* [PATCH net-next v6 1/3] connector/cn_proc: Add hash table for threads
2024-10-23 16:20 [PATCH net-next v6 0/3] Threads support in proc connector Anjali Kulkarni
@ 2024-10-23 16:20 ` Anjali Kulkarni
2024-10-31 0:57 ` Jakub Kicinski
2024-10-23 16:20 ` [PATCH net-next v6 2/3] connector/cn_proc: Kunit tests for threads hash table Anjali Kulkarni
2024-10-23 16:20 ` [PATCH net-next v6 3/3] connector/cn_proc: Selftest for threads Anjali Kulkarni
2 siblings, 1 reply; 5+ messages in thread
From: Anjali Kulkarni @ 2024-10-23 16:20 UTC (permalink / raw)
To: davem, Liam.Howlett
Cc: edumazet, kuba, pabeni, mingo, peterz, juri.lelli,
vincent.guittot, dietmar.eggemann, rostedt, bsegall, mgorman,
vschneid, jiri, linux-kernel, netdev, akpm, brendan.higgins,
davidgow, rmoar, johannes.berg, mic, gnoack, jk, kunit-dev, shuah,
linux-kselftest, anjali.k.kulkarni, peili.io
Add a new type PROC_CN_MCAST_NOTIFY to proc connector API, which allows a
thread to notify the kernel that is going to exit with a non-zero exit
code and specify the exit code in it. When thread exits in the kernel,
it will send this exit code as a proc filter notification to any
listening process.
Exiting thread can call this either when it wants to call pthread_exit()
with non-zero value or from signal handler.
Add a new file cn_hash.c which implements a hash table storing the exit
codes of abnormally exiting threads, received by the system call above.
The key used for the hash table is the pid of the thread, so when the
thread actually exits, we lookup it's pid in the hash table and retrieve
the exit code sent by user. If the exit code in struct task is 0, we
then replace it with the user supplied non-zero exit code.
cn_hash.c implements the hash table add, delete, lookup operations.
mutex_lock() and mutex_unlock() operations are used to safeguard the
integrity of the hash table while adding or deleting elements.
connector.c has the API calls, called from cn_proc.c, as well as calls
to allocate, initialize and free the hash table.
Add a new flag in PF_* flags of task_struct - EXIT_NOTIFY. This flag is
set when user sends the exit code via PROC_CN_MCAST_NOTIFY. While
exiting, this flag is checked and the hash table add or delete calls
are only made if this flag is set.
A refcount field hrefcnt is added in struct cn_hash_dev, to keep track
of number of threads which have added an entry in hash table. Before
freeing the struct cn_hash_dev, this value must be 0.
This refcnt check is added in case CONFIG_CONNECTOR is compiled as a
module. In that case, when unloading the module, we need to make sure
no hash entries are still present in the hdev table.
Signed-off-by: Anjali Kulkarni <anjali.k.kulkarni@oracle.com>
---
drivers/connector/Makefile | 2 +-
drivers/connector/cn_hash.c | 176 ++++++++++++++++++++++++++++++++++
drivers/connector/cn_proc.c | 81 +++++++++++++---
drivers/connector/connector.c | 76 +++++++++++++--
include/linux/connector.h | 58 ++++++++---
include/linux/sched.h | 2 +-
include/uapi/linux/cn_proc.h | 4 +-
7 files changed, 364 insertions(+), 35 deletions(-)
create mode 100644 drivers/connector/cn_hash.c
diff --git a/drivers/connector/Makefile b/drivers/connector/Makefile
index 1bf67d3df97d..cb1dcdf067ad 100644
--- a/drivers/connector/Makefile
+++ b/drivers/connector/Makefile
@@ -2,4 +2,4 @@
obj-$(CONFIG_CONNECTOR) += cn.o
obj-$(CONFIG_PROC_EVENTS) += cn_proc.o
-cn-y += cn_queue.o connector.o
+cn-y += cn_hash.o cn_queue.o connector.o
diff --git a/drivers/connector/cn_hash.c b/drivers/connector/cn_hash.c
new file mode 100644
index 000000000000..b94f6c461496
--- /dev/null
+++ b/drivers/connector/cn_hash.c
@@ -0,0 +1,176 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Author: Anjali Kulkarni <anjali.k.kulkarni@oracle.com>
+ *
+ * Copyright (c) 2024 Oracle and/or its affiliates.
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/connector.h>
+#include <linux/mutex.h>
+#include <linux/pid_namespace.h>
+
+#include <linux/cn_proc.h>
+
+struct cn_hash_dev *cn_hash_alloc_dev(const char *name)
+{
+ struct cn_hash_dev *hdev;
+
+ hdev = kzalloc(sizeof(*hdev), GFP_KERNEL);
+ if (!hdev)
+ return NULL;
+
+ snprintf(hdev->name, sizeof(hdev->name), "%s", name);
+ atomic_set(&hdev->hrefcnt, 0);
+ mutex_init(&hdev->uexit_hash_lock);
+ hash_init(hdev->uexit_pid_htable);
+ return hdev;
+}
+
+void cn_hash_free_dev(struct cn_hash_dev *hdev)
+{
+ struct uexit_pid_hnode *hnode;
+ struct hlist_node *tmp;
+ int bucket;
+
+ pr_debug("%s: Freeing entire hdev %p\n", __func__, hdev);
+
+ mutex_lock(&hdev->uexit_hash_lock);
+ hash_for_each_safe(hdev->uexit_pid_htable, bucket, tmp,
+ hnode, uexit_pid_hlist) {
+ hash_del(&hnode->uexit_pid_hlist);
+ pr_debug("%s: Freeing node for pid %d\n",
+ __func__, hnode->pid);
+ kfree(hnode);
+ }
+
+ mutex_unlock(&hdev->uexit_hash_lock);
+ mutex_destroy(&hdev->uexit_hash_lock);
+
+ /*
+ * This refcnt check is added in case CONFIG_CONNECTOR is
+ * compiled with =m as a module. In that case, when unloading
+ * the module, we need to make sure no hash entries are still
+ * present in the hdev table.
