Skip to contentSkip to conversation

samples/bpf: Add xdp_stat sample program

PATCH In review Eric Sage 3 participants 3 messages Mar 29, 2020 – Mar 30, 2020

Subsystems (4)
lore
Share & tools
lore

Eric Sage

author
#0 lore raw

PATCH v4 1/1 samples/bpf: Add xdp_stat sample program

At Facebook we use tail calls to jump between our firewall filters and our L4LB. This is a program I wrote to estimate per program performance by swapping out the entries in the program array with interceptors that take measurements and then jump to the original entries.

I found the sample programs to be invaluable in understanding how to use the libbpf API (as well as the test env from the xdp-tutorial repo for testing), and want to return the favor. I am currently working on my next iteration that uses fentry/fexit to be less invasive, but I thought it was an interesting PoC of what you can do with program arrays.

v4:
- rebase
v3:
- Fixed typos in xdp_stat_kern.c
- Switch to using key_size, value_size for prog arrays

---
 samples/bpf/Makefile          |   3 +
 samples/bpf/xdp_stat          | Bin 0 -> 200488 bytes
 samples/bpf/xdp_stat_common.h |  28 ++
 samples/bpf/xdp_stat_kern.c   | 192 +++++++++
 samples/bpf/xdp_stat_user.c   | 748 ++++++++++++++++++++++++++++++++++
 5 files changed, 971 insertions(+)
 create mode 100755 samples/bpf/xdp_stat
 create mode 100644 samples/bpf/xdp_stat_common.h
 create mode 100644 samples/bpf/xdp_stat_kern.c
 create mode 100644 samples/bpf/xdp_stat_user.c
samples/bpf/Makefile +3 -0
index 424f6fe7ce38..52ceabdca08e 100644
@@ -53,6 +53,7 @@ tprogs-y += task_fd_query
 tprogs-y += xdp_sample_pkts
 tprogs-y += ibumad
 tprogs-y += hbm
+tprogs-y += xdp_stat
 
 # Libbpf dependencies
 LIBBPF = $(TOOLS_PATH)/lib/bpf/libbpf.a
@@ -109,6 +110,7 @@ task_fd_query-objs := bpf_load.o task_fd_query_user.o $(TRACE_HELPERS)
 xdp_sample_pkts-objs := xdp_sample_pkts_user.o $(TRACE_HELPERS)
 ibumad-objs := bpf_load.o ibumad_user.o $(TRACE_HELPERS)
 hbm-objs := bpf_load.o hbm.o $(CGROUP_HELPERS)
+xdp_stat-objs := xdp_stat_user.o
 
 # Tell kbuild to always build the programs
 always-y := $(tprogs-y)
@@ -170,6 +172,7 @@ always-y += ibumad_kern.o
 always-y += hbm_out_kern.o
 always-y += hbm_edt_kern.o
 always-y += xdpsock_kern.o
+always-y += xdp_stat_kern.o
 
 ifeq ($(ARCH), arm)
 # Strip all except -D__LINUX_ARM_ARCH__ option needed to handle linux
samples/bpf/xdp_stat new file binary +0 -0
new file mode 100755
index 0000000000000000000000000000000000000000..32a05e4e3f804400914d5048bfb602888af00b11
GIT binary patch
samples/bpf/xdp_stat_common.h new file +28 -0
new file mode 100644
index 000000000000..7c0557410704
@@ -0,0 +1,28 @@
+/* SPDX-License-Identifier: GPL-2.0
+ * Copyright (c) 2019 Facebook
+ */
+
+#ifndef __XDP_STAT_COMMON_HEADER_H
+#define __XDP_STAT_COMMON_HEADER_H
+
+/* WARNING: Must match the number of interceptors generated in
+ * xdp_stat_kern.c including xdp/interceptor_0.
+ */
+#define MAX_INTERCEPTORS 10
+
+/* prog_stats_rec contains stats specific to an intercepted BPF program.
+ */
+struct prog_stats_rec {
+	__u64 nr_terminal_runs;
+	__u64 nr_chained_runs;
+	__u64 ns_chained_runtime;
+};
+
+/* interception_info_rec contains global to all interceptors on a single CPU.
+ */
+struct interception_info_rec {
+	__u32 prev_interceptor_nr;
+	__u64 prev_ns_start;
+};
+
+#endif /* __XDP_STAT_COMMON_HEADER_H */
samples/bpf/xdp_stat_kern.c new file +192 -0

192 lines not on this page · raw message

samples/bpf/xdp_stat_user.c new file +748 -0

748 lines not on this page · raw message

Signature · 1 line
2.25.1
#1 lore raw
Quoted 19 lines · Eric Sage

At Facebook we use tail calls to jump between our firewall filters and our L4LB. This is a program I wrote to estimate per program performance by swapping out the entries in the program array with interceptors that take measurements and then jump to the original entries.

