mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-06 02:56:44 +07:00
6da2ec5605
The kmalloc() function has a 2-factor argument form, kmalloc_array(). This patch replaces cases of: kmalloc(a * b, gfp) with: kmalloc_array(a * b, gfp) as well as handling cases of: kmalloc(a * b * c, gfp) with: kmalloc(array3_size(a, b, c), gfp) as it's slightly less ugly than: kmalloc_array(array_size(a, b), c, gfp) This does, however, attempt to ignore constant size factors like: kmalloc(4 * 1024, gfp) though any constants defined via macros get caught up in the conversion. Any factors with a sizeof() of "unsigned char", "char", and "u8" were dropped, since they're redundant. The tools/ directory was manually excluded, since it has its own implementation of kmalloc(). The Coccinelle script used for this was: // Fix redundant parens around sizeof(). @@ type TYPE; expression THING, E; @@ ( kmalloc( - (sizeof(TYPE)) * E + sizeof(TYPE) * E , ...) | kmalloc( - (sizeof(THING)) * E + sizeof(THING) * E , ...) ) // Drop single-byte sizes and redundant parens. @@ expression COUNT; typedef u8; typedef __u8; @@ ( kmalloc( - sizeof(u8) * (COUNT) + COUNT , ...) | kmalloc( - sizeof(__u8) * (COUNT) + COUNT , ...) | kmalloc( - sizeof(char) * (COUNT) + COUNT , ...) | kmalloc( - sizeof(unsigned char) * (COUNT) + COUNT , ...) | kmalloc( - sizeof(u8) * COUNT + COUNT , ...) | kmalloc( - sizeof(__u8) * COUNT + COUNT , ...) | kmalloc( - sizeof(char) * COUNT + COUNT , ...) | kmalloc( - sizeof(unsigned char) * COUNT + COUNT , ...) ) // 2-factor product with sizeof(type/expression) and identifier or constant. @@ type TYPE; expression THING; identifier COUNT_ID; constant COUNT_CONST; @@ ( - kmalloc + kmalloc_array ( - sizeof(TYPE) * (COUNT_ID) + COUNT_ID, sizeof(TYPE) , ...) | - kmalloc + kmalloc_array ( - sizeof(TYPE) * COUNT_ID + COUNT_ID, sizeof(TYPE) , ...) | - kmalloc + kmalloc_array ( - sizeof(TYPE) * (COUNT_CONST) + COUNT_CONST, sizeof(TYPE) , ...) | - kmalloc + kmalloc_array ( - sizeof(TYPE) * COUNT_CONST + COUNT_CONST, sizeof(TYPE) , ...) | - kmalloc + kmalloc_array ( - sizeof(THING) * (COUNT_ID) + COUNT_ID, sizeof(THING) , ...) | - kmalloc + kmalloc_array ( - sizeof(THING) * COUNT_ID + COUNT_ID, sizeof(THING) , ...) | - kmalloc + kmalloc_array ( - sizeof(THING) * (COUNT_CONST) + COUNT_CONST, sizeof(THING) , ...) | - kmalloc + kmalloc_array ( - sizeof(THING) * COUNT_CONST + COUNT_CONST, sizeof(THING) , ...) ) // 2-factor product, only identifiers. @@ identifier SIZE, COUNT; @@ - kmalloc + kmalloc_array ( - SIZE * COUNT + COUNT, SIZE , ...) // 3-factor product with 1 sizeof(type) or sizeof(expression), with // redundant parens removed. @@ expression THING; identifier STRIDE, COUNT; type TYPE; @@ ( kmalloc( - sizeof(TYPE) * (COUNT) * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kmalloc( - sizeof(TYPE) * (COUNT) * STRIDE + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kmalloc( - sizeof(TYPE) * COUNT * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kmalloc( - sizeof(TYPE) * COUNT * STRIDE + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kmalloc( - sizeof(THING) * (COUNT) * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kmalloc( - sizeof(THING) * (COUNT) * STRIDE + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kmalloc( - sizeof(THING) * COUNT * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kmalloc( - sizeof(THING) * COUNT * STRIDE + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) ) // 3-factor product with 2 sizeof(variable), with redundant parens removed. @@ expression THING1, THING2; identifier COUNT; type TYPE1, TYPE2; @@ ( kmalloc( - sizeof(TYPE1) * sizeof(TYPE2) * COUNT + array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2)) , ...) | kmalloc( - sizeof(TYPE1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2)) , ...) | kmalloc( - sizeof(THING1) * sizeof(THING2) * COUNT + array3_size(COUNT, sizeof(THING1), sizeof(THING2)) , ...) | kmalloc( - sizeof(THING1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(THING1), sizeof(THING2)) , ...) | kmalloc( - sizeof(TYPE1) * sizeof(THING2) * COUNT + array3_size(COUNT, sizeof(TYPE1), sizeof(THING2)) , ...) | kmalloc( - sizeof(TYPE1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(TYPE1), sizeof(THING2)) , ...) ) // 3-factor product, only identifiers, with redundant parens removed. @@ identifier STRIDE, SIZE, COUNT; @@ ( kmalloc( - (COUNT) * STRIDE * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kmalloc( - COUNT * (STRIDE) * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kmalloc( - COUNT * STRIDE * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kmalloc( - (COUNT) * (STRIDE) * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kmalloc( - COUNT * (STRIDE) * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kmalloc( - (COUNT) * STRIDE * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kmalloc( - (COUNT) * (STRIDE) * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kmalloc( - COUNT * STRIDE * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) ) // Any remaining multi-factor products, first at least 3-factor products, // when they're not all constants... @@ expression E1, E2, E3; constant C1, C2, C3; @@ ( kmalloc(C1 * C2 * C3, ...) | kmalloc( - (E1) * E2 * E3 + array3_size(E1, E2, E3) , ...) | kmalloc( - (E1) * (E2) * E3 + array3_size(E1, E2, E3) , ...) | kmalloc( - (E1) * (E2) * (E3) + array3_size(E1, E2, E3) , ...) | kmalloc( - E1 * E2 * E3 + array3_size(E1, E2, E3) , ...) ) // And then all remaining 2 factors products when they're not all constants, // keeping sizeof() as the second factor argument. @@ expression THING, E1, E2; type TYPE; constant C1, C2, C3; @@ ( kmalloc(sizeof(THING) * C2, ...) | kmalloc(sizeof(TYPE) * C2, ...) | kmalloc(C1 * C2 * C3, ...) | kmalloc(C1 * C2, ...) | - kmalloc + kmalloc_array ( - sizeof(TYPE) * (E2) + E2, sizeof(TYPE) , ...) | - kmalloc + kmalloc_array ( - sizeof(TYPE) * E2 + E2, sizeof(TYPE) , ...) | - kmalloc + kmalloc_array ( - sizeof(THING) * (E2) + E2, sizeof(THING) , ...) | - kmalloc + kmalloc_array ( - sizeof(THING) * E2 + E2, sizeof(THING) , ...) | - kmalloc + kmalloc_array ( - (E1) * E2 + E1, E2 , ...) | - kmalloc + kmalloc_array ( - (E1) * (E2) + E1, E2 , ...) | - kmalloc + kmalloc_array ( - E1 * E2 + E1, E2 , ...) ) Signed-off-by: Kees Cook <keescook@chromium.org>
411 lines
9.4 KiB
C
411 lines
9.4 KiB
C
#include <linux/module.h>
|
|
#include <linux/moduleparam.h>
|
|
#include <linux/rbtree_augmented.h>
|
|
#include <linux/random.h>
|
|
#include <linux/slab.h>
|
|
#include <asm/timex.h>
|
|
|
|
#define __param(type, name, init, msg) \
|
|
static type name = init; \
|
|
module_param(name, type, 0444); \
|
|
MODULE_PARM_DESC(name, msg);
|
|
|
|
__param(int, nnodes, 100, "Number of nodes in the rb-tree");
|
|
__param(int, perf_loops, 1000, "Number of iterations modifying the rb-tree");
|
