--- /dev/null
+/*
+ * Copyright (c) 2016 Facebook
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ */
+#define _GNU_SOURCE
+#include <linux/types.h>
+#include <stdio.h>
+#include <unistd.h>
+#include <linux/bpf.h>
+#include <errno.h>
+#include <string.h>
+#include <assert.h>
+#include <sched.h>
+#include <sys/wait.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+#include <stdlib.h>
+#include <time.h>
+#include "libbpf.h"
+
+#define min(a, b) ((a) < (b) ? (a) : (b))
+#define offsetof(TYPE, MEMBER) ((size_t)&((TYPE *)0)->MEMBER)
+#define container_of(ptr, type, member) ({ \
+ const typeof( ((type *)0)->member ) *__mptr = (ptr); \
+ (type *)( (char *)__mptr - offsetof(type,member) );})
+
+static int nr_cpus;
+static unsigned long long *dist_keys;
+static unsigned int dist_key_counts;
+
+struct list_head {
+ struct list_head *next, *prev;
+};
+
+static inline void INIT_LIST_HEAD(struct list_head *list)
+{
+ list->next = list;
+ list->prev = list;
+}
+
+static inline int list_empty(const struct list_head *head)
+{
+ return head->next == head;
+}
+
+static inline void __list_add(struct list_head *new,
+ struct list_head *prev,
+ struct list_head *next)
+{
+ next->prev = new;
+ new->next = next;
+ new->prev = prev;
+ prev->next = new;
+}
+
+static inline void list_add(struct list_head *new, struct list_head *head)
+{
+ __list_add(new, head, head->next);
+}
+
+static inline void __list_del(struct list_head *prev, struct list_head *next)
+{
+ next->prev = prev;
+ prev->next = next;
+}
+
+static inline void __list_del_entry(struct list_head *entry)
+{
+ __list_del(entry->prev, entry->next);
+}
+
+static inline void list_move(struct list_head *list, struct list_head *head)
+{
+ __list_del_entry(list);
+ list_add(list, head);
+}
+
+#define list_entry(ptr, type, member) \
+ container_of(ptr, type, member)
+
+#define list_last_entry(ptr, type, member) \
+ list_entry((ptr)->prev, type, member)
+
+struct pfect_lru_node {
+ struct list_head list;
+ unsigned long long key;
+};
+
+struct pfect_lru {
+ struct list_head list;
+ struct pfect_lru_node *free_nodes;
+ unsigned int cur_size;
+ unsigned int lru_size;
+ unsigned int nr_unique;
+ unsigned int nr_misses;
+ unsigned int total;
+ int map_fd;
+};
+
+static void pfect_lru_init(struct pfect_lru *lru, unsigned int lru_size,
+ unsigned int nr_possible_elems)
+{
+ lru->map_fd = bpf_create_map(BPF_MAP_TYPE_HASH,
+ sizeof(unsigned long long),
+ sizeof(struct pfect_lru_node *),
+ nr_possible_elems, 0);
+ assert(lru->map_fd != -1);
+
+ lru->free_nodes = malloc(lru_size * sizeof(struct pfect_lru_node));
+ assert(lru->free_nodes);
+
+ INIT_LIST_HEAD(&lru->list);
+ lru->cur_size = 0;
+ lru->lru_size = lru_size;
+ lru->nr_unique = lru->nr_misses = lru->total = 0;
+}
+
+static void pfect_lru_destroy(struct pfect_lru *lru)
+{
+ close(lru->map_fd);
+ free(lru->free_nodes);
+}
+
+static int pfect_lru_lookup_or_insert(struct pfect_lru *lru,
+ unsigned long long key)
+{
+ struct pfect_lru_node *node = NULL;
+ int seen = 0;
+
+ lru->total++;
+ if (!bpf_lookup_elem(lru->map_fd, &key, &node)) {
+ if (node) {
+ list_move(&node->list, &lru->list);
+ return 1;
+ }
+ seen = 1;
+ }
+
+ if (lru->cur_size < lru->lru_size) {
+ node = &lru->free_nodes[lru->cur_size++];
+ INIT_LIST_HEAD(&node->list);
+ } else {
+ struct pfect_lru_node *null_node = NULL;
+
+ node = list_last_entry(&lru->list,
+ struct pfect_lru_node,
+ list);
+ bpf_update_elem(lru->map_fd, &node->key, &null_node, BPF_EXIST);
+ }
+
+ node->key = key;
+ list_move(&node->list, &lru->list);
+
+ lru->nr_misses++;
+ if (seen) {
