Re: [dpdk-dev] [PATCH 00/14] cleanup resources on shutdown

[David Marchand <david.marchand@redhat.com>]

On Sat, Jan 4, 2020 at 2:34 AM Stephen Hemminger
<stephen@networkplumber.org> wrote:
>
> Recently started using valgrind with DPDK, and the results
> are not clean.
>
> The DPDK has a function that applications can use to tell it
> to cleanup resources on shutdown (rte_eal_cleanup). But the
> current coverage of that API is spotty. Many internal parts of
> DPDK leave files and allocated memory behind.
>
> This patch set is a start at getting the sub-parts of
> DPDK to cleanup after themselves. These are the easier ones,
> the harder and more critical ones are in the drivers
> and the memory subsystem.
>
> There are no visible API or ABI changes here.

I was about to push the series (except patch 10), but I hit a crash
when passing an invalid option to test-null.sh.

Reproduced with:

Core was generated by
`/home/dmarchan/builds/x86_64-native-linux-gcc+shared+kmods/app/testpmd
-c 0x3 --log-level='.
Program terminated with signal SIGSEGV, Segmentation fault.
#0  0x00007fd5231dba64 in pthread_cancel () from /usr/lib64/libpthread.so.0
Missing separate debuginfos, use: dnf debuginfo-install
elfutils-libelf-0.178-7.fc30.x86_64 glibc-2.29-28.fc30.x86_64
jansson-2.12-2.fc30.x86_64 libgcc-9.2.1-1.fc30.x86_64
libpcap-1.9.1-1.fc30.x86_64 numactl-libs-2.0.12-2.fc30.x86_64
zlib-1.2.11-19.fc30.x86_64
(gdb) bt full
#0  0x00007fd5231dba64 in pthread_cancel () from /usr/lib64/libpthread.so.0
No symbol table info available.
#1  0x00007fd52320c586 in rte_eal_cleanup () at
/home/dmarchan/dpdk/lib/librte_eal/linux/eal.c:1339
        i = 1
#2  0x00007fd523215f5e in rte_exit (exit_code=exit_code@entry=1,
format=format@entry=0x47ada4 "Cannot init EAL: %s\n") at
/home/dmarchan/dpdk/lib/librte_eal/linux/eal_debug.c:83
        ap = {{gp_offset = 24, fp_offset = 48, overflow_arg_area =
0x7ffecdf7aa70, reg_save_area = 0x7ffecdf7a9a0}}
#3  0x000000000043535b in main (argc=21, argv=0x7ffecdf7abc8) at
/home/dmarchan/dpdk/app/test-pmd/testpmd.c:3647
        diag = -1
        port_id = <optimized out>
        count = <optimized out>
        ret = <optimized out>
(gdb) f 1
#1  0x00007fd52320c586 in rte_eal_cleanup () at
/home/dmarchan/dpdk/lib/librte_eal/linux/eal.c:1339
1339            pthread_cancel(lcore_config[i].thread_id);
(gdb) p lcore_config[1].thread_id
$1 = 0

rte_eal_cleanup() is called from rte_exit() by testpmd.
But since rte_eal_init() failed at parsing, lcore_config[*].thread_id
are invalid, and we crash on pthread_cancel.
I have no quick idea to fix this, series postponed to rc2.


-- 
David Marchand