linux/net/core/drop_monitor.c

397 lines
8.7 KiB
C
Raw Normal View History

/*
* Monitoring code for network dropped packet alerts
*
* Copyright (C) 2009 Neil Horman <nhorman@tuxdriver.com>
*/
#include <linux/netdevice.h>
#include <linux/etherdevice.h>
#include <linux/string.h>
#include <linux/if_arp.h>
#include <linux/inetdevice.h>
#include <linux/inet.h>
#include <linux/interrupt.h>
#include <linux/netpoll.h>
#include <linux/sched.h>
#include <linux/delay.h>
#include <linux/types.h>
#include <linux/workqueue.h>
#include <linux/netlink.h>
#include <linux/net_dropmon.h>
#include <linux/percpu.h>
#include <linux/timer.h>
#include <linux/bitops.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 08:04:11 +00:00
#include <linux/slab.h>
#include <net/genetlink.h>
#include <net/netevent.h>
#include <trace/events/skb.h>
#include <trace/events/napi.h>
#include <asm/unaligned.h>
#define TRACE_ON 1
#define TRACE_OFF 0
static void send_dm_alert(struct work_struct *unused);
/*
* Globals, our netlink socket pointer
* and the work handle that will send up
* netlink alerts
*/
static int trace_state = TRACE_OFF;
static DEFINE_SPINLOCK(trace_state_lock);
struct per_cpu_dm_data {
struct work_struct dm_alert_work;
struct sk_buff *skb;
atomic_t dm_hit_count;
struct timer_list send_timer;
};
struct dm_hw_stat_delta {
struct net_device *dev;
unsigned long last_rx;
struct list_head list;
struct rcu_head rcu;
unsigned long last_drop_val;
};
static struct genl_family net_drop_monitor_family = {
.id = GENL_ID_GENERATE,
.hdrsize = 0,
.name = "NET_DM",
.version = 2,
.maxattr = NET_DM_CMD_MAX,
};
static DEFINE_PER_CPU(struct per_cpu_dm_data, dm_cpu_data);
static int dm_hit_limit = 64;
static int dm_delay = 1;
static unsigned long dm_hw_check_delta = 2*HZ;
static LIST_HEAD(hw_stats_list);
static void reset_per_cpu_data(struct per_cpu_dm_data *data)
{
size_t al;
struct net_dm_alert_msg *msg;
struct nlattr *nla;
al = sizeof(struct net_dm_alert_msg);
al += dm_hit_limit * sizeof(struct net_dm_drop_point);
al += sizeof(struct nlattr);
data->skb = genlmsg_new(al, GFP_KERNEL);
genlmsg_put(data->skb, 0, 0, &net_drop_monitor_family,
0, NET_DM_CMD_ALERT);
nla = nla_reserve(data->skb, NLA_UNSPEC, sizeof(struct net_dm_alert_msg));
msg = nla_data(nla);
memset(msg, 0, al);
atomic_set(&data->dm_hit_count, dm_hit_limit);
}
static void send_dm_alert(struct work_struct *unused)
{
struct sk_buff *skb;
struct per_cpu_dm_data *data = &__get_cpu_var(dm_cpu_data);
/*
* Grab the skb we're about to send
*/
skb = data->skb;
/*
* Replace it with a new one
*/
reset_per_cpu_data(data);
/*
* Ship it!
*/
genlmsg_multicast(skb, 0, NET_DM_GRP_ALERT, GFP_KERNEL);
}
/*
* This is the timer function to delay the sending of an alert
* in the event that more drops will arrive during the
* hysteresis period. Note that it operates under the timer interrupt
* so we don't need to disable preemption here
*/
static void sched_send_work(unsigned long unused)
{
struct per_cpu_dm_data *data = &__get_cpu_var(dm_cpu_data);
schedule_work(&data->dm_alert_work);
}
static void trace_drop_common(struct sk_buff *skb, void *location)
{
struct net_dm_alert_msg *msg;
struct nlmsghdr *nlh;
struct nlattr *nla;
int i;
struct per_cpu_dm_data *data = &__get_cpu_var(dm_cpu_data);
if (!atomic_add_unless(&data->dm_hit_count, -1, 0)) {
/*
* we're already at zero, discard this hit
*/
goto out;
}
nlh = (struct nlmsghdr *)data->skb->data;
nla = genlmsg_data(nlmsg_data(nlh));
msg = nla_data(nla);
for (i = 0; i < msg->entries; i++) {
if (!memcmp(&location, msg->points[i].pc, sizeof(void *))) {
msg->points[i].count++;
goto out;
}
}
/*
* We need to create a new entry
*/
__nla_reserve_nohdr(data->skb, sizeof(struct net_dm_drop_point));
nla->nla_len += NLA_ALIGN(sizeof(struct net_dm_drop_point));
memcpy(msg->points[msg->entries].pc, &location, sizeof(void *));
msg->points[msg->entries].count = 1;
msg->entries++;
if (!timer_pending(&data->send_timer)) {
data->send_timer.expires = jiffies + dm_delay * HZ;
add_timer_on(&data->send_timer, smp_processor_id());
}
out:
return;
}
static void trace_kfree_skb_hit(struct sk_buff *skb, void *location)
{
trace_drop_common(skb, location);
}
static void trace_napi_poll_hit(struct napi_struct *napi)
{
struct dm_hw_stat_delta *new_stat;
/*
