On 1 Dec 2011, at 23:28, Iain Sandoe wrote:
now I'm slightly confused - do we need to preserve if across the
call or not?
erm. not well phrased.
I am trying to get a grasp on what determines the set of registers
that should be saved.
Initially, I was thinking that it was the "call-saved" set - which,
in the Darwin ABI is silent about the FPSCR (consistent with
Joseph's remark - although I note that the ABI doc, in most cases,
states YES/NO for each register).
Now I'm wondering if the saved set needs to include most/all of the
set that are saved for exceptions?
Notwithstanding the questions above, (which still stand) - attached is
a first stab at the Darwin version.
David: I steered clear of using R2 - so it might have some bits useful
for Aix too.
Richard: things that I did, intentionally, differently (and I'm not
sure are correct).
1. I saved the CR
2. Once the vrs are saved, I update the VRsave mask to reflect that.
I used the config machinery - because the sjlj.S code ended up looking
more different than similar.
two failures to track down .... but maybe the answers to the questions
above will produce a reason ;-)
cheers
Iain
=--------=
Native configuration is powerpc-apple-darwin9
=== libitm tests ===
Schedule of variations:
unix/-m32
unix/-m64
Running target unix/-m32
Using /usr/local/dejagnu-1-4-4/share/dejagnu/baseboards/unix.exp as
board description file for target.
Using /usr/local/dejagnu-1-4-4/share/dejagnu/config/unix.exp as
generic interface file for target.
Using /GCC/gcc-live-trunk/libitm/testsuite/config/default.exp as tool-
and-target-specific interface file.
Running /GCC/gcc-live-trunk/libitm/testsuite/libitm.c/c.exp ...
FAIL: libitm.c/cancel.c execution test
FAIL: libitm.c/simple-2.c execution test
Running /GCC/gcc-live-trunk/libitm/testsuite/libitm.c++/c++.exp ...
WARNING: libitm.c++/static_ctor.C compilation failed to produce
executable
=== libitm Summary for unix/-m32 ===
# of expected passes 21
# of unexpected failures 2
# of expected failures 5
Running target unix/-m64
Using /usr/local/dejagnu-1-4-4/share/dejagnu/baseboards/unix.exp as
board description file for target.
Using /usr/local/dejagnu-1-4-4/share/dejagnu/config/unix.exp as
generic interface file for target.
Using /GCC/gcc-live-trunk/libitm/testsuite/config/default.exp as tool-
and-target-specific interface file.
Running /GCC/gcc-live-trunk/libitm/testsuite/libitm.c/c.exp ...
FAIL: libitm.c/cancel.c execution test
FAIL: libitm.c/simple-2.c execution test
Running /GCC/gcc-live-trunk/libitm/testsuite/libitm.c++/c++.exp ...
WARNING: libitm.c++/static_ctor.C compilation failed to produce
executable
=== libitm Summary for unix/-m64 ===
# of expected passes 21
# of unexpected failures 2
# of expected failures 5
=== libitm Summary ===
# of expected passes 42
# of unexpected failures 4
# of expected failures 10
==--===
Index: libitm/config/darwin/powerpc/sjlj.S
===================================================================
--- libitm/config/darwin/powerpc/sjlj.S (revision 0)
+++ libitm/config/darwin/powerpc/sjlj.S (revision 0)
@@ -0,0 +1,335 @@
+/* Copyright (C) 2011 Free Software Foundation, Inc.
+ Contributed by Iain Sandoe <ia...@gcc.gnu.org>.
+
+ This file is part of the GNU Transactional Memory Library (libitm).
+
+ Libitm is free software; you can redistribute it and/or modify it
+ under the terms of the GNU General Public License as published by
+ the Free Software Foundation; either version 3 of the License, or
+ (at your option) any later version.
+
+ Libitm is distributed in the hope that it will be useful, but WITHOUT ANY
+ WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS
+ FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ more details.
+
+ Under Section 7 of GPL version 3, you are granted additional
+ permissions described in the GCC Runtime Library Exception, version
+ 3.1, as published by the Free Software Foundation.