|
__param(int, check_loops, 100, "Number of iterations modifying and verifying the rb-tree");
|
|
|
|
struct test_node {
|
|
u32 key;
|
|
struct rb_node rb;
|
|
|
|
/* following fields used for testing augmented rbtree functionality */
|
|
u32 val;
|
|
u32 augmented;
|
|
};
|
|
|
|
static struct rb_root_cached root = RB_ROOT_CACHED;
|
|
static struct test_node *nodes = NULL;
|
|
|
|
static struct rnd_state rnd;
|
|
|
|
static void insert(struct test_node *node, struct rb_root_cached *root)
|
|
{
|
|
struct rb_node **new = &root->rb_root.rb_node, *parent = NULL;
|
|
u32 key = node->key;
|
|
|
|
while (*new) {
|
|
parent = *new;
|
|
if (key < rb_entry(parent, struct test_node, rb)->key)
|
|
new = &parent->rb_left;
|
|
else
|
|
new = &parent->rb_right;
|
|
}
|
|
|
|
rb_link_node(&node->rb, parent, new);
|
|
rb_insert_color(&node->rb, &root->rb_root);
|
|
}
|
|
|
|
static void insert_cached(struct test_node *node, struct rb_root_cached *root)
|
|
{
|
|
struct rb_node **new = &root->rb_root.rb_node, *parent = NULL;
|
|
u32 key = node->key;
|
|
bool leftmost = true;
|
|
|
|
while (*new) {
|
|
parent = *new;
|
|
if (key < rb_entry(parent, struct test_node, rb)->key)
|
|
new = &parent->rb_left;
|
|
else {
|
|
new = &parent->rb_right;
|
|
leftmost = false;
|
|
}
|
|
}
|
|
|
|
rb_link_node(&node->rb, parent, new);
|
|
rb_insert_color_cached(&node->rb, root, leftmost);
|
|
}
|
|
|
|
static inline void erase(struct test_node *node, struct rb_root_cached *root)
|
|
{
|
|
rb_erase(&node->rb, &root->rb_root);
|
|
}
|
|
|
|
static inline void erase_cached(struct test_node *node, struct rb_root_cached *root)
|
|
{
|
|
rb_erase_cached(&node->rb, root);
|
|
}
|
|
|
|
|
|
static inline u32 augment_recompute(struct test_node *node)
|
|
{
|
|
u32 max = node->val, child_augmented;
|
|
if (node->rb.rb_left) {
|
|
child_augmented = rb_entry(node->rb.rb_left, struct test_node,
|
|
rb)->augmented;
|
|
if (max < child_augmented)
|
|
max = child_augmented;
|
|
}
|
|
if (node->rb.rb_right) {
|
|
child_augmented = rb_entry(node->rb.rb_right, struct test_node,
|
|
rb)->augmented;
|
|
if (max < child_augmented)
|
|
max = child_augmented;
|
|
}
|
|
return max;
|
|
}
|
|
|
|
RB_DECLARE_CALLBACKS(static, augment_callbacks, struct test_node, rb,
|
|
u32, augmented, augment_recompute)
|
|
|
|
static void insert_augmented(struct test_node *node,
|
|
struct rb_root_cached *root)
|
|
{
|
|
struct rb_node **new = &root->rb_root.rb_node, *rb_parent = NULL;
|
|
u32 key = node->key;
|
|
u32 val = node->val;
|
|
struct test_node *parent;
|
|
|
|
while (*new) {
|
|
rb_parent = *new;
|
|
parent = rb_entry(rb_parent, struct test_node, rb);
|
|
if (parent->augmented < val)
|
|
parent->augmented = val;
|
|
if (key < parent->key)
|
|
new = &parent->rb.rb_left;
|
|
else
|
|
new = &parent->rb.rb_right;
|
|
}
|
|
|
|
node->augmented = val;
|
|
rb_link_node(&node->rb, rb_parent, new);
|
|
rb_insert_augmented(&node->rb, &root->rb_root, &augment_callbacks);
|
|
}
|
|
|
|
static void insert_augmented_cached(struct test_node *node,
|
|
struct rb_root_cached *root)
|
|
{
|
|
struct rb_node **new = &root->rb_root.rb_node, *rb_parent = NULL;
|
|
u32 key = node->key;
|
|
u32 val = node->val;
|
|
struct test_node *parent;
|
|
bool leftmost = true;
|
|
|
|
while (*new) {
|
|
rb_parent = *new;
|
|
parent = rb_entry(rb_parent, struct test_node, rb);
|
|
if (parent->augmented < val)
|
|
parent->augmented = val;
