summaryrefslogtreecommitdiff
path: root/lib
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2023-11-02 05:15:42 +0300
committerLinus Torvalds <torvalds@linux-foundation.org>2023-11-02 05:15:42 +0300
commit05bf73aa27ba89474763cea7b9cd2626eda61e01 (patch)
tree0430a2d85df344f59030ac518a696a63139bfafd /lib
parent1b10d2c8c6219bfc86d8c7d53a4f97a0a706d1ba (diff)
parent4758560fa268cecfa1144f015aa9f2525d164b7e (diff)
downloadlinux-05bf73aa27ba89474763cea7b9cd2626eda61e01.tar.xz
Merge tag 'probes-v6.7' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace
Pull probes updates from Masami Hiramatsu: "Cleanups: - kprobes: Fixes typo in kprobes samples - tracing/eprobes: Remove 'break' after return kretprobe/fprobe performance improvements: - lib: Introduce new `objpool`, which is a high performance lockless object queue. This uses per-cpu ring array to allocate/release objects from the pre-allocated object pool. Since the index of ring array is a 32bit sequential counter, we can retry to push/pop the object pointer from the ring without lock (as seq-lock does) - lib: Add an objpool test module to test the functionality and evaluate the performance under some circumstances - kprobes/fprobe: Improve kretprobe and rethook scalability performance with objpool. This improves both legacy kretprobe and fprobe exit handler (which is based on rethook) to be scalable on SMP systems. Even with 8-threads parallel test, it shows a great scalability improvement - Remove unneeded freelist.h which is replaced by objpool - objpool: Add maintainers entry for the objpool - objpool: Fix to remove unused include header lines" * tag 'probes-v6.7' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace: kprobes: unused header files removed MAINTAINERS: objpool added kprobes: freelist.h removed kprobes: kretprobe scalability improvement lib: objpool test module added lib: objpool added: ring-array based lockless MPMC tracing/eprobe: drop unneeded breaks samples: kprobes: Fixes a typo
Diffstat (limited to 'lib')
-rw-r--r--lib/Kconfig.debug11
-rw-r--r--lib/Makefile4
-rw-r--r--lib/objpool.c280
-rw-r--r--lib/test_objpool.c690
4 files changed, 984 insertions, 1 deletions
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 40b77c437a74..cc7d53d9dc01 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -2954,6 +2954,17 @@ config TEST_CLOCKSOURCE_WATCHDOG
If unsure, say N.
+config TEST_OBJPOOL
+ tristate "Test module for correctness and stress of objpool"
+ default n
+ depends on m && DEBUG_KERNEL
+ help
+ This builds the "test_objpool" module that should be used for
+ correctness verification and concurrent testings of objects
+ allocation and reclamation.
+
+ If unsure, say N.
+
endif # RUNTIME_TESTING_MENU
config ARCH_USE_MEMTEST
diff --git a/lib/Makefile b/lib/Makefile
index 1b311c7fd32b..9e0972f7b764 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -34,7 +34,7 @@ lib-y := ctype.o string.o vsprintf.o cmdline.o \
is_single_threaded.o plist.o decompress.o kobject_uevent.o \
earlycpio.o seq_buf.o siphash.o dec_and_lock.o \
nmi_backtrace.o win_minmax.o memcat_p.o \
- buildid.o
+ buildid.o objpool.o
lib-$(CONFIG_PRINTK) += dump_stack.o
lib-$(CONFIG_SMP) += cpumask.o
@@ -107,6 +107,8 @@ obj-$(CONFIG_KPROBES_SANITY_TEST) += test_kprobes.o
obj-$(CONFIG_TEST_REF_TRACKER) += test_ref_tracker.o
CFLAGS_test_fprobe.o += $(CC_FLAGS_FTRACE)
obj-$(CONFIG_FPROBE_SANITY_TEST) += test_fprobe.o
+obj-$(CONFIG_TEST_OBJPOOL) += test_objpool.o
+
