| Message ID | 20190322223848.3338614-2-javierhonduco@fb.com |
|---|---|
| State | Changes Requested |
| Delegated to: | BPF Maintainers |
| Headers | show |
| Series | bpf: add bpf_progenyof helper | expand |
On 03/22/2019 11:38 PM, Javier Honduvilla Coto wrote: > This patch adds the bpf_progenyof helper which receives a PID and returns > 1 if the process currently being executed is in the process hierarchy > including itself or 0 if not. > > This is very useful in tracing programs when we want to filter by a > given PID and all the children it might spawn. The current workarounds > most people implement for this purpose have issues: > > - Attaching to process spawning syscalls and dynamically add those PIDs > to some bpf map that would be used to filter is cumbersome and > potentially racy. > - Unrolling some loop to perform what this helper is doing consumes lots > of instructions. That and the impossibility to jump backwards makes it > really hard to be correct in really large process chains. > > Signed-off-by: Javier Honduvilla Coto <javierhonduco@fb.com> > --- > include/linux/bpf.h | 1 + > include/uapi/linux/bpf.h | 10 +++++++++- > kernel/bpf/core.c | 1 + > kernel/bpf/helpers.c | 32 ++++++++++++++++++++++++++++++++ > kernel/trace/bpf_trace.c | 2 ++ > 5 files changed, 45 insertions(+), 1 deletion(-) > > diff --git a/include/linux/bpf.h b/include/linux/bpf.h > index f62897198844..bd0d2b38e7d5 100644 > --- a/include/linux/bpf.h > +++ b/include/linux/bpf.h > @@ -930,6 +930,7 @@ extern const struct bpf_func_proto bpf_sk_redirect_map_proto; > extern const struct bpf_func_proto bpf_spin_lock_proto; > extern const struct bpf_func_proto bpf_spin_unlock_proto; > extern const struct bpf_func_proto bpf_get_local_storage_proto; > +extern const struct bpf_func_proto bpf_progenyof_proto; > > /* Shared helpers among cBPF and eBPF. */ > void bpf_user_rnd_init_once(void); > diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h > index 3c04410137d9..cf54cc739bf4 100644 > --- a/include/uapi/linux/bpf.h > +++ b/include/uapi/linux/bpf.h > @@ -2463,6 +2463,13 @@ union bpf_attr { > * Return > * 0 if iph and th are a valid SYN cookie ACK, or a negative error > * otherwise. > + * int bpf_progenyof(int pid) > + * Description > + * This helper is useful in programs that want to filter events > + * happening to a pid of any of its descendants. > + * Return > + * 1 if the currently executing process' pid is in the process > + * hierarchy of the passed pid. 0 Otherwise. What about the -EINVAL? > */ > #define __BPF_FUNC_MAPPER(FN) \ > FN(unspec), \ > @@ -2565,7 +2572,8 @@ union bpf_attr { > FN(skb_ecn_set_ce), \ > FN(get_listener_sock), \ > FN(skc_lookup_tcp), \ > - FN(tcp_check_syncookie), > + FN(tcp_check_syncookie), \ > + FN(progenyof), > > /* integer value in 'imm' field of BPF_CALL instruction selects which helper > * function eBPF program intends to call > diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c > index ff09d32a8a1b..437986497468 100644 > --- a/kernel/bpf/core.c > +++ b/kernel/bpf/core.c > @@ -2044,6 +2044,7 @@ const struct bpf_func_proto bpf_get_current_uid_gid_proto __weak; > const struct bpf_func_proto bpf_get_current_comm_proto __weak; > const struct bpf_func_proto bpf_get_current_cgroup_id_proto __weak; > const struct bpf_func_proto bpf_get_local_storage_proto __weak; > +const struct bpf_func_proto bpf_progenyof_proto __weak; > > const struct bpf_func_proto * __weak bpf_get_trace_printk_proto(void) > { > diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c > index a411fc17d265..f093b35d1ba8 100644 > --- a/kernel/bpf/helpers.c > +++ b/kernel/bpf/helpers.c > @@ -18,6 +18,7 @@ > #include <linux/sched.h> > #include <linux/uidgid.h> > #include <linux/filter.h> > +#include <linux/init_task.h> > > /* If kernel subsystem is allowing eBPF programs to call this function, > * inside its own verifier_ops->get_func_proto() callback it should return > @@ -364,3 +365,34 @@ const struct bpf_func_proto bpf_get_local_storage_proto = { > }; > #endif > #endif > + > +BPF_CALL_1(bpf_progenyof, int, pid) Nit: could we add a more descriptive helper name? What's progenyof? Also s/int/pid_t/? > +{ > + int result = 0; > + struct task_struct *task = current; > + > + WARN_ON(!rcu_read_lock_held()); This is not needed since it's guaranteed in BPF. > + if (unlikely(!task)) > + return -EINVAL; > + > + if (pid == 0) > + return 1; > + > + while (task != &init_task) { > + if (task->pid == pid) { > + result = 1; > + break; > + } > + task = rcu_dereference(task->real_parent); > + } > + > + return result; > +} > + > +const struct bpf_func_proto bpf_progenyof_proto = { > + .func = bpf_progenyof, > + .gpl_only = false, > + .ret_type = RET_INTEGER, > + .arg1_type = ARG_ANYTHING, > +}; > diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c > index d64c00afceb5..e69283d423ff 100644 > --- a/kernel/trace/bpf_trace.c > +++ b/kernel/trace/bpf_trace.c > @@ -599,6 +599,8 @@ tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) > return &bpf_get_prandom_u32_proto; > case BPF_FUNC_probe_read_str: > return &bpf_probe_read_str_proto; > + case BPF_FUNC_progenyof: > + return &bpf_progenyof_proto; > #ifdef CONFIG_CGROUPS > case BPF_FUNC_get_current_cgroup_id: > return &bpf_get_current_cgroup_id_proto; >
On Mon, Mar 25, 2019 at 03:17:03PM +0100, Daniel Borkmann wrote: > On 03/22/2019 11:38 PM, Javier Honduvilla Coto wrote: > > This patch adds the bpf_progenyof helper which receives a PID and returns > > 1 if the process currently being executed is in the process hierarchy > > including itself or 0 if not. > > > > This is very useful in tracing programs when we want to filter by a > > given PID and all the children it might spawn. The current workarounds > > most people implement for this purpose have issues: > > > > - Attaching to process spawning syscalls and dynamically add those PIDs > > to some bpf map that would be used to filter is cumbersome and > > potentially racy. > > - Unrolling some loop to perform what this helper is doing consumes lots > > of instructions. That and the impossibility to jump backwards makes it > > really hard to be correct in really large process chains. > > > > Signed-off-by: Javier Honduvilla Coto <javierhonduco@fb.com> > > --- > > include/linux/bpf.h | 1 + > > include/uapi/linux/bpf.h | 10 +++++++++- > > kernel/bpf/core.c | 1 + > > kernel/bpf/helpers.c | 32 ++++++++++++++++++++++++++++++++ > > kernel/trace/bpf_trace.c | 2 ++ > > 5 files changed, 45 insertions(+), 1 deletion(-) > > > > diff --git a/include/linux/bpf.h b/include/linux/bpf.h > > index f62897198844..bd0d2b38e7d5 100644 > > --- a/include/linux/bpf.h > > +++ b/include/linux/bpf.h > > @@ -930,6 +930,7 @@ extern const struct bpf_func_proto bpf_sk_redirect_map_proto; > > extern const struct bpf_func_proto bpf_spin_lock_proto; > > extern const struct bpf_func_proto bpf_spin_unlock_proto; > > extern const struct bpf_func_proto bpf_get_local_storage_proto; > > +extern const struct bpf_func_proto bpf_progenyof_proto; > > > > /* Shared helpers among cBPF and eBPF. */ > > void bpf_user_rnd_init_once(void); > > diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h > > index 3c04410137d9..cf54cc739bf4 100644 > > --- a/include/uapi/linux/bpf.h > > +++ b/include/uapi/linux/bpf.h > > @@ -2463,6 +2463,13 @@ union bpf_attr { > > * Return > > * 0 if iph and th are a valid SYN cookie ACK, or a negative error > > * otherwise. > > + * int bpf_progenyof(int pid) > > + * Description > > + * This helper is useful in programs