[PATCH v2 6/7] sm501: Optimize small overlapping blits

[BALATON Zoltan <balaton@eik.bme.hu>]

AmigaOS tends to do a lot of small blits (even 1 pixel). Avoid malloc
overhead by keeping around a buffer for this and only alloc when
blitting larger areas.

Signed-off-by: BALATON Zoltan <balaton@eik.bme.hu>
---
 hw/display/sm501.c | 15 +++++++++++----
 1 file changed, 11 insertions(+), 4 deletions(-)

diff --git a/hw/display/sm501.c b/hw/display/sm501.c
index 8bf4d111f4..e7a9f77de7 100644
--- a/hw/display/sm501.c
+++ b/hw/display/sm501.c
@@ -750,6 +750,7 @@ static void sm501_2d_operation(SM501State *s)
     switch (cmd) {
     case 0: /* BitBlt */
     {
+        static uint32_t tmp_buf[16384];
         unsigned int src_x = (s->twoD_source >> 16) & 0x01FFF;
         unsigned int src_y = s->twoD_source & 0xFFFF;
         uint32_t src_base = s->twoD_source_base & 0x03FFFFFF;
@@ -812,10 +813,14 @@ static void sm501_2d_operation(SM501State *s)
             de = db + width + height * (width + dst_pitch);
             if (rtl && ((db >= sb && db <= se) || (de >= sb && de <= se))) {
                 /* regions may overlap: copy via temporary */
-                int llb = width * (1 << format);
+                int free_buf = 0, llb = width * (1 << format);
                 int tmp_stride = DIV_ROUND_UP(llb, sizeof(uint32_t));
-                uint32_t *tmp = g_malloc(tmp_stride * sizeof(uint32_t) *
-                                         height);
+                uint32_t *tmp = tmp_buf;
+
+                if (tmp_stride * sizeof(uint32_t) * height > sizeof(tmp_buf)) {
+                    tmp = g_malloc(tmp_stride * sizeof(uint32_t) * height);
+                    free_buf = 1;
+                }
                 pixman_blt((uint32_t *)&s->local_mem[src_base], tmp,
                            src_pitch * (1 << format) / sizeof(uint32_t),
                            tmp_stride, 8 * (1 << format), 8 * (1 << format),
@@ -825,7 +830,9 @@ static void sm501_2d_operation(SM501State *s)
                            dst_pitch * (1 << format) / sizeof(uint32_t),
                            8 * (1 << format), 8 * (1 << format),
                            0, 0, dst_x, dst_y, width, height);
-                g_free(tmp);
+                if (free_buf) {
+                    g_free(tmp);
+                }
             } else {
                 pixman_blt((uint32_t *)&s->local_mem[src_base],
                            (uint32_t *)&s->local_mem[dst_base],
-- 
2.21.3