1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
|
From 67e9e0337185f05a0d8d362473e63d8a9dfdebed Mon Sep 17 00:00:00 2001
From: Manoj Gupta <manojgupta@google.com>
Date: Thu, 27 Dec 2018 11:06:26 -0800
Subject: [PATCH] libavcodec: Remove dynamic relocs from h264idct_neon.S
Some of the assembly functions e.g. ff_h264_idct_dc_add_neon
has code like:
movrel x14, X(ff_h264_idct_add_neon)
Linker cannot resolve them fully at link time and emits GOT
relocations.
Use explicit labels instead so that no dynamic relocations are
needed at all.
BUG=chromium:917919
TEST=lld complains are fixed.
Change-Id: Ie533a10aab1fe3834300599ce650d3673a674f4e
Reviewed-on: https://chromium-review.googlesource.com/c/1390286
Reviewed-by: Frank Liberato <liberato@chromium.org>
---
libavcodec/aarch64/h264idct_neon.S | 20 ++++++++++++--------
1 file changed, 12 insertions(+), 8 deletions(-)
diff --git a/src/third_party/ffmpeg/libavcodec/aarch64/h264idct_neon.S b/src/third_party/ffmpeg/libavcodec/aarch64/h264idct_neon.S
index 825ec49f8c6d..7de44205d39a 100644
--- a/src/third_party/ffmpeg/libavcodec/aarch64/h264idct_neon.S
+++ b/src/third_party/ffmpeg/libavcodec/aarch64/h264idct_neon.S
@@ -23,6 +23,7 @@
#include "neon.S"
function ff_h264_idct_add_neon, export=1
+.L_ff_h264_idct_add_neon:
ld1 {v0.4H, v1.4H, v2.4H, v3.4H}, [x1]
sxtw x2, w2
movi v30.8H, #0
@@ -77,6 +78,7 @@ function ff_h264_idct_add_neon, export=1
endfunc
function ff_h264_idct_dc_add_neon, export=1
+.L_ff_h264_idct_dc_add_neon:
sxtw x2, w2
mov w3, #0
ld1r {v2.8H}, [x1]
@@ -106,8 +108,8 @@ function ff_h264_idct_add16_neon, export=1
mov w9, w3 // stride
movrel x7, scan8
mov x10, #16
- movrel x13, X(ff_h264_idct_dc_add_neon)
- movrel x14, X(ff_h264_idct_add_neon)
+ movrel x13, .L_ff_h264_idct_dc_add_neon
+ movrel x14, .L_ff_h264_idct_add_neon
1: mov w2, w9
ldrb w3, [x7], #1
ldrsw x0, [x5], #4
@@ -133,8 +135,8 @@ function ff_h264_idct_add16intra_neon, export=1
mov w9, w3 // stride
movrel x7, scan8
mov x10, #16
- movrel x13, X(ff_h264_idct_dc_add_neon)
- movrel x14, X(ff_h264_idct_add_neon)
+ movrel x13, .L_ff_h264_idct_dc_add_neon
+ movrel x14, .L_ff_h264_idct_add_neon
1: mov w2, w9
ldrb w3, [x7], #1
ldrsw x0, [x5], #4
@@ -160,8 +162,8 @@ function ff_h264_idct_add8_neon, export=1
add x5, x1, #16*4 // block_offset
add x9, x2, #16*32 // block
mov w19, w3 // stride
- movrel x13, X(ff_h264_idct_dc_add_neon)
- movrel x14, X(ff_h264_idct_add_neon)
+ movrel x13, .L_ff_h264_idct_dc_add_neon
+ movrel x14, .L_ff_h264_idct_add_neon
movrel x7, scan8, 16
mov x10, #0
mov x11, #16
@@ -263,6 +265,7 @@ endfunc
.endm
function ff_h264_idct8_add_neon, export=1
+.L_ff_h264_idct8_add_neon:
movi v19.8H, #0
sxtw x2, w2
ld1 {v24.8H, v25.8H}, [x1]
@@ -326,6 +329,7 @@ function ff_h264_idct8_add_neon, export=1
endfunc
function ff_h264_idct8_dc_add_neon, export=1
+.L_ff_h264_idct8_dc_add_neon:
mov w3, #0
sxtw x2, w2
ld1r {v31.8H}, [x1]
@@ -375,8 +379,8 @@ function ff_h264_idct8_add4_neon, export=1
mov w2, w3
movrel x7, scan8
mov w10, #16
- movrel x13, X(ff_h264_idct8_dc_add_neon)
- movrel x14, X(ff_h264_idct8_add_neon)
+ movrel x13, .L_ff_h264_idct8_dc_add_neon
+ movrel x14, .L_ff_h264_idct8_add_neon
1: ldrb w9, [x7], #4
ldrsw x0, [x5], #16
ldrb w9, [x4, w9, UXTW]
--
2.21.0
|
