mirror of
https://github.com/torvalds/linux.git
synced 2024-11-26 14:12:06 +00:00
d4ccaf58a8
Cgroup_iter is a type of bpf_iter. It walks over cgroups in four modes: - walking a cgroup's descendants in pre-order. - walking a cgroup's descendants in post-order. - walking a cgroup's ancestors. - process only the given cgroup. When attaching cgroup_iter, one can set a cgroup to the iter_link created from attaching. This cgroup is passed as a file descriptor or cgroup id and serves as the starting point of the walk. If no cgroup is specified, the starting point will be the root cgroup v2. For walking descendants, one can specify the order: either pre-order or post-order. For walking ancestors, the walk starts at the specified cgroup and ends at the root. One can also terminate the walk early by returning 1 from the iter program. Note that because walking cgroup hierarchy holds cgroup_mutex, the iter program is called with cgroup_mutex held. Currently only one session is supported, which means, depending on the volume of data bpf program intends to send to user space, the number of cgroups that can be walked is limited. For example, given the current buffer size is 8 * PAGE_SIZE, if the program sends 64B data for each cgroup, assuming PAGE_SIZE is 4kb, the total number of cgroups that can be walked is 512. This is a limitation of cgroup_iter. If the output data is larger than the kernel buffer size, after all data in the kernel buffer is consumed by user space, the subsequent read() syscall will signal EOPNOTSUPP. In order to work around, the user may have to update their program to reduce the volume of data sent to output. For example, skip some uninteresting cgroups. In future, we may extend bpf_iter flags to allow customizing buffer size. Acked-by: Yonghong Song <yhs@fb.com> Acked-by: Tejun Heo <tj@kernel.org> Signed-off-by: Hao Luo <haoluo@google.com> Link: https://lore.kernel.org/r/20220824233117.1312810-2-haoluo@google.com Signed-off-by: Alexei Starovoitov <ast@kernel.org>
46 lines
1.7 KiB
Makefile
46 lines
1.7 KiB
Makefile
# SPDX-License-Identifier: GPL-2.0
|
|
obj-y := core.o
|
|
ifneq ($(CONFIG_BPF_JIT_ALWAYS_ON),y)
|
|
# ___bpf_prog_run() needs GCSE disabled on x86; see 3193c0836f203 for details
|
|
cflags-nogcse-$(CONFIG_X86)$(CONFIG_CC_IS_GCC) := -fno-gcse
|
|
endif
|
|
CFLAGS_core.o += $(call cc-disable-warning, override-init) $(cflags-nogcse-yy)
|
|
|
|
obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o bpf_iter.o map_iter.o task_iter.o prog_iter.o link_iter.o
|
|
obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list.o lpm_trie.o map_in_map.o bloom_filter.o
|
|
obj-$(CONFIG_BPF_SYSCALL) += local_storage.o queue_stack_maps.o ringbuf.o
|
|
obj-$(CONFIG_BPF_SYSCALL) += bpf_local_storage.o bpf_task_storage.o
|
|
obj-${CONFIG_BPF_LSM} += bpf_inode_storage.o
|
|
obj-$(CONFIG_BPF_SYSCALL) += disasm.o
|
|
obj-$(CONFIG_BPF_JIT) += trampoline.o
|
|
obj-$(CONFIG_BPF_SYSCALL) += btf.o
|
|
obj-$(CONFIG_BPF_JIT) += dispatcher.o
|
|
ifeq ($(CONFIG_NET),y)
|
|
obj-$(CONFIG_BPF_SYSCALL) += devmap.o
|
|
obj-$(CONFIG_BPF_SYSCALL) += cpumap.o
|
|
obj-$(CONFIG_BPF_SYSCALL) += offload.o
|
|
obj-$(CONFIG_BPF_SYSCALL) += net_namespace.o
|
|
endif
|
|
ifeq ($(CONFIG_PERF_EVENTS),y)
|
|
obj-$(CONFIG_BPF_SYSCALL) += stackmap.o
|
|
endif
|
|
ifeq ($(CONFIG_CGROUPS),y)
|
|
obj-$(CONFIG_BPF_SYSCALL) += cgroup_iter.o
|
|
endif
|
|
obj-$(CONFIG_CGROUP_BPF) += cgroup.o
|
|
ifeq ($(CONFIG_INET),y)
|
|
obj-$(CONFIG_BPF_SYSCALL) += reuseport_array.o
|
|
endif
|
|
ifeq ($(CONFIG_SYSFS),y)
|
|
obj-$(CONFIG_DEBUG_INFO_BTF) += sysfs_btf.o
|
|
endif
|
|
ifeq ($(CONFIG_BPF_JIT),y)
|
|
obj-$(CONFIG_BPF_SYSCALL) += bpf_struct_ops.o
|
|
obj-${CONFIG_BPF_LSM} += bpf_lsm.o
|
|
endif
|
|
obj-$(CONFIG_BPF_PRELOAD) += preload/
|
|
|
|
obj-$(CONFIG_BPF_SYSCALL) += relo_core.o
|
|
$(obj)/relo_core.o: $(srctree)/tools/lib/bpf/relo_core.c FORCE
|
|
$(call if_changed_rule,cc_o_c)
|