This way GSO packets don't get handled differently.
With help from Eric Dumazet.
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
If some skb are queued to our backlog, we are delaying IPI sending at
the end of net_rx_action(), increasing latencies. This defeats the
queueing, since we want to quickly dispatch packets to the pool of
worker cpus, then eventually deeply process our packets.
It's better to send IPI before processing our packets in upper layers,
from process_backlog().
Change the _and_disable_irq suffix to _and_enable_irq(), since we enable
local irq in net_rps_action(), sorry for the confusion.
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
At this point, skb->destructor is not the original one (stored in
DEV_GSO_CB(skb)->destructor)
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Since netdev_chain is guarded by rtnl_lock, ASSERT_RTNL should be
present here to make sure that all callers of call_netdevice_notifiers
does the locking properly.
Signed-off-by: Jiri Pirko <jpirko@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In case we compute a software skb->rxhash, we can generate a consistent
hash : Its value will be the same in both flow directions.
This helps some workloads, like conntracking, since the same state needs
to be accessed in both directions.
tbench + RFS + this patch gives better results than tbench with default
kernel configuration (no RPS, no RFS)
Also fixed some sparse warnings.
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
struct softnet_data holds many queues, so consistent use "sd" name
instead of "queue" is better.
Adds a rps_ipi_queued() helper to cleanup enqueue_to_backlog()
Adds a _and_irq_disable suffix to net_rps_action() name, as David
suggested.
incr_input_queue_head() becomes input_queue_head_incr()
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
net_rps_action() is a bit expensive on NR_CPUS=64..4096 kernels, even if
RPS is not active.
Tom Herbert used two bitmasks to hold information needed to send IPI,
but a single LIFO list seems more appropriate.
Move all RPS logic into net_rps_action() to cleanup net_rx_action() code
(remove two ifdefs)
Move rps_remote_softirq_cpus into softnet_data to share its first cache
line, filling an existing hole.
In a future patch, we could call net_rps_action() from process_backlog()
to make sure we send IPI before handling this cpu backlog.
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Transmitted skb might be attached to a socket and a destructor, for
memory accounting purposes.
Traditionally, this destructor is called at tx completion time, when skb
is freed.
When tx completion is performed by another cpu than the sender, this
forces some cache lines to change ownership. XPS was an attempt to give
tx completion to initial cpu.
David idea is to call destructor right before giving skb to device (call
to ndo_start_xmit()). Because device queues are usually small, orphaning
skb before tx completion is not a big deal. Some drivers already do
this, we could do it in upper level.
There is one known exception to this early orphaning, called tx
timestamping. It needs to keep a reference to socket until device can
give a hardware or software timestamp.
This patch adds a skb_orphan_try() helper, to centralize all exceptions
to early orphaning in one spot, and use it in dev_hard_start_xmit().
"tbench 16" results on a Nehalem machine (2 X5570 @ 2.93GHz)
before: Throughput 4428.9 MB/sec 16 procs
after: Throughput 4448.14 MB/sec 16 procs
UDP should get even better results, its destructor being more complex,
since SOCK_USE_WRITE_QUEUE is not set (four atomic ops instead of one)
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
- There is no point to enforce a time limit in process_backlog(), since
other napi instances dont follow same rule. We can exit after only one
packet processed...
The normal quota of 64 packets per napi instance should be the norm, and
net_rx_action() already has its own time limit.
Note : /proc/net/core/dev_weight can be used to tune this 64 default
value.
- Use DEFINE_PER_CPU_ALIGNED for softnet_data definition.
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch implements receive flow steering (RFS). RFS steers
received packets for layer 3 and 4 processing to the CPU where
the application for the corresponding flow is running. RFS is an
extension of Receive Packet Steering (RPS).
