This is the updated patch of pr58066-3.patch.
The calls added in the templates of tls_local_dynamic_base_32 and
tls_global_dynamic_32 in pr58066-3.patch are used to prevent sched2
from moving sp setting across implicit tls calls, but those calls make
the combine of UNSPEC_TLS_LD_BASE and UNSPEC_DTPOFF difficult, so that
the optimization in tls_local_dynamic_32_once to convert local_dynamic
to global_dynamic mode for single tls reference cannot take effect. In
the updated patch, I remove those calls from insn templates and add
"reg:SI SP_REG" explicitly in the templates of UNSPEC_TLS_GD and
UNSPEC_TLS_LD_BASE. It solves the sched2 and combine problems above,
and now the optimization in tls_local_dynamic_32_once works.
bootstrapped ok on x86_64-linux-gnu. regression is going on. Is it OK
if regression passes?
Thanks.
Wei.
ChangeLog:
gcc/
2014-05-07 Wei Mi <w...@google.com>
* config/i386/i386.c (ix86_compute_frame_layout):
preferred_stack_boundary updated for tls expanded call.
* config/i386/i386.md: Set ix86_tls_descriptor_calls_expanded_in_cfun.
gcc/testsuite/
2014-05-07 Wei Mi <w...@google.com>
* gcc.target/i386/pr58066.c: New test.
Index: testsuite/gcc.target/i386/pr58066.c
===================================================================
--- testsuite/gcc.target/i386/pr58066.c (revision 0)
+++ testsuite/gcc.target/i386/pr58066.c (revision 0)
@@ -0,0 +1,18 @@
+/* { dg-do compile } */
+/* { dg-options "-fPIC -O2" } */
+
+/* Check whether the stack frame starting addresses of tls expanded calls
+ in foo and goo are 16bytes aligned. */
+static __thread char ccc1;
+void* foo()
+{
+ return &ccc1;
+}
+
+__thread char ccc2;
+void* goo()
+{
+ return &ccc2;
+}
+
+/* { dg-final { scan-assembler-times ".cfi_def_cfa_offset 16" 2 } } */
Index: config/i386/i386.c
===================================================================
--- config/i386/i386.c (revision 209979)
+++ config/i386/i386.c (working copy)
@@ -9485,20 +9485,30 @@ ix86_compute_frame_layout (struct ix86_f
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);
Index: config/i386/i386.md
===================================================================
--- config/i386/i386.md (revision 209979)
+++ config/i386/i386.md (working copy)
@@ -12530,7 +12530,8 @@
(unspec:SI
[(match_operand:SI 1 "register_operand" "b")
(match_operand 2 "tls_symbolic_operand")
- (match_operand 3 "constant_call_address_operand" "z")]
+ (match_operand 3 "constant_call_address_operand" "z")
+ (reg:SI SP_REG)]
UNSPEC_TLS_GD))
(clobber (match_scratch:SI 4 "=d"))
(clobber (match_scratch:SI 5 "=c"))
@@ -12555,11 +12556,14 @@
[(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")]
+ (match_operand 3 "constant_call_address_operand")
+ (reg:SI SP_REG)]
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")
@@ -12614,13 +12618,15 @@
(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")]
+ (match_operand 2 "constant_call_address_operand" "z")
+ (reg:SI SP_REG)]
UNSPEC_TLS_LD_BASE))
(clobber (match_scratch:SI 3 "=d"))
(clobber (match_scratch:SI 4 "=c"))
@@ -12646,11 +12652,14 @@
[(set (match_operand:SI 0 "register_operand")
(unspec:SI
[(match_operand:SI 1 "register_operand")
- (match_operand 2 "constant_call_address_operand")]
+ (match_operand 2 "constant_call_address_operand")
+ (reg:SI SP_REG)]
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")
@@ -12697,7 +12706,8 @@
(mem:QI (match_operand 1))
(const_int 0)))
(unspec:P [(const_int 0)] UNSPEC_TLS_LD_BASE)])]
- "TARGET_64BIT")
+ "TARGET_64BIT"
+ "ix86_tls_descriptor_calls_expanded_in_cfun = true;")
;; Local dynamic of a single variable is a lose. Show combine how
;; to convert that back to global dynamic.
@@ -12706,7 +12716,8 @@
[(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")]
+ (match_operand 2 "constant_call_address_operand" "z")
+ (reg:SI SP_REG)]
UNSPEC_TLS_LD_BASE)
(const:SI (unspec:SI
[(match_operand 3 "tls_symbolic_operand")]
@@ -12719,7 +12730,8 @@
""
[(parallel
[(set (match_dup 0)
- (unspec:SI [(match_dup 1) (match_dup 3) (match_dup 2)]
+ (unspec:SI [(match_dup 1) (match_dup 3) (match_dup 2)
+ (reg:SI SP_REG)]
UNSPEC_TLS_GD))
(clobber (match_dup 4))
(clobber (match_dup 5))