+
+ You should have received a copy of the GNU General Public License and
+ a copy of the GCC Runtime Library Exception along with this program;
+ see the files COPYING3 and COPYING.RUNTIME respectively. If not, see
+ <http://www.gnu.org/licenses/>. */
+
+
+#if defined(__ppc64__)
+#define MODE_CHOICE(x, y) y
+#else
+#define MODE_CHOICE(x, y) x
+#endif
+
+#define MACHINE MODE_CHOICE(ppc7400,ppc64)
+#define g_long MODE_CHOICE(long, quad) /* usage is ".g_long" */
+#define GPR_BYTES MODE_CHOICE(4,8) /* size of a GPR in bytes */
+#define LOG2_GPR_BYTES MODE_CHOICE(2,3) /* log2(GPR_BYTES) */
+
+#define cmpg MODE_CHOICE(cmpw, cmpd)
+#define lg MODE_CHOICE(lwz, ld)
+#define stg MODE_CHOICE(stw, std)
+#define lgx MODE_CHOICE(lwzx, ldx)
+#define stgx MODE_CHOICE(stwx, stdx)
+#define lgu MODE_CHOICE(lwzu, ldu)
+#define stgu MODE_CHOICE(stwu, stdu)
+#define lgux MODE_CHOICE(lwzux, ldux)
+#define stgux MODE_CHOICE(stwux, stdux)
+#define lgwa MODE_CHOICE(lwz, lwa)
+
+/* Stack frame constants. */
+#define SAVED_LR_OFFSET MODE_CHOICE(8,16)
+#define SAVED_CR_OFFSET MODE_CHOICE(4,8)
+#define RED_ZONE_SIZE MODE_CHOICE(224,288)
+#define LINKAGE_SIZE MODE_CHOICE(24,48)
+#define GPR_COUNT MODE_CHOICE(19,18)
+
+/* For Darwin we will assume that Altivec is present. If the code should be
+ ported to support G3, then the vecSave/Restore sections should be
+ conditionalized on __cpu_has_altivec from the system framework (as is done
in
+ save_world () from libgcc). */
+
+# define VECS_SIZ 12*16
+
+#ifdef __ppc64__
+# define VRSAVE_SIZ 4
+# define FPSCRPAD 4
+#else
+/* Included in red zone. */
+# define VRSAVE_SIZ 0
+# define FPSCRPAD 8
+#endif
+
+#define FPSCR 8
+
+#define VECSCR (VECS_SIZ + VRSAVE_SIZ + FPSCRPAD + FPSCR)
+
+/* The red zone is enough to accommodate all the call-saved regs other than
+ the Vecs. LINKAGE_SIZE is the space reserved for the start of the next
+ frame. */
+
+#define FRAME_SIZE (((LINKAGE_SIZE + RED_ZONE_SIZE + VECSCR + 15) / 16) * 16)
+
+/* From the start of the gtm_jmpbuf. */
+#define VRSAVE_OFF (VECS_SIZ + FPSCR + FPSCRPAD)
+#define FPSCRS_OFF VECS_SIZ
+#define GPRS_OFF (VRSAVE_OFF + 4)
+#define FPRS_OFF (GPRS_OFF + GPR_COUNT * GPR_BYTES)
+#define PREV_OFF (FPRS_OFF + 8 * 18)
+
+ .text
+
+ .machine MACHINE
+
+ .align 4
+
+ /* _ITM_beginTransaction(uint32_t, ...) */
+
+ .globl __ITM_beginTransaction
+__ITM_beginTransaction:
+
+ mflr r0
+ stg r0,SAVED_LR_OFFSET(r1) /* Stash return addr. */
+
+ mfcr r4
+ stw r4,SAVED_CR_OFFSET(r1) /* stash CR */
+
+ /* ??? Determine when FPRs not present. */
+ /* ??? Test r3 for pr_hasNoFloatUpdate and skip the fp save.
+ This is not yet set by the compiler. */
+
+ stfd f14,-144(r1)
+ stfd f15,-136(r1)
+ stfd f16,-128(r1)
+ stfd f17,-120(r1)
+ stfd f18,-112(r1)
+ stfd f19,-104(r1)
+ stfd f20,-96(r1)
+ stfd f21,-88(r1)
+ stfd f22,-80(r1)
+ stfd f23,-72(r1)
+ stfd f24,-64(r1)
+ stfd f25,-56(r1)
+ stfd f26,-48(r1)
+ stfd f27,-40(r1)
+ stfd f28,-32(r1)
+ stfd f29,-24(r1)
+ stfd f30,-16(r1)
+ mffs f0
+ stfd f31,-8(r1)
+
+#ifndef __ppc64__
+ /* This might not be the best approach - stmw could be slower than the
+ one-by-one store.
+
+ | gpr13
+ ======= -220 (r1)
+ | 4 bytes of VRSave
+ ======= -224 (r1)
+ | 8 bytes pad.
