The removal function of nft_hash currently stores a reference to the
previous element during lookup which is used to optimize removal later
on. This was possible because a lock is held throughout calling
rhashtable_lookup() and rhashtable_remove().
With the introdution of deferred table resizing in parallel to lookups
and insertions, the nftables lock will no longer synchronize all
table mutations and the stored pprev may become invalid.
Removing this optimization makes removal slightly more expensive on
average but allows taking the resize cost out of the insert and
remove path.
Signed-off-by: Thomas Graf <tgraf@suug.ch>
Cc: netfilter-devel@vger.kernel.org
Signed-off-by: David S. Miller <davem@davemloft.net>
Subsequent patches will require access to the bucket tail. Access
to the tail is relatively cheap as the automatic resizing of the
table should keep the number of entries per bucket to no more
than 0.75 on average.
Signed-off-by: Thomas Graf <tgraf@suug.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch is in preparation to introduce per bucket spinlocks. It
extends all iterator macros to take the bucket table and bucket
index. It also introduces a new rht_dereference_bucket() to
handle protected accesses to buckets.
It introduces a barrier() to the RCU iterators to the prevent
the compiler from caching the first element.
The lockdep verifier is introduced as stub which always succeeds
and properly implement in the next patch when the locks are
introduced.
Signed-off-by: Thomas Graf <tgraf@suug.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
Hash the key inside of rhashtable_lookup_compare() like
rhashtable_lookup() does. This allows to simplify the hashing
functions and keep them private.
Signed-off-by: Thomas Graf <tgraf@suug.ch>
Cc: netfilter-devel@vger.kernel.org
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch effectively reverts commit 500f808726 ("net: ovs: use CRC32
accelerated flow hash if available"), and other remaining arch_fast_hash()
users such as from nfsd via commit 6282cd5655 ("NFSD: Don't hand out
delegations for 30 seconds after recalling them.") where it has been used
as a hash function for bloom filtering.
While we think that these users are actually not much of concern, it has
been requested to remove the arch_fast_hash() library bits that arose
from [1] entirely as per recent discussion [2]. The main argument is that
using it as a hash may introduce bias due to its linearity (see avalanche
criterion) and thus makes it less clear (though we tried to document that)
when this security/performance trade-off is actually acceptable for a
general purpose library function.
Lets therefore avoid any further confusion on this matter and remove it to
prevent any future accidental misuse of it. For the time being, this is
going to make hashing of flow keys a bit more expensive in the ovs case,
but future work could reevaluate a different hashing discipline.
[1] https://patchwork.ozlabs.org/patch/299369/
[2] https://patchwork.ozlabs.org/patch/418756/
Cc: Neil Brown <neilb@suse.de>
Cc: Francesco Fusco <fusco@ntop.org>
Cc: Jesse Gross <jesse@nicira.com>
Cc: Thomas Graf <tgraf@suug.ch>
Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Verify whether both the lock and RCU protected iterators see all
test entries before and after expanding and shrinking has been
performed. Also verify whether the number of entries in the hashtable
remains stable during expansion and shrinking.
Signed-off-by: Thomas Graf <tgraf@suug.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
Conflicts:
drivers/net/ethernet/chelsio/cxgb4vf/sge.c
drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c
sge.c was overlapping two changes, one to use the new
__dev_alloc_page() in net-next, and one to use s->fl_pg_order in net.
ixgbe_phy.c was a set of overlapping whitespace changes.
Signed-off-by: David S. Miller <davem@davemloft.net>
Reallocation is only required for shrinking and expanding and both rely
on a mutex for synchronization and callers of rhashtable_init() are in
non atomic context. Therefore, no reason to continue passing allocation
hints through the API.
Instead, use GFP_KERNEL and add __GFP_NOWARN | __GFP_NORETRY to allow
for silent fall back to vzalloc() without the OOM killer jumping in as
pointed out by Eric Dumazet and Eric W. Biederman.
Signed-off-by: Thomas Graf <tgraf@suug.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
Currently mutex_is_held can only test locks in the that are global
since it takes no arguments. This prevents rhashtable from being
used in places where locks are lock, e.g., per-namespace locks.
This patch adds a parent field to mutex_is_held and rhashtable_params
so that local locks can be used (and tested).
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
The rhashtable function mutex_is_held is only used when PROVE_LOCKING
is enabled. This patch makes the mutex_is_held field in rhashtable
optional depending on PROVE_LOCKING.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
My editor spewed garbage that looked like memory corruption on
my screen. It turns out that a number of occurences of "fi" got
turned into a ligature.
This patch replaces these ligatures with the ASCII letters "fi".
