linux/net/core/drop_monitor.c

464 lines
10 KiB
C
Raw Normal View History

/*
* Monitoring code for network dropped packet alerts
*
* Copyright (C) 2009 Neil Horman <nhorman@tuxdriver.com>
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#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 <linux/module.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
/*
* Globals, our netlink socket pointer
* and the work handle that will send up
* netlink alerts
*/
static int trace_state = TRACE_OFF;
drop_monitor: fix sleeping in invalid context warning Eric Dumazet pointed out this warning in the drop_monitor protocol to me: [ 38.352571] BUG: sleeping function called from invalid context at kernel/mutex.c:85 [ 38.352576] in_atomic(): 1, irqs_disabled(): 0, pid: 4415, name: dropwatch [ 38.352580] Pid: 4415, comm: dropwatch Not tainted 3.4.0-rc2+ #71 [ 38.352582] Call Trace: [ 38.352592] [<ffffffff8153aaf0>] ? trace_napi_poll_hit+0xd0/0xd0 [ 38.352599] [<ffffffff81063f2a>] __might_sleep+0xca/0xf0 [ 38.352606] [<ffffffff81655b16>] mutex_lock+0x26/0x50 [ 38.352610] [<ffffffff8153aaf0>] ? trace_napi_poll_hit+0xd0/0xd0 [ 38.352616] [<ffffffff810b72d9>] tracepoint_probe_register+0x29/0x90 [ 38.352621] [<ffffffff8153a585>] set_all_monitor_traces+0x105/0x170 [ 38.352625] [<ffffffff8153a8ca>] net_dm_cmd_trace+0x2a/0x40 [ 38.352630] [<ffffffff8154a81a>] genl_rcv_msg+0x21a/0x2b0 [ 38.352636] [<ffffffff810f8029>] ? zone_statistics+0x99/0xc0 [ 38.352640] [<ffffffff8154a600>] ? genl_rcv+0x30/0x30 [ 38.352645] [<ffffffff8154a059>] netlink_rcv_skb+0xa9/0xd0 [ 38.352649] [<ffffffff8154a5f0>] genl_rcv+0x20/0x30 [ 38.352653] [<ffffffff81549a7e>] netlink_unicast+0x1ae/0x1f0 [ 38.352658] [<ffffffff81549d76>] netlink_sendmsg+0x2b6/0x310 [ 38.352663] [<ffffffff8150824f>] sock_sendmsg+0x10f/0x130 [ 38.352668] [<ffffffff8150abe0>] ? move_addr_to_kernel+0x60/0xb0 [ 38.352673] [<ffffffff81515f04>] ? verify_iovec+0x64/0xe0 [ 38.352677] [<ffffffff81509c46>] __sys_sendmsg+0x386/0x390 [ 38.352682] [<ffffffff810ffaf9>] ? handle_mm_fault+0x139/0x210 [ 38.352687] [<ffffffff8165b5bc>] ? do_page_fault+0x1ec/0x4f0 [ 38.352693] [<ffffffff8106ba4d>] ? set_next_entity+0x9d/0xb0 [ 38.352699] [<ffffffff81310b49>] ? tty_ldisc_deref+0x9/0x10 [ 38.352703] [<ffffffff8106d363>] ? pick_next_task_fair+0x63/0x140 [ 38.352708] [<ffffffff8150b8d4>] sys_sendmsg+0x44/0x80 [ 38.352713] [<ffffffff8165f8e2>] system_call_fastpath+0x16/0x1b It stems from holding a spinlock (trace_state_lock) while attempting to register or unregister tracepoint hooks, making in_atomic() true in this context, leading to the warning when the tracepoint calls might_sleep() while its taking a mutex. Since we only use the trace_state_lock to prevent trace protocol state races, as well as hardware stat list updates on an rcu write side, we can just convert the spinlock to a mutex to avoid this problem. Signed-off-by: Neil Horman <nhorman@tuxdriver.com> Reported-by: Eric Dumazet <eric.dumazet@gmail.com> CC: David Miller <davem@davemloft.net> Acked-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-04-27 10:11:48 +00:00
static DEFINE_MUTEX(trace_state_mutex);
struct per_cpu_dm_data {
drop_monitor: dont sleep in atomic context drop_monitor calls several sleeping functions while in atomic context. BUG: sleeping function called from invalid context at mm/slub.c:943 in_atomic(): 1, irqs_disabled(): 0, pid: 2103, name: kworker/0:2 Pid: 2103, comm: kworker/0:2 Not tainted 3.5.0-rc1+ #55 Call Trace: [<ffffffff810697ca>] __might_sleep+0xca/0xf0 [<ffffffff811345a3>] kmem_cache_alloc_node+0x1b3/0x1c0 [<ffffffff8105578c>] ? queue_delayed_work_on+0x11c/0x130 [<ffffffff815343fb>] __alloc_skb+0x4b/0x230 [<ffffffffa00b0360>] ? reset_per_cpu_data+0x160/0x160 [drop_monitor] [<ffffffffa00b022f>] reset_per_cpu_data+0x2f/0x160 [drop_monitor] [<ffffffffa00b03ab>] send_dm_alert+0x4b/0xb0 [drop_monitor] [<ffffffff810568e0>] process_one_work+0x130/0x4c0 [<ffffffff81058249>] worker_thread+0x159/0x360 [<ffffffff810580f0>] ? manage_workers.isra.27+0x240/0x240 [<ffffffff8105d403>] kthread+0x93/0xa0 [<ffffffff816be6d4>] kernel_thread_helper+0x4/0x10 [<ffffffff8105d370>] ? kthread_freezable_should_stop+0x80/0x80 [<ffffffff816be6d0>] ? gs_change+0xb/0xb Rework the logic to call the sleeping functions in right context. Use standard timer/workqueue api to let system chose any cpu to perform the allocation and netlink send. Also avoid a loop if reset_per_cpu_data() cannot allocate memory : use mod_timer() to wait 1/10 second before next try. Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Neil Horman <nhorman@tuxdriver.com> Reviewed-by: Neil Horman <nhorman@tuxdriver.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-06-04 00:18:19 +00:00
spinlock_t lock;
struct sk_buff *skb;
struct work_struct dm_alert_work;
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;
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);
drop_monitor: dont sleep in atomic context drop_monitor calls several sleeping functions while in atomic context. BUG: sleeping function called from invalid context at mm/slub.c:943 in_atomic(): 1, irqs_disabled(): 0, pid: 2103, name: kworker/0:2 Pid: 2103, comm: kworker/0:2 Not tainted 3.5.0-rc1+ #55 Call Trace: [<ffffffff810697ca>] __might_sleep+0xca/0xf0 [<ffffffff811345a3>] kmem_cache_alloc_node+0x1b3/0x1c0 [<ffffffff8105578c>] ? queue_delayed_work_on+0x11c/0x130 [<ffffffff815343fb>] __alloc_skb+0x4b/0x230 [<ffffffffa00b0360>] ? reset_per_cpu_data+0x160/0x160 [drop_monitor] [<ffffffffa00b022f>] reset_per_cpu_data+0x2f/0x160 [drop_monitor] [<ffffffffa00b03ab>] send_dm_alert+0x4b/0xb0 [drop_monitor] [<ffffffff810568e0>] process_one_work+0x130/0x4c0 [<ffffffff81058249>] worker_thread+0x159/0x360 [<ffffffff810580f0>] ? manage_workers.isra.27+0x240/0x240 [<ffffffff8105d403>] kthread+0x93/0xa0 [<ffffffff816be6d4>] kernel_thread_helper+0x4/0x10 [<ffffffff8105d370>] ? kthread_freezable_should_stop+0x80/0x80 [<ffffffff816be6d0>] ? gs_change+0xb/0xb Rework the logic to call the sleeping functions in right context. Use standard timer/workqueue api to let system chose any cpu to perform the allocation and netlink send. Also avoid a loop if reset_per_cpu_data() cannot allocate memory : use mod_timer() to wait 1/10 second before next try. Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Neil Horman <nhorman@tuxdriver.com> Reviewed-by: Neil Horman <nhorman@tuxdriver.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-06-04 00:18:19 +00:00
static struct sk_buff *reset_per_cpu_data(struct per_cpu_dm_data *data)
{
size_t al;
struct net_dm_alert_msg *msg;
struct nlattr *nla;
struct sk_buff *skb;
drop_monitor: dont sleep in atomic context drop_monitor calls several sleeping functions while in atomic context. BUG: sleeping function called from invalid context at mm/slub.c:943 in_atomic(): 1, irqs_disabled(): 0, pid: 2103, name: kworker/0:2 Pid: 2103, comm: kworker/0:2 Not tainted 3.5.0-rc1+ #55 Call Trace: [<ffffffff810697ca>] __might_sleep+0xca/0xf0 [<ffffffff811345a3>] kmem_cache_alloc_node+0x1b3/0x1c0 [<ffffffff8105578c>] ? queue_delayed_work_on+0x11c/0x130 [<ffffffff815343fb>] __alloc_skb+0x4b/0x230 [<ffffffffa00b0360>] ? reset_per_cpu_data+0x160/0x160 [drop_monitor] [<ffffffffa00b022f>] reset_per_cpu_data+0x2f/0x160 [drop_monitor] [<ffffffffa00b03ab>] send_dm_alert+0x4b/0xb0 [drop_monitor] [<ffffffff810568e0>] process_one_work+0x130/0x4c0 [<ffffffff81058249>] worker_thread+0x159/0x360 [<ffffffff810580f0>] ? manage_workers.isra.27+0x240/0x240 [<ffffffff8105d403>] kthread+0x93/0xa0 [<ffffffff816be6d4>] kernel_thread_helper+0x4/0x10 [<ffffffff8105d370>] ? kthread_freezable_should_stop+0x80/0x80 [<ffffffff816be6d0>] ? gs_change+0xb/0xb Rework the logic to call the sleeping functions in right context. Use standard timer/workqueue api to let system chose any cpu to perform the allocation and netlink send. Also avoid a loop if reset_per_cpu_data() cannot allocate memory : use mod_timer() to wait 1/10 second before next try. Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Neil Horman <nhorman@tuxdriver.com> Reviewed-by: Neil Horman <nhorman@tuxdriver.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-06-04 00:18:19 +00:00
unsigned long flags;
void *msg_header;
al = sizeof(struct net_dm_alert_msg);