* Don't check napi structures with no associated device
*/
if (!napi->dev)
return;
rcu_read_lock();
list_for_each_entry_rcu(new_stat, &hw_stats_list, list) {
/*
* only add a note to our monitor buffer if:
* 1) this is the dev we received on
* 2) its after the last_rx delta
* 3) our rx_dropped count has gone up
*/
if ((new_stat->dev == napi->dev) &&
(time_after(jiffies, new_stat->last_rx + dm_hw_check_delta)) &&
(napi->dev->stats.rx_dropped != new_stat->last_drop_val)) {
trace_drop_common(NULL, NULL);
new_stat->last_drop_val = napi->dev->stats.rx_dropped;
new_stat->last_rx = jiffies;
break;
}
}
rcu_read_unlock();
}
static void free_dm_hw_stat(struct rcu_head *head)
{
struct dm_hw_stat_delta *n;
n = container_of(head, struct dm_hw_stat_delta, rcu);
kfree(n);
}
static int set_all_monitor_traces(int state)
{
int rc = 0;
struct dm_hw_stat_delta *new_stat = NULL;
struct dm_hw_stat_delta *temp;
spin_lock(&trace_state_lock);
switch (state) {
case TRACE_ON:
rc |= register_trace_kfree_skb(trace_kfree_skb_hit);
rc |= register_trace_napi_poll(trace_napi_poll_hit);
break;
case TRACE_OFF:
rc |= unregister_trace_kfree_skb(trace_kfree_skb_hit);
rc |= unregister_trace_napi_poll(trace_napi_poll_hit);
tracepoint_synchronize_unregister();
/*
* Clean the device list
*/
list_for_each_entry_safe(new_stat, temp, &hw_stats_list, list) {
if (new_stat->dev == NULL) {
list_del_rcu(&new_stat->list);
call_rcu(&new_stat->rcu, free_dm_hw_stat);
}
}
break;
default:
rc = 1;
break;
}
if (!rc)
trace_state = state;
spin_unlock(&trace_state_lock);
if (rc)
return -EINPROGRESS;
return rc;
}
static int net_dm_cmd_config(struct sk_buff *skb,
struct genl_info *info)
{
return -ENOTSUPP;
}
static int net_dm_cmd_trace(struct sk_buff *skb,
struct genl_info *info)
{
switch (info->genlhdr->cmd) {
case NET_DM_CMD_START:
return set_all_monitor_traces(TRACE_ON);
break;
case NET_DM_CMD_STOP:
return set_all_monitor_traces(TRACE_OFF);
break;
}
return -ENOTSUPP;
}
static int dropmon_net_event(struct notifier_block *ev_block,
unsigned long event, void *ptr)
{
struct net_device *dev = ptr;
struct dm_hw_stat_delta *new_stat = NULL;
struct dm_hw_stat_delta *tmp;
switch (event) {
case NETDEV_REGISTER:
new_stat = kzalloc(sizeof(struct dm_hw_stat_delta), GFP_KERNEL);
if (!new_stat)
goto out;
new_stat->dev = dev;
new_stat->last_rx = jiffies;
spin_lock(&trace_state_lock);
list_add_rcu(&new_stat->list, &hw_stats_list);
spin_unlock(&trace_state_lock);
break;
case NETDEV_UNREGISTER:
spin_lock(&trace_state_lock);
list_for_each_entry_safe(new_stat, tmp, &hw_stats_list, list) {
if (new_stat->dev == dev) {
new_stat->dev = NULL;
if (trace_state == TRACE_OFF) {
list_del_rcu(&new_stat->list);
call_rcu(&new_stat->rcu, free_dm_hw_stat);
break;
}
}
}
spin_unlock(&trace_state_lock);
break;
}
out:
return NOTIFY_DONE;
}
static struct genl_ops dropmon_ops[] = {
{
.cmd = NET_DM_CMD_CONFIG,
.doit = net_dm_cmd_config,
},
{
.cmd = NET_DM_CMD_START,
.doit = net_dm_cmd_trace,
},
{
.cmd = NET_DM_CMD_STOP,
.doit = net_dm_cmd_trace,
},
};
static struct notifier_block dropmon_net_notifier = {
.notifier_call = dropmon_net_event
};
static int __init init_net_drop_monitor(void)
{
int cpu;
int rc, i, ret;
struct per_cpu_dm_data *data;
printk(KERN_INFO "Initalizing network drop monitor service\n");
if (sizeof(void *) > 8) {
printk(KERN_ERR "Unable to store program counters on this arch, Drop monitor failed\n");
return -ENOSPC;
}
if (genl_register_family(&net_drop_monitor_family) < 0) {
printk(KERN_ERR "Could not create drop monitor netlink family\n");
return -EFAULT;
}
rc = -EFAULT;
for (i = 0; i < ARRAY_SIZE(dropmon_ops); i++) {
ret = genl_register_ops(&net_drop_monitor_family,
&dropmon_ops[i]);
if (ret) {
printk(KERN_CRIT "Failed to register operation %d\n",
dropmon_ops[i].cmd);
goto out_unreg;
}
}
rc = register_netdevice_notifier(&dropmon_net_notifier);
if (rc < 0) {
printk(KERN_CRIT "Failed to register netdevice notifier\n");
goto out_unreg;
}
rc = 0;
for_each_present_cpu(cpu) {
data = &per_cpu(dm_cpu_data, cpu);
reset_per_cpu_data(data);
INIT_WORK(&data->dm_alert_work, send_dm_alert);
init_timer(&data->send_timer);
data->send_timer.data = cpu;
data->send_timer.function = sched_send_work;
}
goto out;
out_unreg:
genl_unregister_family(&net_drop_monitor_family);
out:
return rc;
}
late_initcall(init_net_drop_monitor);