diff options
| author | Oded Gabbay <oded.gabbay@gmail.com> | 2020-07-07 17:30:13 +0300 |
|---|---|---|
| committer | Oded Gabbay <oded.gabbay@gmail.com> | 2020-07-10 19:53:03 +0300 |
| commit | 788cacf308871db0a619952321bedfec8f1773e2 (patch) | |
| tree | 4e507fb09ad60b5131d6f371e9e3780670fad83c /drivers/misc/habanalabs/goya | |
| parent | e38bfd30e08802d9661efffb8c048bd53a3acfc4 (diff) | |
| download | linux-788cacf308871db0a619952321bedfec8f1773e2.tar.bz2 | |
habanalabs: set 4s timeout for message to device CPU
We see that sometimes the CPU in GOYA and GAUDI is occupied by the
power/thermal loop and can't answer requests from the driver fast enough.
Therefore, to avoid false notifications on timeouts, increase the timeout
to 4 seconds on each message sent to the device CPU.
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
Reviewed-by: Tomer Tayar <ttayar@habana.ai>
Diffstat (limited to 'drivers/misc/habanalabs/goya')
| -rw-r--r-- | drivers/misc/habanalabs/goya/goya.c | 12 |
1 files changed, 8 insertions, 4 deletions
diff --git a/drivers/misc/habanalabs/goya/goya.c b/drivers/misc/habanalabs/goya/goya.c index 83f0c70f140b..88460b2138d8 100644 --- a/drivers/misc/habanalabs/goya/goya.c +++ b/drivers/misc/habanalabs/goya/goya.c @@ -88,6 +88,7 @@ #define GOYA_PLDM_MMU_TIMEOUT_USEC (MMU_CONFIG_TIMEOUT_USEC * 100) #define GOYA_PLDM_QMAN0_TIMEOUT_USEC (HL_DEVICE_TIMEOUT_USEC * 30) #define GOYA_BOOT_FIT_REQ_TIMEOUT_USEC 1000000 /* 1s */ +#define GOYA_MSG_TO_CPU_TIMEOUT_USEC 4000000 /* 4s */ #define GOYA_QMAN0_FENCE_VAL 0xD169B243 @@ -2830,6 +2831,9 @@ int goya_send_cpu_message(struct hl_device *hdev, u32 *msg, u16 len, return 0; } + if (!timeout) + timeout = GOYA_MSG_TO_CPU_TIMEOUT_USEC; + return hl_fw_send_cpu_message(hdev, GOYA_QUEUE_ID_CPU_PQ, msg, len, timeout, result); } @@ -4431,8 +4435,8 @@ static int goya_unmask_irq_arr(struct hl_device *hdev, u32 *irq_arr, pkt->armcp_pkt.ctl = cpu_to_le32(ARMCP_PACKET_UNMASK_RAZWI_IRQ_ARRAY << ARMCP_PKT_CTL_OPCODE_SHIFT); - rc = goya_send_cpu_message(hdev, (u32 *) pkt, total_pkt_size, - HL_DEVICE_TIMEOUT_USEC, &result); + rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) pkt, + total_pkt_size, 0, &result); if (rc) dev_err(hdev->dev, "failed to unmask IRQ array\n"); @@ -4464,8 +4468,8 @@ static int goya_unmask_irq(struct hl_device *hdev, u16 event_type) ARMCP_PKT_CTL_OPCODE_SHIFT); pkt.value = cpu_to_le64(event_type); - rc = goya_send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt), - HL_DEVICE_TIMEOUT_USEC, &result); + rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt), + 0, &result); if (rc) dev_err(hdev->dev, "failed to unmask RAZWI IRQ %d", event_type); |