If local fragmentation is allowed, then ip_select_ident() and
ip_select_ident_more() need to generate unique IDs to ensure
correct defragmentation on the peer.
For example, if IPsec (tunnel mode) has to encrypt large skbs
that have local_df bit set, then all IP fragments that belonged
to different ESP datagrams would have used the same identificator.
If one of these IP fragments would get lost or reordered, then
peer could possibly stitch together wrong IP fragments that did
not belong to the same datagram. This would lead to a packet loss
or data corruption.
Signed-off-by: Ansis Atteka <aatteka@nicira.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Pull workqueue changes from Tejun Heo:
"This is workqueue updates for v3.7-rc1. A lot of activities this
round including considerable API and behavior cleanups.
* delayed_work combines a timer and a work item. The handling of the
timer part has always been a bit clunky leading to confusing
cancelation API with weird corner-case behaviors. delayed_work is
updated to use new IRQ safe timer and cancelation now works as
expected.
* Another deficiency of delayed_work was lack of the counterpart of
mod_timer() which led to cancel+queue combinations or open-coded
timer+work usages. mod_delayed_work[_on]() are added.
These two delayed_work changes make delayed_work provide interface
and behave like timer which is executed with process context.
* A work item could be executed concurrently on multiple CPUs, which
is rather unintuitive and made flush_work() behavior confusing and
half-broken under certain circumstances. This problem doesn't
exist for non-reentrant workqueues. While non-reentrancy check
isn't free, the overhead is incurred only when a work item bounces
across different CPUs and even in simulated pathological scenario
the overhead isn't too high.
All workqueues are made non-reentrant. This removes the
distinction between flush_[delayed_]work() and
flush_[delayed_]_work_sync(). The former is now as strong as the
latter and the specified work item is guaranteed to have finished
execution of any previous queueing on return.
* In addition to the various bug fixes, Lai redid and simplified CPU
hotplug handling significantly.
* Joonsoo introduced system_highpri_wq and used it during CPU
hotplug.
There are two merge commits - one to pull in IRQ safe timer from
tip/timers/core and the other to pull in CPU hotplug fixes from
wq/for-3.6-fixes as Lai's hotplug restructuring depended on them."
Fixed a number of trivial conflicts, but the more interesting conflicts
were silent ones where the deprecated interfaces had been used by new
code in the merge window, and thus didn't cause any real data conflicts.
Tejun pointed out a few of them, I fixed a couple more.
* 'for-3.7' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/wq: (46 commits)
workqueue: remove spurious WARN_ON_ONCE(in_irq()) from try_to_grab_pending()
workqueue: use cwq_set_max_active() helper for workqueue_set_max_active()
workqueue: introduce cwq_set_max_active() helper for thaw_workqueues()
workqueue: remove @delayed from cwq_dec_nr_in_flight()
workqueue: fix possible stall on try_to_grab_pending() of a delayed work item
workqueue: use hotcpu_notifier() for workqueue_cpu_down_callback()
workqueue: use __cpuinit instead of __devinit for cpu callbacks
workqueue: rename manager_mutex to assoc_mutex
workqueue: WORKER_REBIND is no longer necessary for idle rebinding
workqueue: WORKER_REBIND is no longer necessary for busy rebinding
workqueue: reimplement idle worker rebinding
workqueue: deprecate __cancel_delayed_work()
workqueue: reimplement cancel_delayed_work() using try_to_grab_pending()
workqueue: use mod_delayed_work() instead of __cancel + queue
workqueue: use irqsafe timer for delayed_work
workqueue: clean up delayed_work initializers and add missing one
workqueue: make deferrable delayed_work initializer names consistent
workqueue: cosmetic whitespace updates for macro definitions
workqueue: deprecate system_nrt[_freezable]_wq
workqueue: deprecate flush[_delayed]_work_sync()
...
When jiffies wraps around (for example, 5 minutes after the boot, see
INITIAL_JIFFIES) and peer has just been created, now - peer->rate_last can be
< XRLIM_BURST_FACTOR * timeout, so token is not set to the maximum value, thus
some icmp packets can be unexpectedly dropped.
Fix this case by initializing last_rate to 60 seconds in the past.
Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Initalizers for deferrable delayed_work are confused.
