@@ -6,6 +6,7 @@ include $(RTE_SDK)/mk/rte.vars.mk
# library name
LIB = librte_timer.a
+CFLAGS += -DALLOW_EXPERIMENTAL_API
CFLAGS += $(WERROR_FLAGS) -I$(SRCDIR) -O3
LDLIBS += -lrte_eal
@@ -5,6 +5,7 @@
#include <string.h>
#include <stdio.h>
#include <stdint.h>
+#include <stdbool.h>
#include <inttypes.h>
#include <assert.h>
#include <sys/queue.h>
@@ -21,23 +22,27 @@
#include <rte_spinlock.h>
#include <rte_random.h>
#include <rte_pause.h>
+#include <rte_memzone.h>
+#include <rte_malloc.h>
#include "rte_timer.h"
-LIST_HEAD(rte_timer_list, rte_timer);
-
+/**
+ * Per-lcore info for timers.
+ */
struct priv_timer {
- struct rte_timer pending_head; /**< dummy timer instance to head up list */
+ struct rte_timer pending_head; /**< dummy timer to head up list */
rte_spinlock_t list_lock; /**< lock to protect list access */
/** per-core variable that true if a timer was updated on this
- * core since last reset of the variable */
+ * core since last reset of the variable
+ */
int updated;
/** track the current depth of the skiplist */
- unsigned curr_skiplist_depth;
+ unsigned int curr_skiplist_depth;
- unsigned prev_lcore; /**< used for lcore round robin */
+ unsigned int prev_lcore; /**< used for lcore round robin */
/** running timer on this lcore now */
struct rte_timer *running_tim;
@@ -48,33 +53,140 @@ struct priv_timer {
#endif
} __rte_cache_aligned;
-/** per-lcore private info for timers */
-static struct priv_timer priv_timer[RTE_MAX_LCORE];
+#define FL_ALLOCATED (1 << 0)
+struct rte_timer_data {
+ struct priv_timer priv_timer[RTE_MAX_LCORE];
+ uint8_t internal_flags;
+};
+
+#define RTE_MAX_DATA_ELS 64
+static struct rte_timer_data *rte_timer_data_arr;
+static uint32_t default_data_id; // id set to zero automatically
+static uint32_t rte_timer_subsystem_initialized;
/* when debug is enabled, store some statistics */
#ifdef RTE_LIBRTE_TIMER_DEBUG
-#define __TIMER_STAT_ADD(name, n) do { \
+#define __TIMER_STAT_ADD(data, name, n) do { \
unsigned __lcore_id = rte_lcore_id(); \
if (__lcore_id < RTE_MAX_LCORE) \
- priv_timer[__lcore_id].stats.name += (n); \
+ data->priv_timer[__lcore_id].stats.name += (n); \
} while(0)
#else
-#define __TIMER_STAT_ADD(name, n) do {} while(0)
+#define __TIMER_STAT_ADD(data, name, n) do {} while (0)
#endif
-/* Init the timer library. */
-void
+static inline int
+timer_data_valid(uint32_t id)
+{
+ return !!(rte_timer_data_arr[id].internal_flags & FL_ALLOCATED);
+}
+
+/* validate ID and retrieve timer data pointer, or return error value */
+#define TIMER_DATA_VALID_GET_OR_ERR_RET(id, timer_data, retval) do { \
+ if (id >= RTE_MAX_DATA_ELS || !timer_data_valid(id)) \
+ return retval; \
+ timer_data = &rte_timer_data_arr[id]; \
+} while (0)
+
+int __rte_experimental
+rte_timer_data_alloc(uint32_t *id_ptr)
+{
+ int i;
+ struct rte_timer_data *data;
+
+ if (!rte_timer_subsystem_initialized)
+ return -ENOMEM;
+
+ for (i = 0; i < RTE_MAX_DATA_ELS; i++) {
+ data = &rte_timer_data_arr[i];
+ if (!(data->internal_flags & FL_ALLOCATED)) {
+ data->internal_flags |= FL_ALLOCATED;
+
+ if (id_ptr)
+ *id_ptr = i;
+
+ return 0;
+ }
+ }
+
+ return -ENOSPC;
+}
+
+int __rte_experimental
+rte_timer_data_dealloc(uint32_t id)
+{
+ struct rte_timer_data *timer_data;
+ TIMER_DATA_VALID_GET_OR_ERR_RET(id, timer_data, -EINVAL);
+
+ timer_data->internal_flags &= ~(FL_ALLOCATED);
+
+ return 0;
+}
+
+/* Init the timer library. Allocate an array of timer data structs in shared
+ * memory, and allocate the zeroth entry for use with original timer
+ * APIs. Since the intersection of the sets of lcore ids in primary and
+ * secondary processes should be empty, the zeroth entry can be shared by
+ * multiple processes.
+ */
+int
rte_timer_subsystem_init(void)
{
- unsigned lcore_id;
+ const struct rte_memzone *mz;
+ struct rte_timer_data *data;
+ int i, lcore_id;
+ static const char *mz_name = "rte_timer_mz";
- /* since priv_timer is static, it's zeroed by default, so only init some
- * fields.
