selftests/bpf: Add LPM trie microbenchmarks

Add benchmarks for the standard set of operations: LOOKUP, INSERT,
UPDATE, DELETE. Also include benchmarks to measure the overhead of the
bench framework itself (NOOP) as well as the overhead of generating keys
(BASELINE). Lastly, this includes a benchmark for FREE (trie_free())
which is known to have terrible performance for maps with many entries.

Benchmarks operate on tries without gaps in the key range, i.e. each
test begins or ends with a trie with valid keys in the range [0,
nr_entries). This is intended to cause maximum branching when traversing
the trie.

LOOKUP, UPDATE, DELETE, and FREE fill a BPF LPM trie from userspace
using bpf_map_update_batch() and run the corresponding benchmark
operation via bpf_loop(). INSERT starts with an empty map and fills it
kernel-side from bpf_loop(). FREE records the time to free a filled LPM
trie by attaching and destroying a BPF prog. NOOP measures the overhead
of the test harness by running an empty function with bpf_loop().
BASELINE is similar to NOOP except that the function generates a key.

Each operation runs 10,000 times using bpf_loop(). Note that this value
is intentionally independent of the number of entries in the LPM trie so
that the stability of the results isn't affected by the number of
entries.

For those benchmarks that need to reset the LPM trie once it's full
(INSERT) or empty (DELETE), throughput and latency results are scaled by
the fraction of a second the operation actually ran to ignore any time
spent reinitialising the trie.

By default, benchmarks run using sequential keys in the range [0,
nr_entries). BASELINE, LOOKUP, and UPDATE can use random keys via the
--random parameter but beware there is a runtime cost involved in
generating random keys. Other benchmarks are prohibited from using
random keys because it can skew the results, e.g. when inserting an
existing key or deleting a missing one.

All measurements are recorded from within the kernel to eliminate
syscall overhead. Most benchmarks run an XDP program to generate stats
but FREE needs to collect latencies using fentry/fexit on
map_free_deferred() because it's not possible to use fentry directly on
lpm_trie.c since commit c83508d ("bpf: Avoid deadlock caused by
nested kprobe and fentry bpf programs") and there's no way to
create/destroy a map from within an XDP program.

Here is example output from an AMD EPYC 9684X 96-Core machine for each
of the benchmarks using a trie with 10K entries and a 32-bit prefix
length, e.g.

  $ ./bench lpm-trie-$op \
  	--prefix_len=32  \
	--producers=1     \
	--nr_entries=10000

     noop: throughput   74.417 ± 0.032 M ops/s ( 74.417M ops/prod), latency   13.438 ns/op
 baseline: throughput   70.107 ± 0.171 M ops/s ( 70.107M ops/prod), latency   14.264 ns/op
   lookup: throughput    8.467 ± 0.047 M ops/s (  8.467M ops/prod), latency  118.109 ns/op
   insert: throughput    2.440 ± 0.015 M ops/s (  2.440M ops/prod), latency  409.290 ns/op
   update: throughput    2.806 ± 0.042 M ops/s (  2.806M ops/prod), latency  356.322 ns/op
   delete: throughput    4.625 ± 0.011 M ops/s (  4.625M ops/prod), latency  215.613 ns/op
     free: throughput    0.578 ± 0.006 K ops/s (  0.578K ops/prod), latency    1.730 ms/op

And the same benchmarks using random keys:

  $ ./bench lpm-trie-$op \
  	--prefix_len=32  \
	--producers=1     \
	--nr_entries=10000 \
	--random

     noop: throughput   74.259 ± 0.335 M ops/s ( 74.259M ops/prod), latency   13.466 ns/op
 baseline: throughput   35.150 ± 0.144 M ops/s ( 35.150M ops/prod), latency   28.450 ns/op
   lookup: throughput    7.119 ± 0.048 M ops/s (  7.119M ops/prod), latency  140.469 ns/op
   insert: N/A
   update: throughput    2.736 ± 0.012 M ops/s (  2.736M ops/prod), latency  365.523 ns/op
   delete: N/A
     free: N/A

Signed-off-by: Matt Fleming <[email protected]>
Signed-off-by: Jesper Dangaard Brouer <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Alexei Starovoitov <[email protected]>

