[X86] Reapply r240257 : "Allow more call sequences to use push instructions for argument passing"

This allows more call sequences to use pushes instead of movs when optimizing for size.
In particular, calling conventions that pass some parameters in registers (e.g. thiscall) are now supported.

This should no longer cause miscompiles, now that a bug in emitPrologue was fixed in r242395.

llvm-svn: 242398

1 files changed, 53 insertions, 40 deletions

diff --git a/llvm/test/CodeGen/X86/movtopush.ll b/llvm/test/CodeGen/X86/movtopush.ll
index f89e52457f3..b02f9ec45e7 100644
--- a/llvm/test/CodeGen/X86/movtopush.ll
+++ b/llvm/test/CodeGen/X86/movtopush.ll
@@ -2,11 +2,15 @@
 ; RUN: llc < %s -mtriple=x86_64-windows | FileCheck %s -check-prefix=X64
 ; RUN: llc < %s -mtriple=i686-windows -force-align-stack -stack-alignment=32 | FileCheck %s -check-prefix=ALIGNED 
 
+%class.Class = type { i32 }
+%struct.s = type { i64 }
+
 declare void @good(i32 %a, i32 %b, i32 %c, i32 %d)
 declare void @inreg(i32 %a, i32 inreg %b, i32 %c, i32 %d)
+declare x86_thiscallcc void @thiscall(%class.Class* %class, i32 %a, i32 %b, i32 %c, i32 %d)
 declare void @oneparam(i32 %a)
 declare void @eightparams(i32 %a, i32 %b, i32 %c, i32 %d, i32 %e, i32 %f, i32 %g, i32 %h)
-
+declare void @struct(%struct.s* byval %a, i32 %b, i32 %c, i32 %d)
 
 ; Here, we should have a reserved frame, so we don't expect pushes
 ; NORMAL-LABEL: test1:
@@ -108,13 +112,12 @@ entry:
   ret void
 }
 
-; We don't support weird calling conventions
+; We support weird calling conventions
 ; NORMAL-LABEL: test4:
-; NORMAL: subl    $12, %esp
-; NORMAL-NEXT: movl    $4, 8(%esp)
-; NORMAL-NEXT: movl    $3, 4(%esp)
-; NORMAL-NEXT: movl    $1, (%esp)
-; NORMAL-NEXT: movl    $2, %eax
+; NORMAL: movl    $2, %eax
+; NORMAL-NEXT: pushl   $4
+; NORMAL-NEXT: pushl   $3
+; NORMAL-NEXT: pushl   $1
 ; NORMAL-NEXT: call
 ; NORMAL-NEXT: addl $12, %esp
 define void @test4() optsize {
@@ -123,6 +126,20 @@ entry:
   ret void
 }
 
+; NORMAL-LABEL: test4b:
+; NORMAL: movl 4(%esp), %ecx
+; NORMAL-NEXT: pushl   $4
+; NORMAL-NEXT: pushl   $3
+; NORMAL-NEXT: pushl   $2
+; NORMAL-NEXT: pushl   $1
+; NORMAL-NEXT: call
+; NORMAL-NEXT: ret
+define void @test4b(%class.Class* %f) optsize {
+entry:
+  call x86_thiscallcc void @thiscall(%class.Class* %f, i32 1, i32 2, i32 3, i32 4)
+  ret void
+}
+
 ; When there is no reserved call frame, check that additional alignment
 ; is added when the pushes don't add up to the required alignment.
 ; ALIGNED-LABEL: test5:
@@ -229,20 +246,27 @@ entry:
 ; NORMAL-NEXT: pushl $1
 ; NORMAL-NEXT: call
 ; NORMAL-NEXT: addl $16, %esp
-; NORMAL-NEXT: subl $16, %esp
-; NORMAL-NEXT: leal 16(%esp), [[EAX:%e..]]
-; NORMAL-NEXT: movl    [[EAX]], 12(%esp)
-; NORMAL-NEXT: movl    $7, 8(%esp)
-; NORMAL-NEXT: movl    $6, 4(%esp)
-; NORMAL-NEXT: movl    $5, (%esp)
+; NORMAL-NEXT: subl $20, %esp
+; NORMAL-NEXT: movl 20(%esp), [[E1:%e..]]
+; NORMAL-NEXT: movl 24(%esp), [[E2:%e..]]
+; NORMAL-NEXT: movl    [[E2]], 4(%esp)
+; NORMAL-NEXT: movl    [[E1]], (%esp)
+; NORMAL-NEXT: leal 32(%esp), [[E3:%e..]]
+; NORMAL-NEXT: movl    [[E3]], 16(%esp)
+; NORMAL-NEXT: leal 28(%esp), [[E4:%e..]]
+; NORMAL-NEXT: movl    [[E4]], 12(%esp)
+; NORMAL-NEXT: movl    $6, 8(%esp)
 ; NORMAL-NEXT: call
-; NORMAL-NEXT: addl $16, %esp
+; NORMAL-NEXT: addl $20, %esp
 define void @test9() optsize {
 entry:
   %p = alloca i32, align 4
+  %q = alloca i32, align 4
+  %s = alloca %struct.s, align 4  
   call void @good(i32 1, i32 2, i32 3, i32 4)
-  %0 = ptrtoint i32* %p to i32
-  call void @good(i32 5, i32 6, i32 7, i32 %0)
+  %pv = ptrtoint i32* %p to i32
+  %qv = ptrtoint i32* %q to i32
+  call void @struct(%struct.s* byval %s, i32 6, i32 %qv, i32 %pv)
   ret void
 }
 