* __DEFERRED_WORK_INITIALIZER()
* DECLARE_DEFERRED_WORK()
* INIT_DELAYED_WORK_DEFERRABLE()
Rename them to
* __DEFERRABLE_WORK_INITIALIZER()
* DECLARE_DEFERRABLE_WORK()
* INIT_DEFERRABLE_WORK()
This patch doesn't cause any functional changes.
Signed-off-by: Tejun Heo <tj@kernel.org>
No need to use cmpxchg() in inetpeer_invalidate_tree() since we hold
base lock.
Also use correct rcu annotations to remove sparse errors
(CONFIG_SPARSE_RCU_POINTER=y)
net/ipv4/inetpeer.c:144:19: error: incompatible types in comparison
expression (different address spaces)
net/ipv4/inetpeer.c:149:20: error: incompatible types in comparison
expression (different address spaces)
net/ipv4/inetpeer.c:595:10: error: incompatible types in comparison
expression (different address spaces)
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Steffen Klassert <steffen.klassert@secunet.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This implementation can deal with having many inetpeer roots, which is
a necessary prerequisite for per-FIB table rooted peer tables.
Each family (AF_INET, AF_INET6) has a sequence number which we bump
when we get a family invalidation request.
Each peer lookup cheaply checks whether the flush sequence of the
root we are using is out of date, and if so flushes it and updates
the sequence number.
Signed-off-by: David S. Miller <davem@davemloft.net>
We only need one interface for this operation, since we always know
which inetpeer root we want to flush.
Signed-off-by: David S. Miller <davem@davemloft.net>
now inetpeer doesn't support namespace,the information will
be leaking across namespace.
this patch move the global vars v4_peers and v6_peers to
netns_ipv4 and netns_ipv6 as a field peers.
add struct pernet_operations inetpeer_ops to initial pernet
inetpeer data.
and change family_to_base and inet_getpeer to support namespace.
Signed-off-by: Gao feng <gaofeng@cn.fujitsu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
commit 5faa5df1fa (inetpeer: Invalidate the inetpeer tree along with
the routing cache) added a race :
Before freeing an inetpeer, we must respect a RCU grace period, and make
sure no user will attempt to increase refcnt.
inetpeer_invalidate_tree() waits for a RCU grace period before inserting
inetpeer tree into gc_list and waking the worker. At that time, no
concurrent lookup can find a inetpeer in this tree.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Steffen Klassert <steffen.klassert@secunet.com>
Acked-by: Steffen Klassert <steffen.klassert@secunet.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
As we invalidate the inetpeer tree along with the routing cache now,
we don't need a genid to reset the redirect handling when the routing
cache is flushed.
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
We initialize the routing metrics with the values cached on the
inetpeer in rt_init_metrics(). So if we have the metrics cached on the
inetpeer, we ignore the user configured fib_metrics.
To fix this issue, we replace the old tree with a fresh initialized
inet_peer_base. The old tree is removed later with a delayed work queue.
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
kmemcheck complains that ->redirect_genid doesn't get initialized.
Presumably it should be set to zero.
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
make C=2 CF="-D__CHECK_ENDIAN__" M=net
And fix flowi4_init_output() prototype for sport
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Computers have become a lot faster since we compromised on the
partial MD4 hash which we use currently for performance reasons.
MD5 is a much safer choice, and is inline with both RFC1948 and
other ISS generators (OpenBSD, Solaris, etc.)
Furthermore, only having 24-bits of the sequence number be truly
unpredictable is a very serious limitation. So the periodic
regeneration and 8-bit counter have been removed. We compute and
use a full 32-bit sequence number.
For ipv6, DCCP was found to use a 32-bit truncated initial sequence
number (it needs 43-bits) and that is fixed here as well.
Reported-by: Dan Kaminsky <dan@doxpara.com>
Tested-by: Willy Tarreau <w@1wt.eu>
Signed-off-by: David S. Miller <davem@davemloft.net>
IPv6 fragment identification generation is way beyond what we use for
IPv4 : It uses a single generator. Its not scalable and allows DOS
attacks.
