From 2d0e30c30f84d08dc16f0f2af41f1b8a85f0755e Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Fri, 21 Oct 2016 12:46:33 +0200 Subject: bpf: add helper for retrieving current numa node id Use case is mainly for soreuseport to select sockets for the local numa node, but since generic, lets also add this for other networking and tracing program types. Suggested-by: Eric Dumazet Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- include/uapi/linux/bpf.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/uapi/linux/bpf.h') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index f09c70b97eca..374ef582ae18 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -426,6 +426,12 @@ enum bpf_func_id { */ BPF_FUNC_set_hash_invalid, + /** + * bpf_get_numa_node_id() + * Returns the id of the current NUMA node. + */ + BPF_FUNC_get_numa_node_id, + __BPF_FUNC_MAX_ID, }; -- cgit v1.2.3 From ebb676daa1a340ccef25eb769aefc09b79c01f8a Mon Sep 17 00:00:00 2001 From: Thomas Graf Date: Thu, 27 Oct 2016 11:23:51 +0200 Subject: bpf: Print function name in addition to function id The verifier currently prints raw function ids when printing CALL instructions or when complaining: 5: (85) call 23 unknown func 23 print a meaningful function name instead: 5: (85) call bpf_redirect#23 unknown func bpf_redirect#23 Moves the function documentation to a single comment and renames all helpers names in the list to conform to the bpf_ prefix notation so they can be greped in the kernel source. Signed-off-by: Thomas Graf Acked-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/uapi/linux/bpf.h | 574 ++++++++++++++++++++++++----------------------- 1 file changed, 289 insertions(+), 285 deletions(-) (limited to 'include/uapi/linux/bpf.h') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 374ef582ae18..e2f38e0091b6 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -143,297 +143,301 @@ union bpf_attr { }; } __attribute__((aligned(8))); +/* BPF helper function descriptions: + * + * void *bpf_map_lookup_elem(&map, &key) + * Return: Map value or NULL + * + * int bpf_map_update_elem(&map, &key, &value, flags) + * Return: 0 on success or negative error + * + * int bpf_map_delete_elem(&map, &key) + * Return: 0 on success or negative error + * + * int bpf_probe_read(void *dst, int size, void *src) + * Return: 0 on success or negative error + * + * u64 bpf_ktime_get_ns(void) + * Return: current ktime + * + * int bpf_trace_printk(const char *fmt, int fmt_size, ...) + * Return: length of buffer written or negative error + * + * u32 bpf_prandom_u32(void) + * Return: random value + * + * u32 bpf_raw_smp_processor_id(void) + * Return: SMP processor ID + * + * int bpf_skb_store_bytes(skb, offset, from, len, flags) + * store bytes into packet + * @skb: pointer to skb + * @offset: offset within packet from skb->mac_header + * @from: pointer where to copy bytes from + * @len: number of bytes to store into packet + * @flags: bit 0 - if true, recompute skb->csum + * other bits - reserved + * Return: 0 on success or negative error + * + * int bpf_l3_csum_replace(skb, offset, from, to, flags) + * recompute IP checksum + * @skb: pointer to skb + * @offset: offset within packet where IP checksum is located + * @from: old value of header field + * @to: new value of header field + * @flags: bits 0-3 - size of header field + * other bits - reserved + * Return: 0 on success or negative error + * + * int bpf_l4_csum_replace(skb, offset, from, to, flags) + * recompute TCP/UDP checksum + * @skb: pointer to skb + * @offset: offset within packet where TCP/UDP checksum is located + * @from: old value of header field + * @to: new value of header field + * @flags: bits 0-3 - size of header field + * bit 4 - is pseudo header + * other bits - reserved + * Return: 0 on success or negative error + * + * int bpf_tail_call(ctx, prog_array_map, index) + * jump into another BPF program + * @ctx: context pointer passed to next program + * @prog_array_map: pointer to map which type is BPF_MAP_TYPE_PROG_ARRAY + * @index: index inside array that selects specific program to run + * Return: 0 on success or negative error + * + * int bpf_clone_redirect(skb, ifindex, flags) + * redirect