diff mbox series

[bpf-next,v3,08/15] libbpf: sync progs autoload with maps autocreate for struct_ops maps

Message ID 20240304225156.24765-9-eddyz87@gmail.com (mailing list archive)
State Superseded
Delegated to: BPF
Headers show
Series libbpf: type suffixes and autocreate flag for struct_ops maps | expand

Checks

Context Check Description
netdev/tree_selection success Clearly marked for bpf-next, async
netdev/apply fail Patch does not apply to bpf-next-0
bpf/vmtest-bpf-next-VM_Test-1 success Logs for ShellCheck
bpf/vmtest-bpf-next-VM_Test-0 success Logs for Lint
bpf/vmtest-bpf-next-VM_Test-2 success Logs for Unittests
bpf/vmtest-bpf-next-VM_Test-5 success Logs for aarch64-gcc / build-release
bpf/vmtest-bpf-next-VM_Test-3 success Logs for Validate matrix.py
bpf/vmtest-bpf-next-VM_Test-4 success Logs for aarch64-gcc / build / build for aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-9 success Logs for aarch64-gcc / test (test_verifier, false, 360) / test_verifier on aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-10 success Logs for aarch64-gcc / veristat
bpf/vmtest-bpf-next-VM_Test-11 success Logs for s390x-gcc / build / build for s390x with gcc
bpf/vmtest-bpf-next-VM_Test-12 success Logs for s390x-gcc / build-release
bpf/vmtest-bpf-next-VM_Test-17 success Logs for s390x-gcc / veristat
bpf/vmtest-bpf-next-VM_Test-18 success Logs for set-matrix
bpf/vmtest-bpf-next-VM_Test-19 success Logs for x86_64-gcc / build / build for x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-20 success Logs for x86_64-gcc / build-release
bpf/vmtest-bpf-next-VM_Test-21 success Logs for x86_64-gcc / test (test_maps, false, 360) / test_maps on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-22 fail Logs for x86_64-gcc / test (test_progs, false, 360) / test_progs on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-23 fail Logs for x86_64-gcc / test (test_progs_no_alu32, false, 360) / test_progs_no_alu32 on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-24 success Logs for x86_64-gcc / test (test_progs_no_alu32_parallel, true, 30) / test_progs_no_alu32_parallel on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-25 success Logs for x86_64-gcc / test (test_progs_parallel, true, 30) / test_progs_parallel on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-26 success Logs for x86_64-gcc / test (test_verifier, false, 360) / test_verifier on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-27 success Logs for x86_64-gcc / veristat / veristat on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-28 fail Logs for x86_64-llvm-17 / build / build for x86_64 with llvm-17
bpf/vmtest-bpf-next-VM_Test-30 success Logs for x86_64-llvm-17 / test
bpf/vmtest-bpf-next-VM_Test-31 success Logs for x86_64-llvm-17 / veristat
bpf/vmtest-bpf-next-VM_Test-32 fail Logs for x86_64-llvm-18 / build / build for x86_64 with llvm-18
bpf/vmtest-bpf-next-VM_Test-34 success Logs for x86_64-llvm-18 / test
bpf/vmtest-bpf-next-VM_Test-35 success Logs for x86_64-llvm-18 / veristat
bpf/vmtest-bpf-next-VM_Test-6 success Logs for aarch64-gcc / test (test_maps, false, 360) / test_maps on aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-7 fail Logs for aarch64-gcc / test (test_progs, false, 360) / test_progs on aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-8 fail Logs for aarch64-gcc / test (test_progs_no_alu32, false, 360) / test_progs_no_alu32 on aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-33 fail Logs for x86_64-llvm-18 / build-release / build for x86_64 with llvm-18 and -O2 optimization
bpf/vmtest-bpf-next-VM_Test-15 fail Logs for s390x-gcc / test (test_progs_no_alu32, false, 360) / test_progs_no_alu32 on s390x with gcc
bpf/vmtest-bpf-next-VM_Test-29 fail Logs for x86_64-llvm-17 / build-release / build for x86_64 with llvm-17 and -O2 optimization
bpf/vmtest-bpf-next-PR fail PR summary
bpf/vmtest-bpf-next-VM_Test-13 fail Logs for s390x-gcc / test (test_maps, false, 360) / test_maps on s390x with gcc
bpf/vmtest-bpf-next-VM_Test-14 fail Logs for s390x-gcc / test (test_progs, false, 360) / test_progs on s390x with gcc
bpf/vmtest-bpf-next-VM_Test-16 fail Logs for s390x-gcc / test (test_verifier, false, 360) / test_verifier on s390x with gcc

