Hi,
As PR111380 (and the discussion in related PRs) shows, for
now how function rs6000_can_inline_p treats the callee
without any target option node is wrong. It considers it's
always safe to inline this kind of callee, but actually its
target flags are from the command line options
(target_option_default_node), it's possible that the flags
of callee don't satisfy the condition of inlining, but it
is still inlined, then result in unexpected consequence.
As the associated test case pr111380-1.c shows, the caller
main is attributed with power8, but the callee foo is
compiled with power9 from command line, it's unexpected to
make main inline foo since foo can contain something that
requires power9 capability. Without this patch, for lto
(with -flto) we can get error message (as it forces the
callee to have a target option node), but for non-lto, it's
inlined unexpectedly.
This patch is to make callee adopt target_option_default_node
when it doesn't have a target option node, it can avoid wrong
inlining decision and fix the inconsistency between LTO and
non-LTO. It also aligns with what the other ports do.
Bootstrapped and regtested on powerpc64-linux-gnu P7/P8/P9
and powerpc64le-linux-gnu P9 and P10.
I'm going to push this soon if no objections.
BR,
Kewen
-----
PR target/111380
gcc/ChangeLog:
* config/rs6000/rs6000.cc (rs6000_can_inline_p): Adopt
target_option_default_node when the callee has no option
attributes, also simplify the existing code accordingly.
gcc/testsuite/ChangeLog:
* gcc.target/powerpc/pr111380-1.c: New test.
* gcc.target/powerpc/pr111380-2.c: New test.
---
gcc/config/rs6000/rs6000.cc | 65 +++++++++----------
gcc/testsuite/gcc.target/powerpc/pr111380-1.c | 20 ++++++
gcc/testsuite/gcc.target/powerpc/pr111380-2.c | 20 ++++++
3 files changed, 70 insertions(+), 35 deletions(-)
create mode 100644 gcc/testsuite/gcc.target/powerpc/pr111380-1.c
create mode 100644 gcc/testsuite/gcc.target/powerpc/pr111380-2.c
diff --git a/gcc/config/rs6000/rs6000.cc b/gcc/config/rs6000/rs6000.cc
index efe9adce1f8..d48134b35f8 100644
--- a/gcc/config/rs6000/rs6000.cc
+++ b/gcc/config/rs6000/rs6000.cc
@@ -25508,49 +25508,44 @@ rs6000_can_inline_p (tree caller, tree callee)
tree caller_tree = DECL_FUNCTION_SPECIFIC_TARGET (caller);
tree callee_tree = DECL_FUNCTION_SPECIFIC_TARGET (callee);
- /* If the callee has no option attributes, then it is ok to inline. */
+ /* If the caller/callee has option attributes, then use them.
+ Otherwise, use the command line options. */
if (!callee_tree)
- ret = true;
+ callee_tree = target_option_default_node;
+ if (!caller_tree)
+ caller_tree = target_option_default_node;
- else
- {
- HOST_WIDE_INT caller_isa;
- struct cl_target_option *callee_opts = TREE_TARGET_OPTION (callee_tree);
- HOST_WIDE_INT callee_isa = callee_opts->x_rs6000_isa_flags;
- HOST_WIDE_INT explicit_isa = callee_opts->x_rs6000_isa_flags_explicit;
+ struct cl_target_option *callee_opts = TREE_TARGET_OPTION (callee_tree);
+ struct cl_target_option *caller_opts = TREE_TARGET_OPTION (caller_tree);
- /* If the caller has option attributes, then use them.
