This patch enables sibling calls for powerpc in a few more cases, and
fixes bugs exposed by that change. We now
a) Allow sibling calls via function pointer. At the time
rs6000_function_ok_for_sibcall was written, I don't think access to
arg types of function pointer calls was available in the target
hook/macro.
b) Allow sibling calls to functions with vector parameters. Contrary
to the previous comment about vector parameters, a problem occurs
with VRSAVE only when the called function has more vector
parameters than the caller (because VRSAVE bits will already be set
for the caller's arguments). Also, the old code did not make any
attempt to determine whether altivec/vsx registers would actually
be used to pass args. Not all vector types fit in these regs.
c) Allow SYSV4 ABI code to make sibling calls to non-local functions
so long as not both flag_pic and TARGET_SECURE_PLT are set.
The PIC -msecure-plt call stubs use r30.
sibcall_value_nonlocal_sysv was trying to read the call cookie from
the wrong operand, a latent bug since the pattern wasn't used until
now. I also fixed a minor problem with CALL_LIBCALL in the call
cookie, which could cause various call insns to match an "n"
constraint rather than a "0" constraint and so give the wrong insn
length. Bootstrapped and regression tested powerpc64-linux and
powerpc-linux.
This patch does affect darwin, not only in removing what are now
redundant insn patterns, but also (a) and (b) above. Would someone
please run a bootstrap and regression test on darwin for me? I don't
have a machine handy to confirm that I didn't break anything there.
I've attached a vector testcase I used to verify some of these
changes.
gcc/
* config/rs6000/rs6000.c (rs6000_function_arg): Remove CALL_LIBCALL
when returning call_cookie.
(rs6000_function_ok_for_sibcall): Allow sibcalls via function
pointers, to functions with no more vector args than the current
function, and some non-local calls for ABI_V4.
* config/rs6000/rs6000.md (sibcall_nonlocal_aix32,
sibcall_nonlocal_aix64): Combine to ..
(sibcall_nonlocal_aix<mode>): ..this. Handle function pointer calls.
(sibcall_value_nonlocal_aix32, sibcall_value_nonlocal_aix64): Combine..
(sibcall_value_nonlocal_aix<mode>): ..likewise.
(*sibcall_nonlocal_sysv<mode>): Handle function pointer calls.
(sibcall_value_nonlocal_sysv<mode>): Likewise. Correct call cookie
operand.
* config/rs6000/darwin.md (sibcall_nonlocal_darwin64,
sibcall_value_nonlocal_darwin64, sibcall_symbolic_64,
sibcall_value_symbolic_64): Delete.
gcc/testsuite/
* gcc.target/powerpc/ppc-pow.c: Allow for tail calls.
Index: gcc/config/rs6000/rs6000.c
===================================================================
--- gcc/config/rs6000/rs6000.c (revision 172094)
+++ gcc/config/rs6000/rs6000.c (working copy)
@@ -19305,39 +19302,73 @@ rs6000_return_addr (int count, rtx frame
return get_hard_reg_initial_val (Pmode, LR_REGNO);
}
-/* Say whether a function is a candidate for sibcall handling or not.
- We do not allow indirect calls to be optimized into sibling calls.
- Also, we can't do it if there are any vector parameters; there's
- nowhere to put the VRsave code so it works; note that functions with
- vector parameters are required to have a prototype, so the argument
- type info must be available here. (The tail recursion case can work
- with vector parameters, but there's no way to distinguish here.) */
+/* Say whether a function is a candidate for sibcall handling or not. */
+
static bool
-rs6000_function_ok_for_sibcall (tree decl, tree exp ATTRIBUTE_UNUSED)
+rs6000_function_ok_for_sibcall (tree decl, tree exp)