The basic idea of RFS is that when an application calls recvmsg
(or sendmsg) the application's running CPU is stored in a hash
table that is indexed by the connection's rxhash which is stored in
the socket structure. The rxhash is passed in skb's received on
the connection from netif_receive_skb. For each received packet,
the associated rxhash is used to look up the CPU in the hash table,
if a valid CPU is set then the packet is steered to that CPU using
the RPS mechanisms.
The convolution of the simple approach is that it would potentially
allow OOO packets. If threads are thrashing around CPUs or multiple
threads are trying to read from the same sockets, a quickly changing
CPU value in the hash table could cause rampant OOO packets--
we consider this a non-starter.
To avoid OOO packets, this solution implements two types of hash
tables: rps_sock_flow_table and rps_dev_flow_table.
rps_sock_table is a global hash table. Each entry is just a CPU
number and it is populated in recvmsg and sendmsg as described above.
This table contains the "desired" CPUs for flows.
rps_dev_flow_table is specific to each device queue. Each entry
contains a CPU and a tail queue counter. The CPU is the "current"
CPU for a matching flow. The tail queue counter holds the value
of a tail queue counter for the associated CPU's backlog queue at
the time of last enqueue for a flow matching the entry.
Each backlog queue has a queue head counter which is incremented
on dequeue, and so a queue tail counter is computed as queue head
count + queue length. When a packet is enqueued on a backlog queue,
the current value of the queue tail counter is saved in the hash
entry of the rps_dev_flow_table.
And now the trick: when selecting the CPU for RPS (get_rps_cpu)
the rps_sock_flow table and the rps_dev_flow table for the RX queue
are consulted. When the desired CPU for the flow (found in the
rps_sock_flow table) does not match the current CPU (found in the
rps_dev_flow table), the current CPU is changed to the desired CPU
if one of the following is true:
- The current CPU is unset (equal to RPS_NO_CPU)
- Current CPU is offline
- The current CPU's queue head counter >= queue tail counter in the
rps_dev_flow table. This checks if the queue tail has advanced
beyond the last packet that was enqueued using this table entry.
This guarantees that all packets queued using this entry have been
dequeued, thus preserving in order delivery.
Making each queue have its own rps_dev_flow table has two advantages:
1) the tail queue counters will be written on each receive, so
keeping the table local to interrupting CPU s good for locality. 2)
this allows lockless access to the table-- the CPU number and queue
tail counter need to be accessed together under mutual exclusion
from netif_receive_skb, we assume that this is only called from
device napi_poll which is non-reentrant.
This patch implements RFS for TCP and connected UDP sockets.
It should be usable for other flow oriented protocols.
There are two configuration parameters for RFS. The
"rps_flow_entries" kernel init parameter sets the number of
entries in the rps_sock_flow_table, the per rxqueue sysfs entry
"rps_flow_cnt" contains the number of entries in the rps_dev_flow
table for the rxqueue. Both are rounded to power of two.
The obvious benefit of RFS (over just RPS) is that it achieves
CPU locality between the receive processing for a flow and the
applications processing; this can result in increased performance
(higher pps, lower latency).
The benefits of RFS are dependent on cache hierarchy, application
load, and other factors. On simple benchmarks, we don't necessarily
see improvement and sometimes see degradation. However, for more
complex benchmarks and for applications where cache pressure is
much higher this technique seems to perform very well.
Below are some benchmark results which show the potential benfit of
this patch. The netperf test has 500 instances of netperf TCP_RR
test with 1 byte req. and resp. The RPC test is an request/response
test similar in structure to netperf RR test ith 100 threads on
each host, but does more work in userspace that netperf.
e1000e on 8 core Intel
No RFS or RPS 104K tps at 30% CPU
No RFS (best RPS config): 290K tps at 63% CPU
RFS 303K tps at 61% CPU
RPC test tps CPU% 50/90/99% usec latency Latency StdDev
No RFS/RPS 103K 48% 757/900/3185 4472.35
RPS only: 174K 73% 415/993/2468 491.66
RFS 223K 73% 379/651/1382 315.61
Signed-off-by: Tom Herbert <therbert@google.com>
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
When dev_pick_tx() caches tx queue_index on a socket, we must check
socket dst_entry matches skb one, or risk a crash later, as reported by
Denys Fedorysychenko, if old packets are in flight during a route
change, involving devices with different number of queues.
