On Wed, Jun 3, 2015 at 1:09 PM, Richard Henderson <[email protected]> wrote:
> On 06/03/2015 11:38 AM, Sriraman Tallam wrote:
>> + { "no_plt", 0, 0, true, false, false,
>> + handle_no_plt_attribute, false },
>
> Call it noplt. We don't add the underscore for noinline, noclone, etc.
Done.
>
>
>
>> Index: config/i386/i386.c
>> ===================================================================
>> --- config/i386/i386.c (revision 223720)
>> +++ config/i386/i386.c (working copy)
>> @@ -5479,7 +5479,10 @@ ix86_function_ok_for_sibcall (tree decl, tree exp)
>> && !TARGET_64BIT
>> && flag_pic
>> && flag_plt
>> - && decl && !targetm.binds_local_p (decl))
>> + && decl
>> + && (TREE_CODE (decl) != FUNCTION_DECL
>> + || !lookup_attribute ("no_plt", DECL_ATTRIBUTES (decl)))
>> + && !targetm.binds_local_p (decl))
>> return false;
>>
>> /* If we need to align the outgoing stack, then sibcalling would
>
> Is this really necessary? I'd expect DECL to be NULL in this case,
> since the non-use of the PLT will mean that the (sib)call is indirect.
Removed.
>
>
>> @@ -25497,13 +25500,19 @@ ix86_expand_call (rtx retval, rtx fnaddr, rtx call
>> }
>> else
>> {
>> - /* Static functions and indirect calls don't need the pic register.
>> */
>> + /* Static functions and indirect calls don't need the pic register.
>> Also,
>> + check if PLT was explicitly avoided via no-plt or "no_plt" attribute,
>> making
>> + it an indirect call. */
>> if (flag_pic
>> && (!TARGET_64BIT
>> || (ix86_cmodel == CM_LARGE_PIC
>> && DEFAULT_ABI != MS_ABI))
>> && GET_CODE (XEXP (fnaddr, 0)) == SYMBOL_REF
>> - && ! SYMBOL_REF_LOCAL_P (XEXP (fnaddr, 0)))
>> + && !SYMBOL_REF_LOCAL_P (XEXP (fnaddr, 0))
>> + && flag_plt
>> + && (TREE_CODE (SYMBOL_REF_DECL (XEXP(fnaddr, 0))) != FUNCTION_DECL
>> + || !lookup_attribute ("no_plt",
>> + DECL_ATTRIBUTES (SYMBOL_REF_DECL (XEXP(fnaddr, 0))))))
>> {
>> use_reg (&use, gen_rtx_REG (Pmode, REAL_PIC_OFFSET_TABLE_REGNUM));
>> if (ix86_use_pseudo_pic_reg ())
>
> Why are you testing FUNCTION_DECL? Even if, somehow, the user were producing
> a
> function call to a data symbol, why do you think that lookup_attribute would
> produce incorrect results?
>
> Similarly in ix86_nopic_no_plt_attribute_p.
Fixed.
Patch attached with those changes.
Thanks
Sri
* c-family/c-common.c (noplt): New attribute.
(handle_noplt_attribute): New handler.
* calls.c (prepare_call_address): Check for noplt
attribute.
* config/i386/i386.c (ix86_function_ok_for_sibcall): Check
for noplt attribute.
(ix86_expand_call): Ditto.
(ix86_nopic_noplt_attribute_p): New function.
(ix86_output_call_insn): Output indirect call for non-pic
no plt calls.
* doc/extend.texi (noplt): Document new attribute.
* doc/invoke.texi: Document new attribute.
* testsuite/gcc.target/i386/noplt-1.c: New test.
* testsuite/gcc.target/i386/noplt-2.c: New test.
* testsuite/gcc.target/i386/noplt-3.c: New test.
* testsuite/gcc.target/i386/noplt-4.c: New test.
This patch does two things:
* Adds new generic function attribute "noplt" that is similar in functionality
to -fno-plt except that it applies only to calls to functions that are marked
with this attribute.
* For x86_64, it makes -fno-plt(and the attribute) also work for non-PIC code by
directly generating an indirect call via a GOT entry.
