PowerPC64 ELFv2 ABI 4/6: Stack frame layout changes

This updates glibc for the changes in the ELFv2 relating to the
stack frame layout.  These are described in more detail here:
http://gcc.gnu.org/ml/gcc-patches/2013-11/msg01149.html
http://gcc.gnu.org/ml/gcc-patches/2013-11/msg01146.html

Specifically, the "compiler and linker doublewords" were removed,
which has the effect that the save slot for the TOC register is
now at offset 24 rather than 40 to the stack pointer.

In addition, a function may now no longer necessarily assume that
its caller has set up a 64-byte register save area its use.

To address the first change, the patch goes through all assembler
files and replaces immediate offsets in instructions accessing the
ABI-defined stack slots by symbolic offsets.  Those already were
defined in ucontext_i.sym and used in some of the context routines,
but that doesn't really seem like the right place for those defines.

The patch instead defines those symbolic offsets in sysdeps.h,
in two variants for the old and new ABI, and uses them systematically
in all assembler files, not just the context routines.

The second change only affected a few assembler files that used
the save area to temporarily store some registers.  In those
cases where this happens within a leaf function, this patch
changes the code to store those registers to the "red zone"
below the stack pointer.  Otherwise, the functions already allocate
a stack frame, and the patch changes them to add extra space in
these frames as temporary space for the ELFv2 ABI.

1 files changed, 25 insertions, 23 deletions

diff --git a/sysdeps/powerpc/powerpc64/dl-trampoline.S b/sysdeps/powerpc/powerpc64/dl-trampoline.S
index e31311cf18..18c8a3aa01 100644
--- a/sysdeps/powerpc/powerpc64/dl-trampoline.S
+++ b/sysdeps/powerpc/powerpc64/dl-trampoline.S
@@ -26,13 +26,13 @@
    parm1 (r3) and the index (r0) need to be converted to an offset
    (index * 24) in parm2 (r4).  */
 
-#define FRAME_SIZE 176
+#define FRAME_SIZE (FRAME_MIN_SIZE+64)
 /* We need to save the registers used to pass parameters, ie. r3 thru
    r10;  Use local var space rather than the parameter save area,
    because gcc as of 2010/05 doesn't allocate a proper stack frame for
    a function that makes no calls except for __tls_get_addr and we
    might be here resolving the __tls_get_addr call.  */
-#define INT_PARMS 112
+#define INT_PARMS FRAME_MIN_SIZE
 EALIGN(_dl_runtime_resolve, 4, 0)
 	stdu	r1,-FRAME_SIZE(r1)
 	cfi_adjust_cfa_offset (FRAME_SIZE)
@@ -48,25 +48,25 @@ EALIGN(_dl_runtime_resolve, 4, 0)
 	mflr	r0
 	std	r8,INT_PARMS+40(r1)
 /* Store the LR in the LR Save area.  */
-	std	r0,FRAME_SIZE+16(r1)
-	cfi_offset (lr, 16)
+	std	r0,FRAME_SIZE+FRAME_LR_SAVE(r1)
+	cfi_offset (lr, FRAME_LR_SAVE)
 	mfcr	r0
 	std	r9,INT_PARMS+48(r1)
 	std	r10,INT_PARMS+56(r1)
 /* I'm almost certain we don't have to save cr...  be safe.  */
-	std	r0,FRAME_SIZE+8(r1)
+	std	r0,FRAME_SIZE+FRAME_CR_SAVE(r1)
 	bl	JUMPTARGET(_dl_fixup)
 #ifndef SHARED
 	nop
 #endif
 /* Put the registers back.  */
-	ld	r0,FRAME_SIZE+16(r1)
+	ld	r0,FRAME_SIZE+FRAME_LR_SAVE(r1)
 	ld	r10,INT_PARMS+56(r1)
 	ld	r9,INT_PARMS+48(r1)
 	ld	r8,INT_PARMS+40(r1)
 	ld	r7,INT_PARMS+32(r1)
 	mtlr	r0
-	ld	r0,FRAME_SIZE+8(r1)
+	ld	r0,FRAME_SIZE+FRAME_CR_SAVE(r1)
 	ld	r6,INT_PARMS+24(r1)
 	ld	r5,INT_PARMS+16(r1)
 	ld	r4,INT_PARMS+8(r1)
@@ -76,7 +76,7 @@ EALIGN(_dl_runtime_resolve, 4, 0)
 	ld	r3,INT_PARMS+0(r1)
 #if _CALL_ELF == 2
 /* Restore the caller's TOC in case we jump to a local entry point.  */
-	ld	r2,FRAME_SIZE+40(r1)
+	ld	r2,FRAME_SIZE+FRAME_TOC_SAVE(r1)
 #endif
 /* Unwind the stack frame, and jump.  */
 	addi	r1,r1,FRAME_SIZE
@@ -86,6 +86,7 @@ END(_dl_runtime_resolve)
 #undef INT_PARMS
 
