> On Oct 2, 2019, at 12:23 PM, Toke Høiland-Jørgensen <t...@redhat.com> wrote: > > Song Liu <songliubrav...@fb.com> writes: > >>> On Oct 2, 2019, at 6:30 AM, Toke Høiland-Jørgensen <t...@redhat.com> wrote: >>> >>> This series adds support for executing multiple XDP programs on a single >>> interface in sequence, through the use of chain calls, as discussed at the >>> Linux >>> Plumbers Conference last month: >>> >>> https://urldefense.proofpoint.com/v2/url?u=https-3A__linuxplumbersconf.org_event_4_contributions_460_&d=DwIDaQ&c=5VD0RTtNlTh3ycd41b3MUw&r=dR8692q0_uaizy0jkrBJQM5k2hfm4CiFxYT8KaysFrg&m=YXqqHTC51zXBviPBEk55y-fQjFQwcXWFlH0IoOqm2KU&s=NF4w3eSPmNhSpJr1-0FLqqlqfgEV8gsCQb9YqWQ9p-k&e= >>> >>> >>> # HIGH-LEVEL IDEA >>> >>> The basic idea is to express the chain call sequence through a special map >>> type, >>> which contains a mapping from a (program, return code) tuple to another >>> program >>> to run in next in the sequence. Userspace can populate this map to express >>> arbitrary call sequences, and update the sequence by updating or replacing >>> the >>> map. >>> >>> The actual execution of the program sequence is done in bpf_prog_run_xdp(), >>> which will lookup the chain sequence map, and if found, will loop through >>> calls >>> to BPF_PROG_RUN, looking up the next XDP program in the sequence based on >>> the >>> previous program ID and return code. >>> >>> An XDP chain call map can be installed on an interface by means of a new >>> netlink >>> attribute containing an fd pointing to a chain call map. This can be >>> supplied >>> along with the XDP prog fd, so that a chain map is always installed together >>> with an XDP program. >> >> Interesting work! >> >> Quick question: can we achieve the same by adding a "retval to >> call_tail_next" map to each program? > > Hmm, that's an interesting idea; I hadn't thought of that. As long as > that map can be manipulated outside of the program itself, it may work. > I wonder how complex it gets to modify the call sequence, though; say > you want to change A->B->C to A->C->B - how do you do that without > interrupting the sequence while you're modifying things? Or is it OK if > that is not possible?
We can always load another copy of B and C, say D == B, and E == C. And make it A->E->D.