that want to filter events > > + * happening to a pid of any of its descendants. > > + * Return > > + * 1 if the currently executing process' pid is in the process > > + * hierarchy of the passed pid. 0 Otherwise. > > What about the -EINVAL? I think we can remove this, as Alexei told me this was not needed anymore (copied it from other helpers that have it). Should we remove that check in other patch for the other helpers that have it? > > > */ > > #define __BPF_FUNC_MAPPER(FN) \ > > FN(unspec), \ > > @@ -2565,7 +2572,8 @@ union bpf_attr { > > FN(skb_ecn_set_ce), \ > > FN(get_listener_sock), \ > > FN(skc_lookup_tcp), \ > > - FN(tcp_check_syncookie), > > + FN(tcp_check_syncookie), \ > > + FN(progenyof), > > > > /* integer value in 'imm' field of BPF_CALL instruction selects which helper > > * function eBPF program intends to call > > diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c > > index ff09d32a8a1b..437986497468 100644 > > --- a/kernel/bpf/core.c > > +++ b/kernel/bpf/core.c > > @@ -2044,6 +2044,7 @@ const struct bpf_func_proto bpf_get_current_uid_gid_proto __weak; > > const struct bpf_func_proto bpf_get_current_comm_proto __weak; > > const struct bpf_func_proto bpf_get_current_cgroup_id_proto __weak; > > const struct bpf_func_proto bpf_get_local_storage_proto __weak; > > +const struct bpf_func_proto bpf_progenyof_proto __weak; > > > > const struct bpf_func_proto * __weak bpf_get_trace_printk_proto(void) > > { > > diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c > > index a411fc17d265..f093b35d1ba8 100644 > > --- a/kernel/bpf/helpers.c > > +++ b/kernel/bpf/helpers.c > > @@ -18,6 +18,7 @@ > > #include <linux/sched.h> > > #include <linux/uidgid.h> > > #include <linux/filter.h> > > +#include <linux/init_task.h> > > > > /* If kernel subsystem is allowing eBPF programs to call this function, > > * inside its own verifier_ops->get_func_proto() callback it should return > > @@ -364,3 +365,34 @@ const struct bpf_func_proto bpf_get_local_storage_proto = { > > }; > > #endif > > #endif > > + > > +BPF_CALL_1(bpf_progenyof, int, pid) > > Nit: could we add a more descriptive helper name? What's progenyof? Also s/int/pid_t/? > It's true that "progeny" is not a very commonly used word :D. A coworker suggested "descendantof", what do you think? It's a bit difficult to convey "is true on the passed pid + on all the process under the hierarchy chain of that pid", so I will try rewording the docs so the semantics are very clear! Will change to pid_t :) Thanks! > > +{ > > + int result = 0; > > + struct task_struct *task = current; > > + > > + WARN_ON(!rcu_read_lock_held()); > > This is not needed since it's guaranteed in BPF. > > > + if (unlikely(!task)) > > + return -EINVAL; > > + > > + if (pid == 0) > > + return 1; > > + > > + while (task != &init_task) { > > + if (task->pid == pid) { > > + result = 1; > > + break; > > + } > > + task = rcu_dereference(task->real_parent); > > + } > > + > > + return result; > > +} > > + > > +const struct bpf_func_proto bpf_progenyof_proto = { > > + .func = bpf_progenyof, > > + .gpl_only = false, > > + .ret_type = RET_INTEGER, > > + .arg1_type = ARG_ANYTHING, > > +}; > > diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c > > index d64c00afceb5..e69283d423ff 100644 > > --- a/kernel/trace/bpf_trace.c > > +++ b/kernel/trace/bpf_trace.c > > @@ -599,6 +599,8 @@ tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) > > return &bpf_get_prandom_u32_proto; > > case BPF_FUNC_probe_read_str: > > return &bpf_probe_read_str_proto; > > + case BPF_FUNC_progenyof: > > + return &bpf_progenyof_proto; > > #ifdef CONFIG_CGROUPS > > case BPF_FUNC_get_current_cgroup_id: > > return &bpf_get_current_cgroup_id_proto; > > >