- */
- for (lcore_id = 0; lcore_id < RTE_MAX_LCORE; lcore_id ++) {
- rte_spinlock_init(&priv_timer[lcore_id].list_lock);
- priv_timer[lcore_id].prev_lcore = lcore_id;
+ if (rte_timer_subsystem_initialized)
+ return -EALREADY;
+
+ if (rte_eal_process_type() != RTE_PROC_PRIMARY) {
+ mz = rte_memzone_lookup(mz_name);
+ if (mz == NULL)
+ return -EEXIST;
+
+ rte_timer_data_arr = mz->addr;
+
+ rte_timer_data_arr[default_data_id].internal_flags |=
+ FL_ALLOCATED;
+
+ rte_timer_subsystem_initialized = 1;
+
+ return 0;
+ }
+
+ mz = rte_memzone_reserve_aligned(mz_name,
+ RTE_MAX_DATA_ELS * sizeof(*rte_timer_data_arr),
+ SOCKET_ID_ANY, 0, RTE_CACHE_LINE_SIZE);
+ if (mz == NULL)
+ return -ENOMEM;
+
+ rte_timer_data_arr = mz->addr;
+
+ for (i = 0; i < RTE_MAX_DATA_ELS; i++) {
+ data = &rte_timer_data_arr[i];
+
+ for (lcore_id = 0; lcore_id < RTE_MAX_LCORE; lcore_id++) {
+ rte_spinlock_init(
+ &data->priv_timer[lcore_id].list_lock);
+ data->priv_timer[lcore_id].prev_lcore = lcore_id;
+ }
}
+
+ rte_timer_data_arr[default_data_id].internal_flags |= FL_ALLOCATED;
+
+ rte_timer_subsystem_initialized = 1;
+
+ return 0;
+}
+
+void __rte_experimental
+rte_timer_subsystem_finalize(void)
+{
+ if (rte_timer_data_arr)
+ rte_free(rte_timer_data_arr);
+
+ rte_timer_subsystem_initialized = 0;
}
/* Initialize the timer handle tim for use */
@@ -95,7 +207,8 @@ rte_timer_init(struct rte_timer *tim)
*/
static int
timer_set_config_state(struct rte_timer *tim,
- union rte_timer_status *ret_prev_status)
+ union rte_timer_status *ret_prev_status,
+ struct rte_timer_data *data)
{
union rte_timer_status prev_status, status;
int success = 0;
@@ -113,7 +226,7 @@ timer_set_config_state(struct rte_timer *tim,
*/
if (prev_status.state == RTE_TIMER_RUNNING &&
(prev_status.owner != (uint16_t)lcore_id ||
- tim != priv_timer[lcore_id].running_tim))
+ tim != data->priv_timer[lcore_id].running_tim))
return -1;
/* timer is being configured on another core */
@@ -207,13 +320,13 @@ timer_get_skiplist_level(unsigned curr_depth)
*/
static void
timer_get_prev_entries(uint64_t time_val, unsigned tim_lcore,
- struct rte_timer **prev)
+ struct rte_timer **prev, struct rte_timer_data *data)
{
- unsigned lvl = priv_timer[tim_lcore].curr_skiplist_depth;
- prev[lvl] = &priv_timer[tim_lcore].pending_head;
- while(lvl != 0) {
+ unsigned int lvl = data->priv_timer[tim_lcore].curr_skiplist_depth;
+ prev[lvl] = &data->priv_timer[tim_lcore].pending_head;
+ while (lvl != 0) {
lvl--;
- prev[lvl] = prev[lvl+1];
+ prev[lvl] = prev[lvl + 1];
while (prev[lvl]->sl_next[lvl] &&
prev[lvl]->sl_next[lvl]->expire <= time_val)
prev[lvl] = prev[lvl]->sl_next[lvl];
@@ -226,14 +339,16 @@ timer_get_prev_entries(uint64_t time_val, unsigned tim_lcore,
*/
static void
timer_get_prev_entries_for_node(struct rte_timer *tim, unsigned tim_lcore,
- struct rte_timer **prev)
+ struct rte_timer **prev,
+ struct rte_timer_data *data)
{
int i;
/* to get a specific entry in the list, look for just lower than the time
* values, and then increment on each level individually if necessary
*/
- timer_get_prev_entries(tim->expire - 1, tim_lcore, prev);
- for (i = priv_timer[tim_lcore].curr_skiplist_depth - 1; i >= 0; i--) {
+ timer_get_prev_entries(tim->expire - 1, tim_lcore, prev, data);
+ for (i = data->priv_timer[tim_lcore].curr_skiplist_depth - 1; i >= 0;
+ i--) {
while (prev[i]->sl_next[i] != NULL &&
prev[i]->sl_next[i] != tim &&
prev[i]->sl_next[i]->expire <= tim->expire)
@@ -247,20 +362,21 @@ timer_get_prev_entries_for_node(struct rte_timer *tim, unsigned tim_lcore,
* timer must not be in a list
*/
static void
-timer_add(struct rte_timer *tim, unsigned int tim_lcore)
+timer_add(struct rte_timer *tim, unsigned int tim_lcore,
+ struct rte_timer_data *data)
{
unsigned lvl;
struct rte_timer *prev[MAX_SKIPLIST_DEPTH+1];
/* find where exactly this element goes in the list of elements
* for each depth. */
- timer_get_prev_entries(tim->expire, tim_lcore, prev);
+ timer_get_prev_entries(tim->expire, tim_lcore, prev, data);
