Merge branch 'udl-fixes' into drm-next

Fixes for usb/udl devices
* udl-fixes:
  drm/udl: disable fb_defio by default
  drm/udl: Inline memcmp() for RLE compression of xfer
  drm/udl: make usage as a console safer
  drm/usb: bind driver to correct device

3 files changed, 72 insertions, 24 deletions

diff --git a/drivers/gpu/drm/udl/udl_drv.h b/drivers/gpu/drm/udl/udl_drv.h
index 87aa5f5d3c8..cc6d90f28c7 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 caa84f1de9c..b9feec9d08d 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;
 	}
@@ -433,6 +468,7 @@ udl_framebuffer_init(struct drm_device *dev,
 {
 	int ret;
 
+	spin_lock_init(&ufb->dirty_lock);
 	ufb->obj = obj;
 	drm_helper_mode_fill_fb_struct(&ufb->base, mode_cmd);
 	ret = drm_framebuffer_init(dev, &ufb->base, &udlfb_funcs);
diff --git a/drivers/gpu/drm/udl/udl_transfer.c b/drivers/gpu/drm/udl/udl_transfer.c
index 142fee5f983..f343db73e09 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;