Bug introduced by commit a4ee3ce3
(net: Use sk_tx_queue_mapping for connected sockets)
Reported-by: Denys Fedorysychenko <nuclearcat@nuclearcat.com>
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Eric Paris reported netif_rx() is calling smp_processor_id() from
preemptible context, in particular when caller is
ip_dev_loopback_xmit().
RPS commit added this smp_processor_id() call, this patch makes sure
preemption is disabled. rps_get_cpus() wants rcu_read_lock() anyway, we
can dot it a bit earlier.
Reported-by: Eric Paris <eparis@redhat.com>
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
skb_bond_should_drop() is too big to be inlined.
This patch reduces kernel text size, and its compilation time as well
(shrinking include/linux/netdevice.h)
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
With latest CONFIG_PROVE_RCU stuff, I felt more comfortable to make this
work.
sk->sk_dst_cache is currently protected by a rwlock (sk_dst_lock)
This rwlock is readlocked for a very small amount of time, and dst
entries are already freed after RCU grace period. This calls for RCU
again :)
This patch converts sk_dst_lock to a spinlock, and use RCU for readers.
__sk_dst_get() is supposed to be called with rcu_read_lock() or if
socket locked by user, so use appropriate rcu_dereference_check()
condition (rcu_read_lock_held() || sock_owned_by_user(sk))
This patch avoids two atomic ops per tx packet on UDP connected sockets,
for example, and permits sk_dst_lock to be much less dirtied.
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Dont use netdev_warn() in dev_cap_txqueue() and get_rps_cpu() so that we
can catch following warnings without crash.
bond0.2240 received packet on queue 6, but number of RX queues is 1
bond0.2240 received packet on queue 11, but number of RX queues is 1
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
As noticed by Changli Gao, we must call local_irq_enable() after
rps_unlock()
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Converts the list and the core manipulating with it to be the same as uc_list.
+uses two functions for adding/removing mc address (normal and "global"
variant) instead of a function parameter.
+removes dev_mcast.c completely.
+exposes netdev_hw_addr_list_* macros along with __hw_addr_* functions for
manipulation with lists on a sandbox (used in bonding and 80211 drivers)
Signed-off-by: Jiri Pirko <jpirko@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
+little renaming of unicast functions to be smooth with multicast ones
Signed-off-by: Jiri Pirko <jpirko@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Followup to commit 5acbbd428d
(net: change illegal_highdma to use dma_mask)
If dev->dev.parent is NULL, we should not try to dereference it.
Dont force inline illegal_highdma() as its pretty big now.
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Robert Hancock pointed out two problems about NETIF_F_HIGHDMA:
-Many drivers only set the flag when they detect they can use 64-bit DMA,
since otherwise they could receive DMA addresses that they can't handle
(which on platforms without IOMMU/SWIOTLB support is fatal). This means that if
64-bit support isn't available, even buffers located below 4GB will get copied
unnecessarily.
-Some drivers set the flag even though they can't actually handle 64-bit DMA,
which would mean that on platforms without IOMMU/SWIOTLB they would get a DMA
mapping error if the memory they received happened to be located above 4GB.
http://lkml.org/lkml/2010/3/3/530
We can use the dma_mask if we need bouncing or not here. Then we can
safely fix drivers that misuse NETIF_F_HIGHDMA.
Signed-off-by: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp>
Signed-off-by: David S. Miller <davem@davemloft.net>
David S. Miller
Eric Dumazet
David Howells
Jiri Pirko
Tom Herbert
FUJITA Tomonori