summaryrefslogtreecommitdiff
path: root/net/rds/ib.c
diff options
context:
space:
mode:
authorDavid S. Miller <davem@davemloft.net>2018-07-24 06:44:13 +0300
committerDavid S. Miller <davem@davemloft.net>2018-07-24 06:44:13 +0300
commita6c90dd321bfeb5e48fc2eb6623b7b976106f6d7 (patch)
treee8693a59141ec1b9d9babe3c03de77700b501d45 /net/rds/ib.c
parentd3585edf8749e151760fc914912a4fee5aa1a2ac (diff)
parentd159b381795b138532436cce1229f5305c6f1a21 (diff)
downloadlinux-a6c90dd321bfeb5e48fc2eb6623b7b976106f6d7.tar.xz
Merge branch 'sched-introduce-chain-templates-support-with-offloading-to-mlxsw'
Jiri Pirko says: ==================== sched: introduce chain templates support with offloading to mlxsw For the TC clsact offload these days, some of HW drivers need to hold a magic ball. The reason is, with the first inserted rule inside HW they need to guess what fields will be used for the matching. If later on this guess proves to be wrong and user adds a filter with a different field to match, there's a problem. Mlxsw resolves it now with couple of patterns. Those try to cover as many match fields as possible. This aproach is far from optimal, both performance-wise and scale-wise. Also, there is a combination of filters that in certain order won't succeed. Most of the time, when user inserts filters in chain, he knows right away how the filters are going to look like - what type and option will they have. For example, he knows that he will only insert filters of type flower matching destination IP address. He can specify a template that would cover all the filters in the chain. This patchset is providing the possibility to user to provide such template to kernel and propagate it all the way down to device drivers. See the examples below. Create dummy device with clsact first: There is no chain present by by default: Add chain number 11 by explicit command: chain parent ffff: chain 11 Add filter to chain number 12 which does not exist. That will create implicit chain 12: chain parent ffff: chain 11 chain parent ffff: chain 12 Delete both chains: Add a chain with template of type flower allowing to insert rules matching on last 2 bytes of destination mac address: The chain with template is now showed in the list: chain parent ffff: flower chain 0 dst_mac 00:00:00:00:00:00/00:00:00:00:ff:ff eth_type ipv4 Add another chain (number 22) with template: chain parent ffff: flower chain 0 dst_mac 00:00:00:00:00:00/00:00:00:00:ff:ff eth_type ipv4 chain parent ffff: flower chain 22 eth_type ipv4 dst_ip 0.0.0.0/16 Add a filter that fits the template: Addition of filters that does not fit the template would fail: Error: cls_flower: Mask does not fit the template. We have an error talking to the kernel, -1 Error: cls_flower: Mask does not fit the template. We have an error talking to the kernel, -1 Additions of filters to chain 22: Error: cls_flower: Mask does not fit the template. We have an error talking to the kernel, -1 Error: cls_flower: Mask does not fit the template. We have an error talking to the kernel, -1 --- v3->v4: - patch 2: - new patch - patch 3: - new patch, derived from the previous v3 chaintemplate obj patch - patch 4: - only templates part as chains creation/deletion is now a separate patch - don't pass template priv as arg of "change" op - patch 6: - rebased on top of flower cvlan patch and ip tos/ttl patch - patch 7: - templave priv is no longer passed as an arg to "change" op - patch 11: - split from the originally single patch - patch 12: - split from the originally single patch v2->v3: - patch 7: - rebase on top of the reoffload patchset - patch 8: - rebase on top of the reoffload patchset v1->v2: - patch 8: - remove leftover extack arg in fl_hw_create_tmplt() ==================== Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net/rds/ib.c')
0 files changed, 0 insertions, 0 deletions