From: Oded Gabbay <ogabbay@kernel.org>
To: linux-kernel@vger.kernel.org
Cc: Dani Liberman <dliberman@habana.ai>
Subject: [PATCH 04/10] habanalabs/gaudi2: fix emda range registers razwi handling
Date: Thu, 19 Jan 2023 12:33:33 +0200 [thread overview]
Message-ID: <20230119103339.718430-4-ogabbay@kernel.org> (raw)
In-Reply-To: <20230119103339.718430-1-ogabbay@kernel.org>
From: Dani Liberman <dliberman@habana.ai>
Handling edma razwi is different than all other engines since edma
uses sft routers. For hbw transactions sft router contain separate
interface for each edma and for lbw there is common interface for
both edma engines of the same dcore.
To handle the razwi correctly we need to:
1. Simplify the calculation of the sft router address.
2. Add razwi handling for edma qm errors, since edma qman doesn't
reports axi error response.
Signed-off-by: Dani Liberman <dliberman@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
---
drivers/accel/habanalabs/gaudi2/gaudi2.c | 69 ++++++++++++------------
1 file changed, 33 insertions(+), 36 deletions(-)
diff --git a/drivers/accel/habanalabs/gaudi2/gaudi2.c b/drivers/accel/habanalabs/gaudi2/gaudi2.c
index 72e08c1eae22..80cd4413b87d 100644
--- a/drivers/accel/habanalabs/gaudi2/gaudi2.c
+++ b/drivers/accel/habanalabs/gaudi2/gaudi2.c
@@ -1604,13 +1604,15 @@ static const u32 gaudi2_nic_initiator_lbw_rtr_id[NIC_NUMBER_OF_MACROS] = {
DCORE2_RTR0, DCORE2_RTR0, DCORE2_RTR0, DCORE3_RTR7, DCORE3_RTR7, DCORE3_RTR7
};
-struct sft_info {
- u8 interface_id;
- u8 dcore_id;
-};
-
-static const struct sft_info gaudi2_edma_initiator_sft_id[NUM_OF_EDMA_PER_DCORE * NUM_OF_DCORES] = {
- {0, 0}, {1, 0}, {0, 1}, {1, 1}, {1, 2}, {1, 3}, {0, 2}, {0, 3},
+static const u32 gaudi2_edma_initiator_hbw_sft[NUM_OF_EDMA_PER_DCORE * NUM_OF_DCORES] = {
+ mmSFT0_HBW_RTR_IF1_MSTR_IF_RR_SHRD_HBW_BASE,
+ mmSFT0_HBW_RTR_IF0_MSTR_IF_RR_SHRD_HBW_BASE,
+ mmSFT1_HBW_RTR_IF1_MSTR_IF_RR_SHRD_HBW_BASE,
+ mmSFT1_HBW_RTR_IF0_MSTR_IF_RR_SHRD_HBW_BASE,
+ mmSFT2_HBW_RTR_IF0_MSTR_IF_RR_SHRD_HBW_BASE,
+ mmSFT2_HBW_RTR_IF1_MSTR_IF_RR_SHRD_HBW_BASE,
+ mmSFT3_HBW_RTR_IF0_MSTR_IF_RR_SHRD_HBW_BASE,
+ mmSFT3_HBW_RTR_IF1_MSTR_IF_RR_SHRD_HBW_BASE
};
static const u32 gaudi2_pdma_initiator_hbw_rtr_id[NUM_OF_PDMA] = {
@@ -7212,7 +7214,7 @@ static void gaudi2_ack_module_razwi_event_handler(struct hl_device *hdev,
u8 module_sub_idx, u64 *event_mask)
{
bool via_sft = false;
- u32 hbw_rtr_id, lbw_rtr_id, dcore_id, dcore_rtr_id, sft_id, eng_id;
+ u32 hbw_rtr_id, lbw_rtr_id, dcore_id, dcore_rtr_id, eng_id;
u64 hbw_rtr_mstr_if_base_addr, lbw_rtr_mstr_if_base_addr;
u32 hbw_shrd_aw = 0, hbw_shrd_ar = 0;
u32 lbw_shrd_aw = 0, lbw_shrd_ar = 0;
@@ -7268,8 +7270,13 @@ static void gaudi2_ack_module_razwi_event_handler(struct hl_device *hdev,
lbw_rtr_id = hbw_rtr_id;
break;
case RAZWI_EDMA:
- sft_id = gaudi2_edma_initiator_sft_id[module_idx].interface_id;
- dcore_id = gaudi2_edma_initiator_sft_id[module_idx].dcore_id;