 	/* Stack layout:
+	   (Note: some of these are not required for the ELFv2 ABI.)
 	  +592   previous backchain
 	  +584   spill_r31
 	  +576   spill_r30
@@ -147,10 +148,11 @@ END(_dl_runtime_resolve)
 	  +64    parm3
 	  +56    parm2
 	  +48    parm1
-	 * Parameter save area, Allocated by the call, at least 8 double words
-	  +40    TOC save area
-	  +32    Reserved for linker
-	  +24    Reserved for compiler
+	 * Parameter save area
+	 * (v1 ABI: Allocated by the call, at least 8 double words)
+	  +40    v1 ABI: TOC save area
+	  +32    v1 ABI: Reserved for linker
+	  +24    v1 ABI: Reserved for compiler / v2 ABI: TOC save area
 	  +16    LR save area
 	  +8     CR save area
 	r1+0     stack back chain
@@ -206,15 +208,15 @@ EALIGN(_dl_profile_resolve, 4, 0)
 /* Store the LR in the LR Save area of the previous frame.  */
 /* XXX Do we have to do this?  */
 	la	r8,FRAME_SIZE(r1)
-	std	r5,FRAME_SIZE+16(r1)
-	cfi_offset (lr, 16)
+	std	r5,FRAME_SIZE+FRAME_LR_SAVE(r1)
+	cfi_offset (lr, FRAME_LR_SAVE)
 	std	r5,CALLING_LR(r1)
 	mfcr	r0
 	std	r9,INT_PARMS+48(r1)
 	std	r10,INT_PARMS+56(r1)
 	std	r8,CALLING_SP(r1)
 /* I'm almost certain we don't have to save cr...  be safe.  */
-	std	r0,FRAME_SIZE+8(r1)
+	std	r0,FRAME_SIZE+FRAME_CR_SAVE(r1)
 	ld	r12,.LC__dl_hwcap@toc(r2)
 #ifdef SHARED
 	/* Load _rtld_local_ro._dl_hwcap.  */
@@ -311,13 +313,13 @@ L(saveFP):
 	lvx	v12,r11,r10
 	lvx	v13,r11,r9
 L(restoreFXR):
-	ld	r0,FRAME_SIZE+16(r1)
+	ld	r0,FRAME_SIZE+FRAME_LR_SAVE(r1)
 	ld	r10,INT_PARMS+56(r1)
 	ld	r9,INT_PARMS+48(r1)
 	ld	r8,INT_PARMS+40(r1)
 	ld	r7,INT_PARMS+32(r1)
 	mtlr	r0
-	ld	r0,FRAME_SIZE+8(r1)
+	ld	r0,FRAME_SIZE+FRAME_CR_SAVE(r1)
 	ld	r6,INT_PARMS+24(r1)
 	ld	r5,INT_PARMS+16(r1)
 	ld	r4,INT_PARMS+8(r1)
@@ -327,7 +329,7 @@ L(restoreFXR):
 	ld	r3,INT_PARMS+0(r1)
 #if _CALL_ELF == 2
 /* Restore the caller's TOC in case we jump to a local entry point.  */
-	ld	r2,FRAME_SIZE+40(r1)
+	ld	r2,FRAME_SIZE+FRAME_TOC_SAVE(r1)
 #endif
 /* Load the floating point registers.  */
 	lfd	fp1,FPR_PARMS+0(r1)
@@ -375,19 +377,19 @@ L(do_pltexit):
 	lvx	v12,r11,r10
 	lvx	v13,r11,r9
 L(restoreFXR2):
-	ld	r0,FRAME_SIZE+16(r1)
+	ld	r0,FRAME_SIZE+FRAME_LR_SAVE(r1)
 	ld	r10,INT_PARMS+56(r1)
 	ld	r9,INT_PARMS+48(r1)
 	ld	r8,INT_PARMS+40(r1)
 	ld	r7,INT_PARMS+32(r1)
 	mtlr	r0
-	ld	r0,FRAME_SIZE+8(r1)
+	ld	r0,FRAME_SIZE+FRAME_CR_SAVE(r1)
 	ld	r6,INT_PARMS+24(r1)
 	ld	r5,INT_PARMS+16(r1)
 	ld	r4,INT_PARMS+8(r1)
 	mtcrf	0xFF,r0
 /* Prepare for calling the function returned by fixup.  */
-	std	r2,40(r1)
+	std	r2,FRAME_TOC_SAVE(r1)
 	PPC64_LOAD_FUNCPTR r3
 	ld	r3,INT_PARMS+0(r1)
 /* Load the floating point registers.  */
@@ -406,7 +408,7 @@ L(restoreFXR2):
 	lfd	fp13,FPR_PARMS+96(r1)
 /* Call the target function.  */
 	bctrl
-	ld	r2,40(r1)
+	ld	r2,FRAME_TOC_SAVE(r1)
 	lwz	r12,VR_VRSAVE(r1)
 /* But return here and store the return values.  */
 	std	r3,INT_RTN(r1)
@@ -441,7 +443,7 @@ L(callpltexit):
 	beq	L(pltexitreturn)
 	lvx	v2,0,r10
 L(pltexitreturn):
-	ld	r0,FRAME_SIZE+16(r1)
+	ld	r0,FRAME_SIZE+FRAME_LR_SAVE(r1)
 	ld	r31,584(r1)
 	ld	r30,576(r1)
 	mtlr	r0