+ */
+ while (atomic_read(&hdev->hrefcnt)) {
+ pr_info("Waiting for %s to become free: refcnt=%d\n",
+ hdev->name, atomic_read(&hdev->hrefcnt));
+ msleep(1000);
+ }
+
+ kfree(hdev);
+ hdev = NULL;
+}
+
+static struct uexit_pid_hnode *cn_hash_alloc_elem(__u32 uexit_code, pid_t pid)
+{
+ struct uexit_pid_hnode *elem;
+
+ elem = kzalloc(sizeof(*elem), GFP_KERNEL);
+ if (!elem)
+ return NULL;
+
+ INIT_HLIST_NODE(&elem->uexit_pid_hlist);
+ elem->uexit_code = uexit_code;
+ elem->pid = pid;
+ return elem;
+}
+
+int cn_hash_add_elem(struct cn_hash_dev *hdev, __u32 uexit_code, pid_t pid)
+{
+ struct uexit_pid_hnode *elem, *hnode;
+
+ elem = cn_hash_alloc_elem(uexit_code, pid);
+ if (!elem) {
+ pr_err("%s: cn_hash_alloc_elem() returned NULL pid %d\n",
+ __func__, pid);
+ return -ENOMEM;
+ }
+
+ mutex_lock(&hdev->uexit_hash_lock);
+ /*
+ * Check if an entry for the same pid already exists
+ */
+ hash_for_each_possible(hdev->uexit_pid_htable,
+ hnode, uexit_pid_hlist, pid) {
+ if (hnode->pid == pid) {
+ mutex_unlock(&hdev->uexit_hash_lock);
+ kfree(elem);
+ pr_debug("%s: pid %d already exists in hash table\n",
+ __func__, pid);
+ return -EEXIST;
+ }
+ }
+
+ hash_add(hdev->uexit_pid_htable, &elem->uexit_pid_hlist, pid);
+ mutex_unlock(&hdev->uexit_hash_lock);
+
+ atomic_inc(&hdev->hrefcnt);
+
+ pr_debug("%s: After hash_add of pid %d elem %p hrefcnt %d\n",
+ __func__, pid, elem, atomic_read(&hdev->hrefcnt));
+ return 0;
+}
+
+int cn_hash_del_get_exval(struct cn_hash_dev *hdev, pid_t pid)
+{
+ struct uexit_pid_hnode *hnode;
+ struct hlist_node *tmp;
+ int excde;
+
+ mutex_lock(&hdev->uexit_hash_lock);
+ hash_for_each_possible_safe(hdev->uexit_pid_htable,
+ hnode, tmp, uexit_pid_hlist, pid) {
+ if (hnode->pid == pid) {
+ excde = hnode->uexit_code;
+ hash_del(&hnode->uexit_pid_hlist);
+ mutex_unlock(&hdev->uexit_hash_lock);
+ kfree(hnode);
+ atomic_dec(&hdev->hrefcnt);
+ pr_debug("%s: After hash_del of pid %d, found exit code %u hrefcnt %d\n",
+ __func__, pid, excde,
+ atomic_read(&hdev->hrefcnt));
+ return excde;
+ }
+ }
+
+ mutex_unlock(&hdev->uexit_hash_lock);
+ pr_err("%s: pid %d not found in hash table\n",
+ __func__, pid);
+ return -EINVAL;
+}
+
+int cn_hash_get_exval(struct cn_hash_dev *hdev, pid_t pid)
+{
+ struct uexit_pid_hnode *hnode;
+ __u32 excde;
+
+ mutex_lock(&hdev->uexit_hash_lock);
+ hash_for_each_possible(hdev->uexit_pid_htable,
+ hnode, uexit_pid_hlist, pid) {
+ if (hnode->pid == pid) {
+ excde = hnode->uexit_code;
+ mutex_unlock(&hdev->uexit_hash_lock);
+ pr_debug("%s: Found exit code %u for pid %d\n",
+ __func__, excde, pid);
+ return excde;
+ }
+ }
+
+ mutex_unlock(&hdev->uexit_hash_lock);
+ pr_debug("%s: pid %d not found in hash table\n",
+ __func__, pid);
+ return -EINVAL;
+}
+
+bool cn_hash_table_empty(struct cn_hash_dev *hdev)
+{
+ bool is_empty;
+
+ is_empty = hash_empty(hdev->uexit_pid_htable);
+ pr_debug("Hash table is %s\n", (is_empty ? "empty" : "not empty"));
+
+ return is_empty;
+}
diff --git a/drivers/connector/cn_proc.c b/drivers/connector/cn_proc.c
index 44b19e696176..36241f2d0c14 100644
--- a/drivers/connector/cn_proc.c
+++ b/drivers/connector/cn_proc.c
@@ -44,6 +44,7 @@ struct local_event {
local_lock_t lock;
__u32 count;
};
+
static DEFINE_PER_CPU(struct local_event, local_event) = {
.lock = INIT_LOCAL_LOCK(lock),
};
@@ -69,12 +70,14 @@ static int cn_filter(struct sock *dsk, struct sk_buff *skb, void *data)
if ((__u32)val == PROC_EVENT_ALL)
return 0;
+ pr_debug("%s: val %lx, what %x\n", __func__, val, what);
+
/*
* Drop packet if we have to report only non-zero exit status
* (PROC_EVENT_NONZERO_EXIT) and exit status is 0
*/
if (((__u32)val & PROC_EVENT_NONZERO_EXIT) &&
- (what == PROC_EVENT_EXIT)) {
+ what == PROC_EVENT_EXIT) {
if (exit_code)
return 0;
}
@@ -187,11 +190,15 @@ void proc_id_connector(struct task_struct *task, int which_id)
rcu_read_lock();
cred = __task_cred(task);
if (which_id == PROC_EVENT_UID) {
- ev->event_data.id.r.ruid = from_kuid_munged(&init_user_ns, cred->uid);
- ev->event_data.id.e.euid = from_kuid_munged(&init_user_ns, cred->euid);
+ ev->event_data.id.r.ruid =
+ from_kuid_munged(&init_user_ns, cred->uid);
+ ev->event_data.id.e.euid =
+ from_kuid_munged(&init_user_ns, cred->euid);
} else if (which_id == PROC_EVENT_GID) {
- ev->event_data.id.r.rgid = from_kgid_munged(&init_user_ns, cred->gid);
- ev->event_data.id.e.egid = from_kgid_munged(&init_user_ns, cred->egid);
+ ev->event_data.id.r.rgid =
+ from_kgid_munged(&init_user_ns, cred->gid);
+ ev->event_data.id.e.egid =
+ from_kgid_munged(&init_user_ns, cred->egid);
} else {
rcu_read_unlock();
return;
@@ -252,8 +259,9 @@ void proc_ptrace_connector(struct task_struct *task, int ptrace_id)
} else if (ptrace_id == PTRACE_DETACH) {
ev->event_data.ptrace.tracer_pid = 0;
ev->event_data.ptrace.tracer_tgid = 0;
- } else
+ } else {
return;
+ }
memcpy(&msg->id, &cn_proc_event_id, sizeof(msg->id));
msg->ack = 0; /* not used */
@@ -326,9 +334,15 @@ void proc_exit_connector(struct task_struct *task)
struct proc_event *ev;
struct task_struct *parent;
__u8 buffer[CN_PROC_MSG_SIZE] __aligned(8);
+ int uexit_code;
- if (atomic_read(&proc_event_num_listeners) < 1)
+ if (atomic_read(&proc_event_num_listeners) < 1) {
+ if (likely(!(task->flags & PF_EXIT_NOTIFY)))
+ return;
+
+ cn_del_get_exval(task->pid);
return;
+ }
msg = buffer_to_cn_msg(buffer);
ev = (struct proc_event *)msg->data;
@@ -337,7 +351,26 @@ void proc_exit_connector(struct task_struct *task)
ev->what = PROC_EVENT_EXIT;
ev->event_data.exit.process_pid = task->pid;
ev->event_data.exit.process_tgid = task->tgid;
- ev->event_data.exit.exit_code = task->exit_code;
+ if (unlikely(task->flags & PF_EXIT_NOTIFY)) {
+ task->flags &= ~PF_EXIT_NOTIFY;
+
+ uexit_code = cn_del_get_exval(task->pid);
+ if (uexit_code <= 0) {
+ pr_debug("%s: err %d returning task's exit code %u\n",
+ __func__, uexit_code,
+ task->exit_code);
+ ev->event_data.exit.exit_code = task->exit_code;
+ } else {
+ ev->event_data.exit.exit_code = uexit_code;
+ pr_debug("%s: Reset PF_EXIT_NOTIFY & retrieved exit code %u from hash table, pid %d\n",
+ __func__,
+ ev->event_data.exit.exit_code,
+ task->pid);
+ }
+ } else {
+ ev->event_data.exit.exit_code = task->exit_code;
+ }
+
ev->event_data.exit.exit_signal = task->exit_signal;
rcu_read_lock();
@@ -356,7 +389,7 @@ void proc_exit_connector(struct task_struct *task)
}
/*
- * Send an acknowledgement message to userspace
+ * Send an acknowledgment message to userspace
*
* Use 0 for success, EFOO otherwise.