to another netdev + * @skb: pointer to skb + * @ifindex: ifindex of the net device + * @flags: bit 0 - if set, redirect to ingress instead of egress + * other bits - reserved + * Return: 0 on success or negative error + * + * u64 bpf_get_current_pid_tgid(void) + * Return: current->tgid << 32 | current->pid + * + * u64 bpf_get_current_uid_gid(void) + * Return: current_gid << 32 | current_uid + * + * int bpf_get_current_comm(char *buf, int size_of_buf) + * stores current->comm into buf + * Return: 0 on success or negative error + * + * u32 bpf_get_cgroup_classid(skb) + * retrieve a proc's classid + * @skb: pointer to skb + * Return: classid if != 0 + * + * int bpf_skb_vlan_push(skb, vlan_proto, vlan_tci) + * Return: 0 on success or negative error + * + * int bpf_skb_vlan_pop(skb) + * Return: 0 on success or negative error + * + * int bpf_skb_get_tunnel_key(skb, key, size, flags) + * int bpf_skb_set_tunnel_key(skb, key, size, flags) + * retrieve or populate tunnel metadata + * @skb: pointer to skb + * @key: pointer to 'struct bpf_tunnel_key' + * @size: size of 'struct bpf_tunnel_key' + * @flags: room for future extensions + * Return: 0 on success or negative error + * + * u64 bpf_perf_event_read(&map, index) + * Return: Number events read or error code + * + * int bpf_redirect(ifindex, flags) + * redirect to another netdev + * @ifindex: ifindex of the net device + * @flags: bit 0 - if set, redirect to ingress instead of egress + * other bits - reserved + * Return: TC_ACT_REDIRECT + * + * u32 bpf_get_route_realm(skb) + * retrieve a dst's tclassid + * @skb: pointer to skb + * Return: realm if != 0 + * + * int bpf_perf_event_output(ctx, map, index, data, size) + * output perf raw sample + * @ctx: struct pt_regs* + * @map: pointer to perf_event_array map + * @index: index of event in the map + * @data: data on stack to be output as raw data + * @size: size of data + * Return: 0 on success or negative error + * + * int bpf_get_stackid(ctx, map, flags) + * walk user or kernel stack and return id + * @ctx: struct pt_regs* + * @map: pointer to stack_trace map + * @flags: bits 0-7 - numer of stack frames to skip + * bit 8 - collect user stack instead of kernel + * bit 9 - compare stacks by hash only + * bit 10 - if two different stacks hash into the same stackid + * discard old + * other bits - reserved + * Return: >= 0 stackid on success or negative error + * + * s64 bpf_csum_diff(from, from_size, to, to_size, seed) + * calculate csum diff + * @from: raw from buffer + * @from_size: length of from buffer + * @to: raw to buffer + * @to_size: length of to buffer + * @seed: optional seed + * Return: csum result or negative error code + * + * int bpf_skb_get_tunnel_opt(skb, opt, size) + * retrieve tunnel options metadata + * @skb: pointer to skb + * @opt: pointer to raw tunnel option data + * @size: size of @opt + * Return: option size + * + * int bpf_skb_set_tunnel_opt(skb, opt, size) + * populate tunnel options metadata + * @skb: pointer to skb + * @opt: pointer to raw tunnel option data + * @size: size of @opt + * Return: 0 on success or negative error + * + * int bpf_skb_change_proto(skb, proto, flags) + * Change protocol of the skb. Currently supported is v4 -> v6, + * v6 -> v4 transitions. The helper will also resize the skb. eBPF + * program is expected to fill the new headers via skb_store_bytes + * and lX_csum_replace. + * @skb: pointer to skb + * @proto: new skb->protocol type + * @flags: reserved + * Return: 0 on success or negative error + * + * int bpf_skb_change_type(skb, type) + * Change packet type of skb. + * @skb: pointer to skb + * @type: new skb->pkt_type type + * Return: 0 on success or negative error + * + * int bpf_skb_under_cgroup(skb, map, index) + * Check cgroup2 membership of skb + * @skb: pointer to skb + * @map: pointer to bpf_map in BPF_MAP_TYPE_CGROUP_ARRAY type + * @index: index of the cgroup in the bpf_map + * Return: + * == 0 skb failed the cgroup2 descendant test + * == 1 skb succeeded the cgroup2 descendant test + * < 0 error + * + * u32 bpf_get_hash_recalc(skb) + * Retrieve and possibly recalculate skb->hash. + * @skb: pointer to skb + * Return: hash + * + * u64 bpf_get_current_task(void) + * Returns