- 20 Mar, 2015 18 commits
-
-
Lendacky, Thomas authored
With ethtool being able to control what is advertised, the advertising field is what should be used for priming the auto-negotiation registers and for various other checks, instead of the supported field. Also, move the initial setting of the supported and advertising fields into the probe function so that they are not reset each time the device is brought up, thus allowing the user to set as desired before bringing the device up. Signed-off-by:
Tom Lendacky <thomas.lendacky@amd.com> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
David S. Miller authored
Herbert Xu says: ==================== rhashtable: Introduce inlined interface This series of patches introduces the inlined rhashtable interface. The idea is to make all the function pointers visible to the compiler by providing the rhashtable_params structure explicitly to each inline rhashtable function. For example, instead of doing obj = rhashtable_lookup(ht, key); you would now do obj = rhashtable_lookup_fast(ht, key, params); Where params is the same data that you would give to rhashtable_init. In particular, within rhashtable.c itself we would simply supply ht->p. So to convert users over, you simply have to make params globally accessible, e.g., by placing it in a static const variable, which can then be used at each inlined call site, as well as by the rhashtable_init call. The only ticky bit is that some users (i.e., netfilter) has a dynamic key length. This is dealt with by using params.key_len in the inline functions when it is non-zero, and otherwise falling back on ht->p.key_len. Note that I've only tested this on one compiler, gcc 4.7.2. So please test this with your compilers as well and make sure that the code is actually inlined without indirect function calls. ==================== Signed-off-by: -
Herbert Xu authored
Now that all rhashtable users have been converted over to the inline interface, this patch removes the unused out-of-line interface. Signed-off-by:
Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by:
-
Herbert Xu authored
This patch converts tipc to the inlined rhashtable interface. Signed-off-by:
-
Herbert Xu authored
This patch converts test_rhashtable to the inlined rhashtable interface. Signed-off-by:
-
Herbert Xu authored
This patch converts nft_hash to the inlined rhashtable interface. This patch also replaces the call to rhashtable_lookup_compare with a straight rhashtable_lookup_fast because it's simply doing a memcmp (in fact nft_hash_lookup already uses memcmp instead of nft_data_cmp). Furthermore, the compare function is only meant to compare, it is not supposed to have side-effects. The current side-effect code can simply be moved into the nft_hash_get. Signed-off-by:
-
Herbert Xu authored
Currently the name space is a de facto key because it has to match before we find an object in the hash table. However, it isn't in the hash value so all objects from different name spaces with the same port ID hash to the same bucket. This is bad as the number of name spaces is unbounded. This patch fixes this by using the namespace when doing the hash. Because the namespace field doesn't lie next to the portid field in the netlink socket, this patch switches over to the rhashtable interface without a fixed key. This patch also uses the new inlined rhashtable interface where possible. Signed-off-by:
-
Herbert Xu authored
This patch deals with the complaint that we make indirect function calls on the fast paths unnecessarily in rhashtable. We resolve it by moving the fast paths into inline functions that take struct rhashtable_param (which obviously must be the same set of parameters supplied to rhashtable_init) as an argument. The only remaining indirect call is to obj_hashfn (or key_hashfn it obj_hashfn is unset) on the rehash as well as the insert-during- rehash slow path. This patch also extends the support of vairable-length keys to include those where the key is fixed but scattered in the object. For example, in netlink we want to key off the namespace and the portid but they're not next to each other. This patch does this by directly using the object hash function as the indicator of whether the key is accessible or not. It also adds a new function obj_cmpfn to compare a key against an object. This means that the caller no longer needs to supply explicit compare functions. All this is done in a backwards compatible manner so no existing users are affected until they convert to the new interface. Signed-off-by:
-
Herbert Xu authored
This patch marks the rhashtable_init params argument const as there is no reason to modify it since we will always make a copy of it in the rhashtable. This patch also fixes a bug where we don't actually round up the value of min_size unless it is less than HASH_MIN_SIZE. Signed-off-by:
