Aaron Lindsay <aa...@os.amperecomputing.com> writes:
> On Oct 20 18:54, Alex Bennée wrote:
>> Have you got a test case you are using so I can try and replicate the
>> failure you are seeing? So far by inspection everything looks OK to me.
>
> I took some time today to put together a minimal(ish) reproducer using
> usermode. The source files used are below, I compiled the test binary on an
> AArch64 system using:
>
> $ gcc -g -o stxp stxp.s stxp.c
>
> Then built the plugin from stxp_plugin.cc, and ran it all like:
>
> qemu-aarch64 \
> -cpu cortex-a57 \
> -D stxp_plugin.log \
> -d plugin \
> -plugin 'stxp_plugin.so' \
> ./stxp
>
> I observe that, for me, the objdump of stxp contains:
> 000000000040070c <loop>:
> 40070c: f9800011 prfm pstl1strm, [x0]
> 400710: c87f4410 ldxp x16, x17, [x0]
> 400714: c8300c02 stxp w16, x2, x3, [x0]
> 400718: f1000652 subs x18, x18, #0x1
> 40071c: 54000040 b.eq 400724 <done> // b.none
> 400720: 17fffffb b 40070c <loop>
>
> But the output in stxp_plugin.log looks something like:
> Executing PC: 0x40070c
> Executing PC: 0x400710
> PC 0x400710 accessed memory at 0x550080ec70
> PC 0x400710 accessed memory at 0x550080ec78
> Executing PC: 0x400714
> Executing PC: 0x400718
> Executing PC: 0x40071c
> Executing PC: 0x400720
>
> From this, I believe the ldxp instruction at PC 0x400710 is reporting two
> memory accesses but the stxp instruction at 0x400714 is not.
This is fascinating but I can't replicate your results. I get the
following pattern:
Executing PC: 0x400910
Executing PC: 0x400914
PC 0x400914 accessed memory at 0x55007fffd0
PC 0x400914 accessed memory at 0x55007fffd8
Executing PC: 0x400918
PC 0x400918 accessed memory at 0x55007fffd0
PC 0x400918 accessed memory at 0x55007fffd8
PC 0x400918 accessed memory at 0x55007fffd0
PC 0x400918 accessed memory at 0x55007fffd8
Executing PC: 0x40091c
Executing PC: 0x400920
Executing PC: 0x400924
Executing PC: 0x400910
Executing PC: 0x400914
PC 0x400914 accessed memory at 0x55007fffd0
PC 0x400914 accessed memory at 0x55007fffd8
Executing PC: 0x400918
PC 0x400918 accessed memory at 0x55007fffd0
PC 0x400918 accessed memory at 0x55007fffd8
PC 0x400918 accessed memory at 0x55007fffd0
PC 0x400918 accessed memory at 0x55007fffd8
Executing PC: 0x40091c
Executing PC: 0x400920
Executing PC: 0x400924
Executing PC: 0x400910
Executing PC: 0x400914
PC 0x400914 accessed memory at 0x55007fffd0
PC 0x400914 accessed memory at 0x55007fffd8
Executing PC: 0x400918
PC 0x400918 accessed memory at 0x55007fffd0
PC 0x400918 accessed memory at 0x55007fffd8
PC 0x400918 accessed memory at 0x55007fffd0
PC 0x400918 accessed memory at 0x55007fffd8
Executing PC: 0x40091c
Executing PC: 0x400920
Executing PC: 0x400924
Executing PC: 0x400910
Executing PC: 0x400914
PC 0x400914 accessed memory at 0x55007fffd0
PC 0x400914 accessed memory at 0x55007fffd8
Executing PC: 0x400918
PC 0x400918 accessed memory at 0x55007fffd0
PC 0x400918 accessed memory at 0x55007fffd8
PC 0x400918 accessed memory at 0x55007fffd0
PC 0x400918 accessed memory at 0x55007fffd8
It's a bit clearer if you use the contrib/execlog plugin:
./qemu-aarch64 -plugin contrib/plugins/libexeclog.so -d plugin
./tests/tcg/aarch64-linux-user/stxp
0, 0x400910, 0xf9800011, "prfm pstl1strm, [x0]
0, 0x400914, 0xc87f4410, "ldxp x16, x17, [x0]", load, 0x55007fffd0, load,
0x55007fffd8
0, 0x400918, 0xc8300c02, "stxp w16, x2, x3, [x0]", load, 0x55007fffd0, load,
0x55007fffd8, store, 0x55007fffd0, store, 0x55007fffd8
0, 0x40091c, 0xf1000652, "subs x18, x18, #1"
0, 0x400920, 0x54000040, "b.eq #0x400928"
0, 0x400924, 0x17fffffb, "b #0x400910"
0, 0x400910, 0xf9800011, "prfm pstl1strm, [x0]
0, 0x400914, 0xc87f4410, "ldxp x16, x17, [x0]", load, 0x55007fffd0, load,
0x55007fffd8
0, 0x400918, 0xc8300c02, "stxp w16, x2, x3, [x0]", load, 0x55007fffd0, load,
0x55007fffd8, store, 0x55007fffd0, store, 0x55007fffd8
0, 0x40091c, 0xf1000652, "subs x18, x18, #1"
0, 0x400920, 0x54000040, "b.eq #0x400928"
0, 0x400924, 0x17fffffb, "b #0x400910"
0, 0x400910, 0xf9800011, "prfm pstl1strm, [x0]
0, 0x400914, 0xc87f4410, "ldxp x16, x17, [x0]", load, 0x55007fffd0, load,
0x55007fffd8
0, 0x400918, 0xc8300c02, "stxp w16, x2, x3, [x0]", load, 0x55007fffd0, load,
0x55007fffd8, store, 0x55007fffd0, store, 0x55007fffd8
0, 0x40091c, 0xf1000652, "subs x18, x18, #1"
0, 0x400920, 0x54000040, "b.eq #0x400928"
0, 0x400924, 0x17fffffb, "b #0x400910"
0, 0x400910, 0xf9800011, "prfm pstl1strm, [x0]
0, 0x400914, 0xc87f4410, "ldxp x16, x17, [x0]", load, 0x55007fffd0, load,
0x55007fffd8
0, 0x400918, 0xc8300c02, "stxp w16, x2, x3, [x0]", load, 0x55007fffd0, load,
0x55007fffd8, store, 0x55007fffd0, store, 0x55007fffd8
0, 0x40091c, 0xf1000652, "subs x18, x18, #1"
0, 0x400920, 0x54000040, "b.eq #0x400928"
0, 0x400924, 0x17fffffb, "b #0x400910"
0, 0x400910, 0xf9800011, "prfm pstl1strm, [x0]
0, 0x400914, 0xc87f4410, "ldxp x16, x17, [x0]", load, 0x55007fffd0, load,
0x55007fffd8
0, 0x400918, 0xc8300c02, "stxp w16, x2, x3, [x0]", load, 0x55007fffd0, load,
0x55007fffd8, store, 0x55007fffd0, store, 0x55007fffd8
0, 0x40091c, 0xf1000652, "subs x18, x18, #1"
0, 0x400920, 0x54000040, "b.eq #0x400928"
0, 0x400924, 0x17fffffb, "b #0x400910"
Although you can see stxp looks a bit weird on account of the loads it
does during the cmpxchng. So consider me stumped. The only thing I can
thing of next is to see how closely I can replicate your build
environment.
--
Alex Bennée
