aboutsummaryrefslogtreecommitdiff
path: root/net
AgeCommit message (Collapse)AuthorFilesLines
2011-03-07ipv4: Inline fib_semantic_match into check_leafDavid S. Miller3-75/+51
This elimiates a lot of pure overhead due to parameter passing. Signed-off-by: David S. Miller <[email protected]>
2011-03-07ipv4: Validate route entry type at insert instead of every lookup.David S. Miller1-26/+28
fib_semantic_match() requires that if the type doesn't signal an automatic error, it must be of type RTN_UNICAST, RTN_LOCAL, RTN_BROADCAST, RTN_ANYCAST, or RTN_MULTICAST. Checking this every route lookup is pointless work. Instead validate it during route insertion, via fib_create_info(). Also, there was nothing making sure the type value was less than RTN_MAX, so add that missing check while we're here. Signed-off-by: David S. Miller <[email protected]>
2011-03-07net: Enter net/ipv6/ even if CONFIG_IPV6=nThomas Graf1-3/+1
exthdrs_core.c and addrconf_core.c in net/ipv6/ contain bits which must be made available even if IPv6 is disabled. net/ipv6/Makefile already correctly includes them if CONFIG_IPV6=n but net/Makefile prevents entering the subdirectory. Signed-off-by: Thomas Graf <[email protected]> Acked-by: Randy Dunlap <[email protected]> Signed-off-by: David S. Miller <[email protected]>
2011-03-07mac80211: fix scan race, simplify codeJohannes Berg1-40/+24
The scan code has a race that Michael reported he ran into, but it's easy to fix while at the same time simplifying the code. The race resulted in the following warning: ------------[ cut here ]------------ WARNING: at net/mac80211/scan.c:310 ieee80211_rx_bss_free+0x20c/0x4b8 [mac80211]() Modules linked in: [...] [<c0033edc>] (unwind_backtrace+0x0/0xe0) from [<c004f2a4>] (warn_slowpath_common+0x4c/0x64) [... backtrace wasn't useful ...] Reported-by: Michael Buesch <[email protected]> Signed-off-by: Johannes Berg <[email protected]> Signed-off-by: John W. Linville <[email protected]>
2011-03-07mac80211: Add log message to ieee80211_restart_hw()Michael Buesch1-0/+3
Add a log message to ieee80211_restart_hw() to highlight that special codepath in the logs. This helps debugging bugs in the rarely tested restart code. Signed-off-by: Michael Buesch <[email protected]> Signed-off-by: John W. Linville <[email protected]>
2011-03-07mac80211: remove unused macrosShan Wei3-5/+0
Compile test only. Signed-off-by: Shan Wei <[email protected]> Signed-off-by: John W. Linville <[email protected]>
2011-03-07gss:krb5 only include enctype numbers in gm_upcall_enctypesKevin Coffman2-2/+2
Make the value in gm_upcall_enctypes just the enctype values. This allows the values to be used more easily elsewhere. Signed-off-by: Kevin Coffman <[email protected]> Signed-off-by: J. Bruce Fields <[email protected]>
2011-03-07Merge branch 'batman-adv/next' of git://git.open-mesh.org/ecsv/linux-mergeDavid S. Miller24-1232/+1634
2011-03-05Merge branch 'for-linus' of ↵Linus Torvalds2-22/+67
git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client * 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client: ceph: no .snap inside of snapped namespace libceph: fix msgr standby handling libceph: fix msgr keepalive flag libceph: fix msgr backoff libceph: retry after authorization failure libceph: fix handling of short returns from get_user_pages ceph: do not clear I_COMPLETE from d_release ceph: do not set I_COMPLETE Revert "ceph: keep reference to parent inode on ceph_dentry"
2011-03-05batman-adv: Disallow regular interface as mesh deviceSven Eckelmann3-12/+36
When trying to associate a net_device with another net_device which already exists, batman-adv assumes that this interface is a fully initialized batman mesh interface without checking it. The behaviour when accessing data behind netdev_priv of a random net_device is undefined and potentially dangerous. Reported-by: Linus Lüssing <[email protected]> Signed-off-by: Marek Lindner <[email protected]>
2011-03-05batman-adv: Remove unused hdr_size variable in route_unicast_packet()Linus Lüssing3-7/+5
Signed-off-by: Linus Lüssing <[email protected]> Signed-off-by: Marek Lindner <[email protected]>
2011-03-05batman-adv: rename batman_if struct to hard_ifaceMarek Lindner18-330/+335
Signed-off-by: Marek Lindner <[email protected]>
2011-03-05batman-adv: rename global if_list to hardif_listMarek Lindner6-22/+22