+ ======= -232 (r1)
+ | 8 bytes of FPSCR
+ ======= -240 (r1) (16 byte boundary)
+ | vecs...
+ */
+ stmw r13,-220(r1)
+
+ addi r4,r1,-240 /* set r4 pointing at the fpscr save */
+
+#else
+
+ /* | gpr14
+ ======= -288 (r1)
+ */
+
+ stg r14,(-304 + 2 * GPR_BYTES)(r1)
+ stg r15,(-304 + 3 * GPR_BYTES)(r1)
+ stg r16,(-304 + 4 * GPR_BYTES)(r1)
+ stg r17,(-304 + 5 * GPR_BYTES)(r1)
+ stg r18,(-304 + 6 * GPR_BYTES)(r1)
+ stg r19,(-304 + 7 * GPR_BYTES)(r1)
+ stg r20,(-304 + 8 * GPR_BYTES)(r1)
+ stg r21,(-304 + 9 * GPR_BYTES)(r1)
+ stg r22,(-304 + 10 * GPR_BYTES)(r1)
+ stg r23,(-304 + 11 * GPR_BYTES)(r1)
+ stg r24,(-304 + 12 * GPR_BYTES)(r1)
+ stg r25,(-304 + 13 * GPR_BYTES)(r1)
+ stg r26,(-304 + 14 * GPR_BYTES)(r1)
+ stg r27,(-304 + 15 * GPR_BYTES)(r1)
+ stg r28,(-304 + 16 * GPR_BYTES)(r1)
+ stg r29,(-304 + 17 * GPR_BYTES)(r1)
+ stg r30,(-304 + 18 * GPR_BYTES)(r1)
+ stg r31,(-304 + 19 * GPR_BYTES)(r1)
+
+ /* ===
+ | 4 bytes of VRSave | 4 of padding
+ ======= -296 (r1)
+ | 8 bytes fpscr.
+ ======= -304 (r1) (16 byte boundry).
+ | vecs...
+ */
+
+ addi r4,r1,-304 /* set r4 pointing at the fpscr save */
+#endif
+
+ stgu r1,-FRAME_SIZE(r1) /* allocate stack frame */
+
+ /* ??? Determine when VRs not present. */
+ /* ??? Test r3 for pr_hasNoVectorUpdate and skip the vr save.
+ This is not yet set by the compiler. */
+
+ mfspr r0,VRsave
+ addi r5,r4,-16 /* Now r5 points at V31 save. */
+#ifndef __ppc64__
+ stw r0,16(r4) /* VRsave lives at -224(R1) */
+#else
+ stw r0,12(r4) /* VRsave lives at -292(R1) */
+#endif
+ stfd f0,0(r4) /* save FPSCR. */
+
+ addi r4,r4,-32
+ stvx v31,0,r5
+ addi r5,r5,-32
+ stvx v30,0,r4
+ addi r4,r4,-32
+ stvx v29,0,r5
+ addi r5,r5,-32
+ stvx v28,0,r4
+ addi r4,r4,-32
+ stvx v27,0,r5
+ addi r5,r5,-32
+ stvx v26,0,r4
+ addi r4,r4,-32
+ stvx v25,0,r5
+ addi r5,r5,-32
+ stvx v24,0,r4
+ addi r4,r4,-32
+ stvx v23,0,r5
+ addi r5,r5,-32
+ stvx v22,0,r4
+ addi r4,r4,-32
+ stvx v21,0,r5
+ ori r0,r0,0x0fff /* we just saved these. */
+ stvx v20,0,r4
+ mtspr VRsave,r0
+
+ /* Point r4 at our saved data "gtm_jmpbuf *". */
+ addi r4, r1, LINKAGE_SIZE
+
+ bl _GTM_begin_transaction
+ nop
+
+ lg r0,(SAVED_LR_OFFSET + FRAME_SIZE)(r1)
+ mtlr r0
+ addi r1, r1, FRAME_SIZE
+ blr
+
+ /* End of _ITM_beginTransaction. */
+
+ /* uint32_t GTM_longjmp (uint32_t, const gtm_jmpbuf *, uint32_t) */
+
+ .private_extern _GTM_longjmp
+_GTM_longjmp:
+
+ /* ??? Determine when VRs not present. */
+ /* ??? Test r5 for pr_hasNoVectorUpdate and skip the vr restore.
