summaryrefslogtreecommitdiffstats
path: root/lib
diff options
context:
space:
mode:
Diffstat (limited to 'lib')
-rw-r--r--lib/Kconfig.debug31
-rw-r--r--lib/Kconfig.kasan32
-rw-r--r--lib/Makefile1
-rw-r--r--lib/assoc_array.c8
-rw-r--r--lib/bsearch.c2
-rw-r--r--lib/cpumask.c3
-rw-r--r--lib/crc32.c4
-rw-r--r--lib/locking-selftest.c2
-rw-r--r--lib/objagg.c583
-rw-r--r--lib/refcount.c18
-rw-r--r--lib/rhashtable.c2
-rw-r--r--lib/smp_processor_id.c7
-rw-r--r--lib/test_bpf.c2
-rw-r--r--lib/test_kasan.c24
-rw-r--r--lib/test_objagg.c199
-rw-r--r--lib/test_rhashtable.c13
-rw-r--r--lib/test_vmalloc.c551
17 files changed, 1386 insertions, 96 deletions
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 42479a9a4769..b19cc9c36475 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -222,7 +222,6 @@ config ENABLE_MUST_CHECK
config FRAME_WARN
int "Warn for stack frames larger than (needs gcc 4.4)"
range 0 8192
- default 3072 if KASAN_EXTRA
default 2048 if GCC_PLUGIN_LATENT_ENTROPY
default 1280 if (!64BIT && PARISC)
default 1024 if (!64BIT && !PARISC)
@@ -266,23 +265,6 @@ config UNUSED_SYMBOLS
you really need it, and what the merge plan to the mainline kernel for
your module is.
-config PAGE_OWNER
- bool "Track page owner"
- depends on DEBUG_KERNEL && STACKTRACE_SUPPORT
- select DEBUG_FS
- select STACKTRACE
- select STACKDEPOT
- select PAGE_EXTENSION
- help
- This keeps track of what call chain is the owner of a page, may
- help to find bare alloc_page(s) leaks. Even if you include this
- feature on your build, it is disabled in default. You should pass
- "page_owner=on" to boot parameter in order to enable it. Eats
- a fair amount of memory if enabled. See tools/vm/page_owner_sort.c
- for user-space helper.
-
- If unsure, say N.
-
config DEBUG_FS
bool "Debug Filesystem"
help
@@ -1875,6 +1857,19 @@ config TEST_LKM
If unsure, say N.
+config TEST_VMALLOC
+ tristate "Test module for stress/performance analysis of vmalloc allocator"
+ default n
+ depends on MMU
+ depends on m
+ help
+ This builds the "test_vmalloc" module that should be used for
+ stress and performance analysis. So, any new change for vmalloc
+ subsystem can be evaluated from performance and stability point
+ of view.
+
+ If unsure, say N.
+
config TEST_USER_COPY
tristate "Test user/kernel boundary protections"
depends on m
diff --git a/lib/Kconfig.kasan b/lib/Kconfig.kasan
index d8c474b6691e..9950b660e62d 100644
--- a/lib/Kconfig.kasan
+++ b/lib/Kconfig.kasan
@@ -78,16 +78,6 @@ config KASAN_SW_TAGS
endchoice
-config KASAN_EXTRA
- bool "KASAN: extra checks"
- depends on KASAN_GENERIC && DEBUG_KERNEL && !COMPILE_TEST
- help
- This enables further checks in generic KASAN, for now it only
- includes the address-use-after-scope check that can lead to
- excessive kernel stack usage, frame size warnings and longer
- compile time.
- See https://gcc.gnu.org/bugzilla/show_bug.cgi?id=81715
-
choice
prompt "Instrumentation type"
depends on KASAN
@@ -113,6 +103,28 @@ config KASAN_INLINE
endchoice
+config KASAN_STACK_ENABLE
+ bool "Enable stack instrumentation (unsafe)" if CC_IS_CLANG && !COMPILE_TEST
+ default !(CLANG_VERSION < 90000)
+ depends on KASAN
+ help
+ The LLVM stack address sanitizer has a know problem that
+ causes excessive stack usage in a lot of functions, see
+ https://bugs.llvm.org/show_bug.cgi?id=38809
+ Disabling asan-stack makes it safe to run kernels build
+ with clang-8 with KASAN enabled, though it loses some of
+ the functionality.
+ This feature is always disabled when compile-testing with clang-8
+ or earlier to avoid cluttering the output in stack overflow
+ warnings, but clang-8 users can still enable it for builds without
+ CONFIG_COMPILE_TEST. On gcc and later clang versions it is
+ assumed to always be safe to use and enabled by default.
+
+config KASAN_STACK
+ int
+ default 1 if KASAN_STACK_ENABLE || CC_IS_GCC
+ default 0
+
config KASAN_S390_4_LEVEL_PAGING
bool "KASan: use 4-level paging"
depends on KASAN && S390
diff --git a/lib/Makefile b/lib/Makefile
index e1b59da71418..cbfacd55aeca 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -60,6 +60,7 @@ UBSAN_SANITIZE_test_ubsan.o := y
obj-$(CONFIG_TEST_KSTRTOX) += test-kstrtox.o
obj-$(CONFIG_TEST_LIST_SORT) += test_list_sort.o
obj-$(CONFIG_TEST_LKM) += test_module.o
+obj-$(CONFIG_TEST_VMALLOC) += test_vmalloc.o
obj-$(CONFIG_TEST_OVERFLOW) += test_overflow.o
obj-$(CONFIG_TEST_RHASHTABLE) += test_rhashtable.o
obj-$(CONFIG_TEST_SORT) += test_sort.o
diff --git a/lib/assoc_array.c b/lib/assoc_array.c
index c6659cb37033..59875eb278ea 100644
--- a/lib/assoc_array.c
+++ b/lib/assoc_array.c
@@ -768,9 +768,11 @@ all_leaves_cluster_together:
new_s0->index_key[i] =
ops->get_key_chunk(index_key, i * ASSOC_ARRAY_KEY_CHUNK_SIZE);
- blank = ULONG_MAX << (level & ASSOC_ARRAY_KEY_CHUNK_MASK);
- pr_devel("blank off [%zu] %d: %lx\n", keylen - 1, level, blank);
- new_s0->index_key[keylen - 1] &= ~blank;
+ if (level & ASSOC_ARRAY_KEY_CHUNK_MASK) {
+ blank = ULONG_MAX << (level & ASSOC_ARRAY_KEY_CHUNK_MASK);
+ pr_devel("blank off [%zu] %d: %lx\n", keylen - 1, level, blank);
+ new_s0->index_key[keylen - 1] &= ~blank;
+ }
/* This now reduces to a node splitting exercise for which we'll need
* to regenerate the disparity table.
diff --git a/lib/bsearch.c b/lib/bsearch.c
index 18b445b010c3..82512fe7b33c 100644
--- a/lib/bsearch.c
+++ b/lib/bsearch.c
@@ -11,6 +11,7 @@
#include <linux/export.h>
#include <linux/bsearch.h>
+#include <linux/kprobes.h>
/*
* bsearch - binary search an array of elements
@@ -53,3 +54,4 @@ void *bsearch(const void *key, const void *base, size_t num, size_t size,
return NULL;
}
EXPORT_SYMBOL(bsearch);
+NOKPROBE_SYMBOL(bsearch);
diff --git a/lib/cpumask.c b/lib/cpumask.c
index 8d666ab84b5c..087a3e9a0202 100644
--- a/lib/cpumask.c
+++ b/lib/cpumask.c
@@ -5,6 +5,7 @@
#include <linux/cpumask.h>
#include <linux/export.h>
#include <linux/memblock.h>
+#include <linux/numa.h>
/**
* cpumask_next - get the next cpu in a cpumask
@@ -206,7 +207,7 @@ unsigned int cpumask_local_spread(unsigned int i, int node)
/* Wrap: we always want a cpu. */
i %= num_online_cpus();
- if (node == -1) {
+ if (node == NUMA_NO_NODE) {
for_each_cpu(cpu, cpu_online_mask)
if (i-- == 0)
return cpu;
diff --git a/lib/crc32.c b/lib/crc32.c
index 45b1d67a1767..4a20455d1f61 100644
--- a/lib/crc32.c
+++ b/lib/crc32.c
@@ -206,8 +206,8 @@ u32 __pure __weak __crc32c_le(u32 crc, unsigned char const *p, size_t len)
EXPORT_SYMBOL(crc32_le);
EXPORT_SYMBOL(__crc32c_le);
-u32 crc32_le_base(u32, unsigned char const *, size_t) __alias(crc32_le);
-u32 __crc32c_le_base(u32, unsigned char const *, size_t) __alias(__crc32c_le);
+u32 __pure crc32_le_base(u32, unsigned char const *, size_t) __alias(crc32_le);
+u32 __pure __crc32c_le_base(u32, unsigned char const *, size_t) __alias(__crc32c_le);
/*
* This multiplies the polynomials x and y modulo the given modulus.
