From 6d60cc7baf662b64e3c50f95826dead58cf8e839 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?R=C3=A9mi=20Denis-Courmont?= <remi@remlab.net>
Date: Thu, 9 Nov 2023 20:19:47 +0200
Subject: [PATCH] sws/rgb2rgb: fix unaligned accesses in R-V V YUYV to I422p

In my personal opinion, we should not need to support unaligned YUY2
pixel maps. They should always be aligned to at least 32 bits, and the
current code assumes just 16 bits. However checkasm does test for
unaligned input bitmaps. QEMU accepts it, but real hardware dose not.

In this particular case, we can at the same time improve performance and
handle unaligned inputs, so do just that.

uyvytoyuv422_c:      104379.0
uyvytoyuv422_c:      104060.0
uyvytoyuv422_rvv_i32: 25284.0 (before)
uyvytoyuv422_rvv_i32: 19303.2 (after)
---
 libswscale/riscv/rgb2rgb.c     |  6 +++--
 libswscale/riscv/rgb2rgb_rvv.S | 47 ++++++++++++++++++----------------
 2 files changed, 29 insertions(+), 24 deletions(-)

diff --git a/libswscale/riscv/rgb2rgb.c b/libswscale/riscv/rgb2rgb.c
index 565f0b77f1..4fa1f5afd9 100644
--- a/libswscale/riscv/rgb2rgb.c
+++ b/libswscale/riscv/rgb2rgb.c
@@ -55,8 +55,10 @@ av_cold void rgb2rgb_init_riscv(void)
         shuffle_bytes_1230 = ff_shuffle_bytes_1230_rvv;
         shuffle_bytes_3012 = ff_shuffle_bytes_3012_rvv;
         interleaveBytes = ff_interleave_bytes_rvv;
-        uyvytoyuv422 = ff_uyvytoyuv422_rvv;
-        yuyvtoyuv422 = ff_yuyvtoyuv422_rvv;
+        if (flags & AV_CPU_FLAG_RVB_BASIC) {
+            uyvytoyuv422 = ff_uyvytoyuv422_rvv;
+            yuyvtoyuv422 = ff_yuyvtoyuv422_rvv;
+        }
     }
 #endif
 }
diff --git a/libswscale/riscv/rgb2rgb_rvv.S b/libswscale/riscv/rgb2rgb_rvv.S
index 172f5918dc..21e30ab8bb 100644
--- a/libswscale/riscv/rgb2rgb_rvv.S
+++ b/libswscale/riscv/rgb2rgb_rvv.S
@@ -126,32 +126,35 @@ func ff_deinterleave_bytes_rvv, zve32x
         ret
 endfunc
 
-.macro yuy2_to_i422p y_shift
-        slli    t4, a4, 1 // pixel width -> (source) byte width
+.macro yuy2_to_i422p luma, chroma
+        srai    t4, a4, 1 // pixel width -> chroma width
         lw      t6, (sp)
+        slli    t5, a4, 1 // pixel width -> (source) byte width
         sub     a6, a6, a4
-        srai    a4, a4, 1 // pixel width -> chroma width
-        sub     a7, a7, a4
-        sub     t6, t6, t4
+        sub     a7, a7, t4
+        sub     t6, t6, t5
+        vsetvli t2, zero, e8, m4, ta, ma
 1:
         mv      t4, a4
         addi    a5, a5, -1
 2:
-        vsetvli    t5, t4, e8, m2, ta, ma
-        vlseg2e16.v v16, (a3)
-        sub        t4, t4, t5
-        vnsrl.wi   v24, v16, \y_shift // Y0
-        sh2add     a3, t5, a3
-        vnsrl.wi   v26, v20, \y_shift // Y1
-        vnsrl.wi   v28, v16, 8 - \y_shift // U
-        vnsrl.wi   v30, v20, 8 - \y_shift // V
-        vsseg2e8.v v24, (a0)
-        sh1add     a0, t5, a0
-        vse8.v     v28, (a1)
-        add        a1, t5, a1
-        vse8.v     v30, (a2)
-        add        a2, t5, a2
-        bnez       t4, 2b
+        min     t0, t2, t4 // ensure even VL on penultimate iteration
+        vsetvli t0, t0, e8, m4, ta, ma
+        vlseg2e8.v v16, (a3)
+        srli    t1, t0, 1
+        vsetvli zero, t1, e8, m2, ta, ma
+        vnsrl.wi   v24, \chroma, 0 // U
+        sub     t4, t4, t0
+        vnsrl.wi   v28, \chroma, 8 // V
+        sh1add  a3, t0, a3
+        vse8.v  v24, (a1)
+        add     a1, t1, a1
+        vse8.v  v28, (a2)
+        add     a2, t1, a2
+        vsetvli zero, t0, e8, m4, ta, ma
+        vse8.v  \luma, (a0)
+        add     a0, t0, a0
+        bnez    t4, 2b
 
         add     a3, a3, t6
         add     a0, a0, a6
@@ -163,9 +166,9 @@ endfunc
 .endm
 
 func ff_uyvytoyuv422_rvv, zve32x
-        yuy2_to_i422p 8
+        yuy2_to_i422p v20, v16
 endfunc
 
 func ff_yuyvtoyuv422_rvv, zve32x
-        yuy2_to_i422p 0
+        yuy2_to_i422p v16, v20
 endfunc