al += dm_hit_limit * sizeof(struct net_dm_drop_point);
al += sizeof(struct nlattr);
skb = genlmsg_new(al, GFP_KERNEL);
if (!skb)
goto err;
msg_header = genlmsg_put(skb, 0, 0, &net_drop_monitor_family,
0, NET_DM_CMD_ALERT);
if (!msg_header) {
nlmsg_free(skb);
skb = NULL;
goto err;
}
nla = nla_reserve(skb, NLA_UNSPEC,
sizeof(struct net_dm_alert_msg));
if (!nla) {
nlmsg_free(skb);
skb = NULL;
goto err;
}
msg = nla_data(nla);
memset(msg, 0, al);
goto out;
err:
mod_timer(&data->send_timer, jiffies + HZ / 10);
out:
drop_monitor: dont sleep in atomic context drop_monitor calls several sleeping functions while in atomic context. BUG: sleeping function called from invalid context at mm/slub.c:943 in_atomic(): 1, irqs_disabled(): 0, pid: 2103, name: kworker/0:2 Pid: 2103, comm: kworker/0:2 Not tainted 3.5.0-rc1+ #55 Call Trace: [<ffffffff810697ca>] __might_sleep+0xca/0xf0 [<ffffffff811345a3>] kmem_cache_alloc_node+0x1b3/0x1c0 [<ffffffff8105578c>] ? queue_delayed_work_on+0x11c/0x130 [<ffffffff815343fb>] __alloc_skb+0x4b/0x230 [<ffffffffa00b0360>] ? reset_per_cpu_data+0x160/0x160 [drop_monitor] [<ffffffffa00b022f>] reset_per_cpu_data+0x2f/0x160 [drop_monitor] [<ffffffffa00b03ab>] send_dm_alert+0x4b/0xb0 [drop_monitor] [<ffffffff810568e0>] process_one_work+0x130/0x4c0 [<ffffffff81058249>] worker_thread+0x159/0x360 [<ffffffff810580f0>] ? manage_workers.isra.27+0x240/0x240 [<ffffffff8105d403>] kthread+0x93/0xa0 [<ffffffff816be6d4>] kernel_thread_helper+0x4/0x10 [<ffffffff8105d370>] ? kthread_freezable_should_stop+0x80/0x80 [<ffffffff816be6d0>] ? gs_change+0xb/0xb Rework the logic to call the sleeping functions in right context. Use standard timer/workqueue api to let system chose any cpu to perform the allocation and netlink send. Also avoid a loop if reset_per_cpu_data() cannot allocate memory : use mod_timer() to wait 1/10 second before next try. Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Neil Horman <nhorman@tuxdriver.com> Reviewed-by: Neil Horman <nhorman@tuxdriver.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-06-04 00:18:19 +00:00
spin_lock_irqsave(&data->lock, flags);
swap(data->skb, skb);
spin_unlock_irqrestore(&data->lock, flags);
if (skb) {
struct nlmsghdr *nlh = (struct nlmsghdr *)skb->data;
struct genlmsghdr *gnlh = (struct genlmsghdr *)nlmsg_data(nlh);
genlmsg_end(skb, genlmsg_data(gnlh));
}
drop_monitor: dont sleep in atomic context drop_monitor calls several sleeping functions while in atomic context. BUG: sleeping function called from invalid context at mm/slub.c:943 in_atomic(): 1, irqs_disabled(): 0, pid: 2103, name: kworker/0:2 Pid: 2103, comm: kworker/0:2 Not tainted 3.5.0-rc1+ #55 Call Trace: [<ffffffff810697ca>] __might_sleep+0xca/0xf0 [<ffffffff811345a3>] kmem_cache_alloc_node+0x1b3/0x1c0 [<ffffffff8105578c>] ? queue_delayed_work_on+0x11c/0x130 [<ffffffff815343fb>] __alloc_skb+0x4b/0x230 [<ffffffffa00b0360>] ? reset_per_cpu_data+0x160/0x160 [drop_monitor] [<ffffffffa00b022f>] reset_per_cpu_data+0x2f/0x160 [drop_monitor] [<ffffffffa00b03ab>] send_dm_alert+0x4b/0xb0 [drop_monitor] [<ffffffff810568e0>] process_one_work+0x130/0x4c0 [<ffffffff81058249>] worker_thread+0x159/0x360 [<ffffffff810580f0>] ? manage_workers.isra.27+0x240/0x240 [<ffffffff8105d403>] kthread+0x93/0xa0 [<ffffffff816be6d4>] kernel_thread_helper+0x4/0x10 [<ffffffff8105d370>] ? kthread_freezable_should_stop+0x80/0x80 [<ffffffff816be6d0>] ? gs_change+0xb/0xb Rework the logic to call the sleeping functions in right context. Use standard timer/workqueue api to let system chose any cpu to perform the allocation and netlink send. Also avoid a loop if reset_per_cpu_data() cannot allocate memory : use mod_timer() to wait 1/10 second before next try. Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Neil Horman <nhorman@tuxdriver.com> Reviewed-by: Neil Horman <nhorman@tuxdriver.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-06-04 00:18:19 +00:00
return skb;
}
static const struct genl_multicast_group dropmon_mcgrps[] = {
{ .name = "events", },
};
drop_monitor: dont sleep in atomic context drop_monitor calls several sleeping functions while in atomic context. BUG: sleeping function called from invalid context at mm/slub.c:943 in_atomic(): 1, irqs_disabled(): 0, pid: 2103, name: kworker/0:2 Pid: 2103, comm: kworker/0:2 Not tainted 3.5.0-rc1+ #55 Call Trace: [<ffffffff810697ca>] __might_sleep+0xca/0xf0 [<ffffffff811345a3>] kmem_cache_alloc_node+0x1b3/0x1c0 [<ffffffff8105578c>] ? queue_delayed_work_on+0x11c/0x130 [<ffffffff815343fb>] __alloc_skb+0x4b/0x230 [<ffffffffa00b0360>] ? reset_per_cpu_data+0x160/0x160 [drop_monitor] [<ffffffffa00b022f>] reset_per_cpu_data+0x2f/0x160 [drop_monitor] [<ffffffffa00b03ab>] send_dm_alert+0x4b/0xb0 [drop_monitor] [<ffffffff810568e0>] process_one_work+0x130/0x4c0 [<ffffffff81058249>] worker_thread+0x159/0x360 [<ffffffff810580f0>] ? manage_workers.isra.27+0x240/0x240 [<ffffffff8105d403>] kthread+0x93/0xa0 [<ffffffff816be6d4>] kernel_thread_helper+0x4/0x10 [<ffffffff8105d370>] ? kthread_freezable_should_stop+0x80/0x80 [<ffffffff816be6d0>] ? gs_change+0xb/0xb Rework the logic to call the sleeping functions in right context. Use standard timer/workqueue api to let system chose any cpu to perform the allocation and netlink send. Also avoid a loop if reset_per_cpu_data() cannot allocate memory : use mod_timer() to wait 1/10 second before next try. Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Neil Horman <nhorman@tuxdriver.com> Reviewed-by: Neil Horman <nhorman@tuxdriver.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-06-04 00:18:19 +00:00
static void send_dm_alert(struct work_struct *work)
{
struct sk_buff *skb;
drop_monitor: dont sleep in atomic context drop_monitor calls several sleeping functions while in atomic context. BUG: sleeping function called from invalid context at mm/slub.c:943 in_atomic(): 1, irqs_disabled(): 0, pid: 2103, name: kworker/0:2 Pid: 2103, comm: kworker/0:2 Not tainted 3.5.0-rc1+ #55 Call Trace: [<ffffffff810697ca>] __might_sleep+0xca/0xf0 [<ffffffff811345a3>] kmem_cache_alloc_node+0x1b3/0x1c0 [<ffffffff8105578c>] ? queue_delayed_work_on+0x11c/0x130 [<ffffffff815343fb>] __alloc_skb+0x4b/0x230 [<ffffffffa00b0360>] ? reset_per_cpu_data+0x160/0x160 [drop_monitor] [<ffffffffa00b022f>] reset_per_cpu_data+0x2f/0x160 [drop_monitor] [<ffffffffa00b03ab>] send_dm_alert+0x4b/0xb0 [drop_monitor] [<ffffffff810568e0>] process_one_work+0x130/0x4c0 [<ffffffff81058249>] worker_thread+0x159/0x360 [<ffffffff810580f0>] ? manage_workers.isra.27+0x240/0x240 [<ffffffff8105d403>] kthread+0x93/0xa0 [<ffffffff816be6d4>] kernel_thread_helper+0x4/0x10 [<ffffffff8105d370>] ? kthread_freezable_should_stop+0x80/0x80 [<ffffffff816be6d0>] ? gs_change+0xb/0xb Rework the logic to call the sleeping functions in right context. Use standard timer/workqueue api to let system chose any cpu to perform the allocation and netlink send. Also avoid a loop if reset_per_cpu_data() cannot allocate memory : use mod_timer() to wait 1/10 second before next try. Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Neil Horman <nhorman@tuxdriver.com> Reviewed-by: Neil Horman <nhorman@tuxdriver.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-06-04 00:18:19 +00:00
struct per_cpu_dm_data *data;
drop_monitor: dont sleep in atomic context drop_monitor calls several sleeping functions while in atomic context. BUG: sleeping function called from invalid context at mm/slub.c:943 in_atomic(): 1, irqs_disabled(): 0, pid: 2103, name: kworker/0:2 Pid: 2103, comm: kworker/0:2 Not tainted 3.5.0-rc1+ #55 Call Trace: [<ffffffff810697ca>] __might_sleep+0xca/0xf0 [<ffffffff811345a3>] kmem_cache_alloc_node+0x1b3/0x1c0 [<ffffffff8105578c>] ? queue_delayed_work_on+0x11c/0x130 [<ffffffff815343fb>] __alloc_skb+0x4b/0x230 [<ffffffffa00b0360>] ? reset_per_cpu_data+0x160/0x160 [drop_monitor] [<ffffffffa00b022f>] reset_per_cpu_data+0x2f/0x160 [drop_monitor] [<ffffffffa00b03ab>] send_dm_alert+0x4b/0xb0 [drop_monitor] [<ffffffff810568e0>] process_one_work+0x130/0x4c0 [<ffffffff81058249>] worker_thread+0x159/0x360 [<ffffffff810580f0>] ? manage_workers.isra.27+0x240/0x240 [<ffffffff8105d403>] kthread+0x93/0xa0 [<ffffffff816be6d4>] kernel_thread_helper+0x4/0x10 [<ffffffff8105d370>] ? kthread_freezable_should_stop+0x80/0x80 [<ffffffff816be6d0>] ? gs_change+0xb/0xb Rework the logic to call the sleeping functions in right context. Use standard timer/workqueue api to let system chose any cpu to perform the allocation and netlink send. Also avoid a loop if reset_per_cpu_data() cannot allocate memory : use mod_timer() to wait 1/10 second before next try. Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Neil Horman <nhorman@tuxdriver.com> Reviewed-by: Neil Horman <nhorman@tuxdriver.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-06-04 00:18:19 +00:00
