summaryrefslogtreecommitdiffstats
path: root/net/packet
AgeCommit message (Collapse)Author
2014-07-29packet: remove deprecated syststamp timestampWillem de Bruijn
No device driver will ever return an skb_shared_info structure with syststamp non-zero, so remove the branch that tests for this and optionally marks the packet timestamp as TP_STATUS_TS_SYS_HARDWARE. Do not remove the definition TP_STATUS_TS_SYS_HARDWARE, as processes may refer to it. Signed-off-by: Willem de Bruijn <willemb@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-07-15packet: remove unnecessary break after returnFabian Frederick
Signed-off-by: Fabian Frederick <fabf@skynet.be> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-04-24net: Use netlink_ns_capable to verify the permisions of netlink messagesEric W. Biederman
It is possible by passing a netlink socket to a more privileged executable and then to fool that executable into writing to the socket data that happens to be valid netlink message to do something that privileged executable did not intend to do. To keep this from happening replace bare capable and ns_capable calls with netlink_capable, netlink_net_calls and netlink_ns_capable calls. Which act the same as the previous calls except they verify that the opener of the socket had the desired permissions as well. Reported-by: Andy Lutomirski <luto@amacapital.net> Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-04-24net: Move the permission check in sock_diag_put_filterinfo to packet_diag_dumpEric W. Biederman
The permission check in sock_diag_put_filterinfo is wrong, and it is so removed from it's sources it is not clear why it is wrong. Move the computation into packet_diag_dump and pass a bool of the result into sock_diag_filterinfo. This does not yet correct the capability check but instead simply moves it to make it clear what is going on. Reported-by: Andy Lutomirski <luto@amacapital.net> Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-04-22net: Fix ns_capable check in sock_diag_put_filterinfoAndrew Lutomirski
The caller needs capabilities on the namespace being queried, not on their own namespace. This is a security bug, although it likely has only a minor impact. Cc: stable@vger.kernel.org Signed-off-by: Andy Lutomirski <luto@amacapital.net> Acked-by: Nicolas Dichtel <nicolas.dichtel@6wind.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-04-11net: Fix use after free by removing length arg from sk_data_ready callbacks.David S. Miller
Several spots in the kernel perform a sequence like: skb_queue_tail(&sk->s_receive_queue, skb); sk->sk_data_ready(sk, skb->len); But at the moment we place the SKB onto the socket receive queue it can be consumed and freed up. So this skb->len access is potentially to freed up memory. Furthermore, the skb->len can be modified by the consumer so it is possible that the value isn't accurate. And finally, no actual implementation of this callback actually uses the length argument. And since nobody actually cared about it's value, lots of call sites pass arbitrary values in such as '0' and even '1'. So just remove the length argument from the callback, that way there is no confusion whatsoever and all of these use-after-free cases get fixed as a side effect. Based upon a patch by Eric Dumazet and his suggestion to audit this issue tree-wide. Signed-off-by: David S. Miller <davem@davemloft.net>
2014-04-03packet: fix packet_direct_xmit for BQL enabled driversDaniel Borkmann
Currently, in packet_direct_xmit() we test the assigned netdevice queue for netif_xmit_frozen_or_stopped() before doing an ndo_start_xmit(). This can have the side-effect that BQL enabled drivers which make use of netdev_tx_sent_queue() internally, set __QUEUE_STATE_STACK_XOFF from within the stack and would not fully fill the device's TX ring from packet sockets with PACKET_QDISC_BYPASS enabled. Instead, use a test without BQL bit so that bursts can be absorbed into the NICs TX ring. Fix and code suggested by Eric Dumazet, thanks! Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: Daniel Borkmann <dborkman@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-04-03packet: report tx_dropped in packet_direct_xmitDaniel Borkmann
Since commit 015f0688f57c ("net: net: add a core netdev->tx_dropped counter"), we can now account for TX drops from within the core stack instead of drivers. Therefore, fix packet_direct_xmit() and increase drop count when we encounter a problem before driver's xmit function was called (we do not want to doubly account for it). Suggested-by: Eric Dumazet <edumazet@google.com> Signed-off-by: Daniel Borkmann <dborkman@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-03-28packet: respect devices with LLTX flag in direct xmitDaniel Borkmann