#
# CFLAGS for compiling floating point code inside the kernel. x86/Makefile turns
# off the generation of FPU/SSE* instructions for kernel proper but FPU_FLAGS
diff --git a/lib/objpool.c b/lib/objpool.c
new file mode 100644
index 000000000000..ce0087f64400
--- /dev/null
+++ b/lib/objpool.c
@@ -0,0 +1,280 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/objpool.h>
+#include <linux/slab.h>
+#include <linux/vmalloc.h>
+#include <linux/atomic.h>
+#include <linux/irqflags.h>
+#include <linux/cpumask.h>
+#include <linux/log2.h>
+
+/*
+ * objpool: ring-array based lockless MPMC/FIFO queues
+ *
+ * Copyright: wuqiang.matt@bytedance.com,mhiramat@kernel.org
+ */
+
+/* initialize percpu objpool_slot */
+static int
+objpool_init_percpu_slot(struct objpool_head *pool,
+ struct objpool_slot *slot,
+ int nodes, void *context,
+ objpool_init_obj_cb objinit)
+{
+ void *obj = (void *)&slot->entries[pool->capacity];
+ int i;
+
+ /* initialize elements of percpu objpool_slot */
+ slot->mask = pool->capacity - 1;
+
+ for (i = 0; i < nodes; i++) {
+ if (objinit) {
+ int rc = objinit(obj, context);
+ if (rc)
+ return rc;
+ }
+ slot->entries[slot->tail & slot->mask] = obj;
+ obj = obj + pool->obj_size;
+ slot->tail++;
+ slot->last = slot->tail;
+ pool->nr_objs++;
+ }
+
+ return 0;
+}
+
+/* allocate and initialize percpu slots */
+static int
+objpool_init_percpu_slots(struct objpool_head *pool, int nr_objs,
+ void *context, objpool_init_obj_cb objinit)
+{
+ int i, cpu_count = 0;
+
+ for (i = 0; i < pool->nr_cpus; i++) {
+
+ struct objpool_slot *slot;
+ int nodes, size, rc;
+
+ /* skip the cpu node which could never be present */
+ if (!cpu_possible(i))
+ continue;
+
+ /* compute how many objects to be allocated with this slot */
+ nodes = nr_objs / num_possible_cpus();
+ if (cpu_count < (nr_objs % num_possible_cpus()))
+ nodes++;
+ cpu_count++;
+
+ size = struct_size(slot, entries, pool->capacity) +
+ pool->obj_size * nodes;
+
+ /*
+ * here we allocate percpu-slot & objs together in a single
+ * allocation to make it more compact, taking advantage of
+ * warm caches and TLB hits. in default vmalloc is used to
+ * reduce the pressure of kernel slab system. as we know,
+ * mimimal size of vmalloc is one page since vmalloc would
+ * always align the requested size to page size
+ */
+ if (pool->gfp & GFP_ATOMIC)
+ slot = kmalloc_node(size, pool->gfp, cpu_to_node(i));
+ else
+ slot = __vmalloc_node(size, sizeof(void *), pool->gfp,
+ cpu_to_node(i), __builtin_return_address(0));
+ if (!slot)
+ return -ENOMEM;
+ memset(slot, 0, size);
+ pool->cpu_slots[i] = slot;
+
+ /* initialize the objpool_slot of cpu node i */
+ rc = objpool_init_percpu_slot(pool, slot, nodes, context, objinit);
+ if (rc)
+ return rc;
+ }
+
+ return 0;
+}
+
+/* cleanup all percpu slots of the object pool */
+static void objpool_fini_percpu_slots(struct objpool_head *pool)
+{
+ int i;
+
+ if (!pool->cpu_slots)
+ return;
+
+ for (i = 0; i < pool->nr_cpus; i++)
+ kvfree(pool->cpu_slots[i]);
+ kfree(pool->cpu_slots);
+}
+
+/* initialize object pool and pre-allocate objects */
+int objpool_init(struct objpool_head *pool, int nr_objs, int object_size,
+ gfp_t gfp, void *context, objpool_init_obj_cb objinit,
+ objpool_fini_cb release)
+{
+ int rc, capacity, slot_size;
+
+ /* check input parameters */
+ if (nr_objs <= 0 || nr_objs > OBJPOOL_NR_OBJECT_MAX ||
+ object_size <= 0 || object_size > OBJPOOL_OBJECT_SIZE_MAX)
+ return -EINVAL;
+
+ /* align up to unsigned long size */
+ object_size = ALIGN(object_size, sizeof(long));
+
+ /* calculate capacity of percpu objpool_slot */