Index: c-family/c-common.c
===================================================================
--- c-family/c-common.c (revision 223720)
+++ c-family/c-common.c (working copy)
@@ -357,6 +357,7 @@ static tree handle_mode_attribute (tree *, tree, t
static tree handle_section_attribute (tree *, tree, tree, int, bool *);
static tree handle_aligned_attribute (tree *, tree, tree, int, bool *);
static tree handle_weak_attribute (tree *, tree, tree, int, bool *) ;
+static tree handle_noplt_attribute (tree *, tree, tree, int, bool *) ;
static tree handle_alias_ifunc_attribute (bool, tree *, tree, tree, bool *);
static tree handle_ifunc_attribute (tree *, tree, tree, int, bool *);
static tree handle_alias_attribute (tree *, tree, tree, int, bool *);
@@ -706,6 +707,8 @@ const struct attribute_spec c_common_attribute_tab
handle_aligned_attribute, false },
{ "weak", 0, 0, true, false, false,
handle_weak_attribute, false },
+ { "noplt", 0, 0, true, false, false,
+ handle_noplt_attribute, false },
{ "ifunc", 1, 1, true, false, false,
handle_ifunc_attribute, false },
{ "alias", 1, 1, true, false, false,
@@ -8185,6 +8188,25 @@ handle_weak_attribute (tree *node, tree name,
return NULL_TREE;
}
+/* Handle a "noplt" attribute; arguments as in
+ struct attribute_spec.handler. */
+
+static tree
+handle_noplt_attribute (tree *node, tree name,
+ tree ARG_UNUSED (args),
+ int ARG_UNUSED (flags),
+ bool * ARG_UNUSED (no_add_attrs))
+{
+ if (TREE_CODE (*node) != FUNCTION_DECL)
+ {
+ warning (OPT_Wattributes,
+ "%qE attribute is only applicable on functions", name);
+ *no_add_attrs = true;
+ return NULL_TREE;
+ }
+ return NULL_TREE;
+}
+
/* Handle an "alias" or "ifunc" attribute; arguments as in
struct attribute_spec.handler, except that IS_ALIAS tells us
whether this is an alias as opposed to ifunc attribute. */
Index: calls.c
===================================================================
--- calls.c (revision 223720)
+++ calls.c (working copy)
@@ -226,10 +226,16 @@ prepare_call_address (tree fndecl_or_type, rtx fun
&& targetm.small_register_classes_for_mode_p (FUNCTION_MODE))
? force_not_mem (memory_address (FUNCTION_MODE, funexp))
: memory_address (FUNCTION_MODE, funexp));
- else if (flag_pic && !flag_plt && fndecl_or_type
+ else if (flag_pic
+ && fndecl_or_type
&& TREE_CODE (fndecl_or_type) == FUNCTION_DECL
+ && (!flag_plt
+ || lookup_attribute ("noplt", DECL_ATTRIBUTES (fndecl_or_type)))
&& !targetm.binds_local_p (fndecl_or_type))
{
+ /* This is done only for PIC code. There is no easy interface to force
the
+ function address into GOT for non-PIC case. non-PIC case needs to be
+ handled specially by the backend. */
funexp = force_reg (Pmode, funexp);
}
else if (! sibcallp)
Index: config/i386/i386.c
===================================================================
--- config/i386/i386.c (revision 223720)
+++ config/i386/i386.c (working copy)
@@ -25497,13 +25497,18 @@ ix86_expand_call (rtx retval, rtx fnaddr, rtx call
}
else
{
- /* Static functions and indirect calls don't need the pic register. */
+ /* Static functions and indirect calls don't need the pic register.
Also,
+ check if PLT was explicitly avoided via no-plt or "noplt" attribute,
making
+ it an indirect call. */
if (flag_pic
&& (!TARGET_64BIT
|| (ix86_cmodel == CM_LARGE_PIC
&& DEFAULT_ABI != MS_ABI))
&& GET_CODE (XEXP (fnaddr, 0)) == SYMBOL_REF
- && ! SYMBOL_REF_LOCAL_P (XEXP (fnaddr, 0)))
+ && !SYMBOL_REF_LOCAL_P (XEXP (fnaddr, 0))
+ && flag_plt
+ && !lookup_attribute ("noplt",
+ DECL_ATTRIBUTES (SYMBOL_REF_DECL (XEXP(fnaddr, 0)))))
{
use_reg (&use, gen_rtx_REG (Pmode, REAL_PIC_OFFSET_TABLE_REGNUM));
if (ix86_use_pseudo_pic_reg ())
@@ -25598,7 +25603,31 @@ ix86_expand_call (rtx retval, rtx fnaddr, rtx call
return call;
}
+/* Return true if the function being called was marked with attribute "noplt"
+ or using -fno-plt and we are compiling for non-PIC and x86_64. We need to
+ handle the non-PIC case in the backend because there is no easy interface
+ for the front-end to force non-PLT calls to use the GOT. This is currently
+ used only with 64-bit ELF targets to call the function marked "noplt"
+ indirectly. */
+static bool
+ix86_nopic_noplt_attribute_p (rtx call_op)
+{
+ if (flag_pic || ix86_cmodel == CM_LARGE
+ || !TARGET_64BIT || TARGET_MACHO|| TARGET_SEH || TARGET_PECOFF
+ || SYMBOL_REF_LOCAL_P (call_op))
+ return false;
+
+ tree symbol_decl = SYMBOL_REF_DECL (call_op);
+
+ if (!flag_plt
+ || (symbol_decl != NULL_TREE
+ && lookup_attribute ("noplt", DECL_ATTRIBUTES (symbol_decl))))
+ return true;
+
+ return false;
+}
+
/* Output the assembly for a call instruction. */
const char *
@@ -25610,7 +25639,9 @@ ix86_output_call_insn (rtx_insn *insn, rtx call_op
if (SIBLING_CALL_P (insn))
{
- if (direct_p)
+ if (direct_p && ix86_nopic_noplt_attribute_p (call_op))
+ xasm = "%!jmp\t*%p0@GOTPCREL(%%rip)";
+ else if (direct_p)
xasm = "%!jmp\t%P0";
/* SEH epilogue detection requires the indirect branch case
to include REX.W. */
@@ -25653,7 +25684,9 @@ ix86_output_call_insn (rtx_insn *insn, rtx call_op
seh_nop_p = true;
}
- if (direct_p)
+ if (direct_p && ix86_nopic_noplt_attribute_p (call_op))
+ xasm = "%!call\t*%p0@GOTPCREL(%%rip)";
+ else if (direct_p)
xasm = "%!call\t%P0";
else
xasm = "%!call\t%A0";
Index: doc/extend.texi
===================================================================
--- doc/extend.texi (revision 223720)
+++ doc/extend.texi (working copy)
@@ -2916,6 +2916,35 @@ the standard C library can be guaranteed not to th
with the notable exceptions of @code{qsort} and @code{bsearch} that
take function pointer arguments.