Quite often it can be useful to test with dummy or similar devices as a blackhole sink for skbs. Such devices are only equipped with a single txq, but marked as NETIF_F_LLTX as they do not require locking their internal queues on xmit (or implement locking themselves). Therefore, rather use HARD_TX_{UN,}LOCK API, so that NETIF_F_LLTX will be respected. trafgen mmap/TX_RING example against dummy device with config foo: { fill(0xff, 64) } results in the following performance improvements for such scenarios on an ordinary Core i7/2.80GHz: Before: Performance counter stats for 'trafgen -i foo -o du0 -n100000000' (10 runs): 160,975,944,159 instructions:k # 0.55 insns per cycle ( +- 0.09% ) 293,319,390,278 cycles:k # 0.000 GHz ( +- 0.35% ) 192,501,104 branch-misses:k ( +- 1.63% ) 831 context-switches:k ( +- 9.18% ) 7 cpu-migrations:k ( +- 7.40% ) 69,382 cache-misses:k # 0.010 % of all cache refs ( +- 2.18% ) 671,552,021 cache-references:k ( +- 1.29% ) 22.856401569 seconds time elapsed ( +- 0.33% ) After: Performance counter stats for 'trafgen -i foo -o du0 -n100000000' (10 runs): 133,788,739,692 instructions:k # 0.92 insns per cycle ( +- 0.06% ) 145,853,213,256 cycles:k # 0.000 GHz ( +- 0.17% ) 59,867,100 branch-misses:k ( +- 4.72% ) 384 context-switches:k ( +- 3.76% ) 6 cpu-migrations:k ( +- 6.28% ) 70,304 cache-misses:k # 0.077 % of all cache refs ( +- 1.73% ) 90,879,408 cache-references:k ( +- 1.35% ) 11.719372413 seconds time elapsed ( +- 0.24% ) Signed-off-by: Daniel Borkmann <dborkman@redhat.com> Cc: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-03-26net: Rename skb->rxhash to skb->hashTom Herbert
The packet hash can be considered a property of the packet, not just on RX path. This patch changes name of rxhash and l4_rxhash skbuff fields to be hash and l4_hash respectively. This includes changing uses of the field in the code which don't call the access functions. Signed-off-by: Tom Herbert <therbert@google.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Mahesh Bandewar <maheshb@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-02-28packet: allow to transmit +4 byte in TX_RING slot for VLAN caseDaniel Borkmann
Commit 57f89bfa2140 ("network: Allow af_packet to transmit +4 bytes for VLAN packets.") added the possibility for non-mmaped frames to send extra 4 byte for VLAN header so the MTU increases from 1500 to 1504 byte, for example. Commit cbd89acb9eb2 ("af_packet: fix for sending VLAN frames via packet_mmap") attempted to fix that for the mmap part but was reverted as it caused regressions while using eth_type_trans() on output path. Lets just act analogous to 57f89bfa2140 and add a similar logic to TX_RING. We presume size_max as overcharged with +4 bytes and later on after skb has been built by tpacket_fill_skb() check for ETH_P_8021Q header on packets larger than normal MTU. Can be easily reproduced with a slightly modified trafgen in mmap(2) mode, test cases: { fill(0xff, 12) const16(0x8100) fill(0xff, <1504|1505>) } { fill(0xff, 12) const16(0x0806) fill(0xff, <1500|1501>) } Note that we need to do the test right after tpacket_fill_skb() as sockets can have PACKET_LOSS set where we would not fail but instead just continue to traverse the ring. Reported-by: Mathias Kretschmer <mathias.kretschmer@fokus.fraunhofer.de> Signed-off-by: Daniel Borkmann <dborkman@redhat.com> Cc: Ben Greear <greearb@candelatech.com> Cc: Phil Sutter <phil@nwl.cc> Tested-by: Mathias Kretschmer <mathias.kretschmer@fokus.fraunhofer.de> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-02-18af_packet: remove a stray tab in packet_set_ring()Dan Carpenter
At first glance it looks like there is a missing curly brace but actually the code works the same either way. I have adjusted the indenting but left the code the same. Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com> Acked-by: Daniel Borkmann <dborkman@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-02-17packet: check for ndo_select_queue during queue selectionDaniel Borkmann
Mathias reported that on an AMD Geode LX embedded board (ALiX) with ath9k driver PACKET_QDISC_BYPASS, introduced in commit d346a3fae3ff ("packet: introduce PACKET_QDISC_BYPASS socket option"), triggers a WARN_ON() coming from the driver itself via 066dae93bdf ("ath9k: rework tx queue selection and fix queue stopping/waking"). The reason why this happened is that ndo_select_queue() call is not invoked from direct xmit path i.e. for ieee80211 subsystem that sets queue and TID (similar to 802.1d tag) which is being put into the frame through 802.11e (WMM, QoS). If that is not set, pending frame counter for e.g. ath9k can get messed up. So the WARN_ON() in ath9k is absolutely legitimate. Generally, the hw queue selection in ieee80211 depends on the type of traffic, and priorities are set according to ieee80211_ac_numbers mapping; working in a similar way as DiffServ only on a lower layer, so that the AP can favour frames that have "real-time" requirements like voice or video data frames. Therefore, check for presence of ndo_select_queue() in netdev ops and, if available, invoke it with a fallback handler to __packet_pick_tx_queue(), so that driver such as bnx2x, ixgbe, or mlx4 can still select a hw queue for transmission in relation to the current CPU while e.g. ieee80211 subsystem can make their own choices. Reported-by: Mathias Kretschmer <mathias.kretschmer@fokus.fraunhofer.de> Signed-off-by: Daniel Borkmann <dborkman@redhat.com> Cc: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-01-22af_packet: Add Queue mapping mode to af_packet fanout operationNeil Horman
