[net-next,v2,3/3] connector/cn_proc: Selftest for threads

Test to check if setting PROC_CN_MCAST_NOTIFY in proc connector API, allows
a thread's non-zero exit status to be returned to proc_filter.

The threads.c program creates 2 child threads. 1st thread handles signal
SIGSEGV, and 2nd thread needs to indicate some error condition (value 1)
to the kernel, instead of using pthread_exit() with 1.

In both cases, child sends notify_netlink_thread_exit(exit_code) to kernel,
to let kernel know it has exited abnormally with exit_code.

Compile:
    make thread
    make proc_filter
To see non-zero exit notifications, run:
    ./proc_filter -f
Run threads code in another window:
    ./threads
Note the 2 child thread IDs reported above
Send SIGSEGV signal to the child handling SIGSEGV:
    kill -11 <child1-tid>
Watch the child 1 tid being notified with exit code 11 to proc_filter
Watch child 2 tid being notified with exit code 1 (value defined in code)
to proc_filter

Signed-off-by: Anjali Kulkarni <anjali.k.kulkarni@oracle.com>
---
 tools/testing/selftests/connector/Makefile    |  23 +++-
 .../testing/selftests/connector/proc_filter.c |   5 +
 tools/testing/selftests/connector/thread.c    | 116 ++++++++++++++++++
 .../selftests/connector/thread_filter.c       |  96 +++++++++++++++
 4 files changed, 239 insertions(+), 1 deletion(-)
 create mode 100644 tools/testing/selftests/connector/thread.c
 create mode 100644 tools/testing/selftests/connector/thread_filter.c