diff --git a/lib/locking-selftest.c b/lib/locking-selftest.c
index 1e1bbf171eca..a1705545e6ac 100644
--- a/lib/locking-selftest.c
+++ b/lib/locking-selftest.c
@@ -1989,6 +1989,7 @@ void locking_selftest(void)
init_shared_classes();
debug_locks_silent = !debug_locks_verbose;
+ lockdep_set_selftest_task(current);
DO_TESTCASE_6R("A-A deadlock", AA);
DO_TESTCASE_6R("A-B-B-A deadlock", ABBA);
@@ -2097,5 +2098,6 @@ void locking_selftest(void)
printk("---------------------------------\n");
debug_locks = 1;
}
+ lockdep_set_selftest_task(NULL);
debug_locks_silent = 0;
}
diff --git a/lib/objagg.c b/lib/objagg.c
index c9b457a91153..576be22e86de 100644
--- a/lib/objagg.c
+++ b/lib/objagg.c
@@ -4,6 +4,7 @@
#include <linux/module.h>
#include <linux/slab.h>
#include <linux/rhashtable.h>
+#include <linux/idr.h>
#include <linux/list.h>
#include <linux/sort.h>
#include <linux/objagg.h>
@@ -11,6 +12,34 @@
#define CREATE_TRACE_POINTS
#include <trace/events/objagg.h>
+struct objagg_hints {
+ struct rhashtable node_ht;
+ struct rhashtable_params ht_params;
+ struct list_head node_list;
+ unsigned int node_count;
+ unsigned int root_count;
+ unsigned int refcount;
+ const struct objagg_ops *ops;
+};
+
+struct objagg_hints_node {
+ struct rhash_head ht_node; /* member of objagg_hints->node_ht */
+ struct list_head list; /* member of objagg_hints->node_list */
+ struct objagg_hints_node *parent;
+ unsigned int root_id;
+ struct objagg_obj_stats_info stats_info;
+ unsigned long obj[0];
+};
+
+static struct objagg_hints_node *
+objagg_hints_lookup(struct objagg_hints *objagg_hints, void *obj)
+{
+ if (!objagg_hints)
+ return NULL;
+ return rhashtable_lookup_fast(&objagg_hints->node_ht, obj,
+ objagg_hints->ht_params);
+}
+
struct objagg {
const struct objagg_ops *ops;
void *priv;
@@ -18,6 +47,8 @@ struct objagg {
struct rhashtable_params ht_params;
struct list_head obj_list;
unsigned int obj_count;
+ struct ida root_ida;
+ struct objagg_hints *hints;
};
struct objagg_obj {
@@ -30,6 +61,7 @@ struct objagg_obj {
void *delta_priv; /* user delta private */
void *root_priv; /* user root private */
};
+ unsigned int root_id;
unsigned int refcount; /* counts number of users of this object
* including nested objects
*/
@@ -130,7 +162,8 @@ static struct objagg_obj *objagg_obj_lookup(struct objagg *objagg, void *obj)
static int objagg_obj_parent_assign(struct objagg *objagg,
struct objagg_obj *objagg_obj,
- struct objagg_obj *parent)
+ struct objagg_obj *parent,
+ bool take_parent_ref)
{
void *delta_priv;
@@ -144,7 +177,8 @@ static int objagg_obj_parent_assign(struct objagg *objagg,
*/
objagg_obj->parent = parent;
objagg_obj->delta_priv = delta_priv;
- objagg_obj_ref_inc(objagg_obj->parent);
+ if (take_parent_ref)
+ objagg_obj_ref_inc(objagg_obj->parent);
trace_objagg_obj_parent_assign(objagg, objagg_obj,
parent,
parent->refcount);
@@ -164,7 +198,7 @@ static int objagg_obj_parent_lookup_assign(struct objagg *objagg,
if (!objagg_obj_is_root(objagg_obj_cur))
continue;
err = objagg_obj_parent_assign(objagg, objagg_obj,
- objagg_obj_cur);
+ objagg_obj_cur, true);
if (!err)
return 0;
}
@@ -184,16 +218,68 @@ static void objagg_obj_parent_unassign(struct objagg *objagg,
__objagg_obj_put(objagg, objagg_obj->parent);
}
+static int objagg_obj_root_id_alloc(struct objagg *objagg,
+ struct objagg_obj *objagg_obj,
+ struct objagg_hints_node *hnode)
+{
+ unsigned int min, max;
+ int root_id;
+
+ /* In case there are no hints available, the root id is invalid. */
+ if (!objagg->hints) {
+ objagg_obj->root_id = OBJAGG_OBJ_ROOT_ID_INVALID;
+ return 0;
+ }
+
+ if (hnode) {
+ min = hnode->root_id;
+ max = hnode->root_id;
+ } else {
+ /* For objects with no hint, start after the last
+ * hinted root_id.
+ */
+ min = objagg->hints->root_count;
+ max = ~0;
+ }
+
+ root_id = ida_alloc_range(&objagg->root_ida, min, max, GFP_KERNEL);
+
+ if (root_id < 0)
+ return root_id;
+ objagg_obj->root_id = root_id;
+ return 0;
+}
+
+static void objagg_obj_root_id_free(struct objagg *objagg,
+ struct objagg_obj *objagg_obj)
+{
+ if (!objagg->hints)
+ return;
+ ida_free(&objagg->root_ida, objagg_obj->root_id);
+}
+
static int objagg_obj_root_create(struct objagg *objagg,
- struct objagg_obj *objagg_obj)
+ struct objagg_obj *objagg_obj,
+ struct objagg_hints_node *hnode)
{
- objagg_obj->root_priv = objagg->ops->root_create(objagg->priv,
- objagg_obj->obj);
- if (IS_ERR(objagg_obj->root_priv))
- return PTR_ERR(objagg_obj->root_priv);
+ int err;
+ err = objagg_obj_root_id_alloc(objagg, objagg_obj, hnode);
+ if (err)
+ return err;
+ objagg_obj->root_priv = objagg->ops->root_create(objagg->priv,
+ objagg_obj->obj,
+ objagg_obj->root_id);
+ if (IS_ERR(objagg_obj->root_priv)) {
+ err = PTR_ERR(objagg_obj->root_priv);
+ goto err_root_create;
+ }
trace_objagg_obj_root_create(objagg, objagg_obj);
return 0;
+
+err_root_create:
+ objagg_obj_root_id_free(objagg, objagg_obj);
+ return err;
}
static void objagg_obj_root_destroy(struct objagg *objagg,
@@ -201,19 +287,69 @@ static void objagg_obj_root_destroy(struct objagg *objagg,
{
trace_objagg_obj_root_destroy(objagg, objagg_obj);
objagg->ops->root_destroy(objagg->priv, objagg_obj->root_priv);
+ objagg_obj_root_id_free(objagg, objagg_obj);
+}
+
+static struct objagg_obj *__objagg_obj_get(struct objagg *objagg, void *obj);
+
+static int objagg_obj_init_with_hints(struct objagg *objagg,
+ struct objagg_obj *objagg_obj,
+ bool *hint_found)
+{
+ struct objagg_hints_node *hnode;
+ struct objagg_obj *parent;
+ int err;
+
+ hnode = objagg_hints_lookup(objagg->hints, objagg_obj->obj);
+ if (!hnode) {
+ *hint_found = false;
+ return 0;
+ }
+ *hint_found = true;
+
+ if (!hnode->parent)
+ return objagg_obj_root_create(objagg, objagg_obj, hnode);
+
+ parent = __objagg_obj_get(objagg, hnode->parent->obj);
+ if (IS_ERR(parent))
+ return PTR_ERR(parent);
+
+ err = objagg_obj_parent_assign(objagg, objagg_obj, parent, false);
+ if (err) {
+ *hint_found = false;
+ err = 0;
+ goto err_parent_assign;
+ }
+
+ return 0;
+
+err_parent_assign:
+ objagg_obj_put(objagg, parent);
+ return err;
}
static int objagg_obj_init(struct objagg *objagg,
struct objagg_obj *objagg_obj)
{
+ bool hint_found;
int err;
+ /* First, try to use hints if they are available and
+ * if they provide result.
