linux/drivers/connector/cn_proc.c

357 lines
10 KiB
C
Raw Normal View History

/*
* cn_proc.c - process events connector
*
* Copyright (C) Matt Helsley, IBM Corp. 2005
* Based on cn_fork.c by Guillaume Thouvenin <guillaume.thouvenin@bull.net>
* Original copyright notice follows:
* Copyright (C) 2005 BULL SA.
*
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*/
#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/ktime.h>
#include <linux/init.h>
#include <linux/connector.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 16:04:11 +08:00
#include <linux/gfp.h>
#include <linux/ptrace.h>
#include <linux/atomic.h>
#include <linux/pid_namespace.h>
#include <asm/unaligned.h>
#include <linux/cn_proc.h>
#define CN_PROC_MSG_SIZE (sizeof(struct cn_msg) + sizeof(struct proc_event))
static atomic_t proc_event_num_listeners = ATOMIC_INIT(0);
static struct cb_id cn_proc_event_id = { CN_IDX_PROC, CN_VAL_PROC };
/* proc_event_counts is used as the sequence number of the netlink message */
static DEFINE_PER_CPU(__u32, proc_event_counts) = { 0 };
static inline void get_seq(__u32 *ts, int *cpu)
{
preempt_disable();
*ts = __this_cpu_inc_return(proc_event_counts) - 1;
*cpu = smp_processor_id();
preempt_enable();
}
void proc_fork_connector(struct task_struct *task)
{
struct cn_msg *msg;
struct proc_event *ev;
__u8 buffer[CN_PROC_MSG_SIZE];
struct timespec ts;
struct task_struct *parent;
if (atomic_read(&proc_event_num_listeners) < 1)
return;
msg = (struct cn_msg *)buffer;
ev = (struct proc_event *)msg->data;
get_seq(&msg->seq, &ev->cpu);
ktime_get_ts(&ts); /* get high res monotonic timestamp */
put_unaligned(timespec_to_ns(&ts), (__u64 *)&ev->timestamp_ns);
ev->what = PROC_EVENT_FORK;
rcu_read_lock();
parent = rcu_dereference(task->real_parent);
ev->event_data.fork.parent_pid = parent->pid;
ev->event_data.fork.parent_tgid = parent->tgid;
rcu_read_unlock();
ev->event_data.fork.child_pid = task->pid;
ev->event_data.fork.child_tgid = task->tgid;
memcpy(&msg->id, &cn_proc_event_id, sizeof(msg->id));
msg->ack = 0; /* not used */
msg->len = sizeof(*ev);
/* If cn_netlink_send() failed, the data is not sent */
cn_netlink_send(msg, CN_IDX_PROC, GFP_KERNEL);
}
void proc_exec_connector(struct task_struct *task)
{
struct cn_msg *msg;
struct proc_event *ev;
struct timespec ts;
__u8 buffer[CN_PROC_MSG_SIZE];
if (atomic_read(&proc_event_num_listeners) < 1)
return;
msg = (struct cn_msg *)buffer;
ev = (struct proc_event *)msg->data;
get_seq(&msg->seq, &ev->cpu);
ktime_get_ts(&ts); /* get high res monotonic timestamp */
put_unaligned(timespec_to_ns(&ts), (__u64 *)&ev->timestamp_ns);
ev->what = PROC_EVENT_EXEC;
ev->event_data.exec.process_pid = task->pid;
ev->event_data.exec.process_tgid = task->tgid;
memcpy(&msg->id, &cn_proc_event_id, sizeof(msg->id));
msg->ack = 0; /* not used */
msg->len = sizeof(*ev);
cn_netlink_send(msg, CN_IDX_PROC, GFP_KERNEL);
}
void proc_id_connector(struct task_struct *task, int which_id)
{
struct cn_msg *msg;
struct proc_event *ev;