current task_struct + * Return: current + * + * int bpf_probe_write_user(void *dst, void *src, int len) + * safely attempt to write to a location + * @dst: destination address in userspace + * @src: source address on stack + * @len: number of bytes to copy + * Return: 0 on success or negative error + * + * int bpf_current_task_under_cgroup(map, index) + * Check cgroup2 membership of current task + * @map: pointer to bpf_map in BPF_MAP_TYPE_CGROUP_ARRAY type + * @index: index of the cgroup in the bpf_map + * Return: + * == 0 current failed the cgroup2 descendant test + * == 1 current succeeded the cgroup2 descendant test + * < 0 error + * + * int bpf_skb_change_tail(skb, len, flags) + * The helper will resize the skb to the given new size, to be used f.e. + * with control messages. + * @skb: pointer to skb + * @len: new skb length + * @flags: reserved + * Return: 0 on success or negative error + * + * int bpf_skb_pull_data(skb, len) + * The helper will pull in non-linear data in case the skb is non-linear + * and not all of len are part of the linear section. Only needed for + * read/write with direct packet access. + * @skb: pointer to skb + * @len: len to make read/writeable + * Return: 0 on success or negative error + * + * s64 bpf_csum_update(skb, csum) + * Adds csum into skb->csum in case of CHECKSUM_COMPLETE. + * @skb: pointer to skb + * @csum: csum to add + * Return: csum on success or negative error + * + * void bpf_set_hash_invalid(skb) + * Invalidate current skb->hash. + * @skb: pointer to skb + * + * int bpf_get_numa_node_id() + * Return: Id of current NUMA node. + */ +#define __BPF_FUNC_MAPPER(FN) \ + FN(unspec), \ + FN(map_lookup_elem), \ + FN(map_update_elem), \ + FN(map_delete_elem), \ + FN(probe_read), \ + FN(ktime_get_ns), \ + FN(trace_printk), \ + FN(get_prandom_u32), \ + FN(get_smp_processor_id), \ + FN(skb_store_bytes), \ + FN(l3_csum_replace), \ + FN(l4_csum_replace), \ + FN(tail_call), \ + FN(clone_redirect), \ + FN(get_current_pid_tgid), \ + FN(get_current_uid_gid), \ + FN(get_current_comm), \ + FN(get_cgroup_classid), \ + FN(skb_vlan_push), \ + FN(skb_vlan_pop), \ + FN(skb_get_tunnel_key), \ + FN(skb_set_tunnel_key), \ + FN(perf_event_read), \ + FN(redirect), \ + FN(get_route_realm), \ + FN(perf_event_output), \ + FN(skb_load_bytes), \ + FN(get_stackid), \ + FN(csum_diff), \ + FN(skb_get_tunnel_opt), \ + FN(skb_set_tunnel_opt), \ + FN(skb_change_proto), \ + FN(skb_change_type), \ + FN(skb_under_cgroup), \ + FN(get_hash_recalc), \ + FN(get_current_task), \ + FN(probe_write_user), \ + FN(current_task_under_cgroup), \ + FN(skb_change_tail), \ + FN(skb_pull_data), \ + FN(csum_update), \ + FN(set_hash_invalid), \ + FN(get_numa_node_id), + /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call */ +#define __BPF_ENUM_FN(x) BPF_FUNC_ ## x enum bpf_func_id { - BPF_FUNC_unspec, - BPF_FUNC_map_lookup_elem, /* void *map_lookup_elem(&map, &key) */ - BPF_FUNC_map_update_elem, /* int map_update_elem(&map, &key, &value, flags) */ - BPF_FUNC_map_delete_elem, /* int map_delete_elem(&map, &key) */ - BPF_FUNC_probe_read, /* int bpf_probe_read(void *dst, int size, void *src) */ - BPF_FUNC_ktime_get_ns, /* u64 bpf_ktime_get_ns(void) */ - BPF_FUNC_trace_printk, /* int bpf_trace_printk(const char *fmt, int fmt_size, ...) */ - BPF_FUNC_get_prandom_u32, /* u32 prandom_u32(void) */ - BPF_FUNC_get_smp_processor_id, /* u32 raw_smp_processor_id(void) */ - - /** - * skb_store_bytes(skb, offset, from, len, flags) - store bytes into packet - * @skb: pointer to skb - * @offset: offset within packet from skb->mac_header - * @from: pointer where to copy bytes from - * @len: number of bytes to store into packet - * @flags: bit 0 - if true, recompute skb->csum - * other bits - reserved - * Return: 0 on success - */ - BPF_FUNC_skb_store_bytes, - - /** - * l3_csum_replace(skb, offset, from, to, flags) - recompute IP checksum - * @skb: pointer to skb - * @offset: offset within packet where IP checksum is located - * @from: old value of header field - * @to: new value of header field - * @flags: bits 0-3 - size of header field - * other bits - reserved - * Return: 0 on success - */ - BPF_FUNC_l3_csum_replace, - - /** - * l4_csum_replace(skb, offset, from, to, flags) - recompute TCP/UDP checksum - * @skb: pointer to skb - * @offset: offset within packet where TCP/UDP checksum is located - * @from: old value of header field - * @to: new value of header field - * @flags: bits 0-3 - size of header field - * bit 4 - is pseudo header - * other bits - reserved - * Return: 0 on success - */ - BPF_FUNC_l4_csum_replace, - - /** - * bpf_tail_call(ctx, prog_array_map, index) - jump into another BPF program - * @ctx: context pointer passed to next program - * @prog_array_map: pointer to map which type is BPF_MAP_TYPE_PROG_ARRAY - * @index: index inside array that selects specific program to run - * Return: 0 on success - */ - BPF_FUNC_tail_call, - - /** - * bpf_clone_redirect(skb, ifindex, flags) - redirect to another netdev - * @skb: pointer to skb - * @ifindex: ifindex of the net device - * @flags: bit 0 - if set, redirect to ingress instead of egress - * other bits - reserved - * Return: 0 on success - */ - BPF_FUNC_clone_redirect, - - /** - * u64 bpf_get_current_pid_tgid(void) - * Return: current->tgid << 32 | current->pid - */ - BPF_FUNC_get_current_pid_tgid, - - /** - * u64 bpf_get_current_uid_gid(void) - * Return: current_gid << 32 | current_uid - */ - BPF_FUNC_get_current_uid_gid, - - /** - * bpf_get_current_comm(char *buf, int size_of_buf) - * stores current->comm into buf - * Return: 0 on success - */ - BPF_FUNC_get_current_comm, - - /** - * bpf_get_cgroup_classid(skb) - retrieve a proc's classid - * @skb: pointer to skb - * Return: classid if != 0 - */ - BPF_FUNC_get_cgroup_classid, - BPF_FUNC_skb_vlan_push, /* bpf_skb_vlan_push(skb, vlan_proto, vlan_tci) */ - BPF_FUNC_skb_vlan_pop, /* bpf_skb_vlan_pop(skb) */ - - /** - * bpf_skb_[gs]et_tunnel_key(skb, key, size, flags) - * retrieve or populate tunnel metadata - * @skb: pointer to skb - * @key: pointer to 'struct bpf_tunnel_key' - * @size: size of 'struct bpf_tunnel_key' - * @flags: room for future extensions - * Retrun: 0 on success - */ - BPF_FUNC_skb_get_tunnel_key, - BPF_FUNC_skb_set_tunnel_key, - BPF_FUNC_perf_event_read, /* u64 bpf_perf_event_read(&map, index) */ - /** - * bpf_redirect(ifindex, flags) - redirect to another netdev - * @ifindex: ifindex of the net device - * @flags: bit 0 - if set, redirect to ingress instead of egress - * other bits - reserved - * Return: TC_ACT_REDIRECT - */ - BPF_FUNC_redirect, - - /** - * bpf_get_route_realm(skb) - retrieve a dst's tclassid - * @skb: pointer to skb - * Return: realm if != 0 - */ - BPF_FUNC_get_route_realm, - - /** - * bpf_perf_event_output(ctx, map, index, data, size) - output perf raw sample - * @ctx: struct pt_regs* - * @map: pointer to perf_event_array map - * @index: index of event in the map - * @data: data on stack to be output as raw data - * @size: size of data - * Return: 0 on success - */ - BPF_FUNC_perf_event_output, - BPF_FUNC_skb_load_bytes, - - /** - * bpf_get_stackid(ctx, map, flags) - walk user or kernel stack and return id - * @ctx: struct pt_regs* - * @map: pointer to stack_trace map - * @flags: bits 0-7 - numer of stack frames to skip - * bit 8 - collect user stack instead of kernel - * bit 9 - compare stacks by hash only - * bit 10 - if two different stacks hash into the same stackid - * discard old - * other bits - reserved - * Return: >= 0 stackid on success or negative error - */ - BPF_FUNC_get_stackid, - - /** - * bpf_csum_diff(from, from_size, to, to_size, seed) - calculate csum diff - * @from: raw from buffer - * @from_size: length of from buffer - * @to: raw to buffer - * @to_size: length of to buffer - * @seed: optional seed - * Return: csum result - */ - BPF_FUNC_csum_diff, - - /** - * bpf_skb_[gs]et_tunnel_opt(skb, opt, size) - * retrieve or populate tunnel options metadata - * @skb: pointer to skb - * @opt: pointer to raw tunnel option data - * @size: size of @opt - * Return: 0 on success for set, option size for get - */ - BPF_FUNC_skb_get_tunnel_opt, - BPF_FUNC_skb_set_tunnel_opt, - - /** - * bpf_skb_change_proto(skb, proto, flags) - * Change protocol of the skb. Currently supported is - * v4 -> v6, v6 -> v4 transitions. The helper will also - * resize the skb. eBPF program is