With this patch, the LowerGC transformation becomes the

ShadowStackCollector, which additionally has reduced overhead with
no sacrifice in portability.

Considering a function @fun with 8 loop-local roots,
ShadowStackCollector introduces the following overhead
(x86):

; shadowstack prologue
        movl    L_llvm_gc_root_chain$non_lazy_ptr, %eax
        movl    (%eax), %ecx
        movl    $___gc_fun, 20(%esp)
        movl    $0, 24(%esp)
        movl    $0, 28(%esp)
        movl    $0, 32(%esp)
        movl    $0, 36(%esp)
        movl    $0, 40(%esp)
        movl    $0, 44(%esp)
        movl    $0, 48(%esp)
        movl    $0, 52(%esp)
        movl    %ecx, 16(%esp)
        leal    16(%esp), %ecx
        movl    %ecx, (%eax)

; shadowstack loop overhead
        (none)

; shadowstack epilogue
        movl    48(%esp), %edx
        movl    %edx, (%ecx)

; shadowstack metadata
        .align  3
___gc_fun:                              # __gc_fun
        .long   8
        .space  4

In comparison to LowerGC:

; lowergc prologue
        movl    L_llvm_gc_root_chain$non_lazy_ptr, %eax
        movl    (%eax), %ecx
        movl    %ecx, 48(%esp)
        movl    $8, 52(%esp)
        movl    $0, 60(%esp)
        movl    $0, 56(%esp)
        movl    $0, 68(%esp)
        movl    $0, 64(%esp)
        movl    $0, 76(%esp)
        movl    $0, 72(%esp)
        movl    $0, 84(%esp)
        movl    $0, 80(%esp)
        movl    $0, 92(%esp)
        movl    $0, 88(%esp)
        movl    $0, 100(%esp)
        movl    $0, 96(%esp)
        movl    $0, 108(%esp)
        movl    $0, 104(%esp)
        movl    $0, 116(%esp)
        movl    $0, 112(%esp)

; lowergc loop overhead
        leal    44(%esp), %eax
        movl    %eax, 56(%esp)
        leal    40(%esp), %eax
        movl    %eax, 64(%esp)
        leal    36(%esp), %eax
        movl    %eax, 72(%esp)
        leal    32(%esp), %eax
        movl    %eax, 80(%esp)
        leal    28(%esp), %eax
        movl    %eax, 88(%esp)
        leal    24(%esp), %eax
        movl    %eax, 96(%esp)
        leal    20(%esp), %eax
        movl    %eax, 104(%esp)
        leal    16(%esp), %eax
        movl    %eax, 112(%esp)

; lowergc epilogue
        movl    48(%esp), %edx
        movl    %edx, (%ecx)

; lowergc metadata
        (none)

llvm-svn: 45670

1 files changed, 17 insertions, 0 deletions

diff --git a/llvm/test/CodeGen/Generic/GC/redundant_init.ll b/llvm/test/CodeGen/Generic/GC/redundant_init.ll
new file mode 100644
index 00000000000..44996034748
--- /dev/null
+++ b/llvm/test/CodeGen/Generic/GC/redundant_init.ll
@@ -0,0 +1,17 @@
+; RUN: llvm-as < %s | llc -march=x86 | \
+; RUN:   ignore grep {movl..0} | count 0
+
+%struct.obj = type { i8*, %struct.obj* }
+
+declare void @g() gc "shadow-stack"
+
+define void @f(i8* %o) gc "shadow-stack" {
+entry:
+	%root = alloca i8*
+	call void @llvm.gcroot(i8** %root, i8* null)
+	store i8* %o, i8** %root
+	call void @g()
+	ret void
+}
+
+declare void @llvm.gcroot(i8**, i8*)