This patch adds a queue mapping mode to the fanout operation of af_packet sockets. This allows user space af_packet users to better filter on flows ingressing and egressing via a specific hardware queue, and avoids the potential packet reordering that can occur when FANOUT_CPU is being used and irq affinity varies. Tested successfully by myself. applies to net-next Signed-off-by: Neil Horman <nhorman@tuxdriver.com> CC: "David S. Miller" <davem@davemloft.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-01-21net: introduce reciprocal_scale helper and convert usersDaniel Borkmann
As David Laight suggests, we shouldn't necessarily call this reciprocal_divide() when users didn't requested a reciprocal_value(); lets keep the basic idea and call it reciprocal_scale(). More background information on this topic can be found in [1]. Joint work with Hannes Frederic Sowa. [1] http://homepage.cs.uiowa.edu/~jones/bcd/divide.html Suggested-by: David Laight <david.laight@aculab.com> Cc: Jakub Zawadzki <darkjames-ws@darkjames.pl> Cc: Eric Dumazet <eric.dumazet@gmail.com> Cc: linux-kernel@vger.kernel.org Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org> Signed-off-by: Daniel Borkmann <dborkman@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-01-21random32: add prandom_u32_max and convert open coded usersDaniel Borkmann
Many functions have open coded a function that returns a random number in range [0,N-1]. Under the assumption that we have a PRNG such as taus113 with being well distributed in [0, ~0U] space, we can implement such a function as uword t = (n*m')>>32, where m' is a random number obtained from PRNG, n the right open interval border and t our resulting random number, with n,m',t in u32 universe. Lets go with Joe and simply call it prandom_u32_max(), although technically we have an right open interval endpoint, but that we have documented. Other users can further be migrated to the new prandom_u32_max() function later on; for now, we need to make sure to migrate reciprocal_divide() users for the reciprocal_divide() follow-up fixup since their function signatures are going to change. Joint work with Hannes Frederic Sowa. Cc: Jakub Zawadzki <darkjames-ws@darkjames.pl> Cc: Eric Dumazet <eric.dumazet@gmail.com> Cc: linux-kernel@vger.kernel.org Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org> Signed-off-by: Daniel Borkmann <dborkman@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-01-21packet: fix a couple of cppcheck warningsDaniel Borkmann
Doesn't bring much, but also doesn't hurt us to fix 'em: 1) In tpacket_rcv() flush dcache page we can restirct the scope for start and end and remove one layer of indent. 2) In tpacket_destruct_skb() we can restirct the scope for ph. 3) In alloc_one_pg_vec_page() we can remove the NULL assignment and change spacing a bit. Signed-off-by: Daniel Borkmann <dborkman@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-01-18net: add build-time checks for msg->msg_name sizeSteffen Hurrle
This is a follow-up patch to f3d3342602f8bc ("net: rework recvmsg handler msg_name and msg_namelen logic"). DECLARE_SOCKADDR validates that the structure we use for writing the name information to is not larger than the buffer which is reserved for msg->msg_name (which is 128 bytes). Also use DECLARE_SOCKADDR consistently in sendmsg code paths. Signed-off-by: Steffen Hurrle <steffen@hurrle.net> Suggested-by: Hannes Frederic Sowa <hannes@stressinduktion.org> Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-01-16packet: use percpu mmap tx frame pending refcountDaniel Borkmann
In PF_PACKET's packet mmap(), we can avoid using one atomic_inc() and one atomic_dec() call in skb destructor and use a percpu reference count instead in order to determine if packets are still pending to be sent out. Micro-benchmark with [1] that has been slightly modified (that is, protcol = 0 in socket(2) and bind(2)), example on a rather crappy testing machine; I expect it to scale and have even better results on bigger machines: ./packet_mm_tx -s7000 -m7200 -z700000 em1, avg over 2500 runs: With patch: 4,022,015 cyc Without patch: 4,812,994 cyc time ./packet_mm_tx -s64 -c10000000 em1 > /dev/null, stable: With patch: real 1m32.241s user 0m0.287s sys 1m29.316s Without patch: real 1m38.386s user 0m0.265s sys 1m35.572s In function tpacket_snd(), it is okay to use packet_read_pending() since in fast-path we short-circuit the condition already with ph != NULL, since we have next frames to process. In case we have MSG_DONTWAIT, we also do not execute this path as need_wait is false here anyway, and in case of _no_ MSG_DONTWAIT flag, it is okay to call a packet_read_pending(), because when we ever reach that path, we're done processing outgoing frames anyway and only look if there are skbs still outstanding to be orphaned. We can stay lockless in this percpu counter since it's acceptable when we reach this path for the sum to be