+ capacity = roundup_pow_of_two(nr_objs);
+ if (!capacity)
+ return -EINVAL;
+
+ /* initialize objpool pool */
+ memset(pool, 0, sizeof(struct objpool_head));
+ pool->nr_cpus = nr_cpu_ids;
+ pool->obj_size = object_size;
+ pool->capacity = capacity;
+ pool->gfp = gfp & ~__GFP_ZERO;
+ pool->context = context;
+ pool->release = release;
+ slot_size = pool->nr_cpus * sizeof(struct objpool_slot);
+ pool->cpu_slots = kzalloc(slot_size, pool->gfp);
+ if (!pool->cpu_slots)
+ return -ENOMEM;
+
+ /* initialize per-cpu slots */
+ rc = objpool_init_percpu_slots(pool, nr_objs, context, objinit);
+ if (rc)
+ objpool_fini_percpu_slots(pool);
+ else
+ refcount_set(&pool->ref, pool->nr_objs + 1);
+
+ return rc;
+}
+EXPORT_SYMBOL_GPL(objpool_init);
+
+/* adding object to slot, abort if the slot was already full */
+static inline int
+objpool_try_add_slot(void *obj, struct objpool_head *pool, int cpu)
+{
+ struct objpool_slot *slot = pool->cpu_slots[cpu];
+ uint32_t head, tail;
+
+ /* loading tail and head as a local snapshot, tail first */
+ tail = READ_ONCE(slot->tail);
+
+ do {
+ head = READ_ONCE(slot->head);
+ /* fault caught: something must be wrong */
+ WARN_ON_ONCE(tail - head > pool->nr_objs);
+ } while (!try_cmpxchg_acquire(&slot->tail, &tail, tail + 1));
+
+ /* now the tail position is reserved for the given obj */
+ WRITE_ONCE(slot->entries[tail & slot->mask], obj);
+ /* update sequence to make this obj available for pop() */
+ smp_store_release(&slot->last, tail + 1);
+
+ return 0;
+}
+
+/* reclaim an object to object pool */
+int objpool_push(void *obj, struct objpool_head *pool)
+{
+ unsigned long flags;
+ int rc;
+
+ /* disable local irq to avoid preemption & interruption */
+ raw_local_irq_save(flags);
+ rc = objpool_try_add_slot(obj, pool, raw_smp_processor_id());
+ raw_local_irq_restore(flags);
+
+ return rc;
+}
+EXPORT_SYMBOL_GPL(objpool_push);
+
+/* try to retrieve object from slot */
+static inline void *objpool_try_get_slot(struct objpool_head *pool, int cpu)
+{
+ struct objpool_slot *slot = pool->cpu_slots[cpu];
+ /* load head snapshot, other cpus may change it */
+ uint32_t head = smp_load_acquire(&slot->head);
+
+ while (head != READ_ONCE(slot->last)) {
+ void *obj;
+
+ /* obj must be retrieved before moving forward head */
+ obj = READ_ONCE(slot->entries[head & slot->mask]);
+
+ /* move head forward to mark it's consumption */
+ if (try_cmpxchg_release(&slot->head, &head, head + 1))
+ return obj;
+ }
+
+ return NULL;
+}
+
+/* allocate an object from object pool */
+void *objpool_pop(struct objpool_head *pool)
+{
+ void *obj = NULL;
+ unsigned long flags;
+ int i, cpu;
+
+ /* disable local irq to avoid preemption & interruption */
+ raw_local_irq_save(flags);
+
+ cpu = raw_smp_processor_id();
+ for (i = 0; i < num_possible_cpus(); i++) {
+ obj = objpool_try_get_slot(pool, cpu);
+ if (obj)
+ break;
+ cpu = cpumask_next_wrap(cpu, cpu_possible_mask, -1, 1);
+ }
+ raw_local_irq_restore(flags);
+
+ return obj;
+}
+EXPORT_SYMBOL_GPL(objpool_pop);
+
+/* release whole objpool forcely */
+void objpool_free(struct objpool_head *pool)
+{
+ if (!pool->cpu_slots)
+ return;
+
+ /* release percpu slots */
+ objpool_fini_percpu_slots(pool);
+
+ /* call user's cleanup callback if provided */
+ if (pool->release)
+ pool->release(pool, pool->context);
+}
+EXPORT_SYMBOL_GPL(objpool_free);
+
+/* drop the allocated object, rather reclaim it to objpool */
+int objpool_drop(void *obj, struct objpool_head *pool)
+{
+ if (!obj || !pool)
+ return -EINVAL;
+
+ if (refcount_dec_and_test(&pool->ref)) {
