[dpdk-dev] [PATCH v4 11/12] raw/ioat: add API to query remaining ring space

[Bruce Richardson <bruce.richardson@intel.com>]

From: Kevin Laatz <kevin.laatz@intel.com>

Add a new API to query remaining descriptor ring capacity. This API is
useful, for example, when an application needs to enqueue a fragmented
packet and wants to ensure that all segments of the packet will be enqueued
together.

Signed-off-by: Kevin Laatz <kevin.laatz@intel.com>
Signed-off-by: Bruce Richardson <bruce.richardson@intel.com>
---
 drivers/raw/ioat/ioat_rawdev_test.c    | 70 +++++++++++++++++++++++++-
 drivers/raw/ioat/rte_idxd_rawdev_fns.h | 22 ++++++++
 drivers/raw/ioat/rte_ioat_rawdev_fns.h | 24 +++++++++
 3 files changed, 115 insertions(+), 1 deletion(-)

diff --git a/drivers/raw/ioat/ioat_rawdev_test.c b/drivers/raw/ioat/ioat_rawdev_test.c
index 51eebe152f..839a716a21 100644
--- a/drivers/raw/ioat/ioat_rawdev_test.c
+++ b/drivers/raw/ioat/ioat_rawdev_test.c
@@ -277,6 +277,70 @@ test_enqueue_fill(int dev_id)
 	return 0;
 }
 
+static int
+test_burst_capacity(int dev_id)
+{
+#define BURST_SIZE			64
+	const unsigned int ring_space = rte_ioat_burst_capacity(dev_id);
+	struct rte_mbuf *src, *dst;
+	unsigned int length = 1024;
+	unsigned int i, j, iter;
+	unsigned int old_cap, cap;
+	uintptr_t completions[BURST_SIZE];
+
+	src = rte_pktmbuf_alloc(pool);
+	dst = rte_pktmbuf_alloc(pool);
+
+	old_cap = ring_space;
+	/* to test capacity, we enqueue elements and check capacity is reduced
+	 * by one each time - rebaselining the expected value after each burst
+	 * as the capacity is only for a burst. We enqueue multiple bursts to
+	 * fill up half the ring, before emptying it again. We do this twice to
+	 * ensure that we get to test scenarios where we get ring wrap-around
+	 */
+	for (iter = 0; iter < 2; iter++) {
+		for (i = 0; i < ring_space / (2 * BURST_SIZE); i++) {
+			cap = rte_ioat_burst_capacity(dev_id);
+			if (cap > old_cap) {
+				PRINT_ERR("Error, avail ring capacity has gone up, not down\n");
+				return -1;
+			}
+			old_cap = cap;
+
+			for (j = 0; j < BURST_SIZE; j++) {
+				if (rte_ioat_enqueue_copy(dev_id, rte_pktmbuf_iova(src),
+						rte_pktmbuf_iova(dst), length, 0, 0) != 1) {
+					PRINT_ERR("Error with rte_ioat_enqueue_copy\n");
+					return -1;
+				}
+				if (cap - rte_ioat_burst_capacity(dev_id) != j + 1) {
+					PRINT_ERR("Error, ring capacity did not change as expected\n");
+					return -1;
+				}
+			}
+			rte_ioat_perform_ops(dev_id);
+		}
+		usleep(100);
+		for (i = 0; i < ring_space / (2 * BURST_SIZE); i++) {
+			if (rte_ioat_completed_ops(dev_id, BURST_SIZE,
+					completions, completions) != BURST_SIZE) {
+				PRINT_ERR("Error with completions\n");
+				return -1;
+			}
+		}
+		if (rte_ioat_burst_capacity(dev_id) != ring_space) {
+			PRINT_ERR("Error, ring capacity has not reset to original value\n");
+			return -1;
+		}
+		old_cap = ring_space;
+	}
+
+	rte_pktmbuf_free(src);
+	rte_pktmbuf_free(dst);
+
+	return 0;
+}
+
 int
 ioat_rawdev_test(uint16_t dev_id)
 {
@@ -321,7 +385,7 @@ ioat_rawdev_test(uint16_t dev_id)
 	}
 
 	pool = rte_pktmbuf_pool_create("TEST_IOAT_POOL",
-			256, /* n == num elements */
+			p.ring_size * 2, /* n == num elements */
 			32,  /* cache size */
 			0,   /* priv size */
 			2048, /* data room size */
@@ -385,6 +449,10 @@ ioat_rawdev_test(uint16_t dev_id)
 	}
 	printf("\n");
 