Now inetpeer is IPv6 aware, we can use it to provide a more secure and
scalable frag ident generator (per destination, instead of system wide)
This patch :
1) defines a new secure_ipv6_id() helper
2) extends inet_getid() to provide 32bit results
3) extends ipv6_select_ident() with a new dest parameter
Reported-by: Fernando Gont <fernando@gont.com.ar>
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
We currently can free inetpeer entries too early :
[ 782.636674] WARNING: kmemcheck: Caught 32-bit read from uninitialized memory (f130f44c)
[ 782.636677] 1f7b13c100000000000000000000000002000000000000000000000000000000
[ 782.636686] i i i i u u u u i i i i u u u u i i i i u u u u u u u u u u u u
[ 782.636694] ^
[ 782.636696]
[ 782.636698] Pid: 4638, comm: ssh Not tainted 3.0.0-rc5+ #270 Hewlett-Packard HP Compaq 6005 Pro SFF PC/3047h
[ 782.636702] EIP: 0060:[<c13fefbb>] EFLAGS: 00010286 CPU: 0
[ 782.636707] EIP is at inet_getpeer+0x25b/0x5a0
[ 782.636709] EAX: 00000002 EBX: 00010080 ECX: f130f3c0 EDX: f0209d30
[ 782.636711] ESI: 0000bc87 EDI: 0000ea60 EBP: f0209ddc ESP: c173134c
[ 782.636712] DS: 007b ES: 007b FS: 00d8 GS: 0033 SS: 0068
[ 782.636714] CR0: 8005003b CR2: f0beca80 CR3: 30246000 CR4: 000006d0
[ 782.636716] DR0: 00000000 DR1: 00000000 DR2: 00000000 DR3: 00000000
[ 782.636717] DR6: ffff4ff0 DR7: 00000400
[ 782.636718] [<c13fbf76>] rt_set_nexthop.clone.45+0x56/0x220
[ 782.636722] [<c13fc449>] __ip_route_output_key+0x309/0x860
[ 782.636724] [<c141dc54>] tcp_v4_connect+0x124/0x450
[ 782.636728] [<c142ce43>] inet_stream_connect+0xa3/0x270
[ 782.636731] [<c13a8da1>] sys_connect+0xa1/0xb0
[ 782.636733] [<c13a99dd>] sys_socketcall+0x25d/0x2a0
[ 782.636736] [<c149deb8>] sysenter_do_call+0x12/0x28
[ 782.636738] [<ffffffff>] 0xffffffff
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Andi Kleen and Tim Chen reported huge contention on inetpeer
unused_peers.lock, on memcached workload on a 40 core machine, with
disabled route cache.
It appears we constantly flip peers refcnt between 0 and 1 values, and
we must insert/remove peers from unused_peers.list, holding a contended
spinlock.
Remove this list completely and perform a garbage collection on-the-fly,
at lookup time, using the expired nodes we met during the tree
traversal.
This removes a lot of code, makes locking more standard, and obsoletes
two sysctls (inet_peer_gc_mintime and inet_peer_gc_maxtime). This also
removes two pointers in inet_peer structure.
There is still a false sharing effect because refcnt is in first cache
line of object [were the links and keys used by lookups are located], we
might move it at the end of inet_peer structure to let this first cache
line mostly read by cpus.
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
CC: Andi Kleen <andi@firstfloor.org>
CC: Tim Chen <tim.c.chen@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Several crashes in cleanup_once() were reported in recent kernels.
Commit d6cc1d642d (inetpeer: various changes) added a race in
unlink_from_unused().
One way to avoid taking unused_peers.lock before doing the list_empty()
test is to catch 0->1 refcnt transitions, using full barrier atomic
operations variants (atomic_cmpxchg() and atomic_inc_return()) instead
of previous atomic_inc() and atomic_add_unless() variants.
We then call unlink_from_unused() only for the owner of the 0->1
transition.
Add a new atomic_add_unless_return() static helper
With help from Arun Sharma.
Refs: https://bugzilla.kernel.org/show_bug.cgi?id=32772
Reported-by: Arun Sharma <asharma@fb.com>
Reported-by: Maximilian Engelhardt <maxi@daemonizer.de>
Reported-by: Yann Dupont <Yann.Dupont@univ-nantes.fr>
Reported-by: Denys Fedoryshchenko <denys@visp.net.lb>
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
After commit 7b46ac4e77 (inetpeer: Don't disable BH for initial
fast RCU lookup.), we should use call_rcu() to wait proper RCU grace
period.
