|
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index] [Xen-changelog] Add a shadow VRAM to track changes to the real VRAM. When the guest
# HG changeset patch
# User kaf24@xxxxxxxxxxxxxxxxxxxx
# Node ID 48211017a16af342fb9b8f9a03f69987d9bf74d5
# Parent a7b6eed7b0a66e28765a6801e3090b9b88cf8bbe
Add a shadow VRAM to track changes to the real VRAM. When the guest
OS was given write access to the VRAM the device model tracked all
VRAM changes by updating the entire screen on every output loop,
causing significant overhead (a CPU bound loop in a guest slows down
by about 35%) and significant mouse latency (VNC uses the same data
path for mouse events and video updates). With the shadow VRAM only
modified pages need to be updated and the comparison of the shadow
VRAM to the real VRAM only adds ~4% overhead while eliminating the
mouse latencies.
Signed-off-by: Don Dugger <donald.d.dugger@xxxxxxxxx>
diff -r a7b6eed7b0a6 -r 48211017a16a tools/ioemu/hw/vga.c
--- a/tools/ioemu/hw/vga.c Thu Mar 16 11:34:27 2006
+++ b/tools/ioemu/hw/vga.c Thu Mar 16 17:41:01 2006
@@ -1340,6 +1340,99 @@
}
}
+extern inline int cmp_vram(VGAState *s, int offset, int n)
+{
+ long *vp, *sp;
+
+ if (s->vram_shadow == NULL)
+ return 1;
+ vp = (long *)(s->vram_ptr + offset);
+ sp = (long *)(s->vram_shadow + offset);
+ while ((n -= sizeof(*vp)) >= 0) {
+ if (*vp++ != *sp++) {
+ memcpy(sp - 1, vp - 1, n + sizeof(*vp));
+ return 1;
+ }
+ }
+ return 0;
+}
+
+#ifdef USE_SSE2
+
+#include <signal.h>
+#include <setjmp.h>
+#include <emmintrin.h>
+
+int sse2_ok = 1;
+
+static inline unsigned int cpuid_edx(unsigned int op)
+{
+ unsigned int eax, edx;
+
+ __asm__("cpuid"
+ : "=a" (eax), "=d" (edx)
+ : "0" (op)
+ : "bx", "cx");
+
+ return edx;
+}
+
+jmp_buf sse_jbuf;
+
+void intr(int sig)
+{
+ sse2_ok = 0;
+ longjmp(sse_jbuf, 1);
+}
+
+void check_sse2(void)
+{
+ /* Check 1: What does CPUID say? */
+ if ((cpuid_edx(1) & 0x4000000) == 0) {
+ sse2_ok = 0;
+ return;
+ }
+
+ /* Check 2: Can we use SSE2 in anger? */
+ signal(SIGILL, intr);
+ if (setjmp(sse_jbuf) == 0)
+ __asm__("xorps %xmm0,%xmm0\n");
+}
+
+int vram_dirty(VGAState *s, int offset, int n)
+{
+ __m128i *sp, *vp;
+
+ if (s->vram_shadow == NULL)
+ return 1;
+ if (sse2_ok == 0)
+ return cmp_vram(s, offset, n);
+ vp = (__m128i *)(s->vram_ptr + offset);
+ sp = (__m128i *)(s->vram_shadow + offset);
+ while ((n -= sizeof(*vp)) >= 0) {
+ if (_mm_movemask_epi8(_mm_cmpeq_epi8(*sp, *vp)) != 0xffff) {
+ while (n >= 0) {
+ _mm_store_si128(sp++, _mm_load_si128(vp++));
+ n -= sizeof(*vp);
+ }
+ return 1;
+ }
+ sp++;
+ vp++;
+ }
+ return 0;
+}
+#else /* !USE_SSE2 */
+int vram_dirty(VGAState *s, int offset, int n)
+{
+ return cmp_vram(s, offset, n);
+}
+
+void check_sse2(void)
+{
+}
+#endif /* !USE_SSE2 */
+
/*
* graphic modes
*/
@@ -1434,6 +1527,9 @@
printf("w=%d h=%d v=%d line_offset=%d cr[0x09]=0x%02x cr[0x17]=0x%02x
linecmp=%d sr[0x01]=0x%02x\n",
width, height, v, line_offset, s->cr[9], s->cr[0x17],
s->line_compare, s->sr[0x01]);
#endif
+ for (y = 0; y < s->vram_size; y += TARGET_PAGE_SIZE)
+ if (vram_dirty(s, y, TARGET_PAGE_SIZE))
+ cpu_physical_memory_set_dirty(s->vram_offset + y);
addr1 = (s->start_addr * 4);
bwidth = width * 4;
y_start = -1;
@@ -1536,8 +1632,17 @@
void vga_update_display(void)
{
+ static int loop;
VGAState *s = vga_state;
int full_update, graphic_mode;
+
+ /*
+ * Only update the display every other time. The responsiveness is
+ * acceptable and it cuts down on the overhead of the VRAM compare
+ * in `vram_dirty'.