+	printf("Running Burst Capacity Test\n");
+	if (test_burst_capacity(dev_id) != 0)
+		goto err;
+
 	rte_rawdev_stop(dev_id);
 	if (rte_rawdev_xstats_reset(dev_id, NULL, 0) != 0) {
 		PRINT_ERR("Error resetting xstat values\n");
diff --git a/drivers/raw/ioat/rte_idxd_rawdev_fns.h b/drivers/raw/ioat/rte_idxd_rawdev_fns.h
index 4c49d2b84a..41f0ad6e99 100644
--- a/drivers/raw/ioat/rte_idxd_rawdev_fns.h
+++ b/drivers/raw/ioat/rte_idxd_rawdev_fns.h
@@ -106,6 +106,28 @@ struct rte_idxd_rawdev {
 	struct rte_idxd_user_hdl *hdl_ring;
 };
 
+static __rte_always_inline uint16_t
+__idxd_burst_capacity(int dev_id)
+{
+	struct rte_idxd_rawdev *idxd =
+			(struct rte_idxd_rawdev *)rte_rawdevs[dev_id].dev_private;
+	uint16_t write_idx = idxd->batch_start + idxd->batch_size;
+	uint16_t used_space;
+
+	/* Check for space in the batch ring */
+	if ((idxd->batch_idx_read == 0 && idxd->batch_idx_write == idxd->max_batches) ||
+			idxd->batch_idx_write + 1 == idxd->batch_idx_read)
+		return 0;
+
+	/* for descriptors, check for wrap-around on write but not read */
+	if (idxd->hdls_read > write_idx)
+		write_idx += idxd->desc_ring_mask + 1;
+	used_space = write_idx - idxd->hdls_read;
+
+	/* Return amount of free space in the descriptor ring */
+	return idxd->desc_ring_mask - used_space;
+}
+
 static __rte_always_inline rte_iova_t
 __desc_idx_to_iova(struct rte_idxd_rawdev *idxd, uint16_t n)
 {
diff --git a/drivers/raw/ioat/rte_ioat_rawdev_fns.h b/drivers/raw/ioat/rte_ioat_rawdev_fns.h
index 598852b1fa..92ccdd03b9 100644
--- a/drivers/raw/ioat/rte_ioat_rawdev_fns.h
+++ b/drivers/raw/ioat/rte_ioat_rawdev_fns.h
@@ -100,6 +100,19 @@ struct rte_ioat_rawdev {
 #define RTE_IOAT_CHANSTS_HALTED			0x3
 #define RTE_IOAT_CHANSTS_ARMED			0x4
 
+static __rte_always_inline uint16_t
+__ioat_burst_capacity(int dev_id)
+{
+	struct rte_ioat_rawdev *ioat =
+			(struct rte_ioat_rawdev *)rte_rawdevs[dev_id].dev_private;
+	unsigned short size = ioat->ring_size - 1;
+	unsigned short read = ioat->next_read;
+	unsigned short write = ioat->next_write;
+	unsigned short space = size - (write - read);
+
+	return space;
+}
+
 static __rte_always_inline int
 __ioat_write_desc(int dev_id, uint32_t op, uint64_t src, phys_addr_t dst,
 		unsigned int length, uintptr_t src_hdl, uintptr_t dst_hdl)
@@ -260,6 +273,17 @@ __ioat_completed_ops(int dev_id, uint8_t max_copies,
 	return count;
 }
 
+static inline uint16_t
+rte_ioat_burst_capacity(int dev_id)
+{
+	enum rte_ioat_dev_type *type =
+		(enum rte_ioat_dev_type *)rte_rawdevs[dev_id].dev_private;
+	if (*type == RTE_IDXD_DEV)
+		return __idxd_burst_capacity(dev_id);
+	else
+		return __ioat_burst_capacity(dev_id);
+}
+
 static inline int
 rte_ioat_enqueue_fill(int dev_id, uint64_t pattern, phys_addr_t dst,
 		unsigned int len, uintptr_t dst_hdl)
-- 
2.30.2