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
On current net-next-2.6, when Linux receives ICMP Type: 3, Code: 4
(Destination unreachable (Fragmentation needed)),
icmp_unreach
-> ip_rt_frag_needed
(peer->pmtu_expires is set here)
-> tcp_v4_err
-> do_pmtu_discovery
-> ip_rt_update_pmtu
(peer->pmtu_expires is already set,
so check_peer_pmtu is skipped.)
-> check_peer_pmtu
check_peer_pmtu is skipped and MTU is not updated.
To fix this, let check_peer_pmtu execute unconditionally.
And some minor fixes
1) Avoid potential peer->pmtu_expires set to be zero.
2) In check_peer_pmtu, argument of time_before is reversed.
3) check_peer_pmtu expects peer->pmtu_orig is initialized as zero,
but not initialized.
Signed-off-by: Hiroaki SHIMODA <shimoda.hiroaki@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
If modifications on other cpus are ok, then modifications to
the tree during lookup done by the local cpu are ok too.
Signed-off-by: David S. Miller <davem@davemloft.net>
David noticed :
------------------
Eric, I was profiling the non-routing-cache case and something that
stuck out is the case of calling inet_getpeer() with create==0.
If an entry is not found, we have to redo the lookup under a spinlock
to make certain that a concurrent writer rebalancing the tree does
not "hide" an existing entry from us.
This makes the case of a create==0 lookup for a not-present entry
really expensive. It is on the order of 600 cpu cycles on my
Niagara2.
I added a hack to not do the relookup under the lock when create==0
and it now costs less than 300 cycles.
This is now a pretty common operation with the way we handle COW'd
metrics, so I think it's definitely worth optimizing.
-----------------
One solution is to use a seqlock instead of a spinlock to protect struct
inet_peer_base.
After a failed avl tree lookup, we can easily detect if a writer did
some changes during our lookup. Taking the lock and redo the lookup is
only necessary in this case.
Note: Add one private rcu_deref_locked() macro to place in one spot the
access to spinlock included in seqlock.
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Validity of the cached PMTU information is indicated by it's
expiration value being non-zero, just as per dst->expires.
The scheme we will use is that we will remember the pre-ICMP value
held in the metrics or route entry, and then at expiration time
we will restore that value.
In this way PMTU expiration does not kill off the cached route as is
done currently.
Redirect information is permanent, or at least until another redirect
is received.
Signed-off-by: David S. Miller <davem@davemloft.net>
Future changes will add caching information, and some of
these new elements will be addresses.
Since the family is implicit via the ->daddr.family member,
replicating the family in ever address we store is entirely
redundant.
Signed-off-by: David S. Miller <davem@davemloft.net>
Like metrics, the ICMP rate limiting bits are cached state about
a destination. So move it into the inet_peer entries.
If an inet_peer cannot be bound (the reason is memory allocation
failure or similar), the policy is to allow.
Signed-off-by: David S. Miller <davem@davemloft.net>
Set the RTAX_LOCKED metric to INETPEER_METRICS_NEW (basically,
all ones) on fresh inetpeer entries.
This way code can determine if default metrics have been loaded
in from a routing table entry already.
Signed-off-by: David S. Miller <davem@davemloft.net>
Family was hard-coded to AF_INET but should be daddr->family.
This fixes crashes when unlinking ipv6 peer entries, since the
unlink code was looking up the base pointer properly.
Reported-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Instead of directly accessing "peer", change to code to
operate using a "struct inet_peer_base *" pointer.
This will facilitate the addition of a seperate tree for
ipv6 peer entries.
Signed-off-by: David S. Miller <davem@davemloft.net>
Adds __rcu annotations to inetpeer
(struct inet_peer)->avl_left
(struct inet_peer)->avl_right
This is a tedious cleanup, but removes one smp_wmb() from link_to_pool()
since we now use more self documenting rcu_assign_pointer().
Note the use of RCU_INIT_POINTER() instead of rcu_assign_pointer() in
all cases we dont need a memory barrier.
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Addition of rcu_head to struct inet_peer added 16bytes on 64bit arches.
Thats a bit unfortunate, since old size was exactly 64 bytes.
This can be solved, using an union between this rcu_head an four fields,
that are normally used only when a refcount is taken on inet_peer.
rcu_head is used only when refcnt=-1, right before structure freeing.