@@ -291,28 +315,17 @@ define void @test11() optsize {
 ; Converting one mov into a push isn't worth it when 
 ; doing so forces too much overhead for other calls.
 ; NORMAL-LABEL: test12:
-; NORMAL: subl    $16, %esp
-; NORMAL-NEXT: movl    $4, 8(%esp)
-; NORMAL-NEXT: movl    $3, 4(%esp)
-; NORMAL-NEXT: movl    $1, (%esp)
-; NORMAL-NEXT: movl    $2, %eax
-; NORMAL-NEXT: calll _inreg
-; NORMAL-NEXT: movl    $8, 12(%esp)
+; NORMAL: movl    $8, 12(%esp)
 ; NORMAL-NEXT: movl    $7, 8(%esp)
 ; NORMAL-NEXT: movl    $6, 4(%esp)
 ; NORMAL-NEXT: movl    $5, (%esp)
 ; NORMAL-NEXT: calll _good
-; NORMAL-NEXT: movl    $12, 8(%esp)
-; NORMAL-NEXT: movl    $11, 4(%esp)
-; NORMAL-NEXT: movl    $9, (%esp)
-; NORMAL-NEXT: movl    $10, %eax
-; NORMAL-NEXT: calll _inreg
-; NORMAL-NEXT: addl $16, %esp
 define void @test12() optsize {
 entry:
-  call void @inreg(i32 1, i32 2, i32 3, i32 4)
+  %s = alloca %struct.s, align 4  
+  call void @struct(%struct.s* %s, i32 2, i32 3, i32 4)
   call void @good(i32 5, i32 6, i32 7, i32 8)
-  call void @inreg(i32 9, i32 10, i32 11, i32 12)
+  call void @struct(%struct.s* %s, i32 10, i32 11, i32 12)
   ret void
 }
 
@@ -324,13 +337,12 @@ entry:
 ; NORMAL-NEXT: pushl    $1
 ; NORMAL-NEXT: calll _good
 ; NORMAL-NEXT: addl    $16, %esp
-; NORMAL-NEXT: subl    $12, %esp
-; NORMAL-NEXT: movl    $8, 8(%esp)
-; NORMAL-NEXT: movl    $7, 4(%esp)
-; NORMAL-NEXT: movl    $5, (%esp)
-; NORMAL-NEXT: movl    $6, %eax
-; NORMAL-NEXT: calll _inreg
-; NORMAL-NEXT: addl    $12, %esp
+; NORMAL-NEXT: subl    $20, %esp
+; NORMAL: movl    $8, 16(%esp)
+; NORMAL-NEXT: movl    $7, 12(%esp)
+; NORMAL-NEXT: movl    $6, 8(%esp)
+; NORMAL-NEXT: calll _struct
+; NORMAL-NEXT: addl    $20, %esp
 ; NORMAL-NEXT: pushl    $12
 ; NORMAL-NEXT: pushl    $11
 ; NORMAL-NEXT: pushl    $10
@@ -339,8 +351,9 @@ entry:
 ; NORMAL-NEXT: addl $16, %esp
 define void @test12b() optsize {
 entry:
-  call void @good(i32 1, i32 2, i32 3, i32 4)
-  call void @inreg(i32 5, i32 6, i32 7, i32 8)
+  %s = alloca %struct.s, align 4  
+  call void @good(i32 1, i32 2, i32 3, i32 4)  
+  call void @struct(%struct.s* %s, i32 6, i32 7, i32 8)
   call void @good(i32 9, i32 10, i32 11, i32 12)
   ret void
 }