Once configured, the device can then be made ready for use by calling the
``rte_rawdev_start()`` API.
+Performing Data Copies
+~~~~~~~~~~~~~~~~~~~~~~~
+
+To perform data copies using IOAT rawdev devices, the functions
+``rte_ioat_enqueue_copy()`` and ``rte_ioat_do_copies()`` should be used.
+Once copies have been completed, the completion will be reported back when
+the application calls ``rte_ioat_completed_copies()``.
+
+The ``rte_ioat_enqueue_copy()`` function enqueues a single copy to the
+device ring for copying at a later point. The parameters to that function
+include the physical addresses of both the source and destination buffers,
+as well as two "handles" to be returned to the user when the copy is
+completed. These handles can be arbitrary values, but two are provided so
+that the library can track handles for both source and destination on
+behalf of the user, e.g. virtual addresses for the buffers, or mbuf
+pointers if packet data is being copied.
+
+While the ``rte_ioat_enqueue_copy()`` function enqueues a copy operation on
+the device ring, the copy will not actually be performed until after the
+application calls the ``rte_ioat_do_copies()`` function. This function
+informs the device hardware of the elements enqueued on the ring, and the
+device will begin to process them. It is expected that, for efficiency
+reasons, a burst of operations will be enqueued to the device via multiple
+enqueue calls between calls to the ``rte_ioat_do_copies()`` function.
+
+The following code from ``test_ioat_rawdev.c`` demonstrates how to enqueue
+a burst of copies to the device and start the hardware processing of them:
+
+.. code-block:: C
+
+ struct rte_mbuf *srcs[32], *dsts[32];
+ unsigned int j;
+
+ for (i = 0; i < RTE_DIM(srcs); i++) {
+ char *src_data;
+
+ srcs[i] = rte_pktmbuf_alloc(pool);
+ dsts[i] = rte_pktmbuf_alloc(pool);
+ srcs[i]->data_len = srcs[i]->pkt_len = length;
+ dsts[i]->data_len = dsts[i]->pkt_len = length;
+ src_data = rte_pktmbuf_mtod(srcs[i], char *);
+
+ for (j = 0; j < length; j++)
+ src_data[j] = rand() & 0xFF;
+
+ if (rte_ioat_enqueue_copy(dev_id,
+ srcs[i]->buf_iova + srcs[i]->data_off,
+ dsts[i]->buf_iova + dsts[i]->data_off,
+ length,
+ (uintptr_t)srcs[i],
+ (uintptr_t)dsts[i],
+ 0 /* nofence */) != 1) {
+ printf("Error with rte_ioat_enqueue_copy for buffer %u\n",
+ i);
+ return -1;
+ }
+ }
+ rte_ioat_do_copies(dev_id);
+
+To retrieve information about completed copies, the API
+``rte_ioat_completed_copies()`` should be used. This API will return to the
+application a set of completion handles passed in when the relevant copies
+were enqueued.
+
+The following code from ``test_ioat_rawdev.c`` shows the test code
+retrieving information about the completed copies and validating the data
+is correct before freeing the data buffers using the returned handles:
+
+.. code-block:: C
+
+ if (rte_ioat_completed_copies(dev_id, 64, (void *)completed_src,
+ (void *)completed_dst) != RTE_DIM(srcs)) {
+ printf("Error with rte_ioat_completed_copies\n");
+ return -1;
+ }
+ for (i = 0; i < RTE_DIM(srcs); i++) {
+ char *src_data, *dst_data;
+
+ if (completed_src[i] != srcs[i]) {
+ printf("Error with source pointer %u\n", i);
+ return -1;
+ }
+ if (completed_dst[i] != dsts[i]) {
+ printf("Error with dest pointer %u\n", i);
+ return -1;
+ }
+
+ src_data = rte_pktmbuf_mtod(srcs[i], char *);
+ dst_data = rte_pktmbuf_mtod(dsts[i], char *);
+ for (j = 0; j < length; j++)
+ if (src_data[j] != dst_data[j]) {
+ printf("Error with copy of packet %u, byte %u\n",