* Note: this is the negative of conventional kernel error
@@ -401,7 +434,7 @@ static void cn_proc_mcast_ctl(struct cn_msg *msg,
int err = 0, initial = 0;
struct sock *sk = NULL;
- /*
+ /*
* Events are reported with respect to the initial pid
* and user namespaces so ignore requestors from
* other namespaces.
@@ -413,6 +446,13 @@ static void cn_proc_mcast_ctl(struct cn_msg *msg,
if (msg->len == sizeof(*pinput)) {
pinput = (struct proc_input *)msg->data;
mc_op = pinput->mcast_op;
+ if (mc_op == PROC_CN_MCAST_NOTIFY) {
+ pr_debug("%s: Received PROC_CN_MCAST_NOTIFY, pid %d\n",
+ __func__, current->pid);
+ current->flags |= PF_EXIT_NOTIFY;
+ err = cn_add_elem(pinput->uexit_code, current->pid);
+ return;
+ }
ev_type = pinput->event_type;
} else if (msg->len == sizeof(mc_op)) {
mc_op = *((enum proc_cn_mcast_op *)msg->data);
@@ -428,10 +468,12 @@ static void cn_proc_mcast_ctl(struct cn_msg *msg,
if (nsp->sk) {
sk = nsp->sk;
- if (sk->sk_user_data == NULL) {
+ if (!sk->sk_user_data) {
sk->sk_user_data = kzalloc(sizeof(struct proc_input),
GFP_KERNEL);
- if (sk->sk_user_data == NULL) {
+ if (!sk->sk_user_data) {
+ pr_err("%s: Alloc fail sk_user_data, pid %d\n",
+ __func__, current->pid);
err = ENOMEM;
goto out;
}
@@ -442,21 +484,32 @@ static void cn_proc_mcast_ctl(struct cn_msg *msg,
}
((struct proc_input *)(sk->sk_user_data))->event_type =
ev_type;
+ pr_debug("%s: sk: %p pid: %d event_type: %x\n",
+ __func__, sk, current->pid, ev_type);
((struct proc_input *)(sk->sk_user_data))->mcast_op = mc_op;
}
switch (mc_op) {
case PROC_CN_MCAST_LISTEN:
- if (initial || (prev_mc_op != PROC_CN_MCAST_LISTEN))
+ if (initial || prev_mc_op != PROC_CN_MCAST_LISTEN) {
atomic_inc(&proc_event_num_listeners);
+ pr_debug("%s: PROC_CN_MCAST_LISTEN pid %d: Incremented listeners to %d\n",
+ __func__, current->pid,
+ atomic_read(&proc_event_num_listeners));
+ }
break;
case PROC_CN_MCAST_IGNORE:
- if (!initial && (prev_mc_op != PROC_CN_MCAST_IGNORE))
+ if (!initial && prev_mc_op != PROC_CN_MCAST_IGNORE) {
atomic_dec(&proc_event_num_listeners);
+ pr_debug("%s: PROC_CN_MCAST_IGNORE pid %d: Decremented listeners to %d\n",
+ __func__, current->pid,
+ atomic_read(&proc_event_num_listeners));
+ }
((struct proc_input *)(sk->sk_user_data))->event_type =
PROC_EVENT_NONE;
break;
default:
+ pr_warn("%s: Invalid value for mc_op %d\n", __func__, mc_op);
err = EINVAL;
break;
}
diff --git a/drivers/connector/connector.c b/drivers/connector/connector.c
index 4028e8eeba82..2494a443fbd6 100644
--- a/drivers/connector/connector.c
+++ b/drivers/connector/connector.c
@@ -48,8 +48,8 @@ static int cn_already_initialized;
* one we are expecting then it is a new message.
*
* If we receive a message and its sequence number is the same as one
- * we are expecting but it's acknowledgement number is not equal to
- * the acknowledgement number in the original message + 1, then it is
+ * we are expecting but it's acknowledgment number is not equal to
+ * the acknowledgment number in the original message + 1, then it is
* a new message.
*
* If msg->len != len, then additional cn_msg messages are expected following
@@ -121,7 +121,7 @@ EXPORT_SYMBOL_GPL(cn_netlink_send_mult);
/* same as cn_netlink_send_mult except msg->len is used for len */
int cn_netlink_send(struct cn_msg *msg, u32 portid, u32 __group,
- gfp_t gfp_mask)
+ gfp_t gfp_mask)
{
return cn_netlink_send_mult(msg, msg->len, portid, __group, gfp_mask,
NULL, NULL);
@@ -155,7 +155,7 @@ static int cn_call_callback(struct sk_buff *skb)
}
spin_unlock_bh(&dev->cbdev->queue_lock);
- if (cbq != NULL) {
+ if (cbq) {
cbq->callback(msg, nsp);
kfree_skb(skb);
cn_queue_release_callback(cbq);
@@ -171,7 +171,7 @@ static int cn_call_callback(struct sk_buff *skb)
*/
static int cn_bind(struct net *net, int group)
{
- unsigned long groups = (unsigned long) group;
+ unsigned long groups = (unsigned long)group;
if (ns_capable(net->user_ns, CAP_NET_ADMIN))
return 0;
@@ -271,6 +271,50 @@ static int __maybe_unused cn_proc_show(struct seq_file *m, void *v)
return 0;
}
+int cn_del_get_exval(pid_t pid)
+{
+ struct cn_dev *dev = &cdev;
+
+ if (!cn_already_initialized)
+ return 0;
+
+ return cn_hash_del_get_exval(dev->hdev, pid);
+}
+EXPORT_SYMBOL_GPL(cn_del_get_exval);
+
+int cn_add_elem(__u32 uexit_code, pid_t pid)
+{
+ struct cn_dev *dev = &cdev;
+
+ if (!cn_already_initialized)
+ return 0;
+
+ return cn_hash_add_elem(dev->hdev, uexit_code, pid);
+}
+EXPORT_SYMBOL_GPL(cn_add_elem);
+
+int cn_get_exval(pid_t pid)
+{
+ struct cn_dev *dev = &cdev;
+
+ if (!cn_already_initialized)
+ return 0;
+
+ return cn_hash_get_exval(dev->hdev, pid);
+}
+EXPORT_SYMBOL_GPL(cn_get_exval);
+
+bool cn_table_empty(void)
+{
+ struct cn_dev *dev = &cdev;
+
+ if (!cn_already_initialized)
+ return 0;
+
+ return cn_hash_table_empty(dev->hdev);
+}
+EXPORT_SYMBOL_GPL(cn_table_empty);
+
static int cn_init(void)
{
struct cn_dev *dev = &cdev;
@@ -283,18 +327,35 @@ static int cn_init(void)
};
dev->nls = netlink_kernel_create(&init_net, NETLINK_CONNECTOR, &cfg);
- if (!dev->nls)
+ if (!dev->nls) {
+ pr_err("%s: netlink_kernel_create failed, connector not initialized\n",
+ __func__);
return -EIO;
+ }
dev->cbdev = cn_queue_alloc_dev("cqueue", dev->nls);
if (!dev->cbdev) {
+ pr_err("%s: Allocation of dev->cbdev failed, connector not initialized\n",
+ __func__);
netlink_kernel_release(dev->nls);
return -EINVAL;
}
+ dev->hdev = cn_hash_alloc_dev("pid hash table");
+ if (!dev->hdev) {
+ pr_err("%s: Allocation of dev->hdev failed, connector not initialized\n",
+ __func__);
+ netlink_kernel_release(dev->nls);
+ cn_queue_free_dev(dev->cbdev);
+ return -ENOMEM;
+ }
+
+ pr_debug("Connector initialized, allocated hdev %p\n", dev->hdev);
+
cn_already_initialized = 1;
- proc_create_single("connector", S_IRUGO, init_net.proc_net, cn_proc_show);
+ proc_create_single("connector", S_IRUGO, init_net.proc_net,
+ cn_proc_show);
return 0;
}
@@ -308,6 +369,7 @@ static void cn_fini(void)
remove_proc_entry("connector", init_net.proc_net);
cn_queue_free_dev(dev->cbdev);
+ cn_hash_free_dev(dev->hdev);
netlink_kernel_release(dev->nls);
}
diff --git a/include/linux/connector.h b/include/linux/connector.h
index 70bc1160f3d8..3f0648c886bc 100644
--- a/include/linux/connector.h
+++ b/include/linux/connector.h
@@ -1,14 +1,13 @@
/* SPDX-License-Identifier: GPL-2.0-or-later */
/*
- * connector.h
- *
+ * connector.h
+ *
* 2004-2005 Copyright (c) Evgeniy Polyakov <zbr@ioremap.net>
* All rights reserved.