Thomas Graf <tgraf@suug.ch> Signed-off-by:
-
Daniel Borkmann authored
Commit c2497395 ("bpf: allow BPF programs access 'protocol' and 'vlan_tci' fields") has added support for accessing protocol, vlan_present and vlan_tci into the skb offset map. As referenced in the below discussion, accessing skb->protocol from an eBPF program should be converted without handling endianess. The reason for this is that an eBPF program could simply do a check more naturally, by f.e. testing skb->protocol == htons(ETH_P_IP), where the LLVM compiler resolves htons() against a constant automatically during compilation time, as opposed to an otherwise needed run time conversion. After all, the way of programming both from a user perspective differs quite a lot, i.e. bpf_asm ["ld proto"] versus a C subset/LLVM. Reference: https://patchwork.ozlabs.org/patch/450819/Signed-off-by:
Daniel Borkmann <daniel@iogearbox.net> Acked-by:
Alexei Starovoitov <ast@plumgrid.com> Signed-off-by:
-
Marcelo Ricardo Leitner authored
Commit baf606d9 ("ipv4,ipv6: grab rtnl before locking the socket") missed to update two setsockopt options, IPV6_JOIN_ANYCAST and IPV6_LEAVE_ANYCAST, causing a lock inverstion regarding to the updated ones. As ipv6_sock_ac_join and ipv6_sock_ac_leave are only called from do_ipv6_setsockopt, we are good to just move the rtnl lock upper. Fixes: baf606d9 ("ipv4,ipv6: grab rtnl before locking the socket") Reported-by:
Ying Huang <ying.huang@intel.com> Signed-off-by:
Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by:
-
Marcelo Ricardo Leitner authored
Test robot noticed that we check the return of vxlan_igmp_join and leave but inside them there was a path that it could be used initialized. It's not really possible because those if() inside these igmp functions would always match as we can't have sockets of other type in there, but this way we keep the compiler happy. Fixes: 56ef9c90 ("vxlan: Move socket initialization to within rtnl scope") Reported-by:
kbuild test robot <fengguang.wu@intel.com> Signed-off-by:
-
Palik, Imre authored
With the current netback, the bandwidth limiter's parameters are only settable during vif setup time. This patch register a watch on them, and thus makes them runtime changeable. When the watch fires, the timer is reset. The timer's mutex is used for fencing the change. Cc: Anthony Liguori <aliguori@amazon.com> Signed-off-by:
Imre Palik <imrep@amazon.de> Acked-by:
Wei Liu <wei.liu2@citrix.com> Signed-off-by:
-
David S. Miller authored
Eric Dumazet says: ==================== inet: tcp listener refactoring part 14 OK, we have serious patches here. We get rid of the central timer handling SYNACK rtx, which is killing us under even medium SYN flood. We still use the listener specific hash table. This will be done in next round ;) ==================== Signed-off-by: -
Eric Dumazet authored
sk_ack_backlog & sk_max_ack_backlog were 16bit fields, meaning listen() backlog was limited to 65535. It is time to increase the width to allow much bigger backlog, if admins change /proc/sys/net/core/somaxconn & /proc/sys/net/ipv4/tcp_max_syn_backlog default values. Tested: echo 5000000 >/proc/sys/net/core/somaxconn echo 5000000 >/proc/sys/net/ipv4/tcp_max_syn_backlog Ran a SYNFLOOD test against a listener using listen(fd, 5000000) myhost~# grep request_sock_TCP /proc/slabinfo request_sock_TCP 4185642 4411940 304 13 1 : tunables 54 27 8 : slabdata 339380 339380 0 Signed-off-by:
Eric Dumazet <edumazet@google.com> Signed-off-by:
-
Eric Dumazet authored
One of the major issue for TCP is the SYNACK rtx handling, done by inet_csk_reqsk_queue_prune(), fired by the keepalive timer of a TCP_LISTEN socket. This function runs for awful long times, with socket lock held, meaning that other cpus needing this lock have to spin for hundred of ms. SYNACK are sent in huge bursts, likely to cause severe drops anyway. This model was OK 15 years ago when memory was very tight. We now can afford to have a timer per request sock. Timer invocations no longer need to lock the listener, and can be run from all cpus in parallel. With following patch increasing somaxconn width to 32 bits, I tested a listener with more than 4 million active request sockets, and a steady SYNFLOOD of ~200,000 SYN per second. Host was sending ~830,000 SYNACK per second. This is ~100 times more what we could achieve before this patch. Later, we will get rid of the listener hash and use ehash instead. Signed-off-by:
-
Eric Dumazet authored
When request sock are put in ehash table, the whole notion of having a previous request to update dl_next is pointless. Also, following patch will get rid of big purge timer, so we want to delete a request sock without holding listener lock. Signed-off-by:
-
Thomas Graf authored