/* now assign it a new level and add at that level */
const unsigned tim_level = timer_get_skiplist_level(
- priv_timer[tim_lcore].curr_skiplist_depth);
- if (tim_level == priv_timer[tim_lcore].curr_skiplist_depth)
- priv_timer[tim_lcore].curr_skiplist_depth++;
+ data->priv_timer[tim_lcore].curr_skiplist_depth);
+ if (tim_level == data->priv_timer[tim_lcore].curr_skiplist_depth)
+ data->priv_timer[tim_lcore].curr_skiplist_depth++;
lvl = tim_level;
while (lvl > 0) {
@@ -272,9 +388,10 @@ timer_add(struct rte_timer *tim, unsigned int tim_lcore)
prev[0]->sl_next[0] = tim;
/* save the lowest list entry into the expire field of the dummy hdr
- * NOTE: this is not atomic on 32-bit*/
- priv_timer[tim_lcore].pending_head.expire = priv_timer[tim_lcore].\
- pending_head.sl_next[0]->expire;
+ * NOTE: this is not atomic on 32-bit
+ */
+ data->priv_timer[tim_lcore].pending_head.expire =
+ data->priv_timer[tim_lcore].pending_head.sl_next[0]->expire;
}
/*
@@ -284,7 +401,7 @@ timer_add(struct rte_timer *tim, unsigned int tim_lcore)
*/
static void
timer_del(struct rte_timer *tim, union rte_timer_status prev_status,
- int local_is_locked)
+ int local_is_locked, struct rte_timer_data *data)
{
unsigned lcore_id = rte_lcore_id();
unsigned prev_owner = prev_status.owner;
@@ -295,30 +412,33 @@ timer_del(struct rte_timer *tim, union rte_timer_status prev_status,
* list; if it is on local core, we need to lock if we are not
* called from rte_timer_manage() */
if (prev_owner != lcore_id || !local_is_locked)
- rte_spinlock_lock(&priv_timer[prev_owner].list_lock);
+ rte_spinlock_lock(&data->priv_timer[prev_owner].list_lock);
/* save the lowest list entry into the expire field of the dummy hdr.
* NOTE: this is not atomic on 32-bit */
- if (tim == priv_timer[prev_owner].pending_head.sl_next[0])
- priv_timer[prev_owner].pending_head.expire =
+ if (tim == data->priv_timer[prev_owner].pending_head.sl_next[0])
+ data->priv_timer[prev_owner].pending_head.expire =
((tim->sl_next[0] == NULL) ? 0 : tim->sl_next[0]->expire);
/* adjust pointers from previous entries to point past this */
- timer_get_prev_entries_for_node(tim, prev_owner, prev);
- for (i = priv_timer[prev_owner].curr_skiplist_depth - 1; i >= 0; i--) {
+ timer_get_prev_entries_for_node(tim, prev_owner, prev, data);
+ i = data->priv_timer[prev_owner].curr_skiplist_depth - 1;
+ for ( ; i >= 0; i--) {
if (prev[i]->sl_next[i] == tim)
prev[i]->sl_next[i] = tim->sl_next[i];
}
/* in case we deleted last entry at a level, adjust down max level */
- for (i = priv_timer[prev_owner].curr_skiplist_depth - 1; i >= 0; i--)
- if (priv_timer[prev_owner].pending_head.sl_next[i] == NULL)
- priv_timer[prev_owner].curr_skiplist_depth --;
+ for (i = data->priv_timer[prev_owner].curr_skiplist_depth - 1; i >= 0;
+ i--)
+ if (data->priv_timer[prev_owner].pending_head.sl_next[i] ==
+ NULL)
+ data->priv_timer[prev_owner].curr_skiplist_depth--;
else
break;
if (prev_owner != lcore_id || !local_is_locked)
- rte_spinlock_unlock(&priv_timer[prev_owner].list_lock);
+ rte_spinlock_unlock(&data->priv_timer[prev_owner].list_lock);
}
/* Reset and start the timer associated with the timer handle (private func) */
@@ -326,7 +446,8 @@ static int
__rte_timer_reset(struct rte_timer *tim, uint64_t expire,
uint64_t period, unsigned tim_lcore,
rte_timer_cb_t fct, void *arg,
- int local_is_locked)
+ int local_is_locked,
+ struct rte_timer_data *data)
{
union rte_timer_status prev_status, status;
int ret;
@@ -337,9 +458,9 @@ __rte_timer_reset(struct rte_timer *tim, uint64_t expire,
if (lcore_id < RTE_MAX_LCORE) {
/* EAL thread with valid lcore_id */
tim_lcore = rte_get_next_lcore(
- priv_timer[lcore_id].prev_lcore,
+ data->priv_timer[lcore_id].prev_lcore,
0, 1);
- priv_timer[lcore_id].prev_lcore = tim_lcore;
+ data->priv_timer[lcore_id].prev_lcore = tim_lcore;
} else
/* non-EAL thread do not run rte_timer_manage(),
* so schedule the timer on the first enabled lcore. */
@@ -348,20 +469,20 @@ __rte_timer_reset(struct rte_timer *tim, uint64_t expire,