expected to fill the - * new headers via skb_store_bytes and lX_csum_replace. - * @skb: pointer to skb - * @proto: new skb->protocol type - * @flags: reserved - * Return: 0 on success or negative error - */ - BPF_FUNC_skb_change_proto, - - /** - * bpf_skb_change_type(skb, type) - * Change packet type of skb. - * @skb: pointer to skb - * @type: new skb->pkt_type type - * Return: 0 on success or negative error - */ - BPF_FUNC_skb_change_type, - - /** - * bpf_skb_under_cgroup(skb, map, index) - Check cgroup2 membership of skb - * @skb: pointer to skb - * @map: pointer to bpf_map in BPF_MAP_TYPE_CGROUP_ARRAY type - * @index: index of the cgroup in the bpf_map - * Return: - * == 0 skb failed the cgroup2 descendant test - * == 1 skb succeeded the cgroup2 descendant test - * < 0 error - */ - BPF_FUNC_skb_under_cgroup, - - /** - * bpf_get_hash_recalc(skb) - * Retrieve and possibly recalculate skb->hash. - * @skb: pointer to skb - * Return: hash - */ - BPF_FUNC_get_hash_recalc, - - /** - * u64 bpf_get_current_task(void) - * Returns current task_struct - * Return: current - */ - BPF_FUNC_get_current_task, - - /** - * bpf_probe_write_user(void *dst, void *src, int len) - * safely attempt to write to a location - * @dst: destination address in userspace - * @src: source address on stack - * @len: number of bytes to copy - * Return: 0 on success or negative error - */ - BPF_FUNC_probe_write_user, - - /** - * bpf_current_task_under_cgroup(map, index) - Check cgroup2 membership of current task - * @map: pointer to bpf_map in BPF_MAP_TYPE_CGROUP_ARRAY type - * @index: index of the cgroup in the bpf_map - * Return: - * == 0 current failed the cgroup2 descendant test - * == 1 current succeeded the cgroup2 descendant test - * < 0 error - */ - BPF_FUNC_current_task_under_cgroup, - - /** - * bpf_skb_change_tail(skb, len, flags) - * The helper will resize the skb to the given new size, - * to be used f.e. with control messages. - * @skb: pointer to skb - * @len: new skb length - * @flags: reserved - * Return: 0 on success or negative error - */ - BPF_FUNC_skb_change_tail, - - /** - * bpf_skb_pull_data(skb, len) - * The helper will pull in non-linear data in case the - * skb is non-linear and not all of len are part of the - * linear section. Only needed for read/write with direct - * packet access. - * @skb: pointer to skb - * @len: len to make read/writeable - * Return: 0 on success or negative error - */ - BPF_FUNC_skb_pull_data, - - /** - * bpf_csum_update(skb, csum) - * Adds csum into skb->csum in case of CHECKSUM_COMPLETE. - * @skb: pointer to skb - * @csum: csum to add - * Return: csum on success or negative error - */ - BPF_FUNC_csum_update, - - /** - * bpf_set_hash_invalid(skb) - * Invalidate current skb>hash. - * @skb: pointer to skb - */ - BPF_FUNC_set_hash_invalid, - - /** - * bpf_get_numa_node_id() - * Returns the id of the current NUMA node. - */ - BPF_FUNC_get_numa_node_id, - + __BPF_FUNC_MAPPER(__BPF_ENUM_FN) __BPF_FUNC_MAX_ID, }; +#undef __BPF_ENUM_FN /* All flags used by eBPF helper functions, placed here. */ -- cgit v1.2.3 From 29ba732acbeece1e34c68483d1ec1f3720fa1bb3 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Fri, 11 Nov 2016 10:55:09 -0800 Subject: bpf: Add BPF_MAP_TYPE_LRU_HASH Provide a LRU version of the existing BPF_MAP_TYPE_HASH. Signed-off-by: Martin KaFai Lau Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/uapi/linux/bpf.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/uapi/linux/bpf.h') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index e2f38e0091b6..ed8c6799fb14 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -85,6 +85,7 @@ enum bpf_map_type { BPF_MAP_TYPE_PERCPU_ARRAY, BPF_MAP_TYPE_STACK_TRACE, BPF_MAP_TYPE_CGROUP_ARRAY, + BPF_MAP_TYPE_LRU_HASH, }; enum bpf_prog_type { @@ -106,6 +107,13 @@ enum bpf_prog_type { #define BPF_EXIST 2 /* update existing element */ #define BPF_F_NO_PREALLOC (1U << 0) +/* Instead of having one common LRU list in the + * BPF_MAP_TYPE_LRU_HASH map, use a percpu LRU list + * which can scale and perform better. + * Note, the LRU nodes (including free nodes) cannot be moved + * across different LRU lists. + */ +#define BPF_F_NO_COMMON_LRU (1U << 1) union bpf_attr { struct { /* anonymous struct used by BPF_MAP_CREATE command */ -- cgit v1.2.3 From 8f8449384ec364ba2a654f11f94e754e4ff719e0 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Fri, 11 Nov 2016 10:55:10 -0800 Subject: bpf: Add BPF_MAP_TYPE_LRU_PERCPU_HASH Provide a LRU version of the existing BPF_MAP_TYPE_PERCPU_HASH Signed-off-by: Martin KaFai Lau Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/uapi/linux/bpf.