On Wed, Mar 12, 2014 at 5:28 PM, Wei Mi <w...@google.com> wrote:
>>> Does my patch fix the original problem?
>>
>> Yes, it works. I am doing bootstrap and regression test for your patch.
>> Thanks!
>>
>
> The patch passes bootstrap and regression test on x86_64-linux-gnu.
>
My patch fails to handle ia32. Here is the updated one.
--
H.J.
diff --git a/gcc/config/i386/i386.c b/gcc/config/i386/i386.c
index 9e33d53..da603b6 100644
--- a/gcc/config/i386/i386.c
+++ b/gcc/config/i386/i386.c
@@ -9490,20 +9490,30 @@ ix86_compute_frame_layout (struct ix86_frame *frame)
frame->nregs = ix86_nsaved_regs ();
frame->nsseregs = ix86_nsaved_sseregs ();
- stack_alignment_needed = crtl->stack_alignment_needed / BITS_PER_UNIT;
- preferred_alignment = crtl->preferred_stack_boundary / BITS_PER_UNIT;
-
/* 64-bit MS ABI seem to require stack alignment to be always 16 except for
function prologues and leaf. */
- if ((TARGET_64BIT_MS_ABI && preferred_alignment < 16)
+ if ((TARGET_64BIT_MS_ABI && crtl->preferred_stack_boundary < 128)
&& (!crtl->is_leaf || cfun->calls_alloca != 0
|| ix86_current_function_calls_tls_descriptor))
{
- preferred_alignment = 16;
- stack_alignment_needed = 16;
crtl->preferred_stack_boundary = 128;
crtl->stack_alignment_needed = 128;
}
+ /* preferred_stack_boundary is never updated for call
+ expanded from tls descriptor. Update it here. We don't update it in
+ expand stage because according to the comments before
+ ix86_current_function_calls_tls_descriptor, tls calls may be optimized
+ away. */
+ else if (ix86_current_function_calls_tls_descriptor
+ && crtl->preferred_stack_boundary < PREFERRED_STACK_BOUNDARY)
+ {
+ crtl->preferred_stack_boundary = PREFERRED_STACK_BOUNDARY;
+ if (crtl->stack_alignment_needed < PREFERRED_STACK_BOUNDARY)
+ crtl->stack_alignment_needed = PREFERRED_STACK_BOUNDARY;
+ }
+
+ stack_alignment_needed = crtl->stack_alignment_needed / BITS_PER_UNIT;
+ preferred_alignment = crtl->preferred_stack_boundary / BITS_PER_UNIT;
gcc_assert (!size || stack_alignment_needed);
gcc_assert (preferred_alignment >= STACK_BOUNDARY / BITS_PER_UNIT);
diff --git a/gcc/config/i386/i386.md b/gcc/config/i386/i386.md
index ea1d85f..bc8fb1f 100644
--- a/gcc/config/i386/i386.md
+++ b/gcc/config/i386/i386.md
@@ -12859,13 +12859,14 @@
(define_insn "*tls_global_dynamic_32_gnu"
[(set (match_operand:SI 0 "register_operand" "=a")
- (unspec:SI
- [(match_operand:SI 1 "register_operand" "b")
- (match_operand 2 "tls_symbolic_operand")
- (match_operand 3 "constant_call_address_operand" "z")]
- UNSPEC_TLS_GD))
- (clobber (match_scratch:SI 4 "=d"))
- (clobber (match_scratch:SI 5 "=c"))
+ (call:SI
+ (mem:QI (match_operand 3 "constant_call_address_operand" "z"))
+ (match_operand 4)))
+ (unspec:SI [(match_operand:SI 1 "register_operand" "b")
+ (match_operand 2 "tls_symbolic_operand")]
+ UNSPEC_TLS_GD)
+ (clobber (match_scratch:SI 5 "=d"))
+ (clobber (match_scratch:SI 6 "=c"))
(clobber (reg:CC FLAGS_REG))]
"!TARGET_64BIT && TARGET_GNU_TLS"
{
@@ -12885,13 +12886,19 @@
(define_expand "tls_global_dynamic_32"
[(parallel
[(set (match_operand:SI 0 "register_operand")
- (unspec:SI [(match_operand:SI 2 "register_operand")
- (match_operand 1 "tls_symbolic_operand")
