- 21 Sep, 2017 20 commits
-
-
Allen Pais authored
Use setup_timer function instead of initializing timer with the function and data fields. Signed-off-by:Allen Pais <allen.lkml@gmail.com> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Allen Pais authored
Use setup_timer function instead of initializing timer with the function and data fields. Signed-off-by: -
Allen Pais authored
Use setup_timer function instead of initializing timer with the function and data fields. Signed-off-by: -
David S. Miller authored
Jiri Pirko says: ==================== mlxsw: Multicast flood update Nogah says: Currently, there are four erroneous flows in MC flood: 1. When MC is disabled it affects only the flood table for unregistered MC packets, but packets that match an entry in the MDB are unaffected. 2. When MC is disabled, MC packets are being sent to all the ports in the bridge (like BC and link-local MC packets) regardless of the designated flag (BR_MCAST_FLAG). 3. When a port is being deleted from a bridge it might remain in the MDB. 4. When MC is enabled packets are flooded to the mrouter ports only if they don't match any entry in the MDB, when they should always be flooded to them. What these problems have in common is the discrepancy between how the hardware handles MDB and mcast flood, and how the driver does it. Each of these problems needs fixing either in the MDB code, or in mcast flood code, and some in both. Patches 1-6 change the way the MDB is handled in the driver to make the following changes easier. Patches 7-8 fix problem number 1 by removing the MDB from the HW when MC is being disabled and restoring it when it is being enabled. Patches 9-10 fix problem number 2 by offloading the flood table by the appropriate flag. Patch 11 fixes problem number 3 by adding MDB flush to the port removal. Patches 12-14 fix problem number 4 by adding the mrouter ports to every MDB entry in the HW to mimic the wanted behaviour. ==================== Signed-off-by: -
Nogah Frankel authored
When a mrouter is registered or leaves a mid, don't update the HW. Signed-off-by:
Nogah Frankel <nogahf@mellanox.com> Signed-off-by:
Jiri Pirko <jiri@mellanox.com> Signed-off-by:
-
Nogah Frankel authored
In mdb flush the port is being removed from all the mids it is registered to. But if the port is mrouter, all the mids floods to it. This patch remove mrouter ports from mids it is not registered to in the mdb flush. Signed-off-by:
-
Nogah Frankel authored
Whenever a port starts / stops being mrouter, update all the mdb entries in the HW to flood / stop flooding mc packets there. The change should happen only if the port is not in the mid. (If it is, the mid should flood mc packets to this port anyway) Signed-off-by:
-
Nogah Frankel authored
When mc is enabled, whenever a mc packet doesn't hit any mdb entry it is being flood to the ports marked as mrouters. However, all mc packets should be flooded to them even if they match an entry in the mdb. This patch adds the mrouter ports to every mdb entry that is being written to the HW. Signed-off-by:
-
Nogah Frankel authored
When a port is being removed from a bridge, flush the bridge mdb to remove the mids of that port. Signed-off-by:
-
Nogah Frankel authored
When multicast is disabled, flood mc packets only to port that are marked BR_MCAST_FLOOD (instead to all). Signed-off-by:
-
Nogah Frankel authored
Use the generic mc flood function to decide whether to flood mc to a port when mc is being enabled / disabled. Move this function in the file to avoid forward declaration. Signed-off-by:
-
Nogah Frankel authored
Remove all the mdb entries from the HW when mc is being disabled and re-write them when it is being enabled. Signed-off-by:
-
Nogah Frankel authored
Don't write multicast related data to the HW when mc is disabled. Also, don't allocate mid id to new mids (so the remove function could know that they weren't wrote to the HW) Signed-off-by:
-
Nogah Frankel authored
Break mid deletion into two function, so it will be possible in the future to delete a mid entry for other reasons then switchdev command (like port deletion). Signed-off-by:
-
Nogah Frankel authored