__u8 buffer[CN_PROC_MSG_SIZE];
struct timespec ts;
const struct cred *cred;
if (atomic_read(&proc_event_num_listeners) < 1)
return;
msg = (struct cn_msg *)buffer;
ev = (struct proc_event *)msg->data;
ev->what = which_id;
ev->event_data.id.process_pid = task->pid;
ev->event_data.id.process_tgid = task->tgid;
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);
} 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);
} else {
rcu_read_unlock();
return;
}
rcu_read_unlock();
get_seq(&msg->seq, &ev->cpu);
ktime_get_ts(&ts); /* get high res monotonic timestamp */
put_unaligned(timespec_to_ns(&ts), (__u64 *)&ev->timestamp_ns);
memcpy(&msg->id, &cn_proc_event_id, sizeof(msg->id));
msg->ack = 0; /* not used */
msg->len = sizeof(*ev);
cn_netlink_send(msg, CN_IDX_PROC, GFP_KERNEL);
}
void proc_sid_connector(struct task_struct *task)
{
struct cn_msg *msg;
struct proc_event *ev;
struct timespec ts;
__u8 buffer[CN_PROC_MSG_SIZE];
if (atomic_read(&proc_event_num_listeners) < 1)
return;
msg = (struct cn_msg *)buffer;
ev = (struct proc_event *)msg->data;
get_seq(&msg->seq, &ev->cpu);
ktime_get_ts(&ts); /* get high res monotonic timestamp */
put_unaligned(timespec_to_ns(&ts), (__u64 *)&ev->timestamp_ns);
ev->what = PROC_EVENT_SID;
ev->event_data.sid.process_pid = task->pid;
ev->event_data.sid.process_tgid = task->tgid;
memcpy(&msg->id, &cn_proc_event_id, sizeof(msg->id));
msg->ack = 0; /* not used */
msg->len = sizeof(*ev);
cn_netlink_send(msg, CN_IDX_PROC, GFP_KERNEL);
}
void proc_ptrace_connector(struct task_struct *task, int ptrace_id)
{
struct cn_msg *msg;
struct proc_event *ev;
struct timespec ts;
__u8 buffer[CN_PROC_MSG_SIZE];
if (atomic_read(&proc_event_num_listeners) < 1)
return;
msg = (struct cn_msg *)buffer;
ev = (struct proc_event *)msg->data;
get_seq(&msg->seq, &ev->cpu);
ktime_get_ts(&ts); /* get high res monotonic timestamp */
put_unaligned(timespec_to_ns(&ts), (__u64 *)&ev->timestamp_ns);
ev->what = PROC_EVENT_PTRACE;
ev->event_data.ptrace.process_pid = task->pid;
ev->event_data.ptrace.process_tgid = task->tgid;
if (ptrace_id == PTRACE_ATTACH) {
ev->event_data.ptrace.tracer_pid = current->pid;
ev->event_data.ptrace.tracer_tgid = current->tgid;
} else if (ptrace_id == PTRACE_DETACH) {
ev->event_data.ptrace.tracer_pid = 0;
ev->event_data.ptrace.tracer_tgid = 0;
} else
return;
memcpy(&msg->id, &cn_proc_event_id, sizeof(msg->id));
msg->ack = 0; /* not used */
msg->len = sizeof(*ev);
cn_netlink_send(msg, CN_IDX_PROC, GFP_KERNEL);
}
void proc_comm_connector(struct task_struct *task)
{
struct cn_msg *msg;
struct proc_event *ev;
struct timespec ts;
__u8 buffer[CN_PROC_MSG_SIZE];
if (atomic_read(&proc_event_num_listeners) < 1)
return;
msg = (struct cn_msg *)buffer;
ev = (struct proc_event *)msg->data;
get_seq(&msg->seq, &ev->cpu);
ktime_get_ts(&ts); /* get high res monotonic timestamp */
put_unaligned(timespec_to_ns(&ts), (__u64 *)&ev->timestamp_ns);
ev->what = PROC_EVENT_COMM;
ev->event_data.comm.process_pid = task->pid;
