[FFmpeg-devel] [PATCH 02/21] aarch64: hevc: Don't iterate with sp in ff_hevc_put_hevc_qpel_uni_w_hv32/64_8_neon_i8mm
Martin Storsjö
martin at martin.st
Mon Mar 25 17:02:24 EET 2024
Many of the routines within hevcdsp_epel_neon and hevcdsp_qpel_neon
store temporary buffers on the stack. When consuming it,
many of these functions use the stack pointer as incremental pointer
for reading the data (instead of storing it in another register),
which is rather unusual.
Technically, this is fine as long as the pointer remains properly
aligned.
However in the case of ff_hevc_put_hevc_qpel_uni_w_hv64_8_neon_i8mm,
after incrementing sp when reading data (within each 16 pixel
wide stripe) it would then reset the stack pointer back to a lower
value, for reading the next 16 pixel wide stripe, expecting the
data to remain untouched.
This can't be assumed; data on the stack below the stack pointer
can be clobbered (e.g. by a signal handler). Some OS ABIs
allow for a little margin that won't be touched, aka a red zone,
but not all do. The ones that do, guarantee 16 or 128 bytes, not
9 KB.
Convert this function to use a separate pointer register to
iterate through the data, retaining the stack pointer to point
at the bottom of the data we require to remain untouched.
---
libavcodec/aarch64/hevcdsp_qpel_neon.S | 130 +++++++++++++------------
1 file changed, 66 insertions(+), 64 deletions(-)
diff --git a/libavcodec/aarch64/hevcdsp_qpel_neon.S b/libavcodec/aarch64/hevcdsp_qpel_neon.S
index 9be29cafe2..815d897094 100644
--- a/libavcodec/aarch64/hevcdsp_qpel_neon.S
+++ b/libavcodec/aarch64/hevcdsp_qpel_neon.S
@@ -3981,24 +3981,25 @@ function ff_hevc_put_hevc_qpel_uni_w_hv32_8_neon_i8mm, export=1
mov x11, sp
mov w12, w22
mov x13, x20
+ mov x14, sp
3:
- ldp q16, q1, [sp]
- add sp, sp, x10
- ldp q17, q2, [sp]
- add sp, sp, x10
- ldp q18, q3, [sp]
- add sp, sp, x10
- ldp q19, q4, [sp]
- add sp, sp, x10
- ldp q20, q5, [sp]
- add sp, sp, x10
- ldp q21, q6, [sp]
- add sp, sp, x10
- ldp q22, q7, [sp]
- add sp, sp, x10
+ ldp q16, q1, [x11]
+ add x11, x11, x10
+ ldp q17, q2, [x11]
+ add x11, x11, x10
+ ldp q18, q3, [x11]
+ add x11, x11, x10
+ ldp q19, q4, [x11]
+ add x11, x11, x10
+ ldp q20, q5, [x11]
+ add x11, x11, x10
+ ldp q21, q6, [x11]
+ add x11, x11, x10
+ ldp q22, q7, [x11]
+ add x11, x11, x10
1:
- ldp q23, q31, [sp]
- add sp, sp, x10
+ ldp q23, q31, [x11]
+ add x11, x11, x10
QPEL_FILTER_H v24, v16, v17, v18, v19, v20, v21, v22, v23
QPEL_FILTER_H2 v25, v16, v17, v18, v19, v20, v21, v22, v23
QPEL_FILTER_H v26, v1, v2, v3, v4, v5, v6, v7, v31
@@ -4007,8 +4008,8 @@ function ff_hevc_put_hevc_qpel_uni_w_hv32_8_neon_i8mm, export=1
subs w22, w22, #1
b.eq 2f
- ldp q16, q1, [sp]
- add sp, sp, x10
+ ldp q16, q1, [x11]
+ add x11, x11, x10
QPEL_FILTER_H v24, v17, v18, v19, v20, v21, v22, v23, v16
QPEL_FILTER_H2 v25, v17, v18, v19, v20, v21, v22, v23, v16
QPEL_FILTER_H v26, v2, v3, v4, v5, v6, v7, v31, v1
@@ -4017,8 +4018,8 @@ function ff_hevc_put_hevc_qpel_uni_w_hv32_8_neon_i8mm, export=1
subs w22, w22, #1
b.eq 2f