+ objpool_free(pool);
+ return 0;
+ }
+
+ return -EAGAIN;
+}
+EXPORT_SYMBOL_GPL(objpool_drop);
+
+/* drop unused objects and defref objpool for releasing */
+void objpool_fini(struct objpool_head *pool)
+{
+ int count = 1; /* extra ref for objpool itself */
+
+ /* drop all remained objects from objpool */
+ while (objpool_pop(pool))
+ count++;
+
+ if (refcount_sub_and_test(count, &pool->ref))
+ objpool_free(pool);
+}
+EXPORT_SYMBOL_GPL(objpool_fini);
diff --git a/lib/test_objpool.c b/lib/test_objpool.c
new file mode 100644
index 000000000000..a94078402138
--- /dev/null
+++ b/lib/test_objpool.c
@@ -0,0 +1,690 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Test module for lockless object pool
+ *
+ * Copyright: wuqiang.matt@bytedance.com
+ */
+
+#include <linux/errno.h>
+#include <linux/module.h>
+#include <linux/moduleparam.h>
+#include <linux/completion.h>
+#include <linux/kthread.h>
+#include <linux/slab.h>
+#include <linux/vmalloc.h>
+#include <linux/delay.h>
+#include <linux/hrtimer.h>
+#include <linux/objpool.h>
+
+#define OT_NR_MAX_BULK (16)
+
+/* memory usage */
+struct ot_mem_stat {
+ atomic_long_t alloc;
+ atomic_long_t free;
+};
+
+/* object allocation results */
+struct ot_obj_stat {
+ unsigned long nhits;
+ unsigned long nmiss;
+};
+
+/* control & results per testcase */
+struct ot_data {
+ struct rw_semaphore start;
+ struct completion wait;
+ struct completion rcu;
+ atomic_t nthreads ____cacheline_aligned_in_smp;
+ atomic_t stop ____cacheline_aligned_in_smp;
+ struct ot_mem_stat kmalloc;
+ struct ot_mem_stat vmalloc;
+ struct ot_obj_stat objects;
+ u64 duration;
+};
+
+/* testcase */
+struct ot_test {
+ int async; /* synchronous or asynchronous */
+ int mode; /* only mode 0 supported */
+ int objsz; /* object size */
+ int duration; /* ms */
+ int delay; /* ms */
+ int bulk_normal;
+ int bulk_irq;
+ unsigned long hrtimer; /* ms */
+ const char *name;
+ struct ot_data data;
+};
+
+/* per-cpu worker */
+struct ot_item {
+ struct objpool_head *pool; /* pool head */
+ struct ot_test *test; /* test parameters */
+
+ void (*worker)(struct ot_item *item, int irq);
+
+ /* hrtimer control */
+ ktime_t hrtcycle;
+ struct hrtimer hrtimer;
+
+ int bulk[2]; /* for thread and irq */
+ int delay;
+ u32 niters;
+
+ /* summary per thread */
+ struct ot_obj_stat stat[2]; /* thread and irq */
+ u64 duration;
+};
+
+/*
+ * memory leakage checking
+ */
+
+static void *ot_kzalloc(struct ot_test *test, long size)
+{
+ void *ptr = kzalloc(size, GFP_KERNEL);
+
+ if (ptr)
+ atomic_long_add(size, &test->data.kmalloc.alloc);
+ return ptr;
+}
+
+static void ot_kfree(struct ot_test *test, void *ptr, long size)
+{
+ if (!ptr)
+ return;
+ atomic_long_add(size, &test->data.kmalloc.free);
+ kfree(ptr);
+}
+
+static void ot_mem_report(struct ot_test *test)
+{
+ long alloc, free;
+
+ pr_info("memory allocation summary for %s\n", test->name);
+
+ alloc = atomic_long_read(&test->data.kmalloc.alloc);
+ free = atomic_long_read(&test->data.kmalloc.free);
+ pr_info(" kmalloc: %lu - %lu = %lu\n", alloc, free, alloc - free);
+
+ alloc = atomic_long_read(&test->data.vmalloc.alloc);
+ free = atomic_long_read(&test->data.vmalloc.free);
+ pr_info(" vmalloc: %lu - %lu = %lu\n", alloc, free, alloc - free);
+}
+
+/* user object instance */
+struct ot_node {
+ void *owner;
+ unsigned long data;
+ unsigned long refs;
+ unsigned long payload[32];
+};
+
+/* user objpool manager */
+struct ot_context {
+ struct objpool_head pool; /* objpool head */
+ struct ot_test *test; /* test parameters */