Commit Message

Eduard Zingerman March 4, 2024, 10:51 p.m. UTC 
Automatically select which struct_ops programs to load depending on
which struct_ops maps are selected for automatic creation.
E.g. for the BPF code below:

    SEC("struct_ops/test_1") int BPF_PROG(foo) { ... }
    SEC("struct_ops/test_2") int BPF_PROG(bar) { ... }

    SEC(".struct_ops.link")
    struct test_ops___v1 A = {
        .foo = (void *)foo
    };

    SEC(".struct_ops.link")
    struct test_ops___v2 B = {
        .foo = (void *)foo,
        .bar = (void *)bar,
    };

And the following libbpf API calls:

    bpf_map__set_autocreate(skel->maps.A, true);
    bpf_map__set_autocreate(skel->maps.B, false);

The autoload would be enabled for program 'foo' and disabled for
program 'bar'.

During load, for each struct_ops program P, referenced from some
struct_ops map M:
- set P.autoload = true if M.autocreate is true for some M;
- set P.autoload = false if M.autocreate is false for all M;
- don't change P.autoload, if P is not referenced from any map.

Do this after bpf_object__init_kern_struct_ops_maps()
to make sure that shadow vars assignment is done.

Signed-off-by: Eduard Zingerman <eddyz87@gmail.com>
---
 tools/lib/bpf/libbpf.c | 48 ++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 48 insertions(+)

Comments

Andrii Nakryiko March 5, 2024, 7:46 p.m. UTC | #1 
On Mon, Mar 4, 2024 at 2:52 PM Eduard Zingerman <eddyz87@gmail.com> wrote:
>
> Automatically select which struct_ops programs to load depending on
> which struct_ops maps are selected for automatic creation.
> E.g. for the BPF code below:
>
>     SEC("struct_ops/test_1") int BPF_PROG(foo) { ... }
>     SEC("struct_ops/test_2") int BPF_PROG(bar) { ... }
>
>     SEC(".struct_ops.link")
>     struct test_ops___v1 A = {
>         .foo = (void *)foo
>     };
>
>     SEC(".struct_ops.link")
>     struct test_ops___v2 B = {
>         .foo = (void *)foo,
>         .bar = (void *)bar,
>     };
>
> And the following libbpf API calls:
>
>     bpf_map__set_autocreate(skel->maps.A, true);
>     bpf_map__set_autocreate(skel->maps.B, false);
>
> The autoload would be enabled for program 'foo' and disabled for
> program 'bar'.
>
> During load, for each struct_ops program P, referenced from some
> struct_ops map M:
> - set P.autoload = true if M.autocreate is true for some M;
> - set P.autoload = false if M.autocreate is false for all M;
> - don't change P.autoload, if P is not referenced from any map.
>
> Do this after bpf_object__init_kern_struct_ops_maps()
> to make sure that shadow vars assignment is done.
>
> Signed-off-by: Eduard Zingerman <eddyz87@gmail.com>
> ---
>  tools/lib/bpf/libbpf.c | 48 ++++++++++++++++++++++++++++++++++++++++++
>  1 file changed, 48 insertions(+)
>
> diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
> index 25c452c20d7d..ce39ae34fec0 100644
> --- a/tools/lib/bpf/libbpf.c
> +++ b/tools/lib/bpf/libbpf.c
> @@ -1031,6 +1031,53 @@ static bool is_valid_st_ops_program(struct bpf_object *obj,
>         return false;
>  }
>
> +/* For each struct_ops program P, referenced from some struct_ops map M,
> + * enable P.autoload if there are Ms for which M.autocreate is true,
> + * disable P.autoload if for all Ms M.autocreate is false.
> + * Don't change P.autoload for programs that are not referenced from any maps.
> + */
> +static int bpf_object__adjust_struct_ops_autoload(struct bpf_object *obj)