- ldp q17, q2, [sp]
- add sp, sp, x10
+ ldp q17, q2, [x11]
+ add x11, x11, x10
QPEL_FILTER_H v24, v18, v19, v20, v21, v22, v23, v16, v17
QPEL_FILTER_H2 v25, v18, v19, v20, v21, v22, v23, v16, v17
QPEL_FILTER_H v26, v3, v4, v5, v6, v7, v31, v1, v2
@@ -4027,8 +4028,8 @@ function ff_hevc_put_hevc_qpel_uni_w_hv32_8_neon_i8mm, export=1
subs w22, w22, #1
b.eq 2f
- ldp q18, q3, [sp]
- add sp, sp, x10
+ ldp q18, q3, [x11]
+ add x11, x11, x10
QPEL_FILTER_H v24, v19, v20, v21, v22, v23, v16, v17, v18
QPEL_FILTER_H2 v25, v19, v20, v21, v22, v23, v16, v17, v18
QPEL_FILTER_H v26, v4, v5, v6, v7, v31, v1, v2, v3
@@ -4037,8 +4038,8 @@ function ff_hevc_put_hevc_qpel_uni_w_hv32_8_neon_i8mm, export=1
subs w22, w22, #1
b.eq 2f
- ldp q19, q4, [sp]
- add sp, sp, x10
+ ldp q19, q4, [x11]
+ add x11, x11, x10
QPEL_FILTER_H v24, v20, v21, v22, v23, v16, v17, v18, v19
QPEL_FILTER_H2 v25, v20, v21, v22, v23, v16, v17, v18, v19
QPEL_FILTER_H v26, v5, v6, v7, v31, v1, v2, v3, v4
@@ -4047,8 +4048,8 @@ function ff_hevc_put_hevc_qpel_uni_w_hv32_8_neon_i8mm, export=1
subs w22, w22, #1
b.eq 2f
- ldp q20, q5, [sp]
- add sp, sp, x10
+ ldp q20, q5, [x11]
+ add x11, x11, x10
QPEL_FILTER_H v24, v21, v22, v23, v16, v17, v18, v19, v20
QPEL_FILTER_H2 v25, v21, v22, v23, v16, v17, v18, v19, v20
QPEL_FILTER_H v26, v6, v7, v31, v1, v2, v3, v4, v5
@@ -4057,8 +4058,8 @@ function ff_hevc_put_hevc_qpel_uni_w_hv32_8_neon_i8mm, export=1
subs w22, w22, #1
b.eq 2f
- ldp q21, q6, [sp]
- add sp, sp, x10
+ ldp q21, q6, [x11]
+ add x11, x11, x10
QPEL_FILTER_H v24, v22, v23, v16, v17, v18, v19, v20, v21
QPEL_FILTER_H2 v25, v22, v23, v16, v17, v18, v19, v20, v21
QPEL_FILTER_H v26, v7, v31, v1, v2, v3, v4, v5, v6
@@ -4067,8 +4068,8 @@ function ff_hevc_put_hevc_qpel_uni_w_hv32_8_neon_i8mm, export=1
subs w22, w22, #1
b.eq 2f
- ldp q22, q7, [sp]
- add sp, sp, x10
+ ldp q22, q7, [x11]
+ add x11, x11, x10
QPEL_FILTER_H v24, v23, v16, v17, v18, v19, v20, v21, v22
QPEL_FILTER_H2 v25, v23, v16, v17, v18, v19, v20, v21, v22
QPEL_FILTER_H v26, v31, v1, v2, v3, v4, v5, v6, v7
@@ -4078,10 +4079,10 @@ function ff_hevc_put_hevc_qpel_uni_w_hv32_8_neon_i8mm, export=1
b.hi 1b
2:
subs w27, w27, #16
- add sp, x11, #32
+ add x11, x14, #32
add x20, x13, #16
mov w22, w12
- mov x11, sp
+ mov x14, x11
mov x13, x20
b.hi 3b
QPEL_UNI_W_HV_END
@@ -4093,24 +4094,25 @@ function ff_hevc_put_hevc_qpel_uni_w_hv64_8_neon_i8mm, export=1
mov x11, sp
mov w12, w22
mov x13, x20
+ mov x14, sp
3:
- ldp q16, q1, [sp]
- add sp, sp, x10
- ldp q17, q2, [sp]
- add sp, sp, x10
- ldp q18, q3, [sp]
- add sp, sp, x10
- ldp q19, q4, [sp]
- add sp, sp, x10
- ldp q20, q5, [sp]
- add sp, sp, x10
- ldp q21, q6, [sp]
- add sp, sp, x10
- ldp q22, q7, [sp]
- add sp, sp, x10
+ ldp q16, q1, [x11]
+ add x11, x11, x10
+ ldp q17, q2, [x11]
+ add x11, x11, x10
+ ldp q18, q3, [x11]
+ add x11, x11, x10
+ ldp q19, q4, [x11]
+ add x11, x11, x10
+ ldp q20, q5, [x11]
+ add x11, x11, x10
+ ldp q21, q6, [x11]
+ add x11, x11, x10
+ ldp q22, q7, [x11]
+ add x11, x11, x10
1:
- ldp q23, q31, [sp]
- add sp, sp, x10
+ ldp q23, q31, [x11]