+ void *ptr; /* user pool buffer */
+ unsigned long size; /* buffer size */
+ struct rcu_head rcu;
+};
+
+static DEFINE_PER_CPU(struct ot_item, ot_pcup_items);
+
+static int ot_init_data(struct ot_data *data)
+{
+ memset(data, 0, sizeof(*data));
+ init_rwsem(&data->start);
+ init_completion(&data->wait);
+ init_completion(&data->rcu);
+ atomic_set(&data->nthreads, 1);
+
+ return 0;
+}
+
+static int ot_init_node(void *nod, void *context)
+{
+ struct ot_context *sop = context;
+ struct ot_node *on = nod;
+
+ on->owner = &sop->pool;
+ return 0;
+}
+
+static enum hrtimer_restart ot_hrtimer_handler(struct hrtimer *hrt)
+{
+ struct ot_item *item = container_of(hrt, struct ot_item, hrtimer);
+ struct ot_test *test = item->test;
+
+ if (atomic_read_acquire(&test->data.stop))
+ return HRTIMER_NORESTART;
+
+ /* do bulk-testings for objects pop/push */
+ item->worker(item, 1);
+
+ hrtimer_forward(hrt, hrt->base->get_time(), item->hrtcycle);
+ return HRTIMER_RESTART;
+}
+
+static void ot_start_hrtimer(struct ot_item *item)
+{
+ if (!item->test->hrtimer)
+ return;
+ hrtimer_start(&item->hrtimer, item->hrtcycle, HRTIMER_MODE_REL);
+}
+
+static void ot_stop_hrtimer(struct ot_item *item)
+{
+ if (!item->test->hrtimer)
+ return;
+ hrtimer_cancel(&item->hrtimer);
+}
+
+static int ot_init_hrtimer(struct ot_item *item, unsigned long hrtimer)
+{
+ struct hrtimer *hrt = &item->hrtimer;
+
+ if (!hrtimer)
+ return -ENOENT;
+
+ item->hrtcycle = ktime_set(0, hrtimer * 1000000UL);
+ hrtimer_init(hrt, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+ hrt->function = ot_hrtimer_handler;
+ return 0;
+}
+
+static int ot_init_cpu_item(struct ot_item *item,
+ struct ot_test *test,
+ struct objpool_head *pool,
+ void (*worker)(struct ot_item *, int))
+{
+ memset(item, 0, sizeof(*item));
+ item->pool = pool;
+ item->test = test;
+ item->worker = worker;
+
+ item->bulk[0] = test->bulk_normal;
+ item->bulk[1] = test->bulk_irq;
+ item->delay = test->delay;
+
+ /* initialize hrtimer */
+ ot_init_hrtimer(item, item->test->hrtimer);
+ return 0;
+}
+
+static int ot_thread_worker(void *arg)
+{
+ struct ot_item *item = arg;
+ struct ot_test *test = item->test;
+ ktime_t start;
+
+ atomic_inc(&test->data.nthreads);
+ down_read(&test->data.start);
+ up_read(&test->data.start);
+ start = ktime_get();
+ ot_start_hrtimer(item);
+ do {
+ if (atomic_read_acquire(&test->data.stop))
+ break;
+ /* do bulk-testings for objects pop/push */
+ item->worker(item, 0);
+ } while (!kthread_should_stop());
+ ot_stop_hrtimer(item);
+ item->duration = (u64) ktime_us_delta(ktime_get(), start);
+ if (atomic_dec_and_test(&test->data.nthreads))
+ complete(&test->data.wait);
+
+ return 0;
+}
+
+static void ot_perf_report(struct ot_test *test, u64 duration)
+{
+ struct ot_obj_stat total, normal = {0}, irq = {0};
+ int cpu, nthreads = 0;
+
+ pr_info("\n");
+ pr_info("Testing summary for %s\n", test->name);
+
+ for_each_possible_cpu(cpu) {
+ struct ot_item *item = per_cpu_ptr(&ot_pcup_items, cpu);
+ if (!item->duration)
+ continue;
+ normal.nhits += item->stat[0].nhits;
+ normal.nmiss += item->stat[0].nmiss;
+ irq.nhits += item->stat[1].nhits;
+ irq.nmiss += item->stat[1].nmiss;
+ pr_info("CPU: %d duration: %lluus\n", cpu, item->duration);
+ pr_info("\tthread:\t%16lu hits \t%16lu miss\n",
+ item->stat[0].nhits, item->stat[0].nmiss);
+ pr_info("\tirq: \t%16lu hits \t%16lu miss\n",
+ item->stat[1].nhits, item->stat[1].nmiss);
+ pr_info("\ttotal: \t%16lu hits \t%16lu miss\n",
+ item->stat[0].nhits + item->stat[1].nhits,