On Mon, Mar 25, 2019 at 03:17:03PM +0100, Daniel Borkmann wrote: > On 03/22/2019 11:38 PM, Javier Honduvilla Coto wrote: > > This patch adds the bpf_progenyof helper which receives a PID and returns > > 1 if the process currently being executed is in the process hierarchy > > including itself or 0 if not. > > > > This is very useful in tracing programs when we want to filter by a > > given PID and all the children it might spawn. The current workarounds > > most people implement for this purpose have issues: > > > > - Attaching to process spawning syscalls and dynamically add those PIDs > > to some bpf map that would be used to filter is cumbersome and > > potentially racy. > > - Unrolling some loop to perform what this helper is doing consumes lots > > of instructions. That and the impossibility to jump backwards makes it > > really hard to be correct in really large process chains. > > > > Signed-off-by: Javier Honduvilla Coto <javierhonduco@fb.com> > > --- > > include/linux/bpf.h | 1 + > > include/uapi/linux/bpf.h | 10 +++++++++- > > kernel/bpf/core.c | 1 + > > kernel/bpf/helpers.c | 32 ++++++++++++++++++++++++++++++++ > > kernel/trace/bpf_trace.c | 2 ++ > > 5 files changed, 45 insertions(+), 1 deletion(-) > > > > diff --git a/include/linux/bpf.h b/include/linux/bpf.h > > index f62897198844..bd0d2b38e7d5 100644 > > --- a/include/linux/bpf.h > > +++ b/include/linux/bpf.h > > @@ -930,6 +930,7 @@ extern const struct bpf_func_proto bpf_sk_redirect_map_proto; > > extern const struct bpf_func_proto bpf_spin_lock_proto; > > extern const struct bpf_func_proto bpf_spin_unlock_proto; > > extern const struct bpf_func_proto bpf_get_local_storage_proto; > > +extern const struct bpf_func_proto bpf_progenyof_proto; > > > > /* Shared helpers among cBPF and eBPF. */ > > void bpf_user_rnd_init_once(void); > > diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h > > index 3c04410137d9..cf54cc739bf4 100644 > > --- a/include/uapi/linux/bpf.h > > +++ b/include/uapi/linux/bpf.h > > @@ -2463,6 +2463,13 @@ union bpf_attr { > > * Return > > * 0 if iph and th are a valid SYN cookie ACK, or a negative error > > * otherwise. > > + * int bpf_progenyof(int pid) > > + * Description > > + * This helper is useful in programs that want to filter events > > + * happening to a pid of any of its descendants. > > + * Return > > + * 1 if the currently executing process' pid is in the process > > + * hierarchy of the passed pid. 0 Otherwise. > > What about the -EINVAL? > > > */ > > #define __BPF_FUNC_MAPPER(FN) \ > > FN(unspec), \ > > @@ -2565,7 +2572,8 @@ union bpf_attr { > > FN(skb_ecn_set_ce), \ > > FN(get_listener_sock), \ > > FN(skc_lookup_tcp), \ > > - FN(tcp_check_syncookie), > > + FN(tcp_check_syncookie), \ > > + FN(progenyof), > > > > /* integer value in 'imm' field of BPF_CALL instruction selects which helper > > * function eBPF program intends to call > > diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c > > index ff09d32a8a1b..437986497468 100644 > > --- a/kernel/bpf/core.c > > +++ b/kernel/bpf/core.c > > @@ -2044,6 +2044,7 @@ const struct bpf_func_proto bpf_get_current_uid_gid_proto __weak; > > const struct bpf_func_proto bpf_get_current_comm_proto __weak; > > const struct bpf_func_proto bpf_get_current_cgroup_id_proto __weak; > > const struct bpf_func_proto bpf_get_local_storage_proto __weak; > > +const struct bpf_func_proto bpf_progenyof_proto __weak; > > > > const struct bpf_func_proto * __weak bpf_get_trace_printk_proto(void) > > { > > diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c > > index a411fc17d265..f093b35d1ba8 100644 > > --- a/kernel/bpf/helpers.c > > +++ b/kernel/bpf/helpers.c > > @@ -18,6 +18,7 @@ > > #include <linux/sched.h> > > #include <linux/uidgid.h> > > #include <linux/filter.h> > > +#include <linux/init_task.h> > > > > /* If