+ assert(!bpf_update_elem(lru->map_fd, &key, &node, BPF_EXIST));
+ } else {
+ lru->nr_unique++;
+ assert(!bpf_update_elem(lru->map_fd, &key, &node, BPF_NOEXIST));
+ }
+
+ return seen;
+}
+
+static unsigned int read_keys(const char *dist_file,
+ unsigned long long **keys)
+{
+ struct stat fst;
+ unsigned long long *retkeys;
+ unsigned int counts = 0;
+ int dist_fd;
+ char *b, *l;
+ int i;
+
+ dist_fd = open(dist_file, 0);
+ assert(dist_fd != -1);
+
+ assert(fstat(dist_fd, &fst) == 0);
+ b = malloc(fst.st_size);
+ assert(b);
+
+ assert(read(dist_fd, b, fst.st_size) == fst.st_size);
+ close(dist_fd);
+ for (i = 0; i < fst.st_size; i++) {
+ if (b[i] == '\n')
+ counts++;
+ }
+ counts++; /* in case the last line has no \n */
+
+ retkeys = malloc(counts * sizeof(unsigned long long));
+ assert(retkeys);
+
+ counts = 0;
+ for (l = strtok(b, "\n"); l; l = strtok(NULL, "\n"))
+ retkeys[counts++] = strtoull(l, NULL, 10);
+ free(b);
+
+ *keys = retkeys;
+
+ return counts;
+}
+
+static int create_map(int map_type, int map_flags, unsigned int size)
+{
+ int map_fd;
+
+ map_fd = bpf_create_map(map_type, sizeof(unsigned long long),
+ sizeof(unsigned long long), size, map_flags);
+
+ if (map_fd == -1)
+ perror("bpf_create_map");
+
+ return map_fd;
+}
+
+static int sched_next_online(int pid, int next_to_try)
+{
+ cpu_set_t cpuset;
+
+ if (next_to_try == nr_cpus)
+ return -1;
+
+ while (next_to_try < nr_cpus) {
+ CPU_ZERO(&cpuset);
+ CPU_SET(next_to_try++, &cpuset);
+ if (!sched_setaffinity(pid, sizeof(cpuset), &cpuset))
+ break;
+ }
+
+ return next_to_try;
+}
+
+static void run_parallel(unsigned int tasks, void (*fn)(int i, void *data),
+ void *data)
+{
+ int next_sched_cpu = 0;
+ pid_t pid[tasks];
+ int i;
+
+ for (i = 0; i < tasks; i++) {
+ pid[i] = fork();
+ if (pid[i] == 0) {
+ next_sched_cpu = sched_next_online(0, next_sched_cpu);
+ fn(i, data);
+ exit(0);
+ } else if (pid[i] == -1) {
+ printf("couldn't spawn #%d process\n", i);
+ exit(1);
+ }
+ /* It is mostly redundant and just allow the parent
+ * process to update next_shced_cpu for the next child
+ * process
+ */
+ next_sched_cpu = sched_next_online(pid[i], next_sched_cpu);
+ }
+ for (i = 0; i < tasks; i++) {
+ int status;
+
+ assert(waitpid(pid[i], &status, 0) == pid[i]);
+ assert(status == 0);
+ }
+}
+
+static void do_test_lru_dist(int task, void *data)
+{
+ unsigned int nr_misses = 0;
+ struct pfect_lru pfect_lru;
+ unsigned long long key, value = 1234;
+ unsigned int i;
+
+ unsigned int lru_map_fd = ((unsigned int *)data)[0];
+ unsigned int lru_size = ((unsigned int *)data)[1];
+ unsigned long long key_offset = task * dist_key_counts;
+
+ pfect_lru_init(&pfect_lru, lru_size, dist_key_counts);
+
+ for (i = 0; i < dist_key_counts; i++) {
+ key = dist_keys[i] + key_offset;
+
+ pfect_lru_lookup_or_insert(&pfect_lru, key);
+
+ if (!bpf_lookup_elem(lru_map_fd, &key, &value))
+ continue;
+
+ if (bpf_update_elem(lru_map_fd, &key, &value, BPF_NOEXIST)) {
+ printf("bpf_update_elem(lru_map_fd, %llu): errno:%d\n",
+ key, errno);
+ assert(0);
+ }
+
+ nr_misses++;
+ }
+
+ printf(" task:%d BPF LRU: nr_unique:%u(/%u) nr_misses:%u(/%u)\n",
+ task, pfect_lru.nr_unique, dist_key_counts, nr_misses,
+ dist_key_counts);
+ printf(" task:%d Perfect LRU: nr_unique:%u(/%u) nr_misses:%u(/%u)\n",
+ task, pfect_lru.nr_unique, pfect_lru.total,
+ pfect_lru.nr_misses, pfect_lru.total);
+
+ pfect_lru_destroy(&pfect_lru);
+ close(lru_map_fd);
+}
+
+static void test_parallel_lru_dist(int map_type, int map_flags,
+ int nr_tasks, unsigned int lru_size)
+{
+ int child_data[2];
+ int lru_map_fd;
+
