tcg: use tcg_debug_assert instead of assert (fix performance regression)

The TCG code is quite performance sensitive, but at the same time can
also be quite tricky. That is why asserts that can be enabled with the
--enable-debug-tcg configure option.

This used to work the following way:

| #include "config.h"
|
| ...
|
| #if !defined(CONFIG_DEBUG_TCG) && !defined(NDEBUG)
| /* define it to suppress various consistency checks (faster) */
| #define NDEBUG
| #endif
|
| ...
|
| #include <assert.h>

Since commit 757e725b (tcg: Clean up includes) "config.h" as been
replaced by "qemu/osdep.h" which itself includes <assert.h>. As a
consequence the assertions are always enabled, even when using
--disable-debug-tcg, causing a performance regression, especially on
targets with many registers. For instance on qemu-system-ppc the
speed difference is about 15%.

tcg_debug_assert is controlled directly by CONFIG_DEBUG_TCG and already
uses in some places. This patch replaces all the calls to assert into
calss to tcg_debug_assert.

Cc: Peter Maydell <peter.maydell@linaro.org>
Cc: Richard Henderson <rth@twiddle.net>
Signed-off-by: Aurelien Jarno <aurelien@aurel32.net>
Message-id: 1461228530-14852-1-git-send-email-aurelien@aurel32.net
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

1 files changed, 4 insertions, 4 deletions

diff --git a/tcg/sparc/tcg-target.inc.c b/tcg/sparc/tcg-target.inc.c
index 54df1bc..d64daba 100644
--- a/tcg/sparc/tcg-target.inc.c
+++ b/tcg/sparc/tcg-target.inc.c
@@ -289,7 +289,7 @@ static void patch_reloc(tcg_insn_unit *code_ptr, int type,
 {
     uint32_t insn;
 
-    assert(addend == 0);
+    tcg_debug_assert(addend == 0);
     value = tcg_ptr_byte_diff((tcg_insn_unit *)value, code_ptr);
 
     switch (type) {
@@ -1108,7 +1108,7 @@ static void tcg_out_qemu_ld(TCGContext *s, TCGReg data, TCGReg addr,
     } else {
         func = qemu_ld_trampoline[memop & (MO_BSWAP | MO_SSIZE)];
     }
-    assert(func != NULL);
+    tcg_debug_assert(func != NULL);
     tcg_out_call_nodelay(s, func);
     /* delay slot */
     tcg_out_movi(s, TCG_TYPE_I32, param, oi);
@@ -1187,7 +1187,7 @@ static void tcg_out_qemu_st(TCGContext *s, TCGReg data, TCGReg addr,
     tcg_out_mov(s, TCG_TYPE_REG, param++, data);
 
     func = qemu_st_trampoline[memop & (MO_BSWAP | MO_SIZE)];
-    assert(func != NULL);
+    tcg_debug_assert(func != NULL);
     tcg_out_call_nodelay(s, func);
     /* delay slot */
     tcg_out_movi(s, TCG_TYPE_I32, param, oi);
@@ -1645,7 +1645,7 @@ void tb_set_jmp_target1(uintptr_t jmp_addr, uintptr_t addr)
 
     /* We can reach the entire address space for 32-bit.  For 64-bit
        the code_gen_buffer can't be larger than 2GB.  */
-    assert(disp == (int32_t)disp);
+    tcg_debug_assert(disp == (int32_t)disp);
 
     *ptr = CALL | (uint32_t)disp >> 2;
     flush_icache_range(jmp_addr, jmp_addr + 4);