Gitweb:
http://git.kernel.org/git/?p=linux/kernel/git/torvalds/linux-2.6.git;a=commit;h=beb659bd8c9f2ccc8195779383f71088f936bf6e
Commit: beb659bd8c9f2ccc8195779383f71088f936bf6e
Parent: 42a73808ed4f30b739eb52bcbb33a02fe62ceef5
Author: Eric Dumazet <[EMAIL PROTECTED]>
AuthorDate: Mon Nov 19 22:43:37 2007 -0800
Committer: David S. Miller <[EMAIL PROTECTED]>
CommitDate: Mon Jan 28 14:54:33 2008 -0800
[PATCH] IPV4 : Move ip route cache flush (secret_rebuild) from softirq to
workqueue
Every 600 seconds (ip_rt_secret_interval), a softirq flush of the
whole ip route cache is triggered. On loaded machines, this can starve
softirq for many seconds and can eventually crash.
This patch moves this flush to a workqueue context, using the worker
we intoduced in commit 39c90ece7565f5c47110c2fa77409d7a9478bd5b (IPV4:
Convert rt_check_expire() from softirq processing to workqueue.)
Also, immediate flushes (echo 0 >/proc/sys/net/ipv4/route/flush) are
using rt_do_flush() helper function, wich take attention to
rescheduling.
Next step will be to handle delayed flushes
("echo -1 >/proc/sys/net/ipv4/route/flush" or "ip route flush cache")
Signed-off-by: Eric Dumazet <[EMAIL PROTECTED]>
Signed-off-by: David S. Miller <[EMAIL PROTECTED]>
---
net/ipv4/route.c | 83 ++++++++++++++++++++++++++++++++++++++---------------
1 files changed, 59 insertions(+), 24 deletions(-)
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index e4b6fb4..fcae074 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -133,13 +133,14 @@ static int ip_rt_mtu_expires = 10 * 60 * HZ;
static int ip_rt_min_pmtu = 512 + 20 + 20;
static int ip_rt_min_advmss = 256;
static int ip_rt_secret_interval = 10 * 60 * HZ;
+static int ip_rt_flush_expected;
static unsigned long rt_deadline;
#define RTprint(a...) printk(KERN_DEBUG a)
static struct timer_list rt_flush_timer;
-static void rt_check_expire(struct work_struct *work);
-static DECLARE_DELAYED_WORK(expires_work, rt_check_expire);
+static void rt_worker_func(struct work_struct *work);
+static DECLARE_DELAYED_WORK(expires_work, rt_worker_func);
static struct timer_list rt_secret_timer;
/*
@@ -561,7 +562,36 @@ static inline int compare_keys(struct flowi *fl1, struct
flowi *fl2)
(fl1->iif ^ fl2->iif)) == 0;
}
-static void rt_check_expire(struct work_struct *work)
+/*
+ * Perform a full scan of hash table and free all entries.
+ * Can be called by a softirq or a process.
+ * In the later case, we want to be reschedule if necessary
+ */
+static void rt_do_flush(int process_context)
+{
+ unsigned int i;
+ struct rtable *rth, *next;
+
+ for (i = 0; i <= rt_hash_mask; i++) {
+ if (process_context && need_resched())
+ cond_resched();
+ rth = rt_hash_table[i].chain;
+ if (!rth)
+ continue;
+
+ spin_lock_bh(rt_hash_lock_addr(i));
+ rth = rt_hash_table[i].chain;
+ rt_hash_table[i].chain = NULL;
+ spin_unlock_bh(rt_hash_lock_addr(i));
+
+ for (; rth; rth = next) {
+ next = rth->u.dst.rt_next;
+ rt_free(rth);
+ }
+ }
+}
+
+static void rt_check_expire(void)
{
static unsigned int rover;
unsigned int i = rover, goal;
@@ -607,33 +637,33 @@ static void rt_check_expire(struct work_struct *work)
spin_unlock_bh(rt_hash_lock_addr(i));
}
rover = i;
+}
+
+/*
+ * rt_worker_func() is run in process context.
+ * If a whole flush was scheduled, it is done.
+ * Else, we call rt_check_expire() to scan part of the hash table
+ */
+static void rt_worker_func(struct work_struct *work)
+{
+ if (ip_rt_flush_expected) {
+ ip_rt_flush_expected = 0;
+ rt_do_flush(1);
+ } else
+ rt_check_expire();
schedule_delayed_work(&expires_work, ip_rt_gc_interval);
}
/* This can run from both BH and non-BH contexts, the latter
* in the case of a forced flush event.
*/
-static void rt_run_flush(unsigned long dummy)
+static void rt_run_flush(unsigned long process_context)
{
- int i;
- struct rtable *rth, *next;
-
rt_deadline = 0;
get_random_bytes(&rt_hash_rnd, 4);
- for (i = rt_hash_mask; i >= 0; i--) {
- spin_lock_bh(rt_hash_lock_addr(i));
- rth = rt_hash_table[i].chain;
- if (rth)
- rt_hash_table[i].chain = NULL;
- spin_unlock_bh(rt_hash_lock_addr(i));
-
- for (; rth; rth = next) {
- next = rth->u.dst.rt_next;
- rt_free(rth);
- }
- }
+ rt_do_flush(process_context);
}
static DEFINE_SPINLOCK(rt_flush_lock);
@@ -667,7 +697,7 @@ void rt_cache_flush(int delay)
if (delay <= 0) {
spin_unlock_bh(&rt_flush_lock);
- rt_run_flush(0);
+ rt_run_flush(user_mode);
return;
}
@@ -678,12 +708,17 @@ void rt_cache_flush(int delay)
spin_unlock_bh(&rt_flush_lock);
}
+/*
+ * We change rt_hash_rnd and ask next rt_worker_func() invocation
+ * to perform a flush in process context
+ */
static void rt_secret_rebuild(unsigned long dummy)
{
- unsigned long now = jiffies;
-
- rt_cache_flush(0);
- mod_timer(&rt_secret_timer, now + ip_rt_secret_interval);
+ get_random_bytes(&rt_hash_rnd, 4);
+ ip_rt_flush_expected = 1;
+ cancel_delayed_work(&expires_work);
+ schedule_delayed_work(&expires_work, HZ/10);
+ mod_timer(&rt_secret_timer, jiffies + ip_rt_secret_interval);
}
/*
-
To unsubscribe from this list: send the line "unsubscribe git-commits-head" in
the body of a message to [EMAIL PROTECTED]
More majordomo info at http://vger.kernel.org/majordomo-info.html
