x86/unwind: Create stack frames for saved syscall registers

The entry code doesn't encode the pt_regs pointer for syscalls.  But the
pt_regs are always at the same location, so we can add a manual check
for them.

A later patch prints them as part of the oops stack dump.  They could be
useful, for example, to determine the arguments to a system call.
Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/e176aa9272930cd3f51fda0b94e2eae356677da4.1476973742.git.jpoimboe@redhat.comSigned-off-by: Ingo Molnar <mingo@kernel.org>

arch/x86/kernel/unwind_frame.c

@@ -24,6 +24,14 @@ unsigned long unwind_get_return_address(struct unwind_state *state)
 }
 EXPORT_SYMBOL_GPL(unwind_get_return_address);
 
+static bool is_last_task_frame(struct unwind_state *state)
+{
+	unsigned long bp = (unsigned long)state->bp;
+	unsigned long regs = (unsigned long)task_pt_regs(state->task);
+
+	return bp == regs - FRAME_HEADER_SIZE;
+}
+
 /*
  * This determines if the frame pointer actually contains an encoded pointer to
  * pt_regs on the stack.  See ENCODE_FRAME_POINTER.
@@ -71,6 +79,33 @@ bool unwind_next_frame(struct unwind_state *state)
 	if (state->regs && user_mode(state->regs))
 		goto the_end;
 
+	if (is_last_task_frame(state)) {
+		regs = task_pt_regs(state->task);
+
+		/*
+		 * kthreads (other than the boot CPU's idle thread) have some
+		 * partial regs at the end of their stack which were placed
+		 * there by copy_thread_tls().  But the regs don't have any
+		 * useful information, so we can skip them.
+		 *
+		 * This user_mode() check is slightly broader than a PF_KTHREAD
+		 * check because it also catches the awkward situation where a
+		 * newly forked kthread transitions into a user task by calling
+		 * do_execve(), which eventually clears PF_KTHREAD.
+		 */
+		if (!user_mode(regs))
+			goto the_end;
+
+		/*
+		 * We're almost at the end, but not quite: there's still the
+		 * syscall regs frame.  Entry code doesn't encode the regs
+		 * pointer for syscalls, so we have to set it manually.
+		 */
+		state->regs = regs;
+		state->bp = NULL;
+		return true;
+	}
+
 	/* get the next frame pointer */
 	if (state->regs)
 		next_bp = (unsigned long *)state->regs->bp;