> On Oct 15, 2024, at 12:27 PM, Liam Howlett <liam.howlett@oracle.com> wrote:
> 
> * Anjali Kulkarni <anjali.k.kulkarni@oracle.com> [241015 13:30]:
>> Test to check if setting PROC_CN_MCAST_NOTIFY in proc connector API, allows
>> a thread's non-zero exit status to be returned to proc_filter.
>> 
>> The threads.c program creates 2 child threads. 1st thread handles signal
>> SIGSEGV, and 2nd thread needs to indicate some error condition (value 1)
>> to the kernel, instead of using pthread_exit() with 1.
>> 
>> In both cases, child sends notify_netlink_thread_exit(exit_code) to kernel,
>> to let kernel know it has exited abnormally with exit_code.
>> 
>> Compile:
>>    make thread
>>    make proc_filter
>> To see non-zero exit notifications, run:
>>    ./proc_filter -f
>> Run threads code in another window:
>>    ./threads
>> Note the 2 child thread IDs reported above
>> Send SIGSEGV signal to the child handling SIGSEGV:
>>    kill -11 <child1-tid>
>> Watch the child 1 tid being notified with exit code 11 to proc_filter
>> Watch child 2 tid being notified with exit code 1 (value defined in code)
>> to proc_filter
>> 
>> Signed-off-by: Anjali Kulkarni <anjali.k.kulkarni@oracle.com>
>> ---
>> tools/testing/selftests/connector/Makefile    |  23 +++-
>> .../testing/selftests/connector/proc_filter.c |   5 +
>> tools/testing/selftests/connector/thread.c    | 116 ++++++++++++++++++
>> .../selftests/connector/thread_filter.c       |  96 +++++++++++++++
>> 4 files changed, 239 insertions(+), 1 deletion(-)
>> create mode 100644 tools/testing/selftests/connector/thread.c
>> create mode 100644 tools/testing/selftests/connector/thread_filter.c
>> 
>> diff --git a/tools/testing/selftests/connector/Makefile b/tools/testing/selftests/connector/Makefile
>> index 92188b9bac5c..bf335826bc3b 100644
>> --- a/tools/testing/selftests/connector/Makefile
>> +++ b/tools/testing/selftests/connector/Makefile
>> @@ -1,5 +1,26 @@
>> # SPDX-License-Identifier: GPL-2.0
>> -CFLAGS += -Wall $(KHDR_INCLUDES)
>> +KERNEL="../../../.."
>> +
>> +CFLAGS += -Wall $(KHDR_INCLUDES) -I $(KERNEL)/include/uapi -I $(KERNEL)/include
>> +
>> +proc_filter: proc_filter.o
>> + cc proc_filter.o -o proc_filter
>> +
>> +proc_filter.o: proc_filter.c
>> + cc -c proc_filter.c -o proc_filter.o $(CFLAGS)
>> +
>> +thread: thread.o thread_filter.o
>> + cc thread.o thread_filter.o -o thread
>> +
>> +thread.o: thread.c $(DEPS)
>> + cc -c thread.c -o thread.o $(CFLAGS)
>> +
>> +thread_filter.o: thread_filter.c
>> + cc -c thread_filter.c -o thread_filter.o $(CFLAGS)
>> +
>> +define EXTRA_CLEAN
>> + rm *.o thread
>> +endef
>> 
>> TEST_GEN_PROGS = proc_filter
>> 
>> diff --git a/tools/testing/selftests/connector/proc_filter.c b/tools/testing/selftests/connector/proc_filter.c
>> index 4a825b997666..6fb4842894f8 100644
>> --- a/tools/testing/selftests/connector/proc_filter.c
>> +++ b/tools/testing/selftests/connector/proc_filter.c
>> @@ -1,4 +1,9 @@
>> // SPDX-License-Identifier: GPL-2.0-only
>> +/*
>> + * Author: Anjali Kulkarni <anjali.k.kulkarni@oracle.com>
>> + *
>> + * Copyright (c) 2024 Oracle and/or its affiliates.
>> + */
>> 
>> #include <sys/types.h>
>> #include <sys/epoll.h>
>> diff --git a/tools/testing/selftests/connector/thread.c b/tools/testing/selftests/connector/thread.c
>> new file mode 100644
>> index 000000000000..8c9abf6115d6
>> --- /dev/null
>> +++ b/tools/testing/selftests/connector/thread.c
>> @@ -0,0 +1,116 @@
>> +// SPDX-License-Identifier: GPL-2.0-only
>> +/*
>> + * Author: Anjali Kulkarni <anjali.k.kulkarni@oracle.com>
>> + *
>> + * Copyright (c) 2024 Oracle and/or its affiliates.
>> + */
>> +
>> +#include <pthread.h>
>> +#include <stdio.h>
>> +#include <unistd.h>
>> +#include <stdlib.h>
>> +#include <signal.h>
>> +
>> +/*
>> + * This code tests a thread exit notification when thread exits abnormally.
>> + * Normally, when a thread exits abnormally, the kernel is not aware of the
>> + * exit code. This is usually only conveyed from child to parent via the
>> + * pthread_exit() and pthread_join() calls. Sometimes, however, a parent
>> + * process cannot monitor all child processes via pthread_join(), particularly
>> + * when there is a huge amount of child processes. In this case, the parent
>> + * has created the child with PTHREAD_CREATE_DETACHED attribute.
>> + * To fix this problem, either when child wants to convey non-zero exit via
>> + * pthread_exit() or in a signal handler, the child can notify the kernel's
>> + * connector module it's exit status via a netlink call with new type
>> + * PROC_CN_MCAST_NOTIFY. (Implemented in the thread_filter.c file).
>> + * This will send the exit code from the child to the kernel, which the kernel
>> + * can later return to proc_filter program when the child actually exits.
>> + * To test this usecase:
>> + * Compile:
>> + * make thread
>> + * make proc_filter
>> + * To see non-zero exit notifications, run:
>> + * ./proc_filter -f
>> + * Start the threads code, creating 2 threads, in another window:
>> + * ./threads
>> + * Note the 2 child thread IDs reported above
>> + * Send SIGSEGV signal to the child handling SIGSEGV:
>> + * kill -11 <child1-tid>
>> + * Watch the event being notified with exit code 11 to proc_filter
>> + * Watch child 2 tid being notified with exit code 1 (value defined in code)
>> + * to proc_filter
>> + */
>> +
>> +extern int notify_netlink_thread_exit(unsigned int exit_code);
>> +
>> +static void sigsegvh(int sig)
>> +{
>> + unsigned int exit_code = (unsigned int) sig;
>> + /*
>> +  * Send any non-zero value to get a notification. Here we are
>> +  * sending the signal number for SIGSEGV which is 11
>> +  */
>> + notify_netlink_thread_exit(exit_code);
>> +}
>> +
>> +void *threadc1(void *ptr)
>> +{
>> + signal(SIGSEGV, sigsegvh);
>> + printf("Child 1 thread id %d, handling SIGSEGV\n", gettid());
>> + sleep(20);
>> + pthread_exit(NULL);
>> +}
>> +
>> +void *threadc2(void *ptr)
>> +{
>> + int exit_val = 1;
>> +
>> + printf("Child 2 thread id %d, wants to exit with value %d\n",
>> + gettid(), exit_val);
>> + sleep(2);
>> + notify_netlink_thread_exit(exit_val);
>> + pthread_exit(NULL);
>> +}
>> +
>> +int main(int argc, char **argv)
>> +{
>> + pthread_t thread1, thread2;
>> + pthread_attr_t attr1, attr2;
>> + int ret;
>> +
>> + ret = pthread_attr_init(&attr1);
>> + if (ret != 0) {
>> + perror("pthread_attr_init failed");
>> + exit(ret);
>> + }
>> + ret = pthread_attr_setdetachstate(&attr1, PTHREAD_CREATE_DETACHED);
>> + if (ret != 0) {
>> + perror("pthread_attr_setdetachstate failed");
>> + exit(ret);
>> + }
>> + ret = pthread_create(&thread1, &attr1, *threadc1, NULL);
>> + if (ret != 0) {
>> + perror("pthread_create failed");
>> + exit(ret);
>> + }
>> +
>> + ret = pthread_attr_init(&attr2);
>> + if (ret != 0) {
>> + perror("pthread_attr_init failed");
>> + exit(ret);
>> + }
>> + ret = pthread_attr_setdetachstate(&attr2, PTHREAD_CREATE_DETACHED);
>> + if (ret != 0) {
>> + perror("pthread_attr_setdetachstate failed");
>> + exit(ret);
>> + }
>> + ret = pthread_create(&thread2, &attr2, *threadc2, NULL);
>> + if (ret != 0) {
>> + perror("pthread_create failed");
>> + exit(ret);
>> + }
> 
> I expected the test to check for the correct value to be returned?
> Could you use pthread_join() and verify the same value is returned
> through the new mechanism, or will they not match?

