[FFmpeg-devel] [PATCH] libavcodec: Remove dynamic relocs from aarch64/h264idct_neon.S

[Manoj Gupta]

Hi All,

I recently had a problem building ffmpeg for AArch64 where lld linker
complained about text relocations in readonly segment. The following
patch fixes the linker complains by referring to a local label instead
of function name.

This is similar in nature as the following previous commits:
https://www.mail-archive.com/ffmpeg-cvslog@ffmpeg.org/msg34290.html
https://www.mail-archive.com/ffmpeg-cvslog@ffmpeg.org/msg34419.html

Thanks,
Manoj

Patch:

libavcodec: Remove dynamic relocs from aarch64/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 dynamic
relocations.
Use explicit labels instead so that no dynamic relocations are
needed at all.

This avoids lld complains about text relocations.

For background, see https://crbug.com/917919

Signed-off-by: Manoj Gupta <manojgupta at chromium.org>
---
 libavcodec/aarch64/h264idct_neon.S | 20 ++++++++++++--------
 1 file changed, 12 insertions(+), 8 deletions(-)

diff --git a/libavcodec/aarch64/h264idct_neon.S
b/libavcodec/aarch64/h264idct_neon.S
index 825ec49f8c..7de44205d3 100644
--- a/libavcodec/aarch64/h264idct_neon.S
+++ b/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]
--