Merge branch 'bpf-add-kmem_cache-iterator-and-kfunc'

Namhyung Kim says:

====================
bpf: Add kmem_cache iterator and kfunc

Hello,

I'm proposing a new iterator and a kfunc for the slab memory allocator
to get information of each kmem_cache like in /proc/slabinfo or
/sys/kernel/slab in more flexible way.

v5 changes

 * set PTR_UNTRUSTED for return value of bpf_get_kmem_cache()  (Alexei)
 * add KF_RCU_PROTECTED to bpf_get_kmem_cache().  See below.  (Song)
 * add WARN_ON_ONCE and comment in kmem_cache_iter_seq_next()  (Song)
 * change kmem_cache_iter_seq functions not to call BPF on intermediate stop
 * add a subtest to compare the kmem cache info with /proc/slabinfo  (Alexei)

v4: https://lore.kernel.org/lkml/20241002180956.1781008-1-namhyung@kernel.org

 * skip kmem_cache_destroy() in kmem_cache_iter_seq_stop() if possible  (Vlastimil)
 * fix a bug in the kmem_cache_iter_seq_start() for the last entry

v3: https://lore.kernel.org/lkml/20241002065456.1580143-1-namhyung@kernel.org/

 * rework kmem_cache_iter not to hold slab_mutex when running BPF  (Alexei)
 * add virt_addr_valid() check  (Alexei)
 * fix random test failure by running test with the current task  (Hyeonggon)

v2: https://lore.kernel.org/lkml/20240927184133.968283-1-namhyung@kernel.org/

 * rename it to "kmem_cache_iter"
 * fix a build issue
 * add Acked-by's from Roman and Vlastimil (Thanks!)
 * add error codes in the test for debugging

v1: https://lore.kernel.org/lkml/20240925223023.735947-1-namhyung@kernel.org/

My use case is `perf lock contention` tool which shows contended locks
but many of them are not global locks and don't have symbols.  If it
can tranlate the address of the lock in a slab object to the name of
the slab, it'd be much more useful.

I'm not aware of type information in slab yet, but I was told there's
a work to associate BTF ID with it.  It'd be definitely helpful to my
use case.  Probably we need another kfunc to get the start address of
the object or the offset in the object from an address if the type
info is available.  But I want to start with a simple thing first.

The kmem_cache_iter iterates kmem_cache objects under slab_mutex and
will be useful for userspace to prepare some work for specific slabs
like setting up filters in advance.  And the bpf_get_kmem_cache()
kfunc will return a pointer to a slab from the address of a lock.

And the test code is to read from the iterator and make sure it finds
a slab cache of the task_struct for the current task.

The code is available at 'bpf/slab-iter-v5' branch in
https://git.kernel.org/pub/scm/linux/kernel/git/namhyung/linux-perf.git

Thanks,
Namhyung
====================

Link: https://lore.kernel.org/r/20241010232505.1339892-1-namhyung@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

