task_current_syscall

This adds the new function task_current_syscall() on machines where the
asm/syscall.h interface is supported (CONFIG_HAVE_ARCH_TRACEHOOK).  It's
exported for modules to use in the future.  This function safely samples
the state of a blocked thread to collect what system call it is blocked
in, and the six system call argument registers.

Signed-off-by: Roland McGrath <roland@redhat.com>
Cc: Oleg Nesterov <oleg@tv-sign.ru>
Reviewed-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

3 files changed, 81 insertions, 0 deletions

diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h
index ed69c03692d9..fd31756e1a00 100644
--- a/include/linux/ptrace.h
+++ b/include/linux/ptrace.h
@@ -314,6 +314,10 @@ static inline void user_enable_block_step(struct task_struct *task)
 #define arch_ptrace_stop(code, info)            do { } while (0)
 #endif
 
+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
 
 #endif
diff --git a/lib/Makefile b/lib/Makefile
index 9085ad6fa53d..942c7250f603 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -78,6 +78,8 @@ lib-$(CONFIG_GENERIC_BUG) += bug.o
 
 obj-$(CONFIG_HAVE_LMB) += lmb.o
 
+obj-$(CONFIG_HAVE_ARCH_TRACEHOOK) += syscall.o
+
 hostprogs-y     := gen_crc32table
 clean-files     := crc32table.h
 
diff --git a/lib/syscall.c b/lib/syscall.c
new file mode 100644
index 000000000000..a4f7067f72fa
--- /dev/null
+++ b/lib/syscall.c
@@ -0,0 +1,75 @@
+#include <linux/ptrace.h>
+#include <linux/sched.h>
+#include <linux/module.h>
+#include <asm/syscall.h>
+
+static int collect_syscall(struct task_struct *target, long *callno,
+                           unsigned long args[6], unsigned int maxargs,
+                           unsigned long *sp, unsigned long *pc)
+{
+        struct pt_regs *regs = task_pt_regs(target);
+        if (unlikely(!regs))
+                return -EAGAIN;
+
+        *sp = user_stack_pointer(regs);
+        *pc = instruction_pointer(regs);
+
+        *callno = syscall_get_nr(target, regs);
+        if (*callno != -1L && maxargs > 0)
+                syscall_get_arguments(target, regs, 0, maxargs, args);
+
+        return 0;
+}
+
+/**
+ * task_current_syscall - Discover what a blocked task is doing.
+ * @target:             thread to examine
+ * @callno:             filled with system call number or -1
+ * @args:               filled with @maxargs system call arguments
+ * @maxargs:            number of elements in @args to fill
+ * @sp:                 filled with user stack pointer
+ * @pc:                 filled with user PC
+ *
+ * If @target is blocked in a system call, returns zero with *@callno
+ * set to the the call's number and @args filled in with its arguments.
+ * Registers not used for system call arguments may not be available and
+ * it is not kosher to use &struct user_regset calls while the system
+ * call is still in progress.  Note we may get this result if @target
+ * has finished its system call but not yet returned to user mode, such
+ * as when it's stopped for signal handling or syscall exit tracing.
+ *
+ * If @target is blocked in the kernel during a fault or exception,
+ * returns zero with *@callno set to -1 and does not fill in @args.
+ * If so, it's now safe to examine @target using &struct user_regset
+ * get() calls as long as we're sure @target won't return to user mode.
+ *
+ * Returns -%EAGAIN if @target does not remain blocked.
+ *
+ * Returns -%EINVAL if @maxargs is too large (maximum is six).
+ */
+int task_current_syscall(struct task_struct *target, long *callno,
+                         unsigned long args[6], unsigned int maxargs,
+                         unsigned long *sp, unsigned long *pc)
+{
+        long state;
+        unsigned long ncsw;
+
+        if (unlikely(maxargs > 6))
+                return -EINVAL;
+
+        if (target == current)
+                return collect_syscall(target, callno, args, maxargs, sp, pc);
+
+        state = target->state;
+        if (unlikely(!state))
+                return -EAGAIN;
+
+        ncsw = wait_task_inactive(target, state);
+        if (unlikely(!ncsw) ||
+            unlikely(collect_syscall(target, callno, args, maxargs, sp, pc)) ||
+            unlikely(wait_task_inactive(target, state) != ncsw))
+                return -EAGAIN;
+
+        return 0;
+}
+EXPORT_SYMBOL_GPL(task_current_syscall);