Merge branch 'drm-next' of git://people.freedesktop.org/~airlied/linux

Pull drm merge from Dave Airlie:
 "Highlights:

   - TI LCD controller KMS driver

   - TI OMAP KMS driver merged from staging

   - drop gma500 stub driver

   - the fbcon locking fixes

   - the vgacon dirty like zebra fix.

   - open firmware videomode and hdmi common code helpers

   - major locking rework for kms object handling - pageflip/cursor
     won't block on polling anymore!

   - fbcon helper and prime helper cleanups

   - i915: all over the map, haswell power well enhancements, valleyview
     macro horrors cleaned up, killing lots of legacy GTT code,

   - radeon: CS ioctl unification, deprecated UMS support, gpu reset
     rework, VM fixes

   - nouveau: reworked thermal code, external dp/tmds encoder support
     (anx9805), fences sleep instead of polling,

   - exynos: all over the driver fixes."

Lovely conflict in radeon/evergreen_cs.c between commit de0babd60d8d
("drm/radeon: enforce use of radeon_get_ib_value when reading user cmd")
and the new changes that modified that evergreen_dma_cs_parse()
function.

* 'drm-next' of git://people.freedesktop.org/~airlied/linux: (508 commits)
  drm/tilcdc: only build on arm
  drm/i915: Revert hdmi HDP pin checks
  drm/tegra: Add list of framebuffers to debugfs
  drm/tegra: Fix color expansion
  drm/tegra: Split DC_CMD_STATE_CONTROL register write
  drm/tegra: Implement page-flipping support
  drm/tegra: Implement VBLANK support
  drm/tegra: Implement .mode_set_base()
  drm/tegra: Add plane support
  drm/tegra: Remove bogus tegra_framebuffer structure
  drm: Add consistency check for page-flipping
  drm/radeon: Use generic HDMI infoframe helpers
  drm/tegra: Use generic HDMI infoframe helpers
  drm: Add EDID helper documentation
  drm: Add HDMI infoframe helpers
  video: Add generic HDMI infoframe helpers
  drm: Add some missing forward declarations
  drm: Move mode tables to drm_edid.c
  drm: Remove duplicate drm_mode_cea_vic()
  gma500: Fix n, m1 and m2 clock limits for sdvo and lvds
  ...

3 files changed, 81 insertions, 45 deletions

diff --git a/drivers/gpu/drm/udl/udl_drv.h b/drivers/gpu/drm/udl/udl_drv.h
index 87aa5f5d3c88..cc6d90f28c71 100644
--- a/drivers/gpu/drm/udl/udl_drv.h
+++ b/drivers/gpu/drm/udl/udl_drv.h
@@ -75,6 +75,8 @@ struct udl_framebuffer {
         struct drm_framebuffer base;
         struct udl_gem_object *obj;
         bool active_16; /* active on the 16-bit channel */
+        int x1, y1, x2, y2; /* dirty rect */
+        spinlock_t dirty_lock;
 };
 
 #define to_udl_fb(x) container_of(x, struct udl_framebuffer, base)
diff --git a/drivers/gpu/drm/udl/udl_fb.c b/drivers/gpu/drm/udl/udl_fb.c
index d4ab3beaada0..9f4be3d4a02e 100644
--- a/drivers/gpu/drm/udl/udl_fb.c
+++ b/drivers/gpu/drm/udl/udl_fb.c
@@ -22,9 +22,9 @@
 
 #include <drm/drm_fb_helper.h>
 
-#define DL_DEFIO_WRITE_DELAY    5 /* fb_deferred_io.delay in jiffies */
+#define DL_DEFIO_WRITE_DELAY    (HZ/20) /* fb_deferred_io.delay in jiffies */
 
-static int fb_defio = 1;  /* Optionally enable experimental fb_defio mmap support */
+static int fb_defio = 0;  /* Optionally enable experimental fb_defio mmap support */
 static int fb_bpp = 16;
 
 module_param(fb_bpp, int, S_IWUSR | S_IRUSR | S_IWGRP | S_IRGRP);
@@ -153,6 +153,9 @@ int udl_handle_damage(struct udl_framebuffer *fb, int x, int y,
         struct urb *urb;
         int aligned_x;
         int bpp = (fb->base.bits_per_pixel / 8);
+        int x2, y2;
+        bool store_for_later = false;
+        unsigned long flags;
 
         if (!fb->active_16)
                 return 0;
@@ -169,8 +172,6 @@ int udl_handle_damage(struct udl_framebuffer *fb, int x, int y,
                 }
         }
 