data = container_of(work, struct per_cpu_dm_data, dm_alert_work);
drop_monitor: dont sleep in atomic context drop_monitor calls several sleeping functions while in atomic context. BUG: sleeping function called from invalid context at mm/slub.c:943 in_atomic(): 1, irqs_disabled(): 0, pid: 2103, name: kworker/0:2 Pid: 2103, comm: kworker/0:2 Not tainted 3.5.0-rc1+ #55 Call Trace: [<ffffffff810697ca>] __might_sleep+0xca/0xf0 [<ffffffff811345a3>] kmem_cache_alloc_node+0x1b3/0x1c0 [<ffffffff8105578c>] ? queue_delayed_work_on+0x11c/0x130 [<ffffffff815343fb>] __alloc_skb+0x4b/0x230 [<ffffffffa00b0360>] ? reset_per_cpu_data+0x160/0x160 [drop_monitor] [<ffffffffa00b022f>] reset_per_cpu_data+0x2f/0x160 [drop_monitor] [<ffffffffa00b03ab>] send_dm_alert+0x4b/0xb0 [drop_monitor] [<ffffffff810568e0>] process_one_work+0x130/0x4c0 [<ffffffff81058249>] worker_thread+0x159/0x360 [<ffffffff810580f0>] ? manage_workers.isra.27+0x240/0x240 [<ffffffff8105d403>] kthread+0x93/0xa0 [<ffffffff816be6d4>] kernel_thread_helper+0x4/0x10 [<ffffffff8105d370>] ? kthread_freezable_should_stop+0x80/0x80 [<ffffffff816be6d0>] ? gs_change+0xb/0xb Rework the logic to call the sleeping functions in right context. Use standard timer/workqueue api to let system chose any cpu to perform the allocation and netlink send. Also avoid a loop if reset_per_cpu_data() cannot allocate memory : use mod_timer() to wait 1/10 second before next try. Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Neil Horman <nhorman@tuxdriver.com> Reviewed-by: Neil Horman <nhorman@tuxdriver.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-06-04 00:18:19 +00:00
skb = reset_per_cpu_data(data);
if (skb)
genlmsg_multicast(&net_drop_monitor_family, skb, 0,
0, GFP_KERNEL);
}
/*
* This is the timer function to delay the sending of an alert
* in the event that more drops will arrive during the
drop_monitor: dont sleep in atomic context drop_monitor calls several sleeping functions while in atomic context. BUG: sleeping function called from invalid context at mm/slub.c:943 in_atomic(): 1, irqs_disabled(): 0, pid: 2103, name: kworker/0:2 Pid: 2103, comm: kworker/0:2 Not tainted 3.5.0-rc1+ #55 Call Trace: [<ffffffff810697ca>] __might_sleep+0xca/0xf0 [<ffffffff811345a3>] kmem_cache_alloc_node+0x1b3/0x1c0 [<ffffffff8105578c>] ? queue_delayed_work_on+0x11c/0x130 [<ffffffff815343fb>] __alloc_skb+0x4b/0x230 [<ffffffffa00b0360>] ? reset_per_cpu_data+0x160/0x160 [drop_monitor] [<ffffffffa00b022f>] reset_per_cpu_data+0x2f/0x160 [drop_monitor] [<ffffffffa00b03ab>] send_dm_alert+0x4b/0xb0 [drop_monitor] [<ffffffff810568e0>] process_one_work+0x130/0x4c0 [<ffffffff81058249>] worker_thread+0x159/0x360 [<ffffffff810580f0>] ? manage_workers.isra.27+0x240/0x240 [<ffffffff8105d403>] kthread+0x93/0xa0 [<ffffffff816be6d4>] kernel_thread_helper+0x4/0x10 [<ffffffff8105d370>] ? kthread_freezable_should_stop+0x80/0x80 [<ffffffff816be6d0>] ? gs_change+0xb/0xb Rework the logic to call the sleeping functions in right context. Use standard timer/workqueue api to let system chose any cpu to perform the allocation and netlink send. Also avoid a loop if reset_per_cpu_data() cannot allocate memory : use mod_timer() to wait 1/10 second before next try. Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Neil Horman <nhorman@tuxdriver.com> Reviewed-by: Neil Horman <nhorman@tuxdriver.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-06-04 00:18:19 +00:00
* hysteresis period.
*/
drop_monitor: dont sleep in atomic context drop_monitor calls several sleeping functions while in atomic context. BUG: sleeping function called from invalid context at mm/slub.c:943 in_atomic(): 1, irqs_disabled(): 0, pid: 2103, name: kworker/0:2 Pid: 2103, comm: kworker/0:2 Not tainted 3.5.0-rc1+ #55 Call Trace: [<ffffffff810697ca>] __might_sleep+0xca/0xf0 [<ffffffff811345a3>] kmem_cache_alloc_node+0x1b3/0x1c0 [<ffffffff8105578c>] ? queue_delayed_work_on+0x11c/0x130 [<ffffffff815343fb>] __alloc_skb+0x4b/0x230 [<ffffffffa00b0360>] ? reset_per_cpu_data+0x160/0x160 [drop_monitor] [<ffffffffa00b022f>] reset_per_cpu_data+0x2f/0x160 [drop_monitor] [<ffffffffa00b03ab>] send_dm_alert+0x4b/0xb0 [drop_monitor] [<ffffffff810568e0>] process_one_work+0x130/0x4c0 [<ffffffff81058249>] worker_thread+0x159/0x360 [<ffffffff810580f0>] ? manage_workers.isra.27+0x240/0x240 [<ffffffff8105d403>] kthread+0x93/0xa0 [<ffffffff816be6d4>] kernel_thread_helper+0x4/0x10 [<ffffffff8105d370>] ? kthread_freezable_should_stop+0x80/0x80 [<ffffffff816be6d0>] ? gs_change+0xb/0xb Rework the logic to call the sleeping functions in right context. Use standard timer/workqueue api to let system chose any cpu to perform the allocation and netlink send. Also avoid a loop if reset_per_cpu_data() cannot allocate memory : use mod_timer() to wait 1/10 second before next try. Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Neil Horman <nhorman@tuxdriver.com> Reviewed-by: Neil Horman <nhorman@tuxdriver.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-06-04 00:18:19 +00:00
static void sched_send_work(unsigned long _data)
{
drop_monitor: dont sleep in atomic context drop_monitor calls several sleeping functions while in atomic context. BUG: sleeping function called from invalid context at mm/slub.c:943 in_atomic(): 1, irqs_disabled(): 0, pid: 2103, name: kworker/0:2 Pid: 2103, comm: kworker/0:2 Not tainted 3.5.0-rc1+ #55 Call Trace: [<ffffffff810697ca>] __might_sleep+0xca/0xf0 [<ffffffff811345a3>] kmem_cache_alloc_node+0x1b3/0x1c0 [<ffffffff8105578c>] ? queue_delayed_work_on+0x11c/0x130 [<ffffffff815343fb>] __alloc_skb+0x4b/0x230 [<ffffffffa00b0360>] ? reset_per_cpu_data+0x160/0x160 [drop_monitor] [<ffffffffa00b022f>] reset_per_cpu_data+0x2f/0x160 [drop_monitor] [<ffffffffa00b03ab>] send_dm_alert+0x4b/0xb0 [drop_monitor] [<ffffffff810568e0>] process_one_work+0x130/0x4c0 [<ffffffff81058249>] worker_thread+0x159/0x360 [<ffffffff810580f0>] ? manage_workers.isra.27+0x240/0x240 [<ffffffff8105d403>] kthread+0x93/0xa0 [<ffffffff816be6d4>] kernel_thread_helper+0x4/0x10 [<ffffffff8105d370>] ? kthread_freezable_should_stop+0x80/0x80 [<ffffffff816be6d0>] ? gs_change+0xb/0xb Rework the logic to call the sleeping functions in right context. Use standard timer/workqueue api to let system chose any cpu to perform the allocation and netlink send. Also avoid a loop if reset_per_cpu_data() cannot allocate memory : use mod_timer() to wait 1/10 second before next try. Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Neil Horman <nhorman@tuxdriver.com> Reviewed-by: Neil Horman <nhorman@tuxdriver.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-06-04 00:18:19 +00:00
struct per_cpu_dm_data *data = (struct per_cpu_dm_data *)_data;
drop_monitor: dont sleep in atomic context drop_monitor calls several sleeping functions while in atomic context. BUG: sleeping function called from invalid context at mm/slub.c:943 in_atomic(): 1, irqs_disabled(): 0, pid: 2103, name: kworker/0:2 Pid: 2103, comm: kworker/0:2 Not tainted 3.5.0-rc1+ #55 Call Trace: [<ffffffff810697ca>] __might_sleep+0xca/0xf0 [<ffffffff811345a3>] kmem_cache_alloc_node+0x1b3/0x1c0 [<ffffffff8105578c>] ? queue_delayed_work_on+0x11c/0x130 [<ffffffff815343fb>] __alloc_skb+0x4b/0x230 [<ffffffffa00b0360>] ? reset_per_cpu_data+0x160/0x160 [drop_monitor] [<ffffffffa00b022f>] reset_per_cpu_data+0x2f/0x160 [drop_monitor] [<ffffffffa00b03ab>] send_dm_alert+0x4b/0xb0 [drop_monitor] [<ffffffff810568e0>] process_one_work+0x130/0x4c0 [<ffffffff81058249>] worker_thread+0x159/0x360 [<ffffffff810580f0>] ? manage_workers.isra.27+0x240/0x240 [<ffffffff8105d403>] kthread+0x93/0xa0 [<ffffffff816be6d4>] kernel_thread_helper+0x4/0x10 [<ffffffff8105d370>] ? kthread_freezable_should_stop+0x80/0x80 [<ffffffff816be6d0>] ? gs_change+0xb/0xb Rework the logic to call the sleeping functions in right context. Use standard timer/workqueue api to let system chose any cpu to perform the allocation and netlink send. Also avoid a loop if reset_per_cpu_data() cannot allocate memory : use mod_timer() to wait 1/10 second before next try. Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Neil Horman <nhorman@tuxdriver.com> Reviewed-by: Neil Horman <nhorman@tuxdriver.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-06-04 00:18:19 +00:00
