habanalabs: add current PI value to cpu packets

In order to increase cpucp messaging reliability we will add
the current PI value to the descriptor sent to F/W.
F/W will wait for the PI value as an indication of a valid packet.

Signed-off-by: Ofir Bitton <obitton@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>

diff --git a/drivers/misc/habanalabs/common/firmware_if.c b/drivers/misc/habanalabs/common/firmware_if.c
index 76741898d922ab2e991bf5c02a6af40166f11acc..34e70cca37c14ea0b822cd80d2c5ff4e04757b53 100644 (file)
--- a/drivers/misc/habanalabs/common/firmware_if.c
+++ b/drivers/misc/habanalabs/common/firmware_if.c
@@ -212,7 +212,8 @@ int hl_fw_send_cpu_message(struct hl_device *hdev, u32 hw_queue_id, u32 *msg,
        struct asic_fixed_properties *prop = &hdev->asic_prop;
        struct cpucp_packet *pkt;
        dma_addr_t pkt_dma_addr;
-       u32 tmp, expected_ack_val;
+       struct hl_bd *sent_bd;
+       u32 tmp, expected_ack_val, pi;
        int rc = 0;
 
        pkt = hdev->asic_funcs->cpu_accessible_dma_pool_alloc(hdev, len,
@@ -237,6 +238,7 @@ int hl_fw_send_cpu_message(struct hl_device *hdev, u32 hw_queue_id, u32 *msg,
 
        /* set fence to a non valid value */
        pkt->fence = cpu_to_le32(UINT_MAX);
+       pi = queue->pi;
 
        /*
         * The CPU queue is a synchronous queue with an effective depth of
@@ -246,7 +248,7 @@ int hl_fw_send_cpu_message(struct hl_device *hdev, u32 hw_queue_id, u32 *msg,
         * Which means that we don't need to lock the access to the entire H/W
         * queues module when submitting a JOB to the CPU queue.
         */
-       hl_hw_queue_submit_bd(hdev, queue, 0, len, pkt_dma_addr);
+       hl_hw_queue_submit_bd(hdev, queue, hl_queue_inc_ptr(queue->pi), len, pkt_dma_addr);
 
        if (prop->fw_app_cpu_boot_dev_sts0 & CPU_BOOT_DEV_STS0_PKT_PI_ACK_EN)
                expected_ack_val = queue->pi;
@@ -278,6 +280,14 @@ int hl_fw_send_cpu_message(struct hl_device *hdev, u32 hw_queue_id, u32 *msg,
                *result = le64_to_cpu(pkt->result);
        }
 
+       /* Scrub previous buffer descriptor 'ctl' field which contains the
+        * previous PI value written during packet submission.
+        * We must do this or else F/W can read an old value upon queue wraparound.
+        */
+       sent_bd = queue->kernel_address;
+       sent_bd += hl_pi_2_offset(pi);
+       sent_bd->ctl = cpu_to_le32(UINT_MAX);
+
 out:
        mutex_unlock(&hdev->send_cpu_message_lock);