/* wait that the timer is in correct status before update,
* and mark it as being configured */
- ret = timer_set_config_state(tim, &prev_status);
+ ret = timer_set_config_state(tim, &prev_status, data);
if (ret < 0)
return -1;
- __TIMER_STAT_ADD(reset, 1);
+ __TIMER_STAT_ADD(data, reset, 1);
if (prev_status.state == RTE_TIMER_RUNNING &&
lcore_id < RTE_MAX_LCORE) {
- priv_timer[lcore_id].updated = 1;
+ data->priv_timer[lcore_id].updated = 1;
}
/* remove it from list */
if (prev_status.state == RTE_TIMER_PENDING) {
- timer_del(tim, prev_status, local_is_locked);
- __TIMER_STAT_ADD(pending, -1);
+ timer_del(tim, prev_status, local_is_locked, data);
+ __TIMER_STAT_ADD(data, pending, -1);
}
tim->period = period;
@@ -374,10 +495,10 @@ __rte_timer_reset(struct rte_timer *tim, uint64_t expire,
* we are not called from rte_timer_manage()
*/
if (tim_lcore != lcore_id || !local_is_locked)
- rte_spinlock_lock(&priv_timer[tim_lcore].list_lock);
+ rte_spinlock_lock(&data->priv_timer[tim_lcore].list_lock);
- __TIMER_STAT_ADD(pending, 1);
- timer_add(tim, tim_lcore);
+ __TIMER_STAT_ADD(data, pending, 1);
+ timer_add(tim, tim_lcore, data);
/* update state: as we are in CONFIG state, only us can modify
* the state so we don't need to use cmpset() here */
@@ -387,7 +508,7 @@ __rte_timer_reset(struct rte_timer *tim, uint64_t expire,
tim->status.u32 = status.u32;
if (tim_lcore != lcore_id || !local_is_locked)
- rte_spinlock_unlock(&priv_timer[tim_lcore].list_lock);
+ rte_spinlock_unlock(&data->priv_timer[tim_lcore].list_lock);
return 0;
}
@@ -395,11 +516,23 @@ __rte_timer_reset(struct rte_timer *tim, uint64_t expire,
/* Reset and start the timer associated with the timer handle tim */
int
rte_timer_reset(struct rte_timer *tim, uint64_t ticks,
- enum rte_timer_type type, unsigned tim_lcore,
- rte_timer_cb_t fct, void *arg)
+ enum rte_timer_type type, unsigned int tim_lcore,
+ rte_timer_cb_t fct, void *arg)
+{
+ return rte_timer_alt_reset(default_data_id, tim, ticks, type,
+ tim_lcore, fct, arg);
+}
+
+int __rte_experimental
+rte_timer_alt_reset(uint32_t timer_data_id, struct rte_timer *tim,
+ uint64_t ticks, enum rte_timer_type type,
+ unsigned int tim_lcore, rte_timer_cb_t fct, void *arg)
{
uint64_t cur_time = rte_get_timer_cycles();
uint64_t period;
+ struct rte_timer_data *timer_data;
+
+ TIMER_DATA_VALID_GET_OR_ERR_RET(timer_data_id, timer_data, -EINVAL);
if (unlikely((tim_lcore != (unsigned)LCORE_ID_ANY) &&
!(rte_lcore_is_enabled(tim_lcore) ||
@@ -412,7 +545,7 @@ rte_timer_reset(struct rte_timer *tim, uint64_t ticks,
period = 0;
return __rte_timer_reset(tim, cur_time + ticks, period, tim_lcore,
- fct, arg, 0);
+ fct, arg, 0, timer_data);
}
/* loop until rte_timer_reset() succeed */
@@ -430,26 +563,35 @@ rte_timer_reset_sync(struct rte_timer *tim, uint64_t ticks,
int
rte_timer_stop(struct rte_timer *tim)
{
+ return rte_timer_alt_stop(default_data_id, tim);
+}
+
+int __rte_experimental
+rte_timer_alt_stop(uint32_t timer_data_id, struct rte_timer *tim)
+{
union rte_timer_status prev_status, status;
unsigned lcore_id = rte_lcore_id();
int ret;
+ struct rte_timer_data *timer_data;
+
+ TIMER_DATA_VALID_GET_OR_ERR_RET(timer_data_id, timer_data, -EINVAL);
/* wait that the timer is in correct status before update,
* and mark it as being configured */
- ret = timer_set_config_state(tim, &prev_status);
+ ret = timer_set_config_state(tim, &prev_status, timer_data);
if (ret < 0)
return -1;
- __TIMER_STAT_ADD(stop, 1);
+ __TIMER_STAT_ADD(timer_data, stop, 1);
if (prev_status.state == RTE_TIMER_RUNNING &&
lcore_id < RTE_MAX_LCORE) {
- priv_timer[lcore_id].updated = 1;
+ timer_data->priv_timer[lcore_id].updated = 1;
}
/* remove it from list */
if (prev_status.state == RTE_TIMER_PENDING) {
- timer_del(tim, prev_status, 0);
- __TIMER_STAT_ADD(pending, -1);
+ timer_del(tim, prev_status, 0, timer_data);
+ __TIMER_STAT_ADD(timer_data, pending, -1);
}
/* mark timer as stopped */
@@ -486,13 +628,14 @@ void rte_timer_manage(void)
struct rte_timer *prev[MAX_SKIPLIST_DEPTH + 1];