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 sk_buff *dskb;
drop_monitor: dont sleep in atomic context drop_monitor calls several sleeping functions while in atomic context. BUG: sleeping function called from invalid context at mm/slub.c:943 in_atomic(): 1, irqs_disabled(): 0, pid: 2103, name: kworker/0:2 Pid: 2103, comm: kworker/0:2 Not tainted 3.5.0-rc1+ #55 Call Trace: [<ffffffff810697ca>] __might_sleep+0xca/0xf0 [<ffffffff811345a3>] kmem_cache_alloc_node+0x1b3/0x1c0 [<ffffffff8105578c>] ? queue_delayed_work_on+0x11c/0x130 [<ffffffff815343fb>] __alloc_skb+0x4b/0x230 [<ffffffffa00b0360>] ? reset_per_cpu_data+0x160/0x160 [drop_monitor] [<ffffffffa00b022f>] reset_per_cpu_data+0x2f/0x160 [drop_monitor] [<ffffffffa00b03ab>] send_dm_alert+0x4b/0xb0 [drop_monitor] [<ffffffff810568e0>] process_one_work+0x130/0x4c0 [<ffffffff81058249>] worker_thread+0x159/0x360 [<ffffffff810580f0>] ? manage_workers.isra.27+0x240/0x240 [<ffffffff8105d403>] kthread+0x93/0xa0 [<ffffffff816be6d4>] kernel_thread_helper+0x4/0x10 [<ffffffff8105d370>] ? kthread_freezable_should_stop+0x80/0x80 [<ffffffff816be6d0>] ? gs_change+0xb/0xb Rework the logic to call the sleeping functions in right context. Use standard timer/workqueue api to let system chose any cpu to perform the allocation and netlink send. Also avoid a loop if reset_per_cpu_data() cannot allocate memory : use mod_timer() to wait 1/10 second before next try. Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Neil Horman <nhorman@tuxdriver.com> Reviewed-by: Neil Horman <nhorman@tuxdriver.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-06-04 00:18:19 +00:00
struct per_cpu_dm_data *data;
unsigned long flags;
drop_monitor: dont sleep in atomic context drop_monitor calls several sleeping functions while in atomic context. BUG: sleeping function called from invalid context at mm/slub.c:943 in_atomic(): 1, irqs_disabled(): 0, pid: 2103, name: kworker/0:2 Pid: 2103, comm: kworker/0:2 Not tainted 3.5.0-rc1+ #55 Call Trace: [<ffffffff810697ca>] __might_sleep+0xca/0xf0 [<ffffffff811345a3>] kmem_cache_alloc_node+0x1b3/0x1c0 [<ffffffff8105578c>] ? queue_delayed_work_on+0x11c/0x130 [<ffffffff815343fb>] __alloc_skb+0x4b/0x230 [<ffffffffa00b0360>] ? reset_per_cpu_data+0x160/0x160 [drop_monitor] [<ffffffffa00b022f>] reset_per_cpu_data+0x2f/0x160 [drop_monitor] [<ffffffffa00b03ab>] send_dm_alert+0x4b/0xb0 [drop_monitor] [<ffffffff810568e0>] process_one_work+0x130/0x4c0 [<ffffffff81058249>] worker_thread+0x159/0x360 [<ffffffff810580f0>] ? manage_workers.isra.27+0x240/0x240 [<ffffffff8105d403>] kthread+0x93/0xa0 [<ffffffff816be6d4>] kernel_thread_helper+0x4/0x10 [<ffffffff8105d370>] ? kthread_freezable_should_stop+0x80/0x80 [<ffffffff816be6d0>] ? gs_change+0xb/0xb Rework the logic to call the sleeping functions in right context. Use standard timer/workqueue api to let system chose any cpu to perform the allocation and netlink send. Also avoid a loop if reset_per_cpu_data() cannot allocate memory : use mod_timer() to wait 1/10 second before next try. Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Neil Horman <nhorman@tuxdriver.com> Reviewed-by: Neil Horman <nhorman@tuxdriver.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-06-04 00:18:19 +00:00
local_irq_save(flags);
data = this_cpu_ptr(&dm_cpu_data);
drop_monitor: dont sleep in atomic context drop_monitor calls several sleeping functions while in atomic context. BUG: sleeping function called from invalid context at mm/slub.c:943 in_atomic(): 1, irqs_disabled(): 0, pid: 2103, name: kworker/0:2 Pid: 2103, comm: kworker/0:2 Not tainted 3.5.0-rc1+ #55 Call Trace: [<ffffffff810697ca>] __might_sleep+0xca/0xf0 [<ffffffff811345a3>] kmem_cache_alloc_node+0x1b3/0x1c0 [<ffffffff8105578c>] ? queue_delayed_work_on+0x11c/0x130 [<ffffffff815343fb>] __alloc_skb+0x4b/0x230 [<ffffffffa00b0360>] ? reset_per_cpu_data+0x160/0x160 [drop_monitor] [<ffffffffa00b022f>] reset_per_cpu_data+0x2f/0x160 [drop_monitor] [<ffffffffa00b03ab>] send_dm_alert+0x4b/0xb0 [drop_monitor] [<ffffffff810568e0>] process_one_work+0x130/0x4c0 [<ffffffff81058249>] worker_thread+0x159/0x360 [<ffffffff810580f0>] ? manage_workers.isra.27+0x240/0x240 [<ffffffff8105d403>] kthread+0x93/0xa0 [<ffffffff816be6d4>] kernel_thread_helper+0x4/0x10 [<ffffffff8105d370>] ? kthread_freezable_should_stop+0x80/0x80 [<ffffffff816be6d0>] ? gs_change+0xb/0xb Rework the logic to call the sleeping functions in right context. Use standard timer/workqueue api to let system chose any cpu to perform the allocation and netlink send. Also avoid a loop if reset_per_cpu_data() cannot allocate memory : use mod_timer() to wait 1/10 second before next try. Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Neil Horman <nhorman@tuxdriver.com> Reviewed-by: Neil Horman <nhorman@tuxdriver.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-06-04 00:18:19 +00:00
spin_lock(&data->lock);
dskb = data->skb;
if (!dskb)
goto out;
nlh = (struct nlmsghdr *)dskb->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;
}
}
drop_monitor: dont sleep in atomic context drop_monitor calls several sleeping functions while in atomic context. BUG: sleeping function called from invalid context at mm/slub.c:943 in_atomic(): 1, irqs_disabled(): 0, pid: 2103, name: kworker/0:2 Pid: 2103, comm: kworker/0:2 Not tainted 3.5.0-rc1+ #55 Call Trace: [<ffffffff810697ca>] __might_sleep+0xca/0xf0 [<ffffffff811345a3>] kmem_cache_alloc_node+0x1b3/0x1c0 [<ffffffff8105578c>] ? queue_delayed_work_on+0x11c/0x130 [<ffffffff815343fb>] __alloc_skb+0x4b/0x230 [<ffffffffa00b0360>] ? reset_per_cpu_data+0x160/0x160 [drop_monitor] [<ffffffffa00b022f>] reset_per_cpu_data+0x2f/0x160 [drop_monitor] [<ffffffffa00b03ab>] send_dm_alert+0x4b/0xb0 [drop_monitor] [<ffffffff810568e0>] process_one_work+0x130/0x4c0 [<ffffffff81058249>] worker_thread+0x159/0x360 [<ffffffff810580f0>] ? manage_workers.isra.27+0x240/0x240 [<ffffffff8105d403>] kthread+0x93/0xa0 [<ffffffff816be6d4>] kernel_thread_helper+0x4/0x10 [<ffffffff8105d370>] ? kthread_freezable_should_stop+0x80/0x80 [<ffffffff816be6d0>] ? gs_change+0xb/0xb Rework the logic to call the sleeping functions in right context. Use standard timer/workqueue api to let system chose any cpu to perform the allocation and netlink send. Also avoid a loop if reset_per_cpu_data() cannot allocate memory : use mod_timer() to wait 1/10 second before next try. Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Neil Horman <nhorman@tuxdriver.com> Reviewed-by: Neil Horman <nhorman@tuxdriver.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-06-04 00:18:19 +00:00
if (msg->entries == dm_hit_limit)
goto out;
/*
* We need to create a new entry
*/
__nla_reserve_nohdr(dskb, 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;
drop_monitor: dont sleep in atomic context drop_monitor calls several sleeping functions while in atomic context. BUG: sleeping function called from invalid context at mm/slub.c:943 in_atomic(): 1, irqs_disabled(): 0, pid: 2103, name: kworker/0:2 Pid: 2103, comm: kworker/0:2 Not tainted 3.5.0-rc1+ #55 Call Trace: [<ffffffff810697ca>] __might_sleep+0xca/0xf0 [<ffffffff811345a3>] kmem_cache_alloc_node+0x1b3/0x1c0 [<ffffffff8105578c>] ? queue_delayed_work_on+0x11c/0x130 [<ffffffff815343fb>] __alloc_skb+0x4b/0x230 [<ffffffffa00b0360>] ? reset_per_cpu_data+0x160/0x160 [drop_monitor] [<ffffffffa00b022f>] reset_per_cpu_data+0x2f/0x160 [drop_monitor] [<ffffffffa00b03ab>] send_dm_alert+0x4b/0xb0 [drop_monitor] [<ffffffff810568e0>] process_one_work+0x130/0x4c0 [<ffffffff81058249>] worker_thread+0x159/0x360 [<ffffffff810580f0>] ? manage_workers.isra.27+0x240/0x240 [<ffffffff8105d403>] kthread+0x93/0xa0 [<ffffffff816be6d4>] kernel_thread_helper+0x4/0x10 [<ffffffff8105d370>] ? kthread_freezable_should_stop+0x80/0x80 [<ffffffff816be6d0>] ? gs_change+0xb/0xb Rework the logic to call the sleeping functions in right context. Use standard timer/workqueue api to let system chose any cpu to perform the allocation and netlink send. Also avoid a loop if reset_per_cpu_data() cannot allocate memory : use mod_timer() to wait 1/10 second before next try. Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Neil Horman <nhorman@tuxdriver.com> Reviewed-by: Neil Horman <nhorman@tuxdriver.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-06-04 00:18:19 +00:00
