summaryrefslogtreecommitdiff
path: root/drivers/video
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2022-03-25 14:57:47 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2022-03-25 14:57:47 -0700
commitcb7cbaae7fd9cee64f19cdfd89d097d807b884f5 (patch)
treee167052fd2768971c79ff7c03dd282ae9d961b02 /drivers/video
parent46f538bf2404ee9c32648deafb886f49144bfd5e (diff)
parent2a81dba4b577099717cea86d429f053e85e74d96 (diff)
Merge tag 'drm-next-2022-03-25' of git://anongit.freedesktop.org/drm/drm
Pull drm fixes from Dave Airlie: "Some fixes were queued up in and in light of the fbdev regressions, I've pulled those in as well. core: - Make audio and color plane support checking only happen when a CEA extension block is found. - Small selftest fix. fbdev: - two regressions fixes from speedup patches. ttm: - Fix a small regression from ttm_resource_fini() i915: - Reject unsupported TMDS rates on ICL+ - Treat SAGV block time 0 as SAGV disabled - Fix PSF GV point mask when SAGV is not possible - Fix renamed INTEL_INFO->media.arch/ver field" * tag 'drm-next-2022-03-25' of git://anongit.freedesktop.org/drm/drm: fbdev: Fix cfb_imageblit() for arbitrary image widths fbdev: Fix sys_imageblit() for arbitrary image widths drm/edid: fix CEA extension byte #3 parsing drm/edid: check basic audio support on CEA extension block drm/i915: Fix renamed struct field drm/i915: Fix PSF GV point mask when SAGV is not possible drm/i915: Treat SAGV block time 0 as SAGV disabled drm/i915: Reject unsupported TMDS rates on ICL+ drm/selftest: plane_helper: Put test structures in static storage drm/ttm: Fix a kernel oops due to an invalid read
Diffstat (limited to 'drivers/video')
-rw-r--r--drivers/video/fbdev/core/cfbimgblt.c28
-rw-r--r--drivers/video/fbdev/core/sysimgblt.c29
2 files changed, 49 insertions, 8 deletions
diff --git a/drivers/video/fbdev/core/cfbimgblt.c b/drivers/video/fbdev/core/cfbimgblt.c
index 7361cfabdd85..9ebda4e0dc7a 100644
--- a/drivers/video/fbdev/core/cfbimgblt.c
+++ b/drivers/video/fbdev/core/cfbimgblt.c
@@ -218,7 +218,7 @@ static inline void fast_imageblit(const struct fb_image *image, struct fb_info *
{
u32 fgx = fgcolor, bgx = bgcolor, bpp = p->var.bits_per_pixel;
u32 ppw = 32/bpp, spitch = (image->width + 7)/8;
- u32 bit_mask, eorx;
+ u32 bit_mask, eorx, shift;
const char *s = image->data, *src;
u32 __iomem *dst;
const u32 *tab = NULL;
@@ -259,17 +259,23 @@ static inline void fast_imageblit(const struct fb_image *image, struct fb_info *
for (i = image->height; i--; ) {
dst = (u32 __iomem *)dst1;
+ shift = 8;
src = s;
+ /*
+ * Manually unroll the per-line copying loop for better
+ * performance. This works until we processed the last
+ * completely filled source byte (inclusive).
