[v2,07/10] dma/ioat: add data path completion functions

Message ID 20210903111734.2734545-8-conor.walsh@intel.com (mailing list archive)
State Superseded, archived
Delegated to: Thomas Monjalon
Headers
Series dma: add dmadev driver for ioat devices |

Checks

Context Check Description
ci/checkpatch success coding style OK

Commit Message

Conor Walsh Sept. 3, 2021, 11:17 a.m. UTC
Add the data path functions for gathering completed operations
from IOAT devices.

Signed-off-by: Conor Walsh <conor.walsh@intel.com>
Signed-off-by: Kevin Laatz <kevin.laatz@intel.com>
---
 doc/guides/dmadevs/ioat.rst    |  48 ++++++++++-
 drivers/dma/ioat/ioat_dmadev.c | 141 +++++++++++++++++++++++++++++++++
 2 files changed, 188 insertions(+), 1 deletion(-)
  

Patch

diff --git a/doc/guides/dmadevs/ioat.rst b/doc/guides/dmadevs/ioat.rst
index 16acfda3e3..9ea5708090 100644
--- a/doc/guides/dmadevs/ioat.rst
+++ b/doc/guides/dmadevs/ioat.rst
@@ -96,7 +96,9 @@  Performing Data Copies
 To perform data copies using IOAT dmadev devices, the functions
 ``rte_dmadev_copy()`` and ``rte_dmadev_submit()`` should be used. Alternatively
 ``rte_dmadev_copy()`` can be called with the ``RTE_DMA_OP_FLAG_SUBMIT`` flag
-set.
+set. Once copies have been completed, the completion will be reported back when
+the application calls ``rte_dmadev_completed()`` or
+``rte_dmadev_completed_status()``.
 
 The ``rte_dmadev_copy()`` function enqueues a single copy to the
 device ring for copying at a later point. The parameters to the function
@@ -135,6 +137,50 @@  device and start the hardware processing of them:
       return -1;
    }
 
