* sysdeps/powerpc/bits/link.h (La_ppc64_regs): Add lr_vrsave.

	(La_ppc64_retval): Correct size of lrc_fp.
	* sysdeps/powerpc/powerpc64/dl-trampoline.S (_dl_profile_resolve):
	Fix up ABI problems and complete function.

3 files changed, 351 insertions, 104 deletions

diff --git a/ChangeLog b/ChangeLog
index 683c403199..c2f12b6085 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,3 +1,10 @@
+2005-02-07  Steven Munroe  <sjmunroe@us.ibm.com>
+
+	* sysdeps/powerpc/bits/link.h (La_ppc64_regs): Add lr_vrsave.
+	(La_ppc64_retval): Correct size of lrc_fp.
+	* sysdeps/powerpc/powerpc64/dl-trampoline.S (_dl_profile_resolve):
+	Fix up ABI problems and complete function.
+
 2005-03-10  Jakub Jelinek  <jakub@redhat.com>
 
 	* math/test-misc.c (main): Add some more tests.
diff --git a/sysdeps/powerpc/bits/link.h b/sysdeps/powerpc/bits/link.h
index f8e6734fe0..6c6f6042a1 100644
--- a/sysdeps/powerpc/bits/link.h
+++ b/sysdeps/powerpc/bits/link.h
@@ -71,7 +71,8 @@ typedef struct La_ppc64_regs
 {
   uint64_t lr_reg[8];
   double lr_fp[13];
-  uint64_t __padding;
+  uint32_t __padding;
+  uint32_t lr_vrsave;
   uint32_t lr_vreg[12][4];
   uint64_t lr_r1;
   uint64_t lr_lr;
@@ -82,8 +83,8 @@ typedef struct La_ppc64_retval
 {
   uint64_t lrv_r3;
   uint64_t lrv_r4;
-  double lrv_fp[8];
-  uint32_t lrv_v2[4];
+  double lrv_fp[4];	/* f1-f4, float - complex long double.  */
+  uint32_t lrv_v2[4];	/* v2.  */ 
 } La_ppc64_retval;
 
 
diff --git a/sysdeps/powerpc/powerpc64/dl-trampoline.S b/sysdeps/powerpc/powerpc64/dl-trampoline.S
index 316f17a405..0c617063c9 100644
--- a/sysdeps/powerpc/powerpc64/dl-trampoline.S
+++ b/sysdeps/powerpc/powerpc64/dl-trampoline.S
@@ -18,9 +18,15 @@
    02111-1307 USA.  */
 
 #include <sysdep.h>
+#include <rtld-global-offsets.h>
 
-	.section ".text"
 
+	.section ".text"
+/* On entry r0 contains the index of the PLT entry we need to fixup
+   and r11 contains the link_map (from PLT0+16).  The link_map becomes
+   parm1 (r3) and the index (r0) need to be converted to an offset
+   (index * 24) in parm2 (r4).  */
+   
 EALIGN(_dl_runtime_resolve, 4, 0)
 /* We need to save the registers used to pass parameters, ie. r3 thru
    r10; the registers are saved in a stack frame.  */
@@ -68,129 +74,362 @@ EALIGN(_dl_runtime_resolve, 4, 0)
 	bctr
 END(_dl_runtime_resolve)
 
