- 09 Oct, 2017 36 commits
-
-
Jakub Kicinski authored
We need to append up to 8 nops after last instruction to make sure the CPU will not fetch garbage instructions with invalid ECC if the code store was not initialized. Signed-off-by:
Jakub Kicinski <jakub.kicinski@netronome.com> Reviewed-by:
Simon Horman <simon.horman@netronome.com> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Jakub Kicinski authored
In the initial PoC firmware I simply disabled ECC on the instruction store. Do the ECC calculation for generated instructions in the driver. Signed-off-by:
-
Jakub Kicinski authored
Datapath ABI version 2 stores the packet information in LMEM instead of NNRs. We also have strict restrictions on which GPRs we can use. Only GPRs 0-23 are reserved for BPF. Adjust the static register locations and "ABI" registers. Note that packet length is packed with other info so we have to extract it into one of the scratch registers, OTOH since LMEM can be used in restricted operands we don't have to extract packet pointer. Signed-off-by:
-
Jakub Kicinski authored
Most instructions have special fields which allow switching between base and extended Local Memory pointers. Introduce those to register encoding, we will use the extra LM pointers to access high addresses of the stack. Signed-off-by:
-
Jakub Kicinski authored
NFP LMEM is a large, indirectly accessed register file. There are two basic indirect access registers. Each access operation may either use offset (up to 8 or 16 words) or perform post decrement/increment. Add encodings of LMEM indexes as instruction operands. Signed-off-by:
-
Jakub Kicinski authored
We need to add longer OP_* defines, move the values away. Purely whitespace commit. Signed-off-by:
-
Jakub Kicinski authored
Temporarily drop support for skb->mark. We are primarily focusing on XDP offload, and implementing skb->mark on the new datapath has lower priority. Signed-off-by:
-
Jakub Kicinski authored
Remove the register renumbering optimization. To implement calling map and other helpers we need more strict register layout. We can't freely reassign register numbers. This will have the effect of running in 4 context/thread mode, which should be OK since we are moving towards integrating the BPF closer with FW app datapath anyway, and the target datapath itself runs in 4 context mode. Signed-off-by:
-
Jakub Kicinski authored
Add encodings of all 64bit shift operations. Signed-off-by:
-
Jakub Kicinski authored
Move the software reg helpers and some static data to nfp_asm.c. They are related to the previous patch, but move is done in a separate commit for ease of review. Signed-off-by:
-
Jakub Kicinski authored
Define a new __bitwise type for software representation of registers. This will allow us to catch incorrect parameter types using sparse. Accessors we define also allow us to return correct enum type and therefore ensure all switches handle all register types. Signed-off-by:
-
Jakub Kicinski authored
Limiting the eBPF offload to a single port was a workaround required for the PoC application FW which has not been released externally. It's not necessary any more. Signed-off-by:
-
Jakub Kicinski authored
Use standard devlink trace point to allow tracing of control messages. Signed-off-by:
-
David S. Miller authored
Yunsheng Lin says: ==================== A few cleanup for hns3 ethernet driver This patchset contains a few cleanup for hns3 ethernet driver. No functional change intended. ==================== Signed-off-by: -
Yunsheng Lin authored
This patch fixes the following warning from sparse: warning: symbol 'hns3_set_multicast_list' was not declared. Should it be static. hns3_set_multicast_list turns out to be not used, so delete it. Signed-off-by:
Yunsheng Lin <linyunsheng@huawei.com> Signed-off-by:
-
Yunsheng Lin authored
This patch fixes a lot of endian issues detected by sparse. Signed-off-by:
-
Yunsheng Lin authored
The hclge_tm module has already added _cmd to the end of struct that used to send cmd to firmware. This will help us finding the endian issues. This patch adds the _cmd to the end of struct that used to send cmd to firmware in hclge_main module. Signed-off-by:
-
Yunsheng Lin authored
This patch uses GENMASK to generate bit mask whenever possible in hns3 driver. Signed-off-by:
-
Yunsheng Lin authored
This patch fixes a few indentation for Kconfig file in the hisilicon folder. Signed-off-by:
-
Yunsheng Lin authored
There are many places that will need to get the handle of netdev, so add a macro to get the handle of netdev. Signed-off-by:
-
Yunsheng Lin authored
This patch fixes a shifting true in hclge_main module. Signed-off-by:
-
Christos Gkekas authored
dcb_app priority is unsigned thus checking whether it is less than zero is redundant. Signed-off-by:
