libbpf: Improve btf__add_btf() with an additional hashmap for strings.

Add a hashmap to map the string offsets from a source btf to the
string offsets from a target btf to reduce overheads.

btf__add_btf() calls btf__add_str() to add strings from a source to a
target btf.  It causes many string comparisons, and it is a major
hotspot when adding a big btf.  btf__add_str() uses strcmp() to check
if a hash entry is the right one.  The extra hashmap here compares
offsets of strings, that are much cheaper.  It remembers the results
of btf__add_str() for later uses to reduce the cost.

We are parallelizing BTF encoding for pahole by creating separated btf
instances for worker threads.  These per-thread btf instances will be
added to the btf instance of the main thread by calling btf__add_str()
to deduplicate and write out.  With this patch and -j4, the running
time of pahole drops to about 6.0s from 6.6s.

The following lines are the summary of 'perf stat' w/o the change.

       6.668126396 seconds time elapsed

      13.451054000 seconds user
       0.715520000 seconds sys

The following lines are the summary w/ the change.

       5.986973919 seconds time elapsed

      12.939903000 seconds user
       0.724152000 seconds sys

V4 fixes a bug of error checking against the pointer returned by
hashmap__new().

[v3] https://lore.kernel.org/bpf/20220118232053.2113139-1-kuifeng@fb.com/
[v2] https://lore.kernel.org/bpf/20220114193713.461349-1-kuifeng@fb.com/Signed-off-by: Kui-Feng Lee <kuifeng@fb.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20220119180214.255634-1-kuifeng@fb.com

tools/lib/bpf/btf.c

@@ -1620,20 +1620,37 @@ static int btf_commit_type(struct btf *btf, int data_sz)
 struct btf_pipe {
 	const struct btf *src;
 	struct btf *dst;
+	struct hashmap *str_off_map; /* map string offsets from src to dst */
 };
 
 static int btf_rewrite_str(__u32 *str_off, void *ctx)
 {
 	struct btf_pipe *p = ctx;
-	int off;
+	void *mapped_off;
+	int off, err;
 
 	if (!*str_off) /* nothing to do for empty strings */
 		return 0;
 
+	if (p->str_off_map &&
+	    hashmap__find(p->str_off_map, (void *)(long)*str_off, &mapped_off)) {
+		*str_off = (__u32)(long)mapped_off;
+		return 0;
+	}
+
 	off = btf__add_str(p->dst, btf__str_by_offset(p->src, *str_off));
 	if (off < 0)
 		return off;
 
+	/* Remember string mapping from src to dst.  It avoids
+	 * performing expensive string comparisons.
+	 */
+	if (p->str_off_map) {
+		err = hashmap__append(p->str_off_map, (void *)(long)*str_off, (void *)(long)off);
+		if (err)
+			return err;
+	}
+
 	*str_off = off;
 	return 0;
 }
@@ -1680,6 +1697,9 @@ static int btf_rewrite_type_ids(__u32 *type_id, void *ctx)
 	return 0;
 }
 
+static size_t btf_dedup_identity_hash_fn(const void *key, void *ctx);
+static bool btf_dedup_equal_fn(const void *k1, const void *k2, void *ctx);
+
 int btf__add_btf(struct btf *btf, const struct btf *src_btf)
 {
 	struct btf_pipe p = { .src = src_btf, .dst = btf };
@@ -1713,6 +1733,11 @@ int btf__add_btf(struct btf *btf, const struct btf *src_btf)
 	if (!off)
 		return libbpf_err(-ENOMEM);
 
+	/* Map the string offsets from src_btf to the offsets from btf to improve performance */
+	p.str_off_map = hashmap__new(btf_dedup_identity_hash_fn, btf_dedup_equal_fn, NULL);
+	if (IS_ERR(p.str_off_map))
+		return libbpf_err(-ENOMEM);
+
 	/* bulk copy types data for all types from src_btf */
 	memcpy(t, src_btf->types_data, data_sz);
 
@@ -1754,6 +1779,8 @@ int btf__add_btf(struct btf *btf, const struct btf *src_btf)
 	btf->hdr->str_off += data_sz;
 	btf->nr_types += cnt;
 
+	hashmap__free(p.str_off_map);
+
 	/* return type ID of the first added BTF type */
 	return btf->start_id + btf->nr_types - cnt;
 err_out:
@@ -1767,6 +1794,8 @@ int btf__add_btf(struct btf *btf, const struct btf *src_btf)
 	 * wasn't modified, so doesn't need restoring, see big comment above */
 	btf->hdr->str_len = old_strs_len;
 
+	hashmap__free(p.str_off_map);
+
 	return libbpf_err(err);
 }