Re: [Bonding-devel] [PATCH] [bonding 2.4] fix creating/destroying the /proc/net/bonding dir

[Jay Vosburgh <fubar@xxxxxxxxxx>]

>This patch makes bonding create the /proc/net/bonding directory only
>if it exists (and destroy it only if it's empty).
>
>Synchronization with the NETDEV_CHANGENAME event is achieved through
>the RTNL semaphore.

        I've managed to break this running some scripts/programs to
simultaneously insmod/rmmod bonding, change the interface names, and
cat /proc/net/bonding/bondX files.  After the scripts run for a while,
the system ends up in a state where /proc/net/bonding/ is always
empty, no matter how many instances of bonding are loaded.

        Removing all instances of bonding also removes
/proc/net/bonding/ from /proc/net ("ls /proc/net" does not show it),
but "ls /proc/net/bonding" will succeed, showing an empty directory.
A subsequent insmod of bonding will create an always-empty
/proc/net/bonding (which again shows up in "ls /proc/net").  This
seems to be bad.

        I'm running this test on a 2 way 933, 640MB memory running
2.4.23-pre9 with the patch appiled.  I've reproduced this result twice
by running all three scripts simultaneously.  I haven't yet determined
what the problem is, but I'm presuming there's a race in the patched
code somewhere.  My test programs (3 scripts and a C program) are
appended.  When the "readproc-random" script stops printing "success"
messages, the error has occured.

        -J

---
        -Jay Vosburgh, IBM Linux Technology Center, fubar@xxxxxxxxxx

insmod-random.sh:
#!/bin/sh

isucc=0
rsucc=0
while /bin/true; do
        insert=${RANDOM};
        insert=`expr ${insert} % 2`
        num=${RANDOM};
        num=`expr ${num} % 10`;

        if [ ${insert} -eq 1 ]; then
                insmod -o bonding${num} bonding mode=0 > /dev/null 2>&1
                if [ $? -eq 0 ]; then
                    isucc=`expr ${isucc} + 1`;
                    echo "insmod success " ${isucc};
                fi
        else
                rmmod bonding${num} > /dev/null 2>&1
                if [ $? -eq 0 ]; then
                    rsucc=`expr ${rsucc} + 1`;
                    echo "rmmod  success " ${rsucc};
                fi
        fi
done

readproc-random.sh:
#!/bin/sh

succ=0
while /bin/true; do
        num=`expr ${RANDOM} % 10`;

        cat /proc/net/bonding/bond${num} > /dev/null 2>&1
        if [ $? -eq 0 ]; then
                succ=`expr ${succ} + 1`
                echo "success " ${succ};
        fi

done

sifname-random.sh:
#!/bin/sh

succ=0;
while /bin/true; do
        num1=`expr ${RANDOM} % 10`;
        num2=`expr ${RANDOM} % 10`;
        if [ ${num1} -eq ${num2} ]; then
                continue;
        fi

        ./sifname bond${num1} bond${num2} > /dev/null 2>&1
        if [ $? -eq 0]; then
                succ=`expr ${succ} + 1`
                echo "success " ${succ};
        fi

done

sifname.c:
#include <stdio.h>
#include <sys/socket.h>
#include <netinet/in.h>
#include <net/if.h>
#include <linux/sockios.h>
#include <sys/ioctl.h>

int
main(int argc, char **argv)
{
        int rv, s;
        struct ifreq ifr;

        if (argc != 3) {
                fprintf(stderr, "usage: %s oldifname newifname\n", argv[0]);
                exit(1);
        }

        s = socket(PF_INET, SOCK_STREAM, 0);
        if (-1 == s) {
                perror("socket");
                exit(1);
        }

        memset(&ifr, 0, sizeof(ifr));
        memmove(&ifr.ifr_name, argv[1], strlen(argv[1]));
        memmove(&ifr.ifr_newname, argv[2], strlen(argv[2]));

        rv = ioctl(s, SIOCSIFNAME, &ifr);
        if (-1 == rv) {
                perror("ioctl(SIOCSIFNAME)");
                exit(1);
        }

        return 0;
}