+ printf("%s (map_type:%d map_flags:0x%X):\n", __func__, map_type,
+ map_flags);
+
+ if (map_flags & BPF_F_NO_COMMON_LRU)
+ lru_map_fd = create_map(map_type, map_flags,
+ nr_cpus * lru_size);
+ else
+ lru_map_fd = create_map(map_type, map_flags,
+ nr_tasks * lru_size);
+ assert(lru_map_fd != -1);
+
+ child_data[0] = lru_map_fd;
+ child_data[1] = lru_size;
+
+ run_parallel(nr_tasks, do_test_lru_dist, child_data);
+
+ close(lru_map_fd);
+}
+
+static void test_lru_loss0(int map_type, int map_flags)
+{
+ unsigned long long key, value[nr_cpus];
+ unsigned int old_unused_losses = 0;
+ unsigned int new_unused_losses = 0;
+ unsigned int used_losses = 0;
+ int map_fd;
+
+ printf("%s (map_type:%d map_flags:0x%X): ", __func__, map_type,
+ map_flags);
+
+ assert(sched_next_online(0, 0) != -1);
+
+ if (map_flags & BPF_F_NO_COMMON_LRU)
+ map_fd = create_map(map_type, map_flags, 900 * nr_cpus);
+ else
+ map_fd = create_map(map_type, map_flags, 900);
+
+ assert(map_fd != -1);
+
+ value[0] = 1234;
+
+ for (key = 1; key <= 1000; key++) {
+ int start_key, end_key;
+
+ assert(bpf_update_elem(map_fd, &key, value, BPF_NOEXIST) == 0);
+
+ start_key = 101;
+ end_key = min(key, 900);
+
+ while (start_key <= end_key) {
+ bpf_lookup_elem(map_fd, &start_key, value);
+ start_key++;
+ }
+ }
+
+ for (key = 1; key <= 1000; key++) {
+ if (bpf_lookup_elem(map_fd, &key, value)) {
+ if (key <= 100)
+ old_unused_losses++;
+ else if (key <= 900)
+ used_losses++;
+ else
+ new_unused_losses++;
+ }
+ }
+
+ close(map_fd);
+
+ printf("older-elem-losses:%d(/100) active-elem-losses:%d(/800) "
+ "newer-elem-losses:%d(/100)\n",
+ old_unused_losses, used_losses, new_unused_losses);
+}
+
+static void test_lru_loss1(int map_type, int map_flags)
+{
+ unsigned long long key, value[nr_cpus];
+ int map_fd;
+ unsigned int nr_losses = 0;
+
+ printf("%s (map_type:%d map_flags:0x%X): ", __func__, map_type,
+ map_flags);
+
+ assert(sched_next_online(0, 0) != -1);
+
+ if (map_flags & BPF_F_NO_COMMON_LRU)
+ map_fd = create_map(map_type, map_flags, 1000 * nr_cpus);
+ else
+ map_fd = create_map(map_type, map_flags, 1000);
+
+ assert(map_fd != -1);
+
+ value[0] = 1234;
+
+ for (key = 1; key <= 1000; key++)
+ assert(!bpf_update_elem(map_fd, &key, value, BPF_NOEXIST));
+
+ for (key = 1; key <= 1000; key++) {
+ if (bpf_lookup_elem(map_fd, &key, value))
+ nr_losses++;
+ }
+
+ close(map_fd);
+
+ printf("nr_losses:%d(/1000)\n", nr_losses);
+}
+
+static void do_test_parallel_lru_loss(int task, void *data)
+{
+ const unsigned int nr_stable_elems = 1000;
+ const unsigned int nr_repeats = 100000;
+
+ int map_fd = *(int *)data;
+ unsigned long long stable_base;
+ unsigned long long key, value[nr_cpus];
+ unsigned long long next_ins_key;
+ unsigned int nr_losses = 0;
+ unsigned int i;
+
+ stable_base = task * nr_repeats * 2 + 1;
+ next_ins_key = stable_base;
+ value[0] = 1234;
+ for (i = 0; i < nr_stable_elems; i++) {
+ assert(bpf_update_elem(map_fd, &next_ins_key, value,
+ BPF_NOEXIST) == 0);
+ next_ins_key++;
+ }
+
+ for (i = 0; i < nr_repeats; i++) {
+ int rn;
+
+ rn = rand();
+
+ if (rn % 10) {
+ key = rn % nr_stable_elems + stable_base;
+ bpf_lookup_elem(map_fd, &key, value);
+ } else {
+ bpf_update_elem(map_fd, &next_ins_key, value,
+ BPF_NOEXIST);
+ next_ins_key++;
+ }
+ }
+
+ key = stable_base;
+ for (i = 0; i < nr_stable_elems; i++) {
+ if (bpf_lookup_elem(map_fd, &key, value))
+ nr_losses++;
+ key++;
+ }
+
+ printf(" task:%d nr_losses:%u\n", task, nr_losses);
+}
+
+static void test_parallel_lru_loss(int map_type, int map_flags, int nr_tasks)
+{
+ int map_fd;
+
+ printf("%s (map_type:%d map_flags:0x%X):\n", __func__, map_type,