- (match_operand 3 "constant_call_address_operand")]
- UNSPEC_TLS_GD))
+ (call:SI
+ (mem:QI (match_operand 3 "constant_call_address_operand"))
+ (const_int 0)))
+ (unspec:SI [(match_operand:SI 2 "register_operand")
+ (match_operand 1 "tls_symbolic_operand")]
+ UNSPEC_TLS_GD)
(clobber (match_scratch:SI 4))
(clobber (match_scratch:SI 5))
- (clobber (reg:CC FLAGS_REG))])])
+ (clobber (reg:CC FLAGS_REG))])]
+ ""
+{
+ ix86_tls_descriptor_calls_expanded_in_cfun = true;
+})
(define_insn "*tls_global_dynamic_64_<mode>"
[(set (match_operand:P 0 "register_operand" "=a")
@@ -12946,16 +12953,20 @@
(const_int 0)))
(unspec:P [(match_operand 1 "tls_symbolic_operand")]
UNSPEC_TLS_GD)])]
- "TARGET_64BIT")
+ "TARGET_64BIT"
+{
+ ix86_tls_descriptor_calls_expanded_in_cfun = true;
+})
(define_insn "*tls_local_dynamic_base_32_gnu"
[(set (match_operand:SI 0 "register_operand" "=a")
- (unspec:SI
- [(match_operand:SI 1 "register_operand" "b")
- (match_operand 2 "constant_call_address_operand" "z")]
- UNSPEC_TLS_LD_BASE))
- (clobber (match_scratch:SI 3 "=d"))
- (clobber (match_scratch:SI 4 "=c"))
+ (call:SI
+ (mem:QI (match_operand 2 "constant_call_address_operand" "z"))
+ (match_operand 3)))
+ (unspec:SI [(match_operand:SI 1 "register_operand" "b")]
+ UNSPEC_TLS_LD_BASE)
+ (clobber (match_scratch:SI 4 "=d"))
+ (clobber (match_scratch:SI 5 "=c"))
(clobber (reg:CC FLAGS_REG))]
"!TARGET_64BIT && TARGET_GNU_TLS"
{
@@ -12976,13 +12987,18 @@
(define_expand "tls_local_dynamic_base_32"
[(parallel
[(set (match_operand:SI 0 "register_operand")
- (unspec:SI
- [(match_operand:SI 1 "register_operand")
- (match_operand 2 "constant_call_address_operand")]
- UNSPEC_TLS_LD_BASE))
+ (call:SI
+ (mem:QI (match_operand 2 "constant_call_address_operand"))
+ (const_int 0)))
+ (unspec:SI [(match_operand:SI 1 "register_operand")]
+ UNSPEC_TLS_LD_BASE)
(clobber (match_scratch:SI 3))
(clobber (match_scratch:SI 4))
- (clobber (reg:CC FLAGS_REG))])])
+ (clobber (reg:CC FLAGS_REG))])]
+ ""
+{
+ ix86_tls_descriptor_calls_expanded_in_cfun = true;
+})
(define_insn "*tls_local_dynamic_base_64_<mode>"
[(set (match_operand:P 0 "register_operand" "=a")
@@ -13029,33 +13045,10 @@
(mem:QI (match_operand 1))
(const_int 0)))
(unspec:P [(const_int 0)] UNSPEC_TLS_LD_BASE)])]
- "TARGET_64BIT")
-
-;; Local dynamic of a single variable is a lose. Show combine how
-;; to convert that back to global dynamic.
-
-(define_insn_and_split "*tls_local_dynamic_32_once"
- [(set (match_operand:SI 0 "register_operand" "=a")
- (plus:SI
- (unspec:SI [(match_operand:SI 1 "register_operand" "b")
- (match_operand 2 "constant_call_address_operand" "z")]
- UNSPEC_TLS_LD_BASE)
- (const:SI (unspec:SI
- [(match_operand 3 "tls_symbolic_operand")]
- UNSPEC_DTPOFF))))
- (clobber (match_scratch:SI 4 "=d"))
- (clobber (match_scratch:SI 5 "=c"))
- (clobber (reg:CC FLAGS_REG))]
- ""
- "#"
- ""
- [(parallel
- [(set (match_dup 0)
- (unspec:SI [(match_dup 1) (match_dup 3) (match_dup 2)]
- UNSPEC_TLS_GD))
- (clobber (match_dup 4))
- (clobber (match_dup 5))
- (clobber (reg:CC FLAGS_REG))])])
+ "TARGET_64BIT"
+{
+ ix86_tls_descriptor_calls_expanded_in_cfun = true;
+})
;; Segment register for the thread base ptr load
(define_mode_attr tp_seg [(SI "gs") (DI "fs")])