+ */
+ err = objagg_obj_init_with_hints(objagg, objagg_obj, &hint_found);
+ if (err)
+ return err;
+
+ if (hint_found)
+ return 0;
+
/* Try to find if the object can be aggregated under an existing one. */
err = objagg_obj_parent_lookup_assign(objagg, objagg_obj);
if (!err)
return 0;
/* If aggregation is not possible, make the object a root. */
- return objagg_obj_root_create(objagg, objagg_obj);
+ return objagg_obj_root_create(objagg, objagg_obj, NULL);
}
static void objagg_obj_fini(struct objagg *objagg,
@@ -349,8 +485,9 @@ EXPORT_SYMBOL(objagg_obj_put);
/**
* objagg_create - creates a new objagg instance
- * @ops: user-specific callbacks
- * @priv: pointer to a private data passed to the ops
+ * @ops: user-specific callbacks
+ * @objagg_hints: hints, can be NULL
+ * @priv: pointer to a private data passed to the ops
*
* Note: all locking must be provided by the caller.
*
@@ -374,18 +511,25 @@ EXPORT_SYMBOL(objagg_obj_put);
* Returns a pointer to newly created objagg instance in case of success,
* otherwise it returns pointer error using ERR_PTR macro.
*/
-struct objagg *objagg_create(const struct objagg_ops *ops, void *priv)
+struct objagg *objagg_create(const struct objagg_ops *ops,
+ struct objagg_hints *objagg_hints, void *priv)
{
struct objagg *objagg;
int err;
if (WARN_ON(!ops || !ops->root_create || !ops->root_destroy ||
- !ops->delta_create || !ops->delta_destroy))
+ !ops->delta_check || !ops->delta_create ||
+ !ops->delta_destroy))
return ERR_PTR(-EINVAL);
+
objagg = kzalloc(sizeof(*objagg), GFP_KERNEL);
if (!objagg)
return ERR_PTR(-ENOMEM);
objagg->ops = ops;
+ if (objagg_hints) {
+ objagg->hints = objagg_hints;
+ objagg_hints->refcount++;
+ }
objagg->priv = priv;
INIT_LIST_HEAD(&objagg->obj_list);
@@ -397,6 +541,8 @@ struct objagg *objagg_create(const struct objagg_ops *ops, void *priv)
if (err)
goto err_rhashtable_init;
+ ida_init(&objagg->root_ida);
+
trace_objagg_create(objagg);
return objagg;
@@ -415,8 +561,11 @@ EXPORT_SYMBOL(objagg_create);
void objagg_destroy(struct objagg *objagg)
{
trace_objagg_destroy(objagg);
+ ida_destroy(&objagg->root_ida);
WARN_ON(!list_empty(&objagg->obj_list));
rhashtable_destroy(&objagg->obj_ht);
+ if (objagg->hints)
+ objagg_hints_put(objagg->hints);
kfree(objagg);
}
EXPORT_SYMBOL(objagg_destroy);
@@ -472,6 +621,8 @@ const struct objagg_stats *objagg_stats_get(struct objagg *objagg)
objagg_stats->stats_info[i].objagg_obj = objagg_obj;
objagg_stats->stats_info[i].is_root =
objagg_obj_is_root(objagg_obj);
+ if (objagg_stats->stats_info[i].is_root)
+ objagg_stats->root_count++;
i++;
}
objagg_stats->stats_info_count = i;
@@ -485,7 +636,7 @@ const struct objagg_stats *objagg_stats_get(struct objagg *objagg)
EXPORT_SYMBOL(objagg_stats_get);
/**
- * objagg_stats_puts - puts stats of the objagg instance
+ * objagg_stats_put - puts stats of the objagg instance
* @objagg_stats: objagg instance stats
*
* Note: all locking must be provided by the caller.
@@ -496,6 +647,410 @@ void objagg_stats_put(const struct objagg_stats *objagg_stats)
}
EXPORT_SYMBOL(objagg_stats_put);
+static struct objagg_hints_node *
+objagg_hints_node_create(struct objagg_hints *objagg_hints,
+ struct objagg_obj *objagg_obj, size_t obj_size,
+ struct objagg_hints_node *parent_hnode)
+{
+ unsigned int user_count = objagg_obj->stats.user_count;
+ struct objagg_hints_node *hnode;
+ int err;
+
+ hnode = kzalloc(sizeof(*hnode) + obj_size, GFP_KERNEL);
+ if (!hnode)
+ return ERR_PTR(-ENOMEM);
+ memcpy(hnode->obj, &objagg_obj->obj, obj_size);
+ hnode->stats_info.stats.user_count = user_count;
+ hnode->stats_info.stats.delta_user_count = user_count;
+ if (parent_hnode) {
+ parent_hnode->stats_info.stats.delta_user_count += user_count;
+ } else {
+ hnode->root_id = objagg_hints->root_count++;
+ hnode->stats_info.is_root = true;
+ }
+ hnode->stats_info.objagg_obj = objagg_obj;
+
+ err = rhashtable_insert_fast(&objagg_hints->node_ht, &hnode->ht_node,
+ objagg_hints->ht_params);
+ if (err)
+ goto err_ht_insert;
+
+ list_add(&hnode->list, &objagg_hints->node_list);
+ hnode->parent = parent_hnode;
+ objagg_hints->node_count++;
+
+ return hnode;
+
+err_ht_insert:
+ kfree(hnode);
+ return ERR_PTR(err);
+}
+
+static void objagg_hints_flush(struct objagg_hints *objagg_hints)
+{
+ struct objagg_hints_node *hnode, *tmp;
+
+ list_for_each_entry_safe(hnode, tmp, &objagg_hints->node_list, list) {
+ list_del(&hnode->list);
+ rhashtable_remove_fast(&objagg_hints->node_ht, &hnode->ht_node,
+ objagg_hints->ht_params);
+ kfree(hnode);
+ }
+}
+
+struct objagg_tmp_node {
+ struct objagg_obj *objagg_obj;
+ bool crossed_out;
+};
+
+struct objagg_tmp_graph {
+ struct objagg_tmp_node *nodes;
+ unsigned long nodes_count;
+ unsigned long *edges;
+};
+
+static int objagg_tmp_graph_edge_index(struct objagg_tmp_graph *graph,
+ int parent_index, int index)
+{
+ return index * graph->nodes_count + parent_index;
+}
+
+static void objagg_tmp_graph_edge_set(struct objagg_tmp_graph *graph,
+ int parent_index, int index)
+{
+ int edge_index = objagg_tmp_graph_edge_index(graph, index,
+ parent_index);
+
+ __set_bit(edge_index, graph->edges);
+}
+
+static bool objagg_tmp_graph_is_edge(struct objagg_tmp_graph *graph,
+ int parent_index, int index)
+{
+ int edge_index = objagg_tmp_graph_edge_index(graph, index,
+ parent_index);
+
+ return test_bit(edge_index, graph->edges);
+}
+
+static unsigned int objagg_tmp_graph_node_weight(struct objagg_tmp_graph *graph,
+ unsigned int index)
+{
+ struct objagg_tmp_node *node = &graph->nodes[index];
+ unsigned int weight = node->objagg_obj->stats.user_count;
+ int j;
+
+ /* Node weight is sum of node users and all other nodes users
+ * that this node can represent with delta.
+ */
+
+ for (j = 0; j < graph->nodes_count; j++) {
+ if (!objagg_tmp_graph_is_edge(graph, index, j))
+ continue;
+ node = &graph->nodes[j];
+ if (node->crossed_out)
+ continue;
+ weight += node->objagg_obj->stats.user_count;
+ }
+ return weight;
+}
+
+static int objagg_tmp_graph_node_max_weight(struct objagg_tmp_graph *graph)
+{
+ struct objagg_tmp_node *node;
+ unsigned int max_weight = 0;
+ unsigned int weight;
+ int max_index = -1;
+ int i;
+
+ for (i = 0; i < graph->nodes_count; i++) {
+ node = &graph->nodes[i];
+ if (node->crossed_out)
+ continue;
+ weight = objagg_tmp_graph_node_weight(graph, i);
+ if (weight >= max_weight) {
+ max_weight = weight;
+ max_index = i;
+ }
+ }
+ return max_index;
+}
+
+static struct objagg_tmp_graph *objagg_tmp_graph_create(struct objagg *objagg)
+{
+ unsigned int nodes_count = objagg->obj_count;
+ struct objagg_tmp_graph *graph;
+ struct objagg_tmp_node *node;
+ struct objagg_tmp_node *pnode;
+ struct objagg_obj *objagg_obj;
+ size_t alloc_size;
+ int i, j;
+
+ graph = kzalloc(sizeof(*graph), GFP_KERNEL);
+ if (!graph)
+ return NULL;
+
+ graph->nodes = kcalloc(nodes_count, sizeof(*graph->nodes), GFP_KERNEL);
+ if (!graph->nodes)
+ goto err_nodes_alloc;
+ graph->nodes_count = nodes_count;
+
+ alloc_size = BITS_TO_LONGS(nodes_count * nodes_count) *
+ sizeof(unsigned long);
+ graph->edges = kzalloc(alloc_size, GFP_KERNEL);
+ if (!graph->edges)
+ goto err_edges_alloc;
+
+ i = 0;
+ list_for_each_entry(objagg_obj, &objagg->obj_list, list) {
+ node = &graph->nodes[i++];
+ node->objagg_obj = objagg_obj;
+ }
+
+ /* Assemble a temporary graph. Insert edge X->Y in case Y can be
+ * in delta of X.
