From af6eea57437a830293eab56246b6025cc7d46ee7 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Sun, 29 Mar 2020 19:59:58 -0700 Subject: bpf: Implement bpf_link-based cgroup BPF program attachment Implement new sub-command to attach cgroup BPF programs and return FD-based bpf_link back on success. bpf_link, once attached to cgroup, cannot be replaced, except by owner having its FD. Cgroup bpf_link supports only BPF_F_ALLOW_MULTI semantics. Both link-based and prog-based BPF_F_ALLOW_MULTI attachments can be freely intermixed. To prevent bpf_cgroup_link from keeping cgroup alive past the point when no BPF program can be executed, implement auto-detachment of link. When cgroup_bpf_release() is called, all attached bpf_links are forced to release cgroup refcounts, but they leave bpf_link otherwise active and allocated, as well as still owning underlying bpf_prog. This is because user-space might still have FDs open and active, so bpf_link as a user-referenced object can't be freed yet. Once last active FD is closed, bpf_link will be freed and underlying bpf_prog refcount will be dropped. But cgroup refcount won't be touched, because cgroup is released already. The inherent race between bpf_cgroup_link release (from closing last FD) and cgroup_bpf_release() is resolved by both operations taking cgroup_mutex. So the only additional check required is when bpf_cgroup_link attempts to detach itself from cgroup. At that time we need to check whether there is still cgroup associated with that link. And if not, exit with success, because bpf_cgroup_link was already successfully detached. Signed-off-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov Acked-by: Roman Gushchin Link: https://lore.kernel.org/bpf/20200330030001.2312810-2-andriin@fb.com --- include/uapi/linux/bpf.h | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 9f786a5a44ac..37dffe5089a0 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -111,6 +111,7 @@ enum bpf_cmd { BPF_MAP_LOOKUP_AND_DELETE_BATCH, BPF_MAP_UPDATE_BATCH, BPF_MAP_DELETE_BATCH, + BPF_LINK_CREATE, }; enum bpf_map_type { @@ -541,7 +542,7 @@ union bpf_attr { __u32 prog_cnt; } query; - struct { + struct { /* anonymous struct used by BPF_RAW_TRACEPOINT_OPEN command */ __u64 name; __u32 prog_fd; } raw_tracepoint; @@ -569,6 +570,13 @@ union bpf_attr { __u64 probe_offset; /* output: probe_offset */ __u64 probe_addr; /* output: probe_addr */ } task_fd_query; + + struct { /* struct used by BPF_LINK_CREATE command */ + __u32 prog_fd; /* eBPF program to attach */ + __u32 target_fd; /* object to attach to */ + __u32 attach_type; /* attach type */ + __u32 flags; /* extra flags */ + } link_create; } __attribute__((aligned(8))); /* The description below is an attempt at providing documentation to eBPF -- cgit v1.2.3 From 0c991ebc8c69d29b7fc44db17075c5aa5253e2ab Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Sun, 29 Mar 2020 19:59:59 -0700 Subject: bpf: Implement bpf_prog replacement for an active bpf_cgroup_link Add new operation (LINK_UPDATE), which allows to replace active bpf_prog from under given bpf_link. Currently this is only supported for bpf_cgroup_link, but will be extended to other kinds of bpf_links in follow-up patches. For bpf_cgroup_link, implemented functionality matches existing semantics for direct bpf_prog attachment (including BPF_F_REPLACE flag). User can either unconditionally set new bpf_prog regardless of which bpf_prog is currently active under given bpf_link, or, optionally, can specify expected active bpf_prog. If active bpf_prog doesn't match expected one, no changes are performed, old bpf_link stays intact and attached, operation returns a failure. cgroup_bpf_replace() operation is resolving race between auto-detachment and bpf_prog update in the same fashion as it's done for bpf_link detachment, except in this case update has no way of succeeding because of target cgroup marked as dying. So in this case error is returned. Signed-off-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200330030001.2312810-3-andriin@fb.com --- include/uapi/linux/bpf.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 37dffe5089a0..2e29a671d67e 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -112,6 +112,7 @@ enum bpf_cmd { BPF_MAP_UPDATE_BATCH, BPF_MAP_DELETE_BATCH, BPF_LINK_CREATE, + BPF_LINK_UPDATE, }; enum bpf_map_type { @@ -577,6 +578,17 @@ union bpf_attr { __u32 attach_type; /* attach type */ __u32 flags; /* extra flags */ } link_create; + + struct { /* struct used by BPF_LINK_UPDATE command */ + __u32 link_fd; /* link fd */ + /* new program fd to update link with */ + __u32 new_prog_fd; + __u32 flags; /* extra flags */ + /* expected link's program fd; is specified only if + * BPF_F_REPLACE flag is set in flags */ + __u32 old_prog_fd; + } link_update; + } __attribute__((aligned(8))); /* The description below is an attempt at providing documentation to eBPF -- cgit v1.2.3