imprecise first, but we'll level out at 0 after all pending frames have reached the skb destructor eventually through tx reclaim. When people pin a tx process to particular CPUs, we expect overflows to happen in the reference counter as on one CPU we expect heavy increase; and distributed through ksoftirqd on all CPUs a decrease, for example. As David Laight points out, since the C language doesn't define the result of signed int overflow (i.e. rather than wrap, it is allowed to saturate as a possible outcome), we have to use unsigned int as reference count. The sum over all CPUs when tx is complete will result in 0 again. The BUG_ON() in tpacket_destruct_skb() we can remove as well. It can _only_ be set from inside tpacket_snd() path and we made sure to increase tx_ring.pending in any case before we called po->xmit(skb). So testing for tx_ring.pending == 0 is not too useful. Instead, it would rather have been useful to test if lower layers didn't orphan the skb so that we're missing ring slots being put back to TP_STATUS_AVAILABLE. But such a bug will be caught in user space already as we end up realizing that we do not have any TP_STATUS_AVAILABLE slots left anymore. Therefore, we're all set. Btw, in case of RX_RING path, we do not make use of the pending member, therefore we also don't need to use up any percpu memory here. Also note that __alloc_percpu() already returns a zero-filled percpu area, so initialization is done already. [1] http://wiki.ipxwarzone.com/index.php5?title=Linux_packet_mmap Signed-off-by: Daniel Borkmann <dborkman@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-01-16packet: don't unconditionally schedule() in case of MSG_DONTWAITDaniel Borkmann
In tpacket_snd(), when we've discovered a first frame that is not in status TP_STATUS_SEND_REQUEST, and return a NULL buffer, we exit the send routine in case of MSG_DONTWAIT, since we've finished traversing the mmaped send ring buffer and don't care about pending frames. While doing so, we still unconditionally call an expensive schedule() in the packet_current_frame() "error" path, which is unnecessary in this case since it's enough to just quit the function. Also, in case MSG_DONTWAIT is not set, we should rather test for need_resched() first and do schedule() only if necessary since meanwhile pending frames could already have finished processing and called skb destructor. Signed-off-by: Daniel Borkmann <dborkman@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-01-16packet: improve socket create/bind latency in some casesDaniel Borkmann
Most people acquire PF_PACKET sockets with a protocol argument in the socket call, e.g. libpcap does so with htons(ETH_P_ALL) for all its sockets. Most likely, at some point in time a subsequent bind() call will follow, e.g. in libpcap with ... memset(&sll, 0, sizeof(sll)); sll.sll_family = AF_PACKET; sll.sll_ifindex = ifindex; sll.sll_protocol = htons(ETH_P_ALL); ... as arguments. What happens in the kernel is that already in socket() syscall, we install a proto hook via register_prot_hook() if our protocol argument is != 0. Yet, in bind() we're almost doing the same work by doing a unregister_prot_hook() with an expensive synchronize_net() call in case during socket() the proto was != 0, plus follow-up register_prot_hook() with a bound device to it this time, in order to limit traffic we get. In the case when the protocol and user supplied device index (== 0) does not change from socket() to bind(), we can spare us doing the same work twice. Similarly for re-binding to the same device and protocol. For these scenarios, we can decrease create/bind latency from ~7447us (sock-bind-2 case) to ~89us (sock-bind-1 case) with this patch. Alternatively, for the first case, if people care, they should simply create their sockets with proto == 0 argument and define the protocol during bind() as this saves a call to synchronize_net() as well (sock-bind-3 case). In all other cases, we're tied to user space behaviour we must not change, also since a bind() is not strictly required. Thus, we need the synchronize_net() to make sure no asynchronous packet processing paths still refer to the previous elements of po->prot_hook. In case of mmap()ed sockets, the workflow that includes bind() is socket() -> setsockopt(<ring>) -> bind(). In that case, a pair of {__unregister, register}_prot_hook is being called from setsockopt() in order to install the new protocol receive handler. Thus, when we call bind and can skip a re-hook, we have already previously installed the new handler. For fanout, this is handled different entirely, so we should be good. Timings on an i7-3520M machine: * sock-bind-1: 89 us * sock-bind-2: 7447 us * sock-bind-3: 75 us sock-bind-1: socket(PF_PACKET, SOCK_RAW, htons(ETH_P_IP)) = 3 bind(3, {sa_family=AF_PACKET, proto=htons(ETH_P_IP), if=all(0), pkttype=PACKET_HOST, addr(0)={0, }, 20) = 0 sock-bind-2: socket(PF_PACKET, SOCK_RAW, htons(ETH_P_IP)) = 3 bind(3, {sa_family=AF_PACKET, proto=htons(ETH_P_IP), if=lo(1), pkttype=PACKET_HOST, addr(0)={0, }, 20) = 0 sock-bind-3: socket(PF_PACKET, SOCK_RAW, 0) = 3 bind(3, {sa_family=AF_PACKET, proto=htons(ETH_P_IP), if=lo(1), pkttype=PACKET_HOST, addr(0)={0, }, 20) = 0 Signed-off-by: Daniel Borkmann <dborkman@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-12-31packet: fix "foo * bar" and "(foo*)" problemsWeilong Chen