+ map_flags);
+
+ /* Give 20% more than the active working set */
+ if (map_flags & BPF_F_NO_COMMON_LRU)
+ map_fd = create_map(map_type, map_flags,
+ nr_cpus * (1000 + 200));
+ else
+ map_fd = create_map(map_type, map_flags,
+ nr_tasks * (1000 + 200));
+
+ assert(map_fd != -1);
+
+ run_parallel(nr_tasks, do_test_parallel_lru_loss, &map_fd);
+
+ close(map_fd);
+}
+
+int main(int argc, char **argv)
+{
+ struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY};
+ int map_flags[] = {0, BPF_F_NO_COMMON_LRU};
+ const char *dist_file;
+ int nr_tasks = 1;
+ int lru_size;
+ int f;
+
+ if (argc < 4) {
+ printf("Usage: %s <dist-file> <lru-size> <nr-tasks>\n",
+ argv[0]);
+ return -1;
+ }
+
+ dist_file = argv[1];
+ lru_size = atoi(argv[2]);
+ nr_tasks = atoi(argv[3]);
+
+ setbuf(stdout, NULL);
+
+ assert(!setrlimit(RLIMIT_MEMLOCK, &r));
+
+ srand(time(NULL));
+
+ nr_cpus = sysconf(_SC_NPROCESSORS_CONF);
+ assert(nr_cpus != -1);
+ printf("nr_cpus:%d\n\n", nr_cpus);
+
+ nr_tasks = min(nr_tasks, nr_cpus);
+
+ dist_key_counts = read_keys(dist_file, &dist_keys);
+ if (!dist_key_counts) {
+ printf("%s has no key\n", dist_file);
+ return -1;
+ }
+
+ for (f = 0; f < sizeof(map_flags) / sizeof(*map_flags); f++) {
+ test_lru_loss0(BPF_MAP_TYPE_LRU_HASH, map_flags[f]);
+ test_lru_loss1(BPF_MAP_TYPE_LRU_HASH, map_flags[f]);
+ test_parallel_lru_loss(BPF_MAP_TYPE_LRU_HASH, map_flags[f],
+ nr_tasks);
+ test_parallel_lru_dist(BPF_MAP_TYPE_LRU_HASH, map_flags[f],
+ nr_tasks, lru_size);
+ printf("\n");
+ }
+
+ free(dist_keys);
+
+ return 0;
+}
--- /dev/null
+/*
+ * Copyright (c) 2016 Facebook
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ */
+#define _GNU_SOURCE
+#include <stdio.h>
+#include <unistd.h>
+#include <errno.h>
+#include <string.h>
+#include <assert.h>
+#include <sched.h>
+#include <sys/wait.h>
+#include <stdlib.h>
+#include <time.h>
+#include "bpf_sys.h"
+
+#define LOCAL_FREE_TARGET (128)
+#define PERCPU_FREE_TARGET (16)
+
+static int nr_cpus;
+
+static int create_map(int map_type, int map_flags, unsigned int size)
+{
+ int map_fd;
+
+ map_fd = bpf_map_create(map_type, sizeof(unsigned long long),
+ sizeof(unsigned long long), size, map_flags);
+
+ if (map_fd == -1)
+ perror("bpf_map_create");
+
+ return map_fd;
+}
+
+static int map_subset(int map0, int map1)
+{
+ unsigned long long next_key = 0;
+ unsigned long long value0[nr_cpus], value1[nr_cpus];
+ int ret;
+
+ while (!bpf_map_next_key(map1, &next_key, &next_key)) {
+ assert(!bpf_map_lookup(map1, &next_key, value1));
+ ret = bpf_map_lookup(map0, &next_key, value0);
+ if (ret) {
+ printf("key:%llu not found from map. %s(%d)\n",
+ next_key, strerror(errno), errno);
+ return 0;
+ }
+ if (value0[0] != value1[0]) {
+ printf("key:%llu value0:%llu != value1:%llu\n",
+ next_key, value0[0], value1[0]);
+ return 0;
+ }
+ }
+ return 1;
+}
+
+static int map_equal(int lru_map, int expected)
+{
+ return map_subset(lru_map, expected) && map_subset(expected, lru_map);
+}
+
+static int sched_next_online(int pid, int next_to_try)
+{
+ cpu_set_t cpuset;
+
+ if (next_to_try == nr_cpus)
+ return -1;
+
+ while (next_to_try < nr_cpus) {
+ CPU_ZERO(&cpuset);
+ CPU_SET(next_to_try++, &cpuset);
+ if (!sched_setaffinity(pid, sizeof(cpuset), &cpuset))
+ break;
+ }
+
+ return next_to_try;
+}
+
+/* Size of the LRU amp is 2
+ * Add key=1 (+1 key)
+ * Add key=2 (+1 key)
+ * Lookup Key=1
+ * Add Key=3
+ * => Key=2 will be removed by LRU
+ * Iterate map. Only found key=1 and key=3
+ */
+static void test_lru_sanity0(int map_type, int map_flags)
+{
