diff options
| author | Moti Haimovski <mhaimovski@habana.ai> | 2020-06-24 19:40:57 +0300 |
|---|---|---|
| committer | Oded Gabbay <oded.gabbay@gmail.com> | 2020-07-24 20:31:37 +0300 |
| commit | a9855a2d91531001f1a952a042f17cc42ef30cb7 (patch) | |
| tree | 7b9be279142498bf05ec44e3ed6968c56db297b5 /drivers/misc/habanalabs/gaudi | |
| parent | 22cb855598ed9aa7812941eb29218dc6033b4b43 (diff) | |
habanalabs: check for DMA errors when clearing memory
In GAUDI we use QMAN0 DMA for clearing the MMU memory region
at initialization. if this operation fails it places the DMA in an error
state and then when trying to initialize QMAN0 we fail and erroneously
assume its the QMAN that failed.
This commit adds a check and clear of such DMA errors at initialization so
we will have a better understanding of what went wrong.
Signed-off-by: Moti Haimovski <mhaimovski@habana.ai>
Reviewed-by: Oded Gabbay <oded.gabbay@gmail.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
Diffstat (limited to 'drivers/misc/habanalabs/gaudi')
| -rw-r--r-- | drivers/misc/habanalabs/gaudi/gaudi.c | 25 |
1 files changed, 23 insertions, 2 deletions
diff --git a/drivers/misc/habanalabs/gaudi/gaudi.c b/drivers/misc/habanalabs/gaudi/gaudi.c index a9fd3d352ef0..57b2b9392cb2 100644 --- a/drivers/misc/habanalabs/gaudi/gaudi.c +++ b/drivers/misc/habanalabs/gaudi/gaudi.c @@ -4253,7 +4253,7 @@ static int gaudi_memset_device_memory(struct hl_device *hdev, u64 addr, { struct packet_lin_dma *lin_dma_pkt; struct hl_cs_job *job; - u32 cb_size, ctl; + u32 cb_size, ctl, err_cause; struct hl_cb *cb; int rc; @@ -4282,6 +4282,15 @@ static int gaudi_memset_device_memory(struct hl_device *hdev, u64 addr, goto release_cb; } + /* Verify DMA is OK */ + err_cause = RREG32(mmDMA0_CORE_ERR_CAUSE); + if (err_cause && !hdev->init_done) { + dev_dbg(hdev->dev, + "Clearing DMA0 engine from errors (cause 0x%x)\n", + err_cause); + WREG32(mmDMA0_CORE_ERR_CAUSE, err_cause); + } + job->id = 0; job->user_cb = cb; job->user_cb->cs_cnt++; @@ -4293,11 +4302,23 @@ static int gaudi_memset_device_memory(struct hl_device *hdev, u64 addr, hl_debugfs_add_job(hdev, job); rc = gaudi_send_job_on_qman0(hdev, job); - hl_debugfs_remove_job(hdev, job); kfree(job); cb->cs_cnt--; + /* Verify DMA is OK */ + err_cause = RREG32(mmDMA0_CORE_ERR_CAUSE); + if (err_cause) { + dev_err(hdev->dev, "DMA Failed, cause 0x%x\n", err_cause); + rc = -EIO; + if (!hdev->init_done) { + dev_dbg(hdev->dev, + "Clearing DMA0 engine from errors (cause 0x%x)\n", + err_cause); + WREG32(mmDMA0_CORE_ERR_CAUSE, err_cause); + } + } + release_cb: hl_cb_put(cb); hl_cb_destroy(hdev, &hdev->kernel_cb_mgr, cb->id << PAGE_SHIFT); |