On 10/02/2018 03:30 AM, Jakub Kicinski wrote: > Hi! > > This series makes the control message parsing for interacting > with BPF maps more flexible. Up until now we had a hard limit > in the ABI for key and value size to be 64B at most. Using > TLV capability allows us to support large map entries. > > Jakub Kicinski (3): > nfp: bpf: parse global BPF ABI version capability > nfp: allow apps to request larger MTU on control vNIC > nfp: bpf: allow control message sizing for map ops > > drivers/net/ethernet/netronome/nfp/bpf/cmsg.c | 70 ++++++++++++++++--- > drivers/net/ethernet/netronome/nfp/bpf/fw.h | 11 ++- > drivers/net/ethernet/netronome/nfp/bpf/main.c | 52 ++++++++++++-- > drivers/net/ethernet/netronome/nfp/bpf/main.h | 11 +++ > drivers/net/ethernet/netronome/nfp/nfp_app.h | 4 ++ > .../ethernet/netronome/nfp/nfp_net_common.c | 14 +++- > .../net/ethernet/netronome/nfp/nfp_net_ctrl.h | 2 +- > 7 files changed, 142 insertions(+), 22 deletions(-) >
Applied to bpf-next, thanks Jakub!
