habanalabs/gaudi: minimize number of register reads

Because the register reads might be trapped by the hypervisor in
certain deployments, minimize the number of reads during runtime by
moving static initializations to functions that occur during device
initialization instead of context open.

Signed-off-by: Oded Gabbay <ogabbay@kernel.org>

diff --git a/drivers/misc/habanalabs/gaudi/gaudi.c b/drivers/misc/habanalabs/gaudi/gaudi.c
index f2abd5011354554645b2db29178a3dd522ec3a67..833ce89c8ab907ab6f3e0a8a5e83820ed0143939 100644 (file)
--- a/drivers/misc/habanalabs/gaudi/gaudi.c
+++ b/drivers/misc/habanalabs/gaudi/gaudi.c
@@ -1595,6 +1595,11 @@ static int gaudi_late_init(struct hl_device *hdev)
                goto disable_pci_access;
        }
 
+       /* We only support a single ASID for the user, so for the sake of optimization, just
+        * initialize the ASID one time during device initialization with the fixed value of 1
+        */
+       gaudi_mmu_prepare(hdev, 1);
+
        return 0;
 
 disable_pci_access:
@@ -6792,6 +6797,9 @@ static void gaudi_mmu_prepare(struct hl_device *hdev, u32 asid)
                                asid);
        }
 
+       gaudi_mmu_prepare_reg(hdev, mmPSOC_GLOBAL_CONF_TRACE_ARUSER, asid);
+       gaudi_mmu_prepare_reg(hdev, mmPSOC_GLOBAL_CONF_TRACE_AWUSER, asid);
+
        hdev->asic_funcs->set_clock_gating(hdev);
 
        mutex_unlock(&gaudi->clk_gate_mutex);
@@ -6841,7 +6849,8 @@ static int gaudi_send_job_on_qman0(struct hl_device *hdev,
 
        dma_offset = gaudi_dma_assignment[GAUDI_PCI_DMA_1] * DMA_CORE_OFFSET;
 
-       WREG32_OR(mmDMA0_CORE_PROT + dma_offset, BIT(DMA0_CORE_PROT_VAL_SHIFT));
+       WREG32(mmDMA0_CORE_PROT + dma_offset,
+                       BIT(DMA0_CORE_PROT_ERR_VAL_SHIFT) | BIT(DMA0_CORE_PROT_VAL_SHIFT));
 
        rc = hl_hw_queue_send_cb_no_cmpl(hdev, GAUDI_QUEUE_ID_DMA_0_0,
                                        job->job_cb_size, cb->bus_address);
@@ -6862,8 +6871,7 @@ static int gaudi_send_job_on_qman0(struct hl_device *hdev,
        }
 
 free_fence_ptr:
-       WREG32_AND(mmDMA0_CORE_PROT + dma_offset,
-                       ~BIT(DMA0_CORE_PROT_VAL_SHIFT));
+       WREG32(mmDMA0_CORE_PROT + dma_offset, BIT(DMA0_CORE_PROT_ERR_VAL_SHIFT));
 
        hdev->asic_funcs->asic_dma_pool_free(hdev, (void *) fence_ptr,
                                        fence_dma_addr);
@@ -8652,7 +8660,6 @@ static int gaudi_ctx_init(struct hl_ctx *ctx)
        if (ctx->asid == HL_KERNEL_ASID_ID)
                return 0;
 
-       gaudi_mmu_prepare(ctx->hdev, ctx->asid);
        return gaudi_internal_cb_pool_init(ctx->hdev, ctx);
 }
 

diff --git a/drivers/misc/habanalabs/gaudi/gaudi_coresight.c b/drivers/misc/habanalabs/gaudi/gaudi_coresight.c
index c2a27ed1c4d11eff26d9b0b845ffc9f85e9d9266..5349c1be13f98898fa19fcb2e760f4ac4c76b338 100644 (file)
--- a/drivers/misc/habanalabs/gaudi/gaudi_coresight.c
+++ b/drivers/misc/habanalabs/gaudi/gaudi_coresight.c
@@ -622,11 +622,6 @@ static int gaudi_config_etr(struct hl_device *hdev,
                        return -EINVAL;
                }
 
-               gaudi_mmu_prepare_reg(hdev, mmPSOC_GLOBAL_CONF_TRACE_ARUSER,
-                                               hdev->compute_ctx->asid);
-               gaudi_mmu_prepare_reg(hdev, mmPSOC_GLOBAL_CONF_TRACE_AWUSER,
-                                               hdev->compute_ctx->asid);
-
                msb = upper_32_bits(input->buffer_address) >> 8;
                msb &= PSOC_GLOBAL_CONF_TRACE_ADDR_MSB_MASK;
                WREG32(mmPSOC_GLOBAL_CONF_TRACE_ADDR, msb);