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux/bpf.h') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index ed8c6799fb14..7d9b2832c280 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -86,6 +86,7 @@ enum bpf_map_type { BPF_MAP_TYPE_STACK_TRACE, BPF_MAP_TYPE_CGROUP_ARRAY, BPF_MAP_TYPE_LRU_HASH, + BPF_MAP_TYPE_LRU_PERCPU_HASH, }; enum bpf_prog_type { @@ -108,7 +109,7 @@ enum bpf_prog_type { #define BPF_F_NO_PREALLOC (1U << 0) /* Instead of having one common LRU list in the - * BPF_MAP_TYPE_LRU_HASH map, use a percpu LRU list + * BPF_MAP_TYPE_LRU_[PERCPU_]HASH map, use a percpu LRU list * which can scale and perform better. * Note, the LRU nodes (including free nodes) cannot be moved * across different LRU lists. -- cgit v1.2.3 From 0e33661de493db325435d565a4a722120ae4cbf3 Mon Sep 17 00:00:00 2001 From: Daniel Mack Date: Wed, 23 Nov 2016 16:52:25 +0100 Subject: bpf: add new prog type for cgroup socket filtering This program type is similar to BPF_PROG_TYPE_SOCKET_FILTER, except that it does not allow BPF_LD_[ABS|IND] instructions and hooks up the bpf_skb_load_bytes() helper. Programs of this type will be attached to cgroups for network filtering and accounting. Signed-off-by: Daniel Mack Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/uapi/linux/bpf.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/uapi/linux/bpf.h') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 7d9b2832c280..5ae679fac993 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -98,8 +98,17 @@ enum bpf_prog_type { BPF_PROG_TYPE_TRACEPOINT, BPF_PROG_TYPE_XDP, BPF_PROG_TYPE_PERF_EVENT, + BPF_PROG_TYPE_CGROUP_SKB, }; +enum bpf_attach_type { + BPF_CGROUP_INET_INGRESS, + BPF_CGROUP_INET_EGRESS, + __MAX_BPF_ATTACH_TYPE +}; + +#define MAX_BPF_ATTACH_TYPE __MAX_BPF_ATTACH_TYPE + #define BPF_PSEUDO_MAP_FD 1 /* flags for BPF_MAP_UPDATE_ELEM command */ -- cgit v1.2.3 From f4324551489e8781d838f941b7aee4208e52e8bf Mon Sep 17 00:00:00 2001 From: Daniel Mack Date: Wed, 23 Nov 2016 16:52:27 +0100 Subject: bpf: add BPF_PROG_ATTACH and BPF_PROG_DETACH commands Extend the bpf(2) syscall by two new commands, BPF_PROG_ATTACH and BPF_PROG_DETACH which allow attaching and detaching eBPF programs to a target. On the API level, the target could be anything that has an fd in userspace, hence the name of the field in union bpf_attr is called 'target_fd'. When called with BPF_ATTACH_TYPE_CGROUP_INET_{E,IN}GRESS, the target is expected to be a valid file descriptor of a cgroup v2 directory which has the bpf controller enabled. These are the only use-cases implemented by this patch at this point, but more can be added. If a program of the given type already exists in the given cgroup, the program is swapped automically, so userspace does not have to drop an existing program first before installing a new one, which would otherwise leave a gap in which no program is attached. For more information on the propagation logic to subcgroups, please refer to the bpf cgroup controller implementation. The API is guarded by CAP_NET_ADMIN. Signed-off-by: Daniel Mack Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/uapi/linux/bpf.