MrBesen
/
ffmpeg
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

aarch64: Add Armv8.5-A BTI support 

Add Branch Target Identifiers (BTIs) to all functions defined in
AArch64 assembly files. Most of the BTI landing pads are added
automatically by the 'function' macro.

BTI support is turned on or off at compile time based on the presence
of the __ARM_FEATURE_BTI_DEFAULT feature macro.

A binary compiled with BTI support can be executed on an Armv8-A
processor without BTI support because the instructions are defined in
NOP space.

Signed-off-by: Jonathan Wright <jonathan.wright@arm.com>
Signed-off-by: Elijah Ahmad <elijah.ahmad@arm.com>
Signed-off-by: Martin Storsjö <martin@martin.st>
This commit is contained in:
Jonathan Wright 2020-09-28 13:35:51 +01:00 committed by Martin Storsjö
parent 6f04cf54f5
commit 08b4716a9e
3 changed files with 38 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
libavcodec/aarch64/fft_neon.S
View File

@ -36,6 +36,7 @@
function fft4_neon
AARCH64_VALID_JUMP_TARGET
ld1 {v0.2s,v1.2s,v2.2s,v3.2s}, [x0]
fadd v4.2s, v0.2s, v1.2s // r0+r1,i0+i1
@ -58,6 +59,7 @@ function fft4_neon
endfunc
function fft8_neon
AARCH64_VALID_JUMP_TARGET
mov x1, x0
ld1 {v0.2s, v1.2s, v2.2s, v3.2s}, [x0], #32
ld1 {v16.2s,v17.2s,v18.2s,v19.2s}, [x0]
@ -108,6 +110,7 @@ function fft8_neon
endfunc
function fft16_neon
AARCH64_VALID_JUMP_TARGET
mov x1, x0
ld1 {v0.2s, v1.2s, v2.2s, v3.2s}, [x0], #32
ld1 {v16.2s,v17.2s,v18.2s,v19.2s}, [x0], #32
@ -337,6 +340,7 @@ endfunc
.macro def_fft n, n2, n4
function fft\n\()_neon, align=6
AARCH64_VALID_JUMP_TARGET
sub sp, sp, #16
stp x28, x30, [sp]
add x28, x0, #\n4*2*8

4
libavcodec/aarch64/h264idct_neon.S
View File

@ -24,6 +24,7 @@
function ff_h264_idct_add_neon, export=1
.L_ff_h264_idct_add_neon:
AARCH64_VALID_CALL_TARGET
ld1 {v0.4H, v1.4H, v2.4H, v3.4H}, [x1]
sxtw x2, w2
movi v30.8H, #0
@ -79,6 +80,7 @@ endfunc
function ff_h264_idct_dc_add_neon, export=1
.L_ff_h264_idct_dc_add_neon:
AARCH64_VALID_CALL_TARGET
sxtw x2, w2
mov w3, #0
ld1r {v2.8H}, [x1]
@ -266,6 +268,7 @@ endfunc
function ff_h264_idct8_add_neon, export=1
.L_ff_h264_idct8_add_neon:
AARCH64_VALID_CALL_TARGET
movi v19.8H, #0
sxtw x2, w2
ld1 {v24.8H, v25.8H}, [x1]
@ -330,6 +333,7 @@ endfunc
function ff_h264_idct8_dc_add_neon, export=1
.L_ff_h264_idct8_dc_add_neon:
AARCH64_VALID_CALL_TARGET
mov w3, #0
sxtw x2, w2
ld1r {v31.8H}, [x1]

30
libavutil/aarch64/asm.S
View File

@ -36,6 +36,35 @@
# define __has_feature(x) 0
#endif
/* Support macros for the Armv8.5-A Branch Target Identification feature which
* requires emitting a .note.gnu.property section with the appropriate
* architecture-dependent feature bits set.
* Read more: "ELF for the Arm® 64-bit Architecture"
*/
#if defined(__ARM_FEATURE_BTI_DEFAULT) && (__ARM_FEATURE_BTI_DEFAULT == 1)
# define GNU_PROPERTY_AARCH64_BTI (1 << 0) // Has BTI
# define AARCH64_VALID_CALL_TARGET hint #34 // BTI 'c'
# define AARCH64_VALID_JUMP_TARGET hint #38 // BTI 'j'
#else
# define GNU_PROPERTY_AARCH64_BTI 0 // No BTI
# define AARCH64_VALID_CALL_TARGET
# define AARCH64_VALID_JUMP_TARGET
#endif
#if (GNU_PROPERTY_AARCH64_BTI != 0)
.pushsection .note.gnu.property, "a"
.balign 8
.long 4
.long 0x10
.long 0x5
.asciz "GNU"
.long 0xc0000000 /* GNU_PROPERTY_AARCH64_FEATURE_1_AND */
.long 4
.long GNU_PROPERTY_AARCH64_BTI
.long 0
.popsection
#endif
.macro function name, export=0, align=2
.macro endfunc
ELF .size \name, . - \name
@ -49,6 +78,7 @@ FUNC .endfunc
ELF .type EXTERN_ASM\name, %function
FUNC .func EXTERN_ASM\name
EXTERN_ASM\name:
AARCH64_VALID_CALL_TARGET
.else
ELF .type \name, %function
FUNC .func \name