Author: mfleming

tools/testing/selftests/bpf/Makefile

@@ -816,6 +816,7 @@ $(OUTPUT)/bench_bpf_hashmap_lookup.o: $(OUTPUT)/bpf_hashmap_lookup.skel.h
 $(OUTPUT)/bench_htab_mem.o: $(OUTPUT)/htab_mem_bench.skel.h
 $(OUTPUT)/bench_bpf_crypto.o: $(OUTPUT)/crypto_bench.skel.h
 $(OUTPUT)/bench_sockmap.o: $(OUTPUT)/bench_sockmap_prog.skel.h
+$(OUTPUT)/bench_lpm_trie_map.o: $(OUTPUT)/lpm_trie_bench.skel.h $(OUTPUT)/lpm_trie_map.skel.h
 $(OUTPUT)/bench.o: bench.h testing_helpers.h $(BPFOBJ)
 $(OUTPUT)/bench: LDLIBS += -lm
 $(OUTPUT)/bench: $(OUTPUT)/bench.o \
@@ -837,6 +838,7 @@ $(OUTPUT)/bench: $(OUTPUT)/bench.o \
 		 $(OUTPUT)/bench_htab_mem.o \
 		 $(OUTPUT)/bench_bpf_crypto.o \
 		 $(OUTPUT)/bench_sockmap.o \
+		 $(OUTPUT)/bench_lpm_trie_map.o \
 		 #
 	$(call msg,BINARY,,$@)
 	$(Q)$(CC) $(CFLAGS) $(LDFLAGS) $(filter %.a %.o,$^) $(LDLIBS) -o $@

tools/testing/selftests/bpf/bench.c

@@ -284,6 +284,7 @@ extern struct argp bench_htab_mem_argp;
 extern struct argp bench_trigger_batch_argp;
 extern struct argp bench_crypto_argp;
 extern struct argp bench_sockmap_argp;
+extern struct argp bench_lpm_trie_map_argp;
 
 static const struct argp_child bench_parsers[] = {
 	{ &bench_ringbufs_argp, 0, "Ring buffers benchmark", 0 },
@@ -299,6 +300,7 @@ static const struct argp_child bench_parsers[] = {
 	{ &bench_trigger_batch_argp, 0, "BPF triggering benchmark", 0 },
 	{ &bench_crypto_argp, 0, "bpf crypto benchmark", 0 },
 	{ &bench_sockmap_argp, 0, "bpf sockmap benchmark", 0 },
+	{ &bench_lpm_trie_map_argp, 0, "LPM trie map benchmark", 0 },
 	{},
 };
 
@@ -558,6 +560,13 @@ extern const struct bench bench_htab_mem;
 extern const struct bench bench_crypto_encrypt;
 extern const struct bench bench_crypto_decrypt;
 extern const struct bench bench_sockmap;
+extern const struct bench bench_lpm_trie_noop;
+extern const struct bench bench_lpm_trie_baseline;
+extern const struct bench bench_lpm_trie_lookup;
+extern const struct bench bench_lpm_trie_insert;
+extern const struct bench bench_lpm_trie_update;
+extern const struct bench bench_lpm_trie_delete;
+extern const struct bench bench_lpm_trie_free;
 
 static const struct bench *benchs[] = {
 	&bench_count_global,
@@ -625,6 +634,13 @@ static const struct bench *benchs[] = {
 	&bench_crypto_encrypt,
 	&bench_crypto_decrypt,
 	&bench_sockmap,
+	&bench_lpm_trie_noop,
+	&bench_lpm_trie_baseline,
+	&bench_lpm_trie_lookup,
+	&bench_lpm_trie_insert,
+	&bench_lpm_trie_update,
+	&bench_lpm_trie_delete,
+	&bench_lpm_trie_free,
 };
 
 static void find_benchmark(void)

tools/testing/selftests/bpf/bench.h

@@ -46,6 +46,7 @@ struct bench_res {
 	unsigned long gp_ns;
 	unsigned long gp_ct;
 	unsigned int stime;
+	unsigned long duration_ns;
 };
 
 struct bench {