+ item->stat[0].nmiss + item->stat[1].nmiss);
+ nthreads++;
+ }
+
+ total.nhits = normal.nhits + irq.nhits;
+ total.nmiss = normal.nmiss + irq.nmiss;
+
+ pr_info("ALL: \tnthreads: %d duration: %lluus\n", nthreads, duration);
+ pr_info("SUM: \t%16lu hits \t%16lu miss\n",
+ total.nhits, total.nmiss);
+
+ test->data.objects = total;
+ test->data.duration = duration;
+}
+
+/*
+ * synchronous test cases for objpool manipulation
+ */
+
+/* objpool manipulation for synchronous mode (percpu objpool) */
+static struct ot_context *ot_init_sync_m0(struct ot_test *test)
+{
+ struct ot_context *sop = NULL;
+ int max = num_possible_cpus() << 3;
+ gfp_t gfp = GFP_KERNEL;
+
+ sop = (struct ot_context *)ot_kzalloc(test, sizeof(*sop));
+ if (!sop)
+ return NULL;
+ sop->test = test;
+ if (test->objsz < 512)
+ gfp = GFP_ATOMIC;
+
+ if (objpool_init(&sop->pool, max, test->objsz,
+ gfp, sop, ot_init_node, NULL)) {
+ ot_kfree(test, sop, sizeof(*sop));
+ return NULL;
+ }
+ WARN_ON(max != sop->pool.nr_objs);
+
+ return sop;
+}
+
+static void ot_fini_sync(struct ot_context *sop)
+{
+ objpool_fini(&sop->pool);
+ ot_kfree(sop->test, sop, sizeof(*sop));
+}
+
+struct {
+ struct ot_context * (*init)(struct ot_test *oc);
+ void (*fini)(struct ot_context *sop);
+} g_ot_sync_ops[] = {
+ {.init = ot_init_sync_m0, .fini = ot_fini_sync},
+};
+
+/*
+ * synchronous test cases: performance mode
+ */
+
+static void ot_bulk_sync(struct ot_item *item, int irq)
+{
+ struct ot_node *nods[OT_NR_MAX_BULK];
+ int i;
+
+ for (i = 0; i < item->bulk[irq]; i++)
+ nods[i] = objpool_pop(item->pool);
+
+ if (!irq && (item->delay || !(++(item->niters) & 0x7FFF)))
+ msleep(item->delay);
+
+ while (i-- > 0) {
+ struct ot_node *on = nods[i];
+ if (on) {
+ on->refs++;
+ objpool_push(on, item->pool);
+ item->stat[irq].nhits++;
+ } else {
+ item->stat[irq].nmiss++;
+ }
+ }
+}
+
+static int ot_start_sync(struct ot_test *test)
+{
+ struct ot_context *sop;
+ ktime_t start;
+ u64 duration;
+ unsigned long timeout;
+ int cpu;
+
+ /* initialize objpool for syncrhonous testcase */
+ sop = g_ot_sync_ops[test->mode].init(test);
+ if (!sop)
+ return -ENOMEM;
+
+ /* grab rwsem to block testing threads */
+ down_write(&test->data.start);
+
+ for_each_possible_cpu(cpu) {
+ struct ot_item *item = per_cpu_ptr(&ot_pcup_items, cpu);
+ struct task_struct *work;
+
+ ot_init_cpu_item(item, test, &sop->pool, ot_bulk_sync);
+
+ /* skip offline cpus */
+ if (!cpu_online(cpu))
+ continue;
+
+ work = kthread_create_on_node(ot_thread_worker, item,
+ cpu_to_node(cpu), "ot_worker_%d", cpu);
+ if (IS_ERR(work)) {
+ pr_err("failed to create thread for cpu %d\n", cpu);
+ } else {
+ kthread_bind(work, cpu);
+ wake_up_process(work);
+ }
+ }
+
+ /* wait a while to make sure all threads waiting at start line */
+ msleep(20);
+
+ /* in case no threads were created: memory insufficient ? */
+ if (atomic_dec_and_test(&test->data.nthreads))
+ complete(&test->data.wait);
+
+ // sched_set_fifo_low(current);
+
+ /* start objpool testing threads */
+ start = ktime_get();
+ up_write(&test->data.start);
+
+ /* yeild cpu to worker threads for duration ms */
+ timeout = msecs_to_jiffies(test->duration);
+ schedule_timeout_interruptible(timeout);
+
+ /* tell workers threads to quit */
+ atomic_set_release(&test->data.stop, 1);
+
+ /* wait all workers threads finish and quit */
+ wait_for_completion(&test->data.wait);
+ duration = (u64) ktime_us_delta(ktime_get(), start);
+
+ /* cleanup objpool */
+ g_ot_sync_ops[test->mode].fini(sop);
+
+ /* report testing summary and performance results */
