new file mode 100644
@@ -0,0 +1,358 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Functions to manage eBPF programs attached to cgroup subsystems
+ *
+ * Copyright 2022 Google LLC.
+ */
+#include <asm-generic/errno.h>
+#include <errno.h>
+#include <sys/types.h>
+#include <sys/mount.h>
+#include <sys/stat.h>
+#include <unistd.h>
+
+#include <test_progs.h>
+#include <bpf/libbpf.h>
+#include <bpf/bpf.h>
+
+#include "cgroup_helpers.h"
+#include "cgroup_hierarchical_stats.skel.h"
+
+#define PAGE_SIZE 4096
+#define MB(x) (x << 20)
+
+#define BPFFS_ROOT "/sys/fs/bpf/"
+#define BPFFS_VMSCAN BPFFS_ROOT"vmscan/"
+
+#define CG_ROOT_NAME "root"
+#define CG_ROOT_ID 1
+
+#define CGROUP_PATH(p, n) {.path = p"/"n, .name = n}
+
+static struct {
+ const char *path, *name;
+ unsigned long long id;
+ int fd;
+} cgroups[] = {
+ CGROUP_PATH("/", "test"),
+ CGROUP_PATH("/test", "child1"),
+ CGROUP_PATH("/test", "child2"),
+ CGROUP_PATH("/test/child1", "child1_1"),
+ CGROUP_PATH("/test/child1", "child1_2"),
+ CGROUP_PATH("/test/child2", "child2_1"),
+ CGROUP_PATH("/test/child2", "child2_2"),
+};
+
+#define N_CGROUPS ARRAY_SIZE(cgroups)
+#define N_NON_LEAF_CGROUPS 3
+
+static int root_cgroup_fd;
+static bool mounted_bpffs;
+
+/* reads file at 'path' to 'buf', returns 0 on success. */
+static int read_from_file(const char *path, char *buf, size_t size)
+{
+ int fd, len;
+
+ fd = open(path, O_RDONLY);
+ if (fd < 0)
+ return fd;
+
+ len = read(fd, buf, size);
+ close(fd);
+ if (len < 0)
+ return len;
+
+ buf[len] = 0;
+ return 0;
+}
+
+/* mounts bpffs and mkdir for reading stats, returns 0 on success. */
+static int setup_bpffs(void)
+{
+ int err;
+
+ /* Mount bpffs */
+ err = mount("bpf", BPFFS_ROOT, "bpf", 0, NULL);
+ mounted_bpffs = !err;
+ if (ASSERT_FALSE(err && errno != EBUSY, "mount"))
+ return err;
+
+ /* Create a directory to contain stat files in bpffs */
+ err = mkdir(BPFFS_VMSCAN, 0755);
+ if (!ASSERT_OK(err, "mkdir"))
+ return err;
+
+ return 0;
+}
+
+static void cleanup_bpffs(void)
+{
+ /* Remove created directory in bpffs */
+ ASSERT_OK(rmdir(BPFFS_VMSCAN), "rmdir "BPFFS_VMSCAN);
+
+ /* Unmount bpffs, if it wasn't already mounted when we started */
+ if (mounted_bpffs)
+ return;
+
+ ASSERT_OK(umount(BPFFS_ROOT), "unmount bpffs");
+}
+
+/* sets up cgroups, returns 0 on success. */
+static int setup_cgroups(void)
+{
+ int i, fd, err;
+
+ err = setup_cgroup_environment();
+ if (!ASSERT_OK(err, "setup_cgroup_environment"))
+ return err;
+
+ root_cgroup_fd = get_root_cgroup();
+ if (!ASSERT_GE(root_cgroup_fd, 0, "get_root_cgroup"))
+ return root_cgroup_fd;
+
+ for (i = 0; i < N_CGROUPS; i++) {
+ fd = create_and_get_cgroup(cgroups[i].path);
+ if (!ASSERT_GE(fd, 0, "create_and_get_cgroup"))
+ return fd;
+
+ cgroups[i].fd = fd;
+ cgroups[i].id = get_cgroup_id(cgroups[i].path);
+
+ /*
+ * Enable memcg controller for the entire hierarchy.
+ * Note that stats are collected for all cgroups in a hierarchy
+ * with memcg enabled anyway, but are only exposed for cgroups
+ * that have memcg enabled.