Cleanup checkpatch errors.Specially,the second changed line is exactly 80 columns long. Signed-off-by: Weilong Chen <chenweilong@huawei.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-12-18packet: deliver VLAN TPID to userspaceAtzm Watanabe
This enables userspace to get VLAN TPID as well as the VLAN TCI. Signed-off-by: Atzm Watanabe <atzm@stratosphere.co.jp> Acked-by: Daniel Borkmann <dborkman@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-12-18packet: fill the gap of TPACKET_ALIGNMENT with zerosAtzm Watanabe
struct tpacket{2,3}_hdr is aligned to a multiple of TPACKET_ALIGNMENT. Explicitly defining and zeroing the gap of this makes additional changes easier. Signed-off-by: Atzm Watanabe <atzm@stratosphere.co.jp> Acked-by: Daniel Borkmann <dborkman@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-12-18packet: make aligned size of struct tpacket{2,3}_hdr clearAtzm Watanabe
struct tpacket{2,3}_hdr is aligned to a multiple of TPACKET_ALIGNMENT. We may add members to them until current aligned size without forcing userspace to call getsockopt(..., PACKET_HDRLEN, ...). Signed-off-by: Atzm Watanabe <atzm@stratosphere.co.jp> Acked-by: Daniel Borkmann <dborkman@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-12-17net: Change skb_get_rxhash to skb_get_hashTom Herbert
Changing name of function as part of making the hash in skbuff to be generic property, not just for receive path. Signed-off-by: Tom Herbert <therbert@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-12-14packet: fix using smp_processor_id() in preemptible codeLi Zhong
This patches fixes the following warning by replacing smp_processor_id() with raw_smp_processor_id(): [ 11.120893] BUG: using smp_processor_id() in preemptible [00000000] code: arping/3510 [ 11.120913] caller is .packet_sendmsg+0xc14/0xe68 [ 11.120920] CPU: 13 PID: 3510 Comm: arping Not tainted 3.13.0-rc3-next-20131211-dirty #1 [ 11.120926] Call Trace: [ 11.120932] [c0000001f803f6f0] [c0000000000138dc] .show_stack+0x110/0x25c (unreliable) [ 11.120942] [c0000001f803f7e0] [c00000000083dd24] .dump_stack+0xa0/0x37c [ 11.120951] [c0000001f803f870] [c000000000493fd4] .debug_smp_processor_id+0xfc/0x12c [ 11.120959] [c0000001f803f900] [c0000000007eba78] .packet_sendmsg+0xc14/0xe68 [ 11.120968] [c0000001f803fa80] [c000000000700968] .sock_sendmsg+0xa0/0xe0 [ 11.120975] [c0000001f803fbf0] [c0000000007014d8] .SyS_sendto+0x100/0x148 [ 11.120983] [c0000001f803fd60] [c0000000006fff10] .SyS_socketcall+0x1c4/0x2e8 [ 11.120990] [c0000001f803fe30] [c00000000000a1e4] syscall_exit+0x0/0x9c Signed-off-by: Li Zhong <zhong@linux.vnet.ibm.com> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Daniel Borkmann <dborkman@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-12-09packet: introduce PACKET_QDISC_BYPASS socket optionDaniel Borkmann
This patch introduces a PACKET_QDISC_BYPASS socket option, that allows for using a similar xmit() function as in pktgen instead of taking the dev_queue_xmit() path. This can be very useful when PF_PACKET applications are required to be used in a similar scenario as pktgen, but with full, flexible packet payload that needs to be provided, for example. On default, nothing changes in behaviour for normal PF_PACKET TX users, so everything stays as is for applications. New users, however, can now set PACKET_QDISC_BYPASS if needed to prevent own packets from i) reentering packet_rcv() and ii) to directly push the frame to the driver. In doing so we can increase pps (here 64 byte packets) for PF_PACKET a bit: # CPUs -- QDISC_BYPASS -- qdisc path -- qdisc path[**] 1 CPU == 1,509,628 pps -- 1,208,708 -- 1,247,436 2 CPUs == 3,198,659 pps -- 2,536,012 -- 1,605,779 3 CPUs == 4,787,992 pps -- 3,788,740 -- 1,735,610 4 CPUs == 6,173,956 pps -- 4,907,799 -- 1,909,114 5 CPUs == 7,495,676 pps -- 5,956,499 -- 2,014,422 6 CPUs == 9,001,496 pps -- 7,145,064 -- 2,155,261 7 CPUs == 10,229,776 pps -- 8,190,596 -- 2,220,619 8 CPUs == 11,040,732 pps -- 9,188,544 -- 2,241,879 9 CPUs == 12,009,076 pps -- 10,275,936 -- 2,068,447 10 CPUs == 11,380,052 pps -- 11,265,337 -- 1,578,689 11 CPUs == 11,672,676 pps -- 11,845,344 -- 1,297,412 [...] 20 CPUs == 11,363,192 pps -- 11,014,933 -- 1,245,081 [**]: qdisc path with packet_rcv(), how probably most people seem to use it (hopefully not anymore if not needed) The test was done using a modified trafgen, sending a simple static 64 bytes packet, on all CPUs. The trick in the fast "qdisc path" case, is to avoid reentering packet_rcv() by setting the RAW socket protocol to zero, like: socket(PF_PACKET, SOCK_RAW, 0); Tradeoffs are documented as well in this patch, clearly, if queues are busy, we will drop more packets, tc disciplines are ignored, and these packets are not visible to taps anymore. For a pktgen like scenario, we argue that this is acceptable. The pointer to the xmit function has been placed in packet socket structure hole between cached_dev and prot_hook that is hot anyway as we're working on cached_dev in each send path. Done in joint work together with Jesper Dangaard Brouer. Signed-off-by: Daniel Borkmann <dborkman@redhat.com> Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-12-09Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/netDavid S. Miller