Round up min_size respectively round down max_size to the next power of two to make sure we always respect the limit specified by the user. This is required because we compare the table size against the limit before we expand or shrink. Also fixes a minor bug where we modified min_size in the params provided instead of the copy stored in struct rhashtable. Signed-off-by:
-
- 19 Mar, 2015 22 commits
-
-
Shannon Nelson authored
Quit complaining about a couple of events that we actually expect to see during an NVM update. Reported-by:
Stefan Assmann <sassmann@redhat.com> Signed-off-by:
Shannon Nelson <shannon.nelson@intel.com> Tested-by:
Jim Young <james.m.young@intel.com> Signed-off-by:
Jeff Kirsher <jeffrey.t.kirsher@intel.com> Signed-off-by:
-
Marcelo Ricardo Leitner authored
We can't directly call ipv6_sock_mc_join() but should use the stub instead and protect it around IS_ENABLED. Fixes: d0f91938 ("tipc: add ip/udp media type") Signed-off-by:
-
David S. Miller authored
Hariprasad Shenai says: ==================== Add Device ID and make device ID table const This patch series adds new device ID and makes device ID table const The patches series is created against 'net-next' tree. And includes patches on cxgb4 and csiostor driver. We have included all the maintainers of respective drivers. Kindly review the change and let us know in case of any review comments. ==================== Signed-off-by: -
Hariprasad Shenai authored
Make PCI Device ID Tables be "const" to move them out of the data segment and remove a redundant check on CH_PCI_DEVICE_ID_TABLE_DEFINE_BEGIN in t4_pci_id_tbl.h to guard the contents of the include file. Signed-off-by:
Casey Leedom <leedom@chelsio.com> Signed-off-by:
Hariprasad Shenai <hariprasad@chelsio.com> Signed-off-by:
-
Hariprasad Shenai authored
Signed-off-by:
-
David S. Miller authored
Merge branch 'for-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/bluetooth/bluetooth-next Johan Hedberg says: ==================== pull request: bluetooth-next 2015-03-19 This wont the last 4.1 bluetooth-next pull request, but we've piled up enough patches in less than a week that I wanted to save you from a single huge "last-minute" pull somewhere closer to the merge window. The main changes are: - Simultaneous LE & BR/EDR discovery support for HW that can do it - Complete LE OOB pairing support - More fine-grained mgmt-command access control (normal user can now do harmless read-only operations). - Added RF power amplifier support in cc2520 ieee802154 driver - Some cleanups/fixes in ieee802154 code Please let me know if there are any issues pulling. Thanks. ==================== Signed-off-by:
-
David S. Miller authored
Erik Hugne says: ==================== tipc: small bugfix an support for datagram connect() Most notable in this series is patch#3 that allows programs to associate a tipc address with a connectionless (RDM/DGRAM) socket. v2: Fix indent issue in patch#3 ==================== Signed-off-by: -
Erik Hugne authored
Following the example of ip4_datagram_connect, we store the address in the socket structure for dgram/rdm sockets and use that as the default destination for subsequent send() calls. It is allowed to connect to any address types, and the behaviour of send() will be the same as a normal sendto() with this address provided. Binding to an AF_UNSPEC address clears the association. Signed-off-by:
Erik Hugne <erik.hugne@ericsson.com> Reviewed-by:
Ying Xue <ying.xue@windriver.com> Reviewed-by:
Jon Maloy <jon.maloy@ericsson.com> Signed-off-by:
-
Erik Hugne authored
Since commit 1186adf7 ("tipc: simplify message forwarding and rejection in socket layer") -EHOSTUNREACH is propagated back to the sending process if we fail to deliver the message to another socket local to the node. This is wrong, host unreachable should only be reported when the destination port/name does not exist in the cluster, and that check is always done before sending the message. Also, this introduces inconsistent sendmsg() behavior for local/remote destinations. Errors occurring on the receiving side should not trickle up to the sender. If message delivery fails TIPC should either discard the packet or reject it back to the sender based on the destination droppable option. Signed-off-by:
-
Erik Hugne authored
tipc_node_remove_conn may be called twice if shutdown() is called on a socket that have messages in the receive queue. Calling this function twice does no harm, but is unnecessary and we remove the redundant call. Signed-off-by:
-
Nicolas Iooss authored
Signed-off-by:
Nicolas Iooss <nicolas.iooss_linux@m4x.org> Fixes: b6eea9ca ("mac802154: introduce driver-ops header") Acked-by:
Alexander Aring <alex.aring@gmail.com> Signed-off-by:
Marcel Holtmann <marcel@holtmann.org>
-
Wu Fengguang authored
Signed-off-by:
-
Jörg Thalheim authored
Signed-off-by:
Jörg Thalheim <joerg@higgsboson.tk> Signed-off-by:
-
David S. Miller authored