+ */
+ if (i < N_NON_LEAF_CGROUPS) {
+ err = enable_controllers(cgroups[i].path, "memory");
+ if (!ASSERT_OK(err, "enable_controllers"))
+ return err;
+ }
+ }
+ return 0;
+}
+
+static void cleanup_cgroups(void)
+{
+ close(root_cgroup_fd);
+ for (int i = 0; i < N_CGROUPS; i++)
+ close(cgroups[i].fd);
+ cleanup_cgroup_environment();
+}
+
+/* Sets up cgroup hiearchary, returns 0 on success. */
+static int setup_hierarchy(void)
+{
+ return setup_bpffs() || setup_cgroups();
+}
+
+static void destroy_hierarchy(void)
+{
+ cleanup_cgroups();
+ cleanup_bpffs();
+}
+
+static int reclaimer(const char *cgroup_path, size_t size)
+{
+ static char size_buf[128];
+ char *buf, *ptr;
+ int err;
+
+ /* Join cgroup in the parent process workdir */
+ if (join_parent_cgroup(cgroup_path))
+ return EACCES;
+
+ /* Allocate memory */
+ buf = malloc(size);
+ if (!buf)
+ return ENOMEM;
+
+ /* Write to memory to make sure it's actually allocated */
+ for (ptr = buf; ptr < buf + size; ptr += PAGE_SIZE)
+ *ptr = 1;
+
+ /* Try to reclaim memory */
+ snprintf(size_buf, 128, "%lu", size);
+ err = write_cgroup_file_parent(cgroup_path, "memory.reclaim", size_buf);
+
+ free(buf);
+ /* memory.reclaim returns EAGAIN if the amount is not fully reclaimed */
+ if (err && errno != EAGAIN)
+ return errno;
+
+ return 0;
+}
+
+static int induce_vmscan(void)
+{
+ int i, status;
+
+ /*
+ * In every leaf cgroup, run a child process that allocates some memory
+ * and attempts to reclaim some of it.
+ */
+ for (i = N_NON_LEAF_CGROUPS; i < N_CGROUPS; i++) {
+ pid_t pid;
+
+ /* Create reclaimer child */
+ pid = fork();
+ if (pid == 0) {
+ status = reclaimer(cgroups[i].path, MB(5));
+ exit(status);
+ }
+
+ /* Cleanup reclaimer child */
+ waitpid(pid, &status, 0);
+ ASSERT_TRUE(WIFEXITED(status), "reclaimer exited");
+ ASSERT_EQ(WEXITSTATUS(status), 0, "reclaim exit code");
+ }
+ return 0;
+}
+
+static unsigned long long
+get_cgroup_vmscan_delay(unsigned long long cgroup_id, const char *file_name)
+{
+ unsigned long long vmscan = 0, id = 0;
+ static char buf[128], path[128];
+
+ /* For every cgroup, read the file generated by cgroup_iter */
+ snprintf(path, 128, "%s%s", BPFFS_VMSCAN, file_name);
+ if (!ASSERT_OK(read_from_file(path, buf, 128), "read cgroup_iter"))
+ return 0;
+
+ /* Check the output file formatting */
+ ASSERT_EQ(sscanf(buf, "cg_id: %llu, total_vmscan_delay: %llu\n",
+ &id, &vmscan), 2, "output format");
+
+ /* Check that the cgroup_id is displayed correctly */
+ ASSERT_EQ(id, cgroup_id, "cgroup_id");
+ /* Check that the vmscan reading is non-zero */
+ ASSERT_GT(vmscan, 0, "vmscan_reading");
+ return vmscan;
+}
+
+static void check_vmscan_stats(void)
+{
+ unsigned long long vmscan_readings[N_CGROUPS], vmscan_root;
+ int i;
+
+ for (i = 0; i < N_CGROUPS; i++) {
+ vmscan_readings[i] = get_cgroup_vmscan_delay(cgroups[i].id,
+ cgroups[i].name);
+ }
+
+ /* Read stats for root too */
+ vmscan_root = get_cgroup_vmscan_delay(CG_ROOT_ID, CG_ROOT_NAME);
+
+ /* Check that child1 == child1_1 + child1_2 */
+ ASSERT_EQ(vmscan_readings[1], vmscan_readings[3] + vmscan_readings[4],
+ "child1_vmscan");
+ /* Check that child2 == child2_1 + child2_2 */
+ ASSERT_EQ(vmscan_readings[2], vmscan_readings[5] + vmscan_readings[6],
+ "child2_vmscan");
+ /* Check that test == child1 + child2 */
+ ASSERT_EQ(vmscan_readings[0], vmscan_readings[1] + vmscan_readings[2],
+ "test_vmscan");
+ /* Check that root >= test */
+ ASSERT_GE(vmscan_root, vmscan_readings[1], "root_vmscan");
+}
+
+/* Creates iter link and pins in bpffs, returns 0 on success, -errno on failure.