Attach mid getting and releasing mid id to the HW write / remove, and add a flag to indicate whether the mid is in the HW. It is done because mid id is also HW index to this mid. This change allows adding in the following patches the ability to have a mid in the mdb cache but not in the HW. It will be useful for being able to disable the multicast. It means that the mdb is being written / delete to the HW in the mid allocation / removing function, not after them. Signed-off-by:
-
Nogah Frankel authored
Break the smid write function into two, one that cleans the ports that might be still written there and one that changes an exiting mid entry. Signed-off-by:
-
Nogah Frankel authored
Instead of saving all the mids in the same list, save them per vlan device. This change allows a more efficient mid find. Also, in the next patches, there will be added a lot of loops over all the mids in bridge device for multicast disable, mrouter change and ndb flush. Signed-off-by:
-
Nogah Frankel authored
Since there is a bitmap for the ports registered to each mid, there is no need for a ref count, since it will always be the number of set bits in this bitmap. Any check of the ref count was replaced with checking if the bitmap is empty. Signed-off-by:
-
Nogah Frankel authored
Add a bitmap of ports to the mid struct to hold the ports that are registered to this mid. Signed-off-by:
-
Nogah Frankel authored
Change the naming of mc_router to mrouter to keep consistency. Signed-off-by:
-
- 20 Sep, 2017 14 commits
-
-
Ganesh Goudar authored
Add 0x50a5, 0x50a6, 0x50a7, 0x50a8 and 0x50a9 T5 device id's. Signed-off-by:
Ganesh Goudar <ganeshgr@chelsio.com> Signed-off-by:
-
David S. Miller authored
Florian Fainelli says: ==================== blackfin: Drop non-functional DSA code I sent those many months ago in the hope that the bfin-linux people would pick those patches but nobody seems to be responding, can you queue those via net-next since this affects DSA? ==================== Signed-off-by: -
Florian Fainelli authored
There is no in tree driver for the KSZ8893M switch driver, so just get rid of the code in that board file. Signed-off-by:
Florian Fainelli <f.fainelli@gmail.com> Signed-off-by:
-
Florian Fainelli authored
Nothing in that file uses definitions from that header, so just get rid of it. Signed-off-by:
-
Florian Fainelli authored
Instead of open coding the check. Signed-off-by:
Vivien Didelot <vivien.didelot@savoirfairelinux.com> Signed-off-by:
-
David S. Miller authored
This reverts commit 00ba4cb3. Discussion with David Ahern determined that this change is actually not needed. Signed-off-by:
-
Paolo Abeni authored
The commit 6b229cf7 ("udp: add batching to udp_rmem_release()") reduced greatly the cacheline contention between the BH and the US reader batching the rmem updates in most scenarios. Such optimization is explicitly avoided if the US reader is faster then BH processing. My fault, I initially suggested this kind of behavior due to concerns of possible regressions with small sk_rcvbuf values. Tests showed such concerns are misplaced, so this commit relaxes the condition for rmem bulk updates, obtaining small but measurable performance gain in the scenario described above. Signed-off-by:
Paolo Abeni <pabeni@redhat.com> Signed-off-by:
-
Jason Wang authored
This patch tries to add XDP_REDIRECT for virtio-net. The changes are not complex as we could use exist XDP_TX helpers for most of the work. The rest is passing the XDP_TX to NAPI handler for implementing batching. Cc: John Fastabend <john.fastabend@gmail.com> Signed-off-by:
Jason Wang <jasowang@redhat.com> Signed-off-by:
-
Jason Wang authored
There's no need to add packet len average in the case of XDP_PASS since it will be done soon after skb is created. Cc: John Fastabend <john.fastabend@gmail.com> Signed-off-by:
-
Jason Wang authored
CC: John Fastabend <john.fastabend@gmail.com> Signed-off-by:
-
Egil Hjelmeland authored
Make the driver react to device tree "fixed-link" declaration on CPU port. - turn off autonegotiation - force speed 10 or 100 mb/s - force duplex mode Signed-off-by:
Egil Hjelmeland <privat@egil-hjelmeland.no> Signed-off-by:
-