uint64_t cur_time;
int i, ret;
+ struct rte_timer_data *data = &rte_timer_data_arr[default_data_id];
/* timer manager only runs on EAL thread with valid lcore_id */
assert(lcore_id < RTE_MAX_LCORE);
- __TIMER_STAT_ADD(manage, 1);
+ __TIMER_STAT_ADD(data, manage, 1);
/* optimize for the case where per-cpu list is empty */
- if (priv_timer[lcore_id].pending_head.sl_next[0] == NULL)
+ if (data->priv_timer[lcore_id].pending_head.sl_next[0] == NULL)
return;
cur_time = rte_get_timer_cycles();
@@ -500,32 +643,34 @@ void rte_timer_manage(void)
/* on 64-bit the value cached in the pending_head.expired will be
* updated atomically, so we can consult that for a quick check here
* outside the lock */
- if (likely(priv_timer[lcore_id].pending_head.expire > cur_time))
+ if (likely(data->priv_timer[lcore_id].pending_head.expire > cur_time))
return;
#endif
/* browse ordered list, add expired timers in 'expired' list */
- rte_spinlock_lock(&priv_timer[lcore_id].list_lock);
+ rte_spinlock_lock(&data->priv_timer[lcore_id].list_lock);
/* if nothing to do just unlock and return */
- if (priv_timer[lcore_id].pending_head.sl_next[0] == NULL ||
- priv_timer[lcore_id].pending_head.sl_next[0]->expire > cur_time) {
- rte_spinlock_unlock(&priv_timer[lcore_id].list_lock);
+ if (data->priv_timer[lcore_id].pending_head.sl_next[0] == NULL ||
+ data->priv_timer[lcore_id].pending_head.sl_next[0]->expire >
+ cur_time) {
+ rte_spinlock_unlock(&data->priv_timer[lcore_id].list_lock);
return;
}
/* save start of list of expired timers */
- tim = priv_timer[lcore_id].pending_head.sl_next[0];
+ tim = data->priv_timer[lcore_id].pending_head.sl_next[0];
/* break the existing list at current time point */
- timer_get_prev_entries(cur_time, lcore_id, prev);
- for (i = priv_timer[lcore_id].curr_skiplist_depth -1; i >= 0; i--) {
- if (prev[i] == &priv_timer[lcore_id].pending_head)
+ timer_get_prev_entries(cur_time, lcore_id, prev, data);
+ for (i = data->priv_timer[lcore_id].curr_skiplist_depth - 1; i >= 0;
+ i--) {
+ if (prev[i] == &data->priv_timer[lcore_id].pending_head)
continue;
- priv_timer[lcore_id].pending_head.sl_next[i] =
+ data->priv_timer[lcore_id].pending_head.sl_next[i] =
prev[i]->sl_next[i];
if (prev[i]->sl_next[i] == NULL)
- priv_timer[lcore_id].curr_skiplist_depth--;
+ data->priv_timer[lcore_id].curr_skiplist_depth--;
prev[i] ->sl_next[i] = NULL;
}
@@ -548,25 +693,25 @@ void rte_timer_manage(void)
}
/* update the next to expire timer value */
- priv_timer[lcore_id].pending_head.expire =
- (priv_timer[lcore_id].pending_head.sl_next[0] == NULL) ? 0 :
- priv_timer[lcore_id].pending_head.sl_next[0]->expire;
+ data->priv_timer[lcore_id].pending_head.expire =
+ (data->priv_timer[lcore_id].pending_head.sl_next[0] == NULL) ? 0 :
+ data->priv_timer[lcore_id].pending_head.sl_next[0]->expire;
- rte_spinlock_unlock(&priv_timer[lcore_id].list_lock);
+ rte_spinlock_unlock(&data->priv_timer[lcore_id].list_lock);
/* now scan expired list and call callbacks */
for (tim = run_first_tim; tim != NULL; tim = next_tim) {
next_tim = tim->sl_next[0];
- priv_timer[lcore_id].updated = 0;
- priv_timer[lcore_id].running_tim = tim;
+ data->priv_timer[lcore_id].updated = 0;
+ data->priv_timer[lcore_id].running_tim = tim;
/* execute callback function with list unlocked */
tim->f(tim, tim->arg);
- __TIMER_STAT_ADD(pending, -1);
+ __TIMER_STAT_ADD(data, pending, -1);
/* the timer was stopped or reloaded by the callback
* function, we have nothing to do here */
- if (priv_timer[lcore_id].updated == 1)
+ if (data->priv_timer[lcore_id].updated == 1)
continue;
if (tim->period == 0) {
@@ -578,33 +723,217 @@ void rte_timer_manage(void)
}
else {
/* keep it in list and mark timer as pending */
- rte_spinlock_lock(&priv_timer[lcore_id].list_lock);
+ rte_spinlock_lock(
+ &data->priv_timer[lcore_id].list_lock);
status.state = RTE_TIMER_PENDING;
- __TIMER_STAT_ADD(pending, 1);
+ __TIMER_STAT_ADD(data, pending, 1);
status.owner = (int16_t)lcore_id;
rte_wmb();
tim->status.u32 = status.u32;