+ */
switch (ppw) {
case 4: /* 8 bpp */
- for (j = k; j; j -= 2, ++src) {
+ for (j = k; j >= 2; j -= 2, ++src) {
FB_WRITEL(colortab[(*src >> 4) & bit_mask], dst++);
FB_WRITEL(colortab[(*src >> 0) & bit_mask], dst++);
}
break;
case 2: /* 16 bpp */
- for (j = k; j; j -= 4, ++src) {
+ for (j = k; j >= 4; j -= 4, ++src) {
FB_WRITEL(colortab[(*src >> 6) & bit_mask], dst++);
FB_WRITEL(colortab[(*src >> 4) & bit_mask], dst++);
FB_WRITEL(colortab[(*src >> 2) & bit_mask], dst++);
@@ -277,7 +283,7 @@ static inline void fast_imageblit(const struct fb_image *image, struct fb_info *
}
break;
case 1: /* 32 bpp */
- for (j = k; j; j -= 8, ++src) {
+ for (j = k; j >= 8; j -= 8, ++src) {
FB_WRITEL(colortab[(*src >> 7) & bit_mask], dst++);
FB_WRITEL(colortab[(*src >> 6) & bit_mask], dst++);
FB_WRITEL(colortab[(*src >> 5) & bit_mask], dst++);
@@ -290,6 +296,20 @@ static inline void fast_imageblit(const struct fb_image *image, struct fb_info *
break;
}
+ /*
+ * For image widths that are not a multiple of 8, there
+ * are trailing pixels left on the current line. Print
+ * them as well.
+ */
+ for (; j--; ) {
+ shift -= ppw;
+ FB_WRITEL(colortab[(*src >> shift) & bit_mask], dst++);
+ if (!shift) {
+ shift = 8;
+ ++src;
+ }
+ }
+
dst1 += p->fix.line_length;
s += spitch;
}
diff --git a/drivers/video/fbdev/core/sysimgblt.c b/drivers/video/fbdev/core/sysimgblt.c
index 722c327a381b..335e92b813fc 100644
--- a/drivers/video/fbdev/core/sysimgblt.c
+++ b/drivers/video/fbdev/core/sysimgblt.c
@@ -188,7 +188,7 @@ static void fast_imageblit(const struct fb_image *image, struct fb_info *p,
{
u32 fgx = fgcolor, bgx = bgcolor, bpp = p->var.bits_per_pixel;
u32 ppw = 32/bpp, spitch = (image->width + 7)/8;
- u32 bit_mask, eorx;
+ u32 bit_mask, eorx, shift;
const char *s = image->data, *src;
u32 *dst;
const u32 *tab;
@@ -229,17 +229,23 @@ static void fast_imageblit(const struct fb_image *image, struct fb_info *p,
for (i = image->height; i--; ) {
dst = dst1;
+ shift = 8;
src = s;
+ /*
+ * Manually unroll the per-line copying loop for better
+ * performance. This works until we processed the last
+ * completely filled source byte (inclusive).
+ */
switch (ppw) {
case 4: /* 8 bpp */
- for (j = k; j; j -= 2, ++src) {
+ for (j = k; j >= 2; j -= 2, ++src) {
*dst++ = colortab[(*src >> 4) & bit_mask];
*dst++ = colortab[(*src >> 0) & bit_mask];
}
break;
case 2: /* 16 bpp */
- for (j = k; j; j -= 4, ++src) {
+ for (j = k; j >= 4; j -= 4, ++src) {
*dst++ = colortab[(*src >> 6) & bit_mask];
*dst++ = colortab[(*src >> 4) & bit_mask];
*dst++ = colortab[(*src >> 2) & bit_mask];
@@ -247,7 +253,7 @@ static void fast_imageblit(const struct fb_image *image, struct fb_info *p,
}
break;
case 1: /* 32 bpp */
- for (j = k; j; j -= 8, ++src) {
+ for (j = k; j >= 8; j -= 8, ++src) {
*dst++ = colortab[(*src >> 7) & bit_mask];
*dst++ = colortab[(*src >> 6) & bit_mask];
*dst++ = colortab[(*src >> 5) & bit_mask];
@@ -259,6 +265,21 @@ static void fast_imageblit(const struct fb_image *image, struct fb_info *p,
}
break;
}
+
+ /*
+ * For image widths that are not a multiple of 8, there
+ * are trailing pixels left on the current line. Print
+ * them as well.
+ */
+ for (; j--; ) {
+ shift -= ppw;
+ *dst++ = colortab[(*src >> shift) & bit_mask];
+ if (!shift) {
+ shift = 8;
+ ++src;
+ }
+ }
+
dst1 += p->fix.line_length;
s += spitch;
}