+ add x11, x11, x10
QPEL_FILTER_H v24, v16, v17, v18, v19, v20, v21, v22, v23
QPEL_FILTER_H2 v25, v16, v17, v18, v19, v20, v21, v22, v23
QPEL_FILTER_H v26, v1, v2, v3, v4, v5, v6, v7, v31
@@ -4119,8 +4121,8 @@ function ff_hevc_put_hevc_qpel_uni_w_hv64_8_neon_i8mm, export=1
subs w22, w22, #1
b.eq 2f
- ldp q16, q1, [sp]
- add sp, sp, x10
+ ldp q16, q1, [x11]
+ add x11, x11, x10
QPEL_FILTER_H v24, v17, v18, v19, v20, v21, v22, v23, v16
QPEL_FILTER_H2 v25, v17, v18, v19, v20, v21, v22, v23, v16
QPEL_FILTER_H v26, v2, v3, v4, v5, v6, v7, v31, v1
@@ -4129,8 +4131,8 @@ function ff_hevc_put_hevc_qpel_uni_w_hv64_8_neon_i8mm, export=1
subs w22, w22, #1
b.eq 2f
- ldp q17, q2, [sp]
- add sp, sp, x10
+ ldp q17, q2, [x11]
+ add x11, x11, x10
QPEL_FILTER_H v24, v18, v19, v20, v21, v22, v23, v16, v17
QPEL_FILTER_H2 v25, v18, v19, v20, v21, v22, v23, v16, v17
QPEL_FILTER_H v26, v3, v4, v5, v6, v7, v31, v1, v2
@@ -4139,8 +4141,8 @@ function ff_hevc_put_hevc_qpel_uni_w_hv64_8_neon_i8mm, export=1
subs w22, w22, #1
b.eq 2f
- ldp q18, q3, [sp]
- add sp, sp, x10
+ ldp q18, q3, [x11]
+ add x11, x11, x10
QPEL_FILTER_H v24, v19, v20, v21, v22, v23, v16, v17, v18
QPEL_FILTER_H2 v25, v19, v20, v21, v22, v23, v16, v17, v18
QPEL_FILTER_H v26, v4, v5, v6, v7, v31, v1, v2, v3
@@ -4149,8 +4151,8 @@ function ff_hevc_put_hevc_qpel_uni_w_hv64_8_neon_i8mm, export=1
subs w22, w22, #1
b.eq 2f
- ldp q19, q4, [sp]
- add sp, sp, x10
+ ldp q19, q4, [x11]
+ add x11, x11, x10
QPEL_FILTER_H v24, v20, v21, v22, v23, v16, v17, v18, v19
QPEL_FILTER_H2 v25, v20, v21, v22, v23, v16, v17, v18, v19
QPEL_FILTER_H v26, v5, v6, v7, v31, v1, v2, v3, v4
@@ -4159,8 +4161,8 @@ function ff_hevc_put_hevc_qpel_uni_w_hv64_8_neon_i8mm, export=1
subs w22, w22, #1
b.eq 2f
- ldp q20, q5, [sp]
- add sp, sp, x10
+ ldp q20, q5, [x11]
+ add x11, x11, x10
QPEL_FILTER_H v24, v21, v22, v23, v16, v17, v18, v19, v20
QPEL_FILTER_H2 v25, v21, v22, v23, v16, v17, v18, v19, v20
QPEL_FILTER_H v26, v6, v7, v31, v1, v2, v3, v4, v5
@@ -4169,8 +4171,8 @@ function ff_hevc_put_hevc_qpel_uni_w_hv64_8_neon_i8mm, export=1
subs w22, w22, #1
b.eq 2f
- ldp q21, q6, [sp]
- add sp, sp, x10
+ ldp q21, q6, [x11]
+ add x11, x11, x10
QPEL_FILTER_H v24, v22, v23, v16, v17, v18, v19, v20, v21
QPEL_FILTER_H2 v25, v22, v23, v16, v17, v18, v19, v20, v21
QPEL_FILTER_H v26, v7, v31, v1, v2, v3, v4, v5, v6
@@ -4179,8 +4181,8 @@ function ff_hevc_put_hevc_qpel_uni_w_hv64_8_neon_i8mm, export=1
subs w22, w22, #1
b.eq 2f
- ldp q22, q7, [sp]
- add sp, sp, x10
+ ldp q22, q7, [x11]
+ add x11, x11, x10
QPEL_FILTER_H v24, v23, v16, v17, v18, v19, v20, v21, v22
QPEL_FILTER_H2 v25, v23, v16, v17, v18, v19, v20, v21, v22
QPEL_FILTER_H v26, v31, v1, v2, v3, v4, v5, v6, v7
@@ -4190,10 +4192,10 @@ function ff_hevc_put_hevc_qpel_uni_w_hv64_8_neon_i8mm, export=1
b.hi 1b
2:
subs w27, w27, #16
- add sp, x11, #32
+ add x11, x14, #32
add x20, x13, #16
mov w22, w12
- mov x11, sp
+ mov x14, x11
mov x13, x20
b.hi 3b
QPEL_UNI_W_HV_END
--
2.39.3 (Apple Git-146)
More information about the ffmpeg-devel
mailing list