Vincent Bernat authored
Currently, when an interface is released from a bridge via ioctl(), we get a RTM_DELLINK event through netlink: Deleted 2: dummy0: <BROADCAST,NOARP,UP,LOWER_UP> mtu 1500 master bridge0 state UNKNOWN link/ether 6e:23:c2:54:3a:b3 Userspace has to interpret that as a removal from the bridge, not as a complete removal of the interface. When an bridged interface is completely removed, we get two events: Deleted 2: dummy0: <BROADCAST,NOARP> mtu 1500 master bridge0 state DOWN link/ether 6e:23:c2:54:3a:b3 Deleted 2: dummy0: <BROADCAST,NOARP> mtu 1500 qdisc noop state DOWN group default link/ether 6e:23:c2:54:3a:b3 brd ff:ff:ff:ff:ff:ff In constrast, when an interface is released from a bond, we get a RTM_NEWLINK with only the new characteristics (no master): 3: dummy1: <BROADCAST,NOARP,SLAVE,UP,LOWER_UP> mtu 1500 qdisc noqueue master bond0 state UNKNOWN group default link/ether ae:dc:7a:8c:9a:3c brd ff:ff:ff:ff:ff:ff 3: dummy1: <BROADCAST,NOARP,UP,LOWER_UP> mtu 1500 qdisc noqueue state UNKNOWN group default link/ether ae:dc:7a:8c:9a:3c brd ff:ff:ff:ff:ff:ff 4: bond0: <BROADCAST,MULTICAST,MASTER,UP,LOWER_UP> mtu 1500 qdisc noqueue state UP group default link/ether ae:dc:7a:8c:9a:3c brd ff:ff:ff:ff:ff:ff 3: dummy1: <BROADCAST,NOARP> mtu 1500 qdisc noqueue state DOWN group default link/ether ae:dc:7a:8c:9a:3c brd ff:ff:ff:ff:ff:ff 3: dummy1: <BROADCAST,NOARP> mtu 1500 qdisc noqueue state DOWN group default link/ether ca:c8:7b:66:f8:25 brd ff:ff:ff:ff:ff:ff 4: bond0: <BROADCAST,MULTICAST,MASTER,UP,LOWER_UP> mtu 1500 qdisc noqueue state UP group default link/ether ae:dc:7a:8c:9a:3c brd ff:ff:ff:ff:ff:ff Userland may be confused by the fact we say a link is deleted while its characteristics are only modified. A first solution would have been to turn the RTM_DELLINK event in del_nbp() into a RTM_NEWLINK event. However, maybe some piece of userland is relying on this RTM_DELLINK to detect when a bridged interface is released. Instead, we also emit a RTM_NEWLINK event once the interface is released (without master info). Deleted 2: dummy0: <BROADCAST,NOARP,UP,LOWER_UP> mtu 1500 master bridge0 state UNKNOWN link/ether 8a:bb:e7:94:b1:f8 2: dummy0: <BROADCAST,NOARP,UP,LOWER_UP> mtu 1500 qdisc noqueue state UNKNOWN group default link/ether 8a:bb:e7:94:b1:f8 brd ff:ff:ff:ff:ff:ff This is done only when using ioctl(). When using Netlink, such an event is already automatically emitted in do_setlink(). Signed-off-by:Vincent Bernat <vincent@bernat.im> Signed-off-by:
-
Zhang Shengju authored
This patch checks data first at one place, return if it's null. Signed-off-by:
Zhang Shengju <zhangshengju@cmss.chinamobile.com> Signed-off-by:
-
Xiang Gao authored
In ipv6_skip_exthdr, the lengh of AH header is computed manually as (hp->hdrlen+2)<<2. However, in include/linux/ipv6.h, a macro named ipv6_authlen is already defined for exactly the same job. This commit replaces the manual computation code with the macro. Signed-off-by:
Xiang Gao <qasdfgtyuiop@gmail.com> Signed-off-by:
-
- 19 Sep, 2017 6 commits
-
-
David S. Miller authored
Eric Dumazet says: ==================== net: speedup netns create/delete time When rate of netns creation/deletion is high enough, we observe softlockups in cleanup_net() caused by huge list of netns and way too many rcu_barrier() calls. This patch series does some optimizations in kobject, and add batching to tunnels so that netns dismantles are less costly. IPv6 addrlabels also get a per netns list, and tcp_metrics also benefit from batch flushing. This gives me one order of magnitude gain. (~50 ms -> ~5 ms for one netns create/delete pair) Tested: for i in `seq 1 40` do (for j in `seq 1 100` ; do unshare -n /bin/true >/dev/null ; done) & done wait ; grep net_namespace /proc/slabinfo Before patch series : $ time ./add_del_unshare.sh net_namespace 116 258 5504 1 2 : tunables 8 4 0 : slabdata 116 258 0 real 3m24.910s user 0m0.747s sys 0m43.162s After : $ time ./add_del_unshare.sh net_namespace 135 291 5504 1 2 : tunables 8 4 0 : slabdata 135 291 0 real 0m22.117s user 0m0.728s sys 0m35.328s ==================== Signed-off-by: -
Eric Dumazet authored