+	/* Stack layout:
+	  +592   previous backchain
+	  +584   spill_r31
+	  +576   spill_r30
+	  +560   v1
+	  +552   fp4
+	  +544   fp3
+	  +536   fp2
+	  +528   fp1
+	  +520   r4
+	  +512   r3
+	   return values
+          +504   free
+	  +496   stackframe
+	  +488   lr
+	  +480   r1
+	  +464   v13
+	  +448   v12
+	  +432   v11
+	  +416   v10
+	  +400   v9
+	  +384   v8
+	  +368   v7
+	  +352   v6
+	  +336   v5
+	  +320   v4
+	  +304   v3
+	  +288   v2
+	 * VMX Parms in V2-V13, V0-V1 are scratch
+	  +284   vrsave
+	  +280   free
+	  +272   fp13
+	  +264   fp12
+	  +256   fp11
+	  +248   fp10
+	  +240   fp9
+	  +232   fp8
+	  +224   fp7
+	  +216   fp6
+	  +208   fp5
+	  +200   fp4
+	  +192   fp3
+	  +184   fp2
+	  +176   fp1
+	 * FP Parms in FP1-FP13, FP0 is a scratch register
+	  +168   r10
+	  +160   r9
+	  +152   r8
+	  +144   r7
+	  +136   r6
+	  +128   r5
+	  +120   r4
+	  +112   r3
+	 * Integer parms in R3-R10, R0 is scratch, R1 SP, R2 is TOC
+	  +104   parm8
+	  +96    parm7
+	  +88    parm6
+	  +80    parm5
+	  +72    parm4
+	  +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 
+	  +16    LR save area 
+	  +8     CR save area
+	r1+0     stack back chain
+	*/
+#define FRAME_SIZE 592
+#define INT_RTN 512
+#define FPR_RTN 528
+#define VR_RTN 560
+#define STACK_FRAME 496
+#define CALLING_LR 488
+#define CALLING_SP 480
+#define INT_PARMS 112
+#define FPR_PARMS 176
+#define VR_PARMS 288
+#define VR_VRSAVE 284
+	.section	".toc","aw"
+.LC__dl_hwcap:
+# ifdef SHARED
+	.tc _rtld_global_ro[TC],_rtld_global_ro
+# else
+	.tc _dl_hwcap[TC],_dl_hwcap
+# endif
+	.section ".text"
 
