Align the stack in _rtld_bind_start. Normally this is called with the

correct stack alignment, however when we have a leaf function that uses
thread local storage it calls __aeabi_read_tp to get the thread pointer.
Neither GCC or clang see this as a function call so will align the stack
to a 4-byte boundary. This may be a problem as _rtld_bind expects to be
on an 8-byte boundary.

The solution is to store a copy of the stack pointer and force the
alignment before calling _rtld_bind.

This fixes a problem with armeb where applications would crash in odd ways.
It should also remove the need for a local patch to clang to force the
stack alignment to an 8-byte boundary, even for leaf functions. Further
testing will be needed before reverting this local change to clang as we
may rely on it in other places.

Reviewed by:	jmg@

1 files changed, 5 insertions, 2 deletions

diff --git a/libexec/rtld-elf/arm/rtld_start.S b/libexec/rtld-elf/arm/rtld_start.S
index 7a4fae4..c482808 100644
--- a/libexec/rtld-elf/arm/rtld_start.S
+++ b/libexec/rtld-elf/arm/rtld_start.S
@@ -77,7 +77,7 @@ __FBSDID("$FreeBSD$");
  *	lr = &GOT[2]
  */
 _rtld_bind_start:
-	stmdb	sp!,{r0-r4,sl,fp}
+	stmdb	sp!,{r0-r5,sl,fp}
 
 	sub	r1, ip, lr		/* r1 = 4 * (n + 1) */
 	sub	r1, r1, #4		/* r1 = 4 * n */
@@ -86,11 +86,14 @@ _rtld_bind_start:
 	ldr	r0, [lr, #-4]		/* get obj ptr from GOT[1] */
 	mov	r4, ip			/* save GOT location */
 
+	mov	r5, sp			/* Save the stack pointer */
+	bic	sp, sp, #7		/* Align the stack pointer */
 	bl	_rtld_bind		/* Call the binder */
+	mov	sp, r5			/* Restore the old stack pointer */
 
 	str	r0, [r4]		/* save address in GOT */
 	mov	ip, r0			/* save new address */
 
-	ldmia	sp!,{r0-r4,sl,fp,lr}	/* restore the stack */
+	ldmia	sp!,{r0-r5,sl,fp,lr}	/* restore the stack */
 	mov	pc, ip			/* jump to the new address */