+ i, j);
+ return -1;
+ }
+ rte_pktmbuf_free(srcs[i]);
+ rte_pktmbuf_free(dsts[i]);
+ }
+
+
Querying Device Statistics
~~~~~~~~~~~~~~~~~~~~~~~~~~~
LDLIBS += -lrte_eal -lrte_rawdev
LDLIBS += -lrte_pci -lrte_bus_pci
+LDLIBS += -lrte_mbuf -lrte_mempool
# library version
LIBABIVER := 1
* Copyright(c) 2019 Intel Corporation
*/
+#include <unistd.h>
#include <inttypes.h>
+#include <rte_mbuf.h>
#include "rte_rawdev.h"
#include "rte_ioat_rawdev.h"
int ioat_rawdev_test(uint16_t dev_id); /* pre-define to keep compiler happy */
+static struct rte_mempool *pool;
+
+static int
+test_enqueue_copies(int dev_id)
+{
+ const unsigned int length = 1024;
+ unsigned int i;
+
+ do {
+ struct rte_mbuf *src, *dst;
+ char *src_data, *dst_data;
+ struct rte_mbuf *completed[2] = {0};
+
+ /* test doing a single copy */
+ src = rte_pktmbuf_alloc(pool);
+ dst = rte_pktmbuf_alloc(pool);
+ src->data_len = src->pkt_len = length;
+ dst->data_len = dst->pkt_len = length;
+ src_data = rte_pktmbuf_mtod(src, char *);
+ dst_data = rte_pktmbuf_mtod(dst, char *);
+
+ for (i = 0; i < length; i++)
+ src_data[i] = rand() & 0xFF;
+
+ if (rte_ioat_enqueue_copy(dev_id,
+ src->buf_iova + src->data_off,
+ dst->buf_iova + dst->data_off,
+ length,
+ (uintptr_t)src,
+ (uintptr_t)dst,
+ 0 /* no fence */) != 1) {
+ printf("Error with rte_ioat_enqueue_copy\n");
+ return -1;
+ }
+ rte_ioat_do_copies(dev_id);
+ usleep(10);
+
+ if (rte_ioat_completed_copies(dev_id, 1, (void *)&completed[0],
+ (void *)&completed[1]) != 1) {
+ printf("Error with rte_ioat_completed_copies\n");
+ return -1;
+ }
+ if (completed[0] != src || completed[1] != dst) {
+ printf("Error with completions: got (%p, %p), not (%p,%p)\n",
+ completed[0], completed[1], src, dst);
+ return -1;
+ }
+
+ for (i = 0; i < length; i++)
+ if (dst_data[i] != src_data[i]) {
+ printf("Data mismatch at char %u\n", i);
+ return -1;
+ }
+ rte_pktmbuf_free(src);
+ rte_pktmbuf_free(dst);
+ } while (0);
+
+ /* test doing multiple copies */
+ do {
+ struct rte_mbuf *srcs[32], *dsts[32];
+ struct rte_mbuf *completed_src[64];
+ struct rte_mbuf *completed_dst[64];
+ unsigned int j;
+
+ for (i = 0; i < RTE_DIM(srcs); i++) {
+ char *src_data;
+
+ srcs[i] = rte_pktmbuf_alloc(pool);
+ dsts[i] = rte_pktmbuf_alloc(pool);
+ srcs[i]->data_len = srcs[i]->pkt_len = length;
+ dsts[i]->data_len = dsts[i]->pkt_len = length;
+ src_data = rte_pktmbuf_mtod(srcs[i], char *);
+
+ for (j = 0; j < length; j++)
+ src_data[j] = rand() & 0xFF;
+
+ if (rte_ioat_enqueue_copy(dev_id,
+ srcs[i]->buf_iova + srcs[i]->data_off,
+ dsts[i]->buf_iova + dsts[i]->data_off,
+ length,
+ (uintptr_t)srcs[i],
+ (uintptr_t)dsts[i],
+ 0 /* nofence */) != 1) {
+ printf("Error with rte_ioat_enqueue_copy for buffer %u\n",
+ i);
+ return -1;
+ }
+ }
+ rte_ioat_do_copies(dev_id);
+ usleep(100);
+
+ if (rte_ioat_completed_copies(dev_id, 64, (void *)completed_src,
+ (void *)completed_dst) != RTE_DIM(srcs)) {
+ printf("Error with rte_ioat_completed_copies\n");
+ return -1;
+ }
+ for (i = 0; i < RTE_DIM(srcs); i++) {
+ char *src_data, *dst_data;
+
+ if (completed_src[i] != srcs[i]) {
+ printf("Error with source pointer %u\n", i);
+ return -1;
+ }
+ if (completed_dst[i] != dsts[i]) {
+ printf("Error with dest pointer %u\n", i);
+ return -1;
+ }
+
+ src_data = rte_pktmbuf_mtod(srcs[i], char *);
+ dst_data = rte_pktmbuf_mtod(dsts[i], char *);
+ for (j = 0; j < length; j++)
+ if (src_data[j] != dst_data[j]) {
+ printf("Error with copy of packet %u, byte %u\n",
+ i, j);
+ return -1;
+ }
