On Fri, May 29, 2015 at 12:35 PM, Jan Hubicka <hubi...@ucw.cz> wrote: >> * config/i386/i386.c (avoid_plt_to_call): New function. >> (ix86_output_call_insn): Generate indirect call for functions >> marked with "noplt" attribute. >> (attribute_spec ix86_attribute_): Define new attribute "noplt". >> * doc/extend.texi: Document new attribute "noplt". >> * gcc.target/i386/noplt-1.c: New testcase. >> * gcc.target/i386/noplt-2.c: New testcase. >> >> Index: config/i386/i386.c >> =================================================================== >> --- config/i386/i386.c (revision 223720) >> +++ config/i386/i386.c (working copy) >> @@ -25599,6 +25599,24 @@ ix86_expand_call (rtx retval, rtx fnaddr, rtx call >> return call; >> } >> >> +/* Return true if the function being called was marked with attribute >> + "noplt". If this function is defined, this should return false. */ >> +static bool >> +avoid_plt_to_call (rtx call_op) >> +{ >> + if (SYMBOL_REF_LOCAL_P (call_op)) >> + return false; >> + >> + tree symbol_decl = SYMBOL_REF_DECL (call_op); >> + >> + if (symbol_decl != NULL_TREE >> + && TREE_CODE (symbol_decl) == FUNCTION_DECL >> + && lookup_attribute ("noplt", DECL_ATTRIBUTES (symbol_decl))) >> + return true; >> + >> + return false; >> +} > > OK, now we have __attribute__ (optimize("noplt")) which binds to the caller > and makes > all calls in the function to skip PLT and __attribute__ ("noplt") which binds > to callee > and makes all calls to function to not use PLT. > > That sort of makes sense to me, but why "noplt" attribute is not implemented > at generic level > just like -fplt? Is it only because every target supporting PLT would need > update in its > call expansion patterns?
Yes, that is what I had in mind. > > Also I think the PLT calls have EBX in call fusage wich is added by > ix86_expand_call. > else > { > /* Static functions and indirect calls don't need the pic register. */ > 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))) > { > use_reg (&use, gen_rtx_REG (Pmode, REAL_PIC_OFFSET_TABLE_REGNUM)); > if (ix86_use_pseudo_pic_reg ()) > emit_move_insn (gen_rtx_REG (Pmode, REAL_PIC_OFFSET_TABLE_REGNUM), > pic_offset_table_rtx); > } > > I think you want to take that away from FUSAGE there just like we do for > local calls > (and in fact the code should already check flag_pic && flag_plt I suppose. Done that now and patch attached. Thanks Sri > > Honza
* config/i386/i386.c (avoid_plt_to_call): New function. (ix86_expand_call): Dont use the PIC register when external function calls are not made via PLT. (ix86_output_call_insn): Generate indirect call for functions marked with "noplt" attribute. (attribute_spec ix86_attribute_): Define new attribute "noplt". * doc/extend.texi: Document new attribute "noplt". * gcc.target/i386/noplt-1.c: New testcase. * gcc.target/i386/noplt-2.c: New testcase. Index: config/i386/i386.c =================================================================== --- config/i386/i386.c (revision 223720) +++ config/i386/i386.c (working copy) @@ -25475,6 +25475,28 @@ construct_plt_address (rtx symbol) return tmp; } +/* Return true if the function being called was marked with attribute + "noplt". If this function is defined, this should return false. This + is currently used only with 64-bit ELF targets. */ +static bool +avoid_plt_to_call (rtx call_op) +{ + if (!TARGET_64BIT || TARGET_MACHO|| TARGET_SEH || TARGET_PECOFF) + return false; + + if (SYMBOL_REF_LOCAL_P (call_op)) + return false; + + tree symbol_decl = SYMBOL_REF_DECL (call_op); + + if (symbol_decl != NULL_TREE + && TREE_CODE (symbol_decl) == FUNCTION_DECL + && lookup_attribute ("noplt", DECL_ATTRIBUTES (symbol_decl))) + return true; + + return false; +} + rtx ix86_expand_call (rtx retval, rtx fnaddr, rtx callarg1, rtx callarg2, @@ -25497,13 +25519,16 @@ 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 && !avoid_plt_to_call (XEXP (fnaddr, 0))) { use_reg (&use, gen_rtx_REG (Pmode, REAL_PIC_OFFSET_TABLE_REGNUM)); if (ix86_use_pseudo_pic_reg ()) @@ -25611,7 +25636,13 @@ ix86_output_call_insn (rtx_insn *insn, rtx call_op if (SIBLING_CALL_P (insn)) { if (direct_p) - xasm = "%!jmp\t%P0"; + { + if (!TARGET_MACHO && !TARGET_SEH && !TARGET_PECOFF + && TARGET_64BIT && avoid_plt_to_call (call_op)) + xasm = "%!jmp\t*%p0@GOTPCREL(%%rip)"; + else + xasm = "%!jmp\t%P0"; + } /* SEH epilogue detection requires the indirect branch case to include REX.W. */ else if (TARGET_SEH) @@ -25654,7 +25685,13 @@ ix86_output_call_insn (rtx_insn *insn, rtx call_op } if (direct_p) - xasm = "%!call\t%P0"; + { + if (!TARGET_MACHO && !TARGET_SEH && !TARGET_PECOFF + && TARGET_64BIT && avoid_plt_to_call (call_op)) + xasm = "%!call\t*%p0@GOTPCREL(%%rip)"; + else + xasm = "%!call\t%P0"; + } else xasm = "%!call\t%A0"; @@ -46628,6 +46665,9 @@ static const struct attribute_spec ix86_attribute_ false }, { "callee_pop_aggregate_return", 1, 1, false, true, true, ix86_handle_callee_pop_aggregate_return, true }, + /* Attribute to avoid calling function via PLT. */ + { "noplt", 0, 0, true, false, false, ix86_handle_fndecl_attribute, + false }, /* End element. */ { NULL, 0, 0, false, false, false, NULL, false } }; Index: doc/extend.texi =================================================================== --- doc/extend.texi (revision 223720) +++ doc/extend.texi (working copy) @@ -4858,6 +4858,13 @@ On x86-32 targets, the @code{stdcall} attribute ca assume that the called function pops off the stack space used to pass arguments, unless it takes a variable number of arguments. +@item noplt +@cindex @code{noplt} function attribute, x86-64 +@cindex functions whose calls do not go via PLT +On x86-64 targets. the @code{noplt} attribute causes the compiler to +call this external function indirectly using a GOT entry and avoid the +PLT. + @item target (@var{options}) @cindex @code{target} function attribute As discussed in @ref{Common Function Attributes}, this attribute 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* } } */ + + +__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" } */ + + +__attribute__ ((noplt)) +int foo(); + +int main() +{ + return foo(); +} + +/* { dg-final { scan-assembler "jmp\[ \t\]\\*.*foo.*@GOTPCREL\\(%rip\\)" } } */