#include <rte_prefetch.h>
#include <rte_branch_prediction.h>
#include <rte_mbuf.h>
+#include <rte_bitmap.h>
#include "rte_sched.h"
-#include "rte_bitmap.h"
#include "rte_sched_common.h"
#include "rte_approx.h"
+#include "rte_reciprocal.h"
#ifdef __INTEL_COMPILER
#pragma warning(disable:2259) /* conversion may lose significant bits */
#ifdef RTE_SCHED_VECTOR
#include <rte_vect.h>
-#if defined(__SSE4__)
+#ifdef RTE_ARCH_X86
#define SCHED_VECTOR_SSE4
+#elif defined(RTE_MACHINE_CPUFLAG_NEON)
+#define SCHED_VECTOR_NEON
#endif
#endif
#define RTE_SCHED_PIPE_INVALID UINT32_MAX
#define RTE_SCHED_BMP_POS_INVALID UINT32_MAX
+/* Scaling for cycles_per_byte calculation
+ * Chosen so that minimum rate is 480 bit/sec
+ */
+#define RTE_SCHED_TIME_SHIFT 8
+
struct rte_sched_subport {
/* Token bucket (TB) */
uint64_t tb_time; /* time of last update */
uint64_t time_cpu_cycles; /* Current CPU time measured in CPU cyles */
uint64_t time_cpu_bytes; /* Current CPU time measured in bytes */
uint64_t time; /* Current NIC TX time measured in bytes */
- double cycles_per_byte; /* CPU cycles per byte */
+ struct rte_reciprocal inv_cycles_per_byte; /* CPU cycles per byte */
/* Scheduling loop detection */
uint32_t pipe_loop;
rte_sched_port_config(struct rte_sched_port_params *params)
{
struct rte_sched_port *port = NULL;
- uint32_t mem_size, bmp_mem_size, n_queues_per_port, i;
+ uint32_t mem_size, bmp_mem_size, n_queues_per_port, i, cycles_per_byte;
/* Check user parameters. Determine the amount of memory to allocate */
mem_size = rte_sched_port_get_memory_footprint(params);
port->time_cpu_cycles = rte_get_tsc_cycles();
port->time_cpu_bytes = 0;
port->time = 0;
- port->cycles_per_byte = ((double) rte_get_tsc_hz()) / ((double) params->rate);
+
+ cycles_per_byte = (rte_get_tsc_hz() << RTE_SCHED_TIME_SHIFT)
+ / params->rate;
+ port->inv_cycles_per_byte = rte_reciprocal_value(cycles_per_byte);
/* Scheduling loop detection */
port->pipe_loop = RTE_SCHED_PIPE_INVALID;
void
rte_sched_port_free(struct rte_sched_port *port)
{
- unsigned int queue;
+ uint32_t qindex;
+ uint32_t n_queues_per_port;
/* Check user parameters */
if (port == NULL)
return;
- /* Free enqueued mbufs */
- for (queue = 0; queue < RTE_SCHED_TRAFFIC_CLASSES_PER_PIPE; queue++) {
- struct rte_mbuf **mbufs = rte_sched_port_qbase(port, queue);
- unsigned int i;
+ n_queues_per_port = rte_sched_port_queues_per_port(port);
- for (i = 0; i < rte_sched_port_qsize(port, queue); i++)
- rte_pktmbuf_free(mbufs[i]);
+ /* Free enqueued mbufs */
+ for (qindex = 0; qindex < n_queues_per_port; qindex++) {
+ struct rte_mbuf **mbufs = rte_sched_port_qbase(port, qindex);
+ uint16_t qsize = rte_sched_port_qsize(port, qindex);
+ struct rte_sched_queue *queue = port->queue + qindex;
+ uint16_t qr = queue->qr & (qsize - 1);
+ uint16_t qw = queue->qw & (qsize - 1);
+
+ for (; qr != qw; qr = (qr + 1) & (qsize - 1))
+ rte_pktmbuf_free(mbufs[qr]);
}
rte_bitmap_free(port->bmp);
memcpy(stats, &s->stats, sizeof(struct rte_sched_subport_stats));
memset(&s->stats, 0, sizeof(struct rte_sched_subport_stats));
- /* Subport TC ovesubscription status */
+ /* Subport TC oversubscription status */
*tc_ov = s->tc_ov;
return 0;
s->stats.n_bytes_tc[tc_index] += pkt_len;
}
+#ifdef RTE_SCHED_RED
+static inline void
+rte_sched_port_update_subport_stats_on_drop(struct rte_sched_port *port,
+ uint32_t qindex,
+ struct rte_mbuf *pkt, uint32_t red)
+#else
static inline void
rte_sched_port_update_subport_stats_on_drop(struct rte_sched_port *port,
- uint32_t qindex,
- struct rte_mbuf *pkt, uint32_t red)
+ uint32_t qindex,
+ struct rte_mbuf *pkt, __rte_unused uint32_t red)
+#endif
{
struct rte_sched_subport *s = port->subport + (qindex / rte_sched_port_queues_per_subport(port));
uint32_t tc_index = (qindex >> 2) & 0x3;
qe->stats.n_bytes += pkt_len;
}
+#ifdef RTE_SCHED_RED
+static inline void
+rte_sched_port_update_queue_stats_on_drop(struct rte_sched_port *port,
+ uint32_t qindex,
+ struct rte_mbuf *pkt, uint32_t red)
+#else
static inline void
rte_sched_port_update_queue_stats_on_drop(struct rte_sched_port *port,
- uint32_t qindex,
- struct rte_mbuf *pkt, uint32_t red)
+ uint32_t qindex,
+ struct rte_mbuf *pkt, __rte_unused uint32_t red)
+#endif
{
struct rte_sched_queue_extra *qe = port->queue_extra + qindex;
uint32_t pkt_len = pkt->pkt_len;
return 1;
}
+#elif defined(SCHED_VECTOR_NEON)
+
+static inline int
+grinder_pipe_exists(struct rte_sched_port *port, uint32_t base_pipe)
+{
+ uint32x4_t index, pipes;
+ uint32_t *pos = (uint32_t *)port->grinder_base_bmp_pos;
+
+ index = vmovq_n_u32(base_pipe);
+ pipes = vld1q_u32(pos);
+ if (!vminvq_u32(veorq_u32(pipes, index)))
+ return 1;
+
+ pipes = vld1q_u32(pos + 4);
+ if (!vminvq_u32(veorq_u32(pipes, index)))
+ return 1;
+
+ return 0;
+}
+
#else
static inline int
{
uint64_t cycles = rte_get_tsc_cycles();
uint64_t cycles_diff = cycles - port->time_cpu_cycles;
- double bytes_diff = ((double) cycles_diff) / port->cycles_per_byte;
+ uint64_t bytes_diff;
+
+ /* Compute elapsed time in bytes */
+ bytes_diff = rte_reciprocal_divide(cycles_diff << RTE_SCHED_TIME_SHIFT,
+ port->inv_cycles_per_byte);
/* Advance port time */
port->time_cpu_cycles = cycles;
- port->time_cpu_bytes += (uint64_t) bytes_diff;
+ port->time_cpu_bytes += bytes_diff;
if (port->time < port->time_cpu_bytes)
port->time = port->time_cpu_bytes;
git.droids-corp.org / dpdk.git / blobdiff