__rte_timer_reset(tim, tim->expire + tim->period,
- tim->period, lcore_id, tim->f, tim->arg, 1);
- rte_spinlock_unlock(&priv_timer[lcore_id].list_lock);
+ tim->period, lcore_id, tim->f, tim->arg, 1,
+ data);
+ rte_spinlock_unlock(
+ &data->priv_timer[lcore_id].list_lock);
+ }
+ }
+ data->priv_timer[lcore_id].running_tim = NULL;
+}
+
+int __rte_experimental
+rte_timer_alt_manage(uint32_t timer_data_id,
+ unsigned int *poll_lcores,
+ int nb_poll_lcores,
+ rte_timer_alt_manage_cb_t f)
+{
+ union rte_timer_status status;
+ struct rte_timer *tim, *next_tim, **pprev;
+ struct rte_timer *run_first_tims[RTE_MAX_LCORE];
+ unsigned int this_lcore = rte_lcore_id();
+ struct rte_timer *prev[MAX_SKIPLIST_DEPTH + 1];
+ uint64_t cur_time;
+ int i, j, ret;
+ int nb_runlists = 0;
+ struct priv_timer *priv_timer;
+ uint32_t poll_lcore;
+ struct rte_timer_data *data;
+
+ TIMER_DATA_VALID_GET_OR_ERR_RET(timer_data_id, data, -EINVAL);
+
+ /* timer manager only runs on EAL thread with valid lcore_id */
+ assert(this_lcore < RTE_MAX_LCORE);
+
+ __TIMER_STAT_ADD(data, manage, 1);
+
+ if (poll_lcores == NULL) {
+ poll_lcores = (unsigned int []){rte_lcore_id()};
+ nb_poll_lcores = 1;
+ }
+
+ for (i = 0, poll_lcore = poll_lcores[i]; i < nb_poll_lcores;
+ poll_lcore = poll_lcores[++i]) {
+ priv_timer = &data->priv_timer[poll_lcore];
+
+ /* optimize for the case where per-cpu list is empty */
+ if (priv_timer->pending_head.sl_next[0] == NULL)
+ continue;
+ cur_time = rte_get_timer_cycles();
+
+#ifdef RTE_ARCH_64
+ /* on 64-bit the value cached in the pending_head.expired will
+ * be updated atomically, so we can consult that for a quick
+ * check here outside the lock
+ */
+ if (likely(priv_timer->pending_head.expire > cur_time))
+ continue;
+#endif
+
+ /* browse ordered list, add expired timers in 'expired' list */
+ rte_spinlock_lock(&priv_timer->list_lock);
+
+ /* if nothing to do just unlock and return */
+ if (priv_timer->pending_head.sl_next[0] == NULL ||
+ priv_timer->pending_head.sl_next[0]->expire > cur_time) {
+ rte_spinlock_unlock(&priv_timer->list_lock);
+ continue;
+ }
+
+ /* save start of list of expired timers */
+ tim = priv_timer->pending_head.sl_next[0];
+
+ /* break the existing list at current time point */
+ timer_get_prev_entries(cur_time, poll_lcore, prev, data);
+ for (j = priv_timer->curr_skiplist_depth - 1; j >= 0; j--) {
+ if (prev[j] == &priv_timer->pending_head)
+ continue;
+
+ priv_timer->pending_head.sl_next[j] =
+ prev[j]->sl_next[j];
+
+ if (prev[j]->sl_next[j] == NULL)
+ priv_timer->curr_skiplist_depth--;
+
+ prev[j]->sl_next[j] = NULL;
+ }
+
+ /* transition run-list from PENDING to RUNNING */
+ run_first_tims[nb_runlists] = tim;
+ pprev = &run_first_tims[nb_runlists];
+ nb_runlists++;
+
+ for ( ; tim != NULL; tim = next_tim) {
+ next_tim = tim->sl_next[0];
+
+ ret = timer_set_running_state(tim);
+ if (likely(ret == 0)) {
+ pprev = &tim->sl_next[0];
+ } else {
+ /* another core is trying to re-config this one,
+ * remove it from local expired list
+ */
+ *pprev = next_tim;
+ }
+ }
+
+ /* update the next to expire timer value */
+ priv_timer->pending_head.expire =
+ (priv_timer->pending_head.sl_next[0] == NULL) ? 0 :
+ priv_timer->pending_head.sl_next[0]->expire;
+
+ rte_spinlock_unlock(&priv_timer->list_lock);
+ }
+
+ /* Now process the run lists */
+ while (1) {
+ bool done = true;
+ uint64_t min_expire = UINT64_MAX;
+ int min_idx = 0;
+
+ /* Find the next oldest timer to process */
+ for (i = 0; i < nb_runlists; i++) {
+ tim = run_first_tims[i];
+
+ if (tim != NULL && tim->expire < min_expire) {
+ min_expire = tim->expire;
+ min_idx = i;
+ done = false;
+ }
+ }
+
+ if (done)
+ break;
+
+ tim = run_first_tims[min_idx];
+
+ /* Move down the runlist from which we picked a timer to
+ * execute
+ */
+ run_first_tims[min_idx] = run_first_tims[min_idx]->sl_next[0];
+
+ priv_timer->updated = 0;
+ priv_timer->running_tim = tim;
+
+ /* Call the provided callback function */
+ f(tim);
+
+ __TIMER_STAT_ADD(data, pending, -1);
+
+ /* the timer was stopped or reloaded by the callback