-
+	.machine	"altivec"
+/* On entry r0 contains the index of the PLT entry we need to fixup
+   and r11 contains the link_map (from PLT0+16).  The link_map becomes
+   parm1 (r3) and the index (r0) needs to be converted to an offset
+   (index * 24) in parm2 (r4).  */
+   
 EALIGN(_dl_profile_resolve, 4, 0)
+/* Spill r30, r31 to preserve the link_map* and reloc_addr, in case we
+   need to call _dl_call_pltexit.  */
+	std	r31,-8(r1)
+	std	r30,-16(r1)
 /* We need to save the registers used to pass parameters, ie. r3 thru
    r10; the registers are saved in a stack frame.  */
-	stdu	r1,-448(r1)
-	/* Stack layout:
-
-	  +432   stackframe
-	  +424   lr
-	  +416   r1
-	  +400   v12
-	  +384   v11
-	  +368   v10
-	  +362   v9
-	  +336   v8
-	  +320   v7
-	  +304   v6
-	  +288   v5
-	  +272   v4
-	  +256   v3
-	  +240   v2
-	  +224   v1
-	  +216   free
-	  +208   fp13
-	  +200   fp12
-	  +192   fp11
-	  +184   fp10
-	  +176   fp9
-	  +168   fp8
-	  +160   fp7
-	  +152   fp6
-	  +144   fp5
-	  +136   fp4
-	  +128   fp3
-	  +120   fp2
-	  +112   fp1
-	  +104   r10
-	  +96    r9
-	  +88    r8
-	  +80    r7
-	  +72    r6
-	  +64    r5
-	  +56    r4
-	  +48    r3
-	  +8     cr
-	   r1    link
-	*/
-	std	r3,48(r1)
+	stdu	r1,-FRAME_SIZE(r1)
+	std	r3,INT_PARMS+0(r1)
 	mr	r3,r11
-	std	r4,56(r1)
-	sldi	r4,r0,1
-	std	r5,64(r1)
-	add	r4,r4,0
-	std	r6,72(r1)
-	sldi	r4,r4,3
-	std	r7,80(r1)
+	std	r4,INT_PARMS+8(r1)
+	sldi	r4,r0,1		/* index * 2 */
+	std	r5,INT_PARMS+16(r1)
+	add	r4,r4,r0	/* index * 3 */
+	std	r6,INT_PARMS+24(r1)
+	sldi	r4,r4,3		/* index * 24  == PLT offset */
 	mflr	r5
-	std	r8,88(r1)
+	std	r7,INT_PARMS+32(r1)
+	std	r8,INT_PARMS+40(r1)
 /* Store the LR in the LR Save area of the previous frame.  */
 /* XXX Do we have to do this?  */
-	std	r5,448+16(r1)
-	std	r5,424(r1)
+	la	r8,FRAME_SIZE(r1)
+	std	r5,FRAME_SIZE+16(r1)
+	std	r5,CALLING_LR(r1)
 	mfcr	r0
-	std	r9,96(r1)
-	std	r10,104(r1)
+	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	r0,8(r1)
+	ld	r12,.LC__dl_hwcap@toc(r2)
+#ifdef SHARED
+	/* Load _rtld-global._dl_hwcap.  */
+	ld	r12,RTLD_GLOBAL_RO_DL_HWCAP_OFFSET(r12)
+#else
+	ld	r12,0(r12) /* Load extern _dl_hwcap.  */
+#endif
+	andis.  r0,r12,(PPC_FEATURE_HAS_ALTIVEC >> 16)
+	beq	L(saveFP)
+	la	r10,(VR_PARMS+0)(r1)
+	la	r9,(VR_PARMS+16)(r1)
+	li	r11,32
+	li	r12,64
+	stvx	v2,0,r10
+	stvx	v3,0,r9
+	
+	stvx	v4,r11,r10
+	stvx	v5,r11,r9
+	addi	r11,r11,64
+	
+	stvx	v6,r12,r10
+	stvx	v7,r12,r9
+	addi	r12,r12,64
+	
+	stvx	v8,r11,r10
+	stvx	v9,r11,r9
+	addi	r11,r11,64
+	
+	stvx	v10,r12,r10
+	stvx	v11,r12,r9
+	mfspr	r0,VRSAVE
+	