+To retrieve information about completed copies, the API
+``rte_dmadev_completed()`` or  ``rte_dmadev_completed_status ()``should be used.
+``rte_dmadev_completed()`` will return to the application how many operations
+have successfully completed up to a supplied maximum, it can also pass back the
+index of the last completed operation and if a completion within the requested
+batch has failed. If ``rte_dmadev_completed()`` passes back ``has_error`` as
+``true`` then ``rte_dmadev_completed_status()`` should be called to retrieve
+the detailed status of each completion in that batch. Once an error has occurred
+``rte_dmadev_completed()`` will not process any more completions until
+``rte_dmadev_completed_status()`` has been called to get the error information.
+The supplied ``status`` array will contain either ``RTE_DMA_STATUS_SUCCESSFUL``
+if the operation was successful or a DMA error code if the operation failed.
+The status codes supported by IOAT are:
+
+* ``RTE_DMA_STATUS_SUCCESSFUL``: The operation was successful.
+* ``RTE_DMA_STATUS_INVALID_SRC_ADDR``: The operation failed due to an invalid source address.
+* ``RTE_DMA_STATUS_INVALID_DST_ADDR``: The operation failed due to an invalid destination address.
+* ``RTE_DMA_STATUS_INVALID_LENGTH``: The operation failed due to an invalid descriptor length.
+* ``RTE_DMA_STATUS_DESCRIPTOR_READ_ERROR``: The device could not read the descriptor.
+* ``RTE_DMA_STATUS_ERROR_UNKNOWN``: The operation failed due to an unspecified error.
+
+``rte_dmadev_completed_status()`` can be used on it's own instead of with
+``rte_dmadev_completed()`` but calling ``rte_dmadev_completed_status()`` may be
+slower than ``rte_dmadev_completed()``.
+
+The following code shows how to retrieve the number of successfully completed
+copies within a burst and then using ``rte_dmadev_completed_status()`` to check
+which operation failed and reset the device:
+
+.. code-block:: C
+
+   enum rte_dma_status_code status[COMP_BURST_SZ];
+   uint16_t count, idx, status_count;
+   bool error = 0;
+
+   count = rte_dmadev_completed(dev_id, vchan, COMP_BURST_SZ, &idx, &error);
+
+   if (error){
+      status_count = rte_dmadev_completed_status(dev_id, vchan, COMP_BURST_SZ, &idx, status);
+   }
+
+After this snippet the application would use the status array to find which copy
+failed and handle it appropriately.
+
 Filling an Area of Memory
 ~~~~~~~~~~~~~~~~~~~~~~~~~~
 
diff --git a/drivers/dma/ioat/ioat_dmadev.c b/drivers/dma/ioat/ioat_dmadev.c
index 7ffe4e4fe9..715beb3b7e 100644
--- a/drivers/dma/ioat/ioat_dmadev.c
+++ b/drivers/dma/ioat/ioat_dmadev.c
@@ -6,6 +6,7 @@ 
 #include <rte_dmadev_pmd.h>
 #include <rte_malloc.h>
 #include <rte_prefetch.h>
+#include <rte_errno.h>
 
 #include "ioat_internal.h"
 
@@ -329,6 +330,144 @@  ioat_dev_dump(const struct rte_dmadev *dev, FILE *f)
 	return 0;
 }
 
+/* Returns the index of the last completed operation. */
+static inline uint16_t
+__get_last_completed(const struct ioat_dmadev *ioat, int *state)
+{
+	/* Status register contains the address of the completed operation */
+	uint64_t status = ioat->status;
+
+	/* lower 3 bits indicate "transfer status" : active, idle, halted.
+	 * We can ignore bit 0.
+	 */
+	*state = status & IOAT_CHANSTS_STATUS;
+
+	/* If we are just after recovering from an error the address returned by
+	 * status will be 0, in this case we return the offset - 1 as the last
+	 * completed. If not return the status value minus the chainaddr which
+	 * gives us an offset into the ring. Right shifting by 6 (divide by 64)
+	 * gives the index of the completion from the HW point of view and adding
+	 * the offset translates the ring index from HW to SW point of view.
+	 */
+	if ((status & ~IOAT_CHANSTS_STATUS) == 0)
+		return ioat->offset - 1;
+
+	return (status - ioat->ring_addr) >> 6;
+}
+
+/* Translates IOAT ChanERRs to DMA error codes. */
+static inline enum rte_dma_status_code
+__translate_status_ioat_to_dma(uint32_t chanerr)
+{
+	if (chanerr & IOAT_CHANERR_INVALID_SRC_ADDR_MASK)
+		return RTE_DMA_STATUS_INVALID_SRC_ADDR;
+	else if (chanerr & IOAT_CHANERR_INVALID_DST_ADDR_MASK)
+		return RTE_DMA_STATUS_INVALID_DST_ADDR;
+	else if (chanerr & IOAT_CHANERR_INVALID_LENGTH_MASK)
+		return RTE_DMA_STATUS_INVALID_LENGTH;
+	else if (chanerr & IOAT_CHANERR_DESCRIPTOR_READ_ERROR_MASK)
+		return RTE_DMA_STATUS_DESCRIPTOR_READ_ERROR;
+	else
+		return RTE_DMA_STATUS_ERROR_UNKNOWN;
+}
+
+/* Returns details of operations that have been completed. */
+static uint16_t
+ioat_completed(struct rte_dmadev *dev, uint16_t qid __rte_unused, const uint16_t max_ops,
+		uint16_t *last_idx, bool *has_error)
+{
+	struct ioat_dmadev *ioat = dev->dev_private;
+
+	const unsigned short mask = (ioat->qcfg.nb_desc - 1);
+	const unsigned short read = ioat->next_read;
+	unsigned short last_completed, count;
+	int state, fails = 0;
+
+	/* Do not do any work if there is an uncleared error. */
+	if (ioat->failure != 0) {
+		*has_error = true;
+		*last_idx = ioat->next_read - 2;
+		return 0;
+	}
+
+	last_completed = __get_last_completed(ioat, &state);
+	count = (last_completed + 1 - read) & mask;
+
+	/* Cap count at max_ops or set as last run in batch. */
+	if (count > max_ops)
+		count = max_ops;
+
+	if (count == max_ops || state != IOAT_CHANSTS_HALTED) {
+		ioat->next_read = read + count;
+		*last_idx = ioat->next_read - 1;
+	} else {
+		*has_error = true;
+		rte_errno = EIO;
+		ioat->failure = ioat->regs->chanerr;
+		ioat->next_read = read + count + 1;
+		if (__ioat_recover(ioat) != 0) {
+			IOAT_PMD_ERR("Device HALTED and could not be recovered\n");
+			ioat_dev_dump(dev, stdout);
+			return 0;
+		}
+		__submit(ioat);
+		fails++;
+		*last_idx = ioat->next_read - 2;
+	}
+
+	return count;
+}
+
+/* Returns detailed status information about operations that have been completed. */
+static uint16_t
+ioat_completed_status(struct rte_dmadev *dev, uint16_t qid __rte_unused,
+		uint16_t max_ops, uint16_t *last_idx, enum rte_dma_status_code *status)
+{
+	struct ioat_dmadev *ioat = dev->dev_private;
+
+	const unsigned short mask = (ioat->qcfg.nb_desc - 1);
+	const unsigned short read = ioat->next_read;
+	unsigned short count, last_completed;
+	uint64_t fails = 0;
+	int state, i;
+
+	last_completed = __get_last_completed(ioat, &state);
+	count = (last_completed + 1 - read) & mask;
+
+	for (i = 0; i < RTE_MIN(count + 1, max_ops); i++)
+		status[i] = RTE_DMA_STATUS_SUCCESSFUL;
+
+	/* Cap count at max_ops or set as last run in batch. */
+	if (count > max_ops)
+		count = max_ops;
+
+	if (count == max_ops || state != IOAT_CHANSTS_HALTED)
+		ioat->next_read = read + count;
+	else {
+		rte_errno = EIO;
+		status[count] = __translate_status_ioat_to_dma(ioat->regs->chanerr);
+		count++;
+		ioat->next_read = read + count;
+		if (__ioat_recover(ioat) != 0) {
+			IOAT_PMD_ERR("Device HALTED and could not be recovered\n");
+			ioat_dev_dump(dev, stdout);
+			return 0;
+		}
+		__submit(ioat);
+		fails++;
+	}
+
+	if (ioat->failure > 0) {
+		status[0] = __translate_status_ioat_to_dma(ioat->failure);
+		count = RTE_MIN(count + 1, max_ops);
+		ioat->failure = 0;
+	}
+
+	*last_idx = ioat->next_read - 1;
+
+	return count;
+}
+
 /* Create a DMA device. */
 static int
 ioat_dmadev_create(const char *name, struct rte_pci_device *dev)
@@ -367,6 +506,8 @@  ioat_dmadev_create(const char *name, struct rte_pci_device *dev)
 
 	dmadev->dev_ops = &ioat_dmadev_ops;
 
+	dmadev->completed = ioat_completed;
+	dmadev->completed_status = ioat_completed_status;
 	dmadev->copy = ioat_enqueue_copy;
 	dmadev->fill = ioat_enqueue_fill;
 	dmadev->submit = ioat_submit;