On 11/03/2017 02:09 AM, Uros Bizjak wrote:
> On Thu, Nov 2, 2017 at 11:43 PM, Daniel Santos <[email protected]>
> wrote:
>
>>>> int_registers_saved = (frame.nregs == 0);
>>>> sse_registers_saved = (frame.nsseregs == 0);
>>>> + save_stub_call_needed = (m->call_ms2sysv);
>>>> + gcc_assert (!(!sse_registers_saved && save_stub_call_needed));
>>> Oooh, double negation :(
>> I'm just saying that we shouldn't be saving SSE registers inline and via
>> the stub. If I followed the naming convention of e.g.,
>> "see_registers_saved" then my variable would end up being called
>> "save_stub_called" which would be incorrect and misleading, similar to
>> how "see_registers_saved" is misleading when there are in fact no SSE
>> register that need to be saved. Maybe I should rename
>> (int|sse)_registers_saved to (int|sse)_register_saves_needed with
>> inverted logic instead.
> But, we can just say
>
> gcc_assert (sse_registers_saved || !save_stub_call_needed);
>
> No?
>
> Uros.
>
Oh yes, I see. Because "sse_registers_saved" really means that we've
either already saved them or don't have to, and not literally that they
have been saved. I ranted about it's name but didn't think it all the
way through. :)
How does this patch look? (Also, I've updated comments for
choose_baseaddr.) Currently re-running tests.
Thanks,
Daniel
diff --git a/gcc/config/i386/i386.c b/gcc/config/i386/i386.c
index 29678722226..fb81d4dba84 100644
--- a/gcc/config/i386/i386.c
+++ b/gcc/config/i386/i386.c
@@ -11515,12 +11515,15 @@ choose_basereg (HOST_WIDE_INT cfa_offset, rtx &base_reg,
an alignment value (in bits) that is preferred or zero and will
recieve the alignment of the base register that was selected,
irrespective of rather or not CFA_OFFSET is a multiple of that
- alignment value.
+ alignment value. If it is possible for the base register offset to be
+ non-immediate then SCRATCH_REGNO should specify a scratch register to
+ use.
The valid base registers are taken from CFUN->MACHINE->FS. */
static rtx
-choose_baseaddr (HOST_WIDE_INT cfa_offset, unsigned int *align)
+choose_baseaddr (HOST_WIDE_INT cfa_offset, unsigned int *align,
+ unsigned int scratch_regno = INVALID_REGNUM)
{
rtx base_reg = NULL;
HOST_WIDE_INT base_offset = 0;
@@ -11534,6 +11537,19 @@ choose_baseaddr (HOST_WIDE_INT cfa_offset, unsigned int *align)
choose_basereg (cfa_offset, base_reg, base_offset, 0, align);
gcc_assert (base_reg != NULL);
+
+ rtx base_offset_rtx = GEN_INT (base_offset);
+
+ if (!x86_64_immediate_operand (base_offset_rtx, Pmode))
+ {
+ gcc_assert (scratch_regno != INVALID_REGNUM);
+
+ rtx scratch_reg = gen_rtx_REG (Pmode, scratch_regno);
+ emit_move_insn (scratch_reg, base_offset_rtx);
+
+ return gen_rtx_PLUS (Pmode, base_reg, scratch_reg);
+ }
+
return plus_constant (Pmode, base_reg, base_offset);
}
@@ -12793,23 +12809,19 @@ ix86_emit_outlined_ms2sysv_save (const struct ix86_frame &frame)
rtx sym, addr;
rtx rax = gen_rtx_REG (word_mode, AX_REG);
const struct xlogue_layout &xlogue = xlogue_layout::get_instance ();
- HOST_WIDE_INT allocate = frame.stack_pointer_offset - m->fs.sp_offset;
/* AL should only be live with sysv_abi. */
gcc_assert (!ix86_eax_live_at_start_p ());
+ gcc_assert (m->fs.sp_offset >= frame.sse_reg_save_offset);
/* Setup RAX as the stub's base pointer. We use stack_realign_offset rather
we've actually realigned the stack or not. */
align = GET_MODE_ALIGNMENT (V4SFmode);
addr = choose_baseaddr (frame.stack_realign_offset
- + xlogue.get_stub_ptr_offset (), &align);
+ + xlogue.get_stub_ptr_offset (), &align, AX_REG);
gcc_assert (align >= GET_MODE_ALIGNMENT (V4SFmode));
- emit_insn (gen_rtx_SET (rax, addr));
- /* Allocate stack if not already done. */
- if (allocate > 0)
- pro_epilogue_adjust_stack (stack_pointer_rtx, stack_pointer_rtx,
- GEN_INT (-allocate), -1, false);
+ emit_insn (gen_rtx_SET (rax, addr));