Merge 'net' into 'net-next' to get the AF_PACKET bug fix that Daniel's direct transmit changes depend upon. Signed-off-by: David S. Miller <davem@davemloft.net>
2013-12-09packet: fix send path when running with proto == 0Daniel Borkmann
Commit e40526cb20b5 introduced a cached dev pointer, that gets hooked into register_prot_hook(), __unregister_prot_hook() to update the device used for the send path. We need to fix this up, as otherwise this will not work with sockets created with protocol = 0, plus with sll_protocol = 0 passed via sockaddr_ll when doing the bind. So instead, assign the pointer directly. The compiler can inline these helper functions automagically. While at it, also assume the cached dev fast-path as likely(), and document this variant of socket creation as it seems it is not widely used (seems not even the author of TX_RING was aware of that in his reference example [1]). Tested with reproducer from e40526cb20b5. [1] http://wiki.ipxwarzone.com/index.php5?title=Linux_packet_mmap#Example Fixes: e40526cb20b5 ("packet: fix use after free race in send path when dev is released") Signed-off-by: Daniel Borkmann <dborkman@redhat.com> Tested-by: Salam Noureddine <noureddine@aristanetworks.com> Tested-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-12-06packet: use macro GET_PBDQC_FROM_RB to simplify the codesDuan Jiong
Signed-off-by: Duan Jiong <duanj.fnst@cn.fujitsu.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-11-29af_packet: block BH in prb_shutdown_retire_blk_timer()Veaceslav Falico
Currently we're using plain spin_lock() in prb_shutdown_retire_blk_timer(), however the timer might fire right in the middle and thus try to re-aquire the same spinlock, leaving us in a endless loop. To fix that, use the spin_lock_bh() to block it. Fixes: f6fb8f100b80 ("af-packet: TPACKET_V3 flexible buffer implementation.") CC: "David S. Miller" <davem@davemloft.net> CC: Daniel Borkmann <dborkman@redhat.com> CC: Willem de Bruijn <willemb@google.com> CC: Phil Sutter <phil@nwl.cc> CC: Eric Dumazet <edumazet@google.com> Reported-by: Jan Stancek <jstancek@redhat.com> Tested-by: Jan Stancek <jstancek@redhat.com> Signed-off-by: Veaceslav Falico <vfalico@redhat.com> Acked-by: Daniel Borkmann <dborkman@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-11-21packet: fix use after free race in send path when dev is releasedDaniel Borkmann
Salam reported a use after free bug in PF_PACKET that occurs when we're sending out frames on a socket bound device and suddenly the net device is being unregistered. It appears that commit 827d9780 introduced a possible race condition between {t,}packet_snd() and packet_notifier(). In the case of a bound socket, packet_notifier() can drop the last reference to the net_device and {t,}packet_snd() might end up suddenly sending a packet over a freed net_device. To avoid reverting 827d9780 and thus introducing a performance regression compared to the current state of things, we decided to hold a cached RCU protected pointer to the net device and maintain it on write side via bind spin_lock protected register_prot_hook() and __unregister_prot_hook() calls. In {t,}packet_snd() path, we access this pointer under rcu_read_lock through packet_cached_dev_get() that holds reference to the device to prevent it from being freed through packet_notifier() while we're in send path. This is okay to do as dev_put()/dev_hold() are per-cpu counters, so this should not be a performance issue. Also, the code simplifies a bit as we don't need need_rls_dev anymore. Fixes: 827d978037d7 ("af-packet: Use existing netdev reference for bound sockets.") Reported-by: Salam Noureddine <noureddine@aristanetworks.com> Signed-off-by: Daniel Borkmann <dborkman@redhat.com> Signed-off-by: Salam Noureddine <noureddine@aristanetworks.com> Cc: Ben Greear <greearb@candelatech.com> Cc: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-11-20net: rework recvmsg handler msg_name and msg_namelen logicHannes Frederic Sowa