+ hbw_rtr_mstr_if_base_addr = gaudi2_edma_initiator_hbw_sft[module_idx];
+ dcore_id = module_idx / NUM_OF_EDMA_PER_DCORE;
+ /* SFT has separate MSTR_IF for LBW, only there we can
+ * read the LBW razwi related registers
+ */
+ lbw_rtr_mstr_if_base_addr = mmSFT0_LBW_RTR_IF_MSTR_IF_RR_SHRD_HBW_BASE +
+ dcore_id * SFT_DCORE_OFFSET;
via_sft = true;
sprintf(initiator_name, "EDMA_%u", module_idx);
break;
@@ -7298,13 +7305,7 @@ static void gaudi2_ack_module_razwi_event_handler(struct hl_device *hdev,
}
/* Find router mstr_if register base */
- if (via_sft) {
- hbw_rtr_mstr_if_base_addr = mmSFT0_HBW_RTR_IF0_RTR_CTRL_BASE +
- dcore_id * SFT_DCORE_OFFSET +
- sft_id * SFT_IF_OFFSET +
- RTR_MSTR_IF_OFFSET;
- lbw_rtr_mstr_if_base_addr = hbw_rtr_mstr_if_base_addr;
- } else {
+ if (!via_sft) {
dcore_id = hbw_rtr_id / NUM_OF_RTR_PER_DCORE;
dcore_rtr_id = hbw_rtr_id % NUM_OF_RTR_PER_DCORE;
hbw_rtr_mstr_if_base_addr = mmDCORE0_RTR0_CTRL_BASE +
@@ -7318,22 +7319,8 @@ static void gaudi2_ack_module_razwi_event_handler(struct hl_device *hdev,
/* Find out event cause by reading "RAZWI_HAPPENED" registers */
hbw_shrd_aw = RREG32(hbw_rtr_mstr_if_base_addr + RR_SHRD_HBW_AW_RAZWI_HAPPENED);
hbw_shrd_ar = RREG32(hbw_rtr_mstr_if_base_addr + RR_SHRD_HBW_AR_RAZWI_HAPPENED);
-
- if (via_sft) {
- /* SFT has separate MSTR_IF for LBW, only there we can
- * read the LBW razwi related registers
- */
- u64 base;
-
- base = mmSFT0_HBW_RTR_IF0_RTR_CTRL_BASE + dcore_id * SFT_DCORE_OFFSET +
- RTR_LBW_MSTR_IF_OFFSET;
-
- lbw_shrd_aw = RREG32(base + RR_SHRD_LBW_AW_RAZWI_HAPPENED);
- lbw_shrd_ar = RREG32(base + RR_SHRD_LBW_AR_RAZWI_HAPPENED);
- } else {
- lbw_shrd_aw = RREG32(lbw_rtr_mstr_if_base_addr + RR_SHRD_LBW_AW_RAZWI_HAPPENED);
- lbw_shrd_ar = RREG32(lbw_rtr_mstr_if_base_addr + RR_SHRD_LBW_AR_RAZWI_HAPPENED);
- }
+ lbw_shrd_aw = RREG32(lbw_rtr_mstr_if_base_addr + RR_SHRD_LBW_AW_RAZWI_HAPPENED);
+ lbw_shrd_ar = RREG32(lbw_rtr_mstr_if_base_addr + RR_SHRD_LBW_AR_RAZWI_HAPPENED);
eng_id = gaudi2_razwi_calc_engine_id(hdev, module, module_idx);
if (hbw_shrd_aw) {
@@ -7855,7 +7842,7 @@ static int gaudi2_handle_qm_sei_err(struct hl_device *hdev, u16 event_type,
return error_count;
}
-static int gaudi2_handle_qman_err(struct hl_device *hdev, u16 event_type)
+static int gaudi2_handle_qman_err(struct hl_device *hdev, u16 event_type, u64 *event_mask)
{
u32 qid_base, error_count = 0;
u64 qman_base;
@@ -7903,34 +7890,42 @@ static int gaudi2_handle_qman_err(struct hl_device *hdev, u16 event_type)
qman_base = mmDCORE3_MME_QM_BASE;
break;
case GAUDI2_EVENT_HDMA0_QM:
+ index = 0;
qid_base = GAUDI2_QUEUE_ID_DCORE0_EDMA_0_0;
qman_base = mmDCORE0_EDMA0_QM_BASE;
break;
case GAUDI2_EVENT_HDMA1_QM:
+ index = 1;
qid_base = GAUDI2_QUEUE_ID_DCORE0_EDMA_1_0;
qman_base = mmDCORE0_EDMA1_QM_BASE;
break;
case GAUDI2_EVENT_HDMA2_QM:
+ index = 2;
qid_base = GAUDI2_QUEUE_ID_DCORE1_EDMA_0_0;
qman_base = mmDCORE1_EDMA0_QM_BASE;
break;
case GAUDI2_EVENT_HDMA3_QM:
+ index = 3;
qid_base = GAUDI2_QUEUE_ID_DCORE1_EDMA_1_0;