+ unsigned long long key, value[nr_cpus];
+ int lru_map_fd, expected_map_fd;
+
+ printf("%s (map_type:%d map_flags:0x%X): ", __func__, map_type,
+ map_flags);
+
+ assert(sched_next_online(0, 0) != -1);
+
+ if (map_flags & BPF_F_NO_COMMON_LRU)
+ lru_map_fd = create_map(map_type, map_flags, 2 * nr_cpus);
+ else
+ lru_map_fd = create_map(map_type, map_flags, 2);
+ assert(lru_map_fd != -1);
+
+ expected_map_fd = create_map(BPF_MAP_TYPE_HASH, 0, 2);
+ assert(expected_map_fd != -1);
+
+ value[0] = 1234;
+
+ /* insert key=1 element */
+
+ key = 1;
+ assert(!bpf_map_update(lru_map_fd, &key, value, BPF_NOEXIST));
+ assert(!bpf_map_update(expected_map_fd, &key, value, BPF_NOEXIST));
+
+ /* BPF_NOEXIST means: add new element if it doesn't exist */
+ assert(bpf_map_update(lru_map_fd, &key, value, BPF_NOEXIST) == -1 &&
+ /* key=1 already exists */
+ errno == EEXIST);
+
+ assert(bpf_map_update(lru_map_fd, &key, value, -1) == -1 &&
+ errno == EINVAL);
+
+ /* insert key=2 element */
+
+ /* check that key=2 is not found */
+ key = 2;
+ assert(bpf_map_lookup(lru_map_fd, &key, value) == -1 &&
+ errno == ENOENT);
+
+ /* BPF_EXIST means: update existing element */
+ assert(bpf_map_update(lru_map_fd, &key, value, BPF_EXIST) == -1 &&
+ /* key=2 is not there */
+ errno == ENOENT);
+
+ assert(!bpf_map_update(lru_map_fd, &key, value, BPF_NOEXIST));
+
+ /* insert key=3 element */
+
+ /* check that key=3 is not found */
+ key = 3;
+ assert(bpf_map_lookup(lru_map_fd, &key, value) == -1 &&
+ errno == ENOENT);
+
+ /* check that key=1 can be found and mark the ref bit to
+ * stop LRU from removing key=1
+ */
+ key = 1;
+ assert(!bpf_map_lookup(lru_map_fd, &key, value));
+ assert(value[0] == 1234);
+
+ key = 3;
+ assert(!bpf_map_update(lru_map_fd, &key, value, BPF_NOEXIST));
+ assert(!bpf_map_update(expected_map_fd, &key, value, BPF_NOEXIST));
+
+ /* key=2 has been removed from the LRU */
+ key = 2;
+ assert(bpf_map_lookup(lru_map_fd, &key, value) == -1);
+
+ assert(map_equal(lru_map_fd, expected_map_fd));
+
+ close(expected_map_fd);
+ close(lru_map_fd);
+
+ printf("Pass\n");
+}
+
+/* Size of the LRU map is 1.5*tgt_free
+ * Insert 1 to tgt_free (+tgt_free keys)
+ * Lookup 1 to tgt_free/2
+ * Insert 1+tgt_free to 2*tgt_free (+tgt_free keys)
+ * => 1+tgt_free/2 to LOCALFREE_TARGET will be removed by LRU
+ */
+static void test_lru_sanity1(int map_type, int map_flags, unsigned int tgt_free)
+{
+ unsigned long long key, end_key, value[nr_cpus];
+ int lru_map_fd, expected_map_fd;
+ unsigned int batch_size;
+ unsigned int map_size;
+
+ if (map_flags & BPF_F_NO_COMMON_LRU)
+ /* Ther percpu lru list (i.e each cpu has its own LRU
+ * list) does not have a local free list. Hence,
+ * it will only free old nodes till there is no free
+ * from the LRU list. Hence, this test does not apply
+ * to BPF_F_NO_COMMON_LRU
+ */
+ return;
+
+ printf("%s (map_type:%d map_flags:0x%X): ", __func__, map_type,
+ map_flags);
+
+ assert(sched_next_online(0, 0) != -1);
+
+ batch_size = tgt_free / 2;
+ assert(batch_size * 2 == tgt_free);
+
+ map_size = tgt_free + batch_size;
+ lru_map_fd = create_map(map_type, map_flags, map_size);
+ assert(lru_map_fd != -1);
+
+ expected_map_fd = create_map(BPF_MAP_TYPE_HASH, 0, map_size);
+ assert(expected_map_fd != -1);
+
+ value[0] = 1234;
+
+ /* Insert 1 to tgt_free (+tgt_free keys) */
+ end_key = 1 + tgt_free;
+ for (key = 1; key < end_key; key++)
+ assert(!bpf_map_update(lru_map_fd, &key, value, BPF_NOEXIST));
+
+ /* Lookup 1 to tgt_free/2 */
+ end_key = 1 + batch_size;
+ for (key = 1; key < end_key; key++) {
+ assert(!bpf_map_lookup(lru_map_fd, &key, value));