+ * function, we have nothing to do here
+ */
+ if (priv_timer->updated == 1)
+ continue;
+
+ if (tim->period == 0) {
+ /* remove from done list and mark timer as stopped */
+ status.state = RTE_TIMER_STOP;
+ status.owner = RTE_TIMER_NO_OWNER;
+ rte_wmb();
+ tim->status.u32 = status.u32;
+ } else {
+ /* keep it in list and mark timer as pending */
+ rte_spinlock_lock(
+ &data->priv_timer[this_lcore].list_lock);
+ status.state = RTE_TIMER_PENDING;
+ __TIMER_STAT_ADD(data, pending, 1);
+ status.owner = (int16_t)this_lcore;
+ rte_wmb();
+ tim->status.u32 = status.u32;
+ __rte_timer_reset(tim, tim->expire + tim->period,
+ tim->period, this_lcore, tim->f, tim->arg, 1,
+ data);
+ rte_spinlock_unlock(
+ &data->priv_timer[this_lcore].list_lock);
}
+
+ priv_timer->running_tim = NULL;
}
- priv_timer[lcore_id].running_tim = NULL;
+
+ return 0;
}
/* dump statistics about timers */
void rte_timer_dump_stats(FILE *f)
{
+ rte_timer_alt_dump_stats(default_data_id, f);
+}
+
+int __rte_experimental
+rte_timer_alt_dump_stats(uint32_t timer_data_id __rte_unused, FILE *f)
+{
#ifdef RTE_LIBRTE_TIMER_DEBUG
struct rte_timer_debug_stats sum;
unsigned lcore_id;
+ struct rte_timer_data *timer_data;
+
+ TIMER_DATA_VALID_GET_OR_ERR_RET(timer_data_id, data, -EINVAL);
memset(&sum, 0, sizeof(sum));
for (lcore_id = 0; lcore_id < RTE_MAX_LCORE; lcore_id++) {
- sum.reset += priv_timer[lcore_id].stats.reset;
- sum.stop += priv_timer[lcore_id].stats.stop;
- sum.manage += priv_timer[lcore_id].stats.manage;
- sum.pending += priv_timer[lcore_id].stats.pending;
+ sum.reset += data->priv_timer[lcore_id].stats.reset;
+ sum.stop += data->priv_timer[lcore_id].stats.stop;
+ sum.manage += data->priv_timer[lcore_id].stats.manage;
+ sum.pending += data->priv_timer[lcore_id].stats.pending;
}
fprintf(f, "Timer statistics:\n");
fprintf(f, " reset = %"PRIu64"\n", sum.reset);
@@ -614,4 +943,5 @@ void rte_timer_dump_stats(FILE *f)
#else
fprintf(f, "No timer statistics, RTE_LIBRTE_TIMER_DEBUG is disabled\n");
#endif
+ return 0;
}
@@ -39,6 +39,7 @@
#include <stddef.h>
#include <rte_common.h>
#include <rte_config.h>
+#include <rte_spinlock.h>
#ifdef __cplusplus
extern "C" {
@@ -132,12 +133,52 @@ struct rte_timer
#endif
/**
+ * @warning
+ * @b EXPERIMENTAL: this API may change without prior notice
+ *
+ * Allocate a timer data instance in shared memory to track a set of pending
+ * timer lists.
+ *
+ * @param id_ptr
+ * Pointer to variable into which to write the identifier of the allocated
+ * timer data instance.
+ *
+ * @return
+ * 0: Success
+ * -ENOSPC: maximum number of timer data instances already allocated
+ */
+int __rte_experimental rte_timer_data_alloc(uint32_t *id_ptr);
+
+/**
+ * @warning
+ * @b EXPERIMENTAL: this API may change without prior notice
+ *
+ * Deallocate a timer data instance.
+ *
+ * @param id
+ * Identifier of the timer data instance to deallocate.
+ *
+ * @return
+ * 0: Success
+ * -EINVAL: invalid timer data instance identifier
+ */
+int __rte_experimental rte_timer_data_dealloc(uint32_t id);
+
+/**
* Initialize the timer library.
*
* Initializes internal variables (list, locks and so on) for the RTE
* timer library.
*/
-void rte_timer_subsystem_init(void);
+int rte_timer_subsystem_init(void);
+
+/**
+ * @warning
+ * @b EXPERIMENTAL: this API may change without prior notice
+ *
+ * Free timer subsystem resources.
+ */
+void __rte_experimental rte_timer_subsystem_finalize(void);
/**
* Initialize a timer handle.
@@ -254,7 +295,6 @@ rte_timer_reset_sync(struct rte_timer *tim, uint64_t ticks,
*/
int rte_timer_stop(struct rte_timer *tim);
-
/**
* Loop until rte_timer_stop() succeeds.
*
@@ -302,6 +342,130 @@ void rte_timer_manage(void);
*/
void rte_timer_dump_stats(FILE *f);
+/**
+ * @warning
+ * @b EXPERIMENTAL: this API may change without prior notice
+ *
+ * This function is the same as rte_timer_reset(), except that it allows a
+ * caller to specify the rte_timer_data instance containing the list to which
+ * the timer should be added.