+ This is not yet set by the compiler. */
+
+ mr r14,r4
+ lwz r0,VRSAVE_OFF(r4)
+ addi r15,r4,16
+
+ lvx v20,0,r14
+ addi r14,r14,32
+ lvx v21,0,r15
+ addi r15,r15,32
+ lvx v22,0,r14
+ addi r14,r14,32
+ lvx v23,0,r15
+ addi r15,r15,32
+ lvx v24,0,r14
+ addi r14,r14,32
+ lvx v25,0,r15
+ addi r15,r15,32
+ lvx v26,0,r14
+ addi r14,r14,32
+ lvx v27,0,r15
+ addi r15,r15,32
+ lvx v28,0,r14
+ addi r14,r14,32
+ lvx v29,0,r15
+ addi r15,r15,32
+ lvx v30,0,r14
+ addi r14,r14,32
+ lvx v31,0,r15
+
+ mtspr VRsave,r0 /* Restored... */
+
+#ifndef __ppc64__
+ lmw r13,GPRS_OFF(r4)
+#else
+ lg r14,(GPRS_OFF + 0 * GPR_BYTES)(r4)
+ lg r15,(GPRS_OFF + 1 * GPR_BYTES)(r4)
+ lg r16,(GPRS_OFF + 2 * GPR_BYTES)(r4)
+ lg r17,(GPRS_OFF + 3 * GPR_BYTES)(r4)
+ lg r18,(GPRS_OFF + 4 * GPR_BYTES)(r4)
+ lg r19,(GPRS_OFF + 5 * GPR_BYTES)(r4)
+ lg r20,(GPRS_OFF + 6 * GPR_BYTES)(r4)
+ lg r21,(GPRS_OFF + 7 * GPR_BYTES)(r4)
+ lg r22,(GPRS_OFF + 8 * GPR_BYTES)(r4)
+ lg r23,(GPRS_OFF + 9 * GPR_BYTES)(r4)
+ lg r24,(GPRS_OFF + 10 * GPR_BYTES)(r4)
+ lg r25,(GPRS_OFF + 11 * GPR_BYTES)(r4)
+ lg r26,(GPRS_OFF + 12 * GPR_BYTES)(r4)
+ lg r27,(GPRS_OFF + 13 * GPR_BYTES)(r4)
+ lg r28,(GPRS_OFF + 14 * GPR_BYTES)(r4)
+ lg r29,(GPRS_OFF + 15 * GPR_BYTES)(r4)
+ lg r30,(GPRS_OFF + 16 * GPR_BYTES)(r4)
+ lg r31,(GPRS_OFF + 17 * GPR_BYTES)(r4)
+#endif
+
+ /* ??? Determine when FPRs not present. */
+ /* ??? Test r5 for pr_hasNoFloatUpdate and skip the fp load.
+ This is not yet set by the compiler. */
+
+ lfd f0,FPSCRS_OFF(r4)
+ lfd f14,(FPRS_OFF + 0)(r4)
+ lfd f15,(FPRS_OFF + 8)(r4)
+ lfd f16,(FPRS_OFF + 16)(r4)
+ lfd f17,(FPRS_OFF + 24)(r4)
+ lfd f18,(FPRS_OFF + 32)(r4)
+ lfd f19,(FPRS_OFF + 40)(r4)
+ lfd f20,(FPRS_OFF + 48)(r4)
+ lfd f21,(FPRS_OFF + 56)(r4)
+ lfd f22,(FPRS_OFF + 64)(r4)
+ lfd f23,(FPRS_OFF + 72)(r4)
+ lfd f24,(FPRS_OFF + 80)(r4)
+ lfd f25,(FPRS_OFF + 88)(r4)
+ lfd f26,(FPRS_OFF + 96)(r4)
+ lfd f27,(FPRS_OFF + 104)(r4)
+ lfd f28,(FPRS_OFF + 112)(r4)
+ lfd f29,(FPRS_OFF + 120)(r4)
+ lfd f30,(FPRS_OFF + 128)(r4)
+ lfd f31,(FPRS_OFF + 136)(r4)
+
+ mtfsf 0xff,f0 /* Restore fpscr. */
+
+ /* So now pick up the previous data. */
+ addi r4,r4,PREV_OFF
+ lwz r0,(PREV_OFF + SAVED_CR_OFFSET)(r4)
+ mtcr r0 /* Restore CR. */
+ lg r0,(PREV_OFF + SAVED_LR_OFFSET)(r4)
+ mtlr r0 /* Ret addr. */
+ lg r1,(PREV_OFF + 0)(r4) /* SP. */
+ blr
+
+ /* End of GTM_longjump */
+
Index: libitm/config/darwin/powerpc/target.h
===================================================================
--- libitm/config/darwin/powerpc/target.h (revision 0)
+++ libitm/config/darwin/powerpc/target.h (revision 0)
@@ -0,0 +1,87 @@
+/* Copyright (C) 2011 Free Software Foundation, Inc.