+ */
+ for (i = 0; i < nodes_count; i++) {
+ for (j = 0; j < nodes_count; j++) {
+ if (i == j)
+ continue;
+ pnode = &graph->nodes[i];
+ node = &graph->nodes[j];
+ if (objagg->ops->delta_check(objagg->priv,
+ pnode->objagg_obj->obj,
+ node->objagg_obj->obj)) {
+ objagg_tmp_graph_edge_set(graph, i, j);
+
+ }
+ }
+ }
+ return graph;
+
+err_edges_alloc:
+ kfree(graph->nodes);
+err_nodes_alloc:
+ kfree(graph);
+ return NULL;
+}
+
+static void objagg_tmp_graph_destroy(struct objagg_tmp_graph *graph)
+{
+ kfree(graph->edges);
+ kfree(graph->nodes);
+ kfree(graph);
+}
+
+static int
+objagg_opt_simple_greedy_fillup_hints(struct objagg_hints *objagg_hints,
+ struct objagg *objagg)
+{
+ struct objagg_hints_node *hnode, *parent_hnode;
+ struct objagg_tmp_graph *graph;
+ struct objagg_tmp_node *node;
+ int index;
+ int j;
+ int err;
+
+ graph = objagg_tmp_graph_create(objagg);
+ if (!graph)
+ return -ENOMEM;
+
+ /* Find the nodes from the ones that can accommodate most users
+ * and cross them out of the graph. Save them to the hint list.
+ */
+ while ((index = objagg_tmp_graph_node_max_weight(graph)) != -1) {
+ node = &graph->nodes[index];
+ node->crossed_out = true;
+ hnode = objagg_hints_node_create(objagg_hints,
+ node->objagg_obj,
+ objagg->ops->obj_size,
+ NULL);
+ if (IS_ERR(hnode)) {
+ err = PTR_ERR(hnode);
+ goto out;
+ }
+ parent_hnode = hnode;
+ for (j = 0; j < graph->nodes_count; j++) {
+ if (!objagg_tmp_graph_is_edge(graph, index, j))
+ continue;
+ node = &graph->nodes[j];
+ if (node->crossed_out)
+ continue;
+ node->crossed_out = true;
+ hnode = objagg_hints_node_create(objagg_hints,
+ node->objagg_obj,
+ objagg->ops->obj_size,
+ parent_hnode);
+ if (IS_ERR(hnode)) {
+ err = PTR_ERR(hnode);
+ goto out;
+ }
+ }
+ }
+
+ err = 0;
+out:
+ objagg_tmp_graph_destroy(graph);
+ return err;
+}
+
+struct objagg_opt_algo {
+ int (*fillup_hints)(struct objagg_hints *objagg_hints,
+ struct objagg *objagg);
+};
+
+static const struct objagg_opt_algo objagg_opt_simple_greedy = {
+ .fillup_hints = objagg_opt_simple_greedy_fillup_hints,
+};
+
+
+static const struct objagg_opt_algo *objagg_opt_algos[] = {
+ [OBJAGG_OPT_ALGO_SIMPLE_GREEDY] = &objagg_opt_simple_greedy,
+};
+
+static int objagg_hints_obj_cmp(struct rhashtable_compare_arg *arg,
+ const void *obj)
+{
+ struct rhashtable *ht = arg->ht;
+ struct objagg_hints *objagg_hints =
+ container_of(ht, struct objagg_hints, node_ht);
+ const struct objagg_ops *ops = objagg_hints->ops;
+ const char *ptr = obj;
+
+ ptr += ht->p.key_offset;
+ return ops->hints_obj_cmp ? ops->hints_obj_cmp(ptr, arg->key) :
+ memcmp(ptr, arg->key, ht->p.key_len);
+}
+
+/**
+ * objagg_hints_get - obtains hints instance
+ * @objagg: objagg instance
+ * @opt_algo_type: type of hints finding algorithm
+ *
+ * Note: all locking must be provided by the caller.
+ *
+ * According to the algo type, the existing objects of objagg instance
+ * are going to be went-through to assemble an optimal tree. We call this
+ * tree hints. These hints can be later on used for creation of
+ * a new objagg instance. There, the future object creations are going
+ * to be consulted with these hints in order to find out, where exactly
+ * the new object should be put as a root or delta.
+ *
+ * Returns a pointer to hints instance in case of success,
+ * otherwise it returns pointer error using ERR_PTR macro.
+ */
+struct objagg_hints *objagg_hints_get(struct objagg *objagg,
+ enum objagg_opt_algo_type opt_algo_type)
+{
+ const struct objagg_opt_algo *algo = objagg_opt_algos[opt_algo_type];
+ struct objagg_hints *objagg_hints;
+ int err;
+
+ objagg_hints = kzalloc(sizeof(*objagg_hints), GFP_KERNEL);
+ if (!objagg_hints)
+ return ERR_PTR(-ENOMEM);
+
+ objagg_hints->ops = objagg->ops;
+ objagg_hints->refcount = 1;
+
+ INIT_LIST_HEAD(&objagg_hints->node_list);
+
+ objagg_hints->ht_params.key_len = objagg->ops->obj_size;
+ objagg_hints->ht_params.key_offset =
+ offsetof(struct objagg_hints_node, obj);
+ objagg_hints->ht_params.head_offset =
+ offsetof(struct objagg_hints_node, ht_node);
+ objagg_hints->ht_params.obj_cmpfn = objagg_hints_obj_cmp;
+
+ err = rhashtable_init(&objagg_hints->node_ht, &objagg_hints->ht_params);
+ if (err)
+ goto err_rhashtable_init;
+
+ err = algo->fillup_hints(objagg_hints, objagg);
+ if (err)
+ goto err_fillup_hints;
+
+ if (WARN_ON(objagg_hints->node_count != objagg->obj_count)) {
+ err = -EINVAL;
+ goto err_node_count_check;
+ }
+
+ return objagg_hints;
+
+err_node_count_check:
+err_fillup_hints:
+ objagg_hints_flush(objagg_hints);
+ rhashtable_destroy(&objagg_hints->node_ht);
+err_rhashtable_init:
+ kfree(objagg_hints);
+ return ERR_PTR(err);
+}
+EXPORT_SYMBOL(objagg_hints_get);
+
+/**
+ * objagg_hints_put - puts hints instance
+ * @objagg_hints: objagg hints instance
+ *
+ * Note: all locking must be provided by the caller.
+ */
+void objagg_hints_put(struct objagg_hints *objagg_hints)
+{
+ if (--objagg_hints->refcount)
+ return;
+ objagg_hints_flush(objagg_hints);
+ rhashtable_destroy(&objagg_hints->node_ht);
+ kfree(objagg_hints);
+}
+EXPORT_SYMBOL(objagg_hints_put);
+
+/**
+ * objagg_hints_stats_get - obtains stats of the hints instance
+ * @objagg_hints: hints instance
+ *
+ * Note: all locking must be provided by the caller.
+ *
+ * The returned structure contains statistics of all objects
+ * currently in use, ordered by following rules:
+ * 1) Root objects are always on lower indexes than the rest.
+ * 2) Objects with higher delta user count are always on lower
+ * indexes.
+ * 3) In case multiple objects have the same delta user count,
+ * the objects are ordered by user count.
+ *
+ * Returns a pointer to stats instance in case of success,
+ * otherwise it returns pointer error using ERR_PTR macro.