{
- tree type;
+ tree fntype;
+
if (decl)
+ fntype = TREE_TYPE (decl);
+ else
+ fntype = TREE_TYPE (TREE_TYPE (CALL_EXPR_FN (exp)));
+
+ /* We can't do it if the called function has more vector parameters
+ than the current function; there's nowhere to put the VRsave code. */
+ if (TARGET_ALTIVEC_ABI
+ && TARGET_ALTIVEC_VRSAVE
+ && !(decl && decl == current_function_decl))
{
- if (TARGET_ALTIVEC_VRSAVE)
- {
- for (type = TYPE_ARG_TYPES (TREE_TYPE (decl));
- type; type = TREE_CHAIN (type))
- {
- if (TREE_CODE (TREE_VALUE (type)) == VECTOR_TYPE)
- return false;
- }
- }
- if (DEFAULT_ABI == ABI_DARWIN
- || ((*targetm.binds_local_p) (decl)
- && (DEFAULT_ABI != ABI_AIX || !DECL_EXTERNAL (decl))))
- {
- tree attr_list = TYPE_ATTRIBUTES (TREE_TYPE (decl));
+ tree type;
+ int nvreg = 0;
- if (!lookup_attribute ("longcall", attr_list)
- || lookup_attribute ("shortcall", attr_list))
- return true;
- }
+ /* Functions with vector parameters are required to have a
+ prototype, so the argument type info must be available
+ here. */
+ for (type = TYPE_ARG_TYPES (fntype);
+ type;
+ type = TREE_CHAIN (type))
+ if (TREE_CODE (TREE_VALUE (type)) == VECTOR_TYPE
+ && (ALTIVEC_VECTOR_MODE (TYPE_MODE (TREE_VALUE (type)))
+ || VSX_VECTOR_MODE (TYPE_MODE (TREE_VALUE (type)))))
+ nvreg++;
+
+ for (type = TYPE_ARG_TYPES (TREE_TYPE (current_function_decl));
+ type;
+ type = TREE_CHAIN (type))
+ if (TREE_CODE (TREE_VALUE (type)) == VECTOR_TYPE
+ && (ALTIVEC_VECTOR_MODE (TYPE_MODE (TREE_VALUE (type)))
+ || VSX_VECTOR_MODE (TYPE_MODE (TREE_VALUE (type)))))
+ nvreg--;
+
+ if (nvreg > 0)
+ return false;
}
+
+ /* Under the AIX ABI we can't allow calls to non-local functions,
+ because the callee may have a different TOC pointer to the
+ caller and there's no way to ensure we restore the TOC when we
+ return. With the secure-plt SYSV ABI we can't make non-local
+ calls when -fpic/PIC because the plt call stubs use r30. */
+ if (DEFAULT_ABI == ABI_DARWIN
+ || (DEFAULT_ABI == ABI_AIX
+ && decl
+ && !DECL_EXTERNAL (decl)
+ && (*targetm.binds_local_p) (decl))
+ || (DEFAULT_ABI == ABI_V4
+ && (!TARGET_SECURE_PLT
+ || !flag_pic
+ || (decl
+ && (*targetm.binds_local_p) (decl)))))
+ {
+ tree attr_list = TYPE_ATTRIBUTES (fntype);
+
+ if (!lookup_attribute ("longcall", attr_list)
+ || lookup_attribute ("shortcall", attr_list))
+ return true;
+ }
+
return false;
}
Index: gcc/config/rs6000/rs6000.md
===================================================================
--- gcc/config/rs6000/rs6000.md (revision 172094)
+++ gcc/config/rs6000/rs6000.md (working copy)
@@ -12963,68 +12963,43 @@ (define_insn "*sibcall_value_local64"
[(set_attr "type" "branch")
(set_attr "length" "4,8")])
-(define_insn "*sibcall_nonlocal_aix32"
- [(call (mem:SI (match_operand:SI 0 "symbol_ref_operand" "s"))
- (match_operand 1 "" "g"))
- (use (match_operand:SI 2 "immediate_operand" "O"))
+(define_insn "*sibcall_nonlocal_aix<mode>"
+ [(call (mem:SI (match_operand:P 0 "call_operand" "s,c"))
+ (match_operand 1 "" "g,g"))
+ (use (match_operand:SI 2 "immediate_operand" "O,O"))
(use (reg:SI LR_REGNO))
(return)]
- "TARGET_32BIT
- && DEFAULT_ABI == ABI_AIX
+ "DEFAULT_ABI == ABI_AIX
&& (INTVAL (operands[2]) & CALL_LONG) == 0"
- "b %z0"
- [(set_attr "type" "branch")
- (set_attr "length" "4")])
-
-(define_insn "*sibcall_nonlocal_aix64"
- [(call (mem:SI (match_operand:DI 0 "symbol_ref_operand" "s"))
- (match_operand 1 "" "g"))
- (use (match_operand:SI 2 "immediate_operand" "O"))
- (use (reg:SI LR_REGNO))
- (return)]
- "TARGET_64BIT
- && DEFAULT_ABI == ABI_AIX
- && (INTVAL (operands[2]) & CALL_LONG) == 0"