*/
#ifndef __CONNECTOR_H
#define __CONNECTOR_H
-
#include <linux/refcount.h>
#include <linux/list.h>
@@ -18,6 +17,8 @@
#include <uapi/linux/connector.h>
#define CN_CBQ_NAMELEN 32
+#define HASHT_NAMELEN 32
+#define PID_HASH_TABLE_BITS 10
struct cn_queue_dev {
atomic_t refcnt;
@@ -40,11 +41,29 @@ struct cn_callback_entry {
struct cn_queue_dev *pdev;
struct cn_callback_id id;
- void (*callback) (struct cn_msg *, struct netlink_skb_parms *);
+ void (*callback)(struct cn_msg *, struct netlink_skb_parms *);
u32 seq, group;
};
+struct uexit_pid_hnode {
+ __u32 uexit_code;
+ pid_t pid;
+ struct hlist_node uexit_pid_hlist;
+};
+
+struct cn_hash_dev {
+ atomic_t hrefcnt;
+ unsigned char name[HASHT_NAMELEN];
+ /*
+ * This mutex is used to lock the hash table to allow
+ * multiple threads to add their pid & exit code to it.
+ * Shared between all threads.
+ */
+ struct mutex uexit_hash_lock;
+ DECLARE_HASHTABLE(uexit_pid_htable, PID_HASH_TABLE_BITS);
+};
+
struct cn_dev {
struct cb_id id;
@@ -52,6 +71,7 @@ struct cn_dev {
struct sock *nls;
struct cn_queue_dev *cbdev;
+ struct cn_hash_dev *hdev;
};
/**
@@ -62,10 +82,11 @@ struct cn_dev {
* in-kernel users.
* @name: connector's callback symbolic name.
* @callback: connector's callback.
- * parameters are %cn_msg and the sender's credentials
+ * parameters are %cn_msg and the sender's credentials
*/
int cn_add_callback(const struct cb_id *id, const char *name,
- void (*callback)(struct cn_msg *, struct netlink_skb_parms *));
+ void (*callback)(struct cn_msg *,
+ struct netlink_skb_parms *));
/**
* cn_del_callback() - Unregisters new callback with connector core.
*
@@ -73,17 +94,16 @@ int cn_add_callback(const struct cb_id *id, const char *name,
*/
void cn_del_callback(const struct cb_id *id);
-
/**
* cn_netlink_send_mult - Sends message to the specified groups.
*
- * @msg: message header(with attached data).
+ * @msg: message header(with attached data).
* @len: Number of @msg to be sent.
* @portid: destination port.
* If non-zero the message will be sent to the given port,
* which should be set to the original sender.
* @group: destination group.
- * If @portid and @group is zero, then appropriate group will
+ * If @portid and @group is zero, then appropriate group will
* be searched through all registered connector users, and
* message will be delivered to the group which was created
* for user with the same ID as in @msg.
@@ -111,7 +131,7 @@ int cn_netlink_send_mult(struct cn_msg *msg, u16 len, u32 portid,
* If non-zero the message will be sent to the given port,
* which should be set to the original sender.
* @group: destination group.
- * If @portid and @group is zero, then appropriate group will
+ * If @portid and @group is zero, then appropriate group will
* be searched through all registered connector users, and
* message will be delivered to the group which was created
* for user with the same ID as in @msg.
@@ -128,7 +148,8 @@ int cn_netlink_send(struct cn_msg *msg, u32 portid, u32 group, gfp_t gfp_mask);
int cn_queue_add_callback(struct cn_queue_dev *dev, const char *name,
const struct cb_id *id,
- void (*callback)(struct cn_msg *, struct netlink_skb_parms *));
+ void (*callback)(struct cn_msg *,
+ struct netlink_skb_parms *));
void cn_queue_del_callback(struct cn_queue_dev *dev, const struct cb_id *id);
void cn_queue_release_callback(struct cn_callback_entry *);
@@ -137,4 +158,19 @@ void cn_queue_free_dev(struct cn_queue_dev *dev);
int cn_cb_equal(const struct cb_id *, const struct cb_id *);
+struct cn_hash_dev *cn_hash_alloc_dev(const char *name);
+void cn_hash_free_dev(struct cn_hash_dev *hdev);
+struct uexit_pid_hnode *cn_hash_find_pid_node(struct cn_hash_dev *hdev,
+ pid_t pid);
+int cn_hash_add_elem(struct cn_hash_dev *hdev, __u32 uexit_code, pid_t pid);
+int cn_hash_del_get_exval(struct cn_hash_dev *hdev, pid_t pid);
+int cn_hash_get_exval(struct cn_hash_dev *hdev, pid_t pid);
+
+int cn_add_elem(__u32 uexit_code, pid_t pid);
+int cn_del_get_exval(pid_t pid);
+int cn_get_exval(pid_t pid);
+
+bool cn_table_empty(void);
+bool cn_hash_table_empty(struct cn_hash_dev *hdev);
+
#endif /* __CONNECTOR_H */
diff --git a/include/linux/sched.h b/include/linux/sched.h
index e6ee4258169a..a2339ae6208b 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1673,7 +1673,7 @@ extern struct pid *cad_pid;
#define PF_USED_MATH 0x00002000 /* If unset the fpu must be initialized before use */
#define PF_USER_WORKER 0x00004000 /* Kernel thread cloned from userspace thread */
#define PF_NOFREEZE 0x00008000 /* This thread should not be frozen */
-#define PF__HOLE__00010000 0x00010000
+#define PF_EXIT_NOTIFY 0x00010000 /* This thread has sent an exit value to be sent as a notification to listening processes */
#define PF_KSWAPD 0x00020000 /* I am kswapd */
#define PF_MEMALLOC_NOFS 0x00040000 /* All allocations inherit GFP_NOFS. See memalloc_nfs_save() */
#define PF_MEMALLOC_NOIO 0x00080000 /* All allocations inherit GFP_NOIO. See memalloc_noio_save() */
diff --git a/include/uapi/linux/cn_proc.h b/include/uapi/linux/cn_proc.h
index 18e3745b86cd..2b12a24e4651 100644
--- a/include/uapi/linux/cn_proc.h
+++ b/include/uapi/linux/cn_proc.h
@@ -27,7 +27,8 @@
*/
enum proc_cn_mcast_op {
PROC_CN_MCAST_LISTEN = 1,
- PROC_CN_MCAST_IGNORE = 2
+ PROC_CN_MCAST_IGNORE = 2,
+ PROC_CN_MCAST_NOTIFY = 3
};
#define PROC_EVENT_ALL (PROC_EVENT_FORK | PROC_EVENT_EXEC | PROC_EVENT_UID | \
@@ -65,6 +66,7 @@ enum proc_cn_event {
struct proc_input {
enum proc_cn_mcast_op mcast_op;
enum proc_cn_event event_type;
+ __u32 uexit_code;
};
static inline enum proc_cn_event valid_event(enum proc_cn_event ev_type)
--
2.46.0
^ permalink raw reply related [flat|nested] 5+ messages in thread* Re: [PATCH net-next v6 1/3] connector/cn_proc: Add hash table for threads
2024-10-23 16:20 ` [PATCH net-next v6 1/3] connector/cn_proc: Add hash table for threads Anjali Kulkarni
@ 2024-10-31 0:57 ` Jakub Kicinski
0 siblings, 0 replies; 5+ messages in thread
From: Jakub Kicinski @ 2024-10-31 0:57 UTC (permalink / raw)
To: Anjali Kulkarni
Cc: davem, Liam.Howlett, edumazet, pabeni, mingo, peterz, juri.lelli,
vincent.guittot, dietmar.eggemann, rostedt, bsegall, mgorman,
vschneid, jiri, linux-kernel, netdev, akpm, brendan.higgins,
davidgow, rmoar, johannes.berg, mic, gnoack, jk, kunit-dev, shuah,
linux-kselftest, peili.io
On Wed, 23 Oct 2024 09:20:04 -0700 Anjali Kulkarni wrote:
> Add a new type PROC_CN_MCAST_NOTIFY to proc connector API, which allows a
> thread to notify the kernel that is going to exit with a non-zero exit
> code and specify the exit code in it. When thread exits in the kernel,
> it will send this exit code as a proc filter notification to any
> listening process.