+ */
+static int setup_cgroup_iter(struct cgroup_hierarchical_stats *obj,
+ int cgroup_fd, const char *file_name)
+{
+ DECLARE_LIBBPF_OPTS(bpf_iter_attach_opts, opts);
+ union bpf_iter_link_info linfo = {};
+ struct bpf_link *link;
+ static char path[128];
+ int err;
+
+ /*
+ * Create an iter link, parameterized by cgroup_fd.
+ * We only want to traverse one cgroup, so set the traversal order to
+ * "pre", and return 1 from dump_vmscan to stop iteration after the
+ * first cgroup.
+ */
+ linfo.cgroup.cgroup_fd = cgroup_fd;
+ linfo.cgroup.traversal_order = BPF_ITER_CGROUP_PRE;
+ opts.link_info = &linfo;
+ opts.link_info_len = sizeof(linfo);
+ link = bpf_program__attach_iter(obj->progs.dump_vmscan, &opts);
+ if (!ASSERT_OK_PTR(link, "attach iter"))
+ return -EFAULT;
+
+ /* Pin the link to a bpffs file */
+ snprintf(path, 128, "%s%s", BPFFS_VMSCAN, file_name);
+ err = bpf_link__pin(link, path);
+ ASSERT_OK(err, "pin cgroup_iter");
+
+ /* Remove the link, leaving only the ref held by the pinned file */
+ bpf_link__destroy(link);
+ return err;
+}
+
+/* Sets up programs for collecting stats, returns 0 on success. */
+static int setup_progs(struct cgroup_hierarchical_stats **skel)
+{
+ int i, err;
+
+ *skel = cgroup_hierarchical_stats__open_and_load();
+ if (!ASSERT_OK_PTR(*skel, "open_and_load"))
+ return 1;
+
+ /* Attach cgroup_iter program that will dump the stats to cgroups */
+ for (i = 0; i < N_CGROUPS; i++) {
+ err = setup_cgroup_iter(*skel, cgroups[i].fd, cgroups[i].name);
+ if (!ASSERT_OK(err, "setup_cgroup_iter"))
+ return err;
+ }
+
+ /* Also dump stats for root */
+ err = setup_cgroup_iter(*skel, root_cgroup_fd, CG_ROOT_NAME);
+ if (!ASSERT_OK(err, "setup_cgroup_iter"))
+ return err;
+
+ err = cgroup_hierarchical_stats__attach(*skel);
+ if (!ASSERT_OK(err, "attach"))
+ return err;
+
+ return 0;
+}
+
+static void destroy_progs(struct cgroup_hierarchical_stats *skel)
+{
+ static char path[128];
+ int i;
+
+ for (i = 0; i < N_CGROUPS; i++) {
+ /* Delete files in bpffs that cgroup_iters are pinned in */
+ snprintf(path, 128, "%s%s", BPFFS_VMSCAN,
+ cgroups[i].name);
+ ASSERT_OK(remove(path), "remove cgroup_iter pin");
+ }
+
+ /* Delete root file in bpffs */
+ snprintf(path, 128, "%s%s", BPFFS_VMSCAN, CG_ROOT_NAME);
+ ASSERT_OK(remove(path), "remove cgroup_iter root pin");
+ cgroup_hierarchical_stats__destroy(skel);
+}
+
+void test_cgroup_hierarchical_stats(void)
+{
+ struct cgroup_hierarchical_stats *skel = NULL;
+
+ if (setup_hierarchy())
+ goto hierarchy_cleanup;
+ if (setup_progs(&skel))
+ goto cleanup;
+ if (induce_vmscan())
+ goto cleanup;
+ check_vmscan_stats();
+cleanup:
+ destroy_progs(skel);
+hierarchy_cleanup:
+ destroy_hierarchy();
+}
new file mode 100644
@@ -0,0 +1,218 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Functions to manage eBPF programs attached to cgroup subsystems
+ *
+ * Copyright 2022 Google LLC.