When a networking device is taken down that has a non-trivial number of VLAN devices configured under it, we eat a full synchronize_net() for every such VLAN device. This is because of the call chain: NETDEV_DOWN notifier --> vlan_device_event() --> dev_change_flags() --> __dev_change_flags() --> __dev_close() --> __dev_close_many() --> dev_deactivate_many() --> synchronize_net() This is kind of rediculous because we already have infrastructure for batching doing operation X to a list of net devices so that we only incur one sync. So make use of that by exporting dev_close_many() and adjusting it's interfaace so that the caller can fully manage the batch list. Use this in vlan_device_event() and all the overhead goes away. Reported-by:
Salam Noureddine <noureddine@arista.com> Signed-off-by:
-
Eric Dumazet authored
On a large hash table, we can easily spend seconds to walk over all entries. Add a cond_resched() to yield cpu if necessary. Signed-off-by:
-
David Ahern authored
Implement the phys_port_name operation. Port names are pulled from the rocker hardware model in qemu and default to the qemu name + port id. e.g., sw1p1: flags=4098<BROADCAST,MULTICAST> mtu 1500 ether 52:54:00:12:35:01 txqueuelen 1000 (Ethernet) RX packets 0 bytes 0 (0.0 B) RX errors 0 dropped 0 overruns 0 frame 0 TX packets 0 bytes 0 (0.0 B) TX errors 0 dropped 0 overruns 0 carrier 0 collisions 0 where 'sw1' comes from the qemu command line -device rocker,name=sw1, and 'p1' is port 1. Patch is adapted from Scott's phys_port_id patch. Signed-off-by:David Ahern <dsahern@gmail.com> Acked-by:
Scott Feldman <sfeldma@gmail.com> Acked-by:
Jiri Pirko <jiri@resnulli.us> Signed-off-by:
-
David Ahern authored
Similar to port id allow netdevices to specify port names and export the name via sysfs. Drivers can implement the netdevice operation to assist udev in having sane default names for the devices using the rule: $ cat /etc/udev/rules.d/80-net-setup-link.rules SUBSYSTEM=="net", ACTION=="add", ATTR{phys_port_name}!="", NAME="$attr{phys_port_name}" Use of phys_name versus phys_id was suggested-by Jiri Pirko. Signed-off-by: -
Marcelo Ricardo Leitner authored
Currently, if a multicast join operation fail, the vxlan interface will be UP but not functional, without even a log message informing the user. Now that we can grab socket lock after already having rntl, we don't need to defer socket creation and multicast operations. By not deferring we can do proper error reporting to the user through ip exit code. This patch thus removes all deferred work that vxlan had and put it back inline. Now the socket will only be created, bound and join multicast group when one bring the interface up, and will undo all that as soon as one put the interface down. As vxlan_sock_hold() is not used after this patch, it was removed too. Signed-off-by:
-
Marcelo Ricardo Leitner authored
in favor of their inner __ ones, which doesn't grab rtnl. As these functions need to operate on a locked socket, we can't be grabbing rtnl by then. It's too late and doing so causes reversed locking. So this patch: - move rtnl handling to callers instead while already fixing some reversed locking situations, like on vxlan and ipvs code. - renames __ ones to not have the __ mark: __ip_mc_{join,leave}_group -> ip_mc_{join,leave}_group __ipv6_sock_mc_{join,drop} -> ipv6_sock_mc_{join,drop} Signed-off-by:Hannes Frederic Sowa <hannes@stressinduktion.org> Signed-off-by:
-
Marcelo Ricardo Leitner authored
There are some setsockopt operations in ipv4 and ipv6 that are grabbing rtnl after having grabbed the socket lock. Yet this makes it impossible to do operations that have to lock the socket when already within a rtnl protected scope, like ndo dev_open and dev_stop. We normally take coarse grained locks first but setsockopt inverted that. So this patch invert the lock logic for these operations and makes setsockopt grab rtnl if it will be needed prior to grabbing socket lock. Signed-off-by:
-
David S. Miller authored
Eric Dumazet says: ==================== inet: tcp listener refactoring, part 13 inet_hash functions are in a bad state : Too much IPv6/IPv4 copy/pasting. Lets refactor a bit. Idea is that we do not want to have an equivalent of inet_csk(sk)->icsk_af_ops for request socks in order to be able to use the right variant. In this patch series, I started to let IPv6/IPv4 converge to common helpers. Idea is to use ipv6_addr_set_v4mapped() even for AF_INET sockets, so that we can test if (sk->sk_family == AF_INET6 && !ipv6_addr_v4mapped(&sk->sk_v6_daddr)) to tell if we deal with an IPv6 socket, or IPv4 one, at least in slow paths. Ideally, we could save 8 bytes per struct sock_common, if we alias skc_daddr & skc_rcv_saddr to skc_v6_daddr[3]/skc_v6_rcv_saddr[3]. ==================== Signed-off-by: -
Eric Dumazet authored
In order to be able to use sk_ehashfn() for request socks, we need to initialize their IPv6/IPv4 addresses. Signed-off-by:
-