While we wait for someone who knows about process management to review
this - could you please split out the whitespace / checkpatch cleanup
changes to a separate commit? They make the change harder to review.
--
pw-bot: cr
^ permalink raw reply [flat|nested] 5+ messages in thread
* [PATCH net-next v6 2/3] connector/cn_proc: Kunit tests for threads hash table
2024-10-23 16:20 [PATCH net-next v6 0/3] Threads support in proc connector Anjali Kulkarni
2024-10-23 16:20 ` [PATCH net-next v6 1/3] connector/cn_proc: Add hash table for threads Anjali Kulkarni
@ 2024-10-23 16:20 ` Anjali Kulkarni
2024-10-23 16:20 ` [PATCH net-next v6 3/3] connector/cn_proc: Selftest for threads Anjali Kulkarni
2 siblings, 0 replies; 5+ messages in thread
From: Anjali Kulkarni @ 2024-10-23 16:20 UTC (permalink / raw)
To: davem, Liam.Howlett
Cc: edumazet, kuba, pabeni, mingo, peterz, juri.lelli,
vincent.guittot, dietmar.eggemann, rostedt, bsegall, mgorman,
vschneid, jiri, linux-kernel, netdev, akpm, brendan.higgins,
davidgow, rmoar, johannes.berg, mic, gnoack, jk, kunit-dev, shuah,
linux-kselftest, anjali.k.kulkarni, peili.io
Kunit tests to test hash table add, delete, duplicate add and delete.
Add following configs and compile kernel code:
CONFIG_CONNECTOR=y
CONFIG_PROC_EVENTS=y
CONFIG_NET=y
CONFIG_KUNIT=m
CONFIG_CN_HASH_KUNIT_TEST=m
To run kunit tests:
sudo modprobe cn_hash_test
Output of kunit tests and hash table contents are displayed in
/var/log/messages (at KERN_DEBUG level).
Signed-off-by: Anjali Kulkarni <anjali.k.kulkarni@oracle.com>
---
drivers/connector/cn_hash.c | 40 +++++
drivers/connector/connector.c | 12 ++
include/linux/connector.h | 4 +
lib/Kconfig.debug | 19 +++
lib/Makefile | 1 +
lib/cn_hash_test.c | 169 +++++++++++++++++++
lib/cn_hash_test.h | 10 ++
tools/testing/kunit/configs/all_tests.config | 5 +
8 files changed, 260 insertions(+)
create mode 100644 lib/cn_hash_test.c
create mode 100644 lib/cn_hash_test.h
diff --git a/drivers/connector/cn_hash.c b/drivers/connector/cn_hash.c
index b94f6c461496..a8b8760c2e8c 100644
--- a/drivers/connector/cn_hash.c
+++ b/drivers/connector/cn_hash.c
@@ -165,6 +165,46 @@ int cn_hash_get_exval(struct cn_hash_dev *hdev, pid_t pid)
return -EINVAL;
}
+int cn_hash_display_hlist(struct cn_hash_dev *hdev, pid_t pid, int max_len,
+ int *hkey, int *key_display)
+{
+ struct uexit_pid_hnode *hnode;
+ int key, count = 0;
+
+ mutex_lock(&hdev->uexit_hash_lock);
+ key = hash_min(pid, HASH_BITS(hdev->uexit_pid_htable));
+ pr_debug("Bucket: %d\n", key);
+
+ hlist_for_each_entry(hnode,
+ &hdev->uexit_pid_htable[key],
+ uexit_pid_hlist) {
+ if (key_display[key] != 1) {
+ if (!hnode->uexit_pid_hlist.next)
+ pr_debug("pid %d ", hnode->pid);
+ else
+ pr_debug("pid %d --> ", hnode->pid);
+ }
+ count++;
+ }
+
+ mutex_unlock(&hdev->uexit_hash_lock);
+
+ if (key_display[key] != 1 && !count)
+ pr_debug("(empty)\n");
+
+ pr_debug("\n");
+
+ *hkey = key;
+
+ if (count > max_len) {
+ pr_err("%d entries in hlist for key %d, expected %d\n",
+ count, key, max_len);
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
bool cn_hash_table_empty(struct cn_hash_dev *hdev)
{
bool is_empty;
diff --git a/drivers/connector/connector.c b/drivers/connector/connector.c
index 2494a443fbd6..9b0cbe134e87 100644
--- a/drivers/connector/connector.c
+++ b/drivers/connector/connector.c
@@ -304,6 +304,18 @@ int cn_get_exval(pid_t pid)
}
EXPORT_SYMBOL_GPL(cn_get_exval);
+int cn_display_hlist(pid_t pid, int max_len, int *hkey, int *key_display)
+{
+ struct cn_dev *dev = &cdev;
+
+ if (!cn_already_initialized)
+ return 0;
+
+ return cn_hash_display_hlist(dev->hdev, pid, max_len,
+ hkey, key_display);
+}
+EXPORT_SYMBOL_GPL(cn_display_hlist);
+
bool cn_table_empty(void)
{
struct cn_dev *dev = &cdev;
diff --git a/include/linux/connector.h b/include/linux/connector.h
index 3f0648c886bc..393e1a391b70 100644
--- a/include/linux/connector.h
+++ b/include/linux/connector.h
@@ -173,4 +173,8 @@ int cn_get_exval(pid_t pid);
bool cn_table_empty(void);
bool cn_hash_table_empty(struct cn_hash_dev *hdev);
+int cn_display_hlist(pid_t pid, int max_len, int *hkey, int *key_display);
+int cn_hash_display_hlist(struct cn_hash_dev *hdev, pid_t pid, int max_len,
+ int *hkey, int *key_display);
+
#endif /* __CONNECTOR_H */
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 7315f643817a..784bd66221ab 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -2705,6 +2705,25 @@ config HASHTABLE_KUNIT_TEST
If unsure, say N.