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/uapi/linux/bpf.h') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 5ae679fac993..1370a9d1456f 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -73,6 +73,8 @@ enum bpf_cmd { BPF_PROG_LOAD, BPF_OBJ_PIN, BPF_OBJ_GET, + BPF_PROG_ATTACH, + BPF_PROG_DETACH, }; enum bpf_map_type { @@ -159,6 +161,12 @@ union bpf_attr { __aligned_u64 pathname; __u32 bpf_fd; }; + + struct { /* anonymous struct used by BPF_PROG_ATTACH/DETACH commands */ + __u32 target_fd; /* container object to attach to */ + __u32 attach_bpf_fd; /* eBPF program to attach */ + __u32 attach_type; + }; } __attribute__((aligned(8))); /* BPF helper function descriptions: -- cgit v1.2.3 From 3a0af8fd61f90920f6fa04e4f1e9a6a73c1b4fd2 Mon Sep 17 00:00:00 2001 From: Thomas Graf Date: Wed, 30 Nov 2016 17:10:10 +0100 Subject: bpf: BPF for lightweight tunnel infrastructure Registers new BPF program types which correspond to the LWT hooks: - BPF_PROG_TYPE_LWT_IN => dst_input() - BPF_PROG_TYPE_LWT_OUT => dst_output() - BPF_PROG_TYPE_LWT_XMIT => lwtunnel_xmit() The separate program types are required to differentiate between the capabilities each LWT hook allows: * Programs attached to dst_input() or dst_output() are restricted and may only read the data of an skb. This prevent modification and possible invalidation of already validated packet headers on receive and the construction of illegal headers while the IP headers are still being assembled. * Programs attached to lwtunnel_xmit() are allowed to modify packet content as well as prepending an L2 header via a newly introduced helper bpf_skb_change_head(). This is safe as lwtunnel_xmit() is invoked after the IP header has been assembled completely. All BPF programs receive an skb with L3 headers attached and may return one of the following error codes: BPF_OK - Continue routing as per nexthop BPF_DROP - Drop skb and return EPERM BPF_REDIRECT - Redirect skb to device as per redirect() helper. (Only valid in lwtunnel_xmit() context) The return codes are binary compatible with their TC_ACT_ relatives to ease compatibility. Signed-off-by: Thomas Graf Acked-by: Alexei Starovoitov Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- include/uapi/linux/bpf.h | 32 +++++++++++++++++++++++++++++++- 1 file changed, 31 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux/bpf.h') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 1370a9d1456f..22ac82792687 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -101,6 +101,9 @@ enum bpf_prog_type { BPF_PROG_TYPE_XDP, BPF_PROG_TYPE_PERF_EVENT, BPF_PROG_TYPE_CGROUP_SKB, + BPF_PROG_TYPE_LWT_IN, + BPF_PROG_TYPE_LWT_OUT, + BPF_PROG_TYPE_LWT_XMIT, }; enum bpf_attach_type { @@ -409,6 +412,16 @@ union bpf_attr { * * int bpf_get_numa_node_id() * Return: Id of current NUMA node. + * + * int bpf_skb_change_head() + * Grows headroom of skb and adjusts MAC header offset accordingly. + * Will extends/reallocae as required automatically. + * May change skb data pointer and will thus invalidate any check + * performed for direct packet access. + * @skb: pointer to skb + * @len: length of header to be pushed in front + * @flags: Flags (unused for now) + * Return: 0 on success or negative error */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -453,7 +466,8 @@ union bpf_attr { FN(skb_pull_data), \ FN(csum_update), \ FN(set_hash_invalid), \ - FN(get_numa_node_id), + FN(get_numa_node_id), \ + FN(skb_change_head), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call @@ -537,6 +551,22 @@ struct bpf_tunnel_key { __u32 tunnel_label; }; +/* Generic BPF return codes which all BPF program types may support. + * The values are binary compatible with their TC_ACT_* counter-part to + * provide backwards compatibility with existing SCHED_CLS and SCHED_ACT + * programs. + * + * XDP is handled seprately, see XDP_*. + */ +enum bpf_ret_code { + BPF_OK = 0, + /* 1 reserved */ + BPF_DROP = 2, + /* 3-6 reserved */ + BPF_REDIRECT = 7, + /* >127 are reserved for prog type specific return codes */ +}; + /* User return codes for XDP prog type. * A valid XDP program must return one of these defined values. All other * return codes are reserved for future use. Unknown return codes will result -- cgit v1.2.3 From 61023658760032e97869b07d54be9681d2529e77 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Thu, 1 Dec 2016 08:48:04 -0800 Subject: bpf: Add new cgroup attach type to enable sock modifications Add new cgroup based program type, BPF_PROG_TYPE_CGROUP_SOCK. Similar to BPF_PROG_TYPE_CGROUP_SKB programs can be attached to a cgroup and run any time a process in the cgroup opens an AF_INET or AF_INET6 socket. Currently only sk_bound_dev_if is exported to userspace for modification by a bpf program. This allows a cgroup to be configured such that AF_INET{6} sockets opened by processes are automatically bound to a specific device. In turn, this enables the running of programs that do not support SO_BINDTODEVICE in a specific VRF context / L3 domain. Signed-off-by: David Ahern Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/uapi/linux/bpf.