Batman-adv works with "hard interfaces" as well as "soft interfaces". The new name should better make clear which kind of interfaces this list stores. Signed-off-by: Marek Lindner <[email protected]>
2011-03-05batman-adv: remove orig_hash spinlockMarek Lindner7-148/+38
Signed-off-by: Marek Lindner <[email protected]>
2011-03-05batman-adv: increase refcount in create_neighbor to be consistentMarek Lindner2-37/+30
Signed-off-by: Marek Lindner <[email protected]>
2011-03-05batman-adv: Correct rcu refcounting for orig_nodeMarek Lindner9-36/+49
It might be possible that 2 threads access the same data in the same rcu grace period. The first thread calls call_rcu() to decrement the refcount and free the data while the second thread increases the refcount to use the data. To avoid this race condition all refcount operations have to be atomic. Reported-by: Sven Eckelmann <[email protected]> Signed-off-by: Marek Lindner <[email protected]>
2011-03-05batman-adv: remove extra layer between hash and hash element - hash bucketMarek Lindner10-294/+298
Signed-off-by: Marek Lindner <[email protected]>
2011-03-05batman-adv: separate ethernet comparing calls from hash functionsMarek Lindner8-42/+51
Note: The function compare_ether_addr() provided by the Linux kernel requires aligned memory. Signed-off-by: Marek Lindner <[email protected]>
2011-03-05batman-adv: Fix possible buffer overflow in softif neigh list outputLinus Lüssing1-21/+1
When printing the soft interface table the number of entries in the softif neigh list are first being counted and a fitting buffer allocated. After that the softif neigh list gets locked again and the buffer printed - which has the following two issues: For one thing, the softif neigh list might have grown when reacquiring the rcu lock, which results in writing outside of the allocated buffer. Furthermore 31 Bytes are not enough for printing an entry with a vid of more than 2 digits. The manual buffering is unnecessary, we can safely print to the seq directly during the rcu_read_lock(). Signed-off-by: Linus Lüssing <[email protected]> Signed-off-by: Marek Lindner <[email protected]>
2011-03-05batman-adv: Increase orig_node refcount before releasing rcu read lockLinus Lüssing2-3/+5
When unicast_send_skb() is increasing the orig_node's refcount another thread might have been freeing this orig_node already. We need to increase the refcount in the rcu read lock protected area to avoid that. Signed-off-by: Linus Lüssing <[email protected]> Signed-off-by: Marek Lindner <[email protected]>
2011-03-05batman-adv: Make bat_priv->curr_gw an rcu protected pointerLinus Lüssing2-32/+72
The rcu protected macros rcu_dereference() and rcu_assign_pointer() for the bat_priv->curr_gw need to be used, as well as spin/rcu locking. Otherwise we might end up using a curr_gw pointer pointing to already freed memory. Reported-by: Sven Eckelmann <[email protected]> Signed-off-by: Linus Lüssing <[email protected]> Signed-off-by: Marek Lindner <[email protected]>
2011-03-05batman-adv: make broadcast seqno operations atomicMarek Lindner3-22/+37
Batman-adv could receive several payload broadcasts at the same time that would trigger access to the broadcast seqno sliding window to determine whether this is a new broadcast or not. If these incoming broadcasts are accessing the sliding window simultaneously it could be left in an inconsistent state. Therefore it is necessary to make sure this access is atomic. Reported-by: Linus Lüssing <[email protected]> Signed-off-by: Marek Lindner <[email protected]>
2011-03-05batman-adv: protect bit operations to count OGMs with spinlockMarek Lindner2-34/+33
Reported-by: Linus Lüssing <[email protected]> Signed-off-by: Marek Lindner <[email protected]>
2011-03-05batman-adv: Correct rcu refcounting for batman_ifMarek Lindner4-38/+33
It might be possible that 2 threads access the same data in the same rcu grace period. The first thread calls call_rcu() to decrement the refcount and free the data while the second thread increases the refcount to use the data. To avoid this race condition all refcount operations have to be atomic. Reported-by: Sven Eckelmann <[email protected]> Signed-off-by: Marek Lindner <[email protected]>
2011-03-05batman-adv: Correct rcu refcounting for softif_neighMarek Lindner2-17/+16