+	stvx	v12,r11,r10
+	stvx	v13,r11,r9
+L(saveFP):
+	stw	r0,VR_VRSAVE(r1)
 /* Save floating registers.  */
-	stfd	fp1,112(r1)
-	stfd	fp2,120(r1)
-	stfd	fp3,128(r1)
-	stfd	fp4,136(r1)
-	stfd	fp5,144(r1)
-	stfd	fp6,152(r1)
-	stfd	fp7,160(r1)
-	stfd	fp8,168(r1)
-	stfd	fp9,176(r1)
-	stfd	fp10,184(r1)
-	stfd	fp11,192(r1)
-	stfd	fp12,200(r1)
-	stfd	fp13,208(r1)
-/* XXX TODO: store vmx registers.  */
-/* Load the extra parameters.  */
-	addi	r6,r1,48
-	addi	r7,r1,432
+	stfd	fp1,FPR_PARMS+0(r1)
+	stfd	fp2,FPR_PARMS+8(r1)
+	stfd	fp3,FPR_PARMS+16(r1)
+	stfd	fp4,FPR_PARMS+24(r1)
+	stfd	fp5,FPR_PARMS+32(r1)
+	stfd	fp6,FPR_PARMS+40(r1)
+	stfd	fp7,FPR_PARMS+48(r1)
+	stfd	fp8,FPR_PARMS+56(r1)
+	stfd	fp9,FPR_PARMS+64(r1)
+	stfd	fp10,FPR_PARMS+72(r1)
+	stfd	fp11,FPR_PARMS+80(r1)
 	li	r0,-1
-	stdu	r0,0(r7)
+	stfd	fp12,FPR_PARMS+88(r1)
+	stfd	fp13,FPR_PARMS+96(r1)
+/* Load the extra parameters.  */
+	addi	r6,r1,INT_PARMS
+	addi	r7,r1,STACK_FRAME
+/* Save  link_map* and reloc_addr parms for later.  */
+	mr	r31,r3
+	mr	r30,r4
+	std	r0,0(r7)
 	bl	JUMPTARGET(_dl_profile_fixup)
-/* Put the registers back.  */
-	ld	r0,448+16(r1)
-	ld	r10,104(r1)
-	ld	r9,96(r1)
-	ld	r8,88(r1)
-	ld	r7,80(r1)
+	nop
+/* Test *framesizep > 0 to see if need to do pltexit processing.  */
+	ld	r0,STACK_FRAME(r1)
+/* Put the registers back.  */	
+	lwz	r12,VR_VRSAVE(r1)
+	cmpdi	cr1,r0,0
+	cmpdi	cr0,r12,0
+	bgt	cr1,L(do_pltexit)
+	la	r10,(VR_PARMS+0)(r1)
+	la	r9,(VR_PARMS+16)(r1)
+/* VRSAVE must be non-zero if VMX is present and VRs are in use. */
+	beq	L(restoreFXR)
+	li	r11,32
+	li	r12,64
+	lvx	v2,0,r10
+	lvx	v3,0,r9
+	
+	lvx	v4,r11,r10
+	lvx	v5,r11,r9
+	addi	r11,r11,64
+	
+	lvx	v6,r12,r10
+	lvx	v7,r12,r9
+	addi	r12,r12,64
+	
+	lvx	v8,r11,r10
+	lvx	v9,r11,r9
+	addi	r11,r11,64
+	
+	lvx	v10,r12,r10
+	lvx	v11,r12,r9
+	
+	lvx	v12,r11,r10
+	lvx	v13,r11,r9
+L(restoreFXR):
+	ld	r0,FRAME_SIZE+16(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	r0,8(r1)
-	ld	r6,72(r1)
-	ld	r5,64(r1)
-	ld	r4,56(r1)
+	ld	r6,INT_PARMS+24(r1)
+	ld	r5,INT_PARMS+16(r1)
+	ld	r4,INT_PARMS+8(r1)
 	mtcrf	0xFF,r0
 /* Load the target address, toc and static chain reg from the function
    descriptor returned by fixup.  */
 	ld	r0,0(r3)
 	ld	r2,8(r3)
-	mtctr	r0
 	ld	r11,16(r3)
-	ld	r3,48(r1)
+	ld	r3,INT_PARMS+0(r1)
+	mtctr	r0
 /* Load the floating point registers.  */
-	lfd	fp1,112(r1)
-	lfd	fp2,120(r1)
-	lfd	fp3,128(r1)
-	lfd	fp4,136(r1)
-	lfd	fp5,144(r1)
-	lfd	fp6,152(r1)
-	lfd	fp7,160(r1)
-	lfd	fp8,168(r1)
-	lfd	fp9,176(r1)
-	lfd	fp10,184(r1)
-	lfd	fp11,192(r1)
-	lfd	fp12,200(r1)
-	lfd	fp13,208(r1)
