[Qemu-devel] [PATCH] vga optimization.

[Glauber Costa <glommer@redhat.com>]

Hypervisors like KVM perform badly while doing mmio on
a loop, because it'll generate an exit on each access.
This is the case with VGA, which results in very bad
performance.

In this patch, we map the linear frame buffer as RAM,
make sure it has dirty region tracking enabled, and then
just let the region to be written.

Cleanups suggestions by:
  Stefano Stabellini <stefano.stabellini@eu.citrix.com>

Signed-off-by: Glauber Costa <glommer@redhat.com>
---
 cpu-all.h       |    2 ++
 exec.c          |    6 ++++++
 hw/cirrus_vga.c |   43 +++++++++++++++++++++++++++++++++++++++++++
 hw/vga.c        |   25 +++++++++++++++++++++++++
 hw/vga_int.h    |   10 +++++++++-
 5 files changed, 85 insertions(+), 1 deletions(-)

diff --git a/cpu-all.h b/cpu-all.h
index cdd79bc..6e12847 100644
--- a/cpu-all.h
+++ b/cpu-all.h
@@ -934,6 +934,8 @@ int cpu_physical_memory_set_dirty_tracking(int enable);
 
 int cpu_physical_memory_get_dirty_tracking(void);
 
+void cpu_physical_sync_dirty_bitmap(ram_addr_t start_addr, ram_addr_t end_addr);
+
 void dump_exec_info(FILE *f,
                     int (*cpu_fprintf)(FILE *f, const char *fmt, ...));
 
diff --git a/exec.c b/exec.c
index ef1072b..975099a 100644
--- a/exec.c
+++ b/exec.c
@@ -1823,6 +1823,12 @@ int cpu_physical_memory_get_dirty_tracking(void)
     return in_migration;
 }
 
+void cpu_physical_sync_dirty_bitmap(ram_addr_t start_addr, ram_addr_t end_addr)
+{
+    if (kvm_enabled())
+        kvm_physical_sync_dirty_bitmap(start_addr, end_addr);
+}
+
 static inline void tlb_update_dirty(CPUTLBEntry *tlb_entry)
 {
     ram_addr_t ram_addr;
diff --git a/hw/cirrus_vga.c b/hw/cirrus_vga.c
index 6b407ef..63983ba 100644
--- a/hw/cirrus_vga.c
+++ b/hw/cirrus_vga.c
@@ -31,6 +31,7 @@
 #include "pci.h"
 #include "console.h"
 #include "vga_int.h"
+#include "kvm.h"
 
 /*
  * TODO:
@@ -2619,6 +2620,39 @@ static CPUWriteMemoryFunc *cirrus_linear_bitblt_write[3] = {
     cirrus_linear_bitblt_writel,
 };
 
+static void map_linear_vram(CirrusVGAState *s)
+{
+    int phys_offset = s->vga_io_memory;
+
+    if (!s->map_addr && s->lfb_addr && s->lfb_end) {
+        s->map_addr = s->lfb_addr;
+        s->map_end = s->lfb_end;
+        cpu_register_physical_memory(s->map_addr, s->map_end - s->map_addr, s->vram_offset);
+        vga_dirty_log_start((VGAState *)s);
+    }
+    
+    if(!(s->cirrus_srcptr != s->cirrus_srcptr_end)
+        && !((s->sr[0x07] & 0x01) == 0)
+        && !((s->gr[0x0B] & 0x14) == 0x14)
+        && !(s->gr[0x0B] & 0x02)) {
+        phys_offset = s->vram_offset | IO_MEM_RAM;
+    }
+    cpu_register_physical_memory(isa_mem_base + 0xa0000, 0x20000, phys_offset);
+}
+
+static void unmap_linear_vram(CirrusVGAState *s)
+{
+
+    if (s->map_addr && s->lfb_addr && s->lfb_end) {
+        vga_dirty_log_stop((VGAState *)s);
+        s->map_addr = s->map_end = 0;
+    }
+
+    cpu_register_physical_memory(isa_mem_base + 0x000a0000, 0x20000,
+                                 s->vga_io_memory);
+
+}
+
 /* Compute the memory access functions */
 static void cirrus_update_memory_access(CirrusVGAState *s)
 {
@@ -2637,11 +2671,13 @@ static void cirrus_update_memory_access(CirrusVGAState *s)
 
 	mode = s->gr[0x05] & 0x7;
 	if (mode < 4 || mode > 5 || ((s->gr[0x0B] & 0x4) == 0)) {
+            map_linear_vram(s);
             s->cirrus_linear_write[0] = cirrus_linear_mem_writeb;
             s->cirrus_linear_write[1] = cirrus_linear_mem_writew;
             s->cirrus_linear_write[2] = cirrus_linear_mem_writel;
         } else {
         generic_io:
+            unmap_linear_vram(s);
             s->cirrus_linear_write[0] = cirrus_linear_writeb;
             s->cirrus_linear_write[1] = cirrus_linear_writew;
             s->cirrus_linear_write[2] = cirrus_linear_writel;
@@ -3262,6 +3298,13 @@ static void cirrus_pci_lfb_map(PCIDevice *d, int region_num,
 				 s->cirrus_linear_io_addr);
     cpu_register_physical_memory(addr + 0x1000000, 0x400000,
 				 s->cirrus_linear_bitblt_io_addr);
+
+    s->map_addr = s->map_end = 0;
+    s->lfb_addr = addr & TARGET_PAGE_MASK; 
+    s->lfb_end = ((addr + VGA_RAM_SIZE) + TARGET_PAGE_SIZE - 1) & TARGET_PAGE_MASK;
+    /* account for overflow */
+    if (s->lfb_end < addr + VGA_RAM_SIZE)
+        s->lfb_end = addr + VGA_RAM_SIZE;
 }
 