I found the sample programs to be invaluable in understanding how to use the libbpf API (as well as the test env from the xdp-tutorial repo for testing), and want to return the favor. I am currently working on my next iteration that uses fentry/fexit to be less invasive, but I thought it was an interesting PoC of what you can do with program arrays.

v4:
- rebase
v3:
- Fixed typos in xdp_stat_kern.c
- Switch to using key_size, value_size for prog arrays

Quoted 5 lines
---
 samples/bpf/Makefile          |   3 +
 samples/bpf/xdp_stat          | Bin 0 -> 200488 bytes

Add xdp_stat to .gitignore?

Quoted 9 lines
 samples/bpf/xdp_stat_common.h |  28 ++
 samples/bpf/xdp_stat_kern.c   | 192 +++++++++
 samples/bpf/xdp_stat_user.c   | 748 ++++++++++++++++++++++++++++++++++
 5 files changed, 971 insertions(+)
 create mode 100755 samples/bpf/xdp_stat
 create mode 100644 samples/bpf/xdp_stat_common.h
 create mode 100644 samples/bpf/xdp_stat_kern.c
 create mode 100644 samples/bpf/xdp_stat_user.c
#2 lore raw
In reply to Eric Sage

On Sun, 29 Mar 2020 16:16:30 -0700
Eric Sage <[email protected]> wrote:

[...]

Quoted 3 lines
---
 samples/bpf/Makefile          |   3 +
 samples/bpf/xdp_stat          | Bin 0 -> 200488 bytes

No binary files please.

Quoted 9 lines
 samples/bpf/xdp_stat_common.h |  28 ++
 samples/bpf/xdp_stat_kern.c   | 192 +++++++++
 samples/bpf/xdp_stat_user.c   | 748 ++++++++++++++++++++++++++++++++++
 5 files changed, 971 insertions(+)
 create mode 100755 samples/bpf/xdp_stat
 create mode 100644 samples/bpf/xdp_stat_common.h
 create mode 100644 samples/bpf/xdp_stat_kern.c
 create mode 100644 samples/bpf/xdp_stat_user.c

[...]

Quoted 8 lines
samples/bpf/xdp_stat new file binary +0 -0
new file mode 100755
index 0000000000000000000000000000000000000000..32a05e4e3f804400914d5048bfb602888af00b11
GIT binary patch

zu2ZL~PMtb+>YP(momu|i;0%{bN&aLgmnlru<rhnk^;=OUbjy@!{whqmG1as&b0b

Quoted 8 lines

z6=}DGF^74@hdd_$fS~dW?4yvwXxhHJAY9|F;Ywy^P%*SzdN5v3i)KY&YxoY)p{1% z1(Q!D+sbCSE_}9FZ|>d%SZC*f5d7bE-_(?ZvHpCGNG#+0VtRtYq@(EJxl{*ION| ze)tNBn0ywhR=G#*XR;izS#EdCD!2QeR=L#ECS$k#O!AX7^8Z?^7@oyQF<s1u;*-BS zpTy-)*>|CFd@t)~6)fv#wU>MbyGt}BAn9(7Uf9i|JxsX7?kVm_R{gC;Yh2-<kRk^ za{lCrw_JSD`IE=>n>=x9xVB$y;l=$fzUaJ~Y3E%a``ru0C{shO9<H46_opwvV6!Ld z#dVX5&-MIzPFB@tpOJ3T!1{>8AL85WlFv${nJ@b#g~gpgSQY-i_H_F(ML!!!u>|DM zpHd``ITR#QZ>NFJL*svj&vE@T_zh{`Z=wT#hJR6-cK@5Ep6k-U{b}H2#Gkc$R2uwa z)6n@#ntFasQ_t8m@X|DJk*3|XY1;i)8vHxbj8~sD_+8TAf0u^N9%<@1FAe;qH1*t@

No binary files please.

Signature · 4 lines
Best regards,
  Jesper Dangaard Brouer
  MSc.CS, Principal Kernel Engineer at Red Hat
  LinkedIn: http://www.linkedin.com/in/brouer