It might be possible that 2 threads access the same data in the same rcu grace period. The first thread calls call_rcu() to decrement the refcount and free the data while the second thread increases the refcount to use the data. To avoid this race condition all refcount operations have to be atomic. Reported-by: Sven Eckelmann <[email protected]> Signed-off-by: Marek Lindner <[email protected]>
2011-03-05batman-adv: Correct rcu refcounting for gw_nodeMarek Lindner2-22/+17
It might be possible that 2 threads access the same data in the same rcu grace period. The first thread calls call_rcu() to decrement the refcount and free the data while the second thread increases the refcount to use the data. To avoid this race condition all refcount operations have to be atomic. Reported-by: Sven Eckelmann <[email protected]> Signed-off-by: Marek Lindner <[email protected]>
2011-03-05batman-adv: Correct rcu refcounting for neigh_nodeMarek Lindner7-174/+313
It might be possible that 2 threads access the same data in the same rcu grace period. The first thread calls call_rcu() to decrement the refcount and free the data while the second thread increases the refcount to use the data. To avoid this race condition all refcount operations have to be atomic. Reported-by: Sven Eckelmann <[email protected]> Signed-off-by: Marek Lindner <[email protected]>
2011-03-05batman-adv: protect bonding with rcu locksSimon Wunderlich7-163/+195
bonding / alternating candidates need to be secured by rcu locks as well. This patch therefore converts the bonding list from a plain pointer list to a rcu securable lists and references the bonding candidates. Signed-off-by: Simon Wunderlich <[email protected]> Signed-off-by: Marek Lindner <[email protected]>
2011-03-05batman-adv: protect ogm counter arrays with spinlockMarek Lindner3-6/+33
Signed-off-by: Marek Lindner <[email protected]>
2011-03-05batman-adv: protect originator nodes with reference countersMarek Lindner4-19/+78
Signed-off-by: Marek Lindner <[email protected]>
2011-03-05batman-adv: protect each hash row with rcu locksMarek Lindner8-45/+141
Signed-off-by: Marek Lindner <[email protected]>
2011-03-05batman-adv: protect neigh_nodes used outside of rcu_locks with refcountingMarek Lindner1-9/+31
Signed-off-by: Marek Lindner <[email protected]>
2011-03-05batman-adv: free neighbors when an interface is deactivatedMarek Lindner1-2/+7
hardif_disable_interface() calls purge_orig_ref() to immediately free all neighbors associated with the interface that is going down. purge_orig_neighbors() checked if the interface status is IF_INACTIVE which is set to IF_NOT_IN_USE shortly before calling purge_orig_ref(). Signed-off-by: Marek Lindner <[email protected]>
2011-03-05batman-adv: protect neighbor list with rcu locksMarek Lindner3-21/+57
Signed-off-by: Marek Lindner <[email protected]>
2011-03-05batman-adv: convert neighbor list to hlistMarek Lindner3-28/+35
Signed-off-by: Marek Lindner <[email protected]>
2011-03-05batman-adv: protect neighbor nodes with reference countersMarek Lindner4-8/+28
Signed-off-by: Marek Lindner <[email protected]>
2011-03-05ipx: remove the BKLArnd Bergmann2-33/+20
This replaces all instances of lock_kernel in the IPX code with lock_sock. As far as I can tell, this is safe to do, because there is no global state that needs to be locked in IPX, and the code does not recursively take the lock or sleep indefinitely while holding it. Compile-tested only. Signed-off-by: Arnd Bergmann <[email protected]> Acked-by: David S. Miller <[email protected]> Cc: Arnaldo Carvalho de Melo <[email protected]> Cc: [email protected]
2011-03-05appletalk: remove the BKLArnd Bergmann1-24/+16
This changes appletalk to use lock_sock instead of lock_kernel for serialization. I tried to make sure that we don't hold the socket lock during sleeping functions, but I did not try to prove whether the locks are necessary in the first place. Compile-tested only. Signed-off-by: Arnd Bergmann <[email protected]> Acked-by: David S. Miller <[email protected]> Cc: Arnaldo Carvalho de Melo <[email protected]> Cc: David Miller <[email protected]> Cc: [email protected]
2011-03-05x25: remove the BKLArnd Bergmann3-43/+23
This replaces all instances of lock_kernel in x25 with lock_sock, taking care to release the socket lock around sleeping functions (sock_alloc_send_skb and skb_recv_datagram). It is not clear whether this is a correct solution, but it seem to be what other protocols do in the same situation. Includes a fix suggested by Eric Dumazet. Signed-off-by: Arnd Bergmann <[email protected]> Acked-by: David S. Miller <[email protected]> Tested-by: Andrew Hendry <[email protected]> Cc: [email protected] Cc: [email protected] Cc: Eric Dumazet <[email protected]>