 static void cirrus_pci_mmio_map(PCIDevice *d, int region_num,
diff --git a/hw/vga.c b/hw/vga.c
index 9540db0..df6179b 100644
--- a/hw/vga.c
+++ b/hw/vga.c
@@ -28,6 +28,7 @@
 #include "vga_int.h"
 #include "pixel_ops.h"
 #include "qemu-timer.h"
+#include "kvm.h"
 
 //#define DEBUG_VGA
 //#define DEBUG_VGA_MEM
@@ -1243,6 +1244,8 @@ static void vga_draw_text(VGAState *s, int full_update)
     vga_draw_glyph8_func *vga_draw_glyph8;
     vga_draw_glyph9_func *vga_draw_glyph9;
 
+    vga_dirty_log_stop(s);
+
     full_update |= update_palette16(s);
     palette = s->last_palette;
 
@@ -1568,6 +1571,9 @@ static void vga_draw_graphic(VGAState *s, int full_update)
     uint32_t v, addr1, addr;
     vga_draw_line_func *vga_draw_line;
 
+    cpu_physical_sync_dirty_bitmap(s->vram_offset, s->vram_offset + VGA_RAM_SIZE);
+    vga_dirty_log_start(s);
+
     full_update |= update_basic_params(s);
 
     s->get_resolution(s, &width, &height);
@@ -1743,6 +1749,8 @@ static void vga_draw_blank(VGAState *s, int full_update)
         return;
     if (s->last_scr_width <= 0 || s->last_scr_height <= 0)
         return;
+    vga_dirty_log_stop(s);
+
     if (s->ds->depth == 8)
         val = s->rgb_to_pixel(0, 0, 0);
     else
@@ -2092,6 +2100,18 @@ typedef struct PCIVGAState {
     VGAState vga_state;
 } PCIVGAState;
 
+void vga_dirty_log_start(VGAState *s)
+{
+    if (kvm_enabled() && s->map_addr)
+        kvm_log_start(s->map_addr, s->map_end - s->map_addr);
+}
+
+void vga_dirty_log_stop(VGAState *s)
+{
+    if (kvm_enabled() && s->map_addr)
+        kvm_log_stop(s->map_addr, s->map_end - s->map_addr);
+}
+
 static void vga_map(PCIDevice *pci_dev, int region_num,
                     uint32_t addr, uint32_t size, int type)
 {
@@ -2102,6 +2122,11 @@ static void vga_map(PCIDevice *pci_dev, int region_num,
     } else {
         cpu_register_physical_memory(addr, s->vram_size, s->vram_offset);
     }
+
+    s->map_addr = addr;
+    s->map_end = addr + VGA_RAM_SIZE;
+
+    vga_dirty_log_start(s);
 }
 
 void vga_common_init(VGAState *s, DisplayState *ds, uint8_t *vga_ram_base,
diff --git a/hw/vga_int.h b/hw/vga_int.h
index fbe5d64..d1d35f9 100644
--- a/hw/vga_int.h
+++ b/hw/vga_int.h
@@ -100,8 +100,12 @@ typedef void (* vga_update_retrace_info_fn)(struct VGAState *s);
 
 #define VGA_STATE_COMMON                                                \
     uint8_t *vram_ptr;                                                  \
-    unsigned long vram_offset;                                          \
+    ram_addr_t vram_offset;                                             \
     unsigned int vram_size;                                             \
+    uint32_t lfb_addr;                                                  \
+    uint32_t lfb_end;                                                   \
+    uint32_t map_addr;                                                  \
+    uint32_t map_end;                                                   \
     unsigned long bios_offset;                                          \
     unsigned int bios_size;                                             \
     target_phys_addr_t base_ctrl;                                       \
@@ -189,6 +193,10 @@ static inline int c6_to_8(int v)
 void vga_common_init(VGAState *s, DisplayState *ds, uint8_t *vga_ram_base,
                      unsigned long vga_ram_offset, int vga_ram_size);
 void vga_init(VGAState *s);
+
+void vga_dirty_log_start(VGAState *s);
+void vga_dirty_log_stop(VGAState *s);
+
 uint32_t vga_mem_readb(void *opaque, target_phys_addr_t addr);
 void vga_mem_writeb(void *opaque, target_phys_addr_t addr, uint32_t val);
 void vga_invalidate_scanlines(VGAState *s, int y1, int y2);
-- 
1.5.6.5