+ rte_pktmbuf_free(srcs[i]);
+ rte_pktmbuf_free(dsts[i]);
+ }
+
+ } while (0);
+
+ return 0;
+}
+
int
ioat_rawdev_test(uint16_t dev_id)
{
return -1;
}
+ pool = rte_pktmbuf_pool_create("TEST_IOAT_POOL",
+ 256, /* n == num elements */
+ 32, /* cache size */
+ 0, /* priv size */
+ 2048, /* data room size */
+ info.socket_id);
+ if (pool == NULL) {
+ printf("Error with mempool creation\n");
+ return -1;
+ }
+
/* allocate memory for xstats names and values */
nb_xstats = rte_rawdev_xstats_names_get(dev_id, NULL, 0);
goto err;
}
- rte_rawdev_xstats_get(dev_id, ids, stats, nb_xstats);
- for (i = 0; i < nb_xstats; i++)
- printf("%s: %"PRIu64" ", snames[i].name, stats[i]);
+ /* run the test cases */
+ for (i = 0; i < 100; i++) {
+ unsigned int j;
+
+ if (test_enqueue_copies(dev_id) != 0)
+ goto err;
+
+ rte_rawdev_xstats_get(dev_id, ids, stats, nb_xstats);
+ for (j = 0; j < nb_xstats; j++)
+ printf("%s: %"PRIu64" ", snames[j].name, stats[j]);
+ printf("\r");
+ }
printf("\n");
+ rte_mempool_free(pool);
free(snames);
free(stats);
free(ids);
return 0;
err:
+ rte_mempool_free(pool);
free(snames);
free(stats);
free(ids);
build = dpdk_conf.has('RTE_ARCH_X86')
sources = files('ioat_rawdev.c',
'ioat_rawdev_test.c')
-deps += ['rawdev', 'bus_pci']
+deps += ['rawdev', 'bus_pci', 'mbuf']
install_headers('rte_ioat_rawdev.h',
'rte_ioat_spec.h')
*/
#include <x86intrin.h>
+#include <rte_atomic.h>
#include <rte_memory.h>
#include <rte_memzone.h>
+#include <rte_prefetch.h>
#include <rte_ioat_spec.h>
/** Name of the device driver */
struct rte_ioat_generic_hw_desc *desc_ring;
__m128i *hdls; /* completion handles for returning to user */
+
+ unsigned short next_read;
+ unsigned short next_write;
+
/* some statistics for tracking, if added/changed update xstats fns*/
uint64_t enqueue_failed __rte_cache_aligned;
uint64_t enqueued;
volatile uint64_t status __rte_cache_aligned;
};
-#endif
+/**
+ * Enqueue a copy operation onto the ioat device
+ *
+ * This queues up a copy operation to be performed by hardware, but does not
+ * trigger hardware to begin that operation.
+ *
+ * @param dev_id
+ * The rawdev device id of the ioat instance
+ * @param src
+ * The physical address of the source buffer
+ * @param dst
+ * The physical address of the destination buffer
+ * @param length
+ * The length of the data to be copied
+ * @param src_hdl
+ * An opaque handle for the source data, to be returned when this operation
+ * has been completed and the user polls for the completion details
+ * @param dst_hdl
+ * An opaque handle for the destination data, to be returned when this
+ * operation has been completed and the user polls for the completion details
+ * @param fence
+ * A flag parameter indicating that hardware should not begin to perform any
+ * subsequently enqueued copy operations until after this operation has
+ * completed
+ * @return
+ * Number of operations enqueued, either 0 or 1
+ */
+static inline int
+rte_ioat_enqueue_copy(int dev_id, phys_addr_t src, phys_addr_t dst,
+ unsigned int length, uintptr_t src_hdl, uintptr_t dst_hdl,
+ int fence)
+{
+ struct rte_ioat_rawdev *ioat = rte_rawdevs[dev_id].dev_private;
+ unsigned short read = ioat->next_read;
+ unsigned short write = ioat->next_write;
+ unsigned short mask = ioat->ring_size - 1;
+ unsigned short space = mask + read - write;
+ struct rte_ioat_generic_hw_desc *desc;
+
+ if (space == 0) {
+ ioat->enqueue_failed++;
+ return 0;
+ }
+
+ ioat->next_write = write + 1;
+ write &= mask;
+
+ desc = &ioat->desc_ring[write];
