bf26c018490c2fce7fe9b629083b96ce0e6ad019 upstream.

When a task is traced and is in a stopped state, the tracer
may execute a ptrace request to examine the tracee state and
get its task struct. Right after, the tracee can be killed
and thus its breakpoints released.
This can happen concurrently when the tracer is in the middle
of reading or modifying these breakpoints, leading to dereferencing
a freed pointer.

Hence, to prepare the fix, create a generic breakpoint reference
holding API. When a reference on the breakpoints of a task is
held, the breakpoints won't be released until the last reference
is dropped. After that, no more ptrace request on the task's
breakpoints can be serviced for the tracer.

Reported-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Prasad <prasad@linux.vnet.ibm.com>
Cc: Paul Mundt <lethal@linux-sh.org>
Link: http://lkml.kernel.org/r/1302284067-7860-2-git-send-email-fweisbec@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h
index 56f2d63a5cbb6b6794959fe1553aa779e79912dd..b0acccac00c95ab8b105cb34c2fede1c69152304 100644 (file)
--- a/include/linux/ptrace.h
+++ b/include/linux/ptrace.h
@@ -168,6 +168,10 @@ static inline void ptrace_init_task(struct task_struct *child, bool ptrace)
                child->ptrace = current->ptrace;
                __ptrace_link(child, current->parent);
        }
+
+#ifdef CONFIG_HAVE_HW_BREAKPOINT
+       atomic_set(&child->ptrace_bp_refcnt, 1);
+#endif
 }
 
 /**
@@ -336,6 +340,13 @@ extern int task_current_syscall(struct task_struct *target, long *callno,
                                unsigned long args[6], unsigned int maxargs,
                                unsigned long *sp, unsigned long *pc);
 
-#endif
+#ifdef CONFIG_HAVE_HW_BREAKPOINT
+extern int ptrace_get_breakpoints(struct task_struct *tsk);
+extern void ptrace_put_breakpoints(struct task_struct *tsk);
+#else
+static inline void ptrace_put_breakpoints(struct task_struct *tsk) { }
+#endif /* CONFIG_HAVE_HW_BREAKPOINT */
+
+#endif /* __KERNEL */
 
 #endif

diff --git a/include/linux/sched.h b/include/linux/sched.h
index db821a408828ab295c493d22c2dd7b86ada1ae6c..f6bac88f0776c2ee188d5dccb8d8332e0135a616 100644 (file)
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1568,6 +1568,9 @@ struct task_struct {
                unsigned long memsw_bytes; /* uncharged mem+swap usage */
        } memcg_batch;
 #endif
+#ifdef CONFIG_HAVE_HW_BREAKPOINT
+       atomic_t ptrace_bp_refcnt;
+#endif
 };
 
 /* Future-safe accessor for struct task_struct's cpus_allowed. */

diff --git a/kernel/exit.c b/kernel/exit.c
index 8856c452e9ace0969d1435fa75fc285cf7cf009c..1e960f4881e8bf02dfe3bb1faaeff593bb347012 100644 (file)
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -1001,7 +1001,7 @@ NORET_TYPE void do_exit(long code)
        /*
         * FIXME: do that only when needed, using sched_exit tracepoint
         */
-       flush_ptrace_hw_breakpoint(tsk);
+       ptrace_put_breakpoints(tsk);
        /*
         * Flush inherited counters to the parent - before the parent
         * gets woken up by child-exit notifications.

diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 05625f6c2293970877157a3044a9f229a7e462d5..0279819f0c2839a5b6483cc66248c70540abfff8 100644 (file)
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -22,6 +22,7 @@
 #include <linux/pid_namespace.h>
 #include <linux/syscalls.h>
 #include <linux/uaccess.h>
+#include <linux/hw_breakpoint.h>
 
 
 /*
@@ -762,3 +763,19 @@ asmlinkage long compat_sys_ptrace(compat_long_t request, compat_long_t pid,
        return ret;
 }
 #endif /* CONFIG_COMPAT */
+
+#ifdef CONFIG_HAVE_HW_BREAKPOINT
+int ptrace_get_breakpoints(struct task_struct *tsk)
+{
+       if (atomic_inc_not_zero(&tsk->ptrace_bp_refcnt))
+               return 0;
+
+       return -1;
+}
+
+void ptrace_put_breakpoints(struct task_struct *tsk)
+{
+       if (atomic_dec_and_test(&tsk->ptrace_bp_refcnt))
+               flush_ptrace_hw_breakpoint(tsk);
+}
+#endif /* CONFIG_HAVE_HW_BREAKPOINT */