+ */
+const struct objagg_stats *
+objagg_hints_stats_get(struct objagg_hints *objagg_hints)
+{
+ struct objagg_stats *objagg_stats;
+ struct objagg_hints_node *hnode;
+ int i;
+
+ objagg_stats = kzalloc(struct_size(objagg_stats, stats_info,
+ objagg_hints->node_count),
+ GFP_KERNEL);
+ if (!objagg_stats)
+ return ERR_PTR(-ENOMEM);
+
+ i = 0;
+ list_for_each_entry(hnode, &objagg_hints->node_list, list) {
+ memcpy(&objagg_stats->stats_info[i], &hnode->stats_info,
+ sizeof(objagg_stats->stats_info[0]));
+ if (objagg_stats->stats_info[i].is_root)
+ objagg_stats->root_count++;
+ i++;
+ }
+ objagg_stats->stats_info_count = i;
+
+ sort(objagg_stats->stats_info, objagg_stats->stats_info_count,
+ sizeof(struct objagg_obj_stats_info),
+ objagg_stats_info_sort_cmp_func, NULL);
+
+ return objagg_stats;
+}
+EXPORT_SYMBOL(objagg_hints_stats_get);
+
MODULE_LICENSE("Dual BSD/GPL");
MODULE_AUTHOR("Jiri Pirko <jiri@mellanox.com>");
MODULE_DESCRIPTION("Object aggregation manager");
diff --git a/lib/refcount.c b/lib/refcount.c
index ebcf8cd49e05..6e904af0fb3e 100644
--- a/lib/refcount.c
+++ b/lib/refcount.c
@@ -33,6 +33,9 @@
* Note that the allocator is responsible for ordering things between free()
* and alloc().
*
+ * The decrements dec_and_test() and sub_and_test() also provide acquire
+ * ordering on success.
+ *
*/
#include <linux/mutex.h>
@@ -164,8 +167,8 @@ EXPORT_SYMBOL(refcount_inc_checked);
* at UINT_MAX.
*
* Provides release memory ordering, such that prior loads and stores are done
- * before, and provides a control dependency such that free() must come after.
- * See the comment on top.
+ * before, and provides an acquire ordering on success such that free()
+ * must come after.
*
* Use of this function is not recommended for the normal reference counting
* use case in which references are taken and released one at a time. In these
@@ -190,7 +193,12 @@ bool refcount_sub_and_test_checked(unsigned int i, refcount_t *r)
} while (!atomic_try_cmpxchg_release(&r->refs, &val, new));
- return !new;
+ if (!new) {
+ smp_acquire__after_ctrl_dep();
+ return true;
+ }
+ return false;
+
}
EXPORT_SYMBOL(refcount_sub_and_test_checked);
@@ -202,8 +210,8 @@ EXPORT_SYMBOL(refcount_sub_and_test_checked);
* decrement when saturated at UINT_MAX.
*
* Provides release memory ordering, such that prior loads and stores are done
- * before, and provides a control dependency such that free() must come after.
- * See the comment on top.
+ * before, and provides an acquire ordering on success such that free()
+ * must come after.
*
* Return: true if the resulting refcount is 0, false otherwise
*/
diff --git a/lib/rhashtable.c b/lib/rhashtable.c
index 852ffa5160f1..0a105d4af166 100644
--- a/lib/rhashtable.c
+++ b/lib/rhashtable.c
@@ -682,7 +682,7 @@ EXPORT_SYMBOL_GPL(rhashtable_walk_enter);
* rhashtable_walk_exit - Free an iterator
* @iter: Hash table Iterator
*
- * This function frees resources allocated by rhashtable_walk_init.
+ * This function frees resources allocated by rhashtable_walk_enter.
*/
void rhashtable_walk_exit(struct rhashtable_iter *iter)
{
diff --git a/lib/smp_processor_id.c b/lib/smp_processor_id.c
index 85925aaa4fff..157d9e31f6c2 100644
--- a/lib/smp_processor_id.c
+++ b/lib/smp_processor_id.c
@@ -5,10 +5,11 @@
* DEBUG_PREEMPT variant of smp_processor_id().
*/
#include <linux/export.h>
+#include <linux/kprobes.h>
#include <linux/sched.h>
-notrace static unsigned int check_preemption_disabled(const char *what1,
- const char *what2)
+notrace static nokprobe_inline
+unsigned int check_preemption_disabled(const char *what1, const char *what2)
{
int this_cpu = raw_smp_processor_id();
@@ -56,9 +57,11 @@ notrace unsigned int debug_smp_processor_id(void)
return check_preemption_disabled("smp_processor_id", "");
}
EXPORT_SYMBOL(debug_smp_processor_id);
+NOKPROBE_SYMBOL(debug_smp_processor_id);
notrace void __this_cpu_preempt_check(const char *op)
{
check_preemption_disabled("__this_cpu_", op);
}
EXPORT_SYMBOL(__this_cpu_preempt_check);
+NOKPROBE_SYMBOL(__this_cpu_preempt_check);
diff --git a/lib/test_bpf.c b/lib/test_bpf.c
index f3e570722a7e..0845f635f404 100644
--- a/lib/test_bpf.c
+++ b/lib/test_bpf.c
@@ -6668,12 +6668,14 @@ static int __run_one(const struct bpf_prog *fp, const void *data,
u64 start, finish;
int ret = 0, i;
+ preempt_disable();
start = ktime_get_ns();
for (i = 0; i < runs; i++)
ret = BPF_PROG_RUN(fp, data);
finish = ktime_get_ns();
+ preempt_enable();
*duration = finish - start;
do_div(*duration, runs);
diff --git a/lib/test_kasan.c b/lib/test_kasan.c
index 51b78405bf24..7de2702621dc 100644
--- a/lib/test_kasan.c
+++ b/lib/test_kasan.c
@@ -480,29 +480,6 @@ static noinline void __init copy_user_test(void)
kfree(kmem);
}
-static noinline void __init use_after_scope_test(void)
-{
- volatile char *volatile p;
-
- pr_info("use-after-scope on int\n");
- {
- int local = 0;
-
- p = (char *)&local;
- }
- p[0] = 1;
- p[3] = 1;
-
- pr_info("use-after-scope on array\n");
- {
- char local[1024] = {0};
-
- p = local;
- }
- p[0] = 1;
- p[1023] = 1;
-}
-
static noinline void __init kasan_alloca_oob_left(void)
{
volatile int i = 10;
@@ -682,7 +659,6 @@ static int __init kmalloc_tests_init(void)
kasan_alloca_oob_right();
ksize_unpoisons_memory();
copy_user_test();
- use_after_scope_test();
kmem_cache_double_free();
kmem_cache_invalid_free();
kasan_memchr();
diff --git a/lib/test_objagg.c b/lib/test_objagg.c
index ab57144bb0cd..72c1abfa154d 100644
--- a/lib/test_objagg.c
+++ b/lib/test_objagg.c
@@ -87,6 +87,15 @@ static void world_obj_put(struct world *world, struct objagg *objagg,
#define MAX_KEY_ID_DIFF 5
+static bool delta_check(void *priv, const void *parent_obj, const void *obj)
+{
+ const struct tokey *parent_key = parent_obj;
+ const struct tokey *key = obj;
+ int diff = key->id - parent_key->id;
+
+ return diff >= 0 && diff <= MAX_KEY_ID_DIFF;
+}
+
static void *delta_create(void *priv, void *parent_obj, void *obj)
{
struct tokey *parent_key = parent_obj;
@@ -95,7 +104,7 @@ static void *delta_create(void *priv, void *parent_obj, void *obj)
int diff = key->id - parent_key->id;
struct delta *delta;
- if (diff < 0 || diff > MAX_KEY_ID_DIFF)
+ if (!delta_check(priv, parent_obj, obj))
return ERR_PTR(-EINVAL);
delta = kzalloc(sizeof(*delta), GFP_KERNEL);
@@ -115,7 +124,7 @@ static void delta_destroy(void *priv, void *delta_priv)
kfree(delta);
}
-static void *root_create(void *priv, void *obj)
+static void *root_create(void *priv, void *obj, unsigned int id)
{
struct world *world = priv;
struct tokey *key = obj;
@@ -268,6 +277,12 @@ stats_put:
return err;
}
+static bool delta_check_dummy(void *priv, const void *parent_obj,
+ const void *obj)
+{
+ return false;
+}
+
static void *delta_create_dummy(void *priv, void *parent_obj, void *obj)
{
return ERR_PTR(-EOPNOTSUPP);
@@ -279,6 +294,7 @@ static void delta_destroy_dummy(void *priv, void *delta_priv)
static const struct objagg_ops nodelta_ops = {
.obj_size = sizeof(struct tokey),
+ .delta_check = delta_check_dummy,
.delta_create = delta_create_dummy,
.delta_destroy = delta_destroy_dummy,
.root_create = root_create,
@@ -292,7 +308,7 @@ static int test_nodelta(void)
int i;
int err;
- objagg = objagg_create(&nodelta_ops, &world);