+ desc->size = length;
+ /* set descriptor write-back every 16th descriptor */
+ desc->u.control_raw = (uint32_t)((!!fence << 4) | (!(write & 0xF)) << 3);
+ desc->src_addr = src;
+ desc->dest_addr = dst;
+
+ ioat->hdls[write] = _mm_set_epi64((__m64)((uint64_t)dst_hdl),
+ (__m64)((uint64_t)src_hdl));
+ rte_prefetch0(&ioat->desc_ring[ioat->next_write & mask]);
+
+ ioat->enqueued++;
+ return 1;
+}
+
+/**
+ * Trigger hardware to begin performing enqueued copy operations
+ *
+ * This API is used to write the "doorbell" to the hardware to trigger it
+ * to begin the copy operations previously enqueued by rte_ioat_enqueue_copy()
+ *
+ * @param dev_id
+ * The rawdev device id of the ioat instance
+ */
+static inline void
+rte_ioat_do_copies(int dev_id)
+{
+ struct rte_ioat_rawdev *ioat = rte_rawdevs[dev_id].dev_private;
+ ioat->desc_ring[(ioat->next_write - 1) & (ioat->ring_size - 1)].u
+ .control.completion_update = 1;
+ rte_compiler_barrier();
+ ioat->regs->dmacount = ioat->next_write;
+ ioat->started = ioat->enqueued;
+}
+
+/**
+ * @internal
+ * Returns the index of the last completed operation.
+ */
+static inline int
+rte_ioat_get_last_completed(struct rte_ioat_rawdev *ioat, int *error)
+{
+ uint64_t status = ioat->status;
+
+ /* lower 3 bits indicate "transfer status" : active, idle, halted.
+ * We can ignore bit 0.
+ */
+ *error = status & (RTE_IOAT_CHANSTS_SUSPENDED | RTE_IOAT_CHANSTS_ARMED);
+ return (status - ioat->ring_addr) >> 6;
+}
+
+/**
+ * Returns details of copy operations that have been completed
+ *
+ * Returns to the caller the user-provided "handles" for the copy operations
+ * which have been completed by the hardware, and not already returned by
+ * a previous call to this API.
+ *
+ * @param dev_id
+ * The rawdev device id of the ioat instance
+ * @param max_copies
+ * The number of entries which can fit in the src_hdls and dst_hdls
+ * arrays, i.e. max number of completed operations to report
+ * @param src_hdls
+ * Array to hold the source handle parameters of the completed copies
+ * @param dst_hdls
+ * Array to hold the destination handle parameters of the completed copies
+ * @return
+ * -1 on error, with rte_errno set appropriately.
+ * Otherwise number of completed operations i.e. number of entries written
+ * to the src_hdls and dst_hdls array parameters.
+ */
+static inline int
+rte_ioat_completed_copies(int dev_id, uint8_t max_copies,
+ uintptr_t *src_hdls, uintptr_t *dst_hdls)
+{
+ struct rte_ioat_rawdev *ioat = rte_rawdevs[dev_id].dev_private;
+ unsigned short mask = (ioat->ring_size - 1);
+ unsigned short read = ioat->next_read;
+ unsigned short end_read, count;
+ int error;
+ int i = 0;
+
+ end_read = (rte_ioat_get_last_completed(ioat, &error) + 1) & mask;
+ count = (end_read - (read & mask)) & mask;
+
+ if (error) {
+ rte_errno = EIO;
+ return -1;
+ }
+
+ if (count > max_copies)
+ count = max_copies;
+
+ for (; i < count - 1; i += 2, read += 2) {
+ __m128i hdls0 = _mm_load_si128(&ioat->hdls[read & mask]);
+ __m128i hdls1 = _mm_load_si128(&ioat->hdls[(read + 1) & mask]);
+
+ _mm_storeu_si128((void *)&src_hdls[i],
+ _mm_unpacklo_epi64(hdls0, hdls1));
+ _mm_storeu_si128((void *)&dst_hdls[i],
+ _mm_unpackhi_epi64(hdls0, hdls1));
+ }
+ for (; i < count; i++, read++) {
+ uintptr_t *hdls = (void *)&ioat->hdls[read & mask];
+ src_hdls[i] = hdls[0];
+ dst_hdls[i] = hdls[1];
+ }
+
+ ioat->next_read = read;
+ ioat->completed += count;
+ return count;
+}
+
+#endif /* _RTE_IOAT_RAWDEV_H_ */
git.droids-corp.org / dpdk.git / commitdiff