+ */
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+char _license[] SEC("license") = "GPL";
+
+/*
+ * Start times are stored per-task, not per-cgroup, as multiple tasks in one
+ * cgroup can perform reclaim concurrently.
+ */
+struct {
+ __uint(type, BPF_MAP_TYPE_TASK_STORAGE);
+ __uint(map_flags, BPF_F_NO_PREALLOC);
+ __type(key, int);
+ __type(value, __u64);
+} vmscan_start_time SEC(".maps");
+
+struct vmscan_percpu {
+ /* Previous percpu state, to figure out if we have new updates */
+ __u64 prev;
+ /* Current percpu state */
+ __u64 state;
+};
+
+struct vmscan {
+ /* State propagated through children, pending aggregation */
+ __u64 pending;
+ /* Total state, including all cpus and all children */
+ __u64 state;
+};
+
+struct {
+ __uint(type, BPF_MAP_TYPE_PERCPU_HASH);
+ __uint(max_entries, 100);
+ __type(key, __u64);
+ __type(value, struct vmscan_percpu);
+} pcpu_cgroup_vmscan_elapsed SEC(".maps");
+
+struct {
+ __uint(type, BPF_MAP_TYPE_HASH);
+ __uint(max_entries, 100);
+ __type(key, __u64);
+ __type(value, struct vmscan);
+} cgroup_vmscan_elapsed SEC(".maps");
+
+extern void cgroup_rstat_updated(struct cgroup *cgrp, int cpu) __ksym;
+extern void cgroup_rstat_flush(struct cgroup *cgrp) __ksym;
+
+static struct cgroup *task_memcg(struct task_struct *task)
+{
+ return task->cgroups->subsys[memory_cgrp_id]->cgroup;
+}
+
+static uint64_t cgroup_id(struct cgroup *cgrp)
+{
+ return cgrp->kn->id;
+}
+
+static int create_vmscan_percpu_elem(__u64 cg_id, __u64 state)
+{
+ struct vmscan_percpu pcpu_init = {.state = state, .prev = 0};
+
+ return bpf_map_update_elem(&pcpu_cgroup_vmscan_elapsed, &cg_id,
+ &pcpu_init, BPF_NOEXIST);
+}
+
+static int create_vmscan_elem(__u64 cg_id, __u64 state, __u64 pending)
+{
+ struct vmscan init = {.state = state, .pending = pending};
+
+ return bpf_map_update_elem(&cgroup_vmscan_elapsed, &cg_id,
+ &init, BPF_NOEXIST);
+}
+
+SEC("tp_btf/mm_vmscan_memcg_reclaim_begin")
+int BPF_PROG(vmscan_start, int order, gfp_t gfp_flags)
+{
+ struct task_struct *task = bpf_get_current_task_btf();
+ __u64 *start_time_ptr;
+
+ start_time_ptr = bpf_task_storage_get(&vmscan_start_time, task, 0,
+ BPF_LOCAL_STORAGE_GET_F_CREATE);
+ if (start_time_ptr)
+ *start_time_ptr = bpf_ktime_get_ns();
+ return 0;
+}
+
+SEC("tp_btf/mm_vmscan_memcg_reclaim_end")
+int BPF_PROG(vmscan_end, unsigned long nr_reclaimed)
+{
+ struct vmscan_percpu *pcpu_stat;
+ struct task_struct *current = bpf_get_current_task_btf();
+ struct cgroup *cgrp;
+ __u64 *start_time_ptr;
+ __u64 current_elapsed, cg_id;
+ __u64 end_time = bpf_ktime_get_ns();
+
+ /*
+ * cgrp is the first parent cgroup of current that has memcg enabled in
+ * its subtree_control, or NULL if memcg is disabled in the entire tree.