This patch now always passes msg->msg_namelen as 0. recvmsg handlers must set msg_namelen to the proper size <= sizeof(struct sockaddr_storage) to return msg_name to the user. This prevents numerous uninitialized memory leaks we had in the recvmsg handlers and makes it harder for new code to accidentally leak uninitialized memory. Optimize for the case recvfrom is called with NULL as address. We don't need to copy the address at all, so set it to NULL before invoking the recvmsg handler. We can do so, because all the recvmsg handlers must cope with the case a plain read() is called on them. read() also sets msg_name to NULL. Also document these changes in include/linux/net.h as suggested by David Miller. Changes since RFC: Set msg->msg_name = NULL if user specified a NULL in msg_name but had a non-null msg_namelen in verify_iovec/verify_compat_iovec. This doesn't affect sendto as it would bail out earlier while trying to copy-in the address. It also more naturally reflects the logic by the callers of verify_iovec. With this change in place I could remove " if (!uaddr || msg_sys->msg_namelen == 0) msg->msg_name = NULL ". This change does not alter the user visible error logic as we ignore msg_namelen as long as msg_name is NULL. Also remove two unnecessary curly brackets in ___sys_recvmsg and change comments to netdev style. Cc: David Miller <davem@davemloft.net> Suggested-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-08-29net: packet: use reciprocal_divide in fanout_demux_hashDaniel Borkmann
Instead of hard-coding reciprocal_divide function, use the inline function from reciprocal_div.h. Signed-off-by: Daniel Borkmann <dborkman@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-08-29net: packet: add randomized fanout schedulerDaniel Borkmann
We currently allow for different fanout scheduling policies in pf_packet such as scheduling by skb's rxhash, round-robin, by cpu, and rollover. Also allow for a random, equidistributed selection of the socket from the fanout process group. Signed-off-by: Daniel Borkmann <dborkman@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-08-26Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/netDavid S. Miller
Conflicts: drivers/net/wireless/iwlwifi/pcie/trans.c include/linux/inetdevice.h The inetdevice.h conflict involves moving the IPV4_DEVCONF values into a UAPI header, overlapping additions of some new entries. The iwlwifi conflict is a context overlap. Signed-off-by: David S. Miller <davem@davemloft.net>
2013-08-20packet: restore packet statistics tp_packets to include dropsWillem de Bruijn
getsockopt PACKET_STATISTICS returns tp_packets + tp_drops. Commit ee80fbf301 ("packet: account statistics only in tpacket_stats_u") cleaned up the getsockopt PACKET_STATISTICS code. This also changed semantics. Historically, tp_packets included tp_drops on return. The commit removed the line that adds tp_drops into tp_packets. This patch reinstates the old semantics. Signed-off-by: Willem de Bruijn <willemb@google.com> Acked-by: Daniel Borkmann <dborkman@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-08-10net: attempt high order allocations in sock_alloc_send_pskb()Eric Dumazet
Adding paged frags skbs to af_unix sockets introduced a performance regression on large sends because of additional page allocations, even if each skb could carry at least 100% more payload than before. We can instruct sock_alloc_send_pskb() to attempt high order allocations. Most of the time, it does a single page allocation instead of 8. I added an additional parameter to sock_alloc_send_pskb() to let other users to opt-in for this new feature on followup patches. Tested: Before patch : $ netperf -t STREAM_STREAM STREAM STREAM TEST Recv Send Send Socket Socket Message Elapsed Size Size Size Time Throughput bytes bytes bytes secs. 10^6bits/sec 2304 212992 212992 10.00 46861.15 After patch : $ netperf -t STREAM_STREAM STREAM STREAM TEST Recv Send Send Socket Socket Message Elapsed Size Size Size Time Throughput bytes bytes bytes secs. 10^6bits/sec 2304 212992 212992 10.00 57981.11 Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: David Rientjes <rientjes@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-08-07packet: Revert recent header parsing changes.David S. Miller
This reverts commits: 0f75b09c798ed00c30d7d5551b896be883bc2aeb cbd89acb9eb257ed3b2be867142583fdcf7fdc5b c483e02614551e44ced3fe6eedda8e36d3277ccc Amongst other things, it's modifies the SKB header to pull the ethernet headers off via eth_type_trans() on the output path which is bogus. It's causing serious regressions for people. Signed-off-by: David S. Miller <davem@davemloft.net>
2013-08-02af_packet: simplify VLAN frame check in packet_sndPhil Sutter
For ethernet frames, eth_type_trans() already parses the header, so one can skip this when checking the frame size. Signed-off-by: Phil Sutter <phil@nwl.cc> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-08-02af_packet: fix for sending VLAN frames via packet_mmapPhil Sutter
Since tpacket_fill_skb() parses the protocol field in ethernet frames' headers, it's easy to see if any passed frame is a VLAN one and account for the extended size. But as the real protocol does not turn up before tpacket_fill_skb() runs which in turn also checks the frame length, move the max frame length calculation into the function. Signed-off-by: Phil Sutter <phil@nwl.cc> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-08-02af_packet: when sending ethernet frames, parse header for skb->protocolPhil Sutter