Christos Gkekas <chris.gekas@gmail.com> Acked-By:
Tomer Tayar <Tomer.Tayar@cavium.com> Signed-off-by:
-
Christos Gkekas authored
Many macros in dwmac-ipq806x are unused and should be removed. Moreover gmac->id is an unsigned variable and therefore checking whether it is less than zero is redundant. Signed-off-by:
-
David S. Miller authored
Eric Dumazet says: ==================== ipv6: ipv6_dev_get_saddr() rcu works Sending IPv6 udp packets on non connected sockets is quite slow, because ipv6_dev_get_saddr() is still using an rwlock and silly references games on ifa. Tested: $ ./super_netperf 16 -H 4444::555:0786 -l 2000 -t UDP_STREAM -- -m 100 & [1] 12527 Performance is boosted from 2.02 Mpps to 4.28 Mpps Kernel profile before patches : 22.62% [kernel] [k] _raw_read_lock_bh 7.04% [kernel] [k] refcount_sub_and_test 6.56% [kernel] [k] ipv6_get_saddr_eval 5.67% [kernel] [k] _raw_read_unlock_bh 5.34% [kernel] [k] __ipv6_dev_get_saddr 4.95% [kernel] [k] refcount_inc_not_zero 4.03% [kernel] [k] __ip6addrlbl_match 3.70% [kernel] [k] _raw_spin_lock 3.44% [kernel] [k] ipv6_dev_get_saddr 3.24% [kernel] [k] ip6_pol_route 3.06% [kernel] [k] refcount_add_not_zero 2.30% [kernel] [k] __local_bh_enable_ip 1.81% [kernel] [k] mlx4_en_xmit 1.20% [kernel] [k] __ip6_append_data 1.12% [kernel] [k] __ip6_make_skb 1.11% [kernel] [k] __dev_queue_xmit 1.06% [kernel] [k] l3mdev_master_ifindex_rcu Kernel profile after patches : 11.36% [kernel] [k] ip6_pol_route 7.65% [kernel] [k] _raw_spin_lock 7.16% [kernel] [k] __ipv6_dev_get_saddr 6.49% [kernel] [k] ipv6_get_saddr_eval 6.04% [kernel] [k] refcount_add_not_zero 3.34% [kernel] [k] __ip6addrlbl_match 2.62% [kernel] [k] __dev_queue_xmit 2.37% [kernel] [k] mlx4_en_xmit 2.26% [kernel] [k] dst_release 1.89% [kernel] [k] __ip6_make_skb 1.87% [kernel] [k] __ip6_append_data 1.86% [kernel] [k] udpv6_sendmsg 1.86% [kernel] [k] ip6t_do_table 1.64% [kernel] [k] ipv6_dev_get_saddr 1.64% [kernel] [k] find_match 1.51% [kernel] [k] l3mdev_master_ifindex_rcu 1.24% [kernel] [k] ipv6_addr_label ==================== Signed-off-by: -
Eric Dumazet authored
By extending the rcu section a bit, we can avoid these very expensive in6_ifa_put()/in6_ifa_hold() calls done in __ipv6_dev_get_saddr() and ipv6_dev_get_saddr() Signed-off-by:
Eric Dumazet <edumazet@google.com> Signed-off-by:
-
Eric Dumazet authored
Callers hold rcu_read_lock(), so we do not need the rcu_read_lock()/rcu_read_unlock() pair. Signed-off-by:
-
Eric Dumazet authored
Signed-off-by:
-
Eric Dumazet authored
Signed-off-by:
-
Eric Dumazet authored
Signed-off-by:
-
Eric Dumazet authored
inet6_ifa_finish_destroy() already uses kfree_rcu() to free inet6_ifaddr structs. We need to use proper list additions/deletions in order to allow readers to use RCU instead of idev->lock rwlock. Signed-off-by:
-
David S. Miller authored
Roopa Prabhu says: ==================== bridge: neigh msg proxy and flood suppression support This series implements arp and nd suppression in the bridge driver for ethernet vpns. It implements rfc7432, section 10 https://tools.ietf.org/html/rfc7432#section-10 for ethernet VPN deployments. It is similar to the existing BR_PROXYARP* flags but has a few semantic differences to conform to EVPN standard. Unlike the existing flags, this new flag suppresses flood of all neigh discovery packets (arp and nd) to tunnel ports. Supports both vlan filtering and non-vlan filtering bridges. In case of EVPN, it is mainly used to avoid flooding of arp and nd packets to tunnel ports like vxlan. v2 : rebase to latest + address some optimization feedback from Nikolay. v3 : fix kbuild reported build errors with CONFIG_INET off v4 : simplify port flag mask as suggested by stephen v5 : address some feedback from Toshiaki v6 : some v5 cleanups in nd suppress (keep it consistent with arp suppress) ==================== Signed-off-by:
-
Roopa Prabhu authored
This patch avoids flooding and proxies ndisc packets for BR_NEIGH_SUPPRESS ports. Signed-off-by:
Roopa Prabhu <roopa@cumulusnetworks.com> Signed-off-by:
-
Roopa Prabhu authored
This patch avoids flooding and proxies arp packets for BR_NEIGH_SUPPRESS ports. Moves existing br_do_proxy_arp to br_do_proxy_suppress_arp to support both proxy arp and neigh suppress. Signed-off-by:
-
Roopa Prabhu authored
This patch adds a new bridge port flag BR_NEIGH_SUPPRESS to suppress arp and nd flood on bridge ports. It implements rfc7432, section 10. https://tools.ietf.org/html/rfc7432#section-10 for ethernet VPN deployments. It is similar to the existing BR_PROXYARP* flags but has a few semantic differences to conform to EVPN standard. Unlike the existing flags, this new flag suppresses flood of all neigh discovery packets (arp and nd) to tunnel ports. Supports both vlan filtering and non-vlan filtering bridges. In case of EVPN, it is mainly used to avoid flooding of arp and nd packets to tunnel ports like vxlan. This patch adds netlink and sysfs support to set this bridge port flag. Signed-off-by:
-
Eric Dumazet authored
Ido reported following splat and provided a patch. [ 122.221814] BUG: using smp_processor_id() in preemptible [00000000] code: sshd/2672 [ 122.221845] caller is debug_smp_processor_id+0x17/0x20 [ 122.221866] CPU: 0 PID: 2672 Comm: sshd Not tainted 4.14.0-rc3-idosch-next-custom #639 [ 122.221880] Hardware name: Mellanox Technologies Ltd. MSN2100-CB2FO/SA001017, BIOS 5.6.5 06/07/2016 [ 122.221893] Call Trace: [ 122.221919] dump_stack+0xb1/0x10c [ 122.221946] ? _atomic_dec_and_lock+0x124/0x124 [ 122.221974] ? ___ratelimit+0xfe/0x240 [ 122.222020] check_preemption_disabled+0x173/0x1b0 [ 122.222060] debug_smp_processor_id+0x17/0x20 [ 122.222083] ip6_pol_route+0x1482/0x24a0 ... I believe we can simplify this code path a bit, since we no longer hold a read_lock and need to release it to avoid a dead lock. By disabling BH, we make sure we'll prevent code re-entry and rt6_get_pcpu_route()/rt6_make_pcpu_route() run on the same cpu. Fixes: 66f5d6ce ("ipv6: replace rwlock with rcu and spinlock in fib6_table") Reported-by:
Ido Schimmel <idosch@mellanox.com> Signed-off-by:
-
git://git.kernel.org/pub/scm/linux/kernel/git/mellanox/linuxDavid S. Miller authored
Saeed Mahameed says: ==================== Mellanox, mlx5 updates 2017-10-06 This series includes some shared code updates for kernel 4.15 to both net-next and rdma-next trees. The series includes mlx5 low level flow steering updates and optimizations to support firmware command parallelism for flow steering requests from Maor Gottlieb and two other small fixes from Matan and Maor. One fix from Matan adds error handling for when the destination list of the flow steering rule is full. Maor introduced a patch to avoid NULL pointer dereference on steering cleanup. Then Some refactoring patches needed by the series for code sharing purposes. and split the Flow Table Entry (FTE) and Flow Group (FG) creation code to two parts: 1) Object allocation - allocate the steering node and initialize its resources. 2) The firmware command execution. This change will give us the ability to take write lock on the parent node (e.g. FG for FTE creating) only on the software data struct allocation and creation part of the procedure where the synchronization is really required, and will allow us to execute multiple firmware commands simultaneously and overcome the firmware bottleneck. Refactor the locking scheme of the mlx5 core flow steering as follows: 1) Replace the mutex lock with readers-writers semaphore and take the write lock only when necessary (e.g. allocating a new flow table entry index or adding a node to the parent's children list). When we try to find a suitable child in the parent's children list (e.g. search for flow group with the same match_criteria of the rule) then we only take the read lock. 2) Add versioning mechanism - each steering entity (FT, FG, FTE, DST) will have an incremental version. The version is increased when the entity is changed (e.g. when a new FTE was added to FG - the FG's version is increased). Versioning is used in order to determine if the last traverse of an entity's children is valid or a rescan under write lock is required. Last patch adds FGs and FTEs memory pool, It is useful because these objects are not small and could be allocated/deallocated many times. This support improves the insertion rate of steering rules from ~5k/sec to ~40k/sec. ==================== Signed-off-by:
-
- 08 Oct, 2017 4 commits
-
-
David S. Miller authored
Haiyang Zhang says: ==================== hv_netvsc: support changing TCP hash level The patch set simplifies the existing hash level switching code for UDP. It also adds the support for changing TCP hash level. So users can switch between L3 an L4 hash levels for TCP and UDP. ==================== Signed-off-by: -
Haiyang Zhang authored
Update Documentation/networking/netvsc.txt for TCP hash level setting and related info. Signed-off-by:
Haiyang Zhang <haiyangz@microsoft.com> Signed-off-by:
-
Haiyang Zhang authored
The patch supports the options to switch TCP hash level between L3 and L4 by ethtool command. TCP over IPv4 and v6 can be set differently. The default hash level is L4. We currently only allow switching TX hash level from within the guests. For example, for TCP over IPv4 on eth0: To include TCP port numbers in hashing: ethtool -N eth0 rx-flow-hash tcp4 sdfn To exclude TCP port numbers in hashing: ethtool -N eth0 rx-flow-hash tcp4 sd To show TCP hash level: ethtool -n eth0 rx-flow-hash tcp4 Signed-off-by:
-
Haiyang Zhang authored
This simplifies the logic and make it easier to add more options. Signed-off-by:
-