|
|
if (key < parent->key)
|
|
new = &parent->rb.rb_left;
|
|
else {
|
|
new = &parent->rb.rb_right;
|
|
leftmost = false;
|
|
}
|
|
}
|
|
|
|
node->augmented = val;
|
|
rb_link_node(&node->rb, rb_parent, new);
|
|
rb_insert_augmented_cached(&node->rb, root,
|
|
leftmost, &augment_callbacks);
|
|
}
|
|
|
|
|
|
static void erase_augmented(struct test_node *node, struct rb_root_cached *root)
|
|
{
|
|
rb_erase_augmented(&node->rb, &root->rb_root, &augment_callbacks);
|
|
}
|
|
|
|
static void erase_augmented_cached(struct test_node *node,
|
|
struct rb_root_cached *root)
|
|
{
|
|
rb_erase_augmented_cached(&node->rb, root, &augment_callbacks);
|
|
}
|
|
|
|
static void init(void)
|
|
{
|
|
int i;
|
|
for (i = 0; i < nnodes; i++) {
|
|
nodes[i].key = prandom_u32_state(&rnd);
|
|
nodes[i].val = prandom_u32_state(&rnd);
|
|
}
|
|
}
|
|
|
|
static bool is_red(struct rb_node *rb)
|
|
{
|
|
return !(rb->__rb_parent_color & 1);
|
|
}
|
|
|
|
static int black_path_count(struct rb_node *rb)
|
|
{
|
|
int count;
|
|
for (count = 0; rb; rb = rb_parent(rb))
|
|
count += !is_red(rb);
|
|
return count;
|
|
}
|
|
|
|
static void check_postorder_foreach(int nr_nodes)
|
|
{
|
|
struct test_node *cur, *n;
|
|
int count = 0;
|
|
rbtree_postorder_for_each_entry_safe(cur, n, &root.rb_root, rb)
|
|
count++;
|
|
|
|
WARN_ON_ONCE(count != nr_nodes);
|
|
}
|
|
|
|
static void check_postorder(int nr_nodes)
|
|
{
|
|
struct rb_node *rb;
|
|
int count = 0;
|
|
for (rb = rb_first_postorder(&root.rb_root); rb; rb = rb_next_postorder(rb))
|
|
count++;
|
|
|
|
WARN_ON_ONCE(count != nr_nodes);
|
|
}
|
|
|
|
static void check(int nr_nodes)
|
|
{
|
|
struct rb_node *rb;
|
|
int count = 0, blacks = 0;
|
|
u32 prev_key = 0;
|
|
|
|
for (rb = rb_first(&root.rb_root); rb; rb = rb_next(rb)) {
|
|
struct test_node *node = rb_entry(rb, struct test_node, rb);
|
|
WARN_ON_ONCE(node->key < prev_key);
|
|
WARN_ON_ONCE(is_red(rb) &&
|
|
(!rb_parent(rb) || is_red(rb_parent(rb))));
|
|
if (!count)
|
|
blacks = black_path_count(rb);
|
|
else
|
|
WARN_ON_ONCE((!rb->rb_left || !rb->rb_right) &&
|
|
blacks != black_path_count(rb));
|
|
prev_key = node->key;
|
|
count++;
|
|
}
|
|
|
|
WARN_ON_ONCE(count != nr_nodes);
|
|
WARN_ON_ONCE(count < (1 << black_path_count(rb_last(&root.rb_root))) - 1);
|
|
|
|
check_postorder(nr_nodes);
|
|
check_postorder_foreach(nr_nodes);
|
|
}
|
|
|
|
static void check_augmented(int nr_nodes)
|
|
{
|
|
struct rb_node *rb;
|
|
|
|
check(nr_nodes);
|
|
for (rb = rb_first(&root.rb_root); rb; rb = rb_next(rb)) {
|
|
struct test_node *node = rb_entry(rb, struct test_node, rb);
|
|
WARN_ON_ONCE(node->augmented != augment_recompute(node));
|
|
}
|
|
}
|
|
|
|
static int __init rbtree_test_init(void)
|
|
{
|
|
int i, j;
|
|
cycles_t time1, time2, time;
|
|
struct rb_node *node;
|
|
|
|
nodes = kmalloc_array(nnodes, sizeof(*nodes), GFP_KERNEL);
|
|
if (!nodes)
|
|
return -ENOMEM;
|
|
|
|
printk(KERN_ALERT "rbtree testing");
|
|
|
|
prandom_seed_state(&rnd, 3141592653589793238ULL);
|
|
init();
|
|
|
|
time1 = get_cycles();
|
|
|
|
for (i = 0; i < perf_loops; i++) {
|
|
for (j = 0; j < nnodes; j++)
|
|
insert(nodes + j, &root);
|
|
for (j = 0; j < nnodes; j++)
|
|
erase(nodes + j, &root);
|
|
}
|
|
|
|
time2 = get_cycles();
|
|
time = time2 - time1;
|
|
|
|
time = div_u64(time, perf_loops);
|
|
printk(" -> test 1 (latency of nnodes insert+delete): %llu cycles\n",
|
|
(unsigned long long)time);