2011-03-04ipv4: Remove flowi from struct rtable.David S. Miller6-85/+133
The only necessary parts are the src/dst addresses, the interface indexes, the TOS, and the mark. The rest is unnecessary bloat, which amounts to nearly 50 bytes on 64-bit. Signed-off-by: David S. Miller <[email protected]>
2011-03-04ipv4: Set rt->rt_iif more sanely on output routes.David S. Miller1-1/+1
rt->rt_iif is only ever inspected on input routes, for example DCCP uses this to populate a route lookup flow key when generating replies to another packet. Therefore, setting it to anything other than zero on output routes makes no sense. Signed-off-by: David S. Miller <[email protected]>
2011-03-04ipv4: Get peer more cheaply in rt_init_metrics().David S. Miller1-2/+2
We know this is a new route object, so doing atomics and stuff makes no sense at all. Signed-off-by: David S. Miller <[email protected]>
2011-03-04ipv4: Optimize flow initialization in output route lookup.David S. Miller1-8/+10
We burn a lot of useless cycles, cpu store buffer traffic, and memory operations memset()'ing the on-stack flow used to perform output route lookups in __ip_route_output_key(). Only the first half of the flow object members even matter for output route lookups in this context, specifically: FIB rules matching cares about: dst, src, tos, iif, oif, mark FIB trie lookup cares about: dst FIB semantic match cares about: tos, scope, oif Therefore only initialize these specific members and elide the memset entirely. On Niagara2 this kills about ~300 cycles from the output route lookup path. Likely, we can take things further, since all callers of output route lookups essentially throw away the on-stack flow they use. So they don't care if we use it as a scratch-pad to compute the final flow key. Signed-off-by: David S. Miller <[email protected]> Acked-by: Eric Dumazet <[email protected]>
2011-03-04inetpeer: seqlock optimizationEric Dumazet1-40/+35
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 <[email protected]> Signed-off-by: David S. Miller <[email protected]>
2011-03-04Merge branch 'for-davem' of ↵David S. Miller14-159/+266
ssh://master.kernel.org/pub/scm/linux/kernel/git/linville/wireless-next-2.6
2011-03-04libceph: fix msgr standby handlingSage Weil1-8/+22
The standby logic used to be pretty dependent on the work requeueing behavior that changed when we switched to WQ_NON_REENTRANT. It was also very fragile. Restructure things so that: - We clear WRITE_PENDING when we set STANDBY. This ensures we will requeue work when we wake up later. - con_work backs off if STANDBY is set. There is nothing to do if we are in standby. - clear_standby() helper is called by both con_send() and con_keepalive(), the two actions that can wake us up again. Move the connect_seq++ logic here. Signed-off-by: Sage Weil <[email protected]>
2011-03-04libceph: fix msgr keepalive flagSage Weil1-5/+4
There was some broken keepalive code using a dead variable. Shift to using the proper bit flag. Signed-off-by: Sage Weil <[email protected]>
2011-03-04libceph: fix msgr backoffSage Weil1-2/+28
With commit f363e45f we replaced a bunch of hacky workqueue mutual exclusion logic with the WQ_NON_REENTRANT flag. One pieces of fallout is that the exponential backoff breaks in certain cases: * con_work attempts to connect. * we get an immediate failure, and the socket state change handler queues immediate work. * con_work calls con_fault, we decide to back off, but can't queue delayed work. In this case, we add a BACKOFF bit to make con_work reschedule delayed work next time it runs (which should be immediately). Signed-off-by: Sage Weil <[email protected]>
2011-03-04Merge branch 'master' of ↵John W. Linville14-159/+266
git://git.kernel.org/pub/scm/linux/kernel/git/linville/wireless-next-2.6 into for-davem
2011-03-04mac80211: Remove redundant preamble and RTS flag setup in minstrel_htHelmut Schaa1-3/+1
mac80211 does the same afterwards anyway. Hence, just drop this redundant code. Signed-off-by: Helmut Schaa <[email protected]> Acked-by: Felix Fietkau <[email protected]> Signed-off-by: John W. Linville <[email protected]>
Powered by cgit, Gruvboxed by Blaster4385.