- Otherwise, use the command line options. */
- if (caller_tree)
- caller_isa = TREE_TARGET_OPTION (caller_tree)->x_rs6000_isa_flags;
- else
- caller_isa = rs6000_isa_flags;
+ HOST_WIDE_INT callee_isa = callee_opts->x_rs6000_isa_flags;
+ HOST_WIDE_INT caller_isa = caller_opts->x_rs6000_isa_flags;
+ HOST_WIDE_INT explicit_isa = callee_opts->x_rs6000_isa_flags_explicit;
- cgraph_node *callee_node = cgraph_node::get (callee);
- if (ipa_fn_summaries && ipa_fn_summaries->get (callee_node) != NULL)
+ cgraph_node *callee_node = cgraph_node::get (callee);
+ if (ipa_fn_summaries && ipa_fn_summaries->get (callee_node) != NULL)
+ {
+ unsigned int info = ipa_fn_summaries->get (callee_node)->target_info;
+ if ((info & RS6000_FN_TARGET_INFO_HTM) == 0)
{
- unsigned int info = ipa_fn_summaries->get (callee_node)->target_info;
- if ((info & RS6000_FN_TARGET_INFO_HTM) == 0)
- {
- callee_isa &= ~OPTION_MASK_HTM;
- explicit_isa &= ~OPTION_MASK_HTM;
- }
+ callee_isa &= ~OPTION_MASK_HTM;
+ explicit_isa &= ~OPTION_MASK_HTM;
}
+ }
- /* Ignore -mpower8-fusion and -mpower10-fusion options for inlining
- purposes. */
- callee_isa &= ~(OPTION_MASK_P8_FUSION | OPTION_MASK_P10_FUSION);
- explicit_isa &= ~(OPTION_MASK_P8_FUSION | OPTION_MASK_P10_FUSION);
+ /* Ignore -mpower8-fusion and -mpower10-fusion options for inlining
+ purposes. */
+ callee_isa &= ~(OPTION_MASK_P8_FUSION | OPTION_MASK_P10_FUSION);
+ explicit_isa &= ~(OPTION_MASK_P8_FUSION | OPTION_MASK_P10_FUSION);
- /* The callee's options must be a subset of the caller's options, i.e.
- a vsx function may inline an altivec function, but a no-vsx function
- must not inline a vsx function. However, for those options that the
- callee has explicitly enabled or disabled, then we must enforce that
- the callee's and caller's options match exactly; see PR70010. */
- if (((caller_isa & callee_isa) == callee_isa)
- && (caller_isa & explicit_isa) == (callee_isa & explicit_isa))
- ret = true;
- }
+ /* The callee's options must be a subset of the caller's options, i.e.
+ a vsx function may inline an altivec function, but a no-vsx function
+ must not inline a vsx function. However, for those options that the
+ callee has explicitly enabled or disabled, then we must enforce that
+ the callee's and caller's options match exactly; see PR70010. */
+ if (((caller_isa & callee_isa) == callee_isa)
+ && (caller_isa & explicit_isa) == (callee_isa & explicit_isa))
+ ret = true;
if (TARGET_DEBUG_TARGET)
fprintf (stderr, "rs6000_can_inline_p:, caller %s, callee %s, %s inline\n",
diff --git a/gcc/testsuite/gcc.target/powerpc/pr111380-1.c
b/gcc/testsuite/gcc.target/powerpc/pr111380-1.c
new file mode 100644
index 00000000000..57ae75ef73a
--- /dev/null
+++ b/gcc/testsuite/gcc.target/powerpc/pr111380-1.c
@@ -0,0 +1,20 @@
+/* { dg-do compile } */
+/* { dg-require-effective-target vect_int } */
+/* { dg-options "-O2 -mdejagnu-cpu=power9" } */
+
+/* Verify it emits error message on inlining even without LTO. */
+
+vector int c, a, b;
+
+static inline void __attribute__ ((__always_inline__))
+foo () /* { dg-error "inlining failed in call to .* target specific option
mismatch" } */
+{
+ c = a + b;
+}
+
+__attribute__ ((target ("cpu=power8")))
+int main ()
+{
+ foo (); /* { dg-message "called from here" } */
+ c = a + b;
+}
diff --git a/gcc/testsuite/gcc.target/powerpc/pr111380-2.c
b/gcc/testsuite/gcc.target/powerpc/pr111380-2.c
new file mode 100644
index 00000000000..7b363940643
--- /dev/null
+++ b/gcc/testsuite/gcc.target/powerpc/pr111380-2.c
@@ -0,0 +1,20 @@
+/* { dg-do compile } */
+/* { dg-require-effective-target vect_int } */
+/* { dg-options "-O2 -mno-vsx" } */
+
+/* Verify it emits error message on inlining even without LTO. */
+
+vector int c, a, b;
+
+static inline void __attribute__ ((__always_inline__))
+foo () /* { dg-error "inlining failed in call to .* target specific option
mismatch" } */
+{
+ c = a + b;
+}
+
+__attribute__ ((target ("vsx")))
+int main ()
+{
+ foo (); /* { dg-message "called from here" } */
+ c = a + b;
+}
--
2.31.1