nit: we try not to use double underscore separate for non-public
internal helper functions (see bpf_object_init_prog_arrays and
bpf_object_prepare_struct_ops)

> +{
> +       struct bpf_program *prog;
> +       struct bpf_map *map;
> +       int i, j, k, vlen;
> +       struct {
> +               __u8 any_map_autocreate:1;
> +               __u8 used_in_struct_ops_map:1;
> +       } *refs;

bit masks just for this to save a few bytes?...

but generally, how about we keep all this much dumber:

for (each program) {
    int use_cnt = 0;
    int should_load = false;

    if (!is_struct_ops_program)
        continue;
    for (each map) {
        if (!is_struct_ops_map)
            continue;
        for (each prog entry in map->st_ops->progs[]) {
            if (prog != slot_prog)
                continue;
            use_cnt++;
            if (map->autocreate)
               should_load = true;
        }
    }
    if (use_cnt)
        prog->autocreate = should_load;
}


Sure it does a few more iterations, but we avoid unnecessary
allocation/cleanup and keep things literally working how you describe
in your comment.

WDYT?

> +
> +       refs = calloc(obj->nr_programs, sizeof(refs[0]));
> +       if (!refs)
> +               return -ENOMEM;
> +
> +       for (i = 0; i < obj->nr_maps; i++) {
> +               map = &obj->maps[i];
> +               if (!bpf_map__is_struct_ops(map))
> +                       continue;
> +
> +               vlen = btf_vlen(map->st_ops->type);
> +               for (j = 0; j < vlen; ++j) {

nit: stay consistent with ++j vs j++?

> +                       prog = map->st_ops->progs[j];
> +                       if (!prog)
> +                               continue;
> +
> +                       k = prog - obj->programs;
> +                       if (k < 0 || k > obj->nr_programs)

>= ? But a clever trick, I like it!

> +                               continue;
> +
> +                       refs[k].used_in_struct_ops_map = true;
> +                       refs[k].any_map_autocreate |= map->autocreate;
> +               }
> +       }
> +
> +       for (i = 0; i < obj->nr_programs; ++i)
> +               if (refs[i].used_in_struct_ops_map)
> +                       obj->programs[i].autoload = refs[i].any_map_autocreate;
> +
> +       free(refs);
> +       return 0;
> +}
> +
>  /* Init the map's fields that depend on kern_btf */
>  static int bpf_map__init_kern_struct_ops(struct bpf_map *map)
>  {
> @@ -8163,6 +8210,7 @@ static int bpf_object_load(struct bpf_object *obj, int extra_log_level, const ch
>         err = err ? : bpf_object__resolve_externs(obj, obj->kconfig);
>         err = err ? : bpf_object__sanitize_maps(obj);
>         err = err ? : bpf_object__init_kern_struct_ops_maps(obj);
> +       err = err ? : bpf_object__adjust_struct_ops_autoload(obj);
>         err = err ? : bpf_object__relocate(obj, obj->btf_custom_path ? : target_btf_path);
>         err = err ? : bpf_object__sanitize_and_load_btf(obj);
>         err = err ? : bpf_object__create_maps(obj);
> --
> 2.43.0
>
Eduard Zingerman March 6, 2024, 12:28 a.m. UTC | #2 
On Tue, 2024-03-05 at 11:46 -0800, Andrii Nakryiko wrote:
[...]