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Cheers,
Acked-by: Thomas Graf <tgraf@suug.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
Pull networking updates from David Miller:
"Most notable changes in here:
1) By far the biggest accomplishment, thanks to a large range of
contributors, is the addition of multi-send for transmit. This is
the result of discussions back in Chicago, and the hard work of
several individuals.
Now, when the ->ndo_start_xmit() method of a driver sees
skb->xmit_more as true, it can choose to defer the doorbell
telling the driver to start processing the new TX queue entires.
skb->xmit_more means that the generic networking is guaranteed to
call the driver immediately with another SKB to send.
There is logic added to the qdisc layer to dequeue multiple
packets at a time, and the handling mis-predicted offloads in
software is now done with no locks held.
Finally, pktgen is extended to have a "burst" parameter that can
be used to test a multi-send implementation.
Several drivers have xmit_more support: i40e, igb, ixgbe, mlx4,
virtio_net
Adding support is almost trivial, so export more drivers to
support this optimization soon.
I want to thank, in no particular or implied order, Jesper
Dangaard Brouer, Eric Dumazet, Alexander Duyck, Tom Herbert, Jamal
Hadi Salim, John Fastabend, Florian Westphal, Daniel Borkmann,
David Tat, Hannes Frederic Sowa, and Rusty Russell.
2) PTP and timestamping support in bnx2x, from Michal Kalderon.
3) Allow adjusting the rx_copybreak threshold for a driver via
ethtool, and add rx_copybreak support to enic driver. From
Govindarajulu Varadarajan.
4) Significant enhancements to the generic PHY layer and the bcm7xxx
driver in particular (EEE support, auto power down, etc.) from
Florian Fainelli.
5) Allow raw buffers to be used for flow dissection, allowing drivers
to determine the optimal "linear pull" size for devices that DMA
into pools of pages. The objective is to get exactly the
necessary amount of headers into the linear SKB area pre-pulled,
but no more. The new interface drivers use is eth_get_headlen().
From WANG Cong, with driver conversions (several had their own
by-hand duplicated implementations) by Alexander Duyck and Eric
Dumazet.
6) Support checksumming more smoothly and efficiently for
encapsulations, and add "foo over UDP" facility. From Tom
Herbert.
7) Add Broadcom SF2 switch driver to DSA layer, from Florian
Fainelli.
8) eBPF now can load programs via a system call and has an extensive
testsuite. Alexei Starovoitov and Daniel Borkmann.
9) Major overhaul of the packet scheduler to use RCU in several major
areas such as the classifiers and rate estimators. From John
Fastabend.
10) Add driver for Intel FM10000 Ethernet Switch, from Alexander
Duyck.
11) Rearrange TCP_SKB_CB() to reduce cache line misses, from Eric
Dumazet.
12) Add Datacenter TCP congestion control algorithm support, From
Florian Westphal.
13) Reorganize sk_buff so that __copy_skb_header() is significantly
faster. From Eric Dumazet"
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1558 commits)
netlabel: directly return netlbl_unlabel_genl_init()
net: add netdev_txq_bql_{enqueue, complete}_prefetchw() helpers
net: description of dma_cookie cause make xmldocs warning
cxgb4: clean up a type issue
cxgb4: potential shift wrapping bug
i40e: skb->xmit_more support
net: fs_enet: Add NAPI TX
net: fs_enet: Remove non NAPI RX
r8169:add support for RTL8168EP
net_sched: copy exts->type in tcf_exts_change()
wimax: convert printk to pr_foo()
af_unix: remove 0 assignment on static
ipv6: Do not warn for informational ICMP messages, regardless of type.
Update Intel Ethernet Driver maintainers list
bridge: Save frag_max_size between PRE_ROUTING and POST_ROUTING
tipc: fix bug in multicast congestion handling
net: better IFF_XMIT_DST_RELEASE support
net/mlx4_en: remove NETDEV_TX_BUSY
3c59x: fix bad split of cpu_to_le32(pci_map_single())
net: bcmgenet: fix Tx ring priority programming
...
Conflicts:
drivers/net/usb/r8152.c
net/netfilter/nfnetlink.c
Both r8152 and nfnetlink conflicts were simple overlapping changes.
Signed-off-by: David S. Miller <davem@davemloft.net>
Pablo Neira Ayuso says:
====================
nf pull request for net
This series contains netfilter fixes for net, they are:
1) Fix lockdep splat in nft_hash when releasing sets from the
rcu_callback context. We don't the mutex there anymore.
2) Remove unnecessary spinlock_bh in the destroy path of the nf_tables
rbtree set type from rcu_callback context.
