Merge branch 'bpf-lpm'

Daniel Mack says:

====================
bpf: add longest prefix match map

This patch set adds a longest prefix match algorithm that can be used
to match IP addresses to a stored set of ranges. It is exposed as a
bpf map type.

Internally, data is stored in an unbalanced tree of nodes that has a
maximum height of n, where n is the prefixlen the trie was created
with.

Note that this has nothing to do with fib or fib6 and is in no way meant
to replace or share code with it. It's rather a much simpler
implementation that is specifically written with bpf maps in mind.

Patch 1/2 adds the implementation, 2/2 an extensive test suite and 3/3
has benchmarking code for the new trie type.

Feedback is much appreciated.

Changelog:

v3 -> v4:
	* David added a 3rd patch that augments map_perf_test for
	  LPM trie benchmarks
	* Limit allocation of maps of this new type to CAP_SYS_ADMIN
	  for now, as requested by Alexei
	* Add a stub .map_delete_elem so the core does not stumble
	  over a NULL pointer when the syscall is invoked
	* Tests for non-power-of-2 prefix lengths were added
	* More comment style fixes

v2 -> v3:
	* Store both the key match data and the caller provided
	  value in the same byte array attached to a node. This
	  avoids double allocations
	* Bring back node->flags to distinguish between 'real'
	  and intermediate nodes
	* Fix comment style and some typos

v1 -> v2:
	* Turn spin lock into raw spinlock
	* Lock with irqsave options during trie_update_elem()
	* Return -ENOMEM properly from trie_alloc()
	* Force attr->flags == BPF_F_NO_PREALLOC during creation
	* Set trie->map.pages after creation to account for map memory
	* Allow arbitrary value sizes
	* Removed node->flags and denode intermediate nodes through
	  node->value == NULL instead

rfc -> v1:
	* Add __rcu pointer annotations to make sparse happy
	* Fold _lpm_trie_find_target_node() into its only caller
	* Fix some minor documentation issues
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 49 insertions, 0 deletions

diff --git a/samples/bpf/map_perf_test_user.c b/samples/bpf/map_perf_test_user.c
index 9505b4d112f4..680260a91f50 100644
--- a/samples/bpf/map_perf_test_user.c
+++ b/samples/bpf/map_perf_test_user.c
@@ -37,6 +37,7 @@ static __u64 time_get_ns(void)
 #define PERCPU_HASH_KMALLOC	(1 << 3)
 #define LRU_HASH_PREALLOC	(1 << 4)
 #define PERCPU_LRU_HASH_PREALLOC	(1 << 5)
+#define LPM_KMALLOC		(1 << 6)
 
 static int test_flags = ~0;
 
@@ -112,6 +113,18 @@ static void test_percpu_hash_kmalloc(int cpu)
 	       cpu, MAX_CNT * 1000000000ll / (time_get_ns() - start_time));
 }
 
+static void test_lpm_kmalloc(int cpu)
+{
+	__u64 start_time;
+	int i;
+
+	start_time = time_get_ns();
+	for (i = 0; i < MAX_CNT; i++)
+		syscall(__NR_gettid);
+	printf("%d:lpm_perf kmalloc %lld events per sec\n",
+	       cpu, MAX_CNT * 1000000000ll / (time_get_ns() - start_time));
+}
+
 static void loop(int cpu)
 {
 	cpu_set_t cpuset;
@@ -137,6 +150,9 @@ static void loop(int cpu)
 
 	if (test_flags & PERCPU_LRU_HASH_PREALLOC)
 		test_percpu_lru_hash_prealloc(cpu);
+
+	if (test_flags & LPM_KMALLOC)
+		test_lpm_kmalloc(cpu);
 }
 
 static void run_perf_test(int tasks)
@@ -162,6 +178,37 @@ static void run_perf_test(int tasks)
 	}
 }
 
+static void fill_lpm_trie(void)
+{
+	struct bpf_lpm_trie_key *key;
+	unsigned long value = 0;
+	unsigned int i;
+	int r;
+
+	key = alloca(sizeof(*key) + 4);
+	key->prefixlen = 32;
+
+	for (i = 0; i < 512; ++i) {
+		key->prefixlen = rand() % 33;
+		key->data[0] = rand() & 0xff;
+		key->data[1] = rand() & 0xff;
+		key->data[2] = rand() & 0xff;
+		key->data[3] = rand() & 0xff;
+		r = bpf_map_update_elem(map_fd[6], key, &value, 0);
+		assert(!r);
+	}
+
+	key->prefixlen = 32;
+	key->data[0] = 192;
+	key->data[1] = 168;
+	key->data[2] = 0;
+	key->data[3] = 1;
+	value = 128;
+
+	r = bpf_map_update_elem(map_fd[6], key, &value, 0);
+	assert(!r);
+}
+
 int main(int argc, char **argv)
 {
 	struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY};
@@ -182,6 +229,8 @@ int main(int argc, char **argv)
 		return 1;
 	}
 
+	fill_lpm_trie();
+
 	run_perf_test(num_cpu);
 
 	return 0;