+ */
+ if (loop++ & 1)
+ return;
if (s->ds->depth == 0) {
/* nothing to do */
@@ -1569,7 +1674,6 @@
full_update = 1;
}
- full_update = 1;
switch(graphic_mode) {
case GMODE_TEXT:
vga_draw_text(s, full_update);
@@ -1874,7 +1978,13 @@
#else
s->vram_ptr = qemu_malloc(vga_ram_size);
#endif
-
+ check_sse2();
+ s->vram_shadow = qemu_malloc(vga_ram_size+TARGET_PAGE_SIZE+1);
+ if (s->vram_shadow == NULL)
+ fprintf(stderr, "Cannot allocate %d bytes for VRAM shadow, "
+ "mouse will be slow\n", vga_ram_size);
+ s->vram_shadow = (uint8_t *)((long)(s->vram_shadow + TARGET_PAGE_SIZE - 1)
+ & ~(TARGET_PAGE_SIZE - 1));
s->vram_offset = vga_ram_offset;
s->vram_size = vga_ram_size;
s->ds = ds;
diff -r a7b6eed7b0a6 -r 48211017a16a tools/ioemu/hw/vga_int.h
--- a/tools/ioemu/hw/vga_int.h Thu Mar 16 11:34:27 2006
+++ b/tools/ioemu/hw/vga_int.h Thu Mar 16 17:41:01 2006
@@ -76,6 +76,7 @@
#define VGA_STATE_COMMON \
uint8_t *vram_ptr; \
+ uint8_t *vram_shadow; \
unsigned long vram_offset; \
unsigned int vram_size; \
uint32_t latch; \
diff -r a7b6eed7b0a6 -r 48211017a16a tools/ioemu/target-i386-dm/Makefile
--- a/tools/ioemu/target-i386-dm/Makefile Thu Mar 16 11:34:27 2006
+++ b/tools/ioemu/target-i386-dm/Makefile Thu Mar 16 17:41:01 2006
@@ -13,8 +13,15 @@
VPATH+=:$(SRC_PATH)/linux-user
DEFINES+=-I$(SRC_PATH)/linux-user -I$(SRC_PATH)/linux-user/$(TARGET_ARCH)
endif
-CFLAGS+=-g -fno-strict-aliasing
-LDFLAGS=-g
+
+SSE2 := $(call test-gcc-flag,$(CC),-msse2)
+ifeq ($(SSE2),-msse2)
+CFLAGS += -DUSE_SSE2=1 -msse2
+endif
+
+CFLAGS += -g -fno-strict-aliasing $(LOCAL_CFLAGS)
+LDFLAGS = -g
+
LIBS=
HELPER_CFLAGS=$(CFLAGS)
DYNGEN=../dyngen$(EXESUF)
_______________________________________________
Xen-changelog mailing list
Xen-changelog@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-changelog
|
 |
Lists.xenproject.org is hosted with RackSpace, monitoring our |