ev->event_data.comm.process_tgid = task->tgid;
get_task_comm(ev->event_data.comm.comm, task);
memcpy(&msg->id, &cn_proc_event_id, sizeof(msg->id));
msg->ack = 0; /* not used */
msg->len = sizeof(*ev);
cn_netlink_send(msg, CN_IDX_PROC, GFP_KERNEL);
}
void proc_exit_connector(struct task_struct *task)
{
struct cn_msg *msg;
struct proc_event *ev;
__u8 buffer[CN_PROC_MSG_SIZE];
struct timespec ts;
if (atomic_read(&proc_event_num_listeners) < 1)
return;
msg = (struct cn_msg *)buffer;
ev = (struct proc_event *)msg->data;
get_seq(&msg->seq, &ev->cpu);
ktime_get_ts(&ts); /* get high res monotonic timestamp */
put_unaligned(timespec_to_ns(&ts), (__u64 *)&ev->timestamp_ns);
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;
ev->event_data.exit.exit_signal = task->exit_signal;
memcpy(&msg->id, &cn_proc_event_id, sizeof(msg->id));
msg->ack = 0; /* not used */
msg->len = sizeof(*ev);
cn_netlink_send(msg, CN_IDX_PROC, GFP_KERNEL);
}
/*
* Send an acknowledgement message to userspace
*
* Use 0 for success, EFOO otherwise.
* Note: this is the negative of conventional kernel error
* values because it's not being returned via syscall return
* mechanisms.
*/
static void cn_proc_ack(int err, int rcvd_seq, int rcvd_ack)
{
struct cn_msg *msg;
struct proc_event *ev;
__u8 buffer[CN_PROC_MSG_SIZE];
struct timespec ts;
if (atomic_read(&proc_event_num_listeners) < 1)
return;
msg = (struct cn_msg *)buffer;
ev = (struct proc_event *)msg->data;
msg->seq = rcvd_seq;
ktime_get_ts(&ts); /* get high res monotonic timestamp */
put_unaligned(timespec_to_ns(&ts), (__u64 *)&ev->timestamp_ns);
ev->cpu = -1;
ev->what = PROC_EVENT_NONE;
ev->event_data.ack.err = err;
memcpy(&msg->id, &cn_proc_event_id, sizeof(msg->id));
msg->ack = rcvd_ack + 1;
msg->len = sizeof(*ev);
cn_netlink_send(msg, CN_IDX_PROC, GFP_KERNEL);
}
/**
* cn_proc_mcast_ctl
* @data: message sent from userspace via the connector
*/
static void cn_proc_mcast_ctl(struct cn_msg *msg,
struct netlink_skb_parms *nsp)
{
enum proc_cn_mcast_op *mc_op = NULL;
int err = 0;
if (msg->len != sizeof(*mc_op))
return;
/*
* Events are reported with respect to the initial pid
* and user namespaces so ignore requestors from
* other namespaces.
*/
if ((current_user_ns() != &init_user_ns) ||
(task_active_pid_ns(current) != &init_pid_ns))
return;
/* Can only change if privileged. */
if (!capable(CAP_NET_ADMIN)) {
err = EPERM;
goto out;
}
mc_op = (enum proc_cn_mcast_op *)msg->data;
switch (*mc_op) {
case PROC_CN_MCAST_LISTEN:
atomic_inc(&proc_event_num_listeners);
break;
case PROC_CN_MCAST_IGNORE:
atomic_dec(&proc_event_num_listeners);
break;
default:
err = EINVAL;
break;
}
out:
cn_proc_ack(err, msg->seq, msg->ack);
}
/*
* cn_proc_init - initialization entry point
*
* Adds the connector callback to the connector driver.
*/
static int __init cn_proc_init(void)
{
int err = cn_add_callback(&cn_proc_event_id,
"cn_proc",
&cn_proc_mcast_ctl);
if (err) {
pr_warn("cn_proc failed to register\n");
return err;
}
return 0;
}
module_init(cn_proc_init);