+ *
+ * @see rte_timer_reset()
+ *
+ * @param timer_data_id
+ * An identifier indicating which instance of timer data should be used for
+ * this operation.
+ * @param tim
+ * The timer handle.
+ * @param ticks
+ * The number of cycles (see rte_get_hpet_hz()) before the callback
+ * function is called.
+ * @param type
+ * The type can be either:
+ * - PERIODICAL: The timer is automatically reloaded after execution
+ * (returns to the PENDING state)
+ * - SINGLE: The timer is one-shot, that is, the timer goes to a
+ * STOPPED state after execution.
+ * @param tim_lcore
+ * The ID of the lcore where the timer callback function has to be
+ * executed. If tim_lcore is LCORE_ID_ANY, the timer library will
+ * launch it on a different core for each call (round-robin).
+ * @param fct
+ * The callback function of the timer. This parameter can be NULL if (and
+ * only if) rte_timer_alt_manage() will be used to manage this timer.
+ * @param arg
+ * The user argument of the callback function.
+ * @return
+ * - 0: Success; the timer is scheduled.
+ * - (-1): Timer is in the RUNNING or CONFIG state.
+ * - -EINVAL: invalid timer_data_id
+ */
+int __rte_experimental
+rte_timer_alt_reset(uint32_t timer_data_id, struct rte_timer *tim,
+ uint64_t ticks, enum rte_timer_type type,
+ unsigned int tim_lcore, rte_timer_cb_t fct, void *arg);
+
+/**
+ * @warning
+ * @b EXPERIMENTAL: this API may change without prior notice
+ *
+ * This function is the same as rte_timer_stop(), except that it allows a
+ * caller to specify the rte_timer_data instance containing the list from which
+ * this timer should be removed.
+ *
+ * @see rte_timer_stop()
+ *
+ * @param timer_data_id
+ * An identifier indicating which instance of timer data should be used for
+ * this operation.
+ * @param tim
+ * The timer handle.
+ * @return
+ * - 0: Success; the timer is stopped.
+ * - (-1): The timer is in the RUNNING or CONFIG state.
+ * - -EINVAL: invalid timer_data_id
+ */
+int __rte_experimental
+rte_timer_alt_stop(uint32_t timer_data_id, struct rte_timer *tim);
+
+/**
+ * Callback function type for rte_timer_alt_manage().
+ */
+typedef void (*rte_timer_alt_manage_cb_t)(void *);
+
+/**
+ * @warning
+ * @b EXPERIMENTAL: this API may change without prior notice
+ *
+ * Manage a set of timer lists and execute the specified callback function for
+ * all expired timers. This function is similar to rte_timer_manage(), except
+ * that it allows a caller to specify the timer_data instance that should
+ * be operated on, as well as a set of lcore IDs identifying which timer lists
+ * should be processed. Callback functions of individual timers are ignored.
+ *
+ * @see rte_timer_manage()
+ *
+ * @param timer_data_id
+ * An identifier indicating which instance of timer data should be used for
+ * this operation.
+ * @param poll_lcores
+ * An array of lcore ids identifying the timer lists that should be processed.
+ * NULL is allowed - if NULL, the timer list corresponding to the lcore
+ * calling this routine is processed (same as rte_timer_manage()).
+ * @param n_poll_lcores
+ * The size of the poll_lcores array. If 'poll_lcores' is NULL, this parameter
+ * is ignored.
+ * @param f
+ * The callback function which should be called for all expired timers.
+ * @return
+ * - 0: success
+ * - -EINVAL: invalid timer_data_id
+ */
+int __rte_experimental
+rte_timer_alt_manage(uint32_t timer_data_id, unsigned int *poll_lcores,
+ int n_poll_lcores, rte_timer_alt_manage_cb_t f);
+
+/**
+ * @warning
+ * @b EXPERIMENTAL: this API may change without prior notice
+ *
+ * This function is the same as rte_timer_dump_stats(), except that it allows
+ * the caller to specify the rte_timer_data instance that should be used.
+ *
+ * @see rte_timer_dump_stats()
+ *
+ * @param timer_data_id
+ * An identifier indicating which instance of timer data should be used for
+ * this operation.
+ * @param f
+ * A pointer to a file for output
+ * @return
+ * - 0: success
+ * - -EINVAL: invalid timer_data_id
+ */
+int __rte_experimental
+rte_timer_alt_dump_stats(uint32_t timer_data_id, FILE *f);
+
#ifdef __cplusplus
}
#endif
@@ -3,13 +3,30 @@ DPDK_2.0 {
rte_timer_dump_stats;
rte_timer_init;
- rte_timer_manage;
rte_timer_pending;
rte_timer_reset;
rte_timer_reset_sync;
rte_timer_stop;
rte_timer_stop_sync;
- rte_timer_subsystem_init;
local: *;
};
+
+DPDK_19.02 {
+ global:
+
+ rte_timer_manage;
+ rte_timer_subsystem_init;
+} DPDK_2.0;
+
+EXPERIMENTAL {
+ global:
+
+ rte_timer_alt_dump_stats;
+ rte_timer_alt_manage;
+ rte_timer_alt_reset;
+ rte_timer_alt_stop;
+ rte_timer_data_alloc;
+ rte_timer_data_dealloc;
+ rte_timer_subsystem_finalize;
+};