From 17419b61edd350147b0cc10c3da0b8461e51a42c Mon Sep 17 00:00:00 2001 From: Roger Sayle Date: Fri, 1 Jul 2022 09:18:07 +0100 Subject: [PATCH] PR target/106122: Don't update %esp via the stack with -Oz on x86. When optimizing for size with -Oz, setting a register can be minimized by pushing an immediate value to the stack and popping it to the destination. Alas the one general register that shouldn't be updated via the stack is the stack pointer itself, where "pop %esp" can't be represented in GCC's RTL ("use of a register mentioned in pre_inc, pre_dec, post_inc or post_dec is not permitted within the same instruction"). This patch fixes PR target/106122 by explicitly checking for SP_REG in the problematic peephole2. 2022-07-01 Roger Sayle gcc/ChangeLog PR target/106122 * config/i386/i386.md (peephole2): Avoid generating pop %esp when optimizing for size. gcc/testsuite/ChangeLog PR target/106122 * gcc.target/i386/pr106122.c: New test case. --- gcc/config/i386/i386.md | 3 ++- gcc/testsuite/gcc.target/i386/pr106122.c | 15 +++++++++++++++ 2 files changed, 17 insertions(+), 1 deletion(-) create mode 100644 gcc/testsuite/gcc.target/i386/pr106122.c diff --git a/gcc/config/i386/i386.md b/gcc/config/i386/i386.md index 646a556a8117..34018144e5fd 100644 --- a/gcc/config/i386/i386.md +++ b/gcc/config/i386/i386.md @@ -2589,7 +2589,8 @@ "optimize_insn_for_size_p () && optimize_size > 1 && operands[1] != const0_rtx && IN_RANGE (INTVAL (operands[1]), -128, 127) - && !ix86_red_zone_used" + && !ix86_red_zone_used + && REGNO (operands[0]) != SP_REG" [(set (match_dup 2) (match_dup 1)) (set (match_dup 0) (match_dup 3))] { diff --git a/gcc/testsuite/gcc.target/i386/pr106122.c b/gcc/testsuite/gcc.target/i386/pr106122.c new file mode 100644 index 000000000000..7d24ed3376dd --- /dev/null +++ b/gcc/testsuite/gcc.target/i386/pr106122.c @@ -0,0 +1,15 @@ +/* PR middle-end/106122 */ +/* { dg-do compile } */ +/* { dg-options "-Oz" } */ + +register volatile int a __asm__("%esp"); +void foo (void *); +void bar (void *); + +void +baz (void) +{ + foo (__builtin_return_address (0)); + a = 0; + bar (__builtin_return_address (0)); +} -- 2.47.2