bpf: Cache the last valid build_id

For binaries that are statically linked, consecutive stack frames are
likely to be in the same VMA and therefore have the same build id.

On a real-world workload, we observed that 66% of CPU cycles in
__bpf_get_stackid() were spent on build_id_parse() and find_vma().

As an optimization for this case, we can cache the previous frame's
VMA, if the new frame has the same VMA as the previous one, reuse the
previous one's build id.

We are holding the MM locks as reader across the entire loop, so we
don't need to worry about VMA going away.

Tested through "stacktrace_build_id" and "stacktrace_build_id_nmi" in
test_progs.
Suggested-by: Greg Thelen <gthelen@google.com>
Signed-off-by: Hao Luo <haoluo@google.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Pasha Tatashin <pasha.tatashin@soleen.com>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Song Liu <songliubraving@fb.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/bpf/20220224000531.1265030-1-haoluo@google.com

kernel/bpf/stackmap.c

@@ -132,7 +132,8 @@ static void stack_map_get_build_id_offset(struct bpf_stack_build_id *id_offs,
 	int i;
 	struct mmap_unlock_irq_work *work = NULL;
 	bool irq_work_busy = bpf_mmap_unlock_get_irq_work(&work);
-	struct vm_area_struct *vma;
+	struct vm_area_struct *vma, *prev_vma = NULL;
+	const char *prev_build_id;
 
 	/* If the irq_work is in use, fall back to report ips. Same
 	 * fallback is used for kernel stack (!user) on a stackmap with
@@ -150,6 +151,12 @@ static void stack_map_get_build_id_offset(struct bpf_stack_build_id *id_offs,
 	}
 
 	for (i = 0; i < trace_nr; i++) {
+		if (range_in_vma(prev_vma, ips[i], ips[i])) {
+			vma = prev_vma;
+			memcpy(id_offs[i].build_id, prev_build_id,
+			       BUILD_ID_SIZE_MAX);
+			goto build_id_valid;
+		}
 		vma = find_vma(current->mm, ips[i]);
 		if (!vma || build_id_parse(vma, id_offs[i].build_id, NULL)) {
 			/* per entry fall back to ips */
@@ -158,9 +165,12 @@ static void stack_map_get_build_id_offset(struct bpf_stack_build_id *id_offs,
 			memset(id_offs[i].build_id, 0, BUILD_ID_SIZE_MAX);
 			continue;
 		}
+build_id_valid:
 		id_offs[i].offset = (vma->vm_pgoff << PAGE_SHIFT) + ips[i]
 			- vma->vm_start;
 		id_offs[i].status = BPF_STACK_BUILD_ID_VALID;
+		prev_vma = vma;
+		prev_build_id = id_offs[i].build_id;
 	}
 	bpf_mmap_unlock_mm(work, current->mm);
 }