objtool: Optimize find_rela_by_dest_range()

Perf shows there is significant time in find_rela_by_dest(); this is
because we have to iterate the address space per byte, looking for
relocation entries.

Optimize this by reducing the address space granularity.

This reduces objtool on vmlinux.o runtime from 4.8 to 4.4 seconds.

Signed-off-by: Peter Zijlstra (Intel) <[e-mail]>
Reviewed-by: Miroslav Benes <[e-mail]>
Acked-by: Josh Poimboeuf <[e-mail]>
Link: https://lkml.kernel.org/r/[e-mail]

tools/objtool/elf.c

···
 struct rela *find_rela_by_dest_range(struct elf *elf, struct section *sec,
 				     unsigned long offset, unsigned int len)
 {
-	struct rela *rela;
+	struct rela *rela, *r = NULL;
 	unsigned long o;
 
 	if (!sec->rela)
···
 
 	sec = sec->rela;
 
-	for (o = offset; o < offset + len; o++) {
+	for_offset_range(o, offset, offset + len) {
 		hash_for_each_possible(elf->rela_hash, rela, hash,
 				       sec_offset_hash(sec, o)) {
-			if (rela->sec == sec && rela->offset == o)
-				return rela;
+			if (rela->sec != sec)
+				continue;
+
+			if (rela->offset >= offset && rela->offset < offset + len) {
+				if (!r || rela->offset < r->offset)
+					r = rela;
+			}
 		}
+		if (r)
+			return r;
 	}
 
 	return NULL;

tools/objtool/elf.h

···
 	DECLARE_HASHTABLE(rela_hash, 20);
 };
 
+#define OFFSET_STRIDE_BITS	4
+#define OFFSET_STRIDE		(1UL << OFFSET_STRIDE_BITS)
+#define OFFSET_STRIDE_MASK	(~(OFFSET_STRIDE - 1))
+
+#define for_offset_range(_offset, _start, _end)		\
+	for (_offset = ((_start) & OFFSET_STRIDE_MASK);	\
+	     _offset <= ((_end) & OFFSET_STRIDE_MASK);	\
+	     _offset += OFFSET_STRIDE)
+
 static inline u32 sec_offset_hash(struct section *sec, unsigned long offset)
 {
-	u32 ol = offset, oh = offset >> 32, idx = sec->idx;
+	u32 ol, oh, idx = sec->idx;
+
+	offset &= OFFSET_STRIDE_MASK;
+
+	ol = offset;
+	oh = offset >> 32;
 
 	__jhash_mix(ol, oh, idx);