+ assert(!bpf_map_update(expected_map_fd, &key, value,
+ BPF_NOEXIST));
+ }
+
+ /* Insert 1+tgt_free to 2*tgt_free
+ * => 1+tgt_free/2 to LOCALFREE_TARGET will be
+ * removed by LRU
+ */
+ key = 1 + tgt_free;
+ end_key = key + tgt_free;
+ for (; key < end_key; key++) {
+ assert(!bpf_map_update(lru_map_fd, &key, value, BPF_NOEXIST));
+ assert(!bpf_map_update(expected_map_fd, &key, value,
+ BPF_NOEXIST));
+ }
+
+ assert(map_equal(lru_map_fd, expected_map_fd));
+
+ close(expected_map_fd);
+ close(lru_map_fd);
+
+ printf("Pass\n");
+}
+
+/* Size of the LRU map 1.5 * tgt_free
+ * Insert 1 to tgt_free (+tgt_free keys)
+ * Update 1 to tgt_free/2
+ * => The original 1 to tgt_free/2 will be removed due to
+ * the LRU shrink process
+ * Re-insert 1 to tgt_free/2 again and do a lookup immeidately
+ * Insert 1+tgt_free to tgt_free*3/2
+ * Insert 1+tgt_free*3/2 to tgt_free*5/2
+ * => Key 1+tgt_free to tgt_free*3/2
+ * will be removed from LRU because it has never
+ * been lookup and ref bit is not set
+ */
+static void test_lru_sanity2(int map_type, int map_flags, unsigned int tgt_free)
+{
+ unsigned long long key, value[nr_cpus];
+ unsigned long long end_key;
+ int lru_map_fd, expected_map_fd;
+ unsigned int batch_size;
+ unsigned int map_size;
+
+ if (map_flags & BPF_F_NO_COMMON_LRU)
+ /* Ther percpu lru list (i.e each cpu has its own LRU
+ * list) does not have a local free list. Hence,
+ * it will only free old nodes till there is no free
+ * from the LRU list. Hence, this test does not apply
+ * to BPF_F_NO_COMMON_LRU
+ */
+ return;
+
+ printf("%s (map_type:%d map_flags:0x%X): ", __func__, map_type,
+ map_flags);
+
+ assert(sched_next_online(0, 0) != -1);
+
+ batch_size = tgt_free / 2;
+ assert(batch_size * 2 == tgt_free);
+
+ map_size = tgt_free + batch_size;
+ if (map_flags & BPF_F_NO_COMMON_LRU)
+ lru_map_fd = create_map(map_type, map_flags,
+ map_size * nr_cpus);
+ else
+ lru_map_fd = create_map(map_type, map_flags, map_size);
+ assert(lru_map_fd != -1);
+
+ expected_map_fd = create_map(BPF_MAP_TYPE_HASH, 0, map_size);
+ assert(expected_map_fd != -1);
+
+ value[0] = 1234;
+
+ /* Insert 1 to tgt_free (+tgt_free keys) */
+ end_key = 1 + tgt_free;
+ for (key = 1; key < end_key; key++)
+ assert(!bpf_map_update(lru_map_fd, &key, value, BPF_NOEXIST));
+
+ /* Any bpf_map_update will require to acquire a new node
+ * from LRU first.
+ *
+ * The local list is running out of free nodes.
+ * It gets from the global LRU list which tries to
+ * shrink the inactive list to get tgt_free
+ * number of free nodes.
+ *
+ * Hence, the oldest key 1 to tgt_free/2
+ * are removed from the LRU list.
+ */
+ key = 1;
+ if (map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH) {
+ assert(!bpf_map_update(lru_map_fd, &key, value, BPF_NOEXIST));
+ assert(!bpf_map_delete(lru_map_fd, &key));
+ } else {
+ assert(bpf_map_update(lru_map_fd, &key, value, BPF_EXIST));
+ }
+
+ /* Re-insert 1 to tgt_free/2 again and do a lookup
+ * immeidately.
+ */
+ end_key = 1 + batch_size;
+ value[0] = 4321;
+ for (key = 1; key < end_key; key++) {
+ assert(bpf_map_lookup(lru_map_fd, &key, value));
+ assert(!bpf_map_update(lru_map_fd, &key, value, BPF_NOEXIST));
+ assert(!bpf_map_lookup(lru_map_fd, &key, value));
+ assert(value[0] == 4321);
+ assert(!bpf_map_update(expected_map_fd, &key, value,
+ BPF_NOEXIST));
+ }
+
+ value[0] = 1234;
+
+ /* Insert 1+tgt_free to tgt_free*3/2 */
+ end_key = 1 + tgt_free + batch_size;
+ for (key = 1 + tgt_free; key < end_key; key++)
+ /* These newly added but not referenced keys will be
+ * gone during the next LRU shrink.