3) Fix another lockdep splat in rhashtable. None of the callers hold
a mutex when calling rhashtable_destroy.
4) Fix duplicated error reporting from nfnetlink when aborting and
replaying a batch.
5) Fix a Kconfig issue reported by kbuild robot.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Conflicts:
arch/mips/net/bpf_jit.c
drivers/net/can/flexcan.c
Both the flexcan and MIPS bpf_jit conflicts were cases of simple
overlapping changes.
Signed-off-by: David S. Miller <davem@davemloft.net>
Although rhashtable library allows user to specify a quiet big size
for user's created hash table, the table may be shrunk to a
very small size - HASH_MIN_SIZE(4) after object is removed from
the table at the first time. Subsequently, even if the total amount
of objects saved in the table is quite lower than user's initial
setting in a long time, the hash table size is still dynamically
adjusted by rhashtable_shrink() or rhashtable_expand() each time
object is inserted or removed from the table. However, as
synchronize_rcu() has to be called when table is shrunk or
expanded by the two functions, we should permit user to set the
minimum table size through configuring the minimum number of shifts
according to user specific requirement, avoiding these expensive
actions of shrinking or expanding because of calling synchronize_rcu().
Signed-off-by: Ying Xue <ying.xue@windriver.com>
Acked-by: Thomas Graf <tgraf@suug.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
No need for rht_dereference() from rhashtable_destroy() since the
existing callers don't hold the mutex when invoking this function
from:
1) Netlink, this is called in case of memory allocation errors in the
initialization path, no nl_sk_hash_lock is held.
2) Netfilter, this is called from the rcu callback, no nfnl_lock is
held either.
I think it's reasonable to assume that the caller has to make sure
that no hash resizing may happen before releasing the bucket array.
Therefore, the caller should be responsible for releasing this in a
safe way, document this to make people aware of it.
This resolves a rcu lockdep splat in nft_hash:
===============================
[ INFO: suspicious RCU usage. ]
3.16.0+ #178 Not tainted
-------------------------------
lib/rhashtable.c:596 suspicious rcu_dereference_protected() usage!
other info that might help us debug this:
rcu_scheduler_active = 1, debug_locks = 1
1 lock held by ksoftirqd/2/18:
#0: (rcu_callback){......}, at: [<ffffffff810918fd>] rcu_process_callbacks+0x27e/0x4c7
stack backtrace:
CPU: 2 PID: 18 Comm: ksoftirqd/2 Not tainted 3.16.0+ #178
Hardware name: LENOVO 23259H1/23259H1, BIOS G2ET32WW (1.12 ) 05/30/2012
0000000000000001 ffff88011706bb68 ffffffff8143debc 0000000000000000
ffff880117062610 ffff88011706bb98 ffffffff81077515 ffff8800ca041a50
0000000000000004 ffff8800ca386480 ffff8800ca041a00 ffff88011706bbb8
Call Trace:
[<ffffffff8143debc>] dump_stack+0x4e/0x68
[<ffffffff81077515>] lockdep_rcu_suspicious+0xfa/0x103
[<ffffffff81228b1b>] rhashtable_destroy+0x46/0x52
[<ffffffffa06f21a7>] nft_hash_destroy+0x73/0x82 [nft_hash]
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Acked-by: Thomas Graf <tgraf@suug.ch>
No need to export rht_obj(), all inner to outer object translations
occur internally. It was intended to be used with rht_for_each() which
now primarily serves as the iterator for rhashtable_remove_pprev() to
effectively flush and free the full table.
Signed-off-by: Thomas Graf <tgraf@suug.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
Properly annotate next pointers as access is RCU protected in
the lookup path.
Signed-off-by: Thomas Graf <tgraf@suug.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
Generic implementation of a resizable, scalable, concurrent hash table
based on [0]. The implementation supports both, fixed size keys specified
via an offset and length, or arbitrary keys via own hash and compare
functions.
Lookups are lockless and protected as RCU read side critical sections.
Automatic growing/shrinking based on user configurable watermarks is
available while allowing concurrent lookups to take place.
Objects to be hashed must include a struct rhash_head. The reason for not
using the existing struct hlist_head is that the expansion and shrinking
will have two buckets point to a single entry which would lead in obscure
reverse chaining behaviour.
Code includes a boot selftest if CONFIG_TEST_RHASHTABLE is defined.
[0] https://www.usenix.org/legacy/event/atc11/tech/final_files/Triplett.pdf
Signed-off-by: Thomas Graf <tgraf@suug.ch>
Reviewed-by: Nikolay Aleksandrov <nikolay@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Thomas Graf