|
|
|
|
time1 = get_cycles();
|
|
|
|
for (i = 0; i < perf_loops; i++) {
|
|
for (j = 0; j < nnodes; j++)
|
|
insert_cached(nodes + j, &root);
|
|
for (j = 0; j < nnodes; j++)
|
|
erase_cached(nodes + j, &root);
|
|
}
|
|
|
|
time2 = get_cycles();
|
|
time = time2 - time1;
|
|
|
|
time = div_u64(time, perf_loops);
|
|
printk(" -> test 2 (latency of nnodes cached insert+delete): %llu cycles\n",
|
|
(unsigned long long)time);
|
|
|
|
for (i = 0; i < nnodes; i++)
|
|
insert(nodes + i, &root);
|
|
|
|
time1 = get_cycles();
|
|
|
|
for (i = 0; i < perf_loops; i++) {
|
|
for (node = rb_first(&root.rb_root); node; node = rb_next(node))
|
|
;
|
|
}
|
|
|
|
time2 = get_cycles();
|
|
time = time2 - time1;
|
|
|
|
time = div_u64(time, perf_loops);
|
|
printk(" -> test 3 (latency of inorder traversal): %llu cycles\n",
|
|
(unsigned long long)time);
|
|
|
|
time1 = get_cycles();
|
|
|
|
for (i = 0; i < perf_loops; i++)
|
|
node = rb_first(&root.rb_root);
|
|
|
|
time2 = get_cycles();
|
|
time = time2 - time1;
|
|
|
|
time = div_u64(time, perf_loops);
|
|
printk(" -> test 4 (latency to fetch first node)\n");
|
|
printk(" non-cached: %llu cycles\n", (unsigned long long)time);
|
|
|
|
time1 = get_cycles();
|
|
|
|
for (i = 0; i < perf_loops; i++)
|
|
node = rb_first_cached(&root);
|
|
|
|
time2 = get_cycles();
|
|
time = time2 - time1;
|
|
|
|
time = div_u64(time, perf_loops);
|
|
printk(" cached: %llu cycles\n", (unsigned long long)time);
|
|
|
|
for (i = 0; i < nnodes; i++)
|
|
erase(nodes + i, &root);
|
|
|
|
/* run checks */
|
|
for (i = 0; i < check_loops; i++) {
|
|
init();
|
|
for (j = 0; j < nnodes; j++) {
|
|
check(j);
|
|
insert(nodes + j, &root);
|
|
}
|
|
for (j = 0; j < nnodes; j++) {
|
|
check(nnodes - j);
|
|
erase(nodes + j, &root);
|
|
}
|
|
check(0);
|
|
}
|
|
|
|
printk(KERN_ALERT "augmented rbtree testing");
|
|
|
|
init();
|
|
|
|
time1 = get_cycles();
|
|
|
|
for (i = 0; i < perf_loops; i++) {
|
|
for (j = 0; j < nnodes; j++)
|
|
insert_augmented(nodes + j, &root);
|
|
for (j = 0; j < nnodes; j++)
|
|
erase_augmented(nodes + j, &root);
|
|
}
|
|
|
|
time2 = get_cycles();
|
|
time = time2 - time1;
|
|
|
|
time = div_u64(time, perf_loops);
|
|
printk(" -> test 1 (latency of nnodes insert+delete): %llu cycles\n", (unsigned long long)time);
|
|
|
|
time1 = get_cycles();
|
|
|
|
for (i = 0; i < perf_loops; i++) {
|
|
for (j = 0; j < nnodes; j++)
|
|
insert_augmented_cached(nodes + j, &root);
|
|
for (j = 0; j < nnodes; j++)
|
|
erase_augmented_cached(nodes + j, &root);
|
|
}
|
|
|
|
time2 = get_cycles();
|
|
time = time2 - time1;
|
|
|
|
time = div_u64(time, perf_loops);
|
|
printk(" -> test 2 (latency of nnodes cached insert+delete): %llu cycles\n", (unsigned long long)time);
|
|
|
|
for (i = 0; i < check_loops; i++) {
|
|
init();
|
|
for (j = 0; j < nnodes; j++) {
|
|
check_augmented(j);
|
|
insert_augmented(nodes + j, &root);
|
|
}
|
|
for (j = 0; j < nnodes; j++) {
|
|
check_augmented(nnodes - j);
|
|
erase_augmented(nodes + j, &root);
|
|
}
|
|
check_augmented(0);
|
|
}
|
|
|
|
kfree(nodes);
|
|
|
|
return -EAGAIN; /* Fail will directly unload the module */
|
|
}
|
|
|
|
static void __exit rbtree_test_exit(void)
|
|
{
|
|
printk(KERN_ALERT "test exit\n");
|
|
}
|
|
|
|
module_init(rbtree_test_init)
|
|
module_exit(rbtree_test_exit)
|
|
|
|
MODULE_LICENSE("GPL");
|
|
MODULE_AUTHOR("Michel Lespinasse");
|
|
MODULE_DESCRIPTION("Red Black Tree test");
|