- "b %z0"
- [(set_attr "type" "branch")
- (set_attr "length" "4")])
-
-(define_insn "*sibcall_value_nonlocal_aix32"
- [(set (match_operand 0 "" "")
- (call (mem:SI (match_operand:SI 1 "symbol_ref_operand" "s"))
- (match_operand 2 "" "g")))
- (use (match_operand:SI 3 "immediate_operand" "O"))
- (use (reg:SI LR_REGNO))
- (return)]
- "TARGET_32BIT
- && DEFAULT_ABI == ABI_AIX
- && (INTVAL (operands[3]) & CALL_LONG) == 0"
- "b %z1"
+ "@
+ b %z0
+ b%T0"
[(set_attr "type" "branch")
(set_attr "length" "4")])
-(define_insn "*sibcall_value_nonlocal_aix64"
+(define_insn "*sibcall_value_nonlocal_aix<mode>"
[(set (match_operand 0 "" "")
- (call (mem:SI (match_operand:DI 1 "symbol_ref_operand" "s"))
- (match_operand 2 "" "g")))
- (use (match_operand:SI 3 "immediate_operand" "O"))
+ (call (mem:SI (match_operand:P 1 "call_operand" "s,c"))
+ (match_operand 2 "" "g,g")))
+ (use (match_operand:SI 3 "immediate_operand" "O,O"))
(use (reg:SI LR_REGNO))
(return)]
- "TARGET_64BIT
- && DEFAULT_ABI == ABI_AIX
+ "DEFAULT_ABI == ABI_AIX
&& (INTVAL (operands[3]) & CALL_LONG) == 0"
- "b %z1"
+ "@
+ b %z1
+ b%T1"
[(set_attr "type" "branch")
(set_attr "length" "4")])
(define_insn "*sibcall_nonlocal_sysv<mode>"
- [(call (mem:SI (match_operand:P 0 "symbol_ref_operand" "s,s"))
+ [(call (mem:SI (match_operand:P 0 "call_operand" "s,s,c,c"))
(match_operand 1 "" ""))
- (use (match_operand 2 "immediate_operand" "O,n"))
+ (use (match_operand 2 "immediate_operand" "O,n,O,n"))
(use (reg:SI LR_REGNO))
(return)]
"(DEFAULT_ABI == ABI_DARWIN
- || DEFAULT_ABI == ABI_V4)
+ || DEFAULT_ABI == ABI_V4)
&& (INTVAL (operands[2]) & CALL_LONG) == 0"
"*
{
@@ -13034,7 +13009,9 @@ (define_insn "*sibcall_nonlocal_sysv<mod
else if (INTVAL (operands[2]) & CALL_V4_CLEAR_FP_ARGS)
output_asm_insn (\"creqv 6,6,6\", operands);
- if (DEFAULT_ABI == ABI_V4 && flag_pic)
+ if (which_alternative >= 2)
+ return \"b%T0\";
+ else if (DEFAULT_ABI == ABI_V4 && flag_pic)
{
gcc_assert (!TARGET_SECURE_PLT);
return \"b %z0@plt\";
@@ -13042,8 +13019,8 @@ (define_insn "*sibcall_nonlocal_sysv<mod
else
return \"b %z0\";
}"
- [(set_attr "type" "branch,branch")
- (set_attr "length" "4,8")])
+ [(set_attr "type" "branch")
+ (set_attr "length" "4,8,4,8")])
(define_expand "sibcall_value"
[(parallel [(set (match_operand 0 "register_operand" "")
@@ -13068,23 +13045,25 @@ (define_expand "sibcall_value"
(define_insn "*sibcall_value_nonlocal_sysv<mode>"
[(set (match_operand 0 "" "")
- (call (mem:SI (match_operand:P 1 "symbol_ref_operand" "s,s"))
+ (call (mem:SI (match_operand:P 1 "call_operand" "s,s,c,c"))
(match_operand 2 "" "")))
- (use (match_operand:SI 3 "immediate_operand" "O,n"))
+ (use (match_operand:SI 3 "immediate_operand" "O,n,O,n"))
(use (reg:SI LR_REGNO))
(return)]
"(DEFAULT_ABI == ABI_DARWIN
- || DEFAULT_ABI == ABI_V4)
+ || DEFAULT_ABI == ABI_V4)
&& (INTVAL (operands[3]) & CALL_LONG) == 0"
"*
{
- if (INTVAL (operands[2]) & CALL_V4_SET_FP_ARGS)
+ if (INTVAL (operands[3]) & CALL_V4_SET_FP_ARGS)
output_asm_insn (\"crxor 6,6,6\", operands);
- else if (INTVAL (operands[2]) & CALL_V4_CLEAR_FP_ARGS)
+ else if (INTVAL (operands[3]) & CALL_V4_CLEAR_FP_ARGS)
output_asm_insn (\"creqv 6,6,6\", operands);
- if (DEFAULT_ABI == ABI_V4 && flag_pic)
+ if (which_alternative >= 2)
+ return \"b%T1\";
+ else if (DEFAULT_ABI == ABI_V4 && flag_pic)
{
gcc_assert (!TARGET_SECURE_PLT);
return \"b %z1@plt\";
@@ -13092,8 +13071,8 @@ (define_insn "*sibcall_value_nonlocal_sy
else
return \"b %z1\";
}"
- [(set_attr "type" "branch,branch")
- (set_attr "length" "4,8")])
+ [(set_attr "type" "branch")
+ (set_attr "length" "4,8,4,8")])