+ objagg = objagg_create(&nodelta_ops, NULL, &world);
if (IS_ERR(objagg))
return PTR_ERR(objagg);
@@ -357,6 +373,7 @@ err_stats_second_zero:
static const struct objagg_ops delta_ops = {
.obj_size = sizeof(struct tokey),
+ .delta_check = delta_check,
.delta_create = delta_create,
.delta_destroy = delta_destroy,
.root_create = root_create,
@@ -728,8 +745,10 @@ static int check_expect_stats(struct objagg *objagg,
int err;
stats = objagg_stats_get(objagg);
- if (IS_ERR(stats))
+ if (IS_ERR(stats)) {
+ *errmsg = "objagg_stats_get() failed.";
return PTR_ERR(stats);
+ }
err = __check_expect_stats(stats, expect_stats, errmsg);
objagg_stats_put(stats);
return err;
@@ -769,7 +788,6 @@ static int test_delta_action_item(struct world *world,
if (err)
goto errout;
- errmsg = NULL;
err = check_expect_stats(objagg, &action_item->expect_stats, &errmsg);
if (err) {
pr_err("Key %u: Stats: %s\n", action_item->key_id, errmsg);
@@ -793,7 +811,7 @@ static int test_delta(void)
int i;
int err;
- objagg = objagg_create(&delta_ops, &world);
+ objagg = objagg_create(&delta_ops, NULL, &world);
if (IS_ERR(objagg))
return PTR_ERR(objagg);
@@ -815,6 +833,170 @@ err_do_action_item:
return err;
}
+struct hints_case {
+ const unsigned int *key_ids;
+ size_t key_ids_count;
+ struct expect_stats expect_stats;
+ struct expect_stats expect_stats_hints;
+};
+
+static const unsigned int hints_case_key_ids[] = {
+ 1, 7, 3, 5, 3, 1, 30, 8, 8, 5, 6, 8,
+};
+
+static const struct hints_case hints_case = {
+ .key_ids = hints_case_key_ids,
+ .key_ids_count = ARRAY_SIZE(hints_case_key_ids),
+ .expect_stats =
+ EXPECT_STATS(7, ROOT(1, 2, 7), ROOT(7, 1, 4), ROOT(30, 1, 1),
+ DELTA(8, 3), DELTA(3, 2),
+ DELTA(5, 2), DELTA(6, 1)),
+ .expect_stats_hints =
+ EXPECT_STATS(7, ROOT(3, 2, 9), ROOT(1, 2, 2), ROOT(30, 1, 1),
+ DELTA(8, 3), DELTA(5, 2),
+ DELTA(6, 1), DELTA(7, 1)),
+};
+
+static void __pr_debug_stats(const struct objagg_stats *stats)
+{
+ int i;
+
+ for (i = 0; i < stats->stats_info_count; i++)
+ pr_debug("Stat index %d key %u: u %d, d %d, %s\n", i,
+ obj_to_key_id(stats->stats_info[i].objagg_obj),
+ stats->stats_info[i].stats.user_count,
+ stats->stats_info[i].stats.delta_user_count,
+ stats->stats_info[i].is_root ? "root" : "noroot");
+}
+
+static void pr_debug_stats(struct objagg *objagg)
+{
+ const struct objagg_stats *stats;
+
+ stats = objagg_stats_get(objagg);
+ if (IS_ERR(stats))
+ return;
+ __pr_debug_stats(stats);
+ objagg_stats_put(stats);
+}
+
+static void pr_debug_hints_stats(struct objagg_hints *objagg_hints)
+{
+ const struct objagg_stats *stats;
+
+ stats = objagg_hints_stats_get(objagg_hints);
+ if (IS_ERR(stats))
+ return;
+ __pr_debug_stats(stats);
+ objagg_stats_put(stats);
+}
+
+static int check_expect_hints_stats(struct objagg_hints *objagg_hints,
+ const struct expect_stats *expect_stats,
+ const char **errmsg)
+{
+ const struct objagg_stats *stats;
+ int err;
+
+ stats = objagg_hints_stats_get(objagg_hints);
+ if (IS_ERR(stats))
+ return PTR_ERR(stats);
+ err = __check_expect_stats(stats, expect_stats, errmsg);
+ objagg_stats_put(stats);
+ return err;
+}
+
+static int test_hints_case(const struct hints_case *hints_case)
+{
+ struct objagg_obj *objagg_obj;
+ struct objagg_hints *hints;
+ struct world world2 = {};
+ struct world world = {};
+ struct objagg *objagg2;
+ struct objagg *objagg;
+ const char *errmsg;
+ int i;
+ int err;
+
+ objagg = objagg_create(&delta_ops, NULL, &world);
+ if (IS_ERR(objagg))
+ return PTR_ERR(objagg);
+
+ for (i = 0; i < hints_case->key_ids_count; i++) {
+ objagg_obj = world_obj_get(&world, objagg,
+ hints_case->key_ids[i]);
+ if (IS_ERR(objagg_obj)) {
+ err = PTR_ERR(objagg_obj);
+ goto err_world_obj_get;
+ }
+ }
+
+ pr_debug_stats(objagg);
+ err = check_expect_stats(objagg, &hints_case->expect_stats, &errmsg);
+ if (err) {
+ pr_err("Stats: %s\n", errmsg);
+ goto err_check_expect_stats;
+ }
+
+ hints = objagg_hints_get(objagg, OBJAGG_OPT_ALGO_SIMPLE_GREEDY);
+ if (IS_ERR(hints)) {
+ err = PTR_ERR(hints);
+ goto err_hints_get;
+ }
+
+ pr_debug_hints_stats(hints);
+ err = check_expect_hints_stats(hints, &hints_case->expect_stats_hints,
+ &errmsg);
+ if (err) {
+ pr_err("Hints stats: %s\n", errmsg);
+ goto err_check_expect_hints_stats;
+ }
+
+ objagg2 = objagg_create(&delta_ops, hints, &world2);
+ if (IS_ERR(objagg2))
+ return PTR_ERR(objagg2);
+
+ for (i = 0; i < hints_case->key_ids_count; i++) {
+ objagg_obj = world_obj_get(&world2, objagg2,
+ hints_case->key_ids[i]);
+ if (IS_ERR(objagg_obj)) {
+ err = PTR_ERR(objagg_obj);
+ goto err_world2_obj_get;
+ }
+ }
+
+ pr_debug_stats(objagg2);
+ err = check_expect_stats(objagg2, &hints_case->expect_stats_hints,
+ &errmsg);
+ if (err) {
+ pr_err("Stats2: %s\n", errmsg);
+ goto err_check_expect_stats2;
+ }
+
+ err = 0;
+
+err_check_expect_stats2:
+err_world2_obj_get:
+ for (i--; i >= 0; i--)
+ world_obj_put(&world2, objagg, hints_case->key_ids[i]);
+ objagg_hints_put(hints);
+ objagg_destroy(objagg2);
+ i = hints_case->key_ids_count;
+err_check_expect_hints_stats:
+err_hints_get:
+err_check_expect_stats:
+err_world_obj_get:
+ for (i--; i >= 0; i--)
+ world_obj_put(&world, objagg, hints_case->key_ids[i]);
+
+ objagg_destroy(objagg);
+ return err;
+}
+static int test_hints(void)
+{
+ return test_hints_case(&hints_case);
+}
+
static int __init test_objagg_init(void)
{
int err;
@@ -822,7 +1004,10 @@ static int __init test_objagg_init(void)
err = test_nodelta();
if (err)
return err;
- return test_delta();
+ err = test_delta();
+ if (err)
+ return err;
+ return test_hints();
}
static void __exit test_objagg_exit(void)
diff --git a/lib/test_rhashtable.c b/lib/test_rhashtable.c
index e52f8cafe227..3bd2e91bfc29 100644
--- a/lib/test_rhashtable.c
+++ b/lib/test_rhashtable.c
@@ -177,16 +177,11 @@ static int __init test_rht_lookup(struct rhashtable *ht, struct test_obj *array,
static void test_bucket_stats(struct rhashtable *ht, unsigned int entries)
{
- unsigned int err, total = 0, chain_len = 0;
+ unsigned int total = 0, chain_len = 0;
struct rhashtable_iter hti;
struct rhash_head *pos;
- err = rhashtable_walk_init(ht, &hti, GFP_KERNEL);
- if (err) {
- pr_warn("Test failed: allocation error");
- return;
- }
-
+ rhashtable_walk_enter(ht, &hti);
rhashtable_walk_start(&hti);
while ((pos = rhashtable_walk_next(&hti))) {
@@ -395,7 +390,7 @@ static int __init test_rhltable(unsigned int entries)
if (WARN(err, "cannot remove element at slot %d", i))
continue;
} else {
- if (WARN(err != -ENOENT, "removed non-existant element %d, error %d not %d",
+ if (WARN(err != -ENOENT, "removed non-existent element %d, error %d not %d",
i, err, -ENOENT))
continue;
}
@@ -440,7 +435,7 @@ static int __init test_rhltable(unsigned int entries)
if (WARN(err, "cannot remove element at slot %d", i))
continue;
} else {
- if (WARN(err != -ENOENT, "removed non-existant element, error %d not %d",
+ if (WARN(err != -ENOENT, "removed non-existent element, error %d not %d",
err, -ENOENT))
continue;
}
diff --git a/lib/test_vmalloc.c b/lib/test_vmalloc.c
new file mode 100644
index 000000000000..83cdcaa82bf6
--- /dev/null
+++ b/lib/test_vmalloc.c
@@ -0,0 +1,551 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Test module for stress and analyze performance of vmalloc allocator.
