// The VBE linear framebuffer: the display the loader left running.
//
// This is the driver half of what used to be kernel/dev/vga.c. That file was
// three things at once -- the owner of the framebuffer, a bitmap drawing
// library, and the text console -- and only the first is a driver. The other
// two are now kernel/dev/gfx.c and do not name any driver at all, so the crash
// screen and the console draw on whatever hardware is bound rather than on
// this one by name. See include/gfx.h.
//
// What stays here is everything that knows *where the pixels are*: the mode the
// loader programmed and handed over in the boot block, the aperture it lives
// in, and the display class vtable that presents all of it as one of possibly
// several displays.

#include "types.h"
#include "x86.h"
#include "memlayout.h"
#include "defs.h"
#include "device.h"
#include "display.h"
#include "gfx.h"
#include "dma.h"
#include "schboot.h"   /* the hand-off block */

static volatile uchar *fb;
// Physical base of the linear framebuffer, as reported by VBE. Everything that
// needs to map the framebuffer -- fork's VMA copy, mmap of /dev/fb0 -- asks
// rather than assuming a value. Three places used to hardcode 0xfd000000,
// which is only where QEMU's stdvga happens to put it.
static uint64 fb_phys;
static uint32 fb_stride;
static uint32 fb_bpp;
static uint32 fb_width  = 800;
static uint32 fb_height = 600;

// Bytes of framebuffer, measured in scanlines rather than as
// width * height * bpp/8 -- the two differ whenever the card pads its rows,
// and it is the stride that says how far apart two rows really are.
uint64
vga_fb_size(void)
{
  if (!fb)
    return 0;
  return (uint64)fb_stride * (uint64)fb_height;
}

// The framebuffer address VBE reported, for the PCI half of this driver to
// cross-check against the aperture it finds on the bus. Zero before init.
uint64
vga_fb_phys(void)
{
  return fb_phys;
}

// Read the mode the loader programmed and publish it as a scanout.
//
// Called from platform_register_devices(), because the framebuffer is a fact
// about the machine that the loader established before any bus was walked --
// the PCI display driver binds much later, and the console has to be able to
// draw long before that.
//
// Deliberately does NOT clear the screen: whoever wants the framebuffer cleared
// says so, and this function is only about where it is. kmain clears it once,
// right after attaching the loader's scanout, and the kernel log runs on screen
// from there -- see cons_serial_only in kernel/core/console.c for why the
// splash no longer survives the whole boot.
void
vga_fb_init(uint64 phys_addr)
{
  struct fb_info info;

  if (phys_addr == 0)
    phys_addr = *(uint32*)(P2V(SCHBOOT_VBE_LFB));

  fb        = (volatile uchar*)P2V(phys_addr);
  fb_phys   = phys_addr;
  fb_stride = *(ushort*)(P2V(SCHBOOT_VBE_STRIDE));
  fb_width  = *(ushort*)(P2V(SCHBOOT_VBE_WIDTH));
  fb_height = *(ushort*)(P2V(SCHBOOT_VBE_HEIGHT));
  fb_bpp    = *(uchar*)(P2V(SCHBOOT_VBE_BPP));

  if (fb_width  == 0) fb_width  = 800;
  if (fb_height == 0) fb_height = 600;
  if (fb_stride == 0) fb_stride = fb_width * (fb_bpp / 8);

  kinfo("vga: %dx%d, %d bpp, stride %d, LFB: 0x%x\n",
          fb_width, fb_height, fb_bpp, fb_stride, (uint32)phys_addr);

  info.ptr    = fb;
  info.phys   = fb_phys;
  info.size   = vga_fb_size();
  info.stride = fb_stride;
  info.bpp    = fb_bpp;
  info.width  = fb_width;
  info.height = fb_height;
  gfx_attach_scanout(&info);
}

// --- display class implementation ------------------------------------------
//
// See include/display.h. The VBE framebuffer presenting itself as a generic
// display, so a compositor is written against the class rather than against
// this file.

static uchar *back;          // shadow buffer in RAM, or 0 if never acquired
static uint64 back_bytes;

static void
vga_disp_mode(struct device *d, struct display_mode *m)
{
  (void)d;
  m->width  = (int)fb_width;
  m->height = (int)fb_height;
  m->bpp    = (int)fb_bpp;
  m->stride = fb_stride;
}

static void *
vga_disp_acquire(struct device *d, uint32 *stride_out)
{
  (void)d;
  if (stride_out)
    *stride_out = fb_stride;
  if (back)
    return back;
  if (!fb || fb_height == 0 || fb_stride == 0)
    return 0;

  back_bytes = (uint64)fb_stride * fb_height;