3 files changed, 209 insertions, 0 deletions

diff --git a/tools/testing/selftests/bpf/prog_tests/kmem_cache_iter.c b/tools/testing/selftests/bpf/prog_tests/kmem_cache_iter.c
new file mode 100644
index 000000000000..848d8fc9171f
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/kmem_cache_iter.c
@@ -0,0 +1,115 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Google */
+
+#include <test_progs.h>
+#include <bpf/libbpf.h>
+#include <bpf/btf.h>
+#include "kmem_cache_iter.skel.h"
+
+#define SLAB_NAME_MAX  32
+
+struct kmem_cache_result {
+	char name[SLAB_NAME_MAX];
+	long obj_size;
+};
+
+static void subtest_kmem_cache_iter_check_task_struct(struct kmem_cache_iter *skel)
+{
+	LIBBPF_OPTS(bpf_test_run_opts, opts,
+		.flags = 0,  /* Run it with the current task */
+	);
+	int prog_fd = bpf_program__fd(skel->progs.check_task_struct);
+
+	/* Get task_struct and check it if's from a slab cache */
+	ASSERT_OK(bpf_prog_test_run_opts(prog_fd, &opts), "prog_test_run");
+
+	/* The BPF program should set 'found' variable */
+	ASSERT_EQ(skel->bss->task_struct_found, 1, "task_struct_found");
+}
+
+static void subtest_kmem_cache_iter_check_slabinfo(struct kmem_cache_iter *skel)
+{
+	FILE *fp;
+	int map_fd;
+	char name[SLAB_NAME_MAX];
+	unsigned long objsize;
+	char rest_of_line[1000];
+	struct kmem_cache_result r;
+	int seen = 0;
+
+	fp = fopen("/proc/slabinfo", "r");
+	if (fp == NULL) {
+		/* CONFIG_SLUB_DEBUG is not enabled */
+		return;
+	}
+
+	map_fd = bpf_map__fd(skel->maps.slab_result);
+
+	/* Ignore first two lines for header */
+	fscanf(fp, "slabinfo - version: %*d.%*d\n");
+	fscanf(fp, "# %*s %*s %*s %*s %*s %*s : %[^\n]\n", rest_of_line);
+
+	/* Compare name and objsize only - others can be changes frequently */
+	while (fscanf(fp, "%s %*u %*u %lu %*u %*u : %[^\n]\n",
+		      name, &objsize, rest_of_line) == 3) {
+		int ret = bpf_map_lookup_elem(map_fd, &seen, &r);
+
+		if (!ASSERT_OK(ret, "kmem_cache_lookup"))
+			break;
+
+		ASSERT_STREQ(r.name, name, "kmem_cache_name");
+		ASSERT_EQ(r.obj_size, objsize, "kmem_cache_objsize");
+
+		seen++;
+	}
+
+	ASSERT_EQ(skel->bss->kmem_cache_seen, seen, "kmem_cache_seen_eq");
+
+	fclose(fp);
+}
+
+void test_kmem_cache_iter(void)
+{
+	DECLARE_LIBBPF_OPTS(bpf_iter_attach_opts, opts);
+	struct kmem_cache_iter *skel = NULL;
+	union bpf_iter_link_info linfo = {};
+	struct bpf_link *link;
+	char buf[256];
+	int iter_fd;
+
+	skel = kmem_cache_iter__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "kmem_cache_iter__open_and_load"))
+		return;
+
+	opts.link_info = &linfo;
+	opts.link_info_len = sizeof(linfo);
+
+	link = bpf_program__attach_iter(skel->progs.slab_info_collector, &opts);
+	if (!ASSERT_OK_PTR(link, "attach_iter"))
+		goto destroy;
+
+	iter_fd = bpf_iter_create(bpf_link__fd(link));
+	if (!ASSERT_GE(iter_fd, 0, "iter_create"))
+		goto free_link;
+
+	memset(buf, 0, sizeof(buf));
+	while (read(iter_fd, buf, sizeof(buf) > 0)) {
+		/* Read out all contents */
+		printf("%s", buf);
+	}
+
+	/* Next reads should return 0 */
+	ASSERT_EQ(read(iter_fd, buf, sizeof(buf)), 0, "read");
+
+	if (test__start_subtest("check_task_struct"))
+		subtest_kmem_cache_iter_check_task_struct(skel);
+	if (test__start_subtest("check_slabinfo"))
+		subtest_kmem_cache_iter_check_slabinfo(skel);
+
+	close(iter_fd);
+
+free_link:
+	bpf_link__destroy(link);
+destroy:
+	kmem_cache_iter__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter.h b/tools/testing/selftests/bpf/progs/bpf_iter.h
index c41ee80533ca..3305dc3a74b3 100644
--- a/tools/testing/selftests/bpf/progs/bpf_iter.h
+++ b/tools/testing/selftests/bpf/progs/bpf_iter.h
@@ -24,6 +24,7 @@
 #define BTF_F_PTR_RAW BTF_F_PTR_RAW___not_used
 #define BTF_F_ZERO BTF_F_ZERO___not_used
 #define bpf_iter__ksym bpf_iter__ksym___not_used
+#define bpf_iter__kmem_cache bpf_iter__kmem_cache___not_used
 #include "vmlinux.h"
 #undef bpf_iter_meta
 #undef bpf_iter__bpf_map
@@ -48,6 +49,7 @@
 #undef BTF_F_PTR_RAW
 #undef BTF_F_ZERO
 #undef bpf_iter__ksym
+#undef bpf_iter__kmem_cache
 