add_timer(&data->send_timer);
}
out:
drop_monitor: dont sleep in atomic context drop_monitor calls several sleeping functions while in atomic context. BUG: sleeping function called from invalid context at mm/slub.c:943 in_atomic(): 1, irqs_disabled(): 0, pid: 2103, name: kworker/0:2 Pid: 2103, comm: kworker/0:2 Not tainted 3.5.0-rc1+ #55 Call Trace: [<ffffffff810697ca>] __might_sleep+0xca/0xf0 [<ffffffff811345a3>] kmem_cache_alloc_node+0x1b3/0x1c0 [<ffffffff8105578c>] ? queue_delayed_work_on+0x11c/0x130 [<ffffffff815343fb>] __alloc_skb+0x4b/0x230 [<ffffffffa00b0360>] ? reset_per_cpu_data+0x160/0x160 [drop_monitor] [<ffffffffa00b022f>] reset_per_cpu_data+0x2f/0x160 [drop_monitor] [<ffffffffa00b03ab>] send_dm_alert+0x4b/0xb0 [drop_monitor] [<ffffffff810568e0>] process_one_work+0x130/0x4c0 [<ffffffff81058249>] worker_thread+0x159/0x360 [<ffffffff810580f0>] ? manage_workers.isra.27+0x240/0x240 [<ffffffff8105d403>] kthread+0x93/0xa0 [<ffffffff816be6d4>] kernel_thread_helper+0x4/0x10 [<ffffffff8105d370>] ? kthread_freezable_should_stop+0x80/0x80 [<ffffffff816be6d0>] ? gs_change+0xb/0xb Rework the logic to call the sleeping functions in right context. Use standard timer/workqueue api to let system chose any cpu to perform the allocation and netlink send. Also avoid a loop if reset_per_cpu_data() cannot allocate memory : use mod_timer() to wait 1/10 second before next try. Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Neil Horman <nhorman@tuxdriver.com> Reviewed-by: Neil Horman <nhorman@tuxdriver.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-06-04 00:18:19 +00:00
spin_unlock_irqrestore(&data->lock, flags);
}
tracing: Let tracepoints have data passed to tracepoint callbacks This patch adds data to be passed to tracepoint callbacks. The created functions from DECLARE_TRACE() now need a mandatory data parameter. For example: DECLARE_TRACE(mytracepoint, int value, value) Will create the register function: int register_trace_mytracepoint((void(*)(void *data, int value))probe, void *data); As the first argument, all callbacks (probes) must take a (void *data) parameter. So a callback for the above tracepoint will look like: void myprobe(void *data, int value) { } The callback may choose to ignore the data parameter. This change allows callbacks to register a private data pointer along with the function probe. void mycallback(void *data, int value); register_trace_mytracepoint(mycallback, mydata); Then the mycallback() will receive the "mydata" as the first parameter before the args. A more detailed example: DECLARE_TRACE(mytracepoint, TP_PROTO(int status), TP_ARGS(status)); /* In the C file */ DEFINE_TRACE(mytracepoint, TP_PROTO(int status), TP_ARGS(status)); [...] trace_mytracepoint(status); /* In a file registering this tracepoint */ int my_callback(void *data, int status) { struct my_struct my_data = data; [...] } [...] my_data = kmalloc(sizeof(*my_data), GFP_KERNEL); init_my_data(my_data); register_trace_mytracepoint(my_callback, my_data); The same callback can also be registered to the same tracepoint as long as the data registered is different. Note, the data must also be used to unregister the callback: unregister_trace_mytracepoint(my_callback, my_data); Because of the data parameter, tracepoints declared this way can not have no args. That is: DECLARE_TRACE(mytracepoint, TP_PROTO(void), TP_ARGS()); will cause an error. If no arguments are needed, a new macro can be used instead: DECLARE_TRACE_NOARGS(mytracepoint); Since there are no arguments, the proto and args fields are left out. This is part of a series to make the tracepoint footprint smaller: text data bss dec hex filename 4913961 1088356 861512 6863829 68bbd5 vmlinux.orig 4914025 1088868 861512 6864405 68be15 vmlinux.class 4918492 1084612 861512 6864616 68bee8 vmlinux.tracepoint Again, this patch also increases the size of the kernel, but lays the ground work for decreasing it. v5: Fixed net/core/drop_monitor.c to handle these updates. v4: Moved the DECLARE_TRACE() DECLARE_TRACE_NOARGS out of the #ifdef CONFIG_TRACE_POINTS, since the two are the same in both cases. The __DECLARE_TRACE() is what changes. Thanks to Frederic Weisbecker for pointing this out. v3: Made all register_* functions require data to be passed and all callbacks to take a void * parameter as its first argument. This makes the calling functions comply with C standards. Also added more comments to the modifications of DECLARE_TRACE(). v2: Made the DECLARE_TRACE() have the ability to pass arguments and added a new DECLARE_TRACE_NOARGS() for tracepoints that do not need any arguments. Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Acked-by: Masami Hiramatsu <mhiramat@redhat.com> Acked-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Neil Horman <nhorman@tuxdriver.com> Cc: David S. Miller <davem@davemloft.net> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2010-04-20 21:04:50 +00:00
static void trace_kfree_skb_hit(void *ignore, struct sk_buff *skb, void *location)
{
trace_drop_common(skb, location);
}
static void trace_napi_poll_hit(void *ignore, struct napi_struct *napi,
int work, int budget)
{
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 int set_all_monitor_traces(int state)
{
int rc = 0;
struct dm_hw_stat_delta *new_stat = NULL;
struct dm_hw_stat_delta *temp;
drop_monitor: fix sleeping in invalid context warning Eric Dumazet pointed out this warning in the drop_monitor protocol to me: [ 38.352571] BUG: sleeping function called from invalid context at kernel/mutex.c:85 [ 38.352576] in_atomic(): 1, irqs_disabled(): 0, pid: 4415, name: dropwatch [ 38.352580] Pid: 4415, comm: dropwatch Not tainted 3.4.0-rc2+ #71 [ 38.352582] Call Trace: [ 38.352592] [<ffffffff8153aaf0>] ? trace_napi_poll_hit+0xd0/0xd0 [ 38.352599] [<ffffffff81063f2a>] __might_sleep+0xca/0xf0 [ 38.352606] [<ffffffff81655b16>] mutex_lock+0x26/0x50 [ 38.352610] [<ffffffff8153aaf0>] ? trace_napi_poll_hit+0xd0/0xd0 [ 38.352616] [<ffffffff810b72d9>] tracepoint_probe_register+0x29/0x90 [ 38.352621] [<ffffffff8153a585>] set_all_monitor_traces+0x105/0x170 [ 38.352625] [<ffffffff8153a8ca>] net_dm_cmd_trace+0x2a/0x40 [ 38.352630] [<ffffffff8154a81a>] genl_rcv_msg+0x21a/0x2b0 [ 38.352636] [<ffffffff810f8029>] ? zone_statistics+0x99/0xc0 [ 38.352640] [<ffffffff8154a600>] ? genl_rcv+0x30/0x30 [ 38.352645] [<ffffffff8154a059>] netlink_rcv_skb+0xa9/0xd0 [ 38.352649] [<ffffffff8154a5f0>] genl_rcv+0x20/0x30 [ 38.352653] [<ffffffff81549a7e>] netlink_unicast+0x1ae/0x1f0 [ 38.352658] [<ffffffff81549d76>] netlink_sendmsg+0x2b6/0x310 [ 38.352663] [<ffffffff8150824f>] sock_sendmsg+0x10f/0x130 [ 38.352668] [<ffffffff8150abe0>] ? move_addr_to_kernel+0x60/0xb0 [ 38.352673] [<ffffffff81515f04>] ? verify_iovec+0x64/0xe0 [ 38.352677] [<ffffffff81509c46>] __sys_sendmsg+0x386/0x390 [ 38.352682] [<ffffffff810ffaf9>] ? handle_mm_fault+0x139/0x210 [ 38.352687] [<ffffffff8165b5bc>] ? do_page_fault+0x1ec/0x4f0 [ 38.352693] [<ffffffff8106ba4d>] ? set_next_entity+0x9d/0xb0 [ 38.352699] [<ffffffff81310b49>] ? tty_ldisc_deref+0x9/0x10 [ 38.352703] [<ffffffff8106d363>] ? pick_next_task_fair+0x63/0x140 [ 38.352708] [<ffffffff8150b8d4>] sys_sendmsg+0x44/0x80 [ 38.352713] [<ffffffff8165f8e2>] system_call_fastpath+0x16/0x1b It stems from holding a spinlock (trace_state_lock) while attempting to register or unregister tracepoint hooks, making in_atomic() true in this context, leading to the warning when the tracepoint calls might_sleep() while its taking a mutex. Since we only use the trace_state_lock to prevent trace protocol state races, as well as hardware stat list updates on an rcu write side, we can just convert the spinlock to a mutex to avoid this problem. Signed-off-by: Neil Horman <nhorman@tuxdriver.com> Reported-by: Eric Dumazet <eric.dumazet@gmail.com> CC: David Miller <davem@davemloft.net> Acked-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-04-27 10:11:48 +00:00