+ * (C) 2018 Uladzislau Rezki (Sony) <urezki@gmail.com>
+ */
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/vmalloc.h>
+#include <linux/random.h>
+#include <linux/kthread.h>
+#include <linux/moduleparam.h>
+#include <linux/completion.h>
+#include <linux/delay.h>
+#include <linux/rwsem.h>
+#include <linux/mm.h>
+
+#define __param(type, name, init, msg) \
+ static type name = init; \
+ module_param(name, type, 0444); \
+ MODULE_PARM_DESC(name, msg) \
+
+__param(bool, single_cpu_test, false,
+ "Use single first online CPU to run tests");
+
+__param(bool, sequential_test_order, false,
+ "Use sequential stress tests order");
+
+__param(int, test_repeat_count, 1,
+ "Set test repeat counter");
+
+__param(int, test_loop_count, 1000000,
+ "Set test loop counter");
+
+__param(int, run_test_mask, INT_MAX,
+ "Set tests specified in the mask.\n\n"
+ "\t\tid: 1, name: fix_size_alloc_test\n"
+ "\t\tid: 2, name: full_fit_alloc_test\n"
+ "\t\tid: 4, name: long_busy_list_alloc_test\n"
+ "\t\tid: 8, name: random_size_alloc_test\n"
+ "\t\tid: 16, name: fix_align_alloc_test\n"
+ "\t\tid: 32, name: random_size_align_alloc_test\n"
+ "\t\tid: 64, name: align_shift_alloc_test\n"
+ "\t\tid: 128, name: pcpu_alloc_test\n"
+ /* Add a new test case description here. */
+);
+
+/*
+ * Depends on single_cpu_test parameter. If it is true, then
+ * use first online CPU to trigger a test on, otherwise go with
+ * all online CPUs.
+ */
+static cpumask_t cpus_run_test_mask = CPU_MASK_NONE;
+
+/*
+ * Read write semaphore for synchronization of setup
+ * phase that is done in main thread and workers.
+ */
+static DECLARE_RWSEM(prepare_for_test_rwsem);
+
+/*
+ * Completion tracking for worker threads.
+ */
+static DECLARE_COMPLETION(test_all_done_comp);
+static atomic_t test_n_undone = ATOMIC_INIT(0);
+
+static inline void
+test_report_one_done(void)
+{
+ if (atomic_dec_and_test(&test_n_undone))
+ complete(&test_all_done_comp);
+}
+
+static int random_size_align_alloc_test(void)
+{
+ unsigned long size, align, rnd;
+ void *ptr;
+ int i;
+
+ for (i = 0; i < test_loop_count; i++) {
+ get_random_bytes(&rnd, sizeof(rnd));
+
+ /*
+ * Maximum 1024 pages, if PAGE_SIZE is 4096.
+ */
+ align = 1 << (rnd % 23);
+
+ /*
+ * Maximum 10 pages.
+ */
+ size = ((rnd % 10) + 1) * PAGE_SIZE;
+
+ ptr = __vmalloc_node_range(size, align,
+ VMALLOC_START, VMALLOC_END,
+ GFP_KERNEL | __GFP_ZERO,
+ PAGE_KERNEL,
+ 0, 0, __builtin_return_address(0));
+
+ if (!ptr)
+ return -1;
+
+ vfree(ptr);
+ }
+
+ return 0;
+}
+
+/*
+ * This test case is supposed to be failed.
+ */
+static int align_shift_alloc_test(void)
+{
+ unsigned long align;
+ void *ptr;
+ int i;
+
+ for (i = 0; i < BITS_PER_LONG; i++) {
+ align = ((unsigned long) 1) << i;
+
+ ptr = __vmalloc_node_range(PAGE_SIZE, align,
+ VMALLOC_START, VMALLOC_END,
+ GFP_KERNEL | __GFP_ZERO,
+ PAGE_KERNEL,
+ 0, 0, __builtin_return_address(0));
+
+ if (!ptr)
+ return -1;
+
+ vfree(ptr);
+ }
+
+ return 0;
+}
+
+static int fix_align_alloc_test(void)
+{
+ void *ptr;
+ int i;
+
+ for (i = 0; i < test_loop_count; i++) {
+ ptr = __vmalloc_node_range(5 * PAGE_SIZE,
+ THREAD_ALIGN << 1,
+ VMALLOC_START, VMALLOC_END,
+ GFP_KERNEL | __GFP_ZERO,
+ PAGE_KERNEL,
+ 0, 0, __builtin_return_address(0));
+
+ if (!ptr)
+ return -1;
+
+ vfree(ptr);
+ }
+
+ return 0;
+}
+
+static int random_size_alloc_test(void)
+{
+ unsigned int n;
+ void *p;
+ int i;
+
+ for (i = 0; i < test_loop_count; i++) {
+ get_random_bytes(&n, sizeof(i));
+ n = (n % 100) + 1;
+
+ p = vmalloc(n * PAGE_SIZE);
+
+ if (!p)
+ return -1;
+
+ *((__u8 *)p) = 1;
+ vfree(p);
+ }
+
+ return 0;
+}
+
+static int long_busy_list_alloc_test(void)
+{
+ void *ptr_1, *ptr_2;
+ void **ptr;
+ int rv = -1;
+ int i;
+
+ ptr = vmalloc(sizeof(void *) * 15000);
+ if (!ptr)
+ return rv;
+
+ for (i = 0; i < 15000; i++)
+ ptr[i] = vmalloc(1 * PAGE_SIZE);
+
+ for (i = 0; i < test_loop_count; i++) {
+ ptr_1 = vmalloc(100 * PAGE_SIZE);
+ if (!ptr_1)
+ goto leave;
+
+ ptr_2 = vmalloc(1 * PAGE_SIZE);
+ if (!ptr_2) {
+ vfree(ptr_1);
+ goto leave;
+ }
+
+ *((__u8 *)ptr_1) = 0;
+ *((__u8 *)ptr_2) = 1;
+
+ vfree(ptr_1);
+ vfree(ptr_2);
+ }
+
+ /* Success */
+ rv = 0;
+
+leave:
+ for (i = 0; i < 15000; i++)
+ vfree(ptr[i]);
+
+ vfree(ptr);
+ return rv;
+}
+
+static int full_fit_alloc_test(void)
+{
+ void **ptr, **junk_ptr, *tmp;
+ int junk_length;
+ int rv = -1;
+ int i;
+
+ junk_length = fls(num_online_cpus());
+ junk_length *= (32 * 1024 * 1024 / PAGE_SIZE);
+
+ ptr = vmalloc(sizeof(void *) * junk_length);
+ if (!ptr)
+ return rv;
+
+ junk_ptr = vmalloc(sizeof(void *) * junk_length);
+ if (!junk_ptr) {
+ vfree(ptr);
+ return rv;
+ }
+
+ for (i = 0; i < junk_length; i++) {
+ ptr[i] = vmalloc(1 * PAGE_SIZE);
+ junk_ptr[i] = vmalloc(1 * PAGE_SIZE);
+ }
+
+ for (i = 0; i < junk_length; i++)
+ vfree(junk_ptr[i]);
+
+ for (i = 0; i < test_loop_count; i++) {
+ tmp = vmalloc(1 * PAGE_SIZE);
+
+ if (!tmp)
+ goto error;
+
+ *((__u8 *)tmp) = 1;
+ vfree(tmp);
+ }
+
+ /* Success */
+ rv = 0;
+
+error:
+ for (i = 0; i < junk_length; i++)
+ vfree(ptr[i]);
+
+ vfree(ptr);
+ vfree(junk_ptr);
+
+ return rv;
+}
+
+static int fix_size_alloc_test(void)
+{
+ void *ptr;
+ int i;
+
+ for (i = 0; i < test_loop_count; i++) {
+ ptr = vmalloc(3 * PAGE_SIZE);
+
+ if (!ptr)
+ return -1;
+
+ *((__u8 *)ptr) = 0;
+
+ vfree(ptr);
+ }
+
+ return 0;
+}
+
+static int
+pcpu_alloc_test(void)
+{
+ int rv = 0;
+#ifndef CONFIG_NEED_PER_CPU_KM
+ void __percpu **pcpu;
+ size_t size, align;
+ int i;
+
+ pcpu = vmalloc(sizeof(void __percpu *) * 35000);
+ if (!pcpu)
+ return -1;
+