kernel subsystem is allowing eBPF programs to call this function, > > * inside its own verifier_ops->get_func_proto() callback it should return > > @@ -364,3 +365,34 @@ const struct bpf_func_proto bpf_get_local_storage_proto = { > > }; > > #endif > > #endif > > + > > +BPF_CALL_1(bpf_progenyof, int, pid) > > Nit: could we add a more descriptive helper name? What's progenyof? Also s/int/pid_t/? > > > +{ > > + int result = 0; > > + struct task_struct *task = current; > > + > > + WARN_ON(!rcu_read_lock_held()); > > This is not needed since it's guaranteed in BPF. Sure, thanks! > > > + if (unlikely(!task)) > > + return -EINVAL; > > + > > + if (pid == 0) > > + return 1; > > + > > + while (task != &init_task) { > > + if (task->pid == pid) { > > + result = 1; > > + break; > > + } > > + task = rcu_dereference(task->real_parent); > > + } > > + > > + return result; > > +} > > + > > +const struct bpf_func_proto bpf_progenyof_proto = { > > + .func = bpf_progenyof, > > + .gpl_only = false, > > + .ret_type = RET_INTEGER, > > + .arg1_type = ARG_ANYTHING, > > +}; > > diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c > > index d64c00afceb5..e69283d423ff 100644 > > --- a/kernel/trace/bpf_trace.c > > +++ b/kernel/trace/bpf_trace.c > > @@ -599,6 +599,8 @@ tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) > > return &bpf_get_prandom_u32_proto; > > case BPF_FUNC_probe_read_str: > > return &bpf_probe_read_str_proto; > > + case BPF_FUNC_progenyof: > > + return &bpf_progenyof_proto; > > #ifdef CONFIG_CGROUPS > > case BPF_FUNC_get_current_cgroup_id: > > return &bpf_get_current_cgroup_id_proto; > > >
On Wed, Mar 27, 2019 at 8:59 AM Javier Honduvilla Coto <javierhonduco@fb.com> wrote: > > On Mon, Mar 25, 2019 at 03:17:03PM +0100, Daniel Borkmann wrote: > > On 03/22/2019 11:38 PM, Javier Honduvilla Coto wrote: > > > This patch adds the bpf_progenyof helper which receives a PID and returns > > > 1 if the process currently being executed is in the process hierarchy > > > including itself or 0 if not. > > > > > > This is very useful in tracing programs when we want to filter by a > > > given PID and all the children it might spawn. The current workarounds > > > most people implement for this purpose have issues: > > > > > > - Attaching to process spawning syscalls and dynamically add those PIDs > > > to some bpf map that would be used to filter is cumbersome and > > > potentially racy. > > > - Unrolling some loop to perform what this helper is doing consumes lots > > > of instructions. That and the impossibility to jump backwards makes it > > > really hard to be correct in really large process chains. > > > > > > Signed-off-by: Javier Honduvilla Coto <javierhonduco@fb.com> > > > --- > > > include/linux/bpf.h | 1 + > > > include/uapi/linux/bpf.h | 10 +++++++++- > > > kernel/bpf/core.c | 1 + > > > kernel/bpf/helpers.c | 32 ++++++++++++++++++++++++++++++++ > > > kernel/trace/bpf_trace.c | 2 ++ > > > 5 files changed, 45 insertions(+), 1 deletion(-) > > > > > > diff --git a/include/linux/bpf.h b/include/linux/bpf.h > > > index f62897198844..bd0d2b38e7d5 100644 > > > --- a/include/linux/bpf.h > > > +++ b/include/linux/bpf.h > > > @@ -930,6 +930,7 @@ extern const struct bpf_func_proto bpf_sk_redirect_map_proto; > > > extern const struct bpf_func_proto bpf_spin_lock_proto; > > > extern const struct bpf_func_proto bpf_spin_unlock_proto; > > > extern const struct bpf_func_proto bpf_get_local_storage_proto; > > > +extern const struct bpf_func_proto bpf_progenyof_proto; > > > > > > /* Shared helpers among cBPF and eBPF. */ > > > void bpf_user_rnd_init_once(void); > > > diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h > > > index 3c04410137d9..cf54cc739bf4 100644 > > > --- a/include/uapi/linux/bpf.h > > > +++ b/include/uapi/linux/bpf.h > > > @@ -2463,6 +2463,13 @@ union bpf_attr { > > > * Return > > > * 0 if iph and th are a valid SYN cookie ACK, or a negative error > > > * otherwise. > > > + * int bpf_progenyof(int pid) > > > + * Description > > > + * This helper is useful in programs that want to filter events > > > + * happening to a pid of any of its descendants. > > > + * Return > > > + * 1 if the currently executing process' pid is in the process > > > + * hierarchy of the passed pid. 0 Otherwise. > > > > What about the -EINVAL? > > I think we can remove this, as Alexei told me this was not needed > anymore (copied it from other helpers that have it). > > Should we remove that check in other patch for the other helpers > that have it? > > > > > > */ > > > #define __BPF_FUNC_MAPPER(FN) \ > > > FN(unspec), \ > > > @@ -2565,7 +2572,8 @@ union bpf_attr { > > > FN(skb_ecn_set_ce), \ > > > FN(get_listener_sock), \ > > > FN(skc_lookup_tcp), \ > > > - FN(tcp_check_syncookie), > > > + FN(tcp_check_syncookie), \ > > > + FN(progenyof), > > > > > > /* integer value in 'imm' field of BPF_CALL instruction selects which helper > > > * function eBPF program intends to call > > > diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c > > > index ff09d32a8a1b..437986497468 100644 > > > --- a/kernel/bpf/core.c > > > +++ b/kernel/bpf/core.c > > > @@ -2044,6 +2044,7 @@ const struct bpf_func_proto bpf_get_current_uid_gid_proto __weak; > > > const struct bpf_func_proto bpf_get_current_comm_proto __weak; > > > const struct bpf_func_proto bpf_get_current_cgroup_id_proto __weak; > > > const struct bpf_func_proto bpf_get_local_storage_proto __weak; > > > +const struct bpf_func_proto bpf_progenyof_proto __weak; > > > > > > const struct bpf_func_proto * __weak bpf_get_trace_printk_proto(void) > > > { > > > diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c > > > index a411fc17d265..f093b35d1ba8 100644 > > > --- a/kernel/bpf/helpers.c > > > +++ b/kernel/bpf/helpers.c > > > @@ -18,6 +18,7 @@ > > > #include <linux/sched.h> > > > #include <linux/uidgid.h> > > > #include <linux/filter.h> > > > +#include <linux/init_task.h> > > > > > > /* If kernel subsystem is allowing eBPF programs to call this function, > > > * inside its own verifier_ops->get_func_proto() callback it should return > > > @@ -364,3 +365,34 @@ const struct bpf_func_proto bpf_get_local_storage_proto = { > > > }; > > > #endif > > > #endif > > > + > > > +BPF_CALL_1(bpf_progenyof, int, pid) > > > > Nit: could we add a more descriptive helper name? What's progenyof? Also s/int/pid_t/? > > > > It's true that "progeny" is not a very commonly used word :D. A coworker > suggested "descendantof", what do you think? It's a bit difficult to > convey "is true on the passed pid + on all the process under the > hierarchy chain of that pid", so I will try rewording the docs so the > semantics are very clear! What about childof? I see the word child used more than anything: $ man ps pgrep pidstat pstree top | grep child | wc -l 29 $ man ps pgrep pidstat pstree top | grep progeny | wc -l 0 $ man ps pgrep pidstat pstree top | grep ancestor | wc -l 2 Brendan
diff --git a/include/linux/bpf.h b/include/linux/bpf.h index f62897198844..bd0d2b38e7d5 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -930,6 +930,7 @@ extern const struct bpf_func_proto bpf_sk_redirect_map_proto; extern const struct bpf_func_proto bpf_spin_lock_proto; extern const struct bpf_func_proto bpf_spin_unlock_proto; extern const struct bpf_func_proto bpf_get_local_storage_proto; +extern const struct bpf_func_proto bpf_progenyof_proto; /* Shared helpers among cBPF and eBPF. */ void bpf_user_rnd_init_once(void); diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 3c04410137d9..cf54cc739bf4 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -2463,6 +2463,13 @@ union bpf_attr { * Return * 0 if iph and th are a valid SYN cookie ACK, or a negative error * otherwise. + * int bpf_progenyof(int pid) + * Description + * This helper is useful in programs that want to filter events + * happening to a pid of any of its descendants. + * Return + * 1 if the currently executing process' pid is in the process + * hierarchy of the passed pid. 0 Otherwise. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -2565,7 +2572,8 @@ union bpf_attr { FN(skb_ecn_set_ce), \ FN(get_listener_sock), \ FN(skc_lookup_tcp), \ - FN(tcp_check_syncookie), + FN(tcp_check_syncookie), \ + FN(progenyof), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index ff09d32a8a1b..437986497468 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -2044,6 +2044,7 @@ const struct bpf_func_proto bpf_get_current_uid_gid_proto __weak; const struct bpf_func_proto bpf_get_current_comm_proto __weak; const struct bpf_func_proto bpf_get_current_cgroup_id_proto __weak; const struct bpf_func_proto bpf_get_local_storage_proto __weak; +const struct bpf_func_proto bpf_progenyof_proto __weak; const struct bpf_func_proto * __weak bpf_get_trace_printk_proto(void) { diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index a411fc17d265..f093b35d1ba8 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -18,6 +18,7 @@ #include <linux/sched.h> #include <linux/uidgid.h> #include <linux/filter.h> +#include <linux/init_task.h> /* If kernel subsystem is allowing eBPF programs to call this function, * inside its own verifier_ops->get_func_proto() callback it should return @@ -364,3 +365,34 @@ const struct bpf_func_proto bpf_get_local_storage_proto = { }; #endif #endif + +BPF_CALL_1(bpf_progenyof, int, pid) +{ + int result = 0; + struct task_struct *task = current; + + WARN_ON(!rcu_read_lock_held()); + + if (unlikely(!task)) + return -EINVAL; + + if (pid == 0) + return 1; + + while (task != &init_task) { + if (task->pid == pid) { + result = 1; + break; + } + task = rcu_dereference(task->real_parent); + } + + return result; +} + +const struct bpf_func_proto bpf_progenyof_proto = { + .func = bpf_progenyof, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_ANYTHING, +}; diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index d64c00afceb5..e69283d423ff 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -599,6 +599,8 @@ tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_get_prandom_u32_proto; case BPF_FUNC_probe_read_str: return &bpf_probe_read_str_proto; + case BPF_FUNC_progenyof: + return &bpf_progenyof_proto; #ifdef CONFIG_CGROUPS case BPF_FUNC_get_current_cgroup_id: return &bpf_get_current_cgroup_id_proto;
This patch adds the bpf_progenyof helper which receives a PID and returns 1 if the process currently being executed is in the process hierarchy including itself or 0 if not. This is very useful in tracing programs when we want to filter by a given PID and all the children it might spawn. The current workarounds most people implement for this purpose have issues: - Attaching to process spawning syscalls and dynamically add those PIDs to some bpf map that would be used to filter is cumbersome and potentially racy. - Unrolling some loop to perform what this helper is doing consumes lots of instructions. That and the impossibility to jump backwards makes it really hard to be correct in really large process chains. Signed-off-by: Javier Honduvilla Coto <javierhonduco@fb.com> --- include/linux/bpf.h | 1 + include/uapi/linux/bpf.h | 10 +++++++++- kernel/bpf/core.c | 1 + kernel/bpf/helpers.c | 32 ++++++++++++++++++++++++++++++++ kernel/trace/bpf_trace.c | 2 ++ 5 files changed, 45 insertions(+), 1 deletion(-)