-        start_cycles = get_cycles();
-
         aligned_x = DL_ALIGN_DOWN(x, sizeof(unsigned long));
         width = DL_ALIGN_UP(width + (x-aligned_x), sizeof(unsigned long));
         x = aligned_x;
@@ -180,19 +181,53 @@ int udl_handle_damage(struct udl_framebuffer *fb, int x, int y,
             (y + height > fb->base.height))
                 return -EINVAL;
 
+        /* if we are in atomic just store the info
+           can't test inside spin lock */
+        if (in_atomic())
+                store_for_later = true;
+
+        x2 = x + width - 1;
+        y2 = y + height - 1;
+
+        spin_lock_irqsave(&fb->dirty_lock, flags);
+
+        if (fb->y1 < y)
+                y = fb->y1;
+        if (fb->y2 > y2)
+                y2 = fb->y2;
+        if (fb->x1 < x)
+                x = fb->x1;
+        if (fb->x2 > x2)
+                x2 = fb->x2;
+
+        if (store_for_later) {
+                fb->x1 = x;
+                fb->x2 = x2;
+                fb->y1 = y;
+                fb->y2 = y2;
+                spin_unlock_irqrestore(&fb->dirty_lock, flags);
+                return 0;
+        }
+
+        fb->x1 = fb->y1 = INT_MAX;
+        fb->x2 = fb->y2 = 0;
+
+        spin_unlock_irqrestore(&fb->dirty_lock, flags);
+        start_cycles = get_cycles();
+
         urb = udl_get_urb(dev);
         if (!urb)
                 return 0;
         cmd = urb->transfer_buffer;
 
-        for (i = y; i < y + height ; i++) {
+        for (i = y; i <= y2 ; i++) {
                 const int line_offset = fb->base.pitches[0] * i;
                 const int byte_offset = line_offset + (x * bpp);
                 const int dev_byte_offset = (fb->base.width * bpp * i) + (x * bpp);
                 if (udl_render_hline(dev, bpp, &urb,
                                      (char *) fb->obj->vmapping,
                                      &cmd, byte_offset, dev_byte_offset,
-                                     width * bpp,
+                                     (x2 - x + 1) * bpp,
                                      &bytes_identical, &bytes_sent))
                         goto error;
         }
@@ -422,7 +457,6 @@ static void udl_user_framebuffer_destroy(struct drm_framebuffer *fb)
 static const struct drm_framebuffer_funcs udlfb_funcs = {
         .destroy = udl_user_framebuffer_destroy,
         .dirty = udl_user_framebuffer_dirty,
-        .create_handle = NULL,
 };
 
 
@@ -434,16 +468,18 @@ udl_framebuffer_init(struct drm_device *dev,
 {
         int ret;
 
+        spin_lock_init(&ufb->dirty_lock);
         ufb->obj = obj;
-        ret = drm_framebuffer_init(dev, &ufb->base, &udlfb_funcs);
         drm_helper_mode_fill_fb_struct(&ufb->base, mode_cmd);
+        ret = drm_framebuffer_init(dev, &ufb->base, &udlfb_funcs);
         return ret;
 }
 
 
-static int udlfb_create(struct udl_fbdev *ufbdev,
+static int udlfb_create(struct drm_fb_helper *helper,
                         struct drm_fb_helper_surface_size *sizes)
 {
+        struct udl_fbdev *ufbdev = (struct udl_fbdev *)helper;
         struct drm_device *dev = ufbdev->helper.dev;
         struct fb_info *info;
         struct device *device = &dev->usbdev->dev;
@@ -521,27 +557,10 @@ out:
         return ret;
 }
 
-static int udl_fb_find_or_create_single(struct drm_fb_helper *helper,
-                                        struct drm_fb_helper_surface_size *sizes)
-{
-        struct udl_fbdev *ufbdev = (struct udl_fbdev *)helper;
-        int new_fb = 0;
-        int ret;
-
-        if (!helper->fb) {
-                ret = udlfb_create(ufbdev, sizes);
-                if (ret)
-                        return ret;
-
-                new_fb = 1;
-        }
-        return new_fb;
-}
-
 static struct drm_fb_helper_funcs udl_fb_helper_funcs = {
         .gamma_set = udl_crtc_fb_gamma_set,
         .gamma_get = udl_crtc_fb_gamma_get,
-        .fb_probe = udl_fb_find_or_create_single,
+        .fb_probe = udlfb_create,
 };
 
 static void udl_fbdev_destroy(struct drm_device *dev,
@@ -556,6 +575,7 @@ static void udl_fbdev_destroy(struct drm_device *dev,
                 framebuffer_release(info);
         }
         drm_fb_helper_fini(&ufbdev->helper);
+        drm_framebuffer_unregister_private(&ufbdev->ufb.base);
         drm_framebuffer_cleanup(&ufbdev->ufb.base);
         drm_gem_object_unreference_unlocked(&ufbdev->ufb.obj->base);
 }
@@ -583,6 +603,10 @@ int udl_fbdev_init(struct drm_device *dev)
         }
 