+ for (i = 0; i < 35000; i++) {
+ unsigned int r;
+
+ get_random_bytes(&r, sizeof(i));
+ size = (r % (PAGE_SIZE / 4)) + 1;
+
+ /*
+ * Maximum PAGE_SIZE
+ */
+ get_random_bytes(&r, sizeof(i));
+ align = 1 << ((i % 11) + 1);
+
+ pcpu[i] = __alloc_percpu(size, align);
+ if (!pcpu[i])
+ rv = -1;
+ }
+
+ for (i = 0; i < 35000; i++)
+ free_percpu(pcpu[i]);
+
+ vfree(pcpu);
+#endif
+ return rv;
+}
+
+struct test_case_desc {
+ const char *test_name;
+ int (*test_func)(void);
+};
+
+static struct test_case_desc test_case_array[] = {
+ { "fix_size_alloc_test", fix_size_alloc_test },
+ { "full_fit_alloc_test", full_fit_alloc_test },
+ { "long_busy_list_alloc_test", long_busy_list_alloc_test },
+ { "random_size_alloc_test", random_size_alloc_test },
+ { "fix_align_alloc_test", fix_align_alloc_test },
+ { "random_size_align_alloc_test", random_size_align_alloc_test },
+ { "align_shift_alloc_test", align_shift_alloc_test },
+ { "pcpu_alloc_test", pcpu_alloc_test },
+ /* Add a new test case here. */
+};
+
+struct test_case_data {
+ int test_failed;
+ int test_passed;
+ u64 time;
+};
+
+/* Split it to get rid of: WARNING: line over 80 characters */
+static struct test_case_data
+ per_cpu_test_data[NR_CPUS][ARRAY_SIZE(test_case_array)];
+
+static struct test_driver {
+ struct task_struct *task;
+ unsigned long start;
+ unsigned long stop;
+ int cpu;
+} per_cpu_test_driver[NR_CPUS];
+
+static void shuffle_array(int *arr, int n)
+{
+ unsigned int rnd;
+ int i, j, x;
+
+ for (i = n - 1; i > 0; i--) {
+ get_random_bytes(&rnd, sizeof(rnd));
+
+ /* Cut the range. */
+ j = rnd % i;
+
+ /* Swap indexes. */
+ x = arr[i];
+ arr[i] = arr[j];
+ arr[j] = x;
+ }
+}
+
+static int test_func(void *private)
+{
+ struct test_driver *t = private;
+ cpumask_t newmask = CPU_MASK_NONE;
+ int random_array[ARRAY_SIZE(test_case_array)];
+ int index, i, j, ret;
+ ktime_t kt;
+ u64 delta;
+
+ cpumask_set_cpu(t->cpu, &newmask);
+ set_cpus_allowed_ptr(current, &newmask);
+
+ for (i = 0; i < ARRAY_SIZE(test_case_array); i++)
+ random_array[i] = i;
+
+ if (!sequential_test_order)
+ shuffle_array(random_array, ARRAY_SIZE(test_case_array));
+
+ /*
+ * Block until initialization is done.
+ */
+ down_read(&prepare_for_test_rwsem);
+
+ t->start = get_cycles();
+ for (i = 0; i < ARRAY_SIZE(test_case_array); i++) {
+ index = random_array[i];
+
+ /*
+ * Skip tests if run_test_mask has been specified.
+ */
+ if (!((run_test_mask & (1 << index)) >> index))
+ continue;
+
+ kt = ktime_get();
+ for (j = 0; j < test_repeat_count; j++) {
+ ret = test_case_array[index].test_func();
+ if (!ret)
+ per_cpu_test_data[t->cpu][index].test_passed++;
+ else
+ per_cpu_test_data[t->cpu][index].test_failed++;
+ }
+
+ /*
+ * Take an average time that test took.
+ */
+ delta = (u64) ktime_us_delta(ktime_get(), kt);
+ do_div(delta, (u32) test_repeat_count);
+
+ per_cpu_test_data[t->cpu][index].time = delta;
+ }
+ t->stop = get_cycles();
+
+ up_read(&prepare_for_test_rwsem);
+ test_report_one_done();
+
+ /*
+ * Wait for the kthread_stop() call.
+ */
+ while (!kthread_should_stop())
+ msleep(10);
+
+ return 0;
+}
+
+static void
+init_test_configurtion(void)
+{
+ /*
+ * Reset all data of all CPUs.
+ */
+ memset(per_cpu_test_data, 0, sizeof(per_cpu_test_data));
+
+ if (single_cpu_test)
+ cpumask_set_cpu(cpumask_first(cpu_online_mask),
+ &cpus_run_test_mask);
+ else
+ cpumask_and(&cpus_run_test_mask, cpu_online_mask,
+ cpu_online_mask);
+
+ if (test_repeat_count <= 0)
+ test_repeat_count = 1;
+
+ if (test_loop_count <= 0)
+ test_loop_count = 1;
+}
+
+static void do_concurrent_test(void)
+{
+ int cpu, ret;
+
+ /*
+ * Set some basic configurations plus sanity check.
+ */
+ init_test_configurtion();
+
+ /*
+ * Put on hold all workers.
+ */
+ down_write(&prepare_for_test_rwsem);
+
+ for_each_cpu(cpu, &cpus_run_test_mask) {
+ struct test_driver *t = &per_cpu_test_driver[cpu];
+
+ t->cpu = cpu;
+ t->task = kthread_run(test_func, t, "vmalloc_test/%d", cpu);
+
+ if (!IS_ERR(t->task))
+ /* Success. */
+ atomic_inc(&test_n_undone);
+ else
+ pr_err("Failed to start kthread for %d CPU\n", cpu);
+ }
+
+ /*
+ * Now let the workers do their job.
+ */
+ up_write(&prepare_for_test_rwsem);
+
+ /*
+ * Sleep quiet until all workers are done with 1 second
+ * interval. Since the test can take a lot of time we
+ * can run into a stack trace of the hung task. That is
+ * why we go with completion_timeout and HZ value.
+ */
+ do {
+ ret = wait_for_completion_timeout(&test_all_done_comp, HZ);
+ } while (!ret);
+
+ for_each_cpu(cpu, &cpus_run_test_mask) {
+ struct test_driver *t = &per_cpu_test_driver[cpu];
+ int i;
+
+ if (!IS_ERR(t->task))
+ kthread_stop(t->task);
+
+ for (i = 0; i < ARRAY_SIZE(test_case_array); i++) {
+ if (!((run_test_mask & (1 << i)) >> i))
+ continue;
+
+ pr_info(
+ "Summary: %s passed: %d failed: %d repeat: %d loops: %d avg: %llu usec\n",
+ test_case_array[i].test_name,
+ per_cpu_test_data[cpu][i].test_passed,
+ per_cpu_test_data[cpu][i].test_failed,
+ test_repeat_count, test_loop_count,
+ per_cpu_test_data[cpu][i].time);
+ }
+
+ pr_info("All test took CPU%d=%lu cycles\n",
+ cpu, t->stop - t->start);
+ }
+}
+
+static int vmalloc_test_init(void)
+{
+ do_concurrent_test();
+ return -EAGAIN; /* Fail will directly unload the module */
+}
+
+static void vmalloc_test_exit(void)
+{
+}
+
+module_init(vmalloc_test_init)
+module_exit(vmalloc_test_exit)
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Uladzislau Rezki");
+MODULE_DESCRIPTION("vmalloc test module");
generated by cgit v1.2.3 (git 2.39.1) at 2024-12-14 02:28:17 +0000