+ ot_perf_report(test, duration);
+
+ /* report memory allocation summary */
+ ot_mem_report(test);
+
+ return 0;
+}
+
+/*
+ * asynchronous test cases: pool lifecycle controlled by refcount
+ */
+
+static void ot_fini_async_rcu(struct rcu_head *rcu)
+{
+ struct ot_context *sop = container_of(rcu, struct ot_context, rcu);
+ struct ot_test *test = sop->test;
+
+ /* here all cpus are aware of the stop event: test->data.stop = 1 */
+ WARN_ON(!atomic_read_acquire(&test->data.stop));
+
+ objpool_fini(&sop->pool);
+ complete(&test->data.rcu);
+}
+
+static void ot_fini_async(struct ot_context *sop)
+{
+ /* make sure the stop event is acknowledged by all cores */
+ call_rcu(&sop->rcu, ot_fini_async_rcu);
+}
+
+static int ot_objpool_release(struct objpool_head *head, void *context)
+{
+ struct ot_context *sop = context;
+
+ WARN_ON(!head || !sop || head != &sop->pool);
+
+ /* do context cleaning if needed */
+ if (sop)
+ ot_kfree(sop->test, sop, sizeof(*sop));
+
+ return 0;
+}
+
+static struct ot_context *ot_init_async_m0(struct ot_test *test)
+{
+ struct ot_context *sop = NULL;
+ int max = num_possible_cpus() << 3;
+ gfp_t gfp = GFP_KERNEL;
+
+ sop = (struct ot_context *)ot_kzalloc(test, sizeof(*sop));
+ if (!sop)
+ return NULL;
+ sop->test = test;
+ if (test->objsz < 512)
+ gfp = GFP_ATOMIC;
+
+ if (objpool_init(&sop->pool, max, test->objsz, gfp, sop,
+ ot_init_node, ot_objpool_release)) {
+ ot_kfree(test, sop, sizeof(*sop));
+ return NULL;
+ }
+ WARN_ON(max != sop->pool.nr_objs);
+
+ return sop;
+}
+
+struct {
+ struct ot_context * (*init)(struct ot_test *oc);
+ void (*fini)(struct ot_context *sop);
+} g_ot_async_ops[] = {
+ {.init = ot_init_async_m0, .fini = ot_fini_async},
+};
+
+static void ot_nod_recycle(struct ot_node *on, struct objpool_head *pool,
+ int release)
+{
+ struct ot_context *sop;
+
+ on->refs++;
+
+ if (!release) {
+ /* push object back to opjpool for reuse */
+ objpool_push(on, pool);
+ return;
+ }
+
+ sop = container_of(pool, struct ot_context, pool);
+ WARN_ON(sop != pool->context);
+
+ /* unref objpool with nod removed forever */
+ objpool_drop(on, pool);
+}
+
+static void ot_bulk_async(struct ot_item *item, int irq)
+{
+ struct ot_test *test = item->test;
+ struct ot_node *nods[OT_NR_MAX_BULK];
+ int i, stop;
+
+ for (i = 0; i < item->bulk[irq]; i++)
+ nods[i] = objpool_pop(item->pool);
+
+ if (!irq) {
+ if (item->delay || !(++(item->niters) & 0x7FFF))
+ msleep(item->delay);
+ get_cpu();
+ }
+
+ stop = atomic_read_acquire(&test->data.stop);
+
+ /* drop all objects and deref objpool */
+ while (i-- > 0) {
+ struct ot_node *on = nods[i];
+
+ if (on) {
+ on->refs++;
+ ot_nod_recycle(on, item->pool, stop);
+ item->stat[irq].nhits++;
+ } else {
+ item->stat[irq].nmiss++;
+ }
+ }
+
+ if (!irq)
+ put_cpu();
+}
+
+static int ot_start_async(struct ot_test *test)
+{
+ struct ot_context *sop;
+ ktime_t start;
+ u64 duration;
+ unsigned long timeout;
+ int cpu;
+
+ /* initialize objpool for syncrhonous testcase */
+ sop = g_ot_async_ops[test->mode].init(test);
+ if (!sop)
+ return -ENOMEM;
+
+ /* grab rwsem to block testing threads */
+ down_write(&test->data.start);
+
+ for_each_possible_cpu(cpu) {
+ struct ot_item *item = per_cpu_ptr(&ot_pcup_items, cpu);
+ struct task_struct *work;
+
+ ot_init_cpu_item(item, test, &sop->pool, ot_bulk_async);
+
+ /* skip offline cpus */
+ if (!cpu_online(cpu))
+ continue;
+
+ work = kthread_create_on_node(ot_thread_worker, item,
+ cpu_to_node(cpu), "ot_worker_%d", cpu);
+ if (IS_ERR(work)) {
+ pr_err("failed to create thread for cpu %d\n", cpu);
