Re: [v3,4/5] fbdev: Improve performance of cfb_imageblit()

[Thomas Zimmermann]

Hi

Am 08.03.22 um 23:52 schrieb Marek Szyprowski:

Hi Thomas,

On 23.02.2022 20:38, Thomas Zimmermann wrote:

Improve the performance of cfb_imageblit() by manually unrolling
the inner blitting loop and moving some invariants out. The compiler
failed to do this automatically. This change keeps cfb_imageblit()
in sync with sys_imagebit().

A microbenchmark measures the average number of CPU cycles
for cfb_imageblit() after a stabilizing period of a few minutes
(i7-4790, FullHD, simpledrm, kernel with debugging).

cfb_imageblit(), new: 15724 cycles
cfb_imageblit(): old: 30566 cycles

In the optimized case, cfb_imageblit() is now ~2x faster than before.

v3:
        * fix commit description (Pekka)

Signed-off-by: Thomas Zimmermann <tzimmerm...@suse.de>
Acked-by: Sam Ravnborg <s...@ravnborg.org>
Reviewed-by: Javier Martinez Canillas <javi...@redhat.com>

This patch landed recently in linux next-20220308 as commit 0d03011894d2
("fbdev: Improve performance of cfb_imageblit()"). Sadly it causes a
freeze after DRM and emulated fbdev initialization on various Samsung
Exynos ARM 32bit based boards. This happens when kernel is compiled from
exynos_defconfig. Surprisingly when kernel is compiled from
multi_v7_defconfig all those boards boot fine, so this is a matter of
one of the debugging options enabled in the exynos_defconfig. I will try
to analyze this further and share the results. Reverting $subject on top
of next-20220308 fixes the boot issue.

Best regards
Thomas

Thanks for reporting. I don't have the hardware to reproduce it and there's no obvious difference to the original version. It's supposed to be the same algorithm with a different implementation. Unless you can figure out the issue, we can also revert the patch easily.

---
   drivers/video/fbdev/core/cfbimgblt.c | 51 +++++++++++++++++++++++-----
   1 file changed, 42 insertions(+), 9 deletions(-)

diff --git a/drivers/video/fbdev/core/cfbimgblt.c 
b/drivers/video/fbdev/core/cfbimgblt.c
index 01b01a279681..7361cfabdd85 100644
--- a/drivers/video/fbdev/core/cfbimgblt.c
+++ b/drivers/video/fbdev/core/cfbimgblt.c
@@ -218,23 +218,29 @@ 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, end_mask, eorx, shift;
+       u32 bit_mask, eorx;
        const char *s = image->data, *src;
        u32 __iomem *dst;
        const u32 *tab = NULL;
+       size_t tablen;
+       u32 colortab[16];
        int i, j, k;

        case 8:
                tab = fb_be_math(p) ? cfb_tab8_be : cfb_tab8_le;
+               tablen = 16;
                break;
        case 16:
                tab = fb_be_math(p) ? cfb_tab16_be : cfb_tab16_le;
+               tablen = 4;
                break;
        case 32:
-       default:
                tab = cfb_tab32;
+               tablen = 2;
                break;
+       default:
+               return;
        }

@@ -248,15 +254,42 @@ static inline void fast_imageblit(const struct fb_image 
*image, struct fb_info *
        eorx = fgx ^ bgx;
        k = image->width/ppw;

-               dst = (u32 __iomem *) dst1, shift = 8; src = s;
+       for (i = 0; i < tablen; ++i)
+               colortab[i] = (tab[i] & eorx) ^ bgx;

-                       shift -= ppw;
-                       end_mask = tab[(*src >> shift) & bit_mask];
-                       FB_WRITEL((end_mask & eorx)^bgx, dst++);
-                       if (!shift) { shift = 8; src++; }
+       for (i = image->height; i--; ) {
+               dst = (u32 __iomem *)dst1;
+               src = s;
+
+               switch (ppw) {
+               case 4: /* 8 bpp */
+                       for (j = k; j; 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) {
+                               FB_WRITEL(colortab[(*src >> 6) & bit_mask], 
dst++);
+                               FB_WRITEL(colortab[(*src >> 4) & bit_mask], 
dst++);
+                               FB_WRITEL(colortab[(*src >> 2) & bit_mask], 
dst++);
+                               FB_WRITEL(colortab[(*src >> 0) & bit_mask], 
dst++);
+                       }
+                       break;
+               case 1: /* 32 bpp */
+                       for (j = k; j; 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++);
+                               FB_WRITEL(colortab[(*src >> 4) & bit_mask], 
dst++);
+                               FB_WRITEL(colortab[(*src >> 3) & bit_mask], 
dst++);
+                               FB_WRITEL(colortab[(*src >> 2) & bit_mask], 
dst++);
+                               FB_WRITEL(colortab[(*src >> 1) & bit_mask], 
dst++);
+                               FB_WRITEL(colortab[(*src >> 0) & bit_mask], 
dst++);
+                       }
+                       break;
                }
+
                dst1 += p->fix.line_length;
                s += spitch;
        }

switch (bpp) { for (i = ppw-1; i--; ) { - for (i = image->height; i--; ) { - for (j = k; j--; ) {

Best regards

--
Thomas Zimmermann
Graphics Driver Developer
SUSE Software Solutions Germany GmbH
Maxfeldstr. 5, 90409 Nürnberg, Germany
(HRB 36809, AG Nürnberg)
Geschäftsführer: Ivo Totev

OpenPGP_signature
Description: OpenPGP digital signature