  // From the DMA arena, which is the wrong pool and is used here because it is
  // the only *physically contiguous* allocator in the kernel -- kalloc hands
  // out single pages whose neighbours are adjacent only by chance, and a
  // framebuffer wants one flat span.
  //
  // At 800x600x32 this is 1.9 MB of a 4 MB arena meant for device rings, which
  // is tolerable only because nothing else large lives there yet. The real fix
  // is a contiguous page allocator, or reserving this at boot from the memory
  // map -- which is work that belongs with the E820 change in docs/architecture/boot.md
  // §3b, since that is what stops the kernel pretending 224 MB exists.
  //
  // Allocated on first use rather than at boot on purpose: a machine that never
  // starts a compositor should not pay two megabytes for one.
  back = dma_alloc(back_bytes, 4096);
  if (!back) {
    cprintf("display: no room for a %d KB back buffer; drawing will tear\n",
            (int)(back_bytes / 1024));
    return 0;
  }
  memset(back, 0, back_bytes);
  cprintf("display: %d KB back buffer, double buffered\n",
          (int)(back_bytes / 1024));
  return back;
}

// Blit a rectangle from the shadow buffer to the framebuffer.
//
// Row at a time rather than one memmove for the whole rectangle: only a
// full-width rectangle is contiguous in either buffer, and a compositor
// updating one window is the case worth being right about.
static void
vga_disp_present(struct device *d, int x, int y, int w, int h)
{
  (void)d;
  if (!back || !fb)
    return;

  if (x < 0) { w += x; x = 0; }
  if (y < 0) { h += y; y = 0; }
  if (x + w > (int)fb_width)  w = (int)fb_width - x;
  if (y + h > (int)fb_height) h = (int)fb_height - y;
  if (w <= 0 || h <= 0)
    return;

  int bytes = w * (int)(fb_bpp / 8);
  uint32 off = (uint32)x * (fb_bpp / 8);
  for (int row = y; row < y + h; row++)
    memmove((void *)(fb + row * fb_stride + off),
            back + row * fb_stride + off, bytes);
}

// Wait for vertical retrace, by polling the VGA input status register.
//
// Bit 3 of 0x3DA is set during vertical retrace. This is the original 1987 VGA
// interface and it still works on everything that emulates a VGA, QEMU's
// stdvga included -- VBE's own protected-mode interface for this is optional
// and frequently absent, so the old port is the portable answer.
//
// Two loops, not one: waiting only for the flag to *be* set would return
// immediately if a retrace is already in progress, having just missed the
// start of it. Waiting for the current one to end and the next to begin is
// what actually lands the blit between frames.
//
// The counters are a deadlock guard. On hardware that never reports retrace
// this returns after a bounded spin instead of hanging the caller forever,
// which matters because this can be called with the console locked.
static void
vga_disp_wait_vblank(struct device *d)
{
  int guard;

  (void)d;
  for (guard = 0; guard < 1000000; guard++)
    if (!(inb(0x3DA) & 0x08))
      break;
  for (guard = 0; guard < 1000000; guard++)
    if (inb(0x3DA) & 0x08)
      break;
}

const struct display_ops vga_display_ops = {
  .mode        = vga_disp_mode,
  .acquire     = vga_disp_acquire,
  .present     = vga_disp_present,
  .wait_vblank = vga_disp_wait_vblank,
};

// Put the VBE framebuffer back on screen.
//
// Called when a better display driver lets go of the hardware -- see
// virtio-gpu's release hook. gfx holds one scanout, last writer wins, so the
// driver that leaves has to name its replacement rather than simply detaching;
// detaching alone leaves gfx pointing at a device nobody is driving.
//
// This is the fallback rule from docs/plan/hybrid.md made real: the kernel
// keeps a minimal driver for everything on the path to a shell, so a fancy
// driver leaving degrades to a working screen instead of to no screen.
int
vga_fb_restore(void)
{
  struct fb_info info;

  // Zero means there is no framebuffer to go back to, and the caller has to
  // care. It used to return void and say nothing here, which reads as "done"
  // -- so on a machine whose only display is the one being handed over, the
  // eviction went ahead and left the console drawing into a driver that had
  // just freed its memory. The answer is not to try harder; it is to say no,
  // which is what the caller now does.
  if (!fb || !fb_width || !fb_height)
    return 0;

  info.ptr    = fb;
  info.phys   = fb_phys;
  info.size   = vga_fb_size();
  info.stride = fb_stride;
  info.bpp    = fb_bpp;
  info.width  = fb_width;
  info.height = fb_height;
  gfx_attach_scanout(&info);
  return 1;
}