         drm_fb_helper_single_add_all_connectors(&ufbdev->helper);
+
+        /* disable all the possible outputs/crtcs before entering KMS mode */
+        drm_helper_disable_unused_functions(dev);
+
         drm_fb_helper_initial_config(&ufbdev->helper, bpp_sel);
         return 0;
 }
diff --git a/drivers/gpu/drm/udl/udl_transfer.c b/drivers/gpu/drm/udl/udl_transfer.c
index 142fee5f983f..f343db73e095 100644
--- a/drivers/gpu/drm/udl/udl_transfer.c
+++ b/drivers/gpu/drm/udl/udl_transfer.c
@@ -75,15 +75,19 @@ static int udl_trim_hline(const u8 *bback, const u8 **bfront, int *width_bytes)
 }
 #endif
 
-static inline u16 pixel32_to_be16p(const uint8_t *pixel)
+static inline u16 pixel32_to_be16(const uint32_t pixel)
 {
-        uint32_t pix = *(uint32_t *)pixel;
-        u16 retval;
+        return (((pixel >> 3) & 0x001f) |
+                ((pixel >> 5) & 0x07e0) |
+                ((pixel >> 8) & 0xf800));
+}
 
-        retval =  (((pix >> 3) & 0x001f) |
-                   ((pix >> 5) & 0x07e0) |
-                   ((pix >> 8) & 0xf800));
-        return retval;
+static bool pixel_repeats(const void *pixel, const uint32_t repeat, int bpp)
+{
+        if (bpp == 2)
+                return *(const uint16_t *)pixel == repeat;
+        else
+                return *(const uint32_t *)pixel == repeat;
 }
 
 /*
@@ -152,29 +156,33 @@ static void udl_compress_hline16(
                 prefetch_range((void *) pixel, (cmd_pixel_end - pixel) * bpp);
 
                 while (pixel < cmd_pixel_end) {
-                        const u8 * const repeating_pixel = pixel;
-
-                        if (bpp == 2)
-                                *(uint16_t *)cmd = cpu_to_be16p((uint16_t *)pixel);
-                        else if (bpp == 4)
-                                *(uint16_t *)cmd = cpu_to_be16(pixel32_to_be16p(pixel));
+                        const u8 *const start = pixel;
+                        u32 repeating_pixel;
+
+                        if (bpp == 2) {
+                                repeating_pixel = *(uint16_t *)pixel;
+                                *(uint16_t *)cmd = cpu_to_be16(repeating_pixel);
+                        } else {
+                                repeating_pixel = *(uint32_t *)pixel;
+                                *(uint16_t *)cmd = cpu_to_be16(pixel32_to_be16(repeating_pixel));
+                        }
 
                         cmd += 2;
                         pixel += bpp;
 
                         if (unlikely((pixel < cmd_pixel_end) &&
-                                     (!memcmp(pixel, repeating_pixel, bpp)))) {
+                                     (pixel_repeats(pixel, repeating_pixel, bpp)))) {
                                 /* go back and fill in raw pixel count */
-                                *raw_pixels_count_byte = (((repeating_pixel -
+                                *raw_pixels_count_byte = (((start -
                                                 raw_pixel_start) / bpp) + 1) & 0xFF;
 
-                                while ((pixel < cmd_pixel_end)
-                                       && (!memcmp(pixel, repeating_pixel, bpp))) {
+                                while ((pixel < cmd_pixel_end) &&
+                                       (pixel_repeats(pixel, repeating_pixel, bpp))) {
                                         pixel += bpp;
                                 }
 
                                 /* immediately after raw data is repeat byte */
-                                *cmd++ = (((pixel - repeating_pixel) / bpp) - 1) & 0xFF;
+                                *cmd++ = (((pixel - start) / bpp) - 1) & 0xFF;
 
                                 /* Then start another raw pixel span */
                                 raw_pixel_start = pixel;
@@ -223,6 +231,8 @@ int udl_render_hline(struct drm_device *dev, int bpp, struct urb **urb_ptr,
         u8 *cmd = *urb_buf_ptr;
         u8 *cmd_end = (u8 *) urb->transfer_buffer + urb->transfer_buffer_length;
 
+        BUG_ON(!(bpp == 2 || bpp == 4));
+
         line_start = (u8 *) (front + byte_offset);
         next_pixel = line_start;
         line_end = next_pixel + byte_width;