This is a manual test, you need to check visually that the proc_filter
Is returning correct values for the 2 cases. I can make this an
automated test, reading the output of proc_filter directly from a file
and checking the values are as expected.
There is also another test program which does an automated test
of the values returned by proc_filter for scale (100k or so), which I
will send out later. (The co-author of that patch, who wrote the
original code for processes, is away - @peili.io@oracle.com)
pthread_join() cannot return a value to the kernel, so we cannot
use it to verify the new mechanism. 

> 
>> +
>> + /* Wait for children to exit or be killed */
>> + sleep(30);
>> + exit(0);
>> +}
>> diff --git a/tools/testing/selftests/connector/thread_filter.c b/tools/testing/selftests/connector/thread_filter.c
>> new file mode 100644
>> index 000000000000..3da740aa7537
>> --- /dev/null
>> +++ b/tools/testing/selftests/connector/thread_filter.c
>> @@ -0,0 +1,96 @@
>> +// SPDX-License-Identifier: GPL-2.0-only
>> +/*
>> + * Author: Anjali Kulkarni <anjali.k.kulkarni@oracle.com>
>> + *
>> + * Copyright (c) 2024 Oracle and/or its affiliates.
>> + */
>> +
>> +#include <sys/types.h>
>> +#include <sys/epoll.h>
>> +#include <sys/socket.h>
>> +#include <linux/netlink.h>
>> +#include <linux/connector.h>
>> +#include <linux/cn_proc.h>
>> +
>> +#include <stddef.h>
>> +#include <stdio.h>
>> +#include <stdlib.h>
>> +#include <unistd.h>
>> +#include <strings.h>
>> +#include <errno.h>
>> +#include <signal.h>
>> +#include <string.h>
>> +
>> +#define NL_MESSAGE_SIZE (sizeof(struct nlmsghdr) + sizeof(struct cn_msg) + \
>> + sizeof(struct proc_input))
>> +
>> +/*
>> + * Send PROC_CN_MCAST_NOTIFY type notification to the connector code in kernel.
>> + * This will send the exit_code specified by user to the connector layer, so
>> + * it can send a notification for that event to any listening process
>> + */
>> +int send_message(int nl_sock, unsigned int exit_code)
>> +{
>> + char buff[NL_MESSAGE_SIZE];
>> + struct nlmsghdr *hdr;
>> + struct cn_msg *msg;
>> +
>> + hdr = (struct nlmsghdr *)buff;
>> + hdr->nlmsg_len = NL_MESSAGE_SIZE;
>> + hdr->nlmsg_type = NLMSG_DONE;
>> + hdr->nlmsg_flags = 0;
>> + hdr->nlmsg_seq = 0;
>> + hdr->nlmsg_pid = getpid();
>> +
>> + msg = (struct cn_msg *)NLMSG_DATA(hdr);
>> + msg->id.idx = CN_IDX_PROC;
>> + msg->id.val = CN_VAL_PROC;
>> + msg->seq = 0;
>> + msg->ack = 0;
>> + msg->flags = 0;
>> +
>> + msg->len = sizeof(struct proc_input);
>> + ((struct proc_input *)msg->data)->mcast_op =
>> + PROC_CN_MCAST_NOTIFY;
>> + ((struct proc_input *)msg->data)->uexit_code = exit_code;
>> +
>> + if (send(nl_sock, hdr, hdr->nlmsg_len, 0) == -1) {
>> + perror("send failed");
>> + return -errno;
>> + }
>> + return 0;
>> +}
>> +
>> +int notify_netlink_thread_exit(unsigned int exit_code)
>> +{
>> + struct sockaddr_nl sa_nl;
>> + int err = 0;
>> + int nl_sock;
>> +
>> + nl_sock = socket(PF_NETLINK, SOCK_DGRAM, NETLINK_CONNECTOR);
>> +
>> + if (nl_sock == -1) {
>> + perror("socket failed");
>> + return -errno;
>> + }
>> +
>> + bzero(&sa_nl, sizeof(sa_nl));
>> + sa_nl.nl_family = AF_NETLINK;
>> + sa_nl.nl_groups = CN_IDX_PROC;
>> + sa_nl.nl_pid    = gettid();
>> +
>> + if (bind(nl_sock, (struct sockaddr *)&sa_nl, sizeof(sa_nl)) == -1) {
>> + perror("bind failed");
>> + close(nl_sock);
>> + return -errno;
>> + }
>> +
>> + err = send_message(nl_sock, exit_code);
>> +
>> + close(nl_sock);
>> +
>> + if (err < 0)
>> + return err;
>> +
>> + return 0;
>> +}
>> -- 
>> 2.46.0