+ * In a cgroup hierarchy like this:
+ * a
+ * / \
+ * b c
+ * If "a" has memcg enabled, while "b" doesn't, then processes in "b"
+ * will accumulate their stats directly to "a". This makes sure that no
+ * stats are lost from processes in leaf cgroups that don't have memcg
+ * enabled, but only exposes stats for cgroups that have memcg enabled.
+ */
+ cgrp = task_memcg(current);
+ if (!cgrp)
+ return 0;
+
+ cg_id = cgroup_id(cgrp);
+ start_time_ptr = bpf_task_storage_get(&vmscan_start_time, current, 0,
+ BPF_LOCAL_STORAGE_GET_F_CREATE);
+ if (!start_time_ptr)
+ return 0;
+
+ current_elapsed = end_time - *start_time_ptr;
+ pcpu_stat = bpf_map_lookup_elem(&pcpu_cgroup_vmscan_elapsed,
+ &cg_id);
+ if (pcpu_stat)
+ pcpu_stat->state += current_elapsed;
+ else if (create_vmscan_percpu_elem(cg_id, current_elapsed))
+ return 0;
+
+ cgroup_rstat_updated(cgrp, bpf_get_smp_processor_id());
+ return 0;
+}
+
+SEC("fentry/bpf_rstat_flush")
+int BPF_PROG(vmscan_flush, struct cgroup *cgrp, struct cgroup *parent, int cpu)
+{
+ struct vmscan_percpu *pcpu_stat;
+ struct vmscan *total_stat, *parent_stat;
+ __u64 cg_id = cgroup_id(cgrp);
+ __u64 parent_cg_id = parent ? cgroup_id(parent) : 0;
+ __u64 *pcpu_vmscan;
+ __u64 state;
+ __u64 delta = 0;
+
+ /* Add CPU changes on this level since the last flush */
+ pcpu_stat = bpf_map_lookup_percpu_elem(&pcpu_cgroup_vmscan_elapsed,
+ &cg_id, cpu);
+ if (pcpu_stat) {
+ state = pcpu_stat->state;
+ delta += state - pcpu_stat->prev;
+ pcpu_stat->prev = state;
+ }
+
+ total_stat = bpf_map_lookup_elem(&cgroup_vmscan_elapsed, &cg_id);
+ if (!total_stat) {
+ if (create_vmscan_elem(cg_id, delta, 0))
+ return 0;
+
+ goto update_parent;
+ }
+
+ /* Collect pending stats from subtree */
+ if (total_stat->pending) {
+ delta += total_stat->pending;
+ total_stat->pending = 0;
+ }
+
+ /* Propagate changes to this cgroup's total */
+ total_stat->state += delta;
+
+update_parent:
+ /* Skip if there are no changes to propagate, or no parent */
+ if (!delta || !parent_cg_id)
+ return 0;
+
+ /* Propagate changes to cgroup's parent */
+ parent_stat = bpf_map_lookup_elem(&cgroup_vmscan_elapsed,
+ &parent_cg_id);
+ if (parent_stat)
+ parent_stat->pending += delta;
+ else
+ create_vmscan_elem(parent_cg_id, 0, delta);
+ return 0;
+}
+
+SEC("iter.s/cgroup")
+int BPF_PROG(dump_vmscan, struct bpf_iter_meta *meta, struct cgroup *cgrp)
+{
+ struct seq_file *seq = meta->seq;
+ struct vmscan *total_stat;
+ __u64 cg_id = cgrp ? cgroup_id(cgrp) : 0;
+
+ /* Do nothing for the terminal call */
+ if (!cg_id)
+ return 1;
+
+ /* Flush the stats to make sure we get the most updated numbers */
+ cgroup_rstat_flush(cgrp);
+
+ total_stat = bpf_map_lookup_elem(&cgroup_vmscan_elapsed, &cg_id);
+ if (!total_stat) {
+ BPF_SEQ_PRINTF(seq, "cg_id: %llu, total_vmscan_delay: 0\n",
+ cg_id);
+ } else {
+ BPF_SEQ_PRINTF(seq, "cg_id: %llu, total_vmscan_delay: %llu\n",
+ cg_id, total_stat->state);
+ }
+
+ /*
+ * We only dump stats for one cgroup here, so return 1 to stop
+ * iteration after the first cgroup.
+ */
+ return 1;
+}