This may be necessary when the SKB is passed to other layers on the go, which check the protocol field on their own. An example is a VLAN packet sent out using AF_PACKET on a bridge interface. The bridging code checks the SKB size, accounting for any VLAN header only if the protocol field is set accordingly. Note that eth_type_trans() sets skb->dev to the passed argument, so this can be skipped in packet_snd() for ethernet frames, as well. Signed-off-by: Phil Sutter <phil@nwl.cc> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-07-22net: Provide a generic socket error queue delivery method for Tx time stamps.Richard Cochran
This patch moves the private error queue delivery function from the af_packet code to the core socket method. In this way, network layers only needing the error queue for transmit time stamping can share common code. Signed-off-by: Richard Cochran <richardcochran@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-06-19Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/netDavid S. Miller
Conflicts: drivers/net/wireless/ath/ath9k/Kconfig drivers/net/xen-netback/netback.c net/batman-adv/bat_iv_ogm.c net/wireless/nl80211.c The ath9k Kconfig conflict was a change of a Kconfig option name right next to the deletion of another option. The xen-netback conflict was overlapping changes involving the handling of the notify list in xen_netbk_rx_action(). Batman conflict resolution provided by Antonio Quartulli, basically keep everything in both conflict hunks. The nl80211 conflict is a little more involved. In 'net' we added a dynamic memory allocation to nl80211_dump_wiphy() to fix a race that Linus reported. Meanwhile in 'net-next' the handlers were converted to use pre and post doit handlers which use a flag to determine whether to hold the RTNL mutex around the operation. However, the dump handlers to not use this logic. Instead they have to explicitly do the locking. There were apparent bugs in the conversion of nl80211_dump_wiphy() in that we were not dropping the RTNL mutex in all the return paths, and it seems we very much should be doing so. So I fixed that whilst handling the overlapping changes. To simplify the initial returns, I take the RTNL mutex after we try to allocate 'tb'. Signed-off-by: David S. Miller <davem@davemloft.net>
2013-06-13packet: packet_getname_spkt: make sure string is always 0-terminatedDaniel Borkmann
uaddr->sa_data is exactly of size 14, which is hard-coded here and passed as a size argument to strncpy(). A device name can be of size IFNAMSIZ (== 16), meaning we might leave the destination string unterminated. Thus, use strlcpy() and also sizeof() while we're at it. We need to memset the data area beforehand, since strlcpy does not padd the remaining buffer with zeroes for user space, so that we do not possibly leak anything. Signed-off-by: Daniel Borkmann <dborkman@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-05-28net: pass info struct via netdevice notifierJiri Pirko
So far, only net_device * could be passed along with netdevice notifier event. This patch provides a possibility to pass custom structure able to provide info that event listener needs to know. Signed-off-by: Jiri Pirko <jiri@resnulli.us> v2->v3: fix typo on simeth shortened dev_getter shortened notifier_info struct name v1->v2: fix notifier_call parameter in call_netdevice_notifier() Signed-off-by: David S. Miller <davem@davemloft.net>
2013-05-03packet: tpacket_v3: do not trigger bug() on wrong header statusDaniel Borkmann
Jakub reported that it is fairly easy to trigger the BUG() macro from user space with TPACKET_V3's RX_RING by just giving a wrong header status flag. We already had a similar situation in commit 7f5c3e3a80e6654 (``af_packet: remove BUG statement in tpacket_destruct_skb'') where this was the case in the TX_RING side that could be triggered from user space. So really, don't use BUG() or BUG_ON() unless there's really no way out, and i.e. don't use it for consistency checking when there's user space involved, no excuses, especially not if you're slapping the user with WARN + dump_stack + BUG all at once. The two functions are of concern: prb_retire_current_block() [when block status != TP_STATUS_KERNEL] prb_open_block() [when block_status != TP_STATUS_KERNEL] Calls to prb_open_block() are guarded by ealier checks if block_status is really TP_STATUS_KERNEL (racy!), but the first one BUG() is easily triggable from user space. System behaves still stable after they are removed. Also remove that yoda condition entirely, since it's already guarded. Reported-by: Jakub Zawadzki <darkjames-ws@darkjames.pl> Signed-off-by: Daniel Borkmann <dborkman@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-04-29sock_diag: allow to dump bpf filtersNicolas Dichtel
This patch allows to dump BPF filters attached to a socket with SO_ATTACH_FILTER. Note that we check CAP_SYS_ADMIN before allowing to dump this info. For now, only AF_PACKET sockets use this feature. Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-04-29packet_diag: disclose meminfo valuesNicolas Dichtel
sk_rmem_alloc is disclosed via /proc/net/packet but not via netlink messages. The goal is to have the same level of information. Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com> Signed-off-by: David S. Miller <davem@davemloft.net>