Add a inet_peer_refcheck() function to check this assertion for a while.
We can bring back SLAB_HWCACHE_ALIGN qualifier in kmem cache creation.
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Followup of commit aa1039e73c (inetpeer: RCU conversion)
Unused inet_peer entries have a null refcnt.
Using atomic_inc_not_zero() in rcu lookups is not going to work for
them, and slow path is taken.
Fix this using -1 marker instead of 0 for deleted entries.
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
inetpeer currently uses an AVL tree protected by an rwlock.
It's possible to make most lookups use RCU
1) Add a struct rcu_head to struct inet_peer
2) add a lookup_rcu_bh() helper to perform lockless and opportunistic
lookup. This is a normal function, not a macro like lookup().
3) Add a limit to number of links followed by lookup_rcu_bh(). This is
needed in case we fall in a loop.
4) add an smp_wmb() in link_to_pool() right before node insert.
5) make unlink_from_pool() use atomic_cmpxchg() to make sure it can take
last reference to an inet_peer, since lockless readers could increase
refcount, even while we hold peers.lock.
6) Delay struct inet_peer freeing after rcu grace period so that
lookup_rcu_bh() cannot crash.
7) inet_getpeer() first attempts lockless lookup.
Note this lookup can fail even if target is in AVL tree, but a
concurrent writer can let tree in a non correct form.
If this attemps fails, lock is taken a regular lookup is performed
again.
8) convert peers.lock from rwlock to a spinlock
9) Remove SLAB_HWCACHE_ALIGN when peer_cachep is created, because
rcu_head adds 16 bytes on 64bit arches, doubling effective size (64 ->
128 bytes)
In a future patch, this is probably possible to revert this part, if rcu
field is put in an union to share space with rid, ip_id_count, tcp_ts &
tcp_ts_stamp. These fields being manipulated only with refcnt > 0.
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Try to reduce cache line contentions in peer management, to reduce IP
defragmentation overhead.
- peer_fake_node is marked 'const' to make sure its not modified.
(tested with CONFIG_DEBUG_RODATA=y)
- Group variables in two structures to reduce number of dirtied cache
lines. One named "peers" for avl tree root, its number of entries, and
associated lock. (candidate for RCU conversion)
- A second one named "unused_peers" for unused list and its lock
- Add a !list_empty() test in unlink_from_unused() to avoid taking lock
when entry is not unused.
- Use atomic_dec_and_lock() in inet_putpeer() to avoid taking lock in
some cases.
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
While investigating for network latencies, I found inet_getid() was a
contention point for some workloads, as inet_peer_idlock is shared
by all inet_getid() users regardless of peers.
One way to fix this is to make ip_id_count an atomic_t instead
of __u16, and use atomic_add_return().
In order to keep sizeof(struct inet_peer) = 64 on 64bit arches
tcp_ts_stamp is also converted to __u32 instead of "unsigned long".
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch removes CVS keywords that weren't updated for a long time
from comments.
Signed-off-by: Adrian Bunk <bunk@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
The inetpeer.c tracks the LRU list of inet_perr-s, but makes
it by hands. Use the list_head-s for this.
Signed-off-by: Pavel Emelyanov <xemul@openvz.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
CC net/ipv4/inetpeer.o
net/ipv4/inetpeer.c: In function 'unlink_from_pool':
net/ipv4/inetpeer.c:297: warning: the address of 'stack' will always evaluate as 'true'
net/ipv4/inetpeer.c:297: warning: the address of 'stack' will always evaluate as 'true'
net/ipv4/inetpeer.c: In function 'inet_getpeer':
net/ipv4/inetpeer.c:409: warning: the address of 'stack' will always evaluate as 'true'
net/ipv4/inetpeer.c:409: warning: the address of 'stack' will always evaluate as 'true'
"Fix" by checking for != NULL.
Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
Slab destructors were no longer supported after Christoph's
c59def9f22 change. They've been
BUGs for both slab and slub, and slob never supported them
either.
This rips out support for the dtor pointer from kmem_cache_create()
completely and fixes up every single callsite in the kernel (there were
about 224, not including the slab allocator definitions themselves,
or the documentation references).
Signed-off-by: Paul Mundt <lethal@linux-sh.org>