qman_base = mmDCORE1_EDMA1_QM_BASE;
break;
case GAUDI2_EVENT_HDMA4_QM:
+ index = 4;
qid_base = GAUDI2_QUEUE_ID_DCORE2_EDMA_0_0;
qman_base = mmDCORE2_EDMA0_QM_BASE;
break;
case GAUDI2_EVENT_HDMA5_QM:
+ index = 5;
qid_base = GAUDI2_QUEUE_ID_DCORE2_EDMA_1_0;
qman_base = mmDCORE2_EDMA1_QM_BASE;
break;
case GAUDI2_EVENT_HDMA6_QM:
+ index = 6;
qid_base = GAUDI2_QUEUE_ID_DCORE3_EDMA_0_0;
qman_base = mmDCORE3_EDMA0_QM_BASE;
break;
case GAUDI2_EVENT_HDMA7_QM:
+ index = 7;
qid_base = GAUDI2_QUEUE_ID_DCORE3_EDMA_1_0;
qman_base = mmDCORE3_EDMA1_QM_BASE;
break;
@@ -7957,8 +7952,10 @@ static int gaudi2_handle_qman_err(struct hl_device *hdev, u16 event_type)
error_count = gaudi2_handle_qman_err_generic(hdev, event_type, qman_base, qid_base);
/* Handle EDMA QM SEI here because there is no AXI error response event for EDMA */
- if (event_type >= GAUDI2_EVENT_HDMA2_QM && event_type <= GAUDI2_EVENT_HDMA5_QM)
+ if (event_type >= GAUDI2_EVENT_HDMA2_QM && event_type <= GAUDI2_EVENT_HDMA5_QM) {
error_count += _gaudi2_handle_qm_sei_err(hdev, qman_base, event_type);
+ gaudi2_ack_module_razwi_event_handler(hdev, RAZWI_EDMA, index, 0, event_mask);
+ }
return error_count;
}
@@ -8868,7 +8865,7 @@ static void gaudi2_handle_eqe(struct hl_device *hdev, struct hl_eq_entry *eq_ent
case GAUDI2_EVENT_ROTATOR0_ROT0_QM ... GAUDI2_EVENT_ROTATOR1_ROT1_QM:
fallthrough;
case GAUDI2_EVENT_NIC0_QM0 ... GAUDI2_EVENT_NIC11_QM1:
- error_count = gaudi2_handle_qman_err(hdev, event_type);
+ error_count = gaudi2_handle_qman_err(hdev, event_type, &event_mask);
event_mask |= HL_NOTIFIER_EVENT_USER_ENGINE_ERR;
break;
--
2.25.1
next prev parent reply other threads:[~2023-01-19 10:34 UTC|newest]
Thread overview: 10+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-01-19 10:33 [PATCH 01/10] habanalabs: update device status sysfs documentation Oded Gabbay
2023-01-19 10:33 ` [PATCH 02/10] habanalabs/gaudi2: print page fault axi transaction id Oded Gabbay
2023-01-19 10:33 ` [PATCH 03/10] habanalabs: block soft-reset on an unusable device Oded Gabbay
2023-01-19 10:33 ` Oded Gabbay [this message]
2023-01-19 10:33 ` [PATCH 05/10] habanalabs: refactor user interrupt type Oded Gabbay
2023-01-19 10:33 ` [PATCH 06/10] habanalabs: optimize command submission completion timestamp Oded Gabbay
2023-01-19 10:33 ` [PATCH 07/10] habanalabs: enhance info printed on FW load errors Oded Gabbay
2023-01-19 10:33 ` [PATCH 08/10] habanalabs: run error handling if scrub_device_mem fails after reset Oded Gabbay
2023-01-19 10:33 ` [PATCH 09/10] habanalabs: clear in_compute_reset when escalating to hard reset Oded Gabbay
2023-01-19 10:33 ` [PATCH 10/10] habanalabs/gaudi2: unsecure tpc kernel_config registers Oded Gabbay
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20230119103339.718430-4-ogabbay@kernel.org \
--to=ogabbay@kernel.org \
--cc=dliberman@habana.ai \
--cc=linux-kernel@vger.kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox
all inboxes | Powered by JetHome®