Implement exit_batch() method to dismantle more devices per round. (rtnl_lock() ... unregister_netdevice_many() ... rtnl_unlock()) Tested: $ cat add_del_unshare.sh for i in `seq 1 40` do (for j in `seq 1 100` ; do unshare -n /bin/true >/dev/null ; done) & done wait ; grep net_namespace /proc/slabinfo Before patch : $ time ./add_del_unshare.sh net_namespace 126 282 5504 1 2 : tunables 8 4 0 : slabdata 126 282 0 real 1m38.965s user 0m0.688s sys 0m37.017s After patch: $ time ./add_del_unshare.sh net_namespace 135 291 5504 1 2 : tunables 8 4 0 : slabdata 135 291 0 real 0m22.117s user 0m0.728s sys 0m35.328s Signed-off-by:
Eric Dumazet <edumazet@google.com> Signed-off-by:
-
Eric Dumazet authored
Implement exit_batch() method to dismantle more devices per round. (rtnl_lock() ... unregister_netdevice_many() ... rtnl_unlock()) Tested: $ cat add_del_unshare.sh for i in `seq 1 40` do (for j in `seq 1 100` ; do unshare -n /bin/true >/dev/null ; done) & done wait ; grep net_namespace /proc/slabinfo Before patch : $ time ./add_del_unshare.sh net_namespace 110 267 5504 1 2 : tunables 8 4 0 : slabdata 110 267 0 real 3m25.292s user 0m0.644s sys 0m40.153s After patch: $ time ./add_del_unshare.sh net_namespace 126 282 5504 1 2 : tunables 8 4 0 : slabdata 126 282 0 real 1m38.965s user 0m0.688s sys 0m37.017s Signed-off-by:
-
Eric Dumazet authored
When dealing with a list of dismantling netns, we can scan tcp_metrics once, saving cpu cycles. Signed-off-by:
-
Eric Dumazet authored
Having a global list of labels do not scale to thousands of netns in the cloud era. This causes quadratic behavior on netns creation and deletion. This is time having a per netns list of ~10 labels. Tested: $ time perf record (for f in `seq 1 3000` ; do ip netns add tast$f; done) [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 3.637 MB perf.data (~158898 samples) ] real 0m20.837s # instead of 0m24.227s user 0m0.328s sys 0m20.338s # instead of 0m23.753s 16.17% ip [kernel.kallsyms] [k] netlink_broadcast_filtered 12.30% ip [kernel.kallsyms] [k] netlink_has_listeners 6.76% ip [kernel.kallsyms] [k] _raw_spin_lock_irqsave 5.78% ip [kernel.kallsyms] [k] memset_erms 5.77% ip [kernel.kallsyms] [k] kobject_uevent_env 5.18% ip [kernel.kallsyms] [k] refcount_sub_and_test 4.96% ip [kernel.kallsyms] [k] _raw_read_lock 3.82% ip [kernel.kallsyms] [k] refcount_inc_not_zero 3.33% ip [kernel.kallsyms] [k] _raw_spin_unlock_irqrestore 2.11% ip [kernel.kallsyms] [k] unmap_page_range 1.77% ip [kernel.kallsyms] [k] __wake_up 1.69% ip [kernel.kallsyms] [k] strlen 1.17% ip [kernel.kallsyms] [k] __wake_up_common 1.09% ip [kernel.kallsyms] [k] insert_header 1.04% ip [kernel.kallsyms] [k] page_remove_rmap 1.01% ip [kernel.kallsyms] [k] consume_skb 0.98% ip [kernel.kallsyms] [k] netlink_trim 0.51% ip [kernel.kallsyms] [k] kernfs_link_sibling 0.51% ip [kernel.kallsyms] [k] filemap_map_pages 0.46% ip [kernel.kallsyms] [k] memcpy_erms Signed-off-by: -
Eric Dumazet authored
We can build one skb and let it be cloned in netlink. This is much faster, and use less memory (all clones will share the same skb->head) Tested: time perf record (for f in `seq 1 3000` ; do ip netns add tast$f; done) [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 4.110 MB perf.data (~179584 samples) ] real 0m24.227s # instead of 0m52.554s user 0m0.329s sys 0m23.753s # instead of 0m51.375s 14.77% ip [kernel.kallsyms] [k] __ip6addrlbl_add 14.56% ip [kernel.kallsyms] [k] netlink_broadcast_filtered 11.65% ip [kernel.kallsyms] [k] netlink_has_listeners 6.19% ip [kernel.kallsyms] [k] _raw_spin_lock_irqsave 5.66% ip [kernel.kallsyms] [k] kobject_uevent_env 4.97% ip [kernel.kallsyms] [k] memset_erms 4.67% ip [kernel.kallsyms] [k] refcount_sub_and_test 4.41% ip [kernel.kallsyms] [k] _raw_read_lock 3.59% ip [kernel.kallsyms] [k] refcount_inc_not_zero 3.13% ip [kernel.kallsyms] [k] _raw_spin_unlock_irqrestore 1.55% ip [kernel.kallsyms] [k] __wake_up 1.20% ip [kernel.kallsyms] [k] strlen 1.03% ip [kernel.kallsyms] [k] __wake_up_common 0.93% ip [kernel.kallsyms] [k] consume_skb 0.92% ip [kernel.kallsyms] [k] netlink_trim 0.87% ip [kernel.kallsyms] [k] insert_header 0.63% ip [kernel.kallsyms] [k] unmap_page_range Signed-off-by:
-