(define_expand "sibcall_epilogue"
[(use (const_int 0))]
Index: gcc/config/rs6000/darwin.md
===================================================================
--- gcc/config/rs6000/darwin.md (revision 172094)
+++ gcc/config/rs6000/darwin.md (working copy)
@@ -370,73 +370,3 @@ (define_insn "*call_value_nonlocal_darwi
}
[(set_attr "type" "branch,branch")
(set_attr "length" "4,8")])
-
-(define_insn "*sibcall_nonlocal_darwin64"
- [(call (mem:SI (match_operand:DI 0 "symbol_ref_operand" "s,s"))
- (match_operand 1 "" ""))
- (use (match_operand 2 "immediate_operand" "O,n"))
- (use (reg:SI 65))
- (return)]
- "(DEFAULT_ABI == ABI_DARWIN)
- && (INTVAL (operands[2]) & CALL_LONG) == 0"
-{
- return "b %z0";
-}
- [(set_attr "type" "branch,branch")
- (set_attr "length" "4,8")])
-
-(define_insn "*sibcall_value_nonlocal_darwin64"
- [(set (match_operand 0 "" "")
- (call (mem:SI (match_operand:DI 1 "symbol_ref_operand" "s,s"))
- (match_operand 2 "" "")))
- (use (match_operand:SI 3 "immediate_operand" "O,n"))
- (use (reg:SI 65))
- (return)]
- "(DEFAULT_ABI == ABI_DARWIN)
- && (INTVAL (operands[3]) & CALL_LONG) == 0"
- "*
-{
- return \"b %z1\";
-}"
- [(set_attr "type" "branch,branch")
- (set_attr "length" "4,8")])
-
-
-(define_insn "*sibcall_symbolic_64"
- [(call (mem:SI (match_operand:DI 0 "call_operand" "s,c")) ; 64
- (match_operand 1 "" ""))
- (use (match_operand 2 "" ""))
- (use (reg:SI 65))
- (return)]
- "TARGET_64BIT && DEFAULT_ABI == ABI_DARWIN"
- "*
-{
- switch (which_alternative)
- {
- case 0: return \"b %z0\";
- case 1: return \"b%T0\";
- default: gcc_unreachable ();
- }
-}"
- [(set_attr "type" "branch")
- (set_attr "length" "4")])
-
-(define_insn "*sibcall_value_symbolic_64"
- [(set (match_operand 0 "" "")
- (call (mem:SI (match_operand:DI 1 "call_operand" "s,c"))
- (match_operand 2 "" "")))
- (use (match_operand:SI 3 "" ""))
- (use (reg:SI 65))
- (return)]
- "TARGET_64BIT && DEFAULT_ABI == ABI_DARWIN"
- "*
-{
- switch (which_alternative)
- {
- case 0: return \"b %z1\";
- case 1: return \"b%T1\";
- default: gcc_unreachable ();
- }
-}"
- [(set_attr "type" "branch")
- (set_attr "length" "4")])
Index: gcc/testsuite/gcc.target/powerpc/ppc-pow.c
===================================================================
--- gcc/testsuite/gcc.target/powerpc/ppc-pow.c (revision 172094)
+++ gcc/testsuite/gcc.target/powerpc/ppc-pow.c (working copy)
@@ -2,8 +2,8 @@
/* { dg-options "-O2 -ffast-math -mcpu=power6" } */
/* { dg-final { scan-assembler-times "fsqrt" 3 } } */
/* { dg-final { scan-assembler-times "fmul" 1 } } */
-/* { dg-final { scan-assembler-times "bl pow" 1 } } */
-/* { dg-final { scan-assembler-times "bl sqrt" 1 } } */
+/* { dg-final { scan-assembler-times "bl? pow" 1 } } */
+/* { dg-final { scan-assembler-times "bl? sqrt" 1 } } */
double
do_pow_0_75_default (double a)
--
Alan Modra
Australia Development Lab, IBM
#define vector __attribute__((vector_size(16)))
vector int v1;
extern void foo (int *, vector int *, vector int *, vector int *);
void f1 (void)
{
int a = sizeof (v1);
vector int v2;
vector int *v3 = __builtin_alloca (sizeof (*v3));
foo (&a, &v1, &v2, v3);
}
vector int f2 (int n, vector int x)
{
if (n <= 1)
return x;
if (n & 1)
return f2 (n >> 1, x + x);
else
return f2 (n >> 1, x);
}
vector int f3 (vector int x)
{
return f2 (3, x);
}
extern vector int bar (vector int, vector int);
vector int f4 (vector int x)
{
return bar (x, x);
}
extern vector int (*extv1) (vector int);
vector int f5 (vector int x)
{
return (*extv1) (x);
}
extern vector int (*extv2) (vector int, vector int);
vector int f6 (vector int x)
{
return (*extv2) (x, x);
}