+@item noplt
+@cindex @code{noplt} function attribute
+The @code{noplt} attribute is the counterpart to option @option{-fno-plt} and
+does not use PLT for calls to functions marked with this attribute in position
+independent code.
+
+@smallexample
+@group
+/* Externally defined function foo. */
+int foo () __attribute__ ((noplt));
+
+int
+main (/* @r{@dots{}} */)
+@{
+ /* @r{@dots{}} */
+ foo ();
+ /* @r{@dots{}} */
+@}
+@end group
+@end smallexample
+
+The @code{noplt} attribute on function foo tells the compiler to assume that
+the function foo is externally defined and the call to foo must avoid the PLT
+in position independent code.
+
+Additionally, a few targets also convert calls to those functions that are
+marked to not use the PLT to use the GOT instead for non-position independent
+code.
+
@item optimize
@cindex @code{optimize} function attribute
The @code{optimize} attribute is used to specify that a function is to
Index: doc/invoke.texi
===================================================================
--- doc/invoke.texi (revision 223720)
+++ doc/invoke.texi (working copy)
@@ -23868,6 +23868,14 @@ PLT stubs expect GOT pointer in a specific registe
register allocation freedom to the compiler. Lazy binding requires PLT:
with @option{-fno-plt} all external symbols are resolved at load time.
+Alternatively, function attribute @code{noplt} can be used to avoid PLT
+for calls to specific external functions by marking those functions with
+this attribute.
+
+Additionally, a few targets also convert calls to those functions that are
+marked to not use the PLT to use the GOT instead for non-position independent
+code.
+
@item -fno-jump-tables
@opindex fno-jump-tables
Do not use jump tables for switch statements even where it would be
Index: testsuite/gcc.target/i386/noplt-1.c
===================================================================
--- testsuite/gcc.target/i386/noplt-1.c (revision 0)
+++ testsuite/gcc.target/i386/noplt-1.c (working copy)
@@ -0,0 +1,13 @@
+/* { dg-do compile { target x86_64-*-linux* } } */
+/* { dg-options "-fno-pic" } */
+
+__attribute__ ((noplt))
+void foo();
+
+int main()
+{
+ foo();
+ return 0;
+}
+
+/* { dg-final { scan-assembler "call\[ \t\]\\*.*foo.*@GOTPCREL\\(%rip\\)" } }
*/
Index: testsuite/gcc.target/i386/noplt-2.c
===================================================================
--- testsuite/gcc.target/i386/noplt-2.c (revision 0)
+++ testsuite/gcc.target/i386/noplt-2.c (working copy)
@@ -0,0 +1,13 @@
+/* { dg-do compile { target x86_64-*-linux* } } */
+/* { dg-options "-O2 -fno-pic" } */
+
+
+__attribute__ ((noplt))
+int foo();
+
+int main()
+{
+ return foo();
+}
+
+/* { dg-final { scan-assembler "jmp\[ \t\]\\*.*foo.*@GOTPCREL\\(%rip\\)" } }
*/
Index: testsuite/gcc.target/i386/noplt-3.c
===================================================================
--- testsuite/gcc.target/i386/noplt-3.c (revision 0)
+++ testsuite/gcc.target/i386/noplt-3.c (working copy)
@@ -0,0 +1,12 @@
+/* { dg-do compile { target x86_64-*-linux* } } */
+/* { dg-options "-fno-pic -fno-plt" } */
+
+void foo();
+
+int main()
+{
+ foo();
+ return 0;
+}
+
+/* { dg-final { scan-assembler "call\[ \t\]\\*.*foo.*@GOTPCREL\\(%rip\\)" } }
*/
Index: testsuite/gcc.target/i386/noplt-4.c
===================================================================
--- testsuite/gcc.target/i386/noplt-4.c (revision 0)
+++ testsuite/gcc.target/i386/noplt-4.c (working copy)
@@ -0,0 +1,11 @@
+/* { dg-do compile { target x86_64-*-linux* } } */
+/* { dg-options "-O2 -fno-pic -fno-plt" } */
+
+int foo();
+
+int main()
+{
+ return foo();
+}
+
+/* { dg-final { scan-assembler "jmp\[ \t\]\\*.*foo.*@GOTPCREL\\(%rip\\)" } } */