/* Get the stub symbol. */
sym = xlogue.get_stub_rtx (frame_pointer_needed ? XLOGUE_STUB_SAVE_HFP
@@ -12841,6 +12853,7 @@ ix86_expand_prologue (void)
HOST_WIDE_INT allocate;
bool int_registers_saved;
bool sse_registers_saved;
+ bool save_stub_call_needed;
rtx static_chain = NULL_RTX;
if (ix86_function_naked (current_function_decl))
@@ -13016,6 +13029,8 @@ ix86_expand_prologue (void)
int_registers_saved = (frame.nregs == 0);
sse_registers_saved = (frame.nsseregs == 0);
+ save_stub_call_needed = (m->call_ms2sysv);
+ gcc_assert (sse_registers_saved || !save_stub_call_needed);
if (frame_pointer_needed && !m->fs.fp_valid)
{
@@ -13110,10 +13125,26 @@ ix86_expand_prologue (void)
target. */
if (TARGET_SEH)
m->fs.sp_valid = false;
- }
- if (m->call_ms2sysv)
- ix86_emit_outlined_ms2sysv_save (frame);
+ /* If SP offset is non-immediate after allocation of the stack frame,
+ then emit SSE saves or stub call prior to allocating the rest of the
+ stack frame. This is less efficient for the out-of-line stub because
+ we can't combine allocations across the call barrier, but it's better
+ than using a scratch register. */
+ else if (!x86_64_immediate_operand (GEN_INT (frame.stack_pointer_offset - m->fs.sp_realigned_offset), Pmode))
+ {
+ if (!sse_registers_saved)
+ {
+ ix86_emit_save_sse_regs_using_mov (frame.sse_reg_save_offset);
+ sse_registers_saved = true;
+ }
+ else if (save_stub_call_needed)
+ {
+ ix86_emit_outlined_ms2sysv_save (frame);
+ save_stub_call_needed = false;
+ }
+ }
+ }
allocate = frame.stack_pointer_offset - m->fs.sp_offset;
@@ -13337,6 +13368,8 @@ ix86_expand_prologue (void)
ix86_emit_save_regs_using_mov (frame.reg_save_offset);
if (!sse_registers_saved)
ix86_emit_save_sse_regs_using_mov (frame.sse_reg_save_offset);
+ else if (save_stub_call_needed)
+ ix86_emit_outlined_ms2sysv_save (frame);
/* For the mcount profiling on 32 bit PIC mode we need to emit SET_GOT
in PROLOGUE. */
@@ -13560,7 +13593,7 @@ ix86_emit_outlined_ms2sysv_restore (const struct ix86_frame &frame,
rtvec v;
unsigned int elems_needed, align, i, vi = 0;
rtx_insn *insn;
- rtx sym, tmp;
+ rtx sym, addr, tmp;
rtx rsi = gen_rtx_REG (word_mode, SI_REG);
rtx r10 = NULL_RTX;
const struct xlogue_layout &xlogue = xlogue_layout::get_instance ();
@@ -13577,9 +13610,13 @@ ix86_emit_outlined_ms2sysv_restore (const struct ix86_frame &frame,
/* Setup RSI as the stub's base pointer. */
align = GET_MODE_ALIGNMENT (V4SFmode);
- tmp = choose_baseaddr (rsi_offset, &align);
+ addr = choose_baseaddr (rsi_offset, &align, SI_REG);
gcc_assert (align >= GET_MODE_ALIGNMENT (V4SFmode));
- emit_insn (gen_rtx_SET (rsi, tmp));
+
+ /* If choose_baseaddr returned our scratch register, then we don't need to
+ do another SET. */
+ if (!REG_P (addr) || REGNO (addr) != SI_REG)
+ emit_insn (gen_rtx_SET (rsi, addr));
/* Get a symbol for the stub. */
if (frame_pointer_needed)
diff --git a/gcc/testsuite/gcc.target/i386/pr82002-2a.c b/gcc/testsuite/gcc.target/i386/pr82002-2a.c
index bc85080ba8e..c31440debe2 100644
--- a/gcc/testsuite/gcc.target/i386/pr82002-2a.c
+++ b/gcc/testsuite/gcc.target/i386/pr82002-2a.c
@@ -1,7 +1,5 @@
/* { dg-do compile { target lp64 } } */
/* { dg-options "-Ofast -mstackrealign -mabi=ms" } */
-/* { dg-xfail-if "" { *-*-* } } */
-/* { dg-xfail-run-if "" { *-*-* } } */
void __attribute__((sysv_abi)) a (char *);
void
diff --git a/gcc/testsuite/gcc.target/i386/pr82002-2b.c b/gcc/testsuite/gcc.target/i386/pr82002-2b.c
index 10e44cd7b1d..939e069517d 100644
--- a/gcc/testsuite/gcc.target/i386/pr82002-2b.c
+++ b/gcc/testsuite/gcc.target/i386/pr82002-2b.c
@@ -1,7 +1,5 @@
/* { dg-do compile { target lp64 } } */
/* { dg-options "-Ofast -mstackrealign -mabi=ms -mcall-ms2sysv-xlogues" } */
-/* { dg-xfail-if "" { *-*-* } } */
-/* { dg-xfail-run-if "" { *-*-* } } */
void __attribute__((sysv_abi)) a (char *);
void