+config CN_HASH_KUNIT_TEST
+ tristate "KUnit Test for connector hashtable code" if !KUNIT_ALL_TESTS
+ depends on KUNIT
+ depends on CONNECTOR && PROC_EVENTS
+ depends on NET
+ default KUNIT_ALL_TESTS
+ help
+ This builds the hashtable KUnit test suite.
+ It tests the basic functionality of the API defined in
+ drivers/connector/cn_hash.c.
+ CONFIG_CONNECTOR=y, CONFIG_PROC_EVENTS=y and CONFIG_NET=y needs
+ to be enabled along with CONFIG_CN_HASH_KUNIT_TEST=m and
+ CONFIG_KUNIT=m in .config file to compile and then test as a
+ kernel module with "modprobe cn_hash_test".
+ For more information on KUnit and unit tests in general please
+ refer to the KUnit documentation in Documentation/dev-tools/kunit/.
+
+ If unsure, say N.
+
config LINEAR_RANGES_TEST
tristate "KUnit test for linear_ranges"
depends on KUNIT
diff --git a/lib/Makefile b/lib/Makefile
index 811ba12c8cd0..2c59c82b0b18 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -379,6 +379,7 @@ obj-$(CONFIG_CMDLINE_KUNIT_TEST) += cmdline_kunit.o
obj-$(CONFIG_SLUB_KUNIT_TEST) += slub_kunit.o
obj-$(CONFIG_MEMCPY_KUNIT_TEST) += memcpy_kunit.o
obj-$(CONFIG_IS_SIGNED_TYPE_KUNIT_TEST) += is_signed_type_kunit.o
+obj-$(CONFIG_CN_HASH_KUNIT_TEST) += cn_hash_test.o
CFLAGS_overflow_kunit.o = $(call cc-disable-warning, tautological-constant-out-of-range-compare)
obj-$(CONFIG_OVERFLOW_KUNIT_TEST) += overflow_kunit.o
CFLAGS_stackinit_kunit.o += $(call cc-disable-warning, switch-unreachable)
diff --git a/lib/cn_hash_test.c b/lib/cn_hash_test.c
new file mode 100644
index 000000000000..efaf727d9b2a
--- /dev/null
+++ b/lib/cn_hash_test.c
@@ -0,0 +1,169 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * KUnit test for the connector threads hashtable code.
+ *
+ * Copyright (c) 2024 Oracle and/or its affiliates.
+ * Author: Anjali Kulkarni <anjali.k.kulkarni@oracle.com>
+ */
+#include <kunit/test.h>
+
+#include "cn_hash_test.h"
+
+#define ARR_SIZE 4
+#define HASH_TABLE_LEN 1024
+
+struct add_data {
+ pid_t pid;
+ int exit_val;
+ int key;
+};
+
+static struct add_data adata[ARR_SIZE];
+static int key_display[HASH_TABLE_LEN];
+
+static int cn_hash_init(struct kunit *test)
+{
+ for (int i = 0; i < HASH_TABLE_LEN; i++)
+ key_display[i] = 0;
+
+ return 0;
+}
+
+static void cn_display_htable(struct kunit *test, int len)
+{
+ int i, err;
+
+ cn_hash_init(test);
+
+ pr_debug("\n");
+ pr_debug("Displaying hash table:\n");
+
+ for (i = 0; i < len; i++) {
+ err = cn_display_hlist(adata[i].pid, len, &adata[i].key,
+ key_display);
+ key_display[adata[i].key] = 1;
+ KUNIT_EXPECT_EQ(test, err, 0);
+ }
+}
+
+static void cn_hash_test_add(struct kunit *test)
+{
+ int err, i;
+ int exit_val;
+
+ adata[0].pid = 1;
+ adata[0].exit_val = 45;
+
+ adata[1].pid = 2;
+ adata[1].exit_val = 13;
+
+ adata[2].pid = 1024;
+ adata[2].exit_val = 16;
+
+ adata[3].pid = 1023;
+ adata[3].exit_val = 71;
+
+ for (i = 0; i < ARRAY_SIZE(adata); i++) {
+ err = cn_add_elem(adata[i].exit_val, adata[i].pid);
+ KUNIT_EXPECT_EQ_MSG(test, 0, err,
+ "Adding pid %d returned err %d",
+ adata[i].pid, err);
+
+ exit_val = cn_get_exval(adata[i].pid);
+ KUNIT_EXPECT_EQ(test, adata[i].exit_val, exit_val);
+ }
+
+ cn_display_htable(test, ARRAY_SIZE(adata));
+}
+
+static void cn_hash_test_del(struct kunit *test)
+{
+ int i, err;
+ int exit_val;
+
+ for (i = 0; i < ARRAY_SIZE(adata); i++) {
+ err = cn_del_get_exval(adata[i].pid);
+ KUNIT_EXPECT_GT_MSG(test, err, 0,
+ "Deleting pid %d returned err %d",
+ adata[i].pid, err);
+
+ exit_val = cn_get_exval(adata[i].pid);
+ KUNIT_EXPECT_EQ(test, -EINVAL, exit_val);
+ }
+
+ cn_display_htable(test, ARRAY_SIZE(adata));
+ KUNIT_EXPECT_TRUE(test, cn_table_empty());
+}
+
+static void cn_hash_test_del_get_exval(struct kunit *test)
+{
+ int i, exval;
+
+ for (i = 0; i < ARRAY_SIZE(adata); i++) {
+ exval = cn_del_get_exval(adata[i].pid);
+ KUNIT_EXPECT_EQ(test, adata[i].exit_val, exval);
+
+ cn_display_htable(test, ARRAY_SIZE(adata));
+ }
+
+ KUNIT_EXPECT_TRUE(test, cn_table_empty());
+}
+
+static void cn_hash_test_dup_add(struct kunit *test)
+{
+ int err, exit_val;
+
+ adata[0].pid = 10;
+ adata[0].exit_val = 21;
+
+ err = cn_add_elem(adata[0].exit_val, adata[0].pid);
+ KUNIT_EXPECT_EQ(test, 0, err);
+
+ exit_val = cn_get_exval(adata[0].pid);
+ KUNIT_EXPECT_EQ(test, 21, exit_val);
+
+ adata[1].pid = 10;
+ adata[1].exit_val = 12;
+
+ err = cn_add_elem(adata[1].exit_val, adata[1].pid);
+ KUNIT_EXPECT_EQ(test, -EEXIST, err);
+
+ exit_val = cn_get_exval(adata[1].pid);
+ KUNIT_EXPECT_EQ(test, 21, exit_val);
+
+ cn_display_htable(test, 1);
+}
+
+static void cn_hash_test_dup_del(struct kunit *test)
+{
+ int err;
+
+ err = cn_del_get_exval(adata[0].pid);
+ KUNIT_EXPECT_EQ(test, adata[0].exit_val, err);
+
+ err = cn_del_get_exval(adata[0].pid);
+ KUNIT_EXPECT_EQ(test, -EINVAL, err);
+
+ KUNIT_EXPECT_TRUE(test, cn_table_empty());
+}
+
+static struct kunit_case cn_hashtable_test_cases[] = {
+ KUNIT_CASE(cn_hash_test_add),
+ KUNIT_CASE(cn_hash_test_del),
+ KUNIT_CASE(cn_hash_test_dup_add),
+ KUNIT_CASE(cn_hash_test_dup_del),
+ KUNIT_CASE(cn_hash_test_add),
+ KUNIT_CASE(cn_hash_test_del_get_exval),
+ {},
+};
+
+static struct kunit_suite cn_hashtable_test_module = {
+ .name = "cn_hashtable",
+ .init = cn_hash_init,
+ .test_cases = cn_hashtable_test_cases,
+};
+
+kunit_test_suite(cn_hashtable_test_module);
+
+MODULE_DESCRIPTION("KUnit test for the connector threads hashtable code");
+MODULE_LICENSE("GPL");
diff --git a/lib/cn_hash_test.h b/lib/cn_hash_test.h
new file mode 100644
index 000000000000..b25033feab09
--- /dev/null
+++ b/lib/cn_hash_test.h
@@ -0,0 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+/*
+ * Copyright (c) 2024 Oracle and/or its affiliates.