+ Contributed by Iain Sandoe <ia...@gcc.gnu.org>.
+ Based on libitm/powerpc/target.h by Richard Henderson.
+
+ This file is part of the GNU Transactional Memory Library (libitm).
+
+ Libitm is free software; you can redistribute it and/or modify it
+ under the terms of the GNU General Public License as published by
+ the Free Software Foundation; either version 3 of the License, or
+ (at your option) any later version.
+
+ Libitm is distributed in the hope that it will be useful, but WITHOUT ANY
+ WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS
+ FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ more details.
+
+ Under Section 7 of GPL version 3, you are granted additional
+ permissions described in the GCC Runtime Library Exception, version
+ 3.1, as published by the Free Software Foundation.
+
+ You should have received a copy of the GNU General Public License and
+ a copy of the GCC Runtime Library Exception along with this program;
+ see the files COPYING3 and COPYING.RUNTIME respectively. If not, see
+ <http://www.gnu.org/licenses/>. */
+
+namespace GTM HIDDEN {
+
+/* We will assume that the code is to be built for a processor with
+ Altivec. If it is desired to make this run on G3 for Darwin < 9 then the
+ vecSave code in sjlj.S will need to be made conditional on __cpu_has_altivec
+ from the system framework (as is done in Darwin's 'world_save ()' routine in
+ libgcc). */
+
+typedef int v128 __attribute__((vector_size(16), may_alias, aligned(16)));
+
+typedef struct gtm_jmpbuf
+{
+ v128 vr[12]; /* vr20-vr31 */
+#ifdef __ppc64__
+ double fpscr; /* ??? should we save this. */
+ unsigned int vscrpad;
+ unsigned int vscr; /* VRsave */
+#else
+ double fpscr; /* ??? should we save this. */
+ unsigned int vscrpad[2];
+ unsigned int vscr; /* VRsave */
+#endif
+#ifdef __ppc64__
+ unsigned long gr[18]; /* r14-r31 */
+#else
+ unsigned long gr[19]; /* r13-r31 */
+#endif
+ double fr[18]; /* f14-f31 */
+ void *cfa; /* backchain. */
+ unsigned int cr; /* Saved CR. */
+#ifdef __ppc64__
+ unsigned int crpad;
+#endif
+ unsigned long pc; /* Saved LR. */
+} gtm_jmpbuf;
+
+/* The size of one line in hardware caches (in bytes). */
+#ifdef __ppc64__
+# define HW_CACHELINE_SIZE 128
+#else
+# define HW_CACHELINE_SIZE 32
+#endif
+
+static inline void
+cpu_relax (void)
+{
+ __asm volatile ("" : : : "memory");
+}
+
+static inline void
+atomic_read_barrier (void)
+{
+ __sync_synchronize ();
+}
+
+static inline void
+atomic_write_barrier (void)
+{
+ __sync_synchronize ();
+}
+
+} // namespace GTM
Index: libitm/configure.tgt
===================================================================
--- libitm/configure.tgt (revision 181902)
+++ libitm/configure.tgt (working copy)
@@ -46,7 +46,8 @@ fi
# Map the target cpu to an ARCH sub-directory. At the same time,
# work out any special compilation flags as necessary.
case "${target_cpu}" in
- alpha*) ARCH=alpha ;;
+ alpha*) ARCH=alpha ;;
+ rs6000 | powerpc*) ARCH=powerpc ;;
i[3456]86)
case " ${CC} ${CFLAGS} " in
@@ -90,6 +91,15 @@ case "${target}" in
fi
;;
+ powerpc*-*-darwin*)
+ config_path="darwin/$ARCH $config_path"
+ ;;
+
+ powerpc*-*-aix* | rs6000-*-aix*)
+ # The system ought to be supported, but sjlj.S has not been ported.
+ UNSUPPORTED=1
+ ;;
+
*-*-gnu* | *-*-k*bsd*-gnu \
| *-*-netbsd* | *-*-freebsd* | *-*-openbsd* \
| *-*-solaris2* | *-*-sysv4* | *-*-irix6* | *-*-osf* | *-*-hpux11* \