+	lfd	fp1,FPR_PARMS+0(r1)
+	lfd	fp2,FPR_PARMS+8(r1)
+	lfd	fp3,FPR_PARMS+16(r1)
+	lfd	fp4,FPR_PARMS+24(r1)
+	lfd	fp5,FPR_PARMS+32(r1)
+	lfd	fp6,FPR_PARMS+40(r1)
+	lfd	fp7,FPR_PARMS+48(r1)
+	lfd	fp8,FPR_PARMS+56(r1)
+	lfd	fp9,FPR_PARMS+64(r1)
+	lfd	fp10,FPR_PARMS+72(r1)
+	lfd	fp11,FPR_PARMS+80(r1)
+	lfd	fp12,FPR_PARMS+88(r1)
+	lfd	fp13,FPR_PARMS+96(r1)
 /* Unwind the stack frame, and jump.  */
-	addi	r1,r1,448
+	ld	r31,584(r1)
+	ld	r30,576(r1)
+	addi	r1,r1,FRAME_SIZE
 	bctr
+L(do_pltexit):
+	la	r10,(VR_PARMS+0)(r1)
+	la	r9,(VR_PARMS+16)(r1)
+	beq	L(restoreFXR2)
+	li	r11,32
+	li	r12,64
+	lvx	v2,0,r10
+	lvx	v3,0,r9
+	
+	lvx	v4,r11,r10
+	lvx	v5,r11,r9
+	addi	r11,r11,64
+	
+	lvx	v6,r12,r10
+	lvx	v7,r12,r9
+	addi	r12,r12,64
+	
+	lvx	v8,r11,r10
+	lvx	v9,r11,r9
+	addi	r11,r11,64
+	
+	lvx	v10,r12,r10
+	lvx	v11,r12,r9
+	
+	lvx	v12,r11,r10
+	lvx	v13,r11,r9
+L(restoreFXR2):
+	ld	r0,FRAME_SIZE+16(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	r0,8(r1)
+	ld	r6,INT_PARMS+24(r1)
+	ld	r5,INT_PARMS+16(r1)
+	ld	r4,INT_PARMS+8(r1)
+	mtcrf	0xFF,r0
+/* Load the target address, toc and static chain reg from the function
+   descriptor returned by fixup.  */
+	ld	r0,0(r3)
+	std	r2,40(r1)
+	ld	r2,8(r3)
+	ld	r11,16(r3)
+	ld	r3,INT_PARMS+0(r1)
+	mtctr	r0
+/* Load the floating point registers.  */
+	lfd	fp1,FPR_PARMS+0(r1)
+	lfd	fp2,FPR_PARMS+8(r1)
+	lfd	fp3,FPR_PARMS+16(r1)
+	lfd	fp4,FPR_PARMS+24(r1)
+	lfd	fp5,FPR_PARMS+32(r1)
+	lfd	fp6,FPR_PARMS+40(r1)
+	lfd	fp7,FPR_PARMS+48(r1)
+	lfd	fp8,FPR_PARMS+56(r1)
+	lfd	fp9,FPR_PARMS+64(r1)
+	lfd	fp10,FPR_PARMS+72(r1)
+	lfd	fp11,FPR_PARMS+80(r1)
+	lfd	fp12,FPR_PARMS+88(r1)
+	lfd	fp13,FPR_PARMS+96(r1)
+/* Call the target function.  */
+	bctrl
+	ld	r2,40(r1)	
+	lwz	r12,VR_VRSAVE(r1)
+/* But return here and store the return values.  */
+	std	r3,INT_RTN(r1)
+	std	r4,INT_RTN+8(r1)
+	stfd	fp1,FPR_PARMS+0(r1)
+	stfd	fp2,FPR_PARMS+8(r1)
+	cmpdi	cr0,r12,0
+	la	r10,VR_RTN(r1)
+	stfd	fp3,FPR_PARMS+16(r1)
+	stfd	fp4,FPR_PARMS+24(r1)
+	mr	r3,r31
+	mr	r4,r30
+	beq	L(callpltexit)
+	stvx	v2,0,r10
+L(callpltexit):
+	addi	r5,r1,INT_PARMS
+	addi	r6,r1,INT_RTN
+	bl	JUMPTARGET(_dl_call_pltexit)
+	nop
+/* Restore the return values from target function.  */	
+	lwz	r12,VR_VRSAVE(r1)
+	ld	r3,INT_RTN(r1)
+	ld	r4,INT_RTN+8(r1)
+	lfd	fp1,FPR_PARMS+0(r1)
+	lfd	fp2,FPR_PARMS+8(r1)
+	cmpdi	cr0,r12,0
+	la	r10,VR_RTN(r1)
+	lfd	fp3,FPR_PARMS+16(r1)
+	lfd	fp4,FPR_PARMS+24(r1)
+	beq	L(pltexitreturn)
+	lvx	v2,0,r10
+L(pltexitreturn):
+	ld	r0,FRAME_SIZE+16(r1)
+	ld	r31,584(r1)
+	ld	r30,576(r1)
+	mtlr	r0
+	ld	r1,0(r1)
+	blr
 END(_dl_profile_resolve)