 struct bpf_iter_meta {
 	struct seq_file *seq;
@@ -165,3 +167,8 @@ struct bpf_iter__ksym {
 	struct bpf_iter_meta *meta;
 	struct kallsym_iter *ksym;
 };
+
+struct bpf_iter__kmem_cache {
+	struct bpf_iter_meta *meta;
+	struct kmem_cache *s;
+} __attribute__((preserve_access_index));
diff --git a/tools/testing/selftests/bpf/progs/kmem_cache_iter.c b/tools/testing/selftests/bpf/progs/kmem_cache_iter.c
new file mode 100644
index 000000000000..72c9dafecd98
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/kmem_cache_iter.c
@@ -0,0 +1,87 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Google */
+
+#include "bpf_iter.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+char _license[] SEC("license") = "GPL";
+
+#define SLAB_NAME_MAX  32
+
+struct kmem_cache_result {
+	char name[SLAB_NAME_MAX];
+	long obj_size;
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(key_size, sizeof(void *));
+	__uint(value_size, SLAB_NAME_MAX);
+	__uint(max_entries, 1);
+} slab_hash SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(key_size, sizeof(int));
+	__uint(value_size, sizeof(struct kmem_cache_result));
+	__uint(max_entries, 1024);
+} slab_result SEC(".maps");
+
+extern struct kmem_cache *bpf_get_kmem_cache(u64 addr) __ksym;
+
+/* Result, will be checked by userspace */
+int task_struct_found;
+int kmem_cache_seen;
+
+SEC("iter/kmem_cache")
+int slab_info_collector(struct bpf_iter__kmem_cache *ctx)
+{
+	struct seq_file *seq = ctx->meta->seq;
+	struct kmem_cache *s = ctx->s;
+	struct kmem_cache_result *r;
+	int idx;
+
+	if (s) {
+		/* To make sure if the slab_iter implements the seq interface
+		 * properly and it's also useful for debugging.
+		 */
+		BPF_SEQ_PRINTF(seq, "%s: %u\n", s->name, s->size);
+
+		idx = kmem_cache_seen;
+		r = bpf_map_lookup_elem(&slab_result, &idx);
+		if (r == NULL)
+			return 0;
+
+		kmem_cache_seen++;
+
+		/* Save name and size to match /proc/slabinfo */
+		bpf_probe_read_kernel_str(r->name, sizeof(r->name), s->name);
+		r->obj_size = s->size;
+
+		if (!bpf_strncmp(r->name, 11, "task_struct"))
+			bpf_map_update_elem(&slab_hash, &s, r->name, BPF_NOEXIST);
+	}
+
+	return 0;
+}
+
+SEC("raw_tp/bpf_test_finish")
+int BPF_PROG(check_task_struct)
+{
+	u64 curr = bpf_get_current_task();
+	struct kmem_cache *s;
+	char *name;
+
+	s = bpf_get_kmem_cache(curr);
+	if (s == NULL) {
+		task_struct_found = -1;
+		return 0;
+	}
+	name = bpf_map_lookup_elem(&slab_hash, &s);
+	if (name && !bpf_strncmp(name, 11, "task_struct"))
+		task_struct_found = 1;
+	else
+		task_struct_found = -2;
+	return 0;
+}