+ * Author: Anjali Kulkarni <anjali.k.kulkarni@oracle.com>
+ */
+int cn_display_hlist(pid_t pid, int max_len, int *hkey, int *key_display);
+int cn_add_elem(__u32 uexit_code, pid_t pid);
+int cn_del_get_exval(pid_t pid);
+int cn_get_exval(pid_t pid);
+bool cn_table_empty(void);
diff --git a/tools/testing/kunit/configs/all_tests.config b/tools/testing/kunit/configs/all_tests.config
index b3b00269a52a..a663280b0f3a 100644
--- a/tools/testing/kunit/configs/all_tests.config
+++ b/tools/testing/kunit/configs/all_tests.config
@@ -52,3 +52,8 @@ CONFIG_SOUND=y
CONFIG_SND=y
CONFIG_SND_SOC=y
CONFIG_SND_SOC_TOPOLOGY_BUILD=y
+
+CONFIG_CONNECTOR=y
+CONFIG_PROC_EVENTS=y
+CONFIG_NET=y
+CONFIG_CN_HASH_KUNIT_TEST=y
--
2.46.0
^ permalink raw reply related [flat|nested] 5+ messages in thread* [PATCH net-next v6 3/3] connector/cn_proc: Selftest for threads
2024-10-23 16:20 [PATCH net-next v6 0/3] Threads support in proc connector Anjali Kulkarni
2024-10-23 16:20 ` [PATCH net-next v6 1/3] connector/cn_proc: Add hash table for threads Anjali Kulkarni
2024-10-23 16:20 ` [PATCH net-next v6 2/3] connector/cn_proc: Kunit tests for threads hash table Anjali Kulkarni
@ 2024-10-23 16:20 ` Anjali Kulkarni
2 siblings, 0 replies; 5+ messages in thread
From: Anjali Kulkarni @ 2024-10-23 16:20 UTC (permalink / raw)
To: davem, Liam.Howlett
Cc: edumazet, kuba, pabeni, mingo, peterz, juri.lelli,
vincent.guittot, dietmar.eggemann, rostedt, bsegall, mgorman,
vschneid, jiri, linux-kernel, netdev, akpm, brendan.higgins,
davidgow, rmoar, johannes.berg, mic, gnoack, jk, kunit-dev, shuah,
linux-kselftest, anjali.k.kulkarni, peili.io
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
Run:
./threads
Signed-off-by: Anjali Kulkarni <anjali.k.kulkarni@oracle.com>
---
tools/testing/selftests/connector/Makefile | 25 ++
.../testing/selftests/connector/proc_filter.c | 63 +++--
tools/testing/selftests/connector/thread.c | 238 ++++++++++++++++++
.../selftests/connector/thread_filter.c | 96 +++++++
4 files changed, 403 insertions(+), 19 deletions(-)
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..675015bdf8ee 100644
--- a/tools/testing/selftests/connector/Makefile
+++ b/tools/testing/selftests/connector/Makefile
@@ -1,6 +1,31 @@
# SPDX-License-Identifier: GPL-2.0
+
+# Enable if you want to use build kernel header files instead of installed
+# kernel files
+# KERNEL="../../../.."
+# CFLAGS += -Wall $(KHDR_INCLUDES) -I $(KERNEL)/include/uapi -I $(KERNEL)/include
+
CFLAGS += -Wall $(KHDR_INCLUDES)
+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
include ../lib.mk
diff --git a/tools/testing/selftests/connector/proc_filter.c b/tools/testing/selftests/connector/proc_filter.c
index 4a825b997666..32a655f95c7f 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>
@@ -28,6 +33,7 @@
volatile static int interrupted;
static int nl_sock, ret_errno, tcount;
static struct epoll_event evn;
+FILE *file;
static int filter;
@@ -37,6 +43,8 @@ static int filter;
#define Printf ksft_print_msg
#endif
+#define EXIT_LOG
+
int send_message(void *pinp)
{
char buff[NL_MESSAGE_SIZE];
@@ -146,58 +154,65 @@ int handle_packet(char *buff, int fd, struct proc_event *event)
tcount++;
switch (event->what) {
case PROC_EVENT_EXIT:
- Printf("Exit process %d (tgid %d) with code %d, signal %d\n",
+#ifdef EXIT_LOG
+ fprintf(file, "pid %d tgid %d code %d\n",
+ event->event_data.exit.process_pid,
+ event->event_data.exit.process_tgid,
+ event->event_data.exit.exit_code);
+#else
+ Printf("Exit pid %d (tgid %d) exitcode %d, signal %d\n",
event->event_data.exit.process_pid,
event->event_data.exit.process_tgid,
event->event_data.exit.exit_code,
event->event_data.exit.exit_signal);
+#endif
break;
case PROC_EVENT_FORK:
- Printf("Fork process %d (tgid %d), parent %d (tgid %d)\n",
+ Printf("Fork pid %d (tgid %d), parent %d (tgid %d)\n",
event->event_data.fork.child_pid,
event->event_data.fork.child_tgid,
event->event_data.fork.parent_pid,
event->event_data.fork.parent_tgid);
break;
case PROC_EVENT_EXEC:
- Printf("Exec process %d (tgid %d)\n",
+ Printf("Exec pid %d (tgid %d)\n",
event->event_data.exec.process_pid,
event->event_data.exec.process_tgid);
break;
case PROC_EVENT_UID:
- Printf("UID process %d (tgid %d) uid %d euid %d\n",
+ Printf("UID pid %d (tgid %d) uid %d euid %d\n",
event->event_data.id.process_pid,
event->event_data.id.process_tgid,
event->event_data.id.r.ruid,
event->event_data.id.e.euid);
break;
case PROC_EVENT_GID:
- Printf("GID process %d (tgid %d) gid %d egid %d\n",
+ Printf("GID pid %d (tgid %d) gid %d egid %d\n",
event->event_data.id.process_pid,
event->event_data.id.process_tgid,
event->event_data.id.r.rgid,
event->event_data.id.e.egid);
break;
case PROC_EVENT_SID:
- Printf("SID process %d (tgid %d)\n",
+ Printf("SID pid %d (tgid %d)\n",
event->event_data.sid.process_pid,
event->event_data.sid.process_tgid);
break;
case PROC_EVENT_PTRACE:
- Printf("Ptrace process %d (tgid %d), Tracer %d (tgid %d)\n",
+ Printf("Ptrace pid %d (tgid %d), Tracer %d (tgid %d)\n",
event->event_data.ptrace.process_pid,
event->event_data.ptrace.process_tgid,
event->event_data.ptrace.tracer_pid,
event->event_data.ptrace.tracer_tgid);
break;
case PROC_EVENT_COMM:
- Printf("Comm process %d (tgid %d) comm %s\n",
+ Printf("Comm pid %d (tgid %d) comm %s\n",
event->event_data.comm.process_pid,
event->event_data.comm.process_tgid,
event->event_data.comm.comm);
break;
case PROC_EVENT_COREDUMP:
- Printf("Coredump process %d (tgid %d) parent %d, (tgid %d)\n",
+ Printf("Coredump pid %d (tgid %d) parent %d, (tgid %d)\n",
