From 70d25e96b69eca96ded689dff8ea3e0decdf9cf7 Mon Sep 17 00:00:00 2001 From: Koby Elbaz Date: Sun, 12 Jun 2022 22:16:25 +0300 Subject: [PATCH] habanalabs/gaudi: fix incorrect MME offset calculation Once FW raised an event following a MME2 QMAN error, the driver should have gone to the corresponding status registers, trying to gather more info on the error, yet it was accidentally accessing MME1 QMAN address space. Generally, we have x4 MMEs, while 0 & 2 are marked MASTER, and 1 & 3 are marked SLAVE. The former can be addressed, yet addressing the latter is considered an access violation, and will result in a hung system, which is what unintentionally happened above. Note that this cannot happen in a secured system, since these registers are protected with range registers. Signed-off-by: Koby Elbaz Reviewed-by: Oded Gabbay Signed-off-by: Oded Gabbay --- drivers/misc/habanalabs/gaudi/gaudi.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) diff --git a/drivers/misc/habanalabs/gaudi/gaudi.c b/drivers/misc/habanalabs/gaudi/gaudi.c index b7460c30aa51e..8b9ff7fa51ea6 100644 --- a/drivers/misc/habanalabs/gaudi/gaudi.c +++ b/drivers/misc/habanalabs/gaudi/gaudi.c @@ -454,7 +454,7 @@ static const int gaudi_queue_id_to_engine_id[] = { [GAUDI_QUEUE_ID_DMA_6_0...GAUDI_QUEUE_ID_DMA_6_3] = GAUDI_ENGINE_ID_DMA_6, [GAUDI_QUEUE_ID_DMA_7_0...GAUDI_QUEUE_ID_DMA_7_3] = GAUDI_ENGINE_ID_DMA_7, [GAUDI_QUEUE_ID_MME_0_0...GAUDI_QUEUE_ID_MME_0_3] = GAUDI_ENGINE_ID_MME_0, - [GAUDI_QUEUE_ID_MME_1_0...GAUDI_QUEUE_ID_MME_1_3] = GAUDI_ENGINE_ID_MME_1, + [GAUDI_QUEUE_ID_MME_1_0...GAUDI_QUEUE_ID_MME_1_3] = GAUDI_ENGINE_ID_MME_2, [GAUDI_QUEUE_ID_TPC_0_0...GAUDI_QUEUE_ID_TPC_0_3] = GAUDI_ENGINE_ID_TPC_0, [GAUDI_QUEUE_ID_TPC_1_0...GAUDI_QUEUE_ID_TPC_1_3] = GAUDI_ENGINE_ID_TPC_1, [GAUDI_QUEUE_ID_TPC_2_0...GAUDI_QUEUE_ID_TPC_2_3] = GAUDI_ENGINE_ID_TPC_2, @@ -7383,8 +7383,13 @@ static void gaudi_handle_qman_err(struct hl_device *hdev, u16 event_type, u64 *e snprintf(desc, ARRAY_SIZE(desc), "%s%d", "TPC_QM", index); break; case GAUDI_EVENT_MME0_QM ... GAUDI_EVENT_MME2_QM: - index = event_type - GAUDI_EVENT_MME0_QM; - qid_base = GAUDI_QUEUE_ID_MME_0_0 + index * QMAN_STREAMS; + if (event_type == GAUDI_EVENT_MME0_QM) { + index = 0; + qid_base = GAUDI_QUEUE_ID_MME_0_0; + } else if (event_type == GAUDI_EVENT_MME2_QM) { + index = 2; + qid_base = GAUDI_QUEUE_ID_MME_1_0; + } qman_base = mmMME0_QM_BASE + index * MME_QMAN_OFFSET; snprintf(desc, ARRAY_SIZE(desc), "%s%d", "MME_QM", index); break; -- 2.30.2