+ } else {
+ kthread_bind(work, cpu);
+ wake_up_process(work);
+ }
+ }
+
+ /* wait a while to make sure all threads waiting at start line */
+ msleep(20);
+
+ /* in case no threads were created: memory insufficient ? */
+ if (atomic_dec_and_test(&test->data.nthreads))
+ complete(&test->data.wait);
+
+ /* start objpool testing threads */
+ start = ktime_get();
+ up_write(&test->data.start);
+
+ /* yeild cpu to worker threads for duration ms */
+ timeout = msecs_to_jiffies(test->duration);
+ schedule_timeout_interruptible(timeout);
+
+ /* tell workers threads to quit */
+ atomic_set_release(&test->data.stop, 1);
+
+ /* do async-finalization */
+ g_ot_async_ops[test->mode].fini(sop);
+
+ /* wait all workers threads finish and quit */
+ wait_for_completion(&test->data.wait);
+ duration = (u64) ktime_us_delta(ktime_get(), start);
+
+ /* assure rcu callback is triggered */
+ wait_for_completion(&test->data.rcu);
+
+ /*
+ * now we are sure that objpool is finalized either
+ * by rcu callback or by worker threads
+ */
+
+ /* report testing summary and performance results */
+ ot_perf_report(test, duration);
+
+ /* report memory allocation summary */
+ ot_mem_report(test);
+
+ return 0;
+}
+
+/*
+ * predefined testing cases:
+ * synchronous case / overrun case / async case
+ *
+ * async: synchronous or asynchronous testing
+ * mode: only mode 0 supported
+ * objsz: object size
+ * duration: int, total test time in ms
+ * delay: int, delay (in ms) between each iteration
+ * bulk_normal: int, repeat times for thread worker
+ * bulk_irq: int, repeat times for irq consumer
+ * hrtimer: unsigned long, hrtimer intervnal in ms
+ * name: char *, tag for current test ot_item
+ */
+
+#define NODE_COMPACT sizeof(struct ot_node)
+#define NODE_VMALLOC (512)
+
+struct ot_test g_testcases[] = {
+
+ /* sync & normal */
+ {0, 0, NODE_COMPACT, 1000, 0, 1, 0, 0, "sync: percpu objpool"},
+ {0, 0, NODE_VMALLOC, 1000, 0, 1, 0, 0, "sync: percpu objpool from vmalloc"},
+
+ /* sync & hrtimer */
+ {0, 0, NODE_COMPACT, 1000, 0, 1, 1, 4, "sync & hrtimer: percpu objpool"},
+ {0, 0, NODE_VMALLOC, 1000, 0, 1, 1, 4, "sync & hrtimer: percpu objpool from vmalloc"},
+
+ /* sync & overrun */
+ {0, 0, NODE_COMPACT, 1000, 0, 16, 0, 0, "sync overrun: percpu objpool"},
+ {0, 0, NODE_VMALLOC, 1000, 0, 16, 0, 0, "sync overrun: percpu objpool from vmalloc"},
+
+ /* async mode */
+ {1, 0, NODE_COMPACT, 1000, 100, 1, 0, 0, "async: percpu objpool"},
+ {1, 0, NODE_VMALLOC, 1000, 100, 1, 0, 0, "async: percpu objpool from vmalloc"},
+
+ /* async + hrtimer mode */
+ {1, 0, NODE_COMPACT, 1000, 0, 4, 4, 4, "async & hrtimer: percpu objpool"},
+ {1, 0, NODE_VMALLOC, 1000, 0, 4, 4, 4, "async & hrtimer: percpu objpool from vmalloc"},
+};
+
+static int __init ot_mod_init(void)
+{
+ int i;
+
+ /* perform testings */
+ for (i = 0; i < ARRAY_SIZE(g_testcases); i++) {
+ ot_init_data(&g_testcases[i].data);
+ if (g_testcases[i].async)
+ ot_start_async(&g_testcases[i]);
+ else
+ ot_start_sync(&g_testcases[i]);
+ }
+
+ /* show tests summary */
+ pr_info("\n");
+ pr_info("Summary of testcases:\n");
+ for (i = 0; i < ARRAY_SIZE(g_testcases); i++) {
+ pr_info(" duration: %lluus \thits: %10lu \tmiss: %10lu \t%s\n",
+ g_testcases[i].data.duration, g_testcases[i].data.objects.nhits,
+ g_testcases[i].data.objects.nmiss, g_testcases[i].name);
+ }
+
+ return -EAGAIN;
+}
+
+static void __exit ot_mod_exit(void)
+{
+}
+
+module_init(ot_mod_init);
+module_exit(ot_mod_exit);
+
+MODULE_LICENSE("GPL"); \ No newline at end of file