event->event_data.coredump.process_pid,
event->event_data.coredump.process_tgid,
event->event_data.coredump.parent_pid,
@@ -263,10 +278,11 @@ int main(int argc, char *argv[])
if (filter) {
input.event_type = PROC_EVENT_NONZERO_EXIT;
input.mcast_op = PROC_CN_MCAST_LISTEN;
- err = register_proc_netlink(&epoll_fd, (void*)&input);
+ err = register_proc_netlink(&epoll_fd, (void *)&input);
} else {
enum proc_cn_mcast_op op = PROC_CN_MCAST_LISTEN;
- err = register_proc_netlink(&epoll_fd, (void*)&op);
+
+ err = register_proc_netlink(&epoll_fd, (void *)&op);
}
if (err < 0) {
@@ -279,31 +295,40 @@ int main(int argc, char *argv[])
exit(1);
}
+#ifdef EXIT_LOG
+ file = fopen("exit.log", "w");
+ if (!file) {
+ perror("Error opening file exit.log");
+ close(nl_sock);
+ close(epoll_fd);
+ exit(1);
+ }
+#endif
+
while (!interrupted) {
err = handle_events(epoll_fd, &proc_ev);
if (err < 0) {
if (ret_errno == EINTR)
continue;
- if (err == -2)
- close(nl_sock);
- if (err == -3) {
- close(nl_sock);
- close(epoll_fd);
- }
+ close(nl_sock);
+ close(epoll_fd);
+ fclose(file);
exit(1);
}
}
if (filter) {
input.mcast_op = PROC_CN_MCAST_IGNORE;
- send_message((void*)&input);
+ send_message((void *)&input);
} else {
enum proc_cn_mcast_op op = PROC_CN_MCAST_IGNORE;
- send_message((void*)&op);
+
+ send_message((void *)&op);
}
close(epoll_fd);
close(nl_sock);
+ fclose(file);
printf("Done total count: %d\n", tcount);
exit(0);
diff --git a/tools/testing/selftests/connector/thread.c b/tools/testing/selftests/connector/thread.c
new file mode 100644
index 000000000000..0c12f8e9f1e1
--- /dev/null
+++ b/tools/testing/selftests/connector/thread.c
@@ -0,0 +1,238 @@
+// 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.
+ * Compile:
+ * make thread
+ * make proc_filter
+ * Run:
+ * ./threads
+ */
+
+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);
+
+ *(int *)ptr = gettid();
+
+ printf("Child 1 thread id %d, handling SIGSEGV\n", gettid());
+ sleep(10);
+ pthread_exit(NULL);
+}
+
+void *threadc2(void *ptr)
+{
+ int exit_val = 1;
+
+ *(int *)ptr = gettid();
+
+ 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);
+}
+
+static void verify_exit_status(int tid1, int tid2)
+{
+ int found1 = 0, found2 = 0;
+ int pid, tgid, exit_code;
+ size_t size = 1024;
+ FILE *file;
+ char *data;
+ int ret;
+
+ data = malloc(size * sizeof(char));
+ if (!data) {
+ perror("malloc for data failed");
+ exit(1);
+ }
+
+ file = fopen("exit.log", "r");
+ if (!file) {
+ perror("fopen of exit.log failed");
+ free(data);
+ exit(1);
+ }
+
+ while (getline(&data, &size, file) != -1) {
+ ret = sscanf(data, "pid %d tgid %d code %d",
+ &pid, &tgid, &exit_code);
+ if (ret != 3) {
+ perror("sscanf error in exit.log");
+ free(data);
+ fclose(file);
+ exit(1);
+ }
+
+ if (tgid != getpid())
+ continue;
+
+ if (pid == tid1) {
+ if (exit_code == 11) {
+ printf("Success: notify of SIGSEGV, tid %d\n",
+ pid);
+ } else {
+ printf("Failure SIGSEGV tid %d, exit code %d\n",
+ pid, exit_code);
+ }
+ found1 = 1;
+ } else if (pid == tid2) {
+ if (exit_code == 1) {
+ printf("Success: notify thread exit tid %d\n",
+ pid);
+ } else {
+ printf("Failure thread exit tid %d, exit code %d\n",
+ pid, exit_code);
+ }
+ found2 = 1;
+ }
+ }
+
+ if (!found1)
+ printf("tid %d not present in exit.log file\n", tid1);
+
+ if (!found2)
+ printf("tid %d not present in exit.log file\n", tid2);
+
+ fclose(file);
+ free(data);
+}
+
+static void init_threads(pthread_attr_t *attr)
+{
+ int ret;
+
+ ret = pthread_attr_init(attr);
+ if (ret != 0) {
+ perror("pthread_attr_init failed");
+ exit(1);
+ }
+
+ ret = pthread_attr_setdetachstate(attr, PTHREAD_CREATE_DETACHED);
+ if (ret != 0) {
+ perror("pthread_attr_setdetachstate failed");
+ exit(1);
+ }
+}
+
+static void destroy_thread_attr(pthread_attr_t *attr)
+{
+ int ret;
+
+ ret = pthread_attr_destroy(attr);
+ if (ret != 0)
+ perror("pthread_attr_destroy failed");
+}
+
+static pid_t start_proc_filter(void)
+{
+ pid_t proc_filter = 0;
+
+ proc_filter = fork();
+ if (proc_filter == -1) {
+ perror("fork() failed");
+ exit(1);
+ }
+
+ if (proc_filter == 0) {
+ static char * const arr[] = {"proc_filter", "-f", NULL};
+ int ret = execv("./proc_filter", arr);
+
+ if (ret == -1) {
+ perror("execv() of proc_filter failed");
+ exit(1);
+ }
+ }
+ sleep(1);
+ return proc_filter;
+}
+
+int main(int argc, char **argv)
+{
+ pthread_t thread1, thread2;
+ pthread_attr_t attr1, attr2;
+ int tid1, tid2, ret;
+ pid_t proc_filter_pid;
+
+ proc_filter_pid = start_proc_filter();
+
+ init_threads(&attr1);
+ ret = pthread_create(&thread1, &attr1, *threadc1, &tid1);
+ if (ret != 0) {
+ perror("pthread_create failed");
+ exit(1);
+ }
+
+ init_threads(&attr2);
+ ret = pthread_create(&thread2, &attr2, *threadc2, &tid2);
+ if (ret != 0) {
+ perror("pthread_create failed");
+ exit(1);
+ }
+
+ sleep(1);
+
+ /* Send SIGSEGV to tid1 */
+ ret = kill(tid1, SIGSEGV);
+ if (ret == -1)
+ perror("kill SIGSEGV failed");
+
+ /*
+ * Wait for children to exit or be killed and for exit.log to
+ * be generated by ./proc_filter
+ */
+ sleep(2);
+
+ /*
+ * Kill proc_filter to get exit.log
+ */
+ ret = kill(proc_filter_pid, SIGINT);
+ if (ret == -1)
+ perror("kill to proc_filter failed");
+
+ /* Required to allow kill to be processed */
+ sleep(1);
+
+ verify_exit_status(tid1, tid2);
+
+ destroy_thread_attr(&attr1);
+ destroy_thread_attr(&attr2);
+
+ 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
^ permalink raw reply related [flat|nested] 5+ messages in thread