+ */
+ assert(!bpf_map_update(lru_map_fd, &key, value, BPF_NOEXIST));
+
+ /* Insert 1+tgt_free*3/2 to tgt_free*5/2 */
+ end_key = key + tgt_free;
+ for (; key < end_key; key++) {
+ assert(!bpf_map_update(lru_map_fd, &key, value, BPF_NOEXIST));
+ assert(!bpf_map_update(expected_map_fd, &key, value,
+ BPF_NOEXIST));
+ }
+
+ assert(map_equal(lru_map_fd, expected_map_fd));
+
+ close(expected_map_fd);
+ close(lru_map_fd);
+
+ printf("Pass\n");
+}
+
+/* Size of the LRU map is 2*tgt_free
+ * It is to test the active/inactive list rotation
+ * Insert 1 to 2*tgt_free (+2*tgt_free keys)
+ * Lookup key 1 to tgt_free*3/2
+ * Add 1+2*tgt_free to tgt_free*5/2 (+tgt_free/2 keys)
+ * => key 1+tgt_free*3/2 to 2*tgt_free are removed from LRU
+ */
+static void test_lru_sanity3(int map_type, int map_flags, unsigned int tgt_free)
+{
+ unsigned long long key, end_key, value[nr_cpus];
+ int lru_map_fd, expected_map_fd;
+ unsigned int batch_size;
+ unsigned int map_size;
+
+ printf("%s (map_type:%d map_flags:0x%X): ", __func__, map_type,
+ map_flags);
+
+ assert(sched_next_online(0, 0) != -1);
+
+ batch_size = tgt_free / 2;
+ assert(batch_size * 2 == tgt_free);
+
+ map_size = tgt_free * 2;
+ if (map_flags & BPF_F_NO_COMMON_LRU)
+ lru_map_fd = create_map(map_type, map_flags,
+ map_size * nr_cpus);
+ else
+ lru_map_fd = create_map(map_type, map_flags, map_size);
+ assert(lru_map_fd != -1);
+
+ expected_map_fd = create_map(BPF_MAP_TYPE_HASH, 0, map_size);
+ assert(expected_map_fd != -1);
+
+ value[0] = 1234;
+
+ /* Insert 1 to 2*tgt_free (+2*tgt_free keys) */
+ end_key = 1 + (2 * tgt_free);
+ for (key = 1; key < end_key; key++)
+ assert(!bpf_map_update(lru_map_fd, &key, value, BPF_NOEXIST));
+
+ /* Lookup key 1 to tgt_free*3/2 */
+ end_key = tgt_free + batch_size;
+ for (key = 1; key < end_key; key++) {
+ assert(!bpf_map_lookup(lru_map_fd, &key, value));
+ assert(!bpf_map_update(expected_map_fd, &key, value,
+ BPF_NOEXIST));
+ }
+
+ /* Add 1+2*tgt_free to tgt_free*5/2
+ * (+tgt_free/2 keys)
+ */
+ key = 2 * tgt_free + 1;
+ end_key = key + batch_size;
+ for (; key < end_key; key++) {
+ assert(!bpf_map_update(lru_map_fd, &key, value, BPF_NOEXIST));
+ assert(!bpf_map_update(expected_map_fd, &key, value,
+ BPF_NOEXIST));
+ }
+
+ assert(map_equal(lru_map_fd, expected_map_fd));
+
+ close(expected_map_fd);
+ close(lru_map_fd);
+
+ printf("Pass\n");
+}
+
+/* Test deletion */
+static void test_lru_sanity4(int map_type, int map_flags, unsigned int tgt_free)
+{
+ int lru_map_fd, expected_map_fd;
+ unsigned long long key, value[nr_cpus];
+ unsigned long long end_key;
+
+ printf("%s (map_type:%d map_flags:0x%X): ", __func__, map_type,
+ map_flags);
+
+ assert(sched_next_online(0, 0) != -1);
+
+ if (map_flags & BPF_F_NO_COMMON_LRU)
+ lru_map_fd = create_map(map_type, map_flags,
+ 3 * tgt_free * nr_cpus);
+ else
+ lru_map_fd = create_map(map_type, map_flags, 3 * tgt_free);
+ assert(lru_map_fd != -1);
+
+ expected_map_fd = create_map(BPF_MAP_TYPE_HASH, 0,
+ 3 * tgt_free);
+ assert(expected_map_fd != -1);
+
+ value[0] = 1234;
+
+ for (key = 1; key <= 2 * tgt_free; key++)
+ assert(!bpf_map_update(lru_map_fd, &key, value, BPF_NOEXIST));
+
+ key = 1;
+ assert(bpf_map_update(lru_map_fd, &key, value, BPF_NOEXIST));
+
+ for (key = 1; key <= tgt_free; key++) {
+ assert(!bpf_map_lookup(lru_map_fd, &key, value));