> bit masks just for this to save a few bytes?...
> 
> but generally, how about we keep all this much dumber:
> 
> for (each program) {
>     int use_cnt = 0;
>     int should_load = false;
> 
>     if (!is_struct_ops_program)
>         continue;
>     for (each map) {
>         if (!is_struct_ops_map)
>             continue;
>         for (each prog entry in map->st_ops->progs[]) {
>             if (prog != slot_prog)
>                 continue;
>             use_cnt++;
>             if (map->autocreate)
>                should_load = true;
>         }
>     }
>     if (use_cnt)
>         prog->autocreate = should_load;
> }
> 
> 
> Sure it does a few more iterations, but we avoid unnecessary
> allocation/cleanup and keep things literally working how you describe
> in your comment.
> 
> WDYT?

I like the version in the patch more but ok,
will switch to suggested scheme as it is a bit simpler.

[...]

> > +                       prog = map->st_ops->progs[j];
> > +                       if (!prog)
> > +                               continue;
> > +
> > +                       k = prog - obj->programs;
> > +                       if (k < 0 || k > obj->nr_programs)
> 
> >= ? But a clever trick, I like it!

Yeah, should have been >=, my bad.
diff mbox series

Patch

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 25c452c20d7d..ce39ae34fec0 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -1031,6 +1031,53 @@  static bool is_valid_st_ops_program(struct bpf_object *obj,
 	return false;
 }
 
+/* For each struct_ops program P, referenced from some struct_ops map M,
+ * enable P.autoload if there are Ms for which M.autocreate is true,
+ * disable P.autoload if for all Ms M.autocreate is false.
+ * Don't change P.autoload for programs that are not referenced from any maps.
+ */
+static int bpf_object__adjust_struct_ops_autoload(struct bpf_object *obj)
+{
+	struct bpf_program *prog;
+	struct bpf_map *map;
+	int i, j, k, vlen;
+	struct {
+		__u8 any_map_autocreate:1;
+		__u8 used_in_struct_ops_map:1;
+	} *refs;
+
+	refs = calloc(obj->nr_programs, sizeof(refs[0]));
+	if (!refs)
+		return -ENOMEM;
+
+	for (i = 0; i < obj->nr_maps; i++) {
+		map = &obj->maps[i];
+		if (!bpf_map__is_struct_ops(map))
+			continue;
+
+		vlen = btf_vlen(map->st_ops->type);
+		for (j = 0; j < vlen; ++j) {
+			prog = map->st_ops->progs[j];
+			if (!prog)
+				continue;
+
+			k = prog - obj->programs;
+			if (k < 0 || k > obj->nr_programs)
+				continue;
+
+			refs[k].used_in_struct_ops_map = true;
+			refs[k].any_map_autocreate |= map->autocreate;
+		}
+	}
+
+	for (i = 0; i < obj->nr_programs; ++i)
+		if (refs[i].used_in_struct_ops_map)
+			obj->programs[i].autoload = refs[i].any_map_autocreate;
+
+	free(refs);
+	return 0;
+}
+
 /* Init the map's fields that depend on kern_btf */
 static int bpf_map__init_kern_struct_ops(struct bpf_map *map)
 {
@@ -8163,6 +8210,7 @@  static int bpf_object_load(struct bpf_object *obj, int extra_log_level, const ch
 	err = err ? : bpf_object__resolve_externs(obj, obj->kconfig);
 	err = err ? : bpf_object__sanitize_maps(obj);
 	err = err ? : bpf_object__init_kern_struct_ops_maps(obj);
+	err = err ? : bpf_object__adjust_struct_ops_autoload(obj);
 	err = err ? : bpf_object__relocate(obj, obj->btf_custom_path ? : target_btf_path);
 	err = err ? : bpf_object__sanitize_and_load_btf(obj);
 	err = err ? : bpf_object__create_maps(obj);