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/uapi/linux/bpf.h') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 22ac82792687..bfe5e31a1288 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -101,6 +101,7 @@ enum bpf_prog_type { BPF_PROG_TYPE_XDP, BPF_PROG_TYPE_PERF_EVENT, BPF_PROG_TYPE_CGROUP_SKB, + BPF_PROG_TYPE_CGROUP_SOCK, BPF_PROG_TYPE_LWT_IN, BPF_PROG_TYPE_LWT_OUT, BPF_PROG_TYPE_LWT_XMIT, @@ -109,6 +110,7 @@ enum bpf_prog_type { enum bpf_attach_type { BPF_CGROUP_INET_INGRESS, BPF_CGROUP_INET_EGRESS, + BPF_CGROUP_INET_SOCK_CREATE, __MAX_BPF_ATTACH_TYPE }; @@ -567,6 +569,10 @@ enum bpf_ret_code { /* >127 are reserved for prog type specific return codes */ }; +struct bpf_sock { + __u32 bound_dev_if; +}; + /* User return codes for XDP prog type. * A valid XDP program must return one of these defined values. All other * return codes are reserved for future use. Unknown return codes will result -- cgit v1.2.3 From aa4c1037a30f4e88f444e83d42c2befbe0d5caf5 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Thu, 1 Dec 2016 08:48:06 -0800 Subject: bpf: Add support for reading socket family, type, protocol Add socket family, type and protocol to bpf_sock allowing bpf programs read-only access. Add __sk_flags_offset[0] to struct sock before the bitfield to programmtically determine the offset of the unsigned int containing protocol and type. Signed-off-by: David Ahern Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/uapi/linux/bpf.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/uapi/linux/bpf.h') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index bfe5e31a1288..6123d9b8e828 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -571,6 +571,9 @@ enum bpf_ret_code { struct bpf_sock { __u32 bound_dev_if; + __u32 family; + __u32 type; + __u32 protocol; }; /* User return codes for XDP prog type. -- cgit v1.2.3 From 17bedab2723145d17b14084430743549e6943d03 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Wed, 7 Dec 2016 15:53:11 -0800 Subject: bpf: xdp: Allow head adjustment in XDP prog This patch allows XDP prog to extend/remove the packet data at the head (like adding or removing header). It is done by adding a new XDP helper bpf_xdp_adjust_head(). It also renames bpf_helper_changes_skb_data() to bpf_helper_changes_pkt_data() to better reflect that XDP prog does not work on skb. This patch adds one "xdp_adjust_head" bit to bpf_prog for the XDP-capable driver to check if the XDP prog requires bpf_xdp_adjust_head() support. The driver can then decide to error out during XDP_SETUP_PROG. Signed-off-by: Martin KaFai Lau Acked-by: Daniel Borkmann Acked-by: Alexei Starovoitov Acked-by: John Fastabend Signed-off-by: David S. Miller --- include/uapi/linux/bpf.h | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux/bpf.h') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 6123d9b8e828..0eb0e87dbe9f 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -424,6 +424,12 @@ union bpf_attr { * @len: length of header to be pushed in front * @flags: Flags (unused for now) * Return: 0 on success or negative error + * + * int bpf_xdp_adjust_head(xdp_md, delta) + * Adjust the xdp_md.data by delta + * @xdp_md: pointer to xdp_md + * @delta: An positive/negative integer to be added to xdp_md.data + * Return: 0 on success or negative on error */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -469,7 +475,8 @@ union bpf_attr { FN(csum_update), \ FN(set_hash_invalid), \ FN(get_numa_node_id), \ - FN(skb_change_head), + FN(skb_change_head), \ + FN(xdp_adjust_head), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call @@ -576,6 +583,8 @@ struct bpf_sock { __u32 protocol; }; +#define XDP_PACKET_HEADROOM 256 + /* User return codes for XDP prog type. * A valid XDP program must return one of these defined values. All other * return codes are reserved for future use. Unknown return codes will result -- cgit v1.2.3