+ assert(!bpf_map_update(expected_map_fd, &key, value,
+ BPF_NOEXIST));
+ }
+
+ for (; key <= 2 * tgt_free; key++) {
+ assert(!bpf_map_delete(lru_map_fd, &key));
+ assert(bpf_map_delete(lru_map_fd, &key));
+ }
+
+ end_key = key + 2 * tgt_free;
+ for (; key < end_key; key++) {
+ assert(!bpf_map_update(lru_map_fd, &key, value, BPF_NOEXIST));
+ assert(!bpf_map_update(expected_map_fd, &key, value,
+ BPF_NOEXIST));
+ }
+
+ assert(map_equal(lru_map_fd, expected_map_fd));
+
+ close(expected_map_fd);
+ close(lru_map_fd);
+
+ printf("Pass\n");
+}
+
+static void do_test_lru_sanity5(unsigned long long last_key, int map_fd)
+{
+ unsigned long long key, value[nr_cpus];
+
+ /* Ensure the last key inserted by previous CPU can be found */
+ assert(!bpf_map_lookup(map_fd, &last_key, value));
+
+ value[0] = 1234;
+
+ key = last_key + 1;
+ assert(!bpf_map_update(map_fd, &key, value, BPF_NOEXIST));
+ assert(!bpf_map_lookup(map_fd, &key, value));
+
+ /* Cannot find the last key because it was removed by LRU */
+ assert(bpf_map_lookup(map_fd, &last_key, value));
+}
+
+/* Test map with only one element */
+static void test_lru_sanity5(int map_type, int map_flags)
+{
+ unsigned long long key, value[nr_cpus];
+ int next_sched_cpu = 0;
+ int map_fd;
+ int i;
+
+ if (map_flags & BPF_F_NO_COMMON_LRU)
+ return;
+
+ printf("%s (map_type:%d map_flags:0x%X): ", __func__, map_type,
+ map_flags);
+
+ map_fd = create_map(map_type, map_flags, 1);
+ assert(map_fd != -1);
+
+ value[0] = 1234;
+ key = 0;
+ assert(!bpf_map_update(map_fd, &key, value, BPF_NOEXIST));
+
+ for (i = 0; i < nr_cpus; i++) {
+ pid_t pid;
+
+ pid = fork();
+ if (pid == 0) {
+ next_sched_cpu = sched_next_online(0, next_sched_cpu);
+ if (next_sched_cpu != -1)
+ do_test_lru_sanity5(key, map_fd);
+ exit(0);
+ } else if (pid == -1) {
+ printf("couldn't spawn #%d process\n", i);
+ exit(1);
+ } else {
+ int status;
+
+ /* It is mostly redundant and just allow the parent
+ * process to update next_shced_cpu for the next child
+ * process
+ */
+ next_sched_cpu = sched_next_online(pid, next_sched_cpu);
+
+ assert(waitpid(pid, &status, 0) == pid);
+ assert(status == 0);
+ key++;
+ }
+ }
+
+ close(map_fd);
+
+ printf("Pass\n");
+}
+
+int main(int argc, char **argv)
+{
+ struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY};
+ int map_types[] = {BPF_MAP_TYPE_LRU_HASH,
+ BPF_MAP_TYPE_LRU_PERCPU_HASH};
+ int map_flags[] = {0, BPF_F_NO_COMMON_LRU};
+ int t, f;
+
+ setbuf(stdout, NULL);
+
+ assert(!setrlimit(RLIMIT_MEMLOCK, &r));
+
+ nr_cpus = sysconf(_SC_NPROCESSORS_CONF);
+ assert(nr_cpus != -1);
+ printf("nr_cpus:%d\n\n", nr_cpus);
+
+ for (f = 0; f < sizeof(map_flags) / sizeof(*map_flags); f++) {
+ unsigned int tgt_free = (map_flags[f] & BPF_F_NO_COMMON_LRU) ?
+ PERCPU_FREE_TARGET : LOCAL_FREE_TARGET;
+
+ for (t = 0; t < sizeof(map_types) / sizeof(*map_types); t++) {
+ test_lru_sanity0(map_types[t], map_flags[f]);
+ test_lru_sanity1(map_types[t], map_flags[f], tgt_free);
+ test_lru_sanity2(map_types[t], map_flags[f], tgt_free);
+ test_lru_sanity3(map_types[t], map_flags[f], tgt_free);
+ test_lru_sanity4(map_types[t], map_flags[f], tgt_free);
+ test_lru_sanity5(map_types[t], map_flags[f]);
+
+ printf("\n");
+ }
+ }
+
+ return 0;
+}
projects / GitHub / MotorolaMobilityLLC / kernel-slsi.git / commitdiff