mutex_lock(&trace_state_mutex);
if (state == trace_state) {
rc = -EAGAIN;
goto out_unlock;
}
switch (state) {
case TRACE_ON:
if (!try_module_get(THIS_MODULE)) {
rc = -ENODEV;
break;
}
tracing: Let tracepoints have data passed to tracepoint callbacks This patch adds data to be passed to tracepoint callbacks. The created functions from DECLARE_TRACE() now need a mandatory data parameter. For example: DECLARE_TRACE(mytracepoint, int value, value) Will create the register function: int register_trace_mytracepoint((void(*)(void *data, int value))probe, void *data); As the first argument, all callbacks (probes) must take a (void *data) parameter. So a callback for the above tracepoint will look like: void myprobe(void *data, int value) { } The callback may choose to ignore the data parameter. This change allows callbacks to register a private data pointer along with the function probe. void mycallback(void *data, int value); register_trace_mytracepoint(mycallback, mydata); Then the mycallback() will receive the "mydata" as the first parameter before the args. A more detailed example: DECLARE_TRACE(mytracepoint, TP_PROTO(int status), TP_ARGS(status)); /* In the C file */ DEFINE_TRACE(mytracepoint, TP_PROTO(int status), TP_ARGS(status)); [...] trace_mytracepoint(status); /* In a file registering this tracepoint */ int my_callback(void *data, int status) { struct my_struct my_data = data; [...] } [...] my_data = kmalloc(sizeof(*my_data), GFP_KERNEL); init_my_data(my_data); register_trace_mytracepoint(my_callback, my_data); The same callback can also be registered to the same tracepoint as long as the data registered is different. Note, the data must also be used to unregister the callback: unregister_trace_mytracepoint(my_callback, my_data); Because of the data parameter, tracepoints declared this way can not have no args. That is: DECLARE_TRACE(mytracepoint, TP_PROTO(void), TP_ARGS()); will cause an error. If no arguments are needed, a new macro can be used instead: DECLARE_TRACE_NOARGS(mytracepoint); Since there are no arguments, the proto and args fields are left out. This is part of a series to make the tracepoint footprint smaller: text data bss dec hex filename 4913961 1088356 861512 6863829 68bbd5 vmlinux.orig 4914025 1088868 861512 6864405 68be15 vmlinux.class 4918492 1084612 861512 6864616 68bee8 vmlinux.tracepoint Again, this patch also increases the size of the kernel, but lays the ground work for decreasing it. v5: Fixed net/core/drop_monitor.c to handle these updates. v4: Moved the DECLARE_TRACE() DECLARE_TRACE_NOARGS out of the #ifdef CONFIG_TRACE_POINTS, since the two are the same in both cases. The __DECLARE_TRACE() is what changes. Thanks to Frederic Weisbecker for pointing this out. v3: Made all register_* functions require data to be passed and all callbacks to take a void * parameter as its first argument. This makes the calling functions comply with C standards. Also added more comments to the modifications of DECLARE_TRACE(). v2: Made the DECLARE_TRACE() have the ability to pass arguments and added a new DECLARE_TRACE_NOARGS() for tracepoints that do not need any arguments. Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Acked-by: Masami Hiramatsu <mhiramat@redhat.com> Acked-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Neil Horman <nhorman@tuxdriver.com> Cc: David S. Miller <davem@davemloft.net> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2010-04-20 21:04:50 +00:00
rc |= register_trace_kfree_skb(trace_kfree_skb_hit, NULL);
rc |= register_trace_napi_poll(trace_napi_poll_hit, NULL);
break;
case TRACE_OFF:
tracing: Let tracepoints have data passed to tracepoint callbacks This patch adds data to be passed to tracepoint callbacks. The created functions from DECLARE_TRACE() now need a mandatory data parameter. For example: DECLARE_TRACE(mytracepoint, int value, value) Will create the register function: int register_trace_mytracepoint((void(*)(void *data, int value))probe, void *data); As the first argument, all callbacks (probes) must take a (void *data) parameter. So a callback for the above tracepoint will look like: void myprobe(void *data, int value) { } The callback may choose to ignore the data parameter. This change allows callbacks to register a private data pointer along with the function probe. void mycallback(void *data, int value); register_trace_mytracepoint(mycallback, mydata); Then the mycallback() will receive the "mydata" as the first parameter before the args. A more detailed example: DECLARE_TRACE(mytracepoint, TP_PROTO(int status), TP_ARGS(status)); /* In the C file */ DEFINE_TRACE(mytracepoint, TP_PROTO(int status), TP_ARGS(status)); [...] trace_mytracepoint(status); /* In a file registering this tracepoint */ int my_callback(void *data, int status) { struct my_struct my_data = data; [...] } [...] my_data = kmalloc(sizeof(*my_data), GFP_KERNEL); init_my_data(my_data); register_trace_mytracepoint(my_callback, my_data); The same callback can also be registered to the same tracepoint as long as the data registered is different. Note, the data must also be used to unregister the callback: unregister_trace_mytracepoint(my_callback, my_data); Because of the data parameter, tracepoints declared this way can not have no args. That is: DECLARE_TRACE(mytracepoint, TP_PROTO(void), TP_ARGS()); will cause an error. If no arguments are needed, a new macro can be used instead: DECLARE_TRACE_NOARGS(mytracepoint); Since there are no arguments, the proto and args fields are left out. This is part of a series to make the tracepoint footprint smaller: text data bss dec hex filename 4913961 1088356 861512 6863829 68bbd5 vmlinux.orig 4914025 1088868 861512 6864405 68be15 vmlinux.class 4918492 1084612 861512 6864616 68bee8 vmlinux.tracepoint Again, this patch also increases the size of the kernel, but lays the ground work for decreasing it. v5: Fixed net/core/drop_monitor.c to handle these updates. v4: Moved the DECLARE_TRACE() DECLARE_TRACE_NOARGS out of the #ifdef CONFIG_TRACE_POINTS, since the two are the same in both cases. The __DECLARE_TRACE() is what changes. Thanks to Frederic Weisbecker for pointing this out. v3: Made all register_* functions require data to be passed and all callbacks to take a void * parameter as its first argument. This makes the calling functions comply with C standards. Also added more comments to the modifications of DECLARE_TRACE(). v2: Made the DECLARE_TRACE() have the ability to pass arguments and added a new DECLARE_TRACE_NOARGS() for tracepoints that do not need any arguments. Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Acked-by: Masami Hiramatsu <mhiramat@redhat.com> Acked-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Neil Horman <nhorman@tuxdriver.com> Cc: David S. Miller <davem@davemloft.net> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2010-04-20 21:04:50 +00:00
rc |= unregister_trace_kfree_skb(trace_kfree_skb_hit, NULL);
rc |= unregister_trace_napi_poll(trace_napi_poll_hit, NULL);
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);
kfree_rcu(new_stat, rcu);
}
}
module_put(THIS_MODULE);
break;
default:
rc = 1;
break;
}
if (!rc)
trace_state = state;
else
rc = -EINPROGRESS;
out_unlock:
drop_monitor: fix sleeping in invalid context warning Eric Dumazet pointed out this warning in the drop_monitor protocol to me: [ 38.352571] BUG: sleeping function called from invalid context at kernel/mutex.c:85 [ 38.352576] in_atomic(): 1, irqs_disabled(): 0, pid: 4415, name: dropwatch [ 38.352580] Pid: 4415, comm: dropwatch Not tainted 3.4.0-rc2+ #71 [ 38.352582] Call Trace: [ 38.352592] [<ffffffff8153aaf0>] ? trace_napi_poll_hit+0xd0/0xd0 [ 38.352599] [<ffffffff81063f2a>] __might_sleep+0xca/0xf0 [ 38.352606] [<ffffffff81655b16>] mutex_lock+0x26/0x50 [ 38.352610] [<ffffffff8153aaf0>] ? trace_napi_poll_hit+0xd0/0xd0 [ 38.352616] [<ffffffff810b72d9>] tracepoint_probe_register+0x29/0x90 [ 38.352621] [<ffffffff8153a585>] set_all_monitor_traces+0x105/0x170 [ 38.352625] [<ffffffff8153a8ca>] net_dm_cmd_trace+0x2a/0x40 [ 38.352630] [<ffffffff8154a81a>] genl_rcv_msg+0x21a/0x2b0 [ 38.352636] [<ffffffff810f8029>] ? zone_statistics+0x99/0xc0 [ 38.352640] [<ffffffff8154a600>] ? genl_rcv+0x30/0x30 [ 38.352645] [<ffffffff8154a059>] netlink_rcv_skb+0xa9/0xd0 [ 38.352649] [<ffffffff8154a5f0>] genl_rcv+0x20/0x30 [ 38.352653] [<ffffffff81549a7e>] netlink_unicast+0x1ae/0x1f0 [ 38.352658] [<ffffffff81549d76>] netlink_sendmsg+0x2b6/0x310 [ 38.352663] [<ffffffff8150824f>] sock_sendmsg+0x10f/0x130 [ 38.352668] [<ffffffff8150abe0>] ? move_addr_to_kernel+0x60/0xb0 [ 38.352673] [<ffffffff81515f04>] ? verify_iovec+0x64/0xe0 [ 38.352677] [<ffffffff81509c46>] __sys_sendmsg+0x386/0x390 [ 38.352682] [<ffffffff810ffaf9>] ? handle_mm_fault+0x139/0x210 [ 38.352687] [<ffffffff8165b5bc>] ? do_page_fault+0x1ec/0x4f0 [ 38.352693] [<ffffffff8106ba4d>] ? set_next_entity+0x9d/0xb0 [ 38.352699] [<ffffffff81310b49>] ? tty_ldisc_deref+0x9/0x10 [ 38.352703] [<ffffffff8106d363>] ? pick_next_task_fair+0x63/0x140 [ 38.352708] [<ffffffff8150b8d4>] sys_sendmsg+0x44/0x80 [ 38.352713] [<ffffffff8165f8e2>] system_call_fastpath+0x16/0x1b It stems from holding a spinlock (trace_state_lock) while attempting to register or unregister tracepoint hooks, making in_atomic() true in this context, leading to the warning when the tracepoint calls might_sleep() while its taking a mutex. Since we only use the trace_state_lock to prevent trace protocol state races, as well as hardware stat list updates on an rcu write side, we can just convert the spinlock to a mutex to avoid this problem. Signed-off-by: Neil Horman <nhorman@tuxdriver.com> Reported-by: Eric Dumazet <eric.dumazet@gmail.com> CC: David Miller <davem@davemloft.net> Acked-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-04-27 10:11:48 +00:00
mutex_unlock(&trace_state_mutex);
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);
case NET_DM_CMD_STOP:
return set_all_monitor_traces(TRACE_OFF);
}
return -ENOTSUPP;
}
static int dropmon_net_event(struct notifier_block *ev_block,
unsigned long event, void *ptr)
{
struct net_device *dev = netdev_notifier_info_to_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;
drop_monitor: fix sleeping in invalid context warning Eric Dumazet pointed out this warning in the drop_monitor protocol to me: [ 38.352571] BUG: sleeping function called from invalid context at kernel/mutex.c:85 [ 38.352576] in_atomic(): 1, irqs_disabled(): 0, pid: 4415, name: dropwatch [ 38.352580] Pid: 4415, comm: dropwatch Not tainted 3.4.0-rc2+ #71 [ 38.352582] Call Trace: [ 38.352592] [<ffffffff8153aaf0>] ? trace_napi_poll_hit+0xd0/0xd0 [ 38.352599] [<ffffffff81063f2a>] __might_sleep+0xca/0xf0 [ 38.352606] [<ffffffff81655b16>] mutex_lock+0x26/0x50 [ 38.352610] [<ffffffff8153aaf0>] ? trace_napi_poll_hit+0xd0/0xd0 [ 38.352616] [<ffffffff810b72d9>] tracepoint_probe_register+0x29/0x90 [ 38.352621] [<ffffffff8153a585>] set_all_monitor_traces+0x105/0x170 [ 38.352625] [<ffffffff8153a8ca>] net_dm_cmd_trace+0x2a/0x40 [ 38.352630] [<ffffffff8154a81a>] genl_rcv_msg+0x21a/0x2b0 [ 38.352636] [<ffffffff810f8029>] ? zone_statistics+0x99/0xc0 [ 38.352640] [<ffffffff8154a600>] ? genl_rcv+0x30/0x30 [ 38.352645] [<ffffffff8154a059>] netlink_rcv_skb+0xa9/0xd0 [ 38.352649] [<ffffffff8154a5f0>] genl_rcv+0x20/0x30 [ 38.352653] [<ffffffff81549a7e>] netlink_unicast+0x1ae/0x1f0 [ 38.352658] [<ffffffff81549d76>] netlink_sendmsg+0x2b6/0x310 [ 38.352663] [<ffffffff8150824f>] sock_sendmsg+0x10f/0x130 [ 38.352668] [<ffffffff8150abe0>] ? move_addr_to_kernel+0x60/0xb0 [ 38.352673] [<ffffffff81515f04>] ? verify_iovec+0x64/0xe0 [ 38.352677] [<ffffffff81509c46>] __sys_sendmsg+0x386/0x390 [ 38.352682] [<ffffffff810ffaf9>] ? handle_mm_fault+0x139/0x210 [ 38.352687] [<ffffffff8165b5bc>] ? do_page_fault+0x1ec/0x4f0 [ 38.352693] [<ffffffff8106ba4d>] ? set_next_entity+0x9d/0xb0 [ 38.352699] [<ffffffff81310b49>] ? tty_ldisc_deref+0x9/0x10 [ 38.352703] [<ffffffff8106d363>] ? pick_next_task_fair+0x63/0x140 [ 38.352708] [<ffffffff8150b8d4>] sys_sendmsg+0x44/0x80 [ 38.352713] [<ffffffff8165f8e2>] system_call_fastpath+0x16/0x1b It stems from holding a spinlock (trace_state_lock) while attempting to register or unregister tracepoint hooks, making in_atomic() true in this context, leading to the warning when the tracepoint calls might_sleep() while its taking a mutex. Since we only use the trace_state_lock to prevent trace protocol state races, as well as hardware stat list updates on an rcu write side, we can just convert the spinlock to a mutex to avoid this problem. Signed-off-by: Neil Horman <nhorman@tuxdriver.com> Reported-by: Eric Dumazet <eric.dumazet@gmail.com> CC: David Miller <davem@davemloft.net> Acked-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-04-27 10:11:48 +00:00
mutex_lock(&trace_state_mutex);
list_add_rcu(&new_stat->list, &hw_stats_list);
drop_monitor: fix sleeping in invalid context warning Eric Dumazet pointed out this warning in the drop_monitor protocol to me: [ 38.352571] BUG: sleeping function called from invalid context at kernel/mutex.c:85 [ 38.352576] in_atomic(): 1, irqs_disabled(): 0, pid: 4415, name: dropwatch [ 38.352580] Pid: 4415, comm: dropwatch Not tainted 3.4.0-rc2+ #71 [ 38.352582] Call Trace: [ 38.352592] [<ffffffff8153aaf0>] ? trace_napi_poll_hit+0xd0/0xd0 [ 38.352599] [<ffffffff81063f2a>] __might_sleep+0xca/0xf0 [ 38.352606] [<ffffffff81655b16>] mutex_lock+0x26/0x50 [ 38.352610] [<ffffffff8153aaf0>] ? trace_napi_poll_hit+0xd0/0xd0 [ 38.352616] [<ffffffff810b72d9>] tracepoint_probe_register+0x29/0x90 [ 38.352621] [<ffffffff8153a585>] set_all_monitor_traces+0x105/0x170 [ 38.352625] [<ffffffff8153a8ca>] net_dm_cmd_trace+0x2a/0x40 [ 38.352630] [<ffffffff8154a81a>] genl_rcv_msg+0x21a/0x2b0 [ 38.352636] [<ffffffff810f8029>] ? zone_statistics+0x99/0xc0 [ 38.352640] [<ffffffff8154a600>] ? genl_rcv+0x30/0x30 [ 38.352645] [<ffffffff8154a059>] netlink_rcv_skb+0xa9/0xd0 [ 38.352649] [<ffffffff8154a5f0>] genl_rcv+0x20/0x30 [ 38.352653] [<ffffffff81549a7e>] netlink_unicast+0x1ae/0x1f0 [ 38.352658] [<ffffffff81549d76>] netlink_sendmsg+0x2b6/0x310 [ 38.352663] [<ffffffff8150824f>] sock_sendmsg+0x10f/0x130 [ 38.352668] [<ffffffff8150abe0>] ? move_addr_to_kernel+0x60/0xb0 [ 38.352673] [<ffffffff81515f04>] ? verify_iovec+0x64/0xe0 [ 38.352677] [<ffffffff81509c46>] __sys_sendmsg+0x386/0x390 [ 38.352682] [<ffffffff810ffaf9>] ? handle_mm_fault+0x139/0x210 [ 38.352687] [<ffffffff8165b5bc>] ? do_page_fault+0x1ec/0x4f0 [ 38.352693] [<ffffffff8106ba4d>] ? set_next_entity+0x9d/0xb0 [ 38.352699] [<ffffffff81310b49>] ? tty_ldisc_deref+0x9/0x10 [ 38.352703] [<ffffffff8106d363>] ? pick_next_task_fair+0x63/0x140 [ 38.352708] [<ffffffff8150b8d4>] sys_sendmsg+0x44/0x80 [ 38.352713] [<ffffffff8165f8e2>] system_call_fastpath+0x16/0x1b It stems from holding a spinlock (trace_state_lock) while attempting to register or unregister tracepoint hooks, making in_atomic() true in this context, leading to the warning when the tracepoint calls might_sleep() while its taking a mutex. Since we only use the trace_state_lock to prevent trace protocol state races, as well as hardware stat list updates on an rcu write side, we can just convert the spinlock to a mutex to avoid this problem. Signed-off-by: Neil Horman <nhorman@tuxdriver.com> Reported-by: Eric Dumazet <eric.dumazet@gmail.com> CC: David Miller <davem@davemloft.net> Acked-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-04-27 10:11:48 +00:00
mutex_unlock(&trace_state_mutex);
break;
case NETDEV_UNREGISTER:
drop_monitor: fix sleeping in invalid context warning Eric Dumazet pointed out this warning in the drop_monitor protocol to me: [ 38.352571] BUG: sleeping function called from invalid context at kernel/mutex.c:85 [ 38.352576] in_atomic(): 1, irqs_disabled(): 0, pid: 4415, name: dropwatch [ 38.352580] Pid: 4415, comm: dropwatch Not tainted 3.4.0-rc2+ #71 [ 38.352582] Call Trace: [ 38.352592] [<ffffffff8153aaf0>] ? trace_napi_poll_hit+0xd0/0xd0 [ 38.352599] [<ffffffff81063f2a>] __might_sleep+0xca/0xf0 [ 38.352606] [<ffffffff81655b16>] mutex_lock+0x26/0x50 [ 38.352610] [<ffffffff8153aaf0>] ? trace_napi_poll_hit+0xd0/0xd0 [ 38.352616] [<ffffffff810b72d9>] tracepoint_probe_register+0x29/0x90 [ 38.352621] [<ffffffff8153a585>] set_all_monitor_traces+0x105/0x170 [ 38.352625] [<ffffffff8153a8ca>] net_dm_cmd_trace+0x2a/0x40 [ 38.352630] [<ffffffff8154a81a>] genl_rcv_msg+0x21a/0x2b0 [ 38.352636] [<ffffffff810f8029>] ? zone_statistics+0x99/0xc0 [ 38.352640] [<ffffffff8154a600>] ? genl_rcv+0x30/0x30 [ 38.352645] [<ffffffff8154a059>] netlink_rcv_skb+0xa9/0xd0 [ 38.352649] [<ffffffff8154a5f0>] genl_rcv+0x20/0x30 [ 38.352653] [<ffffffff81549a7e>] netlink_unicast+0x1ae/0x1f0 [ 38.352658] [<ffffffff81549d76>] netlink_sendmsg+0x2b6/0x310 [ 38.352663] [<ffffffff8150824f>] sock_sendmsg+0x10f/0x130 [ 38.352668] [<ffffffff8150abe0>] ? move_addr_to_kernel+0x60/0xb0 [ 38.352673] [<ffffffff81515f04>] ? verify_iovec+0x64/0xe0 [ 38.352677] [<ffffffff81509c46>] __sys_sendmsg+0x386/0x390 [ 38.352682] [<ffffffff810ffaf9>] ? handle_mm_fault+0x139/0x210 [ 38.352687] [<ffffffff8165b5bc>] ? do_page_fault+0x1ec/0x4f0 [ 38.352693] [<ffffffff8106ba4d>] ? set_next_entity+0x9d/0xb0 [ 38.352699] [<ffffffff81310b49>] ? tty_ldisc_deref+0x9/0x10 [ 38.352703] [<ffffffff8106d363>] ? pick_next_task_fair+0x63/0x140 [ 38.352708] [<ffffffff8150b8d4>] sys_sendmsg+0x44/0x80 [ 38.352713] [<ffffffff8165f8e2>] system_call_fastpath+0x16/0x1b It stems from holding a spinlock (trace_state_lock) while attempting to register or unregister tracepoint hooks, making in_atomic() true in this context, leading to the warning when the tracepoint calls might_sleep() while its taking a mutex. Since we only use the trace_state_lock to prevent trace protocol state races, as well as hardware stat list updates on an rcu write side, we can just convert the spinlock to a mutex to avoid this problem. Signed-off-by: Neil Horman <nhorman@tuxdriver.com> Reported-by: Eric Dumazet <eric.dumazet@gmail.com> CC: David Miller <davem@davemloft.net> Acked-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-04-27 10:11:48 +00:00
mutex_lock(&trace_state_mutex);
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);
kfree_rcu(new_stat, rcu);
break;
}
}
}
drop_monitor: fix sleeping in invalid context warning Eric Dumazet pointed out this warning in the drop_monitor protocol to me: [ 38.352571] BUG: sleeping function called from invalid context at kernel/mutex.c:85 [ 38.352576] in_atomic(): 1, irqs_disabled(): 0, pid: 4415, name: dropwatch [ 38.352580] Pid: 4415, comm: dropwatch Not tainted 3.4.0-rc2+ #71 [ 38.352582] Call Trace: [ 38.352592] [<ffffffff8153aaf0>] ? trace_napi_poll_hit+0xd0/0xd0 [ 38.352599] [<ffffffff81063f2a>] __might_sleep+0xca/0xf0 [ 38.352606] [<ffffffff81655b16>] mutex_lock+0x26/0x50 [ 38.352610] [<ffffffff8153aaf0>] ? trace_napi_poll_hit+0xd0/0xd0 [ 38.352616] [<ffffffff810b72d9>] tracepoint_probe_register+0x29/0x90 [ 38.352621] [<ffffffff8153a585>] set_all_monitor_traces+0x105/0x170 [ 38.352625] [<ffffffff8153a8ca>] net_dm_cmd_trace+0x2a/0x40 [ 38.352630] [<ffffffff8154a81a>] genl_rcv_msg+0x21a/0x2b0 [ 38.352636] [<ffffffff810f8029>] ? zone_statistics+0x99/0xc0 [ 38.352640] [<ffffffff8154a600>] ? genl_rcv+0x30/0x30 [ 38.352645] [<ffffffff8154a059>] netlink_rcv_skb+0xa9/0xd0 [ 38.352649] [<ffffffff8154a5f0>] genl_rcv+0x20/0x30 [ 38.352653] [<ffffffff81549a7e>] netlink_unicast+0x1ae/0x1f0 [ 38.352658] [<ffffffff81549d76>] netlink_sendmsg+0x2b6/0x310 [ 38.352663] [<ffffffff8150824f>] sock_sendmsg+0x10f/0x130 [ 38.352668] [<ffffffff8150abe0>] ? move_addr_to_kernel+0x60/0xb0 [ 38.352673] [<ffffffff81515f04>] ? verify_iovec+0x64/0xe0 [ 38.352677] [<ffffffff81509c46>] __sys_sendmsg+0x386/0x390 [ 38.352682] [<ffffffff810ffaf9>] ? handle_mm_fault+0x139/0x210 [ 38.352687] [<ffffffff8165b5bc>] ? do_page_fault+0x1ec/0x4f0 [ 38.352693] [<ffffffff8106ba4d>] ? set_next_entity+0x9d/0xb0 [ 38.352699] [<ffffffff81310b49>] ? tty_ldisc_deref+0x9/0x10 [ 38.352703] [<ffffffff8106d363>] ? pick_next_task_fair+0x63/0x140 [ 38.352708] [<ffffffff8150b8d4>] sys_sendmsg+0x44/0x80 [ 38.352713] [<ffffffff8165f8e2>] system_call_fastpath+0x16/0x1b It stems from holding a spinlock (trace_state_lock) while attempting to register or unregister tracepoint hooks, making in_atomic() true in this context, leading to the warning when the tracepoint calls might_sleep() while its taking a mutex. Since we only use the trace_state_lock to prevent trace protocol state races, as well as hardware stat list updates on an rcu write side, we can just convert the spinlock to a mutex to avoid this problem. Signed-off-by: Neil Horman <nhorman@tuxdriver.com> Reported-by: Eric Dumazet <eric.dumazet@gmail.com> CC: David Miller <davem@davemloft.net> Acked-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-04-27 10:11:48 +00:00
mutex_unlock(&trace_state_mutex);
break;
}
out:
return NOTIFY_DONE;
}
static const 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 genl_family net_drop_monitor_family __ro_after_init = {
.hdrsize = 0,
.name = "NET_DM",
.version = 2,
.module = THIS_MODULE,
.ops = dropmon_ops,
.n_ops = ARRAY_SIZE(dropmon_ops),
.mcgrps = dropmon_mcgrps,
.n_mcgrps = ARRAY_SIZE(dropmon_mcgrps),
};
static struct notifier_block dropmon_net_notifier = {
.notifier_call = dropmon_net_event
};
static int __init init_net_drop_monitor(void)
{
struct per_cpu_dm_data *data;
int cpu, rc;
pr_info("Initializing network drop monitor service\n");
if (sizeof(void *) > 8) {
pr_err("Unable to store program counters on this arch, Drop monitor failed\n");
return -ENOSPC;
}
rc = genl_register_family(&net_drop_monitor_family);
if (rc) {
pr_err("Could not create drop monitor netlink family\n");
return rc;
}
WARN_ON(net_drop_monitor_family.mcgrp_offset != NET_DM_GRP_ALERT);
rc = register_netdevice_notifier(&dropmon_net_notifier);
if (rc < 0) {
pr_crit("Failed to register netdevice notifier\n");
goto out_unreg;
}
rc = 0;
for_each_possible_cpu(cpu) {
data = &per_cpu(dm_cpu_data, cpu);
INIT_WORK(&data->dm_alert_work, send_dm_alert);
setup_timer(&data->send_timer, sched_send_work,
(unsigned long)data);
drop_monitor: dont sleep in atomic context drop_monitor calls several sleeping functions while in atomic context. BUG: sleeping function called from invalid context at mm/slub.c:943 in_atomic(): 1, irqs_disabled(): 0, pid: 2103, name: kworker/0:2 Pid: 2103, comm: kworker/0:2 Not tainted 3.5.0-rc1+ #55 Call Trace: [<ffffffff810697ca>] __might_sleep+0xca/0xf0 [<ffffffff811345a3>] kmem_cache_alloc_node+0x1b3/0x1c0 [<ffffffff8105578c>] ? queue_delayed_work_on+0x11c/0x130 [<ffffffff815343fb>] __alloc_skb+0x4b/0x230 [<ffffffffa00b0360>] ? reset_per_cpu_data+0x160/0x160 [drop_monitor] [<ffffffffa00b022f>] reset_per_cpu_data+0x2f/0x160 [drop_monitor] [<ffffffffa00b03ab>] send_dm_alert+0x4b/0xb0 [drop_monitor] [<ffffffff810568e0>] process_one_work+0x130/0x4c0 [<ffffffff81058249>] worker_thread+0x159/0x360 [<ffffffff810580f0>] ? manage_workers.isra.27+0x240/0x240 [<ffffffff8105d403>] kthread+0x93/0xa0 [<ffffffff816be6d4>] kernel_thread_helper+0x4/0x10 [<ffffffff8105d370>] ? kthread_freezable_should_stop+0x80/0x80 [<ffffffff816be6d0>] ? gs_change+0xb/0xb Rework the logic to call the sleeping functions in right context. Use standard timer/workqueue api to let system chose any cpu to perform the allocation and netlink send. Also avoid a loop if reset_per_cpu_data() cannot allocate memory : use mod_timer() to wait 1/10 second before next try. Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Neil Horman <nhorman@tuxdriver.com> Reviewed-by: Neil Horman <nhorman@tuxdriver.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-06-04 00:18:19 +00:00
spin_lock_init(&data->lock);
reset_per_cpu_data(data);
}
goto out;
out_unreg:
genl_unregister_family(&net_drop_monitor_family);
out:
return rc;
}
static void exit_net_drop_monitor(void)
{
struct per_cpu_dm_data *data;
int cpu;
BUG_ON(unregister_netdevice_notifier(&dropmon_net_notifier));
/*
* Because of the module_get/put we do in the trace state change path
* we are guarnateed not to have any current users when we get here
* all we need to do is make sure that we don't have any running timers
* or pending schedule calls
*/
for_each_possible_cpu(cpu) {
data = &per_cpu(dm_cpu_data, cpu);
del_timer_sync(&data->send_timer);
cancel_work_sync(&data->dm_alert_work);
/*
* At this point, we should have exclusive access
* to this struct and can free the skb inside it
*/
kfree_skb(data->skb);
}
BUG_ON(genl_unregister_family(&net_drop_monitor_family));
}
module_init(init_net_drop_monitor);
module_exit(exit_net_drop_monitor);
MODULE_LICENSE("GPL v2");
MODULE_AUTHOR("Neil Horman <nhorman@tuxdriver.com>");
MODULE_ALIAS_GENL_FAMILY("NET_DM");